diff options
Diffstat (limited to 'tools')
831 files changed, 46040 insertions, 17141 deletions
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 1f6d904c6481..798e60b5454b 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -434,6 +434,7 @@ #define X86_FEATURE_SEV_ES (19*32+ 3) /* AMD Secure Encrypted Virtualization - Encrypted State */ #define X86_FEATURE_V_TSC_AUX (19*32+ 9) /* "" Virtual TSC_AUX */ #define X86_FEATURE_SME_COHERENT (19*32+10) /* "" AMD hardware-enforced cache coherency */ +#define X86_FEATURE_DEBUG_SWAP (19*32+14) /* AMD SEV-ES full debug state swap support */ /* AMD-defined Extended Feature 2 EAX, CPUID level 0x80000021 (EAX), word 20 */ #define X86_FEATURE_NO_NESTED_DATA_BP (20*32+ 0) /* "" No Nested Data Breakpoints */ diff --git a/tools/arch/x86/include/asm/irq_vectors.h b/tools/arch/x86/include/asm/irq_vectors.h index 43dcb9284208..3a19904c2db6 100644 --- a/tools/arch/x86/include/asm/irq_vectors.h +++ b/tools/arch/x86/include/asm/irq_vectors.h @@ -35,13 +35,6 @@ */ #define FIRST_EXTERNAL_VECTOR 0x20 -/* - * Reserve the lowest usable vector (and hence lowest priority) 0x20 for - * triggering cleanup after irq migration. 0x21-0x2f will still be used - * for device interrupts. - */ -#define IRQ_MOVE_CLEANUP_VECTOR FIRST_EXTERNAL_VECTOR - #define IA32_SYSCALL_VECTOR 0x80 /* diff --git a/tools/arch/x86/include/uapi/asm/unistd_32.h b/tools/arch/x86/include/uapi/asm/unistd_32.h index bc48a4dabe5d..4798f9d18fe8 100644 --- a/tools/arch/x86/include/uapi/asm/unistd_32.h +++ b/tools/arch/x86/include/uapi/asm/unistd_32.h @@ -26,3 +26,6 @@ #ifndef __NR_setns #define __NR_setns 346 #endif +#ifdef __NR_seccomp +#define __NR_seccomp 354 +#endif diff --git a/tools/arch/x86/include/uapi/asm/unistd_64.h b/tools/arch/x86/include/uapi/asm/unistd_64.h index f70d2cada256..d0f2043d7132 100644 --- a/tools/arch/x86/include/uapi/asm/unistd_64.h +++ b/tools/arch/x86/include/uapi/asm/unistd_64.h @@ -26,3 +26,6 @@ #ifndef __NR_getcpu #define __NR_getcpu 309 #endif +#ifndef __NR_seccomp +#define __NR_seccomp 317 +#endif diff --git a/tools/bpf/bpftool/Documentation/bpftool-gen.rst b/tools/bpf/bpftool/Documentation/bpftool-gen.rst index 68454ef28f58..5006e724d1bc 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-gen.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-gen.rst @@ -260,9 +260,9 @@ EXAMPLES This is example BPF application with two BPF programs and a mix of BPF maps and global variables. Source code is split across two source code files. -**$ clang -target bpf -g example1.bpf.c -o example1.bpf.o** +**$ clang --target=bpf -g example1.bpf.c -o example1.bpf.o** -**$ clang -target bpf -g example2.bpf.c -o example2.bpf.o** +**$ clang --target=bpf -g example2.bpf.c -o example2.bpf.o** **$ bpftool gen object example.bpf.o example1.bpf.o example2.bpf.o** diff --git a/tools/bpf/bpftool/Documentation/bpftool-net.rst b/tools/bpf/bpftool/Documentation/bpftool-net.rst index f4e0a516335a..5e2abd3de5ab 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-net.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-net.rst @@ -4,7 +4,7 @@ bpftool-net ================ ------------------------------------------------------------------------------- -tool for inspection of netdev/tc related bpf prog attachments +tool for inspection of networking related bpf prog attachments ------------------------------------------------------------------------------- :Manual section: 8 @@ -37,10 +37,13 @@ DESCRIPTION **bpftool net { show | list }** [ **dev** *NAME* ] List bpf program attachments in the kernel networking subsystem. - Currently, only device driver xdp attachments and tc filter - classification/action attachments are implemented, i.e., for - program types **BPF_PROG_TYPE_SCHED_CLS**, - **BPF_PROG_TYPE_SCHED_ACT** and **BPF_PROG_TYPE_XDP**. + Currently, device driver xdp attachments, tcx and old-style tc + classifier/action attachments, flow_dissector as well as netfilter + attachments are implemented, i.e., for + program types **BPF_PROG_TYPE_XDP**, **BPF_PROG_TYPE_SCHED_CLS**, + **BPF_PROG_TYPE_SCHED_ACT**, **BPF_PROG_TYPE_FLOW_DISSECTOR**, + **BPF_PROG_TYPE_NETFILTER**. + For programs attached to a particular cgroup, e.g., **BPF_PROG_TYPE_CGROUP_SKB**, **BPF_PROG_TYPE_CGROUP_SOCK**, **BPF_PROG_TYPE_SOCK_OPS** and **BPF_PROG_TYPE_CGROUP_SOCK_ADDR**, @@ -49,12 +52,13 @@ DESCRIPTION bpf programs, users should consult other tools, e.g., iproute2. The current output will start with all xdp program attachments, followed by - all tc class/qdisc bpf program attachments. Both xdp programs and - tc programs are ordered based on ifindex number. If multiple bpf - programs attached to the same networking device through **tc filter**, - the order will be first all bpf programs attached to tc classes, then - all bpf programs attached to non clsact qdiscs, and finally all - bpf programs attached to root and clsact qdisc. + all tcx, then tc class/qdisc bpf program attachments, then flow_dissector + and finally netfilter programs. Both xdp programs and tcx/tc programs are + ordered based on ifindex number. If multiple bpf programs attached + to the same networking device through **tc**, the order will be first + all bpf programs attached to tcx, then tc classes, then all bpf programs + attached to non clsact qdiscs, and finally all bpf programs attached + to root and clsact qdisc. **bpftool** **net attach** *ATTACH_TYPE* *PROG* **dev** *NAME* [ **overwrite** ] Attach bpf program *PROG* to network interface *NAME* with diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index 681fbcc5ed50..e9154ace80ff 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -216,7 +216,7 @@ $(OUTPUT)%.bpf.o: skeleton/%.bpf.c $(OUTPUT)vmlinux.h $(LIBBPF_BOOTSTRAP) -I$(srctree)/tools/include/uapi/ \ -I$(LIBBPF_BOOTSTRAP_INCLUDE) \ -g -O2 -Wall -fno-stack-protector \ - -target bpf -c $< -o $@ + --target=bpf -c $< -o $@ $(Q)$(LLVM_STRIP) -g $@ $(OUTPUT)%.skel.h: $(OUTPUT)%.bpf.o $(BPFTOOL_BOOTSTRAP) diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c index 294de231db99..1b7f69714604 100644 --- a/tools/bpf/bpftool/btf_dumper.c +++ b/tools/bpf/bpftool/btf_dumper.c @@ -835,7 +835,7 @@ static void dotlabel_puts(const char *s) case '|': case ' ': putchar('\\'); - /* fallthrough */ + fallthrough; default: putchar(*s); } diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c index 0675d6a46413..edda4fc2c4d0 100644 --- a/tools/bpf/bpftool/feature.c +++ b/tools/bpf/bpftool/feature.c @@ -757,7 +757,7 @@ probe_helpers_for_progtype(enum bpf_prog_type prog_type, case BPF_FUNC_probe_write_user: if (!full_mode) continue; - /* fallthrough */ + fallthrough; default: probe_res |= probe_helper_for_progtype(prog_type, supported_type, define_prefix, id, prog_type_str, diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c index 2d786072ed0d..2e5c231e08ac 100644 --- a/tools/bpf/bpftool/link.c +++ b/tools/bpf/bpftool/link.c @@ -5,6 +5,7 @@ #include <linux/err.h> #include <linux/netfilter.h> #include <linux/netfilter_arp.h> +#include <linux/perf_event.h> #include <net/if.h> #include <stdio.h> #include <unistd.h> @@ -14,8 +15,78 @@ #include "json_writer.h" #include "main.h" +#include "xlated_dumper.h" + +#define PERF_HW_CACHE_LEN 128 static struct hashmap *link_table; +static struct dump_data dd; + +static const char *perf_type_name[PERF_TYPE_MAX] = { + [PERF_TYPE_HARDWARE] = "hardware", + [PERF_TYPE_SOFTWARE] = "software", + [PERF_TYPE_TRACEPOINT] = "tracepoint", + [PERF_TYPE_HW_CACHE] = "hw-cache", + [PERF_TYPE_RAW] = "raw", + [PERF_TYPE_BREAKPOINT] = "breakpoint", +}; + +const char *event_symbols_hw[PERF_COUNT_HW_MAX] = { + [PERF_COUNT_HW_CPU_CYCLES] = "cpu-cycles", + [PERF_COUNT_HW_INSTRUCTIONS] = "instructions", + [PERF_COUNT_HW_CACHE_REFERENCES] = "cache-references", + [PERF_COUNT_HW_CACHE_MISSES] = "cache-misses", + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = "branch-instructions", + [PERF_COUNT_HW_BRANCH_MISSES] = "branch-misses", + [PERF_COUNT_HW_BUS_CYCLES] = "bus-cycles", + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = "stalled-cycles-frontend", + [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = "stalled-cycles-backend", + [PERF_COUNT_HW_REF_CPU_CYCLES] = "ref-cycles", +}; + +const char *event_symbols_sw[PERF_COUNT_SW_MAX] = { + [PERF_COUNT_SW_CPU_CLOCK] = "cpu-clock", + [PERF_COUNT_SW_TASK_CLOCK] = "task-clock", + [PERF_COUNT_SW_PAGE_FAULTS] = "page-faults", + [PERF_COUNT_SW_CONTEXT_SWITCHES] = "context-switches", + [PERF_COUNT_SW_CPU_MIGRATIONS] = "cpu-migrations", + [PERF_COUNT_SW_PAGE_FAULTS_MIN] = "minor-faults", + [PERF_COUNT_SW_PAGE_FAULTS_MAJ] = "major-faults", + [PERF_COUNT_SW_ALIGNMENT_FAULTS] = "alignment-faults", + [PERF_COUNT_SW_EMULATION_FAULTS] = "emulation-faults", + [PERF_COUNT_SW_DUMMY] = "dummy", + [PERF_COUNT_SW_BPF_OUTPUT] = "bpf-output", + [PERF_COUNT_SW_CGROUP_SWITCHES] = "cgroup-switches", +}; + +const char *evsel__hw_cache[PERF_COUNT_HW_CACHE_MAX] = { + [PERF_COUNT_HW_CACHE_L1D] = "L1-dcache", + [PERF_COUNT_HW_CACHE_L1I] = "L1-icache", + [PERF_COUNT_HW_CACHE_LL] = "LLC", + [PERF_COUNT_HW_CACHE_DTLB] = "dTLB", + [PERF_COUNT_HW_CACHE_ITLB] = "iTLB", + [PERF_COUNT_HW_CACHE_BPU] = "branch", + [PERF_COUNT_HW_CACHE_NODE] = "node", +}; + +const char *evsel__hw_cache_op[PERF_COUNT_HW_CACHE_OP_MAX] = { + [PERF_COUNT_HW_CACHE_OP_READ] = "load", + [PERF_COUNT_HW_CACHE_OP_WRITE] = "store", + [PERF_COUNT_HW_CACHE_OP_PREFETCH] = "prefetch", +}; + +const char *evsel__hw_cache_result[PERF_COUNT_HW_CACHE_RESULT_MAX] = { + [PERF_COUNT_HW_CACHE_RESULT_ACCESS] = "refs", + [PERF_COUNT_HW_CACHE_RESULT_MISS] = "misses", +}; + +#define perf_event_name(array, id) ({ \ + const char *event_str = NULL; \ + \ + if ((id) < ARRAY_SIZE(array)) \ + event_str = array[id]; \ + event_str; \ +}) static int link_parse_fd(int *argc, char ***argv) { @@ -79,6 +150,18 @@ static void show_link_attach_type_json(__u32 attach_type, json_writer_t *wtr) jsonw_uint_field(wtr, "attach_type", attach_type); } +static void show_link_ifindex_json(__u32 ifindex, json_writer_t *wtr) +{ + char devname[IF_NAMESIZE] = "(unknown)"; + + if (ifindex) + if_indextoname(ifindex, devname); + else + snprintf(devname, sizeof(devname), "(detached)"); + jsonw_string_field(wtr, "devname", devname); + jsonw_uint_field(wtr, "ifindex", ifindex); +} + static bool is_iter_map_target(const char *target_name) { return strcmp(target_name, "bpf_map_elem") == 0 || @@ -166,6 +249,154 @@ static int get_prog_info(int prog_id, struct bpf_prog_info *info) return err; } +static int cmp_u64(const void *A, const void *B) +{ + const __u64 *a = A, *b = B; + + return *a - *b; +} + +static void +show_kprobe_multi_json(struct bpf_link_info *info, json_writer_t *wtr) +{ + __u32 i, j = 0; + __u64 *addrs; + + jsonw_bool_field(json_wtr, "retprobe", + info->kprobe_multi.flags & BPF_F_KPROBE_MULTI_RETURN); + jsonw_uint_field(json_wtr, "func_cnt", info->kprobe_multi.count); + jsonw_name(json_wtr, "funcs"); + jsonw_start_array(json_wtr); + addrs = u64_to_ptr(info->kprobe_multi.addrs); + qsort(addrs, info->kprobe_multi.count, sizeof(addrs[0]), cmp_u64); + + /* Load it once for all. */ + if (!dd.sym_count) + kernel_syms_load(&dd); + for (i = 0; i < dd.sym_count; i++) { + if (dd.sym_mapping[i].address != addrs[j]) + continue; + jsonw_start_object(json_wtr); + jsonw_uint_field(json_wtr, "addr", dd.sym_mapping[i].address); + jsonw_string_field(json_wtr, "func", dd.sym_mapping[i].name); + /* Print null if it is vmlinux */ + if (dd.sym_mapping[i].module[0] == '\0') { + jsonw_name(json_wtr, "module"); + jsonw_null(json_wtr); + } else { + jsonw_string_field(json_wtr, "module", dd.sym_mapping[i].module); + } + jsonw_end_object(json_wtr); + if (j++ == info->kprobe_multi.count) + break; + } + jsonw_end_array(json_wtr); +} + +static void +show_perf_event_kprobe_json(struct bpf_link_info *info, json_writer_t *wtr) +{ + jsonw_bool_field(wtr, "retprobe", info->perf_event.type == BPF_PERF_EVENT_KRETPROBE); + jsonw_uint_field(wtr, "addr", info->perf_event.kprobe.addr); + jsonw_string_field(wtr, "func", + u64_to_ptr(info->perf_event.kprobe.func_name)); + jsonw_uint_field(wtr, "offset", info->perf_event.kprobe.offset); +} + +static void +show_perf_event_uprobe_json(struct bpf_link_info *info, json_writer_t *wtr) +{ + jsonw_bool_field(wtr, "retprobe", info->perf_event.type == BPF_PERF_EVENT_URETPROBE); + jsonw_string_field(wtr, "file", + u64_to_ptr(info->perf_event.uprobe.file_name)); + jsonw_uint_field(wtr, "offset", info->perf_event.uprobe.offset); +} + +static void +show_perf_event_tracepoint_json(struct bpf_link_info *info, json_writer_t *wtr) +{ + jsonw_string_field(wtr, "tracepoint", + u64_to_ptr(info->perf_event.tracepoint.tp_name)); +} + +static char *perf_config_hw_cache_str(__u64 config) +{ + const char *hw_cache, *result, *op; + char *str = malloc(PERF_HW_CACHE_LEN); + + if (!str) { + p_err("mem alloc failed"); + return NULL; + } + + hw_cache = perf_event_name(evsel__hw_cache, config & 0xff); + if (hw_cache) + snprintf(str, PERF_HW_CACHE_LEN, "%s-", hw_cache); + else + snprintf(str, PERF_HW_CACHE_LEN, "%lld-", config & 0xff); + + op = perf_event_name(evsel__hw_cache_op, (config >> 8) & 0xff); + if (op) + snprintf(str + strlen(str), PERF_HW_CACHE_LEN - strlen(str), + "%s-", op); + else + snprintf(str + strlen(str), PERF_HW_CACHE_LEN - strlen(str), + "%lld-", (config >> 8) & 0xff); + + result = perf_event_name(evsel__hw_cache_result, config >> 16); + if (result) + snprintf(str + strlen(str), PERF_HW_CACHE_LEN - strlen(str), + "%s", result); + else + snprintf(str + strlen(str), PERF_HW_CACHE_LEN - strlen(str), + "%lld", config >> 16); + return str; +} + +static const char *perf_config_str(__u32 type, __u64 config) +{ + const char *perf_config; + + switch (type) { + case PERF_TYPE_HARDWARE: + perf_config = perf_event_name(event_symbols_hw, config); + break; + case PERF_TYPE_SOFTWARE: + perf_config = perf_event_name(event_symbols_sw, config); + break; + case PERF_TYPE_HW_CACHE: + perf_config = perf_config_hw_cache_str(config); + break; + default: + perf_config = NULL; + break; + } + return perf_config; +} + +static void +show_perf_event_event_json(struct bpf_link_info *info, json_writer_t *wtr) +{ + __u64 config = info->perf_event.event.config; + __u32 type = info->perf_event.event.type; + const char *perf_type, *perf_config; + + perf_type = perf_event_name(perf_type_name, type); + if (perf_type) + jsonw_string_field(wtr, "event_type", perf_type); + else + jsonw_uint_field(wtr, "event_type", type); + + perf_config = perf_config_str(type, config); + if (perf_config) + jsonw_string_field(wtr, "event_config", perf_config); + else + jsonw_uint_field(wtr, "event_config", config); + + if (type == PERF_TYPE_HW_CACHE && perf_config) + free((void *)perf_config); +} + static int show_link_close_json(int fd, struct bpf_link_info *info) { struct bpf_prog_info prog_info; @@ -214,10 +445,40 @@ static int show_link_close_json(int fd, struct bpf_link_info *info) case BPF_LINK_TYPE_NETFILTER: netfilter_dump_json(info, json_wtr); break; + case BPF_LINK_TYPE_TCX: + show_link_ifindex_json(info->tcx.ifindex, json_wtr); + show_link_attach_type_json(info->tcx.attach_type, json_wtr); + break; + case BPF_LINK_TYPE_XDP: + show_link_ifindex_json(info->xdp.ifindex, json_wtr); + break; case BPF_LINK_TYPE_STRUCT_OPS: jsonw_uint_field(json_wtr, "map_id", info->struct_ops.map_id); break; + case BPF_LINK_TYPE_KPROBE_MULTI: + show_kprobe_multi_json(info, json_wtr); + break; + case BPF_LINK_TYPE_PERF_EVENT: + switch (info->perf_event.type) { + case BPF_PERF_EVENT_EVENT: + show_perf_event_event_json(info, json_wtr); + break; + case BPF_PERF_EVENT_TRACEPOINT: + show_perf_event_tracepoint_json(info, json_wtr); + break; + case BPF_PERF_EVENT_KPROBE: + case BPF_PERF_EVENT_KRETPROBE: + show_perf_event_kprobe_json(info, json_wtr); + break; + case BPF_PERF_EVENT_UPROBE: + case BPF_PERF_EVENT_URETPROBE: + show_perf_event_uprobe_json(info, json_wtr); + break; + default: + break; + } + break; default: break; } @@ -267,6 +528,22 @@ static void show_link_attach_type_plain(__u32 attach_type) printf("attach_type %u ", attach_type); } +static void show_link_ifindex_plain(__u32 ifindex) +{ + char devname[IF_NAMESIZE * 2] = "(unknown)"; + char tmpname[IF_NAMESIZE]; + char *ret = NULL; + + if (ifindex) + ret = if_indextoname(ifindex, tmpname); + else + snprintf(devname, sizeof(devname), "(detached)"); + if (ret) + snprintf(devname, sizeof(devname), "%s(%d)", + tmpname, ifindex); + printf("ifindex %s ", devname); +} + static void show_iter_plain(struct bpf_link_info *info) { const char *target_name = u64_to_ptr(info->iter.target_name); @@ -351,6 +628,113 @@ void netfilter_dump_plain(const struct bpf_link_info *info) printf(" flags 0x%x", info->netfilter.flags); } +static void show_kprobe_multi_plain(struct bpf_link_info *info) +{ + __u32 i, j = 0; + __u64 *addrs; + + if (!info->kprobe_multi.count) + return; + + if (info->kprobe_multi.flags & BPF_F_KPROBE_MULTI_RETURN) + printf("\n\tkretprobe.multi "); + else + printf("\n\tkprobe.multi "); + printf("func_cnt %u ", info->kprobe_multi.count); + addrs = (__u64 *)u64_to_ptr(info->kprobe_multi.addrs); + qsort(addrs, info->kprobe_multi.count, sizeof(__u64), cmp_u64); + + /* Load it once for all. */ + if (!dd.sym_count) + kernel_syms_load(&dd); + if (!dd.sym_count) + return; + + printf("\n\t%-16s %s", "addr", "func [module]"); + for (i = 0; i < dd.sym_count; i++) { + if (dd.sym_mapping[i].address != addrs[j]) + continue; + printf("\n\t%016lx %s", + dd.sym_mapping[i].address, dd.sym_mapping[i].name); + if (dd.sym_mapping[i].module[0] != '\0') + printf(" [%s] ", dd.sym_mapping[i].module); + else + printf(" "); + + if (j++ == info->kprobe_multi.count) + break; + } +} + +static void show_perf_event_kprobe_plain(struct bpf_link_info *info) +{ + const char *buf; + + buf = u64_to_ptr(info->perf_event.kprobe.func_name); + if (buf[0] == '\0' && !info->perf_event.kprobe.addr) + return; + + if (info->perf_event.type == BPF_PERF_EVENT_KRETPROBE) + printf("\n\tkretprobe "); + else + printf("\n\tkprobe "); + if (info->perf_event.kprobe.addr) + printf("%llx ", info->perf_event.kprobe.addr); + printf("%s", buf); + if (info->perf_event.kprobe.offset) + printf("+%#x", info->perf_event.kprobe.offset); + printf(" "); +} + +static void show_perf_event_uprobe_plain(struct bpf_link_info *info) +{ + const char *buf; + + buf = u64_to_ptr(info->perf_event.uprobe.file_name); + if (buf[0] == '\0') + return; + + if (info->perf_event.type == BPF_PERF_EVENT_URETPROBE) + printf("\n\turetprobe "); + else + printf("\n\tuprobe "); + printf("%s+%#x ", buf, info->perf_event.uprobe.offset); +} + +static void show_perf_event_tracepoint_plain(struct bpf_link_info *info) +{ + const char *buf; + + buf = u64_to_ptr(info->perf_event.tracepoint.tp_name); + if (buf[0] == '\0') + return; + + printf("\n\ttracepoint %s ", buf); +} + +static void show_perf_event_event_plain(struct bpf_link_info *info) +{ + __u64 config = info->perf_event.event.config; + __u32 type = info->perf_event.event.type; + const char *perf_type, *perf_config; + + printf("\n\tevent "); + perf_type = perf_event_name(perf_type_name, type); + if (perf_type) + printf("%s:", perf_type); + else + printf("%u :", type); + + perf_config = perf_config_str(type, config); + if (perf_config) + printf("%s ", perf_config); + else + printf("%llu ", config); + + if (type == PERF_TYPE_HW_CACHE && perf_config) + free((void *)perf_config); +} + static int show_link_close_plain(int fd, struct bpf_link_info *info) { struct bpf_prog_info prog_info; @@ -396,6 +780,38 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info) case BPF_LINK_TYPE_NETFILTER: netfilter_dump_plain(info); break; + case BPF_LINK_TYPE_TCX: + printf("\n\t"); + show_link_ifindex_plain(info->tcx.ifindex); + show_link_attach_type_plain(info->tcx.attach_type); + break; + case BPF_LINK_TYPE_XDP: + printf("\n\t"); + show_link_ifindex_plain(info->xdp.ifindex); + break; + case BPF_LINK_TYPE_KPROBE_MULTI: + show_kprobe_multi_plain(info); + break; + case BPF_LINK_TYPE_PERF_EVENT: + switch (info->perf_event.type) { + case BPF_PERF_EVENT_EVENT: + show_perf_event_event_plain(info); + break; + case BPF_PERF_EVENT_TRACEPOINT: + show_perf_event_tracepoint_plain(info); + break; + case BPF_PERF_EVENT_KPROBE: + case BPF_PERF_EVENT_KRETPROBE: + show_perf_event_kprobe_plain(info); + break; + case BPF_PERF_EVENT_UPROBE: + case BPF_PERF_EVENT_URETPROBE: + show_perf_event_uprobe_plain(info); + break; + default: + break; + } + break; default: break; } @@ -417,10 +833,13 @@ static int do_show_link(int fd) { struct bpf_link_info info; __u32 len = sizeof(info); - char buf[256]; + __u64 *addrs = NULL; + char buf[PATH_MAX]; + int count; int err; memset(&info, 0, sizeof(info)); + buf[0] = '\0'; again: err = bpf_link_get_info_by_fd(fd, &info, &len); if (err) { @@ -431,22 +850,67 @@ again: } if (info.type == BPF_LINK_TYPE_RAW_TRACEPOINT && !info.raw_tracepoint.tp_name) { - info.raw_tracepoint.tp_name = (unsigned long)&buf; + info.raw_tracepoint.tp_name = ptr_to_u64(&buf); info.raw_tracepoint.tp_name_len = sizeof(buf); goto again; } if (info.type == BPF_LINK_TYPE_ITER && !info.iter.target_name) { - info.iter.target_name = (unsigned long)&buf; + info.iter.target_name = ptr_to_u64(&buf); info.iter.target_name_len = sizeof(buf); goto again; } + if (info.type == BPF_LINK_TYPE_KPROBE_MULTI && + !info.kprobe_multi.addrs) { + count = info.kprobe_multi.count; + if (count) { + addrs = calloc(count, sizeof(__u64)); + if (!addrs) { + p_err("mem alloc failed"); + close(fd); + return -ENOMEM; + } + info.kprobe_multi.addrs = ptr_to_u64(addrs); + goto again; + } + } + if (info.type == BPF_LINK_TYPE_PERF_EVENT) { + switch (info.perf_event.type) { + case BPF_PERF_EVENT_TRACEPOINT: + if (!info.perf_event.tracepoint.tp_name) { + info.perf_event.tracepoint.tp_name = ptr_to_u64(&buf); + info.perf_event.tracepoint.name_len = sizeof(buf); + goto again; + } + break; + case BPF_PERF_EVENT_KPROBE: + case BPF_PERF_EVENT_KRETPROBE: + if (!info.perf_event.kprobe.func_name) { + info.perf_event.kprobe.func_name = ptr_to_u64(&buf); + info.perf_event.kprobe.name_len = sizeof(buf); + goto again; + } + break; + case BPF_PERF_EVENT_UPROBE: + case BPF_PERF_EVENT_URETPROBE: + if (!info.perf_event.uprobe.file_name) { + info.perf_event.uprobe.file_name = ptr_to_u64(&buf); + info.perf_event.uprobe.name_len = sizeof(buf); + goto again; + } + break; + default: + break; + } + } if (json_output) show_link_close_json(fd, &info); else show_link_close_plain(fd, &info); + if (addrs) + free(addrs); close(fd); return 0; } @@ -471,7 +935,8 @@ static int do_show(int argc, char **argv) fd = link_parse_fd(&argc, &argv); if (fd < 0) return fd; - return do_show_link(fd); + do_show_link(fd); + goto out; } if (argc) @@ -510,6 +975,9 @@ static int do_show(int argc, char **argv) if (show_pinned) delete_pinned_obj_table(link_table); +out: + if (dd.sym_count) + kernel_syms_destroy(&dd); return errno == ENOENT ? 0 : -1; } diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c index 26a49965bf71..66a8ce8ae012 100644 --- a/tools/bpf/bpftool/net.c +++ b/tools/bpf/bpftool/net.c @@ -76,6 +76,11 @@ static const char * const attach_type_strings[] = { [NET_ATTACH_TYPE_XDP_OFFLOAD] = "xdpoffload", }; +static const char * const attach_loc_strings[] = { + [BPF_TCX_INGRESS] = "tcx/ingress", + [BPF_TCX_EGRESS] = "tcx/egress", +}; + const size_t net_attach_type_size = ARRAY_SIZE(attach_type_strings); static enum net_attach_type parse_attach_type(const char *str) @@ -422,8 +427,89 @@ static int dump_filter_nlmsg(void *cookie, void *msg, struct nlattr **tb) filter_info->devname, filter_info->ifindex); } -static int show_dev_tc_bpf(int sock, unsigned int nl_pid, - struct ip_devname_ifindex *dev) +static int __show_dev_tc_bpf_name(__u32 id, char *name, size_t len) +{ + struct bpf_prog_info info = {}; + __u32 ilen = sizeof(info); + int fd, ret; + + fd = bpf_prog_get_fd_by_id(id); + if (fd < 0) + return fd; + ret = bpf_obj_get_info_by_fd(fd, &info, &ilen); + if (ret < 0) + goto out; + ret = -ENOENT; + if (info.name[0]) { + get_prog_full_name(&info, fd, name, len); + ret = 0; + } +out: + close(fd); + return ret; +} + +static void __show_dev_tc_bpf(const struct ip_devname_ifindex *dev, + const enum bpf_attach_type loc) +{ + __u32 prog_flags[64] = {}, link_flags[64] = {}, i, j; + __u32 prog_ids[64] = {}, link_ids[64] = {}; + LIBBPF_OPTS(bpf_prog_query_opts, optq); + char prog_name[MAX_PROG_FULL_NAME]; + int ret; + + optq.prog_ids = prog_ids; + optq.prog_attach_flags = prog_flags; + optq.link_ids = link_ids; + optq.link_attach_flags = link_flags; + optq.count = ARRAY_SIZE(prog_ids); + + ret = bpf_prog_query_opts(dev->ifindex, loc, &optq); + if (ret) + return; + for (i = 0; i < optq.count; i++) { + NET_START_OBJECT; + NET_DUMP_STR("devname", "%s", dev->devname); + NET_DUMP_UINT("ifindex", "(%u)", dev->ifindex); + NET_DUMP_STR("kind", " %s", attach_loc_strings[loc]); + ret = __show_dev_tc_bpf_name(prog_ids[i], prog_name, + sizeof(prog_name)); + if (!ret) + NET_DUMP_STR("name", " %s", prog_name); + NET_DUMP_UINT("prog_id", " prog_id %u ", prog_ids[i]); + if (prog_flags[i] || json_output) { + NET_START_ARRAY("prog_flags", "%s "); + for (j = 0; prog_flags[i] && j < 32; j++) { + if (!(prog_flags[i] & (1 << j))) + continue; + NET_DUMP_UINT_ONLY(1 << j); + } + NET_END_ARRAY(""); + } + if (link_ids[i] || json_output) { + NET_DUMP_UINT("link_id", "link_id %u ", link_ids[i]); + if (link_flags[i] || json_output) { + NET_START_ARRAY("link_flags", "%s "); + for (j = 0; link_flags[i] && j < 32; j++) { + if (!(link_flags[i] & (1 << j))) + continue; + NET_DUMP_UINT_ONLY(1 << j); + } + NET_END_ARRAY(""); + } + } + NET_END_OBJECT_FINAL; + } +} + +static void show_dev_tc_bpf(struct ip_devname_ifindex *dev) +{ + __show_dev_tc_bpf(dev, BPF_TCX_INGRESS); + __show_dev_tc_bpf(dev, BPF_TCX_EGRESS); +} + +static int show_dev_tc_bpf_classic(int sock, unsigned int nl_pid, + struct ip_devname_ifindex *dev) { struct bpf_filter_t filter_info; struct bpf_tcinfo_t tcinfo; @@ -790,8 +876,9 @@ static int do_show(int argc, char **argv) if (!ret) { NET_START_ARRAY("tc", "%s:\n"); for (i = 0; i < dev_array.used_len; i++) { - ret = show_dev_tc_bpf(sock, nl_pid, - &dev_array.devices[i]); + show_dev_tc_bpf(&dev_array.devices[i]); + ret = show_dev_tc_bpf_classic(sock, nl_pid, + &dev_array.devices[i]); if (ret) break; } @@ -839,7 +926,8 @@ static int do_help(int argc, char **argv) " ATTACH_TYPE := { xdp | xdpgeneric | xdpdrv | xdpoffload }\n" " " HELP_SPEC_OPTIONS " }\n" "\n" - "Note: Only xdp and tc attachments are supported now.\n" + "Note: Only xdp, tcx, tc, flow_dissector and netfilter attachments\n" + " are currently supported.\n" " For progs attached to cgroups, use \"bpftool cgroup\"\n" " to dump program attachments. For program types\n" " sk_{filter,skb,msg,reuseport} and lwt/seg6, please\n" diff --git a/tools/bpf/bpftool/netlink_dumper.h b/tools/bpf/bpftool/netlink_dumper.h index 774af6c62ef5..96318106fb49 100644 --- a/tools/bpf/bpftool/netlink_dumper.h +++ b/tools/bpf/bpftool/netlink_dumper.h @@ -76,6 +76,14 @@ fprintf(stdout, fmt_str, val); \ } +#define NET_DUMP_UINT_ONLY(str) \ +{ \ + if (json_output) \ + jsonw_uint(json_wtr, str); \ + else \ + fprintf(stdout, "%u ", str); \ +} + #define NET_DUMP_STR(name, fmt_str, str) \ { \ if (json_output) \ diff --git a/tools/bpf/bpftool/perf.c b/tools/bpf/bpftool/perf.c index 91743445e4c7..80de2874dabe 100644 --- a/tools/bpf/bpftool/perf.c +++ b/tools/bpf/bpftool/perf.c @@ -236,7 +236,7 @@ static int do_help(int argc, char **argv) { fprintf(stderr, "Usage: %1$s %2$s { show | list }\n" - " %1$s %2$s help }\n" + " %1$s %2$s help\n" "\n" " " HELP_SPEC_OPTIONS " }\n" "", diff --git a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c index eb05ea53afb1..26004f0c5a6a 100644 --- a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c +++ b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c @@ -15,6 +15,19 @@ enum bpf_obj_type { BPF_OBJ_BTF, }; +struct bpf_perf_link___local { + struct bpf_link link; + struct file *perf_file; +} __attribute__((preserve_access_index)); + +struct perf_event___local { + u64 bpf_cookie; +} __attribute__((preserve_access_index)); + +enum bpf_link_type___local { + BPF_LINK_TYPE_PERF_EVENT___local = 7, +}; + extern const void bpf_link_fops __ksym; extern const void bpf_map_fops __ksym; extern const void bpf_prog_fops __ksym; @@ -41,10 +54,10 @@ static __always_inline __u32 get_obj_id(void *ent, enum bpf_obj_type type) /* could be used only with BPF_LINK_TYPE_PERF_EVENT links */ static __u64 get_bpf_cookie(struct bpf_link *link) { - struct bpf_perf_link *perf_link; - struct perf_event *event; + struct bpf_perf_link___local *perf_link; + struct perf_event___local *event; - perf_link = container_of(link, struct bpf_perf_link, link); + perf_link = container_of(link, struct bpf_perf_link___local, link); event = BPF_CORE_READ(perf_link, perf_file, private_data); return BPF_CORE_READ(event, bpf_cookie); } @@ -84,10 +97,13 @@ int iter(struct bpf_iter__task_file *ctx) e.pid = task->tgid; e.id = get_obj_id(file->private_data, obj_type); - if (obj_type == BPF_OBJ_LINK) { + if (obj_type == BPF_OBJ_LINK && + bpf_core_enum_value_exists(enum bpf_link_type___local, + BPF_LINK_TYPE_PERF_EVENT___local)) { struct bpf_link *link = (struct bpf_link *) file->private_data; - if (BPF_CORE_READ(link, type) == BPF_LINK_TYPE_PERF_EVENT) { + if (link->type == bpf_core_enum_value(enum bpf_link_type___local, + BPF_LINK_TYPE_PERF_EVENT___local)) { e.has_bpf_cookie = true; e.bpf_cookie = get_bpf_cookie(link); } diff --git a/tools/bpf/bpftool/skeleton/profiler.bpf.c b/tools/bpf/bpftool/skeleton/profiler.bpf.c index ce5b65e07ab1..2f80edc682f1 100644 --- a/tools/bpf/bpftool/skeleton/profiler.bpf.c +++ b/tools/bpf/bpftool/skeleton/profiler.bpf.c @@ -4,6 +4,12 @@ #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> +struct bpf_perf_event_value___local { + __u64 counter; + __u64 enabled; + __u64 running; +} __attribute__((preserve_access_index)); + /* map of perf event fds, num_cpu * num_metric entries */ struct { __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); @@ -15,14 +21,14 @@ struct { struct { __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); __uint(key_size, sizeof(u32)); - __uint(value_size, sizeof(struct bpf_perf_event_value)); + __uint(value_size, sizeof(struct bpf_perf_event_value___local)); } fentry_readings SEC(".maps"); /* accumulated readings */ struct { __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); __uint(key_size, sizeof(u32)); - __uint(value_size, sizeof(struct bpf_perf_event_value)); + __uint(value_size, sizeof(struct bpf_perf_event_value___local)); } accum_readings SEC(".maps"); /* sample counts, one per cpu */ @@ -39,7 +45,7 @@ const volatile __u32 num_metric = 1; SEC("fentry/XXX") int BPF_PROG(fentry_XXX) { - struct bpf_perf_event_value *ptrs[MAX_NUM_MATRICS]; + struct bpf_perf_event_value___local *ptrs[MAX_NUM_MATRICS]; u32 key = bpf_get_smp_processor_id(); u32 i; @@ -53,10 +59,10 @@ int BPF_PROG(fentry_XXX) } for (i = 0; i < num_metric && i < MAX_NUM_MATRICS; i++) { - struct bpf_perf_event_value reading; + struct bpf_perf_event_value___local reading; int err; - err = bpf_perf_event_read_value(&events, key, &reading, + err = bpf_perf_event_read_value(&events, key, (void *)&reading, sizeof(reading)); if (err) return 0; @@ -68,14 +74,14 @@ int BPF_PROG(fentry_XXX) } static inline void -fexit_update_maps(u32 id, struct bpf_perf_event_value *after) +fexit_update_maps(u32 id, struct bpf_perf_event_value___local *after) { - struct bpf_perf_event_value *before, diff; + struct bpf_perf_event_value___local *before, diff; before = bpf_map_lookup_elem(&fentry_readings, &id); /* only account samples with a valid fentry_reading */ if (before && before->counter) { - struct bpf_perf_event_value *accum; + struct bpf_perf_event_value___local *accum; diff.counter = after->counter - before->counter; diff.enabled = after->enabled - before->enabled; @@ -93,7 +99,7 @@ fexit_update_maps(u32 id, struct bpf_perf_event_value *after) SEC("fexit/XXX") int BPF_PROG(fexit_XXX) { - struct bpf_perf_event_value readings[MAX_NUM_MATRICS]; + struct bpf_perf_event_value___local readings[MAX_NUM_MATRICS]; u32 cpu = bpf_get_smp_processor_id(); u32 i, zero = 0; int err; @@ -102,7 +108,8 @@ int BPF_PROG(fexit_XXX) /* read all events before updating the maps, to reduce error */ for (i = 0; i < num_metric && i < MAX_NUM_MATRICS; i++) { err = bpf_perf_event_read_value(&events, cpu + i * num_cpu, - readings + i, sizeof(*readings)); + (void *)(readings + i), + sizeof(*readings)); if (err) return 0; } diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c index da608e10c843..567f56dfd9f1 100644 --- a/tools/bpf/bpftool/xlated_dumper.c +++ b/tools/bpf/bpftool/xlated_dumper.c @@ -46,7 +46,11 @@ out: } dd->sym_mapping = tmp; sym = &dd->sym_mapping[dd->sym_count]; - if (sscanf(buff, "%p %*c %s", &address, sym->name) != 2) + + /* module is optional */ + sym->module[0] = '\0'; + /* trim the square brackets around the module name */ + if (sscanf(buff, "%p %*c %s [%[^]]s", &address, sym->name, sym->module) < 2) continue; sym->address = (unsigned long)address; if (!strcmp(sym->name, "__bpf_call_base")) { diff --git a/tools/bpf/bpftool/xlated_dumper.h b/tools/bpf/bpftool/xlated_dumper.h index 9a946377b0e6..db3ba0671501 100644 --- a/tools/bpf/bpftool/xlated_dumper.h +++ b/tools/bpf/bpftool/xlated_dumper.h @@ -5,12 +5,14 @@ #define __BPF_TOOL_XLATED_DUMPER_H #define SYM_MAX_NAME 256 +#define MODULE_MAX_NAME 64 struct bpf_prog_linfo; struct kernel_sym { unsigned long address; char name[SYM_MAX_NAME]; + char module[MODULE_MAX_NAME]; }; struct dump_data { diff --git a/tools/bpf/runqslower/Makefile b/tools/bpf/runqslower/Makefile index 47acf6936516..d8288936c912 100644 --- a/tools/bpf/runqslower/Makefile +++ b/tools/bpf/runqslower/Makefile @@ -62,7 +62,7 @@ $(OUTPUT)/%.skel.h: $(OUTPUT)/%.bpf.o | $(BPFTOOL) $(QUIET_GEN)$(BPFTOOL) gen skeleton $< > $@ $(OUTPUT)/%.bpf.o: %.bpf.c $(BPFOBJ) | $(OUTPUT) - $(QUIET_GEN)$(CLANG) -g -O2 -target bpf $(INCLUDES) \ + $(QUIET_GEN)$(CLANG) -g -O2 --target=bpf $(INCLUDES) \ -c $(filter %.c,$^) -o $@ && \ $(LLVM_STRIP) -g $@ diff --git a/tools/build/Makefile.build b/tools/build/Makefile.build index 89430338a3d9..fac42486a8cf 100644 --- a/tools/build/Makefile.build +++ b/tools/build/Makefile.build @@ -117,6 +117,16 @@ $(OUTPUT)%.s: %.c FORCE $(call rule_mkdir) $(call if_changed_dep,cc_s_c) +# bison and flex files are generated in the OUTPUT directory +# so it needs a separate rule to depend on them properly +$(OUTPUT)%-bison.o: $(OUTPUT)%-bison.c FORCE + $(call rule_mkdir) + $(call if_changed_dep,$(host)cc_o_c) + +$(OUTPUT)%-flex.o: $(OUTPUT)%-flex.c FORCE + $(call rule_mkdir) + $(call if_changed_dep,$(host)cc_o_c) + # Gather build data: # obj-y - list of build objects # subdir-y - list of directories to nest diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index 2cd6dbbee088..dad79ede4e0a 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -340,7 +340,7 @@ $(OUTPUT)test-jvmti-cmlr.bin: $(BUILD) $(OUTPUT)test-llvm.bin: - $(BUILDXX) -std=gnu++14 \ + $(BUILDXX) -std=gnu++17 \ -I$(shell $(LLVM_CONFIG) --includedir) \ -L$(shell $(LLVM_CONFIG) --libdir) \ $(shell $(LLVM_CONFIG) --libs Core BPF) \ @@ -348,17 +348,15 @@ $(OUTPUT)test-llvm.bin: > $(@:.bin=.make.output) 2>&1 $(OUTPUT)test-llvm-version.bin: - $(BUILDXX) -std=gnu++14 \ + $(BUILDXX) -std=gnu++17 \ -I$(shell $(LLVM_CONFIG) --includedir) \ > $(@:.bin=.make.output) 2>&1 $(OUTPUT)test-clang.bin: - $(BUILDXX) -std=gnu++14 \ + $(BUILDXX) -std=gnu++17 \ -I$(shell $(LLVM_CONFIG) --includedir) \ -L$(shell $(LLVM_CONFIG) --libdir) \ - -Wl,--start-group -lclangBasic -lclangDriver \ - -lclangFrontend -lclangEdit -lclangLex \ - -lclangAST -Wl,--end-group \ + -Wl,--start-group -lclang-cpp -Wl,--end-group \ $(shell $(LLVM_CONFIG) --libs Core option) \ $(shell $(LLVM_CONFIG) --system-libs) \ > $(@:.bin=.make.output) 2>&1 @@ -372,7 +370,7 @@ $(OUTPUT)test-libzstd.bin: $(BUILD) -lzstd $(OUTPUT)test-clang-bpf-co-re.bin: - $(CLANG) -S -g -target bpf -o - $(patsubst %.bin,%.c,$(@F)) | \ + $(CLANG) -S -g --target=bpf -o - $(patsubst %.bin,%.c,$(@F)) | \ grep BTF_KIND_VAR $(OUTPUT)test-file-handle.bin: diff --git a/tools/build/feature/test-clang.cpp b/tools/build/feature/test-clang.cpp deleted file mode 100644 index 7d87075cd1c5..000000000000 --- a/tools/build/feature/test-clang.cpp +++ /dev/null @@ -1,28 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include "clang/Basic/Version.h" -#if CLANG_VERSION_MAJOR < 8 -#include "clang/Basic/VirtualFileSystem.h" -#endif -#include "clang/Driver/Driver.h" -#include "clang/Frontend/TextDiagnosticPrinter.h" -#include "llvm/ADT/IntrusiveRefCntPtr.h" -#include "llvm/Support/ManagedStatic.h" -#if CLANG_VERSION_MAJOR >= 8 -#include "llvm/Support/VirtualFileSystem.h" -#endif -#include "llvm/Support/raw_ostream.h" - -using namespace clang; -using namespace clang::driver; - -int main() -{ - IntrusiveRefCntPtr<DiagnosticIDs> DiagID(new DiagnosticIDs()); - IntrusiveRefCntPtr<DiagnosticOptions> DiagOpts = new DiagnosticOptions(); - - DiagnosticsEngine Diags(DiagID, &*DiagOpts); - Driver TheDriver("test", "bpf-pc-linux", Diags); - - llvm::llvm_shutdown(); - return 0; -} diff --git a/tools/build/feature/test-cxx.cpp b/tools/build/feature/test-cxx.cpp deleted file mode 100644 index 396aaedd2418..000000000000 --- a/tools/build/feature/test-cxx.cpp +++ /dev/null @@ -1,16 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <iostream> -#include <memory> - -static void print_str(std::string s) -{ - std::cout << s << std::endl; -} - -int main() -{ - std::string s("Hello World!"); - print_str(std::move(s)); - std::cout << "|" << s << "|" << std::endl; - return 0; -} diff --git a/tools/build/feature/test-llvm-version.cpp b/tools/build/feature/test-llvm-version.cpp deleted file mode 100644 index 8a091625446a..000000000000 --- a/tools/build/feature/test-llvm-version.cpp +++ /dev/null @@ -1,12 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <cstdio> -#include "llvm/Config/llvm-config.h" - -#define NUM_VERSION (((LLVM_VERSION_MAJOR) << 16) + (LLVM_VERSION_MINOR << 8) + LLVM_VERSION_PATCH) -#define pass int main() {printf("%x\n", NUM_VERSION); return 0;} - -#if NUM_VERSION >= 0x030900 -pass -#else -# error This LLVM is not tested yet. -#endif diff --git a/tools/build/feature/test-llvm.cpp b/tools/build/feature/test-llvm.cpp deleted file mode 100644 index 88a3d1bdd9f6..000000000000 --- a/tools/build/feature/test-llvm.cpp +++ /dev/null @@ -1,14 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include "llvm/Support/ManagedStatic.h" -#include "llvm/Support/raw_ostream.h" -#define NUM_VERSION (((LLVM_VERSION_MAJOR) << 16) + (LLVM_VERSION_MINOR << 8) + LLVM_VERSION_PATCH) - -#if NUM_VERSION < 0x030900 -# error "LLVM version too low" -#endif -int main() -{ - llvm::errs() << "Hello World!\n"; - llvm::llvm_shutdown(); - return 0; -} diff --git a/tools/cgroup/iocost_monitor.py b/tools/cgroup/iocost_monitor.py index 0dbbc67400fc..933c750b319b 100644 --- a/tools/cgroup/iocost_monitor.py +++ b/tools/cgroup/iocost_monitor.py @@ -100,6 +100,7 @@ class IocStat: self.period_at = ioc.period_at.value_() / 1_000_000 self.vperiod_at = ioc.period_at_vtime.value_() / VTIME_PER_SEC self.vrate_pct = ioc.vtime_base_rate.value_() * 100 / VTIME_PER_USEC + self.ivrate_pct = ioc.vtime_rate.counter.value_() * 100 / VTIME_PER_USEC self.busy_level = ioc.busy_level.value_() self.autop_idx = ioc.autop_idx.value_() self.user_cost_model = ioc.user_cost_model.value_() @@ -119,7 +120,9 @@ class IocStat: 'period_at' : self.period_at, 'period_vtime_at' : self.vperiod_at, 'busy_level' : self.busy_level, - 'vrate_pct' : self.vrate_pct, } + 'vrate_pct' : self.vrate_pct, + 'ivrate_pct' : self.ivrate_pct, + } def table_preamble_str(self): state = ('RUN' if self.running else 'IDLE') if self.enabled else 'OFF' @@ -127,7 +130,7 @@ class IocStat: f'per={self.period_ms}ms ' \ f'cur_per={self.period_at:.3f}:v{self.vperiod_at:.3f} ' \ f'busy={self.busy_level:+3} ' \ - f'vrate={self.vrate_pct:6.2f}% ' \ + f'vrate={self.vrate_pct:6.2f}%:{self.ivrate_pct:6.2f}% ' \ f'params={self.autop_name}' if self.user_cost_model or self.user_qos_params: output += f'({"C" if self.user_cost_model else ""}{"Q" if self.user_qos_params else ""})' @@ -135,7 +138,7 @@ class IocStat: def table_header_str(self): return f'{"":25} active {"weight":>9} {"hweight%":>13} {"inflt%":>6} ' \ - f'{"debt":>7} {"delay":>7} {"usage%"}' + f'{"usage%":>6} {"wait":>7} {"debt":>7} {"delay":>7}' class IocgStat: def __init__(self, iocg): @@ -161,6 +164,8 @@ class IocgStat: self.usage = (100 * iocg.usage_delta_us.value_() / ioc.period_us.value_()) if self.active else 0 + self.wait_ms = (iocg.stat.wait_us.value_() - + iocg.last_stat.wait_us.value_()) / 1000 self.debt_ms = iocg.abs_vdebt.value_() / VTIME_PER_USEC / 1000 if blkg.use_delay.counter.value_() != 0: self.delay_ms = blkg.delay_nsec.counter.value_() / 1_000_000 @@ -177,9 +182,10 @@ class IocgStat: 'hweight_active_pct' : self.hwa_pct, 'hweight_inuse_pct' : self.hwi_pct, 'inflight_pct' : self.inflight_pct, + 'usage_pct' : self.usage, + 'wait_ms' : self.wait_ms, 'debt_ms' : self.debt_ms, 'delay_ms' : self.delay_ms, - 'usage_pct' : self.usage, 'address' : self.address } return out @@ -189,9 +195,10 @@ class IocgStat: f'{round(self.inuse):5}/{round(self.active):5} ' \ f'{self.hwi_pct:6.2f}/{self.hwa_pct:6.2f} ' \ f'{self.inflight_pct:6.2f} ' \ + f'{min(self.usage, 999):6.2f} ' \ + f'{self.wait_ms:7.2f} ' \ f'{self.debt_ms:7.2f} ' \ - f'{self.delay_ms:7.2f} '\ - f'{min(self.usage, 999):6.2f}' + f'{self.delay_ms:7.2f}' out = out.rstrip(':') return out @@ -221,7 +228,7 @@ ioc = None for i, ptr in radix_tree_for_each(blkcg_root.blkg_tree.address_of_()): blkg = drgn.Object(prog, 'struct blkcg_gq', address=ptr) try: - if devname == blkg.q.kobj.parent.name.string_().decode('utf-8'): + if devname == blkg.q.mq_kobj.parent.name.string_().decode('utf-8'): q_id = blkg.q.id.value_() if blkg.pd[plid]: root_iocg = container_of(blkg.pd[plid], 'struct ioc_gq', 'pd') diff --git a/tools/crypto/ccp/.gitignore b/tools/crypto/ccp/.gitignore new file mode 100644 index 000000000000..bee8a64b79a9 --- /dev/null +++ b/tools/crypto/ccp/.gitignore @@ -0,0 +1 @@ +__pycache__ diff --git a/tools/crypto/ccp/Makefile b/tools/crypto/ccp/Makefile new file mode 100644 index 000000000000..ae4a66d1558a --- /dev/null +++ b/tools/crypto/ccp/Makefile @@ -0,0 +1,13 @@ +# SPDX-License-Identifier: GPL-2.0-only +CFLAGS += -D__EXPORTED_HEADERS__ -I../../../include/uapi -I../../../include + +TARGET = dbc_library.so + +all: $(TARGET) + +dbc_library.so: dbc.c + $(CC) $(CFLAGS) $(LDFLAGS) -shared -o $@ $< + chmod -x $@ + +clean: + $(RM) $(TARGET) diff --git a/tools/crypto/ccp/dbc.c b/tools/crypto/ccp/dbc.c new file mode 100644 index 000000000000..37e813175642 --- /dev/null +++ b/tools/crypto/ccp/dbc.c @@ -0,0 +1,72 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * AMD Secure Processor Dynamic Boost Control sample library + * + * Copyright (C) 2023 Advanced Micro Devices, Inc. + * + * Author: Mario Limonciello <mario.limonciello@amd.com> + */ + +#include <assert.h> +#include <string.h> +#include <sys/ioctl.h> + +/* if uapi header isn't installed, this might not yet exist */ +#ifndef __packed +#define __packed __attribute__((packed)) +#endif +#include <linux/psp-dbc.h> + +int get_nonce(int fd, void *nonce_out, void *signature) +{ + struct dbc_user_nonce tmp = { + .auth_needed = !!signature, + }; + int ret; + + assert(nonce_out); + + if (signature) + memcpy(tmp.signature, signature, sizeof(tmp.signature)); + + ret = ioctl(fd, DBCIOCNONCE, &tmp); + if (ret) + return ret; + memcpy(nonce_out, tmp.nonce, sizeof(tmp.nonce)); + + return 0; +} + +int set_uid(int fd, __u8 *uid, __u8 *signature) +{ + struct dbc_user_setuid tmp; + + assert(uid); + assert(signature); + + memcpy(tmp.uid, uid, sizeof(tmp.uid)); + memcpy(tmp.signature, signature, sizeof(tmp.signature)); + + return ioctl(fd, DBCIOCUID, &tmp); +} + +int process_param(int fd, int msg_index, __u8 *signature, int *data) +{ + struct dbc_user_param tmp = { + .msg_index = msg_index, + .param = *data, + }; + int ret; + + assert(signature); + assert(data); + + memcpy(tmp.signature, signature, sizeof(tmp.signature)); + + ret = ioctl(fd, DBCIOCPARAM, &tmp); + if (ret) + return ret; + + *data = tmp.param; + return 0; +} diff --git a/tools/crypto/ccp/dbc.py b/tools/crypto/ccp/dbc.py new file mode 100644 index 000000000000..3f6a825ffc9e --- /dev/null +++ b/tools/crypto/ccp/dbc.py @@ -0,0 +1,64 @@ +#!/usr/bin/python3 +# SPDX-License-Identifier: GPL-2.0 + +import ctypes +import os + +DBC_UID_SIZE = 16 +DBC_NONCE_SIZE = 16 +DBC_SIG_SIZE = 32 + +PARAM_GET_FMAX_CAP = (0x3,) +PARAM_SET_FMAX_CAP = (0x4,) +PARAM_GET_PWR_CAP = (0x5,) +PARAM_SET_PWR_CAP = (0x6,) +PARAM_GET_GFX_MODE = (0x7,) +PARAM_SET_GFX_MODE = (0x8,) +PARAM_GET_CURR_TEMP = (0x9,) +PARAM_GET_FMAX_MAX = (0xA,) +PARAM_GET_FMAX_MIN = (0xB,) +PARAM_GET_SOC_PWR_MAX = (0xC,) +PARAM_GET_SOC_PWR_MIN = (0xD,) +PARAM_GET_SOC_PWR_CUR = (0xE,) + +DEVICE_NODE = "/dev/dbc" + +lib = ctypes.CDLL("./dbc_library.so", mode=ctypes.RTLD_GLOBAL) + + +def handle_error(code): + val = code * -1 + raise OSError(val, os.strerror(val)) + + +def get_nonce(device, signature): + if not device: + raise ValueError("Device required") + buf = ctypes.create_string_buffer(DBC_NONCE_SIZE) + ret = lib.get_nonce(device.fileno(), ctypes.byref(buf), signature) + if ret: + handle_error(ret) + return buf.value + + +def set_uid(device, new_uid, signature): + if not signature: + raise ValueError("Signature required") + if not new_uid: + raise ValueError("UID required") + ret = lib.set_uid(device.fileno(), new_uid, signature) + if ret: + handle_error(ret) + return True + + +def process_param(device, message, signature, data=None): + if not signature: + raise ValueError("Signature required") + if type(message) != tuple: + raise ValueError("Expected message tuple") + arg = ctypes.c_int(data if data else 0) + ret = lib.process_param(device.fileno(), message[0], signature, ctypes.pointer(arg)) + if ret: + handle_error(ret) + return arg, signature diff --git a/tools/crypto/ccp/dbc_cli.py b/tools/crypto/ccp/dbc_cli.py new file mode 100755 index 000000000000..bf52233fd038 --- /dev/null +++ b/tools/crypto/ccp/dbc_cli.py @@ -0,0 +1,134 @@ +#!/usr/bin/python3 +# SPDX-License-Identifier: GPL-2.0 +import argparse +import binascii +import os +import errno +from dbc import * + +ERRORS = { + errno.EACCES: "Access is denied", + errno.E2BIG: "Excess data provided", + errno.EINVAL: "Bad parameters", + errno.EAGAIN: "Bad state", + errno.ENOENT: "Not implemented or message failure", + errno.EBUSY: "Busy", + errno.ENFILE: "Overflow", + errno.EPERM: "Signature invalid", +} + +messages = { + "get-fmax-cap": PARAM_GET_FMAX_CAP, + "set-fmax-cap": PARAM_SET_FMAX_CAP, + "get-power-cap": PARAM_GET_PWR_CAP, + "set-power-cap": PARAM_SET_PWR_CAP, + "get-graphics-mode": PARAM_GET_GFX_MODE, + "set-graphics-mode": PARAM_SET_GFX_MODE, + "get-current-temp": PARAM_GET_CURR_TEMP, + "get-fmax-max": PARAM_GET_FMAX_MAX, + "get-fmax-min": PARAM_GET_FMAX_MIN, + "get-soc-power-max": PARAM_GET_SOC_PWR_MAX, + "get-soc-power-min": PARAM_GET_SOC_PWR_MIN, + "get-soc-power-cur": PARAM_GET_SOC_PWR_CUR, +} + + +def _pretty_buffer(ba): + return str(binascii.hexlify(ba, " ")) + + +def parse_args(): + parser = argparse.ArgumentParser( + description="Dynamic Boost control command line interface" + ) + parser.add_argument( + "command", + choices=["get-nonce", "get-param", "set-param", "set-uid"], + help="Command to send", + ) + parser.add_argument("--device", default="/dev/dbc", help="Device to operate") + parser.add_argument("--signature", help="File containing signature for command") + parser.add_argument("--message", choices=messages.keys(), help="Message index") + parser.add_argument("--data", help="Argument to pass to message") + parser.add_argument("--uid", help="File containing UID to pass") + return parser.parse_args() + + +def pretty_error(code): + if code in ERRORS: + print(ERRORS[code]) + else: + print("failed with return code %d" % code) + + +if __name__ == "__main__": + args = parse_args() + data = 0 + sig = None + uid = None + if not os.path.exists(args.device): + raise IOError("Missing device {device}".format(device=args.device)) + if args.signature: + if not os.path.exists(args.signature): + raise ValueError("Invalid signature file %s" % args.signature) + with open(args.signature, "rb") as f: + sig = f.read() + if len(sig) != DBC_SIG_SIZE: + raise ValueError( + "Invalid signature length %d (expected %d)" % (len(sig), DBC_SIG_SIZE) + ) + if args.uid: + if not os.path.exists(args.uid): + raise ValueError("Invalid uid file %s" % args.uid) + with open(args.uid, "rb") as f: + uid = f.read() + if len(uid) != DBC_UID_SIZE: + raise ValueError( + "Invalid UID length %d (expected %d)" % (len(uid), DBC_UID_SIZE) + ) + if args.data: + try: + data = int(args.data, 10) + except ValueError: + data = int(args.data, 16) + + with open(args.device) as d: + if args.command == "get-nonce": + try: + nonce = get_nonce(d, sig) + print("Nonce: %s" % _pretty_buffer(bytes(nonce))) + except OSError as e: + pretty_error(e.errno) + elif args.command == "set-uid": + try: + result = set_uid(d, uid, sig) + if result: + print("Set UID") + except OSError as e: + pretty_error(e.errno) + elif args.command == "get-param": + if not args.message or args.message.startswith("set"): + raise ValueError("Invalid message %s" % args.message) + try: + param, signature = process_param(d, messages[args.message], sig) + print( + "Parameter: {par}, response signature {sig}".format( + par=param, + sig=_pretty_buffer(bytes(signature)), + ) + ) + except OSError as e: + pretty_error(e.errno) + elif args.command == "set-param": + if not args.message or args.message.startswith("get"): + raise ValueError("Invalid message %s" % args.message) + try: + param, signature = process_param(d, messages[args.message], sig, data) + print( + "Parameter: {par}, response signature {sig}".format( + par=param, + sig=_pretty_buffer(bytes(signature)), + ) + ) + except OSError as e: + pretty_error(e.errno) diff --git a/tools/crypto/ccp/test_dbc.py b/tools/crypto/ccp/test_dbc.py new file mode 100755 index 000000000000..998bb3e3cd04 --- /dev/null +++ b/tools/crypto/ccp/test_dbc.py @@ -0,0 +1,266 @@ +#!/usr/bin/python3 +# SPDX-License-Identifier: GPL-2.0 +import unittest +import os +import time +import glob +from dbc import * + +# Artificial delay between set commands +SET_DELAY = 0.5 + + +class invalid_param(ctypes.Structure): + _fields_ = [ + ("data", ctypes.c_uint8), + ] + + +def system_is_secured() -> bool: + fused_part = glob.glob("/sys/bus/pci/drivers/ccp/**/fused_part")[0] + if os.path.exists(fused_part): + with open(fused_part, "r") as r: + return int(r.read()) == 1 + return True + + +class DynamicBoostControlTest(unittest.TestCase): + def __init__(self, data) -> None: + self.d = None + self.signature = "FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF" + self.uid = "1111111111111111" + super().__init__(data) + + def setUp(self) -> None: + self.d = open(DEVICE_NODE) + return super().setUp() + + def tearDown(self) -> None: + if self.d: + self.d.close() + return super().tearDown() + + +class TestUnsupportedSystem(DynamicBoostControlTest): + def setUp(self) -> None: + if os.path.exists(DEVICE_NODE): + self.skipTest("system is supported") + with self.assertRaises(FileNotFoundError) as error: + super().setUp() + self.assertEqual(error.exception.errno, 2) + + def test_unauthenticated_nonce(self) -> None: + """fetch unauthenticated nonce""" + with self.assertRaises(ValueError) as error: + get_nonce(self.d, None) + + +class TestInvalidIoctls(DynamicBoostControlTest): + def __init__(self, data) -> None: + self.data = invalid_param() + self.data.data = 1 + super().__init__(data) + + def setUp(self) -> None: + if not os.path.exists(DEVICE_NODE): + self.skipTest("system is unsupported") + return super().setUp() + + def test_invalid_nonce_ioctl(self) -> None: + """tries to call get_nonce ioctl with invalid data structures""" + + # 0x1 (get nonce), and invalid data + INVALID1 = IOWR(ord("D"), 0x01, invalid_param) + with self.assertRaises(OSError) as error: + fcntl.ioctl(self.d, INVALID1, self.data, True) + self.assertEqual(error.exception.errno, 22) + + def test_invalid_setuid_ioctl(self) -> None: + """tries to call set_uid ioctl with invalid data structures""" + + # 0x2 (set uid), and invalid data + INVALID2 = IOW(ord("D"), 0x02, invalid_param) + with self.assertRaises(OSError) as error: + fcntl.ioctl(self.d, INVALID2, self.data, True) + self.assertEqual(error.exception.errno, 22) + + def test_invalid_setuid_rw_ioctl(self) -> None: + """tries to call set_uid ioctl with invalid data structures""" + + # 0x2 as RW (set uid), and invalid data + INVALID3 = IOWR(ord("D"), 0x02, invalid_param) + with self.assertRaises(OSError) as error: + fcntl.ioctl(self.d, INVALID3, self.data, True) + self.assertEqual(error.exception.errno, 22) + + def test_invalid_param_ioctl(self) -> None: + """tries to call param ioctl with invalid data structures""" + # 0x3 (param), and invalid data + INVALID4 = IOWR(ord("D"), 0x03, invalid_param) + with self.assertRaises(OSError) as error: + fcntl.ioctl(self.d, INVALID4, self.data, True) + self.assertEqual(error.exception.errno, 22) + + def test_invalid_call_ioctl(self) -> None: + """tries to call the DBC ioctl with invalid data structures""" + # 0x4, and invalid data + INVALID5 = IOWR(ord("D"), 0x04, invalid_param) + with self.assertRaises(OSError) as error: + fcntl.ioctl(self.d, INVALID5, self.data, True) + self.assertEqual(error.exception.errno, 22) + + +class TestInvalidSignature(DynamicBoostControlTest): + def setUp(self) -> None: + if not os.path.exists(DEVICE_NODE): + self.skipTest("system is unsupported") + if not system_is_secured(): + self.skipTest("system is unfused") + return super().setUp() + + def test_unauthenticated_nonce(self) -> None: + """fetch unauthenticated nonce""" + get_nonce(self.d, None) + + def test_multiple_unauthenticated_nonce(self) -> None: + """ensure state machine always returns nonce""" + for count in range(0, 2): + get_nonce(self.d, None) + + def test_authenticated_nonce(self) -> None: + """fetch authenticated nonce""" + with self.assertRaises(OSError) as error: + get_nonce(self.d, self.signature) + self.assertEqual(error.exception.errno, 1) + + def test_set_uid(self) -> None: + """set uid""" + with self.assertRaises(OSError) as error: + set_uid(self.d, self.uid, self.signature) + self.assertEqual(error.exception.errno, 1) + + def test_get_param(self) -> None: + """fetch a parameter""" + with self.assertRaises(OSError) as error: + process_param(self.d, PARAM_GET_SOC_PWR_CUR, self.signature) + self.assertEqual(error.exception.errno, 1) + + def test_set_param(self) -> None: + """set a parameter""" + with self.assertRaises(OSError) as error: + process_param(self.d, PARAM_SET_PWR_CAP, self.signature, 1000) + self.assertEqual(error.exception.errno, 1) + + +class TestUnFusedSystem(DynamicBoostControlTest): + def setup_identity(self) -> None: + """sets up the identity of the caller""" + # if already authenticated these may fail + try: + get_nonce(self.d, None) + except PermissionError: + pass + try: + set_uid(self.d, self.uid, self.signature) + except BlockingIOError: + pass + try: + get_nonce(self.d, self.signature) + except PermissionError: + pass + + def setUp(self) -> None: + if not os.path.exists(DEVICE_NODE): + self.skipTest("system is unsupported") + if system_is_secured(): + self.skipTest("system is fused") + super().setUp() + self.setup_identity() + time.sleep(SET_DELAY) + + def test_get_valid_param(self) -> None: + """fetch all possible parameters""" + # SOC power + soc_power_max = process_param(self.d, PARAM_GET_SOC_PWR_MAX, self.signature) + soc_power_min = process_param(self.d, PARAM_GET_SOC_PWR_MIN, self.signature) + self.assertGreater(soc_power_max.parameter, soc_power_min.parameter) + + # fmax + fmax_max = process_param(self.d, PARAM_GET_FMAX_MAX, self.signature) + fmax_min = process_param(self.d, PARAM_GET_FMAX_MIN, self.signature) + self.assertGreater(fmax_max.parameter, fmax_min.parameter) + + # cap values + keys = { + "fmax-cap": PARAM_GET_FMAX_CAP, + "power-cap": PARAM_GET_PWR_CAP, + "current-temp": PARAM_GET_CURR_TEMP, + "soc-power-cur": PARAM_GET_SOC_PWR_CUR, + } + for k in keys: + result = process_param(self.d, keys[k], self.signature) + self.assertGreater(result.parameter, 0) + + def test_get_invalid_param(self) -> None: + """fetch an invalid parameter""" + try: + set_uid(self.d, self.uid, self.signature) + except OSError: + pass + with self.assertRaises(OSError) as error: + process_param(self.d, (0xF,), self.signature) + self.assertEqual(error.exception.errno, 22) + + def test_set_fmax(self) -> None: + """get/set fmax limit""" + # fetch current + original = process_param(self.d, PARAM_GET_FMAX_CAP, self.signature) + + # set the fmax + target = original.parameter - 100 + process_param(self.d, PARAM_SET_FMAX_CAP, self.signature, target) + time.sleep(SET_DELAY) + new = process_param(self.d, PARAM_GET_FMAX_CAP, self.signature) + self.assertEqual(new.parameter, target) + + # revert back to current + process_param(self.d, PARAM_SET_FMAX_CAP, self.signature, original.parameter) + time.sleep(SET_DELAY) + cur = process_param(self.d, PARAM_GET_FMAX_CAP, self.signature) + self.assertEqual(cur.parameter, original.parameter) + + def test_set_power_cap(self) -> None: + """get/set power cap limit""" + # fetch current + original = process_param(self.d, PARAM_GET_PWR_CAP, self.signature) + + # set the fmax + target = original.parameter - 10 + process_param(self.d, PARAM_SET_PWR_CAP, self.signature, target) + time.sleep(SET_DELAY) + new = process_param(self.d, PARAM_GET_PWR_CAP, self.signature) + self.assertEqual(new.parameter, target) + + # revert back to current + process_param(self.d, PARAM_SET_PWR_CAP, self.signature, original.parameter) + time.sleep(SET_DELAY) + cur = process_param(self.d, PARAM_GET_PWR_CAP, self.signature) + self.assertEqual(cur.parameter, original.parameter) + + def test_set_3d_graphics_mode(self) -> None: + """set/get 3d graphics mode""" + # these aren't currently implemented but may be some day + # they are *expected* to fail + with self.assertRaises(OSError) as error: + process_param(self.d, PARAM_GET_GFX_MODE, self.signature) + self.assertEqual(error.exception.errno, 2) + + time.sleep(SET_DELAY) + + with self.assertRaises(OSError) as error: + process_param(self.d, PARAM_SET_GFX_MODE, self.signature, 1) + self.assertEqual(error.exception.errno, 2) + + +if __name__ == "__main__": + unittest.main() diff --git a/tools/iio/iio_generic_buffer.c b/tools/iio/iio_generic_buffer.c index f8deae4e26a1..44bbf80f0cfd 100644 --- a/tools/iio/iio_generic_buffer.c +++ b/tools/iio/iio_generic_buffer.c @@ -51,9 +51,9 @@ enum autochan { * Has the side effect of filling the channels[i].location values used * in processing the buffer output. **/ -static int size_from_channelarray(struct iio_channel_info *channels, int num_channels) +static unsigned int size_from_channelarray(struct iio_channel_info *channels, int num_channels) { - int bytes = 0; + unsigned int bytes = 0; int i = 0; while (i < num_channels) { @@ -348,7 +348,7 @@ int main(int argc, char **argv) ssize_t read_size; int dev_num = -1, trig_num = -1; char *buffer_access = NULL; - int scan_size; + unsigned int scan_size; int noevents = 0; int notrigger = 0; char *dummy; @@ -674,7 +674,16 @@ int main(int argc, char **argv) } scan_size = size_from_channelarray(channels, num_channels); - data = malloc(scan_size * buf_len); + + size_t total_buf_len = scan_size * buf_len; + + if (scan_size > 0 && total_buf_len / scan_size != buf_len) { + ret = -EFAULT; + perror("Integer overflow happened when calculate scan_size * buf_len"); + goto error; + } + + data = malloc(total_buf_len); if (!data) { ret = -ENOMEM; goto error; diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h index 9d36c8ce1fe7..1684216e826a 100644 --- a/tools/include/linux/compiler.h +++ b/tools/include/linux/compiler.h @@ -42,6 +42,18 @@ # define __always_inline inline __attribute__((always_inline)) #endif +#ifndef __always_unused +#define __always_unused __attribute__((__unused__)) +#endif + +#ifndef __noreturn +#define __noreturn __attribute__((__noreturn__)) +#endif + +#ifndef unreachable +#define unreachable() __builtin_unreachable() +#endif + #ifndef noinline #define noinline #endif @@ -190,4 +202,10 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s #define ___PASTE(a, b) a##b #define __PASTE(a, b) ___PASTE(a, b) +#ifndef OPTIMIZER_HIDE_VAR +/* Make the optimizer believe the variable can be manipulated arbitrarily. */ +#define OPTIMIZER_HIDE_VAR(var) \ + __asm__ ("" : "=r" (var) : "0" (var)) +#endif + #endif /* _TOOLS_LINUX_COMPILER_H */ diff --git a/tools/include/nolibc/Makefile b/tools/include/nolibc/Makefile index 64d67b080744..909b6eb500fe 100644 --- a/tools/include/nolibc/Makefile +++ b/tools/include/nolibc/Makefile @@ -27,6 +27,7 @@ nolibc_arch := $(patsubst arm64,aarch64,$(ARCH)) arch_file := arch-$(nolibc_arch).h all_files := \ compiler.h \ + crt.h \ ctype.h \ errno.h \ nolibc.h \ diff --git a/tools/include/nolibc/arch-aarch64.h b/tools/include/nolibc/arch-aarch64.h index 11f294a406b7..6c33c46848e3 100644 --- a/tools/include/nolibc/arch-aarch64.h +++ b/tools/include/nolibc/arch-aarch64.h @@ -8,34 +8,7 @@ #define _NOLIBC_ARCH_AARCH64_H #include "compiler.h" - -/* The struct returned by the newfstatat() syscall. Differs slightly from the - * x86_64's stat one by field ordering, so be careful. - */ -struct sys_stat_struct { - unsigned long st_dev; - unsigned long st_ino; - unsigned int st_mode; - unsigned int st_nlink; - unsigned int st_uid; - unsigned int st_gid; - - unsigned long st_rdev; - unsigned long __pad1; - long st_size; - int st_blksize; - int __pad2; - - long st_blocks; - long st_atime; - unsigned long st_atime_nsec; - long st_mtime; - - unsigned long st_mtime_nsec; - long st_ctime; - unsigned long st_ctime_nsec; - unsigned int __unused[2]; -}; +#include "crt.h" /* Syscalls for AARCH64 : * - registers are 64-bit @@ -56,8 +29,8 @@ struct sys_stat_struct { ({ \ register long _num __asm__ ("x8") = (num); \ register long _arg1 __asm__ ("x0"); \ - \ - __asm__ volatile ( \ + \ + __asm__ volatile ( \ "svc #0\n" \ : "=r"(_arg1) \ : "r"(_num) \ @@ -70,8 +43,8 @@ struct sys_stat_struct { ({ \ register long _num __asm__ ("x8") = (num); \ register long _arg1 __asm__ ("x0") = (long)(arg1); \ - \ - __asm__ volatile ( \ + \ + __asm__ volatile ( \ "svc #0\n" \ : "=r"(_arg1) \ : "r"(_arg1), \ @@ -86,8 +59,8 @@ struct sys_stat_struct { register long _num __asm__ ("x8") = (num); \ register long _arg1 __asm__ ("x0") = (long)(arg1); \ register long _arg2 __asm__ ("x1") = (long)(arg2); \ - \ - __asm__ volatile ( \ + \ + __asm__ volatile ( \ "svc #0\n" \ : "=r"(_arg1) \ : "r"(_arg1), "r"(_arg2), \ @@ -103,8 +76,8 @@ struct sys_stat_struct { register long _arg1 __asm__ ("x0") = (long)(arg1); \ register long _arg2 __asm__ ("x1") = (long)(arg2); \ register long _arg3 __asm__ ("x2") = (long)(arg3); \ - \ - __asm__ volatile ( \ + \ + __asm__ volatile ( \ "svc #0\n" \ : "=r"(_arg1) \ : "r"(_arg1), "r"(_arg2), "r"(_arg3), \ @@ -121,8 +94,8 @@ struct sys_stat_struct { register long _arg2 __asm__ ("x1") = (long)(arg2); \ register long _arg3 __asm__ ("x2") = (long)(arg3); \ register long _arg4 __asm__ ("x3") = (long)(arg4); \ - \ - __asm__ volatile ( \ + \ + __asm__ volatile ( \ "svc #0\n" \ : "=r"(_arg1) \ : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \ @@ -140,8 +113,8 @@ struct sys_stat_struct { register long _arg3 __asm__ ("x2") = (long)(arg3); \ register long _arg4 __asm__ ("x3") = (long)(arg4); \ register long _arg5 __asm__ ("x4") = (long)(arg5); \ - \ - __asm__ volatile ( \ + \ + __asm__ volatile ( \ "svc #0\n" \ : "=r" (_arg1) \ : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ @@ -160,8 +133,8 @@ struct sys_stat_struct { register long _arg4 __asm__ ("x3") = (long)(arg4); \ register long _arg5 __asm__ ("x4") = (long)(arg5); \ register long _arg6 __asm__ ("x5") = (long)(arg6); \ - \ - __asm__ volatile ( \ + \ + __asm__ volatile ( \ "svc #0\n" \ : "=r" (_arg1) \ : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ @@ -171,33 +144,13 @@ struct sys_stat_struct { _arg1; \ }) -char **environ __attribute__((weak)); -const unsigned long *_auxv __attribute__((weak)); - /* startup code */ -void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) __no_stack_protector _start(void) +void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_stack_protector _start(void) { __asm__ volatile ( -#ifdef _NOLIBC_STACKPROTECTOR - "bl __stack_chk_init\n" /* initialize stack protector */ -#endif - "ldr x0, [sp]\n" /* argc (x0) was in the stack */ - "add x1, sp, 8\n" /* argv (x1) = sp */ - "lsl x2, x0, 3\n" /* envp (x2) = 8*argc ... */ - "add x2, x2, 8\n" /* + 8 (skip null) */ - "add x2, x2, x1\n" /* + argv */ - "adrp x3, environ\n" /* x3 = &environ (high bits) */ - "str x2, [x3, #:lo12:environ]\n" /* store envp into environ */ - "mov x4, x2\n" /* search for auxv (follows NULL after last env) */ - "0:\n" - "ldr x5, [x4], 8\n" /* x5 = *x4; x4 += 8 */ - "cbnz x5, 0b\n" /* and stop at NULL after last env */ - "adrp x3, _auxv\n" /* x3 = &_auxv (high bits) */ - "str x4, [x3, #:lo12:_auxv]\n" /* store x4 into _auxv */ - "and sp, x1, -16\n" /* sp must be 16-byte aligned in the callee */ - "bl main\n" /* main() returns the status code, we'll exit with it. */ - "mov x8, 93\n" /* NR_exit == 93 */ - "svc #0\n" + "mov x0, sp\n" /* save stack pointer to x0, as arg1 of _start_c */ + "and sp, x0, -16\n" /* sp must be 16-byte aligned in the callee */ + "bl _start_c\n" /* transfer to c runtime */ ); __builtin_unreachable(); } diff --git a/tools/include/nolibc/arch-arm.h b/tools/include/nolibc/arch-arm.h index ca4c66987497..cae4afa7c1c7 100644 --- a/tools/include/nolibc/arch-arm.h +++ b/tools/include/nolibc/arch-arm.h @@ -8,43 +8,7 @@ #define _NOLIBC_ARCH_ARM_H #include "compiler.h" - -/* The struct returned by the stat() syscall, 32-bit only, the syscall returns - * exactly 56 bytes (stops before the unused array). In big endian, the format - * differs as devices are returned as short only. - */ -struct sys_stat_struct { -#if defined(__ARMEB__) - unsigned short st_dev; - unsigned short __pad1; -#else - unsigned long st_dev; -#endif - unsigned long st_ino; - unsigned short st_mode; - unsigned short st_nlink; - unsigned short st_uid; - unsigned short st_gid; - -#if defined(__ARMEB__) - unsigned short st_rdev; - unsigned short __pad2; -#else - unsigned long st_rdev; -#endif - unsigned long st_size; - unsigned long st_blksize; - unsigned long st_blocks; - - unsigned long st_atime; - unsigned long st_atime_nsec; - unsigned long st_mtime; - unsigned long st_mtime_nsec; - - unsigned long st_ctime; - unsigned long st_ctime_nsec; - unsigned long __unused[2]; -}; +#include "crt.h" /* Syscalls for ARM in ARM or Thumb modes : * - registers are 32-bit @@ -90,8 +54,8 @@ struct sys_stat_struct { ({ \ register long _num __asm__(_NOLIBC_SYSCALL_REG) = (num); \ register long _arg1 __asm__ ("r0"); \ - \ - __asm__ volatile ( \ + \ + __asm__ volatile ( \ _NOLIBC_THUMB_SET_R7 \ "svc #0\n" \ _NOLIBC_THUMB_RESTORE_R7 \ @@ -107,8 +71,8 @@ struct sys_stat_struct { ({ \ register long _num __asm__(_NOLIBC_SYSCALL_REG) = (num); \ register long _arg1 __asm__ ("r0") = (long)(arg1); \ - \ - __asm__ volatile ( \ + \ + __asm__ volatile ( \ _NOLIBC_THUMB_SET_R7 \ "svc #0\n" \ _NOLIBC_THUMB_RESTORE_R7 \ @@ -125,8 +89,8 @@ struct sys_stat_struct { register long _num __asm__(_NOLIBC_SYSCALL_REG) = (num); \ register long _arg1 __asm__ ("r0") = (long)(arg1); \ register long _arg2 __asm__ ("r1") = (long)(arg2); \ - \ - __asm__ volatile ( \ + \ + __asm__ volatile ( \ _NOLIBC_THUMB_SET_R7 \ "svc #0\n" \ _NOLIBC_THUMB_RESTORE_R7 \ @@ -144,8 +108,8 @@ struct sys_stat_struct { register long _arg1 __asm__ ("r0") = (long)(arg1); \ register long _arg2 __asm__ ("r1") = (long)(arg2); \ register long _arg3 __asm__ ("r2") = (long)(arg3); \ - \ - __asm__ volatile ( \ + \ + __asm__ volatile ( \ _NOLIBC_THUMB_SET_R7 \ "svc #0\n" \ _NOLIBC_THUMB_RESTORE_R7 \ @@ -164,8 +128,8 @@ struct sys_stat_struct { register long _arg2 __asm__ ("r1") = (long)(arg2); \ register long _arg3 __asm__ ("r2") = (long)(arg3); \ register long _arg4 __asm__ ("r3") = (long)(arg4); \ - \ - __asm__ volatile ( \ + \ + __asm__ volatile ( \ _NOLIBC_THUMB_SET_R7 \ "svc #0\n" \ _NOLIBC_THUMB_RESTORE_R7 \ @@ -185,8 +149,8 @@ struct sys_stat_struct { register long _arg3 __asm__ ("r2") = (long)(arg3); \ register long _arg4 __asm__ ("r3") = (long)(arg4); \ register long _arg5 __asm__ ("r4") = (long)(arg5); \ - \ - __asm__ volatile ( \ + \ + __asm__ volatile ( \ _NOLIBC_THUMB_SET_R7 \ "svc #0\n" \ _NOLIBC_THUMB_RESTORE_R7 \ @@ -207,8 +171,8 @@ struct sys_stat_struct { register long _arg4 __asm__ ("r3") = (long)(arg4); \ register long _arg5 __asm__ ("r4") = (long)(arg5); \ register long _arg6 __asm__ ("r5") = (long)(arg6); \ - \ - __asm__ volatile ( \ + \ + __asm__ volatile ( \ _NOLIBC_THUMB_SET_R7 \ "svc #0\n" \ _NOLIBC_THUMB_RESTORE_R7 \ @@ -220,49 +184,14 @@ struct sys_stat_struct { _arg1; \ }) - -char **environ __attribute__((weak)); -const unsigned long *_auxv __attribute__((weak)); - /* startup code */ -void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) __no_stack_protector _start(void) +void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_stack_protector _start(void) { __asm__ volatile ( -#ifdef _NOLIBC_STACKPROTECTOR - "bl __stack_chk_init\n" /* initialize stack protector */ -#endif - "pop {%r0}\n" /* argc was in the stack */ - "mov %r1, %sp\n" /* argv = sp */ - - "add %r2, %r0, $1\n" /* envp = (argc + 1) ... */ - "lsl %r2, %r2, $2\n" /* * 4 ... */ - "add %r2, %r2, %r1\n" /* + argv */ - "ldr %r3, 1f\n" /* r3 = &environ (see below) */ - "str %r2, [r3]\n" /* store envp into environ */ - - "mov r4, r2\n" /* search for auxv (follows NULL after last env) */ - "0:\n" - "mov r5, r4\n" /* r5 = r4 */ - "add r4, r4, #4\n" /* r4 += 4 */ - "ldr r5,[r5]\n" /* r5 = *r5 = *(r4-4) */ - "cmp r5, #0\n" /* and stop at NULL after last env */ - "bne 0b\n" - "ldr %r3, 2f\n" /* r3 = &_auxv (low bits) */ - "str r4, [r3]\n" /* store r4 into _auxv */ - - "mov %r3, $8\n" /* AAPCS : sp must be 8-byte aligned in the */ - "neg %r3, %r3\n" /* callee, and bl doesn't push (lr=pc) */ - "and %r3, %r3, %r1\n" /* so we do sp = r1(=sp) & r3(=-8); */ - "mov %sp, %r3\n" - - "bl main\n" /* main() returns the status code, we'll exit with it. */ - "movs r7, $1\n" /* NR_exit == 1 */ - "svc $0x00\n" - ".align 2\n" /* below are the pointers to a few variables */ - "1:\n" - ".word environ\n" - "2:\n" - ".word _auxv\n" + "mov %r0, sp\n" /* save stack pointer to %r0, as arg1 of _start_c */ + "and ip, %r0, #-8\n" /* sp must be 8-byte aligned in the callee */ + "mov sp, ip\n" + "bl _start_c\n" /* transfer to c runtime */ ); __builtin_unreachable(); } diff --git a/tools/include/nolibc/arch-i386.h b/tools/include/nolibc/arch-i386.h index 3d672d925e9e..64415b9fac77 100644 --- a/tools/include/nolibc/arch-i386.h +++ b/tools/include/nolibc/arch-i386.h @@ -8,32 +8,7 @@ #define _NOLIBC_ARCH_I386_H #include "compiler.h" - -/* The struct returned by the stat() syscall, 32-bit only, the syscall returns - * exactly 56 bytes (stops before the unused array). - */ -struct sys_stat_struct { - unsigned long st_dev; - unsigned long st_ino; - unsigned short st_mode; - unsigned short st_nlink; - unsigned short st_uid; - unsigned short st_gid; - - unsigned long st_rdev; - unsigned long st_size; - unsigned long st_blksize; - unsigned long st_blocks; - - unsigned long st_atime; - unsigned long st_atime_nsec; - unsigned long st_mtime; - unsigned long st_mtime_nsec; - - unsigned long st_ctime; - unsigned long st_ctime_nsec; - unsigned long __unused[2]; -}; +#include "crt.h" /* Syscalls for i386 : * - mostly similar to x86_64 @@ -57,8 +32,8 @@ struct sys_stat_struct { ({ \ long _ret; \ register long _num __asm__ ("eax") = (num); \ - \ - __asm__ volatile ( \ + \ + __asm__ volatile ( \ "int $0x80\n" \ : "=a" (_ret) \ : "0"(_num) \ @@ -72,8 +47,8 @@ struct sys_stat_struct { long _ret; \ register long _num __asm__ ("eax") = (num); \ register long _arg1 __asm__ ("ebx") = (long)(arg1); \ - \ - __asm__ volatile ( \ + \ + __asm__ volatile ( \ "int $0x80\n" \ : "=a" (_ret) \ : "r"(_arg1), \ @@ -89,8 +64,8 @@ struct sys_stat_struct { register long _num __asm__ ("eax") = (num); \ register long _arg1 __asm__ ("ebx") = (long)(arg1); \ register long _arg2 __asm__ ("ecx") = (long)(arg2); \ - \ - __asm__ volatile ( \ + \ + __asm__ volatile ( \ "int $0x80\n" \ : "=a" (_ret) \ : "r"(_arg1), "r"(_arg2), \ @@ -107,8 +82,8 @@ struct sys_stat_struct { register long _arg1 __asm__ ("ebx") = (long)(arg1); \ register long _arg2 __asm__ ("ecx") = (long)(arg2); \ register long _arg3 __asm__ ("edx") = (long)(arg3); \ - \ - __asm__ volatile ( \ + \ + __asm__ volatile ( \ "int $0x80\n" \ : "=a" (_ret) \ : "r"(_arg1), "r"(_arg2), "r"(_arg3), \ @@ -126,8 +101,8 @@ struct sys_stat_struct { register long _arg2 __asm__ ("ecx") = (long)(arg2); \ register long _arg3 __asm__ ("edx") = (long)(arg3); \ register long _arg4 __asm__ ("esi") = (long)(arg4); \ - \ - __asm__ volatile ( \ + \ + __asm__ volatile ( \ "int $0x80\n" \ : "=a" (_ret) \ : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \ @@ -146,8 +121,8 @@ struct sys_stat_struct { register long _arg3 __asm__ ("edx") = (long)(arg3); \ register long _arg4 __asm__ ("esi") = (long)(arg4); \ register long _arg5 __asm__ ("edi") = (long)(arg5); \ - \ - __asm__ volatile ( \ + \ + __asm__ volatile ( \ "int $0x80\n" \ : "=a" (_ret) \ : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ @@ -180,9 +155,6 @@ struct sys_stat_struct { _eax; \ }) -char **environ __attribute__((weak)); -const unsigned long *_auxv __attribute__((weak)); - /* startup code */ /* * i386 System V ABI mandates: @@ -190,33 +162,15 @@ const unsigned long *_auxv __attribute__((weak)); * 2) The deepest stack frame should be set to zero * */ -void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) __no_stack_protector _start(void) +void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_stack_protector _start(void) { __asm__ volatile ( -#ifdef _NOLIBC_STACKPROTECTOR - "call __stack_chk_init\n" /* initialize stack protector */ -#endif - "pop %eax\n" /* argc (first arg, %eax) */ - "mov %esp, %ebx\n" /* argv[] (second arg, %ebx) */ - "lea 4(%ebx,%eax,4),%ecx\n" /* then a NULL then envp (third arg, %ecx) */ - "mov %ecx, environ\n" /* save environ */ - "xor %ebp, %ebp\n" /* zero the stack frame */ - "mov %ecx, %edx\n" /* search for auxv (follows NULL after last env) */ - "0:\n" - "add $4, %edx\n" /* search for auxv using edx, it follows the */ - "cmp -4(%edx), %ebp\n" /* ... NULL after last env (ebp is zero here) */ - "jnz 0b\n" - "mov %edx, _auxv\n" /* save it into _auxv */ - "and $-16, %esp\n" /* x86 ABI : esp must be 16-byte aligned before */ - "sub $4, %esp\n" /* the call instruction (args are aligned) */ - "push %ecx\n" /* push all registers on the stack so that we */ - "push %ebx\n" /* support both regparm and plain stack modes */ - "push %eax\n" - "call main\n" /* main() returns the status code in %eax */ - "mov %eax, %ebx\n" /* retrieve exit code (32-bit int) */ - "movl $1, %eax\n" /* NR_exit == 1 */ - "int $0x80\n" /* exit now */ - "hlt\n" /* ensure it does not */ + "xor %ebp, %ebp\n" /* zero the stack frame */ + "mov %esp, %eax\n" /* save stack pointer to %eax, as arg1 of _start_c */ + "and $-16, %esp\n" /* last pushed argument must be 16-byte aligned */ + "push %eax\n" /* push arg1 on stack to support plain stack modes too */ + "call _start_c\n" /* transfer to c runtime */ + "hlt\n" /* ensure it does not return */ ); __builtin_unreachable(); } diff --git a/tools/include/nolibc/arch-loongarch.h b/tools/include/nolibc/arch-loongarch.h index ad3f266e7093..bf98f6220195 100644 --- a/tools/include/nolibc/arch-loongarch.h +++ b/tools/include/nolibc/arch-loongarch.h @@ -8,6 +8,7 @@ #define _NOLIBC_ARCH_LOONGARCH_H #include "compiler.h" +#include "crt.h" /* Syscalls for LoongArch : * - stack is 16-byte aligned @@ -22,18 +23,19 @@ * On LoongArch, select() is not implemented so we have to use pselect6(). */ #define __ARCH_WANT_SYS_PSELECT6 +#define _NOLIBC_SYSCALL_CLOBBERLIST \ + "memory", "$t0", "$t1", "$t2", "$t3", "$t4", "$t5", "$t6", "$t7", "$t8" #define my_syscall0(num) \ ({ \ register long _num __asm__ ("a7") = (num); \ register long _arg1 __asm__ ("a0"); \ \ - __asm__ volatile ( \ + __asm__ volatile ( \ "syscall 0\n" \ : "=r"(_arg1) \ : "r"(_num) \ - : "memory", "$t0", "$t1", "$t2", "$t3", \ - "$t4", "$t5", "$t6", "$t7", "$t8" \ + : _NOLIBC_SYSCALL_CLOBBERLIST \ ); \ _arg1; \ }) @@ -43,12 +45,11 @@ register long _num __asm__ ("a7") = (num); \ register long _arg1 __asm__ ("a0") = (long)(arg1); \ \ - __asm__ volatile ( \ + __asm__ volatile ( \ "syscall 0\n" \ : "+r"(_arg1) \ : "r"(_num) \ - : "memory", "$t0", "$t1", "$t2", "$t3", \ - "$t4", "$t5", "$t6", "$t7", "$t8" \ + : _NOLIBC_SYSCALL_CLOBBERLIST \ ); \ _arg1; \ }) @@ -59,13 +60,12 @@ register long _arg1 __asm__ ("a0") = (long)(arg1); \ register long _arg2 __asm__ ("a1") = (long)(arg2); \ \ - __asm__ volatile ( \ + __asm__ volatile ( \ "syscall 0\n" \ : "+r"(_arg1) \ : "r"(_arg2), \ "r"(_num) \ - : "memory", "$t0", "$t1", "$t2", "$t3", \ - "$t4", "$t5", "$t6", "$t7", "$t8" \ + : _NOLIBC_SYSCALL_CLOBBERLIST \ ); \ _arg1; \ }) @@ -77,13 +77,12 @@ register long _arg2 __asm__ ("a1") = (long)(arg2); \ register long _arg3 __asm__ ("a2") = (long)(arg3); \ \ - __asm__ volatile ( \ + __asm__ volatile ( \ "syscall 0\n" \ : "+r"(_arg1) \ : "r"(_arg2), "r"(_arg3), \ "r"(_num) \ - : "memory", "$t0", "$t1", "$t2", "$t3", \ - "$t4", "$t5", "$t6", "$t7", "$t8" \ + : _NOLIBC_SYSCALL_CLOBBERLIST \ ); \ _arg1; \ }) @@ -96,13 +95,12 @@ register long _arg3 __asm__ ("a2") = (long)(arg3); \ register long _arg4 __asm__ ("a3") = (long)(arg4); \ \ - __asm__ volatile ( \ + __asm__ volatile ( \ "syscall 0\n" \ : "+r"(_arg1) \ : "r"(_arg2), "r"(_arg3), "r"(_arg4), \ "r"(_num) \ - : "memory", "$t0", "$t1", "$t2", "$t3", \ - "$t4", "$t5", "$t6", "$t7", "$t8" \ + : _NOLIBC_SYSCALL_CLOBBERLIST \ ); \ _arg1; \ }) @@ -116,13 +114,12 @@ register long _arg4 __asm__ ("a3") = (long)(arg4); \ register long _arg5 __asm__ ("a4") = (long)(arg5); \ \ - __asm__ volatile ( \ + __asm__ volatile ( \ "syscall 0\n" \ : "+r"(_arg1) \ : "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ "r"(_num) \ - : "memory", "$t0", "$t1", "$t2", "$t3", \ - "$t4", "$t5", "$t6", "$t7", "$t8" \ + : _NOLIBC_SYSCALL_CLOBBERLIST \ ); \ _arg1; \ }) @@ -137,67 +134,29 @@ register long _arg5 __asm__ ("a4") = (long)(arg5); \ register long _arg6 __asm__ ("a5") = (long)(arg6); \ \ - __asm__ volatile ( \ + __asm__ volatile ( \ "syscall 0\n" \ : "+r"(_arg1) \ : "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), "r"(_arg6), \ "r"(_num) \ - : "memory", "$t0", "$t1", "$t2", "$t3", \ - "$t4", "$t5", "$t6", "$t7", "$t8" \ + : _NOLIBC_SYSCALL_CLOBBERLIST \ ); \ _arg1; \ }) -char **environ __attribute__((weak)); -const unsigned long *_auxv __attribute__((weak)); - #if __loongarch_grlen == 32 -#define LONGLOG "2" -#define SZREG "4" -#define REG_L "ld.w" -#define LONG_S "st.w" -#define LONG_ADD "add.w" -#define LONG_ADDI "addi.w" -#define LONG_SLL "slli.w" #define LONG_BSTRINS "bstrins.w" #else /* __loongarch_grlen == 64 */ -#define LONGLOG "3" -#define SZREG "8" -#define REG_L "ld.d" -#define LONG_S "st.d" -#define LONG_ADD "add.d" -#define LONG_ADDI "addi.d" -#define LONG_SLL "slli.d" #define LONG_BSTRINS "bstrins.d" #endif /* startup code */ -void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) __no_stack_protector _start(void) +void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_stack_protector _start(void) { __asm__ volatile ( -#ifdef _NOLIBC_STACKPROTECTOR - "bl __stack_chk_init\n" /* initialize stack protector */ -#endif - REG_L " $a0, $sp, 0\n" /* argc (a0) was in the stack */ - LONG_ADDI " $a1, $sp, "SZREG"\n" /* argv (a1) = sp + SZREG */ - LONG_SLL " $a2, $a0, "LONGLOG"\n" /* envp (a2) = SZREG*argc ... */ - LONG_ADDI " $a2, $a2, "SZREG"\n" /* + SZREG (skip null) */ - LONG_ADD " $a2, $a2, $a1\n" /* + argv */ - - "move $a3, $a2\n" /* iterate a3 over envp to find auxv (after NULL) */ - "0:\n" /* do { */ - REG_L " $a4, $a3, 0\n" /* a4 = *a3; */ - LONG_ADDI " $a3, $a3, "SZREG"\n" /* a3 += sizeof(void*); */ - "bne $a4, $zero, 0b\n" /* } while (a4); */ - "la.pcrel $a4, _auxv\n" /* a4 = &_auxv */ - LONG_S " $a3, $a4, 0\n" /* store a3 into _auxv */ - - "la.pcrel $a3, environ\n" /* a3 = &environ */ - LONG_S " $a2, $a3, 0\n" /* store envp(a2) into environ */ - LONG_BSTRINS " $sp, $zero, 3, 0\n" /* sp must be 16-byte aligned */ - "bl main\n" /* main() returns the status code, we'll exit with it. */ - "li.w $a7, 93\n" /* NR_exit == 93 */ - "syscall 0\n" + "move $a0, $sp\n" /* save stack pointer to $a0, as arg1 of _start_c */ + LONG_BSTRINS " $sp, $zero, 3, 0\n" /* $sp must be 16-byte aligned */ + "bl _start_c\n" /* transfer to c runtime */ ); __builtin_unreachable(); } diff --git a/tools/include/nolibc/arch-mips.h b/tools/include/nolibc/arch-mips.h index db24e0837a39..4ab6fa54beee 100644 --- a/tools/include/nolibc/arch-mips.h +++ b/tools/include/nolibc/arch-mips.h @@ -8,34 +8,7 @@ #define _NOLIBC_ARCH_MIPS_H #include "compiler.h" - -/* The struct returned by the stat() syscall. 88 bytes are returned by the - * syscall. - */ -struct sys_stat_struct { - unsigned int st_dev; - long st_pad1[3]; - unsigned long st_ino; - unsigned int st_mode; - unsigned int st_nlink; - unsigned int st_uid; - unsigned int st_gid; - unsigned int st_rdev; - long st_pad2[2]; - long st_size; - long st_pad3; - - long st_atime; - long st_atime_nsec; - long st_mtime; - long st_mtime_nsec; - - long st_ctime; - long st_ctime_nsec; - long st_blksize; - long st_blocks; - long st_pad4[14]; -}; +#include "crt.h" /* Syscalls for MIPS ABI O32 : * - WARNING! there's always a delayed slot! @@ -57,19 +30,22 @@ struct sys_stat_struct { * don't have to experience issues with register constraints. */ +#define _NOLIBC_SYSCALL_CLOBBERLIST \ + "memory", "cc", "at", "v1", "hi", "lo", \ + "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" + #define my_syscall0(num) \ ({ \ register long _num __asm__ ("v0") = (num); \ register long _arg4 __asm__ ("a3"); \ - \ - __asm__ volatile ( \ + \ + __asm__ volatile ( \ "addiu $sp, $sp, -32\n" \ "syscall\n" \ "addiu $sp, $sp, 32\n" \ : "=r"(_num), "=r"(_arg4) \ : "r"(_num) \ - : "memory", "cc", "at", "v1", "hi", "lo", \ - "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \ + : _NOLIBC_SYSCALL_CLOBBERLIST \ ); \ _arg4 ? -_num : _num; \ }) @@ -79,16 +55,15 @@ struct sys_stat_struct { register long _num __asm__ ("v0") = (num); \ register long _arg1 __asm__ ("a0") = (long)(arg1); \ register long _arg4 __asm__ ("a3"); \ - \ - __asm__ volatile ( \ + \ + __asm__ volatile ( \ "addiu $sp, $sp, -32\n" \ "syscall\n" \ "addiu $sp, $sp, 32\n" \ : "=r"(_num), "=r"(_arg4) \ : "0"(_num), \ "r"(_arg1) \ - : "memory", "cc", "at", "v1", "hi", "lo", \ - "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \ + : _NOLIBC_SYSCALL_CLOBBERLIST \ ); \ _arg4 ? -_num : _num; \ }) @@ -99,16 +74,15 @@ struct sys_stat_struct { register long _arg1 __asm__ ("a0") = (long)(arg1); \ register long _arg2 __asm__ ("a1") = (long)(arg2); \ register long _arg4 __asm__ ("a3"); \ - \ - __asm__ volatile ( \ + \ + __asm__ volatile ( \ "addiu $sp, $sp, -32\n" \ "syscall\n" \ "addiu $sp, $sp, 32\n" \ : "=r"(_num), "=r"(_arg4) \ : "0"(_num), \ "r"(_arg1), "r"(_arg2) \ - : "memory", "cc", "at", "v1", "hi", "lo", \ - "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \ + : _NOLIBC_SYSCALL_CLOBBERLIST \ ); \ _arg4 ? -_num : _num; \ }) @@ -120,16 +94,15 @@ struct sys_stat_struct { register long _arg2 __asm__ ("a1") = (long)(arg2); \ register long _arg3 __asm__ ("a2") = (long)(arg3); \ register long _arg4 __asm__ ("a3"); \ - \ - __asm__ volatile ( \ + \ + __asm__ volatile ( \ "addiu $sp, $sp, -32\n" \ "syscall\n" \ "addiu $sp, $sp, 32\n" \ : "=r"(_num), "=r"(_arg4) \ : "0"(_num), \ "r"(_arg1), "r"(_arg2), "r"(_arg3) \ - : "memory", "cc", "at", "v1", "hi", "lo", \ - "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \ + : _NOLIBC_SYSCALL_CLOBBERLIST \ ); \ _arg4 ? -_num : _num; \ }) @@ -141,16 +114,15 @@ struct sys_stat_struct { register long _arg2 __asm__ ("a1") = (long)(arg2); \ register long _arg3 __asm__ ("a2") = (long)(arg3); \ register long _arg4 __asm__ ("a3") = (long)(arg4); \ - \ - __asm__ volatile ( \ + \ + __asm__ volatile ( \ "addiu $sp, $sp, -32\n" \ "syscall\n" \ "addiu $sp, $sp, 32\n" \ : "=r" (_num), "=r"(_arg4) \ : "0"(_num), \ "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4) \ - : "memory", "cc", "at", "v1", "hi", "lo", \ - "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \ + : _NOLIBC_SYSCALL_CLOBBERLIST \ ); \ _arg4 ? -_num : _num; \ }) @@ -163,65 +135,58 @@ struct sys_stat_struct { register long _arg3 __asm__ ("a2") = (long)(arg3); \ register long _arg4 __asm__ ("a3") = (long)(arg4); \ register long _arg5 = (long)(arg5); \ - \ - __asm__ volatile ( \ + \ + __asm__ volatile ( \ "addiu $sp, $sp, -32\n" \ "sw %7, 16($sp)\n" \ - "syscall\n " \ + "syscall\n" \ "addiu $sp, $sp, 32\n" \ : "=r" (_num), "=r"(_arg4) \ : "0"(_num), \ "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5) \ - : "memory", "cc", "at", "v1", "hi", "lo", \ - "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \ + : _NOLIBC_SYSCALL_CLOBBERLIST \ ); \ _arg4 ? -_num : _num; \ }) -char **environ __attribute__((weak)); -const unsigned long *_auxv __attribute__((weak)); +#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \ +({ \ + register long _num __asm__ ("v0") = (num); \ + register long _arg1 __asm__ ("a0") = (long)(arg1); \ + register long _arg2 __asm__ ("a1") = (long)(arg2); \ + register long _arg3 __asm__ ("a2") = (long)(arg3); \ + register long _arg4 __asm__ ("a3") = (long)(arg4); \ + register long _arg5 = (long)(arg5); \ + register long _arg6 = (long)(arg6); \ + \ + __asm__ volatile ( \ + "addiu $sp, $sp, -32\n" \ + "sw %7, 16($sp)\n" \ + "sw %8, 20($sp)\n" \ + "syscall\n" \ + "addiu $sp, $sp, 32\n" \ + : "=r" (_num), "=r"(_arg4) \ + : "0"(_num), \ + "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ + "r"(_arg6) \ + : _NOLIBC_SYSCALL_CLOBBERLIST \ + ); \ + _arg4 ? -_num : _num; \ +}) /* startup code, note that it's called __start on MIPS */ -void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) __no_stack_protector __start(void) +void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_stack_protector __start(void) { __asm__ volatile ( - /*".set nomips16\n"*/ ".set push\n" - ".set noreorder\n" + ".set noreorder\n" ".option pic0\n" -#ifdef _NOLIBC_STACKPROTECTOR - "jal __stack_chk_init\n" /* initialize stack protector */ - "nop\n" /* delayed slot */ -#endif - /*".ent __start\n"*/ - /*"__start:\n"*/ - "lw $a0,($sp)\n" /* argc was in the stack */ - "addiu $a1, $sp, 4\n" /* argv = sp + 4 */ - "sll $a2, $a0, 2\n" /* a2 = argc * 4 */ - "add $a2, $a2, $a1\n" /* envp = argv + 4*argc ... */ - "addiu $a2, $a2, 4\n" /* ... + 4 */ - "lui $a3, %hi(environ)\n" /* load environ into a3 (hi) */ - "addiu $a3, %lo(environ)\n" /* load environ into a3 (lo) */ - "sw $a2,($a3)\n" /* store envp(a2) into environ */ - - "move $t0, $a2\n" /* iterate t0 over envp, look for NULL */ - "0:" /* do { */ - "lw $a3, ($t0)\n" /* a3=*(t0); */ - "bne $a3, $0, 0b\n" /* } while (a3); */ - "addiu $t0, $t0, 4\n" /* delayed slot: t0+=4; */ - "lui $a3, %hi(_auxv)\n" /* load _auxv into a3 (hi) */ - "addiu $a3, %lo(_auxv)\n" /* load _auxv into a3 (lo) */ - "sw $t0, ($a3)\n" /* store t0 into _auxv */ - - "li $t0, -8\n" - "and $sp, $sp, $t0\n" /* sp must be 8-byte aligned */ - "addiu $sp,$sp,-16\n" /* the callee expects to save a0..a3 there! */ - "jal main\n" /* main() returns the status code, we'll exit with it. */ - "nop\n" /* delayed slot */ - "move $a0, $v0\n" /* retrieve 32-bit exit code from v0 */ - "li $v0, 4001\n" /* NR_exit == 4001 */ - "syscall\n" - /*".end __start\n"*/ + "move $a0, $sp\n" /* save stack pointer to $a0, as arg1 of _start_c */ + "li $t0, -8\n" + "and $sp, $sp, $t0\n" /* $sp must be 8-byte aligned */ + "addiu $sp, $sp, -16\n" /* the callee expects to save a0..a3 there */ + "jal _start_c\n" /* transfer to c runtime */ + " nop\n" /* delayed slot */ ".set pop\n" ); __builtin_unreachable(); diff --git a/tools/include/nolibc/arch-powerpc.h b/tools/include/nolibc/arch-powerpc.h new file mode 100644 index 000000000000..ac212e6185b2 --- /dev/null +++ b/tools/include/nolibc/arch-powerpc.h @@ -0,0 +1,221 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * PowerPC specific definitions for NOLIBC + * Copyright (C) 2023 Zhangjin Wu <falcon@tinylab.org> + */ + +#ifndef _NOLIBC_ARCH_POWERPC_H +#define _NOLIBC_ARCH_POWERPC_H + +#include "compiler.h" +#include "crt.h" + +/* Syscalls for PowerPC : + * - stack is 16-byte aligned + * - syscall number is passed in r0 + * - arguments are in r3, r4, r5, r6, r7, r8, r9 + * - the system call is performed by calling "sc" + * - syscall return comes in r3, and the summary overflow bit is checked + * to know if an error occurred, in which case errno is in r3. + * - the arguments are cast to long and assigned into the target + * registers which are then simply passed as registers to the asm code, + * so that we don't have to experience issues with register constraints. + */ + +#define _NOLIBC_SYSCALL_CLOBBERLIST \ + "memory", "cr0", "r12", "r11", "r10", "r9" + +#define my_syscall0(num) \ +({ \ + register long _ret __asm__ ("r3"); \ + register long _num __asm__ ("r0") = (num); \ + \ + __asm__ volatile ( \ + " sc\n" \ + " bns+ 1f\n" \ + " neg %0, %0\n" \ + "1:\n" \ + : "=r"(_ret), "+r"(_num) \ + : \ + : _NOLIBC_SYSCALL_CLOBBERLIST, "r8", "r7", "r6", "r5", "r4" \ + ); \ + _ret; \ +}) + +#define my_syscall1(num, arg1) \ +({ \ + register long _ret __asm__ ("r3"); \ + register long _num __asm__ ("r0") = (num); \ + register long _arg1 __asm__ ("r3") = (long)(arg1); \ + \ + __asm__ volatile ( \ + " sc\n" \ + " bns+ 1f\n" \ + " neg %0, %0\n" \ + "1:\n" \ + : "=r"(_ret), "+r"(_num) \ + : "0"(_arg1) \ + : _NOLIBC_SYSCALL_CLOBBERLIST, "r8", "r7", "r6", "r5", "r4" \ + ); \ + _ret; \ +}) + + +#define my_syscall2(num, arg1, arg2) \ +({ \ + register long _ret __asm__ ("r3"); \ + register long _num __asm__ ("r0") = (num); \ + register long _arg1 __asm__ ("r3") = (long)(arg1); \ + register long _arg2 __asm__ ("r4") = (long)(arg2); \ + \ + __asm__ volatile ( \ + " sc\n" \ + " bns+ 1f\n" \ + " neg %0, %0\n" \ + "1:\n" \ + : "=r"(_ret), "+r"(_num), "+r"(_arg2) \ + : "0"(_arg1) \ + : _NOLIBC_SYSCALL_CLOBBERLIST, "r8", "r7", "r6", "r5" \ + ); \ + _ret; \ +}) + + +#define my_syscall3(num, arg1, arg2, arg3) \ +({ \ + register long _ret __asm__ ("r3"); \ + register long _num __asm__ ("r0") = (num); \ + register long _arg1 __asm__ ("r3") = (long)(arg1); \ + register long _arg2 __asm__ ("r4") = (long)(arg2); \ + register long _arg3 __asm__ ("r5") = (long)(arg3); \ + \ + __asm__ volatile ( \ + " sc\n" \ + " bns+ 1f\n" \ + " neg %0, %0\n" \ + "1:\n" \ + : "=r"(_ret), "+r"(_num), "+r"(_arg2), "+r"(_arg3) \ + : "0"(_arg1) \ + : _NOLIBC_SYSCALL_CLOBBERLIST, "r8", "r7", "r6" \ + ); \ + _ret; \ +}) + + +#define my_syscall4(num, arg1, arg2, arg3, arg4) \ +({ \ + register long _ret __asm__ ("r3"); \ + register long _num __asm__ ("r0") = (num); \ + register long _arg1 __asm__ ("r3") = (long)(arg1); \ + register long _arg2 __asm__ ("r4") = (long)(arg2); \ + register long _arg3 __asm__ ("r5") = (long)(arg3); \ + register long _arg4 __asm__ ("r6") = (long)(arg4); \ + \ + __asm__ volatile ( \ + " sc\n" \ + " bns+ 1f\n" \ + " neg %0, %0\n" \ + "1:\n" \ + : "=r"(_ret), "+r"(_num), "+r"(_arg2), "+r"(_arg3), \ + "+r"(_arg4) \ + : "0"(_arg1) \ + : _NOLIBC_SYSCALL_CLOBBERLIST, "r8", "r7" \ + ); \ + _ret; \ +}) + + +#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \ +({ \ + register long _ret __asm__ ("r3"); \ + register long _num __asm__ ("r0") = (num); \ + register long _arg1 __asm__ ("r3") = (long)(arg1); \ + register long _arg2 __asm__ ("r4") = (long)(arg2); \ + register long _arg3 __asm__ ("r5") = (long)(arg3); \ + register long _arg4 __asm__ ("r6") = (long)(arg4); \ + register long _arg5 __asm__ ("r7") = (long)(arg5); \ + \ + __asm__ volatile ( \ + " sc\n" \ + " bns+ 1f\n" \ + " neg %0, %0\n" \ + "1:\n" \ + : "=r"(_ret), "+r"(_num), "+r"(_arg2), "+r"(_arg3), \ + "+r"(_arg4), "+r"(_arg5) \ + : "0"(_arg1) \ + : _NOLIBC_SYSCALL_CLOBBERLIST, "r8" \ + ); \ + _ret; \ +}) + +#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \ +({ \ + register long _ret __asm__ ("r3"); \ + register long _num __asm__ ("r0") = (num); \ + register long _arg1 __asm__ ("r3") = (long)(arg1); \ + register long _arg2 __asm__ ("r4") = (long)(arg2); \ + register long _arg3 __asm__ ("r5") = (long)(arg3); \ + register long _arg4 __asm__ ("r6") = (long)(arg4); \ + register long _arg5 __asm__ ("r7") = (long)(arg5); \ + register long _arg6 __asm__ ("r8") = (long)(arg6); \ + \ + __asm__ volatile ( \ + " sc\n" \ + " bns+ 1f\n" \ + " neg %0, %0\n" \ + "1:\n" \ + : "=r"(_ret), "+r"(_num), "+r"(_arg2), "+r"(_arg3), \ + "+r"(_arg4), "+r"(_arg5), "+r"(_arg6) \ + : "0"(_arg1) \ + : _NOLIBC_SYSCALL_CLOBBERLIST \ + ); \ + _ret; \ +}) + +#ifndef __powerpc64__ +/* FIXME: For 32-bit PowerPC, with newer gcc compilers (e.g. gcc 13.1.0), + * "omit-frame-pointer" fails with __attribute__((no_stack_protector)) but + * works with __attribute__((__optimize__("-fno-stack-protector"))) + */ +#ifdef __no_stack_protector +#undef __no_stack_protector +#define __no_stack_protector __attribute__((__optimize__("-fno-stack-protector"))) +#endif +#endif /* !__powerpc64__ */ + +/* startup code */ +void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_stack_protector _start(void) +{ +#ifdef __powerpc64__ +#if _CALL_ELF == 2 + /* with -mabi=elfv2, save TOC/GOT pointer to r2 + * r12 is global entry pointer, we use it to compute TOC from r12 + * https://www.llvm.org/devmtg/2014-04/PDFs/Talks/Euro-LLVM-2014-Weigand.pdf + * https://refspecs.linuxfoundation.org/ELF/ppc64/PPC-elf64abi.pdf + */ + __asm__ volatile ( + "addis 2, 12, .TOC. - _start@ha\n" + "addi 2, 2, .TOC. - _start@l\n" + ); +#endif /* _CALL_ELF == 2 */ + + __asm__ volatile ( + "mr 3, 1\n" /* save stack pointer to r3, as arg1 of _start_c */ + "clrrdi 1, 1, 4\n" /* align the stack to 16 bytes */ + "li 0, 0\n" /* zero the frame pointer */ + "stdu 1, -32(1)\n" /* the initial stack frame */ + "bl _start_c\n" /* transfer to c runtime */ + ); +#else + __asm__ volatile ( + "mr 3, 1\n" /* save stack pointer to r3, as arg1 of _start_c */ + "clrrwi 1, 1, 4\n" /* align the stack to 16 bytes */ + "li 0, 0\n" /* zero the frame pointer */ + "stwu 1, -16(1)\n" /* the initial stack frame */ + "bl _start_c\n" /* transfer to c runtime */ + ); +#endif + __builtin_unreachable(); +} + +#endif /* _NOLIBC_ARCH_POWERPC_H */ diff --git a/tools/include/nolibc/arch-riscv.h b/tools/include/nolibc/arch-riscv.h index a2e8564e66d6..950cc2283fd7 100644 --- a/tools/include/nolibc/arch-riscv.h +++ b/tools/include/nolibc/arch-riscv.h @@ -8,41 +8,7 @@ #define _NOLIBC_ARCH_RISCV_H #include "compiler.h" - -struct sys_stat_struct { - unsigned long st_dev; /* Device. */ - unsigned long st_ino; /* File serial number. */ - unsigned int st_mode; /* File mode. */ - unsigned int st_nlink; /* Link count. */ - unsigned int st_uid; /* User ID of the file's owner. */ - unsigned int st_gid; /* Group ID of the file's group. */ - unsigned long st_rdev; /* Device number, if device. */ - unsigned long __pad1; - long st_size; /* Size of file, in bytes. */ - int st_blksize; /* Optimal block size for I/O. */ - int __pad2; - long st_blocks; /* Number 512-byte blocks allocated. */ - long st_atime; /* Time of last access. */ - unsigned long st_atime_nsec; - long st_mtime; /* Time of last modification. */ - unsigned long st_mtime_nsec; - long st_ctime; /* Time of last status change. */ - unsigned long st_ctime_nsec; - unsigned int __unused4; - unsigned int __unused5; -}; - -#if __riscv_xlen == 64 -#define PTRLOG "3" -#define SZREG "8" -#define REG_L "ld" -#define REG_S "sd" -#elif __riscv_xlen == 32 -#define PTRLOG "2" -#define SZREG "4" -#define REG_L "lw" -#define REG_S "sw" -#endif +#include "crt.h" /* Syscalls for RISCV : * - stack is 16-byte aligned @@ -63,7 +29,7 @@ struct sys_stat_struct { register long _num __asm__ ("a7") = (num); \ register long _arg1 __asm__ ("a0"); \ \ - __asm__ volatile ( \ + __asm__ volatile ( \ "ecall\n\t" \ : "=r"(_arg1) \ : "r"(_num) \ @@ -77,7 +43,7 @@ struct sys_stat_struct { register long _num __asm__ ("a7") = (num); \ register long _arg1 __asm__ ("a0") = (long)(arg1); \ \ - __asm__ volatile ( \ + __asm__ volatile ( \ "ecall\n" \ : "+r"(_arg1) \ : "r"(_num) \ @@ -92,7 +58,7 @@ struct sys_stat_struct { register long _arg1 __asm__ ("a0") = (long)(arg1); \ register long _arg2 __asm__ ("a1") = (long)(arg2); \ \ - __asm__ volatile ( \ + __asm__ volatile ( \ "ecall\n" \ : "+r"(_arg1) \ : "r"(_arg2), \ @@ -109,7 +75,7 @@ struct sys_stat_struct { register long _arg2 __asm__ ("a1") = (long)(arg2); \ register long _arg3 __asm__ ("a2") = (long)(arg3); \ \ - __asm__ volatile ( \ + __asm__ volatile ( \ "ecall\n\t" \ : "+r"(_arg1) \ : "r"(_arg2), "r"(_arg3), \ @@ -127,7 +93,7 @@ struct sys_stat_struct { register long _arg3 __asm__ ("a2") = (long)(arg3); \ register long _arg4 __asm__ ("a3") = (long)(arg4); \ \ - __asm__ volatile ( \ + __asm__ volatile ( \ "ecall\n" \ : "+r"(_arg1) \ : "r"(_arg2), "r"(_arg3), "r"(_arg4), \ @@ -146,7 +112,7 @@ struct sys_stat_struct { register long _arg4 __asm__ ("a3") = (long)(arg4); \ register long _arg5 __asm__ ("a4") = (long)(arg5); \ \ - __asm__ volatile ( \ + __asm__ volatile ( \ "ecall\n" \ : "+r"(_arg1) \ : "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ @@ -166,7 +132,7 @@ struct sys_stat_struct { register long _arg5 __asm__ ("a4") = (long)(arg5); \ register long _arg6 __asm__ ("a5") = (long)(arg6); \ \ - __asm__ volatile ( \ + __asm__ volatile ( \ "ecall\n" \ : "+r"(_arg1) \ : "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), "r"(_arg6), \ @@ -176,40 +142,17 @@ struct sys_stat_struct { _arg1; \ }) -char **environ __attribute__((weak)); -const unsigned long *_auxv __attribute__((weak)); - /* startup code */ -void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) __no_stack_protector _start(void) +void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_stack_protector _start(void) { __asm__ volatile ( ".option push\n" ".option norelax\n" - "lla gp, __global_pointer$\n" + "lla gp, __global_pointer$\n" ".option pop\n" -#ifdef _NOLIBC_STACKPROTECTOR - "call __stack_chk_init\n" /* initialize stack protector */ -#endif - REG_L" a0, 0(sp)\n" /* argc (a0) was in the stack */ - "add a1, sp, "SZREG"\n" /* argv (a1) = sp */ - "slli a2, a0, "PTRLOG"\n" /* envp (a2) = SZREG*argc ... */ - "add a2, a2, "SZREG"\n" /* + SZREG (skip null) */ - "add a2,a2,a1\n" /* + argv */ - - "add a3, a2, zero\n" /* iterate a3 over envp to find auxv (after NULL) */ - "0:\n" /* do { */ - REG_L" a4, 0(a3)\n" /* a4 = *a3; */ - "add a3, a3, "SZREG"\n" /* a3 += sizeof(void*); */ - "bne a4, zero, 0b\n" /* } while (a4); */ - "lui a4, %hi(_auxv)\n" /* a4 = &_auxv (high bits) */ - REG_S" a3, %lo(_auxv)(a4)\n" /* store a3 into _auxv */ - - "lui a3, %hi(environ)\n" /* a3 = &environ (high bits) */ - REG_S" a2,%lo(environ)(a3)\n"/* store envp(a2) into environ */ - "andi sp,a1,-16\n" /* sp must be 16-byte aligned */ - "call main\n" /* main() returns the status code, we'll exit with it. */ - "li a7, 93\n" /* NR_exit == 93 */ - "ecall\n" + "mv a0, sp\n" /* save stack pointer to a0, as arg1 of _start_c */ + "andi sp, a0, -16\n" /* sp must be 16-byte aligned */ + "call _start_c\n" /* transfer to c runtime */ ); __builtin_unreachable(); } diff --git a/tools/include/nolibc/arch-s390.h b/tools/include/nolibc/arch-s390.h index 516dff5bff8b..5d60fd43f883 100644 --- a/tools/include/nolibc/arch-s390.h +++ b/tools/include/nolibc/arch-s390.h @@ -9,31 +9,7 @@ #include <asm/unistd.h> #include "compiler.h" - -/* The struct returned by the stat() syscall, equivalent to stat64(). The - * syscall returns 116 bytes and stops in the middle of __unused. - */ - -struct sys_stat_struct { - unsigned long st_dev; - unsigned long st_ino; - unsigned long st_nlink; - unsigned int st_mode; - unsigned int st_uid; - unsigned int st_gid; - unsigned int __pad1; - unsigned long st_rdev; - unsigned long st_size; - unsigned long st_atime; - unsigned long st_atime_nsec; - unsigned long st_mtime; - unsigned long st_mtime_nsec; - unsigned long st_ctime; - unsigned long st_ctime_nsec; - unsigned long st_blksize; - long st_blocks; - unsigned long __unused[3]; -}; +#include "crt.h" /* Syscalls for s390: * - registers are 64-bit @@ -52,7 +28,7 @@ struct sys_stat_struct { register long _num __asm__ ("1") = (num); \ register long _rc __asm__ ("2"); \ \ - __asm__ volatile ( \ + __asm__ volatile ( \ "svc 0\n" \ : "=d"(_rc) \ : "d"(_num) \ @@ -66,7 +42,7 @@ struct sys_stat_struct { register long _num __asm__ ("1") = (num); \ register long _arg1 __asm__ ("2") = (long)(arg1); \ \ - __asm__ volatile ( \ + __asm__ volatile ( \ "svc 0\n" \ : "+d"(_arg1) \ : "d"(_num) \ @@ -81,7 +57,7 @@ struct sys_stat_struct { register long _arg1 __asm__ ("2") = (long)(arg1); \ register long _arg2 __asm__ ("3") = (long)(arg2); \ \ - __asm__ volatile ( \ + __asm__ volatile ( \ "svc 0\n" \ : "+d"(_arg1) \ : "d"(_arg2), "d"(_num) \ @@ -97,7 +73,7 @@ struct sys_stat_struct { register long _arg2 __asm__ ("3") = (long)(arg2); \ register long _arg3 __asm__ ("4") = (long)(arg3); \ \ - __asm__ volatile ( \ + __asm__ volatile ( \ "svc 0\n" \ : "+d"(_arg1) \ : "d"(_arg2), "d"(_arg3), "d"(_num) \ @@ -114,7 +90,7 @@ struct sys_stat_struct { register long _arg3 __asm__ ("4") = (long)(arg3); \ register long _arg4 __asm__ ("5") = (long)(arg4); \ \ - __asm__ volatile ( \ + __asm__ volatile ( \ "svc 0\n" \ : "+d"(_arg1) \ : "d"(_arg2), "d"(_arg3), "d"(_arg4), "d"(_num) \ @@ -132,7 +108,7 @@ struct sys_stat_struct { register long _arg4 __asm__ ("5") = (long)(arg4); \ register long _arg5 __asm__ ("6") = (long)(arg5); \ \ - __asm__ volatile ( \ + __asm__ volatile ( \ "svc 0\n" \ : "+d"(_arg1) \ : "d"(_arg2), "d"(_arg3), "d"(_arg4), "d"(_arg5), \ @@ -152,7 +128,7 @@ struct sys_stat_struct { register long _arg5 __asm__ ("6") = (long)(arg5); \ register long _arg6 __asm__ ("7") = (long)(arg6); \ \ - __asm__ volatile ( \ + __asm__ volatile ( \ "svc 0\n" \ : "+d"(_arg1) \ : "d"(_arg2), "d"(_arg3), "d"(_arg4), "d"(_arg5), \ @@ -162,41 +138,14 @@ struct sys_stat_struct { _arg1; \ }) -char **environ __attribute__((weak)); -const unsigned long *_auxv __attribute__((weak)); - /* startup code */ -void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) __no_stack_protector _start(void) +void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_stack_protector _start(void) { __asm__ volatile ( - "lg %r2,0(%r15)\n" /* argument count */ - "la %r3,8(%r15)\n" /* argument pointers */ - - "xgr %r0,%r0\n" /* r0 will be our NULL value */ - /* search for envp */ - "lgr %r4,%r3\n" /* start at argv */ - "0:\n" - "clg %r0,0(%r4)\n" /* entry zero? */ - "la %r4,8(%r4)\n" /* advance pointer */ - "jnz 0b\n" /* no -> test next pointer */ - /* yes -> r4 now contains start of envp */ - "larl %r1,environ\n" - "stg %r4,0(%r1)\n" - - /* search for auxv */ - "lgr %r5,%r4\n" /* start at envp */ - "1:\n" - "clg %r0,0(%r5)\n" /* entry zero? */ - "la %r5,8(%r5)\n" /* advance pointer */ - "jnz 1b\n" /* no -> test next pointer */ - "larl %r1,_auxv\n" /* yes -> store value in _auxv */ - "stg %r5,0(%r1)\n" - - "aghi %r15,-160\n" /* allocate new stackframe */ - "xc 0(8,%r15),0(%r15)\n" /* clear backchain */ - "brasl %r14,main\n" /* ret value of main is arg to exit */ - "lghi %r1,1\n" /* __NR_exit */ - "svc 0\n" + "lgr %r2, %r15\n" /* save stack pointer to %r2, as arg1 of _start_c */ + "aghi %r15, -160\n" /* allocate new stackframe */ + "xc 0(8,%r15), 0(%r15)\n" /* clear backchain */ + "brasl %r14, _start_c\n" /* transfer to c runtime */ ); __builtin_unreachable(); } diff --git a/tools/include/nolibc/arch-x86_64.h b/tools/include/nolibc/arch-x86_64.h index 6fc4d8392742..e5ccb926c903 100644 --- a/tools/include/nolibc/arch-x86_64.h +++ b/tools/include/nolibc/arch-x86_64.h @@ -8,33 +8,7 @@ #define _NOLIBC_ARCH_X86_64_H #include "compiler.h" - -/* The struct returned by the stat() syscall, equivalent to stat64(). The - * syscall returns 116 bytes and stops in the middle of __unused. - */ -struct sys_stat_struct { - unsigned long st_dev; - unsigned long st_ino; - unsigned long st_nlink; - unsigned int st_mode; - unsigned int st_uid; - - unsigned int st_gid; - unsigned int __pad0; - unsigned long st_rdev; - long st_size; - long st_blksize; - - long st_blocks; - unsigned long st_atime; - unsigned long st_atime_nsec; - unsigned long st_mtime; - - unsigned long st_mtime_nsec; - unsigned long st_ctime; - unsigned long st_ctime_nsec; - long __unused[3]; -}; +#include "crt.h" /* Syscalls for x86_64 : * - registers are 64-bit @@ -59,8 +33,8 @@ struct sys_stat_struct { ({ \ long _ret; \ register long _num __asm__ ("rax") = (num); \ - \ - __asm__ volatile ( \ + \ + __asm__ volatile ( \ "syscall\n" \ : "=a"(_ret) \ : "0"(_num) \ @@ -74,8 +48,8 @@ struct sys_stat_struct { long _ret; \ register long _num __asm__ ("rax") = (num); \ register long _arg1 __asm__ ("rdi") = (long)(arg1); \ - \ - __asm__ volatile ( \ + \ + __asm__ volatile ( \ "syscall\n" \ : "=a"(_ret) \ : "r"(_arg1), \ @@ -91,8 +65,8 @@ struct sys_stat_struct { register long _num __asm__ ("rax") = (num); \ register long _arg1 __asm__ ("rdi") = (long)(arg1); \ register long _arg2 __asm__ ("rsi") = (long)(arg2); \ - \ - __asm__ volatile ( \ + \ + __asm__ volatile ( \ "syscall\n" \ : "=a"(_ret) \ : "r"(_arg1), "r"(_arg2), \ @@ -109,8 +83,8 @@ struct sys_stat_struct { register long _arg1 __asm__ ("rdi") = (long)(arg1); \ register long _arg2 __asm__ ("rsi") = (long)(arg2); \ register long _arg3 __asm__ ("rdx") = (long)(arg3); \ - \ - __asm__ volatile ( \ + \ + __asm__ volatile ( \ "syscall\n" \ : "=a"(_ret) \ : "r"(_arg1), "r"(_arg2), "r"(_arg3), \ @@ -128,8 +102,8 @@ struct sys_stat_struct { register long _arg2 __asm__ ("rsi") = (long)(arg2); \ register long _arg3 __asm__ ("rdx") = (long)(arg3); \ register long _arg4 __asm__ ("r10") = (long)(arg4); \ - \ - __asm__ volatile ( \ + \ + __asm__ volatile ( \ "syscall\n" \ : "=a"(_ret) \ : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \ @@ -148,8 +122,8 @@ struct sys_stat_struct { register long _arg3 __asm__ ("rdx") = (long)(arg3); \ register long _arg4 __asm__ ("r10") = (long)(arg4); \ register long _arg5 __asm__ ("r8") = (long)(arg5); \ - \ - __asm__ volatile ( \ + \ + __asm__ volatile ( \ "syscall\n" \ : "=a"(_ret) \ : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ @@ -169,8 +143,8 @@ struct sys_stat_struct { register long _arg4 __asm__ ("r10") = (long)(arg4); \ register long _arg5 __asm__ ("r8") = (long)(arg5); \ register long _arg6 __asm__ ("r9") = (long)(arg6); \ - \ - __asm__ volatile ( \ + \ + __asm__ volatile ( \ "syscall\n" \ : "=a"(_ret) \ : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ @@ -180,9 +154,6 @@ struct sys_stat_struct { _ret; \ }) -char **environ __attribute__((weak)); -const unsigned long *_auxv __attribute__((weak)); - /* startup code */ /* * x86-64 System V ABI mandates: @@ -190,29 +161,14 @@ const unsigned long *_auxv __attribute__((weak)); * 2) The deepest stack frame should be zero (the %rbp). * */ -void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) __no_stack_protector _start(void) +void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_stack_protector _start(void) { __asm__ volatile ( -#ifdef _NOLIBC_STACKPROTECTOR - "call __stack_chk_init\n" /* initialize stack protector */ -#endif - "pop %rdi\n" /* argc (first arg, %rdi) */ - "mov %rsp, %rsi\n" /* argv[] (second arg, %rsi) */ - "lea 8(%rsi,%rdi,8),%rdx\n" /* then a NULL then envp (third arg, %rdx) */ - "mov %rdx, environ\n" /* save environ */ - "xor %ebp, %ebp\n" /* zero the stack frame */ - "mov %rdx, %rax\n" /* search for auxv (follows NULL after last env) */ - "0:\n" - "add $8, %rax\n" /* search for auxv using rax, it follows the */ - "cmp -8(%rax), %rbp\n" /* ... NULL after last env (rbp is zero here) */ - "jnz 0b\n" - "mov %rax, _auxv\n" /* save it into _auxv */ - "and $-16, %rsp\n" /* x86 ABI : esp must be 16-byte aligned before call */ - "call main\n" /* main() returns the status code, we'll exit with it. */ - "mov %eax, %edi\n" /* retrieve exit code (32 bit) */ - "mov $60, %eax\n" /* NR_exit == 60 */ - "syscall\n" /* really exit */ - "hlt\n" /* ensure it does not return */ + "xor %ebp, %ebp\n" /* zero the stack frame */ + "mov %rsp, %rdi\n" /* save stack pointer to %rdi, as arg1 of _start_c */ + "and $-16, %rsp\n" /* %rsp must be 16-byte aligned before call */ + "call _start_c\n" /* transfer to c runtime */ + "hlt\n" /* ensure it does not return */ ); __builtin_unreachable(); } diff --git a/tools/include/nolibc/arch.h b/tools/include/nolibc/arch.h index 82b43935650f..e276fb0680af 100644 --- a/tools/include/nolibc/arch.h +++ b/tools/include/nolibc/arch.h @@ -25,6 +25,8 @@ #include "arch-aarch64.h" #elif defined(__mips__) && defined(_ABIO32) #include "arch-mips.h" +#elif defined(__powerpc__) +#include "arch-powerpc.h" #elif defined(__riscv) #include "arch-riscv.h" #elif defined(__s390x__) diff --git a/tools/include/nolibc/crt.h b/tools/include/nolibc/crt.h new file mode 100644 index 000000000000..a5f33fef1672 --- /dev/null +++ b/tools/include/nolibc/crt.h @@ -0,0 +1,61 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * C Run Time support for NOLIBC + * Copyright (C) 2023 Zhangjin Wu <falcon@tinylab.org> + */ + +#ifndef _NOLIBC_CRT_H +#define _NOLIBC_CRT_H + +char **environ __attribute__((weak)); +const unsigned long *_auxv __attribute__((weak)); + +static void __stack_chk_init(void); +static void exit(int); + +void _start_c(long *sp) +{ + long argc; + char **argv; + char **envp; + const unsigned long *auxv; + /* silence potential warning: conflicting types for 'main' */ + int _nolibc_main(int, char **, char **) __asm__ ("main"); + + /* initialize stack protector */ + __stack_chk_init(); + + /* + * sp : argc <-- argument count, required by main() + * argv: argv[0] <-- argument vector, required by main() + * argv[1] + * ... + * argv[argc-1] + * null + * environ: environ[0] <-- environment variables, required by main() and getenv() + * environ[1] + * ... + * null + * _auxv: _auxv[0] <-- auxiliary vector, required by getauxval() + * _auxv[1] + * ... + * null + */ + + /* assign argc and argv */ + argc = *sp; + argv = (void *)(sp + 1); + + /* find environ */ + environ = envp = argv + argc + 1; + + /* find _auxv */ + for (auxv = (void *)envp; *auxv++;) + ; + _auxv = auxv; + + /* go to application */ + exit(_nolibc_main(argc, argv, envp)); +} + +#endif /* _NOLIBC_CRT_H */ diff --git a/tools/include/nolibc/nolibc.h b/tools/include/nolibc/nolibc.h index 05a228a6ee78..1f8d821000ac 100644 --- a/tools/include/nolibc/nolibc.h +++ b/tools/include/nolibc/nolibc.h @@ -13,11 +13,10 @@ * Syscalls are split into 3 levels: * - The lower level is the arch-specific syscall() definition, consisting in * assembly code in compound expressions. These are called my_syscall0() to - * my_syscall6() depending on the number of arguments. The MIPS - * implementation is limited to 5 arguments. All input arguments are cast - * to a long stored in a register. These expressions always return the - * syscall's return value as a signed long value which is often either a - * pointer or the negated errno value. + * my_syscall6() depending on the number of arguments. All input arguments + * are castto a long stored in a register. These expressions always return + * the syscall's return value as a signed long value which is often either + * a pointer or the negated errno value. * * - The second level is mostly architecture-independent. It is made of * static functions called sys_<name>() which rely on my_syscallN() diff --git a/tools/include/nolibc/stackprotector.h b/tools/include/nolibc/stackprotector.h index 88f7b2d098ff..13f1d0e60387 100644 --- a/tools/include/nolibc/stackprotector.h +++ b/tools/include/nolibc/stackprotector.h @@ -37,14 +37,15 @@ void __stack_chk_fail_local(void) __attribute__((weak,section(".data.nolibc_stack_chk"))) uintptr_t __stack_chk_guard; -__attribute__((weak,section(".text.nolibc_stack_chk"))) __no_stack_protector -void __stack_chk_init(void) +static __no_stack_protector void __stack_chk_init(void) { my_syscall3(__NR_getrandom, &__stack_chk_guard, sizeof(__stack_chk_guard), 0); /* a bit more randomness in case getrandom() fails, ensure the guard is never 0 */ if (__stack_chk_guard != (uintptr_t) &__stack_chk_guard) __stack_chk_guard ^= (uintptr_t) &__stack_chk_guard; } +#else /* !defined(_NOLIBC_STACKPROTECTOR) */ +static void __stack_chk_init(void) {} #endif /* defined(_NOLIBC_STACKPROTECTOR) */ #endif /* _NOLIBC_STACKPROTECTOR_H */ diff --git a/tools/include/nolibc/stdint.h b/tools/include/nolibc/stdint.h index 4b282435a59a..6665e272e213 100644 --- a/tools/include/nolibc/stdint.h +++ b/tools/include/nolibc/stdint.h @@ -15,7 +15,7 @@ typedef unsigned int uint32_t; typedef signed int int32_t; typedef unsigned long long uint64_t; typedef signed long long int64_t; -typedef unsigned long size_t; +typedef __SIZE_TYPE__ size_t; typedef signed long ssize_t; typedef unsigned long uintptr_t; typedef signed long intptr_t; diff --git a/tools/include/nolibc/stdio.h b/tools/include/nolibc/stdio.h index 0eef91daf289..cae402c11e57 100644 --- a/tools/include/nolibc/stdio.h +++ b/tools/include/nolibc/stdio.h @@ -21,6 +21,11 @@ #define EOF (-1) #endif +/* Buffering mode used by setvbuf. */ +#define _IOFBF 0 /* Fully buffered. */ +#define _IOLBF 1 /* Line buffered. */ +#define _IONBF 2 /* No buffering. */ + /* just define FILE as a non-empty type. The value of the pointer gives * the FD: FILE=~fd for fd>=0 or NULL for fd<0. This way positive FILE * are immediately identified as abnormal entries (i.e. possible copies @@ -350,6 +355,28 @@ void perror(const char *msg) fprintf(stderr, "%s%serrno=%d\n", (msg && *msg) ? msg : "", (msg && *msg) ? ": " : "", errno); } +static __attribute__((unused)) +int setvbuf(FILE *stream __attribute__((unused)), + char *buf __attribute__((unused)), + int mode, + size_t size __attribute__((unused))) +{ + /* + * nolibc does not support buffering so this is a nop. Just check mode + * is valid as required by the spec. + */ + switch (mode) { + case _IOFBF: + case _IOLBF: + case _IONBF: + break; + default: + return EOF; + } + + return 0; +} + /* make sure to include all global symbols */ #include "nolibc.h" diff --git a/tools/include/nolibc/stdlib.h b/tools/include/nolibc/stdlib.h index 902162f80337..bacfd35c5156 100644 --- a/tools/include/nolibc/stdlib.h +++ b/tools/include/nolibc/stdlib.h @@ -83,11 +83,10 @@ void free(void *ptr) * declared as a char **, and must be terminated by a NULL (it is recommended * to set this variable to the "envp" argument of main()). If the requested * environment variable exists its value is returned otherwise NULL is - * returned. getenv() is forcefully inlined so that the reference to "environ" - * will be dropped if unused, even at -O0. + * returned. */ static __attribute__((unused)) -char *_getenv(const char *name, char **environ) +char *getenv(const char *name) { int idx, i; @@ -102,13 +101,6 @@ char *_getenv(const char *name, char **environ) return NULL; } -static __inline__ __attribute__((unused,always_inline)) -char *getenv(const char *name) -{ - extern char **environ; - return _getenv(name, environ); -} - static __attribute__((unused)) unsigned long getauxval(unsigned long type) { diff --git a/tools/include/nolibc/sys.h b/tools/include/nolibc/sys.h index 856249a11890..fdb6bd6c0e2f 100644 --- a/tools/include/nolibc/sys.h +++ b/tools/include/nolibc/sys.h @@ -21,7 +21,6 @@ #include <linux/auxvec.h> #include <linux/fcntl.h> /* for O_* and AT_* */ #include <linux/stat.h> /* for statx() */ -#include <linux/reboot.h> /* for LINUX_REBOOT_* */ #include <linux/prctl.h> #include "arch.h" @@ -29,6 +28,22 @@ #include "types.h" +/* Syscall return helper: takes the syscall value in argument and checks for an + * error in it. This may only be used with signed returns (int or long), but + * not with pointers. An error is any value < 0. When an error is encountered, + * -ret is set into errno and -1 is returned. Otherwise the returned value is + * passed as-is with its type preserved. + */ + +#define __sysret(arg) \ +({ \ + __typeof__(arg) __sysret_arg = (arg); \ + (__sysret_arg < 0) /* error ? */ \ + ? (({ SET_ERRNO(-__sysret_arg); }), -1) /* ret -1 with errno = -arg */ \ + : __sysret_arg; /* return original value */ \ +}) + + /* Functions in this file only describe syscalls. They're declared static so * that the compiler usually decides to inline them while still being allowed * to pass a pointer to one of their instances. Each syscall exists in two @@ -78,10 +93,10 @@ int brk(void *addr) static __attribute__((unused)) void *sbrk(intptr_t inc) { - void *ret; - /* first call to find current end */ - if ((ret = sys_brk(0)) && (sys_brk(ret + inc) == ret + inc)) + void *ret = sys_brk(0); + + if (ret && sys_brk(ret + inc) == ret + inc) return ret + inc; SET_ERRNO(ENOMEM); @@ -102,13 +117,7 @@ int sys_chdir(const char *path) static __attribute__((unused)) int chdir(const char *path) { - int ret = sys_chdir(path); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; + return __sysret(sys_chdir(path)); } @@ -124,20 +133,14 @@ int sys_chmod(const char *path, mode_t mode) #elif defined(__NR_chmod) return my_syscall2(__NR_chmod, path, mode); #else -#error Neither __NR_fchmodat nor __NR_chmod defined, cannot implement sys_chmod() + return -ENOSYS; #endif } static __attribute__((unused)) int chmod(const char *path, mode_t mode) { - int ret = sys_chmod(path, mode); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; + return __sysret(sys_chmod(path, mode)); } @@ -153,20 +156,14 @@ int sys_chown(const char *path, uid_t owner, gid_t group) #elif defined(__NR_chown) return my_syscall3(__NR_chown, path, owner, group); #else -#error Neither __NR_fchownat nor __NR_chown defined, cannot implement sys_chown() + return -ENOSYS; #endif } static __attribute__((unused)) int chown(const char *path, uid_t owner, gid_t group) { - int ret = sys_chown(path, owner, group); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; + return __sysret(sys_chown(path, owner, group)); } @@ -183,13 +180,7 @@ int sys_chroot(const char *path) static __attribute__((unused)) int chroot(const char *path) { - int ret = sys_chroot(path); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; + return __sysret(sys_chroot(path)); } @@ -206,13 +197,7 @@ int sys_close(int fd) static __attribute__((unused)) int close(int fd) { - int ret = sys_close(fd); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; + return __sysret(sys_close(fd)); } @@ -229,13 +214,7 @@ int sys_dup(int fd) static __attribute__((unused)) int dup(int fd) { - int ret = sys_dup(fd); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; + return __sysret(sys_dup(fd)); } @@ -251,20 +230,14 @@ int sys_dup2(int old, int new) #elif defined(__NR_dup2) return my_syscall2(__NR_dup2, old, new); #else -#error Neither __NR_dup3 nor __NR_dup2 defined, cannot implement sys_dup2() + return -ENOSYS; #endif } static __attribute__((unused)) int dup2(int old, int new) { - int ret = sys_dup2(old, new); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; + return __sysret(sys_dup2(old, new)); } @@ -282,13 +255,7 @@ int sys_dup3(int old, int new, int flags) static __attribute__((unused)) int dup3(int old, int new, int flags) { - int ret = sys_dup3(old, new, flags); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; + return __sysret(sys_dup3(old, new, flags)); } #endif @@ -306,13 +273,7 @@ int sys_execve(const char *filename, char *const argv[], char *const envp[]) static __attribute__((unused)) int execve(const char *filename, char *const argv[], char *const envp[]) { - int ret = sys_execve(filename, argv, envp); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; + return __sysret(sys_execve(filename, argv, envp)); } @@ -351,7 +312,7 @@ pid_t sys_fork(void) #elif defined(__NR_fork) return my_syscall0(__NR_fork); #else -#error Neither __NR_clone nor __NR_fork defined, cannot implement sys_fork() + return -ENOSYS; #endif } #endif @@ -359,13 +320,7 @@ pid_t sys_fork(void) static __attribute__((unused)) pid_t fork(void) { - pid_t ret = sys_fork(); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; + return __sysret(sys_fork()); } @@ -382,13 +337,7 @@ int sys_fsync(int fd) static __attribute__((unused)) int fsync(int fd) { - int ret = sys_fsync(fd); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; + return __sysret(sys_fsync(fd)); } @@ -405,13 +354,7 @@ int sys_getdents64(int fd, struct linux_dirent64 *dirp, int count) static __attribute__((unused)) int getdents64(int fd, struct linux_dirent64 *dirp, int count) { - int ret = sys_getdents64(fd, dirp, count); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; + return __sysret(sys_getdents64(fd, dirp, count)); } @@ -449,13 +392,7 @@ pid_t sys_getpgid(pid_t pid) static __attribute__((unused)) pid_t getpgid(pid_t pid) { - pid_t ret = sys_getpgid(pid); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; + return __sysret(sys_getpgid(pid)); } @@ -529,21 +466,13 @@ pid_t gettid(void) static unsigned long getauxval(unsigned long key); /* - * long getpagesize(void); + * int getpagesize(void); */ static __attribute__((unused)) -long getpagesize(void) +int getpagesize(void) { - long ret; - - ret = getauxval(AT_PAGESZ); - if (!ret) { - SET_ERRNO(ENOENT); - return -1; - } - - return ret; + return __sysret((int)getauxval(AT_PAGESZ) ?: -ENOENT); } @@ -554,19 +483,17 @@ long getpagesize(void) static __attribute__((unused)) int sys_gettimeofday(struct timeval *tv, struct timezone *tz) { +#ifdef __NR_gettimeofday return my_syscall2(__NR_gettimeofday, tv, tz); +#else + return -ENOSYS; +#endif } static __attribute__((unused)) int gettimeofday(struct timeval *tv, struct timezone *tz) { - int ret = sys_gettimeofday(tv, tz); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; + return __sysret(sys_gettimeofday(tv, tz)); } @@ -604,13 +531,7 @@ int sys_ioctl(int fd, unsigned long req, void *value) static __attribute__((unused)) int ioctl(int fd, unsigned long req, void *value) { - int ret = sys_ioctl(fd, req, value); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; + return __sysret(sys_ioctl(fd, req, value)); } /* @@ -626,13 +547,7 @@ int sys_kill(pid_t pid, int signal) static __attribute__((unused)) int kill(pid_t pid, int signal) { - int ret = sys_kill(pid, signal); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; + return __sysret(sys_kill(pid, signal)); } @@ -648,20 +563,14 @@ int sys_link(const char *old, const char *new) #elif defined(__NR_link) return my_syscall2(__NR_link, old, new); #else -#error Neither __NR_linkat nor __NR_link defined, cannot implement sys_link() + return -ENOSYS; #endif } static __attribute__((unused)) int link(const char *old, const char *new) { - int ret = sys_link(old, new); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; + return __sysret(sys_link(old, new)); } @@ -672,19 +581,17 @@ int link(const char *old, const char *new) static __attribute__((unused)) off_t sys_lseek(int fd, off_t offset, int whence) { +#ifdef __NR_lseek return my_syscall3(__NR_lseek, fd, offset, whence); +#else + return -ENOSYS; +#endif } static __attribute__((unused)) off_t lseek(int fd, off_t offset, int whence) { - off_t ret = sys_lseek(fd, offset, whence); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; + return __sysret(sys_lseek(fd, offset, whence)); } @@ -700,20 +607,36 @@ int sys_mkdir(const char *path, mode_t mode) #elif defined(__NR_mkdir) return my_syscall2(__NR_mkdir, path, mode); #else -#error Neither __NR_mkdirat nor __NR_mkdir defined, cannot implement sys_mkdir() + return -ENOSYS; #endif } static __attribute__((unused)) int mkdir(const char *path, mode_t mode) { - int ret = sys_mkdir(path, mode); + return __sysret(sys_mkdir(path, mode)); +} - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; +/* + * int rmdir(const char *path); + */ + +static __attribute__((unused)) +int sys_rmdir(const char *path) +{ +#ifdef __NR_rmdir + return my_syscall1(__NR_rmdir, path); +#elif defined(__NR_unlinkat) + return my_syscall3(__NR_unlinkat, AT_FDCWD, path, AT_REMOVEDIR); +#else + return -ENOSYS; +#endif +} + +static __attribute__((unused)) +int rmdir(const char *path) +{ + return __sysret(sys_rmdir(path)); } @@ -729,42 +652,21 @@ long sys_mknod(const char *path, mode_t mode, dev_t dev) #elif defined(__NR_mknod) return my_syscall3(__NR_mknod, path, mode, dev); #else -#error Neither __NR_mknodat nor __NR_mknod defined, cannot implement sys_mknod() + return -ENOSYS; #endif } static __attribute__((unused)) int mknod(const char *path, mode_t mode, dev_t dev) { - int ret = sys_mknod(path, mode, dev); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; + return __sysret(sys_mknod(path, mode, dev)); } -#ifndef MAP_SHARED -#define MAP_SHARED 0x01 /* Share changes */ -#define MAP_PRIVATE 0x02 /* Changes are private */ -#define MAP_SHARED_VALIDATE 0x03 /* share + validate extension flags */ -#endif - -#ifndef MAP_FAILED -#define MAP_FAILED ((void *)-1) -#endif - #ifndef sys_mmap static __attribute__((unused)) void *sys_mmap(void *addr, size_t length, int prot, int flags, int fd, off_t offset) { -#ifndef my_syscall6 - /* Function not implemented. */ - return (void *)-ENOSYS; -#else - int n; #if defined(__NR_mmap2) @@ -775,10 +677,14 @@ void *sys_mmap(void *addr, size_t length, int prot, int flags, int fd, #endif return (void *)my_syscall6(n, addr, length, prot, flags, fd, offset); -#endif } #endif +/* Note that on Linux, MAP_FAILED is -1 so we can use the generic __sysret() + * which returns -1 upon error and still satisfy user land that checks for + * MAP_FAILED. + */ + static __attribute__((unused)) void *mmap(void *addr, size_t length, int prot, int flags, int fd, off_t offset) { @@ -800,13 +706,7 @@ int sys_munmap(void *addr, size_t length) static __attribute__((unused)) int munmap(void *addr, size_t length) { - int ret = sys_munmap(addr, length); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; + return __sysret(sys_munmap(addr, length)); } /* @@ -826,13 +726,7 @@ int mount(const char *src, const char *tgt, const char *fst, unsigned long flags, const void *data) { - int ret = sys_mount(src, tgt, fst, flags, data); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; + return __sysret(sys_mount(src, tgt, fst, flags, data)); } @@ -848,7 +742,7 @@ int sys_open(const char *path, int flags, mode_t mode) #elif defined(__NR_open) return my_syscall3(__NR_open, path, flags, mode); #else -#error Neither __NR_openat nor __NR_open defined, cannot implement sys_open() + return -ENOSYS; #endif } @@ -856,7 +750,6 @@ static __attribute__((unused)) int open(const char *path, int flags, ...) { mode_t mode = 0; - int ret; if (flags & O_CREAT) { va_list args; @@ -866,13 +759,31 @@ int open(const char *path, int flags, ...) va_end(args); } - ret = sys_open(path, flags, mode); + return __sysret(sys_open(path, flags, mode)); +} - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; + +/* + * int pipe2(int pipefd[2], int flags); + * int pipe(int pipefd[2]); + */ + +static __attribute__((unused)) +int sys_pipe2(int pipefd[2], int flags) +{ + return my_syscall2(__NR_pipe2, pipefd, flags); +} + +static __attribute__((unused)) +int pipe2(int pipefd[2], int flags) +{ + return __sysret(sys_pipe2(pipefd, flags)); +} + +static __attribute__((unused)) +int pipe(int pipefd[2]) +{ + return pipe2(pipefd, 0); } @@ -892,13 +803,7 @@ static __attribute__((unused)) int prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5) { - int ret = sys_prctl(option, arg2, arg3, arg4, arg5); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; + return __sysret(sys_prctl(option, arg2, arg3, arg4, arg5)); } @@ -915,13 +820,7 @@ int sys_pivot_root(const char *new, const char *old) static __attribute__((unused)) int pivot_root(const char *new, const char *old) { - int ret = sys_pivot_root(new, old); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; + return __sysret(sys_pivot_root(new, old)); } @@ -943,20 +842,14 @@ int sys_poll(struct pollfd *fds, int nfds, int timeout) #elif defined(__NR_poll) return my_syscall3(__NR_poll, fds, nfds, timeout); #else -#error Neither __NR_ppoll nor __NR_poll defined, cannot implement sys_poll() + return -ENOSYS; #endif } static __attribute__((unused)) int poll(struct pollfd *fds, int nfds, int timeout) { - int ret = sys_poll(fds, nfds, timeout); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; + return __sysret(sys_poll(fds, nfds, timeout)); } @@ -973,13 +866,7 @@ ssize_t sys_read(int fd, void *buf, size_t count) static __attribute__((unused)) ssize_t read(int fd, void *buf, size_t count) { - ssize_t ret = sys_read(fd, buf, count); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; + return __sysret(sys_read(fd, buf, count)); } @@ -997,13 +884,7 @@ ssize_t sys_reboot(int magic1, int magic2, int cmd, void *arg) static __attribute__((unused)) int reboot(int cmd) { - int ret = sys_reboot(LINUX_REBOOT_MAGIC1, LINUX_REBOOT_MAGIC2, cmd, 0); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; + return __sysret(sys_reboot(LINUX_REBOOT_MAGIC1, LINUX_REBOOT_MAGIC2, cmd, 0)); } @@ -1020,13 +901,7 @@ int sys_sched_yield(void) static __attribute__((unused)) int sched_yield(void) { - int ret = sys_sched_yield(); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; + return __sysret(sys_sched_yield()); } @@ -1059,20 +934,14 @@ int sys_select(int nfds, fd_set *rfds, fd_set *wfds, fd_set *efds, struct timeva #endif return my_syscall5(__NR__newselect, nfds, rfds, wfds, efds, timeout); #else -#error None of __NR_select, __NR_pselect6, nor __NR__newselect defined, cannot implement sys_select() + return -ENOSYS; #endif } static __attribute__((unused)) int select(int nfds, fd_set *rfds, fd_set *wfds, fd_set *efds, struct timeval *timeout) { - int ret = sys_select(nfds, rfds, wfds, efds, timeout); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; + return __sysret(sys_select(nfds, rfds, wfds, efds, timeout)); } @@ -1089,13 +958,7 @@ int sys_setpgid(pid_t pid, pid_t pgid) static __attribute__((unused)) int setpgid(pid_t pid, pid_t pgid) { - int ret = sys_setpgid(pid, pgid); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; + return __sysret(sys_setpgid(pid, pgid)); } @@ -1112,55 +975,41 @@ pid_t sys_setsid(void) static __attribute__((unused)) pid_t setsid(void) { - pid_t ret = sys_setsid(); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; + return __sysret(sys_setsid()); } -#if defined(__NR_statx) /* * int statx(int fd, const char *path, int flags, unsigned int mask, struct statx *buf); + * int stat(const char *path, struct stat *buf); */ static __attribute__((unused)) int sys_statx(int fd, const char *path, int flags, unsigned int mask, struct statx *buf) { +#ifdef __NR_statx return my_syscall5(__NR_statx, fd, path, flags, mask, buf); +#else + return -ENOSYS; +#endif } static __attribute__((unused)) int statx(int fd, const char *path, int flags, unsigned int mask, struct statx *buf) { - int ret = sys_statx(fd, path, flags, mask, buf); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; + return __sysret(sys_statx(fd, path, flags, mask, buf)); } -#endif -/* - * int stat(const char *path, struct stat *buf); - * Warning: the struct stat's layout is arch-dependent. - */ -#if defined(__NR_statx) && !defined(__NR_newfstatat) && !defined(__NR_stat) -/* - * Maybe we can just use statx() when available for all architectures? - */ static __attribute__((unused)) -int sys_stat(const char *path, struct stat *buf) +int stat(const char *path, struct stat *buf) { struct statx statx; long ret; - ret = sys_statx(AT_FDCWD, path, AT_NO_AUTOMOUNT, STATX_BASIC_STATS, &statx); + ret = __sysret(sys_statx(AT_FDCWD, path, AT_NO_AUTOMOUNT, STATX_BASIC_STATS, &statx)); + if (ret == -1) + return ret; + buf->st_dev = ((statx.stx_dev_minor & 0xff) | (statx.stx_dev_major << 8) | ((statx.stx_dev_minor & ~0xff) << 12)); @@ -1181,53 +1030,8 @@ int sys_stat(const char *path, struct stat *buf) buf->st_mtim.tv_nsec = statx.stx_mtime.tv_nsec; buf->st_ctim.tv_sec = statx.stx_ctime.tv_sec; buf->st_ctim.tv_nsec = statx.stx_ctime.tv_nsec; - return ret; -} -#else -static __attribute__((unused)) -int sys_stat(const char *path, struct stat *buf) -{ - struct sys_stat_struct stat; - long ret; - -#ifdef __NR_newfstatat - /* only solution for arm64 */ - ret = my_syscall4(__NR_newfstatat, AT_FDCWD, path, &stat, 0); -#elif defined(__NR_stat) - ret = my_syscall2(__NR_stat, path, &stat); -#else -#error Neither __NR_newfstatat nor __NR_stat defined, cannot implement sys_stat() -#endif - buf->st_dev = stat.st_dev; - buf->st_ino = stat.st_ino; - buf->st_mode = stat.st_mode; - buf->st_nlink = stat.st_nlink; - buf->st_uid = stat.st_uid; - buf->st_gid = stat.st_gid; - buf->st_rdev = stat.st_rdev; - buf->st_size = stat.st_size; - buf->st_blksize = stat.st_blksize; - buf->st_blocks = stat.st_blocks; - buf->st_atim.tv_sec = stat.st_atime; - buf->st_atim.tv_nsec = stat.st_atime_nsec; - buf->st_mtim.tv_sec = stat.st_mtime; - buf->st_mtim.tv_nsec = stat.st_mtime_nsec; - buf->st_ctim.tv_sec = stat.st_ctime; - buf->st_ctim.tv_nsec = stat.st_ctime_nsec; - return ret; -} -#endif -static __attribute__((unused)) -int stat(const char *path, struct stat *buf) -{ - int ret = sys_stat(path, buf); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; + return 0; } @@ -1243,20 +1047,14 @@ int sys_symlink(const char *old, const char *new) #elif defined(__NR_symlink) return my_syscall2(__NR_symlink, old, new); #else -#error Neither __NR_symlinkat nor __NR_symlink defined, cannot implement sys_symlink() + return -ENOSYS; #endif } static __attribute__((unused)) int symlink(const char *old, const char *new) { - int ret = sys_symlink(old, new); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; + return __sysret(sys_symlink(old, new)); } @@ -1290,13 +1088,7 @@ int sys_umount2(const char *path, int flags) static __attribute__((unused)) int umount2(const char *path, int flags) { - int ret = sys_umount2(path, flags); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; + return __sysret(sys_umount2(path, flags)); } @@ -1312,20 +1104,14 @@ int sys_unlink(const char *path) #elif defined(__NR_unlink) return my_syscall1(__NR_unlink, path); #else -#error Neither __NR_unlinkat nor __NR_unlink defined, cannot implement sys_unlink() + return -ENOSYS; #endif } static __attribute__((unused)) int unlink(const char *path) { - int ret = sys_unlink(path); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; + return __sysret(sys_unlink(path)); } @@ -1338,44 +1124,30 @@ int unlink(const char *path) static __attribute__((unused)) pid_t sys_wait4(pid_t pid, int *status, int options, struct rusage *rusage) { +#ifdef __NR_wait4 return my_syscall4(__NR_wait4, pid, status, options, rusage); +#else + return -ENOSYS; +#endif } static __attribute__((unused)) pid_t wait(int *status) { - pid_t ret = sys_wait4(-1, status, 0, NULL); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; + return __sysret(sys_wait4(-1, status, 0, NULL)); } static __attribute__((unused)) pid_t wait4(pid_t pid, int *status, int options, struct rusage *rusage) { - pid_t ret = sys_wait4(pid, status, options, rusage); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; + return __sysret(sys_wait4(pid, status, options, rusage)); } static __attribute__((unused)) pid_t waitpid(pid_t pid, int *status, int options) { - pid_t ret = sys_wait4(pid, status, options, NULL); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; + return __sysret(sys_wait4(pid, status, options, NULL)); } @@ -1392,13 +1164,7 @@ ssize_t sys_write(int fd, const void *buf, size_t count) static __attribute__((unused)) ssize_t write(int fd, const void *buf, size_t count) { - ssize_t ret = sys_write(fd, buf, count); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; + return __sysret(sys_write(fd, buf, count)); } @@ -1415,13 +1181,7 @@ int sys_memfd_create(const char *name, unsigned int flags) static __attribute__((unused)) int memfd_create(const char *name, unsigned int flags) { - ssize_t ret = sys_memfd_create(name, flags); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; + return __sysret(sys_memfd_create(name, flags)); } /* make sure to include all global symbols */ diff --git a/tools/include/nolibc/types.h b/tools/include/nolibc/types.h index f96e28bff4ba..8cfc4c860fa4 100644 --- a/tools/include/nolibc/types.h +++ b/tools/include/nolibc/types.h @@ -8,13 +8,15 @@ #define _NOLIBC_TYPES_H #include "std.h" -#include <linux/time.h> +#include <linux/mman.h> +#include <linux/reboot.h> /* for LINUX_REBOOT_* */ #include <linux/stat.h> +#include <linux/time.h> /* Only the generic macros and types may be defined here. The arch-specific - * ones such as the O_RDONLY and related macros used by fcntl() and open(), or - * the layout of sys_stat_struct must not be defined here. + * ones such as the O_RDONLY and related macros used by fcntl() and open() + * must not be defined here. */ /* stat flags (WARNING, octal here). We need to check for an existing @@ -81,11 +83,25 @@ #define MAXPATHLEN (PATH_MAX) #endif +/* flags for mmap */ +#ifndef MAP_FAILED +#define MAP_FAILED ((void *)-1) +#endif + /* whence values for lseek() */ #define SEEK_SET 0 #define SEEK_CUR 1 #define SEEK_END 2 +/* flags for reboot */ +#define RB_AUTOBOOT LINUX_REBOOT_CMD_RESTART +#define RB_HALT_SYSTEM LINUX_REBOOT_CMD_HALT +#define RB_ENABLE_CAD LINUX_REBOOT_CMD_CAD_ON +#define RB_DISABLE_CAD LINUX_REBOOT_CMD_CAD_OFF +#define RB_POWER_OFF LINUX_REBOOT_CMD_POWER_OFF +#define RB_SW_SUSPEND LINUX_REBOOT_CMD_SW_SUSPEND +#define RB_KEXEC LINUX_REBOOT_CMD_KEXEC + /* Macros used on waitpid()'s return status */ #define WEXITSTATUS(status) (((status) & 0xff00) >> 8) #define WIFEXITED(status) (((status) & 0x7f) == 0) diff --git a/tools/include/nolibc/unistd.h b/tools/include/nolibc/unistd.h index 0e832e10a0b2..e38f3660c051 100644 --- a/tools/include/nolibc/unistd.h +++ b/tools/include/nolibc/unistd.h @@ -56,18 +56,9 @@ int tcsetpgrp(int fd, pid_t pid) return ioctl(fd, TIOCSPGRP, &pid); } -#define _syscall(N, ...) \ -({ \ - long _ret = my_syscall##N(__VA_ARGS__); \ - if (_ret < 0) { \ - SET_ERRNO(-_ret); \ - _ret = -1; \ - } \ - _ret; \ -}) - -#define _syscall_narg(...) __syscall_narg(__VA_ARGS__, 6, 5, 4, 3, 2, 1, 0) #define __syscall_narg(_0, _1, _2, _3, _4, _5, _6, N, ...) N +#define _syscall_narg(...) __syscall_narg(__VA_ARGS__, 6, 5, 4, 3, 2, 1, 0) +#define _syscall(N, ...) __sysret(my_syscall##N(__VA_ARGS__)) #define _syscall_n(N, ...) _syscall(N, __VA_ARGS__) #define syscall(...) _syscall_n(_syscall_narg(__VA_ARGS__), ##__VA_ARGS__) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 60a9d59beeab..8790b3962e4b 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -19,6 +19,7 @@ /* ld/ldx fields */ #define BPF_DW 0x18 /* double word (64-bit) */ +#define BPF_MEMSX 0x80 /* load with sign extension */ #define BPF_ATOMIC 0xc0 /* atomic memory ops - op type in immediate */ #define BPF_XADD 0xc0 /* exclusive add - legacy name */ @@ -1036,6 +1037,9 @@ enum bpf_attach_type { BPF_LSM_CGROUP, BPF_STRUCT_OPS, BPF_NETFILTER, + BPF_TCX_INGRESS, + BPF_TCX_EGRESS, + BPF_TRACE_UPROBE_MULTI, __MAX_BPF_ATTACH_TYPE }; @@ -1053,10 +1057,21 @@ enum bpf_link_type { BPF_LINK_TYPE_KPROBE_MULTI = 8, BPF_LINK_TYPE_STRUCT_OPS = 9, BPF_LINK_TYPE_NETFILTER = 10, - + BPF_LINK_TYPE_TCX = 11, + BPF_LINK_TYPE_UPROBE_MULTI = 12, MAX_BPF_LINK_TYPE, }; +enum bpf_perf_event_type { + BPF_PERF_EVENT_UNSPEC = 0, + BPF_PERF_EVENT_UPROBE = 1, + BPF_PERF_EVENT_URETPROBE = 2, + BPF_PERF_EVENT_KPROBE = 3, + BPF_PERF_EVENT_KRETPROBE = 4, + BPF_PERF_EVENT_TRACEPOINT = 5, + BPF_PERF_EVENT_EVENT = 6, +}; + /* cgroup-bpf attach flags used in BPF_PROG_ATTACH command * * NONE(default): No further bpf programs allowed in the subtree. @@ -1103,7 +1118,12 @@ enum bpf_link_type { */ #define BPF_F_ALLOW_OVERRIDE (1U << 0) #define BPF_F_ALLOW_MULTI (1U << 1) +/* Generic attachment flags. */ #define BPF_F_REPLACE (1U << 2) +#define BPF_F_BEFORE (1U << 3) +#define BPF_F_AFTER (1U << 4) +#define BPF_F_ID (1U << 5) +#define BPF_F_LINK BPF_F_LINK /* 1 << 13 */ /* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the * verifier will perform strict alignment checking as if the kernel @@ -1168,7 +1188,21 @@ enum bpf_link_type { /* link_create.kprobe_multi.flags used in LINK_CREATE command for * BPF_TRACE_KPROBE_MULTI attach type to create return probe. */ -#define BPF_F_KPROBE_MULTI_RETURN (1U << 0) +enum { + BPF_F_KPROBE_MULTI_RETURN = (1U << 0) +}; + +/* link_create.uprobe_multi.flags used in LINK_CREATE command for + * BPF_TRACE_UPROBE_MULTI attach type to create return probe. + */ +enum { + BPF_F_UPROBE_MULTI_RETURN = (1U << 0) +}; + +/* link_create.netfilter.flags used in LINK_CREATE command for + * BPF_PROG_TYPE_NETFILTER to enable IP packet defragmentation. + */ +#define BPF_F_NETFILTER_IP_DEFRAG (1U << 0) /* When BPF ldimm64's insn[0].src_reg != 0 then this can have * the following extensions: @@ -1434,14 +1468,19 @@ union bpf_attr { }; struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */ - __u32 target_fd; /* container object to attach to */ - __u32 attach_bpf_fd; /* eBPF program to attach */ + union { + __u32 target_fd; /* target object to attach to or ... */ + __u32 target_ifindex; /* target ifindex */ + }; + __u32 attach_bpf_fd; __u32 attach_type; __u32 attach_flags; - __u32 replace_bpf_fd; /* previously attached eBPF - * program to replace if - * BPF_F_REPLACE is used - */ + __u32 replace_bpf_fd; + union { + __u32 relative_fd; + __u32 relative_id; + }; + __u64 expected_revision; }; struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */ @@ -1487,16 +1526,26 @@ union bpf_attr { } info; struct { /* anonymous struct used by BPF_PROG_QUERY command */ - __u32 target_fd; /* container object to query */ + union { + __u32 target_fd; /* target object to query or ... */ + __u32 target_ifindex; /* target ifindex */ + }; __u32 attach_type; __u32 query_flags; __u32 attach_flags; __aligned_u64 prog_ids; - __u32 prog_cnt; + union { + __u32 prog_cnt; + __u32 count; + }; + __u32 :32; /* output: per-program attach_flags. * not allowed to be set during effective query. */ __aligned_u64 prog_attach_flags; + __aligned_u64 link_ids; + __aligned_u64 link_attach_flags; + __u64 revision; } query; struct { /* anonymous struct used by BPF_RAW_TRACEPOINT_OPEN command */ @@ -1539,13 +1588,13 @@ union bpf_attr { __u32 map_fd; /* struct_ops to attach */ }; union { - __u32 target_fd; /* object to attach to */ - __u32 target_ifindex; /* target ifindex */ + __u32 target_fd; /* target object to attach to or ... */ + __u32 target_ifindex; /* target ifindex */ }; __u32 attach_type; /* attach type */ __u32 flags; /* extra flags */ union { - __u32 target_btf_id; /* btf_id of target to attach to */ + __u32 target_btf_id; /* btf_id of target to attach to */ struct { __aligned_u64 iter_info; /* extra bpf_iter_link_info */ __u32 iter_info_len; /* iter_info length */ @@ -1579,6 +1628,22 @@ union bpf_attr { __s32 priority; __u32 flags; } netfilter; + struct { + union { + __u32 relative_fd; + __u32 relative_id; + }; + __u64 expected_revision; + } tcx; + struct { + __aligned_u64 path; + __aligned_u64 offsets; + __aligned_u64 ref_ctr_offsets; + __aligned_u64 cookies; + __u32 cnt; + __u32 flags; + __u32 pid; + } uprobe_multi; }; } link_create; @@ -4159,9 +4224,6 @@ union bpf_attr { * **-EOPNOTSUPP** if the operation is not supported, for example * a call from outside of TC ingress. * - * **-ESOCKTNOSUPPORT** if the socket type is not supported - * (reuseport). - * * long bpf_sk_assign(struct bpf_sk_lookup *ctx, struct bpf_sock *sk, u64 flags) * Description * Helper is overloaded depending on BPF program type. This @@ -5044,9 +5106,14 @@ union bpf_attr { * u64 bpf_get_func_ip(void *ctx) * Description * Get address of the traced function (for tracing and kprobe programs). + * + * When called for kprobe program attached as uprobe it returns + * probe address for both entry and return uprobe. + * * Return - * Address of the traced function. + * Address of the traced function for kprobe. * 0 for kprobes placed within the function (not at the entry). + * Address of the probe for uprobe and return uprobe. * * u64 bpf_get_attach_cookie(void *ctx) * Description @@ -6187,6 +6254,19 @@ struct bpf_sock_tuple { }; }; +/* (Simplified) user return codes for tcx prog type. + * A valid tcx program must return one of these defined values. All other + * return codes are reserved for future use. Must remain compatible with + * their TC_ACT_* counter-parts. For compatibility in behavior, unknown + * return codes are mapped to TCX_NEXT. + */ +enum tcx_action_base { + TCX_NEXT = -1, + TCX_PASS = 0, + TCX_DROP = 2, + TCX_REDIRECT = 7, +}; + struct bpf_xdp_sock { __u32 queue_id; }; @@ -6439,6 +6519,40 @@ struct bpf_link_info { __s32 priority; __u32 flags; } netfilter; + struct { + __aligned_u64 addrs; + __u32 count; /* in/out: kprobe_multi function count */ + __u32 flags; + } kprobe_multi; + struct { + __u32 type; /* enum bpf_perf_event_type */ + __u32 :32; + union { + struct { + __aligned_u64 file_name; /* in/out */ + __u32 name_len; + __u32 offset; /* offset from file_name */ + } uprobe; /* BPF_PERF_EVENT_UPROBE, BPF_PERF_EVENT_URETPROBE */ + struct { + __aligned_u64 func_name; /* in/out */ + __u32 name_len; + __u32 offset; /* offset from func_name */ + __u64 addr; + } kprobe; /* BPF_PERF_EVENT_KPROBE, BPF_PERF_EVENT_KRETPROBE */ + struct { + __aligned_u64 tp_name; /* in/out */ + __u32 name_len; + } tracepoint; /* BPF_PERF_EVENT_TRACEPOINT */ + struct { + __u64 config; + __u32 type; + } event; /* BPF_PERF_EVENT_EVENT */ + }; + } perf_event; + struct { + __u32 ifindex; + __u32 attach_type; + } tcx; }; } __attribute__((aligned(8))); @@ -7012,6 +7126,7 @@ struct bpf_list_head { struct bpf_list_node { __u64 :64; __u64 :64; + __u64 :64; } __attribute__((aligned(8))); struct bpf_rb_root { @@ -7023,6 +7138,7 @@ struct bpf_rb_node { __u64 :64; __u64 :64; __u64 :64; + __u64 :64; } __attribute__((aligned(8))); struct bpf_refcount { diff --git a/tools/include/uapi/linux/if_xdp.h b/tools/include/uapi/linux/if_xdp.h index a78a8096f4ce..73a47da885dc 100644 --- a/tools/include/uapi/linux/if_xdp.h +++ b/tools/include/uapi/linux/if_xdp.h @@ -25,6 +25,12 @@ * application. */ #define XDP_USE_NEED_WAKEUP (1 << 3) +/* By setting this option, userspace application indicates that it can + * handle multiple descriptors per packet thus enabling xsk core to split + * multi-buffer XDP frames into multiple Rx descriptors. Without this set + * such frames will be dropped by xsk. + */ +#define XDP_USE_SG (1 << 4) /* Flags for xsk_umem_config flags */ #define XDP_UMEM_UNALIGNED_CHUNK_FLAG (1 << 0) @@ -106,6 +112,9 @@ struct xdp_desc { __u32 options; }; +/* Flag indicating packet constitutes of multiple buffers*/ +#define XDP_PKT_CONTD (1 << 0) + /* UMEM descriptor is __u64 */ #endif /* _LINUX_IF_XDP_H */ diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index 639524b59930..c1634b95c223 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -11,7 +11,7 @@ /** * enum netdev_xdp_act - * @NETDEV_XDP_ACT_BASIC: XDP feautues set supported by all drivers + * @NETDEV_XDP_ACT_BASIC: XDP features set supported by all drivers * (XDP_ABORTED, XDP_DROP, XDP_PASS, XDP_TX) * @NETDEV_XDP_ACT_REDIRECT: The netdev supports XDP_REDIRECT * @NETDEV_XDP_ACT_NDO_XMIT: This feature informs if netdev implements @@ -34,6 +34,7 @@ enum netdev_xdp_act { NETDEV_XDP_ACT_RX_SG = 32, NETDEV_XDP_ACT_NDO_XMIT_SG = 64, + /* private: */ NETDEV_XDP_ACT_MASK = 127, }; @@ -41,6 +42,7 @@ enum { NETDEV_A_DEV_IFINDEX = 1, NETDEV_A_DEV_PAD, NETDEV_A_DEV_XDP_FEATURES, + NETDEV_A_DEV_XDP_ZC_MAX_SEGS, __NETDEV_A_DEV_MAX, NETDEV_A_DEV_MAX = (__NETDEV_A_DEV_MAX - 1) diff --git a/tools/io_uring/Makefile b/tools/io_uring/Makefile deleted file mode 100644 index 00f146c54c53..000000000000 --- a/tools/io_uring/Makefile +++ /dev/null @@ -1,18 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -# Makefile for io_uring test tools -CFLAGS += -Wall -Wextra -g -D_GNU_SOURCE -LDLIBS += -lpthread - -all: io_uring-cp io_uring-bench -%: %.c - $(CC) $(CFLAGS) -o $@ $^ - -io_uring-bench: syscall.o io_uring-bench.o - $(CC) $(CFLAGS) -o $@ $^ $(LDLIBS) - -io_uring-cp: setup.o syscall.o queue.o - -clean: - $(RM) io_uring-cp io_uring-bench *.o - -.PHONY: all clean diff --git a/tools/io_uring/README b/tools/io_uring/README deleted file mode 100644 index 67fd70115cff..000000000000 --- a/tools/io_uring/README +++ /dev/null @@ -1,29 +0,0 @@ -This directory includes a few programs that demonstrate how to use io_uring -in an application. The examples are: - -io_uring-cp - A very basic io_uring implementation of cp(1). It takes two - arguments, copies the first argument to the second. This example - is part of liburing, and hence uses the simplified liburing API - for setting up an io_uring instance, submitting IO, completing IO, - etc. The support functions in queue.c and setup.c are straight - out of liburing. - -io_uring-bench - Benchmark program that does random reads on a number of files. This - app demonstrates the various features of io_uring, like fixed files, - fixed buffers, and polled IO. There are options in the program to - control which features to use. Arguments is the file (or files) that - io_uring-bench should operate on. This uses the raw io_uring - interface. - -liburing can be cloned with git here: - - git://git.kernel.dk/liburing - -and contains a number of unit tests as well for testing io_uring. It also -comes with man pages for the three system calls. - -Fio includes an io_uring engine, you can clone fio here: - - git://git.kernel.dk/fio diff --git a/tools/io_uring/barrier.h b/tools/io_uring/barrier.h deleted file mode 100644 index ef00f6722ba9..000000000000 --- a/tools/io_uring/barrier.h +++ /dev/null @@ -1,16 +0,0 @@ -#ifndef LIBURING_BARRIER_H -#define LIBURING_BARRIER_H - -#if defined(__x86_64) || defined(__i386__) -#define read_barrier() __asm__ __volatile__("":::"memory") -#define write_barrier() __asm__ __volatile__("":::"memory") -#else -/* - * Add arch appropriate definitions. Be safe and use full barriers for - * archs we don't have support for. - */ -#define read_barrier() __sync_synchronize() -#define write_barrier() __sync_synchronize() -#endif - -#endif diff --git a/tools/io_uring/io_uring-bench.c b/tools/io_uring/io_uring-bench.c deleted file mode 100644 index 7703f0118385..000000000000 --- a/tools/io_uring/io_uring-bench.c +++ /dev/null @@ -1,592 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Simple benchmark program that uses the various features of io_uring - * to provide fast random access to a device/file. It has various - * options that are control how we use io_uring, see the OPTIONS section - * below. This uses the raw io_uring interface. - * - * Copyright (C) 2018-2019 Jens Axboe - */ -#include <stdio.h> -#include <errno.h> -#include <assert.h> -#include <stdlib.h> -#include <stddef.h> -#include <signal.h> -#include <inttypes.h> - -#include <sys/types.h> -#include <sys/stat.h> -#include <sys/ioctl.h> -#include <sys/syscall.h> -#include <sys/resource.h> -#include <sys/mman.h> -#include <sys/uio.h> -#include <linux/fs.h> -#include <fcntl.h> -#include <unistd.h> -#include <string.h> -#include <pthread.h> -#include <sched.h> - -#include "liburing.h" -#include "barrier.h" - -#define min(a, b) ((a < b) ? (a) : (b)) - -struct io_sq_ring { - unsigned *head; - unsigned *tail; - unsigned *ring_mask; - unsigned *ring_entries; - unsigned *flags; - unsigned *array; -}; - -struct io_cq_ring { - unsigned *head; - unsigned *tail; - unsigned *ring_mask; - unsigned *ring_entries; - struct io_uring_cqe *cqes; -}; - -#define DEPTH 128 - -#define BATCH_SUBMIT 32 -#define BATCH_COMPLETE 32 - -#define BS 4096 - -#define MAX_FDS 16 - -static unsigned sq_ring_mask, cq_ring_mask; - -struct file { - unsigned long max_blocks; - unsigned pending_ios; - int real_fd; - int fixed_fd; -}; - -struct submitter { - pthread_t thread; - int ring_fd; - struct drand48_data rand; - struct io_sq_ring sq_ring; - struct io_uring_sqe *sqes; - struct iovec iovecs[DEPTH]; - struct io_cq_ring cq_ring; - int inflight; - unsigned long reaps; - unsigned long done; - unsigned long calls; - volatile int finish; - - __s32 *fds; - - struct file files[MAX_FDS]; - unsigned nr_files; - unsigned cur_file; -}; - -static struct submitter submitters[1]; -static volatile int finish; - -/* - * OPTIONS: Set these to test the various features of io_uring. - */ -static int polled = 1; /* use IO polling */ -static int fixedbufs = 1; /* use fixed user buffers */ -static int register_files = 1; /* use fixed files */ -static int buffered = 0; /* use buffered IO, not O_DIRECT */ -static int sq_thread_poll = 0; /* use kernel submission/poller thread */ -static int sq_thread_cpu = -1; /* pin above thread to this CPU */ -static int do_nop = 0; /* no-op SQ ring commands */ - -static int io_uring_register_buffers(struct submitter *s) -{ - if (do_nop) - return 0; - - return io_uring_register(s->ring_fd, IORING_REGISTER_BUFFERS, s->iovecs, - DEPTH); -} - -static int io_uring_register_files(struct submitter *s) -{ - unsigned i; - - if (do_nop) - return 0; - - s->fds = calloc(s->nr_files, sizeof(__s32)); - for (i = 0; i < s->nr_files; i++) { - s->fds[i] = s->files[i].real_fd; - s->files[i].fixed_fd = i; - } - - return io_uring_register(s->ring_fd, IORING_REGISTER_FILES, s->fds, - s->nr_files); -} - -static int lk_gettid(void) -{ - return syscall(__NR_gettid); -} - -static unsigned file_depth(struct submitter *s) -{ - return (DEPTH + s->nr_files - 1) / s->nr_files; -} - -static void init_io(struct submitter *s, unsigned index) -{ - struct io_uring_sqe *sqe = &s->sqes[index]; - unsigned long offset; - struct file *f; - long r; - - if (do_nop) { - sqe->opcode = IORING_OP_NOP; - return; - } - - if (s->nr_files == 1) { - f = &s->files[0]; - } else { - f = &s->files[s->cur_file]; - if (f->pending_ios >= file_depth(s)) { - s->cur_file++; - if (s->cur_file == s->nr_files) - s->cur_file = 0; - f = &s->files[s->cur_file]; - } - } - f->pending_ios++; - - lrand48_r(&s->rand, &r); - offset = (r % (f->max_blocks - 1)) * BS; - - if (register_files) { - sqe->flags = IOSQE_FIXED_FILE; - sqe->fd = f->fixed_fd; - } else { - sqe->flags = 0; - sqe->fd = f->real_fd; - } - if (fixedbufs) { - sqe->opcode = IORING_OP_READ_FIXED; - sqe->addr = (unsigned long) s->iovecs[index].iov_base; - sqe->len = BS; - sqe->buf_index = index; - } else { - sqe->opcode = IORING_OP_READV; - sqe->addr = (unsigned long) &s->iovecs[index]; - sqe->len = 1; - sqe->buf_index = 0; - } - sqe->ioprio = 0; - sqe->off = offset; - sqe->user_data = (unsigned long) f; -} - -static int prep_more_ios(struct submitter *s, unsigned max_ios) -{ - struct io_sq_ring *ring = &s->sq_ring; - unsigned index, tail, next_tail, prepped = 0; - - next_tail = tail = *ring->tail; - do { - next_tail++; - read_barrier(); - if (next_tail == *ring->head) - break; - - index = tail & sq_ring_mask; - init_io(s, index); - ring->array[index] = index; - prepped++; - tail = next_tail; - } while (prepped < max_ios); - - if (*ring->tail != tail) { - /* order tail store with writes to sqes above */ - write_barrier(); - *ring->tail = tail; - write_barrier(); - } - return prepped; -} - -static int get_file_size(struct file *f) -{ - struct stat st; - - if (fstat(f->real_fd, &st) < 0) - return -1; - if (S_ISBLK(st.st_mode)) { - unsigned long long bytes; - - if (ioctl(f->real_fd, BLKGETSIZE64, &bytes) != 0) - return -1; - - f->max_blocks = bytes / BS; - return 0; - } else if (S_ISREG(st.st_mode)) { - f->max_blocks = st.st_size / BS; - return 0; - } - - return -1; -} - -static int reap_events(struct submitter *s) -{ - struct io_cq_ring *ring = &s->cq_ring; - struct io_uring_cqe *cqe; - unsigned head, reaped = 0; - - head = *ring->head; - do { - struct file *f; - - read_barrier(); - if (head == *ring->tail) - break; - cqe = &ring->cqes[head & cq_ring_mask]; - if (!do_nop) { - f = (struct file *) (uintptr_t) cqe->user_data; - f->pending_ios--; - if (cqe->res != BS) { - printf("io: unexpected ret=%d\n", cqe->res); - if (polled && cqe->res == -EOPNOTSUPP) - printf("Your filesystem doesn't support poll\n"); - return -1; - } - } - reaped++; - head++; - } while (1); - - s->inflight -= reaped; - *ring->head = head; - write_barrier(); - return reaped; -} - -static void *submitter_fn(void *data) -{ - struct submitter *s = data; - struct io_sq_ring *ring = &s->sq_ring; - int ret, prepped; - - printf("submitter=%d\n", lk_gettid()); - - srand48_r(pthread_self(), &s->rand); - - prepped = 0; - do { - int to_wait, to_submit, this_reap, to_prep; - - if (!prepped && s->inflight < DEPTH) { - to_prep = min(DEPTH - s->inflight, BATCH_SUBMIT); - prepped = prep_more_ios(s, to_prep); - } - s->inflight += prepped; -submit_more: - to_submit = prepped; -submit: - if (to_submit && (s->inflight + to_submit <= DEPTH)) - to_wait = 0; - else - to_wait = min(s->inflight + to_submit, BATCH_COMPLETE); - - /* - * Only need to call io_uring_enter if we're not using SQ thread - * poll, or if IORING_SQ_NEED_WAKEUP is set. - */ - if (!sq_thread_poll || (*ring->flags & IORING_SQ_NEED_WAKEUP)) { - unsigned flags = 0; - - if (to_wait) - flags = IORING_ENTER_GETEVENTS; - if ((*ring->flags & IORING_SQ_NEED_WAKEUP)) - flags |= IORING_ENTER_SQ_WAKEUP; - ret = io_uring_enter(s->ring_fd, to_submit, to_wait, - flags, NULL); - s->calls++; - } - - /* - * For non SQ thread poll, we already got the events we needed - * through the io_uring_enter() above. For SQ thread poll, we - * need to loop here until we find enough events. - */ - this_reap = 0; - do { - int r; - r = reap_events(s); - if (r == -1) { - s->finish = 1; - break; - } else if (r > 0) - this_reap += r; - } while (sq_thread_poll && this_reap < to_wait); - s->reaps += this_reap; - - if (ret >= 0) { - if (!ret) { - to_submit = 0; - if (s->inflight) - goto submit; - continue; - } else if (ret < to_submit) { - int diff = to_submit - ret; - - s->done += ret; - prepped -= diff; - goto submit_more; - } - s->done += ret; - prepped = 0; - continue; - } else if (ret < 0) { - if (errno == EAGAIN) { - if (s->finish) - break; - if (this_reap) - goto submit; - to_submit = 0; - goto submit; - } - printf("io_submit: %s\n", strerror(errno)); - break; - } - } while (!s->finish); - - finish = 1; - return NULL; -} - -static void sig_int(int sig) -{ - printf("Exiting on signal %d\n", sig); - submitters[0].finish = 1; - finish = 1; -} - -static void arm_sig_int(void) -{ - struct sigaction act; - - memset(&act, 0, sizeof(act)); - act.sa_handler = sig_int; - act.sa_flags = SA_RESTART; - sigaction(SIGINT, &act, NULL); -} - -static int setup_ring(struct submitter *s) -{ - struct io_sq_ring *sring = &s->sq_ring; - struct io_cq_ring *cring = &s->cq_ring; - struct io_uring_params p; - int ret, fd; - void *ptr; - - memset(&p, 0, sizeof(p)); - - if (polled && !do_nop) - p.flags |= IORING_SETUP_IOPOLL; - if (sq_thread_poll) { - p.flags |= IORING_SETUP_SQPOLL; - if (sq_thread_cpu != -1) { - p.flags |= IORING_SETUP_SQ_AFF; - p.sq_thread_cpu = sq_thread_cpu; - } - } - - fd = io_uring_setup(DEPTH, &p); - if (fd < 0) { - perror("io_uring_setup"); - return 1; - } - s->ring_fd = fd; - - if (fixedbufs) { - ret = io_uring_register_buffers(s); - if (ret < 0) { - perror("io_uring_register_buffers"); - return 1; - } - } - - if (register_files) { - ret = io_uring_register_files(s); - if (ret < 0) { - perror("io_uring_register_files"); - return 1; - } - } - - ptr = mmap(0, p.sq_off.array + p.sq_entries * sizeof(__u32), - PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE, fd, - IORING_OFF_SQ_RING); - printf("sq_ring ptr = 0x%p\n", ptr); - sring->head = ptr + p.sq_off.head; - sring->tail = ptr + p.sq_off.tail; - sring->ring_mask = ptr + p.sq_off.ring_mask; - sring->ring_entries = ptr + p.sq_off.ring_entries; - sring->flags = ptr + p.sq_off.flags; - sring->array = ptr + p.sq_off.array; - sq_ring_mask = *sring->ring_mask; - - s->sqes = mmap(0, p.sq_entries * sizeof(struct io_uring_sqe), - PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE, fd, - IORING_OFF_SQES); - printf("sqes ptr = 0x%p\n", s->sqes); - - ptr = mmap(0, p.cq_off.cqes + p.cq_entries * sizeof(struct io_uring_cqe), - PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE, fd, - IORING_OFF_CQ_RING); - printf("cq_ring ptr = 0x%p\n", ptr); - cring->head = ptr + p.cq_off.head; - cring->tail = ptr + p.cq_off.tail; - cring->ring_mask = ptr + p.cq_off.ring_mask; - cring->ring_entries = ptr + p.cq_off.ring_entries; - cring->cqes = ptr + p.cq_off.cqes; - cq_ring_mask = *cring->ring_mask; - return 0; -} - -static void file_depths(char *buf) -{ - struct submitter *s = &submitters[0]; - unsigned i; - char *p; - - buf[0] = '\0'; - p = buf; - for (i = 0; i < s->nr_files; i++) { - struct file *f = &s->files[i]; - - if (i + 1 == s->nr_files) - p += sprintf(p, "%d", f->pending_ios); - else - p += sprintf(p, "%d, ", f->pending_ios); - } -} - -int main(int argc, char *argv[]) -{ - struct submitter *s = &submitters[0]; - unsigned long done, calls, reap; - int err, i, flags, fd; - char *fdepths; - void *ret; - - if (!do_nop && argc < 2) { - printf("%s: filename\n", argv[0]); - return 1; - } - - flags = O_RDONLY | O_NOATIME; - if (!buffered) - flags |= O_DIRECT; - - i = 1; - while (!do_nop && i < argc) { - struct file *f; - - if (s->nr_files == MAX_FDS) { - printf("Max number of files (%d) reached\n", MAX_FDS); - break; - } - fd = open(argv[i], flags); - if (fd < 0) { - perror("open"); - return 1; - } - - f = &s->files[s->nr_files]; - f->real_fd = fd; - if (get_file_size(f)) { - printf("failed getting size of device/file\n"); - return 1; - } - if (f->max_blocks <= 1) { - printf("Zero file/device size?\n"); - return 1; - } - f->max_blocks--; - - printf("Added file %s\n", argv[i]); - s->nr_files++; - i++; - } - - if (fixedbufs) { - struct rlimit rlim; - - rlim.rlim_cur = RLIM_INFINITY; - rlim.rlim_max = RLIM_INFINITY; - if (setrlimit(RLIMIT_MEMLOCK, &rlim) < 0) { - perror("setrlimit"); - return 1; - } - } - - arm_sig_int(); - - for (i = 0; i < DEPTH; i++) { - void *buf; - - if (posix_memalign(&buf, BS, BS)) { - printf("failed alloc\n"); - return 1; - } - s->iovecs[i].iov_base = buf; - s->iovecs[i].iov_len = BS; - } - - err = setup_ring(s); - if (err) { - printf("ring setup failed: %s, %d\n", strerror(errno), err); - return 1; - } - printf("polled=%d, fixedbufs=%d, buffered=%d", polled, fixedbufs, buffered); - printf(" QD=%d, sq_ring=%d, cq_ring=%d\n", DEPTH, *s->sq_ring.ring_entries, *s->cq_ring.ring_entries); - - pthread_create(&s->thread, NULL, submitter_fn, s); - - fdepths = malloc(8 * s->nr_files); - reap = calls = done = 0; - do { - unsigned long this_done = 0; - unsigned long this_reap = 0; - unsigned long this_call = 0; - unsigned long rpc = 0, ipc = 0; - - sleep(1); - this_done += s->done; - this_call += s->calls; - this_reap += s->reaps; - if (this_call - calls) { - rpc = (this_done - done) / (this_call - calls); - ipc = (this_reap - reap) / (this_call - calls); - } else - rpc = ipc = -1; - file_depths(fdepths); - printf("IOPS=%lu, IOS/call=%ld/%ld, inflight=%u (%s)\n", - this_done - done, rpc, ipc, s->inflight, - fdepths); - done = this_done; - calls = this_call; - reap = this_reap; - } while (!finish); - - pthread_join(s->thread, &ret); - close(s->ring_fd); - free(fdepths); - return 0; -} diff --git a/tools/io_uring/io_uring-cp.c b/tools/io_uring/io_uring-cp.c deleted file mode 100644 index d9bd6f5f8f46..000000000000 --- a/tools/io_uring/io_uring-cp.c +++ /dev/null @@ -1,283 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Simple test program that demonstrates a file copy through io_uring. This - * uses the API exposed by liburing. - * - * Copyright (C) 2018-2019 Jens Axboe - */ -#include <stdio.h> -#include <fcntl.h> -#include <string.h> -#include <stdlib.h> -#include <unistd.h> -#include <assert.h> -#include <errno.h> -#include <inttypes.h> -#include <sys/types.h> -#include <sys/stat.h> -#include <sys/ioctl.h> - -#include "liburing.h" - -#define QD 64 -#define BS (32*1024) - -static int infd, outfd; - -struct io_data { - int read; - off_t first_offset, offset; - size_t first_len; - struct iovec iov; -}; - -static int setup_context(unsigned entries, struct io_uring *ring) -{ - int ret; - - ret = io_uring_queue_init(entries, ring, 0); - if (ret < 0) { - fprintf(stderr, "queue_init: %s\n", strerror(-ret)); - return -1; - } - - return 0; -} - -static int get_file_size(int fd, off_t *size) -{ - struct stat st; - - if (fstat(fd, &st) < 0) - return -1; - if (S_ISREG(st.st_mode)) { - *size = st.st_size; - return 0; - } else if (S_ISBLK(st.st_mode)) { - unsigned long long bytes; - - if (ioctl(fd, BLKGETSIZE64, &bytes) != 0) - return -1; - - *size = bytes; - return 0; - } - - return -1; -} - -static void queue_prepped(struct io_uring *ring, struct io_data *data) -{ - struct io_uring_sqe *sqe; - - sqe = io_uring_get_sqe(ring); - assert(sqe); - - if (data->read) - io_uring_prep_readv(sqe, infd, &data->iov, 1, data->offset); - else - io_uring_prep_writev(sqe, outfd, &data->iov, 1, data->offset); - - io_uring_sqe_set_data(sqe, data); -} - -static int queue_read(struct io_uring *ring, off_t size, off_t offset) -{ - struct io_uring_sqe *sqe; - struct io_data *data; - - data = malloc(size + sizeof(*data)); - if (!data) - return 1; - - sqe = io_uring_get_sqe(ring); - if (!sqe) { - free(data); - return 1; - } - - data->read = 1; - data->offset = data->first_offset = offset; - - data->iov.iov_base = data + 1; - data->iov.iov_len = size; - data->first_len = size; - - io_uring_prep_readv(sqe, infd, &data->iov, 1, offset); - io_uring_sqe_set_data(sqe, data); - return 0; -} - -static void queue_write(struct io_uring *ring, struct io_data *data) -{ - data->read = 0; - data->offset = data->first_offset; - - data->iov.iov_base = data + 1; - data->iov.iov_len = data->first_len; - - queue_prepped(ring, data); - io_uring_submit(ring); -} - -static int copy_file(struct io_uring *ring, off_t insize) -{ - unsigned long reads, writes; - struct io_uring_cqe *cqe; - off_t write_left, offset; - int ret; - - write_left = insize; - writes = reads = offset = 0; - - while (insize || write_left) { - int had_reads, got_comp; - - /* - * Queue up as many reads as we can - */ - had_reads = reads; - while (insize) { - off_t this_size = insize; - - if (reads + writes >= QD) - break; - if (this_size > BS) - this_size = BS; - else if (!this_size) - break; - - if (queue_read(ring, this_size, offset)) - break; - - insize -= this_size; - offset += this_size; - reads++; - } - - if (had_reads != reads) { - ret = io_uring_submit(ring); - if (ret < 0) { - fprintf(stderr, "io_uring_submit: %s\n", strerror(-ret)); - break; - } - } - - /* - * Queue is full at this point. Find at least one completion. - */ - got_comp = 0; - while (write_left) { - struct io_data *data; - - if (!got_comp) { - ret = io_uring_wait_cqe(ring, &cqe); - got_comp = 1; - } else { - ret = io_uring_peek_cqe(ring, &cqe); - if (ret == -EAGAIN) { - cqe = NULL; - ret = 0; - } - } - if (ret < 0) { - fprintf(stderr, "io_uring_peek_cqe: %s\n", - strerror(-ret)); - return 1; - } - if (!cqe) - break; - - data = io_uring_cqe_get_data(cqe); - if (cqe->res < 0) { - if (cqe->res == -EAGAIN) { - queue_prepped(ring, data); - io_uring_cqe_seen(ring, cqe); - continue; - } - fprintf(stderr, "cqe failed: %s\n", - strerror(-cqe->res)); - return 1; - } else if (cqe->res != data->iov.iov_len) { - /* Short read/write, adjust and requeue */ - data->iov.iov_base += cqe->res; - data->iov.iov_len -= cqe->res; - data->offset += cqe->res; - queue_prepped(ring, data); - io_uring_cqe_seen(ring, cqe); - continue; - } - - /* - * All done. if write, nothing else to do. if read, - * queue up corresponding write. - */ - if (data->read) { - queue_write(ring, data); - write_left -= data->first_len; - reads--; - writes++; - } else { - free(data); - writes--; - } - io_uring_cqe_seen(ring, cqe); - } - } - - /* wait out pending writes */ - while (writes) { - struct io_data *data; - - ret = io_uring_wait_cqe(ring, &cqe); - if (ret) { - fprintf(stderr, "wait_cqe=%d\n", ret); - return 1; - } - if (cqe->res < 0) { - fprintf(stderr, "write res=%d\n", cqe->res); - return 1; - } - data = io_uring_cqe_get_data(cqe); - free(data); - writes--; - io_uring_cqe_seen(ring, cqe); - } - - return 0; -} - -int main(int argc, char *argv[]) -{ - struct io_uring ring; - off_t insize; - int ret; - - if (argc < 3) { - printf("%s: infile outfile\n", argv[0]); - return 1; - } - - infd = open(argv[1], O_RDONLY); - if (infd < 0) { - perror("open infile"); - return 1; - } - outfd = open(argv[2], O_WRONLY | O_CREAT | O_TRUNC, 0644); - if (outfd < 0) { - perror("open outfile"); - return 1; - } - - if (setup_context(QD, &ring)) - return 1; - if (get_file_size(infd, &insize)) - return 1; - - ret = copy_file(&ring, insize); - - close(infd); - close(outfd); - io_uring_queue_exit(&ring); - return ret; -} diff --git a/tools/io_uring/liburing.h b/tools/io_uring/liburing.h deleted file mode 100644 index 28a837b6069d..000000000000 --- a/tools/io_uring/liburing.h +++ /dev/null @@ -1,187 +0,0 @@ -#ifndef LIB_URING_H -#define LIB_URING_H - -#ifdef __cplusplus -extern "C" { -#endif - -#include <sys/uio.h> -#include <signal.h> -#include <string.h> -#include "../../include/uapi/linux/io_uring.h" -#include <inttypes.h> -#include <linux/swab.h> -#include "barrier.h" - -/* - * Library interface to io_uring - */ -struct io_uring_sq { - unsigned *khead; - unsigned *ktail; - unsigned *kring_mask; - unsigned *kring_entries; - unsigned *kflags; - unsigned *kdropped; - unsigned *array; - struct io_uring_sqe *sqes; - - unsigned sqe_head; - unsigned sqe_tail; - - size_t ring_sz; -}; - -struct io_uring_cq { - unsigned *khead; - unsigned *ktail; - unsigned *kring_mask; - unsigned *kring_entries; - unsigned *koverflow; - struct io_uring_cqe *cqes; - - size_t ring_sz; -}; - -struct io_uring { - struct io_uring_sq sq; - struct io_uring_cq cq; - int ring_fd; -}; - -/* - * System calls - */ -extern int io_uring_setup(unsigned entries, struct io_uring_params *p); -extern int io_uring_enter(int fd, unsigned to_submit, - unsigned min_complete, unsigned flags, sigset_t *sig); -extern int io_uring_register(int fd, unsigned int opcode, void *arg, - unsigned int nr_args); - -/* - * Library interface - */ -extern int io_uring_queue_init(unsigned entries, struct io_uring *ring, - unsigned flags); -extern int io_uring_queue_mmap(int fd, struct io_uring_params *p, - struct io_uring *ring); -extern void io_uring_queue_exit(struct io_uring *ring); -extern int io_uring_peek_cqe(struct io_uring *ring, - struct io_uring_cqe **cqe_ptr); -extern int io_uring_wait_cqe(struct io_uring *ring, - struct io_uring_cqe **cqe_ptr); -extern int io_uring_submit(struct io_uring *ring); -extern struct io_uring_sqe *io_uring_get_sqe(struct io_uring *ring); - -/* - * Must be called after io_uring_{peek,wait}_cqe() after the cqe has - * been processed by the application. - */ -static inline void io_uring_cqe_seen(struct io_uring *ring, - struct io_uring_cqe *cqe) -{ - if (cqe) { - struct io_uring_cq *cq = &ring->cq; - - (*cq->khead)++; - /* - * Ensure that the kernel sees our new head, the kernel has - * the matching read barrier. - */ - write_barrier(); - } -} - -/* - * Command prep helpers - */ -static inline void io_uring_sqe_set_data(struct io_uring_sqe *sqe, void *data) -{ - sqe->user_data = (unsigned long) data; -} - -static inline void *io_uring_cqe_get_data(struct io_uring_cqe *cqe) -{ - return (void *) (uintptr_t) cqe->user_data; -} - -static inline void io_uring_prep_rw(int op, struct io_uring_sqe *sqe, int fd, - const void *addr, unsigned len, - off_t offset) -{ - memset(sqe, 0, sizeof(*sqe)); - sqe->opcode = op; - sqe->fd = fd; - sqe->off = offset; - sqe->addr = (unsigned long) addr; - sqe->len = len; -} - -static inline void io_uring_prep_readv(struct io_uring_sqe *sqe, int fd, - const struct iovec *iovecs, - unsigned nr_vecs, off_t offset) -{ - io_uring_prep_rw(IORING_OP_READV, sqe, fd, iovecs, nr_vecs, offset); -} - -static inline void io_uring_prep_read_fixed(struct io_uring_sqe *sqe, int fd, - void *buf, unsigned nbytes, - off_t offset) -{ - io_uring_prep_rw(IORING_OP_READ_FIXED, sqe, fd, buf, nbytes, offset); -} - -static inline void io_uring_prep_writev(struct io_uring_sqe *sqe, int fd, - const struct iovec *iovecs, - unsigned nr_vecs, off_t offset) -{ - io_uring_prep_rw(IORING_OP_WRITEV, sqe, fd, iovecs, nr_vecs, offset); -} - -static inline void io_uring_prep_write_fixed(struct io_uring_sqe *sqe, int fd, - const void *buf, unsigned nbytes, - off_t offset) -{ - io_uring_prep_rw(IORING_OP_WRITE_FIXED, sqe, fd, buf, nbytes, offset); -} - -static inline void io_uring_prep_poll_add(struct io_uring_sqe *sqe, int fd, - unsigned poll_mask) -{ - memset(sqe, 0, sizeof(*sqe)); - sqe->opcode = IORING_OP_POLL_ADD; - sqe->fd = fd; -#if __BYTE_ORDER == __BIG_ENDIAN - poll_mask = __swahw32(poll_mask); -#endif - sqe->poll_events = poll_mask; -} - -static inline void io_uring_prep_poll_remove(struct io_uring_sqe *sqe, - void *user_data) -{ - memset(sqe, 0, sizeof(*sqe)); - sqe->opcode = IORING_OP_POLL_REMOVE; - sqe->addr = (unsigned long) user_data; -} - -static inline void io_uring_prep_fsync(struct io_uring_sqe *sqe, int fd, - unsigned fsync_flags) -{ - memset(sqe, 0, sizeof(*sqe)); - sqe->opcode = IORING_OP_FSYNC; - sqe->fd = fd; - sqe->fsync_flags = fsync_flags; -} - -static inline void io_uring_prep_nop(struct io_uring_sqe *sqe) -{ - memset(sqe, 0, sizeof(*sqe)); - sqe->opcode = IORING_OP_NOP; -} - -#ifdef __cplusplus -} -#endif - -#endif diff --git a/tools/io_uring/queue.c b/tools/io_uring/queue.c deleted file mode 100644 index 321819c132c7..000000000000 --- a/tools/io_uring/queue.c +++ /dev/null @@ -1,156 +0,0 @@ -#include <sys/types.h> -#include <sys/stat.h> -#include <sys/mman.h> -#include <unistd.h> -#include <errno.h> -#include <string.h> - -#include "liburing.h" -#include "barrier.h" - -static int __io_uring_get_cqe(struct io_uring *ring, - struct io_uring_cqe **cqe_ptr, int wait) -{ - struct io_uring_cq *cq = &ring->cq; - const unsigned mask = *cq->kring_mask; - unsigned head; - int ret; - - *cqe_ptr = NULL; - head = *cq->khead; - do { - /* - * It's necessary to use a read_barrier() before reading - * the CQ tail, since the kernel updates it locklessly. The - * kernel has the matching store barrier for the update. The - * kernel also ensures that previous stores to CQEs are ordered - * with the tail update. - */ - read_barrier(); - if (head != *cq->ktail) { - *cqe_ptr = &cq->cqes[head & mask]; - break; - } - if (!wait) - break; - ret = io_uring_enter(ring->ring_fd, 0, 1, - IORING_ENTER_GETEVENTS, NULL); - if (ret < 0) - return -errno; - } while (1); - - return 0; -} - -/* - * Return an IO completion, if one is readily available. Returns 0 with - * cqe_ptr filled in on success, -errno on failure. - */ -int io_uring_peek_cqe(struct io_uring *ring, struct io_uring_cqe **cqe_ptr) -{ - return __io_uring_get_cqe(ring, cqe_ptr, 0); -} - -/* - * Return an IO completion, waiting for it if necessary. Returns 0 with - * cqe_ptr filled in on success, -errno on failure. - */ -int io_uring_wait_cqe(struct io_uring *ring, struct io_uring_cqe **cqe_ptr) -{ - return __io_uring_get_cqe(ring, cqe_ptr, 1); -} - -/* - * Submit sqes acquired from io_uring_get_sqe() to the kernel. - * - * Returns number of sqes submitted - */ -int io_uring_submit(struct io_uring *ring) -{ - struct io_uring_sq *sq = &ring->sq; - const unsigned mask = *sq->kring_mask; - unsigned ktail, ktail_next, submitted, to_submit; - int ret; - - /* - * If we have pending IO in the kring, submit it first. We need a - * read barrier here to match the kernels store barrier when updating - * the SQ head. - */ - read_barrier(); - if (*sq->khead != *sq->ktail) { - submitted = *sq->kring_entries; - goto submit; - } - - if (sq->sqe_head == sq->sqe_tail) - return 0; - - /* - * Fill in sqes that we have queued up, adding them to the kernel ring - */ - submitted = 0; - ktail = ktail_next = *sq->ktail; - to_submit = sq->sqe_tail - sq->sqe_head; - while (to_submit--) { - ktail_next++; - read_barrier(); - - sq->array[ktail & mask] = sq->sqe_head & mask; - ktail = ktail_next; - - sq->sqe_head++; - submitted++; - } - - if (!submitted) - return 0; - - if (*sq->ktail != ktail) { - /* - * First write barrier ensures that the SQE stores are updated - * with the tail update. This is needed so that the kernel - * will never see a tail update without the preceeding sQE - * stores being done. - */ - write_barrier(); - *sq->ktail = ktail; - /* - * The kernel has the matching read barrier for reading the - * SQ tail. - */ - write_barrier(); - } - -submit: - ret = io_uring_enter(ring->ring_fd, submitted, 0, - IORING_ENTER_GETEVENTS, NULL); - if (ret < 0) - return -errno; - - return ret; -} - -/* - * Return an sqe to fill. Application must later call io_uring_submit() - * when it's ready to tell the kernel about it. The caller may call this - * function multiple times before calling io_uring_submit(). - * - * Returns a vacant sqe, or NULL if we're full. - */ -struct io_uring_sqe *io_uring_get_sqe(struct io_uring *ring) -{ - struct io_uring_sq *sq = &ring->sq; - unsigned next = sq->sqe_tail + 1; - struct io_uring_sqe *sqe; - - /* - * All sqes are used - */ - if (next - sq->sqe_head > *sq->kring_entries) - return NULL; - - sqe = &sq->sqes[sq->sqe_tail & *sq->kring_mask]; - sq->sqe_tail = next; - return sqe; -} diff --git a/tools/io_uring/setup.c b/tools/io_uring/setup.c deleted file mode 100644 index 0b50fcd78520..000000000000 --- a/tools/io_uring/setup.c +++ /dev/null @@ -1,107 +0,0 @@ -#include <sys/types.h> -#include <sys/stat.h> -#include <sys/mman.h> -#include <unistd.h> -#include <errno.h> -#include <string.h> - -#include "liburing.h" - -static int io_uring_mmap(int fd, struct io_uring_params *p, - struct io_uring_sq *sq, struct io_uring_cq *cq) -{ - size_t size; - void *ptr; - int ret; - - sq->ring_sz = p->sq_off.array + p->sq_entries * sizeof(unsigned); - ptr = mmap(0, sq->ring_sz, PROT_READ | PROT_WRITE, - MAP_SHARED | MAP_POPULATE, fd, IORING_OFF_SQ_RING); - if (ptr == MAP_FAILED) - return -errno; - sq->khead = ptr + p->sq_off.head; - sq->ktail = ptr + p->sq_off.tail; - sq->kring_mask = ptr + p->sq_off.ring_mask; - sq->kring_entries = ptr + p->sq_off.ring_entries; - sq->kflags = ptr + p->sq_off.flags; - sq->kdropped = ptr + p->sq_off.dropped; - sq->array = ptr + p->sq_off.array; - - size = p->sq_entries * sizeof(struct io_uring_sqe); - sq->sqes = mmap(0, size, PROT_READ | PROT_WRITE, - MAP_SHARED | MAP_POPULATE, fd, - IORING_OFF_SQES); - if (sq->sqes == MAP_FAILED) { - ret = -errno; -err: - munmap(sq->khead, sq->ring_sz); - return ret; - } - - cq->ring_sz = p->cq_off.cqes + p->cq_entries * sizeof(struct io_uring_cqe); - ptr = mmap(0, cq->ring_sz, PROT_READ | PROT_WRITE, - MAP_SHARED | MAP_POPULATE, fd, IORING_OFF_CQ_RING); - if (ptr == MAP_FAILED) { - ret = -errno; - munmap(sq->sqes, p->sq_entries * sizeof(struct io_uring_sqe)); - goto err; - } - cq->khead = ptr + p->cq_off.head; - cq->ktail = ptr + p->cq_off.tail; - cq->kring_mask = ptr + p->cq_off.ring_mask; - cq->kring_entries = ptr + p->cq_off.ring_entries; - cq->koverflow = ptr + p->cq_off.overflow; - cq->cqes = ptr + p->cq_off.cqes; - return 0; -} - -/* - * For users that want to specify sq_thread_cpu or sq_thread_idle, this - * interface is a convenient helper for mmap()ing the rings. - * Returns -1 on error, or zero on success. On success, 'ring' - * contains the necessary information to read/write to the rings. - */ -int io_uring_queue_mmap(int fd, struct io_uring_params *p, struct io_uring *ring) -{ - int ret; - - memset(ring, 0, sizeof(*ring)); - ret = io_uring_mmap(fd, p, &ring->sq, &ring->cq); - if (!ret) - ring->ring_fd = fd; - return ret; -} - -/* - * Returns -1 on error, or zero on success. On success, 'ring' - * contains the necessary information to read/write to the rings. - */ -int io_uring_queue_init(unsigned entries, struct io_uring *ring, unsigned flags) -{ - struct io_uring_params p; - int fd, ret; - - memset(&p, 0, sizeof(p)); - p.flags = flags; - - fd = io_uring_setup(entries, &p); - if (fd < 0) - return fd; - - ret = io_uring_queue_mmap(fd, &p, ring); - if (ret) - close(fd); - - return ret; -} - -void io_uring_queue_exit(struct io_uring *ring) -{ - struct io_uring_sq *sq = &ring->sq; - struct io_uring_cq *cq = &ring->cq; - - munmap(sq->sqes, *sq->kring_entries * sizeof(struct io_uring_sqe)); - munmap(sq->khead, sq->ring_sz); - munmap(cq->khead, cq->ring_sz); - close(ring->ring_fd); -} diff --git a/tools/io_uring/syscall.c b/tools/io_uring/syscall.c deleted file mode 100644 index b22e0aa54e9d..000000000000 --- a/tools/io_uring/syscall.c +++ /dev/null @@ -1,52 +0,0 @@ -/* - * Will go away once libc support is there - */ -#include <unistd.h> -#include <sys/syscall.h> -#include <sys/uio.h> -#include <signal.h> -#include "liburing.h" - -#ifdef __alpha__ -/* - * alpha is the only exception, all other architectures - * have common numbers for new system calls. - */ -# ifndef __NR_io_uring_setup -# define __NR_io_uring_setup 535 -# endif -# ifndef __NR_io_uring_enter -# define __NR_io_uring_enter 536 -# endif -# ifndef __NR_io_uring_register -# define __NR_io_uring_register 537 -# endif -#else /* !__alpha__ */ -# ifndef __NR_io_uring_setup -# define __NR_io_uring_setup 425 -# endif -# ifndef __NR_io_uring_enter -# define __NR_io_uring_enter 426 -# endif -# ifndef __NR_io_uring_register -# define __NR_io_uring_register 427 -# endif -#endif - -int io_uring_register(int fd, unsigned int opcode, void *arg, - unsigned int nr_args) -{ - return syscall(__NR_io_uring_register, fd, opcode, arg, nr_args); -} - -int io_uring_setup(unsigned int entries, struct io_uring_params *p) -{ - return syscall(__NR_io_uring_setup, entries, p); -} - -int io_uring_enter(int fd, unsigned int to_submit, unsigned int min_complete, - unsigned int flags, sigset_t *sig) -{ - return syscall(__NR_io_uring_enter, fd, to_submit, min_complete, - flags, sig, _NSIG / 8); -} diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build index b8b0a6369363..2d0c282c8588 100644 --- a/tools/lib/bpf/Build +++ b/tools/lib/bpf/Build @@ -1,4 +1,4 @@ libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o \ netlink.o bpf_prog_linfo.o libbpf_probes.o hashmap.o \ btf_dump.o ringbuf.o strset.o linker.o gen_loader.o relo_core.o \ - usdt.o zip.o + usdt.o zip.o elf.o diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index cf7f02c67968..4be7144e4803 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -293,11 +293,11 @@ help: @echo ' HINT: use "V=1" to enable verbose build' @echo ' all - build libraries and pkgconfig' @echo ' clean - remove all generated files' - @echo ' check - check abi and version info' + @echo ' check - check ABI and version info' @echo '' @echo 'libbpf install targets:' @echo ' HINT: use "prefix"(defaults to "/usr/local") or "DESTDIR" (defaults to "/")' - @echo ' to adjust target desitantion, e.g. "make prefix=/usr/local install"' + @echo ' to adjust target destination, e.g. "make prefix=/usr/local install"' @echo ' install - build and install all headers, libraries and pkgconfig' @echo ' install_headers - install only headers to include/bpf' @echo '' diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index ed86b37d8024..b0f1913763a3 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -629,55 +629,89 @@ int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type, return bpf_prog_attach_opts(prog_fd, target_fd, type, &opts); } -int bpf_prog_attach_opts(int prog_fd, int target_fd, - enum bpf_attach_type type, - const struct bpf_prog_attach_opts *opts) +int bpf_prog_attach_opts(int prog_fd, int target, enum bpf_attach_type type, + const struct bpf_prog_attach_opts *opts) { - const size_t attr_sz = offsetofend(union bpf_attr, replace_bpf_fd); + const size_t attr_sz = offsetofend(union bpf_attr, expected_revision); + __u32 relative_id, flags; + int ret, relative_fd; union bpf_attr attr; - int ret; if (!OPTS_VALID(opts, bpf_prog_attach_opts)) return libbpf_err(-EINVAL); + relative_id = OPTS_GET(opts, relative_id, 0); + relative_fd = OPTS_GET(opts, relative_fd, 0); + flags = OPTS_GET(opts, flags, 0); + + /* validate we don't have unexpected combinations of non-zero fields */ + if (relative_fd && relative_id) + return libbpf_err(-EINVAL); + memset(&attr, 0, attr_sz); - attr.target_fd = target_fd; - attr.attach_bpf_fd = prog_fd; - attr.attach_type = type; - attr.attach_flags = OPTS_GET(opts, flags, 0); - attr.replace_bpf_fd = OPTS_GET(opts, replace_prog_fd, 0); + attr.target_fd = target; + attr.attach_bpf_fd = prog_fd; + attr.attach_type = type; + attr.replace_bpf_fd = OPTS_GET(opts, replace_fd, 0); + attr.expected_revision = OPTS_GET(opts, expected_revision, 0); + + if (relative_id) { + attr.attach_flags = flags | BPF_F_ID; + attr.relative_id = relative_id; + } else { + attr.attach_flags = flags; + attr.relative_fd = relative_fd; + } ret = sys_bpf(BPF_PROG_ATTACH, &attr, attr_sz); return libbpf_err_errno(ret); } -int bpf_prog_detach(int target_fd, enum bpf_attach_type type) +int bpf_prog_detach_opts(int prog_fd, int target, enum bpf_attach_type type, + const struct bpf_prog_detach_opts *opts) { - const size_t attr_sz = offsetofend(union bpf_attr, replace_bpf_fd); + const size_t attr_sz = offsetofend(union bpf_attr, expected_revision); + __u32 relative_id, flags; + int ret, relative_fd; union bpf_attr attr; - int ret; + + if (!OPTS_VALID(opts, bpf_prog_detach_opts)) + return libbpf_err(-EINVAL); + + relative_id = OPTS_GET(opts, relative_id, 0); + relative_fd = OPTS_GET(opts, relative_fd, 0); + flags = OPTS_GET(opts, flags, 0); + + /* validate we don't have unexpected combinations of non-zero fields */ + if (relative_fd && relative_id) + return libbpf_err(-EINVAL); memset(&attr, 0, attr_sz); - attr.target_fd = target_fd; - attr.attach_type = type; + attr.target_fd = target; + attr.attach_bpf_fd = prog_fd; + attr.attach_type = type; + attr.expected_revision = OPTS_GET(opts, expected_revision, 0); + + if (relative_id) { + attr.attach_flags = flags | BPF_F_ID; + attr.relative_id = relative_id; + } else { + attr.attach_flags = flags; + attr.relative_fd = relative_fd; + } ret = sys_bpf(BPF_PROG_DETACH, &attr, attr_sz); return libbpf_err_errno(ret); } -int bpf_prog_detach2(int prog_fd, int target_fd, enum bpf_attach_type type) +int bpf_prog_detach(int target_fd, enum bpf_attach_type type) { - const size_t attr_sz = offsetofend(union bpf_attr, replace_bpf_fd); - union bpf_attr attr; - int ret; - - memset(&attr, 0, attr_sz); - attr.target_fd = target_fd; - attr.attach_bpf_fd = prog_fd; - attr.attach_type = type; + return bpf_prog_detach_opts(0, target_fd, type, NULL); +} - ret = sys_bpf(BPF_PROG_DETACH, &attr, attr_sz); - return libbpf_err_errno(ret); +int bpf_prog_detach2(int prog_fd, int target_fd, enum bpf_attach_type type) +{ + return bpf_prog_detach_opts(prog_fd, target_fd, type, NULL); } int bpf_link_create(int prog_fd, int target_fd, @@ -685,9 +719,9 @@ int bpf_link_create(int prog_fd, int target_fd, const struct bpf_link_create_opts *opts) { const size_t attr_sz = offsetofend(union bpf_attr, link_create); - __u32 target_btf_id, iter_info_len; + __u32 target_btf_id, iter_info_len, relative_id; + int fd, err, relative_fd; union bpf_attr attr; - int fd, err; if (!OPTS_VALID(opts, bpf_link_create_opts)) return libbpf_err(-EINVAL); @@ -733,6 +767,17 @@ int bpf_link_create(int prog_fd, int target_fd, if (!OPTS_ZEROED(opts, kprobe_multi)) return libbpf_err(-EINVAL); break; + case BPF_TRACE_UPROBE_MULTI: + attr.link_create.uprobe_multi.flags = OPTS_GET(opts, uprobe_multi.flags, 0); + attr.link_create.uprobe_multi.cnt = OPTS_GET(opts, uprobe_multi.cnt, 0); + attr.link_create.uprobe_multi.path = ptr_to_u64(OPTS_GET(opts, uprobe_multi.path, 0)); + attr.link_create.uprobe_multi.offsets = ptr_to_u64(OPTS_GET(opts, uprobe_multi.offsets, 0)); + attr.link_create.uprobe_multi.ref_ctr_offsets = ptr_to_u64(OPTS_GET(opts, uprobe_multi.ref_ctr_offsets, 0)); + attr.link_create.uprobe_multi.cookies = ptr_to_u64(OPTS_GET(opts, uprobe_multi.cookies, 0)); + attr.link_create.uprobe_multi.pid = OPTS_GET(opts, uprobe_multi.pid, 0); + if (!OPTS_ZEROED(opts, uprobe_multi)) + return libbpf_err(-EINVAL); + break; case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: case BPF_MODIFY_RETURN: @@ -741,6 +786,30 @@ int bpf_link_create(int prog_fd, int target_fd, if (!OPTS_ZEROED(opts, tracing)) return libbpf_err(-EINVAL); break; + case BPF_NETFILTER: + attr.link_create.netfilter.pf = OPTS_GET(opts, netfilter.pf, 0); + attr.link_create.netfilter.hooknum = OPTS_GET(opts, netfilter.hooknum, 0); + attr.link_create.netfilter.priority = OPTS_GET(opts, netfilter.priority, 0); + attr.link_create.netfilter.flags = OPTS_GET(opts, netfilter.flags, 0); + if (!OPTS_ZEROED(opts, netfilter)) + return libbpf_err(-EINVAL); + break; + case BPF_TCX_INGRESS: + case BPF_TCX_EGRESS: + relative_fd = OPTS_GET(opts, tcx.relative_fd, 0); + relative_id = OPTS_GET(opts, tcx.relative_id, 0); + if (relative_fd && relative_id) + return libbpf_err(-EINVAL); + if (relative_id) { + attr.link_create.tcx.relative_id = relative_id; + attr.link_create.flags |= BPF_F_ID; + } else { + attr.link_create.tcx.relative_fd = relative_fd; + } + attr.link_create.tcx.expected_revision = OPTS_GET(opts, tcx.expected_revision, 0); + if (!OPTS_ZEROED(opts, tcx)) + return libbpf_err(-EINVAL); + break; default: if (!OPTS_ZEROED(opts, flags)) return libbpf_err(-EINVAL); @@ -833,8 +902,7 @@ int bpf_iter_create(int link_fd) return libbpf_err_errno(fd); } -int bpf_prog_query_opts(int target_fd, - enum bpf_attach_type type, +int bpf_prog_query_opts(int target, enum bpf_attach_type type, struct bpf_prog_query_opts *opts) { const size_t attr_sz = offsetofend(union bpf_attr, query); @@ -845,18 +913,20 @@ int bpf_prog_query_opts(int target_fd, return libbpf_err(-EINVAL); memset(&attr, 0, attr_sz); - - attr.query.target_fd = target_fd; - attr.query.attach_type = type; - attr.query.query_flags = OPTS_GET(opts, query_flags, 0); - attr.query.prog_cnt = OPTS_GET(opts, prog_cnt, 0); - attr.query.prog_ids = ptr_to_u64(OPTS_GET(opts, prog_ids, NULL)); - attr.query.prog_attach_flags = ptr_to_u64(OPTS_GET(opts, prog_attach_flags, NULL)); + attr.query.target_fd = target; + attr.query.attach_type = type; + attr.query.query_flags = OPTS_GET(opts, query_flags, 0); + attr.query.count = OPTS_GET(opts, count, 0); + attr.query.prog_ids = ptr_to_u64(OPTS_GET(opts, prog_ids, NULL)); + attr.query.link_ids = ptr_to_u64(OPTS_GET(opts, link_ids, NULL)); + attr.query.prog_attach_flags = ptr_to_u64(OPTS_GET(opts, prog_attach_flags, NULL)); + attr.query.link_attach_flags = ptr_to_u64(OPTS_GET(opts, link_attach_flags, NULL)); ret = sys_bpf(BPF_PROG_QUERY, &attr, attr_sz); OPTS_SET(opts, attach_flags, attr.query.attach_flags); - OPTS_SET(opts, prog_cnt, attr.query.prog_cnt); + OPTS_SET(opts, revision, attr.query.revision); + OPTS_SET(opts, count, attr.query.count); return libbpf_err_errno(ret); } diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 9aa0ee473754..74c2887cfd24 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -312,22 +312,68 @@ LIBBPF_API int bpf_obj_get(const char *pathname); LIBBPF_API int bpf_obj_get_opts(const char *pathname, const struct bpf_obj_get_opts *opts); -struct bpf_prog_attach_opts { - size_t sz; /* size of this struct for forward/backward compatibility */ - unsigned int flags; - int replace_prog_fd; -}; -#define bpf_prog_attach_opts__last_field replace_prog_fd - LIBBPF_API int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type, unsigned int flags); -LIBBPF_API int bpf_prog_attach_opts(int prog_fd, int attachable_fd, - enum bpf_attach_type type, - const struct bpf_prog_attach_opts *opts); LIBBPF_API int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type); LIBBPF_API int bpf_prog_detach2(int prog_fd, int attachable_fd, enum bpf_attach_type type); +struct bpf_prog_attach_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + __u32 flags; + union { + int replace_prog_fd; + int replace_fd; + }; + int relative_fd; + __u32 relative_id; + __u64 expected_revision; + size_t :0; +}; +#define bpf_prog_attach_opts__last_field expected_revision + +struct bpf_prog_detach_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + __u32 flags; + int relative_fd; + __u32 relative_id; + __u64 expected_revision; + size_t :0; +}; +#define bpf_prog_detach_opts__last_field expected_revision + +/** + * @brief **bpf_prog_attach_opts()** attaches the BPF program corresponding to + * *prog_fd* to a *target* which can represent a file descriptor or netdevice + * ifindex. + * + * @param prog_fd BPF program file descriptor + * @param target attach location file descriptor or ifindex + * @param type attach type for the BPF program + * @param opts options for configuring the attachment + * @return 0, on success; negative error code, otherwise (errno is also set to + * the error code) + */ +LIBBPF_API int bpf_prog_attach_opts(int prog_fd, int target, + enum bpf_attach_type type, + const struct bpf_prog_attach_opts *opts); + +/** + * @brief **bpf_prog_detach_opts()** detaches the BPF program corresponding to + * *prog_fd* from a *target* which can represent a file descriptor or netdevice + * ifindex. + * + * @param prog_fd BPF program file descriptor + * @param target detach location file descriptor or ifindex + * @param type detach type for the BPF program + * @param opts options for configuring the detachment + * @return 0, on success; negative error code, otherwise (errno is also set to + * the error code) + */ +LIBBPF_API int bpf_prog_detach_opts(int prog_fd, int target, + enum bpf_attach_type type, + const struct bpf_prog_detach_opts *opts); + union bpf_iter_link_info; /* defined in up-to-date linux/bpf.h */ struct bpf_link_create_opts { size_t sz; /* size of this struct for forward/backward compatibility */ @@ -347,12 +393,32 @@ struct bpf_link_create_opts { const __u64 *cookies; } kprobe_multi; struct { + __u32 flags; + __u32 cnt; + const char *path; + const unsigned long *offsets; + const unsigned long *ref_ctr_offsets; + const __u64 *cookies; + __u32 pid; + } uprobe_multi; + struct { __u64 cookie; } tracing; + struct { + __u32 pf; + __u32 hooknum; + __s32 priority; + __u32 flags; + } netfilter; + struct { + __u32 relative_fd; + __u32 relative_id; + __u64 expected_revision; + } tcx; }; size_t :0; }; -#define bpf_link_create_opts__last_field kprobe_multi.cookies +#define bpf_link_create_opts__last_field uprobe_multi.pid LIBBPF_API int bpf_link_create(int prog_fd, int target_fd, enum bpf_attach_type attach_type, @@ -489,13 +555,31 @@ struct bpf_prog_query_opts { __u32 query_flags; __u32 attach_flags; /* output argument */ __u32 *prog_ids; - __u32 prog_cnt; /* input+output argument */ + union { + /* input+output argument */ + __u32 prog_cnt; + __u32 count; + }; __u32 *prog_attach_flags; + __u32 *link_ids; + __u32 *link_attach_flags; + __u64 revision; + size_t :0; }; -#define bpf_prog_query_opts__last_field prog_attach_flags +#define bpf_prog_query_opts__last_field revision -LIBBPF_API int bpf_prog_query_opts(int target_fd, - enum bpf_attach_type type, +/** + * @brief **bpf_prog_query_opts()** queries the BPF programs and BPF links + * which are attached to *target* which can represent a file descriptor or + * netdevice ifindex. + * + * @param target query location file descriptor or ifindex + * @param type attach type for the BPF program + * @param opts options for configuring the query + * @return 0, on success; negative error code, otherwise (errno is also set to + * the error code) + */ +LIBBPF_API int bpf_prog_query_opts(int target, enum bpf_attach_type type, struct bpf_prog_query_opts *opts); LIBBPF_API int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags, __u32 *attach_flags, diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h index be076a4041ab..3803479dbe10 100644 --- a/tools/lib/bpf/bpf_tracing.h +++ b/tools/lib/bpf/bpf_tracing.h @@ -2,7 +2,7 @@ #ifndef __BPF_TRACING_H__ #define __BPF_TRACING_H__ -#include <bpf/bpf_helpers.h> +#include "bpf_helpers.h" /* Scan the ARCH passed in from ARCH env variable (see Makefile) */ #if defined(__TARGET_ARCH_x86) diff --git a/tools/lib/bpf/elf.c b/tools/lib/bpf/elf.c new file mode 100644 index 000000000000..9d0296c1726a --- /dev/null +++ b/tools/lib/bpf/elf.c @@ -0,0 +1,440 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +#include <libelf.h> +#include <gelf.h> +#include <fcntl.h> +#include <linux/kernel.h> + +#include "libbpf_internal.h" +#include "str_error.h" + +#define STRERR_BUFSIZE 128 + +int elf_open(const char *binary_path, struct elf_fd *elf_fd) +{ + char errmsg[STRERR_BUFSIZE]; + int fd, ret; + Elf *elf; + + if (elf_version(EV_CURRENT) == EV_NONE) { + pr_warn("elf: failed to init libelf for %s\n", binary_path); + return -LIBBPF_ERRNO__LIBELF; + } + fd = open(binary_path, O_RDONLY | O_CLOEXEC); + if (fd < 0) { + ret = -errno; + pr_warn("elf: failed to open %s: %s\n", binary_path, + libbpf_strerror_r(ret, errmsg, sizeof(errmsg))); + return ret; + } + elf = elf_begin(fd, ELF_C_READ_MMAP, NULL); + if (!elf) { + pr_warn("elf: could not read elf from %s: %s\n", binary_path, elf_errmsg(-1)); + close(fd); + return -LIBBPF_ERRNO__FORMAT; + } + elf_fd->fd = fd; + elf_fd->elf = elf; + return 0; +} + +void elf_close(struct elf_fd *elf_fd) +{ + if (!elf_fd) + return; + elf_end(elf_fd->elf); + close(elf_fd->fd); +} + +/* Return next ELF section of sh_type after scn, or first of that type if scn is NULL. */ +static Elf_Scn *elf_find_next_scn_by_type(Elf *elf, int sh_type, Elf_Scn *scn) +{ + while ((scn = elf_nextscn(elf, scn)) != NULL) { + GElf_Shdr sh; + + if (!gelf_getshdr(scn, &sh)) + continue; + if (sh.sh_type == sh_type) + return scn; + } + return NULL; +} + +struct elf_sym { + const char *name; + GElf_Sym sym; + GElf_Shdr sh; +}; + +struct elf_sym_iter { + Elf *elf; + Elf_Data *syms; + size_t nr_syms; + size_t strtabidx; + size_t next_sym_idx; + struct elf_sym sym; + int st_type; +}; + +static int elf_sym_iter_new(struct elf_sym_iter *iter, + Elf *elf, const char *binary_path, + int sh_type, int st_type) +{ + Elf_Scn *scn = NULL; + GElf_Ehdr ehdr; + GElf_Shdr sh; + + memset(iter, 0, sizeof(*iter)); + + if (!gelf_getehdr(elf, &ehdr)) { + pr_warn("elf: failed to get ehdr from %s: %s\n", binary_path, elf_errmsg(-1)); + return -EINVAL; + } + + scn = elf_find_next_scn_by_type(elf, sh_type, NULL); + if (!scn) { + pr_debug("elf: failed to find symbol table ELF sections in '%s'\n", + binary_path); + return -ENOENT; + } + + if (!gelf_getshdr(scn, &sh)) + return -EINVAL; + + iter->strtabidx = sh.sh_link; + iter->syms = elf_getdata(scn, 0); + if (!iter->syms) { + pr_warn("elf: failed to get symbols for symtab section in '%s': %s\n", + binary_path, elf_errmsg(-1)); + return -EINVAL; + } + iter->nr_syms = iter->syms->d_size / sh.sh_entsize; + iter->elf = elf; + iter->st_type = st_type; + return 0; +} + +static struct elf_sym *elf_sym_iter_next(struct elf_sym_iter *iter) +{ + struct elf_sym *ret = &iter->sym; + GElf_Sym *sym = &ret->sym; + const char *name = NULL; + Elf_Scn *sym_scn; + size_t idx; + + for (idx = iter->next_sym_idx; idx < iter->nr_syms; idx++) { + if (!gelf_getsym(iter->syms, idx, sym)) + continue; + if (GELF_ST_TYPE(sym->st_info) != iter->st_type) + continue; + name = elf_strptr(iter->elf, iter->strtabidx, sym->st_name); + if (!name) + continue; + sym_scn = elf_getscn(iter->elf, sym->st_shndx); + if (!sym_scn) + continue; + if (!gelf_getshdr(sym_scn, &ret->sh)) + continue; + + iter->next_sym_idx = idx + 1; + ret->name = name; + return ret; + } + + return NULL; +} + + +/* Transform symbol's virtual address (absolute for binaries and relative + * for shared libs) into file offset, which is what kernel is expecting + * for uprobe/uretprobe attachment. + * See Documentation/trace/uprobetracer.rst for more details. This is done + * by looking up symbol's containing section's header and using iter's virtual + * address (sh_addr) and corresponding file offset (sh_offset) to transform + * sym.st_value (virtual address) into desired final file offset. + */ +static unsigned long elf_sym_offset(struct elf_sym *sym) +{ + return sym->sym.st_value - sym->sh.sh_addr + sym->sh.sh_offset; +} + +/* Find offset of function name in the provided ELF object. "binary_path" is + * the path to the ELF binary represented by "elf", and only used for error + * reporting matters. "name" matches symbol name or name@@LIB for library + * functions. + */ +long elf_find_func_offset(Elf *elf, const char *binary_path, const char *name) +{ + int i, sh_types[2] = { SHT_DYNSYM, SHT_SYMTAB }; + bool is_shared_lib, is_name_qualified; + long ret = -ENOENT; + size_t name_len; + GElf_Ehdr ehdr; + + if (!gelf_getehdr(elf, &ehdr)) { + pr_warn("elf: failed to get ehdr from %s: %s\n", binary_path, elf_errmsg(-1)); + ret = -LIBBPF_ERRNO__FORMAT; + goto out; + } + /* for shared lib case, we do not need to calculate relative offset */ + is_shared_lib = ehdr.e_type == ET_DYN; + + name_len = strlen(name); + /* Does name specify "@@LIB"? */ + is_name_qualified = strstr(name, "@@") != NULL; + + /* Search SHT_DYNSYM, SHT_SYMTAB for symbol. This search order is used because if + * a binary is stripped, it may only have SHT_DYNSYM, and a fully-statically + * linked binary may not have SHT_DYMSYM, so absence of a section should not be + * reported as a warning/error. + */ + for (i = 0; i < ARRAY_SIZE(sh_types); i++) { + struct elf_sym_iter iter; + struct elf_sym *sym; + int last_bind = -1; + int cur_bind; + + ret = elf_sym_iter_new(&iter, elf, binary_path, sh_types[i], STT_FUNC); + if (ret == -ENOENT) + continue; + if (ret) + goto out; + + while ((sym = elf_sym_iter_next(&iter))) { + /* User can specify func, func@@LIB or func@@LIB_VERSION. */ + if (strncmp(sym->name, name, name_len) != 0) + continue; + /* ...but we don't want a search for "foo" to match 'foo2" also, so any + * additional characters in sname should be of the form "@@LIB". + */ + if (!is_name_qualified && sym->name[name_len] != '\0' && sym->name[name_len] != '@') + continue; + + cur_bind = GELF_ST_BIND(sym->sym.st_info); + + if (ret > 0) { + /* handle multiple matches */ + if (last_bind != STB_WEAK && cur_bind != STB_WEAK) { + /* Only accept one non-weak bind. */ + pr_warn("elf: ambiguous match for '%s', '%s' in '%s'\n", + sym->name, name, binary_path); + ret = -LIBBPF_ERRNO__FORMAT; + goto out; + } else if (cur_bind == STB_WEAK) { + /* already have a non-weak bind, and + * this is a weak bind, so ignore. + */ + continue; + } + } + + ret = elf_sym_offset(sym); + last_bind = cur_bind; + } + if (ret > 0) + break; + } + + if (ret > 0) { + pr_debug("elf: symbol address match for '%s' in '%s': 0x%lx\n", name, binary_path, + ret); + } else { + if (ret == 0) { + pr_warn("elf: '%s' is 0 in symtab for '%s': %s\n", name, binary_path, + is_shared_lib ? "should not be 0 in a shared library" : + "try using shared library path instead"); + ret = -ENOENT; + } else { + pr_warn("elf: failed to find symbol '%s' in '%s'\n", name, binary_path); + } + } +out: + return ret; +} + +/* Find offset of function name in ELF object specified by path. "name" matches + * symbol name or name@@LIB for library functions. + */ +long elf_find_func_offset_from_file(const char *binary_path, const char *name) +{ + struct elf_fd elf_fd; + long ret = -ENOENT; + + ret = elf_open(binary_path, &elf_fd); + if (ret) + return ret; + ret = elf_find_func_offset(elf_fd.elf, binary_path, name); + elf_close(&elf_fd); + return ret; +} + +struct symbol { + const char *name; + int bind; + int idx; +}; + +static int symbol_cmp(const void *a, const void *b) +{ + const struct symbol *sym_a = a; + const struct symbol *sym_b = b; + + return strcmp(sym_a->name, sym_b->name); +} + +/* + * Return offsets in @poffsets for symbols specified in @syms array argument. + * On success returns 0 and offsets are returned in allocated array with @cnt + * size, that needs to be released by the caller. + */ +int elf_resolve_syms_offsets(const char *binary_path, int cnt, + const char **syms, unsigned long **poffsets) +{ + int sh_types[2] = { SHT_DYNSYM, SHT_SYMTAB }; + int err = 0, i, cnt_done = 0; + unsigned long *offsets; + struct symbol *symbols; + struct elf_fd elf_fd; + + err = elf_open(binary_path, &elf_fd); + if (err) + return err; + + offsets = calloc(cnt, sizeof(*offsets)); + symbols = calloc(cnt, sizeof(*symbols)); + + if (!offsets || !symbols) { + err = -ENOMEM; + goto out; + } + + for (i = 0; i < cnt; i++) { + symbols[i].name = syms[i]; + symbols[i].idx = i; + } + + qsort(symbols, cnt, sizeof(*symbols), symbol_cmp); + + for (i = 0; i < ARRAY_SIZE(sh_types); i++) { + struct elf_sym_iter iter; + struct elf_sym *sym; + + err = elf_sym_iter_new(&iter, elf_fd.elf, binary_path, sh_types[i], STT_FUNC); + if (err == -ENOENT) + continue; + if (err) + goto out; + + while ((sym = elf_sym_iter_next(&iter))) { + unsigned long sym_offset = elf_sym_offset(sym); + int bind = GELF_ST_BIND(sym->sym.st_info); + struct symbol *found, tmp = { + .name = sym->name, + }; + unsigned long *offset; + + found = bsearch(&tmp, symbols, cnt, sizeof(*symbols), symbol_cmp); + if (!found) + continue; + + offset = &offsets[found->idx]; + if (*offset > 0) { + /* same offset, no problem */ + if (*offset == sym_offset) + continue; + /* handle multiple matches */ + if (found->bind != STB_WEAK && bind != STB_WEAK) { + /* Only accept one non-weak bind. */ + pr_warn("elf: ambiguous match found '%s@%lu' in '%s' previous offset %lu\n", + sym->name, sym_offset, binary_path, *offset); + err = -ESRCH; + goto out; + } else if (bind == STB_WEAK) { + /* already have a non-weak bind, and + * this is a weak bind, so ignore. + */ + continue; + } + } else { + cnt_done++; + } + *offset = sym_offset; + found->bind = bind; + } + } + + if (cnt != cnt_done) { + err = -ENOENT; + goto out; + } + + *poffsets = offsets; + +out: + free(symbols); + if (err) + free(offsets); + elf_close(&elf_fd); + return err; +} + +/* + * Return offsets in @poffsets for symbols specified by @pattern argument. + * On success returns 0 and offsets are returned in allocated @poffsets + * array with the @pctn size, that needs to be released by the caller. + */ +int elf_resolve_pattern_offsets(const char *binary_path, const char *pattern, + unsigned long **poffsets, size_t *pcnt) +{ + int sh_types[2] = { SHT_SYMTAB, SHT_DYNSYM }; + unsigned long *offsets = NULL; + size_t cap = 0, cnt = 0; + struct elf_fd elf_fd; + int err = 0, i; + + err = elf_open(binary_path, &elf_fd); + if (err) + return err; + + for (i = 0; i < ARRAY_SIZE(sh_types); i++) { + struct elf_sym_iter iter; + struct elf_sym *sym; + + err = elf_sym_iter_new(&iter, elf_fd.elf, binary_path, sh_types[i], STT_FUNC); + if (err == -ENOENT) + continue; + if (err) + goto out; + + while ((sym = elf_sym_iter_next(&iter))) { + if (!glob_match(sym->name, pattern)) + continue; + + err = libbpf_ensure_mem((void **) &offsets, &cap, sizeof(*offsets), + cnt + 1); + if (err) + goto out; + + offsets[cnt++] = elf_sym_offset(sym); + } + + /* If we found anything in the first symbol section, + * do not search others to avoid duplicates. + */ + if (cnt) + break; + } + + if (cnt) { + *poffsets = offsets; + *pcnt = cnt; + } else { + err = -ENOENT; + } + +out: + if (err) + free(offsets); + elf_close(&elf_fd); + return err; +} diff --git a/tools/lib/bpf/hashmap.h b/tools/lib/bpf/hashmap.h index 0a5bf1937a7c..c12f8320e668 100644 --- a/tools/lib/bpf/hashmap.h +++ b/tools/lib/bpf/hashmap.h @@ -80,16 +80,6 @@ struct hashmap { size_t sz; }; -#define HASHMAP_INIT(hash_fn, equal_fn, ctx) { \ - .hash_fn = (hash_fn), \ - .equal_fn = (equal_fn), \ - .ctx = (ctx), \ - .buckets = NULL, \ - .cap = 0, \ - .cap_bits = 0, \ - .sz = 0, \ -} - void hashmap__init(struct hashmap *map, hashmap_hash_fn hash_fn, hashmap_equal_fn equal_fn, void *ctx); struct hashmap *hashmap__new(hashmap_hash_fn hash_fn, diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 214f828ece6b..96ff1aa4bf6a 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -118,6 +118,9 @@ static const char * const attach_type_name[] = { [BPF_TRACE_KPROBE_MULTI] = "trace_kprobe_multi", [BPF_STRUCT_OPS] = "struct_ops", [BPF_NETFILTER] = "netfilter", + [BPF_TCX_INGRESS] = "tcx_ingress", + [BPF_TCX_EGRESS] = "tcx_egress", + [BPF_TRACE_UPROBE_MULTI] = "trace_uprobe_multi", }; static const char * const link_type_name[] = { @@ -132,6 +135,8 @@ static const char * const link_type_name[] = { [BPF_LINK_TYPE_KPROBE_MULTI] = "kprobe_multi", [BPF_LINK_TYPE_STRUCT_OPS] = "struct_ops", [BPF_LINK_TYPE_NETFILTER] = "netfilter", + [BPF_LINK_TYPE_TCX] = "tcx", + [BPF_LINK_TYPE_UPROBE_MULTI] = "uprobe_multi", }; static const char * const map_type_name[] = { @@ -362,6 +367,8 @@ enum sec_def_flags { SEC_SLEEPABLE = 8, /* BPF program support non-linear XDP buffer */ SEC_XDP_FRAGS = 16, + /* Setup proper attach type for usdt probes. */ + SEC_USDT = 32, }; struct bpf_sec_def { @@ -547,6 +554,7 @@ struct extern_desc { int btf_id; int sec_btf_id; const char *name; + char *essent_name; bool is_set; bool is_weak; union { @@ -1975,9 +1983,9 @@ static int bpf_object__read_kconfig_file(struct bpf_object *obj, void *data) return -ENAMETOOLONG; /* gzopen also accepts uncompressed files. */ - file = gzopen(buf, "r"); + file = gzopen(buf, "re"); if (!file) - file = gzopen("/proc/config.gz", "r"); + file = gzopen("/proc/config.gz", "re"); if (!file) { pr_warn("failed to open system Kconfig\n"); @@ -3767,6 +3775,7 @@ static int bpf_object__collect_externs(struct bpf_object *obj) struct extern_desc *ext; int i, n, off, dummy_var_btf_id; const char *ext_name, *sec_name; + size_t ext_essent_len; Elf_Scn *scn; Elf64_Shdr *sh; @@ -3816,6 +3825,14 @@ static int bpf_object__collect_externs(struct bpf_object *obj) ext->sym_idx = i; ext->is_weak = ELF64_ST_BIND(sym->st_info) == STB_WEAK; + ext_essent_len = bpf_core_essential_name_len(ext->name); + ext->essent_name = NULL; + if (ext_essent_len != strlen(ext->name)) { + ext->essent_name = strndup(ext->name, ext_essent_len); + if (!ext->essent_name) + return -ENOMEM; + } + ext->sec_btf_id = find_extern_sec_btf_id(obj->btf, ext->btf_id); if (ext->sec_btf_id <= 0) { pr_warn("failed to find BTF for extern '%s' [%d] section: %d\n", @@ -4814,6 +4831,39 @@ static int probe_perf_link(void) return link_fd < 0 && err == -EBADF; } +static int probe_uprobe_multi_link(void) +{ + LIBBPF_OPTS(bpf_prog_load_opts, load_opts, + .expected_attach_type = BPF_TRACE_UPROBE_MULTI, + ); + LIBBPF_OPTS(bpf_link_create_opts, link_opts); + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + int prog_fd, link_fd, err; + unsigned long offset = 0; + + prog_fd = bpf_prog_load(BPF_PROG_TYPE_KPROBE, NULL, "GPL", + insns, ARRAY_SIZE(insns), &load_opts); + if (prog_fd < 0) + return -errno; + + /* Creating uprobe in '/' binary should fail with -EBADF. */ + link_opts.uprobe_multi.path = "/"; + link_opts.uprobe_multi.offsets = &offset; + link_opts.uprobe_multi.cnt = 1; + + link_fd = bpf_link_create(prog_fd, -1, BPF_TRACE_UPROBE_MULTI, &link_opts); + err = -errno; /* close() can clobber errno */ + + if (link_fd >= 0) + close(link_fd); + close(prog_fd); + + return link_fd < 0 && err == -EBADF; +} + static int probe_kern_bpf_cookie(void) { struct bpf_insn insns[] = { @@ -4910,6 +4960,9 @@ static struct kern_feature_desc { [FEAT_SYSCALL_WRAPPER] = { "Kernel using syscall wrapper", probe_kern_syscall_wrapper, }, + [FEAT_UPROBE_MULTI_LINK] = { + "BPF multi-uprobe link support", probe_uprobe_multi_link, + }, }; bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id) @@ -5471,6 +5524,10 @@ static int load_module_btfs(struct bpf_object *obj) err = bpf_btf_get_next_id(id, &id); if (err && errno == ENOENT) return 0; + if (err && errno == EPERM) { + pr_debug("skipping module BTFs loading, missing privileges\n"); + return 0; + } if (err) { err = -errno; pr_warn("failed to iterate BTF objects: %d\n", err); @@ -6157,7 +6214,11 @@ static int append_subprog_relos(struct bpf_program *main_prog, struct bpf_progra if (main_prog == subprog) return 0; relos = libbpf_reallocarray(main_prog->reloc_desc, new_cnt, sizeof(*relos)); - if (!relos) + /* if new count is zero, reallocarray can return a valid NULL result; + * in this case the previous pointer will be freed, so we *have to* + * reassign old pointer to the new value (even if it's NULL) + */ + if (!relos && new_cnt) return -ENOMEM; if (subprog->nr_reloc) memcpy(relos + main_prog->nr_reloc, subprog->reloc_desc, @@ -6769,6 +6830,10 @@ static int libbpf_prepare_prog_load(struct bpf_program *prog, if (prog->type == BPF_PROG_TYPE_XDP && (def & SEC_XDP_FRAGS)) opts->prog_flags |= BPF_F_XDP_HAS_FRAGS; + /* special check for usdt to use uprobe_multi link */ + if ((def & SEC_USDT) && kernel_supports(prog->obj, FEAT_UPROBE_MULTI_LINK)) + prog->expected_attach_type = BPF_TRACE_UPROBE_MULTI; + if ((def & SEC_ATTACH_BTF) && !prog->attach_btf_id) { int btf_obj_fd = 0, btf_type_id = 0, err; const char *attach_name; @@ -6837,7 +6902,6 @@ static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog if (!insns || !insns_cnt) return -EINVAL; - load_attr.expected_attach_type = prog->expected_attach_type; if (kernel_supports(obj, FEAT_PROG_NAME)) prog_name = prog->name; load_attr.attach_prog_fd = prog->attach_prog_fd; @@ -6873,6 +6937,9 @@ static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog insns_cnt = prog->insns_cnt; } + /* allow prog_prepare_load_fn to change expected_attach_type */ + load_attr.expected_attach_type = prog->expected_attach_type; + if (obj->gen_loader) { bpf_gen__prog_load(obj->gen_loader, prog->type, prog->name, license, insns, insns_cnt, &load_attr, @@ -7613,7 +7680,8 @@ static int bpf_object__resolve_ksym_func_btf_id(struct bpf_object *obj, local_func_proto_id = ext->ksym.type_id; - kfunc_id = find_ksym_btf_id(obj, ext->name, BTF_KIND_FUNC, &kern_btf, &mod_btf); + kfunc_id = find_ksym_btf_id(obj, ext->essent_name ?: ext->name, BTF_KIND_FUNC, &kern_btf, + &mod_btf); if (kfunc_id < 0) { if (kfunc_id == -ESRCH && ext->is_weak) return 0; @@ -7628,6 +7696,9 @@ static int bpf_object__resolve_ksym_func_btf_id(struct bpf_object *obj, ret = bpf_core_types_are_compat(obj->btf, local_func_proto_id, kern_btf, kfunc_proto_id); if (ret <= 0) { + if (ext->is_weak) + return 0; + pr_warn("extern (func ksym) '%s': func_proto [%d] incompatible with %s [%d]\n", ext->name, local_func_proto_id, mod_btf ? mod_btf->name : "vmlinux", kfunc_proto_id); @@ -8305,6 +8376,21 @@ int bpf_object__pin(struct bpf_object *obj, const char *path) return 0; } +int bpf_object__unpin(struct bpf_object *obj, const char *path) +{ + int err; + + err = bpf_object__unpin_programs(obj, path); + if (err) + return libbpf_err(err); + + err = bpf_object__unpin_maps(obj, path); + if (err) + return libbpf_err(err); + + return 0; +} + static void bpf_map__destroy(struct bpf_map *map) { if (map->inner_map) { @@ -8352,6 +8438,7 @@ void bpf_object__close(struct bpf_object *obj) bpf_object__elf_finish(obj); bpf_object_unload(obj); btf__free(obj->btf); + btf__free(obj->btf_vmlinux); btf_ext__free(obj->btf_ext); for (i = 0; i < obj->nr_maps; i++) @@ -8359,6 +8446,10 @@ void bpf_object__close(struct bpf_object *obj) zfree(&obj->btf_custom_path); zfree(&obj->kconfig); + + for (i = 0; i < obj->nr_extern; i++) + zfree(&obj->externs[i].essent_name); + zfree(&obj->externs); obj->nr_extern = 0; @@ -8528,7 +8619,8 @@ int bpf_program__set_insns(struct bpf_program *prog, return -EBUSY; insns = libbpf_reallocarray(prog->insns, new_insn_cnt, sizeof(*insns)); - if (!insns) { + /* NULL is a valid return from reallocarray if the new count is zero */ + if (!insns && new_insn_cnt) { pr_warn("prog '%s': failed to realloc prog code\n", prog->name); return -ENOMEM; } @@ -8558,13 +8650,31 @@ enum bpf_prog_type bpf_program__type(const struct bpf_program *prog) return prog->type; } +static size_t custom_sec_def_cnt; +static struct bpf_sec_def *custom_sec_defs; +static struct bpf_sec_def custom_fallback_def; +static bool has_custom_fallback_def; +static int last_custom_sec_def_handler_id; + int bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type) { if (prog->obj->loaded) return libbpf_err(-EBUSY); + /* if type is not changed, do nothing */ + if (prog->type == type) + return 0; + prog->type = type; - prog->sec_def = NULL; + + /* If a program type was changed, we need to reset associated SEC() + * handler, as it will be invalid now. The only exception is a generic + * fallback handler, which by definition is program type-agnostic and + * is a catch-all custom handler, optionally set by the application, + * so should be able to handle any type of BPF program. + */ + if (prog->sec_def != &custom_fallback_def) + prog->sec_def = NULL; return 0; } @@ -8651,6 +8761,7 @@ static int attach_tp(const struct bpf_program *prog, long cookie, struct bpf_lin static int attach_raw_tp(const struct bpf_program *prog, long cookie, struct bpf_link **link); static int attach_trace(const struct bpf_program *prog, long cookie, struct bpf_link **link); static int attach_kprobe_multi(const struct bpf_program *prog, long cookie, struct bpf_link **link); +static int attach_uprobe_multi(const struct bpf_program *prog, long cookie, struct bpf_link **link); static int attach_lsm(const struct bpf_program *prog, long cookie, struct bpf_link **link); static int attach_iter(const struct bpf_program *prog, long cookie, struct bpf_link **link); @@ -8666,12 +8777,21 @@ static const struct bpf_sec_def section_defs[] = { SEC_DEF("uretprobe.s+", KPROBE, 0, SEC_SLEEPABLE, attach_uprobe), SEC_DEF("kprobe.multi+", KPROBE, BPF_TRACE_KPROBE_MULTI, SEC_NONE, attach_kprobe_multi), SEC_DEF("kretprobe.multi+", KPROBE, BPF_TRACE_KPROBE_MULTI, SEC_NONE, attach_kprobe_multi), + SEC_DEF("uprobe.multi+", KPROBE, BPF_TRACE_UPROBE_MULTI, SEC_NONE, attach_uprobe_multi), + SEC_DEF("uretprobe.multi+", KPROBE, BPF_TRACE_UPROBE_MULTI, SEC_NONE, attach_uprobe_multi), + SEC_DEF("uprobe.multi.s+", KPROBE, BPF_TRACE_UPROBE_MULTI, SEC_SLEEPABLE, attach_uprobe_multi), + SEC_DEF("uretprobe.multi.s+", KPROBE, BPF_TRACE_UPROBE_MULTI, SEC_SLEEPABLE, attach_uprobe_multi), SEC_DEF("ksyscall+", KPROBE, 0, SEC_NONE, attach_ksyscall), SEC_DEF("kretsyscall+", KPROBE, 0, SEC_NONE, attach_ksyscall), - SEC_DEF("usdt+", KPROBE, 0, SEC_NONE, attach_usdt), - SEC_DEF("tc", SCHED_CLS, 0, SEC_NONE), - SEC_DEF("classifier", SCHED_CLS, 0, SEC_NONE), - SEC_DEF("action", SCHED_ACT, 0, SEC_NONE), + SEC_DEF("usdt+", KPROBE, 0, SEC_USDT, attach_usdt), + SEC_DEF("usdt.s+", KPROBE, 0, SEC_USDT | SEC_SLEEPABLE, attach_usdt), + SEC_DEF("tc/ingress", SCHED_CLS, BPF_TCX_INGRESS, SEC_NONE), /* alias for tcx */ + SEC_DEF("tc/egress", SCHED_CLS, BPF_TCX_EGRESS, SEC_NONE), /* alias for tcx */ + SEC_DEF("tcx/ingress", SCHED_CLS, BPF_TCX_INGRESS, SEC_NONE), + SEC_DEF("tcx/egress", SCHED_CLS, BPF_TCX_EGRESS, SEC_NONE), + SEC_DEF("tc", SCHED_CLS, 0, SEC_NONE), /* deprecated / legacy, use tcx */ + SEC_DEF("classifier", SCHED_CLS, 0, SEC_NONE), /* deprecated / legacy, use tcx */ + SEC_DEF("action", SCHED_ACT, 0, SEC_NONE), /* deprecated / legacy, use tcx */ SEC_DEF("tracepoint+", TRACEPOINT, 0, SEC_NONE, attach_tp), SEC_DEF("tp+", TRACEPOINT, 0, SEC_NONE, attach_tp), SEC_DEF("raw_tracepoint+", RAW_TRACEPOINT, 0, SEC_NONE, attach_raw_tp), @@ -8740,13 +8860,6 @@ static const struct bpf_sec_def section_defs[] = { SEC_DEF("netfilter", NETFILTER, BPF_NETFILTER, SEC_NONE), }; -static size_t custom_sec_def_cnt; -static struct bpf_sec_def *custom_sec_defs; -static struct bpf_sec_def custom_fallback_def; -static bool has_custom_fallback_def; - -static int last_custom_sec_def_handler_id; - int libbpf_register_prog_handler(const char *sec, enum bpf_prog_type prog_type, enum bpf_attach_type exp_attach_type, @@ -8826,7 +8939,11 @@ int libbpf_unregister_prog_handler(int handler_id) /* try to shrink the array, but it's ok if we couldn't */ sec_defs = libbpf_reallocarray(custom_sec_defs, custom_sec_def_cnt, sizeof(*sec_defs)); - if (sec_defs) + /* if new count is zero, reallocarray can return a valid NULL result; + * in this case the previous pointer will be freed, so we *have to* + * reassign old pointer to the new value (even if it's NULL) + */ + if (sec_defs || custom_sec_def_cnt == 0) custom_sec_defs = sec_defs; return 0; @@ -10224,6 +10341,18 @@ static const char *tracefs_uprobe_events(void) return use_debugfs() ? DEBUGFS"/uprobe_events" : TRACEFS"/uprobe_events"; } +static const char *tracefs_available_filter_functions(void) +{ + return use_debugfs() ? DEBUGFS"/available_filter_functions" + : TRACEFS"/available_filter_functions"; +} + +static const char *tracefs_available_filter_functions_addrs(void) +{ + return use_debugfs() ? DEBUGFS"/available_filter_functions_addrs" + : TRACEFS"/available_filter_functions_addrs"; +} + static void gen_kprobe_legacy_event_name(char *buf, size_t buf_sz, const char *kfunc_name, size_t offset) { @@ -10506,7 +10635,7 @@ struct bpf_link *bpf_program__attach_ksyscall(const struct bpf_program *prog, } /* Adapted from perf/util/string.c */ -static bool glob_match(const char *str, const char *pat) +bool glob_match(const char *str, const char *pat) { while (*str && *pat && *pat != '*') { if (*pat == '?') { /* Matches any single character */ @@ -10539,25 +10668,158 @@ struct kprobe_multi_resolve { size_t cnt; }; -static int -resolve_kprobe_multi_cb(unsigned long long sym_addr, char sym_type, - const char *sym_name, void *ctx) +struct avail_kallsyms_data { + char **syms; + size_t cnt; + struct kprobe_multi_resolve *res; +}; + +static int avail_func_cmp(const void *a, const void *b) { - struct kprobe_multi_resolve *res = ctx; + return strcmp(*(const char **)a, *(const char **)b); +} + +static int avail_kallsyms_cb(unsigned long long sym_addr, char sym_type, + const char *sym_name, void *ctx) +{ + struct avail_kallsyms_data *data = ctx; + struct kprobe_multi_resolve *res = data->res; int err; - if (!glob_match(sym_name, res->pattern)) + if (!bsearch(&sym_name, data->syms, data->cnt, sizeof(*data->syms), avail_func_cmp)) return 0; - err = libbpf_ensure_mem((void **) &res->addrs, &res->cap, sizeof(unsigned long), - res->cnt + 1); + err = libbpf_ensure_mem((void **)&res->addrs, &res->cap, sizeof(*res->addrs), res->cnt + 1); if (err) return err; - res->addrs[res->cnt++] = (unsigned long) sym_addr; + res->addrs[res->cnt++] = (unsigned long)sym_addr; return 0; } +static int libbpf_available_kallsyms_parse(struct kprobe_multi_resolve *res) +{ + const char *available_functions_file = tracefs_available_filter_functions(); + struct avail_kallsyms_data data; + char sym_name[500]; + FILE *f; + int err = 0, ret, i; + char **syms = NULL; + size_t cap = 0, cnt = 0; + + f = fopen(available_functions_file, "re"); + if (!f) { + err = -errno; + pr_warn("failed to open %s: %d\n", available_functions_file, err); + return err; + } + + while (true) { + char *name; + + ret = fscanf(f, "%499s%*[^\n]\n", sym_name); + if (ret == EOF && feof(f)) + break; + + if (ret != 1) { + pr_warn("failed to parse available_filter_functions entry: %d\n", ret); + err = -EINVAL; + goto cleanup; + } + + if (!glob_match(sym_name, res->pattern)) + continue; + + err = libbpf_ensure_mem((void **)&syms, &cap, sizeof(*syms), cnt + 1); + if (err) + goto cleanup; + + name = strdup(sym_name); + if (!name) { + err = -errno; + goto cleanup; + } + + syms[cnt++] = name; + } + + /* no entries found, bail out */ + if (cnt == 0) { + err = -ENOENT; + goto cleanup; + } + + /* sort available functions */ + qsort(syms, cnt, sizeof(*syms), avail_func_cmp); + + data.syms = syms; + data.res = res; + data.cnt = cnt; + libbpf_kallsyms_parse(avail_kallsyms_cb, &data); + + if (res->cnt == 0) + err = -ENOENT; + +cleanup: + for (i = 0; i < cnt; i++) + free((char *)syms[i]); + free(syms); + + fclose(f); + return err; +} + +static bool has_available_filter_functions_addrs(void) +{ + return access(tracefs_available_filter_functions_addrs(), R_OK) != -1; +} + +static int libbpf_available_kprobes_parse(struct kprobe_multi_resolve *res) +{ + const char *available_path = tracefs_available_filter_functions_addrs(); + char sym_name[500]; + FILE *f; + int ret, err = 0; + unsigned long long sym_addr; + + f = fopen(available_path, "re"); + if (!f) { + err = -errno; + pr_warn("failed to open %s: %d\n", available_path, err); + return err; + } + + while (true) { + ret = fscanf(f, "%llx %499s%*[^\n]\n", &sym_addr, sym_name); + if (ret == EOF && feof(f)) + break; + + if (ret != 2) { + pr_warn("failed to parse available_filter_functions_addrs entry: %d\n", + ret); + err = -EINVAL; + goto cleanup; + } + + if (!glob_match(sym_name, res->pattern)) + continue; + + err = libbpf_ensure_mem((void **)&res->addrs, &res->cap, + sizeof(*res->addrs), res->cnt + 1); + if (err) + goto cleanup; + + res->addrs[res->cnt++] = (unsigned long)sym_addr; + } + + if (res->cnt == 0) + err = -ENOENT; + +cleanup: + fclose(f); + return err; +} + struct bpf_link * bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog, const char *pattern, @@ -10594,13 +10856,12 @@ bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog, return libbpf_err_ptr(-EINVAL); if (pattern) { - err = libbpf_kallsyms_parse(resolve_kprobe_multi_cb, &res); + if (has_available_filter_functions_addrs()) + err = libbpf_available_kprobes_parse(&res); + else + err = libbpf_available_kallsyms_parse(&res); if (err) goto error; - if (!res.cnt) { - err = -ENOENT; - goto error; - } addrs = res.addrs; cnt = res.cnt; } @@ -10727,6 +10988,37 @@ static int attach_kprobe_multi(const struct bpf_program *prog, long cookie, stru return libbpf_get_error(*link); } +static int attach_uprobe_multi(const struct bpf_program *prog, long cookie, struct bpf_link **link) +{ + char *probe_type = NULL, *binary_path = NULL, *func_name = NULL; + LIBBPF_OPTS(bpf_uprobe_multi_opts, opts); + int n, ret = -EINVAL; + + *link = NULL; + + n = sscanf(prog->sec_name, "%m[^/]/%m[^:]:%ms", + &probe_type, &binary_path, &func_name); + switch (n) { + case 1: + /* handle SEC("u[ret]probe") - format is valid, but auto-attach is impossible. */ + ret = 0; + break; + case 3: + opts.retprobe = strcmp(probe_type, "uretprobe.multi") == 0; + *link = bpf_program__attach_uprobe_multi(prog, -1, binary_path, func_name, &opts); + ret = libbpf_get_error(*link); + break; + default: + pr_warn("prog '%s': invalid format of section definition '%s'\n", prog->name, + prog->sec_name); + break; + } + free(probe_type); + free(binary_path); + free(func_name); + return ret; +} + static void gen_uprobe_legacy_event_name(char *buf, size_t buf_sz, const char *binary_path, uint64_t offset) { @@ -10809,191 +11101,6 @@ err_clean_legacy: return err; } -/* Return next ELF section of sh_type after scn, or first of that type if scn is NULL. */ -static Elf_Scn *elf_find_next_scn_by_type(Elf *elf, int sh_type, Elf_Scn *scn) -{ - while ((scn = elf_nextscn(elf, scn)) != NULL) { - GElf_Shdr sh; - - if (!gelf_getshdr(scn, &sh)) - continue; - if (sh.sh_type == sh_type) - return scn; - } - return NULL; -} - -/* Find offset of function name in the provided ELF object. "binary_path" is - * the path to the ELF binary represented by "elf", and only used for error - * reporting matters. "name" matches symbol name or name@@LIB for library - * functions. - */ -static long elf_find_func_offset(Elf *elf, const char *binary_path, const char *name) -{ - int i, sh_types[2] = { SHT_DYNSYM, SHT_SYMTAB }; - bool is_shared_lib, is_name_qualified; - long ret = -ENOENT; - size_t name_len; - GElf_Ehdr ehdr; - - if (!gelf_getehdr(elf, &ehdr)) { - pr_warn("elf: failed to get ehdr from %s: %s\n", binary_path, elf_errmsg(-1)); - ret = -LIBBPF_ERRNO__FORMAT; - goto out; - } - /* for shared lib case, we do not need to calculate relative offset */ - is_shared_lib = ehdr.e_type == ET_DYN; - - name_len = strlen(name); - /* Does name specify "@@LIB"? */ - is_name_qualified = strstr(name, "@@") != NULL; - - /* Search SHT_DYNSYM, SHT_SYMTAB for symbol. This search order is used because if - * a binary is stripped, it may only have SHT_DYNSYM, and a fully-statically - * linked binary may not have SHT_DYMSYM, so absence of a section should not be - * reported as a warning/error. - */ - for (i = 0; i < ARRAY_SIZE(sh_types); i++) { - size_t nr_syms, strtabidx, idx; - Elf_Data *symbols = NULL; - Elf_Scn *scn = NULL; - int last_bind = -1; - const char *sname; - GElf_Shdr sh; - - scn = elf_find_next_scn_by_type(elf, sh_types[i], NULL); - if (!scn) { - pr_debug("elf: failed to find symbol table ELF sections in '%s'\n", - binary_path); - continue; - } - if (!gelf_getshdr(scn, &sh)) - continue; - strtabidx = sh.sh_link; - symbols = elf_getdata(scn, 0); - if (!symbols) { - pr_warn("elf: failed to get symbols for symtab section in '%s': %s\n", - binary_path, elf_errmsg(-1)); - ret = -LIBBPF_ERRNO__FORMAT; - goto out; - } - nr_syms = symbols->d_size / sh.sh_entsize; - - for (idx = 0; idx < nr_syms; idx++) { - int curr_bind; - GElf_Sym sym; - Elf_Scn *sym_scn; - GElf_Shdr sym_sh; - - if (!gelf_getsym(symbols, idx, &sym)) - continue; - - if (GELF_ST_TYPE(sym.st_info) != STT_FUNC) - continue; - - sname = elf_strptr(elf, strtabidx, sym.st_name); - if (!sname) - continue; - - curr_bind = GELF_ST_BIND(sym.st_info); - - /* User can specify func, func@@LIB or func@@LIB_VERSION. */ - if (strncmp(sname, name, name_len) != 0) - continue; - /* ...but we don't want a search for "foo" to match 'foo2" also, so any - * additional characters in sname should be of the form "@@LIB". - */ - if (!is_name_qualified && sname[name_len] != '\0' && sname[name_len] != '@') - continue; - - if (ret >= 0) { - /* handle multiple matches */ - if (last_bind != STB_WEAK && curr_bind != STB_WEAK) { - /* Only accept one non-weak bind. */ - pr_warn("elf: ambiguous match for '%s', '%s' in '%s'\n", - sname, name, binary_path); - ret = -LIBBPF_ERRNO__FORMAT; - goto out; - } else if (curr_bind == STB_WEAK) { - /* already have a non-weak bind, and - * this is a weak bind, so ignore. - */ - continue; - } - } - - /* Transform symbol's virtual address (absolute for - * binaries and relative for shared libs) into file - * offset, which is what kernel is expecting for - * uprobe/uretprobe attachment. - * See Documentation/trace/uprobetracer.rst for more - * details. - * This is done by looking up symbol's containing - * section's header and using it's virtual address - * (sh_addr) and corresponding file offset (sh_offset) - * to transform sym.st_value (virtual address) into - * desired final file offset. - */ - sym_scn = elf_getscn(elf, sym.st_shndx); - if (!sym_scn) - continue; - if (!gelf_getshdr(sym_scn, &sym_sh)) - continue; - - ret = sym.st_value - sym_sh.sh_addr + sym_sh.sh_offset; - last_bind = curr_bind; - } - if (ret > 0) - break; - } - - if (ret > 0) { - pr_debug("elf: symbol address match for '%s' in '%s': 0x%lx\n", name, binary_path, - ret); - } else { - if (ret == 0) { - pr_warn("elf: '%s' is 0 in symtab for '%s': %s\n", name, binary_path, - is_shared_lib ? "should not be 0 in a shared library" : - "try using shared library path instead"); - ret = -ENOENT; - } else { - pr_warn("elf: failed to find symbol '%s' in '%s'\n", name, binary_path); - } - } -out: - return ret; -} - -/* Find offset of function name in ELF object specified by path. "name" matches - * symbol name or name@@LIB for library functions. - */ -static long elf_find_func_offset_from_file(const char *binary_path, const char *name) -{ - char errmsg[STRERR_BUFSIZE]; - long ret = -ENOENT; - Elf *elf; - int fd; - - fd = open(binary_path, O_RDONLY | O_CLOEXEC); - if (fd < 0) { - ret = -errno; - pr_warn("failed to open %s: %s\n", binary_path, - libbpf_strerror_r(ret, errmsg, sizeof(errmsg))); - return ret; - } - elf = elf_begin(fd, ELF_C_READ_MMAP, NULL); - if (!elf) { - pr_warn("elf: could not read elf from %s: %s\n", binary_path, elf_errmsg(-1)); - close(fd); - return -LIBBPF_ERRNO__FORMAT; - } - - ret = elf_find_func_offset(elf, binary_path, name); - elf_end(elf); - close(fd); - return ret; -} - /* Find offset of function name in archive specified by path. Currently * supported are .zip files that do not compress their contents, as used on * Android in the form of APKs, for example. "file_name" is the name of the ELF @@ -11136,6 +11243,120 @@ static int resolve_full_path(const char *file, char *result, size_t result_sz) return -ENOENT; } +struct bpf_link * +bpf_program__attach_uprobe_multi(const struct bpf_program *prog, + pid_t pid, + const char *path, + const char *func_pattern, + const struct bpf_uprobe_multi_opts *opts) +{ + const unsigned long *ref_ctr_offsets = NULL, *offsets = NULL; + LIBBPF_OPTS(bpf_link_create_opts, lopts); + unsigned long *resolved_offsets = NULL; + int err = 0, link_fd, prog_fd; + struct bpf_link *link = NULL; + char errmsg[STRERR_BUFSIZE]; + char full_path[PATH_MAX]; + const __u64 *cookies; + const char **syms; + size_t cnt; + + if (!OPTS_VALID(opts, bpf_uprobe_multi_opts)) + return libbpf_err_ptr(-EINVAL); + + syms = OPTS_GET(opts, syms, NULL); + offsets = OPTS_GET(opts, offsets, NULL); + ref_ctr_offsets = OPTS_GET(opts, ref_ctr_offsets, NULL); + cookies = OPTS_GET(opts, cookies, NULL); + cnt = OPTS_GET(opts, cnt, 0); + + /* + * User can specify 2 mutually exclusive set of inputs: + * + * 1) use only path/func_pattern/pid arguments + * + * 2) use path/pid with allowed combinations of: + * syms/offsets/ref_ctr_offsets/cookies/cnt + * + * - syms and offsets are mutually exclusive + * - ref_ctr_offsets and cookies are optional + * + * Any other usage results in error. + */ + + if (!path) + return libbpf_err_ptr(-EINVAL); + if (!func_pattern && cnt == 0) + return libbpf_err_ptr(-EINVAL); + + if (func_pattern) { + if (syms || offsets || ref_ctr_offsets || cookies || cnt) + return libbpf_err_ptr(-EINVAL); + } else { + if (!!syms == !!offsets) + return libbpf_err_ptr(-EINVAL); + } + + if (func_pattern) { + if (!strchr(path, '/')) { + err = resolve_full_path(path, full_path, sizeof(full_path)); + if (err) { + pr_warn("prog '%s': failed to resolve full path for '%s': %d\n", + prog->name, path, err); + return libbpf_err_ptr(err); + } + path = full_path; + } + + err = elf_resolve_pattern_offsets(path, func_pattern, + &resolved_offsets, &cnt); + if (err < 0) + return libbpf_err_ptr(err); + offsets = resolved_offsets; + } else if (syms) { + err = elf_resolve_syms_offsets(path, cnt, syms, &resolved_offsets); + if (err < 0) + return libbpf_err_ptr(err); + offsets = resolved_offsets; + } + + lopts.uprobe_multi.path = path; + lopts.uprobe_multi.offsets = offsets; + lopts.uprobe_multi.ref_ctr_offsets = ref_ctr_offsets; + lopts.uprobe_multi.cookies = cookies; + lopts.uprobe_multi.cnt = cnt; + lopts.uprobe_multi.flags = OPTS_GET(opts, retprobe, false) ? BPF_F_UPROBE_MULTI_RETURN : 0; + + if (pid == 0) + pid = getpid(); + if (pid > 0) + lopts.uprobe_multi.pid = pid; + + link = calloc(1, sizeof(*link)); + if (!link) { + err = -ENOMEM; + goto error; + } + link->detach = &bpf_link__detach_fd; + + prog_fd = bpf_program__fd(prog); + link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &lopts); + if (link_fd < 0) { + err = -errno; + pr_warn("prog '%s': failed to attach multi-uprobe: %s\n", + prog->name, libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + goto error; + } + link->fd = link_fd; + free(resolved_offsets); + return link; + +error: + free(resolved_offsets); + free(link); + return libbpf_err_ptr(err); +} + LIBBPF_API struct bpf_link * bpf_program__attach_uprobe_opts(const struct bpf_program *prog, pid_t pid, const char *binary_path, size_t func_offset, @@ -11680,11 +11901,10 @@ static int attach_lsm(const struct bpf_program *prog, long cookie, struct bpf_li } static struct bpf_link * -bpf_program__attach_fd(const struct bpf_program *prog, int target_fd, int btf_id, - const char *target_name) +bpf_program_attach_fd(const struct bpf_program *prog, + int target_fd, const char *target_name, + const struct bpf_link_create_opts *opts) { - DECLARE_LIBBPF_OPTS(bpf_link_create_opts, opts, - .target_btf_id = btf_id); enum bpf_attach_type attach_type; char errmsg[STRERR_BUFSIZE]; struct bpf_link *link; @@ -11702,7 +11922,7 @@ bpf_program__attach_fd(const struct bpf_program *prog, int target_fd, int btf_id link->detach = &bpf_link__detach_fd; attach_type = bpf_program__expected_attach_type(prog); - link_fd = bpf_link_create(prog_fd, target_fd, attach_type, &opts); + link_fd = bpf_link_create(prog_fd, target_fd, attach_type, opts); if (link_fd < 0) { link_fd = -errno; free(link); @@ -11718,19 +11938,54 @@ bpf_program__attach_fd(const struct bpf_program *prog, int target_fd, int btf_id struct bpf_link * bpf_program__attach_cgroup(const struct bpf_program *prog, int cgroup_fd) { - return bpf_program__attach_fd(prog, cgroup_fd, 0, "cgroup"); + return bpf_program_attach_fd(prog, cgroup_fd, "cgroup", NULL); } struct bpf_link * bpf_program__attach_netns(const struct bpf_program *prog, int netns_fd) { - return bpf_program__attach_fd(prog, netns_fd, 0, "netns"); + return bpf_program_attach_fd(prog, netns_fd, "netns", NULL); } struct bpf_link *bpf_program__attach_xdp(const struct bpf_program *prog, int ifindex) { /* target_fd/target_ifindex use the same field in LINK_CREATE */ - return bpf_program__attach_fd(prog, ifindex, 0, "xdp"); + return bpf_program_attach_fd(prog, ifindex, "xdp", NULL); +} + +struct bpf_link * +bpf_program__attach_tcx(const struct bpf_program *prog, int ifindex, + const struct bpf_tcx_opts *opts) +{ + LIBBPF_OPTS(bpf_link_create_opts, link_create_opts); + __u32 relative_id; + int relative_fd; + + if (!OPTS_VALID(opts, bpf_tcx_opts)) + return libbpf_err_ptr(-EINVAL); + + relative_id = OPTS_GET(opts, relative_id, 0); + relative_fd = OPTS_GET(opts, relative_fd, 0); + + /* validate we don't have unexpected combinations of non-zero fields */ + if (!ifindex) { + pr_warn("prog '%s': target netdevice ifindex cannot be zero\n", + prog->name); + return libbpf_err_ptr(-EINVAL); + } + if (relative_fd && relative_id) { + pr_warn("prog '%s': relative_fd and relative_id cannot be set at the same time\n", + prog->name); + return libbpf_err_ptr(-EINVAL); + } + + link_create_opts.tcx.expected_revision = OPTS_GET(opts, expected_revision, 0); + link_create_opts.tcx.relative_fd = relative_fd; + link_create_opts.tcx.relative_id = relative_id; + link_create_opts.flags = OPTS_GET(opts, flags, 0); + + /* target_fd/target_ifindex use the same field in LINK_CREATE */ + return bpf_program_attach_fd(prog, ifindex, "tcx", &link_create_opts); } struct bpf_link *bpf_program__attach_freplace(const struct bpf_program *prog, @@ -11752,11 +12007,16 @@ struct bpf_link *bpf_program__attach_freplace(const struct bpf_program *prog, } if (target_fd) { + LIBBPF_OPTS(bpf_link_create_opts, target_opts); + btf_id = libbpf_find_prog_btf_id(attach_func_name, target_fd); if (btf_id < 0) return libbpf_err_ptr(btf_id); - return bpf_program__attach_fd(prog, target_fd, btf_id, "freplace"); + target_opts.target_btf_id = btf_id; + + return bpf_program_attach_fd(prog, target_fd, "freplace", + &target_opts); } else { /* no target, so use raw_tracepoint_open for compatibility * with old kernels @@ -11811,6 +12071,48 @@ static int attach_iter(const struct bpf_program *prog, long cookie, struct bpf_l return libbpf_get_error(*link); } +struct bpf_link *bpf_program__attach_netfilter(const struct bpf_program *prog, + const struct bpf_netfilter_opts *opts) +{ + LIBBPF_OPTS(bpf_link_create_opts, lopts); + struct bpf_link *link; + int prog_fd, link_fd; + + if (!OPTS_VALID(opts, bpf_netfilter_opts)) + return libbpf_err_ptr(-EINVAL); + + prog_fd = bpf_program__fd(prog); + if (prog_fd < 0) { + pr_warn("prog '%s': can't attach before loaded\n", prog->name); + return libbpf_err_ptr(-EINVAL); + } + + link = calloc(1, sizeof(*link)); + if (!link) + return libbpf_err_ptr(-ENOMEM); + + link->detach = &bpf_link__detach_fd; + + lopts.netfilter.pf = OPTS_GET(opts, pf, 0); + lopts.netfilter.hooknum = OPTS_GET(opts, hooknum, 0); + lopts.netfilter.priority = OPTS_GET(opts, priority, 0); + lopts.netfilter.flags = OPTS_GET(opts, flags, 0); + + link_fd = bpf_link_create(prog_fd, 0, BPF_NETFILTER, &lopts); + if (link_fd < 0) { + char errmsg[STRERR_BUFSIZE]; + + link_fd = -errno; + free(link); + pr_warn("prog '%s': failed to attach to netfilter: %s\n", + prog->name, libbpf_strerror_r(link_fd, errmsg, sizeof(errmsg))); + return libbpf_err_ptr(link_fd); + } + link->fd = link_fd; + + return link; +} + struct bpf_link *bpf_program__attach(const struct bpf_program *prog) { struct bpf_link *link = NULL; diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 754da73c643b..0e52621cba43 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -266,6 +266,7 @@ LIBBPF_API int bpf_object__pin_programs(struct bpf_object *obj, LIBBPF_API int bpf_object__unpin_programs(struct bpf_object *obj, const char *path); LIBBPF_API int bpf_object__pin(struct bpf_object *object, const char *path); +LIBBPF_API int bpf_object__unpin(struct bpf_object *object, const char *path); LIBBPF_API const char *bpf_object__name(const struct bpf_object *obj); LIBBPF_API unsigned int bpf_object__kversion(const struct bpf_object *obj); @@ -529,6 +530,57 @@ bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog, const char *pattern, const struct bpf_kprobe_multi_opts *opts); +struct bpf_uprobe_multi_opts { + /* size of this struct, for forward/backward compatibility */ + size_t sz; + /* array of function symbols to attach to */ + const char **syms; + /* array of function addresses to attach to */ + const unsigned long *offsets; + /* optional, array of associated ref counter offsets */ + const unsigned long *ref_ctr_offsets; + /* optional, array of associated BPF cookies */ + const __u64 *cookies; + /* number of elements in syms/addrs/cookies arrays */ + size_t cnt; + /* create return uprobes */ + bool retprobe; + size_t :0; +}; + +#define bpf_uprobe_multi_opts__last_field retprobe + +/** + * @brief **bpf_program__attach_uprobe_multi()** attaches a BPF program + * to multiple uprobes with uprobe_multi link. + * + * User can specify 2 mutually exclusive set of inputs: + * + * 1) use only path/func_pattern/pid arguments + * + * 2) use path/pid with allowed combinations of + * syms/offsets/ref_ctr_offsets/cookies/cnt + * + * - syms and offsets are mutually exclusive + * - ref_ctr_offsets and cookies are optional + * + * + * @param prog BPF program to attach + * @param pid Process ID to attach the uprobe to, 0 for self (own process), + * -1 for all processes + * @param binary_path Path to binary + * @param func_pattern Regular expression to specify functions to attach + * BPF program to + * @param opts Additional options (see **struct bpf_uprobe_multi_opts**) + * @return 0, on success; negative error code, otherwise + */ +LIBBPF_API struct bpf_link * +bpf_program__attach_uprobe_multi(const struct bpf_program *prog, + pid_t pid, + const char *binary_path, + const char *func_pattern, + const struct bpf_uprobe_multi_opts *opts); + struct bpf_ksyscall_opts { /* size of this struct, for forward/backward compatibility */ size_t sz; @@ -718,6 +770,36 @@ LIBBPF_API struct bpf_link * bpf_program__attach_freplace(const struct bpf_program *prog, int target_fd, const char *attach_func_name); +struct bpf_netfilter_opts { + /* size of this struct, for forward/backward compatibility */ + size_t sz; + + __u32 pf; + __u32 hooknum; + __s32 priority; + __u32 flags; +}; +#define bpf_netfilter_opts__last_field flags + +LIBBPF_API struct bpf_link * +bpf_program__attach_netfilter(const struct bpf_program *prog, + const struct bpf_netfilter_opts *opts); + +struct bpf_tcx_opts { + /* size of this struct, for forward/backward compatibility */ + size_t sz; + __u32 flags; + __u32 relative_fd; + __u32 relative_id; + __u64 expected_revision; + size_t :0; +}; +#define bpf_tcx_opts__last_field expected_revision + +LIBBPF_API struct bpf_link * +bpf_program__attach_tcx(const struct bpf_program *prog, int ifindex, + const struct bpf_tcx_opts *opts); + struct bpf_map; LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map); @@ -1090,9 +1172,10 @@ struct bpf_xdp_query_opts { __u32 skb_prog_id; /* output */ __u8 attach_mode; /* output */ __u64 feature_flags; /* output */ + __u32 xdp_zc_max_segs; /* output */ size_t :0; }; -#define bpf_xdp_query_opts__last_field feature_flags +#define bpf_xdp_query_opts__last_field xdp_zc_max_segs LIBBPF_API int bpf_xdp_attach(int ifindex, int prog_fd, __u32 flags, const struct bpf_xdp_attach_opts *opts); diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index 7521a2fb7626..57712321490f 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -395,4 +395,9 @@ LIBBPF_1.2.0 { LIBBPF_1.3.0 { global: bpf_obj_pin_opts; + bpf_object__unpin; + bpf_prog_detach_opts; + bpf_program__attach_netfilter; + bpf_program__attach_tcx; + bpf_program__attach_uprobe_multi; } LIBBPF_1.2.0; diff --git a/tools/lib/bpf/libbpf_common.h b/tools/lib/bpf/libbpf_common.h index 9a7937f339df..b7060f254486 100644 --- a/tools/lib/bpf/libbpf_common.h +++ b/tools/lib/bpf/libbpf_common.h @@ -70,4 +70,20 @@ }; \ }) +/* Helper macro to clear and optionally reinitialize libbpf options struct + * + * Small helper macro to reset all fields and to reinitialize the common + * structure size member. Values provided by users in struct initializer- + * syntax as varargs can be provided as well to reinitialize options struct + * specific members. + */ +#define LIBBPF_OPTS_RESET(NAME, ...) \ + do { \ + memset(&NAME, 0, sizeof(NAME)); \ + NAME = (typeof(NAME)) { \ + .sz = sizeof(NAME), \ + __VA_ARGS__ \ + }; \ + } while (0) + #endif /* __LIBBPF_LIBBPF_COMMON_H */ diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index e4d05662a96c..f0f08635adb0 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -15,6 +15,7 @@ #include <linux/err.h> #include <fcntl.h> #include <unistd.h> +#include <libelf.h> #include "relo_core.h" /* make sure libbpf doesn't use kernel-only integer typedefs */ @@ -354,6 +355,8 @@ enum kern_feature_id { FEAT_BTF_ENUM64, /* Kernel uses syscall wrapper (CONFIG_ARCH_HAS_SYSCALL_WRAPPER) */ FEAT_SYSCALL_WRAPPER, + /* BPF multi-uprobe link support */ + FEAT_UPROBE_MULTI_LINK, __FEAT_CNT, }; @@ -577,4 +580,22 @@ static inline bool is_pow_of_2(size_t x) #define PROG_LOAD_ATTEMPTS 5 int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int attempts); +bool glob_match(const char *str, const char *pat); + +long elf_find_func_offset(Elf *elf, const char *binary_path, const char *name); +long elf_find_func_offset_from_file(const char *binary_path, const char *name); + +struct elf_fd { + Elf *elf; + int fd; +}; + +int elf_open(const char *binary_path, struct elf_fd *elf_fd); +void elf_close(struct elf_fd *elf_fd); + +int elf_resolve_syms_offsets(const char *binary_path, int cnt, + const char **syms, unsigned long **poffsets); +int elf_resolve_pattern_offsets(const char *binary_path, const char *pattern, + unsigned long **poffsets, size_t *pcnt); + #endif /* __LIBBPF_LIBBPF_INTERNAL_H */ diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c index 84dd5fa14905..090bcf6e3b3d 100644 --- a/tools/lib/bpf/netlink.c +++ b/tools/lib/bpf/netlink.c @@ -45,6 +45,7 @@ struct xdp_id_md { struct xdp_features_md { int ifindex; + __u32 xdp_zc_max_segs; __u64 flags; }; @@ -421,6 +422,9 @@ static int parse_xdp_features(struct nlmsghdr *nh, libbpf_dump_nlmsg_t fn, return NL_CONT; md->flags = libbpf_nla_getattr_u64(tb[NETDEV_A_DEV_XDP_FEATURES]); + if (tb[NETDEV_A_DEV_XDP_ZC_MAX_SEGS]) + md->xdp_zc_max_segs = + libbpf_nla_getattr_u32(tb[NETDEV_A_DEV_XDP_ZC_MAX_SEGS]); return NL_DONE; } @@ -493,6 +497,7 @@ int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts) return libbpf_err(err); opts->feature_flags = md.flags; + opts->xdp_zc_max_segs = md.xdp_zc_max_segs; skip_feature_flags: return 0; diff --git a/tools/lib/bpf/relo_core.c b/tools/lib/bpf/relo_core.c index a26b2f5fa0fc..63a4d5ad12d1 100644 --- a/tools/lib/bpf/relo_core.c +++ b/tools/lib/bpf/relo_core.c @@ -776,7 +776,7 @@ static int bpf_core_calc_field_relo(const char *prog_name, break; case BPF_CORE_FIELD_SIGNED: *val = (btf_is_any_enum(mt) && BTF_INFO_KFLAG(mt->info)) || - (btf_int_encoding(mt) & BTF_INT_SIGNED); + (btf_is_int(mt) && (btf_int_encoding(mt) & BTF_INT_SIGNED)); if (validate) *validate = true; /* signedness is never ambiguous */ break; diff --git a/tools/lib/bpf/usdt.bpf.h b/tools/lib/bpf/usdt.bpf.h index 0bd4c135acc2..f6763300b26a 100644 --- a/tools/lib/bpf/usdt.bpf.h +++ b/tools/lib/bpf/usdt.bpf.h @@ -4,8 +4,8 @@ #define __USDT_BPF_H__ #include <linux/errno.h> -#include <bpf/bpf_helpers.h> -#include <bpf/bpf_tracing.h> +#include "bpf_helpers.h" +#include "bpf_tracing.h" /* Below types and maps are internal implementation details of libbpf's USDT * support and are subjects to change. Also, bpf_usdt_xxx() API helpers should diff --git a/tools/lib/bpf/usdt.c b/tools/lib/bpf/usdt.c index f1a141555f08..93794f01bb67 100644 --- a/tools/lib/bpf/usdt.c +++ b/tools/lib/bpf/usdt.c @@ -250,6 +250,7 @@ struct usdt_manager { bool has_bpf_cookie; bool has_sema_refcnt; + bool has_uprobe_multi; }; struct usdt_manager *usdt_manager_new(struct bpf_object *obj) @@ -284,6 +285,11 @@ struct usdt_manager *usdt_manager_new(struct bpf_object *obj) */ man->has_sema_refcnt = faccessat(AT_FDCWD, ref_ctr_sysfs_path, F_OK, AT_EACCESS) == 0; + /* + * Detect kernel support for uprobe multi link to be used for attaching + * usdt probes. + */ + man->has_uprobe_multi = kernel_supports(obj, FEAT_UPROBE_MULTI_LINK); return man; } @@ -808,6 +814,8 @@ struct bpf_link_usdt { long abs_ip; struct bpf_link *link; } *uprobes; + + struct bpf_link *multi_link; }; static int bpf_link_usdt_detach(struct bpf_link *link) @@ -816,6 +824,9 @@ static int bpf_link_usdt_detach(struct bpf_link *link) struct usdt_manager *man = usdt_link->usdt_man; int i; + bpf_link__destroy(usdt_link->multi_link); + + /* When having multi_link, uprobe_cnt is 0 */ for (i = 0; i < usdt_link->uprobe_cnt; i++) { /* detach underlying uprobe link */ bpf_link__destroy(usdt_link->uprobes[i].link); @@ -852,8 +863,11 @@ static int bpf_link_usdt_detach(struct bpf_link *link) * system is so exhausted on memory, it's the least of user's * concerns, probably. * So just do our best here to return those IDs to usdt_manager. + * Another edge case when we can legitimately get NULL is when + * new_cnt is zero, which can happen in some edge cases, so we + * need to be careful about that. */ - if (new_free_ids) { + if (new_free_ids || new_cnt == 0) { memcpy(new_free_ids + man->free_spec_cnt, usdt_link->spec_ids, usdt_link->spec_cnt * sizeof(*usdt_link->spec_ids)); man->free_spec_ids = new_free_ids; @@ -943,32 +957,24 @@ struct bpf_link *usdt_manager_attach_usdt(struct usdt_manager *man, const struct const char *usdt_provider, const char *usdt_name, __u64 usdt_cookie) { - int i, fd, err, spec_map_fd, ip_map_fd; + unsigned long *offsets = NULL, *ref_ctr_offsets = NULL; + int i, err, spec_map_fd, ip_map_fd; LIBBPF_OPTS(bpf_uprobe_opts, opts); struct hashmap *specs_hash = NULL; struct bpf_link_usdt *link = NULL; struct usdt_target *targets = NULL; + __u64 *cookies = NULL; + struct elf_fd elf_fd; size_t target_cnt; - Elf *elf; spec_map_fd = bpf_map__fd(man->specs_map); ip_map_fd = bpf_map__fd(man->ip_to_spec_id_map); - fd = open(path, O_RDONLY | O_CLOEXEC); - if (fd < 0) { - err = -errno; - pr_warn("usdt: failed to open ELF binary '%s': %d\n", path, err); + err = elf_open(path, &elf_fd); + if (err) return libbpf_err_ptr(err); - } - - elf = elf_begin(fd, ELF_C_READ_MMAP, NULL); - if (!elf) { - err = -EBADF; - pr_warn("usdt: failed to parse ELF binary '%s': %s\n", path, elf_errmsg(-1)); - goto err_out; - } - err = sanity_check_usdt_elf(elf, path); + err = sanity_check_usdt_elf(elf_fd.elf, path); if (err) goto err_out; @@ -981,7 +987,7 @@ struct bpf_link *usdt_manager_attach_usdt(struct usdt_manager *man, const struct /* discover USDT in given binary, optionally limiting * activations to a given PID, if pid > 0 */ - err = collect_usdt_targets(man, elf, path, pid, usdt_provider, usdt_name, + err = collect_usdt_targets(man, elf_fd.elf, path, pid, usdt_provider, usdt_name, usdt_cookie, &targets, &target_cnt); if (err <= 0) { err = (err == 0) ? -ENOENT : err; @@ -1004,10 +1010,21 @@ struct bpf_link *usdt_manager_attach_usdt(struct usdt_manager *man, const struct link->link.detach = &bpf_link_usdt_detach; link->link.dealloc = &bpf_link_usdt_dealloc; - link->uprobes = calloc(target_cnt, sizeof(*link->uprobes)); - if (!link->uprobes) { - err = -ENOMEM; - goto err_out; + if (man->has_uprobe_multi) { + offsets = calloc(target_cnt, sizeof(*offsets)); + cookies = calloc(target_cnt, sizeof(*cookies)); + ref_ctr_offsets = calloc(target_cnt, sizeof(*ref_ctr_offsets)); + + if (!offsets || !ref_ctr_offsets || !cookies) { + err = -ENOMEM; + goto err_out; + } + } else { + link->uprobes = calloc(target_cnt, sizeof(*link->uprobes)); + if (!link->uprobes) { + err = -ENOMEM; + goto err_out; + } } for (i = 0; i < target_cnt; i++) { @@ -1048,37 +1065,65 @@ struct bpf_link *usdt_manager_attach_usdt(struct usdt_manager *man, const struct goto err_out; } - opts.ref_ctr_offset = target->sema_off; - opts.bpf_cookie = man->has_bpf_cookie ? spec_id : 0; - uprobe_link = bpf_program__attach_uprobe_opts(prog, pid, path, - target->rel_ip, &opts); - err = libbpf_get_error(uprobe_link); - if (err) { - pr_warn("usdt: failed to attach uprobe #%d for '%s:%s' in '%s': %d\n", - i, usdt_provider, usdt_name, path, err); + if (man->has_uprobe_multi) { + offsets[i] = target->rel_ip; + ref_ctr_offsets[i] = target->sema_off; + cookies[i] = spec_id; + } else { + opts.ref_ctr_offset = target->sema_off; + opts.bpf_cookie = man->has_bpf_cookie ? spec_id : 0; + uprobe_link = bpf_program__attach_uprobe_opts(prog, pid, path, + target->rel_ip, &opts); + err = libbpf_get_error(uprobe_link); + if (err) { + pr_warn("usdt: failed to attach uprobe #%d for '%s:%s' in '%s': %d\n", + i, usdt_provider, usdt_name, path, err); + goto err_out; + } + + link->uprobes[i].link = uprobe_link; + link->uprobes[i].abs_ip = target->abs_ip; + link->uprobe_cnt++; + } + } + + if (man->has_uprobe_multi) { + LIBBPF_OPTS(bpf_uprobe_multi_opts, opts_multi, + .ref_ctr_offsets = ref_ctr_offsets, + .offsets = offsets, + .cookies = cookies, + .cnt = target_cnt, + ); + + link->multi_link = bpf_program__attach_uprobe_multi(prog, pid, path, + NULL, &opts_multi); + if (!link->multi_link) { + err = -errno; + pr_warn("usdt: failed to attach uprobe multi for '%s:%s' in '%s': %d\n", + usdt_provider, usdt_name, path, err); goto err_out; } - link->uprobes[i].link = uprobe_link; - link->uprobes[i].abs_ip = target->abs_ip; - link->uprobe_cnt++; + free(offsets); + free(ref_ctr_offsets); + free(cookies); } free(targets); hashmap__free(specs_hash); - elf_end(elf); - close(fd); - + elf_close(&elf_fd); return &link->link; err_out: + free(offsets); + free(ref_ctr_offsets); + free(cookies); + if (link) bpf_link__destroy(&link->link); free(targets); hashmap__free(specs_hash); - if (elf) - elf_end(elf); - close(fd); + elf_close(&elf_fd); return libbpf_err_ptr(err); } diff --git a/tools/lib/perf/include/perf/event.h b/tools/lib/perf/include/perf/event.h index ba2dcf64f4e6..ae64090184d3 100644 --- a/tools/lib/perf/include/perf/event.h +++ b/tools/lib/perf/include/perf/event.h @@ -148,8 +148,18 @@ struct perf_record_switch { struct perf_record_header_attr { struct perf_event_header header; struct perf_event_attr attr; - __u64 id[]; -}; + /* + * Array of u64 id follows here but we cannot use a flexible array + * because size of attr in the data can be different then current + * version. Please use perf_record_header_attr_id() below. + * + * __u64 id[]; // do not use this + */ +}; + +/* Returns the pointer to id array based on the actual attr size. */ +#define perf_record_header_attr_id(evt) \ + ((void *)&(evt)->attr.attr + (evt)->attr.attr.size) enum { PERF_CPU_MAP__CPUS = 0, diff --git a/tools/lib/perf/mmap.c b/tools/lib/perf/mmap.c index 0d1634cedf44..2184814b37dd 100644 --- a/tools/lib/perf/mmap.c +++ b/tools/lib/perf/mmap.c @@ -392,6 +392,72 @@ static u64 read_perf_counter(unsigned int counter) static u64 read_timestamp(void) { return read_sysreg(cntvct_el0); } +/* __riscv_xlen contains the witdh of the native base integer, here 64-bit */ +#elif defined(__riscv) && __riscv_xlen == 64 + +/* TODO: implement rv32 support */ + +#define CSR_CYCLE 0xc00 +#define CSR_TIME 0xc01 + +#define csr_read(csr) \ +({ \ + register unsigned long __v; \ + __asm__ __volatile__ ("csrr %0, %1" \ + : "=r" (__v) \ + : "i" (csr) : ); \ + __v; \ +}) + +static unsigned long csr_read_num(int csr_num) +{ +#define switchcase_csr_read(__csr_num, __val) {\ + case __csr_num: \ + __val = csr_read(__csr_num); \ + break; } +#define switchcase_csr_read_2(__csr_num, __val) {\ + switchcase_csr_read(__csr_num + 0, __val) \ + switchcase_csr_read(__csr_num + 1, __val)} +#define switchcase_csr_read_4(__csr_num, __val) {\ + switchcase_csr_read_2(__csr_num + 0, __val) \ + switchcase_csr_read_2(__csr_num + 2, __val)} +#define switchcase_csr_read_8(__csr_num, __val) {\ + switchcase_csr_read_4(__csr_num + 0, __val) \ + switchcase_csr_read_4(__csr_num + 4, __val)} +#define switchcase_csr_read_16(__csr_num, __val) {\ + switchcase_csr_read_8(__csr_num + 0, __val) \ + switchcase_csr_read_8(__csr_num + 8, __val)} +#define switchcase_csr_read_32(__csr_num, __val) {\ + switchcase_csr_read_16(__csr_num + 0, __val) \ + switchcase_csr_read_16(__csr_num + 16, __val)} + + unsigned long ret = 0; + + switch (csr_num) { + switchcase_csr_read_32(CSR_CYCLE, ret) + default: + break; + } + + return ret; +#undef switchcase_csr_read_32 +#undef switchcase_csr_read_16 +#undef switchcase_csr_read_8 +#undef switchcase_csr_read_4 +#undef switchcase_csr_read_2 +#undef switchcase_csr_read +} + +static u64 read_perf_counter(unsigned int counter) +{ + return csr_read_num(CSR_CYCLE + counter); +} + +static u64 read_timestamp(void) +{ + return csr_read_num(CSR_TIME); +} + #else static u64 read_perf_counter(unsigned int counter __maybe_unused) { return 0; } static u64 read_timestamp(void) { return 0; } diff --git a/tools/mm/Makefile b/tools/mm/Makefile index 6c1da51f4177..1c5606cc3334 100644 --- a/tools/mm/Makefile +++ b/tools/mm/Makefile @@ -8,8 +8,8 @@ TARGETS=page-types slabinfo page_owner_sort LIB_DIR = ../lib/api LIBS = $(LIB_DIR)/libapi.a -CFLAGS += -Wall -Wextra -I../lib/ -LDFLAGS += $(LIBS) +CFLAGS += -Wall -Wextra -I../lib/ -pthread +LDFLAGS += $(LIBS) -pthread all: $(TARGETS) diff --git a/tools/net/ynl/Makefile b/tools/net/ynl/Makefile index d664b36deb5b..8156f03e23ac 100644 --- a/tools/net/ynl/Makefile +++ b/tools/net/ynl/Makefile @@ -3,6 +3,7 @@ SUBDIRS = lib generated samples all: $(SUBDIRS) + ./ynl-regen.sh -f -p $(PWD)/../../../ $(SUBDIRS): @if [ -f "$@/Makefile" ] ; then \ diff --git a/tools/net/ynl/cli.py b/tools/net/ynl/cli.py index ffaa8038aa8c..564ecf07cd2c 100755 --- a/tools/net/ynl/cli.py +++ b/tools/net/ynl/cli.py @@ -6,7 +6,7 @@ import json import pprint import time -from lib import YnlFamily +from lib import YnlFamily, Netlink def main(): @@ -19,6 +19,14 @@ def main(): parser.add_argument('--dump', dest='dump', type=str) parser.add_argument('--sleep', dest='sleep', type=int) parser.add_argument('--subscribe', dest='ntf', type=str) + parser.add_argument('--replace', dest='flags', action='append_const', + const=Netlink.NLM_F_REPLACE) + parser.add_argument('--excl', dest='flags', action='append_const', + const=Netlink.NLM_F_EXCL) + parser.add_argument('--create', dest='flags', action='append_const', + const=Netlink.NLM_F_CREATE) + parser.add_argument('--append', dest='flags', action='append_const', + const=Netlink.NLM_F_APPEND) args = parser.parse_args() if args.no_schema: @@ -37,7 +45,7 @@ def main(): time.sleep(args.sleep) if args.do: - reply = ynl.do(args.do, attrs) + reply = ynl.do(args.do, attrs, args.flags) pprint.PrettyPrinter().pprint(reply) if args.dump: reply = ynl.dump(args.dump, attrs) diff --git a/tools/net/ynl/generated/devlink-user.c b/tools/net/ynl/generated/devlink-user.c index 939bd45feaca..3a8d8499fab6 100644 --- a/tools/net/ynl/generated/devlink-user.c +++ b/tools/net/ynl/generated/devlink-user.c @@ -15,7 +15,21 @@ /* Enums */ static const char * const devlink_op_strmap[] = { [3] = "get", + [7] = "port-get", + [DEVLINK_CMD_SB_GET] = "sb-get", + [DEVLINK_CMD_SB_POOL_GET] = "sb-pool-get", + [DEVLINK_CMD_SB_PORT_POOL_GET] = "sb-port-pool-get", + [DEVLINK_CMD_SB_TC_POOL_BIND_GET] = "sb-tc-pool-bind-get", + [DEVLINK_CMD_PARAM_GET] = "param-get", + [DEVLINK_CMD_REGION_GET] = "region-get", [DEVLINK_CMD_INFO_GET] = "info-get", + [DEVLINK_CMD_HEALTH_REPORTER_GET] = "health-reporter-get", + [DEVLINK_CMD_TRAP_GET] = "trap-get", + [DEVLINK_CMD_TRAP_GROUP_GET] = "trap-group-get", + [DEVLINK_CMD_TRAP_POLICER_GET] = "trap-policer-get", + [DEVLINK_CMD_RATE_GET] = "rate-get", + [DEVLINK_CMD_LINECARD_GET] = "linecard-get", + [DEVLINK_CMD_SELFTESTS_GET] = "selftests-get", }; const char *devlink_op_str(int op) @@ -25,6 +39,18 @@ const char *devlink_op_str(int op) return devlink_op_strmap[op]; } +static const char * const devlink_sb_pool_type_strmap[] = { + [0] = "ingress", + [1] = "egress", +}; + +const char *devlink_sb_pool_type_str(enum devlink_sb_pool_type value) +{ + if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_sb_pool_type_strmap)) + return NULL; + return devlink_sb_pool_type_strmap[value]; +} + /* Policies */ struct ynl_policy_attr devlink_dl_info_version_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_INFO_VERSION_NAME] = { .name = "info-version-name", .type = YNL_PT_NUL_STR, }, @@ -88,6 +114,12 @@ struct ynl_policy_attr devlink_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .name = "bus-name", .type = YNL_PT_NUL_STR, }, [DEVLINK_ATTR_DEV_NAME] = { .name = "dev-name", .type = YNL_PT_NUL_STR, }, [DEVLINK_ATTR_PORT_INDEX] = { .name = "port-index", .type = YNL_PT_U32, }, + [DEVLINK_ATTR_SB_INDEX] = { .name = "sb-index", .type = YNL_PT_U32, }, + [DEVLINK_ATTR_SB_POOL_INDEX] = { .name = "sb-pool-index", .type = YNL_PT_U16, }, + [DEVLINK_ATTR_SB_POOL_TYPE] = { .name = "sb-pool-type", .type = YNL_PT_U8, }, + [DEVLINK_ATTR_SB_TC_INDEX] = { .name = "sb-tc-index", .type = YNL_PT_U16, }, + [DEVLINK_ATTR_PARAM_NAME] = { .name = "param-name", .type = YNL_PT_NUL_STR, }, + [DEVLINK_ATTR_REGION_NAME] = { .name = "region-name", .type = YNL_PT_NUL_STR, }, [DEVLINK_ATTR_INFO_DRIVER_NAME] = { .name = "info-driver-name", .type = YNL_PT_NUL_STR, }, [DEVLINK_ATTR_INFO_SERIAL_NUMBER] = { .name = "info-serial-number", .type = YNL_PT_NUL_STR, }, [DEVLINK_ATTR_INFO_VERSION_FIXED] = { .name = "info-version-fixed", .type = YNL_PT_NEST, .nest = &devlink_dl_info_version_nest, }, @@ -95,7 +127,11 @@ struct ynl_policy_attr devlink_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_INFO_VERSION_STORED] = { .name = "info-version-stored", .type = YNL_PT_NEST, .nest = &devlink_dl_info_version_nest, }, [DEVLINK_ATTR_INFO_VERSION_NAME] = { .name = "info-version-name", .type = YNL_PT_NUL_STR, }, [DEVLINK_ATTR_INFO_VERSION_VALUE] = { .name = "info-version-value", .type = YNL_PT_NUL_STR, }, + [DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .name = "health-reporter-name", .type = YNL_PT_NUL_STR, }, + [DEVLINK_ATTR_TRAP_NAME] = { .name = "trap-name", .type = YNL_PT_NUL_STR, }, + [DEVLINK_ATTR_TRAP_GROUP_NAME] = { .name = "trap-group-name", .type = YNL_PT_NUL_STR, }, [DEVLINK_ATTR_RELOAD_FAILED] = { .name = "reload-failed", .type = YNL_PT_U8, }, + [DEVLINK_ATTR_TRAP_POLICER_ID] = { .name = "trap-policer-id", .type = YNL_PT_U32, }, [DEVLINK_ATTR_RELOAD_ACTION] = { .name = "reload-action", .type = YNL_PT_U8, }, [DEVLINK_ATTR_DEV_STATS] = { .name = "dev-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_dev_stats_nest, }, [DEVLINK_ATTR_RELOAD_STATS] = { .name = "reload-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_stats_nest, }, @@ -105,6 +141,8 @@ struct ynl_policy_attr devlink_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_REMOTE_RELOAD_STATS] = { .name = "remote-reload-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_stats_nest, }, [DEVLINK_ATTR_RELOAD_ACTION_INFO] = { .name = "reload-action-info", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_act_info_nest, }, [DEVLINK_ATTR_RELOAD_ACTION_STATS] = { .name = "reload-action-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_act_stats_nest, }, + [DEVLINK_ATTR_RATE_NODE_NAME] = { .name = "rate-node-name", .type = YNL_PT_NUL_STR, }, + [DEVLINK_ATTR_LINECARD_INDEX] = { .name = "linecard-index", .type = YNL_PT_U32, }, }; struct ynl_policy_nest devlink_nest = { @@ -531,6 +569,1126 @@ free_list: return NULL; } +/* ============== DEVLINK_CMD_PORT_GET ============== */ +/* DEVLINK_CMD_PORT_GET - do */ +void devlink_port_get_req_free(struct devlink_port_get_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req); +} + +void devlink_port_get_rsp_free(struct devlink_port_get_rsp *rsp) +{ + free(rsp->bus_name); + free(rsp->dev_name); + free(rsp); +} + +int devlink_port_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_parse_arg *yarg = data; + struct devlink_port_get_rsp *dst; + const struct nlattr *attr; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } else if (type == DEVLINK_ATTR_PORT_INDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.port_index = 1; + dst->port_index = mnl_attr_get_u32(attr); + } + } + + return MNL_CB_OK; +} + +struct devlink_port_get_rsp * +devlink_port_get(struct ynl_sock *ys, struct devlink_port_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct devlink_port_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_PORT_GET, 1); + ys->req_policy = &devlink_nest; + yrs.yarg.rsp_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.port_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = devlink_port_get_rsp_parse; + yrs.rsp_cmd = 7; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + devlink_port_get_rsp_free(rsp); + return NULL; +} + +/* DEVLINK_CMD_PORT_GET - dump */ +int devlink_port_get_rsp_dump_parse(const struct nlmsghdr *nlh, void *data) +{ + struct devlink_port_get_rsp_dump *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } else if (type == DEVLINK_ATTR_PORT_INDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.port_index = 1; + dst->port_index = mnl_attr_get_u32(attr); + } + } + + return MNL_CB_OK; +} + +void devlink_port_get_rsp_list_free(struct devlink_port_get_rsp_list *rsp) +{ + struct devlink_port_get_rsp_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + free(rsp->obj.bus_name); + free(rsp->obj.dev_name); + free(rsp); + } +} + +struct devlink_port_get_rsp_list * +devlink_port_get_dump(struct ynl_sock *ys, + struct devlink_port_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct devlink_port_get_rsp_list); + yds.cb = devlink_port_get_rsp_dump_parse; + yds.rsp_cmd = 7; + yds.rsp_policy = &devlink_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_PORT_GET, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + devlink_port_get_rsp_list_free(yds.first); + return NULL; +} + +/* ============== DEVLINK_CMD_SB_GET ============== */ +/* DEVLINK_CMD_SB_GET - do */ +void devlink_sb_get_req_free(struct devlink_sb_get_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req); +} + +void devlink_sb_get_rsp_free(struct devlink_sb_get_rsp *rsp) +{ + free(rsp->bus_name); + free(rsp->dev_name); + free(rsp); +} + +int devlink_sb_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_parse_arg *yarg = data; + struct devlink_sb_get_rsp *dst; + const struct nlattr *attr; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } else if (type == DEVLINK_ATTR_SB_INDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.sb_index = 1; + dst->sb_index = mnl_attr_get_u32(attr); + } + } + + return MNL_CB_OK; +} + +struct devlink_sb_get_rsp * +devlink_sb_get(struct ynl_sock *ys, struct devlink_sb_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct devlink_sb_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SB_GET, 1); + ys->req_policy = &devlink_nest; + yrs.yarg.rsp_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.sb_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_INDEX, req->sb_index); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = devlink_sb_get_rsp_parse; + yrs.rsp_cmd = DEVLINK_CMD_SB_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + devlink_sb_get_rsp_free(rsp); + return NULL; +} + +/* DEVLINK_CMD_SB_GET - dump */ +void devlink_sb_get_list_free(struct devlink_sb_get_list *rsp) +{ + struct devlink_sb_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + free(rsp->obj.bus_name); + free(rsp->obj.dev_name); + free(rsp); + } +} + +struct devlink_sb_get_list * +devlink_sb_get_dump(struct ynl_sock *ys, struct devlink_sb_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct devlink_sb_get_list); + yds.cb = devlink_sb_get_rsp_parse; + yds.rsp_cmd = DEVLINK_CMD_SB_GET; + yds.rsp_policy = &devlink_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_SB_GET, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + devlink_sb_get_list_free(yds.first); + return NULL; +} + +/* ============== DEVLINK_CMD_SB_POOL_GET ============== */ +/* DEVLINK_CMD_SB_POOL_GET - do */ +void devlink_sb_pool_get_req_free(struct devlink_sb_pool_get_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req); +} + +void devlink_sb_pool_get_rsp_free(struct devlink_sb_pool_get_rsp *rsp) +{ + free(rsp->bus_name); + free(rsp->dev_name); + free(rsp); +} + +int devlink_sb_pool_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct devlink_sb_pool_get_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } else if (type == DEVLINK_ATTR_SB_INDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.sb_index = 1; + dst->sb_index = mnl_attr_get_u32(attr); + } else if (type == DEVLINK_ATTR_SB_POOL_INDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.sb_pool_index = 1; + dst->sb_pool_index = mnl_attr_get_u16(attr); + } + } + + return MNL_CB_OK; +} + +struct devlink_sb_pool_get_rsp * +devlink_sb_pool_get(struct ynl_sock *ys, struct devlink_sb_pool_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct devlink_sb_pool_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SB_POOL_GET, 1); + ys->req_policy = &devlink_nest; + yrs.yarg.rsp_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.sb_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_INDEX, req->sb_index); + if (req->_present.sb_pool_index) + mnl_attr_put_u16(nlh, DEVLINK_ATTR_SB_POOL_INDEX, req->sb_pool_index); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = devlink_sb_pool_get_rsp_parse; + yrs.rsp_cmd = DEVLINK_CMD_SB_POOL_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + devlink_sb_pool_get_rsp_free(rsp); + return NULL; +} + +/* DEVLINK_CMD_SB_POOL_GET - dump */ +void devlink_sb_pool_get_list_free(struct devlink_sb_pool_get_list *rsp) +{ + struct devlink_sb_pool_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + free(rsp->obj.bus_name); + free(rsp->obj.dev_name); + free(rsp); + } +} + +struct devlink_sb_pool_get_list * +devlink_sb_pool_get_dump(struct ynl_sock *ys, + struct devlink_sb_pool_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct devlink_sb_pool_get_list); + yds.cb = devlink_sb_pool_get_rsp_parse; + yds.rsp_cmd = DEVLINK_CMD_SB_POOL_GET; + yds.rsp_policy = &devlink_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_SB_POOL_GET, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + devlink_sb_pool_get_list_free(yds.first); + return NULL; +} + +/* ============== DEVLINK_CMD_SB_PORT_POOL_GET ============== */ +/* DEVLINK_CMD_SB_PORT_POOL_GET - do */ +void +devlink_sb_port_pool_get_req_free(struct devlink_sb_port_pool_get_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req); +} + +void +devlink_sb_port_pool_get_rsp_free(struct devlink_sb_port_pool_get_rsp *rsp) +{ + free(rsp->bus_name); + free(rsp->dev_name); + free(rsp); +} + +int devlink_sb_port_pool_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct devlink_sb_port_pool_get_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } else if (type == DEVLINK_ATTR_PORT_INDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.port_index = 1; + dst->port_index = mnl_attr_get_u32(attr); + } else if (type == DEVLINK_ATTR_SB_INDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.sb_index = 1; + dst->sb_index = mnl_attr_get_u32(attr); + } else if (type == DEVLINK_ATTR_SB_POOL_INDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.sb_pool_index = 1; + dst->sb_pool_index = mnl_attr_get_u16(attr); + } + } + + return MNL_CB_OK; +} + +struct devlink_sb_port_pool_get_rsp * +devlink_sb_port_pool_get(struct ynl_sock *ys, + struct devlink_sb_port_pool_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct devlink_sb_port_pool_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SB_PORT_POOL_GET, 1); + ys->req_policy = &devlink_nest; + yrs.yarg.rsp_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.port_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index); + if (req->_present.sb_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_INDEX, req->sb_index); + if (req->_present.sb_pool_index) + mnl_attr_put_u16(nlh, DEVLINK_ATTR_SB_POOL_INDEX, req->sb_pool_index); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = devlink_sb_port_pool_get_rsp_parse; + yrs.rsp_cmd = DEVLINK_CMD_SB_PORT_POOL_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + devlink_sb_port_pool_get_rsp_free(rsp); + return NULL; +} + +/* DEVLINK_CMD_SB_PORT_POOL_GET - dump */ +void +devlink_sb_port_pool_get_list_free(struct devlink_sb_port_pool_get_list *rsp) +{ + struct devlink_sb_port_pool_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + free(rsp->obj.bus_name); + free(rsp->obj.dev_name); + free(rsp); + } +} + +struct devlink_sb_port_pool_get_list * +devlink_sb_port_pool_get_dump(struct ynl_sock *ys, + struct devlink_sb_port_pool_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct devlink_sb_port_pool_get_list); + yds.cb = devlink_sb_port_pool_get_rsp_parse; + yds.rsp_cmd = DEVLINK_CMD_SB_PORT_POOL_GET; + yds.rsp_policy = &devlink_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_SB_PORT_POOL_GET, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + devlink_sb_port_pool_get_list_free(yds.first); + return NULL; +} + +/* ============== DEVLINK_CMD_SB_TC_POOL_BIND_GET ============== */ +/* DEVLINK_CMD_SB_TC_POOL_BIND_GET - do */ +void +devlink_sb_tc_pool_bind_get_req_free(struct devlink_sb_tc_pool_bind_get_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req); +} + +void +devlink_sb_tc_pool_bind_get_rsp_free(struct devlink_sb_tc_pool_bind_get_rsp *rsp) +{ + free(rsp->bus_name); + free(rsp->dev_name); + free(rsp); +} + +int devlink_sb_tc_pool_bind_get_rsp_parse(const struct nlmsghdr *nlh, + void *data) +{ + struct devlink_sb_tc_pool_bind_get_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } else if (type == DEVLINK_ATTR_PORT_INDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.port_index = 1; + dst->port_index = mnl_attr_get_u32(attr); + } else if (type == DEVLINK_ATTR_SB_INDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.sb_index = 1; + dst->sb_index = mnl_attr_get_u32(attr); + } else if (type == DEVLINK_ATTR_SB_POOL_TYPE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.sb_pool_type = 1; + dst->sb_pool_type = mnl_attr_get_u8(attr); + } else if (type == DEVLINK_ATTR_SB_TC_INDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.sb_tc_index = 1; + dst->sb_tc_index = mnl_attr_get_u16(attr); + } + } + + return MNL_CB_OK; +} + +struct devlink_sb_tc_pool_bind_get_rsp * +devlink_sb_tc_pool_bind_get(struct ynl_sock *ys, + struct devlink_sb_tc_pool_bind_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct devlink_sb_tc_pool_bind_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SB_TC_POOL_BIND_GET, 1); + ys->req_policy = &devlink_nest; + yrs.yarg.rsp_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.port_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index); + if (req->_present.sb_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_INDEX, req->sb_index); + if (req->_present.sb_pool_type) + mnl_attr_put_u8(nlh, DEVLINK_ATTR_SB_POOL_TYPE, req->sb_pool_type); + if (req->_present.sb_tc_index) + mnl_attr_put_u16(nlh, DEVLINK_ATTR_SB_TC_INDEX, req->sb_tc_index); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = devlink_sb_tc_pool_bind_get_rsp_parse; + yrs.rsp_cmd = DEVLINK_CMD_SB_TC_POOL_BIND_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + devlink_sb_tc_pool_bind_get_rsp_free(rsp); + return NULL; +} + +/* DEVLINK_CMD_SB_TC_POOL_BIND_GET - dump */ +void +devlink_sb_tc_pool_bind_get_list_free(struct devlink_sb_tc_pool_bind_get_list *rsp) +{ + struct devlink_sb_tc_pool_bind_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + free(rsp->obj.bus_name); + free(rsp->obj.dev_name); + free(rsp); + } +} + +struct devlink_sb_tc_pool_bind_get_list * +devlink_sb_tc_pool_bind_get_dump(struct ynl_sock *ys, + struct devlink_sb_tc_pool_bind_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct devlink_sb_tc_pool_bind_get_list); + yds.cb = devlink_sb_tc_pool_bind_get_rsp_parse; + yds.rsp_cmd = DEVLINK_CMD_SB_TC_POOL_BIND_GET; + yds.rsp_policy = &devlink_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_SB_TC_POOL_BIND_GET, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + devlink_sb_tc_pool_bind_get_list_free(yds.first); + return NULL; +} + +/* ============== DEVLINK_CMD_PARAM_GET ============== */ +/* DEVLINK_CMD_PARAM_GET - do */ +void devlink_param_get_req_free(struct devlink_param_get_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req->param_name); + free(req); +} + +void devlink_param_get_rsp_free(struct devlink_param_get_rsp *rsp) +{ + free(rsp->bus_name); + free(rsp->dev_name); + free(rsp->param_name); + free(rsp); +} + +int devlink_param_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct devlink_param_get_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } else if (type == DEVLINK_ATTR_PARAM_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.param_name_len = len; + dst->param_name = malloc(len + 1); + memcpy(dst->param_name, mnl_attr_get_str(attr), len); + dst->param_name[len] = 0; + } + } + + return MNL_CB_OK; +} + +struct devlink_param_get_rsp * +devlink_param_get(struct ynl_sock *ys, struct devlink_param_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct devlink_param_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_PARAM_GET, 1); + ys->req_policy = &devlink_nest; + yrs.yarg.rsp_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.param_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_PARAM_NAME, req->param_name); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = devlink_param_get_rsp_parse; + yrs.rsp_cmd = DEVLINK_CMD_PARAM_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + devlink_param_get_rsp_free(rsp); + return NULL; +} + +/* DEVLINK_CMD_PARAM_GET - dump */ +void devlink_param_get_list_free(struct devlink_param_get_list *rsp) +{ + struct devlink_param_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + free(rsp->obj.bus_name); + free(rsp->obj.dev_name); + free(rsp->obj.param_name); + free(rsp); + } +} + +struct devlink_param_get_list * +devlink_param_get_dump(struct ynl_sock *ys, + struct devlink_param_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct devlink_param_get_list); + yds.cb = devlink_param_get_rsp_parse; + yds.rsp_cmd = DEVLINK_CMD_PARAM_GET; + yds.rsp_policy = &devlink_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_PARAM_GET, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + devlink_param_get_list_free(yds.first); + return NULL; +} + +/* ============== DEVLINK_CMD_REGION_GET ============== */ +/* DEVLINK_CMD_REGION_GET - do */ +void devlink_region_get_req_free(struct devlink_region_get_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req->region_name); + free(req); +} + +void devlink_region_get_rsp_free(struct devlink_region_get_rsp *rsp) +{ + free(rsp->bus_name); + free(rsp->dev_name); + free(rsp->region_name); + free(rsp); +} + +int devlink_region_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct devlink_region_get_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } else if (type == DEVLINK_ATTR_PORT_INDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.port_index = 1; + dst->port_index = mnl_attr_get_u32(attr); + } else if (type == DEVLINK_ATTR_REGION_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.region_name_len = len; + dst->region_name = malloc(len + 1); + memcpy(dst->region_name, mnl_attr_get_str(attr), len); + dst->region_name[len] = 0; + } + } + + return MNL_CB_OK; +} + +struct devlink_region_get_rsp * +devlink_region_get(struct ynl_sock *ys, struct devlink_region_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct devlink_region_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_REGION_GET, 1); + ys->req_policy = &devlink_nest; + yrs.yarg.rsp_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.port_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index); + if (req->_present.region_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_REGION_NAME, req->region_name); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = devlink_region_get_rsp_parse; + yrs.rsp_cmd = DEVLINK_CMD_REGION_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + devlink_region_get_rsp_free(rsp); + return NULL; +} + +/* DEVLINK_CMD_REGION_GET - dump */ +void devlink_region_get_list_free(struct devlink_region_get_list *rsp) +{ + struct devlink_region_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + free(rsp->obj.bus_name); + free(rsp->obj.dev_name); + free(rsp->obj.region_name); + free(rsp); + } +} + +struct devlink_region_get_list * +devlink_region_get_dump(struct ynl_sock *ys, + struct devlink_region_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct devlink_region_get_list); + yds.cb = devlink_region_get_rsp_parse; + yds.rsp_cmd = DEVLINK_CMD_REGION_GET; + yds.rsp_policy = &devlink_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_REGION_GET, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + devlink_region_get_list_free(yds.first); + return NULL; +} + /* ============== DEVLINK_CMD_INFO_GET ============== */ /* DEVLINK_CMD_INFO_GET - do */ void devlink_info_get_req_free(struct devlink_info_get_req *req) @@ -716,6 +1874,1109 @@ err_free: return NULL; } +/* DEVLINK_CMD_INFO_GET - dump */ +void devlink_info_get_list_free(struct devlink_info_get_list *rsp) +{ + struct devlink_info_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + unsigned int i; + + rsp = next; + next = rsp->next; + + free(rsp->obj.bus_name); + free(rsp->obj.dev_name); + free(rsp->obj.info_driver_name); + free(rsp->obj.info_serial_number); + for (i = 0; i < rsp->obj.n_info_version_fixed; i++) + devlink_dl_info_version_free(&rsp->obj.info_version_fixed[i]); + free(rsp->obj.info_version_fixed); + for (i = 0; i < rsp->obj.n_info_version_running; i++) + devlink_dl_info_version_free(&rsp->obj.info_version_running[i]); + free(rsp->obj.info_version_running); + for (i = 0; i < rsp->obj.n_info_version_stored; i++) + devlink_dl_info_version_free(&rsp->obj.info_version_stored[i]); + free(rsp->obj.info_version_stored); + free(rsp); + } +} + +struct devlink_info_get_list *devlink_info_get_dump(struct ynl_sock *ys) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct devlink_info_get_list); + yds.cb = devlink_info_get_rsp_parse; + yds.rsp_cmd = DEVLINK_CMD_INFO_GET; + yds.rsp_policy = &devlink_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_INFO_GET, 1); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + devlink_info_get_list_free(yds.first); + return NULL; +} + +/* ============== DEVLINK_CMD_HEALTH_REPORTER_GET ============== */ +/* DEVLINK_CMD_HEALTH_REPORTER_GET - do */ +void +devlink_health_reporter_get_req_free(struct devlink_health_reporter_get_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req->health_reporter_name); + free(req); +} + +void +devlink_health_reporter_get_rsp_free(struct devlink_health_reporter_get_rsp *rsp) +{ + free(rsp->bus_name); + free(rsp->dev_name); + free(rsp->health_reporter_name); + free(rsp); +} + +int devlink_health_reporter_get_rsp_parse(const struct nlmsghdr *nlh, + void *data) +{ + struct devlink_health_reporter_get_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } else if (type == DEVLINK_ATTR_PORT_INDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.port_index = 1; + dst->port_index = mnl_attr_get_u32(attr); + } else if (type == DEVLINK_ATTR_HEALTH_REPORTER_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.health_reporter_name_len = len; + dst->health_reporter_name = malloc(len + 1); + memcpy(dst->health_reporter_name, mnl_attr_get_str(attr), len); + dst->health_reporter_name[len] = 0; + } + } + + return MNL_CB_OK; +} + +struct devlink_health_reporter_get_rsp * +devlink_health_reporter_get(struct ynl_sock *ys, + struct devlink_health_reporter_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct devlink_health_reporter_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_HEALTH_REPORTER_GET, 1); + ys->req_policy = &devlink_nest; + yrs.yarg.rsp_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.port_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index); + if (req->_present.health_reporter_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_HEALTH_REPORTER_NAME, req->health_reporter_name); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = devlink_health_reporter_get_rsp_parse; + yrs.rsp_cmd = DEVLINK_CMD_HEALTH_REPORTER_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + devlink_health_reporter_get_rsp_free(rsp); + return NULL; +} + +/* DEVLINK_CMD_HEALTH_REPORTER_GET - dump */ +void +devlink_health_reporter_get_list_free(struct devlink_health_reporter_get_list *rsp) +{ + struct devlink_health_reporter_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + free(rsp->obj.bus_name); + free(rsp->obj.dev_name); + free(rsp->obj.health_reporter_name); + free(rsp); + } +} + +struct devlink_health_reporter_get_list * +devlink_health_reporter_get_dump(struct ynl_sock *ys, + struct devlink_health_reporter_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct devlink_health_reporter_get_list); + yds.cb = devlink_health_reporter_get_rsp_parse; + yds.rsp_cmd = DEVLINK_CMD_HEALTH_REPORTER_GET; + yds.rsp_policy = &devlink_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_HEALTH_REPORTER_GET, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.port_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + devlink_health_reporter_get_list_free(yds.first); + return NULL; +} + +/* ============== DEVLINK_CMD_TRAP_GET ============== */ +/* DEVLINK_CMD_TRAP_GET - do */ +void devlink_trap_get_req_free(struct devlink_trap_get_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req->trap_name); + free(req); +} + +void devlink_trap_get_rsp_free(struct devlink_trap_get_rsp *rsp) +{ + free(rsp->bus_name); + free(rsp->dev_name); + free(rsp->trap_name); + free(rsp); +} + +int devlink_trap_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_parse_arg *yarg = data; + struct devlink_trap_get_rsp *dst; + const struct nlattr *attr; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } else if (type == DEVLINK_ATTR_TRAP_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.trap_name_len = len; + dst->trap_name = malloc(len + 1); + memcpy(dst->trap_name, mnl_attr_get_str(attr), len); + dst->trap_name[len] = 0; + } + } + + return MNL_CB_OK; +} + +struct devlink_trap_get_rsp * +devlink_trap_get(struct ynl_sock *ys, struct devlink_trap_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct devlink_trap_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_TRAP_GET, 1); + ys->req_policy = &devlink_nest; + yrs.yarg.rsp_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.trap_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_TRAP_NAME, req->trap_name); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = devlink_trap_get_rsp_parse; + yrs.rsp_cmd = DEVLINK_CMD_TRAP_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + devlink_trap_get_rsp_free(rsp); + return NULL; +} + +/* DEVLINK_CMD_TRAP_GET - dump */ +void devlink_trap_get_list_free(struct devlink_trap_get_list *rsp) +{ + struct devlink_trap_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + free(rsp->obj.bus_name); + free(rsp->obj.dev_name); + free(rsp->obj.trap_name); + free(rsp); + } +} + +struct devlink_trap_get_list * +devlink_trap_get_dump(struct ynl_sock *ys, + struct devlink_trap_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct devlink_trap_get_list); + yds.cb = devlink_trap_get_rsp_parse; + yds.rsp_cmd = DEVLINK_CMD_TRAP_GET; + yds.rsp_policy = &devlink_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_TRAP_GET, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + devlink_trap_get_list_free(yds.first); + return NULL; +} + +/* ============== DEVLINK_CMD_TRAP_GROUP_GET ============== */ +/* DEVLINK_CMD_TRAP_GROUP_GET - do */ +void devlink_trap_group_get_req_free(struct devlink_trap_group_get_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req->trap_group_name); + free(req); +} + +void devlink_trap_group_get_rsp_free(struct devlink_trap_group_get_rsp *rsp) +{ + free(rsp->bus_name); + free(rsp->dev_name); + free(rsp->trap_group_name); + free(rsp); +} + +int devlink_trap_group_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct devlink_trap_group_get_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } else if (type == DEVLINK_ATTR_TRAP_GROUP_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.trap_group_name_len = len; + dst->trap_group_name = malloc(len + 1); + memcpy(dst->trap_group_name, mnl_attr_get_str(attr), len); + dst->trap_group_name[len] = 0; + } + } + + return MNL_CB_OK; +} + +struct devlink_trap_group_get_rsp * +devlink_trap_group_get(struct ynl_sock *ys, + struct devlink_trap_group_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct devlink_trap_group_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_TRAP_GROUP_GET, 1); + ys->req_policy = &devlink_nest; + yrs.yarg.rsp_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.trap_group_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_TRAP_GROUP_NAME, req->trap_group_name); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = devlink_trap_group_get_rsp_parse; + yrs.rsp_cmd = DEVLINK_CMD_TRAP_GROUP_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + devlink_trap_group_get_rsp_free(rsp); + return NULL; +} + +/* DEVLINK_CMD_TRAP_GROUP_GET - dump */ +void devlink_trap_group_get_list_free(struct devlink_trap_group_get_list *rsp) +{ + struct devlink_trap_group_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + free(rsp->obj.bus_name); + free(rsp->obj.dev_name); + free(rsp->obj.trap_group_name); + free(rsp); + } +} + +struct devlink_trap_group_get_list * +devlink_trap_group_get_dump(struct ynl_sock *ys, + struct devlink_trap_group_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct devlink_trap_group_get_list); + yds.cb = devlink_trap_group_get_rsp_parse; + yds.rsp_cmd = DEVLINK_CMD_TRAP_GROUP_GET; + yds.rsp_policy = &devlink_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_TRAP_GROUP_GET, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + devlink_trap_group_get_list_free(yds.first); + return NULL; +} + +/* ============== DEVLINK_CMD_TRAP_POLICER_GET ============== */ +/* DEVLINK_CMD_TRAP_POLICER_GET - do */ +void +devlink_trap_policer_get_req_free(struct devlink_trap_policer_get_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req); +} + +void +devlink_trap_policer_get_rsp_free(struct devlink_trap_policer_get_rsp *rsp) +{ + free(rsp->bus_name); + free(rsp->dev_name); + free(rsp); +} + +int devlink_trap_policer_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct devlink_trap_policer_get_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } else if (type == DEVLINK_ATTR_TRAP_POLICER_ID) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.trap_policer_id = 1; + dst->trap_policer_id = mnl_attr_get_u32(attr); + } + } + + return MNL_CB_OK; +} + +struct devlink_trap_policer_get_rsp * +devlink_trap_policer_get(struct ynl_sock *ys, + struct devlink_trap_policer_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct devlink_trap_policer_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_TRAP_POLICER_GET, 1); + ys->req_policy = &devlink_nest; + yrs.yarg.rsp_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.trap_policer_id) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_TRAP_POLICER_ID, req->trap_policer_id); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = devlink_trap_policer_get_rsp_parse; + yrs.rsp_cmd = DEVLINK_CMD_TRAP_POLICER_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + devlink_trap_policer_get_rsp_free(rsp); + return NULL; +} + +/* DEVLINK_CMD_TRAP_POLICER_GET - dump */ +void +devlink_trap_policer_get_list_free(struct devlink_trap_policer_get_list *rsp) +{ + struct devlink_trap_policer_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + free(rsp->obj.bus_name); + free(rsp->obj.dev_name); + free(rsp); + } +} + +struct devlink_trap_policer_get_list * +devlink_trap_policer_get_dump(struct ynl_sock *ys, + struct devlink_trap_policer_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct devlink_trap_policer_get_list); + yds.cb = devlink_trap_policer_get_rsp_parse; + yds.rsp_cmd = DEVLINK_CMD_TRAP_POLICER_GET; + yds.rsp_policy = &devlink_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_TRAP_POLICER_GET, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + devlink_trap_policer_get_list_free(yds.first); + return NULL; +} + +/* ============== DEVLINK_CMD_RATE_GET ============== */ +/* DEVLINK_CMD_RATE_GET - do */ +void devlink_rate_get_req_free(struct devlink_rate_get_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req->rate_node_name); + free(req); +} + +void devlink_rate_get_rsp_free(struct devlink_rate_get_rsp *rsp) +{ + free(rsp->bus_name); + free(rsp->dev_name); + free(rsp->rate_node_name); + free(rsp); +} + +int devlink_rate_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_parse_arg *yarg = data; + struct devlink_rate_get_rsp *dst; + const struct nlattr *attr; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } else if (type == DEVLINK_ATTR_PORT_INDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.port_index = 1; + dst->port_index = mnl_attr_get_u32(attr); + } else if (type == DEVLINK_ATTR_RATE_NODE_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.rate_node_name_len = len; + dst->rate_node_name = malloc(len + 1); + memcpy(dst->rate_node_name, mnl_attr_get_str(attr), len); + dst->rate_node_name[len] = 0; + } + } + + return MNL_CB_OK; +} + +struct devlink_rate_get_rsp * +devlink_rate_get(struct ynl_sock *ys, struct devlink_rate_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct devlink_rate_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_RATE_GET, 1); + ys->req_policy = &devlink_nest; + yrs.yarg.rsp_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.port_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index); + if (req->_present.rate_node_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_RATE_NODE_NAME, req->rate_node_name); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = devlink_rate_get_rsp_parse; + yrs.rsp_cmd = DEVLINK_CMD_RATE_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + devlink_rate_get_rsp_free(rsp); + return NULL; +} + +/* DEVLINK_CMD_RATE_GET - dump */ +void devlink_rate_get_list_free(struct devlink_rate_get_list *rsp) +{ + struct devlink_rate_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + free(rsp->obj.bus_name); + free(rsp->obj.dev_name); + free(rsp->obj.rate_node_name); + free(rsp); + } +} + +struct devlink_rate_get_list * +devlink_rate_get_dump(struct ynl_sock *ys, + struct devlink_rate_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct devlink_rate_get_list); + yds.cb = devlink_rate_get_rsp_parse; + yds.rsp_cmd = DEVLINK_CMD_RATE_GET; + yds.rsp_policy = &devlink_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_RATE_GET, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + devlink_rate_get_list_free(yds.first); + return NULL; +} + +/* ============== DEVLINK_CMD_LINECARD_GET ============== */ +/* DEVLINK_CMD_LINECARD_GET - do */ +void devlink_linecard_get_req_free(struct devlink_linecard_get_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req); +} + +void devlink_linecard_get_rsp_free(struct devlink_linecard_get_rsp *rsp) +{ + free(rsp->bus_name); + free(rsp->dev_name); + free(rsp); +} + +int devlink_linecard_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct devlink_linecard_get_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } else if (type == DEVLINK_ATTR_LINECARD_INDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.linecard_index = 1; + dst->linecard_index = mnl_attr_get_u32(attr); + } + } + + return MNL_CB_OK; +} + +struct devlink_linecard_get_rsp * +devlink_linecard_get(struct ynl_sock *ys, struct devlink_linecard_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct devlink_linecard_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_LINECARD_GET, 1); + ys->req_policy = &devlink_nest; + yrs.yarg.rsp_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.linecard_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_LINECARD_INDEX, req->linecard_index); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = devlink_linecard_get_rsp_parse; + yrs.rsp_cmd = DEVLINK_CMD_LINECARD_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + devlink_linecard_get_rsp_free(rsp); + return NULL; +} + +/* DEVLINK_CMD_LINECARD_GET - dump */ +void devlink_linecard_get_list_free(struct devlink_linecard_get_list *rsp) +{ + struct devlink_linecard_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + free(rsp->obj.bus_name); + free(rsp->obj.dev_name); + free(rsp); + } +} + +struct devlink_linecard_get_list * +devlink_linecard_get_dump(struct ynl_sock *ys, + struct devlink_linecard_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct devlink_linecard_get_list); + yds.cb = devlink_linecard_get_rsp_parse; + yds.rsp_cmd = DEVLINK_CMD_LINECARD_GET; + yds.rsp_policy = &devlink_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_LINECARD_GET, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + devlink_linecard_get_list_free(yds.first); + return NULL; +} + +/* ============== DEVLINK_CMD_SELFTESTS_GET ============== */ +/* DEVLINK_CMD_SELFTESTS_GET - do */ +void devlink_selftests_get_req_free(struct devlink_selftests_get_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req); +} + +void devlink_selftests_get_rsp_free(struct devlink_selftests_get_rsp *rsp) +{ + free(rsp->bus_name); + free(rsp->dev_name); + free(rsp); +} + +int devlink_selftests_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct devlink_selftests_get_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } + } + + return MNL_CB_OK; +} + +struct devlink_selftests_get_rsp * +devlink_selftests_get(struct ynl_sock *ys, + struct devlink_selftests_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct devlink_selftests_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SELFTESTS_GET, 1); + ys->req_policy = &devlink_nest; + yrs.yarg.rsp_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = devlink_selftests_get_rsp_parse; + yrs.rsp_cmd = DEVLINK_CMD_SELFTESTS_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + devlink_selftests_get_rsp_free(rsp); + return NULL; +} + +/* DEVLINK_CMD_SELFTESTS_GET - dump */ +void devlink_selftests_get_list_free(struct devlink_selftests_get_list *rsp) +{ + struct devlink_selftests_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + free(rsp->obj.bus_name); + free(rsp->obj.dev_name); + free(rsp); + } +} + +struct devlink_selftests_get_list * +devlink_selftests_get_dump(struct ynl_sock *ys) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct devlink_selftests_get_list); + yds.cb = devlink_selftests_get_rsp_parse; + yds.rsp_cmd = DEVLINK_CMD_SELFTESTS_GET; + yds.rsp_policy = &devlink_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_SELFTESTS_GET, 1); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + devlink_selftests_get_list_free(yds.first); + return NULL; +} + const struct ynl_family ynl_devlink_family = { .name = "devlink", }; diff --git a/tools/net/ynl/generated/devlink-user.h b/tools/net/ynl/generated/devlink-user.h index a008b99b6e24..4b686d147613 100644 --- a/tools/net/ynl/generated/devlink-user.h +++ b/tools/net/ynl/generated/devlink-user.h @@ -17,6 +17,7 @@ extern const struct ynl_family ynl_devlink_family; /* Enums */ const char *devlink_op_str(int op); +const char *devlink_sb_pool_type_str(enum devlink_sb_pool_type value); /* Common nested types */ struct devlink_dl_info_version { @@ -140,6 +141,939 @@ void devlink_get_list_free(struct devlink_get_list *rsp); struct devlink_get_list *devlink_get_dump(struct ynl_sock *ys); +/* ============== DEVLINK_CMD_PORT_GET ============== */ +/* DEVLINK_CMD_PORT_GET - do */ +struct devlink_port_get_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; +}; + +static inline struct devlink_port_get_req *devlink_port_get_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_port_get_req)); +} +void devlink_port_get_req_free(struct devlink_port_get_req *req); + +static inline void +devlink_port_get_req_set_bus_name(struct devlink_port_get_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_port_get_req_set_dev_name(struct devlink_port_get_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_port_get_req_set_port_index(struct devlink_port_get_req *req, + __u32 port_index) +{ + req->_present.port_index = 1; + req->port_index = port_index; +} + +struct devlink_port_get_rsp { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; +}; + +void devlink_port_get_rsp_free(struct devlink_port_get_rsp *rsp); + +/* + * Get devlink port instances. + */ +struct devlink_port_get_rsp * +devlink_port_get(struct ynl_sock *ys, struct devlink_port_get_req *req); + +/* DEVLINK_CMD_PORT_GET - dump */ +struct devlink_port_get_req_dump { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + } _present; + + char *bus_name; + char *dev_name; +}; + +static inline struct devlink_port_get_req_dump * +devlink_port_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct devlink_port_get_req_dump)); +} +void devlink_port_get_req_dump_free(struct devlink_port_get_req_dump *req); + +static inline void +devlink_port_get_req_dump_set_bus_name(struct devlink_port_get_req_dump *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_port_get_req_dump_set_dev_name(struct devlink_port_get_req_dump *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} + +struct devlink_port_get_rsp_dump { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; +}; + +struct devlink_port_get_rsp_list { + struct devlink_port_get_rsp_list *next; + struct devlink_port_get_rsp_dump obj __attribute__ ((aligned (8))); +}; + +void devlink_port_get_rsp_list_free(struct devlink_port_get_rsp_list *rsp); + +struct devlink_port_get_rsp_list * +devlink_port_get_dump(struct ynl_sock *ys, + struct devlink_port_get_req_dump *req); + +/* ============== DEVLINK_CMD_SB_GET ============== */ +/* DEVLINK_CMD_SB_GET - do */ +struct devlink_sb_get_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 sb_index:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 sb_index; +}; + +static inline struct devlink_sb_get_req *devlink_sb_get_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_sb_get_req)); +} +void devlink_sb_get_req_free(struct devlink_sb_get_req *req); + +static inline void +devlink_sb_get_req_set_bus_name(struct devlink_sb_get_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_sb_get_req_set_dev_name(struct devlink_sb_get_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_sb_get_req_set_sb_index(struct devlink_sb_get_req *req, __u32 sb_index) +{ + req->_present.sb_index = 1; + req->sb_index = sb_index; +} + +struct devlink_sb_get_rsp { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 sb_index:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 sb_index; +}; + +void devlink_sb_get_rsp_free(struct devlink_sb_get_rsp *rsp); + +/* + * Get shared buffer instances. + */ +struct devlink_sb_get_rsp * +devlink_sb_get(struct ynl_sock *ys, struct devlink_sb_get_req *req); + +/* DEVLINK_CMD_SB_GET - dump */ +struct devlink_sb_get_req_dump { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + } _present; + + char *bus_name; + char *dev_name; +}; + +static inline struct devlink_sb_get_req_dump * +devlink_sb_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct devlink_sb_get_req_dump)); +} +void devlink_sb_get_req_dump_free(struct devlink_sb_get_req_dump *req); + +static inline void +devlink_sb_get_req_dump_set_bus_name(struct devlink_sb_get_req_dump *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_sb_get_req_dump_set_dev_name(struct devlink_sb_get_req_dump *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} + +struct devlink_sb_get_list { + struct devlink_sb_get_list *next; + struct devlink_sb_get_rsp obj __attribute__ ((aligned (8))); +}; + +void devlink_sb_get_list_free(struct devlink_sb_get_list *rsp); + +struct devlink_sb_get_list * +devlink_sb_get_dump(struct ynl_sock *ys, struct devlink_sb_get_req_dump *req); + +/* ============== DEVLINK_CMD_SB_POOL_GET ============== */ +/* DEVLINK_CMD_SB_POOL_GET - do */ +struct devlink_sb_pool_get_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 sb_index:1; + __u32 sb_pool_index:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 sb_index; + __u16 sb_pool_index; +}; + +static inline struct devlink_sb_pool_get_req * +devlink_sb_pool_get_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_sb_pool_get_req)); +} +void devlink_sb_pool_get_req_free(struct devlink_sb_pool_get_req *req); + +static inline void +devlink_sb_pool_get_req_set_bus_name(struct devlink_sb_pool_get_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_sb_pool_get_req_set_dev_name(struct devlink_sb_pool_get_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_sb_pool_get_req_set_sb_index(struct devlink_sb_pool_get_req *req, + __u32 sb_index) +{ + req->_present.sb_index = 1; + req->sb_index = sb_index; +} +static inline void +devlink_sb_pool_get_req_set_sb_pool_index(struct devlink_sb_pool_get_req *req, + __u16 sb_pool_index) +{ + req->_present.sb_pool_index = 1; + req->sb_pool_index = sb_pool_index; +} + +struct devlink_sb_pool_get_rsp { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 sb_index:1; + __u32 sb_pool_index:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 sb_index; + __u16 sb_pool_index; +}; + +void devlink_sb_pool_get_rsp_free(struct devlink_sb_pool_get_rsp *rsp); + +/* + * Get shared buffer pool instances. + */ +struct devlink_sb_pool_get_rsp * +devlink_sb_pool_get(struct ynl_sock *ys, struct devlink_sb_pool_get_req *req); + +/* DEVLINK_CMD_SB_POOL_GET - dump */ +struct devlink_sb_pool_get_req_dump { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + } _present; + + char *bus_name; + char *dev_name; +}; + +static inline struct devlink_sb_pool_get_req_dump * +devlink_sb_pool_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct devlink_sb_pool_get_req_dump)); +} +void +devlink_sb_pool_get_req_dump_free(struct devlink_sb_pool_get_req_dump *req); + +static inline void +devlink_sb_pool_get_req_dump_set_bus_name(struct devlink_sb_pool_get_req_dump *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_sb_pool_get_req_dump_set_dev_name(struct devlink_sb_pool_get_req_dump *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} + +struct devlink_sb_pool_get_list { + struct devlink_sb_pool_get_list *next; + struct devlink_sb_pool_get_rsp obj __attribute__ ((aligned (8))); +}; + +void devlink_sb_pool_get_list_free(struct devlink_sb_pool_get_list *rsp); + +struct devlink_sb_pool_get_list * +devlink_sb_pool_get_dump(struct ynl_sock *ys, + struct devlink_sb_pool_get_req_dump *req); + +/* ============== DEVLINK_CMD_SB_PORT_POOL_GET ============== */ +/* DEVLINK_CMD_SB_PORT_POOL_GET - do */ +struct devlink_sb_port_pool_get_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + __u32 sb_index:1; + __u32 sb_pool_index:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; + __u32 sb_index; + __u16 sb_pool_index; +}; + +static inline struct devlink_sb_port_pool_get_req * +devlink_sb_port_pool_get_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_sb_port_pool_get_req)); +} +void +devlink_sb_port_pool_get_req_free(struct devlink_sb_port_pool_get_req *req); + +static inline void +devlink_sb_port_pool_get_req_set_bus_name(struct devlink_sb_port_pool_get_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_sb_port_pool_get_req_set_dev_name(struct devlink_sb_port_pool_get_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_sb_port_pool_get_req_set_port_index(struct devlink_sb_port_pool_get_req *req, + __u32 port_index) +{ + req->_present.port_index = 1; + req->port_index = port_index; +} +static inline void +devlink_sb_port_pool_get_req_set_sb_index(struct devlink_sb_port_pool_get_req *req, + __u32 sb_index) +{ + req->_present.sb_index = 1; + req->sb_index = sb_index; +} +static inline void +devlink_sb_port_pool_get_req_set_sb_pool_index(struct devlink_sb_port_pool_get_req *req, + __u16 sb_pool_index) +{ + req->_present.sb_pool_index = 1; + req->sb_pool_index = sb_pool_index; +} + +struct devlink_sb_port_pool_get_rsp { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + __u32 sb_index:1; + __u32 sb_pool_index:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; + __u32 sb_index; + __u16 sb_pool_index; +}; + +void +devlink_sb_port_pool_get_rsp_free(struct devlink_sb_port_pool_get_rsp *rsp); + +/* + * Get shared buffer port-pool combinations and threshold. + */ +struct devlink_sb_port_pool_get_rsp * +devlink_sb_port_pool_get(struct ynl_sock *ys, + struct devlink_sb_port_pool_get_req *req); + +/* DEVLINK_CMD_SB_PORT_POOL_GET - dump */ +struct devlink_sb_port_pool_get_req_dump { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + } _present; + + char *bus_name; + char *dev_name; +}; + +static inline struct devlink_sb_port_pool_get_req_dump * +devlink_sb_port_pool_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct devlink_sb_port_pool_get_req_dump)); +} +void +devlink_sb_port_pool_get_req_dump_free(struct devlink_sb_port_pool_get_req_dump *req); + +static inline void +devlink_sb_port_pool_get_req_dump_set_bus_name(struct devlink_sb_port_pool_get_req_dump *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_sb_port_pool_get_req_dump_set_dev_name(struct devlink_sb_port_pool_get_req_dump *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} + +struct devlink_sb_port_pool_get_list { + struct devlink_sb_port_pool_get_list *next; + struct devlink_sb_port_pool_get_rsp obj __attribute__ ((aligned (8))); +}; + +void +devlink_sb_port_pool_get_list_free(struct devlink_sb_port_pool_get_list *rsp); + +struct devlink_sb_port_pool_get_list * +devlink_sb_port_pool_get_dump(struct ynl_sock *ys, + struct devlink_sb_port_pool_get_req_dump *req); + +/* ============== DEVLINK_CMD_SB_TC_POOL_BIND_GET ============== */ +/* DEVLINK_CMD_SB_TC_POOL_BIND_GET - do */ +struct devlink_sb_tc_pool_bind_get_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + __u32 sb_index:1; + __u32 sb_pool_type:1; + __u32 sb_tc_index:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; + __u32 sb_index; + enum devlink_sb_pool_type sb_pool_type; + __u16 sb_tc_index; +}; + +static inline struct devlink_sb_tc_pool_bind_get_req * +devlink_sb_tc_pool_bind_get_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_sb_tc_pool_bind_get_req)); +} +void +devlink_sb_tc_pool_bind_get_req_free(struct devlink_sb_tc_pool_bind_get_req *req); + +static inline void +devlink_sb_tc_pool_bind_get_req_set_bus_name(struct devlink_sb_tc_pool_bind_get_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_sb_tc_pool_bind_get_req_set_dev_name(struct devlink_sb_tc_pool_bind_get_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_sb_tc_pool_bind_get_req_set_port_index(struct devlink_sb_tc_pool_bind_get_req *req, + __u32 port_index) +{ + req->_present.port_index = 1; + req->port_index = port_index; +} +static inline void +devlink_sb_tc_pool_bind_get_req_set_sb_index(struct devlink_sb_tc_pool_bind_get_req *req, + __u32 sb_index) +{ + req->_present.sb_index = 1; + req->sb_index = sb_index; +} +static inline void +devlink_sb_tc_pool_bind_get_req_set_sb_pool_type(struct devlink_sb_tc_pool_bind_get_req *req, + enum devlink_sb_pool_type sb_pool_type) +{ + req->_present.sb_pool_type = 1; + req->sb_pool_type = sb_pool_type; +} +static inline void +devlink_sb_tc_pool_bind_get_req_set_sb_tc_index(struct devlink_sb_tc_pool_bind_get_req *req, + __u16 sb_tc_index) +{ + req->_present.sb_tc_index = 1; + req->sb_tc_index = sb_tc_index; +} + +struct devlink_sb_tc_pool_bind_get_rsp { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + __u32 sb_index:1; + __u32 sb_pool_type:1; + __u32 sb_tc_index:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; + __u32 sb_index; + enum devlink_sb_pool_type sb_pool_type; + __u16 sb_tc_index; +}; + +void +devlink_sb_tc_pool_bind_get_rsp_free(struct devlink_sb_tc_pool_bind_get_rsp *rsp); + +/* + * Get shared buffer port-TC to pool bindings and threshold. + */ +struct devlink_sb_tc_pool_bind_get_rsp * +devlink_sb_tc_pool_bind_get(struct ynl_sock *ys, + struct devlink_sb_tc_pool_bind_get_req *req); + +/* DEVLINK_CMD_SB_TC_POOL_BIND_GET - dump */ +struct devlink_sb_tc_pool_bind_get_req_dump { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + } _present; + + char *bus_name; + char *dev_name; +}; + +static inline struct devlink_sb_tc_pool_bind_get_req_dump * +devlink_sb_tc_pool_bind_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct devlink_sb_tc_pool_bind_get_req_dump)); +} +void +devlink_sb_tc_pool_bind_get_req_dump_free(struct devlink_sb_tc_pool_bind_get_req_dump *req); + +static inline void +devlink_sb_tc_pool_bind_get_req_dump_set_bus_name(struct devlink_sb_tc_pool_bind_get_req_dump *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_sb_tc_pool_bind_get_req_dump_set_dev_name(struct devlink_sb_tc_pool_bind_get_req_dump *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} + +struct devlink_sb_tc_pool_bind_get_list { + struct devlink_sb_tc_pool_bind_get_list *next; + struct devlink_sb_tc_pool_bind_get_rsp obj __attribute__ ((aligned (8))); +}; + +void +devlink_sb_tc_pool_bind_get_list_free(struct devlink_sb_tc_pool_bind_get_list *rsp); + +struct devlink_sb_tc_pool_bind_get_list * +devlink_sb_tc_pool_bind_get_dump(struct ynl_sock *ys, + struct devlink_sb_tc_pool_bind_get_req_dump *req); + +/* ============== DEVLINK_CMD_PARAM_GET ============== */ +/* DEVLINK_CMD_PARAM_GET - do */ +struct devlink_param_get_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 param_name_len; + } _present; + + char *bus_name; + char *dev_name; + char *param_name; +}; + +static inline struct devlink_param_get_req *devlink_param_get_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_param_get_req)); +} +void devlink_param_get_req_free(struct devlink_param_get_req *req); + +static inline void +devlink_param_get_req_set_bus_name(struct devlink_param_get_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_param_get_req_set_dev_name(struct devlink_param_get_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_param_get_req_set_param_name(struct devlink_param_get_req *req, + const char *param_name) +{ + free(req->param_name); + req->_present.param_name_len = strlen(param_name); + req->param_name = malloc(req->_present.param_name_len + 1); + memcpy(req->param_name, param_name, req->_present.param_name_len); + req->param_name[req->_present.param_name_len] = 0; +} + +struct devlink_param_get_rsp { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 param_name_len; + } _present; + + char *bus_name; + char *dev_name; + char *param_name; +}; + +void devlink_param_get_rsp_free(struct devlink_param_get_rsp *rsp); + +/* + * Get param instances. + */ +struct devlink_param_get_rsp * +devlink_param_get(struct ynl_sock *ys, struct devlink_param_get_req *req); + +/* DEVLINK_CMD_PARAM_GET - dump */ +struct devlink_param_get_req_dump { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + } _present; + + char *bus_name; + char *dev_name; +}; + +static inline struct devlink_param_get_req_dump * +devlink_param_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct devlink_param_get_req_dump)); +} +void devlink_param_get_req_dump_free(struct devlink_param_get_req_dump *req); + +static inline void +devlink_param_get_req_dump_set_bus_name(struct devlink_param_get_req_dump *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_param_get_req_dump_set_dev_name(struct devlink_param_get_req_dump *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} + +struct devlink_param_get_list { + struct devlink_param_get_list *next; + struct devlink_param_get_rsp obj __attribute__ ((aligned (8))); +}; + +void devlink_param_get_list_free(struct devlink_param_get_list *rsp); + +struct devlink_param_get_list * +devlink_param_get_dump(struct ynl_sock *ys, + struct devlink_param_get_req_dump *req); + +/* ============== DEVLINK_CMD_REGION_GET ============== */ +/* DEVLINK_CMD_REGION_GET - do */ +struct devlink_region_get_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + __u32 region_name_len; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; + char *region_name; +}; + +static inline struct devlink_region_get_req *devlink_region_get_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_region_get_req)); +} +void devlink_region_get_req_free(struct devlink_region_get_req *req); + +static inline void +devlink_region_get_req_set_bus_name(struct devlink_region_get_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_region_get_req_set_dev_name(struct devlink_region_get_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_region_get_req_set_port_index(struct devlink_region_get_req *req, + __u32 port_index) +{ + req->_present.port_index = 1; + req->port_index = port_index; +} +static inline void +devlink_region_get_req_set_region_name(struct devlink_region_get_req *req, + const char *region_name) +{ + free(req->region_name); + req->_present.region_name_len = strlen(region_name); + req->region_name = malloc(req->_present.region_name_len + 1); + memcpy(req->region_name, region_name, req->_present.region_name_len); + req->region_name[req->_present.region_name_len] = 0; +} + +struct devlink_region_get_rsp { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + __u32 region_name_len; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; + char *region_name; +}; + +void devlink_region_get_rsp_free(struct devlink_region_get_rsp *rsp); + +/* + * Get region instances. + */ +struct devlink_region_get_rsp * +devlink_region_get(struct ynl_sock *ys, struct devlink_region_get_req *req); + +/* DEVLINK_CMD_REGION_GET - dump */ +struct devlink_region_get_req_dump { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + } _present; + + char *bus_name; + char *dev_name; +}; + +static inline struct devlink_region_get_req_dump * +devlink_region_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct devlink_region_get_req_dump)); +} +void devlink_region_get_req_dump_free(struct devlink_region_get_req_dump *req); + +static inline void +devlink_region_get_req_dump_set_bus_name(struct devlink_region_get_req_dump *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_region_get_req_dump_set_dev_name(struct devlink_region_get_req_dump *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} + +struct devlink_region_get_list { + struct devlink_region_get_list *next; + struct devlink_region_get_rsp obj __attribute__ ((aligned (8))); +}; + +void devlink_region_get_list_free(struct devlink_region_get_list *rsp); + +struct devlink_region_get_list * +devlink_region_get_dump(struct ynl_sock *ys, + struct devlink_region_get_req_dump *req); + /* ============== DEVLINK_CMD_INFO_GET ============== */ /* DEVLINK_CMD_INFO_GET - do */ struct devlink_info_get_req { @@ -207,4 +1141,852 @@ void devlink_info_get_rsp_free(struct devlink_info_get_rsp *rsp); struct devlink_info_get_rsp * devlink_info_get(struct ynl_sock *ys, struct devlink_info_get_req *req); +/* DEVLINK_CMD_INFO_GET - dump */ +struct devlink_info_get_list { + struct devlink_info_get_list *next; + struct devlink_info_get_rsp obj __attribute__ ((aligned (8))); +}; + +void devlink_info_get_list_free(struct devlink_info_get_list *rsp); + +struct devlink_info_get_list *devlink_info_get_dump(struct ynl_sock *ys); + +/* ============== DEVLINK_CMD_HEALTH_REPORTER_GET ============== */ +/* DEVLINK_CMD_HEALTH_REPORTER_GET - do */ +struct devlink_health_reporter_get_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + __u32 health_reporter_name_len; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; + char *health_reporter_name; +}; + +static inline struct devlink_health_reporter_get_req * +devlink_health_reporter_get_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_health_reporter_get_req)); +} +void +devlink_health_reporter_get_req_free(struct devlink_health_reporter_get_req *req); + +static inline void +devlink_health_reporter_get_req_set_bus_name(struct devlink_health_reporter_get_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_health_reporter_get_req_set_dev_name(struct devlink_health_reporter_get_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_health_reporter_get_req_set_port_index(struct devlink_health_reporter_get_req *req, + __u32 port_index) +{ + req->_present.port_index = 1; + req->port_index = port_index; +} +static inline void +devlink_health_reporter_get_req_set_health_reporter_name(struct devlink_health_reporter_get_req *req, + const char *health_reporter_name) +{ + free(req->health_reporter_name); + req->_present.health_reporter_name_len = strlen(health_reporter_name); + req->health_reporter_name = malloc(req->_present.health_reporter_name_len + 1); + memcpy(req->health_reporter_name, health_reporter_name, req->_present.health_reporter_name_len); + req->health_reporter_name[req->_present.health_reporter_name_len] = 0; +} + +struct devlink_health_reporter_get_rsp { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + __u32 health_reporter_name_len; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; + char *health_reporter_name; +}; + +void +devlink_health_reporter_get_rsp_free(struct devlink_health_reporter_get_rsp *rsp); + +/* + * Get health reporter instances. + */ +struct devlink_health_reporter_get_rsp * +devlink_health_reporter_get(struct ynl_sock *ys, + struct devlink_health_reporter_get_req *req); + +/* DEVLINK_CMD_HEALTH_REPORTER_GET - dump */ +struct devlink_health_reporter_get_req_dump { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; +}; + +static inline struct devlink_health_reporter_get_req_dump * +devlink_health_reporter_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct devlink_health_reporter_get_req_dump)); +} +void +devlink_health_reporter_get_req_dump_free(struct devlink_health_reporter_get_req_dump *req); + +static inline void +devlink_health_reporter_get_req_dump_set_bus_name(struct devlink_health_reporter_get_req_dump *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_health_reporter_get_req_dump_set_dev_name(struct devlink_health_reporter_get_req_dump *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_health_reporter_get_req_dump_set_port_index(struct devlink_health_reporter_get_req_dump *req, + __u32 port_index) +{ + req->_present.port_index = 1; + req->port_index = port_index; +} + +struct devlink_health_reporter_get_list { + struct devlink_health_reporter_get_list *next; + struct devlink_health_reporter_get_rsp obj __attribute__ ((aligned (8))); +}; + +void +devlink_health_reporter_get_list_free(struct devlink_health_reporter_get_list *rsp); + +struct devlink_health_reporter_get_list * +devlink_health_reporter_get_dump(struct ynl_sock *ys, + struct devlink_health_reporter_get_req_dump *req); + +/* ============== DEVLINK_CMD_TRAP_GET ============== */ +/* DEVLINK_CMD_TRAP_GET - do */ +struct devlink_trap_get_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 trap_name_len; + } _present; + + char *bus_name; + char *dev_name; + char *trap_name; +}; + +static inline struct devlink_trap_get_req *devlink_trap_get_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_trap_get_req)); +} +void devlink_trap_get_req_free(struct devlink_trap_get_req *req); + +static inline void +devlink_trap_get_req_set_bus_name(struct devlink_trap_get_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_trap_get_req_set_dev_name(struct devlink_trap_get_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_trap_get_req_set_trap_name(struct devlink_trap_get_req *req, + const char *trap_name) +{ + free(req->trap_name); + req->_present.trap_name_len = strlen(trap_name); + req->trap_name = malloc(req->_present.trap_name_len + 1); + memcpy(req->trap_name, trap_name, req->_present.trap_name_len); + req->trap_name[req->_present.trap_name_len] = 0; +} + +struct devlink_trap_get_rsp { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 trap_name_len; + } _present; + + char *bus_name; + char *dev_name; + char *trap_name; +}; + +void devlink_trap_get_rsp_free(struct devlink_trap_get_rsp *rsp); + +/* + * Get trap instances. + */ +struct devlink_trap_get_rsp * +devlink_trap_get(struct ynl_sock *ys, struct devlink_trap_get_req *req); + +/* DEVLINK_CMD_TRAP_GET - dump */ +struct devlink_trap_get_req_dump { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + } _present; + + char *bus_name; + char *dev_name; +}; + +static inline struct devlink_trap_get_req_dump * +devlink_trap_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct devlink_trap_get_req_dump)); +} +void devlink_trap_get_req_dump_free(struct devlink_trap_get_req_dump *req); + +static inline void +devlink_trap_get_req_dump_set_bus_name(struct devlink_trap_get_req_dump *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_trap_get_req_dump_set_dev_name(struct devlink_trap_get_req_dump *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} + +struct devlink_trap_get_list { + struct devlink_trap_get_list *next; + struct devlink_trap_get_rsp obj __attribute__ ((aligned (8))); +}; + +void devlink_trap_get_list_free(struct devlink_trap_get_list *rsp); + +struct devlink_trap_get_list * +devlink_trap_get_dump(struct ynl_sock *ys, + struct devlink_trap_get_req_dump *req); + +/* ============== DEVLINK_CMD_TRAP_GROUP_GET ============== */ +/* DEVLINK_CMD_TRAP_GROUP_GET - do */ +struct devlink_trap_group_get_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 trap_group_name_len; + } _present; + + char *bus_name; + char *dev_name; + char *trap_group_name; +}; + +static inline struct devlink_trap_group_get_req * +devlink_trap_group_get_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_trap_group_get_req)); +} +void devlink_trap_group_get_req_free(struct devlink_trap_group_get_req *req); + +static inline void +devlink_trap_group_get_req_set_bus_name(struct devlink_trap_group_get_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_trap_group_get_req_set_dev_name(struct devlink_trap_group_get_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_trap_group_get_req_set_trap_group_name(struct devlink_trap_group_get_req *req, + const char *trap_group_name) +{ + free(req->trap_group_name); + req->_present.trap_group_name_len = strlen(trap_group_name); + req->trap_group_name = malloc(req->_present.trap_group_name_len + 1); + memcpy(req->trap_group_name, trap_group_name, req->_present.trap_group_name_len); + req->trap_group_name[req->_present.trap_group_name_len] = 0; +} + +struct devlink_trap_group_get_rsp { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 trap_group_name_len; + } _present; + + char *bus_name; + char *dev_name; + char *trap_group_name; +}; + +void devlink_trap_group_get_rsp_free(struct devlink_trap_group_get_rsp *rsp); + +/* + * Get trap group instances. + */ +struct devlink_trap_group_get_rsp * +devlink_trap_group_get(struct ynl_sock *ys, + struct devlink_trap_group_get_req *req); + +/* DEVLINK_CMD_TRAP_GROUP_GET - dump */ +struct devlink_trap_group_get_req_dump { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + } _present; + + char *bus_name; + char *dev_name; +}; + +static inline struct devlink_trap_group_get_req_dump * +devlink_trap_group_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct devlink_trap_group_get_req_dump)); +} +void +devlink_trap_group_get_req_dump_free(struct devlink_trap_group_get_req_dump *req); + +static inline void +devlink_trap_group_get_req_dump_set_bus_name(struct devlink_trap_group_get_req_dump *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_trap_group_get_req_dump_set_dev_name(struct devlink_trap_group_get_req_dump *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} + +struct devlink_trap_group_get_list { + struct devlink_trap_group_get_list *next; + struct devlink_trap_group_get_rsp obj __attribute__ ((aligned (8))); +}; + +void devlink_trap_group_get_list_free(struct devlink_trap_group_get_list *rsp); + +struct devlink_trap_group_get_list * +devlink_trap_group_get_dump(struct ynl_sock *ys, + struct devlink_trap_group_get_req_dump *req); + +/* ============== DEVLINK_CMD_TRAP_POLICER_GET ============== */ +/* DEVLINK_CMD_TRAP_POLICER_GET - do */ +struct devlink_trap_policer_get_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 trap_policer_id:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 trap_policer_id; +}; + +static inline struct devlink_trap_policer_get_req * +devlink_trap_policer_get_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_trap_policer_get_req)); +} +void +devlink_trap_policer_get_req_free(struct devlink_trap_policer_get_req *req); + +static inline void +devlink_trap_policer_get_req_set_bus_name(struct devlink_trap_policer_get_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_trap_policer_get_req_set_dev_name(struct devlink_trap_policer_get_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_trap_policer_get_req_set_trap_policer_id(struct devlink_trap_policer_get_req *req, + __u32 trap_policer_id) +{ + req->_present.trap_policer_id = 1; + req->trap_policer_id = trap_policer_id; +} + +struct devlink_trap_policer_get_rsp { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 trap_policer_id:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 trap_policer_id; +}; + +void +devlink_trap_policer_get_rsp_free(struct devlink_trap_policer_get_rsp *rsp); + +/* + * Get trap policer instances. + */ +struct devlink_trap_policer_get_rsp * +devlink_trap_policer_get(struct ynl_sock *ys, + struct devlink_trap_policer_get_req *req); + +/* DEVLINK_CMD_TRAP_POLICER_GET - dump */ +struct devlink_trap_policer_get_req_dump { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + } _present; + + char *bus_name; + char *dev_name; +}; + +static inline struct devlink_trap_policer_get_req_dump * +devlink_trap_policer_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct devlink_trap_policer_get_req_dump)); +} +void +devlink_trap_policer_get_req_dump_free(struct devlink_trap_policer_get_req_dump *req); + +static inline void +devlink_trap_policer_get_req_dump_set_bus_name(struct devlink_trap_policer_get_req_dump *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_trap_policer_get_req_dump_set_dev_name(struct devlink_trap_policer_get_req_dump *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} + +struct devlink_trap_policer_get_list { + struct devlink_trap_policer_get_list *next; + struct devlink_trap_policer_get_rsp obj __attribute__ ((aligned (8))); +}; + +void +devlink_trap_policer_get_list_free(struct devlink_trap_policer_get_list *rsp); + +struct devlink_trap_policer_get_list * +devlink_trap_policer_get_dump(struct ynl_sock *ys, + struct devlink_trap_policer_get_req_dump *req); + +/* ============== DEVLINK_CMD_RATE_GET ============== */ +/* DEVLINK_CMD_RATE_GET - do */ +struct devlink_rate_get_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + __u32 rate_node_name_len; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; + char *rate_node_name; +}; + +static inline struct devlink_rate_get_req *devlink_rate_get_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_rate_get_req)); +} +void devlink_rate_get_req_free(struct devlink_rate_get_req *req); + +static inline void +devlink_rate_get_req_set_bus_name(struct devlink_rate_get_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_rate_get_req_set_dev_name(struct devlink_rate_get_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_rate_get_req_set_port_index(struct devlink_rate_get_req *req, + __u32 port_index) +{ + req->_present.port_index = 1; + req->port_index = port_index; +} +static inline void +devlink_rate_get_req_set_rate_node_name(struct devlink_rate_get_req *req, + const char *rate_node_name) +{ + free(req->rate_node_name); + req->_present.rate_node_name_len = strlen(rate_node_name); + req->rate_node_name = malloc(req->_present.rate_node_name_len + 1); + memcpy(req->rate_node_name, rate_node_name, req->_present.rate_node_name_len); + req->rate_node_name[req->_present.rate_node_name_len] = 0; +} + +struct devlink_rate_get_rsp { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + __u32 rate_node_name_len; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; + char *rate_node_name; +}; + +void devlink_rate_get_rsp_free(struct devlink_rate_get_rsp *rsp); + +/* + * Get rate instances. + */ +struct devlink_rate_get_rsp * +devlink_rate_get(struct ynl_sock *ys, struct devlink_rate_get_req *req); + +/* DEVLINK_CMD_RATE_GET - dump */ +struct devlink_rate_get_req_dump { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + } _present; + + char *bus_name; + char *dev_name; +}; + +static inline struct devlink_rate_get_req_dump * +devlink_rate_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct devlink_rate_get_req_dump)); +} +void devlink_rate_get_req_dump_free(struct devlink_rate_get_req_dump *req); + +static inline void +devlink_rate_get_req_dump_set_bus_name(struct devlink_rate_get_req_dump *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_rate_get_req_dump_set_dev_name(struct devlink_rate_get_req_dump *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} + +struct devlink_rate_get_list { + struct devlink_rate_get_list *next; + struct devlink_rate_get_rsp obj __attribute__ ((aligned (8))); +}; + +void devlink_rate_get_list_free(struct devlink_rate_get_list *rsp); + +struct devlink_rate_get_list * +devlink_rate_get_dump(struct ynl_sock *ys, + struct devlink_rate_get_req_dump *req); + +/* ============== DEVLINK_CMD_LINECARD_GET ============== */ +/* DEVLINK_CMD_LINECARD_GET - do */ +struct devlink_linecard_get_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 linecard_index:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 linecard_index; +}; + +static inline struct devlink_linecard_get_req * +devlink_linecard_get_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_linecard_get_req)); +} +void devlink_linecard_get_req_free(struct devlink_linecard_get_req *req); + +static inline void +devlink_linecard_get_req_set_bus_name(struct devlink_linecard_get_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_linecard_get_req_set_dev_name(struct devlink_linecard_get_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_linecard_get_req_set_linecard_index(struct devlink_linecard_get_req *req, + __u32 linecard_index) +{ + req->_present.linecard_index = 1; + req->linecard_index = linecard_index; +} + +struct devlink_linecard_get_rsp { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 linecard_index:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 linecard_index; +}; + +void devlink_linecard_get_rsp_free(struct devlink_linecard_get_rsp *rsp); + +/* + * Get line card instances. + */ +struct devlink_linecard_get_rsp * +devlink_linecard_get(struct ynl_sock *ys, struct devlink_linecard_get_req *req); + +/* DEVLINK_CMD_LINECARD_GET - dump */ +struct devlink_linecard_get_req_dump { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + } _present; + + char *bus_name; + char *dev_name; +}; + +static inline struct devlink_linecard_get_req_dump * +devlink_linecard_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct devlink_linecard_get_req_dump)); +} +void +devlink_linecard_get_req_dump_free(struct devlink_linecard_get_req_dump *req); + +static inline void +devlink_linecard_get_req_dump_set_bus_name(struct devlink_linecard_get_req_dump *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_linecard_get_req_dump_set_dev_name(struct devlink_linecard_get_req_dump *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} + +struct devlink_linecard_get_list { + struct devlink_linecard_get_list *next; + struct devlink_linecard_get_rsp obj __attribute__ ((aligned (8))); +}; + +void devlink_linecard_get_list_free(struct devlink_linecard_get_list *rsp); + +struct devlink_linecard_get_list * +devlink_linecard_get_dump(struct ynl_sock *ys, + struct devlink_linecard_get_req_dump *req); + +/* ============== DEVLINK_CMD_SELFTESTS_GET ============== */ +/* DEVLINK_CMD_SELFTESTS_GET - do */ +struct devlink_selftests_get_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + } _present; + + char *bus_name; + char *dev_name; +}; + +static inline struct devlink_selftests_get_req * +devlink_selftests_get_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_selftests_get_req)); +} +void devlink_selftests_get_req_free(struct devlink_selftests_get_req *req); + +static inline void +devlink_selftests_get_req_set_bus_name(struct devlink_selftests_get_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_selftests_get_req_set_dev_name(struct devlink_selftests_get_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} + +struct devlink_selftests_get_rsp { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + } _present; + + char *bus_name; + char *dev_name; +}; + +void devlink_selftests_get_rsp_free(struct devlink_selftests_get_rsp *rsp); + +/* + * Get device selftest instances. + */ +struct devlink_selftests_get_rsp * +devlink_selftests_get(struct ynl_sock *ys, + struct devlink_selftests_get_req *req); + +/* DEVLINK_CMD_SELFTESTS_GET - dump */ +struct devlink_selftests_get_list { + struct devlink_selftests_get_list *next; + struct devlink_selftests_get_rsp obj __attribute__ ((aligned (8))); +}; + +void devlink_selftests_get_list_free(struct devlink_selftests_get_list *rsp); + +struct devlink_selftests_get_list * +devlink_selftests_get_dump(struct ynl_sock *ys); + #endif /* _LINUX_DEVLINK_GEN_H */ diff --git a/tools/net/ynl/generated/ethtool-user.h b/tools/net/ynl/generated/ethtool-user.h index d7d4ba855f43..ddc1a5209992 100644 --- a/tools/net/ynl/generated/ethtool-user.h +++ b/tools/net/ynl/generated/ethtool-user.h @@ -1422,6 +1422,7 @@ ethtool_wol_set_req_set_sopass(struct ethtool_wol_set_req *req, const void *sopass, size_t len) { free(req->sopass); + req->_present.sopass_len = len; req->sopass = malloc(req->_present.sopass_len); memcpy(req->sopass, sopass, req->_present.sopass_len); } @@ -4071,6 +4072,7 @@ ethtool_fec_set_req_set_stats_corrected(struct ethtool_fec_set_req *req, const void *corrected, size_t len) { free(req->stats.corrected); + req->stats._present.corrected_len = len; req->stats.corrected = malloc(req->stats._present.corrected_len); memcpy(req->stats.corrected, corrected, req->stats._present.corrected_len); } @@ -4079,6 +4081,7 @@ ethtool_fec_set_req_set_stats_uncorr(struct ethtool_fec_set_req *req, const void *uncorr, size_t len) { free(req->stats.uncorr); + req->stats._present.uncorr_len = len; req->stats.uncorr = malloc(req->stats._present.uncorr_len); memcpy(req->stats.uncorr, uncorr, req->stats._present.uncorr_len); } @@ -4087,6 +4090,7 @@ ethtool_fec_set_req_set_stats_corr_bits(struct ethtool_fec_set_req *req, const void *corr_bits, size_t len) { free(req->stats.corr_bits); + req->stats._present.corr_bits_len = len; req->stats.corr_bits = malloc(req->stats._present.corr_bits_len); memcpy(req->stats.corr_bits, corr_bits, req->stats._present.corr_bits_len); } diff --git a/tools/net/ynl/generated/fou-user.h b/tools/net/ynl/generated/fou-user.h index d8ab50579cd1..a8f860892540 100644 --- a/tools/net/ynl/generated/fou-user.h +++ b/tools/net/ynl/generated/fou-user.h @@ -91,6 +91,7 @@ fou_add_req_set_local_v6(struct fou_add_req *req, const void *local_v6, size_t len) { free(req->local_v6); + req->_present.local_v6_len = len; req->local_v6 = malloc(req->_present.local_v6_len); memcpy(req->local_v6, local_v6, req->_present.local_v6_len); } @@ -99,6 +100,7 @@ fou_add_req_set_peer_v6(struct fou_add_req *req, const void *peer_v6, size_t len) { free(req->peer_v6); + req->_present.peer_v6_len = len; req->peer_v6 = malloc(req->_present.peer_v6_len); memcpy(req->peer_v6, peer_v6, req->_present.peer_v6_len); } @@ -192,6 +194,7 @@ fou_del_req_set_local_v6(struct fou_del_req *req, const void *local_v6, size_t len) { free(req->local_v6); + req->_present.local_v6_len = len; req->local_v6 = malloc(req->_present.local_v6_len); memcpy(req->local_v6, local_v6, req->_present.local_v6_len); } @@ -200,6 +203,7 @@ fou_del_req_set_peer_v6(struct fou_del_req *req, const void *peer_v6, size_t len) { free(req->peer_v6); + req->_present.peer_v6_len = len; req->peer_v6 = malloc(req->_present.peer_v6_len); memcpy(req->peer_v6, peer_v6, req->_present.peer_v6_len); } @@ -280,6 +284,7 @@ fou_get_req_set_local_v6(struct fou_get_req *req, const void *local_v6, size_t len) { free(req->local_v6); + req->_present.local_v6_len = len; req->local_v6 = malloc(req->_present.local_v6_len); memcpy(req->local_v6, local_v6, req->_present.local_v6_len); } @@ -288,6 +293,7 @@ fou_get_req_set_peer_v6(struct fou_get_req *req, const void *peer_v6, size_t len) { free(req->peer_v6); + req->_present.peer_v6_len = len; req->peer_v6 = malloc(req->_present.peer_v6_len); memcpy(req->peer_v6, peer_v6, req->_present.peer_v6_len); } diff --git a/tools/net/ynl/generated/netdev-user.c b/tools/net/ynl/generated/netdev-user.c index 4eb8aefef0cd..68b408ca0f7f 100644 --- a/tools/net/ynl/generated/netdev-user.c +++ b/tools/net/ynl/generated/netdev-user.c @@ -50,6 +50,7 @@ struct ynl_policy_attr netdev_dev_policy[NETDEV_A_DEV_MAX + 1] = { [NETDEV_A_DEV_IFINDEX] = { .name = "ifindex", .type = YNL_PT_U32, }, [NETDEV_A_DEV_PAD] = { .name = "pad", .type = YNL_PT_IGNORE, }, [NETDEV_A_DEV_XDP_FEATURES] = { .name = "xdp-features", .type = YNL_PT_U64, }, + [NETDEV_A_DEV_XDP_ZC_MAX_SEGS] = { .name = "xdp-zc-max-segs", .type = YNL_PT_U32, }, }; struct ynl_policy_nest netdev_dev_nest = { @@ -91,6 +92,11 @@ int netdev_dev_get_rsp_parse(const struct nlmsghdr *nlh, void *data) return MNL_CB_ERROR; dst->_present.xdp_features = 1; dst->xdp_features = mnl_attr_get_u64(attr); + } else if (type == NETDEV_A_DEV_XDP_ZC_MAX_SEGS) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.xdp_zc_max_segs = 1; + dst->xdp_zc_max_segs = mnl_attr_get_u32(attr); } } diff --git a/tools/net/ynl/generated/netdev-user.h b/tools/net/ynl/generated/netdev-user.h index 5554dc69bb9c..0952d3261f4d 100644 --- a/tools/net/ynl/generated/netdev-user.h +++ b/tools/net/ynl/generated/netdev-user.h @@ -47,10 +47,12 @@ struct netdev_dev_get_rsp { struct { __u32 ifindex:1; __u32 xdp_features:1; + __u32 xdp_zc_max_segs:1; } _present; __u32 ifindex; __u64 xdp_features; + __u32 xdp_zc_max_segs; }; void netdev_dev_get_rsp_free(struct netdev_dev_get_rsp *rsp); diff --git a/tools/net/ynl/lib/__init__.py b/tools/net/ynl/lib/__init__.py index 4b3797fe784b..f7eaa07783e7 100644 --- a/tools/net/ynl/lib/__init__.py +++ b/tools/net/ynl/lib/__init__.py @@ -2,7 +2,7 @@ from .nlspec import SpecAttr, SpecAttrSet, SpecEnumEntry, SpecEnumSet, \ SpecFamily, SpecOperation -from .ynl import YnlFamily +from .ynl import YnlFamily, Netlink __all__ = ["SpecAttr", "SpecAttrSet", "SpecEnumEntry", "SpecEnumSet", - "SpecFamily", "SpecOperation", "YnlFamily"] + "SpecFamily", "SpecOperation", "YnlFamily", "Netlink"] diff --git a/tools/net/ynl/lib/nlspec.py b/tools/net/ynl/lib/nlspec.py index 0ff0d18666b2..37bcb4d8b37b 100644 --- a/tools/net/ynl/lib/nlspec.py +++ b/tools/net/ynl/lib/nlspec.py @@ -322,6 +322,26 @@ class SpecOperation(SpecElement): self.attr_set = self.family.attr_sets[attr_set_name] +class SpecMcastGroup(SpecElement): + """Netlink Multicast Group + + Information about a multicast group. + + Value is only used for classic netlink families that use the + netlink-raw schema. Genetlink families use dynamic ID allocation + where the ids of multicast groups get resolved at runtime. Value + will be None for genetlink families. + + Attributes: + name name of the mulitcast group + value integer id of this multicast group for netlink-raw or None + yaml raw spec as loaded from the spec file + """ + def __init__(self, family, yaml): + super().__init__(family, yaml) + self.value = self.yaml.get('value') + + class SpecFamily(SpecElement): """ Netlink Family Spec class. @@ -343,6 +363,7 @@ class SpecFamily(SpecElement): ntfs dict of all async events consts dict of all constants/enums fixed_header string, optional name of family default fixed header struct + mcast_groups dict of all multicast groups (index by name) """ def __init__(self, spec_path, schema_path=None, exclude_ops=None): with open(spec_path, "r") as stream: @@ -384,6 +405,7 @@ class SpecFamily(SpecElement): self.ops = collections.OrderedDict() self.ntfs = collections.OrderedDict() self.consts = collections.OrderedDict() + self.mcast_groups = collections.OrderedDict() last_exception = None while len(self._resolution_list) > 0: @@ -416,6 +438,9 @@ class SpecFamily(SpecElement): def new_operation(self, elem, req_val, rsp_val): return SpecOperation(self, elem, req_val, rsp_val) + def new_mcast_group(self, elem): + return SpecMcastGroup(self, elem) + def add_unresolved(self, elem): self._resolution_list.append(elem) @@ -512,3 +537,9 @@ class SpecFamily(SpecElement): self.ops[op.name] = op elif op.is_async: self.ntfs[op.name] = op + + mcgs = self.yaml.get('mcast-groups') + if mcgs: + for elem in mcgs['list']: + mcg = self.new_mcast_group(elem) + self.mcast_groups[elem['name']] = mcg diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/lib/ynl.py index 3ca28d4bcb18..13c4b019a881 100644 --- a/tools/net/ynl/lib/ynl.py +++ b/tools/net/ynl/lib/ynl.py @@ -25,6 +25,7 @@ class Netlink: NETLINK_ADD_MEMBERSHIP = 1 NETLINK_CAP_ACK = 10 NETLINK_EXT_ACK = 11 + NETLINK_GET_STRICT_CHK = 12 # Netlink message NLMSG_ERROR = 2 @@ -34,6 +35,10 @@ class Netlink: NLM_F_ACK = 4 NLM_F_ROOT = 0x100 NLM_F_MATCH = 0x200 + + NLM_F_REPLACE = 0x100 + NLM_F_EXCL = 0x200 + NLM_F_CREATE = 0x400 NLM_F_APPEND = 0x800 NLM_F_CAPPED = 0x100 @@ -228,6 +233,9 @@ class NlMsg: desc += f" ({spec['doc']})" self.extack['miss-type'] = desc + def cmd(self): + return self.nl_type + def __repr__(self): msg = f"nl_len = {self.nl_len} ({len(self.raw)}) nl_flags = 0x{self.nl_flags:x} nl_type = {self.nl_type}\n" if self.error: @@ -293,7 +301,7 @@ def _genl_load_families(): gm = GenlMsg(nl_msg) fam = dict() - for attr in gm.raw_attrs: + for attr in NlAttrs(gm.raw): if attr.type == Netlink.CTRL_ATTR_FAMILY_ID: fam['id'] = attr.as_scalar('u16') elif attr.type == Netlink.CTRL_ATTR_FAMILY_NAME: @@ -317,23 +325,13 @@ def _genl_load_families(): class GenlMsg: - def __init__(self, nl_msg, fixed_header_members=[]): + def __init__(self, nl_msg): self.nl = nl_msg + self.genl_cmd, self.genl_version, _ = struct.unpack_from("BBH", nl_msg.raw, 0) + self.raw = nl_msg.raw[4:] - self.hdr = nl_msg.raw[0:4] - offset = 4 - - self.genl_cmd, self.genl_version, _ = struct.unpack("BBH", self.hdr) - - self.fixed_header_attrs = dict() - for m in fixed_header_members: - format = NlAttr.get_format(m.type, m.byte_order) - decoded = format.unpack_from(nl_msg.raw, offset) - offset += format.size - self.fixed_header_attrs[m.name] = decoded[0] - - self.raw = nl_msg.raw[offset:] - self.raw_attrs = NlAttrs(self.raw) + def cmd(self): + return self.genl_cmd def __repr__(self): msg = repr(self.nl) @@ -343,9 +341,41 @@ class GenlMsg: return msg -class GenlFamily: - def __init__(self, family_name): +class NetlinkProtocol: + def __init__(self, family_name, proto_num): self.family_name = family_name + self.proto_num = proto_num + + def _message(self, nl_type, nl_flags, seq=None): + if seq is None: + seq = random.randint(1, 1024) + nlmsg = struct.pack("HHII", nl_type, nl_flags, seq, 0) + return nlmsg + + def message(self, flags, command, version, seq=None): + return self._message(command, flags, seq) + + def _decode(self, nl_msg): + return nl_msg + + def decode(self, ynl, nl_msg): + msg = self._decode(nl_msg) + fixed_header_size = 0 + if ynl: + op = ynl.rsp_by_value[msg.cmd()] + fixed_header_size = ynl._fixed_header_size(op) + msg.raw_attrs = NlAttrs(msg.raw[fixed_header_size:]) + return msg + + def get_mcast_id(self, mcast_name, mcast_groups): + if mcast_name not in mcast_groups: + raise Exception(f'Multicast group "{mcast_name}" not present in the spec') + return mcast_groups[mcast_name].value + + +class GenlProtocol(NetlinkProtocol): + def __init__(self, family_name): + super().__init__(family_name, Netlink.NETLINK_GENERIC) global genl_family_name_to_id if genl_family_name_to_id is None: @@ -354,6 +384,19 @@ class GenlFamily: self.genl_family = genl_family_name_to_id[family_name] self.family_id = genl_family_name_to_id[family_name]['id'] + def message(self, flags, command, version, seq=None): + nlmsg = self._message(self.family_id, flags, seq) + genlmsg = struct.pack("BBH", command, version, 0) + return nlmsg + genlmsg + + def _decode(self, nl_msg): + return GenlMsg(nl_msg) + + def get_mcast_id(self, mcast_name, mcast_groups): + if mcast_name not in self.genl_family['mcast']: + raise Exception(f'Multicast group "{mcast_name}" not present in the family') + return self.genl_family['mcast'][mcast_name] + # # YNL implementation details. @@ -366,9 +409,19 @@ class YnlFamily(SpecFamily): self.include_raw = False - self.sock = socket.socket(socket.AF_NETLINK, socket.SOCK_RAW, Netlink.NETLINK_GENERIC) + try: + if self.proto == "netlink-raw": + self.nlproto = NetlinkProtocol(self.yaml['name'], + self.yaml['protonum']) + else: + self.nlproto = GenlProtocol(self.yaml['name']) + except KeyError: + raise Exception(f"Family '{self.yaml['name']}' not supported by the kernel") + + self.sock = socket.socket(socket.AF_NETLINK, socket.SOCK_RAW, self.nlproto.proto_num) self.sock.setsockopt(Netlink.SOL_NETLINK, Netlink.NETLINK_CAP_ACK, 1) self.sock.setsockopt(Netlink.SOL_NETLINK, Netlink.NETLINK_EXT_ACK, 1) + self.sock.setsockopt(Netlink.SOL_NETLINK, Netlink.NETLINK_GET_STRICT_CHK, 1) self.async_msg_ids = set() self.async_msg_queue = [] @@ -381,21 +434,18 @@ class YnlFamily(SpecFamily): bound_f = functools.partial(self._op, op_name) setattr(self, op.ident_name, bound_f) - try: - self.family = GenlFamily(self.yaml['name']) - except KeyError: - raise Exception(f"Family '{self.yaml['name']}' not supported by the kernel") def ntf_subscribe(self, mcast_name): - if mcast_name not in self.family.genl_family['mcast']: - raise Exception(f'Multicast group "{mcast_name}" not present in the family') - + mcast_id = self.nlproto.get_mcast_id(mcast_name, self.mcast_groups) self.sock.bind((0, 0)) self.sock.setsockopt(Netlink.SOL_NETLINK, Netlink.NETLINK_ADD_MEMBERSHIP, - self.family.genl_family['mcast'][mcast_name]) + mcast_id) def _add_attr(self, space, name, value): - attr = self.attr_sets[space][name] + try: + attr = self.attr_sets[space][name] + except KeyError: + raise Exception(f"Space '{space}' has no attribute '{name}'") nl_type = attr.value if attr["type"] == 'nest': nl_type |= Netlink.NLA_F_NESTED @@ -407,7 +457,12 @@ class YnlFamily(SpecFamily): elif attr["type"] == 'string': attr_payload = str(value).encode('ascii') + b'\x00' elif attr["type"] == 'binary': - attr_payload = bytes.fromhex(value) + if isinstance(value, bytes): + attr_payload = value + elif isinstance(value, str): + attr_payload = bytes.fromhex(value) + else: + raise Exception(f'Unknown type for binary attribute, value: {value}') elif attr['type'] in NlAttr.type_formats: format = NlAttr.get_format(attr['type'], attr.byte_order) attr_payload = format.pack(int(value)) @@ -446,11 +501,25 @@ class YnlFamily(SpecFamily): decoded = NlAttr.formatted_string(decoded, attr_spec.display_hint) return decoded + def _decode_array_nest(self, attr, attr_spec): + decoded = [] + offset = 0 + while offset < len(attr.raw): + item = NlAttr(attr.raw, offset) + offset += item.full_len + + subattrs = self._decode(NlAttrs(item.raw), attr_spec['nested-attributes']) + decoded.append({ item.type: subattrs }) + return decoded + def _decode(self, attrs, space): attr_space = self.attr_sets[space] rsp = dict() for attr in attrs: - attr_spec = attr_space.attrs_by_val[attr.type] + try: + attr_spec = attr_space.attrs_by_val[attr.type] + except KeyError: + raise Exception(f"Space '{space}' has no attribute with value '{attr.type}'") if attr_spec["type"] == 'nest': subdict = self._decode(NlAttrs(attr.raw), attr_spec['nested-attributes']) decoded = subdict @@ -462,6 +531,8 @@ class YnlFamily(SpecFamily): decoded = True elif attr_spec["type"] in NlAttr.type_formats: decoded = attr.as_scalar(attr_spec['type'], attr_spec.byte_order) + elif attr_spec["type"] == 'array-nest': + decoded = self._decode_array_nest(attr, attr_spec) else: raise Exception(f'Unknown {attr_spec["type"]} with name {attr_spec["name"]}') @@ -479,7 +550,10 @@ class YnlFamily(SpecFamily): def _decode_extack_path(self, attrs, attr_set, offset, target): for attr in attrs: - attr_spec = attr_set.attrs_by_val[attr.type] + try: + attr_spec = attr_set.attrs_by_val[attr.type] + except KeyError: + raise Exception(f"Space '{attr_set.name}' has no attribute with value '{attr.type}'") if offset > target: break if offset == target: @@ -500,25 +574,53 @@ class YnlFamily(SpecFamily): return None - def _decode_extack(self, request, attr_space, extack): + def _decode_extack(self, request, op, extack): if 'bad-attr-offs' not in extack: return - genl_req = GenlMsg(NlMsg(request, 0, attr_space=attr_space)) - path = self._decode_extack_path(genl_req.raw_attrs, attr_space, - 20, extack['bad-attr-offs']) + msg = self.nlproto.decode(self, NlMsg(request, 0, op.attr_set)) + offset = 20 + self._fixed_header_size(op) + path = self._decode_extack_path(msg.raw_attrs, op.attr_set, offset, + extack['bad-attr-offs']) if path: del extack['bad-attr-offs'] extack['bad-attr'] = path - def handle_ntf(self, nl_msg, genl_msg): + def _fixed_header_size(self, op): + if op.fixed_header: + fixed_header_members = self.consts[op.fixed_header].members + size = 0 + for m in fixed_header_members: + format = NlAttr.get_format(m.type, m.byte_order) + size += format.size + return size + else: + return 0 + + def _decode_fixed_header(self, msg, name): + fixed_header_members = self.consts[name].members + fixed_header_attrs = dict() + offset = 0 + for m in fixed_header_members: + format = NlAttr.get_format(m.type, m.byte_order) + [ value ] = format.unpack_from(msg.raw, offset) + offset += format.size + if m.enum: + value = self._decode_enum(value, m) + fixed_header_attrs[m.name] = value + return fixed_header_attrs + + def handle_ntf(self, decoded): msg = dict() if self.include_raw: - msg['nlmsg'] = nl_msg - msg['genlmsg'] = genl_msg - op = self.rsp_by_value[genl_msg.genl_cmd] + msg['raw'] = decoded + op = self.rsp_by_value[decoded.cmd()] + attrs = self._decode(decoded.raw_attrs, op.attr_set.name) + if op.fixed_header: + attrs.update(self._decode_fixed_header(decoded, op.fixed_header)) + msg['name'] = op['name'] - msg['msg'] = self._decode(genl_msg.raw_attrs, op.attr_set.name) + msg['msg'] = attrs self.async_msg_queue.append(msg) def check_ntf(self): @@ -538,12 +640,12 @@ class YnlFamily(SpecFamily): print("Netlink done while checking for ntf!?") continue - gm = GenlMsg(nl_msg) - if gm.genl_cmd not in self.async_msg_ids: - print("Unexpected msg id done while checking for ntf", gm) + decoded = self.nlproto.decode(self, nl_msg) + if decoded.cmd() not in self.async_msg_ids: + print("Unexpected msg id done while checking for ntf", decoded) continue - self.handle_ntf(nl_msg, gm) + self.handle_ntf(decoded) def operation_do_attributes(self, name): """ @@ -556,15 +658,17 @@ class YnlFamily(SpecFamily): return op['do']['request']['attributes'].copy() - def _op(self, method, vals, dump=False): + def _op(self, method, vals, flags, dump=False): op = self.ops[method] nl_flags = Netlink.NLM_F_REQUEST | Netlink.NLM_F_ACK + for flag in flags or []: + nl_flags |= flag if dump: nl_flags |= Netlink.NLM_F_DUMP req_seq = random.randint(1024, 65535) - msg = _genl_msg(self.family.family_id, nl_flags, op.req_value, 1, req_seq) + msg = self.nlproto.message(nl_flags, op.req_value, 1, req_seq) fixed_header_members = [] if op.fixed_header: fixed_header_members = self.consts[op.fixed_header].members @@ -585,7 +689,7 @@ class YnlFamily(SpecFamily): nms = NlMsgs(reply, attr_space=op.attr_set) for nl_msg in nms: if nl_msg.extack: - self._decode_extack(msg, op.attr_set, nl_msg.extack) + self._decode_extack(msg, op, nl_msg.extack) if nl_msg.error: raise NlError(nl_msg) @@ -596,18 +700,20 @@ class YnlFamily(SpecFamily): done = True break - gm = GenlMsg(nl_msg, fixed_header_members) + decoded = self.nlproto.decode(self, nl_msg) + # Check if this is a reply to our request - if nl_msg.nl_seq != req_seq or gm.genl_cmd != op.rsp_value: - if gm.genl_cmd in self.async_msg_ids: - self.handle_ntf(nl_msg, gm) + if nl_msg.nl_seq != req_seq or decoded.cmd() != op.rsp_value: + if decoded.cmd() in self.async_msg_ids: + self.handle_ntf(decoded) continue else: - print('Unexpected message: ' + repr(gm)) + print('Unexpected message: ' + repr(decoded)) continue - rsp_msg = self._decode(gm.raw_attrs, op.attr_set.name) - rsp_msg.update(gm.fixed_header_attrs) + rsp_msg = self._decode(decoded.raw_attrs, op.attr_set.name) + if op.fixed_header: + rsp_msg.update(self._decode_fixed_header(decoded, op.fixed_header)) rsp.append(rsp_msg) if not rsp: @@ -616,8 +722,8 @@ class YnlFamily(SpecFamily): return rsp[0] return rsp - def do(self, method, vals): - return self._op(method, vals) + def do(self, method, vals, flags): + return self._op(method, vals, flags) def dump(self, method, vals): - return self._op(method, vals, dump=True) + return self._op(method, vals, [], dump=True) diff --git a/tools/net/ynl/samples/netdev.c b/tools/net/ynl/samples/netdev.c index d31268aa47c5..06433400dddd 100644 --- a/tools/net/ynl/samples/netdev.c +++ b/tools/net/ynl/samples/netdev.c @@ -38,6 +38,8 @@ static void netdev_print_device(struct netdev_dev_get_rsp *d, unsigned int op) printf(" %s", netdev_xdp_act_str(1 << i)); } + printf(" xdp-zc-max-segs=%u", d->xdp_zc_max_segs); + name = netdev_op_str(op); if (name) printf(" (ntf: %s)", name); diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py index 71c5e79e877f..897af958cee8 100755 --- a/tools/net/ynl/ynl-gen-c.py +++ b/tools/net/ynl/ynl-gen-c.py @@ -5,6 +5,8 @@ import argparse import collections import os import re +import shutil +import tempfile import yaml from lib import SpecFamily, SpecAttrSet, SpecAttr, SpecOperation, SpecEnumSet, SpecEnumEntry @@ -426,6 +428,7 @@ class TypeBinary(Type): def _setter_lines(self, ri, member, presence): return [f"free({member});", + f"{presence}_len = len;", f"{member} = malloc({presence}_len);", f'memcpy({member}, {self.c_name}, {presence}_len);'] @@ -612,7 +615,7 @@ class Struct: self.attr_list = [] self.attrs = dict() - if type_list: + if type_list is not None: for t in type_list: self.attr_list.append((t, self.attr_set[t]),) else: @@ -975,7 +978,9 @@ class Family(SpecFamily): for op_mode in ['do', 'dump']: if op_mode in op: - global_set.update(op[op_mode].get('request', [])) + req = op[op_mode].get('request') + if req: + global_set.update(req.get('attributes', [])) self.global_policy = [] self.global_policy_set = attr_set_name @@ -1040,14 +1045,30 @@ class RenderInfo: class CodeWriter: - def __init__(self, nlib, out_file): + def __init__(self, nlib, out_file=None): self.nlib = nlib self._nl = False self._block_end = False self._silent_block = False self._ind = 0 - self._out = out_file + if out_file is None: + self._out = os.sys.stdout + else: + self._out = tempfile.TemporaryFile('w+') + self._out_file = out_file + + def __del__(self): + self.close_out_file() + + def close_out_file(self): + if self._out == os.sys.stdout: + return + with open(self._out_file, 'w+') as out_file: + self._out.seek(0) + shutil.copyfileobj(self._out, out_file) + self._out.close() + self._out = os.sys.stdout @classmethod def _is_cond(cls, line): @@ -1538,7 +1559,14 @@ def parse_rsp_msg(ri, deref=False): ri.cw.write_func_prot('int', f'{op_prefix(ri, "reply", deref=deref)}_parse', func_args) - _multi_parse(ri, ri.struct["reply"], init_lines, local_vars) + if ri.struct["reply"].member_list(): + _multi_parse(ri, ri.struct["reply"], init_lines, local_vars) + else: + # Empty reply + ri.cw.block_start() + ri.cw.p('return MNL_CB_OK;') + ri.cw.block_end() + ri.cw.nl() def print_req(ri): @@ -1843,13 +1871,13 @@ def print_ntf_type_free(ri): def print_req_policy_fwd(cw, struct, ri=None, terminate=True): - if terminate and ri and kernel_can_gen_family_struct(struct.family): + if terminate and ri and policy_should_be_static(struct.family): return if terminate: prefix = 'extern ' else: - if kernel_can_gen_family_struct(struct.family) and ri: + if ri and policy_should_be_static(struct.family): prefix = 'static ' else: prefix = '' @@ -1871,12 +1899,17 @@ def print_req_policy(cw, struct, ri=None): for _, arg in struct.member_list(): arg.attr_policy(cw) cw.p("};") + cw.nl() def kernel_can_gen_family_struct(family): return family.proto == 'genetlink' +def policy_should_be_static(family): + return family.kernel_policy == 'split' or kernel_can_gen_family_struct(family) + + def print_kernel_op_table_fwd(family, cw, terminate): exported = not kernel_can_gen_family_struct(family) @@ -1988,9 +2021,18 @@ def print_kernel_op_table(family, cw): cw.block_start() members = [('cmd', op.enum_name)] if 'dont-validate' in op: - members.append(('validate', - ' | '.join([c_upper('genl-dont-validate-' + x) - for x in op['dont-validate']])), ) + dont_validate = [] + for x in op['dont-validate']: + if op_mode == 'do' and x in ['dump', 'dump-strict']: + continue + if op_mode == "dump" and x == 'strict': + continue + dont_validate.append(x) + + if dont_validate: + members.append(('validate', + ' | '.join([c_upper('genl-dont-validate-' + x) + for x in dont_validate])), ) name = c_lower(f"{family.name}-nl-{op_name}-{op_mode}it") if 'pre' in op[op_mode]: members.append((cb_names[op_mode]['pre'], c_lower(op[op_mode]['pre']))) @@ -2125,6 +2167,7 @@ def render_uapi(family, cw): if const.get('render-max', False): cw.nl() + cw.p('/* private: */') if const['type'] == 'flags': max_name = c_upper(name_pfx + 'mask') max_val = f' = {enum.get_mask()},' @@ -2286,11 +2329,9 @@ def main(): parser.add_argument('--source', dest='header', action='store_false') parser.add_argument('--user-header', nargs='+', default=[]) parser.add_argument('--exclude-op', action='append', default=[]) - parser.add_argument('-o', dest='out_file', type=str) + parser.add_argument('-o', dest='out_file', type=str, default=None) args = parser.parse_args() - out_file = open(args.out_file, 'w+') if args.out_file else os.sys.stdout - if args.header is None: parser.error("--header or --source is required") @@ -2308,13 +2349,13 @@ def main(): return supported_models = ['unified'] - if args.mode == 'user': + if args.mode in ['user', 'kernel']: supported_models += ['directional'] if parsed.msg_id_model not in supported_models: print(f'Message enum-model {parsed.msg_id_model} not supported for {args.mode} generation') os.sys.exit(1) - cw = CodeWriter(BaseNlLib(), out_file) + cw = CodeWriter(BaseNlLib(), args.out_file) _, spec_kernel = find_kernel_root(args.spec) if args.mode == 'uapi' or args.header: diff --git a/tools/net/ynl/ynl-regen.sh b/tools/net/ynl/ynl-regen.sh index 8d4ca6a50582..bdba24066cf1 100755 --- a/tools/net/ynl/ynl-regen.sh +++ b/tools/net/ynl/ynl-regen.sh @@ -4,15 +4,18 @@ TOOL=$(dirname $(realpath $0))/ynl-gen-c.py force= +search= while [ ! -z "$1" ]; do case "$1" in -f ) force=yes; shift ;; + -p ) search=$2; shift 2 ;; * ) echo "Unrecognized option '$1'"; exit 1 ;; esac done KDIR=$(dirname $(dirname $(dirname $(dirname $(realpath $0))))) +pushd ${search:-$KDIR} >>/dev/null files=$(git grep --files-with-matches '^/\* YNL-GEN \(kernel\|uapi\|user\)') for f in $files; do @@ -30,3 +33,5 @@ for f in $files; do $TOOL --mode ${params[2]} --${params[3]} --spec $KDIR/${params[0]} \ $args -o $f done + +popd >>/dev/null diff --git a/tools/perf/Documentation/perf-bench.txt b/tools/perf/Documentation/perf-bench.txt index f04f0eaded98..ca5789625cd2 100644 --- a/tools/perf/Documentation/perf-bench.txt +++ b/tools/perf/Documentation/perf-bench.txt @@ -67,6 +67,9 @@ SUBSYSTEM 'internals':: Benchmark internal perf functionality. +'uprobe':: + Benchmark overhead of uprobe + BPF. + 'all':: All benchmark subsystems. diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt index 1478068ad5dd..0b4e79dbd3f6 100644 --- a/tools/perf/Documentation/perf-config.txt +++ b/tools/perf/Documentation/perf-config.txt @@ -125,9 +125,6 @@ Given a $HOME/.perfconfig like this: group = true skip-empty = true - [llvm] - dump-obj = true - clang-opt = -g You can hide source code of annotate feature setting the config to false with @@ -657,36 +654,6 @@ ftrace.*:: -F option is not specified. Possible values are 'function' and 'function_graph'. -llvm.*:: - llvm.clang-path:: - Path to clang. If omit, search it from $PATH. - - llvm.clang-bpf-cmd-template:: - Cmdline template. Below lines show its default value. Environment - variable is used to pass options. - "$CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS "\ - "-DLINUX_VERSION_CODE=$LINUX_VERSION_CODE " \ - "$CLANG_OPTIONS $PERF_BPF_INC_OPTIONS $KERNEL_INC_OPTIONS " \ - "-Wno-unused-value -Wno-pointer-sign " \ - "-working-directory $WORKING_DIR " \ - "-c \"$CLANG_SOURCE\" --target=bpf $CLANG_EMIT_LLVM -O2 -o - $LLVM_OPTIONS_PIPE" - - llvm.clang-opt:: - Options passed to clang. - - llvm.kbuild-dir:: - kbuild directory. If not set, use /lib/modules/`uname -r`/build. - If set to "" deliberately, skip kernel header auto-detector. - - llvm.kbuild-opts:: - Options passed to 'make' when detecting kernel header options. - - llvm.dump-obj:: - Enable perf dump BPF object files compiled by LLVM. - - llvm.opts:: - Options passed to llc. - samples.*:: samples.context:: diff --git a/tools/perf/Documentation/perf-dlfilter.txt b/tools/perf/Documentation/perf-dlfilter.txt index fb22e3b31dc5..8887cc20a809 100644 --- a/tools/perf/Documentation/perf-dlfilter.txt +++ b/tools/perf/Documentation/perf-dlfilter.txt @@ -64,6 +64,12 @@ internal filtering. If implemented, 'filter_description' should return a one-line description of the filter, and optionally a longer description. +Do not assume the 'sample' argument is valid (dereferenceable) +after 'filter_event' and 'filter_event_early' return. + +Do not assume data referenced by pointers in struct perf_dlfilter_sample +is valid (dereferenceable) after 'filter_event' and 'filter_event_early' return. + The perf_dlfilter_sample structure ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ @@ -150,7 +156,8 @@ struct perf_dlfilter_fns { const char *(*srcline)(void *ctx, __u32 *line_number); struct perf_event_attr *(*attr)(void *ctx); __s32 (*object_code)(void *ctx, __u64 ip, void *buf, __u32 len); - void *(*reserved[120])(void *); + void (*al_cleanup)(void *ctx, struct perf_dlfilter_al *al); + void *(*reserved[119])(void *); }; ---- @@ -161,7 +168,8 @@ struct perf_dlfilter_fns { 'args' returns arguments from --dlarg options. 'resolve_address' provides information about 'address'. al->size must be set -before calling. Returns 0 on success, -1 otherwise. +before calling. Returns 0 on success, -1 otherwise. Call al_cleanup() (if present, +see below) when 'al' data is no longer needed. 'insn' returns instruction bytes and length. @@ -171,6 +179,12 @@ before calling. Returns 0 on success, -1 otherwise. 'object_code' reads object code and returns the number of bytes read. +'al_cleanup' must be called (if present, so check perf_dlfilter_fns.al_cleanup != NULL) +after resolve_address() to free any associated resources. + +Do not assume pointers obtained via perf_dlfilter_fns are valid (dereferenceable) +after 'filter_event' and 'filter_event_early' return. + The perf_dlfilter_al structure ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ @@ -197,9 +211,13 @@ struct perf_dlfilter_al { /* Below members are only populated by resolve_ip() */ __u8 filtered; /* true if this sample event will be filtered out */ const char *comm; + void *priv; /* Private data. Do not change */ }; ---- +Do not assume data referenced by pointers in struct perf_dlfilter_al +is valid (dereferenceable) after 'filter_event' and 'filter_event_early' return. + perf_dlfilter_sample flags ~~~~~~~~~~~~~~~~~~~~~~~~~~ diff --git a/tools/perf/Documentation/perf-ftrace.txt b/tools/perf/Documentation/perf-ftrace.txt index df4595563801..d780b93fcf87 100644 --- a/tools/perf/Documentation/perf-ftrace.txt +++ b/tools/perf/Documentation/perf-ftrace.txt @@ -96,8 +96,9 @@ OPTIONS for 'perf ftrace trace' --func-opts:: List of options allowed to set: - call-graph - Display kernel stack trace for function tracer. - irq-info - Display irq context info for function tracer. + + - call-graph - Display kernel stack trace for function tracer. + - irq-info - Display irq context info for function tracer. -G:: --graph-funcs=:: @@ -118,11 +119,12 @@ OPTIONS for 'perf ftrace trace' --graph-opts:: List of options allowed to set: - nosleep-time - Measure on-CPU time only for function_graph tracer. - noirqs - Ignore functions that happen inside interrupt. - verbose - Show process names, PIDs, timestamps, etc. - thresh=<n> - Setup trace duration threshold in microseconds. - depth=<n> - Set max depth for function graph tracer to follow. + + - nosleep-time - Measure on-CPU time only for function_graph tracer. + - noirqs - Ignore functions that happen inside interrupt. + - verbose - Show process names, PIDs, timestamps, etc. + - thresh=<n> - Setup trace duration threshold in microseconds. + - depth=<n> - Set max depth for function graph tracer to follow. OPTIONS for 'perf ftrace latency' diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 680396c56bd1..d5217be012d7 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -99,20 +99,6 @@ OPTIONS If you want to profile write accesses in [0x1000~1008), just set 'mem:0x1000/8:w'. - - a BPF source file (ending in .c) or a precompiled object file (ending - in .o) selects one or more BPF events. - The BPF program can attach to various perf events based on the ELF section - names. - - When processing a '.c' file, perf searches an installed LLVM to compile it - into an object file first. Optional clang options can be passed via the - '--clang-opt' command line option, e.g.: - - perf record --clang-opt "-DLINUX_VERSION_CODE=0x50000" \ - -e tests/bpf-script-example.c - - Note: '--clang-opt' must be placed before '--event/-e'. - - a group of events surrounded by a pair of brace ("{event1,event2,...}"). Each event is separated by commas and the group should be quoted to prevent the shell interpretation. You also need to use --group on @@ -523,9 +509,10 @@ CLOCK_BOOTTIME, CLOCK_REALTIME and CLOCK_TAI. Select AUX area tracing Snapshot Mode. This option is valid only with an AUX area tracing event. Optionally, certain snapshot capturing parameters can be specified in a string that follows this option: - 'e': take one last snapshot on exit; guarantees that there is at least one + + - 'e': take one last snapshot on exit; guarantees that there is at least one snapshot in the output file; - <size>: if the PMU supports this, specify the desired snapshot size. + - <size>: if the PMU supports this, specify the desired snapshot size. In Snapshot Mode trace data is captured only when signal SIGUSR2 is received and on exit if the above 'e' option is given. @@ -547,14 +534,6 @@ PERF_RECORD_SWITCH_CPU_WIDE. In some cases (e.g. Intel PT, CoreSight or Arm SPE) switch events will be enabled automatically, which can be suppressed by by the option --no-switch-events. ---clang-path=PATH:: -Path to clang binary to use for compiling BPF scriptlets. -(enabled when BPF support is on) - ---clang-opt=OPTIONS:: -Options passed to clang when compiling BPF scriptlets. -(enabled when BPF support is on) - --vmlinux=PATH:: Specify vmlinux path which has debuginfo. (enabled when BPF prologue is on) @@ -572,8 +551,9 @@ providing implementation for Posix AIO API. --affinity=mode:: Set affinity mask of trace reading thread according to the policy defined by 'mode' value: - node - thread affinity mask is set to NUMA node cpu mask of the processed mmap buffer - cpu - thread affinity mask is set to cpu of the processed mmap buffer + + - node - thread affinity mask is set to NUMA node cpu mask of the processed mmap buffer + - cpu - thread affinity mask is set to cpu of the processed mmap buffer --mmap-flush=number:: @@ -625,16 +605,17 @@ Record timestamp boundary (time of first/last samples). --switch-output[=mode]:: Generate multiple perf.data files, timestamp prefixed, switching to a new one based on 'mode' value: - "signal" - when receiving a SIGUSR2 (default value) or - <size> - when reaching the size threshold, size is expected to - be a number with appended unit character - B/K/M/G - <time> - when reaching the time threshold, size is expected to - be a number with appended unit character - s/m/h/d - Note: the precision of the size threshold hugely depends - on your configuration - the number and size of your ring - buffers (-m). It is generally more precise for higher sizes - (like >5M), for lower values expect different sizes. + - "signal" - when receiving a SIGUSR2 (default value) or + - <size> - when reaching the size threshold, size is expected to + be a number with appended unit character - B/K/M/G + - <time> - when reaching the time threshold, size is expected to + be a number with appended unit character - s/m/h/d + + Note: the precision of the size threshold hugely depends + on your configuration - the number and size of your ring + buffers (-m). It is generally more precise for higher sizes + (like >5M), for lower values expect different sizes. A possible use case is to, given an external event, slice the perf.data file that gets then processed, possibly via a perf script, to decide if that @@ -680,11 +661,12 @@ choice in this option. For example, --synth=no would have MMAP events for kernel and modules. Available types are: - 'task' - synthesize FORK and COMM events for each task - 'mmap' - synthesize MMAP events for each process (implies 'task') - 'cgroup' - synthesize CGROUP events for each cgroup - 'all' - synthesize all events (default) - 'no' - do not synthesize any of the above events + + - 'task' - synthesize FORK and COMM events for each task + - 'mmap' - synthesize MMAP events for each process (implies 'task') + - 'cgroup' - synthesize CGROUP events for each cgroup + - 'all' - synthesize all events (default) + - 'no' - do not synthesize any of the above events --tail-synthesize:: Instead of collecting non-sample events (for example, fork, comm, mmap) at @@ -736,18 +718,19 @@ ctl-fifo / ack-fifo are opened and used as ctl-fd / ack-fd as follows. Listen on ctl-fd descriptor for command to control measurement. Available commands: - 'enable' : enable events - 'disable' : disable events - 'enable name' : enable event 'name' - 'disable name' : disable event 'name' - 'snapshot' : AUX area tracing snapshot). - 'stop' : stop perf record - 'ping' : ping - - 'evlist [-v|-g|-F] : display all events - -F Show just the sample frequency used for each event. - -v Show all fields. - -g Show event group information. + + - 'enable' : enable events + - 'disable' : disable events + - 'enable name' : enable event 'name' + - 'disable name' : disable event 'name' + - 'snapshot' : AUX area tracing snapshot). + - 'stop' : stop perf record + - 'ping' : ping + - 'evlist [-v|-g|-F] : display all events + + -F Show just the sample frequency used for each event. + -v Show all fields. + -g Show event group information. Measurements can be started with events disabled using --delay=-1 option. Optionally send control command completion ('ack\n') to ack-fd descriptor to synchronize with the @@ -808,10 +791,10 @@ the second monitors CPUs 1 and 5-7 with the affinity mask 5-7. <spec> value can also be a string meaning predefined parallel threads layout: - cpu - create new data streaming thread for every monitored cpu - core - create new thread to monitor CPUs grouped by a core - package - create new thread to monitor CPUs grouped by a package - numa - create new threed to monitor CPUs grouped by a NUMA domain + - cpu - create new data streaming thread for every monitored cpu + - core - create new thread to monitor CPUs grouped by a core + - package - create new thread to monitor CPUs grouped by a package + - numa - create new threed to monitor CPUs grouped by a NUMA domain Predefined layouts can be used on systems with large number of CPUs in order not to spawn multiple per-cpu streaming threads but still avoid LOST diff --git a/tools/perf/Documentation/perf.data-file-format.txt b/tools/perf/Documentation/perf.data-file-format.txt index 635ba043fd7d..010a4edcd384 100644 --- a/tools/perf/Documentation/perf.data-file-format.txt +++ b/tools/perf/Documentation/perf.data-file-format.txt @@ -43,7 +43,7 @@ struct perf_file_section { Flags section: -For each of the optional features a perf_file_section it placed after the data +For each of the optional features a perf_file_section is placed after the data section if the feature bit is set in the perf_header flags bitset. The respective perf_file_section points to the data of the additional header and defines its size. diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index c5db0de49868..d66b52407e19 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -246,6 +246,9 @@ ifeq ($(CC_NO_CLANG), 0) else CORE_CFLAGS += -O6 endif +else + CORE_CFLAGS += -g + CXXFLAGS += -g endif ifdef PARSER_DEBUG @@ -256,6 +259,11 @@ ifdef PARSER_DEBUG $(call detected_var,PARSER_DEBUG_FLEX) endif +ifdef LTO + CORE_CFLAGS += -flto + CXXFLAGS += -flto +endif + # Try different combinations to accommodate systems that only have # python[2][3]-config in weird combinations in the following order of # priority from lowest to highest: @@ -319,18 +327,14 @@ FEATURE_CHECK_LDFLAGS-disassembler-four-args = -lbfd -lopcodes -ldl FEATURE_CHECK_LDFLAGS-disassembler-init-styled = -lbfd -lopcodes -ldl CORE_CFLAGS += -fno-omit-frame-pointer -CORE_CFLAGS += -ggdb3 -CORE_CFLAGS += -funwind-tables CORE_CFLAGS += -Wall CORE_CFLAGS += -Wextra CORE_CFLAGS += -std=gnu11 -CXXFLAGS += -std=gnu++14 -fno-exceptions -fno-rtti +CXXFLAGS += -std=gnu++17 -fno-exceptions -fno-rtti CXXFLAGS += -Wall +CXXFLAGS += -Wextra CXXFLAGS += -fno-omit-frame-pointer -CXXFLAGS += -ggdb3 -CXXFLAGS += -funwind-tables -CXXFLAGS += -Wno-strict-aliasing HOSTCFLAGS += -Wall HOSTCFLAGS += -Wextra @@ -585,18 +589,6 @@ ifndef NO_LIBELF LIBBPF_STATIC := 1 endif endif - - ifndef NO_DWARF - ifdef PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET - CFLAGS += -DHAVE_BPF_PROLOGUE - $(call detected,CONFIG_BPF_PROLOGUE) - else - msg := $(warning BPF prologue is not supported by architecture $(SRCARCH), missing regs_query_register_offset()); - endif - else - msg := $(warning DWARF support is off, BPF prologue is disabled); - endif - endif # NO_LIBBPF endif # NO_LIBELF @@ -1123,37 +1115,6 @@ ifndef NO_JVMTI endif endif -USE_CXX = 0 -USE_CLANGLLVM = 0 -ifdef LIBCLANGLLVM - $(call feature_check,cxx) - ifneq ($(feature-cxx), 1) - msg := $(warning No g++ found, disable clang and llvm support. Please install g++) - else - $(call feature_check,llvm) - $(call feature_check,llvm-version) - ifneq ($(feature-llvm), 1) - msg := $(warning No suitable libLLVM found, disabling builtin clang and LLVM support. Please install llvm-dev(el) (>= 3.9.0)) - else - $(call feature_check,clang) - ifneq ($(feature-clang), 1) - msg := $(warning No suitable libclang found, disabling builtin clang and LLVM support. Please install libclang-dev(el) (>= 3.9.0)) - else - CFLAGS += -DHAVE_LIBCLANGLLVM_SUPPORT - CXXFLAGS += -DHAVE_LIBCLANGLLVM_SUPPORT -I$(shell $(LLVM_CONFIG) --includedir) - $(call detected,CONFIG_CXX) - $(call detected,CONFIG_CLANGLLVM) - USE_CXX = 1 - USE_LLVM = 1 - USE_CLANG = 1 - ifneq ($(feature-llvm-version),1) - msg := $(warning This version of LLVM is not tested. May cause build errors) - endif - endif - endif - endif -endif - ifndef NO_LIBPFM4 $(call feature_check,libpfm4) ifeq ($(feature-libpfm4), 1) diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 097316ef38e6..37af6df7b978 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -99,10 +99,6 @@ include ../scripts/utilities.mak # Define NO_JVMTI_CMLR (debug only) if you do not want to process CMLR # data for java source lines. # -# Define LIBCLANGLLVM if you DO want builtin clang and llvm support. -# When selected, pass LLVM_CONFIG=/path/to/llvm-config to `make' if -# llvm-config is not in $PATH. -# # Define CORESIGHT if you DO WANT support for CoreSight trace decoding. # # Define NO_AIO if you do not want support of Posix AIO based trace @@ -381,7 +377,7 @@ ifndef NO_JVMTI PROGRAMS += $(OUTPUT)$(LIBJVMTI) endif -DLFILTERS := dlfilter-test-api-v0.so dlfilter-show-cycles.so +DLFILTERS := dlfilter-test-api-v0.so dlfilter-test-api-v2.so dlfilter-show-cycles.so DLFILTERS := $(patsubst %,$(OUTPUT)dlfilters/%,$(DLFILTERS)) # what 'all' will build and 'install' will install, in perfexecdir @@ -425,22 +421,6 @@ endif EXTLIBS := $(call filter-out,$(EXCLUDE_EXTLIBS),$(EXTLIBS)) LIBS = -Wl,--whole-archive $(PERFLIBS) $(EXTRA_PERFLIBS) -Wl,--no-whole-archive -Wl,--start-group $(EXTLIBS) -Wl,--end-group -ifeq ($(USE_CLANG), 1) - CLANGLIBS_LIST = AST Basic CodeGen Driver Frontend Lex Tooling Edit Sema Analysis Parse Serialization - CLANGLIBS_NOEXT_LIST = $(foreach l,$(CLANGLIBS_LIST),$(shell $(LLVM_CONFIG) --libdir)/libclang$(l)) - LIBCLANG = $(foreach l,$(CLANGLIBS_NOEXT_LIST),$(wildcard $(l).a $(l).so)) - LIBS += -Wl,--start-group $(LIBCLANG) -Wl,--end-group -endif - -ifeq ($(USE_LLVM), 1) - LIBLLVM = $(shell $(LLVM_CONFIG) --libs all) $(shell $(LLVM_CONFIG) --system-libs) - LIBS += -L$(shell $(LLVM_CONFIG) --libdir) $(LIBLLVM) -endif - -ifeq ($(USE_CXX), 1) - LIBS += -lstdc++ -endif - export INSTALL SHELL_PATH ### Build rules @@ -978,11 +958,6 @@ ifndef NO_JVMTI endif $(call QUIET_INSTALL, libexec) \ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)' -ifndef NO_LIBBPF - $(call QUIET_INSTALL, bpf-examples) \ - $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'; \ - $(INSTALL) examples/bpf/*.c -m 644 -t '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf' -endif $(call QUIET_INSTALL, perf-archive) \ $(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)' $(call QUIET_INSTALL, perf-iostat) \ @@ -1057,6 +1032,8 @@ SKELETONS += $(SKEL_OUT)/bperf_leader.skel.h $(SKEL_OUT)/bperf_follower.skel.h SKELETONS += $(SKEL_OUT)/bperf_cgroup.skel.h $(SKEL_OUT)/func_latency.skel.h SKELETONS += $(SKEL_OUT)/off_cpu.skel.h $(SKEL_OUT)/lock_contention.skel.h SKELETONS += $(SKEL_OUT)/kwork_trace.skel.h $(SKEL_OUT)/sample_filter.skel.h +SKELETONS += $(SKEL_OUT)/bench_uprobe.skel.h +SKELETONS += $(SKEL_OUT)/augmented_raw_syscalls.skel.h $(SKEL_TMP_OUT) $(LIBAPI_OUTPUT) $(LIBBPF_OUTPUT) $(LIBPERF_OUTPUT) $(LIBSUBCMD_OUTPUT) $(LIBSYMBOL_OUTPUT): $(Q)$(MKDIR) -p $@ @@ -1079,10 +1056,15 @@ ifneq ($(CROSS_COMPILE),) CLANG_TARGET_ARCH = --target=$(notdir $(CROSS_COMPILE:%-=%)) endif +CLANG_OPTIONS = -Wall CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG),$(CLANG_TARGET_ARCH)) BPF_INCLUDE := -I$(SKEL_TMP_OUT)/.. -I$(LIBBPF_INCLUDE) $(CLANG_SYS_INCLUDES) TOOLS_UAPI_INCLUDE := -I$(srctree)/tools/include/uapi +ifneq ($(WERROR),0) + CLANG_OPTIONS += -Werror +endif + $(BPFTOOL): | $(SKEL_TMP_OUT) $(Q)CFLAGS= $(MAKE) -C ../bpf/bpftool \ OUTPUT=$(SKEL_TMP_OUT)/ bootstrap @@ -1124,7 +1106,7 @@ else endif $(SKEL_TMP_OUT)/%.bpf.o: util/bpf_skel/%.bpf.c $(LIBBPF) $(SKEL_OUT)/vmlinux.h | $(SKEL_TMP_OUT) - $(QUIET_CLANG)$(CLANG) -g -O2 --target=bpf -Wall -Werror $(BPF_INCLUDE) $(TOOLS_UAPI_INCLUDE) \ + $(QUIET_CLANG)$(CLANG) -g -O2 --target=bpf $(CLANG_OPTIONS) $(BPF_INCLUDE) $(TOOLS_UAPI_INCLUDE) \ -c $(filter util/bpf_skel/%.bpf.c,$^) -o $@ $(SKEL_OUT)/%.skel.h: $(SKEL_TMP_OUT)/%.bpf.o | $(BPFTOOL) diff --git a/tools/perf/arch/arm/include/perf_regs.h b/tools/perf/arch/arm/include/perf_regs.h index 99a06550e25d..75ce1c370114 100644 --- a/tools/perf/arch/arm/include/perf_regs.h +++ b/tools/perf/arch/arm/include/perf_regs.h @@ -12,7 +12,4 @@ void perf_regs_load(u64 *regs); #define PERF_REGS_MAX PERF_REG_ARM_MAX #define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_32 -#define PERF_REG_IP PERF_REG_ARM_PC -#define PERF_REG_SP PERF_REG_ARM_SP - #endif /* ARCH_PERF_REGS_H */ diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index 7c51fa182b51..b8d6a953fd74 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -79,9 +79,9 @@ static int cs_etm_validate_context_id(struct auxtrace_record *itr, int err; u32 val; u64 contextid = evsel->core.attr.config & - (perf_pmu__format_bits(&cs_etm_pmu->format, "contextid") | - perf_pmu__format_bits(&cs_etm_pmu->format, "contextid1") | - perf_pmu__format_bits(&cs_etm_pmu->format, "contextid2")); + (perf_pmu__format_bits(cs_etm_pmu, "contextid") | + perf_pmu__format_bits(cs_etm_pmu, "contextid1") | + perf_pmu__format_bits(cs_etm_pmu, "contextid2")); if (!contextid) return 0; @@ -106,7 +106,7 @@ static int cs_etm_validate_context_id(struct auxtrace_record *itr, } if (contextid & - perf_pmu__format_bits(&cs_etm_pmu->format, "contextid1")) { + perf_pmu__format_bits(cs_etm_pmu, "contextid1")) { /* * TRCIDR2.CIDSIZE, bit [9-5], indicates whether contextID * tracing is supported: @@ -122,7 +122,7 @@ static int cs_etm_validate_context_id(struct auxtrace_record *itr, } if (contextid & - perf_pmu__format_bits(&cs_etm_pmu->format, "contextid2")) { + perf_pmu__format_bits(cs_etm_pmu, "contextid2")) { /* * TRCIDR2.VMIDOPT[30:29] != 0 and * TRCIDR2.VMIDSIZE[14:10] == 0b00100 (32bit virtual contextid) @@ -151,7 +151,7 @@ static int cs_etm_validate_timestamp(struct auxtrace_record *itr, u32 val; if (!(evsel->core.attr.config & - perf_pmu__format_bits(&cs_etm_pmu->format, "timestamp"))) + perf_pmu__format_bits(cs_etm_pmu, "timestamp"))) return 0; if (!cs_etm_is_etmv4(itr, cpu)) { diff --git a/tools/perf/arch/arm/util/perf_regs.c b/tools/perf/arch/arm/util/perf_regs.c index 2833e101a7c6..2c56e8b56ddf 100644 --- a/tools/perf/arch/arm/util/perf_regs.c +++ b/tools/perf/arch/arm/util/perf_regs.c @@ -1,6 +1,17 @@ // SPDX-License-Identifier: GPL-2.0 +#include "perf_regs.h" #include "../../../util/perf_regs.h" const struct sample_reg sample_reg_masks[] = { SMPL_REG_END }; + +uint64_t arch__intr_reg_mask(void) +{ + return PERF_REGS_MASK; +} + +uint64_t arch__user_reg_mask(void) +{ + return PERF_REGS_MASK; +} diff --git a/tools/perf/arch/arm/util/unwind-libdw.c b/tools/perf/arch/arm/util/unwind-libdw.c index 1834a0cd9ce3..4e02cef461e3 100644 --- a/tools/perf/arch/arm/util/unwind-libdw.c +++ b/tools/perf/arch/arm/util/unwind-libdw.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <elfutils/libdwfl.h> +#include "perf_regs.h" #include "../../../util/unwind-libdw.h" #include "../../../util/perf_regs.h" #include "../../../util/sample.h" diff --git a/tools/perf/arch/arm64/include/arch-tests.h b/tools/perf/arch/arm64/include/arch-tests.h index 452b3d904521..474d7cf5afbd 100644 --- a/tools/perf/arch/arm64/include/arch-tests.h +++ b/tools/perf/arch/arm64/include/arch-tests.h @@ -2,6 +2,9 @@ #ifndef ARCH_TESTS_H #define ARCH_TESTS_H +struct test_suite; + +int test__cpuid_match(struct test_suite *test, int subtest); extern struct test_suite *arch_tests[]; #endif diff --git a/tools/perf/arch/arm64/include/perf_regs.h b/tools/perf/arch/arm64/include/perf_regs.h index 35a3cc775b39..58639ee9f7ea 100644 --- a/tools/perf/arch/arm64/include/perf_regs.h +++ b/tools/perf/arch/arm64/include/perf_regs.h @@ -14,7 +14,4 @@ void perf_regs_load(u64 *regs); #define PERF_REGS_MAX PERF_REG_ARM64_MAX #define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_64 -#define PERF_REG_IP PERF_REG_ARM64_PC -#define PERF_REG_SP PERF_REG_ARM64_SP - #endif /* ARCH_PERF_REGS_H */ diff --git a/tools/perf/arch/arm64/tests/Build b/tools/perf/arch/arm64/tests/Build index a61c06bdb757..e337c09e7f56 100644 --- a/tools/perf/arch/arm64/tests/Build +++ b/tools/perf/arch/arm64/tests/Build @@ -2,3 +2,4 @@ perf-y += regs_load.o perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o perf-y += arch-tests.o +perf-y += cpuid-match.o diff --git a/tools/perf/arch/arm64/tests/arch-tests.c b/tools/perf/arch/arm64/tests/arch-tests.c index ad16b4f8f63e..74932e72c727 100644 --- a/tools/perf/arch/arm64/tests/arch-tests.c +++ b/tools/perf/arch/arm64/tests/arch-tests.c @@ -3,9 +3,13 @@ #include "tests/tests.h" #include "arch-tests.h" + +DEFINE_SUITE("arm64 CPUID matching", cpuid_match); + struct test_suite *arch_tests[] = { #ifdef HAVE_DWARF_UNWIND_SUPPORT &suite__dwarf_unwind, #endif + &suite__cpuid_match, NULL, }; diff --git a/tools/perf/arch/arm64/tests/cpuid-match.c b/tools/perf/arch/arm64/tests/cpuid-match.c new file mode 100644 index 000000000000..e8e3947cca18 --- /dev/null +++ b/tools/perf/arch/arm64/tests/cpuid-match.c @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/compiler.h> + +#include "arch-tests.h" +#include "tests/tests.h" +#include "util/header.h" + +int test__cpuid_match(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) +{ + /* midr with no leading zeros matches */ + if (strcmp_cpuid_str("0x410fd0c0", "0x00000000410fd0c0")) + return -1; + /* Upper case matches */ + if (strcmp_cpuid_str("0x410fd0c0", "0x00000000410FD0C0")) + return -1; + /* r0p0 = r0p0 matches */ + if (strcmp_cpuid_str("0x00000000410fd480", "0x00000000410fd480")) + return -1; + /* r0p1 > r0p0 matches */ + if (strcmp_cpuid_str("0x00000000410fd480", "0x00000000410fd481")) + return -1; + /* r1p0 > r0p0 matches*/ + if (strcmp_cpuid_str("0x00000000410fd480", "0x00000000411fd480")) + return -1; + /* r0p0 < r0p1 doesn't match */ + if (!strcmp_cpuid_str("0x00000000410fd481", "0x00000000410fd480")) + return -1; + /* r0p0 < r1p0 doesn't match */ + if (!strcmp_cpuid_str("0x00000000411fd480", "0x00000000410fd480")) + return -1; + /* Different CPU doesn't match */ + if (!strcmp_cpuid_str("0x00000000410fd4c0", "0x00000000430f0af0")) + return -1; + + return 0; +} diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c index 3b1676ff03f9..9cc3d6dcb849 100644 --- a/tools/perf/arch/arm64/util/arm-spe.c +++ b/tools/perf/arch/arm64/util/arm-spe.c @@ -230,7 +230,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, * inform that the resulting output's SPE samples contain physical addresses * where applicable. */ - bit = perf_pmu__format_bits(&arm_spe_pmu->format, "pa_enable"); + bit = perf_pmu__format_bits(arm_spe_pmu, "pa_enable"); if (arm_spe_evsel->core.attr.config & bit) evsel__set_sample_bit(arm_spe_evsel, PHYS_ADDR); diff --git a/tools/perf/arch/arm64/util/header.c b/tools/perf/arch/arm64/util/header.c index 80b9f6287fe2..a2eef9ec5491 100644 --- a/tools/perf/arch/arm64/util/header.c +++ b/tools/perf/arch/arm64/util/header.c @@ -1,3 +1,6 @@ +#include <linux/kernel.h> +#include <linux/bits.h> +#include <linux/bitfield.h> #include <stdio.h> #include <stdlib.h> #include <perf/cpumap.h> @@ -10,15 +13,14 @@ #define MIDR "/regs/identification/midr_el1" #define MIDR_SIZE 19 -#define MIDR_REVISION_MASK 0xf -#define MIDR_VARIANT_SHIFT 20 -#define MIDR_VARIANT_MASK (0xf << MIDR_VARIANT_SHIFT) +#define MIDR_REVISION_MASK GENMASK(3, 0) +#define MIDR_VARIANT_MASK GENMASK(23, 20) static int _get_cpuid(char *buf, size_t sz, struct perf_cpu_map *cpus) { const char *sysfs = sysfs__mountpoint(); - u64 midr = 0; int cpu; + int ret = EINVAL; if (!sysfs || sz < MIDR_SIZE) return EINVAL; @@ -44,22 +46,13 @@ static int _get_cpuid(char *buf, size_t sz, struct perf_cpu_map *cpus) } fclose(file); - /* Ignore/clear Variant[23:20] and - * Revision[3:0] of MIDR - */ - midr = strtoul(buf, NULL, 16); - midr &= (~(MIDR_VARIANT_MASK | MIDR_REVISION_MASK)); - scnprintf(buf, MIDR_SIZE, "0x%016lx", midr); /* got midr break loop */ + ret = 0; break; } perf_cpu_map__put(cpus); - - if (!midr) - return EINVAL; - - return 0; + return ret; } int get_cpuid(char *buf, size_t sz) @@ -99,3 +92,47 @@ char *get_cpuid_str(struct perf_pmu *pmu) return buf; } + +/* + * Return 0 if idstr is a higher or equal to version of the same part as + * mapcpuid. Therefore, if mapcpuid has 0 for revision and variant then any + * version of idstr will match as long as it's the same CPU type. + * + * Return 1 if the CPU type is different or the version of idstr is lower. + */ +int strcmp_cpuid_str(const char *mapcpuid, const char *idstr) +{ + u64 map_id = strtoull(mapcpuid, NULL, 16); + char map_id_variant = FIELD_GET(MIDR_VARIANT_MASK, map_id); + char map_id_revision = FIELD_GET(MIDR_REVISION_MASK, map_id); + u64 id = strtoull(idstr, NULL, 16); + char id_variant = FIELD_GET(MIDR_VARIANT_MASK, id); + char id_revision = FIELD_GET(MIDR_REVISION_MASK, id); + u64 id_fields = ~(MIDR_VARIANT_MASK | MIDR_REVISION_MASK); + + /* Compare without version first */ + if ((map_id & id_fields) != (id & id_fields)) + return 1; + + /* + * ID matches, now compare version. + * + * Arm revisions (like r0p0) are compared here like two digit semver + * values eg. 1.3 < 2.0 < 2.1 < 2.2. + * + * r = high value = 'Variant' field in MIDR + * p = low value = 'Revision' field in MIDR + * + */ + if (id_variant > map_id_variant) + return 0; + + if (id_variant == map_id_variant && id_revision >= map_id_revision) + return 0; + + /* + * variant is less than mapfile variant or variants are the same but + * the revision doesn't match. Return no match. + */ + return 1; +} diff --git a/tools/perf/arch/arm64/util/machine.c b/tools/perf/arch/arm64/util/machine.c index 235a0a1e1ec7..ba1144366e85 100644 --- a/tools/perf/arch/arm64/util/machine.c +++ b/tools/perf/arch/arm64/util/machine.c @@ -6,6 +6,7 @@ #include "debug.h" #include "symbol.h" #include "callchain.h" +#include "perf_regs.h" #include "record.h" #include "util/perf_regs.h" diff --git a/tools/perf/arch/arm64/util/mem-events.c b/tools/perf/arch/arm64/util/mem-events.c index df817d1f9f3e..3bcc5c7035c2 100644 --- a/tools/perf/arch/arm64/util/mem-events.c +++ b/tools/perf/arch/arm64/util/mem-events.c @@ -20,7 +20,7 @@ struct perf_mem_event *perf_mem_events__ptr(int i) return &perf_mem_events[i]; } -char *perf_mem_events__name(int i, char *pmu_name __maybe_unused) +const char *perf_mem_events__name(int i, const char *pmu_name __maybe_unused) { struct perf_mem_event *e = perf_mem_events__ptr(i); diff --git a/tools/perf/arch/arm64/util/perf_regs.c b/tools/perf/arch/arm64/util/perf_regs.c index 006692c9b040..1b79d8eab22f 100644 --- a/tools/perf/arch/arm64/util/perf_regs.c +++ b/tools/perf/arch/arm64/util/perf_regs.c @@ -6,6 +6,7 @@ #include <linux/kernel.h> #include <linux/zalloc.h> +#include "perf_regs.h" #include "../../../perf-sys.h" #include "../../../util/debug.h" #include "../../../util/event.h" @@ -139,6 +140,11 @@ int arch_sdt_arg_parse_op(char *old_op, char **new_op) return SDT_ARG_VALID; } +uint64_t arch__intr_reg_mask(void) +{ + return PERF_REGS_MASK; +} + uint64_t arch__user_reg_mask(void) { struct perf_event_attr attr = { diff --git a/tools/perf/arch/arm64/util/pmu.c b/tools/perf/arch/arm64/util/pmu.c index 512a8f13c4de..615084eb88d8 100644 --- a/tools/perf/arch/arm64/util/pmu.c +++ b/tools/perf/arch/arm64/util/pmu.c @@ -2,28 +2,12 @@ #include <internal/cpumap.h> #include "../../../util/cpumap.h" +#include "../../../util/header.h" #include "../../../util/pmu.h" #include "../../../util/pmus.h" #include <api/fs/fs.h> #include <math.h> -static struct perf_pmu *pmu__find_core_pmu(void) -{ - struct perf_pmu *pmu = NULL; - - while ((pmu = perf_pmus__scan_core(pmu))) { - /* - * The cpumap should cover all CPUs. Otherwise, some CPUs may - * not support some events or have different event IDs. - */ - if (RC_CHK_ACCESS(pmu->cpus)->nr != cpu__max_cpu().cpu) - return NULL; - - return pmu; - } - return NULL; -} - const struct pmu_metrics_table *pmu_metrics_table__find(void) { struct perf_pmu *pmu = pmu__find_core_pmu(); diff --git a/tools/perf/arch/arm64/util/unwind-libdw.c b/tools/perf/arch/arm64/util/unwind-libdw.c index 09385081bb03..e056d50ab42e 100644 --- a/tools/perf/arch/arm64/util/unwind-libdw.c +++ b/tools/perf/arch/arm64/util/unwind-libdw.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <elfutils/libdwfl.h> +#include "perf_regs.h" #include "../../../util/unwind-libdw.h" #include "../../../util/perf_regs.h" #include "../../../util/sample.h" diff --git a/tools/perf/arch/csky/include/perf_regs.h b/tools/perf/arch/csky/include/perf_regs.h index 1afcc0e916c2..076c7746c8a2 100644 --- a/tools/perf/arch/csky/include/perf_regs.h +++ b/tools/perf/arch/csky/include/perf_regs.h @@ -12,7 +12,4 @@ #define PERF_REGS_MAX PERF_REG_CSKY_MAX #define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_32 -#define PERF_REG_IP PERF_REG_CSKY_PC -#define PERF_REG_SP PERF_REG_CSKY_SP - #endif /* ARCH_PERF_REGS_H */ diff --git a/tools/perf/arch/csky/util/perf_regs.c b/tools/perf/arch/csky/util/perf_regs.c index 2864e2e3776d..c0877c264d49 100644 --- a/tools/perf/arch/csky/util/perf_regs.c +++ b/tools/perf/arch/csky/util/perf_regs.c @@ -1,6 +1,17 @@ // SPDX-License-Identifier: GPL-2.0 +#include "perf_regs.h" #include "../../util/perf_regs.h" const struct sample_reg sample_reg_masks[] = { SMPL_REG_END }; + +uint64_t arch__intr_reg_mask(void) +{ + return PERF_REGS_MASK; +} + +uint64_t arch__user_reg_mask(void) +{ + return PERF_REGS_MASK; +} diff --git a/tools/perf/arch/csky/util/unwind-libdw.c b/tools/perf/arch/csky/util/unwind-libdw.c index 4bb4a06776e4..79df4374ab18 100644 --- a/tools/perf/arch/csky/util/unwind-libdw.c +++ b/tools/perf/arch/csky/util/unwind-libdw.c @@ -2,6 +2,7 @@ // Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd. #include <elfutils/libdwfl.h> +#include "perf_regs.h" #include "../../util/unwind-libdw.h" #include "../../util/perf_regs.h" #include "../../util/event.h" diff --git a/tools/perf/arch/loongarch/include/perf_regs.h b/tools/perf/arch/loongarch/include/perf_regs.h index 7833c7dbd38d..45c799fa5330 100644 --- a/tools/perf/arch/loongarch/include/perf_regs.h +++ b/tools/perf/arch/loongarch/include/perf_regs.h @@ -7,8 +7,6 @@ #include <asm/perf_regs.h> #define PERF_REGS_MAX PERF_REG_LOONGARCH_MAX -#define PERF_REG_IP PERF_REG_LOONGARCH_PC -#define PERF_REG_SP PERF_REG_LOONGARCH_R3 #define PERF_REGS_MASK ((1ULL << PERF_REG_LOONGARCH_MAX) - 1) diff --git a/tools/perf/arch/loongarch/util/perf_regs.c b/tools/perf/arch/loongarch/util/perf_regs.c index 2833e101a7c6..2c56e8b56ddf 100644 --- a/tools/perf/arch/loongarch/util/perf_regs.c +++ b/tools/perf/arch/loongarch/util/perf_regs.c @@ -1,6 +1,17 @@ // SPDX-License-Identifier: GPL-2.0 +#include "perf_regs.h" #include "../../../util/perf_regs.h" const struct sample_reg sample_reg_masks[] = { SMPL_REG_END }; + +uint64_t arch__intr_reg_mask(void) +{ + return PERF_REGS_MASK; +} + +uint64_t arch__user_reg_mask(void) +{ + return PERF_REGS_MASK; +} diff --git a/tools/perf/arch/loongarch/util/unwind-libdw.c b/tools/perf/arch/loongarch/util/unwind-libdw.c index a9415385230a..7b3b9a4b21f8 100644 --- a/tools/perf/arch/loongarch/util/unwind-libdw.c +++ b/tools/perf/arch/loongarch/util/unwind-libdw.c @@ -2,6 +2,7 @@ /* Copyright (C) 2020-2023 Loongson Technology Corporation Limited */ #include <elfutils/libdwfl.h> +#include "perf_regs.h" #include "../../util/unwind-libdw.h" #include "../../util/perf_regs.h" #include "../../util/sample.h" diff --git a/tools/perf/arch/mips/include/perf_regs.h b/tools/perf/arch/mips/include/perf_regs.h index b8cd8bbb37ba..7082e91e0ed1 100644 --- a/tools/perf/arch/mips/include/perf_regs.h +++ b/tools/perf/arch/mips/include/perf_regs.h @@ -7,8 +7,6 @@ #include <asm/perf_regs.h> #define PERF_REGS_MAX PERF_REG_MIPS_MAX -#define PERF_REG_IP PERF_REG_MIPS_PC -#define PERF_REG_SP PERF_REG_MIPS_R29 #define PERF_REGS_MASK ((1ULL << PERF_REG_MIPS_MAX) - 1) diff --git a/tools/perf/arch/mips/util/perf_regs.c b/tools/perf/arch/mips/util/perf_regs.c index 2864e2e3776d..c0877c264d49 100644 --- a/tools/perf/arch/mips/util/perf_regs.c +++ b/tools/perf/arch/mips/util/perf_regs.c @@ -1,6 +1,17 @@ // SPDX-License-Identifier: GPL-2.0 +#include "perf_regs.h" #include "../../util/perf_regs.h" const struct sample_reg sample_reg_masks[] = { SMPL_REG_END }; + +uint64_t arch__intr_reg_mask(void) +{ + return PERF_REGS_MASK; +} + +uint64_t arch__user_reg_mask(void) +{ + return PERF_REGS_MASK; +} diff --git a/tools/perf/arch/powerpc/include/perf_regs.h b/tools/perf/arch/powerpc/include/perf_regs.h index 9bb17c3f370b..1c66f6ba6773 100644 --- a/tools/perf/arch/powerpc/include/perf_regs.h +++ b/tools/perf/arch/powerpc/include/perf_regs.h @@ -16,7 +16,4 @@ void perf_regs_load(u64 *regs); #define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_32 #endif -#define PERF_REG_IP PERF_REG_POWERPC_NIP -#define PERF_REG_SP PERF_REG_POWERPC_R1 - #endif /* ARCH_PERF_REGS_H */ diff --git a/tools/perf/arch/powerpc/util/mem-events.c b/tools/perf/arch/powerpc/util/mem-events.c index 4120fafe0be4..78b986e5268d 100644 --- a/tools/perf/arch/powerpc/util/mem-events.c +++ b/tools/perf/arch/powerpc/util/mem-events.c @@ -3,10 +3,10 @@ #include "mem-events.h" /* PowerPC does not support 'ldlat' parameter. */ -char *perf_mem_events__name(int i, char *pmu_name __maybe_unused) +const char *perf_mem_events__name(int i, const char *pmu_name __maybe_unused) { if (i == PERF_MEM_EVENTS__LOAD) - return (char *) "cpu/mem-loads/"; + return "cpu/mem-loads/"; - return (char *) "cpu/mem-stores/"; + return "cpu/mem-stores/"; } diff --git a/tools/perf/arch/powerpc/util/perf_regs.c b/tools/perf/arch/powerpc/util/perf_regs.c index 8d07a78e742a..b38aa056eea0 100644 --- a/tools/perf/arch/powerpc/util/perf_regs.c +++ b/tools/perf/arch/powerpc/util/perf_regs.c @@ -4,6 +4,7 @@ #include <regex.h> #include <linux/zalloc.h> +#include "perf_regs.h" #include "../../../util/perf_regs.h" #include "../../../util/debug.h" #include "../../../util/event.h" @@ -226,3 +227,8 @@ uint64_t arch__intr_reg_mask(void) } return mask; } + +uint64_t arch__user_reg_mask(void) +{ + return PERF_REGS_MASK; +} diff --git a/tools/perf/arch/powerpc/util/unwind-libdw.c b/tools/perf/arch/powerpc/util/unwind-libdw.c index e616642c754c..e9a5a8bb67d9 100644 --- a/tools/perf/arch/powerpc/util/unwind-libdw.c +++ b/tools/perf/arch/powerpc/util/unwind-libdw.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <elfutils/libdwfl.h> #include <linux/kernel.h> +#include "perf_regs.h" #include "../../../util/unwind-libdw.h" #include "../../../util/perf_regs.h" #include "../../../util/sample.h" diff --git a/tools/perf/arch/riscv/include/perf_regs.h b/tools/perf/arch/riscv/include/perf_regs.h index 6944bf0de53e..d482edb413e5 100644 --- a/tools/perf/arch/riscv/include/perf_regs.h +++ b/tools/perf/arch/riscv/include/perf_regs.h @@ -16,7 +16,4 @@ #define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_32 #endif -#define PERF_REG_IP PERF_REG_RISCV_PC -#define PERF_REG_SP PERF_REG_RISCV_SP - #endif /* ARCH_PERF_REGS_H */ diff --git a/tools/perf/arch/riscv/util/perf_regs.c b/tools/perf/arch/riscv/util/perf_regs.c index 2864e2e3776d..c0877c264d49 100644 --- a/tools/perf/arch/riscv/util/perf_regs.c +++ b/tools/perf/arch/riscv/util/perf_regs.c @@ -1,6 +1,17 @@ // SPDX-License-Identifier: GPL-2.0 +#include "perf_regs.h" #include "../../util/perf_regs.h" const struct sample_reg sample_reg_masks[] = { SMPL_REG_END }; + +uint64_t arch__intr_reg_mask(void) +{ + return PERF_REGS_MASK; +} + +uint64_t arch__user_reg_mask(void) +{ + return PERF_REGS_MASK; +} diff --git a/tools/perf/arch/riscv/util/unwind-libdw.c b/tools/perf/arch/riscv/util/unwind-libdw.c index 54a198714eb8..5c98010d8b59 100644 --- a/tools/perf/arch/riscv/util/unwind-libdw.c +++ b/tools/perf/arch/riscv/util/unwind-libdw.c @@ -2,6 +2,7 @@ /* Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd. */ #include <elfutils/libdwfl.h> +#include "perf_regs.h" #include "../../util/unwind-libdw.h" #include "../../util/perf_regs.h" #include "../../util/sample.h" diff --git a/tools/perf/arch/s390/include/perf_regs.h b/tools/perf/arch/s390/include/perf_regs.h index 52fcc0891da6..130dfad2b96a 100644 --- a/tools/perf/arch/s390/include/perf_regs.h +++ b/tools/perf/arch/s390/include/perf_regs.h @@ -11,7 +11,4 @@ void perf_regs_load(u64 *regs); #define PERF_REGS_MAX PERF_REG_S390_MAX #define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_64 -#define PERF_REG_IP PERF_REG_S390_PC -#define PERF_REG_SP PERF_REG_S390_R15 - #endif /* ARCH_PERF_REGS_H */ diff --git a/tools/perf/arch/s390/util/perf_regs.c b/tools/perf/arch/s390/util/perf_regs.c index 2864e2e3776d..c0877c264d49 100644 --- a/tools/perf/arch/s390/util/perf_regs.c +++ b/tools/perf/arch/s390/util/perf_regs.c @@ -1,6 +1,17 @@ // SPDX-License-Identifier: GPL-2.0 +#include "perf_regs.h" #include "../../util/perf_regs.h" const struct sample_reg sample_reg_masks[] = { SMPL_REG_END }; + +uint64_t arch__intr_reg_mask(void) +{ + return PERF_REGS_MASK; +} + +uint64_t arch__user_reg_mask(void) +{ + return PERF_REGS_MASK; +} diff --git a/tools/perf/arch/s390/util/unwind-libdw.c b/tools/perf/arch/s390/util/unwind-libdw.c index 7d92452d5287..f50fb6dbb35c 100644 --- a/tools/perf/arch/s390/util/unwind-libdw.c +++ b/tools/perf/arch/s390/util/unwind-libdw.c @@ -5,6 +5,7 @@ #include "../../util/event.h" #include "../../util/sample.h" #include "dwarf-regs-table.h" +#include "perf_regs.h" bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg) diff --git a/tools/perf/arch/x86/entry/syscalls/syscalltbl.sh b/tools/perf/arch/x86/entry/syscalls/syscalltbl.sh index fa526a993845..59d7914ed6bb 100755 --- a/tools/perf/arch/x86/entry/syscalls/syscalltbl.sh +++ b/tools/perf/arch/x86/entry/syscalls/syscalltbl.sh @@ -24,7 +24,7 @@ sorted_table=$(mktemp /tmp/syscalltbl.XXXXXX) grep '^[0-9]' "$in" | sort -n > $sorted_table max_nr=0 -while read nr abi name entry compat; do +while read nr _abi name entry _compat; do if [ $nr -ge 512 ] ; then # discard compat sycalls break fi diff --git a/tools/perf/arch/x86/include/perf_regs.h b/tools/perf/arch/x86/include/perf_regs.h index 16e23b722042..f209ce2c1dd9 100644 --- a/tools/perf/arch/x86/include/perf_regs.h +++ b/tools/perf/arch/x86/include/perf_regs.h @@ -20,7 +20,5 @@ void perf_regs_load(u64 *regs); #define PERF_REGS_MASK (((1ULL << PERF_REG_X86_64_MAX) - 1) & ~REG_NOSUPPORT) #define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_64 #endif -#define PERF_REG_IP PERF_REG_X86_IP -#define PERF_REG_SP PERF_REG_X86_SP #endif /* ARCH_PERF_REGS_H */ diff --git a/tools/perf/arch/x86/util/evlist.c b/tools/perf/arch/x86/util/evlist.c index cbd582182932..b1ce0c52d88d 100644 --- a/tools/perf/arch/x86/util/evlist.c +++ b/tools/perf/arch/x86/util/evlist.c @@ -75,11 +75,12 @@ int arch_evlist__add_default_attrs(struct evlist *evlist, int arch_evlist__cmp(const struct evsel *lhs, const struct evsel *rhs) { - if (topdown_sys_has_perf_metrics() && evsel__sys_has_perf_metrics(lhs)) { + if (topdown_sys_has_perf_metrics() && + (arch_evsel__must_be_in_group(lhs) || arch_evsel__must_be_in_group(rhs))) { /* Ensure the topdown slots comes first. */ - if (strcasestr(lhs->name, "slots")) + if (strcasestr(lhs->name, "slots") && !strcasestr(lhs->name, "uops_retired.slots")) return -1; - if (strcasestr(rhs->name, "slots")) + if (strcasestr(rhs->name, "slots") && !strcasestr(rhs->name, "uops_retired.slots")) return 1; /* Followed by topdown events. */ if (strcasestr(lhs->name, "topdown") && !strcasestr(rhs->name, "topdown")) diff --git a/tools/perf/arch/x86/util/evsel.c b/tools/perf/arch/x86/util/evsel.c index 81d22657922a..090d0f371891 100644 --- a/tools/perf/arch/x86/util/evsel.c +++ b/tools/perf/arch/x86/util/evsel.c @@ -40,12 +40,11 @@ bool evsel__sys_has_perf_metrics(const struct evsel *evsel) bool arch_evsel__must_be_in_group(const struct evsel *evsel) { - if (!evsel__sys_has_perf_metrics(evsel)) + if (!evsel__sys_has_perf_metrics(evsel) || !evsel->name || + strcasestr(evsel->name, "uops_retired.slots")) return false; - return evsel->name && - (strcasestr(evsel->name, "slots") || - strcasestr(evsel->name, "topdown")); + return strcasestr(evsel->name, "topdown") || strcasestr(evsel->name, "slots"); } int arch_evsel__hw_name(struct evsel *evsel, char *bf, size_t size) diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c index 74b70fd379df..31807791589e 100644 --- a/tools/perf/arch/x86/util/intel-pt.c +++ b/tools/perf/arch/x86/util/intel-pt.c @@ -60,8 +60,7 @@ struct intel_pt_recording { size_t priv_size; }; -static int intel_pt_parse_terms_with_default(const char *pmu_name, - struct list_head *formats, +static int intel_pt_parse_terms_with_default(struct perf_pmu *pmu, const char *str, u64 *config) { @@ -75,13 +74,12 @@ static int intel_pt_parse_terms_with_default(const char *pmu_name, INIT_LIST_HEAD(terms); - err = parse_events_terms(terms, str); + err = parse_events_terms(terms, str, /*input=*/ NULL); if (err) goto out_free; attr.config = *config; - err = perf_pmu__config_terms(pmu_name, formats, &attr, terms, true, - NULL); + err = perf_pmu__config_terms(pmu, &attr, terms, /*zero=*/true, /*err=*/NULL); if (err) goto out_free; @@ -91,12 +89,10 @@ out_free: return err; } -static int intel_pt_parse_terms(const char *pmu_name, struct list_head *formats, - const char *str, u64 *config) +static int intel_pt_parse_terms(struct perf_pmu *pmu, const char *str, u64 *config) { *config = 0; - return intel_pt_parse_terms_with_default(pmu_name, formats, str, - config); + return intel_pt_parse_terms_with_default(pmu, str, config); } static u64 intel_pt_masked_bits(u64 mask, u64 bits) @@ -126,7 +122,7 @@ static int intel_pt_read_config(struct perf_pmu *intel_pt_pmu, const char *str, *res = 0; - mask = perf_pmu__format_bits(&intel_pt_pmu->format, str); + mask = perf_pmu__format_bits(intel_pt_pmu, str); if (!mask) return -EINVAL; @@ -236,8 +232,7 @@ static u64 intel_pt_default_config(struct perf_pmu *intel_pt_pmu) pr_debug2("%s default config: %s\n", intel_pt_pmu->name, buf); - intel_pt_parse_terms(intel_pt_pmu->name, &intel_pt_pmu->format, buf, - &config); + intel_pt_parse_terms(intel_pt_pmu, buf, &config); close(dirfd); return config; @@ -348,16 +343,11 @@ static int intel_pt_info_fill(struct auxtrace_record *itr, if (priv_size != ptr->priv_size) return -EINVAL; - intel_pt_parse_terms(intel_pt_pmu->name, &intel_pt_pmu->format, - "tsc", &tsc_bit); - intel_pt_parse_terms(intel_pt_pmu->name, &intel_pt_pmu->format, - "noretcomp", &noretcomp_bit); - intel_pt_parse_terms(intel_pt_pmu->name, &intel_pt_pmu->format, - "mtc", &mtc_bit); - mtc_freq_bits = perf_pmu__format_bits(&intel_pt_pmu->format, - "mtc_period"); - intel_pt_parse_terms(intel_pt_pmu->name, &intel_pt_pmu->format, - "cyc", &cyc_bit); + intel_pt_parse_terms(intel_pt_pmu, "tsc", &tsc_bit); + intel_pt_parse_terms(intel_pt_pmu, "noretcomp", &noretcomp_bit); + intel_pt_parse_terms(intel_pt_pmu, "mtc", &mtc_bit); + mtc_freq_bits = perf_pmu__format_bits(intel_pt_pmu, "mtc_period"); + intel_pt_parse_terms(intel_pt_pmu, "cyc", &cyc_bit); intel_pt_tsc_ctc_ratio(&tsc_ctc_ratio_n, &tsc_ctc_ratio_d); @@ -511,7 +501,7 @@ static int intel_pt_val_config_term(struct perf_pmu *intel_pt_pmu, int dirfd, valid |= 1; - bits = perf_pmu__format_bits(&intel_pt_pmu->format, name); + bits = perf_pmu__format_bits(intel_pt_pmu, name); config &= bits; @@ -781,8 +771,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, intel_pt_evsel->core.attr.aux_watermark = aux_watermark; } - intel_pt_parse_terms(intel_pt_pmu->name, &intel_pt_pmu->format, - "tsc", &tsc_bit); + intel_pt_parse_terms(intel_pt_pmu, "tsc", &tsc_bit); if (opts->full_auxtrace && (intel_pt_evsel->core.attr.config & tsc_bit)) have_timing_info = true; diff --git a/tools/perf/arch/x86/util/mem-events.c b/tools/perf/arch/x86/util/mem-events.c index a8a782bcb121..191b372f9a2d 100644 --- a/tools/perf/arch/x86/util/mem-events.c +++ b/tools/perf/arch/x86/util/mem-events.c @@ -52,7 +52,7 @@ bool is_mem_loads_aux_event(struct evsel *leader) return leader->core.attr.config == MEM_LOADS_AUX; } -char *perf_mem_events__name(int i, char *pmu_name) +const char *perf_mem_events__name(int i, const char *pmu_name) { struct perf_mem_event *e = perf_mem_events__ptr(i); @@ -65,7 +65,7 @@ char *perf_mem_events__name(int i, char *pmu_name) if (!pmu_name) { mem_loads_name__init = true; - pmu_name = (char *)"cpu"; + pmu_name = "cpu"; } if (perf_pmus__have_event(pmu_name, "mem-loads-aux")) { @@ -82,12 +82,12 @@ char *perf_mem_events__name(int i, char *pmu_name) if (i == PERF_MEM_EVENTS__STORE) { if (!pmu_name) - pmu_name = (char *)"cpu"; + pmu_name = "cpu"; scnprintf(mem_stores_name, sizeof(mem_stores_name), e->name, pmu_name); return mem_stores_name; } - return (char *)e->name; + return e->name; } diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c index 8ad4112ad10c..b813502a2727 100644 --- a/tools/perf/arch/x86/util/perf_regs.c +++ b/tools/perf/arch/x86/util/perf_regs.c @@ -5,6 +5,7 @@ #include <linux/kernel.h> #include <linux/zalloc.h> +#include "perf_regs.h" #include "../../../perf-sys.h" #include "../../../util/perf_regs.h" #include "../../../util/debug.h" @@ -317,3 +318,8 @@ uint64_t arch__intr_reg_mask(void) return PERF_REGS_MASK; } + +uint64_t arch__user_reg_mask(void) +{ + return PERF_REGS_MASK; +} diff --git a/tools/perf/arch/x86/util/pmu.c b/tools/perf/arch/x86/util/pmu.c index 65d8cdff4d5f..f428cffb0378 100644 --- a/tools/perf/arch/x86/util/pmu.c +++ b/tools/perf/arch/x86/util/pmu.c @@ -126,7 +126,7 @@ close_dir: return ret; } -static char *__pmu_find_real_name(const char *name) +static const char *__pmu_find_real_name(const char *name) { struct pmu_alias *pmu_alias; @@ -135,10 +135,10 @@ static char *__pmu_find_real_name(const char *name) return pmu_alias->name; } - return (char *)name; + return name; } -char *pmu_find_real_name(const char *name) +const char *pmu_find_real_name(const char *name) { if (cached_list) return __pmu_find_real_name(name); @@ -149,7 +149,7 @@ char *pmu_find_real_name(const char *name) return __pmu_find_real_name(name); } -static char *__pmu_find_alias_name(const char *name) +static const char *__pmu_find_alias_name(const char *name) { struct pmu_alias *pmu_alias; @@ -160,7 +160,7 @@ static char *__pmu_find_alias_name(const char *name) return NULL; } -char *pmu_find_alias_name(const char *name) +const char *pmu_find_alias_name(const char *name) { if (cached_list) return __pmu_find_alias_name(name); diff --git a/tools/perf/arch/x86/util/unwind-libdw.c b/tools/perf/arch/x86/util/unwind-libdw.c index ef71e8bf80bf..edb77e20e083 100644 --- a/tools/perf/arch/x86/util/unwind-libdw.c +++ b/tools/perf/arch/x86/util/unwind-libdw.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <elfutils/libdwfl.h> +#include "perf_regs.h" #include "../../../util/unwind-libdw.h" #include "../../../util/perf_regs.h" #include "util/sample.h" diff --git a/tools/perf/bench/Build b/tools/perf/bench/Build index 0f158dc8139b..c2ab30907ae7 100644 --- a/tools/perf/bench/Build +++ b/tools/perf/bench/Build @@ -1,5 +1,6 @@ perf-y += sched-messaging.o perf-y += sched-pipe.o +perf-y += sched-seccomp-notify.o perf-y += syscall.o perf-y += mem-functions.o perf-y += futex-hash.o @@ -16,6 +17,7 @@ perf-y += inject-buildid.o perf-y += evlist-open-close.o perf-y += breakpoint.o perf-y += pmu-scan.o +perf-y += uprobe.o perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-asm.o perf-$(CONFIG_X86_64) += mem-memset-x86-64-asm.o diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h index 0d2b65976212..faa18e6d2467 100644 --- a/tools/perf/bench/bench.h +++ b/tools/perf/bench/bench.h @@ -21,6 +21,7 @@ extern struct timeval bench__start, bench__end, bench__runtime; int bench_numa(int argc, const char **argv); int bench_sched_messaging(int argc, const char **argv); int bench_sched_pipe(int argc, const char **argv); +int bench_sched_seccomp_notify(int argc, const char **argv); int bench_syscall_basic(int argc, const char **argv); int bench_syscall_getpgid(int argc, const char **argv); int bench_syscall_fork(int argc, const char **argv); @@ -42,6 +43,9 @@ int bench_inject_build_id(int argc, const char **argv); int bench_evlist_open_close(int argc, const char **argv); int bench_breakpoint_thread(int argc, const char **argv); int bench_breakpoint_enable(int argc, const char **argv); +int bench_uprobe_baseline(int argc, const char **argv); +int bench_uprobe_empty(int argc, const char **argv); +int bench_uprobe_trace_printk(int argc, const char **argv); int bench_pmu_scan(int argc, const char **argv); #define BENCH_FORMAT_DEFAULT_STR "default" diff --git a/tools/perf/bench/breakpoint.c b/tools/perf/bench/breakpoint.c index 41385f89ffc7..dfd18f5db97d 100644 --- a/tools/perf/bench/breakpoint.c +++ b/tools/perf/bench/breakpoint.c @@ -47,6 +47,7 @@ struct breakpoint { static int breakpoint_setup(void *addr) { struct perf_event_attr attr = { .size = 0, }; + int fd; attr.type = PERF_TYPE_BREAKPOINT; attr.size = sizeof(attr); @@ -56,7 +57,12 @@ static int breakpoint_setup(void *addr) attr.bp_addr = (unsigned long)addr; attr.bp_type = HW_BREAKPOINT_RW; attr.bp_len = HW_BREAKPOINT_LEN_1; - return syscall(SYS_perf_event_open, &attr, 0, -1, -1, 0); + fd = syscall(SYS_perf_event_open, &attr, 0, -1, -1, 0); + + if (fd < 0) + fd = -errno; + + return fd; } static void *passive_thread(void *arg) @@ -122,8 +128,14 @@ int bench_breakpoint_thread(int argc, const char **argv) for (i = 0; i < thread_params.nbreakpoints; i++) { breakpoints[i].fd = breakpoint_setup(&breakpoints[i].watched); - if (breakpoints[i].fd == -1) + + if (breakpoints[i].fd < 0) { + if (breakpoints[i].fd == -ENODEV) { + printf("Skipping perf bench breakpoint thread: No hardware support\n"); + return 0; + } exit((perror("perf_event_open"), EXIT_FAILURE)); + } } gettimeofday(&start, NULL); for (i = 0; i < thread_params.nparallel; i++) { @@ -196,8 +208,14 @@ int bench_breakpoint_enable(int argc, const char **argv) exit(EXIT_FAILURE); } fd = breakpoint_setup(&watched); - if (fd == -1) + + if (fd < 0) { + if (fd == -ENODEV) { + printf("Skipping perf bench breakpoint enable: No hardware support\n"); + return 0; + } exit((perror("perf_event_open"), EXIT_FAILURE)); + } nthreads = enable_params.npassive + enable_params.nactive; threads = calloc(nthreads, sizeof(threads[0])); if (!threads) diff --git a/tools/perf/bench/pmu-scan.c b/tools/perf/bench/pmu-scan.c index c7d207f8e13c..9e4d36486f62 100644 --- a/tools/perf/bench/pmu-scan.c +++ b/tools/perf/bench/pmu-scan.c @@ -57,9 +57,7 @@ static int save_result(void) r->is_core = pmu->is_core; r->nr_caps = pmu->nr_caps; - r->nr_aliases = 0; - list_for_each(list, &pmu->aliases) - r->nr_aliases++; + r->nr_aliases = perf_pmu__num_events(pmu); r->nr_formats = 0; list_for_each(list, &pmu->format) @@ -98,9 +96,7 @@ static int check_result(bool core_only) return -1; } - nr = 0; - list_for_each(list, &pmu->aliases) - nr++; + nr = perf_pmu__num_events(pmu); if (nr != r->nr_aliases) { pr_err("Unmatched number of event aliases in %s: expect %d vs got %d\n", pmu->name, r->nr_aliases, nr); diff --git a/tools/perf/bench/sched-seccomp-notify.c b/tools/perf/bench/sched-seccomp-notify.c new file mode 100644 index 000000000000..b04ebcde4036 --- /dev/null +++ b/tools/perf/bench/sched-seccomp-notify.c @@ -0,0 +1,178 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <subcmd/parse-options.h> +#include "bench.h" + +#include <uapi/linux/filter.h> +#include <sys/types.h> +#include <sys/time.h> +#include <linux/unistd.h> +#include <sys/syscall.h> +#include <sys/ioctl.h> +#include <linux/time64.h> +#include <linux/seccomp.h> +#include <sys/prctl.h> + +#include <unistd.h> +#include <limits.h> +#include <stddef.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <signal.h> +#include <sys/wait.h> +#include <string.h> +#include <errno.h> +#include <err.h> +#include <inttypes.h> + +#define LOOPS_DEFAULT 1000000UL +static uint64_t loops = LOOPS_DEFAULT; +static bool sync_mode; + +static const struct option options[] = { + OPT_U64('l', "loop", &loops, "Specify number of loops"), + OPT_BOOLEAN('s', "sync-mode", &sync_mode, + "Enable the synchronious mode for seccomp notifications"), + OPT_END() +}; + +static const char * const bench_seccomp_usage[] = { + "perf bench sched secccomp-notify <options>", + NULL +}; + +static int seccomp(unsigned int op, unsigned int flags, void *args) +{ + return syscall(__NR_seccomp, op, flags, args); +} + +static int user_notif_syscall(int nr, unsigned int flags) +{ + struct sock_filter filter[] = { + BPF_STMT(BPF_LD|BPF_W|BPF_ABS, + offsetof(struct seccomp_data, nr)), + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, nr, 0, 1), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_USER_NOTIF), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), + }; + + struct sock_fprog prog = { + .len = (unsigned short)ARRAY_SIZE(filter), + .filter = filter, + }; + + return seccomp(SECCOMP_SET_MODE_FILTER, flags, &prog); +} + +#define USER_NOTIF_MAGIC INT_MAX +static void user_notification_sync_loop(int listener) +{ + struct seccomp_notif_resp resp; + struct seccomp_notif req; + uint64_t nr; + + for (nr = 0; nr < loops; nr++) { + memset(&req, 0, sizeof(req)); + if (ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req)) + err(EXIT_FAILURE, "SECCOMP_IOCTL_NOTIF_RECV failed"); + + if (req.data.nr != __NR_gettid) + errx(EXIT_FAILURE, "unexpected syscall: %d", req.data.nr); + + resp.id = req.id; + resp.error = 0; + resp.val = USER_NOTIF_MAGIC; + resp.flags = 0; + if (ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp)) + err(EXIT_FAILURE, "SECCOMP_IOCTL_NOTIF_SEND failed"); + } +} + +#ifndef SECCOMP_USER_NOTIF_FD_SYNC_WAKE_UP +#define SECCOMP_USER_NOTIF_FD_SYNC_WAKE_UP (1UL << 0) +#define SECCOMP_IOCTL_NOTIF_SET_FLAGS SECCOMP_IOW(4, __u64) +#endif +int bench_sched_seccomp_notify(int argc, const char **argv) +{ + struct timeval start, stop, diff; + unsigned long long result_usec = 0; + int status, listener; + pid_t pid; + long ret; + + argc = parse_options(argc, argv, options, bench_seccomp_usage, 0); + + gettimeofday(&start, NULL); + + prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + listener = user_notif_syscall(__NR_gettid, + SECCOMP_FILTER_FLAG_NEW_LISTENER); + if (listener < 0) + err(EXIT_FAILURE, "can't create a notification descriptor"); + + pid = fork(); + if (pid < 0) + err(EXIT_FAILURE, "fork"); + if (pid == 0) { + if (prctl(PR_SET_PDEATHSIG, SIGKILL, 0, 0, 0)) + err(EXIT_FAILURE, "can't set the parent death signal"); + while (1) { + ret = syscall(__NR_gettid); + if (ret == USER_NOTIF_MAGIC) + continue; + break; + } + _exit(1); + } + + if (sync_mode) { + if (ioctl(listener, SECCOMP_IOCTL_NOTIF_SET_FLAGS, + SECCOMP_USER_NOTIF_FD_SYNC_WAKE_UP, 0)) + err(EXIT_FAILURE, + "can't set SECCOMP_USER_NOTIF_FD_SYNC_WAKE_UP"); + } + user_notification_sync_loop(listener); + + kill(pid, SIGKILL); + if (waitpid(pid, &status, 0) != pid) + err(EXIT_FAILURE, "waitpid(%d) failed", pid); + if (!WIFSIGNALED(status) || WTERMSIG(status) != SIGKILL) + errx(EXIT_FAILURE, "unexpected exit code: %d", status); + + gettimeofday(&stop, NULL); + timersub(&stop, &start, &diff); + + switch (bench_format) { + case BENCH_FORMAT_DEFAULT: + printf("# Executed %" PRIu64 " system calls\n\n", + loops); + + result_usec = diff.tv_sec * USEC_PER_SEC; + result_usec += diff.tv_usec; + + printf(" %14s: %lu.%03lu [sec]\n\n", "Total time", + (unsigned long) diff.tv_sec, + (unsigned long) (diff.tv_usec / USEC_PER_MSEC)); + + printf(" %14lf usecs/op\n", + (double)result_usec / (double)loops); + printf(" %14d ops/sec\n", + (int)((double)loops / + ((double)result_usec / (double)USEC_PER_SEC))); + break; + + case BENCH_FORMAT_SIMPLE: + printf("%lu.%03lu\n", + (unsigned long) diff.tv_sec, + (unsigned long) (diff.tv_usec / USEC_PER_MSEC)); + break; + + default: + /* reaching here is something disaster */ + fprintf(stderr, "Unknown format:%d\n", bench_format); + exit(1); + break; + } + + return 0; +} diff --git a/tools/perf/bench/uprobe.c b/tools/perf/bench/uprobe.c new file mode 100644 index 000000000000..914c0817fe8a --- /dev/null +++ b/tools/perf/bench/uprobe.c @@ -0,0 +1,198 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* + * uprobe.c + * + * uprobe benchmarks + * + * Copyright (C) 2023, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com> + */ +#include "../perf.h" +#include "../util/util.h" +#include <subcmd/parse-options.h> +#include "../builtin.h" +#include "bench.h" +#include <linux/compiler.h> +#include <linux/time64.h> + +#include <inttypes.h> +#include <stdio.h> +#include <sys/time.h> +#include <sys/types.h> +#include <time.h> +#include <unistd.h> +#include <stdlib.h> + +#define LOOPS_DEFAULT 1000 +static int loops = LOOPS_DEFAULT; + +enum bench_uprobe { + BENCH_UPROBE__BASELINE, + BENCH_UPROBE__EMPTY, + BENCH_UPROBE__TRACE_PRINTK, +}; + +static const struct option options[] = { + OPT_INTEGER('l', "loop", &loops, "Specify number of loops"), + OPT_END() +}; + +static const char * const bench_uprobe_usage[] = { + "perf bench uprobe <options>", + NULL +}; + +#ifdef HAVE_BPF_SKEL +#include "bpf_skel/bench_uprobe.skel.h" + +#define bench_uprobe__attach_uprobe(prog) \ + skel->links.prog = bpf_program__attach_uprobe_opts(/*prog=*/skel->progs.prog, \ + /*pid=*/-1, \ + /*binary_path=*/"/lib64/libc.so.6", \ + /*func_offset=*/0, \ + /*opts=*/&uprobe_opts); \ + if (!skel->links.prog) { \ + err = -errno; \ + fprintf(stderr, "Failed to attach bench uprobe \"%s\": %s\n", #prog, strerror(errno)); \ + goto cleanup; \ + } + +struct bench_uprobe_bpf *skel; + +static int bench_uprobe__setup_bpf_skel(enum bench_uprobe bench) +{ + DECLARE_LIBBPF_OPTS(bpf_uprobe_opts, uprobe_opts); + int err; + + /* Load and verify BPF application */ + skel = bench_uprobe_bpf__open(); + if (!skel) { + fprintf(stderr, "Failed to open and load uprobes bench BPF skeleton\n"); + return -1; + } + + err = bench_uprobe_bpf__load(skel); + if (err) { + fprintf(stderr, "Failed to load and verify BPF skeleton\n"); + goto cleanup; + } + + uprobe_opts.func_name = "usleep"; + switch (bench) { + case BENCH_UPROBE__BASELINE: break; + case BENCH_UPROBE__EMPTY: bench_uprobe__attach_uprobe(empty); break; + case BENCH_UPROBE__TRACE_PRINTK: bench_uprobe__attach_uprobe(trace_printk); break; + default: + fprintf(stderr, "Invalid bench: %d\n", bench); + goto cleanup; + } + + return err; +cleanup: + bench_uprobe_bpf__destroy(skel); + return err; +} + +static void bench_uprobe__teardown_bpf_skel(void) +{ + if (skel) { + bench_uprobe_bpf__destroy(skel); + skel = NULL; + } +} +#else +static int bench_uprobe__setup_bpf_skel(enum bench_uprobe bench __maybe_unused) { return 0; } +static void bench_uprobe__teardown_bpf_skel(void) {}; +#endif + +static int bench_uprobe_format__default_fprintf(const char *name, const char *unit, u64 diff, FILE *fp) +{ + static u64 baseline, previous; + s64 diff_to_baseline = diff - baseline, + diff_to_previous = diff - previous; + int printed = fprintf(fp, "# Executed %'d %s calls\n", loops, name); + + printed += fprintf(fp, " %14s: %'" PRIu64 " %ss", "Total time", diff, unit); + + if (baseline) { + printed += fprintf(fp, " %s%'" PRId64 " to baseline", diff_to_baseline > 0 ? "+" : "", diff_to_baseline); + + if (previous != baseline) + fprintf(stdout, " %s%'" PRId64 " to previous", diff_to_previous > 0 ? "+" : "", diff_to_previous); + } + + printed += fprintf(fp, "\n\n %'.3f %ss/op", (double)diff / (double)loops, unit); + + if (baseline) { + printed += fprintf(fp, " %'.3f %ss/op to baseline", (double)diff_to_baseline / (double)loops, unit); + + if (previous != baseline) + printed += fprintf(fp, " %'.3f %ss/op to previous", (double)diff_to_previous / (double)loops, unit); + } else { + baseline = diff; + } + + fputc('\n', fp); + + previous = diff; + + return printed + 1; +} + +static int bench_uprobe(int argc, const char **argv, enum bench_uprobe bench) +{ + const char *name = "usleep(1000)", *unit = "usec"; + struct timespec start, end; + u64 diff; + int i; + + argc = parse_options(argc, argv, options, bench_uprobe_usage, 0); + + if (bench != BENCH_UPROBE__BASELINE && bench_uprobe__setup_bpf_skel(bench) < 0) + return 0; + + clock_gettime(CLOCK_REALTIME, &start); + + for (i = 0; i < loops; i++) { + usleep(USEC_PER_MSEC); + } + + clock_gettime(CLOCK_REALTIME, &end); + + diff = end.tv_sec * NSEC_PER_SEC + end.tv_nsec - (start.tv_sec * NSEC_PER_SEC + start.tv_nsec); + diff /= NSEC_PER_USEC; + + switch (bench_format) { + case BENCH_FORMAT_DEFAULT: + bench_uprobe_format__default_fprintf(name, unit, diff, stdout); + break; + + case BENCH_FORMAT_SIMPLE: + printf("%" PRIu64 "\n", diff); + break; + + default: + /* reaching here is something of a disaster */ + fprintf(stderr, "Unknown format:%d\n", bench_format); + exit(1); + } + + if (bench != BENCH_UPROBE__BASELINE) + bench_uprobe__teardown_bpf_skel(); + + return 0; +} + +int bench_uprobe_baseline(int argc, const char **argv) +{ + return bench_uprobe(argc, argv, BENCH_UPROBE__BASELINE); +} + +int bench_uprobe_empty(int argc, const char **argv) +{ + return bench_uprobe(argc, argv, BENCH_UPROBE__EMPTY); +} + +int bench_uprobe_trace_printk(int argc, const char **argv) +{ + return bench_uprobe(argc, argv, BENCH_UPROBE__TRACE_PRINTK); +} diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c index db435b791a09..1a8898d5b560 100644 --- a/tools/perf/builtin-bench.c +++ b/tools/perf/builtin-bench.c @@ -47,6 +47,7 @@ static struct bench numa_benchmarks[] = { static struct bench sched_benchmarks[] = { { "messaging", "Benchmark for scheduling and IPC", bench_sched_messaging }, { "pipe", "Benchmark for pipe() between two processes", bench_sched_pipe }, + { "seccomp-notify", "Benchmark for seccomp user notify", bench_sched_seccomp_notify}, { "all", "Run all scheduler benchmarks", NULL }, { NULL, NULL, NULL } }; @@ -104,6 +105,13 @@ static struct bench breakpoint_benchmarks[] = { { NULL, NULL, NULL }, }; +static struct bench uprobe_benchmarks[] = { + { "baseline", "Baseline libc usleep(1000) call", bench_uprobe_baseline, }, + { "empty", "Attach empty BPF prog to uprobe on usleep, system wide", bench_uprobe_empty, }, + { "trace_printk", "Attach trace_printk BPF prog to uprobe on usleep syswide", bench_uprobe_trace_printk, }, + { NULL, NULL, NULL }, +}; + struct collection { const char *name; const char *summary; @@ -123,6 +131,7 @@ static struct collection collections[] = { #endif { "internals", "Perf-internals benchmarks", internals_benchmarks }, { "breakpoint", "Breakpoint benchmarks", breakpoint_benchmarks }, + { "uprobe", "uprobe benchmarks", uprobe_benchmarks }, { "all", "All benchmarks", NULL }, { NULL, NULL, NULL } }; diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index e8a1b16aa5f8..57d300d8e570 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -1915,8 +1915,8 @@ static int data_init(int argc, const char **argv) struct perf_data *data = &d->data; data->path = use_default ? defaults[i] : argv[i]; - data->mode = PERF_DATA_MODE_READ, - data->force = force, + data->mode = PERF_DATA_MODE_READ; + data->force = force; d->idx = i; } diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c index 7fec2cca759f..a343823c8ddf 100644 --- a/tools/perf/builtin-list.c +++ b/tools/perf/builtin-list.c @@ -145,9 +145,20 @@ static void default_print_event(void *ps, const char *pmu_name, const char *topi putchar('\n'); if (desc && print_state->desc) { + char *desc_with_unit = NULL; + int desc_len = -1; + + if (pmu_name && strcmp(pmu_name, "default_core")) { + desc_len = strlen(desc); + desc_len = asprintf(&desc_with_unit, + desc[desc_len - 1] != '.' + ? "%s. Unit: %s" : "%s Unit: %s", + desc, pmu_name); + } printf("%*s", 8, "["); - wordwrap(desc, 8, pager_get_columns(), 0); + wordwrap(desc_len > 0 ? desc_with_unit : desc, 8, pager_get_columns(), 0); printf("]\n"); + free(desc_with_unit); } long_desc = long_desc ?: desc; if (long_desc && print_state->long_desc) { @@ -423,6 +434,13 @@ static void json_print_metric(void *ps __maybe_unused, const char *group, strbuf_release(&buf); } +static bool default_skip_duplicate_pmus(void *ps) +{ + struct print_state *print_state = ps; + + return !print_state->long_desc; +} + int cmd_list(int argc, const char **argv) { int i, ret = 0; @@ -434,6 +452,7 @@ int cmd_list(int argc, const char **argv) .print_end = default_print_end, .print_event = default_print_event, .print_metric = default_print_metric, + .skip_duplicate_pmus = default_skip_duplicate_pmus, }; const char *cputype = NULL; const char *unit_name = NULL; @@ -502,7 +521,7 @@ int cmd_list(int argc, const char **argv) ret = -1; goto out; } - default_ps.pmu_glob = pmu->name; + default_ps.pmu_glob = strdup(pmu->name); } } print_cb.print_start(ps); diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index c15386cb1033..b141f2134274 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -2052,6 +2052,7 @@ static int __cmd_contention(int argc, const char **argv) if (IS_ERR(session)) { pr_err("Initializing perf session failed\n"); err = PTR_ERR(session); + session = NULL; goto out_delete; } @@ -2506,7 +2507,7 @@ int cmd_lock(int argc, const char **argv) OPT_CALLBACK('M', "map-nr-entries", &bpf_map_entries, "num", "Max number of BPF map entries", parse_map_entry), OPT_CALLBACK(0, "max-stack", &max_stack_depth, "num", - "Set the maximum stack depth when collecting lopck contention, " + "Set the maximum stack depth when collecting lock contention, " "Default: " __stringify(CONTENTION_STACK_DEPTH), parse_max_stack), OPT_INTEGER(0, "stack-skip", &stack_skip, "Set the number of stack depth to skip when finding a lock caller, " diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index aec18db7ff23..34bb31f08bb5 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -37,8 +37,6 @@ #include "util/parse-branch-options.h" #include "util/parse-regs-options.h" #include "util/perf_api_probe.h" -#include "util/llvm-utils.h" -#include "util/bpf-loader.h" #include "util/trigger.h" #include "util/perf-hooks.h" #include "util/cpu-set-sched.h" @@ -2465,16 +2463,6 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) } } - err = bpf__apply_obj_config(); - if (err) { - char errbuf[BUFSIZ]; - - bpf__strerror_apply_obj_config(err, errbuf, sizeof(errbuf)); - pr_err("ERROR: Apply config to BPF failed: %s\n", - errbuf); - goto out_free_threads; - } - /* * Normally perf_session__new would do this, but it doesn't have the * evlist. @@ -3486,10 +3474,6 @@ static struct option __record_options[] = { "collect kernel callchains"), OPT_BOOLEAN(0, "user-callchains", &record.opts.user_callchains, "collect user callchains"), - OPT_STRING(0, "clang-path", &llvm_param.clang_path, "clang path", - "clang binary to use for compiling BPF scriptlets"), - OPT_STRING(0, "clang-opt", &llvm_param.clang_opt, "clang options", - "options passed to clang when compiling BPF scriptlets"), OPT_STRING(0, "vmlinux", &symbol_conf.vmlinux_name, "file", "vmlinux pathname"), OPT_BOOLEAN(0, "buildid-all", &record.buildid_all, @@ -3967,27 +3951,6 @@ int cmd_record(int argc, const char **argv) setlocale(LC_ALL, ""); -#ifndef HAVE_LIBBPF_SUPPORT -# define set_nobuild(s, l, c) set_option_nobuild(record_options, s, l, "NO_LIBBPF=1", c) - set_nobuild('\0', "clang-path", true); - set_nobuild('\0', "clang-opt", true); -# undef set_nobuild -#endif - -#ifndef HAVE_BPF_PROLOGUE -# if !defined (HAVE_DWARF_SUPPORT) -# define REASON "NO_DWARF=1" -# elif !defined (HAVE_LIBBPF_SUPPORT) -# define REASON "NO_LIBBPF=1" -# else -# define REASON "this architecture doesn't support BPF prologue" -# endif -# define set_nobuild(s, l, c) set_option_nobuild(record_options, s, l, REASON, c) - set_nobuild('\0', "vmlinux", true); -# undef set_nobuild -# undef REASON -#endif - #ifndef HAVE_BPF_SKEL # define set_nobuild(s, l, m, c) set_option_nobuild(record_options, s, l, m, c) set_nobuild('\0', "off-cpu", "no BUILD_BPF_SKEL=1", true); @@ -4116,14 +4079,6 @@ int cmd_record(int argc, const char **argv) if (dry_run) goto out; - err = bpf__setup_stdout(rec->evlist); - if (err) { - bpf__strerror_setup_stdout(rec->evlist, err, errbuf, sizeof(errbuf)); - pr_err("ERROR: Setup BPF stdout failed: %s\n", - errbuf); - goto out; - } - err = -ENOMEM; if (rec->no_buildid_cache || rec->no_buildid) { diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 200b3e7ea8da..517bf25750c8 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -2199,6 +2199,17 @@ static void process_event(struct perf_script *script, if (PRINT_FIELD(RETIRE_LAT)) fprintf(fp, "%16" PRIu16, sample->retire_lat); + if (PRINT_FIELD(CGROUP)) { + const char *cgrp_name; + struct cgroup *cgrp = cgroup__find(machine->env, + sample->cgroup); + if (cgrp != NULL) + cgrp_name = cgrp->name; + else + cgrp_name = "unknown"; + fprintf(fp, " %s", cgrp_name); + } + if (PRINT_FIELD(IP)) { struct callchain_cursor *cursor = NULL; @@ -2243,17 +2254,6 @@ static void process_event(struct perf_script *script, if (PRINT_FIELD(CODE_PAGE_SIZE)) fprintf(fp, " %s", get_page_size_name(sample->code_page_size, str)); - if (PRINT_FIELD(CGROUP)) { - const char *cgrp_name; - struct cgroup *cgrp = cgroup__find(machine->env, - sample->cgroup); - if (cgrp != NULL) - cgrp_name = cgrp->name; - else - cgrp_name = "unknown"; - fprintf(fp, " %s", cgrp_name); - } - perf_sample__fprintf_ipc(sample, attr, fp); fprintf(fp, "\n"); diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 1baa2acb3ced..ea8c7eca5eee 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1805,6 +1805,7 @@ int cmd_top(int argc, const char **argv) top.session = perf_session__new(NULL, NULL); if (IS_ERR(top.session)) { status = PTR_ERR(top.session); + top.session = NULL; goto out_delete_evlist; } diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 6e73d0e95715..e541d0e2777a 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -18,6 +18,10 @@ #include <api/fs/tracing_path.h> #ifdef HAVE_LIBBPF_SUPPORT #include <bpf/bpf.h> +#include <bpf/libbpf.h> +#ifdef HAVE_BPF_SKEL +#include "bpf_skel/augmented_raw_syscalls.skel.h" +#endif #endif #include "util/bpf_map.h" #include "util/rlimit.h" @@ -53,7 +57,6 @@ #include "trace/beauty/beauty.h" #include "trace-event.h" #include "util/parse-events.h" -#include "util/bpf-loader.h" #include "util/tracepoint.h" #include "callchain.h" #include "print_binary.h" @@ -127,25 +130,19 @@ struct trace { struct syscalltbl *sctbl; struct { struct syscall *table; - struct { // per syscall BPF_MAP_TYPE_PROG_ARRAY - struct bpf_map *sys_enter, - *sys_exit; - } prog_array; struct { struct evsel *sys_enter, - *sys_exit, - *augmented; + *sys_exit, + *bpf_output; } events; - struct bpf_program *unaugmented_prog; } syscalls; - struct { - struct bpf_map *map; - } dump; +#ifdef HAVE_BPF_SKEL + struct augmented_raw_syscalls_bpf *skel; +#endif struct record_opts opts; struct evlist *evlist; struct machine *host; struct thread *current; - struct bpf_object *bpf_obj; struct cgroup *cgroup; u64 base_time; FILE *output; @@ -415,6 +412,7 @@ static int evsel__init_syscall_tp(struct evsel *evsel) if (evsel__init_tp_uint_field(evsel, &sc->id, "__syscall_nr") && evsel__init_tp_uint_field(evsel, &sc->id, "nr")) return -ENOENT; + return 0; } @@ -1296,6 +1294,22 @@ static struct thread_trace *thread_trace__new(void) return ttrace; } +static void thread_trace__free_files(struct thread_trace *ttrace); + +static void thread_trace__delete(void *pttrace) +{ + struct thread_trace *ttrace = pttrace; + + if (!ttrace) + return; + + intlist__delete(ttrace->syscall_stats); + ttrace->syscall_stats = NULL; + thread_trace__free_files(ttrace); + zfree(&ttrace->entry_str); + free(ttrace); +} + static struct thread_trace *thread__trace(struct thread *thread, FILE *fp) { struct thread_trace *ttrace; @@ -1333,6 +1347,17 @@ void syscall_arg__set_ret_scnprintf(struct syscall_arg *arg, static const size_t trace__entry_str_size = 2048; +static void thread_trace__free_files(struct thread_trace *ttrace) +{ + for (int i = 0; i < ttrace->files.max; ++i) { + struct file *file = ttrace->files.table + i; + zfree(&file->pathname); + } + + zfree(&ttrace->files.table); + ttrace->files.max = -1; +} + static struct file *thread_trace__files_entry(struct thread_trace *ttrace, int fd) { if (fd < 0) @@ -1635,6 +1660,8 @@ static int trace__symbols_init(struct trace *trace, struct evlist *evlist) if (trace->host == NULL) return -ENOMEM; + thread__set_priv_destructor(thread_trace__delete); + err = trace_event__register_resolver(trace->host, trace__machine__resolve_kernel_addr); if (err < 0) goto out; @@ -2816,7 +2843,7 @@ static int trace__event_handler(struct trace *trace, struct evsel *evsel, if (thread) trace__fprintf_comm_tid(trace, thread, trace->output); - if (evsel == trace->syscalls.events.augmented) { + if (evsel == trace->syscalls.events.bpf_output) { int id = perf_evsel__sc_tp_uint(evsel, id, sample); struct syscall *sc = trace__syscall_info(trace, evsel, id); @@ -3136,13 +3163,8 @@ static void evlist__free_syscall_tp_fields(struct evlist *evlist) struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { - struct evsel_trace *et = evsel->priv; - - if (!et || !evsel->tp_format || strcmp(evsel->tp_format->system, "syscalls")) - continue; - - zfree(&et->fmt); - free(et); + evsel_trace__delete(evsel->priv); + evsel->priv = NULL; } } @@ -3254,35 +3276,16 @@ out_enomem: goto out; } -#ifdef HAVE_LIBBPF_SUPPORT -static struct bpf_map *trace__find_bpf_map_by_name(struct trace *trace, const char *name) -{ - if (trace->bpf_obj == NULL) - return NULL; - - return bpf_object__find_map_by_name(trace->bpf_obj, name); -} - -static void trace__set_bpf_map_filtered_pids(struct trace *trace) -{ - trace->filter_pids.map = trace__find_bpf_map_by_name(trace, "pids_filtered"); -} - -static void trace__set_bpf_map_syscalls(struct trace *trace) -{ - trace->syscalls.prog_array.sys_enter = trace__find_bpf_map_by_name(trace, "syscalls_sys_enter"); - trace->syscalls.prog_array.sys_exit = trace__find_bpf_map_by_name(trace, "syscalls_sys_exit"); -} - +#ifdef HAVE_BPF_SKEL static struct bpf_program *trace__find_bpf_program_by_title(struct trace *trace, const char *name) { struct bpf_program *pos, *prog = NULL; const char *sec_name; - if (trace->bpf_obj == NULL) + if (trace->skel->obj == NULL) return NULL; - bpf_object__for_each_program(pos, trace->bpf_obj) { + bpf_object__for_each_program(pos, trace->skel->obj) { sec_name = bpf_program__section_name(pos); if (sec_name && !strcmp(sec_name, name)) { prog = pos; @@ -3300,12 +3303,12 @@ static struct bpf_program *trace__find_syscall_bpf_prog(struct trace *trace, str if (prog_name == NULL) { char default_prog_name[256]; - scnprintf(default_prog_name, sizeof(default_prog_name), "!syscalls:sys_%s_%s", type, sc->name); + scnprintf(default_prog_name, sizeof(default_prog_name), "tp/syscalls/sys_%s_%s", type, sc->name); prog = trace__find_bpf_program_by_title(trace, default_prog_name); if (prog != NULL) goto out_found; if (sc->fmt && sc->fmt->alias) { - scnprintf(default_prog_name, sizeof(default_prog_name), "!syscalls:sys_%s_%s", type, sc->fmt->alias); + scnprintf(default_prog_name, sizeof(default_prog_name), "tp/syscalls/sys_%s_%s", type, sc->fmt->alias); prog = trace__find_bpf_program_by_title(trace, default_prog_name); if (prog != NULL) goto out_found; @@ -3323,7 +3326,7 @@ out_found: pr_debug("Couldn't find BPF prog \"%s\" to associate with syscalls:sys_%s_%s, not augmenting it\n", prog_name, type, sc->name); out_unaugmented: - return trace->syscalls.unaugmented_prog; + return trace->skel->progs.syscall_unaugmented; } static void trace__init_syscall_bpf_progs(struct trace *trace, int id) @@ -3340,13 +3343,13 @@ static void trace__init_syscall_bpf_progs(struct trace *trace, int id) static int trace__bpf_prog_sys_enter_fd(struct trace *trace, int id) { struct syscall *sc = trace__syscall_info(trace, NULL, id); - return sc ? bpf_program__fd(sc->bpf_prog.sys_enter) : bpf_program__fd(trace->syscalls.unaugmented_prog); + return sc ? bpf_program__fd(sc->bpf_prog.sys_enter) : bpf_program__fd(trace->skel->progs.syscall_unaugmented); } static int trace__bpf_prog_sys_exit_fd(struct trace *trace, int id) { struct syscall *sc = trace__syscall_info(trace, NULL, id); - return sc ? bpf_program__fd(sc->bpf_prog.sys_exit) : bpf_program__fd(trace->syscalls.unaugmented_prog); + return sc ? bpf_program__fd(sc->bpf_prog.sys_exit) : bpf_program__fd(trace->skel->progs.syscall_unaugmented); } static struct bpf_program *trace__find_usable_bpf_prog_entry(struct trace *trace, struct syscall *sc) @@ -3371,7 +3374,7 @@ try_to_find_pair: bool is_candidate = false; if (pair == NULL || pair == sc || - pair->bpf_prog.sys_enter == trace->syscalls.unaugmented_prog) + pair->bpf_prog.sys_enter == trace->skel->progs.syscall_unaugmented) continue; for (field = sc->args, candidate_field = pair->args; @@ -3395,6 +3398,19 @@ try_to_find_pair: if (strcmp(field->type, candidate_field->type)) goto next_candidate; + /* + * This is limited in the BPF program but sys_write + * uses "const char *" for its "buf" arg so we need to + * use some heuristic that is kinda future proof... + */ + if (strcmp(field->type, "const char *") == 0 && + !(strstr(field->name, "name") || + strstr(field->name, "path") || + strstr(field->name, "file") || + strstr(field->name, "root") || + strstr(field->name, "description"))) + goto next_candidate; + is_candidate = true; } @@ -3424,7 +3440,7 @@ try_to_find_pair: */ if (pair_prog == NULL) { pair_prog = trace__find_syscall_bpf_prog(trace, pair, pair->fmt ? pair->fmt->bpf_prog_name.sys_enter : NULL, "enter"); - if (pair_prog == trace->syscalls.unaugmented_prog) + if (pair_prog == trace->skel->progs.syscall_unaugmented) goto next_candidate; } @@ -3439,8 +3455,8 @@ try_to_find_pair: static int trace__init_syscalls_bpf_prog_array_maps(struct trace *trace) { - int map_enter_fd = bpf_map__fd(trace->syscalls.prog_array.sys_enter), - map_exit_fd = bpf_map__fd(trace->syscalls.prog_array.sys_exit); + int map_enter_fd = bpf_map__fd(trace->skel->maps.syscalls_sys_enter); + int map_exit_fd = bpf_map__fd(trace->skel->maps.syscalls_sys_exit); int err = 0, key; for (key = 0; key < trace->sctbl->syscalls.nr_entries; ++key) { @@ -3502,7 +3518,7 @@ static int trace__init_syscalls_bpf_prog_array_maps(struct trace *trace) * For now we're just reusing the sys_enter prog, and if it * already has an augmenter, we don't need to find one. */ - if (sc->bpf_prog.sys_enter != trace->syscalls.unaugmented_prog) + if (sc->bpf_prog.sys_enter != trace->skel->progs.syscall_unaugmented) continue; /* @@ -3525,74 +3541,9 @@ static int trace__init_syscalls_bpf_prog_array_maps(struct trace *trace) break; } - return err; } - -static void trace__delete_augmented_syscalls(struct trace *trace) -{ - struct evsel *evsel, *tmp; - - evlist__remove(trace->evlist, trace->syscalls.events.augmented); - evsel__delete(trace->syscalls.events.augmented); - trace->syscalls.events.augmented = NULL; - - evlist__for_each_entry_safe(trace->evlist, tmp, evsel) { - if (evsel->bpf_obj == trace->bpf_obj) { - evlist__remove(trace->evlist, evsel); - evsel__delete(evsel); - } - - } - - bpf_object__close(trace->bpf_obj); - trace->bpf_obj = NULL; -} -#else // HAVE_LIBBPF_SUPPORT -static struct bpf_map *trace__find_bpf_map_by_name(struct trace *trace __maybe_unused, - const char *name __maybe_unused) -{ - return NULL; -} - -static void trace__set_bpf_map_filtered_pids(struct trace *trace __maybe_unused) -{ -} - -static void trace__set_bpf_map_syscalls(struct trace *trace __maybe_unused) -{ -} - -static struct bpf_program *trace__find_bpf_program_by_title(struct trace *trace __maybe_unused, - const char *name __maybe_unused) -{ - return NULL; -} - -static int trace__init_syscalls_bpf_prog_array_maps(struct trace *trace __maybe_unused) -{ - return 0; -} - -static void trace__delete_augmented_syscalls(struct trace *trace __maybe_unused) -{ -} -#endif // HAVE_LIBBPF_SUPPORT - -static bool trace__only_augmented_syscalls_evsels(struct trace *trace) -{ - struct evsel *evsel; - - evlist__for_each_entry(trace->evlist, evsel) { - if (evsel == trace->syscalls.events.augmented || - evsel->bpf_obj == trace->bpf_obj) - continue; - - return false; - } - - return true; -} +#endif // HAVE_BPF_SKEL static int trace__set_ev_qualifier_filter(struct trace *trace) { @@ -3956,23 +3907,31 @@ static int trace__run(struct trace *trace, int argc, const char **argv) err = evlist__open(evlist); if (err < 0) goto out_error_open; +#ifdef HAVE_BPF_SKEL + if (trace->syscalls.events.bpf_output) { + struct perf_cpu cpu; - err = bpf__apply_obj_config(); - if (err) { - char errbuf[BUFSIZ]; - - bpf__strerror_apply_obj_config(err, errbuf, sizeof(errbuf)); - pr_err("ERROR: Apply config to BPF failed: %s\n", - errbuf); - goto out_error_open; + /* + * Set up the __augmented_syscalls__ BPF map to hold for each + * CPU the bpf-output event's file descriptor. + */ + perf_cpu_map__for_each_cpu(cpu, i, trace->syscalls.events.bpf_output->core.cpus) { + bpf_map__update_elem(trace->skel->maps.__augmented_syscalls__, + &cpu.cpu, sizeof(int), + xyarray__entry(trace->syscalls.events.bpf_output->core.fd, + cpu.cpu, 0), + sizeof(__u32), BPF_ANY); + } } - +#endif err = trace__set_filter_pids(trace); if (err < 0) goto out_error_mem; - if (trace->syscalls.prog_array.sys_enter) +#ifdef HAVE_BPF_SKEL + if (trace->skel && trace->skel->progs.sys_enter) trace__init_syscalls_bpf_prog_array_maps(trace); +#endif if (trace->ev_qualifier_ids.nr > 0) { err = trace__set_ev_qualifier_filter(trace); @@ -4005,9 +3964,6 @@ static int trace__run(struct trace *trace, int argc, const char **argv) if (err < 0) goto out_error_apply_filters; - if (trace->dump.map) - bpf_map__fprintf(trace->dump.map, trace->output); - err = evlist__mmap(evlist, trace->opts.mmap_pages); if (err < 0) goto out_error_mmap; @@ -4704,6 +4660,18 @@ static void trace__exit(struct trace *trace) zfree(&trace->perfconfig_events); } +#ifdef HAVE_BPF_SKEL +static int bpf__setup_bpf_output(struct evlist *evlist) +{ + int err = parse_event(evlist, "bpf-output/no-inherit=1,name=__augmented_syscalls__/"); + + if (err) + pr_debug("ERROR: failed to create the \"__augmented_syscalls__\" bpf-output event\n"); + + return err; +} +#endif + int cmd_trace(int argc, const char **argv) { const char *trace_usage[] = { @@ -4735,7 +4703,6 @@ int cmd_trace(int argc, const char **argv) .max_stack = UINT_MAX, .max_events = ULONG_MAX, }; - const char *map_dump_str = NULL; const char *output_name = NULL; const struct option trace_options[] = { OPT_CALLBACK('e', "event", &trace, "event", @@ -4769,9 +4736,6 @@ int cmd_trace(int argc, const char **argv) OPT_CALLBACK(0, "duration", &trace, "float", "show only events with duration > N.M ms", trace__set_duration), -#ifdef HAVE_LIBBPF_SUPPORT - OPT_STRING(0, "map-dump", &map_dump_str, "BPF map", "BPF map to periodically dump"), -#endif OPT_BOOLEAN(0, "sched", &trace.sched, "show blocking scheduler events"), OPT_INCR('v', "verbose", &verbose, "be more verbose"), OPT_BOOLEAN('T', "time", &trace.full_time, @@ -4898,87 +4862,48 @@ int cmd_trace(int argc, const char **argv) "cgroup monitoring only available in system-wide mode"); } - evsel = bpf__setup_output_event(trace.evlist, "__augmented_syscalls__"); - if (IS_ERR(evsel)) { - bpf__strerror_setup_output_event(trace.evlist, PTR_ERR(evsel), bf, sizeof(bf)); - pr_err("ERROR: Setup trace syscalls enter failed: %s\n", bf); - goto out; - } - - if (evsel) { - trace.syscalls.events.augmented = evsel; +#ifdef HAVE_BPF_SKEL + if (!trace.trace_syscalls) + goto skip_augmentation; - evsel = evlist__find_tracepoint_by_name(trace.evlist, "raw_syscalls:sys_enter"); - if (evsel == NULL) { - pr_err("ERROR: raw_syscalls:sys_enter not found in the augmented BPF object\n"); - goto out; - } + trace.skel = augmented_raw_syscalls_bpf__open(); + if (!trace.skel) { + pr_debug("Failed to open augmented syscalls BPF skeleton"); + } else { + /* + * Disable attaching the BPF programs except for sys_enter and + * sys_exit that tail call into this as necessary. + */ + struct bpf_program *prog; - if (evsel->bpf_obj == NULL) { - pr_err("ERROR: raw_syscalls:sys_enter not associated to a BPF object\n"); - goto out; + bpf_object__for_each_program(prog, trace.skel->obj) { + if (prog != trace.skel->progs.sys_enter && prog != trace.skel->progs.sys_exit) + bpf_program__set_autoattach(prog, /*autoattach=*/false); } - trace.bpf_obj = evsel->bpf_obj; + err = augmented_raw_syscalls_bpf__load(trace.skel); - /* - * If we have _just_ the augmenter event but don't have a - * explicit --syscalls, then assume we want all strace-like - * syscalls: - */ - if (!trace.trace_syscalls && trace__only_augmented_syscalls_evsels(&trace)) - trace.trace_syscalls = true; - /* - * So, if we have a syscall augmenter, but trace_syscalls, aka - * strace-like syscall tracing is not set, then we need to trow - * away the augmenter, i.e. all the events that were created - * from that BPF object file. - * - * This is more to fix the current .perfconfig trace.add_events - * style of setting up the strace-like eBPF based syscall point - * payload augmenter. - * - * All this complexity will be avoided by adding an alternative - * to trace.add_events in the form of - * trace.bpf_augmented_syscalls, that will be only parsed if we - * need it. - * - * .perfconfig trace.add_events is still useful if we want, for - * instance, have msr_write.msr in some .perfconfig profile based - * 'perf trace --config determinism.profile' mode, where for some - * particular goal/workload type we want a set of events and - * output mode (with timings, etc) instead of having to add - * all via the command line. - * - * Also --config to specify an alternate .perfconfig file needs - * to be implemented. - */ - if (!trace.trace_syscalls) { - trace__delete_augmented_syscalls(&trace); + if (err < 0) { + libbpf_strerror(err, bf, sizeof(bf)); + pr_debug("Failed to load augmented syscalls BPF skeleton: %s\n", bf); } else { - trace__set_bpf_map_filtered_pids(&trace); - trace__set_bpf_map_syscalls(&trace); - trace.syscalls.unaugmented_prog = trace__find_bpf_program_by_title(&trace, "!raw_syscalls:unaugmented"); + augmented_raw_syscalls_bpf__attach(trace.skel); + trace__add_syscall_newtp(&trace); } } - err = bpf__setup_stdout(trace.evlist); + err = bpf__setup_bpf_output(trace.evlist); if (err) { - bpf__strerror_setup_stdout(trace.evlist, err, bf, sizeof(bf)); - pr_err("ERROR: Setup BPF stdout failed: %s\n", bf); + libbpf_strerror(err, bf, sizeof(bf)); + pr_err("ERROR: Setup BPF output event failed: %s\n", bf); goto out; } - + trace.syscalls.events.bpf_output = evlist__last(trace.evlist); + assert(!strcmp(evsel__name(trace.syscalls.events.bpf_output), "__augmented_syscalls__")); +skip_augmentation: +#endif err = -1; - if (map_dump_str) { - trace.dump.map = trace__find_bpf_map_by_name(&trace, map_dump_str); - if (trace.dump.map == NULL) { - pr_err("ERROR: BPF map \"%s\" not found\n", map_dump_str); - goto out; - } - } - if (trace.trace_pgfaults) { trace.opts.sample_address = true; trace.opts.sample_time = true; @@ -5029,7 +4954,7 @@ int cmd_trace(int argc, const char **argv) * buffers that are being copied from kernel to userspace, think 'read' * syscall. */ - if (trace.syscalls.events.augmented) { + if (trace.syscalls.events.bpf_output) { evlist__for_each_entry(trace.evlist, evsel) { bool raw_syscalls_sys_exit = strcmp(evsel__name(evsel), "raw_syscalls:sys_exit") == 0; @@ -5038,9 +4963,9 @@ int cmd_trace(int argc, const char **argv) goto init_augmented_syscall_tp; } - if (trace.syscalls.events.augmented->priv == NULL && + if (trace.syscalls.events.bpf_output->priv == NULL && strstr(evsel__name(evsel), "syscalls:sys_enter")) { - struct evsel *augmented = trace.syscalls.events.augmented; + struct evsel *augmented = trace.syscalls.events.bpf_output; if (evsel__init_augmented_syscall_tp(augmented, evsel) || evsel__init_augmented_syscall_tp_args(augmented)) goto out; @@ -5145,5 +5070,8 @@ out_close: fclose(trace.output); out: trace__exit(&trace); +#ifdef HAVE_BPF_SKEL + augmented_raw_syscalls_bpf__destroy(trace.skel); +#endif return err; } diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index a0f1d8adce60..4314c9197850 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -123,7 +123,7 @@ check () { shift - check_2 "tools/$file" "$file" $* + check_2 "tools/$file" "$file" "$@" } beauty_check () { @@ -131,7 +131,7 @@ beauty_check () { shift - check_2 "tools/perf/trace/beauty/$file" "$file" $* + check_2 "tools/perf/trace/beauty/$file" "$file" "$@" } # Check if we have the kernel headers (tools/perf/../../include), else @@ -183,7 +183,7 @@ done check_2 tools/perf/util/hashmap.h tools/lib/bpf/hashmap.h check_2 tools/perf/util/hashmap.c tools/lib/bpf/hashmap.c -cd tools/perf +cd tools/perf || exit if [ ${#FAILURES[@]} -gt 0 ] then diff --git a/tools/perf/dlfilters/dlfilter-test-api-v0.c b/tools/perf/dlfilters/dlfilter-test-api-v0.c index b1f51efd67d6..72f263d49121 100644 --- a/tools/perf/dlfilters/dlfilter-test-api-v0.c +++ b/tools/perf/dlfilters/dlfilter-test-api-v0.c @@ -254,6 +254,30 @@ static int check_addr_al(void *ctx) return 0; } +static int check_address_al(void *ctx, const struct perf_dlfilter_sample *sample) +{ + struct perf_dlfilter_al address_al; + const struct perf_dlfilter_al *al; + + al = perf_dlfilter_fns.resolve_ip(ctx); + if (!al) + return test_fail("resolve_ip() failed"); + + address_al.size = sizeof(address_al); + if (perf_dlfilter_fns.resolve_address(ctx, sample->ip, &address_al)) + return test_fail("resolve_address() failed"); + + CHECK(address_al.sym && al->sym); + CHECK(!strcmp(address_al.sym, al->sym)); + CHECK(address_al.addr == al->addr); + CHECK(address_al.sym_start == al->sym_start); + CHECK(address_al.sym_end == al->sym_end); + CHECK(address_al.dso && al->dso); + CHECK(!strcmp(address_al.dso, al->dso)); + + return 0; +} + static int check_attr(void *ctx) { struct perf_event_attr *attr = perf_dlfilter_fns.attr(ctx); @@ -290,7 +314,7 @@ static int do_checks(void *data, const struct perf_dlfilter_sample *sample, void if (early && !d->do_early) return 0; - if (check_al(ctx) || check_addr_al(ctx)) + if (check_al(ctx) || check_addr_al(ctx) || check_address_al(ctx, sample)) return -1; if (early) diff --git a/tools/perf/dlfilters/dlfilter-test-api-v2.c b/tools/perf/dlfilters/dlfilter-test-api-v2.c new file mode 100644 index 000000000000..38e593d92920 --- /dev/null +++ b/tools/perf/dlfilters/dlfilter-test-api-v2.c @@ -0,0 +1,377 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Test v2 API for perf --dlfilter shared object + * Copyright (c) 2023, Intel Corporation. + */ +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <stdbool.h> + +/* + * Copy v2 API instead of including current API + */ +#include <linux/perf_event.h> +#include <linux/types.h> + +/* + * The following macro can be used to determine if this header defines + * perf_dlfilter_sample machine_pid and vcpu. + */ +#define PERF_DLFILTER_HAS_MACHINE_PID + +/* Definitions for perf_dlfilter_sample flags */ +enum { + PERF_DLFILTER_FLAG_BRANCH = 1ULL << 0, + PERF_DLFILTER_FLAG_CALL = 1ULL << 1, + PERF_DLFILTER_FLAG_RETURN = 1ULL << 2, + PERF_DLFILTER_FLAG_CONDITIONAL = 1ULL << 3, + PERF_DLFILTER_FLAG_SYSCALLRET = 1ULL << 4, + PERF_DLFILTER_FLAG_ASYNC = 1ULL << 5, + PERF_DLFILTER_FLAG_INTERRUPT = 1ULL << 6, + PERF_DLFILTER_FLAG_TX_ABORT = 1ULL << 7, + PERF_DLFILTER_FLAG_TRACE_BEGIN = 1ULL << 8, + PERF_DLFILTER_FLAG_TRACE_END = 1ULL << 9, + PERF_DLFILTER_FLAG_IN_TX = 1ULL << 10, + PERF_DLFILTER_FLAG_VMENTRY = 1ULL << 11, + PERF_DLFILTER_FLAG_VMEXIT = 1ULL << 12, +}; + +/* + * perf sample event information (as per perf script and <linux/perf_event.h>) + */ +struct perf_dlfilter_sample { + __u32 size; /* Size of this structure (for compatibility checking) */ + __u16 ins_lat; /* Refer PERF_SAMPLE_WEIGHT_TYPE in <linux/perf_event.h> */ + __u16 p_stage_cyc; /* Refer PERF_SAMPLE_WEIGHT_TYPE in <linux/perf_event.h> */ + __u64 ip; + __s32 pid; + __s32 tid; + __u64 time; + __u64 addr; + __u64 id; + __u64 stream_id; + __u64 period; + __u64 weight; /* Refer PERF_SAMPLE_WEIGHT_TYPE in <linux/perf_event.h> */ + __u64 transaction; /* Refer PERF_SAMPLE_TRANSACTION in <linux/perf_event.h> */ + __u64 insn_cnt; /* For instructions-per-cycle (IPC) */ + __u64 cyc_cnt; /* For instructions-per-cycle (IPC) */ + __s32 cpu; + __u32 flags; /* Refer PERF_DLFILTER_FLAG_* above */ + __u64 data_src; /* Refer PERF_SAMPLE_DATA_SRC in <linux/perf_event.h> */ + __u64 phys_addr; /* Refer PERF_SAMPLE_PHYS_ADDR in <linux/perf_event.h> */ + __u64 data_page_size; /* Refer PERF_SAMPLE_DATA_PAGE_SIZE in <linux/perf_event.h> */ + __u64 code_page_size; /* Refer PERF_SAMPLE_CODE_PAGE_SIZE in <linux/perf_event.h> */ + __u64 cgroup; /* Refer PERF_SAMPLE_CGROUP in <linux/perf_event.h> */ + __u8 cpumode; /* Refer CPUMODE_MASK etc in <linux/perf_event.h> */ + __u8 addr_correlates_sym; /* True => resolve_addr() can be called */ + __u16 misc; /* Refer perf_event_header in <linux/perf_event.h> */ + __u32 raw_size; /* Refer PERF_SAMPLE_RAW in <linux/perf_event.h> */ + const void *raw_data; /* Refer PERF_SAMPLE_RAW in <linux/perf_event.h> */ + __u64 brstack_nr; /* Number of brstack entries */ + const struct perf_branch_entry *brstack; /* Refer <linux/perf_event.h> */ + __u64 raw_callchain_nr; /* Number of raw_callchain entries */ + const __u64 *raw_callchain; /* Refer <linux/perf_event.h> */ + const char *event; + __s32 machine_pid; + __s32 vcpu; +}; + +/* + * Address location (as per perf script) + */ +struct perf_dlfilter_al { + __u32 size; /* Size of this structure (for compatibility checking) */ + __u32 symoff; + const char *sym; + __u64 addr; /* Mapped address (from dso) */ + __u64 sym_start; + __u64 sym_end; + const char *dso; + __u8 sym_binding; /* STB_LOCAL, STB_GLOBAL or STB_WEAK, refer <elf.h> */ + __u8 is_64_bit; /* Only valid if dso is not NULL */ + __u8 is_kernel_ip; /* True if in kernel space */ + __u32 buildid_size; + __u8 *buildid; + /* Below members are only populated by resolve_ip() */ + __u8 filtered; /* True if this sample event will be filtered out */ + const char *comm; + void *priv; /* Private data (v2 API) */ +}; + +struct perf_dlfilter_fns { + /* Return information about ip */ + const struct perf_dlfilter_al *(*resolve_ip)(void *ctx); + /* Return information about addr (if addr_correlates_sym) */ + const struct perf_dlfilter_al *(*resolve_addr)(void *ctx); + /* Return arguments from --dlarg option */ + char **(*args)(void *ctx, int *dlargc); + /* + * Return information about address (al->size must be set before + * calling). Returns 0 on success, -1 otherwise. Call al_cleanup() + * when 'al' data is no longer needed. + */ + __s32 (*resolve_address)(void *ctx, __u64 address, struct perf_dlfilter_al *al); + /* Return instruction bytes and length */ + const __u8 *(*insn)(void *ctx, __u32 *length); + /* Return source file name and line number */ + const char *(*srcline)(void *ctx, __u32 *line_number); + /* Return perf_event_attr, refer <linux/perf_event.h> */ + struct perf_event_attr *(*attr)(void *ctx); + /* Read object code, return numbers of bytes read */ + __s32 (*object_code)(void *ctx, __u64 ip, void *buf, __u32 len); + /* + * If present (i.e. must check al_cleanup != NULL), call after + * resolve_address() to free any associated resources. (v2 API) + */ + void (*al_cleanup)(void *ctx, struct perf_dlfilter_al *al); + /* Reserved */ + void *(*reserved[119])(void *); +}; + +struct perf_dlfilter_fns perf_dlfilter_fns; + +static int verbose; + +#define pr_debug(fmt, ...) do { \ + if (verbose > 0) \ + fprintf(stderr, fmt, ##__VA_ARGS__); \ + } while (0) + +static int test_fail(const char *msg) +{ + pr_debug("%s\n", msg); + return -1; +} + +#define CHECK(x) do { \ + if (!(x)) \ + return test_fail("Check '" #x "' failed\n"); \ + } while (0) + +struct filter_data { + __u64 ip; + __u64 addr; + int do_early; + int early_filter_cnt; + int filter_cnt; +}; + +static struct filter_data *filt_dat; + +int start(void **data, void *ctx) +{ + int dlargc; + char **dlargv; + struct filter_data *d; + static bool called; + + verbose = 1; + + CHECK(!filt_dat && !called); + called = true; + + d = calloc(1, sizeof(*d)); + if (!d) + test_fail("Failed to allocate memory"); + filt_dat = d; + *data = d; + + dlargv = perf_dlfilter_fns.args(ctx, &dlargc); + + CHECK(dlargc == 6); + CHECK(!strcmp(dlargv[0], "first")); + verbose = strtol(dlargv[1], NULL, 0); + d->ip = strtoull(dlargv[2], NULL, 0); + d->addr = strtoull(dlargv[3], NULL, 0); + d->do_early = strtol(dlargv[4], NULL, 0); + CHECK(!strcmp(dlargv[5], "last")); + + pr_debug("%s API\n", __func__); + + return 0; +} + +#define CHECK_SAMPLE(x) do { \ + if (sample->x != expected.x) \ + return test_fail("'" #x "' not expected value\n"); \ + } while (0) + +static int check_sample(struct filter_data *d, const struct perf_dlfilter_sample *sample) +{ + struct perf_dlfilter_sample expected = { + .ip = d->ip, + .pid = 12345, + .tid = 12346, + .time = 1234567890, + .addr = d->addr, + .id = 99, + .stream_id = 101, + .period = 543212345, + .cpu = 31, + .cpumode = PERF_RECORD_MISC_USER, + .addr_correlates_sym = 1, + .misc = PERF_RECORD_MISC_USER, + }; + + CHECK(sample->size >= sizeof(struct perf_dlfilter_sample)); + + CHECK_SAMPLE(ip); + CHECK_SAMPLE(pid); + CHECK_SAMPLE(tid); + CHECK_SAMPLE(time); + CHECK_SAMPLE(addr); + CHECK_SAMPLE(id); + CHECK_SAMPLE(stream_id); + CHECK_SAMPLE(period); + CHECK_SAMPLE(cpu); + CHECK_SAMPLE(cpumode); + CHECK_SAMPLE(addr_correlates_sym); + CHECK_SAMPLE(misc); + + CHECK(!sample->raw_data); + CHECK_SAMPLE(brstack_nr); + CHECK(!sample->brstack); + CHECK_SAMPLE(raw_callchain_nr); + CHECK(!sample->raw_callchain); + +#define EVENT_NAME "branches:" + CHECK(!strncmp(sample->event, EVENT_NAME, strlen(EVENT_NAME))); + + return 0; +} + +static int check_al(void *ctx) +{ + const struct perf_dlfilter_al *al; + + al = perf_dlfilter_fns.resolve_ip(ctx); + if (!al) + return test_fail("resolve_ip() failed"); + + CHECK(al->sym && !strcmp("foo", al->sym)); + CHECK(!al->symoff); + + return 0; +} + +static int check_addr_al(void *ctx) +{ + const struct perf_dlfilter_al *addr_al; + + addr_al = perf_dlfilter_fns.resolve_addr(ctx); + if (!addr_al) + return test_fail("resolve_addr() failed"); + + CHECK(addr_al->sym && !strcmp("bar", addr_al->sym)); + CHECK(!addr_al->symoff); + + return 0; +} + +static int check_address_al(void *ctx, const struct perf_dlfilter_sample *sample) +{ + struct perf_dlfilter_al address_al; + const struct perf_dlfilter_al *al; + + al = perf_dlfilter_fns.resolve_ip(ctx); + if (!al) + return test_fail("resolve_ip() failed"); + + address_al.size = sizeof(address_al); + if (perf_dlfilter_fns.resolve_address(ctx, sample->ip, &address_al)) + return test_fail("resolve_address() failed"); + + CHECK(address_al.sym && al->sym); + CHECK(!strcmp(address_al.sym, al->sym)); + CHECK(address_al.addr == al->addr); + CHECK(address_al.sym_start == al->sym_start); + CHECK(address_al.sym_end == al->sym_end); + CHECK(address_al.dso && al->dso); + CHECK(!strcmp(address_al.dso, al->dso)); + + /* al_cleanup() is v2 API so may not be present */ + if (perf_dlfilter_fns.al_cleanup) + perf_dlfilter_fns.al_cleanup(ctx, &address_al); + + return 0; +} + +static int check_attr(void *ctx) +{ + struct perf_event_attr *attr = perf_dlfilter_fns.attr(ctx); + + CHECK(attr); + CHECK(attr->type == PERF_TYPE_HARDWARE); + CHECK(attr->config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS); + + return 0; +} + +static int do_checks(void *data, const struct perf_dlfilter_sample *sample, void *ctx, bool early) +{ + struct filter_data *d = data; + + CHECK(data && filt_dat == data); + + if (early) { + CHECK(!d->early_filter_cnt); + d->early_filter_cnt += 1; + } else { + CHECK(!d->filter_cnt); + CHECK(d->early_filter_cnt); + CHECK(d->do_early != 2); + d->filter_cnt += 1; + } + + if (check_sample(data, sample)) + return -1; + + if (check_attr(ctx)) + return -1; + + if (early && !d->do_early) + return 0; + + if (check_al(ctx) || check_addr_al(ctx) || check_address_al(ctx, sample)) + return -1; + + if (early) + return d->do_early == 2; + + return 1; +} + +int filter_event_early(void *data, const struct perf_dlfilter_sample *sample, void *ctx) +{ + pr_debug("%s API\n", __func__); + + return do_checks(data, sample, ctx, true); +} + +int filter_event(void *data, const struct perf_dlfilter_sample *sample, void *ctx) +{ + pr_debug("%s API\n", __func__); + + return do_checks(data, sample, ctx, false); +} + +int stop(void *data, void *ctx) +{ + static bool called; + + pr_debug("%s API\n", __func__); + + CHECK(data && filt_dat == data && !called); + called = true; + + free(data); + filt_dat = NULL; + return 0; +} + +const char *filter_description(const char **long_description) +{ + *long_description = "Filter used by the 'dlfilter C API' perf test"; + return "dlfilter to test v2 C API"; +} diff --git a/tools/perf/examples/bpf/5sec.c b/tools/perf/examples/bpf/5sec.c deleted file mode 100644 index 3bd7fc17631f..000000000000 --- a/tools/perf/examples/bpf/5sec.c +++ /dev/null @@ -1,53 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - Description: - - . Disable strace like syscall tracing (--no-syscalls), or try tracing - just some (-e *sleep). - - . Attach a filter function to a kernel function, returning when it should - be considered, i.e. appear on the output. - - . Run it system wide, so that any sleep of >= 5 seconds and < than 6 - seconds gets caught. - - . Ask for callgraphs using DWARF info, so that userspace can be unwound - - . While this is running, run something like "sleep 5s". - - . If we decide to add tv_nsec as well, then it becomes: - - int probe(hrtimer_nanosleep, rqtp->tv_sec rqtp->tv_nsec)(void *ctx, int err, long sec, long nsec) - - I.e. add where it comes from (rqtp->tv_nsec) and where it will be - accessible in the function body (nsec) - - # perf trace --no-syscalls -e tools/perf/examples/bpf/5sec.c/call-graph=dwarf/ - 0.000 perf_bpf_probe:func:(ffffffff9811b5f0) tv_sec=5 - hrtimer_nanosleep ([kernel.kallsyms]) - __x64_sys_nanosleep ([kernel.kallsyms]) - do_syscall_64 ([kernel.kallsyms]) - entry_SYSCALL_64 ([kernel.kallsyms]) - __GI___nanosleep (/usr/lib64/libc-2.26.so) - rpl_nanosleep (/usr/bin/sleep) - xnanosleep (/usr/bin/sleep) - main (/usr/bin/sleep) - __libc_start_main (/usr/lib64/libc-2.26.so) - _start (/usr/bin/sleep) - ^C# - - Copyright (C) 2018 Red Hat, Inc., Arnaldo Carvalho de Melo <acme@redhat.com> -*/ - -#include <linux/bpf.h> -#include <bpf/bpf_helpers.h> - -#define NSEC_PER_SEC 1000000000L - -SEC("hrtimer_nanosleep=hrtimer_nanosleep rqtp") -int hrtimer_nanosleep(void *ctx, int err, long long sec) -{ - return sec / NSEC_PER_SEC == 5ULL; -} - -char _license[] SEC("license") = "GPL"; diff --git a/tools/perf/examples/bpf/hello.c b/tools/perf/examples/bpf/hello.c deleted file mode 100644 index e9080b0df158..000000000000 --- a/tools/perf/examples/bpf/hello.c +++ /dev/null @@ -1,27 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <linux/bpf.h> -#include <bpf/bpf_helpers.h> - -struct __bpf_stdout__ { - __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); - __type(key, int); - __type(value, __u32); - __uint(max_entries, __NR_CPUS__); -} __bpf_stdout__ SEC(".maps"); - -#define puts(from) \ - ({ const int __len = sizeof(from); \ - char __from[sizeof(from)] = from; \ - bpf_perf_event_output(args, &__bpf_stdout__, BPF_F_CURRENT_CPU, \ - &__from, __len & (sizeof(from) - 1)); }) - -struct syscall_enter_args; - -SEC("raw_syscalls:sys_enter") -int sys_enter(struct syscall_enter_args *args) -{ - puts("Hello, world\n"); - return 0; -} - -char _license[] SEC("license") = "GPL"; diff --git a/tools/perf/examples/bpf/sys_enter_openat.c b/tools/perf/examples/bpf/sys_enter_openat.c deleted file mode 100644 index c4481c390d23..000000000000 --- a/tools/perf/examples/bpf/sys_enter_openat.c +++ /dev/null @@ -1,33 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Hook into 'openat' syscall entry tracepoint - * - * Test it with: - * - * perf trace -e tools/perf/examples/bpf/sys_enter_openat.c cat /etc/passwd > /dev/null - * - * It'll catch some openat syscalls related to the dynamic linked and - * the last one should be the one for '/etc/passwd'. - * - * The syscall_enter_openat_args can be used to get the syscall fields - * and use them for filtering calls, i.e. use in expressions for - * the return value. - */ - -#include <bpf/bpf.h> - -struct syscall_enter_openat_args { - unsigned long long unused; - long syscall_nr; - long dfd; - char *filename_ptr; - long flags; - long mode; -}; - -int syscall_enter(openat)(struct syscall_enter_openat_args *args) -{ - return 1; -} - -license(GPL); diff --git a/tools/perf/include/perf/perf_dlfilter.h b/tools/perf/include/perf/perf_dlfilter.h index a26e2f129f83..16fc4568ac53 100644 --- a/tools/perf/include/perf/perf_dlfilter.h +++ b/tools/perf/include/perf/perf_dlfilter.h @@ -91,6 +91,7 @@ struct perf_dlfilter_al { /* Below members are only populated by resolve_ip() */ __u8 filtered; /* True if this sample event will be filtered out */ const char *comm; + void *priv; /* Private data. Do not change */ }; struct perf_dlfilter_fns { @@ -102,7 +103,8 @@ struct perf_dlfilter_fns { char **(*args)(void *ctx, int *dlargc); /* * Return information about address (al->size must be set before - * calling). Returns 0 on success, -1 otherwise. + * calling). Returns 0 on success, -1 otherwise. Call al_cleanup() + * when 'al' data is no longer needed. */ __s32 (*resolve_address)(void *ctx, __u64 address, struct perf_dlfilter_al *al); /* Return instruction bytes and length */ @@ -113,8 +115,13 @@ struct perf_dlfilter_fns { struct perf_event_attr *(*attr)(void *ctx); /* Read object code, return numbers of bytes read */ __s32 (*object_code)(void *ctx, __u64 ip, void *buf, __u32 len); + /* + * If present (i.e. must check al_cleanup != NULL), call after + * resolve_address() to free any associated resources. + */ + void (*al_cleanup)(void *ctx, struct perf_dlfilter_al *al); /* Reserved */ - void *(*reserved[120])(void *); + void *(*reserved[119])(void *); }; /* diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 38cae4721583..d3fc8090413c 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -18,7 +18,6 @@ #include <subcmd/run-command.h> #include "util/parse-events.h" #include <subcmd/parse-options.h> -#include "util/bpf-loader.h" #include "util/debug.h" #include "util/event.h" #include "util/util.h" // usage() @@ -324,7 +323,6 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv) perf_config__exit(); exit_browser(status); perf_env__exit(&perf_env); - bpf__clear(); if (status) return status & 0xff; diff --git a/tools/perf/pmu-events/Build b/tools/perf/pmu-events/Build index 150765f2baee..1d18bb89402e 100644 --- a/tools/perf/pmu-events/Build +++ b/tools/perf/pmu-events/Build @@ -35,3 +35,9 @@ $(PMU_EVENTS_C): $(JSON) $(JSON_TEST) $(JEVENTS_PY) $(METRIC_PY) $(METRIC_TEST_L $(call rule_mkdir) $(Q)$(call echo-cmd,gen)$(PYTHON) $(JEVENTS_PY) $(JEVENTS_ARCH) $(JEVENTS_MODEL) pmu-events/arch $@ endif + +# pmu-events.c file is generated in the OUTPUT directory so it needs a +# separate rule to depend on it properly +$(OUTPUT)pmu-events/pmu-events.o: $(PMU_EVENTS_C) + $(call rule_mkdir) + $(call if_changed_dep,cc_o_c) diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/cache.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/cache.json index fc0633054211..7a2b7b200f14 100644 --- a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/cache.json +++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/cache.json @@ -93,9 +93,6 @@ "ArchStdEvent": "L1D_CACHE_LMISS_RD" }, { - "ArchStdEvent": "L1D_CACHE_LMISS" - }, - { "ArchStdEvent": "L1I_CACHE_LMISS" }, { diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/core-imp-def.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/core-imp-def.json index 95c30243f2b2..88b23b85e33c 100644 --- a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/core-imp-def.json +++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/core-imp-def.json @@ -534,66 +534,6 @@ "BriefDescription": "L2D OTB allocate" }, { - "PublicDescription": "DTLB Translation cache hit on S1L2 walk cache entry", - "EventCode": "0xD801", - "EventName": "MMU_D_TRANS_CACHE_HIT_S1L2_WALK", - "BriefDescription": "DTLB Translation cache hit on S1L2 walk cache entry" - }, - { - "PublicDescription": "DTLB Translation cache hit on S1L1 walk cache entry", - "EventCode": "0xD802", - "EventName": "MMU_D_TRANS_CACHE_HIT_S1L1_WALK", - "BriefDescription": "DTLB Translation cache hit on S1L1 walk cache entry" - }, - { - "PublicDescription": "DTLB Translation cache hit on S1L0 walk cache entry", - "EventCode": "0xD803", - "EventName": "MMU_D_TRANS_CACHE_HIT_S1L0_WALK", - "BriefDescription": "DTLB Translation cache hit on S1L0 walk cache entry" - }, - { - "PublicDescription": "DTLB Translation cache hit on S2L2 walk cache entry", - "EventCode": "0xD804", - "EventName": "MMU_D_TRANS_CACHE_HIT_S2L2_WALK", - "BriefDescription": "DTLB Translation cache hit on S2L2 walk cache entry" - }, - { - "PublicDescription": "DTLB Translation cache hit on S2L1 walk cache entry", - "EventCode": "0xD805", - "EventName": "MMU_D_TRANS_CACHE_HIT_S2L1_WALK", - "BriefDescription": "DTLB Translation cache hit on S2L1 walk cache entry" - }, - { - "PublicDescription": "DTLB Translation cache hit on S2L0 walk cache entry", - "EventCode": "0xD806", - "EventName": "MMU_D_TRANS_CACHE_HIT_S2L0_WALK", - "BriefDescription": "DTLB Translation cache hit on S2L0 walk cache entry" - }, - { - "PublicDescription": "D-side S1 Page walk cache lookup", - "EventCode": "0xD807", - "EventName": "MMU_D_S1_WALK_CACHE_LOOKUP", - "BriefDescription": "D-side S1 Page walk cache lookup" - }, - { - "PublicDescription": "D-side S1 Page walk cache refill", - "EventCode": "0xD808", - "EventName": "MMU_D_S1_WALK_CACHE_REFILL", - "BriefDescription": "D-side S1 Page walk cache refill" - }, - { - "PublicDescription": "D-side S2 Page walk cache lookup", - "EventCode": "0xD809", - "EventName": "MMU_D_S2_WALK_CACHE_LOOKUP", - "BriefDescription": "D-side S2 Page walk cache lookup" - }, - { - "PublicDescription": "D-side S2 Page walk cache refill", - "EventCode": "0xD80A", - "EventName": "MMU_D_S2_WALK_CACHE_REFILL", - "BriefDescription": "D-side S2 Page walk cache refill" - }, - { "PublicDescription": "D-side Stage1 tablewalk fault", "EventCode": "0xD80B", "EventName": "MMU_D_S1_WALK_FAULT", @@ -618,66 +558,6 @@ "BriefDescription": "L2I OTB allocate" }, { - "PublicDescription": "ITLB Translation cache hit on S1L2 walk cache entry", - "EventCode": "0xD901", - "EventName": "MMU_I_TRANS_CACHE_HIT_S1L2_WALK", - "BriefDescription": "ITLB Translation cache hit on S1L2 walk cache entry" - }, - { - "PublicDescription": "ITLB Translation cache hit on S1L1 walk cache entry", - "EventCode": "0xD902", - "EventName": "MMU_I_TRANS_CACHE_HIT_S1L1_WALK", - "BriefDescription": "ITLB Translation cache hit on S1L1 walk cache entry" - }, - { - "PublicDescription": "ITLB Translation cache hit on S1L0 walk cache entry", - "EventCode": "0xD903", - "EventName": "MMU_I_TRANS_CACHE_HIT_S1L0_WALK", - "BriefDescription": "ITLB Translation cache hit on S1L0 walk cache entry" - }, - { - "PublicDescription": "ITLB Translation cache hit on S2L2 walk cache entry", - "EventCode": "0xD904", - "EventName": "MMU_I_TRANS_CACHE_HIT_S2L2_WALK", - "BriefDescription": "ITLB Translation cache hit on S2L2 walk cache entry" - }, - { - "PublicDescription": "ITLB Translation cache hit on S2L1 walk cache entry", - "EventCode": "0xD905", - "EventName": "MMU_I_TRANS_CACHE_HIT_S2L1_WALK", - "BriefDescription": "ITLB Translation cache hit on S2L1 walk cache entry" - }, - { - "PublicDescription": "ITLB Translation cache hit on S2L0 walk cache entry", - "EventCode": "0xD906", - "EventName": "MMU_I_TRANS_CACHE_HIT_S2L0_WALK", - "BriefDescription": "ITLB Translation cache hit on S2L0 walk cache entry" - }, - { - "PublicDescription": "I-side S1 Page walk cache lookup", - "EventCode": "0xD907", - "EventName": "MMU_I_S1_WALK_CACHE_LOOKUP", - "BriefDescription": "I-side S1 Page walk cache lookup" - }, - { - "PublicDescription": "I-side S1 Page walk cache refill", - "EventCode": "0xD908", - "EventName": "MMU_I_S1_WALK_CACHE_REFILL", - "BriefDescription": "I-side S1 Page walk cache refill" - }, - { - "PublicDescription": "I-side S2 Page walk cache lookup", - "EventCode": "0xD909", - "EventName": "MMU_I_S2_WALK_CACHE_LOOKUP", - "BriefDescription": "I-side S2 Page walk cache lookup" - }, - { - "PublicDescription": "I-side S2 Page walk cache refill", - "EventCode": "0xD90A", - "EventName": "MMU_I_S2_WALK_CACHE_REFILL", - "BriefDescription": "I-side S2 Page walk cache refill" - }, - { "PublicDescription": "I-side Stage1 tablewalk fault", "EventCode": "0xD90B", "EventName": "MMU_I_S1_WALK_FAULT", diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/metrics.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/metrics.json new file mode 100644 index 000000000000..1e7e8901a445 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/metrics.json @@ -0,0 +1,362 @@ +[ + { + "MetricExpr": "BR_MIS_PRED / BR_PRED", + "BriefDescription": "Branch predictor misprediction rate. May not count branches that are never resolved because they are in the misprediction shadow of an earlier branch", + "MetricGroup": "Branch Prediction", + "MetricName": "Misprediction" + }, + { + "MetricExpr": "BR_MIS_PRED_RETIRED / BR_RETIRED", + "BriefDescription": "Branch predictor misprediction rate", + "MetricGroup": "Branch Prediction", + "MetricName": "Misprediction (retired)" + }, + { + "MetricExpr": "BUS_ACCESS / ( BUS_CYCLES * 1)", + "BriefDescription": "Core-to-uncore bus utilization", + "MetricGroup": "Bus", + "MetricName": "Bus utilization" + }, + { + "MetricExpr": "L1D_CACHE_REFILL / L1D_CACHE", + "BriefDescription": "L1D cache miss rate", + "MetricGroup": "Cache", + "MetricName": "L1D cache miss" + }, + { + "MetricExpr": "L1D_CACHE_LMISS_RD / L1D_CACHE_RD", + "BriefDescription": "L1D cache read miss rate", + "MetricGroup": "Cache", + "MetricName": "L1D cache read miss" + }, + { + "MetricExpr": "L1I_CACHE_REFILL / L1I_CACHE", + "BriefDescription": "L1I cache miss rate", + "MetricGroup": "Cache", + "MetricName": "L1I cache miss" + }, + { + "MetricExpr": "L2D_CACHE_REFILL / L2D_CACHE", + "BriefDescription": "L2 cache miss rate", + "MetricGroup": "Cache", + "MetricName": "L2 cache miss" + }, + { + "MetricExpr": "L1I_CACHE_LMISS / L1I_CACHE", + "BriefDescription": "L1I cache read miss rate", + "MetricGroup": "Cache", + "MetricName": "L1I cache read miss" + }, + { + "MetricExpr": "L2D_CACHE_LMISS_RD / L2D_CACHE_RD", + "BriefDescription": "L2 cache read miss rate", + "MetricGroup": "Cache", + "MetricName": "L2 cache read miss" + }, + { + "MetricExpr": "(L1D_CACHE_LMISS_RD * 1000) / INST_RETIRED", + "BriefDescription": "Misses per thousand instructions (data)", + "MetricGroup": "Cache", + "MetricName": "MPKI data" + }, + { + "MetricExpr": "(L1I_CACHE_LMISS * 1000) / INST_RETIRED", + "BriefDescription": "Misses per thousand instructions (instruction)", + "MetricGroup": "Cache", + "MetricName": "MPKI instruction" + }, + { + "MetricExpr": "ASE_SPEC / OP_SPEC", + "BriefDescription": "Proportion of advanced SIMD data processing operations (excluding DP_SPEC/LD_SPEC) operations", + "MetricGroup": "Instruction", + "MetricName": "ASE mix" + }, + { + "MetricExpr": "CRYPTO_SPEC / OP_SPEC", + "BriefDescription": "Proportion of crypto data processing operations", + "MetricGroup": "Instruction", + "MetricName": "Crypto mix" + }, + { + "MetricExpr": "VFP_SPEC / (duration_time *1000000000)", + "BriefDescription": "Giga-floating point operations per second", + "MetricGroup": "Instruction", + "MetricName": "GFLOPS_ISSUED" + }, + { + "MetricExpr": "DP_SPEC / OP_SPEC", + "BriefDescription": "Proportion of integer data processing operations", + "MetricGroup": "Instruction", + "MetricName": "Integer mix" + }, + { + "MetricExpr": "INST_RETIRED / CPU_CYCLES", + "BriefDescription": "Instructions per cycle", + "MetricGroup": "Instruction", + "MetricName": "IPC" + }, + { + "MetricExpr": "LD_SPEC / OP_SPEC", + "BriefDescription": "Proportion of load operations", + "MetricGroup": "Instruction", + "MetricName": "Load mix" + }, + { + "MetricExpr": "LDST_SPEC/ OP_SPEC", + "BriefDescription": "Proportion of load & store operations", + "MetricGroup": "Instruction", + "MetricName": "Load-store mix" + }, + { + "MetricExpr": "INST_RETIRED / (duration_time * 1000000)", + "BriefDescription": "Millions of instructions per second", + "MetricGroup": "Instruction", + "MetricName": "MIPS_RETIRED" + }, + { + "MetricExpr": "INST_SPEC / (duration_time * 1000000)", + "BriefDescription": "Millions of instructions per second", + "MetricGroup": "Instruction", + "MetricName": "MIPS_UTILIZATION" + }, + { + "MetricExpr": "PC_WRITE_SPEC / OP_SPEC", + "BriefDescription": "Proportion of software change of PC operations", + "MetricGroup": "Instruction", + "MetricName": "PC write mix" + }, + { + "MetricExpr": "ST_SPEC / OP_SPEC", + "BriefDescription": "Proportion of store operations", + "MetricGroup": "Instruction", + "MetricName": "Store mix" + }, + { + "MetricExpr": "VFP_SPEC / OP_SPEC", + "BriefDescription": "Proportion of FP operations", + "MetricGroup": "Instruction", + "MetricName": "VFP mix" + }, + { + "MetricExpr": "1 - (OP_RETIRED/ (CPU_CYCLES * 4))", + "BriefDescription": "Proportion of slots lost", + "MetricGroup": "Speculation / TDA", + "MetricName": "CPU lost" + }, + { + "MetricExpr": "OP_RETIRED/ (CPU_CYCLES * 4)", + "BriefDescription": "Proportion of slots retiring", + "MetricGroup": "Speculation / TDA", + "MetricName": "CPU utilization" + }, + { + "MetricExpr": "OP_RETIRED - OP_SPEC", + "BriefDescription": "Operations lost due to misspeculation", + "MetricGroup": "Speculation / TDA", + "MetricName": "Operations lost" + }, + { + "MetricExpr": "1 - (OP_RETIRED / OP_SPEC)", + "BriefDescription": "Proportion of operations lost", + "MetricGroup": "Speculation / TDA", + "MetricName": "Operations lost (ratio)" + }, + { + "MetricExpr": "OP_RETIRED / OP_SPEC", + "BriefDescription": "Proportion of operations retired", + "MetricGroup": "Speculation / TDA", + "MetricName": "Operations retired" + }, + { + "MetricExpr": "STALL_BACKEND_CACHE / CPU_CYCLES", + "BriefDescription": "Proportion of cycles stalled and no operations issued to backend and cache miss", + "MetricGroup": "Stall", + "MetricName": "Stall backend cache cycles" + }, + { + "MetricExpr": "STALL_BACKEND_RESOURCE / CPU_CYCLES", + "BriefDescription": "Proportion of cycles stalled and no operations issued to backend and resource full", + "MetricGroup": "Stall", + "MetricName": "Stall backend resource cycles" + }, + { + "MetricExpr": "STALL_BACKEND_TLB / CPU_CYCLES", + "BriefDescription": "Proportion of cycles stalled and no operations issued to backend and TLB miss", + "MetricGroup": "Stall", + "MetricName": "Stall backend tlb cycles" + }, + { + "MetricExpr": "STALL_FRONTEND_CACHE / CPU_CYCLES", + "BriefDescription": "Proportion of cycles stalled and no ops delivered from frontend and cache miss", + "MetricGroup": "Stall", + "MetricName": "Stall frontend cache cycles" + }, + { + "MetricExpr": "STALL_FRONTEND_TLB / CPU_CYCLES", + "BriefDescription": "Proportion of cycles stalled and no ops delivered from frontend and TLB miss", + "MetricGroup": "Stall", + "MetricName": "Stall frontend tlb cycles" + }, + { + "MetricExpr": "DTLB_WALK / L1D_TLB", + "BriefDescription": "D-side walk per d-side translation request", + "MetricGroup": "TLB", + "MetricName": "DTLB walks" + }, + { + "MetricExpr": "ITLB_WALK / L1I_TLB", + "BriefDescription": "I-side walk per i-side translation request", + "MetricGroup": "TLB", + "MetricName": "ITLB walks" + }, + { + "MetricExpr": "STALL_SLOT_BACKEND / (CPU_CYCLES * 4)", + "BriefDescription": "Fraction of slots backend bound", + "MetricGroup": "TopDownL1", + "MetricName": "backend" + }, + { + "MetricExpr": "1 - (retiring + lost + backend)", + "BriefDescription": "Fraction of slots frontend bound", + "MetricGroup": "TopDownL1", + "MetricName": "frontend" + }, + { + "MetricExpr": "((OP_SPEC - OP_RETIRED) / (CPU_CYCLES * 4))", + "BriefDescription": "Fraction of slots lost due to misspeculation", + "MetricGroup": "TopDownL1", + "MetricName": "lost" + }, + { + "MetricExpr": "(OP_RETIRED / (CPU_CYCLES * 4))", + "BriefDescription": "Fraction of slots retiring, useful work", + "MetricGroup": "TopDownL1", + "MetricName": "retiring" + }, + { + "MetricExpr": "backend - backend_memory", + "BriefDescription": "Fraction of slots the CPU was stalled due to backend non-memory subsystem issues", + "MetricGroup": "TopDownL2", + "MetricName": "backend_core" + }, + { + "MetricExpr": "(STALL_BACKEND_TLB + STALL_BACKEND_CACHE + STALL_BACKEND_MEM) / CPU_CYCLES ", + "BriefDescription": "Fraction of slots the CPU was stalled due to backend memory subsystem issues (cache/tlb miss)", + "MetricGroup": "TopDownL2", + "MetricName": "backend_memory" + }, + { + "MetricExpr": " (BR_MIS_PRED_RETIRED / GPC_FLUSH) * lost", + "BriefDescription": "Fraction of slots lost due to branch misprediciton", + "MetricGroup": "TopDownL2", + "MetricName": "branch_mispredict" + }, + { + "MetricExpr": "frontend - frontend_latency", + "BriefDescription": "Fraction of slots the CPU did not dispatch at full bandwidth - able to dispatch partial slots only (1, 2, or 3 uops)", + "MetricGroup": "TopDownL2", + "MetricName": "frontend_bandwidth" + }, + { + "MetricExpr": "(STALL_FRONTEND - ((STALL_SLOT_FRONTEND - (frontend * CPU_CYCLES * 4)) / 4)) / CPU_CYCLES", + "BriefDescription": "Fraction of slots the CPU was stalled due to frontend latency issues (cache/tlb miss); nothing to dispatch", + "MetricGroup": "TopDownL2", + "MetricName": "frontend_latency" + }, + { + "MetricExpr": "lost - branch_mispredict", + "BriefDescription": "Fraction of slots lost due to other/non-branch misprediction misspeculation", + "MetricGroup": "TopDownL2", + "MetricName": "other_clears" + }, + { + "MetricExpr": "(IXU_NUM_UOPS_ISSUED + FSU_ISSUED) / (CPU_CYCLES * 6)", + "BriefDescription": "Fraction of execute slots utilized", + "MetricGroup": "TopDownL2", + "MetricName": "pipe_utilization" + }, + { + "MetricExpr": "STALL_BACKEND_MEM / CPU_CYCLES", + "BriefDescription": "Fraction of cycles the CPU was stalled due to data L2 cache miss", + "MetricGroup": "TopDownL3", + "MetricName": "d_cache_l2_miss" + }, + { + "MetricExpr": "STALL_BACKEND_CACHE / CPU_CYCLES", + "BriefDescription": "Fraction of cycles the CPU was stalled due to data cache miss", + "MetricGroup": "TopDownL3", + "MetricName": "d_cache_miss" + }, + { + "MetricExpr": "STALL_BACKEND_TLB / CPU_CYCLES", + "BriefDescription": "Fraction of cycles the CPU was stalled due to data TLB miss", + "MetricGroup": "TopDownL3", + "MetricName": "d_tlb_miss" + }, + { + "MetricExpr": "FSU_ISSUED / (CPU_CYCLES * 2)", + "BriefDescription": "Fraction of FSU execute slots utilized", + "MetricGroup": "TopDownL3", + "MetricName": "fsu_pipe_utilization" + }, + { + "MetricExpr": "STALL_FRONTEND_CACHE / CPU_CYCLES", + "BriefDescription": "Fraction of cycles the CPU was stalled due to instruction cache miss", + "MetricGroup": "TopDownL3", + "MetricName": "i_cache_miss" + }, + { + "MetricExpr": " STALL_FRONTEND_TLB / CPU_CYCLES ", + "BriefDescription": "Fraction of cycles the CPU was stalled due to instruction TLB miss", + "MetricGroup": "TopDownL3", + "MetricName": "i_tlb_miss" + }, + { + "MetricExpr": "IXU_NUM_UOPS_ISSUED / (CPU_CYCLES / 4)", + "BriefDescription": "Fraction of IXU execute slots utilized", + "MetricGroup": "TopDownL3", + "MetricName": "ixu_pipe_utilization" + }, + { + "MetricExpr": "IDR_STALL_FLUSH / CPU_CYCLES", + "BriefDescription": "Fraction of cycles the CPU was stalled due to flush recovery", + "MetricGroup": "TopDownL3", + "MetricName": "recovery" + }, + { + "MetricExpr": "STALL_BACKEND_RESOURCE / CPU_CYCLES", + "BriefDescription": "Fraction of cycles the CPU was stalled due to core resource shortage", + "MetricGroup": "TopDownL3", + "MetricName": "resource" + }, + { + "MetricExpr": "IDR_STALL_FSU_SCHED / CPU_CYCLES ", + "BriefDescription": "Fraction of cycles the CPU was stalled and FSU was full", + "MetricGroup": "TopDownL4", + "MetricName": "stall_fsu_sched" + }, + { + "MetricExpr": "IDR_STALL_IXU_SCHED / CPU_CYCLES ", + "BriefDescription": "Fraction of cycles the CPU was stalled and IXU was full", + "MetricGroup": "TopDownL4", + "MetricName": "stall_ixu_sched" + }, + { + "MetricExpr": "IDR_STALL_LOB_ID / CPU_CYCLES ", + "BriefDescription": "Fraction of cycles the CPU was stalled and LOB was full", + "MetricGroup": "TopDownL4", + "MetricName": "stall_lob_id" + }, + { + "MetricExpr": "IDR_STALL_ROB_ID / CPU_CYCLES", + "BriefDescription": "Fraction of cycles the CPU was stalled and ROB was full", + "MetricGroup": "TopDownL4", + "MetricName": "stall_rob_id" + }, + { + "MetricExpr": "IDR_STALL_SOB_ID / CPU_CYCLES ", + "BriefDescription": "Fraction of cycles the CPU was stalled and SOB was full", + "MetricGroup": "TopDownL4", + "MetricName": "stall_sob_id" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/pipeline.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/pipeline.json index f9fae15f7555..711028377f3e 100644 --- a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/pipeline.json +++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/pipeline.json @@ -1,18 +1,24 @@ [ { - "ArchStdEvent": "STALL_FRONTEND" + "ArchStdEvent": "STALL_FRONTEND", + "Errata": "Errata AC03_CPU_29", + "BriefDescription": "Impacted by errata, use metrics instead -" }, { "ArchStdEvent": "STALL_BACKEND" }, { - "ArchStdEvent": "STALL" + "ArchStdEvent": "STALL", + "Errata": "Errata AC03_CPU_29", + "BriefDescription": "Impacted by errata, use metrics instead -" }, { "ArchStdEvent": "STALL_SLOT_BACKEND" }, { - "ArchStdEvent": "STALL_SLOT_FRONTEND" + "ArchStdEvent": "STALL_SLOT_FRONTEND", + "Errata": "Errata AC03_CPU_29", + "BriefDescription": "Impacted by errata, use metrics instead -" }, { "ArchStdEvent": "STALL_SLOT" diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/branch.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/branch.json deleted file mode 100644 index 79f2016c53b0..000000000000 --- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/branch.json +++ /dev/null @@ -1,8 +0,0 @@ -[ - { - "ArchStdEvent": "BR_MIS_PRED" - }, - { - "ArchStdEvent": "BR_PRED" - } -] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/bus.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/bus.json index 579c1c993d17..2e11a8c4a484 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/bus.json +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/bus.json @@ -1,20 +1,18 @@ [ { - "ArchStdEvent": "CPU_CYCLES" + "ArchStdEvent": "BUS_ACCESS", + "PublicDescription": "Counts memory transactions issued by the CPU to the external bus, including snoop requests and snoop responses. Each beat of data is counted individually." }, { - "ArchStdEvent": "BUS_ACCESS" + "ArchStdEvent": "BUS_CYCLES", + "PublicDescription": "Counts bus cycles in the CPU. Bus cycles represent a clock cycle in which a transaction could be sent or received on the interface from the CPU to the external bus. Since that interface is driven at the same clock speed as the CPU, this event is a duplicate of CPU_CYCLES." }, { - "ArchStdEvent": "BUS_CYCLES" + "ArchStdEvent": "BUS_ACCESS_RD", + "PublicDescription": "Counts memory read transactions seen on the external bus. Each beat of data is counted individually." }, { - "ArchStdEvent": "BUS_ACCESS_RD" - }, - { - "ArchStdEvent": "BUS_ACCESS_WR" - }, - { - "ArchStdEvent": "CNT_CYCLES" + "ArchStdEvent": "BUS_ACCESS_WR", + "PublicDescription": "Counts memory write transactions seen on the external bus. Each beat of data is counted individually." } ] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/cache.json deleted file mode 100644 index 0141f749bff3..000000000000 --- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/cache.json +++ /dev/null @@ -1,155 +0,0 @@ -[ - { - "ArchStdEvent": "L1I_CACHE_REFILL" - }, - { - "ArchStdEvent": "L1I_TLB_REFILL" - }, - { - "ArchStdEvent": "L1D_CACHE_REFILL" - }, - { - "ArchStdEvent": "L1D_CACHE" - }, - { - "ArchStdEvent": "L1D_TLB_REFILL" - }, - { - "ArchStdEvent": "L1I_CACHE" - }, - { - "ArchStdEvent": "L1D_CACHE_WB" - }, - { - "ArchStdEvent": "L2D_CACHE" - }, - { - "ArchStdEvent": "L2D_CACHE_REFILL" - }, - { - "ArchStdEvent": "L2D_CACHE_WB" - }, - { - "ArchStdEvent": "L2D_CACHE_ALLOCATE" - }, - { - "ArchStdEvent": "L1D_TLB" - }, - { - "ArchStdEvent": "L1I_TLB" - }, - { - "ArchStdEvent": "L3D_CACHE_ALLOCATE" - }, - { - "ArchStdEvent": "L3D_CACHE_REFILL" - }, - { - "ArchStdEvent": "L3D_CACHE" - }, - { - "ArchStdEvent": "L2D_TLB_REFILL" - }, - { - "ArchStdEvent": "L2D_TLB" - }, - { - "ArchStdEvent": "DTLB_WALK" - }, - { - "ArchStdEvent": "ITLB_WALK" - }, - { - "ArchStdEvent": "LL_CACHE_RD" - }, - { - "ArchStdEvent": "LL_CACHE_MISS_RD" - }, - { - "ArchStdEvent": "L1D_CACHE_LMISS_RD" - }, - { - "ArchStdEvent": "L1D_CACHE_RD" - }, - { - "ArchStdEvent": "L1D_CACHE_WR" - }, - { - "ArchStdEvent": "L1D_CACHE_REFILL_RD" - }, - { - "ArchStdEvent": "L1D_CACHE_REFILL_WR" - }, - { - "ArchStdEvent": "L1D_CACHE_REFILL_INNER" - }, - { - "ArchStdEvent": "L1D_CACHE_REFILL_OUTER" - }, - { - "ArchStdEvent": "L1D_CACHE_WB_VICTIM" - }, - { - "ArchStdEvent": "L1D_CACHE_WB_CLEAN" - }, - { - "ArchStdEvent": "L1D_CACHE_INVAL" - }, - { - "ArchStdEvent": "L1D_TLB_REFILL_RD" - }, - { - "ArchStdEvent": "L1D_TLB_REFILL_WR" - }, - { - "ArchStdEvent": "L1D_TLB_RD" - }, - { - "ArchStdEvent": "L1D_TLB_WR" - }, - { - "ArchStdEvent": "L2D_CACHE_RD" - }, - { - "ArchStdEvent": "L2D_CACHE_WR" - }, - { - "ArchStdEvent": "L2D_CACHE_REFILL_RD" - }, - { - "ArchStdEvent": "L2D_CACHE_REFILL_WR" - }, - { - "ArchStdEvent": "L2D_CACHE_WB_VICTIM" - }, - { - "ArchStdEvent": "L2D_CACHE_WB_CLEAN" - }, - { - "ArchStdEvent": "L2D_CACHE_INVAL" - }, - { - "ArchStdEvent": "L2D_TLB_REFILL_RD" - }, - { - "ArchStdEvent": "L2D_TLB_REFILL_WR" - }, - { - "ArchStdEvent": "L2D_TLB_RD" - }, - { - "ArchStdEvent": "L2D_TLB_WR" - }, - { - "ArchStdEvent": "L3D_CACHE_RD" - }, - { - "ArchStdEvent": "L1I_CACHE_LMISS" - }, - { - "ArchStdEvent": "L2D_CACHE_LMISS_RD" - }, - { - "ArchStdEvent": "L3D_CACHE_LMISS_RD" - } -] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/exception.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/exception.json index 344a2d552ad5..4404b8e91690 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/exception.json +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/exception.json @@ -1,47 +1,62 @@ [ { - "ArchStdEvent": "EXC_TAKEN" + "ArchStdEvent": "EXC_TAKEN", + "PublicDescription": "Counts any taken architecturally visible exceptions such as IRQ, FIQ, SError, and other synchronous exceptions. Exceptions are counted whether or not they are taken locally." }, { - "ArchStdEvent": "MEMORY_ERROR" + "ArchStdEvent": "EXC_RETURN", + "PublicDescription": "Counts any architecturally executed exception return instructions. Eg: AArch64: ERET" }, { - "ArchStdEvent": "EXC_UNDEF" + "ArchStdEvent": "EXC_UNDEF", + "PublicDescription": "Counts the number of synchronous exceptions which are taken locally that are due to attempting to execute an instruction that is UNDEFINED. Attempting to execute instruction bit patterns that have not been allocated. Attempting to execute instructions when they are disabled. Attempting to execute instructions at an inappropriate Exception level. Attempting to execute an instruction when the value of PSTATE.IL is 1." }, { - "ArchStdEvent": "EXC_SVC" + "ArchStdEvent": "EXC_SVC", + "PublicDescription": "Counts SVC exceptions taken locally." }, { - "ArchStdEvent": "EXC_PABORT" + "ArchStdEvent": "EXC_PABORT", + "PublicDescription": "Counts synchronous exceptions that are taken locally and caused by Instruction Aborts." }, { - "ArchStdEvent": "EXC_DABORT" + "ArchStdEvent": "EXC_DABORT", + "PublicDescription": "Counts exceptions that are taken locally and are caused by data aborts or SErrors. Conditions that could cause those exceptions are attempting to read or write memory where the MMU generates a fault, attempting to read or write memory with a misaligned address, interrupts from the nSEI inputs and internally generated SErrors." }, { - "ArchStdEvent": "EXC_IRQ" + "ArchStdEvent": "EXC_IRQ", + "PublicDescription": "Counts IRQ exceptions including the virtual IRQs that are taken locally." }, { - "ArchStdEvent": "EXC_FIQ" + "ArchStdEvent": "EXC_FIQ", + "PublicDescription": "Counts FIQ exceptions including the virtual FIQs that are taken locally." }, { - "ArchStdEvent": "EXC_SMC" + "ArchStdEvent": "EXC_SMC", + "PublicDescription": "Counts SMC exceptions take to EL3." }, { - "ArchStdEvent": "EXC_HVC" + "ArchStdEvent": "EXC_HVC", + "PublicDescription": "Counts HVC exceptions taken to EL2." }, { - "ArchStdEvent": "EXC_TRAP_PABORT" + "ArchStdEvent": "EXC_TRAP_PABORT", + "PublicDescription": "Counts exceptions which are traps not taken locally and are caused by Instruction Aborts. For example, attempting to execute an instruction with a misaligned PC." }, { - "ArchStdEvent": "EXC_TRAP_DABORT" + "ArchStdEvent": "EXC_TRAP_DABORT", + "PublicDescription": "Counts exceptions which are traps not taken locally and are caused by Data Aborts or SError interrupts. Conditions that could cause those exceptions are:\n\n1. Attempting to read or write memory where the MMU generates a fault,\n2. Attempting to read or write memory with a misaligned address,\n3. Interrupts from the SEI input.\n4. internally generated SErrors." }, { - "ArchStdEvent": "EXC_TRAP_OTHER" + "ArchStdEvent": "EXC_TRAP_OTHER", + "PublicDescription": "Counts the number of synchronous trap exceptions which are not taken locally and are not SVC, SMC, HVC, data aborts, Instruction Aborts, or interrupts." }, { - "ArchStdEvent": "EXC_TRAP_IRQ" + "ArchStdEvent": "EXC_TRAP_IRQ", + "PublicDescription": "Counts IRQ exceptions including the virtual IRQs that are not taken locally." }, { - "ArchStdEvent": "EXC_TRAP_FIQ" + "ArchStdEvent": "EXC_TRAP_FIQ", + "PublicDescription": "Counts FIQs which are not taken locally but taken from EL0, EL1,\n or EL2 to EL3 (which would be the normal behavior for FIQs when not executing\n in EL3)." } ] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/fp_operation.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/fp_operation.json new file mode 100644 index 000000000000..cec3435ac766 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/fp_operation.json @@ -0,0 +1,22 @@ +[ + { + "ArchStdEvent": "FP_HP_SPEC", + "PublicDescription": "Counts speculatively executed half precision floating point operations." + }, + { + "ArchStdEvent": "FP_SP_SPEC", + "PublicDescription": "Counts speculatively executed single precision floating point operations." + }, + { + "ArchStdEvent": "FP_DP_SPEC", + "PublicDescription": "Counts speculatively executed double precision floating point operations." + }, + { + "ArchStdEvent": "FP_SCALE_OPS_SPEC", + "PublicDescription": "Counts speculatively executed scalable single precision floating point operations." + }, + { + "ArchStdEvent": "FP_FIXED_OPS_SPEC", + "PublicDescription": "Counts speculatively executed non-scalable single precision floating point operations." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/general.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/general.json new file mode 100644 index 000000000000..428810f855b8 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/general.json @@ -0,0 +1,10 @@ +[ + { + "ArchStdEvent": "CPU_CYCLES", + "PublicDescription": "Counts CPU clock cycles (not timer cycles). The clock measured by this event is defined as the physical clock driving the CPU logic." + }, + { + "ArchStdEvent": "CNT_CYCLES", + "PublicDescription": "Counts constant frequency cycles" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/instruction.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/instruction.json deleted file mode 100644 index e57cd55937c6..000000000000 --- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/instruction.json +++ /dev/null @@ -1,143 +0,0 @@ -[ - { - "ArchStdEvent": "SW_INCR" - }, - { - "ArchStdEvent": "INST_RETIRED" - }, - { - "ArchStdEvent": "EXC_RETURN" - }, - { - "ArchStdEvent": "CID_WRITE_RETIRED" - }, - { - "ArchStdEvent": "INST_SPEC" - }, - { - "ArchStdEvent": "TTBR_WRITE_RETIRED" - }, - { - "ArchStdEvent": "BR_RETIRED" - }, - { - "ArchStdEvent": "BR_MIS_PRED_RETIRED" - }, - { - "ArchStdEvent": "OP_RETIRED" - }, - { - "ArchStdEvent": "OP_SPEC" - }, - { - "ArchStdEvent": "LDREX_SPEC" - }, - { - "ArchStdEvent": "STREX_PASS_SPEC" - }, - { - "ArchStdEvent": "STREX_FAIL_SPEC" - }, - { - "ArchStdEvent": "STREX_SPEC" - }, - { - "ArchStdEvent": "LD_SPEC" - }, - { - "ArchStdEvent": "ST_SPEC" - }, - { - "ArchStdEvent": "DP_SPEC" - }, - { - "ArchStdEvent": "ASE_SPEC" - }, - { - "ArchStdEvent": "VFP_SPEC" - }, - { - "ArchStdEvent": "PC_WRITE_SPEC" - }, - { - "ArchStdEvent": "CRYPTO_SPEC" - }, - { - "ArchStdEvent": "BR_IMMED_SPEC" - }, - { - "ArchStdEvent": "BR_RETURN_SPEC" - }, - { - "ArchStdEvent": "BR_INDIRECT_SPEC" - }, - { - "ArchStdEvent": "ISB_SPEC" - }, - { - "ArchStdEvent": "DSB_SPEC" - }, - { - "ArchStdEvent": "DMB_SPEC" - }, - { - "ArchStdEvent": "RC_LD_SPEC" - }, - { - "ArchStdEvent": "RC_ST_SPEC" - }, - { - "ArchStdEvent": "ASE_INST_SPEC" - }, - { - "ArchStdEvent": "SVE_INST_SPEC" - }, - { - "ArchStdEvent": "FP_HP_SPEC" - }, - { - "ArchStdEvent": "FP_SP_SPEC" - }, - { - "ArchStdEvent": "FP_DP_SPEC" - }, - { - "ArchStdEvent": "SVE_PRED_SPEC" - }, - { - "ArchStdEvent": "SVE_PRED_EMPTY_SPEC" - }, - { - "ArchStdEvent": "SVE_PRED_FULL_SPEC" - }, - { - "ArchStdEvent": "SVE_PRED_PARTIAL_SPEC" - }, - { - "ArchStdEvent": "SVE_PRED_NOT_FULL_SPEC" - }, - { - "ArchStdEvent": "SVE_LDFF_SPEC" - }, - { - "ArchStdEvent": "SVE_LDFF_FAULT_SPEC" - }, - { - "ArchStdEvent": "FP_SCALE_OPS_SPEC" - }, - { - "ArchStdEvent": "FP_FIXED_OPS_SPEC" - }, - { - "ArchStdEvent": "ASE_SVE_INT8_SPEC" - }, - { - "ArchStdEvent": "ASE_SVE_INT16_SPEC" - }, - { - "ArchStdEvent": "ASE_SVE_INT32_SPEC" - }, - { - "ArchStdEvent": "ASE_SVE_INT64_SPEC" - } -] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l1d_cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l1d_cache.json new file mode 100644 index 000000000000..da7c129f2569 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l1d_cache.json @@ -0,0 +1,54 @@ +[ + { + "ArchStdEvent": "L1D_CACHE_REFILL", + "PublicDescription": "Counts level 1 data cache refills caused by speculatively executed load or store operations that missed in the level 1 data cache. This event only counts one event per cache line. This event does not count cache line allocations from preload instructions or from hardware cache prefetching." + }, + { + "ArchStdEvent": "L1D_CACHE", + "PublicDescription": "Counts level 1 data cache accesses from any load/store operations. Atomic operations that resolve in the CPUs caches (near atomic operations) count as both a write access and read access. Each access to a cache line is counted including the multiple accesses caused by single instructions such as LDM or STM. Each access to other level 1 data or unified memory structures, for example refill buffers, write buffers, and write-back buffers, are also counted." + }, + { + "ArchStdEvent": "L1D_CACHE_WB", + "PublicDescription": "Counts write-backs of dirty data from the L1 data cache to the L2 cache. This occurs when either a dirty cache line is evicted from L1 data cache and allocated in the L2 cache or dirty data is written to the L2 and possibly to the next level of cache. This event counts both victim cache line evictions and cache write-backs from snoops or cache maintenance operations. The following cache operations are not counted:\n\n1. Invalidations which do not result in data being transferred out of the L1 (such as evictions of clean data),\n2. Full line writes which write to L2 without writing L1, such as write streaming mode." + }, + { + "ArchStdEvent": "L1D_CACHE_LMISS_RD", + "PublicDescription": "Counts cache line refills into the level 1 data cache from any memory read operations, that incurred additional latency." + }, + { + "ArchStdEvent": "L1D_CACHE_RD", + "PublicDescription": "Counts level 1 data cache accesses from any load operation. Atomic load operations that resolve in the CPUs caches count as both a write access and read access." + }, + { + "ArchStdEvent": "L1D_CACHE_WR", + "PublicDescription": "Counts level 1 data cache accesses generated by store operations. This event also counts accesses caused by a DC ZVA (data cache zero, specified by virtual address) instruction. Near atomic operations that resolve in the CPUs caches count as a write access and read access." + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_RD", + "PublicDescription": "Counts level 1 data cache refills caused by speculatively executed load instructions where the memory read operation misses in the level 1 data cache. This event only counts one event per cache line." + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_WR", + "PublicDescription": "Counts level 1 data cache refills caused by speculatively executed store instructions where the memory write operation misses in the level 1 data cache. This event only counts one event per cache line." + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_INNER", + "PublicDescription": "Counts level 1 data cache refills where the cache line data came from caches inside the immediate cluster of the core." + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_OUTER", + "PublicDescription": "Counts level 1 data cache refills for which the cache line data came from outside the immediate cluster of the core, like an SLC in the system interconnect or DRAM." + }, + { + "ArchStdEvent": "L1D_CACHE_WB_VICTIM", + "PublicDescription": "Counts dirty cache line evictions from the level 1 data cache caused by a new cache line allocation. This event does not count evictions caused by cache maintenance operations." + }, + { + "ArchStdEvent": "L1D_CACHE_WB_CLEAN", + "PublicDescription": "Counts write-backs from the level 1 data cache that are a result of a coherency operation made by another CPU. Event count includes cache maintenance operations." + }, + { + "ArchStdEvent": "L1D_CACHE_INVAL", + "PublicDescription": "Counts each explicit invalidation of a cache line in the level 1 data cache caused by:\n\n- Cache Maintenance Operations (CMO) that operate by a virtual address.\n- Broadcast cache coherency operations from another CPU in the system.\n\nThis event does not count for the following conditions:\n\n1. A cache refill invalidates a cache line.\n2. A CMO which is executed on that CPU and invalidates a cache line specified by set/way.\n\nNote that CMOs that operate by set/way cannot be broadcast from one CPU to another." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l1i_cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l1i_cache.json new file mode 100644 index 000000000000..633f1030359d --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l1i_cache.json @@ -0,0 +1,14 @@ +[ + { + "ArchStdEvent": "L1I_CACHE_REFILL", + "PublicDescription": "Counts cache line refills in the level 1 instruction cache caused by a missed instruction fetch. Instruction fetches may include accessing multiple instructions, but the single cache line allocation is counted once." + }, + { + "ArchStdEvent": "L1I_CACHE", + "PublicDescription": "Counts instruction fetches which access the level 1 instruction cache. Instruction cache accesses caused by cache maintenance operations are not counted." + }, + { + "ArchStdEvent": "L1I_CACHE_LMISS", + "PublicDescription": "Counts cache line refills into the level 1 instruction cache, that incurred additional latency." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l2_cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l2_cache.json new file mode 100644 index 000000000000..0e31d0daf88b --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l2_cache.json @@ -0,0 +1,50 @@ +[ + { + "ArchStdEvent": "L2D_CACHE", + "PublicDescription": "Counts level 2 cache accesses. level 2 cache is a unified cache for data and instruction accesses. Accesses are for misses in the first level caches or translation resolutions due to accesses. This event also counts write back of dirty data from level 1 data cache to the L2 cache." + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL", + "PublicDescription": "Counts cache line refills into the level 2 cache. level 2 cache is a unified cache for data and instruction accesses. Accesses are for misses in the level 1 caches or translation resolutions due to accesses." + }, + { + "ArchStdEvent": "L2D_CACHE_WB", + "PublicDescription": "Counts write-backs of data from the L2 cache to outside the CPU. This includes snoops to the L2 (from other CPUs) which return data even if the snoops cause an invalidation. L2 cache line invalidations which do not write data outside the CPU and snoops which return data from an L1 cache are not counted. Data would not be written outside the cache when invalidating a clean cache line." + }, + { + "ArchStdEvent": "L2D_CACHE_ALLOCATE", + "PublicDescription": "TBD" + }, + { + "ArchStdEvent": "L2D_CACHE_RD", + "PublicDescription": "Counts level 2 cache accesses due to memory read operations. level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 caches or translation resolutions due to accesses." + }, + { + "ArchStdEvent": "L2D_CACHE_WR", + "PublicDescription": "Counts level 2 cache accesses due to memory write operations. level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 caches or translation resolutions due to accesses." + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL_RD", + "PublicDescription": "Counts refills for memory accesses due to memory read operation counted by L2D_CACHE_RD. level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 caches or translation resolutions due to accesses." + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL_WR", + "PublicDescription": "Counts refills for memory accesses due to memory write operation counted by L2D_CACHE_WR. level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 caches or translation resolutions due to accesses." + }, + { + "ArchStdEvent": "L2D_CACHE_WB_VICTIM", + "PublicDescription": "Counts evictions from the level 2 cache because of a line being allocated into the L2 cache." + }, + { + "ArchStdEvent": "L2D_CACHE_WB_CLEAN", + "PublicDescription": "Counts write-backs from the level 2 cache that are a result of either:\n\n1. Cache maintenance operations,\n\n2. Snoop responses or,\n\n3. Direct cache transfers to another CPU due to a forwarding snoop request." + }, + { + "ArchStdEvent": "L2D_CACHE_INVAL", + "PublicDescription": "Counts each explicit invalidation of a cache line in the level 2 cache by cache maintenance operations that operate by a virtual address, or by external coherency operations. This event does not count if either:\n\n1. A cache refill invalidates a cache line or,\n2. A Cache Maintenance Operation (CMO), which invalidates a cache line specified by set/way, is executed on that CPU.\n\nCMOs that operate by set/way cannot be broadcast from one CPU to another." + }, + { + "ArchStdEvent": "L2D_CACHE_LMISS_RD", + "PublicDescription": "Counts cache line refills into the level 2 unified cache from any memory read operations that incurred additional latency." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l3_cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l3_cache.json new file mode 100644 index 000000000000..45bfba532df7 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l3_cache.json @@ -0,0 +1,22 @@ +[ + { + "ArchStdEvent": "L3D_CACHE_ALLOCATE", + "PublicDescription": "Counts level 3 cache line allocates that do not fetch data from outside the level 3 data or unified cache. For example, allocates due to streaming stores." + }, + { + "ArchStdEvent": "L3D_CACHE_REFILL", + "PublicDescription": "Counts level 3 accesses that receive data from outside the L3 cache." + }, + { + "ArchStdEvent": "L3D_CACHE", + "PublicDescription": "Counts level 3 cache accesses. level 3 cache is a unified cache for data and instruction accesses. Accesses are for misses in the lower level caches or translation resolutions due to accesses." + }, + { + "ArchStdEvent": "L3D_CACHE_RD", + "PublicDescription": "TBD" + }, + { + "ArchStdEvent": "L3D_CACHE_LMISS_RD", + "PublicDescription": "Counts any cache line refill into the level 3 cache from memory read operations that incurred additional latency." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/ll_cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/ll_cache.json new file mode 100644 index 000000000000..bb712d57d58a --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/ll_cache.json @@ -0,0 +1,10 @@ +[ + { + "ArchStdEvent": "LL_CACHE_RD", + "PublicDescription": "Counts read transactions that were returned from outside the core cluster. This event counts when the system register CPUECTLR.EXTLLC bit is set. This event counts read transactions returned from outside the core if those transactions are either hit in the system level cache or missed in the SLC and are returned from any other external sources." + }, + { + "ArchStdEvent": "LL_CACHE_MISS_RD", + "PublicDescription": "Counts read transactions that were returned from outside the core cluster but missed in the system level cache. This event counts when the system register CPUECTLR.EXTLLC bit is set. This event counts read transactions returned from outside the core if those transactions are missed in the System level Cache. The data source of the transaction is indicated by a field in the CHI transaction returning to the CPU. This event does not count reads caused by cache maintenance operations." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/memory.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/memory.json index 7b2b21ac150f..106a97f8b2e7 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/memory.json +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/memory.json @@ -1,41 +1,46 @@ [ { - "ArchStdEvent": "MEM_ACCESS" + "ArchStdEvent": "MEM_ACCESS", + "PublicDescription": "Counts memory accesses issued by the CPU load store unit, where those accesses are issued due to load or store operations. This event counts memory accesses no matter whether the data is received from any level of cache hierarchy or external memory. If memory accesses are broken up into smaller transactions than what were specified in the load or store instructions, then the event counts those smaller memory transactions." }, { - "ArchStdEvent": "REMOTE_ACCESS" + "ArchStdEvent": "MEMORY_ERROR", + "PublicDescription": "Counts any detected correctable or uncorrectable physical memory errors (ECC or parity) in protected CPUs RAMs. On the core, this event counts errors in the caches (including data and tag rams). Any detected memory error (from either a speculative and abandoned access, or an architecturally executed access) is counted. Note that errors are only detected when the actual protected memory is accessed by an operation." }, { - "ArchStdEvent": "MEM_ACCESS_RD" + "ArchStdEvent": "REMOTE_ACCESS", + "PublicDescription": "Counts accesses to another chip, which is implemented as a different CMN mesh in the system. If the CHI bus response back to the core indicates that the data source is from another chip (mesh), then the counter is updated. If no data is returned, even if the system snoops another chip/mesh, then the counter is not updated." }, { - "ArchStdEvent": "MEM_ACCESS_WR" + "ArchStdEvent": "MEM_ACCESS_RD", + "PublicDescription": "Counts memory accesses issued by the CPU due to load operations. The event counts any memory load access, no matter whether the data is received from any level of cache hierarchy or external memory. The event also counts atomic load operations. If memory accesses are broken up by the load/store unit into smaller transactions that are issued by the bus interface, then the event counts those smaller transactions." }, { - "ArchStdEvent": "UNALIGNED_LD_SPEC" + "ArchStdEvent": "MEM_ACCESS_WR", + "PublicDescription": "Counts memory accesses issued by the CPU due to store operations. The event counts any memory store access, no matter whether the data is located in any level of cache or external memory. The event also counts atomic load and store operations. If memory accesses are broken up by the load/store unit into smaller transactions that are issued by the bus interface, then the event counts those smaller transactions." }, { - "ArchStdEvent": "UNALIGNED_ST_SPEC" + "ArchStdEvent": "LDST_ALIGN_LAT", + "PublicDescription": "Counts the number of memory read and write accesses in a cycle that incurred additional latency, due to the alignment of the address and the size of data being accessed, which results in store crossing a single cache line." }, { - "ArchStdEvent": "UNALIGNED_LDST_SPEC" + "ArchStdEvent": "LD_ALIGN_LAT", + "PublicDescription": "Counts the number of memory read accesses in a cycle that incurred additional latency, due to the alignment of the address and size of data being accessed, which results in load crossing a single cache line." }, { - "ArchStdEvent": "LDST_ALIGN_LAT" + "ArchStdEvent": "ST_ALIGN_LAT", + "PublicDescription": "Counts the number of memory write access in a cycle that incurred additional latency, due to the alignment of the address and size of data being accessed incurred additional latency." }, { - "ArchStdEvent": "LD_ALIGN_LAT" + "ArchStdEvent": "MEM_ACCESS_CHECKED", + "PublicDescription": "Counts the number of memory read and write accesses in a cycle that are tag checked by the Memory Tagging Extension (MTE)." }, { - "ArchStdEvent": "ST_ALIGN_LAT" + "ArchStdEvent": "MEM_ACCESS_CHECKED_RD", + "PublicDescription": "Counts the number of memory read accesses in a cycle that are tag checked by the Memory Tagging Extension (MTE)." }, { - "ArchStdEvent": "MEM_ACCESS_CHECKED" - }, - { - "ArchStdEvent": "MEM_ACCESS_CHECKED_RD" - }, - { - "ArchStdEvent": "MEM_ACCESS_CHECKED_WR" + "ArchStdEvent": "MEM_ACCESS_CHECKED_WR", + "PublicDescription": "Counts the number of memory write accesses in a cycle that is tag checked by the Memory Tagging Extension (MTE)." } ] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/metrics.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/metrics.json index 8ad15b726dca..5f449270b448 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/metrics.json +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/metrics.json @@ -1,272 +1,303 @@ [ { - "ArchStdEvent": "FRONTEND_BOUND", - "MetricExpr": "((stall_slot_frontend) if (#slots - 5) else (stall_slot_frontend - cpu_cycles)) / (#slots * cpu_cycles)" + "ArchStdEvent": "backend_bound", + "MetricExpr": "(100 * ((STALL_SLOT_BACKEND / (CPU_CYCLES * #slots)) - ((BR_MIS_PRED * 3) / CPU_CYCLES)))" }, { - "ArchStdEvent": "BAD_SPECULATION", - "MetricExpr": "(1 - op_retired / op_spec) * (1 - (stall_slot if (#slots - 5) else (stall_slot - cpu_cycles)) / (#slots * cpu_cycles))" + "MetricName": "backend_stalled_cycles", + "MetricExpr": "((STALL_BACKEND / CPU_CYCLES) * 100)", + "BriefDescription": "This metric is the percentage of cycles that were stalled due to resource constraints in the backend unit of the processor.", + "MetricGroup": "Cycle_Accounting", + "ScaleUnit": "1percent of cycles" }, { - "ArchStdEvent": "RETIRING", - "MetricExpr": "(op_retired / op_spec) * (1 - (stall_slot if (#slots - 5) else (stall_slot - cpu_cycles)) / (#slots * cpu_cycles))" + "ArchStdEvent": "bad_speculation", + "MetricExpr": "(100 * (((1 - (OP_RETIRED / OP_SPEC)) * (1 - (((STALL_SLOT) if (strcmp_cpuid_str(0x410fd493) | strcmp_cpuid_str(0x410fd490) ^ 1) else (STALL_SLOT - CPU_CYCLES)) / (CPU_CYCLES * #slots)))) + ((BR_MIS_PRED * 4) / CPU_CYCLES)))" }, { - "ArchStdEvent": "BACKEND_BOUND" + "MetricName": "branch_misprediction_ratio", + "MetricExpr": "(BR_MIS_PRED_RETIRED / BR_RETIRED)", + "BriefDescription": "This metric measures the ratio of branches mispredicted to the total number of branches architecturally executed. This gives an indication of the effectiveness of the branch prediction unit.", + "MetricGroup": "Miss_Ratio;Branch_Effectiveness", + "ScaleUnit": "1per branch" }, { - "MetricExpr": "L1D_TLB_REFILL / L1D_TLB", - "BriefDescription": "The rate of L1D TLB refill to the overall L1D TLB lookups", - "MetricGroup": "TLB", - "MetricName": "l1d_tlb_miss_rate", - "ScaleUnit": "100%" + "MetricName": "branch_mpki", + "MetricExpr": "((BR_MIS_PRED_RETIRED / INST_RETIRED) * 1000)", + "BriefDescription": "This metric measures the number of branch mispredictions per thousand instructions executed.", + "MetricGroup": "MPKI;Branch_Effectiveness", + "ScaleUnit": "1MPKI" }, { - "MetricExpr": "L1I_TLB_REFILL / L1I_TLB", - "BriefDescription": "The rate of L1I TLB refill to the overall L1I TLB lookups", - "MetricGroup": "TLB", - "MetricName": "l1i_tlb_miss_rate", - "ScaleUnit": "100%" + "MetricName": "branch_percentage", + "MetricExpr": "(((BR_IMMED_SPEC + BR_INDIRECT_SPEC) / INST_SPEC) * 100)", + "BriefDescription": "This metric measures branch operations as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" }, { - "MetricExpr": "L2D_TLB_REFILL / L2D_TLB", - "BriefDescription": "The rate of L2D TLB refill to the overall L2D TLB lookups", - "MetricGroup": "TLB", - "MetricName": "l2_tlb_miss_rate", - "ScaleUnit": "100%" + "MetricName": "crypto_percentage", + "MetricExpr": "((CRYPTO_SPEC / INST_SPEC) * 100)", + "BriefDescription": "This metric measures crypto operations as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" }, { - "MetricExpr": "DTLB_WALK / INST_RETIRED * 1000", - "BriefDescription": "The rate of TLB Walks per kilo instructions for data accesses", - "MetricGroup": "TLB", "MetricName": "dtlb_mpki", + "MetricExpr": "((DTLB_WALK / INST_RETIRED) * 1000)", + "BriefDescription": "This metric measures the number of data TLB Walks per thousand instructions executed.", + "MetricGroup": "MPKI;DTLB_Effectiveness", "ScaleUnit": "1MPKI" }, { - "MetricExpr": "DTLB_WALK / L1D_TLB", - "BriefDescription": "The rate of DTLB Walks to the overall L1D TLB lookups", - "MetricGroup": "TLB", - "MetricName": "dtlb_walk_rate", - "ScaleUnit": "100%" + "MetricName": "dtlb_walk_ratio", + "MetricExpr": "(DTLB_WALK / L1D_TLB)", + "BriefDescription": "This metric measures the ratio of data TLB Walks to the total number of data TLB accesses. This gives an indication of the effectiveness of the data TLB accesses.", + "MetricGroup": "Miss_Ratio;DTLB_Effectiveness", + "ScaleUnit": "1per TLB access" }, { - "MetricExpr": "ITLB_WALK / INST_RETIRED * 1000", - "BriefDescription": "The rate of TLB Walks per kilo instructions for instruction accesses", - "MetricGroup": "TLB", - "MetricName": "itlb_mpki", - "ScaleUnit": "1MPKI" + "ArchStdEvent": "frontend_bound", + "MetricExpr": "(100 * ((((STALL_SLOT_FRONTEND) if (strcmp_cpuid_str(0x410fd493) | strcmp_cpuid_str(0x410fd490) ^ 1) else (STALL_SLOT_FRONTEND - CPU_CYCLES)) / (CPU_CYCLES * #slots)) - (BR_MIS_PRED / CPU_CYCLES)))" }, { - "MetricExpr": "ITLB_WALK / L1I_TLB", - "BriefDescription": "The rate of ITLB Walks to the overall L1I TLB lookups", - "MetricGroup": "TLB", - "MetricName": "itlb_walk_rate", - "ScaleUnit": "100%" + "MetricName": "frontend_stalled_cycles", + "MetricExpr": "((STALL_FRONTEND / CPU_CYCLES) * 100)", + "BriefDescription": "This metric is the percentage of cycles that were stalled due to resource constraints in the frontend unit of the processor.", + "MetricGroup": "Cycle_Accounting", + "ScaleUnit": "1percent of cycles" }, { - "MetricExpr": "L1I_CACHE_REFILL / INST_RETIRED * 1000", - "BriefDescription": "The rate of L1 I-Cache misses per kilo instructions", - "MetricGroup": "Cache", - "MetricName": "l1i_cache_mpki", + "MetricName": "integer_dp_percentage", + "MetricExpr": "((DP_SPEC / INST_SPEC) * 100)", + "BriefDescription": "This metric measures scalar integer operations as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" + }, + { + "MetricName": "ipc", + "MetricExpr": "(INST_RETIRED / CPU_CYCLES)", + "BriefDescription": "This metric measures the number of instructions retired per cycle.", + "MetricGroup": "General", + "ScaleUnit": "1per cycle" + }, + { + "MetricName": "itlb_mpki", + "MetricExpr": "((ITLB_WALK / INST_RETIRED) * 1000)", + "BriefDescription": "This metric measures the number of instruction TLB Walks per thousand instructions executed.", + "MetricGroup": "MPKI;ITLB_Effectiveness", "ScaleUnit": "1MPKI" }, { - "MetricExpr": "L1I_CACHE_REFILL / L1I_CACHE", - "BriefDescription": "The rate of L1 I-Cache misses to the overall L1 I-Cache", - "MetricGroup": "Cache", - "MetricName": "l1i_cache_miss_rate", - "ScaleUnit": "100%" + "MetricName": "itlb_walk_ratio", + "MetricExpr": "(ITLB_WALK / L1I_TLB)", + "BriefDescription": "This metric measures the ratio of instruction TLB Walks to the total number of instruction TLB accesses. This gives an indication of the effectiveness of the instruction TLB accesses.", + "MetricGroup": "Miss_Ratio;ITLB_Effectiveness", + "ScaleUnit": "1per TLB access" + }, + { + "MetricName": "l1d_cache_miss_ratio", + "MetricExpr": "(L1D_CACHE_REFILL / L1D_CACHE)", + "BriefDescription": "This metric measures the ratio of level 1 data cache accesses missed to the total number of level 1 data cache accesses. This gives an indication of the effectiveness of the level 1 data cache.", + "MetricGroup": "Miss_Ratio;L1D_Cache_Effectiveness", + "ScaleUnit": "1per cache access" }, { - "MetricExpr": "L1D_CACHE_REFILL / INST_RETIRED * 1000", - "BriefDescription": "The rate of L1 D-Cache misses per kilo instructions", - "MetricGroup": "Cache", "MetricName": "l1d_cache_mpki", + "MetricExpr": "((L1D_CACHE_REFILL / INST_RETIRED) * 1000)", + "BriefDescription": "This metric measures the number of level 1 data cache accesses missed per thousand instructions executed.", + "MetricGroup": "MPKI;L1D_Cache_Effectiveness", "ScaleUnit": "1MPKI" }, { - "MetricExpr": "L1D_CACHE_REFILL / L1D_CACHE", - "BriefDescription": "The rate of L1 D-Cache misses to the overall L1 D-Cache", - "MetricGroup": "Cache", - "MetricName": "l1d_cache_miss_rate", - "ScaleUnit": "100%" + "MetricName": "l1d_tlb_miss_ratio", + "MetricExpr": "(L1D_TLB_REFILL / L1D_TLB)", + "BriefDescription": "This metric measures the ratio of level 1 data TLB accesses missed to the total number of level 1 data TLB accesses. This gives an indication of the effectiveness of the level 1 data TLB.", + "MetricGroup": "Miss_Ratio;DTLB_Effectiveness", + "ScaleUnit": "1per TLB access" }, { - "MetricExpr": "L2D_CACHE_REFILL / INST_RETIRED * 1000", - "BriefDescription": "The rate of L2 D-Cache misses per kilo instructions", - "MetricGroup": "Cache", - "MetricName": "l2d_cache_mpki", + "MetricName": "l1d_tlb_mpki", + "MetricExpr": "((L1D_TLB_REFILL / INST_RETIRED) * 1000)", + "BriefDescription": "This metric measures the number of level 1 instruction TLB accesses missed per thousand instructions executed.", + "MetricGroup": "MPKI;DTLB_Effectiveness", "ScaleUnit": "1MPKI" }, { - "MetricExpr": "L2D_CACHE_REFILL / L2D_CACHE", - "BriefDescription": "The rate of L2 D-Cache misses to the overall L2 D-Cache", - "MetricGroup": "Cache", - "MetricName": "l2d_cache_miss_rate", - "ScaleUnit": "100%" + "MetricName": "l1i_cache_miss_ratio", + "MetricExpr": "(L1I_CACHE_REFILL / L1I_CACHE)", + "BriefDescription": "This metric measures the ratio of level 1 instruction cache accesses missed to the total number of level 1 instruction cache accesses. This gives an indication of the effectiveness of the level 1 instruction cache.", + "MetricGroup": "Miss_Ratio;L1I_Cache_Effectiveness", + "ScaleUnit": "1per cache access" }, { - "MetricExpr": "L3D_CACHE_REFILL / INST_RETIRED * 1000", - "BriefDescription": "The rate of L3 D-Cache misses per kilo instructions", - "MetricGroup": "Cache", - "MetricName": "l3d_cache_mpki", + "MetricName": "l1i_cache_mpki", + "MetricExpr": "((L1I_CACHE_REFILL / INST_RETIRED) * 1000)", + "BriefDescription": "This metric measures the number of level 1 instruction cache accesses missed per thousand instructions executed.", + "MetricGroup": "MPKI;L1I_Cache_Effectiveness", "ScaleUnit": "1MPKI" }, { - "MetricExpr": "L3D_CACHE_REFILL / L3D_CACHE", - "BriefDescription": "The rate of L3 D-Cache misses to the overall L3 D-Cache", - "MetricGroup": "Cache", - "MetricName": "l3d_cache_miss_rate", - "ScaleUnit": "100%" + "MetricName": "l1i_tlb_miss_ratio", + "MetricExpr": "(L1I_TLB_REFILL / L1I_TLB)", + "BriefDescription": "This metric measures the ratio of level 1 instruction TLB accesses missed to the total number of level 1 instruction TLB accesses. This gives an indication of the effectiveness of the level 1 instruction TLB.", + "MetricGroup": "Miss_Ratio;ITLB_Effectiveness", + "ScaleUnit": "1per TLB access" }, { - "MetricExpr": "LL_CACHE_MISS_RD / INST_RETIRED * 1000", - "BriefDescription": "The rate of LL Cache read misses per kilo instructions", - "MetricGroup": "Cache", - "MetricName": "ll_cache_read_mpki", + "MetricName": "l1i_tlb_mpki", + "MetricExpr": "((L1I_TLB_REFILL / INST_RETIRED) * 1000)", + "BriefDescription": "This metric measures the number of level 1 instruction TLB accesses missed per thousand instructions executed.", + "MetricGroup": "MPKI;ITLB_Effectiveness", "ScaleUnit": "1MPKI" }, { - "MetricExpr": "LL_CACHE_MISS_RD / LL_CACHE_RD", - "BriefDescription": "The rate of LL Cache read misses to the overall LL Cache read", - "MetricGroup": "Cache", - "MetricName": "ll_cache_read_miss_rate", - "ScaleUnit": "100%" + "MetricName": "l2_cache_miss_ratio", + "MetricExpr": "(L2D_CACHE_REFILL / L2D_CACHE)", + "BriefDescription": "This metric measures the ratio of level 2 cache accesses missed to the total number of level 2 cache accesses. This gives an indication of the effectiveness of the level 2 cache, which is a unified cache that stores both data and instruction. Note that cache accesses in this cache are either data memory access or instruction fetch as this is a unified cache.", + "MetricGroup": "Miss_Ratio;L2_Cache_Effectiveness", + "ScaleUnit": "1per cache access" }, { - "MetricExpr": "(LL_CACHE_RD - LL_CACHE_MISS_RD) / LL_CACHE_RD", - "BriefDescription": "The rate of LL Cache read hit to the overall LL Cache read", - "MetricGroup": "Cache", - "MetricName": "ll_cache_read_hit_rate", - "ScaleUnit": "100%" + "MetricName": "l2_cache_mpki", + "MetricExpr": "((L2D_CACHE_REFILL / INST_RETIRED) * 1000)", + "BriefDescription": "This metric measures the number of level 2 unified cache accesses missed per thousand instructions executed. Note that cache accesses in this cache are either data memory access or instruction fetch as this is a unified cache.", + "MetricGroup": "MPKI;L2_Cache_Effectiveness", + "ScaleUnit": "1MPKI" }, { - "MetricExpr": "BR_MIS_PRED_RETIRED / INST_RETIRED * 1000", - "BriefDescription": "The rate of branches mis-predicted per kilo instructions", - "MetricGroup": "Branch", - "MetricName": "branch_mpki", + "MetricName": "l2_tlb_miss_ratio", + "MetricExpr": "(L2D_TLB_REFILL / L2D_TLB)", + "BriefDescription": "This metric measures the ratio of level 2 unified TLB accesses missed to the total number of level 2 unified TLB accesses. This gives an indication of the effectiveness of the level 2 TLB.", + "MetricGroup": "Miss_Ratio;ITLB_Effectiveness;DTLB_Effectiveness", + "ScaleUnit": "1per TLB access" + }, + { + "MetricName": "l2_tlb_mpki", + "MetricExpr": "((L2D_TLB_REFILL / INST_RETIRED) * 1000)", + "BriefDescription": "This metric measures the number of level 2 unified TLB accesses missed per thousand instructions executed.", + "MetricGroup": "MPKI;ITLB_Effectiveness;DTLB_Effectiveness", "ScaleUnit": "1MPKI" }, { - "MetricExpr": "BR_RETIRED / INST_RETIRED * 1000", - "BriefDescription": "The rate of branches retired per kilo instructions", - "MetricGroup": "Branch", - "MetricName": "branch_pki", - "ScaleUnit": "1PKI" + "MetricName": "ll_cache_read_hit_ratio", + "MetricExpr": "((LL_CACHE_RD - LL_CACHE_MISS_RD) / LL_CACHE_RD)", + "BriefDescription": "This metric measures the ratio of last level cache read accesses hit in the cache to the total number of last level cache accesses. This gives an indication of the effectiveness of the last level cache for read traffic. Note that cache accesses in this cache are either data memory access or instruction fetch as this is a system level cache.", + "MetricGroup": "LL_Cache_Effectiveness", + "ScaleUnit": "1per cache access" }, { - "MetricExpr": "BR_MIS_PRED_RETIRED / BR_RETIRED", - "BriefDescription": "The rate of branches mis-predited to the overall branches", - "MetricGroup": "Branch", - "MetricName": "branch_miss_pred_rate", - "ScaleUnit": "100%" + "MetricName": "ll_cache_read_miss_ratio", + "MetricExpr": "(LL_CACHE_MISS_RD / LL_CACHE_RD)", + "BriefDescription": "This metric measures the ratio of last level cache read accesses missed to the total number of last level cache accesses. This gives an indication of the effectiveness of the last level cache for read traffic. Note that cache accesses in this cache are either data memory access or instruction fetch as this is a system level cache.", + "MetricGroup": "Miss_Ratio;LL_Cache_Effectiveness", + "ScaleUnit": "1per cache access" }, { - "MetricExpr": "instructions / CPU_CYCLES", - "BriefDescription": "The average number of instructions executed for each cycle.", - "MetricGroup": "PEutilization", - "MetricName": "ipc" + "MetricName": "ll_cache_read_mpki", + "MetricExpr": "((LL_CACHE_MISS_RD / INST_RETIRED) * 1000)", + "BriefDescription": "This metric measures the number of last level cache read accesses missed per thousand instructions executed.", + "MetricGroup": "MPKI;LL_Cache_Effectiveness", + "ScaleUnit": "1MPKI" }, { - "MetricExpr": "ipc / 5", - "BriefDescription": "IPC percentage of peak. The peak of IPC is 5.", - "MetricGroup": "PEutilization", - "MetricName": "ipc_rate", - "ScaleUnit": "100%" + "MetricName": "load_percentage", + "MetricExpr": "((LD_SPEC / INST_SPEC) * 100)", + "BriefDescription": "This metric measures load operations as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" }, { - "MetricExpr": "INST_RETIRED / CPU_CYCLES", - "BriefDescription": "Architecturally executed Instructions Per Cycle (IPC)", - "MetricGroup": "PEutilization", - "MetricName": "retired_ipc" + "ArchStdEvent": "retiring", + "MetricExpr": "(100 * ((OP_RETIRED / OP_SPEC) * (1 - (((STALL_SLOT) if (strcmp_cpuid_str(0x410fd493) | strcmp_cpuid_str(0x410fd490) ^ 1) else (STALL_SLOT - CPU_CYCLES)) / (CPU_CYCLES * #slots)))))" }, { - "MetricExpr": "INST_SPEC / CPU_CYCLES", - "BriefDescription": "Speculatively executed Instructions Per Cycle (IPC)", - "MetricGroup": "PEutilization", - "MetricName": "spec_ipc" + "MetricName": "scalar_fp_percentage", + "MetricExpr": "((VFP_SPEC / INST_SPEC) * 100)", + "BriefDescription": "This metric measures scalar floating point operations as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" }, { - "MetricExpr": "OP_RETIRED / OP_SPEC", - "BriefDescription": "Of all the micro-operations issued, what percentage are retired(committed)", - "MetricGroup": "PEutilization", - "MetricName": "retired_rate", - "ScaleUnit": "100%" + "MetricName": "simd_percentage", + "MetricExpr": "((ASE_SPEC / INST_SPEC) * 100)", + "BriefDescription": "This metric measures advanced SIMD operations as a percentage of total operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" }, { - "MetricExpr": "1 - OP_RETIRED / OP_SPEC", - "BriefDescription": "Of all the micro-operations issued, what percentage are not retired(committed)", - "MetricGroup": "PEutilization", - "MetricName": "wasted_rate", - "ScaleUnit": "100%" + "MetricName": "store_percentage", + "MetricExpr": "((ST_SPEC / INST_SPEC) * 100)", + "BriefDescription": "This metric measures store operations as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" }, { - "MetricExpr": "OP_RETIRED / OP_SPEC * (1 - (STALL_SLOT if (#slots - 5) else (STALL_SLOT - CPU_CYCLES)) / (#slots * CPU_CYCLES))", - "BriefDescription": "The truly effective ratio of micro-operations executed by the CPU, which means that misprediction and stall are not included", - "MetricGroup": "PEutilization", - "MetricName": "cpu_utilization", - "ScaleUnit": "100%" + "MetricExpr": "L3D_CACHE_REFILL / INST_RETIRED * 1000", + "BriefDescription": "The rate of L3 D-Cache misses per kilo instructions", + "MetricGroup": "MPKI;L3_Cache_Effectiveness", + "MetricName": "l3d_cache_mpki", + "ScaleUnit": "1MPKI" }, { - "MetricExpr": "LD_SPEC / INST_SPEC", - "BriefDescription": "The rate of load instructions speculatively executed to overall instructions speclatively executed", - "MetricGroup": "InstructionMix", - "MetricName": "load_spec_rate", + "MetricExpr": "L3D_CACHE_REFILL / L3D_CACHE", + "BriefDescription": "The rate of L3 D-Cache misses to the overall L3 D-Cache", + "MetricGroup": "Miss_Ratio;L3_Cache_Effectiveness", + "MetricName": "l3d_cache_miss_rate", "ScaleUnit": "100%" }, { - "MetricExpr": "ST_SPEC / INST_SPEC", - "BriefDescription": "The rate of store instructions speculatively executed to overall instructions speclatively executed", - "MetricGroup": "InstructionMix", - "MetricName": "store_spec_rate", - "ScaleUnit": "100%" + "MetricExpr": "BR_RETIRED / INST_RETIRED * 1000", + "BriefDescription": "The rate of branches retired per kilo instructions", + "MetricGroup": "MPKI;Branch_Effectiveness", + "MetricName": "branch_pki", + "ScaleUnit": "1PKI" }, { - "MetricExpr": "DP_SPEC / INST_SPEC", - "BriefDescription": "The rate of integer data-processing instructions speculatively executed to overall instructions speclatively executed", - "MetricGroup": "InstructionMix", - "MetricName": "data_process_spec_rate", + "MetricExpr": "ipc / #slots", + "BriefDescription": "IPC percentage of peak. The peak of IPC is the number of slots.", + "MetricGroup": "General", + "MetricName": "ipc_rate", "ScaleUnit": "100%" }, { - "MetricExpr": "ASE_SPEC / INST_SPEC", - "BriefDescription": "The rate of advanced SIMD instructions speculatively executed to overall instructions speclatively executed", - "MetricGroup": "InstructionMix", - "MetricName": "advanced_simd_spec_rate", - "ScaleUnit": "100%" + "MetricExpr": "INST_SPEC / CPU_CYCLES", + "BriefDescription": "Speculatively executed Instructions Per Cycle (IPC)", + "MetricGroup": "General", + "MetricName": "spec_ipc" }, { - "MetricExpr": "VFP_SPEC / INST_SPEC", - "BriefDescription": "The rate of floating point instructions speculatively executed to overall instructions speclatively executed", - "MetricGroup": "InstructionMix", - "MetricName": "float_point_spec_rate", + "MetricExpr": "OP_RETIRED / OP_SPEC", + "BriefDescription": "Of all the micro-operations issued, what percentage are retired(committed)", + "MetricGroup": "General", + "MetricName": "retired_rate", "ScaleUnit": "100%" }, { - "MetricExpr": "CRYPTO_SPEC / INST_SPEC", - "BriefDescription": "The rate of crypto instructions speculatively executed to overall instructions speclatively executed", - "MetricGroup": "InstructionMix", - "MetricName": "crypto_spec_rate", + "MetricExpr": "1 - OP_RETIRED / OP_SPEC", + "BriefDescription": "Of all the micro-operations issued, what percentage are not retired(committed)", + "MetricGroup": "General", + "MetricName": "wasted_rate", "ScaleUnit": "100%" }, { "MetricExpr": "BR_IMMED_SPEC / INST_SPEC", - "BriefDescription": "The rate of branch immediate instructions speculatively executed to overall instructions speclatively executed", - "MetricGroup": "InstructionMix", + "BriefDescription": "The rate of branch immediate instructions speculatively executed to overall instructions speculatively executed", + "MetricGroup": "Operation_Mix", "MetricName": "branch_immed_spec_rate", "ScaleUnit": "100%" }, { "MetricExpr": "BR_RETURN_SPEC / INST_SPEC", - "BriefDescription": "The rate of procedure return instructions speculatively executed to overall instructions speclatively executed", - "MetricGroup": "InstructionMix", + "BriefDescription": "The rate of procedure return instructions speculatively executed to overall instructions speculatively executed", + "MetricGroup": "Operation_Mix", "MetricName": "branch_return_spec_rate", "ScaleUnit": "100%" }, { "MetricExpr": "BR_INDIRECT_SPEC / INST_SPEC", - "BriefDescription": "The rate of indirect branch instructions speculatively executed to overall instructions speclatively executed", - "MetricGroup": "InstructionMix", + "BriefDescription": "The rate of indirect branch instructions speculatively executed to overall instructions speculatively executed", + "MetricGroup": "Operation_Mix", "MetricName": "branch_indirect_spec_rate", "ScaleUnit": "100%" } diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/pipeline.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/pipeline.json deleted file mode 100644 index f9fae15f7555..000000000000 --- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/pipeline.json +++ /dev/null @@ -1,23 +0,0 @@ -[ - { - "ArchStdEvent": "STALL_FRONTEND" - }, - { - "ArchStdEvent": "STALL_BACKEND" - }, - { - "ArchStdEvent": "STALL" - }, - { - "ArchStdEvent": "STALL_SLOT_BACKEND" - }, - { - "ArchStdEvent": "STALL_SLOT_FRONTEND" - }, - { - "ArchStdEvent": "STALL_SLOT" - }, - { - "ArchStdEvent": "STALL_BACKEND_MEM" - } -] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/retired.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/retired.json new file mode 100644 index 000000000000..f297b049b62f --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/retired.json @@ -0,0 +1,30 @@ +[ + { + "ArchStdEvent": "SW_INCR", + "PublicDescription": "Counts software writes to the PMSWINC_EL0 (software PMU increment) register. The PMSWINC_EL0 register is a manually updated counter for use by application software.\n\nThis event could be used to measure any user program event, such as accesses to a particular data structure (by writing to the PMSWINC_EL0 register each time the data structure is accessed).\n\nTo use the PMSWINC_EL0 register and event, developers must insert instructions that write to the PMSWINC_EL0 register into the source code.\n\nSince the SW_INCR event records writes to the PMSWINC_EL0 register, there is no need to do a read/increment/write sequence to the PMSWINC_EL0 register." + }, + { + "ArchStdEvent": "INST_RETIRED", + "PublicDescription": "Counts instructions that have been architecturally executed." + }, + { + "ArchStdEvent": "CID_WRITE_RETIRED", + "PublicDescription": "Counts architecturally executed writes to the CONTEXTIDR register, which usually contain the kernel PID and can be output with hardware trace." + }, + { + "ArchStdEvent": "TTBR_WRITE_RETIRED", + "PublicDescription": "Counts architectural writes to TTBR0/1_EL1. If virtualization host extensions are enabled (by setting the HCR_EL2.E2H bit to 1), then accesses to TTBR0/1_EL1 that are redirected to TTBR0/1_EL2, or accesses to TTBR0/1_EL12, are counted. TTBRn registers are typically updated when the kernel is swapping user-space threads or applications." + }, + { + "ArchStdEvent": "BR_RETIRED", + "PublicDescription": "Counts architecturally executed branches, whether the branch is taken or not. Instructions that explicitly write to the PC are also counted." + }, + { + "ArchStdEvent": "BR_MIS_PRED_RETIRED", + "PublicDescription": "Counts branches counted by BR_RETIRED which were mispredicted and caused a pipeline flush." + }, + { + "ArchStdEvent": "OP_RETIRED", + "PublicDescription": "Counts micro-operations that are architecturally executed. This is a count of number of micro-operations retired from the commit queue in a single cycle." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/spe.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/spe.json index 20f2165c85fe..5de8b0f3a440 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/spe.json +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/spe.json @@ -1,14 +1,18 @@ [ { - "ArchStdEvent": "SAMPLE_POP" + "ArchStdEvent": "SAMPLE_POP", + "PublicDescription": "Counts statistical profiling sample population, the count of all operations that could be sampled but may or may not be chosen for sampling." }, { - "ArchStdEvent": "SAMPLE_FEED" + "ArchStdEvent": "SAMPLE_FEED", + "PublicDescription": "Counts statistical profiling samples taken for sampling." }, { - "ArchStdEvent": "SAMPLE_FILTRATE" + "ArchStdEvent": "SAMPLE_FILTRATE", + "PublicDescription": "Counts statistical profiling samples taken which are not removed by filtering." }, { - "ArchStdEvent": "SAMPLE_COLLISION" + "ArchStdEvent": "SAMPLE_COLLISION", + "PublicDescription": "Counts statistical profiling samples that have collided with a previous sample and so therefore not taken." } ] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/spec_operation.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/spec_operation.json new file mode 100644 index 000000000000..1af961f8a6c8 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/spec_operation.json @@ -0,0 +1,110 @@ +[ + { + "ArchStdEvent": "BR_MIS_PRED", + "PublicDescription": "Counts branches which are speculatively executed and mispredicted." + }, + { + "ArchStdEvent": "BR_PRED", + "PublicDescription": "Counts branches speculatively executed and were predicted right." + }, + { + "ArchStdEvent": "INST_SPEC", + "PublicDescription": "Counts operations that have been speculatively executed." + }, + { + "ArchStdEvent": "OP_SPEC", + "PublicDescription": "Counts micro-operations speculatively executed. This is the count of the number of micro-operations dispatched in a cycle." + }, + { + "ArchStdEvent": "UNALIGNED_LD_SPEC", + "PublicDescription": "Counts unaligned memory read operations issued by the CPU. This event counts unaligned accesses (as defined by the actual instruction), even if they are subsequently issued as multiple aligned accesses. The event does not count preload operations (PLD, PLI)." + }, + { + "ArchStdEvent": "UNALIGNED_ST_SPEC", + "PublicDescription": "Counts unaligned memory write operations issued by the CPU. This event counts unaligned accesses (as defined by the actual instruction), even if they are subsequently issued as multiple aligned accesses." + }, + { + "ArchStdEvent": "UNALIGNED_LDST_SPEC", + "PublicDescription": "Counts unaligned memory operations issued by the CPU. This event counts unaligned accesses (as defined by the actual instruction), even if they are subsequently issued as multiple aligned accesses." + }, + { + "ArchStdEvent": "LDREX_SPEC", + "PublicDescription": "Counts Load-Exclusive operations that have been speculatively executed. Eg: LDREX, LDX" + }, + { + "ArchStdEvent": "STREX_PASS_SPEC", + "PublicDescription": "Counts store-exclusive operations that have been speculatively executed and have successfully completed the store operation." + }, + { + "ArchStdEvent": "STREX_FAIL_SPEC", + "PublicDescription": "Counts store-exclusive operations that have been speculatively executed and have not successfully completed the store operation." + }, + { + "ArchStdEvent": "STREX_SPEC", + "PublicDescription": "Counts store-exclusive operations that have been speculatively executed." + }, + { + "ArchStdEvent": "LD_SPEC", + "PublicDescription": "Counts speculatively executed load operations including Single Instruction Multiple Data (SIMD) load operations." + }, + { + "ArchStdEvent": "ST_SPEC", + "PublicDescription": "Counts speculatively executed store operations including Single Instruction Multiple Data (SIMD) store operations." + }, + { + "ArchStdEvent": "DP_SPEC", + "PublicDescription": "Counts speculatively executed logical or arithmetic instructions such as MOV/MVN operations." + }, + { + "ArchStdEvent": "ASE_SPEC", + "PublicDescription": "Counts speculatively executed Advanced SIMD operations excluding load, store and move micro-operations that move data to or from SIMD (vector) registers." + }, + { + "ArchStdEvent": "VFP_SPEC", + "PublicDescription": "Counts speculatively executed floating point operations. This event does not count operations that move data to or from floating point (vector) registers." + }, + { + "ArchStdEvent": "PC_WRITE_SPEC", + "PublicDescription": "Counts speculatively executed operations which cause software changes of the PC. Those operations include all taken branch operations." + }, + { + "ArchStdEvent": "CRYPTO_SPEC", + "PublicDescription": "Counts speculatively executed cryptographic operations except for PMULL and VMULL operations." + }, + { + "ArchStdEvent": "BR_IMMED_SPEC", + "PublicDescription": "Counts immediate branch operations which are speculatively executed." + }, + { + "ArchStdEvent": "BR_RETURN_SPEC", + "PublicDescription": "Counts procedure return operations (RET) which are speculatively executed." + }, + { + "ArchStdEvent": "BR_INDIRECT_SPEC", + "PublicDescription": "Counts indirect branch operations including procedure returns, which are speculatively executed. This includes operations that force a software change of the PC, other than exception-generating operations. Eg: BR Xn, RET" + }, + { + "ArchStdEvent": "ISB_SPEC", + "PublicDescription": "Counts ISB operations that are executed." + }, + { + "ArchStdEvent": "DSB_SPEC", + "PublicDescription": "Counts DSB operations that are speculatively issued to Load/Store unit in the CPU." + }, + { + "ArchStdEvent": "DMB_SPEC", + "PublicDescription": "Counts DMB operations that are speculatively issued to the Load/Store unit in the CPU. This event does not count implied barriers from load acquire/store release operations." + }, + { + "ArchStdEvent": "RC_LD_SPEC", + "PublicDescription": "Counts any load acquire operations that are speculatively executed. Eg: LDAR, LDARH, LDARB" + }, + { + "ArchStdEvent": "RC_ST_SPEC", + "PublicDescription": "Counts any store release operations that are speculatively executed. Eg: STLR, STLRH, STLRB'" + }, + { + "ArchStdEvent": "ASE_INST_SPEC", + "PublicDescription": "Counts speculatively executed Advanced SIMD operations." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/stall.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/stall.json new file mode 100644 index 000000000000..bbbebc805034 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/stall.json @@ -0,0 +1,30 @@ +[ + { + "ArchStdEvent": "STALL_FRONTEND", + "PublicDescription": "Counts cycles when frontend could not send any micro-operations to the rename stage because of frontend resource stalls caused by fetch memory latency or branch prediction flow stalls. All the frontend slots were empty during the cycle when this event counts." + }, + { + "ArchStdEvent": "STALL_BACKEND", + "PublicDescription": "Counts cycles whenever the rename unit is unable to send any micro-operations to the backend of the pipeline because of backend resource constraints. Backend resource constraints can include issue stage fullness, execution stage fullness, or other internal pipeline resource fullness. All the backend slots were empty during the cycle when this event counts." + }, + { + "ArchStdEvent": "STALL", + "PublicDescription": "Counts cycles when no operations are sent to the rename unit from the frontend or from the rename unit to the backend for any reason (either frontend or backend stall)." + }, + { + "ArchStdEvent": "STALL_SLOT_BACKEND", + "PublicDescription": "Counts slots per cycle in which no operations are sent from the rename unit to the backend due to backend resource constraints." + }, + { + "ArchStdEvent": "STALL_SLOT_FRONTEND", + "PublicDescription": "Counts slots per cycle in which no operations are sent to the rename unit from the frontend due to frontend resource constraints." + }, + { + "ArchStdEvent": "STALL_SLOT", + "PublicDescription": "Counts slots per cycle in which no operations are sent to the rename unit from the frontend or from the rename unit to the backend for any reason (either frontend or backend stall)." + }, + { + "ArchStdEvent": "STALL_BACKEND_MEM", + "PublicDescription": "Counts cycles when the backend is stalled because there is a pending demand load request in progress in the last level core cache." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/sve.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/sve.json new file mode 100644 index 000000000000..51dab48cb2ba --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/sve.json @@ -0,0 +1,50 @@ +[ + { + "ArchStdEvent": "SVE_INST_SPEC", + "PublicDescription": "Counts speculatively executed operations that are SVE operations." + }, + { + "ArchStdEvent": "SVE_PRED_SPEC", + "PublicDescription": "Counts speculatively executed predicated SVE operations." + }, + { + "ArchStdEvent": "SVE_PRED_EMPTY_SPEC", + "PublicDescription": "Counts speculatively executed predicated SVE operations with no active predicate elements." + }, + { + "ArchStdEvent": "SVE_PRED_FULL_SPEC", + "PublicDescription": "Counts speculatively executed predicated SVE operations with all predicate elements active." + }, + { + "ArchStdEvent": "SVE_PRED_PARTIAL_SPEC", + "PublicDescription": "Counts speculatively executed predicated SVE operations with at least one but not all active predicate elements." + }, + { + "ArchStdEvent": "SVE_PRED_NOT_FULL_SPEC", + "PublicDescription": "Counts speculatively executed predicated SVE operations with at least one non active predicate elements." + }, + { + "ArchStdEvent": "SVE_LDFF_SPEC", + "PublicDescription": "Counts speculatively executed SVE first fault or non-fault load operations." + }, + { + "ArchStdEvent": "SVE_LDFF_FAULT_SPEC", + "PublicDescription": "Counts speculatively executed SVE first fault or non-fault load operations that clear at least one bit in the FFR." + }, + { + "ArchStdEvent": "ASE_SVE_INT8_SPEC", + "PublicDescription": "Counts speculatively executed Advanced SIMD or SVE integer operations with the largest data type an 8-bit integer." + }, + { + "ArchStdEvent": "ASE_SVE_INT16_SPEC", + "PublicDescription": "Counts speculatively executed Advanced SIMD or SVE integer operations with the largest data type a 16-bit integer." + }, + { + "ArchStdEvent": "ASE_SVE_INT32_SPEC", + "PublicDescription": "Counts speculatively executed Advanced SIMD or SVE integer operations with the largest data type a 32-bit integer." + }, + { + "ArchStdEvent": "ASE_SVE_INT64_SPEC", + "PublicDescription": "Counts speculatively executed Advanced SIMD or SVE integer operations with the largest data type a 64-bit integer." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/tlb.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/tlb.json new file mode 100644 index 000000000000..b550af1831f5 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/tlb.json @@ -0,0 +1,66 @@ +[ + { + "ArchStdEvent": "L1I_TLB_REFILL", + "PublicDescription": "Counts level 1 instruction TLB refills from any Instruction fetch. If there are multiple misses in the TLB that are resolved by the refill, then this event only counts once. This event will not count if the translation table walk results in a fault (such as a translation or access fault), since there is no new translation created for the TLB." + }, + { + "ArchStdEvent": "L1D_TLB_REFILL", + "PublicDescription": "Counts level 1 data TLB accesses that resulted in TLB refills. If there are multiple misses in the TLB that are resolved by the refill, then this event only counts once. This event counts for refills caused by preload instructions or hardware prefetch accesses. This event counts regardless of whether the miss hits in L2 or results in a translation table walk. This event will not count if the translation table walk results in a fault (such as a translation or access fault), since there is no new translation created for the TLB. This event will not count on an access from an AT(address translation) instruction." + }, + { + "ArchStdEvent": "L1D_TLB", + "PublicDescription": "Counts level 1 data TLB accesses caused by any memory load or store operation. Note that load or store instructions can be broken up into multiple memory operations. This event does not count TLB maintenance operations." + }, + { + "ArchStdEvent": "L1I_TLB", + "PublicDescription": "Counts level 1 instruction TLB accesses, whether the access hits or misses in the TLB. This event counts both demand accesses and prefetch or preload generated accesses." + }, + { + "ArchStdEvent": "L2D_TLB_REFILL", + "PublicDescription": "Counts level 2 TLB refills caused by memory operations from both data and instruction fetch, except for those caused by TLB maintenance operations and hardware prefetches." + }, + { + "ArchStdEvent": "L2D_TLB", + "PublicDescription": "Counts level 2 TLB accesses except those caused by TLB maintenance operations." + }, + { + "ArchStdEvent": "DTLB_WALK", + "PublicDescription": "Counts data memory translation table walks caused by a miss in the L2 TLB driven by a memory access. Note that partial translations that also cause a table walk are counted. This event does not count table walks caused by TLB maintenance operations." + }, + { + "ArchStdEvent": "ITLB_WALK", + "PublicDescription": "Counts instruction memory translation table walks caused by a miss in the L2 TLB driven by a memory access. Partial translations that also cause a table walk are counted. This event does not count table walks caused by TLB maintenance operations." + }, + { + "ArchStdEvent": "L1D_TLB_REFILL_RD", + "PublicDescription": "Counts level 1 data TLB refills caused by memory read operations. If there are multiple misses in the TLB that are resolved by the refill, then this event only counts once. This event counts for refills caused by preload instructions or hardware prefetch accesses. This event counts regardless of whether the miss hits in L2 or results in a translation table walk. This event will not count if the translation table walk results in a fault (such as a translation or access fault), since there is no new translation created for the TLB. This event will not count on an access from an Address Translation (AT) instruction." + }, + { + "ArchStdEvent": "L1D_TLB_REFILL_WR", + "PublicDescription": "Counts level 1 data TLB refills caused by data side memory write operations. If there are multiple misses in the TLB that are resolved by the refill, then this event only counts once. This event counts for refills caused by preload instructions or hardware prefetch accesses. This event counts regardless of whether the miss hits in L2 or results in a translation table walk. This event will not count if the table walk results in a fault (such as a translation or access fault), since there is no new translation created for the TLB. This event will not count with an access from an Address Translation (AT) instruction." + }, + { + "ArchStdEvent": "L1D_TLB_RD", + "PublicDescription": "Counts level 1 data TLB accesses caused by memory read operations. This event counts whether the access hits or misses in the TLB. This event does not count TLB maintenance operations." + }, + { + "ArchStdEvent": "L1D_TLB_WR", + "PublicDescription": "Counts any L1 data side TLB accesses caused by memory write operations. This event counts whether the access hits or misses in the TLB. This event does not count TLB maintenance operations." + }, + { + "ArchStdEvent": "L2D_TLB_REFILL_RD", + "PublicDescription": "Counts level 2 TLB refills caused by memory read operations from both data and instruction fetch except for those caused by TLB maintenance operations or hardware prefetches." + }, + { + "ArchStdEvent": "L2D_TLB_REFILL_WR", + "PublicDescription": "Counts level 2 TLB refills caused by memory write operations from both data and instruction fetch except for those caused by TLB maintenance operations." + }, + { + "ArchStdEvent": "L2D_TLB_RD", + "PublicDescription": "Counts level 2 TLB accesses caused by memory read operations from both data and instruction fetch except for those caused by TLB maintenance operations." + }, + { + "ArchStdEvent": "L2D_TLB_WR", + "PublicDescription": "Counts level 2 TLB accesses caused by memory write operations from both data and instruction fetch except for those caused by TLB maintenance operations." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/trace.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/trace.json index 3116135c59e2..98f6fabfebc7 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/trace.json +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/trace.json @@ -1,29 +1,38 @@ [ { - "ArchStdEvent": "TRB_WRAP" + "ArchStdEvent": "TRB_WRAP", + "PublicDescription": "This event is generated each time the current write pointer is wrapped to the base pointer." }, { - "ArchStdEvent": "TRCEXTOUT0" + "ArchStdEvent": "TRCEXTOUT0", + "PublicDescription": "This event is generated each time an event is signaled by ETE external event 0." }, { - "ArchStdEvent": "TRCEXTOUT1" + "ArchStdEvent": "TRCEXTOUT1", + "PublicDescription": "This event is generated each time an event is signaled by ETE external event 1." }, { - "ArchStdEvent": "TRCEXTOUT2" + "ArchStdEvent": "TRCEXTOUT2", + "PublicDescription": "This event is generated each time an event is signaled by ETE external event 2." }, { - "ArchStdEvent": "TRCEXTOUT3" + "ArchStdEvent": "TRCEXTOUT3", + "PublicDescription": "This event is generated each time an event is signaled by ETE external event 3." }, { - "ArchStdEvent": "CTI_TRIGOUT4" + "ArchStdEvent": "CTI_TRIGOUT4", + "PublicDescription": "This event is generated each time an event is signaled on CTI output trigger 4." }, { - "ArchStdEvent": "CTI_TRIGOUT5" + "ArchStdEvent": "CTI_TRIGOUT5", + "PublicDescription": "This event is generated each time an event is signaled on CTI output trigger 5." }, { - "ArchStdEvent": "CTI_TRIGOUT6" + "ArchStdEvent": "CTI_TRIGOUT6", + "PublicDescription": "This event is generated each time an event is signaled on CTI output trigger 6." }, { - "ArchStdEvent": "CTI_TRIGOUT7" + "ArchStdEvent": "CTI_TRIGOUT7", + "PublicDescription": "This event is generated each time an event is signaled on CTI output trigger 7." } ] diff --git a/tools/perf/pmu-events/arch/arm64/freescale/yitian710/sys/ali_drw.json b/tools/perf/pmu-events/arch/arm64/freescale/yitian710/sys/ali_drw.json new file mode 100644 index 000000000000..e21c469a8ef0 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/freescale/yitian710/sys/ali_drw.json @@ -0,0 +1,373 @@ +[ + { + "BriefDescription": "A Write or Read Op at HIF interface. The unit is 64B.", + "ConfigCode": "0x0", + "EventName": "hif_rd_or_wr", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "A Write Op at HIF interface. The unit is 64B.", + "ConfigCode": "0x1", + "EventName": "hif_wr", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "A Read Op at HIF interface. The unit is 64B.", + "ConfigCode": "0x2", + "EventName": "hif_rd", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "A Read-Modify-Write Op at HIF interface. The unit is 64B.", + "ConfigCode": "0x3", + "EventName": "hif_rmw", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "A high priority Read at HIF interface. The unit is 64B.", + "ConfigCode": "0x4", + "EventName": "hif_hi_pri_rd", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "A write data cycle at DFI interface (to DRAM).", + "ConfigCode": "0x7", + "EventName": "dfi_wr_data_cycles", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "A read data cycle at DFI interface (to DRAM).", + "ConfigCode": "0x8", + "EventName": "dfi_rd_data_cycles", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "A high priority read becomes critical.", + "ConfigCode": "0x9", + "EventName": "hpr_xact_when_critical", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "A low priority read becomes critical.", + "ConfigCode": "0xA", + "EventName": "lpr_xact_when_critical", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "A write becomes critical.", + "ConfigCode": "0xB", + "EventName": "wr_xact_when_critical", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "An Activate(ACT) command to DRAM.", + "ConfigCode": "0xC", + "EventName": "op_is_activate", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "A Read or Write CAS command to DRAM.", + "ConfigCode": "0xD", + "EventName": "op_is_rd_or_wr", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "An Activate(ACT) command for read to DRAM.", + "ConfigCode": "0xE", + "EventName": "op_is_rd_activate", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "A Read CAS command to DRAM.", + "ConfigCode": "0xF", + "EventName": "op_is_rd", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "A Write CAS command to DRAM.", + "ConfigCode": "0x10", + "EventName": "op_is_wr", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "A Masked Write command to DRAM.", + "ConfigCode": "0x11", + "EventName": "op_is_mwr", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "A Precharge(PRE) command to DRAM.", + "ConfigCode": "0x12", + "EventName": "op_is_precharge", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "A Precharge(PRE) required by read or write.", + "ConfigCode": "0x13", + "EventName": "precharge_for_rdwr", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "A Precharge(PRE) required by other conditions.", + "ConfigCode": "0x14", + "EventName": "precharge_for_other", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "A read-write turnaround.", + "ConfigCode": "0x15", + "EventName": "rdwr_transitions", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "A write combine(merge) in write data buffer.", + "ConfigCode": "0x16", + "EventName": "write_combine", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "A Write-After-Read hazard.", + "ConfigCode": "0x17", + "EventName": "war_hazard", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "A Read-After-Write hazard.", + "ConfigCode": "0x18", + "EventName": "raw_hazard", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "A Write-After-Write hazard.", + "ConfigCode": "0x19", + "EventName": "waw_hazard", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "Rank0 enters self-refresh(SRE).", + "ConfigCode": "0x1A", + "EventName": "op_is_enter_selfref_rk0", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "Rank1 enters self-refresh(SRE).", + "ConfigCode": "0x1B", + "EventName": "op_is_enter_selfref_rk1", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "Rank2 enters self-refresh(SRE).", + "ConfigCode": "0x1C", + "EventName": "op_is_enter_selfref_rk2", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "Rank3 enters self-refresh(SRE).", + "ConfigCode": "0x1D", + "EventName": "op_is_enter_selfref_rk3", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "Rank0 enters power-down(PDE).", + "ConfigCode": "0x1E", + "EventName": "op_is_enter_powerdown_rk0", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "Rank1 enters power-down(PDE).", + "ConfigCode": "0x1F", + "EventName": "op_is_enter_powerdown_rk1", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "Rank2 enters power-down(PDE).", + "ConfigCode": "0x20", + "EventName": "op_is_enter_powerdown_rk2", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "Rank3 enters power-down(PDE).", + "ConfigCode": "0x21", + "EventName": "op_is_enter_powerdown_rk3", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "A cycle that Rank0 stays in self-refresh mode.", + "ConfigCode": "0x26", + "EventName": "selfref_mode_rk0", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "A cycle that Rank1 stays in self-refresh mode.", + "ConfigCode": "0x27", + "EventName": "selfref_mode_rk1", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "A cycle that Rank2 stays in self-refresh mode.", + "ConfigCode": "0x28", + "EventName": "selfref_mode_rk2", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "A cycle that Rank3 stays in self-refresh mode.", + "ConfigCode": "0x29", + "EventName": "selfref_mode_rk3", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "An auto-refresh(REF) command to DRAM.", + "ConfigCode": "0x2A", + "EventName": "op_is_refresh", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "A critical auto-refresh(REF) command to DRAM.", + "ConfigCode": "0x2B", + "EventName": "op_is_crit_ref", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "An MRR or MRW command to DRAM.", + "ConfigCode": "0x2D", + "EventName": "op_is_load_mode", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "A ZQCal command to DRAM.", + "ConfigCode": "0x2E", + "EventName": "op_is_zqcl", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "At least one entry in read queue reaches the visible window limit.", + "ConfigCode": "0x30", + "EventName": "visible_window_limit_reached_rd", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "At least one entry in write queue reaches the visible window limit.", + "ConfigCode": "0x31", + "EventName": "visible_window_limit_reached_wr", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "A DQS Oscillator MPC command to DRAM.", + "ConfigCode": "0x34", + "EventName": "op_is_dqsosc_mpc", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "A DQS Oscillator MRR command to DRAM.", + "ConfigCode": "0x35", + "EventName": "op_is_dqsosc_mrr", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "A Temperature Compensated Refresh(TCR) MRR command to DRAM.", + "ConfigCode": "0x36", + "EventName": "op_is_tcr_mrr", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "A ZQCal Start command to DRAM.", + "ConfigCode": "0x37", + "EventName": "op_is_zqstart", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "A ZQCal Latch command to DRAM.", + "ConfigCode": "0x38", + "EventName": "op_is_zqlatch", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "A packet at CHI TXREQ interface (request).", + "ConfigCode": "0x39", + "EventName": "chi_txreq", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "A packet at CHI TXDAT interface (read data).", + "ConfigCode": "0x3A", + "EventName": "chi_txdat", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "A packet at CHI RXDAT interface (write data).", + "ConfigCode": "0x3B", + "EventName": "chi_rxdat", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "A packet at CHI RXRSP interface.", + "ConfigCode": "0x3C", + "EventName": "chi_rxrsp", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "A violation detected in TZC.", + "ConfigCode": "0x3D", + "EventName": "tsz_vio", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "BriefDescription": "The ddr cycles.", + "ConfigCode": "0x80", + "EventName": "ddr_cycles", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/freescale/yitian710/sys/metrics.json b/tools/perf/pmu-events/arch/arm64/freescale/yitian710/sys/metrics.json new file mode 100644 index 000000000000..bc865b374b6a --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/freescale/yitian710/sys/metrics.json @@ -0,0 +1,20 @@ +[ + { + "MetricName": "ddr_read_bandwidth.all", + "BriefDescription": "The ddr read bandwidth(MB/s).", + "MetricGroup": "ali_drw", + "MetricExpr": "hif_rd * 64 / 1e6 / duration_time", + "ScaleUnit": "1MB/s", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + }, + { + "MetricName": "ddr_write_bandwidth.all", + "BriefDescription": "The ddr write bandwidth(MB/s).", + "MetricGroup": "ali_drw", + "MetricExpr": "(hif_wr + hif_rmw) * 64 / 1e6 / duration_time", + "ScaleUnit": "1MB/s", + "Unit": "ali_drw", + "Compat": "ali_drw_pmu" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/sbsa.json b/tools/perf/pmu-events/arch/arm64/sbsa.json index f90b338261ac..4eed79a28f6e 100644 --- a/tools/perf/pmu-events/arch/arm64/sbsa.json +++ b/tools/perf/pmu-events/arch/arm64/sbsa.json @@ -1,34 +1,34 @@ [ { - "MetricExpr": "stall_slot_frontend / (#slots * cpu_cycles)", - "BriefDescription": "Frontend bound L1 topdown metric", + "MetricExpr": "100 * (stall_slot_frontend / (#slots * cpu_cycles))", + "BriefDescription": "This metric is the percentage of total slots that were stalled due to resource constraints in the frontend of the processor.", "DefaultMetricgroupName": "TopdownL1", "MetricGroup": "Default;TopdownL1", "MetricName": "frontend_bound", - "ScaleUnit": "100%" + "ScaleUnit": "1percent of slots" }, { - "MetricExpr": "(1 - op_retired / op_spec) * (1 - stall_slot / (#slots * cpu_cycles))", - "BriefDescription": "Bad speculation L1 topdown metric", + "MetricExpr": "100 * ((1 - op_retired / op_spec) * (1 - stall_slot / (#slots * cpu_cycles)))", + "BriefDescription": "This metric is the percentage of total slots that executed operations and didn't retire due to a pipeline flush.\nThis indicates cycles that were utilized but inefficiently.", "DefaultMetricgroupName": "TopdownL1", "MetricGroup": "Default;TopdownL1", "MetricName": "bad_speculation", - "ScaleUnit": "100%" + "ScaleUnit": "1percent of slots" }, { - "MetricExpr": "(op_retired / op_spec) * (1 - stall_slot / (#slots * cpu_cycles))", - "BriefDescription": "Retiring L1 topdown metric", + "MetricExpr": "100 * ((op_retired / op_spec) * (1 - stall_slot / (#slots * cpu_cycles)))", + "BriefDescription": "This metric is the percentage of total slots that retired operations, which indicates cycles that were utilized efficiently.", "DefaultMetricgroupName": "TopdownL1", "MetricGroup": "Default;TopdownL1", "MetricName": "retiring", - "ScaleUnit": "100%" + "ScaleUnit": "1percent of slots" }, { - "MetricExpr": "stall_slot_backend / (#slots * cpu_cycles)", - "BriefDescription": "Backend Bound L1 topdown metric", + "MetricExpr": "100 * (stall_slot_backend / (#slots * cpu_cycles))", + "BriefDescription": "This metric is the percentage of total slots that were stalled due to resource constraints in the backend of the processor.", "DefaultMetricgroupName": "TopdownL1", "MetricGroup": "Default;TopdownL1", "MetricName": "backend_bound", - "ScaleUnit": "100%" + "ScaleUnit": "1percent of slots" } ] diff --git a/tools/perf/pmu-events/arch/powerpc/power10/cache.json b/tools/perf/pmu-events/arch/powerpc/power10/cache.json index 605be14f441c..839ae26945fb 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/cache.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/cache.json @@ -1,53 +1,8 @@ [ { - "EventCode": "0x1003C", - "EventName": "PM_EXEC_STALL_DMISS_L2L3", - "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from either the local L2 or local L3." - }, - { - "EventCode": "0x1E054", - "EventName": "PM_EXEC_STALL_DMISS_L21_L31", - "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from another core's L2 or L3 on the same chip." - }, - { - "EventCode": "0x34054", - "EventName": "PM_EXEC_STALL_DMISS_L2L3_NOCONFLICT", - "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from the local L2 or local L3, without a dispatch conflict." - }, - { - "EventCode": "0x34056", - "EventName": "PM_EXEC_STALL_LOAD_FINISH", - "BriefDescription": "Cycles in which the oldest instruction in the pipeline was finishing a load after its data was reloaded from a data source beyond the local L1; cycles in which the LSU was processing an L1-hit; cycles in which the NTF instruction merged with another load in the LMQ; cycles in which the NTF instruction is waiting for a data reload for a load miss, but the data comes back with a non-NTF instruction." - }, - { - "EventCode": "0x3006C", - "EventName": "PM_RUN_CYC_SMT2_MODE", - "BriefDescription": "Cycles when this thread's run latch is set and the core is in SMT2 mode." - }, - { "EventCode": "0x300F4", "EventName": "PM_RUN_INST_CMPL_CONC", - "BriefDescription": "PowerPC instructions completed by this thread when all threads in the core had the run-latch set." - }, - { - "EventCode": "0x4C016", - "EventName": "PM_EXEC_STALL_DMISS_L2L3_CONFLICT", - "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from the local L2 or local L3, with a dispatch conflict." - }, - { - "EventCode": "0x4D014", - "EventName": "PM_EXEC_STALL_LOAD", - "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a load instruction executing in the Load Store Unit." - }, - { - "EventCode": "0x4D016", - "EventName": "PM_EXEC_STALL_PTESYNC", - "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a PTESYNC instruction executing in the Load Store Unit." - }, - { - "EventCode": "0x401EA", - "EventName": "PM_THRESH_EXC_128", - "BriefDescription": "Threshold counter exceeded a value of 128." + "BriefDescription": "PowerPC instruction completed by this thread when all threads in the core had the run-latch set." }, { "EventCode": "0x400F6", diff --git a/tools/perf/pmu-events/arch/powerpc/power10/floating_point.json b/tools/perf/pmu-events/arch/powerpc/power10/floating_point.json index 54acb55e2c8c..e816cd10c129 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/floating_point.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/floating_point.json @@ -1,7 +1,67 @@ [ { - "EventCode": "0x4016E", - "EventName": "PM_THRESH_NOT_MET", - "BriefDescription": "Threshold counter did not meet threshold." + "EventCode": "0x100F4", + "EventName": "PM_FLOP_CMPL", + "BriefDescription": "Floating Point Operations Completed. Includes any type. It counts once for each 1, 2, 4 or 8 flop instruction. Use PM_1|2|4|8_FLOP_CMPL events to count flops." + }, + { + "EventCode": "0x45050", + "EventName": "PM_1FLOP_CMPL", + "BriefDescription": "One floating point instruction completed (fadd, fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg)." + }, + { + "EventCode": "0x45052", + "EventName": "PM_4FLOP_CMPL", + "BriefDescription": "Four floating point instruction completed (fadd, fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg)." + }, + { + "EventCode": "0x45054", + "EventName": "PM_FMA_CMPL", + "BriefDescription": "Two floating point instruction completed (FMA class of instructions: fmadd, fnmadd, fmsub, fnmsub). Scalar instructions only." + }, + { + "EventCode": "0x45056", + "EventName": "PM_SCALAR_FLOP_CMPL", + "BriefDescription": "Scalar floating point instruction completed." + }, + { + "EventCode": "0x4505A", + "EventName": "PM_SP_FLOP_CMPL", + "BriefDescription": "Single Precision floating point instruction completed." + }, + { + "EventCode": "0x4505C", + "EventName": "PM_MATH_FLOP_CMPL", + "BriefDescription": "Math floating point instruction completed." + }, + { + "EventCode": "0x4D052", + "EventName": "PM_2FLOP_CMPL", + "BriefDescription": "Double Precision vector version of fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg completed." + }, + { + "EventCode": "0x4D054", + "EventName": "PM_8FLOP_CMPL", + "BriefDescription": "Four Double Precision vector instruction completed." + }, + { + "EventCode": "0x4D056", + "EventName": "PM_NON_FMA_FLOP_CMPL", + "BriefDescription": "Non FMA instruction completed." + }, + { + "EventCode": "0x4D058", + "EventName": "PM_VECTOR_FLOP_CMPL", + "BriefDescription": "Vector floating point instruction completed." + }, + { + "EventCode": "0x4D05A", + "EventName": "PM_NON_MATH_FLOP_CMPL", + "BriefDescription": "Non Math instruction completed." + }, + { + "EventCode": "0x4D05C", + "EventName": "PM_DPP_FLOP_CMPL", + "BriefDescription": "Double-Precision or Quad-Precision instruction completed." } ] diff --git a/tools/perf/pmu-events/arch/powerpc/power10/frontend.json b/tools/perf/pmu-events/arch/powerpc/power10/frontend.json index 558f9530f54e..5977f5e64212 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/frontend.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/frontend.json @@ -1,43 +1,13 @@ [ { - "EventCode": "0x10004", - "EventName": "PM_EXEC_STALL_TRANSLATION", - "BriefDescription": "Cycles in which the oldest instruction in the pipeline suffered a TLB miss or ERAT miss and waited for it to resolve." + "EventCode": "0x1D054", + "EventName": "PM_DTLB_HIT_2M", + "BriefDescription": "Data TLB hit (DERAT reload) page size 2M. Implies radix translation. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "0x10006", - "EventName": "PM_DISP_STALL_HELD_OTHER_CYC", - "BriefDescription": "Cycles in which the NTC instruction is held at dispatch for any other reason." - }, - { - "EventCode": "0x10010", - "EventName": "PM_PMC4_OVERFLOW", - "BriefDescription": "The event selected for PMC4 caused the event counter to overflow." - }, - { - "EventCode": "0x10020", - "EventName": "PM_PMC4_REWIND", - "BriefDescription": "The speculative event selected for PMC4 rewinds and the counter for PMC4 is not charged." - }, - { - "EventCode": "0x10038", - "EventName": "PM_DISP_STALL_TRANSLATION", - "BriefDescription": "Cycles when dispatch was stalled for this thread because the MMU was handling a translation miss." - }, - { - "EventCode": "0x1003A", - "EventName": "PM_DISP_STALL_BR_MPRED_IC_L2", - "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L2 after suffering a branch mispredict." - }, - { - "EventCode": "0x1D05E", - "EventName": "PM_DISP_STALL_HELD_HALT_CYC", - "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because of power management." - }, - { - "EventCode": "0x1E050", - "EventName": "PM_DISP_STALL_HELD_STF_MAPPER_CYC", - "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because the STF mapper/SRB was full. Includes GPR (count, link, tar), VSR, VMR, FPR." + "EventCode": "0x1D058", + "EventName": "PM_ITLB_HIT_64K", + "BriefDescription": "Instruction TLB hit (IERAT reload) page size 64K. When MMCR1[17]=0 this event counts only for demand misses. When MMCR1[17]=1 this event includes demand misses and prefetches." }, { "EventCode": "0x1F054", @@ -45,21 +15,6 @@ "BriefDescription": "The PTE required by the instruction was resident in the TLB (data TLB access). When MMCR1[16]=0 this event counts only demand hits. When MMCR1[16]=1 this event includes demand and prefetch. Applies to both HPT and RPT." }, { - "EventCode": "0x10064", - "EventName": "PM_DISP_STALL_IC_L2", - "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L2." - }, - { - "EventCode": "0x101E8", - "EventName": "PM_THRESH_EXC_256", - "BriefDescription": "Threshold counter exceeded a count of 256." - }, - { - "EventCode": "0x101EC", - "EventName": "PM_THRESH_MET", - "BriefDescription": "Threshold exceeded." - }, - { "EventCode": "0x100F2", "EventName": "PM_1PLUS_PPC_CMPL", "BriefDescription": "Cycles in which at least one instruction is completed by this thread." @@ -67,57 +22,7 @@ { "EventCode": "0x100F6", "EventName": "PM_IERAT_MISS", - "BriefDescription": "IERAT Reloaded to satisfy an IERAT miss. All page sizes are counted by this event." - }, - { - "EventCode": "0x100F8", - "EventName": "PM_DISP_STALL_CYC", - "BriefDescription": "Cycles the ICT has no itags assigned to this thread (no instructions were dispatched during these cycles)." - }, - { - "EventCode": "0x20006", - "EventName": "PM_DISP_STALL_HELD_ISSQ_FULL_CYC", - "BriefDescription": "Cycles in which the NTC instruction is held at dispatch due to Issue queue full. Includes issue queue and branch queue." - }, - { - "EventCode": "0x20114", - "EventName": "PM_MRK_L2_RC_DISP", - "BriefDescription": "Marked instruction RC dispatched in L2." - }, - { - "EventCode": "0x2C010", - "EventName": "PM_EXEC_STALL_LSU", - "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in the Load Store Unit. This does not include simple fixed point instructions." - }, - { - "EventCode": "0x2C016", - "EventName": "PM_DISP_STALL_IERAT_ONLY_MISS", - "BriefDescription": "Cycles when dispatch was stalled while waiting to resolve an instruction ERAT miss." - }, - { - "EventCode": "0x2C01E", - "EventName": "PM_DISP_STALL_BR_MPRED_IC_L3", - "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L3 after suffering a branch mispredict." - }, - { - "EventCode": "0x2D01A", - "EventName": "PM_DISP_STALL_IC_MISS", - "BriefDescription": "Cycles when dispatch was stalled for this thread due to an Icache Miss." - }, - { - "EventCode": "0x2E018", - "EventName": "PM_DISP_STALL_FETCH", - "BriefDescription": "Cycles when dispatch was stalled for this thread because Fetch was being held." - }, - { - "EventCode": "0x2E01A", - "EventName": "PM_DISP_STALL_HELD_XVFC_MAPPER_CYC", - "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because the XVFC mapper/SRB was full." - }, - { - "EventCode": "0x2C142", - "EventName": "PM_MRK_XFER_FROM_SRC_PMC2", - "BriefDescription": "For a marked data transfer instruction, the processor's L1 data cache was reloaded from the source specified in MMCR3[15:27]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads." + "BriefDescription": "IERAT Reloaded to satisfy an IERAT miss. All page sizes are counted by this event. This event only counts instruction demand access." }, { "EventCode": "0x24050", @@ -135,11 +40,6 @@ "BriefDescription": "Branch Taken instruction completed." }, { - "EventCode": "0x30004", - "EventName": "PM_DISP_STALL_FLUSH", - "BriefDescription": "Cycles when dispatch was stalled because of a flush that happened to an instruction(s) that was not yet NTC. PM_EXEC_STALL_NTC_FLUSH only includes instructions that were flushed after becoming NTC." - }, - { "EventCode": "0x3000A", "EventName": "PM_DISP_STALL_ITLB_MISS", "BriefDescription": "Cycles when dispatch was stalled while waiting to resolve an instruction TLB miss." @@ -150,59 +50,24 @@ "BriefDescription": "The instruction that was next to complete (oldest in the pipeline) did not complete because it suffered a flush." }, { - "EventCode": "0x30014", - "EventName": "PM_EXEC_STALL_STORE", - "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a store instruction executing in the Load Store Unit." - }, - { - "EventCode": "0x30018", - "EventName": "PM_DISP_STALL_HELD_SCOREBOARD_CYC", - "BriefDescription": "Cycles in which the NTC instruction is held at dispatch while waiting on the Scoreboard. This event combines VSCR and FPSCR together." - }, - { - "EventCode": "0x30026", - "EventName": "PM_EXEC_STALL_STORE_MISS", - "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a store whose cache line was not resident in the L1 and was waiting for allocation of the missing line into the L1." - }, - { - "EventCode": "0x3012A", - "EventName": "PM_MRK_L2_RC_DONE", - "BriefDescription": "L2 RC machine completed the transaction for the marked instruction." - }, - { "EventCode": "0x3F046", "EventName": "PM_ITLB_HIT_1G", "BriefDescription": "Instruction TLB hit (IERAT reload) page size 1G, which implies Radix Page Table translation is in use. When MMCR1[17]=0 this event counts only for demand misses. When MMCR1[17]=1 this event includes demand misses and prefetches." }, { - "EventCode": "0x34058", - "EventName": "PM_DISP_STALL_BR_MPRED_ICMISS", - "BriefDescription": "Cycles when dispatch was stalled after a mispredicted branch resulted in an instruction cache miss." - }, - { - "EventCode": "0x3D05C", - "EventName": "PM_DISP_STALL_HELD_RENAME_CYC", - "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because the mapper/SRB was full. Includes GPR (count, link, tar), VSR, VMR, FPR and XVFC." - }, - { - "EventCode": "0x3E052", - "EventName": "PM_DISP_STALL_IC_L3", - "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L3." + "EventCode": "0x3C05A", + "EventName": "PM_DTLB_HIT_64K", + "BriefDescription": "Data TLB hit (DERAT reload) page size 64K. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { "EventCode": "0x3E054", "EventName": "PM_LD_MISS_L1", - "BriefDescription": "Load Missed L1, counted at execution time (can be greater than loads finished). LMQ merges are not included in this count. i.e. if a load instruction misses on an address that is already allocated on the LMQ, this event will not increment for that load). Note that this count is per slice, so if a load spans multiple slices this event will increment multiple times for a single load." - }, - { - "EventCode": "0x301EA", - "EventName": "PM_THRESH_EXC_1024", - "BriefDescription": "Threshold counter exceeded a value of 1024." + "BriefDescription": "Load missed L1, counted at finish time. LMQ merges are not included in this count. i.e. if a load instruction misses on an address that is already allocated on the LMQ, this event will not increment for that load). Note that this count is per slice, so if a load spans multiple slices this event will increment multiple times for a single load." }, { "EventCode": "0x300FA", "EventName": "PM_INST_FROM_L3MISS", - "BriefDescription": "The processor's instruction cache was reloaded from a source other than the local core's L1, L2, or L3 due to a demand miss." + "BriefDescription": "The processor's instruction cache was reloaded from beyond the local core's L3 due to a demand miss." }, { "EventCode": "0x40006", @@ -210,38 +75,18 @@ "BriefDescription": "Cycles in which an instruction or group of instructions were cancelled after being issued. This event increments once per occurrence, regardless of how many instructions are included in the issue group." }, { - "EventCode": "0x40116", - "EventName": "PM_MRK_LARX_FIN", - "BriefDescription": "Marked load and reserve instruction (LARX) finished. LARX and STCX are instructions used to acquire a lock." - }, - { - "EventCode": "0x4C010", - "EventName": "PM_DISP_STALL_BR_MPRED_IC_L3MISS", - "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from sources beyond the local L3 after suffering a mispredicted branch." - }, - { - "EventCode": "0x4D01E", - "EventName": "PM_DISP_STALL_BR_MPRED", - "BriefDescription": "Cycles when dispatch was stalled for this thread due to a mispredicted branch." - }, - { - "EventCode": "0x4E010", - "EventName": "PM_DISP_STALL_IC_L3MISS", - "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from any source beyond the local L3." - }, - { - "EventCode": "0x4E01A", - "EventName": "PM_DISP_STALL_HELD_CYC", - "BriefDescription": "Cycles in which the NTC instruction is held at dispatch for any reason." + "EventCode": "0x44056", + "EventName": "PM_VECTOR_ST_CMPL", + "BriefDescription": "Vector store instruction completed." }, { - "EventCode": "0x4003C", - "EventName": "PM_DISP_STALL_HELD_SYNC_CYC", - "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because of a synchronizing instruction that requires the ICT to be empty before dispatch." + "EventCode": "0x4E054", + "EventName": "PM_DTLB_HIT_1G", + "BriefDescription": "Data TLB hit (DERAT reload) page size 1G. Implies radix translation. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "0x44056", - "EventName": "PM_VECTOR_ST_CMPL", - "BriefDescription": "Vector store instructions completed." + "EventCode": "0x400FC", + "EventName": "PM_ITLB_MISS", + "BriefDescription": "Instruction TLB reload (after a miss), all page sizes. Includes only demand misses." } ] diff --git a/tools/perf/pmu-events/arch/powerpc/power10/marked.json b/tools/perf/pmu-events/arch/powerpc/power10/marked.json index 58b5dfe3a273..78f71a9eadfd 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/marked.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/marked.json @@ -1,15 +1,35 @@ [ { - "EventCode": "0x1002C", - "EventName": "PM_LD_PREFETCH_CACHE_LINE_MISS", - "BriefDescription": "The L1 cache was reloaded with a line that fulfills a prefetch request." - }, - { "EventCode": "0x10132", "EventName": "PM_MRK_INST_ISSUED", "BriefDescription": "Marked instruction issued. Note that stores always get issued twice, the address gets issued to the LSU and the data gets issued to the VSU. Also, issues can sometimes get killed/cancelled and cause multiple sequential issues for the same instruction." }, { + "EventCode": "0x10134", + "EventName": "PM_MRK_ST_DONE_L2", + "BriefDescription": "Marked store completed in L2." + }, + { + "EventCode": "0x1C142", + "EventName": "PM_MRK_XFER_FROM_SRC_PMC1", + "BriefDescription": "For a marked data transfer instruction, the processor's L1 data cache was reloaded from the source specified in MMCR3[0:12]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads." + }, + { + "EventCode": "0x1C144", + "EventName": "PM_MRK_XFER_FROM_SRC_CYC_PMC1", + "BriefDescription": "Cycles taken for a marked demand miss to reload a line from the source specified in MMCR3[0:12]." + }, + { + "EventCode": "0x1D15C", + "EventName": "PM_MRK_DTLB_MISS_1G", + "BriefDescription": "Marked Data TLB reload (after a miss) page size 1G. Implies radix translation was used. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." + }, + { + "EventCode": "0x1F150", + "EventName": "PM_MRK_ST_L2_CYC", + "BriefDescription": "Cycles from L2 RC dispatch to L2 RC completion." + }, + { "EventCode": "0x101E0", "EventName": "PM_MRK_INST_DISP", "BriefDescription": "The thread has dispatched a randomly sampled marked instruction." @@ -20,14 +40,39 @@ "BriefDescription": "Marked Branch Taken instruction completed." }, { - "EventCode": "0x20112", - "EventName": "PM_MRK_NTF_FIN", - "BriefDescription": "The marked instruction became the oldest in the pipeline before it finished. It excludes instructions that finish at dispatch." + "EventCode": "0x101E4", + "EventName": "PM_MRK_L1_ICACHE_MISS", + "BriefDescription": "Marked instruction suffered an instruction cache miss." + }, + { + "EventCode": "0x101EA", + "EventName": "PM_MRK_L1_RELOAD_VALID", + "BriefDescription": "Marked demand reload." }, { - "EventCode": "0x2C01C", - "EventName": "PM_EXEC_STALL_DMISS_OFF_CHIP", - "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from a remote chip." + "EventCode": "0x20114", + "EventName": "PM_MRK_L2_RC_DISP", + "BriefDescription": "Marked instruction RC dispatched in L2." + }, + { + "EventCode": "0x2011C", + "EventName": "PM_MRK_NTF_CYC", + "BriefDescription": "Cycles in which the marked instruction is the oldest in the pipeline (next-to-finish or next-to-complete)." + }, + { + "EventCode": "0x20130", + "EventName": "PM_MRK_INST_DECODED", + "BriefDescription": "An instruction was marked at decode time. Random Instruction Sampling (RIS) only." + }, + { + "EventCode": "0x20132", + "EventName": "PM_MRK_DFU_ISSUE", + "BriefDescription": "The marked instruction was a decimal floating point operation issued to the VSU. Measured at issue time." + }, + { + "EventCode": "0x20134", + "EventName": "PM_MRK_FXU_ISSUE", + "BriefDescription": "The marked instruction was a fixed point operation issued to the VSU. Measured at issue time." }, { "EventCode": "0x20138", @@ -40,6 +85,16 @@ "BriefDescription": "Marked Branch instruction finished." }, { + "EventCode": "0x2013C", + "EventName": "PM_MRK_FX_LSU_FIN", + "BriefDescription": "The marked instruction was simple fixed point that was issued to the store unit. Measured at finish time." + }, + { + "EventCode": "0x2C142", + "EventName": "PM_MRK_XFER_FROM_SRC_PMC2", + "BriefDescription": "For a marked data transfer instruction, the processor's L1 data cache was reloaded from the source specified in MMCR3[15:27]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads." + }, + { "EventCode": "0x2C144", "EventName": "PM_MRK_XFER_FROM_SRC_CYC_PMC2", "BriefDescription": "Cycles taken for a marked demand miss to reload a line from the source specified in MMCR3[15:27]." @@ -60,19 +115,54 @@ "BriefDescription": "A marked branch completed. All branches are included." }, { - "EventCode": "0x200FD", - "EventName": "PM_L1_ICACHE_MISS", - "BriefDescription": "Demand iCache Miss." + "EventCode": "0x2D154", + "EventName": "PM_MRK_DERAT_MISS_64K", + "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 64K for a marked instruction. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." + }, + { + "EventCode": "0x201E0", + "EventName": "PM_MRK_DATA_FROM_MEMORY", + "BriefDescription": "The processor's data cache was reloaded from local, remote, or distant memory due to a demand miss for a marked load." }, { - "EventCode": "0x30130", - "EventName": "PM_MRK_INST_FIN", - "BriefDescription": "marked instruction finished. Excludes instructions that finish at dispatch. Note that stores always finish twice since the address gets issued to the LSU and the data gets issued to the VSU." + "EventCode": "0x201E2", + "EventName": "PM_MRK_LD_MISS_L1", + "BriefDescription": "Marked demand data load miss counted at finish time." + }, + { + "EventCode": "0x201E4", + "EventName": "PM_MRK_DATA_FROM_L3MISS", + "BriefDescription": "The processor's data cache was reloaded from a source other than the local core's L1, L2, or L3 due to a demand miss for a marked load." + }, + { + "EventCode": "0x3012A", + "EventName": "PM_MRK_L2_RC_DONE", + "BriefDescription": "L2 RC machine completed the transaction for the marked instruction." + }, + { + "EventCode": "0x3012E", + "EventName": "PM_MRK_DTLB_MISS_2M", + "BriefDescription": "Marked Data TLB reload (after a miss) page size 2M, which implies Radix Page Table translation was used. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." + }, + { + "EventCode": "0x30132", + "EventName": "PM_MRK_VSU_FIN", + "BriefDescription": "VSU marked instruction finished. Excludes simple FX instructions issued to the Store Unit." }, { "EventCode": "0x34146", "EventName": "PM_MRK_LD_CMPL", - "BriefDescription": "Marked loads completed." + "BriefDescription": "Marked load instruction completed." + }, + { + "EventCode": "0x3C142", + "EventName": "PM_MRK_XFER_FROM_SRC_PMC3", + "BriefDescription": "For a marked data transfer instruction, the processor's L1 data cache was reloaded from the source specified in MMCR3[30:42]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads." + }, + { + "EventCode": "0x3C144", + "EventName": "PM_MRK_XFER_FROM_SRC_CYC_PMC3", + "BriefDescription": "Cycles taken for a marked demand miss to reload a line from the source specified in MMCR3[30:42]." }, { "EventCode": "0x3E158", @@ -82,12 +172,22 @@ { "EventCode": "0x3E15A", "EventName": "PM_MRK_ST_FIN", - "BriefDescription": "The marked instruction was a store of any kind." + "BriefDescription": "Marked store instruction finished." + }, + { + "EventCode": "0x3F150", + "EventName": "PM_MRK_ST_DRAIN_CYC", + "BriefDescription": "Cycles in which the marked store drained from the core to the L2." }, { - "EventCode": "0x30068", - "EventName": "PM_L1_ICACHE_RELOADED_PREF", - "BriefDescription": "Counts all Icache prefetch reloads ( includes demand turned into prefetch)." + "EventCode": "0x30162", + "EventName": "PM_MRK_ISSUE_DEPENDENT_LOAD", + "BriefDescription": "The marked instruction was dependent on a load. It is eligible for issue kill." + }, + { + "EventCode": "0x301E2", + "EventName": "PM_MRK_ST_CMPL", + "BriefDescription": "Marked store completed and sent to nest. Note that this count excludes cache-inhibited stores." }, { "EventCode": "0x301E4", @@ -95,48 +195,78 @@ "BriefDescription": "Marked Branch Mispredicted. Includes direction and target." }, { - "EventCode": "0x300F6", - "EventName": "PM_LD_DEMAND_MISS_L1", - "BriefDescription": "The L1 cache was reloaded with a line that fulfills a demand miss request. Counted at reload time, before finish." + "EventCode": "0x301E6", + "EventName": "PM_MRK_DERAT_MISS", + "BriefDescription": "Marked Erat Miss (Data TLB Access) All page sizes. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." + }, + { + "EventCode": "0x4010E", + "EventName": "PM_MRK_TLBIE_FIN", + "BriefDescription": "Marked TLBIE instruction finished. Includes TLBIE and TLBIEL instructions." + }, + { + "EventCode": "0x40116", + "EventName": "PM_MRK_LARX_FIN", + "BriefDescription": "Marked load and reserve instruction (LARX) finished. LARX and STCX are instructions used to acquire a lock." + }, + { + "EventCode": "0x40132", + "EventName": "PM_MRK_LSU_FIN", + "BriefDescription": "LSU marked instruction finish." + }, + { + "EventCode": "0x44146", + "EventName": "PM_MRK_STCX_CORE_CYC", + "BriefDescription": "Cycles spent in the core portion of a marked STCX instruction. It starts counting when the instruction is decoded and stops counting when it drains into the L2." }, { - "EventCode": "0x300FE", - "EventName": "PM_DATA_FROM_L3MISS", - "BriefDescription": "The processor's data cache was reloaded from a source other than the local core's L1, L2, or L3 due to a demand miss." + "EventCode": "0x4C142", + "EventName": "PM_MRK_XFER_FROM_SRC_PMC4", + "BriefDescription": "For a marked data transfer instruction, the processor's L1 data cache was reloaded from the source specified in MMCR3[45:57]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads." }, { - "EventCode": "0x40012", - "EventName": "PM_L1_ICACHE_RELOADED_ALL", - "BriefDescription": "Counts all Icache reloads includes demand, prefetch, prefetch turned into demand and demand turned into prefetch." + "EventCode": "0x4C144", + "EventName": "PM_MRK_XFER_FROM_SRC_CYC_PMC4", + "BriefDescription": "Cycles taken for a marked demand miss to reload a line from the source specified in MMCR3[45:57]." }, { - "EventCode": "0x40134", - "EventName": "PM_MRK_INST_TIMEO", - "BriefDescription": "Marked instruction finish timeout (instruction was lost)." + "EventCode": "0x4C15C", + "EventName": "PM_MRK_DERAT_MISS_1G", + "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 1G for a marked instruction. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "0x4505A", - "EventName": "PM_SP_FLOP_CMPL", - "BriefDescription": "Single Precision floating point instructions completed." + "EventCode": "0x4C15E", + "EventName": "PM_MRK_DTLB_MISS_64K", + "BriefDescription": "Marked Data TLB reload (after a miss) page size 64K. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "0x4D058", - "EventName": "PM_VECTOR_FLOP_CMPL", - "BriefDescription": "Vector floating point instructions completed." + "EventCode": "0x4E15E", + "EventName": "PM_MRK_INST_FLUSHED", + "BriefDescription": "The marked instruction was flushed." }, { - "EventCode": "0x4D05A", - "EventName": "PM_NON_MATH_FLOP_CMPL", - "BriefDescription": "Non Math instructions completed." + "EventCode": "0x40164", + "EventName": "PM_MRK_DERAT_MISS_2M", + "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 2M for a marked instruction. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { "EventCode": "0x401E0", "EventName": "PM_MRK_INST_CMPL", - "BriefDescription": "marked instruction completed." + "BriefDescription": "Marked instruction completed." + }, + { + "EventCode": "0x401E4", + "EventName": "PM_MRK_DTLB_MISS", + "BriefDescription": "The DPTEG required for the marked load/store instruction in execution was missing from the TLB. This event only counts for demand misses." + }, + { + "EventCode": "0x401E6", + "EventName": "PM_MRK_INST_FROM_L3MISS", + "BriefDescription": "The processor's instruction cache was reloaded from beyond the local core's L3 due to a demand miss for a marked instruction." }, { - "EventCode": "0x400FE", - "EventName": "PM_DATA_FROM_MEMORY", - "BriefDescription": "The processor's data cache was reloaded from local, remote, or distant memory due to a demand miss." + "EventCode": "0x401E8", + "EventName": "PM_MRK_DATA_FROM_L2MISS", + "BriefDescription": "The processor's L1 data cache was reloaded from a source beyond the local core's L2 due to a demand miss for a marked instruction." } ] diff --git a/tools/perf/pmu-events/arch/powerpc/power10/memory.json b/tools/perf/pmu-events/arch/powerpc/power10/memory.json index 843b51f531e9..885262957beb 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/memory.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/memory.json @@ -1,25 +1,10 @@ [ { - "EventCode": "0x1000A", - "EventName": "PM_PMC3_REWIND", - "BriefDescription": "The speculative event selected for PMC3 rewinds and the counter for PMC3 is not charged." - }, - { "EventCode": "0x1C040", "EventName": "PM_XFER_FROM_SRC_PMC1", "BriefDescription": "The processor's L1 data cache was reloaded from the source specified in MMCR3[0:12]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads." }, { - "EventCode": "0x1C142", - "EventName": "PM_MRK_XFER_FROM_SRC_PMC1", - "BriefDescription": "For a marked data transfer instruction, the processor's L1 data cache was reloaded from the source specified in MMCR3[0:12]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads." - }, - { - "EventCode": "0x1C144", - "EventName": "PM_MRK_XFER_FROM_SRC_CYC_PMC1", - "BriefDescription": "Cycles taken for a marked demand miss to reload a line from the source specified in MMCR3[0:12]." - }, - { "EventCode": "0x1C056", "EventName": "PM_DERAT_MISS_4K", "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 4K. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." @@ -35,24 +20,9 @@ "BriefDescription": "Data TLB reload (after a miss) page size 2M. Implies radix translation was used. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "0x1E056", - "EventName": "PM_EXEC_STALL_STORE_PIPE", - "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in the store unit. This does not include cycles spent handling store misses, PTESYNC instructions or TLBIE instructions." - }, - { - "EventCode": "0x1F150", - "EventName": "PM_MRK_ST_L2_CYC", - "BriefDescription": "Cycles from L2 RC dispatch to L2 RC completion." - }, - { "EventCode": "0x10062", "EventName": "PM_LD_L3MISS_PEND_CYC", - "BriefDescription": "Cycles L3 miss was pending for this thread." - }, - { - "EventCode": "0x20010", - "EventName": "PM_PMC1_OVERFLOW", - "BriefDescription": "The event selected for PMC1 caused the event counter to overflow." + "BriefDescription": "Cycles in which an L3 miss was pending for this thread." }, { "EventCode": "0x2001A", @@ -80,9 +50,9 @@ "BriefDescription": "Data TLB reload (after a miss) page size 4K. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "0x2D154", - "EventName": "PM_MRK_DERAT_MISS_64K", - "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 64K for a marked instruction. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." + "EventCode": "0x2C05A", + "EventName": "PM_DERAT_MISS_1G", + "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 1G. Implies radix translation. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { "EventCode": "0x200F6", @@ -90,9 +60,9 @@ "BriefDescription": "DERAT Reloaded to satisfy a DERAT miss. All page sizes are counted by this event. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { - "EventCode": "0x30016", - "EventName": "PM_EXEC_STALL_DERAT_DTLB_MISS", - "BriefDescription": "Cycles in which the oldest instruction in the pipeline suffered a TLB miss and waited for it resolve." + "EventCode": "0x34044", + "EventName": "PM_DERAT_MISS_PREF", + "BriefDescription": "DERAT miss (TLB access) while servicing a data prefetch." }, { "EventCode": "0x3C040", @@ -100,16 +70,6 @@ "BriefDescription": "The processor's L1 data cache was reloaded from the source specified in MMCR3[30:42]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads." }, { - "EventCode": "0x3C142", - "EventName": "PM_MRK_XFER_FROM_SRC_PMC3", - "BriefDescription": "For a marked data transfer instruction, the processor's L1 data cache was reloaded from the source specified in MMCR3[30:42]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads." - }, - { - "EventCode": "0x3C144", - "EventName": "PM_MRK_XFER_FROM_SRC_CYC_PMC3", - "BriefDescription": "Cycles taken for a marked demand miss to reload a line from the source specified in MMCR3[30:42]." - }, - { "EventCode": "0x3C054", "EventName": "PM_DERAT_MISS_16M", "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 16M. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." @@ -125,24 +85,14 @@ "BriefDescription": "Load and reserve instruction (LARX) finished. LARX and STCX are instructions used to acquire a lock." }, { - "EventCode": "0x301E2", - "EventName": "PM_MRK_ST_CMPL", - "BriefDescription": "Marked store completed and sent to nest. Note that this count excludes cache-inhibited stores." - }, - { "EventCode": "0x300FC", "EventName": "PM_DTLB_MISS", - "BriefDescription": "The DPTEG required for the load/store instruction in execution was missing from the TLB. It includes pages of all sizes for demand and prefetch activity." - }, - { - "EventCode": "0x4D02C", - "EventName": "PM_PMC1_REWIND", - "BriefDescription": "The speculative event selected for PMC1 rewinds and the counter for PMC1 is not charged." + "BriefDescription": "The DPTEG required for the load/store instruction in execution was missing from the TLB. This event only counts for demand misses." }, { "EventCode": "0x4003E", "EventName": "PM_LD_CMPL", - "BriefDescription": "Loads completed." + "BriefDescription": "Load instruction completed." }, { "EventCode": "0x4C040", @@ -150,16 +100,6 @@ "BriefDescription": "The processor's L1 data cache was reloaded from the source specified in MMCR3[45:57]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads." }, { - "EventCode": "0x4C142", - "EventName": "PM_MRK_XFER_FROM_SRC_PMC4", - "BriefDescription": "For a marked data transfer instruction, the processor's L1 data cache was reloaded from the source specified in MMCR3[45:57]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads." - }, - { - "EventCode": "0x4C144", - "EventName": "PM_MRK_XFER_FROM_SRC_CYC_PMC4", - "BriefDescription": "Cycles taken for a marked demand miss to reload a line from the source specified in MMCR3[45:57]." - }, - { "EventCode": "0x4C056", "EventName": "PM_DTLB_MISS_16M", "BriefDescription": "Data TLB reload (after a miss) page size 16M. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." @@ -168,20 +108,5 @@ "EventCode": "0x4C05A", "EventName": "PM_DTLB_MISS_1G", "BriefDescription": "Data TLB reload (after a miss) page size 1G. Implies radix translation was used. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." - }, - { - "EventCode": "0x4C15E", - "EventName": "PM_MRK_DTLB_MISS_64K", - "BriefDescription": "Marked Data TLB reload (after a miss) page size 64K. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." - }, - { - "EventCode": "0x4D056", - "EventName": "PM_NON_FMA_FLOP_CMPL", - "BriefDescription": "Non FMA instruction completed." - }, - { - "EventCode": "0x40164", - "EventName": "PM_MRK_DERAT_MISS_2M", - "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 2M for a marked instruction. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." } ] diff --git a/tools/perf/pmu-events/arch/powerpc/power10/metrics.json b/tools/perf/pmu-events/arch/powerpc/power10/metrics.json index 6f53583a0c62..4d66b75c6ad5 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/metrics.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/metrics.json @@ -16,133 +16,139 @@ "BriefDescription": "Average cycles per completed instruction when dispatch was stalled for any reason", "MetricExpr": "PM_DISP_STALL_CYC / PM_RUN_INST_CMPL", "MetricGroup": "CPI;CPI_STALL_RATIO", - "MetricName": "DISPATCHED_CPI" + "MetricName": "DISPATCH_STALL_CPI" }, { "BriefDescription": "Average cycles per completed instruction when dispatch was stalled because there was a flush", "MetricExpr": "PM_DISP_STALL_FLUSH / PM_RUN_INST_CMPL", "MetricGroup": "CPI", - "MetricName": "DISPATCHED_FLUSH_CPI" + "MetricName": "DISPATCH_STALL_FLUSH_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when dispatch was stalled because Fetch was being held, so there was nothing in the pipeline for this thread", + "MetricExpr": "PM_DISP_STALL_FETCH / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISPATCH_STALL_FETCH_CPI" }, { "BriefDescription": "Average cycles per completed instruction when dispatch was stalled because the MMU was handling a translation miss", "MetricExpr": "PM_DISP_STALL_TRANSLATION / PM_RUN_INST_CMPL", "MetricGroup": "CPI", - "MetricName": "DISPATCHED_TRANSLATION_CPI" + "MetricName": "DISPATCH_STALL_TRANSLATION_CPI" }, { "BriefDescription": "Average cycles per completed instruction when dispatch was stalled waiting to resolve an instruction ERAT miss", "MetricExpr": "PM_DISP_STALL_IERAT_ONLY_MISS / PM_RUN_INST_CMPL", "MetricGroup": "CPI", - "MetricName": "DISPATCHED_IERAT_ONLY_MISS_CPI" + "MetricName": "DISPATCH_STALL_IERAT_ONLY_MISS_CPI" }, { "BriefDescription": "Average cycles per completed instruction when dispatch was stalled waiting to resolve an instruction TLB miss", "MetricExpr": "PM_DISP_STALL_ITLB_MISS / PM_RUN_INST_CMPL", "MetricGroup": "CPI", - "MetricName": "DISPATCHED_ITLB_MISS_CPI" + "MetricName": "DISPATCH_STALL_ITLB_MISS_CPI" }, { "BriefDescription": "Average cycles per completed instruction when dispatch was stalled due to an icache miss", "MetricExpr": "PM_DISP_STALL_IC_MISS / PM_RUN_INST_CMPL", "MetricGroup": "CPI", - "MetricName": "DISPATCHED_IC_MISS_CPI" + "MetricName": "DISPATCH_STALL_IC_MISS_CPI" }, { "BriefDescription": "Average cycles per completed instruction when dispatch was stalled while the instruction was fetched from the local L2", "MetricExpr": "PM_DISP_STALL_IC_L2 / PM_RUN_INST_CMPL", "MetricGroup": "CPI", - "MetricName": "DISPATCHED_IC_L2_CPI" + "MetricName": "DISPATCH_STALL_IC_L2_CPI" }, { "BriefDescription": "Average cycles per completed instruction when dispatch was stalled while the instruction was fetched from the local L3", "MetricExpr": "PM_DISP_STALL_IC_L3 / PM_RUN_INST_CMPL", "MetricGroup": "CPI", - "MetricName": "DISPATCHED_IC_L3_CPI" + "MetricName": "DISPATCH_STALL_IC_L3_CPI" }, { "BriefDescription": "Average cycles per completed instruction when dispatch was stalled while the instruction was fetched from any source beyond the local L3", "MetricExpr": "PM_DISP_STALL_IC_L3MISS / PM_RUN_INST_CMPL", "MetricGroup": "CPI", - "MetricName": "DISPATCHED_IC_L3MISS_CPI" + "MetricName": "DISPATCH_STALL_IC_L3MISS_CPI" }, { "BriefDescription": "Average cycles per completed instruction when dispatch was stalled due to an icache miss after a branch mispredict", "MetricExpr": "PM_DISP_STALL_BR_MPRED_ICMISS / PM_RUN_INST_CMPL", "MetricGroup": "CPI", - "MetricName": "DISPATCHED_BR_MPRED_ICMISS_CPI" + "MetricName": "DISPATCH_STALL_BR_MPRED_ICMISS_CPI" }, { "BriefDescription": "Average cycles per completed instruction when dispatch was stalled while instruction was fetched from the local L2 after suffering a branch mispredict", "MetricExpr": "PM_DISP_STALL_BR_MPRED_IC_L2 / PM_RUN_INST_CMPL", "MetricGroup": "CPI", - "MetricName": "DISPATCHED_BR_MPRED_IC_L2_CPI" + "MetricName": "DISPATCH_STALL_BR_MPRED_IC_L2_CPI" }, { "BriefDescription": "Average cycles per completed instruction when dispatch was stalled while instruction was fetched from the local L3 after suffering a branch mispredict", "MetricExpr": "PM_DISP_STALL_BR_MPRED_IC_L3 / PM_RUN_INST_CMPL", "MetricGroup": "CPI", - "MetricName": "DISPATCHED_BR_MPRED_IC_L3_CPI" + "MetricName": "DISPATCH_STALL_BR_MPRED_IC_L3_CPI" }, { "BriefDescription": "Average cycles per completed instruction when dispatch was stalled while instruction was fetched from any source beyond the local L3 after suffering a branch mispredict", "MetricExpr": "PM_DISP_STALL_BR_MPRED_IC_L3MISS / PM_RUN_INST_CMPL", "MetricGroup": "CPI", - "MetricName": "DISPATCHED_BR_MPRED_IC_L3MISS_CPI" + "MetricName": "DISPATCH_STALL_BR_MPRED_IC_L3MISS_CPI" }, { "BriefDescription": "Average cycles per completed instruction when dispatch was stalled due to a branch mispredict", "MetricExpr": "PM_DISP_STALL_BR_MPRED / PM_RUN_INST_CMPL", "MetricGroup": "CPI", - "MetricName": "DISPATCHED_BR_MPRED_CPI" + "MetricName": "DISPATCH_STALL_BR_MPRED_CPI" }, { "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch for any reason", "MetricExpr": "PM_DISP_STALL_HELD_CYC / PM_RUN_INST_CMPL", "MetricGroup": "CPI", - "MetricName": "DISPATCHED_HELD_CPI" + "MetricName": "DISPATCH_STALL_HELD_CPI" }, { "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch because of a synchronizing instruction that requires the ICT to be empty before dispatch", "MetricExpr": "PM_DISP_STALL_HELD_SYNC_CYC / PM_RUN_INST_CMPL", "MetricGroup": "CPI", - "MetricName": "DISP_HELD_STALL_SYNC_CPI" + "MetricName": "DISPATCH_STALL_HELD_SYNC_CPI" }, { "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch while waiting on the scoreboard", "MetricExpr": "PM_DISP_STALL_HELD_SCOREBOARD_CYC / PM_RUN_INST_CMPL", "MetricGroup": "CPI", - "MetricName": "DISP_HELD_STALL_SCOREBOARD_CPI" + "MetricName": "DISPATCH_STALL_HELD_SCOREBOARD_CPI" }, { "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch due to issue queue full", "MetricExpr": "PM_DISP_STALL_HELD_ISSQ_FULL_CYC / PM_RUN_INST_CMPL", "MetricGroup": "CPI", - "MetricName": "DISP_HELD_STALL_ISSQ_FULL_CPI" + "MetricName": "DISPATCH_STALL_HELD_ISSQ_FULL_CPI" }, { "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch because the mapper/SRB was full", "MetricExpr": "PM_DISP_STALL_HELD_RENAME_CYC / PM_RUN_INST_CMPL", "MetricGroup": "CPI", - "MetricName": "DISPATCHED_HELD_RENAME_CPI" + "MetricName": "DISPATCH_STALL_HELD_RENAME_CPI" }, { "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch because the STF mapper/SRB was full", "MetricExpr": "PM_DISP_STALL_HELD_STF_MAPPER_CYC / PM_RUN_INST_CMPL", "MetricGroup": "CPI", - "MetricName": "DISPATCHED_HELD_STF_MAPPER_CPI" + "MetricName": "DISPATCH_STALL_HELD_STF_MAPPER_CPI" }, { "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch because the XVFC mapper/SRB was full", "MetricExpr": "PM_DISP_STALL_HELD_XVFC_MAPPER_CYC / PM_RUN_INST_CMPL", "MetricGroup": "CPI", - "MetricName": "DISPATCHED_HELD_XVFC_MAPPER_CPI" + "MetricName": "DISPATCH_STALL_HELD_XVFC_MAPPER_CPI" }, { "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch for any other reason", "MetricExpr": "PM_DISP_STALL_HELD_OTHER_CYC / PM_RUN_INST_CMPL", "MetricGroup": "CPI", - "MetricName": "DISPATCHED_HELD_OTHER_CPI" + "MetricName": "DISPATCH_STALL_HELD_OTHER_CPI" }, { "BriefDescription": "Average cycles per completed instruction when the NTC instruction has been dispatched but not issued for any reason", @@ -352,13 +358,13 @@ "BriefDescription": "Average cycles per completed instruction when dispatch was stalled because fetch was being held, so there was nothing in the pipeline for this thread", "MetricExpr": "PM_DISP_STALL_FETCH / PM_RUN_INST_CMPL", "MetricGroup": "CPI", - "MetricName": "DISPATCHED_FETCH_CPI" + "MetricName": "DISPATCH_STALL_FETCH_CPI" }, { "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch because of power management", "MetricExpr": "PM_DISP_STALL_HELD_HALT_CYC / PM_RUN_INST_CMPL", "MetricGroup": "CPI", - "MetricName": "DISPATCHED_HELD_HALT_CPI" + "MetricName": "DISPATCH_STALL_HELD_HALT_CPI" }, { "BriefDescription": "Percentage of flushes per completed instruction", @@ -395,6 +401,13 @@ "ScaleUnit": "1%" }, { + "BriefDescription": "Percentage of completed instructions that were stores that missed the L1", + "MetricExpr": "PM_ST_MISS_L1 * 100 / PM_RUN_INST_CMPL", + "MetricGroup": "Others", + "MetricName": "L1_ST_MISS_RATE", + "ScaleUnit": "1%" + }, + { "BriefDescription": "Percentage of completed instructions when the DPTEG required for the load/store instruction in execution was missing from the TLB", "MetricExpr": "PM_DTLB_MISS / PM_RUN_INST_CMPL * 100", "MetricGroup": "Others", @@ -454,12 +467,6 @@ "MetricName": "LOADS_PER_INST" }, { - "BriefDescription": "Average number of finished stores per completed instruction", - "MetricExpr": "PM_ST_FIN / PM_RUN_INST_CMPL", - "MetricGroup": "General", - "MetricName": "STORES_PER_INST" - }, - { "BriefDescription": "Percentage of demand loads that reloaded from beyond the L2 per completed instruction", "MetricExpr": "PM_DATA_FROM_L2MISS / PM_RUN_INST_CMPL * 100", "MetricGroup": "dL1_Reloads", @@ -474,6 +481,13 @@ "ScaleUnit": "1%" }, { + "BriefDescription": "Percentage of ITLB misses per completed run instruction", + "MetricExpr": "PM_ITLB_MISS / PM_RUN_INST_CMPL * 100", + "MetricGroup": "General", + "MetricName": "ITLB_MISS_RATE", + "ScaleUnit": "1%" + }, + { "BriefDescription": "Percentage of DERAT misses with 4k page size per completed instruction", "MetricExpr": "PM_DERAT_MISS_4K / PM_RUN_INST_CMPL * 100", "MetricGroup": "Translation", @@ -566,7 +580,7 @@ "BriefDescription": "Average number of STCX instructions finshed per completed instruction", "MetricExpr": "PM_STCX_FIN / PM_RUN_INST_CMPL", "MetricGroup": "General", - "MetricName": "STXC_PER_INST" + "MetricName": "STCX_PER_INST" }, { "BriefDescription": "Average number of LARX instructions finshed per completed instruction", @@ -629,6 +643,13 @@ "ScaleUnit": "1%" }, { + "BriefDescription": "Percentage of DERAT misses with 1G page size per completed run instruction", + "MetricExpr": "PM_DERAT_MISS_1G * 100 / PM_RUN_INST_CMPL", + "MetricGroup": "Translation", + "MetricName": "DERAT_1G_MISS_RATE", + "ScaleUnit": "1%" + }, + { "BriefDescription": "DERAT miss ratio for 4K page size", "MetricExpr": "PM_DERAT_MISS_4K / PM_DERAT_MISS", "MetricGroup": "Translation", @@ -647,6 +668,12 @@ "MetricName": "DERAT_16M_MISS_RATIO" }, { + "BriefDescription": "DERAT miss ratio for 1G page size", + "MetricExpr": "PM_DERAT_MISS_1G / PM_DERAT_MISS", + "MetricGroup": "Translation", + "MetricName": "DERAT_1G_MISS_RATIO" + }, + { "BriefDescription": "DERAT miss ratio for 64K page size", "MetricExpr": "PM_DERAT_MISS_64K / PM_DERAT_MISS", "MetricGroup": "Translation", diff --git a/tools/perf/pmu-events/arch/powerpc/power10/others.json b/tools/perf/pmu-events/arch/powerpc/power10/others.json index a771e4b6bec5..0e21e7ba1959 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/others.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/others.json @@ -1,28 +1,13 @@ [ { - "EventCode": "0x10016", - "EventName": "PM_VSU0_ISSUE", - "BriefDescription": "VSU instructions issued to VSU pipe 0." - }, - { - "EventCode": "0x1001C", - "EventName": "PM_ULTRAVISOR_INST_CMPL", - "BriefDescription": "PowerPC instructions that completed while the thread was in ultravisor state." - }, - { - "EventCode": "0x100F0", - "EventName": "PM_CYC", - "BriefDescription": "Processor cycles." - }, - { - "EventCode": "0x10134", - "EventName": "PM_MRK_ST_DONE_L2", - "BriefDescription": "Marked stores completed in L2 (RC machine done)." + "EventCode": "0x1002C", + "EventName": "PM_LD_PREFETCH_CACHE_LINE_MISS", + "BriefDescription": "The L1 cache was reloaded with a line that fulfills a prefetch request." }, { "EventCode": "0x1505E", "EventName": "PM_LD_HIT_L1", - "BriefDescription": "Loads that finished without experiencing an L1 miss." + "BriefDescription": "Load finished without experiencing an L1 miss." }, { "EventCode": "0x1F056", @@ -30,9 +15,9 @@ "BriefDescription": "Cycles in which Superslice 0 dispatches either 1 or 2 instructions." }, { - "EventCode": "0x1F15C", - "EventName": "PM_MRK_STCX_L2_CYC", - "BriefDescription": "Cycles spent in the nest portion of a marked Stcx instruction. It starts counting when the operation starts to drain to the L2 and it stops counting when the instruction retires from the Instruction Completion Table (ICT) in the Instruction Sequencing Unit (ISU)." + "EventCode": "0x1F05A", + "EventName": "PM_DISP_HELD_SYNC_CYC", + "BriefDescription": "Cycles dispatch is held because of a synchronizing instruction that requires the ICT to be empty before dispatch." }, { "EventCode": "0x10066", @@ -40,39 +25,14 @@ "BriefDescription": "Cycles in which the thread is in Adjunct state. MSR[S HV PR] bits = 011." }, { - "EventCode": "0x101E4", - "EventName": "PM_MRK_L1_ICACHE_MISS", - "BriefDescription": "Marked Instruction suffered an icache Miss." - }, - { - "EventCode": "0x101EA", - "EventName": "PM_MRK_L1_RELOAD_VALID", - "BriefDescription": "Marked demand reload." - }, - { - "EventCode": "0x100F4", - "EventName": "PM_FLOP_CMPL", - "BriefDescription": "Floating Point Operations Completed. Includes any type. It counts once for each 1, 2, 4 or 8 flop instruction. Use PM_1|2|4|8_FLOP_CMPL events to count flops." - }, - { - "EventCode": "0x100FA", - "EventName": "PM_RUN_LATCH_ANY_THREAD_CYC", - "BriefDescription": "Cycles when at least one thread has the run latch set." - }, - { "EventCode": "0x100FC", "EventName": "PM_LD_REF_L1", "BriefDescription": "All L1 D cache load references counted at finish, gated by reject. In P9 and earlier this event counted only cacheable loads but in P10 both cacheable and non-cacheable loads are included." }, { - "EventCode": "0x2000C", - "EventName": "PM_RUN_LATCH_ALL_THREADS_CYC", - "BriefDescription": "Cycles when the run latch is set for all threads." - }, - { "EventCode": "0x2E010", "EventName": "PM_ADJUNCT_INST_CMPL", - "BriefDescription": "PowerPC instructions that completed while the thread is in Adjunct state." + "BriefDescription": "PowerPC instruction completed while the thread was in Adjunct state." }, { "EventCode": "0x2E014", @@ -80,26 +40,6 @@ "BriefDescription": "Conditional store instruction (STCX) finished. LARX and STCX are instructions used to acquire a lock." }, { - "EventCode": "0x20130", - "EventName": "PM_MRK_INST_DECODED", - "BriefDescription": "An instruction was marked at decode time. Random Instruction Sampling (RIS) only." - }, - { - "EventCode": "0x20132", - "EventName": "PM_MRK_DFU_ISSUE", - "BriefDescription": "The marked instruction was a decimal floating point operation issued to the VSU. Measured at issue time." - }, - { - "EventCode": "0x20134", - "EventName": "PM_MRK_FXU_ISSUE", - "BriefDescription": "The marked instruction was a fixed point operation issued to the VSU. Measured at issue time." - }, - { - "EventCode": "0x2505C", - "EventName": "PM_VSU_ISSUE", - "BriefDescription": "At least one VSU instruction was issued to one of the VSU pipes. Up to 4 per cycle. Includes fixed point operations." - }, - { "EventCode": "0x2F054", "EventName": "PM_DISP_SS1_2_INSTR_CYC", "BriefDescription": "Cycles in which Superslice 1 dispatches either 1 or 2 instructions." @@ -110,39 +50,14 @@ "BriefDescription": "Cycles in which Superslice 1 dispatches either 3 or 4 instructions." }, { - "EventCode": "0x2006C", - "EventName": "PM_RUN_CYC_SMT4_MODE", - "BriefDescription": "Cycles when this thread's run latch is set and the core is in SMT4 mode." - }, - { - "EventCode": "0x201E0", - "EventName": "PM_MRK_DATA_FROM_MEMORY", - "BriefDescription": "The processor's data cache was reloaded from local, remote, or distant memory due to a demand miss for a marked load." - }, - { - "EventCode": "0x201E4", - "EventName": "PM_MRK_DATA_FROM_L3MISS", - "BriefDescription": "The processor's data cache was reloaded from a source other than the local core's L1, L2, or L3 due to a demand miss for a marked load." - }, - { - "EventCode": "0x201E8", - "EventName": "PM_THRESH_EXC_512", - "BriefDescription": "Threshold counter exceeded a value of 512." - }, - { "EventCode": "0x200F2", "EventName": "PM_INST_DISP", - "BriefDescription": "PowerPC instructions dispatched." - }, - { - "EventCode": "0x30132", - "EventName": "PM_MRK_VSU_FIN", - "BriefDescription": "VSU marked instructions finished. Excludes simple FX instructions issued to the Store Unit." + "BriefDescription": "PowerPC instruction dispatched." }, { - "EventCode": "0x30038", - "EventName": "PM_EXEC_STALL_DMISS_LMEM", - "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from the local memory, local OpenCapp cache, or local OpenCapp memory." + "EventCode": "0x200FD", + "EventName": "PM_L1_ICACHE_MISS", + "BriefDescription": "Demand instruction cache miss." }, { "EventCode": "0x3F04A", @@ -152,12 +67,7 @@ { "EventCode": "0x3405A", "EventName": "PM_PRIVILEGED_INST_CMPL", - "BriefDescription": "PowerPC Instructions that completed while the thread is in Privileged state." - }, - { - "EventCode": "0x3F150", - "EventName": "PM_MRK_ST_DRAIN_CYC", - "BriefDescription": "cycles to drain st from core to L2." + "BriefDescription": "PowerPC instruction completed while the thread was in Privileged state." }, { "EventCode": "0x3F054", @@ -170,74 +80,29 @@ "BriefDescription": "Cycles in which Superslice 0 dispatches either 5, 6, 7 or 8 instructions." }, { - "EventCode": "0x30162", - "EventName": "PM_MRK_ISSUE_DEPENDENT_LOAD", - "BriefDescription": "The marked instruction was dependent on a load. It is eligible for issue kill." - }, - { - "EventCode": "0x40114", - "EventName": "PM_MRK_START_PROBE_NOP_DISP", - "BriefDescription": "Marked Start probe nop dispatched. Instruction AND R0,R0,R0." - }, - { - "EventCode": "0x4001C", - "EventName": "PM_VSU_FIN", - "BriefDescription": "VSU instructions finished." - }, - { - "EventCode": "0x4C01A", - "EventName": "PM_EXEC_STALL_DMISS_OFF_NODE", - "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from a distant chip." - }, - { - "EventCode": "0x4D012", - "EventName": "PM_PMC3_SAVED", - "BriefDescription": "The conditions for the speculative event selected for PMC3 are met and PMC3 is charged." - }, - { - "EventCode": "0x4D022", - "EventName": "PM_HYPERVISOR_INST_CMPL", - "BriefDescription": "PowerPC instructions that completed while the thread is in hypervisor state." - }, - { - "EventCode": "0x4D026", - "EventName": "PM_ULTRAVISOR_CYC", - "BriefDescription": "Cycles when the thread is in Ultravisor state. MSR[S HV PR]=110." + "EventCode": "0x30068", + "EventName": "PM_L1_ICACHE_RELOADED_PREF", + "BriefDescription": "Counts all instruction cache prefetch reloads (includes demand turned into prefetch)." }, { - "EventCode": "0x4D028", - "EventName": "PM_PRIVILEGED_CYC", - "BriefDescription": "Cycles when the thread is in Privileged state. MSR[S HV PR]=x00." + "EventCode": "0x300F6", + "EventName": "PM_LD_DEMAND_MISS_L1", + "BriefDescription": "The L1 cache was reloaded with a line that fulfills a demand miss request. Counted at reload time, before finish." }, { - "EventCode": "0x40030", - "EventName": "PM_INST_FIN", - "BriefDescription": "Instructions finished." + "EventCode": "0x300FE", + "EventName": "PM_DATA_FROM_L3MISS", + "BriefDescription": "The processor's data cache was reloaded from a source other than the local core's L1, L2, or L3 due to a demand miss." }, { - "EventCode": "0x44146", - "EventName": "PM_MRK_STCX_CORE_CYC", - "BriefDescription": "Cycles spent in the core portion of a marked Stcx instruction. It starts counting when the instruction is decoded and stops counting when it drains into the L2." + "EventCode": "0x40012", + "EventName": "PM_L1_ICACHE_RELOADED_ALL", + "BriefDescription": "Counts all instruction cache reloads includes demand, prefetch, prefetch turned into demand and demand turned into prefetch." }, { "EventCode": "0x44054", "EventName": "PM_VECTOR_LD_CMPL", - "BriefDescription": "Vector load instructions completed." - }, - { - "EventCode": "0x45054", - "EventName": "PM_FMA_CMPL", - "BriefDescription": "Two floating point instructions completed (FMA class of instructions: fmadd, fnmadd, fmsub, fnmsub). Scalar instructions only." - }, - { - "EventCode": "0x45056", - "EventName": "PM_SCALAR_FLOP_CMPL", - "BriefDescription": "Scalar floating point instructions completed." - }, - { - "EventCode": "0x4505C", - "EventName": "PM_MATH_FLOP_CMPL", - "BriefDescription": "Math floating point instructions completed." + "BriefDescription": "Vector load instruction completed." }, { "EventCode": "0x4D05E", @@ -245,28 +110,13 @@ "BriefDescription": "A branch completed. All branches are included." }, { - "EventCode": "0x4E15E", - "EventName": "PM_MRK_INST_FLUSHED", - "BriefDescription": "The marked instruction was flushed." - }, - { - "EventCode": "0x401E6", - "EventName": "PM_MRK_INST_FROM_L3MISS", - "BriefDescription": "The processor's instruction cache was reloaded from a source other than the local core's L1, L2, or L3 due to a demand miss for a marked instruction." - }, - { - "EventCode": "0x401E8", - "EventName": "PM_MRK_DATA_FROM_L2MISS", - "BriefDescription": "The processor's data cache was reloaded from a source other than the local core's L1 or L2 due to a demand miss for a marked load." - }, - { "EventCode": "0x400F0", "EventName": "PM_LD_DEMAND_MISS_L1_FIN", - "BriefDescription": "Load Missed L1, counted at finish time." + "BriefDescription": "Load missed L1, counted at finish time." }, { - "EventCode": "0x500FA", - "EventName": "PM_RUN_INST_CMPL", - "BriefDescription": "Completed PowerPC instructions gated by the run latch." + "EventCode": "0x400FE", + "EventName": "PM_DATA_FROM_MEMORY", + "BriefDescription": "The processor's data cache was reloaded from local, remote, or distant memory due to a demand miss." } ] diff --git a/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json b/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json index b8aded6045fa..21b23bb55d0d 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json @@ -1,8 +1,13 @@ [ { - "EventCode": "0x100FE", - "EventName": "PM_INST_CMPL", - "BriefDescription": "PowerPC instructions completed." + "EventCode": "0x10004", + "EventName": "PM_EXEC_STALL_TRANSLATION", + "BriefDescription": "Cycles in which the oldest instruction in the pipeline suffered a TLB miss or ERAT miss and waited for it to resolve." + }, + { + "EventCode": "0x10006", + "EventName": "PM_DISP_STALL_HELD_OTHER_CYC", + "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch for any other reason." }, { "EventCode": "0x1000C", @@ -12,7 +17,7 @@ { "EventCode": "0x1000E", "EventName": "PM_MMA_ISSUED", - "BriefDescription": "MMA instructions issued." + "BriefDescription": "MMA instruction issued." }, { "EventCode": "0x10012", @@ -30,14 +35,24 @@ "BriefDescription": "Cycles in which an instruction reload is pending to satisfy a demand miss." }, { - "EventCode": "0x10022", - "EventName": "PM_PMC2_SAVED", - "BriefDescription": "The conditions for the speculative event selected for PMC2 are met and PMC2 is charged." + "EventCode": "0x10028", + "EventName": "PM_NTC_FLUSH", + "BriefDescription": "The instruction was flushed after becoming next-to-complete (NTC)." + }, + { + "EventCode": "0x10038", + "EventName": "PM_DISP_STALL_TRANSLATION", + "BriefDescription": "Cycles when dispatch was stalled for this thread because the MMU was handling a translation miss." + }, + { + "EventCode": "0x1003A", + "EventName": "PM_DISP_STALL_BR_MPRED_IC_L2", + "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L2 after suffering a branch mispredict." }, { - "EventCode": "0x10024", - "EventName": "PM_PMC5_OVERFLOW", - "BriefDescription": "The event selected for PMC5 caused the event counter to overflow." + "EventCode": "0x1003C", + "EventName": "PM_EXEC_STALL_DMISS_L2L3", + "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from either the local L2 or local L3." }, { "EventCode": "0x10058", @@ -55,11 +70,41 @@ "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 2M. Implies radix translation. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches." }, { + "EventCode": "0x1D05E", + "EventName": "PM_DISP_STALL_HELD_HALT_CYC", + "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch because of power management." + }, + { + "EventCode": "0x1E050", + "EventName": "PM_DISP_STALL_HELD_STF_MAPPER_CYC", + "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch because the STF mapper/SRB was full. Includes GPR (count, link, tar), VSR, VMR, FPR." + }, + { + "EventCode": "0x1E054", + "EventName": "PM_EXEC_STALL_DMISS_L21_L31", + "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from another core's L2 or L3 on the same chip." + }, + { + "EventCode": "0x1E056", + "EventName": "PM_EXEC_STALL_STORE_PIPE", + "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in the store unit. This does not include cycles spent handling store misses, PTESYNC instructions or TLBIE instructions." + }, + { "EventCode": "0x1E05A", "EventName": "PM_CMPL_STALL_LWSYNC", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a lwsync waiting to complete." }, { + "EventCode": "0x1F058", + "EventName": "PM_DISP_HELD_CYC", + "BriefDescription": "Cycles dispatch is held." + }, + { + "EventCode": "0x10064", + "EventName": "PM_DISP_STALL_IC_L2", + "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L2." + }, + { "EventCode": "0x10068", "EventName": "PM_BR_FIN", "BriefDescription": "A branch instruction finished. Includes predicted/mispredicted/unconditional." @@ -70,9 +115,9 @@ "BriefDescription": "Simple fixed point instruction issued to the store unit. Measured at finish time." }, { - "EventCode": "0x1006C", - "EventName": "PM_RUN_CYC_ST_MODE", - "BriefDescription": "Cycles when the run latch is set and the core is in ST mode." + "EventCode": "0x100F8", + "EventName": "PM_DISP_STALL_CYC", + "BriefDescription": "Cycles the ICT has no itags assigned to this thread (no instructions were dispatched during these cycles)." }, { "EventCode": "0x20004", @@ -80,9 +125,9 @@ "BriefDescription": "Cycles in which the oldest instruction in the pipeline was dispatched but not issued yet." }, { - "EventCode": "0x2000A", - "EventName": "PM_HYPERVISOR_CYC", - "BriefDescription": "Cycles when the thread is in Hypervisor state. MSR[S HV PR]=010." + "EventCode": "0x20006", + "EventName": "PM_DISP_STALL_HELD_ISSQ_FULL_CYC", + "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch due to Issue queue full. Includes issue queue and branch queue." }, { "EventCode": "0x2000E", @@ -90,24 +135,59 @@ "BriefDescription": "LSU Finished an internal operation in LD1 port." }, { + "EventCode": "0x2C010", + "EventName": "PM_EXEC_STALL_LSU", + "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in the Load Store Unit. This does not include simple fixed point instructions." + }, + { "EventCode": "0x2C014", "EventName": "PM_CMPL_STALL_SPECIAL", "BriefDescription": "Cycles in which the oldest instruction in the pipeline required special handling before completing." }, { + "EventCode": "0x2C016", + "EventName": "PM_DISP_STALL_IERAT_ONLY_MISS", + "BriefDescription": "Cycles when dispatch was stalled while waiting to resolve an instruction ERAT miss." + }, + { "EventCode": "0x2C018", "EventName": "PM_EXEC_STALL_DMISS_L3MISS", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from a source beyond the local L2 or local L3." }, { + "EventCode": "0x2C01C", + "EventName": "PM_EXEC_STALL_DMISS_OFF_CHIP", + "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from a remote chip." + }, + { + "EventCode": "0x2C01E", + "EventName": "PM_DISP_STALL_BR_MPRED_IC_L3", + "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L3 after suffering a branch mispredict." + }, + { "EventCode": "0x2D010", "EventName": "PM_LSU_ST1_FIN", "BriefDescription": "LSU Finished an internal operation in ST1 port." }, { + "EventCode": "0x10016", + "EventName": "PM_VSU0_ISSUE", + "BriefDescription": "VSU instruction issued to VSU pipe 0." + }, + { "EventCode": "0x2D012", "EventName": "PM_VSU1_ISSUE", - "BriefDescription": "VSU instructions issued to VSU pipe 1." + "BriefDescription": "VSU instruction issued to VSU pipe 1." + }, + { + "EventCode": "0x2505C", + "EventName": "PM_VSU_ISSUE", + "BriefDescription": "At least one VSU instruction was issued to one of the VSU pipes. Up to 4 per cycle. Includes fixed point operations." + }, + { + "EventCode": "0x4001C", + "EventName": "PM_VSU_FIN", + "BriefDescription": "VSU instruction finished." }, { "EventCode": "0x2D018", @@ -115,19 +195,34 @@ "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in the VSU (includes FXU, VSU, CRU)." }, { + "EventCode": "0x2D01A", + "EventName": "PM_DISP_STALL_IC_MISS", + "BriefDescription": "Cycles when dispatch was stalled for this thread due to an instruction cache miss." + }, + { "EventCode": "0x2D01C", "EventName": "PM_CMPL_STALL_STCX", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a stcx waiting for resolution from the nest before completing." }, { - "EventCode": "0x2E01E", - "EventName": "PM_EXEC_STALL_NTC_FLUSH", - "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in any unit before it was flushed. Note that if the flush of the oldest instruction happens after finish, the cycles from dispatch to issue will be included in PM_DISP_STALL and the cycles from issue to finish will be included in PM_EXEC_STALL and its corresponding children. This event will also count cycles when the previous NTF instruction is still completing and the new NTF instruction is stalled at dispatch." + "EventCode": "0x2E018", + "EventName": "PM_DISP_STALL_FETCH", + "BriefDescription": "Cycles when dispatch was stalled for this thread because Fetch was being held." + }, + { + "EventCode": "0x2E01A", + "EventName": "PM_DISP_STALL_HELD_XVFC_MAPPER_CYC", + "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch because the XVFC mapper/SRB was full." + }, + { + "EventCode": "0x2E01C", + "EventName": "PM_EXEC_STALL_TLBIE", + "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a TLBIE instruction executing in the Load Store Unit." }, { - "EventCode": "0x2013C", - "EventName": "PM_MRK_FX_LSU_FIN", - "BriefDescription": "The marked instruction was simple fixed point that was issued to the store unit. Measured at finish time." + "EventCode": "0x2E01E", + "EventName": "PM_EXEC_STALL_NTC_FLUSH", + "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in any unit before it was flushed. Note that if the flush of the oldest instruction happens after finish, the cycles from dispatch to issue will be included in PM_DISP_STALL and the cycles from issue to finish will be included in PM_EXEC_STALL and its corresponding children. This event will also count cycles when the previous next-to-finish (NTF) instruction is still completing and the new NTF instruction is stalled at dispatch." }, { "EventCode": "0x2405A", @@ -135,14 +230,19 @@ "BriefDescription": "Cycles in which the oldest instruction in the pipeline (NTC) finishes. Note that instructions can finish out of order, therefore not all the instructions that finish have a Next-to-complete status." }, { - "EventCode": "0x201E2", - "EventName": "PM_MRK_LD_MISS_L1", - "BriefDescription": "Marked DL1 Demand Miss counted at finish time." + "EventCode": "0x20066", + "EventName": "PM_DISP_HELD_OTHER_CYC", + "BriefDescription": "Cycles dispatch is held for any other reason." + }, + { + "EventCode": "0x2006A", + "EventName": "PM_DISP_HELD_STF_MAPPER_CYC", + "BriefDescription": "Cycles dispatch is held because the STF mapper/SRB was full. Includes GPR (count, link, tar), VSR, VMR, FPR." }, { - "EventCode": "0x200F4", - "EventName": "PM_RUN_CYC", - "BriefDescription": "Processor cycles gated by the run latch." + "EventCode": "0x30004", + "EventName": "PM_DISP_STALL_FLUSH", + "BriefDescription": "Cycles when dispatch was stalled because of a flush that happened to an instruction(s) that was not yet next-to-complete (NTC). PM_EXEC_STALL_NTC_FLUSH only includes instructions that were flushed after becoming NTC." }, { "EventCode": "0x30008", @@ -150,29 +250,34 @@ "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting to finish in one of the execution units (BRU, LSU, VSU). Only cycles between issue and finish are counted in this category." }, { - "EventCode": "0x3001A", - "EventName": "PM_LSU_ST2_FIN", - "BriefDescription": "LSU Finished an internal operation in ST2 port." + "EventCode": "0x30014", + "EventName": "PM_EXEC_STALL_STORE", + "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a store instruction executing in the Load Store Unit." + }, + { + "EventCode": "0x30016", + "EventName": "PM_EXEC_STALL_DERAT_DTLB_MISS", + "BriefDescription": "Cycles in which the oldest instruction in the pipeline suffered a TLB miss and waited for it resolve." }, { - "EventCode": "0x30020", - "EventName": "PM_PMC2_REWIND", - "BriefDescription": "The speculative event selected for PMC2 rewinds and the counter for PMC2 is not charged." + "EventCode": "0x30018", + "EventName": "PM_DISP_STALL_HELD_SCOREBOARD_CYC", + "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch while waiting on the Scoreboard. This event combines VSCR and FPSCR together." }, { - "EventCode": "0x30022", - "EventName": "PM_PMC4_SAVED", - "BriefDescription": "The conditions for the speculative event selected for PMC4 are met and PMC4 is charged." + "EventCode": "0x3001A", + "EventName": "PM_LSU_ST2_FIN", + "BriefDescription": "LSU Finished an internal operation in ST2 port." }, { - "EventCode": "0x30024", - "EventName": "PM_PMC6_OVERFLOW", - "BriefDescription": "The event selected for PMC6 caused the event counter to overflow." + "EventCode": "0x30026", + "EventName": "PM_EXEC_STALL_STORE_MISS", + "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a store whose cache line was not resident in the L1 and was waiting for allocation of the missing line into the L1." }, { "EventCode": "0x30028", "EventName": "PM_CMPL_STALL_MEM_ECC", - "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for the non-speculative finish of either a stcx waiting for its result or a load waiting for non-critical sectors of data and ECC." + "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for the non-speculative finish of either a STCX waiting for its result or a load waiting for non-critical sectors of data and ECC." }, { "EventCode": "0x30036", @@ -180,6 +285,11 @@ "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a simple fixed point instruction executing in the Load Store Unit." }, { + "EventCode": "0x30038", + "EventName": "PM_EXEC_STALL_DMISS_LMEM", + "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from the local memory, local OpenCAPI cache, or local OpenCAPI memory." + }, + { "EventCode": "0x3003A", "EventName": "PM_CMPL_STALL_EXCEPTION", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was not allowed to complete because it was interrupted by ANY exception, which has to be serviced before the instruction can complete." @@ -187,17 +297,42 @@ { "EventCode": "0x3F044", "EventName": "PM_VSU2_ISSUE", - "BriefDescription": "VSU instructions issued to VSU pipe 2." + "BriefDescription": "VSU instruction issued to VSU pipe 2." }, { "EventCode": "0x30058", "EventName": "PM_TLBIE_FIN", - "BriefDescription": "TLBIE instructions finished in the LSU. Two TLBIEs can finish each cycle. All will be counted." + "BriefDescription": "TLBIE instruction finished in the LSU. Two TLBIEs can finish each cycle. All will be counted." }, { - "EventCode": "0x3D058", - "EventName": "PM_SCALAR_FSQRT_FDIV_ISSUE", - "BriefDescription": "Scalar versions of four floating point operations: fdiv,fsqrt (xvdivdp, xvdivsp, xvsqrtdp, xvsqrtsp)." + "EventCode": "0x34054", + "EventName": "PM_EXEC_STALL_DMISS_L2L3_NOCONFLICT", + "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from the local L2 or local L3, without a dispatch conflict." + }, + { + "EventCode": "0x34056", + "EventName": "PM_EXEC_STALL_LOAD_FINISH", + "BriefDescription": "Cycles in which the oldest instruction in the pipeline was finishing a load after its data was reloaded from a data source beyond the local L1; cycles in which the LSU was processing an L1-hit; cycles in which the next-to-finish (NTF) instruction merged with another load in the LMQ; cycles in which the NTF instruction is waiting for a data reload for a load miss, but the data comes back with a non-NTF instruction." + }, + { + "EventCode": "0x34058", + "EventName": "PM_DISP_STALL_BR_MPRED_ICMISS", + "BriefDescription": "Cycles when dispatch was stalled after a mispredicted branch resulted in an instruction cache miss." + }, + { + "EventCode": "0x3D05C", + "EventName": "PM_DISP_STALL_HELD_RENAME_CYC", + "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch because the mapper/SRB was full. Includes GPR (count, link, tar), VSR, VMR, FPR and XVFC." + }, + { + "EventCode": "0x3E052", + "EventName": "PM_DISP_STALL_IC_L3", + "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L3." + }, + { + "EventCode": "0x30060", + "EventName": "PM_DISP_HELD_XVFC_MAPPER_CYC", + "BriefDescription": "Cycles dispatch is held because the XVFC mapper/SRB was full." }, { "EventCode": "0x30066", @@ -215,9 +350,9 @@ "BriefDescription": "Cycles in which both instructions in the ICT entry pair show as finished. These are the cycles between finish and completion for the oldest pair of instructions in the pipeline." }, { - "EventCode": "0x40010", - "EventName": "PM_PMC3_OVERFLOW", - "BriefDescription": "The event selected for PMC3 caused the event counter to overflow." + "EventCode": "0x4C010", + "EventName": "PM_DISP_STALL_BR_MPRED_IC_L3MISS", + "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from sources beyond the local L3 after suffering a mispredicted branch." }, { "EventCode": "0x4C012", @@ -225,16 +360,36 @@ "BriefDescription": "Cycles in which the oldest instruction in the pipeline suffered an ERAT miss and waited for it resolve." }, { + "EventCode": "0x4C016", + "EventName": "PM_EXEC_STALL_DMISS_L2L3_CONFLICT", + "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from the local L2 or local L3, with a dispatch conflict." + }, + { "EventCode": "0x4C018", "EventName": "PM_CMPL_STALL", "BriefDescription": "Cycles in which the oldest instruction in the pipeline cannot complete because the thread was blocked for any reason." }, { + "EventCode": "0x4C01A", + "EventName": "PM_EXEC_STALL_DMISS_OFF_NODE", + "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from a distant chip." + }, + { "EventCode": "0x4C01E", "EventName": "PM_LSU_ST3_FIN", "BriefDescription": "LSU Finished an internal operation in ST3 port." }, { + "EventCode": "0x4D014", + "EventName": "PM_EXEC_STALL_LOAD", + "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a load instruction executing in the Load Store Unit." + }, + { + "EventCode": "0x4D016", + "EventName": "PM_EXEC_STALL_PTESYNC", + "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a PTESYNC instruction executing in the Load Store Unit." + }, + { "EventCode": "0x4D018", "EventName": "PM_EXEC_STALL_BRU", "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in the Branch unit." @@ -250,9 +405,24 @@ "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a TLBIEL instruction executing in the Load Store Unit. TLBIEL instructions have lower overhead than TLBIE instructions because they don't get set to the nest." }, { + "EventCode": "0x4D01E", + "EventName": "PM_DISP_STALL_BR_MPRED", + "BriefDescription": "Cycles when dispatch was stalled for this thread due to a mispredicted branch." + }, + { + "EventCode": "0x4E010", + "EventName": "PM_DISP_STALL_IC_L3MISS", + "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from any source beyond the local L3." + }, + { "EventCode": "0x4E012", "EventName": "PM_EXEC_STALL_UNKNOWN", - "BriefDescription": "Cycles in which the oldest instruction in the pipeline completed without an ntf_type pulse. The ntf_pulse was missed by the ISU because the NTF finishes and completions came too close together." + "BriefDescription": "Cycles in which the oldest instruction in the pipeline completed without an ntf_type pulse. The ntf_pulse was missed by the ISU because the next-to-finish (NTF) instruction finishes and completions came too close together." + }, + { + "EventCode": "0x4E01A", + "EventName": "PM_DISP_STALL_HELD_CYC", + "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch for any reason." }, { "EventCode": "0x4D020", @@ -260,24 +430,24 @@ "BriefDescription": "VSU instruction was issued to VSU pipe 3." }, { - "EventCode": "0x40132", - "EventName": "PM_MRK_LSU_FIN", - "BriefDescription": "LSU marked instruction finish." + "EventCode": "0x4003C", + "EventName": "PM_DISP_STALL_HELD_SYNC_CYC", + "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch because of a synchronizing instruction that requires the ICT to be empty before dispatch." }, { "EventCode": "0x45058", "EventName": "PM_IC_MISS_CMPL", - "BriefDescription": "Non-speculative icache miss, counted at completion." + "BriefDescription": "Non-speculative instruction cache miss, counted at completion." }, { - "EventCode": "0x4D050", - "EventName": "PM_VSU_NON_FLOP_CMPL", - "BriefDescription": "Non-floating point VSU instructions completed." + "EventCode": "0x40060", + "EventName": "PM_DISP_HELD_SCOREBOARD_CYC", + "BriefDescription": "Cycles dispatch is held while waiting on the Scoreboard. This event combines VSCR and FPSCR together." }, { - "EventCode": "0x4D052", - "EventName": "PM_2FLOP_CMPL", - "BriefDescription": "Double Precision vector version of fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg completed." + "EventCode": "0x40062", + "EventName": "PM_DISP_HELD_RENAME_CYC", + "BriefDescription": "Cycles dispatch is held because the mapper/SRB was full. Includes GPR (count, link, tar), VSR, VMR, FPR and XVFC." }, { "EventCode": "0x400F2", diff --git a/tools/perf/pmu-events/arch/powerpc/power10/pmc.json b/tools/perf/pmu-events/arch/powerpc/power10/pmc.json index b5d1bd39cfb2..c606ae03cd27 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/pmc.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/pmc.json @@ -1,22 +1,202 @@ [ { + "EventCode": "0x100FE", + "EventName": "PM_INST_CMPL", + "BriefDescription": "PowerPC instruction completed." + }, + { + "EventCode": "0x1000A", + "EventName": "PM_PMC3_REWIND", + "BriefDescription": "The speculative event selected for PMC3 rewinds and the counter for PMC3 is not charged." + }, + { + "EventCode": "0x10010", + "EventName": "PM_PMC4_OVERFLOW", + "BriefDescription": "The event selected for PMC4 caused the event counter to overflow." + }, + { + "EventCode": "0x1001C", + "EventName": "PM_ULTRAVISOR_INST_CMPL", + "BriefDescription": "PowerPC instruction completed while the thread was in ultravisor state." + }, + { + "EventCode": "0x100F0", + "EventName": "PM_CYC", + "BriefDescription": "Processor cycles." + }, + { + "EventCode": "0x10020", + "EventName": "PM_PMC4_REWIND", + "BriefDescription": "The speculative event selected for PMC4 rewinds and the counter for PMC4 is not charged." + }, + { + "EventCode": "0x10022", + "EventName": "PM_PMC2_SAVED", + "BriefDescription": "The conditions for the speculative event selected for PMC2 are met and PMC2 is charged." + }, + { + "EventCode": "0x10024", + "EventName": "PM_PMC5_OVERFLOW", + "BriefDescription": "The event selected for PMC5 caused the event counter to overflow." + }, + { + "EventCode": "0x1002A", + "EventName": "PM_PMC3_HELD_CYC", + "BriefDescription": "Cycles when the speculative counter for PMC3 is frozen." + }, + { + "EventCode": "0x1F15E", + "EventName": "PM_MRK_START_PROBE_NOP_CMPL", + "BriefDescription": "Marked Start probe nop (AND R0,R0,R0) completed." + }, + { + "EventCode": "0x1006C", + "EventName": "PM_RUN_CYC_ST_MODE", + "BriefDescription": "Cycles when the run latch is set and the core is in ST mode." + }, + { + "EventCode": "0x101E8", + "EventName": "PM_THRESH_EXC_256", + "BriefDescription": "Threshold counter exceeded a count of 256." + }, + { + "EventCode": "0x101EC", + "EventName": "PM_THRESH_MET", + "BriefDescription": "Threshold exceeded." + }, + { + "EventCode": "0x100FA", + "EventName": "PM_RUN_LATCH_ANY_THREAD_CYC", + "BriefDescription": "Cycles when at least one thread has the run latch set." + }, + { + "EventCode": "0x2000A", + "EventName": "PM_HYPERVISOR_CYC", + "BriefDescription": "Cycles when the thread is in Hypervisor state. MSR[S HV PR]=010." + }, + { + "EventCode": "0x2000C", + "EventName": "PM_RUN_LATCH_ALL_THREADS_CYC", + "BriefDescription": "Cycles when the run latch is set for all threads." + }, + { + "EventCode": "0x20010", + "EventName": "PM_PMC1_OVERFLOW", + "BriefDescription": "The event selected for PMC1 caused the event counter to overflow." + }, + { + "EventCode": "0x2006C", + "EventName": "PM_RUN_CYC_SMT4_MODE", + "BriefDescription": "Cycles when this thread's run latch is set and the core is in SMT4 mode." + }, + { + "EventCode": "0x201E6", + "EventName": "PM_THRESH_EXC_32", + "BriefDescription": "Threshold counter exceeded a value of 32." + }, + { + "EventCode": "0x201E8", + "EventName": "PM_THRESH_EXC_512", + "BriefDescription": "Threshold counter exceeded a value of 512." + }, + { + "EventCode": "0x200F4", + "EventName": "PM_RUN_CYC", + "BriefDescription": "Processor cycles gated by the run latch." + }, + { + "EventCode": "0x30010", + "EventName": "PM_PMC2_OVERFLOW", + "BriefDescription": "The event selected for PMC2 caused the event counter to overflow." + }, + { + "EventCode": "0x30020", + "EventName": "PM_PMC2_REWIND", + "BriefDescription": "The speculative event selected for PMC2 rewinds and the counter for PMC2 is not charged." + }, + { + "EventCode": "0x30022", + "EventName": "PM_PMC4_SAVED", + "BriefDescription": "The conditions for the speculative event selected for PMC4 are met and PMC4 is charged." + }, + { + "EventCode": "0x30024", + "EventName": "PM_PMC6_OVERFLOW", + "BriefDescription": "The event selected for PMC6 caused the event counter to overflow." + }, + { + "EventCode": "0x3006C", + "EventName": "PM_RUN_CYC_SMT2_MODE", + "BriefDescription": "Cycles when this thread's run latch is set and the core is in SMT2 mode." + }, + { "EventCode": "0x301E8", "EventName": "PM_THRESH_EXC_64", "BriefDescription": "Threshold counter exceeded a value of 64." }, { - "EventCode": "0x45050", - "EventName": "PM_1FLOP_CMPL", - "BriefDescription": "One floating point instruction completed (fadd, fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg)." + "EventCode": "0x301EA", + "EventName": "PM_THRESH_EXC_1024", + "BriefDescription": "Threshold counter exceeded a value of 1024." + }, + { + "EventCode": "0x40010", + "EventName": "PM_PMC3_OVERFLOW", + "BriefDescription": "The event selected for PMC3 caused the event counter to overflow." + }, + { + "EventCode": "0x40114", + "EventName": "PM_MRK_START_PROBE_NOP_DISP", + "BriefDescription": "Marked Start probe nop dispatched. Instruction AND R0,R0,R0." + }, + { + "EventCode": "0x4D010", + "EventName": "PM_PMC1_SAVED", + "BriefDescription": "The conditions for the speculative event selected for PMC1 are met and PMC1 is charged." + }, + { + "EventCode": "0x4D012", + "EventName": "PM_PMC3_SAVED", + "BriefDescription": "The conditions for the speculative event selected for PMC3 are met and PMC3 is charged." + }, + { + "EventCode": "0x4D022", + "EventName": "PM_HYPERVISOR_INST_CMPL", + "BriefDescription": "PowerPC instruction completed while the thread was in hypervisor state." + }, + { + "EventCode": "0x4D026", + "EventName": "PM_ULTRAVISOR_CYC", + "BriefDescription": "Cycles when the thread is in Ultravisor state. MSR[S HV PR]=110." + }, + { + "EventCode": "0x4D028", + "EventName": "PM_PRIVILEGED_CYC", + "BriefDescription": "Cycles when the thread is in Privileged state. MSR[S HV PR]=x00." + }, + { + "EventCode": "0x4D02C", + "EventName": "PM_PMC1_REWIND", + "BriefDescription": "The speculative event selected for PMC1 rewinds and the counter for PMC1 is not charged." + }, + { + "EventCode": "0x40030", + "EventName": "PM_INST_FIN", + "BriefDescription": "Instruction finished." + }, + { + "EventCode": "0x40134", + "EventName": "PM_MRK_INST_TIMEO", + "BriefDescription": "Marked instruction finish timeout (instruction was lost)." }, { - "EventCode": "0x45052", - "EventName": "PM_4FLOP_CMPL", - "BriefDescription": "Four floating point instructions completed (fadd, fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg)." + "EventCode": "0x401EA", + "EventName": "PM_THRESH_EXC_128", + "BriefDescription": "Threshold counter exceeded a value of 128." }, { - "EventCode": "0x4D054", - "EventName": "PM_8FLOP_CMPL", - "BriefDescription": "Four Double Precision vector instructions completed." + "EventCode": "0x400FA", + "EventName": "PM_RUN_INST_CMPL", + "BriefDescription": "PowerPC instruction completed while the run latch is set." } ] diff --git a/tools/perf/pmu-events/arch/powerpc/power10/translation.json b/tools/perf/pmu-events/arch/powerpc/power10/translation.json index db3766dca07c..ea73900d248a 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/translation.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/translation.json @@ -1,35 +1,10 @@ [ { - "EventCode": "0x1F15E", - "EventName": "PM_MRK_START_PROBE_NOP_CMPL", - "BriefDescription": "Marked Start probe nop (AND R0,R0,R0) completed." - }, - { - "EventCode": "0x20016", - "EventName": "PM_ST_FIN", - "BriefDescription": "Store finish count. Includes speculative activity." - }, - { "EventCode": "0x20018", "EventName": "PM_ST_FWD", "BriefDescription": "Store forwards that finished." }, { - "EventCode": "0x2011C", - "EventName": "PM_MRK_NTF_CYC", - "BriefDescription": "Cycles during which the marked instruction is the oldest in the pipeline (NTF or NTC)." - }, - { - "EventCode": "0x2E01C", - "EventName": "PM_EXEC_STALL_TLBIE", - "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a TLBIE instruction executing in the Load Store Unit." - }, - { - "EventCode": "0x201E6", - "EventName": "PM_THRESH_EXC_32", - "BriefDescription": "Threshold counter exceeded a value of 32." - }, - { "EventCode": "0x200F0", "EventName": "PM_ST_CMPL", "BriefDescription": "Stores completed from S2Q (2nd-level store queue). This event includes regular stores, stcx and cache inhibited stores. The following operations are excluded (pteupdate, snoop tlbie complete, store atomics, miso, load atomic payloads, tlbie, tlbsync, slbieg, isync, msgsnd, slbiag, cpabort, copy, tcheck, tend, stsync, dcbst, icbi, dcbf, hwsync, lwsync, ptesync, eieio, msgsync)." @@ -37,21 +12,11 @@ { "EventCode": "0x200FE", "EventName": "PM_DATA_FROM_L2MISS", - "BriefDescription": "The processor's data cache was reloaded from a source other than the local core's L1 or L2 due to a demand miss." - }, - { - "EventCode": "0x30010", - "EventName": "PM_PMC2_OVERFLOW", - "BriefDescription": "The event selected for PMC2 caused the event counter to overflow." - }, - { - "EventCode": "0x4D010", - "EventName": "PM_PMC1_SAVED", - "BriefDescription": "The conditions for the speculative event selected for PMC1 are met and PMC1 is charged." + "BriefDescription": "The processor's L1 data cache was reloaded from a source beyond the local core's L2 due to a demand miss." }, { - "EventCode": "0x4D05C", - "EventName": "PM_DPP_FLOP_CMPL", - "BriefDescription": "Double-Precision or Quad-Precision instructions completed." + "EventCode": "0x300F0", + "EventName": "PM_ST_MISS_L1", + "BriefDescription": "Store Missed L1." } ] diff --git a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json index daf9458f0b77..c6780d5c456b 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json @@ -558,6 +558,7 @@ }, { "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the Last Level Cache (LLC) or other core with HITE/F/M.", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "cpu_atom@MEM_BOUND_STALLS.LOAD_LLC_HIT@ / tma_info_core_clks - max((cpu_atom@MEM_BOUND_STALLS.LOAD@ - cpu_atom@LD_HEAD.L1_MISS_AT_RET@) / tma_info_core_clks, 0) * cpu_atom@MEM_BOUND_STALLS.LOAD_LLC_HIT@ / cpu_atom@MEM_BOUND_STALLS.LOAD@", "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", @@ -800,6 +801,7 @@ }, { "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a store forward block.", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "LD_HEAD.ST_ADDR_AT_RET / tma_info_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", @@ -1058,7 +1060,6 @@ }, { "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector", "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", @@ -1230,6 +1231,7 @@ }, { "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", "MetricName": "tma_info_botlnk_l2_ic_misses", @@ -1267,6 +1269,7 @@ }, { "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))", "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW", "MetricName": "tma_info_bottleneck_memory_bandwidth", @@ -1355,7 +1358,6 @@ }, { "BriefDescription": "Floating Point Operations Per Cycle", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.SCALAR_SINGLE@ + cpu_core@FP_ARITH_INST_RETIRED.SCALAR_DOUBLE@ + 2 * cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + 4 * (cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@) + 8 * cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@) / tma_info_core_core_clks", "MetricGroup": "Flops;Ret", "MetricName": "tma_info_core_flopc", @@ -1363,7 +1365,6 @@ }, { "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(cpu_core@FP_ARITH_DISPATCHED.PORT_0@ + cpu_core@FP_ARITH_DISPATCHED.PORT_1@ + cpu_core@FP_ARITH_DISPATCHED.PORT_5@) / (2 * tma_info_core_core_clks)", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_core_fp_arith_utilization", @@ -1769,7 +1770,6 @@ }, { "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@", "MetricGroup": "Pipeline;Ret", "MetricName": "tma_info_pipeline_retire", @@ -2002,6 +2002,7 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "(cpu_core@MEMORY_ACTIVITY.STALLS_L2_MISS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L3_MISS@) / tma_info_thread_clks", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", @@ -2375,6 +2376,7 @@ }, { "BriefDescription": "This metric represents rate of split store accesses", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", @@ -2405,6 +2407,7 @@ }, { "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "13 * cpu_core@LD_BLOCKS.STORE_FORWARD@ / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json index 0f1628d698da..06e67e34e1bf 100644 --- a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json +++ b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json @@ -466,6 +466,7 @@ }, { "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the Last Level Cache (LLC) or other core with HITE/F/M.", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "MEM_BOUND_STALLS.LOAD_LLC_HIT / tma_info_core_clks - max((MEM_BOUND_STALLS.LOAD - LD_HEAD.L1_MISS_AT_RET) / tma_info_core_clks, 0) * MEM_BOUND_STALLS.LOAD_LLC_HIT / MEM_BOUND_STALLS.LOAD", "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", @@ -682,6 +683,7 @@ }, { "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a store forward block.", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "LD_HEAD.ST_ADDR_AT_RET / tma_info_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", diff --git a/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json b/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json index 8fcc05c4e0a1..a6eed0d9a26d 100644 --- a/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json @@ -85,6 +85,7 @@ }, { "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", @@ -319,7 +320,6 @@ }, { "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector", "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", @@ -464,6 +464,7 @@ }, { "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", "MetricName": "tma_info_botlnk_l2_ic_misses", @@ -497,6 +498,7 @@ }, { "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))", "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW", "MetricName": "tma_info_bottleneck_memory_bandwidth", @@ -574,14 +576,12 @@ }, { "BriefDescription": "Floating Point Operations Per Cycle", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@ + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / tma_info_core_core_clks", "MetricGroup": "Flops;Ret", "MetricName": "tma_info_core_flopc" }, { "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@) / (2 * tma_info_core_core_clks)", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_core_fp_arith_utilization", @@ -927,7 +927,6 @@ }, { "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", "MetricGroup": "Pipeline;Ret", "MetricName": "tma_info_pipeline_retire" @@ -1100,6 +1099,7 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", @@ -1419,6 +1419,7 @@ }, { "BriefDescription": "This metric represents rate of split store accesses", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", @@ -1446,6 +1447,7 @@ }, { "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", diff --git a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json index 9bb7e3f20f7f..7082ad5ba961 100644 --- a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json @@ -289,6 +289,7 @@ }, { "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", @@ -523,7 +524,6 @@ }, { "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector", "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", @@ -668,6 +668,7 @@ }, { "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", "MetricName": "tma_info_botlnk_l2_ic_misses", @@ -701,6 +702,7 @@ }, { "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))", "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW", "MetricName": "tma_info_bottleneck_memory_bandwidth", @@ -778,14 +780,12 @@ }, { "BriefDescription": "Floating Point Operations Per Cycle", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@ + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / tma_info_core_core_clks", "MetricGroup": "Flops;Ret", "MetricName": "tma_info_core_flopc" }, { "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@) / (2 * tma_info_core_core_clks)", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_core_fp_arith_utilization", @@ -1144,7 +1144,6 @@ }, { "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", "MetricGroup": "Pipeline;Ret", "MetricName": "tma_info_pipeline_retire" @@ -1369,6 +1368,7 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", @@ -1715,6 +1715,7 @@ }, { "BriefDescription": "This metric represents rate of split store accesses", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", @@ -1742,6 +1743,7 @@ }, { "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index 6650100830c4..3a8770e29fe8 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -19,12 +19,12 @@ GenuineIntel-6-3A,v24,ivybridge,core GenuineIntel-6-3E,v23,ivytown,core GenuineIntel-6-2D,v23,jaketown,core GenuineIntel-6-(57|85),v10,knightslanding,core -GenuineIntel-6-A[AC],v1.03,meteorlake,core +GenuineIntel-6-A[AC],v1.04,meteorlake,core GenuineIntel-6-1[AEF],v3,nehalemep,core GenuineIntel-6-2E,v3,nehalemex,core GenuineIntel-6-A7,v1.01,rocketlake,core GenuineIntel-6-2A,v19,sandybridge,core -GenuineIntel-6-(8F|CF),v1.14,sapphirerapids,core +GenuineIntel-6-(8F|CF),v1.15,sapphirerapids,core GenuineIntel-6-AF,v1.00,sierraforest,core GenuineIntel-6-(37|4A|4C|4D|5A),v15,silvermont,core GenuineIntel-6-(4E|5E|8E|9E|A5|A6),v57,skylake,core diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/cache.json b/tools/perf/pmu-events/arch/x86/meteorlake/cache.json index e1ae7c92f38e..1de0200b32f6 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/cache.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/cache.json @@ -37,6 +37,15 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Number of cycles a demand request has waited due to L1D due to lack of L2 resources.", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.L2_STALLS", + "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { "BriefDescription": "Number of L1D misses that are outstanding", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING", @@ -261,6 +270,15 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Cycles when L1D is locked", + "EventCode": "0x42", + "EventName": "LOCK_CYCLES.CACHE_LOCK_DURATION", + "PublicDescription": "This event counts the number of cycles when the L1D is locked. It is a superset of the 0x1 mask (BUS_LOCK_CLOCKS.BUS_LOCK_DURATION).", + "SampleAfterValue": "2000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts the number of cacheable memory requests that miss in the LLC. Counts on a per core basis.", "EventCode": "0x2e", "EventName": "LONGEST_LAT_CACHE.MISS", @@ -515,6 +533,17 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", + "Data_LA": "1", + "EventCode": "0xd2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS", + "PEBS": "1", + "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", + "SampleAfterValue": "20011", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { "BriefDescription": "Retired load instructions whose data sources were hits in L3 without snoops required", "Data_LA": "1", "EventCode": "0xd2", @@ -731,6 +760,14 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "MEM_STORE_RETIRED.L2_HIT", + "EventCode": "0x44", + "EventName": "MEM_STORE_RETIRED.L2_HIT", + "SampleAfterValue": "200003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts the number of load ops retired.", "Data_LA": "1", "EventCode": "0xd0", @@ -978,6 +1015,15 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Cacheable and Non-Cacheable code read requests", + "EventCode": "0x21", + "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD", + "PublicDescription": "Counts both cacheable and Non-Cacheable code read requests.", + "SampleAfterValue": "100003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { "BriefDescription": "Demand Data Read requests sent to uncore", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD", @@ -996,6 +1042,89 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.", + "CounterMask": "1", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles with offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore.", + "CounterMask": "1", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD", + "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles where at least 1 outstanding demand data read request is pending.", + "CounterMask": "1", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles with offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore.", + "CounterMask": "1", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", + "PublicDescription": "Counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore, every cycle.", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD", + "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "For every cycle, increments by the number of outstanding demand data read requests pending.", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD", + "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending. Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor.", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.", + "CounterMask": "6", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Store Read transactions pending for off-core. Highly correlated.", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO", + "PublicDescription": "Counts the number of off-core outstanding read-for-ownership (RFO) store transactions every cycle. An RFO transaction is considered to be in the Off-core outstanding state between L2 cache miss and transaction completion.", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts bus locks, accounts for cache line split locks and UC locks.", "EventCode": "0x2c", "EventName": "SQ_MISC.BUS_LOCK", @@ -1005,6 +1134,42 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Number of PREFETCHNTA instructions executed.", + "EventCode": "0x40", + "EventName": "SW_PREFETCH_ACCESS.NTA", + "PublicDescription": "Counts the number of PREFETCHNTA instructions executed.", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of PREFETCHW instructions executed.", + "EventCode": "0x40", + "EventName": "SW_PREFETCH_ACCESS.PREFETCHW", + "PublicDescription": "Counts the number of PREFETCHW instructions executed.", + "SampleAfterValue": "100003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of PREFETCHT0 instructions executed.", + "EventCode": "0x40", + "EventName": "SW_PREFETCH_ACCESS.T0", + "PublicDescription": "Counts the number of PREFETCHT0 instructions executed.", + "SampleAfterValue": "100003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of PREFETCHT1 or PREFETCHT2 instructions executed.", + "EventCode": "0x40", + "EventName": "SW_PREFETCH_ACCESS.T1_T2", + "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed.", + "SampleAfterValue": "100003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to an icache miss", "EventCode": "0x71", "EventName": "TOPDOWN_FE_BOUND.ICACHE", diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/floating-point.json b/tools/perf/pmu-events/arch/x86/meteorlake/floating-point.json index 616489f0974a..f66506ee37ef 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/floating-point.json @@ -42,6 +42,14 @@ "Unit": "cpu_core" }, { + "BriefDescription": "FP_ARITH_DISPATCHED.PORT_5", + "EventCode": "0xb3", + "EventName": "FP_ARITH_DISPATCHED.PORT_5", + "SampleAfterValue": "2000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE", diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json b/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json index 0f064518d1c0..8264419500a5 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json @@ -44,6 +44,14 @@ "Unit": "cpu_core" }, { + "BriefDescription": "DSB_FILL.FB_STALL_OT", + "EventCode": "0x62", + "EventName": "DSB_FILL.FB_STALL_OT", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { "BriefDescription": "Retired ANT branches", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.ANY_ANT", @@ -56,6 +64,30 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Retired Instructions who experienced DSB miss.", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x1", + "PEBS": "1", + "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired Instructions who experienced a critical DSB miss.", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.DSB_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x11", + "PEBS": "1", + "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts the number of instructions retired that were tagged because empty issue slots were seen before the uop due to ITLB miss", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.ITLB_MISS", @@ -89,6 +121,18 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss.", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.L2_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x13", + "PEBS": "1", + "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { "BriefDescription": "Retired instructions after front-end starvation of at least 1 cycle", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.LATENCY_GE_1", @@ -244,6 +288,18 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss.", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.STLB_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x15", + "PEBS": "1", + "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { "BriefDescription": "FRONTEND_RETIRED.UNKNOWN_BRANCH", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.UNKNOWN_BRANCH", diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/memory.json b/tools/perf/pmu-events/arch/x86/meteorlake/memory.json index 67e949b4c789..2605e1d0ba9f 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/memory.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/memory.json @@ -67,6 +67,15 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "Number of machine clears due to memory ordering conflicts.", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", + "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture", + "SampleAfterValue": "100003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.", "CounterMask": "3", "EventCode": "0x47", @@ -96,6 +105,35 @@ "Unit": "cpu_core" }, { + "BriefDescription": "MEMORY_ORDERING.MD_NUKE", + "EventCode": "0x09", + "EventName": "MEMORY_ORDERING.MD_NUKE", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of memory ordering machine clears due to memory renaming.", + "EventCode": "0x09", + "EventName": "MEMORY_ORDERING.MRN_NUKE", + "SampleAfterValue": "100003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles.", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_1024", + "MSRIndex": "0x3F6", + "MSRValue": "0x400", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "53", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.", "Data_LA": "1", "EventCode": "0xcd", @@ -122,6 +160,19 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles.", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_2048", + "MSRIndex": "0x3F6", + "MSRValue": "0x800", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "23", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.", "Data_LA": "1", "EventCode": "0xcd", @@ -235,5 +286,34 @@ "SampleAfterValue": "100003", "UMask": "0x10", "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles where data return is pending for a Demand Data Read request who miss L3 cache.", + "CounterMask": "1", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD", + "PublicDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ.", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache.", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD", + "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache. Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache.", + "SampleAfterValue": "2000003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles where the core is waiting on at least 6 outstanding demand data read requests known to have missed the L3 cache.", + "CounterMask": "6", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD_GE_6", + "PublicDescription": "Cycles where the core is waiting on at least 6 outstanding demand data read requests known to have missed the L3 cache. Note that this event does not capture all elapsed cycles while the requests are outstanding - only cycles from when the requests were known to have missed the L3 cache.", + "SampleAfterValue": "2000003", + "UMask": "0x10", + "Unit": "cpu_core" } ] diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/other.json b/tools/perf/pmu-events/arch/x86/meteorlake/other.json index 2ec57f487525..f4c603599df4 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/other.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/other.json @@ -1,5 +1,13 @@ [ { + "BriefDescription": "ASSISTS.PAGE_FAULT", + "EventCode": "0xc1", + "EventName": "ASSISTS.PAGE_FAULT", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts streaming stores that have any type of response.", "EventCode": "0x2A,0x2B", "EventName": "OCR.STREAMING_WR.ANY_RESPONSE", @@ -31,6 +39,14 @@ "Unit": "cpu_core" }, { + "BriefDescription": "RS.EMPTY_RESOURCE", + "EventCode": "0xa5", + "EventName": "RS.EMPTY_RESOURCE", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state. For Tremont, UMWAIT and TPAUSE will only put the CPU into C0.1 activity state (not C0.2 activity state)", "EventCode": "0x75", "EventName": "SERIALIZATION.C01_MS_SCB", diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json b/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json index eeaa7a97f71c..352c5efafc06 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json @@ -312,6 +312,16 @@ "Unit": "cpu_core" }, { + "BriefDescription": "This event counts the number of mispredicted ret instructions retired. Non PEBS", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.RET", + "PEBS": "1", + "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.", + "SampleAfterValue": "100007", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts the number of mispredicted near RET branch instructions retired.", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.RETURN", @@ -330,6 +340,33 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state.", + "EventCode": "0xec", + "EventName": "CPU_CLK_UNHALTED.C01", + "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions.", + "SampleAfterValue": "2000003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state.", + "EventCode": "0xec", + "EventName": "CPU_CLK_UNHALTED.C02", + "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions.", + "SampleAfterValue": "2000003", + "UMask": "0x20", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Core clocks when the thread is in the C0.1 or C0.2 or running a PAUSE in C0 ACPI state.", + "EventCode": "0xec", + "EventName": "CPU_CLK_UNHALTED.C0_WAIT", + "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction.", + "SampleAfterValue": "2000003", + "UMask": "0x70", + "Unit": "cpu_core" + }, + { "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles", "EventName": "CPU_CLK_UNHALTED.CORE", "SampleAfterValue": "2000003", @@ -362,6 +399,24 @@ "Unit": "cpu_core" }, { + "BriefDescription": "CPU_CLK_UNHALTED.PAUSE", + "EventCode": "0xec", + "EventName": "CPU_CLK_UNHALTED.PAUSE", + "SampleAfterValue": "2000003", + "UMask": "0x40", + "Unit": "cpu_core" + }, + { + "BriefDescription": "CPU_CLK_UNHALTED.PAUSE_INST", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0xec", + "EventName": "CPU_CLK_UNHALTED.PAUSE_INST", + "SampleAfterValue": "2000003", + "UMask": "0x40", + "Unit": "cpu_core" + }, + { "BriefDescription": "Core crystal clock cycles. Cycle counts are evenly distributed between active threads in the Core.", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.REF_DISTRIBUTED", @@ -603,6 +658,15 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Retired NOP instructions.", + "EventCode": "0xc0", + "EventName": "INST_RETIRED.NOP", + "PublicDescription": "Counts all retired NOP or ENDBR32/64 or PREFETCHIT0/1 instructions", + "SampleAfterValue": "2000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { "BriefDescription": "Precise instruction retired with PEBS precise-distribution", "EventName": "INST_RETIRED.PREC_DIST", "PEBS": "1", @@ -612,6 +676,15 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Iterations of Repeat string retired instructions.", + "EventCode": "0xc0", + "EventName": "INST_RETIRED.REP_ITERATION", + "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent.", + "SampleAfterValue": "2000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { "BriefDescription": "Cycles the Backend cluster is recovering after a miss-speculation or a Store Buffer or Load Buffer drain stall.", "CounterMask": "1", "EventCode": "0xad", @@ -622,6 +695,17 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Clears speculative count", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0xad", + "EventName": "INT_MISC.CLEARS_COUNT", + "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears", + "SampleAfterValue": "500009", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.", "EventCode": "0xad", "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES", @@ -631,6 +715,15 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Cycles when Resource Allocation Table (RAT) external stall is sent to Instruction Decode Queue (IDQ) for the thread", + "EventCode": "0xad", + "EventName": "INT_MISC.RAT_STALLS", + "PublicDescription": "This event counts the number of cycles during which Resource Allocation Table (RAT) external stall is sent to Instruction Decode Queue (IDQ) for the current thread. This also includes the cycles during which the Allocator is serving another thread.", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for this thread", "EventCode": "0xad", "EventName": "INT_MISC.RECOVERY_CYCLES", @@ -734,6 +827,15 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "False dependencies in MOB due to partial compare on address.", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.ADDRESS_ALIAS", + "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address.", + "SampleAfterValue": "100003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts the number of retired loads that are blocked because its address exactly matches an older store whose data is not ready.", "EventCode": "0x03", "EventName": "LD_BLOCKS.DATA_UNKNOWN", @@ -743,6 +845,15 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.NO_SR", + "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.", + "SampleAfterValue": "100003", + "UMask": "0x88", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts the number of retired loads that are blocked because its address partially overlapped with an older store.", "EventCode": "0x03", "EventName": "LD_BLOCKS.STORE_FORWARD", @@ -752,6 +863,15 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "Loads blocked due to overlapping with a preceding store that cannot be forwarded.", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.STORE_FORWARD", + "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide.", + "SampleAfterValue": "100003", + "UMask": "0x82", + "Unit": "cpu_core" + }, + { "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.", "CounterMask": "1", "EventCode": "0xa8", @@ -824,6 +944,24 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "Self-modifying code (SMC) detected.", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.SMC", + "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.", + "SampleAfterValue": "100003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "LFENCE instructions retired", + "EventCode": "0xe0", + "EventName": "MISC2_RETIRED.LFENCE", + "PublicDescription": "number of LFENCE retired instructions", + "SampleAfterValue": "400009", + "UMask": "0x20", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts cycles where the pipeline is stalled due to serializing operations.", "EventCode": "0xa2", "EventName": "RESOURCE_STALLS.SCOREBOARD", @@ -1261,6 +1399,16 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Cycles with retired uop(s).", + "CounterMask": "1", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.CYCLES", + "PublicDescription": "Counts cycles where at least one uop has retired.", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { "BriefDescription": "Retired uops except the last uop of each instruction.", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.HEAVY", @@ -1307,6 +1455,17 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Cycles without actually retired uops.", + "CounterMask": "1", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.STALLS", + "Invert": "1", + "PublicDescription": "This event counts cycles without actually retired uops.", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { "BriefDescription": "Cycles with less than 10 actually retired uops.", "CounterMask": "10", "EventCode": "0xc2", diff --git a/tools/perf/pmu-events/arch/x86/rocketlake/rkl-metrics.json b/tools/perf/pmu-events/arch/x86/rocketlake/rkl-metrics.json index 1bb9cededa56..a0191c8b708d 100644 --- a/tools/perf/pmu-events/arch/x86/rocketlake/rkl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/rocketlake/rkl-metrics.json @@ -85,6 +85,7 @@ }, { "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", @@ -319,7 +320,6 @@ }, { "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector", "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", @@ -464,6 +464,7 @@ }, { "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", "MetricName": "tma_info_botlnk_l2_ic_misses", @@ -497,6 +498,7 @@ }, { "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))", "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW", "MetricName": "tma_info_bottleneck_memory_bandwidth", @@ -574,14 +576,12 @@ }, { "BriefDescription": "Floating Point Operations Per Cycle", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@ + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / tma_info_core_core_clks", "MetricGroup": "Flops;Ret", "MetricName": "tma_info_core_flopc" }, { "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@) / (2 * tma_info_core_core_clks)", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_core_fp_arith_utilization", @@ -933,7 +933,6 @@ }, { "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", "MetricGroup": "Pipeline;Ret", "MetricName": "tma_info_pipeline_retire" @@ -1126,6 +1125,7 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", @@ -1445,6 +1445,7 @@ }, { "BriefDescription": "This metric represents rate of split store accesses", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", @@ -1472,6 +1473,7 @@ }, { "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/other.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/other.json index 31b6be9fb8c7..442ef3807a9d 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/other.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/other.json @@ -77,6 +77,24 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts demand data reads that were supplied by PMM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts PMM accesses that are controlled by the close or distant SNC Cluster.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.LOCAL_SOCKET_PMM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x700C00001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by PMM.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.PMM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x703C00001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to another socket.", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_DATA_RD.REMOTE_DRAM", diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json index c207c851a9f9..222212abd811 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json @@ -553,7 +553,6 @@ }, { "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector + tma_fp_amx", "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", @@ -717,6 +716,7 @@ }, { "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", "MetricName": "tma_info_botlnk_l2_ic_misses", @@ -750,6 +750,7 @@ }, { "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))", "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW", "MetricName": "tma_info_bottleneck_memory_bandwidth", @@ -827,14 +828,12 @@ }, { "BriefDescription": "Floating Point Operations Per Cycle", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + FP_ARITH_INST_RETIRED2.SCALAR_HALF + 2 * (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF) + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * (FP_ARITH_INST_RETIRED2.128B_PACKED_HALF + cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@) + 16 * (FP_ARITH_INST_RETIRED2.256B_PACKED_HALF + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) + 32 * FP_ARITH_INST_RETIRED2.512B_PACKED_HALF + 4 * AMX_OPS_RETIRED.BF16", "MetricGroup": "Flops;Ret", "MetricName": "tma_info_core_flopc" }, { "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(FP_ARITH_DISPATCHED.PORT_0 + FP_ARITH_DISPATCHED.PORT_1 + FP_ARITH_DISPATCHED.PORT_5) / (2 * tma_info_core_core_clks)", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_core_fp_arith_utilization", @@ -1216,7 +1215,6 @@ }, { "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", "MetricGroup": "Pipeline;Ret", "MetricName": "tma_info_pipeline_retire" @@ -1467,6 +1465,7 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L2_MISS - MEMORY_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", @@ -1841,6 +1840,7 @@ }, { "BriefDescription": "This metric represents rate of split store accesses", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", @@ -1868,6 +1868,7 @@ }, { "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", diff --git a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json index 94cb38540b5a..2795a404bb58 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json @@ -923,7 +923,7 @@ }, { "BriefDescription": "Average number of parallel data read requests to external memory", - "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.DATA_READ / UNC_ARB_TRK_OCCUPANCY.DATA_READ@thresh\\=1@", + "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.DATA_READ / UNC_ARB_TRK_OCCUPANCY.DATA_READ@cmask\\=1@", "MetricGroup": "Mem;MemoryBW;SoC", "MetricName": "tma_info_system_mem_parallel_reads", "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json b/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json index c7c2d6ab1a93..fab084e1bc69 100644 --- a/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json @@ -79,6 +79,7 @@ }, { "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", @@ -313,7 +314,6 @@ }, { "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector", "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", @@ -458,6 +458,7 @@ }, { "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", "MetricName": "tma_info_botlnk_l2_ic_misses", @@ -491,6 +492,7 @@ }, { "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))", "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW", "MetricName": "tma_info_bottleneck_memory_bandwidth", @@ -568,14 +570,12 @@ }, { "BriefDescription": "Floating Point Operations Per Cycle", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@ + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / tma_info_core_core_clks", "MetricGroup": "Flops;Ret", "MetricName": "tma_info_core_flopc" }, { "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@) / (2 * tma_info_core_core_clks)", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_core_fp_arith_utilization", @@ -927,7 +927,6 @@ }, { "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", "MetricGroup": "Pipeline;Ret", "MetricName": "tma_info_pipeline_retire" @@ -1114,6 +1113,7 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", @@ -1433,6 +1433,7 @@ }, { "BriefDescription": "This metric represents rate of split store accesses", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", @@ -1460,6 +1461,7 @@ }, { "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", diff --git a/tools/perf/pmu-events/empty-pmu-events.c b/tools/perf/pmu-events/empty-pmu-events.c index a630c617e879..12bd043a05e3 100644 --- a/tools/perf/pmu-events/empty-pmu-events.c +++ b/tools/perf/pmu-events/empty-pmu-events.c @@ -266,19 +266,53 @@ static const struct pmu_sys_events pmu_sys_event_tables[] = { }, }; -int pmu_events_table_for_each_event(const struct pmu_events_table *table, pmu_event_iter_fn fn, - void *data) +int pmu_events_table__for_each_event(const struct pmu_events_table *table, struct perf_pmu *pmu, + pmu_event_iter_fn fn, void *data) { for (const struct pmu_event *pe = &table->entries[0]; pe->name; pe++) { - int ret = fn(pe, table, data); + int ret; + if (pmu && !pmu__name_match(pmu, pe->pmu)) + continue; + + ret = fn(pe, table, data); if (ret) return ret; } return 0; } -int pmu_metrics_table_for_each_metric(const struct pmu_metrics_table *table, pmu_metric_iter_fn fn, +int pmu_events_table__find_event(const struct pmu_events_table *table, + struct perf_pmu *pmu, + const char *name, + pmu_event_iter_fn fn, + void *data) +{ + for (const struct pmu_event *pe = &table->entries[0]; pe->name; pe++) { + if (pmu && !pmu__name_match(pmu, pe->pmu)) + continue; + + if (!strcasecmp(pe->name, name)) + return fn(pe, table, data); + } + return -1000; +} + +size_t pmu_events_table__num_events(const struct pmu_events_table *table, + struct perf_pmu *pmu) +{ + size_t count = 0; + + for (const struct pmu_event *pe = &table->entries[0]; pe->name; pe++) { + if (pmu && !pmu__name_match(pmu, pe->pmu)) + continue; + + count++; + } + return count; +} + +int pmu_metrics_table__for_each_metric(const struct pmu_metrics_table *table, pmu_metric_iter_fn fn, void *data) { for (const struct pmu_metric *pm = &table->entries[0]; pm->metric_expr; pm++) { @@ -371,7 +405,8 @@ const struct pmu_metrics_table *find_core_metrics_table(const char *arch, const int pmu_for_each_core_event(pmu_event_iter_fn fn, void *data) { for (const struct pmu_events_map *tables = &pmu_events_map[0]; tables->arch; tables++) { - int ret = pmu_events_table_for_each_event(&tables->event_table, fn, data); + int ret = pmu_events_table__for_each_event(&tables->event_table, + /*pmu=*/ NULL, fn, data); if (ret) return ret; @@ -384,7 +419,7 @@ int pmu_for_each_core_metric(pmu_metric_iter_fn fn, void *data) for (const struct pmu_events_map *tables = &pmu_events_map[0]; tables->arch; tables++) { - int ret = pmu_metrics_table_for_each_metric(&tables->metric_table, fn, data); + int ret = pmu_metrics_table__for_each_metric(&tables->metric_table, fn, data); if (ret) return ret; @@ -408,7 +443,7 @@ int pmu_for_each_sys_event(pmu_event_iter_fn fn, void *data) for (const struct pmu_sys_events *tables = &pmu_sys_event_tables[0]; tables->name; tables++) { - int ret = pmu_events_table_for_each_event(&tables->table, fn, data); + int ret = pmu_events_table__for_each_event(&tables->table, /*pmu=*/ NULL, fn, data); if (ret) return ret; diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py index 12e80bb7939b..a7e88332276d 100755 --- a/tools/perf/pmu-events/jevents.py +++ b/tools/perf/pmu-events/jevents.py @@ -42,7 +42,7 @@ _metricgroups = {} # Order specific JsonEvent attributes will be visited. _json_event_attributes = [ # cmp_sevent related attributes. - 'name', 'pmu', 'topic', 'desc', + 'name', 'topic', 'desc', # Seems useful, put it early. 'event', # Short things in alphabetical order. @@ -53,7 +53,7 @@ _json_event_attributes = [ # Attributes that are in pmu_metric rather than pmu_event. _json_metric_attributes = [ - 'pmu', 'metric_name', 'metric_group', 'metric_expr', 'metric_threshold', + 'metric_name', 'metric_group', 'metric_expr', 'metric_threshold', 'desc', 'long_desc', 'unit', 'compat', 'metricgroup_no_group', 'default_metricgroup_name', 'aggr_mode', 'event_grouping' ] @@ -113,13 +113,24 @@ class BigCString: strings: Set[str] big_string: Sequence[str] offsets: Dict[str, int] + insert_number: int + insert_point: Dict[str, int] + metrics: Set[str] def __init__(self): self.strings = set() + self.insert_number = 0; + self.insert_point = {} + self.metrics = set() - def add(self, s: str) -> None: + def add(self, s: str, metric: bool) -> None: """Called to add to the big string.""" - self.strings.add(s) + if s not in self.strings: + self.strings.add(s) + self.insert_point[s] = self.insert_number + self.insert_number += 1 + if metric: + self.metrics.add(s) def compute(self) -> None: """Called once all strings are added to compute the string and offsets.""" @@ -160,8 +171,11 @@ class BigCString: self.big_string = [] self.offsets = {} + def string_cmp_key(s: str) -> Tuple[bool, int, str]: + return (s in self.metrics, self.insert_point[s], s) + # Emit all strings that aren't folded in a sorted manner. - for s in sorted(self.strings): + for s in sorted(self.strings, key=string_cmp_key): if s not in folded_strings: self.offsets[s] = big_string_offset self.big_string.append(f'/* offset={big_string_offset} */ "') @@ -252,7 +266,7 @@ class JsonEvent: def unit_to_pmu(unit: str) -> Optional[str]: """Convert a JSON Unit to Linux PMU name.""" if not unit: - return None + return 'default_core' # Comment brought over from jevents.c: # it's not realistic to keep adding these, we need something more scalable ... table = { @@ -274,6 +288,7 @@ class JsonEvent: 'DFPMC': 'amd_df', 'cpu_core': 'cpu_core', 'cpu_atom': 'cpu_atom', + 'ali_drw': 'ali_drw', } return table[unit] if unit in table else f'uncore_{unit.lower()}' @@ -342,16 +357,15 @@ class JsonEvent: self.desc += extra_desc if self.long_desc and extra_desc: self.long_desc += extra_desc - if self.pmu: - if self.desc and not self.desc.endswith('. '): - self.desc += '. ' - self.desc = (self.desc if self.desc else '') + ('Unit: ' + self.pmu + ' ') - if arch_std and arch_std.lower() in _arch_std_events: - event = _arch_std_events[arch_std.lower()].event - # Copy from the architecture standard event to self for undefined fields. - for attr, value in _arch_std_events[arch_std.lower()].__dict__.items(): - if hasattr(self, attr) and not getattr(self, attr): - setattr(self, attr, value) + if arch_std: + if arch_std.lower() in _arch_std_events: + event = _arch_std_events[arch_std.lower()].event + # Copy from the architecture standard event to self for undefined fields. + for attr, value in _arch_std_events[arch_std.lower()].__dict__.items(): + if hasattr(self, attr) and not getattr(self, attr): + setattr(self, attr, value) + else: + raise argparse.ArgumentTypeError('Cannot find arch std event:', arch_std) self.event = real_event(self.name, event) @@ -433,13 +447,13 @@ def add_events_table_entries(item: os.DirEntry, topic: str) -> None: def print_pending_events() -> None: """Optionally close events table.""" - def event_cmp_key(j: JsonEvent) -> Tuple[bool, str, str, str, str]: + def event_cmp_key(j: JsonEvent) -> Tuple[str, str, bool, str, str]: def fix_none(s: Optional[str]) -> str: if s is None: return '' return s - return (j.desc is not None, fix_none(j.topic), fix_none(j.name), fix_none(j.pmu), + return (fix_none(j.pmu).replace(',','_'), fix_none(j.name), j.desc is not None, fix_none(j.topic), fix_none(j.metric_name)) global _pending_events @@ -454,13 +468,36 @@ def print_pending_events() -> None: global event_tables _event_tables.append(_pending_events_tblname) - _args.output_file.write( - f'static const struct compact_pmu_event {_pending_events_tblname}[] = {{\n') - + first = True + last_pmu = None + pmus = set() for event in sorted(_pending_events, key=event_cmp_key): + if event.pmu != last_pmu: + if not first: + _args.output_file.write('};\n') + pmu_name = event.pmu.replace(',', '_') + _args.output_file.write( + f'static const struct compact_pmu_event {_pending_events_tblname}_{pmu_name}[] = {{\n') + first = False + last_pmu = event.pmu + pmus.add((event.pmu, pmu_name)) + _args.output_file.write(event.to_c_string(metric=False)) _pending_events = [] + _args.output_file.write(f""" +}}; + +const struct pmu_table_entry {_pending_events_tblname}[] = {{ +""") + for (pmu, tbl_pmu) in sorted(pmus): + pmu_name = f"{pmu}\\000" + _args.output_file.write(f"""{{ + .entries = {_pending_events_tblname}_{tbl_pmu}, + .num_entries = ARRAY_SIZE({_pending_events_tblname}_{tbl_pmu}), + .pmu_name = {{ {_bcs.offsets[pmu_name]} /* {pmu_name} */ }}, +}}, +""") _args.output_file.write('};\n\n') def print_pending_metrics() -> None: @@ -486,13 +523,36 @@ def print_pending_metrics() -> None: global metric_tables _metric_tables.append(_pending_metrics_tblname) - _args.output_file.write( - f'static const struct compact_pmu_event {_pending_metrics_tblname}[] = {{\n') - + first = True + last_pmu = None + pmus = set() for metric in sorted(_pending_metrics, key=metric_cmp_key): + if metric.pmu != last_pmu: + if not first: + _args.output_file.write('};\n') + pmu_name = metric.pmu.replace(',', '_') + _args.output_file.write( + f'static const struct compact_pmu_event {_pending_metrics_tblname}_{pmu_name}[] = {{\n') + first = False + last_pmu = metric.pmu + pmus.add((metric.pmu, pmu_name)) + _args.output_file.write(metric.to_c_string(metric=True)) _pending_metrics = [] + _args.output_file.write(f""" +}}; + +const struct pmu_table_entry {_pending_metrics_tblname}[] = {{ +""") + for (pmu, tbl_pmu) in sorted(pmus): + pmu_name = f"{pmu}\\000" + _args.output_file.write(f"""{{ + .entries = {_pending_metrics_tblname}_{tbl_pmu}, + .num_entries = ARRAY_SIZE({_pending_metrics_tblname}_{tbl_pmu}), + .pmu_name = {{ {_bcs.offsets[pmu_name]} /* {pmu_name} */ }}, +}}, +""") _args.output_file.write('};\n\n') def get_topic(topic: str) -> str: @@ -521,17 +581,20 @@ def preprocess_one_file(parents: Sequence[str], item: os.DirEntry) -> None: assert len(mgroup) > 1, parents description = f"{metricgroup_descriptions[mgroup]}\\000" mgroup = f"{mgroup}\\000" - _bcs.add(mgroup) - _bcs.add(description) + _bcs.add(mgroup, metric=True) + _bcs.add(description, metric=True) _metricgroups[mgroup] = description return topic = get_topic(item.name) for event in read_json_events(item.path, topic): + pmu_name = f"{event.pmu}\\000" if event.name: - _bcs.add(event.build_c_string(metric=False)) + _bcs.add(pmu_name, metric=False) + _bcs.add(event.build_c_string(metric=False), metric=False) if event.metric_name: - _bcs.add(event.build_c_string(metric=True)) + _bcs.add(pmu_name, metric=True) + _bcs.add(event.build_c_string(metric=True), metric=True) def process_one_file(parents: Sequence[str], item: os.DirEntry) -> None: """Process a JSON file during the main walk.""" @@ -573,14 +636,14 @@ def print_mapping_table(archs: Sequence[str]) -> None: _args.output_file.write(""" /* Struct used to make the PMU event table implementation opaque to callers. */ struct pmu_events_table { - const struct compact_pmu_event *entries; - size_t length; + const struct pmu_table_entry *pmus; + uint32_t num_pmus; }; /* Struct used to make the PMU metric table implementation opaque to callers. */ struct pmu_metrics_table { - const struct compact_pmu_event *entries; - size_t length; + const struct pmu_table_entry *pmus; + uint32_t num_pmus; }; /* @@ -610,12 +673,12 @@ const struct pmu_events_map pmu_events_map[] = { \t.arch = "testarch", \t.cpuid = "testcpu", \t.event_table = { -\t\t.entries = pmu_events__test_soc_cpu, -\t\t.length = ARRAY_SIZE(pmu_events__test_soc_cpu), +\t\t.pmus = pmu_events__test_soc_cpu, +\t\t.num_pmus = ARRAY_SIZE(pmu_events__test_soc_cpu), \t}, \t.metric_table = { -\t\t.entries = pmu_metrics__test_soc_cpu, -\t\t.length = ARRAY_SIZE(pmu_metrics__test_soc_cpu), +\t\t.pmus = pmu_metrics__test_soc_cpu, +\t\t.num_pmus = ARRAY_SIZE(pmu_metrics__test_soc_cpu), \t} }, """) @@ -645,12 +708,12 @@ const struct pmu_events_map pmu_events_map[] = { \t.arch = "{arch}", \t.cpuid = "{cpuid}", \t.event_table = {{ -\t\t.entries = {event_tblname}, -\t\t.length = {event_size} +\t\t.pmus = {event_tblname}, +\t\t.num_pmus = {event_size} \t}}, \t.metric_table = {{ -\t\t.entries = {metric_tblname}, -\t\t.length = {metric_size} +\t\t.pmus = {metric_tblname}, +\t\t.num_pmus = {metric_size} \t}} }}, """) @@ -681,15 +744,15 @@ static const struct pmu_sys_events pmu_sys_event_tables[] = { for tblname in _sys_event_tables: _args.output_file.write(f"""\t{{ \t\t.event_table = {{ -\t\t\t.entries = {tblname}, -\t\t\t.length = ARRAY_SIZE({tblname}) +\t\t\t.pmus = {tblname}, +\t\t\t.num_pmus = ARRAY_SIZE({tblname}) \t\t}},""") metric_tblname = _sys_event_table_to_metric_table_mapping[tblname] if metric_tblname in _sys_metric_tables: _args.output_file.write(f""" \t\t.metric_table = {{ -\t\t\t.entries = {metric_tblname}, -\t\t\t.length = ARRAY_SIZE({metric_tblname}) +\t\t\t.pmus = {metric_tblname}, +\t\t\t.num_pmus = ARRAY_SIZE({metric_tblname}) \t\t}},""") printed_metric_tables.append(metric_tblname) _args.output_file.write(f""" @@ -749,15 +812,18 @@ static void decompress_metric(int offset, struct pmu_metric *pm) _args.output_file.write('\twhile (*p++);') _args.output_file.write("""} -int pmu_events_table_for_each_event(const struct pmu_events_table *table, - pmu_event_iter_fn fn, - void *data) +static int pmu_events_table__for_each_event_pmu(const struct pmu_events_table *table, + const struct pmu_table_entry *pmu, + pmu_event_iter_fn fn, + void *data) { - for (size_t i = 0; i < table->length; i++) { - struct pmu_event pe; - int ret; + int ret; + struct pmu_event pe = { + .pmu = &big_c_string[pmu->pmu_name.offset], + }; - decompress_event(table->entries[i].offset, &pe); + for (uint32_t i = 0; i < pmu->num_entries; i++) { + decompress_event(pmu->entries[i].offset, &pe); if (!pe.name) continue; ret = fn(&pe, table, data); @@ -765,17 +831,119 @@ int pmu_events_table_for_each_event(const struct pmu_events_table *table, return ret; } return 0; + } + +static int pmu_events_table__find_event_pmu(const struct pmu_events_table *table, + const struct pmu_table_entry *pmu, + const char *name, + pmu_event_iter_fn fn, + void *data) +{ + struct pmu_event pe = { + .pmu = &big_c_string[pmu->pmu_name.offset], + }; + int low = 0, high = pmu->num_entries - 1; + + while (low <= high) { + int cmp, mid = (low + high) / 2; + + decompress_event(pmu->entries[mid].offset, &pe); + + if (!pe.name && !name) + goto do_call; + + if (!pe.name && name) { + low = mid + 1; + continue; + } + if (pe.name && !name) { + high = mid - 1; + continue; + } + + cmp = strcasecmp(pe.name, name); + if (cmp < 0) { + low = mid + 1; + continue; + } + if (cmp > 0) { + high = mid - 1; + continue; + } + do_call: + return fn ? fn(&pe, table, data) : 0; + } + return -1000; } -int pmu_metrics_table_for_each_metric(const struct pmu_metrics_table *table, - pmu_metric_iter_fn fn, - void *data) +int pmu_events_table__for_each_event(const struct pmu_events_table *table, + struct perf_pmu *pmu, + pmu_event_iter_fn fn, + void *data) +{ + for (size_t i = 0; i < table->num_pmus; i++) { + const struct pmu_table_entry *table_pmu = &table->pmus[i]; + const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset]; + int ret; + + if (pmu && !pmu__name_match(pmu, pmu_name)) + continue; + + ret = pmu_events_table__for_each_event_pmu(table, table_pmu, fn, data); + if (pmu || ret) + return ret; + } + return 0; +} + +int pmu_events_table__find_event(const struct pmu_events_table *table, + struct perf_pmu *pmu, + const char *name, + pmu_event_iter_fn fn, + void *data) { - for (size_t i = 0; i < table->length; i++) { - struct pmu_metric pm; + for (size_t i = 0; i < table->num_pmus; i++) { + const struct pmu_table_entry *table_pmu = &table->pmus[i]; + const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset]; int ret; - decompress_metric(table->entries[i].offset, &pm); + if (!pmu__name_match(pmu, pmu_name)) + continue; + + ret = pmu_events_table__find_event_pmu(table, table_pmu, name, fn, data); + if (ret != -1000) + return ret; + } + return -1000; +} + +size_t pmu_events_table__num_events(const struct pmu_events_table *table, + struct perf_pmu *pmu) +{ + size_t count = 0; + + for (size_t i = 0; i < table->num_pmus; i++) { + const struct pmu_table_entry *table_pmu = &table->pmus[i]; + const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset]; + + if (pmu__name_match(pmu, pmu_name)) + count += table_pmu->num_entries; + } + return count; +} + +static int pmu_metrics_table__for_each_metric_pmu(const struct pmu_metrics_table *table, + const struct pmu_table_entry *pmu, + pmu_metric_iter_fn fn, + void *data) +{ + int ret; + struct pmu_metric pm = { + .pmu = &big_c_string[pmu->pmu_name.offset], + }; + + for (uint32_t i = 0; i < pmu->num_entries; i++) { + decompress_metric(pmu->entries[i].offset, &pm); if (!pm.metric_expr) continue; ret = fn(&pm, table, data); @@ -785,11 +953,25 @@ int pmu_metrics_table_for_each_metric(const struct pmu_metrics_table *table, return 0; } +int pmu_metrics_table__for_each_metric(const struct pmu_metrics_table *table, + pmu_metric_iter_fn fn, + void *data) +{ + for (size_t i = 0; i < table->num_pmus; i++) { + int ret = pmu_metrics_table__for_each_metric_pmu(table, &table->pmus[i], + fn, data); + + if (ret) + return ret; + } + return 0; +} + const struct pmu_events_table *perf_pmu__find_events_table(struct perf_pmu *pmu) { const struct pmu_events_table *table = NULL; char *cpuid = perf_pmu__getcpuid(pmu); - int i; + size_t i; /* on some platforms which uses cpus map, cpuid can be NULL for * PMUs other than CORE PMUs. @@ -809,7 +991,17 @@ const struct pmu_events_table *perf_pmu__find_events_table(struct perf_pmu *pmu) } } free(cpuid); - return table; + if (!pmu) + return table; + + for (i = 0; i < table->num_pmus; i++) { + const struct pmu_table_entry *table_pmu = &table->pmus[i]; + const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset]; + + if (pmu__name_match(pmu, pmu_name)) + return table; + } + return NULL; } const struct pmu_metrics_table *perf_pmu__find_metrics_table(struct perf_pmu *pmu) @@ -866,7 +1058,8 @@ int pmu_for_each_core_event(pmu_event_iter_fn fn, void *data) for (const struct pmu_events_map *tables = &pmu_events_map[0]; tables->arch; tables++) { - int ret = pmu_events_table_for_each_event(&tables->event_table, fn, data); + int ret = pmu_events_table__for_each_event(&tables->event_table, + /*pmu=*/ NULL, fn, data); if (ret) return ret; @@ -879,7 +1072,7 @@ int pmu_for_each_core_metric(pmu_metric_iter_fn fn, void *data) for (const struct pmu_events_map *tables = &pmu_events_map[0]; tables->arch; tables++) { - int ret = pmu_metrics_table_for_each_metric(&tables->metric_table, fn, data); + int ret = pmu_metrics_table__for_each_metric(&tables->metric_table, fn, data); if (ret) return ret; @@ -903,7 +1096,8 @@ int pmu_for_each_sys_event(pmu_event_iter_fn fn, void *data) for (const struct pmu_sys_events *tables = &pmu_sys_event_tables[0]; tables->name; tables++) { - int ret = pmu_events_table_for_each_event(&tables->event_table, fn, data); + int ret = pmu_events_table__for_each_event(&tables->event_table, + /*pmu=*/ NULL, fn, data); if (ret) return ret; @@ -916,7 +1110,7 @@ int pmu_for_each_sys_metric(pmu_metric_iter_fn fn, void *data) for (const struct pmu_sys_events *tables = &pmu_sys_event_tables[0]; tables->name; tables++) { - int ret = pmu_metrics_table_for_each_metric(&tables->metric_table, fn, data); + int ret = pmu_metrics_table__for_each_metric(&tables->metric_table, fn, data); if (ret) return ret; @@ -999,14 +1193,20 @@ such as "arm/cortex-a34".''', _args = ap.parse_args() _args.output_file.write(""" -#include "pmu-events/pmu-events.h" +#include <pmu-events/pmu-events.h> #include "util/header.h" #include "util/pmu.h" #include <string.h> #include <stddef.h> struct compact_pmu_event { - int offset; + int offset; +}; + +struct pmu_table_entry { + const struct compact_pmu_event *entries; + uint32_t num_entries; + struct compact_pmu_event pmu_name; }; """) diff --git a/tools/perf/pmu-events/metric.py b/tools/perf/pmu-events/metric.py index 85a3545f5b6a..0e9ec65d92ae 100644 --- a/tools/perf/pmu-events/metric.py +++ b/tools/perf/pmu-events/metric.py @@ -413,6 +413,10 @@ def has_event(event: Event) -> Function: # pylint: disable=invalid-name return Function('has_event', event) +def strcmp_cpuid_str(event: str) -> Function: + # pylint: disable=redefined-builtin + # pylint: disable=invalid-name + return Function('strcmp_cpuid_str', event) class Metric: """An individual metric that will specifiable on the perf command line.""" @@ -541,14 +545,23 @@ def ParsePerfJson(orig: str) -> Expression: """ # pylint: disable=eval-used py = orig.strip() + # First try to convert everything that looks like a string (event name) into Event(r"EVENT_NAME"). + # This isn't very selective so is followed up by converting some unwanted conversions back again py = re.sub(r'([a-zA-Z][^-+/\* \\\(\),]*(?:\\.[^-+/\* \\\(\),]*)*)', r'Event(r"\1")', py) + # If it started with a # it should have been a literal, rather than an event name py = re.sub(r'#Event\(r"([^"]*)"\)', r'Literal("#\1")', py) + # Convert accidentally converted hex constants ("0Event(r"xDEADBEEF)"") back to a constant, + # but keep it wrapped in Event(), otherwise Python drops the 0x prefix and it gets interpreted as + # a double by the Bison parser + py = re.sub(r'0Event\(r"[xX]([0-9a-fA-F]*)"\)', r'Event("0x\1")', py) + # Convert accidentally converted scientific notation constants back py = re.sub(r'([0-9]+)Event\(r"(e[0-9]+)"\)', r'\1\2', py) - keywords = ['if', 'else', 'min', 'max', 'd_ratio', 'source_count', 'has_event'] + # Convert all the known keywords back from events to just the keyword + keywords = ['if', 'else', 'min', 'max', 'd_ratio', 'source_count', 'has_event', 'strcmp_cpuid_str', + 'cpuid_not_more_than'] for kw in keywords: py = re.sub(rf'Event\(r"{kw}"\)', kw, py) - try: parsed = ast.parse(py, mode='eval') except SyntaxError as e: diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h index caf59f23cd64..f5aa96f1685c 100644 --- a/tools/perf/pmu-events/pmu-events.h +++ b/tools/perf/pmu-events/pmu-events.h @@ -3,6 +3,7 @@ #define PMU_EVENTS_H #include <stdbool.h> +#include <stddef.h> struct perf_pmu; @@ -77,9 +78,19 @@ typedef int (*pmu_metric_iter_fn)(const struct pmu_metric *pm, const struct pmu_metrics_table *table, void *data); -int pmu_events_table_for_each_event(const struct pmu_events_table *table, pmu_event_iter_fn fn, +int pmu_events_table__for_each_event(const struct pmu_events_table *table, + struct perf_pmu *pmu, + pmu_event_iter_fn fn, void *data); -int pmu_metrics_table_for_each_metric(const struct pmu_metrics_table *table, pmu_metric_iter_fn fn, +int pmu_events_table__find_event(const struct pmu_events_table *table, + struct perf_pmu *pmu, + const char *name, + pmu_event_iter_fn fn, + void *data); +size_t pmu_events_table__num_events(const struct pmu_events_table *table, + struct perf_pmu *pmu); + +int pmu_metrics_table__for_each_metric(const struct pmu_metrics_table *table, pmu_metric_iter_fn fn, void *data); const struct pmu_events_table *perf_pmu__find_events_table(struct perf_pmu *pmu); diff --git a/tools/perf/scripts/python/Perf-Trace-Util/Build b/tools/perf/scripts/python/Perf-Trace-Util/Build index 7d0e33ce6aba..5b0b5ff7e14a 100644 --- a/tools/perf/scripts/python/Perf-Trace-Util/Build +++ b/tools/perf/scripts/python/Perf-Trace-Util/Build @@ -1,3 +1,4 @@ perf-y += Context.o -CFLAGS_Context.o += $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs +# -Wno-declaration-after-statement: The python headers have mixed code with declarations (decls after asserts, for instance) +CFLAGS_Context.o += $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs -Wno-declaration-after-statement diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py index 7384dcb628c4..b75d31858e54 100644 --- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py +++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py @@ -54,6 +54,7 @@ try: import audit machine_to_id = { 'x86_64': audit.MACH_86_64, + 'aarch64': audit.MACH_AARCH64, 'alpha' : audit.MACH_ALPHA, 'ia64' : audit.MACH_IA64, 'ppc' : audit.MACH_PPC, @@ -73,9 +74,9 @@ try: except: if not audit_package_warned: audit_package_warned = True - print("Install the audit-libs-python package to get syscall names.\n" - "For example:\n # apt-get install python-audit (Ubuntu)" - "\n # yum install audit-libs-python (Fedora)" + print("Install the python-audit package to get syscall names.\n" + "For example:\n # apt-get install python3-audit (Ubuntu)" + "\n # yum install python3-audit (Fedora)" "\n etc.\n") def syscall_name(id): diff --git a/tools/perf/scripts/python/bin/gecko-record b/tools/perf/scripts/python/bin/gecko-record new file mode 100644 index 000000000000..f0d1aa55f171 --- /dev/null +++ b/tools/perf/scripts/python/bin/gecko-record @@ -0,0 +1,2 @@ +#!/bin/bash +perf record -F 99 -g "$@" diff --git a/tools/perf/scripts/python/bin/gecko-report b/tools/perf/scripts/python/bin/gecko-report new file mode 100755 index 000000000000..1867ec8d9757 --- /dev/null +++ b/tools/perf/scripts/python/bin/gecko-report @@ -0,0 +1,7 @@ +#!/bin/bash +# description: create firefox gecko profile json format from perf.data +if [ "$*" = "-i -" ]; then +perf script -s "$PERF_EXEC_PATH"/scripts/python/gecko.py +else +perf script -s "$PERF_EXEC_PATH"/scripts/python/gecko.py -- "$@" +fi diff --git a/tools/perf/scripts/python/gecko.py b/tools/perf/scripts/python/gecko.py new file mode 100644 index 000000000000..bc5a72f94bfa --- /dev/null +++ b/tools/perf/scripts/python/gecko.py @@ -0,0 +1,395 @@ +# gecko.py - Convert perf record output to Firefox's gecko profile format +# SPDX-License-Identifier: GPL-2.0 +# +# The script converts perf.data to Gecko Profile Format, +# which can be read by https://profiler.firefox.com/. +# +# Usage: +# +# perf record -a -g -F 99 sleep 60 +# perf script report gecko +# +# Combined: +# +# perf script gecko -F 99 -a sleep 60 + +import os +import sys +import time +import json +import string +import random +import argparse +import threading +import webbrowser +import urllib.parse +from os import system +from functools import reduce +from dataclasses import dataclass, field +from http.server import HTTPServer, SimpleHTTPRequestHandler, test +from typing import List, Dict, Optional, NamedTuple, Set, Tuple, Any + +# Add the Perf-Trace-Util library to the Python path +sys.path.append(os.environ['PERF_EXEC_PATH'] + \ + '/scripts/python/Perf-Trace-Util/lib/Perf/Trace') + +from perf_trace_context import * +from Core import * + +StringID = int +StackID = int +FrameID = int +CategoryID = int +Milliseconds = float + +# start_time is intialiazed only once for the all event traces. +start_time = None + +# https://github.com/firefox-devtools/profiler/blob/53970305b51b9b472e26d7457fee1d66cd4e2737/src/types/profile.js#L425 +# Follow Brendan Gregg's Flamegraph convention: orange for kernel and yellow for user space by default. +CATEGORIES = None + +# The product name is used by the profiler UI to show the Operating system and Processor. +PRODUCT = os.popen('uname -op').read().strip() + +# store the output file +output_file = None + +# Here key = tid, value = Thread +tid_to_thread = dict() + +# The HTTP server is used to serve the profile to the profiler UI. +http_server_thread = None + +# The category index is used by the profiler UI to show the color of the flame graph. +USER_CATEGORY_INDEX = 0 +KERNEL_CATEGORY_INDEX = 1 + +# https://github.com/firefox-devtools/profiler/blob/53970305b51b9b472e26d7457fee1d66cd4e2737/src/types/gecko-profile.js#L156 +class Frame(NamedTuple): + string_id: StringID + relevantForJS: bool + innerWindowID: int + implementation: None + optimizations: None + line: None + column: None + category: CategoryID + subcategory: int + +# https://github.com/firefox-devtools/profiler/blob/53970305b51b9b472e26d7457fee1d66cd4e2737/src/types/gecko-profile.js#L216 +class Stack(NamedTuple): + prefix_id: Optional[StackID] + frame_id: FrameID + +# https://github.com/firefox-devtools/profiler/blob/53970305b51b9b472e26d7457fee1d66cd4e2737/src/types/gecko-profile.js#L90 +class Sample(NamedTuple): + stack_id: Optional[StackID] + time_ms: Milliseconds + responsiveness: int + +@dataclass +class Thread: + """A builder for a profile of the thread. + + Attributes: + comm: Thread command-line (name). + pid: process ID of containing process. + tid: thread ID. + samples: Timeline of profile samples. + frameTable: interned stack frame ID -> stack frame. + stringTable: interned string ID -> string. + stringMap: interned string -> string ID. + stackTable: interned stack ID -> stack. + stackMap: (stack prefix ID, leaf stack frame ID) -> interned Stack ID. + frameMap: Stack Frame string -> interned Frame ID. + comm: str + pid: int + tid: int + samples: List[Sample] = field(default_factory=list) + frameTable: List[Frame] = field(default_factory=list) + stringTable: List[str] = field(default_factory=list) + stringMap: Dict[str, int] = field(default_factory=dict) + stackTable: List[Stack] = field(default_factory=list) + stackMap: Dict[Tuple[Optional[int], int], int] = field(default_factory=dict) + frameMap: Dict[str, int] = field(default_factory=dict) + """ + comm: str + pid: int + tid: int + samples: List[Sample] = field(default_factory=list) + frameTable: List[Frame] = field(default_factory=list) + stringTable: List[str] = field(default_factory=list) + stringMap: Dict[str, int] = field(default_factory=dict) + stackTable: List[Stack] = field(default_factory=list) + stackMap: Dict[Tuple[Optional[int], int], int] = field(default_factory=dict) + frameMap: Dict[str, int] = field(default_factory=dict) + + def _intern_stack(self, frame_id: int, prefix_id: Optional[int]) -> int: + """Gets a matching stack, or saves the new stack. Returns a Stack ID.""" + key = f"{frame_id}" if prefix_id is None else f"{frame_id},{prefix_id}" + # key = (prefix_id, frame_id) + stack_id = self.stackMap.get(key) + if stack_id is None: + # return stack_id + stack_id = len(self.stackTable) + self.stackTable.append(Stack(prefix_id=prefix_id, frame_id=frame_id)) + self.stackMap[key] = stack_id + return stack_id + + def _intern_string(self, string: str) -> int: + """Gets a matching string, or saves the new string. Returns a String ID.""" + string_id = self.stringMap.get(string) + if string_id is not None: + return string_id + string_id = len(self.stringTable) + self.stringTable.append(string) + self.stringMap[string] = string_id + return string_id + + def _intern_frame(self, frame_str: str) -> int: + """Gets a matching stack frame, or saves the new frame. Returns a Frame ID.""" + frame_id = self.frameMap.get(frame_str) + if frame_id is not None: + return frame_id + frame_id = len(self.frameTable) + self.frameMap[frame_str] = frame_id + string_id = self._intern_string(frame_str) + + symbol_name_to_category = KERNEL_CATEGORY_INDEX if frame_str.find('kallsyms') != -1 \ + or frame_str.find('/vmlinux') != -1 \ + or frame_str.endswith('.ko)') \ + else USER_CATEGORY_INDEX + + self.frameTable.append(Frame( + string_id=string_id, + relevantForJS=False, + innerWindowID=0, + implementation=None, + optimizations=None, + line=None, + column=None, + category=symbol_name_to_category, + subcategory=None, + )) + return frame_id + + def _add_sample(self, comm: str, stack: List[str], time_ms: Milliseconds) -> None: + """Add a timestamped stack trace sample to the thread builder. + Args: + comm: command-line (name) of the thread at this sample + stack: sampled stack frames. Root first, leaf last. + time_ms: timestamp of sample in milliseconds. + """ + # Ihreads may not set their names right after they are created. + # Instead, they might do it later. In such situations, to use the latest name they have set. + if self.comm != comm: + self.comm = comm + + prefix_stack_id = reduce(lambda prefix_id, frame: self._intern_stack + (self._intern_frame(frame), prefix_id), stack, None) + if prefix_stack_id is not None: + self.samples.append(Sample(stack_id=prefix_stack_id, + time_ms=time_ms, + responsiveness=0)) + + def _to_json_dict(self) -> Dict: + """Converts current Thread to GeckoThread JSON format.""" + # Gecko profile format is row-oriented data as List[List], + # And a schema for interpreting each index. + # Schema: + # https://github.com/firefox-devtools/profiler/blob/main/docs-developer/gecko-profile-format.md + # https://github.com/firefox-devtools/profiler/blob/53970305b51b9b472e26d7457fee1d66cd4e2737/src/types/gecko-profile.js#L230 + return { + "tid": self.tid, + "pid": self.pid, + "name": self.comm, + # https://github.com/firefox-devtools/profiler/blob/53970305b51b9b472e26d7457fee1d66cd4e2737/src/types/gecko-profile.js#L51 + "markers": { + "schema": { + "name": 0, + "startTime": 1, + "endTime": 2, + "phase": 3, + "category": 4, + "data": 5, + }, + "data": [], + }, + + # https://github.com/firefox-devtools/profiler/blob/53970305b51b9b472e26d7457fee1d66cd4e2737/src/types/gecko-profile.js#L90 + "samples": { + "schema": { + "stack": 0, + "time": 1, + "responsiveness": 2, + }, + "data": self.samples + }, + + # https://github.com/firefox-devtools/profiler/blob/53970305b51b9b472e26d7457fee1d66cd4e2737/src/types/gecko-profile.js#L156 + "frameTable": { + "schema": { + "location": 0, + "relevantForJS": 1, + "innerWindowID": 2, + "implementation": 3, + "optimizations": 4, + "line": 5, + "column": 6, + "category": 7, + "subcategory": 8, + }, + "data": self.frameTable, + }, + + # https://github.com/firefox-devtools/profiler/blob/53970305b51b9b472e26d7457fee1d66cd4e2737/src/types/gecko-profile.js#L216 + "stackTable": { + "schema": { + "prefix": 0, + "frame": 1, + }, + "data": self.stackTable, + }, + "stringTable": self.stringTable, + "registerTime": 0, + "unregisterTime": None, + "processType": "default", + } + +# Uses perf script python interface to parse each +# event and store the data in the thread builder. +def process_event(param_dict: Dict) -> None: + global start_time + global tid_to_thread + time_stamp = (param_dict['sample']['time'] // 1000) / 1000 + pid = param_dict['sample']['pid'] + tid = param_dict['sample']['tid'] + comm = param_dict['comm'] + + # Start time is the time of the first sample + if not start_time: + start_time = time_stamp + + # Parse and append the callchain of the current sample into a stack. + stack = [] + if param_dict['callchain']: + for call in param_dict['callchain']: + if 'sym' not in call: + continue + stack.append(f'{call["sym"]["name"]} (in {call["dso"]})') + if len(stack) != 0: + # Reverse the stack, as root come first and the leaf at the end. + stack = stack[::-1] + + # During perf record if -g is not used, the callchain is not available. + # In that case, the symbol and dso are available in the event parameters. + else: + func = param_dict['symbol'] if 'symbol' in param_dict else '[unknown]' + dso = param_dict['dso'] if 'dso' in param_dict else '[unknown]' + stack.append(f'{func} (in {dso})') + + # Add sample to the specific thread. + thread = tid_to_thread.get(tid) + if thread is None: + thread = Thread(comm=comm, pid=pid, tid=tid) + tid_to_thread[tid] = thread + thread._add_sample(comm=comm, stack=stack, time_ms=time_stamp) + +def trace_begin() -> None: + global output_file + if (output_file is None): + print("Staring Firefox Profiler on your default browser...") + global http_server_thread + http_server_thread = threading.Thread(target=test, args=(CORSRequestHandler, HTTPServer,)) + http_server_thread.daemon = True + http_server_thread.start() + +# Trace_end runs at the end and will be used to aggregate +# the data into the final json object and print it out to stdout. +def trace_end() -> None: + global output_file + threads = [thread._to_json_dict() for thread in tid_to_thread.values()] + + # Schema: https://github.com/firefox-devtools/profiler/blob/53970305b51b9b472e26d7457fee1d66cd4e2737/src/types/gecko-profile.js#L305 + gecko_profile_with_meta = { + "meta": { + "interval": 1, + "processType": 0, + "product": PRODUCT, + "stackwalk": 1, + "debug": 0, + "gcpoison": 0, + "asyncstack": 1, + "startTime": start_time, + "shutdownTime": None, + "version": 24, + "presymbolicated": True, + "categories": CATEGORIES, + "markerSchema": [], + }, + "libs": [], + "threads": threads, + "processes": [], + "pausedRanges": [], + } + # launch the profiler on local host if not specified --save-only args, otherwise print to file + if (output_file is None): + output_file = 'gecko_profile.json' + with open(output_file, 'w') as f: + json.dump(gecko_profile_with_meta, f, indent=2) + launchFirefox(output_file) + time.sleep(1) + print(f'[ perf gecko: Captured and wrote into {output_file} ]') + else: + print(f'[ perf gecko: Captured and wrote into {output_file} ]') + with open(output_file, 'w') as f: + json.dump(gecko_profile_with_meta, f, indent=2) + +# Used to enable Cross-Origin Resource Sharing (CORS) for requests coming from 'https://profiler.firefox.com', allowing it to access resources from this server. +class CORSRequestHandler(SimpleHTTPRequestHandler): + def end_headers (self): + self.send_header('Access-Control-Allow-Origin', 'https://profiler.firefox.com') + SimpleHTTPRequestHandler.end_headers(self) + +# start a local server to serve the gecko_profile.json file to the profiler.firefox.com +def launchFirefox(file): + safe_string = urllib.parse.quote_plus(f'http://localhost:8000/{file}') + url = 'https://profiler.firefox.com/from-url/' + safe_string + webbrowser.open(f'{url}') + +def main() -> None: + global output_file + global CATEGORIES + parser = argparse.ArgumentParser(description="Convert perf.data to Firefox\'s Gecko Profile format which can be uploaded to profiler.firefox.com for visualization") + + # Add the command-line options + # Colors must be defined according to this: + # https://github.com/firefox-devtools/profiler/blob/50124adbfa488adba6e2674a8f2618cf34b59cd2/res/css/categories.css + parser.add_argument('--user-color', default='yellow', help='Color for the User category', choices=['yellow', 'blue', 'purple', 'green', 'orange', 'red', 'grey', 'magenta']) + parser.add_argument('--kernel-color', default='orange', help='Color for the Kernel category', choices=['yellow', 'blue', 'purple', 'green', 'orange', 'red', 'grey', 'magenta']) + # If --save-only is specified, the output will be saved to a file instead of opening Firefox's profiler directly. + parser.add_argument('--save-only', help='Save the output to a file instead of opening Firefox\'s profiler') + + # Parse the command-line arguments + args = parser.parse_args() + # Access the values provided by the user + user_color = args.user_color + kernel_color = args.kernel_color + output_file = args.save_only + + CATEGORIES = [ + { + "name": 'User', + "color": user_color, + "subcategories": ['Other'] + }, + { + "name": 'Kernel', + "color": kernel_color, + "subcategories": ['Other'] + }, + ] + +if __name__ == '__main__': + main() diff --git a/tools/perf/tests/.gitignore b/tools/perf/tests/.gitignore deleted file mode 100644 index d053b325f728..000000000000 --- a/tools/perf/tests/.gitignore +++ /dev/null @@ -1,5 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -llvm-src-base.c -llvm-src-kbuild.c -llvm-src-prologue.c -llvm-src-relocation.c diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build index fb9ac5dc4079..63d5e6d5f165 100644 --- a/tools/perf/tests/Build +++ b/tools/perf/tests/Build @@ -37,8 +37,6 @@ perf-y += sample-parsing.o perf-y += parse-no-sample-id-all.o perf-y += kmod-path.o perf-y += thread-map.o -perf-y += llvm.o llvm-src-base.o llvm-src-kbuild.o llvm-src-prologue.o llvm-src-relocation.o -perf-y += bpf.o perf-y += topology.o perf-y += mem.o perf-y += cpumap.o @@ -51,7 +49,6 @@ perf-y += sdt.o perf-y += is_printable_array.o perf-y += bitmap.o perf-y += perf-hooks.o -perf-y += clang.o perf-y += unit_number__scnprintf.o perf-y += mem2node.o perf-y += maps.o @@ -70,34 +67,6 @@ perf-y += sigtrap.o perf-y += event_groups.o perf-y += symbols.o -$(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build - $(call rule_mkdir) - $(Q)echo '#include <tests/llvm.h>' > $@ - $(Q)echo 'const char test_llvm__bpf_base_prog[] =' >> $@ - $(Q)sed -e 's/"/\\"/g' -e 's/\(.*\)/"\1\\n"/g' $< >> $@ - $(Q)echo ';' >> $@ - -$(OUTPUT)tests/llvm-src-kbuild.c: tests/bpf-script-test-kbuild.c tests/Build - $(call rule_mkdir) - $(Q)echo '#include <tests/llvm.h>' > $@ - $(Q)echo 'const char test_llvm__bpf_test_kbuild_prog[] =' >> $@ - $(Q)sed -e 's/"/\\"/g' -e 's/\(.*\)/"\1\\n"/g' $< >> $@ - $(Q)echo ';' >> $@ - -$(OUTPUT)tests/llvm-src-prologue.c: tests/bpf-script-test-prologue.c tests/Build - $(call rule_mkdir) - $(Q)echo '#include <tests/llvm.h>' > $@ - $(Q)echo 'const char test_llvm__bpf_test_prologue_prog[] =' >> $@ - $(Q)sed -e 's/"/\\"/g' -e 's/\(.*\)/"\1\\n"/g' $< >> $@ - $(Q)echo ';' >> $@ - -$(OUTPUT)tests/llvm-src-relocation.c: tests/bpf-script-test-relocation.c tests/Build - $(call rule_mkdir) - $(Q)echo '#include <tests/llvm.h>' > $@ - $(Q)echo 'const char test_llvm__bpf_test_relocation[] =' >> $@ - $(Q)sed -e 's/"/\\"/g' -e 's/\(.*\)/"\1\\n"/g' $< >> $@ - $(Q)echo ';' >> $@ - ifeq ($(SRCARCH),$(filter $(SRCARCH),x86 arm arm64 powerpc)) perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o endif diff --git a/tools/perf/tests/bpf-script-example.c b/tools/perf/tests/bpf-script-example.c deleted file mode 100644 index b638cc99d5ae..000000000000 --- a/tools/perf/tests/bpf-script-example.c +++ /dev/null @@ -1,60 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * bpf-script-example.c - * Test basic LLVM building - */ -#ifndef LINUX_VERSION_CODE -# error Need LINUX_VERSION_CODE -# error Example: for 4.2 kernel, put 'clang-opt="-DLINUX_VERSION_CODE=0x40200" into llvm section of ~/.perfconfig' -#endif -#define BPF_ANY 0 -#define BPF_MAP_TYPE_ARRAY 2 -#define BPF_FUNC_map_lookup_elem 1 -#define BPF_FUNC_map_update_elem 2 - -static void *(*bpf_map_lookup_elem)(void *map, void *key) = - (void *) BPF_FUNC_map_lookup_elem; -static void *(*bpf_map_update_elem)(void *map, void *key, void *value, int flags) = - (void *) BPF_FUNC_map_update_elem; - -/* - * Following macros are taken from tools/lib/bpf/bpf_helpers.h, - * and are used to create BTF defined maps. It is easier to take - * 2 simple macros, than being able to include above header in - * runtime. - * - * __uint - defines integer attribute of BTF map definition, - * Such attributes are represented using a pointer to an array, - * in which dimensionality of array encodes specified integer - * value. - * - * __type - defines pointer variable with typeof(val) type for - * attributes like key or value, which will be defined by the - * size of the type. - */ -#define __uint(name, val) int (*name)[val] -#define __type(name, val) typeof(val) *name - -#define SEC(NAME) __attribute__((section(NAME), used)) -struct { - __uint(type, BPF_MAP_TYPE_ARRAY); - __uint(max_entries, 1); - __type(key, int); - __type(value, int); -} flip_table SEC(".maps"); - -SEC("syscalls:sys_enter_epoll_pwait") -int bpf_func__SyS_epoll_pwait(void *ctx) -{ - int ind =0; - int *flag = bpf_map_lookup_elem(&flip_table, &ind); - int new_flag; - if (!flag) - return 0; - /* flip flag and store back */ - new_flag = !*flag; - bpf_map_update_elem(&flip_table, &ind, &new_flag, BPF_ANY); - return new_flag; -} -char _license[] SEC("license") = "GPL"; -int _version SEC("version") = LINUX_VERSION_CODE; diff --git a/tools/perf/tests/bpf-script-test-kbuild.c b/tools/perf/tests/bpf-script-test-kbuild.c deleted file mode 100644 index 219673aa278f..000000000000 --- a/tools/perf/tests/bpf-script-test-kbuild.c +++ /dev/null @@ -1,21 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * bpf-script-test-kbuild.c - * Test include from kernel header - */ -#ifndef LINUX_VERSION_CODE -# error Need LINUX_VERSION_CODE -# error Example: for 4.2 kernel, put 'clang-opt="-DLINUX_VERSION_CODE=0x40200" into llvm section of ~/.perfconfig' -#endif -#define SEC(NAME) __attribute__((section(NAME), used)) - -#include <uapi/linux/fs.h> - -SEC("func=vfs_llseek") -int bpf_func__vfs_llseek(void *ctx) -{ - return 0; -} - -char _license[] SEC("license") = "GPL"; -int _version SEC("version") = LINUX_VERSION_CODE; diff --git a/tools/perf/tests/bpf-script-test-prologue.c b/tools/perf/tests/bpf-script-test-prologue.c deleted file mode 100644 index 91778b5c6125..000000000000 --- a/tools/perf/tests/bpf-script-test-prologue.c +++ /dev/null @@ -1,49 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * bpf-script-test-prologue.c - * Test BPF prologue - */ -#ifndef LINUX_VERSION_CODE -# error Need LINUX_VERSION_CODE -# error Example: for 4.2 kernel, put 'clang-opt="-DLINUX_VERSION_CODE=0x40200" into llvm section of ~/.perfconfig' -#endif -#define SEC(NAME) __attribute__((section(NAME), used)) - -#include <uapi/linux/fs.h> - -/* - * If CONFIG_PROFILE_ALL_BRANCHES is selected, - * 'if' is redefined after include kernel header. - * Recover 'if' for BPF object code. - */ -#ifdef if -# undef if -#endif - -typedef unsigned int __bitwise fmode_t; - -#define FMODE_READ 0x1 -#define FMODE_WRITE 0x2 - -static void (*bpf_trace_printk)(const char *fmt, int fmt_size, ...) = - (void *) 6; - -SEC("func=null_lseek file->f_mode offset orig") -int bpf_func__null_lseek(void *ctx, int err, unsigned long _f_mode, - unsigned long offset, unsigned long orig) -{ - fmode_t f_mode = (fmode_t)_f_mode; - - if (err) - return 0; - if (f_mode & FMODE_WRITE) - return 0; - if (offset & 1) - return 0; - if (orig == SEEK_CUR) - return 0; - return 1; -} - -char _license[] SEC("license") = "GPL"; -int _version SEC("version") = LINUX_VERSION_CODE; diff --git a/tools/perf/tests/bpf-script-test-relocation.c b/tools/perf/tests/bpf-script-test-relocation.c deleted file mode 100644 index 74006e4b2d24..000000000000 --- a/tools/perf/tests/bpf-script-test-relocation.c +++ /dev/null @@ -1,51 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * bpf-script-test-relocation.c - * Test BPF loader checking relocation - */ -#ifndef LINUX_VERSION_CODE -# error Need LINUX_VERSION_CODE -# error Example: for 4.2 kernel, put 'clang-opt="-DLINUX_VERSION_CODE=0x40200" into llvm section of ~/.perfconfig' -#endif -#define BPF_ANY 0 -#define BPF_MAP_TYPE_ARRAY 2 -#define BPF_FUNC_map_lookup_elem 1 -#define BPF_FUNC_map_update_elem 2 - -static void *(*bpf_map_lookup_elem)(void *map, void *key) = - (void *) BPF_FUNC_map_lookup_elem; -static void *(*bpf_map_update_elem)(void *map, void *key, void *value, int flags) = - (void *) BPF_FUNC_map_update_elem; - -struct bpf_map_def { - unsigned int type; - unsigned int key_size; - unsigned int value_size; - unsigned int max_entries; -}; - -#define SEC(NAME) __attribute__((section(NAME), used)) -struct bpf_map_def SEC("maps") my_table = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(int), - .value_size = sizeof(int), - .max_entries = 1, -}; - -int this_is_a_global_val; - -SEC("func=sys_write") -int bpf_func__sys_write(void *ctx) -{ - int key = 0; - int value = 0; - - /* - * Incorrect relocation. Should not allow this program be - * loaded into kernel. - */ - bpf_map_update_elem(&this_is_a_global_val, &key, &value, 0); - return 0; -} -char _license[] SEC("license") = "GPL"; -int _version SEC("version") = LINUX_VERSION_CODE; diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c deleted file mode 100644 index 8beb46066034..000000000000 --- a/tools/perf/tests/bpf.c +++ /dev/null @@ -1,389 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <errno.h> -#include <stdio.h> -#include <stdlib.h> -#include <sys/epoll.h> -#include <sys/types.h> -#include <sys/stat.h> -#include <fcntl.h> -#include <util/record.h> -#include <util/util.h> -#include <util/bpf-loader.h> -#include <util/evlist.h> -#include <linux/filter.h> -#include <linux/kernel.h> -#include <linux/string.h> -#include <api/fs/fs.h> -#include <perf/mmap.h> -#include "tests.h" -#include "llvm.h" -#include "debug.h" -#include "parse-events.h" -#include "util/mmap.h" -#define NR_ITERS 111 -#define PERF_TEST_BPF_PATH "/sys/fs/bpf/perf_test" - -#if defined(HAVE_LIBBPF_SUPPORT) && defined(HAVE_LIBTRACEEVENT) -#include <linux/bpf.h> -#include <bpf/bpf.h> - -static int epoll_pwait_loop(void) -{ - int i; - - /* Should fail NR_ITERS times */ - for (i = 0; i < NR_ITERS; i++) - epoll_pwait(-(i + 1), NULL, 0, 0, NULL); - return 0; -} - -#ifdef HAVE_BPF_PROLOGUE - -static int llseek_loop(void) -{ - int fds[2], i; - - fds[0] = open("/dev/null", O_RDONLY); - fds[1] = open("/dev/null", O_RDWR); - - if (fds[0] < 0 || fds[1] < 0) - return -1; - - for (i = 0; i < NR_ITERS; i++) { - lseek(fds[i % 2], i, (i / 2) % 2 ? SEEK_CUR : SEEK_SET); - lseek(fds[(i + 1) % 2], i, (i / 2) % 2 ? SEEK_CUR : SEEK_SET); - } - close(fds[0]); - close(fds[1]); - return 0; -} - -#endif - -static struct { - enum test_llvm__testcase prog_id; - const char *name; - const char *msg_compile_fail; - const char *msg_load_fail; - int (*target_func)(void); - int expect_result; - bool pin; -} bpf_testcase_table[] = { - { - .prog_id = LLVM_TESTCASE_BASE, - .name = "[basic_bpf_test]", - .msg_compile_fail = "fix 'perf test LLVM' first", - .msg_load_fail = "load bpf object failed", - .target_func = &epoll_pwait_loop, - .expect_result = (NR_ITERS + 1) / 2, - }, - { - .prog_id = LLVM_TESTCASE_BASE, - .name = "[bpf_pinning]", - .msg_compile_fail = "fix kbuild first", - .msg_load_fail = "check your vmlinux setting?", - .target_func = &epoll_pwait_loop, - .expect_result = (NR_ITERS + 1) / 2, - .pin = true, - }, -#ifdef HAVE_BPF_PROLOGUE - { - .prog_id = LLVM_TESTCASE_BPF_PROLOGUE, - .name = "[bpf_prologue_test]", - .msg_compile_fail = "fix kbuild first", - .msg_load_fail = "check your vmlinux setting?", - .target_func = &llseek_loop, - .expect_result = (NR_ITERS + 1) / 4, - }, -#endif -}; - -static int do_test(struct bpf_object *obj, int (*func)(void), - int expect) -{ - struct record_opts opts = { - .target = { - .uid = UINT_MAX, - .uses_mmap = true, - }, - .freq = 0, - .mmap_pages = 256, - .default_interval = 1, - }; - - char pid[16]; - char sbuf[STRERR_BUFSIZE]; - struct evlist *evlist; - int i, ret = TEST_FAIL, err = 0, count = 0; - - struct parse_events_state parse_state; - struct parse_events_error parse_error; - - parse_events_error__init(&parse_error); - bzero(&parse_state, sizeof(parse_state)); - parse_state.error = &parse_error; - INIT_LIST_HEAD(&parse_state.list); - - err = parse_events_load_bpf_obj(&parse_state, &parse_state.list, obj, NULL); - parse_events_error__exit(&parse_error); - if (err == -ENODATA) { - pr_debug("Failed to add events selected by BPF, debuginfo package not installed\n"); - return TEST_SKIP; - } - if (err || list_empty(&parse_state.list)) { - pr_debug("Failed to add events selected by BPF\n"); - return TEST_FAIL; - } - - snprintf(pid, sizeof(pid), "%d", getpid()); - pid[sizeof(pid) - 1] = '\0'; - opts.target.tid = opts.target.pid = pid; - - /* Instead of evlist__new_default, don't add default events */ - evlist = evlist__new(); - if (!evlist) { - pr_debug("Not enough memory to create evlist\n"); - return TEST_FAIL; - } - - err = evlist__create_maps(evlist, &opts.target); - if (err < 0) { - pr_debug("Not enough memory to create thread/cpu maps\n"); - goto out_delete_evlist; - } - - evlist__splice_list_tail(evlist, &parse_state.list); - - evlist__config(evlist, &opts, NULL); - - err = evlist__open(evlist); - if (err < 0) { - pr_debug("perf_evlist__open: %s\n", - str_error_r(errno, sbuf, sizeof(sbuf))); - goto out_delete_evlist; - } - - err = evlist__mmap(evlist, opts.mmap_pages); - if (err < 0) { - pr_debug("evlist__mmap: %s\n", - str_error_r(errno, sbuf, sizeof(sbuf))); - goto out_delete_evlist; - } - - evlist__enable(evlist); - (*func)(); - evlist__disable(evlist); - - for (i = 0; i < evlist->core.nr_mmaps; i++) { - union perf_event *event; - struct mmap *md; - - md = &evlist->mmap[i]; - if (perf_mmap__read_init(&md->core) < 0) - continue; - - while ((event = perf_mmap__read_event(&md->core)) != NULL) { - const u32 type = event->header.type; - - if (type == PERF_RECORD_SAMPLE) - count ++; - } - perf_mmap__read_done(&md->core); - } - - if (count != expect * evlist->core.nr_entries) { - pr_debug("BPF filter result incorrect, expected %d, got %d samples\n", expect * evlist->core.nr_entries, count); - goto out_delete_evlist; - } - - ret = TEST_OK; - -out_delete_evlist: - evlist__delete(evlist); - return ret; -} - -static struct bpf_object * -prepare_bpf(void *obj_buf, size_t obj_buf_sz, const char *name) -{ - struct bpf_object *obj; - - obj = bpf__prepare_load_buffer(obj_buf, obj_buf_sz, name); - if (IS_ERR(obj)) { - pr_debug("Compile BPF program failed.\n"); - return NULL; - } - return obj; -} - -static int __test__bpf(int idx) -{ - int ret; - void *obj_buf; - size_t obj_buf_sz; - struct bpf_object *obj; - - ret = test_llvm__fetch_bpf_obj(&obj_buf, &obj_buf_sz, - bpf_testcase_table[idx].prog_id, - false, NULL); - if (ret != TEST_OK || !obj_buf || !obj_buf_sz) { - pr_debug("Unable to get BPF object, %s\n", - bpf_testcase_table[idx].msg_compile_fail); - if ((idx == 0) || (ret == TEST_SKIP)) - return TEST_SKIP; - else - return TEST_FAIL; - } - - obj = prepare_bpf(obj_buf, obj_buf_sz, - bpf_testcase_table[idx].name); - if ((!!bpf_testcase_table[idx].target_func) != (!!obj)) { - if (!obj) - pr_debug("Fail to load BPF object: %s\n", - bpf_testcase_table[idx].msg_load_fail); - else - pr_debug("Success unexpectedly: %s\n", - bpf_testcase_table[idx].msg_load_fail); - ret = TEST_FAIL; - goto out; - } - - if (obj) { - ret = do_test(obj, - bpf_testcase_table[idx].target_func, - bpf_testcase_table[idx].expect_result); - if (ret != TEST_OK) - goto out; - if (bpf_testcase_table[idx].pin) { - int err; - - if (!bpf_fs__mount()) { - pr_debug("BPF filesystem not mounted\n"); - ret = TEST_FAIL; - goto out; - } - err = mkdir(PERF_TEST_BPF_PATH, 0777); - if (err && errno != EEXIST) { - pr_debug("Failed to make perf_test dir: %s\n", - strerror(errno)); - ret = TEST_FAIL; - goto out; - } - if (bpf_object__pin(obj, PERF_TEST_BPF_PATH)) - ret = TEST_FAIL; - if (rm_rf(PERF_TEST_BPF_PATH)) - ret = TEST_FAIL; - } - } - -out: - free(obj_buf); - bpf__clear(); - return ret; -} - -static int check_env(void) -{ - LIBBPF_OPTS(bpf_prog_load_opts, opts); - int err; - char license[] = "GPL"; - - struct bpf_insn insns[] = { - BPF_MOV64_IMM(BPF_REG_0, 1), - BPF_EXIT_INSN(), - }; - - err = fetch_kernel_version(&opts.kern_version, NULL, 0); - if (err) { - pr_debug("Unable to get kernel version\n"); - return err; - } - err = bpf_prog_load(BPF_PROG_TYPE_KPROBE, NULL, license, insns, - ARRAY_SIZE(insns), &opts); - if (err < 0) { - pr_err("Missing basic BPF support, skip this test: %s\n", - strerror(errno)); - return err; - } - close(err); - - return 0; -} - -static int test__bpf(int i) -{ - int err; - - if (i < 0 || i >= (int)ARRAY_SIZE(bpf_testcase_table)) - return TEST_FAIL; - - if (geteuid() != 0) { - pr_debug("Only root can run BPF test\n"); - return TEST_SKIP; - } - - if (check_env()) - return TEST_SKIP; - - err = __test__bpf(i); - return err; -} -#endif - -static int test__basic_bpf_test(struct test_suite *test __maybe_unused, - int subtest __maybe_unused) -{ -#if defined(HAVE_LIBBPF_SUPPORT) && defined(HAVE_LIBTRACEEVENT) - return test__bpf(0); -#else - pr_debug("Skip BPF test because BPF or libtraceevent support is not compiled\n"); - return TEST_SKIP; -#endif -} - -static int test__bpf_pinning(struct test_suite *test __maybe_unused, - int subtest __maybe_unused) -{ -#if defined(HAVE_LIBBPF_SUPPORT) && defined(HAVE_LIBTRACEEVENT) - return test__bpf(1); -#else - pr_debug("Skip BPF test because BPF or libtraceevent support is not compiled\n"); - return TEST_SKIP; -#endif -} - -static int test__bpf_prologue_test(struct test_suite *test __maybe_unused, - int subtest __maybe_unused) -{ -#if defined(HAVE_LIBBPF_SUPPORT) && defined(HAVE_BPF_PROLOGUE) && defined(HAVE_LIBTRACEEVENT) - return test__bpf(2); -#else - pr_debug("Skip BPF test because BPF or libtraceevent support is not compiled\n"); - return TEST_SKIP; -#endif -} - - -static struct test_case bpf_tests[] = { -#if defined(HAVE_LIBBPF_SUPPORT) && defined(HAVE_LIBTRACEEVENT) - TEST_CASE("Basic BPF filtering", basic_bpf_test), - TEST_CASE_REASON("BPF pinning", bpf_pinning, - "clang isn't installed or environment missing BPF support"), -#ifdef HAVE_BPF_PROLOGUE - TEST_CASE_REASON("BPF prologue generation", bpf_prologue_test, - "clang/debuginfo isn't installed or environment missing BPF support"), -#else - TEST_CASE_REASON("BPF prologue generation", bpf_prologue_test, "not compiled in"), -#endif -#else - TEST_CASE_REASON("Basic BPF filtering", basic_bpf_test, "not compiled in or missing libtraceevent support"), - TEST_CASE_REASON("BPF pinning", bpf_pinning, "not compiled in or missing libtraceevent support"), - TEST_CASE_REASON("BPF prologue generation", bpf_prologue_test, "not compiled in or missing libtraceevent support"), -#endif - { .name = NULL, } -}; - -struct test_suite suite__bpf = { - .desc = "BPF filter", - .test_cases = bpf_tests, -}; diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index 1f6557ce3b0a..0ad18cf6dd22 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -33,9 +33,18 @@ static bool dont_fork; const char *dso_to_test; -struct test_suite *__weak arch_tests[] = { +/* + * List of architecture specific tests. Not a weak symbol as the array length is + * dependent on the initialization, as such GCC with LTO complains of + * conflicting definitions with a weak symbol. + */ +#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__) || defined(__powerpc64__) +extern struct test_suite *arch_tests[]; +#else +static struct test_suite *arch_tests[] = { NULL, }; +#endif static struct test_suite *generic_tests[] = { &suite__vmlinux_matches_kallsyms, @@ -83,9 +92,7 @@ static struct test_suite *generic_tests[] = { &suite__fdarray__add, &suite__kmod_path__parse, &suite__thread_map, - &suite__llvm, &suite__session_topology, - &suite__bpf, &suite__thread_map_synthesize, &suite__thread_map_remove, &suite__cpu_map, @@ -99,7 +106,6 @@ static struct test_suite *generic_tests[] = { &suite__is_printable_array, &suite__bitmap_print, &suite__perf_hooks, - &suite__clang, &suite__unit_number__scnprint, &suite__mem2node, &suite__time_utils, diff --git a/tools/perf/tests/clang.c b/tools/perf/tests/clang.c deleted file mode 100644 index a7111005d5b9..000000000000 --- a/tools/perf/tests/clang.c +++ /dev/null @@ -1,32 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include "tests.h" -#include "c++/clang-c.h" -#include <linux/kernel.h> - -#ifndef HAVE_LIBCLANGLLVM_SUPPORT -static int test__clang_to_IR(struct test_suite *test __maybe_unused, - int subtest __maybe_unused) -{ - return TEST_SKIP; -} - -static int test__clang_to_obj(struct test_suite *test __maybe_unused, - int subtest __maybe_unused) -{ - return TEST_SKIP; -} -#endif - -static struct test_case clang_tests[] = { - TEST_CASE_REASON("builtin clang compile C source to IR", clang_to_IR, - "not compiled in"), - TEST_CASE_REASON("builtin clang compile C source to ELF object", - clang_to_obj, - "not compiled in"), - { .name = NULL, } -}; - -struct test_suite suite__clang = { - .desc = "builtin clang support", - .test_cases = clang_tests, -}; diff --git a/tools/perf/tests/config-fragments/README b/tools/perf/tests/config-fragments/README new file mode 100644 index 000000000000..fe7de5d93674 --- /dev/null +++ b/tools/perf/tests/config-fragments/README @@ -0,0 +1,7 @@ +This folder is for kernel config fragments that can be merged with +defconfig to give full test coverage of a perf test run. This is only +an optimistic set as some features require hardware support in order to +pass and not skip. + +'config' is shared across all platforms, and for arch specific files, +the file name should match that used in the ARCH=... make option. diff --git a/tools/perf/tests/config-fragments/arm64 b/tools/perf/tests/config-fragments/arm64 new file mode 100644 index 000000000000..64c4ab17cd58 --- /dev/null +++ b/tools/perf/tests/config-fragments/arm64 @@ -0,0 +1 @@ +CONFIG_CORESIGHT_SOURCE_ETM4X=y diff --git a/tools/perf/tests/config-fragments/config b/tools/perf/tests/config-fragments/config new file mode 100644 index 000000000000..c340b3195fca --- /dev/null +++ b/tools/perf/tests/config-fragments/config @@ -0,0 +1,11 @@ +CONFIG_TRACEPOINTS=y +CONFIG_STACKTRACE=y +CONFIG_NOP_TRACER=y +CONFIG_RING_BUFFER=y +CONFIG_EVENT_TRACING=y +CONFIG_CONTEXT_SWITCH_TRACER=y +CONFIG_TRACING=y +CONFIG_GENERIC_TRACER=y +CONFIG_FTRACE=y +CONFIG_FTRACE_SYSCALLS=y +CONFIG_BRANCH_PROFILE_NONE=y diff --git a/tools/perf/tests/dlfilter-test.c b/tools/perf/tests/dlfilter-test.c index 086fd2179e41..da3a9b50b1b1 100644 --- a/tools/perf/tests/dlfilter-test.c +++ b/tools/perf/tests/dlfilter-test.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* * Test dlfilter C API. A perf.data file is synthesized and then processed - * by perf script with a dlfilter named dlfilter-test-api-v0.so. Also a C file + * by perf script with dlfilters named dlfilter-test-api-v*.so. Also a C file * is compiled to provide a dso to match the synthesized perf.data file. */ @@ -37,6 +37,8 @@ #define MAP_START 0x400000 +#define DLFILTER_TEST_NAME_MAX 128 + struct test_data { struct perf_tool tool; struct machine *machine; @@ -45,6 +47,8 @@ struct test_data { u64 bar; u64 ip; u64 addr; + char name[DLFILTER_TEST_NAME_MAX]; + char desc[DLFILTER_TEST_NAME_MAX]; char perf[PATH_MAX]; char perf_data_file_name[PATH_MAX]; char c_file_name[PATH_MAX]; @@ -215,7 +219,7 @@ static int write_prog(char *file_name) return err ? -1 : 0; } -static int get_dlfilters_path(char *buf, size_t sz) +static int get_dlfilters_path(const char *name, char *buf, size_t sz) { char perf[PATH_MAX]; char path[PATH_MAX]; @@ -224,12 +228,12 @@ static int get_dlfilters_path(char *buf, size_t sz) perf_exe(perf, sizeof(perf)); perf_path = dirname(perf); - snprintf(path, sizeof(path), "%s/dlfilters/dlfilter-test-api-v0.so", perf_path); + snprintf(path, sizeof(path), "%s/dlfilters/%s", perf_path, name); if (access(path, R_OK)) { exec_path = get_argv_exec_path(); if (!exec_path) return -1; - snprintf(path, sizeof(path), "%s/dlfilters/dlfilter-test-api-v0.so", exec_path); + snprintf(path, sizeof(path), "%s/dlfilters/%s", exec_path, name); free(exec_path); if (access(path, R_OK)) return -1; @@ -244,9 +248,9 @@ static int check_filter_desc(struct test_data *td) char *desc = NULL; int ret; - if (get_filter_desc(td->dlfilters, "dlfilter-test-api-v0.so", &desc, &long_desc) && + if (get_filter_desc(td->dlfilters, td->name, &desc, &long_desc) && long_desc && !strcmp(long_desc, "Filter used by the 'dlfilter C API' perf test") && - desc && !strcmp(desc, "dlfilter to test v0 C API")) + desc && !strcmp(desc, td->desc)) ret = 0; else ret = -1; @@ -284,7 +288,7 @@ static int get_ip_addr(struct test_data *td) static int do_run_perf_script(struct test_data *td, int do_early) { return system_cmd("%s script -i %s " - "--dlfilter %s/dlfilter-test-api-v0.so " + "--dlfilter %s/%s " "--dlarg first " "--dlarg %d " "--dlarg %" PRIu64 " " @@ -292,7 +296,7 @@ static int do_run_perf_script(struct test_data *td, int do_early) "--dlarg %d " "--dlarg last", td->perf, td->perf_data_file_name, td->dlfilters, - verbose, td->ip, td->addr, do_early); + td->name, verbose, td->ip, td->addr, do_early); } static int run_perf_script(struct test_data *td) @@ -321,7 +325,7 @@ static int test__dlfilter_test(struct test_data *td) u64 id = 99; int err; - if (get_dlfilters_path(td->dlfilters, PATH_MAX)) + if (get_dlfilters_path(td->name, td->dlfilters, PATH_MAX)) return test_result("dlfilters not found", TEST_SKIP); if (check_filter_desc(td)) @@ -399,14 +403,18 @@ static void test_data__free(struct test_data *td) } } -static int test__dlfilter(struct test_suite *test __maybe_unused, int subtest __maybe_unused) +static int test__dlfilter_ver(int ver) { struct test_data td = {.fd = -1}; int pid = getpid(); int err; + pr_debug("\n-- Testing version %d API --\n", ver); + perf_exe(td.perf, sizeof(td.perf)); + snprintf(td.name, sizeof(td.name), "dlfilter-test-api-v%d.so", ver); + snprintf(td.desc, sizeof(td.desc), "dlfilter to test v%d C API", ver); snprintf(td.perf_data_file_name, PATH_MAX, "/tmp/dlfilter-test-%u-perf-data", pid); snprintf(td.c_file_name, PATH_MAX, "/tmp/dlfilter-test-%u-prog.c", pid); snprintf(td.prog_file_name, PATH_MAX, "/tmp/dlfilter-test-%u-prog", pid); @@ -416,4 +424,14 @@ static int test__dlfilter(struct test_suite *test __maybe_unused, int subtest __ return err; } +static int test__dlfilter(struct test_suite *test __maybe_unused, int subtest __maybe_unused) +{ + int err = test__dlfilter_ver(0); + + if (err) + return err; + /* No test for version 1 */ + return test__dlfilter_ver(2); +} + DEFINE_SUITE("dlfilter C API", dlfilter); diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c index c1c3fcbc2753..81229fa4f1e9 100644 --- a/tools/perf/tests/expr.c +++ b/tools/perf/tests/expr.c @@ -70,7 +70,7 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u { struct expr_id_data *val_ptr; const char *p; - double val, num_cpus, num_cores, num_dies, num_packages; + double val, num_cpus_online, num_cpus, num_cores, num_dies, num_packages; int ret; struct expr_parse_ctx *ctx; bool is_intel = false; @@ -227,7 +227,10 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u /* Test toplogy constants appear well ordered. */ expr__ctx_clear(ctx); + TEST_ASSERT_VAL("#num_cpus_online", + expr__parse(&num_cpus_online, ctx, "#num_cpus_online") == 0); TEST_ASSERT_VAL("#num_cpus", expr__parse(&num_cpus, ctx, "#num_cpus") == 0); + TEST_ASSERT_VAL("#num_cpus >= #num_cpus_online", num_cpus >= num_cpus_online); TEST_ASSERT_VAL("#num_cores", expr__parse(&num_cores, ctx, "#num_cores") == 0); TEST_ASSERT_VAL("#num_cpus >= #num_cores", num_cpus >= num_cores); TEST_ASSERT_VAL("#num_dies", expr__parse(&num_dies, ctx, "#num_dies") == 0); diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c deleted file mode 100644 index 0bc25a56cfef..000000000000 --- a/tools/perf/tests/llvm.c +++ /dev/null @@ -1,219 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <stdio.h> -#include <stdlib.h> -#include <string.h> -#include "tests.h" -#include "debug.h" - -#ifdef HAVE_LIBBPF_SUPPORT -#include <bpf/libbpf.h> -#include <util/llvm-utils.h> -#include "llvm.h" -static int test__bpf_parsing(void *obj_buf, size_t obj_buf_sz) -{ - struct bpf_object *obj; - - obj = bpf_object__open_mem(obj_buf, obj_buf_sz, NULL); - if (libbpf_get_error(obj)) - return TEST_FAIL; - bpf_object__close(obj); - return TEST_OK; -} - -static struct { - const char *source; - const char *desc; - bool should_load_fail; -} bpf_source_table[__LLVM_TESTCASE_MAX] = { - [LLVM_TESTCASE_BASE] = { - .source = test_llvm__bpf_base_prog, - .desc = "Basic BPF llvm compile", - }, - [LLVM_TESTCASE_KBUILD] = { - .source = test_llvm__bpf_test_kbuild_prog, - .desc = "kbuild searching", - }, - [LLVM_TESTCASE_BPF_PROLOGUE] = { - .source = test_llvm__bpf_test_prologue_prog, - .desc = "Compile source for BPF prologue generation", - }, - [LLVM_TESTCASE_BPF_RELOCATION] = { - .source = test_llvm__bpf_test_relocation, - .desc = "Compile source for BPF relocation", - .should_load_fail = true, - }, -}; - -int -test_llvm__fetch_bpf_obj(void **p_obj_buf, - size_t *p_obj_buf_sz, - enum test_llvm__testcase idx, - bool force, - bool *should_load_fail) -{ - const char *source; - const char *desc; - const char *tmpl_old, *clang_opt_old; - char *tmpl_new = NULL, *clang_opt_new = NULL; - int err, old_verbose, ret = TEST_FAIL; - - if (idx >= __LLVM_TESTCASE_MAX) - return TEST_FAIL; - - source = bpf_source_table[idx].source; - desc = bpf_source_table[idx].desc; - if (should_load_fail) - *should_load_fail = bpf_source_table[idx].should_load_fail; - - /* - * Skip this test if user's .perfconfig doesn't set [llvm] section - * and clang is not found in $PATH - */ - if (!force && (!llvm_param.user_set_param && - llvm__search_clang())) { - pr_debug("No clang, skip this test\n"); - return TEST_SKIP; - } - - /* - * llvm is verbosity when error. Suppress all error output if - * not 'perf test -v'. - */ - old_verbose = verbose; - if (verbose == 0) - verbose = -1; - - *p_obj_buf = NULL; - *p_obj_buf_sz = 0; - - if (!llvm_param.clang_bpf_cmd_template) - goto out; - - if (!llvm_param.clang_opt) - llvm_param.clang_opt = strdup(""); - - err = asprintf(&tmpl_new, "echo '%s' | %s%s", source, - llvm_param.clang_bpf_cmd_template, - old_verbose ? "" : " 2>/dev/null"); - if (err < 0) - goto out; - err = asprintf(&clang_opt_new, "-xc %s", llvm_param.clang_opt); - if (err < 0) - goto out; - - tmpl_old = llvm_param.clang_bpf_cmd_template; - llvm_param.clang_bpf_cmd_template = tmpl_new; - clang_opt_old = llvm_param.clang_opt; - llvm_param.clang_opt = clang_opt_new; - - err = llvm__compile_bpf("-", p_obj_buf, p_obj_buf_sz); - - llvm_param.clang_bpf_cmd_template = tmpl_old; - llvm_param.clang_opt = clang_opt_old; - - verbose = old_verbose; - if (err) - goto out; - - ret = TEST_OK; -out: - free(tmpl_new); - free(clang_opt_new); - if (ret != TEST_OK) - pr_debug("Failed to compile test case: '%s'\n", desc); - return ret; -} - -static int test__llvm(int subtest) -{ - int ret; - void *obj_buf = NULL; - size_t obj_buf_sz = 0; - bool should_load_fail = false; - - if ((subtest < 0) || (subtest >= __LLVM_TESTCASE_MAX)) - return TEST_FAIL; - - ret = test_llvm__fetch_bpf_obj(&obj_buf, &obj_buf_sz, - subtest, false, &should_load_fail); - - if (ret == TEST_OK && !should_load_fail) { - ret = test__bpf_parsing(obj_buf, obj_buf_sz); - if (ret != TEST_OK) { - pr_debug("Failed to parse test case '%s'\n", - bpf_source_table[subtest].desc); - } - } - free(obj_buf); - - return ret; -} -#endif //HAVE_LIBBPF_SUPPORT - -static int test__llvm__bpf_base_prog(struct test_suite *test __maybe_unused, - int subtest __maybe_unused) -{ -#ifdef HAVE_LIBBPF_SUPPORT - return test__llvm(LLVM_TESTCASE_BASE); -#else - pr_debug("Skip LLVM test because BPF support is not compiled\n"); - return TEST_SKIP; -#endif -} - -static int test__llvm__bpf_test_kbuild_prog(struct test_suite *test __maybe_unused, - int subtest __maybe_unused) -{ -#ifdef HAVE_LIBBPF_SUPPORT - return test__llvm(LLVM_TESTCASE_KBUILD); -#else - pr_debug("Skip LLVM test because BPF support is not compiled\n"); - return TEST_SKIP; -#endif -} - -static int test__llvm__bpf_test_prologue_prog(struct test_suite *test __maybe_unused, - int subtest __maybe_unused) -{ -#ifdef HAVE_LIBBPF_SUPPORT - return test__llvm(LLVM_TESTCASE_BPF_PROLOGUE); -#else - pr_debug("Skip LLVM test because BPF support is not compiled\n"); - return TEST_SKIP; -#endif -} - -static int test__llvm__bpf_test_relocation(struct test_suite *test __maybe_unused, - int subtest __maybe_unused) -{ -#ifdef HAVE_LIBBPF_SUPPORT - return test__llvm(LLVM_TESTCASE_BPF_RELOCATION); -#else - pr_debug("Skip LLVM test because BPF support is not compiled\n"); - return TEST_SKIP; -#endif -} - - -static struct test_case llvm_tests[] = { -#ifdef HAVE_LIBBPF_SUPPORT - TEST_CASE("Basic BPF llvm compile", llvm__bpf_base_prog), - TEST_CASE("kbuild searching", llvm__bpf_test_kbuild_prog), - TEST_CASE("Compile source for BPF prologue generation", - llvm__bpf_test_prologue_prog), - TEST_CASE("Compile source for BPF relocation", llvm__bpf_test_relocation), -#else - TEST_CASE_REASON("Basic BPF llvm compile", llvm__bpf_base_prog, "not compiled in"), - TEST_CASE_REASON("kbuild searching", llvm__bpf_test_kbuild_prog, "not compiled in"), - TEST_CASE_REASON("Compile source for BPF prologue generation", - llvm__bpf_test_prologue_prog, "not compiled in"), - TEST_CASE_REASON("Compile source for BPF relocation", - llvm__bpf_test_relocation, "not compiled in"), -#endif - { .name = NULL, } -}; - -struct test_suite suite__llvm = { - .desc = "LLVM search and compile", - .test_cases = llvm_tests, -}; diff --git a/tools/perf/tests/llvm.h b/tools/perf/tests/llvm.h deleted file mode 100644 index f68b0d9b8ae2..000000000000 --- a/tools/perf/tests/llvm.h +++ /dev/null @@ -1,31 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef PERF_TEST_LLVM_H -#define PERF_TEST_LLVM_H - -#ifdef __cplusplus -extern "C" { -#endif - -#include <stddef.h> /* for size_t */ -#include <stdbool.h> /* for bool */ - -extern const char test_llvm__bpf_base_prog[]; -extern const char test_llvm__bpf_test_kbuild_prog[]; -extern const char test_llvm__bpf_test_prologue_prog[]; -extern const char test_llvm__bpf_test_relocation[]; - -enum test_llvm__testcase { - LLVM_TESTCASE_BASE, - LLVM_TESTCASE_KBUILD, - LLVM_TESTCASE_BPF_PROLOGUE, - LLVM_TESTCASE_BPF_RELOCATION, - __LLVM_TESTCASE_MAX, -}; - -int test_llvm__fetch_bpf_obj(void **p_obj_buf, size_t *p_obj_buf_sz, - enum test_llvm__testcase index, bool force, - bool *should_load_fail); -#ifdef __cplusplus -} -#endif -#endif diff --git a/tools/perf/tests/make b/tools/perf/tests/make index 58cf96d762d0..ea4c341f5af1 100644 --- a/tools/perf/tests/make +++ b/tools/perf/tests/make @@ -95,7 +95,6 @@ make_with_babeltrace:= LIBBABELTRACE=1 make_with_coresight := CORESIGHT=1 make_no_sdt := NO_SDT=1 make_no_syscall_tbl := NO_SYSCALL_TABLE=1 -make_with_clangllvm := LIBCLANGLLVM=1 make_no_libpfm4 := NO_LIBPFM4=1 make_with_gtk2 := GTK2=1 make_refcnt_check := EXTRA_CFLAGS="-DREFCNT_CHECKING=1" diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c index e68ca6229756..886a13a77a16 100644 --- a/tools/perf/tests/mmap-basic.c +++ b/tools/perf/tests/mmap-basic.c @@ -284,7 +284,8 @@ static struct test_case tests__basic_mmap[] = { "permissions"), TEST_CASE_REASON("User space counter reading of instructions", mmap_user_read_instr, -#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__) +#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__) || \ + (defined(__riscv) && __riscv_xlen == 64) "permissions" #else "unsupported" @@ -292,7 +293,8 @@ static struct test_case tests__basic_mmap[] = { ), TEST_CASE_REASON("User space counter reading of cycles", mmap_user_read_cycles, -#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__) +#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__) || \ + (defined(__riscv) && __riscv_xlen == 64) "permissions" #else "unsupported" diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index 658fb9599d95..d47f1f871164 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -2170,7 +2170,7 @@ static const struct evlist_test test__events[] = { static const struct evlist_test test__events_pmu[] = { { - .name = "cpu/config=10,config1,config2=3,period=1000/u", + .name = "cpu/config=10,config1=1,config2=3,period=1000/u", .valid = test__pmu_cpu_valid, .check = test__checkevent_pmu, /* 0 */ @@ -2472,7 +2472,7 @@ static int test_term(const struct terms_test *t) INIT_LIST_HEAD(&terms); - ret = parse_events_terms(&terms, t->str); + ret = parse_events_terms(&terms, t->str, /*input=*/ NULL); if (ret) { pr_debug("failed to parse terms '%s', err %d\n", t->str , ret); diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c index 64383fc34ef1..f5321fbdee79 100644 --- a/tools/perf/tests/pmu-events.c +++ b/tools/perf/tests/pmu-events.c @@ -44,6 +44,7 @@ struct perf_pmu_test_pmu { static const struct perf_pmu_test_event bp_l1_btb_correct = { .event = { + .pmu = "default_core", .name = "bp_l1_btb_correct", .event = "event=0x8a", .desc = "L1 BTB Correction", @@ -55,6 +56,7 @@ static const struct perf_pmu_test_event bp_l1_btb_correct = { static const struct perf_pmu_test_event bp_l2_btb_correct = { .event = { + .pmu = "default_core", .name = "bp_l2_btb_correct", .event = "event=0x8b", .desc = "L2 BTB Correction", @@ -66,6 +68,7 @@ static const struct perf_pmu_test_event bp_l2_btb_correct = { static const struct perf_pmu_test_event segment_reg_loads_any = { .event = { + .pmu = "default_core", .name = "segment_reg_loads.any", .event = "event=0x6,period=200000,umask=0x80", .desc = "Number of segment register loads", @@ -77,6 +80,7 @@ static const struct perf_pmu_test_event segment_reg_loads_any = { static const struct perf_pmu_test_event dispatch_blocked_any = { .event = { + .pmu = "default_core", .name = "dispatch_blocked.any", .event = "event=0x9,period=200000,umask=0x20", .desc = "Memory cluster signals to block micro-op dispatch for any reason", @@ -88,6 +92,7 @@ static const struct perf_pmu_test_event dispatch_blocked_any = { static const struct perf_pmu_test_event eist_trans = { .event = { + .pmu = "default_core", .name = "eist_trans", .event = "event=0x3a,period=200000,umask=0x0", .desc = "Number of Enhanced Intel SpeedStep(R) Technology (EIST) transitions", @@ -99,6 +104,7 @@ static const struct perf_pmu_test_event eist_trans = { static const struct perf_pmu_test_event l3_cache_rd = { .event = { + .pmu = "default_core", .name = "l3_cache_rd", .event = "event=0x40", .desc = "L3 cache access, read", @@ -123,7 +129,7 @@ static const struct perf_pmu_test_event uncore_hisi_ddrc_flux_wcmd = { .event = { .name = "uncore_hisi_ddrc.flux_wcmd", .event = "event=0x2", - .desc = "DDRC write commands. Unit: hisi_sccl,ddrc ", + .desc = "DDRC write commands", .topic = "uncore", .long_desc = "DDRC write commands", .pmu = "hisi_sccl,ddrc", @@ -137,7 +143,7 @@ static const struct perf_pmu_test_event unc_cbo_xsnp_response_miss_eviction = { .event = { .name = "unc_cbo_xsnp_response.miss_eviction", .event = "event=0x22,umask=0x81", - .desc = "A cross-core snoop resulted from L3 Eviction which misses in some processor core. Unit: uncore_cbox ", + .desc = "A cross-core snoop resulted from L3 Eviction which misses in some processor core", .topic = "uncore", .long_desc = "A cross-core snoop resulted from L3 Eviction which misses in some processor core", .pmu = "uncore_cbox", @@ -151,7 +157,7 @@ static const struct perf_pmu_test_event uncore_hyphen = { .event = { .name = "event-hyphen", .event = "event=0xe0,umask=0x00", - .desc = "UNC_CBO_HYPHEN. Unit: uncore_cbox ", + .desc = "UNC_CBO_HYPHEN", .topic = "uncore", .long_desc = "UNC_CBO_HYPHEN", .pmu = "uncore_cbox", @@ -165,7 +171,7 @@ static const struct perf_pmu_test_event uncore_two_hyph = { .event = { .name = "event-two-hyph", .event = "event=0xc0,umask=0x00", - .desc = "UNC_CBO_TWO_HYPH. Unit: uncore_cbox ", + .desc = "UNC_CBO_TWO_HYPH", .topic = "uncore", .long_desc = "UNC_CBO_TWO_HYPH", .pmu = "uncore_cbox", @@ -179,7 +185,7 @@ static const struct perf_pmu_test_event uncore_hisi_l3c_rd_hit_cpipe = { .event = { .name = "uncore_hisi_l3c.rd_hit_cpipe", .event = "event=0x7", - .desc = "Total read hits. Unit: hisi_sccl,l3c ", + .desc = "Total read hits", .topic = "uncore", .long_desc = "Total read hits", .pmu = "hisi_sccl,l3c", @@ -193,7 +199,7 @@ static const struct perf_pmu_test_event uncore_imc_free_running_cache_miss = { .event = { .name = "uncore_imc_free_running.cache_miss", .event = "event=0x12", - .desc = "Total cache misses. Unit: uncore_imc_free_running ", + .desc = "Total cache misses", .topic = "uncore", .long_desc = "Total cache misses", .pmu = "uncore_imc_free_running", @@ -207,7 +213,7 @@ static const struct perf_pmu_test_event uncore_imc_cache_hits = { .event = { .name = "uncore_imc.cache_hits", .event = "event=0x34", - .desc = "Total cache hits. Unit: uncore_imc ", + .desc = "Total cache hits", .topic = "uncore", .long_desc = "Total cache hits", .pmu = "uncore_imc", @@ -232,13 +238,13 @@ static const struct perf_pmu_test_event sys_ddr_pmu_write_cycles = { .event = { .name = "sys_ddr_pmu.write_cycles", .event = "event=0x2b", - .desc = "ddr write-cycles event. Unit: uncore_sys_ddr_pmu ", + .desc = "ddr write-cycles event", .topic = "uncore", .pmu = "uncore_sys_ddr_pmu", .compat = "v8", }, .alias_str = "event=0x2b", - .alias_long_desc = "ddr write-cycles event. Unit: uncore_sys_ddr_pmu ", + .alias_long_desc = "ddr write-cycles event", .matching_pmu = "uncore_sys_ddr_pmu", }; @@ -246,13 +252,13 @@ static const struct perf_pmu_test_event sys_ccn_pmu_read_cycles = { .event = { .name = "sys_ccn_pmu.read_cycles", .event = "config=0x2c", - .desc = "ccn read-cycles event. Unit: uncore_sys_ccn_pmu ", + .desc = "ccn read-cycles event", .topic = "uncore", .pmu = "uncore_sys_ccn_pmu", .compat = "0x01", }, .alias_str = "config=0x2c", - .alias_long_desc = "ccn read-cycles event. Unit: uncore_sys_ccn_pmu ", + .alias_long_desc = "ccn read-cycles event", .matching_pmu = "uncore_sys_ccn_pmu", }; @@ -341,7 +347,7 @@ static int compare_pmu_events(const struct pmu_event *e1, const struct pmu_event return 0; } -static int compare_alias_to_test_event(struct perf_pmu_alias *alias, +static int compare_alias_to_test_event(struct pmu_event_info *alias, struct perf_pmu_test_event const *test_event, char const *pmu_name) { @@ -385,8 +391,8 @@ static int compare_alias_to_test_event(struct perf_pmu_alias *alias, return -1; } - - if (!is_same(alias->pmu_name, test_event->event.pmu)) { + if (!is_same(alias->pmu_name, test_event->event.pmu) && + !is_same(alias->pmu_name, "default_core")) { pr_debug("testing aliases PMU %s: mismatched pmu_name, %s vs %s\n", pmu_name, alias->pmu_name, test_event->event.pmu); return -1; @@ -403,7 +409,7 @@ static int test__pmu_event_table_core_callback(const struct pmu_event *pe, struct perf_pmu_test_event const **test_event_table; bool found = false; - if (pe->pmu) + if (strcmp(pe->pmu, "default_core")) test_event_table = &uncore_events[0]; else test_event_table = &core_events[0]; @@ -477,12 +483,14 @@ static int test__pmu_event_table(struct test_suite *test __maybe_unused, if (!table || !sys_event_table) return -1; - err = pmu_events_table_for_each_event(table, test__pmu_event_table_core_callback, + err = pmu_events_table__for_each_event(table, /*pmu=*/ NULL, + test__pmu_event_table_core_callback, &map_events); if (err) return err; - err = pmu_events_table_for_each_event(sys_event_table, test__pmu_event_table_sys_callback, + err = pmu_events_table__for_each_event(sys_event_table, /*pmu=*/ NULL, + test__pmu_event_table_sys_callback, &map_events); if (err) return err; @@ -496,26 +504,30 @@ static int test__pmu_event_table(struct test_suite *test __maybe_unused, return 0; } -static struct perf_pmu_alias *find_alias(const char *test_event, struct list_head *aliases) -{ - struct perf_pmu_alias *alias; +struct test_core_pmu_event_aliases_cb_args { + struct perf_pmu_test_event const *test_event; + int *count; +}; - list_for_each_entry(alias, aliases, list) - if (!strcmp(test_event, alias->name)) - return alias; +static int test_core_pmu_event_aliases_cb(void *state, struct pmu_event_info *alias) +{ + struct test_core_pmu_event_aliases_cb_args *args = state; - return NULL; + if (compare_alias_to_test_event(alias, args->test_event, alias->pmu->name)) + return -1; + (*args->count)++; + pr_debug2("testing aliases core PMU %s: matched event %s\n", + alias->pmu_name, alias->name); + return 0; } /* Verify aliases are as expected */ -static int __test_core_pmu_event_aliases(char *pmu_name, int *count) +static int __test_core_pmu_event_aliases(const char *pmu_name, int *count) { struct perf_pmu_test_event const **test_event_table; struct perf_pmu *pmu; - LIST_HEAD(aliases); int res = 0; const struct pmu_events_table *table = find_core_events_table("testarch", "testcpu"); - struct perf_pmu_alias *a, *tmp; if (!table) return -1; @@ -526,37 +538,40 @@ static int __test_core_pmu_event_aliases(char *pmu_name, int *count) if (!pmu) return -1; - pmu->name = pmu_name; - - pmu_add_cpu_aliases_table(&aliases, pmu, table); - + INIT_LIST_HEAD(&pmu->format); + INIT_LIST_HEAD(&pmu->aliases); + INIT_LIST_HEAD(&pmu->caps); + INIT_LIST_HEAD(&pmu->list); + pmu->name = strdup(pmu_name); + pmu->is_core = true; + + pmu->events_table = table; + pmu_add_cpu_aliases_table(pmu, table); + pmu->cpu_aliases_added = true; + pmu->sysfs_aliases_loaded = true; + + res = pmu_events_table__find_event(table, pmu, "bp_l1_btb_correct", NULL, NULL); + if (res != 0) { + pr_debug("Missing test event in test architecture"); + return res; + } for (; *test_event_table; test_event_table++) { - struct perf_pmu_test_event const *test_event = *test_event_table; - struct pmu_event const *event = &test_event->event; - struct perf_pmu_alias *alias = find_alias(event->name, &aliases); - - if (!alias) { - pr_debug("testing aliases core PMU %s: no alias, alias_table->name=%s\n", - pmu_name, event->name); - res = -1; - break; - } - - if (compare_alias_to_test_event(alias, test_event, pmu_name)) { - res = -1; - break; - } - - (*count)++; - pr_debug2("testing aliases core PMU %s: matched event %s\n", - pmu_name, alias->name); + struct perf_pmu_test_event test_event = **test_event_table; + struct pmu_event const *event = &test_event.event; + struct test_core_pmu_event_aliases_cb_args args = { + .test_event = &test_event, + .count = count, + }; + int err; + + test_event.event.pmu = pmu_name; + err = perf_pmu__find_event(pmu, event->name, &args, + test_core_pmu_event_aliases_cb); + if (err) + res = err; } + perf_pmu__delete(pmu); - list_for_each_entry_safe(a, tmp, &aliases, list) { - list_del(&a->list); - perf_pmu_free_alias(a); - } - free(pmu); return res; } @@ -566,20 +581,20 @@ static int __test_uncore_pmu_event_aliases(struct perf_pmu_test_pmu *test_pmu) struct perf_pmu_test_event const **table; struct perf_pmu *pmu = &test_pmu->pmu; const char *pmu_name = pmu->name; - struct perf_pmu_alias *a, *tmp, *alias; const struct pmu_events_table *events_table; - LIST_HEAD(aliases); int res = 0; events_table = find_core_events_table("testarch", "testcpu"); if (!events_table) return -1; - pmu_add_cpu_aliases_table(&aliases, pmu, events_table); - pmu_add_sys_aliases(&aliases, pmu); + pmu->events_table = events_table; + pmu_add_cpu_aliases_table(pmu, events_table); + pmu->cpu_aliases_added = true; + pmu->sysfs_aliases_loaded = true; + pmu_add_sys_aliases(pmu); /* Count how many aliases we generated */ - list_for_each_entry(alias, &aliases, list) - alias_count++; + alias_count = perf_pmu__num_events(pmu); /* Count how many aliases we expect from the known table */ for (table = &test_pmu->aliases[0]; *table; table++) @@ -588,33 +603,25 @@ static int __test_uncore_pmu_event_aliases(struct perf_pmu_test_pmu *test_pmu) if (alias_count != to_match_count) { pr_debug("testing aliases uncore PMU %s: mismatch expected aliases (%d) vs found (%d)\n", pmu_name, to_match_count, alias_count); - res = -1; - goto out; + return -1; } - list_for_each_entry(alias, &aliases, list) { - bool matched = false; - - for (table = &test_pmu->aliases[0]; *table; table++) { - struct perf_pmu_test_event const *test_event = *table; - struct pmu_event const *event = &test_event->event; - - if (!strcmp(event->name, alias->name)) { - if (compare_alias_to_test_event(alias, - test_event, - pmu_name)) { - continue; - } - matched = true; - matched_count++; - } - } - - if (matched == false) { + for (table = &test_pmu->aliases[0]; *table; table++) { + struct perf_pmu_test_event test_event = **table; + struct pmu_event const *event = &test_event.event; + int err; + struct test_core_pmu_event_aliases_cb_args args = { + .test_event = &test_event, + .count = &matched_count, + }; + + err = perf_pmu__find_event(pmu, event->name, &args, + test_core_pmu_event_aliases_cb); + if (err) { + res = err; pr_debug("testing aliases uncore PMU %s: could not match alias %s\n", - pmu_name, alias->name); - res = -1; - goto out; + pmu_name, event->name); + return -1; } } @@ -623,19 +630,13 @@ static int __test_uncore_pmu_event_aliases(struct perf_pmu_test_pmu *test_pmu) pmu_name, matched_count, alias_count); res = -1; } - -out: - list_for_each_entry_safe(a, tmp, &aliases, list) { - list_del(&a->list); - perf_pmu_free_alias(a); - } return res; } static struct perf_pmu_test_pmu test_pmus[] = { { .pmu = { - .name = (char *)"hisi_sccl1_ddrc2", + .name = "hisi_sccl1_ddrc2", .is_uncore = 1, }, .aliases = { @@ -644,7 +645,7 @@ static struct perf_pmu_test_pmu test_pmus[] = { }, { .pmu = { - .name = (char *)"uncore_cbox_0", + .name = "uncore_cbox_0", .is_uncore = 1, }, .aliases = { @@ -655,7 +656,7 @@ static struct perf_pmu_test_pmu test_pmus[] = { }, { .pmu = { - .name = (char *)"hisi_sccl3_l3c7", + .name = "hisi_sccl3_l3c7", .is_uncore = 1, }, .aliases = { @@ -664,7 +665,7 @@ static struct perf_pmu_test_pmu test_pmus[] = { }, { .pmu = { - .name = (char *)"uncore_imc_free_running_0", + .name = "uncore_imc_free_running_0", .is_uncore = 1, }, .aliases = { @@ -673,7 +674,7 @@ static struct perf_pmu_test_pmu test_pmus[] = { }, { .pmu = { - .name = (char *)"uncore_imc_0", + .name = "uncore_imc_0", .is_uncore = 1, }, .aliases = { @@ -682,9 +683,9 @@ static struct perf_pmu_test_pmu test_pmus[] = { }, { .pmu = { - .name = (char *)"uncore_sys_ddr_pmu0", + .name = "uncore_sys_ddr_pmu0", .is_uncore = 1, - .id = (char *)"v8", + .id = "v8", }, .aliases = { &sys_ddr_pmu_write_cycles, @@ -692,9 +693,9 @@ static struct perf_pmu_test_pmu test_pmus[] = { }, { .pmu = { - .name = (char *)"uncore_sys_ccn_pmu4", + .name = "uncore_sys_ccn_pmu4", .is_uncore = 1, - .id = (char *)"0x01", + .id = "0x01", }, .aliases = { &sys_ccn_pmu_read_cycles, @@ -732,8 +733,13 @@ static int test__aliases(struct test_suite *test __maybe_unused, } for (i = 0; i < ARRAY_SIZE(test_pmus); i++) { - int res = __test_uncore_pmu_event_aliases(&test_pmus[i]); + int res; + + INIT_LIST_HEAD(&test_pmus[i].pmu.format); + INIT_LIST_HEAD(&test_pmus[i].pmu.aliases); + INIT_LIST_HEAD(&test_pmus[i].pmu.caps); + res = __test_uncore_pmu_event_aliases(&test_pmus[i]); if (res) return res; } diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c index a4452639a3d4..eb60e5f66859 100644 --- a/tools/perf/tests/pmu.c +++ b/tools/perf/tests/pmu.c @@ -7,6 +7,7 @@ #include <stdio.h> #include <linux/kernel.h> #include <linux/limits.h> +#include <linux/zalloc.h> /* Simulated format definitions. */ static struct test_format { @@ -27,55 +28,55 @@ static struct test_format { /* Simulated users input. */ static struct parse_events_term test_terms[] = { { - .config = (char *) "krava01", + .config = "krava01", .val.num = 15, .type_val = PARSE_EVENTS__TERM_TYPE_NUM, .type_term = PARSE_EVENTS__TERM_TYPE_USER, }, { - .config = (char *) "krava02", + .config = "krava02", .val.num = 170, .type_val = PARSE_EVENTS__TERM_TYPE_NUM, .type_term = PARSE_EVENTS__TERM_TYPE_USER, }, { - .config = (char *) "krava03", + .config = "krava03", .val.num = 1, .type_val = PARSE_EVENTS__TERM_TYPE_NUM, .type_term = PARSE_EVENTS__TERM_TYPE_USER, }, { - .config = (char *) "krava11", + .config = "krava11", .val.num = 27, .type_val = PARSE_EVENTS__TERM_TYPE_NUM, .type_term = PARSE_EVENTS__TERM_TYPE_USER, }, { - .config = (char *) "krava12", + .config = "krava12", .val.num = 1, .type_val = PARSE_EVENTS__TERM_TYPE_NUM, .type_term = PARSE_EVENTS__TERM_TYPE_USER, }, { - .config = (char *) "krava13", + .config = "krava13", .val.num = 2, .type_val = PARSE_EVENTS__TERM_TYPE_NUM, .type_term = PARSE_EVENTS__TERM_TYPE_USER, }, { - .config = (char *) "krava21", + .config = "krava21", .val.num = 119, .type_val = PARSE_EVENTS__TERM_TYPE_NUM, .type_term = PARSE_EVENTS__TERM_TYPE_USER, }, { - .config = (char *) "krava22", + .config = "krava22", .val.num = 11, .type_val = PARSE_EVENTS__TERM_TYPE_NUM, .type_term = PARSE_EVENTS__TERM_TYPE_USER, }, { - .config = (char *) "krava23", + .config = "krava23", .val.num = 2, .type_val = PARSE_EVENTS__TERM_TYPE_NUM, .type_term = PARSE_EVENTS__TERM_TYPE_USER, @@ -141,48 +142,55 @@ static struct list_head *test_terms_list(void) static int test__pmu(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { char dir[PATH_MAX]; - char *format = test_format_dir_get(dir, sizeof(dir)); - LIST_HEAD(formats); + char *format; struct list_head *terms = test_terms_list(); + struct perf_event_attr attr; + struct perf_pmu *pmu; + int fd; int ret; - if (!format) - return -EINVAL; - - do { - struct perf_event_attr attr; - int fd; - - memset(&attr, 0, sizeof(attr)); - - fd = open(format, O_DIRECTORY); - if (fd < 0) { - ret = fd; - break; - } - ret = perf_pmu__format_parse(fd, &formats); - if (ret) - break; - - ret = perf_pmu__config_terms("perf-pmu-test", &formats, &attr, - terms, false, NULL); - if (ret) - break; + pmu = zalloc(sizeof(*pmu)); + if (!pmu) + return -ENOMEM; - ret = -EINVAL; + INIT_LIST_HEAD(&pmu->format); + INIT_LIST_HEAD(&pmu->aliases); + INIT_LIST_HEAD(&pmu->caps); + format = test_format_dir_get(dir, sizeof(dir)); + if (!format) { + free(pmu); + return -EINVAL; + } - if (attr.config != 0xc00000000002a823) - break; - if (attr.config1 != 0x8000400000000145) - break; - if (attr.config2 != 0x0400000020041d07) - break; + memset(&attr, 0, sizeof(attr)); - ret = 0; - } while (0); + fd = open(format, O_DIRECTORY); + if (fd < 0) { + ret = fd; + goto out; + } - perf_pmu__del_formats(&formats); + pmu->name = strdup("perf-pmu-test"); + ret = perf_pmu__format_parse(pmu, fd, /*eager_load=*/true); + if (ret) + goto out; + + ret = perf_pmu__config_terms(pmu, &attr, terms, /*zero=*/false, /*err=*/NULL); + if (ret) + goto out; + + ret = -EINVAL; + if (attr.config != 0xc00000000002a823) + goto out; + if (attr.config1 != 0x8000400000000145) + goto out; + if (attr.config2 != 0x0400000020041d07) + goto out; + + ret = 0; +out: test_format_dir_put(format); + perf_pmu__delete(pmu); return ret; } diff --git a/tools/perf/tests/shell/coresight/asm_pure_loop.sh b/tools/perf/tests/shell/coresight/asm_pure_loop.sh index 569e9d46162b..779bc8608e1e 100755 --- a/tools/perf/tests/shell/coresight/asm_pure_loop.sh +++ b/tools/perf/tests/shell/coresight/asm_pure_loop.sh @@ -5,7 +5,7 @@ # Carsten Haitzler <carsten.haitzler@arm.com>, 2021 TEST="asm_pure_loop" -. $(dirname $0)/../lib/coresight.sh +. "$(dirname $0)"/../lib/coresight.sh ARGS="" DATV="out" DATA="$DATD/perf-$TEST-$DATV.data" diff --git a/tools/perf/tests/shell/coresight/memcpy_thread_16k_10.sh b/tools/perf/tests/shell/coresight/memcpy_thread_16k_10.sh index d21ba8545938..08a44e52ce9b 100755 --- a/tools/perf/tests/shell/coresight/memcpy_thread_16k_10.sh +++ b/tools/perf/tests/shell/coresight/memcpy_thread_16k_10.sh @@ -5,7 +5,7 @@ # Carsten Haitzler <carsten.haitzler@arm.com>, 2021 TEST="memcpy_thread" -. $(dirname $0)/../lib/coresight.sh +. "$(dirname $0)"/../lib/coresight.sh ARGS="16 10 1" DATV="16k_10" DATA="$DATD/perf-$TEST-$DATV.data" diff --git a/tools/perf/tests/shell/coresight/thread_loop_check_tid_10.sh b/tools/perf/tests/shell/coresight/thread_loop_check_tid_10.sh index 7c13636fc778..c83a200dede4 100755 --- a/tools/perf/tests/shell/coresight/thread_loop_check_tid_10.sh +++ b/tools/perf/tests/shell/coresight/thread_loop_check_tid_10.sh @@ -5,7 +5,7 @@ # Carsten Haitzler <carsten.haitzler@arm.com>, 2021 TEST="thread_loop" -. $(dirname $0)/../lib/coresight.sh +. "$(dirname $0)"/../lib/coresight.sh ARGS="10 1" DATV="check-tid-10th" DATA="$DATD/perf-$TEST-$DATV.data" diff --git a/tools/perf/tests/shell/coresight/thread_loop_check_tid_2.sh b/tools/perf/tests/shell/coresight/thread_loop_check_tid_2.sh index a067145af43c..6346fd5e87c8 100755 --- a/tools/perf/tests/shell/coresight/thread_loop_check_tid_2.sh +++ b/tools/perf/tests/shell/coresight/thread_loop_check_tid_2.sh @@ -5,7 +5,7 @@ # Carsten Haitzler <carsten.haitzler@arm.com>, 2021 TEST="thread_loop" -. $(dirname $0)/../lib/coresight.sh +. "$(dirname $0)"/../lib/coresight.sh ARGS="2 20" DATV="check-tid-2th" DATA="$DATD/perf-$TEST-$DATV.data" diff --git a/tools/perf/tests/shell/coresight/unroll_loop_thread_10.sh b/tools/perf/tests/shell/coresight/unroll_loop_thread_10.sh index f48c85230b15..7304e3d3a6ff 100755 --- a/tools/perf/tests/shell/coresight/unroll_loop_thread_10.sh +++ b/tools/perf/tests/shell/coresight/unroll_loop_thread_10.sh @@ -5,7 +5,7 @@ # Carsten Haitzler <carsten.haitzler@arm.com>, 2021 TEST="unroll_loop_thread" -. $(dirname $0)/../lib/coresight.sh +. "$(dirname $0)"/../lib/coresight.sh ARGS="10" DATV="10" DATA="$DATD/perf-$TEST-$DATV.data" diff --git a/tools/perf/tests/shell/lib/probe.sh b/tools/perf/tests/shell/lib/probe.sh index 51e3f60baba0..5aa6e2ec5734 100644 --- a/tools/perf/tests/shell/lib/probe.sh +++ b/tools/perf/tests/shell/lib/probe.sh @@ -1,3 +1,4 @@ +#!/bin/bash # SPDX-License-Identifier: GPL-2.0 # Arnaldo Carvalho de Melo <acme@kernel.org>, 2017 diff --git a/tools/perf/tests/shell/lib/probe_vfs_getname.sh b/tools/perf/tests/shell/lib/probe_vfs_getname.sh index 60c5e34f90c4..bf4c1fb71c4b 100644 --- a/tools/perf/tests/shell/lib/probe_vfs_getname.sh +++ b/tools/perf/tests/shell/lib/probe_vfs_getname.sh @@ -1,3 +1,4 @@ +#!/bin/sh # Arnaldo Carvalho de Melo <acme@kernel.org>, 2017 perf probe -l 2>&1 | grep -q probe:vfs_getname @@ -10,11 +11,11 @@ cleanup_probe_vfs_getname() { } add_probe_vfs_getname() { - local verbose=$1 + add_probe_verbose=$1 if [ $had_vfs_getname -eq 1 ] ; then line=$(perf probe -L getname_flags 2>&1 | grep -E 'result.*=.*filename;' | sed -r 's/[[:space:]]+([[:digit:]]+)[[:space:]]+result->uptr.*/\1/') perf probe -q "vfs_getname=getname_flags:${line} pathname=result->name:string" || \ - perf probe $verbose "vfs_getname=getname_flags:${line} pathname=filename:ustring" + perf probe $add_probe_verbose "vfs_getname=getname_flags:${line} pathname=filename:ustring" fi } diff --git a/tools/perf/tests/shell/lib/stat_output.sh b/tools/perf/tests/shell/lib/stat_output.sh index 698343f0ecf9..3cc158a64326 100644 --- a/tools/perf/tests/shell/lib/stat_output.sh +++ b/tools/perf/tests/shell/lib/stat_output.sh @@ -1,3 +1,4 @@ +#!/bin/bash # SPDX-License-Identifier: GPL-2.0 # Return true if perf_event_paranoid is > $1 and not running as root. diff --git a/tools/perf/tests/shell/lib/waiting.sh b/tools/perf/tests/shell/lib/waiting.sh index e7a39134a68e..bdd5a7c71591 100644 --- a/tools/perf/tests/shell/lib/waiting.sh +++ b/tools/perf/tests/shell/lib/waiting.sh @@ -1,3 +1,4 @@ +#!/bin/sh # SPDX-License-Identifier: GPL-2.0 tenths=date\ +%s%1N diff --git a/tools/perf/tests/shell/lock_contention.sh b/tools/perf/tests/shell/lock_contention.sh index 4a194420416e..d120e83db7d9 100755 --- a/tools/perf/tests/shell/lock_contention.sh +++ b/tools/perf/tests/shell/lock_contention.sh @@ -21,7 +21,7 @@ trap_cleanup() { trap trap_cleanup EXIT TERM INT check() { - if [ `id -u` != 0 ]; then + if [ "$(id -u)" != 0 ]; then echo "[Skip] No root permission" err=2 exit @@ -157,10 +157,10 @@ test_lock_filter() perf lock contention -i ${perfdata} -L tasklist_lock -q 2> ${result} # find out the type of tasklist_lock - local type=$(head -1 "${result}" | awk '{ print $8 }' | sed -e 's/:.*//') + test_lock_filter_type=$(head -1 "${result}" | awk '{ print $8 }' | sed -e 's/:.*//') - if [ "$(grep -c -v "${type}" "${result}")" != "0" ]; then - echo "[Fail] Recorded result should not have non-${type} locks:" "$(cat "${result}")" + if [ "$(grep -c -v "${test_lock_filter_type}" "${result}")" != "0" ]; then + echo "[Fail] Recorded result should not have non-${test_lock_filter_type} locks:" "$(cat "${result}")" err=1 exit fi @@ -170,8 +170,8 @@ test_lock_filter() fi perf lock con -a -b -L tasklist_lock -q -- perf bench sched messaging > /dev/null 2> ${result} - if [ "$(grep -c -v "${type}" "${result}")" != "0" ]; then - echo "[Fail] BPF result should not have non-${type} locks:" "$(cat "${result}")" + if [ "$(grep -c -v "${test_lock_filter_type}" "${result}")" != "0" ]; then + echo "[Fail] BPF result should not have non-${test_lock_filter_type} locks:" "$(cat "${result}")" err=1 exit fi diff --git a/tools/perf/tests/shell/probe_vfs_getname.sh b/tools/perf/tests/shell/probe_vfs_getname.sh index 5d1b63d3f3e1..871243d6d03a 100755 --- a/tools/perf/tests/shell/probe_vfs_getname.sh +++ b/tools/perf/tests/shell/probe_vfs_getname.sh @@ -4,11 +4,11 @@ # SPDX-License-Identifier: GPL-2.0 # Arnaldo Carvalho de Melo <acme@kernel.org>, 2017 -. $(dirname $0)/lib/probe.sh +. "$(dirname $0)"/lib/probe.sh skip_if_no_perf_probe || exit 2 -. $(dirname $0)/lib/probe_vfs_getname.sh +. "$(dirname $0)"/lib/probe_vfs_getname.sh add_probe_vfs_getname || skip_if_no_debuginfo err=$? diff --git a/tools/perf/tests/shell/record+zstd_comp_decomp.sh b/tools/perf/tests/shell/record+zstd_comp_decomp.sh index 49bd875d5122..8929046e9057 100755 --- a/tools/perf/tests/shell/record+zstd_comp_decomp.sh +++ b/tools/perf/tests/shell/record+zstd_comp_decomp.sh @@ -13,25 +13,25 @@ skip_if_no_z_record() { collect_z_record() { echo "Collecting compressed record file:" [ "$(uname -m)" != s390x ] && gflag='-g' - $perf_tool record -o $trace_file $gflag -z -F 5000 -- \ + $perf_tool record -o "$trace_file" $gflag -z -F 5000 -- \ dd count=500 if=/dev/urandom of=/dev/null } check_compressed_stats() { echo "Checking compressed events stats:" - $perf_tool report -i $trace_file --header --stats | \ + $perf_tool report -i "$trace_file" --header --stats | \ grep -E "(# compressed : Zstd,)|(COMPRESSED events:)" } check_compressed_output() { - $perf_tool inject -i $trace_file -o $trace_file.decomp && - $perf_tool report -i $trace_file --stdio -F comm,dso,sym | head -n -3 > $trace_file.comp.output && - $perf_tool report -i $trace_file.decomp --stdio -F comm,dso,sym | head -n -3 > $trace_file.decomp.output && - diff $trace_file.comp.output $trace_file.decomp.output + $perf_tool inject -i "$trace_file" -o "$trace_file.decomp" && + $perf_tool report -i "$trace_file" --stdio -F comm,dso,sym | head -n -3 > "$trace_file.comp.output" && + $perf_tool report -i "$trace_file.decomp" --stdio -F comm,dso,sym | head -n -3 > "$trace_file.decomp.output" && + diff "$trace_file.comp.output" "$trace_file.decomp.output" } skip_if_no_z_record || exit 2 collect_z_record && check_compressed_stats && check_compressed_output err=$? -rm -f $trace_file* +rm -f "$trace_file*" exit $err diff --git a/tools/perf/tests/shell/record_bpf_filter.sh b/tools/perf/tests/shell/record_bpf_filter.sh new file mode 100755 index 000000000000..31c593966e8c --- /dev/null +++ b/tools/perf/tests/shell/record_bpf_filter.sh @@ -0,0 +1,134 @@ +#!/bin/sh +# perf record sample filtering (by BPF) tests +# SPDX-License-Identifier: GPL-2.0 + +set -e + +err=0 +perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX) + +cleanup() { + rm -f "${perfdata}" + rm -f "${perfdata}".old + trap - EXIT TERM INT +} + +trap_cleanup() { + cleanup + exit 1 +} +trap trap_cleanup EXIT TERM INT + +test_bpf_filter_priv() { + echo "Checking BPF-filter privilege" + + if [ "$(id -u)" != 0 ] + then + echo "bpf-filter test [Skipped permission]" + err=2 + return + fi + if ! perf record -e task-clock --filter 'period > 1' \ + -o /dev/null --quiet true 2>&1 + then + echo "bpf-filter test [Skipped missing BPF support]" + err=2 + return + fi +} + +test_bpf_filter_basic() { + echo "Basic bpf-filter test" + + if ! perf record -e task-clock -c 10000 --filter 'ip < 0xffffffff00000000' \ + -o "${perfdata}" true 2> /dev/null + then + echo "Basic bpf-filter test [Failed record]" + err=1 + return + fi + if perf script -i "${perfdata}" -F ip | grep 'ffffffff[0-9a-f]*' + then + if uname -r | grep -q ^6.2 + then + echo "Basic bpf-filter test [Skipped unsupported kernel]" + err=2 + return + fi + echo "Basic bpf-filter test [Failed invalid output]" + err=1 + return + fi + echo "Basic bpf-filter test [Success]" +} + +test_bpf_filter_fail() { + echo "Failing bpf-filter test" + + # 'cpu' requires PERF_SAMPLE_CPU flag + if ! perf record -e task-clock --filter 'cpu > 0' \ + -o /dev/null true 2>&1 | grep PERF_SAMPLE_CPU + then + echo "Failing bpf-filter test [Failed forbidden CPU]" + err=1 + return + fi + + if ! perf record --sample-cpu -e task-clock --filter 'cpu > 0' \ + -o /dev/null true 2>/dev/null + then + echo "Failing bpf-filter test [Failed should succeed]" + err=1 + return + fi + + echo "Failing bpf-filter test [Success]" +} + +test_bpf_filter_group() { + echo "Group bpf-filter test" + + if ! perf record -e task-clock --filter 'period > 1000 || ip > 0' \ + -o /dev/null true 2>/dev/null + then + echo "Group bpf-filter test [Failed should succeed]" + err=1 + return + fi + + if ! perf record -e task-clock --filter 'cpu > 0 || ip > 0' \ + -o /dev/null true 2>&1 | grep PERF_SAMPLE_CPU + then + echo "Group bpf-filter test [Failed forbidden CPU]" + err=1 + return + fi + + if ! perf record -e task-clock --filter 'period > 0 || code_pgsz > 4096' \ + -o /dev/null true 2>&1 | grep PERF_SAMPLE_CODE_PAGE_SIZE + then + echo "Group bpf-filter test [Failed forbidden CODE_PAGE_SIZE]" + err=1 + return + fi + + echo "Group bpf-filter test [Success]" +} + + +test_bpf_filter_priv + +if [ $err = 0 ]; then + test_bpf_filter_basic +fi + +if [ $err = 0 ]; then + test_bpf_filter_fail +fi + +if [ $err = 0 ]; then + test_bpf_filter_group +fi + +cleanup +exit $err diff --git a/tools/perf/tests/shell/record_offcpu.sh b/tools/perf/tests/shell/record_offcpu.sh index f062ae9a95e1..a0d14cd0aa79 100755 --- a/tools/perf/tests/shell/record_offcpu.sh +++ b/tools/perf/tests/shell/record_offcpu.sh @@ -10,19 +10,19 @@ perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX) cleanup() { rm -f ${perfdata} rm -f ${perfdata}.old - trap - exit term int + trap - EXIT TERM INT } trap_cleanup() { cleanup exit 1 } -trap trap_cleanup exit term int +trap trap_cleanup EXIT TERM INT test_offcpu_priv() { echo "Checking off-cpu privilege" - if [ `id -u` != 0 ] + if [ "$(id -u)" != 0 ] then echo "off-cpu test [Skipped permission]" err=2 diff --git a/tools/perf/tests/shell/stat+csv_output.sh b/tools/perf/tests/shell/stat+csv_output.sh index 34a0701fee05..d890eb26e914 100755 --- a/tools/perf/tests/shell/stat+csv_output.sh +++ b/tools/perf/tests/shell/stat+csv_output.sh @@ -6,7 +6,7 @@ set -e -. $(dirname $0)/lib/stat_output.sh +. "$(dirname $0)"/lib/stat_output.sh csv_sep=@ diff --git a/tools/perf/tests/shell/stat+csv_summary.sh b/tools/perf/tests/shell/stat+csv_summary.sh index 5571ff75eb42..8bae9c8a835e 100755 --- a/tools/perf/tests/shell/stat+csv_summary.sh +++ b/tools/perf/tests/shell/stat+csv_summary.sh @@ -10,7 +10,7 @@ set -e # perf stat -e cycles -x' ' -I1000 --interval-count 1 --summary 2>&1 | \ grep -e summary | \ -while read summary num event run pct +while read summary _num _event _run _pct do if [ $summary != "summary" ]; then exit 1 @@ -23,7 +23,7 @@ done # perf stat -e cycles -x' ' -I1000 --interval-count 1 --summary --no-csv-summary 2>&1 | \ grep -e summary | \ -while read num event run pct +while read _num _event _run _pct do exit 1 done diff --git a/tools/perf/tests/shell/stat+shadow_stat.sh b/tools/perf/tests/shell/stat+shadow_stat.sh index 0e9cba84e757..a1918a15e36a 100755 --- a/tools/perf/tests/shell/stat+shadow_stat.sh +++ b/tools/perf/tests/shell/stat+shadow_stat.sh @@ -14,7 +14,7 @@ test_global_aggr() { perf stat -a --no-big-num -e cycles,instructions sleep 1 2>&1 | \ grep -e cycles -e instructions | \ - while read num evt hash ipc rest + while read num evt _hash ipc rest do # skip not counted events if [ "$num" = "<not" ]; then @@ -45,7 +45,7 @@ test_no_aggr() { perf stat -a -A --no-big-num -e cycles,instructions sleep 1 2>&1 | \ grep ^CPU | \ - while read cpu num evt hash ipc rest + while read cpu num evt _hash ipc rest do # skip not counted events if [ "$num" = "<not" ]; then diff --git a/tools/perf/tests/shell/stat+std_output.sh b/tools/perf/tests/shell/stat+std_output.sh index f972b31fa0c2..fb2b10547a11 100755 --- a/tools/perf/tests/shell/stat+std_output.sh +++ b/tools/perf/tests/shell/stat+std_output.sh @@ -6,7 +6,7 @@ set -e -. $(dirname $0)/lib/stat_output.sh +. "$(dirname $0)"/lib/stat_output.sh stat_output=$(mktemp /tmp/__perf_test.stat_output.std.XXXXX) @@ -28,7 +28,6 @@ trap trap_cleanup EXIT TERM INT function commachecker() { - local -i cnt=0 local prefix=1 case "$1" diff --git a/tools/perf/tests/shell/stat_bpf_counters.sh b/tools/perf/tests/shell/stat_bpf_counters.sh index 13473aeba489..a87bb2814b4c 100755 --- a/tools/perf/tests/shell/stat_bpf_counters.sh +++ b/tools/perf/tests/shell/stat_bpf_counters.sh @@ -22,21 +22,21 @@ compare_number() } # skip if --bpf-counters is not supported -if ! perf stat --bpf-counters true > /dev/null 2>&1; then +if ! perf stat -e cycles --bpf-counters true > /dev/null 2>&1; then if [ "$1" = "-v" ]; then echo "Skipping: --bpf-counters not supported" - perf --no-pager stat --bpf-counters true || true + perf --no-pager stat -e cycles --bpf-counters true || true fi exit 2 fi base_cycles=$(perf stat --no-big-num -e cycles -- perf bench sched messaging -g 1 -l 100 -t 2>&1 | awk '/cycles/ {print $1}') -if [ "$base_cycles" == "<not" ]; then +if [ "$base_cycles" = "<not" ]; then echo "Skipping: cycles event not counted" exit 2 fi bpf_cycles=$(perf stat --no-big-num --bpf-counters -e cycles -- perf bench sched messaging -g 1 -l 100 -t 2>&1 | awk '/cycles/ {print $1}') -if [ "$bpf_cycles" == "<not" ]; then +if [ "$bpf_cycles" = "<not" ]; then echo "Failed: cycles not counted with --bpf-counters" exit 1 fi diff --git a/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh b/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh index d724855d097c..e75d0780dc78 100755 --- a/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh +++ b/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh @@ -25,22 +25,22 @@ check_bpf_counter() find_cgroups() { # try usual systemd slices first - if [ -d /sys/fs/cgroup/system.slice -a -d /sys/fs/cgroup/user.slice ]; then + if [ -d /sys/fs/cgroup/system.slice ] && [ -d /sys/fs/cgroup/user.slice ]; then test_cgroups="system.slice,user.slice" return fi # try root and self cgroups - local self_cgrp=$(grep perf_event /proc/self/cgroup | cut -d: -f3) - if [ -z ${self_cgrp} ]; then + find_cgroups_self_cgrp=$(grep perf_event /proc/self/cgroup | cut -d: -f3) + if [ -z ${find_cgroups_self_cgrp} ]; then # cgroup v2 doesn't specify perf_event - self_cgrp=$(grep ^0: /proc/self/cgroup | cut -d: -f3) + find_cgroups_self_cgrp=$(grep ^0: /proc/self/cgroup | cut -d: -f3) fi - if [ -z ${self_cgrp} ]; then + if [ -z ${find_cgroups_self_cgrp} ]; then test_cgroups="/" else - test_cgroups="/,${self_cgrp}" + test_cgroups="/,${find_cgroups_self_cgrp}" fi } @@ -48,13 +48,11 @@ find_cgroups() # Just check if it runs without failure and has non-zero results. check_system_wide_counted() { - local output - - output=$(perf stat -a --bpf-counters --for-each-cgroup ${test_cgroups} -e cpu-clock -x, sleep 1 2>&1) - if echo ${output} | grep -q -F "<not "; then + check_system_wide_counted_output=$(perf stat -a --bpf-counters --for-each-cgroup ${test_cgroups} -e cpu-clock -x, sleep 1 2>&1) + if echo ${check_system_wide_counted_output} | grep -q -F "<not "; then echo "Some system-wide events are not counted" if [ "${verbose}" = "1" ]; then - echo ${output} + echo ${check_system_wide_counted_output} fi exit 1 fi @@ -62,13 +60,11 @@ check_system_wide_counted() check_cpu_list_counted() { - local output - - output=$(perf stat -C 1 --bpf-counters --for-each-cgroup ${test_cgroups} -e cpu-clock -x, taskset -c 1 sleep 1 2>&1) - if echo ${output} | grep -q -F "<not "; then + check_cpu_list_counted_output=$(perf stat -C 0,1 --bpf-counters --for-each-cgroup ${test_cgroups} -e cpu-clock -x, taskset -c 1 sleep 1 2>&1) + if echo ${check_cpu_list_counted_output} | grep -q -F "<not "; then echo "Some CPU events are not counted" if [ "${verbose}" = "1" ]; then - echo ${output} + echo ${check_cpu_list_counted_output} fi exit 1 fi diff --git a/tools/perf/tests/shell/test_arm_spe_fork.sh b/tools/perf/tests/shell/test_arm_spe_fork.sh index fad361675a1d..1a7e6a82d0e3 100755 --- a/tools/perf/tests/shell/test_arm_spe_fork.sh +++ b/tools/perf/tests/shell/test_arm_spe_fork.sh @@ -22,7 +22,7 @@ cleanup_files() rm -f ${PERF_DATA} } -trap cleanup_files exit term int +trap cleanup_files EXIT TERM INT echo "Recording workload..." perf record -o ${PERF_DATA} -e arm_spe/period=65536/ -vvv -- $TEST_PROGRAM > ${PERF_RECORD_LOG} 2>&1 & diff --git a/tools/perf/tests/shell/test_perf_data_converter_json.sh b/tools/perf/tests/shell/test_perf_data_converter_json.sh index 72ac6c83231c..6ded58f98f55 100755 --- a/tools/perf/tests/shell/test_perf_data_converter_json.sh +++ b/tools/perf/tests/shell/test_perf_data_converter_json.sh @@ -39,7 +39,7 @@ test_json_converter_command() echo "Testing Perf Data Convertion Command to JSON" perf record -o "$perfdata" -F 99 -g -- perf test -w noploop > /dev/null 2>&1 perf data convert --to-json "$result" --force -i "$perfdata" >/dev/null 2>&1 - if [ $(cat "${result}" | wc -l) -gt "0" ] ; then + if [ "$(cat ${result} | wc -l)" -gt "0" ] ; then echo "Perf Data Converter Command to JSON [SUCCESS]" else echo "Perf Data Converter Command to JSON [FAILED]" diff --git a/tools/perf/tests/shell/test_task_analyzer.sh b/tools/perf/tests/shell/test_task_analyzer.sh index 0095abbe20ca..92d15154ba79 100755 --- a/tools/perf/tests/shell/test_task_analyzer.sh +++ b/tools/perf/tests/shell/test_task_analyzer.sh @@ -52,7 +52,7 @@ find_str_or_fail() { # check if perf is compiled with libtraceevent support skip_no_probe_record_support() { - perf record -e "sched:sched_switch" -a -- sleep 1 2>&1 | grep "libtraceevent is necessary for tracepoint support" && return 2 + perf version --build-options | grep -q " OFF .* HAVE_LIBTRACEEVENT" && return 2 return 0 } diff --git a/tools/perf/tests/shell/trace+probe_vfs_getname.sh b/tools/perf/tests/shell/trace+probe_vfs_getname.sh index 0a4bac3dd77e..4014487cf4d9 100755 --- a/tools/perf/tests/shell/trace+probe_vfs_getname.sh +++ b/tools/perf/tests/shell/trace+probe_vfs_getname.sh @@ -10,17 +10,17 @@ # SPDX-License-Identifier: GPL-2.0 # Arnaldo Carvalho de Melo <acme@kernel.org>, 2017 -. $(dirname $0)/lib/probe.sh +. "$(dirname $0)"/lib/probe.sh skip_if_no_perf_probe || exit 2 skip_if_no_perf_trace || exit 2 -. $(dirname $0)/lib/probe_vfs_getname.sh +. "$(dirname $0)"/lib/probe_vfs_getname.sh trace_open_vfs_getname() { - evts=$(echo $(perf list syscalls:sys_enter_open* 2>/dev/null | grep -E 'open(at)? ' | sed -r 's/.*sys_enter_([a-z]+) +\[.*$/\1/') | sed 's/ /,/') + evts="$(echo "$(perf list syscalls:sys_enter_open* 2>/dev/null | grep -E 'open(at)? ' | sed -r 's/.*sys_enter_([a-z]+) +\[.*$/\1/')" | sed ':a;N;s:\n:,:g')" perf trace -e $evts touch $file 2>&1 | \ - grep -E " +[0-9]+\.[0-9]+ +\( +[0-9]+\.[0-9]+ ms\): +touch\/[0-9]+ open(at)?\((dfd: +CWD, +)?filename: +${file}, +flags: CREAT\|NOCTTY\|NONBLOCK\|WRONLY, +mode: +IRUGO\|IWUGO\) += +[0-9]+$" + grep -E " +[0-9]+\.[0-9]+ +\( +[0-9]+\.[0-9]+ ms\): +touch/[0-9]+ open(at)?\((dfd: +CWD, +)?filename: +\"?${file}\"?, +flags: CREAT\|NOCTTY\|NONBLOCK\|WRONLY, +mode: +IRUGO\|IWUGO\) += +[0-9]+$" } diff --git a/tools/perf/tests/stat.c b/tools/perf/tests/stat.c index 500974040fe3..706780fb5695 100644 --- a/tools/perf/tests/stat.c +++ b/tools/perf/tests/stat.c @@ -27,7 +27,7 @@ static int process_stat_config_event(struct perf_tool *tool __maybe_unused, struct machine *machine __maybe_unused) { struct perf_record_stat_config *config = &event->stat_config; - struct perf_stat_config stat_config; + struct perf_stat_config stat_config = {}; #define HAS(term, val) \ has_term(config, PERF_STAT_CONFIG_TERM__##term, val) diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h index f424c0b7f43f..f33cfc3c19a4 100644 --- a/tools/perf/tests/tests.h +++ b/tools/perf/tests/tests.h @@ -113,7 +113,6 @@ DECLARE_SUITE(fdarray__filter); DECLARE_SUITE(fdarray__add); DECLARE_SUITE(kmod_path__parse); DECLARE_SUITE(thread_map); -DECLARE_SUITE(llvm); DECLARE_SUITE(bpf); DECLARE_SUITE(session_topology); DECLARE_SUITE(thread_map_synthesize); @@ -129,7 +128,6 @@ DECLARE_SUITE(sdt_event); DECLARE_SUITE(is_printable_array); DECLARE_SUITE(bitmap_print); DECLARE_SUITE(perf_hooks); -DECLARE_SUITE(clang); DECLARE_SUITE(unit_number__scnprint); DECLARE_SUITE(mem2node); DECLARE_SUITE(maps__merge_in); diff --git a/tools/perf/trace/beauty/arch_errno_names.sh b/tools/perf/trace/beauty/arch_errno_names.sh index 37c53bac5f56..cc09dcaa891e 100755 --- a/tools/perf/trace/beauty/arch_errno_names.sh +++ b/tools/perf/trace/beauty/arch_errno_names.sh @@ -17,8 +17,7 @@ arch_string() asm_errno_file() { - local arch="$1" - local header + arch="$1" header="$toolsdir/arch/$arch/include/uapi/asm/errno.h" if test -r "$header"; then @@ -30,8 +29,7 @@ asm_errno_file() create_errno_lookup_func() { - local arch=$(arch_string "$1") - local nr name + arch=$(arch_string "$1") printf "static const char *errno_to_name__%s(int err)\n{\n\tswitch (err) {\n" $arch @@ -44,8 +42,8 @@ create_errno_lookup_func() process_arch() { - local arch="$1" - local asm_errno=$(asm_errno_file "$arch") + arch="$1" + asm_errno=$(asm_errno_file "$arch") $gcc $CFLAGS $include_path -E -dM -x c $asm_errno \ |grep -hE '^#define[[:blank:]]+(E[^[:blank:]]+)[[:blank:]]+([[:digit:]]+).*' \ @@ -56,9 +54,8 @@ process_arch() create_arch_errno_table_func() { - local archlist="$1" - local default="$2" - local arch + archlist="$1" + default="$2" printf 'const char *arch_syscalls__strerrno(const char *arch, int err)\n' printf '{\n' diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h index 3d12bf0f6d07..788e8f6bd90e 100644 --- a/tools/perf/trace/beauty/beauty.h +++ b/tools/perf/trace/beauty/beauty.h @@ -67,15 +67,14 @@ extern struct strarray strarray__socket_level; /** * augmented_arg: extra payload for syscall pointer arguments - * If perf_sample->raw_size is more than what a syscall sys_enter_FOO puts, - * then its the arguments contents, so that we can show more than just a + * If perf_sample->raw_size is more than what a syscall sys_enter_FOO puts, then + * its the arguments contents, so that we can show more than just a * pointer. This will be done initially with eBPF, the start of that is at the - * tools/perf/examples/bpf/augmented_syscalls.c example for the openat, but - * will eventually be done automagically caching the running kernel tracefs - * events data into an eBPF C script, that then gets compiled and its .o file - * cached for subsequent use. For char pointers like the ones for 'open' like - * syscalls its easy, for the rest we should use DWARF or better, BTF, much - * more compact. + * tools/perf/util/bpf_skel/augmented_syscalls.bpf.c that will eventually be + * done automagically caching the running kernel tracefs events data into an + * eBPF C script, that then gets compiled and its .o file cached for subsequent + * use. For char pointers like the ones for 'open' like syscalls its easy, for + * the rest we should use DWARF or better, BTF, much more compact. * * @size: 8 if all we need is an integer, otherwise all of the augmented arg. * @int_arg: will be used for integer like pointer contents, like 'accept's 'upeer_addrlen' diff --git a/tools/perf/trace/beauty/mmap_flags.sh b/tools/perf/trace/beauty/mmap_flags.sh index 3022597c8c17..6ecdb3c5a99e 100755 --- a/tools/perf/trace/beauty/mmap_flags.sh +++ b/tools/perf/trace/beauty/mmap_flags.sh @@ -19,6 +19,7 @@ arch_mman=${arch_header_dir}/mman.h printf "static const char *mmap_flags[] = {\n" regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MAP_([[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*.*' +test -f ${arch_mman} && \ grep -E -q $regex ${arch_mman} && \ (grep -E $regex ${arch_mman} | \ sed -r "s/$regex/\2 \1 \1 \1 \2/g" | \ @@ -28,12 +29,14 @@ grep -E -q $regex ${linux_mman} && \ grep -E -vw 'MAP_(UNINITIALIZED|TYPE|SHARED_VALIDATE)' | \ sed -r "s/$regex/\2 \1 \1 \1 \2/g" | \ xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n#ifndef MAP_%s\n#define MAP_%s %s\n#endif\n") -([ ! -f ${arch_mman} ] || grep -E -q '#[[:space:]]*include[[:space:]]+.*uapi/asm-generic/mman.*' ${arch_mman}) && +( ! test -f ${arch_mman} || \ +grep -E -q '#[[:space:]]*include[[:space:]]+.*uapi/asm-generic/mman.*' ${arch_mman}) && (grep -E $regex ${header_dir}/mman-common.h | \ grep -E -vw 'MAP_(UNINITIALIZED|TYPE|SHARED_VALIDATE)' | \ sed -r "s/$regex/\2 \1 \1 \1 \2/g" | \ xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n#ifndef MAP_%s\n#define MAP_%s %s\n#endif\n") -([ ! -f ${arch_mman} ] || grep -E -q '#[[:space:]]*include[[:space:]]+.*uapi/asm-generic/mman.h>.*' ${arch_mman}) && +( ! test -f ${arch_mman} || \ +grep -E -q '#[[:space:]]*include[[:space:]]+.*uapi/asm-generic/mman.h>.*' ${arch_mman}) && (grep -E $regex ${header_dir}/mman.h | \ sed -r "s/$regex/\2 \1 \1 \1 \2/g" | \ xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n#ifndef MAP_%s\n#define MAP_%s %s\n#endif\n") diff --git a/tools/perf/trace/beauty/mmap_prot.sh b/tools/perf/trace/beauty/mmap_prot.sh index 49e8c865214b..4436fcd6e861 100755 --- a/tools/perf/trace/beauty/mmap_prot.sh +++ b/tools/perf/trace/beauty/mmap_prot.sh @@ -17,12 +17,13 @@ prefix="PROT" printf "static const char *mmap_prot[] = {\n" regex=`printf '^[[:space:]]*#[[:space:]]*define[[:space:]]+%s_([[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*.*' ${prefix}` -([ ! -f ${arch_mman} ] || grep -E -q '#[[:space:]]*include[[:space:]]+.*uapi/asm-generic/mman.*' ${arch_mman}) && +( ! test -f ${arch_mman} \ +|| grep -E -q '#[[:space:]]*include[[:space:]]+.*uapi/asm-generic/mman.*' ${arch_mman}) && (grep -E $regex ${common_mman} | \ grep -E -vw PROT_NONE | \ sed -r "s/$regex/\2 \1 \1 \1 \2/g" | \ xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n#ifndef ${prefix}_%s\n#define ${prefix}_%s %s\n#endif\n") -[ -f ${arch_mman} ] && grep -E -q $regex ${arch_mman} && +test -f ${arch_mman} && grep -E -q $regex ${arch_mman} && (grep -E $regex ${arch_mman} | \ grep -E -vw PROT_NONE | \ sed -r "s/$regex/\2 \1 \1 \1 \2/g" | \ diff --git a/tools/perf/trace/beauty/tracepoints/x86_irq_vectors.sh b/tools/perf/trace/beauty/tracepoints/x86_irq_vectors.sh index eed9ce0fcbe6..87dc68c7de0c 100755 --- a/tools/perf/trace/beauty/tracepoints/x86_irq_vectors.sh +++ b/tools/perf/trace/beauty/tracepoints/x86_irq_vectors.sh @@ -12,7 +12,7 @@ x86_irq_vectors=${arch_x86_header_dir}/irq_vectors.h # FIRST_EXTERNAL_VECTOR is not that useful, find what is its number # and then replace whatever is using it and that is useful, which at -# the time of writing of this script was: IRQ_MOVE_CLEANUP_VECTOR. +# the time of writing of this script was: 0x20. first_external_regex='^#define[[:space:]]+FIRST_EXTERNAL_VECTOR[[:space:]]+(0x[[:xdigit:]]+)$' first_external_vector=$(grep -E ${first_external_regex} ${x86_irq_vectors} | sed -r "s/${first_external_regex}/\1/g") diff --git a/tools/perf/trace/beauty/x86_arch_prctl.sh b/tools/perf/trace/beauty/x86_arch_prctl.sh index fd5c740512c5..b1596df251f0 100755 --- a/tools/perf/trace/beauty/x86_arch_prctl.sh +++ b/tools/perf/trace/beauty/x86_arch_prctl.sh @@ -7,9 +7,9 @@ prctl_arch_header=${x86_header_dir}/prctl.h print_range () { - local idx=$1 - local prefix=$2 - local first_entry=$3 + idx=$1 + prefix=$2 + first_entry=$3 printf "#define x86_arch_prctl_codes_%d_offset %s\n" $idx $first_entry printf "static const char *x86_arch_prctl_codes_%d[] = {\n" $idx diff --git a/tools/perf/ui/Build b/tools/perf/ui/Build index 3aff83c3275f..6b6d7143a37b 100644 --- a/tools/perf/ui/Build +++ b/tools/perf/ui/Build @@ -10,5 +10,3 @@ CFLAGS_setup.o += -DLIBDIR="BUILD_STR($(LIBDIR))" perf-$(CONFIG_SLANG) += browser.o perf-$(CONFIG_SLANG) += browsers/ perf-$(CONFIG_SLANG) += tui/ - -CFLAGS_browser.o += -DENABLE_SLFUTURE_CONST diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c index 78fb01d6ad63..603d11283cbd 100644 --- a/tools/perf/ui/browser.c +++ b/tools/perf/ui/browser.c @@ -57,12 +57,12 @@ void ui_browser__gotorc(struct ui_browser *browser, int y, int x) void ui_browser__write_nstring(struct ui_browser *browser __maybe_unused, const char *msg, unsigned int width) { - slsmg_write_nstring(msg, width); + SLsmg_write_nstring(msg, width); } void ui_browser__vprintf(struct ui_browser *browser __maybe_unused, const char *fmt, va_list args) { - slsmg_vprintf(fmt, args); + SLsmg_vprintf(fmt, args); } void ui_browser__printf(struct ui_browser *browser __maybe_unused, const char *fmt, ...) @@ -808,6 +808,6 @@ void ui_browser__init(void) while (ui_browser__colorsets[i].name) { struct ui_browser_colorset *c = &ui_browser__colorsets[i++]; - sltt_set_color(c->colorset, c->name, c->fg, c->bg); + SLtt_set_color(c->colorset, c->name, c->fg, c->bg); } } diff --git a/tools/perf/ui/browsers/Build b/tools/perf/ui/browsers/Build index fdf86f7981ca..7a1d5ddaf688 100644 --- a/tools/perf/ui/browsers/Build +++ b/tools/perf/ui/browsers/Build @@ -4,8 +4,3 @@ perf-y += map.o perf-y += scripts.o perf-y += header.o perf-y += res_sample.o - -CFLAGS_annotate.o += -DENABLE_SLFUTURE_CONST -CFLAGS_hists.o += -DENABLE_SLFUTURE_CONST -CFLAGS_map.o += -DENABLE_SLFUTURE_CONST -CFLAGS_scripts.o += -DENABLE_SLFUTURE_CONST diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index c7ad9e003080..70db5a717905 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -407,11 +407,6 @@ static bool hist_browser__selection_has_children(struct hist_browser *browser) return container_of(ms, struct callchain_list, ms)->has_children; } -static bool hist_browser__he_selection_unfolded(struct hist_browser *browser) -{ - return browser->he_selection ? browser->he_selection->unfolded : false; -} - static bool hist_browser__selection_unfolded(struct hist_browser *browser) { struct hist_entry *he = browser->he_selection; @@ -584,8 +579,8 @@ static int hierarchy_set_folding(struct hist_browser *hb, struct hist_entry *he, return n; } -static void __hist_entry__set_folding(struct hist_entry *he, - struct hist_browser *hb, bool unfold) +static void hist_entry__set_folding(struct hist_entry *he, + struct hist_browser *hb, bool unfold) { hist_entry__init_have_children(he); he->unfolded = unfold ? he->has_children : false; @@ -603,34 +598,12 @@ static void __hist_entry__set_folding(struct hist_entry *he, he->nr_rows = 0; } -static void hist_entry__set_folding(struct hist_entry *he, - struct hist_browser *browser, bool unfold) -{ - double percent; - - percent = hist_entry__get_percent_limit(he); - if (he->filtered || percent < browser->min_pcnt) - return; - - __hist_entry__set_folding(he, browser, unfold); - - if (!he->depth || unfold) - browser->nr_hierarchy_entries++; - if (he->leaf) - browser->nr_callchain_rows += he->nr_rows; - else if (unfold && !hist_entry__has_hierarchy_children(he, browser->min_pcnt)) { - browser->nr_hierarchy_entries++; - he->has_no_entry = true; - he->nr_rows = 1; - } else - he->has_no_entry = false; -} - static void __hist_browser__set_folding(struct hist_browser *browser, bool unfold) { struct rb_node *nd; struct hist_entry *he; + double percent; nd = rb_first_cached(&browser->hists->entries); while (nd) { @@ -640,6 +613,21 @@ __hist_browser__set_folding(struct hist_browser *browser, bool unfold) nd = __rb_hierarchy_next(nd, HMD_FORCE_CHILD); hist_entry__set_folding(he, browser, unfold); + + percent = hist_entry__get_percent_limit(he); + if (he->filtered || percent < browser->min_pcnt) + continue; + + if (!he->depth || unfold) + browser->nr_hierarchy_entries++; + if (he->leaf) + browser->nr_callchain_rows += he->nr_rows; + else if (unfold && !hist_entry__has_hierarchy_children(he, browser->min_pcnt)) { + browser->nr_hierarchy_entries++; + he->has_no_entry = true; + he->nr_rows = 1; + } else + he->has_no_entry = false; } } @@ -659,8 +647,10 @@ static void hist_browser__set_folding_selected(struct hist_browser *browser, boo if (!browser->he_selection) return; - hist_entry__set_folding(browser->he_selection, browser, unfold); - browser->b.nr_entries = hist_browser__nr_entries(browser); + if (unfold == browser->he_selection->unfolded) + return; + + hist_browser__toggle_fold(browser); } static void ui_browser__warn_lost_events(struct ui_browser *browser) @@ -732,8 +722,8 @@ static int hist_browser__handle_hotkey(struct hist_browser *browser, bool warn_l hist_browser__set_folding(browser, true); break; case 'e': - /* Expand the selected entry. */ - hist_browser__set_folding_selected(browser, !hist_browser__he_selection_unfolded(browser)); + /* Toggle expand/collapse the selected entry. */ + hist_browser__toggle_fold(browser); break; case 'H': browser->show_headers = !browser->show_headers; @@ -1779,7 +1769,7 @@ static void hists_browser__hierarchy_headers(struct hist_browser *browser) hists_browser__scnprintf_hierarchy_headers(browser, headers, sizeof(headers)); - ui_browser__gotorc(&browser->b, 0, 0); + ui_browser__gotorc_title(&browser->b, 0, 0); ui_browser__set_color(&browser->b, HE_COLORSET_ROOT); ui_browser__write_nstring(&browser->b, headers, browser->b.width + 1); } diff --git a/tools/perf/ui/libslang.h b/tools/perf/ui/libslang.h index 991e692b9b46..1dff3020e9d5 100644 --- a/tools/perf/ui/libslang.h +++ b/tools/perf/ui/libslang.h @@ -11,28 +11,16 @@ #define HAVE_LONG_LONG __GLIBC_HAVE_LONG_LONG #endif +/* Enable future slang's corrected function prototypes. */ +#define ENABLE_SLFUTURE_CONST 1 +#define ENABLE_SLFUTURE_VOID 1 + #ifdef HAVE_SLANG_INCLUDE_SUBDIR #include <slang/slang.h> #else #include <slang.h> #endif -#if SLANG_VERSION < 20104 -#define slsmg_printf(msg, args...) \ - SLsmg_printf((char *)(msg), ##args) -#define slsmg_vprintf(msg, vargs) \ - SLsmg_vprintf((char *)(msg), vargs) -#define slsmg_write_nstring(msg, len) \ - SLsmg_write_nstring((char *)(msg), len) -#define sltt_set_color(obj, name, fg, bg) \ - SLtt_set_color(obj,(char *)(name), (char *)(fg), (char *)(bg)) -#else -#define slsmg_printf SLsmg_printf -#define slsmg_vprintf SLsmg_vprintf -#define slsmg_write_nstring SLsmg_write_nstring -#define sltt_set_color SLtt_set_color -#endif - #define SL_KEY_UNTAB 0x1000 #endif /* _PERF_UI_SLANG_H_ */ diff --git a/tools/perf/ui/tui/helpline.c b/tools/perf/ui/tui/helpline.c index db4952f5990b..b39451314f43 100644 --- a/tools/perf/ui/tui/helpline.c +++ b/tools/perf/ui/tui/helpline.c @@ -22,7 +22,7 @@ static void tui_helpline__push(const char *msg) SLsmg_gotorc(SLtt_Screen_Rows - 1, 0); SLsmg_set_color(0); - SLsmg_write_nstring((char *)msg, SLtt_Screen_Cols); + SLsmg_write_nstring(msg, SLtt_Screen_Cols); SLsmg_refresh(); strlcpy(ui_helpline__current, msg, sz); } diff --git a/tools/perf/ui/tui/setup.c b/tools/perf/ui/tui/setup.c index c1886aa184b3..605d9e175ea7 100644 --- a/tools/perf/ui/tui/setup.c +++ b/tools/perf/ui/tui/setup.c @@ -142,7 +142,7 @@ int ui__init(void) goto out; } - SLkp_define_keysym((char *)"^(kB)", SL_KEY_UNTAB); + SLkp_define_keysym("^(kB)", SL_KEY_UNTAB); signal(SIGSEGV, ui__signal_backtrace); signal(SIGFPE, ui__signal_backtrace); diff --git a/tools/perf/ui/tui/util.c b/tools/perf/ui/tui/util.c index 3c5174854ac8..e4d322ce0b54 100644 --- a/tools/perf/ui/tui/util.c +++ b/tools/perf/ui/tui/util.c @@ -106,7 +106,7 @@ int ui_browser__input_window(const char *title, const char *text, char *input, SLsmg_draw_box(y, x++, nr_lines, max_len); if (title) { SLsmg_gotorc(y, x + 1); - SLsmg_write_string((char *)title); + SLsmg_write_string(title); } SLsmg_gotorc(++y, x); nr_lines -= 7; @@ -117,12 +117,12 @@ int ui_browser__input_window(const char *title, const char *text, char *input, len = 5; while (len--) { SLsmg_gotorc(y + len - 1, x); - SLsmg_write_nstring((char *)" ", max_len); + SLsmg_write_nstring(" ", max_len); } SLsmg_draw_box(y++, x + 1, 3, max_len - 2); SLsmg_gotorc(y + 3, x); - SLsmg_write_nstring((char *)exit_msg, max_len); + SLsmg_write_nstring(exit_msg, max_len); SLsmg_refresh(); mutex_unlock(&ui__lock); @@ -197,7 +197,7 @@ void __ui__info_window(const char *title, const char *text, const char *exit_msg SLsmg_draw_box(y, x++, nr_lines, max_len); if (title) { SLsmg_gotorc(y, x + 1); - SLsmg_write_string((char *)title); + SLsmg_write_string(title); } SLsmg_gotorc(++y, x); if (exit_msg) @@ -207,9 +207,9 @@ void __ui__info_window(const char *title, const char *text, const char *exit_msg nr_lines, max_len, 1); if (exit_msg) { SLsmg_gotorc(y + nr_lines - 2, x); - SLsmg_write_nstring((char *)" ", max_len); + SLsmg_write_nstring(" ", max_len); SLsmg_gotorc(y + nr_lines - 1, x); - SLsmg_write_nstring((char *)exit_msg, max_len); + SLsmg_write_nstring(exit_msg, max_len); } } diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 96f4ea1d45c5..6d657c9927f7 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -1,3 +1,6 @@ +include $(srctree)/tools/scripts/Makefile.include +include $(srctree)/tools/scripts/utilities.mak + perf-y += arm64-frame-pointer-unwind-support.o perf-y += addr_location.o perf-y += annotate.o @@ -20,13 +23,13 @@ perf-y += evswitch.o perf-y += find_bit.o perf-y += get_current_dir_name.o perf-y += levenshtein.o -perf-y += llvm-utils.o perf-y += mmap.o perf-y += memswap.o perf-y += parse-events.o perf-y += print-events.o perf-y += tracepoint.o perf-y += perf_regs.o +perf-y += perf-regs-arch/ perf-y += path.o perf-y += print_binary.o perf-y += rlimit.o @@ -147,7 +150,6 @@ perf-y += list_sort.o perf-y += mutex.o perf-y += sharded_mutex.o -perf-$(CONFIG_LIBBPF) += bpf-loader.o perf-$(CONFIG_LIBBPF) += bpf_map.o perf-$(CONFIG_PERF_BPF_SKEL) += bpf_counter.o perf-$(CONFIG_PERF_BPF_SKEL) += bpf_counter_cgroup.o @@ -165,7 +167,6 @@ ifeq ($(CONFIG_LIBTRACEEVENT),y) perf-$(CONFIG_PERF_BPF_SKEL) += bpf_kwork.o endif -perf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o perf-$(CONFIG_LIBELF) += symbol-elf.o perf-$(CONFIG_LIBELF) += probe-file.o perf-$(CONFIG_LIBELF) += probe-event.o @@ -229,12 +230,9 @@ perf-y += perf-hooks.o perf-$(CONFIG_LIBBPF) += bpf-event.o perf-$(CONFIG_LIBBPF) += bpf-utils.o -perf-$(CONFIG_CXX) += c++/ - perf-$(CONFIG_LIBPFM4) += pfm.o CFLAGS_config.o += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" -CFLAGS_llvm-utils.o += -DLIBBPF_INCLUDE_DIR="BUILD_STR($(libbpf_include_dir_SQ))" # avoid compiler warnings in 32-bit mode CFLAGS_genelf_debug.o += -Wno-packed @@ -246,7 +244,7 @@ $(OUTPUT)util/parse-events-flex.c $(OUTPUT)util/parse-events-flex.h: util/parse- $(OUTPUT)util/parse-events-bison.c $(OUTPUT)util/parse-events-bison.h: util/parse-events.y $(call rule_mkdir) - $(Q)$(call echo-cmd,bison)$(BISON) -v $< -d $(PARSER_DEBUG_BISON) $(BISON_FILE_PREFIX_MAP) \ + $(Q)$(call echo-cmd,bison)$(BISON) -v $< -d $(PARSER_DEBUG_BISON) $(BISON_FILE_PREFIX_MAP) $(BISON_FALLBACK_FLAGS) \ -o $(OUTPUT)util/parse-events-bison.c -p parse_events_ $(OUTPUT)util/expr-flex.c $(OUTPUT)util/expr-flex.h: util/expr.l $(OUTPUT)util/expr-bison.c @@ -279,28 +277,58 @@ $(OUTPUT)util/bpf-filter-bison.c $(OUTPUT)util/bpf-filter-bison.h: util/bpf-filt $(Q)$(call echo-cmd,bison)$(BISON) -v $< -d $(PARSER_DEBUG_BISON) $(BISON_FILE_PREFIX_MAP) \ -o $(OUTPUT)util/bpf-filter-bison.c -p perf_bpf_filter_ -FLEX_GE_26 := $(shell expr $(shell $(FLEX) --version | sed -e 's/flex \([0-9]\+\).\([0-9]\+\)/\1\2/g') \>\= 26) -ifeq ($(FLEX_GE_26),1) - flex_flags := -Wno-switch-enum -Wno-switch-default -Wno-unused-function -Wno-redundant-decls -Wno-sign-compare -Wno-unused-parameter -Wno-missing-prototypes -Wno-missing-declarations - CC_HASNT_MISLEADING_INDENTATION := $(shell echo "int main(void) { return 0 }" | $(CC) -Werror -Wno-misleading-indentation -o /dev/null -xc - 2>&1 | grep -q -- -Wno-misleading-indentation ; echo $$?) - ifeq ($(CC_HASNT_MISLEADING_INDENTATION), 1) - flex_flags += -Wno-misleading-indentation +FLEX_VERSION := $(shell $(FLEX) --version | cut -d' ' -f2) + +FLEX_GE_260 := $(call version-ge3,$(FLEX_VERSION),2.6.0) +ifeq ($(FLEX_GE_260),1) + flex_flags := -Wno-redundant-decls -Wno-switch-default -Wno-unused-function -Wno-misleading-indentation + + # Some newer clang and gcc version complain about this + # util/parse-events-bison.c:1317:9: error: variable 'parse_events_nerrs' set but not used [-Werror,-Wunused-but-set-variable] + # int yynerrs = 0; + + flex_flags += -Wno-unused-but-set-variable + + FLEX_LT_262 := $(call version-lt3,$(FLEX_VERSION),2.6.2) + ifeq ($(FLEX_LT_262),1) + flex_flags += -Wno-sign-compare endif else flex_flags := -w endif -CFLAGS_parse-events-flex.o += $(flex_flags) -CFLAGS_pmu-flex.o += $(flex_flags) -CFLAGS_expr-flex.o += $(flex_flags) -CFLAGS_bpf-filter-flex.o += $(flex_flags) -bison_flags := -DYYENABLE_NLS=0 -BISON_GE_35 := $(shell expr $(shell $(BISON) --version | grep bison | sed -e 's/.\+ \([0-9]\+\).\([0-9]\+\)/\1\2/g') \>\= 35) -ifeq ($(BISON_GE_35),1) - bison_flags += -Wno-unused-parameter -Wno-nested-externs -Wno-implicit-function-declaration -Wno-switch-enum -Wno-unused-but-set-variable -Wno-unknown-warning-option +# Some newer clang and gcc version complain about this +# util/parse-events-bison.c:1317:9: error: variable 'parse_events_nerrs' set but not used [-Werror,-Wunused-but-set-variable] +# int yynerrs = 0; + +bison_flags := -DYYENABLE_NLS=0 -Wno-unused-but-set-variable + +# Old clangs don't grok -Wno-unused-but-set-variable, remove it +ifeq ($(CC_NO_CLANG), 0) + CLANG_VERSION := $(shell $(CLANG) --version | head -1 | sed 's/.*clang version \([[:digit:]]\+.[[:digit:]]\+.[[:digit:]]\+\).*/\1/g') + ifeq ($(call version-lt3,$(CLANG_VERSION),13.0.0),1) + bison_flags := $(subst -Wno-unused-but-set-variable,,$(bison_flags)) + flex_flags := $(subst -Wno-unused-but-set-variable,,$(flex_flags)) + endif +endif + +BISON_GE_382 := $(shell expr $(shell $(BISON) --version | grep bison | sed -e 's/.\+ \([0-9]\+\).\([0-9]\+\).\([0-9]\+\)/\1\2\3/g') \>\= 382) +ifeq ($(BISON_GE_382),1) + bison_flags += -Wno-switch-enum else bison_flags += -w endif + +BISON_LT_381 := $(shell expr $(shell $(BISON) --version | grep bison | sed -e 's/.\+ \([0-9]\+\).\([0-9]\+\).\([0-9]\+\)/\1\2\3/g') \< 381) +ifeq ($(BISON_LT_381),1) + bison_flags += -DYYNOMEM=YYABORT +endif + +CFLAGS_parse-events-flex.o += $(flex_flags) -Wno-unused-label +CFLAGS_pmu-flex.o += $(flex_flags) +CFLAGS_expr-flex.o += $(flex_flags) +CFLAGS_bpf-filter-flex.o += $(flex_flags) + CFLAGS_parse-events-bison.o += $(bison_flags) CFLAGS_pmu-bison.o += -DYYLTYPE_IS_TRIVIAL=0 $(bison_flags) CFLAGS_expr-bison.o += -DYYLTYPE_IS_TRIVIAL=0 $(bison_flags) @@ -316,8 +344,6 @@ CFLAGS_find_bit.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ET CFLAGS_rbtree.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" CFLAGS_libstring.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" CFLAGS_hweight.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" -CFLAGS_parse-events.o += -Wno-redundant-decls -CFLAGS_expr.o += -Wno-redundant-decls CFLAGS_header.o += -include $(OUTPUT)PERF-VERSION-FILE CFLAGS_arm-spe.o += -I$(srctree)/tools/arch/arm64/include/ diff --git a/tools/perf/util/amd-sample-raw.c b/tools/perf/util/amd-sample-raw.c index 6a6ddba76c75..9d0ce88e90e4 100644 --- a/tools/perf/util/amd-sample-raw.c +++ b/tools/perf/util/amd-sample-raw.c @@ -15,7 +15,6 @@ #include "session.h" #include "evlist.h" #include "sample-raw.h" -#include "pmu-events/pmu-events.h" #include "util/sample.h" static u32 cpu_family, cpu_model, ibs_fetch_type, ibs_op_type; diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index ba988a13dacb..82956adf9963 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -1846,8 +1846,11 @@ static int symbol__disassemble_bpf(struct symbol *sym, perf_exe(tpath, sizeof(tpath)); bfdf = bfd_openr(tpath, NULL); - assert(bfdf); - assert(bfd_check_format(bfdf, bfd_object)); + if (bfdf == NULL) + abort(); + + if (!bfd_check_format(bfdf, bfd_object)) + abort(); s = open_memstream(&buf, &buf_size); if (!s) { @@ -1895,7 +1898,8 @@ static int symbol__disassemble_bpf(struct symbol *sym, #else disassemble = disassembler(bfdf); #endif - assert(disassemble); + if (disassemble == NULL) + abort(); fflush(s); do { diff --git a/tools/perf/util/bpf-filter.c b/tools/perf/util/bpf-filter.c index 0b30688d78a7..b51544996046 100644 --- a/tools/perf/util/bpf-filter.c +++ b/tools/perf/util/bpf-filter.c @@ -9,8 +9,8 @@ #include "util/evsel.h" #include "util/bpf-filter.h" -#include "util/bpf-filter-flex.h" -#include "util/bpf-filter-bison.h" +#include <util/bpf-filter-flex.h> +#include <util/bpf-filter-bison.h> #include "bpf_skel/sample-filter.h" #include "bpf_skel/sample_filter.skel.h" @@ -62,6 +62,16 @@ static int check_sample_flags(struct evsel *evsel, struct perf_bpf_filter_expr * if (evsel->core.attr.sample_type & expr->sample_flags) return 0; + if (expr->op == PBF_OP_GROUP_BEGIN) { + struct perf_bpf_filter_expr *group; + + list_for_each_entry(group, &expr->groups, list) { + if (check_sample_flags(evsel, group) < 0) + return -1; + } + return 0; + } + info = get_sample_info(expr->sample_flags); if (info == NULL) { pr_err("Error: %s event does not have sample flags %lx\n", diff --git a/tools/perf/util/bpf-filter.y b/tools/perf/util/bpf-filter.y index 07d6c7926c13..5dfa948fc986 100644 --- a/tools/perf/util/bpf-filter.y +++ b/tools/perf/util/bpf-filter.y @@ -9,6 +9,8 @@ #include <linux/list.h> #include "bpf-filter.h" +int perf_bpf_filter_lex(void); + static void perf_bpf_filter_error(struct list_head *expr __maybe_unused, char const *msg) { diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c deleted file mode 100644 index 44cde27d6389..000000000000 --- a/tools/perf/util/bpf-loader.c +++ /dev/null @@ -1,2110 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * bpf-loader.c - * - * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com> - * Copyright (C) 2015 Huawei Inc. - */ - -#include <linux/bpf.h> -#include <bpf/libbpf.h> -#include <bpf/bpf.h> -#include <linux/filter.h> -#include <linux/err.h> -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/zalloc.h> -#include <errno.h> -#include <stdlib.h> -#include "debug.h" -#include "evlist.h" -#include "bpf-loader.h" -#include "bpf-prologue.h" -#include "probe-event.h" -#include "probe-finder.h" // for MAX_PROBES -#include "parse-events.h" -#include "strfilter.h" -#include "util.h" -#include "llvm-utils.h" -#include "c++/clang-c.h" -#include "util/hashmap.h" -#include "asm/bug.h" - -#include <internal/xyarray.h> - -/* temporarily disable libbpf deprecation warnings */ -#pragma GCC diagnostic ignored "-Wdeprecated-declarations" - -static int libbpf_perf_print(enum libbpf_print_level level __attribute__((unused)), - const char *fmt, va_list args) -{ - return veprintf(1, verbose, pr_fmt(fmt), args); -} - -struct bpf_prog_priv { - bool is_tp; - char *sys_name; - char *evt_name; - struct perf_probe_event pev; - bool need_prologue; - struct bpf_insn *insns_buf; - int nr_types; - int *type_mapping; - int *prologue_fds; -}; - -struct bpf_perf_object { - struct list_head list; - struct bpf_object *obj; -}; - -struct bpf_preproc_result { - struct bpf_insn *new_insn_ptr; - int new_insn_cnt; -}; - -static LIST_HEAD(bpf_objects_list); -static struct hashmap *bpf_program_hash; -static struct hashmap *bpf_map_hash; - -static struct bpf_perf_object * -bpf_perf_object__next(struct bpf_perf_object *prev) -{ - if (!prev) { - if (list_empty(&bpf_objects_list)) - return NULL; - - return list_first_entry(&bpf_objects_list, struct bpf_perf_object, list); - } - if (list_is_last(&prev->list, &bpf_objects_list)) - return NULL; - - return list_next_entry(prev, list); -} - -#define bpf_perf_object__for_each(perf_obj, tmp) \ - for ((perf_obj) = bpf_perf_object__next(NULL), \ - (tmp) = bpf_perf_object__next(perf_obj); \ - (perf_obj) != NULL; \ - (perf_obj) = (tmp), (tmp) = bpf_perf_object__next(tmp)) - -static bool libbpf_initialized; -static int libbpf_sec_handler; - -static int bpf_perf_object__add(struct bpf_object *obj) -{ - struct bpf_perf_object *perf_obj = zalloc(sizeof(*perf_obj)); - - if (perf_obj) { - INIT_LIST_HEAD(&perf_obj->list); - perf_obj->obj = obj; - list_add_tail(&perf_obj->list, &bpf_objects_list); - } - return perf_obj ? 0 : -ENOMEM; -} - -static void *program_priv(const struct bpf_program *prog) -{ - void *priv; - - if (IS_ERR_OR_NULL(bpf_program_hash)) - return NULL; - if (!hashmap__find(bpf_program_hash, prog, &priv)) - return NULL; - return priv; -} - -static struct bpf_insn prologue_init_insn[] = { - BPF_MOV64_IMM(BPF_REG_2, 0), - BPF_MOV64_IMM(BPF_REG_3, 0), - BPF_MOV64_IMM(BPF_REG_4, 0), - BPF_MOV64_IMM(BPF_REG_5, 0), -}; - -static int libbpf_prog_prepare_load_fn(struct bpf_program *prog, - struct bpf_prog_load_opts *opts __maybe_unused, - long cookie __maybe_unused) -{ - size_t init_size_cnt = ARRAY_SIZE(prologue_init_insn); - size_t orig_insn_cnt, insn_cnt, init_size, orig_size; - struct bpf_prog_priv *priv = program_priv(prog); - const struct bpf_insn *orig_insn; - struct bpf_insn *insn; - - if (IS_ERR_OR_NULL(priv)) { - pr_debug("bpf: failed to get private field\n"); - return -BPF_LOADER_ERRNO__INTERNAL; - } - - if (!priv->need_prologue) - return 0; - - /* prepend initialization code to program instructions */ - orig_insn = bpf_program__insns(prog); - orig_insn_cnt = bpf_program__insn_cnt(prog); - init_size = init_size_cnt * sizeof(*insn); - orig_size = orig_insn_cnt * sizeof(*insn); - - insn_cnt = orig_insn_cnt + init_size_cnt; - insn = malloc(insn_cnt * sizeof(*insn)); - if (!insn) - return -ENOMEM; - - memcpy(insn, prologue_init_insn, init_size); - memcpy((char *) insn + init_size, orig_insn, orig_size); - bpf_program__set_insns(prog, insn, insn_cnt); - return 0; -} - -static int libbpf_init(void) -{ - LIBBPF_OPTS(libbpf_prog_handler_opts, handler_opts, - .prog_prepare_load_fn = libbpf_prog_prepare_load_fn, - ); - - if (libbpf_initialized) - return 0; - - libbpf_set_print(libbpf_perf_print); - libbpf_sec_handler = libbpf_register_prog_handler(NULL, BPF_PROG_TYPE_KPROBE, - 0, &handler_opts); - if (libbpf_sec_handler < 0) { - pr_debug("bpf: failed to register libbpf section handler: %d\n", - libbpf_sec_handler); - return -BPF_LOADER_ERRNO__INTERNAL; - } - libbpf_initialized = true; - return 0; -} - -struct bpf_object * -bpf__prepare_load_buffer(void *obj_buf, size_t obj_buf_sz, const char *name) -{ - LIBBPF_OPTS(bpf_object_open_opts, opts, .object_name = name); - struct bpf_object *obj; - int err; - - err = libbpf_init(); - if (err) - return ERR_PTR(err); - - obj = bpf_object__open_mem(obj_buf, obj_buf_sz, &opts); - if (IS_ERR_OR_NULL(obj)) { - pr_debug("bpf: failed to load buffer\n"); - return ERR_PTR(-EINVAL); - } - - if (bpf_perf_object__add(obj)) { - bpf_object__close(obj); - return ERR_PTR(-ENOMEM); - } - - return obj; -} - -static void bpf_perf_object__close(struct bpf_perf_object *perf_obj) -{ - list_del(&perf_obj->list); - bpf_object__close(perf_obj->obj); - free(perf_obj); -} - -struct bpf_object *bpf__prepare_load(const char *filename, bool source) -{ - LIBBPF_OPTS(bpf_object_open_opts, opts, .object_name = filename); - struct bpf_object *obj; - int err; - - err = libbpf_init(); - if (err) - return ERR_PTR(err); - - if (source) { - void *obj_buf; - size_t obj_buf_sz; - - perf_clang__init(); - err = perf_clang__compile_bpf(filename, &obj_buf, &obj_buf_sz); - perf_clang__cleanup(); - if (err) { - pr_debug("bpf: builtin compilation failed: %d, try external compiler\n", err); - err = llvm__compile_bpf(filename, &obj_buf, &obj_buf_sz); - if (err) - return ERR_PTR(-BPF_LOADER_ERRNO__COMPILE); - } else - pr_debug("bpf: successful builtin compilation\n"); - obj = bpf_object__open_mem(obj_buf, obj_buf_sz, &opts); - - if (!IS_ERR_OR_NULL(obj) && llvm_param.dump_obj) - llvm__dump_obj(filename, obj_buf, obj_buf_sz); - - free(obj_buf); - } else { - obj = bpf_object__open(filename); - } - - if (IS_ERR_OR_NULL(obj)) { - pr_debug("bpf: failed to load %s\n", filename); - return obj; - } - - if (bpf_perf_object__add(obj)) { - bpf_object__close(obj); - return ERR_PTR(-BPF_LOADER_ERRNO__COMPILE); - } - - return obj; -} - -static void close_prologue_programs(struct bpf_prog_priv *priv) -{ - struct perf_probe_event *pev; - int i, fd; - - if (!priv->need_prologue) - return; - pev = &priv->pev; - for (i = 0; i < pev->ntevs; i++) { - fd = priv->prologue_fds[i]; - if (fd != -1) - close(fd); - } -} - -static void -clear_prog_priv(const struct bpf_program *prog __maybe_unused, - void *_priv) -{ - struct bpf_prog_priv *priv = _priv; - - close_prologue_programs(priv); - cleanup_perf_probe_events(&priv->pev, 1); - zfree(&priv->insns_buf); - zfree(&priv->prologue_fds); - zfree(&priv->type_mapping); - zfree(&priv->sys_name); - zfree(&priv->evt_name); - free(priv); -} - -static void bpf_program_hash_free(void) -{ - struct hashmap_entry *cur; - size_t bkt; - - if (IS_ERR_OR_NULL(bpf_program_hash)) - return; - - hashmap__for_each_entry(bpf_program_hash, cur, bkt) - clear_prog_priv(cur->pkey, cur->pvalue); - - hashmap__free(bpf_program_hash); - bpf_program_hash = NULL; -} - -static void bpf_map_hash_free(void); - -void bpf__clear(void) -{ - struct bpf_perf_object *perf_obj, *tmp; - - bpf_perf_object__for_each(perf_obj, tmp) { - bpf__unprobe(perf_obj->obj); - bpf_perf_object__close(perf_obj); - } - - bpf_program_hash_free(); - bpf_map_hash_free(); -} - -static size_t ptr_hash(const long __key, void *ctx __maybe_unused) -{ - return __key; -} - -static bool ptr_equal(long key1, long key2, void *ctx __maybe_unused) -{ - return key1 == key2; -} - -static int program_set_priv(struct bpf_program *prog, void *priv) -{ - void *old_priv; - - /* - * Should not happen, we warn about it in the - * caller function - config_bpf_program - */ - if (IS_ERR(bpf_program_hash)) - return PTR_ERR(bpf_program_hash); - - if (!bpf_program_hash) { - bpf_program_hash = hashmap__new(ptr_hash, ptr_equal, NULL); - if (IS_ERR(bpf_program_hash)) - return PTR_ERR(bpf_program_hash); - } - - old_priv = program_priv(prog); - if (old_priv) { - clear_prog_priv(prog, old_priv); - return hashmap__set(bpf_program_hash, prog, priv, NULL, NULL); - } - return hashmap__add(bpf_program_hash, prog, priv); -} - -static int -prog_config__exec(const char *value, struct perf_probe_event *pev) -{ - pev->uprobes = true; - pev->target = strdup(value); - if (!pev->target) - return -ENOMEM; - return 0; -} - -static int -prog_config__module(const char *value, struct perf_probe_event *pev) -{ - pev->uprobes = false; - pev->target = strdup(value); - if (!pev->target) - return -ENOMEM; - return 0; -} - -static int -prog_config__bool(const char *value, bool *pbool, bool invert) -{ - int err; - bool bool_value; - - if (!pbool) - return -EINVAL; - - err = strtobool(value, &bool_value); - if (err) - return err; - - *pbool = invert ? !bool_value : bool_value; - return 0; -} - -static int -prog_config__inlines(const char *value, - struct perf_probe_event *pev __maybe_unused) -{ - return prog_config__bool(value, &probe_conf.no_inlines, true); -} - -static int -prog_config__force(const char *value, - struct perf_probe_event *pev __maybe_unused) -{ - return prog_config__bool(value, &probe_conf.force_add, false); -} - -static struct { - const char *key; - const char *usage; - const char *desc; - int (*func)(const char *, struct perf_probe_event *); -} bpf_prog_config_terms[] = { - { - .key = "exec", - .usage = "exec=<full path of file>", - .desc = "Set uprobe target", - .func = prog_config__exec, - }, - { - .key = "module", - .usage = "module=<module name> ", - .desc = "Set kprobe module", - .func = prog_config__module, - }, - { - .key = "inlines", - .usage = "inlines=[yes|no] ", - .desc = "Probe at inline symbol", - .func = prog_config__inlines, - }, - { - .key = "force", - .usage = "force=[yes|no] ", - .desc = "Forcibly add events with existing name", - .func = prog_config__force, - }, -}; - -static int -do_prog_config(const char *key, const char *value, - struct perf_probe_event *pev) -{ - unsigned int i; - - pr_debug("config bpf program: %s=%s\n", key, value); - for (i = 0; i < ARRAY_SIZE(bpf_prog_config_terms); i++) - if (strcmp(key, bpf_prog_config_terms[i].key) == 0) - return bpf_prog_config_terms[i].func(value, pev); - - pr_debug("BPF: ERROR: invalid program config option: %s=%s\n", - key, value); - - pr_debug("\nHint: Valid options are:\n"); - for (i = 0; i < ARRAY_SIZE(bpf_prog_config_terms); i++) - pr_debug("\t%s:\t%s\n", bpf_prog_config_terms[i].usage, - bpf_prog_config_terms[i].desc); - pr_debug("\n"); - - return -BPF_LOADER_ERRNO__PROGCONF_TERM; -} - -static const char * -parse_prog_config_kvpair(const char *config_str, struct perf_probe_event *pev) -{ - char *text = strdup(config_str); - char *sep, *line; - const char *main_str = NULL; - int err = 0; - - if (!text) { - pr_debug("Not enough memory: dup config_str failed\n"); - return ERR_PTR(-ENOMEM); - } - - line = text; - while ((sep = strchr(line, ';'))) { - char *equ; - - *sep = '\0'; - equ = strchr(line, '='); - if (!equ) { - pr_warning("WARNING: invalid config in BPF object: %s\n", - line); - pr_warning("\tShould be 'key=value'.\n"); - goto nextline; - } - *equ = '\0'; - - err = do_prog_config(line, equ + 1, pev); - if (err) - break; -nextline: - line = sep + 1; - } - - if (!err) - main_str = config_str + (line - text); - free(text); - - return err ? ERR_PTR(err) : main_str; -} - -static int -parse_prog_config(const char *config_str, const char **p_main_str, - bool *is_tp, struct perf_probe_event *pev) -{ - int err; - const char *main_str = parse_prog_config_kvpair(config_str, pev); - - if (IS_ERR(main_str)) - return PTR_ERR(main_str); - - *p_main_str = main_str; - if (!strchr(main_str, '=')) { - /* Is a tracepoint event? */ - const char *s = strchr(main_str, ':'); - - if (!s) { - pr_debug("bpf: '%s' is not a valid tracepoint\n", - config_str); - return -BPF_LOADER_ERRNO__CONFIG; - } - - *is_tp = true; - return 0; - } - - *is_tp = false; - err = parse_perf_probe_command(main_str, pev); - if (err < 0) { - pr_debug("bpf: '%s' is not a valid config string\n", - config_str); - /* parse failed, don't need clear pev. */ - return -BPF_LOADER_ERRNO__CONFIG; - } - return 0; -} - -static int -config_bpf_program(struct bpf_program *prog) -{ - struct perf_probe_event *pev = NULL; - struct bpf_prog_priv *priv = NULL; - const char *config_str, *main_str; - bool is_tp = false; - int err; - - /* Initialize per-program probing setting */ - probe_conf.no_inlines = false; - probe_conf.force_add = false; - - priv = calloc(sizeof(*priv), 1); - if (!priv) { - pr_debug("bpf: failed to alloc priv\n"); - return -ENOMEM; - } - pev = &priv->pev; - - config_str = bpf_program__section_name(prog); - pr_debug("bpf: config program '%s'\n", config_str); - err = parse_prog_config(config_str, &main_str, &is_tp, pev); - if (err) - goto errout; - - if (is_tp) { - char *s = strchr(main_str, ':'); - - priv->is_tp = true; - priv->sys_name = strndup(main_str, s - main_str); - priv->evt_name = strdup(s + 1); - goto set_priv; - } - - if (pev->group && strcmp(pev->group, PERF_BPF_PROBE_GROUP)) { - pr_debug("bpf: '%s': group for event is set and not '%s'.\n", - config_str, PERF_BPF_PROBE_GROUP); - err = -BPF_LOADER_ERRNO__GROUP; - goto errout; - } else if (!pev->group) - pev->group = strdup(PERF_BPF_PROBE_GROUP); - - if (!pev->group) { - pr_debug("bpf: strdup failed\n"); - err = -ENOMEM; - goto errout; - } - - if (!pev->event) { - pr_debug("bpf: '%s': event name is missing. Section name should be 'key=value'\n", - config_str); - err = -BPF_LOADER_ERRNO__EVENTNAME; - goto errout; - } - pr_debug("bpf: config '%s' is ok\n", config_str); - -set_priv: - err = program_set_priv(prog, priv); - if (err) { - pr_debug("Failed to set priv for program '%s'\n", config_str); - goto errout; - } - - return 0; - -errout: - if (pev) - clear_perf_probe_event(pev); - free(priv); - return err; -} - -static int bpf__prepare_probe(void) -{ - static int err = 0; - static bool initialized = false; - - /* - * Make err static, so if init failed the first, bpf__prepare_probe() - * fails each time without calling init_probe_symbol_maps multiple - * times. - */ - if (initialized) - return err; - - initialized = true; - err = init_probe_symbol_maps(false); - if (err < 0) - pr_debug("Failed to init_probe_symbol_maps\n"); - probe_conf.max_probes = MAX_PROBES; - return err; -} - -static int -preproc_gen_prologue(struct bpf_program *prog, int n, - const struct bpf_insn *orig_insns, int orig_insns_cnt, - struct bpf_preproc_result *res) -{ - struct bpf_prog_priv *priv = program_priv(prog); - struct probe_trace_event *tev; - struct perf_probe_event *pev; - struct bpf_insn *buf; - size_t prologue_cnt = 0; - int i, err; - - if (IS_ERR_OR_NULL(priv) || priv->is_tp) - goto errout; - - pev = &priv->pev; - - if (n < 0 || n >= priv->nr_types) - goto errout; - - /* Find a tev belongs to that type */ - for (i = 0; i < pev->ntevs; i++) { - if (priv->type_mapping[i] == n) - break; - } - - if (i >= pev->ntevs) { - pr_debug("Internal error: prologue type %d not found\n", n); - return -BPF_LOADER_ERRNO__PROLOGUE; - } - - tev = &pev->tevs[i]; - - buf = priv->insns_buf; - err = bpf__gen_prologue(tev->args, tev->nargs, - buf, &prologue_cnt, - BPF_MAXINSNS - orig_insns_cnt); - if (err) { - const char *title; - - title = bpf_program__section_name(prog); - pr_debug("Failed to generate prologue for program %s\n", - title); - return err; - } - - memcpy(&buf[prologue_cnt], orig_insns, - sizeof(struct bpf_insn) * orig_insns_cnt); - - res->new_insn_ptr = buf; - res->new_insn_cnt = prologue_cnt + orig_insns_cnt; - return 0; - -errout: - pr_debug("Internal error in preproc_gen_prologue\n"); - return -BPF_LOADER_ERRNO__PROLOGUE; -} - -/* - * compare_tev_args is reflexive, transitive and antisymmetric. - * I can proof it but this margin is too narrow to contain. - */ -static int compare_tev_args(const void *ptev1, const void *ptev2) -{ - int i, ret; - const struct probe_trace_event *tev1 = - *(const struct probe_trace_event **)ptev1; - const struct probe_trace_event *tev2 = - *(const struct probe_trace_event **)ptev2; - - ret = tev2->nargs - tev1->nargs; - if (ret) - return ret; - - for (i = 0; i < tev1->nargs; i++) { - struct probe_trace_arg *arg1, *arg2; - struct probe_trace_arg_ref *ref1, *ref2; - - arg1 = &tev1->args[i]; - arg2 = &tev2->args[i]; - - ret = strcmp(arg1->value, arg2->value); - if (ret) - return ret; - - ref1 = arg1->ref; - ref2 = arg2->ref; - - while (ref1 && ref2) { - ret = ref2->offset - ref1->offset; - if (ret) - return ret; - - ref1 = ref1->next; - ref2 = ref2->next; - } - - if (ref1 || ref2) - return ref2 ? 1 : -1; - } - - return 0; -} - -/* - * Assign a type number to each tevs in a pev. - * mapping is an array with same slots as tevs in that pev. - * nr_types will be set to number of types. - */ -static int map_prologue(struct perf_probe_event *pev, int *mapping, - int *nr_types) -{ - int i, type = 0; - struct probe_trace_event **ptevs; - - size_t array_sz = sizeof(*ptevs) * pev->ntevs; - - ptevs = malloc(array_sz); - if (!ptevs) { - pr_debug("Not enough memory: alloc ptevs failed\n"); - return -ENOMEM; - } - - pr_debug("In map_prologue, ntevs=%d\n", pev->ntevs); - for (i = 0; i < pev->ntevs; i++) - ptevs[i] = &pev->tevs[i]; - - qsort(ptevs, pev->ntevs, sizeof(*ptevs), - compare_tev_args); - - for (i = 0; i < pev->ntevs; i++) { - int n; - - n = ptevs[i] - pev->tevs; - if (i == 0) { - mapping[n] = type; - pr_debug("mapping[%d]=%d\n", n, type); - continue; - } - - if (compare_tev_args(ptevs + i, ptevs + i - 1) == 0) - mapping[n] = type; - else - mapping[n] = ++type; - - pr_debug("mapping[%d]=%d\n", n, mapping[n]); - } - free(ptevs); - *nr_types = type + 1; - - return 0; -} - -static int hook_load_preprocessor(struct bpf_program *prog) -{ - struct bpf_prog_priv *priv = program_priv(prog); - struct perf_probe_event *pev; - bool need_prologue = false; - int i; - - if (IS_ERR_OR_NULL(priv)) { - pr_debug("Internal error when hook preprocessor\n"); - return -BPF_LOADER_ERRNO__INTERNAL; - } - - if (priv->is_tp) { - priv->need_prologue = false; - return 0; - } - - pev = &priv->pev; - for (i = 0; i < pev->ntevs; i++) { - struct probe_trace_event *tev = &pev->tevs[i]; - - if (tev->nargs > 0) { - need_prologue = true; - break; - } - } - - /* - * Since all tevs don't have argument, we don't need generate - * prologue. - */ - if (!need_prologue) { - priv->need_prologue = false; - return 0; - } - - priv->need_prologue = true; - priv->insns_buf = malloc(sizeof(struct bpf_insn) * BPF_MAXINSNS); - if (!priv->insns_buf) { - pr_debug("Not enough memory: alloc insns_buf failed\n"); - return -ENOMEM; - } - - priv->prologue_fds = malloc(sizeof(int) * pev->ntevs); - if (!priv->prologue_fds) { - pr_debug("Not enough memory: alloc prologue fds failed\n"); - return -ENOMEM; - } - memset(priv->prologue_fds, -1, sizeof(int) * pev->ntevs); - - priv->type_mapping = malloc(sizeof(int) * pev->ntevs); - if (!priv->type_mapping) { - pr_debug("Not enough memory: alloc type_mapping failed\n"); - return -ENOMEM; - } - memset(priv->type_mapping, -1, - sizeof(int) * pev->ntevs); - - return map_prologue(pev, priv->type_mapping, &priv->nr_types); -} - -int bpf__probe(struct bpf_object *obj) -{ - int err = 0; - struct bpf_program *prog; - struct bpf_prog_priv *priv; - struct perf_probe_event *pev; - - err = bpf__prepare_probe(); - if (err) { - pr_debug("bpf__prepare_probe failed\n"); - return err; - } - - bpf_object__for_each_program(prog, obj) { - err = config_bpf_program(prog); - if (err) - goto out; - - priv = program_priv(prog); - if (IS_ERR_OR_NULL(priv)) { - if (!priv) - err = -BPF_LOADER_ERRNO__INTERNAL; - else - err = PTR_ERR(priv); - goto out; - } - - if (priv->is_tp) { - bpf_program__set_type(prog, BPF_PROG_TYPE_TRACEPOINT); - continue; - } - - bpf_program__set_type(prog, BPF_PROG_TYPE_KPROBE); - pev = &priv->pev; - - err = convert_perf_probe_events(pev, 1); - if (err < 0) { - pr_debug("bpf_probe: failed to convert perf probe events\n"); - goto out; - } - - err = apply_perf_probe_events(pev, 1); - if (err < 0) { - pr_debug("bpf_probe: failed to apply perf probe events\n"); - goto out; - } - - /* - * After probing, let's consider prologue, which - * adds program fetcher to BPF programs. - * - * hook_load_preprocessor() hooks pre-processor - * to bpf_program, let it generate prologue - * dynamically during loading. - */ - err = hook_load_preprocessor(prog); - if (err) - goto out; - } -out: - return err < 0 ? err : 0; -} - -#define EVENTS_WRITE_BUFSIZE 4096 -int bpf__unprobe(struct bpf_object *obj) -{ - int err, ret = 0; - struct bpf_program *prog; - - bpf_object__for_each_program(prog, obj) { - struct bpf_prog_priv *priv = program_priv(prog); - int i; - - if (IS_ERR_OR_NULL(priv) || priv->is_tp) - continue; - - for (i = 0; i < priv->pev.ntevs; i++) { - struct probe_trace_event *tev = &priv->pev.tevs[i]; - char name_buf[EVENTS_WRITE_BUFSIZE]; - struct strfilter *delfilter; - - snprintf(name_buf, EVENTS_WRITE_BUFSIZE, - "%s:%s", tev->group, tev->event); - name_buf[EVENTS_WRITE_BUFSIZE - 1] = '\0'; - - delfilter = strfilter__new(name_buf, NULL); - if (!delfilter) { - pr_debug("Failed to create filter for unprobing\n"); - ret = -ENOMEM; - continue; - } - - err = del_perf_probe_events(delfilter); - strfilter__delete(delfilter); - if (err) { - pr_debug("Failed to delete %s\n", name_buf); - ret = err; - continue; - } - } - } - return ret; -} - -static int bpf_object__load_prologue(struct bpf_object *obj) -{ - int init_cnt = ARRAY_SIZE(prologue_init_insn); - const struct bpf_insn *orig_insns; - struct bpf_preproc_result res; - struct perf_probe_event *pev; - struct bpf_program *prog; - int orig_insns_cnt; - - bpf_object__for_each_program(prog, obj) { - struct bpf_prog_priv *priv = program_priv(prog); - int err, i, fd; - - if (IS_ERR_OR_NULL(priv)) { - pr_debug("bpf: failed to get private field\n"); - return -BPF_LOADER_ERRNO__INTERNAL; - } - - if (!priv->need_prologue) - continue; - - /* - * For each program that needs prologue we do following: - * - * - take its current instructions and use them - * to generate the new code with prologue - * - load new instructions with bpf_prog_load - * and keep the fd in prologue_fds - * - new fd will be used in bpf__foreach_event - * to connect this program with perf evsel - */ - orig_insns = bpf_program__insns(prog); - orig_insns_cnt = bpf_program__insn_cnt(prog); - - pev = &priv->pev; - for (i = 0; i < pev->ntevs; i++) { - /* - * Skipping artificall prologue_init_insn instructions - * (init_cnt), so the prologue can be generated instead - * of them. - */ - err = preproc_gen_prologue(prog, i, - orig_insns + init_cnt, - orig_insns_cnt - init_cnt, - &res); - if (err) - return err; - - fd = bpf_prog_load(bpf_program__get_type(prog), - bpf_program__name(prog), "GPL", - res.new_insn_ptr, - res.new_insn_cnt, NULL); - if (fd < 0) { - char bf[128]; - - libbpf_strerror(-errno, bf, sizeof(bf)); - pr_debug("bpf: load objects with prologue failed: err=%d: (%s)\n", - -errno, bf); - return -errno; - } - priv->prologue_fds[i] = fd; - } - /* - * We no longer need the original program, - * we can unload it. - */ - bpf_program__unload(prog); - } - return 0; -} - -int bpf__load(struct bpf_object *obj) -{ - int err; - - err = bpf_object__load(obj); - if (err) { - char bf[128]; - libbpf_strerror(err, bf, sizeof(bf)); - pr_debug("bpf: load objects failed: err=%d: (%s)\n", err, bf); - return err; - } - return bpf_object__load_prologue(obj); -} - -int bpf__foreach_event(struct bpf_object *obj, - bpf_prog_iter_callback_t func, - void *arg) -{ - struct bpf_program *prog; - int err; - - bpf_object__for_each_program(prog, obj) { - struct bpf_prog_priv *priv = program_priv(prog); - struct probe_trace_event *tev; - struct perf_probe_event *pev; - int i, fd; - - if (IS_ERR_OR_NULL(priv)) { - pr_debug("bpf: failed to get private field\n"); - return -BPF_LOADER_ERRNO__INTERNAL; - } - - if (priv->is_tp) { - fd = bpf_program__fd(prog); - err = (*func)(priv->sys_name, priv->evt_name, fd, obj, arg); - if (err) { - pr_debug("bpf: tracepoint call back failed, stop iterate\n"); - return err; - } - continue; - } - - pev = &priv->pev; - for (i = 0; i < pev->ntevs; i++) { - tev = &pev->tevs[i]; - - if (priv->need_prologue) - fd = priv->prologue_fds[i]; - else - fd = bpf_program__fd(prog); - - if (fd < 0) { - pr_debug("bpf: failed to get file descriptor\n"); - return fd; - } - - err = (*func)(tev->group, tev->event, fd, obj, arg); - if (err) { - pr_debug("bpf: call back failed, stop iterate\n"); - return err; - } - } - } - return 0; -} - -enum bpf_map_op_type { - BPF_MAP_OP_SET_VALUE, - BPF_MAP_OP_SET_EVSEL, -}; - -enum bpf_map_key_type { - BPF_MAP_KEY_ALL, - BPF_MAP_KEY_RANGES, -}; - -struct bpf_map_op { - struct list_head list; - enum bpf_map_op_type op_type; - enum bpf_map_key_type key_type; - union { - struct parse_events_array array; - } k; - union { - u64 value; - struct evsel *evsel; - } v; -}; - -struct bpf_map_priv { - struct list_head ops_list; -}; - -static void -bpf_map_op__delete(struct bpf_map_op *op) -{ - if (!list_empty(&op->list)) - list_del_init(&op->list); - if (op->key_type == BPF_MAP_KEY_RANGES) - parse_events__clear_array(&op->k.array); - free(op); -} - -static void -bpf_map_priv__purge(struct bpf_map_priv *priv) -{ - struct bpf_map_op *pos, *n; - - list_for_each_entry_safe(pos, n, &priv->ops_list, list) { - list_del_init(&pos->list); - bpf_map_op__delete(pos); - } -} - -static void -bpf_map_priv__clear(const struct bpf_map *map __maybe_unused, - void *_priv) -{ - struct bpf_map_priv *priv = _priv; - - bpf_map_priv__purge(priv); - free(priv); -} - -static void *map_priv(const struct bpf_map *map) -{ - void *priv; - - if (IS_ERR_OR_NULL(bpf_map_hash)) - return NULL; - if (!hashmap__find(bpf_map_hash, map, &priv)) - return NULL; - return priv; -} - -static void bpf_map_hash_free(void) -{ - struct hashmap_entry *cur; - size_t bkt; - - if (IS_ERR_OR_NULL(bpf_map_hash)) - return; - - hashmap__for_each_entry(bpf_map_hash, cur, bkt) - bpf_map_priv__clear(cur->pkey, cur->pvalue); - - hashmap__free(bpf_map_hash); - bpf_map_hash = NULL; -} - -static int map_set_priv(struct bpf_map *map, void *priv) -{ - void *old_priv; - - if (WARN_ON_ONCE(IS_ERR(bpf_map_hash))) - return PTR_ERR(bpf_program_hash); - - if (!bpf_map_hash) { - bpf_map_hash = hashmap__new(ptr_hash, ptr_equal, NULL); - if (IS_ERR(bpf_map_hash)) - return PTR_ERR(bpf_map_hash); - } - - old_priv = map_priv(map); - if (old_priv) { - bpf_map_priv__clear(map, old_priv); - return hashmap__set(bpf_map_hash, map, priv, NULL, NULL); - } - return hashmap__add(bpf_map_hash, map, priv); -} - -static int -bpf_map_op_setkey(struct bpf_map_op *op, struct parse_events_term *term) -{ - op->key_type = BPF_MAP_KEY_ALL; - if (!term) - return 0; - - if (term->array.nr_ranges) { - size_t memsz = term->array.nr_ranges * - sizeof(op->k.array.ranges[0]); - - op->k.array.ranges = memdup(term->array.ranges, memsz); - if (!op->k.array.ranges) { - pr_debug("Not enough memory to alloc indices for map\n"); - return -ENOMEM; - } - op->key_type = BPF_MAP_KEY_RANGES; - op->k.array.nr_ranges = term->array.nr_ranges; - } - return 0; -} - -static struct bpf_map_op * -bpf_map_op__new(struct parse_events_term *term) -{ - struct bpf_map_op *op; - int err; - - op = zalloc(sizeof(*op)); - if (!op) { - pr_debug("Failed to alloc bpf_map_op\n"); - return ERR_PTR(-ENOMEM); - } - INIT_LIST_HEAD(&op->list); - - err = bpf_map_op_setkey(op, term); - if (err) { - free(op); - return ERR_PTR(err); - } - return op; -} - -static struct bpf_map_op * -bpf_map_op__clone(struct bpf_map_op *op) -{ - struct bpf_map_op *newop; - - newop = memdup(op, sizeof(*op)); - if (!newop) { - pr_debug("Failed to alloc bpf_map_op\n"); - return NULL; - } - - INIT_LIST_HEAD(&newop->list); - if (op->key_type == BPF_MAP_KEY_RANGES) { - size_t memsz = op->k.array.nr_ranges * - sizeof(op->k.array.ranges[0]); - - newop->k.array.ranges = memdup(op->k.array.ranges, memsz); - if (!newop->k.array.ranges) { - pr_debug("Failed to alloc indices for map\n"); - free(newop); - return NULL; - } - } - - return newop; -} - -static struct bpf_map_priv * -bpf_map_priv__clone(struct bpf_map_priv *priv) -{ - struct bpf_map_priv *newpriv; - struct bpf_map_op *pos, *newop; - - newpriv = zalloc(sizeof(*newpriv)); - if (!newpriv) { - pr_debug("Not enough memory to alloc map private\n"); - return NULL; - } - INIT_LIST_HEAD(&newpriv->ops_list); - - list_for_each_entry(pos, &priv->ops_list, list) { - newop = bpf_map_op__clone(pos); - if (!newop) { - bpf_map_priv__purge(newpriv); - return NULL; - } - list_add_tail(&newop->list, &newpriv->ops_list); - } - - return newpriv; -} - -static int -bpf_map__add_op(struct bpf_map *map, struct bpf_map_op *op) -{ - const char *map_name = bpf_map__name(map); - struct bpf_map_priv *priv = map_priv(map); - - if (IS_ERR(priv)) { - pr_debug("Failed to get private from map %s\n", map_name); - return PTR_ERR(priv); - } - - if (!priv) { - priv = zalloc(sizeof(*priv)); - if (!priv) { - pr_debug("Not enough memory to alloc map private\n"); - return -ENOMEM; - } - INIT_LIST_HEAD(&priv->ops_list); - - if (map_set_priv(map, priv)) { - free(priv); - return -BPF_LOADER_ERRNO__INTERNAL; - } - } - - list_add_tail(&op->list, &priv->ops_list); - return 0; -} - -static struct bpf_map_op * -bpf_map__add_newop(struct bpf_map *map, struct parse_events_term *term) -{ - struct bpf_map_op *op; - int err; - - op = bpf_map_op__new(term); - if (IS_ERR(op)) - return op; - - err = bpf_map__add_op(map, op); - if (err) { - bpf_map_op__delete(op); - return ERR_PTR(err); - } - return op; -} - -static int -__bpf_map__config_value(struct bpf_map *map, - struct parse_events_term *term) -{ - struct bpf_map_op *op; - const char *map_name = bpf_map__name(map); - - if (!map) { - pr_debug("Map '%s' is invalid\n", map_name); - return -BPF_LOADER_ERRNO__INTERNAL; - } - - if (bpf_map__type(map) != BPF_MAP_TYPE_ARRAY) { - pr_debug("Map %s type is not BPF_MAP_TYPE_ARRAY\n", - map_name); - return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE; - } - if (bpf_map__key_size(map) < sizeof(unsigned int)) { - pr_debug("Map %s has incorrect key size\n", map_name); - return -BPF_LOADER_ERRNO__OBJCONF_MAP_KEYSIZE; - } - switch (bpf_map__value_size(map)) { - case 1: - case 2: - case 4: - case 8: - break; - default: - pr_debug("Map %s has incorrect value size\n", map_name); - return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUESIZE; - } - - op = bpf_map__add_newop(map, term); - if (IS_ERR(op)) - return PTR_ERR(op); - op->op_type = BPF_MAP_OP_SET_VALUE; - op->v.value = term->val.num; - return 0; -} - -static int -bpf_map__config_value(struct bpf_map *map, - struct parse_events_term *term, - struct evlist *evlist __maybe_unused) -{ - if (!term->err_val) { - pr_debug("Config value not set\n"); - return -BPF_LOADER_ERRNO__OBJCONF_CONF; - } - - if (term->type_val != PARSE_EVENTS__TERM_TYPE_NUM) { - pr_debug("ERROR: wrong value type for 'value'\n"); - return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE; - } - - return __bpf_map__config_value(map, term); -} - -static int -__bpf_map__config_event(struct bpf_map *map, - struct parse_events_term *term, - struct evlist *evlist) -{ - struct bpf_map_op *op; - const char *map_name = bpf_map__name(map); - struct evsel *evsel = evlist__find_evsel_by_str(evlist, term->val.str); - - if (!evsel) { - pr_debug("Event (for '%s') '%s' doesn't exist\n", - map_name, term->val.str); - return -BPF_LOADER_ERRNO__OBJCONF_MAP_NOEVT; - } - - if (!map) { - pr_debug("Map '%s' is invalid\n", map_name); - return PTR_ERR(map); - } - - /* - * No need to check key_size and value_size: - * kernel has already checked them. - */ - if (bpf_map__type(map) != BPF_MAP_TYPE_PERF_EVENT_ARRAY) { - pr_debug("Map %s type is not BPF_MAP_TYPE_PERF_EVENT_ARRAY\n", - map_name); - return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE; - } - - op = bpf_map__add_newop(map, term); - if (IS_ERR(op)) - return PTR_ERR(op); - op->op_type = BPF_MAP_OP_SET_EVSEL; - op->v.evsel = evsel; - return 0; -} - -static int -bpf_map__config_event(struct bpf_map *map, - struct parse_events_term *term, - struct evlist *evlist) -{ - if (!term->err_val) { - pr_debug("Config value not set\n"); - return -BPF_LOADER_ERRNO__OBJCONF_CONF; - } - - if (term->type_val != PARSE_EVENTS__TERM_TYPE_STR) { - pr_debug("ERROR: wrong value type for 'event'\n"); - return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE; - } - - return __bpf_map__config_event(map, term, evlist); -} - -struct bpf_obj_config__map_func { - const char *config_opt; - int (*config_func)(struct bpf_map *, struct parse_events_term *, - struct evlist *); -}; - -struct bpf_obj_config__map_func bpf_obj_config__map_funcs[] = { - {"value", bpf_map__config_value}, - {"event", bpf_map__config_event}, -}; - -static int -config_map_indices_range_check(struct parse_events_term *term, - struct bpf_map *map, - const char *map_name) -{ - struct parse_events_array *array = &term->array; - unsigned int i; - - if (!array->nr_ranges) - return 0; - if (!array->ranges) { - pr_debug("ERROR: map %s: array->nr_ranges is %d but range array is NULL\n", - map_name, (int)array->nr_ranges); - return -BPF_LOADER_ERRNO__INTERNAL; - } - - if (!map) { - pr_debug("Map '%s' is invalid\n", map_name); - return -BPF_LOADER_ERRNO__INTERNAL; - } - - for (i = 0; i < array->nr_ranges; i++) { - unsigned int start = array->ranges[i].start; - size_t length = array->ranges[i].length; - unsigned int idx = start + length - 1; - - if (idx >= bpf_map__max_entries(map)) { - pr_debug("ERROR: index %d too large\n", idx); - return -BPF_LOADER_ERRNO__OBJCONF_MAP_IDX2BIG; - } - } - return 0; -} - -static int -bpf__obj_config_map(struct bpf_object *obj, - struct parse_events_term *term, - struct evlist *evlist, - int *key_scan_pos) -{ - /* key is "map:<mapname>.<config opt>" */ - char *map_name = strdup(term->config + sizeof("map:") - 1); - struct bpf_map *map; - int err = -BPF_LOADER_ERRNO__OBJCONF_OPT; - char *map_opt; - size_t i; - - if (!map_name) - return -ENOMEM; - - map_opt = strchr(map_name, '.'); - if (!map_opt) { - pr_debug("ERROR: Invalid map config: %s\n", map_name); - goto out; - } - - *map_opt++ = '\0'; - if (*map_opt == '\0') { - pr_debug("ERROR: Invalid map option: %s\n", term->config); - goto out; - } - - map = bpf_object__find_map_by_name(obj, map_name); - if (!map) { - pr_debug("ERROR: Map %s doesn't exist\n", map_name); - err = -BPF_LOADER_ERRNO__OBJCONF_MAP_NOTEXIST; - goto out; - } - - *key_scan_pos += strlen(map_opt); - err = config_map_indices_range_check(term, map, map_name); - if (err) - goto out; - *key_scan_pos -= strlen(map_opt); - - for (i = 0; i < ARRAY_SIZE(bpf_obj_config__map_funcs); i++) { - struct bpf_obj_config__map_func *func = - &bpf_obj_config__map_funcs[i]; - - if (strcmp(map_opt, func->config_opt) == 0) { - err = func->config_func(map, term, evlist); - goto out; - } - } - - pr_debug("ERROR: Invalid map config option '%s'\n", map_opt); - err = -BPF_LOADER_ERRNO__OBJCONF_MAP_OPT; -out: - if (!err) - *key_scan_pos += strlen(map_opt); - - free(map_name); - return err; -} - -int bpf__config_obj(struct bpf_object *obj, - struct parse_events_term *term, - struct evlist *evlist, - int *error_pos) -{ - int key_scan_pos = 0; - int err; - - if (!obj || !term || !term->config) - return -EINVAL; - - if (strstarts(term->config, "map:")) { - key_scan_pos = sizeof("map:") - 1; - err = bpf__obj_config_map(obj, term, evlist, &key_scan_pos); - goto out; - } - err = -BPF_LOADER_ERRNO__OBJCONF_OPT; -out: - if (error_pos) - *error_pos = key_scan_pos; - return err; - -} - -typedef int (*map_config_func_t)(const char *name, int map_fd, - const struct bpf_map *map, - struct bpf_map_op *op, - void *pkey, void *arg); - -static int -foreach_key_array_all(map_config_func_t func, - void *arg, const char *name, - int map_fd, const struct bpf_map *map, - struct bpf_map_op *op) -{ - unsigned int i; - int err; - - for (i = 0; i < bpf_map__max_entries(map); i++) { - err = func(name, map_fd, map, op, &i, arg); - if (err) { - pr_debug("ERROR: failed to insert value to %s[%u]\n", - name, i); - return err; - } - } - return 0; -} - -static int -foreach_key_array_ranges(map_config_func_t func, void *arg, - const char *name, int map_fd, - const struct bpf_map *map, - struct bpf_map_op *op) -{ - unsigned int i, j; - int err; - - for (i = 0; i < op->k.array.nr_ranges; i++) { - unsigned int start = op->k.array.ranges[i].start; - size_t length = op->k.array.ranges[i].length; - - for (j = 0; j < length; j++) { - unsigned int idx = start + j; - - err = func(name, map_fd, map, op, &idx, arg); - if (err) { - pr_debug("ERROR: failed to insert value to %s[%u]\n", - name, idx); - return err; - } - } - } - return 0; -} - -static int -bpf_map_config_foreach_key(struct bpf_map *map, - map_config_func_t func, - void *arg) -{ - int err, map_fd, type; - struct bpf_map_op *op; - const char *name = bpf_map__name(map); - struct bpf_map_priv *priv = map_priv(map); - - if (IS_ERR(priv)) { - pr_debug("ERROR: failed to get private from map %s\n", name); - return -BPF_LOADER_ERRNO__INTERNAL; - } - if (!priv || list_empty(&priv->ops_list)) { - pr_debug("INFO: nothing to config for map %s\n", name); - return 0; - } - - if (!map) { - pr_debug("Map '%s' is invalid\n", name); - return -BPF_LOADER_ERRNO__INTERNAL; - } - map_fd = bpf_map__fd(map); - if (map_fd < 0) { - pr_debug("ERROR: failed to get fd from map %s\n", name); - return map_fd; - } - - type = bpf_map__type(map); - list_for_each_entry(op, &priv->ops_list, list) { - switch (type) { - case BPF_MAP_TYPE_ARRAY: - case BPF_MAP_TYPE_PERF_EVENT_ARRAY: - switch (op->key_type) { - case BPF_MAP_KEY_ALL: - err = foreach_key_array_all(func, arg, name, - map_fd, map, op); - break; - case BPF_MAP_KEY_RANGES: - err = foreach_key_array_ranges(func, arg, name, - map_fd, map, op); - break; - default: - pr_debug("ERROR: keytype for map '%s' invalid\n", - name); - return -BPF_LOADER_ERRNO__INTERNAL; - } - if (err) - return err; - break; - default: - pr_debug("ERROR: type of '%s' incorrect\n", name); - return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE; - } - } - - return 0; -} - -static int -apply_config_value_for_key(int map_fd, void *pkey, - size_t val_size, u64 val) -{ - int err = 0; - - switch (val_size) { - case 1: { - u8 _val = (u8)(val); - err = bpf_map_update_elem(map_fd, pkey, &_val, BPF_ANY); - break; - } - case 2: { - u16 _val = (u16)(val); - err = bpf_map_update_elem(map_fd, pkey, &_val, BPF_ANY); - break; - } - case 4: { - u32 _val = (u32)(val); - err = bpf_map_update_elem(map_fd, pkey, &_val, BPF_ANY); - break; - } - case 8: { - err = bpf_map_update_elem(map_fd, pkey, &val, BPF_ANY); - break; - } - default: - pr_debug("ERROR: invalid value size\n"); - return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUESIZE; - } - if (err && errno) - err = -errno; - return err; -} - -static int -apply_config_evsel_for_key(const char *name, int map_fd, void *pkey, - struct evsel *evsel) -{ - struct xyarray *xy = evsel->core.fd; - struct perf_event_attr *attr; - unsigned int key, events; - bool check_pass = false; - int *evt_fd; - int err; - - if (!xy) { - pr_debug("ERROR: evsel not ready for map %s\n", name); - return -BPF_LOADER_ERRNO__INTERNAL; - } - - if (xy->row_size / xy->entry_size != 1) { - pr_debug("ERROR: Dimension of target event is incorrect for map %s\n", - name); - return -BPF_LOADER_ERRNO__OBJCONF_MAP_EVTDIM; - } - - attr = &evsel->core.attr; - if (attr->inherit) { - pr_debug("ERROR: Can't put inherit event into map %s\n", name); - return -BPF_LOADER_ERRNO__OBJCONF_MAP_EVTINH; - } - - if (evsel__is_bpf_output(evsel)) - check_pass = true; - if (attr->type == PERF_TYPE_RAW) - check_pass = true; - if (attr->type == PERF_TYPE_HARDWARE) - check_pass = true; - if (!check_pass) { - pr_debug("ERROR: Event type is wrong for map %s\n", name); - return -BPF_LOADER_ERRNO__OBJCONF_MAP_EVTTYPE; - } - - events = xy->entries / (xy->row_size / xy->entry_size); - key = *((unsigned int *)pkey); - if (key >= events) { - pr_debug("ERROR: there is no event %d for map %s\n", - key, name); - return -BPF_LOADER_ERRNO__OBJCONF_MAP_MAPSIZE; - } - evt_fd = xyarray__entry(xy, key, 0); - err = bpf_map_update_elem(map_fd, pkey, evt_fd, BPF_ANY); - if (err && errno) - err = -errno; - return err; -} - -static int -apply_obj_config_map_for_key(const char *name, int map_fd, - const struct bpf_map *map, - struct bpf_map_op *op, - void *pkey, void *arg __maybe_unused) -{ - int err; - - switch (op->op_type) { - case BPF_MAP_OP_SET_VALUE: - err = apply_config_value_for_key(map_fd, pkey, - bpf_map__value_size(map), - op->v.value); - break; - case BPF_MAP_OP_SET_EVSEL: - err = apply_config_evsel_for_key(name, map_fd, pkey, - op->v.evsel); - break; - default: - pr_debug("ERROR: unknown value type for '%s'\n", name); - err = -BPF_LOADER_ERRNO__INTERNAL; - } - return err; -} - -static int -apply_obj_config_map(struct bpf_map *map) -{ - return bpf_map_config_foreach_key(map, - apply_obj_config_map_for_key, - NULL); -} - -static int -apply_obj_config_object(struct bpf_object *obj) -{ - struct bpf_map *map; - int err; - - bpf_object__for_each_map(map, obj) { - err = apply_obj_config_map(map); - if (err) - return err; - } - return 0; -} - -int bpf__apply_obj_config(void) -{ - struct bpf_perf_object *perf_obj, *tmp; - int err; - - bpf_perf_object__for_each(perf_obj, tmp) { - err = apply_obj_config_object(perf_obj->obj); - if (err) - return err; - } - - return 0; -} - -#define bpf__perf_for_each_map(map, pobj, tmp) \ - bpf_perf_object__for_each(pobj, tmp) \ - bpf_object__for_each_map(map, pobj->obj) - -#define bpf__perf_for_each_map_named(map, pobj, pobjtmp, name) \ - bpf__perf_for_each_map(map, pobj, pobjtmp) \ - if (bpf_map__name(map) && (strcmp(name, bpf_map__name(map)) == 0)) - -struct evsel *bpf__setup_output_event(struct evlist *evlist, const char *name) -{ - struct bpf_map_priv *tmpl_priv = NULL; - struct bpf_perf_object *perf_obj, *tmp; - struct evsel *evsel = NULL; - struct bpf_map *map; - int err; - bool need_init = false; - - bpf__perf_for_each_map_named(map, perf_obj, tmp, name) { - struct bpf_map_priv *priv = map_priv(map); - - if (IS_ERR(priv)) - return ERR_PTR(-BPF_LOADER_ERRNO__INTERNAL); - - /* - * No need to check map type: type should have been - * verified by kernel. - */ - if (!need_init && !priv) - need_init = !priv; - if (!tmpl_priv && priv) - tmpl_priv = priv; - } - - if (!need_init) - return NULL; - - if (!tmpl_priv) { - char *event_definition = NULL; - - if (asprintf(&event_definition, "bpf-output/no-inherit=1,name=%s/", name) < 0) - return ERR_PTR(-ENOMEM); - - err = parse_event(evlist, event_definition); - free(event_definition); - - if (err) { - pr_debug("ERROR: failed to create the \"%s\" bpf-output event\n", name); - return ERR_PTR(-err); - } - - evsel = evlist__last(evlist); - } - - bpf__perf_for_each_map_named(map, perf_obj, tmp, name) { - struct bpf_map_priv *priv = map_priv(map); - - if (IS_ERR(priv)) - return ERR_PTR(-BPF_LOADER_ERRNO__INTERNAL); - if (priv) - continue; - - if (tmpl_priv) { - priv = bpf_map_priv__clone(tmpl_priv); - if (!priv) - return ERR_PTR(-ENOMEM); - - err = map_set_priv(map, priv); - if (err) { - bpf_map_priv__clear(map, priv); - return ERR_PTR(err); - } - } else if (evsel) { - struct bpf_map_op *op; - - op = bpf_map__add_newop(map, NULL); - if (IS_ERR(op)) - return ERR_CAST(op); - op->op_type = BPF_MAP_OP_SET_EVSEL; - op->v.evsel = evsel; - } - } - - return evsel; -} - -int bpf__setup_stdout(struct evlist *evlist) -{ - struct evsel *evsel = bpf__setup_output_event(evlist, "__bpf_stdout__"); - return PTR_ERR_OR_ZERO(evsel); -} - -#define ERRNO_OFFSET(e) ((e) - __BPF_LOADER_ERRNO__START) -#define ERRCODE_OFFSET(c) ERRNO_OFFSET(BPF_LOADER_ERRNO__##c) -#define NR_ERRNO (__BPF_LOADER_ERRNO__END - __BPF_LOADER_ERRNO__START) - -static const char *bpf_loader_strerror_table[NR_ERRNO] = { - [ERRCODE_OFFSET(CONFIG)] = "Invalid config string", - [ERRCODE_OFFSET(GROUP)] = "Invalid group name", - [ERRCODE_OFFSET(EVENTNAME)] = "No event name found in config string", - [ERRCODE_OFFSET(INTERNAL)] = "BPF loader internal error", - [ERRCODE_OFFSET(COMPILE)] = "Error when compiling BPF scriptlet", - [ERRCODE_OFFSET(PROGCONF_TERM)] = "Invalid program config term in config string", - [ERRCODE_OFFSET(PROLOGUE)] = "Failed to generate prologue", - [ERRCODE_OFFSET(PROLOGUE2BIG)] = "Prologue too big for program", - [ERRCODE_OFFSET(PROLOGUEOOB)] = "Offset out of bound for prologue", - [ERRCODE_OFFSET(OBJCONF_OPT)] = "Invalid object config option", - [ERRCODE_OFFSET(OBJCONF_CONF)] = "Config value not set (missing '=')", - [ERRCODE_OFFSET(OBJCONF_MAP_OPT)] = "Invalid object map config option", - [ERRCODE_OFFSET(OBJCONF_MAP_NOTEXIST)] = "Target map doesn't exist", - [ERRCODE_OFFSET(OBJCONF_MAP_VALUE)] = "Incorrect value type for map", - [ERRCODE_OFFSET(OBJCONF_MAP_TYPE)] = "Incorrect map type", - [ERRCODE_OFFSET(OBJCONF_MAP_KEYSIZE)] = "Incorrect map key size", - [ERRCODE_OFFSET(OBJCONF_MAP_VALUESIZE)] = "Incorrect map value size", - [ERRCODE_OFFSET(OBJCONF_MAP_NOEVT)] = "Event not found for map setting", - [ERRCODE_OFFSET(OBJCONF_MAP_MAPSIZE)] = "Invalid map size for event setting", - [ERRCODE_OFFSET(OBJCONF_MAP_EVTDIM)] = "Event dimension too large", - [ERRCODE_OFFSET(OBJCONF_MAP_EVTINH)] = "Doesn't support inherit event", - [ERRCODE_OFFSET(OBJCONF_MAP_EVTTYPE)] = "Wrong event type for map", - [ERRCODE_OFFSET(OBJCONF_MAP_IDX2BIG)] = "Index too large", -}; - -static int -bpf_loader_strerror(int err, char *buf, size_t size) -{ - char sbuf[STRERR_BUFSIZE]; - const char *msg; - - if (!buf || !size) - return -1; - - err = err > 0 ? err : -err; - - if (err >= __LIBBPF_ERRNO__START) - return libbpf_strerror(err, buf, size); - - if (err >= __BPF_LOADER_ERRNO__START && err < __BPF_LOADER_ERRNO__END) { - msg = bpf_loader_strerror_table[ERRNO_OFFSET(err)]; - snprintf(buf, size, "%s", msg); - buf[size - 1] = '\0'; - return 0; - } - - if (err >= __BPF_LOADER_ERRNO__END) - snprintf(buf, size, "Unknown bpf loader error %d", err); - else - snprintf(buf, size, "%s", - str_error_r(err, sbuf, sizeof(sbuf))); - - buf[size - 1] = '\0'; - return -1; -} - -#define bpf__strerror_head(err, buf, size) \ - char sbuf[STRERR_BUFSIZE], *emsg;\ - if (!size)\ - return 0;\ - if (err < 0)\ - err = -err;\ - bpf_loader_strerror(err, sbuf, sizeof(sbuf));\ - emsg = sbuf;\ - switch (err) {\ - default:\ - scnprintf(buf, size, "%s", emsg);\ - break; - -#define bpf__strerror_entry(val, fmt...)\ - case val: {\ - scnprintf(buf, size, fmt);\ - break;\ - } - -#define bpf__strerror_end(buf, size)\ - }\ - buf[size - 1] = '\0'; - -int bpf__strerror_prepare_load(const char *filename, bool source, - int err, char *buf, size_t size) -{ - size_t n; - int ret; - - n = snprintf(buf, size, "Failed to load %s%s: ", - filename, source ? " from source" : ""); - if (n >= size) { - buf[size - 1] = '\0'; - return 0; - } - buf += n; - size -= n; - - ret = bpf_loader_strerror(err, buf, size); - buf[size - 1] = '\0'; - return ret; -} - -int bpf__strerror_probe(struct bpf_object *obj __maybe_unused, - int err, char *buf, size_t size) -{ - bpf__strerror_head(err, buf, size); - case BPF_LOADER_ERRNO__PROGCONF_TERM: { - scnprintf(buf, size, "%s (add -v to see detail)", emsg); - break; - } - bpf__strerror_entry(EEXIST, "Probe point exist. Try 'perf probe -d \"*\"' and set 'force=yes'"); - bpf__strerror_entry(EACCES, "You need to be root"); - bpf__strerror_entry(EPERM, "You need to be root, and /proc/sys/kernel/kptr_restrict should be 0"); - bpf__strerror_entry(ENOENT, "You need to check probing points in BPF file"); - bpf__strerror_end(buf, size); - return 0; -} - -int bpf__strerror_load(struct bpf_object *obj, - int err, char *buf, size_t size) -{ - bpf__strerror_head(err, buf, size); - case LIBBPF_ERRNO__KVER: { - unsigned int obj_kver = bpf_object__kversion(obj); - unsigned int real_kver; - - if (fetch_kernel_version(&real_kver, NULL, 0)) { - scnprintf(buf, size, "Unable to fetch kernel version"); - break; - } - - if (obj_kver != real_kver) { - scnprintf(buf, size, - "'version' ("KVER_FMT") doesn't match running kernel ("KVER_FMT")", - KVER_PARAM(obj_kver), - KVER_PARAM(real_kver)); - break; - } - - scnprintf(buf, size, "Failed to load program for unknown reason"); - break; - } - bpf__strerror_end(buf, size); - return 0; -} - -int bpf__strerror_config_obj(struct bpf_object *obj __maybe_unused, - struct parse_events_term *term __maybe_unused, - struct evlist *evlist __maybe_unused, - int *error_pos __maybe_unused, int err, - char *buf, size_t size) -{ - bpf__strerror_head(err, buf, size); - bpf__strerror_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE, - "Can't use this config term with this map type"); - bpf__strerror_end(buf, size); - return 0; -} - -int bpf__strerror_apply_obj_config(int err, char *buf, size_t size) -{ - bpf__strerror_head(err, buf, size); - bpf__strerror_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_EVTDIM, - "Cannot set event to BPF map in multi-thread tracing"); - bpf__strerror_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_EVTINH, - "%s (Hint: use -i to turn off inherit)", emsg); - bpf__strerror_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_EVTTYPE, - "Can only put raw, hardware and BPF output event into a BPF map"); - bpf__strerror_end(buf, size); - return 0; -} - -int bpf__strerror_setup_output_event(struct evlist *evlist __maybe_unused, - int err, char *buf, size_t size) -{ - bpf__strerror_head(err, buf, size); - bpf__strerror_end(buf, size); - return 0; -} diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h deleted file mode 100644 index 5d1c725cea29..000000000000 --- a/tools/perf/util/bpf-loader.h +++ /dev/null @@ -1,216 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright (C) 2015, Wang Nan <wangnan0@huawei.com> - * Copyright (C) 2015, Huawei Inc. - */ -#ifndef __BPF_LOADER_H -#define __BPF_LOADER_H - -#include <linux/compiler.h> -#include <linux/err.h> - -#ifdef HAVE_LIBBPF_SUPPORT -#include <bpf/libbpf.h> - -enum bpf_loader_errno { - __BPF_LOADER_ERRNO__START = __LIBBPF_ERRNO__START - 100, - /* Invalid config string */ - BPF_LOADER_ERRNO__CONFIG = __BPF_LOADER_ERRNO__START, - BPF_LOADER_ERRNO__GROUP, /* Invalid group name */ - BPF_LOADER_ERRNO__EVENTNAME, /* Event name is missing */ - BPF_LOADER_ERRNO__INTERNAL, /* BPF loader internal error */ - BPF_LOADER_ERRNO__COMPILE, /* Error when compiling BPF scriptlet */ - BPF_LOADER_ERRNO__PROGCONF_TERM,/* Invalid program config term in config string */ - BPF_LOADER_ERRNO__PROLOGUE, /* Failed to generate prologue */ - BPF_LOADER_ERRNO__PROLOGUE2BIG, /* Prologue too big for program */ - BPF_LOADER_ERRNO__PROLOGUEOOB, /* Offset out of bound for prologue */ - BPF_LOADER_ERRNO__OBJCONF_OPT, /* Invalid object config option */ - BPF_LOADER_ERRNO__OBJCONF_CONF, /* Config value not set (lost '=')) */ - BPF_LOADER_ERRNO__OBJCONF_MAP_OPT, /* Invalid object map config option */ - BPF_LOADER_ERRNO__OBJCONF_MAP_NOTEXIST, /* Target map not exist */ - BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE, /* Incorrect value type for map */ - BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE, /* Incorrect map type */ - BPF_LOADER_ERRNO__OBJCONF_MAP_KEYSIZE, /* Incorrect map key size */ - BPF_LOADER_ERRNO__OBJCONF_MAP_VALUESIZE,/* Incorrect map value size */ - BPF_LOADER_ERRNO__OBJCONF_MAP_NOEVT, /* Event not found for map setting */ - BPF_LOADER_ERRNO__OBJCONF_MAP_MAPSIZE, /* Invalid map size for event setting */ - BPF_LOADER_ERRNO__OBJCONF_MAP_EVTDIM, /* Event dimension too large */ - BPF_LOADER_ERRNO__OBJCONF_MAP_EVTINH, /* Doesn't support inherit event */ - BPF_LOADER_ERRNO__OBJCONF_MAP_EVTTYPE, /* Wrong event type for map */ - BPF_LOADER_ERRNO__OBJCONF_MAP_IDX2BIG, /* Index too large */ - __BPF_LOADER_ERRNO__END, -}; -#endif // HAVE_LIBBPF_SUPPORT - -struct evsel; -struct evlist; -struct bpf_object; -struct parse_events_term; -#define PERF_BPF_PROBE_GROUP "perf_bpf_probe" - -typedef int (*bpf_prog_iter_callback_t)(const char *group, const char *event, - int fd, struct bpf_object *obj, void *arg); - -#ifdef HAVE_LIBBPF_SUPPORT -struct bpf_object *bpf__prepare_load(const char *filename, bool source); -int bpf__strerror_prepare_load(const char *filename, bool source, - int err, char *buf, size_t size); - -struct bpf_object *bpf__prepare_load_buffer(void *obj_buf, size_t obj_buf_sz, - const char *name); - -void bpf__clear(void); - -int bpf__probe(struct bpf_object *obj); -int bpf__unprobe(struct bpf_object *obj); -int bpf__strerror_probe(struct bpf_object *obj, int err, - char *buf, size_t size); - -int bpf__load(struct bpf_object *obj); -int bpf__strerror_load(struct bpf_object *obj, int err, - char *buf, size_t size); -int bpf__foreach_event(struct bpf_object *obj, - bpf_prog_iter_callback_t func, void *arg); - -int bpf__config_obj(struct bpf_object *obj, struct parse_events_term *term, - struct evlist *evlist, int *error_pos); -int bpf__strerror_config_obj(struct bpf_object *obj, - struct parse_events_term *term, - struct evlist *evlist, - int *error_pos, int err, char *buf, - size_t size); -int bpf__apply_obj_config(void); -int bpf__strerror_apply_obj_config(int err, char *buf, size_t size); - -int bpf__setup_stdout(struct evlist *evlist); -struct evsel *bpf__setup_output_event(struct evlist *evlist, const char *name); -int bpf__strerror_setup_output_event(struct evlist *evlist, int err, char *buf, size_t size); -#else -#include <errno.h> -#include <string.h> -#include "debug.h" - -static inline struct bpf_object * -bpf__prepare_load(const char *filename __maybe_unused, - bool source __maybe_unused) -{ - pr_debug("ERROR: eBPF object loading is disabled during compiling.\n"); - return ERR_PTR(-ENOTSUP); -} - -static inline struct bpf_object * -bpf__prepare_load_buffer(void *obj_buf __maybe_unused, - size_t obj_buf_sz __maybe_unused) -{ - return ERR_PTR(-ENOTSUP); -} - -static inline void bpf__clear(void) { } - -static inline int bpf__probe(struct bpf_object *obj __maybe_unused) { return 0;} -static inline int bpf__unprobe(struct bpf_object *obj __maybe_unused) { return 0;} -static inline int bpf__load(struct bpf_object *obj __maybe_unused) { return 0; } - -static inline int -bpf__foreach_event(struct bpf_object *obj __maybe_unused, - bpf_prog_iter_callback_t func __maybe_unused, - void *arg __maybe_unused) -{ - return 0; -} - -static inline int -bpf__config_obj(struct bpf_object *obj __maybe_unused, - struct parse_events_term *term __maybe_unused, - struct evlist *evlist __maybe_unused, - int *error_pos __maybe_unused) -{ - return 0; -} - -static inline int -bpf__apply_obj_config(void) -{ - return 0; -} - -static inline int -bpf__setup_stdout(struct evlist *evlist __maybe_unused) -{ - return 0; -} - -static inline struct evsel * -bpf__setup_output_event(struct evlist *evlist __maybe_unused, const char *name __maybe_unused) -{ - return NULL; -} - -static inline int -__bpf_strerror(char *buf, size_t size) -{ - if (!size) - return 0; - strncpy(buf, - "ERROR: eBPF object loading is disabled during compiling.\n", - size); - buf[size - 1] = '\0'; - return 0; -} - -static inline -int bpf__strerror_prepare_load(const char *filename __maybe_unused, - bool source __maybe_unused, - int err __maybe_unused, - char *buf, size_t size) -{ - return __bpf_strerror(buf, size); -} - -static inline int -bpf__strerror_probe(struct bpf_object *obj __maybe_unused, - int err __maybe_unused, - char *buf, size_t size) -{ - return __bpf_strerror(buf, size); -} - -static inline int bpf__strerror_load(struct bpf_object *obj __maybe_unused, - int err __maybe_unused, - char *buf, size_t size) -{ - return __bpf_strerror(buf, size); -} - -static inline int -bpf__strerror_config_obj(struct bpf_object *obj __maybe_unused, - struct parse_events_term *term __maybe_unused, - struct evlist *evlist __maybe_unused, - int *error_pos __maybe_unused, - int err __maybe_unused, - char *buf, size_t size) -{ - return __bpf_strerror(buf, size); -} - -static inline int -bpf__strerror_apply_obj_config(int err __maybe_unused, - char *buf, size_t size) -{ - return __bpf_strerror(buf, size); -} - -static inline int -bpf__strerror_setup_output_event(struct evlist *evlist __maybe_unused, - int err __maybe_unused, char *buf, size_t size) -{ - return __bpf_strerror(buf, size); -} - -#endif - -static inline int bpf__strerror_setup_stdout(struct evlist *evlist, int err, char *buf, size_t size) -{ - return bpf__strerror_setup_output_event(evlist, err, buf, size); -} -#endif diff --git a/tools/perf/examples/bpf/augmented_raw_syscalls.c b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c index 9a03189d33d3..90ce22f9c1a9 100644 --- a/tools/perf/examples/bpf/augmented_raw_syscalls.c +++ b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c @@ -2,22 +2,26 @@ /* * Augment the raw_syscalls tracepoints with the contents of the pointer arguments. * - * Test it with: - * - * perf trace -e tools/perf/examples/bpf/augmented_raw_syscalls.c cat /etc/passwd > /dev/null - * * This exactly matches what is marshalled into the raw_syscall:sys_enter * payload expected by the 'perf trace' beautifiers. - * - * For now it just uses the existing tracepoint augmentation code in 'perf - * trace', in the next csets we'll hook up these with the sys_enter/sys_exit - * code that will combine entry/exit in a strace like way. */ #include <linux/bpf.h> #include <bpf/bpf_helpers.h> #include <linux/limits.h> +/** + * is_power_of_2() - check if a value is a power of two + * @n: the value to check + * + * Determine whether some value is a power of two, where zero is *not* + * considered a power of two. Return: true if @n is a power of 2, otherwise + * false. + */ +#define is_power_of_2(n) (n != 0 && ((n & (n - 1)) == 0)) + +#define MAX_CPUS 4096 + // FIXME: These should come from system headers typedef char bool; typedef int pid_t; @@ -34,7 +38,7 @@ struct __augmented_syscalls__ { __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); __type(key, int); __type(value, __u32); - __uint(max_entries, __NR_CPUS__); + __uint(max_entries, MAX_CPUS); } __augmented_syscalls__ SEC(".maps"); /* @@ -156,6 +160,7 @@ unsigned int augmented_arg__read_str(struct augmented_arg *augmented_arg, const */ if (string_len > 0) { augmented_len -= sizeof(augmented_arg->value) - string_len; + _Static_assert(is_power_of_2(sizeof(augmented_arg->value)), "sizeof(augmented_arg->value) needs to be a power of two"); augmented_len &= sizeof(augmented_arg->value) - 1; augmented_arg->size = string_len; } else { @@ -170,7 +175,7 @@ unsigned int augmented_arg__read_str(struct augmented_arg *augmented_arg, const return augmented_len; } -SEC("!raw_syscalls:unaugmented") +SEC("tp/raw_syscalls/sys_enter") int syscall_unaugmented(struct syscall_enter_args *args) { return 1; @@ -182,7 +187,7 @@ int syscall_unaugmented(struct syscall_enter_args *args) * on from there, reading the first syscall arg as a string, i.e. open's * filename. */ -SEC("!syscalls:sys_enter_connect") +SEC("tp/syscalls/sys_enter_connect") int sys_enter_connect(struct syscall_enter_args *args) { struct augmented_args_payload *augmented_args = augmented_args_payload(); @@ -193,15 +198,15 @@ int sys_enter_connect(struct syscall_enter_args *args) if (augmented_args == NULL) return 1; /* Failure: don't filter */ - if (socklen > sizeof(augmented_args->saddr)) - socklen = sizeof(augmented_args->saddr); + _Static_assert(is_power_of_2(sizeof(augmented_args->saddr)), "sizeof(augmented_args->saddr) needs to be a power of two"); + socklen &= sizeof(augmented_args->saddr) - 1; bpf_probe_read(&augmented_args->saddr, socklen, sockaddr_arg); return augmented__output(args, augmented_args, len + socklen); } -SEC("!syscalls:sys_enter_sendto") +SEC("tp/syscalls/sys_enter_sendto") int sys_enter_sendto(struct syscall_enter_args *args) { struct augmented_args_payload *augmented_args = augmented_args_payload(); @@ -212,15 +217,14 @@ int sys_enter_sendto(struct syscall_enter_args *args) if (augmented_args == NULL) return 1; /* Failure: don't filter */ - if (socklen > sizeof(augmented_args->saddr)) - socklen = sizeof(augmented_args->saddr); + socklen &= sizeof(augmented_args->saddr) - 1; bpf_probe_read(&augmented_args->saddr, socklen, sockaddr_arg); return augmented__output(args, augmented_args, len + socklen); } -SEC("!syscalls:sys_enter_open") +SEC("tp/syscalls/sys_enter_open") int sys_enter_open(struct syscall_enter_args *args) { struct augmented_args_payload *augmented_args = augmented_args_payload(); @@ -235,7 +239,7 @@ int sys_enter_open(struct syscall_enter_args *args) return augmented__output(args, augmented_args, len); } -SEC("!syscalls:sys_enter_openat") +SEC("tp/syscalls/sys_enter_openat") int sys_enter_openat(struct syscall_enter_args *args) { struct augmented_args_payload *augmented_args = augmented_args_payload(); @@ -250,7 +254,7 @@ int sys_enter_openat(struct syscall_enter_args *args) return augmented__output(args, augmented_args, len); } -SEC("!syscalls:sys_enter_rename") +SEC("tp/syscalls/sys_enter_rename") int sys_enter_rename(struct syscall_enter_args *args) { struct augmented_args_payload *augmented_args = augmented_args_payload(); @@ -267,7 +271,7 @@ int sys_enter_rename(struct syscall_enter_args *args) return augmented__output(args, augmented_args, len); } -SEC("!syscalls:sys_enter_renameat") +SEC("tp/syscalls/sys_enter_renameat") int sys_enter_renameat(struct syscall_enter_args *args) { struct augmented_args_payload *augmented_args = augmented_args_payload(); @@ -295,7 +299,7 @@ struct perf_event_attr_size { __u32 size; }; -SEC("!syscalls:sys_enter_perf_event_open") +SEC("tp/syscalls/sys_enter_perf_event_open") int sys_enter_perf_event_open(struct syscall_enter_args *args) { struct augmented_args_payload *augmented_args = augmented_args_payload(); @@ -327,7 +331,7 @@ failure: return 1; /* Failure: don't filter */ } -SEC("!syscalls:sys_enter_clock_nanosleep") +SEC("tp/syscalls/sys_enter_clock_nanosleep") int sys_enter_clock_nanosleep(struct syscall_enter_args *args) { struct augmented_args_payload *augmented_args = augmented_args_payload(); @@ -358,7 +362,7 @@ static bool pid_filter__has(struct pids_filtered *pids, pid_t pid) return bpf_map_lookup_elem(pids, &pid) != NULL; } -SEC("raw_syscalls:sys_enter") +SEC("tp/raw_syscalls/sys_enter") int sys_enter(struct syscall_enter_args *args) { struct augmented_args_payload *augmented_args; @@ -371,7 +375,6 @@ int sys_enter(struct syscall_enter_args *args) * We'll add to this as we add augmented syscalls right after that * initial, non-augmented raw_syscalls:sys_enter payload. */ - unsigned int len = sizeof(augmented_args->args); if (pid_filter__has(&pids_filtered, getpid())) return 0; @@ -393,7 +396,7 @@ int sys_enter(struct syscall_enter_args *args) return 0; } -SEC("raw_syscalls:sys_exit") +SEC("tp/raw_syscalls/sys_exit") int sys_exit(struct syscall_exit_args *args) { struct syscall_exit_args exit_args; diff --git a/tools/perf/util/bpf_skel/bench_uprobe.bpf.c b/tools/perf/util/bpf_skel/bench_uprobe.bpf.c new file mode 100644 index 000000000000..2c55896bb33c --- /dev/null +++ b/tools/perf/util/bpf_skel/bench_uprobe.bpf.c @@ -0,0 +1,23 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +// Copyright (c) 2023 Red Hat +#include "vmlinux.h" +#include <bpf/bpf_tracing.h> + +unsigned int nr_uprobes; + +SEC("uprobe") +int BPF_UPROBE(empty) +{ + return 0; +} + +SEC("uprobe") +int BPF_UPROBE(trace_printk) +{ + char fmt[] = "perf bench uprobe %u"; + + bpf_trace_printk(fmt, sizeof(fmt), ++nr_uprobes); + return 0; +} + +char LICENSE[] SEC("license") = "Dual BSD/GPL"; diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index 36728222a5b4..03c64b85383b 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -560,7 +560,7 @@ char *build_id_cache__cachedir(const char *sbuild_id, const char *name, struct nsinfo *nsi, bool is_kallsyms, bool is_vdso) { - char *realname = (char *)name, *filename; + char *realname = NULL, *filename; bool slash = is_kallsyms || is_vdso; if (!slash) @@ -571,9 +571,7 @@ char *build_id_cache__cachedir(const char *sbuild_id, const char *name, sbuild_id ? "/" : "", sbuild_id ?: "") < 0) filename = NULL; - if (!slash) - free(realname); - + free(realname); return filename; } diff --git a/tools/perf/util/c++/Build b/tools/perf/util/c++/Build deleted file mode 100644 index 613ecfd76527..000000000000 --- a/tools/perf/util/c++/Build +++ /dev/null @@ -1,2 +0,0 @@ -perf-$(CONFIG_CLANGLLVM) += clang.o -perf-$(CONFIG_CLANGLLVM) += clang-test.o diff --git a/tools/perf/util/c++/clang-c.h b/tools/perf/util/c++/clang-c.h deleted file mode 100644 index d3731a876b6c..000000000000 --- a/tools/perf/util/c++/clang-c.h +++ /dev/null @@ -1,43 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef PERF_UTIL_CLANG_C_H -#define PERF_UTIL_CLANG_C_H - -#include <stddef.h> /* for size_t */ - -#ifdef __cplusplus -extern "C" { -#endif - -#ifdef HAVE_LIBCLANGLLVM_SUPPORT -extern void perf_clang__init(void); -extern void perf_clang__cleanup(void); - -struct test_suite; -extern int test__clang_to_IR(struct test_suite *test, int subtest); -extern int test__clang_to_obj(struct test_suite *test, int subtest); - -extern int perf_clang__compile_bpf(const char *filename, - void **p_obj_buf, - size_t *p_obj_buf_sz); -#else - -#include <errno.h> -#include <linux/compiler.h> /* for __maybe_unused */ - -static inline void perf_clang__init(void) { } -static inline void perf_clang__cleanup(void) { } - -static inline int -perf_clang__compile_bpf(const char *filename __maybe_unused, - void **p_obj_buf __maybe_unused, - size_t *p_obj_buf_sz __maybe_unused) -{ - return -ENOTSUP; -} - -#endif - -#ifdef __cplusplus -} -#endif -#endif diff --git a/tools/perf/util/c++/clang-test.cpp b/tools/perf/util/c++/clang-test.cpp deleted file mode 100644 index a4683ca53697..000000000000 --- a/tools/perf/util/c++/clang-test.cpp +++ /dev/null @@ -1,67 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include "clang.h" -#include "clang-c.h" -extern "C" { -#include "../util.h" -} -#include "llvm/IR/Function.h" -#include "llvm/IR/LLVMContext.h" - -#include <tests/llvm.h> -#include <string> - -class perf_clang_scope { -public: - explicit perf_clang_scope() {perf_clang__init();} - ~perf_clang_scope() {perf_clang__cleanup();} -}; - -static std::unique_ptr<llvm::Module> -__test__clang_to_IR(void) -{ - unsigned int kernel_version; - - if (fetch_kernel_version(&kernel_version, NULL, 0)) - return std::unique_ptr<llvm::Module>(nullptr); - - std::string cflag_kver("-DLINUX_VERSION_CODE=" + - std::to_string(kernel_version)); - - std::unique_ptr<llvm::Module> M = - perf::getModuleFromSource({cflag_kver.c_str()}, - "perf-test.c", - test_llvm__bpf_base_prog); - return M; -} - -extern "C" { -int test__clang_to_IR(struct test_suite *test __maybe_unused, - int subtest __maybe_unused) -{ - perf_clang_scope _scope; - - auto M = __test__clang_to_IR(); - if (!M) - return -1; - for (llvm::Function& F : *M) - if (F.getName() == "bpf_func__SyS_epoll_pwait") - return 0; - return -1; -} - -int test__clang_to_obj(struct test_suite *test __maybe_unused, - int subtest __maybe_unused) -{ - perf_clang_scope _scope; - - auto M = __test__clang_to_IR(); - if (!M) - return -1; - - auto Buffer = perf::getBPFObjectFromModule(&*M); - if (!Buffer) - return -1; - return 0; -} - -} diff --git a/tools/perf/util/c++/clang.cpp b/tools/perf/util/c++/clang.cpp deleted file mode 100644 index 1aad7d6d34aa..000000000000 --- a/tools/perf/util/c++/clang.cpp +++ /dev/null @@ -1,225 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * llvm C frontend for perf. Support dynamically compile C file - * - * Inspired by clang example code: - * http://llvm.org/svn/llvm-project/cfe/trunk/examples/clang-interpreter/main.cpp - * - * Copyright (C) 2016 Wang Nan <wangnan0@huawei.com> - * Copyright (C) 2016 Huawei Inc. - */ - -#include "clang/Basic/Version.h" -#include "clang/CodeGen/CodeGenAction.h" -#include "clang/Frontend/CompilerInvocation.h" -#include "clang/Frontend/CompilerInstance.h" -#include "clang/Frontend/TextDiagnosticPrinter.h" -#include "clang/Tooling/Tooling.h" -#include "llvm/IR/LegacyPassManager.h" -#include "llvm/IR/Module.h" -#include "llvm/Option/Option.h" -#include "llvm/Support/FileSystem.h" -#include "llvm/Support/ManagedStatic.h" -#if CLANG_VERSION_MAJOR >= 14 -#include "llvm/MC/TargetRegistry.h" -#else -#include "llvm/Support/TargetRegistry.h" -#endif -#include "llvm/Support/TargetSelect.h" -#include "llvm/Target/TargetMachine.h" -#include "llvm/Target/TargetOptions.h" -#include <memory> - -#include "clang.h" -#include "clang-c.h" - -namespace perf { - -static std::unique_ptr<llvm::LLVMContext> LLVMCtx; - -using namespace clang; - -static CompilerInvocation * -createCompilerInvocation(llvm::opt::ArgStringList CFlags, StringRef& Path, - DiagnosticsEngine& Diags) -{ - llvm::opt::ArgStringList CCArgs { - "-cc1", - "-triple", "bpf-pc-linux", - "-fsyntax-only", - "-O2", - "-nostdsysteminc", - "-nobuiltininc", - "-vectorize-loops", - "-vectorize-slp", - "-Wno-unused-value", - "-Wno-pointer-sign", - "-x", "c"}; - - CCArgs.append(CFlags.begin(), CFlags.end()); - CompilerInvocation *CI = tooling::newInvocation(&Diags, CCArgs -#if CLANG_VERSION_MAJOR >= 11 - ,/*BinaryName=*/nullptr -#endif - ); - - FrontendOptions& Opts = CI->getFrontendOpts(); - Opts.Inputs.clear(); - Opts.Inputs.emplace_back(Path, - FrontendOptions::getInputKindForExtension("c")); - return CI; -} - -static std::unique_ptr<llvm::Module> -getModuleFromSource(llvm::opt::ArgStringList CFlags, - StringRef Path, IntrusiveRefCntPtr<vfs::FileSystem> VFS) -{ - CompilerInstance Clang; - Clang.createDiagnostics(); - -#if CLANG_VERSION_MAJOR < 9 - Clang.setVirtualFileSystem(&*VFS); -#else - Clang.createFileManager(&*VFS); -#endif - -#if CLANG_VERSION_MAJOR < 4 - IntrusiveRefCntPtr<CompilerInvocation> CI = - createCompilerInvocation(std::move(CFlags), Path, - Clang.getDiagnostics()); - Clang.setInvocation(&*CI); -#else - std::shared_ptr<CompilerInvocation> CI( - createCompilerInvocation(std::move(CFlags), Path, - Clang.getDiagnostics())); - Clang.setInvocation(CI); -#endif - - std::unique_ptr<CodeGenAction> Act(new EmitLLVMOnlyAction(&*LLVMCtx)); - if (!Clang.ExecuteAction(*Act)) - return std::unique_ptr<llvm::Module>(nullptr); - - return Act->takeModule(); -} - -std::unique_ptr<llvm::Module> -getModuleFromSource(llvm::opt::ArgStringList CFlags, - StringRef Name, StringRef Content) -{ - using namespace vfs; - - llvm::IntrusiveRefCntPtr<OverlayFileSystem> OverlayFS( - new OverlayFileSystem(getRealFileSystem())); - llvm::IntrusiveRefCntPtr<InMemoryFileSystem> MemFS( - new InMemoryFileSystem(true)); - - /* - * pushOverlay helps setting working dir for MemFS. Must call - * before addFile. - */ - OverlayFS->pushOverlay(MemFS); - MemFS->addFile(Twine(Name), 0, llvm::MemoryBuffer::getMemBuffer(Content)); - - return getModuleFromSource(std::move(CFlags), Name, OverlayFS); -} - -std::unique_ptr<llvm::Module> -getModuleFromSource(llvm::opt::ArgStringList CFlags, StringRef Path) -{ - IntrusiveRefCntPtr<vfs::FileSystem> VFS(vfs::getRealFileSystem()); - return getModuleFromSource(std::move(CFlags), Path, VFS); -} - -std::unique_ptr<llvm::SmallVectorImpl<char>> -getBPFObjectFromModule(llvm::Module *Module) -{ - using namespace llvm; - - std::string TargetTriple("bpf-pc-linux"); - std::string Error; - const Target* Target = TargetRegistry::lookupTarget(TargetTriple, Error); - if (!Target) { - llvm::errs() << Error; - return std::unique_ptr<llvm::SmallVectorImpl<char>>(nullptr); - } - - llvm::TargetOptions Opt; - TargetMachine *TargetMachine = - Target->createTargetMachine(TargetTriple, - "generic", "", - Opt, Reloc::Static); - - Module->setDataLayout(TargetMachine->createDataLayout()); - Module->setTargetTriple(TargetTriple); - - std::unique_ptr<SmallVectorImpl<char>> Buffer(new SmallVector<char, 0>()); - raw_svector_ostream ostream(*Buffer); - - legacy::PassManager PM; - bool NotAdded; - NotAdded = TargetMachine->addPassesToEmitFile(PM, ostream -#if CLANG_VERSION_MAJOR >= 7 - , /*DwoOut=*/nullptr -#endif -#if CLANG_VERSION_MAJOR < 10 - , TargetMachine::CGFT_ObjectFile -#else - , llvm::CGFT_ObjectFile -#endif - ); - if (NotAdded) { - llvm::errs() << "TargetMachine can't emit a file of this type\n"; - return std::unique_ptr<llvm::SmallVectorImpl<char>>(nullptr); - } - PM.run(*Module); - - return Buffer; -} - -} - -extern "C" { -void perf_clang__init(void) -{ - perf::LLVMCtx.reset(new llvm::LLVMContext()); - LLVMInitializeBPFTargetInfo(); - LLVMInitializeBPFTarget(); - LLVMInitializeBPFTargetMC(); - LLVMInitializeBPFAsmPrinter(); -} - -void perf_clang__cleanup(void) -{ - perf::LLVMCtx.reset(nullptr); - llvm::llvm_shutdown(); -} - -int perf_clang__compile_bpf(const char *filename, - void **p_obj_buf, - size_t *p_obj_buf_sz) -{ - using namespace perf; - - if (!p_obj_buf || !p_obj_buf_sz) - return -EINVAL; - - llvm::opt::ArgStringList CFlags; - auto M = getModuleFromSource(std::move(CFlags), filename); - if (!M) - return -EINVAL; - auto O = getBPFObjectFromModule(&*M); - if (!O) - return -EINVAL; - - size_t size = O->size_in_bytes(); - void *buffer; - - buffer = malloc(size); - if (!buffer) - return -ENOMEM; - memcpy(buffer, O->data(), size); - *p_obj_buf = buffer; - *p_obj_buf_sz = size; - return 0; -} -} diff --git a/tools/perf/util/c++/clang.h b/tools/perf/util/c++/clang.h deleted file mode 100644 index 6ce33e22f23c..000000000000 --- a/tools/perf/util/c++/clang.h +++ /dev/null @@ -1,27 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef PERF_UTIL_CLANG_H -#define PERF_UTIL_CLANG_H - -#include "llvm/ADT/StringRef.h" -#include "llvm/IR/LLVMContext.h" -#include "llvm/IR/Module.h" -#include "llvm/Option/Option.h" -#include <memory> - -namespace perf { - -using namespace llvm; - -std::unique_ptr<Module> -getModuleFromSource(opt::ArgStringList CFlags, - StringRef Name, StringRef Content); - -std::unique_ptr<Module> -getModuleFromSource(opt::ArgStringList CFlags, - StringRef Path); - -std::unique_ptr<llvm::SmallVectorImpl<char>> -getBPFObjectFromModule(llvm::Module *Module); - -} -#endif diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index 46f144c46827..7a650de0db83 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -16,7 +16,6 @@ #include <subcmd/exec-cmd.h> #include "util/event.h" /* proc_map_timeout */ #include "util/hist.h" /* perf_hist_config */ -#include "util/llvm-utils.h" /* perf_llvm_config */ #include "util/stat.h" /* perf_stat__set_big_num */ #include "util/evsel.h" /* evsel__hw_names, evsel__use_bpf_counters */ #include "util/srcline.h" /* addr2line_timeout_ms */ @@ -486,9 +485,6 @@ int perf_default_config(const char *var, const char *value, if (strstarts(var, "call-graph.")) return perf_callchain_config(var, value); - if (strstarts(var, "llvm.")) - return perf_llvm_config(var, value); - if (strstarts(var, "buildid.")) return perf_buildid_config(var, value); diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 1419b40dfbe8..9729d006550d 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -6,10 +6,11 @@ * Author: Mathieu Poirier <mathieu.poirier@linaro.org> */ +#include <linux/kernel.h> +#include <linux/bitfield.h> #include <linux/bitops.h> #include <linux/coresight-pmu.h> #include <linux/err.h> -#include <linux/kernel.h> #include <linux/log2.h> #include <linux/types.h> #include <linux/zalloc.h> @@ -282,17 +283,6 @@ static int cs_etm__metadata_set_trace_id(u8 trace_chan_id, u64 *cpu_metadata) } /* - * FIELD_GET (linux/bitfield.h) not available outside kernel code, - * and the header contains too many dependencies to just copy over, - * so roll our own based on the original - */ -#define __bf_shf(x) (__builtin_ffsll(x) - 1) -#define FIELD_GET(_mask, _reg) \ - ({ \ - (typeof(_mask))(((_reg) & (_mask)) >> __bf_shf(_mask)); \ - }) - -/* * Get a metadata for a specific cpu from an array. * */ diff --git a/tools/perf/util/dlfilter.c b/tools/perf/util/dlfilter.c index 46f74b2344db..1dbf27822ee2 100644 --- a/tools/perf/util/dlfilter.c +++ b/tools/perf/util/dlfilter.c @@ -10,6 +10,8 @@ #include <subcmd/exec-cmd.h> #include <linux/zalloc.h> #include <linux/build_bug.h> +#include <linux/kernel.h> +#include <linux/string.h> #include "debug.h" #include "event.h" @@ -63,6 +65,7 @@ static void al_to_d_al(struct addr_location *al, struct perf_dlfilter_al *d_al) d_al->addr = al->addr; d_al->comm = NULL; d_al->filtered = 0; + d_al->priv = NULL; } static struct addr_location *get_al(struct dlfilter *d) @@ -151,6 +154,11 @@ static char **dlfilter__args(void *ctx, int *dlargc) return d->dlargv; } +static bool has_priv(struct perf_dlfilter_al *d_al_p) +{ + return d_al_p->size >= offsetof(struct perf_dlfilter_al, priv) + sizeof(d_al_p->priv); +} + static __s32 dlfilter__resolve_address(void *ctx, __u64 address, struct perf_dlfilter_al *d_al_p) { struct dlfilter *d = (struct dlfilter *)ctx; @@ -166,6 +174,7 @@ static __s32 dlfilter__resolve_address(void *ctx, __u64 address, struct perf_dlf if (!thread) return -1; + addr_location__init(&al); thread__find_symbol_fb(thread, d->sample->cpumode, address, &al); al_to_d_al(&al, &d_al); @@ -176,9 +185,31 @@ static __s32 dlfilter__resolve_address(void *ctx, __u64 address, struct perf_dlf memcpy(d_al_p, &d_al, min((size_t)sz, sizeof(d_al))); d_al_p->size = sz; + if (has_priv(d_al_p)) + d_al_p->priv = memdup(&al, sizeof(al)); + else /* Avoid leak for v0 API */ + addr_location__exit(&al); + return 0; } +static void dlfilter__al_cleanup(void *ctx __maybe_unused, struct perf_dlfilter_al *d_al_p) +{ + struct addr_location *al; + + /* Ensure backward compatibility */ + if (!has_priv(d_al_p) || !d_al_p->priv) + return; + + al = d_al_p->priv; + + d_al_p->priv = NULL; + + addr_location__exit(al); + + free(al); +} + static const __u8 *dlfilter__insn(void *ctx, __u32 *len) { struct dlfilter *d = (struct dlfilter *)ctx; @@ -296,6 +327,7 @@ static const struct perf_dlfilter_fns perf_dlfilter_fns = { .resolve_addr = dlfilter__resolve_addr, .args = dlfilter__args, .resolve_address = dlfilter__resolve_address, + .al_cleanup = dlfilter__al_cleanup, .insn = dlfilter__insn, .srcline = dlfilter__srcline, .attr = dlfilter__attr, diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index 9eabf3ec56e9..a164164001fb 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -324,11 +324,9 @@ int perf_env__read_pmu_mappings(struct perf_env *env) u32 pmu_num = 0; struct strbuf sb; - while ((pmu = perf_pmus__scan(pmu))) { - if (!pmu->name) - continue; + while ((pmu = perf_pmus__scan(pmu))) pmu_num++; - } + if (!pmu_num) { pr_debug("pmu mappings not available\n"); return -ENOENT; @@ -339,8 +337,6 @@ int perf_env__read_pmu_mappings(struct perf_env *env) return -ENOMEM; while ((pmu = perf_pmus__scan(pmu))) { - if (!pmu->name) - continue; if (strbuf_addf(&sb, "%u:%s", pmu->type, pmu->name) < 0) goto error; /* include a NULL character at the end */ diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 4cbb092e0684..923c0fb15122 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -93,8 +93,8 @@ struct process_symbol_args { u64 start; }; -static int find_symbol_cb(void *arg, const char *name, char type, - u64 start) +static int find_func_symbol_cb(void *arg, const char *name, char type, + u64 start) { struct process_symbol_args *args = arg; @@ -110,12 +110,36 @@ static int find_symbol_cb(void *arg, const char *name, char type, return 1; } +static int find_any_symbol_cb(void *arg, const char *name, + char type __maybe_unused, u64 start) +{ + struct process_symbol_args *args = arg; + + if (strcmp(name, args->name)) + return 0; + + args->start = start; + return 1; +} + int kallsyms__get_function_start(const char *kallsyms_filename, const char *symbol_name, u64 *addr) { struct process_symbol_args args = { .name = symbol_name, }; - if (kallsyms__parse(kallsyms_filename, &args, find_symbol_cb) <= 0) + if (kallsyms__parse(kallsyms_filename, &args, find_func_symbol_cb) <= 0) + return -1; + + *addr = args.start; + return 0; +} + +int kallsyms__get_symbol_start(const char *kallsyms_filename, + const char *symbol_name, u64 *addr) +{ + struct process_symbol_args args = { .name = symbol_name, }; + + if (kallsyms__parse(kallsyms_filename, &args, find_any_symbol_cb) <= 0) return -1; *addr = args.start; diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index de20e01c9d72..d8bcee2e9b93 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -360,6 +360,8 @@ size_t perf_event__fprintf(union perf_event *event, struct machine *machine, FIL int kallsyms__get_function_start(const char *kallsyms_filename, const char *symbol_name, u64 *addr); +int kallsyms__get_symbol_start(const char *kallsyms_filename, + const char *symbol_name, u64 *addr); void event_attr_init(struct perf_event_attr *attr); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 762e2b2634a5..a8a5ff87cc1f 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -845,6 +845,7 @@ static void __evsel__config_callchain(struct evsel *evsel, struct record_opts *o { bool function = evsel__is_function_event(evsel); struct perf_event_attr *attr = &evsel->core.attr; + const char *arch = perf_env__arch(evsel__env(evsel)); evsel__set_sample_bit(evsel, CALLCHAIN); @@ -877,8 +878,9 @@ static void __evsel__config_callchain(struct evsel *evsel, struct record_opts *o if (!function) { evsel__set_sample_bit(evsel, REGS_USER); evsel__set_sample_bit(evsel, STACK_USER); - if (opts->sample_user_regs && DWARF_MINIMAL_REGS != PERF_REGS_MASK) { - attr->sample_regs_user |= DWARF_MINIMAL_REGS; + if (opts->sample_user_regs && + DWARF_MINIMAL_REGS(arch) != arch__user_reg_mask()) { + attr->sample_regs_user |= DWARF_MINIMAL_REGS(arch); pr_warning("WARNING: The use of --call-graph=dwarf may require all the user registers, " "specifying a subset with --user-regs may render DWARF unwinding unreliable, " "so the minimal registers set (IP, SP) is explicitly forced.\n"); @@ -1474,6 +1476,7 @@ void evsel__exit(struct evsel *evsel) perf_thread_map__put(evsel->core.threads); zfree(&evsel->group_name); zfree(&evsel->name); + zfree(&evsel->filter); zfree(&evsel->pmu_name); zfree(&evsel->group_pmu_name); zfree(&evsel->unit); @@ -2826,9 +2829,6 @@ u64 evsel__intval(struct evsel *evsel, struct perf_sample *sample, const char *n { struct tep_format_field *field = evsel__field(evsel, name); - if (!field) - return 0; - return field ? format_field__intval(field, sample, evsel->needs_swap) : 0; } #endif diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c index 4814262e3805..4488f306de78 100644 --- a/tools/perf/util/expr.c +++ b/tools/perf/util/expr.c @@ -10,9 +10,11 @@ #include "debug.h" #include "evlist.h" #include "expr.h" -#include "expr-bison.h" -#include "expr-flex.h" +#include <util/expr-bison.h> +#include <util/expr-flex.h> #include "util/hashmap.h" +#include "util/header.h" +#include "util/pmu.h" #include "smt.h" #include "tsc.h" #include <api/fs/fs.h> @@ -425,6 +427,13 @@ double expr__get_literal(const char *literal, const struct expr_scanner_ctx *ctx result = cpu__max_present_cpu().cpu; goto out; } + if (!strcmp("#num_cpus_online", literal)) { + struct perf_cpu_map *online = cpu_map__online(); + + if (online) + result = perf_cpu_map__nr(online); + goto out; + } if (!strcasecmp("#system_tsc_freq", literal)) { result = arch_get_tsc_freq(); @@ -495,3 +504,19 @@ double expr__has_event(const struct expr_parse_ctx *ctx, bool compute_ids, const evlist__delete(tmp); return ret; } + +double expr__strcmp_cpuid_str(const struct expr_parse_ctx *ctx __maybe_unused, + bool compute_ids __maybe_unused, const char *test_id) +{ + double ret; + struct perf_pmu *pmu = pmu__find_core_pmu(); + char *cpuid = perf_pmu__getcpuid(pmu); + + if (!cpuid) + return NAN; + + ret = !strcmp_cpuid_str(test_id, cpuid); + + free(cpuid); + return ret; +} diff --git a/tools/perf/util/expr.h b/tools/perf/util/expr.h index 3c1e49b3e35d..c0cec29ddc29 100644 --- a/tools/perf/util/expr.h +++ b/tools/perf/util/expr.h @@ -55,5 +55,6 @@ double expr_id_data__value(const struct expr_id_data *data); double expr_id_data__source_count(const struct expr_id_data *data); double expr__get_literal(const char *literal, const struct expr_scanner_ctx *ctx); double expr__has_event(const struct expr_parse_ctx *ctx, bool compute_ids, const char *id); +double expr__strcmp_cpuid_str(const struct expr_parse_ctx *ctx, bool compute_ids, const char *id); #endif diff --git a/tools/perf/util/expr.l b/tools/perf/util/expr.l index dbb117414710..0feef0726c48 100644 --- a/tools/perf/util/expr.l +++ b/tools/perf/util/expr.l @@ -114,6 +114,7 @@ if { return IF; } else { return ELSE; } source_count { return SOURCE_COUNT; } has_event { return HAS_EVENT; } +strcmp_cpuid_str { return STRCMP_CPUID_STR; } {literal} { return literal(yyscanner, sctx); } {number} { return value(yyscanner); } {symbol} { return str(yyscanner, ID, sctx->runtime); } diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y index dd504afd8f36..6c93b358cc2d 100644 --- a/tools/perf/util/expr.y +++ b/tools/perf/util/expr.y @@ -7,6 +7,8 @@ #include "util/debug.h" #define IN_EXPR_Y 1 #include "expr.h" +#include "expr-bison.h" +int expr_lex(YYSTYPE * yylval_param , void *yyscanner); %} %define api.pure full @@ -37,7 +39,7 @@ } ids; } -%token ID NUMBER MIN MAX IF ELSE LITERAL D_RATIO SOURCE_COUNT HAS_EVENT EXPR_ERROR +%token ID NUMBER MIN MAX IF ELSE LITERAL D_RATIO SOURCE_COUNT HAS_EVENT STRCMP_CPUID_STR EXPR_ERROR %left MIN MAX IF %left '|' %left '^' @@ -56,7 +58,7 @@ static void expr_error(double *final_val __maybe_unused, struct expr_parse_ctx *ctx __maybe_unused, bool compute_ids __maybe_unused, - void *scanner, + void *scanner __maybe_unused, const char *s) { pr_debug("%s\n", s); @@ -205,6 +207,12 @@ expr: NUMBER $$.ids = NULL; free($3); } +| STRCMP_CPUID_STR '(' ID ')' +{ + $$.val = expr__strcmp_cpuid_str(ctx, compute_ids, $3); + $$.ids = NULL; + free($3); +} | expr '|' expr { if (is_const($1.val) && is_const($3.val)) { diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 52fbf526fe74..d812e1e371a7 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -456,6 +456,8 @@ static int write_cpudesc(struct feat_fd *ff, #define CPUINFO_PROC { "Processor", } #elif defined(__xtensa__) #define CPUINFO_PROC { "core ID", } +#elif defined(__loongarch__) +#define CPUINFO_PROC { "Model Name", } #else #define CPUINFO_PROC { "model name", } #endif @@ -746,20 +748,14 @@ static int write_pmu_mappings(struct feat_fd *ff, * Do a first pass to count number of pmu to avoid lseek so this * works in pipe mode as well. */ - while ((pmu = perf_pmus__scan(pmu))) { - if (!pmu->name) - continue; + while ((pmu = perf_pmus__scan(pmu))) pmu_num++; - } ret = do_write(ff, &pmu_num, sizeof(pmu_num)); if (ret < 0) return ret; while ((pmu = perf_pmus__scan(pmu))) { - if (!pmu->name) - continue; - ret = do_write(ff, &pmu->type, sizeof(pmu->type)); if (ret < 0) return ret; @@ -1605,8 +1601,15 @@ static int write_pmu_caps(struct feat_fd *ff, int ret; while ((pmu = perf_pmus__scan(pmu))) { - if (!pmu->name || !strcmp(pmu->name, "cpu") || - perf_pmu__caps_parse(pmu) <= 0) + if (!strcmp(pmu->name, "cpu")) { + /* + * The "cpu" PMU is special and covered by + * HEADER_CPU_PMU_CAPS. Note, core PMUs are + * counted/written here for ARM, s390 and Intel hybrid. + */ + continue; + } + if (perf_pmu__caps_parse(pmu) <= 0) continue; nr_pmu++; } @@ -1619,23 +1622,17 @@ static int write_pmu_caps(struct feat_fd *ff, return 0; /* - * Write hybrid pmu caps first to maintain compatibility with - * older perf tool. + * Note older perf tools assume core PMUs come first, this is a property + * of perf_pmus__scan. */ - if (perf_pmus__num_core_pmus() > 1) { - pmu = NULL; - while ((pmu = perf_pmus__scan_core(pmu))) { - ret = __write_pmu_caps(ff, pmu, true); - if (ret < 0) - return ret; - } - } - pmu = NULL; while ((pmu = perf_pmus__scan(pmu))) { - if (pmu->is_core || !pmu->nr_caps) + if (!strcmp(pmu->name, "cpu")) { + /* Skip as above. */ + continue; + } + if (perf_pmu__caps_parse(pmu) <= 0) continue; - ret = __write_pmu_caps(ff, pmu, true); if (ret < 0) return ret; @@ -4381,7 +4378,8 @@ int perf_event__process_attr(struct perf_tool *tool __maybe_unused, union perf_event *event, struct evlist **pevlist) { - u32 i, ids, n_ids; + u32 i, n_ids; + u64 *ids; struct evsel *evsel; struct evlist *evlist = *pevlist; @@ -4397,9 +4395,8 @@ int perf_event__process_attr(struct perf_tool *tool __maybe_unused, evlist__add(evlist, evsel); - ids = event->header.size; - ids -= (void *)&event->attr.id - (void *)event; - n_ids = ids / sizeof(u64); + n_ids = event->header.size - sizeof(event->header) - event->attr.attr.size; + n_ids = n_ids / sizeof(u64); /* * We don't have the cpu and thread maps on the header, so * for allocating the perf_sample_id table we fake 1 cpu and @@ -4408,8 +4405,9 @@ int perf_event__process_attr(struct perf_tool *tool __maybe_unused, if (perf_evsel__alloc_id(&evsel->core, 1, n_ids)) return -ENOMEM; + ids = perf_record_header_attr_id(event); for (i = 0; i < n_ids; i++) { - perf_evlist__id_add(&evlist->core, &evsel->core, 0, i, event->attr.id[i]); + perf_evlist__id_add(&evlist->core, &evsel->core, 0, i, ids[i]); } return 0; diff --git a/tools/perf/util/libunwind/arm64.c b/tools/perf/util/libunwind/arm64.c index 014d82159656..37ecef0c53b9 100644 --- a/tools/perf/util/libunwind/arm64.c +++ b/tools/perf/util/libunwind/arm64.c @@ -18,8 +18,6 @@ * defined before including "unwind.h" */ #define LIBUNWIND__ARCH_REG_ID(regnum) libunwind__arm64_reg_id(regnum) -#define LIBUNWIND__ARCH_REG_IP PERF_REG_ARM64_PC -#define LIBUNWIND__ARCH_REG_SP PERF_REG_ARM64_SP #include "unwind.h" #include "libunwind-aarch64.h" diff --git a/tools/perf/util/libunwind/x86_32.c b/tools/perf/util/libunwind/x86_32.c index b2b92d030aef..1697dece1b74 100644 --- a/tools/perf/util/libunwind/x86_32.c +++ b/tools/perf/util/libunwind/x86_32.c @@ -18,8 +18,6 @@ * defined before including "unwind.h" */ #define LIBUNWIND__ARCH_REG_ID(regnum) libunwind__x86_reg_id(regnum) -#define LIBUNWIND__ARCH_REG_IP PERF_REG_X86_IP -#define LIBUNWIND__ARCH_REG_SP PERF_REG_X86_SP #include "unwind.h" #include "libunwind-x86.h" diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c deleted file mode 100644 index c6c9c2228578..000000000000 --- a/tools/perf/util/llvm-utils.c +++ /dev/null @@ -1,612 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (C) 2015, Wang Nan <wangnan0@huawei.com> - * Copyright (C) 2015, Huawei Inc. - */ - -#include <errno.h> -#include <limits.h> -#include <stdio.h> -#include <stdlib.h> -#include <unistd.h> -#include <linux/err.h> -#include <linux/string.h> -#include <linux/zalloc.h> -#include "debug.h" -#include "llvm-utils.h" -#include "config.h" -#include "util.h" -#include <sys/wait.h> -#include <subcmd/exec-cmd.h> - -#define CLANG_BPF_CMD_DEFAULT_TEMPLATE \ - "$CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS "\ - "-DLINUX_VERSION_CODE=$LINUX_VERSION_CODE " \ - "$CLANG_OPTIONS $PERF_BPF_INC_OPTIONS $KERNEL_INC_OPTIONS " \ - "-Wno-unused-value -Wno-pointer-sign " \ - "-working-directory $WORKING_DIR " \ - "-c \"$CLANG_SOURCE\" --target=bpf $CLANG_EMIT_LLVM -g -O2 -o - $LLVM_OPTIONS_PIPE" - -struct llvm_param llvm_param = { - .clang_path = "clang", - .llc_path = "llc", - .clang_bpf_cmd_template = CLANG_BPF_CMD_DEFAULT_TEMPLATE, - .clang_opt = NULL, - .opts = NULL, - .kbuild_dir = NULL, - .kbuild_opts = NULL, - .user_set_param = false, -}; - -static void version_notice(void); - -int perf_llvm_config(const char *var, const char *value) -{ - if (!strstarts(var, "llvm.")) - return 0; - var += sizeof("llvm.") - 1; - - if (!strcmp(var, "clang-path")) - llvm_param.clang_path = strdup(value); - else if (!strcmp(var, "clang-bpf-cmd-template")) - llvm_param.clang_bpf_cmd_template = strdup(value); - else if (!strcmp(var, "clang-opt")) - llvm_param.clang_opt = strdup(value); - else if (!strcmp(var, "kbuild-dir")) - llvm_param.kbuild_dir = strdup(value); - else if (!strcmp(var, "kbuild-opts")) - llvm_param.kbuild_opts = strdup(value); - else if (!strcmp(var, "dump-obj")) - llvm_param.dump_obj = !!perf_config_bool(var, value); - else if (!strcmp(var, "opts")) - llvm_param.opts = strdup(value); - else { - pr_debug("Invalid LLVM config option: %s\n", value); - return -1; - } - llvm_param.user_set_param = true; - return 0; -} - -static int -search_program(const char *def, const char *name, - char *output) -{ - char *env, *path, *tmp = NULL; - char buf[PATH_MAX]; - int ret; - - output[0] = '\0'; - if (def && def[0] != '\0') { - if (def[0] == '/') { - if (access(def, F_OK) == 0) { - strlcpy(output, def, PATH_MAX); - return 0; - } - } else if (def[0] != '\0') - name = def; - } - - env = getenv("PATH"); - if (!env) - return -1; - env = strdup(env); - if (!env) - return -1; - - ret = -ENOENT; - path = strtok_r(env, ":", &tmp); - while (path) { - scnprintf(buf, sizeof(buf), "%s/%s", path, name); - if (access(buf, F_OK) == 0) { - strlcpy(output, buf, PATH_MAX); - ret = 0; - break; - } - path = strtok_r(NULL, ":", &tmp); - } - - free(env); - return ret; -} - -static int search_program_and_warn(const char *def, const char *name, - char *output) -{ - int ret = search_program(def, name, output); - - if (ret) { - pr_err("ERROR:\tunable to find %s.\n" - "Hint:\tTry to install latest clang/llvm to support BPF. Check your $PATH\n" - " \tand '%s-path' option in [llvm] section of ~/.perfconfig.\n", - name, name); - version_notice(); - } - return ret; -} - -#define READ_SIZE 4096 -static int -read_from_pipe(const char *cmd, void **p_buf, size_t *p_read_sz) -{ - int err = 0; - void *buf = NULL; - FILE *file = NULL; - size_t read_sz = 0, buf_sz = 0; - char serr[STRERR_BUFSIZE]; - - file = popen(cmd, "r"); - if (!file) { - pr_err("ERROR: unable to popen cmd: %s\n", - str_error_r(errno, serr, sizeof(serr))); - return -EINVAL; - } - - while (!feof(file) && !ferror(file)) { - /* - * Make buf_sz always have obe byte extra space so we - * can put '\0' there. - */ - if (buf_sz - read_sz < READ_SIZE + 1) { - void *new_buf; - - buf_sz = read_sz + READ_SIZE + 1; - new_buf = realloc(buf, buf_sz); - - if (!new_buf) { - pr_err("ERROR: failed to realloc memory\n"); - err = -ENOMEM; - goto errout; - } - - buf = new_buf; - } - read_sz += fread(buf + read_sz, 1, READ_SIZE, file); - } - - if (buf_sz - read_sz < 1) { - pr_err("ERROR: internal error\n"); - err = -EINVAL; - goto errout; - } - - if (ferror(file)) { - pr_err("ERROR: error occurred when reading from pipe: %s\n", - str_error_r(errno, serr, sizeof(serr))); - err = -EIO; - goto errout; - } - - err = WEXITSTATUS(pclose(file)); - file = NULL; - if (err) { - err = -EINVAL; - goto errout; - } - - /* - * If buf is string, give it terminal '\0' to make our life - * easier. If buf is not string, that '\0' is out of space - * indicated by read_sz so caller won't even notice it. - */ - ((char *)buf)[read_sz] = '\0'; - - if (!p_buf) - free(buf); - else - *p_buf = buf; - - if (p_read_sz) - *p_read_sz = read_sz; - return 0; - -errout: - if (file) - pclose(file); - free(buf); - if (p_buf) - *p_buf = NULL; - if (p_read_sz) - *p_read_sz = 0; - return err; -} - -static inline void -force_set_env(const char *var, const char *value) -{ - if (value) { - setenv(var, value, 1); - pr_debug("set env: %s=%s\n", var, value); - } else { - unsetenv(var); - pr_debug("unset env: %s\n", var); - } -} - -static void -version_notice(void) -{ - pr_err( -" \tLLVM 3.7 or newer is required. Which can be found from http://llvm.org\n" -" \tYou may want to try git trunk:\n" -" \t\tgit clone http://llvm.org/git/llvm.git\n" -" \t\t and\n" -" \t\tgit clone http://llvm.org/git/clang.git\n\n" -" \tOr fetch the latest clang/llvm 3.7 from pre-built llvm packages for\n" -" \tdebian/ubuntu:\n" -" \t\thttps://apt.llvm.org/\n\n" -" \tIf you are using old version of clang, change 'clang-bpf-cmd-template'\n" -" \toption in [llvm] section of ~/.perfconfig to:\n\n" -" \t \"$CLANG_EXEC $CLANG_OPTIONS $KERNEL_INC_OPTIONS $PERF_BPF_INC_OPTIONS \\\n" -" \t -working-directory $WORKING_DIR -c $CLANG_SOURCE \\\n" -" \t -emit-llvm -o - | /path/to/llc -march=bpf -filetype=obj -o -\"\n" -" \t(Replace /path/to/llc with path to your llc)\n\n" -); -} - -static int detect_kbuild_dir(char **kbuild_dir) -{ - const char *test_dir = llvm_param.kbuild_dir; - const char *prefix_dir = ""; - const char *suffix_dir = ""; - - /* _UTSNAME_LENGTH is 65 */ - char release[128]; - - char *autoconf_path; - - int err; - - if (!test_dir) { - err = fetch_kernel_version(NULL, release, - sizeof(release)); - if (err) - return -EINVAL; - - test_dir = release; - prefix_dir = "/lib/modules/"; - suffix_dir = "/build"; - } - - err = asprintf(&autoconf_path, "%s%s%s/include/generated/autoconf.h", - prefix_dir, test_dir, suffix_dir); - if (err < 0) - return -ENOMEM; - - if (access(autoconf_path, R_OK) == 0) { - free(autoconf_path); - - err = asprintf(kbuild_dir, "%s%s%s", prefix_dir, test_dir, - suffix_dir); - if (err < 0) - return -ENOMEM; - return 0; - } - pr_debug("%s: Couldn't find \"%s\", missing kernel-devel package?.\n", - __func__, autoconf_path); - free(autoconf_path); - return -ENOENT; -} - -static const char *kinc_fetch_script = -"#!/usr/bin/env sh\n" -"if ! test -d \"$KBUILD_DIR\"\n" -"then\n" -" exit 1\n" -"fi\n" -"if ! test -f \"$KBUILD_DIR/include/generated/autoconf.h\"\n" -"then\n" -" exit 1\n" -"fi\n" -"TMPDIR=`mktemp -d`\n" -"if test -z \"$TMPDIR\"\n" -"then\n" -" exit 1\n" -"fi\n" -"cat << EOF > $TMPDIR/Makefile\n" -"obj-y := dummy.o\n" -"\\$(obj)/%.o: \\$(src)/%.c\n" -"\t@echo -n \"\\$(NOSTDINC_FLAGS) \\$(LINUXINCLUDE) \\$(EXTRA_CFLAGS)\"\n" -"\t\\$(CC) -c -o \\$@ \\$<\n" -"EOF\n" -"touch $TMPDIR/dummy.c\n" -"make -s -C $KBUILD_DIR M=$TMPDIR $KBUILD_OPTS dummy.o 2>/dev/null\n" -"RET=$?\n" -"rm -rf $TMPDIR\n" -"exit $RET\n"; - -void llvm__get_kbuild_opts(char **kbuild_dir, char **kbuild_include_opts) -{ - static char *saved_kbuild_dir; - static char *saved_kbuild_include_opts; - int err; - - if (!kbuild_dir || !kbuild_include_opts) - return; - - *kbuild_dir = NULL; - *kbuild_include_opts = NULL; - - if (saved_kbuild_dir && saved_kbuild_include_opts && - !IS_ERR(saved_kbuild_dir) && !IS_ERR(saved_kbuild_include_opts)) { - *kbuild_dir = strdup(saved_kbuild_dir); - *kbuild_include_opts = strdup(saved_kbuild_include_opts); - - if (*kbuild_dir && *kbuild_include_opts) - return; - - zfree(kbuild_dir); - zfree(kbuild_include_opts); - /* - * Don't fall through: it may breaks saved_kbuild_dir and - * saved_kbuild_include_opts if detect them again when - * memory is low. - */ - return; - } - - if (llvm_param.kbuild_dir && !llvm_param.kbuild_dir[0]) { - pr_debug("[llvm.kbuild-dir] is set to \"\" deliberately.\n"); - pr_debug("Skip kbuild options detection.\n"); - goto errout; - } - - err = detect_kbuild_dir(kbuild_dir); - if (err) { - pr_warning( -"WARNING:\tunable to get correct kernel building directory.\n" -"Hint:\tSet correct kbuild directory using 'kbuild-dir' option in [llvm]\n" -" \tsection of ~/.perfconfig or set it to \"\" to suppress kbuild\n" -" \tdetection.\n\n"); - goto errout; - } - - pr_debug("Kernel build dir is set to %s\n", *kbuild_dir); - force_set_env("KBUILD_DIR", *kbuild_dir); - force_set_env("KBUILD_OPTS", llvm_param.kbuild_opts); - err = read_from_pipe(kinc_fetch_script, - (void **)kbuild_include_opts, - NULL); - if (err) { - pr_warning( -"WARNING:\tunable to get kernel include directories from '%s'\n" -"Hint:\tTry set clang include options using 'clang-bpf-cmd-template'\n" -" \toption in [llvm] section of ~/.perfconfig and set 'kbuild-dir'\n" -" \toption in [llvm] to \"\" to suppress this detection.\n\n", - *kbuild_dir); - - zfree(kbuild_dir); - goto errout; - } - - pr_debug("include option is set to %s\n", *kbuild_include_opts); - - saved_kbuild_dir = strdup(*kbuild_dir); - saved_kbuild_include_opts = strdup(*kbuild_include_opts); - - if (!saved_kbuild_dir || !saved_kbuild_include_opts) { - zfree(&saved_kbuild_dir); - zfree(&saved_kbuild_include_opts); - } - return; -errout: - saved_kbuild_dir = ERR_PTR(-EINVAL); - saved_kbuild_include_opts = ERR_PTR(-EINVAL); -} - -int llvm__get_nr_cpus(void) -{ - static int nr_cpus_avail = 0; - char serr[STRERR_BUFSIZE]; - - if (nr_cpus_avail > 0) - return nr_cpus_avail; - - nr_cpus_avail = sysconf(_SC_NPROCESSORS_CONF); - if (nr_cpus_avail <= 0) { - pr_err( -"WARNING:\tunable to get available CPUs in this system: %s\n" -" \tUse 128 instead.\n", str_error_r(errno, serr, sizeof(serr))); - nr_cpus_avail = 128; - } - return nr_cpus_avail; -} - -void llvm__dump_obj(const char *path, void *obj_buf, size_t size) -{ - char *obj_path = strdup(path); - FILE *fp; - char *p; - - if (!obj_path) { - pr_warning("WARNING: Not enough memory, skip object dumping\n"); - return; - } - - p = strrchr(obj_path, '.'); - if (!p || (strcmp(p, ".c") != 0)) { - pr_warning("WARNING: invalid llvm source path: '%s', skip object dumping\n", - obj_path); - goto out; - } - - p[1] = 'o'; - fp = fopen(obj_path, "wb"); - if (!fp) { - pr_warning("WARNING: failed to open '%s': %s, skip object dumping\n", - obj_path, strerror(errno)); - goto out; - } - - pr_debug("LLVM: dumping %s\n", obj_path); - if (fwrite(obj_buf, size, 1, fp) != 1) - pr_debug("WARNING: failed to write to file '%s': %s, skip object dumping\n", obj_path, strerror(errno)); - fclose(fp); -out: - free(obj_path); -} - -int llvm__compile_bpf(const char *path, void **p_obj_buf, - size_t *p_obj_buf_sz) -{ - size_t obj_buf_sz; - void *obj_buf = NULL; - int err, nr_cpus_avail; - unsigned int kernel_version; - char linux_version_code_str[64]; - const char *clang_opt = llvm_param.clang_opt; - char clang_path[PATH_MAX], llc_path[PATH_MAX], abspath[PATH_MAX], nr_cpus_avail_str[64]; - char serr[STRERR_BUFSIZE]; - char *kbuild_dir = NULL, *kbuild_include_opts = NULL, - *perf_bpf_include_opts = NULL; - const char *template = llvm_param.clang_bpf_cmd_template; - char *pipe_template = NULL; - const char *opts = llvm_param.opts; - char *command_echo = NULL, *command_out; - char *libbpf_include_dir = system_path(LIBBPF_INCLUDE_DIR); - - if (path[0] != '-' && realpath(path, abspath) == NULL) { - err = errno; - pr_err("ERROR: problems with path %s: %s\n", - path, str_error_r(err, serr, sizeof(serr))); - return -err; - } - - if (!template) - template = CLANG_BPF_CMD_DEFAULT_TEMPLATE; - - err = search_program_and_warn(llvm_param.clang_path, - "clang", clang_path); - if (err) - return -ENOENT; - - /* - * This is an optional work. Even it fail we can continue our - * work. Needn't check error return. - */ - llvm__get_kbuild_opts(&kbuild_dir, &kbuild_include_opts); - - nr_cpus_avail = llvm__get_nr_cpus(); - snprintf(nr_cpus_avail_str, sizeof(nr_cpus_avail_str), "%d", - nr_cpus_avail); - - if (fetch_kernel_version(&kernel_version, NULL, 0)) - kernel_version = 0; - - snprintf(linux_version_code_str, sizeof(linux_version_code_str), - "0x%x", kernel_version); - if (asprintf(&perf_bpf_include_opts, "-I%s/", libbpf_include_dir) < 0) - goto errout; - force_set_env("NR_CPUS", nr_cpus_avail_str); - force_set_env("LINUX_VERSION_CODE", linux_version_code_str); - force_set_env("CLANG_EXEC", clang_path); - force_set_env("CLANG_OPTIONS", clang_opt); - force_set_env("KERNEL_INC_OPTIONS", kbuild_include_opts); - force_set_env("PERF_BPF_INC_OPTIONS", perf_bpf_include_opts); - force_set_env("WORKING_DIR", kbuild_dir ? : "."); - - if (opts) { - err = search_program_and_warn(llvm_param.llc_path, "llc", llc_path); - if (err) - goto errout; - - err = -ENOMEM; - if (asprintf(&pipe_template, "%s -emit-llvm | %s -march=bpf %s -filetype=obj -o -", - template, llc_path, opts) < 0) { - pr_err("ERROR:\tnot enough memory to setup command line\n"); - goto errout; - } - - template = pipe_template; - - } - - /* - * Since we may reset clang's working dir, path of source file - * should be transferred into absolute path, except we want - * stdin to be source file (testing). - */ - force_set_env("CLANG_SOURCE", - (path[0] == '-') ? path : abspath); - - pr_debug("llvm compiling command template: %s\n", template); - - /* - * Below, substitute control characters for values that can cause the - * echo to misbehave, then substitute the values back. - */ - err = -ENOMEM; - if (asprintf(&command_echo, "echo -n \a%s\a", template) < 0) - goto errout; - -#define SWAP_CHAR(a, b) do { if (*p == a) *p = b; } while (0) - for (char *p = command_echo; *p; p++) { - SWAP_CHAR('<', '\001'); - SWAP_CHAR('>', '\002'); - SWAP_CHAR('"', '\003'); - SWAP_CHAR('\'', '\004'); - SWAP_CHAR('|', '\005'); - SWAP_CHAR('&', '\006'); - SWAP_CHAR('\a', '"'); - } - err = read_from_pipe(command_echo, (void **) &command_out, NULL); - if (err) - goto errout; - - for (char *p = command_out; *p; p++) { - SWAP_CHAR('\001', '<'); - SWAP_CHAR('\002', '>'); - SWAP_CHAR('\003', '"'); - SWAP_CHAR('\004', '\''); - SWAP_CHAR('\005', '|'); - SWAP_CHAR('\006', '&'); - } -#undef SWAP_CHAR - pr_debug("llvm compiling command : %s\n", command_out); - - err = read_from_pipe(template, &obj_buf, &obj_buf_sz); - if (err) { - pr_err("ERROR:\tunable to compile %s\n", path); - pr_err("Hint:\tCheck error message shown above.\n"); - pr_err("Hint:\tYou can also pre-compile it into .o using:\n"); - pr_err(" \t\tclang --target=bpf -O2 -c %s\n", path); - pr_err(" \twith proper -I and -D options.\n"); - goto errout; - } - - free(command_echo); - free(command_out); - free(kbuild_dir); - free(kbuild_include_opts); - free(perf_bpf_include_opts); - free(libbpf_include_dir); - - if (!p_obj_buf) - free(obj_buf); - else - *p_obj_buf = obj_buf; - - if (p_obj_buf_sz) - *p_obj_buf_sz = obj_buf_sz; - return 0; -errout: - free(command_echo); - free(kbuild_dir); - free(kbuild_include_opts); - free(obj_buf); - free(perf_bpf_include_opts); - free(libbpf_include_dir); - free(pipe_template); - if (p_obj_buf) - *p_obj_buf = NULL; - if (p_obj_buf_sz) - *p_obj_buf_sz = 0; - return err; -} - -int llvm__search_clang(void) -{ - char clang_path[PATH_MAX]; - - return search_program_and_warn(llvm_param.clang_path, "clang", clang_path); -} diff --git a/tools/perf/util/llvm-utils.h b/tools/perf/util/llvm-utils.h deleted file mode 100644 index 7878a0e3fa98..000000000000 --- a/tools/perf/util/llvm-utils.h +++ /dev/null @@ -1,69 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright (C) 2015, Wang Nan <wangnan0@huawei.com> - * Copyright (C) 2015, Huawei Inc. - */ -#ifndef __LLVM_UTILS_H -#define __LLVM_UTILS_H - -#include <stdbool.h> - -struct llvm_param { - /* Path of clang executable */ - const char *clang_path; - /* Path of llc executable */ - const char *llc_path; - /* - * Template of clang bpf compiling. 5 env variables - * can be used: - * $CLANG_EXEC: Path to clang. - * $CLANG_OPTIONS: Extra options to clang. - * $KERNEL_INC_OPTIONS: Kernel include directories. - * $WORKING_DIR: Kernel source directory. - * $CLANG_SOURCE: Source file to be compiled. - */ - const char *clang_bpf_cmd_template; - /* Will be filled in $CLANG_OPTIONS */ - const char *clang_opt; - /* - * If present it'll add -emit-llvm to $CLANG_OPTIONS to pipe - * the clang output to llc, useful for new llvm options not - * yet selectable via 'clang -mllvm option', such as -mattr=dwarfris - * in clang 6.0/llvm 7 - */ - const char *opts; - /* Where to find kbuild system */ - const char *kbuild_dir; - /* - * Arguments passed to make, like 'ARCH=arm' if doing cross - * compiling. Should not be used for dynamic compiling. - */ - const char *kbuild_opts; - /* - * Default is false. If set to true, write compiling result - * to object file. - */ - bool dump_obj; - /* - * Default is false. If one of the above fields is set by user - * explicitly then user_set_llvm is set to true. This is used - * for perf test. If user doesn't set anything in .perfconfig - * and clang is not found, don't trigger llvm test. - */ - bool user_set_param; -}; - -extern struct llvm_param llvm_param; -int perf_llvm_config(const char *var, const char *value); - -int llvm__compile_bpf(const char *path, void **p_obj_buf, size_t *p_obj_buf_sz); - -/* This function is for test__llvm() use only */ -int llvm__search_clang(void); - -/* Following functions are reused by builtin clang support */ -void llvm__get_kbuild_opts(char **kbuild_dir, char **kbuild_include_opts); -int llvm__get_nr_cpus(void); - -void llvm__dump_obj(const char *path, void *obj_buf, size_t size); -#endif diff --git a/tools/perf/util/lzma.c b/tools/perf/util/lzma.c index 51424cdc3b68..af9a97612f9d 100644 --- a/tools/perf/util/lzma.c +++ b/tools/perf/util/lzma.c @@ -45,15 +45,13 @@ int lzma_decompress_to_file(const char *input, int output_fd) infile = fopen(input, "rb"); if (!infile) { - pr_err("lzma: fopen failed on %s: '%s'\n", - input, strerror(errno)); + pr_debug("lzma: fopen failed on %s: '%s'\n", input, strerror(errno)); return -1; } ret = lzma_stream_decoder(&strm, UINT64_MAX, LZMA_CONCATENATED); if (ret != LZMA_OK) { - pr_err("lzma: lzma_stream_decoder failed %s (%d)\n", - lzma_strerror(ret), ret); + pr_debug("lzma: lzma_stream_decoder failed %s (%d)\n", lzma_strerror(ret), ret); goto err_fclose; } @@ -68,7 +66,7 @@ int lzma_decompress_to_file(const char *input, int output_fd) strm.avail_in = fread(buf_in, 1, sizeof(buf_in), infile); if (ferror(infile)) { - pr_err("lzma: read error: %s\n", strerror(errno)); + pr_debug("lzma: read error: %s\n", strerror(errno)); goto err_lzma_end; } @@ -82,7 +80,7 @@ int lzma_decompress_to_file(const char *input, int output_fd) ssize_t write_size = sizeof(buf_out) - strm.avail_out; if (writen(output_fd, buf_out, write_size) != write_size) { - pr_err("lzma: write error: %s\n", strerror(errno)); + pr_debug("lzma: write error: %s\n", strerror(errno)); goto err_lzma_end; } @@ -94,7 +92,7 @@ int lzma_decompress_to_file(const char *input, int output_fd) if (ret == LZMA_STREAM_END) break; - pr_err("lzma: failed %s\n", lzma_strerror(ret)); + pr_debug("lzma: failed %s\n", lzma_strerror(ret)); goto err_lzma_end; } } diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index f4cb41ee23cd..88f31b3a63ac 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1215,7 +1215,9 @@ static int machine__get_running_kernel_start(struct machine *machine, *start = addr; - err = kallsyms__get_function_start(filename, "_etext", &addr); + err = kallsyms__get_symbol_start(filename, "_edata", &addr); + if (err) + err = kallsyms__get_function_start(filename, "_etext", &addr); if (!err) *end = addr; diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c index c07fe3a90722..39ffe8ceb380 100644 --- a/tools/perf/util/mem-events.c +++ b/tools/perf/util/mem-events.c @@ -37,7 +37,7 @@ struct perf_mem_event * __weak perf_mem_events__ptr(int i) return &perf_mem_events[i]; } -char * __weak perf_mem_events__name(int i, char *pmu_name __maybe_unused) +const char * __weak perf_mem_events__name(int i, const char *pmu_name __maybe_unused) { struct perf_mem_event *e = perf_mem_events__ptr(i); @@ -53,7 +53,7 @@ char * __weak perf_mem_events__name(int i, char *pmu_name __maybe_unused) return mem_loads_name; } - return (char *)e->name; + return e->name; } __weak bool is_mem_loads_aux_event(struct evsel *leader __maybe_unused) @@ -186,7 +186,6 @@ int perf_mem_events__record_args(const char **rec_argv, int *argv_nr, int i = *argv_nr, k = 0; struct perf_mem_event *e; struct perf_pmu *pmu; - char *s; for (int j = 0; j < PERF_MEM_EVENTS__MAX; j++) { e = perf_mem_events__ptr(j); @@ -209,15 +208,16 @@ int perf_mem_events__record_args(const char **rec_argv, int *argv_nr, } while ((pmu = perf_pmus__scan(pmu)) != NULL) { + const char *s = perf_mem_events__name(j, pmu->name); + rec_argv[i++] = "-e"; - s = perf_mem_events__name(j, pmu->name); if (s) { - s = strdup(s); - if (!s) + char *copy = strdup(s); + if (!copy) return -1; - rec_argv[i++] = s; - rec_tmp[k++] = s; + rec_argv[i++] = copy; + rec_tmp[k++] = copy; } } } diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h index 12372309d60e..b40ad6ea93fc 100644 --- a/tools/perf/util/mem-events.h +++ b/tools/perf/util/mem-events.h @@ -38,7 +38,7 @@ extern unsigned int perf_mem_events__loads_ldlat; int perf_mem_events__parse(const char *str); int perf_mem_events__init(void); -char *perf_mem_events__name(int i, char *pmu_name); +const char *perf_mem_events__name(int i, const char *pmu_name); struct perf_mem_event *perf_mem_events__ptr(int i); bool is_mem_loads_aux_event(struct evsel *leader); diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index a6a5ed44a679..6231044a491e 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -527,7 +527,7 @@ void metricgroup__print(const struct print_callbacks *print_cb, void *print_stat groups.node_delete = mep_delete; table = pmu_metrics_table__find(); if (table) { - pmu_metrics_table_for_each_metric(table, + pmu_metrics_table__for_each_metric(table, metricgroup__add_to_mep_groups_callback, &groups); } @@ -1069,7 +1069,7 @@ static bool metricgroup__find_metric(const char *pmu, .pm = pm, }; - return pmu_metrics_table_for_each_metric(table, metricgroup__find_metric_callback, &data) + return pmu_metrics_table__for_each_metric(table, metricgroup__find_metric_callback, &data) ? true : false; } @@ -1255,7 +1255,7 @@ static int metricgroup__add_metric(const char *pmu, const char *metric_name, con * Iterate over all metrics seeing if metric matches either the * name or group. When it does add the metric to the list. */ - ret = pmu_metrics_table_for_each_metric(table, metricgroup__add_metric_callback, + ret = pmu_metrics_table__for_each_metric(table, metricgroup__add_metric_callback, &data); if (ret) goto out; @@ -1740,7 +1740,7 @@ bool metricgroup__has_metric(const char *pmu, const char *metric) if (!table) return false; - return pmu_metrics_table_for_each_metric(table, metricgroup__has_metric_callback, &data) + return pmu_metrics_table__for_each_metric(table, metricgroup__has_metric_callback, &data) ? true : false; } @@ -1770,7 +1770,7 @@ unsigned int metricgroups__topdown_max_level(void) if (!table) return false; - pmu_metrics_table_for_each_metric(table, metricgroup__topdown_max_level_callback, + pmu_metrics_table__for_each_metric(table, metricgroup__topdown_max_level_callback, &max_level); return max_level; } diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index c9ec0cafb69d..65608a3cba81 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -13,13 +13,12 @@ #include <subcmd/parse-options.h> #include "parse-events.h" #include "string2.h" -#include "strlist.h" -#include "bpf-loader.h" +#include "strbuf.h" #include "debug.h" #include <api/fs/tracing_path.h> #include <perf/cpumap.h> -#include "parse-events-bison.h" -#include "parse-events-flex.h" +#include <util/parse-events-bison.h> +#include <util/parse-events-flex.h> #include "pmu.h" #include "pmus.h" #include "asm/bug.h" @@ -35,7 +34,6 @@ #ifdef PARSER_DEBUG extern int parse_events_debug; #endif -int parse_events_parse(void *parse_state, void *scanner); static int get_config_terms(struct list_head *head_config, struct list_head *head_terms __maybe_unused); @@ -155,7 +153,7 @@ const char *event_type(int type) return "unknown"; } -static char *get_config_str(struct list_head *head_terms, int type_term) +static char *get_config_str(struct list_head *head_terms, enum parse_events__term_type type_term) { struct parse_events_term *term; @@ -195,38 +193,31 @@ static void fix_raw(struct list_head *config_terms, struct perf_pmu *pmu) struct parse_events_term *term; list_for_each_entry(term, config_terms, list) { - struct perf_pmu_alias *alias; - bool matched = false; + u64 num; if (term->type_term != PARSE_EVENTS__TERM_TYPE_RAW) continue; - list_for_each_entry(alias, &pmu->aliases, list) { - if (!strcmp(alias->name, term->val.str)) { - free(term->config); - term->config = term->val.str; - term->type_val = PARSE_EVENTS__TERM_TYPE_NUM; - term->type_term = PARSE_EVENTS__TERM_TYPE_USER; - term->val.num = 1; - term->no_value = true; - matched = true; - break; - } - } - if (!matched) { - u64 num; - - free(term->config); - term->config = strdup("config"); - errno = 0; - num = strtoull(term->val.str + 1, NULL, 16); - assert(errno == 0); - free(term->val.str); + if (perf_pmu__have_event(pmu, term->val.str)) { + zfree(&term->config); + term->config = term->val.str; term->type_val = PARSE_EVENTS__TERM_TYPE_NUM; - term->type_term = PARSE_EVENTS__TERM_TYPE_CONFIG; - term->val.num = num; - term->no_value = false; + term->type_term = PARSE_EVENTS__TERM_TYPE_USER; + term->val.num = 1; + term->no_value = true; + continue; } + + zfree(&term->config); + term->config = strdup("config"); + errno = 0; + num = strtoull(term->val.str + 1, NULL, 16); + assert(errno == 0); + free(term->val.str); + term->type_val = PARSE_EVENTS__TERM_TYPE_NUM; + term->type_term = PARSE_EVENTS__TERM_TYPE_CONFIG; + term->val.num = num; + term->no_value = false; } } @@ -271,7 +262,7 @@ __add_event(struct list_head *list, int *idx, evsel->core.is_pmu_core = pmu ? pmu->is_core : false; evsel->auto_merge_stats = auto_merge_stats; evsel->pmu = pmu; - evsel->pmu_name = pmu && pmu->name ? strdup(pmu->name) : NULL; + evsel->pmu_name = pmu ? strdup(pmu->name) : NULL; if (name) evsel->name = strdup(name); @@ -446,9 +437,6 @@ bool parse_events__filter_pmu(const struct parse_events_state *parse_state, if (parse_state->pmu_filter == NULL) return false; - if (pmu->name == NULL) - return true; - return strcmp(parse_state->pmu_filter, pmu->name) != 0; } @@ -499,7 +487,7 @@ int parse_events_add_cache(struct list_head *list, int *idx, const char *name, #ifdef HAVE_LIBTRACEEVENT static void tracepoint_error(struct parse_events_error *e, int err, - const char *sys, const char *name) + const char *sys, const char *name, int column) { const char *str; char help[BUFSIZ]; @@ -526,18 +514,19 @@ static void tracepoint_error(struct parse_events_error *e, int err, } tracing_path__strerror_open_tp(err, help, sizeof(help), sys, name); - parse_events_error__handle(e, 0, strdup(str), strdup(help)); + parse_events_error__handle(e, column, strdup(str), strdup(help)); } static int add_tracepoint(struct list_head *list, int *idx, const char *sys_name, const char *evt_name, struct parse_events_error *err, - struct list_head *head_config) + struct list_head *head_config, void *loc_) { + YYLTYPE *loc = loc_; struct evsel *evsel = evsel__newtp_idx(sys_name, evt_name, (*idx)++); if (IS_ERR(evsel)) { - tracepoint_error(err, PTR_ERR(evsel), sys_name, evt_name); + tracepoint_error(err, PTR_ERR(evsel), sys_name, evt_name, loc->first_column); return PTR_ERR(evsel); } @@ -556,7 +545,7 @@ static int add_tracepoint(struct list_head *list, int *idx, static int add_tracepoint_multi_event(struct list_head *list, int *idx, const char *sys_name, const char *evt_name, struct parse_events_error *err, - struct list_head *head_config) + struct list_head *head_config, YYLTYPE *loc) { char *evt_path; struct dirent *evt_ent; @@ -565,13 +554,13 @@ static int add_tracepoint_multi_event(struct list_head *list, int *idx, evt_path = get_events_file(sys_name); if (!evt_path) { - tracepoint_error(err, errno, sys_name, evt_name); + tracepoint_error(err, errno, sys_name, evt_name, loc->first_column); return -1; } evt_dir = opendir(evt_path); if (!evt_dir) { put_events_file(evt_path); - tracepoint_error(err, errno, sys_name, evt_name); + tracepoint_error(err, errno, sys_name, evt_name, loc->first_column); return -1; } @@ -588,11 +577,11 @@ static int add_tracepoint_multi_event(struct list_head *list, int *idx, found++; ret = add_tracepoint(list, idx, sys_name, evt_ent->d_name, - err, head_config); + err, head_config, loc); } if (!found) { - tracepoint_error(err, ENOENT, sys_name, evt_name); + tracepoint_error(err, ENOENT, sys_name, evt_name, loc->first_column); ret = -1; } @@ -604,19 +593,19 @@ static int add_tracepoint_multi_event(struct list_head *list, int *idx, static int add_tracepoint_event(struct list_head *list, int *idx, const char *sys_name, const char *evt_name, struct parse_events_error *err, - struct list_head *head_config) + struct list_head *head_config, YYLTYPE *loc) { return strpbrk(evt_name, "*?") ? - add_tracepoint_multi_event(list, idx, sys_name, evt_name, - err, head_config) : - add_tracepoint(list, idx, sys_name, evt_name, - err, head_config); + add_tracepoint_multi_event(list, idx, sys_name, evt_name, + err, head_config, loc) : + add_tracepoint(list, idx, sys_name, evt_name, + err, head_config, loc); } static int add_tracepoint_multi_sys(struct list_head *list, int *idx, const char *sys_name, const char *evt_name, struct parse_events_error *err, - struct list_head *head_config) + struct list_head *head_config, YYLTYPE *loc) { struct dirent *events_ent; DIR *events_dir; @@ -624,7 +613,7 @@ static int add_tracepoint_multi_sys(struct list_head *list, int *idx, events_dir = tracing_events__opendir(); if (!events_dir) { - tracepoint_error(err, errno, sys_name, evt_name); + tracepoint_error(err, errno, sys_name, evt_name, loc->first_column); return -1; } @@ -640,7 +629,7 @@ static int add_tracepoint_multi_sys(struct list_head *list, int *idx, continue; ret = add_tracepoint_event(list, idx, events_ent->d_name, - evt_name, err, head_config); + evt_name, err, head_config, loc); } closedir(events_dir); @@ -648,264 +637,6 @@ static int add_tracepoint_multi_sys(struct list_head *list, int *idx, } #endif /* HAVE_LIBTRACEEVENT */ -#ifdef HAVE_LIBBPF_SUPPORT -struct __add_bpf_event_param { - struct parse_events_state *parse_state; - struct list_head *list; - struct list_head *head_config; -}; - -static int add_bpf_event(const char *group, const char *event, int fd, struct bpf_object *obj, - void *_param) -{ - LIST_HEAD(new_evsels); - struct __add_bpf_event_param *param = _param; - struct parse_events_state *parse_state = param->parse_state; - struct list_head *list = param->list; - struct evsel *pos; - int err; - /* - * Check if we should add the event, i.e. if it is a TP but starts with a '!', - * then don't add the tracepoint, this will be used for something else, like - * adding to a BPF_MAP_TYPE_PROG_ARRAY. - * - * See tools/perf/examples/bpf/augmented_raw_syscalls.c - */ - if (group[0] == '!') - return 0; - - pr_debug("add bpf event %s:%s and attach bpf program %d\n", - group, event, fd); - - err = parse_events_add_tracepoint(&new_evsels, &parse_state->idx, group, - event, parse_state->error, - param->head_config); - if (err) { - struct evsel *evsel, *tmp; - - pr_debug("Failed to add BPF event %s:%s\n", - group, event); - list_for_each_entry_safe(evsel, tmp, &new_evsels, core.node) { - list_del_init(&evsel->core.node); - evsel__delete(evsel); - } - return err; - } - pr_debug("adding %s:%s\n", group, event); - - list_for_each_entry(pos, &new_evsels, core.node) { - pr_debug("adding %s:%s to %p\n", - group, event, pos); - pos->bpf_fd = fd; - pos->bpf_obj = obj; - } - list_splice(&new_evsels, list); - return 0; -} - -int parse_events_load_bpf_obj(struct parse_events_state *parse_state, - struct list_head *list, - struct bpf_object *obj, - struct list_head *head_config) -{ - int err; - char errbuf[BUFSIZ]; - struct __add_bpf_event_param param = {parse_state, list, head_config}; - static bool registered_unprobe_atexit = false; - - if (IS_ERR(obj) || !obj) { - snprintf(errbuf, sizeof(errbuf), - "Internal error: load bpf obj with NULL"); - err = -EINVAL; - goto errout; - } - - /* - * Register atexit handler before calling bpf__probe() so - * bpf__probe() don't need to unprobe probe points its already - * created when failure. - */ - if (!registered_unprobe_atexit) { - atexit(bpf__clear); - registered_unprobe_atexit = true; - } - - err = bpf__probe(obj); - if (err) { - bpf__strerror_probe(obj, err, errbuf, sizeof(errbuf)); - goto errout; - } - - err = bpf__load(obj); - if (err) { - bpf__strerror_load(obj, err, errbuf, sizeof(errbuf)); - goto errout; - } - - err = bpf__foreach_event(obj, add_bpf_event, ¶m); - if (err) { - snprintf(errbuf, sizeof(errbuf), - "Attach events in BPF object failed"); - goto errout; - } - - return 0; -errout: - parse_events_error__handle(parse_state->error, 0, - strdup(errbuf), strdup("(add -v to see detail)")); - return err; -} - -static int -parse_events_config_bpf(struct parse_events_state *parse_state, - struct bpf_object *obj, - struct list_head *head_config) -{ - struct parse_events_term *term; - int error_pos; - - if (!head_config || list_empty(head_config)) - return 0; - - list_for_each_entry(term, head_config, list) { - int err; - - if (term->type_term != PARSE_EVENTS__TERM_TYPE_USER) { - parse_events_error__handle(parse_state->error, term->err_term, - strdup("Invalid config term for BPF object"), - NULL); - return -EINVAL; - } - - err = bpf__config_obj(obj, term, parse_state->evlist, &error_pos); - if (err) { - char errbuf[BUFSIZ]; - int idx; - - bpf__strerror_config_obj(obj, term, parse_state->evlist, - &error_pos, err, errbuf, - sizeof(errbuf)); - - if (err == -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE) - idx = term->err_val; - else - idx = term->err_term + error_pos; - - parse_events_error__handle(parse_state->error, idx, - strdup(errbuf), - strdup( -"Hint:\tValid config terms:\n" -" \tmap:[<arraymap>].value<indices>=[value]\n" -" \tmap:[<eventmap>].event<indices>=[event]\n" -"\n" -" \twhere <indices> is something like [0,3...5] or [all]\n" -" \t(add -v to see detail)")); - return err; - } - } - return 0; -} - -/* - * Split config terms: - * perf record -e bpf.c/call-graph=fp,map:array.value[0]=1/ ... - * 'call-graph=fp' is 'evt config', should be applied to each - * events in bpf.c. - * 'map:array.value[0]=1' is 'obj config', should be processed - * with parse_events_config_bpf. - * - * Move object config terms from the first list to obj_head_config. - */ -static void -split_bpf_config_terms(struct list_head *evt_head_config, - struct list_head *obj_head_config) -{ - struct parse_events_term *term, *temp; - - /* - * Currently, all possible user config term - * belong to bpf object. parse_events__is_hardcoded_term() - * happens to be a good flag. - * - * See parse_events_config_bpf() and - * config_term_tracepoint(). - */ - list_for_each_entry_safe(term, temp, evt_head_config, list) - if (!parse_events__is_hardcoded_term(term)) - list_move_tail(&term->list, obj_head_config); -} - -int parse_events_load_bpf(struct parse_events_state *parse_state, - struct list_head *list, - char *bpf_file_name, - bool source, - struct list_head *head_config) -{ - int err; - struct bpf_object *obj; - LIST_HEAD(obj_head_config); - - if (head_config) - split_bpf_config_terms(head_config, &obj_head_config); - - obj = bpf__prepare_load(bpf_file_name, source); - if (IS_ERR(obj)) { - char errbuf[BUFSIZ]; - - err = PTR_ERR(obj); - - if (err == -ENOTSUP) - snprintf(errbuf, sizeof(errbuf), - "BPF support is not compiled"); - else - bpf__strerror_prepare_load(bpf_file_name, - source, - -err, errbuf, - sizeof(errbuf)); - - parse_events_error__handle(parse_state->error, 0, - strdup(errbuf), strdup("(add -v to see detail)")); - return err; - } - - err = parse_events_load_bpf_obj(parse_state, list, obj, head_config); - if (err) - return err; - err = parse_events_config_bpf(parse_state, obj, &obj_head_config); - - /* - * Caller doesn't know anything about obj_head_config, - * so combine them together again before returning. - */ - if (head_config) - list_splice_tail(&obj_head_config, head_config); - return err; -} -#else // HAVE_LIBBPF_SUPPORT -int parse_events_load_bpf_obj(struct parse_events_state *parse_state, - struct list_head *list __maybe_unused, - struct bpf_object *obj __maybe_unused, - struct list_head *head_config __maybe_unused) -{ - parse_events_error__handle(parse_state->error, 0, - strdup("BPF support is not compiled"), - strdup("Make sure libbpf-devel is available at build time.")); - return -ENOTSUP; -} - -int parse_events_load_bpf(struct parse_events_state *parse_state, - struct list_head *list __maybe_unused, - char *bpf_file_name __maybe_unused, - bool source __maybe_unused, - struct list_head *head_config __maybe_unused) -{ - parse_events_error__handle(parse_state->error, 0, - strdup("BPF support is not compiled"), - strdup("Make sure libbpf-devel is available at build time.")); - return -ENOTSUP; -} -#endif // HAVE_LIBBPF_SUPPORT - static int parse_breakpoint_type(const char *type, struct perf_event_attr *attr) { @@ -991,7 +722,7 @@ int parse_events_add_breakpoint(struct parse_events_state *parse_state, static int check_type_val(struct parse_events_term *term, struct parse_events_error *err, - int type) + enum parse_events__term_val_type type) { if (type == term->type_val) return 0; @@ -1006,42 +737,49 @@ static int check_type_val(struct parse_events_term *term, return -EINVAL; } -/* - * Update according to parse-events.l - */ -static const char *config_term_names[__PARSE_EVENTS__TERM_TYPE_NR] = { - [PARSE_EVENTS__TERM_TYPE_USER] = "<sysfs term>", - [PARSE_EVENTS__TERM_TYPE_CONFIG] = "config", - [PARSE_EVENTS__TERM_TYPE_CONFIG1] = "config1", - [PARSE_EVENTS__TERM_TYPE_CONFIG2] = "config2", - [PARSE_EVENTS__TERM_TYPE_CONFIG3] = "config3", - [PARSE_EVENTS__TERM_TYPE_NAME] = "name", - [PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD] = "period", - [PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ] = "freq", - [PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE] = "branch_type", - [PARSE_EVENTS__TERM_TYPE_TIME] = "time", - [PARSE_EVENTS__TERM_TYPE_CALLGRAPH] = "call-graph", - [PARSE_EVENTS__TERM_TYPE_STACKSIZE] = "stack-size", - [PARSE_EVENTS__TERM_TYPE_NOINHERIT] = "no-inherit", - [PARSE_EVENTS__TERM_TYPE_INHERIT] = "inherit", - [PARSE_EVENTS__TERM_TYPE_MAX_STACK] = "max-stack", - [PARSE_EVENTS__TERM_TYPE_MAX_EVENTS] = "nr", - [PARSE_EVENTS__TERM_TYPE_OVERWRITE] = "overwrite", - [PARSE_EVENTS__TERM_TYPE_NOOVERWRITE] = "no-overwrite", - [PARSE_EVENTS__TERM_TYPE_DRV_CFG] = "driver-config", - [PARSE_EVENTS__TERM_TYPE_PERCORE] = "percore", - [PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT] = "aux-output", - [PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE] = "aux-sample-size", - [PARSE_EVENTS__TERM_TYPE_METRIC_ID] = "metric-id", - [PARSE_EVENTS__TERM_TYPE_RAW] = "raw", - [PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE] = "legacy-cache", - [PARSE_EVENTS__TERM_TYPE_HARDWARE] = "hardware", -}; - static bool config_term_shrinked; +static const char *config_term_name(enum parse_events__term_type term_type) +{ + /* + * Update according to parse-events.l + */ + static const char *config_term_names[__PARSE_EVENTS__TERM_TYPE_NR] = { + [PARSE_EVENTS__TERM_TYPE_USER] = "<sysfs term>", + [PARSE_EVENTS__TERM_TYPE_CONFIG] = "config", + [PARSE_EVENTS__TERM_TYPE_CONFIG1] = "config1", + [PARSE_EVENTS__TERM_TYPE_CONFIG2] = "config2", + [PARSE_EVENTS__TERM_TYPE_CONFIG3] = "config3", + [PARSE_EVENTS__TERM_TYPE_NAME] = "name", + [PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD] = "period", + [PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ] = "freq", + [PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE] = "branch_type", + [PARSE_EVENTS__TERM_TYPE_TIME] = "time", + [PARSE_EVENTS__TERM_TYPE_CALLGRAPH] = "call-graph", + [PARSE_EVENTS__TERM_TYPE_STACKSIZE] = "stack-size", + [PARSE_EVENTS__TERM_TYPE_NOINHERIT] = "no-inherit", + [PARSE_EVENTS__TERM_TYPE_INHERIT] = "inherit", + [PARSE_EVENTS__TERM_TYPE_MAX_STACK] = "max-stack", + [PARSE_EVENTS__TERM_TYPE_MAX_EVENTS] = "nr", + [PARSE_EVENTS__TERM_TYPE_OVERWRITE] = "overwrite", + [PARSE_EVENTS__TERM_TYPE_NOOVERWRITE] = "no-overwrite", + [PARSE_EVENTS__TERM_TYPE_DRV_CFG] = "driver-config", + [PARSE_EVENTS__TERM_TYPE_PERCORE] = "percore", + [PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT] = "aux-output", + [PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE] = "aux-sample-size", + [PARSE_EVENTS__TERM_TYPE_METRIC_ID] = "metric-id", + [PARSE_EVENTS__TERM_TYPE_RAW] = "raw", + [PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE] = "legacy-cache", + [PARSE_EVENTS__TERM_TYPE_HARDWARE] = "hardware", + }; + if ((unsigned int)term_type >= __PARSE_EVENTS__TERM_TYPE_NR) + return "unknown term"; + + return config_term_names[term_type]; +} + static bool -config_term_avail(int term_type, struct parse_events_error *err) +config_term_avail(enum parse_events__term_type term_type, struct parse_events_error *err) { char *err_str; @@ -1063,13 +801,31 @@ config_term_avail(int term_type, struct parse_events_error *err) case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD: case PARSE_EVENTS__TERM_TYPE_PERCORE: return true; + case PARSE_EVENTS__TERM_TYPE_USER: + case PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ: + case PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE: + case PARSE_EVENTS__TERM_TYPE_TIME: + case PARSE_EVENTS__TERM_TYPE_CALLGRAPH: + case PARSE_EVENTS__TERM_TYPE_STACKSIZE: + case PARSE_EVENTS__TERM_TYPE_NOINHERIT: + case PARSE_EVENTS__TERM_TYPE_INHERIT: + case PARSE_EVENTS__TERM_TYPE_MAX_STACK: + case PARSE_EVENTS__TERM_TYPE_MAX_EVENTS: + case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE: + case PARSE_EVENTS__TERM_TYPE_OVERWRITE: + case PARSE_EVENTS__TERM_TYPE_DRV_CFG: + case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT: + case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE: + case PARSE_EVENTS__TERM_TYPE_RAW: + case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE: + case PARSE_EVENTS__TERM_TYPE_HARDWARE: default: if (!err) return false; /* term_type is validated so indexing is safe */ if (asprintf(&err_str, "'%s' is not usable in 'perf stat'", - config_term_names[term_type]) >= 0) + config_term_name(term_type)) >= 0) parse_events_error__handle(err, -1, err_str, NULL); return false; } @@ -1187,10 +943,14 @@ do { \ return -EINVAL; } break; + case PARSE_EVENTS__TERM_TYPE_DRV_CFG: + case PARSE_EVENTS__TERM_TYPE_USER: + case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE: + case PARSE_EVENTS__TERM_TYPE_HARDWARE: default: parse_events_error__handle(err, term->err_term, - strdup("unknown term"), - parse_events_formats_error_string(NULL)); + strdup(config_term_name(term->type_term)), + parse_events_formats_error_string(NULL)); return -EINVAL; } @@ -1276,10 +1036,26 @@ static int config_term_tracepoint(struct perf_event_attr *attr, case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT: case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE: return config_term_common(attr, term, err); + case PARSE_EVENTS__TERM_TYPE_USER: + case PARSE_EVENTS__TERM_TYPE_CONFIG: + case PARSE_EVENTS__TERM_TYPE_CONFIG1: + case PARSE_EVENTS__TERM_TYPE_CONFIG2: + case PARSE_EVENTS__TERM_TYPE_CONFIG3: + case PARSE_EVENTS__TERM_TYPE_NAME: + case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD: + case PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ: + case PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE: + case PARSE_EVENTS__TERM_TYPE_TIME: + case PARSE_EVENTS__TERM_TYPE_DRV_CFG: + case PARSE_EVENTS__TERM_TYPE_PERCORE: + case PARSE_EVENTS__TERM_TYPE_METRIC_ID: + case PARSE_EVENTS__TERM_TYPE_RAW: + case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE: + case PARSE_EVENTS__TERM_TYPE_HARDWARE: default: if (err) { parse_events_error__handle(err, term->err_term, - strdup("unknown term"), + strdup(config_term_name(term->type_term)), strdup("valid terms: call-graph,stack-size\n")); } return -EINVAL; @@ -1397,6 +1173,16 @@ do { \ ADD_CONFIG_TERM_VAL(AUX_SAMPLE_SIZE, aux_sample_size, term->val.num, term->weak); break; + case PARSE_EVENTS__TERM_TYPE_USER: + case PARSE_EVENTS__TERM_TYPE_CONFIG: + case PARSE_EVENTS__TERM_TYPE_CONFIG1: + case PARSE_EVENTS__TERM_TYPE_CONFIG2: + case PARSE_EVENTS__TERM_TYPE_CONFIG3: + case PARSE_EVENTS__TERM_TYPE_NAME: + case PARSE_EVENTS__TERM_TYPE_METRIC_ID: + case PARSE_EVENTS__TERM_TYPE_RAW: + case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE: + case PARSE_EVENTS__TERM_TYPE_HARDWARE: default: break; } @@ -1418,14 +1204,38 @@ static int get_config_chgs(struct perf_pmu *pmu, struct list_head *head_config, list_for_each_entry(term, head_config, list) { switch (term->type_term) { case PARSE_EVENTS__TERM_TYPE_USER: - type = perf_pmu__format_type(&pmu->format, term->config); + type = perf_pmu__format_type(pmu, term->config); if (type != PERF_PMU_FORMAT_VALUE_CONFIG) continue; - bits |= perf_pmu__format_bits(&pmu->format, term->config); + bits |= perf_pmu__format_bits(pmu, term->config); break; case PARSE_EVENTS__TERM_TYPE_CONFIG: bits = ~(u64)0; break; + case PARSE_EVENTS__TERM_TYPE_CONFIG1: + case PARSE_EVENTS__TERM_TYPE_CONFIG2: + case PARSE_EVENTS__TERM_TYPE_CONFIG3: + case PARSE_EVENTS__TERM_TYPE_NAME: + case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD: + case PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ: + case PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE: + case PARSE_EVENTS__TERM_TYPE_TIME: + case PARSE_EVENTS__TERM_TYPE_CALLGRAPH: + case PARSE_EVENTS__TERM_TYPE_STACKSIZE: + case PARSE_EVENTS__TERM_TYPE_NOINHERIT: + case PARSE_EVENTS__TERM_TYPE_INHERIT: + case PARSE_EVENTS__TERM_TYPE_MAX_STACK: + case PARSE_EVENTS__TERM_TYPE_MAX_EVENTS: + case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE: + case PARSE_EVENTS__TERM_TYPE_OVERWRITE: + case PARSE_EVENTS__TERM_TYPE_DRV_CFG: + case PARSE_EVENTS__TERM_TYPE_PERCORE: + case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT: + case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE: + case PARSE_EVENTS__TERM_TYPE_METRIC_ID: + case PARSE_EVENTS__TERM_TYPE_RAW: + case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE: + case PARSE_EVENTS__TERM_TYPE_HARDWARE: default: break; } @@ -1441,8 +1251,9 @@ static int get_config_chgs(struct perf_pmu *pmu, struct list_head *head_config, int parse_events_add_tracepoint(struct list_head *list, int *idx, const char *sys, const char *event, struct parse_events_error *err, - struct list_head *head_config) + struct list_head *head_config, void *loc_) { + YYLTYPE *loc = loc_; #ifdef HAVE_LIBTRACEEVENT if (head_config) { struct perf_event_attr attr; @@ -1454,17 +1265,17 @@ int parse_events_add_tracepoint(struct list_head *list, int *idx, if (strpbrk(sys, "*?")) return add_tracepoint_multi_sys(list, idx, sys, event, - err, head_config); + err, head_config, loc); else return add_tracepoint_event(list, idx, sys, event, - err, head_config); + err, head_config, loc); #else (void)list; (void)idx; (void)sys; (void)event; (void)head_config; - parse_events_error__handle(err, 0, strdup("unsupported tracepoint"), + parse_events_error__handle(err, loc->first_column, strdup("unsupported tracepoint"), strdup("libtraceevent is necessary for tracepoint support")); return -1; #endif @@ -1557,41 +1368,44 @@ static bool config_term_percore(struct list_head *config_terms) } int parse_events_add_pmu(struct parse_events_state *parse_state, - struct list_head *list, char *name, + struct list_head *list, const char *name, struct list_head *head_config, - bool auto_merge_stats) + bool auto_merge_stats, void *loc_) { struct perf_event_attr attr; struct perf_pmu_info info; struct perf_pmu *pmu; struct evsel *evsel; struct parse_events_error *err = parse_state->error; + YYLTYPE *loc = loc_; LIST_HEAD(config_terms); pmu = parse_state->fake_pmu ?: perf_pmus__find(name); - if (verbose > 1 && !(pmu && pmu->selectable)) { - fprintf(stderr, "Attempting to add event pmu '%s' with '", - name); - if (head_config) { - struct parse_events_term *term; - - list_for_each_entry(term, head_config, list) { - fprintf(stderr, "%s,", term->config); - } - } - fprintf(stderr, "' that may result in non-fatal errors\n"); - } - if (!pmu) { char *err_str; if (asprintf(&err_str, "Cannot find PMU `%s'. Missing kernel support?", name) >= 0) - parse_events_error__handle(err, 0, err_str, NULL); + parse_events_error__handle(err, loc->first_column, err_str, NULL); return -EINVAL; } + + if (verbose > 1) { + struct strbuf sb; + + strbuf_init(&sb, /*hint=*/ 0); + if (pmu->selectable && !head_config) { + strbuf_addf(&sb, "%s//", name); + } else { + strbuf_addf(&sb, "%s/", name); + parse_events_term__to_strbuf(head_config, &sb); + strbuf_addch(&sb, '/'); + } + fprintf(stderr, "Attempt to add: %s\n", sb.buf); + strbuf_release(&sb); + } if (head_config) fix_raw(head_config, pmu); @@ -1612,20 +1426,16 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, return evsel ? 0 : -ENOMEM; } - if (!parse_state->fake_pmu && perf_pmu__check_alias(pmu, head_config, &info)) + if (!parse_state->fake_pmu && perf_pmu__check_alias(pmu, head_config, &info, err)) return -EINVAL; if (verbose > 1) { - fprintf(stderr, "After aliases, add event pmu '%s' with '", - name); - if (head_config) { - struct parse_events_term *term; + struct strbuf sb; - list_for_each_entry(term, head_config, list) { - fprintf(stderr, "%s,", term->config); - } - } - fprintf(stderr, "' that may result in non-fatal errors\n"); + strbuf_init(&sb, /*hint=*/ 0); + parse_events_term__to_strbuf(head_config, &sb); + fprintf(stderr, "..after resolving event: %s/%s/\n", name, sb.buf); + strbuf_release(&sb); } /* @@ -1675,14 +1485,15 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, int parse_events_multi_pmu_add(struct parse_events_state *parse_state, char *str, struct list_head *head, - struct list_head **listp) + struct list_head **listp, void *loc_) { struct parse_events_term *term; struct list_head *list = NULL; struct list_head *orig_head = NULL; struct perf_pmu *pmu = NULL; + YYLTYPE *loc = loc_; int ok = 0; - char *config; + const char *config; *listp = NULL; @@ -1699,9 +1510,9 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, if (parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, - config, 1, false, NULL, - NULL) < 0) { - free(config); + config, /*num=*/1, /*novalue=*/true, + loc, /*loc_val=*/NULL) < 0) { + zfree(&config); goto out_err; } list_add_tail(&term->list, head); @@ -1714,33 +1525,38 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, INIT_LIST_HEAD(list); while ((pmu = perf_pmus__scan(pmu)) != NULL) { - struct perf_pmu_alias *alias; bool auto_merge_stats; if (parse_events__filter_pmu(parse_state, pmu)) continue; - auto_merge_stats = perf_pmu__auto_merge_stats(pmu); + if (!perf_pmu__have_event(pmu, str)) + continue; - list_for_each_entry(alias, &pmu->aliases, list) { - if (!strcasecmp(alias->name, str)) { - parse_events_copy_term_list(head, &orig_head); - if (!parse_events_add_pmu(parse_state, list, - pmu->name, orig_head, - auto_merge_stats)) { - pr_debug("%s -> %s/%s/\n", str, - pmu->name, alias->str); - ok++; - } - parse_events_terms__delete(orig_head); - } + auto_merge_stats = perf_pmu__auto_merge_stats(pmu); + parse_events_copy_term_list(head, &orig_head); + if (!parse_events_add_pmu(parse_state, list, pmu->name, + orig_head, auto_merge_stats, loc)) { + struct strbuf sb; + + strbuf_init(&sb, /*hint=*/ 0); + parse_events_term__to_strbuf(orig_head, &sb); + pr_debug("%s -> %s/%s/\n", str, pmu->name, sb.buf); + strbuf_release(&sb); + ok++; } + parse_events_terms__delete(orig_head); } if (parse_state->fake_pmu) { if (!parse_events_add_pmu(parse_state, list, str, head, - /*auto_merge_stats=*/true)) { - pr_debug("%s -> %s/%s/\n", str, "fake_pmu", str); + /*auto_merge_stats=*/true, loc)) { + struct strbuf sb; + + strbuf_init(&sb, /*hint=*/ 0); + parse_events_term__to_strbuf(head, &sb); + pr_debug("%s -> %s/%s/\n", str, "fake_pmu", sb.buf); + strbuf_release(&sb); ok++; } } @@ -1972,14 +1788,18 @@ int parse_events_name(struct list_head *list, const char *name) struct evsel *evsel; __evlist__for_each_entry(list, evsel) { - if (!evsel->name) + if (!evsel->name) { evsel->name = strdup(name); + if (!evsel->name) + return -ENOMEM; + } } return 0; } static int parse_events__scanner(const char *str, + FILE *input, struct parse_events_state *parse_state) { YY_BUFFER_STATE buffer; @@ -1990,7 +1810,10 @@ static int parse_events__scanner(const char *str, if (ret) return ret; - buffer = parse_events__scan_string(str, scanner); + if (str) + buffer = parse_events__scan_string(str, scanner); + else + parse_events_set_in(input, scanner); #ifdef PARSER_DEBUG parse_events_debug = 1; @@ -1998,8 +1821,10 @@ static int parse_events__scanner(const char *str, #endif ret = parse_events_parse(parse_state, scanner); - parse_events__flush_buffer(buffer, scanner); - parse_events__delete_buffer(buffer, scanner); + if (str) { + parse_events__flush_buffer(buffer, scanner); + parse_events__delete_buffer(buffer, scanner); + } parse_events_lex_destroy(scanner); return ret; } @@ -2007,7 +1832,7 @@ static int parse_events__scanner(const char *str, /* * parse event config string, return a list of event terms. */ -int parse_events_terms(struct list_head *terms, const char *str) +int parse_events_terms(struct list_head *terms, const char *str, FILE *input) { struct parse_events_state parse_state = { .terms = NULL, @@ -2015,7 +1840,7 @@ int parse_events_terms(struct list_head *terms, const char *str) }; int ret; - ret = parse_events__scanner(str, &parse_state); + ret = parse_events__scanner(str, input, &parse_state); if (!ret) { list_splice(parse_state.terms, terms); @@ -2259,7 +2084,6 @@ int __parse_events(struct evlist *evlist, const char *str, const char *pmu_filte .list = LIST_HEAD_INIT(parse_state.list), .idx = evlist->core.nr_entries, .error = err, - .evlist = evlist, .stoken = PE_START_EVENTS, .fake_pmu = fake_pmu, .pmu_filter = pmu_filter, @@ -2267,7 +2091,7 @@ int __parse_events(struct evlist *evlist, const char *str, const char *pmu_filte }; int ret, ret2; - ret = parse_events__scanner(str, &parse_state); + ret = parse_events__scanner(str, /*input=*/ NULL, &parse_state); if (!ret && list_empty(&parse_state.list)) { WARN_ONCE(true, "WARNING: event parser found nothing\n"); @@ -2348,7 +2172,7 @@ void parse_events_error__handle(struct parse_events_error *err, int idx, break; default: pr_debug("Multiple errors dropping message: %s (%s)\n", - err->str, err->help); + err->str, err->help ?: "<no help>"); free(err->str); err->str = str; free(err->help); @@ -2641,7 +2465,8 @@ static int new_term(struct parse_events_term **_term, } int parse_events_term__num(struct parse_events_term **term, - int type_term, char *config, u64 num, + enum parse_events__term_type type_term, + const char *config, u64 num, bool no_value, void *loc_term_, void *loc_val_) { @@ -2651,17 +2476,18 @@ int parse_events_term__num(struct parse_events_term **term, struct parse_events_term temp = { .type_val = PARSE_EVENTS__TERM_TYPE_NUM, .type_term = type_term, - .config = config ? : strdup(config_term_names[type_term]), + .config = config ? : strdup(config_term_name(type_term)), .no_value = no_value, .err_term = loc_term ? loc_term->first_column : 0, .err_val = loc_val ? loc_val->first_column : 0, }; - return new_term(term, &temp, NULL, num); + return new_term(term, &temp, /*str=*/NULL, num); } int parse_events_term__str(struct parse_events_term **term, - int type_term, char *config, char *str, + enum parse_events__term_type type_term, + char *config, char *str, void *loc_term_, void *loc_val_) { YYLTYPE *loc_term = loc_term_; @@ -2675,15 +2501,16 @@ int parse_events_term__str(struct parse_events_term **term, .err_val = loc_val ? loc_val->first_column : 0, }; - return new_term(term, &temp, str, 0); + return new_term(term, &temp, str, /*num=*/0); } int parse_events_term__term(struct parse_events_term **term, - int term_lhs, int term_rhs, + enum parse_events__term_type term_lhs, + enum parse_events__term_type term_rhs, void *loc_term, void *loc_val) { return parse_events_term__str(term, term_lhs, NULL, - strdup(config_term_names[term_rhs]), + strdup(config_term_name(term_rhs)), loc_term, loc_val); } @@ -2691,33 +2518,25 @@ int parse_events_term__clone(struct parse_events_term **new, struct parse_events_term *term) { char *str; - struct parse_events_term temp = { - .type_val = term->type_val, - .type_term = term->type_term, - .config = NULL, - .err_term = term->err_term, - .err_val = term->err_val, - }; + struct parse_events_term temp = *term; + temp.used = false; if (term->config) { temp.config = strdup(term->config); if (!temp.config) return -ENOMEM; } if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM) - return new_term(new, &temp, NULL, term->val.num); + return new_term(new, &temp, /*str=*/NULL, term->val.num); str = strdup(term->val.str); if (!str) return -ENOMEM; - return new_term(new, &temp, str, 0); + return new_term(new, &temp, str, /*num=*/0); } void parse_events_term__delete(struct parse_events_term *term) { - if (term->array.nr_ranges) - zfree(&term->array.ranges); - if (term->type_val != PARSE_EVENTS__TERM_TYPE_NUM) zfree(&term->val.str); @@ -2768,9 +2587,47 @@ void parse_events_terms__delete(struct list_head *terms) free(terms); } -void parse_events__clear_array(struct parse_events_array *a) +int parse_events_term__to_strbuf(struct list_head *term_list, struct strbuf *sb) { - zfree(&a->ranges); + struct parse_events_term *term; + bool first = true; + + if (!term_list) + return 0; + + list_for_each_entry(term, term_list, list) { + int ret; + + if (!first) { + ret = strbuf_addch(sb, ','); + if (ret < 0) + return ret; + } + first = false; + + if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM) + if (term->no_value) { + assert(term->val.num == 1); + ret = strbuf_addf(sb, "%s", term->config); + } else + ret = strbuf_addf(sb, "%s=%#"PRIx64, term->config, term->val.num); + else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR) { + if (term->config) { + ret = strbuf_addf(sb, "%s=", term->config); + if (ret < 0) + return ret; + } else if ((unsigned int)term->type_term < __PARSE_EVENTS__TERM_TYPE_NR) { + ret = strbuf_addf(sb, "%s=", config_term_name(term->type_term)); + if (ret < 0) + return ret; + } + assert(!term->no_value); + ret = strbuf_addf(sb, "%s", term->val.str); + } + if (ret < 0) + return ret; + } + return 0; } void parse_events_evlist_error(struct parse_events_state *parse_state, @@ -2789,7 +2646,7 @@ static void config_terms_list(char *buf, size_t buf_sz) buf[0] = '\0'; for (i = 0; i < __PARSE_EVENTS__TERM_TYPE_NR; i++) { - const char *name = config_term_names[i]; + const char *name = config_term_name(i); if (!config_term_avail(i, NULL)) continue; diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index b0eb95f93e9c..594e5d2dc67f 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -9,6 +9,7 @@ #include <stdbool.h> #include <linux/types.h> #include <linux/perf_event.h> +#include <stdio.h> #include <string.h> struct evsel; @@ -17,6 +18,7 @@ struct parse_events_error; struct option; struct perf_pmu; +struct strbuf; const char *event_type(int type); @@ -42,16 +44,16 @@ static inline int parse_events(struct evlist *evlist, const char *str, int parse_event(struct evlist *evlist, const char *str); -int parse_events_terms(struct list_head *terms, const char *str); +int parse_events_terms(struct list_head *terms, const char *str, FILE *input); int parse_filter(const struct option *opt, const char *str, int unset); int exclude_perf(const struct option *opt, const char *arg, int unset); -enum { +enum parse_events__term_val_type { PARSE_EVENTS__TERM_TYPE_NUM, PARSE_EVENTS__TERM_TYPE_STR, }; -enum { +enum parse_events__term_type { PARSE_EVENTS__TERM_TYPE_USER, PARSE_EVENTS__TERM_TYPE_CONFIG, PARSE_EVENTS__TERM_TYPE_CONFIG1, @@ -78,36 +80,54 @@ enum { PARSE_EVENTS__TERM_TYPE_RAW, PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE, PARSE_EVENTS__TERM_TYPE_HARDWARE, - __PARSE_EVENTS__TERM_TYPE_NR, -}; - -struct parse_events_array { - size_t nr_ranges; - struct { - unsigned int start; - size_t length; - } *ranges; +#define __PARSE_EVENTS__TERM_TYPE_NR (PARSE_EVENTS__TERM_TYPE_HARDWARE + 1) }; struct parse_events_term { - char *config; - struct parse_events_array array; + /** @list: The term list the term is a part of. */ + struct list_head list; + /** + * @config: The left-hand side of a term assignment, so the term + * "event=8" would have the config be "event" + */ + const char *config; + /** + * @val: The right-hand side of a term assignment that can either be a + * string or a number depending on type_val. + */ union { char *str; u64 num; } val; - int type_val; - int type_term; - struct list_head list; - bool used; - bool no_value; - - /* error string indexes for within parsed string */ + /** @type_val: The union variable in val to be used for the term. */ + enum parse_events__term_val_type type_val; + /** + * @type_term: A predefined term type or PARSE_EVENTS__TERM_TYPE_USER + * when not inbuilt. + */ + enum parse_events__term_type type_term; + /** + * @err_term: The column index of the term from parsing, used during + * error output. + */ int err_term; + /** + * @err_val: The column index of the val from parsing, used during error + * output. + */ int err_val; - - /* Coming from implicit alias */ + /** @used: Was the term used during parameterized-eval. */ + bool used; + /** + * @weak: A term from the sysfs or json encoding of an event that + * shouldn't override terms coming from the command line. + */ bool weak; + /** + * @no_value: Is there no value. If a numeric term has no value then the + * value is assumed to be 1. An event name also has no value. + */ + bool no_value; }; struct parse_events_error { @@ -121,17 +141,23 @@ struct parse_events_error { }; struct parse_events_state { + /* The list parsed events are placed on. */ struct list_head list; + /* The updated index used by entries as they are added. */ int idx; + /* Error information. */ struct parse_events_error *error; - struct evlist *evlist; + /* Holds returned terms for term parsing. */ struct list_head *terms; + /* Start token. */ int stoken; + /* Special fake PMU marker for testing. */ struct perf_pmu *fake_pmu; /* If non-null, when wildcard matching only match the given PMU. */ const char *pmu_filter; /* Should PE_LEGACY_NAME tokens be generated for config terms? */ bool match_legacy_cache_terms; + /* Were multiple PMUs scanned to find events? */ bool wild_card_pmus; }; @@ -140,39 +166,31 @@ bool parse_events__filter_pmu(const struct parse_events_state *parse_state, void parse_events__shrink_config_terms(void); int parse_events__is_hardcoded_term(struct parse_events_term *term); int parse_events_term__num(struct parse_events_term **term, - int type_term, char *config, u64 num, + enum parse_events__term_type type_term, + const char *config, u64 num, bool novalue, void *loc_term, void *loc_val); int parse_events_term__str(struct parse_events_term **term, - int type_term, char *config, char *str, + enum parse_events__term_type type_term, + char *config, char *str, void *loc_term, void *loc_val); int parse_events_term__term(struct parse_events_term **term, - int term_lhs, int term_rhs, + enum parse_events__term_type term_lhs, + enum parse_events__term_type term_rhs, void *loc_term, void *loc_val); int parse_events_term__clone(struct parse_events_term **new, struct parse_events_term *term); void parse_events_term__delete(struct parse_events_term *term); void parse_events_terms__delete(struct list_head *terms); void parse_events_terms__purge(struct list_head *terms); -void parse_events__clear_array(struct parse_events_array *a); +int parse_events_term__to_strbuf(struct list_head *term_list, struct strbuf *sb); int parse_events__modifier_event(struct list_head *list, char *str, bool add); int parse_events__modifier_group(struct list_head *list, char *event_mod); int parse_events_name(struct list_head *list, const char *name); int parse_events_add_tracepoint(struct list_head *list, int *idx, const char *sys, const char *event, struct parse_events_error *error, - struct list_head *head_config); -int parse_events_load_bpf(struct parse_events_state *parse_state, - struct list_head *list, - char *bpf_file_name, - bool source, - struct list_head *head_config); -/* Provide this function for perf test */ -struct bpf_object; -int parse_events_load_bpf_obj(struct parse_events_state *parse_state, - struct list_head *list, - struct bpf_object *obj, - struct list_head *head_config); + struct list_head *head_config, void *loc); int parse_events_add_numeric(struct parse_events_state *parse_state, struct list_head *list, u32 type, u64 config, @@ -190,9 +208,9 @@ int parse_events_add_breakpoint(struct parse_events_state *parse_state, u64 addr, char *type, u64 len, struct list_head *head_config); int parse_events_add_pmu(struct parse_events_state *parse_state, - struct list_head *list, char *name, + struct list_head *list, const char *name, struct list_head *head_config, - bool auto_merge_stats); + bool auto_merge_stats, void *loc); struct evsel *parse_events__add_event(int idx, struct perf_event_attr *attr, const char *name, const char *metric_id, @@ -201,7 +219,7 @@ struct evsel *parse_events__add_event(int idx, struct perf_event_attr *attr, int parse_events_multi_pmu_add(struct parse_events_state *parse_state, char *str, struct list_head *head_config, - struct list_head **listp); + struct list_head **listp, void *loc); int parse_events_copy_term_list(struct list_head *old, struct list_head **new); diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index 99335ec586ae..4ef4b6f171a0 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -68,31 +68,6 @@ static int lc_str(yyscan_t scanner, const struct parse_events_state *state) return str(scanner, state->match_legacy_cache_terms ? PE_LEGACY_CACHE : PE_NAME); } -static bool isbpf_suffix(char *text) -{ - int len = strlen(text); - - if (len < 2) - return false; - if ((text[len - 1] == 'c' || text[len - 1] == 'o') && - text[len - 2] == '.') - return true; - if (len > 4 && !strcmp(text + len - 4, ".obj")) - return true; - return false; -} - -static bool isbpf(yyscan_t scanner) -{ - char *text = parse_events_get_text(scanner); - struct stat st; - - if (!isbpf_suffix(text)) - return false; - - return stat(text, &st) == 0; -} - /* * This function is called when the parser gets two kind of input: * @@ -141,7 +116,7 @@ static int tool(yyscan_t scanner, enum perf_tool_event event) return PE_VALUE_SYM_TOOL; } -static int term(yyscan_t scanner, int type) +static int term(yyscan_t scanner, enum parse_events__term_type type) { YYSTYPE *yylval = parse_events_get_lval(scanner); @@ -175,13 +150,10 @@ do { \ %x mem %s config %x event -%x array group [^,{}/]*[{][^}]*[}][^,{}/]* event_pmu [^,{}/]+[/][^/]*[/][^,{}/]* event [^,{}/]+ -bpf_object [^,{}]+\.(o|bpf)[a-zA-Z0-9._]* -bpf_source [^,{}]+\.c[a-zA-Z0-9._]* num_dec [0-9]+ num_hex 0x[a-fA-F0-9]+ @@ -234,8 +206,6 @@ non_digit [^0-9] } {event_pmu} | -{bpf_object} | -{bpf_source} | {event} { BEGIN(INITIAL); REWIND(1); @@ -251,14 +221,6 @@ non_digit [^0-9] } } -<array>{ -"]" { BEGIN(config); return ']'; } -{num_dec} { return value(yyscanner, 10); } -{num_hex} { return value(yyscanner, 16); } -, { return ','; } -"\.\.\." { return PE_ARRAY_RANGE; } -} - <config>{ /* * Please update config_term_names when new static term is added. @@ -302,8 +264,6 @@ r0x{num_raw_hex} { return str(yyscanner, PE_RAW); } {lc_type}-{lc_op_result} { return lc_str(yyscanner, _parse_state); } {lc_type}-{lc_op_result}-{lc_op_result} { return lc_str(yyscanner, _parse_state); } {name_minus} { return str(yyscanner, PE_NAME); } -\[all\] { return PE_ARRAY_ALL; } -"[" { BEGIN(array); return '['; } @{drv_cfg_term} { return drv_str(yyscanner, PE_DRV_CFG_TERM); } } @@ -374,8 +334,6 @@ r{num_raw_hex} { return str(yyscanner, PE_RAW); } {num_hex} { return value(yyscanner, 16); } {modifier_event} { return str(yyscanner, PE_MODIFIER_EVENT); } -{bpf_object} { if (!isbpf(yyscanner)) { USER_REJECT }; return str(yyscanner, PE_BPF_OBJECT); } -{bpf_source} { if (!isbpf(yyscanner)) { USER_REJECT }; return str(yyscanner, PE_BPF_SOURCE); } {name} { return str(yyscanner, PE_NAME); } {name_tag} { return str(yyscanner, PE_NAME); } "/" { BEGIN(config); return '/'; } diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index 9f28d4b5502f..21bfe7e0d944 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -20,12 +20,14 @@ #include "parse-events.h" #include "parse-events-bison.h" +int parse_events_lex(YYSTYPE * yylval_param, YYLTYPE * yylloc_param , void *yyscanner); void parse_events_error(YYLTYPE *loc, void *parse_state, void *scanner, char const *msg); -#define ABORT_ON(val) \ +#define PE_ABORT(val) \ do { \ - if (val) \ - YYABORT; \ + if (val == -ENOMEM) \ + YYNOMEM; \ + YYABORT; \ } while (0) static struct list_head* alloc_list(void) @@ -58,13 +60,10 @@ static void free_list_evsel(struct list_head* list_evsel) %token PE_VALUE_SYM_TOOL %token PE_EVENT_NAME %token PE_RAW PE_NAME -%token PE_BPF_OBJECT PE_BPF_SOURCE %token PE_MODIFIER_EVENT PE_MODIFIER_BP PE_BP_COLON PE_BP_SLASH %token PE_LEGACY_CACHE -%token PE_PREFIX_MEM PE_PREFIX_RAW PE_PREFIX_GROUP +%token PE_PREFIX_MEM %token PE_ERROR -%token PE_KERNEL_PMU_EVENT PE_PMU_EVENT_FAKE -%token PE_ARRAY_ALL PE_ARRAY_RANGE %token PE_DRV_CFG_TERM %token PE_TERM_HW %type <num> PE_VALUE @@ -75,13 +74,10 @@ static void free_list_evsel(struct list_head* list_evsel) %type <num> value_sym %type <str> PE_RAW %type <str> PE_NAME -%type <str> PE_BPF_OBJECT -%type <str> PE_BPF_SOURCE %type <str> PE_LEGACY_CACHE %type <str> PE_MODIFIER_EVENT %type <str> PE_MODIFIER_BP %type <str> PE_EVENT_NAME -%type <str> PE_KERNEL_PMU_EVENT PE_PMU_EVENT_FAKE %type <str> PE_DRV_CFG_TERM %type <str> name_or_raw name_or_legacy %destructor { free ($$); } <str> @@ -98,7 +94,6 @@ static void free_list_evsel(struct list_head* list_evsel) %type <list_evsel> event_legacy_tracepoint %type <list_evsel> event_legacy_numeric %type <list_evsel> event_legacy_raw -%type <list_evsel> event_bpf_file %type <list_evsel> event_def %type <list_evsel> event_mod %type <list_evsel> event_name @@ -109,11 +104,6 @@ static void free_list_evsel(struct list_head* list_evsel) %type <list_evsel> groups %destructor { free_list_evsel ($$); } <list_evsel> %type <tracepoint_name> tracepoint_name -%destructor { free ($$.sys); free ($$.event); } <tracepoint_name> -%type <array> array -%type <array> array_term -%type <array> array_terms -%destructor { free ($$.ranges); } <array> %type <hardware_term> PE_TERM_HW %destructor { free ($$.str); } <hardware_term> @@ -128,7 +118,6 @@ static void free_list_evsel(struct list_head* list_evsel) char *sys; char *event; } tracepoint_name; - struct parse_events_array array; struct hardware_term { char *str; u64 num; @@ -265,7 +254,7 @@ PE_EVENT_NAME event_def free($1); if (err) { free_list_evsel($2); - YYABORT; + YYNOMEM; } $$ = $2; } @@ -278,47 +267,47 @@ event_def: event_pmu | event_legacy_mem sep_dc | event_legacy_tracepoint sep_dc | event_legacy_numeric sep_dc | - event_legacy_raw sep_dc | - event_bpf_file + event_legacy_raw sep_dc event_pmu: PE_NAME opt_pmu_config { struct parse_events_state *parse_state = _parse_state; - struct parse_events_error *error = parse_state->error; struct list_head *list = NULL, *orig_terms = NULL, *terms= NULL; char *pattern = NULL; -#define CLEANUP_YYABORT \ +#define CLEANUP \ do { \ parse_events_terms__delete($2); \ parse_events_terms__delete(orig_terms); \ free(list); \ free($1); \ free(pattern); \ - YYABORT; \ } while(0) - if (parse_events_copy_term_list($2, &orig_terms)) - CLEANUP_YYABORT; - - if (error) - error->idx = @1.first_column; + if (parse_events_copy_term_list($2, &orig_terms)) { + CLEANUP; + YYNOMEM; + } list = alloc_list(); - if (!list) - CLEANUP_YYABORT; + if (!list) { + CLEANUP; + YYNOMEM; + } /* Attempt to add to list assuming $1 is a PMU name. */ - if (parse_events_add_pmu(parse_state, list, $1, $2, /*auto_merge_stats=*/false)) { + if (parse_events_add_pmu(parse_state, list, $1, $2, /*auto_merge_stats=*/false, &@1)) { struct perf_pmu *pmu = NULL; int ok = 0; /* Failure to add, try wildcard expansion of $1 as a PMU name. */ - if (asprintf(&pattern, "%s*", $1) < 0) - CLEANUP_YYABORT; + if (asprintf(&pattern, "%s*", $1) < 0) { + CLEANUP; + YYNOMEM; + } while ((pmu = perf_pmus__scan(pmu)) != NULL) { - char *name = pmu->name; + const char *name = pmu->name; if (parse_events__filter_pmu(parse_state, pmu)) continue; @@ -330,10 +319,12 @@ PE_NAME opt_pmu_config !perf_pmu__match(pattern, pmu->alias_name, $1)) { bool auto_merge_stats = perf_pmu__auto_merge_stats(pmu); - if (parse_events_copy_term_list(orig_terms, &terms)) - CLEANUP_YYABORT; + if (parse_events_copy_term_list(orig_terms, &terms)) { + CLEANUP; + YYNOMEM; + } if (!parse_events_add_pmu(parse_state, list, pmu->name, terms, - auto_merge_stats)) { + auto_merge_stats, &@1)) { ok++; parse_state->wild_card_pmus = true; } @@ -344,30 +335,26 @@ PE_NAME opt_pmu_config if (!ok) { /* Failure to add, assume $1 is an event name. */ zfree(&list); - ok = !parse_events_multi_pmu_add(parse_state, $1, $2, &list); + ok = !parse_events_multi_pmu_add(parse_state, $1, $2, &list, &@1); $2 = NULL; } - if (!ok) - CLEANUP_YYABORT; + if (!ok) { + struct parse_events_error *error = parse_state->error; + char *help; + + if (asprintf(&help, "Unable to find PMU or event on a PMU of '%s'", $1) < 0) + help = NULL; + parse_events_error__handle(error, @1.first_column, + strdup("Bad event or PMU"), + help); + CLEANUP; + YYABORT; + } } - parse_events_terms__delete($2); - parse_events_terms__delete(orig_terms); - free(pattern); - free($1); - $$ = list; -#undef CLEANUP_YYABORT -} -| -PE_KERNEL_PMU_EVENT sep_dc -{ - struct list_head *list; - int err; - - err = parse_events_multi_pmu_add(_parse_state, $1, NULL, &list); - free($1); - if (err < 0) - YYABORT; $$ = list; + list = NULL; + CLEANUP; +#undef CLEANUP } | PE_NAME sep_dc @@ -375,61 +362,19 @@ PE_NAME sep_dc struct list_head *list; int err; - err = parse_events_multi_pmu_add(_parse_state, $1, NULL, &list); - free($1); - if (err < 0) - YYABORT; - $$ = list; -} -| -PE_KERNEL_PMU_EVENT opt_pmu_config -{ - struct list_head *list; - int err; - - /* frees $2 */ - err = parse_events_multi_pmu_add(_parse_state, $1, $2, &list); - free($1); - if (err < 0) - YYABORT; - $$ = list; -} -| -PE_PMU_EVENT_FAKE sep_dc -{ - struct list_head *list; - int err; - - list = alloc_list(); - if (!list) - YYABORT; - - err = parse_events_add_pmu(_parse_state, list, $1, /*head_config=*/NULL, - /*auto_merge_stats=*/false); - free($1); + err = parse_events_multi_pmu_add(_parse_state, $1, NULL, &list, &@1); if (err < 0) { - free(list); - YYABORT; - } - $$ = list; -} -| -PE_PMU_EVENT_FAKE opt_pmu_config -{ - struct list_head *list; - int err; - - list = alloc_list(); - if (!list) - YYABORT; + struct parse_events_state *parse_state = _parse_state; + struct parse_events_error *error = parse_state->error; + char *help; - err = parse_events_add_pmu(_parse_state, list, $1, $2, /*auto_merge_stats=*/false); - free($1); - parse_events_terms__delete($2); - if (err < 0) { - free(list); - YYABORT; + if (asprintf(&help, "Unable to find event on a PMU of '%s'", $1) < 0) + help = NULL; + parse_events_error__handle(error, @1.first_column, strdup("Bad event name"), help); + free($1); + PE_ABORT(err); } + free($1); $$ = list; } @@ -448,12 +393,13 @@ value_sym '/' event_config '/' bool wildcard = (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_HW_CACHE); list = alloc_list(); - ABORT_ON(!list); + if (!list) + YYNOMEM; err = parse_events_add_numeric(_parse_state, list, type, config, $3, wildcard); parse_events_terms__delete($3); if (err) { free_list_evsel(list); - YYABORT; + PE_ABORT(err); } $$ = list; } @@ -464,21 +410,28 @@ value_sym sep_slash_slash_dc int type = $1 >> 16; int config = $1 & 255; bool wildcard = (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_HW_CACHE); + int err; list = alloc_list(); - ABORT_ON(!list); - ABORT_ON(parse_events_add_numeric(_parse_state, list, type, config, - /*head_config=*/NULL, wildcard)); + if (!list) + YYNOMEM; + err = parse_events_add_numeric(_parse_state, list, type, config, /*head_config=*/NULL, wildcard); + if (err) + PE_ABORT(err); $$ = list; } | PE_VALUE_SYM_TOOL sep_slash_slash_dc { struct list_head *list; + int err; list = alloc_list(); - ABORT_ON(!list); - ABORT_ON(parse_events_add_tool(_parse_state, list, $1)); + if (!list) + YYNOMEM; + err = parse_events_add_tool(_parse_state, list, $1); + if (err) + YYNOMEM; $$ = list; } @@ -490,14 +443,16 @@ PE_LEGACY_CACHE opt_event_config int err; list = alloc_list(); - ABORT_ON(!list); + if (!list) + YYNOMEM; + err = parse_events_add_cache(list, &parse_state->idx, $1, parse_state, $2); parse_events_terms__delete($2); free($1); if (err) { free_list_evsel(list); - YYABORT; + PE_ABORT(err); } $$ = list; } @@ -509,14 +464,16 @@ PE_PREFIX_MEM PE_VALUE PE_BP_SLASH PE_VALUE PE_BP_COLON PE_MODIFIER_BP opt_event int err; list = alloc_list(); - ABORT_ON(!list); + if (!list) + YYNOMEM; + err = parse_events_add_breakpoint(_parse_state, list, $2, $6, $4, $7); parse_events_terms__delete($7); free($6); if (err) { free(list); - YYABORT; + PE_ABORT(err); } $$ = list; } @@ -527,13 +484,15 @@ PE_PREFIX_MEM PE_VALUE PE_BP_SLASH PE_VALUE opt_event_config int err; list = alloc_list(); - ABORT_ON(!list); + if (!list) + YYNOMEM; + err = parse_events_add_breakpoint(_parse_state, list, $2, NULL, $4, $5); parse_events_terms__delete($5); if (err) { free(list); - YYABORT; + PE_ABORT(err); } $$ = list; } @@ -544,14 +503,16 @@ PE_PREFIX_MEM PE_VALUE PE_BP_COLON PE_MODIFIER_BP opt_event_config int err; list = alloc_list(); - ABORT_ON(!list); + if (!list) + YYNOMEM; + err = parse_events_add_breakpoint(_parse_state, list, $2, $4, 0, $5); parse_events_terms__delete($5); free($4); if (err) { free(list); - YYABORT; + PE_ABORT(err); } $$ = list; } @@ -562,13 +523,14 @@ PE_PREFIX_MEM PE_VALUE opt_event_config int err; list = alloc_list(); - ABORT_ON(!list); + if (!list) + YYNOMEM; err = parse_events_add_breakpoint(_parse_state, list, $2, NULL, 0, $3); parse_events_terms__delete($3); if (err) { free(list); - YYABORT; + PE_ABORT(err); } $$ = list; } @@ -582,19 +544,20 @@ tracepoint_name opt_event_config int err; list = alloc_list(); - ABORT_ON(!list); + if (!list) + YYNOMEM; if (error) error->idx = @1.first_column; err = parse_events_add_tracepoint(list, &parse_state->idx, $1.sys, $1.event, - error, $2); + error, $2, &@1); parse_events_terms__delete($2); free($1.sys); free($1.event); if (err) { free(list); - YYABORT; + PE_ABORT(err); } $$ = list; } @@ -614,13 +577,14 @@ PE_VALUE ':' PE_VALUE opt_event_config int err; list = alloc_list(); - ABORT_ON(!list); + if (!list) + YYNOMEM; err = parse_events_add_numeric(_parse_state, list, (u32)$1, $3, $4, /*wildcard=*/false); parse_events_terms__delete($4); if (err) { free(list); - YYABORT; + PE_ABORT(err); } $$ = list; } @@ -633,52 +597,20 @@ PE_RAW opt_event_config u64 num; list = alloc_list(); - ABORT_ON(!list); + if (!list) + YYNOMEM; errno = 0; num = strtoull($1 + 1, NULL, 16); - ABORT_ON(errno); + /* Given the lexer will only give [a-fA-F0-9]+ a failure here should be impossible. */ + if (errno) + YYABORT; free($1); err = parse_events_add_numeric(_parse_state, list, PERF_TYPE_RAW, num, $2, /*wildcard=*/false); parse_events_terms__delete($2); if (err) { free(list); - YYABORT; - } - $$ = list; -} - -event_bpf_file: -PE_BPF_OBJECT opt_event_config -{ - struct parse_events_state *parse_state = _parse_state; - struct list_head *list; - int err; - - list = alloc_list(); - ABORT_ON(!list); - err = parse_events_load_bpf(parse_state, list, $1, false, $2); - parse_events_terms__delete($2); - free($1); - if (err) { - free(list); - YYABORT; - } - $$ = list; -} -| -PE_BPF_SOURCE opt_event_config -{ - struct list_head *list; - int err; - - list = alloc_list(); - ABORT_ON(!list); - err = parse_events_load_bpf(_parse_state, list, $1, true, $2); - parse_events_terms__delete($2); - if (err) { - free(list); - YYABORT; + PE_ABORT(err); } $$ = list; } @@ -738,7 +670,8 @@ event_term struct list_head *head = malloc(sizeof(*head)); struct parse_events_term *term = $1; - ABORT_ON(!head); + if (!head) + YYNOMEM; INIT_LIST_HEAD(head); list_add_tail(&term->list, head); $$ = head; @@ -752,11 +685,12 @@ event_term: PE_RAW { struct parse_events_term *term; + int err = parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_RAW, + strdup("raw"), $1, &@1, &@1); - if (parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_RAW, - strdup("raw"), $1, &@1, &@1)) { + if (err) { free($1); - YYABORT; + PE_ABORT(err); } $$ = term; } @@ -764,12 +698,12 @@ PE_RAW name_or_raw '=' name_or_legacy { struct parse_events_term *term; + int err = parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER, $1, $3, &@1, &@3); - if (parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER, - $1, $3, &@1, &@3)) { + if (err) { free($1); free($3); - YYABORT; + PE_ABORT(err); } $$ = term; } @@ -777,11 +711,12 @@ name_or_raw '=' name_or_legacy name_or_raw '=' PE_VALUE { struct parse_events_term *term; + int err = parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, + $1, $3, /*novalue=*/false, &@1, &@3); - if (parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, - $1, $3, false, &@1, &@3)) { + if (err) { free($1); - YYABORT; + PE_ABORT(err); } $$ = term; } @@ -789,12 +724,13 @@ name_or_raw '=' PE_VALUE name_or_raw '=' PE_TERM_HW { struct parse_events_term *term; + int err = parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER, + $1, $3.str, &@1, &@3); - if (parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER, - $1, $3.str, &@1, &@3)) { + if (err) { free($1); free($3.str); - YYABORT; + PE_ABORT(err); } $$ = term; } @@ -802,11 +738,12 @@ name_or_raw '=' PE_TERM_HW PE_LEGACY_CACHE { struct parse_events_term *term; + int err = parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE, + $1, /*num=*/1, /*novalue=*/true, &@1, /*loc_val=*/NULL); - if (parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE, - $1, 1, true, &@1, NULL)) { + if (err) { free($1); - YYABORT; + PE_ABORT(err); } $$ = term; } @@ -814,11 +751,12 @@ PE_LEGACY_CACHE PE_NAME { struct parse_events_term *term; + int err = parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, + $1, /*num=*/1, /*novalue=*/true, &@1, /*loc_val=*/NULL); - if (parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, - $1, 1, true, &@1, NULL)) { + if (err) { free($1); - YYABORT; + PE_ABORT(err); } $$ = term; } @@ -826,11 +764,13 @@ PE_NAME PE_TERM_HW { struct parse_events_term *term; + int err = parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_HARDWARE, + $1.str, $1.num & 255, /*novalue=*/false, + &@1, /*loc_val=*/NULL); - if (parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_HARDWARE, - $1.str, $1.num & 255, false, &@1, NULL)) { + if (err) { free($1.str); - YYABORT; + PE_ABORT(err); } $$ = term; } @@ -838,10 +778,12 @@ PE_TERM_HW PE_TERM '=' name_or_legacy { struct parse_events_term *term; + int err = parse_events_term__str(&term, (enum parse_events__term_type)$1, + /*config=*/NULL, $3, &@1, &@3); - if (parse_events_term__str(&term, (int)$1, NULL, $3, &@1, &@3)) { + if (err) { free($3); - YYABORT; + PE_ABORT(err); } $$ = term; } @@ -849,10 +791,12 @@ PE_TERM '=' name_or_legacy PE_TERM '=' PE_TERM_HW { struct parse_events_term *term; + int err = parse_events_term__str(&term, (enum parse_events__term_type)$1, + /*config=*/NULL, $3.str, &@1, &@3); - if (parse_events_term__str(&term, (int)$1, NULL, $3.str, &@1, &@3)) { + if (err) { free($3.str); - YYABORT; + PE_ABORT(err); } $$ = term; } @@ -860,53 +804,39 @@ PE_TERM '=' PE_TERM_HW PE_TERM '=' PE_TERM { struct parse_events_term *term; + int err = parse_events_term__term(&term, + (enum parse_events__term_type)$1, + (enum parse_events__term_type)$3, + &@1, &@3); + + if (err) + PE_ABORT(err); - ABORT_ON(parse_events_term__term(&term, (int)$1, (int)$3, &@1, &@3)); $$ = term; } | PE_TERM '=' PE_VALUE { struct parse_events_term *term; + int err = parse_events_term__num(&term, (enum parse_events__term_type)$1, + /*config=*/NULL, $3, /*novalue=*/false, &@1, &@3); + + if (err) + PE_ABORT(err); - ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, $3, false, &@1, &@3)); $$ = term; } | PE_TERM { struct parse_events_term *term; + int err = parse_events_term__num(&term, (enum parse_events__term_type)$1, + /*config=*/NULL, /*num=*/1, /*novalue=*/true, + &@1, /*loc_val=*/NULL); - ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, 1, true, &@1, NULL)); - $$ = term; -} -| -name_or_raw array '=' name_or_legacy -{ - struct parse_events_term *term; + if (err) + PE_ABORT(err); - if (parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER, - $1, $4, &@1, &@4)) { - free($1); - free($4); - free($2.ranges); - YYABORT; - } - term->array = $2; - $$ = term; -} -| -name_or_raw array '=' PE_VALUE -{ - struct parse_events_term *term; - - if (parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, - $1, $4, false, &@1, &@4)) { - free($1); - free($2.ranges); - YYABORT; - } - term->array = $2; $$ = term; } | @@ -914,73 +844,19 @@ PE_DRV_CFG_TERM { struct parse_events_term *term; char *config = strdup($1); + int err; - ABORT_ON(!config); - if (parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_DRV_CFG, - config, $1, &@1, NULL)) { + if (!config) + YYNOMEM; + err = parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_DRV_CFG, config, $1, &@1, NULL); + if (err) { free($1); free(config); - YYABORT; + PE_ABORT(err); } $$ = term; } -array: -'[' array_terms ']' -{ - $$ = $2; -} -| -PE_ARRAY_ALL -{ - $$.nr_ranges = 0; - $$.ranges = NULL; -} - -array_terms: -array_terms ',' array_term -{ - struct parse_events_array new_array; - - new_array.nr_ranges = $1.nr_ranges + $3.nr_ranges; - new_array.ranges = realloc($1.ranges, - sizeof(new_array.ranges[0]) * - new_array.nr_ranges); - ABORT_ON(!new_array.ranges); - memcpy(&new_array.ranges[$1.nr_ranges], $3.ranges, - $3.nr_ranges * sizeof(new_array.ranges[0])); - free($3.ranges); - $$ = new_array; -} -| -array_term - -array_term: -PE_VALUE -{ - struct parse_events_array array; - - array.nr_ranges = 1; - array.ranges = malloc(sizeof(array.ranges[0])); - ABORT_ON(!array.ranges); - array.ranges[0].start = $1; - array.ranges[0].length = 1; - $$ = array; -} -| -PE_VALUE PE_ARRAY_RANGE PE_VALUE -{ - struct parse_events_array array; - - ABORT_ON($3 < $1); - array.nr_ranges = 1; - array.ranges = malloc(sizeof(array.ranges[0])); - ABORT_ON(!array.ranges); - array.ranges[0].start = $1; - array.ranges[0].length = $3 - $1 + 1; - $$ = array; -} - sep_dc: ':' | sep_slash_slash_dc: '/' '/' | ':' | diff --git a/tools/perf/util/perf-regs-arch/Build b/tools/perf/util/perf-regs-arch/Build new file mode 100644 index 000000000000..d9d596d330a7 --- /dev/null +++ b/tools/perf/util/perf-regs-arch/Build @@ -0,0 +1,9 @@ +perf-y += perf_regs_aarch64.o +perf-y += perf_regs_arm.o +perf-y += perf_regs_csky.o +perf-y += perf_regs_loongarch.o +perf-y += perf_regs_mips.o +perf-y += perf_regs_powerpc.o +perf-y += perf_regs_riscv.o +perf-y += perf_regs_s390.o +perf-y += perf_regs_x86.o diff --git a/tools/perf/util/perf-regs-arch/perf_regs_aarch64.c b/tools/perf/util/perf-regs-arch/perf_regs_aarch64.c new file mode 100644 index 000000000000..696566c54768 --- /dev/null +++ b/tools/perf/util/perf-regs-arch/perf_regs_aarch64.c @@ -0,0 +1,96 @@ +// SPDX-License-Identifier: GPL-2.0 + +#ifdef HAVE_PERF_REGS_SUPPORT + +#include "../perf_regs.h" +#include "../../../arch/arm64/include/uapi/asm/perf_regs.h" + +const char *__perf_reg_name_arm64(int id) +{ + switch (id) { + case PERF_REG_ARM64_X0: + return "x0"; + case PERF_REG_ARM64_X1: + return "x1"; + case PERF_REG_ARM64_X2: + return "x2"; + case PERF_REG_ARM64_X3: + return "x3"; + case PERF_REG_ARM64_X4: + return "x4"; + case PERF_REG_ARM64_X5: + return "x5"; + case PERF_REG_ARM64_X6: + return "x6"; + case PERF_REG_ARM64_X7: + return "x7"; + case PERF_REG_ARM64_X8: + return "x8"; + case PERF_REG_ARM64_X9: + return "x9"; + case PERF_REG_ARM64_X10: + return "x10"; + case PERF_REG_ARM64_X11: + return "x11"; + case PERF_REG_ARM64_X12: + return "x12"; + case PERF_REG_ARM64_X13: + return "x13"; + case PERF_REG_ARM64_X14: + return "x14"; + case PERF_REG_ARM64_X15: + return "x15"; + case PERF_REG_ARM64_X16: + return "x16"; + case PERF_REG_ARM64_X17: + return "x17"; + case PERF_REG_ARM64_X18: + return "x18"; + case PERF_REG_ARM64_X19: + return "x19"; + case PERF_REG_ARM64_X20: + return "x20"; + case PERF_REG_ARM64_X21: + return "x21"; + case PERF_REG_ARM64_X22: + return "x22"; + case PERF_REG_ARM64_X23: + return "x23"; + case PERF_REG_ARM64_X24: + return "x24"; + case PERF_REG_ARM64_X25: + return "x25"; + case PERF_REG_ARM64_X26: + return "x26"; + case PERF_REG_ARM64_X27: + return "x27"; + case PERF_REG_ARM64_X28: + return "x28"; + case PERF_REG_ARM64_X29: + return "x29"; + case PERF_REG_ARM64_SP: + return "sp"; + case PERF_REG_ARM64_LR: + return "lr"; + case PERF_REG_ARM64_PC: + return "pc"; + case PERF_REG_ARM64_VG: + return "vg"; + default: + return NULL; + } + + return NULL; +} + +uint64_t __perf_reg_ip_arm64(void) +{ + return PERF_REG_ARM64_PC; +} + +uint64_t __perf_reg_sp_arm64(void) +{ + return PERF_REG_ARM64_SP; +} + +#endif diff --git a/tools/perf/util/perf-regs-arch/perf_regs_arm.c b/tools/perf/util/perf-regs-arch/perf_regs_arm.c new file mode 100644 index 000000000000..700fd07cd2aa --- /dev/null +++ b/tools/perf/util/perf-regs-arch/perf_regs_arm.c @@ -0,0 +1,60 @@ +// SPDX-License-Identifier: GPL-2.0 + +#ifdef HAVE_PERF_REGS_SUPPORT + +#include "../perf_regs.h" +#include "../../../arch/arm/include/uapi/asm/perf_regs.h" + +const char *__perf_reg_name_arm(int id) +{ + switch (id) { + case PERF_REG_ARM_R0: + return "r0"; + case PERF_REG_ARM_R1: + return "r1"; + case PERF_REG_ARM_R2: + return "r2"; + case PERF_REG_ARM_R3: + return "r3"; + case PERF_REG_ARM_R4: + return "r4"; + case PERF_REG_ARM_R5: + return "r5"; + case PERF_REG_ARM_R6: + return "r6"; + case PERF_REG_ARM_R7: + return "r7"; + case PERF_REG_ARM_R8: + return "r8"; + case PERF_REG_ARM_R9: + return "r9"; + case PERF_REG_ARM_R10: + return "r10"; + case PERF_REG_ARM_FP: + return "fp"; + case PERF_REG_ARM_IP: + return "ip"; + case PERF_REG_ARM_SP: + return "sp"; + case PERF_REG_ARM_LR: + return "lr"; + case PERF_REG_ARM_PC: + return "pc"; + default: + return NULL; + } + + return NULL; +} + +uint64_t __perf_reg_ip_arm(void) +{ + return PERF_REG_ARM_PC; +} + +uint64_t __perf_reg_sp_arm(void) +{ + return PERF_REG_ARM_SP; +} + +#endif diff --git a/tools/perf/util/perf-regs-arch/perf_regs_csky.c b/tools/perf/util/perf-regs-arch/perf_regs_csky.c new file mode 100644 index 000000000000..a2841094e096 --- /dev/null +++ b/tools/perf/util/perf-regs-arch/perf_regs_csky.c @@ -0,0 +1,100 @@ +// SPDX-License-Identifier: GPL-2.0 + +#ifdef HAVE_PERF_REGS_SUPPORT + +#include "../perf_regs.h" +#include "../../arch/csky/include/uapi/asm/perf_regs.h" + +const char *__perf_reg_name_csky(int id) +{ + switch (id) { + case PERF_REG_CSKY_A0: + return "a0"; + case PERF_REG_CSKY_A1: + return "a1"; + case PERF_REG_CSKY_A2: + return "a2"; + case PERF_REG_CSKY_A3: + return "a3"; + case PERF_REG_CSKY_REGS0: + return "regs0"; + case PERF_REG_CSKY_REGS1: + return "regs1"; + case PERF_REG_CSKY_REGS2: + return "regs2"; + case PERF_REG_CSKY_REGS3: + return "regs3"; + case PERF_REG_CSKY_REGS4: + return "regs4"; + case PERF_REG_CSKY_REGS5: + return "regs5"; + case PERF_REG_CSKY_REGS6: + return "regs6"; + case PERF_REG_CSKY_REGS7: + return "regs7"; + case PERF_REG_CSKY_REGS8: + return "regs8"; + case PERF_REG_CSKY_REGS9: + return "regs9"; + case PERF_REG_CSKY_SP: + return "sp"; + case PERF_REG_CSKY_LR: + return "lr"; + case PERF_REG_CSKY_PC: + return "pc"; +#if defined(__CSKYABIV2__) + case PERF_REG_CSKY_EXREGS0: + return "exregs0"; + case PERF_REG_CSKY_EXREGS1: + return "exregs1"; + case PERF_REG_CSKY_EXREGS2: + return "exregs2"; + case PERF_REG_CSKY_EXREGS3: + return "exregs3"; + case PERF_REG_CSKY_EXREGS4: + return "exregs4"; + case PERF_REG_CSKY_EXREGS5: + return "exregs5"; + case PERF_REG_CSKY_EXREGS6: + return "exregs6"; + case PERF_REG_CSKY_EXREGS7: + return "exregs7"; + case PERF_REG_CSKY_EXREGS8: + return "exregs8"; + case PERF_REG_CSKY_EXREGS9: + return "exregs9"; + case PERF_REG_CSKY_EXREGS10: + return "exregs10"; + case PERF_REG_CSKY_EXREGS11: + return "exregs11"; + case PERF_REG_CSKY_EXREGS12: + return "exregs12"; + case PERF_REG_CSKY_EXREGS13: + return "exregs13"; + case PERF_REG_CSKY_EXREGS14: + return "exregs14"; + case PERF_REG_CSKY_TLS: + return "tls"; + case PERF_REG_CSKY_HI: + return "hi"; + case PERF_REG_CSKY_LO: + return "lo"; +#endif + default: + return NULL; + } + + return NULL; +} + +uint64_t __perf_reg_ip_csky(void) +{ + return PERF_REG_CSKY_PC; +} + +uint64_t __perf_reg_sp_csky(void) +{ + return PERF_REG_CSKY_SP; +} + +#endif diff --git a/tools/perf/util/perf-regs-arch/perf_regs_loongarch.c b/tools/perf/util/perf-regs-arch/perf_regs_loongarch.c new file mode 100644 index 000000000000..a9ba0f934123 --- /dev/null +++ b/tools/perf/util/perf-regs-arch/perf_regs_loongarch.c @@ -0,0 +1,91 @@ +// SPDX-License-Identifier: GPL-2.0 + +#ifdef HAVE_PERF_REGS_SUPPORT + +#include "../perf_regs.h" +#include "../../../arch/loongarch/include/uapi/asm/perf_regs.h" + +const char *__perf_reg_name_loongarch(int id) +{ + switch (id) { + case PERF_REG_LOONGARCH_PC: + return "PC"; + case PERF_REG_LOONGARCH_R1: + return "%r1"; + case PERF_REG_LOONGARCH_R2: + return "%r2"; + case PERF_REG_LOONGARCH_R3: + return "%r3"; + case PERF_REG_LOONGARCH_R4: + return "%r4"; + case PERF_REG_LOONGARCH_R5: + return "%r5"; + case PERF_REG_LOONGARCH_R6: + return "%r6"; + case PERF_REG_LOONGARCH_R7: + return "%r7"; + case PERF_REG_LOONGARCH_R8: + return "%r8"; + case PERF_REG_LOONGARCH_R9: + return "%r9"; + case PERF_REG_LOONGARCH_R10: + return "%r10"; + case PERF_REG_LOONGARCH_R11: + return "%r11"; + case PERF_REG_LOONGARCH_R12: + return "%r12"; + case PERF_REG_LOONGARCH_R13: + return "%r13"; + case PERF_REG_LOONGARCH_R14: + return "%r14"; + case PERF_REG_LOONGARCH_R15: + return "%r15"; + case PERF_REG_LOONGARCH_R16: + return "%r16"; + case PERF_REG_LOONGARCH_R17: + return "%r17"; + case PERF_REG_LOONGARCH_R18: + return "%r18"; + case PERF_REG_LOONGARCH_R19: + return "%r19"; + case PERF_REG_LOONGARCH_R20: + return "%r20"; + case PERF_REG_LOONGARCH_R21: + return "%r21"; + case PERF_REG_LOONGARCH_R22: + return "%r22"; + case PERF_REG_LOONGARCH_R23: + return "%r23"; + case PERF_REG_LOONGARCH_R24: + return "%r24"; + case PERF_REG_LOONGARCH_R25: + return "%r25"; + case PERF_REG_LOONGARCH_R26: + return "%r26"; + case PERF_REG_LOONGARCH_R27: + return "%r27"; + case PERF_REG_LOONGARCH_R28: + return "%r28"; + case PERF_REG_LOONGARCH_R29: + return "%r29"; + case PERF_REG_LOONGARCH_R30: + return "%r30"; + case PERF_REG_LOONGARCH_R31: + return "%r31"; + default: + break; + } + return NULL; +} + +uint64_t __perf_reg_ip_loongarch(void) +{ + return PERF_REG_LOONGARCH_PC; +} + +uint64_t __perf_reg_sp_loongarch(void) +{ + return PERF_REG_LOONGARCH_R3; +} + +#endif diff --git a/tools/perf/util/perf-regs-arch/perf_regs_mips.c b/tools/perf/util/perf-regs-arch/perf_regs_mips.c new file mode 100644 index 000000000000..5a45830cfbf5 --- /dev/null +++ b/tools/perf/util/perf-regs-arch/perf_regs_mips.c @@ -0,0 +1,87 @@ +// SPDX-License-Identifier: GPL-2.0 + +#ifdef HAVE_PERF_REGS_SUPPORT + +#include "../perf_regs.h" +#include "../../../arch/mips/include/uapi/asm/perf_regs.h" + +const char *__perf_reg_name_mips(int id) +{ + switch (id) { + case PERF_REG_MIPS_PC: + return "PC"; + case PERF_REG_MIPS_R1: + return "$1"; + case PERF_REG_MIPS_R2: + return "$2"; + case PERF_REG_MIPS_R3: + return "$3"; + case PERF_REG_MIPS_R4: + return "$4"; + case PERF_REG_MIPS_R5: + return "$5"; + case PERF_REG_MIPS_R6: + return "$6"; + case PERF_REG_MIPS_R7: + return "$7"; + case PERF_REG_MIPS_R8: + return "$8"; + case PERF_REG_MIPS_R9: + return "$9"; + case PERF_REG_MIPS_R10: + return "$10"; + case PERF_REG_MIPS_R11: + return "$11"; + case PERF_REG_MIPS_R12: + return "$12"; + case PERF_REG_MIPS_R13: + return "$13"; + case PERF_REG_MIPS_R14: + return "$14"; + case PERF_REG_MIPS_R15: + return "$15"; + case PERF_REG_MIPS_R16: + return "$16"; + case PERF_REG_MIPS_R17: + return "$17"; + case PERF_REG_MIPS_R18: + return "$18"; + case PERF_REG_MIPS_R19: + return "$19"; + case PERF_REG_MIPS_R20: + return "$20"; + case PERF_REG_MIPS_R21: + return "$21"; + case PERF_REG_MIPS_R22: + return "$22"; + case PERF_REG_MIPS_R23: + return "$23"; + case PERF_REG_MIPS_R24: + return "$24"; + case PERF_REG_MIPS_R25: + return "$25"; + case PERF_REG_MIPS_R28: + return "$28"; + case PERF_REG_MIPS_R29: + return "$29"; + case PERF_REG_MIPS_R30: + return "$30"; + case PERF_REG_MIPS_R31: + return "$31"; + default: + break; + } + return NULL; +} + +uint64_t __perf_reg_ip_mips(void) +{ + return PERF_REG_MIPS_PC; +} + +uint64_t __perf_reg_sp_mips(void) +{ + return PERF_REG_MIPS_R29; +} + +#endif diff --git a/tools/perf/util/perf-regs-arch/perf_regs_powerpc.c b/tools/perf/util/perf-regs-arch/perf_regs_powerpc.c new file mode 100644 index 000000000000..1f0d682db74a --- /dev/null +++ b/tools/perf/util/perf-regs-arch/perf_regs_powerpc.c @@ -0,0 +1,145 @@ +// SPDX-License-Identifier: GPL-2.0 + +#ifdef HAVE_PERF_REGS_SUPPORT + +#include "../perf_regs.h" +#include "../../../arch/powerpc/include/uapi/asm/perf_regs.h" + +const char *__perf_reg_name_powerpc(int id) +{ + switch (id) { + case PERF_REG_POWERPC_R0: + return "r0"; + case PERF_REG_POWERPC_R1: + return "r1"; + case PERF_REG_POWERPC_R2: + return "r2"; + case PERF_REG_POWERPC_R3: + return "r3"; + case PERF_REG_POWERPC_R4: + return "r4"; + case PERF_REG_POWERPC_R5: + return "r5"; + case PERF_REG_POWERPC_R6: + return "r6"; + case PERF_REG_POWERPC_R7: + return "r7"; + case PERF_REG_POWERPC_R8: + return "r8"; + case PERF_REG_POWERPC_R9: + return "r9"; + case PERF_REG_POWERPC_R10: + return "r10"; + case PERF_REG_POWERPC_R11: + return "r11"; + case PERF_REG_POWERPC_R12: + return "r12"; + case PERF_REG_POWERPC_R13: + return "r13"; + case PERF_REG_POWERPC_R14: + return "r14"; + case PERF_REG_POWERPC_R15: + return "r15"; + case PERF_REG_POWERPC_R16: + return "r16"; + case PERF_REG_POWERPC_R17: + return "r17"; + case PERF_REG_POWERPC_R18: + return "r18"; + case PERF_REG_POWERPC_R19: + return "r19"; + case PERF_REG_POWERPC_R20: + return "r20"; + case PERF_REG_POWERPC_R21: + return "r21"; + case PERF_REG_POWERPC_R22: + return "r22"; + case PERF_REG_POWERPC_R23: + return "r23"; + case PERF_REG_POWERPC_R24: + return "r24"; + case PERF_REG_POWERPC_R25: + return "r25"; + case PERF_REG_POWERPC_R26: + return "r26"; + case PERF_REG_POWERPC_R27: + return "r27"; + case PERF_REG_POWERPC_R28: + return "r28"; + case PERF_REG_POWERPC_R29: + return "r29"; + case PERF_REG_POWERPC_R30: + return "r30"; + case PERF_REG_POWERPC_R31: + return "r31"; + case PERF_REG_POWERPC_NIP: + return "nip"; + case PERF_REG_POWERPC_MSR: + return "msr"; + case PERF_REG_POWERPC_ORIG_R3: + return "orig_r3"; + case PERF_REG_POWERPC_CTR: + return "ctr"; + case PERF_REG_POWERPC_LINK: + return "link"; + case PERF_REG_POWERPC_XER: + return "xer"; + case PERF_REG_POWERPC_CCR: + return "ccr"; + case PERF_REG_POWERPC_SOFTE: + return "softe"; + case PERF_REG_POWERPC_TRAP: + return "trap"; + case PERF_REG_POWERPC_DAR: + return "dar"; + case PERF_REG_POWERPC_DSISR: + return "dsisr"; + case PERF_REG_POWERPC_SIER: + return "sier"; + case PERF_REG_POWERPC_MMCRA: + return "mmcra"; + case PERF_REG_POWERPC_MMCR0: + return "mmcr0"; + case PERF_REG_POWERPC_MMCR1: + return "mmcr1"; + case PERF_REG_POWERPC_MMCR2: + return "mmcr2"; + case PERF_REG_POWERPC_MMCR3: + return "mmcr3"; + case PERF_REG_POWERPC_SIER2: + return "sier2"; + case PERF_REG_POWERPC_SIER3: + return "sier3"; + case PERF_REG_POWERPC_PMC1: + return "pmc1"; + case PERF_REG_POWERPC_PMC2: + return "pmc2"; + case PERF_REG_POWERPC_PMC3: + return "pmc3"; + case PERF_REG_POWERPC_PMC4: + return "pmc4"; + case PERF_REG_POWERPC_PMC5: + return "pmc5"; + case PERF_REG_POWERPC_PMC6: + return "pmc6"; + case PERF_REG_POWERPC_SDAR: + return "sdar"; + case PERF_REG_POWERPC_SIAR: + return "siar"; + default: + break; + } + return NULL; +} + +uint64_t __perf_reg_ip_powerpc(void) +{ + return PERF_REG_POWERPC_NIP; +} + +uint64_t __perf_reg_sp_powerpc(void) +{ + return PERF_REG_POWERPC_R1; +} + +#endif diff --git a/tools/perf/util/perf-regs-arch/perf_regs_riscv.c b/tools/perf/util/perf-regs-arch/perf_regs_riscv.c new file mode 100644 index 000000000000..e432630be4c5 --- /dev/null +++ b/tools/perf/util/perf-regs-arch/perf_regs_riscv.c @@ -0,0 +1,92 @@ +// SPDX-License-Identifier: GPL-2.0 + +#ifdef HAVE_PERF_REGS_SUPPORT + +#include "../perf_regs.h" +#include "../../../arch/riscv/include/uapi/asm/perf_regs.h" + +const char *__perf_reg_name_riscv(int id) +{ + switch (id) { + case PERF_REG_RISCV_PC: + return "pc"; + case PERF_REG_RISCV_RA: + return "ra"; + case PERF_REG_RISCV_SP: + return "sp"; + case PERF_REG_RISCV_GP: + return "gp"; + case PERF_REG_RISCV_TP: + return "tp"; + case PERF_REG_RISCV_T0: + return "t0"; + case PERF_REG_RISCV_T1: + return "t1"; + case PERF_REG_RISCV_T2: + return "t2"; + case PERF_REG_RISCV_S0: + return "s0"; + case PERF_REG_RISCV_S1: + return "s1"; + case PERF_REG_RISCV_A0: + return "a0"; + case PERF_REG_RISCV_A1: + return "a1"; + case PERF_REG_RISCV_A2: + return "a2"; + case PERF_REG_RISCV_A3: + return "a3"; + case PERF_REG_RISCV_A4: + return "a4"; + case PERF_REG_RISCV_A5: + return "a5"; + case PERF_REG_RISCV_A6: + return "a6"; + case PERF_REG_RISCV_A7: + return "a7"; + case PERF_REG_RISCV_S2: + return "s2"; + case PERF_REG_RISCV_S3: + return "s3"; + case PERF_REG_RISCV_S4: + return "s4"; + case PERF_REG_RISCV_S5: + return "s5"; + case PERF_REG_RISCV_S6: + return "s6"; + case PERF_REG_RISCV_S7: + return "s7"; + case PERF_REG_RISCV_S8: + return "s8"; + case PERF_REG_RISCV_S9: + return "s9"; + case PERF_REG_RISCV_S10: + return "s10"; + case PERF_REG_RISCV_S11: + return "s11"; + case PERF_REG_RISCV_T3: + return "t3"; + case PERF_REG_RISCV_T4: + return "t4"; + case PERF_REG_RISCV_T5: + return "t5"; + case PERF_REG_RISCV_T6: + return "t6"; + default: + return NULL; + } + + return NULL; +} + +uint64_t __perf_reg_ip_riscv(void) +{ + return PERF_REG_RISCV_PC; +} + +uint64_t __perf_reg_sp_riscv(void) +{ + return PERF_REG_RISCV_SP; +} + +#endif diff --git a/tools/perf/util/perf-regs-arch/perf_regs_s390.c b/tools/perf/util/perf-regs-arch/perf_regs_s390.c new file mode 100644 index 000000000000..1c7a46db778c --- /dev/null +++ b/tools/perf/util/perf-regs-arch/perf_regs_s390.c @@ -0,0 +1,96 @@ +// SPDX-License-Identifier: GPL-2.0 + +#ifdef HAVE_PERF_REGS_SUPPORT + +#include "../perf_regs.h" +#include "../../../arch/s390/include/uapi/asm/perf_regs.h" + +const char *__perf_reg_name_s390(int id) +{ + switch (id) { + case PERF_REG_S390_R0: + return "R0"; + case PERF_REG_S390_R1: + return "R1"; + case PERF_REG_S390_R2: + return "R2"; + case PERF_REG_S390_R3: + return "R3"; + case PERF_REG_S390_R4: + return "R4"; + case PERF_REG_S390_R5: + return "R5"; + case PERF_REG_S390_R6: + return "R6"; + case PERF_REG_S390_R7: + return "R7"; + case PERF_REG_S390_R8: + return "R8"; + case PERF_REG_S390_R9: + return "R9"; + case PERF_REG_S390_R10: + return "R10"; + case PERF_REG_S390_R11: + return "R11"; + case PERF_REG_S390_R12: + return "R12"; + case PERF_REG_S390_R13: + return "R13"; + case PERF_REG_S390_R14: + return "R14"; + case PERF_REG_S390_R15: + return "R15"; + case PERF_REG_S390_FP0: + return "FP0"; + case PERF_REG_S390_FP1: + return "FP1"; + case PERF_REG_S390_FP2: + return "FP2"; + case PERF_REG_S390_FP3: + return "FP3"; + case PERF_REG_S390_FP4: + return "FP4"; + case PERF_REG_S390_FP5: + return "FP5"; + case PERF_REG_S390_FP6: + return "FP6"; + case PERF_REG_S390_FP7: + return "FP7"; + case PERF_REG_S390_FP8: + return "FP8"; + case PERF_REG_S390_FP9: + return "FP9"; + case PERF_REG_S390_FP10: + return "FP10"; + case PERF_REG_S390_FP11: + return "FP11"; + case PERF_REG_S390_FP12: + return "FP12"; + case PERF_REG_S390_FP13: + return "FP13"; + case PERF_REG_S390_FP14: + return "FP14"; + case PERF_REG_S390_FP15: + return "FP15"; + case PERF_REG_S390_MASK: + return "MASK"; + case PERF_REG_S390_PC: + return "PC"; + default: + return NULL; + } + + return NULL; +} + +uint64_t __perf_reg_ip_s390(void) +{ + return PERF_REG_S390_PC; +} + +uint64_t __perf_reg_sp_s390(void) +{ + return PERF_REG_S390_R15; +} + +#endif diff --git a/tools/perf/util/perf-regs-arch/perf_regs_x86.c b/tools/perf/util/perf-regs-arch/perf_regs_x86.c new file mode 100644 index 000000000000..873c620f0634 --- /dev/null +++ b/tools/perf/util/perf-regs-arch/perf_regs_x86.c @@ -0,0 +1,98 @@ +// SPDX-License-Identifier: GPL-2.0 + +#ifdef HAVE_PERF_REGS_SUPPORT + +#include "../perf_regs.h" +#include "../../../arch/x86/include/uapi/asm/perf_regs.h" + +const char *__perf_reg_name_x86(int id) +{ + switch (id) { + case PERF_REG_X86_AX: + return "AX"; + case PERF_REG_X86_BX: + return "BX"; + case PERF_REG_X86_CX: + return "CX"; + case PERF_REG_X86_DX: + return "DX"; + case PERF_REG_X86_SI: + return "SI"; + case PERF_REG_X86_DI: + return "DI"; + case PERF_REG_X86_BP: + return "BP"; + case PERF_REG_X86_SP: + return "SP"; + case PERF_REG_X86_IP: + return "IP"; + case PERF_REG_X86_FLAGS: + return "FLAGS"; + case PERF_REG_X86_CS: + return "CS"; + case PERF_REG_X86_SS: + return "SS"; + case PERF_REG_X86_DS: + return "DS"; + case PERF_REG_X86_ES: + return "ES"; + case PERF_REG_X86_FS: + return "FS"; + case PERF_REG_X86_GS: + return "GS"; + case PERF_REG_X86_R8: + return "R8"; + case PERF_REG_X86_R9: + return "R9"; + case PERF_REG_X86_R10: + return "R10"; + case PERF_REG_X86_R11: + return "R11"; + case PERF_REG_X86_R12: + return "R12"; + case PERF_REG_X86_R13: + return "R13"; + case PERF_REG_X86_R14: + return "R14"; + case PERF_REG_X86_R15: + return "R15"; + +#define XMM(x) \ + case PERF_REG_X86_XMM ## x: \ + case PERF_REG_X86_XMM ## x + 1: \ + return "XMM" #x; + XMM(0) + XMM(1) + XMM(2) + XMM(3) + XMM(4) + XMM(5) + XMM(6) + XMM(7) + XMM(8) + XMM(9) + XMM(10) + XMM(11) + XMM(12) + XMM(13) + XMM(14) + XMM(15) +#undef XMM + default: + return NULL; + } + + return NULL; +} + +uint64_t __perf_reg_ip_x86(void) +{ + return PERF_REG_X86_IP; +} + +uint64_t __perf_reg_sp_x86(void) +{ + return PERF_REG_X86_SP; +} + +#endif diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c index 9bdbaa37f813..e2275856b570 100644 --- a/tools/perf/util/perf_regs.c +++ b/tools/perf/util/perf_regs.c @@ -3,6 +3,7 @@ #include <string.h> #include "perf_regs.h" #include "util/sample.h" +#include "debug.h" int __weak arch_sdt_arg_parse_op(char *old_op __maybe_unused, char **new_op __maybe_unused) @@ -12,732 +13,16 @@ int __weak arch_sdt_arg_parse_op(char *old_op __maybe_unused, uint64_t __weak arch__intr_reg_mask(void) { - return PERF_REGS_MASK; + return 0; } uint64_t __weak arch__user_reg_mask(void) { - return PERF_REGS_MASK; + return 0; } #ifdef HAVE_PERF_REGS_SUPPORT -#define perf_event_arm_regs perf_event_arm64_regs -#include "../../arch/arm64/include/uapi/asm/perf_regs.h" -#undef perf_event_arm_regs - -#include "../../arch/arm/include/uapi/asm/perf_regs.h" -#include "../../arch/csky/include/uapi/asm/perf_regs.h" -#include "../../arch/loongarch/include/uapi/asm/perf_regs.h" -#include "../../arch/mips/include/uapi/asm/perf_regs.h" -#include "../../arch/powerpc/include/uapi/asm/perf_regs.h" -#include "../../arch/riscv/include/uapi/asm/perf_regs.h" -#include "../../arch/s390/include/uapi/asm/perf_regs.h" -#include "../../arch/x86/include/uapi/asm/perf_regs.h" - -static const char *__perf_reg_name_arm64(int id) -{ - switch (id) { - case PERF_REG_ARM64_X0: - return "x0"; - case PERF_REG_ARM64_X1: - return "x1"; - case PERF_REG_ARM64_X2: - return "x2"; - case PERF_REG_ARM64_X3: - return "x3"; - case PERF_REG_ARM64_X4: - return "x4"; - case PERF_REG_ARM64_X5: - return "x5"; - case PERF_REG_ARM64_X6: - return "x6"; - case PERF_REG_ARM64_X7: - return "x7"; - case PERF_REG_ARM64_X8: - return "x8"; - case PERF_REG_ARM64_X9: - return "x9"; - case PERF_REG_ARM64_X10: - return "x10"; - case PERF_REG_ARM64_X11: - return "x11"; - case PERF_REG_ARM64_X12: - return "x12"; - case PERF_REG_ARM64_X13: - return "x13"; - case PERF_REG_ARM64_X14: - return "x14"; - case PERF_REG_ARM64_X15: - return "x15"; - case PERF_REG_ARM64_X16: - return "x16"; - case PERF_REG_ARM64_X17: - return "x17"; - case PERF_REG_ARM64_X18: - return "x18"; - case PERF_REG_ARM64_X19: - return "x19"; - case PERF_REG_ARM64_X20: - return "x20"; - case PERF_REG_ARM64_X21: - return "x21"; - case PERF_REG_ARM64_X22: - return "x22"; - case PERF_REG_ARM64_X23: - return "x23"; - case PERF_REG_ARM64_X24: - return "x24"; - case PERF_REG_ARM64_X25: - return "x25"; - case PERF_REG_ARM64_X26: - return "x26"; - case PERF_REG_ARM64_X27: - return "x27"; - case PERF_REG_ARM64_X28: - return "x28"; - case PERF_REG_ARM64_X29: - return "x29"; - case PERF_REG_ARM64_SP: - return "sp"; - case PERF_REG_ARM64_LR: - return "lr"; - case PERF_REG_ARM64_PC: - return "pc"; - case PERF_REG_ARM64_VG: - return "vg"; - default: - return NULL; - } - - return NULL; -} - -static const char *__perf_reg_name_arm(int id) -{ - switch (id) { - case PERF_REG_ARM_R0: - return "r0"; - case PERF_REG_ARM_R1: - return "r1"; - case PERF_REG_ARM_R2: - return "r2"; - case PERF_REG_ARM_R3: - return "r3"; - case PERF_REG_ARM_R4: - return "r4"; - case PERF_REG_ARM_R5: - return "r5"; - case PERF_REG_ARM_R6: - return "r6"; - case PERF_REG_ARM_R7: - return "r7"; - case PERF_REG_ARM_R8: - return "r8"; - case PERF_REG_ARM_R9: - return "r9"; - case PERF_REG_ARM_R10: - return "r10"; - case PERF_REG_ARM_FP: - return "fp"; - case PERF_REG_ARM_IP: - return "ip"; - case PERF_REG_ARM_SP: - return "sp"; - case PERF_REG_ARM_LR: - return "lr"; - case PERF_REG_ARM_PC: - return "pc"; - default: - return NULL; - } - - return NULL; -} - -static const char *__perf_reg_name_csky(int id) -{ - switch (id) { - case PERF_REG_CSKY_A0: - return "a0"; - case PERF_REG_CSKY_A1: - return "a1"; - case PERF_REG_CSKY_A2: - return "a2"; - case PERF_REG_CSKY_A3: - return "a3"; - case PERF_REG_CSKY_REGS0: - return "regs0"; - case PERF_REG_CSKY_REGS1: - return "regs1"; - case PERF_REG_CSKY_REGS2: - return "regs2"; - case PERF_REG_CSKY_REGS3: - return "regs3"; - case PERF_REG_CSKY_REGS4: - return "regs4"; - case PERF_REG_CSKY_REGS5: - return "regs5"; - case PERF_REG_CSKY_REGS6: - return "regs6"; - case PERF_REG_CSKY_REGS7: - return "regs7"; - case PERF_REG_CSKY_REGS8: - return "regs8"; - case PERF_REG_CSKY_REGS9: - return "regs9"; - case PERF_REG_CSKY_SP: - return "sp"; - case PERF_REG_CSKY_LR: - return "lr"; - case PERF_REG_CSKY_PC: - return "pc"; -#if defined(__CSKYABIV2__) - case PERF_REG_CSKY_EXREGS0: - return "exregs0"; - case PERF_REG_CSKY_EXREGS1: - return "exregs1"; - case PERF_REG_CSKY_EXREGS2: - return "exregs2"; - case PERF_REG_CSKY_EXREGS3: - return "exregs3"; - case PERF_REG_CSKY_EXREGS4: - return "exregs4"; - case PERF_REG_CSKY_EXREGS5: - return "exregs5"; - case PERF_REG_CSKY_EXREGS6: - return "exregs6"; - case PERF_REG_CSKY_EXREGS7: - return "exregs7"; - case PERF_REG_CSKY_EXREGS8: - return "exregs8"; - case PERF_REG_CSKY_EXREGS9: - return "exregs9"; - case PERF_REG_CSKY_EXREGS10: - return "exregs10"; - case PERF_REG_CSKY_EXREGS11: - return "exregs11"; - case PERF_REG_CSKY_EXREGS12: - return "exregs12"; - case PERF_REG_CSKY_EXREGS13: - return "exregs13"; - case PERF_REG_CSKY_EXREGS14: - return "exregs14"; - case PERF_REG_CSKY_TLS: - return "tls"; - case PERF_REG_CSKY_HI: - return "hi"; - case PERF_REG_CSKY_LO: - return "lo"; -#endif - default: - return NULL; - } - - return NULL; -} - -static inline const char *__perf_reg_name_loongarch(int id) -{ - switch (id) { - case PERF_REG_LOONGARCH_PC: - return "PC"; - case PERF_REG_LOONGARCH_R1: - return "%r1"; - case PERF_REG_LOONGARCH_R2: - return "%r2"; - case PERF_REG_LOONGARCH_R3: - return "%r3"; - case PERF_REG_LOONGARCH_R4: - return "%r4"; - case PERF_REG_LOONGARCH_R5: - return "%r5"; - case PERF_REG_LOONGARCH_R6: - return "%r6"; - case PERF_REG_LOONGARCH_R7: - return "%r7"; - case PERF_REG_LOONGARCH_R8: - return "%r8"; - case PERF_REG_LOONGARCH_R9: - return "%r9"; - case PERF_REG_LOONGARCH_R10: - return "%r10"; - case PERF_REG_LOONGARCH_R11: - return "%r11"; - case PERF_REG_LOONGARCH_R12: - return "%r12"; - case PERF_REG_LOONGARCH_R13: - return "%r13"; - case PERF_REG_LOONGARCH_R14: - return "%r14"; - case PERF_REG_LOONGARCH_R15: - return "%r15"; - case PERF_REG_LOONGARCH_R16: - return "%r16"; - case PERF_REG_LOONGARCH_R17: - return "%r17"; - case PERF_REG_LOONGARCH_R18: - return "%r18"; - case PERF_REG_LOONGARCH_R19: - return "%r19"; - case PERF_REG_LOONGARCH_R20: - return "%r20"; - case PERF_REG_LOONGARCH_R21: - return "%r21"; - case PERF_REG_LOONGARCH_R22: - return "%r22"; - case PERF_REG_LOONGARCH_R23: - return "%r23"; - case PERF_REG_LOONGARCH_R24: - return "%r24"; - case PERF_REG_LOONGARCH_R25: - return "%r25"; - case PERF_REG_LOONGARCH_R26: - return "%r26"; - case PERF_REG_LOONGARCH_R27: - return "%r27"; - case PERF_REG_LOONGARCH_R28: - return "%r28"; - case PERF_REG_LOONGARCH_R29: - return "%r29"; - case PERF_REG_LOONGARCH_R30: - return "%r30"; - case PERF_REG_LOONGARCH_R31: - return "%r31"; - default: - break; - } - return NULL; -} - -static const char *__perf_reg_name_mips(int id) -{ - switch (id) { - case PERF_REG_MIPS_PC: - return "PC"; - case PERF_REG_MIPS_R1: - return "$1"; - case PERF_REG_MIPS_R2: - return "$2"; - case PERF_REG_MIPS_R3: - return "$3"; - case PERF_REG_MIPS_R4: - return "$4"; - case PERF_REG_MIPS_R5: - return "$5"; - case PERF_REG_MIPS_R6: - return "$6"; - case PERF_REG_MIPS_R7: - return "$7"; - case PERF_REG_MIPS_R8: - return "$8"; - case PERF_REG_MIPS_R9: - return "$9"; - case PERF_REG_MIPS_R10: - return "$10"; - case PERF_REG_MIPS_R11: - return "$11"; - case PERF_REG_MIPS_R12: - return "$12"; - case PERF_REG_MIPS_R13: - return "$13"; - case PERF_REG_MIPS_R14: - return "$14"; - case PERF_REG_MIPS_R15: - return "$15"; - case PERF_REG_MIPS_R16: - return "$16"; - case PERF_REG_MIPS_R17: - return "$17"; - case PERF_REG_MIPS_R18: - return "$18"; - case PERF_REG_MIPS_R19: - return "$19"; - case PERF_REG_MIPS_R20: - return "$20"; - case PERF_REG_MIPS_R21: - return "$21"; - case PERF_REG_MIPS_R22: - return "$22"; - case PERF_REG_MIPS_R23: - return "$23"; - case PERF_REG_MIPS_R24: - return "$24"; - case PERF_REG_MIPS_R25: - return "$25"; - case PERF_REG_MIPS_R28: - return "$28"; - case PERF_REG_MIPS_R29: - return "$29"; - case PERF_REG_MIPS_R30: - return "$30"; - case PERF_REG_MIPS_R31: - return "$31"; - default: - break; - } - return NULL; -} - -static const char *__perf_reg_name_powerpc(int id) -{ - switch (id) { - case PERF_REG_POWERPC_R0: - return "r0"; - case PERF_REG_POWERPC_R1: - return "r1"; - case PERF_REG_POWERPC_R2: - return "r2"; - case PERF_REG_POWERPC_R3: - return "r3"; - case PERF_REG_POWERPC_R4: - return "r4"; - case PERF_REG_POWERPC_R5: - return "r5"; - case PERF_REG_POWERPC_R6: - return "r6"; - case PERF_REG_POWERPC_R7: - return "r7"; - case PERF_REG_POWERPC_R8: - return "r8"; - case PERF_REG_POWERPC_R9: - return "r9"; - case PERF_REG_POWERPC_R10: - return "r10"; - case PERF_REG_POWERPC_R11: - return "r11"; - case PERF_REG_POWERPC_R12: - return "r12"; - case PERF_REG_POWERPC_R13: - return "r13"; - case PERF_REG_POWERPC_R14: - return "r14"; - case PERF_REG_POWERPC_R15: - return "r15"; - case PERF_REG_POWERPC_R16: - return "r16"; - case PERF_REG_POWERPC_R17: - return "r17"; - case PERF_REG_POWERPC_R18: - return "r18"; - case PERF_REG_POWERPC_R19: - return "r19"; - case PERF_REG_POWERPC_R20: - return "r20"; - case PERF_REG_POWERPC_R21: - return "r21"; - case PERF_REG_POWERPC_R22: - return "r22"; - case PERF_REG_POWERPC_R23: - return "r23"; - case PERF_REG_POWERPC_R24: - return "r24"; - case PERF_REG_POWERPC_R25: - return "r25"; - case PERF_REG_POWERPC_R26: - return "r26"; - case PERF_REG_POWERPC_R27: - return "r27"; - case PERF_REG_POWERPC_R28: - return "r28"; - case PERF_REG_POWERPC_R29: - return "r29"; - case PERF_REG_POWERPC_R30: - return "r30"; - case PERF_REG_POWERPC_R31: - return "r31"; - case PERF_REG_POWERPC_NIP: - return "nip"; - case PERF_REG_POWERPC_MSR: - return "msr"; - case PERF_REG_POWERPC_ORIG_R3: - return "orig_r3"; - case PERF_REG_POWERPC_CTR: - return "ctr"; - case PERF_REG_POWERPC_LINK: - return "link"; - case PERF_REG_POWERPC_XER: - return "xer"; - case PERF_REG_POWERPC_CCR: - return "ccr"; - case PERF_REG_POWERPC_SOFTE: - return "softe"; - case PERF_REG_POWERPC_TRAP: - return "trap"; - case PERF_REG_POWERPC_DAR: - return "dar"; - case PERF_REG_POWERPC_DSISR: - return "dsisr"; - case PERF_REG_POWERPC_SIER: - return "sier"; - case PERF_REG_POWERPC_MMCRA: - return "mmcra"; - case PERF_REG_POWERPC_MMCR0: - return "mmcr0"; - case PERF_REG_POWERPC_MMCR1: - return "mmcr1"; - case PERF_REG_POWERPC_MMCR2: - return "mmcr2"; - case PERF_REG_POWERPC_MMCR3: - return "mmcr3"; - case PERF_REG_POWERPC_SIER2: - return "sier2"; - case PERF_REG_POWERPC_SIER3: - return "sier3"; - case PERF_REG_POWERPC_PMC1: - return "pmc1"; - case PERF_REG_POWERPC_PMC2: - return "pmc2"; - case PERF_REG_POWERPC_PMC3: - return "pmc3"; - case PERF_REG_POWERPC_PMC4: - return "pmc4"; - case PERF_REG_POWERPC_PMC5: - return "pmc5"; - case PERF_REG_POWERPC_PMC6: - return "pmc6"; - case PERF_REG_POWERPC_SDAR: - return "sdar"; - case PERF_REG_POWERPC_SIAR: - return "siar"; - default: - break; - } - return NULL; -} - -static const char *__perf_reg_name_riscv(int id) -{ - switch (id) { - case PERF_REG_RISCV_PC: - return "pc"; - case PERF_REG_RISCV_RA: - return "ra"; - case PERF_REG_RISCV_SP: - return "sp"; - case PERF_REG_RISCV_GP: - return "gp"; - case PERF_REG_RISCV_TP: - return "tp"; - case PERF_REG_RISCV_T0: - return "t0"; - case PERF_REG_RISCV_T1: - return "t1"; - case PERF_REG_RISCV_T2: - return "t2"; - case PERF_REG_RISCV_S0: - return "s0"; - case PERF_REG_RISCV_S1: - return "s1"; - case PERF_REG_RISCV_A0: - return "a0"; - case PERF_REG_RISCV_A1: - return "a1"; - case PERF_REG_RISCV_A2: - return "a2"; - case PERF_REG_RISCV_A3: - return "a3"; - case PERF_REG_RISCV_A4: - return "a4"; - case PERF_REG_RISCV_A5: - return "a5"; - case PERF_REG_RISCV_A6: - return "a6"; - case PERF_REG_RISCV_A7: - return "a7"; - case PERF_REG_RISCV_S2: - return "s2"; - case PERF_REG_RISCV_S3: - return "s3"; - case PERF_REG_RISCV_S4: - return "s4"; - case PERF_REG_RISCV_S5: - return "s5"; - case PERF_REG_RISCV_S6: - return "s6"; - case PERF_REG_RISCV_S7: - return "s7"; - case PERF_REG_RISCV_S8: - return "s8"; - case PERF_REG_RISCV_S9: - return "s9"; - case PERF_REG_RISCV_S10: - return "s10"; - case PERF_REG_RISCV_S11: - return "s11"; - case PERF_REG_RISCV_T3: - return "t3"; - case PERF_REG_RISCV_T4: - return "t4"; - case PERF_REG_RISCV_T5: - return "t5"; - case PERF_REG_RISCV_T6: - return "t6"; - default: - return NULL; - } - - return NULL; -} - -static const char *__perf_reg_name_s390(int id) -{ - switch (id) { - case PERF_REG_S390_R0: - return "R0"; - case PERF_REG_S390_R1: - return "R1"; - case PERF_REG_S390_R2: - return "R2"; - case PERF_REG_S390_R3: - return "R3"; - case PERF_REG_S390_R4: - return "R4"; - case PERF_REG_S390_R5: - return "R5"; - case PERF_REG_S390_R6: - return "R6"; - case PERF_REG_S390_R7: - return "R7"; - case PERF_REG_S390_R8: - return "R8"; - case PERF_REG_S390_R9: - return "R9"; - case PERF_REG_S390_R10: - return "R10"; - case PERF_REG_S390_R11: - return "R11"; - case PERF_REG_S390_R12: - return "R12"; - case PERF_REG_S390_R13: - return "R13"; - case PERF_REG_S390_R14: - return "R14"; - case PERF_REG_S390_R15: - return "R15"; - case PERF_REG_S390_FP0: - return "FP0"; - case PERF_REG_S390_FP1: - return "FP1"; - case PERF_REG_S390_FP2: - return "FP2"; - case PERF_REG_S390_FP3: - return "FP3"; - case PERF_REG_S390_FP4: - return "FP4"; - case PERF_REG_S390_FP5: - return "FP5"; - case PERF_REG_S390_FP6: - return "FP6"; - case PERF_REG_S390_FP7: - return "FP7"; - case PERF_REG_S390_FP8: - return "FP8"; - case PERF_REG_S390_FP9: - return "FP9"; - case PERF_REG_S390_FP10: - return "FP10"; - case PERF_REG_S390_FP11: - return "FP11"; - case PERF_REG_S390_FP12: - return "FP12"; - case PERF_REG_S390_FP13: - return "FP13"; - case PERF_REG_S390_FP14: - return "FP14"; - case PERF_REG_S390_FP15: - return "FP15"; - case PERF_REG_S390_MASK: - return "MASK"; - case PERF_REG_S390_PC: - return "PC"; - default: - return NULL; - } - - return NULL; -} - -static const char *__perf_reg_name_x86(int id) -{ - switch (id) { - case PERF_REG_X86_AX: - return "AX"; - case PERF_REG_X86_BX: - return "BX"; - case PERF_REG_X86_CX: - return "CX"; - case PERF_REG_X86_DX: - return "DX"; - case PERF_REG_X86_SI: - return "SI"; - case PERF_REG_X86_DI: - return "DI"; - case PERF_REG_X86_BP: - return "BP"; - case PERF_REG_X86_SP: - return "SP"; - case PERF_REG_X86_IP: - return "IP"; - case PERF_REG_X86_FLAGS: - return "FLAGS"; - case PERF_REG_X86_CS: - return "CS"; - case PERF_REG_X86_SS: - return "SS"; - case PERF_REG_X86_DS: - return "DS"; - case PERF_REG_X86_ES: - return "ES"; - case PERF_REG_X86_FS: - return "FS"; - case PERF_REG_X86_GS: - return "GS"; - case PERF_REG_X86_R8: - return "R8"; - case PERF_REG_X86_R9: - return "R9"; - case PERF_REG_X86_R10: - return "R10"; - case PERF_REG_X86_R11: - return "R11"; - case PERF_REG_X86_R12: - return "R12"; - case PERF_REG_X86_R13: - return "R13"; - case PERF_REG_X86_R14: - return "R14"; - case PERF_REG_X86_R15: - return "R15"; - -#define XMM(x) \ - case PERF_REG_X86_XMM ## x: \ - case PERF_REG_X86_XMM ## x + 1: \ - return "XMM" #x; - XMM(0) - XMM(1) - XMM(2) - XMM(3) - XMM(4) - XMM(5) - XMM(6) - XMM(7) - XMM(8) - XMM(9) - XMM(10) - XMM(11) - XMM(12) - XMM(13) - XMM(14) - XMM(15) -#undef XMM - default: - return NULL; - } - - return NULL; -} - const char *perf_reg_name(int id, const char *arch) { const char *reg_name = NULL; @@ -790,4 +75,55 @@ out: *valp = regs->cache_regs[id]; return 0; } + +uint64_t perf_arch_reg_ip(const char *arch) +{ + if (!strcmp(arch, "arm")) + return __perf_reg_ip_arm(); + else if (!strcmp(arch, "arm64")) + return __perf_reg_ip_arm64(); + else if (!strcmp(arch, "csky")) + return __perf_reg_ip_csky(); + else if (!strcmp(arch, "loongarch")) + return __perf_reg_ip_loongarch(); + else if (!strcmp(arch, "mips")) + return __perf_reg_ip_mips(); + else if (!strcmp(arch, "powerpc")) + return __perf_reg_ip_powerpc(); + else if (!strcmp(arch, "riscv")) + return __perf_reg_ip_riscv(); + else if (!strcmp(arch, "s390")) + return __perf_reg_ip_s390(); + else if (!strcmp(arch, "x86")) + return __perf_reg_ip_x86(); + + pr_err("Fail to find IP register for arch %s, returns 0\n", arch); + return 0; +} + +uint64_t perf_arch_reg_sp(const char *arch) +{ + if (!strcmp(arch, "arm")) + return __perf_reg_sp_arm(); + else if (!strcmp(arch, "arm64")) + return __perf_reg_sp_arm64(); + else if (!strcmp(arch, "csky")) + return __perf_reg_sp_csky(); + else if (!strcmp(arch, "loongarch")) + return __perf_reg_sp_loongarch(); + else if (!strcmp(arch, "mips")) + return __perf_reg_sp_mips(); + else if (!strcmp(arch, "powerpc")) + return __perf_reg_sp_powerpc(); + else if (!strcmp(arch, "riscv")) + return __perf_reg_sp_riscv(); + else if (!strcmp(arch, "s390")) + return __perf_reg_sp_s390(); + else if (!strcmp(arch, "x86")) + return __perf_reg_sp_x86(); + + pr_err("Fail to find SP register for arch %s, returns 0\n", arch); + return 0; +} + #endif diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h index ce1127af05e4..ecd2a5362042 100644 --- a/tools/perf/util/perf_regs.h +++ b/tools/perf/util/perf_regs.h @@ -30,18 +30,49 @@ uint64_t arch__user_reg_mask(void); #ifdef HAVE_PERF_REGS_SUPPORT extern const struct sample_reg sample_reg_masks[]; -#include <perf_regs.h> - -#define DWARF_MINIMAL_REGS ((1ULL << PERF_REG_IP) | (1ULL << PERF_REG_SP)) - const char *perf_reg_name(int id, const char *arch); int perf_reg_value(u64 *valp, struct regs_dump *regs, int id); +uint64_t perf_arch_reg_ip(const char *arch); +uint64_t perf_arch_reg_sp(const char *arch); +const char *__perf_reg_name_arm64(int id); +uint64_t __perf_reg_ip_arm64(void); +uint64_t __perf_reg_sp_arm64(void); +const char *__perf_reg_name_arm(int id); +uint64_t __perf_reg_ip_arm(void); +uint64_t __perf_reg_sp_arm(void); +const char *__perf_reg_name_csky(int id); +uint64_t __perf_reg_ip_csky(void); +uint64_t __perf_reg_sp_csky(void); +const char *__perf_reg_name_loongarch(int id); +uint64_t __perf_reg_ip_loongarch(void); +uint64_t __perf_reg_sp_loongarch(void); +const char *__perf_reg_name_mips(int id); +uint64_t __perf_reg_ip_mips(void); +uint64_t __perf_reg_sp_mips(void); +const char *__perf_reg_name_powerpc(int id); +uint64_t __perf_reg_ip_powerpc(void); +uint64_t __perf_reg_sp_powerpc(void); +const char *__perf_reg_name_riscv(int id); +uint64_t __perf_reg_ip_riscv(void); +uint64_t __perf_reg_sp_riscv(void); +const char *__perf_reg_name_s390(int id); +uint64_t __perf_reg_ip_s390(void); +uint64_t __perf_reg_sp_s390(void); +const char *__perf_reg_name_x86(int id); +uint64_t __perf_reg_ip_x86(void); +uint64_t __perf_reg_sp_x86(void); + +static inline uint64_t DWARF_MINIMAL_REGS(const char *arch) +{ + return (1ULL << perf_arch_reg_ip(arch)) | (1ULL << perf_arch_reg_sp(arch)); +} #else -#define PERF_REGS_MASK 0 -#define PERF_REGS_MAX 0 -#define DWARF_MINIMAL_REGS PERF_REGS_MASK +static inline uint64_t DWARF_MINIMAL_REGS(const char *arch __maybe_unused) +{ + return 0; +} static inline const char *perf_reg_name(int id __maybe_unused, const char *arch __maybe_unused) { @@ -54,5 +85,16 @@ static inline int perf_reg_value(u64 *valp __maybe_unused, { return 0; } + +static inline uint64_t perf_arch_reg_ip(const char *arch __maybe_unused) +{ + return 0; +} + +static inline uint64_t perf_arch_reg_sp(const char *arch __maybe_unused) +{ + return 0; +} + #endif /* HAVE_PERF_REGS_SUPPORT */ #endif /* __PERF_REGS_H */ diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 28380e7aa8d0..d85602aa4b9f 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -19,8 +19,8 @@ #include "evsel.h" #include "pmu.h" #include "pmus.h" -#include "pmu-bison.h" -#include "pmu-flex.h" +#include <util/pmu-bison.h> +#include <util/pmu-flex.h> #include "parse-events.h" #include "print-events.h" #include "header.h" @@ -29,7 +29,63 @@ #include "fncache.h" #include "util/evsel_config.h" -struct perf_pmu perf_pmu__fake; +struct perf_pmu perf_pmu__fake = { + .name = "fake", +}; + +#define UNIT_MAX_LEN 31 /* max length for event unit name */ + +/** + * struct perf_pmu_alias - An event either read from sysfs or builtin in + * pmu-events.c, created by parsing the pmu-events json files. + */ +struct perf_pmu_alias { + /** @name: Name of the event like "mem-loads". */ + char *name; + /** @desc: Optional short description of the event. */ + char *desc; + /** @long_desc: Optional long description. */ + char *long_desc; + /** + * @topic: Optional topic such as cache or pipeline, particularly for + * json events. + */ + char *topic; + /** @terms: Owned list of the original parsed parameters. */ + struct list_head terms; + /** @list: List element of struct perf_pmu aliases. */ + struct list_head list; + /** + * @pmu_name: The name copied from the json struct pmu_event. This can + * differ from the PMU name as it won't have suffixes. + */ + char *pmu_name; + /** @unit: Units for the event, such as bytes or cache lines. */ + char unit[UNIT_MAX_LEN+1]; + /** @scale: Value to scale read counter values by. */ + double scale; + /** + * @per_pkg: Does the file + * <sysfs>/bus/event_source/devices/<pmu_name>/events/<name>.per-pkg or + * equivalent json value exist and have the value 1. + */ + bool per_pkg; + /** + * @snapshot: Does the file + * <sysfs>/bus/event_source/devices/<pmu_name>/events/<name>.snapshot + * exist and have the value 1. + */ + bool snapshot; + /** + * @deprecated: Is the event hidden and so not shown in perf list by + * default. + */ + bool deprecated; + /** @from_sysfs: Was the alias from sysfs or a json event? */ + bool from_sysfs; + /** @info_loaded: Have the scale, unit and other values been read from disk? */ + bool info_loaded; +}; /** * struct perf_pmu_format - Values from a format file read from @@ -40,6 +96,10 @@ struct perf_pmu perf_pmu__fake; * value=PERF_PMU_FORMAT_VALUE_CONFIG and bits 0 to 7 will be set. */ struct perf_pmu_format { + /** @list: Element on list within struct perf_pmu. */ + struct list_head list; + /** @bits: Which config bits are set by this format value. */ + DECLARE_BITMAP(bits, PERF_PMU_FORMAT_BITS); /** @name: The modifier/file name. */ char *name; /** @@ -47,18 +107,81 @@ struct perf_pmu_format { * are from PERF_PMU_FORMAT_VALUE_CONFIG to * PERF_PMU_FORMAT_VALUE_CONFIG_END. */ - int value; - /** @bits: Which config bits are set by this format value. */ - DECLARE_BITMAP(bits, PERF_PMU_FORMAT_BITS); - /** @list: Element on list within struct perf_pmu. */ - struct list_head list; + u16 value; + /** @loaded: Has the contents been loaded/parsed. */ + bool loaded; }; +static int pmu_aliases_parse(struct perf_pmu *pmu); + +static struct perf_pmu_format *perf_pmu__new_format(struct list_head *list, char *name) +{ + struct perf_pmu_format *format; + + format = zalloc(sizeof(*format)); + if (!format) + return NULL; + + format->name = strdup(name); + if (!format->name) { + free(format); + return NULL; + } + list_add_tail(&format->list, list); + return format; +} + +/* Called at the end of parsing a format. */ +void perf_pmu_format__set_value(void *vformat, int config, unsigned long *bits) +{ + struct perf_pmu_format *format = vformat; + + format->value = config; + memcpy(format->bits, bits, sizeof(format->bits)); +} + +static void __perf_pmu_format__load(struct perf_pmu_format *format, FILE *file) +{ + void *scanner; + int ret; + + ret = perf_pmu_lex_init(&scanner); + if (ret) + return; + + perf_pmu_set_in(file, scanner); + ret = perf_pmu_parse(format, scanner); + perf_pmu_lex_destroy(scanner); + format->loaded = true; +} + +static void perf_pmu_format__load(struct perf_pmu *pmu, struct perf_pmu_format *format) +{ + char path[PATH_MAX]; + FILE *file = NULL; + + if (format->loaded) + return; + + if (!perf_pmu__pathname_scnprintf(path, sizeof(path), pmu->name, "format")) + return; + + assert(strlen(path) + strlen(format->name) + 2 < sizeof(path)); + strcat(path, "/"); + strcat(path, format->name); + + file = fopen(path, "r"); + if (!file) + return; + __perf_pmu_format__load(format, file); + fclose(file); +} + /* * Parse & process all the sysfs attributes located under * the directory specified in 'dir' parameter. */ -int perf_pmu__format_parse(int dirfd, struct list_head *head) +int perf_pmu__format_parse(struct perf_pmu *pmu, int dirfd, bool eager_load) { struct dirent *evt_ent; DIR *format_dir; @@ -68,37 +191,35 @@ int perf_pmu__format_parse(int dirfd, struct list_head *head) if (!format_dir) return -EINVAL; - while (!ret && (evt_ent = readdir(format_dir))) { + while ((evt_ent = readdir(format_dir)) != NULL) { + struct perf_pmu_format *format; char *name = evt_ent->d_name; - int fd; - void *scanner; - FILE *file; if (!strcmp(name, ".") || !strcmp(name, "..")) continue; - - ret = -EINVAL; - fd = openat(dirfd, name, O_RDONLY); - if (fd < 0) - break; - - file = fdopen(fd, "r"); - if (!file) { - close(fd); + format = perf_pmu__new_format(&pmu->format, name); + if (!format) { + ret = -ENOMEM; break; } - ret = perf_pmu_lex_init(&scanner); - if (ret) { + if (eager_load) { + FILE *file; + int fd = openat(dirfd, name, O_RDONLY); + + if (fd < 0) { + ret = -errno; + break; + } + file = fdopen(fd, "r"); + if (!file) { + close(fd); + break; + } + __perf_pmu_format__load(format, file); fclose(file); - break; } - - perf_pmu_set_in(file, scanner); - ret = perf_pmu_parse(head, name, scanner); - perf_pmu_lex_destroy(scanner); - fclose(file); } closedir(format_dir); @@ -110,7 +231,7 @@ int perf_pmu__format_parse(int dirfd, struct list_head *head) * located at: * /sys/bus/event_source/devices/<dev>/format as sysfs group attributes. */ -static int pmu_format(int dirfd, const char *name, struct list_head *format) +static int pmu_format(struct perf_pmu *pmu, int dirfd, const char *name) { int fd; @@ -119,7 +240,7 @@ static int pmu_format(int dirfd, const char *name, struct list_head *format) return 0; /* it'll close the fd */ - if (perf_pmu__format_parse(fd, format)) + if (perf_pmu__format_parse(pmu, fd, /*eager_load=*/false)) return -1; return 0; @@ -162,17 +283,21 @@ out: return ret; } -static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, int dirfd, char *name) +static int perf_pmu__parse_scale(struct perf_pmu *pmu, struct perf_pmu_alias *alias) { struct stat st; ssize_t sret; + size_t len; char scale[128]; int fd, ret = -1; char path[PATH_MAX]; - scnprintf(path, PATH_MAX, "%s.scale", name); + len = perf_pmu__event_source_devices_scnprintf(path, sizeof(path)); + if (!len) + return 0; + scnprintf(path + len, sizeof(path) - len, "%s/%s.scale", pmu->name, alias->name); - fd = openat(dirfd, path, O_RDONLY); + fd = open(path, O_RDONLY); if (fd == -1) return -1; @@ -194,15 +319,20 @@ error: return ret; } -static int perf_pmu__parse_unit(struct perf_pmu_alias *alias, int dirfd, char *name) +static int perf_pmu__parse_unit(struct perf_pmu *pmu, struct perf_pmu_alias *alias) { char path[PATH_MAX]; + size_t len; ssize_t sret; int fd; - scnprintf(path, PATH_MAX, "%s.unit", name); - fd = openat(dirfd, path, O_RDONLY); + len = perf_pmu__event_source_devices_scnprintf(path, sizeof(path)); + if (!len) + return 0; + scnprintf(path + len, sizeof(path) - len, "%s/%s.unit", pmu->name, alias->name); + + fd = open(path, O_RDONLY); if (fd == -1) return -1; @@ -225,14 +355,18 @@ error: } static int -perf_pmu__parse_per_pkg(struct perf_pmu_alias *alias, int dirfd, char *name) +perf_pmu__parse_per_pkg(struct perf_pmu *pmu, struct perf_pmu_alias *alias) { char path[PATH_MAX]; + size_t len; int fd; - scnprintf(path, PATH_MAX, "%s.per-pkg", name); + len = perf_pmu__event_source_devices_scnprintf(path, sizeof(path)); + if (!len) + return 0; + scnprintf(path + len, sizeof(path) - len, "%s/%s.per-pkg", pmu->name, alias->name); - fd = openat(dirfd, path, O_RDONLY); + fd = open(path, O_RDONLY); if (fd == -1) return -1; @@ -242,15 +376,18 @@ perf_pmu__parse_per_pkg(struct perf_pmu_alias *alias, int dirfd, char *name) return 0; } -static int perf_pmu__parse_snapshot(struct perf_pmu_alias *alias, - int dirfd, char *name) +static int perf_pmu__parse_snapshot(struct perf_pmu *pmu, struct perf_pmu_alias *alias) { char path[PATH_MAX]; + size_t len; int fd; - scnprintf(path, PATH_MAX, "%s.snapshot", name); + len = perf_pmu__event_source_devices_scnprintf(path, sizeof(path)); + if (!len) + return 0; + scnprintf(path + len, sizeof(path) - len, "%s/%s.snapshot", pmu->name, alias->name); - fd = openat(dirfd, path, O_RDONLY); + fd = open(path, O_RDONLY); if (fd == -1) return -1; @@ -259,46 +396,13 @@ static int perf_pmu__parse_snapshot(struct perf_pmu_alias *alias, return 0; } -static void perf_pmu_assign_str(char *name, const char *field, char **old_str, - char **new_str) -{ - if (!*old_str) - goto set_new; - - if (*new_str) { /* Have new string, check with old */ - if (strcasecmp(*old_str, *new_str)) - pr_debug("alias %s differs in field '%s'\n", - name, field); - zfree(old_str); - } else /* Nothing new --> keep old string */ - return; -set_new: - *old_str = *new_str; - *new_str = NULL; -} - -static void perf_pmu_update_alias(struct perf_pmu_alias *old, - struct perf_pmu_alias *newalias) -{ - perf_pmu_assign_str(old->name, "desc", &old->desc, &newalias->desc); - perf_pmu_assign_str(old->name, "long_desc", &old->long_desc, - &newalias->long_desc); - perf_pmu_assign_str(old->name, "topic", &old->topic, &newalias->topic); - perf_pmu_assign_str(old->name, "value", &old->str, &newalias->str); - old->scale = newalias->scale; - old->per_pkg = newalias->per_pkg; - old->snapshot = newalias->snapshot; - memcpy(old->unit, newalias->unit, sizeof(old->unit)); -} - /* Delete an alias entry. */ -void perf_pmu_free_alias(struct perf_pmu_alias *newalias) +static void perf_pmu_free_alias(struct perf_pmu_alias *newalias) { zfree(&newalias->name); zfree(&newalias->desc); zfree(&newalias->long_desc); zfree(&newalias->topic); - zfree(&newalias->str); zfree(&newalias->pmu_name); parse_events_terms__purge(&newalias->terms); free(newalias); @@ -314,38 +418,99 @@ static void perf_pmu__del_aliases(struct perf_pmu *pmu) } } -/* Merge an alias, search in alias list. If this name is already - * present merge both of them to combine all information. - */ -static bool perf_pmu_merge_alias(struct perf_pmu_alias *newalias, - struct list_head *alist) +static struct perf_pmu_alias *perf_pmu__find_alias(struct perf_pmu *pmu, + const char *name, + bool load) { - struct perf_pmu_alias *a; + struct perf_pmu_alias *alias; - list_for_each_entry(a, alist, list) { - if (!strcasecmp(newalias->name, a->name)) { - if (newalias->pmu_name && a->pmu_name && - !strcasecmp(newalias->pmu_name, a->pmu_name)) { - continue; - } - perf_pmu_update_alias(a, newalias); - perf_pmu_free_alias(newalias); - return true; - } + if (load && !pmu->sysfs_aliases_loaded) + pmu_aliases_parse(pmu); + + list_for_each_entry(alias, &pmu->aliases, list) { + if (!strcasecmp(alias->name, name)) + return alias; } - return false; + return NULL; } -static int __perf_pmu__new_alias(struct list_head *list, int dirfd, char *name, - char *desc, char *val, const struct pmu_event *pe) +static bool assign_str(const char *name, const char *field, char **old_str, + const char *new_str) +{ + if (!*old_str && new_str) { + *old_str = strdup(new_str); + return true; + } + + if (!new_str || !strcasecmp(*old_str, new_str)) + return false; /* Nothing to update. */ + + pr_debug("alias %s differs in field '%s' ('%s' != '%s')\n", + name, field, *old_str, new_str); + zfree(old_str); + *old_str = strdup(new_str); + return true; +} + +static void read_alias_info(struct perf_pmu *pmu, struct perf_pmu_alias *alias) +{ + if (!alias->from_sysfs || alias->info_loaded) + return; + + /* + * load unit name and scale if available + */ + perf_pmu__parse_unit(pmu, alias); + perf_pmu__parse_scale(pmu, alias); + perf_pmu__parse_per_pkg(pmu, alias); + perf_pmu__parse_snapshot(pmu, alias); +} + +struct update_alias_data { + struct perf_pmu *pmu; + struct perf_pmu_alias *alias; +}; + +static int update_alias(const struct pmu_event *pe, + const struct pmu_events_table *table __maybe_unused, + void *vdata) +{ + struct update_alias_data *data = vdata; + int ret = 0; + + read_alias_info(data->pmu, data->alias); + assign_str(pe->name, "desc", &data->alias->desc, pe->desc); + assign_str(pe->name, "long_desc", &data->alias->long_desc, pe->long_desc); + assign_str(pe->name, "topic", &data->alias->topic, pe->topic); + data->alias->per_pkg = pe->perpkg; + if (pe->event) { + parse_events_terms__purge(&data->alias->terms); + ret = parse_events_terms(&data->alias->terms, pe->event, /*input=*/NULL); + } + if (!ret && pe->unit) { + char *unit; + + ret = perf_pmu__convert_scale(pe->unit, &unit, &data->alias->scale); + if (!ret) + snprintf(data->alias->unit, sizeof(data->alias->unit), "%s", unit); + } + return ret; +} + +static int perf_pmu__new_alias(struct perf_pmu *pmu, const char *name, + const char *desc, const char *val, FILE *val_fd, + const struct pmu_event *pe) { - struct parse_events_term *term; struct perf_pmu_alias *alias; int ret; - char newval[256]; const char *long_desc = NULL, *topic = NULL, *unit = NULL, *pmu_name = NULL; bool deprecated = false, perpkg = false; + if (perf_pmu__find_alias(pmu, name, /*load=*/ false)) { + /* Alias was already created/loaded. */ + return 0; + } + if (pe) { long_desc = pe->long_desc; topic = pe->topic; @@ -366,80 +531,49 @@ static int __perf_pmu__new_alias(struct list_head *list, int dirfd, char *name, alias->snapshot = false; alias->deprecated = deprecated; - ret = parse_events_terms(&alias->terms, val); + ret = parse_events_terms(&alias->terms, val, val_fd); if (ret) { pr_err("Cannot parse alias %s: %d\n", val, ret); free(alias); return ret; } - /* Scan event and remove leading zeroes, spaces, newlines, some - * platforms have terms specified as - * event=0x0091 (read from files ../<PMU>/events/<FILE> - * and terms specified as event=0x91 (read from JSON files). - * - * Rebuild string to make alias->str member comparable. - */ - memset(newval, 0, sizeof(newval)); - ret = 0; - list_for_each_entry(term, &alias->terms, list) { - if (ret) - ret += scnprintf(newval + ret, sizeof(newval) - ret, - ","); - if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM) - ret += scnprintf(newval + ret, sizeof(newval) - ret, - "%s=%#x", term->config, term->val.num); - else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR) - ret += scnprintf(newval + ret, sizeof(newval) - ret, - "%s=%s", term->config, term->val.str); - } - alias->name = strdup(name); - if (dirfd >= 0) { - /* - * load unit name and scale if available - */ - perf_pmu__parse_unit(alias, dirfd, name); - perf_pmu__parse_scale(alias, dirfd, name); - perf_pmu__parse_per_pkg(alias, dirfd, name); - perf_pmu__parse_snapshot(alias, dirfd, name); - } - alias->desc = desc ? strdup(desc) : NULL; alias->long_desc = long_desc ? strdup(long_desc) : desc ? strdup(desc) : NULL; alias->topic = topic ? strdup(topic) : NULL; + alias->pmu_name = pmu_name ? strdup(pmu_name) : NULL; if (unit) { - if (perf_pmu__convert_scale(unit, (char **)&unit, &alias->scale) < 0) + if (perf_pmu__convert_scale(unit, (char **)&unit, &alias->scale) < 0) { + perf_pmu_free_alias(alias); return -1; + } snprintf(alias->unit, sizeof(alias->unit), "%s", unit); } - alias->str = strdup(newval); - alias->pmu_name = pmu_name ? strdup(pmu_name) : NULL; - - if (!perf_pmu_merge_alias(alias, list)) - list_add_tail(&alias->list, list); + if (!pe) { + /* Update an event from sysfs with json data. */ + struct update_alias_data data = { + .pmu = pmu, + .alias = alias, + }; + + alias->from_sysfs = true; + if (pmu->events_table) { + if (pmu_events_table__find_event(pmu->events_table, pmu, name, + update_alias, &data) == 0) + pmu->loaded_json_aliases++; + } + } + if (!pe) + pmu->sysfs_aliases++; + else + pmu->loaded_json_aliases++; + list_add_tail(&alias->list, &pmu->aliases); return 0; } -static int perf_pmu__new_alias(struct list_head *list, int dirfd, char *name, FILE *file) -{ - char buf[256]; - int ret; - - ret = fread(buf, 1, sizeof(buf), file); - if (ret == 0) - return -EINVAL; - - buf[ret] = 0; - - /* Remove trailing newline from sysfs file */ - strim(buf); - - return __perf_pmu__new_alias(list, dirfd, name, NULL, buf, NULL); -} - static inline bool pmu_alias_info_file(char *name) { size_t len; @@ -458,18 +592,33 @@ static inline bool pmu_alias_info_file(char *name) } /* - * Process all the sysfs attributes located under the directory - * specified in 'dir' parameter. + * Reading the pmu event aliases definition, which should be located at: + * /sys/bus/event_source/devices/<dev>/events as sysfs group attributes. */ -static int pmu_aliases_parse(int dirfd, struct list_head *head) +static int pmu_aliases_parse(struct perf_pmu *pmu) { + char path[PATH_MAX]; struct dirent *evt_ent; DIR *event_dir; - int fd; + size_t len; + int fd, dir_fd; - event_dir = fdopendir(dirfd); - if (!event_dir) + len = perf_pmu__event_source_devices_scnprintf(path, sizeof(path)); + if (!len) + return 0; + scnprintf(path + len, sizeof(path) - len, "%s/events", pmu->name); + + dir_fd = open(path, O_DIRECTORY); + if (dir_fd == -1) { + pmu->sysfs_aliases_loaded = true; + return 0; + } + + event_dir = fdopendir(dir_fd); + if (!event_dir){ + close (dir_fd); return -EINVAL; + } while ((evt_ent = readdir(event_dir))) { char *name = evt_ent->d_name; @@ -484,7 +633,7 @@ static int pmu_aliases_parse(int dirfd, struct list_head *head) if (pmu_alias_info_file(name)) continue; - fd = openat(dirfd, name, O_RDONLY); + fd = openat(dir_fd, name, O_RDONLY); if (fd == -1) { pr_debug("Cannot open %s\n", name); continue; @@ -495,31 +644,15 @@ static int pmu_aliases_parse(int dirfd, struct list_head *head) continue; } - if (perf_pmu__new_alias(head, dirfd, name, file) < 0) + if (perf_pmu__new_alias(pmu, name, /*desc=*/ NULL, + /*val=*/ NULL, file, /*pe=*/ NULL) < 0) pr_debug("Cannot set up %s\n", name); fclose(file); } closedir(event_dir); - return 0; -} - -/* - * Reading the pmu event aliases definition, which should be located at: - * /sys/bus/event_source/devices/<dev>/events as sysfs group attributes. - */ -static int pmu_aliases(int dirfd, const char *name, struct list_head *head) -{ - int fd; - - fd = perf_pmu__pathname_fd(dirfd, name, "events", O_DIRECTORY); - if (fd < 0) - return 0; - - /* it'll close the fd */ - if (pmu_aliases_parse(fd, head)) - return -1; - + close (dir_fd); + pmu->sysfs_aliases_loaded = true; return 0; } @@ -741,28 +874,13 @@ out: return res; } -struct pmu_add_cpu_aliases_map_data { - /* List being added to. */ - struct list_head *head; - /* If a pmu_event lacks a given PMU the default used. */ - char *default_pmu_name; - /* The PMU that we're searching for events for. */ - struct perf_pmu *pmu; -}; - static int pmu_add_cpu_aliases_map_callback(const struct pmu_event *pe, const struct pmu_events_table *table __maybe_unused, void *vdata) { - struct pmu_add_cpu_aliases_map_data *data = vdata; - const char *pname = pe->pmu ?: data->default_pmu_name; + struct perf_pmu *pmu = vdata; - if (!strcmp(pname, data->pmu->name) || - (data->pmu->is_uncore && pmu_uncore_alias_match(pname, data->pmu->name))) { - /* need type casts to override 'const' */ - __perf_pmu__new_alias(data->head, -1, (char *)pe->name, (char *)pe->desc, - (char *)pe->event, pe); - } + perf_pmu__new_alias(pmu, pe->name, pe->desc, pe->event, /*val_fd=*/ NULL, pe); return 0; } @@ -770,68 +888,51 @@ static int pmu_add_cpu_aliases_map_callback(const struct pmu_event *pe, * From the pmu_events_table, find the events that correspond to the given * PMU and add them to the list 'head'. */ -void pmu_add_cpu_aliases_table(struct list_head *head, struct perf_pmu *pmu, - const struct pmu_events_table *table) +void pmu_add_cpu_aliases_table(struct perf_pmu *pmu, const struct pmu_events_table *table) { - struct pmu_add_cpu_aliases_map_data data = { - .head = head, - .default_pmu_name = perf_pmus__default_pmu_name(), - .pmu = pmu, - }; - - pmu_events_table_for_each_event(table, pmu_add_cpu_aliases_map_callback, &data); - free(data.default_pmu_name); + pmu_events_table__for_each_event(table, pmu, pmu_add_cpu_aliases_map_callback, pmu); } -static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu) +static void pmu_add_cpu_aliases(struct perf_pmu *pmu) { - const struct pmu_events_table *table; + if (!pmu->events_table) + return; - table = perf_pmu__find_events_table(pmu); - if (!table) + if (pmu->cpu_aliases_added) return; - pmu_add_cpu_aliases_table(head, pmu, table); + pmu_add_cpu_aliases_table(pmu, pmu->events_table); + pmu->cpu_aliases_added = true; } -struct pmu_sys_event_iter_data { - struct list_head *head; - struct perf_pmu *pmu; -}; - static int pmu_add_sys_aliases_iter_fn(const struct pmu_event *pe, const struct pmu_events_table *table __maybe_unused, - void *data) + void *vdata) { - struct pmu_sys_event_iter_data *idata = data; - struct perf_pmu *pmu = idata->pmu; + struct perf_pmu *pmu = vdata; if (!pe->compat || !pe->pmu) return 0; if (!strcmp(pmu->id, pe->compat) && pmu_uncore_alias_match(pe->pmu, pmu->name)) { - __perf_pmu__new_alias(idata->head, -1, - (char *)pe->name, - (char *)pe->desc, - (char *)pe->event, - pe); + perf_pmu__new_alias(pmu, + pe->name, + pe->desc, + pe->event, + /*val_fd=*/ NULL, + pe); } return 0; } -void pmu_add_sys_aliases(struct list_head *head, struct perf_pmu *pmu) +void pmu_add_sys_aliases(struct perf_pmu *pmu) { - struct pmu_sys_event_iter_data idata = { - .head = head, - .pmu = pmu, - }; - if (!pmu->id) return; - pmu_for_each_sys_event(pmu_add_sys_aliases_iter_fn, &idata); + pmu_for_each_sys_event(pmu_add_sys_aliases_iter_fn, pmu); } struct perf_event_attr * __weak @@ -840,13 +941,13 @@ perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused) return NULL; } -char * __weak +const char * __weak pmu_find_real_name(const char *name) { - return (char *)name; + return name; } -char * __weak +const char * __weak pmu_find_alias_name(const char *name __maybe_unused) { return NULL; @@ -863,40 +964,41 @@ static int pmu_max_precise(int dirfd, struct perf_pmu *pmu) struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char *lookup_name) { struct perf_pmu *pmu; - LIST_HEAD(format); - LIST_HEAD(aliases); __u32 type; - char *name = pmu_find_real_name(lookup_name); - char *alias_name; - - /* - * The pmu data we store & need consists of the pmu - * type value and format definitions. Load both right - * now. - */ - if (pmu_format(dirfd, name, &format)) - return NULL; - - /* - * Check the aliases first to avoid unnecessary work. - */ - if (pmu_aliases(dirfd, name, &aliases)) - return NULL; + const char *name = pmu_find_real_name(lookup_name); + const char *alias_name; pmu = zalloc(sizeof(*pmu)); if (!pmu) return NULL; - pmu->is_core = is_pmu_core(name); - pmu->cpus = pmu_cpumask(dirfd, name, pmu->is_core); pmu->name = strdup(name); if (!pmu->name) goto err; - /* Read type, and ensure that type value is successfully assigned (return 1) */ + /* + * Read type early to fail fast if a lookup name isn't a PMU. Ensure + * that type value is successfully assigned (return 1). + */ if (perf_pmu__scan_file_at(pmu, dirfd, "type", "%u", &type) != 1) goto err; + INIT_LIST_HEAD(&pmu->format); + INIT_LIST_HEAD(&pmu->aliases); + INIT_LIST_HEAD(&pmu->caps); + + /* + * The pmu data we store & need consists of the pmu + * type value and format definitions. Load both right + * now. + */ + if (pmu_format(pmu, dirfd, name)) { + free(pmu); + return NULL; + } + pmu->is_core = is_pmu_core(name); + pmu->cpus = pmu_cpumask(dirfd, name, pmu->is_core); + alias_name = pmu_find_alias_name(name); if (alias_name) { pmu->alias_name = strdup(alias_name); @@ -909,14 +1011,8 @@ struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char if (pmu->is_uncore) pmu->id = pmu_id(name); pmu->max_precise = pmu_max_precise(dirfd, pmu); - pmu_add_cpu_aliases(&aliases, pmu); - pmu_add_sys_aliases(&aliases, pmu); - - INIT_LIST_HEAD(&pmu->format); - INIT_LIST_HEAD(&pmu->aliases); - INIT_LIST_HEAD(&pmu->caps); - list_splice(&format, &pmu->format); - list_splice(&aliases, &pmu->aliases); + pmu->events_table = perf_pmu__find_events_table(pmu); + pmu_add_sys_aliases(pmu); list_add_tail(&pmu->list, pmus); pmu->default_config = perf_pmu__get_default_config(pmu); @@ -966,13 +1062,15 @@ void perf_pmu__warn_invalid_formats(struct perf_pmu *pmu) if (pmu == &perf_pmu__fake) return; - list_for_each_entry(format, &pmu->format, list) + list_for_each_entry(format, &pmu->format, list) { + perf_pmu_format__load(pmu, format); if (format->value >= PERF_PMU_FORMAT_VALUE_CONFIG_END) { pr_warning("WARNING: '%s' format '%s' requires 'perf_event_attr::config%d'" "which is not supported by this version of perf!\n", pmu->name, format->name, format->value); return; } + } } bool evsel__is_aux_event(const struct evsel *evsel) @@ -1000,7 +1098,7 @@ void evsel__set_config_if_unset(struct perf_pmu *pmu, struct evsel *evsel, if (term) user_bits = term->val.cfg_chg; - bits = perf_pmu__format_bits(&pmu->format, config_name); + bits = perf_pmu__format_bits(pmu, config_name); /* Do nothing if the user changed the value */ if (bits & user_bits) @@ -1023,9 +1121,9 @@ pmu_find_format(struct list_head *formats, const char *name) return NULL; } -__u64 perf_pmu__format_bits(struct list_head *formats, const char *name) +__u64 perf_pmu__format_bits(struct perf_pmu *pmu, const char *name) { - struct perf_pmu_format *format = pmu_find_format(formats, name); + struct perf_pmu_format *format = pmu_find_format(&pmu->format, name); __u64 bits = 0; int fbit; @@ -1038,13 +1136,14 @@ __u64 perf_pmu__format_bits(struct list_head *formats, const char *name) return bits; } -int perf_pmu__format_type(struct list_head *formats, const char *name) +int perf_pmu__format_type(struct perf_pmu *pmu, const char *name) { - struct perf_pmu_format *format = pmu_find_format(formats, name); + struct perf_pmu_format *format = pmu_find_format(&pmu->format, name); if (!format) return -1; + perf_pmu_format__load(pmu, format); return format->value; } @@ -1135,8 +1234,7 @@ error: * Setup one of config[12] attr members based on the * user input data - term parameter. */ -static int pmu_config_term(const char *pmu_name, - struct list_head *formats, +static int pmu_config_term(struct perf_pmu *pmu, struct perf_event_attr *attr, struct parse_events_term *term, struct list_head *head_terms, @@ -1160,15 +1258,15 @@ static int pmu_config_term(const char *pmu_name, if (parse_events__is_hardcoded_term(term)) return 0; - format = pmu_find_format(formats, term->config); + format = pmu_find_format(&pmu->format, term->config); if (!format) { - char *pmu_term = pmu_formats_string(formats); + char *pmu_term = pmu_formats_string(&pmu->format); char *unknown_term; char *help_msg; if (asprintf(&unknown_term, "unknown term '%s' for pmu '%s'", - term->config, pmu_name) < 0) + term->config, pmu->name) < 0) unknown_term = NULL; help_msg = parse_events_formats_error_string(pmu_term); if (err) { @@ -1182,7 +1280,7 @@ static int pmu_config_term(const char *pmu_name, free(pmu_term); return -EINVAL; } - + perf_pmu_format__load(pmu, format); switch (format->value) { case PERF_PMU_FORMAT_VALUE_CONFIG: vp = &attr->config; @@ -1259,7 +1357,7 @@ static int pmu_config_term(const char *pmu_name, return 0; } -int perf_pmu__config_terms(const char *pmu_name, struct list_head *formats, +int perf_pmu__config_terms(struct perf_pmu *pmu, struct perf_event_attr *attr, struct list_head *head_terms, bool zero, struct parse_events_error *err) @@ -1267,8 +1365,7 @@ int perf_pmu__config_terms(const char *pmu_name, struct list_head *formats, struct parse_events_term *term; list_for_each_entry(term, head_terms, list) { - if (pmu_config_term(pmu_name, formats, attr, term, head_terms, - zero, err)) + if (pmu_config_term(pmu, attr, term, head_terms, zero, err)) return -EINVAL; } @@ -1286,25 +1383,25 @@ int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr, { bool zero = !!pmu->default_config; - return perf_pmu__config_terms(pmu->name, &pmu->format, attr, - head_terms, zero, err); + return perf_pmu__config_terms(pmu, attr, head_terms, zero, err); } static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu, struct parse_events_term *term) { struct perf_pmu_alias *alias; - char *name; + const char *name; if (parse_events__is_hardcoded_term(term)) return NULL; if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM) { - if (term->val.num != 1) + if (!term->no_value) return NULL; if (pmu_find_format(&pmu->format, term->config)) return NULL; name = term->config; + } else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR) { if (strcasecmp(term->config, "event")) return NULL; @@ -1313,26 +1410,51 @@ static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu, return NULL; } - list_for_each_entry(alias, &pmu->aliases, list) { - if (!strcasecmp(alias->name, name)) - return alias; + alias = perf_pmu__find_alias(pmu, name, /*load=*/ true); + if (alias || pmu->cpu_aliases_added) + return alias; + + /* Alias doesn't exist, try to get it from the json events. */ + if (pmu->events_table && + pmu_events_table__find_event(pmu->events_table, pmu, name, + pmu_add_cpu_aliases_map_callback, + pmu) == 0) { + alias = perf_pmu__find_alias(pmu, name, /*load=*/ false); } - return NULL; + return alias; } -static int check_info_data(struct perf_pmu_alias *alias, - struct perf_pmu_info *info) +static int check_info_data(struct perf_pmu *pmu, + struct perf_pmu_alias *alias, + struct perf_pmu_info *info, + struct parse_events_error *err, + int column) { + read_alias_info(pmu, alias); /* * Only one term in event definition can * define unit, scale and snapshot, fail * if there's more than one. */ - if ((info->unit && alias->unit[0]) || - (info->scale && alias->scale) || - (info->snapshot && alias->snapshot)) + if (info->unit && alias->unit[0]) { + parse_events_error__handle(err, column, + strdup("Attempt to set event's unit twice"), + NULL); return -EINVAL; + } + if (info->scale && alias->scale) { + parse_events_error__handle(err, column, + strdup("Attempt to set event's scale twice"), + NULL); + return -EINVAL; + } + if (info->snapshot && alias->snapshot) { + parse_events_error__handle(err, column, + strdup("Attempt to set event snapshot twice"), + NULL); + return -EINVAL; + } if (alias->unit[0]) info->unit = alias->unit; @@ -1351,7 +1473,7 @@ static int check_info_data(struct perf_pmu_alias *alias, * defined for the alias */ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms, - struct perf_pmu_info *info) + struct perf_pmu_info *info, struct parse_events_error *err) { struct parse_events_term *term, *h; struct perf_pmu_alias *alias; @@ -1372,10 +1494,14 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms, if (!alias) continue; ret = pmu_alias_terms(alias, &term->list); - if (ret) + if (ret) { + parse_events_error__handle(err, term->err_term, + strdup("Failure to duplicate terms"), + NULL); return ret; + } - ret = check_info_data(alias, info); + ret = check_info_data(pmu, alias, info, err, term->err_term); if (ret) return ret; @@ -1400,36 +1526,36 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms, return 0; } -int perf_pmu__new_format(struct list_head *list, char *name, - int config, unsigned long *bits) -{ - struct perf_pmu_format *format; +struct find_event_args { + const char *event; + void *state; + pmu_event_callback cb; +}; - format = zalloc(sizeof(*format)); - if (!format) - return -ENOMEM; +static int find_event_callback(void *state, struct pmu_event_info *info) +{ + struct find_event_args *args = state; - format->name = strdup(name); - format->value = config; - memcpy(format->bits, bits, sizeof(format->bits)); + if (!strcmp(args->event, info->name)) + return args->cb(args->state, info); - list_add_tail(&format->list, list); return 0; } -void perf_pmu__set_format(unsigned long *bits, long from, long to) +int perf_pmu__find_event(struct perf_pmu *pmu, const char *event, void *state, pmu_event_callback cb) { - long b; - - if (!to) - to = from; + struct find_event_args args = { + .event = event, + .state = state, + .cb = cb, + }; - memset(bits, 0, BITS_TO_BYTES(PERF_PMU_FORMAT_BITS)); - for (b = from; b <= to; b++) - __set_bit(b, bits); + /* Sub-optimal, but function is only used by tests. */ + return perf_pmu__for_each_event(pmu, /*skip_duplicate_pmus=*/ false, + &args, find_event_callback); } -void perf_pmu__del_formats(struct list_head *formats) +static void perf_pmu__del_formats(struct list_head *formats) { struct perf_pmu_format *fmt, *tmp; @@ -1466,15 +1592,145 @@ bool perf_pmu__auto_merge_stats(const struct perf_pmu *pmu) return !pmu->is_core || perf_pmus__num_core_pmus() == 1; } -bool perf_pmu__have_event(const struct perf_pmu *pmu, const char *name) +bool perf_pmu__have_event(struct perf_pmu *pmu, const char *name) { - struct perf_pmu_alias *alias; + if (perf_pmu__find_alias(pmu, name, /*load=*/ true) != NULL) + return true; + if (pmu->cpu_aliases_added || !pmu->events_table) + return false; + return pmu_events_table__find_event(pmu->events_table, pmu, name, NULL, NULL) == 0; +} - list_for_each_entry(alias, &pmu->aliases, list) { - if (!strcmp(alias->name, name)) - return true; +size_t perf_pmu__num_events(struct perf_pmu *pmu) +{ + size_t nr; + + if (!pmu->sysfs_aliases_loaded) + pmu_aliases_parse(pmu); + + nr = pmu->sysfs_aliases; + + if (pmu->cpu_aliases_added) + nr += pmu->loaded_json_aliases; + else if (pmu->events_table) + nr += pmu_events_table__num_events(pmu->events_table, pmu) - pmu->loaded_json_aliases; + + return pmu->selectable ? nr + 1 : nr; +} + +static int sub_non_neg(int a, int b) +{ + if (b > a) + return 0; + return a - b; +} + +static char *format_alias(char *buf, int len, const struct perf_pmu *pmu, + const struct perf_pmu_alias *alias, bool skip_duplicate_pmus) +{ + struct parse_events_term *term; + int pmu_name_len = skip_duplicate_pmus + ? pmu_name_len_no_suffix(pmu->name, /*num=*/NULL) + : (int)strlen(pmu->name); + int used = snprintf(buf, len, "%.*s/%s", pmu_name_len, pmu->name, alias->name); + + list_for_each_entry(term, &alias->terms, list) { + if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR) + used += snprintf(buf + used, sub_non_neg(len, used), + ",%s=%s", term->config, + term->val.str); } - return false; + + if (sub_non_neg(len, used) > 0) { + buf[used] = '/'; + used++; + } + if (sub_non_neg(len, used) > 0) { + buf[used] = '\0'; + used++; + } else + buf[len - 1] = '\0'; + + return buf; +} + +int perf_pmu__for_each_event(struct perf_pmu *pmu, bool skip_duplicate_pmus, + void *state, pmu_event_callback cb) +{ + char buf[1024]; + struct perf_pmu_alias *event; + struct pmu_event_info info = { + .pmu = pmu, + }; + int ret = 0; + struct strbuf sb; + + strbuf_init(&sb, /*hint=*/ 0); + pmu_add_cpu_aliases(pmu); + list_for_each_entry(event, &pmu->aliases, list) { + size_t buf_used; + + info.pmu_name = event->pmu_name ?: pmu->name; + info.alias = NULL; + if (event->desc) { + info.name = event->name; + buf_used = 0; + } else { + info.name = format_alias(buf, sizeof(buf), pmu, event, + skip_duplicate_pmus); + if (pmu->is_core) { + info.alias = info.name; + info.name = event->name; + } + buf_used = strlen(buf) + 1; + } + info.scale_unit = NULL; + if (strlen(event->unit) || event->scale != 1.0) { + info.scale_unit = buf + buf_used; + buf_used += snprintf(buf + buf_used, sizeof(buf) - buf_used, + "%G%s", event->scale, event->unit) + 1; + } + info.desc = event->desc; + info.long_desc = event->long_desc; + info.encoding_desc = buf + buf_used; + parse_events_term__to_strbuf(&event->terms, &sb); + buf_used += snprintf(buf + buf_used, sizeof(buf) - buf_used, + "%s/%s/", info.pmu_name, sb.buf) + 1; + info.topic = event->topic; + info.str = sb.buf; + info.deprecated = event->deprecated; + ret = cb(state, &info); + if (ret) + goto out; + strbuf_setlen(&sb, /*len=*/ 0); + } + if (pmu->selectable) { + info.name = buf; + snprintf(buf, sizeof(buf), "%s//", pmu->name); + info.alias = NULL; + info.scale_unit = NULL; + info.desc = NULL; + info.long_desc = NULL; + info.encoding_desc = NULL; + info.topic = NULL; + info.pmu_name = pmu->name; + info.deprecated = false; + ret = cb(state, &info); + } +out: + strbuf_release(&sb); + return ret; +} + +bool pmu__name_match(const struct perf_pmu *pmu, const char *pmu_name) +{ + return !strcmp(pmu->name, pmu_name) || + (pmu->is_uncore && pmu_uncore_alias_match(pmu_name, pmu->name)) || + /* + * jevents and tests use default_core as a marker for any core + * PMU as the PMU name varies across architectures. + */ + (pmu->is_core && !strcmp(pmu_name, "default_core")); } bool perf_pmu__is_software(const struct perf_pmu *pmu) @@ -1710,7 +1966,7 @@ void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config, name ?: "N/A", buf, config_name, config); } -int perf_pmu__match(char *pattern, char *name, char *tok) +int perf_pmu__match(const char *pattern, const char *name, const char *tok) { if (!name) return -1; @@ -1756,17 +2012,19 @@ int perf_pmu__event_source_devices_fd(void) * then pathname will be filled with * "/sys/bus/event_source/devices/cs_etm/format" * - * Return 0 if the sysfs mountpoint couldn't be found or if no - * characters were written. + * Return 0 if the sysfs mountpoint couldn't be found, if no characters were + * written or if the buffer size is exceeded. */ int perf_pmu__pathname_scnprintf(char *buf, size_t size, const char *pmu_name, const char *filename) { - char base_path[PATH_MAX]; + size_t len; - if (!perf_pmu__event_source_devices_scnprintf(base_path, sizeof(base_path))) + len = perf_pmu__event_source_devices_scnprintf(buf, size); + if (!len || (len + strlen(pmu_name) + strlen(filename) + 1) >= size) return 0; - return scnprintf(buf, size, "%s%s/%s", base_path, pmu_name, filename); + + return scnprintf(buf + len, size - len, "%s/%s", pmu_name, filename); } int perf_pmu__pathname_fd(int dirfd, const char *pmu_name, const char *filename, int flags) @@ -1788,5 +2046,23 @@ void perf_pmu__delete(struct perf_pmu *pmu) zfree(&pmu->default_config); zfree(&pmu->name); zfree(&pmu->alias_name); + zfree(&pmu->id); free(pmu); } + +struct perf_pmu *pmu__find_core_pmu(void) +{ + struct perf_pmu *pmu = NULL; + + while ((pmu = perf_pmus__scan_core(pmu))) { + /* + * The cpumap should cover all CPUs. Otherwise, some CPUs may + * not support some events or have different event IDs. + */ + if (RC_CHK_ACCESS(pmu->cpus)->nr != cpu__max_cpu().cpu) + return NULL; + + return pmu; + } + return NULL; +} diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index 6b414cecbad2..6a4e170c61d6 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -39,7 +39,7 @@ struct perf_pmu_caps { */ struct perf_pmu { /** @name: The name of the PMU such as "cpu". */ - char *name; + const char *name; /** * @alias_name: Optional alternate name for the PMU determined in * architecture specific code. @@ -49,7 +49,7 @@ struct perf_pmu { * @id: Optional PMU identifier read from * <sysfs>/bus/event_source/devices/<name>/identifier. */ - char *id; + const char *id; /** * @type: Perf event attributed type value, read from * <sysfs>/bus/event_source/devices/<name>/type. @@ -114,6 +114,21 @@ struct perf_pmu { * from json events in pmu-events.c. */ struct list_head aliases; + /** + * @events_table: The events table for json events in pmu-events.c. + */ + const struct pmu_events_table *events_table; + /** @sysfs_aliases: Number of sysfs aliases loaded. */ + uint32_t sysfs_aliases; + /** @sysfs_aliases: Number of json event aliases loaded. */ + uint32_t loaded_json_aliases; + /** @sysfs_aliases_loaded: Are sysfs aliases loaded from disk? */ + bool sysfs_aliases_loaded; + /** + * @cpu_aliases_added: Have all json events table entries for the PMU + * been added? + */ + bool cpu_aliases_added; /** @caps_initialized: Has the list caps been initialized? */ bool caps_initialized; /** @nr_caps: The length of the list caps. */ @@ -158,88 +173,49 @@ struct perf_pmu_info { bool snapshot; }; -#define UNIT_MAX_LEN 31 /* max length for event unit name */ - -/** - * struct perf_pmu_alias - An event either read from sysfs or builtin in - * pmu-events.c, created by parsing the pmu-events json files. - */ -struct perf_pmu_alias { - /** @name: Name of the event like "mem-loads". */ - char *name; - /** @desc: Optional short description of the event. */ - char *desc; - /** @long_desc: Optional long description. */ - char *long_desc; - /** - * @topic: Optional topic such as cache or pipeline, particularly for - * json events. - */ - char *topic; - /** - * @str: Comma separated parameter list like - * "event=0xcd,umask=0x1,ldlat=0x3". - */ - char *str; - /** @terms: Owned list of the original parsed parameters. */ - struct list_head terms; - /** @list: List element of struct perf_pmu aliases. */ - struct list_head list; - /** @unit: Units for the event, such as bytes or cache lines. */ - char unit[UNIT_MAX_LEN+1]; - /** @scale: Value to scale read counter values by. */ - double scale; - /** - * @per_pkg: Does the file - * <sysfs>/bus/event_source/devices/<pmu_name>/events/<name>.per-pkg or - * equivalent json value exist and have the value 1. - */ - bool per_pkg; - /** - * @snapshot: Does the file - * <sysfs>/bus/event_source/devices/<pmu_name>/events/<name>.snapshot - * exist and have the value 1. - */ - bool snapshot; - /** - * @deprecated: Is the event hidden and so not shown in perf list by - * default. - */ +struct pmu_event_info { + const struct perf_pmu *pmu; + const char *name; + const char* alias; + const char *scale_unit; + const char *desc; + const char *long_desc; + const char *encoding_desc; + const char *topic; + const char *pmu_name; + const char *str; bool deprecated; - /** - * @pmu_name: The name copied from the json struct pmu_event. This can - * differ from the PMU name as it won't have suffixes. - */ - char *pmu_name; }; -void pmu_add_sys_aliases(struct list_head *head, struct perf_pmu *pmu); +typedef int (*pmu_event_callback)(void *state, struct pmu_event_info *info); + +void pmu_add_sys_aliases(struct perf_pmu *pmu); int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr, struct list_head *head_terms, struct parse_events_error *error); -int perf_pmu__config_terms(const char *pmu_name, struct list_head *formats, +int perf_pmu__config_terms(struct perf_pmu *pmu, struct perf_event_attr *attr, struct list_head *head_terms, bool zero, struct parse_events_error *error); -__u64 perf_pmu__format_bits(struct list_head *formats, const char *name); -int perf_pmu__format_type(struct list_head *formats, const char *name); +__u64 perf_pmu__format_bits(struct perf_pmu *pmu, const char *name); +int perf_pmu__format_type(struct perf_pmu *pmu, const char *name); int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms, - struct perf_pmu_info *info); -struct list_head *perf_pmu__alias(struct perf_pmu *pmu, - struct list_head *head_terms); -void perf_pmu_error(struct list_head *list, char *name, void *scanner, char const *msg); + struct perf_pmu_info *info, struct parse_events_error *err); +int perf_pmu__find_event(struct perf_pmu *pmu, const char *event, void *state, pmu_event_callback cb); -int perf_pmu__new_format(struct list_head *list, char *name, - int config, unsigned long *bits); -void perf_pmu__set_format(unsigned long *bits, long from, long to); -int perf_pmu__format_parse(int dirfd, struct list_head *head); -void perf_pmu__del_formats(struct list_head *formats); +int perf_pmu__format_parse(struct perf_pmu *pmu, int dirfd, bool eager_load); +void perf_pmu_format__set_value(void *format, int config, unsigned long *bits); bool perf_pmu__has_format(const struct perf_pmu *pmu, const char *name); bool is_pmu_core(const char *name); bool perf_pmu__supports_legacy_cache(const struct perf_pmu *pmu); bool perf_pmu__auto_merge_stats(const struct perf_pmu *pmu); -bool perf_pmu__have_event(const struct perf_pmu *pmu, const char *name); +bool perf_pmu__have_event(struct perf_pmu *pmu, const char *name); +size_t perf_pmu__num_events(struct perf_pmu *pmu); +int perf_pmu__for_each_event(struct perf_pmu *pmu, bool skip_duplicate_pmus, + void *state, pmu_event_callback cb); +bool pmu__name_match(const struct perf_pmu *pmu, const char *pmu_name); + /** * perf_pmu_is_software - is the PMU a software PMU as in it uses the * perf_sw_context in the kernel? @@ -258,13 +234,12 @@ bool perf_pmu__file_exists(struct perf_pmu *pmu, const char *name); int perf_pmu__test(void); struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu); -void pmu_add_cpu_aliases_table(struct list_head *head, struct perf_pmu *pmu, +void pmu_add_cpu_aliases_table(struct perf_pmu *pmu, const struct pmu_events_table *table); char *perf_pmu__getcpuid(struct perf_pmu *pmu); const struct pmu_events_table *pmu_events_table__find(void); const struct pmu_metrics_table *pmu_metrics_table__find(void); -void perf_pmu_free_alias(struct perf_pmu_alias *alias); int perf_pmu__convert_scale(const char *scale, char **end, double *sval); @@ -275,10 +250,10 @@ void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config, const char *config_name); void perf_pmu__warn_invalid_formats(struct perf_pmu *pmu); -int perf_pmu__match(char *pattern, char *name, char *tok); +int perf_pmu__match(const char *pattern, const char *name, const char *tok); -char *pmu_find_real_name(const char *name); -char *pmu_find_alias_name(const char *name); +const char *pmu_find_real_name(const char *name); +const char *pmu_find_alias_name(const char *name); double perf_pmu__cpu_slots_per_cycle(void); int perf_pmu__event_source_devices_scnprintf(char *pathname, size_t size); int perf_pmu__pathname_scnprintf(char *buf, size_t size, @@ -289,5 +264,6 @@ int perf_pmu__pathname_fd(int dirfd, const char *pmu_name, const char *filename, struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char *lookup_name); struct perf_pmu *perf_pmu__create_placeholder_core_pmu(struct list_head *core_pmus); void perf_pmu__delete(struct perf_pmu *pmu); +struct perf_pmu *pmu__find_core_pmu(void); #endif /* __PMU_H */ diff --git a/tools/perf/util/pmu.y b/tools/perf/util/pmu.y index dff4e892ac4d..600c8c158c8e 100644 --- a/tools/perf/util/pmu.y +++ b/tools/perf/util/pmu.y @@ -1,6 +1,5 @@ %define api.pure full -%parse-param {struct list_head *format} -%parse-param {char *name} +%parse-param {void *format} %parse-param {void *scanner} %lex-param {void* scanner} @@ -11,6 +10,9 @@ #include <linux/bitmap.h> #include <string.h> #include "pmu.h" +#include "pmu-bison.h" + +int perf_pmu_lex(YYSTYPE * yylval_param , void *yyscanner); #define ABORT_ON(val) \ do { \ @@ -18,6 +20,20 @@ do { \ YYABORT; \ } while (0) +static void perf_pmu_error(void *format, void *scanner, const char *msg); + +static void perf_pmu__set_format(unsigned long *bits, long from, long to) +{ + long b; + + if (!to) + to = from; + + memset(bits, 0, BITS_TO_BYTES(PERF_PMU_FORMAT_BITS)); + for (b = from; b <= to; b++) + __set_bit(b, bits); +} + %} %token PP_CONFIG @@ -42,16 +58,12 @@ format_term format_term: PP_CONFIG ':' bits { - ABORT_ON(perf_pmu__new_format(format, name, - PERF_PMU_FORMAT_VALUE_CONFIG, - $3)); + perf_pmu_format__set_value(format, PERF_PMU_FORMAT_VALUE_CONFIG, $3); } | PP_CONFIG PP_VALUE ':' bits { - ABORT_ON(perf_pmu__new_format(format, name, - $2, - $4)); + perf_pmu_format__set_value(format, $2, $4); } bits: @@ -78,9 +90,8 @@ PP_VALUE %% -void perf_pmu_error(struct list_head *list __maybe_unused, - char *name __maybe_unused, - void *scanner __maybe_unused, - char const *msg __maybe_unused) +static void perf_pmu_error(void *format __maybe_unused, + void *scanner __maybe_unused, + const char *msg __maybe_unused) { } diff --git a/tools/perf/util/pmus.c b/tools/perf/util/pmus.c index c58ba9fb6a36..6631367c756f 100644 --- a/tools/perf/util/pmus.c +++ b/tools/perf/util/pmus.c @@ -1,8 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/list.h> +#include <linux/list_sort.h> +#include <linux/string.h> #include <linux/zalloc.h> #include <subcmd/pager.h> #include <sys/types.h> +#include <ctype.h> #include <dirent.h> #include <pthread.h> #include <string.h> @@ -33,6 +36,31 @@ static LIST_HEAD(other_pmus); static bool read_sysfs_core_pmus; static bool read_sysfs_all_pmus; +int pmu_name_len_no_suffix(const char *str, unsigned long *num) +{ + int orig_len, len; + + orig_len = len = strlen(str); + + /* Non-uncore PMUs have their full length, for example, i915. */ + if (!strstarts(str, "uncore_")) + return len; + + /* + * Count trailing digits and '_', if '_{num}' suffix isn't present use + * the full length. + */ + while (len > 0 && isdigit(str[len - 1])) + len--; + + if (len > 0 && len != orig_len && str[len - 1] == '_') { + if (num) + *num = strtoul(&str[len], NULL, 10); + return len - 1; + } + return orig_len; +} + void perf_pmus__destroy(void) { struct perf_pmu *pmu, *tmp; @@ -122,6 +150,25 @@ static struct perf_pmu *perf_pmu__find2(int dirfd, const char *name) return perf_pmu__lookup(core_pmu ? &core_pmus : &other_pmus, dirfd, name); } +static int pmus_cmp(void *priv __maybe_unused, + const struct list_head *lhs, const struct list_head *rhs) +{ + unsigned long lhs_num = 0, rhs_num = 0; + struct perf_pmu *lhs_pmu = container_of(lhs, struct perf_pmu, list); + struct perf_pmu *rhs_pmu = container_of(rhs, struct perf_pmu, list); + const char *lhs_pmu_name = lhs_pmu->name ?: ""; + const char *rhs_pmu_name = rhs_pmu->name ?: ""; + int lhs_pmu_name_len = pmu_name_len_no_suffix(lhs_pmu_name, &lhs_num); + int rhs_pmu_name_len = pmu_name_len_no_suffix(rhs_pmu_name, &rhs_num); + int ret = strncmp(lhs_pmu_name, rhs_pmu_name, + lhs_pmu_name_len < rhs_pmu_name_len ? lhs_pmu_name_len : rhs_pmu_name_len); + + if (lhs_pmu_name_len != rhs_pmu_name_len || ret != 0 || lhs_pmu_name_len == 0) + return ret; + + return lhs_num < rhs_num ? -1 : (lhs_num > rhs_num ? 1 : 0); +} + /* Add all pmus in sysfs to pmu list: */ static void pmu_read_sysfs(bool core_only) { @@ -156,6 +203,8 @@ static void pmu_read_sysfs(bool core_only) if (!perf_pmu__create_placeholder_core_pmu(&core_pmus)) pr_err("Failure to set up any core PMUs\n"); } + list_sort(NULL, &core_pmus, pmus_cmp); + list_sort(NULL, &other_pmus, pmus_cmp); if (!list_empty(&core_pmus)) { read_sysfs_core_pmus = true; if (!core_only) @@ -227,6 +276,43 @@ struct perf_pmu *perf_pmus__scan_core(struct perf_pmu *pmu) return NULL; } +static struct perf_pmu *perf_pmus__scan_skip_duplicates(struct perf_pmu *pmu) +{ + bool use_core_pmus = !pmu || pmu->is_core; + int last_pmu_name_len = 0; + const char *last_pmu_name = (pmu && pmu->name) ? pmu->name : ""; + + if (!pmu) { + pmu_read_sysfs(/*core_only=*/false); + pmu = list_prepare_entry(pmu, &core_pmus, list); + } else + last_pmu_name_len = pmu_name_len_no_suffix(pmu->name ?: "", NULL); + + if (use_core_pmus) { + list_for_each_entry_continue(pmu, &core_pmus, list) { + int pmu_name_len = pmu_name_len_no_suffix(pmu->name ?: "", /*num=*/NULL); + + if (last_pmu_name_len == pmu_name_len && + !strncmp(last_pmu_name, pmu->name ?: "", pmu_name_len)) + continue; + + return pmu; + } + pmu = NULL; + pmu = list_prepare_entry(pmu, &other_pmus, list); + } + list_for_each_entry_continue(pmu, &other_pmus, list) { + int pmu_name_len = pmu_name_len_no_suffix(pmu->name ?: "", /*num=*/NULL); + + if (last_pmu_name_len == pmu_name_len && + !strncmp(last_pmu_name, pmu->name ?: "", pmu_name_len)) + continue; + + return pmu; + } + return NULL; +} + const struct perf_pmu *perf_pmus__pmu_for_pmu_filter(const char *str) { struct perf_pmu *pmu = NULL; @@ -258,219 +344,153 @@ int __weak perf_pmus__num_mem_pmus(void) struct sevent { /** PMU for event. */ const struct perf_pmu *pmu; - /** - * Optional event for name, desc, etc. If not present then this is a - * selectable PMU and the event name is shown as "//". - */ - const struct perf_pmu_alias *event; - /** Is the PMU for the CPU? */ - bool is_cpu; + const char *name; + const char* alias; + const char *scale_unit; + const char *desc; + const char *long_desc; + const char *encoding_desc; + const char *topic; + const char *pmu_name; + bool deprecated; }; static int cmp_sevent(const void *a, const void *b) { const struct sevent *as = a; const struct sevent *bs = b; - const char *a_pmu_name = NULL, *b_pmu_name = NULL; - const char *a_name = "//", *a_desc = NULL, *a_topic = ""; - const char *b_name = "//", *b_desc = NULL, *b_topic = ""; + bool a_iscpu, b_iscpu; int ret; - if (as->event) { - a_name = as->event->name; - a_desc = as->event->desc; - a_topic = as->event->topic ?: ""; - a_pmu_name = as->event->pmu_name; - } - if (bs->event) { - b_name = bs->event->name; - b_desc = bs->event->desc; - b_topic = bs->event->topic ?: ""; - b_pmu_name = bs->event->pmu_name; - } /* Put extra events last. */ - if (!!a_desc != !!b_desc) - return !!a_desc - !!b_desc; + if (!!as->desc != !!bs->desc) + return !!as->desc - !!bs->desc; /* Order by topics. */ - ret = strcmp(a_topic, b_topic); + ret = strcmp(as->topic ?: "", bs->topic ?: ""); if (ret) return ret; /* Order CPU core events to be first */ - if (as->is_cpu != bs->is_cpu) - return as->is_cpu ? -1 : 1; + a_iscpu = as->pmu ? as->pmu->is_core : true; + b_iscpu = bs->pmu ? bs->pmu->is_core : true; + if (a_iscpu != b_iscpu) + return a_iscpu ? -1 : 1; /* Order by PMU name. */ if (as->pmu != bs->pmu) { - a_pmu_name = a_pmu_name ?: (as->pmu->name ?: ""); - b_pmu_name = b_pmu_name ?: (bs->pmu->name ?: ""); - ret = strcmp(a_pmu_name, b_pmu_name); + ret = strcmp(as->pmu_name ?: "", bs->pmu_name ?: ""); if (ret) return ret; } /* Order by event name. */ - return strcmp(a_name, b_name); + return strcmp(as->name, bs->name); } -static bool pmu_alias_is_duplicate(struct sevent *alias_a, - struct sevent *alias_b) +static bool pmu_alias_is_duplicate(struct sevent *a, struct sevent *b) { - const char *a_pmu_name = NULL, *b_pmu_name = NULL; - const char *a_name = "//", *b_name = "//"; - - - if (alias_a->event) { - a_name = alias_a->event->name; - a_pmu_name = alias_a->event->pmu_name; - } - if (alias_b->event) { - b_name = alias_b->event->name; - b_pmu_name = alias_b->event->pmu_name; - } - /* Different names -> never duplicates */ - if (strcmp(a_name, b_name)) + if (strcmp(a->name ?: "//", b->name ?: "//")) return false; /* Don't remove duplicates for different PMUs */ - a_pmu_name = a_pmu_name ?: (alias_a->pmu->name ?: ""); - b_pmu_name = b_pmu_name ?: (alias_b->pmu->name ?: ""); - return strcmp(a_pmu_name, b_pmu_name) == 0; + return strcmp(a->pmu_name, b->pmu_name) == 0; } -static int sub_non_neg(int a, int b) -{ - if (b > a) - return 0; - return a - b; -} +struct events_callback_state { + struct sevent *aliases; + size_t aliases_len; + size_t index; +}; -static char *format_alias(char *buf, int len, const struct perf_pmu *pmu, - const struct perf_pmu_alias *alias) +static int perf_pmus__print_pmu_events__callback(void *vstate, + struct pmu_event_info *info) { - struct parse_events_term *term; - int used = snprintf(buf, len, "%s/%s", pmu->name, alias->name); - - list_for_each_entry(term, &alias->terms, list) { - if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR) - used += snprintf(buf + used, sub_non_neg(len, used), - ",%s=%s", term->config, - term->val.str); - } + struct events_callback_state *state = vstate; + struct sevent *s; - if (sub_non_neg(len, used) > 0) { - buf[used] = '/'; - used++; + if (state->index >= state->aliases_len) { + pr_err("Unexpected event %s/%s/\n", info->pmu->name, info->name); + return 1; } - if (sub_non_neg(len, used) > 0) { - buf[used] = '\0'; - used++; - } else - buf[len - 1] = '\0'; - - return buf; + s = &state->aliases[state->index]; + s->pmu = info->pmu; +#define COPY_STR(str) s->str = info->str ? strdup(info->str) : NULL + COPY_STR(name); + COPY_STR(alias); + COPY_STR(scale_unit); + COPY_STR(desc); + COPY_STR(long_desc); + COPY_STR(encoding_desc); + COPY_STR(topic); + COPY_STR(pmu_name); +#undef COPY_STR + s->deprecated = info->deprecated; + state->index++; + return 0; } void perf_pmus__print_pmu_events(const struct print_callbacks *print_cb, void *print_state) { struct perf_pmu *pmu; - struct perf_pmu_alias *event; - char buf[1024]; int printed = 0; - int len, j; + int len; struct sevent *aliases; + struct events_callback_state state; + bool skip_duplicate_pmus = print_cb->skip_duplicate_pmus(print_state); + struct perf_pmu *(*scan_fn)(struct perf_pmu *); + + if (skip_duplicate_pmus) + scan_fn = perf_pmus__scan_skip_duplicates; + else + scan_fn = perf_pmus__scan; pmu = NULL; len = 0; - while ((pmu = perf_pmus__scan(pmu)) != NULL) { - list_for_each_entry(event, &pmu->aliases, list) - len++; - if (pmu->selectable) - len++; - } + while ((pmu = scan_fn(pmu)) != NULL) + len += perf_pmu__num_events(pmu); + aliases = zalloc(sizeof(struct sevent) * len); if (!aliases) { pr_err("FATAL: not enough memory to print PMU events\n"); return; } pmu = NULL; - j = 0; - while ((pmu = perf_pmus__scan(pmu)) != NULL) { - bool is_cpu = pmu->is_core; - - list_for_each_entry(event, &pmu->aliases, list) { - aliases[j].event = event; - aliases[j].pmu = pmu; - aliases[j].is_cpu = is_cpu; - j++; - } - if (pmu->selectable) { - aliases[j].event = NULL; - aliases[j].pmu = pmu; - aliases[j].is_cpu = is_cpu; - j++; - } + state = (struct events_callback_state) { + .aliases = aliases, + .aliases_len = len, + .index = 0, + }; + while ((pmu = scan_fn(pmu)) != NULL) { + perf_pmu__for_each_event(pmu, skip_duplicate_pmus, &state, + perf_pmus__print_pmu_events__callback); } - len = j; qsort(aliases, len, sizeof(struct sevent), cmp_sevent); - for (j = 0; j < len; j++) { - const char *name, *alias = NULL, *scale_unit = NULL, - *desc = NULL, *long_desc = NULL, - *encoding_desc = NULL, *topic = NULL, - *pmu_name = NULL; - bool deprecated = false; - size_t buf_used; - + for (int j = 0; j < len; j++) { /* Skip duplicates */ if (j > 0 && pmu_alias_is_duplicate(&aliases[j], &aliases[j - 1])) continue; - if (!aliases[j].event) { - /* A selectable event. */ - pmu_name = aliases[j].pmu->name; - buf_used = snprintf(buf, sizeof(buf), "%s//", pmu_name) + 1; - name = buf; - } else { - if (aliases[j].event->desc) { - name = aliases[j].event->name; - buf_used = 0; - } else { - name = format_alias(buf, sizeof(buf), aliases[j].pmu, - aliases[j].event); - if (aliases[j].is_cpu) { - alias = name; - name = aliases[j].event->name; - } - buf_used = strlen(buf) + 1; - } - pmu_name = aliases[j].event->pmu_name ?: (aliases[j].pmu->name ?: ""); - if (strlen(aliases[j].event->unit) || aliases[j].event->scale != 1.0) { - scale_unit = buf + buf_used; - buf_used += snprintf(buf + buf_used, sizeof(buf) - buf_used, - "%G%s", aliases[j].event->scale, - aliases[j].event->unit) + 1; - } - desc = aliases[j].event->desc; - long_desc = aliases[j].event->long_desc; - topic = aliases[j].event->topic; - encoding_desc = buf + buf_used; - buf_used += snprintf(buf + buf_used, sizeof(buf) - buf_used, - "%s/%s/", pmu_name, aliases[j].event->str) + 1; - deprecated = aliases[j].event->deprecated; - } print_cb->print_event(print_state, - pmu_name, - topic, - name, - alias, - scale_unit, - deprecated, + aliases[j].pmu_name, + aliases[j].topic, + aliases[j].name, + aliases[j].alias, + aliases[j].scale_unit, + aliases[j].deprecated, "Kernel PMU event", - desc, - long_desc, - encoding_desc); + aliases[j].desc, + aliases[j].long_desc, + aliases[j].encoding_desc); + zfree(&aliases[j].name); + zfree(&aliases[j].alias); + zfree(&aliases[j].scale_unit); + zfree(&aliases[j].desc); + zfree(&aliases[j].long_desc); + zfree(&aliases[j].encoding_desc); + zfree(&aliases[j].topic); + zfree(&aliases[j].pmu_name); } if (printed && pager_in_use()) printf("\n"); diff --git a/tools/perf/util/pmus.h b/tools/perf/util/pmus.h index a21464432d0f..4c67153ac257 100644 --- a/tools/perf/util/pmus.h +++ b/tools/perf/util/pmus.h @@ -5,6 +5,8 @@ struct perf_pmu; struct print_callbacks; +int pmu_name_len_no_suffix(const char *str, unsigned long *num); + void perf_pmus__destroy(void); struct perf_pmu *perf_pmus__find(const char *name); diff --git a/tools/perf/util/print-events.h b/tools/perf/util/print-events.h index d7fab411e75c..bf4290bef0cd 100644 --- a/tools/perf/util/print-events.h +++ b/tools/perf/util/print-events.h @@ -26,6 +26,7 @@ struct print_callbacks { const char *expr, const char *threshold, const char *unit); + bool (*skip_duplicate_pmus)(void *print_state); }; /** Print all events, the default when no options are specified. */ diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 16822a8a540f..1a5b7fa459b2 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -53,6 +53,8 @@ bool probe_event_dry_run; /* Dry run flag */ struct probe_conf probe_conf = { .magic_num = DEFAULT_PROBE_MAGIC_NUM }; +static char *synthesize_perf_probe_point(struct perf_probe_point *pp); + #define semantic_error(msg ...) pr_err("Semantic error :" msg) int e_snprintf(char *str, size_t size, const char *format, ...) @@ -961,8 +963,9 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev, debuginfo__delete(dinfo); if (ntevs == 0) { /* No error but failed to find probe point. */ - pr_warning("Probe point '%s' not found.\n", - synthesize_perf_probe_point(&pev->point)); + char *probe_point = synthesize_perf_probe_point(&pev->point); + pr_warning("Probe point '%s' not found.\n", probe_point); + free(probe_point); return -ENODEV; } else if (ntevs < 0) { /* Error path : ntevs < 0 */ @@ -2009,7 +2012,7 @@ out: } /* Compose only probe point (not argument) */ -char *synthesize_perf_probe_point(struct perf_probe_point *pp) +static char *synthesize_perf_probe_point(struct perf_probe_point *pp) { struct strbuf buf; char *tmp, *ret = NULL; @@ -2062,14 +2065,18 @@ char *synthesize_perf_probe_command(struct perf_probe_event *pev) goto out; tmp = synthesize_perf_probe_point(&pev->point); - if (!tmp || strbuf_addstr(&buf, tmp) < 0) + if (!tmp || strbuf_addstr(&buf, tmp) < 0) { + free(tmp); goto out; + } free(tmp); for (i = 0; i < pev->nargs; i++) { tmp = synthesize_perf_probe_arg(pev->args + i); - if (!tmp || strbuf_addf(&buf, " %s", tmp) < 0) + if (!tmp || strbuf_addf(&buf, " %s", tmp) < 0) { + free(tmp); goto out; + } free(tmp); } @@ -2800,13 +2807,18 @@ static void warn_uprobe_event_compat(struct probe_trace_event *tev) if (!tev->uprobes || tev->nargs == 0 || !buf) goto out; - for (i = 0; i < tev->nargs; i++) - if (strglobmatch(tev->args[i].value, "[$@+-]*")) { - pr_warning("Please upgrade your kernel to at least " - "3.14 to have access to feature %s\n", + for (i = 0; i < tev->nargs; i++) { + if (strchr(tev->args[i].value, '@')) { + pr_warning("%s accesses a variable by symbol name, but that is not supported for user application probe.\n", tev->args[i].value); break; } + if (strglobmatch(tev->args[i].value, "[$+-]*")) { + pr_warning("Please upgrade your kernel to at least 3.14 to have access to feature %s\n", + tev->args[i].value); + break; + } + } out: free(buf); } diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h index 8ad5b1579f1d..7e3b6c3d1f74 100644 --- a/tools/perf/util/probe-event.h +++ b/tools/perf/util/probe-event.h @@ -137,7 +137,6 @@ int parse_probe_trace_command(const char *cmd, struct probe_trace_event *tev); char *synthesize_perf_probe_command(struct perf_probe_event *pev); char *synthesize_probe_trace_command(struct probe_trace_event *tev); char *synthesize_perf_probe_arg(struct perf_probe_arg *pa); -char *synthesize_perf_probe_point(struct perf_probe_point *pp); int perf_probe_event__copy(struct perf_probe_event *dst, struct perf_probe_event *src); diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index d4c9b4cd35ef..26e1c8d973ea 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -40,3 +40,12 @@ util/rwsem.c util/hashmap.c util/perf_regs.c util/fncache.c +util/perf-regs-arch/perf_regs_aarch64.c +util/perf-regs-arch/perf_regs_arm.c +util/perf-regs-arch/perf_regs_csky.c +util/perf-regs-arch/perf_regs_loongarch.c +util/perf-regs-arch/perf_regs_mips.c +util/perf-regs-arch/perf_regs_powerpc.c +util/perf-regs-arch/perf_regs_riscv.c +util/perf-regs-arch/perf_regs_s390.c +util/perf-regs-arch/perf_regs_x86.c diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 4eed8ec23994..c29f5f0bb552 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -113,6 +113,11 @@ bool evsel__is_aux_event(const struct evsel *evsel __maybe_unused) return false; } +bool perf_pmus__supports_extended_type(void) +{ + return false; +} + /* * Add this one here not to drag util/metricgroup.c */ diff --git a/tools/perf/util/s390-sample-raw.c b/tools/perf/util/s390-sample-raw.c index c10b891dbad6..115b16edb451 100644 --- a/tools/perf/util/s390-sample-raw.c +++ b/tools/perf/util/s390-sample-raw.c @@ -27,7 +27,7 @@ #include "color.h" #include "sample-raw.h" #include "s390-cpumcf-kernel.h" -#include "pmu-events/pmu-events.h" +#include "util/pmu.h" #include "util/sample.h" static size_t ctrset_size(struct cf_ctrset_entry *set) @@ -132,56 +132,58 @@ static int get_counterset_start(int setnr) struct get_counter_name_data { int wanted; - const char *result; + char *result; }; -static int get_counter_name_callback(const struct pmu_event *evp, - const struct pmu_events_table *table __maybe_unused, - void *vdata) +static int get_counter_name_callback(void *vdata, struct pmu_event_info *info) { struct get_counter_name_data *data = vdata; int rc, event_nr; + const char *event_str; - if (evp->name == NULL || evp->event == NULL) + if (info->str == NULL) return 0; - rc = sscanf(evp->event, "event=%x", &event_nr); + + event_str = strstr(info->str, "event="); + if (!event_str) + return 0; + + rc = sscanf(event_str, "event=%x", &event_nr); if (rc == 1 && event_nr == data->wanted) { - data->result = evp->name; + data->result = strdup(info->name); return 1; /* Terminate the search. */ } return 0; } -/* Scan the PMU table and extract the logical name of a counter from the - * PMU events table. Input is the counter set and counter number with in the - * set. Construct the event number and use this as key. If they match return - * the name of this counter. +/* Scan the PMU and extract the logical name of a counter from the event. Input + * is the counter set and counter number with in the set. Construct the event + * number and use this as key. If they match return the name of this counter. * If no match is found a NULL pointer is returned. */ -static const char *get_counter_name(int set, int nr, const struct pmu_events_table *table) +static char *get_counter_name(int set, int nr, struct perf_pmu *pmu) { struct get_counter_name_data data = { .wanted = get_counterset_start(set) + nr, .result = NULL, }; - if (!table) + if (!pmu) return NULL; - pmu_events_table_for_each_event(table, get_counter_name_callback, &data); + perf_pmu__for_each_event(pmu, /*skip_duplicate_pmus=*/ true, + &data, get_counter_name_callback); return data.result; } -static void s390_cpumcfdg_dump(struct perf_sample *sample) +static void s390_cpumcfdg_dump(struct perf_pmu *pmu, struct perf_sample *sample) { size_t i, len = sample->raw_size, offset = 0; unsigned char *buf = sample->raw_data; const char *color = PERF_COLOR_BLUE; struct cf_ctrset_entry *cep, ce; - const struct pmu_events_table *table; u64 *p; - table = pmu_events_table__find(); while (offset < len) { cep = (struct cf_ctrset_entry *)(buf + offset); @@ -199,11 +201,12 @@ static void s390_cpumcfdg_dump(struct perf_sample *sample) color_fprintf(stdout, color, " [%#08zx] Counterset:%d" " Counters:%d\n", offset, ce.set, ce.ctr); for (i = 0, p = (u64 *)(cep + 1); i < ce.ctr; ++i, ++p) { - const char *ev_name = get_counter_name(ce.set, i, table); + char *ev_name = get_counter_name(ce.set, i, pmu); color_fprintf(stdout, color, "\tCounter:%03d %s Value:%#018lx\n", i, ev_name ?: "<unknown>", be64_to_cpu(*p)); + free(ev_name); } offset += ctrset_size(&ce); } @@ -216,14 +219,14 @@ static void s390_cpumcfdg_dump(struct perf_sample *sample) */ void evlist__s390_sample_raw(struct evlist *evlist, union perf_event *event, struct perf_sample *sample) { - struct evsel *ev_bc000; + struct evsel *evsel; if (event->header.type != PERF_RECORD_SAMPLE) return; - ev_bc000 = evlist__event2evsel(evlist, event); - if (ev_bc000 == NULL || - ev_bc000->core.attr.config != PERF_EVENT_CPUM_CF_DIAG) + evsel = evlist__event2evsel(evlist, event); + if (evsel == NULL || + evsel->core.attr.config != PERF_EVENT_CPUM_CF_DIAG) return; /* Display raw data on screen */ @@ -231,5 +234,5 @@ void evlist__s390_sample_raw(struct evlist *evlist, union perf_event *event, str pr_err("Invalid counter set data encountered\n"); return; } - s390_cpumcfdg_dump(sample); + s390_cpumcfdg_dump(evsel->pmu, sample); } diff --git a/tools/perf/util/scripting-engines/Build b/tools/perf/util/scripting-engines/Build index c220fec97032..586b94e90f4e 100644 --- a/tools/perf/util/scripting-engines/Build +++ b/tools/perf/util/scripting-engines/Build @@ -5,4 +5,5 @@ perf-$(CONFIG_LIBPYTHON) += trace-event-python.o CFLAGS_trace-event-perl.o += $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-nested-externs -Wno-undef -Wno-switch-default -Wno-bad-function-cast -Wno-declaration-after-statement -Wno-switch-enum -CFLAGS_trace-event-python.o += $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-deprecated-declarations -Wno-switch-enum +# -Wno-declaration-after-statement: The python headers have mixed code with declarations (decls after asserts, for instance) +CFLAGS_trace-event-python.o += $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-deprecated-declarations -Wno-switch-enum -Wno-declaration-after-statement diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 00d18c74c090..1e9aa8ed15b6 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -833,8 +833,8 @@ static void perf_event__hdr_attr_swap(union perf_event *event, perf_event__attr_swap(&event->attr.attr); size = event->header.size; - size -= (void *)&event->attr.id - (void *)event; - mem_bswap_64(event->attr.id, size); + size -= perf_record_header_attr_id(event) - (void *)event; + mem_bswap_64(perf_record_header_attr_id(event), size); } static void perf_event__event_update_swap(union perf_event *event, diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py index 869738fc06c3..79d5e2955f85 100644 --- a/tools/perf/util/setup.py +++ b/tools/perf/util/setup.py @@ -66,6 +66,9 @@ if cc_is_clang: else: cflags += ['-Wno-cast-function-type' ] +# The python headers have mixed code with declarations (decls after asserts, for instance) +cflags += [ "-Wno-declaration-after-statement" ] + src_perf = getenv('srctree') + '/tools/perf' build_lib = getenv('PYTHON_EXTBUILD_LIB') build_tmp = getenv('PYTHON_EXTBUILD_TMP') diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index d45d5dcb0e2b..afe6db8e7bf4 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -578,7 +578,7 @@ static void print_metric_only_csv(struct perf_stat_config *config __maybe_unused if (!valid_only_metric(unit)) return; unit = fixunit(tbuf, os->evsel, unit); - snprintf(buf, sizeof buf, fmt, val); + snprintf(buf, sizeof(buf), fmt ?: "", val); ends = vals = skip_spaces(buf); while (isdigit(*ends) || *ends == '.') ends++; @@ -600,7 +600,7 @@ static void print_metric_only_json(struct perf_stat_config *config __maybe_unuse if (!valid_only_metric(unit)) return; unit = fixunit(tbuf, os->evsel, unit); - snprintf(buf, sizeof(buf), fmt, val); + snprintf(buf, sizeof(buf), fmt ?: "", val); ends = vals = skip_spaces(buf); while (isdigit(*ends) || *ends == '.') ends++; diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 967e583392c7..ec3506042217 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -729,7 +729,7 @@ size_t perf_event__fprintf_stat_round(union perf_event *event, FILE *fp) size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp) { - struct perf_stat_config sc; + struct perf_stat_config sc = {}; size_t ret; perf_event__read_stat_config(&sc, &event->stat_config); diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c index 5c62d3118c41..0e4dc31c6c9c 100644 --- a/tools/perf/util/svghelper.c +++ b/tools/perf/util/svghelper.c @@ -331,7 +331,7 @@ static char *cpu_model(void) file = fopen("/proc/cpuinfo", "r"); if (file) { while (fgets(buf, 255, file)) { - if (strstr(buf, "model name")) { + if (strcasestr(buf, "model name")) { strlcpy(cpu_m, &buf[13], 255); break; } diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 8bd466d1c2bd..95e99c332d7e 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -1440,6 +1440,8 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map, curr_dso->kernel = dso->kernel; curr_dso->long_name = dso->long_name; curr_dso->long_name_len = dso->long_name_len; + curr_dso->binary_type = dso->binary_type; + curr_dso->adjust_symbols = dso->adjust_symbols; curr_map = map__new2(start, curr_dso); dso__put(curr_dso); if (curr_map == NULL) diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index f849f9ef68e6..3f36675b7c8f 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -2204,15 +2204,20 @@ int dso__load_vmlinux(struct dso *dso, struct map *map, if (symsrc__init(&ss, dso, symfs_vmlinux, symtab_type)) return -1; + /* + * dso__load_sym() may copy 'dso' which will result in the copies having + * an incorrect long name unless we set it here first. + */ + dso__set_long_name(dso, vmlinux, vmlinux_allocated); + if (dso->kernel == DSO_SPACE__KERNEL_GUEST) + dso->binary_type = DSO_BINARY_TYPE__GUEST_VMLINUX; + else + dso->binary_type = DSO_BINARY_TYPE__VMLINUX; + err = dso__load_sym(dso, map, &ss, &ss, 0); symsrc__destroy(&ss); if (err > 0) { - if (dso->kernel == DSO_SPACE__KERNEL_GUEST) - dso->binary_type = DSO_BINARY_TYPE__GUEST_VMLINUX; - else - dso->binary_type = DSO_BINARY_TYPE__VMLINUX; - dso__set_long_name(dso, vmlinux, vmlinux_allocated); dso__set_loaded(dso); pr_debug("Using %s for symbols\n", symfs_vmlinux); } diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index 45714a2785fd..a0579c7d7b9e 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -2145,7 +2145,7 @@ int perf_event__synthesize_attr(struct perf_tool *tool, struct perf_event_attr * return -ENOMEM; ev->attr.attr = *attr; - memcpy(ev->attr.id, id, ids * sizeof(u64)); + memcpy(perf_record_header_attr_id(ev), id, ids * sizeof(u64)); ev->attr.header.type = PERF_RECORD_HEADER_ATTR; ev->attr.header.size = (u16)size; diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 0b166404c5c3..fe5e6991ae4b 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -80,6 +80,15 @@ err_thread: return NULL; } +static void (*thread__priv_destructor)(void *priv); + +void thread__set_priv_destructor(void (*destructor)(void *priv)) +{ + assert(thread__priv_destructor == NULL); + + thread__priv_destructor = destructor; +} + void thread__delete(struct thread *thread) { struct namespaces *namespaces, *tmp_namespaces; @@ -112,6 +121,10 @@ void thread__delete(struct thread *thread) exit_rwsem(thread__namespaces_lock(thread)); exit_rwsem(thread__comm_lock(thread)); thread__free_stitch_list(thread); + + if (thread__priv_destructor) + thread__priv_destructor(thread__priv(thread)); + RC_CHK_FREE(thread); } diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index 9068a21ce0fa..e79225a0ea46 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -71,6 +71,8 @@ struct thread *thread__new(pid_t pid, pid_t tid); int thread__init_maps(struct thread *thread, struct machine *machine); void thread__delete(struct thread *thread); +void thread__set_priv_destructor(void (*destructor)(void *priv)); + struct thread *thread__get(struct thread *thread); void thread__put(struct thread *thread); diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index 2a96df4c8d42..8554db3fc0d7 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -17,6 +17,7 @@ #include "event.h" #include "perf_regs.h" #include "callchain.h" +#include "util/env.h" static char *debuginfo_path; @@ -170,12 +171,14 @@ static bool memory_read(Dwfl *dwfl __maybe_unused, Dwarf_Addr addr, Dwarf_Word * void *arg) { struct unwind_info *ui = arg; + const char *arch = perf_env__arch(ui->machine->env); struct stack_dump *stack = &ui->sample->user_stack; u64 start, end; int offset; int ret; - ret = perf_reg_value(&start, &ui->sample->user_regs, PERF_REG_SP); + ret = perf_reg_value(&start, &ui->sample->user_regs, + perf_arch_reg_sp(arch)); if (ret) return false; @@ -253,6 +256,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg, .max_stack = max_stack, .best_effort = best_effort }; + const char *arch = perf_env__arch(ui_buf.machine->env); Dwarf_Word ip; int err = -EINVAL, i; @@ -269,7 +273,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg, if (!ui->dwfl) goto out; - err = perf_reg_value(&ip, &data->user_regs, PERF_REG_IP); + err = perf_reg_value(&ip, &data->user_regs, perf_arch_reg_ip(arch)); if (err) goto out; diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index ebfde537b99b..c0641882fd2f 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -553,6 +553,7 @@ static int access_mem(unw_addr_space_t __maybe_unused as, int __write, void *arg) { struct unwind_info *ui = arg; + const char *arch = perf_env__arch(ui->machine->env); struct stack_dump *stack = &ui->sample->user_stack; u64 start, end; int offset; @@ -565,7 +566,7 @@ static int access_mem(unw_addr_space_t __maybe_unused as, } ret = perf_reg_value(&start, &ui->sample->user_regs, - LIBUNWIND__ARCH_REG_SP); + perf_arch_reg_sp(arch)); if (ret) return ret; @@ -714,6 +715,7 @@ static void _unwind__finish_access(struct maps *maps) static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, void *arg, int max_stack) { + const char *arch = perf_env__arch(ui->machine->env); u64 val; unw_word_t ips[max_stack]; unw_addr_space_t addr_space; @@ -721,7 +723,7 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, int ret, i = 0; ret = perf_reg_value(&val, &ui->sample->user_regs, - LIBUNWIND__ARCH_REG_IP); + perf_arch_reg_ip(arch)); if (ret) return ret; diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h index b2a03fa5289b..9f7164c6d9aa 100644 --- a/tools/perf/util/unwind.h +++ b/tools/perf/util/unwind.h @@ -42,14 +42,6 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg, #define LIBUNWIND__ARCH_REG_ID(regnum) libunwind__arch_reg_id(regnum) #endif -#ifndef LIBUNWIND__ARCH_REG_SP -#define LIBUNWIND__ARCH_REG_SP PERF_REG_SP -#endif - -#ifndef LIBUNWIND__ARCH_REG_IP -#define LIBUNWIND__ARCH_REG_IP PERF_REG_IP -#endif - int LIBUNWIND__ARCH_REG_ID(int regnum); int unwind__prepare_access(struct maps *maps, struct map *map, bool *initialized); void unwind__flush_access(struct maps *maps); diff --git a/tools/power/cpupower/Makefile b/tools/power/cpupower/Makefile index 59bfa05dec5d..b53753dee02f 100644 --- a/tools/power/cpupower/Makefile +++ b/tools/power/cpupower/Makefile @@ -53,11 +53,11 @@ DESTDIR ?= VERSION:= $(shell ./utils/version-gen.sh) LIB_MAJ= 0.0.1 -LIB_MIN= 0 +LIB_MIN= 1 PACKAGE = cpupower PACKAGE_BUGREPORT = linux-pm@vger.kernel.org -LANGUAGES = de fr it cs pt +LANGUAGES = de fr it cs pt ka # Directory definitions. These are default and most probably diff --git a/tools/power/cpupower/lib/cpupower.c b/tools/power/cpupower/lib/cpupower.c index 3f7d0c0c5067..7a2ef691b20e 100644 --- a/tools/power/cpupower/lib/cpupower.c +++ b/tools/power/cpupower/lib/cpupower.c @@ -14,6 +14,13 @@ #include "cpupower.h" #include "cpupower_intern.h" +int is_valid_path(const char *path) +{ + if (access(path, F_OK) == -1) + return 0; + return 1; +} + unsigned int cpupower_read_sysfs(const char *path, char *buf, size_t buflen) { ssize_t numread; diff --git a/tools/power/cpupower/lib/cpupower_intern.h b/tools/power/cpupower/lib/cpupower_intern.h index ac1112b956ec..5fdb8620d41b 100644 --- a/tools/power/cpupower/lib/cpupower_intern.h +++ b/tools/power/cpupower/lib/cpupower_intern.h @@ -7,5 +7,6 @@ #define SYSFS_PATH_MAX 255 +int is_valid_path(const char *path); unsigned int cpupower_read_sysfs(const char *path, char *buf, size_t buflen); unsigned int cpupower_write_sysfs(const char *path, char *buf, size_t buflen); diff --git a/tools/power/cpupower/utils/cpuidle-set.c b/tools/power/cpupower/utils/cpuidle-set.c index 46158928f9ad..a551d1d4ac51 100644 --- a/tools/power/cpupower/utils/cpuidle-set.c +++ b/tools/power/cpupower/utils/cpuidle-set.c @@ -41,14 +41,6 @@ int cmd_idle_set(int argc, char **argv) cont = 0; break; case 'd': - if (param) { - param = -1; - cont = 0; - break; - } - param = ret; - idlestate = atoi(optarg); - break; case 'e': if (param) { param = -1; @@ -56,7 +48,13 @@ int cmd_idle_set(int argc, char **argv) break; } param = ret; - idlestate = atoi(optarg); + strtol(optarg, &endptr, 10); + if (*endptr != '\0') { + printf(_("Bad value: %s, Integer expected\n"), optarg); + exit(EXIT_FAILURE); + } else { + idlestate = atoi(optarg); + } break; case 'D': if (param) { diff --git a/tools/power/cpupower/utils/cpupower-set.c b/tools/power/cpupower/utils/cpupower-set.c index 180d5ba877e6..0677b58374ab 100644 --- a/tools/power/cpupower/utils/cpupower-set.c +++ b/tools/power/cpupower/utils/cpupower-set.c @@ -18,6 +18,9 @@ static struct option set_opts[] = { {"perf-bias", required_argument, NULL, 'b'}, + {"epp", required_argument, NULL, 'e'}, + {"amd-pstate-mode", required_argument, NULL, 'm'}, + {"turbo-boost", required_argument, NULL, 't'}, { }, }; @@ -37,11 +40,15 @@ int cmd_set(int argc, char **argv) union { struct { int perf_bias:1; + int epp:1; + int mode:1; + int turbo_boost:1; }; int params; } params; - int perf_bias = 0; + int perf_bias = 0, turbo_boost = 1; int ret = 0; + char epp[30], mode[20]; ret = uname(&uts); if (!ret && (!strcmp(uts.machine, "ppc64le") || @@ -55,7 +62,7 @@ int cmd_set(int argc, char **argv) params.params = 0; /* parameter parsing */ - while ((ret = getopt_long(argc, argv, "b:", + while ((ret = getopt_long(argc, argv, "b:e:m:", set_opts, NULL)) != -1) { switch (ret) { case 'b': @@ -69,6 +76,38 @@ int cmd_set(int argc, char **argv) } params.perf_bias = 1; break; + case 'e': + if (params.epp) + print_wrong_arg_exit(); + if (sscanf(optarg, "%29s", epp) != 1) { + print_wrong_arg_exit(); + return -EINVAL; + } + params.epp = 1; + break; + case 'm': + if (cpupower_cpu_info.vendor != X86_VENDOR_AMD) + print_wrong_arg_exit(); + if (params.mode) + print_wrong_arg_exit(); + if (sscanf(optarg, "%19s", mode) != 1) { + print_wrong_arg_exit(); + return -EINVAL; + } + params.mode = 1; + break; + case 't': + if (params.turbo_boost) + print_wrong_arg_exit(); + turbo_boost = atoi(optarg); + if (turbo_boost < 0 || turbo_boost > 1) { + printf("--turbo-boost param out of range [0-1]\n"); + print_wrong_arg_exit(); + } + params.turbo_boost = 1; + break; + + default: print_wrong_arg_exit(); } @@ -77,6 +116,18 @@ int cmd_set(int argc, char **argv) if (!params.params) print_wrong_arg_exit(); + if (params.mode) { + ret = cpupower_set_amd_pstate_mode(mode); + if (ret) + fprintf(stderr, "Error setting mode\n"); + } + + if (params.turbo_boost) { + ret = cpupower_set_turbo_boost(turbo_boost); + if (ret) + fprintf(stderr, "Error setting turbo-boost\n"); + } + /* Default is: set all CPUs */ if (bitmask_isallclear(cpus_chosen)) bitmask_setall(cpus_chosen); @@ -102,6 +153,16 @@ int cmd_set(int argc, char **argv) break; } } + + if (params.epp) { + ret = cpupower_set_epp(cpu, epp); + if (ret) { + fprintf(stderr, + "Error setting epp value on CPU %d\n", cpu); + break; + } + } + } return ret; } diff --git a/tools/power/cpupower/utils/helpers/helpers.h b/tools/power/cpupower/utils/helpers/helpers.h index 96e4bede078b..95749b8ee475 100644 --- a/tools/power/cpupower/utils/helpers/helpers.h +++ b/tools/power/cpupower/utils/helpers/helpers.h @@ -116,6 +116,10 @@ extern int cpupower_intel_set_perf_bias(unsigned int cpu, unsigned int val); extern int cpupower_intel_get_perf_bias(unsigned int cpu); extern unsigned long long msr_intel_get_turbo_ratio(unsigned int cpu); +extern int cpupower_set_epp(unsigned int cpu, char *epp); +extern int cpupower_set_amd_pstate_mode(char *mode); +extern int cpupower_set_turbo_boost(int turbo_boost); + /* Read/Write msr ****************************/ /* PCI stuff ****************************/ @@ -173,6 +177,13 @@ static inline int cpupower_intel_get_perf_bias(unsigned int cpu) static inline unsigned long long msr_intel_get_turbo_ratio(unsigned int cpu) { return 0; }; +static inline int cpupower_set_epp(unsigned int cpu, char *epp) +{ return -1; }; +static inline int cpupower_set_amd_pstate_mode(char *mode) +{ return -1; }; +static inline int cpupower_set_turbo_boost(int turbo_boost) +{ return -1; }; + /* Read/Write msr ****************************/ static inline int cpufreq_has_boost_support(unsigned int cpu, int *support, diff --git a/tools/power/cpupower/utils/helpers/misc.c b/tools/power/cpupower/utils/helpers/misc.c index 9547b29254a7..76e461ff4f74 100644 --- a/tools/power/cpupower/utils/helpers/misc.c +++ b/tools/power/cpupower/utils/helpers/misc.c @@ -87,6 +87,61 @@ int cpupower_intel_set_perf_bias(unsigned int cpu, unsigned int val) return 0; } +int cpupower_set_epp(unsigned int cpu, char *epp) +{ + char path[SYSFS_PATH_MAX]; + char linebuf[30] = {}; + + snprintf(path, sizeof(path), + PATH_TO_CPU "cpu%u/cpufreq/energy_performance_preference", cpu); + + if (!is_valid_path(path)) + return -1; + + snprintf(linebuf, sizeof(linebuf), "%s", epp); + + if (cpupower_write_sysfs(path, linebuf, 30) <= 0) + return -1; + + return 0; +} + +int cpupower_set_amd_pstate_mode(char *mode) +{ + char path[SYSFS_PATH_MAX]; + char linebuf[20] = {}; + + snprintf(path, sizeof(path), PATH_TO_CPU "amd_pstate/status"); + + if (!is_valid_path(path)) + return -1; + + snprintf(linebuf, sizeof(linebuf), "%s\n", mode); + + if (cpupower_write_sysfs(path, linebuf, 20) <= 0) + return -1; + + return 0; +} + +int cpupower_set_turbo_boost(int turbo_boost) +{ + char path[SYSFS_PATH_MAX]; + char linebuf[2] = {}; + + snprintf(path, sizeof(path), PATH_TO_CPU "cpufreq/boost"); + + if (!is_valid_path(path)) + return -1; + + snprintf(linebuf, sizeof(linebuf), "%d", turbo_boost); + + if (cpupower_write_sysfs(path, linebuf, 2) <= 0) + return -1; + + return 0; +} + bool cpupower_amd_pstate_enabled(void) { char *driver = cpufreq_get_driver(0); @@ -95,7 +150,7 @@ bool cpupower_amd_pstate_enabled(void) if (!driver) return ret; - if (!strcmp(driver, "amd-pstate")) + if (!strncmp(driver, "amd", 3)) ret = true; cpufreq_put_driver(driver); diff --git a/tools/power/x86/intel-speed-select/isst-config.c b/tools/power/x86/intel-speed-select/isst-config.c index a73346e854b8..5fcc2a92957e 100644 --- a/tools/power/x86/intel-speed-select/isst-config.c +++ b/tools/power/x86/intel-speed-select/isst-config.c @@ -5,6 +5,7 @@ */ #include <linux/isst_if.h> +#include <sys/utsname.h> #include "isst.h" @@ -15,7 +16,7 @@ struct process_cmd_struct { int arg; }; -static const char *version_str = "v1.16"; +static const char *version_str = "v1.17"; static const int supported_api_ver = 2; static struct isst_if_platform_info isst_platform_info; @@ -473,11 +474,44 @@ static unsigned int is_cpu_online(int cpu) return online; } +static int get_kernel_version(int *major, int *minor) +{ + struct utsname buf; + int ret; + + ret = uname(&buf); + if (ret) + return ret; + + ret = sscanf(buf.release, "%d.%d", major, minor); + if (ret != 2) + return ret; + + return 0; +} + +#define CPU0_HOTPLUG_DEPRECATE_MAJOR_VER 6 +#define CPU0_HOTPLUG_DEPRECATE_MINOR_VER 5 + void set_cpu_online_offline(int cpu, int state) { char buffer[128]; int fd, ret; + if (!cpu) { + int major, minor; + + ret = get_kernel_version(&major, &minor); + if (!ret) { + if (major > CPU0_HOTPLUG_DEPRECATE_MAJOR_VER || (major == CPU0_HOTPLUG_DEPRECATE_MAJOR_VER && + minor >= CPU0_HOTPLUG_DEPRECATE_MINOR_VER)) { + debug_printf("Ignore CPU 0 offline/online for kernel version >= %d.%d\n", major, minor); + debug_printf("Use cgroups to isolate CPU 0\n"); + return; + } + } + } + snprintf(buffer, sizeof(buffer), "/sys/devices/system/cpu/cpu%d/online", cpu); @@ -778,6 +812,7 @@ static void create_cpu_map(void) map.cpu_map[0].logical_cpu); } else { update_punit_cpu_info(map.cpu_map[0].physical_cpu, &cpu_map[i]); + punit_id = cpu_map[i].punit_id; } } cpu_map[i].initialized = 1; @@ -2621,10 +2656,11 @@ static struct process_cmd_struct isst_cmds[] = { */ void parse_cpu_command(char *optarg) { - unsigned int start, end; + unsigned int start, end, invalid_count; char *next; next = optarg; + invalid_count = 0; while (next && *next) { if (*next == '-') /* no negative cpu numbers */ @@ -2634,6 +2670,8 @@ void parse_cpu_command(char *optarg) if (max_target_cpus < MAX_CPUS_IN_ONE_REQ) target_cpus[max_target_cpus++] = start; + else + invalid_count = 1; if (*next == '\0') break; @@ -2660,6 +2698,8 @@ void parse_cpu_command(char *optarg) while (++start <= end) { if (max_target_cpus < MAX_CPUS_IN_ONE_REQ) target_cpus[max_target_cpus++] = start; + else + invalid_count = 1; } if (*next == ',') @@ -2668,6 +2708,13 @@ void parse_cpu_command(char *optarg) goto error; } + if (invalid_count) { + isst_ctdp_display_information_start(outf); + isst_display_error_info_message(1, "Too many CPUs in one request: max is", 1, MAX_CPUS_IN_ONE_REQ - 1); + isst_ctdp_display_information_end(outf); + exit(-1); + } + #ifdef DEBUG { int i; diff --git a/tools/power/x86/intel-speed-select/isst-display.c b/tools/power/x86/intel-speed-select/isst-display.c index 0403d42ab1ba..14c9b037859a 100644 --- a/tools/power/x86/intel-speed-select/isst-display.c +++ b/tools/power/x86/intel-speed-select/isst-display.c @@ -442,7 +442,7 @@ void isst_ctdp_display_information(struct isst_id *id, FILE *outf, int tdp_level } if (ctdp_level->mem_freq) { - snprintf(header, sizeof(header), "mem-frequency(MHz)"); + snprintf(header, sizeof(header), "max-mem-frequency(MHz)"); snprintf(value, sizeof(value), "%d", ctdp_level->mem_freq); format_and_print(outf, level + 2, header, value); diff --git a/tools/power/x86/intel-speed-select/isst.h b/tools/power/x86/intel-speed-select/isst.h index 54fc21575d56..8def22dec4a2 100644 --- a/tools/power/x86/intel-speed-select/isst.h +++ b/tools/power/x86/intel-speed-select/isst.h @@ -79,7 +79,7 @@ #define DISP_FREQ_MULTIPLIER 100 -#define MAX_PACKAGE_COUNT 8 +#define MAX_PACKAGE_COUNT 32 #define MAX_DIE_PER_PACKAGE 2 #define MAX_PUNIT_PER_DIE 8 diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 8a36ba5df9f9..9a10512e3407 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -5447,7 +5447,7 @@ unsigned int intel_model_duplicates(unsigned int model) case INTEL_FAM6_LAKEFIELD: case INTEL_FAM6_ALDERLAKE: case INTEL_FAM6_ALDERLAKE_L: - case INTEL_FAM6_ALDERLAKE_N: + case INTEL_FAM6_ATOM_GRACEMONT: case INTEL_FAM6_RAPTORLAKE: case INTEL_FAM6_RAPTORLAKE_P: case INTEL_FAM6_RAPTORLAKE_S: diff --git a/tools/scripts/utilities.mak b/tools/scripts/utilities.mak index 172e47273b5d..d69d0345cc23 100644 --- a/tools/scripts/utilities.mak +++ b/tools/scripts/utilities.mak @@ -177,3 +177,23 @@ $(if $($(1)),$(call _ge_attempt,$($(1)),$(1)),$(call _ge_attempt,$(2))) endef _ge_attempt = $(or $(get-executable),$(call _gea_err,$(2))) _gea_err = $(if $(1),$(error Please set '$(1)' appropriately)) + +# version-ge3 +# +# Usage $(call version-ge3,2.6.4,$(FLEX_VERSION)) +# +# To compare if a 3 component version is greater or equal to another, first use +# was to check the flex version to see if we can use compiler warnings as +# errors for one of the cases flex generates code C compilers complains about. + +version-ge3 = $(shell echo "$(1).$(2)" | awk -F'.' '{ printf("%d\n", (10000000 * $$1 + 10000 * $$2 + $$3) >= (10000000 * $$4 + 10000 * $$5 + $$6)) }') + +# version-lt3 +# +# Usage $(call version-lt3,2.6.2,$(FLEX_VERSION)) +# +# To compare if a 3 component version is less thjan another, first use was to +# check the flex version to see if we can use compiler warnings as errors for +# one of the cases flex generates code C compilers complains about. + +version-lt3 = $(shell echo "$(1).$(2)" | awk -F'.' '{ printf("%d\n", (10000000 * $$1 + 10000 * $$2 + $$3) < (10000000 * $$4 + 10000 * $$5 + $$6)) }') diff --git a/tools/testing/kunit/configs/all_tests.config b/tools/testing/kunit/configs/all_tests.config index 0393940c706a..3bf506d4a63c 100644 --- a/tools/testing/kunit/configs/all_tests.config +++ b/tools/testing/kunit/configs/all_tests.config @@ -33,5 +33,12 @@ CONFIG_DAMON_PADDR=y CONFIG_DEBUG_FS=y CONFIG_DAMON_DBGFS=y +CONFIG_REGMAP_BUILD=y + CONFIG_SECURITY=y CONFIG_SECURITY_APPARMOR=y + +CONFIG_SOUND=y +CONFIG_SND=y +CONFIG_SND_SOC=y +CONFIG_SND_SOC_TOPOLOGY_BUILD=y diff --git a/tools/testing/kunit/kunit.py b/tools/testing/kunit/kunit.py index 3905c43369c3..bc74088c458a 100755 --- a/tools/testing/kunit/kunit.py +++ b/tools/testing/kunit/kunit.py @@ -55,8 +55,12 @@ class KunitExecRequest(KunitParseRequest): build_dir: str timeout: int filter_glob: str + filter: str + filter_action: Optional[str] kernel_args: Optional[List[str]] run_isolated: Optional[str] + list_tests: bool + list_tests_attr: bool @dataclass class KunitRequest(KunitExecRequest, KunitBuildRequest): @@ -102,19 +106,41 @@ def config_and_build_tests(linux: kunit_kernel.LinuxSourceTree, def _list_tests(linux: kunit_kernel.LinuxSourceTree, request: KunitExecRequest) -> List[str]: args = ['kunit.action=list'] + + if request.kernel_args: + args.extend(request.kernel_args) + + output = linux.run_kernel(args=args, + timeout=request.timeout, + filter_glob=request.filter_glob, + filter=request.filter, + filter_action=request.filter_action, + build_dir=request.build_dir) + lines = kunit_parser.extract_tap_lines(output) + # Hack! Drop the dummy TAP version header that the executor prints out. + lines.pop() + + # Filter out any extraneous non-test output that might have gotten mixed in. + return [l for l in output if re.match(r'^[^\s.]+\.[^\s.]+$', l)] + +def _list_tests_attr(linux: kunit_kernel.LinuxSourceTree, request: KunitExecRequest) -> Iterable[str]: + args = ['kunit.action=list_attr'] + if request.kernel_args: args.extend(request.kernel_args) output = linux.run_kernel(args=args, timeout=request.timeout, filter_glob=request.filter_glob, + filter=request.filter, + filter_action=request.filter_action, build_dir=request.build_dir) lines = kunit_parser.extract_tap_lines(output) # Hack! Drop the dummy TAP version header that the executor prints out. lines.pop() # Filter out any extraneous non-test output that might have gotten mixed in. - return [l for l in lines if re.match(r'^[^\s.]+\.[^\s.]+$', l)] + return lines def _suites_from_test_list(tests: List[str]) -> List[str]: """Extracts all the suites from an ordered list of tests.""" @@ -128,10 +154,18 @@ def _suites_from_test_list(tests: List[str]) -> List[str]: suites.append(suite) return suites - - def exec_tests(linux: kunit_kernel.LinuxSourceTree, request: KunitExecRequest) -> KunitResult: filter_globs = [request.filter_glob] + if request.list_tests: + output = _list_tests(linux, request) + for line in output: + print(line.rstrip()) + return KunitResult(status=KunitStatus.SUCCESS, elapsed_time=0.0) + if request.list_tests_attr: + attr_output = _list_tests_attr(linux, request) + for line in attr_output: + print(line.rstrip()) + return KunitResult(status=KunitStatus.SUCCESS, elapsed_time=0.0) if request.run_isolated: tests = _list_tests(linux, request) if request.run_isolated == 'test': @@ -155,6 +189,8 @@ def exec_tests(linux: kunit_kernel.LinuxSourceTree, request: KunitExecRequest) - args=request.kernel_args, timeout=request.timeout, filter_glob=filter_glob, + filter=request.filter, + filter_action=request.filter_action, build_dir=request.build_dir) _, test_result = parse_tests(request, metadata, run_result) @@ -341,6 +377,16 @@ def add_exec_opts(parser: argparse.ArgumentParser) -> None: nargs='?', default='', metavar='filter_glob') + parser.add_argument('--filter', + help='Filter KUnit tests with attributes, ' + 'e.g. module=example or speed>slow', + type=str, + default='') + parser.add_argument('--filter_action', + help='If set to skip, filtered tests will be skipped, ' + 'e.g. --filter_action=skip. Otherwise they will not run.', + type=str, + choices=['skip']) parser.add_argument('--kernel_args', help='Kernel command-line parameters. Maybe be repeated', action='append', metavar='') @@ -350,6 +396,12 @@ def add_exec_opts(parser: argparse.ArgumentParser) -> None: 'what ran before it.', type=str, choices=['suite', 'test']) + parser.add_argument('--list_tests', help='If set, list all tests that will be ' + 'run.', + action='store_true') + parser.add_argument('--list_tests_attr', help='If set, list all tests and test ' + 'attributes.', + action='store_true') def add_parse_opts(parser: argparse.ArgumentParser) -> None: parser.add_argument('--raw_output', help='If set don\'t parse output from kernel. ' @@ -398,8 +450,12 @@ def run_handler(cli_args: argparse.Namespace) -> None: json=cli_args.json, timeout=cli_args.timeout, filter_glob=cli_args.filter_glob, + filter=cli_args.filter, + filter_action=cli_args.filter_action, kernel_args=cli_args.kernel_args, - run_isolated=cli_args.run_isolated) + run_isolated=cli_args.run_isolated, + list_tests=cli_args.list_tests, + list_tests_attr=cli_args.list_tests_attr) result = run_tests(linux, request) if result.status != KunitStatus.SUCCESS: sys.exit(1) @@ -441,8 +497,12 @@ def exec_handler(cli_args: argparse.Namespace) -> None: json=cli_args.json, timeout=cli_args.timeout, filter_glob=cli_args.filter_glob, + filter=cli_args.filter, + filter_action=cli_args.filter_action, kernel_args=cli_args.kernel_args, - run_isolated=cli_args.run_isolated) + run_isolated=cli_args.run_isolated, + list_tests=cli_args.list_tests, + list_tests_attr=cli_args.list_tests_attr) result = exec_tests(linux, exec_request) stdout.print_with_timestamp(( 'Elapsed time: %.3fs\n') % (result.elapsed_time)) diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py index 7f648802caf6..0b6488efed47 100644 --- a/tools/testing/kunit/kunit_kernel.py +++ b/tools/testing/kunit/kunit_kernel.py @@ -330,11 +330,15 @@ class LinuxSourceTree: return False return self.validate_config(build_dir) - def run_kernel(self, args: Optional[List[str]]=None, build_dir: str='', filter_glob: str='', timeout: Optional[int]=None) -> Iterator[str]: + def run_kernel(self, args: Optional[List[str]]=None, build_dir: str='', filter_glob: str='', filter: str='', filter_action: Optional[str]=None, timeout: Optional[int]=None) -> Iterator[str]: if not args: args = [] if filter_glob: - args.append('kunit.filter_glob='+filter_glob) + args.append('kunit.filter_glob=' + filter_glob) + if filter: + args.append('kunit.filter="' + filter + '"') + if filter_action: + args.append('kunit.filter_action=' + filter_action) args.append('kunit.enable=1') process = self._ops.start(args, build_dir) diff --git a/tools/testing/kunit/kunit_parser.py b/tools/testing/kunit/kunit_parser.py index fbc094f0567e..79d8832c862a 100644 --- a/tools/testing/kunit/kunit_parser.py +++ b/tools/testing/kunit/kunit_parser.py @@ -212,6 +212,7 @@ KTAP_START = re.compile(r'\s*KTAP version ([0-9]+)$') TAP_START = re.compile(r'\s*TAP version ([0-9]+)$') KTAP_END = re.compile(r'\s*(List of all partitions:|' 'Kernel panic - not syncing: VFS:|reboot: System halted)') +EXECUTOR_ERROR = re.compile(r'\s*kunit executor: (.*)$') def extract_tap_lines(kernel_output: Iterable[str]) -> LineStream: """Extracts KTAP lines from the kernel output.""" @@ -242,6 +243,8 @@ def extract_tap_lines(kernel_output: Iterable[str]) -> LineStream: # remove the prefix, if any. line = line[prefix_len:] yield line_num, line + elif EXECUTOR_ERROR.search(line): + yield line_num, line return LineStream(lines=isolate_ktap_output(kernel_output)) KTAP_VERSIONS = [1] @@ -447,7 +450,7 @@ def parse_diagnostic(lines: LineStream) -> List[str]: Log of diagnostic lines """ log = [] # type: List[str] - non_diagnostic_lines = [TEST_RESULT, TEST_HEADER, KTAP_START] + non_diagnostic_lines = [TEST_RESULT, TEST_HEADER, KTAP_START, TAP_START] while lines and not any(re.match(lines.peek()) for re in non_diagnostic_lines): log.append(lines.pop()) @@ -713,6 +716,11 @@ def parse_test(lines: LineStream, expected_num: int, log: List[str], is_subtest: """ test = Test() test.log.extend(log) + + # Parse any errors prior to parsing tests + err_log = parse_diagnostic(lines) + test.log.extend(err_log) + if not is_subtest: # If parsing the main/top-level test, parse KTAP version line and # test plan @@ -774,6 +782,7 @@ def parse_test(lines: LineStream, expected_num: int, log: List[str], is_subtest: # Don't override a bad status if this test had one reported. # Assumption: no subtests means CRASHED is from Test.__init__() if test.status in (TestStatus.TEST_CRASHED, TestStatus.SUCCESS): + print_log(test.log) test.status = TestStatus.NO_TESTS test.add_error('0 tests run!') diff --git a/tools/testing/kunit/kunit_tool_test.py b/tools/testing/kunit/kunit_tool_test.py index be35999bb84f..b28c1510be2e 100755 --- a/tools/testing/kunit/kunit_tool_test.py +++ b/tools/testing/kunit/kunit_tool_test.py @@ -597,7 +597,7 @@ class KUnitMainTest(unittest.TestCase): self.assertEqual(self.linux_source_mock.build_reconfig.call_count, 0) self.assertEqual(self.linux_source_mock.run_kernel.call_count, 1) self.linux_source_mock.run_kernel.assert_called_once_with( - args=None, build_dir='.kunit', filter_glob='', timeout=300) + args=None, build_dir='.kunit', filter_glob='', filter='', filter_action=None, timeout=300) self.print_mock.assert_any_call(StrContains('Testing complete.')) def test_run_passes_args_pass(self): @@ -605,7 +605,7 @@ class KUnitMainTest(unittest.TestCase): self.assertEqual(self.linux_source_mock.build_reconfig.call_count, 1) self.assertEqual(self.linux_source_mock.run_kernel.call_count, 1) self.linux_source_mock.run_kernel.assert_called_once_with( - args=None, build_dir='.kunit', filter_glob='', timeout=300) + args=None, build_dir='.kunit', filter_glob='', filter='', filter_action=None, timeout=300) self.print_mock.assert_any_call(StrContains('Testing complete.')) def test_exec_passes_args_fail(self): @@ -629,7 +629,7 @@ class KUnitMainTest(unittest.TestCase): kunit.main(['run']) self.assertEqual(e.exception.code, 1) self.linux_source_mock.run_kernel.assert_called_once_with( - args=None, build_dir='.kunit', filter_glob='', timeout=300) + args=None, build_dir='.kunit', filter_glob='', filter='', filter_action=None, timeout=300) self.print_mock.assert_any_call(StrContains(' 0 tests run!')) def test_exec_raw_output(self): @@ -670,13 +670,13 @@ class KUnitMainTest(unittest.TestCase): self.linux_source_mock.run_kernel = mock.Mock(return_value=[]) kunit.main(['run', '--raw_output', 'filter_glob']) self.linux_source_mock.run_kernel.assert_called_once_with( - args=None, build_dir='.kunit', filter_glob='filter_glob', timeout=300) + args=None, build_dir='.kunit', filter_glob='filter_glob', filter='', filter_action=None, timeout=300) def test_exec_timeout(self): timeout = 3453 kunit.main(['exec', '--timeout', str(timeout)]) self.linux_source_mock.run_kernel.assert_called_once_with( - args=None, build_dir='.kunit', filter_glob='', timeout=timeout) + args=None, build_dir='.kunit', filter_glob='', filter='', filter_action=None, timeout=timeout) self.print_mock.assert_any_call(StrContains('Testing complete.')) def test_run_timeout(self): @@ -684,7 +684,7 @@ class KUnitMainTest(unittest.TestCase): kunit.main(['run', '--timeout', str(timeout)]) self.assertEqual(self.linux_source_mock.build_reconfig.call_count, 1) self.linux_source_mock.run_kernel.assert_called_once_with( - args=None, build_dir='.kunit', filter_glob='', timeout=timeout) + args=None, build_dir='.kunit', filter_glob='', filter='', filter_action=None, timeout=timeout) self.print_mock.assert_any_call(StrContains('Testing complete.')) def test_run_builddir(self): @@ -692,7 +692,7 @@ class KUnitMainTest(unittest.TestCase): kunit.main(['run', '--build_dir=.kunit']) self.assertEqual(self.linux_source_mock.build_reconfig.call_count, 1) self.linux_source_mock.run_kernel.assert_called_once_with( - args=None, build_dir=build_dir, filter_glob='', timeout=300) + args=None, build_dir=build_dir, filter_glob='', filter='', filter_action=None, timeout=300) self.print_mock.assert_any_call(StrContains('Testing complete.')) def test_config_builddir(self): @@ -710,7 +710,7 @@ class KUnitMainTest(unittest.TestCase): build_dir = '.kunit' kunit.main(['exec', '--build_dir', build_dir]) self.linux_source_mock.run_kernel.assert_called_once_with( - args=None, build_dir=build_dir, filter_glob='', timeout=300) + args=None, build_dir=build_dir, filter_glob='', filter='', filter_action=None, timeout=300) self.print_mock.assert_any_call(StrContains('Testing complete.')) def test_run_kunitconfig(self): @@ -786,7 +786,7 @@ class KUnitMainTest(unittest.TestCase): kunit.main(['run', '--kernel_args=a=1', '--kernel_args=b=2']) self.assertEqual(self.linux_source_mock.build_reconfig.call_count, 1) self.linux_source_mock.run_kernel.assert_called_once_with( - args=['a=1','b=2'], build_dir='.kunit', filter_glob='', timeout=300) + args=['a=1','b=2'], build_dir='.kunit', filter_glob='', filter='', filter_action=None, timeout=300) self.print_mock.assert_any_call(StrContains('Testing complete.')) def test_list_tests(self): @@ -794,13 +794,11 @@ class KUnitMainTest(unittest.TestCase): self.linux_source_mock.run_kernel.return_value = ['TAP version 14', 'init: random output'] + want got = kunit._list_tests(self.linux_source_mock, - kunit.KunitExecRequest(None, None, '.kunit', 300, 'suite*', None, 'suite')) - + kunit.KunitExecRequest(None, None, '.kunit', 300, 'suite*', '', None, None, 'suite', False, False)) self.assertEqual(got, want) # Should respect the user's filter glob when listing tests. self.linux_source_mock.run_kernel.assert_called_once_with( - args=['kunit.action=list'], build_dir='.kunit', filter_glob='suite*', timeout=300) - + args=['kunit.action=list'], build_dir='.kunit', filter_glob='suite*', filter='', filter_action=None, timeout=300) @mock.patch.object(kunit, '_list_tests') def test_run_isolated_by_suite(self, mock_tests): @@ -809,10 +807,10 @@ class KUnitMainTest(unittest.TestCase): # Should respect the user's filter glob when listing tests. mock_tests.assert_called_once_with(mock.ANY, - kunit.KunitExecRequest(None, None, '.kunit', 300, 'suite*.test*', None, 'suite')) + kunit.KunitExecRequest(None, None, '.kunit', 300, 'suite*.test*', '', None, None, 'suite', False, False)) self.linux_source_mock.run_kernel.assert_has_calls([ - mock.call(args=None, build_dir='.kunit', filter_glob='suite.test*', timeout=300), - mock.call(args=None, build_dir='.kunit', filter_glob='suite2.test*', timeout=300), + mock.call(args=None, build_dir='.kunit', filter_glob='suite.test*', filter='', filter_action=None, timeout=300), + mock.call(args=None, build_dir='.kunit', filter_glob='suite2.test*', filter='', filter_action=None, timeout=300), ]) @mock.patch.object(kunit, '_list_tests') @@ -822,13 +820,12 @@ class KUnitMainTest(unittest.TestCase): # Should respect the user's filter glob when listing tests. mock_tests.assert_called_once_with(mock.ANY, - kunit.KunitExecRequest(None, None, '.kunit', 300, 'suite*', None, 'test')) + kunit.KunitExecRequest(None, None, '.kunit', 300, 'suite*', '', None, None, 'test', False, False)) self.linux_source_mock.run_kernel.assert_has_calls([ - mock.call(args=None, build_dir='.kunit', filter_glob='suite.test1', timeout=300), - mock.call(args=None, build_dir='.kunit', filter_glob='suite.test2', timeout=300), - mock.call(args=None, build_dir='.kunit', filter_glob='suite2.test1', timeout=300), + mock.call(args=None, build_dir='.kunit', filter_glob='suite.test1', filter='', filter_action=None, timeout=300), + mock.call(args=None, build_dir='.kunit', filter_glob='suite.test2', filter='', filter_action=None, timeout=300), + mock.call(args=None, build_dir='.kunit', filter_glob='suite2.test1', filter='', filter_action=None, timeout=300), ]) - if __name__ == '__main__': unittest.main() diff --git a/tools/testing/kunit/qemu_configs/arm64.py b/tools/testing/kunit/qemu_configs/arm64.py index 67d04064f785..d3ff27024755 100644 --- a/tools/testing/kunit/qemu_configs/arm64.py +++ b/tools/testing/kunit/qemu_configs/arm64.py @@ -9,4 +9,4 @@ CONFIG_SERIAL_AMBA_PL011_CONSOLE=y''', qemu_arch='aarch64', kernel_path='arch/arm64/boot/Image.gz', kernel_command_line='console=ttyAMA0', - extra_qemu_params=['-machine', 'virt', '-cpu', 'cortex-a57']) + extra_qemu_params=['-machine', 'virt', '-cpu', 'max,pauth-impdef=on']) diff --git a/tools/testing/radix-tree/maple.c b/tools/testing/radix-tree/maple.c index 75ea2081a317..e5da1cad70ba 100644 --- a/tools/testing/radix-tree/maple.c +++ b/tools/testing/radix-tree/maple.c @@ -45,6 +45,13 @@ struct rcu_test_struct2 { unsigned long last[RCU_RANGE_COUNT]; }; +struct rcu_test_struct3 { + struct maple_tree *mt; + unsigned long index; + unsigned long last; + bool stop; +}; + struct rcu_reader_struct { unsigned int id; int mod; @@ -34954,6 +34961,70 @@ void run_check_rcu(struct maple_tree *mt, struct rcu_test_struct *vals) MT_BUG_ON(mt, !vals->seen_entry2); } +static void *rcu_slot_store_reader(void *ptr) +{ + struct rcu_test_struct3 *test = ptr; + MA_STATE(mas, test->mt, test->index, test->index); + + rcu_register_thread(); + + rcu_read_lock(); + while (!test->stop) { + mas_walk(&mas); + /* The length of growth to both sides must be equal. */ + RCU_MT_BUG_ON(test, (test->index - mas.index) != + (mas.last - test->last)); + } + rcu_read_unlock(); + + rcu_unregister_thread(); + return NULL; +} + +static noinline void run_check_rcu_slot_store(struct maple_tree *mt) +{ + pthread_t readers[20]; + int range_cnt = 200, i, limit = 10000; + unsigned long len = ULONG_MAX / range_cnt, start, end; + struct rcu_test_struct3 test = {.stop = false, .mt = mt}; + + start = range_cnt / 2 * len; + end = start + len - 1; + test.index = start; + test.last = end; + + for (i = 0; i < range_cnt; i++) { + mtree_store_range(mt, i * len, i * len + len - 1, + xa_mk_value(i * 100), GFP_KERNEL); + } + + mt_set_in_rcu(mt); + MT_BUG_ON(mt, !mt_in_rcu(mt)); + + for (i = 0; i < ARRAY_SIZE(readers); i++) { + if (pthread_create(&readers[i], NULL, rcu_slot_store_reader, + &test)) { + perror("creating reader thread"); + exit(1); + } + } + + usleep(5); + + while (limit--) { + /* Step by step, expand the most middle range to both sides. */ + mtree_store_range(mt, --start, ++end, xa_mk_value(100), + GFP_KERNEL); + } + + test.stop = true; + + while (i--) + pthread_join(readers[i], NULL); + + mt_validate(mt); +} + static noinline void run_check_rcu_slowread(struct maple_tree *mt, struct rcu_test_struct *vals) { @@ -35206,6 +35277,10 @@ static noinline void __init check_rcu_threaded(struct maple_tree *mt) run_check_rcu(mt, &vals); mtree_destroy(mt); + /* Check expanding range in RCU mode */ + mt_init_flags(mt, MT_FLAGS_ALLOC_RANGE); + run_check_rcu_slot_store(mt); + mtree_destroy(mt); /* Forward writer for rcu stress */ mt_init_flags(mt, MT_FLAGS_ALLOC_RANGE); @@ -35383,7 +35458,9 @@ static noinline void __init check_prealloc(struct maple_tree *mt) for (i = 0; i <= max; i++) mtree_test_store_range(mt, i * 10, i * 10 + 5, &i); - MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); + /* Spanning store */ + mas_set_range(&mas, 470, 500); + MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); MT_BUG_ON(mt, allocated == 0); @@ -35392,105 +35469,108 @@ static noinline void __init check_prealloc(struct maple_tree *mt) allocated = mas_allocated(&mas); MT_BUG_ON(mt, allocated != 0); - MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); MT_BUG_ON(mt, allocated == 0); MT_BUG_ON(mt, allocated != 1 + height * 3); - MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); mas_destroy(&mas); allocated = mas_allocated(&mas); MT_BUG_ON(mt, allocated != 0); - MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); - MT_BUG_ON(mt, allocated == 0); MT_BUG_ON(mt, allocated != 1 + height * 3); mn = mas_pop_node(&mas); MT_BUG_ON(mt, mas_allocated(&mas) != allocated - 1); mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); - MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); mas_destroy(&mas); allocated = mas_allocated(&mas); MT_BUG_ON(mt, allocated != 0); - MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); - MT_BUG_ON(mt, allocated == 0); MT_BUG_ON(mt, allocated != 1 + height * 3); mn = mas_pop_node(&mas); MT_BUG_ON(mt, mas_allocated(&mas) != allocated - 1); - MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); mas_destroy(&mas); allocated = mas_allocated(&mas); MT_BUG_ON(mt, allocated != 0); mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); - MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); - MT_BUG_ON(mt, allocated == 0); MT_BUG_ON(mt, allocated != 1 + height * 3); mn = mas_pop_node(&mas); MT_BUG_ON(mt, mas_allocated(&mas) != allocated - 1); mas_push_node(&mas, mn); MT_BUG_ON(mt, mas_allocated(&mas) != allocated); - MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); mas_destroy(&mas); allocated = mas_allocated(&mas); MT_BUG_ON(mt, allocated != 0); - MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); - MT_BUG_ON(mt, allocated == 0); MT_BUG_ON(mt, allocated != 1 + height * 3); mas_store_prealloc(&mas, ptr); MT_BUG_ON(mt, mas_allocated(&mas) != 0); - MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); + /* Slot store does not need allocations */ + mas_set_range(&mas, 6, 9); + MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); allocated = mas_allocated(&mas); - height = mas_mt_height(&mas); - MT_BUG_ON(mt, allocated == 0); - MT_BUG_ON(mt, allocated != 1 + height * 3); + MT_BUG_ON(mt, allocated != 0); mas_store_prealloc(&mas, ptr); MT_BUG_ON(mt, mas_allocated(&mas) != 0); - MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); + + mas_set_range(&mas, 6, 10); + MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); - MT_BUG_ON(mt, allocated == 0); - MT_BUG_ON(mt, allocated != 1 + height * 3); + MT_BUG_ON(mt, allocated != 1); mas_store_prealloc(&mas, ptr); + MT_BUG_ON(mt, mas_allocated(&mas) != 0); - MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); + /* Split */ + mas_set_range(&mas, 54, 54); + MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); - MT_BUG_ON(mt, allocated == 0); - MT_BUG_ON(mt, allocated != 1 + height * 3); + MT_BUG_ON(mt, allocated != 1 + height * 2); mas_store_prealloc(&mas, ptr); MT_BUG_ON(mt, mas_allocated(&mas) != 0); mt_set_non_kernel(1); - MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL & GFP_NOWAIT) == 0); + /* Spanning store */ + mas_set_range(&mas, 1, 100); + MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL & GFP_NOWAIT) == 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); MT_BUG_ON(mt, allocated != 0); mas_destroy(&mas); - MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); + /* Spanning store */ + MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); MT_BUG_ON(mt, allocated == 0); MT_BUG_ON(mt, allocated != 1 + height * 3); mas_store_prealloc(&mas, ptr); MT_BUG_ON(mt, mas_allocated(&mas) != 0); + mas_set_range(&mas, 0, 200); mt_set_non_kernel(1); - MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL & GFP_NOWAIT) == 0); + MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL & GFP_NOWAIT) == 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); MT_BUG_ON(mt, allocated != 0); diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c index e00520cc6349..cffaf2245d4f 100644 --- a/tools/testing/radix-tree/multiorder.c +++ b/tools/testing/radix-tree/multiorder.c @@ -159,7 +159,7 @@ void multiorder_tagged_iteration(struct xarray *xa) item_kill_tree(xa); } -bool stop_iteration = false; +bool stop_iteration; static void *creator_func(void *ptr) { @@ -201,6 +201,7 @@ static void multiorder_iteration_race(struct xarray *xa) pthread_t worker_thread[num_threads]; int i; + stop_iteration = false; pthread_create(&worker_thread[0], NULL, &creator_func, xa); for (i = 1; i < num_threads; i++) pthread_create(&worker_thread[i], NULL, &iterator_func, xa); @@ -211,6 +212,61 @@ static void multiorder_iteration_race(struct xarray *xa) item_kill_tree(xa); } +static void *load_creator(void *ptr) +{ + /* 'order' is set up to ensure we have sibling entries */ + unsigned int order; + struct radix_tree_root *tree = ptr; + int i; + + rcu_register_thread(); + item_insert_order(tree, 3 << RADIX_TREE_MAP_SHIFT, 0); + item_insert_order(tree, 2 << RADIX_TREE_MAP_SHIFT, 0); + for (i = 0; i < 10000; i++) { + for (order = 1; order < RADIX_TREE_MAP_SHIFT; order++) { + unsigned long index = (3 << RADIX_TREE_MAP_SHIFT) - + (1 << order); + item_insert_order(tree, index, order); + item_delete_rcu(tree, index); + } + } + rcu_unregister_thread(); + + stop_iteration = true; + return NULL; +} + +static void *load_worker(void *ptr) +{ + unsigned long index = (3 << RADIX_TREE_MAP_SHIFT) - 1; + + rcu_register_thread(); + while (!stop_iteration) { + struct item *item = xa_load(ptr, index); + assert(!xa_is_internal(item)); + } + rcu_unregister_thread(); + + return NULL; +} + +static void load_race(struct xarray *xa) +{ + const int num_threads = sysconf(_SC_NPROCESSORS_ONLN) * 4; + pthread_t worker_thread[num_threads]; + int i; + + stop_iteration = false; + pthread_create(&worker_thread[0], NULL, &load_creator, xa); + for (i = 1; i < num_threads; i++) + pthread_create(&worker_thread[i], NULL, &load_worker, xa); + + for (i = 0; i < num_threads; i++) + pthread_join(worker_thread[i], NULL); + + item_kill_tree(xa); +} + static DEFINE_XARRAY(array); void multiorder_checks(void) @@ -218,12 +274,20 @@ void multiorder_checks(void) multiorder_iteration(&array); multiorder_tagged_iteration(&array); multiorder_iteration_race(&array); + load_race(&array); radix_tree_cpu_dead(0); } -int __weak main(void) +int __weak main(int argc, char **argv) { + int opt; + + while ((opt = getopt(argc, argv, "ls:v")) != -1) { + if (opt == 'v') + test_verbose++; + } + rcu_register_thread(); radix_tree_init(); multiorder_checks(); diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 666b56f22a41..42806add0114 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -8,16 +8,19 @@ TARGETS += cachestat TARGETS += capabilities TARGETS += cgroup TARGETS += clone3 +TARGETS += connector TARGETS += core TARGETS += cpufreq TARGETS += cpu-hotplug TARGETS += damon +TARGETS += dmabuf-heaps TARGETS += drivers/dma-buf TARGETS += drivers/s390x/uvdevice TARGETS += drivers/net/bonding TARGETS += drivers/net/team TARGETS += efivarfs TARGETS += exec +TARGETS += fchmodat2 TARGETS += filesystems TARGETS += filesystems/binderfs TARGETS += filesystems/epoll @@ -56,6 +59,7 @@ TARGETS += net/mptcp TARGETS += net/openvswitch TARGETS += netfilter TARGETS += nsfs +TARGETS += perf_events TARGETS += pidfd TARGETS += pid_namespace TARGETS += powerpc @@ -88,7 +92,9 @@ endif TARGETS += tmpfs TARGETS += tpm2 TARGETS += tty +TARGETS += uevents TARGETS += user +TARGETS += user_events TARGETS += vDSO TARGETS += mm TARGETS += x86 diff --git a/tools/testing/selftests/alsa/pcm-test.c b/tools/testing/selftests/alsa/pcm-test.c index b7eef32addb4..2f5e3c462194 100644 --- a/tools/testing/selftests/alsa/pcm-test.c +++ b/tools/testing/selftests/alsa/pcm-test.c @@ -258,6 +258,8 @@ static void test_pcm_time(struct pcm_data *data, enum test_class class, const char *test_name, snd_config_t *pcm_cfg) { char name[64], key[128], msg[256]; + const int duration_s = 2, margin_ms = 100; + const int duration_ms = duration_s * 1000; const char *cs; int i, err; snd_pcm_t *handle = NULL; @@ -442,7 +444,7 @@ __format: skip = false; timestamp_now(&tstamp); - for (i = 0; i < 4; i++) { + for (i = 0; i < duration_s; i++) { if (data->stream == SND_PCM_STREAM_PLAYBACK) { frames = snd_pcm_writei(handle, samples, rate); if (frames < 0) { @@ -472,8 +474,8 @@ __format: snd_pcm_drain(handle); ms = timestamp_diff_ms(&tstamp); - if (ms < 3900 || ms > 4100) { - snprintf(msg, sizeof(msg), "time mismatch: expected 4000ms got %lld", ms); + if (ms < duration_ms - margin_ms || ms > duration_ms + margin_ms) { + snprintf(msg, sizeof(msg), "time mismatch: expected %dms got %lld", duration_ms, ms); goto __close; } diff --git a/tools/testing/selftests/arm64/Makefile b/tools/testing/selftests/arm64/Makefile index ace8b67fb22d..28b93cab8c0d 100644 --- a/tools/testing/selftests/arm64/Makefile +++ b/tools/testing/selftests/arm64/Makefile @@ -19,6 +19,8 @@ CFLAGS += -I$(top_srcdir)/tools/testing/selftests/ CFLAGS += $(KHDR_INCLUDES) +CFLAGS += -I$(top_srcdir)/tools/include + export CFLAGS export top_srcdir diff --git a/tools/testing/selftests/arm64/abi/hwcap.c b/tools/testing/selftests/arm64/abi/hwcap.c index d4ad813fed10..e3d262831d91 100644 --- a/tools/testing/selftests/arm64/abi/hwcap.c +++ b/tools/testing/selftests/arm64/abi/hwcap.c @@ -19,19 +19,38 @@ #include "../../kselftest.h" -#define TESTS_PER_HWCAP 2 +#define TESTS_PER_HWCAP 3 /* - * Function expected to generate SIGILL when the feature is not - * supported and return when it is supported. If SIGILL is generated - * then the handler must be able to skip over the instruction safely. + * Function expected to generate exception when the feature is not + * supported and return when it is supported. If the specific exception + * is generated then the handler must be able to skip over the + * instruction safely. * * Note that it is expected that for many architecture extensions * there are no specific traps due to no architecture state being * added so we may not fault if running on a kernel which doesn't know * to add the hwcap. */ -typedef void (*sigill_fn)(void); +typedef void (*sig_fn)(void); + +static void aes_sigill(void) +{ + /* AESE V0.16B, V0.16B */ + asm volatile(".inst 0x4e284800" : : : ); +} + +static void atomics_sigill(void) +{ + /* STADD W0, [SP] */ + asm volatile(".inst 0xb82003ff" : : : ); +} + +static void crc32_sigill(void) +{ + /* CRC32W W0, W0, W1 */ + asm volatile(".inst 0x1ac14800" : : : ); +} static void cssc_sigill(void) { @@ -39,6 +58,29 @@ static void cssc_sigill(void) asm volatile(".inst 0xdac01c00" : : : "x0"); } +static void fp_sigill(void) +{ + asm volatile("fmov s0, #1"); +} + +static void ilrcpc_sigill(void) +{ + /* LDAPUR W0, [SP, #8] */ + asm volatile(".inst 0x994083e0" : : : ); +} + +static void jscvt_sigill(void) +{ + /* FJCVTZS W0, D0 */ + asm volatile(".inst 0x1e7e0000" : : : ); +} + +static void lrcpc_sigill(void) +{ + /* LDAPR W0, [SP, #0] */ + asm volatile(".inst 0xb8bfc3e0" : : : ); +} + static void mops_sigill(void) { char dst[1], src[1]; @@ -53,11 +95,35 @@ static void mops_sigill(void) : "cc", "memory"); } +static void pmull_sigill(void) +{ + /* PMULL V0.1Q, V0.1D, V0.1D */ + asm volatile(".inst 0x0ee0e000" : : : ); +} + static void rng_sigill(void) { asm volatile("mrs x0, S3_3_C2_C4_0" : : : "x0"); } +static void sha1_sigill(void) +{ + /* SHA1H S0, S0 */ + asm volatile(".inst 0x5e280800" : : : ); +} + +static void sha2_sigill(void) +{ + /* SHA256H Q0, Q0, V0.4S */ + asm volatile(".inst 0x5e004000" : : : ); +} + +static void sha512_sigill(void) +{ + /* SHA512H Q0, Q0, V0.2D */ + asm volatile(".inst 0xce608000" : : : ); +} + static void sme_sigill(void) { /* RDSVL x0, #0 */ @@ -208,15 +274,46 @@ static void svebf16_sigill(void) asm volatile(".inst 0x658aa000" : : : "z0"); } +static void hbc_sigill(void) +{ + /* BC.EQ +4 */ + asm volatile("cmp xzr, xzr\n" + ".inst 0x54000030" : : : "cc"); +} + +static void uscat_sigbus(void) +{ + /* unaligned atomic access */ + asm volatile("ADD x1, sp, #2" : : : ); + /* STADD W0, [X1] */ + asm volatile(".inst 0xb820003f" : : : ); +} + static const struct hwcap_data { const char *name; unsigned long at_hwcap; unsigned long hwcap_bit; const char *cpuinfo; - sigill_fn sigill_fn; + sig_fn sigill_fn; bool sigill_reliable; + sig_fn sigbus_fn; + bool sigbus_reliable; } hwcaps[] = { { + .name = "AES", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_AES, + .cpuinfo = "aes", + .sigill_fn = aes_sigill, + }, + { + .name = "CRC32", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_CRC32, + .cpuinfo = "crc32", + .sigill_fn = crc32_sigill, + }, + { .name = "CSSC", .at_hwcap = AT_HWCAP2, .hwcap_bit = HWCAP2_CSSC, @@ -224,6 +321,50 @@ static const struct hwcap_data { .sigill_fn = cssc_sigill, }, { + .name = "FP", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_FP, + .cpuinfo = "fp", + .sigill_fn = fp_sigill, + }, + { + .name = "JSCVT", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_JSCVT, + .cpuinfo = "jscvt", + .sigill_fn = jscvt_sigill, + }, + { + .name = "LRCPC", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_LRCPC, + .cpuinfo = "lrcpc", + .sigill_fn = lrcpc_sigill, + }, + { + .name = "LRCPC2", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_ILRCPC, + .cpuinfo = "ilrcpc", + .sigill_fn = ilrcpc_sigill, + }, + { + .name = "LSE", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_ATOMICS, + .cpuinfo = "atomics", + .sigill_fn = atomics_sigill, + }, + { + .name = "LSE2", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_USCAT, + .cpuinfo = "uscat", + .sigill_fn = atomics_sigill, + .sigbus_fn = uscat_sigbus, + .sigbus_reliable = true, + }, + { .name = "MOPS", .at_hwcap = AT_HWCAP2, .hwcap_bit = HWCAP2_MOPS, @@ -232,6 +373,13 @@ static const struct hwcap_data { .sigill_reliable = true, }, { + .name = "PMULL", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_PMULL, + .cpuinfo = "pmull", + .sigill_fn = pmull_sigill, + }, + { .name = "RNG", .at_hwcap = AT_HWCAP2, .hwcap_bit = HWCAP2_RNG, @@ -245,6 +393,27 @@ static const struct hwcap_data { .cpuinfo = "rprfm", }, { + .name = "SHA1", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_SHA1, + .cpuinfo = "sha1", + .sigill_fn = sha1_sigill, + }, + { + .name = "SHA2", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_SHA2, + .cpuinfo = "sha2", + .sigill_fn = sha2_sigill, + }, + { + .name = "SHA512", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_SHA512, + .cpuinfo = "sha512", + .sigill_fn = sha512_sigill, + }, + { .name = "SME", .at_hwcap = AT_HWCAP2, .hwcap_bit = HWCAP2_SME, @@ -386,20 +555,32 @@ static const struct hwcap_data { .hwcap_bit = HWCAP2_SVE_EBF16, .cpuinfo = "sveebf16", }, + { + .name = "HBC", + .at_hwcap = AT_HWCAP2, + .hwcap_bit = HWCAP2_HBC, + .cpuinfo = "hbc", + .sigill_fn = hbc_sigill, + .sigill_reliable = true, + }, }; -static bool seen_sigill; - -static void handle_sigill(int sig, siginfo_t *info, void *context) -{ - ucontext_t *uc = context; - - seen_sigill = true; - - /* Skip over the offending instruction */ - uc->uc_mcontext.pc += 4; +typedef void (*sighandler_fn)(int, siginfo_t *, void *); + +#define DEF_SIGHANDLER_FUNC(SIG, NUM) \ +static bool seen_##SIG; \ +static void handle_##SIG(int sig, siginfo_t *info, void *context) \ +{ \ + ucontext_t *uc = context; \ + \ + seen_##SIG = true; \ + /* Skip over the offending instruction */ \ + uc->uc_mcontext.pc += 4; \ } +DEF_SIGHANDLER_FUNC(sigill, SIGILL); +DEF_SIGHANDLER_FUNC(sigbus, SIGBUS); + bool cpuinfo_present(const char *name) { FILE *f; @@ -442,24 +623,77 @@ bool cpuinfo_present(const char *name) return false; } -int main(void) +static int install_sigaction(int signum, sighandler_fn handler) { - const struct hwcap_data *hwcap; - int i, ret; - bool have_cpuinfo, have_hwcap; + int ret; struct sigaction sa; - ksft_print_header(); - ksft_set_plan(ARRAY_SIZE(hwcaps) * TESTS_PER_HWCAP); - memset(&sa, 0, sizeof(sa)); - sa.sa_sigaction = handle_sigill; + sa.sa_sigaction = handler; sa.sa_flags = SA_RESTART | SA_SIGINFO; sigemptyset(&sa.sa_mask); - ret = sigaction(SIGILL, &sa, NULL); + ret = sigaction(signum, &sa, NULL); if (ret < 0) - ksft_exit_fail_msg("Failed to install SIGILL handler: %s (%d)\n", + ksft_exit_fail_msg("Failed to install SIGNAL handler: %s (%d)\n", + strerror(errno), errno); + + return ret; +} + +static void uninstall_sigaction(int signum) +{ + if (sigaction(signum, NULL, NULL) < 0) + ksft_exit_fail_msg("Failed to uninstall SIGNAL handler: %s (%d)\n", strerror(errno), errno); +} + +#define DEF_INST_RAISE_SIG(SIG, NUM) \ +static bool inst_raise_##SIG(const struct hwcap_data *hwcap, \ + bool have_hwcap) \ +{ \ + if (!hwcap->SIG##_fn) { \ + ksft_test_result_skip(#SIG"_%s\n", hwcap->name); \ + /* assume that it would raise exception in default */ \ + return true; \ + } \ + \ + install_sigaction(NUM, handle_##SIG); \ + \ + seen_##SIG = false; \ + hwcap->SIG##_fn(); \ + \ + if (have_hwcap) { \ + /* Should be able to use the extension */ \ + ksft_test_result(!seen_##SIG, \ + #SIG"_%s\n", hwcap->name); \ + } else if (hwcap->SIG##_reliable) { \ + /* Guaranteed a SIGNAL */ \ + ksft_test_result(seen_##SIG, \ + #SIG"_%s\n", hwcap->name); \ + } else { \ + /* Missing SIGNAL might be fine */ \ + ksft_print_msg(#SIG"_%sreported for %s\n", \ + seen_##SIG ? "" : "not ", \ + hwcap->name); \ + ksft_test_result_skip(#SIG"_%s\n", \ + hwcap->name); \ + } \ + \ + uninstall_sigaction(NUM); \ + return seen_##SIG; \ +} + +DEF_INST_RAISE_SIG(sigill, SIGILL); +DEF_INST_RAISE_SIG(sigbus, SIGBUS); + +int main(void) +{ + int i; + const struct hwcap_data *hwcap; + bool have_cpuinfo, have_hwcap, raise_sigill; + + ksft_print_header(); + ksft_set_plan(ARRAY_SIZE(hwcaps) * TESTS_PER_HWCAP); for (i = 0; i < ARRAY_SIZE(hwcaps); i++) { hwcap = &hwcaps[i]; @@ -473,30 +707,15 @@ int main(void) ksft_test_result(have_hwcap == have_cpuinfo, "cpuinfo_match_%s\n", hwcap->name); - if (hwcap->sigill_fn) { - seen_sigill = false; - hwcap->sigill_fn(); - - if (have_hwcap) { - /* Should be able to use the extension */ - ksft_test_result(!seen_sigill, "sigill_%s\n", - hwcap->name); - } else if (hwcap->sigill_reliable) { - /* Guaranteed a SIGILL */ - ksft_test_result(seen_sigill, "sigill_%s\n", - hwcap->name); - } else { - /* Missing SIGILL might be fine */ - ksft_print_msg("SIGILL %sreported for %s\n", - seen_sigill ? "" : "not ", - hwcap->name); - ksft_test_result_skip("sigill_%s\n", - hwcap->name); - } - } else { - ksft_test_result_skip("sigill_%s\n", - hwcap->name); - } + /* + * Testing for SIGBUS only makes sense after make sure + * that the instruction does not cause a SIGILL signal. + */ + raise_sigill = inst_raise_sigill(hwcap, have_hwcap); + if (!raise_sigill) + inst_raise_sigbus(hwcap, have_hwcap); + else + ksft_test_result_skip("sigbus_%s\n", hwcap->name); } ksft_print_cnts(); diff --git a/tools/testing/selftests/arm64/abi/syscall-abi.c b/tools/testing/selftests/arm64/abi/syscall-abi.c index 18cc123e2347..d704511a0955 100644 --- a/tools/testing/selftests/arm64/abi/syscall-abi.c +++ b/tools/testing/selftests/arm64/abi/syscall-abi.c @@ -20,12 +20,20 @@ #include "syscall-abi.h" +/* + * The kernel defines a much larger SVE_VQ_MAX than is expressable in + * the architecture, this creates a *lot* of overhead filling the + * buffers (especially ZA) on emulated platforms so use the actual + * architectural maximum instead. + */ +#define ARCH_SVE_VQ_MAX 16 + static int default_sme_vl; static int sve_vl_count; -static unsigned int sve_vls[SVE_VQ_MAX]; +static unsigned int sve_vls[ARCH_SVE_VQ_MAX]; static int sme_vl_count; -static unsigned int sme_vls[SVE_VQ_MAX]; +static unsigned int sme_vls[ARCH_SVE_VQ_MAX]; extern void do_syscall(int sve_vl, int sme_vl); @@ -130,9 +138,9 @@ static int check_fpr(struct syscall_cfg *cfg, int sve_vl, int sme_vl, #define SVE_Z_SHARED_BYTES (128 / 8) -static uint8_t z_zero[__SVE_ZREG_SIZE(SVE_VQ_MAX)]; -uint8_t z_in[SVE_NUM_ZREGS * __SVE_ZREG_SIZE(SVE_VQ_MAX)]; -uint8_t z_out[SVE_NUM_ZREGS * __SVE_ZREG_SIZE(SVE_VQ_MAX)]; +static uint8_t z_zero[__SVE_ZREG_SIZE(ARCH_SVE_VQ_MAX)]; +uint8_t z_in[SVE_NUM_ZREGS * __SVE_ZREG_SIZE(ARCH_SVE_VQ_MAX)]; +uint8_t z_out[SVE_NUM_ZREGS * __SVE_ZREG_SIZE(ARCH_SVE_VQ_MAX)]; static void setup_z(struct syscall_cfg *cfg, int sve_vl, int sme_vl, uint64_t svcr) @@ -190,8 +198,8 @@ static int check_z(struct syscall_cfg *cfg, int sve_vl, int sme_vl, return errors; } -uint8_t p_in[SVE_NUM_PREGS * __SVE_PREG_SIZE(SVE_VQ_MAX)]; -uint8_t p_out[SVE_NUM_PREGS * __SVE_PREG_SIZE(SVE_VQ_MAX)]; +uint8_t p_in[SVE_NUM_PREGS * __SVE_PREG_SIZE(ARCH_SVE_VQ_MAX)]; +uint8_t p_out[SVE_NUM_PREGS * __SVE_PREG_SIZE(ARCH_SVE_VQ_MAX)]; static void setup_p(struct syscall_cfg *cfg, int sve_vl, int sme_vl, uint64_t svcr) @@ -222,8 +230,8 @@ static int check_p(struct syscall_cfg *cfg, int sve_vl, int sme_vl, return errors; } -uint8_t ffr_in[__SVE_PREG_SIZE(SVE_VQ_MAX)]; -uint8_t ffr_out[__SVE_PREG_SIZE(SVE_VQ_MAX)]; +uint8_t ffr_in[__SVE_PREG_SIZE(ARCH_SVE_VQ_MAX)]; +uint8_t ffr_out[__SVE_PREG_SIZE(ARCH_SVE_VQ_MAX)]; static void setup_ffr(struct syscall_cfg *cfg, int sve_vl, int sme_vl, uint64_t svcr) @@ -300,8 +308,8 @@ static int check_svcr(struct syscall_cfg *cfg, int sve_vl, int sme_vl, return errors; } -uint8_t za_in[ZA_SIG_REGS_SIZE(SVE_VQ_MAX)]; -uint8_t za_out[ZA_SIG_REGS_SIZE(SVE_VQ_MAX)]; +uint8_t za_in[ZA_SIG_REGS_SIZE(ARCH_SVE_VQ_MAX)]; +uint8_t za_out[ZA_SIG_REGS_SIZE(ARCH_SVE_VQ_MAX)]; static void setup_za(struct syscall_cfg *cfg, int sve_vl, int sme_vl, uint64_t svcr) @@ -470,9 +478,9 @@ void sve_count_vls(void) return; /* - * Enumerate up to SVE_VQ_MAX vector lengths + * Enumerate up to ARCH_SVE_VQ_MAX vector lengths */ - for (vq = SVE_VQ_MAX; vq > 0; vq /= 2) { + for (vq = ARCH_SVE_VQ_MAX; vq > 0; vq /= 2) { vl = prctl(PR_SVE_SET_VL, vq * 16); if (vl == -1) ksft_exit_fail_msg("PR_SVE_SET_VL failed: %s (%d)\n", @@ -496,9 +504,9 @@ void sme_count_vls(void) return; /* - * Enumerate up to SVE_VQ_MAX vector lengths + * Enumerate up to ARCH_SVE_VQ_MAX vector lengths */ - for (vq = SVE_VQ_MAX; vq > 0; vq /= 2) { + for (vq = ARCH_SVE_VQ_MAX; vq > 0; vq /= 2) { vl = prctl(PR_SME_SET_VL, vq * 16); if (vl == -1) ksft_exit_fail_msg("PR_SME_SET_VL failed: %s (%d)\n", diff --git a/tools/testing/selftests/arm64/bti/Makefile b/tools/testing/selftests/arm64/bti/Makefile index ccdac414ad94..05e4ee523a53 100644 --- a/tools/testing/selftests/arm64/bti/Makefile +++ b/tools/testing/selftests/arm64/bti/Makefile @@ -2,8 +2,6 @@ TEST_GEN_PROGS := btitest nobtitest -PROGS := $(patsubst %,gen/%,$(TEST_GEN_PROGS)) - # These tests are built as freestanding binaries since otherwise BTI # support in ld.so is required which is not currently widespread; when # it is available it will still be useful to test this separately as the @@ -18,44 +16,41 @@ CFLAGS_COMMON = -ffreestanding -Wall -Wextra $(CFLAGS) BTI_CC_COMMAND = $(CC) $(CFLAGS_BTI) $(CFLAGS_COMMON) -c -o $@ $< NOBTI_CC_COMMAND = $(CC) $(CFLAGS_NOBTI) $(CFLAGS_COMMON) -c -o $@ $< -%-bti.o: %.c +$(OUTPUT)/%-bti.o: %.c $(BTI_CC_COMMAND) -%-bti.o: %.S +$(OUTPUT)/%-bti.o: %.S $(BTI_CC_COMMAND) -%-nobti.o: %.c +$(OUTPUT)/%-nobti.o: %.c $(NOBTI_CC_COMMAND) -%-nobti.o: %.S +$(OUTPUT)/%-nobti.o: %.S $(NOBTI_CC_COMMAND) BTI_OBJS = \ - test-bti.o \ - signal-bti.o \ - start-bti.o \ - syscall-bti.o \ - system-bti.o \ - teststubs-bti.o \ - trampoline-bti.o -gen/btitest: $(BTI_OBJS) + $(OUTPUT)/test-bti.o \ + $(OUTPUT)/signal-bti.o \ + $(OUTPUT)/start-bti.o \ + $(OUTPUT)/syscall-bti.o \ + $(OUTPUT)/system-bti.o \ + $(OUTPUT)/teststubs-bti.o \ + $(OUTPUT)/trampoline-bti.o +$(OUTPUT)/btitest: $(BTI_OBJS) $(CC) $(CFLAGS_BTI) $(CFLAGS_COMMON) -nostdlib -static -o $@ $^ NOBTI_OBJS = \ - test-nobti.o \ - signal-nobti.o \ - start-nobti.o \ - syscall-nobti.o \ - system-nobti.o \ - teststubs-nobti.o \ - trampoline-nobti.o -gen/nobtitest: $(NOBTI_OBJS) + $(OUTPUT)/test-nobti.o \ + $(OUTPUT)/signal-nobti.o \ + $(OUTPUT)/start-nobti.o \ + $(OUTPUT)/syscall-nobti.o \ + $(OUTPUT)/system-nobti.o \ + $(OUTPUT)/teststubs-nobti.o \ + $(OUTPUT)/trampoline-nobti.o +$(OUTPUT)/nobtitest: $(NOBTI_OBJS) $(CC) $(CFLAGS_BTI) $(CFLAGS_COMMON) -nostdlib -static -o $@ $^ # Including KSFT lib.mk here will also mangle the TEST_GEN_PROGS list # to account for any OUTPUT target-dirs optionally provided by # the toplevel makefile include ../../lib.mk - -$(TEST_GEN_PROGS): $(PROGS) - cp $(PROGS) $(OUTPUT)/ diff --git a/tools/testing/selftests/arm64/bti/compiler.h b/tools/testing/selftests/arm64/bti/compiler.h deleted file mode 100644 index ebb6204f447a..000000000000 --- a/tools/testing/selftests/arm64/bti/compiler.h +++ /dev/null @@ -1,21 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright (C) 2019 Arm Limited - * Original author: Dave Martin <Dave.Martin@arm.com> - */ - -#ifndef COMPILER_H -#define COMPILER_H - -#define __always_unused __attribute__((__unused__)) -#define __noreturn __attribute__((__noreturn__)) -#define __unreachable() __builtin_unreachable() - -/* curse(e) has value e, but the compiler cannot assume so */ -#define curse(e) ({ \ - __typeof__(e) __curse_e = (e); \ - asm ("" : "+r" (__curse_e)); \ - __curse_e; \ -}) - -#endif /* ! COMPILER_H */ diff --git a/tools/testing/selftests/arm64/bti/gen/.gitignore b/tools/testing/selftests/arm64/bti/gen/.gitignore deleted file mode 100644 index 73869fabada4..000000000000 --- a/tools/testing/selftests/arm64/bti/gen/.gitignore +++ /dev/null @@ -1,2 +0,0 @@ -btitest -nobtitest diff --git a/tools/testing/selftests/arm64/bti/system.c b/tools/testing/selftests/arm64/bti/system.c index 6385d8d4973b..93d772b00bfe 100644 --- a/tools/testing/selftests/arm64/bti/system.c +++ b/tools/testing/selftests/arm64/bti/system.c @@ -8,12 +8,10 @@ #include <asm/unistd.h> -#include "compiler.h" - void __noreturn exit(int n) { syscall(__NR_exit, n); - __unreachable(); + unreachable(); } ssize_t write(int fd, const void *buf, size_t size) diff --git a/tools/testing/selftests/arm64/bti/system.h b/tools/testing/selftests/arm64/bti/system.h index aca118589705..2e9ee1284a0c 100644 --- a/tools/testing/selftests/arm64/bti/system.h +++ b/tools/testing/selftests/arm64/bti/system.h @@ -14,12 +14,12 @@ typedef __kernel_size_t size_t; typedef __kernel_ssize_t ssize_t; #include <linux/errno.h> +#include <linux/compiler.h> + #include <asm/hwcap.h> #include <asm/ptrace.h> #include <asm/unistd.h> -#include "compiler.h" - long syscall(int nr, ...); void __noreturn exit(int n); diff --git a/tools/testing/selftests/arm64/bti/test.c b/tools/testing/selftests/arm64/bti/test.c index 2cd8dcee5aec..28a8e8a28a84 100644 --- a/tools/testing/selftests/arm64/bti/test.c +++ b/tools/testing/selftests/arm64/bti/test.c @@ -17,7 +17,6 @@ typedef struct ucontext ucontext_t; #include "btitest.h" -#include "compiler.h" #include "signal.h" #define EXPECTED_TESTS 18 diff --git a/tools/testing/selftests/arm64/fp/vec-syscfg.c b/tools/testing/selftests/arm64/fp/vec-syscfg.c index 9bcfcdc34ee9..5f648b97a06f 100644 --- a/tools/testing/selftests/arm64/fp/vec-syscfg.c +++ b/tools/testing/selftests/arm64/fp/vec-syscfg.c @@ -6,6 +6,7 @@ #include <assert.h> #include <errno.h> #include <fcntl.h> +#include <stdbool.h> #include <stddef.h> #include <stdio.h> #include <stdlib.h> @@ -39,9 +40,11 @@ struct vec_data { int max_vl; }; +#define VEC_SVE 0 +#define VEC_SME 1 static struct vec_data vec_data[] = { - { + [VEC_SVE] = { .name = "SVE", .hwcap_type = AT_HWCAP, .hwcap = HWCAP_SVE, @@ -51,7 +54,7 @@ static struct vec_data vec_data[] = { .prctl_set = PR_SVE_SET_VL, .default_vl_file = "/proc/sys/abi/sve_default_vector_length", }, - { + [VEC_SME] = { .name = "SME", .hwcap_type = AT_HWCAP2, .hwcap = HWCAP2_SME, @@ -551,7 +554,8 @@ static void prctl_set_onexec(struct vec_data *data) /* For each VQ verify that setting via prctl() does the right thing */ static void prctl_set_all_vqs(struct vec_data *data) { - int ret, vq, vl, new_vl; + int ret, vq, vl, new_vl, i; + int orig_vls[ARRAY_SIZE(vec_data)]; int errors = 0; if (!data->min_vl || !data->max_vl) { @@ -560,6 +564,9 @@ static void prctl_set_all_vqs(struct vec_data *data) return; } + for (i = 0; i < ARRAY_SIZE(vec_data); i++) + orig_vls[i] = vec_data[i].rdvl(); + for (vq = SVE_VQ_MIN; vq <= SVE_VQ_MAX; vq++) { vl = sve_vl_from_vq(vq); @@ -582,6 +589,22 @@ static void prctl_set_all_vqs(struct vec_data *data) errors++; } + /* Did any other VLs change? */ + for (i = 0; i < ARRAY_SIZE(vec_data); i++) { + if (&vec_data[i] == data) + continue; + + if (!(getauxval(vec_data[i].hwcap_type) & vec_data[i].hwcap)) + continue; + + if (vec_data[i].rdvl() != orig_vls[i]) { + ksft_print_msg("%s VL changed from %d to %d\n", + vec_data[i].name, orig_vls[i], + vec_data[i].rdvl()); + errors++; + } + } + /* Was that the VL we asked for? */ if (new_vl == vl) continue; @@ -644,18 +667,107 @@ static const test_type tests[] = { prctl_set_all_vqs, }; +static inline void smstart(void) +{ + asm volatile("msr S0_3_C4_C7_3, xzr"); +} + +static inline void smstart_sm(void) +{ + asm volatile("msr S0_3_C4_C3_3, xzr"); +} + +static inline void smstop(void) +{ + asm volatile("msr S0_3_C4_C6_3, xzr"); +} + + +/* + * Verify we can change the SVE vector length while SME is active and + * continue to use SME afterwards. + */ +static void change_sve_with_za(void) +{ + struct vec_data *sve_data = &vec_data[VEC_SVE]; + bool pass = true; + int ret, i; + + if (sve_data->min_vl == sve_data->max_vl) { + ksft_print_msg("Only one SVE VL supported, can't change\n"); + ksft_test_result_skip("change_sve_while_sme\n"); + return; + } + + /* Ensure we will trigger a change when we set the maximum */ + ret = prctl(sve_data->prctl_set, sve_data->min_vl); + if (ret != sve_data->min_vl) { + ksft_print_msg("Failed to set SVE VL %d: %d\n", + sve_data->min_vl, ret); + pass = false; + } + + /* Enable SM and ZA */ + smstart(); + + /* Trigger another VL change */ + ret = prctl(sve_data->prctl_set, sve_data->max_vl); + if (ret != sve_data->max_vl) { + ksft_print_msg("Failed to set SVE VL %d: %d\n", + sve_data->max_vl, ret); + pass = false; + } + + /* + * Spin for a bit with SM enabled to try to trigger another + * save/restore. We can't use syscalls without exiting + * streaming mode. + */ + for (i = 0; i < 100000000; i++) + smstart_sm(); + + /* + * TODO: Verify that ZA was preserved over the VL change and + * spin. + */ + + /* Clean up after ourselves */ + smstop(); + ret = prctl(sve_data->prctl_set, sve_data->default_vl); + if (ret != sve_data->default_vl) { + ksft_print_msg("Failed to restore SVE VL %d: %d\n", + sve_data->default_vl, ret); + pass = false; + } + + ksft_test_result(pass, "change_sve_with_za\n"); +} + +typedef void (*test_all_type)(void); + +static const struct { + const char *name; + test_all_type test; +} all_types_tests[] = { + { "change_sve_with_za", change_sve_with_za }, +}; + int main(void) { + bool all_supported = true; int i, j; ksft_print_header(); - ksft_set_plan(ARRAY_SIZE(tests) * ARRAY_SIZE(vec_data)); + ksft_set_plan(ARRAY_SIZE(tests) * ARRAY_SIZE(vec_data) + + ARRAY_SIZE(all_types_tests)); for (i = 0; i < ARRAY_SIZE(vec_data); i++) { struct vec_data *data = &vec_data[i]; unsigned long supported; supported = getauxval(data->hwcap_type) & data->hwcap; + if (!supported) + all_supported = false; for (j = 0; j < ARRAY_SIZE(tests); j++) { if (supported) @@ -666,5 +778,12 @@ int main(void) } } + for (i = 0; i < ARRAY_SIZE(all_types_tests); i++) { + if (all_supported) + all_types_tests[i].test(); + else + ksft_test_result_skip("%s\n", all_types_tests[i].name); + } + ksft_exit_pass(); } diff --git a/tools/testing/selftests/arm64/signal/test_signals_utils.h b/tools/testing/selftests/arm64/signal/test_signals_utils.h index 222093f51b67..762c8fe9c54a 100644 --- a/tools/testing/selftests/arm64/signal/test_signals_utils.h +++ b/tools/testing/selftests/arm64/signal/test_signals_utils.h @@ -8,6 +8,8 @@ #include <stdio.h> #include <string.h> +#include <linux/compiler.h> + #include "test_signals.h" int test_init(struct tdescr *td); @@ -60,13 +62,25 @@ static __always_inline bool get_current_context(struct tdescr *td, size_t dest_sz) { static volatile bool seen_already; + int i; + char *uc = (char *)dest_uc; assert(td && dest_uc); /* it's a genuine invocation..reinit */ seen_already = 0; td->live_uc_valid = 0; td->live_sz = dest_sz; - memset(dest_uc, 0x00, td->live_sz); + + /* + * This is a memset() but we don't want the compiler to + * optimise it into either instructions or a library call + * which might be incompatible with streaming mode. + */ + for (i = 0; i < td->live_sz; i++) { + uc[i] = 0; + OPTIMIZER_HIDE_VAR(uc[0]); + } + td->live_uc = dest_uc; /* * Grab ucontext_t triggering a SIGTRAP. @@ -104,6 +118,17 @@ static __always_inline bool get_current_context(struct tdescr *td, : "memory"); /* + * If we were grabbing a streaming mode context then we may + * have entered streaming mode behind the system's back and + * libc or compiler generated code might decide to do + * something invalid in streaming mode, or potentially even + * the state of ZA. Issue a SMSTOP to exit both now we have + * grabbed the state. + */ + if (td->feats_supported & FEAT_SME) + asm volatile("msr S0_3_C4_C6_3, xzr"); + + /* * If we get here with seen_already==1 it implies the td->live_uc * context has been used to get back here....this probably means * a test has failed to cause a SEGV...anyway live_uc does not diff --git a/tools/testing/selftests/arm64/signal/testcases/zt_regs.c b/tools/testing/selftests/arm64/signal/testcases/zt_regs.c index e1eb4d5c027a..2e384d731618 100644 --- a/tools/testing/selftests/arm64/signal/testcases/zt_regs.c +++ b/tools/testing/selftests/arm64/signal/testcases/zt_regs.c @@ -65,6 +65,7 @@ int zt_regs_run(struct tdescr *td, siginfo_t *si, ucontext_t *uc) if (memcmp(zeros, (char *)zt + ZT_SIG_REGS_OFFSET, ZT_SIG_REGS_SIZE(zt->nregs)) != 0) { fprintf(stderr, "ZT data invalid\n"); + free(zeros); return 1; } diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index 116fecf80ca1..f1aebabfb017 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -13,6 +13,7 @@ test_dev_cgroup /test_progs /test_progs-no_alu32 /test_progs-bpf_gcc +/test_progs-cpuv4 test_verifier_log feature test_sock @@ -36,12 +37,14 @@ test_cpp *.lskel.h /no_alu32 /bpf_gcc +/cpuv4 /host-tools /tools /runqslower /bench /veristat /sign-file +/uprobe_multi *.ko *.tmp xskxceiver diff --git a/tools/testing/selftests/bpf/DENYLIST.aarch64 b/tools/testing/selftests/bpf/DENYLIST.aarch64 index 08adc805878b..7f768d335698 100644 --- a/tools/testing/selftests/bpf/DENYLIST.aarch64 +++ b/tools/testing/selftests/bpf/DENYLIST.aarch64 @@ -10,3 +10,8 @@ kprobe_multi_test/link_api_addrs # link_fd unexpected link_fd: a kprobe_multi_test/link_api_syms # link_fd unexpected link_fd: actual -95 < expected 0 kprobe_multi_test/skel_api # libbpf: failed to load BPF skeleton 'kprobe_multi': -3 module_attach # prog 'kprobe_multi': failed to auto-attach: -95 +fentry_test/fentry_many_args # fentry_many_args:FAIL:fentry_many_args_attach unexpected error: -524 +fexit_test/fexit_many_args # fexit_many_args:FAIL:fexit_many_args_attach unexpected error: -524 +fill_link_info/kprobe_multi_link_info # bpf_program__attach_kprobe_multi_opts unexpected error: -95 +fill_link_info/kretprobe_multi_link_info # bpf_program__attach_kprobe_multi_opts unexpected error: -95 +fill_link_info/kprobe_multi_invalid_ubuff # bpf_program__attach_kprobe_multi_opts unexpected error: -95 diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 538df8fb8c42..caede9b574cb 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -12,7 +12,11 @@ BPFDIR := $(LIBDIR)/bpf TOOLSINCDIR := $(TOOLSDIR)/include BPFTOOLDIR := $(TOOLSDIR)/bpf/bpftool APIDIR := $(TOOLSINCDIR)/uapi +ifneq ($(O),) +GENDIR := $(O)/include/generated +else GENDIR := $(abspath ../../../../include/generated) +endif GENHDR := $(GENDIR)/autoconf.h HOSTPKG_CONFIG := pkg-config @@ -29,11 +33,16 @@ CFLAGS += -g -O0 -rdynamic -Wall -Werror $(GENFLAGS) $(SAN_CFLAGS) \ LDFLAGS += $(SAN_LDFLAGS) LDLIBS += -lelf -lz -lrt -lpthread -# Silence some warnings when compiled with clang ifneq ($(LLVM),) +# Silence some warnings when compiled with clang CFLAGS += -Wno-unused-command-line-argument endif +# Check whether bpf cpu=v4 is supported or not by clang +ifneq ($(shell $(CLANG) --target=bpf -mcpu=help 2>&1 | grep 'v4'),) +CLANG_CPUV4 := 1 +endif + # Order correspond to 'make run_tests' order TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \ test_dev_cgroup \ @@ -41,10 +50,17 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test test_cgroup_storage \ test_tcpnotify_user test_sysctl \ test_progs-no_alu32 +TEST_INST_SUBDIRS := no_alu32 # Also test bpf-gcc, if present ifneq ($(BPF_GCC),) TEST_GEN_PROGS += test_progs-bpf_gcc +TEST_INST_SUBDIRS += bpf_gcc +endif + +ifneq ($(CLANG_CPUV4),) +TEST_GEN_PROGS += test_progs-cpuv4 +TEST_INST_SUBDIRS += cpuv4 endif TEST_GEN_FILES = test_lwt_ip_encap.bpf.o test_tc_edt.bpf.o @@ -331,7 +347,7 @@ $(RESOLVE_BTFIDS): $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/resolve_btfids \ OUTPUT=$(HOST_BUILD_DIR)/resolve_btfids/ BPFOBJ=$(HOST_BPFOBJ) # Get Clang's default includes on this system, as opposed to those seen by -# '-target bpf'. This fixes "missing" files on some architectures/distros, +# '--target=bpf'. This fixes "missing" files on some architectures/distros, # such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc. # # Use '-idirafter': Don't interfere with include mechanics except where the @@ -372,12 +388,17 @@ $(OUTPUT)/cgroup_getset_retval_hooks.o: cgroup_getset_retval_hooks.h # $3 - CFLAGS define CLANG_BPF_BUILD_RULE $(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2) - $(Q)$(CLANG) $3 -O2 -target bpf -c $1 -mcpu=v3 -o $2 + $(Q)$(CLANG) $3 -O2 --target=bpf -c $1 -mcpu=v3 -o $2 endef # Similar to CLANG_BPF_BUILD_RULE, but with disabled alu32 define CLANG_NOALU32_BPF_BUILD_RULE $(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2) - $(Q)$(CLANG) $3 -O2 -target bpf -c $1 -mcpu=v2 -o $2 + $(Q)$(CLANG) $3 -O2 --target=bpf -c $1 -mcpu=v2 -o $2 +endef +# Similar to CLANG_BPF_BUILD_RULE, but with cpu-v4 +define CLANG_CPUV4_BPF_BUILD_RULE + $(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2) + $(Q)$(CLANG) $3 -O2 --target=bpf -c $1 -mcpu=v4 -o $2 endef # Build BPF object using GCC define GCC_BPF_BUILD_RULE @@ -421,7 +442,7 @@ LINKED_BPF_SRCS := $(patsubst %.bpf.o,%.c,$(foreach skel,$(LINKED_SKELS),$($(ske # $eval()) and pass control to DEFINE_TEST_RUNNER_RULES. # Parameters: # $1 - test runner base binary name (e.g., test_progs) -# $2 - test runner extra "flavor" (e.g., no_alu32, gcc-bpf, etc) +# $2 - test runner extra "flavor" (e.g., no_alu32, cpuv4, gcc-bpf, etc) define DEFINE_TEST_RUNNER TRUNNER_OUTPUT := $(OUTPUT)$(if $2,/)$2 @@ -449,7 +470,7 @@ endef # Using TRUNNER_XXX variables, provided by callers of DEFINE_TEST_RUNNER and # set up by DEFINE_TEST_RUNNER itself, create test runner build rules with: # $1 - test runner base binary name (e.g., test_progs) -# $2 - test runner extra "flavor" (e.g., no_alu32, gcc-bpf, etc) +# $2 - test runner extra "flavor" (e.g., no_alu32, cpuv4, gcc-bpf, etc) define DEFINE_TEST_RUNNER_RULES ifeq ($($(TRUNNER_OUTPUT)-dir),) @@ -561,12 +582,13 @@ TRUNNER_EXTRA_SOURCES := test_progs.c cgroup_helpers.c trace_helpers.c \ network_helpers.c testing_helpers.c \ btf_helpers.c flow_dissector_load.h \ cap_helpers.c test_loader.c xsk.c disasm.c \ - json_writer.c unpriv_helpers.c - + json_writer.c unpriv_helpers.c \ + ip_check_defrag_frags.h TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read $(OUTPUT)/bpf_testmod.ko \ $(OUTPUT)/liburandom_read.so \ $(OUTPUT)/xdp_synproxy \ $(OUTPUT)/sign-file \ + $(OUTPUT)/uprobe_multi \ ima_setup.sh \ verify_sig_setup.sh \ $(wildcard progs/btf_dump_test_case_*.c) \ @@ -580,6 +602,13 @@ TRUNNER_BPF_BUILD_RULE := CLANG_NOALU32_BPF_BUILD_RULE TRUNNER_BPF_CFLAGS := $(BPF_CFLAGS) $(CLANG_CFLAGS) $(eval $(call DEFINE_TEST_RUNNER,test_progs,no_alu32)) +# Define test_progs-cpuv4 test runner. +ifneq ($(CLANG_CPUV4),) +TRUNNER_BPF_BUILD_RULE := CLANG_CPUV4_BPF_BUILD_RULE +TRUNNER_BPF_CFLAGS := $(BPF_CFLAGS) $(CLANG_CFLAGS) +$(eval $(call DEFINE_TEST_RUNNER,test_progs,cpuv4)) +endif + # Define test_progs BPF-GCC-flavored test runner. ifneq ($(BPF_GCC),) TRUNNER_BPF_BUILD_RULE := GCC_BPF_BUILD_RULE @@ -644,11 +673,13 @@ $(OUTPUT)/bench_local_storage.o: $(OUTPUT)/local_storage_bench.skel.h $(OUTPUT)/bench_local_storage_rcu_tasks_trace.o: $(OUTPUT)/local_storage_rcu_tasks_trace_bench.skel.h $(OUTPUT)/bench_local_storage_create.o: $(OUTPUT)/bench_local_storage_create.skel.h $(OUTPUT)/bench_bpf_hashmap_lookup.o: $(OUTPUT)/bpf_hashmap_lookup.skel.h +$(OUTPUT)/bench_htab_mem.o: $(OUTPUT)/htab_mem_bench.skel.h $(OUTPUT)/bench.o: bench.h testing_helpers.h $(BPFOBJ) $(OUTPUT)/bench: LDLIBS += -lm $(OUTPUT)/bench: $(OUTPUT)/bench.o \ $(TESTING_HELPERS) \ $(TRACE_HELPERS) \ + $(CGROUP_HELPERS) \ $(OUTPUT)/bench_count.o \ $(OUTPUT)/bench_rename.o \ $(OUTPUT)/bench_trigger.o \ @@ -661,6 +692,7 @@ $(OUTPUT)/bench: $(OUTPUT)/bench.o \ $(OUTPUT)/bench_local_storage_rcu_tasks_trace.o \ $(OUTPUT)/bench_bpf_hashmap_lookup.o \ $(OUTPUT)/bench_local_storage_create.o \ + $(OUTPUT)/bench_htab_mem.o \ # $(call msg,BINARY,,$@) $(Q)$(CC) $(CFLAGS) $(LDFLAGS) $(filter %.a %.o,$^) $(LDLIBS) -o $@ @@ -670,14 +702,27 @@ $(OUTPUT)/veristat: $(OUTPUT)/veristat.o $(call msg,BINARY,,$@) $(Q)$(CC) $(CFLAGS) $(LDFLAGS) $(filter %.a %.o,$^) $(LDLIBS) -o $@ +$(OUTPUT)/uprobe_multi: uprobe_multi.c + $(call msg,BINARY,,$@) + $(Q)$(CC) $(CFLAGS) $(LDFLAGS) $^ $(LDLIBS) -o $@ + EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(SCRATCH_DIR) $(HOST_SCRATCH_DIR) \ prog_tests/tests.h map_tests/tests.h verifier/tests.h \ feature bpftool \ $(addprefix $(OUTPUT)/,*.o *.skel.h *.lskel.h *.subskel.h \ - no_alu32 bpf_gcc bpf_testmod.ko \ + no_alu32 cpuv4 bpf_gcc bpf_testmod.ko \ liburandom_read.so) .PHONY: docs docs-clean # Delete partially updated (corrupted) files on error .DELETE_ON_ERROR: + +DEFAULT_INSTALL_RULE := $(INSTALL_RULE) +override define INSTALL_RULE + $(DEFAULT_INSTALL_RULE) + @for DIR in $(TEST_INST_SUBDIRS); do \ + mkdir -p $(INSTALL_PATH)/$$DIR; \ + rsync -a $(OUTPUT)/$$DIR/*.bpf.o $(INSTALL_PATH)/$$DIR;\ + done +endef diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c index 41fe5a82b88b..73ce11b0547d 100644 --- a/tools/testing/selftests/bpf/bench.c +++ b/tools/testing/selftests/bpf/bench.c @@ -279,6 +279,7 @@ extern struct argp bench_local_storage_rcu_tasks_trace_argp; extern struct argp bench_strncmp_argp; extern struct argp bench_hashmap_lookup_argp; extern struct argp bench_local_storage_create_argp; +extern struct argp bench_htab_mem_argp; static const struct argp_child bench_parsers[] = { { &bench_ringbufs_argp, 0, "Ring buffers benchmark", 0 }, @@ -290,6 +291,7 @@ static const struct argp_child bench_parsers[] = { "local_storage RCU Tasks Trace slowdown benchmark", 0 }, { &bench_hashmap_lookup_argp, 0, "Hashmap lookup benchmark", 0 }, { &bench_local_storage_create_argp, 0, "local-storage-create benchmark", 0 }, + { &bench_htab_mem_argp, 0, "hash map memory benchmark", 0 }, {}, }; @@ -520,6 +522,7 @@ extern const struct bench bench_local_storage_cache_hashmap_control; extern const struct bench bench_local_storage_tasks_trace; extern const struct bench bench_bpf_hashmap_lookup; extern const struct bench bench_local_storage_create; +extern const struct bench bench_htab_mem; static const struct bench *benchs[] = { &bench_count_global, @@ -561,6 +564,7 @@ static const struct bench *benchs[] = { &bench_local_storage_tasks_trace, &bench_bpf_hashmap_lookup, &bench_local_storage_create, + &bench_htab_mem, }; static void find_benchmark(void) diff --git a/tools/testing/selftests/bpf/bench.h b/tools/testing/selftests/bpf/bench.h index 7ff32be3d730..68180d8f8558 100644 --- a/tools/testing/selftests/bpf/bench.h +++ b/tools/testing/selftests/bpf/bench.h @@ -81,15 +81,6 @@ void grace_period_latency_basic_stats(struct bench_res res[], int res_cnt, void grace_period_ticks_basic_stats(struct bench_res res[], int res_cnt, struct basic_stats *gp_stat); -static inline __u64 get_time_ns(void) -{ - struct timespec t; - - clock_gettime(CLOCK_MONOTONIC, &t); - - return (u64)t.tv_sec * 1000000000 + t.tv_nsec; -} - static inline void atomic_inc(long *value) { (void)__atomic_add_fetch(value, 1, __ATOMIC_RELAXED); diff --git a/tools/testing/selftests/bpf/benchs/bench_htab_mem.c b/tools/testing/selftests/bpf/benchs/bench_htab_mem.c new file mode 100644 index 000000000000..9146d3f414d2 --- /dev/null +++ b/tools/testing/selftests/bpf/benchs/bench_htab_mem.c @@ -0,0 +1,350 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023. Huawei Technologies Co., Ltd */ +#include <argp.h> +#include <stdbool.h> +#include <pthread.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <sys/param.h> +#include <fcntl.h> + +#include "bench.h" +#include "bpf_util.h" +#include "cgroup_helpers.h" +#include "htab_mem_bench.skel.h" + +struct htab_mem_use_case { + const char *name; + const char **progs; + /* Do synchronization between addition thread and deletion thread */ + bool need_sync; +}; + +static struct htab_mem_ctx { + const struct htab_mem_use_case *uc; + struct htab_mem_bench *skel; + pthread_barrier_t *notify; + int fd; +} ctx; + +const char *ow_progs[] = {"overwrite", NULL}; +const char *batch_progs[] = {"batch_add_batch_del", NULL}; +const char *add_del_progs[] = {"add_only", "del_only", NULL}; +const static struct htab_mem_use_case use_cases[] = { + { .name = "overwrite", .progs = ow_progs }, + { .name = "batch_add_batch_del", .progs = batch_progs }, + { .name = "add_del_on_diff_cpu", .progs = add_del_progs, .need_sync = true }, +}; + +static struct htab_mem_args { + u32 value_size; + const char *use_case; + bool preallocated; +} args = { + .value_size = 8, + .use_case = "overwrite", + .preallocated = false, +}; + +enum { + ARG_VALUE_SIZE = 10000, + ARG_USE_CASE = 10001, + ARG_PREALLOCATED = 10002, +}; + +static const struct argp_option opts[] = { + { "value-size", ARG_VALUE_SIZE, "VALUE_SIZE", 0, + "Set the value size of hash map (default 8)" }, + { "use-case", ARG_USE_CASE, "USE_CASE", 0, + "Set the use case of hash map: overwrite|batch_add_batch_del|add_del_on_diff_cpu" }, + { "preallocated", ARG_PREALLOCATED, NULL, 0, "use preallocated hash map" }, + {}, +}; + +static error_t htab_mem_parse_arg(int key, char *arg, struct argp_state *state) +{ + switch (key) { + case ARG_VALUE_SIZE: + args.value_size = strtoul(arg, NULL, 10); + if (args.value_size > 4096) { + fprintf(stderr, "too big value size %u\n", args.value_size); + argp_usage(state); + } + break; + case ARG_USE_CASE: + args.use_case = strdup(arg); + if (!args.use_case) { + fprintf(stderr, "no mem for use-case\n"); + argp_usage(state); + } + break; + case ARG_PREALLOCATED: + args.preallocated = true; + break; + default: + return ARGP_ERR_UNKNOWN; + } + + return 0; +} + +const struct argp bench_htab_mem_argp = { + .options = opts, + .parser = htab_mem_parse_arg, +}; + +static void htab_mem_validate(void) +{ + if (!strcmp(use_cases[2].name, args.use_case) && env.producer_cnt % 2) { + fprintf(stderr, "%s needs an even number of producers\n", args.use_case); + exit(1); + } +} + +static int htab_mem_bench_init_barriers(void) +{ + pthread_barrier_t *barriers; + unsigned int i, nr; + + if (!ctx.uc->need_sync) + return 0; + + nr = (env.producer_cnt + 1) / 2; + barriers = calloc(nr, sizeof(*barriers)); + if (!barriers) + return -1; + + /* Used for synchronization between two threads */ + for (i = 0; i < nr; i++) + pthread_barrier_init(&barriers[i], NULL, 2); + + ctx.notify = barriers; + return 0; +} + +static void htab_mem_bench_exit_barriers(void) +{ + unsigned int i, nr; + + if (!ctx.notify) + return; + + nr = (env.producer_cnt + 1) / 2; + for (i = 0; i < nr; i++) + pthread_barrier_destroy(&ctx.notify[i]); + free(ctx.notify); +} + +static const struct htab_mem_use_case *htab_mem_find_use_case_or_exit(const char *name) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(use_cases); i++) { + if (!strcmp(name, use_cases[i].name)) + return &use_cases[i]; + } + + fprintf(stderr, "no such use-case: %s\n", name); + fprintf(stderr, "available use case:"); + for (i = 0; i < ARRAY_SIZE(use_cases); i++) + fprintf(stderr, " %s", use_cases[i].name); + fprintf(stderr, "\n"); + exit(1); +} + +static void htab_mem_setup(void) +{ + struct bpf_map *map; + const char **names; + int err; + + setup_libbpf(); + + ctx.uc = htab_mem_find_use_case_or_exit(args.use_case); + err = htab_mem_bench_init_barriers(); + if (err) { + fprintf(stderr, "failed to init barrier\n"); + exit(1); + } + + ctx.fd = cgroup_setup_and_join("/htab_mem"); + if (ctx.fd < 0) + goto cleanup; + + ctx.skel = htab_mem_bench__open(); + if (!ctx.skel) { + fprintf(stderr, "failed to open skeleton\n"); + goto cleanup; + } + + map = ctx.skel->maps.htab; + bpf_map__set_value_size(map, args.value_size); + /* Ensure that different CPUs can operate on different subset */ + bpf_map__set_max_entries(map, MAX(8192, 64 * env.nr_cpus)); + if (args.preallocated) + bpf_map__set_map_flags(map, bpf_map__map_flags(map) & ~BPF_F_NO_PREALLOC); + + names = ctx.uc->progs; + while (*names) { + struct bpf_program *prog; + + prog = bpf_object__find_program_by_name(ctx.skel->obj, *names); + if (!prog) { + fprintf(stderr, "no such program %s\n", *names); + goto cleanup; + } + bpf_program__set_autoload(prog, true); + names++; + } + ctx.skel->bss->nr_thread = env.producer_cnt; + + err = htab_mem_bench__load(ctx.skel); + if (err) { + fprintf(stderr, "failed to load skeleton\n"); + goto cleanup; + } + err = htab_mem_bench__attach(ctx.skel); + if (err) { + fprintf(stderr, "failed to attach skeleton\n"); + goto cleanup; + } + return; + +cleanup: + htab_mem_bench__destroy(ctx.skel); + htab_mem_bench_exit_barriers(); + if (ctx.fd >= 0) { + close(ctx.fd); + cleanup_cgroup_environment(); + } + exit(1); +} + +static void htab_mem_add_fn(pthread_barrier_t *notify) +{ + while (true) { + /* Do addition */ + (void)syscall(__NR_getpgid, 0); + /* Notify deletion thread to do deletion */ + pthread_barrier_wait(notify); + /* Wait for deletion to complete */ + pthread_barrier_wait(notify); + } +} + +static void htab_mem_delete_fn(pthread_barrier_t *notify) +{ + while (true) { + /* Wait for addition to complete */ + pthread_barrier_wait(notify); + /* Do deletion */ + (void)syscall(__NR_getppid); + /* Notify addition thread to do addition */ + pthread_barrier_wait(notify); + } +} + +static void *htab_mem_producer(void *arg) +{ + pthread_barrier_t *notify; + int seq; + + if (!ctx.uc->need_sync) { + while (true) + (void)syscall(__NR_getpgid, 0); + return NULL; + } + + seq = (long)arg; + notify = &ctx.notify[seq / 2]; + if (seq & 1) + htab_mem_delete_fn(notify); + else + htab_mem_add_fn(notify); + return NULL; +} + +static void htab_mem_read_mem_cgrp_file(const char *name, unsigned long *value) +{ + char buf[32]; + ssize_t got; + int fd; + + fd = openat(ctx.fd, name, O_RDONLY); + if (fd < 0) { + /* cgroup v1 ? */ + fprintf(stderr, "no %s\n", name); + *value = 0; + return; + } + + got = read(fd, buf, sizeof(buf) - 1); + if (got <= 0) { + *value = 0; + return; + } + buf[got] = 0; + + *value = strtoull(buf, NULL, 0); + + close(fd); +} + +static void htab_mem_measure(struct bench_res *res) +{ + res->hits = atomic_swap(&ctx.skel->bss->op_cnt, 0) / env.producer_cnt; + htab_mem_read_mem_cgrp_file("memory.current", &res->gp_ct); +} + +static void htab_mem_report_progress(int iter, struct bench_res *res, long delta_ns) +{ + double loop, mem; + + loop = res->hits / 1000.0 / (delta_ns / 1000000000.0); + mem = res->gp_ct / 1048576.0; + printf("Iter %3d (%7.3lfus): ", iter, (delta_ns - 1000000000) / 1000.0); + printf("per-prod-op %7.2lfk/s, memory usage %7.2lfMiB\n", loop, mem); +} + +static void htab_mem_report_final(struct bench_res res[], int res_cnt) +{ + double mem_mean = 0.0, mem_stddev = 0.0; + double loop_mean = 0.0, loop_stddev = 0.0; + unsigned long peak_mem; + int i; + + for (i = 0; i < res_cnt; i++) { + loop_mean += res[i].hits / 1000.0 / (0.0 + res_cnt); + mem_mean += res[i].gp_ct / 1048576.0 / (0.0 + res_cnt); + } + if (res_cnt > 1) { + for (i = 0; i < res_cnt; i++) { + loop_stddev += (loop_mean - res[i].hits / 1000.0) * + (loop_mean - res[i].hits / 1000.0) / + (res_cnt - 1.0); + mem_stddev += (mem_mean - res[i].gp_ct / 1048576.0) * + (mem_mean - res[i].gp_ct / 1048576.0) / + (res_cnt - 1.0); + } + loop_stddev = sqrt(loop_stddev); + mem_stddev = sqrt(mem_stddev); + } + + htab_mem_read_mem_cgrp_file("memory.peak", &peak_mem); + printf("Summary: per-prod-op %7.2lf \u00B1 %7.2lfk/s, memory usage %7.2lf \u00B1 %7.2lfMiB," + " peak memory usage %7.2lfMiB\n", + loop_mean, loop_stddev, mem_mean, mem_stddev, peak_mem / 1048576.0); + + cleanup_cgroup_environment(); +} + +const struct bench bench_htab_mem = { + .name = "htab-mem", + .argp = &bench_htab_mem_argp, + .validate = htab_mem_validate, + .setup = htab_mem_setup, + .producer_thread = htab_mem_producer, + .measure = htab_mem_measure, + .report_progress = htab_mem_report_progress, + .report_final = htab_mem_report_final, +}; diff --git a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c index 3ca14ad36607..e1ee979e6acc 100644 --- a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c +++ b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c @@ -399,7 +399,7 @@ static void perfbuf_libbpf_setup(void) ctx->skel = perfbuf_setup_skeleton(); memset(&attr, 0, sizeof(attr)); - attr.config = PERF_COUNT_SW_BPF_OUTPUT, + attr.config = PERF_COUNT_SW_BPF_OUTPUT; attr.type = PERF_TYPE_SOFTWARE; attr.sample_type = PERF_SAMPLE_RAW; /* notify only every Nth sample */ diff --git a/tools/testing/selftests/bpf/benchs/run_bench_htab_mem.sh b/tools/testing/selftests/bpf/benchs/run_bench_htab_mem.sh new file mode 100755 index 000000000000..9ff5832463a2 --- /dev/null +++ b/tools/testing/selftests/bpf/benchs/run_bench_htab_mem.sh @@ -0,0 +1,40 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source ./benchs/run_common.sh + +set -eufo pipefail + +htab_mem() +{ + echo -n "per-prod-op: " + echo -n "$*" | sed -E "s/.* per-prod-op\s+([0-9]+\.[0-9]+ ± [0-9]+\.[0-9]+k\/s).*/\1/" + echo -n -e ", avg mem: " + echo -n "$*" | sed -E "s/.* memory usage\s+([0-9]+\.[0-9]+ ± [0-9]+\.[0-9]+MiB).*/\1/" + echo -n ", peak mem: " + echo "$*" | sed -E "s/.* peak memory usage\s+([0-9]+\.[0-9]+MiB).*/\1/" +} + +summarize_htab_mem() +{ + local bench="$1" + local summary=$(echo $2 | tail -n1) + + printf "%-20s %s\n" "$bench" "$(htab_mem $summary)" +} + +htab_mem_bench() +{ + local name + + for name in overwrite batch_add_batch_del add_del_on_diff_cpu + do + summarize_htab_mem "$name" "$($RUN_BENCH htab-mem --use-case $name -p8 "$@")" + done +} + +header "preallocated" +htab_mem_bench "--preallocated" + +header "normal bpf ma" +htab_mem_bench diff --git a/tools/testing/selftests/bpf/benchs/run_bench_rename.sh b/tools/testing/selftests/bpf/benchs/run_bench_rename.sh index 16f774b1cdbe..7b281dbe4165 100755 --- a/tools/testing/selftests/bpf/benchs/run_bench_rename.sh +++ b/tools/testing/selftests/bpf/benchs/run_bench_rename.sh @@ -2,7 +2,7 @@ set -eufo pipefail -for i in base kprobe kretprobe rawtp fentry fexit fmodret +for i in base kprobe kretprobe rawtp fentry fexit do summary=$(sudo ./bench -w2 -d5 -a rename-$i | tail -n1 | cut -d'(' -f1 | cut -d' ' -f3-) printf "%-10s: %s\n" $i "$summary" diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c index aaf6ef1201c7..cefc5dd72573 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c @@ -34,6 +34,11 @@ struct bpf_testmod_struct_arg_3 { int b[]; }; +struct bpf_testmod_struct_arg_4 { + u64 a; + int b; +}; + __diag_push(); __diag_ignore_all("-Wmissing-prototypes", "Global functions as their definitions will be in bpf_testmod.ko BTF"); @@ -75,6 +80,30 @@ bpf_testmod_test_struct_arg_6(struct bpf_testmod_struct_arg_3 *a) { return bpf_testmod_test_struct_arg_result; } +noinline int +bpf_testmod_test_struct_arg_7(u64 a, void *b, short c, int d, void *e, + struct bpf_testmod_struct_arg_4 f) +{ + bpf_testmod_test_struct_arg_result = a + (long)b + c + d + + (long)e + f.a + f.b; + return bpf_testmod_test_struct_arg_result; +} + +noinline int +bpf_testmod_test_struct_arg_8(u64 a, void *b, short c, int d, void *e, + struct bpf_testmod_struct_arg_4 f, int g) +{ + bpf_testmod_test_struct_arg_result = a + (long)b + c + d + + (long)e + f.a + f.b + g; + return bpf_testmod_test_struct_arg_result; +} + +noinline int +bpf_testmod_test_arg_ptr_to_struct(struct bpf_testmod_struct_arg_1 *a) { + bpf_testmod_test_struct_arg_result = a->a; + return bpf_testmod_test_struct_arg_result; +} + __bpf_kfunc void bpf_testmod_test_mod_kfunc(int i) { @@ -191,6 +220,20 @@ noinline int bpf_testmod_fentry_test3(char a, int b, u64 c) return a + b + c; } +noinline int bpf_testmod_fentry_test7(u64 a, void *b, short c, int d, + void *e, char f, int g) +{ + return a + (long)b + c + d + (long)e + f + g; +} + +noinline int bpf_testmod_fentry_test11(u64 a, void *b, short c, int d, + void *e, char f, int g, + unsigned int h, long i, __u64 j, + unsigned long k) +{ + return a + (long)b + c + d + (long)e + f + g + h + i + j + k; +} + int bpf_testmod_fentry_ok; noinline ssize_t @@ -203,9 +246,10 @@ bpf_testmod_test_read(struct file *file, struct kobject *kobj, .off = off, .len = len, }; - struct bpf_testmod_struct_arg_1 struct_arg1 = {10}; + struct bpf_testmod_struct_arg_1 struct_arg1 = {10}, struct_arg1_2 = {-1}; struct bpf_testmod_struct_arg_2 struct_arg2 = {2, 3}; struct bpf_testmod_struct_arg_3 *struct_arg3; + struct bpf_testmod_struct_arg_4 struct_arg4 = {21, 22}; int i = 1; while (bpf_testmod_return_ptr(i)) @@ -216,6 +260,12 @@ bpf_testmod_test_read(struct file *file, struct kobject *kobj, (void)bpf_testmod_test_struct_arg_3(1, 4, struct_arg2); (void)bpf_testmod_test_struct_arg_4(struct_arg1, 1, 2, 3, struct_arg2); (void)bpf_testmod_test_struct_arg_5(); + (void)bpf_testmod_test_struct_arg_7(16, (void *)17, 18, 19, + (void *)20, struct_arg4); + (void)bpf_testmod_test_struct_arg_8(16, (void *)17, 18, 19, + (void *)20, struct_arg4, 23); + + (void)bpf_testmod_test_arg_ptr_to_struct(&struct_arg1_2); struct_arg3 = kmalloc((sizeof(struct bpf_testmod_struct_arg_3) + sizeof(int)), GFP_KERNEL); @@ -243,7 +293,11 @@ bpf_testmod_test_read(struct file *file, struct kobject *kobj, if (bpf_testmod_fentry_test1(1) != 2 || bpf_testmod_fentry_test2(2, 3) != 5 || - bpf_testmod_fentry_test3(4, 5, 6) != 15) + bpf_testmod_fentry_test3(4, 5, 6) != 15 || + bpf_testmod_fentry_test7(16, (void *)17, 18, 19, (void *)20, + 21, 22) != 133 || + bpf_testmod_fentry_test11(16, (void *)17, 18, 19, (void *)20, + 21, 22, 23, 24, 25, 26) != 231) goto out; bpf_testmod_fentry_ok = 1; diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c index 9e95b37a7dff..2caee8423ee0 100644 --- a/tools/testing/selftests/bpf/cgroup_helpers.c +++ b/tools/testing/selftests/bpf/cgroup_helpers.c @@ -278,6 +278,18 @@ int join_cgroup(const char *relative_path) } /** + * join_root_cgroup() - Join the root cgroup + * + * This function joins the root cgroup. + * + * On success, it returns 0, otherwise on failure it returns 1. + */ +int join_root_cgroup(void) +{ + return join_cgroup_from_top(CGROUP_MOUNT_PATH); +} + +/** * join_parent_cgroup() - Join a cgroup in the parent process workdir * @relative_path: The cgroup path, relative to parent process workdir, to join * diff --git a/tools/testing/selftests/bpf/cgroup_helpers.h b/tools/testing/selftests/bpf/cgroup_helpers.h index f099a166c94d..5c2cb9c8b546 100644 --- a/tools/testing/selftests/bpf/cgroup_helpers.h +++ b/tools/testing/selftests/bpf/cgroup_helpers.h @@ -22,6 +22,7 @@ void remove_cgroup(const char *relative_path); unsigned long long get_cgroup_id(const char *relative_path); int join_cgroup(const char *relative_path); +int join_root_cgroup(void); int join_parent_cgroup(const char *relative_path); int setup_cgroup_environment(void); diff --git a/tools/testing/selftests/bpf/cgroup_tcp_skb.h b/tools/testing/selftests/bpf/cgroup_tcp_skb.h new file mode 100644 index 000000000000..7f6b24f102fb --- /dev/null +++ b/tools/testing/selftests/bpf/cgroup_tcp_skb.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +/* Define states of a socket to tracking messages sending to and from the + * socket. + * + * These states are based on rfc9293 with some modifications to support + * tracking of messages sent out from a socket. For example, when a SYN is + * received, a new socket is transiting to the SYN_RECV state defined in + * rfc9293. But, we put it in SYN_RECV_SENDING_SYN_ACK state and when + * SYN-ACK is sent out, it moves to SYN_RECV state. With this modification, + * we can track the message sent out from a socket. + */ + +#ifndef __CGROUP_TCP_SKB_H__ +#define __CGROUP_TCP_SKB_H__ + +enum { + INIT, + CLOSED, + SYN_SENT, + SYN_RECV_SENDING_SYN_ACK, + SYN_RECV, + ESTABLISHED, + FIN_WAIT1, + FIN_WAIT2, + CLOSE_WAIT_SENDING_ACK, + CLOSE_WAIT, + CLOSING, + LAST_ACK, + TIME_WAIT_SENDING_ACK, + TIME_WAIT, +}; + +#endif /* __CGROUP_TCP_SKB_H__ */ diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index 3b350bc31343..1c7584e8dd9e 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -16,6 +16,7 @@ CONFIG_CRYPTO_USER_API_HASH=y CONFIG_DEBUG_INFO=y CONFIG_DEBUG_INFO_BTF=y CONFIG_DEBUG_INFO_DWARF4=y +CONFIG_DUMMY=y CONFIG_DYNAMIC_FTRACE=y CONFIG_FPROBE=y CONFIG_FTRACE_SYSCALLS=y @@ -59,6 +60,7 @@ CONFIG_NET_IPGRE=y CONFIG_NET_IPGRE_DEMUX=y CONFIG_NET_IPIP=y CONFIG_NET_MPLS_GSO=y +CONFIG_NET_SCH_FQ=y CONFIG_NET_SCH_INGRESS=y CONFIG_NET_SCHED=y CONFIG_NETDEVSIM=y diff --git a/tools/testing/selftests/bpf/generate_udp_fragments.py b/tools/testing/selftests/bpf/generate_udp_fragments.py new file mode 100755 index 000000000000..2b8a1187991c --- /dev/null +++ b/tools/testing/selftests/bpf/generate_udp_fragments.py @@ -0,0 +1,90 @@ +#!/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +""" +This script helps generate fragmented UDP packets. + +While it is technically possible to dynamically generate +fragmented packets in C, it is much harder to read and write +said code. `scapy` is relatively industry standard and really +easy to read / write. + +So we choose to write this script that generates a valid C +header. Rerun script and commit generated file after any +modifications. +""" + +import argparse +import os + +from scapy.all import * + + +# These constants must stay in sync with `ip_check_defrag.c` +VETH1_ADDR = "172.16.1.200" +VETH0_ADDR6 = "fc00::100" +VETH1_ADDR6 = "fc00::200" +CLIENT_PORT = 48878 +SERVER_PORT = 48879 +MAGIC_MESSAGE = "THIS IS THE ORIGINAL MESSAGE, PLEASE REASSEMBLE ME" + + +def print_header(f): + f.write("// SPDX-License-Identifier: GPL-2.0\n") + f.write("/* DO NOT EDIT -- this file is generated */\n") + f.write("\n") + f.write("#ifndef _IP_CHECK_DEFRAG_FRAGS_H\n") + f.write("#define _IP_CHECK_DEFRAG_FRAGS_H\n") + f.write("\n") + f.write("#include <stdint.h>\n") + f.write("\n") + + +def print_frags(f, frags, v6): + for idx, frag in enumerate(frags): + # 10 bytes per line to keep width in check + chunks = [frag[i : i + 10] for i in range(0, len(frag), 10)] + chunks_fmted = [", ".join([str(hex(b)) for b in chunk]) for chunk in chunks] + suffix = "6" if v6 else "" + + f.write(f"static uint8_t frag{suffix}_{idx}[] = {{\n") + for chunk in chunks_fmted: + f.write(f"\t{chunk},\n") + f.write(f"}};\n") + + +def print_trailer(f): + f.write("\n") + f.write("#endif /* _IP_CHECK_DEFRAG_FRAGS_H */\n") + + +def main(f): + # srcip of 0 is filled in by IP_HDRINCL + sip = "0.0.0.0" + sip6 = VETH0_ADDR6 + dip = VETH1_ADDR + dip6 = VETH1_ADDR6 + sport = CLIENT_PORT + dport = SERVER_PORT + payload = MAGIC_MESSAGE.encode() + + # Disable UDPv4 checksums to keep code simpler + pkt = IP(src=sip,dst=dip) / UDP(sport=sport,dport=dport,chksum=0) / Raw(load=payload) + # UDPv6 requires a checksum + # Also pin the ipv6 fragment header ID, otherwise it's a random value + pkt6 = IPv6(src=sip6,dst=dip6) / IPv6ExtHdrFragment(id=0xBEEF) / UDP(sport=sport,dport=dport) / Raw(load=payload) + + frags = [f.build() for f in pkt.fragment(24)] + frags6 = [f.build() for f in fragment6(pkt6, 72)] + + print_header(f) + print_frags(f, frags, False) + print_frags(f, frags6, True) + print_trailer(f) + + +if __name__ == "__main__": + dir = os.path.dirname(os.path.realpath(__file__)) + header = f"{dir}/ip_check_defrag_frags.h" + with open(header, "w") as f: + main(f) diff --git a/tools/testing/selftests/bpf/gnu/stubs.h b/tools/testing/selftests/bpf/gnu/stubs.h index 719225b16626..1c638d9dce1a 100644 --- a/tools/testing/selftests/bpf/gnu/stubs.h +++ b/tools/testing/selftests/bpf/gnu/stubs.h @@ -1 +1 @@ -/* dummy .h to trick /usr/include/features.h to work with 'clang -target bpf' */ +/* dummy .h to trick /usr/include/features.h to work with 'clang --target=bpf' */ diff --git a/tools/testing/selftests/bpf/ip_check_defrag_frags.h b/tools/testing/selftests/bpf/ip_check_defrag_frags.h new file mode 100644 index 000000000000..70ab7e9fa22b --- /dev/null +++ b/tools/testing/selftests/bpf/ip_check_defrag_frags.h @@ -0,0 +1,57 @@ +// SPDX-License-Identifier: GPL-2.0 +/* DO NOT EDIT -- this file is generated */ + +#ifndef _IP_CHECK_DEFRAG_FRAGS_H +#define _IP_CHECK_DEFRAG_FRAGS_H + +#include <stdint.h> + +static uint8_t frag_0[] = { + 0x45, 0x0, 0x0, 0x2c, 0x0, 0x1, 0x20, 0x0, 0x40, 0x11, + 0xac, 0xe8, 0x0, 0x0, 0x0, 0x0, 0xac, 0x10, 0x1, 0xc8, + 0xbe, 0xee, 0xbe, 0xef, 0x0, 0x3a, 0x0, 0x0, 0x54, 0x48, + 0x49, 0x53, 0x20, 0x49, 0x53, 0x20, 0x54, 0x48, 0x45, 0x20, + 0x4f, 0x52, 0x49, 0x47, +}; +static uint8_t frag_1[] = { + 0x45, 0x0, 0x0, 0x2c, 0x0, 0x1, 0x20, 0x3, 0x40, 0x11, + 0xac, 0xe5, 0x0, 0x0, 0x0, 0x0, 0xac, 0x10, 0x1, 0xc8, + 0x49, 0x4e, 0x41, 0x4c, 0x20, 0x4d, 0x45, 0x53, 0x53, 0x41, + 0x47, 0x45, 0x2c, 0x20, 0x50, 0x4c, 0x45, 0x41, 0x53, 0x45, + 0x20, 0x52, 0x45, 0x41, +}; +static uint8_t frag_2[] = { + 0x45, 0x0, 0x0, 0x1e, 0x0, 0x1, 0x0, 0x6, 0x40, 0x11, + 0xcc, 0xf0, 0x0, 0x0, 0x0, 0x0, 0xac, 0x10, 0x1, 0xc8, + 0x53, 0x53, 0x45, 0x4d, 0x42, 0x4c, 0x45, 0x20, 0x4d, 0x45, +}; +static uint8_t frag6_0[] = { + 0x60, 0x0, 0x0, 0x0, 0x0, 0x20, 0x2c, 0x40, 0xfc, 0x0, + 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, + 0x0, 0x0, 0x1, 0x0, 0xfc, 0x0, 0x0, 0x0, 0x0, 0x0, + 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x2, 0x0, + 0x11, 0x0, 0x0, 0x1, 0x0, 0x0, 0xbe, 0xef, 0xbe, 0xee, + 0xbe, 0xef, 0x0, 0x3a, 0xd0, 0xf8, 0x54, 0x48, 0x49, 0x53, + 0x20, 0x49, 0x53, 0x20, 0x54, 0x48, 0x45, 0x20, 0x4f, 0x52, + 0x49, 0x47, +}; +static uint8_t frag6_1[] = { + 0x60, 0x0, 0x0, 0x0, 0x0, 0x20, 0x2c, 0x40, 0xfc, 0x0, + 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, + 0x0, 0x0, 0x1, 0x0, 0xfc, 0x0, 0x0, 0x0, 0x0, 0x0, + 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x2, 0x0, + 0x11, 0x0, 0x0, 0x19, 0x0, 0x0, 0xbe, 0xef, 0x49, 0x4e, + 0x41, 0x4c, 0x20, 0x4d, 0x45, 0x53, 0x53, 0x41, 0x47, 0x45, + 0x2c, 0x20, 0x50, 0x4c, 0x45, 0x41, 0x53, 0x45, 0x20, 0x52, + 0x45, 0x41, +}; +static uint8_t frag6_2[] = { + 0x60, 0x0, 0x0, 0x0, 0x0, 0x12, 0x2c, 0x40, 0xfc, 0x0, + 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, + 0x0, 0x0, 0x1, 0x0, 0xfc, 0x0, 0x0, 0x0, 0x0, 0x0, + 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x2, 0x0, + 0x11, 0x0, 0x0, 0x30, 0x0, 0x0, 0xbe, 0xef, 0x53, 0x53, + 0x45, 0x4d, 0x42, 0x4c, 0x45, 0x20, 0x4d, 0x45, +}; + +#endif /* _IP_CHECK_DEFRAG_FRAGS_H */ diff --git a/tools/testing/selftests/bpf/map_tests/map_percpu_stats.c b/tools/testing/selftests/bpf/map_tests/map_percpu_stats.c new file mode 100644 index 000000000000..1a9eeefda9a8 --- /dev/null +++ b/tools/testing/selftests/bpf/map_tests/map_percpu_stats.c @@ -0,0 +1,447 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Isovalent */ + +#include <errno.h> +#include <unistd.h> +#include <pthread.h> + +#include <bpf/bpf.h> +#include <bpf/libbpf.h> + +#include <bpf_util.h> +#include <test_maps.h> + +#include "map_percpu_stats.skel.h" + +#define MAX_ENTRIES 16384 +#define MAX_ENTRIES_HASH_OF_MAPS 64 +#define N_THREADS 8 +#define MAX_MAP_KEY_SIZE 4 + +static void map_info(int map_fd, struct bpf_map_info *info) +{ + __u32 len = sizeof(*info); + int ret; + + memset(info, 0, sizeof(*info)); + + ret = bpf_obj_get_info_by_fd(map_fd, info, &len); + CHECK(ret < 0, "bpf_obj_get_info_by_fd", "error: %s\n", strerror(errno)); +} + +static const char *map_type_to_s(__u32 type) +{ + switch (type) { + case BPF_MAP_TYPE_HASH: + return "HASH"; + case BPF_MAP_TYPE_PERCPU_HASH: + return "PERCPU_HASH"; + case BPF_MAP_TYPE_LRU_HASH: + return "LRU_HASH"; + case BPF_MAP_TYPE_LRU_PERCPU_HASH: + return "LRU_PERCPU_HASH"; + case BPF_MAP_TYPE_HASH_OF_MAPS: + return "BPF_MAP_TYPE_HASH_OF_MAPS"; + default: + return "<define-me>"; + } +} + +static __u32 map_count_elements(__u32 type, int map_fd) +{ + __u32 key = -1; + int n = 0; + + while (!bpf_map_get_next_key(map_fd, &key, &key)) + n++; + return n; +} + +#define BATCH true + +static void delete_and_lookup_batch(int map_fd, void *keys, __u32 count) +{ + static __u8 values[(8 << 10) * MAX_ENTRIES]; + void *in_batch = NULL, *out_batch; + __u32 save_count = count; + int ret; + + ret = bpf_map_lookup_and_delete_batch(map_fd, + &in_batch, &out_batch, + keys, values, &count, + NULL); + + /* + * Despite what uapi header says, lookup_and_delete_batch will return + * -ENOENT in case we successfully have deleted all elements, so check + * this separately + */ + CHECK(ret < 0 && (errno != ENOENT || !count), "bpf_map_lookup_and_delete_batch", + "error: %s\n", strerror(errno)); + + CHECK(count != save_count, + "bpf_map_lookup_and_delete_batch", + "deleted not all elements: removed=%u expected=%u\n", + count, save_count); +} + +static void delete_all_elements(__u32 type, int map_fd, bool batch) +{ + static __u8 val[8 << 10]; /* enough for 1024 CPUs */ + __u32 key = -1; + void *keys; + __u32 i, n; + int ret; + + keys = calloc(MAX_MAP_KEY_SIZE, MAX_ENTRIES); + CHECK(!keys, "calloc", "error: %s\n", strerror(errno)); + + for (n = 0; !bpf_map_get_next_key(map_fd, &key, &key); n++) + memcpy(keys + n*MAX_MAP_KEY_SIZE, &key, MAX_MAP_KEY_SIZE); + + if (batch) { + /* Can't mix delete_batch and delete_and_lookup_batch because + * they have different semantics in relation to the keys + * argument. However, delete_batch utilize map_delete_elem, + * so we actually test it in non-batch scenario */ + delete_and_lookup_batch(map_fd, keys, n); + } else { + /* Intentionally mix delete and lookup_and_delete so we can test both */ + for (i = 0; i < n; i++) { + void *keyp = keys + i*MAX_MAP_KEY_SIZE; + + if (i % 2 || type == BPF_MAP_TYPE_HASH_OF_MAPS) { + ret = bpf_map_delete_elem(map_fd, keyp); + CHECK(ret < 0, "bpf_map_delete_elem", + "error: key %u: %s\n", i, strerror(errno)); + } else { + ret = bpf_map_lookup_and_delete_elem(map_fd, keyp, val); + CHECK(ret < 0, "bpf_map_lookup_and_delete_elem", + "error: key %u: %s\n", i, strerror(errno)); + } + } + } + + free(keys); +} + +static bool is_lru(__u32 map_type) +{ + return map_type == BPF_MAP_TYPE_LRU_HASH || + map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH; +} + +struct upsert_opts { + __u32 map_type; + int map_fd; + __u32 n; +}; + +static int create_small_hash(void) +{ + int map_fd; + + map_fd = bpf_map_create(BPF_MAP_TYPE_HASH, "small", 4, 4, 4, NULL); + CHECK(map_fd < 0, "bpf_map_create()", "error:%s (name=%s)\n", + strerror(errno), "small"); + + return map_fd; +} + +static void *patch_map_thread(void *arg) +{ + struct upsert_opts *opts = arg; + int val; + int ret; + int i; + + for (i = 0; i < opts->n; i++) { + if (opts->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) + val = create_small_hash(); + else + val = rand(); + ret = bpf_map_update_elem(opts->map_fd, &i, &val, 0); + CHECK(ret < 0, "bpf_map_update_elem", "key=%d error: %s\n", i, strerror(errno)); + + if (opts->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) + close(val); + } + return NULL; +} + +static void upsert_elements(struct upsert_opts *opts) +{ + pthread_t threads[N_THREADS]; + int ret; + int i; + + for (i = 0; i < ARRAY_SIZE(threads); i++) { + ret = pthread_create(&i[threads], NULL, patch_map_thread, opts); + CHECK(ret != 0, "pthread_create", "error: %s\n", strerror(ret)); + } + + for (i = 0; i < ARRAY_SIZE(threads); i++) { + ret = pthread_join(i[threads], NULL); + CHECK(ret != 0, "pthread_join", "error: %s\n", strerror(ret)); + } +} + +static __u32 read_cur_elements(int iter_fd) +{ + char buf[64]; + ssize_t n; + __u32 ret; + + n = read(iter_fd, buf, sizeof(buf)-1); + CHECK(n <= 0, "read", "error: %s\n", strerror(errno)); + buf[n] = '\0'; + + errno = 0; + ret = (__u32)strtol(buf, NULL, 10); + CHECK(errno != 0, "strtol", "error: %s\n", strerror(errno)); + + return ret; +} + +static __u32 get_cur_elements(int map_id) +{ + struct map_percpu_stats *skel; + struct bpf_link *link; + __u32 n_elements; + int iter_fd; + int ret; + + skel = map_percpu_stats__open(); + CHECK(skel == NULL, "map_percpu_stats__open", "error: %s", strerror(errno)); + + skel->bss->target_id = map_id; + + ret = map_percpu_stats__load(skel); + CHECK(ret != 0, "map_percpu_stats__load", "error: %s", strerror(errno)); + + link = bpf_program__attach_iter(skel->progs.dump_bpf_map, NULL); + CHECK(!link, "bpf_program__attach_iter", "error: %s\n", strerror(errno)); + + iter_fd = bpf_iter_create(bpf_link__fd(link)); + CHECK(iter_fd < 0, "bpf_iter_create", "error: %s\n", strerror(errno)); + + n_elements = read_cur_elements(iter_fd); + + close(iter_fd); + bpf_link__destroy(link); + map_percpu_stats__destroy(skel); + + return n_elements; +} + +static void check_expected_number_elements(__u32 n_inserted, int map_fd, + struct bpf_map_info *info) +{ + __u32 n_real; + __u32 n_iter; + + /* Count the current number of elements in the map by iterating through + * all the map keys via bpf_get_next_key + */ + n_real = map_count_elements(info->type, map_fd); + + /* The "real" number of elements should be the same as the inserted + * number of elements in all cases except LRU maps, where some elements + * may have been evicted + */ + if (n_inserted == 0 || !is_lru(info->type)) + CHECK(n_inserted != n_real, "map_count_elements", + "n_real(%u) != n_inserted(%u)\n", n_real, n_inserted); + + /* Count the current number of elements in the map using an iterator */ + n_iter = get_cur_elements(info->id); + + /* Both counts should be the same, as all updates are over */ + CHECK(n_iter != n_real, "get_cur_elements", + "n_iter=%u, expected %u (map_type=%s,map_flags=%08x)\n", + n_iter, n_real, map_type_to_s(info->type), info->map_flags); +} + +static void __test(int map_fd) +{ + struct upsert_opts opts = { + .map_fd = map_fd, + }; + struct bpf_map_info info; + + map_info(map_fd, &info); + opts.map_type = info.type; + opts.n = info.max_entries; + + /* Reduce the number of elements we are updating such that we don't + * bump into -E2BIG from non-preallocated hash maps, but still will + * have some evictions for LRU maps */ + if (opts.map_type != BPF_MAP_TYPE_HASH_OF_MAPS) + opts.n -= 512; + else + opts.n /= 2; + + /* + * Upsert keys [0, n) under some competition: with random values from + * N_THREADS threads. Check values, then delete all elements and check + * values again. + */ + upsert_elements(&opts); + check_expected_number_elements(opts.n, map_fd, &info); + delete_all_elements(info.type, map_fd, !BATCH); + check_expected_number_elements(0, map_fd, &info); + + /* Now do the same, but using batch delete operations */ + upsert_elements(&opts); + check_expected_number_elements(opts.n, map_fd, &info); + delete_all_elements(info.type, map_fd, BATCH); + check_expected_number_elements(0, map_fd, &info); + + close(map_fd); +} + +static int map_create_opts(__u32 type, const char *name, + struct bpf_map_create_opts *map_opts, + __u32 key_size, __u32 val_size) +{ + int max_entries; + int map_fd; + + if (type == BPF_MAP_TYPE_HASH_OF_MAPS) + max_entries = MAX_ENTRIES_HASH_OF_MAPS; + else + max_entries = MAX_ENTRIES; + + map_fd = bpf_map_create(type, name, key_size, val_size, max_entries, map_opts); + CHECK(map_fd < 0, "bpf_map_create()", "error:%s (name=%s)\n", + strerror(errno), name); + + return map_fd; +} + +static int map_create(__u32 type, const char *name, struct bpf_map_create_opts *map_opts) +{ + return map_create_opts(type, name, map_opts, sizeof(int), sizeof(int)); +} + +static int create_hash(void) +{ + struct bpf_map_create_opts map_opts = { + .sz = sizeof(map_opts), + .map_flags = BPF_F_NO_PREALLOC, + }; + + return map_create(BPF_MAP_TYPE_HASH, "hash", &map_opts); +} + +static int create_percpu_hash(void) +{ + struct bpf_map_create_opts map_opts = { + .sz = sizeof(map_opts), + .map_flags = BPF_F_NO_PREALLOC, + }; + + return map_create(BPF_MAP_TYPE_PERCPU_HASH, "percpu_hash", &map_opts); +} + +static int create_hash_prealloc(void) +{ + return map_create(BPF_MAP_TYPE_HASH, "hash", NULL); +} + +static int create_percpu_hash_prealloc(void) +{ + return map_create(BPF_MAP_TYPE_PERCPU_HASH, "percpu_hash_prealloc", NULL); +} + +static int create_lru_hash(__u32 type, __u32 map_flags) +{ + struct bpf_map_create_opts map_opts = { + .sz = sizeof(map_opts), + .map_flags = map_flags, + }; + + return map_create(type, "lru_hash", &map_opts); +} + +static int create_hash_of_maps(void) +{ + struct bpf_map_create_opts map_opts = { + .sz = sizeof(map_opts), + .map_flags = BPF_F_NO_PREALLOC, + .inner_map_fd = create_small_hash(), + }; + int ret; + + ret = map_create_opts(BPF_MAP_TYPE_HASH_OF_MAPS, "hash_of_maps", + &map_opts, sizeof(int), sizeof(int)); + close(map_opts.inner_map_fd); + return ret; +} + +static void map_percpu_stats_hash(void) +{ + __test(create_hash()); + printf("test_%s:PASS\n", __func__); +} + +static void map_percpu_stats_percpu_hash(void) +{ + __test(create_percpu_hash()); + printf("test_%s:PASS\n", __func__); +} + +static void map_percpu_stats_hash_prealloc(void) +{ + __test(create_hash_prealloc()); + printf("test_%s:PASS\n", __func__); +} + +static void map_percpu_stats_percpu_hash_prealloc(void) +{ + __test(create_percpu_hash_prealloc()); + printf("test_%s:PASS\n", __func__); +} + +static void map_percpu_stats_lru_hash(void) +{ + __test(create_lru_hash(BPF_MAP_TYPE_LRU_HASH, 0)); + printf("test_%s:PASS\n", __func__); +} + +static void map_percpu_stats_lru_hash_no_common(void) +{ + __test(create_lru_hash(BPF_MAP_TYPE_LRU_HASH, BPF_F_NO_COMMON_LRU)); + printf("test_%s:PASS\n", __func__); +} + +static void map_percpu_stats_percpu_lru_hash(void) +{ + __test(create_lru_hash(BPF_MAP_TYPE_LRU_PERCPU_HASH, 0)); + printf("test_%s:PASS\n", __func__); +} + +static void map_percpu_stats_percpu_lru_hash_no_common(void) +{ + __test(create_lru_hash(BPF_MAP_TYPE_LRU_PERCPU_HASH, BPF_F_NO_COMMON_LRU)); + printf("test_%s:PASS\n", __func__); +} + +static void map_percpu_stats_hash_of_maps(void) +{ + __test(create_hash_of_maps()); + printf("test_%s:PASS\n", __func__); +} + +void test_map_percpu_stats(void) +{ + map_percpu_stats_hash(); + map_percpu_stats_percpu_hash(); + map_percpu_stats_hash_prealloc(); + map_percpu_stats_percpu_hash_prealloc(); + map_percpu_stats_lru_hash(); + map_percpu_stats_lru_hash_no_common(); + map_percpu_stats_percpu_lru_hash(); + map_percpu_stats_percpu_lru_hash_no_common(); + map_percpu_stats_hash_of_maps(); +} diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c index a105c0cd008a..da72a3a66230 100644 --- a/tools/testing/selftests/bpf/network_helpers.c +++ b/tools/testing/selftests/bpf/network_helpers.c @@ -270,14 +270,23 @@ int connect_to_fd_opts(int server_fd, const struct network_helper_opts *opts) opts = &default_opts; optlen = sizeof(type); - if (getsockopt(server_fd, SOL_SOCKET, SO_TYPE, &type, &optlen)) { - log_err("getsockopt(SOL_TYPE)"); - return -1; + + if (opts->type) { + type = opts->type; + } else { + if (getsockopt(server_fd, SOL_SOCKET, SO_TYPE, &type, &optlen)) { + log_err("getsockopt(SOL_TYPE)"); + return -1; + } } - if (getsockopt(server_fd, SOL_SOCKET, SO_PROTOCOL, &protocol, &optlen)) { - log_err("getsockopt(SOL_PROTOCOL)"); - return -1; + if (opts->proto) { + protocol = opts->proto; + } else { + if (getsockopt(server_fd, SOL_SOCKET, SO_PROTOCOL, &protocol, &optlen)) { + log_err("getsockopt(SOL_PROTOCOL)"); + return -1; + } } addrlen = sizeof(addr); @@ -301,8 +310,9 @@ int connect_to_fd_opts(int server_fd, const struct network_helper_opts *opts) strlen(opts->cc) + 1)) goto error_close; - if (connect_fd_to_addr(fd, &addr, addrlen, opts->must_fail)) - goto error_close; + if (!opts->noconnect) + if (connect_fd_to_addr(fd, &addr, addrlen, opts->must_fail)) + goto error_close; return fd; @@ -423,6 +433,9 @@ fail: void close_netns(struct nstoken *token) { + if (!token) + return; + ASSERT_OK(setns(token->orig_netns_fd, CLONE_NEWNET), "setns"); close(token->orig_netns_fd); free(token); diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h index 694185644da6..5eccc67d1a99 100644 --- a/tools/testing/selftests/bpf/network_helpers.h +++ b/tools/testing/selftests/bpf/network_helpers.h @@ -21,6 +21,9 @@ struct network_helper_opts { const char *cc; int timeout_ms; bool must_fail; + bool noconnect; + int type; + int proto; }; /* ipv4 test vector */ diff --git a/tools/testing/selftests/bpf/prog_tests/assign_reuse.c b/tools/testing/selftests/bpf/prog_tests/assign_reuse.c new file mode 100644 index 000000000000..989ee4d9785b --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/assign_reuse.c @@ -0,0 +1,199 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Isovalent */ +#include <uapi/linux/if_link.h> +#include <test_progs.h> + +#include <netinet/tcp.h> +#include <netinet/udp.h> + +#include "network_helpers.h" +#include "test_assign_reuse.skel.h" + +#define NS_TEST "assign_reuse" +#define LOOPBACK 1 +#define PORT 4443 + +static int attach_reuseport(int sock_fd, int prog_fd) +{ + return setsockopt(sock_fd, SOL_SOCKET, SO_ATTACH_REUSEPORT_EBPF, + &prog_fd, sizeof(prog_fd)); +} + +static __u64 cookie(int fd) +{ + __u64 cookie = 0; + socklen_t cookie_len = sizeof(cookie); + int ret; + + ret = getsockopt(fd, SOL_SOCKET, SO_COOKIE, &cookie, &cookie_len); + ASSERT_OK(ret, "cookie"); + ASSERT_GT(cookie, 0, "cookie_invalid"); + + return cookie; +} + +static int echo_test_udp(int fd_sv) +{ + struct sockaddr_storage addr = {}; + socklen_t len = sizeof(addr); + char buff[1] = {}; + int fd_cl = -1, ret; + + fd_cl = connect_to_fd(fd_sv, 100); + ASSERT_GT(fd_cl, 0, "create_client"); + ASSERT_EQ(getsockname(fd_cl, (void *)&addr, &len), 0, "getsockname"); + + ASSERT_EQ(send(fd_cl, buff, sizeof(buff), 0), 1, "send_client"); + + ret = recv(fd_sv, buff, sizeof(buff), 0); + if (ret < 0) { + close(fd_cl); + return errno; + } + + ASSERT_EQ(ret, 1, "recv_server"); + ASSERT_EQ(sendto(fd_sv, buff, sizeof(buff), 0, (void *)&addr, len), 1, "send_server"); + ASSERT_EQ(recv(fd_cl, buff, sizeof(buff), 0), 1, "recv_client"); + close(fd_cl); + return 0; +} + +static int echo_test_tcp(int fd_sv) +{ + char buff[1] = {}; + int fd_cl = -1, fd_sv_cl = -1; + + fd_cl = connect_to_fd(fd_sv, 100); + if (fd_cl < 0) + return errno; + + fd_sv_cl = accept(fd_sv, NULL, NULL); + ASSERT_GE(fd_sv_cl, 0, "accept_fd"); + + ASSERT_EQ(send(fd_cl, buff, sizeof(buff), 0), 1, "send_client"); + ASSERT_EQ(recv(fd_sv_cl, buff, sizeof(buff), 0), 1, "recv_server"); + ASSERT_EQ(send(fd_sv_cl, buff, sizeof(buff), 0), 1, "send_server"); + ASSERT_EQ(recv(fd_cl, buff, sizeof(buff), 0), 1, "recv_client"); + close(fd_sv_cl); + close(fd_cl); + return 0; +} + +void run_assign_reuse(int family, int sotype, const char *ip, __u16 port) +{ + DECLARE_LIBBPF_OPTS(bpf_tc_hook, tc_hook, + .ifindex = LOOPBACK, + .attach_point = BPF_TC_INGRESS, + ); + DECLARE_LIBBPF_OPTS(bpf_tc_opts, tc_opts, + .handle = 1, + .priority = 1, + ); + bool hook_created = false, tc_attached = false; + int ret, fd_tc, fd_accept, fd_drop, fd_map; + int *fd_sv = NULL; + __u64 fd_val; + struct test_assign_reuse *skel; + const int zero = 0; + + skel = test_assign_reuse__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + goto cleanup; + + skel->rodata->dest_port = port; + + ret = test_assign_reuse__load(skel); + if (!ASSERT_OK(ret, "skel_load")) + goto cleanup; + + ASSERT_EQ(skel->bss->sk_cookie_seen, 0, "cookie_init"); + + fd_tc = bpf_program__fd(skel->progs.tc_main); + fd_accept = bpf_program__fd(skel->progs.reuse_accept); + fd_drop = bpf_program__fd(skel->progs.reuse_drop); + fd_map = bpf_map__fd(skel->maps.sk_map); + + fd_sv = start_reuseport_server(family, sotype, ip, port, 100, 1); + if (!ASSERT_NEQ(fd_sv, NULL, "start_reuseport_server")) + goto cleanup; + + ret = attach_reuseport(*fd_sv, fd_drop); + if (!ASSERT_OK(ret, "attach_reuseport")) + goto cleanup; + + fd_val = *fd_sv; + ret = bpf_map_update_elem(fd_map, &zero, &fd_val, BPF_NOEXIST); + if (!ASSERT_OK(ret, "bpf_sk_map")) + goto cleanup; + + ret = bpf_tc_hook_create(&tc_hook); + if (ret == 0) + hook_created = true; + ret = ret == -EEXIST ? 0 : ret; + if (!ASSERT_OK(ret, "bpf_tc_hook_create")) + goto cleanup; + + tc_opts.prog_fd = fd_tc; + ret = bpf_tc_attach(&tc_hook, &tc_opts); + if (!ASSERT_OK(ret, "bpf_tc_attach")) + goto cleanup; + tc_attached = true; + + if (sotype == SOCK_STREAM) + ASSERT_EQ(echo_test_tcp(*fd_sv), ECONNREFUSED, "drop_tcp"); + else + ASSERT_EQ(echo_test_udp(*fd_sv), EAGAIN, "drop_udp"); + ASSERT_EQ(skel->bss->reuseport_executed, 1, "program executed once"); + + skel->bss->sk_cookie_seen = 0; + skel->bss->reuseport_executed = 0; + ASSERT_OK(attach_reuseport(*fd_sv, fd_accept), "attach_reuseport(accept)"); + + if (sotype == SOCK_STREAM) + ASSERT_EQ(echo_test_tcp(*fd_sv), 0, "echo_tcp"); + else + ASSERT_EQ(echo_test_udp(*fd_sv), 0, "echo_udp"); + + ASSERT_EQ(skel->bss->sk_cookie_seen, cookie(*fd_sv), + "cookie_mismatch"); + ASSERT_EQ(skel->bss->reuseport_executed, 1, "program executed once"); +cleanup: + if (tc_attached) { + tc_opts.flags = tc_opts.prog_fd = tc_opts.prog_id = 0; + ret = bpf_tc_detach(&tc_hook, &tc_opts); + ASSERT_OK(ret, "bpf_tc_detach"); + } + if (hook_created) { + tc_hook.attach_point = BPF_TC_INGRESS | BPF_TC_EGRESS; + bpf_tc_hook_destroy(&tc_hook); + } + test_assign_reuse__destroy(skel); + free_fds(fd_sv, 1); +} + +void test_assign_reuse(void) +{ + struct nstoken *tok = NULL; + + SYS(out, "ip netns add %s", NS_TEST); + SYS(cleanup, "ip -net %s link set dev lo up", NS_TEST); + + tok = open_netns(NS_TEST); + if (!ASSERT_OK_PTR(tok, "netns token")) + return; + + if (test__start_subtest("tcpv4")) + run_assign_reuse(AF_INET, SOCK_STREAM, "127.0.0.1", PORT); + if (test__start_subtest("tcpv6")) + run_assign_reuse(AF_INET6, SOCK_STREAM, "::1", PORT); + if (test__start_subtest("udpv4")) + run_assign_reuse(AF_INET, SOCK_DGRAM, "127.0.0.1", PORT); + if (test__start_subtest("udpv6")) + run_assign_reuse(AF_INET6, SOCK_DGRAM, "::1", PORT); + +cleanup: + close_netns(tok); + SYS_NOFAIL("ip netns delete %s", NS_TEST); +out: + return; +} diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c index 26b2d1bffdfd..1454cebc262b 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c @@ -11,6 +11,7 @@ #include <bpf/btf.h> #include "test_bpf_cookie.skel.h" #include "kprobe_multi.skel.h" +#include "uprobe_multi.skel.h" /* uprobe attach point */ static noinline void trigger_func(void) @@ -239,6 +240,81 @@ cleanup: bpf_link__destroy(link1); kprobe_multi__destroy(skel); } + +/* defined in prog_tests/uprobe_multi_test.c */ +void uprobe_multi_func_1(void); +void uprobe_multi_func_2(void); +void uprobe_multi_func_3(void); + +static void uprobe_multi_test_run(struct uprobe_multi *skel) +{ + skel->bss->uprobe_multi_func_1_addr = (__u64) uprobe_multi_func_1; + skel->bss->uprobe_multi_func_2_addr = (__u64) uprobe_multi_func_2; + skel->bss->uprobe_multi_func_3_addr = (__u64) uprobe_multi_func_3; + + skel->bss->pid = getpid(); + skel->bss->test_cookie = true; + + uprobe_multi_func_1(); + uprobe_multi_func_2(); + uprobe_multi_func_3(); + + ASSERT_EQ(skel->bss->uprobe_multi_func_1_result, 1, "uprobe_multi_func_1_result"); + ASSERT_EQ(skel->bss->uprobe_multi_func_2_result, 1, "uprobe_multi_func_2_result"); + ASSERT_EQ(skel->bss->uprobe_multi_func_3_result, 1, "uprobe_multi_func_3_result"); + + ASSERT_EQ(skel->bss->uretprobe_multi_func_1_result, 1, "uretprobe_multi_func_1_result"); + ASSERT_EQ(skel->bss->uretprobe_multi_func_2_result, 1, "uretprobe_multi_func_2_result"); + ASSERT_EQ(skel->bss->uretprobe_multi_func_3_result, 1, "uretprobe_multi_func_3_result"); +} + +static void uprobe_multi_attach_api_subtest(void) +{ + struct bpf_link *link1 = NULL, *link2 = NULL; + struct uprobe_multi *skel = NULL; + LIBBPF_OPTS(bpf_uprobe_multi_opts, opts); + const char *syms[3] = { + "uprobe_multi_func_1", + "uprobe_multi_func_2", + "uprobe_multi_func_3", + }; + __u64 cookies[3]; + + cookies[0] = 3; /* uprobe_multi_func_1 */ + cookies[1] = 1; /* uprobe_multi_func_2 */ + cookies[2] = 2; /* uprobe_multi_func_3 */ + + opts.syms = syms; + opts.cnt = ARRAY_SIZE(syms); + opts.cookies = &cookies[0]; + + skel = uprobe_multi__open_and_load(); + if (!ASSERT_OK_PTR(skel, "uprobe_multi")) + goto cleanup; + + link1 = bpf_program__attach_uprobe_multi(skel->progs.uprobe, -1, + "/proc/self/exe", NULL, &opts); + if (!ASSERT_OK_PTR(link1, "bpf_program__attach_uprobe_multi")) + goto cleanup; + + cookies[0] = 2; /* uprobe_multi_func_1 */ + cookies[1] = 3; /* uprobe_multi_func_2 */ + cookies[2] = 1; /* uprobe_multi_func_3 */ + + opts.retprobe = true; + link2 = bpf_program__attach_uprobe_multi(skel->progs.uretprobe, -1, + "/proc/self/exe", NULL, &opts); + if (!ASSERT_OK_PTR(link2, "bpf_program__attach_uprobe_multi_retprobe")) + goto cleanup; + + uprobe_multi_test_run(skel); + +cleanup: + bpf_link__destroy(link2); + bpf_link__destroy(link1); + uprobe_multi__destroy(skel); +} + static void uprobe_subtest(struct test_bpf_cookie *skel) { DECLARE_LIBBPF_OPTS(bpf_uprobe_opts, opts); @@ -515,6 +591,8 @@ void test_bpf_cookie(void) kprobe_multi_attach_api_subtest(); if (test__start_subtest("uprobe")) uprobe_subtest(skel); + if (test__start_subtest("multi_uprobe_attach_api")) + uprobe_multi_attach_api_subtest(); if (test__start_subtest("tracepoint")) tp_subtest(skel); if (test__start_subtest("perf_event")) diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_nf.c b/tools/testing/selftests/bpf/prog_tests/bpf_nf.c index c8ba4009e4ab..b30ff6b3b81a 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_nf.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_nf.c @@ -123,12 +123,13 @@ static void test_bpf_nf_ct(int mode) ASSERT_EQ(skel->data->test_snat_addr, 0, "Test for source natting"); ASSERT_EQ(skel->data->test_dnat_addr, 0, "Test for destination natting"); end: - if (srv_client_fd != -1) - close(srv_client_fd); if (client_fd != -1) close(client_fd); + if (srv_client_fd != -1) + close(srv_client_fd); if (srv_fd != -1) close(srv_fd); + snprintf(cmd, sizeof(cmd), iptables, "-D"); system(cmd); test_bpf_nf__destroy(skel); diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_obj_pinning.c b/tools/testing/selftests/bpf/prog_tests/bpf_obj_pinning.c index 31f1e815f671..ee0458a5ce78 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_obj_pinning.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_obj_pinning.c @@ -8,6 +8,7 @@ #include <linux/unistd.h> #include <linux/mount.h> #include <sys/syscall.h> +#include "bpf/libbpf_internal.h" static inline int sys_fsopen(const char *fsname, unsigned flags) { @@ -155,7 +156,7 @@ static void validate_pin(int map_fd, const char *map_name, int src_value, ASSERT_OK(err, "obj_pin"); /* cleanup */ - if (pin_opts.path_fd >= 0) + if (path_kind == PATH_FD_REL && pin_opts.path_fd >= 0) close(pin_opts.path_fd); if (old_cwd[0]) ASSERT_OK(chdir(old_cwd), "restore_cwd"); @@ -220,7 +221,7 @@ static void validate_get(int map_fd, const char *map_name, int src_value, goto cleanup; /* cleanup */ - if (get_opts.path_fd >= 0) + if (path_kind == PATH_FD_REL && get_opts.path_fd >= 0) close(get_opts.path_fd); if (old_cwd[0]) ASSERT_OK(chdir(old_cwd), "restore_cwd"); diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_tcp_skb.c b/tools/testing/selftests/bpf/prog_tests/cgroup_tcp_skb.c new file mode 100644 index 000000000000..a1542faf7873 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_tcp_skb.c @@ -0,0 +1,344 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Facebook */ +#include <test_progs.h> +#include <linux/in6.h> +#include <sys/socket.h> +#include <sched.h> +#include <unistd.h> +#include "cgroup_helpers.h" +#include "testing_helpers.h" +#include "cgroup_tcp_skb.skel.h" +#include "cgroup_tcp_skb.h" +#include "network_helpers.h" + +#define CGROUP_TCP_SKB_PATH "/test_cgroup_tcp_skb" + +static int install_filters(int cgroup_fd, + struct bpf_link **egress_link, + struct bpf_link **ingress_link, + struct bpf_program *egress_prog, + struct bpf_program *ingress_prog, + struct cgroup_tcp_skb *skel) +{ + /* Prepare filters */ + skel->bss->g_sock_state = 0; + skel->bss->g_unexpected = 0; + *egress_link = + bpf_program__attach_cgroup(egress_prog, + cgroup_fd); + if (!ASSERT_OK_PTR(egress_link, "egress_link")) + return -1; + *ingress_link = + bpf_program__attach_cgroup(ingress_prog, + cgroup_fd); + if (!ASSERT_OK_PTR(ingress_link, "ingress_link")) + return -1; + + return 0; +} + +static void uninstall_filters(struct bpf_link **egress_link, + struct bpf_link **ingress_link) +{ + bpf_link__destroy(*egress_link); + *egress_link = NULL; + bpf_link__destroy(*ingress_link); + *ingress_link = NULL; +} + +static int create_client_sock_v6(void) +{ + int fd; + + fd = socket(AF_INET6, SOCK_STREAM, 0); + if (fd < 0) { + perror("socket"); + return -1; + } + + return fd; +} + +/* Connect to the server in a cgroup from the outside of the cgroup. */ +static int talk_to_cgroup(int *client_fd, int *listen_fd, int *service_fd, + struct cgroup_tcp_skb *skel) +{ + int err, cp; + char buf[5]; + int port; + + /* Create client & server socket */ + err = join_root_cgroup(); + if (!ASSERT_OK(err, "join_root_cgroup")) + return -1; + *client_fd = create_client_sock_v6(); + if (!ASSERT_GE(*client_fd, 0, "client_fd")) + return -1; + err = join_cgroup(CGROUP_TCP_SKB_PATH); + if (!ASSERT_OK(err, "join_cgroup")) + return -1; + *listen_fd = start_server(AF_INET6, SOCK_STREAM, NULL, 0, 0); + if (!ASSERT_GE(*listen_fd, 0, "listen_fd")) + return -1; + port = get_socket_local_port(*listen_fd); + if (!ASSERT_GE(port, 0, "get_socket_local_port")) + return -1; + skel->bss->g_sock_port = ntohs(port); + + /* Connect client to server */ + err = connect_fd_to_fd(*client_fd, *listen_fd, 0); + if (!ASSERT_OK(err, "connect_fd_to_fd")) + return -1; + *service_fd = accept(*listen_fd, NULL, NULL); + if (!ASSERT_GE(*service_fd, 0, "service_fd")) + return -1; + err = join_root_cgroup(); + if (!ASSERT_OK(err, "join_root_cgroup")) + return -1; + cp = write(*client_fd, "hello", 5); + if (!ASSERT_EQ(cp, 5, "write")) + return -1; + cp = read(*service_fd, buf, 5); + if (!ASSERT_EQ(cp, 5, "read")) + return -1; + + return 0; +} + +/* Connect to the server out of a cgroup from inside the cgroup. */ +static int talk_to_outside(int *client_fd, int *listen_fd, int *service_fd, + struct cgroup_tcp_skb *skel) + +{ + int err, cp; + char buf[5]; + int port; + + /* Create client & server socket */ + err = join_root_cgroup(); + if (!ASSERT_OK(err, "join_root_cgroup")) + return -1; + *listen_fd = start_server(AF_INET6, SOCK_STREAM, NULL, 0, 0); + if (!ASSERT_GE(*listen_fd, 0, "listen_fd")) + return -1; + err = join_cgroup(CGROUP_TCP_SKB_PATH); + if (!ASSERT_OK(err, "join_cgroup")) + return -1; + *client_fd = create_client_sock_v6(); + if (!ASSERT_GE(*client_fd, 0, "client_fd")) + return -1; + err = join_root_cgroup(); + if (!ASSERT_OK(err, "join_root_cgroup")) + return -1; + port = get_socket_local_port(*listen_fd); + if (!ASSERT_GE(port, 0, "get_socket_local_port")) + return -1; + skel->bss->g_sock_port = ntohs(port); + + /* Connect client to server */ + err = connect_fd_to_fd(*client_fd, *listen_fd, 0); + if (!ASSERT_OK(err, "connect_fd_to_fd")) + return -1; + *service_fd = accept(*listen_fd, NULL, NULL); + if (!ASSERT_GE(*service_fd, 0, "service_fd")) + return -1; + cp = write(*client_fd, "hello", 5); + if (!ASSERT_EQ(cp, 5, "write")) + return -1; + cp = read(*service_fd, buf, 5); + if (!ASSERT_EQ(cp, 5, "read")) + return -1; + + return 0; +} + +static int close_connection(int *closing_fd, int *peer_fd, int *listen_fd, + struct cgroup_tcp_skb *skel) +{ + __u32 saved_packet_count = 0; + int err; + int i; + + /* Wait for ACKs to be sent */ + saved_packet_count = skel->bss->g_packet_count; + usleep(100000); /* 0.1s */ + for (i = 0; + skel->bss->g_packet_count != saved_packet_count && i < 10; + i++) { + saved_packet_count = skel->bss->g_packet_count; + usleep(100000); /* 0.1s */ + } + if (!ASSERT_EQ(skel->bss->g_packet_count, saved_packet_count, + "packet_count")) + return -1; + + skel->bss->g_packet_count = 0; + saved_packet_count = 0; + + /* Half shutdown to make sure the closing socket having a chance to + * receive a FIN from the peer. + */ + err = shutdown(*closing_fd, SHUT_WR); + if (!ASSERT_OK(err, "shutdown closing_fd")) + return -1; + + /* Wait for FIN and the ACK of the FIN to be observed */ + for (i = 0; + skel->bss->g_packet_count < saved_packet_count + 2 && i < 10; + i++) + usleep(100000); /* 0.1s */ + if (!ASSERT_GE(skel->bss->g_packet_count, saved_packet_count + 2, + "packet_count")) + return -1; + + saved_packet_count = skel->bss->g_packet_count; + + /* Fully shutdown the connection */ + err = close(*peer_fd); + if (!ASSERT_OK(err, "close peer_fd")) + return -1; + *peer_fd = -1; + + /* Wait for FIN and the ACK of the FIN to be observed */ + for (i = 0; + skel->bss->g_packet_count < saved_packet_count + 2 && i < 10; + i++) + usleep(100000); /* 0.1s */ + if (!ASSERT_GE(skel->bss->g_packet_count, saved_packet_count + 2, + "packet_count")) + return -1; + + err = close(*closing_fd); + if (!ASSERT_OK(err, "close closing_fd")) + return -1; + *closing_fd = -1; + + close(*listen_fd); + *listen_fd = -1; + + return 0; +} + +/* This test case includes four scenarios: + * 1. Connect to the server from outside the cgroup and close the connection + * from outside the cgroup. + * 2. Connect to the server from outside the cgroup and close the connection + * from inside the cgroup. + * 3. Connect to the server from inside the cgroup and close the connection + * from outside the cgroup. + * 4. Connect to the server from inside the cgroup and close the connection + * from inside the cgroup. + * + * The test case is to verify that cgroup_skb/{egress,ingress} filters + * receive expected packets including SYN, SYN/ACK, ACK, FIN, and FIN/ACK. + */ +void test_cgroup_tcp_skb(void) +{ + struct bpf_link *ingress_link = NULL; + struct bpf_link *egress_link = NULL; + int client_fd = -1, listen_fd = -1; + struct cgroup_tcp_skb *skel; + int service_fd = -1; + int cgroup_fd = -1; + int err; + + skel = cgroup_tcp_skb__open_and_load(); + if (!ASSERT_OK(!skel, "skel_open_load")) + return; + + err = setup_cgroup_environment(); + if (!ASSERT_OK(err, "setup_cgroup_environment")) + goto cleanup; + + cgroup_fd = create_and_get_cgroup(CGROUP_TCP_SKB_PATH); + if (!ASSERT_GE(cgroup_fd, 0, "cgroup_fd")) + goto cleanup; + + /* Scenario 1 */ + err = install_filters(cgroup_fd, &egress_link, &ingress_link, + skel->progs.server_egress, + skel->progs.server_ingress, + skel); + if (!ASSERT_OK(err, "install_filters")) + goto cleanup; + + err = talk_to_cgroup(&client_fd, &listen_fd, &service_fd, skel); + if (!ASSERT_OK(err, "talk_to_cgroup")) + goto cleanup; + + err = close_connection(&client_fd, &service_fd, &listen_fd, skel); + if (!ASSERT_OK(err, "close_connection")) + goto cleanup; + + ASSERT_EQ(skel->bss->g_unexpected, 0, "g_unexpected"); + ASSERT_EQ(skel->bss->g_sock_state, CLOSED, "g_sock_state"); + + uninstall_filters(&egress_link, &ingress_link); + + /* Scenario 2 */ + err = install_filters(cgroup_fd, &egress_link, &ingress_link, + skel->progs.server_egress_srv, + skel->progs.server_ingress_srv, + skel); + + err = talk_to_cgroup(&client_fd, &listen_fd, &service_fd, skel); + if (!ASSERT_OK(err, "talk_to_cgroup")) + goto cleanup; + + err = close_connection(&service_fd, &client_fd, &listen_fd, skel); + if (!ASSERT_OK(err, "close_connection")) + goto cleanup; + + ASSERT_EQ(skel->bss->g_unexpected, 0, "g_unexpected"); + ASSERT_EQ(skel->bss->g_sock_state, TIME_WAIT, "g_sock_state"); + + uninstall_filters(&egress_link, &ingress_link); + + /* Scenario 3 */ + err = install_filters(cgroup_fd, &egress_link, &ingress_link, + skel->progs.client_egress_srv, + skel->progs.client_ingress_srv, + skel); + + err = talk_to_outside(&client_fd, &listen_fd, &service_fd, skel); + if (!ASSERT_OK(err, "talk_to_outside")) + goto cleanup; + + err = close_connection(&service_fd, &client_fd, &listen_fd, skel); + if (!ASSERT_OK(err, "close_connection")) + goto cleanup; + + ASSERT_EQ(skel->bss->g_unexpected, 0, "g_unexpected"); + ASSERT_EQ(skel->bss->g_sock_state, CLOSED, "g_sock_state"); + + uninstall_filters(&egress_link, &ingress_link); + + /* Scenario 4 */ + err = install_filters(cgroup_fd, &egress_link, &ingress_link, + skel->progs.client_egress, + skel->progs.client_ingress, + skel); + + err = talk_to_outside(&client_fd, &listen_fd, &service_fd, skel); + if (!ASSERT_OK(err, "talk_to_outside")) + goto cleanup; + + err = close_connection(&client_fd, &service_fd, &listen_fd, skel); + if (!ASSERT_OK(err, "close_connection")) + goto cleanup; + + ASSERT_EQ(skel->bss->g_unexpected, 0, "g_unexpected"); + ASSERT_EQ(skel->bss->g_sock_state, TIME_WAIT, "g_sock_state"); + + uninstall_filters(&egress_link, &ingress_link); + +cleanup: + close(client_fd); + close(listen_fd); + close(service_fd); + close(cgroup_fd); + bpf_link__destroy(egress_link); + bpf_link__destroy(ingress_link); + cleanup_cgroup_environment(); + cgroup_tcp_skb__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/d_path.c b/tools/testing/selftests/bpf/prog_tests/d_path.c index 911345c526e6..ccc768592e66 100644 --- a/tools/testing/selftests/bpf/prog_tests/d_path.c +++ b/tools/testing/selftests/bpf/prog_tests/d_path.c @@ -12,6 +12,17 @@ #include "test_d_path_check_rdonly_mem.skel.h" #include "test_d_path_check_types.skel.h" +/* sys_close_range is not around for long time, so let's + * make sure we can call it on systems with older glibc + */ +#ifndef __NR_close_range +#ifdef __alpha__ +#define __NR_close_range 546 +#else +#define __NR_close_range 436 +#endif +#endif + static int duration; static struct { @@ -90,7 +101,11 @@ static int trigger_fstat_events(pid_t pid) fstat(indicatorfd, &fileStat); out_close: - /* triggers filp_close */ + /* sys_close no longer triggers filp_close, but we can + * call sys_close_range instead which still does + */ +#define close(fd) syscall(__NR_close_range, fd, fd, 0) + close(pipefd[0]); close(pipefd[1]); close(sockfd); @@ -98,6 +113,8 @@ out_close: close(devfd); close(localfd); close(indicatorfd); + +#undef close return ret; } diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_test.c b/tools/testing/selftests/bpf/prog_tests/fentry_test.c index c0d1d61d5f66..aee1bc77a17f 100644 --- a/tools/testing/selftests/bpf/prog_tests/fentry_test.c +++ b/tools/testing/selftests/bpf/prog_tests/fentry_test.c @@ -2,8 +2,9 @@ /* Copyright (c) 2019 Facebook */ #include <test_progs.h> #include "fentry_test.lskel.h" +#include "fentry_many_args.skel.h" -static int fentry_test(struct fentry_test_lskel *fentry_skel) +static int fentry_test_common(struct fentry_test_lskel *fentry_skel) { int err, prog_fd, i; int link_fd; @@ -37,7 +38,7 @@ static int fentry_test(struct fentry_test_lskel *fentry_skel) return 0; } -void test_fentry_test(void) +static void fentry_test(void) { struct fentry_test_lskel *fentry_skel = NULL; int err; @@ -46,13 +47,47 @@ void test_fentry_test(void) if (!ASSERT_OK_PTR(fentry_skel, "fentry_skel_load")) goto cleanup; - err = fentry_test(fentry_skel); + err = fentry_test_common(fentry_skel); if (!ASSERT_OK(err, "fentry_first_attach")) goto cleanup; - err = fentry_test(fentry_skel); + err = fentry_test_common(fentry_skel); ASSERT_OK(err, "fentry_second_attach"); cleanup: fentry_test_lskel__destroy(fentry_skel); } + +static void fentry_many_args(void) +{ + struct fentry_many_args *fentry_skel = NULL; + int err; + + fentry_skel = fentry_many_args__open_and_load(); + if (!ASSERT_OK_PTR(fentry_skel, "fentry_many_args_skel_load")) + goto cleanup; + + err = fentry_many_args__attach(fentry_skel); + if (!ASSERT_OK(err, "fentry_many_args_attach")) + goto cleanup; + + ASSERT_OK(trigger_module_test_read(1), "trigger_read"); + + ASSERT_EQ(fentry_skel->bss->test1_result, 1, + "fentry_many_args_result1"); + ASSERT_EQ(fentry_skel->bss->test2_result, 1, + "fentry_many_args_result2"); + ASSERT_EQ(fentry_skel->bss->test3_result, 1, + "fentry_many_args_result3"); + +cleanup: + fentry_many_args__destroy(fentry_skel); +} + +void test_fentry_test(void) +{ + if (test__start_subtest("fentry")) + fentry_test(); + if (test__start_subtest("fentry_many_args")) + fentry_many_args(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_test.c b/tools/testing/selftests/bpf/prog_tests/fexit_test.c index 101b7343036b..1c13007e37dd 100644 --- a/tools/testing/selftests/bpf/prog_tests/fexit_test.c +++ b/tools/testing/selftests/bpf/prog_tests/fexit_test.c @@ -2,8 +2,9 @@ /* Copyright (c) 2019 Facebook */ #include <test_progs.h> #include "fexit_test.lskel.h" +#include "fexit_many_args.skel.h" -static int fexit_test(struct fexit_test_lskel *fexit_skel) +static int fexit_test_common(struct fexit_test_lskel *fexit_skel) { int err, prog_fd, i; int link_fd; @@ -37,7 +38,7 @@ static int fexit_test(struct fexit_test_lskel *fexit_skel) return 0; } -void test_fexit_test(void) +static void fexit_test(void) { struct fexit_test_lskel *fexit_skel = NULL; int err; @@ -46,13 +47,47 @@ void test_fexit_test(void) if (!ASSERT_OK_PTR(fexit_skel, "fexit_skel_load")) goto cleanup; - err = fexit_test(fexit_skel); + err = fexit_test_common(fexit_skel); if (!ASSERT_OK(err, "fexit_first_attach")) goto cleanup; - err = fexit_test(fexit_skel); + err = fexit_test_common(fexit_skel); ASSERT_OK(err, "fexit_second_attach"); cleanup: fexit_test_lskel__destroy(fexit_skel); } + +static void fexit_many_args(void) +{ + struct fexit_many_args *fexit_skel = NULL; + int err; + + fexit_skel = fexit_many_args__open_and_load(); + if (!ASSERT_OK_PTR(fexit_skel, "fexit_many_args_skel_load")) + goto cleanup; + + err = fexit_many_args__attach(fexit_skel); + if (!ASSERT_OK(err, "fexit_many_args_attach")) + goto cleanup; + + ASSERT_OK(trigger_module_test_read(1), "trigger_read"); + + ASSERT_EQ(fexit_skel->bss->test1_result, 1, + "fexit_many_args_result1"); + ASSERT_EQ(fexit_skel->bss->test2_result, 1, + "fexit_many_args_result2"); + ASSERT_EQ(fexit_skel->bss->test3_result, 1, + "fexit_many_args_result3"); + +cleanup: + fexit_many_args__destroy(fexit_skel); +} + +void test_fexit_test(void) +{ + if (test__start_subtest("fexit")) + fexit_test(); + if (test__start_subtest("fexit_many_args")) + fexit_many_args(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/fill_link_info.c b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c new file mode 100644 index 000000000000..9d768e083714 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c @@ -0,0 +1,342 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023 Yafang Shao <laoar.shao@gmail.com> */ + +#include <string.h> +#include <linux/bpf.h> +#include <linux/limits.h> +#include <test_progs.h> +#include "trace_helpers.h" +#include "test_fill_link_info.skel.h" + +#define TP_CAT "sched" +#define TP_NAME "sched_switch" + +static const char *kmulti_syms[] = { + "bpf_fentry_test2", + "bpf_fentry_test1", + "bpf_fentry_test3", +}; +#define KMULTI_CNT ARRAY_SIZE(kmulti_syms) +static __u64 kmulti_addrs[KMULTI_CNT]; + +#define KPROBE_FUNC "bpf_fentry_test1" +static __u64 kprobe_addr; + +#define UPROBE_FILE "/proc/self/exe" +static ssize_t uprobe_offset; +/* uprobe attach point */ +static noinline void uprobe_func(void) +{ + asm volatile (""); +} + +static int verify_perf_link_info(int fd, enum bpf_perf_event_type type, long addr, + ssize_t offset, ssize_t entry_offset) +{ + struct bpf_link_info info; + __u32 len = sizeof(info); + char buf[PATH_MAX]; + int err; + + memset(&info, 0, sizeof(info)); + buf[0] = '\0'; + +again: + err = bpf_link_get_info_by_fd(fd, &info, &len); + if (!ASSERT_OK(err, "get_link_info")) + return -1; + + if (!ASSERT_EQ(info.type, BPF_LINK_TYPE_PERF_EVENT, "link_type")) + return -1; + if (!ASSERT_EQ(info.perf_event.type, type, "perf_type_match")) + return -1; + + switch (info.perf_event.type) { + case BPF_PERF_EVENT_KPROBE: + case BPF_PERF_EVENT_KRETPROBE: + ASSERT_EQ(info.perf_event.kprobe.offset, offset, "kprobe_offset"); + + /* In case kernel.kptr_restrict is not permitted or MAX_SYMS is reached */ + if (addr) + ASSERT_EQ(info.perf_event.kprobe.addr, addr + entry_offset, + "kprobe_addr"); + + if (!info.perf_event.kprobe.func_name) { + ASSERT_EQ(info.perf_event.kprobe.name_len, 0, "name_len"); + info.perf_event.kprobe.func_name = ptr_to_u64(&buf); + info.perf_event.kprobe.name_len = sizeof(buf); + goto again; + } + + err = strncmp(u64_to_ptr(info.perf_event.kprobe.func_name), KPROBE_FUNC, + strlen(KPROBE_FUNC)); + ASSERT_EQ(err, 0, "cmp_kprobe_func_name"); + break; + case BPF_PERF_EVENT_TRACEPOINT: + if (!info.perf_event.tracepoint.tp_name) { + ASSERT_EQ(info.perf_event.tracepoint.name_len, 0, "name_len"); + info.perf_event.tracepoint.tp_name = ptr_to_u64(&buf); + info.perf_event.tracepoint.name_len = sizeof(buf); + goto again; + } + + err = strncmp(u64_to_ptr(info.perf_event.tracepoint.tp_name), TP_NAME, + strlen(TP_NAME)); + ASSERT_EQ(err, 0, "cmp_tp_name"); + break; + case BPF_PERF_EVENT_UPROBE: + case BPF_PERF_EVENT_URETPROBE: + ASSERT_EQ(info.perf_event.uprobe.offset, offset, "uprobe_offset"); + + if (!info.perf_event.uprobe.file_name) { + ASSERT_EQ(info.perf_event.uprobe.name_len, 0, "name_len"); + info.perf_event.uprobe.file_name = ptr_to_u64(&buf); + info.perf_event.uprobe.name_len = sizeof(buf); + goto again; + } + + err = strncmp(u64_to_ptr(info.perf_event.uprobe.file_name), UPROBE_FILE, + strlen(UPROBE_FILE)); + ASSERT_EQ(err, 0, "cmp_file_name"); + break; + default: + err = -1; + break; + } + return err; +} + +static void kprobe_fill_invalid_user_buffer(int fd) +{ + struct bpf_link_info info; + __u32 len = sizeof(info); + int err; + + memset(&info, 0, sizeof(info)); + + info.perf_event.kprobe.func_name = 0x1; /* invalid address */ + err = bpf_link_get_info_by_fd(fd, &info, &len); + ASSERT_EQ(err, -EINVAL, "invalid_buff_and_len"); + + info.perf_event.kprobe.name_len = 64; + err = bpf_link_get_info_by_fd(fd, &info, &len); + ASSERT_EQ(err, -EFAULT, "invalid_buff"); + + info.perf_event.kprobe.func_name = 0; + err = bpf_link_get_info_by_fd(fd, &info, &len); + ASSERT_EQ(err, -EINVAL, "invalid_len"); + + ASSERT_EQ(info.perf_event.kprobe.addr, 0, "func_addr"); + ASSERT_EQ(info.perf_event.kprobe.offset, 0, "func_offset"); + ASSERT_EQ(info.perf_event.type, 0, "type"); +} + +static void test_kprobe_fill_link_info(struct test_fill_link_info *skel, + enum bpf_perf_event_type type, + bool invalid) +{ + DECLARE_LIBBPF_OPTS(bpf_kprobe_opts, opts, + .attach_mode = PROBE_ATTACH_MODE_LINK, + .retprobe = type == BPF_PERF_EVENT_KRETPROBE, + ); + ssize_t entry_offset = 0; + int link_fd, err; + + skel->links.kprobe_run = bpf_program__attach_kprobe_opts(skel->progs.kprobe_run, + KPROBE_FUNC, &opts); + if (!ASSERT_OK_PTR(skel->links.kprobe_run, "attach_kprobe")) + return; + + link_fd = bpf_link__fd(skel->links.kprobe_run); + if (!invalid) { + /* See also arch_adjust_kprobe_addr(). */ + if (skel->kconfig->CONFIG_X86_KERNEL_IBT) + entry_offset = 4; + err = verify_perf_link_info(link_fd, type, kprobe_addr, 0, entry_offset); + ASSERT_OK(err, "verify_perf_link_info"); + } else { + kprobe_fill_invalid_user_buffer(link_fd); + } + bpf_link__detach(skel->links.kprobe_run); +} + +static void test_tp_fill_link_info(struct test_fill_link_info *skel) +{ + int link_fd, err; + + skel->links.tp_run = bpf_program__attach_tracepoint(skel->progs.tp_run, TP_CAT, TP_NAME); + if (!ASSERT_OK_PTR(skel->links.tp_run, "attach_tp")) + return; + + link_fd = bpf_link__fd(skel->links.tp_run); + err = verify_perf_link_info(link_fd, BPF_PERF_EVENT_TRACEPOINT, 0, 0, 0); + ASSERT_OK(err, "verify_perf_link_info"); + bpf_link__detach(skel->links.tp_run); +} + +static void test_uprobe_fill_link_info(struct test_fill_link_info *skel, + enum bpf_perf_event_type type) +{ + int link_fd, err; + + skel->links.uprobe_run = bpf_program__attach_uprobe(skel->progs.uprobe_run, + type == BPF_PERF_EVENT_URETPROBE, + 0, /* self pid */ + UPROBE_FILE, uprobe_offset); + if (!ASSERT_OK_PTR(skel->links.uprobe_run, "attach_uprobe")) + return; + + link_fd = bpf_link__fd(skel->links.uprobe_run); + err = verify_perf_link_info(link_fd, type, 0, uprobe_offset, 0); + ASSERT_OK(err, "verify_perf_link_info"); + bpf_link__detach(skel->links.uprobe_run); +} + +static int verify_kmulti_link_info(int fd, bool retprobe) +{ + struct bpf_link_info info; + __u32 len = sizeof(info); + __u64 addrs[KMULTI_CNT]; + int flags, i, err; + + memset(&info, 0, sizeof(info)); + +again: + err = bpf_link_get_info_by_fd(fd, &info, &len); + if (!ASSERT_OK(err, "get_link_info")) + return -1; + + if (!ASSERT_EQ(info.type, BPF_LINK_TYPE_KPROBE_MULTI, "kmulti_type")) + return -1; + + ASSERT_EQ(info.kprobe_multi.count, KMULTI_CNT, "func_cnt"); + flags = info.kprobe_multi.flags & BPF_F_KPROBE_MULTI_RETURN; + if (!retprobe) + ASSERT_EQ(flags, 0, "kmulti_flags"); + else + ASSERT_NEQ(flags, 0, "kretmulti_flags"); + + if (!info.kprobe_multi.addrs) { + info.kprobe_multi.addrs = ptr_to_u64(addrs); + goto again; + } + for (i = 0; i < KMULTI_CNT; i++) + ASSERT_EQ(addrs[i], kmulti_addrs[i], "kmulti_addrs"); + return 0; +} + +static void verify_kmulti_invalid_user_buffer(int fd) +{ + struct bpf_link_info info; + __u32 len = sizeof(info); + __u64 addrs[KMULTI_CNT]; + int err, i; + + memset(&info, 0, sizeof(info)); + + info.kprobe_multi.count = KMULTI_CNT; + err = bpf_link_get_info_by_fd(fd, &info, &len); + ASSERT_EQ(err, -EINVAL, "no_addr"); + + info.kprobe_multi.addrs = ptr_to_u64(addrs); + info.kprobe_multi.count = 0; + err = bpf_link_get_info_by_fd(fd, &info, &len); + ASSERT_EQ(err, -EINVAL, "no_cnt"); + + for (i = 0; i < KMULTI_CNT; i++) + addrs[i] = 0; + info.kprobe_multi.count = KMULTI_CNT - 1; + err = bpf_link_get_info_by_fd(fd, &info, &len); + ASSERT_EQ(err, -ENOSPC, "smaller_cnt"); + for (i = 0; i < KMULTI_CNT - 1; i++) + ASSERT_EQ(addrs[i], kmulti_addrs[i], "kmulti_addrs"); + ASSERT_EQ(addrs[i], 0, "kmulti_addrs"); + + for (i = 0; i < KMULTI_CNT; i++) + addrs[i] = 0; + info.kprobe_multi.count = KMULTI_CNT + 1; + err = bpf_link_get_info_by_fd(fd, &info, &len); + ASSERT_EQ(err, 0, "bigger_cnt"); + for (i = 0; i < KMULTI_CNT; i++) + ASSERT_EQ(addrs[i], kmulti_addrs[i], "kmulti_addrs"); + + info.kprobe_multi.count = KMULTI_CNT; + info.kprobe_multi.addrs = 0x1; /* invalid addr */ + err = bpf_link_get_info_by_fd(fd, &info, &len); + ASSERT_EQ(err, -EFAULT, "invalid_buff"); +} + +static int symbols_cmp_r(const void *a, const void *b) +{ + const char **str_a = (const char **) a; + const char **str_b = (const char **) b; + + return strcmp(*str_a, *str_b); +} + +static void test_kprobe_multi_fill_link_info(struct test_fill_link_info *skel, + bool retprobe, bool invalid) +{ + LIBBPF_OPTS(bpf_kprobe_multi_opts, opts); + int link_fd, err; + + opts.syms = kmulti_syms; + opts.cnt = KMULTI_CNT; + opts.retprobe = retprobe; + skel->links.kmulti_run = bpf_program__attach_kprobe_multi_opts(skel->progs.kmulti_run, + NULL, &opts); + if (!ASSERT_OK_PTR(skel->links.kmulti_run, "attach_kprobe_multi")) + return; + + link_fd = bpf_link__fd(skel->links.kmulti_run); + if (!invalid) { + err = verify_kmulti_link_info(link_fd, retprobe); + ASSERT_OK(err, "verify_kmulti_link_info"); + } else { + verify_kmulti_invalid_user_buffer(link_fd); + } + bpf_link__detach(skel->links.kmulti_run); +} + +void test_fill_link_info(void) +{ + struct test_fill_link_info *skel; + int i; + + skel = test_fill_link_info__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + return; + + /* load kallsyms to compare the addr */ + if (!ASSERT_OK(load_kallsyms_refresh(), "load_kallsyms_refresh")) + goto cleanup; + + kprobe_addr = ksym_get_addr(KPROBE_FUNC); + if (test__start_subtest("kprobe_link_info")) + test_kprobe_fill_link_info(skel, BPF_PERF_EVENT_KPROBE, false); + if (test__start_subtest("kretprobe_link_info")) + test_kprobe_fill_link_info(skel, BPF_PERF_EVENT_KRETPROBE, false); + if (test__start_subtest("kprobe_invalid_ubuff")) + test_kprobe_fill_link_info(skel, BPF_PERF_EVENT_KPROBE, true); + if (test__start_subtest("tracepoint_link_info")) + test_tp_fill_link_info(skel); + + uprobe_offset = get_uprobe_offset(&uprobe_func); + if (test__start_subtest("uprobe_link_info")) + test_uprobe_fill_link_info(skel, BPF_PERF_EVENT_UPROBE); + if (test__start_subtest("uretprobe_link_info")) + test_uprobe_fill_link_info(skel, BPF_PERF_EVENT_URETPROBE); + + qsort(kmulti_syms, KMULTI_CNT, sizeof(kmulti_syms[0]), symbols_cmp_r); + for (i = 0; i < KMULTI_CNT; i++) + kmulti_addrs[i] = ksym_get_addr(kmulti_syms[i]); + if (test__start_subtest("kprobe_multi_link_info")) + test_kprobe_multi_fill_link_info(skel, false, false); + if (test__start_subtest("kretprobe_multi_link_info")) + test_kprobe_multi_fill_link_info(skel, true, false); + if (test__start_subtest("kprobe_multi_invalid_ubuff")) + test_kprobe_multi_fill_link_info(skel, true, true); + +cleanup: + test_fill_link_info__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/get_func_args_test.c b/tools/testing/selftests/bpf/prog_tests/get_func_args_test.c index 28cf63963cb7..64a9c95d4acf 100644 --- a/tools/testing/selftests/bpf/prog_tests/get_func_args_test.c +++ b/tools/testing/selftests/bpf/prog_tests/get_func_args_test.c @@ -30,7 +30,9 @@ void test_get_func_args_test(void) prog_fd = bpf_program__fd(skel->progs.fmod_ret_test); err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "test_run"); - ASSERT_EQ(topts.retval, 1234, "test_run"); + + ASSERT_EQ(topts.retval >> 16, 1, "test_run"); + ASSERT_EQ(topts.retval & 0xffff, 1234 + 29, "test_run"); ASSERT_EQ(skel->bss->test1_result, 1, "test1_result"); ASSERT_EQ(skel->bss->test2_result, 1, "test2_result"); diff --git a/tools/testing/selftests/bpf/prog_tests/get_func_ip_test.c b/tools/testing/selftests/bpf/prog_tests/get_func_ip_test.c index fede8ef58b5b..c40242dfa8fb 100644 --- a/tools/testing/selftests/bpf/prog_tests/get_func_ip_test.c +++ b/tools/testing/selftests/bpf/prog_tests/get_func_ip_test.c @@ -1,6 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> #include "get_func_ip_test.skel.h" +#include "get_func_ip_uprobe_test.skel.h" + +static noinline void uprobe_trigger(void) +{ +} static void test_function_entry(void) { @@ -20,6 +25,8 @@ static void test_function_entry(void) if (!ASSERT_OK(err, "get_func_ip_test__attach")) goto cleanup; + skel->bss->uprobe_trigger = (unsigned long) uprobe_trigger; + prog_fd = bpf_program__fd(skel->progs.test1); err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "test_run"); @@ -30,21 +37,31 @@ static void test_function_entry(void) ASSERT_OK(err, "test_run"); + uprobe_trigger(); + ASSERT_EQ(skel->bss->test1_result, 1, "test1_result"); ASSERT_EQ(skel->bss->test2_result, 1, "test2_result"); ASSERT_EQ(skel->bss->test3_result, 1, "test3_result"); ASSERT_EQ(skel->bss->test4_result, 1, "test4_result"); ASSERT_EQ(skel->bss->test5_result, 1, "test5_result"); + ASSERT_EQ(skel->bss->test7_result, 1, "test7_result"); + ASSERT_EQ(skel->bss->test8_result, 1, "test8_result"); cleanup: get_func_ip_test__destroy(skel); } -/* test6 is x86_64 specific because of the instruction - * offset, disabling it for all other archs - */ #ifdef __x86_64__ -static void test_function_body(void) +extern void uprobe_trigger_body(void); +asm( +".globl uprobe_trigger_body\n" +".type uprobe_trigger_body, @function\n" +"uprobe_trigger_body:\n" +" nop\n" +" ret\n" +); + +static void test_function_body_kprobe(void) { struct get_func_ip_test *skel = NULL; LIBBPF_OPTS(bpf_test_run_opts, topts); @@ -56,6 +73,9 @@ static void test_function_body(void) if (!ASSERT_OK_PTR(skel, "get_func_ip_test__open")) return; + /* test6 is x86_64 specific and is disabled by default, + * enable it for body test. + */ bpf_program__set_autoload(skel->progs.test6, true); err = get_func_ip_test__load(skel); @@ -79,6 +99,35 @@ cleanup: bpf_link__destroy(link6); get_func_ip_test__destroy(skel); } + +static void test_function_body_uprobe(void) +{ + struct get_func_ip_uprobe_test *skel = NULL; + int err; + + skel = get_func_ip_uprobe_test__open_and_load(); + if (!ASSERT_OK_PTR(skel, "get_func_ip_uprobe_test__open_and_load")) + return; + + err = get_func_ip_uprobe_test__attach(skel); + if (!ASSERT_OK(err, "get_func_ip_test__attach")) + goto cleanup; + + skel->bss->uprobe_trigger_body = (unsigned long) uprobe_trigger_body; + + uprobe_trigger_body(); + + ASSERT_EQ(skel->bss->test1_result, 1, "test1_result"); + +cleanup: + get_func_ip_uprobe_test__destroy(skel); +} + +static void test_function_body(void) +{ + test_function_body_kprobe(); + test_function_body_uprobe(); +} #else #define test_function_body() #endif diff --git a/tools/testing/selftests/bpf/prog_tests/global_map_resize.c b/tools/testing/selftests/bpf/prog_tests/global_map_resize.c index fd41425d2e5c..56b5baef35c8 100644 --- a/tools/testing/selftests/bpf/prog_tests/global_map_resize.c +++ b/tools/testing/selftests/bpf/prog_tests/global_map_resize.c @@ -22,7 +22,7 @@ static void global_map_resize_bss_subtest(void) struct test_global_map_resize *skel; struct bpf_map *map; const __u32 desired_sz = sizeof(skel->bss->sum) + sysconf(_SC_PAGE_SIZE) * 2; - size_t array_len, actual_sz; + size_t array_len, actual_sz, new_sz; skel = test_global_map_resize__open(); if (!ASSERT_OK_PTR(skel, "test_global_map_resize__open")) @@ -42,6 +42,10 @@ static void global_map_resize_bss_subtest(void) if (!ASSERT_EQ(bpf_map__value_size(map), desired_sz, "resize")) goto teardown; + new_sz = sizeof(skel->data_percpu_arr->percpu_arr[0]) * libbpf_num_possible_cpus(); + err = bpf_map__set_value_size(skel->maps.data_percpu_arr, new_sz); + ASSERT_OK(err, "percpu_arr_resize"); + /* set the expected number of elements based on the resized array */ array_len = (desired_sz - sizeof(skel->bss->sum)) / sizeof(skel->bss->array[0]); if (!ASSERT_GT(array_len, 1, "array_len")) @@ -84,11 +88,11 @@ teardown: static void global_map_resize_data_subtest(void) { - int err; struct test_global_map_resize *skel; struct bpf_map *map; const __u32 desired_sz = sysconf(_SC_PAGE_SIZE) * 2; - size_t array_len, actual_sz; + size_t array_len, actual_sz, new_sz; + int err; skel = test_global_map_resize__open(); if (!ASSERT_OK_PTR(skel, "test_global_map_resize__open")) @@ -108,6 +112,10 @@ static void global_map_resize_data_subtest(void) if (!ASSERT_EQ(bpf_map__value_size(map), desired_sz, "resize")) goto teardown; + new_sz = sizeof(skel->data_percpu_arr->percpu_arr[0]) * libbpf_num_possible_cpus(); + err = bpf_map__set_value_size(skel->maps.data_percpu_arr, new_sz); + ASSERT_OK(err, "percpu_arr_resize"); + /* set the expected number of elements based on the resized array */ array_len = (desired_sz - sizeof(skel->bss->sum)) / sizeof(skel->data_custom->my_array[0]); if (!ASSERT_GT(array_len, 1, "array_len")) diff --git a/tools/testing/selftests/bpf/prog_tests/ip_check_defrag.c b/tools/testing/selftests/bpf/prog_tests/ip_check_defrag.c new file mode 100644 index 000000000000..57c814f5f6a7 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/ip_check_defrag.c @@ -0,0 +1,283 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include <net/if.h> +#include <linux/netfilter.h> +#include <network_helpers.h> +#include "ip_check_defrag.skel.h" +#include "ip_check_defrag_frags.h" + +/* + * This selftest spins up a client and an echo server, each in their own + * network namespace. The client will send a fragmented message to the server. + * The prog attached to the server will shoot down any fragments. Thus, if + * the server is able to correctly echo back the message to the client, we will + * have verified that netfilter is reassembling packets for us. + * + * Topology: + * ========= + * NS0 | NS1 + * | + * client | server + * ---------- | ---------- + * | veth0 | --------- | veth1 | + * ---------- peer ---------- + * | + * | with bpf + */ + +#define NS0 "defrag_ns0" +#define NS1 "defrag_ns1" +#define VETH0 "veth0" +#define VETH1 "veth1" +#define VETH0_ADDR "172.16.1.100" +#define VETH0_ADDR6 "fc00::100" +/* The following constants must stay in sync with `generate_udp_fragments.py` */ +#define VETH1_ADDR "172.16.1.200" +#define VETH1_ADDR6 "fc00::200" +#define CLIENT_PORT 48878 +#define SERVER_PORT 48879 +#define MAGIC_MESSAGE "THIS IS THE ORIGINAL MESSAGE, PLEASE REASSEMBLE ME" + +static int setup_topology(bool ipv6) +{ + bool up; + int i; + + SYS(fail, "ip netns add " NS0); + SYS(fail, "ip netns add " NS1); + SYS(fail, "ip link add " VETH0 " netns " NS0 " type veth peer name " VETH1 " netns " NS1); + if (ipv6) { + SYS(fail, "ip -6 -net " NS0 " addr add " VETH0_ADDR6 "/64 dev " VETH0 " nodad"); + SYS(fail, "ip -6 -net " NS1 " addr add " VETH1_ADDR6 "/64 dev " VETH1 " nodad"); + } else { + SYS(fail, "ip -net " NS0 " addr add " VETH0_ADDR "/24 dev " VETH0); + SYS(fail, "ip -net " NS1 " addr add " VETH1_ADDR "/24 dev " VETH1); + } + SYS(fail, "ip -net " NS0 " link set dev " VETH0 " up"); + SYS(fail, "ip -net " NS1 " link set dev " VETH1 " up"); + + /* Wait for up to 5s for links to come up */ + for (i = 0; i < 5; ++i) { + if (ipv6) + up = !system("ip netns exec " NS0 " ping -6 -c 1 -W 1 " VETH1_ADDR6 " &>/dev/null"); + else + up = !system("ip netns exec " NS0 " ping -c 1 -W 1 " VETH1_ADDR " &>/dev/null"); + + if (up) + break; + } + + return 0; +fail: + return -1; +} + +static void cleanup_topology(void) +{ + SYS_NOFAIL("test -f /var/run/netns/" NS0 " && ip netns delete " NS0); + SYS_NOFAIL("test -f /var/run/netns/" NS1 " && ip netns delete " NS1); +} + +static int attach(struct ip_check_defrag *skel, bool ipv6) +{ + LIBBPF_OPTS(bpf_netfilter_opts, opts, + .pf = ipv6 ? NFPROTO_IPV6 : NFPROTO_IPV4, + .priority = 42, + .flags = BPF_F_NETFILTER_IP_DEFRAG); + struct nstoken *nstoken; + int err = -1; + + nstoken = open_netns(NS1); + + skel->links.defrag = bpf_program__attach_netfilter(skel->progs.defrag, &opts); + if (!ASSERT_OK_PTR(skel->links.defrag, "program attach")) + goto out; + + err = 0; +out: + close_netns(nstoken); + return err; +} + +static int send_frags(int client) +{ + struct sockaddr_storage saddr; + struct sockaddr *saddr_p; + socklen_t saddr_len; + int err; + + saddr_p = (struct sockaddr *)&saddr; + err = make_sockaddr(AF_INET, VETH1_ADDR, SERVER_PORT, &saddr, &saddr_len); + if (!ASSERT_OK(err, "make_sockaddr")) + return -1; + + err = sendto(client, frag_0, sizeof(frag_0), 0, saddr_p, saddr_len); + if (!ASSERT_GE(err, 0, "sendto frag_0")) + return -1; + + err = sendto(client, frag_1, sizeof(frag_1), 0, saddr_p, saddr_len); + if (!ASSERT_GE(err, 0, "sendto frag_1")) + return -1; + + err = sendto(client, frag_2, sizeof(frag_2), 0, saddr_p, saddr_len); + if (!ASSERT_GE(err, 0, "sendto frag_2")) + return -1; + + return 0; +} + +static int send_frags6(int client) +{ + struct sockaddr_storage saddr; + struct sockaddr *saddr_p; + socklen_t saddr_len; + int err; + + saddr_p = (struct sockaddr *)&saddr; + /* Port needs to be set to 0 for raw ipv6 socket for some reason */ + err = make_sockaddr(AF_INET6, VETH1_ADDR6, 0, &saddr, &saddr_len); + if (!ASSERT_OK(err, "make_sockaddr")) + return -1; + + err = sendto(client, frag6_0, sizeof(frag6_0), 0, saddr_p, saddr_len); + if (!ASSERT_GE(err, 0, "sendto frag6_0")) + return -1; + + err = sendto(client, frag6_1, sizeof(frag6_1), 0, saddr_p, saddr_len); + if (!ASSERT_GE(err, 0, "sendto frag6_1")) + return -1; + + err = sendto(client, frag6_2, sizeof(frag6_2), 0, saddr_p, saddr_len); + if (!ASSERT_GE(err, 0, "sendto frag6_2")) + return -1; + + return 0; +} + +void test_bpf_ip_check_defrag_ok(bool ipv6) +{ + struct network_helper_opts rx_opts = { + .timeout_ms = 1000, + .noconnect = true, + }; + struct network_helper_opts tx_ops = { + .timeout_ms = 1000, + .type = SOCK_RAW, + .proto = IPPROTO_RAW, + .noconnect = true, + }; + struct sockaddr_storage caddr; + struct ip_check_defrag *skel; + struct nstoken *nstoken; + int client_tx_fd = -1; + int client_rx_fd = -1; + socklen_t caddr_len; + int srv_fd = -1; + char buf[1024]; + int len, err; + + skel = ip_check_defrag__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + return; + + if (!ASSERT_OK(setup_topology(ipv6), "setup_topology")) + goto out; + + if (!ASSERT_OK(attach(skel, ipv6), "attach")) + goto out; + + /* Start server in ns1 */ + nstoken = open_netns(NS1); + if (!ASSERT_OK_PTR(nstoken, "setns ns1")) + goto out; + srv_fd = start_server(ipv6 ? AF_INET6 : AF_INET, SOCK_DGRAM, NULL, SERVER_PORT, 0); + close_netns(nstoken); + if (!ASSERT_GE(srv_fd, 0, "start_server")) + goto out; + + /* Open tx raw socket in ns0 */ + nstoken = open_netns(NS0); + if (!ASSERT_OK_PTR(nstoken, "setns ns0")) + goto out; + client_tx_fd = connect_to_fd_opts(srv_fd, &tx_ops); + close_netns(nstoken); + if (!ASSERT_GE(client_tx_fd, 0, "connect_to_fd_opts")) + goto out; + + /* Open rx socket in ns0 */ + nstoken = open_netns(NS0); + if (!ASSERT_OK_PTR(nstoken, "setns ns0")) + goto out; + client_rx_fd = connect_to_fd_opts(srv_fd, &rx_opts); + close_netns(nstoken); + if (!ASSERT_GE(client_rx_fd, 0, "connect_to_fd_opts")) + goto out; + + /* Bind rx socket to a premeditated port */ + memset(&caddr, 0, sizeof(caddr)); + nstoken = open_netns(NS0); + if (!ASSERT_OK_PTR(nstoken, "setns ns0")) + goto out; + if (ipv6) { + struct sockaddr_in6 *c = (struct sockaddr_in6 *)&caddr; + + c->sin6_family = AF_INET6; + inet_pton(AF_INET6, VETH0_ADDR6, &c->sin6_addr); + c->sin6_port = htons(CLIENT_PORT); + err = bind(client_rx_fd, (struct sockaddr *)c, sizeof(*c)); + } else { + struct sockaddr_in *c = (struct sockaddr_in *)&caddr; + + c->sin_family = AF_INET; + inet_pton(AF_INET, VETH0_ADDR, &c->sin_addr); + c->sin_port = htons(CLIENT_PORT); + err = bind(client_rx_fd, (struct sockaddr *)c, sizeof(*c)); + } + close_netns(nstoken); + if (!ASSERT_OK(err, "bind")) + goto out; + + /* Send message in fragments */ + if (ipv6) { + if (!ASSERT_OK(send_frags6(client_tx_fd), "send_frags6")) + goto out; + } else { + if (!ASSERT_OK(send_frags(client_tx_fd), "send_frags")) + goto out; + } + + if (!ASSERT_EQ(skel->bss->shootdowns, 0, "shootdowns")) + goto out; + + /* Receive reassembled msg on server and echo back to client */ + caddr_len = sizeof(caddr); + len = recvfrom(srv_fd, buf, sizeof(buf), 0, (struct sockaddr *)&caddr, &caddr_len); + if (!ASSERT_GE(len, 0, "server recvfrom")) + goto out; + len = sendto(srv_fd, buf, len, 0, (struct sockaddr *)&caddr, caddr_len); + if (!ASSERT_GE(len, 0, "server sendto")) + goto out; + + /* Expect reassembed message to be echoed back */ + len = recvfrom(client_rx_fd, buf, sizeof(buf), 0, NULL, NULL); + if (!ASSERT_EQ(len, sizeof(MAGIC_MESSAGE) - 1, "client short read")) + goto out; + +out: + if (client_rx_fd != -1) + close(client_rx_fd); + if (client_tx_fd != -1) + close(client_tx_fd); + if (srv_fd != -1) + close(srv_fd); + cleanup_topology(); + ip_check_defrag__destroy(skel); +} + +void test_bpf_ip_check_defrag(void) +{ + if (test__start_subtest("v4")) + test_bpf_ip_check_defrag_ok(false); + if (test__start_subtest("v6")) + test_bpf_ip_check_defrag_ok(true); +} diff --git a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c index a543742cd7bd..2eb71559713c 100644 --- a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c +++ b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c @@ -173,8 +173,8 @@ static void verify_fail(struct kfunc_test_params *param) case tc_test: topts.data_in = &pkt_v4; topts.data_size_in = sizeof(pkt_v4); - break; topts.repeat = 1; + break; } skel = kfunc_call_fail__open_opts(&opts); diff --git a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c index 2173c4bb555e..179fe300534f 100644 --- a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c +++ b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c @@ -304,14 +304,6 @@ cleanup: kprobe_multi__destroy(skel); } -static inline __u64 get_time_ns(void) -{ - struct timespec t; - - clock_gettime(CLOCK_MONOTONIC, &t); - return (__u64) t.tv_sec * 1000000000 + t.tv_nsec; -} - static size_t symbol_hash(long key, void *ctx __maybe_unused) { return str_hash((const char *) key); diff --git a/tools/testing/selftests/bpf/prog_tests/linked_list.c b/tools/testing/selftests/bpf/prog_tests/linked_list.c index f63309fd0e28..18cf7b17463d 100644 --- a/tools/testing/selftests/bpf/prog_tests/linked_list.c +++ b/tools/testing/selftests/bpf/prog_tests/linked_list.c @@ -23,7 +23,7 @@ static struct { "bpf_spin_lock at off=" #off " must be held for bpf_list_head" }, \ { #test "_missing_lock_pop_back", \ "bpf_spin_lock at off=" #off " must be held for bpf_list_head" }, - TEST(kptr, 32) + TEST(kptr, 40) TEST(global, 16) TEST(map, 0) TEST(inner_map, 0) @@ -31,7 +31,7 @@ static struct { #define TEST(test, op) \ { #test "_kptr_incorrect_lock_" #op, \ "held lock and object are not in the same allocation\n" \ - "bpf_spin_lock at off=32 must be held for bpf_list_head" }, \ + "bpf_spin_lock at off=40 must be held for bpf_list_head" }, \ { #test "_global_incorrect_lock_" #op, \ "held lock and object are not in the same allocation\n" \ "bpf_spin_lock at off=16 must be held for bpf_list_head" }, \ @@ -84,23 +84,23 @@ static struct { { "double_push_back", "arg#1 expected pointer to allocated object" }, { "no_node_value_type", "bpf_list_node not found at offset=0" }, { "incorrect_value_type", - "operation on bpf_list_head expects arg#1 bpf_list_node at offset=40 in struct foo, " + "operation on bpf_list_head expects arg#1 bpf_list_node at offset=48 in struct foo, " "but arg is at offset=0 in struct bar" }, { "incorrect_node_var_off", "variable ptr_ access var_off=(0x0; 0xffffffff) disallowed" }, - { "incorrect_node_off1", "bpf_list_node not found at offset=41" }, - { "incorrect_node_off2", "arg#1 offset=0, but expected bpf_list_node at offset=40 in struct foo" }, + { "incorrect_node_off1", "bpf_list_node not found at offset=49" }, + { "incorrect_node_off2", "arg#1 offset=0, but expected bpf_list_node at offset=48 in struct foo" }, { "no_head_type", "bpf_list_head not found at offset=0" }, { "incorrect_head_var_off1", "R1 doesn't have constant offset" }, { "incorrect_head_var_off2", "variable ptr_ access var_off=(0x0; 0xffffffff) disallowed" }, - { "incorrect_head_off1", "bpf_list_head not found at offset=17" }, + { "incorrect_head_off1", "bpf_list_head not found at offset=25" }, { "incorrect_head_off2", "bpf_list_head not found at offset=1" }, { "pop_front_off", - "15: (bf) r1 = r6 ; R1_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=40,imm=0) " - "R6_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=40,imm=0) refs=2,4\n" + "15: (bf) r1 = r6 ; R1_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=48,imm=0) " + "R6_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=48,imm=0) refs=2,4\n" "16: (85) call bpf_this_cpu_ptr#154\nR1 type=ptr_or_null_ expected=percpu_ptr_" }, { "pop_back_off", - "15: (bf) r1 = r6 ; R1_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=40,imm=0) " - "R6_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=40,imm=0) refs=2,4\n" + "15: (bf) r1 = r6 ; R1_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=48,imm=0) " + "R6_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=48,imm=0) refs=2,4\n" "16: (85) call bpf_this_cpu_ptr#154\nR1 type=ptr_or_null_ expected=percpu_ptr_" }, }; @@ -257,7 +257,7 @@ static struct btf *init_btf(void) hid = btf__add_struct(btf, "bpf_list_head", 16); if (!ASSERT_EQ(hid, LIST_HEAD, "btf__add_struct bpf_list_head")) goto end; - nid = btf__add_struct(btf, "bpf_list_node", 16); + nid = btf__add_struct(btf, "bpf_list_node", 24); if (!ASSERT_EQ(nid, LIST_NODE, "btf__add_struct bpf_list_node")) goto end; return btf; @@ -276,7 +276,7 @@ static void list_and_rb_node_same_struct(bool refcount_field) if (!ASSERT_OK_PTR(btf, "init_btf")) return; - bpf_rb_node_btf_id = btf__add_struct(btf, "bpf_rb_node", 24); + bpf_rb_node_btf_id = btf__add_struct(btf, "bpf_rb_node", 32); if (!ASSERT_GT(bpf_rb_node_btf_id, 0, "btf__add_struct bpf_rb_node")) return; @@ -286,17 +286,17 @@ static void list_and_rb_node_same_struct(bool refcount_field) return; } - id = btf__add_struct(btf, "bar", refcount_field ? 44 : 40); + id = btf__add_struct(btf, "bar", refcount_field ? 60 : 56); if (!ASSERT_GT(id, 0, "btf__add_struct bar")) return; err = btf__add_field(btf, "a", LIST_NODE, 0, 0); if (!ASSERT_OK(err, "btf__add_field bar::a")) return; - err = btf__add_field(btf, "c", bpf_rb_node_btf_id, 128, 0); + err = btf__add_field(btf, "c", bpf_rb_node_btf_id, 192, 0); if (!ASSERT_OK(err, "btf__add_field bar::c")) return; if (refcount_field) { - err = btf__add_field(btf, "ref", bpf_refcount_btf_id, 320, 0); + err = btf__add_field(btf, "ref", bpf_refcount_btf_id, 448, 0); if (!ASSERT_OK(err, "btf__add_field bar::ref")) return; } @@ -527,7 +527,7 @@ static void test_btf(void) btf = init_btf(); if (!ASSERT_OK_PTR(btf, "init_btf")) break; - id = btf__add_struct(btf, "foo", 36); + id = btf__add_struct(btf, "foo", 44); if (!ASSERT_EQ(id, 5, "btf__add_struct foo")) break; err = btf__add_field(btf, "a", LIST_HEAD, 0, 0); @@ -536,7 +536,7 @@ static void test_btf(void) err = btf__add_field(btf, "b", LIST_NODE, 128, 0); if (!ASSERT_OK(err, "btf__add_field foo::b")) break; - err = btf__add_field(btf, "c", SPIN_LOCK, 256, 0); + err = btf__add_field(btf, "c", SPIN_LOCK, 320, 0); if (!ASSERT_OK(err, "btf__add_field foo::c")) break; id = btf__add_decl_tag(btf, "contains:foo:b", 5, 0); @@ -553,7 +553,7 @@ static void test_btf(void) btf = init_btf(); if (!ASSERT_OK_PTR(btf, "init_btf")) break; - id = btf__add_struct(btf, "foo", 36); + id = btf__add_struct(btf, "foo", 44); if (!ASSERT_EQ(id, 5, "btf__add_struct foo")) break; err = btf__add_field(btf, "a", LIST_HEAD, 0, 0); @@ -562,13 +562,13 @@ static void test_btf(void) err = btf__add_field(btf, "b", LIST_NODE, 128, 0); if (!ASSERT_OK(err, "btf__add_field foo::b")) break; - err = btf__add_field(btf, "c", SPIN_LOCK, 256, 0); + err = btf__add_field(btf, "c", SPIN_LOCK, 320, 0); if (!ASSERT_OK(err, "btf__add_field foo::c")) break; id = btf__add_decl_tag(btf, "contains:bar:b", 5, 0); if (!ASSERT_EQ(id, 6, "btf__add_decl_tag contains:bar:b")) break; - id = btf__add_struct(btf, "bar", 36); + id = btf__add_struct(btf, "bar", 44); if (!ASSERT_EQ(id, 7, "btf__add_struct bar")) break; err = btf__add_field(btf, "a", LIST_HEAD, 0, 0); @@ -577,7 +577,7 @@ static void test_btf(void) err = btf__add_field(btf, "b", LIST_NODE, 128, 0); if (!ASSERT_OK(err, "btf__add_field bar::b")) break; - err = btf__add_field(btf, "c", SPIN_LOCK, 256, 0); + err = btf__add_field(btf, "c", SPIN_LOCK, 320, 0); if (!ASSERT_OK(err, "btf__add_field bar::c")) break; id = btf__add_decl_tag(btf, "contains:foo:b", 7, 0); @@ -594,19 +594,19 @@ static void test_btf(void) btf = init_btf(); if (!ASSERT_OK_PTR(btf, "init_btf")) break; - id = btf__add_struct(btf, "foo", 20); + id = btf__add_struct(btf, "foo", 28); if (!ASSERT_EQ(id, 5, "btf__add_struct foo")) break; err = btf__add_field(btf, "a", LIST_HEAD, 0, 0); if (!ASSERT_OK(err, "btf__add_field foo::a")) break; - err = btf__add_field(btf, "b", SPIN_LOCK, 128, 0); + err = btf__add_field(btf, "b", SPIN_LOCK, 192, 0); if (!ASSERT_OK(err, "btf__add_field foo::b")) break; id = btf__add_decl_tag(btf, "contains:bar:a", 5, 0); if (!ASSERT_EQ(id, 6, "btf__add_decl_tag contains:bar:a")) break; - id = btf__add_struct(btf, "bar", 16); + id = btf__add_struct(btf, "bar", 24); if (!ASSERT_EQ(id, 7, "btf__add_struct bar")) break; err = btf__add_field(btf, "a", LIST_NODE, 0, 0); @@ -623,19 +623,19 @@ static void test_btf(void) btf = init_btf(); if (!ASSERT_OK_PTR(btf, "init_btf")) break; - id = btf__add_struct(btf, "foo", 20); + id = btf__add_struct(btf, "foo", 28); if (!ASSERT_EQ(id, 5, "btf__add_struct foo")) break; err = btf__add_field(btf, "a", LIST_HEAD, 0, 0); if (!ASSERT_OK(err, "btf__add_field foo::a")) break; - err = btf__add_field(btf, "b", SPIN_LOCK, 128, 0); + err = btf__add_field(btf, "b", SPIN_LOCK, 192, 0); if (!ASSERT_OK(err, "btf__add_field foo::b")) break; id = btf__add_decl_tag(btf, "contains:bar:b", 5, 0); if (!ASSERT_EQ(id, 6, "btf__add_decl_tag contains:bar:b")) break; - id = btf__add_struct(btf, "bar", 36); + id = btf__add_struct(btf, "bar", 44); if (!ASSERT_EQ(id, 7, "btf__add_struct bar")) break; err = btf__add_field(btf, "a", LIST_HEAD, 0, 0); @@ -644,13 +644,13 @@ static void test_btf(void) err = btf__add_field(btf, "b", LIST_NODE, 128, 0); if (!ASSERT_OK(err, "btf__add_field bar::b")) break; - err = btf__add_field(btf, "c", SPIN_LOCK, 256, 0); + err = btf__add_field(btf, "c", SPIN_LOCK, 320, 0); if (!ASSERT_OK(err, "btf__add_field bar::c")) break; id = btf__add_decl_tag(btf, "contains:baz:a", 7, 0); if (!ASSERT_EQ(id, 8, "btf__add_decl_tag contains:baz:a")) break; - id = btf__add_struct(btf, "baz", 16); + id = btf__add_struct(btf, "baz", 24); if (!ASSERT_EQ(id, 9, "btf__add_struct baz")) break; err = btf__add_field(btf, "a", LIST_NODE, 0, 0); @@ -667,7 +667,7 @@ static void test_btf(void) btf = init_btf(); if (!ASSERT_OK_PTR(btf, "init_btf")) break; - id = btf__add_struct(btf, "foo", 36); + id = btf__add_struct(btf, "foo", 44); if (!ASSERT_EQ(id, 5, "btf__add_struct foo")) break; err = btf__add_field(btf, "a", LIST_HEAD, 0, 0); @@ -676,13 +676,13 @@ static void test_btf(void) err = btf__add_field(btf, "b", LIST_NODE, 128, 0); if (!ASSERT_OK(err, "btf__add_field foo::b")) break; - err = btf__add_field(btf, "c", SPIN_LOCK, 256, 0); + err = btf__add_field(btf, "c", SPIN_LOCK, 320, 0); if (!ASSERT_OK(err, "btf__add_field foo::c")) break; id = btf__add_decl_tag(btf, "contains:bar:b", 5, 0); if (!ASSERT_EQ(id, 6, "btf__add_decl_tag contains:bar:b")) break; - id = btf__add_struct(btf, "bar", 36); + id = btf__add_struct(btf, "bar", 44); if (!ASSERT_EQ(id, 7, "btf__add_struct bar")) break; err = btf__add_field(btf, "a", LIST_HEAD, 0, 0); @@ -691,13 +691,13 @@ static void test_btf(void) err = btf__add_field(btf, "b", LIST_NODE, 128, 0); if (!ASSERT_OK(err, "btf__add_field bar:b")) break; - err = btf__add_field(btf, "c", SPIN_LOCK, 256, 0); + err = btf__add_field(btf, "c", SPIN_LOCK, 320, 0); if (!ASSERT_OK(err, "btf__add_field bar:c")) break; id = btf__add_decl_tag(btf, "contains:baz:a", 7, 0); if (!ASSERT_EQ(id, 8, "btf__add_decl_tag contains:baz:a")) break; - id = btf__add_struct(btf, "baz", 16); + id = btf__add_struct(btf, "baz", 24); if (!ASSERT_EQ(id, 9, "btf__add_struct baz")) break; err = btf__add_field(btf, "a", LIST_NODE, 0, 0); @@ -726,7 +726,7 @@ static void test_btf(void) id = btf__add_decl_tag(btf, "contains:bar:b", 5, 0); if (!ASSERT_EQ(id, 6, "btf__add_decl_tag contains:bar:b")) break; - id = btf__add_struct(btf, "bar", 36); + id = btf__add_struct(btf, "bar", 44); if (!ASSERT_EQ(id, 7, "btf__add_struct bar")) break; err = btf__add_field(btf, "a", LIST_HEAD, 0, 0); @@ -735,13 +735,13 @@ static void test_btf(void) err = btf__add_field(btf, "b", LIST_NODE, 128, 0); if (!ASSERT_OK(err, "btf__add_field bar::b")) break; - err = btf__add_field(btf, "c", SPIN_LOCK, 256, 0); + err = btf__add_field(btf, "c", SPIN_LOCK, 320, 0); if (!ASSERT_OK(err, "btf__add_field bar::c")) break; id = btf__add_decl_tag(btf, "contains:baz:b", 7, 0); if (!ASSERT_EQ(id, 8, "btf__add_decl_tag")) break; - id = btf__add_struct(btf, "baz", 36); + id = btf__add_struct(btf, "baz", 44); if (!ASSERT_EQ(id, 9, "btf__add_struct baz")) break; err = btf__add_field(btf, "a", LIST_HEAD, 0, 0); @@ -750,13 +750,13 @@ static void test_btf(void) err = btf__add_field(btf, "b", LIST_NODE, 128, 0); if (!ASSERT_OK(err, "btf__add_field bar::b")) break; - err = btf__add_field(btf, "c", SPIN_LOCK, 256, 0); + err = btf__add_field(btf, "c", SPIN_LOCK, 320, 0); if (!ASSERT_OK(err, "btf__add_field bar::c")) break; id = btf__add_decl_tag(btf, "contains:bam:a", 9, 0); if (!ASSERT_EQ(id, 10, "btf__add_decl_tag contains:bam:a")) break; - id = btf__add_struct(btf, "bam", 16); + id = btf__add_struct(btf, "bam", 24); if (!ASSERT_EQ(id, 11, "btf__add_struct bam")) break; err = btf__add_field(btf, "a", LIST_NODE, 0, 0); diff --git a/tools/testing/selftests/bpf/prog_tests/local_kptr_stash.c b/tools/testing/selftests/bpf/prog_tests/local_kptr_stash.c index 76f1da877f81..b25b870f87ba 100644 --- a/tools/testing/selftests/bpf/prog_tests/local_kptr_stash.c +++ b/tools/testing/selftests/bpf/prog_tests/local_kptr_stash.c @@ -5,6 +5,7 @@ #include <network_helpers.h> #include "local_kptr_stash.skel.h" +#include "local_kptr_stash_fail.skel.h" static void test_local_kptr_stash_simple(void) { LIBBPF_OPTS(bpf_test_run_opts, opts, @@ -26,6 +27,27 @@ static void test_local_kptr_stash_simple(void) local_kptr_stash__destroy(skel); } +static void test_local_kptr_stash_plain(void) +{ + LIBBPF_OPTS(bpf_test_run_opts, opts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); + struct local_kptr_stash *skel; + int ret; + + skel = local_kptr_stash__open_and_load(); + if (!ASSERT_OK_PTR(skel, "local_kptr_stash__open_and_load")) + return; + + ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.stash_plain), &opts); + ASSERT_OK(ret, "local_kptr_stash_add_plain run"); + ASSERT_OK(opts.retval, "local_kptr_stash_add_plain retval"); + + local_kptr_stash__destroy(skel); +} + static void test_local_kptr_stash_unstash(void) { LIBBPF_OPTS(bpf_test_run_opts, opts, @@ -51,10 +73,19 @@ static void test_local_kptr_stash_unstash(void) local_kptr_stash__destroy(skel); } -void test_local_kptr_stash_success(void) +static void test_local_kptr_stash_fail(void) +{ + RUN_TESTS(local_kptr_stash_fail); +} + +void test_local_kptr_stash(void) { if (test__start_subtest("local_kptr_stash_simple")) test_local_kptr_stash_simple(); + if (test__start_subtest("local_kptr_stash_plain")) + test_local_kptr_stash_plain(); if (test__start_subtest("local_kptr_stash_unstash")) test_local_kptr_stash_unstash(); + if (test__start_subtest("local_kptr_stash_fail")) + test_local_kptr_stash_fail(); } diff --git a/tools/testing/selftests/bpf/prog_tests/log_fixup.c b/tools/testing/selftests/bpf/prog_tests/log_fixup.c index dba71d98a227..effd78b2a657 100644 --- a/tools/testing/selftests/bpf/prog_tests/log_fixup.c +++ b/tools/testing/selftests/bpf/prog_tests/log_fixup.c @@ -124,7 +124,7 @@ static void missing_map(void) ASSERT_FALSE(bpf_map__autocreate(skel->maps.missing_map), "missing_map_autocreate"); ASSERT_HAS_SUBSTR(log_buf, - "8: <invalid BPF map reference>\n" + ": <invalid BPF map reference>\n" "BPF map 'missing_map' is referenced but wasn't created\n", "log_buf"); diff --git a/tools/testing/selftests/bpf/prog_tests/lwt_helpers.h b/tools/testing/selftests/bpf/prog_tests/lwt_helpers.h new file mode 100644 index 000000000000..61333f2a03f9 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/lwt_helpers.h @@ -0,0 +1,139 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __LWT_HELPERS_H +#define __LWT_HELPERS_H + +#include <time.h> +#include <net/if.h> +#include <linux/if_tun.h> +#include <linux/icmp.h> + +#include "test_progs.h" + +#define log_err(MSG, ...) \ + fprintf(stderr, "(%s:%d: errno: %s) " MSG "\n", \ + __FILE__, __LINE__, strerror(errno), ##__VA_ARGS__) + +#define RUN_TEST(name) \ + ({ \ + if (test__start_subtest(#name)) \ + if (ASSERT_OK(netns_create(), "netns_create")) { \ + struct nstoken *token = open_netns(NETNS); \ + if (ASSERT_OK_PTR(token, "setns")) { \ + test_ ## name(); \ + close_netns(token); \ + } \ + netns_delete(); \ + } \ + }) + +#define NETNS "ns_lwt" + +static inline int netns_create(void) +{ + return system("ip netns add " NETNS); +} + +static inline int netns_delete(void) +{ + return system("ip netns del " NETNS ">/dev/null 2>&1"); +} + +static int open_tuntap(const char *dev_name, bool need_mac) +{ + int err = 0; + struct ifreq ifr; + int fd = open("/dev/net/tun", O_RDWR); + + if (!ASSERT_GT(fd, 0, "open(/dev/net/tun)")) + return -1; + + ifr.ifr_flags = IFF_NO_PI | (need_mac ? IFF_TAP : IFF_TUN); + memcpy(ifr.ifr_name, dev_name, IFNAMSIZ); + + err = ioctl(fd, TUNSETIFF, &ifr); + if (!ASSERT_OK(err, "ioctl(TUNSETIFF)")) { + close(fd); + return -1; + } + + err = fcntl(fd, F_SETFL, O_NONBLOCK); + if (!ASSERT_OK(err, "fcntl(O_NONBLOCK)")) { + close(fd); + return -1; + } + + return fd; +} + +#define ICMP_PAYLOAD_SIZE 100 + +/* Match an ICMP packet with payload len ICMP_PAYLOAD_SIZE */ +static int __expect_icmp_ipv4(char *buf, ssize_t len) +{ + struct iphdr *ip = (struct iphdr *)buf; + struct icmphdr *icmp = (struct icmphdr *)(ip + 1); + ssize_t min_header_len = sizeof(*ip) + sizeof(*icmp); + + if (len < min_header_len) + return -1; + + if (ip->protocol != IPPROTO_ICMP) + return -1; + + if (icmp->type != ICMP_ECHO) + return -1; + + return len == ICMP_PAYLOAD_SIZE + min_header_len; +} + +typedef int (*filter_t) (char *, ssize_t); + +/* wait_for_packet - wait for a packet that matches the filter + * + * @fd: tun fd/packet socket to read packet + * @filter: filter function, returning 1 if matches + * @timeout: timeout to wait for the packet + * + * Returns 1 if a matching packet is read, 0 if timeout expired, -1 on error. + */ +static int wait_for_packet(int fd, filter_t filter, struct timeval *timeout) +{ + char buf[4096]; + int max_retry = 5; /* in case we read some spurious packets */ + fd_set fds; + + FD_ZERO(&fds); + while (max_retry--) { + /* Linux modifies timeout arg... So make a copy */ + struct timeval copied_timeout = *timeout; + ssize_t ret = -1; + + FD_SET(fd, &fds); + + ret = select(1 + fd, &fds, NULL, NULL, &copied_timeout); + if (ret <= 0) { + if (errno == EINTR) + continue; + else if (errno == EAGAIN || ret == 0) + return 0; + + log_err("select failed"); + return -1; + } + + ret = read(fd, buf, sizeof(buf)); + + if (ret <= 0) { + log_err("read(dev): %ld", ret); + return -1; + } + + if (filter && filter(buf, ret) > 0) + return 1; + } + + return 0; +} + +#endif /* __LWT_HELPERS_H */ diff --git a/tools/testing/selftests/bpf/prog_tests/lwt_redirect.c b/tools/testing/selftests/bpf/prog_tests/lwt_redirect.c new file mode 100644 index 000000000000..59b38569f310 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/lwt_redirect.c @@ -0,0 +1,330 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause + +/* + * Test suite of lwt_xmit BPF programs that redirect packets + * The file tests focus not only if these programs work as expected normally, + * but also if they can handle abnormal situations gracefully. + * + * WARNING + * ------- + * This test suite may crash the kernel, thus should be run in a VM. + * + * Setup: + * --------- + * All tests are performed in a single netns. Two lwt encap routes are setup for + * each subtest: + * + * ip route add 10.0.0.0/24 encap bpf xmit <obj> sec "<ingress_sec>" dev link_err + * ip route add 20.0.0.0/24 encap bpf xmit <obj> sec "<egress_sec>" dev link_err + * + * Here <obj> is statically defined to test_lwt_redirect.bpf.o, and each section + * of this object holds a program entry to test. The BPF object is built from + * progs/test_lwt_redirect.c. We didn't use generated BPF skeleton since the + * attachment for lwt programs are not supported by libbpf yet. + * + * For testing, ping commands are run in the test netns: + * + * ping 10.0.0.<ifindex> -c 1 -w 1 -s 100 + * ping 20.0.0.<ifindex> -c 1 -w 1 -s 100 + * + * Scenarios: + * -------------------------------- + * 1. Redirect to a running tap/tun device + * 2. Redirect to a down tap/tun device + * 3. Redirect to a vlan device with lower layer down + * + * Case 1, ping packets should be received by packet socket on target device + * when redirected to ingress, and by tun/tap fd when redirected to egress. + * + * Case 2,3 are considered successful as long as they do not crash the kernel + * as a regression. + * + * Case 1,2 use tap device to test redirect to device that requires MAC + * header, and tun device to test the case with no MAC header added. + */ +#include <sys/socket.h> +#include <net/if.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/if_tun.h> +#include <linux/icmp.h> +#include <arpa/inet.h> +#include <unistd.h> +#include <errno.h> +#include <stdbool.h> +#include <stdlib.h> + +#include "lwt_helpers.h" +#include "test_progs.h" +#include "network_helpers.h" + +#define BPF_OBJECT "test_lwt_redirect.bpf.o" +#define INGRESS_SEC(need_mac) ((need_mac) ? "redir_ingress" : "redir_ingress_nomac") +#define EGRESS_SEC(need_mac) ((need_mac) ? "redir_egress" : "redir_egress_nomac") +#define LOCAL_SRC "10.0.0.1" +#define CIDR_TO_INGRESS "10.0.0.0/24" +#define CIDR_TO_EGRESS "20.0.0.0/24" + +/* ping to redirect toward given dev, with last byte of dest IP being the target + * device index. + * + * Note: ping command inside BPF-CI is busybox version, so it does not have certain + * function, such like -m option to set packet mark. + */ +static void ping_dev(const char *dev, bool is_ingress) +{ + int link_index = if_nametoindex(dev); + char ip[256]; + + if (!ASSERT_GE(link_index, 0, "if_nametoindex")) + return; + + if (is_ingress) + snprintf(ip, sizeof(ip), "10.0.0.%d", link_index); + else + snprintf(ip, sizeof(ip), "20.0.0.%d", link_index); + + /* We won't get a reply. Don't fail here */ + SYS_NOFAIL("ping %s -c1 -W1 -s %d >/dev/null 2>&1", + ip, ICMP_PAYLOAD_SIZE); +} + +static int new_packet_sock(const char *ifname) +{ + int err = 0; + int ignore_outgoing = 1; + int ifindex = -1; + int s = -1; + + s = socket(AF_PACKET, SOCK_RAW, 0); + if (!ASSERT_GE(s, 0, "socket(AF_PACKET)")) + return -1; + + ifindex = if_nametoindex(ifname); + if (!ASSERT_GE(ifindex, 0, "if_nametoindex")) { + close(s); + return -1; + } + + struct sockaddr_ll addr = { + .sll_family = AF_PACKET, + .sll_protocol = htons(ETH_P_IP), + .sll_ifindex = ifindex, + }; + + err = bind(s, (struct sockaddr *)&addr, sizeof(addr)); + if (!ASSERT_OK(err, "bind(AF_PACKET)")) { + close(s); + return -1; + } + + /* Use packet socket to capture only the ingress, so we can distinguish + * the case where a regression that actually redirects the packet to + * the egress. + */ + err = setsockopt(s, SOL_PACKET, PACKET_IGNORE_OUTGOING, + &ignore_outgoing, sizeof(ignore_outgoing)); + if (!ASSERT_OK(err, "setsockopt(PACKET_IGNORE_OUTGOING)")) { + close(s); + return -1; + } + + err = fcntl(s, F_SETFL, O_NONBLOCK); + if (!ASSERT_OK(err, "fcntl(O_NONBLOCK)")) { + close(s); + return -1; + } + + return s; +} + +static int expect_icmp(char *buf, ssize_t len) +{ + struct ethhdr *eth = (struct ethhdr *)buf; + + if (len < (ssize_t)sizeof(*eth)) + return -1; + + if (eth->h_proto == htons(ETH_P_IP)) + return __expect_icmp_ipv4((char *)(eth + 1), len - sizeof(*eth)); + + return -1; +} + +static int expect_icmp_nomac(char *buf, ssize_t len) +{ + return __expect_icmp_ipv4(buf, len); +} + +static void send_and_capture_test_packets(const char *test_name, int tap_fd, + const char *target_dev, bool need_mac) +{ + int psock = -1; + struct timeval timeo = { + .tv_sec = 0, + .tv_usec = 250000, + }; + int ret = -1; + + filter_t filter = need_mac ? expect_icmp : expect_icmp_nomac; + + ping_dev(target_dev, false); + + ret = wait_for_packet(tap_fd, filter, &timeo); + if (!ASSERT_EQ(ret, 1, "wait_for_epacket")) { + log_err("%s egress test fails", test_name); + goto out; + } + + psock = new_packet_sock(target_dev); + ping_dev(target_dev, true); + + ret = wait_for_packet(psock, filter, &timeo); + if (!ASSERT_EQ(ret, 1, "wait_for_ipacket")) { + log_err("%s ingress test fails", test_name); + goto out; + } + +out: + if (psock >= 0) + close(psock); +} + +static int setup_redirect_target(const char *target_dev, bool need_mac) +{ + int target_index = -1; + int tap_fd = -1; + + tap_fd = open_tuntap(target_dev, need_mac); + if (!ASSERT_GE(tap_fd, 0, "open_tuntap")) + goto fail; + + target_index = if_nametoindex(target_dev); + if (!ASSERT_GE(target_index, 0, "if_nametoindex")) + goto fail; + + SYS(fail, "ip link add link_err type dummy"); + SYS(fail, "ip link set lo up"); + SYS(fail, "ip addr add dev lo " LOCAL_SRC "/32"); + SYS(fail, "ip link set link_err up"); + SYS(fail, "ip link set %s up", target_dev); + + SYS(fail, "ip route add %s dev link_err encap bpf xmit obj %s sec %s", + CIDR_TO_INGRESS, BPF_OBJECT, INGRESS_SEC(need_mac)); + + SYS(fail, "ip route add %s dev link_err encap bpf xmit obj %s sec %s", + CIDR_TO_EGRESS, BPF_OBJECT, EGRESS_SEC(need_mac)); + + return tap_fd; + +fail: + if (tap_fd >= 0) + close(tap_fd); + return -1; +} + +static void test_lwt_redirect_normal(void) +{ + const char *target_dev = "tap0"; + int tap_fd = -1; + bool need_mac = true; + + tap_fd = setup_redirect_target(target_dev, need_mac); + if (!ASSERT_GE(tap_fd, 0, "setup_redirect_target")) + return; + + send_and_capture_test_packets(__func__, tap_fd, target_dev, need_mac); + close(tap_fd); +} + +static void test_lwt_redirect_normal_nomac(void) +{ + const char *target_dev = "tun0"; + int tap_fd = -1; + bool need_mac = false; + + tap_fd = setup_redirect_target(target_dev, need_mac); + if (!ASSERT_GE(tap_fd, 0, "setup_redirect_target")) + return; + + send_and_capture_test_packets(__func__, tap_fd, target_dev, need_mac); + close(tap_fd); +} + +/* This test aims to prevent regression of future. As long as the kernel does + * not panic, it is considered as success. + */ +static void __test_lwt_redirect_dev_down(bool need_mac) +{ + const char *target_dev = "tap0"; + int tap_fd = -1; + + tap_fd = setup_redirect_target(target_dev, need_mac); + if (!ASSERT_GE(tap_fd, 0, "setup_redirect_target")) + return; + + SYS(out, "ip link set %s down", target_dev); + ping_dev(target_dev, true); + ping_dev(target_dev, false); + +out: + close(tap_fd); +} + +static void test_lwt_redirect_dev_down(void) +{ + __test_lwt_redirect_dev_down(true); +} + +static void test_lwt_redirect_dev_down_nomac(void) +{ + __test_lwt_redirect_dev_down(false); +} + +/* This test aims to prevent regression of future. As long as the kernel does + * not panic, it is considered as success. + */ +static void test_lwt_redirect_dev_carrier_down(void) +{ + const char *lower_dev = "tap0"; + const char *vlan_dev = "vlan100"; + int tap_fd = -1; + + tap_fd = setup_redirect_target(lower_dev, true); + if (!ASSERT_GE(tap_fd, 0, "setup_redirect_target")) + return; + + SYS(out, "ip link add vlan100 link %s type vlan id 100", lower_dev); + SYS(out, "ip link set %s up", vlan_dev); + SYS(out, "ip link set %s down", lower_dev); + ping_dev(vlan_dev, true); + ping_dev(vlan_dev, false); + +out: + close(tap_fd); +} + +static void *test_lwt_redirect_run(void *arg) +{ + netns_delete(); + RUN_TEST(lwt_redirect_normal); + RUN_TEST(lwt_redirect_normal_nomac); + RUN_TEST(lwt_redirect_dev_down); + RUN_TEST(lwt_redirect_dev_down_nomac); + RUN_TEST(lwt_redirect_dev_carrier_down); + return NULL; +} + +void test_lwt_redirect(void) +{ + pthread_t test_thread; + int err; + + /* Run the tests in their own thread to isolate the namespace changes + * so they do not affect the environment of other tests. + * (specifically needed because of unshare(CLONE_NEWNS) in open_netns()) + */ + err = pthread_create(&test_thread, NULL, &test_lwt_redirect_run, NULL); + if (ASSERT_OK(err, "pthread_create")) + ASSERT_OK(pthread_join(test_thread, NULL), "pthread_join"); +} diff --git a/tools/testing/selftests/bpf/prog_tests/lwt_reroute.c b/tools/testing/selftests/bpf/prog_tests/lwt_reroute.c new file mode 100644 index 000000000000..f4bb2d5fcae0 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/lwt_reroute.c @@ -0,0 +1,262 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause + +/* + * Test suite of lwt BPF programs that reroutes packets + * The file tests focus not only if these programs work as expected normally, + * but also if they can handle abnormal situations gracefully. This test + * suite currently only covers lwt_xmit hook. lwt_in tests have not been + * implemented. + * + * WARNING + * ------- + * This test suite can crash the kernel, thus should be run in a VM. + * + * Setup: + * --------- + * all tests are performed in a single netns. A lwt encap route is setup for + * each subtest: + * + * ip route add 10.0.0.0/24 encap bpf xmit <obj> sec "<section_N>" dev link_err + * + * Here <obj> is statically defined to test_lwt_reroute.bpf.o, and it contains + * a single test program entry. This program sets packet mark by last byte of + * the IPv4 daddr. For example, a packet going to 1.2.3.4 will receive a skb + * mark 4. A packet will only be marked once, and IP x.x.x.0 will be skipped + * to avoid route loop. We didn't use generated BPF skeleton since the + * attachment for lwt programs are not supported by libbpf yet. + * + * The test program will bring up a tun device, and sets up the following + * routes: + * + * ip rule add pref 100 from all fwmark <tun_index> lookup 100 + * ip route add table 100 default dev tun0 + * + * For normal testing, a ping command is running in the test netns: + * + * ping 10.0.0.<tun_index> -c 1 -w 1 -s 100 + * + * For abnormal testing, fq is used as the qdisc of the tun device. Then a UDP + * socket will try to overflow the fq queue and trigger qdisc drop error. + * + * Scenarios: + * -------------------------------- + * 1. Reroute to a running tun device + * 2. Reroute to a device where qdisc drop + * + * For case 1, ping packets should be received by the tun device. + * + * For case 2, force UDP packets to overflow fq limit. As long as kernel + * is not crashed, it is considered successful. + */ +#include "lwt_helpers.h" +#include "network_helpers.h" +#include <linux/net_tstamp.h> + +#define BPF_OBJECT "test_lwt_reroute.bpf.o" +#define LOCAL_SRC "10.0.0.1" +#define TEST_CIDR "10.0.0.0/24" +#define XMIT_HOOK "xmit" +#define XMIT_SECTION "lwt_xmit" +#define NSEC_PER_SEC 1000000000ULL + +/* send a ping to be rerouted to the target device */ +static void ping_once(const char *ip) +{ + /* We won't get a reply. Don't fail here */ + SYS_NOFAIL("ping %s -c1 -W1 -s %d >/dev/null 2>&1", + ip, ICMP_PAYLOAD_SIZE); +} + +/* Send snd_target UDP packets to overflow the fq queue and trigger qdisc drop + * error. This is done via TX tstamp to force buffering delayed packets. + */ +static int overflow_fq(int snd_target, const char *target_ip) +{ + struct sockaddr_in addr = { + .sin_family = AF_INET, + .sin_port = htons(1234), + }; + + char data_buf[8]; /* only #pkts matter, so use a random small buffer */ + char control_buf[CMSG_SPACE(sizeof(uint64_t))]; + struct iovec iov = { + .iov_base = data_buf, + .iov_len = sizeof(data_buf), + }; + int err = -1; + int s = -1; + struct sock_txtime txtime_on = { + .clockid = CLOCK_MONOTONIC, + .flags = 0, + }; + struct msghdr msg = { + .msg_name = &addr, + .msg_namelen = sizeof(addr), + .msg_control = control_buf, + .msg_controllen = sizeof(control_buf), + .msg_iovlen = 1, + .msg_iov = &iov, + }; + struct cmsghdr *cmsg = CMSG_FIRSTHDR(&msg); + + memset(data_buf, 0, sizeof(data_buf)); + + s = socket(AF_INET, SOCK_DGRAM, 0); + if (!ASSERT_GE(s, 0, "socket")) + goto out; + + err = setsockopt(s, SOL_SOCKET, SO_TXTIME, &txtime_on, sizeof(txtime_on)); + if (!ASSERT_OK(err, "setsockopt(SO_TXTIME)")) + goto out; + + err = inet_pton(AF_INET, target_ip, &addr.sin_addr); + if (!ASSERT_EQ(err, 1, "inet_pton")) + goto out; + + while (snd_target > 0) { + struct timespec now; + + memset(control_buf, 0, sizeof(control_buf)); + cmsg->cmsg_type = SCM_TXTIME; + cmsg->cmsg_level = SOL_SOCKET; + cmsg->cmsg_len = CMSG_LEN(sizeof(uint64_t)); + + err = clock_gettime(CLOCK_MONOTONIC, &now); + if (!ASSERT_OK(err, "clock_gettime(CLOCK_MONOTONIC)")) { + err = -1; + goto out; + } + + *(uint64_t *)CMSG_DATA(cmsg) = (now.tv_nsec + 1) * NSEC_PER_SEC + + now.tv_nsec; + + /* we will intentionally send more than fq limit, so ignore + * the error here. + */ + sendmsg(s, &msg, MSG_NOSIGNAL); + snd_target--; + } + + /* no kernel crash so far is considered success */ + err = 0; + +out: + if (s >= 0) + close(s); + + return err; +} + +static int setup(const char *tun_dev) +{ + int target_index = -1; + int tap_fd = -1; + + tap_fd = open_tuntap(tun_dev, false); + if (!ASSERT_GE(tap_fd, 0, "open_tun")) + return -1; + + target_index = if_nametoindex(tun_dev); + if (!ASSERT_GE(target_index, 0, "if_nametoindex")) + return -1; + + SYS(fail, "ip link add link_err type dummy"); + SYS(fail, "ip link set lo up"); + SYS(fail, "ip addr add dev lo " LOCAL_SRC "/32"); + SYS(fail, "ip link set link_err up"); + SYS(fail, "ip link set %s up", tun_dev); + + SYS(fail, "ip route add %s dev link_err encap bpf xmit obj %s sec lwt_xmit", + TEST_CIDR, BPF_OBJECT); + + SYS(fail, "ip rule add pref 100 from all fwmark %d lookup 100", + target_index); + SYS(fail, "ip route add t 100 default dev %s", tun_dev); + + return tap_fd; + +fail: + if (tap_fd >= 0) + close(tap_fd); + return -1; +} + +static void test_lwt_reroute_normal_xmit(void) +{ + const char *tun_dev = "tun0"; + int tun_fd = -1; + int ifindex = -1; + char ip[256]; + struct timeval timeo = { + .tv_sec = 0, + .tv_usec = 250000, + }; + + tun_fd = setup(tun_dev); + if (!ASSERT_GE(tun_fd, 0, "setup_reroute")) + return; + + ifindex = if_nametoindex(tun_dev); + if (!ASSERT_GE(ifindex, 0, "if_nametoindex")) + return; + + snprintf(ip, 256, "10.0.0.%d", ifindex); + + /* ping packets should be received by the tun device */ + ping_once(ip); + + if (!ASSERT_EQ(wait_for_packet(tun_fd, __expect_icmp_ipv4, &timeo), 1, + "wait_for_packet")) + log_err("%s xmit", __func__); +} + +/* + * Test the failure case when the skb is dropped at the qdisc. This is a + * regression prevention at the xmit hook only. + */ +static void test_lwt_reroute_qdisc_dropped(void) +{ + const char *tun_dev = "tun0"; + int tun_fd = -1; + int ifindex = -1; + char ip[256]; + + tun_fd = setup(tun_dev); + if (!ASSERT_GE(tun_fd, 0, "setup_reroute")) + goto fail; + + SYS(fail, "tc qdisc replace dev %s root fq limit 5 flow_limit 5", tun_dev); + + ifindex = if_nametoindex(tun_dev); + if (!ASSERT_GE(ifindex, 0, "if_nametoindex")) + return; + + snprintf(ip, 256, "10.0.0.%d", ifindex); + ASSERT_EQ(overflow_fq(10, ip), 0, "overflow_fq"); + +fail: + if (tun_fd >= 0) + close(tun_fd); +} + +static void *test_lwt_reroute_run(void *arg) +{ + netns_delete(); + RUN_TEST(lwt_reroute_normal_xmit); + RUN_TEST(lwt_reroute_qdisc_dropped); + return NULL; +} + +void test_lwt_reroute(void) +{ + pthread_t test_thread; + int err; + + /* Run the tests in their own thread to isolate the namespace changes + * so they do not affect the environment of other tests. + * (specifically needed because of unshare(CLONE_NEWNS) in open_netns()) + */ + err = pthread_create(&test_thread, NULL, &test_lwt_reroute_run, NULL); + if (ASSERT_OK(err, "pthread_create")) + ASSERT_OK(pthread_join(test_thread, NULL), "pthread_join"); +} diff --git a/tools/testing/selftests/bpf/prog_tests/modify_return.c b/tools/testing/selftests/bpf/prog_tests/modify_return.c index 5d9955af6247..a70c99c2f8c8 100644 --- a/tools/testing/selftests/bpf/prog_tests/modify_return.c +++ b/tools/testing/selftests/bpf/prog_tests/modify_return.c @@ -41,6 +41,10 @@ static void run_test(__u32 input_retval, __u16 want_side_effect, __s16 want_ret) ASSERT_EQ(skel->bss->fexit_result, 1, "modify_return fexit_result"); ASSERT_EQ(skel->bss->fmod_ret_result, 1, "modify_return fmod_ret_result"); + ASSERT_EQ(skel->bss->fentry_result2, 1, "modify_return fentry_result2"); + ASSERT_EQ(skel->bss->fexit_result2, 1, "modify_return fexit_result2"); + ASSERT_EQ(skel->bss->fmod_ret_result2, 1, "modify_return fmod_ret_result2"); + cleanup: modify_return__destroy(skel); } @@ -49,9 +53,9 @@ cleanup: void serial_test_modify_return(void) { run_test(0 /* input_retval */, - 1 /* want_side_effect */, - 4 /* want_ret */); + 2 /* want_side_effect */, + 33 /* want_ret */); run_test(-EINVAL /* input_retval */, 0 /* want_side_effect */, - -EINVAL /* want_ret */); + -EINVAL * 2 /* want_ret */); } diff --git a/tools/testing/selftests/bpf/prog_tests/mptcp.c b/tools/testing/selftests/bpf/prog_tests/mptcp.c index cd0c42fff7c0..7c0be7cf550b 100644 --- a/tools/testing/selftests/bpf/prog_tests/mptcp.c +++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c @@ -2,17 +2,59 @@ /* Copyright (c) 2020, Tessares SA. */ /* Copyright (c) 2022, SUSE. */ +#include <linux/const.h> +#include <netinet/in.h> #include <test_progs.h> #include "cgroup_helpers.h" #include "network_helpers.h" #include "mptcp_sock.skel.h" +#include "mptcpify.skel.h" #define NS_TEST "mptcp_ns" +#ifndef IPPROTO_MPTCP +#define IPPROTO_MPTCP 262 +#endif + +#ifndef SOL_MPTCP +#define SOL_MPTCP 284 +#endif +#ifndef MPTCP_INFO +#define MPTCP_INFO 1 +#endif +#ifndef MPTCP_INFO_FLAG_FALLBACK +#define MPTCP_INFO_FLAG_FALLBACK _BITUL(0) +#endif +#ifndef MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED +#define MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED _BITUL(1) +#endif + #ifndef TCP_CA_NAME_MAX #define TCP_CA_NAME_MAX 16 #endif +struct __mptcp_info { + __u8 mptcpi_subflows; + __u8 mptcpi_add_addr_signal; + __u8 mptcpi_add_addr_accepted; + __u8 mptcpi_subflows_max; + __u8 mptcpi_add_addr_signal_max; + __u8 mptcpi_add_addr_accepted_max; + __u32 mptcpi_flags; + __u32 mptcpi_token; + __u64 mptcpi_write_seq; + __u64 mptcpi_snd_una; + __u64 mptcpi_rcv_nxt; + __u8 mptcpi_local_addr_used; + __u8 mptcpi_local_addr_max; + __u8 mptcpi_csum_enabled; + __u32 mptcpi_retransmits; + __u64 mptcpi_bytes_retrans; + __u64 mptcpi_bytes_sent; + __u64 mptcpi_bytes_received; + __u64 mptcpi_bytes_acked; +}; + struct mptcp_storage { __u32 invoked; __u32 is_mptcp; @@ -22,6 +64,24 @@ struct mptcp_storage { char ca_name[TCP_CA_NAME_MAX]; }; +static struct nstoken *create_netns(void) +{ + SYS(fail, "ip netns add %s", NS_TEST); + SYS(fail, "ip -net %s link set dev lo up", NS_TEST); + + return open_netns(NS_TEST); +fail: + return NULL; +} + +static void cleanup_netns(struct nstoken *nstoken) +{ + if (nstoken) + close_netns(nstoken); + + SYS_NOFAIL("ip netns del %s &> /dev/null", NS_TEST); +} + static int verify_tsk(int map_fd, int client_fd) { int err, cfd = client_fd; @@ -100,24 +160,14 @@ static int run_test(int cgroup_fd, int server_fd, bool is_mptcp) sock_skel = mptcp_sock__open_and_load(); if (!ASSERT_OK_PTR(sock_skel, "skel_open_load")) - return -EIO; + return libbpf_get_error(sock_skel); err = mptcp_sock__attach(sock_skel); if (!ASSERT_OK(err, "skel_attach")) goto out; prog_fd = bpf_program__fd(sock_skel->progs._sockops); - if (!ASSERT_GE(prog_fd, 0, "bpf_program__fd")) { - err = -EIO; - goto out; - } - map_fd = bpf_map__fd(sock_skel->maps.socket_storage_map); - if (!ASSERT_GE(map_fd, 0, "bpf_map__fd")) { - err = -EIO; - goto out; - } - err = bpf_prog_attach(prog_fd, cgroup_fd, BPF_CGROUP_SOCK_OPS, 0); if (!ASSERT_OK(err, "bpf_prog_attach")) goto out; @@ -147,11 +197,8 @@ static void test_base(void) if (!ASSERT_GE(cgroup_fd, 0, "test__join_cgroup")) return; - SYS(fail, "ip netns add %s", NS_TEST); - SYS(fail, "ip -net %s link set dev lo up", NS_TEST); - - nstoken = open_netns(NS_TEST); - if (!ASSERT_OK_PTR(nstoken, "open_netns")) + nstoken = create_netns(); + if (!ASSERT_OK_PTR(nstoken, "create_netns")) goto fail; /* without MPTCP */ @@ -174,11 +221,104 @@ with_mptcp: close(server_fd); fail: - if (nstoken) - close_netns(nstoken); + cleanup_netns(nstoken); + close(cgroup_fd); +} - SYS_NOFAIL("ip netns del " NS_TEST " &> /dev/null"); +static void send_byte(int fd) +{ + char b = 0x55; + + ASSERT_EQ(write(fd, &b, sizeof(b)), 1, "send single byte"); +} + +static int verify_mptcpify(int server_fd, int client_fd) +{ + struct __mptcp_info info; + socklen_t optlen; + int protocol; + int err = 0; + + optlen = sizeof(protocol); + if (!ASSERT_OK(getsockopt(server_fd, SOL_SOCKET, SO_PROTOCOL, &protocol, &optlen), + "getsockopt(SOL_PROTOCOL)")) + return -1; + + if (!ASSERT_EQ(protocol, IPPROTO_MPTCP, "protocol isn't MPTCP")) + err++; + optlen = sizeof(info); + if (!ASSERT_OK(getsockopt(client_fd, SOL_MPTCP, MPTCP_INFO, &info, &optlen), + "getsockopt(MPTCP_INFO)")) + return -1; + + if (!ASSERT_GE(info.mptcpi_flags, 0, "unexpected mptcpi_flags")) + err++; + if (!ASSERT_FALSE(info.mptcpi_flags & MPTCP_INFO_FLAG_FALLBACK, + "MPTCP fallback")) + err++; + if (!ASSERT_TRUE(info.mptcpi_flags & MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED, + "no remote key received")) + err++; + + return err; +} + +static int run_mptcpify(int cgroup_fd) +{ + int server_fd, client_fd, err = 0; + struct mptcpify *mptcpify_skel; + + mptcpify_skel = mptcpify__open_and_load(); + if (!ASSERT_OK_PTR(mptcpify_skel, "skel_open_load")) + return libbpf_get_error(mptcpify_skel); + + err = mptcpify__attach(mptcpify_skel); + if (!ASSERT_OK(err, "skel_attach")) + goto out; + + /* without MPTCP */ + server_fd = start_server(AF_INET, SOCK_STREAM, NULL, 0, 0); + if (!ASSERT_GE(server_fd, 0, "start_server")) { + err = -EIO; + goto out; + } + + client_fd = connect_to_fd(server_fd, 0); + if (!ASSERT_GE(client_fd, 0, "connect to fd")) { + err = -EIO; + goto close_server; + } + + send_byte(client_fd); + + err = verify_mptcpify(server_fd, client_fd); + + close(client_fd); +close_server: + close(server_fd); +out: + mptcpify__destroy(mptcpify_skel); + return err; +} + +static void test_mptcpify(void) +{ + struct nstoken *nstoken = NULL; + int cgroup_fd; + + cgroup_fd = test__join_cgroup("/mptcpify"); + if (!ASSERT_GE(cgroup_fd, 0, "test__join_cgroup")) + return; + + nstoken = create_netns(); + if (!ASSERT_OK_PTR(nstoken, "create_netns")) + goto fail; + + ASSERT_OK(run_mptcpify(cgroup_fd), "run_mptcpify"); + +fail: + cleanup_netns(nstoken); close(cgroup_fd); } @@ -186,4 +326,6 @@ void test_mptcp(void) { if (test__start_subtest("base")) test_base(); + if (test__start_subtest("mptcpify")) + test_mptcpify(); } diff --git a/tools/testing/selftests/bpf/prog_tests/netfilter_link_attach.c b/tools/testing/selftests/bpf/prog_tests/netfilter_link_attach.c new file mode 100644 index 000000000000..4297a2a4cb11 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/netfilter_link_attach.c @@ -0,0 +1,86 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#include <netinet/in.h> +#include <linux/netfilter.h> + +#include "test_progs.h" +#include "test_netfilter_link_attach.skel.h" + +struct nf_link_test { + __u32 pf; + __u32 hooknum; + __s32 priority; + __u32 flags; + + bool expect_success; + const char * const name; +}; + +static const struct nf_link_test nf_hook_link_tests[] = { + { .name = "allzero", }, + { .pf = NFPROTO_NUMPROTO, .name = "invalid-pf", }, + { .pf = NFPROTO_IPV4, .hooknum = 42, .name = "invalid-hooknum", }, + { .pf = NFPROTO_IPV4, .priority = INT_MIN, .name = "invalid-priority-min", }, + { .pf = NFPROTO_IPV4, .priority = INT_MAX, .name = "invalid-priority-max", }, + { .pf = NFPROTO_IPV4, .flags = UINT_MAX, .name = "invalid-flags", }, + + { .pf = NFPROTO_INET, .priority = 1, .name = "invalid-inet-not-supported", }, + + { .pf = NFPROTO_IPV4, .priority = -10000, .expect_success = true, .name = "attach ipv4", }, + { .pf = NFPROTO_IPV6, .priority = 10001, .expect_success = true, .name = "attach ipv6", }, +}; + +void test_netfilter_link_attach(void) +{ + struct test_netfilter_link_attach *skel; + struct bpf_program *prog; + LIBBPF_OPTS(bpf_netfilter_opts, opts); + int i; + + skel = test_netfilter_link_attach__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_netfilter_link_attach__open_and_load")) + goto out; + + prog = skel->progs.nf_link_attach_test; + if (!ASSERT_OK_PTR(prog, "attach program")) + goto out; + + for (i = 0; i < ARRAY_SIZE(nf_hook_link_tests); i++) { + struct bpf_link *link; + + if (!test__start_subtest(nf_hook_link_tests[i].name)) + continue; + +#define X(opts, m, i) opts.m = nf_hook_link_tests[(i)].m + X(opts, pf, i); + X(opts, hooknum, i); + X(opts, priority, i); + X(opts, flags, i); +#undef X + link = bpf_program__attach_netfilter(prog, &opts); + if (nf_hook_link_tests[i].expect_success) { + struct bpf_link *link2; + + if (!ASSERT_OK_PTR(link, "program attach successful")) + continue; + + link2 = bpf_program__attach_netfilter(prog, &opts); + ASSERT_ERR_PTR(link2, "attach program with same pf/hook/priority"); + + if (!ASSERT_OK(bpf_link__destroy(link), "link destroy")) + break; + + link2 = bpf_program__attach_netfilter(prog, &opts); + if (!ASSERT_OK_PTR(link2, "program reattach successful")) + continue; + if (!ASSERT_OK(bpf_link__destroy(link2), "link destroy")) + break; + } else { + ASSERT_ERR_PTR(link, "program load failure"); + } + } + +out: + test_netfilter_link_attach__destroy(skel); +} + diff --git a/tools/testing/selftests/bpf/prog_tests/ptr_untrusted.c b/tools/testing/selftests/bpf/prog_tests/ptr_untrusted.c new file mode 100644 index 000000000000..8d077d150c56 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/ptr_untrusted.c @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023 Yafang Shao <laoar.shao@gmail.com> */ + +#include <string.h> +#include <linux/bpf.h> +#include <test_progs.h> +#include "test_ptr_untrusted.skel.h" + +#define TP_NAME "sched_switch" + +void serial_test_ptr_untrusted(void) +{ + struct test_ptr_untrusted *skel; + int err; + + skel = test_ptr_untrusted__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + goto cleanup; + + /* First, attach lsm prog */ + skel->links.lsm_run = bpf_program__attach_lsm(skel->progs.lsm_run); + if (!ASSERT_OK_PTR(skel->links.lsm_run, "lsm_attach")) + goto cleanup; + + /* Second, attach raw_tp prog. The lsm prog will be triggered. */ + skel->links.raw_tp_run = bpf_program__attach_raw_tracepoint(skel->progs.raw_tp_run, + TP_NAME); + if (!ASSERT_OK_PTR(skel->links.raw_tp_run, "raw_tp_attach")) + goto cleanup; + + err = strncmp(skel->bss->tp_name, TP_NAME, strlen(TP_NAME)); + ASSERT_EQ(err, 0, "cmp_tp_name"); + +cleanup: + test_ptr_untrusted__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/refcounted_kptr.c b/tools/testing/selftests/bpf/prog_tests/refcounted_kptr.c index 595cbf92bff5..d6bd5e16e637 100644 --- a/tools/testing/selftests/bpf/prog_tests/refcounted_kptr.c +++ b/tools/testing/selftests/bpf/prog_tests/refcounted_kptr.c @@ -9,8 +9,38 @@ void test_refcounted_kptr(void) { + RUN_TESTS(refcounted_kptr); } void test_refcounted_kptr_fail(void) { + RUN_TESTS(refcounted_kptr_fail); +} + +void test_refcounted_kptr_wrong_owner(void) +{ + LIBBPF_OPTS(bpf_test_run_opts, opts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); + struct refcounted_kptr *skel; + int ret; + + skel = refcounted_kptr__open_and_load(); + if (!ASSERT_OK_PTR(skel, "refcounted_kptr__open_and_load")) + return; + + ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.rbtree_wrong_owner_remove_fail_a1), &opts); + ASSERT_OK(ret, "rbtree_wrong_owner_remove_fail_a1"); + ASSERT_OK(opts.retval, "rbtree_wrong_owner_remove_fail_a1 retval"); + + ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.rbtree_wrong_owner_remove_fail_b), &opts); + ASSERT_OK(ret, "rbtree_wrong_owner_remove_fail_b"); + ASSERT_OK(opts.retval, "rbtree_wrong_owner_remove_fail_b retval"); + + ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.rbtree_wrong_owner_remove_fail_a2), &opts); + ASSERT_OK(ret, "rbtree_wrong_owner_remove_fail_a2"); + ASSERT_OK(opts.retval, "rbtree_wrong_owner_remove_fail_a2 retval"); + refcounted_kptr__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/sk_storage_omem_uncharge.c b/tools/testing/selftests/bpf/prog_tests/sk_storage_omem_uncharge.c new file mode 100644 index 000000000000..f35852d245e3 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/sk_storage_omem_uncharge.c @@ -0,0 +1,56 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Facebook */ +#include <test_progs.h> +#include <bpf/libbpf.h> +#include <sys/types.h> +#include <sys/socket.h> +#include "sk_storage_omem_uncharge.skel.h" + +void test_sk_storage_omem_uncharge(void) +{ + struct sk_storage_omem_uncharge *skel; + int sk_fd = -1, map_fd, err, value; + socklen_t optlen; + + skel = sk_storage_omem_uncharge__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel open_and_load")) + return; + map_fd = bpf_map__fd(skel->maps.sk_storage); + + /* A standalone socket not binding to addr:port, + * so nentns is not needed. + */ + sk_fd = socket(AF_INET6, SOCK_STREAM, 0); + if (!ASSERT_GE(sk_fd, 0, "socket")) + goto done; + + optlen = sizeof(skel->bss->cookie); + err = getsockopt(sk_fd, SOL_SOCKET, SO_COOKIE, &skel->bss->cookie, &optlen); + if (!ASSERT_OK(err, "getsockopt(SO_COOKIE)")) + goto done; + + value = 0; + err = bpf_map_update_elem(map_fd, &sk_fd, &value, 0); + if (!ASSERT_OK(err, "bpf_map_update_elem(value=0)")) + goto done; + + value = 0xdeadbeef; + err = bpf_map_update_elem(map_fd, &sk_fd, &value, 0); + if (!ASSERT_OK(err, "bpf_map_update_elem(value=0xdeadbeef)")) + goto done; + + err = sk_storage_omem_uncharge__attach(skel); + if (!ASSERT_OK(err, "attach")) + goto done; + + close(sk_fd); + sk_fd = -1; + + ASSERT_EQ(skel->bss->cookie_found, 2, "cookie_found"); + ASSERT_EQ(skel->bss->omem, 0, "omem"); + +done: + sk_storage_omem_uncharge__destroy(skel); + if (sk_fd != -1) + close(sk_fd); +} diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h index d12665490a90..36d829a65aa4 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h @@ -179,6 +179,32 @@ __ret; \ }) +static inline int poll_connect(int fd, unsigned int timeout_sec) +{ + struct timeval timeout = { .tv_sec = timeout_sec }; + fd_set wfds; + int r, eval; + socklen_t esize = sizeof(eval); + + FD_ZERO(&wfds); + FD_SET(fd, &wfds); + + r = select(fd + 1, NULL, &wfds, NULL, &timeout); + if (r == 0) + errno = ETIME; + if (r != 1) + return -1; + + if (getsockopt(fd, SOL_SOCKET, SO_ERROR, &eval, &esize) < 0) + return -1; + if (eval != 0) { + errno = eval; + return -1; + } + + return 0; +} + static inline int poll_read(int fd, unsigned int timeout_sec) { struct timeval timeout = { .tv_sec = timeout_sec }; diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c index 5674a9d0cacf..8df8cbb447f1 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c @@ -1452,11 +1452,18 @@ static int vsock_socketpair_connectible(int sotype, int *v0, int *v1) if (p < 0) goto close_cli; + if (poll_connect(c, IO_TIMEOUT_SEC) < 0) { + FAIL_ERRNO("poll_connect"); + goto close_acc; + } + *v0 = p; *v1 = c; return 0; +close_acc: + close(p); close_cli: close(c); close_srv: diff --git a/tools/testing/selftests/bpf/prog_tests/spin_lock.c b/tools/testing/selftests/bpf/prog_tests/spin_lock.c index d9270bd3d920..f29c08d93beb 100644 --- a/tools/testing/selftests/bpf/prog_tests/spin_lock.c +++ b/tools/testing/selftests/bpf/prog_tests/spin_lock.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#include <regex.h> #include <test_progs.h> #include <network_helpers.h> @@ -19,12 +20,16 @@ static struct { "; R1_w=map_value(off=0,ks=4,vs=4,imm=0)\n2: (85) call bpf_this_cpu_ptr#154\n" "R1 type=map_value expected=percpu_ptr_" }, { "lock_id_mapval_preserve", - "8: (bf) r1 = r0 ; R0_w=map_value(id=1,off=0,ks=4,vs=8,imm=0) " - "R1_w=map_value(id=1,off=0,ks=4,vs=8,imm=0)\n9: (85) call bpf_this_cpu_ptr#154\n" + "[0-9]\\+: (bf) r1 = r0 ;" + " R0_w=map_value(id=1,off=0,ks=4,vs=8,imm=0)" + " R1_w=map_value(id=1,off=0,ks=4,vs=8,imm=0)\n" + "[0-9]\\+: (85) call bpf_this_cpu_ptr#154\n" "R1 type=map_value expected=percpu_ptr_" }, { "lock_id_innermapval_preserve", - "13: (bf) r1 = r0 ; R0=map_value(id=2,off=0,ks=4,vs=8,imm=0) " - "R1_w=map_value(id=2,off=0,ks=4,vs=8,imm=0)\n14: (85) call bpf_this_cpu_ptr#154\n" + "[0-9]\\+: (bf) r1 = r0 ;" + " R0=map_value(id=2,off=0,ks=4,vs=8,imm=0)" + " R1_w=map_value(id=2,off=0,ks=4,vs=8,imm=0)\n" + "[0-9]\\+: (85) call bpf_this_cpu_ptr#154\n" "R1 type=map_value expected=percpu_ptr_" }, { "lock_id_mismatch_kptr_kptr", "bpf_spin_unlock of different lock" }, { "lock_id_mismatch_kptr_global", "bpf_spin_unlock of different lock" }, @@ -45,6 +50,24 @@ static struct { { "lock_id_mismatch_innermapval_mapval", "bpf_spin_unlock of different lock" }, }; +static int match_regex(const char *pattern, const char *string) +{ + int err, rc; + regex_t re; + + err = regcomp(&re, pattern, REG_NOSUB); + if (err) { + char errbuf[512]; + + regerror(err, &re, errbuf, sizeof(errbuf)); + PRINT_FAIL("Can't compile regex: %s\n", errbuf); + return -1; + } + rc = regexec(&re, string, 0, NULL, 0); + regfree(&re); + return rc == 0 ? 1 : 0; +} + static void test_spin_lock_fail_prog(const char *prog_name, const char *err_msg) { LIBBPF_OPTS(bpf_object_open_opts, opts, .kernel_log_buf = log_buf, @@ -74,7 +97,11 @@ static void test_spin_lock_fail_prog(const char *prog_name, const char *err_msg) goto end; } - if (!ASSERT_OK_PTR(strstr(log_buf, err_msg), "expected error message")) { + ret = match_regex(err_msg, log_buf); + if (!ASSERT_GE(ret, 0, "match_regex")) + goto end; + + if (!ASSERT_TRUE(ret, "no match for expected error message")) { fprintf(stderr, "Expected: %s\n", err_msg); fprintf(stderr, "Verifier: %s\n", log_buf); } diff --git a/tools/testing/selftests/bpf/prog_tests/task_kfunc.c b/tools/testing/selftests/bpf/prog_tests/task_kfunc.c index 740d5f644b40..d4579f735398 100644 --- a/tools/testing/selftests/bpf/prog_tests/task_kfunc.c +++ b/tools/testing/selftests/bpf/prog_tests/task_kfunc.c @@ -79,6 +79,8 @@ static const char * const success_tests[] = { "test_task_from_pid_current", "test_task_from_pid_invalid", "task_kfunc_acquire_trusted_walked", + "test_task_kfunc_flavor_relo", + "test_task_kfunc_flavor_relo_not_found", }; void test_task_kfunc(void) diff --git a/tools/testing/selftests/bpf/prog_tests/tc_bpf.c b/tools/testing/selftests/bpf/prog_tests/tc_bpf.c index e873766276d1..48b55539331e 100644 --- a/tools/testing/selftests/bpf/prog_tests/tc_bpf.c +++ b/tools/testing/selftests/bpf/prog_tests/tc_bpf.c @@ -3,6 +3,7 @@ #include <test_progs.h> #include <linux/pkt_cls.h> +#include "cap_helpers.h" #include "test_tc_bpf.skel.h" #define LO_IFINDEX 1 @@ -327,7 +328,7 @@ static int test_tc_bpf_api(struct bpf_tc_hook *hook, int fd) return 0; } -void test_tc_bpf(void) +void tc_bpf_root(void) { DECLARE_LIBBPF_OPTS(bpf_tc_hook, hook, .ifindex = LO_IFINDEX, .attach_point = BPF_TC_INGRESS); @@ -393,3 +394,36 @@ end: } test_tc_bpf__destroy(skel); } + +void tc_bpf_non_root(void) +{ + struct test_tc_bpf *skel = NULL; + __u64 caps = 0; + int ret; + + /* In case CAP_BPF and CAP_PERFMON is not set */ + ret = cap_enable_effective(1ULL << CAP_BPF | 1ULL << CAP_NET_ADMIN, &caps); + if (!ASSERT_OK(ret, "set_cap_bpf_cap_net_admin")) + return; + ret = cap_disable_effective(1ULL << CAP_SYS_ADMIN | 1ULL << CAP_PERFMON, NULL); + if (!ASSERT_OK(ret, "disable_cap_sys_admin")) + goto restore_cap; + + skel = test_tc_bpf__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_tc_bpf__open_and_load")) + goto restore_cap; + + test_tc_bpf__destroy(skel); + +restore_cap: + if (caps) + cap_enable_effective(caps, NULL); +} + +void test_tc_bpf(void) +{ + if (test__start_subtest("tc_bpf_root")) + tc_bpf_root(); + if (test__start_subtest("tc_bpf_non_root")) + tc_bpf_non_root(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/tc_helpers.h b/tools/testing/selftests/bpf/prog_tests/tc_helpers.h new file mode 100644 index 000000000000..6c93215be8a3 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/tc_helpers.h @@ -0,0 +1,72 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2023 Isovalent */ +#ifndef TC_HELPERS +#define TC_HELPERS +#include <test_progs.h> + +static inline __u32 id_from_prog_fd(int fd) +{ + struct bpf_prog_info prog_info = {}; + __u32 prog_info_len = sizeof(prog_info); + int err; + + err = bpf_obj_get_info_by_fd(fd, &prog_info, &prog_info_len); + if (!ASSERT_OK(err, "id_from_prog_fd")) + return 0; + + ASSERT_NEQ(prog_info.id, 0, "prog_info.id"); + return prog_info.id; +} + +static inline __u32 id_from_link_fd(int fd) +{ + struct bpf_link_info link_info = {}; + __u32 link_info_len = sizeof(link_info); + int err; + + err = bpf_link_get_info_by_fd(fd, &link_info, &link_info_len); + if (!ASSERT_OK(err, "id_from_link_fd")) + return 0; + + ASSERT_NEQ(link_info.id, 0, "link_info.id"); + return link_info.id; +} + +static inline __u32 ifindex_from_link_fd(int fd) +{ + struct bpf_link_info link_info = {}; + __u32 link_info_len = sizeof(link_info); + int err; + + err = bpf_link_get_info_by_fd(fd, &link_info, &link_info_len); + if (!ASSERT_OK(err, "id_from_link_fd")) + return 0; + + return link_info.tcx.ifindex; +} + +static inline void __assert_mprog_count(int target, int expected, bool miniq, int ifindex) +{ + __u32 count = 0, attach_flags = 0; + int err; + + err = bpf_prog_query(ifindex, target, 0, &attach_flags, + NULL, &count); + ASSERT_EQ(count, expected, "count"); + if (!expected && !miniq) + ASSERT_EQ(err, -ENOENT, "prog_query"); + else + ASSERT_EQ(err, 0, "prog_query"); +} + +static inline void assert_mprog_count(int target, int expected) +{ + __assert_mprog_count(target, expected, false, loopback); +} + +static inline void assert_mprog_count_ifindex(int ifindex, int target, int expected) +{ + __assert_mprog_count(target, expected, false, ifindex); +} + +#endif /* TC_HELPERS */ diff --git a/tools/testing/selftests/bpf/prog_tests/tc_links.c b/tools/testing/selftests/bpf/prog_tests/tc_links.c new file mode 100644 index 000000000000..74fc1fe9ee26 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/tc_links.c @@ -0,0 +1,1919 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Isovalent */ +#include <uapi/linux/if_link.h> +#include <uapi/linux/pkt_sched.h> +#include <net/if.h> +#include <test_progs.h> + +#define loopback 1 +#define ping_cmd "ping -q -c1 -w1 127.0.0.1 > /dev/null" + +#include "test_tc_link.skel.h" +#include "tc_helpers.h" + +void serial_test_tc_links_basic(void) +{ + LIBBPF_OPTS(bpf_prog_query_opts, optq); + LIBBPF_OPTS(bpf_tcx_opts, optl); + __u32 prog_ids[2], link_ids[2]; + __u32 pid1, pid2, lid1, lid2; + struct test_tc_link *skel; + struct bpf_link *link; + int err; + + skel = test_tc_link__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_load")) + goto cleanup; + + pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1)); + pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2)); + + ASSERT_NEQ(pid1, pid2, "prog_ids_1_2"); + + assert_mprog_count(BPF_TCX_INGRESS, 0); + assert_mprog_count(BPF_TCX_EGRESS, 0); + + ASSERT_EQ(skel->bss->seen_tc1, false, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2"); + + link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc1 = link; + + lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1)); + + assert_mprog_count(BPF_TCX_INGRESS, 1); + assert_mprog_count(BPF_TCX_EGRESS, 0); + + optq.prog_ids = prog_ids; + optq.link_ids = link_ids; + + memset(prog_ids, 0, sizeof(prog_ids)); + memset(link_ids, 0, sizeof(link_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, BPF_TCX_INGRESS, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup; + + ASSERT_EQ(optq.count, 1, "count"); + ASSERT_EQ(optq.revision, 2, "revision"); + ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]"); + ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]"); + ASSERT_EQ(optq.link_ids[1], 0, "link_ids[1]"); + + ASSERT_OK(system(ping_cmd), ping_cmd); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2"); + + link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc2 = link; + + lid2 = id_from_link_fd(bpf_link__fd(skel->links.tc2)); + ASSERT_NEQ(lid1, lid2, "link_ids_1_2"); + + assert_mprog_count(BPF_TCX_INGRESS, 1); + assert_mprog_count(BPF_TCX_EGRESS, 1); + + memset(prog_ids, 0, sizeof(prog_ids)); + memset(link_ids, 0, sizeof(link_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, BPF_TCX_EGRESS, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup; + + ASSERT_EQ(optq.count, 1, "count"); + ASSERT_EQ(optq.revision, 2, "revision"); + ASSERT_EQ(optq.prog_ids[0], pid2, "prog_ids[0]"); + ASSERT_EQ(optq.link_ids[0], lid2, "link_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]"); + ASSERT_EQ(optq.link_ids[1], 0, "link_ids[1]"); + + ASSERT_OK(system(ping_cmd), ping_cmd); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2"); +cleanup: + test_tc_link__destroy(skel); + + assert_mprog_count(BPF_TCX_INGRESS, 0); + assert_mprog_count(BPF_TCX_EGRESS, 0); +} + +static void test_tc_links_before_target(int target) +{ + LIBBPF_OPTS(bpf_prog_query_opts, optq); + LIBBPF_OPTS(bpf_tcx_opts, optl); + __u32 prog_ids[5], link_ids[5]; + __u32 pid1, pid2, pid3, pid4; + __u32 lid1, lid2, lid3, lid4; + struct test_tc_link *skel; + struct bpf_link *link; + int err; + + skel = test_tc_link__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + goto cleanup; + + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, target), + 0, "tc1_attach_type"); + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, target), + 0, "tc2_attach_type"); + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc3, target), + 0, "tc3_attach_type"); + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc4, target), + 0, "tc4_attach_type"); + + err = test_tc_link__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto cleanup; + + pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1)); + pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2)); + pid3 = id_from_prog_fd(bpf_program__fd(skel->progs.tc3)); + pid4 = id_from_prog_fd(bpf_program__fd(skel->progs.tc4)); + + ASSERT_NEQ(pid1, pid2, "prog_ids_1_2"); + ASSERT_NEQ(pid3, pid4, "prog_ids_3_4"); + ASSERT_NEQ(pid2, pid3, "prog_ids_2_3"); + + assert_mprog_count(target, 0); + + link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc1 = link; + + lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1)); + + assert_mprog_count(target, 1); + + link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc2 = link; + + lid2 = id_from_link_fd(bpf_link__fd(skel->links.tc2)); + + assert_mprog_count(target, 2); + + optq.prog_ids = prog_ids; + optq.link_ids = link_ids; + + memset(prog_ids, 0, sizeof(prog_ids)); + memset(link_ids, 0, sizeof(link_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup; + + ASSERT_EQ(optq.count, 2, "count"); + ASSERT_EQ(optq.revision, 3, "revision"); + ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]"); + ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], pid2, "prog_ids[1]"); + ASSERT_EQ(optq.link_ids[1], lid2, "link_ids[1]"); + ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]"); + ASSERT_EQ(optq.link_ids[2], 0, "link_ids[2]"); + + ASSERT_OK(system(ping_cmd), ping_cmd); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2"); + ASSERT_EQ(skel->bss->seen_tc3, false, "seen_tc3"); + ASSERT_EQ(skel->bss->seen_tc4, false, "seen_tc4"); + + skel->bss->seen_tc1 = false; + skel->bss->seen_tc2 = false; + + LIBBPF_OPTS_RESET(optl, + .flags = BPF_F_BEFORE, + .relative_fd = bpf_program__fd(skel->progs.tc2), + ); + + link = bpf_program__attach_tcx(skel->progs.tc3, loopback, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc3 = link; + + lid3 = id_from_link_fd(bpf_link__fd(skel->links.tc3)); + + LIBBPF_OPTS_RESET(optl, + .flags = BPF_F_BEFORE | BPF_F_LINK, + .relative_id = lid1, + ); + + link = bpf_program__attach_tcx(skel->progs.tc4, loopback, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc4 = link; + + lid4 = id_from_link_fd(bpf_link__fd(skel->links.tc4)); + + assert_mprog_count(target, 4); + + memset(prog_ids, 0, sizeof(prog_ids)); + memset(link_ids, 0, sizeof(link_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup; + + ASSERT_EQ(optq.count, 4, "count"); + ASSERT_EQ(optq.revision, 5, "revision"); + ASSERT_EQ(optq.prog_ids[0], pid4, "prog_ids[0]"); + ASSERT_EQ(optq.link_ids[0], lid4, "link_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], pid1, "prog_ids[1]"); + ASSERT_EQ(optq.link_ids[1], lid1, "link_ids[1]"); + ASSERT_EQ(optq.prog_ids[2], pid3, "prog_ids[2]"); + ASSERT_EQ(optq.link_ids[2], lid3, "link_ids[2]"); + ASSERT_EQ(optq.prog_ids[3], pid2, "prog_ids[3]"); + ASSERT_EQ(optq.link_ids[3], lid2, "link_ids[3]"); + ASSERT_EQ(optq.prog_ids[4], 0, "prog_ids[4]"); + ASSERT_EQ(optq.link_ids[4], 0, "link_ids[4]"); + + ASSERT_OK(system(ping_cmd), ping_cmd); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2"); + ASSERT_EQ(skel->bss->seen_tc3, true, "seen_tc3"); + ASSERT_EQ(skel->bss->seen_tc4, true, "seen_tc4"); +cleanup: + test_tc_link__destroy(skel); + assert_mprog_count(target, 0); +} + +void serial_test_tc_links_before(void) +{ + test_tc_links_before_target(BPF_TCX_INGRESS); + test_tc_links_before_target(BPF_TCX_EGRESS); +} + +static void test_tc_links_after_target(int target) +{ + LIBBPF_OPTS(bpf_prog_query_opts, optq); + LIBBPF_OPTS(bpf_tcx_opts, optl); + __u32 prog_ids[5], link_ids[5]; + __u32 pid1, pid2, pid3, pid4; + __u32 lid1, lid2, lid3, lid4; + struct test_tc_link *skel; + struct bpf_link *link; + int err; + + skel = test_tc_link__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + goto cleanup; + + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, target), + 0, "tc1_attach_type"); + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, target), + 0, "tc2_attach_type"); + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc3, target), + 0, "tc3_attach_type"); + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc4, target), + 0, "tc4_attach_type"); + + err = test_tc_link__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto cleanup; + + pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1)); + pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2)); + pid3 = id_from_prog_fd(bpf_program__fd(skel->progs.tc3)); + pid4 = id_from_prog_fd(bpf_program__fd(skel->progs.tc4)); + + ASSERT_NEQ(pid1, pid2, "prog_ids_1_2"); + ASSERT_NEQ(pid3, pid4, "prog_ids_3_4"); + ASSERT_NEQ(pid2, pid3, "prog_ids_2_3"); + + assert_mprog_count(target, 0); + + link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc1 = link; + + lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1)); + + assert_mprog_count(target, 1); + + link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc2 = link; + + lid2 = id_from_link_fd(bpf_link__fd(skel->links.tc2)); + + assert_mprog_count(target, 2); + + optq.prog_ids = prog_ids; + optq.link_ids = link_ids; + + memset(prog_ids, 0, sizeof(prog_ids)); + memset(link_ids, 0, sizeof(link_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup; + + ASSERT_EQ(optq.count, 2, "count"); + ASSERT_EQ(optq.revision, 3, "revision"); + ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]"); + ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], pid2, "prog_ids[1]"); + ASSERT_EQ(optq.link_ids[1], lid2, "link_ids[1]"); + ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]"); + ASSERT_EQ(optq.link_ids[2], 0, "link_ids[2]"); + + ASSERT_OK(system(ping_cmd), ping_cmd); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2"); + ASSERT_EQ(skel->bss->seen_tc3, false, "seen_tc3"); + ASSERT_EQ(skel->bss->seen_tc4, false, "seen_tc4"); + + skel->bss->seen_tc1 = false; + skel->bss->seen_tc2 = false; + + LIBBPF_OPTS_RESET(optl, + .flags = BPF_F_AFTER, + .relative_fd = bpf_program__fd(skel->progs.tc1), + ); + + link = bpf_program__attach_tcx(skel->progs.tc3, loopback, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc3 = link; + + lid3 = id_from_link_fd(bpf_link__fd(skel->links.tc3)); + + LIBBPF_OPTS_RESET(optl, + .flags = BPF_F_AFTER | BPF_F_LINK, + .relative_fd = bpf_link__fd(skel->links.tc2), + ); + + link = bpf_program__attach_tcx(skel->progs.tc4, loopback, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc4 = link; + + lid4 = id_from_link_fd(bpf_link__fd(skel->links.tc4)); + + assert_mprog_count(target, 4); + + memset(prog_ids, 0, sizeof(prog_ids)); + memset(link_ids, 0, sizeof(link_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup; + + ASSERT_EQ(optq.count, 4, "count"); + ASSERT_EQ(optq.revision, 5, "revision"); + ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]"); + ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], pid3, "prog_ids[1]"); + ASSERT_EQ(optq.link_ids[1], lid3, "link_ids[1]"); + ASSERT_EQ(optq.prog_ids[2], pid2, "prog_ids[2]"); + ASSERT_EQ(optq.link_ids[2], lid2, "link_ids[2]"); + ASSERT_EQ(optq.prog_ids[3], pid4, "prog_ids[3]"); + ASSERT_EQ(optq.link_ids[3], lid4, "link_ids[3]"); + ASSERT_EQ(optq.prog_ids[4], 0, "prog_ids[4]"); + ASSERT_EQ(optq.link_ids[4], 0, "link_ids[4]"); + + ASSERT_OK(system(ping_cmd), ping_cmd); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2"); + ASSERT_EQ(skel->bss->seen_tc3, true, "seen_tc3"); + ASSERT_EQ(skel->bss->seen_tc4, true, "seen_tc4"); +cleanup: + test_tc_link__destroy(skel); + assert_mprog_count(target, 0); +} + +void serial_test_tc_links_after(void) +{ + test_tc_links_after_target(BPF_TCX_INGRESS); + test_tc_links_after_target(BPF_TCX_EGRESS); +} + +static void test_tc_links_revision_target(int target) +{ + LIBBPF_OPTS(bpf_prog_query_opts, optq); + LIBBPF_OPTS(bpf_tcx_opts, optl); + __u32 prog_ids[3], link_ids[3]; + __u32 pid1, pid2, lid1, lid2; + struct test_tc_link *skel; + struct bpf_link *link; + int err; + + skel = test_tc_link__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + goto cleanup; + + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, target), + 0, "tc1_attach_type"); + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, target), + 0, "tc2_attach_type"); + + err = test_tc_link__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto cleanup; + + pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1)); + pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2)); + + ASSERT_NEQ(pid1, pid2, "prog_ids_1_2"); + + assert_mprog_count(target, 0); + + optl.expected_revision = 1; + + link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc1 = link; + + lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1)); + + assert_mprog_count(target, 1); + + optl.expected_revision = 1; + + link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl); + if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) { + bpf_link__destroy(link); + goto cleanup; + } + + assert_mprog_count(target, 1); + + optl.expected_revision = 2; + + link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc2 = link; + + lid2 = id_from_link_fd(bpf_link__fd(skel->links.tc2)); + + assert_mprog_count(target, 2); + + optq.prog_ids = prog_ids; + optq.link_ids = link_ids; + + memset(prog_ids, 0, sizeof(prog_ids)); + memset(link_ids, 0, sizeof(link_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup; + + ASSERT_EQ(optq.count, 2, "count"); + ASSERT_EQ(optq.revision, 3, "revision"); + ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]"); + ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], pid2, "prog_ids[1]"); + ASSERT_EQ(optq.link_ids[1], lid2, "link_ids[1]"); + ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]"); + ASSERT_EQ(optq.link_ids[2], 0, "prog_ids[2]"); + + ASSERT_OK(system(ping_cmd), ping_cmd); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2"); +cleanup: + test_tc_link__destroy(skel); + assert_mprog_count(target, 0); +} + +void serial_test_tc_links_revision(void) +{ + test_tc_links_revision_target(BPF_TCX_INGRESS); + test_tc_links_revision_target(BPF_TCX_EGRESS); +} + +static void test_tc_chain_classic(int target, bool chain_tc_old) +{ + LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1); + LIBBPF_OPTS(bpf_tc_hook, tc_hook, .ifindex = loopback); + bool hook_created = false, tc_attached = false; + LIBBPF_OPTS(bpf_tcx_opts, optl); + __u32 pid1, pid2, pid3; + struct test_tc_link *skel; + struct bpf_link *link; + int err; + + skel = test_tc_link__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + goto cleanup; + + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, target), + 0, "tc1_attach_type"); + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, target), + 0, "tc2_attach_type"); + + err = test_tc_link__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto cleanup; + + pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1)); + pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2)); + pid3 = id_from_prog_fd(bpf_program__fd(skel->progs.tc3)); + + ASSERT_NEQ(pid1, pid2, "prog_ids_1_2"); + ASSERT_NEQ(pid2, pid3, "prog_ids_2_3"); + + assert_mprog_count(target, 0); + + if (chain_tc_old) { + tc_hook.attach_point = target == BPF_TCX_INGRESS ? + BPF_TC_INGRESS : BPF_TC_EGRESS; + err = bpf_tc_hook_create(&tc_hook); + if (err == 0) + hook_created = true; + err = err == -EEXIST ? 0 : err; + if (!ASSERT_OK(err, "bpf_tc_hook_create")) + goto cleanup; + + tc_opts.prog_fd = bpf_program__fd(skel->progs.tc3); + err = bpf_tc_attach(&tc_hook, &tc_opts); + if (!ASSERT_OK(err, "bpf_tc_attach")) + goto cleanup; + tc_attached = true; + } + + link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc1 = link; + + link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc2 = link; + + assert_mprog_count(target, 2); + + ASSERT_OK(system(ping_cmd), ping_cmd); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2"); + ASSERT_EQ(skel->bss->seen_tc3, chain_tc_old, "seen_tc3"); + + skel->bss->seen_tc1 = false; + skel->bss->seen_tc2 = false; + skel->bss->seen_tc3 = false; + + err = bpf_link__detach(skel->links.tc2); + if (!ASSERT_OK(err, "prog_detach")) + goto cleanup; + + assert_mprog_count(target, 1); + + ASSERT_OK(system(ping_cmd), ping_cmd); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2"); + ASSERT_EQ(skel->bss->seen_tc3, chain_tc_old, "seen_tc3"); +cleanup: + if (tc_attached) { + tc_opts.flags = tc_opts.prog_fd = tc_opts.prog_id = 0; + err = bpf_tc_detach(&tc_hook, &tc_opts); + ASSERT_OK(err, "bpf_tc_detach"); + } + if (hook_created) { + tc_hook.attach_point = BPF_TC_INGRESS | BPF_TC_EGRESS; + bpf_tc_hook_destroy(&tc_hook); + } + assert_mprog_count(target, 1); + test_tc_link__destroy(skel); + assert_mprog_count(target, 0); +} + +void serial_test_tc_links_chain_classic(void) +{ + test_tc_chain_classic(BPF_TCX_INGRESS, false); + test_tc_chain_classic(BPF_TCX_EGRESS, false); + test_tc_chain_classic(BPF_TCX_INGRESS, true); + test_tc_chain_classic(BPF_TCX_EGRESS, true); +} + +static void test_tc_links_replace_target(int target) +{ + LIBBPF_OPTS(bpf_prog_query_opts, optq); + LIBBPF_OPTS(bpf_tcx_opts, optl); + __u32 pid1, pid2, pid3, lid1, lid2; + __u32 prog_ids[4], link_ids[4]; + struct test_tc_link *skel; + struct bpf_link *link; + int err; + + skel = test_tc_link__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + goto cleanup; + + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, target), + 0, "tc1_attach_type"); + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, target), + 0, "tc2_attach_type"); + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc3, target), + 0, "tc3_attach_type"); + + err = test_tc_link__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto cleanup; + + pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1)); + pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2)); + pid3 = id_from_prog_fd(bpf_program__fd(skel->progs.tc3)); + + ASSERT_NEQ(pid1, pid2, "prog_ids_1_2"); + ASSERT_NEQ(pid2, pid3, "prog_ids_2_3"); + + assert_mprog_count(target, 0); + + optl.expected_revision = 1; + + link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc1 = link; + + lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1)); + + assert_mprog_count(target, 1); + + LIBBPF_OPTS_RESET(optl, + .flags = BPF_F_BEFORE, + .relative_id = pid1, + .expected_revision = 2, + ); + + link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc2 = link; + + lid2 = id_from_link_fd(bpf_link__fd(skel->links.tc2)); + + assert_mprog_count(target, 2); + + optq.prog_ids = prog_ids; + optq.link_ids = link_ids; + + memset(prog_ids, 0, sizeof(prog_ids)); + memset(link_ids, 0, sizeof(link_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup; + + ASSERT_EQ(optq.count, 2, "count"); + ASSERT_EQ(optq.revision, 3, "revision"); + ASSERT_EQ(optq.prog_ids[0], pid2, "prog_ids[0]"); + ASSERT_EQ(optq.link_ids[0], lid2, "link_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], pid1, "prog_ids[1]"); + ASSERT_EQ(optq.link_ids[1], lid1, "link_ids[1]"); + ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]"); + ASSERT_EQ(optq.link_ids[2], 0, "link_ids[2]"); + + ASSERT_OK(system(ping_cmd), ping_cmd); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2"); + ASSERT_EQ(skel->bss->seen_tc3, false, "seen_tc3"); + + skel->bss->seen_tc1 = false; + skel->bss->seen_tc2 = false; + skel->bss->seen_tc3 = false; + + LIBBPF_OPTS_RESET(optl, + .flags = BPF_F_REPLACE, + .relative_fd = bpf_program__fd(skel->progs.tc2), + .expected_revision = 3, + ); + + link = bpf_program__attach_tcx(skel->progs.tc3, loopback, &optl); + if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) { + bpf_link__destroy(link); + goto cleanup; + } + + assert_mprog_count(target, 2); + + LIBBPF_OPTS_RESET(optl, + .flags = BPF_F_REPLACE | BPF_F_LINK, + .relative_fd = bpf_link__fd(skel->links.tc2), + .expected_revision = 3, + ); + + link = bpf_program__attach_tcx(skel->progs.tc3, loopback, &optl); + if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) { + bpf_link__destroy(link); + goto cleanup; + } + + assert_mprog_count(target, 2); + + LIBBPF_OPTS_RESET(optl, + .flags = BPF_F_REPLACE | BPF_F_LINK | BPF_F_AFTER, + .relative_id = lid2, + ); + + link = bpf_program__attach_tcx(skel->progs.tc3, loopback, &optl); + if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) { + bpf_link__destroy(link); + goto cleanup; + } + + assert_mprog_count(target, 2); + + err = bpf_link__update_program(skel->links.tc2, skel->progs.tc3); + if (!ASSERT_OK(err, "link_update")) + goto cleanup; + + assert_mprog_count(target, 2); + + memset(prog_ids, 0, sizeof(prog_ids)); + memset(link_ids, 0, sizeof(link_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup; + + ASSERT_EQ(optq.count, 2, "count"); + ASSERT_EQ(optq.revision, 4, "revision"); + ASSERT_EQ(optq.prog_ids[0], pid3, "prog_ids[0]"); + ASSERT_EQ(optq.link_ids[0], lid2, "link_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], pid1, "prog_ids[1]"); + ASSERT_EQ(optq.link_ids[1], lid1, "link_ids[1]"); + ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]"); + ASSERT_EQ(optq.link_ids[2], 0, "link_ids[2]"); + + ASSERT_OK(system(ping_cmd), ping_cmd); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2"); + ASSERT_EQ(skel->bss->seen_tc3, true, "seen_tc3"); + + skel->bss->seen_tc1 = false; + skel->bss->seen_tc2 = false; + skel->bss->seen_tc3 = false; + + err = bpf_link__detach(skel->links.tc2); + if (!ASSERT_OK(err, "link_detach")) + goto cleanup; + + assert_mprog_count(target, 1); + + memset(prog_ids, 0, sizeof(prog_ids)); + memset(link_ids, 0, sizeof(link_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup; + + ASSERT_EQ(optq.count, 1, "count"); + ASSERT_EQ(optq.revision, 5, "revision"); + ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]"); + ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]"); + ASSERT_EQ(optq.link_ids[1], 0, "link_ids[1]"); + + ASSERT_OK(system(ping_cmd), ping_cmd); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2"); + ASSERT_EQ(skel->bss->seen_tc3, false, "seen_tc3"); + + skel->bss->seen_tc1 = false; + skel->bss->seen_tc2 = false; + skel->bss->seen_tc3 = false; + + err = bpf_link__update_program(skel->links.tc1, skel->progs.tc1); + if (!ASSERT_OK(err, "link_update_self")) + goto cleanup; + + assert_mprog_count(target, 1); + + memset(prog_ids, 0, sizeof(prog_ids)); + memset(link_ids, 0, sizeof(link_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup; + + ASSERT_EQ(optq.count, 1, "count"); + ASSERT_EQ(optq.revision, 5, "revision"); + ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]"); + ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]"); + ASSERT_EQ(optq.link_ids[1], 0, "link_ids[1]"); + + ASSERT_OK(system(ping_cmd), ping_cmd); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2"); + ASSERT_EQ(skel->bss->seen_tc3, false, "seen_tc3"); +cleanup: + test_tc_link__destroy(skel); + assert_mprog_count(target, 0); +} + +void serial_test_tc_links_replace(void) +{ + test_tc_links_replace_target(BPF_TCX_INGRESS); + test_tc_links_replace_target(BPF_TCX_EGRESS); +} + +static void test_tc_links_invalid_target(int target) +{ + LIBBPF_OPTS(bpf_prog_query_opts, optq); + LIBBPF_OPTS(bpf_tcx_opts, optl); + __u32 pid1, pid2, lid1; + struct test_tc_link *skel; + struct bpf_link *link; + int err; + + skel = test_tc_link__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + goto cleanup; + + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, target), + 0, "tc1_attach_type"); + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, target), + 0, "tc2_attach_type"); + + err = test_tc_link__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto cleanup; + + pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1)); + pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2)); + + ASSERT_NEQ(pid1, pid2, "prog_ids_1_2"); + + assert_mprog_count(target, 0); + + optl.flags = BPF_F_BEFORE | BPF_F_AFTER; + + link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl); + if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) { + bpf_link__destroy(link); + goto cleanup; + } + + assert_mprog_count(target, 0); + + LIBBPF_OPTS_RESET(optl, + .flags = BPF_F_BEFORE | BPF_F_ID, + ); + + link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl); + if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) { + bpf_link__destroy(link); + goto cleanup; + } + + assert_mprog_count(target, 0); + + LIBBPF_OPTS_RESET(optl, + .flags = BPF_F_AFTER | BPF_F_ID, + ); + + link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl); + if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) { + bpf_link__destroy(link); + goto cleanup; + } + + assert_mprog_count(target, 0); + + LIBBPF_OPTS_RESET(optl, + .flags = BPF_F_ID, + ); + + link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl); + if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) { + bpf_link__destroy(link); + goto cleanup; + } + + assert_mprog_count(target, 0); + + LIBBPF_OPTS_RESET(optl, + .flags = BPF_F_LINK, + .relative_fd = bpf_program__fd(skel->progs.tc2), + ); + + link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl); + if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) { + bpf_link__destroy(link); + goto cleanup; + } + + assert_mprog_count(target, 0); + + LIBBPF_OPTS_RESET(optl, + .flags = BPF_F_LINK, + ); + + link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl); + if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) { + bpf_link__destroy(link); + goto cleanup; + } + + assert_mprog_count(target, 0); + + LIBBPF_OPTS_RESET(optl, + .relative_fd = bpf_program__fd(skel->progs.tc2), + ); + + link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl); + if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) { + bpf_link__destroy(link); + goto cleanup; + } + + assert_mprog_count(target, 0); + + LIBBPF_OPTS_RESET(optl, + .flags = BPF_F_BEFORE | BPF_F_AFTER, + .relative_fd = bpf_program__fd(skel->progs.tc2), + ); + + link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl); + if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) { + bpf_link__destroy(link); + goto cleanup; + } + + assert_mprog_count(target, 0); + + LIBBPF_OPTS_RESET(optl, + .flags = BPF_F_BEFORE, + .relative_fd = bpf_program__fd(skel->progs.tc1), + ); + + link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl); + if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) { + bpf_link__destroy(link); + goto cleanup; + } + + assert_mprog_count(target, 0); + + LIBBPF_OPTS_RESET(optl, + .flags = BPF_F_ID, + .relative_id = pid2, + ); + + link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl); + if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) { + bpf_link__destroy(link); + goto cleanup; + } + + assert_mprog_count(target, 0); + + LIBBPF_OPTS_RESET(optl, + .flags = BPF_F_ID, + .relative_id = 42, + ); + + link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl); + if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) { + bpf_link__destroy(link); + goto cleanup; + } + + assert_mprog_count(target, 0); + + LIBBPF_OPTS_RESET(optl, + .flags = BPF_F_BEFORE, + .relative_fd = bpf_program__fd(skel->progs.tc1), + ); + + link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl); + if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) { + bpf_link__destroy(link); + goto cleanup; + } + + assert_mprog_count(target, 0); + + LIBBPF_OPTS_RESET(optl, + .flags = BPF_F_BEFORE | BPF_F_LINK, + .relative_fd = bpf_program__fd(skel->progs.tc1), + ); + + link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl); + if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) { + bpf_link__destroy(link); + goto cleanup; + } + + assert_mprog_count(target, 0); + + LIBBPF_OPTS_RESET(optl, + .flags = BPF_F_AFTER, + .relative_fd = bpf_program__fd(skel->progs.tc1), + ); + + link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl); + if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) { + bpf_link__destroy(link); + goto cleanup; + } + + assert_mprog_count(target, 0); + + LIBBPF_OPTS_RESET(optl); + + link = bpf_program__attach_tcx(skel->progs.tc1, 0, &optl); + if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) { + bpf_link__destroy(link); + goto cleanup; + } + + assert_mprog_count(target, 0); + + LIBBPF_OPTS_RESET(optl, + .flags = BPF_F_AFTER | BPF_F_LINK, + .relative_fd = bpf_program__fd(skel->progs.tc1), + ); + + link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl); + if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) { + bpf_link__destroy(link); + goto cleanup; + } + + assert_mprog_count(target, 0); + + LIBBPF_OPTS_RESET(optl); + + link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc1 = link; + + lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1)); + + assert_mprog_count(target, 1); + + LIBBPF_OPTS_RESET(optl, + .flags = BPF_F_AFTER | BPF_F_LINK, + .relative_fd = bpf_program__fd(skel->progs.tc1), + ); + + link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl); + if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) { + bpf_link__destroy(link); + goto cleanup; + } + + assert_mprog_count(target, 1); + + LIBBPF_OPTS_RESET(optl, + .flags = BPF_F_BEFORE | BPF_F_LINK | BPF_F_ID, + .relative_id = ~0, + ); + + link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl); + if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) { + bpf_link__destroy(link); + goto cleanup; + } + + assert_mprog_count(target, 1); + + LIBBPF_OPTS_RESET(optl, + .flags = BPF_F_BEFORE | BPF_F_LINK | BPF_F_ID, + .relative_id = lid1, + ); + + link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl); + if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) { + bpf_link__destroy(link); + goto cleanup; + } + + assert_mprog_count(target, 1); + + LIBBPF_OPTS_RESET(optl, + .flags = BPF_F_BEFORE | BPF_F_ID, + .relative_id = pid1, + ); + + link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl); + if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) { + bpf_link__destroy(link); + goto cleanup; + } + assert_mprog_count(target, 1); + + LIBBPF_OPTS_RESET(optl, + .flags = BPF_F_BEFORE | BPF_F_LINK | BPF_F_ID, + .relative_id = lid1, + ); + + link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc2 = link; + + assert_mprog_count(target, 2); +cleanup: + test_tc_link__destroy(skel); + assert_mprog_count(target, 0); +} + +void serial_test_tc_links_invalid(void) +{ + test_tc_links_invalid_target(BPF_TCX_INGRESS); + test_tc_links_invalid_target(BPF_TCX_EGRESS); +} + +static void test_tc_links_prepend_target(int target) +{ + LIBBPF_OPTS(bpf_prog_query_opts, optq); + LIBBPF_OPTS(bpf_tcx_opts, optl); + __u32 prog_ids[5], link_ids[5]; + __u32 pid1, pid2, pid3, pid4; + __u32 lid1, lid2, lid3, lid4; + struct test_tc_link *skel; + struct bpf_link *link; + int err; + + skel = test_tc_link__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + goto cleanup; + + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, target), + 0, "tc1_attach_type"); + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, target), + 0, "tc2_attach_type"); + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc3, target), + 0, "tc3_attach_type"); + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc4, target), + 0, "tc4_attach_type"); + + err = test_tc_link__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto cleanup; + + pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1)); + pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2)); + pid3 = id_from_prog_fd(bpf_program__fd(skel->progs.tc3)); + pid4 = id_from_prog_fd(bpf_program__fd(skel->progs.tc4)); + + ASSERT_NEQ(pid1, pid2, "prog_ids_1_2"); + ASSERT_NEQ(pid3, pid4, "prog_ids_3_4"); + ASSERT_NEQ(pid2, pid3, "prog_ids_2_3"); + + assert_mprog_count(target, 0); + + link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc1 = link; + + lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1)); + + assert_mprog_count(target, 1); + + LIBBPF_OPTS_RESET(optl, + .flags = BPF_F_BEFORE, + ); + + link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc2 = link; + + lid2 = id_from_link_fd(bpf_link__fd(skel->links.tc2)); + + assert_mprog_count(target, 2); + + optq.prog_ids = prog_ids; + optq.link_ids = link_ids; + + memset(prog_ids, 0, sizeof(prog_ids)); + memset(link_ids, 0, sizeof(link_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup; + + ASSERT_EQ(optq.count, 2, "count"); + ASSERT_EQ(optq.revision, 3, "revision"); + ASSERT_EQ(optq.prog_ids[0], pid2, "prog_ids[0]"); + ASSERT_EQ(optq.link_ids[0], lid2, "link_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], pid1, "prog_ids[1]"); + ASSERT_EQ(optq.link_ids[1], lid1, "link_ids[1]"); + ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]"); + ASSERT_EQ(optq.link_ids[2], 0, "link_ids[2]"); + + ASSERT_OK(system(ping_cmd), ping_cmd); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2"); + ASSERT_EQ(skel->bss->seen_tc3, false, "seen_tc3"); + ASSERT_EQ(skel->bss->seen_tc4, false, "seen_tc4"); + + skel->bss->seen_tc1 = false; + skel->bss->seen_tc2 = false; + + LIBBPF_OPTS_RESET(optl, + .flags = BPF_F_BEFORE, + ); + + link = bpf_program__attach_tcx(skel->progs.tc3, loopback, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc3 = link; + + lid3 = id_from_link_fd(bpf_link__fd(skel->links.tc3)); + + LIBBPF_OPTS_RESET(optl, + .flags = BPF_F_BEFORE, + ); + + link = bpf_program__attach_tcx(skel->progs.tc4, loopback, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc4 = link; + + lid4 = id_from_link_fd(bpf_link__fd(skel->links.tc4)); + + assert_mprog_count(target, 4); + + memset(prog_ids, 0, sizeof(prog_ids)); + memset(link_ids, 0, sizeof(link_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup; + + ASSERT_EQ(optq.count, 4, "count"); + ASSERT_EQ(optq.revision, 5, "revision"); + ASSERT_EQ(optq.prog_ids[0], pid4, "prog_ids[0]"); + ASSERT_EQ(optq.link_ids[0], lid4, "link_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], pid3, "prog_ids[1]"); + ASSERT_EQ(optq.link_ids[1], lid3, "link_ids[1]"); + ASSERT_EQ(optq.prog_ids[2], pid2, "prog_ids[2]"); + ASSERT_EQ(optq.link_ids[2], lid2, "link_ids[2]"); + ASSERT_EQ(optq.prog_ids[3], pid1, "prog_ids[3]"); + ASSERT_EQ(optq.link_ids[3], lid1, "link_ids[3]"); + ASSERT_EQ(optq.prog_ids[4], 0, "prog_ids[4]"); + ASSERT_EQ(optq.link_ids[4], 0, "link_ids[4]"); + + ASSERT_OK(system(ping_cmd), ping_cmd); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2"); + ASSERT_EQ(skel->bss->seen_tc3, true, "seen_tc3"); + ASSERT_EQ(skel->bss->seen_tc4, true, "seen_tc4"); +cleanup: + test_tc_link__destroy(skel); + assert_mprog_count(target, 0); +} + +void serial_test_tc_links_prepend(void) +{ + test_tc_links_prepend_target(BPF_TCX_INGRESS); + test_tc_links_prepend_target(BPF_TCX_EGRESS); +} + +static void test_tc_links_append_target(int target) +{ + LIBBPF_OPTS(bpf_prog_query_opts, optq); + LIBBPF_OPTS(bpf_tcx_opts, optl); + __u32 prog_ids[5], link_ids[5]; + __u32 pid1, pid2, pid3, pid4; + __u32 lid1, lid2, lid3, lid4; + struct test_tc_link *skel; + struct bpf_link *link; + int err; + + skel = test_tc_link__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + goto cleanup; + + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, target), + 0, "tc1_attach_type"); + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, target), + 0, "tc2_attach_type"); + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc3, target), + 0, "tc3_attach_type"); + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc4, target), + 0, "tc4_attach_type"); + + err = test_tc_link__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto cleanup; + + pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1)); + pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2)); + pid3 = id_from_prog_fd(bpf_program__fd(skel->progs.tc3)); + pid4 = id_from_prog_fd(bpf_program__fd(skel->progs.tc4)); + + ASSERT_NEQ(pid1, pid2, "prog_ids_1_2"); + ASSERT_NEQ(pid3, pid4, "prog_ids_3_4"); + ASSERT_NEQ(pid2, pid3, "prog_ids_2_3"); + + assert_mprog_count(target, 0); + + link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc1 = link; + + lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1)); + + assert_mprog_count(target, 1); + + LIBBPF_OPTS_RESET(optl, + .flags = BPF_F_AFTER, + ); + + link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc2 = link; + + lid2 = id_from_link_fd(bpf_link__fd(skel->links.tc2)); + + assert_mprog_count(target, 2); + + optq.prog_ids = prog_ids; + optq.link_ids = link_ids; + + memset(prog_ids, 0, sizeof(prog_ids)); + memset(link_ids, 0, sizeof(link_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup; + + ASSERT_EQ(optq.count, 2, "count"); + ASSERT_EQ(optq.revision, 3, "revision"); + ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]"); + ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], pid2, "prog_ids[1]"); + ASSERT_EQ(optq.link_ids[1], lid2, "link_ids[1]"); + ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]"); + ASSERT_EQ(optq.link_ids[2], 0, "link_ids[2]"); + + ASSERT_OK(system(ping_cmd), ping_cmd); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2"); + ASSERT_EQ(skel->bss->seen_tc3, false, "seen_tc3"); + ASSERT_EQ(skel->bss->seen_tc4, false, "seen_tc4"); + + skel->bss->seen_tc1 = false; + skel->bss->seen_tc2 = false; + + LIBBPF_OPTS_RESET(optl, + .flags = BPF_F_AFTER, + ); + + link = bpf_program__attach_tcx(skel->progs.tc3, loopback, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc3 = link; + + lid3 = id_from_link_fd(bpf_link__fd(skel->links.tc3)); + + LIBBPF_OPTS_RESET(optl, + .flags = BPF_F_AFTER, + ); + + link = bpf_program__attach_tcx(skel->progs.tc4, loopback, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc4 = link; + + lid4 = id_from_link_fd(bpf_link__fd(skel->links.tc4)); + + assert_mprog_count(target, 4); + + memset(prog_ids, 0, sizeof(prog_ids)); + memset(link_ids, 0, sizeof(link_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup; + + ASSERT_EQ(optq.count, 4, "count"); + ASSERT_EQ(optq.revision, 5, "revision"); + ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]"); + ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], pid2, "prog_ids[1]"); + ASSERT_EQ(optq.link_ids[1], lid2, "link_ids[1]"); + ASSERT_EQ(optq.prog_ids[2], pid3, "prog_ids[2]"); + ASSERT_EQ(optq.link_ids[2], lid3, "link_ids[2]"); + ASSERT_EQ(optq.prog_ids[3], pid4, "prog_ids[3]"); + ASSERT_EQ(optq.link_ids[3], lid4, "link_ids[3]"); + ASSERT_EQ(optq.prog_ids[4], 0, "prog_ids[4]"); + ASSERT_EQ(optq.link_ids[4], 0, "link_ids[4]"); + + ASSERT_OK(system(ping_cmd), ping_cmd); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2"); + ASSERT_EQ(skel->bss->seen_tc3, true, "seen_tc3"); + ASSERT_EQ(skel->bss->seen_tc4, true, "seen_tc4"); +cleanup: + test_tc_link__destroy(skel); + assert_mprog_count(target, 0); +} + +void serial_test_tc_links_append(void) +{ + test_tc_links_append_target(BPF_TCX_INGRESS); + test_tc_links_append_target(BPF_TCX_EGRESS); +} + +static void test_tc_links_dev_cleanup_target(int target) +{ + LIBBPF_OPTS(bpf_tcx_opts, optl); + LIBBPF_OPTS(bpf_prog_query_opts, optq); + __u32 pid1, pid2, pid3, pid4; + struct test_tc_link *skel; + struct bpf_link *link; + int err, ifindex; + + ASSERT_OK(system("ip link add dev tcx_opts1 type veth peer name tcx_opts2"), "add veth"); + ifindex = if_nametoindex("tcx_opts1"); + ASSERT_NEQ(ifindex, 0, "non_zero_ifindex"); + + skel = test_tc_link__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + goto cleanup; + + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, target), + 0, "tc1_attach_type"); + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, target), + 0, "tc2_attach_type"); + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc3, target), + 0, "tc3_attach_type"); + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc4, target), + 0, "tc4_attach_type"); + + err = test_tc_link__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto cleanup; + + pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1)); + pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2)); + pid3 = id_from_prog_fd(bpf_program__fd(skel->progs.tc3)); + pid4 = id_from_prog_fd(bpf_program__fd(skel->progs.tc4)); + + ASSERT_NEQ(pid1, pid2, "prog_ids_1_2"); + ASSERT_NEQ(pid3, pid4, "prog_ids_3_4"); + ASSERT_NEQ(pid2, pid3, "prog_ids_2_3"); + + assert_mprog_count(target, 0); + + link = bpf_program__attach_tcx(skel->progs.tc1, ifindex, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc1 = link; + + assert_mprog_count_ifindex(ifindex, target, 1); + + link = bpf_program__attach_tcx(skel->progs.tc2, ifindex, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc2 = link; + + assert_mprog_count_ifindex(ifindex, target, 2); + + link = bpf_program__attach_tcx(skel->progs.tc3, ifindex, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc3 = link; + + assert_mprog_count_ifindex(ifindex, target, 3); + + link = bpf_program__attach_tcx(skel->progs.tc4, ifindex, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc4 = link; + + assert_mprog_count_ifindex(ifindex, target, 4); + + ASSERT_OK(system("ip link del dev tcx_opts1"), "del veth"); + ASSERT_EQ(if_nametoindex("tcx_opts1"), 0, "dev1_removed"); + ASSERT_EQ(if_nametoindex("tcx_opts2"), 0, "dev2_removed"); + + ASSERT_EQ(ifindex_from_link_fd(bpf_link__fd(skel->links.tc1)), 0, "tc1_ifindex"); + ASSERT_EQ(ifindex_from_link_fd(bpf_link__fd(skel->links.tc2)), 0, "tc2_ifindex"); + ASSERT_EQ(ifindex_from_link_fd(bpf_link__fd(skel->links.tc3)), 0, "tc3_ifindex"); + ASSERT_EQ(ifindex_from_link_fd(bpf_link__fd(skel->links.tc4)), 0, "tc4_ifindex"); + + test_tc_link__destroy(skel); + return; +cleanup: + test_tc_link__destroy(skel); + + ASSERT_OK(system("ip link del dev tcx_opts1"), "del veth"); + ASSERT_EQ(if_nametoindex("tcx_opts1"), 0, "dev1_removed"); + ASSERT_EQ(if_nametoindex("tcx_opts2"), 0, "dev2_removed"); +} + +void serial_test_tc_links_dev_cleanup(void) +{ + test_tc_links_dev_cleanup_target(BPF_TCX_INGRESS); + test_tc_links_dev_cleanup_target(BPF_TCX_EGRESS); +} + +static void test_tc_chain_mixed(int target) +{ + LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1); + LIBBPF_OPTS(bpf_tc_hook, tc_hook, .ifindex = loopback); + LIBBPF_OPTS(bpf_tcx_opts, optl); + struct test_tc_link *skel; + struct bpf_link *link; + __u32 pid1, pid2, pid3; + int err; + + skel = test_tc_link__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + goto cleanup; + + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc4, target), + 0, "tc4_attach_type"); + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc5, target), + 0, "tc5_attach_type"); + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc6, target), + 0, "tc6_attach_type"); + + err = test_tc_link__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto cleanup; + + pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc4)); + pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc5)); + pid3 = id_from_prog_fd(bpf_program__fd(skel->progs.tc6)); + + ASSERT_NEQ(pid1, pid2, "prog_ids_1_2"); + ASSERT_NEQ(pid2, pid3, "prog_ids_2_3"); + + assert_mprog_count(target, 0); + + tc_hook.attach_point = target == BPF_TCX_INGRESS ? + BPF_TC_INGRESS : BPF_TC_EGRESS; + err = bpf_tc_hook_create(&tc_hook); + err = err == -EEXIST ? 0 : err; + if (!ASSERT_OK(err, "bpf_tc_hook_create")) + goto cleanup; + + tc_opts.prog_fd = bpf_program__fd(skel->progs.tc5); + err = bpf_tc_attach(&tc_hook, &tc_opts); + if (!ASSERT_OK(err, "bpf_tc_attach")) + goto cleanup; + + link = bpf_program__attach_tcx(skel->progs.tc6, loopback, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc6 = link; + + assert_mprog_count(target, 1); + + ASSERT_OK(system(ping_cmd), ping_cmd); + + ASSERT_EQ(skel->bss->seen_tc4, false, "seen_tc4"); + ASSERT_EQ(skel->bss->seen_tc5, false, "seen_tc5"); + ASSERT_EQ(skel->bss->seen_tc6, true, "seen_tc6"); + + skel->bss->seen_tc4 = false; + skel->bss->seen_tc5 = false; + skel->bss->seen_tc6 = false; + + err = bpf_link__update_program(skel->links.tc6, skel->progs.tc4); + if (!ASSERT_OK(err, "link_update")) + goto cleanup; + + assert_mprog_count(target, 1); + + ASSERT_OK(system(ping_cmd), ping_cmd); + + ASSERT_EQ(skel->bss->seen_tc4, true, "seen_tc4"); + ASSERT_EQ(skel->bss->seen_tc5, true, "seen_tc5"); + ASSERT_EQ(skel->bss->seen_tc6, false, "seen_tc6"); + + skel->bss->seen_tc4 = false; + skel->bss->seen_tc5 = false; + skel->bss->seen_tc6 = false; + + err = bpf_link__detach(skel->links.tc6); + if (!ASSERT_OK(err, "prog_detach")) + goto cleanup; + + __assert_mprog_count(target, 0, true, loopback); + + ASSERT_OK(system(ping_cmd), ping_cmd); + + ASSERT_EQ(skel->bss->seen_tc4, false, "seen_tc4"); + ASSERT_EQ(skel->bss->seen_tc5, true, "seen_tc5"); + ASSERT_EQ(skel->bss->seen_tc6, false, "seen_tc6"); + +cleanup: + tc_opts.flags = tc_opts.prog_fd = tc_opts.prog_id = 0; + err = bpf_tc_detach(&tc_hook, &tc_opts); + ASSERT_OK(err, "bpf_tc_detach"); + + tc_hook.attach_point = BPF_TC_INGRESS | BPF_TC_EGRESS; + bpf_tc_hook_destroy(&tc_hook); + + test_tc_link__destroy(skel); +} + +void serial_test_tc_links_chain_mixed(void) +{ + test_tc_chain_mixed(BPF_TCX_INGRESS); + test_tc_chain_mixed(BPF_TCX_EGRESS); +} + +static void test_tc_links_ingress(int target, bool chain_tc_old, + bool tcx_teardown_first) +{ + LIBBPF_OPTS(bpf_tc_opts, tc_opts, + .handle = 1, + .priority = 1, + ); + LIBBPF_OPTS(bpf_tc_hook, tc_hook, + .ifindex = loopback, + .attach_point = BPF_TC_CUSTOM, + .parent = TC_H_INGRESS, + ); + bool hook_created = false, tc_attached = false; + LIBBPF_OPTS(bpf_tcx_opts, optl); + __u32 pid1, pid2, pid3; + struct test_tc_link *skel; + struct bpf_link *link; + int err; + + skel = test_tc_link__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + goto cleanup; + + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, target), + 0, "tc1_attach_type"); + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, target), + 0, "tc2_attach_type"); + + err = test_tc_link__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto cleanup; + + pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1)); + pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2)); + pid3 = id_from_prog_fd(bpf_program__fd(skel->progs.tc3)); + + ASSERT_NEQ(pid1, pid2, "prog_ids_1_2"); + ASSERT_NEQ(pid2, pid3, "prog_ids_2_3"); + + assert_mprog_count(target, 0); + + if (chain_tc_old) { + ASSERT_OK(system("tc qdisc add dev lo ingress"), "add_ingress"); + hook_created = true; + + tc_opts.prog_fd = bpf_program__fd(skel->progs.tc3); + err = bpf_tc_attach(&tc_hook, &tc_opts); + if (!ASSERT_OK(err, "bpf_tc_attach")) + goto cleanup; + tc_attached = true; + } + + link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc1 = link; + + link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc2 = link; + + assert_mprog_count(target, 2); + + ASSERT_OK(system(ping_cmd), ping_cmd); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2"); + ASSERT_EQ(skel->bss->seen_tc3, chain_tc_old, "seen_tc3"); + + skel->bss->seen_tc1 = false; + skel->bss->seen_tc2 = false; + skel->bss->seen_tc3 = false; + + err = bpf_link__detach(skel->links.tc2); + if (!ASSERT_OK(err, "prog_detach")) + goto cleanup; + + assert_mprog_count(target, 1); + + ASSERT_OK(system(ping_cmd), ping_cmd); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2"); + ASSERT_EQ(skel->bss->seen_tc3, chain_tc_old, "seen_tc3"); +cleanup: + if (tc_attached) { + tc_opts.flags = tc_opts.prog_fd = tc_opts.prog_id = 0; + err = bpf_tc_detach(&tc_hook, &tc_opts); + ASSERT_OK(err, "bpf_tc_detach"); + } + ASSERT_OK(system(ping_cmd), ping_cmd); + assert_mprog_count(target, 1); + if (hook_created && tcx_teardown_first) + ASSERT_OK(system("tc qdisc del dev lo ingress"), "del_ingress"); + ASSERT_OK(system(ping_cmd), ping_cmd); + test_tc_link__destroy(skel); + ASSERT_OK(system(ping_cmd), ping_cmd); + if (hook_created && !tcx_teardown_first) + ASSERT_OK(system("tc qdisc del dev lo ingress"), "del_ingress"); + ASSERT_OK(system(ping_cmd), ping_cmd); + assert_mprog_count(target, 0); +} + +void serial_test_tc_links_ingress(void) +{ + test_tc_links_ingress(BPF_TCX_INGRESS, true, true); + test_tc_links_ingress(BPF_TCX_INGRESS, true, false); + test_tc_links_ingress(BPF_TCX_INGRESS, false, false); +} + +static void test_tc_links_dev_mixed(int target) +{ + LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1); + LIBBPF_OPTS(bpf_tc_hook, tc_hook); + LIBBPF_OPTS(bpf_tcx_opts, optl); + __u32 pid1, pid2, pid3, pid4; + struct test_tc_link *skel; + struct bpf_link *link; + int err, ifindex; + + ASSERT_OK(system("ip link add dev tcx_opts1 type veth peer name tcx_opts2"), "add veth"); + ifindex = if_nametoindex("tcx_opts1"); + ASSERT_NEQ(ifindex, 0, "non_zero_ifindex"); + + skel = test_tc_link__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + goto cleanup; + + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, target), + 0, "tc1_attach_type"); + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, target), + 0, "tc2_attach_type"); + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc3, target), + 0, "tc3_attach_type"); + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc4, target), + 0, "tc4_attach_type"); + + err = test_tc_link__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto cleanup; + + pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1)); + pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2)); + pid3 = id_from_prog_fd(bpf_program__fd(skel->progs.tc3)); + pid4 = id_from_prog_fd(bpf_program__fd(skel->progs.tc4)); + + ASSERT_NEQ(pid1, pid2, "prog_ids_1_2"); + ASSERT_NEQ(pid3, pid4, "prog_ids_3_4"); + ASSERT_NEQ(pid2, pid3, "prog_ids_2_3"); + + assert_mprog_count(target, 0); + + link = bpf_program__attach_tcx(skel->progs.tc1, ifindex, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc1 = link; + + assert_mprog_count_ifindex(ifindex, target, 1); + + link = bpf_program__attach_tcx(skel->progs.tc2, ifindex, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc2 = link; + + assert_mprog_count_ifindex(ifindex, target, 2); + + link = bpf_program__attach_tcx(skel->progs.tc3, ifindex, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc3 = link; + + assert_mprog_count_ifindex(ifindex, target, 3); + + link = bpf_program__attach_tcx(skel->progs.tc4, ifindex, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc4 = link; + + assert_mprog_count_ifindex(ifindex, target, 4); + + tc_hook.ifindex = ifindex; + tc_hook.attach_point = target == BPF_TCX_INGRESS ? + BPF_TC_INGRESS : BPF_TC_EGRESS; + + err = bpf_tc_hook_create(&tc_hook); + err = err == -EEXIST ? 0 : err; + if (!ASSERT_OK(err, "bpf_tc_hook_create")) + goto cleanup; + + tc_opts.prog_fd = bpf_program__fd(skel->progs.tc5); + err = bpf_tc_attach(&tc_hook, &tc_opts); + if (!ASSERT_OK(err, "bpf_tc_attach")) + goto cleanup; + + ASSERT_OK(system("ip link del dev tcx_opts1"), "del veth"); + ASSERT_EQ(if_nametoindex("tcx_opts1"), 0, "dev1_removed"); + ASSERT_EQ(if_nametoindex("tcx_opts2"), 0, "dev2_removed"); + + ASSERT_EQ(ifindex_from_link_fd(bpf_link__fd(skel->links.tc1)), 0, "tc1_ifindex"); + ASSERT_EQ(ifindex_from_link_fd(bpf_link__fd(skel->links.tc2)), 0, "tc2_ifindex"); + ASSERT_EQ(ifindex_from_link_fd(bpf_link__fd(skel->links.tc3)), 0, "tc3_ifindex"); + ASSERT_EQ(ifindex_from_link_fd(bpf_link__fd(skel->links.tc4)), 0, "tc4_ifindex"); + + test_tc_link__destroy(skel); + return; +cleanup: + test_tc_link__destroy(skel); + + ASSERT_OK(system("ip link del dev tcx_opts1"), "del veth"); + ASSERT_EQ(if_nametoindex("tcx_opts1"), 0, "dev1_removed"); + ASSERT_EQ(if_nametoindex("tcx_opts2"), 0, "dev2_removed"); +} + +void serial_test_tc_links_dev_mixed(void) +{ + test_tc_links_dev_mixed(BPF_TCX_INGRESS); + test_tc_links_dev_mixed(BPF_TCX_EGRESS); +} diff --git a/tools/testing/selftests/bpf/prog_tests/tc_opts.c b/tools/testing/selftests/bpf/prog_tests/tc_opts.c new file mode 100644 index 000000000000..7a2ecd4eca5d --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/tc_opts.c @@ -0,0 +1,2380 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Isovalent */ +#include <uapi/linux/if_link.h> +#include <net/if.h> +#include <test_progs.h> + +#define loopback 1 +#define ping_cmd "ping -q -c1 -w1 127.0.0.1 > /dev/null" + +#include "test_tc_link.skel.h" +#include "tc_helpers.h" + +void serial_test_tc_opts_basic(void) +{ + LIBBPF_OPTS(bpf_prog_attach_opts, opta); + LIBBPF_OPTS(bpf_prog_detach_opts, optd); + LIBBPF_OPTS(bpf_prog_query_opts, optq); + __u32 fd1, fd2, id1, id2; + struct test_tc_link *skel; + __u32 prog_ids[2]; + int err; + + skel = test_tc_link__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_load")) + goto cleanup; + + fd1 = bpf_program__fd(skel->progs.tc1); + fd2 = bpf_program__fd(skel->progs.tc2); + + id1 = id_from_prog_fd(fd1); + id2 = id_from_prog_fd(fd2); + + ASSERT_NEQ(id1, id2, "prog_ids_1_2"); + + assert_mprog_count(BPF_TCX_INGRESS, 0); + assert_mprog_count(BPF_TCX_EGRESS, 0); + + ASSERT_EQ(skel->bss->seen_tc1, false, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2"); + + err = bpf_prog_attach_opts(fd1, loopback, BPF_TCX_INGRESS, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup; + + assert_mprog_count(BPF_TCX_INGRESS, 1); + assert_mprog_count(BPF_TCX_EGRESS, 0); + + optq.prog_ids = prog_ids; + + memset(prog_ids, 0, sizeof(prog_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, BPF_TCX_INGRESS, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup_in; + + ASSERT_EQ(optq.count, 1, "count"); + ASSERT_EQ(optq.revision, 2, "revision"); + ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]"); + + ASSERT_OK(system(ping_cmd), ping_cmd); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2"); + + err = bpf_prog_attach_opts(fd2, loopback, BPF_TCX_EGRESS, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup_in; + + assert_mprog_count(BPF_TCX_INGRESS, 1); + assert_mprog_count(BPF_TCX_EGRESS, 1); + + memset(prog_ids, 0, sizeof(prog_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, BPF_TCX_EGRESS, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup_eg; + + ASSERT_EQ(optq.count, 1, "count"); + ASSERT_EQ(optq.revision, 2, "revision"); + ASSERT_EQ(optq.prog_ids[0], id2, "prog_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]"); + + ASSERT_OK(system(ping_cmd), ping_cmd); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2"); + +cleanup_eg: + err = bpf_prog_detach_opts(fd2, loopback, BPF_TCX_EGRESS, &optd); + ASSERT_OK(err, "prog_detach_eg"); + + assert_mprog_count(BPF_TCX_INGRESS, 1); + assert_mprog_count(BPF_TCX_EGRESS, 0); + +cleanup_in: + err = bpf_prog_detach_opts(fd1, loopback, BPF_TCX_INGRESS, &optd); + ASSERT_OK(err, "prog_detach_in"); + + assert_mprog_count(BPF_TCX_INGRESS, 0); + assert_mprog_count(BPF_TCX_EGRESS, 0); + +cleanup: + test_tc_link__destroy(skel); +} + +static void test_tc_opts_before_target(int target) +{ + LIBBPF_OPTS(bpf_prog_attach_opts, opta); + LIBBPF_OPTS(bpf_prog_detach_opts, optd); + LIBBPF_OPTS(bpf_prog_query_opts, optq); + __u32 fd1, fd2, fd3, fd4, id1, id2, id3, id4; + struct test_tc_link *skel; + __u32 prog_ids[5]; + int err; + + skel = test_tc_link__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_load")) + goto cleanup; + + fd1 = bpf_program__fd(skel->progs.tc1); + fd2 = bpf_program__fd(skel->progs.tc2); + fd3 = bpf_program__fd(skel->progs.tc3); + fd4 = bpf_program__fd(skel->progs.tc4); + + id1 = id_from_prog_fd(fd1); + id2 = id_from_prog_fd(fd2); + id3 = id_from_prog_fd(fd3); + id4 = id_from_prog_fd(fd4); + + ASSERT_NEQ(id1, id2, "prog_ids_1_2"); + ASSERT_NEQ(id3, id4, "prog_ids_3_4"); + ASSERT_NEQ(id2, id3, "prog_ids_2_3"); + + assert_mprog_count(target, 0); + + err = bpf_prog_attach_opts(fd1, loopback, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup; + + assert_mprog_count(target, 1); + + err = bpf_prog_attach_opts(fd2, loopback, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup_target; + + assert_mprog_count(target, 2); + + optq.prog_ids = prog_ids; + + memset(prog_ids, 0, sizeof(prog_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup_target2; + + ASSERT_EQ(optq.count, 2, "count"); + ASSERT_EQ(optq.revision, 3, "revision"); + ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], id2, "prog_ids[1]"); + ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]"); + + ASSERT_OK(system(ping_cmd), ping_cmd); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2"); + ASSERT_EQ(skel->bss->seen_tc3, false, "seen_tc3"); + ASSERT_EQ(skel->bss->seen_tc4, false, "seen_tc4"); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_BEFORE, + .relative_fd = fd2, + ); + + err = bpf_prog_attach_opts(fd3, loopback, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup_target2; + + memset(prog_ids, 0, sizeof(prog_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup_target3; + + ASSERT_EQ(optq.count, 3, "count"); + ASSERT_EQ(optq.revision, 4, "revision"); + ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], id3, "prog_ids[1]"); + ASSERT_EQ(optq.prog_ids[2], id2, "prog_ids[2]"); + ASSERT_EQ(optq.prog_ids[3], 0, "prog_ids[3]"); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_BEFORE, + .relative_id = id1, + ); + + err = bpf_prog_attach_opts(fd4, loopback, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup_target3; + + assert_mprog_count(target, 4); + + memset(prog_ids, 0, sizeof(prog_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup_target4; + + ASSERT_EQ(optq.count, 4, "count"); + ASSERT_EQ(optq.revision, 5, "revision"); + ASSERT_EQ(optq.prog_ids[0], id4, "prog_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], id1, "prog_ids[1]"); + ASSERT_EQ(optq.prog_ids[2], id3, "prog_ids[2]"); + ASSERT_EQ(optq.prog_ids[3], id2, "prog_ids[3]"); + ASSERT_EQ(optq.prog_ids[4], 0, "prog_ids[4]"); + + ASSERT_OK(system(ping_cmd), ping_cmd); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2"); + ASSERT_EQ(skel->bss->seen_tc3, true, "seen_tc3"); + ASSERT_EQ(skel->bss->seen_tc4, true, "seen_tc4"); + +cleanup_target4: + err = bpf_prog_detach_opts(fd4, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(target, 3); + +cleanup_target3: + err = bpf_prog_detach_opts(fd3, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(target, 2); + +cleanup_target2: + err = bpf_prog_detach_opts(fd2, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(target, 1); + +cleanup_target: + err = bpf_prog_detach_opts(fd1, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(target, 0); + +cleanup: + test_tc_link__destroy(skel); +} + +void serial_test_tc_opts_before(void) +{ + test_tc_opts_before_target(BPF_TCX_INGRESS); + test_tc_opts_before_target(BPF_TCX_EGRESS); +} + +static void test_tc_opts_after_target(int target) +{ + LIBBPF_OPTS(bpf_prog_attach_opts, opta); + LIBBPF_OPTS(bpf_prog_detach_opts, optd); + LIBBPF_OPTS(bpf_prog_query_opts, optq); + __u32 fd1, fd2, fd3, fd4, id1, id2, id3, id4; + struct test_tc_link *skel; + __u32 prog_ids[5]; + int err; + + skel = test_tc_link__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_load")) + goto cleanup; + + fd1 = bpf_program__fd(skel->progs.tc1); + fd2 = bpf_program__fd(skel->progs.tc2); + fd3 = bpf_program__fd(skel->progs.tc3); + fd4 = bpf_program__fd(skel->progs.tc4); + + id1 = id_from_prog_fd(fd1); + id2 = id_from_prog_fd(fd2); + id3 = id_from_prog_fd(fd3); + id4 = id_from_prog_fd(fd4); + + ASSERT_NEQ(id1, id2, "prog_ids_1_2"); + ASSERT_NEQ(id3, id4, "prog_ids_3_4"); + ASSERT_NEQ(id2, id3, "prog_ids_2_3"); + + assert_mprog_count(target, 0); + + err = bpf_prog_attach_opts(fd1, loopback, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup; + + assert_mprog_count(target, 1); + + err = bpf_prog_attach_opts(fd2, loopback, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup_target; + + assert_mprog_count(target, 2); + + optq.prog_ids = prog_ids; + + memset(prog_ids, 0, sizeof(prog_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup_target2; + + ASSERT_EQ(optq.count, 2, "count"); + ASSERT_EQ(optq.revision, 3, "revision"); + ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], id2, "prog_ids[1]"); + ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]"); + + ASSERT_OK(system(ping_cmd), ping_cmd); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2"); + ASSERT_EQ(skel->bss->seen_tc3, false, "seen_tc3"); + ASSERT_EQ(skel->bss->seen_tc4, false, "seen_tc4"); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_AFTER, + .relative_fd = fd1, + ); + + err = bpf_prog_attach_opts(fd3, loopback, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup_target2; + + memset(prog_ids, 0, sizeof(prog_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup_target3; + + ASSERT_EQ(optq.count, 3, "count"); + ASSERT_EQ(optq.revision, 4, "revision"); + ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], id3, "prog_ids[1]"); + ASSERT_EQ(optq.prog_ids[2], id2, "prog_ids[2]"); + ASSERT_EQ(optq.prog_ids[3], 0, "prog_ids[3]"); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_AFTER, + .relative_id = id2, + ); + + err = bpf_prog_attach_opts(fd4, loopback, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup_target3; + + assert_mprog_count(target, 4); + + memset(prog_ids, 0, sizeof(prog_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup_target4; + + ASSERT_EQ(optq.count, 4, "count"); + ASSERT_EQ(optq.revision, 5, "revision"); + ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], id3, "prog_ids[1]"); + ASSERT_EQ(optq.prog_ids[2], id2, "prog_ids[2]"); + ASSERT_EQ(optq.prog_ids[3], id4, "prog_ids[3]"); + ASSERT_EQ(optq.prog_ids[4], 0, "prog_ids[4]"); + + ASSERT_OK(system(ping_cmd), ping_cmd); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2"); + ASSERT_EQ(skel->bss->seen_tc3, true, "seen_tc3"); + ASSERT_EQ(skel->bss->seen_tc4, true, "seen_tc4"); + +cleanup_target4: + err = bpf_prog_detach_opts(fd4, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(target, 3); + + memset(prog_ids, 0, sizeof(prog_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup_target3; + + ASSERT_EQ(optq.count, 3, "count"); + ASSERT_EQ(optq.revision, 6, "revision"); + ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], id3, "prog_ids[1]"); + ASSERT_EQ(optq.prog_ids[2], id2, "prog_ids[2]"); + ASSERT_EQ(optq.prog_ids[3], 0, "prog_ids[3]"); + +cleanup_target3: + err = bpf_prog_detach_opts(fd3, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(target, 2); + + memset(prog_ids, 0, sizeof(prog_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup_target2; + + ASSERT_EQ(optq.count, 2, "count"); + ASSERT_EQ(optq.revision, 7, "revision"); + ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], id2, "prog_ids[1]"); + ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]"); + +cleanup_target2: + err = bpf_prog_detach_opts(fd2, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(target, 1); + + memset(prog_ids, 0, sizeof(prog_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup_target; + + ASSERT_EQ(optq.count, 1, "count"); + ASSERT_EQ(optq.revision, 8, "revision"); + ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]"); + +cleanup_target: + err = bpf_prog_detach_opts(fd1, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(target, 0); + +cleanup: + test_tc_link__destroy(skel); +} + +void serial_test_tc_opts_after(void) +{ + test_tc_opts_after_target(BPF_TCX_INGRESS); + test_tc_opts_after_target(BPF_TCX_EGRESS); +} + +static void test_tc_opts_revision_target(int target) +{ + LIBBPF_OPTS(bpf_prog_attach_opts, opta); + LIBBPF_OPTS(bpf_prog_detach_opts, optd); + LIBBPF_OPTS(bpf_prog_query_opts, optq); + __u32 fd1, fd2, id1, id2; + struct test_tc_link *skel; + __u32 prog_ids[3]; + int err; + + skel = test_tc_link__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_load")) + goto cleanup; + + fd1 = bpf_program__fd(skel->progs.tc1); + fd2 = bpf_program__fd(skel->progs.tc2); + + id1 = id_from_prog_fd(fd1); + id2 = id_from_prog_fd(fd2); + + ASSERT_NEQ(id1, id2, "prog_ids_1_2"); + + assert_mprog_count(target, 0); + + LIBBPF_OPTS_RESET(opta, + .expected_revision = 1, + ); + + err = bpf_prog_attach_opts(fd1, loopback, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup; + + assert_mprog_count(target, 1); + + LIBBPF_OPTS_RESET(opta, + .expected_revision = 1, + ); + + err = bpf_prog_attach_opts(fd2, loopback, target, &opta); + if (!ASSERT_EQ(err, -ESTALE, "prog_attach")) + goto cleanup_target; + + assert_mprog_count(target, 1); + + LIBBPF_OPTS_RESET(opta, + .expected_revision = 2, + ); + + err = bpf_prog_attach_opts(fd2, loopback, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup_target; + + assert_mprog_count(target, 2); + + optq.prog_ids = prog_ids; + + memset(prog_ids, 0, sizeof(prog_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup_target2; + + ASSERT_EQ(optq.count, 2, "count"); + ASSERT_EQ(optq.revision, 3, "revision"); + ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], id2, "prog_ids[1]"); + ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]"); + + ASSERT_OK(system(ping_cmd), ping_cmd); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2"); + + LIBBPF_OPTS_RESET(optd, + .expected_revision = 2, + ); + + err = bpf_prog_detach_opts(fd2, loopback, target, &optd); + ASSERT_EQ(err, -ESTALE, "prog_detach"); + assert_mprog_count(target, 2); + +cleanup_target2: + LIBBPF_OPTS_RESET(optd, + .expected_revision = 3, + ); + + err = bpf_prog_detach_opts(fd2, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(target, 1); + +cleanup_target: + LIBBPF_OPTS_RESET(optd); + + err = bpf_prog_detach_opts(fd1, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(target, 0); + +cleanup: + test_tc_link__destroy(skel); +} + +void serial_test_tc_opts_revision(void) +{ + test_tc_opts_revision_target(BPF_TCX_INGRESS); + test_tc_opts_revision_target(BPF_TCX_EGRESS); +} + +static void test_tc_chain_classic(int target, bool chain_tc_old) +{ + LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1); + LIBBPF_OPTS(bpf_tc_hook, tc_hook, .ifindex = loopback); + LIBBPF_OPTS(bpf_prog_attach_opts, opta); + LIBBPF_OPTS(bpf_prog_detach_opts, optd); + bool hook_created = false, tc_attached = false; + __u32 fd1, fd2, fd3, id1, id2, id3; + struct test_tc_link *skel; + int err; + + skel = test_tc_link__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_load")) + goto cleanup; + + fd1 = bpf_program__fd(skel->progs.tc1); + fd2 = bpf_program__fd(skel->progs.tc2); + fd3 = bpf_program__fd(skel->progs.tc3); + + id1 = id_from_prog_fd(fd1); + id2 = id_from_prog_fd(fd2); + id3 = id_from_prog_fd(fd3); + + ASSERT_NEQ(id1, id2, "prog_ids_1_2"); + ASSERT_NEQ(id2, id3, "prog_ids_2_3"); + + assert_mprog_count(target, 0); + + if (chain_tc_old) { + tc_hook.attach_point = target == BPF_TCX_INGRESS ? + BPF_TC_INGRESS : BPF_TC_EGRESS; + err = bpf_tc_hook_create(&tc_hook); + if (err == 0) + hook_created = true; + err = err == -EEXIST ? 0 : err; + if (!ASSERT_OK(err, "bpf_tc_hook_create")) + goto cleanup; + + tc_opts.prog_fd = fd3; + err = bpf_tc_attach(&tc_hook, &tc_opts); + if (!ASSERT_OK(err, "bpf_tc_attach")) + goto cleanup; + tc_attached = true; + } + + err = bpf_prog_attach_opts(fd1, loopback, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup; + + err = bpf_prog_attach_opts(fd2, loopback, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup_detach; + + assert_mprog_count(target, 2); + + ASSERT_OK(system(ping_cmd), ping_cmd); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2"); + ASSERT_EQ(skel->bss->seen_tc3, chain_tc_old, "seen_tc3"); + + skel->bss->seen_tc1 = false; + skel->bss->seen_tc2 = false; + skel->bss->seen_tc3 = false; + + err = bpf_prog_detach_opts(fd2, loopback, target, &optd); + if (!ASSERT_OK(err, "prog_detach")) + goto cleanup_detach; + + assert_mprog_count(target, 1); + + ASSERT_OK(system(ping_cmd), ping_cmd); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2"); + ASSERT_EQ(skel->bss->seen_tc3, chain_tc_old, "seen_tc3"); + +cleanup_detach: + err = bpf_prog_detach_opts(fd1, loopback, target, &optd); + if (!ASSERT_OK(err, "prog_detach")) + goto cleanup; + + __assert_mprog_count(target, 0, chain_tc_old, loopback); +cleanup: + if (tc_attached) { + tc_opts.flags = tc_opts.prog_fd = tc_opts.prog_id = 0; + err = bpf_tc_detach(&tc_hook, &tc_opts); + ASSERT_OK(err, "bpf_tc_detach"); + } + if (hook_created) { + tc_hook.attach_point = BPF_TC_INGRESS | BPF_TC_EGRESS; + bpf_tc_hook_destroy(&tc_hook); + } + test_tc_link__destroy(skel); + assert_mprog_count(target, 0); +} + +void serial_test_tc_opts_chain_classic(void) +{ + test_tc_chain_classic(BPF_TCX_INGRESS, false); + test_tc_chain_classic(BPF_TCX_EGRESS, false); + test_tc_chain_classic(BPF_TCX_INGRESS, true); + test_tc_chain_classic(BPF_TCX_EGRESS, true); +} + +static void test_tc_opts_replace_target(int target) +{ + LIBBPF_OPTS(bpf_prog_attach_opts, opta); + LIBBPF_OPTS(bpf_prog_detach_opts, optd); + LIBBPF_OPTS(bpf_prog_query_opts, optq); + __u32 fd1, fd2, fd3, id1, id2, id3, detach_fd; + __u32 prog_ids[4], prog_flags[4]; + struct test_tc_link *skel; + int err; + + skel = test_tc_link__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_load")) + goto cleanup; + + fd1 = bpf_program__fd(skel->progs.tc1); + fd2 = bpf_program__fd(skel->progs.tc2); + fd3 = bpf_program__fd(skel->progs.tc3); + + id1 = id_from_prog_fd(fd1); + id2 = id_from_prog_fd(fd2); + id3 = id_from_prog_fd(fd3); + + ASSERT_NEQ(id1, id2, "prog_ids_1_2"); + ASSERT_NEQ(id2, id3, "prog_ids_2_3"); + + assert_mprog_count(target, 0); + + LIBBPF_OPTS_RESET(opta, + .expected_revision = 1, + ); + + err = bpf_prog_attach_opts(fd1, loopback, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup; + + assert_mprog_count(target, 1); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_BEFORE, + .relative_id = id1, + .expected_revision = 2, + ); + + err = bpf_prog_attach_opts(fd2, loopback, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup_target; + + detach_fd = fd2; + + assert_mprog_count(target, 2); + + optq.prog_attach_flags = prog_flags; + optq.prog_ids = prog_ids; + + memset(prog_flags, 0, sizeof(prog_flags)); + memset(prog_ids, 0, sizeof(prog_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup_target2; + + ASSERT_EQ(optq.count, 2, "count"); + ASSERT_EQ(optq.revision, 3, "revision"); + ASSERT_EQ(optq.prog_ids[0], id2, "prog_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], id1, "prog_ids[1]"); + ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]"); + + ASSERT_EQ(optq.prog_attach_flags[0], 0, "prog_flags[0]"); + ASSERT_EQ(optq.prog_attach_flags[1], 0, "prog_flags[1]"); + ASSERT_EQ(optq.prog_attach_flags[2], 0, "prog_flags[2]"); + + ASSERT_OK(system(ping_cmd), ping_cmd); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2"); + ASSERT_EQ(skel->bss->seen_tc3, false, "seen_tc3"); + + skel->bss->seen_tc1 = false; + skel->bss->seen_tc2 = false; + skel->bss->seen_tc3 = false; + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_REPLACE, + .replace_prog_fd = fd2, + .expected_revision = 3, + ); + + err = bpf_prog_attach_opts(fd3, loopback, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup_target2; + + detach_fd = fd3; + + assert_mprog_count(target, 2); + + memset(prog_ids, 0, sizeof(prog_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup_target2; + + ASSERT_EQ(optq.count, 2, "count"); + ASSERT_EQ(optq.revision, 4, "revision"); + ASSERT_EQ(optq.prog_ids[0], id3, "prog_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], id1, "prog_ids[1]"); + ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]"); + + ASSERT_OK(system(ping_cmd), ping_cmd); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2"); + ASSERT_EQ(skel->bss->seen_tc3, true, "seen_tc3"); + + skel->bss->seen_tc1 = false; + skel->bss->seen_tc2 = false; + skel->bss->seen_tc3 = false; + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_REPLACE | BPF_F_BEFORE, + .replace_prog_fd = fd3, + .relative_fd = fd1, + .expected_revision = 4, + ); + + err = bpf_prog_attach_opts(fd2, loopback, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup_target2; + + detach_fd = fd2; + + assert_mprog_count(target, 2); + + memset(prog_ids, 0, sizeof(prog_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup_target2; + + ASSERT_EQ(optq.count, 2, "count"); + ASSERT_EQ(optq.revision, 5, "revision"); + ASSERT_EQ(optq.prog_ids[0], id2, "prog_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], id1, "prog_ids[1]"); + ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]"); + + ASSERT_OK(system(ping_cmd), ping_cmd); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2"); + ASSERT_EQ(skel->bss->seen_tc3, false, "seen_tc3"); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_REPLACE, + .replace_prog_fd = fd2, + ); + + err = bpf_prog_attach_opts(fd2, loopback, target, &opta); + ASSERT_EQ(err, -EEXIST, "prog_attach"); + assert_mprog_count(target, 2); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_REPLACE | BPF_F_AFTER, + .replace_prog_fd = fd2, + .relative_fd = fd1, + .expected_revision = 5, + ); + + err = bpf_prog_attach_opts(fd3, loopback, target, &opta); + ASSERT_EQ(err, -ERANGE, "prog_attach"); + assert_mprog_count(target, 2); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_BEFORE | BPF_F_AFTER | BPF_F_REPLACE, + .replace_prog_fd = fd2, + .relative_fd = fd1, + .expected_revision = 5, + ); + + err = bpf_prog_attach_opts(fd3, loopback, target, &opta); + ASSERT_EQ(err, -ERANGE, "prog_attach"); + assert_mprog_count(target, 2); + + LIBBPF_OPTS_RESET(optd, + .flags = BPF_F_BEFORE, + .relative_id = id1, + .expected_revision = 5, + ); + +cleanup_target2: + err = bpf_prog_detach_opts(detach_fd, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(target, 1); + +cleanup_target: + LIBBPF_OPTS_RESET(optd); + + err = bpf_prog_detach_opts(fd1, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(target, 0); + +cleanup: + test_tc_link__destroy(skel); +} + +void serial_test_tc_opts_replace(void) +{ + test_tc_opts_replace_target(BPF_TCX_INGRESS); + test_tc_opts_replace_target(BPF_TCX_EGRESS); +} + +static void test_tc_opts_invalid_target(int target) +{ + LIBBPF_OPTS(bpf_prog_attach_opts, opta); + LIBBPF_OPTS(bpf_prog_detach_opts, optd); + __u32 fd1, fd2, id1, id2; + struct test_tc_link *skel; + int err; + + skel = test_tc_link__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_load")) + goto cleanup; + + fd1 = bpf_program__fd(skel->progs.tc1); + fd2 = bpf_program__fd(skel->progs.tc2); + + id1 = id_from_prog_fd(fd1); + id2 = id_from_prog_fd(fd2); + + ASSERT_NEQ(id1, id2, "prog_ids_1_2"); + + assert_mprog_count(target, 0); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_BEFORE | BPF_F_AFTER, + ); + + err = bpf_prog_attach_opts(fd1, loopback, target, &opta); + ASSERT_EQ(err, -ERANGE, "prog_attach"); + assert_mprog_count(target, 0); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_BEFORE | BPF_F_ID, + ); + + err = bpf_prog_attach_opts(fd1, loopback, target, &opta); + ASSERT_EQ(err, -ENOENT, "prog_attach"); + assert_mprog_count(target, 0); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_AFTER | BPF_F_ID, + ); + + err = bpf_prog_attach_opts(fd1, loopback, target, &opta); + ASSERT_EQ(err, -ENOENT, "prog_attach"); + assert_mprog_count(target, 0); + + LIBBPF_OPTS_RESET(opta, + .relative_fd = fd2, + ); + + err = bpf_prog_attach_opts(fd1, loopback, target, &opta); + ASSERT_EQ(err, -EINVAL, "prog_attach"); + assert_mprog_count(target, 0); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_BEFORE | BPF_F_AFTER, + .relative_fd = fd2, + ); + + err = bpf_prog_attach_opts(fd1, loopback, target, &opta); + ASSERT_EQ(err, -ENOENT, "prog_attach"); + assert_mprog_count(target, 0); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_ID, + .relative_id = id2, + ); + + err = bpf_prog_attach_opts(fd1, loopback, target, &opta); + ASSERT_EQ(err, -EINVAL, "prog_attach"); + assert_mprog_count(target, 0); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_BEFORE, + .relative_fd = fd1, + ); + + err = bpf_prog_attach_opts(fd1, loopback, target, &opta); + ASSERT_EQ(err, -ENOENT, "prog_attach"); + assert_mprog_count(target, 0); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_AFTER, + .relative_fd = fd1, + ); + + err = bpf_prog_attach_opts(fd1, loopback, target, &opta); + ASSERT_EQ(err, -ENOENT, "prog_attach"); + assert_mprog_count(target, 0); + + LIBBPF_OPTS_RESET(opta); + + err = bpf_prog_attach_opts(fd1, loopback, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup; + + assert_mprog_count(target, 1); + + LIBBPF_OPTS_RESET(opta); + + err = bpf_prog_attach_opts(fd1, loopback, target, &opta); + ASSERT_EQ(err, -EEXIST, "prog_attach"); + assert_mprog_count(target, 1); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_BEFORE, + .relative_fd = fd1, + ); + + err = bpf_prog_attach_opts(fd1, loopback, target, &opta); + ASSERT_EQ(err, -EEXIST, "prog_attach"); + assert_mprog_count(target, 1); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_AFTER, + .relative_fd = fd1, + ); + + err = bpf_prog_attach_opts(fd1, loopback, target, &opta); + ASSERT_EQ(err, -EEXIST, "prog_attach"); + assert_mprog_count(target, 1); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_REPLACE, + .relative_fd = fd1, + ); + + err = bpf_prog_attach_opts(fd1, loopback, target, &opta); + ASSERT_EQ(err, -EINVAL, "prog_attach_x1"); + assert_mprog_count(target, 1); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_REPLACE, + .replace_prog_fd = fd1, + ); + + err = bpf_prog_attach_opts(fd1, loopback, target, &opta); + ASSERT_EQ(err, -EEXIST, "prog_attach"); + assert_mprog_count(target, 1); + + err = bpf_prog_detach_opts(fd1, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(target, 0); +cleanup: + test_tc_link__destroy(skel); +} + +void serial_test_tc_opts_invalid(void) +{ + test_tc_opts_invalid_target(BPF_TCX_INGRESS); + test_tc_opts_invalid_target(BPF_TCX_EGRESS); +} + +static void test_tc_opts_prepend_target(int target) +{ + LIBBPF_OPTS(bpf_prog_attach_opts, opta); + LIBBPF_OPTS(bpf_prog_detach_opts, optd); + LIBBPF_OPTS(bpf_prog_query_opts, optq); + __u32 fd1, fd2, fd3, fd4, id1, id2, id3, id4; + struct test_tc_link *skel; + __u32 prog_ids[5]; + int err; + + skel = test_tc_link__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_load")) + goto cleanup; + + fd1 = bpf_program__fd(skel->progs.tc1); + fd2 = bpf_program__fd(skel->progs.tc2); + fd3 = bpf_program__fd(skel->progs.tc3); + fd4 = bpf_program__fd(skel->progs.tc4); + + id1 = id_from_prog_fd(fd1); + id2 = id_from_prog_fd(fd2); + id3 = id_from_prog_fd(fd3); + id4 = id_from_prog_fd(fd4); + + ASSERT_NEQ(id1, id2, "prog_ids_1_2"); + ASSERT_NEQ(id3, id4, "prog_ids_3_4"); + ASSERT_NEQ(id2, id3, "prog_ids_2_3"); + + assert_mprog_count(target, 0); + + err = bpf_prog_attach_opts(fd1, loopback, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup; + + assert_mprog_count(target, 1); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_BEFORE, + ); + + err = bpf_prog_attach_opts(fd2, loopback, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup_target; + + assert_mprog_count(target, 2); + + optq.prog_ids = prog_ids; + + memset(prog_ids, 0, sizeof(prog_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup_target2; + + ASSERT_EQ(optq.count, 2, "count"); + ASSERT_EQ(optq.revision, 3, "revision"); + ASSERT_EQ(optq.prog_ids[0], id2, "prog_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], id1, "prog_ids[1]"); + ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]"); + + ASSERT_OK(system(ping_cmd), ping_cmd); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2"); + ASSERT_EQ(skel->bss->seen_tc3, false, "seen_tc3"); + ASSERT_EQ(skel->bss->seen_tc4, false, "seen_tc4"); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_BEFORE, + ); + + err = bpf_prog_attach_opts(fd3, loopback, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup_target2; + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_BEFORE, + ); + + err = bpf_prog_attach_opts(fd4, loopback, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup_target3; + + assert_mprog_count(target, 4); + + memset(prog_ids, 0, sizeof(prog_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup_target4; + + ASSERT_EQ(optq.count, 4, "count"); + ASSERT_EQ(optq.revision, 5, "revision"); + ASSERT_EQ(optq.prog_ids[0], id4, "prog_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], id3, "prog_ids[1]"); + ASSERT_EQ(optq.prog_ids[2], id2, "prog_ids[2]"); + ASSERT_EQ(optq.prog_ids[3], id1, "prog_ids[3]"); + ASSERT_EQ(optq.prog_ids[4], 0, "prog_ids[4]"); + + ASSERT_OK(system(ping_cmd), ping_cmd); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2"); + ASSERT_EQ(skel->bss->seen_tc3, true, "seen_tc3"); + ASSERT_EQ(skel->bss->seen_tc4, true, "seen_tc4"); + +cleanup_target4: + err = bpf_prog_detach_opts(fd4, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(target, 3); + +cleanup_target3: + err = bpf_prog_detach_opts(fd3, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(target, 2); + +cleanup_target2: + err = bpf_prog_detach_opts(fd2, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(target, 1); + +cleanup_target: + err = bpf_prog_detach_opts(fd1, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(target, 0); + +cleanup: + test_tc_link__destroy(skel); +} + +void serial_test_tc_opts_prepend(void) +{ + test_tc_opts_prepend_target(BPF_TCX_INGRESS); + test_tc_opts_prepend_target(BPF_TCX_EGRESS); +} + +static void test_tc_opts_append_target(int target) +{ + LIBBPF_OPTS(bpf_prog_attach_opts, opta); + LIBBPF_OPTS(bpf_prog_detach_opts, optd); + LIBBPF_OPTS(bpf_prog_query_opts, optq); + __u32 fd1, fd2, fd3, fd4, id1, id2, id3, id4; + struct test_tc_link *skel; + __u32 prog_ids[5]; + int err; + + skel = test_tc_link__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_load")) + goto cleanup; + + fd1 = bpf_program__fd(skel->progs.tc1); + fd2 = bpf_program__fd(skel->progs.tc2); + fd3 = bpf_program__fd(skel->progs.tc3); + fd4 = bpf_program__fd(skel->progs.tc4); + + id1 = id_from_prog_fd(fd1); + id2 = id_from_prog_fd(fd2); + id3 = id_from_prog_fd(fd3); + id4 = id_from_prog_fd(fd4); + + ASSERT_NEQ(id1, id2, "prog_ids_1_2"); + ASSERT_NEQ(id3, id4, "prog_ids_3_4"); + ASSERT_NEQ(id2, id3, "prog_ids_2_3"); + + assert_mprog_count(target, 0); + + err = bpf_prog_attach_opts(fd1, loopback, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup; + + assert_mprog_count(target, 1); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_AFTER, + ); + + err = bpf_prog_attach_opts(fd2, loopback, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup_target; + + assert_mprog_count(target, 2); + + optq.prog_ids = prog_ids; + + memset(prog_ids, 0, sizeof(prog_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup_target2; + + ASSERT_EQ(optq.count, 2, "count"); + ASSERT_EQ(optq.revision, 3, "revision"); + ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], id2, "prog_ids[1]"); + ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]"); + + ASSERT_OK(system(ping_cmd), ping_cmd); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2"); + ASSERT_EQ(skel->bss->seen_tc3, false, "seen_tc3"); + ASSERT_EQ(skel->bss->seen_tc4, false, "seen_tc4"); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_AFTER, + ); + + err = bpf_prog_attach_opts(fd3, loopback, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup_target2; + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_AFTER, + ); + + err = bpf_prog_attach_opts(fd4, loopback, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup_target3; + + assert_mprog_count(target, 4); + + memset(prog_ids, 0, sizeof(prog_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup_target4; + + ASSERT_EQ(optq.count, 4, "count"); + ASSERT_EQ(optq.revision, 5, "revision"); + ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], id2, "prog_ids[1]"); + ASSERT_EQ(optq.prog_ids[2], id3, "prog_ids[2]"); + ASSERT_EQ(optq.prog_ids[3], id4, "prog_ids[3]"); + ASSERT_EQ(optq.prog_ids[4], 0, "prog_ids[4]"); + + ASSERT_OK(system(ping_cmd), ping_cmd); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2"); + ASSERT_EQ(skel->bss->seen_tc3, true, "seen_tc3"); + ASSERT_EQ(skel->bss->seen_tc4, true, "seen_tc4"); + +cleanup_target4: + err = bpf_prog_detach_opts(fd4, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(target, 3); + +cleanup_target3: + err = bpf_prog_detach_opts(fd3, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(target, 2); + +cleanup_target2: + err = bpf_prog_detach_opts(fd2, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(target, 1); + +cleanup_target: + err = bpf_prog_detach_opts(fd1, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(target, 0); + +cleanup: + test_tc_link__destroy(skel); +} + +void serial_test_tc_opts_append(void) +{ + test_tc_opts_append_target(BPF_TCX_INGRESS); + test_tc_opts_append_target(BPF_TCX_EGRESS); +} + +static void test_tc_opts_dev_cleanup_target(int target) +{ + LIBBPF_OPTS(bpf_prog_attach_opts, opta); + LIBBPF_OPTS(bpf_prog_detach_opts, optd); + LIBBPF_OPTS(bpf_prog_query_opts, optq); + __u32 fd1, fd2, fd3, fd4, id1, id2, id3, id4; + struct test_tc_link *skel; + int err, ifindex; + + ASSERT_OK(system("ip link add dev tcx_opts1 type veth peer name tcx_opts2"), "add veth"); + ifindex = if_nametoindex("tcx_opts1"); + ASSERT_NEQ(ifindex, 0, "non_zero_ifindex"); + + skel = test_tc_link__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_load")) + goto cleanup; + + fd1 = bpf_program__fd(skel->progs.tc1); + fd2 = bpf_program__fd(skel->progs.tc2); + fd3 = bpf_program__fd(skel->progs.tc3); + fd4 = bpf_program__fd(skel->progs.tc4); + + id1 = id_from_prog_fd(fd1); + id2 = id_from_prog_fd(fd2); + id3 = id_from_prog_fd(fd3); + id4 = id_from_prog_fd(fd4); + + ASSERT_NEQ(id1, id2, "prog_ids_1_2"); + ASSERT_NEQ(id3, id4, "prog_ids_3_4"); + ASSERT_NEQ(id2, id3, "prog_ids_2_3"); + + assert_mprog_count_ifindex(ifindex, target, 0); + + err = bpf_prog_attach_opts(fd1, ifindex, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup; + + assert_mprog_count_ifindex(ifindex, target, 1); + + err = bpf_prog_attach_opts(fd2, ifindex, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup1; + + assert_mprog_count_ifindex(ifindex, target, 2); + + err = bpf_prog_attach_opts(fd3, ifindex, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup2; + + assert_mprog_count_ifindex(ifindex, target, 3); + + err = bpf_prog_attach_opts(fd4, ifindex, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup3; + + assert_mprog_count_ifindex(ifindex, target, 4); + + ASSERT_OK(system("ip link del dev tcx_opts1"), "del veth"); + ASSERT_EQ(if_nametoindex("tcx_opts1"), 0, "dev1_removed"); + ASSERT_EQ(if_nametoindex("tcx_opts2"), 0, "dev2_removed"); + return; +cleanup3: + err = bpf_prog_detach_opts(fd3, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + + assert_mprog_count_ifindex(ifindex, target, 2); +cleanup2: + err = bpf_prog_detach_opts(fd2, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + + assert_mprog_count_ifindex(ifindex, target, 1); +cleanup1: + err = bpf_prog_detach_opts(fd1, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + + assert_mprog_count_ifindex(ifindex, target, 0); +cleanup: + test_tc_link__destroy(skel); + + ASSERT_OK(system("ip link del dev tcx_opts1"), "del veth"); + ASSERT_EQ(if_nametoindex("tcx_opts1"), 0, "dev1_removed"); + ASSERT_EQ(if_nametoindex("tcx_opts2"), 0, "dev2_removed"); +} + +void serial_test_tc_opts_dev_cleanup(void) +{ + test_tc_opts_dev_cleanup_target(BPF_TCX_INGRESS); + test_tc_opts_dev_cleanup_target(BPF_TCX_EGRESS); +} + +static void test_tc_opts_mixed_target(int target) +{ + LIBBPF_OPTS(bpf_prog_attach_opts, opta); + LIBBPF_OPTS(bpf_prog_detach_opts, optd); + LIBBPF_OPTS(bpf_prog_query_opts, optq); + LIBBPF_OPTS(bpf_tcx_opts, optl); + __u32 pid1, pid2, pid3, pid4, lid2, lid4; + __u32 prog_flags[4], link_flags[4]; + __u32 prog_ids[4], link_ids[4]; + struct test_tc_link *skel; + struct bpf_link *link; + int err, detach_fd; + + skel = test_tc_link__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + goto cleanup; + + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, target), + 0, "tc1_attach_type"); + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, target), + 0, "tc2_attach_type"); + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc3, target), + 0, "tc3_attach_type"); + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc4, target), + 0, "tc4_attach_type"); + + err = test_tc_link__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto cleanup; + + pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1)); + pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2)); + pid3 = id_from_prog_fd(bpf_program__fd(skel->progs.tc3)); + pid4 = id_from_prog_fd(bpf_program__fd(skel->progs.tc4)); + + ASSERT_NEQ(pid1, pid2, "prog_ids_1_2"); + ASSERT_NEQ(pid3, pid4, "prog_ids_3_4"); + ASSERT_NEQ(pid2, pid3, "prog_ids_2_3"); + + assert_mprog_count(target, 0); + + err = bpf_prog_attach_opts(bpf_program__fd(skel->progs.tc1), + loopback, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup; + + detach_fd = bpf_program__fd(skel->progs.tc1); + + assert_mprog_count(target, 1); + + link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup1; + skel->links.tc2 = link; + + lid2 = id_from_link_fd(bpf_link__fd(skel->links.tc2)); + + assert_mprog_count(target, 2); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_REPLACE, + .replace_prog_fd = bpf_program__fd(skel->progs.tc1), + ); + + err = bpf_prog_attach_opts(bpf_program__fd(skel->progs.tc2), + loopback, target, &opta); + ASSERT_EQ(err, -EEXIST, "prog_attach"); + + assert_mprog_count(target, 2); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_REPLACE, + .replace_prog_fd = bpf_program__fd(skel->progs.tc2), + ); + + err = bpf_prog_attach_opts(bpf_program__fd(skel->progs.tc1), + loopback, target, &opta); + ASSERT_EQ(err, -EEXIST, "prog_attach"); + + assert_mprog_count(target, 2); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_REPLACE, + .replace_prog_fd = bpf_program__fd(skel->progs.tc2), + ); + + err = bpf_prog_attach_opts(bpf_program__fd(skel->progs.tc3), + loopback, target, &opta); + ASSERT_EQ(err, -EBUSY, "prog_attach"); + + assert_mprog_count(target, 2); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_REPLACE, + .replace_prog_fd = bpf_program__fd(skel->progs.tc1), + ); + + err = bpf_prog_attach_opts(bpf_program__fd(skel->progs.tc3), + loopback, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup1; + + detach_fd = bpf_program__fd(skel->progs.tc3); + + assert_mprog_count(target, 2); + + link = bpf_program__attach_tcx(skel->progs.tc4, loopback, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup1; + skel->links.tc4 = link; + + lid4 = id_from_link_fd(bpf_link__fd(skel->links.tc4)); + + assert_mprog_count(target, 3); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_REPLACE, + .replace_prog_fd = bpf_program__fd(skel->progs.tc4), + ); + + err = bpf_prog_attach_opts(bpf_program__fd(skel->progs.tc2), + loopback, target, &opta); + ASSERT_EQ(err, -EEXIST, "prog_attach"); + + optq.prog_ids = prog_ids; + optq.prog_attach_flags = prog_flags; + optq.link_ids = link_ids; + optq.link_attach_flags = link_flags; + + memset(prog_ids, 0, sizeof(prog_ids)); + memset(prog_flags, 0, sizeof(prog_flags)); + memset(link_ids, 0, sizeof(link_ids)); + memset(link_flags, 0, sizeof(link_flags)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup1; + + ASSERT_EQ(optq.count, 3, "count"); + ASSERT_EQ(optq.revision, 5, "revision"); + ASSERT_EQ(optq.prog_ids[0], pid3, "prog_ids[0]"); + ASSERT_EQ(optq.prog_attach_flags[0], 0, "prog_flags[0]"); + ASSERT_EQ(optq.link_ids[0], 0, "link_ids[0]"); + ASSERT_EQ(optq.link_attach_flags[0], 0, "link_flags[0]"); + ASSERT_EQ(optq.prog_ids[1], pid2, "prog_ids[1]"); + ASSERT_EQ(optq.prog_attach_flags[1], 0, "prog_flags[1]"); + ASSERT_EQ(optq.link_ids[1], lid2, "link_ids[1]"); + ASSERT_EQ(optq.link_attach_flags[1], 0, "link_flags[1]"); + ASSERT_EQ(optq.prog_ids[2], pid4, "prog_ids[2]"); + ASSERT_EQ(optq.prog_attach_flags[2], 0, "prog_flags[2]"); + ASSERT_EQ(optq.link_ids[2], lid4, "link_ids[2]"); + ASSERT_EQ(optq.link_attach_flags[2], 0, "link_flags[2]"); + ASSERT_EQ(optq.prog_ids[3], 0, "prog_ids[3]"); + ASSERT_EQ(optq.prog_attach_flags[3], 0, "prog_flags[3]"); + ASSERT_EQ(optq.link_ids[3], 0, "link_ids[3]"); + ASSERT_EQ(optq.link_attach_flags[3], 0, "link_flags[3]"); + + ASSERT_OK(system(ping_cmd), ping_cmd); + +cleanup1: + err = bpf_prog_detach_opts(detach_fd, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(target, 2); + +cleanup: + test_tc_link__destroy(skel); + assert_mprog_count(target, 0); +} + +void serial_test_tc_opts_mixed(void) +{ + test_tc_opts_mixed_target(BPF_TCX_INGRESS); + test_tc_opts_mixed_target(BPF_TCX_EGRESS); +} + +static void test_tc_opts_demixed_target(int target) +{ + LIBBPF_OPTS(bpf_prog_attach_opts, opta); + LIBBPF_OPTS(bpf_prog_detach_opts, optd); + LIBBPF_OPTS(bpf_tcx_opts, optl); + struct test_tc_link *skel; + struct bpf_link *link; + __u32 pid1, pid2; + int err; + + skel = test_tc_link__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + goto cleanup; + + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, target), + 0, "tc1_attach_type"); + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, target), + 0, "tc2_attach_type"); + + err = test_tc_link__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto cleanup; + + pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1)); + pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2)); + ASSERT_NEQ(pid1, pid2, "prog_ids_1_2"); + + assert_mprog_count(target, 0); + + err = bpf_prog_attach_opts(bpf_program__fd(skel->progs.tc1), + loopback, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup; + + assert_mprog_count(target, 1); + + link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup1; + skel->links.tc2 = link; + + assert_mprog_count(target, 2); + + LIBBPF_OPTS_RESET(optd, + .flags = BPF_F_AFTER, + ); + + err = bpf_prog_detach_opts(0, loopback, target, &optd); + ASSERT_EQ(err, -EBUSY, "prog_detach"); + + assert_mprog_count(target, 2); + + LIBBPF_OPTS_RESET(optd, + .flags = BPF_F_BEFORE, + ); + + err = bpf_prog_detach_opts(0, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + + assert_mprog_count(target, 1); + goto cleanup; + +cleanup1: + err = bpf_prog_detach_opts(bpf_program__fd(skel->progs.tc1), + loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(target, 2); + +cleanup: + test_tc_link__destroy(skel); + assert_mprog_count(target, 0); +} + +void serial_test_tc_opts_demixed(void) +{ + test_tc_opts_demixed_target(BPF_TCX_INGRESS); + test_tc_opts_demixed_target(BPF_TCX_EGRESS); +} + +static void test_tc_opts_detach_target(int target) +{ + LIBBPF_OPTS(bpf_prog_attach_opts, opta); + LIBBPF_OPTS(bpf_prog_detach_opts, optd); + LIBBPF_OPTS(bpf_prog_query_opts, optq); + __u32 fd1, fd2, fd3, fd4, id1, id2, id3, id4; + struct test_tc_link *skel; + __u32 prog_ids[5]; + int err; + + skel = test_tc_link__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_load")) + goto cleanup; + + fd1 = bpf_program__fd(skel->progs.tc1); + fd2 = bpf_program__fd(skel->progs.tc2); + fd3 = bpf_program__fd(skel->progs.tc3); + fd4 = bpf_program__fd(skel->progs.tc4); + + id1 = id_from_prog_fd(fd1); + id2 = id_from_prog_fd(fd2); + id3 = id_from_prog_fd(fd3); + id4 = id_from_prog_fd(fd4); + + ASSERT_NEQ(id1, id2, "prog_ids_1_2"); + ASSERT_NEQ(id3, id4, "prog_ids_3_4"); + ASSERT_NEQ(id2, id3, "prog_ids_2_3"); + + assert_mprog_count(target, 0); + + err = bpf_prog_attach_opts(fd1, loopback, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup; + + assert_mprog_count(target, 1); + + err = bpf_prog_attach_opts(fd2, loopback, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup1; + + assert_mprog_count(target, 2); + + err = bpf_prog_attach_opts(fd3, loopback, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup2; + + assert_mprog_count(target, 3); + + err = bpf_prog_attach_opts(fd4, loopback, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup3; + + assert_mprog_count(target, 4); + + optq.prog_ids = prog_ids; + + memset(prog_ids, 0, sizeof(prog_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup4; + + ASSERT_EQ(optq.count, 4, "count"); + ASSERT_EQ(optq.revision, 5, "revision"); + ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], id2, "prog_ids[1]"); + ASSERT_EQ(optq.prog_ids[2], id3, "prog_ids[2]"); + ASSERT_EQ(optq.prog_ids[3], id4, "prog_ids[3]"); + ASSERT_EQ(optq.prog_ids[4], 0, "prog_ids[4]"); + + LIBBPF_OPTS_RESET(optd, + .flags = BPF_F_BEFORE, + ); + + err = bpf_prog_detach_opts(0, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + + assert_mprog_count(target, 3); + + memset(prog_ids, 0, sizeof(prog_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup4; + + ASSERT_EQ(optq.count, 3, "count"); + ASSERT_EQ(optq.revision, 6, "revision"); + ASSERT_EQ(optq.prog_ids[0], id2, "prog_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], id3, "prog_ids[1]"); + ASSERT_EQ(optq.prog_ids[2], id4, "prog_ids[2]"); + ASSERT_EQ(optq.prog_ids[3], 0, "prog_ids[3]"); + + LIBBPF_OPTS_RESET(optd, + .flags = BPF_F_AFTER, + ); + + err = bpf_prog_detach_opts(0, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + + assert_mprog_count(target, 2); + + memset(prog_ids, 0, sizeof(prog_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup4; + + ASSERT_EQ(optq.count, 2, "count"); + ASSERT_EQ(optq.revision, 7, "revision"); + ASSERT_EQ(optq.prog_ids[0], id2, "prog_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], id3, "prog_ids[1]"); + ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]"); + + LIBBPF_OPTS_RESET(optd); + + err = bpf_prog_detach_opts(fd3, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(target, 1); + + err = bpf_prog_detach_opts(fd2, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(target, 0); + + LIBBPF_OPTS_RESET(optd, + .flags = BPF_F_BEFORE, + ); + + err = bpf_prog_detach_opts(0, loopback, target, &optd); + ASSERT_EQ(err, -ENOENT, "prog_detach"); + + LIBBPF_OPTS_RESET(optd, + .flags = BPF_F_AFTER, + ); + + err = bpf_prog_detach_opts(0, loopback, target, &optd); + ASSERT_EQ(err, -ENOENT, "prog_detach"); + goto cleanup; + +cleanup4: + err = bpf_prog_detach_opts(fd4, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(target, 3); + +cleanup3: + err = bpf_prog_detach_opts(fd3, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(target, 2); + +cleanup2: + err = bpf_prog_detach_opts(fd2, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(target, 1); + +cleanup1: + err = bpf_prog_detach_opts(fd1, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(target, 0); + +cleanup: + test_tc_link__destroy(skel); +} + +void serial_test_tc_opts_detach(void) +{ + test_tc_opts_detach_target(BPF_TCX_INGRESS); + test_tc_opts_detach_target(BPF_TCX_EGRESS); +} + +static void test_tc_opts_detach_before_target(int target) +{ + LIBBPF_OPTS(bpf_prog_attach_opts, opta); + LIBBPF_OPTS(bpf_prog_detach_opts, optd); + LIBBPF_OPTS(bpf_prog_query_opts, optq); + __u32 fd1, fd2, fd3, fd4, id1, id2, id3, id4; + struct test_tc_link *skel; + __u32 prog_ids[5]; + int err; + + skel = test_tc_link__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_load")) + goto cleanup; + + fd1 = bpf_program__fd(skel->progs.tc1); + fd2 = bpf_program__fd(skel->progs.tc2); + fd3 = bpf_program__fd(skel->progs.tc3); + fd4 = bpf_program__fd(skel->progs.tc4); + + id1 = id_from_prog_fd(fd1); + id2 = id_from_prog_fd(fd2); + id3 = id_from_prog_fd(fd3); + id4 = id_from_prog_fd(fd4); + + ASSERT_NEQ(id1, id2, "prog_ids_1_2"); + ASSERT_NEQ(id3, id4, "prog_ids_3_4"); + ASSERT_NEQ(id2, id3, "prog_ids_2_3"); + + assert_mprog_count(target, 0); + + err = bpf_prog_attach_opts(fd1, loopback, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup; + + assert_mprog_count(target, 1); + + err = bpf_prog_attach_opts(fd2, loopback, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup1; + + assert_mprog_count(target, 2); + + err = bpf_prog_attach_opts(fd3, loopback, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup2; + + assert_mprog_count(target, 3); + + err = bpf_prog_attach_opts(fd4, loopback, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup3; + + assert_mprog_count(target, 4); + + optq.prog_ids = prog_ids; + + memset(prog_ids, 0, sizeof(prog_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup4; + + ASSERT_EQ(optq.count, 4, "count"); + ASSERT_EQ(optq.revision, 5, "revision"); + ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], id2, "prog_ids[1]"); + ASSERT_EQ(optq.prog_ids[2], id3, "prog_ids[2]"); + ASSERT_EQ(optq.prog_ids[3], id4, "prog_ids[3]"); + ASSERT_EQ(optq.prog_ids[4], 0, "prog_ids[4]"); + + LIBBPF_OPTS_RESET(optd, + .flags = BPF_F_BEFORE, + .relative_fd = fd2, + ); + + err = bpf_prog_detach_opts(fd1, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + + assert_mprog_count(target, 3); + + memset(prog_ids, 0, sizeof(prog_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup4; + + ASSERT_EQ(optq.count, 3, "count"); + ASSERT_EQ(optq.revision, 6, "revision"); + ASSERT_EQ(optq.prog_ids[0], id2, "prog_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], id3, "prog_ids[1]"); + ASSERT_EQ(optq.prog_ids[2], id4, "prog_ids[2]"); + ASSERT_EQ(optq.prog_ids[3], 0, "prog_ids[3]"); + + LIBBPF_OPTS_RESET(optd, + .flags = BPF_F_BEFORE, + .relative_fd = fd2, + ); + + err = bpf_prog_detach_opts(fd1, loopback, target, &optd); + ASSERT_EQ(err, -ENOENT, "prog_detach"); + assert_mprog_count(target, 3); + + LIBBPF_OPTS_RESET(optd, + .flags = BPF_F_BEFORE, + .relative_fd = fd4, + ); + + err = bpf_prog_detach_opts(fd2, loopback, target, &optd); + ASSERT_EQ(err, -ERANGE, "prog_detach"); + assert_mprog_count(target, 3); + + LIBBPF_OPTS_RESET(optd, + .flags = BPF_F_BEFORE, + .relative_fd = fd1, + ); + + err = bpf_prog_detach_opts(fd2, loopback, target, &optd); + ASSERT_EQ(err, -ENOENT, "prog_detach"); + assert_mprog_count(target, 3); + + LIBBPF_OPTS_RESET(optd, + .flags = BPF_F_BEFORE, + .relative_fd = fd3, + ); + + err = bpf_prog_detach_opts(fd2, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + + assert_mprog_count(target, 2); + + memset(prog_ids, 0, sizeof(prog_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup4; + + ASSERT_EQ(optq.count, 2, "count"); + ASSERT_EQ(optq.revision, 7, "revision"); + ASSERT_EQ(optq.prog_ids[0], id3, "prog_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], id4, "prog_ids[1]"); + ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]"); + + LIBBPF_OPTS_RESET(optd, + .flags = BPF_F_BEFORE, + .relative_fd = fd4, + ); + + err = bpf_prog_detach_opts(0, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + + assert_mprog_count(target, 1); + + memset(prog_ids, 0, sizeof(prog_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup4; + + ASSERT_EQ(optq.count, 1, "count"); + ASSERT_EQ(optq.revision, 8, "revision"); + ASSERT_EQ(optq.prog_ids[0], id4, "prog_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]"); + + LIBBPF_OPTS_RESET(optd, + .flags = BPF_F_BEFORE, + ); + + err = bpf_prog_detach_opts(0, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + + assert_mprog_count(target, 0); + goto cleanup; + +cleanup4: + err = bpf_prog_detach_opts(fd4, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(target, 3); + +cleanup3: + err = bpf_prog_detach_opts(fd3, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(target, 2); + +cleanup2: + err = bpf_prog_detach_opts(fd2, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(target, 1); + +cleanup1: + err = bpf_prog_detach_opts(fd1, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(target, 0); + +cleanup: + test_tc_link__destroy(skel); +} + +void serial_test_tc_opts_detach_before(void) +{ + test_tc_opts_detach_before_target(BPF_TCX_INGRESS); + test_tc_opts_detach_before_target(BPF_TCX_EGRESS); +} + +static void test_tc_opts_detach_after_target(int target) +{ + LIBBPF_OPTS(bpf_prog_attach_opts, opta); + LIBBPF_OPTS(bpf_prog_detach_opts, optd); + LIBBPF_OPTS(bpf_prog_query_opts, optq); + __u32 fd1, fd2, fd3, fd4, id1, id2, id3, id4; + struct test_tc_link *skel; + __u32 prog_ids[5]; + int err; + + skel = test_tc_link__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_load")) + goto cleanup; + + fd1 = bpf_program__fd(skel->progs.tc1); + fd2 = bpf_program__fd(skel->progs.tc2); + fd3 = bpf_program__fd(skel->progs.tc3); + fd4 = bpf_program__fd(skel->progs.tc4); + + id1 = id_from_prog_fd(fd1); + id2 = id_from_prog_fd(fd2); + id3 = id_from_prog_fd(fd3); + id4 = id_from_prog_fd(fd4); + + ASSERT_NEQ(id1, id2, "prog_ids_1_2"); + ASSERT_NEQ(id3, id4, "prog_ids_3_4"); + ASSERT_NEQ(id2, id3, "prog_ids_2_3"); + + assert_mprog_count(target, 0); + + err = bpf_prog_attach_opts(fd1, loopback, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup; + + assert_mprog_count(target, 1); + + err = bpf_prog_attach_opts(fd2, loopback, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup1; + + assert_mprog_count(target, 2); + + err = bpf_prog_attach_opts(fd3, loopback, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup2; + + assert_mprog_count(target, 3); + + err = bpf_prog_attach_opts(fd4, loopback, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup3; + + assert_mprog_count(target, 4); + + optq.prog_ids = prog_ids; + + memset(prog_ids, 0, sizeof(prog_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup4; + + ASSERT_EQ(optq.count, 4, "count"); + ASSERT_EQ(optq.revision, 5, "revision"); + ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], id2, "prog_ids[1]"); + ASSERT_EQ(optq.prog_ids[2], id3, "prog_ids[2]"); + ASSERT_EQ(optq.prog_ids[3], id4, "prog_ids[3]"); + ASSERT_EQ(optq.prog_ids[4], 0, "prog_ids[4]"); + + LIBBPF_OPTS_RESET(optd, + .flags = BPF_F_AFTER, + .relative_fd = fd1, + ); + + err = bpf_prog_detach_opts(fd2, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + + assert_mprog_count(target, 3); + + memset(prog_ids, 0, sizeof(prog_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup4; + + ASSERT_EQ(optq.count, 3, "count"); + ASSERT_EQ(optq.revision, 6, "revision"); + ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], id3, "prog_ids[1]"); + ASSERT_EQ(optq.prog_ids[2], id4, "prog_ids[2]"); + ASSERT_EQ(optq.prog_ids[3], 0, "prog_ids[3]"); + + LIBBPF_OPTS_RESET(optd, + .flags = BPF_F_AFTER, + .relative_fd = fd1, + ); + + err = bpf_prog_detach_opts(fd2, loopback, target, &optd); + ASSERT_EQ(err, -ENOENT, "prog_detach"); + assert_mprog_count(target, 3); + + LIBBPF_OPTS_RESET(optd, + .flags = BPF_F_AFTER, + .relative_fd = fd4, + ); + + err = bpf_prog_detach_opts(fd1, loopback, target, &optd); + ASSERT_EQ(err, -ERANGE, "prog_detach"); + assert_mprog_count(target, 3); + + LIBBPF_OPTS_RESET(optd, + .flags = BPF_F_AFTER, + .relative_fd = fd3, + ); + + err = bpf_prog_detach_opts(fd1, loopback, target, &optd); + ASSERT_EQ(err, -ERANGE, "prog_detach"); + assert_mprog_count(target, 3); + + LIBBPF_OPTS_RESET(optd, + .flags = BPF_F_AFTER, + .relative_fd = fd1, + ); + + err = bpf_prog_detach_opts(fd1, loopback, target, &optd); + ASSERT_EQ(err, -ERANGE, "prog_detach"); + assert_mprog_count(target, 3); + + LIBBPF_OPTS_RESET(optd, + .flags = BPF_F_AFTER, + .relative_fd = fd1, + ); + + err = bpf_prog_detach_opts(fd3, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + + assert_mprog_count(target, 2); + + memset(prog_ids, 0, sizeof(prog_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup4; + + ASSERT_EQ(optq.count, 2, "count"); + ASSERT_EQ(optq.revision, 7, "revision"); + ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], id4, "prog_ids[1]"); + ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]"); + + LIBBPF_OPTS_RESET(optd, + .flags = BPF_F_AFTER, + .relative_fd = fd1, + ); + + err = bpf_prog_detach_opts(0, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + + assert_mprog_count(target, 1); + + memset(prog_ids, 0, sizeof(prog_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(loopback, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup4; + + ASSERT_EQ(optq.count, 1, "count"); + ASSERT_EQ(optq.revision, 8, "revision"); + ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]"); + + LIBBPF_OPTS_RESET(optd, + .flags = BPF_F_AFTER, + ); + + err = bpf_prog_detach_opts(0, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + + assert_mprog_count(target, 0); + goto cleanup; + +cleanup4: + err = bpf_prog_detach_opts(fd4, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(target, 3); + +cleanup3: + err = bpf_prog_detach_opts(fd3, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(target, 2); + +cleanup2: + err = bpf_prog_detach_opts(fd2, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(target, 1); + +cleanup1: + err = bpf_prog_detach_opts(fd1, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(target, 0); + +cleanup: + test_tc_link__destroy(skel); +} + +void serial_test_tc_opts_detach_after(void) +{ + test_tc_opts_detach_after_target(BPF_TCX_INGRESS); + test_tc_opts_detach_after_target(BPF_TCX_EGRESS); +} + +static void test_tc_opts_delete_empty(int target, bool chain_tc_old) +{ + LIBBPF_OPTS(bpf_tc_hook, tc_hook, .ifindex = loopback); + LIBBPF_OPTS(bpf_prog_detach_opts, optd); + int err; + + assert_mprog_count(target, 0); + if (chain_tc_old) { + tc_hook.attach_point = target == BPF_TCX_INGRESS ? + BPF_TC_INGRESS : BPF_TC_EGRESS; + err = bpf_tc_hook_create(&tc_hook); + ASSERT_OK(err, "bpf_tc_hook_create"); + __assert_mprog_count(target, 0, true, loopback); + } + err = bpf_prog_detach_opts(0, loopback, target, &optd); + ASSERT_EQ(err, -ENOENT, "prog_detach"); + if (chain_tc_old) { + tc_hook.attach_point = BPF_TC_INGRESS | BPF_TC_EGRESS; + bpf_tc_hook_destroy(&tc_hook); + } + assert_mprog_count(target, 0); +} + +void serial_test_tc_opts_delete_empty(void) +{ + test_tc_opts_delete_empty(BPF_TCX_INGRESS, false); + test_tc_opts_delete_empty(BPF_TCX_EGRESS, false); + test_tc_opts_delete_empty(BPF_TCX_INGRESS, true); + test_tc_opts_delete_empty(BPF_TCX_EGRESS, true); +} + +static void test_tc_chain_mixed(int target) +{ + LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1); + LIBBPF_OPTS(bpf_tc_hook, tc_hook, .ifindex = loopback); + LIBBPF_OPTS(bpf_prog_attach_opts, opta); + LIBBPF_OPTS(bpf_prog_detach_opts, optd); + __u32 fd1, fd2, fd3, id1, id2, id3; + struct test_tc_link *skel; + int err, detach_fd; + + skel = test_tc_link__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_load")) + goto cleanup; + + fd1 = bpf_program__fd(skel->progs.tc4); + fd2 = bpf_program__fd(skel->progs.tc5); + fd3 = bpf_program__fd(skel->progs.tc6); + + id1 = id_from_prog_fd(fd1); + id2 = id_from_prog_fd(fd2); + id3 = id_from_prog_fd(fd3); + + ASSERT_NEQ(id1, id2, "prog_ids_1_2"); + ASSERT_NEQ(id2, id3, "prog_ids_2_3"); + + assert_mprog_count(target, 0); + + tc_hook.attach_point = target == BPF_TCX_INGRESS ? + BPF_TC_INGRESS : BPF_TC_EGRESS; + err = bpf_tc_hook_create(&tc_hook); + err = err == -EEXIST ? 0 : err; + if (!ASSERT_OK(err, "bpf_tc_hook_create")) + goto cleanup; + + tc_opts.prog_fd = fd2; + err = bpf_tc_attach(&tc_hook, &tc_opts); + if (!ASSERT_OK(err, "bpf_tc_attach")) + goto cleanup_hook; + + err = bpf_prog_attach_opts(fd3, loopback, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup_filter; + + detach_fd = fd3; + + assert_mprog_count(target, 1); + + ASSERT_OK(system(ping_cmd), ping_cmd); + + ASSERT_EQ(skel->bss->seen_tc4, false, "seen_tc4"); + ASSERT_EQ(skel->bss->seen_tc5, false, "seen_tc5"); + ASSERT_EQ(skel->bss->seen_tc6, true, "seen_tc6"); + + skel->bss->seen_tc4 = false; + skel->bss->seen_tc5 = false; + skel->bss->seen_tc6 = false; + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_REPLACE, + .replace_prog_fd = fd3, + ); + + err = bpf_prog_attach_opts(fd1, loopback, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup_opts; + + detach_fd = fd1; + + assert_mprog_count(target, 1); + + ASSERT_OK(system(ping_cmd), ping_cmd); + + ASSERT_EQ(skel->bss->seen_tc4, true, "seen_tc4"); + ASSERT_EQ(skel->bss->seen_tc5, true, "seen_tc5"); + ASSERT_EQ(skel->bss->seen_tc6, false, "seen_tc6"); + + skel->bss->seen_tc4 = false; + skel->bss->seen_tc5 = false; + skel->bss->seen_tc6 = false; + +cleanup_opts: + err = bpf_prog_detach_opts(detach_fd, loopback, target, &optd); + ASSERT_OK(err, "prog_detach"); + __assert_mprog_count(target, 0, true, loopback); + + ASSERT_OK(system(ping_cmd), ping_cmd); + + ASSERT_EQ(skel->bss->seen_tc4, false, "seen_tc4"); + ASSERT_EQ(skel->bss->seen_tc5, true, "seen_tc5"); + ASSERT_EQ(skel->bss->seen_tc6, false, "seen_tc6"); + +cleanup_filter: + tc_opts.flags = tc_opts.prog_fd = tc_opts.prog_id = 0; + err = bpf_tc_detach(&tc_hook, &tc_opts); + ASSERT_OK(err, "bpf_tc_detach"); + +cleanup_hook: + tc_hook.attach_point = BPF_TC_INGRESS | BPF_TC_EGRESS; + bpf_tc_hook_destroy(&tc_hook); + +cleanup: + test_tc_link__destroy(skel); +} + +void serial_test_tc_opts_chain_mixed(void) +{ + test_tc_chain_mixed(BPF_TCX_INGRESS); + test_tc_chain_mixed(BPF_TCX_EGRESS); +} diff --git a/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c b/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c index 13bcaeb028b8..56685fc03c7e 100644 --- a/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c +++ b/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c @@ -347,7 +347,7 @@ static void syncookie_estab(void) exp_active_estab_in.max_delack_ms = 22; exp_passive_hdr_stg.syncookie = true; - exp_active_hdr_stg.resend_syn = true, + exp_active_hdr_stg.resend_syn = true; prepare_out(); diff --git a/tools/testing/selftests/bpf/prog_tests/test_ldsx_insn.c b/tools/testing/selftests/bpf/prog_tests/test_ldsx_insn.c new file mode 100644 index 000000000000..375677c19146 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/test_ldsx_insn.c @@ -0,0 +1,139 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates.*/ + +#include <test_progs.h> +#include <network_helpers.h> +#include "test_ldsx_insn.skel.h" + +static void test_map_val_and_probed_memory(void) +{ + struct test_ldsx_insn *skel; + int err; + + skel = test_ldsx_insn__open(); + if (!ASSERT_OK_PTR(skel, "test_ldsx_insn__open")) + return; + + if (skel->rodata->skip) { + test__skip(); + goto out; + } + + bpf_program__set_autoload(skel->progs.rdonly_map_prog, true); + bpf_program__set_autoload(skel->progs.map_val_prog, true); + bpf_program__set_autoload(skel->progs.test_ptr_struct_arg, true); + + err = test_ldsx_insn__load(skel); + if (!ASSERT_OK(err, "test_ldsx_insn__load")) + goto out; + + err = test_ldsx_insn__attach(skel); + if (!ASSERT_OK(err, "test_ldsx_insn__attach")) + goto out; + + ASSERT_OK(trigger_module_test_read(256), "trigger_read"); + + ASSERT_EQ(skel->bss->done1, 1, "done1"); + ASSERT_EQ(skel->bss->ret1, 1, "ret1"); + ASSERT_EQ(skel->bss->done2, 1, "done2"); + ASSERT_EQ(skel->bss->ret2, 1, "ret2"); + ASSERT_EQ(skel->bss->int_member, -1, "int_member"); + +out: + test_ldsx_insn__destroy(skel); +} + +static void test_ctx_member_sign_ext(void) +{ + struct test_ldsx_insn *skel; + int err, fd, cgroup_fd; + char buf[16] = {0}; + socklen_t optlen; + + cgroup_fd = test__join_cgroup("/ldsx_test"); + if (!ASSERT_GE(cgroup_fd, 0, "join_cgroup /ldsx_test")) + return; + + skel = test_ldsx_insn__open(); + if (!ASSERT_OK_PTR(skel, "test_ldsx_insn__open")) + goto close_cgroup_fd; + + if (skel->rodata->skip) { + test__skip(); + goto destroy_skel; + } + + bpf_program__set_autoload(skel->progs._getsockopt, true); + + err = test_ldsx_insn__load(skel); + if (!ASSERT_OK(err, "test_ldsx_insn__load")) + goto destroy_skel; + + skel->links._getsockopt = + bpf_program__attach_cgroup(skel->progs._getsockopt, cgroup_fd); + if (!ASSERT_OK_PTR(skel->links._getsockopt, "getsockopt_link")) + goto destroy_skel; + + fd = socket(AF_INET, SOCK_STREAM, 0); + if (!ASSERT_GE(fd, 0, "socket")) + goto destroy_skel; + + optlen = sizeof(buf); + (void)getsockopt(fd, SOL_IP, IP_TTL, buf, &optlen); + + ASSERT_EQ(skel->bss->set_optlen, -1, "optlen"); + ASSERT_EQ(skel->bss->set_retval, -1, "retval"); + + close(fd); +destroy_skel: + test_ldsx_insn__destroy(skel); +close_cgroup_fd: + close(cgroup_fd); +} + +static void test_ctx_member_narrow_sign_ext(void) +{ + struct test_ldsx_insn *skel; + struct __sk_buff skb = {}; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .ctx_in = &skb, + .ctx_size_in = sizeof(skb), + ); + int err, prog_fd; + + skel = test_ldsx_insn__open(); + if (!ASSERT_OK_PTR(skel, "test_ldsx_insn__open")) + return; + + if (skel->rodata->skip) { + test__skip(); + goto out; + } + + bpf_program__set_autoload(skel->progs._tc, true); + + err = test_ldsx_insn__load(skel); + if (!ASSERT_OK(err, "test_ldsx_insn__load")) + goto out; + + prog_fd = bpf_program__fd(skel->progs._tc); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); + + ASSERT_EQ(skel->bss->set_mark, -2, "set_mark"); + +out: + test_ldsx_insn__destroy(skel); +} + +void test_ldsx_insn(void) +{ + if (test__start_subtest("map_val and probed_memory")) + test_map_val_and_probed_memory(); + if (test__start_subtest("ctx_member_sign_ext")) + test_ctx_member_sign_ext(); + if (test__start_subtest("ctx_member_narrow_sign_ext")) + test_ctx_member_narrow_sign_ext(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/tracing_struct.c b/tools/testing/selftests/bpf/prog_tests/tracing_struct.c index 1c75a32186d6..fe0fb0c9849a 100644 --- a/tools/testing/selftests/bpf/prog_tests/tracing_struct.c +++ b/tools/testing/selftests/bpf/prog_tests/tracing_struct.c @@ -55,6 +55,25 @@ static void test_fentry(void) ASSERT_EQ(skel->bss->t6, 1, "t6 ret"); + ASSERT_EQ(skel->bss->t7_a, 16, "t7:a"); + ASSERT_EQ(skel->bss->t7_b, 17, "t7:b"); + ASSERT_EQ(skel->bss->t7_c, 18, "t7:c"); + ASSERT_EQ(skel->bss->t7_d, 19, "t7:d"); + ASSERT_EQ(skel->bss->t7_e, 20, "t7:e"); + ASSERT_EQ(skel->bss->t7_f_a, 21, "t7:f.a"); + ASSERT_EQ(skel->bss->t7_f_b, 22, "t7:f.b"); + ASSERT_EQ(skel->bss->t7_ret, 133, "t7 ret"); + + ASSERT_EQ(skel->bss->t8_a, 16, "t8:a"); + ASSERT_EQ(skel->bss->t8_b, 17, "t8:b"); + ASSERT_EQ(skel->bss->t8_c, 18, "t8:c"); + ASSERT_EQ(skel->bss->t8_d, 19, "t8:d"); + ASSERT_EQ(skel->bss->t8_e, 20, "t8:e"); + ASSERT_EQ(skel->bss->t8_f_a, 21, "t8:f.a"); + ASSERT_EQ(skel->bss->t8_f_b, 22, "t8:f.b"); + ASSERT_EQ(skel->bss->t8_g, 23, "t8:g"); + ASSERT_EQ(skel->bss->t8_ret, 156, "t8 ret"); + tracing_struct__detach(skel); destroy_skel: tracing_struct__destroy(skel); diff --git a/tools/testing/selftests/bpf/prog_tests/trampoline_count.c b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c index e91d0d1769f1..6cd7349d4a2b 100644 --- a/tools/testing/selftests/bpf/prog_tests/trampoline_count.c +++ b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c @@ -88,8 +88,8 @@ void serial_test_trampoline_count(void) if (!ASSERT_OK(err, "bpf_prog_test_run_opts")) goto cleanup; - ASSERT_EQ(opts.retval & 0xffff, 4, "bpf_modify_return_test.result"); - ASSERT_EQ(opts.retval >> 16, 1, "bpf_modify_return_test.side_effect"); + ASSERT_EQ(opts.retval & 0xffff, 33, "bpf_modify_return_test.result"); + ASSERT_EQ(opts.retval >> 16, 2, "bpf_modify_return_test.side_effect"); cleanup: for (; i >= 0; i--) { diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c new file mode 100644 index 000000000000..cd051d3901a9 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c @@ -0,0 +1,415 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <unistd.h> +#include <test_progs.h> +#include "uprobe_multi.skel.h" +#include "uprobe_multi_bench.skel.h" +#include "uprobe_multi_usdt.skel.h" +#include "bpf/libbpf_internal.h" +#include "testing_helpers.h" + +static char test_data[] = "test_data"; + +noinline void uprobe_multi_func_1(void) +{ + asm volatile (""); +} + +noinline void uprobe_multi_func_2(void) +{ + asm volatile (""); +} + +noinline void uprobe_multi_func_3(void) +{ + asm volatile (""); +} + +struct child { + int go[2]; + int pid; +}; + +static void release_child(struct child *child) +{ + int child_status; + + if (!child) + return; + close(child->go[1]); + close(child->go[0]); + if (child->pid > 0) + waitpid(child->pid, &child_status, 0); +} + +static void kick_child(struct child *child) +{ + char c = 1; + + if (child) { + write(child->go[1], &c, 1); + release_child(child); + } + fflush(NULL); +} + +static struct child *spawn_child(void) +{ + static struct child child; + int err; + int c; + + /* pipe to notify child to execute the trigger functions */ + if (pipe(child.go)) + return NULL; + + child.pid = fork(); + if (child.pid < 0) { + release_child(&child); + errno = EINVAL; + return NULL; + } + + /* child */ + if (child.pid == 0) { + close(child.go[1]); + + /* wait for parent's kick */ + err = read(child.go[0], &c, 1); + if (err != 1) + exit(err); + + uprobe_multi_func_1(); + uprobe_multi_func_2(); + uprobe_multi_func_3(); + + exit(errno); + } + + return &child; +} + +static void uprobe_multi_test_run(struct uprobe_multi *skel, struct child *child) +{ + skel->bss->uprobe_multi_func_1_addr = (__u64) uprobe_multi_func_1; + skel->bss->uprobe_multi_func_2_addr = (__u64) uprobe_multi_func_2; + skel->bss->uprobe_multi_func_3_addr = (__u64) uprobe_multi_func_3; + + skel->bss->user_ptr = test_data; + + /* + * Disable pid check in bpf program if we are pid filter test, + * because the probe should be executed only by child->pid + * passed at the probe attach. + */ + skel->bss->pid = child ? 0 : getpid(); + + if (child) + kick_child(child); + + /* trigger all probes */ + uprobe_multi_func_1(); + uprobe_multi_func_2(); + uprobe_multi_func_3(); + + /* + * There are 2 entry and 2 exit probe called for each uprobe_multi_func_[123] + * function and each slepable probe (6) increments uprobe_multi_sleep_result. + */ + ASSERT_EQ(skel->bss->uprobe_multi_func_1_result, 2, "uprobe_multi_func_1_result"); + ASSERT_EQ(skel->bss->uprobe_multi_func_2_result, 2, "uprobe_multi_func_2_result"); + ASSERT_EQ(skel->bss->uprobe_multi_func_3_result, 2, "uprobe_multi_func_3_result"); + + ASSERT_EQ(skel->bss->uretprobe_multi_func_1_result, 2, "uretprobe_multi_func_1_result"); + ASSERT_EQ(skel->bss->uretprobe_multi_func_2_result, 2, "uretprobe_multi_func_2_result"); + ASSERT_EQ(skel->bss->uretprobe_multi_func_3_result, 2, "uretprobe_multi_func_3_result"); + + ASSERT_EQ(skel->bss->uprobe_multi_sleep_result, 6, "uprobe_multi_sleep_result"); + + if (child) + ASSERT_EQ(skel->bss->child_pid, child->pid, "uprobe_multi_child_pid"); +} + +static void test_skel_api(void) +{ + struct uprobe_multi *skel = NULL; + int err; + + skel = uprobe_multi__open_and_load(); + if (!ASSERT_OK_PTR(skel, "uprobe_multi__open_and_load")) + goto cleanup; + + err = uprobe_multi__attach(skel); + if (!ASSERT_OK(err, "uprobe_multi__attach")) + goto cleanup; + + uprobe_multi_test_run(skel, NULL); + +cleanup: + uprobe_multi__destroy(skel); +} + +static void +__test_attach_api(const char *binary, const char *pattern, struct bpf_uprobe_multi_opts *opts, + struct child *child) +{ + pid_t pid = child ? child->pid : -1; + struct uprobe_multi *skel = NULL; + + skel = uprobe_multi__open_and_load(); + if (!ASSERT_OK_PTR(skel, "uprobe_multi__open_and_load")) + goto cleanup; + + opts->retprobe = false; + skel->links.uprobe = bpf_program__attach_uprobe_multi(skel->progs.uprobe, pid, + binary, pattern, opts); + if (!ASSERT_OK_PTR(skel->links.uprobe, "bpf_program__attach_uprobe_multi")) + goto cleanup; + + opts->retprobe = true; + skel->links.uretprobe = bpf_program__attach_uprobe_multi(skel->progs.uretprobe, pid, + binary, pattern, opts); + if (!ASSERT_OK_PTR(skel->links.uretprobe, "bpf_program__attach_uprobe_multi")) + goto cleanup; + + opts->retprobe = false; + skel->links.uprobe_sleep = bpf_program__attach_uprobe_multi(skel->progs.uprobe_sleep, pid, + binary, pattern, opts); + if (!ASSERT_OK_PTR(skel->links.uprobe_sleep, "bpf_program__attach_uprobe_multi")) + goto cleanup; + + opts->retprobe = true; + skel->links.uretprobe_sleep = bpf_program__attach_uprobe_multi(skel->progs.uretprobe_sleep, + pid, binary, pattern, opts); + if (!ASSERT_OK_PTR(skel->links.uretprobe_sleep, "bpf_program__attach_uprobe_multi")) + goto cleanup; + + opts->retprobe = false; + skel->links.uprobe_extra = bpf_program__attach_uprobe_multi(skel->progs.uprobe_extra, -1, + binary, pattern, opts); + if (!ASSERT_OK_PTR(skel->links.uprobe_extra, "bpf_program__attach_uprobe_multi")) + goto cleanup; + + uprobe_multi_test_run(skel, child); + +cleanup: + uprobe_multi__destroy(skel); +} + +static void +test_attach_api(const char *binary, const char *pattern, struct bpf_uprobe_multi_opts *opts) +{ + struct child *child; + + /* no pid filter */ + __test_attach_api(binary, pattern, opts, NULL); + + /* pid filter */ + child = spawn_child(); + if (!ASSERT_OK_PTR(child, "spawn_child")) + return; + + __test_attach_api(binary, pattern, opts, child); +} + +static void test_attach_api_pattern(void) +{ + LIBBPF_OPTS(bpf_uprobe_multi_opts, opts); + + test_attach_api("/proc/self/exe", "uprobe_multi_func_*", &opts); + test_attach_api("/proc/self/exe", "uprobe_multi_func_?", &opts); +} + +static void test_attach_api_syms(void) +{ + LIBBPF_OPTS(bpf_uprobe_multi_opts, opts); + const char *syms[3] = { + "uprobe_multi_func_1", + "uprobe_multi_func_2", + "uprobe_multi_func_3", + }; + + opts.syms = syms; + opts.cnt = ARRAY_SIZE(syms); + test_attach_api("/proc/self/exe", NULL, &opts); +} + +static void __test_link_api(struct child *child) +{ + int prog_fd, link1_fd = -1, link2_fd = -1, link3_fd = -1, link4_fd = -1; + LIBBPF_OPTS(bpf_link_create_opts, opts); + const char *path = "/proc/self/exe"; + struct uprobe_multi *skel = NULL; + unsigned long *offsets = NULL; + const char *syms[3] = { + "uprobe_multi_func_1", + "uprobe_multi_func_2", + "uprobe_multi_func_3", + }; + int link_extra_fd = -1; + int err; + + err = elf_resolve_syms_offsets(path, 3, syms, (unsigned long **) &offsets); + if (!ASSERT_OK(err, "elf_resolve_syms_offsets")) + return; + + opts.uprobe_multi.path = path; + opts.uprobe_multi.offsets = offsets; + opts.uprobe_multi.cnt = ARRAY_SIZE(syms); + opts.uprobe_multi.pid = child ? child->pid : 0; + + skel = uprobe_multi__open_and_load(); + if (!ASSERT_OK_PTR(skel, "uprobe_multi__open_and_load")) + goto cleanup; + + opts.kprobe_multi.flags = 0; + prog_fd = bpf_program__fd(skel->progs.uprobe); + link1_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts); + if (!ASSERT_GE(link1_fd, 0, "link1_fd")) + goto cleanup; + + opts.kprobe_multi.flags = BPF_F_UPROBE_MULTI_RETURN; + prog_fd = bpf_program__fd(skel->progs.uretprobe); + link2_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts); + if (!ASSERT_GE(link2_fd, 0, "link2_fd")) + goto cleanup; + + opts.kprobe_multi.flags = 0; + prog_fd = bpf_program__fd(skel->progs.uprobe_sleep); + link3_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts); + if (!ASSERT_GE(link3_fd, 0, "link3_fd")) + goto cleanup; + + opts.kprobe_multi.flags = BPF_F_UPROBE_MULTI_RETURN; + prog_fd = bpf_program__fd(skel->progs.uretprobe_sleep); + link4_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts); + if (!ASSERT_GE(link4_fd, 0, "link4_fd")) + goto cleanup; + + opts.kprobe_multi.flags = 0; + opts.uprobe_multi.pid = 0; + prog_fd = bpf_program__fd(skel->progs.uprobe_extra); + link_extra_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts); + if (!ASSERT_GE(link_extra_fd, 0, "link_extra_fd")) + goto cleanup; + + uprobe_multi_test_run(skel, child); + +cleanup: + if (link1_fd >= 0) + close(link1_fd); + if (link2_fd >= 0) + close(link2_fd); + if (link3_fd >= 0) + close(link3_fd); + if (link4_fd >= 0) + close(link4_fd); + if (link_extra_fd >= 0) + close(link_extra_fd); + + uprobe_multi__destroy(skel); + free(offsets); +} + +void test_link_api(void) +{ + struct child *child; + + /* no pid filter */ + __test_link_api(NULL); + + /* pid filter */ + child = spawn_child(); + if (!ASSERT_OK_PTR(child, "spawn_child")) + return; + + __test_link_api(child); +} + +static void test_bench_attach_uprobe(void) +{ + long attach_start_ns = 0, attach_end_ns = 0; + struct uprobe_multi_bench *skel = NULL; + long detach_start_ns, detach_end_ns; + double attach_delta, detach_delta; + int err; + + skel = uprobe_multi_bench__open_and_load(); + if (!ASSERT_OK_PTR(skel, "uprobe_multi_bench__open_and_load")) + goto cleanup; + + attach_start_ns = get_time_ns(); + + err = uprobe_multi_bench__attach(skel); + if (!ASSERT_OK(err, "uprobe_multi_bench__attach")) + goto cleanup; + + attach_end_ns = get_time_ns(); + + system("./uprobe_multi bench"); + + ASSERT_EQ(skel->bss->count, 50000, "uprobes_count"); + +cleanup: + detach_start_ns = get_time_ns(); + uprobe_multi_bench__destroy(skel); + detach_end_ns = get_time_ns(); + + attach_delta = (attach_end_ns - attach_start_ns) / 1000000000.0; + detach_delta = (detach_end_ns - detach_start_ns) / 1000000000.0; + + printf("%s: attached in %7.3lfs\n", __func__, attach_delta); + printf("%s: detached in %7.3lfs\n", __func__, detach_delta); +} + +static void test_bench_attach_usdt(void) +{ + long attach_start_ns = 0, attach_end_ns = 0; + struct uprobe_multi_usdt *skel = NULL; + long detach_start_ns, detach_end_ns; + double attach_delta, detach_delta; + + skel = uprobe_multi_usdt__open_and_load(); + if (!ASSERT_OK_PTR(skel, "uprobe_multi__open")) + goto cleanup; + + attach_start_ns = get_time_ns(); + + skel->links.usdt0 = bpf_program__attach_usdt(skel->progs.usdt0, -1, "./uprobe_multi", + "test", "usdt", NULL); + if (!ASSERT_OK_PTR(skel->links.usdt0, "bpf_program__attach_usdt")) + goto cleanup; + + attach_end_ns = get_time_ns(); + + system("./uprobe_multi usdt"); + + ASSERT_EQ(skel->bss->count, 50000, "usdt_count"); + +cleanup: + detach_start_ns = get_time_ns(); + uprobe_multi_usdt__destroy(skel); + detach_end_ns = get_time_ns(); + + attach_delta = (attach_end_ns - attach_start_ns) / 1000000000.0; + detach_delta = (detach_end_ns - detach_start_ns) / 1000000000.0; + + printf("%s: attached in %7.3lfs\n", __func__, attach_delta); + printf("%s: detached in %7.3lfs\n", __func__, detach_delta); +} + +void test_uprobe_multi_test(void) +{ + if (test__start_subtest("skel_api")) + test_skel_api(); + if (test__start_subtest("attach_api_pattern")) + test_attach_api_pattern(); + if (test__start_subtest("attach_api_syms")) + test_attach_api_syms(); + if (test__start_subtest("link_api")) + test_link_api(); + if (test__start_subtest("bench_uprobe")) + test_bench_attach_uprobe(); + if (test__start_subtest("bench_usdt")) + test_bench_attach_usdt(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c index 070a13833c3f..e3e68c97b40c 100644 --- a/tools/testing/selftests/bpf/prog_tests/verifier.c +++ b/tools/testing/selftests/bpf/prog_tests/verifier.c @@ -11,6 +11,7 @@ #include "verifier_bounds_deduction_non_const.skel.h" #include "verifier_bounds_mix_sign_unsign.skel.h" #include "verifier_bpf_get_stack.skel.h" +#include "verifier_bswap.skel.h" #include "verifier_btf_ctx_access.skel.h" #include "verifier_cfg.skel.h" #include "verifier_cgroup_inv_retcode.skel.h" @@ -24,6 +25,7 @@ #include "verifier_direct_stack_access_wraparound.skel.h" #include "verifier_div0.skel.h" #include "verifier_div_overflow.skel.h" +#include "verifier_gotol.skel.h" #include "verifier_helper_access_var_len.skel.h" #include "verifier_helper_packet_access.skel.h" #include "verifier_helper_restricted.skel.h" @@ -31,6 +33,7 @@ #include "verifier_int_ptr.skel.h" #include "verifier_jeq_infer_not_null.skel.h" #include "verifier_ld_ind.skel.h" +#include "verifier_ldsx.skel.h" #include "verifier_leak_ptr.skel.h" #include "verifier_loops1.skel.h" #include "verifier_lwt.skel.h" @@ -40,6 +43,7 @@ #include "verifier_map_ret_val.skel.h" #include "verifier_masking.skel.h" #include "verifier_meta_access.skel.h" +#include "verifier_movsx.skel.h" #include "verifier_netfilter_ctx.skel.h" #include "verifier_netfilter_retcode.skel.h" #include "verifier_prevent_map_lookup.skel.h" @@ -51,6 +55,7 @@ #include "verifier_ringbuf.skel.h" #include "verifier_runtime_jit.skel.h" #include "verifier_scalar_ids.skel.h" +#include "verifier_sdiv.skel.h" #include "verifier_search_pruning.skel.h" #include "verifier_sock.skel.h" #include "verifier_spill_fill.skel.h" @@ -58,6 +63,7 @@ #include "verifier_stack_ptr.skel.h" #include "verifier_subprog_precision.skel.h" #include "verifier_subreg.skel.h" +#include "verifier_typedef.skel.h" #include "verifier_uninit.skel.h" #include "verifier_unpriv.skel.h" #include "verifier_unpriv_perf.skel.h" @@ -112,6 +118,7 @@ void test_verifier_bounds_deduction(void) { RUN(verifier_bounds_deduction); void test_verifier_bounds_deduction_non_const(void) { RUN(verifier_bounds_deduction_non_const); } void test_verifier_bounds_mix_sign_unsign(void) { RUN(verifier_bounds_mix_sign_unsign); } void test_verifier_bpf_get_stack(void) { RUN(verifier_bpf_get_stack); } +void test_verifier_bswap(void) { RUN(verifier_bswap); } void test_verifier_btf_ctx_access(void) { RUN(verifier_btf_ctx_access); } void test_verifier_cfg(void) { RUN(verifier_cfg); } void test_verifier_cgroup_inv_retcode(void) { RUN(verifier_cgroup_inv_retcode); } @@ -125,6 +132,7 @@ void test_verifier_direct_packet_access(void) { RUN(verifier_direct_packet_acces void test_verifier_direct_stack_access_wraparound(void) { RUN(verifier_direct_stack_access_wraparound); } void test_verifier_div0(void) { RUN(verifier_div0); } void test_verifier_div_overflow(void) { RUN(verifier_div_overflow); } +void test_verifier_gotol(void) { RUN(verifier_gotol); } void test_verifier_helper_access_var_len(void) { RUN(verifier_helper_access_var_len); } void test_verifier_helper_packet_access(void) { RUN(verifier_helper_packet_access); } void test_verifier_helper_restricted(void) { RUN(verifier_helper_restricted); } @@ -132,6 +140,7 @@ void test_verifier_helper_value_access(void) { RUN(verifier_helper_value_access void test_verifier_int_ptr(void) { RUN(verifier_int_ptr); } void test_verifier_jeq_infer_not_null(void) { RUN(verifier_jeq_infer_not_null); } void test_verifier_ld_ind(void) { RUN(verifier_ld_ind); } +void test_verifier_ldsx(void) { RUN(verifier_ldsx); } void test_verifier_leak_ptr(void) { RUN(verifier_leak_ptr); } void test_verifier_loops1(void) { RUN(verifier_loops1); } void test_verifier_lwt(void) { RUN(verifier_lwt); } @@ -141,6 +150,7 @@ void test_verifier_map_ptr_mixing(void) { RUN(verifier_map_ptr_mixing); } void test_verifier_map_ret_val(void) { RUN(verifier_map_ret_val); } void test_verifier_masking(void) { RUN(verifier_masking); } void test_verifier_meta_access(void) { RUN(verifier_meta_access); } +void test_verifier_movsx(void) { RUN(verifier_movsx); } void test_verifier_netfilter_ctx(void) { RUN(verifier_netfilter_ctx); } void test_verifier_netfilter_retcode(void) { RUN(verifier_netfilter_retcode); } void test_verifier_prevent_map_lookup(void) { RUN(verifier_prevent_map_lookup); } @@ -152,6 +162,7 @@ void test_verifier_regalloc(void) { RUN(verifier_regalloc); } void test_verifier_ringbuf(void) { RUN(verifier_ringbuf); } void test_verifier_runtime_jit(void) { RUN(verifier_runtime_jit); } void test_verifier_scalar_ids(void) { RUN(verifier_scalar_ids); } +void test_verifier_sdiv(void) { RUN(verifier_sdiv); } void test_verifier_search_pruning(void) { RUN(verifier_search_pruning); } void test_verifier_sock(void) { RUN(verifier_sock); } void test_verifier_spill_fill(void) { RUN(verifier_spill_fill); } @@ -159,6 +170,7 @@ void test_verifier_spin_lock(void) { RUN(verifier_spin_lock); } void test_verifier_stack_ptr(void) { RUN(verifier_stack_ptr); } void test_verifier_subprog_precision(void) { RUN(verifier_subprog_precision); } void test_verifier_subreg(void) { RUN(verifier_subreg); } +void test_verifier_typedef(void) { RUN(verifier_typedef); } void test_verifier_uninit(void) { RUN(verifier_uninit); } void test_verifier_unpriv(void) { RUN(verifier_unpriv); } void test_verifier_unpriv_perf(void) { RUN(verifier_unpriv_perf); } diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_attach.c index fa3cac5488f5..e6bcb6051402 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_attach.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> +#include "test_xdp_attach_fail.skel.h" #define IFINDEX_LO 1 #define XDP_FLAGS_REPLACE (1U << 4) @@ -85,10 +86,74 @@ out_1: bpf_object__close(obj1); } +#define ERRMSG_LEN 64 + +struct xdp_errmsg { + char msg[ERRMSG_LEN]; +}; + +static void on_xdp_errmsg(void *ctx, int cpu, void *data, __u32 size) +{ + struct xdp_errmsg *ctx_errmg = ctx, *tp_errmsg = data; + + memcpy(&ctx_errmg->msg, &tp_errmsg->msg, ERRMSG_LEN); +} + +static const char tgt_errmsg[] = "Invalid XDP flags for BPF link attachment"; + +static void test_xdp_attach_fail(const char *file) +{ + struct test_xdp_attach_fail *skel = NULL; + struct xdp_errmsg errmsg = {}; + struct perf_buffer *pb = NULL; + struct bpf_object *obj = NULL; + int err, fd_xdp; + + LIBBPF_OPTS(bpf_link_create_opts, opts); + + skel = test_xdp_attach_fail__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_xdp_attach_fail__open_and_load")) + goto out_close; + + err = test_xdp_attach_fail__attach(skel); + if (!ASSERT_EQ(err, 0, "test_xdp_attach_fail__attach")) + goto out_close; + + /* set up perf buffer */ + pb = perf_buffer__new(bpf_map__fd(skel->maps.xdp_errmsg_pb), 1, + on_xdp_errmsg, NULL, &errmsg, NULL); + if (!ASSERT_OK_PTR(pb, "perf_buffer__new")) + goto out_close; + + err = bpf_prog_test_load(file, BPF_PROG_TYPE_XDP, &obj, &fd_xdp); + if (!ASSERT_EQ(err, 0, "bpf_prog_test_load")) + goto out_close; + + opts.flags = 0xFF; // invalid flags to fail to attach XDP prog + err = bpf_link_create(fd_xdp, IFINDEX_LO, BPF_XDP, &opts); + if (!ASSERT_EQ(err, -EINVAL, "bpf_link_create")) + goto out_close; + + /* read perf buffer */ + err = perf_buffer__poll(pb, 100); + if (!ASSERT_GT(err, -1, "perf_buffer__poll")) + goto out_close; + + ASSERT_STRNEQ((const char *) errmsg.msg, tgt_errmsg, + 42 /* strlen(tgt_errmsg) */, "check error message"); + +out_close: + perf_buffer__free(pb); + bpf_object__close(obj); + test_xdp_attach_fail__destroy(skel); +} + void serial_test_xdp_attach(void) { if (test__start_subtest("xdp_attach")) test_xdp_attach("./test_xdp.bpf.o"); if (test__start_subtest("xdp_attach_dynptr")) test_xdp_attach("./test_xdp_dynptr.bpf.o"); + if (test__start_subtest("xdp_attach_failed")) + test_xdp_attach_fail("./xdp_dummy.bpf.o"); } diff --git a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h index cfed4df490f3..0b793a102791 100644 --- a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h +++ b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h @@ -88,6 +88,7 @@ #define sk_v6_rcv_saddr __sk_common.skc_v6_rcv_saddr #define sk_flags __sk_common.skc_flags #define sk_reuse __sk_common.skc_reuse +#define sk_cookie __sk_common.skc_cookie #define s6_addr32 in6_u.u6_addr32 diff --git a/tools/testing/selftests/bpf/progs/cgroup_tcp_skb.c b/tools/testing/selftests/bpf/progs/cgroup_tcp_skb.c new file mode 100644 index 000000000000..1e2e73f3b749 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cgroup_tcp_skb.c @@ -0,0 +1,382 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ +#include <linux/bpf.h> +#include <bpf/bpf_endian.h> +#include <bpf/bpf_helpers.h> + +#include <linux/if_ether.h> +#include <linux/in.h> +#include <linux/in6.h> +#include <linux/ipv6.h> +#include <linux/tcp.h> + +#include <sys/types.h> +#include <sys/socket.h> + +#include "cgroup_tcp_skb.h" + +char _license[] SEC("license") = "GPL"; + +__u16 g_sock_port = 0; +__u32 g_sock_state = 0; +int g_unexpected = 0; +__u32 g_packet_count = 0; + +int needed_tcp_pkt(struct __sk_buff *skb, struct tcphdr *tcph) +{ + struct ipv6hdr ip6h; + + if (skb->protocol != bpf_htons(ETH_P_IPV6)) + return 0; + if (bpf_skb_load_bytes(skb, 0, &ip6h, sizeof(ip6h))) + return 0; + + if (ip6h.nexthdr != IPPROTO_TCP) + return 0; + + if (bpf_skb_load_bytes(skb, sizeof(ip6h), tcph, sizeof(*tcph))) + return 0; + + if (tcph->source != bpf_htons(g_sock_port) && + tcph->dest != bpf_htons(g_sock_port)) + return 0; + + return 1; +} + +/* Run accept() on a socket in the cgroup to receive a new connection. */ +static int egress_accept(struct tcphdr *tcph) +{ + if (g_sock_state == SYN_RECV_SENDING_SYN_ACK) { + if (tcph->fin || !tcph->syn || !tcph->ack) + g_unexpected++; + else + g_sock_state = SYN_RECV; + return 1; + } + + return 0; +} + +static int ingress_accept(struct tcphdr *tcph) +{ + switch (g_sock_state) { + case INIT: + if (!tcph->syn || tcph->fin || tcph->ack) + g_unexpected++; + else + g_sock_state = SYN_RECV_SENDING_SYN_ACK; + break; + case SYN_RECV: + if (tcph->fin || tcph->syn || !tcph->ack) + g_unexpected++; + else + g_sock_state = ESTABLISHED; + break; + default: + return 0; + } + + return 1; +} + +/* Run connect() on a socket in the cgroup to start a new connection. */ +static int egress_connect(struct tcphdr *tcph) +{ + if (g_sock_state == INIT) { + if (!tcph->syn || tcph->fin || tcph->ack) + g_unexpected++; + else + g_sock_state = SYN_SENT; + return 1; + } + + return 0; +} + +static int ingress_connect(struct tcphdr *tcph) +{ + if (g_sock_state == SYN_SENT) { + if (tcph->fin || !tcph->syn || !tcph->ack) + g_unexpected++; + else + g_sock_state = ESTABLISHED; + return 1; + } + + return 0; +} + +/* The connection is closed by the peer outside the cgroup. */ +static int egress_close_remote(struct tcphdr *tcph) +{ + switch (g_sock_state) { + case ESTABLISHED: + break; + case CLOSE_WAIT_SENDING_ACK: + if (tcph->fin || tcph->syn || !tcph->ack) + g_unexpected++; + else + g_sock_state = CLOSE_WAIT; + break; + case CLOSE_WAIT: + if (!tcph->fin) + g_unexpected++; + else + g_sock_state = LAST_ACK; + break; + default: + return 0; + } + + return 1; +} + +static int ingress_close_remote(struct tcphdr *tcph) +{ + switch (g_sock_state) { + case ESTABLISHED: + if (tcph->fin) + g_sock_state = CLOSE_WAIT_SENDING_ACK; + break; + case LAST_ACK: + if (tcph->fin || tcph->syn || !tcph->ack) + g_unexpected++; + else + g_sock_state = CLOSED; + break; + default: + return 0; + } + + return 1; +} + +/* The connection is closed by the endpoint inside the cgroup. */ +static int egress_close_local(struct tcphdr *tcph) +{ + switch (g_sock_state) { + case ESTABLISHED: + if (tcph->fin) + g_sock_state = FIN_WAIT1; + break; + case TIME_WAIT_SENDING_ACK: + if (tcph->fin || tcph->syn || !tcph->ack) + g_unexpected++; + else + g_sock_state = TIME_WAIT; + break; + default: + return 0; + } + + return 1; +} + +static int ingress_close_local(struct tcphdr *tcph) +{ + switch (g_sock_state) { + case ESTABLISHED: + break; + case FIN_WAIT1: + if (tcph->fin || tcph->syn || !tcph->ack) + g_unexpected++; + else + g_sock_state = FIN_WAIT2; + break; + case FIN_WAIT2: + if (!tcph->fin || tcph->syn || !tcph->ack) + g_unexpected++; + else + g_sock_state = TIME_WAIT_SENDING_ACK; + break; + default: + return 0; + } + + return 1; +} + +/* Check the types of outgoing packets of a server socket to make sure they + * are consistent with the state of the server socket. + * + * The connection is closed by the client side. + */ +SEC("cgroup_skb/egress") +int server_egress(struct __sk_buff *skb) +{ + struct tcphdr tcph; + + if (!needed_tcp_pkt(skb, &tcph)) + return 1; + + g_packet_count++; + + /* Egress of the server socket. */ + if (egress_accept(&tcph) || egress_close_remote(&tcph)) + return 1; + + g_unexpected++; + return 1; +} + +/* Check the types of incoming packets of a server socket to make sure they + * are consistent with the state of the server socket. + * + * The connection is closed by the client side. + */ +SEC("cgroup_skb/ingress") +int server_ingress(struct __sk_buff *skb) +{ + struct tcphdr tcph; + + if (!needed_tcp_pkt(skb, &tcph)) + return 1; + + g_packet_count++; + + /* Ingress of the server socket. */ + if (ingress_accept(&tcph) || ingress_close_remote(&tcph)) + return 1; + + g_unexpected++; + return 1; +} + +/* Check the types of outgoing packets of a server socket to make sure they + * are consistent with the state of the server socket. + * + * The connection is closed by the server side. + */ +SEC("cgroup_skb/egress") +int server_egress_srv(struct __sk_buff *skb) +{ + struct tcphdr tcph; + + if (!needed_tcp_pkt(skb, &tcph)) + return 1; + + g_packet_count++; + + /* Egress of the server socket. */ + if (egress_accept(&tcph) || egress_close_local(&tcph)) + return 1; + + g_unexpected++; + return 1; +} + +/* Check the types of incoming packets of a server socket to make sure they + * are consistent with the state of the server socket. + * + * The connection is closed by the server side. + */ +SEC("cgroup_skb/ingress") +int server_ingress_srv(struct __sk_buff *skb) +{ + struct tcphdr tcph; + + if (!needed_tcp_pkt(skb, &tcph)) + return 1; + + g_packet_count++; + + /* Ingress of the server socket. */ + if (ingress_accept(&tcph) || ingress_close_local(&tcph)) + return 1; + + g_unexpected++; + return 1; +} + +/* Check the types of outgoing packets of a client socket to make sure they + * are consistent with the state of the client socket. + * + * The connection is closed by the server side. + */ +SEC("cgroup_skb/egress") +int client_egress_srv(struct __sk_buff *skb) +{ + struct tcphdr tcph; + + if (!needed_tcp_pkt(skb, &tcph)) + return 1; + + g_packet_count++; + + /* Egress of the server socket. */ + if (egress_connect(&tcph) || egress_close_remote(&tcph)) + return 1; + + g_unexpected++; + return 1; +} + +/* Check the types of incoming packets of a client socket to make sure they + * are consistent with the state of the client socket. + * + * The connection is closed by the server side. + */ +SEC("cgroup_skb/ingress") +int client_ingress_srv(struct __sk_buff *skb) +{ + struct tcphdr tcph; + + if (!needed_tcp_pkt(skb, &tcph)) + return 1; + + g_packet_count++; + + /* Ingress of the server socket. */ + if (ingress_connect(&tcph) || ingress_close_remote(&tcph)) + return 1; + + g_unexpected++; + return 1; +} + +/* Check the types of outgoing packets of a client socket to make sure they + * are consistent with the state of the client socket. + * + * The connection is closed by the client side. + */ +SEC("cgroup_skb/egress") +int client_egress(struct __sk_buff *skb) +{ + struct tcphdr tcph; + + if (!needed_tcp_pkt(skb, &tcph)) + return 1; + + g_packet_count++; + + /* Egress of the server socket. */ + if (egress_connect(&tcph) || egress_close_local(&tcph)) + return 1; + + g_unexpected++; + return 1; +} + +/* Check the types of incoming packets of a client socket to make sure they + * are consistent with the state of the client socket. + * + * The connection is closed by the client side. + */ +SEC("cgroup_skb/ingress") +int client_ingress(struct __sk_buff *skb) +{ + struct tcphdr tcph; + + if (!needed_tcp_pkt(skb, &tcph)) + return 1; + + g_packet_count++; + + /* Ingress of the server socket. */ + if (ingress_connect(&tcph) || ingress_close_local(&tcph)) + return 1; + + g_unexpected++; + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/fentry_many_args.c b/tools/testing/selftests/bpf/progs/fentry_many_args.c new file mode 100644 index 000000000000..b61bb92fee2c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/fentry_many_args.c @@ -0,0 +1,39 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Tencent */ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +__u64 test1_result = 0; +SEC("fentry/bpf_testmod_fentry_test7") +int BPF_PROG(test1, __u64 a, void *b, short c, int d, void *e, char f, + int g) +{ + test1_result = a == 16 && b == (void *)17 && c == 18 && d == 19 && + e == (void *)20 && f == 21 && g == 22; + return 0; +} + +__u64 test2_result = 0; +SEC("fentry/bpf_testmod_fentry_test11") +int BPF_PROG(test2, __u64 a, void *b, short c, int d, void *e, char f, + int g, unsigned int h, long i, __u64 j, unsigned long k) +{ + test2_result = a == 16 && b == (void *)17 && c == 18 && d == 19 && + e == (void *)20 && f == 21 && g == 22 && h == 23 && + i == 24 && j == 25 && k == 26; + return 0; +} + +__u64 test3_result = 0; +SEC("fentry/bpf_testmod_fentry_test11") +int BPF_PROG(test3, __u64 a, __u64 b, __u64 c, __u64 d, __u64 e, __u64 f, + __u64 g, __u64 h, __u64 i, __u64 j, __u64 k) +{ + test3_result = a == 16 && b == 17 && c == 18 && d == 19 && + e == 20 && f == 21 && g == 22 && h == 23 && + i == 24 && j == 25 && k == 26; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/fexit_many_args.c b/tools/testing/selftests/bpf/progs/fexit_many_args.c new file mode 100644 index 000000000000..53b335c2dafb --- /dev/null +++ b/tools/testing/selftests/bpf/progs/fexit_many_args.c @@ -0,0 +1,40 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Tencent */ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +__u64 test1_result = 0; +SEC("fexit/bpf_testmod_fentry_test7") +int BPF_PROG(test1, __u64 a, void *b, short c, int d, void *e, char f, + int g, int ret) +{ + test1_result = a == 16 && b == (void *)17 && c == 18 && d == 19 && + e == (void *)20 && f == 21 && g == 22 && ret == 133; + return 0; +} + +__u64 test2_result = 0; +SEC("fexit/bpf_testmod_fentry_test11") +int BPF_PROG(test2, __u64 a, void *b, short c, int d, void *e, char f, + int g, unsigned int h, long i, __u64 j, unsigned long k, + int ret) +{ + test2_result = a == 16 && b == (void *)17 && c == 18 && d == 19 && + e == (void *)20 && f == 21 && g == 22 && h == 23 && + i == 24 && j == 25 && k == 26 && ret == 231; + return 0; +} + +__u64 test3_result = 0; +SEC("fexit/bpf_testmod_fentry_test11") +int BPF_PROG(test3, __u64 a, __u64 b, __u64 c, __u64 d, __u64 e, __u64 f, + __u64 g, __u64 h, __u64 i, __u64 j, __u64 k, __u64 ret) +{ + test3_result = a == 16 && b == 17 && c == 18 && d == 19 && + e == 20 && f == 21 && g == 22 && h == 23 && + i == 24 && j == 25 && k == 26 && ret == 231; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/get_branch_snapshot.c b/tools/testing/selftests/bpf/progs/get_branch_snapshot.c index a1b139888048..511ac634eef0 100644 --- a/tools/testing/selftests/bpf/progs/get_branch_snapshot.c +++ b/tools/testing/selftests/bpf/progs/get_branch_snapshot.c @@ -15,7 +15,7 @@ long total_entries = 0; #define ENTRY_CNT 32 struct perf_branch_entry entries[ENTRY_CNT] = {}; -static inline bool in_range(__u64 val) +static inline bool gbs_in_range(__u64 val) { return (val >= address_low) && (val < address_high); } @@ -31,7 +31,7 @@ int BPF_PROG(test1, int n, int ret) for (i = 0; i < ENTRY_CNT; i++) { if (i >= total_entries) break; - if (in_range(entries[i].from) && in_range(entries[i].to)) + if (gbs_in_range(entries[i].from) && gbs_in_range(entries[i].to)) test1_hits++; else if (!test1_hits) wasted_entries++; diff --git a/tools/testing/selftests/bpf/progs/get_func_ip_test.c b/tools/testing/selftests/bpf/progs/get_func_ip_test.c index 8559e698b40d..8956eb78a226 100644 --- a/tools/testing/selftests/bpf/progs/get_func_ip_test.c +++ b/tools/testing/selftests/bpf/progs/get_func_ip_test.c @@ -1,8 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 -#include <linux/bpf.h> +#include "vmlinux.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> -#include <stdbool.h> char _license[] SEC("license") = "GPL"; @@ -83,3 +82,25 @@ int test6(struct pt_regs *ctx) test6_result = (const void *) addr == 0; return 0; } + +unsigned long uprobe_trigger; + +__u64 test7_result = 0; +SEC("uprobe//proc/self/exe:uprobe_trigger") +int BPF_UPROBE(test7) +{ + __u64 addr = bpf_get_func_ip(ctx); + + test7_result = (const void *) addr == (const void *) uprobe_trigger; + return 0; +} + +__u64 test8_result = 0; +SEC("uretprobe//proc/self/exe:uprobe_trigger") +int BPF_URETPROBE(test8, int ret) +{ + __u64 addr = bpf_get_func_ip(ctx); + + test8_result = (const void *) addr == (const void *) uprobe_trigger; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/get_func_ip_uprobe_test.c b/tools/testing/selftests/bpf/progs/get_func_ip_uprobe_test.c new file mode 100644 index 000000000000..052f8a4345a8 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/get_func_ip_uprobe_test.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +unsigned long uprobe_trigger_body; + +__u64 test1_result = 0; +SEC("uprobe//proc/self/exe:uprobe_trigger_body+1") +int BPF_UPROBE(test1) +{ + __u64 addr = bpf_get_func_ip(ctx); + + test1_result = (const void *) addr == (const void *) uprobe_trigger_body + 1; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/htab_mem_bench.c b/tools/testing/selftests/bpf/progs/htab_mem_bench.c new file mode 100644 index 000000000000..b1b721b14d67 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/htab_mem_bench.c @@ -0,0 +1,105 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023. Huawei Technologies Co., Ltd */ +#include <stdbool.h> +#include <errno.h> +#include <linux/types.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +#define OP_BATCH 64 + +struct update_ctx { + unsigned int from; + unsigned int step; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(key_size, 4); + __uint(map_flags, BPF_F_NO_PREALLOC); +} htab SEC(".maps"); + +char _license[] SEC("license") = "GPL"; + +unsigned char zeroed_value[4096]; +unsigned int nr_thread = 0; +long op_cnt = 0; + +static int write_htab(unsigned int i, struct update_ctx *ctx, unsigned int flags) +{ + bpf_map_update_elem(&htab, &ctx->from, zeroed_value, flags); + ctx->from += ctx->step; + + return 0; +} + +static int overwrite_htab(unsigned int i, struct update_ctx *ctx) +{ + return write_htab(i, ctx, 0); +} + +static int newwrite_htab(unsigned int i, struct update_ctx *ctx) +{ + return write_htab(i, ctx, BPF_NOEXIST); +} + +static int del_htab(unsigned int i, struct update_ctx *ctx) +{ + bpf_map_delete_elem(&htab, &ctx->from); + ctx->from += ctx->step; + + return 0; +} + +SEC("?tp/syscalls/sys_enter_getpgid") +int overwrite(void *ctx) +{ + struct update_ctx update; + + update.from = bpf_get_smp_processor_id(); + update.step = nr_thread; + bpf_loop(OP_BATCH, overwrite_htab, &update, 0); + __sync_fetch_and_add(&op_cnt, 1); + return 0; +} + +SEC("?tp/syscalls/sys_enter_getpgid") +int batch_add_batch_del(void *ctx) +{ + struct update_ctx update; + + update.from = bpf_get_smp_processor_id(); + update.step = nr_thread; + bpf_loop(OP_BATCH, overwrite_htab, &update, 0); + + update.from = bpf_get_smp_processor_id(); + bpf_loop(OP_BATCH, del_htab, &update, 0); + + __sync_fetch_and_add(&op_cnt, 2); + return 0; +} + +SEC("?tp/syscalls/sys_enter_getpgid") +int add_only(void *ctx) +{ + struct update_ctx update; + + update.from = bpf_get_smp_processor_id() / 2; + update.step = nr_thread / 2; + bpf_loop(OP_BATCH, newwrite_htab, &update, 0); + __sync_fetch_and_add(&op_cnt, 1); + return 0; +} + +SEC("?tp/syscalls/sys_enter_getppid") +int del_only(void *ctx) +{ + struct update_ctx update; + + update.from = bpf_get_smp_processor_id() / 2; + update.step = nr_thread / 2; + bpf_loop(OP_BATCH, del_htab, &update, 0); + __sync_fetch_and_add(&op_cnt, 1); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/ip_check_defrag.c b/tools/testing/selftests/bpf/progs/ip_check_defrag.c new file mode 100644 index 000000000000..1c2b6c1616b0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/ip_check_defrag.c @@ -0,0 +1,104 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> +#include "bpf_tracing_net.h" + +#define NF_DROP 0 +#define NF_ACCEPT 1 +#define ETH_P_IP 0x0800 +#define ETH_P_IPV6 0x86DD +#define IP_MF 0x2000 +#define IP_OFFSET 0x1FFF +#define NEXTHDR_FRAGMENT 44 + +extern int bpf_dynptr_from_skb(struct sk_buff *skb, __u64 flags, + struct bpf_dynptr *ptr__uninit) __ksym; +extern void *bpf_dynptr_slice(const struct bpf_dynptr *ptr, uint32_t offset, + void *buffer, uint32_t buffer__sz) __ksym; + +volatile int shootdowns = 0; + +static bool is_frag_v4(struct iphdr *iph) +{ + int offset; + int flags; + + offset = bpf_ntohs(iph->frag_off); + flags = offset & ~IP_OFFSET; + offset &= IP_OFFSET; + offset <<= 3; + + return (flags & IP_MF) || offset; +} + +static bool is_frag_v6(struct ipv6hdr *ip6h) +{ + /* Simplifying assumption that there are no extension headers + * between fixed header and fragmentation header. This assumption + * is only valid in this test case. It saves us the hassle of + * searching all potential extension headers. + */ + return ip6h->nexthdr == NEXTHDR_FRAGMENT; +} + +static int handle_v4(struct sk_buff *skb) +{ + struct bpf_dynptr ptr; + u8 iph_buf[20] = {}; + struct iphdr *iph; + + if (bpf_dynptr_from_skb(skb, 0, &ptr)) + return NF_DROP; + + iph = bpf_dynptr_slice(&ptr, 0, iph_buf, sizeof(iph_buf)); + if (!iph) + return NF_DROP; + + /* Shootdown any frags */ + if (is_frag_v4(iph)) { + shootdowns++; + return NF_DROP; + } + + return NF_ACCEPT; +} + +static int handle_v6(struct sk_buff *skb) +{ + struct bpf_dynptr ptr; + struct ipv6hdr *ip6h; + u8 ip6h_buf[40] = {}; + + if (bpf_dynptr_from_skb(skb, 0, &ptr)) + return NF_DROP; + + ip6h = bpf_dynptr_slice(&ptr, 0, ip6h_buf, sizeof(ip6h_buf)); + if (!ip6h) + return NF_DROP; + + /* Shootdown any frags */ + if (is_frag_v6(ip6h)) { + shootdowns++; + return NF_DROP; + } + + return NF_ACCEPT; +} + +SEC("netfilter") +int defrag(struct bpf_nf_ctx *ctx) +{ + struct sk_buff *skb = ctx->skb; + + switch (bpf_ntohs(skb->protocol)) { + case ETH_P_IP: + return handle_v4(skb); + case ETH_P_IPV6: + return handle_v6(skb); + default: + return NF_ACCEPT; + } +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/linked_list.c b/tools/testing/selftests/bpf/progs/linked_list.c index 57440a554304..84d1777a9e6c 100644 --- a/tools/testing/selftests/bpf/progs/linked_list.c +++ b/tools/testing/selftests/bpf/progs/linked_list.c @@ -96,7 +96,7 @@ static __always_inline int list_push_pop_multiple(struct bpf_spin_lock *lock, struct bpf_list_head *head, bool leave_in_map) { struct bpf_list_node *n; - struct foo *f[8], *pf; + struct foo *f[200], *pf; int i; /* Loop following this check adds nodes 2-at-a-time in order to diff --git a/tools/testing/selftests/bpf/progs/local_kptr_stash.c b/tools/testing/selftests/bpf/progs/local_kptr_stash.c index 06838083079c..b567a666d2b8 100644 --- a/tools/testing/selftests/bpf/progs/local_kptr_stash.c +++ b/tools/testing/selftests/bpf/progs/local_kptr_stash.c @@ -14,10 +14,16 @@ struct node_data { struct bpf_rb_node node; }; +struct plain_local { + long key; + long data; +}; + struct map_value { struct prog_test_ref_kfunc *not_kptr; struct prog_test_ref_kfunc __kptr *val; struct node_data __kptr *node; + struct plain_local __kptr *plain; }; /* This is necessary so that LLVM generates BTF for node_data struct @@ -67,6 +73,28 @@ long stash_rb_nodes(void *ctx) } SEC("tc") +long stash_plain(void *ctx) +{ + struct map_value *mapval; + struct plain_local *res; + int idx = 0; + + mapval = bpf_map_lookup_elem(&some_nodes, &idx); + if (!mapval) + return 1; + + res = bpf_obj_new(typeof(*res)); + if (!res) + return 1; + res->key = 41; + + res = bpf_kptr_xchg(&mapval->plain, res); + if (res) + bpf_obj_drop(res); + return 0; +} + +SEC("tc") long unstash_rb_node(void *ctx) { struct map_value *mapval; diff --git a/tools/testing/selftests/bpf/progs/local_kptr_stash_fail.c b/tools/testing/selftests/bpf/progs/local_kptr_stash_fail.c new file mode 100644 index 000000000000..fcf7a7567da2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/local_kptr_stash_fail.c @@ -0,0 +1,85 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_core_read.h> +#include "../bpf_experimental.h" +#include "bpf_misc.h" + +struct node_data { + long key; + long data; + struct bpf_rb_node node; +}; + +struct map_value { + struct node_data __kptr *node; +}; + +struct node_data2 { + long key[4]; +}; + +/* This is necessary so that LLVM generates BTF for node_data struct + * If it's not included, a fwd reference for node_data will be generated but + * no struct. Example BTF of "node" field in map_value when not included: + * + * [10] PTR '(anon)' type_id=35 + * [34] FWD 'node_data' fwd_kind=struct + * [35] TYPE_TAG 'kptr_ref' type_id=34 + */ +struct node_data *just_here_because_btf_bug; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, struct map_value); + __uint(max_entries, 2); +} some_nodes SEC(".maps"); + +SEC("tc") +__failure __msg("invalid kptr access, R2 type=ptr_node_data2 expected=ptr_node_data") +long stash_rb_nodes(void *ctx) +{ + struct map_value *mapval; + struct node_data2 *res; + int idx = 0; + + mapval = bpf_map_lookup_elem(&some_nodes, &idx); + if (!mapval) + return 1; + + res = bpf_obj_new(typeof(*res)); + if (!res) + return 1; + res->key[0] = 40; + + res = bpf_kptr_xchg(&mapval->node, res); + if (res) + bpf_obj_drop(res); + return 0; +} + +SEC("tc") +__failure __msg("R1 must have zero offset when passed to release func") +long drop_rb_node_off(void *ctx) +{ + struct map_value *mapval; + struct node_data *res; + int idx = 0; + + mapval = bpf_map_lookup_elem(&some_nodes, &idx); + if (!mapval) + return 1; + + res = bpf_obj_new(typeof(*res)); + if (!res) + return 1; + /* Try releasing with graph node offset */ + bpf_obj_drop(&res->node); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/map_percpu_stats.c b/tools/testing/selftests/bpf/progs/map_percpu_stats.c new file mode 100644 index 000000000000..10b2325c1720 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/map_percpu_stats.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Isovalent */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +__u32 target_id; + +__s64 bpf_map_sum_elem_count(struct bpf_map *map) __ksym; + +SEC("iter/bpf_map") +int dump_bpf_map(struct bpf_iter__bpf_map *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + struct bpf_map *map = ctx->map; + + if (map && map->id == target_id) + BPF_SEQ_PRINTF(seq, "%lld", bpf_map_sum_elem_count(map)); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/map_ptr_kern.c b/tools/testing/selftests/bpf/progs/map_ptr_kern.c index db388f593d0a..3325da17ec81 100644 --- a/tools/testing/selftests/bpf/progs/map_ptr_kern.c +++ b/tools/testing/selftests/bpf/progs/map_ptr_kern.c @@ -103,6 +103,8 @@ struct { __type(value, __u32); } m_hash SEC(".maps"); +__s64 bpf_map_sum_elem_count(struct bpf_map *map) __ksym; + static inline int check_hash(void) { struct bpf_htab *hash = (struct bpf_htab *)&m_hash; @@ -115,6 +117,8 @@ static inline int check_hash(void) VERIFY(hash->elem_size == 64); VERIFY(hash->count.counter == 0); + VERIFY(bpf_map_sum_elem_count(map) == 0); + for (i = 0; i < HALF_ENTRIES; ++i) { const __u32 key = i; const __u32 val = 1; @@ -123,6 +127,7 @@ static inline int check_hash(void) return 0; } VERIFY(hash->count.counter == HALF_ENTRIES); + VERIFY(bpf_map_sum_elem_count(map) == HALF_ENTRIES); return 1; } diff --git a/tools/testing/selftests/bpf/progs/modify_return.c b/tools/testing/selftests/bpf/progs/modify_return.c index 8b7466a15c6b..3376d4849f58 100644 --- a/tools/testing/selftests/bpf/progs/modify_return.c +++ b/tools/testing/selftests/bpf/progs/modify_return.c @@ -47,3 +47,43 @@ int BPF_PROG(fexit_test, int a, __u64 b, int ret) return 0; } + +static int sequence2; + +__u64 fentry_result2 = 0; +SEC("fentry/bpf_modify_return_test2") +int BPF_PROG(fentry_test2, int a, int *b, short c, int d, void *e, char f, + int g) +{ + sequence2++; + fentry_result2 = (sequence2 == 1); + return 0; +} + +__u64 fmod_ret_result2 = 0; +SEC("fmod_ret/bpf_modify_return_test2") +int BPF_PROG(fmod_ret_test2, int a, int *b, short c, int d, void *e, char f, + int g, int ret) +{ + sequence2++; + /* This is the first fmod_ret program, the ret passed should be 0 */ + fmod_ret_result2 = (sequence2 == 2 && ret == 0); + return input_retval; +} + +__u64 fexit_result2 = 0; +SEC("fexit/bpf_modify_return_test2") +int BPF_PROG(fexit_test2, int a, int *b, short c, int d, void *e, char f, + int g, int ret) +{ + sequence2++; + /* If the input_reval is non-zero a successful modification should have + * occurred. + */ + if (input_retval) + fexit_result2 = (sequence2 == 3 && ret == input_retval); + else + fexit_result2 = (sequence2 == 3 && ret == 29); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/mptcpify.c b/tools/testing/selftests/bpf/progs/mptcpify.c new file mode 100644 index 000000000000..53301ae8a8f7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/mptcpify.c @@ -0,0 +1,20 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023, SUSE. */ + +#include "vmlinux.h" +#include <bpf/bpf_tracing.h> +#include "bpf_tracing_net.h" + +char _license[] SEC("license") = "GPL"; + +SEC("fmod_ret/update_socket_protocol") +int BPF_PROG(mptcpify, int family, int type, int protocol) +{ + if ((family == AF_INET || family == AF_INET6) && + type == SOCK_STREAM && + (!protocol || protocol == IPPROTO_TCP)) { + return IPPROTO_MPTCP; + } + + return protocol; +} diff --git a/tools/testing/selftests/bpf/progs/nested_trust_failure.c b/tools/testing/selftests/bpf/progs/nested_trust_failure.c index 0d1aa6bbace4..ea39497f11ed 100644 --- a/tools/testing/selftests/bpf/progs/nested_trust_failure.c +++ b/tools/testing/selftests/bpf/progs/nested_trust_failure.c @@ -10,6 +10,13 @@ char _license[] SEC("license") = "GPL"; +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, u64); +} sk_storage_map SEC(".maps"); + /* Prototype for all of the program trace events below: * * TRACE_EVENT(task_newtask, @@ -31,3 +38,12 @@ int BPF_PROG(test_invalid_nested_offset, struct task_struct *task, u64 clone_fla bpf_cpumask_first_zero(&task->cpus_mask); return 0; } + +/* Although R2 is of type sk_buff but sock_common is expected, we will hit untrusted ptr first. */ +SEC("tp_btf/tcp_probe") +__failure __msg("R2 type=untrusted_ptr_ expected=ptr_, trusted_ptr_, rcu_ptr_") +int BPF_PROG(test_invalid_skb_field, struct sock *sk, struct sk_buff *skb) +{ + bpf_sk_storage_get(&sk_storage_map, skb->next, 0, 0); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/nested_trust_success.c b/tools/testing/selftests/bpf/progs/nested_trust_success.c index 886ade4aa99d..833840bffd3b 100644 --- a/tools/testing/selftests/bpf/progs/nested_trust_success.c +++ b/tools/testing/selftests/bpf/progs/nested_trust_success.c @@ -10,6 +10,13 @@ char _license[] SEC("license") = "GPL"; +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, u64); +} sk_storage_map SEC(".maps"); + SEC("tp_btf/task_newtask") __success int BPF_PROG(test_read_cpumask, struct task_struct *task, u64 clone_flags) @@ -17,3 +24,11 @@ int BPF_PROG(test_read_cpumask, struct task_struct *task, u64 clone_flags) bpf_cpumask_test_cpu(0, task->cpus_ptr); return 0; } + +SEC("tp_btf/tcp_probe") +__success +int BPF_PROG(test_skb_field, struct sock *sk, struct sk_buff *skb) +{ + bpf_sk_storage_get(&sk_storage_map, skb->sk, 0, 0); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/refcounted_kptr.c b/tools/testing/selftests/bpf/progs/refcounted_kptr.c index a3da610b1e6b..893a4fdb4b6e 100644 --- a/tools/testing/selftests/bpf/progs/refcounted_kptr.c +++ b/tools/testing/selftests/bpf/progs/refcounted_kptr.c @@ -8,6 +8,9 @@ #include "bpf_misc.h" #include "bpf_experimental.h" +extern void bpf_rcu_read_lock(void) __ksym; +extern void bpf_rcu_read_unlock(void) __ksym; + struct node_data { long key; long list_data; @@ -24,7 +27,7 @@ struct { __uint(type, BPF_MAP_TYPE_ARRAY); __type(key, int); __type(value, struct map_value); - __uint(max_entries, 1); + __uint(max_entries, 2); } stashed_nodes SEC(".maps"); struct node_acquire { @@ -42,6 +45,9 @@ private(A) struct bpf_list_head head __contains(node_data, l); private(B) struct bpf_spin_lock alock; private(B) struct bpf_rb_root aroot __contains(node_acquire, node); +private(C) struct bpf_spin_lock block; +private(C) struct bpf_rb_root broot __contains(node_data, r); + static bool less(struct bpf_rb_node *node_a, const struct bpf_rb_node *node_b) { struct node_data *a; @@ -405,4 +411,161 @@ long rbtree_refcounted_node_ref_escapes_owning_input(void *ctx) return 0; } +static long __stash_map_empty_xchg(struct node_data *n, int idx) +{ + struct map_value *mapval = bpf_map_lookup_elem(&stashed_nodes, &idx); + + if (!mapval) { + bpf_obj_drop(n); + return 1; + } + n = bpf_kptr_xchg(&mapval->node, n); + if (n) { + bpf_obj_drop(n); + return 2; + } + return 0; +} + +SEC("tc") +long rbtree_wrong_owner_remove_fail_a1(void *ctx) +{ + struct node_data *n, *m; + + n = bpf_obj_new(typeof(*n)); + if (!n) + return 1; + m = bpf_refcount_acquire(n); + + if (__stash_map_empty_xchg(n, 0)) { + bpf_obj_drop(m); + return 2; + } + + if (__stash_map_empty_xchg(m, 1)) + return 3; + + return 0; +} + +SEC("tc") +long rbtree_wrong_owner_remove_fail_b(void *ctx) +{ + struct map_value *mapval; + struct node_data *n; + int idx = 0; + + mapval = bpf_map_lookup_elem(&stashed_nodes, &idx); + if (!mapval) + return 1; + + n = bpf_kptr_xchg(&mapval->node, NULL); + if (!n) + return 2; + + bpf_spin_lock(&block); + + bpf_rbtree_add(&broot, &n->r, less); + + bpf_spin_unlock(&block); + return 0; +} + +SEC("tc") +long rbtree_wrong_owner_remove_fail_a2(void *ctx) +{ + struct map_value *mapval; + struct bpf_rb_node *res; + struct node_data *m; + int idx = 1; + + mapval = bpf_map_lookup_elem(&stashed_nodes, &idx); + if (!mapval) + return 1; + + m = bpf_kptr_xchg(&mapval->node, NULL); + if (!m) + return 2; + bpf_spin_lock(&lock); + + /* make m non-owning ref */ + bpf_list_push_back(&head, &m->l); + res = bpf_rbtree_remove(&root, &m->r); + + bpf_spin_unlock(&lock); + if (res) { + bpf_obj_drop(container_of(res, struct node_data, r)); + return 3; + } + return 0; +} + +SEC("?fentry.s/bpf_testmod_test_read") +__success +int BPF_PROG(rbtree_sleepable_rcu, + struct file *file, struct kobject *kobj, + struct bin_attribute *bin_attr, char *buf, loff_t off, size_t len) +{ + struct bpf_rb_node *rb; + struct node_data *n, *m = NULL; + + n = bpf_obj_new(typeof(*n)); + if (!n) + return 0; + + bpf_rcu_read_lock(); + bpf_spin_lock(&lock); + bpf_rbtree_add(&root, &n->r, less); + rb = bpf_rbtree_first(&root); + if (!rb) + goto err_out; + + rb = bpf_rbtree_remove(&root, rb); + if (!rb) + goto err_out; + + m = container_of(rb, struct node_data, r); + +err_out: + bpf_spin_unlock(&lock); + bpf_rcu_read_unlock(); + if (m) + bpf_obj_drop(m); + return 0; +} + +SEC("?fentry.s/bpf_testmod_test_read") +__success +int BPF_PROG(rbtree_sleepable_rcu_no_explicit_rcu_lock, + struct file *file, struct kobject *kobj, + struct bin_attribute *bin_attr, char *buf, loff_t off, size_t len) +{ + struct bpf_rb_node *rb; + struct node_data *n, *m = NULL; + + n = bpf_obj_new(typeof(*n)); + if (!n) + return 0; + + /* No explicit bpf_rcu_read_lock */ + bpf_spin_lock(&lock); + bpf_rbtree_add(&root, &n->r, less); + rb = bpf_rbtree_first(&root); + if (!rb) + goto err_out; + + rb = bpf_rbtree_remove(&root, rb); + if (!rb) + goto err_out; + + m = container_of(rb, struct node_data, r); + +err_out: + bpf_spin_unlock(&lock); + /* No explicit bpf_rcu_read_unlock */ + if (m) + bpf_obj_drop(m); + return 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c b/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c index 0b09e5c915b1..1ef07f6ee580 100644 --- a/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c +++ b/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c @@ -13,6 +13,9 @@ struct node_acquire { struct bpf_refcount refcount; }; +extern void bpf_rcu_read_lock(void) __ksym; +extern void bpf_rcu_read_unlock(void) __ksym; + #define private(name) SEC(".data." #name) __hidden __attribute__((aligned(8))) private(A) struct bpf_spin_lock glock; private(A) struct bpf_rb_root groot __contains(node_acquire, node); @@ -71,4 +74,29 @@ long rbtree_refcounted_node_ref_escapes_owning_input(void *ctx) return 0; } +SEC("?fentry.s/bpf_testmod_test_read") +__failure __msg("function calls are not allowed while holding a lock") +int BPF_PROG(rbtree_fail_sleepable_lock_across_rcu, + struct file *file, struct kobject *kobj, + struct bin_attribute *bin_attr, char *buf, loff_t off, size_t len) +{ + struct node_acquire *n; + + n = bpf_obj_new(typeof(*n)); + if (!n) + return 0; + + /* spin_{lock,unlock} are in different RCU CS */ + bpf_rcu_read_lock(); + bpf_spin_lock(&glock); + bpf_rbtree_add(&groot, &n->node, less); + bpf_rcu_read_unlock(); + + bpf_rcu_read_lock(); + bpf_spin_unlock(&glock); + bpf_rcu_read_unlock(); + + return 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/sk_storage_omem_uncharge.c b/tools/testing/selftests/bpf/progs/sk_storage_omem_uncharge.c new file mode 100644 index 000000000000..3e745793b27a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/sk_storage_omem_uncharge.c @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Facebook */ +#include "vmlinux.h" +#include "bpf_tracing_net.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_core_read.h> + +void *local_storage_ptr = NULL; +void *sk_ptr = NULL; +int cookie_found = 0; +__u64 cookie = 0; +__u32 omem = 0; + +void *bpf_rdonly_cast(void *, __u32) __ksym; + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, int); +} sk_storage SEC(".maps"); + +SEC("fexit/bpf_local_storage_destroy") +int BPF_PROG(bpf_local_storage_destroy, struct bpf_local_storage *local_storage) +{ + struct sock *sk; + + if (local_storage_ptr != local_storage) + return 0; + + sk = bpf_rdonly_cast(sk_ptr, bpf_core_type_id_kernel(struct sock)); + if (sk->sk_cookie.counter != cookie) + return 0; + + cookie_found++; + omem = sk->sk_omem_alloc.counter; + local_storage_ptr = NULL; + + return 0; +} + +SEC("fentry/inet6_sock_destruct") +int BPF_PROG(inet6_sock_destruct, struct sock *sk) +{ + int *value; + + if (!cookie || sk->sk_cookie.counter != cookie) + return 0; + + value = bpf_sk_storage_get(&sk_storage, sk, 0, 0); + if (value && *value == 0xdeadbeef) { + cookie_found++; + sk_ptr = sk; + local_storage_ptr = sk->sk_bpf_storage; + } + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/task_kfunc_success.c b/tools/testing/selftests/bpf/progs/task_kfunc_success.c index b09371bba204..70df695312dc 100644 --- a/tools/testing/selftests/bpf/progs/task_kfunc_success.c +++ b/tools/testing/selftests/bpf/progs/task_kfunc_success.c @@ -18,6 +18,13 @@ int err, pid; */ struct task_struct *bpf_task_acquire(struct task_struct *p) __ksym __weak; + +struct task_struct *bpf_task_acquire___one(struct task_struct *task) __ksym __weak; +/* The two-param bpf_task_acquire doesn't exist */ +struct task_struct *bpf_task_acquire___two(struct task_struct *p, void *ctx) __ksym __weak; +/* Incorrect type for first param */ +struct task_struct *bpf_task_acquire___three(void *ctx) __ksym __weak; + void invalid_kfunc(void) __ksym __weak; void bpf_testmod_test_mod_kfunc(int i) __ksym __weak; @@ -56,6 +63,50 @@ static int test_acquire_release(struct task_struct *task) } SEC("tp_btf/task_newtask") +int BPF_PROG(test_task_kfunc_flavor_relo, struct task_struct *task, u64 clone_flags) +{ + struct task_struct *acquired = NULL; + int fake_ctx = 42; + + if (bpf_ksym_exists(bpf_task_acquire___one)) { + acquired = bpf_task_acquire___one(task); + } else if (bpf_ksym_exists(bpf_task_acquire___two)) { + /* Here, bpf_object__resolve_ksym_func_btf_id's find_ksym_btf_id + * call will find vmlinux's bpf_task_acquire, but subsequent + * bpf_core_types_are_compat will fail + */ + acquired = bpf_task_acquire___two(task, &fake_ctx); + err = 3; + return 0; + } else if (bpf_ksym_exists(bpf_task_acquire___three)) { + /* bpf_core_types_are_compat will fail similarly to above case */ + acquired = bpf_task_acquire___three(&fake_ctx); + err = 4; + return 0; + } + + if (acquired) + bpf_task_release(acquired); + else + err = 5; + return 0; +} + +SEC("tp_btf/task_newtask") +int BPF_PROG(test_task_kfunc_flavor_relo_not_found, struct task_struct *task, u64 clone_flags) +{ + /* Neither symbol should successfully resolve. + * Success or failure of one ___flavor should not affect others + */ + if (bpf_ksym_exists(bpf_task_acquire___two)) + err = 1; + else if (bpf_ksym_exists(bpf_task_acquire___three)) + err = 2; + + return 0; +} + +SEC("tp_btf/task_newtask") int BPF_PROG(test_task_acquire_release_argument, struct task_struct *task, u64 clone_flags) { if (!is_test_kfunc_task()) diff --git a/tools/testing/selftests/bpf/progs/test_assign_reuse.c b/tools/testing/selftests/bpf/progs/test_assign_reuse.c new file mode 100644 index 000000000000..4f2e2321ea06 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_assign_reuse.c @@ -0,0 +1,142 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Isovalent */ +#include <stdbool.h> +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include <linux/in.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/tcp.h> +#include <linux/udp.h> +#include <bpf/bpf_endian.h> +#include <bpf/bpf_helpers.h> +#include <linux/pkt_cls.h> + +char LICENSE[] SEC("license") = "GPL"; + +__u64 sk_cookie_seen; +__u64 reuseport_executed; +union { + struct tcphdr tcp; + struct udphdr udp; +} headers; + +const volatile __u16 dest_port; + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} sk_map SEC(".maps"); + +SEC("sk_reuseport") +int reuse_accept(struct sk_reuseport_md *ctx) +{ + reuseport_executed++; + + if (ctx->ip_protocol == IPPROTO_TCP) { + if (ctx->data + sizeof(headers.tcp) > ctx->data_end) + return SK_DROP; + + if (__builtin_memcmp(&headers.tcp, ctx->data, sizeof(headers.tcp)) != 0) + return SK_DROP; + } else if (ctx->ip_protocol == IPPROTO_UDP) { + if (ctx->data + sizeof(headers.udp) > ctx->data_end) + return SK_DROP; + + if (__builtin_memcmp(&headers.udp, ctx->data, sizeof(headers.udp)) != 0) + return SK_DROP; + } else { + return SK_DROP; + } + + sk_cookie_seen = bpf_get_socket_cookie(ctx->sk); + return SK_PASS; +} + +SEC("sk_reuseport") +int reuse_drop(struct sk_reuseport_md *ctx) +{ + reuseport_executed++; + sk_cookie_seen = 0; + return SK_DROP; +} + +static int +assign_sk(struct __sk_buff *skb) +{ + int zero = 0, ret = 0; + struct bpf_sock *sk; + + sk = bpf_map_lookup_elem(&sk_map, &zero); + if (!sk) + return TC_ACT_SHOT; + ret = bpf_sk_assign(skb, sk, 0); + bpf_sk_release(sk); + return ret ? TC_ACT_SHOT : TC_ACT_OK; +} + +static bool +maybe_assign_tcp(struct __sk_buff *skb, struct tcphdr *th) +{ + if (th + 1 > (void *)(long)(skb->data_end)) + return TC_ACT_SHOT; + + if (!th->syn || th->ack || th->dest != bpf_htons(dest_port)) + return TC_ACT_OK; + + __builtin_memcpy(&headers.tcp, th, sizeof(headers.tcp)); + return assign_sk(skb); +} + +static bool +maybe_assign_udp(struct __sk_buff *skb, struct udphdr *uh) +{ + if (uh + 1 > (void *)(long)(skb->data_end)) + return TC_ACT_SHOT; + + if (uh->dest != bpf_htons(dest_port)) + return TC_ACT_OK; + + __builtin_memcpy(&headers.udp, uh, sizeof(headers.udp)); + return assign_sk(skb); +} + +SEC("tc") +int tc_main(struct __sk_buff *skb) +{ + void *data_end = (void *)(long)skb->data_end; + void *data = (void *)(long)skb->data; + struct ethhdr *eth; + + eth = (struct ethhdr *)(data); + if (eth + 1 > data_end) + return TC_ACT_SHOT; + + if (eth->h_proto == bpf_htons(ETH_P_IP)) { + struct iphdr *iph = (struct iphdr *)(data + sizeof(*eth)); + + if (iph + 1 > data_end) + return TC_ACT_SHOT; + + if (iph->protocol == IPPROTO_TCP) + return maybe_assign_tcp(skb, (struct tcphdr *)(iph + 1)); + else if (iph->protocol == IPPROTO_UDP) + return maybe_assign_udp(skb, (struct udphdr *)(iph + 1)); + else + return TC_ACT_SHOT; + } else { + struct ipv6hdr *ip6h = (struct ipv6hdr *)(data + sizeof(*eth)); + + if (ip6h + 1 > data_end) + return TC_ACT_SHOT; + + if (ip6h->nexthdr == IPPROTO_TCP) + return maybe_assign_tcp(skb, (struct tcphdr *)(ip6h + 1)); + else if (ip6h->nexthdr == IPPROTO_UDP) + return maybe_assign_udp(skb, (struct udphdr *)(ip6h + 1)); + else + return TC_ACT_SHOT; + } +} diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect.h b/tools/testing/selftests/bpf/progs/test_cls_redirect.h index 76eab0aacba0..233b089d1fba 100644 --- a/tools/testing/selftests/bpf/progs/test_cls_redirect.h +++ b/tools/testing/selftests/bpf/progs/test_cls_redirect.h @@ -12,6 +12,15 @@ #include <linux/ipv6.h> #include <linux/udp.h> +/* offsetof() is used in static asserts, and the libbpf-redefined CO-RE + * friendly version breaks compilation for older clang versions <= 15 + * when invoked in a static assert. Restore original here. + */ +#ifdef offsetof +#undef offsetof +#define offsetof(type, member) __builtin_offsetof(type, member) +#endif + struct gre_base_hdr { uint16_t flags; uint16_t protocol; diff --git a/tools/testing/selftests/bpf/progs/test_fill_link_info.c b/tools/testing/selftests/bpf/progs/test_fill_link_info.c new file mode 100644 index 000000000000..564f402d56fe --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_fill_link_info.c @@ -0,0 +1,42 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023 Yafang Shao <laoar.shao@gmail.com> */ + +#include "vmlinux.h" +#include <bpf/bpf_tracing.h> +#include <stdbool.h> + +extern bool CONFIG_X86_KERNEL_IBT __kconfig __weak; + +/* This function is here to have CONFIG_X86_KERNEL_IBT + * used and added to object BTF. + */ +int unused(void) +{ + return CONFIG_X86_KERNEL_IBT ? 0 : 1; +} + +SEC("kprobe") +int BPF_PROG(kprobe_run) +{ + return 0; +} + +SEC("uprobe") +int BPF_PROG(uprobe_run) +{ + return 0; +} + +SEC("tracepoint") +int BPF_PROG(tp_run) +{ + return 0; +} + +SEC("kprobe.multi") +int BPF_PROG(kmulti_run) +{ + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_global_map_resize.c b/tools/testing/selftests/bpf/progs/test_global_map_resize.c index 2588f2384246..1fbb73d3e5d5 100644 --- a/tools/testing/selftests/bpf/progs/test_global_map_resize.c +++ b/tools/testing/selftests/bpf/progs/test_global_map_resize.c @@ -29,13 +29,16 @@ int my_int SEC(".data.non_array"); int my_array_first[1] SEC(".data.array_not_last"); int my_int_last SEC(".data.array_not_last"); +int percpu_arr[1] SEC(".data.percpu_arr"); + SEC("tp/syscalls/sys_enter_getpid") int bss_array_sum(void *ctx) { if (pid != (bpf_get_current_pid_tgid() >> 32)) return 0; - sum = 0; + /* this will be zero, we just rely on verifier not rejecting this */ + sum = percpu_arr[bpf_get_smp_processor_id()]; for (size_t i = 0; i < bss_array_len; ++i) sum += array[i]; @@ -49,7 +52,8 @@ int data_array_sum(void *ctx) if (pid != (bpf_get_current_pid_tgid() >> 32)) return 0; - sum = 0; + /* this will be zero, we just rely on verifier not rejecting this */ + sum = percpu_arr[bpf_get_smp_processor_id()]; for (size_t i = 0; i < data_array_len; ++i) sum += my_array[i]; diff --git a/tools/testing/selftests/bpf/progs/test_ldsx_insn.c b/tools/testing/selftests/bpf/progs/test_ldsx_insn.c new file mode 100644 index 000000000000..67c14ba1e87b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_ldsx_insn.c @@ -0,0 +1,119 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \ + (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64)) && __clang_major__ >= 18 +const volatile int skip = 0; +#else +const volatile int skip = 1; +#endif + +volatile const short val1 = -1; +volatile const int val2 = -1; +short val3 = -1; +int val4 = -1; +int done1, done2, ret1, ret2; + +SEC("?raw_tp/sys_enter") +int rdonly_map_prog(const void *ctx) +{ + if (done1) + return 0; + + done1 = 1; + /* val1/val2 readonly map */ + if (val1 == val2) + ret1 = 1; + return 0; + +} + +SEC("?raw_tp/sys_enter") +int map_val_prog(const void *ctx) +{ + if (done2) + return 0; + + done2 = 1; + /* val1/val2 regular read/write map */ + if (val3 == val4) + ret2 = 1; + return 0; + +} + +struct bpf_testmod_struct_arg_1 { + int a; +}; + +long long int_member; + +SEC("?fentry/bpf_testmod_test_arg_ptr_to_struct") +int BPF_PROG2(test_ptr_struct_arg, struct bpf_testmod_struct_arg_1 *, p) +{ + /* probed memory access */ + int_member = p->a; + return 0; +} + +long long set_optlen, set_retval; + +SEC("?cgroup/getsockopt") +int _getsockopt(volatile struct bpf_sockopt *ctx) +{ + int old_optlen, old_retval; + + old_optlen = ctx->optlen; + old_retval = ctx->retval; + + ctx->optlen = -1; + ctx->retval = -1; + + /* sign extension for ctx member */ + set_optlen = ctx->optlen; + set_retval = ctx->retval; + + ctx->optlen = old_optlen; + ctx->retval = old_retval; + + return 0; +} + +long long set_mark; + +SEC("?tc") +int _tc(volatile struct __sk_buff *skb) +{ + long long tmp_mark; + int old_mark; + + old_mark = skb->mark; + + skb->mark = 0xf6fe; + + /* narrowed sign extension for ctx member */ +#if __clang_major__ >= 18 + /* force narrow one-byte signed load. Otherwise, compiler may + * generate a 32-bit unsigned load followed by an s8 movsx. + */ + asm volatile ("r1 = *(s8 *)(%[ctx] + %[off_mark])\n\t" + "%[tmp_mark] = r1" + : [tmp_mark]"=r"(tmp_mark) + : [ctx]"r"(skb), + [off_mark]"i"(offsetof(struct __sk_buff, mark)) + : "r1"); +#else + tmp_mark = (char)skb->mark; +#endif + set_mark = tmp_mark; + + skb->mark = old_mark; + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_lwt_redirect.c b/tools/testing/selftests/bpf/progs/test_lwt_redirect.c new file mode 100644 index 000000000000..8c895122f293 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_lwt_redirect.c @@ -0,0 +1,90 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_endian.h> +#include <bpf/bpf_helpers.h> +#include <linux/ip.h> +#include "bpf_tracing_net.h" + +/* We don't care about whether the packet can be received by network stack. + * Just care if the packet is sent to the correct device at correct direction + * and not panic the kernel. + */ +static int prepend_dummy_mac(struct __sk_buff *skb) +{ + char mac[] = {0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0xf, + 0xe, 0xd, 0xc, 0xb, 0xa, 0x08, 0x00}; + + if (bpf_skb_change_head(skb, ETH_HLEN, 0)) + return -1; + + if (bpf_skb_store_bytes(skb, 0, mac, sizeof(mac), 0)) + return -1; + + return 0; +} + +/* Use the last byte of IP address to redirect the packet */ +static int get_redirect_target(struct __sk_buff *skb) +{ + struct iphdr *iph = NULL; + void *start = (void *)(long)skb->data; + void *end = (void *)(long)skb->data_end; + + if (start + sizeof(*iph) > end) + return -1; + + iph = (struct iphdr *)start; + return bpf_ntohl(iph->daddr) & 0xff; +} + +SEC("redir_ingress") +int test_lwt_redirect_in(struct __sk_buff *skb) +{ + int target = get_redirect_target(skb); + + if (target < 0) + return BPF_OK; + + if (prepend_dummy_mac(skb)) + return BPF_DROP; + + return bpf_redirect(target, BPF_F_INGRESS); +} + +SEC("redir_egress") +int test_lwt_redirect_out(struct __sk_buff *skb) +{ + int target = get_redirect_target(skb); + + if (target < 0) + return BPF_OK; + + if (prepend_dummy_mac(skb)) + return BPF_DROP; + + return bpf_redirect(target, 0); +} + +SEC("redir_egress_nomac") +int test_lwt_redirect_out_nomac(struct __sk_buff *skb) +{ + int target = get_redirect_target(skb); + + if (target < 0) + return BPF_OK; + + return bpf_redirect(target, 0); +} + +SEC("redir_ingress_nomac") +int test_lwt_redirect_in_nomac(struct __sk_buff *skb) +{ + int target = get_redirect_target(skb); + + if (target < 0) + return BPF_OK; + + return bpf_redirect(target, BPF_F_INGRESS); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_lwt_reroute.c b/tools/testing/selftests/bpf/progs/test_lwt_reroute.c new file mode 100644 index 000000000000..1dc64351929c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_lwt_reroute.c @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <inttypes.h> +#include <linux/bpf.h> +#include <bpf/bpf_endian.h> +#include <bpf/bpf_helpers.h> +#include <linux/if_ether.h> +#include <linux/ip.h> + +/* This function extracts the last byte of the daddr, and uses it + * as output dev index. + */ +SEC("lwt_xmit") +int test_lwt_reroute(struct __sk_buff *skb) +{ + struct iphdr *iph = NULL; + void *start = (void *)(long)skb->data; + void *end = (void *)(long)skb->data_end; + + /* set mark at most once */ + if (skb->mark != 0) + return BPF_OK; + + if (start + sizeof(*iph) > end) + return BPF_DROP; + + iph = (struct iphdr *)start; + skb->mark = bpf_ntohl(iph->daddr) & 0xff; + + /* do not reroute x.x.x.0 packets */ + if (skb->mark == 0) + return BPF_OK; + + return BPF_LWT_REROUTE; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_netfilter_link_attach.c b/tools/testing/selftests/bpf/progs/test_netfilter_link_attach.c new file mode 100644 index 000000000000..03a475160abe --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_netfilter_link_attach.c @@ -0,0 +1,14 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +#define NF_ACCEPT 1 + +SEC("netfilter") +int nf_link_attach_test(struct bpf_nf_ctx *ctx) +{ + return NF_ACCEPT; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_ptr_untrusted.c b/tools/testing/selftests/bpf/progs/test_ptr_untrusted.c new file mode 100644 index 000000000000..4bdd65b5aa2d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_ptr_untrusted.c @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023 Yafang Shao <laoar.shao@gmail.com> */ + +#include "vmlinux.h" +#include <bpf/bpf_tracing.h> + +char tp_name[128]; + +SEC("lsm/bpf") +int BPF_PROG(lsm_run, int cmd, union bpf_attr *attr, unsigned int size) +{ + switch (cmd) { + case BPF_RAW_TRACEPOINT_OPEN: + bpf_probe_read_user_str(tp_name, sizeof(tp_name) - 1, + (void *)attr->raw_tracepoint.name); + break; + default: + break; + } + return 0; +} + +SEC("raw_tracepoint") +int BPF_PROG(raw_tp_run) +{ + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tc_bpf.c b/tools/testing/selftests/bpf/progs/test_tc_bpf.c index d28ca8d1f3d0..ef7da419632a 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_bpf.c +++ b/tools/testing/selftests/bpf/progs/test_tc_bpf.c @@ -2,6 +2,8 @@ #include <linux/bpf.h> #include <bpf/bpf_helpers.h> +#include <linux/if_ether.h> +#include <linux/ip.h> /* Dummy prog to test TC-BPF API */ @@ -10,3 +12,14 @@ int cls(struct __sk_buff *skb) { return 0; } + +/* Prog to verify tc-bpf without cap_sys_admin and cap_perfmon */ +SEC("tcx/ingress") +int pkt_ptr(struct __sk_buff *skb) +{ + struct iphdr *iph = (void *)(long)skb->data + sizeof(struct ethhdr); + + if ((long)(iph + 1) > (long)skb->data_end) + return 1; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_tc_link.c b/tools/testing/selftests/bpf/progs/test_tc_link.c new file mode 100644 index 000000000000..30e7124c49a1 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_tc_link.c @@ -0,0 +1,56 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Isovalent */ +#include <stdbool.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +char LICENSE[] SEC("license") = "GPL"; + +bool seen_tc1; +bool seen_tc2; +bool seen_tc3; +bool seen_tc4; +bool seen_tc5; +bool seen_tc6; + +SEC("tc/ingress") +int tc1(struct __sk_buff *skb) +{ + seen_tc1 = true; + return TCX_NEXT; +} + +SEC("tc/egress") +int tc2(struct __sk_buff *skb) +{ + seen_tc2 = true; + return TCX_NEXT; +} + +SEC("tc/egress") +int tc3(struct __sk_buff *skb) +{ + seen_tc3 = true; + return TCX_NEXT; +} + +SEC("tc/egress") +int tc4(struct __sk_buff *skb) +{ + seen_tc4 = true; + return TCX_NEXT; +} + +SEC("tc/egress") +int tc5(struct __sk_buff *skb) +{ + seen_tc5 = true; + return TCX_PASS; +} + +SEC("tc/egress") +int tc6(struct __sk_buff *skb) +{ + seen_tc6 = true; + return TCX_PASS; +} diff --git a/tools/testing/selftests/bpf/progs/test_xdp_attach_fail.c b/tools/testing/selftests/bpf/progs/test_xdp_attach_fail.c new file mode 100644 index 000000000000..2ff1b596e87e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_attach_fail.c @@ -0,0 +1,54 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright Leon Hwang */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +#define ERRMSG_LEN 64 + +struct xdp_errmsg { + char msg[ERRMSG_LEN]; +}; + +struct { + __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); + __type(key, int); + __type(value, int); +} xdp_errmsg_pb SEC(".maps"); + +struct xdp_attach_error_ctx { + unsigned long unused; + + /* + * bpf does not support tracepoint __data_loc directly. + * + * Actually, this field is a 32 bit integer whose value encodes + * information on where to find the actual data. The first 2 bytes is + * the size of the data. The last 2 bytes is the offset from the start + * of the tracepoint struct where the data begins. + * -- https://github.com/iovisor/bpftrace/pull/1542 + */ + __u32 msg; // __data_loc char[] msg; +}; + +/* + * Catch the error message at the tracepoint. + */ + +SEC("tp/xdp/bpf_xdp_link_attach_failed") +int tp__xdp__bpf_xdp_link_attach_failed(struct xdp_attach_error_ctx *ctx) +{ + char *msg = (void *)(__u64) ((void *) ctx + (__u16) ctx->msg); + struct xdp_errmsg errmsg = {}; + + bpf_probe_read_kernel_str(&errmsg.msg, ERRMSG_LEN, msg); + bpf_perf_event_output(ctx, &xdp_errmsg_pb, BPF_F_CURRENT_CPU, &errmsg, + ERRMSG_LEN); + return 0; +} + +/* + * Reuse the XDP program in xdp_dummy.c. + */ + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/tracing_struct.c b/tools/testing/selftests/bpf/progs/tracing_struct.c index c435a3a8328a..515daef3c84b 100644 --- a/tools/testing/selftests/bpf/progs/tracing_struct.c +++ b/tools/testing/selftests/bpf/progs/tracing_struct.c @@ -18,6 +18,11 @@ struct bpf_testmod_struct_arg_3 { int b[]; }; +struct bpf_testmod_struct_arg_4 { + u64 a; + int b; +}; + long t1_a_a, t1_a_b, t1_b, t1_c, t1_ret, t1_nregs; __u64 t1_reg0, t1_reg1, t1_reg2, t1_reg3; long t2_a, t2_b_a, t2_b_b, t2_c, t2_ret; @@ -25,6 +30,9 @@ long t3_a, t3_b, t3_c_a, t3_c_b, t3_ret; long t4_a_a, t4_b, t4_c, t4_d, t4_e_a, t4_e_b, t4_ret; long t5_ret; int t6; +long t7_a, t7_b, t7_c, t7_d, t7_e, t7_f_a, t7_f_b, t7_ret; +long t8_a, t8_b, t8_c, t8_d, t8_e, t8_f_a, t8_f_b, t8_g, t8_ret; + SEC("fentry/bpf_testmod_test_struct_arg_1") int BPF_PROG2(test_struct_arg_1, struct bpf_testmod_struct_arg_2, a, int, b, int, c) @@ -130,4 +138,50 @@ int BPF_PROG2(test_struct_arg_11, struct bpf_testmod_struct_arg_3 *, a) return 0; } +SEC("fentry/bpf_testmod_test_struct_arg_7") +int BPF_PROG2(test_struct_arg_12, __u64, a, void *, b, short, c, int, d, + void *, e, struct bpf_testmod_struct_arg_4, f) +{ + t7_a = a; + t7_b = (long)b; + t7_c = c; + t7_d = d; + t7_e = (long)e; + t7_f_a = f.a; + t7_f_b = f.b; + return 0; +} + +SEC("fexit/bpf_testmod_test_struct_arg_7") +int BPF_PROG2(test_struct_arg_13, __u64, a, void *, b, short, c, int, d, + void *, e, struct bpf_testmod_struct_arg_4, f, int, ret) +{ + t7_ret = ret; + return 0; +} + +SEC("fentry/bpf_testmod_test_struct_arg_8") +int BPF_PROG2(test_struct_arg_14, __u64, a, void *, b, short, c, int, d, + void *, e, struct bpf_testmod_struct_arg_4, f, int, g) +{ + t8_a = a; + t8_b = (long)b; + t8_c = c; + t8_d = d; + t8_e = (long)e; + t8_f_a = f.a; + t8_f_b = f.b; + t8_g = g; + return 0; +} + +SEC("fexit/bpf_testmod_test_struct_arg_8") +int BPF_PROG2(test_struct_arg_15, __u64, a, void *, b, short, c, int, d, + void *, e, struct bpf_testmod_struct_arg_4, f, int, g, + int, ret) +{ + t8_ret = ret; + return 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/uprobe_multi.c b/tools/testing/selftests/bpf/progs/uprobe_multi.c new file mode 100644 index 000000000000..419d9aa28fce --- /dev/null +++ b/tools/testing/selftests/bpf/progs/uprobe_multi.c @@ -0,0 +1,101 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <stdbool.h> + +char _license[] SEC("license") = "GPL"; + +__u64 uprobe_multi_func_1_addr = 0; +__u64 uprobe_multi_func_2_addr = 0; +__u64 uprobe_multi_func_3_addr = 0; + +__u64 uprobe_multi_func_1_result = 0; +__u64 uprobe_multi_func_2_result = 0; +__u64 uprobe_multi_func_3_result = 0; + +__u64 uretprobe_multi_func_1_result = 0; +__u64 uretprobe_multi_func_2_result = 0; +__u64 uretprobe_multi_func_3_result = 0; + +__u64 uprobe_multi_sleep_result = 0; + +int pid = 0; +int child_pid = 0; + +bool test_cookie = false; +void *user_ptr = 0; + +static __always_inline bool verify_sleepable_user_copy(void) +{ + char data[9]; + + bpf_copy_from_user(data, sizeof(data), user_ptr); + return bpf_strncmp(data, sizeof(data), "test_data") == 0; +} + +static void uprobe_multi_check(void *ctx, bool is_return, bool is_sleep) +{ + child_pid = bpf_get_current_pid_tgid() >> 32; + + if (pid && child_pid != pid) + return; + + __u64 cookie = test_cookie ? bpf_get_attach_cookie(ctx) : 0; + __u64 addr = bpf_get_func_ip(ctx); + +#define SET(__var, __addr, __cookie) ({ \ + if (addr == __addr && \ + (!test_cookie || (cookie == __cookie))) \ + __var += 1; \ +}) + + if (is_return) { + SET(uretprobe_multi_func_1_result, uprobe_multi_func_1_addr, 2); + SET(uretprobe_multi_func_2_result, uprobe_multi_func_2_addr, 3); + SET(uretprobe_multi_func_3_result, uprobe_multi_func_3_addr, 1); + } else { + SET(uprobe_multi_func_1_result, uprobe_multi_func_1_addr, 3); + SET(uprobe_multi_func_2_result, uprobe_multi_func_2_addr, 1); + SET(uprobe_multi_func_3_result, uprobe_multi_func_3_addr, 2); + } + +#undef SET + + if (is_sleep && verify_sleepable_user_copy()) + uprobe_multi_sleep_result += 1; +} + +SEC("uprobe.multi//proc/self/exe:uprobe_multi_func_*") +int uprobe(struct pt_regs *ctx) +{ + uprobe_multi_check(ctx, false, false); + return 0; +} + +SEC("uretprobe.multi//proc/self/exe:uprobe_multi_func_*") +int uretprobe(struct pt_regs *ctx) +{ + uprobe_multi_check(ctx, true, false); + return 0; +} + +SEC("uprobe.multi.s//proc/self/exe:uprobe_multi_func_*") +int uprobe_sleep(struct pt_regs *ctx) +{ + uprobe_multi_check(ctx, false, true); + return 0; +} + +SEC("uretprobe.multi.s//proc/self/exe:uprobe_multi_func_*") +int uretprobe_sleep(struct pt_regs *ctx) +{ + uprobe_multi_check(ctx, true, true); + return 0; +} + +SEC("uprobe.multi//proc/self/exe:uprobe_multi_func_*") +int uprobe_extra(struct pt_regs *ctx) +{ + return 0; +} diff --git a/tools/perf/examples/bpf/empty.c b/tools/testing/selftests/bpf/progs/uprobe_multi_bench.c index 3e296c0c53d7..5367f6105e30 100644 --- a/tools/perf/examples/bpf/empty.c +++ b/tools/testing/selftests/bpf/progs/uprobe_multi_bench.c @@ -1,12 +1,15 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/bpf.h> #include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> -struct syscall_enter_args; +char _license[] SEC("license") = "GPL"; + +int count; -SEC("raw_syscalls:sys_enter") -int sys_enter(struct syscall_enter_args *args) +SEC("uprobe.multi/./uprobe_multi:uprobe_multi_func_*") +int uprobe_bench(struct pt_regs *ctx) { + count++; return 0; } -char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/uprobe_multi_usdt.c b/tools/testing/selftests/bpf/progs/uprobe_multi_usdt.c new file mode 100644 index 000000000000..9e1c33d0bd2f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/uprobe_multi_usdt.c @@ -0,0 +1,16 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/usdt.bpf.h> + +char _license[] SEC("license") = "GPL"; + +int count; + +SEC("usdt") +int usdt0(struct pt_regs *ctx) +{ + count++; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/verifier_bswap.c b/tools/testing/selftests/bpf/progs/verifier_bswap.c new file mode 100644 index 000000000000..8893094725f0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_bswap.c @@ -0,0 +1,60 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \ + (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64)) && __clang_major__ >= 18 + +SEC("socket") +__description("BSWAP, 16") +__success __success_unpriv __retval(0x23ff) +__naked void bswap_16(void) +{ + asm volatile (" \ + r0 = 0xff23; \ + r0 = bswap16 r0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("BSWAP, 32") +__success __success_unpriv __retval(0x23ff0000) +__naked void bswap_32(void) +{ + asm volatile (" \ + r0 = 0xff23; \ + r0 = bswap32 r0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("BSWAP, 64") +__success __success_unpriv __retval(0x34ff12ff) +__naked void bswap_64(void) +{ + asm volatile (" \ + r0 = %[u64_val] ll; \ + r0 = bswap64 r0; \ + exit; \ +" : + : [u64_val]"i"(0xff12ff34ff56ff78ull) + : __clobber_all); +} + +#else + +SEC("socket") +__description("cpuv4 is not supported by compiler or jit, use a dummy test") +__success +int dummy_test(void) +{ + return 0; +} + +#endif + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_gotol.c b/tools/testing/selftests/bpf/progs/verifier_gotol.c new file mode 100644 index 000000000000..2dae5322a18e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_gotol.c @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \ + (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64)) && __clang_major__ >= 18 + +SEC("socket") +__description("gotol, small_imm") +__success __success_unpriv __retval(1) +__naked void gotol_small_imm(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + if r0 == 0 goto l0_%=; \ + gotol l1_%=; \ +l2_%=: \ + gotol l3_%=; \ +l1_%=: \ + r0 = 1; \ + gotol l2_%=; \ +l0_%=: \ + r0 = 2; \ +l3_%=: \ + exit; \ +" : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +#else + +SEC("socket") +__description("cpuv4 is not supported by compiler or jit, use a dummy test") +__success +int dummy_test(void) +{ + return 0; +} + +#endif + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_ldsx.c b/tools/testing/selftests/bpf/progs/verifier_ldsx.c new file mode 100644 index 000000000000..0c638f45aaf1 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_ldsx.c @@ -0,0 +1,132 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \ + (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64)) && __clang_major__ >= 18 + +SEC("socket") +__description("LDSX, S8") +__success __success_unpriv __retval(-2) +__naked void ldsx_s8(void) +{ + asm volatile (" \ + r1 = 0x3fe; \ + *(u64 *)(r10 - 8) = r1; \ + r0 = *(s8 *)(r10 - 8); \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("LDSX, S16") +__success __success_unpriv __retval(-2) +__naked void ldsx_s16(void) +{ + asm volatile (" \ + r1 = 0x3fffe; \ + *(u64 *)(r10 - 8) = r1; \ + r0 = *(s16 *)(r10 - 8); \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("LDSX, S32") +__success __success_unpriv __retval(-1) +__naked void ldsx_s32(void) +{ + asm volatile (" \ + r1 = 0xfffffffe; \ + *(u64 *)(r10 - 8) = r1; \ + r0 = *(s32 *)(r10 - 8); \ + r0 >>= 1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("LDSX, S8 range checking, privileged") +__log_level(2) __success __retval(1) +__msg("R1_w=scalar(smin=-128,smax=127)") +__naked void ldsx_s8_range_priv(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + *(u64 *)(r10 - 8) = r0; \ + r1 = *(s8 *)(r10 - 8); \ + /* r1 with s8 range */ \ + if r1 s> 0x7f goto l0_%=; \ + if r1 s< -0x80 goto l0_%=; \ + r0 = 1; \ +l1_%=: \ + exit; \ +l0_%=: \ + r0 = 2; \ + goto l1_%=; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("LDSX, S16 range checking") +__success __success_unpriv __retval(1) +__naked void ldsx_s16_range(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + *(u64 *)(r10 - 8) = r0; \ + r1 = *(s16 *)(r10 - 8); \ + /* r1 with s16 range */ \ + if r1 s> 0x7fff goto l0_%=; \ + if r1 s< -0x8000 goto l0_%=; \ + r0 = 1; \ +l1_%=: \ + exit; \ +l0_%=: \ + r0 = 2; \ + goto l1_%=; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("LDSX, S32 range checking") +__success __success_unpriv __retval(1) +__naked void ldsx_s32_range(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + *(u64 *)(r10 - 8) = r0; \ + r1 = *(s32 *)(r10 - 8); \ + /* r1 with s16 range */ \ + if r1 s> 0x7fffFFFF goto l0_%=; \ + if r1 s< -0x80000000 goto l0_%=; \ + r0 = 1; \ +l1_%=: \ + exit; \ +l0_%=: \ + r0 = 2; \ + goto l1_%=; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +#else + +SEC("socket") +__description("cpuv4 is not supported by compiler or jit, use a dummy test") +__success +int dummy_test(void) +{ + return 0; +} + +#endif + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_movsx.c b/tools/testing/selftests/bpf/progs/verifier_movsx.c new file mode 100644 index 000000000000..3c8ac2c57b1b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_movsx.c @@ -0,0 +1,236 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \ + (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64)) && __clang_major__ >= 18 + +SEC("socket") +__description("MOV32SX, S8") +__success __success_unpriv __retval(0x23) +__naked void mov32sx_s8(void) +{ + asm volatile (" \ + w0 = 0xff23; \ + w0 = (s8)w0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("MOV32SX, S16") +__success __success_unpriv __retval(0xFFFFff23) +__naked void mov32sx_s16(void) +{ + asm volatile (" \ + w0 = 0xff23; \ + w0 = (s16)w0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("MOV64SX, S8") +__success __success_unpriv __retval(-2) +__naked void mov64sx_s8(void) +{ + asm volatile (" \ + r0 = 0x1fe; \ + r0 = (s8)r0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("MOV64SX, S16") +__success __success_unpriv __retval(0xf23) +__naked void mov64sx_s16(void) +{ + asm volatile (" \ + r0 = 0xf0f23; \ + r0 = (s16)r0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("MOV64SX, S32") +__success __success_unpriv __retval(-1) +__naked void mov64sx_s32(void) +{ + asm volatile (" \ + r0 = 0xfffffffe; \ + r0 = (s32)r0; \ + r0 >>= 1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("MOV32SX, S8, range_check") +__success __success_unpriv __retval(1) +__naked void mov32sx_s8_range(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + w1 = (s8)w0; \ + /* w1 with s8 range */ \ + if w1 s> 0x7f goto l0_%=; \ + if w1 s< -0x80 goto l0_%=; \ + r0 = 1; \ +l1_%=: \ + exit; \ +l0_%=: \ + r0 = 2; \ + goto l1_%=; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("MOV32SX, S16, range_check") +__success __success_unpriv __retval(1) +__naked void mov32sx_s16_range(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + w1 = (s16)w0; \ + /* w1 with s16 range */ \ + if w1 s> 0x7fff goto l0_%=; \ + if w1 s< -0x80ff goto l0_%=; \ + r0 = 1; \ +l1_%=: \ + exit; \ +l0_%=: \ + r0 = 2; \ + goto l1_%=; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("MOV32SX, S16, range_check 2") +__success __success_unpriv __retval(1) +__naked void mov32sx_s16_range_2(void) +{ + asm volatile (" \ + r1 = 65535; \ + w2 = (s16)w1; \ + r2 >>= 1; \ + if r2 != 0x7fffFFFF goto l0_%=; \ + r0 = 1; \ +l1_%=: \ + exit; \ +l0_%=: \ + r0 = 0; \ + goto l1_%=; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("MOV64SX, S8, range_check") +__success __success_unpriv __retval(1) +__naked void mov64sx_s8_range(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r1 = (s8)r0; \ + /* r1 with s8 range */ \ + if r1 s> 0x7f goto l0_%=; \ + if r1 s< -0x80 goto l0_%=; \ + r0 = 1; \ +l1_%=: \ + exit; \ +l0_%=: \ + r0 = 2; \ + goto l1_%=; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("MOV64SX, S16, range_check") +__success __success_unpriv __retval(1) +__naked void mov64sx_s16_range(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r1 = (s16)r0; \ + /* r1 with s16 range */ \ + if r1 s> 0x7fff goto l0_%=; \ + if r1 s< -0x8000 goto l0_%=; \ + r0 = 1; \ +l1_%=: \ + exit; \ +l0_%=: \ + r0 = 2; \ + goto l1_%=; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("MOV64SX, S32, range_check") +__success __success_unpriv __retval(1) +__naked void mov64sx_s32_range(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r1 = (s32)r0; \ + /* r1 with s32 range */ \ + if r1 s> 0x7fffffff goto l0_%=; \ + if r1 s< -0x80000000 goto l0_%=; \ + r0 = 1; \ +l1_%=: \ + exit; \ +l0_%=: \ + r0 = 2; \ + goto l1_%=; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("MOV64SX, S16, R10 Sign Extension") +__failure __msg("R1 type=scalar expected=fp, pkt, pkt_meta, map_key, map_value, mem, ringbuf_mem, buf, trusted_ptr_") +__failure_unpriv __msg_unpriv("R10 sign-extension part of pointer") +__naked void mov64sx_s16_r10(void) +{ + asm volatile (" \ + r1 = 553656332; \ + *(u32 *)(r10 - 8) = r1; \ + r1 = (s16)r10; \ + r1 += -8; \ + r2 = 3; \ + if r2 <= r1 goto l0_%=; \ +l0_%=: \ + call %[bpf_trace_printk]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_trace_printk) + : __clobber_all); +} + +#else + +SEC("socket") +__description("cpuv4 is not supported by compiler or jit, use a dummy test") +__success +int dummy_test(void) +{ + return 0; +} + +#endif + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_sdiv.c b/tools/testing/selftests/bpf/progs/verifier_sdiv.c new file mode 100644 index 000000000000..0990f8825675 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_sdiv.c @@ -0,0 +1,782 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \ + (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64)) && __clang_major__ >= 18 + +SEC("socket") +__description("SDIV32, non-zero imm divisor, check 1") +__success __success_unpriv __retval(-20) +__naked void sdiv32_non_zero_imm_1(void) +{ + asm volatile (" \ + w0 = -41; \ + w0 s/= 2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV32, non-zero imm divisor, check 2") +__success __success_unpriv __retval(-20) +__naked void sdiv32_non_zero_imm_2(void) +{ + asm volatile (" \ + w0 = 41; \ + w0 s/= -2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV32, non-zero imm divisor, check 3") +__success __success_unpriv __retval(20) +__naked void sdiv32_non_zero_imm_3(void) +{ + asm volatile (" \ + w0 = -41; \ + w0 s/= -2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV32, non-zero imm divisor, check 4") +__success __success_unpriv __retval(-21) +__naked void sdiv32_non_zero_imm_4(void) +{ + asm volatile (" \ + w0 = -42; \ + w0 s/= 2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV32, non-zero imm divisor, check 5") +__success __success_unpriv __retval(-21) +__naked void sdiv32_non_zero_imm_5(void) +{ + asm volatile (" \ + w0 = 42; \ + w0 s/= -2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV32, non-zero imm divisor, check 6") +__success __success_unpriv __retval(21) +__naked void sdiv32_non_zero_imm_6(void) +{ + asm volatile (" \ + w0 = -42; \ + w0 s/= -2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV32, non-zero imm divisor, check 7") +__success __success_unpriv __retval(21) +__naked void sdiv32_non_zero_imm_7(void) +{ + asm volatile (" \ + w0 = 42; \ + w0 s/= 2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV32, non-zero imm divisor, check 8") +__success __success_unpriv __retval(20) +__naked void sdiv32_non_zero_imm_8(void) +{ + asm volatile (" \ + w0 = 41; \ + w0 s/= 2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV32, non-zero reg divisor, check 1") +__success __success_unpriv __retval(-20) +__naked void sdiv32_non_zero_reg_1(void) +{ + asm volatile (" \ + w0 = -41; \ + w1 = 2; \ + w0 s/= w1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV32, non-zero reg divisor, check 2") +__success __success_unpriv __retval(-20) +__naked void sdiv32_non_zero_reg_2(void) +{ + asm volatile (" \ + w0 = 41; \ + w1 = -2; \ + w0 s/= w1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV32, non-zero reg divisor, check 3") +__success __success_unpriv __retval(20) +__naked void sdiv32_non_zero_reg_3(void) +{ + asm volatile (" \ + w0 = -41; \ + w1 = -2; \ + w0 s/= w1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV32, non-zero reg divisor, check 4") +__success __success_unpriv __retval(-21) +__naked void sdiv32_non_zero_reg_4(void) +{ + asm volatile (" \ + w0 = -42; \ + w1 = 2; \ + w0 s/= w1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV32, non-zero reg divisor, check 5") +__success __success_unpriv __retval(-21) +__naked void sdiv32_non_zero_reg_5(void) +{ + asm volatile (" \ + w0 = 42; \ + w1 = -2; \ + w0 s/= w1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV32, non-zero reg divisor, check 6") +__success __success_unpriv __retval(21) +__naked void sdiv32_non_zero_reg_6(void) +{ + asm volatile (" \ + w0 = -42; \ + w1 = -2; \ + w0 s/= w1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV32, non-zero reg divisor, check 7") +__success __success_unpriv __retval(21) +__naked void sdiv32_non_zero_reg_7(void) +{ + asm volatile (" \ + w0 = 42; \ + w1 = 2; \ + w0 s/= w1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV32, non-zero reg divisor, check 8") +__success __success_unpriv __retval(20) +__naked void sdiv32_non_zero_reg_8(void) +{ + asm volatile (" \ + w0 = 41; \ + w1 = 2; \ + w0 s/= w1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV64, non-zero imm divisor, check 1") +__success __success_unpriv __retval(-20) +__naked void sdiv64_non_zero_imm_1(void) +{ + asm volatile (" \ + r0 = -41; \ + r0 s/= 2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV64, non-zero imm divisor, check 2") +__success __success_unpriv __retval(-20) +__naked void sdiv64_non_zero_imm_2(void) +{ + asm volatile (" \ + r0 = 41; \ + r0 s/= -2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV64, non-zero imm divisor, check 3") +__success __success_unpriv __retval(20) +__naked void sdiv64_non_zero_imm_3(void) +{ + asm volatile (" \ + r0 = -41; \ + r0 s/= -2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV64, non-zero imm divisor, check 4") +__success __success_unpriv __retval(-21) +__naked void sdiv64_non_zero_imm_4(void) +{ + asm volatile (" \ + r0 = -42; \ + r0 s/= 2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV64, non-zero imm divisor, check 5") +__success __success_unpriv __retval(-21) +__naked void sdiv64_non_zero_imm_5(void) +{ + asm volatile (" \ + r0 = 42; \ + r0 s/= -2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV64, non-zero imm divisor, check 6") +__success __success_unpriv __retval(21) +__naked void sdiv64_non_zero_imm_6(void) +{ + asm volatile (" \ + r0 = -42; \ + r0 s/= -2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV64, non-zero reg divisor, check 1") +__success __success_unpriv __retval(-20) +__naked void sdiv64_non_zero_reg_1(void) +{ + asm volatile (" \ + r0 = -41; \ + r1 = 2; \ + r0 s/= r1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV64, non-zero reg divisor, check 2") +__success __success_unpriv __retval(-20) +__naked void sdiv64_non_zero_reg_2(void) +{ + asm volatile (" \ + r0 = 41; \ + r1 = -2; \ + r0 s/= r1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV64, non-zero reg divisor, check 3") +__success __success_unpriv __retval(20) +__naked void sdiv64_non_zero_reg_3(void) +{ + asm volatile (" \ + r0 = -41; \ + r1 = -2; \ + r0 s/= r1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV64, non-zero reg divisor, check 4") +__success __success_unpriv __retval(-21) +__naked void sdiv64_non_zero_reg_4(void) +{ + asm volatile (" \ + r0 = -42; \ + r1 = 2; \ + r0 s/= r1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV64, non-zero reg divisor, check 5") +__success __success_unpriv __retval(-21) +__naked void sdiv64_non_zero_reg_5(void) +{ + asm volatile (" \ + r0 = 42; \ + r1 = -2; \ + r0 s/= r1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV64, non-zero reg divisor, check 6") +__success __success_unpriv __retval(21) +__naked void sdiv64_non_zero_reg_6(void) +{ + asm volatile (" \ + r0 = -42; \ + r1 = -2; \ + r0 s/= r1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD32, non-zero imm divisor, check 1") +__success __success_unpriv __retval(-1) +__naked void smod32_non_zero_imm_1(void) +{ + asm volatile (" \ + w0 = -41; \ + w0 s%%= 2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD32, non-zero imm divisor, check 2") +__success __success_unpriv __retval(1) +__naked void smod32_non_zero_imm_2(void) +{ + asm volatile (" \ + w0 = 41; \ + w0 s%%= -2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD32, non-zero imm divisor, check 3") +__success __success_unpriv __retval(-1) +__naked void smod32_non_zero_imm_3(void) +{ + asm volatile (" \ + w0 = -41; \ + w0 s%%= -2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD32, non-zero imm divisor, check 4") +__success __success_unpriv __retval(0) +__naked void smod32_non_zero_imm_4(void) +{ + asm volatile (" \ + w0 = -42; \ + w0 s%%= 2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD32, non-zero imm divisor, check 5") +__success __success_unpriv __retval(0) +__naked void smod32_non_zero_imm_5(void) +{ + asm volatile (" \ + w0 = 42; \ + w0 s%%= -2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD32, non-zero imm divisor, check 6") +__success __success_unpriv __retval(0) +__naked void smod32_non_zero_imm_6(void) +{ + asm volatile (" \ + w0 = -42; \ + w0 s%%= -2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD32, non-zero reg divisor, check 1") +__success __success_unpriv __retval(-1) +__naked void smod32_non_zero_reg_1(void) +{ + asm volatile (" \ + w0 = -41; \ + w1 = 2; \ + w0 s%%= w1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD32, non-zero reg divisor, check 2") +__success __success_unpriv __retval(1) +__naked void smod32_non_zero_reg_2(void) +{ + asm volatile (" \ + w0 = 41; \ + w1 = -2; \ + w0 s%%= w1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD32, non-zero reg divisor, check 3") +__success __success_unpriv __retval(-1) +__naked void smod32_non_zero_reg_3(void) +{ + asm volatile (" \ + w0 = -41; \ + w1 = -2; \ + w0 s%%= w1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD32, non-zero reg divisor, check 4") +__success __success_unpriv __retval(0) +__naked void smod32_non_zero_reg_4(void) +{ + asm volatile (" \ + w0 = -42; \ + w1 = 2; \ + w0 s%%= w1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD32, non-zero reg divisor, check 5") +__success __success_unpriv __retval(0) +__naked void smod32_non_zero_reg_5(void) +{ + asm volatile (" \ + w0 = 42; \ + w1 = -2; \ + w0 s%%= w1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD32, non-zero reg divisor, check 6") +__success __success_unpriv __retval(0) +__naked void smod32_non_zero_reg_6(void) +{ + asm volatile (" \ + w0 = -42; \ + w1 = -2; \ + w0 s%%= w1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD64, non-zero imm divisor, check 1") +__success __success_unpriv __retval(-1) +__naked void smod64_non_zero_imm_1(void) +{ + asm volatile (" \ + r0 = -41; \ + r0 s%%= 2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD64, non-zero imm divisor, check 2") +__success __success_unpriv __retval(1) +__naked void smod64_non_zero_imm_2(void) +{ + asm volatile (" \ + r0 = 41; \ + r0 s%%= -2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD64, non-zero imm divisor, check 3") +__success __success_unpriv __retval(-1) +__naked void smod64_non_zero_imm_3(void) +{ + asm volatile (" \ + r0 = -41; \ + r0 s%%= -2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD64, non-zero imm divisor, check 4") +__success __success_unpriv __retval(0) +__naked void smod64_non_zero_imm_4(void) +{ + asm volatile (" \ + r0 = -42; \ + r0 s%%= 2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD64, non-zero imm divisor, check 5") +__success __success_unpriv __retval(-0) +__naked void smod64_non_zero_imm_5(void) +{ + asm volatile (" \ + r0 = 42; \ + r0 s%%= -2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD64, non-zero imm divisor, check 6") +__success __success_unpriv __retval(0) +__naked void smod64_non_zero_imm_6(void) +{ + asm volatile (" \ + r0 = -42; \ + r0 s%%= -2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD64, non-zero imm divisor, check 7") +__success __success_unpriv __retval(0) +__naked void smod64_non_zero_imm_7(void) +{ + asm volatile (" \ + r0 = 42; \ + r0 s%%= 2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD64, non-zero imm divisor, check 8") +__success __success_unpriv __retval(1) +__naked void smod64_non_zero_imm_8(void) +{ + asm volatile (" \ + r0 = 41; \ + r0 s%%= 2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD64, non-zero reg divisor, check 1") +__success __success_unpriv __retval(-1) +__naked void smod64_non_zero_reg_1(void) +{ + asm volatile (" \ + r0 = -41; \ + r1 = 2; \ + r0 s%%= r1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD64, non-zero reg divisor, check 2") +__success __success_unpriv __retval(1) +__naked void smod64_non_zero_reg_2(void) +{ + asm volatile (" \ + r0 = 41; \ + r1 = -2; \ + r0 s%%= r1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD64, non-zero reg divisor, check 3") +__success __success_unpriv __retval(-1) +__naked void smod64_non_zero_reg_3(void) +{ + asm volatile (" \ + r0 = -41; \ + r1 = -2; \ + r0 s%%= r1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD64, non-zero reg divisor, check 4") +__success __success_unpriv __retval(0) +__naked void smod64_non_zero_reg_4(void) +{ + asm volatile (" \ + r0 = -42; \ + r1 = 2; \ + r0 s%%= r1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD64, non-zero reg divisor, check 5") +__success __success_unpriv __retval(0) +__naked void smod64_non_zero_reg_5(void) +{ + asm volatile (" \ + r0 = 42; \ + r1 = -2; \ + r0 s%%= r1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD64, non-zero reg divisor, check 6") +__success __success_unpriv __retval(0) +__naked void smod64_non_zero_reg_6(void) +{ + asm volatile (" \ + r0 = -42; \ + r1 = -2; \ + r0 s%%= r1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD64, non-zero reg divisor, check 7") +__success __success_unpriv __retval(0) +__naked void smod64_non_zero_reg_7(void) +{ + asm volatile (" \ + r0 = 42; \ + r1 = 2; \ + r0 s%%= r1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD64, non-zero reg divisor, check 8") +__success __success_unpriv __retval(1) +__naked void smod64_non_zero_reg_8(void) +{ + asm volatile (" \ + r0 = 41; \ + r1 = 2; \ + r0 s%%= r1; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV32, zero divisor") +__success __success_unpriv __retval(0) +__naked void sdiv32_zero_divisor(void) +{ + asm volatile (" \ + w0 = 42; \ + w1 = 0; \ + w2 = -1; \ + w2 s/= w1; \ + w0 = w2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SDIV64, zero divisor") +__success __success_unpriv __retval(0) +__naked void sdiv64_zero_divisor(void) +{ + asm volatile (" \ + r0 = 42; \ + r1 = 0; \ + r2 = -1; \ + r2 s/= r1; \ + r0 = r2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD32, zero divisor") +__success __success_unpriv __retval(-1) +__naked void smod32_zero_divisor(void) +{ + asm volatile (" \ + w0 = 42; \ + w1 = 0; \ + w2 = -1; \ + w2 s%%= w1; \ + w0 = w2; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("SMOD64, zero divisor") +__success __success_unpriv __retval(-1) +__naked void smod64_zero_divisor(void) +{ + asm volatile (" \ + r0 = 42; \ + r1 = 0; \ + r2 = -1; \ + r2 s%%= r1; \ + r0 = r2; \ + exit; \ +" ::: __clobber_all); +} + +#else + +SEC("socket") +__description("cpuv4 is not supported by compiler or jit, use a dummy test") +__success +int dummy_test(void) +{ + return 0; +} + +#endif + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_typedef.c b/tools/testing/selftests/bpf/progs/verifier_typedef.c new file mode 100644 index 000000000000..08481cfaac4b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_typedef.c @@ -0,0 +1,23 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +SEC("fentry/bpf_fentry_test_sinfo") +__description("typedef: resolve") +__success __retval(0) +__naked void resolve_typedef(void) +{ + asm volatile (" \ + r1 = *(u64 *)(r1 +0); \ + r2 = *(u64 *)(r1 +%[frags_offs]); \ + r0 = 0; \ + exit; \ +" : + : __imm_const(frags_offs, + offsetof(struct skb_shared_info, frags)) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c b/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c index a630c95c7471..24369f242853 100644 --- a/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c +++ b/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c @@ -15,12 +15,12 @@ struct { static unsigned int idx; int count = 0; -SEC("xdp") int xsk_def_prog(struct xdp_md *xdp) +SEC("xdp.frags") int xsk_def_prog(struct xdp_md *xdp) { return bpf_redirect_map(&xsk, 0, XDP_DROP); } -SEC("xdp") int xsk_xdp_drop(struct xdp_md *xdp) +SEC("xdp.frags") int xsk_xdp_drop(struct xdp_md *xdp) { /* Drop every other packet */ if (idx++ % 2) @@ -29,7 +29,7 @@ SEC("xdp") int xsk_xdp_drop(struct xdp_md *xdp) return bpf_redirect_map(&xsk, 0, XDP_DROP); } -SEC("xdp") int xsk_xdp_populate_metadata(struct xdp_md *xdp) +SEC("xdp.frags") int xsk_xdp_populate_metadata(struct xdp_md *xdp) { void *data, *data_meta; struct xdp_info *meta; diff --git a/tools/testing/selftests/bpf/test_xsk.sh b/tools/testing/selftests/bpf/test_xsk.sh index c2ad50f26b63..2aa5a3445056 100755 --- a/tools/testing/selftests/bpf/test_xsk.sh +++ b/tools/testing/selftests/bpf/test_xsk.sh @@ -171,7 +171,10 @@ exec_xskxceiver if [ -z $ETH ]; then cleanup_exit ${VETH0} ${VETH1} +else + cleanup_iface ${ETH} ${MTU} fi + TEST_NAME="XSK_SELFTESTS_${VETH0}_BUSY_POLL" busy_poll=1 @@ -184,6 +187,8 @@ exec_xskxceiver if [ -z $ETH ]; then cleanup_exit ${VETH0} ${VETH1} +else + cleanup_iface ${ETH} ${MTU} fi failures=0 diff --git a/tools/testing/selftests/bpf/testing_helpers.h b/tools/testing/selftests/bpf/testing_helpers.h index 5312323881b6..5b7a55136741 100644 --- a/tools/testing/selftests/bpf/testing_helpers.h +++ b/tools/testing/selftests/bpf/testing_helpers.h @@ -7,6 +7,7 @@ #include <stdbool.h> #include <bpf/bpf.h> #include <bpf/libbpf.h> +#include <time.h> int parse_num_list(const char *s, bool **set, int *set_len); __u32 link_info_prog_id(const struct bpf_link *link, struct bpf_link_info *info); @@ -33,4 +34,13 @@ int load_bpf_testmod(bool verbose); int unload_bpf_testmod(bool verbose); int kern_sync_rcu(void); +static inline __u64 get_time_ns(void) +{ + struct timespec t; + + clock_gettime(CLOCK_MONOTONIC, &t); + + return (u64)t.tv_sec * 1000000000 + t.tv_nsec; +} + #endif /* __TESTING_HELPERS_H */ diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c index 9b070cdf44ac..f83d9f65c65b 100644 --- a/tools/testing/selftests/bpf/trace_helpers.c +++ b/tools/testing/selftests/bpf/trace_helpers.c @@ -18,7 +18,7 @@ #define TRACEFS_PIPE "/sys/kernel/tracing/trace_pipe" #define DEBUGFS_PIPE "/sys/kernel/debug/tracing/trace_pipe" -#define MAX_SYMS 300000 +#define MAX_SYMS 400000 static struct ksym syms[MAX_SYMS]; static int sym_cnt; @@ -46,6 +46,9 @@ int load_kallsyms_refresh(void) break; if (!addr) continue; + if (i >= MAX_SYMS) + return -EFBIG; + syms[i].addr = (long) addr; syms[i].name = strdup(func); i++; diff --git a/tools/testing/selftests/bpf/uprobe_multi.c b/tools/testing/selftests/bpf/uprobe_multi.c new file mode 100644 index 000000000000..a61ceab60b68 --- /dev/null +++ b/tools/testing/selftests/bpf/uprobe_multi.c @@ -0,0 +1,91 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <stdio.h> +#include <string.h> +#include <sdt.h> + +#define __PASTE(a, b) a##b +#define PASTE(a, b) __PASTE(a, b) + +#define NAME(name, idx) PASTE(name, idx) + +#define DEF(name, idx) int NAME(name, idx)(void) { return 0; } +#define CALL(name, idx) NAME(name, idx)(); + +#define F(body, name, idx) body(name, idx) + +#define F10(body, name, idx) \ + F(body, PASTE(name, idx), 0) F(body, PASTE(name, idx), 1) F(body, PASTE(name, idx), 2) \ + F(body, PASTE(name, idx), 3) F(body, PASTE(name, idx), 4) F(body, PASTE(name, idx), 5) \ + F(body, PASTE(name, idx), 6) F(body, PASTE(name, idx), 7) F(body, PASTE(name, idx), 8) \ + F(body, PASTE(name, idx), 9) + +#define F100(body, name, idx) \ + F10(body, PASTE(name, idx), 0) F10(body, PASTE(name, idx), 1) F10(body, PASTE(name, idx), 2) \ + F10(body, PASTE(name, idx), 3) F10(body, PASTE(name, idx), 4) F10(body, PASTE(name, idx), 5) \ + F10(body, PASTE(name, idx), 6) F10(body, PASTE(name, idx), 7) F10(body, PASTE(name, idx), 8) \ + F10(body, PASTE(name, idx), 9) + +#define F1000(body, name, idx) \ + F100(body, PASTE(name, idx), 0) F100(body, PASTE(name, idx), 1) F100(body, PASTE(name, idx), 2) \ + F100(body, PASTE(name, idx), 3) F100(body, PASTE(name, idx), 4) F100(body, PASTE(name, idx), 5) \ + F100(body, PASTE(name, idx), 6) F100(body, PASTE(name, idx), 7) F100(body, PASTE(name, idx), 8) \ + F100(body, PASTE(name, idx), 9) + +#define F10000(body, name, idx) \ + F1000(body, PASTE(name, idx), 0) F1000(body, PASTE(name, idx), 1) F1000(body, PASTE(name, idx), 2) \ + F1000(body, PASTE(name, idx), 3) F1000(body, PASTE(name, idx), 4) F1000(body, PASTE(name, idx), 5) \ + F1000(body, PASTE(name, idx), 6) F1000(body, PASTE(name, idx), 7) F1000(body, PASTE(name, idx), 8) \ + F1000(body, PASTE(name, idx), 9) + +F10000(DEF, uprobe_multi_func_, 0) +F10000(DEF, uprobe_multi_func_, 1) +F10000(DEF, uprobe_multi_func_, 2) +F10000(DEF, uprobe_multi_func_, 3) +F10000(DEF, uprobe_multi_func_, 4) + +static int bench(void) +{ + F10000(CALL, uprobe_multi_func_, 0) + F10000(CALL, uprobe_multi_func_, 1) + F10000(CALL, uprobe_multi_func_, 2) + F10000(CALL, uprobe_multi_func_, 3) + F10000(CALL, uprobe_multi_func_, 4) + return 0; +} + +#define PROBE STAP_PROBE(test, usdt); + +#define PROBE10 PROBE PROBE PROBE PROBE PROBE \ + PROBE PROBE PROBE PROBE PROBE +#define PROBE100 PROBE10 PROBE10 PROBE10 PROBE10 PROBE10 \ + PROBE10 PROBE10 PROBE10 PROBE10 PROBE10 +#define PROBE1000 PROBE100 PROBE100 PROBE100 PROBE100 PROBE100 \ + PROBE100 PROBE100 PROBE100 PROBE100 PROBE100 +#define PROBE10000 PROBE1000 PROBE1000 PROBE1000 PROBE1000 PROBE1000 \ + PROBE1000 PROBE1000 PROBE1000 PROBE1000 PROBE1000 + +static int usdt(void) +{ + PROBE10000 + PROBE10000 + PROBE10000 + PROBE10000 + PROBE10000 + return 0; +} + +int main(int argc, char **argv) +{ + if (argc != 2) + goto error; + + if (!strcmp("bench", argv[1])) + return bench(); + if (!strcmp("usdt", argv[1])) + return usdt(); + +error: + fprintf(stderr, "usage: %s <bench|usdt>\n", argv[0]); + return -1; +} diff --git a/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c b/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c index b39665f33524..319337bdcfc8 100644 --- a/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c +++ b/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c @@ -242,4 +242,5 @@ .result = REJECT, .errstr = "R0 invalid mem access", .errstr_unpriv = "R10 partial copy of pointer", + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, diff --git a/tools/testing/selftests/bpf/verifier/basic_instr.c b/tools/testing/selftests/bpf/verifier/basic_instr.c index 071dbc889e8c..bd928a72ad73 100644 --- a/tools/testing/selftests/bpf/verifier/basic_instr.c +++ b/tools/testing/selftests/bpf/verifier/basic_instr.c @@ -176,11 +176,11 @@ .retval = 1, }, { - "invalid 64-bit BPF_END", + "invalid 64-bit BPF_END with BPF_TO_BE", .insns = { BPF_MOV32_IMM(BPF_REG_0, 0), { - .code = BPF_ALU64 | BPF_END | BPF_TO_LE, + .code = BPF_ALU64 | BPF_END | BPF_TO_BE, .dst_reg = BPF_REG_0, .src_reg = 0, .off = 0, @@ -188,7 +188,7 @@ }, BPF_EXIT_INSN(), }, - .errstr = "unknown opcode d7", + .errstr = "unknown opcode df", .result = REJECT, }, { diff --git a/tools/testing/selftests/bpf/verifier/ctx_skb.c b/tools/testing/selftests/bpf/verifier/ctx_skb.c index 83cecfbd6739..0b394a7f7a2d 100644 --- a/tools/testing/selftests/bpf/verifier/ctx_skb.c +++ b/tools/testing/selftests/bpf/verifier/ctx_skb.c @@ -1169,6 +1169,7 @@ }, .result = ACCEPT, .prog_type = BPF_PROG_TYPE_SK_SKB, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "pkt_end < pkt taken check", @@ -1190,4 +1191,5 @@ }, .result = ACCEPT, .prog_type = BPF_PROG_TYPE_SK_SKB, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, diff --git a/tools/testing/selftests/bpf/verifier/jmp32.c b/tools/testing/selftests/bpf/verifier/jmp32.c index 1a27a6210554..43776f6f92f4 100644 --- a/tools/testing/selftests/bpf/verifier/jmp32.c +++ b/tools/testing/selftests/bpf/verifier/jmp32.c @@ -290,6 +290,7 @@ .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "jgt32: BPF_K", @@ -360,6 +361,7 @@ .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "jle32: BPF_K", @@ -430,6 +432,7 @@ .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "jlt32: BPF_K", @@ -500,6 +503,7 @@ .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "jsge32: BPF_K", @@ -570,6 +574,7 @@ .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "jsgt32: BPF_K", @@ -640,6 +645,7 @@ .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "jsle32: BPF_K", @@ -710,6 +716,7 @@ .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "jslt32: BPF_K", @@ -780,6 +787,7 @@ .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "jgt32: range bound deduction, reg op imm", diff --git a/tools/testing/selftests/bpf/verifier/map_kptr.c b/tools/testing/selftests/bpf/verifier/map_kptr.c index a0cfc06d75bc..d25c3e9605f1 100644 --- a/tools/testing/selftests/bpf/verifier/map_kptr.c +++ b/tools/testing/selftests/bpf/verifier/map_kptr.c @@ -68,6 +68,7 @@ .fixup_map_kptr = { 1 }, .result = REJECT, .errstr = "kptr access cannot have variable offset", + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "map_kptr: bpf_kptr_xchg non-const var_off", @@ -121,6 +122,7 @@ .fixup_map_kptr = { 1 }, .result = REJECT, .errstr = "kptr access misaligned expected=0 off=7", + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "map_kptr: reject var_off != 0", diff --git a/tools/testing/selftests/bpf/verifier/precise.c b/tools/testing/selftests/bpf/verifier/precise.c index 99272bb890da..0d84dd1f38b6 100644 --- a/tools/testing/selftests/bpf/verifier/precise.c +++ b/tools/testing/selftests/bpf/verifier/precise.c @@ -216,7 +216,7 @@ }, .fixup_map_ringbuf = { 1 }, .prog_type = BPF_PROG_TYPE_XDP, - .flags = BPF_F_TEST_STATE_FREQ, + .flags = BPF_F_TEST_STATE_FREQ | F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, .errstr = "invalid access to memory, mem_size=1 off=42 size=8", .result = REJECT, }, diff --git a/tools/testing/selftests/bpf/xsk.c b/tools/testing/selftests/bpf/xsk.c index 687d83e707f8..d9fb2b730a2c 100644 --- a/tools/testing/selftests/bpf/xsk.c +++ b/tools/testing/selftests/bpf/xsk.c @@ -18,17 +18,19 @@ #include <linux/ethtool.h> #include <linux/filter.h> #include <linux/if_ether.h> +#include <linux/if_link.h> #include <linux/if_packet.h> #include <linux/if_xdp.h> #include <linux/kernel.h> #include <linux/list.h> +#include <linux/netlink.h> +#include <linux/rtnetlink.h> #include <linux/sockios.h> #include <net/if.h> #include <sys/ioctl.h> #include <sys/mman.h> #include <sys/socket.h> #include <sys/types.h> -#include <linux/if_link.h> #include <bpf/bpf.h> #include <bpf/libbpf.h> @@ -81,6 +83,12 @@ struct xsk_socket { int fd; }; +struct nl_mtu_req { + struct nlmsghdr nh; + struct ifinfomsg msg; + char buf[512]; +}; + int xsk_umem__fd(const struct xsk_umem *umem) { return umem ? umem->fd : -EINVAL; @@ -286,6 +294,132 @@ bool xsk_is_in_mode(u32 ifindex, int mode) return false; } +/* Lifted from netlink.c in tools/lib/bpf */ +static int netlink_recvmsg(int sock, struct msghdr *mhdr, int flags) +{ + int len; + + do { + len = recvmsg(sock, mhdr, flags); + } while (len < 0 && (errno == EINTR || errno == EAGAIN)); + + if (len < 0) + return -errno; + return len; +} + +/* Lifted from netlink.c in tools/lib/bpf */ +static int alloc_iov(struct iovec *iov, int len) +{ + void *nbuf; + + nbuf = realloc(iov->iov_base, len); + if (!nbuf) + return -ENOMEM; + + iov->iov_base = nbuf; + iov->iov_len = len; + return 0; +} + +/* Original version lifted from netlink.c in tools/lib/bpf */ +static int netlink_recv(int sock) +{ + struct iovec iov = {}; + struct msghdr mhdr = { + .msg_iov = &iov, + .msg_iovlen = 1, + }; + bool multipart = true; + struct nlmsgerr *err; + struct nlmsghdr *nh; + int len, ret; + + ret = alloc_iov(&iov, 4096); + if (ret) + goto done; + + while (multipart) { + multipart = false; + len = netlink_recvmsg(sock, &mhdr, MSG_PEEK | MSG_TRUNC); + if (len < 0) { + ret = len; + goto done; + } + + if (len > iov.iov_len) { + ret = alloc_iov(&iov, len); + if (ret) + goto done; + } + + len = netlink_recvmsg(sock, &mhdr, 0); + if (len < 0) { + ret = len; + goto done; + } + + if (len == 0) + break; + + for (nh = (struct nlmsghdr *)iov.iov_base; NLMSG_OK(nh, len); + nh = NLMSG_NEXT(nh, len)) { + if (nh->nlmsg_flags & NLM_F_MULTI) + multipart = true; + switch (nh->nlmsg_type) { + case NLMSG_ERROR: + err = (struct nlmsgerr *)NLMSG_DATA(nh); + if (!err->error) + continue; + ret = err->error; + goto done; + case NLMSG_DONE: + ret = 0; + goto done; + default: + break; + } + } + } + ret = 0; +done: + free(iov.iov_base); + return ret; +} + +int xsk_set_mtu(int ifindex, int mtu) +{ + struct nl_mtu_req req; + struct rtattr *rta; + int fd, ret; + + fd = socket(AF_NETLINK, SOCK_DGRAM, NETLINK_ROUTE); + if (fd < 0) + return fd; + + memset(&req, 0, sizeof(req)); + req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)); + req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK; + req.nh.nlmsg_type = RTM_NEWLINK; + req.msg.ifi_family = AF_UNSPEC; + req.msg.ifi_index = ifindex; + rta = (struct rtattr *)(((char *)&req) + NLMSG_ALIGN(req.nh.nlmsg_len)); + rta->rta_type = IFLA_MTU; + rta->rta_len = RTA_LENGTH(sizeof(unsigned int)); + req.nh.nlmsg_len = NLMSG_ALIGN(req.nh.nlmsg_len) + RTA_LENGTH(sizeof(mtu)); + memcpy(RTA_DATA(rta), &mtu, sizeof(mtu)); + + ret = send(fd, &req, req.nh.nlmsg_len, 0); + if (ret < 0) { + close(fd); + return errno; + } + + ret = netlink_recv(fd); + close(fd); + return ret; +} + int xsk_attach_xdp_program(struct bpf_program *prog, int ifindex, u32 xdp_flags) { int prog_fd; diff --git a/tools/testing/selftests/bpf/xsk.h b/tools/testing/selftests/bpf/xsk.h index 8da8d557768b..d93200fdaa8d 100644 --- a/tools/testing/selftests/bpf/xsk.h +++ b/tools/testing/selftests/bpf/xsk.h @@ -239,6 +239,8 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr, int xsk_umem__delete(struct xsk_umem *umem); void xsk_socket__delete(struct xsk_socket *xsk); +int xsk_set_mtu(int ifindex, int mtu); + #ifdef __cplusplus } /* extern "C" */ #endif diff --git a/tools/testing/selftests/bpf/xsk_prereqs.sh b/tools/testing/selftests/bpf/xsk_prereqs.sh index ae697a10a056..29175682c44d 100755 --- a/tools/testing/selftests/bpf/xsk_prereqs.sh +++ b/tools/testing/selftests/bpf/xsk_prereqs.sh @@ -53,6 +53,13 @@ test_exit() exit 1 } +cleanup_iface() +{ + ip link set $1 mtu $2 + ip link set $1 xdp off + ip link set $1 xdpgeneric off +} + clear_configs() { [ $(ip link show $1 &>/dev/null; echo $?;) == 0 ] && diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c index 218d7f694e5c..2827f2d7cf30 100644 --- a/tools/testing/selftests/bpf/xskxceiver.c +++ b/tools/testing/selftests/bpf/xskxceiver.c @@ -49,8 +49,11 @@ * h. tests for invalid and corner case Tx descriptors so that the correct ones * are discarded and let through, respectively. * i. 2K frame size tests - * - * Total tests: 12 + * j. If multi-buffer is supported, send 9k packets divided into 3 frames + * k. If multi-buffer and huge pages are supported, send 9k packets in a single frame + * using unaligned mode + * l. If multi-buffer is supported, try various nasty combinations of descriptors to + * check if they pass the validation or not * * Flow: * ----- @@ -73,10 +76,10 @@ #include <fcntl.h> #include <errno.h> #include <getopt.h> -#include <asm/barrier.h> #include <linux/if_link.h> #include <linux/if_ether.h> #include <linux/mman.h> +#include <linux/netdev.h> #include <arpa/inet.h> #include <net/if.h> #include <locale.h> @@ -91,7 +94,6 @@ #include <sys/socket.h> #include <sys/time.h> #include <sys/types.h> -#include <time.h> #include <unistd.h> #include "xsk_xdp_progs.skel.h" @@ -253,6 +255,8 @@ static int __xsk_configure_socket(struct xsk_socket_info *xsk, struct xsk_umem_i cfg.bind_flags = ifobject->bind_flags; if (shared) cfg.bind_flags |= XDP_SHARED_UMEM; + if (ifobject->pkt_stream && ifobject->mtu > MAX_ETH_PKT_SIZE) + cfg.bind_flags |= XDP_USE_SG; txr = ifobject->tx_on ? &xsk->tx : NULL; rxr = ifobject->rx_on ? &xsk->rx : NULL; @@ -415,6 +419,7 @@ static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx, test->total_steps = 1; test->nb_sockets = 1; test->fail = false; + test->mtu = MAX_ETH_PKT_SIZE; test->xdp_prog_rx = ifobj_rx->xdp_progs->progs.xsk_def_prog; test->xskmap_rx = ifobj_rx->xdp_progs->maps.xsk; test->xdp_prog_tx = ifobj_tx->xdp_progs->progs.xsk_def_prog; @@ -468,6 +473,26 @@ static void test_spec_set_xdp_prog(struct test_spec *test, struct bpf_program *x test->xskmap_tx = xskmap_tx; } +static int test_spec_set_mtu(struct test_spec *test, int mtu) +{ + int err; + + if (test->ifobj_rx->mtu != mtu) { + err = xsk_set_mtu(test->ifobj_rx->ifindex, mtu); + if (err) + return err; + test->ifobj_rx->mtu = mtu; + } + if (test->ifobj_tx->mtu != mtu) { + err = xsk_set_mtu(test->ifobj_tx->ifindex, mtu); + if (err) + return err; + test->ifobj_tx->mtu = mtu; + } + + return 0; +} + static void pkt_stream_reset(struct pkt_stream *pkt_stream) { if (pkt_stream) @@ -533,23 +558,49 @@ static struct pkt_stream *__pkt_stream_alloc(u32 nb_pkts) return pkt_stream; } +static bool pkt_continues(u32 options) +{ + return options & XDP_PKT_CONTD; +} + static u32 ceil_u32(u32 a, u32 b) { return (a + b - 1) / b; } -static u32 pkt_nb_frags(u32 frame_size, struct pkt *pkt) +static u32 pkt_nb_frags(u32 frame_size, struct pkt_stream *pkt_stream, struct pkt *pkt) { - if (!pkt || !pkt->valid) + u32 nb_frags = 1, next_frag; + + if (!pkt) return 1; - return ceil_u32(pkt->len, frame_size); + + if (!pkt_stream->verbatim) { + if (!pkt->valid || !pkt->len) + return 1; + return ceil_u32(pkt->len, frame_size); + } + + /* Search for the end of the packet in verbatim mode */ + if (!pkt_continues(pkt->options)) + return nb_frags; + + next_frag = pkt_stream->current_pkt_nb; + pkt++; + while (next_frag++ < pkt_stream->nb_pkts) { + nb_frags++; + if (!pkt_continues(pkt->options) || !pkt->valid) + break; + pkt++; + } + return nb_frags; } static void pkt_set(struct xsk_umem_info *umem, struct pkt *pkt, int offset, u32 len) { pkt->offset = offset; pkt->len = len; - if (len > umem->frame_size - XDP_PACKET_HEADROOM - MIN_PKT_SIZE * 2 - umem->frame_headroom) + if (len > MAX_ETH_JUMBO_SIZE) pkt->valid = false; else pkt->valid = true; @@ -637,6 +688,11 @@ static u64 pkt_get_addr(struct pkt *pkt, struct xsk_umem_info *umem) return pkt->offset + umem_alloc_buffer(umem); } +static void pkt_stream_cancel(struct pkt_stream *pkt_stream) +{ + pkt_stream->current_pkt_nb--; +} + static void pkt_generate(struct ifobject *ifobject, u64 addr, u32 len, u32 pkt_nb, u32 bytes_written) { @@ -657,34 +713,59 @@ static void pkt_generate(struct ifobject *ifobject, u64 addr, u32 len, u32 pkt_n write_payload(data, pkt_nb, bytes_written, len); } -static void __pkt_stream_generate_custom(struct ifobject *ifobj, - struct pkt *pkts, u32 nb_pkts) +static struct pkt_stream *__pkt_stream_generate_custom(struct ifobject *ifobj, struct pkt *frames, + u32 nb_frames, bool verbatim) { + u32 i, len = 0, pkt_nb = 0, payload = 0; struct pkt_stream *pkt_stream; - u32 i; - pkt_stream = __pkt_stream_alloc(nb_pkts); + pkt_stream = __pkt_stream_alloc(nb_frames); if (!pkt_stream) exit_with_error(ENOMEM); - for (i = 0; i < nb_pkts; i++) { - struct pkt *pkt = &pkt_stream->pkts[i]; + for (i = 0; i < nb_frames; i++) { + struct pkt *pkt = &pkt_stream->pkts[pkt_nb]; + struct pkt *frame = &frames[i]; - pkt->offset = pkts[i].offset; - pkt->len = pkts[i].len; - pkt->pkt_nb = i; - pkt->valid = pkts[i].valid; - if (pkt->len > pkt_stream->max_pkt_len) + pkt->offset = frame->offset; + if (verbatim) { + *pkt = *frame; + pkt->pkt_nb = payload; + if (!frame->valid || !pkt_continues(frame->options)) + payload++; + } else { + if (frame->valid) + len += frame->len; + if (frame->valid && pkt_continues(frame->options)) + continue; + + pkt->pkt_nb = pkt_nb; + pkt->len = len; + pkt->valid = frame->valid; + pkt->options = 0; + + len = 0; + } + + if (pkt->valid && pkt->len > pkt_stream->max_pkt_len) pkt_stream->max_pkt_len = pkt->len; + pkt_nb++; } - ifobj->pkt_stream = pkt_stream; + pkt_stream->nb_pkts = pkt_nb; + pkt_stream->verbatim = verbatim; + return pkt_stream; } static void pkt_stream_generate_custom(struct test_spec *test, struct pkt *pkts, u32 nb_pkts) { - __pkt_stream_generate_custom(test->ifobj_tx, pkts, nb_pkts); - __pkt_stream_generate_custom(test->ifobj_rx, pkts, nb_pkts); + struct pkt_stream *pkt_stream; + + pkt_stream = __pkt_stream_generate_custom(test->ifobj_tx, pkts, nb_pkts, true); + test->ifobj_tx->pkt_stream = pkt_stream; + + pkt_stream = __pkt_stream_generate_custom(test->ifobj_rx, pkts, nb_pkts, false); + test->ifobj_rx->pkt_stream = pkt_stream; } static void pkt_print_data(u32 *data, u32 cnt) @@ -765,43 +846,76 @@ static bool is_metadata_correct(struct pkt *pkt, void *buffer, u64 addr) return true; } -static bool is_pkt_valid(struct pkt *pkt, void *buffer, u64 addr, u32 len) +static bool is_frag_valid(struct xsk_umem_info *umem, u64 addr, u32 len, u32 expected_pkt_nb, + u32 bytes_processed) { - void *data = xsk_umem__get_data(buffer, addr); - u32 seqnum, pkt_data; + u32 seqnum, pkt_nb, *pkt_data, words_to_end, expected_seqnum; + void *data = xsk_umem__get_data(umem->buffer, addr); - if (!pkt) { - ksft_print_msg("[%s] too many packets received\n", __func__); - goto error; + addr -= umem->base_addr; + + if (addr >= umem->num_frames * umem->frame_size || + addr + len > umem->num_frames * umem->frame_size) { + ksft_print_msg("Frag invalid addr: %llx len: %u\n", addr, len); + return false; + } + if (!umem->unaligned_mode && addr % umem->frame_size + len > umem->frame_size) { + ksft_print_msg("Frag crosses frame boundary addr: %llx len: %u\n", addr, len); + return false; } - if (len < MIN_PKT_SIZE || pkt->len < MIN_PKT_SIZE) { - /* Do not try to verify packets that are smaller than minimum size. */ - return true; + pkt_data = data; + if (!bytes_processed) { + pkt_data += PKT_HDR_SIZE / sizeof(*pkt_data); + len -= PKT_HDR_SIZE; + } else { + bytes_processed -= PKT_HDR_SIZE; } - if (pkt->len != len) { - ksft_print_msg("[%s] expected length [%d], got length [%d]\n", - __func__, pkt->len, len); + expected_seqnum = bytes_processed / sizeof(*pkt_data); + seqnum = ntohl(*pkt_data) & 0xffff; + pkt_nb = ntohl(*pkt_data) >> 16; + + if (expected_pkt_nb != pkt_nb) { + ksft_print_msg("[%s] expected pkt_nb [%u], got pkt_nb [%u]\n", + __func__, expected_pkt_nb, pkt_nb); + goto error; + } + if (expected_seqnum != seqnum) { + ksft_print_msg("[%s] expected seqnum at start [%u], got seqnum [%u]\n", + __func__, expected_seqnum, seqnum); goto error; } - pkt_data = ntohl(*((u32 *)(data + PKT_HDR_SIZE))); - seqnum = pkt_data >> 16; - - if (pkt->pkt_nb != seqnum) { - ksft_print_msg("[%s] expected seqnum [%d], got seqnum [%d]\n", - __func__, pkt->pkt_nb, seqnum); + words_to_end = len / sizeof(*pkt_data) - 1; + pkt_data += words_to_end; + seqnum = ntohl(*pkt_data) & 0xffff; + expected_seqnum += words_to_end; + if (expected_seqnum != seqnum) { + ksft_print_msg("[%s] expected seqnum at end [%u], got seqnum [%u]\n", + __func__, expected_seqnum, seqnum); goto error; } return true; error: - pkt_dump(data, len, true); + pkt_dump(data, len, !bytes_processed); return false; } +static bool is_pkt_valid(struct pkt *pkt, void *buffer, u64 addr, u32 len) +{ + if (pkt->len != len) { + ksft_print_msg("[%s] expected packet length [%d], got length [%d]\n", + __func__, pkt->len, len); + pkt_dump(xsk_umem__get_data(buffer, addr), len, true); + return false; + } + + return true; +} + static void kick_tx(struct xsk_socket_info *xsk) { int ret; @@ -854,8 +968,8 @@ static int receive_pkts(struct test_spec *test, struct pollfd *fds) { struct timeval tv_end, tv_now, tv_timeout = {THREAD_TMOUT, 0}; struct pkt_stream *pkt_stream = test->ifobj_rx->pkt_stream; - u32 idx_rx = 0, idx_fq = 0, rcvd, i, pkts_sent = 0; struct xsk_socket_info *xsk = test->ifobj_rx->xsk; + u32 idx_rx = 0, idx_fq = 0, rcvd, pkts_sent = 0; struct ifobject *ifobj = test->ifobj_rx; struct xsk_umem_info *umem = xsk->umem; struct pkt *pkt; @@ -868,6 +982,9 @@ static int receive_pkts(struct test_spec *test, struct pollfd *fds) pkt = pkt_stream_get_next_rx_pkt(pkt_stream, &pkts_sent); while (pkt) { + u32 frags_processed = 0, nb_frags = 0, pkt_len = 0; + u64 first_addr; + ret = gettimeofday(&tv_now, NULL); if (ret) exit_with_error(errno); @@ -888,7 +1005,6 @@ static int receive_pkts(struct test_spec *test, struct pollfd *fds) ksft_print_msg("ERROR: [%s] Poll timed out\n", __func__); return TEST_FAILURE; - } if (!(fds->revents & POLLIN)) @@ -913,27 +1029,59 @@ static int receive_pkts(struct test_spec *test, struct pollfd *fds) } } - for (i = 0; i < rcvd; i++) { + while (frags_processed < rcvd) { const struct xdp_desc *desc = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx++); u64 addr = desc->addr, orig; orig = xsk_umem__extract_addr(addr); addr = xsk_umem__add_offset_to_addr(addr); - if (!is_pkt_valid(pkt, umem->buffer, addr, desc->len) || + if (!pkt) { + ksft_print_msg("[%s] received too many packets addr: %lx len %u\n", + __func__, addr, desc->len); + return TEST_FAILURE; + } + + if (!is_frag_valid(umem, addr, desc->len, pkt->pkt_nb, pkt_len) || !is_offset_correct(umem, pkt, addr) || (ifobj->use_metadata && !is_metadata_correct(pkt, umem->buffer, addr))) return TEST_FAILURE; + if (!nb_frags++) + first_addr = addr; + frags_processed++; + pkt_len += desc->len; if (ifobj->use_fill_ring) *xsk_ring_prod__fill_addr(&umem->fq, idx_fq++) = orig; + + if (pkt_continues(desc->options)) + continue; + + /* The complete packet has been received */ + if (!is_pkt_valid(pkt, umem->buffer, first_addr, pkt_len) || + !is_offset_correct(umem, pkt, addr)) + return TEST_FAILURE; + pkt = pkt_stream_get_next_rx_pkt(pkt_stream, &pkts_sent); + nb_frags = 0; + pkt_len = 0; + } + + if (nb_frags) { + /* In the middle of a packet. Start over from beginning of packet. */ + idx_rx -= nb_frags; + xsk_ring_cons__cancel(&xsk->rx, nb_frags); + if (ifobj->use_fill_ring) { + idx_fq -= nb_frags; + xsk_ring_prod__cancel(&umem->fq, nb_frags); + } + frags_processed -= nb_frags; } if (ifobj->use_fill_ring) - xsk_ring_prod__submit(&umem->fq, rcvd); + xsk_ring_prod__submit(&umem->fq, frags_processed); if (ifobj->release_rx) - xsk_ring_cons__release(&xsk->rx, rcvd); + xsk_ring_cons__release(&xsk->rx, frags_processed); pthread_mutex_lock(&pacing_mutex); pkts_in_flight -= pkts_sent; @@ -946,13 +1094,14 @@ static int receive_pkts(struct test_spec *test, struct pollfd *fds) static int __send_pkts(struct ifobject *ifobject, struct pollfd *fds, bool timeout) { + u32 i, idx = 0, valid_pkts = 0, valid_frags = 0, buffer_len; + struct pkt_stream *pkt_stream = ifobject->pkt_stream; struct xsk_socket_info *xsk = ifobject->xsk; struct xsk_umem_info *umem = ifobject->umem; - u32 i, idx = 0, valid_pkts = 0, buffer_len; bool use_poll = ifobject->use_poll; int ret; - buffer_len = pkt_get_buffer_len(umem, ifobject->pkt_stream->max_pkt_len); + buffer_len = pkt_get_buffer_len(umem, pkt_stream->max_pkt_len); /* pkts_in_flight might be negative if many invalid packets are sent */ if (pkts_in_flight >= (int)((umem_size(umem) - BATCH_SIZE * buffer_len) / buffer_len)) { kick_tx(xsk); @@ -983,17 +1132,49 @@ static int __send_pkts(struct ifobject *ifobject, struct pollfd *fds, bool timeo } for (i = 0; i < BATCH_SIZE; i++) { - struct xdp_desc *tx_desc = xsk_ring_prod__tx_desc(&xsk->tx, idx + i); - struct pkt *pkt = pkt_stream_get_next_tx_pkt(ifobject->pkt_stream); + struct pkt *pkt = pkt_stream_get_next_tx_pkt(pkt_stream); + u32 nb_frags_left, nb_frags, bytes_written = 0; if (!pkt) break; - tx_desc->addr = pkt_get_addr(pkt, umem); - tx_desc->len = pkt->len; - if (pkt->valid) { + nb_frags = pkt_nb_frags(umem->frame_size, pkt_stream, pkt); + if (nb_frags > BATCH_SIZE - i) { + pkt_stream_cancel(pkt_stream); + xsk_ring_prod__cancel(&xsk->tx, BATCH_SIZE - i); + break; + } + nb_frags_left = nb_frags; + + while (nb_frags_left--) { + struct xdp_desc *tx_desc = xsk_ring_prod__tx_desc(&xsk->tx, idx + i); + + tx_desc->addr = pkt_get_addr(pkt, ifobject->umem); + if (pkt_stream->verbatim) { + tx_desc->len = pkt->len; + tx_desc->options = pkt->options; + } else if (nb_frags_left) { + tx_desc->len = umem->frame_size; + tx_desc->options = XDP_PKT_CONTD; + } else { + tx_desc->len = pkt->len - bytes_written; + tx_desc->options = 0; + } + if (pkt->valid) + pkt_generate(ifobject, tx_desc->addr, tx_desc->len, pkt->pkt_nb, + bytes_written); + bytes_written += tx_desc->len; + + if (nb_frags_left) { + i++; + if (pkt_stream->verbatim) + pkt = pkt_stream_get_next_tx_pkt(pkt_stream); + } + } + + if (pkt && pkt->valid) { valid_pkts++; - pkt_generate(ifobject, tx_desc->addr, tx_desc->len, pkt->pkt_nb, 0); + valid_frags += nb_frags; } } @@ -1002,7 +1183,7 @@ static int __send_pkts(struct ifobject *ifobject, struct pollfd *fds, bool timeo pthread_mutex_unlock(&pacing_mutex); xsk_ring_prod__submit(&xsk->tx, i); - xsk->outstanding_tx += valid_pkts; + xsk->outstanding_tx += valid_frags; if (use_poll) { ret = poll(fds, 1, POLL_TMOUT); @@ -1222,7 +1403,7 @@ static void xsk_populate_fill_ring(struct xsk_umem_info *umem, struct pkt_stream u64 addr; u32 i; - for (i = 0; i < pkt_nb_frags(rx_frame_size, pkt); i++) { + for (i = 0; i < pkt_nb_frags(rx_frame_size, pkt_stream, pkt); i++) { if (!pkt) { if (!fill_up) break; @@ -1415,6 +1596,25 @@ static int __testapp_validate_traffic(struct test_spec *test, struct ifobject *i struct ifobject *ifobj2) { pthread_t t0, t1; + int err; + + if (test->mtu > MAX_ETH_PKT_SIZE) { + if (test->mode == TEST_MODE_ZC && (!ifobj1->multi_buff_zc_supp || + (ifobj2 && !ifobj2->multi_buff_zc_supp))) { + ksft_test_result_skip("Multi buffer for zero-copy not supported.\n"); + return TEST_SKIP; + } + if (test->mode != TEST_MODE_ZC && (!ifobj1->multi_buff_supp || + (ifobj2 && !ifobj2->multi_buff_supp))) { + ksft_test_result_skip("Multi buffer not supported.\n"); + return TEST_SKIP; + } + } + err = test_spec_set_mtu(test, test->mtu); + if (err) { + ksft_print_msg("Error, could not set mtu.\n"); + exit_with_error(err); + } if (ifobj2) { if (pthread_barrier_init(&barr, NULL, 2)) @@ -1616,6 +1816,16 @@ static int testapp_unaligned(struct test_spec *test) return testapp_validate_traffic(test); } +static int testapp_unaligned_mb(struct test_spec *test) +{ + test_spec_set_name(test, "UNALIGNED_MODE_9K"); + test->mtu = MAX_ETH_JUMBO_SIZE; + test->ifobj_tx->umem->unaligned_mode = true; + test->ifobj_rx->umem->unaligned_mode = true; + pkt_stream_replace(test, DEFAULT_PKT_CNT, MAX_ETH_JUMBO_SIZE); + return testapp_validate_traffic(test); +} + static int testapp_single_pkt(struct test_spec *test) { struct pkt pkts[] = {{0, MIN_PKT_SIZE, 0, true}}; @@ -1624,6 +1834,55 @@ static int testapp_single_pkt(struct test_spec *test) return testapp_validate_traffic(test); } +static int testapp_multi_buffer(struct test_spec *test) +{ + test_spec_set_name(test, "RUN_TO_COMPLETION_9K_PACKETS"); + test->mtu = MAX_ETH_JUMBO_SIZE; + pkt_stream_replace(test, DEFAULT_PKT_CNT, MAX_ETH_JUMBO_SIZE); + + return testapp_validate_traffic(test); +} + +static int testapp_invalid_desc_mb(struct test_spec *test) +{ + struct xsk_umem_info *umem = test->ifobj_tx->umem; + u64 umem_size = umem->num_frames * umem->frame_size; + struct pkt pkts[] = { + /* Valid packet for synch to start with */ + {0, MIN_PKT_SIZE, 0, true, 0}, + /* Zero frame len is not legal */ + {0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, + {0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, + {0, 0, 0, false, 0}, + /* Invalid address in the second frame */ + {0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, + {umem_size, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, + /* Invalid len in the middle */ + {0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, + {0, XSK_UMEM__INVALID_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, + /* Invalid options in the middle */ + {0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, + {0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XSK_DESC__INVALID_OPTION}, + /* Transmit 2 frags, receive 3 */ + {0, XSK_UMEM__MAX_FRAME_SIZE, 0, true, XDP_PKT_CONTD}, + {0, XSK_UMEM__MAX_FRAME_SIZE, 0, true, 0}, + /* Middle frame crosses chunk boundary with small length */ + {0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, + {-MIN_PKT_SIZE / 2, MIN_PKT_SIZE, 0, false, 0}, + /* Valid packet for synch so that something is received */ + {0, MIN_PKT_SIZE, 0, true, 0}}; + + if (umem->unaligned_mode) { + /* Crossing a chunk boundary allowed */ + pkts[12].valid = true; + pkts[13].valid = true; + } + + test->mtu = MAX_ETH_JUMBO_SIZE; + pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts)); + return testapp_validate_traffic(test); +} + static int testapp_invalid_desc(struct test_spec *test) { struct xsk_umem_info *umem = test->ifobj_tx->umem; @@ -1690,7 +1949,6 @@ static int testapp_xdp_metadata_count(struct test_spec *test) int count = 0; int key = 0; - test_spec_set_name(test, "XDP_METADATA_COUNT"); test_spec_set_xdp_prog(test, skel_rx->progs.xsk_xdp_populate_metadata, skel_tx->progs.xsk_xdp_populate_metadata, skel_rx->maps.xsk, skel_tx->maps.xsk); @@ -1724,6 +1982,48 @@ static int testapp_poll_rxq_tmout(struct test_spec *test) return testapp_validate_traffic_single_thread(test, test->ifobj_rx); } +static int testapp_too_many_frags(struct test_spec *test) +{ + struct pkt pkts[2 * XSK_DESC__MAX_SKB_FRAGS + 2] = {}; + u32 max_frags, i; + + test_spec_set_name(test, "TOO_MANY_FRAGS"); + if (test->mode == TEST_MODE_ZC) + max_frags = test->ifobj_tx->xdp_zc_max_segs; + else + max_frags = XSK_DESC__MAX_SKB_FRAGS; + + test->mtu = MAX_ETH_JUMBO_SIZE; + + /* Valid packet for synch */ + pkts[0].len = MIN_PKT_SIZE; + pkts[0].valid = true; + + /* One valid packet with the max amount of frags */ + for (i = 1; i < max_frags + 1; i++) { + pkts[i].len = MIN_PKT_SIZE; + pkts[i].options = XDP_PKT_CONTD; + pkts[i].valid = true; + } + pkts[max_frags].options = 0; + + /* An invalid packet with the max amount of frags but signals packet + * continues on the last frag + */ + for (i = max_frags + 1; i < 2 * max_frags + 1; i++) { + pkts[i].len = MIN_PKT_SIZE; + pkts[i].options = XDP_PKT_CONTD; + pkts[i].valid = false; + } + + /* Valid packet for synch */ + pkts[2 * max_frags + 1].len = MIN_PKT_SIZE; + pkts[2 * max_frags + 1].valid = true; + + pkt_stream_generate_custom(test, pkts, 2 * max_frags + 2); + return testapp_validate_traffic(test); +} + static int xsk_load_xdp_programs(struct ifobject *ifobj) { ifobj->xdp_progs = xsk_xdp_progs__open_and_load(); @@ -1757,6 +2057,7 @@ static bool hugepages_present(void) static void init_iface(struct ifobject *ifobj, const char *dst_mac, const char *src_mac, thread_func_t func_ptr) { + LIBBPF_OPTS(bpf_xdp_query_opts, query_opts); int err; memcpy(ifobj->dst_mac, dst_mac, ETH_ALEN); @@ -1772,6 +2073,22 @@ static void init_iface(struct ifobject *ifobj, const char *dst_mac, const char * if (hugepages_present()) ifobj->unaligned_supp = true; + + err = bpf_xdp_query(ifobj->ifindex, XDP_FLAGS_DRV_MODE, &query_opts); + if (err) { + ksft_print_msg("Error querying XDP capabilities\n"); + exit_with_error(-err); + } + if (query_opts.feature_flags & NETDEV_XDP_ACT_RX_SG) + ifobj->multi_buff_supp = true; + if (query_opts.feature_flags & NETDEV_XDP_ACT_XSK_ZEROCOPY) { + if (query_opts.xdp_zc_max_segs > 1) { + ifobj->multi_buff_zc_supp = true; + ifobj->xdp_zc_max_segs = query_opts.xdp_zc_max_segs; + } else { + ifobj->xdp_zc_max_segs = 0; + } + } } static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_type type) @@ -1804,6 +2121,9 @@ static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_ test_spec_set_name(test, "RUN_TO_COMPLETION"); ret = testapp_validate_traffic(test); break; + case TEST_TYPE_RUN_TO_COMPLETION_MB: + ret = testapp_multi_buffer(test); + break; case TEST_TYPE_RUN_TO_COMPLETION_SINGLE_PKT: test_spec_set_name(test, "RUN_TO_COMPLETION_SINGLE_PKT"); ret = testapp_single_pkt(test); @@ -1866,9 +2186,22 @@ static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_ ret = testapp_invalid_desc(test); break; } + case TEST_TYPE_ALIGNED_INV_DESC_MB: + test_spec_set_name(test, "ALIGNED_INV_DESC_MULTI_BUFF"); + ret = testapp_invalid_desc_mb(test); + break; + case TEST_TYPE_UNALIGNED_INV_DESC_MB: + test_spec_set_name(test, "UNALIGNED_INV_DESC_MULTI_BUFF"); + test->ifobj_tx->umem->unaligned_mode = true; + test->ifobj_rx->umem->unaligned_mode = true; + ret = testapp_invalid_desc_mb(test); + break; case TEST_TYPE_UNALIGNED: ret = testapp_unaligned(test); break; + case TEST_TYPE_UNALIGNED_MB: + ret = testapp_unaligned_mb(test); + break; case TEST_TYPE_HEADROOM: ret = testapp_headroom(test); break; @@ -1876,8 +2209,17 @@ static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_ ret = testapp_xdp_drop(test); break; case TEST_TYPE_XDP_METADATA_COUNT: + test_spec_set_name(test, "XDP_METADATA_COUNT"); + ret = testapp_xdp_metadata_count(test); + break; + case TEST_TYPE_XDP_METADATA_COUNT_MB: + test_spec_set_name(test, "XDP_METADATA_COUNT_MULTI_BUFF"); + test->mtu = MAX_ETH_JUMBO_SIZE; ret = testapp_xdp_metadata_count(test); break; + case TEST_TYPE_TOO_MANY_FRAGS: + ret = testapp_too_many_frags(test); + break; default: break; } diff --git a/tools/testing/selftests/bpf/xskxceiver.h b/tools/testing/selftests/bpf/xskxceiver.h index aaf27e067640..233b66cef64a 100644 --- a/tools/testing/selftests/bpf/xskxceiver.h +++ b/tools/testing/selftests/bpf/xskxceiver.h @@ -38,6 +38,8 @@ #define MAX_TEARDOWN_ITER 10 #define PKT_HDR_SIZE (sizeof(struct ethhdr) + 2) /* Just to align the data in the packet */ #define MIN_PKT_SIZE 64 +#define MAX_ETH_PKT_SIZE 1518 +#define MAX_ETH_JUMBO_SIZE 9000 #define USLEEP_MAX 10000 #define SOCK_RECONF_CTR 10 #define BATCH_SIZE 64 @@ -47,7 +49,11 @@ #define DEFAULT_UMEM_BUFFERS (DEFAULT_PKT_CNT / 4) #define RX_FULL_RXQSIZE 32 #define UMEM_HEADROOM_TEST_SIZE 128 -#define XSK_UMEM__INVALID_FRAME_SIZE (XSK_UMEM__DEFAULT_FRAME_SIZE + 1) +#define XSK_UMEM__INVALID_FRAME_SIZE (MAX_ETH_JUMBO_SIZE + 1) +#define XSK_UMEM__LARGE_FRAME_SIZE (3 * 1024) +#define XSK_UMEM__MAX_FRAME_SIZE (4 * 1024) +#define XSK_DESC__INVALID_OPTION (0xffff) +#define XSK_DESC__MAX_SKB_FRAGS 18 #define HUGEPAGE_SIZE (2 * 1024 * 1024) #define PKT_DUMP_NB_TO_PRINT 16 @@ -83,6 +89,12 @@ enum test_type { TEST_TYPE_BPF_RES, TEST_TYPE_XDP_DROP_HALF, TEST_TYPE_XDP_METADATA_COUNT, + TEST_TYPE_XDP_METADATA_COUNT_MB, + TEST_TYPE_RUN_TO_COMPLETION_MB, + TEST_TYPE_UNALIGNED_MB, + TEST_TYPE_ALIGNED_INV_DESC_MB, + TEST_TYPE_UNALIGNED_INV_DESC_MB, + TEST_TYPE_TOO_MANY_FRAGS, TEST_TYPE_MAX }; @@ -115,6 +127,7 @@ struct pkt { u32 len; u32 pkt_nb; bool valid; + u16 options; }; struct pkt_stream { @@ -122,6 +135,7 @@ struct pkt_stream { u32 current_pkt_nb; struct pkt *pkts; u32 max_pkt_len; + bool verbatim; }; struct ifobject; @@ -141,7 +155,9 @@ struct ifobject { struct bpf_program *xdp_prog; enum test_mode mode; int ifindex; + int mtu; u32 bind_flags; + u32 xdp_zc_max_segs; bool tx_on; bool rx_on; bool use_poll; @@ -151,6 +167,8 @@ struct ifobject { bool shared_umem; bool use_metadata; bool unaligned_supp; + bool multi_buff_supp; + bool multi_buff_zc_supp; u8 dst_mac[ETH_ALEN]; u8 src_mac[ETH_ALEN]; }; @@ -164,6 +182,7 @@ struct test_spec { struct bpf_program *xdp_prog_tx; struct bpf_map *xskmap_rx; struct bpf_map *xskmap_tx; + int mtu; u16 total_steps; u16 current_step; u16 nb_sockets; diff --git a/tools/testing/selftests/cachestat/Makefile b/tools/testing/selftests/cachestat/Makefile index fca73aaa7d14..778b54ebb036 100644 --- a/tools/testing/selftests/cachestat/Makefile +++ b/tools/testing/selftests/cachestat/Makefile @@ -3,6 +3,6 @@ TEST_GEN_PROGS := test_cachestat CFLAGS += $(KHDR_INCLUDES) CFLAGS += -Wall -CFLAGS += -lrt +LDLIBS += -lrt include ../lib.mk diff --git a/tools/testing/selftests/cachestat/test_cachestat.c b/tools/testing/selftests/cachestat/test_cachestat.c index 54d09b820ed4..4804c7dc7b31 100644 --- a/tools/testing/selftests/cachestat/test_cachestat.c +++ b/tools/testing/selftests/cachestat/test_cachestat.c @@ -4,10 +4,12 @@ #include <stdio.h> #include <stdbool.h> #include <linux/kernel.h> +#include <linux/magic.h> #include <linux/mman.h> #include <sys/mman.h> #include <sys/shm.h> #include <sys/syscall.h> +#include <sys/vfs.h> #include <unistd.h> #include <string.h> #include <fcntl.h> @@ -15,11 +17,12 @@ #include "../kselftest.h" +#define NR_TESTS 9 + static const char * const dev_files[] = { "/dev/zero", "/dev/null", "/dev/urandom", "/proc/version", "/proc" }; -static const int cachestat_nr = 451; void print_cachestat(struct cachestat *cs) { @@ -91,19 +94,33 @@ out: } /* + * fsync() is implemented via noop_fsync() on tmpfs. This makes the fsync() + * test fail below, so we need to check for test file living on a tmpfs. + */ +static bool is_on_tmpfs(int fd) +{ + struct statfs statfs_buf; + + if (fstatfs(fd, &statfs_buf)) + return false; + + return statfs_buf.f_type == TMPFS_MAGIC; +} + +/* * Open/create the file at filename, (optionally) write random data to it * (exactly num_pages), then test the cachestat syscall on this file. * * If test_fsync == true, fsync the file, then check the number of dirty * pages. */ -bool test_cachestat(const char *filename, bool write_random, bool create, - bool test_fsync, unsigned long num_pages, int open_flags, - mode_t open_mode) +static int test_cachestat(const char *filename, bool write_random, bool create, + bool test_fsync, unsigned long num_pages, + int open_flags, mode_t open_mode) { size_t PS = sysconf(_SC_PAGESIZE); int filesize = num_pages * PS; - bool ret = true; + int ret = KSFT_PASS; long syscall_ret; struct cachestat cs; struct cachestat_range cs_range = { 0, filesize }; @@ -112,7 +129,7 @@ bool test_cachestat(const char *filename, bool write_random, bool create, if (fd == -1) { ksft_print_msg("Unable to create/open file.\n"); - ret = false; + ret = KSFT_FAIL; goto out; } else { ksft_print_msg("Create/open %s\n", filename); @@ -121,18 +138,18 @@ bool test_cachestat(const char *filename, bool write_random, bool create, if (write_random) { if (!write_exactly(fd, filesize)) { ksft_print_msg("Unable to access urandom.\n"); - ret = false; + ret = KSFT_FAIL; goto out1; } } - syscall_ret = syscall(cachestat_nr, fd, &cs_range, &cs, 0); + syscall_ret = syscall(__NR_cachestat, fd, &cs_range, &cs, 0); ksft_print_msg("Cachestat call returned %ld\n", syscall_ret); if (syscall_ret) { ksft_print_msg("Cachestat returned non-zero.\n"); - ret = false; + ret = KSFT_FAIL; goto out1; } else { @@ -142,17 +159,19 @@ bool test_cachestat(const char *filename, bool write_random, bool create, if (cs.nr_cache + cs.nr_evicted != num_pages) { ksft_print_msg( "Total number of cached and evicted pages is off.\n"); - ret = false; + ret = KSFT_FAIL; } } } if (test_fsync) { - if (fsync(fd)) { + if (is_on_tmpfs(fd)) { + ret = KSFT_SKIP; + } else if (fsync(fd)) { ksft_print_msg("fsync fails.\n"); - ret = false; + ret = KSFT_FAIL; } else { - syscall_ret = syscall(cachestat_nr, fd, &cs_range, &cs, 0); + syscall_ret = syscall(__NR_cachestat, fd, &cs_range, &cs, 0); ksft_print_msg("Cachestat call (after fsync) returned %ld\n", syscall_ret); @@ -161,13 +180,13 @@ bool test_cachestat(const char *filename, bool write_random, bool create, print_cachestat(&cs); if (cs.nr_dirty) { - ret = false; + ret = KSFT_FAIL; ksft_print_msg( "Number of dirty should be zero after fsync.\n"); } } else { ksft_print_msg("Cachestat (after fsync) returned non-zero.\n"); - ret = false; + ret = KSFT_FAIL; goto out1; } } @@ -213,7 +232,7 @@ bool test_cachestat_shmem(void) goto close_fd; } - syscall_ret = syscall(cachestat_nr, fd, &cs_range, &cs, 0); + syscall_ret = syscall(__NR_cachestat, fd, &cs_range, &cs, 0); if (syscall_ret) { ksft_print_msg("Cachestat returned non-zero.\n"); @@ -236,13 +255,29 @@ out: int main(void) { - int ret = 0; + int ret; + + ksft_print_header(); + + ret = syscall(__NR_cachestat, -1, NULL, NULL, 0); + if (ret == -1 && errno == ENOSYS) + ksft_exit_skip("cachestat syscall not available\n"); + + ksft_set_plan(NR_TESTS); + + if (ret == -1 && errno == EBADF) { + ksft_test_result_pass("bad file descriptor recognized\n"); + ret = 0; + } else { + ksft_test_result_fail("bad file descriptor ignored\n"); + ret = 1; + } for (int i = 0; i < 5; i++) { const char *dev_filename = dev_files[i]; if (test_cachestat(dev_filename, false, false, false, - 4, O_RDONLY, 0400)) + 4, O_RDONLY, 0400) == KSFT_PASS) ksft_test_result_pass("cachestat works with %s\n", dev_filename); else { ksft_test_result_fail("cachestat fails with %s\n", dev_filename); @@ -251,13 +286,27 @@ int main(void) } if (test_cachestat("tmpfilecachestat", true, true, - true, 4, O_CREAT | O_RDWR, 0400 | 0600)) + false, 4, O_CREAT | O_RDWR, 0600) == KSFT_PASS) ksft_test_result_pass("cachestat works with a normal file\n"); else { ksft_test_result_fail("cachestat fails with normal file\n"); ret = 1; } + switch (test_cachestat("tmpfilecachestat", true, true, + true, 4, O_CREAT | O_RDWR, 0600)) { + case KSFT_FAIL: + ksft_test_result_fail("cachestat fsync fails with normal file\n"); + ret = KSFT_FAIL; + break; + case KSFT_PASS: + ksft_test_result_pass("cachestat fsync works with a normal file\n"); + break; + case KSFT_SKIP: + ksft_test_result_skip("tmpfilecachestat is on tmpfs\n"); + break; + } + if (test_cachestat_shmem()) ksft_test_result_pass("cachestat works with a shmem file\n"); else { diff --git a/tools/testing/selftests/cgroup/.gitignore b/tools/testing/selftests/cgroup/.gitignore index c4a57e69f749..af8c3f30b9c1 100644 --- a/tools/testing/selftests/cgroup/.gitignore +++ b/tools/testing/selftests/cgroup/.gitignore @@ -5,4 +5,6 @@ test_freezer test_kmem test_kill test_cpu +test_cpuset +test_zswap wait_inotify diff --git a/tools/testing/selftests/cgroup/Makefile b/tools/testing/selftests/cgroup/Makefile index 3d263747d2ad..c27f05f6ce9b 100644 --- a/tools/testing/selftests/cgroup/Makefile +++ b/tools/testing/selftests/cgroup/Makefile @@ -12,6 +12,8 @@ TEST_GEN_PROGS += test_core TEST_GEN_PROGS += test_freezer TEST_GEN_PROGS += test_kill TEST_GEN_PROGS += test_cpu +TEST_GEN_PROGS += test_cpuset +TEST_GEN_PROGS += test_zswap LOCAL_HDRS += $(selfdir)/clone3/clone3_selftests.h $(selfdir)/pidfd/pidfd.h @@ -23,3 +25,5 @@ $(OUTPUT)/test_core: cgroup_util.c $(OUTPUT)/test_freezer: cgroup_util.c $(OUTPUT)/test_kill: cgroup_util.c $(OUTPUT)/test_cpu: cgroup_util.c +$(OUTPUT)/test_cpuset: cgroup_util.c +$(OUTPUT)/test_zswap: cgroup_util.c diff --git a/tools/testing/selftests/cgroup/cgroup_util.c b/tools/testing/selftests/cgroup/cgroup_util.c index e8bbbdb77e0d..0340d4ca8f51 100644 --- a/tools/testing/selftests/cgroup/cgroup_util.c +++ b/tools/testing/selftests/cgroup/cgroup_util.c @@ -286,6 +286,8 @@ int cg_destroy(const char *cgroup) { int ret; + if (!cgroup) + return 0; retry: ret = rmdir(cgroup); if (ret && errno == EBUSY) { diff --git a/tools/testing/selftests/cgroup/cgroup_util.h b/tools/testing/selftests/cgroup/cgroup_util.h index c92df4e5d395..1df7f202214a 100644 --- a/tools/testing/selftests/cgroup/cgroup_util.h +++ b/tools/testing/selftests/cgroup/cgroup_util.h @@ -11,6 +11,8 @@ #define USEC_PER_SEC 1000000L #define NSEC_PER_SEC 1000000000L +#define TEST_UID 65534 /* usually nobody, any !root is fine */ + /* * Checks if two given values differ by less than err% of their sum. */ diff --git a/tools/testing/selftests/cgroup/test_core.c b/tools/testing/selftests/cgroup/test_core.c index 600123503063..80aa6b2373b9 100644 --- a/tools/testing/selftests/cgroup/test_core.c +++ b/tools/testing/selftests/cgroup/test_core.c @@ -683,7 +683,7 @@ cleanup: */ static int test_cgcore_lesser_euid_open(const char *root) { - const uid_t test_euid = 65534; /* usually nobody, any !root is fine */ + const uid_t test_euid = TEST_UID; int ret = KSFT_FAIL; char *cg_test_a = NULL, *cg_test_b = NULL; char *cg_test_a_procs = NULL, *cg_test_b_procs = NULL; diff --git a/tools/testing/selftests/cgroup/test_cpuset.c b/tools/testing/selftests/cgroup/test_cpuset.c new file mode 100644 index 000000000000..b061ed1e05b4 --- /dev/null +++ b/tools/testing/selftests/cgroup/test_cpuset.c @@ -0,0 +1,275 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/limits.h> +#include <signal.h> + +#include "../kselftest.h" +#include "cgroup_util.h" + +static int idle_process_fn(const char *cgroup, void *arg) +{ + (void)pause(); + return 0; +} + +static int do_migration_fn(const char *cgroup, void *arg) +{ + int object_pid = (int)(size_t)arg; + + if (setuid(TEST_UID)) + return EXIT_FAILURE; + + // XXX checking /proc/$pid/cgroup would be quicker than wait + if (cg_enter(cgroup, object_pid) || + cg_wait_for_proc_count(cgroup, 1)) + return EXIT_FAILURE; + + return EXIT_SUCCESS; +} + +static int do_controller_fn(const char *cgroup, void *arg) +{ + const char *child = cgroup; + const char *parent = arg; + + if (setuid(TEST_UID)) + return EXIT_FAILURE; + + if (!cg_read_strstr(child, "cgroup.controllers", "cpuset")) + return EXIT_FAILURE; + + if (cg_write(parent, "cgroup.subtree_control", "+cpuset")) + return EXIT_FAILURE; + + if (cg_read_strstr(child, "cgroup.controllers", "cpuset")) + return EXIT_FAILURE; + + if (cg_write(parent, "cgroup.subtree_control", "-cpuset")) + return EXIT_FAILURE; + + if (!cg_read_strstr(child, "cgroup.controllers", "cpuset")) + return EXIT_FAILURE; + + return EXIT_SUCCESS; +} + +/* + * Migrate a process between two sibling cgroups. + * The success should only depend on the parent cgroup permissions and not the + * migrated process itself (cpuset controller is in place because it uses + * security_task_setscheduler() in cgroup v1). + * + * Deliberately don't set cpuset.cpus in children to avoid definining migration + * permissions between two different cpusets. + */ +static int test_cpuset_perms_object(const char *root, bool allow) +{ + char *parent = NULL, *child_src = NULL, *child_dst = NULL; + char *parent_procs = NULL, *child_src_procs = NULL, *child_dst_procs = NULL; + const uid_t test_euid = TEST_UID; + int object_pid = 0; + int ret = KSFT_FAIL; + + parent = cg_name(root, "cpuset_test_0"); + if (!parent) + goto cleanup; + parent_procs = cg_name(parent, "cgroup.procs"); + if (!parent_procs) + goto cleanup; + if (cg_create(parent)) + goto cleanup; + + child_src = cg_name(parent, "cpuset_test_1"); + if (!child_src) + goto cleanup; + child_src_procs = cg_name(child_src, "cgroup.procs"); + if (!child_src_procs) + goto cleanup; + if (cg_create(child_src)) + goto cleanup; + + child_dst = cg_name(parent, "cpuset_test_2"); + if (!child_dst) + goto cleanup; + child_dst_procs = cg_name(child_dst, "cgroup.procs"); + if (!child_dst_procs) + goto cleanup; + if (cg_create(child_dst)) + goto cleanup; + + if (cg_write(parent, "cgroup.subtree_control", "+cpuset")) + goto cleanup; + + if (cg_read_strstr(child_src, "cgroup.controllers", "cpuset") || + cg_read_strstr(child_dst, "cgroup.controllers", "cpuset")) + goto cleanup; + + /* Enable permissions along src->dst tree path */ + if (chown(child_src_procs, test_euid, -1) || + chown(child_dst_procs, test_euid, -1)) + goto cleanup; + + if (allow && chown(parent_procs, test_euid, -1)) + goto cleanup; + + /* Fork a privileged child as a test object */ + object_pid = cg_run_nowait(child_src, idle_process_fn, NULL); + if (object_pid < 0) + goto cleanup; + + /* Carry out migration in a child process that can drop all privileges + * (including capabilities), the main process must remain privileged for + * cleanup. + * Child process's cgroup is irrelevant but we place it into child_dst + * as hacky way to pass information about migration target to the child. + */ + if (allow ^ (cg_run(child_dst, do_migration_fn, (void *)(size_t)object_pid) == EXIT_SUCCESS)) + goto cleanup; + + ret = KSFT_PASS; + +cleanup: + if (object_pid > 0) { + (void)kill(object_pid, SIGTERM); + (void)clone_reap(object_pid, WEXITED); + } + + cg_destroy(child_dst); + free(child_dst_procs); + free(child_dst); + + cg_destroy(child_src); + free(child_src_procs); + free(child_src); + + cg_destroy(parent); + free(parent_procs); + free(parent); + + return ret; +} + +static int test_cpuset_perms_object_allow(const char *root) +{ + return test_cpuset_perms_object(root, true); +} + +static int test_cpuset_perms_object_deny(const char *root) +{ + return test_cpuset_perms_object(root, false); +} + +/* + * Migrate a process between parent and child implicitely + * Implicit migration happens when a controller is enabled/disabled. + * + */ +static int test_cpuset_perms_subtree(const char *root) +{ + char *parent = NULL, *child = NULL; + char *parent_procs = NULL, *parent_subctl = NULL, *child_procs = NULL; + const uid_t test_euid = TEST_UID; + int object_pid = 0; + int ret = KSFT_FAIL; + + parent = cg_name(root, "cpuset_test_0"); + if (!parent) + goto cleanup; + parent_procs = cg_name(parent, "cgroup.procs"); + if (!parent_procs) + goto cleanup; + parent_subctl = cg_name(parent, "cgroup.subtree_control"); + if (!parent_subctl) + goto cleanup; + if (cg_create(parent)) + goto cleanup; + + child = cg_name(parent, "cpuset_test_1"); + if (!child) + goto cleanup; + child_procs = cg_name(child, "cgroup.procs"); + if (!child_procs) + goto cleanup; + if (cg_create(child)) + goto cleanup; + + /* Enable permissions as in a delegated subtree */ + if (chown(parent_procs, test_euid, -1) || + chown(parent_subctl, test_euid, -1) || + chown(child_procs, test_euid, -1)) + goto cleanup; + + /* Put a privileged child in the subtree and modify controller state + * from an unprivileged process, the main process remains privileged + * for cleanup. + * The unprivileged child runs in subtree too to avoid parent and + * internal-node constraing violation. + */ + object_pid = cg_run_nowait(child, idle_process_fn, NULL); + if (object_pid < 0) + goto cleanup; + + if (cg_run(child, do_controller_fn, parent) != EXIT_SUCCESS) + goto cleanup; + + ret = KSFT_PASS; + +cleanup: + if (object_pid > 0) { + (void)kill(object_pid, SIGTERM); + (void)clone_reap(object_pid, WEXITED); + } + + cg_destroy(child); + free(child_procs); + free(child); + + cg_destroy(parent); + free(parent_subctl); + free(parent_procs); + free(parent); + + return ret; +} + + +#define T(x) { x, #x } +struct cpuset_test { + int (*fn)(const char *root); + const char *name; +} tests[] = { + T(test_cpuset_perms_object_allow), + T(test_cpuset_perms_object_deny), + T(test_cpuset_perms_subtree), +}; +#undef T + +int main(int argc, char *argv[]) +{ + char root[PATH_MAX]; + int i, ret = EXIT_SUCCESS; + + if (cg_find_unified_root(root, sizeof(root))) + ksft_exit_skip("cgroup v2 isn't mounted\n"); + + if (cg_read_strstr(root, "cgroup.subtree_control", "cpuset")) + if (cg_write(root, "cgroup.subtree_control", "+cpuset")) + ksft_exit_skip("Failed to set cpuset controller\n"); + + for (i = 0; i < ARRAY_SIZE(tests); i++) { + switch (tests[i].fn(root)) { + case KSFT_PASS: + ksft_test_result_pass("%s\n", tests[i].name); + break; + case KSFT_SKIP: + ksft_test_result_skip("%s\n", tests[i].name); + break; + default: + ret = EXIT_FAILURE; + ksft_test_result_fail("%s\n", tests[i].name); + break; + } + } + + return ret; +} diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh index 2b5215cc599f..4afb132e4e4f 100755 --- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh +++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh @@ -10,7 +10,7 @@ skip_test() { echo "$1" echo "Test SKIPPED" - exit 0 + exit 4 # ksft_skip } [[ $(id -u) -eq 0 ]] || skip_test "Test must be run as root!" diff --git a/tools/testing/selftests/cgroup/test_kmem.c b/tools/testing/selftests/cgroup/test_kmem.c index 1b2cec9d18a4..c82f974b85c9 100644 --- a/tools/testing/selftests/cgroup/test_kmem.c +++ b/tools/testing/selftests/cgroup/test_kmem.c @@ -75,11 +75,11 @@ static int test_kmem_basic(const char *root) sleep(1); slab1 = cg_read_key_long(cg, "memory.stat", "slab "); - if (slab1 <= 0) + if (slab1 < 0) goto cleanup; current = cg_read_long(cg, "memory.current"); - if (current <= 0) + if (current < 0) goto cleanup; if (slab1 < slab0 / 2 && current < slab0 / 2) @@ -162,11 +162,11 @@ static int cg_run_in_subcgroups(const char *parent, * allocates some slab memory (mostly negative dentries) using 2 * NR_CPUS * threads. Then it checks the sanity of numbers on the parent level: * the total size of the cgroups should be roughly equal to - * anon + file + slab + kernel_stack. + * anon + file + kernel + sock. */ static int test_kmem_memcg_deletion(const char *root) { - long current, slab, anon, file, kernel_stack, pagetables, percpu, sock, sum; + long current, anon, file, kernel, sock, sum; int ret = KSFT_FAIL; char *parent; @@ -184,29 +184,22 @@ static int test_kmem_memcg_deletion(const char *root) goto cleanup; current = cg_read_long(parent, "memory.current"); - slab = cg_read_key_long(parent, "memory.stat", "slab "); anon = cg_read_key_long(parent, "memory.stat", "anon "); file = cg_read_key_long(parent, "memory.stat", "file "); - kernel_stack = cg_read_key_long(parent, "memory.stat", "kernel_stack "); - pagetables = cg_read_key_long(parent, "memory.stat", "pagetables "); - percpu = cg_read_key_long(parent, "memory.stat", "percpu "); + kernel = cg_read_key_long(parent, "memory.stat", "kernel "); sock = cg_read_key_long(parent, "memory.stat", "sock "); - if (current < 0 || slab < 0 || anon < 0 || file < 0 || - kernel_stack < 0 || pagetables < 0 || percpu < 0 || sock < 0) + if (current < 0 || anon < 0 || file < 0 || kernel < 0 || sock < 0) goto cleanup; - sum = slab + anon + file + kernel_stack + pagetables + percpu + sock; + sum = anon + file + kernel + sock; if (abs(sum - current) < MAX_VMSTAT_ERROR) { ret = KSFT_PASS; } else { printf("memory.current = %ld\n", current); - printf("slab + anon + file + kernel_stack = %ld\n", sum); - printf("slab = %ld\n", slab); + printf("anon + file + kernel + sock = %ld\n", sum); printf("anon = %ld\n", anon); printf("file = %ld\n", file); - printf("kernel_stack = %ld\n", kernel_stack); - printf("pagetables = %ld\n", pagetables); - printf("percpu = %ld\n", percpu); + printf("kernel = %ld\n", kernel); printf("sock = %ld\n", sock); } diff --git a/tools/testing/selftests/cgroup/test_zswap.c b/tools/testing/selftests/cgroup/test_zswap.c new file mode 100644 index 000000000000..49def87a909b --- /dev/null +++ b/tools/testing/selftests/cgroup/test_zswap.c @@ -0,0 +1,286 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE + +#include <linux/limits.h> +#include <unistd.h> +#include <stdio.h> +#include <signal.h> +#include <sys/sysinfo.h> +#include <string.h> +#include <sys/wait.h> +#include <sys/mman.h> + +#include "../kselftest.h" +#include "cgroup_util.h" + +static int read_int(const char *path, size_t *value) +{ + FILE *file; + int ret = 0; + + file = fopen(path, "r"); + if (!file) + return -1; + if (fscanf(file, "%ld", value) != 1) + ret = -1; + fclose(file); + return ret; +} + +static int set_min_free_kb(size_t value) +{ + FILE *file; + int ret; + + file = fopen("/proc/sys/vm/min_free_kbytes", "w"); + if (!file) + return -1; + ret = fprintf(file, "%ld\n", value); + fclose(file); + return ret; +} + +static int read_min_free_kb(size_t *value) +{ + return read_int("/proc/sys/vm/min_free_kbytes", value); +} + +static int get_zswap_stored_pages(size_t *value) +{ + return read_int("/sys/kernel/debug/zswap/stored_pages", value); +} + +static int get_zswap_written_back_pages(size_t *value) +{ + return read_int("/sys/kernel/debug/zswap/written_back_pages", value); +} + +static int allocate_bytes(const char *cgroup, void *arg) +{ + size_t size = (size_t)arg; + char *mem = (char *)malloc(size); + + if (!mem) + return -1; + for (int i = 0; i < size; i += 4095) + mem[i] = 'a'; + free(mem); + return 0; +} + +/* + * When trying to store a memcg page in zswap, if the memcg hits its memory + * limit in zswap, writeback should not be triggered. + * + * This was fixed with commit 0bdf0efa180a("zswap: do not shrink if cgroup may + * not zswap"). Needs to be revised when a per memcg writeback mechanism is + * implemented. + */ +static int test_no_invasive_cgroup_shrink(const char *root) +{ + size_t written_back_before, written_back_after; + int ret = KSFT_FAIL; + char *test_group; + + /* Set up */ + test_group = cg_name(root, "no_shrink_test"); + if (!test_group) + goto out; + if (cg_create(test_group)) + goto out; + if (cg_write(test_group, "memory.max", "1M")) + goto out; + if (cg_write(test_group, "memory.zswap.max", "10K")) + goto out; + if (get_zswap_written_back_pages(&written_back_before)) + goto out; + + /* Allocate 10x memory.max to push memory into zswap */ + if (cg_run(test_group, allocate_bytes, (void *)MB(10))) + goto out; + + /* Verify that no writeback happened because of the memcg allocation */ + if (get_zswap_written_back_pages(&written_back_after)) + goto out; + if (written_back_after == written_back_before) + ret = KSFT_PASS; +out: + cg_destroy(test_group); + free(test_group); + return ret; +} + +struct no_kmem_bypass_child_args { + size_t target_alloc_bytes; + size_t child_allocated; +}; + +static int no_kmem_bypass_child(const char *cgroup, void *arg) +{ + struct no_kmem_bypass_child_args *values = arg; + void *allocation; + + allocation = malloc(values->target_alloc_bytes); + if (!allocation) { + values->child_allocated = true; + return -1; + } + for (long i = 0; i < values->target_alloc_bytes; i += 4095) + ((char *)allocation)[i] = 'a'; + values->child_allocated = true; + pause(); + free(allocation); + return 0; +} + +/* + * When pages owned by a memcg are pushed to zswap by kswapd, they should be + * charged to that cgroup. This wasn't the case before commit + * cd08d80ecdac("mm: correctly charge compressed memory to its memcg"). + * + * The test first allocates memory in a memcg, then raises min_free_kbytes to + * a very high value so that the allocation falls below low wm, then makes + * another allocation to trigger kswapd that should push the memcg-owned pages + * to zswap and verifies that the zswap pages are correctly charged. + * + * To be run on a VM with at most 4G of memory. + */ +static int test_no_kmem_bypass(const char *root) +{ + size_t min_free_kb_high, min_free_kb_low, min_free_kb_original; + struct no_kmem_bypass_child_args *values; + size_t trigger_allocation_size; + int wait_child_iteration = 0; + long stored_pages_threshold; + struct sysinfo sys_info; + int ret = KSFT_FAIL; + int child_status; + char *test_group; + pid_t child_pid; + + /* Read sys info and compute test values accordingly */ + if (sysinfo(&sys_info) != 0) + return KSFT_FAIL; + if (sys_info.totalram > 5000000000) + return KSFT_SKIP; + values = mmap(0, sizeof(struct no_kmem_bypass_child_args), PROT_READ | + PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, -1, 0); + if (values == MAP_FAILED) + return KSFT_FAIL; + if (read_min_free_kb(&min_free_kb_original)) + return KSFT_FAIL; + min_free_kb_high = sys_info.totalram / 2000; + min_free_kb_low = sys_info.totalram / 500000; + values->target_alloc_bytes = (sys_info.totalram - min_free_kb_high * 1000) + + sys_info.totalram * 5 / 100; + stored_pages_threshold = sys_info.totalram / 5 / 4096; + trigger_allocation_size = sys_info.totalram / 20; + + /* Set up test memcg */ + if (cg_write(root, "cgroup.subtree_control", "+memory")) + goto out; + test_group = cg_name(root, "kmem_bypass_test"); + if (!test_group) + goto out; + + /* Spawn memcg child and wait for it to allocate */ + set_min_free_kb(min_free_kb_low); + if (cg_create(test_group)) + goto out; + values->child_allocated = false; + child_pid = cg_run_nowait(test_group, no_kmem_bypass_child, values); + if (child_pid < 0) + goto out; + while (!values->child_allocated && wait_child_iteration++ < 10000) + usleep(1000); + + /* Try to wakeup kswapd and let it push child memory to zswap */ + set_min_free_kb(min_free_kb_high); + for (int i = 0; i < 20; i++) { + size_t stored_pages; + char *trigger_allocation = malloc(trigger_allocation_size); + + if (!trigger_allocation) + break; + for (int i = 0; i < trigger_allocation_size; i += 4095) + trigger_allocation[i] = 'b'; + usleep(100000); + free(trigger_allocation); + if (get_zswap_stored_pages(&stored_pages)) + break; + if (stored_pages < 0) + break; + /* If memory was pushed to zswap, verify it belongs to memcg */ + if (stored_pages > stored_pages_threshold) { + int zswapped = cg_read_key_long(test_group, "memory.stat", "zswapped "); + int delta = stored_pages * 4096 - zswapped; + int result_ok = delta < stored_pages * 4096 / 4; + + ret = result_ok ? KSFT_PASS : KSFT_FAIL; + break; + } + } + + kill(child_pid, SIGTERM); + waitpid(child_pid, &child_status, 0); +out: + set_min_free_kb(min_free_kb_original); + cg_destroy(test_group); + free(test_group); + return ret; +} + +#define T(x) { x, #x } +struct zswap_test { + int (*fn)(const char *root); + const char *name; +} tests[] = { + T(test_no_kmem_bypass), + T(test_no_invasive_cgroup_shrink), +}; +#undef T + +static bool zswap_configured(void) +{ + return access("/sys/module/zswap", F_OK) == 0; +} + +int main(int argc, char **argv) +{ + char root[PATH_MAX]; + int i, ret = EXIT_SUCCESS; + + if (cg_find_unified_root(root, sizeof(root))) + ksft_exit_skip("cgroup v2 isn't mounted\n"); + + if (!zswap_configured()) + ksft_exit_skip("zswap isn't configured\n"); + + /* + * Check that memory controller is available: + * memory is listed in cgroup.controllers + */ + if (cg_read_strstr(root, "cgroup.controllers", "memory")) + ksft_exit_skip("memory controller isn't available\n"); + + if (cg_read_strstr(root, "cgroup.subtree_control", "memory")) + if (cg_write(root, "cgroup.subtree_control", "+memory")) + ksft_exit_skip("Failed to set memory controller\n"); + + for (i = 0; i < ARRAY_SIZE(tests); i++) { + switch (tests[i].fn(root)) { + case KSFT_PASS: + ksft_test_result_pass("%s\n", tests[i].name); + break; + case KSFT_SKIP: + ksft_test_result_skip("%s\n", tests[i].name); + break; + default: + ret = EXIT_FAILURE; + ksft_test_result_fail("%s\n", tests[i].name); + break; + } + } + + return ret; +} diff --git a/tools/testing/selftests/connector/.gitignore b/tools/testing/selftests/connector/.gitignore new file mode 100644 index 000000000000..c90098199a44 --- /dev/null +++ b/tools/testing/selftests/connector/.gitignore @@ -0,0 +1 @@ +proc_filter diff --git a/tools/testing/selftests/connector/Makefile b/tools/testing/selftests/connector/Makefile new file mode 100644 index 000000000000..92188b9bac5c --- /dev/null +++ b/tools/testing/selftests/connector/Makefile @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0 +CFLAGS += -Wall $(KHDR_INCLUDES) + +TEST_GEN_PROGS = proc_filter + +include ../lib.mk diff --git a/tools/testing/selftests/connector/proc_filter.c b/tools/testing/selftests/connector/proc_filter.c new file mode 100644 index 000000000000..4a825b997666 --- /dev/null +++ b/tools/testing/selftests/connector/proc_filter.c @@ -0,0 +1,310 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <sys/types.h> +#include <sys/epoll.h> +#include <sys/socket.h> +#include <linux/netlink.h> +#include <linux/connector.h> +#include <linux/cn_proc.h> + +#include <stddef.h> +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <strings.h> +#include <errno.h> +#include <signal.h> +#include <string.h> + +#include "../kselftest.h" + +#define NL_MESSAGE_SIZE (sizeof(struct nlmsghdr) + sizeof(struct cn_msg) + \ + sizeof(struct proc_input)) +#define NL_MESSAGE_SIZE_NF (sizeof(struct nlmsghdr) + sizeof(struct cn_msg) + \ + sizeof(int)) + +#define MAX_EVENTS 1 + +volatile static int interrupted; +static int nl_sock, ret_errno, tcount; +static struct epoll_event evn; + +static int filter; + +#ifdef ENABLE_PRINTS +#define Printf printf +#else +#define Printf ksft_print_msg +#endif + +int send_message(void *pinp) +{ + char buff[NL_MESSAGE_SIZE]; + struct nlmsghdr *hdr; + struct cn_msg *msg; + + hdr = (struct nlmsghdr *)buff; + if (filter) + hdr->nlmsg_len = NL_MESSAGE_SIZE; + else + hdr->nlmsg_len = NL_MESSAGE_SIZE_NF; + hdr->nlmsg_type = NLMSG_DONE; + hdr->nlmsg_flags = 0; + hdr->nlmsg_seq = 0; + hdr->nlmsg_pid = getpid(); + + msg = (struct cn_msg *)NLMSG_DATA(hdr); + msg->id.idx = CN_IDX_PROC; + msg->id.val = CN_VAL_PROC; + msg->seq = 0; + msg->ack = 0; + msg->flags = 0; + + if (filter) { + msg->len = sizeof(struct proc_input); + ((struct proc_input *)msg->data)->mcast_op = + ((struct proc_input *)pinp)->mcast_op; + ((struct proc_input *)msg->data)->event_type = + ((struct proc_input *)pinp)->event_type; + } else { + msg->len = sizeof(int); + *(int *)msg->data = *(enum proc_cn_mcast_op *)pinp; + } + + if (send(nl_sock, hdr, hdr->nlmsg_len, 0) == -1) { + ret_errno = errno; + perror("send failed"); + return -3; + } + return 0; +} + +int register_proc_netlink(int *efd, void *input) +{ + struct sockaddr_nl sa_nl; + int err = 0, epoll_fd; + + nl_sock = socket(PF_NETLINK, SOCK_DGRAM, NETLINK_CONNECTOR); + + if (nl_sock == -1) { + ret_errno = errno; + perror("socket failed"); + return -1; + } + + bzero(&sa_nl, sizeof(sa_nl)); + sa_nl.nl_family = AF_NETLINK; + sa_nl.nl_groups = CN_IDX_PROC; + sa_nl.nl_pid = getpid(); + + if (bind(nl_sock, (struct sockaddr *)&sa_nl, sizeof(sa_nl)) == -1) { + ret_errno = errno; + perror("bind failed"); + return -2; + } + + epoll_fd = epoll_create1(EPOLL_CLOEXEC); + if (epoll_fd < 0) { + ret_errno = errno; + perror("epoll_create1 failed"); + return -2; + } + + err = send_message(input); + + if (err < 0) + return err; + + evn.events = EPOLLIN; + evn.data.fd = nl_sock; + if (epoll_ctl(epoll_fd, EPOLL_CTL_ADD, nl_sock, &evn) < 0) { + ret_errno = errno; + perror("epoll_ctl failed"); + return -3; + } + *efd = epoll_fd; + return 0; +} + +static void sigint(int sig) +{ + interrupted = 1; +} + +int handle_packet(char *buff, int fd, struct proc_event *event) +{ + struct nlmsghdr *hdr; + + hdr = (struct nlmsghdr *)buff; + + if (hdr->nlmsg_type == NLMSG_ERROR) { + perror("NLMSG_ERROR error\n"); + return -3; + } else if (hdr->nlmsg_type == NLMSG_DONE) { + event = (struct proc_event *) + ((struct cn_msg *)NLMSG_DATA(hdr))->data; + tcount++; + switch (event->what) { + case PROC_EVENT_EXIT: + Printf("Exit process %d (tgid %d) with code %d, signal %d\n", + event->event_data.exit.process_pid, + event->event_data.exit.process_tgid, + event->event_data.exit.exit_code, + event->event_data.exit.exit_signal); + break; + case PROC_EVENT_FORK: + Printf("Fork process %d (tgid %d), parent %d (tgid %d)\n", + event->event_data.fork.child_pid, + event->event_data.fork.child_tgid, + event->event_data.fork.parent_pid, + event->event_data.fork.parent_tgid); + break; + case PROC_EVENT_EXEC: + Printf("Exec process %d (tgid %d)\n", + event->event_data.exec.process_pid, + event->event_data.exec.process_tgid); + break; + case PROC_EVENT_UID: + Printf("UID process %d (tgid %d) uid %d euid %d\n", + event->event_data.id.process_pid, + event->event_data.id.process_tgid, + event->event_data.id.r.ruid, + event->event_data.id.e.euid); + break; + case PROC_EVENT_GID: + Printf("GID process %d (tgid %d) gid %d egid %d\n", + event->event_data.id.process_pid, + event->event_data.id.process_tgid, + event->event_data.id.r.rgid, + event->event_data.id.e.egid); + break; + case PROC_EVENT_SID: + Printf("SID process %d (tgid %d)\n", + event->event_data.sid.process_pid, + event->event_data.sid.process_tgid); + break; + case PROC_EVENT_PTRACE: + Printf("Ptrace process %d (tgid %d), Tracer %d (tgid %d)\n", + event->event_data.ptrace.process_pid, + event->event_data.ptrace.process_tgid, + event->event_data.ptrace.tracer_pid, + event->event_data.ptrace.tracer_tgid); + break; + case PROC_EVENT_COMM: + Printf("Comm process %d (tgid %d) comm %s\n", + event->event_data.comm.process_pid, + event->event_data.comm.process_tgid, + event->event_data.comm.comm); + break; + case PROC_EVENT_COREDUMP: + Printf("Coredump process %d (tgid %d) parent %d, (tgid %d)\n", + event->event_data.coredump.process_pid, + event->event_data.coredump.process_tgid, + event->event_data.coredump.parent_pid, + event->event_data.coredump.parent_tgid); + break; + default: + break; + } + } + return 0; +} + +int handle_events(int epoll_fd, struct proc_event *pev) +{ + char buff[CONNECTOR_MAX_MSG_SIZE]; + struct epoll_event ev[MAX_EVENTS]; + int i, event_count = 0, err = 0; + + event_count = epoll_wait(epoll_fd, ev, MAX_EVENTS, -1); + if (event_count < 0) { + ret_errno = errno; + if (ret_errno != EINTR) + perror("epoll_wait failed"); + return -3; + } + for (i = 0; i < event_count; i++) { + if (!(ev[i].events & EPOLLIN)) + continue; + if (recv(ev[i].data.fd, buff, sizeof(buff), 0) == -1) { + ret_errno = errno; + perror("recv failed"); + return -3; + } + err = handle_packet(buff, ev[i].data.fd, pev); + if (err < 0) + return err; + } + return 0; +} + +int main(int argc, char *argv[]) +{ + int epoll_fd, err; + struct proc_event proc_ev; + struct proc_input input; + + signal(SIGINT, sigint); + + if (argc > 2) { + printf("Expected 0(assume no-filter) or 1 argument(-f)\n"); + exit(KSFT_SKIP); + } + + if (argc == 2) { + if (strcmp(argv[1], "-f") == 0) { + filter = 1; + } else { + printf("Valid option : -f (for filter feature)\n"); + exit(KSFT_SKIP); + } + } + + if (filter) { + input.event_type = PROC_EVENT_NONZERO_EXIT; + input.mcast_op = PROC_CN_MCAST_LISTEN; + err = register_proc_netlink(&epoll_fd, (void*)&input); + } else { + enum proc_cn_mcast_op op = PROC_CN_MCAST_LISTEN; + err = register_proc_netlink(&epoll_fd, (void*)&op); + } + + if (err < 0) { + if (err == -2) + close(nl_sock); + if (err == -3) { + close(nl_sock); + close(epoll_fd); + } + exit(1); + } + + while (!interrupted) { + err = handle_events(epoll_fd, &proc_ev); + if (err < 0) { + if (ret_errno == EINTR) + continue; + if (err == -2) + close(nl_sock); + if (err == -3) { + close(nl_sock); + close(epoll_fd); + } + exit(1); + } + } + + if (filter) { + input.mcast_op = PROC_CN_MCAST_IGNORE; + send_message((void*)&input); + } else { + enum proc_cn_mcast_op op = PROC_CN_MCAST_IGNORE; + send_message((void*)&op); + } + + close(epoll_fd); + close(nl_sock); + + printf("Done total count: %d\n", tcount); + exit(0); +} diff --git a/tools/testing/selftests/damon/sysfs.sh b/tools/testing/selftests/damon/sysfs.sh index bcd4734ca094..60a9a305aef0 100644 --- a/tools/testing/selftests/damon/sysfs.sh +++ b/tools/testing/selftests/damon/sysfs.sh @@ -84,6 +84,7 @@ test_tried_regions() { tried_regions_dir=$1 ensure_dir "$tried_regions_dir" "exist" + ensure_file "$tried_regions_dir/total_bytes" "exist" "400" } test_stats() @@ -102,9 +103,14 @@ test_filter() ensure_file "$filter_dir/type" "exist" "600" ensure_write_succ "$filter_dir/type" "anon" "valid input" ensure_write_succ "$filter_dir/type" "memcg" "valid input" + ensure_write_succ "$filter_dir/type" "addr" "valid input" + ensure_write_succ "$filter_dir/type" "target" "valid input" ensure_write_fail "$filter_dir/type" "foo" "invalid input" ensure_file "$filter_dir/matching" "exist" "600" ensure_file "$filter_dir/memcg_path" "exist" "600" + ensure_file "$filter_dir/addr_start" "exist" "600" + ensure_file "$filter_dir/addr_end" "exist" "600" + ensure_file "$filter_dir/damon_target_idx" "exist" "600" } test_filters() diff --git a/tools/testing/selftests/drivers/net/bonding/Makefile b/tools/testing/selftests/drivers/net/bonding/Makefile index 03f92d7aeb19..8a72bb7de70f 100644 --- a/tools/testing/selftests/drivers/net/bonding/Makefile +++ b/tools/testing/selftests/drivers/net/bonding/Makefile @@ -9,10 +9,12 @@ TEST_PROGS := \ mode-1-recovery-updelay.sh \ mode-2-recovery-updelay.sh \ bond_options.sh \ - bond-eth-type-change.sh + bond-eth-type-change.sh \ + bond_macvlan.sh TEST_FILES := \ lag_lib.sh \ + bond_topo_2d1c.sh \ bond_topo_3d1c.sh \ net_forwarding_lib.sh diff --git a/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh b/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh index 71c00bfafbc9..4917dbb35a44 100755 --- a/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh @@ -11,7 +11,6 @@ finish() { ip netns delete server || true ip netns delete client || true - ip link del link1_1 || true } trap finish EXIT @@ -23,14 +22,12 @@ server_ip4=192.168.1.254 echo 180 >/proc/sys/kernel/panic # build namespaces -ip link add dev link1_1 type veth peer name link1_2 - ip netns add "server" -ip link set dev link1_2 netns server up name eth0 +ip netns add "client" +ip -n client link add eth0 type veth peer name eth0 netns server +ip netns exec server ip link set dev eth0 up ip netns exec server ip addr add ${server_ip4}/24 dev eth0 -ip netns add "client" -ip link set dev link1_1 netns client down name eth0 ip netns exec client ip link add dev bond0 down type bond mode 1 \ miimon 100 all_slaves_active 1 ip netns exec client ip link set dev eth0 down master bond0 diff --git a/tools/testing/selftests/drivers/net/bonding/bond-break-lacpdu-tx.sh b/tools/testing/selftests/drivers/net/bonding/bond-break-lacpdu-tx.sh index 47ab90596acb..6358df5752f9 100755 --- a/tools/testing/selftests/drivers/net/bonding/bond-break-lacpdu-tx.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond-break-lacpdu-tx.sh @@ -57,8 +57,8 @@ ip link add name veth2-bond type veth peer name veth2-end # add ports ip link set fbond master fab-br0 -ip link set veth1-bond down master fbond -ip link set veth2-bond down master fbond +ip link set veth1-bond master fbond +ip link set veth2-bond master fbond # bring up ip link set veth1-end up diff --git a/tools/testing/selftests/drivers/net/bonding/bond_macvlan.sh b/tools/testing/selftests/drivers/net/bonding/bond_macvlan.sh new file mode 100755 index 000000000000..b609fb6231f4 --- /dev/null +++ b/tools/testing/selftests/drivers/net/bonding/bond_macvlan.sh @@ -0,0 +1,99 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test macvlan over balance-alb + +lib_dir=$(dirname "$0") +source ${lib_dir}/bond_topo_2d1c.sh + +m1_ns="m1-$(mktemp -u XXXXXX)" +m2_ns="m1-$(mktemp -u XXXXXX)" +m1_ip4="192.0.2.11" +m1_ip6="2001:db8::11" +m2_ip4="192.0.2.12" +m2_ip6="2001:db8::12" + +cleanup() +{ + ip -n ${m1_ns} link del macv0 + ip netns del ${m1_ns} + ip -n ${m2_ns} link del macv0 + ip netns del ${m2_ns} + + client_destroy + server_destroy + gateway_destroy +} + +check_connection() +{ + local ns=${1} + local target=${2} + local message=${3:-"macvlan_over_bond"} + RET=0 + + + ip netns exec ${ns} ping ${target} -c 4 -i 0.1 &>/dev/null + check_err $? "ping failed" + log_test "$mode: $message" +} + +macvlan_over_bond() +{ + local param="$1" + RET=0 + + # setup new bond mode + bond_reset "${param}" + + ip -n ${s_ns} link add link bond0 name macv0 type macvlan mode bridge + ip -n ${s_ns} link set macv0 netns ${m1_ns} + ip -n ${m1_ns} link set dev macv0 up + ip -n ${m1_ns} addr add ${m1_ip4}/24 dev macv0 + ip -n ${m1_ns} addr add ${m1_ip6}/24 dev macv0 + + ip -n ${s_ns} link add link bond0 name macv0 type macvlan mode bridge + ip -n ${s_ns} link set macv0 netns ${m2_ns} + ip -n ${m2_ns} link set dev macv0 up + ip -n ${m2_ns} addr add ${m2_ip4}/24 dev macv0 + ip -n ${m2_ns} addr add ${m2_ip6}/24 dev macv0 + + sleep 2 + + check_connection "${c_ns}" "${s_ip4}" "IPv4: client->server" + check_connection "${c_ns}" "${s_ip6}" "IPv6: client->server" + check_connection "${c_ns}" "${m1_ip4}" "IPv4: client->macvlan_1" + check_connection "${c_ns}" "${m1_ip6}" "IPv6: client->macvlan_1" + check_connection "${c_ns}" "${m2_ip4}" "IPv4: client->macvlan_2" + check_connection "${c_ns}" "${m2_ip6}" "IPv6: client->macvlan_2" + check_connection "${m1_ns}" "${m2_ip4}" "IPv4: macvlan_1->macvlan_2" + check_connection "${m1_ns}" "${m2_ip6}" "IPv6: macvlan_1->macvlan_2" + + + sleep 5 + + check_connection "${s_ns}" "${c_ip4}" "IPv4: server->client" + check_connection "${s_ns}" "${c_ip6}" "IPv6: server->client" + check_connection "${m1_ns}" "${c_ip4}" "IPv4: macvlan_1->client" + check_connection "${m1_ns}" "${c_ip6}" "IPv6: macvlan_1->client" + check_connection "${m2_ns}" "${c_ip4}" "IPv4: macvlan_2->client" + check_connection "${m2_ns}" "${c_ip6}" "IPv6: macvlan_2->client" + check_connection "${m2_ns}" "${m1_ip4}" "IPv4: macvlan_2->macvlan_2" + check_connection "${m2_ns}" "${m1_ip6}" "IPv6: macvlan_2->macvlan_2" + + ip -n ${c_ns} neigh flush dev eth0 +} + +trap cleanup EXIT + +setup_prepare +ip netns add ${m1_ns} +ip netns add ${m2_ns} + +modes="active-backup balance-tlb balance-alb" + +for mode in $modes; do + macvlan_over_bond "mode $mode" +done + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/bonding/bond_options.sh b/tools/testing/selftests/drivers/net/bonding/bond_options.sh index 607ba5c38977..c54d1697f439 100755 --- a/tools/testing/selftests/drivers/net/bonding/bond_options.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond_options.sh @@ -9,10 +9,7 @@ ALL_TESTS=" num_grat_arp " -REQUIRE_MZ=no -NUM_NETIFS=0 lib_dir=$(dirname "$0") -source ${lib_dir}/net_forwarding_lib.sh source ${lib_dir}/bond_topo_3d1c.sh skip_prio() diff --git a/tools/testing/selftests/drivers/net/bonding/bond_topo_2d1c.sh b/tools/testing/selftests/drivers/net/bonding/bond_topo_2d1c.sh new file mode 100644 index 000000000000..a509ef949dcf --- /dev/null +++ b/tools/testing/selftests/drivers/net/bonding/bond_topo_2d1c.sh @@ -0,0 +1,158 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Topology for Bond mode 1,5,6 testing +# +# +-------------------------+ +# | bond0 | Server +# | + | 192.0.2.1/24 +# | eth0 | eth1 | 2001:db8::1/24 +# | +---+---+ | +# | | | | +# +-------------------------+ +# | | +# +-------------------------+ +# | | | | +# | +---+-------+---+ | Gateway +# | | br0 | | 192.0.2.254/24 +# | +-------+-------+ | 2001:db8::254/24 +# | | | +# +-------------------------+ +# | +# +-------------------------+ +# | | | Client +# | + | 192.0.2.10/24 +# | eth0 | 2001:db8::10/24 +# +-------------------------+ + +REQUIRE_MZ=no +NUM_NETIFS=0 +lib_dir=$(dirname "$0") +source ${lib_dir}/net_forwarding_lib.sh + +s_ns="s-$(mktemp -u XXXXXX)" +c_ns="c-$(mktemp -u XXXXXX)" +g_ns="g-$(mktemp -u XXXXXX)" +s_ip4="192.0.2.1" +c_ip4="192.0.2.10" +g_ip4="192.0.2.254" +s_ip6="2001:db8::1" +c_ip6="2001:db8::10" +g_ip6="2001:db8::254" + +gateway_create() +{ + ip netns add ${g_ns} + ip -n ${g_ns} link add br0 type bridge + ip -n ${g_ns} link set br0 up + ip -n ${g_ns} addr add ${g_ip4}/24 dev br0 + ip -n ${g_ns} addr add ${g_ip6}/24 dev br0 +} + +gateway_destroy() +{ + ip -n ${g_ns} link del br0 + ip netns del ${g_ns} +} + +server_create() +{ + ip netns add ${s_ns} + ip -n ${s_ns} link add bond0 type bond mode active-backup miimon 100 + + for i in $(seq 0 1); do + ip -n ${s_ns} link add eth${i} type veth peer name s${i} netns ${g_ns} + + ip -n ${g_ns} link set s${i} up + ip -n ${g_ns} link set s${i} master br0 + ip -n ${s_ns} link set eth${i} master bond0 + + tc -n ${g_ns} qdisc add dev s${i} clsact + done + + ip -n ${s_ns} link set bond0 up + ip -n ${s_ns} addr add ${s_ip4}/24 dev bond0 + ip -n ${s_ns} addr add ${s_ip6}/24 dev bond0 + sleep 2 +} + +# Reset bond with new mode and options +bond_reset() +{ + # Count the eth link number in real-time as this function + # maybe called from other topologies. + local link_num=$(ip -n ${s_ns} -br link show | grep -c "^eth") + local param="$1" + link_num=$((link_num -1)) + + ip -n ${s_ns} link set bond0 down + ip -n ${s_ns} link del bond0 + + ip -n ${s_ns} link add bond0 type bond $param + for i in $(seq 0 ${link_num}); do + ip -n ${s_ns} link set eth$i master bond0 + done + + ip -n ${s_ns} link set bond0 up + ip -n ${s_ns} addr add ${s_ip4}/24 dev bond0 + ip -n ${s_ns} addr add ${s_ip6}/24 dev bond0 + sleep 2 +} + +server_destroy() +{ + # Count the eth link number in real-time as this function + # maybe called from other topologies. + local link_num=$(ip -n ${s_ns} -br link show | grep -c "^eth") + link_num=$((link_num -1)) + for i in $(seq 0 ${link_num}); do + ip -n ${s_ns} link del eth${i} + done + ip netns del ${s_ns} +} + +client_create() +{ + ip netns add ${c_ns} + ip -n ${c_ns} link add eth0 type veth peer name c0 netns ${g_ns} + + ip -n ${g_ns} link set c0 up + ip -n ${g_ns} link set c0 master br0 + + ip -n ${c_ns} link set eth0 up + ip -n ${c_ns} addr add ${c_ip4}/24 dev eth0 + ip -n ${c_ns} addr add ${c_ip6}/24 dev eth0 +} + +client_destroy() +{ + ip -n ${c_ns} link del eth0 + ip netns del ${c_ns} +} + +setup_prepare() +{ + gateway_create + server_create + client_create +} + +cleanup() +{ + pre_cleanup + + client_destroy + server_destroy + gateway_destroy +} + +bond_check_connection() +{ + local msg=${1:-"check connection"} + + sleep 2 + ip netns exec ${s_ns} ping ${c_ip4} -c5 -i 0.1 &>/dev/null + check_err $? "${msg}: ping failed" + ip netns exec ${s_ns} ping6 ${c_ip6} -c5 -i 0.1 &>/dev/null + check_err $? "${msg}: ping6 failed" +} diff --git a/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh b/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh index 69ab99a56043..3a1333d9a85b 100644 --- a/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh @@ -25,121 +25,19 @@ # | eth0 | 2001:db8::10/24 # +-------------------------------------+ -s_ns="s-$(mktemp -u XXXXXX)" -c_ns="c-$(mktemp -u XXXXXX)" -g_ns="g-$(mktemp -u XXXXXX)" -s_ip4="192.0.2.1" -c_ip4="192.0.2.10" -g_ip4="192.0.2.254" -s_ip6="2001:db8::1" -c_ip6="2001:db8::10" -g_ip6="2001:db8::254" - -gateway_create() -{ - ip netns add ${g_ns} - ip -n ${g_ns} link add br0 type bridge - ip -n ${g_ns} link set br0 up - ip -n ${g_ns} addr add ${g_ip4}/24 dev br0 - ip -n ${g_ns} addr add ${g_ip6}/24 dev br0 -} - -gateway_destroy() -{ - ip -n ${g_ns} link del br0 - ip netns del ${g_ns} -} - -server_create() -{ - ip netns add ${s_ns} - ip -n ${s_ns} link add bond0 type bond mode active-backup miimon 100 - - for i in $(seq 0 2); do - ip -n ${s_ns} link add eth${i} type veth peer name s${i} netns ${g_ns} - - ip -n ${g_ns} link set s${i} up - ip -n ${g_ns} link set s${i} master br0 - ip -n ${s_ns} link set eth${i} master bond0 - - tc -n ${g_ns} qdisc add dev s${i} clsact - done - - ip -n ${s_ns} link set bond0 up - ip -n ${s_ns} addr add ${s_ip4}/24 dev bond0 - ip -n ${s_ns} addr add ${s_ip6}/24 dev bond0 - sleep 2 -} - -# Reset bond with new mode and options -bond_reset() -{ - local param="$1" - - ip -n ${s_ns} link set bond0 down - ip -n ${s_ns} link del bond0 - - ip -n ${s_ns} link add bond0 type bond $param - for i in $(seq 0 2); do - ip -n ${s_ns} link set eth$i master bond0 - done - - ip -n ${s_ns} link set bond0 up - ip -n ${s_ns} addr add ${s_ip4}/24 dev bond0 - ip -n ${s_ns} addr add ${s_ip6}/24 dev bond0 - sleep 2 -} - -server_destroy() -{ - for i in $(seq 0 2); do - ip -n ${s_ns} link del eth${i} - done - ip netns del ${s_ns} -} - -client_create() -{ - ip netns add ${c_ns} - ip -n ${c_ns} link add eth0 type veth peer name c0 netns ${g_ns} - - ip -n ${g_ns} link set c0 up - ip -n ${g_ns} link set c0 master br0 - - ip -n ${c_ns} link set eth0 up - ip -n ${c_ns} addr add ${c_ip4}/24 dev eth0 - ip -n ${c_ns} addr add ${c_ip6}/24 dev eth0 -} - -client_destroy() -{ - ip -n ${c_ns} link del eth0 - ip netns del ${c_ns} -} +source bond_topo_2d1c.sh setup_prepare() { gateway_create server_create client_create -} - -cleanup() -{ - pre_cleanup - - client_destroy - server_destroy - gateway_destroy -} - -bond_check_connection() -{ - local msg=${1:-"check connection"} - sleep 2 - ip netns exec ${s_ns} ping ${c_ip4} -c5 -i 0.1 &>/dev/null - check_err $? "${msg}: ping failed" - ip netns exec ${s_ns} ping6 ${c_ip6} -c5 -i 0.1 &>/dev/null - check_err $? "${msg}: ping6 failed" + # Add the extra device as we use 3 down links for bond0 + local i=2 + ip -n ${s_ns} link add eth${i} type veth peer name s${i} netns ${g_ns} + ip -n ${g_ns} link set s${i} up + ip -n ${g_ns} link set s${i} master br0 + ip -n ${s_ns} link set eth${i} master bond0 + tc -n ${g_ns} qdisc add dev s${i} clsact } diff --git a/tools/testing/selftests/drivers/net/mlxsw/port_range_occ.sh b/tools/testing/selftests/drivers/net/mlxsw/port_range_occ.sh new file mode 100755 index 000000000000..b1f0781f6b25 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/port_range_occ.sh @@ -0,0 +1,111 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test that filters that match on the same port range, but with different +# combination of IPv4/IPv6 and TCP/UDP all use the same port range register by +# observing port range registers' occupancy via devlink-resource. + +lib_dir=$(dirname $0)/../../../net/forwarding + +ALL_TESTS=" + port_range_occ_test +" +NUM_NETIFS=2 +source $lib_dir/lib.sh +source $lib_dir/devlink_lib.sh + +h1_create() +{ + simple_if_init $h1 +} + +h1_destroy() +{ + simple_if_fini $h1 +} + +switch_create() +{ + simple_if_init $swp1 + tc qdisc add dev $swp1 clsact +} + +switch_destroy() +{ + tc qdisc del dev $swp1 clsact + simple_if_fini $swp1 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + vrf_prepare + + h1_create + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + h1_destroy + + vrf_cleanup +} + +port_range_occ_get() +{ + devlink_resource_occ_get port_range_registers +} + +port_range_occ_test() +{ + RET=0 + + local occ=$(port_range_occ_get) + + # Two port range registers are used, for source and destination port + # ranges. + tc filter add dev $swp1 ingress pref 1 handle 101 proto ip \ + flower skip_sw ip_proto udp src_port 1-100 dst_port 1-100 \ + action pass + (( occ + 2 == $(port_range_occ_get) )) + check_err $? "Got occupancy $(port_range_occ_get), expected $((occ + 2))" + + tc filter add dev $swp1 ingress pref 1 handle 102 proto ip \ + flower skip_sw ip_proto tcp src_port 1-100 dst_port 1-100 \ + action pass + tc filter add dev $swp1 ingress pref 2 handle 103 proto ipv6 \ + flower skip_sw ip_proto udp src_port 1-100 dst_port 1-100 \ + action pass + tc filter add dev $swp1 ingress pref 2 handle 104 proto ipv6 \ + flower skip_sw ip_proto tcp src_port 1-100 dst_port 1-100 \ + action pass + (( occ + 2 == $(port_range_occ_get) )) + check_err $? "Got occupancy $(port_range_occ_get), expected $((occ + 2))" + + tc filter del dev $swp1 ingress pref 2 handle 104 flower + tc filter del dev $swp1 ingress pref 2 handle 103 flower + tc filter del dev $swp1 ingress pref 1 handle 102 flower + (( occ + 2 == $(port_range_occ_get) )) + check_err $? "Got occupancy $(port_range_occ_get), expected $((occ + 2))" + + tc filter del dev $swp1 ingress pref 1 handle 101 flower + (( occ == $(port_range_occ_get) )) + check_err $? "Got occupancy $(port_range_occ_get), expected $occ" + + log_test "port range occupancy" +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/mlxsw/port_range_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/port_range_scale.sh new file mode 100644 index 000000000000..2a70840ff14b --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/port_range_scale.sh @@ -0,0 +1,95 @@ +# SPDX-License-Identifier: GPL-2.0 + +PORT_RANGE_NUM_NETIFS=2 + +port_range_h1_create() +{ + simple_if_init $h1 +} + +port_range_h1_destroy() +{ + simple_if_fini $h1 +} + +port_range_switch_create() +{ + simple_if_init $swp1 + tc qdisc add dev $swp1 clsact +} + +port_range_switch_destroy() +{ + tc qdisc del dev $swp1 clsact + simple_if_fini $swp1 +} + +port_range_rules_create() +{ + local count=$1; shift + local should_fail=$1; shift + local batch_file="$(mktemp)" + + for ((i = 0; i < count; ++i)); do + cat >> $batch_file <<-EOF + filter add dev $swp1 ingress \ + prot ipv4 \ + pref 1000 \ + flower skip_sw \ + ip_proto udp dst_port 1-$((100 + i)) \ + action pass + EOF + done + + tc -b $batch_file + check_err_fail $should_fail $? "Rule insertion" + + rm -f $batch_file +} + +__port_range_test() +{ + local count=$1; shift + local should_fail=$1; shift + + port_range_rules_create $count $should_fail + + offload_count=$(tc -j filter show dev $swp1 ingress | + jq "[.[] | select(.options.in_hw == true)] | length") + ((offload_count == count)) + check_err_fail $should_fail $? "port range offload count" +} + +port_range_test() +{ + local count=$1; shift + local should_fail=$1; shift + + if ! tc_offload_check $PORT_RANGE_NUM_NETIFS; then + check_err 1 "Could not test offloaded functionality" + return + fi + + __port_range_test $count $should_fail +} + +port_range_setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + vrf_prepare + + port_range_h1_create + port_range_switch_create +} + +port_range_cleanup() +{ + pre_cleanup + + port_range_switch_destroy + port_range_h1_destroy + + vrf_cleanup +} diff --git a/tools/testing/selftests/drivers/net/mlxsw/rif_bridge.sh b/tools/testing/selftests/drivers/net/mlxsw/rif_bridge.sh new file mode 100755 index 000000000000..b79542a4dcc7 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/rif_bridge.sh @@ -0,0 +1,183 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +lib_dir=$(dirname $0)/../../../net/forwarding + +ALL_TESTS=" + bridge_rif_add + bridge_rif_nomaster + bridge_rif_remaster + bridge_rif_nomaster_addr + bridge_rif_nomaster_port + bridge_rif_remaster_port +" + +NUM_NETIFS=2 +source $lib_dir/lib.sh +source $lib_dir/devlink_lib.sh + +setup_prepare() +{ + swp1=${NETIFS[p1]} + swp2=${NETIFS[p2]} + + team_create lag1 lacp + ip link set dev lag1 addrgenmode none + ip link set dev lag1 address $(mac_get $swp1) + + team_create lag2 lacp + ip link set dev lag2 addrgenmode none + ip link set dev lag2 address $(mac_get $swp2) + + ip link add name br1 type bridge vlan_filtering 1 + ip link set dev br1 addrgenmode none + ip link set dev br1 address $(mac_get lag1) + ip link set dev br1 up + + ip link set dev lag1 master br1 + + ip link set dev $swp1 master lag1 + ip link set dev $swp1 up + + ip link set dev $swp2 master lag2 + ip link set dev $swp2 up +} + +cleanup() +{ + pre_cleanup + + ip link set dev $swp2 nomaster + ip link set dev $swp2 down + + ip link set dev $swp1 nomaster + ip link set dev $swp1 down + + ip link del dev lag2 + ip link set dev lag1 nomaster + ip link del dev lag1 + + ip link del dev br1 +} + +bridge_rif_add() +{ + RET=0 + + local rifs_occ_t0=$(devlink_resource_occ_get rifs) + __addr_add_del br1 add 192.0.2.2/28 + sleep 1 + local rifs_occ_t1=$(devlink_resource_occ_get rifs) + local expected_rifs=$((rifs_occ_t0 + 1)) + + ((expected_rifs == rifs_occ_t1)) + check_err $? "Expected $expected_rifs RIFs, $rifs_occ_t1 are used" + + log_test "Add RIF for bridge on address addition" +} + +bridge_rif_nomaster() +{ + RET=0 + + local rifs_occ_t0=$(devlink_resource_occ_get rifs) + ip link set dev lag1 nomaster + sleep 1 + local rifs_occ_t1=$(devlink_resource_occ_get rifs) + local expected_rifs=$((rifs_occ_t0 - 1)) + + ((expected_rifs == rifs_occ_t1)) + check_err $? "Expected $expected_rifs RIFs, $rifs_occ_t1 are used" + + log_test "Drop RIF for bridge on LAG deslavement" +} + +bridge_rif_remaster() +{ + RET=0 + + local rifs_occ_t0=$(devlink_resource_occ_get rifs) + ip link set dev lag1 master br1 + sleep 1 + local rifs_occ_t1=$(devlink_resource_occ_get rifs) + local expected_rifs=$((rifs_occ_t0 + 1)) + + ((expected_rifs == rifs_occ_t1)) + check_err $? "Expected $expected_rifs RIFs, $rifs_occ_t1 are used" + + log_test "Add RIF for bridge on LAG reenslavement" +} + +bridge_rif_nomaster_addr() +{ + local rifs_occ_t0=$(devlink_resource_occ_get rifs) + + # Adding an address while the LAG is enslaved shouldn't generate a RIF. + __addr_add_del lag1 add 192.0.2.65/28 + sleep 1 + local rifs_occ_t1=$(devlink_resource_occ_get rifs) + local expected_rifs=$((rifs_occ_t0)) + + ((expected_rifs == rifs_occ_t1)) + check_err $? "After adding IP: Expected $expected_rifs RIFs, $rifs_occ_t1 are used" + + # Removing the LAG from the bridge should drop RIF for the bridge (as + # tested in bridge_rif_lag_nomaster), but since the LAG now has an + # address, it should gain a RIF. + ip link set dev lag1 nomaster + sleep 1 + local rifs_occ_t2=$(devlink_resource_occ_get rifs) + local expected_rifs=$((rifs_occ_t0)) + + ((expected_rifs == rifs_occ_t2)) + check_err $? "After deslaving: Expected $expected_rifs RIFs, $rifs_occ_t2 are used" + + log_test "Add RIF for LAG on deslavement from bridge" + + __addr_add_del lag1 del 192.0.2.65/28 + ip link set dev lag1 master br1 + sleep 1 +} + +bridge_rif_nomaster_port() +{ + RET=0 + + local rifs_occ_t0=$(devlink_resource_occ_get rifs) + ip link set dev $swp1 nomaster + sleep 1 + local rifs_occ_t1=$(devlink_resource_occ_get rifs) + local expected_rifs=$((rifs_occ_t0 - 1)) + + ((expected_rifs == rifs_occ_t1)) + check_err $? "Expected $expected_rifs RIFs, $rifs_occ_t1 are used" + + log_test "Drop RIF for bridge on deslavement of port from LAG" +} + +bridge_rif_remaster_port() +{ + RET=0 + + local rifs_occ_t0=$(devlink_resource_occ_get rifs) + ip link set dev $swp1 down + ip link set dev $swp1 master lag1 + ip link set dev $swp1 up + setup_wait_dev $swp1 + local rifs_occ_t1=$(devlink_resource_occ_get rifs) + local expected_rifs=$((rifs_occ_t0 + 1)) + + ((expected_rifs == rifs_occ_t1)) + check_err $? "Expected $expected_rifs RIFs, $rifs_occ_t1 are used" + + log_test "Add RIF for bridge on reenslavement of port to LAG" +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/mlxsw/rif_lag.sh b/tools/testing/selftests/drivers/net/mlxsw/rif_lag.sh new file mode 100755 index 000000000000..e28f978104f3 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/rif_lag.sh @@ -0,0 +1,136 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +lib_dir=$(dirname $0)/../../../net/forwarding + +ALL_TESTS=" + lag_rif_add + lag_rif_nomaster + lag_rif_remaster + lag_rif_nomaster_addr +" + +NUM_NETIFS=2 +source $lib_dir/lib.sh +source $lib_dir/devlink_lib.sh + +setup_prepare() +{ + swp1=${NETIFS[p1]} + swp2=${NETIFS[p2]} + + team_create lag1 lacp + ip link set dev lag1 addrgenmode none + ip link set dev lag1 address $(mac_get $swp1) + + team_create lag2 lacp + ip link set dev lag2 addrgenmode none + ip link set dev lag2 address $(mac_get $swp2) + + ip link set dev $swp1 master lag1 + ip link set dev $swp1 up + + ip link set dev $swp2 master lag2 + ip link set dev $swp2 up +} + +cleanup() +{ + pre_cleanup + + ip link set dev $swp2 nomaster + ip link set dev $swp2 down + + ip link set dev $swp1 nomaster + ip link set dev $swp1 down + + ip link del dev lag2 + ip link del dev lag1 +} + +lag_rif_add() +{ + RET=0 + + local rifs_occ_t0=$(devlink_resource_occ_get rifs) + __addr_add_del lag1 add 192.0.2.2/28 + sleep 1 + local rifs_occ_t1=$(devlink_resource_occ_get rifs) + local expected_rifs=$((rifs_occ_t0 + 1)) + + ((expected_rifs == rifs_occ_t1)) + check_err $? "Expected $expected_rifs RIFs, $rifs_occ_t1 are used" + + log_test "Add RIF for LAG on address addition" +} + +lag_rif_nomaster() +{ + RET=0 + + local rifs_occ_t0=$(devlink_resource_occ_get rifs) + ip link set dev $swp1 nomaster + sleep 1 + local rifs_occ_t1=$(devlink_resource_occ_get rifs) + local expected_rifs=$((rifs_occ_t0 - 1)) + + ((expected_rifs == rifs_occ_t1)) + check_err $? "Expected $expected_rifs RIFs, $rifs_occ_t1 are used" + + log_test "Drop RIF for LAG on port deslavement" +} + +lag_rif_remaster() +{ + RET=0 + + local rifs_occ_t0=$(devlink_resource_occ_get rifs) + ip link set dev $swp1 down + ip link set dev $swp1 master lag1 + ip link set dev $swp1 up + setup_wait_dev $swp1 + local rifs_occ_t1=$(devlink_resource_occ_get rifs) + local expected_rifs=$((rifs_occ_t0 + 1)) + + ((expected_rifs == rifs_occ_t1)) + check_err $? "Expected $expected_rifs RIFs, $rifs_occ_t1 are used" + + log_test "Add RIF for LAG on port reenslavement" +} + +lag_rif_nomaster_addr() +{ + local rifs_occ_t0=$(devlink_resource_occ_get rifs) + + # Adding an address while the port is LAG'd shouldn't generate a RIF. + __addr_add_del $swp1 add 192.0.2.65/28 + sleep 1 + local rifs_occ_t1=$(devlink_resource_occ_get rifs) + local expected_rifs=$((rifs_occ_t0)) + + ((expected_rifs == rifs_occ_t1)) + check_err $? "After adding IP: Expected $expected_rifs RIFs, $rifs_occ_t1 are used" + + # Removing the port from LAG should drop RIF for the LAG (as tested in + # lag_rif_nomaster), but since the port now has an address, it should + # gain a RIF. + ip link set dev $swp1 nomaster + sleep 1 + local rifs_occ_t2=$(devlink_resource_occ_get rifs) + local expected_rifs=$((rifs_occ_t0)) + + ((expected_rifs == rifs_occ_t2)) + check_err $? "After deslaving: Expected $expected_rifs RIFs, $rifs_occ_t2 are used" + + __addr_add_del $swp1 del 192.0.2.65/28 + log_test "Add RIF for port on deslavement from LAG" +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/mlxsw/rif_lag_vlan.sh b/tools/testing/selftests/drivers/net/mlxsw/rif_lag_vlan.sh new file mode 100755 index 000000000000..6318cfa6434c --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/rif_lag_vlan.sh @@ -0,0 +1,146 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +lib_dir=$(dirname $0)/../../../net/forwarding + +ALL_TESTS=" + lag_rif_add + lag_rif_nomaster + lag_rif_remaster + lag_rif_nomaster_addr +" + +NUM_NETIFS=2 +source $lib_dir/lib.sh +source $lib_dir/devlink_lib.sh + +setup_prepare() +{ + swp1=${NETIFS[p1]} + swp2=${NETIFS[p2]} + + team_create lag1 lacp + ip link set dev lag1 addrgenmode none + ip link set dev lag1 address $(mac_get $swp1) + + team_create lag2 lacp + ip link set dev lag2 addrgenmode none + ip link set dev lag2 address $(mac_get $swp2) + + ip link set dev $swp1 master lag1 + ip link set dev $swp1 up + + ip link set dev $swp2 master lag2 + ip link set dev $swp2 up + + vlan_create lag1 100 + ip link set dev lag1.100 addrgenmode none + + vlan_create lag1 200 + ip link set dev lag1.200 addrgenmode none +} + +cleanup() +{ + pre_cleanup + + ip link del dev lag1.200 + ip link del dev lag1.100 + + ip link set dev $swp2 nomaster + ip link set dev $swp2 down + + ip link set dev $swp1 nomaster + ip link set dev $swp1 down + + ip link del dev lag2 + ip link del dev lag1 +} + +lag_rif_add() +{ + RET=0 + + local rifs_occ_t0=$(devlink_resource_occ_get rifs) + __addr_add_del lag1.100 add 192.0.2.2/28 + __addr_add_del lag1.200 add 192.0.2.18/28 + sleep 1 + local rifs_occ_t1=$(devlink_resource_occ_get rifs) + local expected_rifs=$((rifs_occ_t0 + 2)) + + ((expected_rifs == rifs_occ_t1)) + check_err $? "Expected $expected_rifs RIFs, $rifs_occ_t1 are used" + + log_test "Add RIFs for LAG VLANs on address addition" +} + +lag_rif_nomaster() +{ + RET=0 + + local rifs_occ_t0=$(devlink_resource_occ_get rifs) + ip link set dev $swp1 nomaster + sleep 1 + local rifs_occ_t1=$(devlink_resource_occ_get rifs) + local expected_rifs=$((rifs_occ_t0 - 2)) + + ((expected_rifs == rifs_occ_t1)) + check_err $? "Expected $expected_rifs RIFs, $rifs_occ_t1 are used" + + log_test "Drop RIFs for LAG VLANs on port deslavement" +} + +lag_rif_remaster() +{ + RET=0 + + local rifs_occ_t0=$(devlink_resource_occ_get rifs) + ip link set dev $swp1 down + ip link set dev $swp1 master lag1 + ip link set dev $swp1 up + setup_wait_dev $swp1 + local rifs_occ_t1=$(devlink_resource_occ_get rifs) + local expected_rifs=$((rifs_occ_t0 + 2)) + + ((expected_rifs == rifs_occ_t1)) + check_err $? "Expected $expected_rifs RIFs, $rifs_occ_t1 are used" + + log_test "Add RIFs for LAG VLANs on port reenslavement" +} + +lag_rif_nomaster_addr() +{ + local rifs_occ_t0=$(devlink_resource_occ_get rifs) + + # Adding an address while the port is LAG'd shouldn't generate a RIF. + __addr_add_del $swp1 add 192.0.2.65/28 + sleep 1 + local rifs_occ_t1=$(devlink_resource_occ_get rifs) + local expected_rifs=$((rifs_occ_t0)) + + ((expected_rifs == rifs_occ_t1)) + check_err $? "After adding IP: Expected $expected_rifs RIFs, $rifs_occ_t1 are used" + + # Removing the port from LAG should drop two RIFs for the LAG VLANs (as + # tested in lag_rif_nomaster), but since the port now has an address, it + # should gain a RIF. + ip link set dev $swp1 nomaster + sleep 1 + local rifs_occ_t2=$(devlink_resource_occ_get rifs) + local expected_rifs=$((rifs_occ_t0 - 1)) + + ((expected_rifs == rifs_occ_t2)) + check_err $? "After deslaving: Expected $expected_rifs RIFs, $rifs_occ_t2 are used" + + __addr_add_del $swp1 del 192.0.2.65/28 + log_test "Add RIF for port on deslavement from LAG" +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/mlxsw/router_bridge_lag.sh b/tools/testing/selftests/drivers/net/mlxsw/router_bridge_lag.sh new file mode 100755 index 000000000000..6ce317cfaf9b --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/router_bridge_lag.sh @@ -0,0 +1,50 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test enslavement to LAG with a clean slate. +# See $lib_dir/router_bridge_lag.sh for further details. + +ALL_TESTS=" + config_devlink_reload + config_enslave_h1 + config_enslave_h2 + config_enslave_h3 + config_enslave_h4 + config_enslave_swp1 + config_enslave_swp2 + config_enslave_swp3 + config_enslave_swp4 + config_wait + ping_ipv4 + ping_ipv6 +" + +config_devlink_reload() +{ + log_info "Devlink reload" + devlink_reload +} + +config_enslave_h1() +{ + config_enslave $h1 lag1 +} + +config_enslave_h2() +{ + config_enslave $h2 lag4 +} + +config_enslave_h3() +{ + config_enslave $h3 lag4 +} + +config_enslave_h4() +{ + config_enslave $h4 lag1 +} + +lib_dir=$(dirname $0)/../../../net/forwarding +EXTRA_SOURCE="source $lib_dir/devlink_lib.sh" +source $lib_dir/router_bridge_lag.sh diff --git a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh index 5e89657857c7..893a693ad805 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh @@ -16,7 +16,6 @@ ALL_TESTS=" bridge_deletion_test bridge_vlan_flags_test vlan_1_test - lag_bridge_upper_test duplicate_vlans_test vlan_rif_refcount_test subport_rif_refcount_test @@ -211,33 +210,6 @@ vlan_1_test() ip link del dev $swp1.1 } -lag_bridge_upper_test() -{ - # Test that ports cannot be enslaved to LAG devices that have uppers - # and that failure is handled gracefully. See commit b3529af6bb0d - # ("spectrum: Reference count VLAN entries") for more details - RET=0 - - ip link add name bond1 type bond mode 802.3ad - - ip link add name br0 type bridge vlan_filtering 1 - ip link set dev bond1 master br0 - - ip link set dev $swp1 down - ip link set dev $swp1 master bond1 &> /dev/null - check_fail $? "managed to enslave port to lag when should not" - - # This might generate a trace, if we did not handle the failure - # correctly - ip -6 address add 2001:db8:1::1/64 dev $swp1 - ip -6 address del 2001:db8:1::1/64 dev $swp1 - - log_test "lag with bridge upper" - - ip link del dev br0 - ip link del dev bond1 -} - duplicate_vlans_test() { # Test that on a given port a VLAN is only used once. Either as VLAN @@ -510,9 +482,6 @@ vlan_interface_uppers_test() ip link set dev $swp1 master br0 ip link add link br0 name br0.10 type vlan id 10 - ip link add link br0.10 name macvlan0 \ - type macvlan mode private &> /dev/null - check_fail $? "managed to create a macvlan when should not" ip -6 address add 2001:db8:1::1/64 dev br0.10 ip link add link br0.10 name macvlan0 type macvlan mode private diff --git a/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh b/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh index 7d9e73a43a49..0c47faff9274 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh @@ -98,12 +98,12 @@ sb_occ_etc_check() port_pool_test() { - local exp_max_occ=288 + local exp_max_occ=$(devlink_cell_size_get) local max_occ devlink sb occupancy clearmax $DEVLINK_DEV - $MZ $h1 -c 1 -p 160 -a $h1mac -b $h2mac -A 192.0.1.1 -B 192.0.1.2 \ + $MZ $h1 -c 1 -p 10 -a $h1mac -b $h2mac -A 192.0.1.1 -B 192.0.1.2 \ -t ip -q devlink sb occupancy snapshot $DEVLINK_DEV @@ -126,12 +126,12 @@ port_pool_test() port_tc_ip_test() { - local exp_max_occ=288 + local exp_max_occ=$(devlink_cell_size_get) local max_occ devlink sb occupancy clearmax $DEVLINK_DEV - $MZ $h1 -c 1 -p 160 -a $h1mac -b $h2mac -A 192.0.1.1 -B 192.0.1.2 \ + $MZ $h1 -c 1 -p 10 -a $h1mac -b $h2mac -A 192.0.1.1 -B 192.0.1.2 \ -t ip -q devlink sb occupancy snapshot $DEVLINK_DEV @@ -154,16 +154,12 @@ port_tc_ip_test() port_tc_arp_test() { - local exp_max_occ=96 + local exp_max_occ=$(devlink_cell_size_get) local max_occ - if [[ $MLXSW_CHIP != "mlxsw_spectrum" ]]; then - exp_max_occ=144 - fi - devlink sb occupancy clearmax $DEVLINK_DEV - $MZ $h1 -c 1 -p 160 -a $h1mac -A 192.0.1.1 -t arp -q + $MZ $h1 -c 1 -p 10 -a $h1mac -A 192.0.1.1 -t arp -q devlink sb occupancy snapshot $DEVLINK_DEV diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/port_range_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/port_range_scale.sh new file mode 120000 index 000000000000..bd670d9dc4e5 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/port_range_scale.sh @@ -0,0 +1 @@ +../spectrum/port_range_scale.sh
\ No newline at end of file diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh index 688338bbeb97..a88d8a8c85f2 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh @@ -33,6 +33,7 @@ ALL_TESTS=" port rif_mac_profile rif_counter + port_range " for current_test in ${TESTS:-$ALL_TESTS}; do diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/port_range_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/port_range_scale.sh new file mode 100644 index 000000000000..d0847e8ea270 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/port_range_scale.sh @@ -0,0 +1,16 @@ +# SPDX-License-Identifier: GPL-2.0 +source ../port_range_scale.sh + +port_range_get_target() +{ + local should_fail=$1; shift + local target + + target=$(devlink_resource_size_get port_range_registers) + + if ((! should_fail)); then + echo $target + else + echo $((target + 1)) + fi +} diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh index 95d9f710a630..f981c957f097 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh @@ -30,6 +30,7 @@ ALL_TESTS=" port rif_mac_profile rif_counter + port_range " for current_test in ${TESTS:-$ALL_TESTS}; do diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/.gitignore b/tools/testing/selftests/fchmodat2/.gitignore index d65462d64816..82a4846cbc4b 100644 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/.gitignore +++ b/tools/testing/selftests/fchmodat2/.gitignore @@ -1,2 +1,2 @@ # SPDX-License-Identifier: GPL-2.0-only -*.out +/*_test diff --git a/tools/testing/selftests/fchmodat2/Makefile b/tools/testing/selftests/fchmodat2/Makefile new file mode 100644 index 000000000000..20839f8e43f2 --- /dev/null +++ b/tools/testing/selftests/fchmodat2/Makefile @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0-or-later + +CFLAGS += -Wall -O2 -g -fsanitize=address -fsanitize=undefined $(KHDR_INCLUDES) +TEST_GEN_PROGS := fchmodat2_test + +include ../lib.mk diff --git a/tools/testing/selftests/fchmodat2/fchmodat2_test.c b/tools/testing/selftests/fchmodat2/fchmodat2_test.c new file mode 100644 index 000000000000..e0319417124d --- /dev/null +++ b/tools/testing/selftests/fchmodat2/fchmodat2_test.c @@ -0,0 +1,142 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#define _GNU_SOURCE +#include <fcntl.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <syscall.h> +#include <unistd.h> + +#include "../kselftest.h" + +int sys_fchmodat2(int dfd, const char *filename, mode_t mode, int flags) +{ + int ret = syscall(__NR_fchmodat2, dfd, filename, mode, flags); + + return ret >= 0 ? ret : -errno; +} + +int setup_testdir(void) +{ + int dfd, ret; + char dirname[] = "/tmp/ksft-fchmodat2.XXXXXX"; + + /* Make the top-level directory. */ + if (!mkdtemp(dirname)) + ksft_exit_fail_msg("%s: failed to create tmpdir\n", __func__); + + dfd = open(dirname, O_PATH | O_DIRECTORY); + if (dfd < 0) + ksft_exit_fail_msg("%s: failed to open tmpdir\n", __func__); + + ret = openat(dfd, "regfile", O_CREAT | O_WRONLY | O_TRUNC, 0644); + if (ret < 0) + ksft_exit_fail_msg("%s: failed to create file in tmpdir\n", + __func__); + close(ret); + + ret = symlinkat("regfile", dfd, "symlink"); + if (ret < 0) + ksft_exit_fail_msg("%s: failed to create symlink in tmpdir\n", + __func__); + + return dfd; +} + +int expect_mode(int dfd, const char *filename, mode_t expect_mode) +{ + struct stat st; + int ret = fstatat(dfd, filename, &st, AT_SYMLINK_NOFOLLOW); + + if (ret) + ksft_exit_fail_msg("%s: %s: fstatat failed\n", + __func__, filename); + + return (st.st_mode == expect_mode); +} + +void test_regfile(void) +{ + int dfd, ret; + + dfd = setup_testdir(); + + ret = sys_fchmodat2(dfd, "regfile", 0640, 0); + + if (ret < 0) + ksft_exit_fail_msg("%s: fchmodat2(noflag) failed\n", __func__); + + if (!expect_mode(dfd, "regfile", 0100640)) + ksft_exit_fail_msg("%s: wrong file mode bits after fchmodat2\n", + __func__); + + ret = sys_fchmodat2(dfd, "regfile", 0600, AT_SYMLINK_NOFOLLOW); + + if (ret < 0) + ksft_exit_fail_msg("%s: fchmodat2(AT_SYMLINK_NOFOLLOW) failed\n", + __func__); + + if (!expect_mode(dfd, "regfile", 0100600)) + ksft_exit_fail_msg("%s: wrong file mode bits after fchmodat2 with nofollow\n", + __func__); + + ksft_test_result_pass("fchmodat2(regfile)\n"); +} + +void test_symlink(void) +{ + int dfd, ret; + + dfd = setup_testdir(); + + ret = sys_fchmodat2(dfd, "symlink", 0640, 0); + + if (ret < 0) + ksft_exit_fail_msg("%s: fchmodat2(noflag) failed\n", __func__); + + if (!expect_mode(dfd, "regfile", 0100640)) + ksft_exit_fail_msg("%s: wrong file mode bits after fchmodat2\n", + __func__); + + if (!expect_mode(dfd, "symlink", 0120777)) + ksft_exit_fail_msg("%s: wrong symlink mode bits after fchmodat2\n", + __func__); + + ret = sys_fchmodat2(dfd, "symlink", 0600, AT_SYMLINK_NOFOLLOW); + + /* + * On certain filesystems (xfs or btrfs), chmod operation fails. So we + * first check the symlink target but if the operation fails we mark the + * test as skipped. + * + * https://sourceware.org/legacy-ml/libc-alpha/2020-02/msg00467.html + */ + if (ret == 0 && !expect_mode(dfd, "symlink", 0120600)) + ksft_exit_fail_msg("%s: wrong symlink mode bits after fchmodat2 with nofollow\n", + __func__); + + if (!expect_mode(dfd, "regfile", 0100640)) + ksft_exit_fail_msg("%s: wrong file mode bits after fchmodat2 with nofollow\n", + __func__); + + if (ret != 0) + ksft_test_result_skip("fchmodat2(symlink)\n"); + else + ksft_test_result_pass("fchmodat2(symlink)\n"); +} + +#define NUM_TESTS 2 + +int main(int argc, char **argv) +{ + ksft_print_header(); + ksft_set_plan(NUM_TESTS); + + test_regfile(); + test_symlink(); + + if (ksft_get_fail_cnt() + ksft_get_error_cnt() > 0) + ksft_exit_fail(); + else + ksft_exit_pass(); +} diff --git a/tools/testing/selftests/filelock/Makefile b/tools/testing/selftests/filelock/Makefile new file mode 100644 index 000000000000..478e82f8b464 --- /dev/null +++ b/tools/testing/selftests/filelock/Makefile @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0 + +TEST_GEN_PROGS := ofdlocks + +include ../lib.mk diff --git a/tools/testing/selftests/filelock/ofdlocks.c b/tools/testing/selftests/filelock/ofdlocks.c new file mode 100644 index 000000000000..a55b79810ab2 --- /dev/null +++ b/tools/testing/selftests/filelock/ofdlocks.c @@ -0,0 +1,132 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE +#include <fcntl.h> +#include <assert.h> +#include <stdio.h> +#include <unistd.h> +#include <string.h> +#include "../kselftest.h" + +static int lock_set(int fd, struct flock *fl) +{ + int ret; + + fl->l_pid = 0; // needed for OFD locks + fl->l_whence = SEEK_SET; + ret = fcntl(fd, F_OFD_SETLK, fl); + if (ret) + perror("fcntl()"); + return ret; +} + +static int lock_get(int fd, struct flock *fl) +{ + int ret; + + fl->l_pid = 0; // needed for OFD locks + fl->l_whence = SEEK_SET; + ret = fcntl(fd, F_OFD_GETLK, fl); + if (ret) + perror("fcntl()"); + return ret; +} + +int main(void) +{ + int rc; + struct flock fl, fl2; + int fd = open("/tmp/aa", O_RDWR | O_CREAT | O_EXCL, 0600); + int fd2 = open("/tmp/aa", O_RDONLY); + + unlink("/tmp/aa"); + assert(fd != -1); + assert(fd2 != -1); + ksft_print_msg("[INFO] opened fds %i %i\n", fd, fd2); + + /* Set some read lock */ + fl.l_type = F_RDLCK; + fl.l_start = 5; + fl.l_len = 3; + rc = lock_set(fd, &fl); + if (rc == 0) { + ksft_print_msg + ("[SUCCESS] set OFD read lock on first fd\n"); + } else { + ksft_print_msg("[FAIL] to set OFD read lock on first fd\n"); + return -1; + } + /* Make sure read locks do not conflict on different fds. */ + fl.l_type = F_RDLCK; + fl.l_start = 5; + fl.l_len = 1; + rc = lock_get(fd2, &fl); + if (rc != 0) + return -1; + if (fl.l_type != F_UNLCK) { + ksft_print_msg("[FAIL] read locks conflicted\n"); + return -1; + } + /* Make sure read/write locks do conflict on different fds. */ + fl.l_type = F_WRLCK; + fl.l_start = 5; + fl.l_len = 1; + rc = lock_get(fd2, &fl); + if (rc != 0) + return -1; + if (fl.l_type != F_UNLCK) { + ksft_print_msg + ("[SUCCESS] read and write locks conflicted\n"); + } else { + ksft_print_msg + ("[SUCCESS] read and write locks not conflicted\n"); + return -1; + } + /* Get info about the lock on first fd. */ + fl.l_type = F_UNLCK; + fl.l_start = 5; + fl.l_len = 1; + rc = lock_get(fd, &fl); + if (rc != 0) { + ksft_print_msg + ("[FAIL] F_OFD_GETLK with F_UNLCK not supported\n"); + return -1; + } + if (fl.l_type != F_UNLCK) { + ksft_print_msg + ("[SUCCESS] F_UNLCK test returns: locked, type %i pid %i len %zi\n", + fl.l_type, fl.l_pid, fl.l_len); + } else { + ksft_print_msg + ("[FAIL] F_OFD_GETLK with F_UNLCK did not return lock info\n"); + return -1; + } + /* Try the same but by locking everything by len==0. */ + fl2.l_type = F_UNLCK; + fl2.l_start = 0; + fl2.l_len = 0; + rc = lock_get(fd, &fl2); + if (rc != 0) { + ksft_print_msg + ("[FAIL] F_OFD_GETLK with F_UNLCK not supported\n"); + return -1; + } + if (memcmp(&fl, &fl2, sizeof(fl))) { + ksft_print_msg + ("[FAIL] F_UNLCK test returns: locked, type %i pid %i len %zi\n", + fl.l_type, fl.l_pid, fl.l_len); + return -1; + } + ksft_print_msg("[SUCCESS] F_UNLCK with len==0 returned the same\n"); + /* Get info about the lock on second fd - no locks on it. */ + fl.l_type = F_UNLCK; + fl.l_start = 0; + fl.l_len = 0; + lock_get(fd2, &fl); + if (fl.l_type != F_UNLCK) { + ksft_print_msg + ("[FAIL] F_OFD_GETLK with F_UNLCK return lock info from another fd\n"); + return -1; + } + return 0; +} diff --git a/tools/testing/selftests/filesystems/fat/run_fat_tests.sh b/tools/testing/selftests/filesystems/fat/run_fat_tests.sh index 7f35dc3d15df..d61264d4795d 100755 --- a/tools/testing/selftests/filesystems/fat/run_fat_tests.sh +++ b/tools/testing/selftests/filesystems/fat/run_fat_tests.sh @@ -12,7 +12,7 @@ set -u set -o pipefail BASE_DIR="$(dirname $0)" -TMP_DIR="$(mktemp -d /tmp/fat_tests_tmp.XXXX)" +TMP_DIR="$(mktemp -d /tmp/fat_tests_tmp.XXXXXX)" IMG_PATH="${TMP_DIR}/fat.img" MNT_PATH="${TMP_DIR}/mnt" diff --git a/tools/testing/selftests/ftrace/test.d/00basic/snapshot1.tc b/tools/testing/selftests/ftrace/test.d/00basic/snapshot1.tc new file mode 100644 index 000000000000..63b76cf2a360 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/00basic/snapshot1.tc @@ -0,0 +1,31 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: Snapshot and tracing_cpumask +# requires: trace_marker tracing_cpumask snapshot +# flags: instance + +# This testcase is constrived to reproduce a problem that the cpu buffers +# become unavailable which is due to 'record_disabled' of array_buffer and +# max_buffer being messed up. + +# Store origin cpumask +ORIG_CPUMASK=`cat tracing_cpumask` + +# Stop tracing all cpu +echo 0 > tracing_cpumask + +# Take a snapshot of the main buffer +echo 1 > snapshot + +# Restore origin cpumask, note that there should be some cpus being traced +echo ${ORIG_CPUMASK} > tracing_cpumask + +# Set tracing on +echo 1 > tracing_on + +# Write a log into buffer +echo "test input 1" > trace_marker + +# Ensure the log writed so that cpu buffers are still available +grep -q "test input 1" trace +exit 0 diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_btfarg.tc b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_btfarg.tc index f34b14ef9781..b9c21a81d248 100644 --- a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_btfarg.tc +++ b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_btfarg.tc @@ -5,6 +5,7 @@ KPROBES= FPROBES= +FIELDS= if grep -qF "p[:[<group>/][<event>]] <place> [<args>]" README ; then KPROBES=yes @@ -12,6 +13,9 @@ fi if grep -qF "f[:[<group>/][<event>]] <func-name>[%return] [<args>]" README ; then FPROBES=yes fi +if grep -qF "<argname>[->field[->field|.field...]]" README ; then + FIELDS=yes +fi if [ -z "$KPROBES" -a -z "$FPROBES" ] ; then exit_unsupported @@ -21,6 +25,9 @@ echo 0 > events/enable echo > dynamic_events TP=kfree +TP2=kmem_cache_alloc +TP3=getname_flags +TP4=sched_wakeup if [ "$FPROBES" ] ; then echo "f:fpevent $TP object" >> dynamic_events @@ -33,6 +40,7 @@ echo > dynamic_events echo "f:fpevent $TP "'$arg1' >> dynamic_events grep -q "fpevent.*object=object" dynamic_events + echo > dynamic_events echo "f:fpevent $TP "'$arg*' >> dynamic_events @@ -45,6 +53,18 @@ fi echo > dynamic_events +if [ "$FIELDS" ] ; then +echo "t:tpevent ${TP2} obj_size=s->object_size" >> dynamic_events +echo "f:fpevent ${TP3}%return path=\$retval->name:string" >> dynamic_events +echo "t:tpevent2 ${TP4} p->se.group_node.next->prev" >> dynamic_events + +grep -q "tpevent .*obj_size=s->object_size" dynamic_events +grep -q "fpevent.*path=\$retval->name:string" dynamic_events +grep -q 'tpevent2 .*p->se.group_node.next->prev' dynamic_events + +echo > dynamic_events +fi + if [ "$KPROBES" ] ; then echo "p:kpevent $TP object" >> dynamic_events grep -q "kpevent.*object=object" dynamic_events diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/fprobe_syntax_errors.tc b/tools/testing/selftests/ftrace/test.d/dynevent/fprobe_syntax_errors.tc index 812f5b3f6055..20e42c030095 100644 --- a/tools/testing/selftests/ftrace/test.d/dynevent/fprobe_syntax_errors.tc +++ b/tools/testing/selftests/ftrace/test.d/dynevent/fprobe_syntax_errors.tc @@ -30,11 +30,11 @@ check_error 'f:^ vfs_read' # NO_EVENT_NAME check_error 'f:foo/^12345678901234567890123456789012345678901234567890123456789012345 vfs_read' # EVENT_TOO_LONG check_error 'f:foo/^bar.1 vfs_read' # BAD_EVENT_NAME -check_error 'f vfs_read ^$retval' # RETVAL_ON_PROBE check_error 'f vfs_read ^$stack10000' # BAD_STACK_NUM check_error 'f vfs_read ^$arg10000' # BAD_ARG_NUM +check_error 'f vfs_read $retval ^$arg1' # BAD_VAR check_error 'f vfs_read ^$none_var' # BAD_VAR check_error 'f vfs_read ^'$REG # BAD_VAR @@ -103,6 +103,14 @@ check_error 'f vfs_read%return ^$arg*' # NOFENTRY_ARGS check_error 'f vfs_read ^hoge' # NO_BTFARG check_error 'f kfree ^$arg10' # NO_BTFARG (exceed the number of parameters) check_error 'f kfree%return ^$retval' # NO_RETVAL + +if grep -qF "<argname>[->field[->field|.field...]]" README ; then +check_error 'f vfs_read%return $retval->^foo' # NO_PTR_STRCT +check_error 'f vfs_read file->^foo' # NO_BTF_FIELD +check_error 'f vfs_read file^-.foo' # BAD_HYPHEN +check_error 'f vfs_read ^file:string' # BAD_TYPE4STR +fi + else check_error 'f vfs_read ^$arg*' # NOSUP_BTFARG check_error 't kfree ^$arg*' # NOSUP_BTFARG diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_char.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_char.tc index 285b4770efad..ff7499eb98d6 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_char.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_char.tc @@ -34,14 +34,19 @@ mips*) esac : "Test get argument (1)" -echo "p:testprobe tracefs_create_dir arg1=+0(${ARG1}):char" > kprobe_events +if grep -q eventfs_add_dir available_filter_functions; then + DIR_NAME="eventfs_add_dir" +else + DIR_NAME="tracefs_create_dir" +fi +echo "p:testprobe ${DIR_NAME} arg1=+0(${ARG1}):char" > kprobe_events echo 1 > events/kprobes/testprobe/enable echo "p:test $FUNCTION_FORK" >> kprobe_events grep -qe "testprobe.* arg1='t'" trace echo 0 > events/kprobes/testprobe/enable : "Test get argument (2)" -echo "p:testprobe tracefs_create_dir arg1=+0(${ARG1}):char arg2=+0(${ARG1}):char[4]" > kprobe_events +echo "p:testprobe ${DIR_NAME} arg1=+0(${ARG1}):char arg2=+0(${ARG1}):char[4]" > kprobe_events echo 1 > events/kprobes/testprobe/enable echo "p:test $FUNCTION_FORK" >> kprobe_events grep -qe "testprobe.* arg1='t' arg2={'t','e','s','t'}" trace diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc index a4f8e7c53c1f..a202b2ea4baf 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc @@ -37,14 +37,19 @@ loongarch*) esac : "Test get argument (1)" -echo "p:testprobe tracefs_create_dir arg1=+0(${ARG1}):string" > kprobe_events +if grep -q eventfs_add_dir available_filter_functions; then + DIR_NAME="eventfs_add_dir" +else + DIR_NAME="tracefs_create_dir" +fi +echo "p:testprobe ${DIR_NAME} arg1=+0(${ARG1}):string" > kprobe_events echo 1 > events/kprobes/testprobe/enable echo "p:test $FUNCTION_FORK" >> kprobe_events grep -qe "testprobe.* arg1=\"test\"" trace echo 0 > events/kprobes/testprobe/enable : "Test get argument (2)" -echo "p:testprobe tracefs_create_dir arg1=+0(${ARG1}):string arg2=+0(${ARG1}):string" > kprobe_events +echo "p:testprobe ${DIR_NAME} arg1=+0(${ARG1}):string arg2=+0(${ARG1}):string" > kprobe_events echo 1 > events/kprobes/testprobe/enable echo "p:test $FUNCTION_FORK" >> kprobe_events grep -qe "testprobe.* arg1=\"test\" arg2=\"test\"" trace diff --git a/tools/testing/selftests/futex/functional/futex_wait_timeout.c b/tools/testing/selftests/futex/functional/futex_wait_timeout.c index 3651ce17beeb..d183f878360b 100644 --- a/tools/testing/selftests/futex/functional/futex_wait_timeout.c +++ b/tools/testing/selftests/futex/functional/futex_wait_timeout.c @@ -24,6 +24,7 @@ static long timeout_ns = 100000; /* 100us default timeout */ static futex_t futex_pi; +static pthread_barrier_t barrier; void usage(char *prog) { @@ -48,6 +49,8 @@ void *get_pi_lock(void *arg) if (ret != 0) error("futex_lock_pi failed\n", ret); + pthread_barrier_wait(&barrier); + /* Blocks forever */ ret = futex_wait(&lock, 0, NULL, 0); error("futex_wait failed\n", ret); @@ -130,6 +133,7 @@ int main(int argc, char *argv[]) basename(argv[0])); ksft_print_msg("\tArguments: timeout=%ldns\n", timeout_ns); + pthread_barrier_init(&barrier, NULL, 2); pthread_create(&thread, NULL, get_pi_lock, NULL); /* initialize relative timeout */ @@ -163,6 +167,9 @@ int main(int argc, char *argv[]) res = futex_wait_requeue_pi(&f1, f1, &futex_pi, &to, 0); test_timeout(res, &ret, "futex_wait_requeue_pi monotonic", ETIMEDOUT); + /* Wait until the other thread calls futex_lock_pi() */ + pthread_barrier_wait(&barrier); + pthread_barrier_destroy(&barrier); /* * FUTEX_LOCK_PI with CLOCK_REALTIME * Due to historical reasons, FUTEX_LOCK_PI supports only realtime diff --git a/tools/testing/selftests/hid/Makefile b/tools/testing/selftests/hid/Makefile index 01c0491d64da..2e986cbf1a46 100644 --- a/tools/testing/selftests/hid/Makefile +++ b/tools/testing/selftests/hid/Makefile @@ -167,7 +167,7 @@ $(RESOLVE_BTFIDS): $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/resolve_btfids \ OUTPUT=$(HOST_BUILD_DIR)/resolve_btfids/ BPFOBJ=$(HOST_BPFOBJ) # Get Clang's default includes on this system, as opposed to those seen by -# '-target bpf'. This fixes "missing" files on some architectures/distros, +# '--target=bpf'. This fixes "missing" files on some architectures/distros, # such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc. # # Use '-idirafter': Don't interfere with include mechanics except where the @@ -196,12 +196,12 @@ CLANG_CFLAGS = $(CLANG_SYS_INCLUDES) \ # $3 - CFLAGS define CLANG_BPF_BUILD_RULE $(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2) - $(Q)$(CLANG) $3 -O2 -target bpf -c $1 -mcpu=v3 -o $2 + $(Q)$(CLANG) $3 -O2 --target=bpf -c $1 -mcpu=v3 -o $2 endef # Similar to CLANG_BPF_BUILD_RULE, but with disabled alu32 define CLANG_NOALU32_BPF_BUILD_RULE $(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2) - $(Q)$(CLANG) $3 -O2 -target bpf -c $1 -mcpu=v2 -o $2 + $(Q)$(CLANG) $3 -O2 --target=bpf -c $1 -mcpu=v2 -o $2 endef # Build BPF object using GCC define GCC_BPF_BUILD_RULE diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c index e4a6b33cfde4..33d08600be13 100644 --- a/tools/testing/selftests/iommu/iommufd.c +++ b/tools/testing/selftests/iommu/iommufd.c @@ -9,9 +9,6 @@ #include "iommufd_utils.h" -static void *buffer; - -static unsigned long PAGE_SIZE; static unsigned long HUGEPAGE_SIZE; #define MOCK_PAGE_SIZE (PAGE_SIZE / 2) @@ -116,6 +113,7 @@ TEST_F(iommufd, cmd_length) } TEST_LENGTH(iommu_destroy, IOMMU_DESTROY); + TEST_LENGTH(iommu_hw_info, IOMMU_GET_HW_INFO); TEST_LENGTH(iommu_ioas_alloc, IOMMU_IOAS_ALLOC); TEST_LENGTH(iommu_ioas_iova_ranges, IOMMU_IOAS_IOVA_RANGES); TEST_LENGTH(iommu_ioas_allow_iovas, IOMMU_IOAS_ALLOW_IOVAS); @@ -188,6 +186,7 @@ FIXTURE(iommufd_ioas) uint32_t ioas_id; uint32_t stdev_id; uint32_t hwpt_id; + uint32_t device_id; uint64_t base_iova; }; @@ -214,7 +213,7 @@ FIXTURE_SETUP(iommufd_ioas) for (i = 0; i != variant->mock_domains; i++) { test_cmd_mock_domain(self->ioas_id, &self->stdev_id, - &self->hwpt_id); + &self->hwpt_id, &self->device_id); self->base_iova = MOCK_APERTURE_START; } } @@ -265,7 +264,7 @@ TEST_F(iommufd_ioas, hwpt_attach) { /* Create a device attached directly to a hwpt */ if (self->stdev_id) { - test_cmd_mock_domain(self->hwpt_id, NULL, NULL); + test_cmd_mock_domain(self->hwpt_id, NULL, NULL, NULL); } else { test_err_mock_domain(ENOENT, self->hwpt_id, NULL, NULL); } @@ -293,6 +292,40 @@ TEST_F(iommufd_ioas, ioas_area_auto_destroy) } } +TEST_F(iommufd_ioas, get_hw_info) +{ + struct iommu_test_hw_info buffer_exact; + struct iommu_test_hw_info_buffer_larger { + struct iommu_test_hw_info info; + uint64_t trailing_bytes; + } buffer_larger; + struct iommu_test_hw_info_buffer_smaller { + __u32 flags; + } buffer_smaller; + + if (self->device_id) { + /* Provide a zero-size user_buffer */ + test_cmd_get_hw_info(self->device_id, NULL, 0); + /* Provide a user_buffer with exact size */ + test_cmd_get_hw_info(self->device_id, &buffer_exact, sizeof(buffer_exact)); + /* + * Provide a user_buffer with size larger than the exact size to check if + * kernel zero the trailing bytes. + */ + test_cmd_get_hw_info(self->device_id, &buffer_larger, sizeof(buffer_larger)); + /* + * Provide a user_buffer with size smaller than the exact size to check if + * the fields within the size range still gets updated. + */ + test_cmd_get_hw_info(self->device_id, &buffer_smaller, sizeof(buffer_smaller)); + } else { + test_err_get_hw_info(ENOENT, self->device_id, + &buffer_exact, sizeof(buffer_exact)); + test_err_get_hw_info(ENOENT, self->device_id, + &buffer_larger, sizeof(buffer_larger)); + } +} + TEST_F(iommufd_ioas, area) { int i; @@ -684,7 +717,7 @@ TEST_F(iommufd_ioas, access_pin) _IOMMU_TEST_CMD(IOMMU_TEST_OP_ACCESS_PAGES), &access_cmd)); test_cmd_mock_domain(self->ioas_id, &mock_stdev_id, - &mock_hwpt_id); + &mock_hwpt_id, NULL); check_map_cmd.id = mock_hwpt_id; ASSERT_EQ(0, ioctl(self->fd, _IOMMU_TEST_CMD(IOMMU_TEST_OP_MD_CHECK_MAP), @@ -839,7 +872,7 @@ TEST_F(iommufd_ioas, fork_gone) * If a domain already existed then everything was pinned within * the fork, so this copies from one domain to another. */ - test_cmd_mock_domain(self->ioas_id, NULL, NULL); + test_cmd_mock_domain(self->ioas_id, NULL, NULL, NULL); check_access_rw(_metadata, self->fd, access_id, MOCK_APERTURE_START, 0); @@ -888,7 +921,7 @@ TEST_F(iommufd_ioas, fork_present) ASSERT_EQ(8, read(efd, &tmp, sizeof(tmp))); /* Read pages from the remote process */ - test_cmd_mock_domain(self->ioas_id, NULL, NULL); + test_cmd_mock_domain(self->ioas_id, NULL, NULL, NULL); check_access_rw(_metadata, self->fd, access_id, MOCK_APERTURE_START, 0); ASSERT_EQ(0, close(pipefds[1])); @@ -1035,6 +1068,8 @@ FIXTURE(iommufd_mock_domain) uint32_t ioas_id; uint32_t hwpt_id; uint32_t hwpt_ids[2]; + uint32_t stdev_ids[2]; + uint32_t idev_ids[2]; int mmap_flags; size_t mmap_buf_size; }; @@ -1056,7 +1091,8 @@ FIXTURE_SETUP(iommufd_mock_domain) ASSERT_GE(ARRAY_SIZE(self->hwpt_ids), variant->mock_domains); for (i = 0; i != variant->mock_domains; i++) - test_cmd_mock_domain(self->ioas_id, NULL, &self->hwpt_ids[i]); + test_cmd_mock_domain(self->ioas_id, &self->stdev_ids[i], + &self->hwpt_ids[i], &self->idev_ids[i]); self->hwpt_id = self->hwpt_ids[0]; self->mmap_flags = MAP_SHARED | MAP_ANONYMOUS; @@ -1250,7 +1286,7 @@ TEST_F(iommufd_mock_domain, all_aligns_copy) /* Add and destroy a domain while the area exists */ old_id = self->hwpt_ids[1]; test_cmd_mock_domain(self->ioas_id, &mock_stdev_id, - &self->hwpt_ids[1]); + &self->hwpt_ids[1], NULL); check_mock_iova(buf + start, iova, length); check_refs(buf + start / PAGE_SIZE * PAGE_SIZE, @@ -1283,7 +1319,13 @@ TEST_F(iommufd_mock_domain, user_copy) .dst_iova = MOCK_APERTURE_START, .length = BUFFER_SIZE, }; - unsigned int ioas_id; + struct iommu_ioas_unmap unmap_cmd = { + .size = sizeof(unmap_cmd), + .ioas_id = self->ioas_id, + .iova = MOCK_APERTURE_START, + .length = BUFFER_SIZE, + }; + unsigned int new_ioas_id, ioas_id; /* Pin the pages in an IOAS with no domains then copy to an IOAS with domains */ test_ioctl_ioas_alloc(&ioas_id); @@ -1301,13 +1343,77 @@ TEST_F(iommufd_mock_domain, user_copy) ASSERT_EQ(0, ioctl(self->fd, IOMMU_IOAS_COPY, ©_cmd)); check_mock_iova(buffer, MOCK_APERTURE_START, BUFFER_SIZE); + /* Now replace the ioas with a new one */ + test_ioctl_ioas_alloc(&new_ioas_id); + test_ioctl_ioas_map_id(new_ioas_id, buffer, BUFFER_SIZE, + ©_cmd.src_iova); + test_cmd_access_replace_ioas(access_cmd.id, new_ioas_id); + + /* Destroy the old ioas and cleanup copied mapping */ + ASSERT_EQ(0, ioctl(self->fd, IOMMU_IOAS_UNMAP, &unmap_cmd)); + test_ioctl_destroy(ioas_id); + + /* Then run the same test again with the new ioas */ + access_cmd.access_pages.iova = copy_cmd.src_iova; + ASSERT_EQ(0, + ioctl(self->fd, _IOMMU_TEST_CMD(IOMMU_TEST_OP_ACCESS_PAGES), + &access_cmd)); + copy_cmd.src_ioas_id = new_ioas_id; + ASSERT_EQ(0, ioctl(self->fd, IOMMU_IOAS_COPY, ©_cmd)); + check_mock_iova(buffer, MOCK_APERTURE_START, BUFFER_SIZE); + test_cmd_destroy_access_pages( access_cmd.id, access_cmd.access_pages.out_access_pages_id); test_cmd_destroy_access(access_cmd.id); + test_ioctl_destroy(new_ioas_id); +} + +TEST_F(iommufd_mock_domain, replace) +{ + uint32_t ioas_id; + + test_ioctl_ioas_alloc(&ioas_id); + + test_cmd_mock_domain_replace(self->stdev_ids[0], ioas_id); + + /* + * Replacing the IOAS causes the prior HWPT to be deallocated, thus we + * should get enoent when we try to use it. + */ + if (variant->mock_domains == 1) + test_err_mock_domain_replace(ENOENT, self->stdev_ids[0], + self->hwpt_ids[0]); + + test_cmd_mock_domain_replace(self->stdev_ids[0], ioas_id); + if (variant->mock_domains >= 2) { + test_cmd_mock_domain_replace(self->stdev_ids[0], + self->hwpt_ids[1]); + test_cmd_mock_domain_replace(self->stdev_ids[0], + self->hwpt_ids[1]); + test_cmd_mock_domain_replace(self->stdev_ids[0], + self->hwpt_ids[0]); + } + + test_cmd_mock_domain_replace(self->stdev_ids[0], self->ioas_id); test_ioctl_destroy(ioas_id); } +TEST_F(iommufd_mock_domain, alloc_hwpt) +{ + int i; + + for (i = 0; i != variant->mock_domains; i++) { + uint32_t stddev_id; + uint32_t hwpt_id; + + test_cmd_hwpt_alloc(self->idev_ids[0], self->ioas_id, &hwpt_id); + test_cmd_mock_domain(hwpt_id, &stddev_id, NULL, NULL); + test_ioctl_destroy(stddev_id); + test_ioctl_destroy(hwpt_id); + } +} + /* VFIO compatibility IOCTLs */ TEST_F(iommufd, simple_ioctls) @@ -1429,7 +1535,7 @@ FIXTURE_SETUP(vfio_compat_mock_domain) /* Create what VFIO would consider a group */ test_ioctl_ioas_alloc(&self->ioas_id); - test_cmd_mock_domain(self->ioas_id, NULL, NULL); + test_cmd_mock_domain(self->ioas_id, NULL, NULL, NULL); /* Attach it to the vfio compat */ vfio_ioas_cmd.ioas_id = self->ioas_id; diff --git a/tools/testing/selftests/iommu/iommufd_fail_nth.c b/tools/testing/selftests/iommu/iommufd_fail_nth.c index d9afcb23810e..a220ca2a689d 100644 --- a/tools/testing/selftests/iommu/iommufd_fail_nth.c +++ b/tools/testing/selftests/iommu/iommufd_fail_nth.c @@ -41,6 +41,8 @@ static int writeat(int dfd, const char *fn, const char *val) static __attribute__((constructor)) void setup_buffer(void) { + PAGE_SIZE = sysconf(_SC_PAGE_SIZE); + BUFFER_SIZE = 2*1024*1024; buffer = mmap(0, BUFFER_SIZE, PROT_READ | PROT_WRITE, @@ -313,7 +315,7 @@ TEST_FAIL_NTH(basic_fail_nth, map_domain) fail_nth_enable(); - if (_test_cmd_mock_domain(self->fd, ioas_id, &stdev_id, &hwpt_id)) + if (_test_cmd_mock_domain(self->fd, ioas_id, &stdev_id, &hwpt_id, NULL)) return -1; if (_test_ioctl_ioas_map(self->fd, ioas_id, buffer, 262144, &iova, @@ -324,7 +326,7 @@ TEST_FAIL_NTH(basic_fail_nth, map_domain) if (_test_ioctl_destroy(self->fd, stdev_id)) return -1; - if (_test_cmd_mock_domain(self->fd, ioas_id, &stdev_id, &hwpt_id)) + if (_test_cmd_mock_domain(self->fd, ioas_id, &stdev_id, &hwpt_id, NULL)) return -1; return 0; } @@ -348,12 +350,13 @@ TEST_FAIL_NTH(basic_fail_nth, map_two_domains) if (_test_ioctl_set_temp_memory_limit(self->fd, 32)) return -1; - if (_test_cmd_mock_domain(self->fd, ioas_id, &stdev_id, &hwpt_id)) + if (_test_cmd_mock_domain(self->fd, ioas_id, &stdev_id, &hwpt_id, NULL)) return -1; fail_nth_enable(); - if (_test_cmd_mock_domain(self->fd, ioas_id, &stdev_id2, &hwpt_id2)) + if (_test_cmd_mock_domain(self->fd, ioas_id, &stdev_id2, &hwpt_id2, + NULL)) return -1; if (_test_ioctl_ioas_map(self->fd, ioas_id, buffer, 262144, &iova, @@ -367,9 +370,10 @@ TEST_FAIL_NTH(basic_fail_nth, map_two_domains) if (_test_ioctl_destroy(self->fd, stdev_id2)) return -1; - if (_test_cmd_mock_domain(self->fd, ioas_id, &stdev_id, &hwpt_id)) + if (_test_cmd_mock_domain(self->fd, ioas_id, &stdev_id, &hwpt_id, NULL)) return -1; - if (_test_cmd_mock_domain(self->fd, ioas_id, &stdev_id2, &hwpt_id2)) + if (_test_cmd_mock_domain(self->fd, ioas_id, &stdev_id2, &hwpt_id2, + NULL)) return -1; return 0; } @@ -526,7 +530,7 @@ TEST_FAIL_NTH(basic_fail_nth, access_pin_domain) if (_test_ioctl_set_temp_memory_limit(self->fd, 32)) return -1; - if (_test_cmd_mock_domain(self->fd, ioas_id, &stdev_id, &hwpt_id)) + if (_test_cmd_mock_domain(self->fd, ioas_id, &stdev_id, &hwpt_id, NULL)) return -1; if (_test_ioctl_ioas_map(self->fd, ioas_id, buffer, BUFFER_SIZE, &iova, @@ -569,4 +573,57 @@ TEST_FAIL_NTH(basic_fail_nth, access_pin_domain) return 0; } +/* device.c */ +TEST_FAIL_NTH(basic_fail_nth, device) +{ + struct iommu_test_hw_info info; + uint32_t ioas_id; + uint32_t ioas_id2; + uint32_t stdev_id; + uint32_t idev_id; + uint32_t hwpt_id; + __u64 iova; + + self->fd = open("/dev/iommu", O_RDWR); + if (self->fd == -1) + return -1; + + if (_test_ioctl_ioas_alloc(self->fd, &ioas_id)) + return -1; + + if (_test_ioctl_ioas_alloc(self->fd, &ioas_id2)) + return -1; + + iova = MOCK_APERTURE_START; + if (_test_ioctl_ioas_map(self->fd, ioas_id, buffer, PAGE_SIZE, &iova, + IOMMU_IOAS_MAP_FIXED_IOVA | + IOMMU_IOAS_MAP_WRITEABLE | + IOMMU_IOAS_MAP_READABLE)) + return -1; + if (_test_ioctl_ioas_map(self->fd, ioas_id2, buffer, PAGE_SIZE, &iova, + IOMMU_IOAS_MAP_FIXED_IOVA | + IOMMU_IOAS_MAP_WRITEABLE | + IOMMU_IOAS_MAP_READABLE)) + return -1; + + fail_nth_enable(); + + if (_test_cmd_mock_domain(self->fd, ioas_id, &stdev_id, NULL, + &idev_id)) + return -1; + + if (_test_cmd_get_hw_info(self->fd, idev_id, &info, sizeof(info))) + return -1; + + if (_test_cmd_hwpt_alloc(self->fd, idev_id, ioas_id, &hwpt_id)) + return -1; + + if (_test_cmd_mock_domain_replace(self->fd, stdev_id, ioas_id2, NULL)) + return -1; + + if (_test_cmd_mock_domain_replace(self->fd, stdev_id, hwpt_id, NULL)) + return -1; + return 0; +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/iommu/iommufd_utils.h b/tools/testing/selftests/iommu/iommufd_utils.h index 85d6662ef8e8..e0753d03ecaa 100644 --- a/tools/testing/selftests/iommu/iommufd_utils.h +++ b/tools/testing/selftests/iommu/iommufd_utils.h @@ -19,6 +19,12 @@ static void *buffer; static unsigned long BUFFER_SIZE; +static unsigned long PAGE_SIZE; + +#define sizeof_field(TYPE, MEMBER) sizeof((((TYPE *)0)->MEMBER)) +#define offsetofend(TYPE, MEMBER) \ + (offsetof(TYPE, MEMBER) + sizeof_field(TYPE, MEMBER)) + /* * Have the kernel check the refcount on pages. I don't know why a freshly * mmap'd anon non-compound page starts out with a ref of 3 @@ -39,7 +45,7 @@ static unsigned long BUFFER_SIZE; }) static int _test_cmd_mock_domain(int fd, unsigned int ioas_id, __u32 *stdev_id, - __u32 *hwpt_id) + __u32 *hwpt_id, __u32 *idev_id) { struct iommu_test_cmd cmd = { .size = sizeof(cmd), @@ -57,14 +63,84 @@ static int _test_cmd_mock_domain(int fd, unsigned int ioas_id, __u32 *stdev_id, assert(cmd.id != 0); if (hwpt_id) *hwpt_id = cmd.mock_domain.out_hwpt_id; + if (idev_id) + *idev_id = cmd.mock_domain.out_idev_id; return 0; } -#define test_cmd_mock_domain(ioas_id, stdev_id, hwpt_id) \ - ASSERT_EQ(0, \ - _test_cmd_mock_domain(self->fd, ioas_id, stdev_id, hwpt_id)) +#define test_cmd_mock_domain(ioas_id, stdev_id, hwpt_id, idev_id) \ + ASSERT_EQ(0, _test_cmd_mock_domain(self->fd, ioas_id, stdev_id, \ + hwpt_id, idev_id)) #define test_err_mock_domain(_errno, ioas_id, stdev_id, hwpt_id) \ EXPECT_ERRNO(_errno, _test_cmd_mock_domain(self->fd, ioas_id, \ - stdev_id, hwpt_id)) + stdev_id, hwpt_id, NULL)) + +static int _test_cmd_mock_domain_replace(int fd, __u32 stdev_id, __u32 pt_id, + __u32 *hwpt_id) +{ + struct iommu_test_cmd cmd = { + .size = sizeof(cmd), + .op = IOMMU_TEST_OP_MOCK_DOMAIN_REPLACE, + .id = stdev_id, + .mock_domain_replace = { + .pt_id = pt_id, + }, + }; + int ret; + + ret = ioctl(fd, IOMMU_TEST_CMD, &cmd); + if (ret) + return ret; + if (hwpt_id) + *hwpt_id = cmd.mock_domain_replace.pt_id; + return 0; +} + +#define test_cmd_mock_domain_replace(stdev_id, pt_id) \ + ASSERT_EQ(0, _test_cmd_mock_domain_replace(self->fd, stdev_id, pt_id, \ + NULL)) +#define test_err_mock_domain_replace(_errno, stdev_id, pt_id) \ + EXPECT_ERRNO(_errno, _test_cmd_mock_domain_replace(self->fd, stdev_id, \ + pt_id, NULL)) + +static int _test_cmd_hwpt_alloc(int fd, __u32 device_id, __u32 pt_id, + __u32 *hwpt_id) +{ + struct iommu_hwpt_alloc cmd = { + .size = sizeof(cmd), + .dev_id = device_id, + .pt_id = pt_id, + }; + int ret; + + ret = ioctl(fd, IOMMU_HWPT_ALLOC, &cmd); + if (ret) + return ret; + if (hwpt_id) + *hwpt_id = cmd.out_hwpt_id; + return 0; +} + +#define test_cmd_hwpt_alloc(device_id, pt_id, hwpt_id) \ + ASSERT_EQ(0, _test_cmd_hwpt_alloc(self->fd, device_id, pt_id, hwpt_id)) + +static int _test_cmd_access_replace_ioas(int fd, __u32 access_id, + unsigned int ioas_id) +{ + struct iommu_test_cmd cmd = { + .size = sizeof(cmd), + .op = IOMMU_TEST_OP_ACCESS_REPLACE_IOAS, + .id = access_id, + .access_replace_ioas = { .ioas_id = ioas_id }, + }; + int ret; + + ret = ioctl(fd, IOMMU_TEST_CMD, &cmd); + if (ret) + return ret; + return 0; +} +#define test_cmd_access_replace_ioas(access_id, ioas_id) \ + ASSERT_EQ(0, _test_cmd_access_replace_ioas(self->fd, access_id, ioas_id)) static int _test_cmd_create_access(int fd, unsigned int ioas_id, __u32 *access_id, unsigned int flags) @@ -276,3 +352,61 @@ static void teardown_iommufd(int fd, struct __test_metadata *_metadata) }) #endif + +/* @data can be NULL */ +static int _test_cmd_get_hw_info(int fd, __u32 device_id, + void *data, size_t data_len) +{ + struct iommu_test_hw_info *info = (struct iommu_test_hw_info *)data; + struct iommu_hw_info cmd = { + .size = sizeof(cmd), + .dev_id = device_id, + .data_len = data_len, + .data_uptr = (uint64_t)data, + }; + int ret; + + ret = ioctl(fd, IOMMU_GET_HW_INFO, &cmd); + if (ret) + return ret; + + assert(cmd.out_data_type == IOMMU_HW_INFO_TYPE_SELFTEST); + + /* + * The struct iommu_test_hw_info should be the one defined + * by the current kernel. + */ + assert(cmd.data_len == sizeof(struct iommu_test_hw_info)); + + /* + * Trailing bytes should be 0 if user buffer is larger than + * the data that kernel reports. + */ + if (data_len > cmd.data_len) { + char *ptr = (char *)(data + cmd.data_len); + int idx = 0; + + while (idx < data_len - cmd.data_len) { + assert(!*(ptr + idx)); + idx++; + } + } + + if (info) { + if (data_len >= offsetofend(struct iommu_test_hw_info, test_reg)) + assert(info->test_reg == IOMMU_HW_INFO_SELFTEST_REGVAL); + if (data_len >= offsetofend(struct iommu_test_hw_info, flags)) + assert(!info->flags); + } + + return 0; +} + +#define test_cmd_get_hw_info(device_id, data, data_len) \ + ASSERT_EQ(0, _test_cmd_get_hw_info(self->fd, device_id, \ + data, data_len)) + +#define test_err_get_hw_info(_errno, device_id, data, data_len) \ + EXPECT_ERRNO(_errno, \ + _test_cmd_get_hw_info(self->fd, device_id, \ + data, data_len)) diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h index 829be379545a..529d29a35900 100644 --- a/tools/testing/selftests/kselftest.h +++ b/tools/testing/selftests/kselftest.h @@ -113,6 +113,15 @@ static inline int ksft_get_error_cnt(void) { return ksft_cnt.ksft_error; } static inline void ksft_print_header(void) { + /* + * Force line buffering; If stdout is not connected to a terminal, it + * will otherwise default to fully buffered, which can cause output + * duplication if there is content in the buffer when fork()ing. If + * there is a crash, line buffering also means the most recent output + * line will be visible. + */ + setvbuf(stdout, NULL, _IOLBF, 0); + if (!(getenv("KSFT_TAP_LEVEL"))) printf("TAP version 13\n"); } diff --git a/tools/testing/selftests/kselftest/runner.sh b/tools/testing/selftests/kselftest/runner.sh index 1c952d1401d4..261c73cab41b 100644 --- a/tools/testing/selftests/kselftest/runner.sh +++ b/tools/testing/selftests/kselftest/runner.sh @@ -105,15 +105,18 @@ run_one() echo "# Warning: file $TEST is missing!" echo "not ok $test_num $TEST_HDR_MSG" else + if [ -x /usr/bin/stdbuf ]; then + stdbuf="/usr/bin/stdbuf --output=L " + fi eval kselftest_cmd_args="\$${kselftest_cmd_args_ref:-}" - cmd="./$BASENAME_TEST $kselftest_cmd_args" + cmd="$stdbuf ./$BASENAME_TEST $kselftest_cmd_args" if [ ! -x "$TEST" ]; then echo "# Warning: file $TEST is not executable" if [ $(head -n 1 "$TEST" | cut -c -2) = "#!" ] then interpreter=$(head -n 1 "$TEST" | cut -c 3-) - cmd="$interpreter ./$BASENAME_TEST" + cmd="$stdbuf $interpreter ./$BASENAME_TEST" else echo "not ok $test_num $TEST_HDR_MSG" return diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index 5fd49ad0c696..e05ac8261046 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -938,7 +938,11 @@ void __wait_for_test(struct __test_metadata *t) fprintf(TH_LOG_STREAM, "# %s: Test terminated by timeout\n", t->name); } else if (WIFEXITED(status)) { - if (t->termsig != -1) { + if (WEXITSTATUS(status) == 255) { + /* SKIP */ + t->passed = 1; + t->skip = 1; + } else if (t->termsig != -1) { t->passed = 0; fprintf(TH_LOG_STREAM, "# %s: Test exited normally instead of by signal (code: %d)\n", @@ -950,11 +954,6 @@ void __wait_for_test(struct __test_metadata *t) case 0: t->passed = 1; break; - /* SKIP */ - case 255: - t->passed = 1; - t->skip = 1; - break; /* Other failure, assume step report. */ default: t->passed = 0; diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index c692cc86e7da..a3bb36fb3cfc 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -23,6 +23,7 @@ LIBKVM += lib/guest_modes.c LIBKVM += lib/io.c LIBKVM += lib/kvm_util.c LIBKVM += lib/memstress.c +LIBKVM += lib/guest_sprintf.c LIBKVM += lib/rbtree.c LIBKVM += lib/sparsebit.c LIBKVM += lib/test_util.c @@ -122,6 +123,7 @@ TEST_GEN_PROGS_x86_64 += access_tracking_perf_test TEST_GEN_PROGS_x86_64 += demand_paging_test TEST_GEN_PROGS_x86_64 += dirty_log_test TEST_GEN_PROGS_x86_64 += dirty_log_perf_test +TEST_GEN_PROGS_x86_64 += guest_print_test TEST_GEN_PROGS_x86_64 += hardware_disable_test TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus TEST_GEN_PROGS_x86_64 += kvm_page_table_test @@ -140,7 +142,6 @@ TEST_GEN_PROGS_EXTENDED_x86_64 += x86_64/nx_huge_pages_test TEST_GEN_PROGS_aarch64 += aarch64/aarch32_id_regs TEST_GEN_PROGS_aarch64 += aarch64/arch_timer TEST_GEN_PROGS_aarch64 += aarch64/debug-exceptions -TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list TEST_GEN_PROGS_aarch64 += aarch64/hypercalls TEST_GEN_PROGS_aarch64 += aarch64/page_fault_test TEST_GEN_PROGS_aarch64 += aarch64/psci_test @@ -152,6 +153,8 @@ TEST_GEN_PROGS_aarch64 += access_tracking_perf_test TEST_GEN_PROGS_aarch64 += demand_paging_test TEST_GEN_PROGS_aarch64 += dirty_log_test TEST_GEN_PROGS_aarch64 += dirty_log_perf_test +TEST_GEN_PROGS_aarch64 += guest_print_test +TEST_GEN_PROGS_aarch64 += get-reg-list TEST_GEN_PROGS_aarch64 += kvm_create_max_vcpus TEST_GEN_PROGS_aarch64 += kvm_page_table_test TEST_GEN_PROGS_aarch64 += memslot_modification_stress_test @@ -166,8 +169,10 @@ TEST_GEN_PROGS_s390x += s390x/resets TEST_GEN_PROGS_s390x += s390x/sync_regs_test TEST_GEN_PROGS_s390x += s390x/tprot TEST_GEN_PROGS_s390x += s390x/cmma_test +TEST_GEN_PROGS_s390x += s390x/debug_test TEST_GEN_PROGS_s390x += demand_paging_test TEST_GEN_PROGS_s390x += dirty_log_test +TEST_GEN_PROGS_s390x += guest_print_test TEST_GEN_PROGS_s390x += kvm_create_max_vcpus TEST_GEN_PROGS_s390x += kvm_page_table_test TEST_GEN_PROGS_s390x += rseq_test @@ -176,11 +181,15 @@ TEST_GEN_PROGS_s390x += kvm_binary_stats_test TEST_GEN_PROGS_riscv += demand_paging_test TEST_GEN_PROGS_riscv += dirty_log_test +TEST_GEN_PROGS_riscv += guest_print_test +TEST_GEN_PROGS_riscv += get-reg-list TEST_GEN_PROGS_riscv += kvm_create_max_vcpus TEST_GEN_PROGS_riscv += kvm_page_table_test TEST_GEN_PROGS_riscv += set_memory_region_test TEST_GEN_PROGS_riscv += kvm_binary_stats_test +SPLIT_TESTS += get-reg-list + TEST_PROGS += $(TEST_PROGS_$(ARCH_DIR)) TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(ARCH_DIR)) TEST_GEN_PROGS_EXTENDED += $(TEST_GEN_PROGS_EXTENDED_$(ARCH_DIR)) @@ -204,6 +213,7 @@ endif CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \ -Wno-gnu-variable-sized-type-not-at-end -MD\ -fno-builtin-memcmp -fno-builtin-memcpy -fno-builtin-memset \ + -fno-builtin-strnlen \ -fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) \ -I$(LINUX_TOOL_ARCH_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude \ -I$(<D) -Iinclude/$(ARCH_DIR) -I ../rseq -I.. $(EXTRA_CFLAGS) \ @@ -228,11 +238,14 @@ LIBKVM_C_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_C)) LIBKVM_S_OBJ := $(patsubst %.S, $(OUTPUT)/%.o, $(LIBKVM_S)) LIBKVM_STRING_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_STRING)) LIBKVM_OBJS = $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ) $(LIBKVM_STRING_OBJ) +SPLIT_TESTS_TARGETS := $(patsubst %, $(OUTPUT)/%, $(SPLIT_TESTS)) +SPLIT_TESTS_OBJS := $(patsubst %, $(ARCH_DIR)/%.o, $(SPLIT_TESTS)) TEST_GEN_OBJ = $(patsubst %, %.o, $(TEST_GEN_PROGS)) TEST_GEN_OBJ += $(patsubst %, %.o, $(TEST_GEN_PROGS_EXTENDED)) TEST_DEP_FILES = $(patsubst %.o, %.d, $(TEST_GEN_OBJ)) TEST_DEP_FILES += $(patsubst %.o, %.d, $(LIBKVM_OBJS)) +TEST_DEP_FILES += $(patsubst %.o, %.d, $(SPLIT_TESTS_OBJS)) -include $(TEST_DEP_FILES) $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED): %: %.o @@ -240,7 +253,10 @@ $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED): %: %.o $(TEST_GEN_OBJ): $(OUTPUT)/%.o: %.c $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@ -EXTRA_CLEAN += $(LIBKVM_OBJS) $(TEST_DEP_FILES) $(TEST_GEN_OBJ) cscope.* +$(SPLIT_TESTS_TARGETS): %: %.o $(SPLIT_TESTS_OBJS) + $(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH) $^ $(LDLIBS) -o $@ + +EXTRA_CLEAN += $(LIBKVM_OBJS) $(TEST_DEP_FILES) $(TEST_GEN_OBJ) $(SPLIT_TESTS_OBJS) cscope.* x := $(shell mkdir -p $(sort $(dir $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ)))) $(LIBKVM_C_OBJ): $(OUTPUT)/%.o: %.c diff --git a/tools/testing/selftests/kvm/aarch64/aarch32_id_regs.c b/tools/testing/selftests/kvm/aarch64/aarch32_id_regs.c index 4951ac53d1f8..b90580840b22 100644 --- a/tools/testing/selftests/kvm/aarch64/aarch32_id_regs.c +++ b/tools/testing/selftests/kvm/aarch64/aarch32_id_regs.c @@ -98,7 +98,7 @@ static void test_user_raz_wi(struct kvm_vcpu *vcpu) uint64_t val; vcpu_get_reg(vcpu, reg_id, &val); - ASSERT_EQ(val, 0); + TEST_ASSERT_EQ(val, 0); /* * Expect the ioctl to succeed with no effect on the register @@ -107,7 +107,7 @@ static void test_user_raz_wi(struct kvm_vcpu *vcpu) vcpu_set_reg(vcpu, reg_id, BAD_ID_REG_VAL); vcpu_get_reg(vcpu, reg_id, &val); - ASSERT_EQ(val, 0); + TEST_ASSERT_EQ(val, 0); } } @@ -127,14 +127,14 @@ static void test_user_raz_invariant(struct kvm_vcpu *vcpu) uint64_t val; vcpu_get_reg(vcpu, reg_id, &val); - ASSERT_EQ(val, 0); + TEST_ASSERT_EQ(val, 0); r = __vcpu_set_reg(vcpu, reg_id, BAD_ID_REG_VAL); TEST_ASSERT(r < 0 && errno == EINVAL, "unexpected KVM_SET_ONE_REG error: r=%d, errno=%d", r, errno); vcpu_get_reg(vcpu, reg_id, &val); - ASSERT_EQ(val, 0); + TEST_ASSERT_EQ(val, 0); } } diff --git a/tools/testing/selftests/kvm/aarch64/arch_timer.c b/tools/testing/selftests/kvm/aarch64/arch_timer.c index 8ef370924a02..274b8465b42a 100644 --- a/tools/testing/selftests/kvm/aarch64/arch_timer.c +++ b/tools/testing/selftests/kvm/aarch64/arch_timer.c @@ -19,7 +19,6 @@ * * Copyright (c) 2021, Google LLC. */ - #define _GNU_SOURCE #include <stdlib.h> @@ -155,11 +154,13 @@ static void guest_validate_irq(unsigned int intid, xcnt_diff_us = cycles_to_usec(xcnt - shared_data->xcnt); /* Make sure we are dealing with the correct timer IRQ */ - GUEST_ASSERT_2(intid == timer_irq, intid, timer_irq); + GUEST_ASSERT_EQ(intid, timer_irq); /* Basic 'timer condition met' check */ - GUEST_ASSERT_3(xcnt >= cval, xcnt, cval, xcnt_diff_us); - GUEST_ASSERT_1(xctl & CTL_ISTATUS, xctl); + __GUEST_ASSERT(xcnt >= cval, + "xcnt = 0x%llx, cval = 0x%llx, xcnt_diff_us = 0x%llx", + xcnt, cval, xcnt_diff_us); + __GUEST_ASSERT(xctl & CTL_ISTATUS, "xcnt = 0x%llx", xcnt); WRITE_ONCE(shared_data->nr_iter, shared_data->nr_iter + 1); } @@ -192,8 +193,7 @@ static void guest_run_stage(struct test_vcpu_shared_data *shared_data, TIMER_TEST_ERR_MARGIN_US); irq_iter = READ_ONCE(shared_data->nr_iter); - GUEST_ASSERT_2(config_iter + 1 == irq_iter, - config_iter + 1, irq_iter); + GUEST_ASSERT_EQ(config_iter + 1, irq_iter); } } @@ -243,13 +243,9 @@ static void *test_vcpu_run(void *arg) break; case UCALL_ABORT: sync_global_from_guest(vm, *shared_data); - REPORT_GUEST_ASSERT_N(uc, "values: %lu, %lu; %lu, vcpu %u; stage; %u; iter: %u", - GUEST_ASSERT_ARG(uc, 0), - GUEST_ASSERT_ARG(uc, 1), - GUEST_ASSERT_ARG(uc, 2), - vcpu_idx, - shared_data->guest_stage, - shared_data->nr_iter); + fprintf(stderr, "Guest assert failed, vcpu %u; stage; %u; iter: %u\n", + vcpu_idx, shared_data->guest_stage, shared_data->nr_iter); + REPORT_GUEST_ASSERT(uc); break; default: TEST_FAIL("Unexpected guest exit\n"); diff --git a/tools/testing/selftests/kvm/aarch64/debug-exceptions.c b/tools/testing/selftests/kvm/aarch64/debug-exceptions.c index 637be796086f..f5b6cb3a0019 100644 --- a/tools/testing/selftests/kvm/aarch64/debug-exceptions.c +++ b/tools/testing/selftests/kvm/aarch64/debug-exceptions.c @@ -365,7 +365,7 @@ static void guest_wp_handler(struct ex_regs *regs) static void guest_ss_handler(struct ex_regs *regs) { - GUEST_ASSERT_1(ss_idx < 4, ss_idx); + __GUEST_ASSERT(ss_idx < 4, "Expected index < 4, got '%u'", ss_idx); ss_addr[ss_idx++] = regs->pc; regs->pstate |= SPSR_SS; } @@ -410,8 +410,8 @@ static void guest_code_ss(int test_cnt) /* Userspace disables Single Step when the end is nigh. */ asm volatile("iter_ss_end:\n"); - GUEST_ASSERT(bvr == w_bvr); - GUEST_ASSERT(wvr == w_wvr); + GUEST_ASSERT_EQ(bvr, w_bvr); + GUEST_ASSERT_EQ(wvr, w_wvr); } GUEST_DONE(); } @@ -450,7 +450,7 @@ static void test_guest_debug_exceptions(uint8_t bpn, uint8_t wpn, uint8_t ctx_bp vcpu_run(vcpu); switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - REPORT_GUEST_ASSERT_2(uc, "values: %#lx, %#lx"); + REPORT_GUEST_ASSERT(uc); break; case UCALL_DONE: goto done; diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c index 4f10055af2aa..709d7d721760 100644 --- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c +++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c @@ -4,50 +4,17 @@ * * Copyright (C) 2020, Red Hat, Inc. * - * When attempting to migrate from a host with an older kernel to a host - * with a newer kernel we allow the newer kernel on the destination to - * list new registers with get-reg-list. We assume they'll be unused, at - * least until the guest reboots, and so they're relatively harmless. - * However, if the destination host with the newer kernel is missing - * registers which the source host with the older kernel has, then that's - * a regression in get-reg-list. This test checks for that regression by - * checking the current list against a blessed list. We should never have - * missing registers, but if new ones appear then they can probably be - * added to the blessed list. A completely new blessed list can be created - * by running the test with the --list command line argument. - * - * Note, the blessed list should be created from the oldest possible - * kernel. We can't go older than v4.15, though, because that's the first - * release to expose the ID system registers in KVM_GET_REG_LIST, see - * commit 93390c0a1b20 ("arm64: KVM: Hide unsupported AArch64 CPU features - * from guests"). Also, one must use the --core-reg-fixup command line - * option when running on an older kernel that doesn't include df205b5c6328 - * ("KVM: arm64: Filter out invalid core register IDs in KVM_GET_REG_LIST") + * While the blessed list should be created from the oldest possible + * kernel, we can't go older than v5.2, though, because that's the first + * release which includes df205b5c6328 ("KVM: arm64: Filter out invalid + * core register IDs in KVM_GET_REG_LIST"). Without that commit the core + * registers won't match expectations. */ #include <stdio.h> -#include <stdlib.h> -#include <string.h> -#include <unistd.h> -#include <sys/types.h> -#include <sys/wait.h> #include "kvm_util.h" #include "test_util.h" #include "processor.h" -static struct kvm_reg_list *reg_list; -static __u64 *blessed_reg, blessed_n; - -struct reg_sublist { - const char *name; - long capability; - int feature; - bool finalize; - __u64 *regs; - __u64 regs_n; - __u64 *rejects_set; - __u64 rejects_set_n; -}; - struct feature_id_reg { __u64 reg; __u64 id_reg; @@ -76,70 +43,7 @@ static struct feature_id_reg feat_id_regs[] = { } }; -struct vcpu_config { - char *name; - struct reg_sublist sublists[]; -}; - -static struct vcpu_config *vcpu_configs[]; -static int vcpu_configs_n; - -#define for_each_sublist(c, s) \ - for ((s) = &(c)->sublists[0]; (s)->regs; ++(s)) - -#define for_each_reg(i) \ - for ((i) = 0; (i) < reg_list->n; ++(i)) - -#define for_each_reg_filtered(i) \ - for_each_reg(i) \ - if (!filter_reg(reg_list->reg[i])) - -#define for_each_missing_reg(i) \ - for ((i) = 0; (i) < blessed_n; ++(i)) \ - if (!find_reg(reg_list->reg, reg_list->n, blessed_reg[i])) \ - if (check_supported_feat_reg(vcpu, blessed_reg[i])) - -#define for_each_new_reg(i) \ - for_each_reg_filtered(i) \ - if (!find_reg(blessed_reg, blessed_n, reg_list->reg[i])) - -static const char *config_name(struct vcpu_config *c) -{ - struct reg_sublist *s; - int len = 0; - - if (c->name) - return c->name; - - for_each_sublist(c, s) - len += strlen(s->name) + 1; - - c->name = malloc(len); - - len = 0; - for_each_sublist(c, s) { - if (!strcmp(s->name, "base")) - continue; - strcat(c->name + len, s->name); - len += strlen(s->name) + 1; - c->name[len - 1] = '+'; - } - c->name[len - 1] = '\0'; - - return c->name; -} - -static bool has_cap(struct vcpu_config *c, long capability) -{ - struct reg_sublist *s; - - for_each_sublist(c, s) - if (s->capability == capability) - return true; - return false; -} - -static bool filter_reg(__u64 reg) +bool filter_reg(__u64 reg) { /* * DEMUX register presence depends on the host's CLIDR_EL1. @@ -151,16 +55,6 @@ static bool filter_reg(__u64 reg) return false; } -static bool find_reg(__u64 regs[], __u64 nr_regs, __u64 reg) -{ - int i; - - for (i = 0; i < nr_regs; ++i) - if (reg == regs[i]) - return true; - return false; -} - static bool check_supported_feat_reg(struct kvm_vcpu *vcpu, __u64 reg) { int i, ret; @@ -180,17 +74,27 @@ static bool check_supported_feat_reg(struct kvm_vcpu *vcpu, __u64 reg) return true; } -static const char *str_with_index(const char *template, __u64 index) +bool check_supported_reg(struct kvm_vcpu *vcpu, __u64 reg) { - char *str, *p; - int n; + return check_supported_feat_reg(vcpu, reg); +} - str = strdup(template); - p = strstr(str, "##"); - n = sprintf(p, "%lld", index); - strcat(p + n, strstr(template, "##") + 2); +bool check_reject_set(int err) +{ + return err == EPERM; +} - return (const char *)str; +void finalize_vcpu(struct kvm_vcpu *vcpu, struct vcpu_reg_list *c) +{ + struct vcpu_reg_sublist *s; + int feature; + + for_each_sublist(c, s) { + if (s->finalize) { + feature = s->feature; + vcpu_ioctl(vcpu, KVM_ARM_VCPU_FINALIZE, &feature); + } + } } #define REG_MASK (KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_ARM_COPROC_MASK) @@ -199,7 +103,7 @@ static const char *str_with_index(const char *template, __u64 index) #define CORE_SPSR_XX_NR_WORDS 2 #define CORE_FPREGS_XX_NR_WORDS 4 -static const char *core_id_to_str(struct vcpu_config *c, __u64 id) +static const char *core_id_to_str(const char *prefix, __u64 id) { __u64 core_off = id & ~REG_MASK, idx; @@ -210,8 +114,8 @@ static const char *core_id_to_str(struct vcpu_config *c, __u64 id) case KVM_REG_ARM_CORE_REG(regs.regs[0]) ... KVM_REG_ARM_CORE_REG(regs.regs[30]): idx = (core_off - KVM_REG_ARM_CORE_REG(regs.regs[0])) / CORE_REGS_XX_NR_WORDS; - TEST_ASSERT(idx < 31, "%s: Unexpected regs.regs index: %lld", config_name(c), idx); - return str_with_index("KVM_REG_ARM_CORE_REG(regs.regs[##])", idx); + TEST_ASSERT(idx < 31, "%s: Unexpected regs.regs index: %lld", prefix, idx); + return strdup_printf("KVM_REG_ARM_CORE_REG(regs.regs[%lld])", idx); case KVM_REG_ARM_CORE_REG(regs.sp): return "KVM_REG_ARM_CORE_REG(regs.sp)"; case KVM_REG_ARM_CORE_REG(regs.pc): @@ -225,24 +129,24 @@ static const char *core_id_to_str(struct vcpu_config *c, __u64 id) case KVM_REG_ARM_CORE_REG(spsr[0]) ... KVM_REG_ARM_CORE_REG(spsr[KVM_NR_SPSR - 1]): idx = (core_off - KVM_REG_ARM_CORE_REG(spsr[0])) / CORE_SPSR_XX_NR_WORDS; - TEST_ASSERT(idx < KVM_NR_SPSR, "%s: Unexpected spsr index: %lld", config_name(c), idx); - return str_with_index("KVM_REG_ARM_CORE_REG(spsr[##])", idx); + TEST_ASSERT(idx < KVM_NR_SPSR, "%s: Unexpected spsr index: %lld", prefix, idx); + return strdup_printf("KVM_REG_ARM_CORE_REG(spsr[%lld])", idx); case KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]) ... KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]): idx = (core_off - KVM_REG_ARM_CORE_REG(fp_regs.vregs[0])) / CORE_FPREGS_XX_NR_WORDS; - TEST_ASSERT(idx < 32, "%s: Unexpected fp_regs.vregs index: %lld", config_name(c), idx); - return str_with_index("KVM_REG_ARM_CORE_REG(fp_regs.vregs[##])", idx); + TEST_ASSERT(idx < 32, "%s: Unexpected fp_regs.vregs index: %lld", prefix, idx); + return strdup_printf("KVM_REG_ARM_CORE_REG(fp_regs.vregs[%lld])", idx); case KVM_REG_ARM_CORE_REG(fp_regs.fpsr): return "KVM_REG_ARM_CORE_REG(fp_regs.fpsr)"; case KVM_REG_ARM_CORE_REG(fp_regs.fpcr): return "KVM_REG_ARM_CORE_REG(fp_regs.fpcr)"; } - TEST_FAIL("%s: Unknown core reg id: 0x%llx", config_name(c), id); + TEST_FAIL("%s: Unknown core reg id: 0x%llx", prefix, id); return NULL; } -static const char *sve_id_to_str(struct vcpu_config *c, __u64 id) +static const char *sve_id_to_str(const char *prefix, __u64 id) { __u64 sve_off, n, i; @@ -252,37 +156,37 @@ static const char *sve_id_to_str(struct vcpu_config *c, __u64 id) sve_off = id & ~(REG_MASK | ((1ULL << 5) - 1)); i = id & (KVM_ARM64_SVE_MAX_SLICES - 1); - TEST_ASSERT(i == 0, "%s: Currently we don't expect slice > 0, reg id 0x%llx", config_name(c), id); + TEST_ASSERT(i == 0, "%s: Currently we don't expect slice > 0, reg id 0x%llx", prefix, id); switch (sve_off) { case KVM_REG_ARM64_SVE_ZREG_BASE ... KVM_REG_ARM64_SVE_ZREG_BASE + (1ULL << 5) * KVM_ARM64_SVE_NUM_ZREGS - 1: n = (id >> 5) & (KVM_ARM64_SVE_NUM_ZREGS - 1); TEST_ASSERT(id == KVM_REG_ARM64_SVE_ZREG(n, 0), - "%s: Unexpected bits set in SVE ZREG id: 0x%llx", config_name(c), id); - return str_with_index("KVM_REG_ARM64_SVE_ZREG(##, 0)", n); + "%s: Unexpected bits set in SVE ZREG id: 0x%llx", prefix, id); + return strdup_printf("KVM_REG_ARM64_SVE_ZREG(%lld, 0)", n); case KVM_REG_ARM64_SVE_PREG_BASE ... KVM_REG_ARM64_SVE_PREG_BASE + (1ULL << 5) * KVM_ARM64_SVE_NUM_PREGS - 1: n = (id >> 5) & (KVM_ARM64_SVE_NUM_PREGS - 1); TEST_ASSERT(id == KVM_REG_ARM64_SVE_PREG(n, 0), - "%s: Unexpected bits set in SVE PREG id: 0x%llx", config_name(c), id); - return str_with_index("KVM_REG_ARM64_SVE_PREG(##, 0)", n); + "%s: Unexpected bits set in SVE PREG id: 0x%llx", prefix, id); + return strdup_printf("KVM_REG_ARM64_SVE_PREG(%lld, 0)", n); case KVM_REG_ARM64_SVE_FFR_BASE: TEST_ASSERT(id == KVM_REG_ARM64_SVE_FFR(0), - "%s: Unexpected bits set in SVE FFR id: 0x%llx", config_name(c), id); + "%s: Unexpected bits set in SVE FFR id: 0x%llx", prefix, id); return "KVM_REG_ARM64_SVE_FFR(0)"; } return NULL; } -static void print_reg(struct vcpu_config *c, __u64 id) +void print_reg(const char *prefix, __u64 id) { unsigned op0, op1, crn, crm, op2; const char *reg_size = NULL; TEST_ASSERT((id & KVM_REG_ARCH_MASK) == KVM_REG_ARM64, - "%s: KVM_REG_ARM64 missing in reg id: 0x%llx", config_name(c), id); + "%s: KVM_REG_ARM64 missing in reg id: 0x%llx", prefix, id); switch (id & KVM_REG_SIZE_MASK) { case KVM_REG_SIZE_U8: @@ -314,16 +218,16 @@ static void print_reg(struct vcpu_config *c, __u64 id) break; default: TEST_FAIL("%s: Unexpected reg size: 0x%llx in reg id: 0x%llx", - config_name(c), (id & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT, id); + prefix, (id & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT, id); } switch (id & KVM_REG_ARM_COPROC_MASK) { case KVM_REG_ARM_CORE: - printf("\tKVM_REG_ARM64 | %s | KVM_REG_ARM_CORE | %s,\n", reg_size, core_id_to_str(c, id)); + printf("\tKVM_REG_ARM64 | %s | KVM_REG_ARM_CORE | %s,\n", reg_size, core_id_to_str(prefix, id)); break; case KVM_REG_ARM_DEMUX: TEST_ASSERT(!(id & ~(REG_MASK | KVM_REG_ARM_DEMUX_ID_MASK | KVM_REG_ARM_DEMUX_VAL_MASK)), - "%s: Unexpected bits set in DEMUX reg id: 0x%llx", config_name(c), id); + "%s: Unexpected bits set in DEMUX reg id: 0x%llx", prefix, id); printf("\tKVM_REG_ARM64 | %s | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | %lld,\n", reg_size, id & KVM_REG_ARM_DEMUX_VAL_MASK); break; @@ -334,370 +238,34 @@ static void print_reg(struct vcpu_config *c, __u64 id) crm = (id & KVM_REG_ARM64_SYSREG_CRM_MASK) >> KVM_REG_ARM64_SYSREG_CRM_SHIFT; op2 = (id & KVM_REG_ARM64_SYSREG_OP2_MASK) >> KVM_REG_ARM64_SYSREG_OP2_SHIFT; TEST_ASSERT(id == ARM64_SYS_REG(op0, op1, crn, crm, op2), - "%s: Unexpected bits set in SYSREG reg id: 0x%llx", config_name(c), id); + "%s: Unexpected bits set in SYSREG reg id: 0x%llx", prefix, id); printf("\tARM64_SYS_REG(%d, %d, %d, %d, %d),\n", op0, op1, crn, crm, op2); break; case KVM_REG_ARM_FW: TEST_ASSERT(id == KVM_REG_ARM_FW_REG(id & 0xffff), - "%s: Unexpected bits set in FW reg id: 0x%llx", config_name(c), id); + "%s: Unexpected bits set in FW reg id: 0x%llx", prefix, id); printf("\tKVM_REG_ARM_FW_REG(%lld),\n", id & 0xffff); break; case KVM_REG_ARM_FW_FEAT_BMAP: TEST_ASSERT(id == KVM_REG_ARM_FW_FEAT_BMAP_REG(id & 0xffff), - "%s: Unexpected bits set in the bitmap feature FW reg id: 0x%llx", config_name(c), id); + "%s: Unexpected bits set in the bitmap feature FW reg id: 0x%llx", prefix, id); printf("\tKVM_REG_ARM_FW_FEAT_BMAP_REG(%lld),\n", id & 0xffff); break; case KVM_REG_ARM64_SVE: - if (has_cap(c, KVM_CAP_ARM_SVE)) - printf("\t%s,\n", sve_id_to_str(c, id)); - else - TEST_FAIL("%s: KVM_REG_ARM64_SVE is an unexpected coproc type in reg id: 0x%llx", config_name(c), id); + printf("\t%s,\n", sve_id_to_str(prefix, id)); break; default: TEST_FAIL("%s: Unexpected coproc type: 0x%llx in reg id: 0x%llx", - config_name(c), (id & KVM_REG_ARM_COPROC_MASK) >> KVM_REG_ARM_COPROC_SHIFT, id); - } -} - -/* - * Older kernels listed each 32-bit word of CORE registers separately. - * For 64 and 128-bit registers we need to ignore the extra words. We - * also need to fixup the sizes, because the older kernels stated all - * registers were 64-bit, even when they weren't. - */ -static void core_reg_fixup(void) -{ - struct kvm_reg_list *tmp; - __u64 id, core_off; - int i; - - tmp = calloc(1, sizeof(*tmp) + reg_list->n * sizeof(__u64)); - - for (i = 0; i < reg_list->n; ++i) { - id = reg_list->reg[i]; - - if ((id & KVM_REG_ARM_COPROC_MASK) != KVM_REG_ARM_CORE) { - tmp->reg[tmp->n++] = id; - continue; - } - - core_off = id & ~REG_MASK; - - switch (core_off) { - case 0x52: case 0xd2: case 0xd6: - /* - * These offsets are pointing at padding. - * We need to ignore them too. - */ - continue; - case KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]) ... - KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]): - if (core_off & 3) - continue; - id &= ~KVM_REG_SIZE_MASK; - id |= KVM_REG_SIZE_U128; - tmp->reg[tmp->n++] = id; - continue; - case KVM_REG_ARM_CORE_REG(fp_regs.fpsr): - case KVM_REG_ARM_CORE_REG(fp_regs.fpcr): - id &= ~KVM_REG_SIZE_MASK; - id |= KVM_REG_SIZE_U32; - tmp->reg[tmp->n++] = id; - continue; - default: - if (core_off & 1) - continue; - tmp->reg[tmp->n++] = id; - break; - } + prefix, (id & KVM_REG_ARM_COPROC_MASK) >> KVM_REG_ARM_COPROC_SHIFT, id); } - - free(reg_list); - reg_list = tmp; -} - -static void prepare_vcpu_init(struct vcpu_config *c, struct kvm_vcpu_init *init) -{ - struct reg_sublist *s; - - for_each_sublist(c, s) - if (s->capability) - init->features[s->feature / 32] |= 1 << (s->feature % 32); -} - -static void finalize_vcpu(struct kvm_vcpu *vcpu, struct vcpu_config *c) -{ - struct reg_sublist *s; - int feature; - - for_each_sublist(c, s) { - if (s->finalize) { - feature = s->feature; - vcpu_ioctl(vcpu, KVM_ARM_VCPU_FINALIZE, &feature); - } - } -} - -static void check_supported(struct vcpu_config *c) -{ - struct reg_sublist *s; - - for_each_sublist(c, s) { - if (!s->capability) - continue; - - __TEST_REQUIRE(kvm_has_cap(s->capability), - "%s: %s not available, skipping tests\n", - config_name(c), s->name); - } -} - -static bool print_list; -static bool print_filtered; -static bool fixup_core_regs; - -static void run_test(struct vcpu_config *c) -{ - struct kvm_vcpu_init init = { .target = -1, }; - int new_regs = 0, missing_regs = 0, i, n; - int failed_get = 0, failed_set = 0, failed_reject = 0; - struct kvm_vcpu *vcpu; - struct kvm_vm *vm; - struct reg_sublist *s; - - check_supported(c); - - vm = vm_create_barebones(); - prepare_vcpu_init(c, &init); - vcpu = __vm_vcpu_add(vm, 0); - aarch64_vcpu_setup(vcpu, &init); - finalize_vcpu(vcpu, c); - - reg_list = vcpu_get_reg_list(vcpu); - - if (fixup_core_regs) - core_reg_fixup(); - - if (print_list || print_filtered) { - putchar('\n'); - for_each_reg(i) { - __u64 id = reg_list->reg[i]; - if ((print_list && !filter_reg(id)) || - (print_filtered && filter_reg(id))) - print_reg(c, id); - } - putchar('\n'); - return; - } - - /* - * We only test that we can get the register and then write back the - * same value. Some registers may allow other values to be written - * back, but others only allow some bits to be changed, and at least - * for ID registers set will fail if the value does not exactly match - * what was returned by get. If registers that allow other values to - * be written need to have the other values tested, then we should - * create a new set of tests for those in a new independent test - * executable. - */ - for_each_reg(i) { - uint8_t addr[2048 / 8]; - struct kvm_one_reg reg = { - .id = reg_list->reg[i], - .addr = (__u64)&addr, - }; - bool reject_reg = false; - int ret; - - ret = __vcpu_get_reg(vcpu, reg_list->reg[i], &addr); - if (ret) { - printf("%s: Failed to get ", config_name(c)); - print_reg(c, reg.id); - putchar('\n'); - ++failed_get; - } - - /* rejects_set registers are rejected after KVM_ARM_VCPU_FINALIZE */ - for_each_sublist(c, s) { - if (s->rejects_set && find_reg(s->rejects_set, s->rejects_set_n, reg.id)) { - reject_reg = true; - ret = __vcpu_ioctl(vcpu, KVM_SET_ONE_REG, ®); - if (ret != -1 || errno != EPERM) { - printf("%s: Failed to reject (ret=%d, errno=%d) ", config_name(c), ret, errno); - print_reg(c, reg.id); - putchar('\n'); - ++failed_reject; - } - break; - } - } - - if (!reject_reg) { - ret = __vcpu_ioctl(vcpu, KVM_SET_ONE_REG, ®); - if (ret) { - printf("%s: Failed to set ", config_name(c)); - print_reg(c, reg.id); - putchar('\n'); - ++failed_set; - } - } - } - - for_each_sublist(c, s) - blessed_n += s->regs_n; - blessed_reg = calloc(blessed_n, sizeof(__u64)); - - n = 0; - for_each_sublist(c, s) { - for (i = 0; i < s->regs_n; ++i) - blessed_reg[n++] = s->regs[i]; - } - - for_each_new_reg(i) - ++new_regs; - - for_each_missing_reg(i) - ++missing_regs; - - if (new_regs || missing_regs) { - n = 0; - for_each_reg_filtered(i) - ++n; - - printf("%s: Number blessed registers: %5lld\n", config_name(c), blessed_n); - printf("%s: Number registers: %5lld (includes %lld filtered registers)\n", - config_name(c), reg_list->n, reg_list->n - n); - } - - if (new_regs) { - printf("\n%s: There are %d new registers.\n" - "Consider adding them to the blessed reg " - "list with the following lines:\n\n", config_name(c), new_regs); - for_each_new_reg(i) - print_reg(c, reg_list->reg[i]); - putchar('\n'); - } - - if (missing_regs) { - printf("\n%s: There are %d missing registers.\n" - "The following lines are missing registers:\n\n", config_name(c), missing_regs); - for_each_missing_reg(i) - print_reg(c, blessed_reg[i]); - putchar('\n'); - } - - TEST_ASSERT(!missing_regs && !failed_get && !failed_set && !failed_reject, - "%s: There are %d missing registers; " - "%d registers failed get; %d registers failed set; %d registers failed reject", - config_name(c), missing_regs, failed_get, failed_set, failed_reject); - - pr_info("%s: PASS\n", config_name(c)); - blessed_n = 0; - free(blessed_reg); - free(reg_list); - kvm_vm_free(vm); -} - -static void help(void) -{ - struct vcpu_config *c; - int i; - - printf( - "\n" - "usage: get-reg-list [--config=<selection>] [--list] [--list-filtered] [--core-reg-fixup]\n\n" - " --config=<selection> Used to select a specific vcpu configuration for the test/listing\n" - " '<selection>' may be\n"); - - for (i = 0; i < vcpu_configs_n; ++i) { - c = vcpu_configs[i]; - printf( - " '%s'\n", config_name(c)); - } - - printf( - "\n" - " --list Print the register list rather than test it (requires --config)\n" - " --list-filtered Print registers that would normally be filtered out (requires --config)\n" - " --core-reg-fixup Needed when running on old kernels with broken core reg listings\n" - "\n" - ); -} - -static struct vcpu_config *parse_config(const char *config) -{ - struct vcpu_config *c; - int i; - - if (config[8] != '=') - help(), exit(1); - - for (i = 0; i < vcpu_configs_n; ++i) { - c = vcpu_configs[i]; - if (strcmp(config_name(c), &config[9]) == 0) - break; - } - - if (i == vcpu_configs_n) - help(), exit(1); - - return c; -} - -int main(int ac, char **av) -{ - struct vcpu_config *c, *sel = NULL; - int i, ret = 0; - pid_t pid; - - for (i = 1; i < ac; ++i) { - if (strcmp(av[i], "--core-reg-fixup") == 0) - fixup_core_regs = true; - else if (strncmp(av[i], "--config", 8) == 0) - sel = parse_config(av[i]); - else if (strcmp(av[i], "--list") == 0) - print_list = true; - else if (strcmp(av[i], "--list-filtered") == 0) - print_filtered = true; - else if (strcmp(av[i], "--help") == 0 || strcmp(av[1], "-h") == 0) - help(), exit(0); - else - help(), exit(1); - } - - if (print_list || print_filtered) { - /* - * We only want to print the register list of a single config. - */ - if (!sel) - help(), exit(1); - } - - for (i = 0; i < vcpu_configs_n; ++i) { - c = vcpu_configs[i]; - if (sel && c != sel) - continue; - - pid = fork(); - - if (!pid) { - run_test(c); - exit(0); - } else { - int wstatus; - pid_t wpid = wait(&wstatus); - TEST_ASSERT(wpid == pid && WIFEXITED(wstatus), "wait: Unexpected return"); - if (WEXITSTATUS(wstatus) && WEXITSTATUS(wstatus) != KSFT_SKIP) - ret = KSFT_FAIL; - } - } - - return ret; } /* - * The current blessed list was primed with the output of kernel version + * The original blessed list was primed with the output of kernel version * v4.15 with --core-reg-fixup and then later updated with new registers. + * (The --core-reg-fixup option and it's fixup function have been removed + * from the test, as it's unlikely to use this type of test on a kernel + * older than v5.2.) * * The blessed list is up to date with kernel version v6.4 (or so we hope) */ @@ -1130,14 +698,14 @@ static __u64 pauth_generic_regs[] = { .regs_n = ARRAY_SIZE(pauth_generic_regs), \ } -static struct vcpu_config vregs_config = { +static struct vcpu_reg_list vregs_config = { .sublists = { BASE_SUBLIST, VREGS_SUBLIST, {0}, }, }; -static struct vcpu_config vregs_pmu_config = { +static struct vcpu_reg_list vregs_pmu_config = { .sublists = { BASE_SUBLIST, VREGS_SUBLIST, @@ -1145,14 +713,14 @@ static struct vcpu_config vregs_pmu_config = { {0}, }, }; -static struct vcpu_config sve_config = { +static struct vcpu_reg_list sve_config = { .sublists = { BASE_SUBLIST, SVE_SUBLIST, {0}, }, }; -static struct vcpu_config sve_pmu_config = { +static struct vcpu_reg_list sve_pmu_config = { .sublists = { BASE_SUBLIST, SVE_SUBLIST, @@ -1160,7 +728,7 @@ static struct vcpu_config sve_pmu_config = { {0}, }, }; -static struct vcpu_config pauth_config = { +static struct vcpu_reg_list pauth_config = { .sublists = { BASE_SUBLIST, VREGS_SUBLIST, @@ -1168,7 +736,7 @@ static struct vcpu_config pauth_config = { {0}, }, }; -static struct vcpu_config pauth_pmu_config = { +static struct vcpu_reg_list pauth_pmu_config = { .sublists = { BASE_SUBLIST, VREGS_SUBLIST, @@ -1178,7 +746,7 @@ static struct vcpu_config pauth_pmu_config = { }, }; -static struct vcpu_config *vcpu_configs[] = { +struct vcpu_reg_list *vcpu_configs[] = { &vregs_config, &vregs_pmu_config, &sve_config, @@ -1186,4 +754,4 @@ static struct vcpu_config *vcpu_configs[] = { &pauth_config, &pauth_pmu_config, }; -static int vcpu_configs_n = ARRAY_SIZE(vcpu_configs); +int vcpu_configs_n = ARRAY_SIZE(vcpu_configs); diff --git a/tools/testing/selftests/kvm/aarch64/hypercalls.c b/tools/testing/selftests/kvm/aarch64/hypercalls.c index bef1499fb465..31f66ba97228 100644 --- a/tools/testing/selftests/kvm/aarch64/hypercalls.c +++ b/tools/testing/selftests/kvm/aarch64/hypercalls.c @@ -8,7 +8,6 @@ * hypercalls are properly masked or unmasked to the guest when disabled or * enabled from the KVM userspace, respectively. */ - #include <errno.h> #include <linux/arm-smccc.h> #include <asm/kvm.h> @@ -105,15 +104,17 @@ static void guest_test_hvc(const struct test_hvc_info *hc_info) switch (stage) { case TEST_STAGE_HVC_IFACE_FEAT_DISABLED: case TEST_STAGE_HVC_IFACE_FALSE_INFO: - GUEST_ASSERT_3(res.a0 == SMCCC_RET_NOT_SUPPORTED, - res.a0, hc_info->func_id, hc_info->arg1); + __GUEST_ASSERT(res.a0 == SMCCC_RET_NOT_SUPPORTED, + "a0 = 0x%lx, func_id = 0x%x, arg1 = 0x%llx, stage = %u", + res.a0, hc_info->func_id, hc_info->arg1, stage); break; case TEST_STAGE_HVC_IFACE_FEAT_ENABLED: - GUEST_ASSERT_3(res.a0 != SMCCC_RET_NOT_SUPPORTED, - res.a0, hc_info->func_id, hc_info->arg1); + __GUEST_ASSERT(res.a0 != SMCCC_RET_NOT_SUPPORTED, + "a0 = 0x%lx, func_id = 0x%x, arg1 = 0x%llx, stage = %u", + res.a0, hc_info->func_id, hc_info->arg1, stage); break; default: - GUEST_ASSERT_1(0, stage); + GUEST_FAIL("Unexpected stage = %u", stage); } } } @@ -132,7 +133,7 @@ static void guest_code(void) guest_test_hvc(false_hvc_info); break; default: - GUEST_ASSERT_1(0, stage); + GUEST_FAIL("Unexpected stage = %u", stage); } GUEST_SYNC(stage); @@ -290,10 +291,7 @@ static void test_run(void) guest_done = true; break; case UCALL_ABORT: - REPORT_GUEST_ASSERT_N(uc, "values: 0x%lx, 0x%lx; 0x%lx, stage: %u", - GUEST_ASSERT_ARG(uc, 0), - GUEST_ASSERT_ARG(uc, 1), - GUEST_ASSERT_ARG(uc, 2), stage); + REPORT_GUEST_ASSERT(uc); break; default: TEST_FAIL("Unexpected guest exit\n"); diff --git a/tools/testing/selftests/kvm/aarch64/page_fault_test.c b/tools/testing/selftests/kvm/aarch64/page_fault_test.c index df10f1ffa20d..47bb914ab2fa 100644 --- a/tools/testing/selftests/kvm/aarch64/page_fault_test.c +++ b/tools/testing/selftests/kvm/aarch64/page_fault_test.c @@ -7,7 +7,6 @@ * hugetlbfs with a hole). It checks that the expected handling method is * called (e.g., uffd faults with the right address and write/read flag). */ - #define _GNU_SOURCE #include <linux/bitmap.h> #include <fcntl.h> @@ -293,12 +292,12 @@ static void guest_code(struct test_desc *test) static void no_dabt_handler(struct ex_regs *regs) { - GUEST_ASSERT_1(false, read_sysreg(far_el1)); + GUEST_FAIL("Unexpected dabt, far_el1 = 0x%llx", read_sysreg(far_el1)); } static void no_iabt_handler(struct ex_regs *regs) { - GUEST_ASSERT_1(false, regs->pc); + GUEST_FAIL("Unexpected iabt, pc = 0x%lx", regs->pc); } static struct uffd_args { @@ -318,7 +317,7 @@ static int uffd_generic_handler(int uffd_mode, int uffd, struct uffd_msg *msg, TEST_ASSERT(uffd_mode == UFFDIO_REGISTER_MODE_MISSING, "The only expected UFFD mode is MISSING"); - ASSERT_EQ(addr, (uint64_t)args->hva); + TEST_ASSERT_EQ(addr, (uint64_t)args->hva); pr_debug("uffd fault: addr=%p write=%d\n", (void *)addr, !!(flags & UFFD_PAGEFAULT_FLAG_WRITE)); @@ -432,7 +431,7 @@ static void mmio_on_test_gpa_handler(struct kvm_vm *vm, struct kvm_run *run) region = vm_get_mem_region(vm, MEM_REGION_TEST_DATA); hva = (void *)region->region.userspace_addr; - ASSERT_EQ(run->mmio.phys_addr, region->region.guest_phys_addr); + TEST_ASSERT_EQ(run->mmio.phys_addr, region->region.guest_phys_addr); memcpy(hva, run->mmio.data, run->mmio.len); events.mmio_exits += 1; @@ -631,9 +630,9 @@ static void setup_default_handlers(struct test_desc *test) static void check_event_counts(struct test_desc *test) { - ASSERT_EQ(test->expected_events.uffd_faults, events.uffd_faults); - ASSERT_EQ(test->expected_events.mmio_exits, events.mmio_exits); - ASSERT_EQ(test->expected_events.fail_vcpu_runs, events.fail_vcpu_runs); + TEST_ASSERT_EQ(test->expected_events.uffd_faults, events.uffd_faults); + TEST_ASSERT_EQ(test->expected_events.mmio_exits, events.mmio_exits); + TEST_ASSERT_EQ(test->expected_events.fail_vcpu_runs, events.fail_vcpu_runs); } static void print_test_banner(enum vm_guest_mode mode, struct test_params *p) @@ -679,7 +678,7 @@ static void vcpu_run_loop(struct kvm_vm *vm, struct kvm_vcpu *vcpu, } break; case UCALL_ABORT: - REPORT_GUEST_ASSERT_2(uc, "values: %#lx, %#lx"); + REPORT_GUEST_ASSERT(uc); break; case UCALL_DONE: goto done; diff --git a/tools/testing/selftests/kvm/aarch64/vgic_irq.c b/tools/testing/selftests/kvm/aarch64/vgic_irq.c index 90d854e0fcff..2e64b4856e38 100644 --- a/tools/testing/selftests/kvm/aarch64/vgic_irq.c +++ b/tools/testing/selftests/kvm/aarch64/vgic_irq.c @@ -7,7 +7,6 @@ * host to inject a specific intid via a GUEST_SYNC call, and then checks that * it received it. */ - #include <asm/kvm.h> #include <asm/kvm_para.h> #include <sys/eventfd.h> @@ -781,7 +780,7 @@ static void test_vgic(uint32_t nr_irqs, bool level_sensitive, bool eoi_split) run_guest_cmd(vcpu, gic_fd, &inject_args, &args); break; case UCALL_ABORT: - REPORT_GUEST_ASSERT_2(uc, "values: %#lx, %#lx"); + REPORT_GUEST_ASSERT(uc); break; case UCALL_DONE: goto done; diff --git a/tools/testing/selftests/kvm/get-reg-list.c b/tools/testing/selftests/kvm/get-reg-list.c new file mode 100644 index 000000000000..be7bf5224434 --- /dev/null +++ b/tools/testing/selftests/kvm/get-reg-list.c @@ -0,0 +1,401 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Check for KVM_GET_REG_LIST regressions. + * + * Copyright (C) 2020, Red Hat, Inc. + * + * When attempting to migrate from a host with an older kernel to a host + * with a newer kernel we allow the newer kernel on the destination to + * list new registers with get-reg-list. We assume they'll be unused, at + * least until the guest reboots, and so they're relatively harmless. + * However, if the destination host with the newer kernel is missing + * registers which the source host with the older kernel has, then that's + * a regression in get-reg-list. This test checks for that regression by + * checking the current list against a blessed list. We should never have + * missing registers, but if new ones appear then they can probably be + * added to the blessed list. A completely new blessed list can be created + * by running the test with the --list command line argument. + * + * The blessed list should be created from the oldest possible kernel. + */ +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <sys/types.h> +#include <sys/wait.h> +#include "kvm_util.h" +#include "test_util.h" +#include "processor.h" + +static struct kvm_reg_list *reg_list; +static __u64 *blessed_reg, blessed_n; + +extern struct vcpu_reg_list *vcpu_configs[]; +extern int vcpu_configs_n; + +#define for_each_reg(i) \ + for ((i) = 0; (i) < reg_list->n; ++(i)) + +#define for_each_reg_filtered(i) \ + for_each_reg(i) \ + if (!filter_reg(reg_list->reg[i])) + +#define for_each_missing_reg(i) \ + for ((i) = 0; (i) < blessed_n; ++(i)) \ + if (!find_reg(reg_list->reg, reg_list->n, blessed_reg[i])) \ + if (check_supported_reg(vcpu, blessed_reg[i])) + +#define for_each_new_reg(i) \ + for_each_reg_filtered(i) \ + if (!find_reg(blessed_reg, blessed_n, reg_list->reg[i])) + +#define for_each_present_blessed_reg(i) \ + for_each_reg(i) \ + if (find_reg(blessed_reg, blessed_n, reg_list->reg[i])) + +static const char *config_name(struct vcpu_reg_list *c) +{ + struct vcpu_reg_sublist *s; + int len = 0; + + if (c->name) + return c->name; + + for_each_sublist(c, s) + len += strlen(s->name) + 1; + + c->name = malloc(len); + + len = 0; + for_each_sublist(c, s) { + if (!strcmp(s->name, "base")) + continue; + strcat(c->name + len, s->name); + len += strlen(s->name) + 1; + c->name[len - 1] = '+'; + } + c->name[len - 1] = '\0'; + + return c->name; +} + +bool __weak check_supported_reg(struct kvm_vcpu *vcpu, __u64 reg) +{ + return true; +} + +bool __weak filter_reg(__u64 reg) +{ + return false; +} + +static bool find_reg(__u64 regs[], __u64 nr_regs, __u64 reg) +{ + int i; + + for (i = 0; i < nr_regs; ++i) + if (reg == regs[i]) + return true; + return false; +} + +void __weak print_reg(const char *prefix, __u64 id) +{ + printf("\t0x%llx,\n", id); +} + +bool __weak check_reject_set(int err) +{ + return true; +} + +void __weak finalize_vcpu(struct kvm_vcpu *vcpu, struct vcpu_reg_list *c) +{ +} + +#ifdef __aarch64__ +static void prepare_vcpu_init(struct vcpu_reg_list *c, struct kvm_vcpu_init *init) +{ + struct vcpu_reg_sublist *s; + + for_each_sublist(c, s) + if (s->capability) + init->features[s->feature / 32] |= 1 << (s->feature % 32); +} + +static struct kvm_vcpu *vcpu_config_get_vcpu(struct vcpu_reg_list *c, struct kvm_vm *vm) +{ + struct kvm_vcpu_init init = { .target = -1, }; + struct kvm_vcpu *vcpu; + + prepare_vcpu_init(c, &init); + vcpu = __vm_vcpu_add(vm, 0); + aarch64_vcpu_setup(vcpu, &init); + + return vcpu; +} +#else +static struct kvm_vcpu *vcpu_config_get_vcpu(struct vcpu_reg_list *c, struct kvm_vm *vm) +{ + return __vm_vcpu_add(vm, 0); +} +#endif + +static void check_supported(struct vcpu_reg_list *c) +{ + struct vcpu_reg_sublist *s; + + for_each_sublist(c, s) { + if (!s->capability) + continue; + + __TEST_REQUIRE(kvm_has_cap(s->capability), + "%s: %s not available, skipping tests\n", + config_name(c), s->name); + } +} + +static bool print_list; +static bool print_filtered; + +static void run_test(struct vcpu_reg_list *c) +{ + int new_regs = 0, missing_regs = 0, i, n; + int failed_get = 0, failed_set = 0, failed_reject = 0; + int skipped_set = 0; + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + struct vcpu_reg_sublist *s; + + check_supported(c); + + vm = vm_create_barebones(); + vcpu = vcpu_config_get_vcpu(c, vm); + finalize_vcpu(vcpu, c); + + reg_list = vcpu_get_reg_list(vcpu); + + if (print_list || print_filtered) { + putchar('\n'); + for_each_reg(i) { + __u64 id = reg_list->reg[i]; + if ((print_list && !filter_reg(id)) || + (print_filtered && filter_reg(id))) + print_reg(config_name(c), id); + } + putchar('\n'); + return; + } + + for_each_sublist(c, s) + blessed_n += s->regs_n; + blessed_reg = calloc(blessed_n, sizeof(__u64)); + + n = 0; + for_each_sublist(c, s) { + for (i = 0; i < s->regs_n; ++i) + blessed_reg[n++] = s->regs[i]; + } + + /* + * We only test that we can get the register and then write back the + * same value. Some registers may allow other values to be written + * back, but others only allow some bits to be changed, and at least + * for ID registers set will fail if the value does not exactly match + * what was returned by get. If registers that allow other values to + * be written need to have the other values tested, then we should + * create a new set of tests for those in a new independent test + * executable. + * + * Only do the get/set tests on present, blessed list registers, + * since we don't know the capabilities of any new registers. + */ + for_each_present_blessed_reg(i) { + uint8_t addr[2048 / 8]; + struct kvm_one_reg reg = { + .id = reg_list->reg[i], + .addr = (__u64)&addr, + }; + bool reject_reg = false, skip_reg = false; + int ret; + + ret = __vcpu_get_reg(vcpu, reg_list->reg[i], &addr); + if (ret) { + printf("%s: Failed to get ", config_name(c)); + print_reg(config_name(c), reg.id); + putchar('\n'); + ++failed_get; + } + + for_each_sublist(c, s) { + /* rejects_set registers are rejected for set operation */ + if (s->rejects_set && find_reg(s->rejects_set, s->rejects_set_n, reg.id)) { + reject_reg = true; + ret = __vcpu_ioctl(vcpu, KVM_SET_ONE_REG, ®); + if (ret != -1 || !check_reject_set(errno)) { + printf("%s: Failed to reject (ret=%d, errno=%d) ", config_name(c), ret, errno); + print_reg(config_name(c), reg.id); + putchar('\n'); + ++failed_reject; + } + break; + } + + /* skips_set registers are skipped for set operation */ + if (s->skips_set && find_reg(s->skips_set, s->skips_set_n, reg.id)) { + skip_reg = true; + ++skipped_set; + break; + } + } + + if (!reject_reg && !skip_reg) { + ret = __vcpu_ioctl(vcpu, KVM_SET_ONE_REG, ®); + if (ret) { + printf("%s: Failed to set ", config_name(c)); + print_reg(config_name(c), reg.id); + putchar('\n'); + ++failed_set; + } + } + } + + for_each_new_reg(i) + ++new_regs; + + for_each_missing_reg(i) + ++missing_regs; + + if (new_regs || missing_regs) { + n = 0; + for_each_reg_filtered(i) + ++n; + + printf("%s: Number blessed registers: %5lld\n", config_name(c), blessed_n); + printf("%s: Number registers: %5lld (includes %lld filtered registers)\n", + config_name(c), reg_list->n, reg_list->n - n); + } + + if (new_regs) { + printf("\n%s: There are %d new registers.\n" + "Consider adding them to the blessed reg " + "list with the following lines:\n\n", config_name(c), new_regs); + for_each_new_reg(i) + print_reg(config_name(c), reg_list->reg[i]); + putchar('\n'); + } + + if (missing_regs) { + printf("\n%s: There are %d missing registers.\n" + "The following lines are missing registers:\n\n", config_name(c), missing_regs); + for_each_missing_reg(i) + print_reg(config_name(c), blessed_reg[i]); + putchar('\n'); + } + + TEST_ASSERT(!missing_regs && !failed_get && !failed_set && !failed_reject, + "%s: There are %d missing registers; %d registers failed get; " + "%d registers failed set; %d registers failed reject; %d registers skipped set", + config_name(c), missing_regs, failed_get, failed_set, failed_reject, skipped_set); + + pr_info("%s: PASS\n", config_name(c)); + blessed_n = 0; + free(blessed_reg); + free(reg_list); + kvm_vm_free(vm); +} + +static void help(void) +{ + struct vcpu_reg_list *c; + int i; + + printf( + "\n" + "usage: get-reg-list [--config=<selection>] [--list] [--list-filtered]\n\n" + " --config=<selection> Used to select a specific vcpu configuration for the test/listing\n" + " '<selection>' may be\n"); + + for (i = 0; i < vcpu_configs_n; ++i) { + c = vcpu_configs[i]; + printf( + " '%s'\n", config_name(c)); + } + + printf( + "\n" + " --list Print the register list rather than test it (requires --config)\n" + " --list-filtered Print registers that would normally be filtered out (requires --config)\n" + "\n" + ); +} + +static struct vcpu_reg_list *parse_config(const char *config) +{ + struct vcpu_reg_list *c = NULL; + int i; + + if (config[8] != '=') + help(), exit(1); + + for (i = 0; i < vcpu_configs_n; ++i) { + c = vcpu_configs[i]; + if (strcmp(config_name(c), &config[9]) == 0) + break; + } + + if (i == vcpu_configs_n) + help(), exit(1); + + return c; +} + +int main(int ac, char **av) +{ + struct vcpu_reg_list *c, *sel = NULL; + int i, ret = 0; + pid_t pid; + + for (i = 1; i < ac; ++i) { + if (strncmp(av[i], "--config", 8) == 0) + sel = parse_config(av[i]); + else if (strcmp(av[i], "--list") == 0) + print_list = true; + else if (strcmp(av[i], "--list-filtered") == 0) + print_filtered = true; + else if (strcmp(av[i], "--help") == 0 || strcmp(av[1], "-h") == 0) + help(), exit(0); + else + help(), exit(1); + } + + if (print_list || print_filtered) { + /* + * We only want to print the register list of a single config. + */ + if (!sel) + help(), exit(1); + } + + for (i = 0; i < vcpu_configs_n; ++i) { + c = vcpu_configs[i]; + if (sel && c != sel) + continue; + + pid = fork(); + + if (!pid) { + run_test(c); + exit(0); + } else { + int wstatus; + pid_t wpid = wait(&wstatus); + TEST_ASSERT(wpid == pid && WIFEXITED(wstatus), "wait: Unexpected return"); + if (WEXITSTATUS(wstatus) && WEXITSTATUS(wstatus) != KSFT_SKIP) + ret = KSFT_FAIL; + } + } + + return ret; +} diff --git a/tools/testing/selftests/kvm/guest_print_test.c b/tools/testing/selftests/kvm/guest_print_test.c new file mode 100644 index 000000000000..41230b746190 --- /dev/null +++ b/tools/testing/selftests/kvm/guest_print_test.c @@ -0,0 +1,219 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * A test for GUEST_PRINTF + * + * Copyright 2022, Google, Inc. and/or its affiliates. + */ +#include <fcntl.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> + +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" + +struct guest_vals { + uint64_t a; + uint64_t b; + uint64_t type; +}; + +static struct guest_vals vals; + +/* GUEST_PRINTF()/GUEST_ASSERT_FMT() does not support float or double. */ +#define TYPE_LIST \ +TYPE(test_type_i64, I64, "%ld", int64_t) \ +TYPE(test_type_u64, U64u, "%lu", uint64_t) \ +TYPE(test_type_x64, U64x, "0x%lx", uint64_t) \ +TYPE(test_type_X64, U64X, "0x%lX", uint64_t) \ +TYPE(test_type_u32, U32u, "%u", uint32_t) \ +TYPE(test_type_x32, U32x, "0x%x", uint32_t) \ +TYPE(test_type_X32, U32X, "0x%X", uint32_t) \ +TYPE(test_type_int, INT, "%d", int) \ +TYPE(test_type_char, CHAR, "%c", char) \ +TYPE(test_type_str, STR, "'%s'", const char *) \ +TYPE(test_type_ptr, PTR, "%p", uintptr_t) + +enum args_type { +#define TYPE(fn, ext, fmt_t, T) TYPE_##ext, + TYPE_LIST +#undef TYPE +}; + +static void run_test(struct kvm_vcpu *vcpu, const char *expected_printf, + const char *expected_assert); + +#define BUILD_TYPE_STRINGS_AND_HELPER(fn, ext, fmt_t, T) \ +const char *PRINTF_FMT_##ext = "Got params a = " fmt_t " and b = " fmt_t; \ +const char *ASSERT_FMT_##ext = "Expected " fmt_t ", got " fmt_t " instead"; \ +static void fn(struct kvm_vcpu *vcpu, T a, T b) \ +{ \ + char expected_printf[UCALL_BUFFER_LEN]; \ + char expected_assert[UCALL_BUFFER_LEN]; \ + \ + snprintf(expected_printf, UCALL_BUFFER_LEN, PRINTF_FMT_##ext, a, b); \ + snprintf(expected_assert, UCALL_BUFFER_LEN, ASSERT_FMT_##ext, a, b); \ + vals = (struct guest_vals){ (uint64_t)a, (uint64_t)b, TYPE_##ext }; \ + sync_global_to_guest(vcpu->vm, vals); \ + run_test(vcpu, expected_printf, expected_assert); \ +} + +#define TYPE(fn, ext, fmt_t, T) \ + BUILD_TYPE_STRINGS_AND_HELPER(fn, ext, fmt_t, T) + TYPE_LIST +#undef TYPE + +static void guest_code(void) +{ + while (1) { + switch (vals.type) { +#define TYPE(fn, ext, fmt_t, T) \ + case TYPE_##ext: \ + GUEST_PRINTF(PRINTF_FMT_##ext, vals.a, vals.b); \ + __GUEST_ASSERT(vals.a == vals.b, \ + ASSERT_FMT_##ext, vals.a, vals.b); \ + break; + TYPE_LIST +#undef TYPE + default: + GUEST_SYNC(vals.type); + } + + GUEST_DONE(); + } +} + +/* + * Unfortunately this gets a little messy because 'assert_msg' doesn't + * just contains the matching string, it also contains additional assert + * info. Fortunately the part that matches should be at the very end of + * 'assert_msg'. + */ +static void ucall_abort(const char *assert_msg, const char *expected_assert_msg) +{ + int len_str = strlen(assert_msg); + int len_substr = strlen(expected_assert_msg); + int offset = len_str - len_substr; + + TEST_ASSERT(len_substr <= len_str, + "Expected '%s' to be a substring of '%s'\n", + assert_msg, expected_assert_msg); + + TEST_ASSERT(strcmp(&assert_msg[offset], expected_assert_msg) == 0, + "Unexpected mismatch. Expected: '%s', got: '%s'", + expected_assert_msg, &assert_msg[offset]); +} + +static void run_test(struct kvm_vcpu *vcpu, const char *expected_printf, + const char *expected_assert) +{ + struct kvm_run *run = vcpu->run; + struct ucall uc; + + while (1) { + vcpu_run(vcpu); + + TEST_ASSERT(run->exit_reason == UCALL_EXIT_REASON, + "Unexpected exit reason: %u (%s),\n", + run->exit_reason, exit_reason_str(run->exit_reason)); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_SYNC: + TEST_FAIL("Unknown 'args_type' = %lu", uc.args[1]); + break; + case UCALL_PRINTF: + TEST_ASSERT(strcmp(uc.buffer, expected_printf) == 0, + "Unexpected mismatch. Expected: '%s', got: '%s'", + expected_printf, uc.buffer); + break; + case UCALL_ABORT: + ucall_abort(uc.buffer, expected_assert); + break; + case UCALL_DONE: + return; + default: + TEST_FAIL("Unknown ucall %lu", uc.cmd); + } + } +} + +static void guest_code_limits(void) +{ + char test_str[UCALL_BUFFER_LEN + 10]; + + memset(test_str, 'a', sizeof(test_str)); + test_str[sizeof(test_str) - 1] = 0; + + GUEST_PRINTF("%s", test_str); +} + +static void test_limits(void) +{ + struct kvm_vcpu *vcpu; + struct kvm_run *run; + struct kvm_vm *vm; + struct ucall uc; + + vm = vm_create_with_one_vcpu(&vcpu, guest_code_limits); + run = vcpu->run; + vcpu_run(vcpu); + + TEST_ASSERT(run->exit_reason == UCALL_EXIT_REASON, + "Unexpected exit reason: %u (%s),\n", + run->exit_reason, exit_reason_str(run->exit_reason)); + + TEST_ASSERT(get_ucall(vcpu, &uc) == UCALL_ABORT, + "Unexpected ucall command: %lu, Expected: %u (UCALL_ABORT)\n", + uc.cmd, UCALL_ABORT); + + kvm_vm_free(vm); +} + +int main(int argc, char *argv[]) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + + test_type_i64(vcpu, -1, -1); + test_type_i64(vcpu, -1, 1); + test_type_i64(vcpu, 0x1234567890abcdef, 0x1234567890abcdef); + test_type_i64(vcpu, 0x1234567890abcdef, 0x1234567890abcdee); + + test_type_u64(vcpu, 0x1234567890abcdef, 0x1234567890abcdef); + test_type_u64(vcpu, 0x1234567890abcdef, 0x1234567890abcdee); + test_type_x64(vcpu, 0x1234567890abcdef, 0x1234567890abcdef); + test_type_x64(vcpu, 0x1234567890abcdef, 0x1234567890abcdee); + test_type_X64(vcpu, 0x1234567890abcdef, 0x1234567890abcdef); + test_type_X64(vcpu, 0x1234567890abcdef, 0x1234567890abcdee); + + test_type_u32(vcpu, 0x90abcdef, 0x90abcdef); + test_type_u32(vcpu, 0x90abcdef, 0x90abcdee); + test_type_x32(vcpu, 0x90abcdef, 0x90abcdef); + test_type_x32(vcpu, 0x90abcdef, 0x90abcdee); + test_type_X32(vcpu, 0x90abcdef, 0x90abcdef); + test_type_X32(vcpu, 0x90abcdef, 0x90abcdee); + + test_type_int(vcpu, -1, -1); + test_type_int(vcpu, -1, 1); + test_type_int(vcpu, 1, 1); + + test_type_char(vcpu, 'a', 'a'); + test_type_char(vcpu, 'a', 'A'); + test_type_char(vcpu, 'a', 'b'); + + test_type_str(vcpu, "foo", "foo"); + test_type_str(vcpu, "foo", "bar"); + + test_type_ptr(vcpu, 0x1234567890abcdef, 0x1234567890abcdef); + test_type_ptr(vcpu, 0x1234567890abcdef, 0x1234567890abcdee); + + kvm_vm_free(vm); + + test_limits(); + + return 0; +} diff --git a/tools/testing/selftests/kvm/include/aarch64/arch_timer.h b/tools/testing/selftests/kvm/include/aarch64/arch_timer.h index cb7c03de3a21..b3e97525cb55 100644 --- a/tools/testing/selftests/kvm/include/aarch64/arch_timer.h +++ b/tools/testing/selftests/kvm/include/aarch64/arch_timer.h @@ -41,7 +41,7 @@ static inline uint64_t timer_get_cntct(enum arch_timer timer) case PHYSICAL: return read_sysreg(cntpct_el0); default: - GUEST_ASSERT_1(0, timer); + GUEST_FAIL("Unexpected timer type = %u", timer); } /* We should not reach here */ @@ -58,7 +58,7 @@ static inline void timer_set_cval(enum arch_timer timer, uint64_t cval) write_sysreg(cval, cntp_cval_el0); break; default: - GUEST_ASSERT_1(0, timer); + GUEST_FAIL("Unexpected timer type = %u", timer); } isb(); @@ -72,7 +72,7 @@ static inline uint64_t timer_get_cval(enum arch_timer timer) case PHYSICAL: return read_sysreg(cntp_cval_el0); default: - GUEST_ASSERT_1(0, timer); + GUEST_FAIL("Unexpected timer type = %u", timer); } /* We should not reach here */ @@ -89,7 +89,7 @@ static inline void timer_set_tval(enum arch_timer timer, uint32_t tval) write_sysreg(tval, cntp_tval_el0); break; default: - GUEST_ASSERT_1(0, timer); + GUEST_FAIL("Unexpected timer type = %u", timer); } isb(); @@ -105,7 +105,7 @@ static inline void timer_set_ctl(enum arch_timer timer, uint32_t ctl) write_sysreg(ctl, cntp_ctl_el0); break; default: - GUEST_ASSERT_1(0, timer); + GUEST_FAIL("Unexpected timer type = %u", timer); } isb(); @@ -119,7 +119,7 @@ static inline uint32_t timer_get_ctl(enum arch_timer timer) case PHYSICAL: return read_sysreg(cntp_ctl_el0); default: - GUEST_ASSERT_1(0, timer); + GUEST_FAIL("Unexpected timer type = %u", timer); } /* We should not reach here */ diff --git a/tools/testing/selftests/kvm/include/aarch64/ucall.h b/tools/testing/selftests/kvm/include/aarch64/ucall.h new file mode 100644 index 000000000000..4b68f37efd36 --- /dev/null +++ b/tools/testing/selftests/kvm/include/aarch64/ucall.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef SELFTEST_KVM_UCALL_H +#define SELFTEST_KVM_UCALL_H + +#include "kvm_util_base.h" + +#define UCALL_EXIT_REASON KVM_EXIT_MMIO + +/* + * ucall_exit_mmio_addr holds per-VM values (global data is duplicated by each + * VM), it must not be accessed from host code. + */ +extern vm_vaddr_t *ucall_exit_mmio_addr; + +static inline void ucall_arch_do_ucall(vm_vaddr_t uc) +{ + WRITE_ONCE(*ucall_exit_mmio_addr, uc); +} + +#endif diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h index eb1ff597bcca..a18db6a7b3cf 100644 --- a/tools/testing/selftests/kvm/include/kvm_util_base.h +++ b/tools/testing/selftests/kvm/include/kvm_util_base.h @@ -15,6 +15,7 @@ #include <linux/kernel.h> #include <linux/kvm.h> #include "linux/rbtree.h" +#include <linux/types.h> #include <asm/atomic.h> @@ -124,6 +125,26 @@ struct kvm_vm { uint32_t memslots[NR_MEM_REGIONS]; }; +struct vcpu_reg_sublist { + const char *name; + long capability; + int feature; + bool finalize; + __u64 *regs; + __u64 regs_n; + __u64 *rejects_set; + __u64 rejects_set_n; + __u64 *skips_set; + __u64 skips_set_n; +}; + +struct vcpu_reg_list { + char *name; + struct vcpu_reg_sublist sublists[]; +}; + +#define for_each_sublist(c, s) \ + for ((s) = &(c)->sublists[0]; (s)->regs; ++(s)) #define kvm_for_each_vcpu(vm, i, vcpu) \ for ((i) = 0; (i) <= (vm)->last_vcpu_id; (i)++) \ diff --git a/tools/testing/selftests/kvm/include/riscv/processor.h b/tools/testing/selftests/kvm/include/riscv/processor.h index d00d213c3805..5b62a3d2aa9b 100644 --- a/tools/testing/selftests/kvm/include/riscv/processor.h +++ b/tools/testing/selftests/kvm/include/riscv/processor.h @@ -38,6 +38,9 @@ static inline uint64_t __kvm_reg_id(uint64_t type, uint64_t idx, KVM_REG_RISCV_TIMER_REG(name), \ KVM_REG_SIZE_U64) +#define RISCV_ISA_EXT_REG(idx) __kvm_reg_id(KVM_REG_RISCV_ISA_EXT, \ + idx, KVM_REG_SIZE_ULONG) + /* L3 index Bit[47:39] */ #define PGTBL_L3_INDEX_MASK 0x0000FF8000000000ULL #define PGTBL_L3_INDEX_SHIFT 39 diff --git a/tools/testing/selftests/kvm/include/riscv/ucall.h b/tools/testing/selftests/kvm/include/riscv/ucall.h new file mode 100644 index 000000000000..be46eb32ec27 --- /dev/null +++ b/tools/testing/selftests/kvm/include/riscv/ucall.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef SELFTEST_KVM_UCALL_H +#define SELFTEST_KVM_UCALL_H + +#include "processor.h" + +#define UCALL_EXIT_REASON KVM_EXIT_RISCV_SBI + +static inline void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa) +{ +} + +static inline void ucall_arch_do_ucall(vm_vaddr_t uc) +{ + sbi_ecall(KVM_RISCV_SELFTESTS_SBI_EXT, + KVM_RISCV_SELFTESTS_SBI_UCALL, + uc, 0, 0, 0, 0, 0); +} + +#endif diff --git a/tools/testing/selftests/kvm/include/s390x/ucall.h b/tools/testing/selftests/kvm/include/s390x/ucall.h new file mode 100644 index 000000000000..b231bf2e49d6 --- /dev/null +++ b/tools/testing/selftests/kvm/include/s390x/ucall.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef SELFTEST_KVM_UCALL_H +#define SELFTEST_KVM_UCALL_H + +#include "kvm_util_base.h" + +#define UCALL_EXIT_REASON KVM_EXIT_S390_SIEIC + +static inline void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa) +{ +} + +static inline void ucall_arch_do_ucall(vm_vaddr_t uc) +{ + /* Exit via DIAGNOSE 0x501 (normally used for breakpoints) */ + asm volatile ("diag 0,%0,0x501" : : "a"(uc) : "memory"); +} + +#endif diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h index a6e9f215ce70..7e614adc6cf4 100644 --- a/tools/testing/selftests/kvm/include/test_util.h +++ b/tools/testing/selftests/kvm/include/test_util.h @@ -53,14 +53,13 @@ void test_assert(bool exp, const char *exp_str, #define TEST_ASSERT(e, fmt, ...) \ test_assert((e), #e, __FILE__, __LINE__, fmt, ##__VA_ARGS__) -#define ASSERT_EQ(a, b) do { \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - TEST_ASSERT(__a == __b, \ - "ASSERT_EQ(%s, %s) failed.\n" \ - "\t%s is %#lx\n" \ - "\t%s is %#lx", \ - #a, #b, #a, (unsigned long) __a, #b, (unsigned long) __b); \ +#define TEST_ASSERT_EQ(a, b) \ +do { \ + typeof(a) __a = (a); \ + typeof(b) __b = (b); \ + test_assert(__a == __b, #a " == " #b, __FILE__, __LINE__, \ + "%#lx != %#lx (%s != %s)", \ + (unsigned long)(__a), (unsigned long)(__b), #a, #b);\ } while (0) #define TEST_ASSERT_KVM_EXIT_REASON(vcpu, expected) do { \ @@ -186,4 +185,9 @@ static inline uint32_t atoi_non_negative(const char *name, const char *num_str) return num; } +int guest_vsnprintf(char *buf, int n, const char *fmt, va_list args); +int guest_snprintf(char *buf, int n, const char *fmt, ...); + +char *strdup_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2), nonnull(1))); + #endif /* SELFTEST_KVM_TEST_UTIL_H */ diff --git a/tools/testing/selftests/kvm/include/ucall_common.h b/tools/testing/selftests/kvm/include/ucall_common.h index 1a6aaef5ccae..112bc1da732a 100644 --- a/tools/testing/selftests/kvm/include/ucall_common.h +++ b/tools/testing/selftests/kvm/include/ucall_common.h @@ -7,21 +7,25 @@ #ifndef SELFTEST_KVM_UCALL_COMMON_H #define SELFTEST_KVM_UCALL_COMMON_H #include "test_util.h" +#include "ucall.h" /* Common ucalls */ enum { UCALL_NONE, UCALL_SYNC, UCALL_ABORT, + UCALL_PRINTF, UCALL_DONE, UCALL_UNHANDLED, }; #define UCALL_MAX_ARGS 7 +#define UCALL_BUFFER_LEN 1024 struct ucall { uint64_t cmd; uint64_t args[UCALL_MAX_ARGS]; + char buffer[UCALL_BUFFER_LEN]; /* Host virtual address of this struct. */ struct ucall *hva; @@ -32,8 +36,12 @@ void ucall_arch_do_ucall(vm_vaddr_t uc); void *ucall_arch_get_ucall(struct kvm_vcpu *vcpu); void ucall(uint64_t cmd, int nargs, ...); +void ucall_fmt(uint64_t cmd, const char *fmt, ...); +void ucall_assert(uint64_t cmd, const char *exp, const char *file, + unsigned int line, const char *fmt, ...); uint64_t get_ucall(struct kvm_vcpu *vcpu, struct ucall *uc); void ucall_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa); +int ucall_nr_pages_required(uint64_t page_size); /* * Perform userspace call without any associated data. This bare call avoids @@ -46,8 +54,11 @@ void ucall_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa); #define GUEST_SYNC_ARGS(stage, arg1, arg2, arg3, arg4) \ ucall(UCALL_SYNC, 6, "hello", stage, arg1, arg2, arg3, arg4) #define GUEST_SYNC(stage) ucall(UCALL_SYNC, 2, "hello", stage) +#define GUEST_PRINTF(_fmt, _args...) ucall_fmt(UCALL_PRINTF, _fmt, ##_args) #define GUEST_DONE() ucall(UCALL_DONE, 0) +#define REPORT_GUEST_PRINTF(ucall) pr_info("%s", (ucall).buffer) + enum guest_assert_builtin_args { GUEST_ERROR_STRING, GUEST_FILE, @@ -55,70 +66,41 @@ enum guest_assert_builtin_args { GUEST_ASSERT_BUILTIN_NARGS }; -#define __GUEST_ASSERT(_condition, _condstr, _nargs, _args...) \ -do { \ - if (!(_condition)) \ - ucall(UCALL_ABORT, GUEST_ASSERT_BUILTIN_NARGS + _nargs, \ - "Failed guest assert: " _condstr, \ - __FILE__, __LINE__, ##_args); \ +#define ____GUEST_ASSERT(_condition, _exp, _fmt, _args...) \ +do { \ + if (!(_condition)) \ + ucall_assert(UCALL_ABORT, _exp, __FILE__, __LINE__, _fmt, ##_args); \ } while (0) -#define GUEST_ASSERT(_condition) \ - __GUEST_ASSERT(_condition, #_condition, 0, 0) - -#define GUEST_ASSERT_1(_condition, arg1) \ - __GUEST_ASSERT(_condition, #_condition, 1, (arg1)) - -#define GUEST_ASSERT_2(_condition, arg1, arg2) \ - __GUEST_ASSERT(_condition, #_condition, 2, (arg1), (arg2)) - -#define GUEST_ASSERT_3(_condition, arg1, arg2, arg3) \ - __GUEST_ASSERT(_condition, #_condition, 3, (arg1), (arg2), (arg3)) - -#define GUEST_ASSERT_4(_condition, arg1, arg2, arg3, arg4) \ - __GUEST_ASSERT(_condition, #_condition, 4, (arg1), (arg2), (arg3), (arg4)) - -#define GUEST_ASSERT_EQ(a, b) __GUEST_ASSERT((a) == (b), #a " == " #b, 2, a, b) +#define __GUEST_ASSERT(_condition, _fmt, _args...) \ + ____GUEST_ASSERT(_condition, #_condition, _fmt, ##_args) -#define __REPORT_GUEST_ASSERT(_ucall, fmt, _args...) \ - TEST_FAIL("%s at %s:%ld\n" fmt, \ - (const char *)(_ucall).args[GUEST_ERROR_STRING], \ - (const char *)(_ucall).args[GUEST_FILE], \ - (_ucall).args[GUEST_LINE], \ - ##_args) +#define GUEST_ASSERT(_condition) \ + __GUEST_ASSERT(_condition, #_condition) -#define GUEST_ASSERT_ARG(ucall, i) ((ucall).args[GUEST_ASSERT_BUILTIN_NARGS + i]) +#define GUEST_FAIL(_fmt, _args...) \ + ucall_assert(UCALL_ABORT, "Unconditional guest failure", \ + __FILE__, __LINE__, _fmt, ##_args) -#define REPORT_GUEST_ASSERT(ucall) \ - __REPORT_GUEST_ASSERT((ucall), "") - -#define REPORT_GUEST_ASSERT_1(ucall, fmt) \ - __REPORT_GUEST_ASSERT((ucall), \ - fmt, \ - GUEST_ASSERT_ARG((ucall), 0)) - -#define REPORT_GUEST_ASSERT_2(ucall, fmt) \ - __REPORT_GUEST_ASSERT((ucall), \ - fmt, \ - GUEST_ASSERT_ARG((ucall), 0), \ - GUEST_ASSERT_ARG((ucall), 1)) - -#define REPORT_GUEST_ASSERT_3(ucall, fmt) \ - __REPORT_GUEST_ASSERT((ucall), \ - fmt, \ - GUEST_ASSERT_ARG((ucall), 0), \ - GUEST_ASSERT_ARG((ucall), 1), \ - GUEST_ASSERT_ARG((ucall), 2)) +#define GUEST_ASSERT_EQ(a, b) \ +do { \ + typeof(a) __a = (a); \ + typeof(b) __b = (b); \ + ____GUEST_ASSERT(__a == __b, #a " == " #b, "%#lx != %#lx (%s != %s)", \ + (unsigned long)(__a), (unsigned long)(__b), #a, #b); \ +} while (0) -#define REPORT_GUEST_ASSERT_4(ucall, fmt) \ - __REPORT_GUEST_ASSERT((ucall), \ - fmt, \ - GUEST_ASSERT_ARG((ucall), 0), \ - GUEST_ASSERT_ARG((ucall), 1), \ - GUEST_ASSERT_ARG((ucall), 2), \ - GUEST_ASSERT_ARG((ucall), 3)) +#define GUEST_ASSERT_NE(a, b) \ +do { \ + typeof(a) __a = (a); \ + typeof(b) __b = (b); \ + ____GUEST_ASSERT(__a != __b, #a " != " #b, "%#lx == %#lx (%s == %s)", \ + (unsigned long)(__a), (unsigned long)(__b), #a, #b); \ +} while (0) -#define REPORT_GUEST_ASSERT_N(ucall, fmt, args...) \ - __REPORT_GUEST_ASSERT((ucall), fmt, ##args) +#define REPORT_GUEST_ASSERT(ucall) \ + test_assert(false, (const char *)(ucall).args[GUEST_ERROR_STRING], \ + (const char *)(ucall).args[GUEST_FILE], \ + (ucall).args[GUEST_LINE], "%s", (ucall).buffer) #endif /* SELFTEST_KVM_UCALL_COMMON_H */ diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index aa434c8f19c5..4fd042112526 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -239,7 +239,12 @@ struct kvm_x86_cpu_property { #define X86_PROPERTY_MAX_BASIC_LEAF KVM_X86_CPU_PROPERTY(0, 0, EAX, 0, 31) #define X86_PROPERTY_PMU_VERSION KVM_X86_CPU_PROPERTY(0xa, 0, EAX, 0, 7) #define X86_PROPERTY_PMU_NR_GP_COUNTERS KVM_X86_CPU_PROPERTY(0xa, 0, EAX, 8, 15) +#define X86_PROPERTY_PMU_GP_COUNTERS_BIT_WIDTH KVM_X86_CPU_PROPERTY(0xa, 0, EAX, 16, 23) #define X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH KVM_X86_CPU_PROPERTY(0xa, 0, EAX, 24, 31) +#define X86_PROPERTY_PMU_EVENTS_MASK KVM_X86_CPU_PROPERTY(0xa, 0, EBX, 0, 7) +#define X86_PROPERTY_PMU_FIXED_COUNTERS_BITMASK KVM_X86_CPU_PROPERTY(0xa, 0, ECX, 0, 31) +#define X86_PROPERTY_PMU_NR_FIXED_COUNTERS KVM_X86_CPU_PROPERTY(0xa, 0, EDX, 0, 4) +#define X86_PROPERTY_PMU_FIXED_COUNTERS_BIT_WIDTH KVM_X86_CPU_PROPERTY(0xa, 0, EDX, 5, 12) #define X86_PROPERTY_SUPPORTED_XCR0_LO KVM_X86_CPU_PROPERTY(0xd, 0, EAX, 0, 31) #define X86_PROPERTY_XSTATE_MAX_SIZE_XCR0 KVM_X86_CPU_PROPERTY(0xd, 0, EBX, 0, 31) diff --git a/tools/testing/selftests/kvm/include/x86_64/ucall.h b/tools/testing/selftests/kvm/include/x86_64/ucall.h new file mode 100644 index 000000000000..06b244bd06ee --- /dev/null +++ b/tools/testing/selftests/kvm/include/x86_64/ucall.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef SELFTEST_KVM_UCALL_H +#define SELFTEST_KVM_UCALL_H + +#include "kvm_util_base.h" + +#define UCALL_EXIT_REASON KVM_EXIT_IO + +static inline void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa) +{ +} + +#endif diff --git a/tools/testing/selftests/kvm/kvm_page_table_test.c b/tools/testing/selftests/kvm/kvm_page_table_test.c index b3b00be1ef82..69f26d80c821 100644 --- a/tools/testing/selftests/kvm/kvm_page_table_test.c +++ b/tools/testing/selftests/kvm/kvm_page_table_test.c @@ -200,7 +200,7 @@ static void *vcpu_worker(void *data) if (READ_ONCE(host_quit)) return NULL; - clock_gettime(CLOCK_MONOTONIC_RAW, &start); + clock_gettime(CLOCK_MONOTONIC, &start); ret = _vcpu_run(vcpu); ts_diff = timespec_elapsed(start); @@ -367,7 +367,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) /* Test the stage of KVM creating mappings */ *current_stage = KVM_CREATE_MAPPINGS; - clock_gettime(CLOCK_MONOTONIC_RAW, &start); + clock_gettime(CLOCK_MONOTONIC, &start); vcpus_complete_new_stage(*current_stage); ts_diff = timespec_elapsed(start); @@ -380,7 +380,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) *current_stage = KVM_UPDATE_MAPPINGS; - clock_gettime(CLOCK_MONOTONIC_RAW, &start); + clock_gettime(CLOCK_MONOTONIC, &start); vcpus_complete_new_stage(*current_stage); ts_diff = timespec_elapsed(start); @@ -392,7 +392,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) *current_stage = KVM_ADJUST_MAPPINGS; - clock_gettime(CLOCK_MONOTONIC_RAW, &start); + clock_gettime(CLOCK_MONOTONIC, &start); vcpus_complete_new_stage(*current_stage); ts_diff = timespec_elapsed(start); diff --git a/tools/testing/selftests/kvm/lib/aarch64/ucall.c b/tools/testing/selftests/kvm/lib/aarch64/ucall.c index f212bd8ab93d..ddab0ce89d4d 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/ucall.c +++ b/tools/testing/selftests/kvm/lib/aarch64/ucall.c @@ -6,11 +6,7 @@ */ #include "kvm_util.h" -/* - * ucall_exit_mmio_addr holds per-VM values (global data is duplicated by each - * VM), it must not be accessed from host code. - */ -static vm_vaddr_t *ucall_exit_mmio_addr; +vm_vaddr_t *ucall_exit_mmio_addr; void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa) { @@ -23,11 +19,6 @@ void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa) write_guest_global(vm, ucall_exit_mmio_addr, (vm_vaddr_t *)mmio_gva); } -void ucall_arch_do_ucall(vm_vaddr_t uc) -{ - WRITE_ONCE(*ucall_exit_mmio_addr, uc); -} - void *ucall_arch_get_ucall(struct kvm_vcpu *vcpu) { struct kvm_run *run = vcpu->run; diff --git a/tools/testing/selftests/kvm/lib/guest_sprintf.c b/tools/testing/selftests/kvm/lib/guest_sprintf.c new file mode 100644 index 000000000000..c4a69d8aeb68 --- /dev/null +++ b/tools/testing/selftests/kvm/lib/guest_sprintf.c @@ -0,0 +1,307 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include "test_util.h" +#include "kvm_util.h" +#include "ucall_common.h" + +#define APPEND_BUFFER_SAFE(str, end, v) \ +do { \ + GUEST_ASSERT(str < end); \ + *str++ = (v); \ +} while (0) + +static int isdigit(int ch) +{ + return (ch >= '0') && (ch <= '9'); +} + +static int skip_atoi(const char **s) +{ + int i = 0; + + while (isdigit(**s)) + i = i * 10 + *((*s)++) - '0'; + return i; +} + +#define ZEROPAD 1 /* pad with zero */ +#define SIGN 2 /* unsigned/signed long */ +#define PLUS 4 /* show plus */ +#define SPACE 8 /* space if plus */ +#define LEFT 16 /* left justified */ +#define SMALL 32 /* Must be 32 == 0x20 */ +#define SPECIAL 64 /* 0x */ + +#define __do_div(n, base) \ +({ \ + int __res; \ + \ + __res = ((uint64_t) n) % (uint32_t) base; \ + n = ((uint64_t) n) / (uint32_t) base; \ + __res; \ +}) + +static char *number(char *str, const char *end, long num, int base, int size, + int precision, int type) +{ + /* we are called with base 8, 10 or 16, only, thus don't need "G..." */ + static const char digits[16] = "0123456789ABCDEF"; /* "GHIJKLMNOPQRSTUVWXYZ"; */ + + char tmp[66]; + char c, sign, locase; + int i; + + /* + * locase = 0 or 0x20. ORing digits or letters with 'locase' + * produces same digits or (maybe lowercased) letters + */ + locase = (type & SMALL); + if (type & LEFT) + type &= ~ZEROPAD; + if (base < 2 || base > 16) + return NULL; + c = (type & ZEROPAD) ? '0' : ' '; + sign = 0; + if (type & SIGN) { + if (num < 0) { + sign = '-'; + num = -num; + size--; + } else if (type & PLUS) { + sign = '+'; + size--; + } else if (type & SPACE) { + sign = ' '; + size--; + } + } + if (type & SPECIAL) { + if (base == 16) + size -= 2; + else if (base == 8) + size--; + } + i = 0; + if (num == 0) + tmp[i++] = '0'; + else + while (num != 0) + tmp[i++] = (digits[__do_div(num, base)] | locase); + if (i > precision) + precision = i; + size -= precision; + if (!(type & (ZEROPAD + LEFT))) + while (size-- > 0) + APPEND_BUFFER_SAFE(str, end, ' '); + if (sign) + APPEND_BUFFER_SAFE(str, end, sign); + if (type & SPECIAL) { + if (base == 8) + APPEND_BUFFER_SAFE(str, end, '0'); + else if (base == 16) { + APPEND_BUFFER_SAFE(str, end, '0'); + APPEND_BUFFER_SAFE(str, end, 'x'); + } + } + if (!(type & LEFT)) + while (size-- > 0) + APPEND_BUFFER_SAFE(str, end, c); + while (i < precision--) + APPEND_BUFFER_SAFE(str, end, '0'); + while (i-- > 0) + APPEND_BUFFER_SAFE(str, end, tmp[i]); + while (size-- > 0) + APPEND_BUFFER_SAFE(str, end, ' '); + + return str; +} + +int guest_vsnprintf(char *buf, int n, const char *fmt, va_list args) +{ + char *str, *end; + const char *s; + uint64_t num; + int i, base; + int len; + + int flags; /* flags to number() */ + + int field_width; /* width of output field */ + int precision; /* + * min. # of digits for integers; max + * number of chars for from string + */ + int qualifier; /* 'h', 'l', or 'L' for integer fields */ + + end = buf + n; + GUEST_ASSERT(buf < end); + GUEST_ASSERT(n > 0); + + for (str = buf; *fmt; ++fmt) { + if (*fmt != '%') { + APPEND_BUFFER_SAFE(str, end, *fmt); + continue; + } + + /* process flags */ + flags = 0; +repeat: + ++fmt; /* this also skips first '%' */ + switch (*fmt) { + case '-': + flags |= LEFT; + goto repeat; + case '+': + flags |= PLUS; + goto repeat; + case ' ': + flags |= SPACE; + goto repeat; + case '#': + flags |= SPECIAL; + goto repeat; + case '0': + flags |= ZEROPAD; + goto repeat; + } + + /* get field width */ + field_width = -1; + if (isdigit(*fmt)) + field_width = skip_atoi(&fmt); + else if (*fmt == '*') { + ++fmt; + /* it's the next argument */ + field_width = va_arg(args, int); + if (field_width < 0) { + field_width = -field_width; + flags |= LEFT; + } + } + + /* get the precision */ + precision = -1; + if (*fmt == '.') { + ++fmt; + if (isdigit(*fmt)) + precision = skip_atoi(&fmt); + else if (*fmt == '*') { + ++fmt; + /* it's the next argument */ + precision = va_arg(args, int); + } + if (precision < 0) + precision = 0; + } + + /* get the conversion qualifier */ + qualifier = -1; + if (*fmt == 'h' || *fmt == 'l' || *fmt == 'L') { + qualifier = *fmt; + ++fmt; + } + + /* default base */ + base = 10; + + switch (*fmt) { + case 'c': + if (!(flags & LEFT)) + while (--field_width > 0) + APPEND_BUFFER_SAFE(str, end, ' '); + APPEND_BUFFER_SAFE(str, end, + (uint8_t)va_arg(args, int)); + while (--field_width > 0) + APPEND_BUFFER_SAFE(str, end, ' '); + continue; + + case 's': + s = va_arg(args, char *); + len = strnlen(s, precision); + + if (!(flags & LEFT)) + while (len < field_width--) + APPEND_BUFFER_SAFE(str, end, ' '); + for (i = 0; i < len; ++i) + APPEND_BUFFER_SAFE(str, end, *s++); + while (len < field_width--) + APPEND_BUFFER_SAFE(str, end, ' '); + continue; + + case 'p': + if (field_width == -1) { + field_width = 2 * sizeof(void *); + flags |= SPECIAL | SMALL | ZEROPAD; + } + str = number(str, end, + (uint64_t)va_arg(args, void *), 16, + field_width, precision, flags); + continue; + + case 'n': + if (qualifier == 'l') { + long *ip = va_arg(args, long *); + *ip = (str - buf); + } else { + int *ip = va_arg(args, int *); + *ip = (str - buf); + } + continue; + + case '%': + APPEND_BUFFER_SAFE(str, end, '%'); + continue; + + /* integer number formats - set up the flags and "break" */ + case 'o': + base = 8; + break; + + case 'x': + flags |= SMALL; + case 'X': + base = 16; + break; + + case 'd': + case 'i': + flags |= SIGN; + case 'u': + break; + + default: + APPEND_BUFFER_SAFE(str, end, '%'); + if (*fmt) + APPEND_BUFFER_SAFE(str, end, *fmt); + else + --fmt; + continue; + } + if (qualifier == 'l') + num = va_arg(args, uint64_t); + else if (qualifier == 'h') { + num = (uint16_t)va_arg(args, int); + if (flags & SIGN) + num = (int16_t)num; + } else if (flags & SIGN) + num = va_arg(args, int); + else + num = va_arg(args, uint32_t); + str = number(str, end, num, base, field_width, precision, flags); + } + + GUEST_ASSERT(str < end); + *str = '\0'; + return str - buf; +} + +int guest_snprintf(char *buf, int n, const char *fmt, ...) +{ + va_list va; + int len; + + va_start(va, fmt); + len = guest_vsnprintf(buf, n, fmt, va); + va_end(va); + + return len; +} diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 9741a7ff6380..7a8af1821f5d 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -312,6 +312,7 @@ static uint64_t vm_nr_pages_required(enum vm_guest_mode mode, uint32_t nr_runnable_vcpus, uint64_t extra_mem_pages) { + uint64_t page_size = vm_guest_mode_params[mode].page_size; uint64_t nr_pages; TEST_ASSERT(nr_runnable_vcpus, @@ -340,6 +341,9 @@ static uint64_t vm_nr_pages_required(enum vm_guest_mode mode, */ nr_pages += (nr_pages + extra_mem_pages) / PTES_PER_MIN_PAGE * 2; + /* Account for the number of pages needed by ucall. */ + nr_pages += ucall_nr_pages_required(page_size); + return vm_adjust_num_guest_pages(mode, nr_pages); } @@ -994,7 +998,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, if (src_type == VM_MEM_SRC_ANONYMOUS_THP) alignment = max(backing_src_pagesz, alignment); - ASSERT_EQ(guest_paddr, align_up(guest_paddr, backing_src_pagesz)); + TEST_ASSERT_EQ(guest_paddr, align_up(guest_paddr, backing_src_pagesz)); /* Add enough memory to align up if necessary */ if (alignment > 1) diff --git a/tools/testing/selftests/kvm/lib/riscv/ucall.c b/tools/testing/selftests/kvm/lib/riscv/ucall.c index 9a3476a2dfca..fe6d1004f018 100644 --- a/tools/testing/selftests/kvm/lib/riscv/ucall.c +++ b/tools/testing/selftests/kvm/lib/riscv/ucall.c @@ -10,10 +10,6 @@ #include "kvm_util.h" #include "processor.h" -void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa) -{ -} - struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0, unsigned long arg1, unsigned long arg2, unsigned long arg3, unsigned long arg4, @@ -40,13 +36,6 @@ struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0, return ret; } -void ucall_arch_do_ucall(vm_vaddr_t uc) -{ - sbi_ecall(KVM_RISCV_SELFTESTS_SBI_EXT, - KVM_RISCV_SELFTESTS_SBI_UCALL, - uc, 0, 0, 0, 0, 0); -} - void *ucall_arch_get_ucall(struct kvm_vcpu *vcpu) { struct kvm_run *run = vcpu->run; diff --git a/tools/testing/selftests/kvm/lib/s390x/ucall.c b/tools/testing/selftests/kvm/lib/s390x/ucall.c index a7f02dc372cf..cca98734653d 100644 --- a/tools/testing/selftests/kvm/lib/s390x/ucall.c +++ b/tools/testing/selftests/kvm/lib/s390x/ucall.c @@ -6,16 +6,6 @@ */ #include "kvm_util.h" -void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa) -{ -} - -void ucall_arch_do_ucall(vm_vaddr_t uc) -{ - /* Exit via DIAGNOSE 0x501 (normally used for breakpoints) */ - asm volatile ("diag 0,%0,0x501" : : "a"(uc) : "memory"); -} - void *ucall_arch_get_ucall(struct kvm_vcpu *vcpu) { struct kvm_run *run = vcpu->run; diff --git a/tools/testing/selftests/kvm/lib/sparsebit.c b/tools/testing/selftests/kvm/lib/sparsebit.c index 50e0cf41a7dd..88cb6b84e6f3 100644 --- a/tools/testing/selftests/kvm/lib/sparsebit.c +++ b/tools/testing/selftests/kvm/lib/sparsebit.c @@ -634,7 +634,6 @@ static void node_reduce(struct sparsebit *s, struct node *nodep) tmp = node_prev(s, nodep); node_rm(s, nodep); - nodep = NULL; nodep = tmp; reduction_performed = true; diff --git a/tools/testing/selftests/kvm/lib/string_override.c b/tools/testing/selftests/kvm/lib/string_override.c index 632398adc229..5d1c87277c49 100644 --- a/tools/testing/selftests/kvm/lib/string_override.c +++ b/tools/testing/selftests/kvm/lib/string_override.c @@ -37,3 +37,12 @@ void *memset(void *s, int c, size_t count) *xs++ = c; return s; } + +size_t strnlen(const char *s, size_t count) +{ + const char *sc; + + for (sc = s; count-- && *sc != '\0'; ++sc) + /* nothing */; + return sc - s; +} diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c index b772193f6c18..3e36019eeb4a 100644 --- a/tools/testing/selftests/kvm/lib/test_util.c +++ b/tools/testing/selftests/kvm/lib/test_util.c @@ -5,6 +5,9 @@ * Copyright (C) 2020, Google LLC. */ +#define _GNU_SOURCE +#include <stdio.h> +#include <stdarg.h> #include <assert.h> #include <ctype.h> #include <limits.h> @@ -377,3 +380,15 @@ int atoi_paranoid(const char *num_str) return num; } + +char *strdup_printf(const char *fmt, ...) +{ + va_list ap; + char *str; + + va_start(ap, fmt); + vasprintf(&str, fmt, ap); + va_end(ap); + + return str; +} diff --git a/tools/testing/selftests/kvm/lib/ucall_common.c b/tools/testing/selftests/kvm/lib/ucall_common.c index 2f0e2ea941cc..816a3fa109bf 100644 --- a/tools/testing/selftests/kvm/lib/ucall_common.c +++ b/tools/testing/selftests/kvm/lib/ucall_common.c @@ -11,6 +11,11 @@ struct ucall_header { struct ucall ucalls[KVM_MAX_VCPUS]; }; +int ucall_nr_pages_required(uint64_t page_size) +{ + return align_up(sizeof(struct ucall_header), page_size) / page_size; +} + /* * ucall_pool holds per-VM values (global data is duplicated by each VM), it * must not be accessed from host code. @@ -70,6 +75,45 @@ static void ucall_free(struct ucall *uc) clear_bit(uc - ucall_pool->ucalls, ucall_pool->in_use); } +void ucall_assert(uint64_t cmd, const char *exp, const char *file, + unsigned int line, const char *fmt, ...) +{ + struct ucall *uc; + va_list va; + + uc = ucall_alloc(); + uc->cmd = cmd; + + WRITE_ONCE(uc->args[GUEST_ERROR_STRING], (uint64_t)(exp)); + WRITE_ONCE(uc->args[GUEST_FILE], (uint64_t)(file)); + WRITE_ONCE(uc->args[GUEST_LINE], line); + + va_start(va, fmt); + guest_vsnprintf(uc->buffer, UCALL_BUFFER_LEN, fmt, va); + va_end(va); + + ucall_arch_do_ucall((vm_vaddr_t)uc->hva); + + ucall_free(uc); +} + +void ucall_fmt(uint64_t cmd, const char *fmt, ...) +{ + struct ucall *uc; + va_list va; + + uc = ucall_alloc(); + uc->cmd = cmd; + + va_start(va, fmt); + guest_vsnprintf(uc->buffer, UCALL_BUFFER_LEN, fmt, va); + va_end(va); + + ucall_arch_do_ucall((vm_vaddr_t)uc->hva); + + ucall_free(uc); +} + void ucall(uint64_t cmd, int nargs, ...) { struct ucall *uc; diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index d4a0b504b1e0..d8288374078e 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -1074,11 +1074,6 @@ static bool kvm_fixup_exception(struct ex_regs *regs) return true; } -void kvm_exit_unexpected_vector(uint32_t value) -{ - ucall(UCALL_UNHANDLED, 1, value); -} - void route_exception(struct ex_regs *regs) { typedef void(*handler)(struct ex_regs *); @@ -1092,7 +1087,10 @@ void route_exception(struct ex_regs *regs) if (kvm_fixup_exception(regs)) return; - kvm_exit_unexpected_vector(regs->vector); + ucall_assert(UCALL_UNHANDLED, + "Unhandled exception in guest", __FILE__, __LINE__, + "Unhandled exception '0x%lx' at guest RIP '0x%lx'", + regs->vector, regs->rip); } void vm_init_descriptor_tables(struct kvm_vm *vm) @@ -1135,12 +1133,8 @@ void assert_on_unhandled_exception(struct kvm_vcpu *vcpu) { struct ucall uc; - if (get_ucall(vcpu, &uc) == UCALL_UNHANDLED) { - uint64_t vector = uc.args[0]; - - TEST_FAIL("Unexpected vectored event in guest (vector:0x%lx)", - vector); - } + if (get_ucall(vcpu, &uc) == UCALL_UNHANDLED) + REPORT_GUEST_ASSERT(uc); } const struct kvm_cpuid_entry2 *get_cpuid_entry(const struct kvm_cpuid2 *cpuid, diff --git a/tools/testing/selftests/kvm/lib/x86_64/ucall.c b/tools/testing/selftests/kvm/lib/x86_64/ucall.c index 4d41dc63cc9e..1265cecc7dd1 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/ucall.c +++ b/tools/testing/selftests/kvm/lib/x86_64/ucall.c @@ -8,14 +8,38 @@ #define UCALL_PIO_PORT ((uint16_t)0x1000) -void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa) -{ -} - void ucall_arch_do_ucall(vm_vaddr_t uc) { - asm volatile("in %[port], %%al" - : : [port] "d" (UCALL_PIO_PORT), "D" (uc) : "rax", "memory"); + /* + * FIXME: Revert this hack (the entire commit that added it) once nVMX + * preserves L2 GPRs across a nested VM-Exit. If a ucall from L2, e.g. + * to do a GUEST_SYNC(), lands the vCPU in L1, any and all GPRs can be + * clobbered by L1. Save and restore non-volatile GPRs (clobbering RBP + * in particular is problematic) along with RDX and RDI (which are + * inputs), and clobber volatile GPRs. *sigh* + */ +#define HORRIFIC_L2_UCALL_CLOBBER_HACK \ + "rcx", "rsi", "r8", "r9", "r10", "r11" + + asm volatile("push %%rbp\n\t" + "push %%r15\n\t" + "push %%r14\n\t" + "push %%r13\n\t" + "push %%r12\n\t" + "push %%rbx\n\t" + "push %%rdx\n\t" + "push %%rdi\n\t" + "in %[port], %%al\n\t" + "pop %%rdi\n\t" + "pop %%rdx\n\t" + "pop %%rbx\n\t" + "pop %%r12\n\t" + "pop %%r13\n\t" + "pop %%r14\n\t" + "pop %%r15\n\t" + "pop %%rbp\n\t" + : : [port] "d" (UCALL_PIO_PORT), "D" (uc) : "rax", "memory", + HORRIFIC_L2_UCALL_CLOBBER_HACK); } void *ucall_arch_get_ucall(struct kvm_vcpu *vcpu) diff --git a/tools/testing/selftests/kvm/max_guest_memory_test.c b/tools/testing/selftests/kvm/max_guest_memory_test.c index feaf2be20ff2..6628dc4dda89 100644 --- a/tools/testing/selftests/kvm/max_guest_memory_test.c +++ b/tools/testing/selftests/kvm/max_guest_memory_test.c @@ -55,7 +55,7 @@ static void rendezvous_with_boss(void) static void run_vcpu(struct kvm_vcpu *vcpu) { vcpu_run(vcpu); - ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_DONE); + TEST_ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_DONE); } static void *vcpu_worker(void *data) diff --git a/tools/testing/selftests/kvm/memslot_perf_test.c b/tools/testing/selftests/kvm/memslot_perf_test.c index 4210cd21d159..20eb2e730800 100644 --- a/tools/testing/selftests/kvm/memslot_perf_test.c +++ b/tools/testing/selftests/kvm/memslot_perf_test.c @@ -157,7 +157,7 @@ static void *vcpu_worker(void *__data) goto done; break; case UCALL_ABORT: - REPORT_GUEST_ASSERT_1(uc, "val = %lu"); + REPORT_GUEST_ASSERT(uc); break; case UCALL_DONE: goto done; @@ -560,7 +560,7 @@ static void guest_code_test_memslot_rw(void) ptr < MEM_TEST_GPA + MEM_TEST_SIZE; ptr += page_size) { uint64_t val = *(uint64_t *)ptr; - GUEST_ASSERT_1(val == MEM_TEST_VAL_2, val); + GUEST_ASSERT_EQ(val, MEM_TEST_VAL_2); *(uint64_t *)ptr = 0; } diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c new file mode 100644 index 000000000000..d8ecacd03ecf --- /dev/null +++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c @@ -0,0 +1,872 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Check for KVM_GET_REG_LIST regressions. + * + * Copyright (c) 2023 Intel Corporation + * + */ +#include <stdio.h> +#include "kvm_util.h" +#include "test_util.h" +#include "processor.h" + +#define REG_MASK (KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK) + +bool filter_reg(__u64 reg) +{ + /* + * Some ISA extensions are optional and not present on all host, + * but they can't be disabled through ISA_EXT registers when present. + * So, to make life easy, just filtering out these kind of registers. + */ + switch (reg & ~REG_MASK) { + case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SSTC: + case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SVINVAL: + case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZIHINTPAUSE: + case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZBB: + case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SSAIA: + case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZBA: + case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZBS: + case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICNTR: + case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICSR: + case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZIFENCEI: + case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZIHPM: + return true; + default: + break; + } + + return false; +} + +bool check_reject_set(int err) +{ + return err == EINVAL; +} + +static inline bool vcpu_has_ext(struct kvm_vcpu *vcpu, int ext) +{ + int ret; + unsigned long value; + + ret = __vcpu_get_reg(vcpu, RISCV_ISA_EXT_REG(ext), &value); + if (ret) { + printf("Failed to get ext %d", ext); + return false; + } + + return !!value; +} + +void finalize_vcpu(struct kvm_vcpu *vcpu, struct vcpu_reg_list *c) +{ + struct vcpu_reg_sublist *s; + + /* + * Disable all extensions which were enabled by default + * if they were available in the risc-v host. + */ + for (int i = 0; i < KVM_RISCV_ISA_EXT_MAX; i++) + __vcpu_set_reg(vcpu, RISCV_ISA_EXT_REG(i), 0); + + for_each_sublist(c, s) { + if (!s->feature) + continue; + + /* Try to enable the desired extension */ + __vcpu_set_reg(vcpu, RISCV_ISA_EXT_REG(s->feature), 1); + + /* Double check whether the desired extension was enabled */ + __TEST_REQUIRE(vcpu_has_ext(vcpu, s->feature), + "%s not available, skipping tests\n", s->name); + } +} + +static const char *config_id_to_str(__u64 id) +{ + /* reg_off is the offset into struct kvm_riscv_config */ + __u64 reg_off = id & ~(REG_MASK | KVM_REG_RISCV_CONFIG); + + switch (reg_off) { + case KVM_REG_RISCV_CONFIG_REG(isa): + return "KVM_REG_RISCV_CONFIG_REG(isa)"; + case KVM_REG_RISCV_CONFIG_REG(zicbom_block_size): + return "KVM_REG_RISCV_CONFIG_REG(zicbom_block_size)"; + case KVM_REG_RISCV_CONFIG_REG(zicboz_block_size): + return "KVM_REG_RISCV_CONFIG_REG(zicboz_block_size)"; + case KVM_REG_RISCV_CONFIG_REG(mvendorid): + return "KVM_REG_RISCV_CONFIG_REG(mvendorid)"; + case KVM_REG_RISCV_CONFIG_REG(marchid): + return "KVM_REG_RISCV_CONFIG_REG(marchid)"; + case KVM_REG_RISCV_CONFIG_REG(mimpid): + return "KVM_REG_RISCV_CONFIG_REG(mimpid)"; + case KVM_REG_RISCV_CONFIG_REG(satp_mode): + return "KVM_REG_RISCV_CONFIG_REG(satp_mode)"; + } + + /* + * Config regs would grow regularly with new pseudo reg added, so + * just show raw id to indicate a new pseudo config reg. + */ + return strdup_printf("KVM_REG_RISCV_CONFIG_REG(%lld) /* UNKNOWN */", reg_off); +} + +static const char *core_id_to_str(const char *prefix, __u64 id) +{ + /* reg_off is the offset into struct kvm_riscv_core */ + __u64 reg_off = id & ~(REG_MASK | KVM_REG_RISCV_CORE); + + switch (reg_off) { + case KVM_REG_RISCV_CORE_REG(regs.pc): + return "KVM_REG_RISCV_CORE_REG(regs.pc)"; + case KVM_REG_RISCV_CORE_REG(regs.ra): + return "KVM_REG_RISCV_CORE_REG(regs.ra)"; + case KVM_REG_RISCV_CORE_REG(regs.sp): + return "KVM_REG_RISCV_CORE_REG(regs.sp)"; + case KVM_REG_RISCV_CORE_REG(regs.gp): + return "KVM_REG_RISCV_CORE_REG(regs.gp)"; + case KVM_REG_RISCV_CORE_REG(regs.tp): + return "KVM_REG_RISCV_CORE_REG(regs.tp)"; + case KVM_REG_RISCV_CORE_REG(regs.t0) ... KVM_REG_RISCV_CORE_REG(regs.t2): + return strdup_printf("KVM_REG_RISCV_CORE_REG(regs.t%lld)", + reg_off - KVM_REG_RISCV_CORE_REG(regs.t0)); + case KVM_REG_RISCV_CORE_REG(regs.s0) ... KVM_REG_RISCV_CORE_REG(regs.s1): + return strdup_printf("KVM_REG_RISCV_CORE_REG(regs.s%lld)", + reg_off - KVM_REG_RISCV_CORE_REG(regs.s0)); + case KVM_REG_RISCV_CORE_REG(regs.a0) ... KVM_REG_RISCV_CORE_REG(regs.a7): + return strdup_printf("KVM_REG_RISCV_CORE_REG(regs.a%lld)", + reg_off - KVM_REG_RISCV_CORE_REG(regs.a0)); + case KVM_REG_RISCV_CORE_REG(regs.s2) ... KVM_REG_RISCV_CORE_REG(regs.s11): + return strdup_printf("KVM_REG_RISCV_CORE_REG(regs.s%lld)", + reg_off - KVM_REG_RISCV_CORE_REG(regs.s2) + 2); + case KVM_REG_RISCV_CORE_REG(regs.t3) ... KVM_REG_RISCV_CORE_REG(regs.t6): + return strdup_printf("KVM_REG_RISCV_CORE_REG(regs.t%lld)", + reg_off - KVM_REG_RISCV_CORE_REG(regs.t3) + 3); + case KVM_REG_RISCV_CORE_REG(mode): + return "KVM_REG_RISCV_CORE_REG(mode)"; + } + + TEST_FAIL("%s: Unknown core reg id: 0x%llx", prefix, id); + return NULL; +} + +#define RISCV_CSR_GENERAL(csr) \ + "KVM_REG_RISCV_CSR_GENERAL | KVM_REG_RISCV_CSR_REG(" #csr ")" +#define RISCV_CSR_AIA(csr) \ + "KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_REG(" #csr ")" + +static const char *general_csr_id_to_str(__u64 reg_off) +{ + /* reg_off is the offset into struct kvm_riscv_csr */ + switch (reg_off) { + case KVM_REG_RISCV_CSR_REG(sstatus): + return RISCV_CSR_GENERAL(sstatus); + case KVM_REG_RISCV_CSR_REG(sie): + return RISCV_CSR_GENERAL(sie); + case KVM_REG_RISCV_CSR_REG(stvec): + return RISCV_CSR_GENERAL(stvec); + case KVM_REG_RISCV_CSR_REG(sscratch): + return RISCV_CSR_GENERAL(sscratch); + case KVM_REG_RISCV_CSR_REG(sepc): + return RISCV_CSR_GENERAL(sepc); + case KVM_REG_RISCV_CSR_REG(scause): + return RISCV_CSR_GENERAL(scause); + case KVM_REG_RISCV_CSR_REG(stval): + return RISCV_CSR_GENERAL(stval); + case KVM_REG_RISCV_CSR_REG(sip): + return RISCV_CSR_GENERAL(sip); + case KVM_REG_RISCV_CSR_REG(satp): + return RISCV_CSR_GENERAL(satp); + case KVM_REG_RISCV_CSR_REG(scounteren): + return RISCV_CSR_GENERAL(scounteren); + } + + TEST_FAIL("Unknown general csr reg: 0x%llx", reg_off); + return NULL; +} + +static const char *aia_csr_id_to_str(__u64 reg_off) +{ + /* reg_off is the offset into struct kvm_riscv_aia_csr */ + switch (reg_off) { + case KVM_REG_RISCV_CSR_AIA_REG(siselect): + return RISCV_CSR_AIA(siselect); + case KVM_REG_RISCV_CSR_AIA_REG(iprio1): + return RISCV_CSR_AIA(iprio1); + case KVM_REG_RISCV_CSR_AIA_REG(iprio2): + return RISCV_CSR_AIA(iprio2); + case KVM_REG_RISCV_CSR_AIA_REG(sieh): + return RISCV_CSR_AIA(sieh); + case KVM_REG_RISCV_CSR_AIA_REG(siph): + return RISCV_CSR_AIA(siph); + case KVM_REG_RISCV_CSR_AIA_REG(iprio1h): + return RISCV_CSR_AIA(iprio1h); + case KVM_REG_RISCV_CSR_AIA_REG(iprio2h): + return RISCV_CSR_AIA(iprio2h); + } + + TEST_FAIL("Unknown aia csr reg: 0x%llx", reg_off); + return NULL; +} + +static const char *csr_id_to_str(const char *prefix, __u64 id) +{ + __u64 reg_off = id & ~(REG_MASK | KVM_REG_RISCV_CSR); + __u64 reg_subtype = reg_off & KVM_REG_RISCV_SUBTYPE_MASK; + + reg_off &= ~KVM_REG_RISCV_SUBTYPE_MASK; + + switch (reg_subtype) { + case KVM_REG_RISCV_CSR_GENERAL: + return general_csr_id_to_str(reg_off); + case KVM_REG_RISCV_CSR_AIA: + return aia_csr_id_to_str(reg_off); + } + + TEST_FAIL("%s: Unknown csr subtype: 0x%llx", prefix, reg_subtype); + return NULL; +} + +static const char *timer_id_to_str(const char *prefix, __u64 id) +{ + /* reg_off is the offset into struct kvm_riscv_timer */ + __u64 reg_off = id & ~(REG_MASK | KVM_REG_RISCV_TIMER); + + switch (reg_off) { + case KVM_REG_RISCV_TIMER_REG(frequency): + return "KVM_REG_RISCV_TIMER_REG(frequency)"; + case KVM_REG_RISCV_TIMER_REG(time): + return "KVM_REG_RISCV_TIMER_REG(time)"; + case KVM_REG_RISCV_TIMER_REG(compare): + return "KVM_REG_RISCV_TIMER_REG(compare)"; + case KVM_REG_RISCV_TIMER_REG(state): + return "KVM_REG_RISCV_TIMER_REG(state)"; + } + + TEST_FAIL("%s: Unknown timer reg id: 0x%llx", prefix, id); + return NULL; +} + +static const char *fp_f_id_to_str(const char *prefix, __u64 id) +{ + /* reg_off is the offset into struct __riscv_f_ext_state */ + __u64 reg_off = id & ~(REG_MASK | KVM_REG_RISCV_FP_F); + + switch (reg_off) { + case KVM_REG_RISCV_FP_F_REG(f[0]) ... + KVM_REG_RISCV_FP_F_REG(f[31]): + return strdup_printf("KVM_REG_RISCV_FP_F_REG(f[%lld])", reg_off); + case KVM_REG_RISCV_FP_F_REG(fcsr): + return "KVM_REG_RISCV_FP_F_REG(fcsr)"; + } + + TEST_FAIL("%s: Unknown fp_f reg id: 0x%llx", prefix, id); + return NULL; +} + +static const char *fp_d_id_to_str(const char *prefix, __u64 id) +{ + /* reg_off is the offset into struct __riscv_d_ext_state */ + __u64 reg_off = id & ~(REG_MASK | KVM_REG_RISCV_FP_D); + + switch (reg_off) { + case KVM_REG_RISCV_FP_D_REG(f[0]) ... + KVM_REG_RISCV_FP_D_REG(f[31]): + return strdup_printf("KVM_REG_RISCV_FP_D_REG(f[%lld])", reg_off); + case KVM_REG_RISCV_FP_D_REG(fcsr): + return "KVM_REG_RISCV_FP_D_REG(fcsr)"; + } + + TEST_FAIL("%s: Unknown fp_d reg id: 0x%llx", prefix, id); + return NULL; +} + +static const char *isa_ext_id_to_str(__u64 id) +{ + /* reg_off is the offset into unsigned long kvm_isa_ext_arr[] */ + __u64 reg_off = id & ~(REG_MASK | KVM_REG_RISCV_ISA_EXT); + + static const char * const kvm_isa_ext_reg_name[] = { + "KVM_RISCV_ISA_EXT_A", + "KVM_RISCV_ISA_EXT_C", + "KVM_RISCV_ISA_EXT_D", + "KVM_RISCV_ISA_EXT_F", + "KVM_RISCV_ISA_EXT_H", + "KVM_RISCV_ISA_EXT_I", + "KVM_RISCV_ISA_EXT_M", + "KVM_RISCV_ISA_EXT_SVPBMT", + "KVM_RISCV_ISA_EXT_SSTC", + "KVM_RISCV_ISA_EXT_SVINVAL", + "KVM_RISCV_ISA_EXT_ZIHINTPAUSE", + "KVM_RISCV_ISA_EXT_ZICBOM", + "KVM_RISCV_ISA_EXT_ZICBOZ", + "KVM_RISCV_ISA_EXT_ZBB", + "KVM_RISCV_ISA_EXT_SSAIA", + "KVM_RISCV_ISA_EXT_V", + "KVM_RISCV_ISA_EXT_SVNAPOT", + "KVM_RISCV_ISA_EXT_ZBA", + "KVM_RISCV_ISA_EXT_ZBS", + "KVM_RISCV_ISA_EXT_ZICNTR", + "KVM_RISCV_ISA_EXT_ZICSR", + "KVM_RISCV_ISA_EXT_ZIFENCEI", + "KVM_RISCV_ISA_EXT_ZIHPM", + }; + + if (reg_off >= ARRAY_SIZE(kvm_isa_ext_reg_name)) { + /* + * isa_ext regs would grow regularly with new isa extension added, so + * just show "reg" to indicate a new extension. + */ + return strdup_printf("%lld /* UNKNOWN */", reg_off); + } + + return kvm_isa_ext_reg_name[reg_off]; +} + +static const char *sbi_ext_single_id_to_str(__u64 reg_off) +{ + /* reg_off is KVM_RISCV_SBI_EXT_ID */ + static const char * const kvm_sbi_ext_reg_name[] = { + "KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_V01", + "KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_TIME", + "KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_IPI", + "KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_RFENCE", + "KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_SRST", + "KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_HSM", + "KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_PMU", + "KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_EXPERIMENTAL", + "KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_VENDOR", + }; + + if (reg_off >= ARRAY_SIZE(kvm_sbi_ext_reg_name)) { + /* + * sbi_ext regs would grow regularly with new sbi extension added, so + * just show "reg" to indicate a new extension. + */ + return strdup_printf("KVM_REG_RISCV_SBI_SINGLE | %lld /* UNKNOWN */", reg_off); + } + + return kvm_sbi_ext_reg_name[reg_off]; +} + +static const char *sbi_ext_multi_id_to_str(__u64 reg_subtype, __u64 reg_off) +{ + if (reg_off > KVM_REG_RISCV_SBI_MULTI_REG_LAST) { + /* + * sbi_ext regs would grow regularly with new sbi extension added, so + * just show "reg" to indicate a new extension. + */ + return strdup_printf("%lld /* UNKNOWN */", reg_off); + } + + switch (reg_subtype) { + case KVM_REG_RISCV_SBI_MULTI_EN: + return strdup_printf("KVM_REG_RISCV_SBI_MULTI_EN | %lld", reg_off); + case KVM_REG_RISCV_SBI_MULTI_DIS: + return strdup_printf("KVM_REG_RISCV_SBI_MULTI_DIS | %lld", reg_off); + } + + return NULL; +} + +static const char *sbi_ext_id_to_str(const char *prefix, __u64 id) +{ + __u64 reg_off = id & ~(REG_MASK | KVM_REG_RISCV_SBI_EXT); + __u64 reg_subtype = reg_off & KVM_REG_RISCV_SUBTYPE_MASK; + + reg_off &= ~KVM_REG_RISCV_SUBTYPE_MASK; + + switch (reg_subtype) { + case KVM_REG_RISCV_SBI_SINGLE: + return sbi_ext_single_id_to_str(reg_off); + case KVM_REG_RISCV_SBI_MULTI_EN: + case KVM_REG_RISCV_SBI_MULTI_DIS: + return sbi_ext_multi_id_to_str(reg_subtype, reg_off); + } + + TEST_FAIL("%s: Unknown sbi ext subtype: 0x%llx", prefix, reg_subtype); + return NULL; +} + +void print_reg(const char *prefix, __u64 id) +{ + const char *reg_size = NULL; + + TEST_ASSERT((id & KVM_REG_ARCH_MASK) == KVM_REG_RISCV, + "%s: KVM_REG_RISCV missing in reg id: 0x%llx", prefix, id); + + switch (id & KVM_REG_SIZE_MASK) { + case KVM_REG_SIZE_U32: + reg_size = "KVM_REG_SIZE_U32"; + break; + case KVM_REG_SIZE_U64: + reg_size = "KVM_REG_SIZE_U64"; + break; + case KVM_REG_SIZE_U128: + reg_size = "KVM_REG_SIZE_U128"; + break; + default: + TEST_FAIL("%s: Unexpected reg size: 0x%llx in reg id: 0x%llx", + prefix, (id & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT, id); + } + + switch (id & KVM_REG_RISCV_TYPE_MASK) { + case KVM_REG_RISCV_CONFIG: + printf("\tKVM_REG_RISCV | %s | KVM_REG_RISCV_CONFIG | %s,\n", + reg_size, config_id_to_str(id)); + break; + case KVM_REG_RISCV_CORE: + printf("\tKVM_REG_RISCV | %s | KVM_REG_RISCV_CORE | %s,\n", + reg_size, core_id_to_str(prefix, id)); + break; + case KVM_REG_RISCV_CSR: + printf("\tKVM_REG_RISCV | %s | KVM_REG_RISCV_CSR | %s,\n", + reg_size, csr_id_to_str(prefix, id)); + break; + case KVM_REG_RISCV_TIMER: + printf("\tKVM_REG_RISCV | %s | KVM_REG_RISCV_TIMER | %s,\n", + reg_size, timer_id_to_str(prefix, id)); + break; + case KVM_REG_RISCV_FP_F: + printf("\tKVM_REG_RISCV | %s | KVM_REG_RISCV_FP_F | %s,\n", + reg_size, fp_f_id_to_str(prefix, id)); + break; + case KVM_REG_RISCV_FP_D: + printf("\tKVM_REG_RISCV | %s | KVM_REG_RISCV_FP_D | %s,\n", + reg_size, fp_d_id_to_str(prefix, id)); + break; + case KVM_REG_RISCV_ISA_EXT: + printf("\tKVM_REG_RISCV | %s | KVM_REG_RISCV_ISA_EXT | %s,\n", + reg_size, isa_ext_id_to_str(id)); + break; + case KVM_REG_RISCV_SBI_EXT: + printf("\tKVM_REG_RISCV | %s | KVM_REG_RISCV_SBI_EXT | %s,\n", + reg_size, sbi_ext_id_to_str(prefix, id)); + break; + default: + TEST_FAIL("%s: Unexpected reg type: 0x%llx in reg id: 0x%llx", prefix, + (id & KVM_REG_RISCV_TYPE_MASK) >> KVM_REG_RISCV_TYPE_SHIFT, id); + } +} + +/* + * The current blessed list was primed with the output of kernel version + * v6.5-rc3 and then later updated with new registers. + */ +static __u64 base_regs[] = { + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(isa), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(mvendorid), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(marchid), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(mimpid), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(satp_mode), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.pc), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.ra), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.sp), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.gp), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.tp), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.t0), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.t1), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.t2), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.s0), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.s1), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.a0), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.a1), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.a2), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.a3), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.a4), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.a5), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.a6), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.a7), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.s2), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.s3), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.s4), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.s5), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.s6), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.s7), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.s8), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.s9), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.s10), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.s11), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.t3), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.t4), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.t5), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.t6), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(mode), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_GENERAL | KVM_REG_RISCV_CSR_REG(sstatus), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_GENERAL | KVM_REG_RISCV_CSR_REG(sie), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_GENERAL | KVM_REG_RISCV_CSR_REG(stvec), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_GENERAL | KVM_REG_RISCV_CSR_REG(sscratch), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_GENERAL | KVM_REG_RISCV_CSR_REG(sepc), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_GENERAL | KVM_REG_RISCV_CSR_REG(scause), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_GENERAL | KVM_REG_RISCV_CSR_REG(stval), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_GENERAL | KVM_REG_RISCV_CSR_REG(sip), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_GENERAL | KVM_REG_RISCV_CSR_REG(satp), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_GENERAL | KVM_REG_RISCV_CSR_REG(scounteren), + KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_TIMER | KVM_REG_RISCV_TIMER_REG(frequency), + KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_TIMER | KVM_REG_RISCV_TIMER_REG(time), + KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_TIMER | KVM_REG_RISCV_TIMER_REG(compare), + KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_TIMER | KVM_REG_RISCV_TIMER_REG(state), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_A, + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_C, + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_I, + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_M, + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_V01, + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_TIME, + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_IPI, + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_RFENCE, + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_SRST, + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_HSM, + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_PMU, + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_EXPERIMENTAL, + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_VENDOR, + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_MULTI_EN | 0, + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_MULTI_DIS | 0, +}; + +/* + * The skips_set list registers that should skip set test. + * - KVM_REG_RISCV_TIMER_REG(state): set would fail if it was not initialized properly. + */ +static __u64 base_skips_set[] = { + KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_TIMER | KVM_REG_RISCV_TIMER_REG(state), +}; + +static __u64 h_regs[] = { + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_H, +}; + +static __u64 zicbom_regs[] = { + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(zicbom_block_size), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICBOM, +}; + +static __u64 zicboz_regs[] = { + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(zicboz_block_size), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICBOZ, +}; + +static __u64 svpbmt_regs[] = { + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SVPBMT, +}; + +static __u64 sstc_regs[] = { + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SSTC, +}; + +static __u64 svinval_regs[] = { + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SVINVAL, +}; + +static __u64 zihintpause_regs[] = { + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZIHINTPAUSE, +}; + +static __u64 zba_regs[] = { + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZBA, +}; + +static __u64 zbb_regs[] = { + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZBB, +}; + +static __u64 zbs_regs[] = { + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZBS, +}; + +static __u64 zicntr_regs[] = { + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICNTR, +}; + +static __u64 zicsr_regs[] = { + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICSR, +}; + +static __u64 zifencei_regs[] = { + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZIFENCEI, +}; + +static __u64 zihpm_regs[] = { + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZIHPM, +}; + +static __u64 aia_regs[] = { + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(siselect), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(iprio1), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(iprio2), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(sieh), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(siph), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(iprio1h), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(iprio2h), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SSAIA, +}; + +static __u64 fp_f_regs[] = { + KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[0]), + KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[1]), + KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[2]), + KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[3]), + KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[4]), + KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[5]), + KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[6]), + KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[7]), + KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[8]), + KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[9]), + KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[10]), + KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[11]), + KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[12]), + KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[13]), + KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[14]), + KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[15]), + KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[16]), + KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[17]), + KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[18]), + KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[19]), + KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[20]), + KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[21]), + KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[22]), + KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[23]), + KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[24]), + KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[25]), + KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[26]), + KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[27]), + KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[28]), + KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[29]), + KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[30]), + KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[31]), + KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(fcsr), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_F, +}; + +static __u64 fp_d_regs[] = { + KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[0]), + KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[1]), + KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[2]), + KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[3]), + KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[4]), + KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[5]), + KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[6]), + KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[7]), + KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[8]), + KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[9]), + KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[10]), + KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[11]), + KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[12]), + KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[13]), + KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[14]), + KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[15]), + KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[16]), + KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[17]), + KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[18]), + KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[19]), + KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[20]), + KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[21]), + KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[22]), + KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[23]), + KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[24]), + KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[25]), + KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[26]), + KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[27]), + KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[28]), + KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[29]), + KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[30]), + KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[31]), + KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(fcsr), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_D, +}; + +#define BASE_SUBLIST \ + {"base", .regs = base_regs, .regs_n = ARRAY_SIZE(base_regs), \ + .skips_set = base_skips_set, .skips_set_n = ARRAY_SIZE(base_skips_set),} +#define H_REGS_SUBLIST \ + {"h", .feature = KVM_RISCV_ISA_EXT_H, .regs = h_regs, .regs_n = ARRAY_SIZE(h_regs),} +#define ZICBOM_REGS_SUBLIST \ + {"zicbom", .feature = KVM_RISCV_ISA_EXT_ZICBOM, .regs = zicbom_regs, .regs_n = ARRAY_SIZE(zicbom_regs),} +#define ZICBOZ_REGS_SUBLIST \ + {"zicboz", .feature = KVM_RISCV_ISA_EXT_ZICBOZ, .regs = zicboz_regs, .regs_n = ARRAY_SIZE(zicboz_regs),} +#define SVPBMT_REGS_SUBLIST \ + {"svpbmt", .feature = KVM_RISCV_ISA_EXT_SVPBMT, .regs = svpbmt_regs, .regs_n = ARRAY_SIZE(svpbmt_regs),} +#define SSTC_REGS_SUBLIST \ + {"sstc", .feature = KVM_RISCV_ISA_EXT_SSTC, .regs = sstc_regs, .regs_n = ARRAY_SIZE(sstc_regs),} +#define SVINVAL_REGS_SUBLIST \ + {"svinval", .feature = KVM_RISCV_ISA_EXT_SVINVAL, .regs = svinval_regs, .regs_n = ARRAY_SIZE(svinval_regs),} +#define ZIHINTPAUSE_REGS_SUBLIST \ + {"zihintpause", .feature = KVM_RISCV_ISA_EXT_ZIHINTPAUSE, .regs = zihintpause_regs, .regs_n = ARRAY_SIZE(zihintpause_regs),} +#define ZBA_REGS_SUBLIST \ + {"zba", .feature = KVM_RISCV_ISA_EXT_ZBA, .regs = zba_regs, .regs_n = ARRAY_SIZE(zba_regs),} +#define ZBB_REGS_SUBLIST \ + {"zbb", .feature = KVM_RISCV_ISA_EXT_ZBB, .regs = zbb_regs, .regs_n = ARRAY_SIZE(zbb_regs),} +#define ZBS_REGS_SUBLIST \ + {"zbs", .feature = KVM_RISCV_ISA_EXT_ZBS, .regs = zbs_regs, .regs_n = ARRAY_SIZE(zbs_regs),} +#define ZICNTR_REGS_SUBLIST \ + {"zicntr", .feature = KVM_RISCV_ISA_EXT_ZICNTR, .regs = zicntr_regs, .regs_n = ARRAY_SIZE(zicntr_regs),} +#define ZICSR_REGS_SUBLIST \ + {"zicsr", .feature = KVM_RISCV_ISA_EXT_ZICSR, .regs = zicsr_regs, .regs_n = ARRAY_SIZE(zicsr_regs),} +#define ZIFENCEI_REGS_SUBLIST \ + {"zifencei", .feature = KVM_RISCV_ISA_EXT_ZIFENCEI, .regs = zifencei_regs, .regs_n = ARRAY_SIZE(zifencei_regs),} +#define ZIHPM_REGS_SUBLIST \ + {"zihpm", .feature = KVM_RISCV_ISA_EXT_ZIHPM, .regs = zihpm_regs, .regs_n = ARRAY_SIZE(zihpm_regs),} +#define AIA_REGS_SUBLIST \ + {"aia", .feature = KVM_RISCV_ISA_EXT_SSAIA, .regs = aia_regs, .regs_n = ARRAY_SIZE(aia_regs),} +#define FP_F_REGS_SUBLIST \ + {"fp_f", .feature = KVM_RISCV_ISA_EXT_F, .regs = fp_f_regs, \ + .regs_n = ARRAY_SIZE(fp_f_regs),} +#define FP_D_REGS_SUBLIST \ + {"fp_d", .feature = KVM_RISCV_ISA_EXT_D, .regs = fp_d_regs, \ + .regs_n = ARRAY_SIZE(fp_d_regs),} + +static struct vcpu_reg_list h_config = { + .sublists = { + BASE_SUBLIST, + H_REGS_SUBLIST, + {0}, + }, +}; + +static struct vcpu_reg_list zicbom_config = { + .sublists = { + BASE_SUBLIST, + ZICBOM_REGS_SUBLIST, + {0}, + }, +}; + +static struct vcpu_reg_list zicboz_config = { + .sublists = { + BASE_SUBLIST, + ZICBOZ_REGS_SUBLIST, + {0}, + }, +}; + +static struct vcpu_reg_list svpbmt_config = { + .sublists = { + BASE_SUBLIST, + SVPBMT_REGS_SUBLIST, + {0}, + }, +}; + +static struct vcpu_reg_list sstc_config = { + .sublists = { + BASE_SUBLIST, + SSTC_REGS_SUBLIST, + {0}, + }, +}; + +static struct vcpu_reg_list svinval_config = { + .sublists = { + BASE_SUBLIST, + SVINVAL_REGS_SUBLIST, + {0}, + }, +}; + +static struct vcpu_reg_list zihintpause_config = { + .sublists = { + BASE_SUBLIST, + ZIHINTPAUSE_REGS_SUBLIST, + {0}, + }, +}; + +static struct vcpu_reg_list zba_config = { + .sublists = { + BASE_SUBLIST, + ZBA_REGS_SUBLIST, + {0}, + }, +}; + +static struct vcpu_reg_list zbb_config = { + .sublists = { + BASE_SUBLIST, + ZBB_REGS_SUBLIST, + {0}, + }, +}; + +static struct vcpu_reg_list zbs_config = { + .sublists = { + BASE_SUBLIST, + ZBS_REGS_SUBLIST, + {0}, + }, +}; + +static struct vcpu_reg_list zicntr_config = { + .sublists = { + BASE_SUBLIST, + ZICNTR_REGS_SUBLIST, + {0}, + }, +}; + +static struct vcpu_reg_list zicsr_config = { + .sublists = { + BASE_SUBLIST, + ZICSR_REGS_SUBLIST, + {0}, + }, +}; + +static struct vcpu_reg_list zifencei_config = { + .sublists = { + BASE_SUBLIST, + ZIFENCEI_REGS_SUBLIST, + {0}, + }, +}; + +static struct vcpu_reg_list zihpm_config = { + .sublists = { + BASE_SUBLIST, + ZIHPM_REGS_SUBLIST, + {0}, + }, +}; + +static struct vcpu_reg_list aia_config = { + .sublists = { + BASE_SUBLIST, + AIA_REGS_SUBLIST, + {0}, + }, +}; + +static struct vcpu_reg_list fp_f_config = { + .sublists = { + BASE_SUBLIST, + FP_F_REGS_SUBLIST, + {0}, + }, +}; + +static struct vcpu_reg_list fp_d_config = { + .sublists = { + BASE_SUBLIST, + FP_D_REGS_SUBLIST, + {0}, + }, +}; + +struct vcpu_reg_list *vcpu_configs[] = { + &h_config, + &zicbom_config, + &zicboz_config, + &svpbmt_config, + &sstc_config, + &svinval_config, + &zihintpause_config, + &zba_config, + &zbb_config, + &zbs_config, + &zicntr_config, + &zicsr_config, + &zifencei_config, + &zihpm_config, + &aia_config, + &fp_f_config, + &fp_d_config, +}; +int vcpu_configs_n = ARRAY_SIZE(vcpu_configs); diff --git a/tools/testing/selftests/kvm/s390x/cmma_test.c b/tools/testing/selftests/kvm/s390x/cmma_test.c index 1d73e78e8fa7..c8e0a6495a63 100644 --- a/tools/testing/selftests/kvm/s390x/cmma_test.c +++ b/tools/testing/selftests/kvm/s390x/cmma_test.c @@ -237,8 +237,8 @@ static void test_get_cmma_basic(void) /* GET_CMMA_BITS without CMMA enabled should fail */ rc = vm_get_cmma_bits(vm, 0, &errno_out); - ASSERT_EQ(rc, -1); - ASSERT_EQ(errno_out, ENXIO); + TEST_ASSERT_EQ(rc, -1); + TEST_ASSERT_EQ(errno_out, ENXIO); enable_cmma(vm); vcpu = vm_vcpu_add(vm, 1, guest_do_one_essa); @@ -247,31 +247,31 @@ static void test_get_cmma_basic(void) /* GET_CMMA_BITS without migration mode and without peeking should fail */ rc = vm_get_cmma_bits(vm, 0, &errno_out); - ASSERT_EQ(rc, -1); - ASSERT_EQ(errno_out, EINVAL); + TEST_ASSERT_EQ(rc, -1); + TEST_ASSERT_EQ(errno_out, EINVAL); /* GET_CMMA_BITS without migration mode and with peeking should work */ rc = vm_get_cmma_bits(vm, KVM_S390_CMMA_PEEK, &errno_out); - ASSERT_EQ(rc, 0); - ASSERT_EQ(errno_out, 0); + TEST_ASSERT_EQ(rc, 0); + TEST_ASSERT_EQ(errno_out, 0); enable_dirty_tracking(vm); enable_migration_mode(vm); /* GET_CMMA_BITS with invalid flags */ rc = vm_get_cmma_bits(vm, 0xfeedc0fe, &errno_out); - ASSERT_EQ(rc, -1); - ASSERT_EQ(errno_out, EINVAL); + TEST_ASSERT_EQ(rc, -1); + TEST_ASSERT_EQ(errno_out, EINVAL); kvm_vm_free(vm); } static void assert_exit_was_hypercall(struct kvm_vcpu *vcpu) { - ASSERT_EQ(vcpu->run->exit_reason, 13); - ASSERT_EQ(vcpu->run->s390_sieic.icptcode, 4); - ASSERT_EQ(vcpu->run->s390_sieic.ipa, 0x8300); - ASSERT_EQ(vcpu->run->s390_sieic.ipb, 0x5010000); + TEST_ASSERT_EQ(vcpu->run->exit_reason, 13); + TEST_ASSERT_EQ(vcpu->run->s390_sieic.icptcode, 4); + TEST_ASSERT_EQ(vcpu->run->s390_sieic.ipa, 0x8300); + TEST_ASSERT_EQ(vcpu->run->s390_sieic.ipb, 0x5010000); } static void test_migration_mode(void) @@ -283,8 +283,8 @@ static void test_migration_mode(void) /* enabling migration mode on a VM without memory should fail */ rc = __enable_migration_mode(vm); - ASSERT_EQ(rc, -1); - ASSERT_EQ(errno, EINVAL); + TEST_ASSERT_EQ(rc, -1); + TEST_ASSERT_EQ(errno, EINVAL); TEST_ASSERT(!is_migration_mode_on(vm), "migration mode should still be off"); errno = 0; @@ -304,8 +304,8 @@ static void test_migration_mode(void) /* migration mode when memslots have dirty tracking off should fail */ rc = __enable_migration_mode(vm); - ASSERT_EQ(rc, -1); - ASSERT_EQ(errno, EINVAL); + TEST_ASSERT_EQ(rc, -1); + TEST_ASSERT_EQ(errno, EINVAL); TEST_ASSERT(!is_migration_mode_on(vm), "migration mode should still be off"); errno = 0; @@ -314,7 +314,7 @@ static void test_migration_mode(void) /* enabling migration mode should work now */ rc = __enable_migration_mode(vm); - ASSERT_EQ(rc, 0); + TEST_ASSERT_EQ(rc, 0); TEST_ASSERT(is_migration_mode_on(vm), "migration mode should be on"); errno = 0; @@ -350,7 +350,7 @@ static void test_migration_mode(void) */ vm_mem_region_set_flags(vm, TEST_DATA_TWO_MEMSLOT, KVM_MEM_LOG_DIRTY_PAGES); rc = __enable_migration_mode(vm); - ASSERT_EQ(rc, 0); + TEST_ASSERT_EQ(rc, 0); TEST_ASSERT(is_migration_mode_on(vm), "migration mode should be on"); errno = 0; @@ -394,9 +394,9 @@ static void assert_all_slots_cmma_dirty(struct kvm_vm *vm) }; memset(cmma_value_buf, 0xff, sizeof(cmma_value_buf)); vm_ioctl(vm, KVM_S390_GET_CMMA_BITS, &args); - ASSERT_EQ(args.count, MAIN_PAGE_COUNT); - ASSERT_EQ(args.remaining, TEST_DATA_PAGE_COUNT); - ASSERT_EQ(args.start_gfn, 0); + TEST_ASSERT_EQ(args.count, MAIN_PAGE_COUNT); + TEST_ASSERT_EQ(args.remaining, TEST_DATA_PAGE_COUNT); + TEST_ASSERT_EQ(args.start_gfn, 0); /* ...and then - after a hole - the TEST_DATA memslot should follow */ args = (struct kvm_s390_cmma_log){ @@ -407,9 +407,9 @@ static void assert_all_slots_cmma_dirty(struct kvm_vm *vm) }; memset(cmma_value_buf, 0xff, sizeof(cmma_value_buf)); vm_ioctl(vm, KVM_S390_GET_CMMA_BITS, &args); - ASSERT_EQ(args.count, TEST_DATA_PAGE_COUNT); - ASSERT_EQ(args.start_gfn, TEST_DATA_START_GFN); - ASSERT_EQ(args.remaining, 0); + TEST_ASSERT_EQ(args.count, TEST_DATA_PAGE_COUNT); + TEST_ASSERT_EQ(args.start_gfn, TEST_DATA_START_GFN); + TEST_ASSERT_EQ(args.remaining, 0); /* ...and nothing else should be there */ args = (struct kvm_s390_cmma_log){ @@ -420,9 +420,9 @@ static void assert_all_slots_cmma_dirty(struct kvm_vm *vm) }; memset(cmma_value_buf, 0xff, sizeof(cmma_value_buf)); vm_ioctl(vm, KVM_S390_GET_CMMA_BITS, &args); - ASSERT_EQ(args.count, 0); - ASSERT_EQ(args.start_gfn, 0); - ASSERT_EQ(args.remaining, 0); + TEST_ASSERT_EQ(args.count, 0); + TEST_ASSERT_EQ(args.start_gfn, 0); + TEST_ASSERT_EQ(args.remaining, 0); } /** @@ -498,11 +498,11 @@ static void assert_cmma_dirty(u64 first_dirty_gfn, u64 dirty_gfn_count, const struct kvm_s390_cmma_log *res) { - ASSERT_EQ(res->start_gfn, first_dirty_gfn); - ASSERT_EQ(res->count, dirty_gfn_count); + TEST_ASSERT_EQ(res->start_gfn, first_dirty_gfn); + TEST_ASSERT_EQ(res->count, dirty_gfn_count); for (size_t i = 0; i < dirty_gfn_count; i++) - ASSERT_EQ(cmma_value_buf[0], 0x0); /* stable state */ - ASSERT_EQ(cmma_value_buf[dirty_gfn_count], 0xff); /* not touched */ + TEST_ASSERT_EQ(cmma_value_buf[0], 0x0); /* stable state */ + TEST_ASSERT_EQ(cmma_value_buf[dirty_gfn_count], 0xff); /* not touched */ } static void test_get_skip_holes(void) diff --git a/tools/testing/selftests/kvm/s390x/debug_test.c b/tools/testing/selftests/kvm/s390x/debug_test.c new file mode 100644 index 000000000000..84313fb27529 --- /dev/null +++ b/tools/testing/selftests/kvm/s390x/debug_test.c @@ -0,0 +1,160 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Test KVM debugging features. */ +#include "kvm_util.h" +#include "test_util.h" + +#include <linux/kvm.h> + +#define __LC_SVC_NEW_PSW 0x1c0 +#define __LC_PGM_NEW_PSW 0x1d0 +#define ICPT_INSTRUCTION 0x04 +#define IPA0_DIAG 0x8300 +#define PGM_SPECIFICATION 0x06 + +/* Common code for testing single-stepping interruptions. */ +extern char int_handler[]; +asm("int_handler:\n" + "j .\n"); + +static struct kvm_vm *test_step_int_1(struct kvm_vcpu **vcpu, void *guest_code, + size_t new_psw_off, uint64_t *new_psw) +{ + struct kvm_guest_debug debug = {}; + struct kvm_regs regs; + struct kvm_vm *vm; + char *lowcore; + + vm = vm_create_with_one_vcpu(vcpu, guest_code); + lowcore = addr_gpa2hva(vm, 0); + new_psw[0] = (*vcpu)->run->psw_mask; + new_psw[1] = (uint64_t)int_handler; + memcpy(lowcore + new_psw_off, new_psw, 16); + vcpu_regs_get(*vcpu, ®s); + regs.gprs[2] = -1; + vcpu_regs_set(*vcpu, ®s); + debug.control = KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_SINGLESTEP; + vcpu_guest_debug_set(*vcpu, &debug); + vcpu_run(*vcpu); + + return vm; +} + +static void test_step_int(void *guest_code, size_t new_psw_off) +{ + struct kvm_vcpu *vcpu; + uint64_t new_psw[2]; + struct kvm_vm *vm; + + vm = test_step_int_1(&vcpu, guest_code, new_psw_off, new_psw); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_DEBUG); + TEST_ASSERT_EQ(vcpu->run->psw_mask, new_psw[0]); + TEST_ASSERT_EQ(vcpu->run->psw_addr, new_psw[1]); + kvm_vm_free(vm); +} + +/* Test single-stepping "boring" program interruptions. */ +extern char test_step_pgm_guest_code[]; +asm("test_step_pgm_guest_code:\n" + ".insn rr,0x1d00,%r1,%r0 /* dr %r1,%r0 */\n" + "j .\n"); + +static void test_step_pgm(void) +{ + test_step_int(test_step_pgm_guest_code, __LC_PGM_NEW_PSW); +} + +/* + * Test single-stepping program interruptions caused by DIAG. + * Userspace emulation must not interfere with single-stepping. + */ +extern char test_step_pgm_diag_guest_code[]; +asm("test_step_pgm_diag_guest_code:\n" + "diag %r0,%r0,0\n" + "j .\n"); + +static void test_step_pgm_diag(void) +{ + struct kvm_s390_irq irq = { + .type = KVM_S390_PROGRAM_INT, + .u.pgm.code = PGM_SPECIFICATION, + }; + struct kvm_vcpu *vcpu; + uint64_t new_psw[2]; + struct kvm_vm *vm; + + vm = test_step_int_1(&vcpu, test_step_pgm_diag_guest_code, + __LC_PGM_NEW_PSW, new_psw); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_S390_SIEIC); + TEST_ASSERT_EQ(vcpu->run->s390_sieic.icptcode, ICPT_INSTRUCTION); + TEST_ASSERT_EQ(vcpu->run->s390_sieic.ipa & 0xff00, IPA0_DIAG); + vcpu_ioctl(vcpu, KVM_S390_IRQ, &irq); + vcpu_run(vcpu); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_DEBUG); + TEST_ASSERT_EQ(vcpu->run->psw_mask, new_psw[0]); + TEST_ASSERT_EQ(vcpu->run->psw_addr, new_psw[1]); + kvm_vm_free(vm); +} + +/* + * Test single-stepping program interruptions caused by ISKE. + * CPUSTAT_KSS handling must not interfere with single-stepping. + */ +extern char test_step_pgm_iske_guest_code[]; +asm("test_step_pgm_iske_guest_code:\n" + "iske %r2,%r2\n" + "j .\n"); + +static void test_step_pgm_iske(void) +{ + test_step_int(test_step_pgm_iske_guest_code, __LC_PGM_NEW_PSW); +} + +/* + * Test single-stepping program interruptions caused by LCTL. + * KVM emulation must not interfere with single-stepping. + */ +extern char test_step_pgm_lctl_guest_code[]; +asm("test_step_pgm_lctl_guest_code:\n" + "lctl %c0,%c0,1\n" + "j .\n"); + +static void test_step_pgm_lctl(void) +{ + test_step_int(test_step_pgm_lctl_guest_code, __LC_PGM_NEW_PSW); +} + +/* Test single-stepping supervisor-call interruptions. */ +extern char test_step_svc_guest_code[]; +asm("test_step_svc_guest_code:\n" + "svc 0\n" + "j .\n"); + +static void test_step_svc(void) +{ + test_step_int(test_step_svc_guest_code, __LC_SVC_NEW_PSW); +} + +/* Run all tests above. */ +static struct testdef { + const char *name; + void (*test)(void); +} testlist[] = { + { "single-step pgm", test_step_pgm }, + { "single-step pgm caused by diag", test_step_pgm_diag }, + { "single-step pgm caused by iske", test_step_pgm_iske }, + { "single-step pgm caused by lctl", test_step_pgm_lctl }, + { "single-step svc", test_step_svc }, +}; + +int main(int argc, char *argv[]) +{ + int idx; + + ksft_print_header(); + ksft_set_plan(ARRAY_SIZE(testlist)); + for (idx = 0; idx < ARRAY_SIZE(testlist); idx++) { + testlist[idx].test(); + ksft_test_result_pass("%s\n", testlist[idx].name); + } + ksft_finished(); +} diff --git a/tools/testing/selftests/kvm/s390x/memop.c b/tools/testing/selftests/kvm/s390x/memop.c index 8e4b94d7b8dd..bb3ca9a5d731 100644 --- a/tools/testing/selftests/kvm/s390x/memop.c +++ b/tools/testing/selftests/kvm/s390x/memop.c @@ -4,7 +4,6 @@ * * Copyright (C) 2019, Red Hat, Inc. */ - #include <stdio.h> #include <stdlib.h> #include <string.h> @@ -279,10 +278,10 @@ enum stage { vcpu_run(__vcpu); \ get_ucall(__vcpu, &uc); \ if (uc.cmd == UCALL_ABORT) { \ - REPORT_GUEST_ASSERT_2(uc, "hints: %lu, %lu"); \ + REPORT_GUEST_ASSERT(uc); \ } \ - ASSERT_EQ(uc.cmd, UCALL_SYNC); \ - ASSERT_EQ(uc.args[1], __stage); \ + TEST_ASSERT_EQ(uc.cmd, UCALL_SYNC); \ + TEST_ASSERT_EQ(uc.args[1], __stage); \ }) \ static void prepare_mem12(void) @@ -469,7 +468,7 @@ static __uint128_t cut_to_size(int size, __uint128_t val) case 16: return val; } - GUEST_ASSERT_1(false, "Invalid size"); + GUEST_FAIL("Invalid size = %u", size); return 0; } @@ -598,7 +597,7 @@ static bool _cmpxchg(int size, void *target, __uint128_t *old_addr, __uint128_t return ret; } } - GUEST_ASSERT_1(false, "Invalid size"); + GUEST_FAIL("Invalid size = %u", size); return 0; } @@ -808,7 +807,7 @@ static void test_termination(void) HOST_SYNC(t.vcpu, STAGE_IDLED); MOP(t.vm, ABSOLUTE, READ, &teid, sizeof(teid), GADDR(prefix + 168)); /* Bits 56, 60, 61 form a code, 0 being the only one allowing for termination */ - ASSERT_EQ(teid & teid_mask, 0); + TEST_ASSERT_EQ(teid & teid_mask, 0); kvm_vm_free(t.kvm_vm); } diff --git a/tools/testing/selftests/kvm/s390x/tprot.c b/tools/testing/selftests/kvm/s390x/tprot.c index a9a0b76e5fa4..c73f948c9b63 100644 --- a/tools/testing/selftests/kvm/s390x/tprot.c +++ b/tools/testing/selftests/kvm/s390x/tprot.c @@ -4,7 +4,6 @@ * * Copyright IBM Corp. 2021 */ - #include <sys/mman.h> #include "test_util.h" #include "kvm_util.h" @@ -156,7 +155,9 @@ static enum stage perform_next_stage(int *i, bool mapped_0) !mapped_0; if (!skip) { result = test_protection(tests[*i].addr, tests[*i].key); - GUEST_ASSERT_2(result == tests[*i].expected, *i, result); + __GUEST_ASSERT(result == tests[*i].expected, + "Wanted %u, got %u, for i = %u", + tests[*i].expected, result, *i); } } return stage; @@ -190,9 +191,9 @@ static void guest_code(void) vcpu_run(__vcpu); \ get_ucall(__vcpu, &uc); \ if (uc.cmd == UCALL_ABORT) \ - REPORT_GUEST_ASSERT_2(uc, "hints: %lu, %lu"); \ - ASSERT_EQ(uc.cmd, UCALL_SYNC); \ - ASSERT_EQ(uc.args[1], __stage); \ + REPORT_GUEST_ASSERT(uc); \ + TEST_ASSERT_EQ(uc.cmd, UCALL_SYNC); \ + TEST_ASSERT_EQ(uc.args[1], __stage); \ }) #define HOST_SYNC(vcpu, stage) \ diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c index a849ce23ca97..b32960189f5f 100644 --- a/tools/testing/selftests/kvm/set_memory_region_test.c +++ b/tools/testing/selftests/kvm/set_memory_region_test.c @@ -88,7 +88,7 @@ static void *vcpu_worker(void *data) } if (run->exit_reason == KVM_EXIT_IO && cmd == UCALL_ABORT) - REPORT_GUEST_ASSERT_1(uc, "val = %lu"); + REPORT_GUEST_ASSERT(uc); return NULL; } @@ -156,19 +156,22 @@ static void guest_code_move_memory_region(void) * window where the memslot is invalid is usually quite small. */ val = guest_spin_on_val(0); - GUEST_ASSERT_1(val == 1 || val == MMIO_VAL, val); + __GUEST_ASSERT(val == 1 || val == MMIO_VAL, + "Expected '1' or MMIO ('%llx'), got '%llx'", MMIO_VAL, val); /* Spin until the misaligning memory region move completes. */ val = guest_spin_on_val(MMIO_VAL); - GUEST_ASSERT_1(val == 1 || val == 0, val); + __GUEST_ASSERT(val == 1 || val == 0, + "Expected '0' or '1' (no MMIO), got '%llx'", val); /* Spin until the memory region starts to get re-aligned. */ val = guest_spin_on_val(0); - GUEST_ASSERT_1(val == 1 || val == MMIO_VAL, val); + __GUEST_ASSERT(val == 1 || val == MMIO_VAL, + "Expected '1' or MMIO ('%llx'), got '%llx'", MMIO_VAL, val); /* Spin until the re-aligning memory region move completes. */ val = guest_spin_on_val(MMIO_VAL); - GUEST_ASSERT_1(val == 1, val); + GUEST_ASSERT_EQ(val, 1); GUEST_DONE(); } @@ -224,15 +227,15 @@ static void guest_code_delete_memory_region(void) /* Spin until the memory region is deleted. */ val = guest_spin_on_val(0); - GUEST_ASSERT_1(val == MMIO_VAL, val); + GUEST_ASSERT_EQ(val, MMIO_VAL); /* Spin until the memory region is recreated. */ val = guest_spin_on_val(MMIO_VAL); - GUEST_ASSERT_1(val == 0, val); + GUEST_ASSERT_EQ(val, 0); /* Spin until the memory region is deleted. */ val = guest_spin_on_val(0); - GUEST_ASSERT_1(val == MMIO_VAL, val); + GUEST_ASSERT_EQ(val, MMIO_VAL); asm("1:\n\t" ".pushsection .rodata\n\t" @@ -249,7 +252,7 @@ static void guest_code_delete_memory_region(void) "final_rip_end: .quad 1b\n\t" ".popsection"); - GUEST_ASSERT_1(0, 0); + GUEST_ASSERT(0); } static void test_delete_memory_region(void) diff --git a/tools/testing/selftests/kvm/steal_time.c b/tools/testing/selftests/kvm/steal_time.c index c87f38712073..171adfb2a6cb 100644 --- a/tools/testing/selftests/kvm/steal_time.c +++ b/tools/testing/selftests/kvm/steal_time.c @@ -31,8 +31,8 @@ static uint64_t guest_stolen_time[NR_VCPUS]; static void check_status(struct kvm_steal_time *st) { GUEST_ASSERT(!(READ_ONCE(st->version) & 1)); - GUEST_ASSERT(READ_ONCE(st->flags) == 0); - GUEST_ASSERT(READ_ONCE(st->preempted) == 0); + GUEST_ASSERT_EQ(READ_ONCE(st->flags), 0); + GUEST_ASSERT_EQ(READ_ONCE(st->preempted), 0); } static void guest_code(int cpu) @@ -40,7 +40,7 @@ static void guest_code(int cpu) struct kvm_steal_time *st = st_gva[cpu]; uint32_t version; - GUEST_ASSERT(rdmsr(MSR_KVM_STEAL_TIME) == ((uint64_t)st_gva[cpu] | KVM_MSR_ENABLED)); + GUEST_ASSERT_EQ(rdmsr(MSR_KVM_STEAL_TIME), ((uint64_t)st_gva[cpu] | KVM_MSR_ENABLED)); memset(st, 0, sizeof(*st)); GUEST_SYNC(0); @@ -122,8 +122,8 @@ static int64_t smccc(uint32_t func, uint64_t arg) static void check_status(struct st_time *st) { - GUEST_ASSERT(READ_ONCE(st->rev) == 0); - GUEST_ASSERT(READ_ONCE(st->attr) == 0); + GUEST_ASSERT_EQ(READ_ONCE(st->rev), 0); + GUEST_ASSERT_EQ(READ_ONCE(st->attr), 0); } static void guest_code(int cpu) @@ -132,15 +132,15 @@ static void guest_code(int cpu) int64_t status; status = smccc(SMCCC_ARCH_FEATURES, PV_TIME_FEATURES); - GUEST_ASSERT(status == 0); + GUEST_ASSERT_EQ(status, 0); status = smccc(PV_TIME_FEATURES, PV_TIME_FEATURES); - GUEST_ASSERT(status == 0); + GUEST_ASSERT_EQ(status, 0); status = smccc(PV_TIME_FEATURES, PV_TIME_ST); - GUEST_ASSERT(status == 0); + GUEST_ASSERT_EQ(status, 0); status = smccc(PV_TIME_ST, 0); - GUEST_ASSERT(status != -1); - GUEST_ASSERT(status == (ulong)st_gva[cpu]); + GUEST_ASSERT_NE(status, -1); + GUEST_ASSERT_EQ(status, (ulong)st_gva[cpu]); st = (struct st_time *)status; GUEST_SYNC(0); diff --git a/tools/testing/selftests/kvm/x86_64/cpuid_test.c b/tools/testing/selftests/kvm/x86_64/cpuid_test.c index d3c3aa93f090..3b34d8156d1c 100644 --- a/tools/testing/selftests/kvm/x86_64/cpuid_test.c +++ b/tools/testing/selftests/kvm/x86_64/cpuid_test.c @@ -35,10 +35,10 @@ static void test_guest_cpuids(struct kvm_cpuid2 *guest_cpuid) guest_cpuid->entries[i].index, &eax, &ebx, &ecx, &edx); - GUEST_ASSERT(eax == guest_cpuid->entries[i].eax && - ebx == guest_cpuid->entries[i].ebx && - ecx == guest_cpuid->entries[i].ecx && - edx == guest_cpuid->entries[i].edx); + GUEST_ASSERT_EQ(eax, guest_cpuid->entries[i].eax); + GUEST_ASSERT_EQ(ebx, guest_cpuid->entries[i].ebx); + GUEST_ASSERT_EQ(ecx, guest_cpuid->entries[i].ecx); + GUEST_ASSERT_EQ(edx, guest_cpuid->entries[i].edx); } } @@ -51,7 +51,7 @@ static void guest_main(struct kvm_cpuid2 *guest_cpuid) GUEST_SYNC(2); - GUEST_ASSERT(this_cpu_property(X86_PROPERTY_MAX_KVM_LEAF) == 0x40000001); + GUEST_ASSERT_EQ(this_cpu_property(X86_PROPERTY_MAX_KVM_LEAF), 0x40000001); GUEST_DONE(); } @@ -116,7 +116,7 @@ static void run_vcpu(struct kvm_vcpu *vcpu, int stage) case UCALL_DONE: return; case UCALL_ABORT: - REPORT_GUEST_ASSERT_2(uc, "values: %#lx, %#lx"); + REPORT_GUEST_ASSERT(uc); default: TEST_ASSERT(false, "Unexpected exit: %s", exit_reason_str(vcpu->run->exit_reason)); diff --git a/tools/testing/selftests/kvm/x86_64/dirty_log_page_splitting_test.c b/tools/testing/selftests/kvm/x86_64/dirty_log_page_splitting_test.c index beb7e2c10211..634c6bfcd572 100644 --- a/tools/testing/selftests/kvm/x86_64/dirty_log_page_splitting_test.c +++ b/tools/testing/selftests/kvm/x86_64/dirty_log_page_splitting_test.c @@ -72,7 +72,7 @@ static void vcpu_worker(struct memstress_vcpu_args *vcpu_args) vcpu_run(vcpu); - ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_SYNC); + TEST_ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_SYNC); vcpu_last_completed_iteration[vcpu_idx] = current_iteration; @@ -179,12 +179,12 @@ static void run_test(enum vm_guest_mode mode, void *unused) * with that capability. */ if (dirty_log_manual_caps) { - ASSERT_EQ(stats_clear_pass[0].hugepages, 0); - ASSERT_EQ(stats_clear_pass[0].pages_4k, total_4k_pages); - ASSERT_EQ(stats_dirty_logging_enabled.hugepages, stats_populated.hugepages); + TEST_ASSERT_EQ(stats_clear_pass[0].hugepages, 0); + TEST_ASSERT_EQ(stats_clear_pass[0].pages_4k, total_4k_pages); + TEST_ASSERT_EQ(stats_dirty_logging_enabled.hugepages, stats_populated.hugepages); } else { - ASSERT_EQ(stats_dirty_logging_enabled.hugepages, 0); - ASSERT_EQ(stats_dirty_logging_enabled.pages_4k, total_4k_pages); + TEST_ASSERT_EQ(stats_dirty_logging_enabled.hugepages, 0); + TEST_ASSERT_EQ(stats_dirty_logging_enabled.pages_4k, total_4k_pages); } /* @@ -192,9 +192,9 @@ static void run_test(enum vm_guest_mode mode, void *unused) * memory again, the page counts should be the same as they were * right after initial population of memory. */ - ASSERT_EQ(stats_populated.pages_4k, stats_repopulated.pages_4k); - ASSERT_EQ(stats_populated.pages_2m, stats_repopulated.pages_2m); - ASSERT_EQ(stats_populated.pages_1g, stats_repopulated.pages_1g); + TEST_ASSERT_EQ(stats_populated.pages_4k, stats_repopulated.pages_4k); + TEST_ASSERT_EQ(stats_populated.pages_2m, stats_repopulated.pages_2m); + TEST_ASSERT_EQ(stats_populated.pages_1g, stats_repopulated.pages_1g); } static void help(char *name) diff --git a/tools/testing/selftests/kvm/x86_64/exit_on_emulation_failure_test.c b/tools/testing/selftests/kvm/x86_64/exit_on_emulation_failure_test.c index e334844d6e1d..6c2e5e0ceb1f 100644 --- a/tools/testing/selftests/kvm/x86_64/exit_on_emulation_failure_test.c +++ b/tools/testing/selftests/kvm/x86_64/exit_on_emulation_failure_test.c @@ -35,7 +35,7 @@ int main(int argc, char *argv[]) vcpu_run(vcpu); handle_flds_emulation_failure_exit(vcpu); vcpu_run(vcpu); - ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_DONE); + TEST_ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_DONE); kvm_vm_free(vm); return 0; diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_extended_hypercalls.c b/tools/testing/selftests/kvm/x86_64/hyperv_extended_hypercalls.c index 73af44d2167f..e036db1f32b9 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_extended_hypercalls.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_extended_hypercalls.c @@ -8,7 +8,6 @@ * Copyright 2022 Google LLC * Author: Vipin Sharma <vipinsh@google.com> */ - #include "kvm_util.h" #include "processor.h" #include "hyperv.h" @@ -84,7 +83,7 @@ int main(void) switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - REPORT_GUEST_ASSERT_2(uc, "arg1 = %ld, arg2 = %ld"); + REPORT_GUEST_ASSERT(uc); break; case UCALL_DONE: break; diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_features.c b/tools/testing/selftests/kvm/x86_64/hyperv_features.c index 78606de9385d..9f28aa276c4e 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_features.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_features.c @@ -53,16 +53,21 @@ static void guest_msr(struct msr_data *msr) vector = rdmsr_safe(msr->idx, &msr_val); if (msr->fault_expected) - GUEST_ASSERT_3(vector == GP_VECTOR, msr->idx, vector, GP_VECTOR); + __GUEST_ASSERT(vector == GP_VECTOR, + "Expected #GP on %sMSR(0x%x), got vector '0x%x'", + msr->idx, msr->write ? "WR" : "RD", vector); else - GUEST_ASSERT_3(!vector, msr->idx, vector, 0); + __GUEST_ASSERT(!vector, + "Expected success on %sMSR(0x%x), got vector '0x%x'", + msr->idx, msr->write ? "WR" : "RD", vector); if (vector || is_write_only_msr(msr->idx)) goto done; if (msr->write) - GUEST_ASSERT_3(msr_val == msr->write_val, msr->idx, - msr_val, msr->write_val); + __GUEST_ASSERT(!vector, + "WRMSR(0x%x) to '0x%llx', RDMSR read '0x%llx'", + msr->idx, msr->write_val, msr_val); /* Invariant TSC bit appears when TSC invariant control MSR is written to */ if (msr->idx == HV_X64_MSR_TSC_INVARIANT_CONTROL) { @@ -82,7 +87,7 @@ static void guest_hcall(vm_vaddr_t pgs_gpa, struct hcall_data *hcall) u64 res, input, output; uint8_t vector; - GUEST_ASSERT(hcall->control); + GUEST_ASSERT_NE(hcall->control, 0); wrmsr(HV_X64_MSR_GUEST_OS_ID, HYPERV_LINUX_OS_ID); wrmsr(HV_X64_MSR_HYPERCALL, pgs_gpa); @@ -96,10 +101,14 @@ static void guest_hcall(vm_vaddr_t pgs_gpa, struct hcall_data *hcall) vector = __hyperv_hypercall(hcall->control, input, output, &res); if (hcall->ud_expected) { - GUEST_ASSERT_2(vector == UD_VECTOR, hcall->control, vector); + __GUEST_ASSERT(vector == UD_VECTOR, + "Expected #UD for control '%u', got vector '0x%x'", + hcall->control, vector); } else { - GUEST_ASSERT_2(!vector, hcall->control, vector); - GUEST_ASSERT_2(res == hcall->expect, hcall->expect, res); + __GUEST_ASSERT(!vector, + "Expected no exception for control '%u', got vector '0x%x'", + hcall->control, vector); + GUEST_ASSERT_EQ(res, hcall->expect); } GUEST_DONE(); @@ -495,7 +504,7 @@ static void guest_test_msrs_access(void) switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - REPORT_GUEST_ASSERT_3(uc, "MSR = %lx, arg1 = %lx, arg2 = %lx"); + REPORT_GUEST_ASSERT(uc); return; case UCALL_DONE: break; @@ -665,7 +674,7 @@ static void guest_test_hcalls_access(void) switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - REPORT_GUEST_ASSERT_2(uc, "arg1 = %lx, arg2 = %lx"); + REPORT_GUEST_ASSERT(uc); return; case UCALL_DONE: break; diff --git a/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c b/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c index f774a9e62858..9e2879af7c20 100644 --- a/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c +++ b/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c @@ -46,10 +46,10 @@ static void test_msr(struct msr_data *msr) PR_MSR(msr); vector = rdmsr_safe(msr->idx, &ignored); - GUEST_ASSERT_1(vector == GP_VECTOR, vector); + GUEST_ASSERT_EQ(vector, GP_VECTOR); vector = wrmsr_safe(msr->idx, 0); - GUEST_ASSERT_1(vector == GP_VECTOR, vector); + GUEST_ASSERT_EQ(vector, GP_VECTOR); } struct hcall_data { @@ -77,7 +77,7 @@ static void test_hcall(struct hcall_data *hc) PR_HCALL(hc); r = kvm_hypercall(hc->nr, 0, 0, 0, 0); - GUEST_ASSERT(r == -KVM_ENOSYS); + GUEST_ASSERT_EQ(r, -KVM_ENOSYS); } static void guest_main(void) @@ -125,7 +125,7 @@ static void enter_guest(struct kvm_vcpu *vcpu) pr_hcall(&uc); break; case UCALL_ABORT: - REPORT_GUEST_ASSERT_1(uc, "vector = %lu"); + REPORT_GUEST_ASSERT(uc); return; case UCALL_DONE: return; diff --git a/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c b/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c index 72812644d7f5..80aa3d8b18f8 100644 --- a/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c +++ b/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c @@ -16,14 +16,25 @@ enum monitor_mwait_testcases { MWAIT_DISABLED = BIT(2), }; +/* + * If both MWAIT and its quirk are disabled, MONITOR/MWAIT should #UD, in all + * other scenarios KVM should emulate them as nops. + */ +#define GUEST_ASSERT_MONITOR_MWAIT(insn, testcase, vector) \ +do { \ + bool fault_wanted = ((testcase) & MWAIT_QUIRK_DISABLED) && \ + ((testcase) & MWAIT_DISABLED); \ + \ + if (fault_wanted) \ + __GUEST_ASSERT((vector) == UD_VECTOR, \ + "Expected #UD on " insn " for testcase '0x%x', got '0x%x'", vector); \ + else \ + __GUEST_ASSERT(!(vector), \ + "Expected success on " insn " for testcase '0x%x', got '0x%x'", vector); \ +} while (0) + static void guest_monitor_wait(int testcase) { - /* - * If both MWAIT and its quirk are disabled, MONITOR/MWAIT should #UD, - * in all other scenarios KVM should emulate them as nops. - */ - bool fault_wanted = (testcase & MWAIT_QUIRK_DISABLED) && - (testcase & MWAIT_DISABLED); u8 vector; GUEST_SYNC(testcase); @@ -33,16 +44,10 @@ static void guest_monitor_wait(int testcase) * intercept checks, so the inputs for MONITOR and MWAIT must be valid. */ vector = kvm_asm_safe("monitor", "a"(guest_monitor_wait), "c"(0), "d"(0)); - if (fault_wanted) - GUEST_ASSERT_2(vector == UD_VECTOR, testcase, vector); - else - GUEST_ASSERT_2(!vector, testcase, vector); + GUEST_ASSERT_MONITOR_MWAIT("MONITOR", testcase, vector); vector = kvm_asm_safe("mwait", "a"(guest_monitor_wait), "c"(0), "d"(0)); - if (fault_wanted) - GUEST_ASSERT_2(vector == UD_VECTOR, testcase, vector); - else - GUEST_ASSERT_2(!vector, testcase, vector); + GUEST_ASSERT_MONITOR_MWAIT("MWAIT", testcase, vector); } static void guest_code(void) @@ -85,7 +90,7 @@ int main(int argc, char *argv[]) testcase = uc.args[1]; break; case UCALL_ABORT: - REPORT_GUEST_ASSERT_2(uc, "testcase = %lx, vector = %ld"); + REPORT_GUEST_ASSERT(uc); goto done; case UCALL_DONE: goto done; diff --git a/tools/testing/selftests/kvm/x86_64/nested_exceptions_test.c b/tools/testing/selftests/kvm/x86_64/nested_exceptions_test.c index 6502aa23c2f8..3670331adf21 100644 --- a/tools/testing/selftests/kvm/x86_64/nested_exceptions_test.c +++ b/tools/testing/selftests/kvm/x86_64/nested_exceptions_test.c @@ -180,9 +180,7 @@ static void assert_ucall_vector(struct kvm_vcpu *vcpu, int vector) "Expected L2 to ask for %d, L2 says it's done", vector); break; case UCALL_ABORT: - TEST_FAIL("%s at %s:%ld (0x%lx != 0x%lx)", - (const char *)uc.args[0], __FILE__, uc.args[1], - uc.args[2], uc.args[3]); + REPORT_GUEST_ASSERT(uc); break; default: TEST_FAIL("Expected L2 to ask for %d, got unexpected ucall %lu", vector, uc.cmd); @@ -247,12 +245,12 @@ int main(int argc, char *argv[]) /* Verify the pending events comes back out the same as it went in. */ vcpu_events_get(vcpu, &events); - ASSERT_EQ(events.flags & KVM_VCPUEVENT_VALID_PAYLOAD, - KVM_VCPUEVENT_VALID_PAYLOAD); - ASSERT_EQ(events.exception.pending, true); - ASSERT_EQ(events.exception.nr, SS_VECTOR); - ASSERT_EQ(events.exception.has_error_code, true); - ASSERT_EQ(events.exception.error_code, SS_ERROR_CODE); + TEST_ASSERT_EQ(events.flags & KVM_VCPUEVENT_VALID_PAYLOAD, + KVM_VCPUEVENT_VALID_PAYLOAD); + TEST_ASSERT_EQ(events.exception.pending, true); + TEST_ASSERT_EQ(events.exception.nr, SS_VECTOR); + TEST_ASSERT_EQ(events.exception.has_error_code, true); + TEST_ASSERT_EQ(events.exception.error_code, SS_ERROR_CODE); /* * Run for real with the pending #SS, L1 should get a VM-Exit due to diff --git a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c index 40507ed9fe8a..283cc55597a4 100644 --- a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c +++ b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c @@ -27,6 +27,15 @@ #define ARCH_PERFMON_BRANCHES_RETIRED 5 #define NUM_BRANCHES 42 +#define INTEL_PMC_IDX_FIXED 32 + +/* Matches KVM_PMU_EVENT_FILTER_MAX_EVENTS in pmu.c */ +#define MAX_FILTER_EVENTS 300 +#define MAX_TEST_EVENTS 10 + +#define PMU_EVENT_FILTER_INVALID_ACTION (KVM_PMU_EVENT_DENY + 1) +#define PMU_EVENT_FILTER_INVALID_FLAGS (KVM_PMU_EVENT_FLAGS_VALID_MASK << 1) +#define PMU_EVENT_FILTER_INVALID_NEVENTS (MAX_FILTER_EVENTS + 1) /* * This is how the event selector and unit mask are stored in an AMD @@ -69,21 +78,33 @@ #define INST_RETIRED EVENT(0xc0, 0) +struct __kvm_pmu_event_filter { + __u32 action; + __u32 nevents; + __u32 fixed_counter_bitmap; + __u32 flags; + __u32 pad[4]; + __u64 events[MAX_FILTER_EVENTS]; +}; + /* * This event list comprises Intel's eight architectural events plus * AMD's "retired branch instructions" for Zen[123] (and possibly * other AMD CPUs). */ -static const uint64_t event_list[] = { - EVENT(0x3c, 0), - INST_RETIRED, - EVENT(0x3c, 1), - EVENT(0x2e, 0x4f), - EVENT(0x2e, 0x41), - EVENT(0xc4, 0), - EVENT(0xc5, 0), - EVENT(0xa4, 1), - AMD_ZEN_BR_RETIRED, +static const struct __kvm_pmu_event_filter base_event_filter = { + .nevents = ARRAY_SIZE(base_event_filter.events), + .events = { + EVENT(0x3c, 0), + INST_RETIRED, + EVENT(0x3c, 1), + EVENT(0x2e, 0x4f), + EVENT(0x2e, 0x41), + EVENT(0xc4, 0), + EVENT(0xc5, 0), + EVENT(0xa4, 1), + AMD_ZEN_BR_RETIRED, + }, }; struct { @@ -225,48 +246,11 @@ static bool sanity_check_pmu(struct kvm_vcpu *vcpu) return !r; } -static struct kvm_pmu_event_filter *alloc_pmu_event_filter(uint32_t nevents) -{ - struct kvm_pmu_event_filter *f; - int size = sizeof(*f) + nevents * sizeof(f->events[0]); - - f = malloc(size); - TEST_ASSERT(f, "Out of memory"); - memset(f, 0, size); - f->nevents = nevents; - return f; -} - - -static struct kvm_pmu_event_filter * -create_pmu_event_filter(const uint64_t event_list[], int nevents, - uint32_t action, uint32_t flags) -{ - struct kvm_pmu_event_filter *f; - int i; - - f = alloc_pmu_event_filter(nevents); - f->action = action; - f->flags = flags; - for (i = 0; i < nevents; i++) - f->events[i] = event_list[i]; - - return f; -} - -static struct kvm_pmu_event_filter *event_filter(uint32_t action) -{ - return create_pmu_event_filter(event_list, - ARRAY_SIZE(event_list), - action, 0); -} - /* * Remove the first occurrence of 'event' (if any) from the filter's * event list. */ -static struct kvm_pmu_event_filter *remove_event(struct kvm_pmu_event_filter *f, - uint64_t event) +static void remove_event(struct __kvm_pmu_event_filter *f, uint64_t event) { bool found = false; int i; @@ -279,7 +263,6 @@ static struct kvm_pmu_event_filter *remove_event(struct kvm_pmu_event_filter *f, } if (found) f->nevents--; - return f; } #define ASSERT_PMC_COUNTING_INSTRUCTIONS() \ @@ -315,66 +298,73 @@ static void test_without_filter(struct kvm_vcpu *vcpu) } static void test_with_filter(struct kvm_vcpu *vcpu, - struct kvm_pmu_event_filter *f) + struct __kvm_pmu_event_filter *__f) { + struct kvm_pmu_event_filter *f = (void *)__f; + vm_ioctl(vcpu->vm, KVM_SET_PMU_EVENT_FILTER, f); run_vcpu_and_sync_pmc_results(vcpu); } static void test_amd_deny_list(struct kvm_vcpu *vcpu) { - uint64_t event = EVENT(0x1C2, 0); - struct kvm_pmu_event_filter *f; + struct __kvm_pmu_event_filter f = { + .action = KVM_PMU_EVENT_DENY, + .nevents = 1, + .events = { + EVENT(0x1C2, 0), + }, + }; - f = create_pmu_event_filter(&event, 1, KVM_PMU_EVENT_DENY, 0); - test_with_filter(vcpu, f); - free(f); + test_with_filter(vcpu, &f); ASSERT_PMC_COUNTING_INSTRUCTIONS(); } static void test_member_deny_list(struct kvm_vcpu *vcpu) { - struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_DENY); + struct __kvm_pmu_event_filter f = base_event_filter; - test_with_filter(vcpu, f); - free(f); + f.action = KVM_PMU_EVENT_DENY; + test_with_filter(vcpu, &f); ASSERT_PMC_NOT_COUNTING_INSTRUCTIONS(); } static void test_member_allow_list(struct kvm_vcpu *vcpu) { - struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_ALLOW); + struct __kvm_pmu_event_filter f = base_event_filter; - test_with_filter(vcpu, f); - free(f); + f.action = KVM_PMU_EVENT_ALLOW; + test_with_filter(vcpu, &f); ASSERT_PMC_COUNTING_INSTRUCTIONS(); } static void test_not_member_deny_list(struct kvm_vcpu *vcpu) { - struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_DENY); + struct __kvm_pmu_event_filter f = base_event_filter; - remove_event(f, INST_RETIRED); - remove_event(f, INTEL_BR_RETIRED); - remove_event(f, AMD_ZEN_BR_RETIRED); - test_with_filter(vcpu, f); - free(f); + f.action = KVM_PMU_EVENT_DENY; + + remove_event(&f, INST_RETIRED); + remove_event(&f, INTEL_BR_RETIRED); + remove_event(&f, AMD_ZEN_BR_RETIRED); + test_with_filter(vcpu, &f); ASSERT_PMC_COUNTING_INSTRUCTIONS(); } static void test_not_member_allow_list(struct kvm_vcpu *vcpu) { - struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_ALLOW); + struct __kvm_pmu_event_filter f = base_event_filter; + + f.action = KVM_PMU_EVENT_ALLOW; - remove_event(f, INST_RETIRED); - remove_event(f, INTEL_BR_RETIRED); - remove_event(f, AMD_ZEN_BR_RETIRED); - test_with_filter(vcpu, f); - free(f); + remove_event(&f, INST_RETIRED); + remove_event(&f, INTEL_BR_RETIRED); + remove_event(&f, AMD_ZEN_BR_RETIRED); + test_with_filter(vcpu, &f); ASSERT_PMC_NOT_COUNTING_INSTRUCTIONS(); } @@ -569,19 +559,16 @@ static void run_masked_events_test(struct kvm_vcpu *vcpu, const uint64_t masked_events[], const int nmasked_events) { - struct kvm_pmu_event_filter *f; + struct __kvm_pmu_event_filter f = { + .nevents = nmasked_events, + .action = KVM_PMU_EVENT_ALLOW, + .flags = KVM_PMU_EVENT_FLAG_MASKED_EVENTS, + }; - f = create_pmu_event_filter(masked_events, nmasked_events, - KVM_PMU_EVENT_ALLOW, - KVM_PMU_EVENT_FLAG_MASKED_EVENTS); - test_with_filter(vcpu, f); - free(f); + memcpy(f.events, masked_events, sizeof(uint64_t) * nmasked_events); + test_with_filter(vcpu, &f); } -/* Matches KVM_PMU_EVENT_FILTER_MAX_EVENTS in pmu.c */ -#define MAX_FILTER_EVENTS 300 -#define MAX_TEST_EVENTS 10 - #define ALLOW_LOADS BIT(0) #define ALLOW_STORES BIT(1) #define ALLOW_LOADS_STORES BIT(2) @@ -753,21 +740,33 @@ static void test_masked_events(struct kvm_vcpu *vcpu) run_masked_events_tests(vcpu, events, nevents); } -static int run_filter_test(struct kvm_vcpu *vcpu, const uint64_t *events, - int nevents, uint32_t flags) +static int set_pmu_event_filter(struct kvm_vcpu *vcpu, + struct __kvm_pmu_event_filter *__f) { - struct kvm_pmu_event_filter *f; - int r; + struct kvm_pmu_event_filter *f = (void *)__f; - f = create_pmu_event_filter(events, nevents, KVM_PMU_EVENT_ALLOW, flags); - r = __vm_ioctl(vcpu->vm, KVM_SET_PMU_EVENT_FILTER, f); - free(f); + return __vm_ioctl(vcpu->vm, KVM_SET_PMU_EVENT_FILTER, f); +} - return r; +static int set_pmu_single_event_filter(struct kvm_vcpu *vcpu, uint64_t event, + uint32_t flags, uint32_t action) +{ + struct __kvm_pmu_event_filter f = { + .nevents = 1, + .flags = flags, + .action = action, + .events = { + event, + }, + }; + + return set_pmu_event_filter(vcpu, &f); } static void test_filter_ioctl(struct kvm_vcpu *vcpu) { + uint8_t nr_fixed_counters = kvm_cpu_property(X86_PROPERTY_PMU_NR_FIXED_COUNTERS); + struct __kvm_pmu_event_filter f; uint64_t e = ~0ul; int r; @@ -775,15 +774,144 @@ static void test_filter_ioctl(struct kvm_vcpu *vcpu) * Unfortunately having invalid bits set in event data is expected to * pass when flags == 0 (bits other than eventsel+umask). */ - r = run_filter_test(vcpu, &e, 1, 0); + r = set_pmu_single_event_filter(vcpu, e, 0, KVM_PMU_EVENT_ALLOW); TEST_ASSERT(r == 0, "Valid PMU Event Filter is failing"); - r = run_filter_test(vcpu, &e, 1, KVM_PMU_EVENT_FLAG_MASKED_EVENTS); + r = set_pmu_single_event_filter(vcpu, e, + KVM_PMU_EVENT_FLAG_MASKED_EVENTS, + KVM_PMU_EVENT_ALLOW); TEST_ASSERT(r != 0, "Invalid PMU Event Filter is expected to fail"); e = KVM_PMU_ENCODE_MASKED_ENTRY(0xff, 0xff, 0xff, 0xf); - r = run_filter_test(vcpu, &e, 1, KVM_PMU_EVENT_FLAG_MASKED_EVENTS); + r = set_pmu_single_event_filter(vcpu, e, + KVM_PMU_EVENT_FLAG_MASKED_EVENTS, + KVM_PMU_EVENT_ALLOW); TEST_ASSERT(r == 0, "Valid PMU Event Filter is failing"); + + f = base_event_filter; + f.action = PMU_EVENT_FILTER_INVALID_ACTION; + r = set_pmu_event_filter(vcpu, &f); + TEST_ASSERT(r, "Set invalid action is expected to fail"); + + f = base_event_filter; + f.flags = PMU_EVENT_FILTER_INVALID_FLAGS; + r = set_pmu_event_filter(vcpu, &f); + TEST_ASSERT(r, "Set invalid flags is expected to fail"); + + f = base_event_filter; + f.nevents = PMU_EVENT_FILTER_INVALID_NEVENTS; + r = set_pmu_event_filter(vcpu, &f); + TEST_ASSERT(r, "Exceeding the max number of filter events should fail"); + + f = base_event_filter; + f.fixed_counter_bitmap = ~GENMASK_ULL(nr_fixed_counters, 0); + r = set_pmu_event_filter(vcpu, &f); + TEST_ASSERT(!r, "Masking non-existent fixed counters should be allowed"); +} + +static void intel_run_fixed_counter_guest_code(uint8_t fixed_ctr_idx) +{ + for (;;) { + wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0); + wrmsr(MSR_CORE_PERF_FIXED_CTR0 + fixed_ctr_idx, 0); + + /* Only OS_EN bit is enabled for fixed counter[idx]. */ + wrmsr(MSR_CORE_PERF_FIXED_CTR_CTRL, BIT_ULL(4 * fixed_ctr_idx)); + wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, + BIT_ULL(INTEL_PMC_IDX_FIXED + fixed_ctr_idx)); + __asm__ __volatile__("loop ." : "+c"((int){NUM_BRANCHES})); + wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0); + + GUEST_SYNC(rdmsr(MSR_CORE_PERF_FIXED_CTR0 + fixed_ctr_idx)); + } +} + +static uint64_t test_with_fixed_counter_filter(struct kvm_vcpu *vcpu, + uint32_t action, uint32_t bitmap) +{ + struct __kvm_pmu_event_filter f = { + .action = action, + .fixed_counter_bitmap = bitmap, + }; + set_pmu_event_filter(vcpu, &f); + + return run_vcpu_to_sync(vcpu); +} + +static uint64_t test_set_gp_and_fixed_event_filter(struct kvm_vcpu *vcpu, + uint32_t action, + uint32_t bitmap) +{ + struct __kvm_pmu_event_filter f = base_event_filter; + + f.action = action; + f.fixed_counter_bitmap = bitmap; + set_pmu_event_filter(vcpu, &f); + + return run_vcpu_to_sync(vcpu); +} + +static void __test_fixed_counter_bitmap(struct kvm_vcpu *vcpu, uint8_t idx, + uint8_t nr_fixed_counters) +{ + unsigned int i; + uint32_t bitmap; + uint64_t count; + + TEST_ASSERT(nr_fixed_counters < sizeof(bitmap) * 8, + "Invalid nr_fixed_counters"); + + /* + * Check the fixed performance counter can count normally when KVM + * userspace doesn't set any pmu filter. + */ + count = run_vcpu_to_sync(vcpu); + TEST_ASSERT(count, "Unexpected count value: %ld\n", count); + + for (i = 0; i < BIT(nr_fixed_counters); i++) { + bitmap = BIT(i); + count = test_with_fixed_counter_filter(vcpu, KVM_PMU_EVENT_ALLOW, + bitmap); + TEST_ASSERT_EQ(!!count, !!(bitmap & BIT(idx))); + + count = test_with_fixed_counter_filter(vcpu, KVM_PMU_EVENT_DENY, + bitmap); + TEST_ASSERT_EQ(!!count, !(bitmap & BIT(idx))); + + /* + * Check that fixed_counter_bitmap has higher priority than + * events[] when both are set. + */ + count = test_set_gp_and_fixed_event_filter(vcpu, + KVM_PMU_EVENT_ALLOW, + bitmap); + TEST_ASSERT_EQ(!!count, !!(bitmap & BIT(idx))); + + count = test_set_gp_and_fixed_event_filter(vcpu, + KVM_PMU_EVENT_DENY, + bitmap); + TEST_ASSERT_EQ(!!count, !(bitmap & BIT(idx))); + } +} + +static void test_fixed_counter_bitmap(void) +{ + uint8_t nr_fixed_counters = kvm_cpu_property(X86_PROPERTY_PMU_NR_FIXED_COUNTERS); + struct kvm_vm *vm; + struct kvm_vcpu *vcpu; + uint8_t idx; + + /* + * Check that pmu_event_filter works as expected when it's applied to + * fixed performance counters. + */ + for (idx = 0; idx < nr_fixed_counters; idx++) { + vm = vm_create_with_one_vcpu(&vcpu, + intel_run_fixed_counter_guest_code); + vcpu_args_set(vcpu, 1, idx); + __test_fixed_counter_bitmap(vcpu, idx, nr_fixed_counters); + kvm_vm_free(vm); + } } int main(int argc, char *argv[]) @@ -829,6 +957,7 @@ int main(int argc, char *argv[]) kvm_vm_free(vm); test_pmu_config_disable(guest_code); + test_fixed_counter_bitmap(); return 0; } diff --git a/tools/testing/selftests/kvm/x86_64/recalc_apic_map_test.c b/tools/testing/selftests/kvm/x86_64/recalc_apic_map_test.c index 4c416ebe7d66..cbc92a862ea9 100644 --- a/tools/testing/selftests/kvm/x86_64/recalc_apic_map_test.c +++ b/tools/testing/selftests/kvm/x86_64/recalc_apic_map_test.c @@ -57,7 +57,7 @@ int main(void) for (i = 0; i < KVM_MAX_VCPUS; i++) vcpu_set_msr(vcpus[i], MSR_IA32_APICBASE, LAPIC_X2APIC); - ASSERT_EQ(pthread_create(&thread, NULL, race, vcpus[0]), 0); + TEST_ASSERT_EQ(pthread_create(&thread, NULL, race, vcpus[0]), 0); vcpuN = vcpus[KVM_MAX_VCPUS - 1]; for (t = time(NULL) + TIMEOUT; time(NULL) < t;) { @@ -65,8 +65,8 @@ int main(void) vcpu_set_msr(vcpuN, MSR_IA32_APICBASE, LAPIC_DISABLED); } - ASSERT_EQ(pthread_cancel(thread), 0); - ASSERT_EQ(pthread_join(thread, NULL), 0); + TEST_ASSERT_EQ(pthread_cancel(thread), 0); + TEST_ASSERT_EQ(pthread_join(thread, NULL), 0); kvm_vm_free(vm); diff --git a/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c b/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c index b25d7556b638..366cf18600bc 100644 --- a/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c +++ b/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c @@ -20,7 +20,7 @@ static void guest_bsp_vcpu(void *arg) { GUEST_SYNC(1); - GUEST_ASSERT(get_bsp_flag() != 0); + GUEST_ASSERT_NE(get_bsp_flag(), 0); GUEST_DONE(); } @@ -29,7 +29,7 @@ static void guest_not_bsp_vcpu(void *arg) { GUEST_SYNC(1); - GUEST_ASSERT(get_bsp_flag() == 0); + GUEST_ASSERT_EQ(get_bsp_flag(), 0); GUEST_DONE(); } @@ -65,7 +65,7 @@ static void run_vcpu(struct kvm_vcpu *vcpu) stage); break; case UCALL_ABORT: - REPORT_GUEST_ASSERT_2(uc, "values: %#lx, %#lx"); + REPORT_GUEST_ASSERT(uc); default: TEST_ASSERT(false, "Unexpected exit: %s", exit_reason_str(vcpu->run->exit_reason)); diff --git a/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c b/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c index 4e2479716da6..7ee44496cf97 100644 --- a/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c +++ b/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c @@ -8,7 +8,6 @@ * Copyright (C) 2021, Red Hat, Inc. * */ - #include <stdatomic.h> #include <stdio.h> #include <unistd.h> @@ -34,13 +33,12 @@ static void l2_guest_code_int(void); static void guest_int_handler(struct ex_regs *regs) { int_fired++; - GUEST_ASSERT_2(regs->rip == (unsigned long)l2_guest_code_int, - regs->rip, (unsigned long)l2_guest_code_int); + GUEST_ASSERT_EQ(regs->rip, (unsigned long)l2_guest_code_int); } static void l2_guest_code_int(void) { - GUEST_ASSERT_1(int_fired == 1, int_fired); + GUEST_ASSERT_EQ(int_fired, 1); /* * Same as the vmmcall() function, but with a ud2 sneaked after the @@ -53,7 +51,7 @@ static void l2_guest_code_int(void) : "rbx", "rdx", "rsi", "rdi", "r8", "r9", "r10", "r11", "r12", "r13", "r14", "r15"); - GUEST_ASSERT_1(bp_fired == 1, bp_fired); + GUEST_ASSERT_EQ(bp_fired, 1); hlt(); } @@ -66,9 +64,9 @@ static void guest_nmi_handler(struct ex_regs *regs) if (nmi_stage_get() == 1) { vmmcall(); - GUEST_ASSERT(false); + GUEST_FAIL("Unexpected resume after VMMCALL"); } else { - GUEST_ASSERT_1(nmi_stage_get() == 3, nmi_stage_get()); + GUEST_ASSERT_EQ(nmi_stage_get(), 3); GUEST_DONE(); } } @@ -104,7 +102,8 @@ static void l1_guest_code(struct svm_test_data *svm, uint64_t is_nmi, uint64_t i } run_guest(vmcb, svm->vmcb_gpa); - GUEST_ASSERT_3(vmcb->control.exit_code == SVM_EXIT_VMMCALL, + __GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_VMMCALL, + "Expected VMMCAL #VMEXIT, got '0x%x', info1 = '0x%llx, info2 = '0x%llx'", vmcb->control.exit_code, vmcb->control.exit_info_1, vmcb->control.exit_info_2); @@ -112,7 +111,7 @@ static void l1_guest_code(struct svm_test_data *svm, uint64_t is_nmi, uint64_t i clgi(); x2apic_write_reg(APIC_ICR, APIC_DEST_SELF | APIC_INT_ASSERT | APIC_DM_NMI); - GUEST_ASSERT_1(nmi_stage_get() == 1, nmi_stage_get()); + GUEST_ASSERT_EQ(nmi_stage_get(), 1); nmi_stage_inc(); stgi(); @@ -133,7 +132,8 @@ static void l1_guest_code(struct svm_test_data *svm, uint64_t is_nmi, uint64_t i vmcb->control.next_rip = vmcb->save.rip + 2; run_guest(vmcb, svm->vmcb_gpa); - GUEST_ASSERT_3(vmcb->control.exit_code == SVM_EXIT_HLT, + __GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_HLT, + "Expected HLT #VMEXIT, got '0x%x', info1 = '0x%llx, info2 = '0x%llx'", vmcb->control.exit_code, vmcb->control.exit_info_1, vmcb->control.exit_info_2); @@ -185,7 +185,7 @@ static void run_test(bool is_nmi) switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - REPORT_GUEST_ASSERT_3(uc, "vals = 0x%lx 0x%lx 0x%lx"); + REPORT_GUEST_ASSERT(uc); break; /* NOT REACHED */ case UCALL_DONE: diff --git a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c index 2da89fdc2471..00965ba33f73 100644 --- a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c +++ b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c @@ -15,6 +15,7 @@ #include <stdlib.h> #include <string.h> #include <sys/ioctl.h> +#include <pthread.h> #include "test_util.h" #include "kvm_util.h" @@ -80,6 +81,133 @@ static void compare_vcpu_events(struct kvm_vcpu_events *left, #define TEST_SYNC_FIELDS (KVM_SYNC_X86_REGS|KVM_SYNC_X86_SREGS|KVM_SYNC_X86_EVENTS) #define INVALID_SYNC_FIELD 0x80000000 +/* + * Set an exception as pending *and* injected while KVM is processing events. + * KVM is supposed to ignore/drop pending exceptions if userspace is also + * requesting that an exception be injected. + */ +static void *race_events_inj_pen(void *arg) +{ + struct kvm_run *run = (struct kvm_run *)arg; + struct kvm_vcpu_events *events = &run->s.regs.events; + + WRITE_ONCE(events->exception.nr, UD_VECTOR); + + for (;;) { + WRITE_ONCE(run->kvm_dirty_regs, KVM_SYNC_X86_EVENTS); + WRITE_ONCE(events->flags, 0); + WRITE_ONCE(events->exception.injected, 1); + WRITE_ONCE(events->exception.pending, 1); + + pthread_testcancel(); + } + + return NULL; +} + +/* + * Set an invalid exception vector while KVM is processing events. KVM is + * supposed to reject any vector >= 32, as well as NMIs (vector 2). + */ +static void *race_events_exc(void *arg) +{ + struct kvm_run *run = (struct kvm_run *)arg; + struct kvm_vcpu_events *events = &run->s.regs.events; + + for (;;) { + WRITE_ONCE(run->kvm_dirty_regs, KVM_SYNC_X86_EVENTS); + WRITE_ONCE(events->flags, 0); + WRITE_ONCE(events->exception.nr, UD_VECTOR); + WRITE_ONCE(events->exception.pending, 1); + WRITE_ONCE(events->exception.nr, 255); + + pthread_testcancel(); + } + + return NULL; +} + +/* + * Toggle CR4.PAE while KVM is processing SREGS, EFER.LME=1 with CR4.PAE=0 is + * illegal, and KVM's MMU heavily relies on vCPU state being valid. + */ +static noinline void *race_sregs_cr4(void *arg) +{ + struct kvm_run *run = (struct kvm_run *)arg; + __u64 *cr4 = &run->s.regs.sregs.cr4; + __u64 pae_enabled = *cr4; + __u64 pae_disabled = *cr4 & ~X86_CR4_PAE; + + for (;;) { + WRITE_ONCE(run->kvm_dirty_regs, KVM_SYNC_X86_SREGS); + WRITE_ONCE(*cr4, pae_enabled); + asm volatile(".rept 512\n\t" + "nop\n\t" + ".endr"); + WRITE_ONCE(*cr4, pae_disabled); + + pthread_testcancel(); + } + + return NULL; +} + +static void race_sync_regs(void *racer) +{ + const time_t TIMEOUT = 2; /* seconds, roughly */ + struct kvm_x86_state *state; + struct kvm_translation tr; + struct kvm_vcpu *vcpu; + struct kvm_run *run; + struct kvm_vm *vm; + pthread_t thread; + time_t t; + + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + run = vcpu->run; + + run->kvm_valid_regs = KVM_SYNC_X86_SREGS; + vcpu_run(vcpu); + run->kvm_valid_regs = 0; + + /* Save state *before* spawning the thread that mucks with vCPU state. */ + state = vcpu_save_state(vcpu); + + /* + * Selftests run 64-bit guests by default, both EFER.LME and CR4.PAE + * should already be set in guest state. + */ + TEST_ASSERT((run->s.regs.sregs.cr4 & X86_CR4_PAE) && + (run->s.regs.sregs.efer & EFER_LME), + "vCPU should be in long mode, CR4.PAE=%d, EFER.LME=%d", + !!(run->s.regs.sregs.cr4 & X86_CR4_PAE), + !!(run->s.regs.sregs.efer & EFER_LME)); + + TEST_ASSERT_EQ(pthread_create(&thread, NULL, racer, (void *)run), 0); + + for (t = time(NULL) + TIMEOUT; time(NULL) < t;) { + /* + * Reload known good state if the vCPU triple faults, e.g. due + * to the unhandled #GPs being injected. VMX preserves state + * on shutdown, but SVM synthesizes an INIT as the VMCB state + * is architecturally undefined on triple fault. + */ + if (!__vcpu_run(vcpu) && run->exit_reason == KVM_EXIT_SHUTDOWN) + vcpu_load_state(vcpu, state); + + if (racer == race_sregs_cr4) { + tr = (struct kvm_translation) { .linear_address = 0 }; + __vcpu_ioctl(vcpu, KVM_TRANSLATE, &tr); + } + } + + TEST_ASSERT_EQ(pthread_cancel(thread), 0); + TEST_ASSERT_EQ(pthread_join(thread, NULL), 0); + + kvm_x86_state_cleanup(state); + kvm_vm_free(vm); +} + int main(int argc, char *argv[]) { struct kvm_vcpu *vcpu; @@ -218,5 +346,9 @@ int main(int argc, char *argv[]) kvm_vm_free(vm); + race_sync_regs(race_sregs_cr4); + race_sync_regs(race_events_exc); + race_sync_regs(race_events_inj_pen); + return 0; } diff --git a/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c b/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c index c9f67702f657..12b0964f4f13 100644 --- a/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c +++ b/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c @@ -84,7 +84,7 @@ static void run_vcpu(struct kvm_vcpu *vcpu, int stage) ksft_test_result_pass("stage %d passed\n", stage + 1); return; case UCALL_ABORT: - REPORT_GUEST_ASSERT_2(uc, "values: %#lx, %#lx"); + REPORT_GUEST_ASSERT(uc); default: TEST_ASSERT(false, "Unexpected exit: %s", exit_reason_str(vcpu->run->exit_reason)); @@ -103,39 +103,39 @@ int main(void) vm = vm_create_with_one_vcpu(&vcpu, guest_code); val = 0; - ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), val); - ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val); + TEST_ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), val); + TEST_ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val); /* Guest: writes to MSR_IA32_TSC affect both MSRs. */ run_vcpu(vcpu, 1); val = 1ull * GUEST_STEP; - ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), val); - ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val); + TEST_ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), val); + TEST_ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val); /* Guest: writes to MSR_IA32_TSC_ADJUST affect both MSRs. */ run_vcpu(vcpu, 2); val = 2ull * GUEST_STEP; - ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), val); - ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val); + TEST_ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), val); + TEST_ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val); /* * Host: writes to MSR_IA32_TSC set the host-side offset * and therefore do not change MSR_IA32_TSC_ADJUST. */ vcpu_set_msr(vcpu, MSR_IA32_TSC, HOST_ADJUST + val); - ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), HOST_ADJUST + val); - ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val); + TEST_ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), HOST_ADJUST + val); + TEST_ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val); run_vcpu(vcpu, 3); /* Host: writes to MSR_IA32_TSC_ADJUST do not modify the TSC. */ vcpu_set_msr(vcpu, MSR_IA32_TSC_ADJUST, UNITY * 123456); - ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), HOST_ADJUST + val); - ASSERT_EQ(vcpu_get_msr(vcpu, MSR_IA32_TSC_ADJUST), UNITY * 123456); + TEST_ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), HOST_ADJUST + val); + TEST_ASSERT_EQ(vcpu_get_msr(vcpu, MSR_IA32_TSC_ADJUST), UNITY * 123456); /* Restore previous value. */ vcpu_set_msr(vcpu, MSR_IA32_TSC_ADJUST, val); - ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), HOST_ADJUST + val); - ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val); + TEST_ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), HOST_ADJUST + val); + TEST_ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val); /* * Guest: writes to MSR_IA32_TSC_ADJUST do not destroy the @@ -143,8 +143,8 @@ int main(void) */ run_vcpu(vcpu, 4); val = 3ull * GUEST_STEP; - ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), HOST_ADJUST + val); - ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val); + TEST_ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), HOST_ADJUST + val); + TEST_ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val); /* * Guest: writes to MSR_IA32_TSC affect both MSRs, so the host-side @@ -152,8 +152,8 @@ int main(void) */ run_vcpu(vcpu, 5); val = 4ull * GUEST_STEP; - ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), val); - ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val - HOST_ADJUST); + TEST_ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), val); + TEST_ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val - HOST_ADJUST); kvm_vm_free(vm); diff --git a/tools/testing/selftests/kvm/x86_64/userspace_io_test.c b/tools/testing/selftests/kvm/x86_64/userspace_io_test.c index 0cb51fa42773..255c50b0dc32 100644 --- a/tools/testing/selftests/kvm/x86_64/userspace_io_test.c +++ b/tools/testing/selftests/kvm/x86_64/userspace_io_test.c @@ -20,8 +20,8 @@ static void guest_ins_port80(uint8_t *buffer, unsigned int count) end = (unsigned long)buffer + 8192; asm volatile("cld; rep; insb" : "+D"(buffer), "+c"(count) : "d"(0x80) : "memory"); - GUEST_ASSERT_1(count == 0, count); - GUEST_ASSERT_2((unsigned long)buffer == end, buffer, end); + GUEST_ASSERT_EQ(count, 0); + GUEST_ASSERT_EQ((unsigned long)buffer, end); } static void guest_code(void) @@ -43,7 +43,9 @@ static void guest_code(void) memset(buffer, 0, sizeof(buffer)); guest_ins_port80(buffer, 8192); for (i = 0; i < 8192; i++) - GUEST_ASSERT_2(buffer[i] == 0xaa, i, buffer[i]); + __GUEST_ASSERT(buffer[i] == 0xaa, + "Expected '0xaa', got '0x%x' at buffer[%u]", + buffer[i], i); GUEST_DONE(); } @@ -91,7 +93,7 @@ int main(int argc, char *argv[]) case UCALL_DONE: break; case UCALL_ABORT: - REPORT_GUEST_ASSERT_2(uc, "argN+1 = 0x%lx, argN+2 = 0x%lx"); + REPORT_GUEST_ASSERT(uc); default: TEST_FAIL("Unknown ucall %lu", uc.cmd); } diff --git a/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c b/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c index be0bdb8c6f78..a9b827c69f32 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c @@ -50,7 +50,7 @@ static void set_timer(void) timer.it_value.tv_sec = 0; timer.it_value.tv_usec = 200; timer.it_interval = timer.it_value; - ASSERT_EQ(setitimer(ITIMER_REAL, &timer, NULL), 0); + TEST_ASSERT_EQ(setitimer(ITIMER_REAL, &timer, NULL), 0); } static void set_or_clear_invalid_guest_state(struct kvm_vcpu *vcpu, bool set) diff --git a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c index 4c90f76930f9..ebbcb0a3f743 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c @@ -10,7 +10,6 @@ * and check it can be retrieved with KVM_GET_MSR, also test * the invalid LBR formats are rejected. */ - #define _GNU_SOURCE /* for program_invocation_short_name */ #include <sys/ioctl.h> @@ -52,23 +51,24 @@ static const union perf_capabilities format_caps = { .pebs_format = -1, }; +static void guest_test_perf_capabilities_gp(uint64_t val) +{ + uint8_t vector = wrmsr_safe(MSR_IA32_PERF_CAPABILITIES, val); + + __GUEST_ASSERT(vector == GP_VECTOR, + "Expected #GP for value '0x%llx', got vector '0x%x'", + val, vector); +} + static void guest_code(uint64_t current_val) { - uint8_t vector; int i; - vector = wrmsr_safe(MSR_IA32_PERF_CAPABILITIES, current_val); - GUEST_ASSERT_2(vector == GP_VECTOR, current_val, vector); - - vector = wrmsr_safe(MSR_IA32_PERF_CAPABILITIES, 0); - GUEST_ASSERT_2(vector == GP_VECTOR, 0, vector); + guest_test_perf_capabilities_gp(current_val); + guest_test_perf_capabilities_gp(0); - for (i = 0; i < 64; i++) { - vector = wrmsr_safe(MSR_IA32_PERF_CAPABILITIES, - current_val ^ BIT_ULL(i)); - GUEST_ASSERT_2(vector == GP_VECTOR, - current_val ^ BIT_ULL(i), vector); - } + for (i = 0; i < 64; i++) + guest_test_perf_capabilities_gp(current_val ^ BIT_ULL(i)); GUEST_DONE(); } @@ -95,7 +95,7 @@ static void test_guest_wrmsr_perf_capabilities(union perf_capabilities host_cap) switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - REPORT_GUEST_ASSERT_2(uc, "val = 0x%lx, vector = %lu"); + REPORT_GUEST_ASSERT(uc); break; case UCALL_DONE: break; @@ -103,7 +103,8 @@ static void test_guest_wrmsr_perf_capabilities(union perf_capabilities host_cap) TEST_FAIL("Unexpected ucall: %lu", uc.cmd); } - ASSERT_EQ(vcpu_get_msr(vcpu, MSR_IA32_PERF_CAPABILITIES), host_cap.capabilities); + TEST_ASSERT_EQ(vcpu_get_msr(vcpu, MSR_IA32_PERF_CAPABILITIES), + host_cap.capabilities); vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, host_cap.capabilities); diff --git a/tools/testing/selftests/kvm/x86_64/xapic_state_test.c b/tools/testing/selftests/kvm/x86_64/xapic_state_test.c index 396c13f42457..ab75b873a4ad 100644 --- a/tools/testing/selftests/kvm/x86_64/xapic_state_test.c +++ b/tools/testing/selftests/kvm/x86_64/xapic_state_test.c @@ -65,17 +65,17 @@ static void ____test_icr(struct xapic_vcpu *x, uint64_t val) vcpu_ioctl(vcpu, KVM_SET_LAPIC, &xapic); vcpu_run(vcpu); - ASSERT_EQ(get_ucall(vcpu, &uc), UCALL_SYNC); - ASSERT_EQ(uc.args[1], val); + TEST_ASSERT_EQ(get_ucall(vcpu, &uc), UCALL_SYNC); + TEST_ASSERT_EQ(uc.args[1], val); vcpu_ioctl(vcpu, KVM_GET_LAPIC, &xapic); icr = (u64)(*((u32 *)&xapic.regs[APIC_ICR])) | (u64)(*((u32 *)&xapic.regs[APIC_ICR2])) << 32; if (!x->is_x2apic) { val &= (-1u | (0xffull << (32 + 24))); - ASSERT_EQ(icr, val & ~APIC_ICR_BUSY); + TEST_ASSERT_EQ(icr, val & ~APIC_ICR_BUSY); } else { - ASSERT_EQ(icr & ~APIC_ICR_BUSY, val & ~APIC_ICR_BUSY); + TEST_ASSERT_EQ(icr & ~APIC_ICR_BUSY, val & ~APIC_ICR_BUSY); } } diff --git a/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c b/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c index 905bd5ae4431..77d04a7bdadd 100644 --- a/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c +++ b/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c @@ -4,7 +4,6 @@ * * Copyright (C) 2022, Google LLC. */ - #include <fcntl.h> #include <stdio.h> #include <stdlib.h> @@ -20,13 +19,14 @@ * Assert that architectural dependency rules are satisfied, e.g. that AVX is * supported if and only if SSE is supported. */ -#define ASSERT_XFEATURE_DEPENDENCIES(supported_xcr0, xfeatures, dependencies) \ -do { \ - uint64_t __supported = (supported_xcr0) & ((xfeatures) | (dependencies)); \ - \ - GUEST_ASSERT_3((__supported & (xfeatures)) != (xfeatures) || \ - __supported == ((xfeatures) | (dependencies)), \ - __supported, (xfeatures), (dependencies)); \ +#define ASSERT_XFEATURE_DEPENDENCIES(supported_xcr0, xfeatures, dependencies) \ +do { \ + uint64_t __supported = (supported_xcr0) & ((xfeatures) | (dependencies)); \ + \ + __GUEST_ASSERT((__supported & (xfeatures)) != (xfeatures) || \ + __supported == ((xfeatures) | (dependencies)), \ + "supported = 0x%llx, xfeatures = 0x%llx, dependencies = 0x%llx", \ + __supported, (xfeatures), (dependencies)); \ } while (0) /* @@ -41,7 +41,8 @@ do { \ do { \ uint64_t __supported = (supported_xcr0) & (xfeatures); \ \ - GUEST_ASSERT_2(!__supported || __supported == (xfeatures), \ + __GUEST_ASSERT(!__supported || __supported == (xfeatures), \ + "supported = 0x%llx, xfeatures = 0x%llx", \ __supported, (xfeatures)); \ } while (0) @@ -79,14 +80,18 @@ static void guest_code(void) XFEATURE_MASK_XTILE); vector = xsetbv_safe(0, supported_xcr0); - GUEST_ASSERT_2(!vector, supported_xcr0, vector); + __GUEST_ASSERT(!vector, + "Expected success on XSETBV(0x%llx), got vector '0x%x'", + supported_xcr0, vector); for (i = 0; i < 64; i++) { if (supported_xcr0 & BIT_ULL(i)) continue; vector = xsetbv_safe(0, supported_xcr0 | BIT_ULL(i)); - GUEST_ASSERT_3(vector == GP_VECTOR, supported_xcr0, vector, BIT_ULL(i)); + __GUEST_ASSERT(vector == GP_VECTOR, + "Expected #GP on XSETBV(0x%llx), supported XCR0 = %llx, got vector '0x%x'", + BIT_ULL(i), supported_xcr0, vector); } GUEST_DONE(); @@ -117,7 +122,7 @@ int main(int argc, char *argv[]) switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - REPORT_GUEST_ASSERT_3(uc, "0x%lx 0x%lx 0x%lx"); + REPORT_GUEST_ASSERT(uc); break; case UCALL_DONE: goto done; diff --git a/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c b/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c index c94cde3b523f..e149d0574961 100644 --- a/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c +++ b/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c @@ -108,16 +108,16 @@ int main(int argc, char *argv[]) vcpu_run(vcpu); if (run->exit_reason == KVM_EXIT_XEN) { - ASSERT_EQ(run->xen.type, KVM_EXIT_XEN_HCALL); - ASSERT_EQ(run->xen.u.hcall.cpl, 0); - ASSERT_EQ(run->xen.u.hcall.longmode, 1); - ASSERT_EQ(run->xen.u.hcall.input, INPUTVALUE); - ASSERT_EQ(run->xen.u.hcall.params[0], ARGVALUE(1)); - ASSERT_EQ(run->xen.u.hcall.params[1], ARGVALUE(2)); - ASSERT_EQ(run->xen.u.hcall.params[2], ARGVALUE(3)); - ASSERT_EQ(run->xen.u.hcall.params[3], ARGVALUE(4)); - ASSERT_EQ(run->xen.u.hcall.params[4], ARGVALUE(5)); - ASSERT_EQ(run->xen.u.hcall.params[5], ARGVALUE(6)); + TEST_ASSERT_EQ(run->xen.type, KVM_EXIT_XEN_HCALL); + TEST_ASSERT_EQ(run->xen.u.hcall.cpl, 0); + TEST_ASSERT_EQ(run->xen.u.hcall.longmode, 1); + TEST_ASSERT_EQ(run->xen.u.hcall.input, INPUTVALUE); + TEST_ASSERT_EQ(run->xen.u.hcall.params[0], ARGVALUE(1)); + TEST_ASSERT_EQ(run->xen.u.hcall.params[1], ARGVALUE(2)); + TEST_ASSERT_EQ(run->xen.u.hcall.params[2], ARGVALUE(3)); + TEST_ASSERT_EQ(run->xen.u.hcall.params[3], ARGVALUE(4)); + TEST_ASSERT_EQ(run->xen.u.hcall.params[4], ARGVALUE(5)); + TEST_ASSERT_EQ(run->xen.u.hcall.params[5], ARGVALUE(6)); run->xen.u.hcall.result = RETVALUE; continue; } diff --git a/tools/testing/selftests/landlock/fs_test.c b/tools/testing/selftests/landlock/fs_test.c index 83d565569512..251594306d40 100644 --- a/tools/testing/selftests/landlock/fs_test.c +++ b/tools/testing/selftests/landlock/fs_test.c @@ -113,7 +113,7 @@ static bool supports_filesystem(const char *const filesystem) { char str[32]; int len; - bool res; + bool res = true; FILE *const inf = fopen("/proc/filesystems", "r"); /* @@ -125,14 +125,16 @@ static bool supports_filesystem(const char *const filesystem) /* filesystem can be null for bind mounts. */ if (!filesystem) - return true; + goto out; len = snprintf(str, sizeof(str), "nodev\t%s\n", filesystem); if (len >= sizeof(str)) /* Ignores too-long filesystem names. */ - return true; + goto out; res = fgrep(inf, str); + +out: fclose(inf); return res; } diff --git a/tools/testing/selftests/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c index dba0e8ba002f..3df008677239 100644 --- a/tools/testing/selftests/memfd/memfd_test.c +++ b/tools/testing/selftests/memfd/memfd_test.c @@ -18,6 +18,7 @@ #include <sys/syscall.h> #include <sys/wait.h> #include <unistd.h> +#include <ctype.h> #include "common.h" @@ -43,7 +44,6 @@ */ static size_t mfd_def_size = MFD_DEF_SIZE; static const char *memfd_str = MEMFD_STR; -static pid_t spawn_newpid_thread(unsigned int flags, int (*fn)(void *)); static int newpid_thread_fn2(void *arg); static void join_newpid_thread(pid_t pid); @@ -96,12 +96,12 @@ static void sysctl_assert_write(const char *val) int fd = open("/proc/sys/vm/memfd_noexec", O_WRONLY | O_CLOEXEC); if (fd < 0) { - printf("open sysctl failed\n"); + printf("open sysctl failed: %m\n"); abort(); } if (write(fd, val, strlen(val)) < 0) { - printf("write sysctl failed\n"); + printf("write sysctl %s failed: %m\n", val); abort(); } } @@ -111,7 +111,7 @@ static void sysctl_fail_write(const char *val) int fd = open("/proc/sys/vm/memfd_noexec", O_WRONLY | O_CLOEXEC); if (fd < 0) { - printf("open sysctl failed\n"); + printf("open sysctl failed: %m\n"); abort(); } @@ -122,6 +122,33 @@ static void sysctl_fail_write(const char *val) } } +static void sysctl_assert_equal(const char *val) +{ + char *p, buf[128] = {}; + int fd = open("/proc/sys/vm/memfd_noexec", O_RDONLY | O_CLOEXEC); + + if (fd < 0) { + printf("open sysctl failed: %m\n"); + abort(); + } + + if (read(fd, buf, sizeof(buf)) < 0) { + printf("read sysctl failed: %m\n"); + abort(); + } + + /* Strip trailing whitespace. */ + p = buf; + while (!isspace(*p)) + p++; + *p = '\0'; + + if (strcmp(buf, val) != 0) { + printf("unexpected sysctl value: expected %s, got %s\n", val, buf); + abort(); + } +} + static int mfd_assert_reopen_fd(int fd_in) { int fd; @@ -736,7 +763,7 @@ static int idle_thread_fn(void *arg) return 0; } -static pid_t spawn_idle_thread(unsigned int flags) +static pid_t spawn_thread(unsigned int flags, int (*fn)(void *), void *arg) { uint8_t *stack; pid_t pid; @@ -747,10 +774,7 @@ static pid_t spawn_idle_thread(unsigned int flags) abort(); } - pid = clone(idle_thread_fn, - stack + STACK_SIZE, - SIGCHLD | flags, - NULL); + pid = clone(fn, stack + STACK_SIZE, SIGCHLD | flags, arg); if (pid < 0) { printf("clone() failed: %m\n"); abort(); @@ -759,6 +783,33 @@ static pid_t spawn_idle_thread(unsigned int flags) return pid; } +static void join_thread(pid_t pid) +{ + int wstatus; + + if (waitpid(pid, &wstatus, 0) < 0) { + printf("newpid thread: waitpid() failed: %m\n"); + abort(); + } + + if (WIFEXITED(wstatus) && WEXITSTATUS(wstatus) != 0) { + printf("newpid thread: exited with non-zero error code %d\n", + WEXITSTATUS(wstatus)); + abort(); + } + + if (WIFSIGNALED(wstatus)) { + printf("newpid thread: killed by signal %d\n", + WTERMSIG(wstatus)); + abort(); + } +} + +static pid_t spawn_idle_thread(unsigned int flags) +{ + return spawn_thread(flags, idle_thread_fn, NULL); +} + static void join_idle_thread(pid_t pid) { kill(pid, SIGTERM); @@ -1111,109 +1162,260 @@ static void test_noexec_seal(void) close(fd); } -static void test_sysctl_child(void) +static void test_sysctl_sysctl0(void) { int fd; - int pid; - printf("%s sysctl 0\n", memfd_str); - sysctl_assert_write("0"); - fd = mfd_assert_new("kern_memfd_sysctl_0", + sysctl_assert_equal("0"); + + fd = mfd_assert_new("kern_memfd_sysctl_0_dfl", mfd_def_size, MFD_CLOEXEC | MFD_ALLOW_SEALING); - mfd_assert_mode(fd, 0777); mfd_assert_has_seals(fd, 0); mfd_assert_chmod(fd, 0644); close(fd); +} - printf("%s sysctl 1\n", memfd_str); - sysctl_assert_write("1"); - fd = mfd_assert_new("kern_memfd_sysctl_1", +static void test_sysctl_set_sysctl0(void) +{ + sysctl_assert_write("0"); + test_sysctl_sysctl0(); +} + +static void test_sysctl_sysctl1(void) +{ + int fd; + + sysctl_assert_equal("1"); + + fd = mfd_assert_new("kern_memfd_sysctl_1_dfl", mfd_def_size, MFD_CLOEXEC | MFD_ALLOW_SEALING); + mfd_assert_mode(fd, 0666); + mfd_assert_has_seals(fd, F_SEAL_EXEC); + mfd_fail_chmod(fd, 0777); + close(fd); - printf("%s child ns\n", memfd_str); - pid = spawn_newpid_thread(CLONE_NEWPID, newpid_thread_fn2); - join_newpid_thread(pid); + fd = mfd_assert_new("kern_memfd_sysctl_1_exec", + mfd_def_size, + MFD_CLOEXEC | MFD_EXEC | MFD_ALLOW_SEALING); + mfd_assert_mode(fd, 0777); + mfd_assert_has_seals(fd, 0); + mfd_assert_chmod(fd, 0644); + close(fd); + fd = mfd_assert_new("kern_memfd_sysctl_1_noexec", + mfd_def_size, + MFD_CLOEXEC | MFD_NOEXEC_SEAL | MFD_ALLOW_SEALING); mfd_assert_mode(fd, 0666); mfd_assert_has_seals(fd, F_SEAL_EXEC); mfd_fail_chmod(fd, 0777); - sysctl_fail_write("0"); close(fd); - - printf("%s sysctl 2\n", memfd_str); - sysctl_assert_write("2"); - mfd_fail_new("kern_memfd_sysctl_2", - MFD_CLOEXEC | MFD_ALLOW_SEALING); - sysctl_fail_write("0"); - sysctl_fail_write("1"); } -static int newpid_thread_fn(void *arg) +static void test_sysctl_set_sysctl1(void) { - test_sysctl_child(); - return 0; + sysctl_assert_write("1"); + test_sysctl_sysctl1(); } -static void test_sysctl_child2(void) +static void test_sysctl_sysctl2(void) { int fd; - sysctl_fail_write("0"); - fd = mfd_assert_new("kern_memfd_sysctl_1", + sysctl_assert_equal("2"); + + fd = mfd_assert_new("kern_memfd_sysctl_2_dfl", mfd_def_size, MFD_CLOEXEC | MFD_ALLOW_SEALING); + mfd_assert_mode(fd, 0666); + mfd_assert_has_seals(fd, F_SEAL_EXEC); + mfd_fail_chmod(fd, 0777); + close(fd); + + mfd_fail_new("kern_memfd_sysctl_2_exec", + MFD_CLOEXEC | MFD_EXEC | MFD_ALLOW_SEALING); + fd = mfd_assert_new("kern_memfd_sysctl_2_noexec", + mfd_def_size, + MFD_CLOEXEC | MFD_NOEXEC_SEAL | MFD_ALLOW_SEALING); mfd_assert_mode(fd, 0666); mfd_assert_has_seals(fd, F_SEAL_EXEC); mfd_fail_chmod(fd, 0777); close(fd); } -static int newpid_thread_fn2(void *arg) +static void test_sysctl_set_sysctl2(void) +{ + sysctl_assert_write("2"); + test_sysctl_sysctl2(); +} + +static int sysctl_simple_child(void *arg) +{ + int fd; + int pid; + + printf("%s sysctl 0\n", memfd_str); + test_sysctl_set_sysctl0(); + + printf("%s sysctl 1\n", memfd_str); + test_sysctl_set_sysctl1(); + + printf("%s sysctl 0\n", memfd_str); + test_sysctl_set_sysctl0(); + + printf("%s sysctl 2\n", memfd_str); + test_sysctl_set_sysctl2(); + + printf("%s sysctl 1\n", memfd_str); + test_sysctl_set_sysctl1(); + + printf("%s sysctl 0\n", memfd_str); + test_sysctl_set_sysctl0(); + + return 0; +} + +/* + * Test sysctl + * A very basic test to make sure the core sysctl semantics work. + */ +static void test_sysctl_simple(void) +{ + int pid = spawn_thread(CLONE_NEWPID, sysctl_simple_child, NULL); + + join_thread(pid); +} + +static int sysctl_nested(void *arg) { - test_sysctl_child2(); + void (*fn)(void) = arg; + + fn(); return 0; } -static pid_t spawn_newpid_thread(unsigned int flags, int (*fn)(void *)) + +static int sysctl_nested_wait(void *arg) { - uint8_t *stack; - pid_t pid; + /* Wait for a SIGCONT. */ + kill(getpid(), SIGSTOP); + return sysctl_nested(arg); +} - stack = malloc(STACK_SIZE); - if (!stack) { - printf("malloc(STACK_SIZE) failed: %m\n"); - abort(); - } +static void test_sysctl_sysctl1_failset(void) +{ + sysctl_fail_write("0"); + test_sysctl_sysctl1(); +} - pid = clone(fn, - stack + STACK_SIZE, - SIGCHLD | flags, - NULL); - if (pid < 0) { - printf("clone() failed: %m\n"); - abort(); - } +static void test_sysctl_sysctl2_failset(void) +{ + sysctl_fail_write("1"); + test_sysctl_sysctl2(); - return pid; + sysctl_fail_write("0"); + test_sysctl_sysctl2(); } -static void join_newpid_thread(pid_t pid) +static int sysctl_nested_child(void *arg) { - waitpid(pid, NULL, 0); + int fd; + int pid; + + printf("%s nested sysctl 0\n", memfd_str); + sysctl_assert_write("0"); + /* A further nested pidns works the same. */ + pid = spawn_thread(CLONE_NEWPID, sysctl_simple_child, NULL); + join_thread(pid); + + printf("%s nested sysctl 1\n", memfd_str); + sysctl_assert_write("1"); + /* Child inherits our setting. */ + pid = spawn_thread(CLONE_NEWPID, sysctl_nested, test_sysctl_sysctl1); + join_thread(pid); + /* Child cannot raise the setting. */ + pid = spawn_thread(CLONE_NEWPID, sysctl_nested, + test_sysctl_sysctl1_failset); + join_thread(pid); + /* Child can lower the setting. */ + pid = spawn_thread(CLONE_NEWPID, sysctl_nested, + test_sysctl_set_sysctl2); + join_thread(pid); + /* Child lowering the setting has no effect on our setting. */ + test_sysctl_sysctl1(); + + printf("%s nested sysctl 2\n", memfd_str); + sysctl_assert_write("2"); + /* Child inherits our setting. */ + pid = spawn_thread(CLONE_NEWPID, sysctl_nested, test_sysctl_sysctl2); + join_thread(pid); + /* Child cannot raise the setting. */ + pid = spawn_thread(CLONE_NEWPID, sysctl_nested, + test_sysctl_sysctl2_failset); + join_thread(pid); + + /* Verify that the rules are actually inherited after fork. */ + printf("%s nested sysctl 0 -> 1 after fork\n", memfd_str); + sysctl_assert_write("0"); + + pid = spawn_thread(CLONE_NEWPID, sysctl_nested_wait, + test_sysctl_sysctl1_failset); + sysctl_assert_write("1"); + kill(pid, SIGCONT); + join_thread(pid); + + printf("%s nested sysctl 0 -> 2 after fork\n", memfd_str); + sysctl_assert_write("0"); + + pid = spawn_thread(CLONE_NEWPID, sysctl_nested_wait, + test_sysctl_sysctl2_failset); + sysctl_assert_write("2"); + kill(pid, SIGCONT); + join_thread(pid); + + /* + * Verify that the current effective setting is saved on fork, meaning + * that the parent lowering the sysctl doesn't affect already-forked + * children. + */ + printf("%s nested sysctl 2 -> 1 after fork\n", memfd_str); + sysctl_assert_write("2"); + pid = spawn_thread(CLONE_NEWPID, sysctl_nested_wait, + test_sysctl_sysctl2); + sysctl_assert_write("1"); + kill(pid, SIGCONT); + join_thread(pid); + + printf("%s nested sysctl 2 -> 0 after fork\n", memfd_str); + sysctl_assert_write("2"); + pid = spawn_thread(CLONE_NEWPID, sysctl_nested_wait, + test_sysctl_sysctl2); + sysctl_assert_write("0"); + kill(pid, SIGCONT); + join_thread(pid); + + printf("%s nested sysctl 1 -> 0 after fork\n", memfd_str); + sysctl_assert_write("1"); + pid = spawn_thread(CLONE_NEWPID, sysctl_nested_wait, + test_sysctl_sysctl1); + sysctl_assert_write("0"); + kill(pid, SIGCONT); + join_thread(pid); + + return 0; } /* - * Test sysctl - * A very basic sealing test to see whether setting/retrieving seals works. + * Test sysctl with nested pid namespaces + * Make sure that the sysctl nesting semantics work correctly. */ -static void test_sysctl(void) +static void test_sysctl_nested(void) { - int pid = spawn_newpid_thread(CLONE_NEWPID, newpid_thread_fn); + int pid = spawn_thread(CLONE_NEWPID, sysctl_nested_child, NULL); - join_newpid_thread(pid); + join_thread(pid); } /* @@ -1399,6 +1601,9 @@ int main(int argc, char **argv) test_seal_grow(); test_seal_resize(); + test_sysctl_simple(); + test_sysctl_nested(); + test_share_dup("SHARE-DUP", ""); test_share_mmap("SHARE-MMAP", ""); test_share_open("SHARE-OPEN", ""); @@ -1413,8 +1618,6 @@ int main(int argc, char **argv) test_share_fork("SHARE-FORK", SHARED_FT_STR); join_idle_thread(pid); - test_sysctl(); - printf("memfd: DONE\n"); return 0; diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore index 7e2a982383c0..cdc9ce4426b9 100644 --- a/tools/testing/selftests/mm/.gitignore +++ b/tools/testing/selftests/mm/.gitignore @@ -5,6 +5,7 @@ hugepage-mremap hugepage-shm hugepage-vmemmap hugetlb-madvise +hugetlb-read-hwpoison khugepaged map_hugetlb map_populate diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index 66d7c07dc177..6a9fc5693145 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -35,39 +35,43 @@ MAKEFLAGS += --no-builtin-rules CFLAGS = -Wall -I $(top_srcdir) $(EXTRA_CFLAGS) $(KHDR_INCLUDES) LDLIBS = -lrt -lpthread -TEST_GEN_PROGS = cow -TEST_GEN_PROGS += compaction_test -TEST_GEN_PROGS += gup_longterm -TEST_GEN_PROGS += gup_test -TEST_GEN_PROGS += hmm-tests -TEST_GEN_PROGS += hugetlb-madvise -TEST_GEN_PROGS += hugepage-mmap -TEST_GEN_PROGS += hugepage-mremap -TEST_GEN_PROGS += hugepage-shm -TEST_GEN_PROGS += hugepage-vmemmap -TEST_GEN_PROGS += khugepaged -TEST_GEN_PROGS += madv_populate -TEST_GEN_PROGS += map_fixed_noreplace -TEST_GEN_PROGS += map_hugetlb -TEST_GEN_PROGS += map_populate -TEST_GEN_PROGS += memfd_secret -TEST_GEN_PROGS += migration -TEST_GEN_PROGS += mkdirty -TEST_GEN_PROGS += mlock-random-test -TEST_GEN_PROGS += mlock2-tests -TEST_GEN_PROGS += mrelease_test -TEST_GEN_PROGS += mremap_dontunmap -TEST_GEN_PROGS += mremap_test -TEST_GEN_PROGS += on-fault-limit -TEST_GEN_PROGS += thuge-gen -TEST_GEN_PROGS += transhuge-stress -TEST_GEN_PROGS += uffd-stress -TEST_GEN_PROGS += uffd-unit-tests +TEST_GEN_FILES = cow +TEST_GEN_FILES += compaction_test +TEST_GEN_FILES += gup_longterm +TEST_GEN_FILES += gup_test +TEST_GEN_FILES += hmm-tests +TEST_GEN_FILES += hugetlb-madvise +TEST_GEN_FILES += hugetlb-read-hwpoison +TEST_GEN_FILES += hugepage-mmap +TEST_GEN_FILES += hugepage-mremap +TEST_GEN_FILES += hugepage-shm +TEST_GEN_FILES += hugepage-vmemmap +TEST_GEN_FILES += khugepaged +TEST_GEN_FILES += madv_populate +TEST_GEN_FILES += map_fixed_noreplace +TEST_GEN_FILES += map_hugetlb +TEST_GEN_FILES += map_populate +TEST_GEN_FILES += memfd_secret +TEST_GEN_FILES += migration +TEST_GEN_FILES += mkdirty +TEST_GEN_FILES += mlock-random-test +TEST_GEN_FILES += mlock2-tests +TEST_GEN_FILES += mrelease_test +TEST_GEN_FILES += mremap_dontunmap +TEST_GEN_FILES += mremap_test +TEST_GEN_FILES += on-fault-limit +TEST_GEN_FILES += thuge-gen +TEST_GEN_FILES += transhuge-stress +TEST_GEN_FILES += uffd-stress +TEST_GEN_FILES += uffd-unit-tests +TEST_GEN_FILES += split_huge_page_test +TEST_GEN_FILES += ksm_tests +TEST_GEN_FILES += ksm_functional_tests +TEST_GEN_FILES += mdwe_test + +ifneq ($(ARCH),arm64) TEST_GEN_PROGS += soft-dirty -TEST_GEN_PROGS += split_huge_page_test -TEST_GEN_PROGS += ksm_tests -TEST_GEN_PROGS += ksm_functional_tests -TEST_GEN_PROGS += mdwe_test +endif ifeq ($(ARCH),x86_64) CAN_BUILD_I386 := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_32bit_program.c -m32) @@ -83,24 +87,24 @@ CFLAGS += -no-pie endif ifeq ($(CAN_BUILD_I386),1) -TEST_GEN_PROGS += $(BINARIES_32) +TEST_GEN_FILES += $(BINARIES_32) endif ifeq ($(CAN_BUILD_X86_64),1) -TEST_GEN_PROGS += $(BINARIES_64) +TEST_GEN_FILES += $(BINARIES_64) endif else ifneq (,$(findstring $(ARCH),ppc64)) -TEST_GEN_PROGS += protection_keys +TEST_GEN_FILES += protection_keys endif endif ifneq (,$(filter $(ARCH),arm64 ia64 mips64 parisc64 ppc64 riscv64 s390x sparc64 x86_64)) -TEST_GEN_PROGS += va_high_addr_switch -TEST_GEN_PROGS += virtual_address_range -TEST_GEN_PROGS += write_to_hugetlbfs +TEST_GEN_FILES += va_high_addr_switch +TEST_GEN_FILES += virtual_address_range +TEST_GEN_FILES += write_to_hugetlbfs endif TEST_PROGS := run_vmtests.sh @@ -112,6 +116,7 @@ TEST_FILES += va_high_addr_switch.sh include ../lib.mk $(TEST_GEN_PROGS): vm_util.c +$(TEST_GEN_FILES): vm_util.c $(OUTPUT)/uffd-stress: uffd-common.c $(OUTPUT)/uffd-unit-tests: uffd-common.c diff --git a/tools/testing/selftests/mm/hmm-tests.c b/tools/testing/selftests/mm/hmm-tests.c index 4adaad1b822f..20294553a5dd 100644 --- a/tools/testing/selftests/mm/hmm-tests.c +++ b/tools/testing/selftests/mm/hmm-tests.c @@ -57,9 +57,14 @@ enum { #define ALIGN(x, a) (((x) + (a - 1)) & (~((a) - 1))) /* Just the flags we need, copied from mm.h: */ + +#ifndef FOLL_WRITE #define FOLL_WRITE 0x01 /* check pte is writable */ -#define FOLL_LONGTERM 0x10000 /* mapping lifetime is indefinite */ +#endif +#ifndef FOLL_LONGTERM +#define FOLL_LONGTERM 0x100 /* mapping lifetime is indefinite */ +#endif FIXTURE(hmm) { int fd; diff --git a/tools/testing/selftests/mm/hugetlb-read-hwpoison.c b/tools/testing/selftests/mm/hugetlb-read-hwpoison.c new file mode 100644 index 000000000000..ba6cc6f9cabc --- /dev/null +++ b/tools/testing/selftests/mm/hugetlb-read-hwpoison.c @@ -0,0 +1,322 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE +#include <stdlib.h> +#include <stdio.h> +#include <string.h> + +#include <linux/magic.h> +#include <sys/mman.h> +#include <sys/statfs.h> +#include <errno.h> +#include <stdbool.h> + +#include "../kselftest.h" + +#define PREFIX " ... " +#define ERROR_PREFIX " !!! " + +#define MAX_WRITE_READ_CHUNK_SIZE (getpagesize() * 16) +#define MAX(a, b) (((a) > (b)) ? (a) : (b)) + +enum test_status { + TEST_PASSED = 0, + TEST_FAILED = 1, + TEST_SKIPPED = 2, +}; + +static char *status_to_str(enum test_status status) +{ + switch (status) { + case TEST_PASSED: + return "TEST_PASSED"; + case TEST_FAILED: + return "TEST_FAILED"; + case TEST_SKIPPED: + return "TEST_SKIPPED"; + default: + return "TEST_???"; + } +} + +static int setup_filemap(char *filemap, size_t len, size_t wr_chunk_size) +{ + char iter = 0; + + for (size_t offset = 0; offset < len; + offset += wr_chunk_size) { + iter++; + memset(filemap + offset, iter, wr_chunk_size); + } + + return 0; +} + +static bool verify_chunk(char *buf, size_t len, char val) +{ + size_t i; + + for (i = 0; i < len; ++i) { + if (buf[i] != val) { + printf(PREFIX ERROR_PREFIX "check fail: buf[%lu] = %u != %u\n", + i, buf[i], val); + return false; + } + } + + return true; +} + +static bool seek_read_hugepage_filemap(int fd, size_t len, size_t wr_chunk_size, + off_t offset, size_t expected) +{ + char buf[MAX_WRITE_READ_CHUNK_SIZE]; + ssize_t ret_count = 0; + ssize_t total_ret_count = 0; + char val = offset / wr_chunk_size + offset % wr_chunk_size; + + printf(PREFIX PREFIX "init val=%u with offset=0x%lx\n", val, offset); + printf(PREFIX PREFIX "expect to read 0x%lx bytes of data in total\n", + expected); + if (lseek(fd, offset, SEEK_SET) < 0) { + perror(PREFIX ERROR_PREFIX "seek failed"); + return false; + } + + while (offset + total_ret_count < len) { + ret_count = read(fd, buf, wr_chunk_size); + if (ret_count == 0) { + printf(PREFIX PREFIX "read reach end of the file\n"); + break; + } else if (ret_count < 0) { + perror(PREFIX ERROR_PREFIX "read failed"); + break; + } + ++val; + if (!verify_chunk(buf, ret_count, val)) + return false; + + total_ret_count += ret_count; + } + printf(PREFIX PREFIX "actually read 0x%lx bytes of data in total\n", + total_ret_count); + + return total_ret_count == expected; +} + +static bool read_hugepage_filemap(int fd, size_t len, + size_t wr_chunk_size, size_t expected) +{ + char buf[MAX_WRITE_READ_CHUNK_SIZE]; + ssize_t ret_count = 0; + ssize_t total_ret_count = 0; + char val = 0; + + printf(PREFIX PREFIX "expect to read 0x%lx bytes of data in total\n", + expected); + while (total_ret_count < len) { + ret_count = read(fd, buf, wr_chunk_size); + if (ret_count == 0) { + printf(PREFIX PREFIX "read reach end of the file\n"); + break; + } else if (ret_count < 0) { + perror(PREFIX ERROR_PREFIX "read failed"); + break; + } + ++val; + if (!verify_chunk(buf, ret_count, val)) + return false; + + total_ret_count += ret_count; + } + printf(PREFIX PREFIX "actually read 0x%lx bytes of data in total\n", + total_ret_count); + + return total_ret_count == expected; +} + +static enum test_status +test_hugetlb_read(int fd, size_t len, size_t wr_chunk_size) +{ + enum test_status status = TEST_SKIPPED; + char *filemap = NULL; + + if (ftruncate(fd, len) < 0) { + perror(PREFIX ERROR_PREFIX "ftruncate failed"); + return status; + } + + filemap = mmap(NULL, len, PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_POPULATE, fd, 0); + if (filemap == MAP_FAILED) { + perror(PREFIX ERROR_PREFIX "mmap for primary mapping failed"); + goto done; + } + + setup_filemap(filemap, len, wr_chunk_size); + status = TEST_FAILED; + + if (read_hugepage_filemap(fd, len, wr_chunk_size, len)) + status = TEST_PASSED; + + munmap(filemap, len); +done: + if (ftruncate(fd, 0) < 0) { + perror(PREFIX ERROR_PREFIX "ftruncate back to 0 failed"); + status = TEST_FAILED; + } + + return status; +} + +static enum test_status +test_hugetlb_read_hwpoison(int fd, size_t len, size_t wr_chunk_size, + bool skip_hwpoison_page) +{ + enum test_status status = TEST_SKIPPED; + char *filemap = NULL; + char *hwp_addr = NULL; + const unsigned long pagesize = getpagesize(); + + if (ftruncate(fd, len) < 0) { + perror(PREFIX ERROR_PREFIX "ftruncate failed"); + return status; + } + + filemap = mmap(NULL, len, PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_POPULATE, fd, 0); + if (filemap == MAP_FAILED) { + perror(PREFIX ERROR_PREFIX "mmap for primary mapping failed"); + goto done; + } + + setup_filemap(filemap, len, wr_chunk_size); + status = TEST_FAILED; + + /* + * Poisoned hugetlb page layout (assume hugepagesize=2MB): + * |<---------------------- 1MB ---------------------->| + * |<---- healthy page ---->|<---- HWPOISON page ----->| + * |<------------------- (1MB - 8KB) ----------------->| + */ + hwp_addr = filemap + len / 2 + pagesize; + if (madvise(hwp_addr, pagesize, MADV_HWPOISON) < 0) { + perror(PREFIX ERROR_PREFIX "MADV_HWPOISON failed"); + goto unmap; + } + + if (!skip_hwpoison_page) { + /* + * Userspace should be able to read (1MB + 1 page) from + * the beginning of the HWPOISONed hugepage. + */ + if (read_hugepage_filemap(fd, len, wr_chunk_size, + len / 2 + pagesize)) + status = TEST_PASSED; + } else { + /* + * Userspace should be able to read (1MB - 2 pages) from + * HWPOISONed hugepage. + */ + if (seek_read_hugepage_filemap(fd, len, wr_chunk_size, + len / 2 + MAX(2 * pagesize, wr_chunk_size), + len / 2 - MAX(2 * pagesize, wr_chunk_size))) + status = TEST_PASSED; + } + +unmap: + munmap(filemap, len); +done: + if (ftruncate(fd, 0) < 0) { + perror(PREFIX ERROR_PREFIX "ftruncate back to 0 failed"); + status = TEST_FAILED; + } + + return status; +} + +static int create_hugetlbfs_file(struct statfs *file_stat) +{ + int fd; + + fd = memfd_create("hugetlb_tmp", MFD_HUGETLB); + if (fd < 0) { + perror(PREFIX ERROR_PREFIX "could not open hugetlbfs file"); + return -1; + } + + memset(file_stat, 0, sizeof(*file_stat)); + if (fstatfs(fd, file_stat)) { + perror(PREFIX ERROR_PREFIX "fstatfs failed"); + goto close; + } + if (file_stat->f_type != HUGETLBFS_MAGIC) { + printf(PREFIX ERROR_PREFIX "not hugetlbfs file\n"); + goto close; + } + + return fd; +close: + close(fd); + return -1; +} + +int main(void) +{ + int fd; + struct statfs file_stat; + enum test_status status; + /* Test read() in different granularity. */ + size_t wr_chunk_sizes[] = { + getpagesize() / 2, getpagesize(), + getpagesize() * 2, getpagesize() * 4 + }; + size_t i; + + for (i = 0; i < ARRAY_SIZE(wr_chunk_sizes); ++i) { + printf("Write/read chunk size=0x%lx\n", + wr_chunk_sizes[i]); + + fd = create_hugetlbfs_file(&file_stat); + if (fd < 0) + goto create_failure; + printf(PREFIX "HugeTLB read regression test...\n"); + status = test_hugetlb_read(fd, file_stat.f_bsize, + wr_chunk_sizes[i]); + printf(PREFIX "HugeTLB read regression test...%s\n", + status_to_str(status)); + close(fd); + if (status == TEST_FAILED) + return -1; + + fd = create_hugetlbfs_file(&file_stat); + if (fd < 0) + goto create_failure; + printf(PREFIX "HugeTLB read HWPOISON test...\n"); + status = test_hugetlb_read_hwpoison(fd, file_stat.f_bsize, + wr_chunk_sizes[i], false); + printf(PREFIX "HugeTLB read HWPOISON test...%s\n", + status_to_str(status)); + close(fd); + if (status == TEST_FAILED) + return -1; + + fd = create_hugetlbfs_file(&file_stat); + if (fd < 0) + goto create_failure; + printf(PREFIX "HugeTLB seek then read HWPOISON test...\n"); + status = test_hugetlb_read_hwpoison(fd, file_stat.f_bsize, + wr_chunk_sizes[i], true); + printf(PREFIX "HugeTLB seek then read HWPOISON test...%s\n", + status_to_str(status)); + close(fd); + if (status == TEST_FAILED) + return -1; + } + + return 0; + +create_failure: + printf(ERROR_PREFIX "Abort test: failed to create hugetlbfs file\n"); + return -1; +} diff --git a/tools/testing/selftests/mm/ksm_functional_tests.c b/tools/testing/selftests/mm/ksm_functional_tests.c index 26853badae70..901e950f9138 100644 --- a/tools/testing/selftests/mm/ksm_functional_tests.c +++ b/tools/testing/selftests/mm/ksm_functional_tests.c @@ -27,8 +27,12 @@ #define KiB 1024u #define MiB (1024 * KiB) +static int mem_fd; static int ksm_fd; static int ksm_full_scans_fd; +static int proc_self_ksm_stat_fd; +static int proc_self_ksm_merging_pages_fd; +static int ksm_use_zero_pages_fd; static int pagemap_fd; static size_t pagesize; @@ -59,6 +63,49 @@ static bool range_maps_duplicates(char *addr, unsigned long size) return false; } +static long get_my_ksm_zero_pages(void) +{ + char buf[200]; + char *substr_ksm_zero; + size_t value_pos; + ssize_t read_size; + unsigned long my_ksm_zero_pages; + + if (!proc_self_ksm_stat_fd) + return 0; + + read_size = pread(proc_self_ksm_stat_fd, buf, sizeof(buf) - 1, 0); + if (read_size < 0) + return -errno; + + buf[read_size] = 0; + + substr_ksm_zero = strstr(buf, "ksm_zero_pages"); + if (!substr_ksm_zero) + return 0; + + value_pos = strcspn(substr_ksm_zero, "0123456789"); + my_ksm_zero_pages = strtol(substr_ksm_zero + value_pos, NULL, 10); + + return my_ksm_zero_pages; +} + +static long get_my_merging_pages(void) +{ + char buf[10]; + ssize_t ret; + + if (proc_self_ksm_merging_pages_fd < 0) + return proc_self_ksm_merging_pages_fd; + + ret = pread(proc_self_ksm_merging_pages_fd, buf, sizeof(buf) - 1, 0); + if (ret <= 0) + return -errno; + buf[ret] = 0; + + return strtol(buf, NULL, 10); +} + static long ksm_get_full_scans(void) { char buf[10]; @@ -91,11 +138,30 @@ static int ksm_merge(void) return 0; } -static char *mmap_and_merge_range(char val, unsigned long size, bool use_prctl) +static int ksm_unmerge(void) +{ + if (write(ksm_fd, "2", 1) != 1) + return -errno; + return 0; +} + +static char *mmap_and_merge_range(char val, unsigned long size, int prot, + bool use_prctl) { char *map; int ret; + /* Stabilize accounting by disabling KSM completely. */ + if (ksm_unmerge()) { + ksft_test_result_fail("Disabling (unmerging) KSM failed\n"); + goto unmap; + } + + if (get_my_merging_pages() > 0) { + ksft_test_result_fail("Still pages merged\n"); + goto unmap; + } + map = mmap(NULL, size, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANON, -1, 0); if (map == MAP_FAILED) { @@ -112,6 +178,11 @@ static char *mmap_and_merge_range(char val, unsigned long size, bool use_prctl) /* Make sure each page contains the same values to merge them. */ memset(map, val, size); + if (mprotect(map, size, prot)) { + ksft_test_result_skip("mprotect() failed\n"); + goto unmap; + } + if (use_prctl) { ret = prctl(PR_SET_MEMORY_MERGE, 1, 0, 0, 0); if (ret < 0 && errno == EINVAL) { @@ -131,6 +202,16 @@ static char *mmap_and_merge_range(char val, unsigned long size, bool use_prctl) ksft_test_result_fail("Running KSM failed\n"); goto unmap; } + + /* + * Check if anything was merged at all. Ignore the zero page that is + * accounted differently (depending on kernel support). + */ + if (val && !get_my_merging_pages()) { + ksft_test_result_fail("No pages got merged\n"); + goto unmap; + } + return map; unmap: munmap(map, size); @@ -144,7 +225,7 @@ static void test_unmerge(void) ksft_print_msg("[RUN] %s\n", __func__); - map = mmap_and_merge_range(0xcf, size, false); + map = mmap_and_merge_range(0xcf, size, PROT_READ | PROT_WRITE, false); if (map == MAP_FAILED) return; @@ -159,6 +240,70 @@ unmap: munmap(map, size); } +static void test_unmerge_zero_pages(void) +{ + const unsigned int size = 2 * MiB; + char *map; + unsigned int offs; + unsigned long pages_expected; + + ksft_print_msg("[RUN] %s\n", __func__); + + if (proc_self_ksm_stat_fd < 0) { + ksft_test_result_skip("open(\"/proc/self/ksm_stat\") failed\n"); + return; + } + if (ksm_use_zero_pages_fd < 0) { + ksft_test_result_skip("open \"/sys/kernel/mm/ksm/use_zero_pages\" failed\n"); + return; + } + if (write(ksm_use_zero_pages_fd, "1", 1) != 1) { + ksft_test_result_skip("write \"/sys/kernel/mm/ksm/use_zero_pages\" failed\n"); + return; + } + + /* Let KSM deduplicate zero pages. */ + map = mmap_and_merge_range(0x00, size, PROT_READ | PROT_WRITE, false); + if (map == MAP_FAILED) + return; + + /* Check if ksm_zero_pages is updated correctly after KSM merging */ + pages_expected = size / pagesize; + if (pages_expected != get_my_ksm_zero_pages()) { + ksft_test_result_fail("'ksm_zero_pages' updated after merging\n"); + goto unmap; + } + + /* Try to unmerge half of the region */ + if (madvise(map, size / 2, MADV_UNMERGEABLE)) { + ksft_test_result_fail("MADV_UNMERGEABLE failed\n"); + goto unmap; + } + + /* Check if ksm_zero_pages is updated correctly after unmerging */ + pages_expected /= 2; + if (pages_expected != get_my_ksm_zero_pages()) { + ksft_test_result_fail("'ksm_zero_pages' updated after unmerging\n"); + goto unmap; + } + + /* Trigger unmerging of the other half by writing to the pages. */ + for (offs = size / 2; offs < size; offs += pagesize) + *((unsigned int *)&map[offs]) = offs; + + /* Now we should have no zeropages remaining. */ + if (get_my_ksm_zero_pages()) { + ksft_test_result_fail("'ksm_zero_pages' updated after write fault\n"); + goto unmap; + } + + /* Check if ksm zero pages are really unmerged */ + ksft_test_result(!range_maps_duplicates(map, size), + "KSM zero pages were unmerged\n"); +unmap: + munmap(map, size); +} + static void test_unmerge_discarded(void) { const unsigned int size = 2 * MiB; @@ -166,7 +311,7 @@ static void test_unmerge_discarded(void) ksft_print_msg("[RUN] %s\n", __func__); - map = mmap_and_merge_range(0xcf, size, false); + map = mmap_and_merge_range(0xcf, size, PROT_READ | PROT_WRITE, false); if (map == MAP_FAILED) return; @@ -198,7 +343,7 @@ static void test_unmerge_uffd_wp(void) ksft_print_msg("[RUN] %s\n", __func__); - map = mmap_and_merge_range(0xcf, size, false); + map = mmap_and_merge_range(0xcf, size, PROT_READ | PROT_WRITE, false); if (map == MAP_FAILED) return; @@ -341,7 +486,7 @@ static void test_prctl_unmerge(void) ksft_print_msg("[RUN] %s\n", __func__); - map = mmap_and_merge_range(0xcf, size, true); + map = mmap_and_merge_range(0xcf, size, PROT_READ | PROT_WRITE, true); if (map == MAP_FAILED) return; @@ -356,9 +501,42 @@ unmap: munmap(map, size); } +static void test_prot_none(void) +{ + const unsigned int size = 2 * MiB; + char *map; + int i; + + ksft_print_msg("[RUN] %s\n", __func__); + + map = mmap_and_merge_range(0x11, size, PROT_NONE, false); + if (map == MAP_FAILED) + goto unmap; + + /* Store a unique value in each page on one half using ptrace */ + for (i = 0; i < size / 2; i += pagesize) { + lseek(mem_fd, (uintptr_t) map + i, SEEK_SET); + if (write(mem_fd, &i, sizeof(i)) != sizeof(i)) { + ksft_test_result_fail("ptrace write failed\n"); + goto unmap; + } + } + + /* Trigger unsharing on the other half. */ + if (madvise(map + size / 2, size / 2, MADV_UNMERGEABLE)) { + ksft_test_result_fail("MADV_UNMERGEABLE failed\n"); + goto unmap; + } + + ksft_test_result(!range_maps_duplicates(map, size), + "Pages were unmerged\n"); +unmap: + munmap(map, size); +} + int main(int argc, char **argv) { - unsigned int tests = 5; + unsigned int tests = 7; int err; #ifdef __NR_userfaultfd @@ -370,6 +548,9 @@ int main(int argc, char **argv) pagesize = getpagesize(); + mem_fd = open("/proc/self/mem", O_RDWR); + if (mem_fd < 0) + ksft_exit_fail_msg("opening /proc/self/mem failed\n"); ksm_fd = open("/sys/kernel/mm/ksm/run", O_RDWR); if (ksm_fd < 0) ksft_exit_skip("open(\"/sys/kernel/mm/ksm/run\") failed\n"); @@ -379,13 +560,20 @@ int main(int argc, char **argv) pagemap_fd = open("/proc/self/pagemap", O_RDONLY); if (pagemap_fd < 0) ksft_exit_skip("open(\"/proc/self/pagemap\") failed\n"); + proc_self_ksm_stat_fd = open("/proc/self/ksm_stat", O_RDONLY); + proc_self_ksm_merging_pages_fd = open("/proc/self/ksm_merging_pages", + O_RDONLY); + ksm_use_zero_pages_fd = open("/sys/kernel/mm/ksm/use_zero_pages", O_RDWR); test_unmerge(); + test_unmerge_zero_pages(); test_unmerge_discarded(); #ifdef __NR_userfaultfd test_unmerge_uffd_wp(); #endif + test_prot_none(); + test_prctl(); test_prctl_fork(); test_prctl_unmerge(); diff --git a/tools/testing/selftests/mm/madv_populate.c b/tools/testing/selftests/mm/madv_populate.c index 60547245e479..17bcb07f19f3 100644 --- a/tools/testing/selftests/mm/madv_populate.c +++ b/tools/testing/selftests/mm/madv_populate.c @@ -264,14 +264,35 @@ static void test_softdirty(void) munmap(addr, SIZE); } +static int system_has_softdirty(void) +{ + /* + * There is no way to check if the kernel supports soft-dirty, other + * than by writing to a page and seeing if the bit was set. But the + * tests are intended to check that the bit gets set when it should, so + * doing that check would turn a potentially legitimate fail into a + * skip. Fortunately, we know for sure that arm64 does not support + * soft-dirty. So for now, let's just use the arch as a corse guide. + */ +#if defined(__aarch64__) + return 0; +#else + return 1; +#endif +} + int main(int argc, char **argv) { + int nr_tests = 16; int err; pagesize = getpagesize(); + if (system_has_softdirty()) + nr_tests += 5; + ksft_print_header(); - ksft_set_plan(21); + ksft_set_plan(nr_tests); sense_support(); test_prot_read(); @@ -279,7 +300,8 @@ int main(int argc, char **argv) test_holes(); test_populate_read(); test_populate_write(); - test_softdirty(); + if (system_has_softdirty()) + test_softdirty(); err = ksft_get_fail_cnt(); if (err) diff --git a/tools/testing/selftests/mm/map_populate.c b/tools/testing/selftests/mm/map_populate.c index 240f2d9dae7a..7945d0754875 100644 --- a/tools/testing/selftests/mm/map_populate.c +++ b/tools/testing/selftests/mm/map_populate.c @@ -77,7 +77,7 @@ int main(int argc, char **argv) unsigned long *smap; ftmp = tmpfile(); - BUG_ON(ftmp == 0, "tmpfile()"); + BUG_ON(!ftmp, "tmpfile()"); ret = ftruncate(fileno(ftmp), MMAP_SZ); BUG_ON(ret, "ftruncate()"); diff --git a/tools/testing/selftests/mm/migration.c b/tools/testing/selftests/mm/migration.c index 379581567f27..6908569ef406 100644 --- a/tools/testing/selftests/mm/migration.c +++ b/tools/testing/selftests/mm/migration.c @@ -10,12 +10,13 @@ #include <numa.h> #include <numaif.h> #include <sys/mman.h> +#include <sys/prctl.h> #include <sys/types.h> #include <signal.h> #include <time.h> #define TWOMEG (2<<20) -#define RUNTIME (60) +#define RUNTIME (20) #define ALIGN(x, a) (((x) + (a - 1)) & (~((a) - 1))) @@ -155,10 +156,15 @@ TEST_F_TIMEOUT(migration, shared_anon, 2*RUNTIME) memset(ptr, 0xde, TWOMEG); for (i = 0; i < self->nthreads - 1; i++) { pid = fork(); - if (!pid) + if (!pid) { + prctl(PR_SET_PDEATHSIG, SIGHUP); + /* Parent may have died before prctl so check now. */ + if (getppid() == 1) + kill(getpid(), SIGHUP); access_mem(ptr); - else + } else { self->pids[i] = pid; + } } ASSERT_EQ(migrate(ptr, self->n1, self->n2), 0); diff --git a/tools/testing/selftests/mm/mrelease_test.c b/tools/testing/selftests/mm/mrelease_test.c index dca21042b679..d822004a374e 100644 --- a/tools/testing/selftests/mm/mrelease_test.c +++ b/tools/testing/selftests/mm/mrelease_test.c @@ -7,6 +7,7 @@ #include <stdbool.h> #include <stdio.h> #include <stdlib.h> +#include <sys/syscall.h> #include <sys/wait.h> #include <unistd.h> #include <asm-generic/unistd.h> diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index 3f26f6e15b2a..3e2bc818d566 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -12,11 +12,14 @@ exitcode=0 usage() { cat <<EOF -usage: ${BASH_SOURCE[0]:-$0} [ -h | -t "<categories>"] +usage: ${BASH_SOURCE[0]:-$0} [ options ] + + -a: run all tests, including extra ones -t: specify specific categories to tests to run -h: display this message -The default behavior is to run all tests. +The default behavior is to run required tests only. If -a is specified, +will run all tests. Alternatively, specific groups tests can be run by passing a string to the -t argument containing one or more of the following categories @@ -55,14 +58,27 @@ separated by spaces: test soft dirty page bit semantics - cow test copy-on-write semantics +- thp + test transparent huge pages +- migration + invoke move_pages(2) to exercise the migration entry code + paths in the kernel +- mkdirty + test handling of code that might set PTE/PMD dirty in + read-only VMAs +- mdwe + test prctl(PR_SET_MDWE, ...) + example: ./run_vmtests.sh -t "hmm mmap ksm" EOF exit 0 } +RUN_ALL=false -while getopts "ht:" OPT; do +while getopts "aht:" OPT; do case ${OPT} in + "a") RUN_ALL=true ;; "h") usage ;; "t") VM_SELFTEST_ITEMS=${OPTARG} ;; esac @@ -85,6 +101,30 @@ test_selected() { fi } +run_gup_matrix() { + # -t: thp=on, -T: thp=off, -H: hugetlb=on + local hugetlb_mb=$(( needmem_KB / 1024 )) + + for huge in -t -T "-H -m $hugetlb_mb"; do + # -u: gup-fast, -U: gup-basic, -a: pin-fast, -b: pin-basic, -L: pin-longterm + for test_cmd in -u -U -a -b -L; do + # -w: write=1, -W: write=0 + for write in -w -W; do + # -S: shared + for share in -S " "; do + # -n: How many pages to fetch together? 512 is special + # because it's default thp size (or 2M on x86), 123 to + # just test partial gup when hit a huge in whatever form + for num in "-n 1" "-n 512" "-n 123"; do + CATEGORY="gup_test" run_test ./gup_test \ + $huge $test_cmd $write $share $num + done + done + done + done + done +} + # get huge pagesize and freepages from /proc/meminfo while read -r name size unit; do if [ "$name" = "HugePages_Free:" ]; then @@ -189,13 +229,16 @@ fi CATEGORY="mmap" run_test ./map_fixed_noreplace -# get_user_pages_fast() benchmark -CATEGORY="gup_test" run_test ./gup_test -u -# pin_user_pages_fast() benchmark -CATEGORY="gup_test" run_test ./gup_test -a +if $RUN_ALL; then + run_gup_matrix +else + # get_user_pages_fast() benchmark + CATEGORY="gup_test" run_test ./gup_test -u + # pin_user_pages_fast() benchmark + CATEGORY="gup_test" run_test ./gup_test -a +fi # Dump pages 0, 19, and 4096, using pin_user_pages: CATEGORY="gup_test" run_test ./gup_test -ct -F 0x1 0 19 0x1000 - CATEGORY="gup_test" run_test ./gup_longterm CATEGORY="userfaultfd" run_test ./uffd-unit-tests @@ -262,6 +305,10 @@ CATEGORY="madv_populate" run_test ./madv_populate CATEGORY="memfd_secret" run_test ./memfd_secret +# KSM KSM_MERGE_TIME_HUGE_PAGES test with size of 100 +CATEGORY="ksm" run_test ./ksm_tests -H -s 100 +# KSM KSM_MERGE_TIME test with size of 100 +CATEGORY="ksm" run_test ./ksm_tests -P -s 100 # KSM MADV_MERGEABLE test with 10 identical pages CATEGORY="ksm" run_test ./ksm_tests -M -p 10 # KSM unmerge test @@ -290,11 +337,26 @@ then CATEGORY="pkey" run_test ./protection_keys_64 fi -CATEGORY="soft_dirty" run_test ./soft-dirty +if [ -x ./soft-dirty ] +then + CATEGORY="soft_dirty" run_test ./soft-dirty +fi # COW tests CATEGORY="cow" run_test ./cow +CATEGORY="thp" run_test ./khugepaged + +CATEGORY="thp" run_test ./transhuge-stress -d 20 + +CATEGORY="thp" run_test ./split_huge_page_test + +CATEGORY="migration" run_test ./migration + +CATEGORY="mkdirty" run_test ./mkdirty + +CATEGORY="mdwe" run_test ./mdwe_test + echo "SUMMARY: PASS=${count_pass} SKIP=${count_skip} FAIL=${count_fail}" exit $exitcode diff --git a/tools/testing/selftests/mm/settings b/tools/testing/selftests/mm/settings index 9abfc60e9e6f..a953c96aa16e 100644 --- a/tools/testing/selftests/mm/settings +++ b/tools/testing/selftests/mm/settings @@ -1 +1 @@ -timeout=45 +timeout=180 diff --git a/tools/testing/selftests/mm/thuge-gen.c b/tools/testing/selftests/mm/thuge-gen.c index 380ab5f0a534..16ed4dfa7359 100644 --- a/tools/testing/selftests/mm/thuge-gen.c +++ b/tools/testing/selftests/mm/thuge-gen.c @@ -139,7 +139,7 @@ void test_mmap(unsigned long size, unsigned flags) before, after, before - after, size); assert(size == getpagesize() || (before - after) == NUM_PAGES); show(size); - err = munmap(map, size); + err = munmap(map, size * NUM_PAGES); assert(!err); } @@ -222,7 +222,7 @@ int main(void) test_mmap(ps, MAP_HUGETLB | arg); } printf("Testing default huge mmap\n"); - test_mmap(default_hps, SHM_HUGETLB); + test_mmap(default_hps, MAP_HUGETLB); puts("Testing non-huge shmget"); test_shmget(getpagesize(), 0); diff --git a/tools/testing/selftests/mm/transhuge-stress.c b/tools/testing/selftests/mm/transhuge-stress.c index ba9d37ad3a89..c61fb9350b8c 100644 --- a/tools/testing/selftests/mm/transhuge-stress.c +++ b/tools/testing/selftests/mm/transhuge-stress.c @@ -25,13 +25,14 @@ int main(int argc, char **argv) { size_t ram, len; void *ptr, *p; - struct timespec a, b; + struct timespec start, a, b; int i = 0; char *name = NULL; double s; uint8_t *map; size_t map_len; int pagemap_fd; + int duration = 0; ram = sysconf(_SC_PHYS_PAGES); if (ram > SIZE_MAX / psize() / 4) @@ -42,9 +43,11 @@ int main(int argc, char **argv) while (++i < argc) { if (!strcmp(argv[i], "-h")) - errx(1, "usage: %s [size in MiB]", argv[0]); + errx(1, "usage: %s [-f <filename>] [-d <duration>] [size in MiB]", argv[0]); else if (!strcmp(argv[i], "-f")) name = argv[++i]; + else if (!strcmp(argv[i], "-d")) + duration = atoi(argv[++i]); else len = atoll(argv[i]) << 20; } @@ -78,6 +81,8 @@ int main(int argc, char **argv) if (!map) errx(2, "map malloc"); + clock_gettime(CLOCK_MONOTONIC, &start); + while (1) { int nr_succeed = 0, nr_failed = 0, nr_pages = 0; @@ -118,5 +123,8 @@ int main(int argc, char **argv) "%4d succeed, %4d failed, %4d different pages", s, s * 1000 / (len >> HPAGE_SHIFT), len / s / (1 << 20), nr_succeed, nr_failed, nr_pages); + + if (duration > 0 && b.tv_sec - start.tv_sec >= duration) + return 0; } } diff --git a/tools/testing/selftests/mm/uffd-common.c b/tools/testing/selftests/mm/uffd-common.c index ba20d7504022..02b89860e193 100644 --- a/tools/testing/selftests/mm/uffd-common.c +++ b/tools/testing/selftests/mm/uffd-common.c @@ -499,6 +499,9 @@ void *uffd_poll_thread(void *arg) int ret; char tmp_chr; + if (!args->handle_fault) + args->handle_fault = uffd_handle_page_fault; + pollfd[0].fd = uffd; pollfd[0].events = POLLIN; pollfd[1].fd = pipefd[cpu*2]; @@ -527,7 +530,7 @@ void *uffd_poll_thread(void *arg) err("unexpected msg event %u\n", msg.event); break; case UFFD_EVENT_PAGEFAULT: - uffd_handle_page_fault(&msg, args); + args->handle_fault(&msg, args); break; case UFFD_EVENT_FORK: close(uffd); diff --git a/tools/testing/selftests/mm/uffd-common.h b/tools/testing/selftests/mm/uffd-common.h index 197f5262fe0d..7c4fa964c3b0 100644 --- a/tools/testing/selftests/mm/uffd-common.h +++ b/tools/testing/selftests/mm/uffd-common.h @@ -77,6 +77,9 @@ struct uffd_args { unsigned long missing_faults; unsigned long wp_faults; unsigned long minor_faults; + + /* A custom fault handler; defaults to uffd_handle_page_fault. */ + void (*handle_fault)(struct uffd_msg *msg, struct uffd_args *args); }; struct uffd_test_ops { diff --git a/tools/testing/selftests/mm/uffd-stress.c b/tools/testing/selftests/mm/uffd-stress.c index 995ff13e74c7..469e0476af26 100644 --- a/tools/testing/selftests/mm/uffd-stress.c +++ b/tools/testing/selftests/mm/uffd-stress.c @@ -53,21 +53,21 @@ pthread_attr_t attr; do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0) const char *examples = - "# Run anonymous memory test on 100MiB region with 99999 bounces:\n" - "./userfaultfd anon 100 99999\n\n" - "# Run share memory test on 1GiB region with 99 bounces:\n" - "./userfaultfd shmem 1000 99\n\n" - "# Run hugetlb memory test on 256MiB region with 50 bounces:\n" - "./userfaultfd hugetlb 256 50\n\n" - "# Run the same hugetlb test but using private file:\n" - "./userfaultfd hugetlb-private 256 50\n\n" - "# 10MiB-~6GiB 999 bounces anonymous test, " - "continue forever unless an error triggers\n" - "while ./userfaultfd anon $[RANDOM % 6000 + 10] 999; do true; done\n\n"; + "# Run anonymous memory test on 100MiB region with 99999 bounces:\n" + "./uffd-stress anon 100 99999\n\n" + "# Run share memory test on 1GiB region with 99 bounces:\n" + "./uffd-stress shmem 1000 99\n\n" + "# Run hugetlb memory test on 256MiB region with 50 bounces:\n" + "./uffd-stress hugetlb 256 50\n\n" + "# Run the same hugetlb test but using private file:\n" + "./uffd-stress hugetlb-private 256 50\n\n" + "# 10MiB-~6GiB 999 bounces anonymous test, " + "continue forever unless an error triggers\n" + "while ./uffd-stress anon $[RANDOM % 6000 + 10] 999; do true; done\n\n"; static void usage(void) { - fprintf(stderr, "\nUsage: ./userfaultfd <test type> <MiB> <bounces>\n\n"); + fprintf(stderr, "\nUsage: ./uffd-stress <test type> <MiB> <bounces>\n\n"); fprintf(stderr, "Supported <test type>: anon, hugetlb, " "hugetlb-private, shmem, shmem-private\n\n"); fprintf(stderr, "Examples:\n\n"); @@ -189,10 +189,8 @@ static int stress(struct uffd_args *args) locking_thread, (void *)cpu)) return 1; if (bounces & BOUNCE_POLL) { - if (pthread_create(&uffd_threads[cpu], &attr, - uffd_poll_thread, - (void *)&args[cpu])) - return 1; + if (pthread_create(&uffd_threads[cpu], &attr, uffd_poll_thread, &args[cpu])) + err("uffd_poll_thread create"); } else { if (pthread_create(&uffd_threads[cpu], &attr, uffd_read_thread, @@ -250,6 +248,8 @@ static int userfaultfd_stress(void) struct uffd_args args[nr_cpus]; uint64_t mem_size = nr_pages * page_size; + memset(args, 0, sizeof(struct uffd_args) * nr_cpus); + if (uffd_test_ctx_init(UFFD_FEATURE_WP_UNPOPULATED, NULL)) err("context init failed"); diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c index 04d91f144d1c..2709a34a39c5 100644 --- a/tools/testing/selftests/mm/uffd-unit-tests.c +++ b/tools/testing/selftests/mm/uffd-unit-tests.c @@ -951,6 +951,117 @@ static void uffd_zeropage_test(uffd_test_args_t *args) uffd_test_pass(); } +static void uffd_register_poison(int uffd, void *addr, uint64_t len) +{ + uint64_t ioctls = 0; + uint64_t expected = (1 << _UFFDIO_COPY) | (1 << _UFFDIO_POISON); + + if (uffd_register_with_ioctls(uffd, addr, len, true, + false, false, &ioctls)) + err("poison register fail"); + + if ((ioctls & expected) != expected) + err("registered area doesn't support COPY and POISON ioctls"); +} + +static void do_uffdio_poison(int uffd, unsigned long offset) +{ + struct uffdio_poison uffdio_poison = { 0 }; + int ret; + __s64 res; + + uffdio_poison.range.start = (unsigned long) area_dst + offset; + uffdio_poison.range.len = page_size; + uffdio_poison.mode = 0; + ret = ioctl(uffd, UFFDIO_POISON, &uffdio_poison); + res = uffdio_poison.updated; + + if (ret) + err("UFFDIO_POISON error: %"PRId64, (int64_t)res); + else if (res != page_size) + err("UFFDIO_POISON unexpected size: %"PRId64, (int64_t)res); +} + +static void uffd_poison_handle_fault( + struct uffd_msg *msg, struct uffd_args *args) +{ + unsigned long offset; + + if (msg->event != UFFD_EVENT_PAGEFAULT) + err("unexpected msg event %u", msg->event); + + if (msg->arg.pagefault.flags & + (UFFD_PAGEFAULT_FLAG_WP | UFFD_PAGEFAULT_FLAG_MINOR)) + err("unexpected fault type %llu", msg->arg.pagefault.flags); + + offset = (char *)(unsigned long)msg->arg.pagefault.address - area_dst; + offset &= ~(page_size-1); + + /* Odd pages -> copy zeroed page; even pages -> poison. */ + if (offset & page_size) + copy_page(uffd, offset, false); + else + do_uffdio_poison(uffd, offset); +} + +static void uffd_poison_test(uffd_test_args_t *targs) +{ + pthread_t uffd_mon; + char c; + struct uffd_args args = { 0 }; + struct sigaction act = { 0 }; + unsigned long nr_sigbus = 0; + unsigned long nr; + + fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK); + + uffd_register_poison(uffd, area_dst, nr_pages * page_size); + memset(area_src, 0, nr_pages * page_size); + + args.handle_fault = uffd_poison_handle_fault; + if (pthread_create(&uffd_mon, NULL, uffd_poll_thread, &args)) + err("uffd_poll_thread create"); + + sigbuf = &jbuf; + act.sa_sigaction = sighndl; + act.sa_flags = SA_SIGINFO; + if (sigaction(SIGBUS, &act, 0)) + err("sigaction"); + + for (nr = 0; nr < nr_pages; ++nr) { + unsigned long offset = nr * page_size; + const char *bytes = (const char *) area_dst + offset; + const char *i; + + if (sigsetjmp(*sigbuf, 1)) { + /* + * Access below triggered a SIGBUS, which was caught by + * sighndl, which then jumped here. Count this SIGBUS, + * and move on to next page. + */ + ++nr_sigbus; + continue; + } + + for (i = bytes; i < bytes + page_size; ++i) { + if (*i) + err("nonzero byte in area_dst (%p) at %p: %u", + area_dst, i, *i); + } + } + + if (write(pipefd[1], &c, sizeof(c)) != sizeof(c)) + err("pipe write"); + if (pthread_join(uffd_mon, NULL)) + err("pthread_join()"); + + if (nr_sigbus != nr_pages / 2) + err("expected to receive %lu SIGBUS, actually received %lu", + nr_pages / 2, nr_sigbus); + + uffd_test_pass(); +} + /* * Test the returned uffdio_register.ioctls with different register modes. * Note that _UFFDIO_ZEROPAGE is tested separately in the zeropage test. @@ -1126,6 +1237,12 @@ uffd_test_case_t uffd_tests[] = { UFFD_FEATURE_PAGEFAULT_FLAG_WP | UFFD_FEATURE_WP_HUGETLBFS_SHMEM, }, + { + .name = "poison", + .uffd_fn = uffd_poison_test, + .mem_targets = MEM_ALL, + .uffd_feature_required = UFFD_FEATURE_POISON, + }, }; static void usage(const char *prog) diff --git a/tools/testing/selftests/mm/va_high_addr_switch.c b/tools/testing/selftests/mm/va_high_addr_switch.c index 7cfaf4a74c57..cfbc501290d3 100644 --- a/tools/testing/selftests/mm/va_high_addr_switch.c +++ b/tools/testing/selftests/mm/va_high_addr_switch.c @@ -292,7 +292,7 @@ static int supported_arch(void) #elif defined(__x86_64__) return 1; #elif defined(__aarch64__) - return 1; + return getpagesize() == PAGE_SIZE; #else return 0; #endif diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 501854a89cc0..2f9d378edec3 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -15,6 +15,7 @@ ip_local_port_range ipsec ipv6_flowlabel ipv6_flowlabel_mgr +log.txt msg_zerocopy nettest psock_fanout @@ -45,6 +46,7 @@ test_unix_oob timestamping tls toeplitz +tools tun txring_overwrite txtimestamp diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 7f3ab2a93ed6..8b017070960d 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -3,6 +3,8 @@ CFLAGS = -Wall -Wl,--no-as-needed -O2 -g CFLAGS += -I../../../../usr/include/ $(KHDR_INCLUDES) +# Additional include paths needed by kselftest.h +CFLAGS += -I../ TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh \ rtnetlink.sh xfrm_policy.sh test_blackhole_dev.sh @@ -38,6 +40,7 @@ TEST_PROGS += srv6_end_dt6_l3vpn_test.sh TEST_PROGS += srv6_hencap_red_l3vpn_test.sh TEST_PROGS += srv6_hl2encap_red_l2vpn_test.sh TEST_PROGS += srv6_end_next_csid_l3vpn_test.sh +TEST_PROGS += srv6_end_x_next_csid_l3vpn_test.sh TEST_PROGS += srv6_end_flavors_test.sh TEST_PROGS += vrf_strict_mode_test.sh TEST_PROGS += arp_ndisc_evict_nocarrier.sh @@ -85,6 +88,7 @@ TEST_GEN_FILES += bind_wildcard TEST_PROGS += test_vxlan_mdb.sh TEST_PROGS += test_bridge_neigh_suppress.sh TEST_PROGS += test_vxlan_nolocalbypass.sh +TEST_PROGS += test_bridge_backup_port.sh TEST_FILES := settings @@ -113,7 +117,7 @@ $(MAKE_DIRS): mkdir -p $@ # Get Clang's default includes on this system, as opposed to those seen by -# '-target bpf'. This fixes "missing" files on some architectures/distros, +# '--target=bpf'. This fixes "missing" files on some architectures/distros, # such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc. # # Use '-idirafter': Don't interfere with include mechanics except where the @@ -131,7 +135,7 @@ endif CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG),$(CLANG_TARGET_ARCH)) $(OUTPUT)/nat6to4.o: nat6to4.c $(BPFOBJ) | $(MAKE_DIRS) - $(CLANG) -O2 -target bpf -c $< $(CCINCLUDE) $(CLANG_SYS_INCLUDES) -o $@ + $(CLANG) -O2 --target=bpf -c $< $(CCINCLUDE) $(CLANG_SYS_INCLUDES) -o $@ $(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile) \ $(APIDIR)/linux/bpf.h \ diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index cd3cc52c59b4..8da562a9ae87 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -51,3 +51,4 @@ CONFIG_AMT=m CONFIG_VXLAN=m CONFIG_IP_SCTP=m CONFIG_NETFILTER_XT_MATCH_POLICY=m +CONFIG_CRYPTO_ARIA=y diff --git a/tools/testing/selftests/net/csum.c b/tools/testing/selftests/net/csum.c index 82a1c1839da6..90eb06fefa59 100644 --- a/tools/testing/selftests/net/csum.c +++ b/tools/testing/selftests/net/csum.c @@ -91,6 +91,8 @@ #include <sys/types.h> #include <unistd.h> +#include "kselftest.h" + static bool cfg_bad_csum; static int cfg_family = PF_INET6; static int cfg_num_pkt = 4; @@ -450,7 +452,7 @@ static void send_packet(int fd, const char *buf, int len) iov[2].iov_len = len; msg.msg_iov = iov; - msg.msg_iovlen = sizeof(iov) / sizeof(iov[0]); + msg.msg_iovlen = ARRAY_SIZE(iov); msg.msg_name = &addr; msg.msg_namelen = sizeof(addr); @@ -505,7 +507,7 @@ static void __recv_prepare_packet_filter(int fd, int off_nexthdr, int off_dport) struct sock_fprog prog = {}; prog.filter = filter; - prog.len = sizeof(filter) / sizeof(struct sock_filter); + prog.len = ARRAY_SIZE(filter); if (setsockopt(fd, SOL_SOCKET, SO_ATTACH_FILTER, &prog, sizeof(prog))) error(1, errno, "setsockopt filter"); } diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index df8d90b51867..a6f2c0b9555d 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -29,6 +29,7 @@ IPV4_TESTS=" ipv4_large_res_grp ipv4_compat_mode ipv4_fdb_grp_fcnal + ipv4_mpath_select ipv4_torture ipv4_res_torture " @@ -42,6 +43,7 @@ IPV6_TESTS=" ipv6_large_res_grp ipv6_compat_mode ipv6_fdb_grp_fcnal + ipv6_mpath_select ipv6_torture ipv6_res_torture " @@ -370,6 +372,27 @@ check_large_res_grp() log_test $? 0 "Dump large (x$buckets) nexthop buckets" } +get_route_dev() +{ + local pfx="$1" + local out + + if out=$($IP -j route get "$pfx" | jq -re ".[0].dev"); then + echo "$out" + fi +} + +check_route_dev() +{ + local pfx="$1" + local expected="$2" + local out + + out=$(get_route_dev "$pfx") + + check_output "$out" "$expected" +} + start_ip_monitor() { local mtype=$1 @@ -575,6 +598,112 @@ ipv4_fdb_grp_fcnal() $IP link del dev vx10 } +ipv4_mpath_select() +{ + local rc dev match h addr + + echo + echo "IPv4 multipath selection" + echo "------------------------" + if [ ! -x "$(command -v jq)" ]; then + echo "SKIP: Could not run test; need jq tool" + return $ksft_skip + fi + + # Use status of existing neighbor entry when determining nexthop for + # multipath routes. + local -A gws + gws=([veth1]=172.16.1.2 [veth3]=172.16.2.2) + local -A other_dev + other_dev=([veth1]=veth3 [veth3]=veth1) + + run_cmd "$IP nexthop add id 1 via ${gws["veth1"]} dev veth1" + run_cmd "$IP nexthop add id 2 via ${gws["veth3"]} dev veth3" + run_cmd "$IP nexthop add id 1001 group 1/2" + run_cmd "$IP ro add 172.16.101.0/24 nhid 1001" + rc=0 + for dev in veth1 veth3; do + match=0 + for h in {1..254}; do + addr="172.16.101.$h" + if [ "$(get_route_dev "$addr")" = "$dev" ]; then + match=1 + break + fi + done + if (( match == 0 )); then + echo "SKIP: Did not find a route using device $dev" + return $ksft_skip + fi + run_cmd "$IP neigh add ${gws[$dev]} dev $dev nud failed" + if ! check_route_dev "$addr" "${other_dev[$dev]}"; then + rc=1 + break + fi + run_cmd "$IP neigh del ${gws[$dev]} dev $dev" + done + log_test $rc 0 "Use valid neighbor during multipath selection" + + run_cmd "$IP neigh add 172.16.1.2 dev veth1 nud incomplete" + run_cmd "$IP neigh add 172.16.2.2 dev veth3 nud incomplete" + run_cmd "$IP route get 172.16.101.1" + # if we did not crash, success + log_test $rc 0 "Multipath selection with no valid neighbor" +} + +ipv6_mpath_select() +{ + local rc dev match h addr + + echo + echo "IPv6 multipath selection" + echo "------------------------" + if [ ! -x "$(command -v jq)" ]; then + echo "SKIP: Could not run test; need jq tool" + return $ksft_skip + fi + + # Use status of existing neighbor entry when determining nexthop for + # multipath routes. + local -A gws + gws=([veth1]=2001:db8:91::2 [veth3]=2001:db8:92::2) + local -A other_dev + other_dev=([veth1]=veth3 [veth3]=veth1) + + run_cmd "$IP nexthop add id 1 via ${gws["veth1"]} dev veth1" + run_cmd "$IP nexthop add id 2 via ${gws["veth3"]} dev veth3" + run_cmd "$IP nexthop add id 1001 group 1/2" + run_cmd "$IP ro add 2001:db8:101::/64 nhid 1001" + rc=0 + for dev in veth1 veth3; do + match=0 + for h in {1..65535}; do + addr=$(printf "2001:db8:101::%x" $h) + if [ "$(get_route_dev "$addr")" = "$dev" ]; then + match=1 + break + fi + done + if (( match == 0 )); then + echo "SKIP: Did not find a route using device $dev" + return $ksft_skip + fi + run_cmd "$IP neigh add ${gws[$dev]} dev $dev nud failed" + if ! check_route_dev "$addr" "${other_dev[$dev]}"; then + rc=1 + break + fi + run_cmd "$IP neigh del ${gws[$dev]} dev $dev" + done + log_test $rc 0 "Use valid neighbor during multipath selection" + + run_cmd "$IP neigh add 2001:db8:91::2 dev veth1 nud incomplete" + run_cmd "$IP neigh add 2001:db8:92::2 dev veth3 nud incomplete" + run_cmd "$IP route get 2001:db8:101::1" + # if we did not crash, success + log_test $rc 0 "Multipath selection with no valid neighbor" +} + ################################################################################ # basic operations (add, delete, replace) on nexthops and nexthop groups # diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 35d89dfa6f11..e7d2a530618a 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -9,13 +9,17 @@ ret=0 ksft_skip=4 # all tests in this script. Can be overridden with -t option -TESTS="unregister down carrier nexthop suppress ipv6_notify ipv4_notify ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics ipv4_route_metrics ipv4_route_v6_gw rp_filter ipv4_del_addr ipv4_mangle ipv6_mangle ipv4_bcast_neigh" +TESTS="unregister down carrier nexthop suppress ipv6_notify ipv4_notify \ + ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics \ + ipv4_route_metrics ipv4_route_v6_gw rp_filter ipv4_del_addr \ + ipv6_del_addr ipv4_mangle ipv6_mangle ipv4_bcast_neigh fib6_gc_test \ + ipv4_mpath_list ipv6_mpath_list" VERBOSE=0 PAUSE_ON_FAIL=no PAUSE=no -IP="ip -netns ns1" -NS_EXEC="ip netns exec ns1" +IP="$(which ip) -netns ns1" +NS_EXEC="$(which ip) netns exec ns1" which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping) @@ -747,6 +751,68 @@ fib_notify_test() cleanup &> /dev/null } +fib6_gc_test() +{ + setup + + echo + echo "Fib6 garbage collection test" + set -e + + EXPIRE=3 + + # Check expiration of routes every $EXPIRE seconds (GC) + $NS_EXEC sysctl -wq net.ipv6.route.gc_interval=$EXPIRE + + $IP link add dummy_10 type dummy + $IP link set dev dummy_10 up + $IP -6 address add 2001:10::1/64 dev dummy_10 + + $NS_EXEC sysctl -wq net.ipv6.route.flush=1 + + # Temporary routes + for i in $(seq 1 1000); do + # Expire route after $EXPIRE seconds + $IP -6 route add 2001:20::$i \ + via 2001:10::2 dev dummy_10 expires $EXPIRE + done + sleep $(($EXPIRE * 2)) + N_EXP_SLEEP=$($IP -6 route list |grep expires|wc -l) + if [ $N_EXP_SLEEP -ne 0 ]; then + echo "FAIL: expected 0 routes with expires, got $N_EXP_SLEEP" + ret=1 + else + ret=0 + fi + + # Permanent routes + for i in $(seq 1 5000); do + $IP -6 route add 2001:30::$i \ + via 2001:10::2 dev dummy_10 + done + # Temporary routes + for i in $(seq 1 1000); do + # Expire route after $EXPIRE seconds + $IP -6 route add 2001:20::$i \ + via 2001:10::2 dev dummy_10 expires $EXPIRE + done + sleep $(($EXPIRE * 2)) + N_EXP_SLEEP=$($IP -6 route list |grep expires|wc -l) + if [ $N_EXP_SLEEP -ne 0 ]; then + echo "FAIL: expected 0 routes with expires," \ + "got $N_EXP_SLEEP (5000 permanent routes)" + ret=1 + else + ret=0 + fi + + set +e + + log_test $ret 0 "ipv6 route garbage collection" + + cleanup &> /dev/null +} + fib_suppress_test() { echo @@ -1869,6 +1935,155 @@ ipv4_del_addr_test() cleanup } +ipv6_del_addr_test() +{ + echo + echo "IPv6 delete address route tests" + + setup + + set -e + for i in $(seq 6); do + $IP li add dummy${i} up type dummy + done + + $IP li add red up type vrf table 1111 + $IP ro add vrf red unreachable default + for i in $(seq 4 6); do + $IP li set dummy${i} vrf red + done + + $IP addr add dev dummy1 fe80::1/128 + $IP addr add dev dummy1 2001:db8:101::1/64 + $IP addr add dev dummy1 2001:db8:101::10/64 + $IP addr add dev dummy1 2001:db8:101::11/64 + $IP addr add dev dummy1 2001:db8:101::12/64 + $IP addr add dev dummy1 2001:db8:101::13/64 + $IP addr add dev dummy1 2001:db8:101::14/64 + $IP addr add dev dummy1 2001:db8:101::15/64 + $IP addr add dev dummy2 fe80::1/128 + $IP addr add dev dummy2 2001:db8:101::1/64 + $IP addr add dev dummy2 2001:db8:101::11/64 + $IP addr add dev dummy3 fe80::1/128 + + $IP addr add dev dummy4 2001:db8:101::1/64 + $IP addr add dev dummy4 2001:db8:101::10/64 + $IP addr add dev dummy4 2001:db8:101::11/64 + $IP addr add dev dummy4 2001:db8:101::12/64 + $IP addr add dev dummy4 2001:db8:101::13/64 + $IP addr add dev dummy4 2001:db8:101::14/64 + $IP addr add dev dummy5 2001:db8:101::1/64 + $IP addr add dev dummy5 2001:db8:101::11/64 + + # Single device using src address + $IP route add 2001:db8:110::/64 dev dummy3 src 2001:db8:101::10 + # Two devices with the same source address + $IP route add 2001:db8:111::/64 dev dummy3 src 2001:db8:101::11 + # VRF with single device using src address + $IP route add vrf red 2001:db8:110::/64 dev dummy6 src 2001:db8:101::10 + # VRF with two devices using src address + $IP route add vrf red 2001:db8:111::/64 dev dummy6 src 2001:db8:101::11 + # src address and nexthop dev in same VRF + $IP route add 2001:db8:112::/64 dev dummy3 src 2001:db8:101::12 + $IP route add vrf red 2001:db8:112::/64 dev dummy6 src 2001:db8:101::12 + # src address and nexthop device in different VRF + $IP route add 2001:db8:113::/64 dev lo src 2001:db8:101::13 + $IP route add vrf red 2001:db8:113::/64 dev lo src 2001:db8:101::13 + # table ID 0 + $IP route add table 0 2001:db8:115::/64 via 2001:db8:101::2 src 2001:db8:101::15 + # Link local source route + $IP route add 2001:db8:116::/64 dev dummy2 src fe80::1 + $IP route add 2001:db8:117::/64 dev dummy3 src fe80::1 + set +e + + echo " Single device using src address" + + $IP addr del dev dummy1 2001:db8:101::10/64 + $IP -6 route show | grep -q "src 2001:db8:101::10 " + log_test $? 1 "Prefsrc removed when src address removed on other device" + + echo " Two devices with the same source address" + + $IP addr del dev dummy1 2001:db8:101::11/64 + $IP -6 route show | grep -q "src 2001:db8:101::11 " + log_test $? 0 "Prefsrc not removed when src address exist on other device" + + $IP addr del dev dummy2 2001:db8:101::11/64 + $IP -6 route show | grep -q "src 2001:db8:101::11 " + log_test $? 1 "Prefsrc removed when src address removed on all devices" + + echo " VRF with single device using src address" + + $IP addr del dev dummy4 2001:db8:101::10/64 + $IP -6 route show vrf red | grep -q "src 2001:db8:101::10 " + log_test $? 1 "Prefsrc removed when src address removed on other device" + + echo " VRF with two devices using src address" + + $IP addr del dev dummy4 2001:db8:101::11/64 + $IP -6 route show vrf red | grep -q "src 2001:db8:101::11 " + log_test $? 0 "Prefsrc not removed when src address exist on other device" + + $IP addr del dev dummy5 2001:db8:101::11/64 + $IP -6 route show vrf red | grep -q "src 2001:db8:101::11 " + log_test $? 1 "Prefsrc removed when src address removed on all devices" + + echo " src address and nexthop dev in same VRF" + + $IP addr del dev dummy4 2001:db8:101::12/64 + $IP -6 route show vrf red | grep -q "src 2001:db8:101::12 " + log_test $? 1 "Prefsrc removed from VRF when source address deleted" + $IP -6 route show | grep -q " src 2001:db8:101::12 " + log_test $? 0 "Prefsrc in default VRF not removed" + + $IP addr add dev dummy4 2001:db8:101::12/64 + $IP route replace vrf red 2001:db8:112::/64 dev dummy6 src 2001:db8:101::12 + $IP addr del dev dummy1 2001:db8:101::12/64 + $IP -6 route show vrf red | grep -q "src 2001:db8:101::12 " + log_test $? 0 "Prefsrc not removed from VRF when source address exist" + $IP -6 route show | grep -q " src 2001:db8:101::12 " + log_test $? 1 "Prefsrc in default VRF removed" + + echo " src address and nexthop device in different VRF" + + $IP addr del dev dummy4 2001:db8:101::13/64 + $IP -6 route show vrf red | grep -q "src 2001:db8:101::13 " + log_test $? 0 "Prefsrc not removed from VRF when nexthop dev in diff VRF" + $IP -6 route show | grep -q "src 2001:db8:101::13 " + log_test $? 0 "Prefsrc not removed in default VRF" + + $IP addr add dev dummy4 2001:db8:101::13/64 + $IP addr del dev dummy1 2001:db8:101::13/64 + $IP -6 route show vrf red | grep -q "src 2001:db8:101::13 " + log_test $? 1 "Prefsrc removed from VRF when nexthop dev in diff VRF" + $IP -6 route show | grep -q "src 2001:db8:101::13 " + log_test $? 1 "Prefsrc removed in default VRF" + + echo " Table ID 0" + + $IP addr del dev dummy1 2001:db8:101::15/64 + $IP -6 route show | grep -q "src 2001:db8:101::15" + log_test $? 1 "Prefsrc removed from default VRF when source address deleted" + + echo " Link local source route" + $IP addr del dev dummy1 fe80::1/128 + $IP -6 route show | grep -q "2001:db8:116::/64 dev dummy2 src fe80::1" + log_test $? 0 "Prefsrc not removed when delete ll addr from other dev" + $IP addr del dev dummy2 fe80::1/128 + $IP -6 route show | grep -q "2001:db8:116::/64 dev dummy2 src fe80::1" + log_test $? 1 "Prefsrc removed when delete ll addr" + $IP -6 route show | grep -q "2001:db8:117::/64 dev dummy3 src fe80::1" + log_test $? 0 "Prefsrc not removed when delete ll addr from other dev" + $IP addr add dev dummy1 fe80::1/128 + $IP addr del dev dummy3 fe80::1/128 + $IP -6 route show | grep -q "2001:db8:117::/64 dev dummy3 src fe80::1" + log_test $? 1 "Prefsrc removed even ll addr still exist on other dev" + + for i in $(seq 6); do + $IP li del dummy${i} + done + cleanup +} ipv4_route_v6_gw_test() { @@ -2138,6 +2353,156 @@ ipv4_bcast_neigh_test() cleanup } +mpath_dep_check() +{ + if [ ! -x "$(command -v mausezahn)" ]; then + echo "mausezahn command not found. Skipping test" + return 1 + fi + + if [ ! -x "$(command -v jq)" ]; then + echo "jq command not found. Skipping test" + return 1 + fi + + if [ ! -x "$(command -v bc)" ]; then + echo "bc command not found. Skipping test" + return 1 + fi + + if [ ! -x "$(command -v perf)" ]; then + echo "perf command not found. Skipping test" + return 1 + fi + + perf list fib:* | grep -q fib_table_lookup + if [ $? -ne 0 ]; then + echo "IPv4 FIB tracepoint not found. Skipping test" + return 1 + fi + + perf list fib6:* | grep -q fib6_table_lookup + if [ $? -ne 0 ]; then + echo "IPv6 FIB tracepoint not found. Skipping test" + return 1 + fi + + return 0 +} + +link_stats_get() +{ + local ns=$1; shift + local dev=$1; shift + local dir=$1; shift + local stat=$1; shift + + ip -n $ns -j -s link show dev $dev \ + | jq '.[]["stats64"]["'$dir'"]["'$stat'"]' +} + +list_rcv_eval() +{ + local file=$1; shift + local expected=$1; shift + + local count=$(tail -n 1 $file | jq '.["counter-value"] | tonumber | floor') + local ratio=$(echo "scale=2; $count / $expected" | bc -l) + local res=$(echo "$ratio >= 0.95" | bc) + [[ $res -eq 1 ]] + log_test $? 0 "Multipath route hit ratio ($ratio)" +} + +ipv4_mpath_list_test() +{ + echo + echo "IPv4 multipath list receive tests" + + mpath_dep_check || return 1 + + route_setup + + set -e + run_cmd "ip netns exec ns1 ethtool -K veth1 tcp-segmentation-offload off" + + run_cmd "ip netns exec ns2 bash -c \"echo 20000 > /sys/class/net/veth2/gro_flush_timeout\"" + run_cmd "ip netns exec ns2 bash -c \"echo 1 > /sys/class/net/veth2/napi_defer_hard_irqs\"" + run_cmd "ip netns exec ns2 ethtool -K veth2 generic-receive-offload on" + run_cmd "ip -n ns2 link add name nh1 up type dummy" + run_cmd "ip -n ns2 link add name nh2 up type dummy" + run_cmd "ip -n ns2 address add 172.16.201.1/24 dev nh1" + run_cmd "ip -n ns2 address add 172.16.202.1/24 dev nh2" + run_cmd "ip -n ns2 neigh add 172.16.201.2 lladdr 00:11:22:33:44:55 nud perm dev nh1" + run_cmd "ip -n ns2 neigh add 172.16.202.2 lladdr 00:aa:bb:cc:dd:ee nud perm dev nh2" + run_cmd "ip -n ns2 route add 203.0.113.0/24 + nexthop via 172.16.201.2 nexthop via 172.16.202.2" + run_cmd "ip netns exec ns2 sysctl -qw net.ipv4.fib_multipath_hash_policy=1" + set +e + + local dmac=$(ip -n ns2 -j link show dev veth2 | jq -r '.[]["address"]') + local tmp_file=$(mktemp) + local cmd="ip netns exec ns1 mausezahn veth1 -a own -b $dmac + -A 172.16.101.1 -B 203.0.113.1 -t udp 'sp=12345,dp=0-65535' -q" + + # Packets forwarded in a list using a multipath route must not reuse a + # cached result so that a flow always hits the same nexthop. In other + # words, the FIB lookup tracepoint needs to be triggered for every + # packet. + local t0_rx_pkts=$(link_stats_get ns2 veth2 rx packets) + run_cmd "perf stat -e fib:fib_table_lookup --filter 'err == 0' -j -o $tmp_file -- $cmd" + local t1_rx_pkts=$(link_stats_get ns2 veth2 rx packets) + local diff=$(echo $t1_rx_pkts - $t0_rx_pkts | bc -l) + list_rcv_eval $tmp_file $diff + + rm $tmp_file + route_cleanup +} + +ipv6_mpath_list_test() +{ + echo + echo "IPv6 multipath list receive tests" + + mpath_dep_check || return 1 + + route_setup + + set -e + run_cmd "ip netns exec ns1 ethtool -K veth1 tcp-segmentation-offload off" + + run_cmd "ip netns exec ns2 bash -c \"echo 20000 > /sys/class/net/veth2/gro_flush_timeout\"" + run_cmd "ip netns exec ns2 bash -c \"echo 1 > /sys/class/net/veth2/napi_defer_hard_irqs\"" + run_cmd "ip netns exec ns2 ethtool -K veth2 generic-receive-offload on" + run_cmd "ip -n ns2 link add name nh1 up type dummy" + run_cmd "ip -n ns2 link add name nh2 up type dummy" + run_cmd "ip -n ns2 -6 address add 2001:db8:201::1/64 dev nh1" + run_cmd "ip -n ns2 -6 address add 2001:db8:202::1/64 dev nh2" + run_cmd "ip -n ns2 -6 neigh add 2001:db8:201::2 lladdr 00:11:22:33:44:55 nud perm dev nh1" + run_cmd "ip -n ns2 -6 neigh add 2001:db8:202::2 lladdr 00:aa:bb:cc:dd:ee nud perm dev nh2" + run_cmd "ip -n ns2 -6 route add 2001:db8:301::/64 + nexthop via 2001:db8:201::2 nexthop via 2001:db8:202::2" + run_cmd "ip netns exec ns2 sysctl -qw net.ipv6.fib_multipath_hash_policy=1" + set +e + + local dmac=$(ip -n ns2 -j link show dev veth2 | jq -r '.[]["address"]') + local tmp_file=$(mktemp) + local cmd="ip netns exec ns1 mausezahn -6 veth1 -a own -b $dmac + -A 2001:db8:101::1 -B 2001:db8:301::1 -t udp 'sp=12345,dp=0-65535' -q" + + # Packets forwarded in a list using a multipath route must not reuse a + # cached result so that a flow always hits the same nexthop. In other + # words, the FIB lookup tracepoint needs to be triggered for every + # packet. + local t0_rx_pkts=$(link_stats_get ns2 veth2 rx packets) + run_cmd "perf stat -e fib6:fib6_table_lookup --filter 'err == 0' -j -o $tmp_file -- $cmd" + local t1_rx_pkts=$(link_stats_get ns2 veth2 rx packets) + local diff=$(echo $t1_rx_pkts - $t0_rx_pkts | bc -l) + list_rcv_eval $tmp_file $diff + + rm $tmp_file + route_cleanup +} + ################################################################################ # usage @@ -2211,12 +2576,16 @@ do ipv6_addr_metric) ipv6_addr_metric_test;; ipv4_addr_metric) ipv4_addr_metric_test;; ipv4_del_addr) ipv4_del_addr_test;; + ipv6_del_addr) ipv6_del_addr_test;; ipv6_route_metrics) ipv6_route_metrics_test;; ipv4_route_metrics) ipv4_route_metrics_test;; ipv4_route_v6_gw) ipv4_route_v6_gw_test;; ipv4_mangle) ipv4_mangle_test;; ipv6_mangle) ipv6_mangle_test;; ipv4_bcast_neigh) ipv4_bcast_neigh_test;; + fib6_gc_test|ipv6_gc) fib6_gc_test;; + ipv4_mpath_list) ipv4_mpath_list_test;; + ipv6_mpath_list) ipv6_mpath_list_test;; help) echo "Test names: $TESTS"; exit 0;; esac diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile index 770efbe24f0d..74e754e266c3 100644 --- a/tools/testing/selftests/net/forwarding/Makefile +++ b/tools/testing/selftests/net/forwarding/Makefile @@ -64,7 +64,13 @@ TEST_PROGS = bridge_igmp.sh \ q_in_vni_ipv6.sh \ q_in_vni.sh \ router_bridge.sh \ + router_bridge_1d.sh \ + router_bridge_1d_lag.sh \ + router_bridge_lag.sh \ router_bridge_vlan.sh \ + router_bridge_vlan_upper.sh \ + router_bridge_pvid_vlan_upper.sh \ + router_bridge_vlan_upper_pvid.sh \ router_broadcast.sh \ router_mpath_nh_res.sh \ router_mpath_nh.sh \ @@ -85,6 +91,7 @@ TEST_PROGS = bridge_igmp.sh \ tc_flower.sh \ tc_flower_l2_miss.sh \ tc_flower_cfm.sh \ + tc_flower_port_range.sh \ tc_mpls_l2vpn.sh \ tc_police.sh \ tc_shblocks.sh \ diff --git a/tools/testing/selftests/net/forwarding/bridge_locked_port.sh b/tools/testing/selftests/net/forwarding/bridge_locked_port.sh index dc92d32464f6..9af9f6964808 100755 --- a/tools/testing/selftests/net/forwarding/bridge_locked_port.sh +++ b/tools/testing/selftests/net/forwarding/bridge_locked_port.sh @@ -9,6 +9,7 @@ ALL_TESTS=" locked_port_mab_roam locked_port_mab_config locked_port_mab_flush + locked_port_mab_redirect " NUM_NETIFS=4 @@ -319,6 +320,41 @@ locked_port_mab_flush() log_test "Locked port MAB FDB flush" } +# Check that traffic can be redirected from a locked bridge port and that it +# does not create locked FDB entries. +locked_port_mab_redirect() +{ + RET=0 + check_port_mab_support || return 0 + + bridge link set dev $swp1 learning on locked on mab on + tc qdisc add dev $swp1 clsact + tc filter add dev $swp1 ingress protocol all pref 1 handle 101 flower \ + action mirred egress redirect dev $swp2 + + ping_do $h1 192.0.2.2 + check_err $? "Ping did not work with redirection" + + bridge fdb get `mac_get $h1` br br0 vlan 1 2> /dev/null | \ + grep "dev $swp1" | grep -q "locked" + check_fail $? "Locked entry created for redirected traffic" + + tc filter del dev $swp1 ingress protocol all pref 1 handle 101 flower + + ping_do $h1 192.0.2.2 + check_fail $? "Ping worked without redirection" + + bridge fdb get `mac_get $h1` br br0 vlan 1 2> /dev/null | \ + grep "dev $swp1" | grep -q "locked" + check_err $? "Locked entry not created after deleting filter" + + bridge fdb del `mac_get $h1` vlan 1 dev $swp1 master + tc qdisc del dev $swp1 clsact + bridge link set dev $swp1 learning off locked off mab off + + log_test "Locked port MAB redirect" +} + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index f69015bf2dea..e37a15eda6c2 100755 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -1232,6 +1232,15 @@ ping_test() log_test "ping$3" } +ping_test_fails() +{ + RET=0 + + ping_do $1 $2 + check_fail $? + log_test "ping fails$3" +} + ping6_do() { local if_name=$1 @@ -1254,6 +1263,15 @@ ping6_test() log_test "ping6$3" } +ping6_test_fails() +{ + RET=0 + + ping6_do $1 $2 + check_fail $? + log_test "ping6 fails$3" +} + learning_test() { local bridge=$1 diff --git a/tools/testing/selftests/net/forwarding/router_bridge.sh b/tools/testing/selftests/net/forwarding/router_bridge.sh index 8ce0aed54ece..0182eb2abfa6 100755 --- a/tools/testing/selftests/net/forwarding/router_bridge.sh +++ b/tools/testing/selftests/net/forwarding/router_bridge.sh @@ -1,9 +1,39 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +# +------------------------+ +----------------------+ +# | H1 (vrf) | | H2 (vrf) | +# | + $h1 | | + $h2 | +# | | 192.0.2.1/28 | | | 192.0.2.130/28 | +# | | 2001:db8:1::1/64 | | | 2001:db8:2::2/64 | +# | | | | | | +# +----|-------------------+ +--|-------------------+ +# | | +# +----|--------------------------------------------------|-------------------+ +# | SW | | | +# | +--|-----------------------------+ + $swp2 | +# | | + $swp1 BR1 (802.1q) | 192.0.2.129/28 | +# | | 192.0.2.2/28 | 2001:db8:2::1/64 | +# | | 2001:db8:1::1/64 | | +# | | | | +# | +--------------------------------+ | +# +---------------------------------------------------------------------------+ + ALL_TESTS=" ping_ipv4 ping_ipv6 + config_remaster + ping_ipv4 + ping_ipv6 + config_remove_pvid + ping_ipv4_fails + ping_ipv6_fails + config_add_pvid + ping_ipv4 + ping_ipv6 + config_late_pvid + ping_ipv4 + ping_ipv6 " NUM_NETIFS=4 source lib.sh @@ -62,6 +92,42 @@ router_destroy() ip link del dev br1 } +config_remaster() +{ + log_info "Remaster bridge slave" + + ip link set dev $swp1 nomaster + sleep 2 + ip link set dev $swp1 master br1 +} + +config_remove_pvid() +{ + log_info "Remove PVID from the bridge" + + bridge vlan add dev br1 vid 1 self + sleep 2 +} + +config_add_pvid() +{ + log_info "Add PVID to the bridge" + + bridge vlan add dev br1 vid 1 self pvid untagged + sleep 2 +} + +config_late_pvid() +{ + log_info "Add bridge PVID after enslaving port" + + ip link set dev $swp1 nomaster + ip link set dev br1 type bridge vlan_default_pvid 0 + sleep 2 + ip link set dev $swp1 master br1 + ip link set dev br1 type bridge vlan_default_pvid 1 +} + setup_prepare() { h1=${NETIFS[p1]} @@ -104,6 +170,16 @@ ping_ipv6() ping6_test $h1 2001:db8:2::2 } +ping_ipv4_fails() +{ + ping_test_fails $h1 192.0.2.130 +} + +ping_ipv6_fails() +{ + ping6_test_fails $h1 2001:db8:2::2 +} + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/net/forwarding/router_bridge_1d.sh b/tools/testing/selftests/net/forwarding/router_bridge_1d.sh new file mode 100755 index 000000000000..6d51f2ca72a2 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/router_bridge_1d.sh @@ -0,0 +1,185 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# +---------------------------------------------+ +----------------------+ +# | H1 (vrf) | | H2 (vrf) | +# | + $h1.100 + $h1.200 | | + $h2 | +# | | 192.0.2.1/28 | 192.0.2.17/28 | | | 192.0.2.130/28 | +# | | 2001:db8:1::1/64 | 2001:db8:3::1/64 | | | 192.0.2.146/28 | +# | \_________ __________/ | | | 2001:db8:2::2/64 | +# | V | | | 2001:db8:4::2/64 | +# | + $h1 | | | | +# +--------------|------------------------------+ +--|-------------------+ +# | | +# +--------------|----------------------------------------|-------------------+ +# | SW + $swp1 + $swp2 | +# | | 192.0.2.129/28 | +# | | 192.0.2.145/28 | +# | | 2001:db8:2::1/64 | +# | ________^___________________________ 2001:db8:4::1/64 | +# | / \ | +# | +---|------------------------------+ +---|------------------------------+ | +# | | + $swp1.100 BR1 (802.1d) | | + $swp1.200 BR2 (802.1d) | | +# | | 192.0.2.2/28 | | 192.0.2.18/28 | | +# | | 2001:db8:1::2/64 | | 2001:db8:3::2/64 | | +# | | | | | | +# | +----------------------------------+ +----------------------------------+ | +# +---------------------------------------------------------------------------+ + +ALL_TESTS=" + ping_ipv4 + ping_ipv6 + config_remaster + ping_ipv4 + ping_ipv6 +" +NUM_NETIFS=4 +source lib.sh + +h1_create() +{ + simple_if_init $h1 + vlan_create $h1 100 v$h1 192.0.2.1/28 2001:db8:1::1/64 + vlan_create $h1 200 v$h1 192.0.2.17/28 2001:db8:3::1/64 + ip -4 route add 192.0.2.128/28 vrf v$h1 nexthop via 192.0.2.2 + ip -4 route add 192.0.2.144/28 vrf v$h1 nexthop via 192.0.2.18 + ip -6 route add 2001:db8:2::/64 vrf v$h1 nexthop via 2001:db8:1::2 + ip -6 route add 2001:db8:4::/64 vrf v$h1 nexthop via 2001:db8:3::2 +} + +h1_destroy() +{ + ip -6 route del 2001:db8:4::/64 vrf v$h1 + ip -6 route del 2001:db8:2::/64 vrf v$h1 + ip -4 route del 192.0.2.144/28 vrf v$h1 + ip -4 route del 192.0.2.128/28 vrf v$h1 + vlan_destroy $h1 200 + vlan_destroy $h1 100 + simple_if_fini $h1 +} + +h2_create() +{ + simple_if_init $h2 192.0.2.130/28 2001:db8:2::2/64 \ + 192.0.2.146/28 2001:db8:4::2/64 + ip -4 route add 192.0.2.0/28 vrf v$h2 nexthop via 192.0.2.129 + ip -4 route add 192.0.2.16/28 vrf v$h2 nexthop via 192.0.2.145 + ip -6 route add 2001:db8:1::/64 vrf v$h2 nexthop via 2001:db8:2::1 + ip -6 route add 2001:db8:3::/64 vrf v$h2 nexthop via 2001:db8:4::1 +} + +h2_destroy() +{ + ip -6 route del 2001:db8:3::/64 vrf v$h2 + ip -6 route del 2001:db8:1::/64 vrf v$h2 + ip -4 route del 192.0.2.16/28 vrf v$h2 + ip -4 route del 192.0.2.0/28 vrf v$h2 + simple_if_fini $h2 192.0.2.130/28 2001:db8:2::2/64 \ + 192.0.2.146/28 2001:db8:4::2/64 +} + +router_create() +{ + ip link set dev $swp1 up + + vlan_create $swp1 100 + ip link add name br1 type bridge vlan_filtering 0 + ip link set dev br1 address $(mac_get $swp1.100) + ip link set dev $swp1.100 master br1 + __addr_add_del br1 add 192.0.2.2/28 2001:db8:1::2/64 + ip link set dev br1 up + + vlan_create $swp1 200 + ip link add name br2 type bridge vlan_filtering 0 + ip link set dev br2 address $(mac_get $swp1.200) + ip link set dev $swp1.200 master br2 + __addr_add_del br2 add 192.0.2.18/28 2001:db8:3::2/64 + ip link set dev br2 up + + ip link set dev $swp2 up + __addr_add_del $swp2 add 192.0.2.129/28 2001:db8:2::1/64 \ + 192.0.2.145/28 2001:db8:4::1/64 +} + +router_destroy() +{ + __addr_add_del $swp2 del 192.0.2.129/28 2001:db8:2::1/64 \ + 192.0.2.145/28 2001:db8:4::1/64 + ip link set dev $swp2 down + + __addr_add_del br2 del 192.0.2.18/28 2001:db8:3::2/64 + ip link set dev $swp1.200 nomaster + ip link del dev br2 + vlan_destroy $swp1 200 + + __addr_add_del br1 del 192.0.2.2/28 2001:db8:1::2/64 + ip link set dev $swp1.100 nomaster + ip link del dev br1 + vlan_destroy $swp1 100 + + ip link set dev $swp1 down +} + +config_remaster() +{ + log_info "Remaster bridge slaves" + + ip link set dev $swp1.100 nomaster + ip link set dev $swp1.200 nomaster + sleep 2 + ip link set dev $swp1.200 master br2 + ip link set dev $swp1.100 master br1 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + vrf_prepare + + h1_create + h2_create + + router_create + + forwarding_enable +} + +cleanup() +{ + pre_cleanup + + forwarding_restore + + router_destroy + + h2_destroy + h1_destroy + + vrf_cleanup +} + +ping_ipv4() +{ + ping_test $h1 192.0.2.130 ": via 100" + ping_test $h1 192.0.2.146 ": via 200" +} + +ping_ipv6() +{ + ping6_test $h1 2001:db8:2::2 ": via 100" + ping6_test $h1 2001:db8:4::2 ": via 200" +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/router_bridge_1d_lag.sh b/tools/testing/selftests/net/forwarding/router_bridge_1d_lag.sh new file mode 100755 index 000000000000..e064b946e821 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/router_bridge_1d_lag.sh @@ -0,0 +1,408 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# +--------------------------------------------+ +# | H1 (vrf) | +# | | +# | + LAG1.100 + LAG1.200 | +# | | 192.0.2.1/28 | 192.0.2.17/28 | +# | | 2001:db8:1::1/64 | 2001:db8:3:1/64 | +# | \___________ _______/ | +# | v | +# | + LAG1 (team) | +# | | | +# | ____^____ | +# | / \ | +# | + $h1 + $h4 | +# | | | | +# +----------|-----------|---------------------+ +# | | +# +----------|-----------|---------------------+ +# | SW | | | +# | + $swp1 + $swp4 | +# | \____ ____/ | +# | v | +# | LAG2 (team) + | +# | | | +# | _______^______________ | +# | / \ | +# | +------|------------+ +-------|----------+ | +# | | + LAG2.100 | | + LAG2.200 | | +# | | | | | | +# | | BR1 (802.1d) | | BR2 (802.1d) | | +# | | 192.0.2.2/28 | | 192.0.2.18/28 | | +# | | 2001:db8:1::2/64 | | 2001:db8:3:2/64 | | +# | | | | | | +# | +-------------------+ +------------------+ | +# | | +# | + LAG3.100 + LAG3.200 | +# | | 192.0.2.129/28 | 192.0.2.145/28 | +# | | 2001:db8:2::1/64 | 2001:db8:4::1/64 | +# | | | | +# | \_________ ___________/ | +# | v | +# | + LAG3 (team) | +# | ____|____ | +# | / \ | +# | + $swp2 + $swp3 | +# | | | | +# +-------|---------|--------------------------+ +# | | +# +-------|---------|--------------------------+ +# | | | | +# | + $h2 + $h3 | +# | \____ ___/ | +# | | | +# | + LAG4 (team) | +# | | | +# | __________^__________ | +# | / \ | +# | | | | +# | + LAG4.100 + LAG4.200 | +# | 192.0.2.130/28 192.0.2.146/28 | +# | 2001:db8:2::2/64 2001:db8:4::2/64 | +# | | +# | H2 (vrf) | +# +--------------------------------------------+ + +ALL_TESTS=" + ping_ipv4 + ping_ipv6 + + $(: exercise remastering of LAG2 slaves ) + config_deslave_swp4 + config_wait + ping_ipv4 + ping_ipv6 + config_enslave_swp4 + config_deslave_swp1 + config_wait + ping_ipv4 + ping_ipv6 + config_deslave_swp4 + config_enslave_swp1 + config_enslave_swp4 + config_wait + ping_ipv4 + ping_ipv6 + + $(: exercise remastering of LAG2 itself ) + config_remaster_lag2 + config_wait + ping_ipv4 + ping_ipv6 + + $(: exercise remastering of LAG3 slaves ) + config_deslave_swp2 + config_wait + ping_ipv4 + ping_ipv6 + config_enslave_swp2 + config_deslave_swp3 + config_wait + ping_ipv4 + ping_ipv6 + config_deslave_swp2 + config_enslave_swp3 + config_enslave_swp2 + config_wait + ping_ipv4 + ping_ipv6 +" +NUM_NETIFS=8 +source lib.sh + +h1_create() +{ + team_create lag1 lacp + ip link set dev lag1 addrgenmode none + ip link set dev lag1 address $(mac_get $h1) + ip link set dev $h1 master lag1 + ip link set dev $h4 master lag1 + simple_if_init lag1 + ip link set dev $h1 up + ip link set dev $h4 up + + vlan_create lag1 100 vlag1 192.0.2.1/28 2001:db8:1::1/64 + vlan_create lag1 200 vlag1 192.0.2.17/28 2001:db8:3::1/64 + + ip -4 route add 192.0.2.128/28 vrf vlag1 nexthop via 192.0.2.2 + ip -6 route add 2001:db8:2::/64 vrf vlag1 nexthop via 2001:db8:1::2 + + ip -4 route add 192.0.2.144/28 vrf vlag1 nexthop via 192.0.2.18 + ip -6 route add 2001:db8:4::/64 vrf vlag1 nexthop via 2001:db8:3::2 +} + +h1_destroy() +{ + ip -6 route del 2001:db8:4::/64 vrf vlag1 + ip -4 route del 192.0.2.144/28 vrf vlag1 + + ip -6 route del 2001:db8:2::/64 vrf vlag1 + ip -4 route del 192.0.2.128/28 vrf vlag1 + + vlan_destroy lag1 200 + vlan_destroy lag1 100 + + ip link set dev $h4 down + ip link set dev $h1 down + simple_if_fini lag1 + ip link set dev $h4 nomaster + ip link set dev $h1 nomaster + team_destroy lag1 +} + +h2_create() +{ + team_create lag4 lacp + ip link set dev lag4 addrgenmode none + ip link set dev lag4 address $(mac_get $h2) + ip link set dev $h2 master lag4 + ip link set dev $h3 master lag4 + simple_if_init lag4 + ip link set dev $h2 up + ip link set dev $h3 up + + vlan_create lag4 100 vlag4 192.0.2.130/28 2001:db8:2::2/64 + vlan_create lag4 200 vlag4 192.0.2.146/28 2001:db8:4::2/64 + + ip -4 route add 192.0.2.0/28 vrf vlag4 nexthop via 192.0.2.129 + ip -6 route add 2001:db8:1::/64 vrf vlag4 nexthop via 2001:db8:2::1 + + ip -4 route add 192.0.2.16/28 vrf vlag4 nexthop via 192.0.2.145 + ip -6 route add 2001:db8:3::/64 vrf vlag4 nexthop via 2001:db8:4::1 +} + +h2_destroy() +{ + ip -6 route del 2001:db8:3::/64 vrf vlag4 + ip -4 route del 192.0.2.16/28 vrf vlag4 + + ip -6 route del 2001:db8:1::/64 vrf vlag4 + ip -4 route del 192.0.2.0/28 vrf vlag4 + + vlan_destroy lag4 200 + vlan_destroy lag4 100 + + ip link set dev $h3 down + ip link set dev $h2 down + simple_if_fini lag4 + ip link set dev $h3 nomaster + ip link set dev $h2 nomaster + team_destroy lag4 +} + +router_create() +{ + team_create lag2 lacp + ip link set dev lag2 addrgenmode none + ip link set dev lag2 address $(mac_get $swp1) + ip link set dev $swp1 master lag2 + ip link set dev $swp4 master lag2 + + vlan_create lag2 100 + vlan_create lag2 200 + + ip link add name br1 type bridge vlan_filtering 0 + ip link set dev br1 address $(mac_get lag2.100) + ip link set dev lag2.100 master br1 + + ip link add name br2 type bridge vlan_filtering 0 + ip link set dev br2 address $(mac_get lag2.200) + ip link set dev lag2.200 master br2 + + ip link set dev $swp1 up + ip link set dev $swp4 up + ip link set dev br1 up + ip link set dev br2 up + + __addr_add_del br1 add 192.0.2.2/28 2001:db8:1::2/64 + __addr_add_del br2 add 192.0.2.18/28 2001:db8:3::2/64 + + team_create lag3 lacp + ip link set dev lag3 addrgenmode none + ip link set dev lag3 address $(mac_get $swp2) + ip link set dev $swp2 master lag3 + ip link set dev $swp3 master lag3 + ip link set dev $swp2 up + ip link set dev $swp3 up + + vlan_create lag3 100 + vlan_create lag3 200 + + __addr_add_del lag3.100 add 192.0.2.129/28 2001:db8:2::1/64 + __addr_add_del lag3.200 add 192.0.2.145/28 2001:db8:4::1/64 +} + +router_destroy() +{ + __addr_add_del lag3.200 del 192.0.2.145/28 2001:db8:4::1/64 + __addr_add_del lag3.100 del 192.0.2.129/28 2001:db8:2::1/64 + + vlan_destroy lag3 200 + vlan_destroy lag3 100 + + ip link set dev $swp3 down + ip link set dev $swp2 down + ip link set dev $swp3 nomaster + ip link set dev $swp2 nomaster + team_destroy lag3 + + __addr_add_del br2 del 192.0.2.18/28 2001:db8:3::2/64 + __addr_add_del br1 del 192.0.2.2/28 2001:db8:1::2/64 + + ip link set dev br2 down + ip link set dev br1 down + ip link set dev $swp4 down + ip link set dev $swp1 down + + ip link set dev lag2.200 nomaster + ip link del dev br2 + + ip link set dev lag2.100 nomaster + ip link del dev br1 + + vlan_destroy lag2 200 + vlan_destroy lag2 100 + + ip link set dev $swp4 nomaster + ip link set dev $swp1 nomaster + team_destroy lag2 +} + +config_remaster_lag2() +{ + log_info "Remaster bridge slaves" + + ip link set dev lag2.200 nomaster + ip link set dev lag2.100 nomaster + sleep 2 + ip link set dev lag2.100 master br1 + ip link set dev lag2.200 master br2 +} + +config_deslave() +{ + local netdev=$1; shift + + log_info "Deslave $netdev" + ip link set dev $netdev down + ip link set dev $netdev nomaster + ip link set dev $netdev up +} + +config_deslave_swp1() +{ + config_deslave $swp1 +} + +config_deslave_swp2() +{ + config_deslave $swp2 +} + +config_deslave_swp3() +{ + config_deslave $swp3 +} + +config_deslave_swp4() +{ + config_deslave $swp4 +} + +config_enslave() +{ + local netdev=$1; shift + local master=$1; shift + + log_info "Enslave $netdev to $master" + ip link set dev $netdev down + ip link set dev $netdev master $master + ip link set dev $netdev up +} + +config_enslave_swp1() +{ + config_enslave $swp1 lag2 +} + +config_enslave_swp2() +{ + config_enslave $swp2 lag3 +} + +config_enslave_swp3() +{ + config_enslave $swp3 lag3 +} + +config_enslave_swp4() +{ + config_enslave $swp4 lag2 +} + +config_wait() +{ + setup_wait_dev lag2 + setup_wait_dev lag3 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + h4=${NETIFS[p7]} + swp4=${NETIFS[p8]} + + vrf_prepare + + h1_create + h2_create + + router_create + + forwarding_enable +} + +cleanup() +{ + pre_cleanup + + forwarding_restore + + router_destroy + + h2_destroy + h1_destroy + + vrf_cleanup +} + +ping_ipv4() +{ + ping_test lag1.100 192.0.2.130 ": via 100" + ping_test lag1.200 192.0.2.146 ": via 200" +} + +ping_ipv6() +{ + ping6_test lag1.100 2001:db8:2::2 ": via 100" + ping6_test lag1.200 2001:db8:4::2 ": via 200" +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/router_bridge_lag.sh b/tools/testing/selftests/net/forwarding/router_bridge_lag.sh new file mode 100755 index 000000000000..f05ffe213c46 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/router_bridge_lag.sh @@ -0,0 +1,323 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# +----------------------------+ +--------------------------+ +# | H1 (vrf) | | H2 (vrf) | +# | | | | +# | + LAG1 (team) | | + LAG4 (team) | +# | | 192.0.2.1/28 | | | 192.0.2.130/28 | +# | | 2001:db8:1::1/64 | | | 2001:db8:2::2/64 | +# | __^___ | | __^_____ | +# | / \ | | / \ | +# | + $h1 + $h4 | | + $h2 + $h3 | +# | | | | | | | | +# +----|--------|--------------+ +-|----------|-------------+ +# | | | | +# +----|--------|------------------------------------|----------|-------------+ +# | SW | | | | | +# | + $swp1 + $swp4 + $swp2 + $swp3 | +# | \__ ___/ \__ _____/ | +# | v v | +# | +------|-------------------------------+ | | +# | | + LAG2 BR1 (802.1q) | + LAG3 (team) | +# | | (team) 192.0.2.2/28 | 192.0.2.129/28 | +# | | 2001:db8:1::2/64 | 2001:db8:2::1/64 | +# | | | | +# | +--------------------------------------+ | +# +---------------------------------------------------------------------------+ + +: ${ALL_TESTS:=" + ping_ipv4 + ping_ipv6 + + $(: exercise remastering of LAG2 slaves ) + config_deslave_swp4 + config_wait + ping_ipv4 + ping_ipv6 + config_enslave_swp4 + config_deslave_swp1 + config_wait + ping_ipv4 + ping_ipv6 + config_deslave_swp4 + config_enslave_swp1 + config_enslave_swp4 + config_wait + ping_ipv4 + ping_ipv6 + + $(: exercise remastering of LAG2 itself ) + config_remaster_lag2 + config_wait + ping_ipv4 + ping_ipv6 + + $(: exercise remastering of LAG3 slaves ) + config_deslave_swp2 + config_wait + ping_ipv4 + ping_ipv6 + config_enslave_swp2 + config_deslave_swp3 + config_wait + ping_ipv4 + ping_ipv6 + config_deslave_swp2 + config_enslave_swp3 + config_enslave_swp2 + config_wait + ping_ipv4 + ping_ipv6 + + $(: move LAG3 to a bridge and then out ) + config_remaster_lag3 + config_wait + ping_ipv4 + ping_ipv6 + "} +NUM_NETIFS=8 +: ${lib_dir:=.} +source $lib_dir/lib.sh +$EXTRA_SOURCE + +h1_create() +{ + team_create lag1 lacp + ip link set dev lag1 address $(mac_get $h1) + ip link set dev $h1 master lag1 + ip link set dev $h4 master lag1 + simple_if_init lag1 192.0.2.1/28 2001:db8:1::1/64 + ip link set dev $h1 up + ip link set dev $h4 up + ip -4 route add 192.0.2.128/28 vrf vlag1 nexthop via 192.0.2.2 + ip -6 route add 2001:db8:2::/64 vrf vlag1 nexthop via 2001:db8:1::2 +} + +h1_destroy() +{ + ip -6 route del 2001:db8:2::/64 vrf vlag1 + ip -4 route del 192.0.2.128/28 vrf vlag1 + ip link set dev $h4 down + ip link set dev $h1 down + simple_if_fini lag1 192.0.2.1/28 2001:db8:1::1/64 + ip link set dev $h4 nomaster + ip link set dev $h1 nomaster + team_destroy lag1 +} + +h2_create() +{ + team_create lag4 lacp + ip link set dev lag4 address $(mac_get $h2) + ip link set dev $h2 master lag4 + ip link set dev $h3 master lag4 + simple_if_init lag4 192.0.2.130/28 2001:db8:2::2/64 + ip link set dev $h2 up + ip link set dev $h3 up + ip -4 route add 192.0.2.0/28 vrf vlag4 nexthop via 192.0.2.129 + ip -6 route add 2001:db8:1::/64 vrf vlag4 nexthop via 2001:db8:2::1 +} + +h2_destroy() +{ + ip -6 route del 2001:db8:1::/64 vrf vlag4 + ip -4 route del 192.0.2.0/28 vrf vlag4 + ip link set dev $h3 down + ip link set dev $h2 down + simple_if_fini lag4 192.0.2.130/28 2001:db8:2::2/64 + ip link set dev $h3 nomaster + ip link set dev $h2 nomaster + team_destroy lag4 +} + +router_create() +{ + team_create lag2 lacp + ip link set dev lag2 address $(mac_get $swp1) + ip link set dev $swp1 master lag2 + ip link set dev $swp4 master lag2 + + ip link add name br1 address $(mac_get lag2) \ + type bridge vlan_filtering 1 + ip link set dev lag2 master br1 + + ip link set dev $swp1 up + ip link set dev $swp4 up + ip link set dev br1 up + + __addr_add_del br1 add 192.0.2.2/28 2001:db8:1::2/64 + + team_create lag3 lacp + ip link set dev lag3 address $(mac_get $swp2) + ip link set dev $swp2 master lag3 + ip link set dev $swp3 master lag3 + ip link set dev $swp2 up + ip link set dev $swp3 up + __addr_add_del lag3 add 192.0.2.129/28 2001:db8:2::1/64 +} + +router_destroy() +{ + __addr_add_del lag3 del 192.0.2.129/28 2001:db8:2::1/64 + ip link set dev $swp3 down + ip link set dev $swp2 down + ip link set dev $swp3 nomaster + ip link set dev $swp2 nomaster + team_destroy lag3 + + __addr_add_del br1 del 192.0.2.2/28 2001:db8:1::2/64 + + ip link set dev $swp4 down + ip link set dev $swp1 down + ip link set dev br1 down + + ip link set dev lag2 nomaster + ip link del dev br1 + + ip link set dev $swp4 nomaster + ip link set dev $swp1 nomaster + team_destroy lag2 +} + +config_remaster_lag2() +{ + log_info "Remaster bridge slave" + + ip link set dev lag2 nomaster + sleep 2 + ip link set dev lag2 master br1 +} + +config_remaster_lag3() +{ + log_info "Move lag3 to the bridge, then out again" + + ip link set dev lag3 master br1 + sleep 2 + ip link set dev lag3 nomaster +} + +config_deslave() +{ + local netdev=$1; shift + + log_info "Deslave $netdev" + ip link set dev $netdev down + ip link set dev $netdev nomaster + ip link set dev $netdev up +} + +config_deslave_swp1() +{ + config_deslave $swp1 +} + +config_deslave_swp2() +{ + config_deslave $swp2 +} + +config_deslave_swp3() +{ + config_deslave $swp3 +} + +config_deslave_swp4() +{ + config_deslave $swp4 +} + +config_enslave() +{ + local netdev=$1; shift + local master=$1; shift + + log_info "Enslave $netdev to $master" + ip link set dev $netdev down + ip link set dev $netdev master $master + ip link set dev $netdev up +} + +config_enslave_swp1() +{ + config_enslave $swp1 lag2 +} + +config_enslave_swp2() +{ + config_enslave $swp2 lag3 +} + +config_enslave_swp3() +{ + config_enslave $swp3 lag3 +} + +config_enslave_swp4() +{ + config_enslave $swp4 lag2 +} + +config_wait() +{ + setup_wait_dev lag2 + setup_wait_dev lag3 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + h4=${NETIFS[p7]} + swp4=${NETIFS[p8]} + + vrf_prepare + + h1_create + h2_create + + router_create + + forwarding_enable +} + +cleanup() +{ + pre_cleanup + + forwarding_restore + + router_destroy + + h2_destroy + h1_destroy + + vrf_cleanup +} + +ping_ipv4() +{ + ping_test lag1 192.0.2.130 +} + +ping_ipv6() +{ + ping6_test lag1 2001:db8:2::2 +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/router_bridge_pvid_vlan_upper.sh b/tools/testing/selftests/net/forwarding/router_bridge_pvid_vlan_upper.sh new file mode 100755 index 000000000000..76e4941fef73 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/router_bridge_pvid_vlan_upper.sh @@ -0,0 +1,155 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# +----------------------------+ +# | H1 (vrf) | +# | + $h1.10 | +----------------------+ +# | | 192.0.2.1/28 | | H2 (vrf) | +# | | 2001:db8:1::1/64 | | + $h2 | +# | | | | | 192.0.2.130/28 | +# | + $h1 | | | 2001:db8:2::2/64 | +# +---|------------------------+ +--|-------------------+ +# | | +# +---|--------------------------------------------------|-------------------+ +# | | router (main VRF) | | +# | +-|----------------------------------+ + $swp2 | +# | | + $swp1 BR1 (802.1q, pvid=10) | 192.0.2.129/28 | +# | | 192.0.2.2/28 | 2001:db8:2::1/64 | +# | | 2001:db8:1::2/64 | | +# | +------------------------------------+ | +# +--------------------------------------------------------------------------+ + +ALL_TESTS=" + ping_ipv4 + ping_ipv6 + shuffle_pvid + ping_ipv4 + ping_ipv6 +" +NUM_NETIFS=4 +source lib.sh + +h1_create() +{ + simple_if_init $h1 + vlan_create $h1 10 v$h1 192.0.2.1/28 2001:db8:1::1/64 + ip -4 route add 192.0.2.128/28 vrf v$h1 nexthop via 192.0.2.2 + ip -6 route add 2001:db8:2::/64 vrf v$h1 nexthop via 2001:db8:1::2 +} + +h1_destroy() +{ + ip -6 route del 2001:db8:2::/64 vrf v$h1 + ip -4 route del 192.0.2.128/28 vrf v$h1 + vlan_destroy $h1 10 + simple_if_fini $h1 +} + +h2_create() +{ + simple_if_init $h2 192.0.2.130/28 2001:db8:2::2/64 + ip -4 route add 192.0.2.0/28 vrf v$h2 nexthop via 192.0.2.129 + ip -6 route add 2001:db8:1::/64 vrf v$h2 nexthop via 2001:db8:2::1 +} + +h2_destroy() +{ + ip -6 route del 2001:db8:1::/64 vrf v$h2 + ip -4 route del 192.0.2.0/28 vrf v$h2 + simple_if_fini $h2 192.0.2.130/28 2001:db8:2::2/64 +} + +router_create() +{ + ip link add name br1 address $(mac_get $swp1) \ + type bridge vlan_filtering 1 vlan_default_pvid 0 + ip link set dev br1 up + __addr_add_del br1 add 192.0.2.2/28 2001:db8:1::2/64 + + ip link set dev $swp1 master br1 + ip link set dev $swp1 up + + ip link set dev $swp2 up + __addr_add_del $swp2 add 192.0.2.129/28 2001:db8:2::1/64 + + bridge vlan add dev br1 vid 10 pvid untagged self + bridge vlan add dev $swp1 vid 10 +} + +router_destroy() +{ + bridge vlan del dev $swp1 vid 10 + bridge vlan del dev br1 vid 10 self + + __addr_add_del $swp2 del 192.0.2.129/28 2001:db8:2::1/64 + ip link set dev $swp2 down + + ip link set dev $swp1 down + ip link set dev $swp1 nomaster + + __addr_add_del br1 del 192.0.2.2/28 2001:db8:1::2/64 + ip link del dev br1 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + vrf_prepare + + h1_create + h2_create + + router_create + + forwarding_enable +} + +shuffle_pvid() +{ + log_info "Add and remove VLAN upper for PVID VLAN" + + # Adding and removing a VLAN upper for the PVID VLAN shouldn't change + # anything. The address is arbitrary, just to make sure it will be an L3 + # netdevice. + vlan_create br1 10 "" 192.0.2.33/28 + sleep 1 + vlan_destroy br1 10 +} + +cleanup() +{ + pre_cleanup + + forwarding_restore + + router_destroy + + h2_destroy + h1_destroy + + vrf_cleanup +} + +ping_ipv4() +{ + ping_test $h1 192.0.2.130 +} + +ping_ipv6() +{ + ping6_test $h1 2001:db8:2::2 +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh b/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh index de2b2d5480dd..b76a4a707a5b 100755 --- a/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh +++ b/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh @@ -1,25 +1,28 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 -# +------------------------+ +----------------------+ -# | H1 (vrf) | | H2 (vrf) | -# | + $h1.555 | | + $h2 | -# | | 192.0.2.1/28 | | | 192.0.2.130/28 | -# | | 2001:db8:1::1/64 | | | 2001:db8:2::2/64 | -# | | | | | | -# | + $h1 | | | | -# +----|-------------------+ +--|-------------------+ +# +------------------------------------------------+ +----------------------+ +# | H1 (vrf) | | H2 (vrf) | +# | + $h1.555 + $h1.777 | | + $h2 | +# | | 192.0.2.1/28 | 192.0.2.17/28 | | | 192.0.2.130/28 | +# | | 2001:db8:1::1/64 | 2001:db8:3::1/64 | | | 192.0.2.146/28 | +# | | .-----------------' | | | 2001:db8:2::2/64 | +# | |/ | | | 2001:db8:4::2/64 | +# | + $h1 | | | | +# +----|-------------------------------------------+ +--|-------------------+ # | | # +----|--------------------------------------------------|-------------------+ # | SW | | | # | +--|-------------------------------+ + $swp2 | # | | + $swp1 | 192.0.2.129/28 | -# | | vid 555 | 2001:db8:2::1/64 | -# | | | | -# | | + BR1 (802.1q) | | +# | | vid 555 777 | 192.0.2.145/28 | +# | | | 2001:db8:2::1/64 | +# | | + BR1 (802.1q) | 2001:db8:4::1/64 | # | | vid 555 pvid untagged | | # | | 192.0.2.2/28 | | +# | | 192.0.2.18/28 | | # | | 2001:db8:1::2/64 | | +# | | 2001:db8:3::2/64 | | # | +----------------------------------+ | # +---------------------------------------------------------------------------+ @@ -27,6 +30,14 @@ ALL_TESTS=" ping_ipv4 ping_ipv6 vlan + config_777 + ping_ipv4_fails + ping_ipv6_fails + ping_ipv4_777 + ping_ipv6_777 + config_555 + ping_ipv4 + ping_ipv6 " NUM_NETIFS=4 source lib.sh @@ -34,31 +45,47 @@ source lib.sh h1_create() { simple_if_init $h1 + vlan_create $h1 555 v$h1 192.0.2.1/28 2001:db8:1::1/64 ip -4 route add 192.0.2.128/28 vrf v$h1 nexthop via 192.0.2.2 ip -6 route add 2001:db8:2::/64 vrf v$h1 nexthop via 2001:db8:1::2 + + vlan_create $h1 777 v$h1 192.0.2.17/28 2001:db8:3::1/64 + ip -4 route add 192.0.2.144/28 vrf v$h1 nexthop via 192.0.2.18 + ip -6 route add 2001:db8:4::/64 vrf v$h1 nexthop via 2001:db8:3::2 } h1_destroy() { + ip -6 route del 2001:db8:4::/64 vrf v$h1 + ip -4 route del 192.0.2.144/28 vrf v$h1 + vlan_destroy $h1 777 + ip -6 route del 2001:db8:2::/64 vrf v$h1 ip -4 route del 192.0.2.128/28 vrf v$h1 vlan_destroy $h1 555 + simple_if_fini $h1 } h2_create() { - simple_if_init $h2 192.0.2.130/28 2001:db8:2::2/64 + simple_if_init $h2 192.0.2.130/28 2001:db8:2::2/64 \ + 192.0.2.146/28 2001:db8:4::2/64 ip -4 route add 192.0.2.0/28 vrf v$h2 nexthop via 192.0.2.129 + ip -4 route add 192.0.2.16/28 vrf v$h2 nexthop via 192.0.2.145 ip -6 route add 2001:db8:1::/64 vrf v$h2 nexthop via 2001:db8:2::1 + ip -6 route add 2001:db8:3::/64 vrf v$h2 nexthop via 2001:db8:4::1 } h2_destroy() { + ip -6 route del 2001:db8:3::/64 vrf v$h2 ip -6 route del 2001:db8:1::/64 vrf v$h2 + ip -4 route del 192.0.2.16/28 vrf v$h2 ip -4 route del 192.0.2.0/28 vrf v$h2 - simple_if_fini $h2 192.0.2.130/28 2001:db8:2::2/64 + simple_if_fini $h2 192.0.2.146/28 2001:db8:4::2/64 \ + 192.0.2.130/28 2001:db8:2::2/64 } router_create() @@ -71,18 +98,23 @@ router_create() bridge vlan add dev br1 vid 555 self pvid untagged bridge vlan add dev $swp1 vid 555 + bridge vlan add dev $swp1 vid 777 __addr_add_del br1 add 192.0.2.2/28 2001:db8:1::2/64 + __addr_add_del br1 add 192.0.2.18/28 2001:db8:3::2/64 ip link set dev $swp2 up __addr_add_del $swp2 add 192.0.2.129/28 2001:db8:2::1/64 + __addr_add_del $swp2 add 192.0.2.145/28 2001:db8:4::1/64 } router_destroy() { + __addr_add_del $swp2 del 192.0.2.145/28 2001:db8:4::1/64 __addr_add_del $swp2 del 192.0.2.129/28 2001:db8:2::1/64 ip link set dev $swp2 down + __addr_add_del br1 del 192.0.2.18/28 2001:db8:3::2/64 __addr_add_del br1 del 192.0.2.2/28 2001:db8:1::2/64 ip link set dev $swp1 down ip link set dev $swp1 nomaster @@ -108,6 +140,24 @@ setup_prepare() forwarding_enable } +config_555() +{ + log_info "Configure VLAN 555 as PVID" + + bridge vlan add dev br1 vid 555 self pvid untagged + bridge vlan del dev br1 vid 777 self + sleep 2 +} + +config_777() +{ + log_info "Configure VLAN 777 as PVID" + + bridge vlan add dev br1 vid 777 self pvid untagged + bridge vlan del dev br1 vid 555 self + sleep 2 +} + cleanup() { pre_cleanup @@ -136,12 +186,32 @@ vlan() ping_ipv4() { - ping_test $h1 192.0.2.130 + ping_test $h1.555 192.0.2.130 } ping_ipv6() { - ping6_test $h1 2001:db8:2::2 + ping6_test $h1.555 2001:db8:2::2 +} + +ping_ipv4_fails() +{ + ping_test_fails $h1.555 192.0.2.130 ": via 555" +} + +ping_ipv6_fails() +{ + ping6_test_fails $h1.555 2001:db8:2::2 ": via 555" +} + +ping_ipv4_777() +{ + ping_test $h1.777 192.0.2.146 ": via 777" +} + +ping_ipv6_777() +{ + ping6_test $h1.777 2001:db8:4::2 ": via 777" } trap cleanup EXIT diff --git a/tools/testing/selftests/net/forwarding/router_bridge_vlan_upper.sh b/tools/testing/selftests/net/forwarding/router_bridge_vlan_upper.sh new file mode 100755 index 000000000000..215309ea1c8c --- /dev/null +++ b/tools/testing/selftests/net/forwarding/router_bridge_vlan_upper.sh @@ -0,0 +1,169 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# +------------------------+ +----------------------+ +# | H1 (vrf) | | H2 (vrf) | +# | + $h1.555 | | + $h2.777 | +# | | 192.0.2.1/28 | | | 192.0.2.18/28 | +# | | 2001:db8:1::1/64 | | | 2001:db8:2::2/64 | +# | | | | | | +# | + $h1 | | + $h2 | +# +----|-------------------+ +--|-------------------+ +# | | +# +----|--------------------------------------------------|-------------------+ +# | SW | | | +# | +--|--------------------------------------------------|-----------------+ | +# | | + $swp1 BR1 (802.1q) + $swp2 | | +# | | | | +# | +------+------------------------------------------+---------------------+ | +# | | | | +# | + br1.555 + br1.777 | +# | 192.0.2.2/28 192.0.2.17/28 | +# | 2001:db8:1::2/64 2001:db8:2::1/64 | +# +---------------------------------------------------------------------------+ + +ALL_TESTS=" + ping_ipv4 + ping_ipv6 + respin_config + ping_ipv4 + ping_ipv6 +" +NUM_NETIFS=4 +source lib.sh + +h1_create() +{ + simple_if_init $h1 + vlan_create $h1 555 v$h1 192.0.2.1/28 2001:db8:1::1/64 + ip -4 route add 192.0.2.16/28 vrf v$h1 nexthop via 192.0.2.2 + ip -6 route add 2001:db8:2::/64 vrf v$h1 nexthop via 2001:db8:1::2 +} + +h1_destroy() +{ + ip -6 route del 2001:db8:2::/64 vrf v$h1 + ip -4 route del 192.0.2.16/28 vrf v$h1 + vlan_destroy $h1 555 + simple_if_fini $h1 +} + +h2_create() +{ + simple_if_init $h2 + vlan_create $h2 777 v$h2 192.0.2.18/28 2001:db8:2::2/64 + ip -4 route add 192.0.2.0/28 vrf v$h2 nexthop via 192.0.2.17 + ip -6 route add 2001:db8:1::/64 vrf v$h2 nexthop via 2001:db8:2::1 +} + +h2_destroy() +{ + ip -6 route del 2001:db8:1::/64 vrf v$h2 + ip -4 route del 192.0.2.0/28 vrf v$h2 + vlan_destroy $h2 777 + simple_if_fini $h2 +} + +router_create() +{ + ip link add name br1 address $(mac_get $swp1) \ + type bridge vlan_filtering 1 + ip link set dev br1 up + + ip link set dev $swp1 master br1 + ip link set dev $swp2 master br1 + ip link set dev $swp1 up + ip link set dev $swp2 up + + bridge vlan add dev br1 vid 555 self + bridge vlan add dev br1 vid 777 self + bridge vlan add dev $swp1 vid 555 + bridge vlan add dev $swp2 vid 777 + + vlan_create br1 555 "" 192.0.2.2/28 2001:db8:1::2/64 + vlan_create br1 777 "" 192.0.2.17/28 2001:db8:2::1/64 +} + +router_destroy() +{ + vlan_destroy br1 777 + vlan_destroy br1 555 + + bridge vlan del dev $swp2 vid 777 + bridge vlan del dev $swp1 vid 555 + bridge vlan del dev br1 vid 777 self + bridge vlan del dev br1 vid 555 self + + ip link set dev $swp2 down nomaster + ip link set dev $swp1 down nomaster + + ip link set dev br1 down + ip link del dev br1 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + vrf_prepare + + h1_create + h2_create + + router_create + + forwarding_enable +} + +cleanup() +{ + pre_cleanup + + forwarding_restore + + router_destroy + + h2_destroy + h1_destroy + + vrf_cleanup +} + +ping_ipv4() +{ + ping_test $h1 192.0.2.18 +} + +ping_ipv6() +{ + ping6_test $h1 2001:db8:2::2 +} + +respin_config() +{ + log_info "Remaster bridge slave" + + ip link set dev $swp2 nomaster + ip link set dev $swp1 nomaster + + sleep 2 + + ip link set dev $swp1 master br1 + ip link set dev $swp2 master br1 + + bridge vlan add dev $swp1 vid 555 + bridge vlan add dev $swp2 vid 777 +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/router_bridge_vlan_upper_pvid.sh b/tools/testing/selftests/net/forwarding/router_bridge_vlan_upper_pvid.sh new file mode 100755 index 000000000000..138558452402 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/router_bridge_vlan_upper_pvid.sh @@ -0,0 +1,171 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# +----------------------------+ +# | H1 (vrf) | +# | + $h1.10 | +----------------------+ +# | | 192.0.2.1/28 | | H2 (vrf) | +# | | 2001:db8:1::1/64 | | + $h2 | +# | | | | | 192.0.2.130/28 | +# | + $h1 | | | 2001:db8:2::2/64 | +# +---|------------------------+ +--|-------------------+ +# | | +# +---|--------------------------------------------------|-------------------+ +# | | router (main VRF) | | +# | +-|--------------------------+ + $swp2 | +# | | + $swp1 BR1 (802.1q) | 192.0.2.129/28 | +# | +-----+----------------------+ 2001:db8:2::1/64 | +# | | | +# | + br1.10 | +# | 192.0.2.2/28 | +# | 2001:db8:1::2/64 | +# +--------------------------------------------------------------------------+ + +ALL_TESTS=" + ping_ipv4 + ping_ipv6 + pvid_set_unset + ping_ipv4 + ping_ipv6 + pvid_set_move + ping_ipv4 + ping_ipv6 +" +NUM_NETIFS=4 +source lib.sh + +h1_create() +{ + simple_if_init $h1 + vlan_create $h1 10 v$h1 192.0.2.1/28 2001:db8:1::1/64 + ip -4 route add 192.0.2.128/28 vrf v$h1 nexthop via 192.0.2.2 + ip -6 route add 2001:db8:2::/64 vrf v$h1 nexthop via 2001:db8:1::2 +} + +h1_destroy() +{ + ip -6 route del 2001:db8:2::/64 vrf v$h1 + ip -4 route del 192.0.2.128/28 vrf v$h1 + vlan_destroy $h1 10 + simple_if_fini $h1 +} + +h2_create() +{ + simple_if_init $h2 192.0.2.130/28 2001:db8:2::2/64 + ip -4 route add 192.0.2.0/28 vrf v$h2 nexthop via 192.0.2.129 + ip -6 route add 2001:db8:1::/64 vrf v$h2 nexthop via 2001:db8:2::1 +} + +h2_destroy() +{ + ip -6 route del 2001:db8:1::/64 vrf v$h2 + ip -4 route del 192.0.2.0/28 vrf v$h2 + simple_if_fini $h2 192.0.2.130/28 2001:db8:2::2/64 +} + +router_create() +{ + ip link add name br1 address $(mac_get $swp1) \ + type bridge vlan_filtering 1 vlan_default_pvid 0 + ip link set dev br1 up + + ip link set dev $swp1 master br1 + ip link set dev $swp1 up + + ip link set dev $swp2 up + __addr_add_del $swp2 add 192.0.2.129/28 2001:db8:2::1/64 + + bridge vlan add dev br1 vid 10 self + bridge vlan add dev $swp1 vid 10 + vlan_create br1 10 "" 192.0.2.2/28 2001:db8:1::2/64 +} + +router_destroy() +{ + vlan_destroy br1 10 + bridge vlan del dev $swp1 vid 10 + bridge vlan del dev br1 vid 10 self + + __addr_add_del $swp2 del 192.0.2.129/28 2001:db8:2::1/64 + ip link set dev $swp2 down + + ip link set dev $swp1 down + ip link set dev $swp1 nomaster + + ip link del dev br1 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + vrf_prepare + + h1_create + h2_create + + router_create + + forwarding_enable +} + +pvid_set_unset() +{ + log_info "Set and unset PVID on VLAN 10" + + bridge vlan add dev br1 vid 10 pvid self + sleep 1 + bridge vlan add dev br1 vid 10 self +} + +pvid_set_move() +{ + log_info "Set PVID on VLAN 10, then move it to VLAN 20" + + bridge vlan add dev br1 vid 10 pvid self + sleep 1 + bridge vlan add dev br1 vid 20 pvid self +} + +shuffle_vlan() +{ + log_info "" +} + +cleanup() +{ + pre_cleanup + + forwarding_restore + + router_destroy + + h2_destroy + h1_destroy + + vrf_cleanup +} + +ping_ipv4() +{ + ping_test $h1 192.0.2.130 +} + +ping_ipv6() +{ + ping6_test $h1 2001:db8:2::2 +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/tc_flower_port_range.sh b/tools/testing/selftests/net/forwarding/tc_flower_port_range.sh new file mode 100755 index 000000000000..3885a2a91f7d --- /dev/null +++ b/tools/testing/selftests/net/forwarding/tc_flower_port_range.sh @@ -0,0 +1,228 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# +-----------------------+ +----------------------+ +# | H1 (vrf) | | H2 (vrf) | +# | + $h1 | | $h2 + | +# | | 192.0.2.1/28 | | 192.0.2.2/28 | | +# | | 2001:db8:1::1/64 | | 2001:db8:1::2/64 | | +# +----|------------------+ +------------------|---+ +# | | +# +----|-------------------------------------------------------------------|---+ +# | SW | | | +# | +-|-------------------------------------------------------------------|-+ | +# | | + $swp1 BR $swp2 + | | +# | +-----------------------------------------------------------------------+ | +# +----------------------------------------------------------------------------+ + +ALL_TESTS=" + test_port_range_ipv4_udp + test_port_range_ipv4_tcp + test_port_range_ipv6_udp + test_port_range_ipv6_tcp +" + +NUM_NETIFS=4 +source lib.sh +source tc_common.sh + +h1_create() +{ + simple_if_init $h1 192.0.2.1/28 2001:db8:1::1/64 +} + +h1_destroy() +{ + simple_if_fini $h1 192.0.2.1/28 2001:db8:1::1/64 +} + +h2_create() +{ + simple_if_init $h2 192.0.2.2/28 2001:db8:1::2/64 +} + +h2_destroy() +{ + simple_if_fini $h2 192.0.2.2/28 2001:db8:1::2/64 +} + +switch_create() +{ + ip link add name br1 type bridge + ip link set dev $swp1 master br1 + ip link set dev $swp1 up + ip link set dev $swp2 master br1 + ip link set dev $swp2 up + ip link set dev br1 up + + tc qdisc add dev $swp1 clsact + tc qdisc add dev $swp2 clsact +} + +switch_destroy() +{ + tc qdisc del dev $swp2 clsact + tc qdisc del dev $swp1 clsact + + ip link set dev br1 down + ip link set dev $swp2 down + ip link set dev $swp2 nomaster + ip link set dev $swp1 down + ip link set dev $swp1 nomaster + ip link del dev br1 +} + +__test_port_range() +{ + local proto=$1; shift + local ip_proto=$1; shift + local sip=$1; shift + local dip=$1; shift + local mode=$1; shift + local name=$1; shift + local dmac=$(mac_get $h2) + local smac=$(mac_get $h1) + local sport_min=100 + local sport_max=200 + local sport_mid=$((sport_min + (sport_max - sport_min) / 2)) + local dport_min=300 + local dport_max=400 + local dport_mid=$((dport_min + (dport_max - dport_min) / 2)) + + RET=0 + + tc filter add dev $swp1 ingress protocol $proto handle 101 pref 1 \ + flower src_ip $sip dst_ip $dip ip_proto $ip_proto \ + src_port $sport_min-$sport_max \ + dst_port $dport_min-$dport_max \ + action pass + tc filter add dev $swp2 egress protocol $proto handle 101 pref 1 \ + flower src_ip $sip dst_ip $dip ip_proto $ip_proto \ + src_port $sport_min-$sport_max \ + dst_port $dport_min-$dport_max \ + action drop + + $MZ $mode $h1 -c 1 -q -p 100 -a $smac -b $dmac -A $sip -B $dip \ + -t $ip_proto "sp=$sport_min,dp=$dport_min" + tc_check_packets "dev $swp1 ingress" 101 1 + check_err $? "Ingress filter not hit with minimum ports" + tc_check_packets "dev $swp2 egress" 101 1 + check_err $? "Egress filter not hit with minimum ports" + + $MZ $mode $h1 -c 1 -q -p 100 -a $smac -b $dmac -A $sip -B $dip \ + -t $ip_proto "sp=$sport_mid,dp=$dport_mid" + tc_check_packets "dev $swp1 ingress" 101 2 + check_err $? "Ingress filter not hit with middle ports" + tc_check_packets "dev $swp2 egress" 101 2 + check_err $? "Egress filter not hit with middle ports" + + $MZ $mode $h1 -c 1 -q -p 100 -a $smac -b $dmac -A $sip -B $dip \ + -t $ip_proto "sp=$sport_max,dp=$dport_max" + tc_check_packets "dev $swp1 ingress" 101 3 + check_err $? "Ingress filter not hit with maximum ports" + tc_check_packets "dev $swp2 egress" 101 3 + check_err $? "Egress filter not hit with maximum ports" + + # Send traffic when both ports are out of range and when only one port + # is out of range. + $MZ $mode $h1 -c 1 -q -p 100 -a $smac -b $dmac -A $sip -B $dip \ + -t $ip_proto "sp=$((sport_min - 1)),dp=$dport_min" + $MZ $mode $h1 -c 1 -q -p 100 -a $smac -b $dmac -A $sip -B $dip \ + -t $ip_proto "sp=$((sport_max + 1)),dp=$dport_min" + $MZ $mode $h1 -c 1 -q -p 100 -a $smac -b $dmac -A $sip -B $dip \ + -t $ip_proto "sp=$sport_min,dp=$((dport_min - 1))" + $MZ $mode $h1 -c 1 -q -p 100 -a $smac -b $dmac -A $sip -B $dip \ + -t $ip_proto "sp=$sport_min,dp=$((dport_max + 1))" + $MZ $mode $h1 -c 1 -q -p 100 -a $smac -b $dmac -A $sip -B $dip \ + -t $ip_proto "sp=$((sport_max + 1)),dp=$((dport_max + 1))" + tc_check_packets "dev $swp1 ingress" 101 3 + check_err $? "Ingress filter was hit when should not" + tc_check_packets "dev $swp2 egress" 101 3 + check_err $? "Egress filter was hit when should not" + + tc filter del dev $swp2 egress protocol $proto pref 1 handle 101 flower + tc filter del dev $swp1 ingress protocol $proto pref 1 handle 101 flower + + log_test "Port range matching - $name" +} + +test_port_range_ipv4_udp() +{ + local proto=ipv4 + local ip_proto=udp + local sip=192.0.2.1 + local dip=192.0.2.2 + local mode="-4" + local name="IPv4 UDP" + + __test_port_range $proto $ip_proto $sip $dip $mode "$name" +} + +test_port_range_ipv4_tcp() +{ + local proto=ipv4 + local ip_proto=tcp + local sip=192.0.2.1 + local dip=192.0.2.2 + local mode="-4" + local name="IPv4 TCP" + + __test_port_range $proto $ip_proto $sip $dip $mode "$name" +} + +test_port_range_ipv6_udp() +{ + local proto=ipv6 + local ip_proto=udp + local sip=2001:db8:1::1 + local dip=2001:db8:1::2 + local mode="-6" + local name="IPv6 UDP" + + __test_port_range $proto $ip_proto $sip $dip $mode "$name" +} + +test_port_range_ipv6_tcp() +{ + local proto=ipv6 + local ip_proto=tcp + local sip=2001:db8:1::1 + local dip=2001:db8:1::2 + local mode="-6" + local name="IPv6 TCP" + + __test_port_range $proto $ip_proto $sip $dip $mode "$name" +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + vrf_prepare + h1_create + h2_create + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + h2_destroy + h1_destroy + vrf_cleanup +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/hwtstamp_config.c b/tools/testing/selftests/net/hwtstamp_config.c index e1fdee841021..170728c96c46 100644 --- a/tools/testing/selftests/net/hwtstamp_config.c +++ b/tools/testing/selftests/net/hwtstamp_config.c @@ -16,6 +16,8 @@ #include <linux/net_tstamp.h> #include <linux/sockios.h> +#include "kselftest.h" + static int lookup_value(const char **names, int size, const char *name) { @@ -50,7 +52,7 @@ static const char *tx_types[] = { TX_TYPE(ONESTEP_SYNC) #undef TX_TYPE }; -#define N_TX_TYPES ((int)(sizeof(tx_types) / sizeof(tx_types[0]))) +#define N_TX_TYPES ((int)(ARRAY_SIZE(tx_types))) static const char *rx_filters[] = { #define RX_FILTER(name) [HWTSTAMP_FILTER_ ## name] = #name @@ -71,7 +73,7 @@ static const char *rx_filters[] = { RX_FILTER(PTP_V2_DELAY_REQ), #undef RX_FILTER }; -#define N_RX_FILTERS ((int)(sizeof(rx_filters) / sizeof(rx_filters[0]))) +#define N_RX_FILTERS ((int)(ARRAY_SIZE(rx_filters))) static void usage(void) { diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh index fa9e09ad97d9..85a8ee9395b3 100755 --- a/tools/testing/selftests/net/mptcp/diag.sh +++ b/tools/testing/selftests/net/mptcp/diag.sh @@ -65,12 +65,15 @@ __chk_nr() if [ $nr != $expected ]; then if [ $nr = "$skip" ] && ! mptcp_lib_expect_all_features; then echo "[ skip ] Feature probably not supported" + mptcp_lib_result_skip "${msg}" else echo "[ fail ] expected $expected found $nr" + mptcp_lib_result_fail "${msg}" ret=$test_cnt fi else echo "[ ok ]" + mptcp_lib_result_pass "${msg}" fi test_cnt=$((test_cnt+1)) } @@ -111,12 +114,15 @@ wait_msk_nr() printf "%-50s" "$msg" if [ $i -ge $timeout ]; then echo "[ fail ] timeout while expecting $expected max $max last $nr" + mptcp_lib_result_fail "${msg} # timeout" ret=$test_cnt elif [ $nr != $expected ]; then echo "[ fail ] expected $expected found $nr" + mptcp_lib_result_fail "${msg} # unexpected result" ret=$test_cnt else echo "[ ok ]" + mptcp_lib_result_pass "${msg}" fi test_cnt=$((test_cnt+1)) } @@ -276,4 +282,5 @@ flush_pids chk_msk_inuse 0 "....chk 0 msk in use after flush" +mptcp_lib_result_print_all_tap exit $ret diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index bbae40882bfa..b1fc8afd072d 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -7,6 +7,7 @@ time_start=$(date +%s) optstring="S:R:d:e:l:r:h4cm:f:tC" ret=0 +final_ret=0 sin="" sout="" cin_disconnect="" @@ -128,6 +129,7 @@ ns3="ns3-$rndh" ns4="ns4-$rndh" TEST_COUNT=0 +TEST_GROUP="" cleanup() { @@ -285,6 +287,7 @@ check_mptcp_disabled() # net.mptcp.enabled should be enabled by default if [ "$(ip netns exec ${disabled_ns} sysctl net.mptcp.enabled | awk '{ print $3 }')" -ne 1 ]; then echo -e "net.mptcp.enabled sysctl is not 1 by default\t\t[ FAIL ]" + mptcp_lib_result_fail "net.mptcp.enabled sysctl is not 1 by default" ret=1 return 1 fi @@ -297,11 +300,13 @@ check_mptcp_disabled() if [ ${err} -eq 0 ]; then echo -e "New MPTCP socket cannot be blocked via sysctl\t\t[ FAIL ]" + mptcp_lib_result_fail "New MPTCP socket cannot be blocked via sysctl" ret=1 return 1 fi echo -e "New MPTCP socket can be blocked via sysctl\t\t[ OK ]" + mptcp_lib_result_pass "New MPTCP socket can be blocked via sysctl" return 0 } @@ -317,14 +322,16 @@ do_ping() local connector_ns="$2" local connect_addr="$3" local ping_args="-q -c 1" + local rc=0 if is_v6 "${connect_addr}"; then $ipv6 || return 0 ping_args="${ping_args} -6" fi - ip netns exec ${connector_ns} ping ${ping_args} $connect_addr >/dev/null - if [ $? -ne 0 ] ; then + ip netns exec ${connector_ns} ping ${ping_args} $connect_addr >/dev/null || rc=1 + + if [ $rc -ne 0 ] ; then echo "$listener_ns -> $connect_addr connectivity [ FAIL ]" 1>&2 ret=1 @@ -403,7 +410,9 @@ do_transfer() local addr_port addr_port=$(printf "%s:%d" ${connect_addr} ${port}) - printf "%.3s %-5s -> %.3s (%-20s) %-5s\t" ${connector_ns} ${cl_proto} ${listener_ns} ${addr_port} ${srv_proto} + local result_msg + result_msg="$(printf "%.3s %-5s -> %.3s (%-20s) %-5s" ${connector_ns} ${cl_proto} ${listener_ns} ${addr_port} ${srv_proto})" + printf "%s\t" "${result_msg}" if $capture; then local capuser @@ -478,6 +487,7 @@ do_transfer() local duration duration=$((stop-start)) + result_msg+=" # time=${duration}ms" printf "(duration %05sms) " "${duration}" if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then echo "[ FAIL ] client exit code $retc, server $rets" 1>&2 @@ -490,6 +500,7 @@ do_transfer() echo cat "$capout" + mptcp_lib_result_fail "${TEST_GROUP}: ${result_msg}" return 1 fi @@ -549,6 +560,9 @@ do_transfer() if [ $retc -eq 0 ] && [ $rets -eq 0 ]; then printf "[ OK ]" + mptcp_lib_result_pass "${TEST_GROUP}: ${result_msg}" + else + mptcp_lib_result_fail "${TEST_GROUP}: ${result_msg}" fi if [ $cookies -eq 2 ];then @@ -691,6 +705,8 @@ run_test_transparent() local lret=0 local r6flag="" + TEST_GROUP="${msg}" + # skip if we don't want v6 if ! $ipv6 && is_v6 "${connect_addr}"; then return 0 @@ -702,6 +718,7 @@ run_test_transparent() # checking for a specific kernel version. if ! mptcp_lib_kallsyms_has "T __ip_sock_set_tos$"; then echo "INFO: ${msg} not supported by the kernel: SKIP" + mptcp_lib_result_skip "${TEST_GROUP}" return fi @@ -719,6 +736,7 @@ EOF if [ $? -ne 0 ]; then echo "SKIP: $msg, could not load nft ruleset" mptcp_lib_fail_if_expected_feature "nft rules" + mptcp_lib_result_skip "${TEST_GROUP}" return fi @@ -735,6 +753,7 @@ EOF ip netns exec "$listener_ns" nft flush ruleset echo "SKIP: $msg, ip $r6flag rule failed" mptcp_lib_fail_if_expected_feature "ip rule" + mptcp_lib_result_skip "${TEST_GROUP}" return fi @@ -744,6 +763,7 @@ EOF ip -net "$listener_ns" $r6flag rule del fwmark 1 lookup 100 echo "SKIP: $msg, ip route add local $local_addr failed" mptcp_lib_fail_if_expected_feature "ip route" + mptcp_lib_result_skip "${TEST_GROUP}" return fi @@ -773,6 +793,7 @@ run_tests_peekmode() { local peekmode="$1" + TEST_GROUP="peek mode: ${peekmode}" echo "INFO: with peek mode: ${peekmode}" run_tests_lo "$ns1" "$ns1" 10.0.1.1 1 "-P ${peekmode}" run_tests_lo "$ns1" "$ns1" dead:beef:1::1 1 "-P ${peekmode}" @@ -780,8 +801,11 @@ run_tests_peekmode() run_tests_mptfo() { + TEST_GROUP="MPTFO" + if ! mptcp_lib_kallsyms_has "mptcp_fastopen_"; then echo "INFO: TFO not supported by the kernel: SKIP" + mptcp_lib_result_skip "${TEST_GROUP}" return fi @@ -805,8 +829,11 @@ run_tests_disconnect() local old_cin=$cin local old_sin=$sin + TEST_GROUP="full disconnect" + if ! mptcp_lib_kallsyms_has "mptcp_pm_data_reset$"; then echo "INFO: Full disconnect not supported: SKIP" + mptcp_lib_result_skip "${TEST_GROUP}" return fi @@ -837,14 +864,26 @@ display_time() echo "Time: ${time_run} seconds" } -stop_if_error() +log_if_error() { local msg="$1" if [ ${ret} -ne 0 ]; then echo "FAIL: ${msg}" 1>&2 + + final_ret=${ret} + ret=0 + + return ${final_ret} + fi +} + +stop_if_error() +{ + if ! log_if_error "${@}"; then display_time - exit ${ret} + mptcp_lib_result_print_all_tap + exit ${final_ret} fi } @@ -874,6 +913,8 @@ for sender in "$ns1" "$ns2" "$ns3" "$ns4";do do_ping "$ns4" $sender dead:beef:3::1 done +mptcp_lib_result_code "${ret}" "ping tests" + stop_if_error "Could not even run ping tests" [ -n "$tc_loss" ] && tc -net "$ns2" qdisc add dev ns2eth3 root netem loss random $tc_loss delay ${tc_delay}ms @@ -903,12 +944,15 @@ echo "on ns3eth4" tc -net "$ns3" qdisc add dev ns3eth4 root netem delay ${reorder_delay}ms $tc_reorder +TEST_GROUP="loopback v4" run_tests_lo "$ns1" "$ns1" 10.0.1.1 1 stop_if_error "Could not even run loopback test" +TEST_GROUP="loopback v6" run_tests_lo "$ns1" "$ns1" dead:beef:1::1 1 stop_if_error "Could not even run loopback v6 test" +TEST_GROUP="multihosts" for sender in $ns1 $ns2 $ns3 $ns4;do # ns1<->ns2 is not subject to reordering/tc delays. Use it to test # mptcp syncookie support. @@ -934,23 +978,25 @@ for sender in $ns1 $ns2 $ns3 $ns4;do run_tests "$ns4" $sender 10.0.3.1 run_tests "$ns4" $sender dead:beef:3::1 - stop_if_error "Tests with $sender as a sender have failed" + log_if_error "Tests with $sender as a sender have failed" done run_tests_peekmode "saveWithPeek" run_tests_peekmode "saveAfterPeek" -stop_if_error "Tests with peek mode have failed" +log_if_error "Tests with peek mode have failed" # MPTFO (MultiPath TCP Fatopen tests) run_tests_mptfo -stop_if_error "Tests with MPTFO have failed" +log_if_error "Tests with MPTFO have failed" # connect to ns4 ip address, ns2 should intercept/proxy run_test_transparent 10.0.3.1 "tproxy ipv4" run_test_transparent dead:beef:3::1 "tproxy ipv6" -stop_if_error "Tests with tproxy have failed" +log_if_error "Tests with tproxy have failed" run_tests_disconnect +log_if_error "Tests of the full disconnection have failed" display_time -exit $ret +mptcp_lib_result_print_all_tap +exit ${final_ret} diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index d01b73a8ed0f..ee1f89a872b3 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -39,7 +39,9 @@ evts_ns1="" evts_ns2="" evts_ns1_pid=0 evts_ns2_pid=0 -stats_dumped=0 +last_test_failed=0 +last_test_skipped=0 +last_test_ignored=1 declare -A all_tests declare -a only_tests_ids @@ -47,13 +49,17 @@ declare -a only_tests_names declare -A failed_tests TEST_COUNT=0 TEST_NAME="" -nr_blank=40 - -export FAILING_LINKS="" -export test_linkfail=0 -export addr_nr_ns1=0 -export addr_nr_ns2=0 -export sflags="" +nr_blank=6 + +# These var are used only in some tests, make sure they are not already set +unset FAILING_LINKS +unset test_linkfail +unset addr_nr_ns1 +unset addr_nr_ns2 +unset sflags +unset fastclose +unset fullmesh +unset speed # generated using "nfbpf_compile '(ip && (ip[54] & 0xf0) == 0x30) || # (ip6 && (ip6[74] & 0xf0) == 0x30)'" @@ -97,10 +103,8 @@ init_partial() fi done - stats_dumped=0 check_invert=0 validate_checksum=$checksum - FAILING_LINKS="" # ns1 ns2 # ns1eth1 ns2eth1 @@ -183,8 +187,8 @@ init() { trap cleanup EXIT - make_file "$cin" "client" 1 - make_file "$sin" "server" 1 + make_file "$cin" "client" 1 >/dev/null + make_file "$sin" "server" 1 >/dev/null } cleanup() @@ -196,10 +200,37 @@ cleanup() cleanup_partial } -# $1: msg print_title() { - printf "%03u %-36s %s" "${TEST_COUNT}" "${TEST_NAME}" "${1}" + printf "%03u %s\n" "${TEST_COUNT}" "${TEST_NAME}" +} + +print_check() +{ + printf "%-${nr_blank}s%-36s" " " "${*}" +} + +print_info() +{ + # It can be empty, no need to print anything then + [ -z "${1}" ] && return + + mptcp_lib_print_info " Info: ${*}" +} + +print_ok() +{ + mptcp_lib_print_ok "[ ok ]${1:+ ${*}}" +} + +print_fail() +{ + mptcp_lib_print_err "[fail]${1:+ ${*}}" +} + +print_skip() +{ + mptcp_lib_print_warn "[skip]${1:+ ${*}}" } # [ $1: fail msg ] @@ -209,8 +240,10 @@ mark_as_skipped() mptcp_lib_fail_if_expected_feature "${msg}" - print_title "[ skip ] ${msg}" - printf "\n" + print_check "${msg}" + print_skip + + last_test_skipped=1 } # $@: condition @@ -243,17 +276,37 @@ skip_test() return 0 } +append_prev_results() +{ + if [ ${last_test_failed} -eq 1 ]; then + mptcp_lib_result_fail "${TEST_NAME}" + elif [ ${last_test_skipped} -eq 1 ]; then + mptcp_lib_result_skip "${TEST_NAME}" + elif [ ${last_test_ignored} -ne 1 ]; then + mptcp_lib_result_pass "${TEST_NAME}" + fi + + last_test_failed=0 + last_test_skipped=0 + last_test_ignored=0 +} + # $1: test name reset() { + append_prev_results + TEST_NAME="${1}" TEST_COUNT=$((TEST_COUNT+1)) if skip_test; then + last_test_ignored=1 return 1 fi + print_title + if [ "${init}" != "1" ]; then init else @@ -434,13 +487,19 @@ reset_with_tcp_filter() fi } +# $1: err msg fail_test() { ret=1 - failed_tests[${TEST_COUNT}]="${TEST_NAME}" - [ "${stats_dumped}" = 0 ] && dump_stats - stats_dumped=1 + print_fail "${@}" + + # just in case a test is marked twice as failed + if [ ${last_test_failed} -eq 0 ]; then + failed_tests[${TEST_COUNT}]="${TEST_NAME}" + dump_stats + last_test_failed=1 + fi } get_failed_tests_ids() @@ -455,7 +514,7 @@ get_failed_tests_ids() print_file_err() { ls -l "$1" 1>&2 - echo "Trailing bytes are: " + echo -n "Trailing bytes are: " tail -c 27 "$1" } @@ -473,8 +532,7 @@ check_transfer() # when truncating we must check the size explicitly out_size=$(wc -c $out | awk '{print $1}') if [ $out_size -ne $bytes ]; then - echo "[ FAIL ] $what output file has wrong size ($out_size, $bytes)" - fail_test + fail_test "$what output file has wrong size ($out_size, $bytes)" return 1 fi @@ -489,14 +547,13 @@ check_transfer() cmp -l "$in" "$out" | while read -r i a b; do local sum=$((0${a} + 0${b})) if [ $check_invert -eq 0 ] || [ $sum -ne $((0xff)) ]; then - echo "[ FAIL ] $what does not match (in, out):" + fail_test "$what does not match (in, out):" print_file_err "$in" print_file_err "$out" - fail_test return 1 else - echo "$what has inverted byte at ${i}" + print_info "$what has inverted byte at ${i}" fi done @@ -510,8 +567,7 @@ do_ping() local connect_addr="$3" if ! ip netns exec ${connector_ns} ping -q -c 1 $connect_addr >/dev/null; then - echo "$listener_ns -> $connect_addr connectivity [ FAIL ]" 1>&2 - fail_test + fail_test "$listener_ns -> $connect_addr connectivity" fi } @@ -750,10 +806,9 @@ pm_nl_change_endpoint() pm_nl_check_endpoint() { local line expected_line - local need_title=$1 - local msg="$2" - local ns=$3 - local addr=$4 + local msg="$1" + local ns=$2 + local addr=$3 local _flags="" local flags local _port @@ -762,13 +817,9 @@ pm_nl_check_endpoint() local _id local id - if [ "${need_title}" = 1 ]; then - printf "%03u %-36s %s" "${TEST_COUNT}" "${TEST_NAME}" "${msg}" - else - printf "%-${nr_blank}s %s" " " "${msg}" - fi + print_check "${msg}" - shift 4 + shift 3 while [ -n "$1" ]; do if [ $1 = "flags" ]; then _flags=$2 @@ -791,7 +842,7 @@ pm_nl_check_endpoint() done if [ -z "$id" ]; then - echo "[skip] bad test - missing endpoint id" + test_fail "bad test - missing endpoint id" return fi @@ -815,10 +866,9 @@ pm_nl_check_endpoint() [ -n "$_port" ] && expected_line="$expected_line $_port" fi if [ "$line" = "$expected_line" ]; then - echo "[ ok ]" + print_ok else - echo "[fail] expected '$expected_line' found '$line'" - fail_test + fail_test "expected '$expected_line' found '$line'" fi } @@ -828,6 +878,17 @@ pm_nl_set_endpoint() local connector_ns="$2" local connect_addr="$3" + local addr_nr_ns1=${addr_nr_ns1:-0} + local addr_nr_ns2=${addr_nr_ns2:-0} + local sflags=${sflags:-""} + local fullmesh=${fullmesh:-""} + + local flags="subflow" + if [ -n "${fullmesh}" ]; then + flags="${flags},fullmesh" + addr_nr_ns2=${fullmesh} + fi + # let the mptcp subflow be established in background before # do endpoint manipulation if [ $addr_nr_ns1 != "0" ] || [ $addr_nr_ns2 != "0" ]; then @@ -975,10 +1036,12 @@ do_transfer() local cl_proto="$3" local srv_proto="$4" local connect_addr="$5" - local speed="$6" local port=$((10000 + TEST_COUNT - 1)) local cappid + local FAILING_LINKS=${FAILING_LINKS:-""} + local fastclose=${fastclose:-""} + local speed=${speed:-"fast"} :> "$cout" :> "$sout" @@ -1011,24 +1074,22 @@ do_transfer() extra_args="-j" elif [ $speed = "slow" ]; then extra_args="-r 50" - elif [[ $speed = "speed_"* ]]; then - extra_args="-r ${speed:6}" + elif [ $speed -gt 0 ]; then + extra_args="-r ${speed}" fi - local flags="subflow" local extra_cl_args="" local extra_srv_args="" local trunc_size="" - if [[ "${addr_nr_ns2}" = "fastclose_"* ]]; then + if [ -n "${fastclose}" ]; then if [ ${test_linkfail} -le 1 ]; then - echo "fastclose tests need test_linkfail argument" - fail_test + fail_test "fastclose tests need test_linkfail argument" return 1 fi # disconnect trunc_size=${test_linkfail} - local side=${addr_nr_ns2:10} + local side=${fastclose} if [ ${side} = "client" ]; then extra_cl_args="-f ${test_linkfail}" @@ -1037,14 +1098,9 @@ do_transfer() extra_srv_args="-f ${test_linkfail}" extra_cl_args="-f -1" else - echo "wrong/unknown fastclose spec ${side}" - fail_test + fail_test "wrong/unknown fastclose spec ${side}" return 1 fi - addr_nr_ns2=0 - elif [[ "${addr_nr_ns2}" = "fullmesh_"* ]]; then - flags="${flags},fullmesh" - addr_nr_ns2=${addr_nr_ns2:9} fi extra_srv_args="$extra_args $extra_srv_args" @@ -1103,7 +1159,7 @@ do_transfer() nstat | grep Tcp > /tmp/${connector_ns}.out if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then - echo " client exit code $retc, server $rets" 1>&2 + fail_test "client exit code $retc, server $rets" echo -e "\nnetns ${listener_ns} socket stat for ${port}:" 1>&2 ip netns exec ${listener_ns} ss -Menita 1>&2 -o "sport = :$port" cat /tmp/${listener_ns}.out @@ -1112,7 +1168,6 @@ do_transfer() cat /tmp/${connector_ns}.out cat "$capout" - fail_test return 1 fi @@ -1147,7 +1202,7 @@ make_file() dd if=/dev/urandom of="$name" bs=1024 count=$size 2> /dev/null echo -e "\nMPTCP_TEST_FILE_END_MARKER" >> "$name" - echo "Created $name (size $size KB) containing data sent by $who" + print_info "Test file (size $size KB) for $who" } run_tests() @@ -1155,9 +1210,9 @@ run_tests() local listener_ns="$1" local connector_ns="$2" local connect_addr="$3" - local speed="${4:-fast}" local size + local test_linkfail=${test_linkfail:-0} # The values above 2 are reused to make test files # with the given sizes (KB) @@ -1199,7 +1254,7 @@ run_tests() make_file "$sinfail" "server" $size fi - do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} ${speed} + do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} } dump_stats() @@ -1228,36 +1283,34 @@ chk_csum_nr() csum_ns2=${csum_ns2:1} fi - printf "%-${nr_blank}s %s" " " "sum" + print_check "sum" count=$(get_counter ${ns1} "MPTcpExtDataCsumErr") if [ "$count" != "$csum_ns1" ]; then extra_msg="$extra_msg ns1=$count" fi if [ -z "$count" ]; then - echo -n "[skip]" + print_skip elif { [ "$count" != $csum_ns1 ] && [ $allow_multi_errors_ns1 -eq 0 ]; } || { [ "$count" -lt $csum_ns1 ] && [ $allow_multi_errors_ns1 -eq 1 ]; }; then - echo "[fail] got $count data checksum error[s] expected $csum_ns1" - fail_test + fail_test "got $count data checksum error[s] expected $csum_ns1" else - echo -n "[ ok ]" + print_ok fi - echo -n " - csum " + print_check "csum" count=$(get_counter ${ns2} "MPTcpExtDataCsumErr") if [ "$count" != "$csum_ns2" ]; then extra_msg="$extra_msg ns2=$count" fi if [ -z "$count" ]; then - echo -n "[skip]" + print_skip elif { [ "$count" != $csum_ns2 ] && [ $allow_multi_errors_ns2 -eq 0 ]; } || { [ "$count" -lt $csum_ns2 ] && [ $allow_multi_errors_ns2 -eq 1 ]; }; then - echo "[fail] got $count data checksum error[s] expected $csum_ns2" - fail_test + fail_test "got $count data checksum error[s] expected $csum_ns2" else - echo -n "[ ok ]" + print_ok fi - echo "$extra_msg" + print_info "$extra_msg" } chk_fail_nr() @@ -1275,7 +1328,7 @@ chk_fail_nr() if [[ $ns_invert = "invert" ]]; then ns_tx=$ns2 ns_rx=$ns1 - extra_msg=" invert" + extra_msg="invert" fi if [[ "${fail_tx}" = "-"* ]]; then @@ -1287,37 +1340,35 @@ chk_fail_nr() fail_rx=${fail_rx:1} fi - printf "%-${nr_blank}s %s" " " "ftx" + print_check "ftx" count=$(get_counter ${ns_tx} "MPTcpExtMPFailTx") if [ "$count" != "$fail_tx" ]; then extra_msg="$extra_msg,tx=$count" fi if [ -z "$count" ]; then - echo -n "[skip]" + print_skip elif { [ "$count" != "$fail_tx" ] && [ $allow_tx_lost -eq 0 ]; } || { [ "$count" -gt "$fail_tx" ] && [ $allow_tx_lost -eq 1 ]; }; then - echo "[fail] got $count MP_FAIL[s] TX expected $fail_tx" - fail_test + fail_test "got $count MP_FAIL[s] TX expected $fail_tx" else - echo -n "[ ok ]" + print_ok fi - echo -n " - failrx" + print_check "failrx" count=$(get_counter ${ns_rx} "MPTcpExtMPFailRx") if [ "$count" != "$fail_rx" ]; then extra_msg="$extra_msg,rx=$count" fi if [ -z "$count" ]; then - echo -n "[skip]" + print_skip elif { [ "$count" != "$fail_rx" ] && [ $allow_rx_lost -eq 0 ]; } || { [ "$count" -gt "$fail_rx" ] && [ $allow_rx_lost -eq 1 ]; }; then - echo "[fail] got $count MP_FAIL[s] RX expected $fail_rx" - fail_test + fail_test "got $count MP_FAIL[s] RX expected $fail_rx" else - echo -n "[ ok ]" + print_ok fi - echo "$extra_msg" + print_info "$extra_msg" } chk_fclose_nr() @@ -1328,39 +1379,37 @@ chk_fclose_nr() local count local ns_tx=$ns2 local ns_rx=$ns1 - local extra_msg=" " + local extra_msg="" if [[ $ns_invert = "invert" ]]; then ns_tx=$ns1 ns_rx=$ns2 - extra_msg=${extra_msg}"invert" + extra_msg="invert" fi - printf "%-${nr_blank}s %s" " " "ctx" + print_check "ctx" count=$(get_counter ${ns_tx} "MPTcpExtMPFastcloseTx") if [ -z "$count" ]; then - echo -n "[skip]" + print_skip elif [ "$count" != "$fclose_tx" ]; then extra_msg="$extra_msg,tx=$count" - echo "[fail] got $count MP_FASTCLOSE[s] TX expected $fclose_tx" - fail_test + fail_test "got $count MP_FASTCLOSE[s] TX expected $fclose_tx" else - echo -n "[ ok ]" + print_ok fi - echo -n " - fclzrx" + print_check "fclzrx" count=$(get_counter ${ns_rx} "MPTcpExtMPFastcloseRx") if [ -z "$count" ]; then - echo -n "[skip]" + print_skip elif [ "$count" != "$fclose_rx" ]; then extra_msg="$extra_msg,rx=$count" - echo "[fail] got $count MP_FASTCLOSE[s] RX expected $fclose_rx" - fail_test + fail_test "got $count MP_FASTCLOSE[s] RX expected $fclose_rx" else - echo -n "[ ok ]" + print_ok fi - echo "$extra_msg" + print_info "$extra_msg" } chk_rst_nr() @@ -1376,32 +1425,30 @@ chk_rst_nr() if [[ $ns_invert = "invert" ]]; then ns_tx=$ns2 ns_rx=$ns1 - extra_msg=" invert" + extra_msg="invert" fi - printf "%-${nr_blank}s %s" " " "rtx" + print_check "rtx" count=$(get_counter ${ns_tx} "MPTcpExtMPRstTx") if [ -z "$count" ]; then - echo -n "[skip]" + print_skip elif [ $count -lt $rst_tx ]; then - echo "[fail] got $count MP_RST[s] TX expected $rst_tx" - fail_test + fail_test "got $count MP_RST[s] TX expected $rst_tx" else - echo -n "[ ok ]" + print_ok fi - echo -n " - rstrx " + print_check "rstrx" count=$(get_counter ${ns_rx} "MPTcpExtMPRstRx") if [ -z "$count" ]; then - echo -n "[skip]" + print_skip elif [ "$count" -lt "$rst_rx" ]; then - echo "[fail] got $count MP_RST[s] RX expected $rst_rx" - fail_test + fail_test "got $count MP_RST[s] RX expected $rst_rx" else - echo -n "[ ok ]" + print_ok fi - echo "$extra_msg" + print_info "$extra_msg" } chk_infi_nr() @@ -1410,26 +1457,24 @@ chk_infi_nr() local infi_rx=$2 local count - printf "%-${nr_blank}s %s" " " "itx" + print_check "itx" count=$(get_counter ${ns2} "MPTcpExtInfiniteMapTx") if [ -z "$count" ]; then - echo -n "[skip]" + print_skip elif [ "$count" != "$infi_tx" ]; then - echo "[fail] got $count infinite map[s] TX expected $infi_tx" - fail_test + fail_test "got $count infinite map[s] TX expected $infi_tx" else - echo -n "[ ok ]" + print_ok fi - echo -n " - infirx" + print_check "infirx" count=$(get_counter ${ns1} "MPTcpExtInfiniteMapRx") if [ -z "$count" ]; then - echo "[skip]" + print_skip elif [ "$count" != "$infi_rx" ]; then - echo "[fail] got $count infinite map[s] RX expected $infi_rx" - fail_test + fail_test "got $count infinite map[s] RX expected $infi_rx" else - echo "[ ok ]" + print_ok fi } @@ -1446,51 +1491,47 @@ chk_join_nr() local corrupted_pkts=${9:-0} local count local with_cookie - local title="${TEST_NAME}" if [ "${corrupted_pkts}" -gt 0 ]; then - title+=": ${corrupted_pkts} corrupted pkts" + print_info "${corrupted_pkts} corrupted pkts" fi - printf "%03u %-36s %s" "${TEST_COUNT}" "${title}" "syn" + print_check "syn" count=$(get_counter ${ns1} "MPTcpExtMPJoinSynRx") if [ -z "$count" ]; then - echo -n "[skip]" + print_skip elif [ "$count" != "$syn_nr" ]; then - echo "[fail] got $count JOIN[s] syn expected $syn_nr" - fail_test + fail_test "got $count JOIN[s] syn expected $syn_nr" else - echo -n "[ ok ]" + print_ok fi - echo -n " - synack" + print_check "synack" with_cookie=$(ip netns exec $ns2 sysctl -n net.ipv4.tcp_syncookies) count=$(get_counter ${ns2} "MPTcpExtMPJoinSynAckRx") if [ -z "$count" ]; then - echo -n "[skip]" + print_skip elif [ "$count" != "$syn_ack_nr" ]; then # simult connections exceeding the limit with cookie enabled could go up to # synack validation as the conn limit can be enforced reliably only after # the subflow creation if [ "$with_cookie" = 2 ] && [ "$count" -gt "$syn_ack_nr" ] && [ "$count" -le "$syn_nr" ]; then - echo -n "[ ok ]" + print_ok else - echo "[fail] got $count JOIN[s] synack expected $syn_ack_nr" - fail_test + fail_test "got $count JOIN[s] synack expected $syn_ack_nr" fi else - echo -n "[ ok ]" + print_ok fi - echo -n " - ack" + print_check "ack" count=$(get_counter ${ns1} "MPTcpExtMPJoinAckRx") if [ -z "$count" ]; then - echo "[skip]" + print_skip elif [ "$count" != "$ack_nr" ]; then - echo "[fail] got $count JOIN[s] ack expected $ack_nr" - fail_test + fail_test "got $count JOIN[s] ack expected $ack_nr" else - echo "[ ok ]" + print_ok fi if [ $validate_checksum -eq 1 ]; then chk_csum_nr $csum_ns1 $csum_ns2 @@ -1515,22 +1556,21 @@ chk_stale_nr() local stale_nr local recover_nr - printf "%-${nr_blank}s %-18s" " " "stale" + print_check "stale" stale_nr=$(get_counter ${ns} "MPTcpExtSubflowStale") recover_nr=$(get_counter ${ns} "MPTcpExtSubflowRecover") if [ -z "$stale_nr" ] || [ -z "$recover_nr" ]; then - echo "[skip]" + print_skip elif [ $stale_nr -lt $stale_min ] || { [ $stale_max -gt 0 ] && [ $stale_nr -gt $stale_max ]; } || [ $((stale_nr - recover_nr)) -ne $stale_delta ]; then - echo "[fail] got $stale_nr stale[s] $recover_nr recover[s], " \ + fail_test "got $stale_nr stale[s] $recover_nr recover[s], " \ " expected stale in range [$stale_min..$stale_max]," \ - " stale-recover delta $stale_delta " - fail_test + " stale-recover delta $stale_delta" dump_stats=1 else - echo "[ ok ]" + print_ok fi if [ "${dump_stats}" = 1 ]; then @@ -1555,103 +1595,93 @@ chk_add_nr() timeout=$(ip netns exec $ns1 sysctl -n net.mptcp.add_addr_timeout) - printf "%-${nr_blank}s %s" " " "add" + print_check "add" count=$(get_counter ${ns2} "MPTcpExtAddAddr") if [ -z "$count" ]; then - echo -n "[skip]" + print_skip # if the test configured a short timeout tolerate greater then expected # add addrs options, due to retransmissions elif [ "$count" != "$add_nr" ] && { [ "$timeout" -gt 1 ] || [ "$count" -lt "$add_nr" ]; }; then - echo "[fail] got $count ADD_ADDR[s] expected $add_nr" - fail_test + fail_test "got $count ADD_ADDR[s] expected $add_nr" else - echo -n "[ ok ]" + print_ok fi - echo -n " - echo " + print_check "echo" count=$(get_counter ${ns1} "MPTcpExtEchoAdd") if [ -z "$count" ]; then - echo -n "[skip]" + print_skip elif [ "$count" != "$echo_nr" ]; then - echo "[fail] got $count ADD_ADDR echo[s] expected $echo_nr" - fail_test + fail_test "got $count ADD_ADDR echo[s] expected $echo_nr" else - echo -n "[ ok ]" + print_ok fi if [ $port_nr -gt 0 ]; then - echo -n " - pt " + print_check "pt" count=$(get_counter ${ns2} "MPTcpExtPortAdd") if [ -z "$count" ]; then - echo "[skip]" + print_skip elif [ "$count" != "$port_nr" ]; then - echo "[fail] got $count ADD_ADDR[s] with a port-number expected $port_nr" - fail_test + fail_test "got $count ADD_ADDR[s] with a port-number expected $port_nr" else - echo "[ ok ]" + print_ok fi - printf "%-${nr_blank}s %s" " " "syn" + print_check "syn" count=$(get_counter ${ns1} "MPTcpExtMPJoinPortSynRx") if [ -z "$count" ]; then - echo -n "[skip]" + print_skip elif [ "$count" != "$syn_nr" ]; then - echo "[fail] got $count JOIN[s] syn with a different \ - port-number expected $syn_nr" - fail_test + fail_test "got $count JOIN[s] syn with a different \ + port-number expected $syn_nr" else - echo -n "[ ok ]" + print_ok fi - echo -n " - synack" + print_check "synack" count=$(get_counter ${ns2} "MPTcpExtMPJoinPortSynAckRx") if [ -z "$count" ]; then - echo -n "[skip]" + print_skip elif [ "$count" != "$syn_ack_nr" ]; then - echo "[fail] got $count JOIN[s] synack with a different \ - port-number expected $syn_ack_nr" - fail_test + fail_test "got $count JOIN[s] synack with a different \ + port-number expected $syn_ack_nr" else - echo -n "[ ok ]" + print_ok fi - echo -n " - ack" + print_check "ack" count=$(get_counter ${ns1} "MPTcpExtMPJoinPortAckRx") if [ -z "$count" ]; then - echo "[skip]" + print_skip elif [ "$count" != "$ack_nr" ]; then - echo "[fail] got $count JOIN[s] ack with a different \ - port-number expected $ack_nr" - fail_test + fail_test "got $count JOIN[s] ack with a different \ + port-number expected $ack_nr" else - echo "[ ok ]" + print_ok fi - printf "%-${nr_blank}s %s" " " "syn" + print_check "syn" count=$(get_counter ${ns1} "MPTcpExtMismatchPortSynRx") if [ -z "$count" ]; then - echo -n "[skip]" + print_skip elif [ "$count" != "$mis_syn_nr" ]; then - echo "[fail] got $count JOIN[s] syn with a mismatched \ - port-number expected $mis_syn_nr" - fail_test + fail_test "got $count JOIN[s] syn with a mismatched \ + port-number expected $mis_syn_nr" else - echo -n "[ ok ]" + print_ok fi - echo -n " - ack " + print_check "ack" count=$(get_counter ${ns1} "MPTcpExtMismatchPortAckRx") if [ -z "$count" ]; then - echo "[skip]" + print_skip elif [ "$count" != "$mis_ack_nr" ]; then - echo "[fail] got $count JOIN[s] ack with a mismatched \ - port-number expected $mis_ack_nr" - fail_test + fail_test "got $count JOIN[s] ack with a mismatched \ + port-number expected $mis_ack_nr" else - echo "[ ok ]" + print_ok fi - else - echo "" fi } @@ -1664,28 +1694,26 @@ chk_add_tx_nr() timeout=$(ip netns exec $ns1 sysctl -n net.mptcp.add_addr_timeout) - printf "%-${nr_blank}s %s" " " "add TX" + print_check "add TX" count=$(get_counter ${ns1} "MPTcpExtAddAddrTx") if [ -z "$count" ]; then - echo -n "[skip]" + print_skip # if the test configured a short timeout tolerate greater then expected # add addrs options, due to retransmissions elif [ "$count" != "$add_tx_nr" ] && { [ "$timeout" -gt 1 ] || [ "$count" -lt "$add_tx_nr" ]; }; then - echo "[fail] got $count ADD_ADDR[s] TX, expected $add_tx_nr" - fail_test + fail_test "got $count ADD_ADDR[s] TX, expected $add_tx_nr" else - echo -n "[ ok ]" + print_ok fi - echo -n " - echo TX " + print_check "echo TX" count=$(get_counter ${ns2} "MPTcpExtEchoAddTx") if [ -z "$count" ]; then - echo "[skip]" + print_skip elif [ "$count" != "$echo_tx_nr" ]; then - echo "[fail] got $count ADD_ADDR echo[s] TX, expected $echo_tx_nr" - fail_test + fail_test "got $count ADD_ADDR echo[s] TX, expected $echo_tx_nr" else - echo "[ ok ]" + print_ok fi } @@ -1713,24 +1741,23 @@ chk_rm_nr() elif [ $invert = "true" ]; then addr_ns=$ns2 subflow_ns=$ns1 - extra_msg=" invert" + extra_msg="invert" fi - printf "%-${nr_blank}s %s" " " "rm " + print_check "rm" count=$(get_counter ${addr_ns} "MPTcpExtRmAddr") if [ -z "$count" ]; then - echo -n "[skip]" + print_skip elif [ "$count" != "$rm_addr_nr" ]; then - echo "[fail] got $count RM_ADDR[s] expected $rm_addr_nr" - fail_test + fail_test "got $count RM_ADDR[s] expected $rm_addr_nr" else - echo -n "[ ok ]" + print_ok fi - echo -n " - rmsf " + print_check "rmsf" count=$(get_counter ${subflow_ns} "MPTcpExtRmSubflow") if [ -z "$count" ]; then - echo -n "[skip]" + print_skip elif [ -n "$simult" ]; then local cnt suffix @@ -1742,34 +1769,31 @@ chk_rm_nr() [ "$count" != "$rm_subflow_nr" ] && suffix="$count in [$rm_subflow_nr:$((rm_subflow_nr*2))]" if [ $count -ge "$rm_subflow_nr" ] && \ [ "$count" -le "$((rm_subflow_nr *2 ))" ]; then - echo -n "[ ok ] $suffix" + print_ok "$suffix" else - echo "[fail] got $count RM_SUBFLOW[s] expected in range [$rm_subflow_nr:$((rm_subflow_nr*2))]" - fail_test + fail_test "got $count RM_SUBFLOW[s] expected in range [$rm_subflow_nr:$((rm_subflow_nr*2))]" fi elif [ "$count" != "$rm_subflow_nr" ]; then - echo "[fail] got $count RM_SUBFLOW[s] expected $rm_subflow_nr" - fail_test + fail_test "got $count RM_SUBFLOW[s] expected $rm_subflow_nr" else - echo -n "[ ok ]" + print_ok fi - echo "$extra_msg" + print_info "$extra_msg" } chk_rm_tx_nr() { local rm_addr_tx_nr=$1 - printf "%-${nr_blank}s %s" " " "rm TX " + print_check "rm TX" count=$(get_counter ${ns2} "MPTcpExtRmAddrTx") if [ -z "$count" ]; then - echo "[skip]" + print_skip elif [ "$count" != "$rm_addr_tx_nr" ]; then - echo "[fail] got $count RM_ADDR[s] expected $rm_addr_tx_nr" - fail_test + fail_test "got $count RM_ADDR[s] expected $rm_addr_tx_nr" else - echo "[ ok ]" + print_ok fi } @@ -1779,52 +1803,44 @@ chk_prio_nr() local mp_prio_nr_rx=$2 local count - printf "%-${nr_blank}s %s" " " "ptx" + print_check "ptx" count=$(get_counter ${ns1} "MPTcpExtMPPrioTx") if [ -z "$count" ]; then - echo -n "[skip]" + print_skip elif [ "$count" != "$mp_prio_nr_tx" ]; then - echo "[fail] got $count MP_PRIO[s] TX expected $mp_prio_nr_tx" - fail_test + fail_test "got $count MP_PRIO[s] TX expected $mp_prio_nr_tx" else - echo -n "[ ok ]" + print_ok fi - echo -n " - prx " + print_check "prx" count=$(get_counter ${ns1} "MPTcpExtMPPrioRx") if [ -z "$count" ]; then - echo "[skip]" + print_skip elif [ "$count" != "$mp_prio_nr_rx" ]; then - echo "[fail] got $count MP_PRIO[s] RX expected $mp_prio_nr_rx" - fail_test + fail_test "got $count MP_PRIO[s] RX expected $mp_prio_nr_rx" else - echo "[ ok ]" + print_ok fi } chk_subflow_nr() { - local need_title="$1" - local msg="$2" - local subflow_nr=$3 + local msg="$1" + local subflow_nr=$2 local cnt1 local cnt2 local dump_stats - if [ -n "${need_title}" ]; then - printf "%03u %-36s %s" "${TEST_COUNT}" "${TEST_NAME}" "${msg}" - else - printf "%-${nr_blank}s %s" " " "${msg}" - fi + print_check "${msg}" cnt1=$(ss -N $ns1 -tOni | grep -c token) cnt2=$(ss -N $ns2 -tOni | grep -c token) if [ "$cnt1" != "$subflow_nr" ] || [ "$cnt2" != "$subflow_nr" ]; then - echo "[fail] got $cnt1:$cnt2 subflows expected $subflow_nr" - fail_test + fail_test "got $cnt1:$cnt2 subflows expected $subflow_nr" dump_stats=1 else - echo "[ ok ]" + print_ok fi if [ "${dump_stats}" = 1 ]; then @@ -1844,7 +1860,7 @@ chk_mptcp_info() local cnt2 local dump_stats - printf "%-${nr_blank}s %-30s" " " "mptcp_info $info1:$info2=$exp1:$exp2" + print_check "mptcp_info ${info1:0:8}=$exp1:$exp2" cnt1=$(ss -N $ns1 -inmHM | grep "$info1:" | sed -n 's/.*\('"$info1"':\)\([[:digit:]]*\).*$/\2/p;q') @@ -1855,11 +1871,10 @@ chk_mptcp_info() [ -z "$cnt2" ] && cnt2=0 if [ "$cnt1" != "$exp1" ] || [ "$cnt2" != "$exp2" ]; then - echo "[fail] got $cnt1:$cnt2 $info1:$info2 expected $exp1:$exp2" - fail_test + fail_test "got $cnt1:$cnt2 $info1:$info2 expected $exp1:$exp2" dump_stats=1 else - echo "[ ok ]" + print_ok fi if [ "$dump_stats" = 1 ]; then @@ -1881,13 +1896,12 @@ chk_link_usage() local tx_rate=$((tx_link * 100 / tx_total)) local tolerance=5 - printf "%-${nr_blank}s %-18s" " " "link usage" + print_check "link usage" if [ $tx_rate -lt $((expected_rate - tolerance)) ] || \ [ $tx_rate -gt $((expected_rate + tolerance)) ]; then - echo "[fail] got $tx_rate% usage, expected $expected_rate%" - fail_test + fail_test "got $tx_rate% usage, expected $expected_rate%" else - echo "[ ok ]" + print_ok fi } @@ -1988,7 +2002,8 @@ subflows_error_tests() pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 0 1 pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 slow + speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 0 0 0 fi @@ -1999,7 +2014,8 @@ subflows_error_tests() pm_nl_set_limits $ns2 0 2 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 slow + speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 1 1 1 fi @@ -2010,7 +2026,8 @@ subflows_error_tests() pm_nl_set_limits $ns2 0 2 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 slow + speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 1 1 1 fi @@ -2022,7 +2039,8 @@ subflows_error_tests() pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 0 1 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 slow & + speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 & # mpj subflow will be in TW after the reset wait_attempt_fail $ns2 @@ -2121,7 +2139,8 @@ signal_address_tests() # the peer could possibly miss some addr notification, allow retransmission ip netns exec $ns1 sysctl -q net.mptcp.add_addr_timeout=1 - run_tests $ns1 $ns2 10.0.1.1 slow + speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 # It is not directly linked to the commit introducing this # symbol but for the parent one which is linked anyway. @@ -2231,7 +2250,8 @@ add_addr_timeout_tests() pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 1 1 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 slow + speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 1 1 1 chk_add_tx_nr 4 4 chk_add_nr 4 0 @@ -2242,7 +2262,8 @@ add_addr_timeout_tests() pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 1 1 pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal - run_tests $ns1 $ns2 dead:beef:1::1 slow + speed=slow \ + run_tests $ns1 $ns2 dead:beef:1::1 chk_join_nr 1 1 1 chk_add_nr 4 0 fi @@ -2253,7 +2274,8 @@ add_addr_timeout_tests() pm_nl_add_endpoint $ns1 10.0.2.1 flags signal pm_nl_add_endpoint $ns1 10.0.3.1 flags signal pm_nl_set_limits $ns2 2 2 - run_tests $ns1 $ns2 10.0.1.1 speed_10 + speed=10 \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 2 2 2 chk_add_nr 8 0 fi @@ -2264,7 +2286,8 @@ add_addr_timeout_tests() pm_nl_add_endpoint $ns1 10.0.12.1 flags signal pm_nl_add_endpoint $ns1 10.0.3.1 flags signal pm_nl_set_limits $ns2 2 2 - run_tests $ns1 $ns2 10.0.1.1 speed_10 + speed=10 \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 1 1 1 chk_add_nr 8 0 fi @@ -2277,8 +2300,8 @@ remove_tests() pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 0 1 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - addr_nr_ns2=-1 \ - run_tests $ns1 $ns2 10.0.1.1 slow + addr_nr_ns2=-1 speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 1 1 1 chk_rm_tx_nr 1 chk_rm_nr 1 1 @@ -2290,8 +2313,8 @@ remove_tests() pm_nl_set_limits $ns2 0 2 pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - addr_nr_ns2=-2 \ - run_tests $ns1 $ns2 10.0.1.1 slow + addr_nr_ns2=-2 speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 2 2 2 chk_rm_nr 2 2 fi @@ -2301,8 +2324,8 @@ remove_tests() pm_nl_set_limits $ns1 0 1 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal pm_nl_set_limits $ns2 1 1 - addr_nr_ns1=-1 \ - run_tests $ns1 $ns2 10.0.1.1 slow + addr_nr_ns1=-1 speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 1 1 1 chk_add_nr 1 1 chk_rm_nr 1 1 invert @@ -2314,8 +2337,8 @@ remove_tests() pm_nl_add_endpoint $ns1 10.0.2.1 flags signal pm_nl_set_limits $ns2 1 2 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - addr_nr_ns1=-1 addr_nr_ns2=-1 \ - run_tests $ns1 $ns2 10.0.1.1 slow + addr_nr_ns1=-1 addr_nr_ns2=-1 speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 2 2 2 chk_add_nr 1 1 chk_rm_nr 1 1 @@ -2328,8 +2351,8 @@ remove_tests() pm_nl_set_limits $ns2 1 3 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow - addr_nr_ns1=-1 addr_nr_ns2=-2 \ - run_tests $ns1 $ns2 10.0.1.1 speed_10 + addr_nr_ns1=-1 addr_nr_ns2=-2 speed=10 \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 3 3 3 chk_add_nr 1 1 chk_rm_nr 2 2 @@ -2342,8 +2365,8 @@ remove_tests() pm_nl_add_endpoint $ns1 10.0.3.1 flags signal pm_nl_add_endpoint $ns1 10.0.4.1 flags signal pm_nl_set_limits $ns2 3 3 - addr_nr_ns1=-3 \ - run_tests $ns1 $ns2 10.0.1.1 speed_10 + addr_nr_ns1=-3 speed=10 \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 3 3 3 chk_add_nr 3 3 chk_rm_nr 3 3 invert @@ -2356,8 +2379,8 @@ remove_tests() pm_nl_add_endpoint $ns1 10.0.3.1 flags signal pm_nl_add_endpoint $ns1 10.0.14.1 flags signal pm_nl_set_limits $ns2 3 3 - addr_nr_ns1=-3 \ - run_tests $ns1 $ns2 10.0.1.1 speed_10 + addr_nr_ns1=-3 speed=10 \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 1 1 1 chk_add_nr 3 3 chk_rm_nr 3 1 invert @@ -2370,8 +2393,8 @@ remove_tests() pm_nl_set_limits $ns2 1 3 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow - addr_nr_ns1=-8 addr_nr_ns2=-8 \ - run_tests $ns1 $ns2 10.0.1.1 slow + addr_nr_ns1=-8 addr_nr_ns2=-8 speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 3 3 3 chk_add_nr 1 1 chk_rm_nr 1 3 invert simult @@ -2384,8 +2407,8 @@ remove_tests() pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow id 150 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow - addr_nr_ns1=-8 addr_nr_ns2=-8 \ - run_tests $ns1 $ns2 10.0.1.1 slow + addr_nr_ns1=-8 addr_nr_ns2=-8 speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 3 3 3 if mptcp_lib_kversion_ge 5.18; then @@ -2403,8 +2426,8 @@ remove_tests() pm_nl_add_endpoint $ns1 10.0.3.1 flags signal pm_nl_add_endpoint $ns1 10.0.4.1 flags signal pm_nl_set_limits $ns2 3 3 - addr_nr_ns1=-8 addr_nr_ns2=-8 \ - run_tests $ns1 $ns2 10.0.1.1 slow + addr_nr_ns1=-8 addr_nr_ns2=-8 speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 3 3 3 chk_add_nr 3 3 chk_rm_nr 3 3 invert simult @@ -2417,8 +2440,8 @@ remove_tests() pm_nl_add_endpoint $ns1 10.0.3.1 flags signal pm_nl_add_endpoint $ns1 10.0.14.1 flags signal pm_nl_set_limits $ns2 3 3 - addr_nr_ns1=-8 \ - run_tests $ns1 $ns2 10.0.1.1 slow + addr_nr_ns1=-8 speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 1 1 1 chk_add_nr 3 3 chk_rm_nr 3 1 invert @@ -2429,8 +2452,8 @@ remove_tests() pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 0 1 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - addr_nr_ns2=-9 \ - run_tests $ns1 $ns2 10.0.1.1 slow + addr_nr_ns2=-9 speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 1 1 1 chk_rm_nr 1 1 fi @@ -2440,8 +2463,8 @@ remove_tests() pm_nl_set_limits $ns1 0 1 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal pm_nl_set_limits $ns2 1 1 - addr_nr_ns1=-9 \ - run_tests $ns1 $ns2 10.0.1.1 slow + addr_nr_ns1=-9 speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 1 1 1 chk_add_nr 1 1 chk_rm_nr 1 1 invert @@ -2454,8 +2477,8 @@ add_tests() if reset "add single subflow"; then pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 0 1 - addr_nr_ns2=1 \ - run_tests $ns1 $ns2 10.0.1.1 slow + addr_nr_ns2=1 speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 1 1 1 fi @@ -2463,8 +2486,8 @@ add_tests() if reset "add signal address"; then pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 1 1 - addr_nr_ns1=1 \ - run_tests $ns1 $ns2 10.0.1.1 slow + addr_nr_ns1=1 speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 1 1 1 chk_add_nr 1 1 fi @@ -2473,8 +2496,8 @@ add_tests() if reset "add multiple subflows"; then pm_nl_set_limits $ns1 0 2 pm_nl_set_limits $ns2 0 2 - addr_nr_ns2=2 \ - run_tests $ns1 $ns2 10.0.1.1 slow + addr_nr_ns2=2 speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 2 2 2 fi @@ -2482,8 +2505,8 @@ add_tests() if reset "add multiple subflows IPv6"; then pm_nl_set_limits $ns1 0 2 pm_nl_set_limits $ns2 0 2 - addr_nr_ns2=2 \ - run_tests $ns1 $ns2 dead:beef:1::1 slow + addr_nr_ns2=2 speed=slow \ + run_tests $ns1 $ns2 dead:beef:1::1 chk_join_nr 2 2 2 fi @@ -2491,8 +2514,8 @@ add_tests() if reset "add multiple addresses IPv6"; then pm_nl_set_limits $ns1 0 2 pm_nl_set_limits $ns2 2 2 - addr_nr_ns1=2 \ - run_tests $ns1 $ns2 dead:beef:1::1 slow + addr_nr_ns1=2 speed=slow \ + run_tests $ns1 $ns2 dead:beef:1::1 chk_join_nr 2 2 2 chk_add_nr 2 2 fi @@ -2505,14 +2528,16 @@ ipv6_tests() pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 0 1 pm_nl_add_endpoint $ns2 dead:beef:3::2 dev ns2eth3 flags subflow - run_tests $ns1 $ns2 dead:beef:1::1 slow + speed=slow \ + run_tests $ns1 $ns2 dead:beef:1::1 chk_join_nr 1 1 1 fi # add_address, unused IPv6 if reset "unused signal address IPv6"; then pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal - run_tests $ns1 $ns2 dead:beef:1::1 slow + speed=slow \ + run_tests $ns1 $ns2 dead:beef:1::1 chk_join_nr 0 0 0 chk_add_nr 1 1 fi @@ -2522,7 +2547,8 @@ ipv6_tests() pm_nl_set_limits $ns1 0 1 pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal pm_nl_set_limits $ns2 1 1 - run_tests $ns1 $ns2 dead:beef:1::1 slow + speed=slow \ + run_tests $ns1 $ns2 dead:beef:1::1 chk_join_nr 1 1 1 chk_add_nr 1 1 fi @@ -2532,8 +2558,8 @@ ipv6_tests() pm_nl_set_limits $ns1 0 1 pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal pm_nl_set_limits $ns2 1 1 - addr_nr_ns1=-1 \ - run_tests $ns1 $ns2 dead:beef:1::1 slow + addr_nr_ns1=-1 speed=slow \ + run_tests $ns1 $ns2 dead:beef:1::1 chk_join_nr 1 1 1 chk_add_nr 1 1 chk_rm_nr 1 1 invert @@ -2545,8 +2571,8 @@ ipv6_tests() pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal pm_nl_set_limits $ns2 1 2 pm_nl_add_endpoint $ns2 dead:beef:3::2 dev ns2eth3 flags subflow - addr_nr_ns1=-1 addr_nr_ns2=-1 \ - run_tests $ns1 $ns2 dead:beef:1::1 slow + addr_nr_ns1=-1 addr_nr_ns2=-1 speed=slow \ + run_tests $ns1 $ns2 dead:beef:1::1 chk_join_nr 2 2 2 chk_add_nr 1 1 chk_rm_nr 1 1 @@ -2647,7 +2673,8 @@ mixed_tests() pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 1 1 pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal - run_tests $ns1 $ns2 10.0.1.1 slow + speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 0 0 0 fi @@ -2657,7 +2684,8 @@ mixed_tests() pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 1 1 pm_nl_add_endpoint $ns1 10.0.1.1 flags signal - run_tests $ns1 $ns2 dead:beef:2::1 slow + speed=slow \ + run_tests $ns1 $ns2 dead:beef:2::1 chk_join_nr 1 1 1 fi @@ -2668,7 +2696,8 @@ mixed_tests() pm_nl_set_limits $ns2 1 4 pm_nl_add_endpoint $ns2 dead:beef:2::2 flags subflow,fullmesh pm_nl_add_endpoint $ns1 10.0.1.1 flags signal - run_tests $ns1 $ns2 dead:beef:2::1 slow + speed=slow \ + run_tests $ns1 $ns2 dead:beef:2::1 chk_join_nr 1 1 1 fi @@ -2680,8 +2709,8 @@ mixed_tests() pm_nl_set_limits $ns2 2 4 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal - addr_nr_ns2=fullmesh_1 \ - run_tests $ns1 $ns2 dead:beef:1::1 slow + fullmesh=1 speed=slow \ + run_tests $ns1 $ns2 dead:beef:1::1 chk_join_nr 4 4 4 fi } @@ -2694,8 +2723,8 @@ backup_tests() pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 0 1 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow,backup - sflags=nobackup \ - run_tests $ns1 $ns2 10.0.1.1 slow + sflags=nobackup speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 1 1 1 chk_prio_nr 0 1 fi @@ -2706,8 +2735,8 @@ backup_tests() pm_nl_set_limits $ns1 0 1 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal pm_nl_set_limits $ns2 1 1 - sflags=backup \ - run_tests $ns1 $ns2 10.0.1.1 slow + sflags=backup speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 1 1 1 chk_add_nr 1 1 chk_prio_nr 1 1 @@ -2719,8 +2748,8 @@ backup_tests() pm_nl_set_limits $ns1 0 1 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 pm_nl_set_limits $ns2 1 1 - sflags=backup \ - run_tests $ns1 $ns2 10.0.1.1 slow + sflags=backup speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 1 1 1 chk_add_nr 1 1 chk_prio_nr 1 1 @@ -2729,7 +2758,8 @@ backup_tests() if reset "mpc backup" && continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,backup - run_tests $ns1 $ns2 10.0.1.1 slow + speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 0 0 0 chk_prio_nr 0 1 fi @@ -2738,7 +2768,8 @@ backup_tests() continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then pm_nl_add_endpoint $ns1 10.0.1.1 flags subflow,backup pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,backup - run_tests $ns1 $ns2 10.0.1.1 slow + speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 0 0 0 chk_prio_nr 1 1 fi @@ -2746,8 +2777,8 @@ backup_tests() if reset "mpc switch to backup" && continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow - sflags=backup \ - run_tests $ns1 $ns2 10.0.1.1 slow + sflags=backup speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 0 0 0 chk_prio_nr 0 1 fi @@ -2756,8 +2787,8 @@ backup_tests() continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then pm_nl_add_endpoint $ns1 10.0.1.1 flags subflow pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow - sflags=backup \ - run_tests $ns1 $ns2 10.0.1.1 slow + sflags=backup speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 0 0 0 chk_prio_nr 1 1 fi @@ -2785,15 +2816,15 @@ verify_listener_events() if [ $e_type = $LISTENER_CREATED ]; then name="LISTENER_CREATED" elif [ $e_type = $LISTENER_CLOSED ]; then - name="LISTENER_CLOSED" + name="LISTENER_CLOSED " else name="$e_type" fi - printf "%-${nr_blank}s %s %s:%s " " " "$name" "$e_saddr" "$e_sport" + print_check "$name $e_saddr:$e_sport" if ! mptcp_lib_kallsyms_has "mptcp_event_pm_listener$"; then - printf "[skip]: event not supported\n" + print_skip "event not supported" return fi @@ -2810,11 +2841,10 @@ verify_listener_events() [ $family ] && [ $family = $e_family ] && [ $saddr ] && [ $saddr = $e_saddr ] && [ $sport ] && [ $sport = $e_sport ]; then - echo "[ ok ]" + print_ok return 0 fi - fail_test - echo "[fail]" + fail_test "$e_type:$type $e_family:$family $e_saddr:$saddr $e_sport:$sport" } add_addr_ports_tests() @@ -2846,8 +2876,8 @@ add_addr_ports_tests() pm_nl_set_limits $ns1 0 1 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 pm_nl_set_limits $ns2 1 1 - addr_nr_ns1=-1 \ - run_tests $ns1 $ns2 10.0.1.1 slow + addr_nr_ns1=-1 speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 1 1 1 chk_add_nr 1 1 1 chk_rm_nr 1 1 invert @@ -2863,8 +2893,8 @@ add_addr_ports_tests() pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 pm_nl_set_limits $ns2 1 2 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - addr_nr_ns1=-1 addr_nr_ns2=-1 \ - run_tests $ns1 $ns2 10.0.1.1 slow + addr_nr_ns1=-1 addr_nr_ns2=-1 speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 2 2 2 chk_add_nr 1 1 1 chk_rm_nr 1 1 @@ -2877,8 +2907,8 @@ add_addr_ports_tests() pm_nl_set_limits $ns2 1 3 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow - addr_nr_ns1=-8 addr_nr_ns2=-2 \ - run_tests $ns1 $ns2 10.0.1.1 slow + addr_nr_ns1=-8 addr_nr_ns2=-2 speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 3 3 3 chk_add_nr 1 1 chk_rm_nr 1 3 invert simult @@ -3080,8 +3110,8 @@ fullmesh_tests() pm_nl_set_limits $ns2 1 4 pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow,fullmesh pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow,fullmesh - addr_nr_ns1=1 \ - run_tests $ns1 $ns2 10.0.1.1 slow + addr_nr_ns1=1 speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 4 4 4 chk_add_nr 1 1 fi @@ -3093,8 +3123,8 @@ fullmesh_tests() pm_nl_set_limits $ns1 1 3 pm_nl_set_limits $ns2 1 3 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - addr_nr_ns2=fullmesh_1 \ - run_tests $ns1 $ns2 10.0.1.1 slow + fullmesh=1 speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 3 3 3 chk_add_nr 1 1 fi @@ -3106,8 +3136,8 @@ fullmesh_tests() pm_nl_set_limits $ns1 2 5 pm_nl_set_limits $ns2 1 5 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - addr_nr_ns2=fullmesh_2 \ - run_tests $ns1 $ns2 10.0.1.1 slow + fullmesh=2 speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 5 5 5 chk_add_nr 1 1 fi @@ -3120,8 +3150,8 @@ fullmesh_tests() pm_nl_set_limits $ns1 2 4 pm_nl_set_limits $ns2 1 4 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - addr_nr_ns2=fullmesh_2 \ - run_tests $ns1 $ns2 10.0.1.1 slow + fullmesh=2 speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 4 4 4 chk_add_nr 1 1 fi @@ -3132,8 +3162,8 @@ fullmesh_tests() pm_nl_set_limits $ns1 4 4 pm_nl_add_endpoint $ns1 10.0.2.1 flags subflow pm_nl_set_limits $ns2 4 4 - addr_nr_ns2=1 sflags=fullmesh \ - run_tests $ns1 $ns2 10.0.1.1 slow + addr_nr_ns2=1 sflags=fullmesh speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 2 2 2 chk_rm_nr 0 1 fi @@ -3144,8 +3174,8 @@ fullmesh_tests() pm_nl_set_limits $ns1 4 4 pm_nl_add_endpoint $ns1 10.0.2.1 flags subflow,fullmesh pm_nl_set_limits $ns2 4 4 - addr_nr_ns2=fullmesh_1 sflags=nofullmesh \ - run_tests $ns1 $ns2 10.0.1.1 slow + fullmesh=1 sflags=nofullmesh speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 2 2 2 chk_rm_nr 0 1 fi @@ -3156,8 +3186,8 @@ fullmesh_tests() pm_nl_set_limits $ns1 4 4 pm_nl_add_endpoint $ns1 10.0.2.1 flags subflow pm_nl_set_limits $ns2 4 4 - addr_nr_ns2=1 sflags=backup,fullmesh \ - run_tests $ns1 $ns2 10.0.1.1 slow + addr_nr_ns2=1 sflags=backup,fullmesh speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 2 2 2 chk_prio_nr 0 1 chk_rm_nr 0 1 @@ -3169,8 +3199,8 @@ fullmesh_tests() pm_nl_set_limits $ns1 4 4 pm_nl_set_limits $ns2 4 4 pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow,backup,fullmesh - sflags=nobackup,nofullmesh \ - run_tests $ns1 $ns2 10.0.1.1 slow + sflags=nobackup,nofullmesh speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 2 2 2 chk_prio_nr 0 1 chk_rm_nr 0 1 @@ -3180,7 +3210,7 @@ fullmesh_tests() fastclose_tests() { if reset_check_counter "fastclose test" "MPTcpExtMPFastcloseTx"; then - test_linkfail=1024 addr_nr_ns2=fastclose_client \ + test_linkfail=1024 fastclose=client \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 0 0 0 chk_fclose_nr 1 1 @@ -3188,7 +3218,7 @@ fastclose_tests() fi if reset_check_counter "fastclose server test" "MPTcpExtMPFastcloseRx"; then - test_linkfail=1024 addr_nr_ns2=fastclose_server \ + test_linkfail=1024 fastclose=server \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 0 0 0 chk_fclose_nr 1 1 invert @@ -3345,8 +3375,8 @@ userspace_tests() pm_nl_set_limits $ns1 1 1 pm_nl_set_limits $ns2 1 1 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - sflags=backup \ - run_tests $ns1 $ns2 10.0.1.1 slow + sflags=backup speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 1 1 0 chk_prio_nr 0 0 fi @@ -3359,8 +3389,8 @@ userspace_tests() pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 0 1 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - addr_nr_ns2=-1 \ - run_tests $ns1 $ns2 10.0.1.1 slow + addr_nr_ns2=-1 speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 0 0 0 chk_rm_nr 0 0 fi @@ -3370,7 +3400,8 @@ userspace_tests() continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns1 pm_nl_set_limits $ns2 1 1 - run_tests $ns1 $ns2 10.0.1.1 speed_10 & + speed=10 \ + run_tests $ns1 $ns2 10.0.1.1 & local tests_pid=$! wait_mpj $ns1 userspace_pm_add_addr 10.0.2.1 10 @@ -3390,7 +3421,8 @@ userspace_tests() continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns2 pm_nl_set_limits $ns1 0 1 - run_tests $ns1 $ns2 10.0.1.1 speed_10 & + speed=10 \ + run_tests $ns1 $ns2 10.0.1.1 & local tests_pid=$! wait_mpj $ns2 userspace_pm_add_sf 10.0.3.2 20 @@ -3413,20 +3445,21 @@ endpoint_tests() pm_nl_set_limits $ns1 2 2 pm_nl_set_limits $ns2 2 2 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 slow 2>/dev/null & + speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 2>/dev/null & wait_mpj $ns1 - pm_nl_check_endpoint 1 "creation" \ + pm_nl_check_endpoint "creation" \ $ns2 10.0.2.2 id 1 flags implicit chk_mptcp_info subflows 1 subflows 1 chk_mptcp_info add_addr_signal 1 add_addr_accepted 1 - pm_nl_add_endpoint $ns2 10.0.2.2 id 33 - pm_nl_check_endpoint 0 "ID change is prevented" \ + pm_nl_add_endpoint $ns2 10.0.2.2 id 33 2>/dev/null + pm_nl_check_endpoint "ID change is prevented" \ $ns2 10.0.2.2 id 1 flags implicit pm_nl_add_endpoint $ns2 10.0.2.2 flags signal - pm_nl_check_endpoint 0 "modif is allowed" \ + pm_nl_check_endpoint "modif is allowed" \ $ns2 10.0.2.2 id 1 flags signal kill_tests_wait fi @@ -3436,21 +3469,21 @@ endpoint_tests() pm_nl_set_limits $ns1 1 1 pm_nl_set_limits $ns2 1 1 pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow - test_linkfail=4 \ - run_tests $ns1 $ns2 10.0.1.1 speed_20 2>/dev/null & + test_linkfail=4 speed=20 \ + run_tests $ns1 $ns2 10.0.1.1 2>/dev/null & wait_mpj $ns2 - chk_subflow_nr needtitle "before delete" 2 + chk_subflow_nr "before delete" 2 chk_mptcp_info subflows 1 subflows 1 pm_nl_del_endpoint $ns2 2 10.0.2.2 sleep 0.5 - chk_subflow_nr "" "after delete" 1 + chk_subflow_nr "after delete" 1 chk_mptcp_info subflows 0 subflows 0 pm_nl_add_endpoint $ns2 10.0.2.2 dev ns2eth2 flags subflow wait_mpj $ns2 - chk_subflow_nr "" "after re-add" 2 + chk_subflow_nr "after re-add" 2 chk_mptcp_info subflows 1 subflows 1 kill_tests_wait fi @@ -3568,4 +3601,7 @@ if [ ${ret} -ne 0 ]; then echo fi +append_prev_results +mptcp_lib_result_print_all_tap + exit $ret diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh index f32045b23b89..92a5befe8039 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -1,9 +1,52 @@ #! /bin/bash # SPDX-License-Identifier: GPL-2.0 +readonly KSFT_PASS=0 readonly KSFT_FAIL=1 readonly KSFT_SKIP=4 +# shellcheck disable=SC2155 # declare and assign separately +readonly KSFT_TEST=$(basename "${0}" | sed 's/\.sh$//g') + +MPTCP_LIB_SUBTESTS=() + +# only if supported (or forced) and not disabled, see no-color.org +if { [ -t 1 ] || [ "${SELFTESTS_MPTCP_LIB_COLOR_FORCE:-}" = "1" ]; } && + [ "${NO_COLOR:-}" != "1" ]; then + readonly MPTCP_LIB_COLOR_RED="\E[1;31m" + readonly MPTCP_LIB_COLOR_GREEN="\E[1;32m" + readonly MPTCP_LIB_COLOR_YELLOW="\E[1;33m" + readonly MPTCP_LIB_COLOR_BLUE="\E[1;34m" + readonly MPTCP_LIB_COLOR_RESET="\E[0m" +else + readonly MPTCP_LIB_COLOR_RED= + readonly MPTCP_LIB_COLOR_GREEN= + readonly MPTCP_LIB_COLOR_YELLOW= + readonly MPTCP_LIB_COLOR_BLUE= + readonly MPTCP_LIB_COLOR_RESET= +fi + +# $1: color, $2: text +mptcp_lib_print_color() { + echo -e "${MPTCP_LIB_START_PRINT:-}${*}${MPTCP_LIB_COLOR_RESET}" +} + +mptcp_lib_print_ok() { + mptcp_lib_print_color "${MPTCP_LIB_COLOR_GREEN}${*}" +} + +mptcp_lib_print_warn() { + mptcp_lib_print_color "${MPTCP_LIB_COLOR_YELLOW}${*}" +} + +mptcp_lib_print_info() { + mptcp_lib_print_color "${MPTCP_LIB_COLOR_BLUE}${*}" +} + +mptcp_lib_print_err() { + mptcp_lib_print_color "${MPTCP_LIB_COLOR_RED}${*}" +} + # SELFTESTS_MPTCP_LIB_EXPECT_ALL_FEATURES env var can be set when validating all # features using the last version of the kernel and the selftests to make sure # a test is not being skipped by mistake. @@ -102,3 +145,65 @@ mptcp_lib_kversion_ge() { mptcp_lib_fail_if_expected_feature "kernel version ${1} lower than ${v}" } + +__mptcp_lib_result_add() { + local result="${1}" + shift + + local id=$((${#MPTCP_LIB_SUBTESTS[@]} + 1)) + + MPTCP_LIB_SUBTESTS+=("${result} ${id} - ${KSFT_TEST}: ${*}") +} + +# $1: test name +mptcp_lib_result_pass() { + __mptcp_lib_result_add "ok" "${1}" +} + +# $1: test name +mptcp_lib_result_fail() { + __mptcp_lib_result_add "not ok" "${1}" +} + +# $1: test name +mptcp_lib_result_skip() { + __mptcp_lib_result_add "ok" "${1} # SKIP" +} + +# $1: result code ; $2: test name +mptcp_lib_result_code() { + local ret="${1}" + local name="${2}" + + case "${ret}" in + "${KSFT_PASS}") + mptcp_lib_result_pass "${name}" + ;; + "${KSFT_FAIL}") + mptcp_lib_result_fail "${name}" + ;; + "${KSFT_SKIP}") + mptcp_lib_result_skip "${name}" + ;; + *) + echo "ERROR: wrong result code: ${ret}" + exit ${KSFT_FAIL} + ;; + esac +} + +mptcp_lib_result_print_all_tap() { + local subtest + + if [ ${#MPTCP_LIB_SUBTESTS[@]} -eq 0 ] || + [ "${SELFTESTS_MPTCP_LIB_NO_TAP:-}" = "1" ]; then + return + fi + + printf "\nTAP version 13\n" + printf "1..%d\n" "${#MPTCP_LIB_SUBTESTS[@]}" + + for subtest in "${MPTCP_LIB_SUBTESTS[@]}"; do + printf "%s\n" "${subtest}" + done +} diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh index dc8d473fc82c..8c8694f21e7d 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh @@ -183,11 +183,13 @@ do_transfer() local mptcp_connect="./mptcp_connect -r 20" - local local_addr + local local_addr ip if is_v6 "${connect_addr}"; then local_addr="::" + ip=ipv6 else local_addr="0.0.0.0" + ip=ipv4 fi cmsg="TIMESTAMPNS" @@ -223,6 +225,8 @@ do_transfer() echo -e "\nnetns ${connector_ns} socket stat for ${port}:" 1>&2 ip netns exec ${connector_ns} ss -Menita 1>&2 -o "dport = :$port" + mptcp_lib_result_fail "transfer ${ip}" + ret=1 return 1 fi @@ -236,9 +240,11 @@ do_transfer() fi check_transfer $cin $sout "file received by server" - rets=$? + mptcp_lib_result_code "${retc}" "mark ${ip}" + mptcp_lib_result_code "${rets}" "transfer ${ip}" + if [ $retc -eq 0 ] && [ $rets -eq 0 ];then return 0 fi @@ -264,6 +270,7 @@ do_mptcp_sockopt_tests() if ! mptcp_lib_kallsyms_has "mptcp_diag_fill_info$"; then echo "INFO: MPTCP sockopt not supported: SKIP" + mptcp_lib_result_skip "sockopt" return fi @@ -272,18 +279,22 @@ do_mptcp_sockopt_tests() if [ $lret -ne 0 ]; then echo "FAIL: SOL_MPTCP getsockopt" 1>&2 + mptcp_lib_result_fail "sockopt v4" ret=$lret return fi + mptcp_lib_result_pass "sockopt v4" ip netns exec "$ns_sbox" ./mptcp_sockopt -6 lret=$? if [ $lret -ne 0 ]; then echo "FAIL: SOL_MPTCP getsockopt (ipv6)" 1>&2 + mptcp_lib_result_fail "sockopt v6" ret=$lret return fi + mptcp_lib_result_pass "sockopt v6" } run_tests() @@ -310,10 +321,12 @@ do_tcpinq_test() if [ $lret -ne 0 ];then ret=$lret echo "FAIL: mptcp_inq $@" 1>&2 + mptcp_lib_result_fail "TCP_INQ: $*" return $lret fi echo "PASS: TCP_INQ cmsg/ioctl $@" + mptcp_lib_result_pass "TCP_INQ: $*" return $lret } @@ -323,6 +336,7 @@ do_tcpinq_tests() if ! mptcp_lib_kallsyms_has "mptcp_ioctl$"; then echo "INFO: TCP_INQ not supported: SKIP" + mptcp_lib_result_skip "TCP_INQ" return fi @@ -367,4 +381,6 @@ if [ $ret -eq 0 ];then fi do_tcpinq_tests + +mptcp_lib_result_print_all_tap exit $ret diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh index d02e0d63a8f9..8f4ff123a7eb 100755 --- a/tools/testing/selftests/net/mptcp/pm_netlink.sh +++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh @@ -58,16 +58,19 @@ check() local out=`$cmd 2>$err` local cmd_ret=$? - printf "%-50s %s" "$msg" + printf "%-50s" "$msg" if [ $cmd_ret -ne 0 ]; then echo "[FAIL] command execution '$cmd' stderr " cat $err + mptcp_lib_result_fail "${msg} # error ${cmd_ret}" ret=1 elif [ "$out" = "$expected" ]; then echo "[ OK ]" + mptcp_lib_result_pass "${msg}" else echo -n "[FAIL] " echo "expected '$expected' got '$out'" + mptcp_lib_result_fail "${msg} # different output" ret=1 fi } @@ -96,7 +99,7 @@ check "ip netns exec $ns1 ./pm_nl_ctl dump" \ "id 1 flags 10.0.1.1 id 3 flags signal,backup 10.0.1.3" "dump addrs after del" -ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.3 +ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.3 2>/dev/null check "ip netns exec $ns1 ./pm_nl_ctl get 4" "" "duplicate addr" ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.4 flags signal @@ -124,10 +127,10 @@ id 8 flags signal 10.0.1.8" "id limit" ip netns exec $ns1 ./pm_nl_ctl flush check "ip netns exec $ns1 ./pm_nl_ctl dump" "" "flush addrs" -ip netns exec $ns1 ./pm_nl_ctl limits 9 1 +ip netns exec $ns1 ./pm_nl_ctl limits 9 1 2>/dev/null check "ip netns exec $ns1 ./pm_nl_ctl limits" "$default_limits" "rcv addrs above hard limit" -ip netns exec $ns1 ./pm_nl_ctl limits 1 9 +ip netns exec $ns1 ./pm_nl_ctl limits 1 9 2>/dev/null check "ip netns exec $ns1 ./pm_nl_ctl limits" "$default_limits" "subflows above hard limit" ip netns exec $ns1 ./pm_nl_ctl limits 8 8 @@ -193,4 +196,5 @@ subflow 10.0.1.1" " (nofullmesh)" subflow,backup,fullmesh 10.0.1.1" " (backup,fullmesh)" fi +mptcp_lib_result_print_all_tap exit $ret diff --git a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c index 1887bd61bd9a..49369c4a5f26 100644 --- a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c +++ b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c @@ -66,20 +66,25 @@ static int init_genl_req(char *data, int family, int cmd, int version) return off; } -static void nl_error(struct nlmsghdr *nh) +static int nl_error(struct nlmsghdr *nh) { struct nlmsgerr *err = (struct nlmsgerr *)NLMSG_DATA(nh); int len = nh->nlmsg_len - sizeof(*nh); uint32_t off; - if (len < sizeof(struct nlmsgerr)) + if (len < sizeof(struct nlmsgerr)) { error(1, 0, "netlink error message truncated %d min %ld", len, sizeof(struct nlmsgerr)); + return -1; + } - if (!err->error) { + if (err->error) { /* check messages from kernel */ struct rtattr *attrs = (struct rtattr *)NLMSG_DATA(nh); + fprintf(stderr, "netlink error %d (%s)\n", + err->error, strerror(-err->error)); + while (RTA_OK(attrs, len)) { if (attrs->rta_type == NLMSGERR_ATTR_MSG) fprintf(stderr, "netlink ext ack msg: %s\n", @@ -91,9 +96,10 @@ static void nl_error(struct nlmsghdr *nh) } attrs = RTA_NEXT(attrs, len); } - } else { - fprintf(stderr, "netlink error %d", err->error); + return -1; } + + return 0; } static int capture_events(int fd, int event_group) @@ -198,7 +204,7 @@ static int capture_events(int fd, int event_group) return 0; } -/* do a netlink command and, if max > 0, fetch the reply */ +/* do a netlink command and, if max > 0, fetch the reply ; nh's size >1024B */ static int do_nl_req(int fd, struct nlmsghdr *nh, int len, int max) { struct sockaddr_nl nladdr = { .nl_family = AF_NETLINK }; @@ -207,12 +213,16 @@ static int do_nl_req(int fd, struct nlmsghdr *nh, int len, int max) int rem, ret; int err = 0; + /* If no expected answer, ask for an ACK to look for errors if any */ + if (max == 0) { + nh->nlmsg_flags |= NLM_F_ACK; + max = 1024; + } + nh->nlmsg_len = len; ret = sendto(fd, data, len, 0, (void *)&nladdr, sizeof(nladdr)); if (ret != len) error(1, errno, "send netlink: %uB != %uB\n", ret, len); - if (max == 0) - return 0; addr_len = sizeof(nladdr); rem = ret = recvfrom(fd, data, max, 0, (void *)&nladdr, &addr_len); @@ -221,10 +231,11 @@ static int do_nl_req(int fd, struct nlmsghdr *nh, int len, int max) /* Beware: the NLMSG_NEXT macro updates the 'rem' argument */ for (; NLMSG_OK(nh, rem); nh = NLMSG_NEXT(nh, rem)) { - if (nh->nlmsg_type == NLMSG_ERROR) { - nl_error(nh); + if (nh->nlmsg_type == NLMSG_DONE) + break; + + if (nh->nlmsg_type == NLMSG_ERROR && nl_error(nh)) err = 1; - } } if (err) error(1, 0, "bailing out due to netlink error[s]"); diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh index 36a3c9d92e20..ce9203b817f8 100755 --- a/tools/testing/selftests/net/mptcp/simult_flows.sh +++ b/tools/testing/selftests/net/mptcp/simult_flows.sh @@ -261,6 +261,7 @@ run_test() printf "%-60s" "$msg" do_transfer $small $large $time lret=$? + mptcp_lib_result_code "${lret}" "${msg}" if [ $lret -ne 0 ]; then ret=$lret [ $bail -eq 0 ] || exit $ret @@ -269,6 +270,7 @@ run_test() printf "%-60s" "$msg - reverse direction" do_transfer $large $small $time lret=$? + mptcp_lib_result_code "${lret}" "${msg}" if [ $lret -ne 0 ]; then ret=$lret [ $bail -eq 0 ] || exit $ret @@ -305,4 +307,6 @@ run_test 10 10 1 50 "balanced bwidth with unbalanced delay" run_test 30 10 0 0 "unbalanced bwidth" run_test 30 10 1 50 "unbalanced bwidth with unbalanced delay" run_test 30 10 50 1 "unbalanced bwidth with opposed, unbalanced delay" + +mptcp_lib_result_print_all_tap exit $ret diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh index b180133a30af..b25a3e33eb25 100755 --- a/tools/testing/selftests/net/mptcp/userspace_pm.sh +++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh @@ -1,6 +1,13 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +# Double quotes to prevent globbing and word splitting is recommended in new +# code but we accept it. +#shellcheck disable=SC2086 + +# Some variables are used below but indirectly, see check_expected_one() +#shellcheck disable=SC2034 + . "$(dirname "${0}")/mptcp_lib.sh" mptcp_lib_check_mptcp @@ -11,8 +18,7 @@ if ! mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then exit ${KSFT_SKIP} fi -ip -Version > /dev/null 2>&1 -if [ $? -ne 0 ];then +if ! ip -Version &> /dev/null; then echo "SKIP: Cannot not run test without ip tool" exit ${KSFT_SKIP} fi @@ -52,10 +58,54 @@ sec=$(date +%s) rndh=$(printf %x "$sec")-$(mktemp -u XXXXXX) ns1="ns1-$rndh" ns2="ns2-$rndh" +ret=0 +test_name="" + +_printf() { + stdbuf -o0 -e0 printf "${@}" +} print_title() { - stdbuf -o0 -e0 printf "INFO: %s\n" "${1}" + _printf "INFO: %s\n" "${1}" +} + +# $1: test name +print_test() +{ + test_name="${1}" + + _printf "%-63s" "${test_name}" +} + +print_results() +{ + _printf "[%s]\n" "${1}" +} + +test_pass() +{ + print_results " OK " + mptcp_lib_result_pass "${test_name}" +} + +test_skip() +{ + print_results "SKIP" + mptcp_lib_result_skip "${test_name}" +} + +# $1: msg +test_fail() +{ + print_results "FAIL" + ret=1 + + if [ -n "${1}" ]; then + _printf "\t%s\n" "${1}" + fi + + mptcp_lib_result_fail "${test_name}" } kill_wait() @@ -67,6 +117,8 @@ kill_wait() wait $1 2>/dev/null } +# This function is used in the cleanup trap +#shellcheck disable=SC2317 cleanup() { print_title "Cleanup" @@ -86,7 +138,7 @@ cleanup() rm -rf $file $client_evts $server_evts - stdbuf -o0 -e0 printf "Done\n" + _printf "Done\n" } trap cleanup EXIT @@ -118,7 +170,8 @@ ip -net "$ns2" addr add dead:beef:2::2/64 dev ns2eth1 nodad ip -net "$ns2" link set ns2eth1 up print_title "Init" -stdbuf -o0 -e0 printf "Created network namespaces ns1, ns2 \t\t\t[OK]\n" +print_test "Created network namespaces ns1, ns2" +test_pass make_file() { @@ -203,16 +256,14 @@ make_connection() server_serverside=$(grep "type:1," "$server_evts" | sed --unbuffered -n 's/.*\(server_side:\)\([[:digit:]]*\).*$/\2/p;q') - stdbuf -o0 -e0 printf "Established IP%s MPTCP Connection ns2 => ns1 \t\t" $is_v6 + print_test "Established IP${is_v6} MPTCP Connection ns2 => ns1" if [ "$client_token" != "" ] && [ "$server_token" != "" ] && [ "$client_serverside" = 0 ] && [ "$server_serverside" = 1 ] then - stdbuf -o0 -e0 printf "[OK]\n" + test_pass else - stdbuf -o0 -e0 printf "[FAIL]\n" - stdbuf -o0 -e0 printf "\tExpected tokens (c:%s - s:%s) and server (c:%d - s:%d)\n" \ - "${client_token}" "${server_token}" \ - "${client_serverside}" "${server_serverside}" + test_fail "Expected tokens (c:${client_token} - s:${server_token}) and server (c:${client_serverside} - s:${server_serverside})" + mptcp_lib_result_print_all_tap exit 1 fi @@ -246,10 +297,10 @@ check_expected_one() if [ "${prev_ret}" = "0" ] then - stdbuf -o0 -e0 printf "[FAIL]\n" + test_fail fi - stdbuf -o0 -e0 printf "\tExpected value for '%s': '%s', got '%s'.\n" \ + _printf "\tExpected value for '%s': '%s', got '%s'.\n" \ "${var}" "${!exp}" "${!var}" return 1 } @@ -257,21 +308,21 @@ check_expected_one() # $@: all var names to check check_expected() { - local ret=0 + local rc=0 local var for var in "${@}" do - check_expected_one "${var}" "${ret}" || ret=1 + check_expected_one "${var}" "${rc}" || rc=1 done - if [ ${ret} -eq 0 ] + if [ ${rc} -eq 0 ] then - stdbuf -o0 -e0 printf "[OK]\n" + test_pass return 0 fi - exit 1 + return 1 } verify_announce_event() @@ -317,21 +368,20 @@ test_announce() local type type=$(sed --unbuffered -n 's/.*\(type:\)\([[:digit:]]*\).*$/\2/p;q' "$server_evts") - stdbuf -o0 -e0 printf "ADD_ADDR 10.0.2.2 (ns2) => ns1, invalid token \t\t" + print_test "ADD_ADDR 10.0.2.2 (ns2) => ns1, invalid token" if [ "$type" = "" ] then - stdbuf -o0 -e0 printf "[OK]\n" + test_pass else - stdbuf -o0 -e0 printf "[FAIL]\n\ttype defined: %s\n" "${type}" - exit 1 + test_fail "type defined: ${type}" fi # ADD_ADDR from the client to server machine reusing the subflow port :>"$server_evts" ip netns exec "$ns2"\ ./pm_nl_ctl ann 10.0.2.2 token "$client4_token" id $client_addr_id dev\ - ns2eth1 > /dev/null 2>&1 - stdbuf -o0 -e0 printf "ADD_ADDR id:%d 10.0.2.2 (ns2) => ns1, reuse port \t\t" $client_addr_id + ns2eth1 + print_test "ADD_ADDR id:${client_addr_id} 10.0.2.2 (ns2) => ns1, reuse port" sleep 0.5 verify_announce_event $server_evts $ANNOUNCED $server4_token "10.0.2.2" $client_addr_id \ "$client4_port" @@ -339,8 +389,8 @@ test_announce() # ADD_ADDR6 from the client to server machine reusing the subflow port :>"$server_evts" ip netns exec "$ns2" ./pm_nl_ctl ann\ - dead:beef:2::2 token "$client6_token" id $client_addr_id dev ns2eth1 > /dev/null 2>&1 - stdbuf -o0 -e0 printf "ADD_ADDR6 id:%d dead:beef:2::2 (ns2) => ns1, reuse port\t\t" $client_addr_id + dead:beef:2::2 token "$client6_token" id $client_addr_id dev ns2eth1 + print_test "ADD_ADDR6 id:${client_addr_id} dead:beef:2::2 (ns2) => ns1, reuse port" sleep 0.5 verify_announce_event "$server_evts" "$ANNOUNCED" "$server6_token" "dead:beef:2::2"\ "$client_addr_id" "$client6_port" "v6" @@ -349,8 +399,8 @@ test_announce() :>"$server_evts" client_addr_id=$((client_addr_id+1)) ip netns exec "$ns2" ./pm_nl_ctl ann 10.0.2.2 token "$client4_token" id\ - $client_addr_id dev ns2eth1 port $new4_port > /dev/null 2>&1 - stdbuf -o0 -e0 printf "ADD_ADDR id:%d 10.0.2.2 (ns2) => ns1, new port \t\t\t" $client_addr_id + $client_addr_id dev ns2eth1 port $new4_port + print_test "ADD_ADDR id:${client_addr_id} 10.0.2.2 (ns2) => ns1, new port" sleep 0.5 verify_announce_event "$server_evts" "$ANNOUNCED" "$server4_token" "10.0.2.2"\ "$client_addr_id" "$new4_port" @@ -360,8 +410,8 @@ test_announce() # ADD_ADDR from the server to client machine reusing the subflow port ip netns exec "$ns1" ./pm_nl_ctl ann 10.0.2.1 token "$server4_token" id\ - $server_addr_id dev ns1eth2 > /dev/null 2>&1 - stdbuf -o0 -e0 printf "ADD_ADDR id:%d 10.0.2.1 (ns1) => ns2, reuse port \t\t" $server_addr_id + $server_addr_id dev ns1eth2 + print_test "ADD_ADDR id:${server_addr_id} 10.0.2.1 (ns1) => ns2, reuse port" sleep 0.5 verify_announce_event "$client_evts" "$ANNOUNCED" "$client4_token" "10.0.2.1"\ "$server_addr_id" "$app4_port" @@ -369,8 +419,8 @@ test_announce() # ADD_ADDR6 from the server to client machine reusing the subflow port :>"$client_evts" ip netns exec "$ns1" ./pm_nl_ctl ann dead:beef:2::1 token "$server6_token" id\ - $server_addr_id dev ns1eth2 > /dev/null 2>&1 - stdbuf -o0 -e0 printf "ADD_ADDR6 id:%d dead:beef:2::1 (ns1) => ns2, reuse port\t\t" $server_addr_id + $server_addr_id dev ns1eth2 + print_test "ADD_ADDR6 id:${server_addr_id} dead:beef:2::1 (ns1) => ns2, reuse port" sleep 0.5 verify_announce_event "$client_evts" "$ANNOUNCED" "$client6_token" "dead:beef:2::1"\ "$server_addr_id" "$app6_port" "v6" @@ -379,8 +429,8 @@ test_announce() :>"$client_evts" server_addr_id=$((server_addr_id+1)) ip netns exec "$ns1" ./pm_nl_ctl ann 10.0.2.1 token "$server4_token" id\ - $server_addr_id dev ns1eth2 port $new4_port > /dev/null 2>&1 - stdbuf -o0 -e0 printf "ADD_ADDR id:%d 10.0.2.1 (ns1) => ns2, new port \t\t\t" $server_addr_id + $server_addr_id dev ns1eth2 port $new4_port + print_test "ADD_ADDR id:${server_addr_id} 10.0.2.1 (ns1) => ns2, new port" sleep 0.5 verify_announce_event "$client_evts" "$ANNOUNCED" "$client4_token" "10.0.2.1"\ "$server_addr_id" "$new4_port" @@ -414,39 +464,34 @@ test_remove() local invalid_token=$(( client4_token - 1 )) ip netns exec "$ns2" ./pm_nl_ctl rem token $invalid_token id\ $client_addr_id > /dev/null 2>&1 - stdbuf -o0 -e0 printf "RM_ADDR id:%d ns2 => ns1, invalid token \t"\ - $client_addr_id + print_test "RM_ADDR id:${client_addr_id} ns2 => ns1, invalid token" local type type=$(sed --unbuffered -n 's/.*\(type:\)\([[:digit:]]*\).*$/\2/p;q' "$server_evts") if [ "$type" = "" ] then - stdbuf -o0 -e0 printf "[OK]\n" + test_pass else - stdbuf -o0 -e0 printf "[FAIL]\n" - exit 1 + test_fail fi # RM_ADDR using an invalid addr id should result in no action local invalid_id=$(( client_addr_id + 1 )) ip netns exec "$ns2" ./pm_nl_ctl rem token "$client4_token" id\ $invalid_id > /dev/null 2>&1 - stdbuf -o0 -e0 printf "RM_ADDR id:%d ns2 => ns1, invalid id \t"\ - $invalid_id + print_test "RM_ADDR id:${invalid_id} ns2 => ns1, invalid id" type=$(sed --unbuffered -n 's/.*\(type:\)\([[:digit:]]*\).*$/\2/p;q' "$server_evts") if [ "$type" = "" ] then - stdbuf -o0 -e0 printf "[OK]\n" + test_pass else - stdbuf -o0 -e0 printf "[FAIL]\n" - exit 1 + test_fail fi # RM_ADDR from the client to server machine :>"$server_evts" ip netns exec "$ns2" ./pm_nl_ctl rem token "$client4_token" id\ - $client_addr_id > /dev/null 2>&1 - stdbuf -o0 -e0 printf "RM_ADDR id:%d ns2 => ns1 \t"\ - $client_addr_id + $client_addr_id + print_test "RM_ADDR id:${client_addr_id} ns2 => ns1" sleep 0.5 verify_remove_event "$server_evts" "$REMOVED" "$server4_token" "$client_addr_id" @@ -454,18 +499,16 @@ test_remove() :>"$server_evts" client_addr_id=$(( client_addr_id - 1 )) ip netns exec "$ns2" ./pm_nl_ctl rem token "$client4_token" id\ - $client_addr_id > /dev/null 2>&1 - stdbuf -o0 -e0 printf "RM_ADDR id:%d ns2 => ns1 \t"\ - $client_addr_id + $client_addr_id + print_test "RM_ADDR id:${client_addr_id} ns2 => ns1" sleep 0.5 verify_remove_event "$server_evts" "$REMOVED" "$server4_token" "$client_addr_id" # RM_ADDR6 from the client to server machine :>"$server_evts" ip netns exec "$ns2" ./pm_nl_ctl rem token "$client6_token" id\ - $client_addr_id > /dev/null 2>&1 - stdbuf -o0 -e0 printf "RM_ADDR6 id:%d ns2 => ns1 \t"\ - $client_addr_id + $client_addr_id + print_test "RM_ADDR6 id:${client_addr_id} ns2 => ns1" sleep 0.5 verify_remove_event "$server_evts" "$REMOVED" "$server6_token" "$client_addr_id" @@ -474,9 +517,8 @@ test_remove() # RM_ADDR from the server to client machine ip netns exec "$ns1" ./pm_nl_ctl rem token "$server4_token" id\ - $server_addr_id > /dev/null 2>&1 - stdbuf -o0 -e0 printf "RM_ADDR id:%d ns1 => ns2 \t"\ - $server_addr_id + $server_addr_id + print_test "RM_ADDR id:${server_addr_id} ns1 => ns2" sleep 0.5 verify_remove_event "$client_evts" "$REMOVED" "$client4_token" "$server_addr_id" @@ -484,16 +526,16 @@ test_remove() :>"$client_evts" server_addr_id=$(( server_addr_id - 1 )) ip netns exec "$ns1" ./pm_nl_ctl rem token "$server4_token" id\ - $server_addr_id > /dev/null 2>&1 - stdbuf -o0 -e0 printf "RM_ADDR id:%d ns1 => ns2 \t" $server_addr_id + $server_addr_id + print_test "RM_ADDR id:${server_addr_id} ns1 => ns2" sleep 0.5 verify_remove_event "$client_evts" "$REMOVED" "$client4_token" "$server_addr_id" # RM_ADDR6 from the server to client machine :>"$client_evts" ip netns exec "$ns1" ./pm_nl_ctl rem token "$server6_token" id\ - $server_addr_id > /dev/null 2>&1 - stdbuf -o0 -e0 printf "RM_ADDR6 id:%d ns1 => ns2 \t" $server_addr_id + $server_addr_id + print_test "RM_ADDR6 id:${server_addr_id} ns1 => ns2" sleep 0.5 verify_remove_event "$client_evts" "$REMOVED" "$client6_token" "$server_addr_id" } @@ -520,25 +562,24 @@ verify_subflow_events() local dport local locid local remid + local info + + info="${e_saddr} (${e_from}) => ${e_daddr} (${e_to})" if [ "$e_type" = "$SUB_ESTABLISHED" ] then if [ "$e_family" = "$AF_INET6" ] then - stdbuf -o0 -e0 printf "CREATE_SUBFLOW6 %s (%s) => %s (%s) "\ - "$e_saddr" "$e_from" "$e_daddr" "$e_to" + print_test "CREATE_SUBFLOW6 ${info}" else - stdbuf -o0 -e0 printf "CREATE_SUBFLOW %s (%s) => %s (%s) \t"\ - "$e_saddr" "$e_from" "$e_daddr" "$e_to" + print_test "CREATE_SUBFLOW ${info}" fi else if [ "$e_family" = "$AF_INET6" ] then - stdbuf -o0 -e0 printf "DESTROY_SUBFLOW6 %s (%s) => %s (%s) "\ - "$e_saddr" "$e_from" "$e_daddr" "$e_to" + print_test "DESTROY_SUBFLOW6 ${info}" else - stdbuf -o0 -e0 printf "DESTROY_SUBFLOW %s (%s) => %s (%s) \t"\ - "$e_saddr" "$e_from" "$e_daddr" "$e_to" + print_test "DESTROY_SUBFLOW ${info}" fi fi @@ -569,18 +610,18 @@ test_subflows() # Attempt to add a listener at 10.0.2.2:<subflow-port> ip netns exec "$ns2" ./pm_nl_ctl listen 10.0.2.2\ - "$client4_port" > /dev/null 2>&1 & + "$client4_port" & local listener_pid=$! # ADD_ADDR from client to server machine reusing the subflow port ip netns exec "$ns2" ./pm_nl_ctl ann 10.0.2.2 token "$client4_token" id\ - $client_addr_id > /dev/null 2>&1 + $client_addr_id sleep 0.5 # CREATE_SUBFLOW from server to client machine :>"$server_evts" ip netns exec "$ns1" ./pm_nl_ctl csf lip 10.0.2.1 lid 23 rip 10.0.2.2\ - rport "$client4_port" token "$server4_token" > /dev/null 2>&1 + rport "$client4_port" token "$server4_token" sleep 0.5 verify_subflow_events $server_evts $SUB_ESTABLISHED $server4_token $AF_INET "10.0.2.1" \ "10.0.2.2" "$client4_port" "23" "$client_addr_id" "ns1" "ns2" @@ -594,31 +635,31 @@ test_subflows() # DESTROY_SUBFLOW from server to client machine :>"$server_evts" ip netns exec "$ns1" ./pm_nl_ctl dsf lip 10.0.2.1 lport "$sport" rip 10.0.2.2 rport\ - "$client4_port" token "$server4_token" > /dev/null 2>&1 + "$client4_port" token "$server4_token" sleep 0.5 verify_subflow_events "$server_evts" "$SUB_CLOSED" "$server4_token" "$AF_INET" "10.0.2.1"\ "10.0.2.2" "$client4_port" "23" "$client_addr_id" "ns1" "ns2" # RM_ADDR from client to server machine ip netns exec "$ns2" ./pm_nl_ctl rem id $client_addr_id token\ - "$client4_token" > /dev/null 2>&1 + "$client4_token" sleep 0.5 # Attempt to add a listener at dead:beef:2::2:<subflow-port> ip netns exec "$ns2" ./pm_nl_ctl listen dead:beef:2::2\ - "$client6_port" > /dev/null 2>&1 & + "$client6_port" & listener_pid=$! # ADD_ADDR6 from client to server machine reusing the subflow port :>"$server_evts" ip netns exec "$ns2" ./pm_nl_ctl ann dead:beef:2::2 token "$client6_token" id\ - $client_addr_id > /dev/null 2>&1 + $client_addr_id sleep 0.5 # CREATE_SUBFLOW6 from server to client machine :>"$server_evts" ip netns exec "$ns1" ./pm_nl_ctl csf lip dead:beef:2::1 lid 23 rip\ - dead:beef:2::2 rport "$client6_port" token "$server6_token" > /dev/null 2>&1 + dead:beef:2::2 rport "$client6_port" token "$server6_token" sleep 0.5 verify_subflow_events "$server_evts" "$SUB_ESTABLISHED" "$server6_token" "$AF_INET6"\ "dead:beef:2::1" "dead:beef:2::2" "$client6_port" "23"\ @@ -632,7 +673,7 @@ test_subflows() # DESTROY_SUBFLOW6 from server to client machine :>"$server_evts" ip netns exec "$ns1" ./pm_nl_ctl dsf lip dead:beef:2::1 lport "$sport" rip\ - dead:beef:2::2 rport "$client6_port" token "$server6_token" > /dev/null 2>&1 + dead:beef:2::2 rport "$client6_port" token "$server6_token" sleep 0.5 verify_subflow_events "$server_evts" "$SUB_CLOSED" "$server6_token" "$AF_INET6"\ "dead:beef:2::1" "dead:beef:2::2" "$client6_port" "23"\ @@ -640,24 +681,24 @@ test_subflows() # RM_ADDR from client to server machine ip netns exec "$ns2" ./pm_nl_ctl rem id $client_addr_id token\ - "$client6_token" > /dev/null 2>&1 + "$client6_token" sleep 0.5 # Attempt to add a listener at 10.0.2.2:<new-port> ip netns exec "$ns2" ./pm_nl_ctl listen 10.0.2.2\ - $new4_port > /dev/null 2>&1 & + $new4_port & listener_pid=$! # ADD_ADDR from client to server machine using a new port :>"$server_evts" ip netns exec "$ns2" ./pm_nl_ctl ann 10.0.2.2 token "$client4_token" id\ - $client_addr_id port $new4_port > /dev/null 2>&1 + $client_addr_id port $new4_port sleep 0.5 # CREATE_SUBFLOW from server to client machine :>"$server_evts" ip netns exec "$ns1" ./pm_nl_ctl csf lip 10.0.2.1 lid 23 rip 10.0.2.2 rport\ - $new4_port token "$server4_token" > /dev/null 2>&1 + $new4_port token "$server4_token" sleep 0.5 verify_subflow_events "$server_evts" "$SUB_ESTABLISHED" "$server4_token" "$AF_INET"\ "10.0.2.1" "10.0.2.2" "$new4_port" "23"\ @@ -671,32 +712,32 @@ test_subflows() # DESTROY_SUBFLOW from server to client machine :>"$server_evts" ip netns exec "$ns1" ./pm_nl_ctl dsf lip 10.0.2.1 lport "$sport" rip 10.0.2.2 rport\ - $new4_port token "$server4_token" > /dev/null 2>&1 + $new4_port token "$server4_token" sleep 0.5 verify_subflow_events "$server_evts" "$SUB_CLOSED" "$server4_token" "$AF_INET" "10.0.2.1"\ "10.0.2.2" "$new4_port" "23" "$client_addr_id" "ns1" "ns2" # RM_ADDR from client to server machine ip netns exec "$ns2" ./pm_nl_ctl rem id $client_addr_id token\ - "$client4_token" > /dev/null 2>&1 + "$client4_token" # Capture events on the network namespace running the client :>"$client_evts" # Attempt to add a listener at 10.0.2.1:<subflow-port> ip netns exec "$ns1" ./pm_nl_ctl listen 10.0.2.1\ - $app4_port > /dev/null 2>&1 & + $app4_port & listener_pid=$! # ADD_ADDR from server to client machine reusing the subflow port ip netns exec "$ns1" ./pm_nl_ctl ann 10.0.2.1 token "$server4_token" id\ - $server_addr_id > /dev/null 2>&1 + $server_addr_id sleep 0.5 # CREATE_SUBFLOW from client to server machine :>"$client_evts" ip netns exec "$ns2" ./pm_nl_ctl csf lip 10.0.2.2 lid 23 rip 10.0.2.1 rport\ - $app4_port token "$client4_token" > /dev/null 2>&1 + $app4_port token "$client4_token" sleep 0.5 verify_subflow_events $client_evts $SUB_ESTABLISHED $client4_token $AF_INET "10.0.2.2"\ "10.0.2.1" "$app4_port" "23" "$server_addr_id" "ns2" "ns1" @@ -709,31 +750,31 @@ test_subflows() # DESTROY_SUBFLOW from client to server machine :>"$client_evts" ip netns exec "$ns2" ./pm_nl_ctl dsf lip 10.0.2.2 lport "$sport" rip 10.0.2.1 rport\ - $app4_port token "$client4_token" > /dev/null 2>&1 + $app4_port token "$client4_token" sleep 0.5 verify_subflow_events "$client_evts" "$SUB_CLOSED" "$client4_token" "$AF_INET" "10.0.2.2"\ "10.0.2.1" "$app4_port" "23" "$server_addr_id" "ns2" "ns1" # RM_ADDR from server to client machine ip netns exec "$ns1" ./pm_nl_ctl rem id $server_addr_id token\ - "$server4_token" > /dev/null 2>&1 + "$server4_token" sleep 0.5 # Attempt to add a listener at dead:beef:2::1:<subflow-port> ip netns exec "$ns1" ./pm_nl_ctl listen dead:beef:2::1\ - $app6_port > /dev/null 2>&1 & + $app6_port & listener_pid=$! # ADD_ADDR6 from server to client machine reusing the subflow port :>"$client_evts" ip netns exec "$ns1" ./pm_nl_ctl ann dead:beef:2::1 token "$server6_token" id\ - $server_addr_id > /dev/null 2>&1 + $server_addr_id sleep 0.5 # CREATE_SUBFLOW6 from client to server machine :>"$client_evts" ip netns exec "$ns2" ./pm_nl_ctl csf lip dead:beef:2::2 lid 23 rip\ - dead:beef:2::1 rport $app6_port token "$client6_token" > /dev/null 2>&1 + dead:beef:2::1 rport $app6_port token "$client6_token" sleep 0.5 verify_subflow_events "$client_evts" "$SUB_ESTABLISHED" "$client6_token"\ "$AF_INET6" "dead:beef:2::2"\ @@ -748,31 +789,31 @@ test_subflows() # DESTROY_SUBFLOW6 from client to server machine :>"$client_evts" ip netns exec "$ns2" ./pm_nl_ctl dsf lip dead:beef:2::2 lport "$sport" rip\ - dead:beef:2::1 rport $app6_port token "$client6_token" > /dev/null 2>&1 + dead:beef:2::1 rport $app6_port token "$client6_token" sleep 0.5 verify_subflow_events $client_evts $SUB_CLOSED $client6_token $AF_INET6 "dead:beef:2::2"\ "dead:beef:2::1" "$app6_port" "23" "$server_addr_id" "ns2" "ns1" # RM_ADDR6 from server to client machine ip netns exec "$ns1" ./pm_nl_ctl rem id $server_addr_id token\ - "$server6_token" > /dev/null 2>&1 + "$server6_token" sleep 0.5 # Attempt to add a listener at 10.0.2.1:<new-port> ip netns exec "$ns1" ./pm_nl_ctl listen 10.0.2.1\ - $new4_port > /dev/null 2>&1 & + $new4_port & listener_pid=$! # ADD_ADDR from server to client machine using a new port :>"$client_evts" ip netns exec "$ns1" ./pm_nl_ctl ann 10.0.2.1 token "$server4_token" id\ - $server_addr_id port $new4_port > /dev/null 2>&1 + $server_addr_id port $new4_port sleep 0.5 # CREATE_SUBFLOW from client to server machine :>"$client_evts" ip netns exec "$ns2" ./pm_nl_ctl csf lip 10.0.2.2 lid 23 rip 10.0.2.1 rport\ - $new4_port token "$client4_token" > /dev/null 2>&1 + $new4_port token "$client4_token" sleep 0.5 verify_subflow_events "$client_evts" "$SUB_ESTABLISHED" "$client4_token" "$AF_INET"\ "10.0.2.2" "10.0.2.1" "$new4_port" "23" "$server_addr_id" "ns2" "ns1" @@ -785,14 +826,14 @@ test_subflows() # DESTROY_SUBFLOW from client to server machine :>"$client_evts" ip netns exec "$ns2" ./pm_nl_ctl dsf lip 10.0.2.2 lport "$sport" rip 10.0.2.1 rport\ - $new4_port token "$client4_token" > /dev/null 2>&1 + $new4_port token "$client4_token" sleep 0.5 verify_subflow_events "$client_evts" "$SUB_CLOSED" "$client4_token" "$AF_INET" "10.0.2.2"\ "10.0.2.1" "$new4_port" "23" "$server_addr_id" "ns2" "ns1" # RM_ADDR from server to client machine ip netns exec "$ns1" ./pm_nl_ctl rem id $server_addr_id token\ - "$server4_token" > /dev/null 2>&1 + "$server4_token" } test_subflows_v4_v6_mix() @@ -801,15 +842,15 @@ test_subflows_v4_v6_mix() # Attempt to add a listener at 10.0.2.1:<subflow-port> ip netns exec "$ns1" ./pm_nl_ctl listen 10.0.2.1\ - $app6_port > /dev/null 2>&1 & + $app6_port & local listener_pid=$! # ADD_ADDR4 from server to client machine reusing the subflow port on # the established v6 connection :>"$client_evts" ip netns exec "$ns1" ./pm_nl_ctl ann 10.0.2.1 token "$server6_token" id\ - $server_addr_id dev ns1eth2 > /dev/null 2>&1 - stdbuf -o0 -e0 printf "ADD_ADDR4 id:%d 10.0.2.1 (ns1) => ns2, reuse port\t\t" $server_addr_id + $server_addr_id dev ns1eth2 + print_test "ADD_ADDR4 id:${server_addr_id} 10.0.2.1 (ns1) => ns2, reuse port" sleep 0.5 verify_announce_event "$client_evts" "$ANNOUNCED" "$client6_token" "10.0.2.1"\ "$server_addr_id" "$app6_port" @@ -817,7 +858,7 @@ test_subflows_v4_v6_mix() # CREATE_SUBFLOW from client to server machine :>"$client_evts" ip netns exec "$ns2" ./pm_nl_ctl csf lip 10.0.2.2 lid 23 rip 10.0.2.1 rport\ - $app6_port token "$client6_token" > /dev/null 2>&1 + $app6_port token "$client6_token" sleep 0.5 verify_subflow_events "$client_evts" "$SUB_ESTABLISHED" "$client6_token"\ "$AF_INET" "10.0.2.2" "10.0.2.1" "$app6_port" "23"\ @@ -831,7 +872,7 @@ test_subflows_v4_v6_mix() # DESTROY_SUBFLOW from client to server machine :>"$client_evts" ip netns exec "$ns2" ./pm_nl_ctl dsf lip 10.0.2.2 lport "$sport" rip 10.0.2.1 rport\ - $app6_port token "$client6_token" > /dev/null 2>&1 + $app6_port token "$client6_token" sleep 0.5 verify_subflow_events "$client_evts" "$SUB_CLOSED" "$client6_token" \ "$AF_INET" "10.0.2.2" "10.0.2.1" "$app6_port" "23"\ @@ -839,7 +880,7 @@ test_subflows_v4_v6_mix() # RM_ADDR from server to client machine ip netns exec "$ns1" ./pm_nl_ctl rem id $server_addr_id token\ - "$server6_token" > /dev/null 2>&1 + "$server6_token" sleep 0.5 } @@ -854,25 +895,23 @@ test_prio() sleep 0.5 # Check TX - stdbuf -o0 -e0 printf "MP_PRIO TX \t" + print_test "MP_PRIO TX" count=$(ip netns exec "$ns2" nstat -as | grep MPTcpExtMPPrioTx | awk '{print $2}') [ -z "$count" ] && count=0 if [ $count != 1 ]; then - stdbuf -o0 -e0 printf "[FAIL]\n\tCount != 1: %d\n" "${count}" - exit 1 + test_fail "Count != 1: ${count}" else - stdbuf -o0 -e0 printf "[OK]\n" + test_pass fi # Check RX - stdbuf -o0 -e0 printf "MP_PRIO RX \t" + print_test "MP_PRIO RX" count=$(ip netns exec "$ns1" nstat -as | grep MPTcpExtMPPrioRx | awk '{print $2}') [ -z "$count" ] && count=0 if [ $count != 1 ]; then - stdbuf -o0 -e0 printf "[FAIL]\n\tCount != 1: %d\n" "${count}" - exit 1 + test_fail "Count != 1: ${count}" else - stdbuf -o0 -e0 printf "[OK]\n" + test_pass fi } @@ -889,11 +928,9 @@ verify_listener_events() local sport if [ $e_type = $LISTENER_CREATED ]; then - stdbuf -o0 -e0 printf "CREATE_LISTENER %s:%s\t\t\t\t\t"\ - $e_saddr $e_sport + print_test "CREATE_LISTENER $e_saddr:$e_sport" elif [ $e_type = $LISTENER_CLOSED ]; then - stdbuf -o0 -e0 printf "CLOSE_LISTENER %s:%s\t\t\t\t\t"\ - $e_saddr $e_sport + print_test "CLOSE_LISTENER $e_saddr:$e_sport" fi type=$(grep "type:$e_type," $evt | @@ -918,7 +955,8 @@ test_listener() print_title "Listener tests" if ! mptcp_lib_kallsyms_has "mptcp_event_pm_listener$"; then - stdbuf -o0 -e0 printf "LISTENER events \t[SKIP] Not supported\n" + print_test "LISTENER events" + test_skip return fi @@ -927,7 +965,7 @@ test_listener() # Attempt to add a listener at 10.0.2.2:<subflow-port> ip netns exec $ns2 ./pm_nl_ctl listen 10.0.2.2\ - $client4_port > /dev/null 2>&1 & + $client4_port & local listener_pid=$! sleep 0.5 @@ -935,12 +973,12 @@ test_listener() # ADD_ADDR from client to server machine reusing the subflow port ip netns exec $ns2 ./pm_nl_ctl ann 10.0.2.2 token $client4_token id\ - $client_addr_id > /dev/null 2>&1 + $client_addr_id sleep 0.5 # CREATE_SUBFLOW from server to client machine ip netns exec $ns1 ./pm_nl_ctl csf lip 10.0.2.1 lid 23 rip 10.0.2.2\ - rport $client4_port token $server4_token > /dev/null 2>&1 + rport $client4_port token $server4_token sleep 0.5 # Delete the listener from the client ns, if one was created @@ -961,4 +999,5 @@ test_subflows_v4_v6_mix test_prio test_listener -exit 0 +mptcp_lib_result_print_all_tap +exit ${ret} diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh index 3117a4be0cd0..9c2012d70b08 100755 --- a/tools/testing/selftests/net/openvswitch/openvswitch.sh +++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh @@ -11,8 +11,13 @@ VERBOSE=0 TRACING=0 tests=" + arp_ping eth-arp: Basic arp ping between two NS + ct_connect_v4 ip4-ct-xon: Basic ipv4 tcp connection using ct + connect_v4 ip4-xon: Basic ipv4 ping between two NS + nat_connect_v4 ip4-nat-xon: Basic ipv4 tcp connection via NAT netlink_checks ovsnl: validate netlink attrs and settings - upcall_interfaces ovs: test the upcall interfaces" + upcall_interfaces ovs: test the upcall interfaces + drop_reason drop: test drop reasons are emitted" info() { [ $VERBOSE = 0 ] || echo $* @@ -127,6 +132,35 @@ ovs_add_netns_and_veths () { return 0 } +ovs_add_flow () { + info "Adding flow to DP: sbx:$1 br:$2 flow:$3 act:$4" + ovs_sbx "$1" python3 $ovs_base/ovs-dpctl.py add-flow "$2" "$3" "$4" + if [ $? -ne 0 ]; then + echo "Flow [ $3 : $4 ] failed" >> ${ovs_dir}/debug.log + return 1 + fi + return 0 +} + +ovs_drop_record_and_run () { + local sbx=$1 + shift + + perf record -a -q -e skb:kfree_skb -o ${ovs_dir}/perf.data $* \ + >> ${ovs_dir}/stdout 2>> ${ovs_dir}/stderr + return $? +} + +ovs_drop_reason_count() +{ + local reason=$1 + + local perf_output=`perf script -i ${ovs_dir}/perf.data -F trace:event,trace` + local pattern="skb:kfree_skb:.*reason: $reason" + + return `echo "$perf_output" | grep "$pattern" | wc -l` +} + usage() { echo echo "$0 [OPTIONS] [TEST]..." @@ -141,6 +175,285 @@ usage() { exit 1 } +# drop_reason test +# - drop packets and verify the right drop reason is reported +test_drop_reason() { + which perf >/dev/null 2>&1 || return $ksft_skip + + sbx_add "test_drop_reason" || return $? + + ovs_add_dp "test_drop_reason" dropreason || return 1 + + info "create namespaces" + for ns in client server; do + ovs_add_netns_and_veths "test_drop_reason" "dropreason" "$ns" \ + "${ns:0:1}0" "${ns:0:1}1" || return 1 + done + + # Setup client namespace + ip netns exec client ip addr add 172.31.110.10/24 dev c1 + ip netns exec client ip link set c1 up + + # Setup server namespace + ip netns exec server ip addr add 172.31.110.20/24 dev s1 + ip netns exec server ip link set s1 up + + # Allow ARP + ovs_add_flow "test_drop_reason" dropreason \ + 'in_port(1),eth(),eth_type(0x0806),arp()' '2' || return 1 + ovs_add_flow "test_drop_reason" dropreason \ + 'in_port(2),eth(),eth_type(0x0806),arp()' '1' || return 1 + + # Allow client ICMP traffic but drop return path + ovs_add_flow "test_drop_reason" dropreason \ + "in_port(1),eth(),eth_type(0x0800),ipv4(src=172.31.110.10,proto=1),icmp()" '2' + ovs_add_flow "test_drop_reason" dropreason \ + "in_port(2),eth(),eth_type(0x0800),ipv4(src=172.31.110.20,proto=1),icmp()" 'drop' + + ovs_drop_record_and_run "test_drop_reason" ip netns exec client ping -c 2 172.31.110.20 + ovs_drop_reason_count 0x30001 # OVS_DROP_FLOW_ACTION + if [[ "$?" -ne "2" ]]; then + info "Did not detect expected drops: $?" + return 1 + fi + + # Drop UDP 6000 traffic with an explicit action and an error code. + ovs_add_flow "test_drop_reason" dropreason \ + "in_port(1),eth(),eth_type(0x0800),ipv4(src=172.31.110.10,proto=17),udp(dst=6000)" \ + 'drop(42)' + # Drop UDP 7000 traffic with an explicit action with no error code. + ovs_add_flow "test_drop_reason" dropreason \ + "in_port(1),eth(),eth_type(0x0800),ipv4(src=172.31.110.10,proto=17),udp(dst=7000)" \ + 'drop(0)' + + ovs_drop_record_and_run \ + "test_drop_reason" ip netns exec client nc -i 1 -zuv 172.31.110.20 6000 + ovs_drop_reason_count 0x30004 # OVS_DROP_EXPLICIT_ACTION_ERROR + if [[ "$?" -ne "1" ]]; then + info "Did not detect expected explicit error drops: $?" + return 1 + fi + + ovs_drop_record_and_run \ + "test_drop_reason" ip netns exec client nc -i 1 -zuv 172.31.110.20 7000 + ovs_drop_reason_count 0x30003 # OVS_DROP_EXPLICIT_ACTION + if [[ "$?" -ne "1" ]]; then + info "Did not detect expected explicit drops: $?" + return 1 + fi + + return 0 +} + +# arp_ping test +# - client has 1500 byte MTU +# - server has 1500 byte MTU +# - send ARP ping between two ns +test_arp_ping () { + + which arping >/dev/null 2>&1 || return $ksft_skip + + sbx_add "test_arp_ping" || return $? + + ovs_add_dp "test_arp_ping" arpping || return 1 + + info "create namespaces" + for ns in client server; do + ovs_add_netns_and_veths "test_arp_ping" "arpping" "$ns" \ + "${ns:0:1}0" "${ns:0:1}1" || return 1 + done + + # Setup client namespace + ip netns exec client ip addr add 172.31.110.10/24 dev c1 + ip netns exec client ip link set c1 up + HW_CLIENT=`ip netns exec client ip link show dev c1 | grep -E 'link/ether [0-9a-f:]+' | awk '{print $2;}'` + info "Client hwaddr: $HW_CLIENT" + + # Setup server namespace + ip netns exec server ip addr add 172.31.110.20/24 dev s1 + ip netns exec server ip link set s1 up + HW_SERVER=`ip netns exec server ip link show dev s1 | grep -E 'link/ether [0-9a-f:]+' | awk '{print $2;}'` + info "Server hwaddr: $HW_SERVER" + + ovs_add_flow "test_arp_ping" arpping \ + "in_port(1),eth(),eth_type(0x0806),arp(sip=172.31.110.10,tip=172.31.110.20,sha=$HW_CLIENT,tha=ff:ff:ff:ff:ff:ff)" '2' || return 1 + ovs_add_flow "test_arp_ping" arpping \ + "in_port(2),eth(),eth_type(0x0806),arp()" '1' || return 1 + + ovs_sbx "test_arp_ping" ip netns exec client arping -I c1 172.31.110.20 -c 1 || return 1 + + return 0 +} + +# ct_connect_v4 test +# - client has 1500 byte MTU +# - server has 1500 byte MTU +# - use ICMP to ping in each direction +# - only allow CT state stuff to pass through new in c -> s +test_ct_connect_v4 () { + + which nc >/dev/null 2>/dev/null || return $ksft_skip + + sbx_add "test_ct_connect_v4" || return $? + + ovs_add_dp "test_ct_connect_v4" ct4 || return 1 + info "create namespaces" + for ns in client server; do + ovs_add_netns_and_veths "test_ct_connect_v4" "ct4" "$ns" \ + "${ns:0:1}0" "${ns:0:1}1" || return 1 + done + + ip netns exec client ip addr add 172.31.110.10/24 dev c1 + ip netns exec client ip link set c1 up + ip netns exec server ip addr add 172.31.110.20/24 dev s1 + ip netns exec server ip link set s1 up + + # Add forwarding for ARP and ip packets - completely wildcarded + ovs_add_flow "test_ct_connect_v4" ct4 \ + 'in_port(1),eth(),eth_type(0x0806),arp()' '2' || return 1 + ovs_add_flow "test_ct_connect_v4" ct4 \ + 'in_port(2),eth(),eth_type(0x0806),arp()' '1' || return 1 + ovs_add_flow "test_ct_connect_v4" ct4 \ + 'ct_state(-trk),eth(),eth_type(0x0800),ipv4()' \ + 'ct(commit),recirc(0x1)' || return 1 + ovs_add_flow "test_ct_connect_v4" ct4 \ + 'recirc_id(0x1),ct_state(+trk+new),in_port(1),eth(),eth_type(0x0800),ipv4(src=172.31.110.10)' \ + '2' || return 1 + ovs_add_flow "test_ct_connect_v4" ct4 \ + 'recirc_id(0x1),ct_state(+trk+est),in_port(1),eth(),eth_type(0x0800),ipv4(src=172.31.110.10)' \ + '2' || return 1 + ovs_add_flow "test_ct_connect_v4" ct4 \ + 'recirc_id(0x1),ct_state(+trk+est),in_port(2),eth(),eth_type(0x0800),ipv4(dst=172.31.110.10)' \ + '1' || return 1 + ovs_add_flow "test_ct_connect_v4" ct4 \ + 'recirc_id(0x1),ct_state(+trk+inv),eth(),eth_type(0x0800),ipv4()' 'drop' || \ + return 1 + + # do a ping + ovs_sbx "test_ct_connect_v4" ip netns exec client ping 172.31.110.20 -c 3 || return 1 + + # create an echo server in 'server' + echo "server" | \ + ovs_netns_spawn_daemon "test_ct_connect_v4" "server" \ + nc -lvnp 4443 + ovs_sbx "test_ct_connect_v4" ip netns exec client nc -i 1 -zv 172.31.110.20 4443 || return 1 + + # Now test in the other direction (should fail) + echo "client" | \ + ovs_netns_spawn_daemon "test_ct_connect_v4" "client" \ + nc -lvnp 4443 + ovs_sbx "test_ct_connect_v4" ip netns exec client nc -i 1 -zv 172.31.110.10 4443 + if [ $? == 0 ]; then + info "ct connect to client was successful" + return 1 + fi + + info "done..." + return 0 +} + +# connect_v4 test +# - client has 1500 byte MTU +# - server has 1500 byte MTU +# - use ICMP to ping in each direction +test_connect_v4 () { + + sbx_add "test_connect_v4" || return $? + + ovs_add_dp "test_connect_v4" cv4 || return 1 + + info "create namespaces" + for ns in client server; do + ovs_add_netns_and_veths "test_connect_v4" "cv4" "$ns" \ + "${ns:0:1}0" "${ns:0:1}1" || return 1 + done + + + ip netns exec client ip addr add 172.31.110.10/24 dev c1 + ip netns exec client ip link set c1 up + ip netns exec server ip addr add 172.31.110.20/24 dev s1 + ip netns exec server ip link set s1 up + + # Add forwarding for ARP and ip packets - completely wildcarded + ovs_add_flow "test_connect_v4" cv4 \ + 'in_port(1),eth(),eth_type(0x0806),arp()' '2' || return 1 + ovs_add_flow "test_connect_v4" cv4 \ + 'in_port(2),eth(),eth_type(0x0806),arp()' '1' || return 1 + ovs_add_flow "test_connect_v4" cv4 \ + 'in_port(1),eth(),eth_type(0x0800),ipv4(src=172.31.110.10)' '2' || return 1 + ovs_add_flow "test_connect_v4" cv4 \ + 'in_port(2),eth(),eth_type(0x0800),ipv4(src=172.31.110.20)' '1' || return 1 + + # do a ping + ovs_sbx "test_connect_v4" ip netns exec client ping 172.31.110.20 -c 3 || return 1 + + info "done..." + return 0 +} + +# nat_connect_v4 test +# - client has 1500 byte MTU +# - server has 1500 byte MTU +# - use ICMP to ping in each direction +# - only allow CT state stuff to pass through new in c -> s +test_nat_connect_v4 () { + which nc >/dev/null 2>/dev/null || return $ksft_skip + + sbx_add "test_nat_connect_v4" || return $? + + ovs_add_dp "test_nat_connect_v4" nat4 || return 1 + info "create namespaces" + for ns in client server; do + ovs_add_netns_and_veths "test_nat_connect_v4" "nat4" "$ns" \ + "${ns:0:1}0" "${ns:0:1}1" || return 1 + done + + ip netns exec client ip addr add 172.31.110.10/24 dev c1 + ip netns exec client ip link set c1 up + ip netns exec server ip addr add 172.31.110.20/24 dev s1 + ip netns exec server ip link set s1 up + + ip netns exec client ip route add default via 172.31.110.20 + + ovs_add_flow "test_nat_connect_v4" nat4 \ + 'in_port(1),eth(),eth_type(0x0806),arp()' '2' || return 1 + ovs_add_flow "test_nat_connect_v4" nat4 \ + 'in_port(2),eth(),eth_type(0x0806),arp()' '1' || return 1 + ovs_add_flow "test_nat_connect_v4" nat4 \ + "ct_state(-trk),in_port(1),eth(),eth_type(0x0800),ipv4(dst=192.168.0.20)" \ + "ct(commit,nat(dst=172.31.110.20)),recirc(0x1)" + ovs_add_flow "test_nat_connect_v4" nat4 \ + "ct_state(-trk),in_port(2),eth(),eth_type(0x0800),ipv4()" \ + "ct(commit,nat),recirc(0x2)" + + ovs_add_flow "test_nat_connect_v4" nat4 \ + "recirc_id(0x1),ct_state(+trk-inv),in_port(1),eth(),eth_type(0x0800),ipv4()" "2" + ovs_add_flow "test_nat_connect_v4" nat4 \ + "recirc_id(0x2),ct_state(+trk-inv),in_port(2),eth(),eth_type(0x0800),ipv4()" "1" + + # do a ping + ovs_sbx "test_nat_connect_v4" ip netns exec client ping 192.168.0.20 -c 3 || return 1 + + # create an echo server in 'server' + echo "server" | \ + ovs_netns_spawn_daemon "test_nat_connect_v4" "server" \ + nc -lvnp 4443 + ovs_sbx "test_nat_connect_v4" ip netns exec client nc -i 1 -zv 192.168.0.20 4443 || return 1 + + # Now test in the other direction (should fail) + echo "client" | \ + ovs_netns_spawn_daemon "test_nat_connect_v4" "client" \ + nc -lvnp 4443 + ovs_sbx "test_nat_connect_v4" ip netns exec client nc -i 1 -zv 172.31.110.10 4443 + if [ $? == 0 ]; then + info "connect to client was successful" + return 1 + fi + + info "done..." + return 0 +} + # netlink_validation # - Create a dp # - check no warning with "old version" simulation @@ -170,6 +483,16 @@ test_netlink_checks () { wc -l) == 2 ] || \ return 1 + ERR_MSG="Flow actions may not be safe on all matching packets" + PRE_TEST=$(dmesg | grep -c "${ERR_MSG}") + ovs_add_flow "test_netlink_checks" nv0 \ + 'in_port(1),eth(),eth_type(0x0806),arp()' 'drop(0),2' \ + &> /dev/null && return 1 + POST_TEST=$(dmesg | grep -c "${ERR_MSG}") + if [ "$PRE_TEST" == "$POST_TEST" ]; then + info "failed - error not generated" + return 1 + fi return 0 } diff --git a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py index 1c8b36bc15d4..912dc8c49085 100644 --- a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py +++ b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py @@ -9,9 +9,12 @@ import errno import ipaddress import logging import multiprocessing +import re import struct import sys import time +import types +import uuid try: from pyroute2 import NDB @@ -59,24 +62,207 @@ def macstr(mac): return outstr -def convert_mac(mac_str, mask=False): - if mac_str is None or mac_str == "": - mac_str = "00:00:00:00:00:00" - if mask is True and mac_str != "00:00:00:00:00:00": - mac_str = "FF:FF:FF:FF:FF:FF" - mac_split = mac_str.split(":") - ret = bytearray([int(i, 16) for i in mac_split]) - return bytes(ret) +def strcspn(str1, str2): + tot = 0 + for char in str1: + if str2.find(char) != -1: + return tot + tot += 1 + return tot -def convert_ipv4(ip, mask=False): - if ip is None: - ip = 0 - if mask is True: - if ip != 0: - ip = int(ipaddress.IPv4Address(ip)) & 0xFFFFFFFF +def strspn(str1, str2): + tot = 0 + for char in str1: + if str2.find(char) == -1: + return tot + tot += 1 + return tot - return int(ipaddress.IPv4Address(ip)) + +def intparse(statestr, defmask="0xffffffff"): + totalparse = strspn(statestr, "0123456789abcdefABCDEFx/") + # scan until "/" + count = strspn(statestr, "x0123456789abcdefABCDEF") + + firstnum = statestr[:count] + if firstnum[-1] == "/": + firstnum = firstnum[:-1] + k = int(firstnum, 0) + + m = None + if defmask is not None: + secondnum = defmask + if statestr[count] == "/": + secondnum = statestr[count + 1 :] # this is wrong... + m = int(secondnum, 0) + + return statestr[totalparse + 1 :], k, m + + +def parse_flags(flag_str, flag_vals): + bitResult = 0 + maskResult = 0 + + if len(flag_str) == 0: + return flag_str, bitResult, maskResult + + if flag_str[0].isdigit(): + idx = 0 + while flag_str[idx].isdigit() or flag_str[idx] == "x": + idx += 1 + digits = flag_str[:idx] + flag_str = flag_str[idx:] + + bitResult = int(digits, 0) + maskResult = int(digits, 0) + + while len(flag_str) > 0 and (flag_str[0] == "+" or flag_str[0] == "-"): + if flag_str[0] == "+": + setFlag = True + elif flag_str[0] == "-": + setFlag = False + + flag_str = flag_str[1:] + + flag_len = 0 + while ( + flag_str[flag_len] != "+" + and flag_str[flag_len] != "-" + and flag_str[flag_len] != "," + and flag_str[flag_len] != ")" + ): + flag_len += 1 + + flag = flag_str[0:flag_len] + + if flag in flag_vals: + if maskResult & flag_vals[flag]: + raise KeyError( + "Flag %s set once, cannot be set in multiples" % flag + ) + + if setFlag: + bitResult |= flag_vals[flag] + + maskResult |= flag_vals[flag] + else: + raise KeyError("Missing flag value: %s" % flag) + + flag_str = flag_str[flag_len:] + + return flag_str, bitResult, maskResult + + +def parse_ct_state(statestr): + ct_flags = { + "new": 1 << 0, + "est": 1 << 1, + "rel": 1 << 2, + "rpl": 1 << 3, + "inv": 1 << 4, + "trk": 1 << 5, + "snat": 1 << 6, + "dnat": 1 << 7, + } + + return parse_flags(statestr, ct_flags) + + +def convert_mac(data): + def to_bytes(mac): + mac_split = mac.split(":") + ret = bytearray([int(i, 16) for i in mac_split]) + return bytes(ret) + + mac_str, _, mask_str = data.partition('/') + + if not mac_str: + mac_str = mask_str = "00:00:00:00:00:00" + elif not mask_str: + mask_str = "FF:FF:FF:FF:FF:FF" + + return to_bytes(mac_str), to_bytes(mask_str) + +def convert_ipv4(data): + ip, _, mask = data.partition('/') + + if not ip: + ip = mask = 0 + elif not mask: + mask = 0xFFFFFFFF + elif mask.isdigit(): + mask = (0xFFFFFFFF << (32 - int(mask))) & 0xFFFFFFFF + + return int(ipaddress.IPv4Address(ip)), int(ipaddress.IPv4Address(mask)) + +def convert_int(size): + def convert_int_sized(data): + value, _, mask = data.partition('/') + + if not value: + return 0, 0 + elif not mask: + return int(value, 0), pow(2, size) - 1 + else: + return int(value, 0), int(mask, 0) + + return convert_int_sized + +def parse_starts_block(block_str, scanstr, returnskipped, scanregex=False): + if scanregex: + m = re.search(scanstr, block_str) + if m is None: + if returnskipped: + return block_str + return False + if returnskipped: + block_str = block_str[len(m.group(0)) :] + return block_str + return True + + if block_str.startswith(scanstr): + if returnskipped: + block_str = block_str[len(scanstr) :] + else: + return True + + if returnskipped: + return block_str + + return False + + +def parse_extract_field( + block_str, fieldstr, scanfmt, convert, masked=False, defval=None +): + if fieldstr and not block_str.startswith(fieldstr): + return block_str, defval + + if fieldstr: + str_skiplen = len(fieldstr) + str_skipped = block_str[str_skiplen:] + if str_skiplen == 0: + return str_skipped, defval + else: + str_skiplen = 0 + str_skipped = block_str + + m = re.search(scanfmt, str_skipped) + if m is None: + raise ValueError("Bad fmt string") + + data = m.group(0) + if convert: + data = convert(m.group(0)) + + str_skipped = str_skipped[len(m.group(0)) :] + if masked: + if str_skipped[0] == "/": + raise ValueError("Masking support TBD...") + + str_skipped = str_skipped[strspn(str_skipped, ", ") :] + return str_skipped, data class ovs_dp_msg(genlmsg): @@ -115,6 +301,7 @@ class ovsactions(nla): ("OVS_ACTION_ATTR_CHECK_PKT_LEN", "none"), ("OVS_ACTION_ATTR_ADD_MPLS", "none"), ("OVS_ACTION_ATTR_DEC_TTL", "none"), + ("OVS_ACTION_ATTR_DROP", "uint32"), ) class ctact(nla): @@ -261,6 +448,8 @@ class ovsactions(nla): print_str += "recirc(0x%x)" % int(self.get_attr(field[0])) elif field[0] == "OVS_ACTION_ATTR_TRUNC": print_str += "trunc(%d)" % int(self.get_attr(field[0])) + elif field[0] == "OVS_ACTION_ATTR_DROP": + print_str += "drop(%d)" % int(self.get_attr(field[0])) elif field[1] == "flag": if field[0] == "OVS_ACTION_ATTR_CT_CLEAR": print_str += "ct_clear" @@ -278,6 +467,153 @@ class ovsactions(nla): return print_str + def parse(self, actstr): + while len(actstr) != 0: + parsed = False + if actstr.startswith("drop"): + # If no reason is provided, the implicit drop is used (i.e no + # action). If some reason is given, an explicit action is used. + actstr, reason = parse_extract_field( + actstr, + "drop(", + "([0-9]+)", + lambda x: int(x, 0), + False, + None, + ) + if reason is not None: + self["attrs"].append(["OVS_ACTION_ATTR_DROP", reason]) + parsed = True + else: + return + + elif parse_starts_block(actstr, "^(\d+)", False, True): + actstr, output = parse_extract_field( + actstr, None, "(\d+)", lambda x: int(x), False, "0" + ) + self["attrs"].append(["OVS_ACTION_ATTR_OUTPUT", output]) + parsed = True + elif parse_starts_block(actstr, "recirc(", False): + actstr, recircid = parse_extract_field( + actstr, + "recirc(", + "([0-9a-fA-Fx]+)", + lambda x: int(x, 0), + False, + 0, + ) + self["attrs"].append(["OVS_ACTION_ATTR_RECIRC", recircid]) + parsed = True + + parse_flat_map = ( + ("ct_clear", "OVS_ACTION_ATTR_CT_CLEAR"), + ("pop_vlan", "OVS_ACTION_ATTR_POP_VLAN"), + ("pop_eth", "OVS_ACTION_ATTR_POP_ETH"), + ("pop_nsh", "OVS_ACTION_ATTR_POP_NSH"), + ) + + for flat_act in parse_flat_map: + if parse_starts_block(actstr, flat_act[0], False): + actstr += len(flat_act[0]) + self["attrs"].append([flat_act[1]]) + actstr = actstr[strspn(actstr, ", ") :] + parsed = True + + if parse_starts_block(actstr, "ct(", False): + actstr = actstr[len("ct(") :] + ctact = ovsactions.ctact() + + for scan in ( + ("commit", "OVS_CT_ATTR_COMMIT", None), + ("force_commit", "OVS_CT_ATTR_FORCE_COMMIT", None), + ("zone", "OVS_CT_ATTR_ZONE", int), + ("mark", "OVS_CT_ATTR_MARK", int), + ("helper", "OVS_CT_ATTR_HELPER", lambda x, y: str(x)), + ("timeout", "OVS_CT_ATTR_TIMEOUT", lambda x, y: str(x)), + ): + if actstr.startswith(scan[0]): + actstr = actstr[len(scan[0]) :] + if scan[2] is not None: + if actstr[0] != "=": + raise ValueError("Invalid ct attr") + actstr = actstr[1:] + pos = strcspn(actstr, ",)") + datum = scan[2](actstr[:pos], 0) + ctact["attrs"].append([scan[1], datum]) + actstr = actstr[pos:] + else: + ctact["attrs"].append([scan[1], None]) + actstr = actstr[strspn(actstr, ", ") :] + # it seems strange to put this here, but nat() is a complex + # sub-action and this lets it sit anywhere in the ct() action + if actstr.startswith("nat"): + actstr = actstr[3:] + natact = ovsactions.ctact.natattr() + + if actstr.startswith("("): + t = None + actstr = actstr[1:] + if actstr.startswith("src"): + t = "OVS_NAT_ATTR_SRC" + actstr = actstr[3:] + elif actstr.startswith("dst"): + t = "OVS_NAT_ATTR_DST" + actstr = actstr[3:] + + actstr, ip_block_min = parse_extract_field( + actstr, "=", "([0-9a-fA-F\.]+)", str, False + ) + actstr, ip_block_max = parse_extract_field( + actstr, "-", "([0-9a-fA-F\.]+)", str, False + ) + + actstr, proto_min = parse_extract_field( + actstr, ":", "(\d+)", int, False + ) + actstr, proto_max = parse_extract_field( + actstr, "-", "(\d+)", int, False + ) + + if t is not None: + natact["attrs"].append([t, None]) + + if ip_block_min is not None: + natact["attrs"].append( + ["OVS_NAT_ATTR_IP_MIN", ip_block_min] + ) + if ip_block_max is not None: + natact["attrs"].append( + ["OVS_NAT_ATTR_IP_MAX", ip_block_max] + ) + if proto_min is not None: + natact["attrs"].append( + ["OVS_NAT_ATTR_PROTO_MIN", proto_min] + ) + if proto_max is not None: + natact["attrs"].append( + ["OVS_NAT_ATTR_PROTO_MAX", proto_max] + ) + + for natscan in ( + ("persistent", "OVS_NAT_ATTR_PERSISTENT"), + ("hash", "OVS_NAT_ATTR_PROTO_HASH"), + ("random", "OVS_NAT_ATTR_PROTO_RANDOM"), + ): + if actstr.startswith(natscan[0]): + actstr = actstr[len(natscan[0]) :] + natact["attrs"].append([natscan[1], None]) + actstr = actstr[strspn(actstr, ", ") :] + + ctact["attrs"].append(["OVS_CT_ATTR_NAT", natact]) + actstr = actstr[strspn(actstr, ",) ") :] + + self["attrs"].append(["OVS_ACTION_ATTR_CT", ctact]) + parsed = True + + actstr = actstr[strspn(actstr, "), ") :] + if not parsed: + raise ValueError("Action str: '%s' not supported" % actstr) + class ovskey(nla): nla_flags = NLA_F_NESTED @@ -324,8 +660,10 @@ class ovskey(nla): ) fields_map = ( - ("src", "src", "%d", lambda x: int(x) if x is not None else 0), - ("dst", "dst", "%d", lambda x: int(x) if x is not None else 0), + ("src", "src", "%d", lambda x: int(x) if x else 0, + convert_int(16)), + ("dst", "dst", "%d", lambda x: int(x) if x else 0, + convert_int(16)), ) def __init__( @@ -347,6 +685,49 @@ class ovskey(nla): init=init, ) + def parse(self, flowstr, typeInst): + if not flowstr.startswith(self.proto_str): + return None, None + + k = typeInst() + m = typeInst() + + flowstr = flowstr[len(self.proto_str) :] + if flowstr.startswith("("): + flowstr = flowstr[1:] + + keybits = b"" + maskbits = b"" + for f in self.fields_map: + if flowstr.startswith(f[1]): + # the following assumes that the field looks + # something like 'field.' where '.' is a + # character that we don't exactly care about. + flowstr = flowstr[len(f[1]) + 1 :] + splitchar = 0 + for c in flowstr: + if c == "," or c == ")": + break + splitchar += 1 + data = flowstr[:splitchar] + flowstr = flowstr[splitchar:] + else: + data = "" + + if len(f) > 4: + k[f[0]], m[f[0]] = f[4](data) + else: + k[f[0]] = f[3](data) + m[f[0]] = f[3](data) + + flowstr = flowstr[strspn(flowstr, ", ") :] + if len(flowstr) == 0: + return flowstr, k, m + + flowstr = flowstr[strspn(flowstr, "), ") :] + + return flowstr, k, m + def dpstr(self, masked=None, more=False): outstr = self.proto_str + "(" first = False @@ -441,10 +822,14 @@ class ovskey(nla): int, convert_ipv4, ), - ("proto", "proto", "%d", lambda x: int(x) if x is not None else 0), - ("tos", "tos", "%d", lambda x: int(x) if x is not None else 0), - ("ttl", "ttl", "%d", lambda x: int(x) if x is not None else 0), - ("frag", "frag", "%d", lambda x: int(x) if x is not None else 0), + ("proto", "proto", "%d", lambda x: int(x) if x else 0, + convert_int(8)), + ("tos", "tos", "%d", lambda x: int(x) if x else 0, + convert_int(8)), + ("ttl", "ttl", "%d", lambda x: int(x) if x else 0, + convert_int(8)), + ("frag", "frag", "%d", lambda x: int(x) if x else 0, + convert_int(8)), ) def __init__( @@ -580,8 +965,8 @@ class ovskey(nla): ) fields_map = ( - ("type", "type", "%d", int), - ("code", "code", "%d", int), + ("type", "type", "%d", lambda x: int(x) if x else 0), + ("code", "code", "%d", lambda x: int(x) if x else 0), ) def __init__( @@ -646,7 +1031,7 @@ class ovskey(nla): int, convert_ipv4, ), - ("op", "op", "%d", lambda x: int(x) if x is not None else 0), + ("op", "op", "%d", lambda x: int(x) if x else 0), ( "sha", "sha", @@ -810,6 +1195,81 @@ class ovskey(nla): class ovs_key_mpls(nla): fields = (("lse", ">I"),) + def parse(self, flowstr, mask=None): + for field in ( + ("OVS_KEY_ATTR_PRIORITY", "skb_priority", intparse), + ("OVS_KEY_ATTR_SKB_MARK", "skb_mark", intparse), + ("OVS_KEY_ATTR_RECIRC_ID", "recirc_id", intparse), + ("OVS_KEY_ATTR_DP_HASH", "dp_hash", intparse), + ("OVS_KEY_ATTR_CT_STATE", "ct_state", parse_ct_state), + ("OVS_KEY_ATTR_CT_ZONE", "ct_zone", intparse), + ("OVS_KEY_ATTR_CT_MARK", "ct_mark", intparse), + ("OVS_KEY_ATTR_IN_PORT", "in_port", intparse), + ( + "OVS_KEY_ATTR_ETHERNET", + "eth", + ovskey.ethaddr, + ), + ( + "OVS_KEY_ATTR_ETHERTYPE", + "eth_type", + lambda x: intparse(x, "0xffff"), + ), + ( + "OVS_KEY_ATTR_IPV4", + "ipv4", + ovskey.ovs_key_ipv4, + ), + ( + "OVS_KEY_ATTR_IPV6", + "ipv6", + ovskey.ovs_key_ipv6, + ), + ( + "OVS_KEY_ATTR_ARP", + "arp", + ovskey.ovs_key_arp, + ), + ( + "OVS_KEY_ATTR_TCP", + "tcp", + ovskey.ovs_key_tcp, + ), + ( + "OVS_KEY_ATTR_UDP", + "udp", + ovskey.ovs_key_udp, + ), + ( + "OVS_KEY_ATTR_ICMP", + "icmp", + ovskey.ovs_key_icmp, + ), + ( + "OVS_KEY_ATTR_TCP_FLAGS", + "tcp_flags", + lambda x: parse_flags(x, None), + ), + ): + fld = field[1] + "(" + if not flowstr.startswith(fld): + continue + + if not isinstance(field[2], types.FunctionType): + nk = field[2]() + flowstr, k, m = nk.parse(flowstr, field[2]) + else: + flowstr = flowstr[len(fld) :] + flowstr, k, m = field[2](flowstr) + + if m and mask is not None: + mask["attrs"].append([field[0], m]) + self["attrs"].append([field[0], k]) + + flowstr = flowstr[strspn(flowstr, "),") :] + + return flowstr + def dpstr(self, mask=None, more=False): print_str = "" @@ -1358,11 +1818,92 @@ class OvsFlow(GenericNetlinkSocket): return print_str + def parse(self, flowstr, actstr, dpidx=0): + OVS_UFID_F_OMIT_KEY = 1 << 0 + OVS_UFID_F_OMIT_MASK = 1 << 1 + OVS_UFID_F_OMIT_ACTIONS = 1 << 2 + + self["cmd"] = 0 + self["version"] = 0 + self["reserved"] = 0 + self["dpifindex"] = 0 + + if flowstr.startswith("ufid:"): + count = 5 + while flowstr[count] != ",": + count += 1 + ufidstr = flowstr[5:count] + flowstr = flowstr[count + 1 :] + else: + ufidstr = str(uuid.uuid4()) + uuidRawObj = uuid.UUID(ufidstr).fields + + self["attrs"].append( + [ + "OVS_FLOW_ATTR_UFID", + [ + uuidRawObj[0], + uuidRawObj[1] << 16 | uuidRawObj[2], + uuidRawObj[3] << 24 + | uuidRawObj[4] << 16 + | uuidRawObj[5] & (0xFF << 32) >> 32, + uuidRawObj[5] & (0xFFFFFFFF), + ], + ] + ) + self["attrs"].append( + [ + "OVS_FLOW_ATTR_UFID_FLAGS", + int( + OVS_UFID_F_OMIT_KEY + | OVS_UFID_F_OMIT_MASK + | OVS_UFID_F_OMIT_ACTIONS + ), + ] + ) + + k = ovskey() + m = ovskey() + k.parse(flowstr, m) + self["attrs"].append(["OVS_FLOW_ATTR_KEY", k]) + self["attrs"].append(["OVS_FLOW_ATTR_MASK", m]) + + a = ovsactions() + a.parse(actstr) + self["attrs"].append(["OVS_FLOW_ATTR_ACTIONS", a]) + def __init__(self): GenericNetlinkSocket.__init__(self) self.bind(OVS_FLOW_FAMILY, OvsFlow.ovs_flow_msg) + def add_flow(self, dpifindex, flowmsg): + """ + Send a new flow message to the kernel. + + dpifindex should be a valid datapath obtained by calling + into the OvsDatapath lookup + + flowmsg is a flow object obtained by calling a dpparse + """ + + flowmsg["cmd"] = OVS_FLOW_CMD_NEW + flowmsg["version"] = OVS_DATAPATH_VERSION + flowmsg["reserved"] = 0 + flowmsg["dpifindex"] = dpifindex + + try: + reply = self.nlm_request( + flowmsg, + msg_type=self.prid, + msg_flags=NLM_F_REQUEST | NLM_F_ACK, + ) + reply = reply[0] + except NetlinkError as ne: + print(flowmsg) + raise ne + return reply + def dump(self, dpifindex, flowspec=None): """ Returns a list of messages containing flows. @@ -1514,6 +2055,11 @@ def main(argv): dumpflcmd = subparsers.add_parser("dump-flows") dumpflcmd.add_argument("dumpdp", help="Datapath Name") + addflcmd = subparsers.add_parser("add-flow") + addflcmd.add_argument("flbr", help="Datapath name") + addflcmd.add_argument("flow", help="Flow specification") + addflcmd.add_argument("acts", help="Flow actions") + args = parser.parse_args() if args.verbose > 0: @@ -1589,6 +2135,14 @@ def main(argv): rep = ovsflow.dump(rep["dpifindex"]) for flow in rep: print(flow.dpstr(True if args.verbose > 0 else False)) + elif hasattr(args, "flbr"): + rep = ovsdp.info(args.flbr, 0) + if rep is None: + print("DP '%s' not found." % args.flbr) + return 1 + flow = OvsFlow.ovs_flow_msg() + flow.parse(args.flow, args.acts, rep["dpifindex"]) + ovsflow.add_flow(rep["dpifindex"], flow) return 0 diff --git a/tools/testing/selftests/net/psock_lib.h b/tools/testing/selftests/net/psock_lib.h index faa884385c45..6e4fef560873 100644 --- a/tools/testing/selftests/net/psock_lib.h +++ b/tools/testing/selftests/net/psock_lib.h @@ -14,6 +14,8 @@ #include <arpa/inet.h> #include <unistd.h> +#include "kselftest.h" + #define DATA_LEN 100 #define DATA_CHAR 'a' #define DATA_CHAR_1 'b' @@ -63,7 +65,7 @@ static __maybe_unused void pair_udp_setfilter(int fd) struct sock_fprog bpf_prog; bpf_prog.filter = bpf_filter; - bpf_prog.len = sizeof(bpf_filter) / sizeof(struct sock_filter); + bpf_prog.len = ARRAY_SIZE(bpf_filter); if (setsockopt(fd, SOL_SOCKET, SO_ATTACH_FILTER, &bpf_prog, sizeof(bpf_prog))) { diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index ba286d680fd9..488f4964365e 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -21,6 +21,7 @@ ALL_TESTS=" kci_test_vrf kci_test_encap kci_test_macsec + kci_test_macsec_offload kci_test_ipsec kci_test_ipsec_offload kci_test_fdb_get @@ -643,6 +644,88 @@ kci_test_macsec() echo "PASS: macsec" } +kci_test_macsec_offload() +{ + sysfsd=/sys/kernel/debug/netdevsim/netdevsim0/ports/0/ + sysfsnet=/sys/bus/netdevsim/devices/netdevsim0/net/ + probed=false + local ret=0 + + ip macsec help 2>&1 | grep -q "^Usage: ip macsec" + if [ $? -ne 0 ]; then + echo "SKIP: macsec: iproute2 too old" + return $ksft_skip + fi + + # setup netdevsim since dummydev doesn't have offload support + if [ ! -w /sys/bus/netdevsim/new_device ] ; then + modprobe -q netdevsim + check_err $? + if [ $ret -ne 0 ]; then + echo "SKIP: macsec_offload can't load netdevsim" + return $ksft_skip + fi + probed=true + fi + + echo "0" > /sys/bus/netdevsim/new_device + while [ ! -d $sysfsnet ] ; do :; done + udevadm settle + dev=`ls $sysfsnet` + + ip link set $dev up + if [ ! -d $sysfsd ] ; then + echo "FAIL: macsec_offload can't create device $dev" + return 1 + fi + + ethtool -k $dev | grep -q 'macsec-hw-offload: on' + if [ $? -eq 1 ] ; then + echo "FAIL: macsec_offload netdevsim doesn't support MACsec offload" + return 1 + fi + + ip link add link $dev kci_macsec1 type macsec port 4 offload mac + check_err $? + + ip link add link $dev kci_macsec2 type macsec address "aa:bb:cc:dd:ee:ff" port 5 offload mac + check_err $? + + ip link add link $dev kci_macsec3 type macsec sci abbacdde01020304 offload mac + check_err $? + + ip link add link $dev kci_macsec4 type macsec port 8 offload mac 2> /dev/null + check_fail $? + + msname=kci_macsec1 + + ip macsec add "$msname" tx sa 0 pn 1024 on key 01 12345678901234567890123456789012 + check_err $? + + ip macsec add "$msname" rx port 1234 address "1c:ed:de:ad:be:ef" + check_err $? + + ip macsec add "$msname" rx port 1234 address "1c:ed:de:ad:be:ef" sa 0 pn 1 on \ + key 00 0123456789abcdef0123456789abcdef + check_err $? + + ip macsec add "$msname" rx port 1235 address "1c:ed:de:ad:be:ef" 2> /dev/null + check_fail $? + + # clean up any leftovers + for msdev in kci_macsec{1,2,3,4} ; do + ip link del $msdev 2> /dev/null + done + echo 0 > /sys/bus/netdevsim/del_device + $probed && rmmod netdevsim + + if [ $ret -ne 0 ]; then + echo "FAIL: macsec_offload" + return 1 + fi + echo "PASS: macsec_offload" +} + #------------------------------------------------------------------- # Example commands # ip x s add proto esp src 14.0.0.52 dst 14.0.0.70 \ diff --git a/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh new file mode 100755 index 000000000000..c79cb8ede17f --- /dev/null +++ b/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh @@ -0,0 +1,1213 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# author: Andrea Mayer <andrea.mayer@uniroma2.it> +# author: Paolo Lungaroni <paolo.lungaroni@uniroma2.it> +# +# This script is designed for testing the support of NEXT-C-SID flavor for SRv6 +# End.X behavior. +# A basic knowledge of SRv6 architecture [1] and of the compressed SID approach +# [2] is assumed for the reader. +# +# The network topology used in the selftest is depicted hereafter, composed of +# two hosts and four routers. Hosts hs-1 and hs-2 are connected through an +# IPv4/IPv6 L3 VPN service, offered by routers rt-1, rt-2, rt-3 and rt-4 using +# the NEXT-C-SID flavor. The key components for such VPNs are: +# +# i) The SRv6 H.Encaps/H.Encaps.Red behaviors [1] apply SRv6 Policies on +# traffic received by connected hosts, initiating the VPN tunnel; +# +# ii) The SRv6 End.X behavior [1] (Endpoint with L3 cross connect) is a +# variant of SRv6 End behavior. It advances the active SID in the SID +# List carried by the SRH and forwards the packet to an L3 adjacency; +# +# iii) The NEXT-C-SID mechanism [2] offers the possibility of encoding several +# SRv6 segments within a single 128-bit SID address, referred to as a +# Compressed SID (C-SID) container. In this way, the length of the SID +# List can be drastically reduced. +# The NEXT-C-SID is provided as a "flavor" of the SRv6 End.X behavior +# which advances the current C-SID (i.e. the Locator-Node Function defined +# in [2]) with the next one carried in the Argument, if available. +# When no more C-SIDs are available in the Argument, the SRv6 End.X +# behavior will apply the End.X function selecting the next SID in the SID +# List; +# +# iv) The SRv6 End.DT46 behavior [1] is used for removing the SRv6 Policy and, +# thus, it terminates the VPN tunnel. Such a behavior is capable of +# handling, at the same time, both tunneled IPv4 and IPv6 traffic. +# +# [1] https://datatracker.ietf.org/doc/html/rfc8986 +# [2] https://datatracker.ietf.org/doc/html/draft-ietf-spring-srv6-srh-compression +# +# +# cafe::1 cafe::2 +# 10.0.0.1 10.0.0.2 +# +--------+ +--------+ +# | | | | +# | hs-1 | | hs-2 | +# | | | | +# +---+----+ +----+---+ +# cafe::/64 | | cafe::/64 +# 10.0.0.0/24 | | 10.0.0.0/24 +# +---+----+ +----+---+ +# | | fcf0:0:1:2::/64 | | +# | rt-1 +-------------------+ rt-2 | +# | | | | +# +---+----+ +----+---+ +# | . . | +# | fcf0:0:1:3::/64 . | +# | . . | +# | . . | +# fcf0:0:1:4::/64 | . | fcf0:0:2:3::/64 +# | . . | +# | . . | +# | fcf0:0:2:4::/64 . | +# | . . | +# +---+----+ +----+---+ +# | | | | +# | rt-4 +-------------------+ rt-3 | +# | | fcf0:0:3:4::/64 | | +# +---+----+ +----+---+ +# +# Every fcf0:0:x:y::/64 network interconnects the SRv6 routers rt-x with rt-y in +# the selftest network. +# +# Local SID/C-SID table +# ===================== +# +# Each SRv6 router is configured with a Local SID/C-SID table in which +# SIDs/C-SIDs are stored. Considering an SRv6 router rt-x, SIDs/C-SIDs are +# configured in the Local SID/C-SIDs table as follows: +# +# Local SID/C-SID table for SRv6 router rt-x +# +-----------------------------------------------------------+ +# |fcff:x::d46 is associated with the non-compressed SRv6 | +# | End.DT46 behavior | +# +-----------------------------------------------------------+ +# |fcbb:0:0x00::/48 is associated with the NEXT-C-SID flavor | +# | of SRv6 End.X behavior | +# +-----------------------------------------------------------+ +# |fcbb:0:0x00:d46::/64 is associated with the SRv6 End.DT46 | +# | behavior when NEXT-C-SID compression is turned on | +# +-----------------------------------------------------------+ +# +# The fcff::/16 prefix is reserved for implementing SRv6 services with regular +# (non compressed) SIDs. Reachability of SIDs is ensured by proper configuration +# of the IPv6 routing tables in the routers. +# Similarly, the fcbb:0::/32 prefix is reserved for implementing SRv6 VPN +# services leveraging the NEXT-C-SID compression mechanism. Indeed, the +# fcbb:0::/32 is used for encoding the Locator-Block while the Locator-Node +# Function is encoded with 16 bits. +# +# Incoming traffic classification and application of SRv6 Policies +# ================================================================ +# +# An SRv6 ingress router applies different SRv6 Policies to the traffic received +# from a connected host, considering the IPv4 or IPv6 destination address. +# SRv6 policy enforcement consists of encapsulating the received traffic into a +# new IPv6 packet with a given SID List contained in the SRH. +# When the SID List contains only one SID, the SRH could be omitted completely +# and that SID is stored directly in the IPv6 Destination Address (DA) (this is +# called "reduced" encapsulation). +# +# Test cases for NEXT-C-SID +# ========================= +# +# We consider two test cases for NEXT-C-SID: i) single SID and ii) double SID. +# +# In the single SID test case we have a number of segments that are all +# contained in a single Compressed SID (C-SID) container. Therefore the +# resulting SID List has only one SID. Using the reduced encapsulation format +# this will result in a packet with no SRH. +# +# In the double SID test case we have one segment carried in a Compressed SID +# (C-SID) container, followed by a regular (non compressed) SID. The resulting +# SID List has two segments and it is possible to test the advance to the next +# SID when all the C-SIDs in a C-SID container have been processed. Using the +# reduced encapsulation format this will result in a packet with an SRH +# containing 1 segment. +# +# For the single SID test case, we use the IPv6 addresses of hs-1 and hs-2, for +# the double SID test case, we use their IPv4 addresses. This is only done to +# simplify the test setup and avoid adding other hosts or multiple addresses on +# the same interface of a host. +# +# Traffic from hs-1 to hs-2 +# ------------------------- +# +# Packets generated from hs-1 and directed towards hs-2 are handled by rt-1 +# which applies the SRv6 Policies as follows: +# +# i) IPv6 DA=cafe::2, H.Encaps.Red with SID List=fcbb:0:0300:0200:d46:: +# ii) IPv4 DA=10.0.0.2, H.Encaps.Red with SID List=fcbb:0:0300::,fcff:2::d46 +# +# ### i) single SID +# +# The router rt-1 is configured to enforce the given Policy through the SRv6 +# H.Encaps.Red behavior which avoids the presence of the SRH at all, since it +# pushes the single SID directly in the IPv6 DA. Such a SID encodes a whole +# C-SID container carrying several C-SIDs (e.g. 0300, 0200, etc). +# +# As the packet reaches the router rt-3, the enabled NEXT-C-SID SRv6 End.X +# behavior (associated with fcbb:0:0300::/48) is triggered. This behavior +# analyzes the IPv6 DA and checks whether the Argument of the C-SID container +# is zero or not. In this case, the Argument is *NOT* zero and the IPv6 DA is +# updated as follows: +# +# +-----------------------------------------------------------------+ +# | Before applying the rt-3 enabled NEXT-C-SID SRv6 End.X behavior | +# +-----------------------------------------------------------------+ +# | +---------- Argument | +# | vvvvvvvvvv | +# | IPv6 DA fcbb:0:0300:0200:d46:: | +# | ^^^^ <-- shifting | +# | | | +# | Locator-Node Function | +# +-----------------------------------------------------------------+ +# | After applying the rt-3 enabled NEXT-C-SID SRv6 End.X behavior | +# +-----------------------------------------------------------------+ +# | +---------- Argument | +# | vvvvvv | +# | IPv6 DA fcbb:0:0200:d46:: | +# | ^^^^ | +# | | | +# | Locator-Node Function | +# +-----------------------------------------------------------------+ +# +# After having applied the enabled NEXT-C-SID SRv6 End.X behavior, the packet +# is sent to rt-4 node using the L3 adjacency address fcf0:0:3:4::4. +# +# The node rt-4 performs a plain IPv6 forward to the rt-2 router according to +# its Local SID table and using the IPv6 DA fcbb:0:0200:d46:: . +# +# The router rt-2 is configured for decapsulating the inner IPv6 packet and, +# for this reason, it applies the SRv6 End.DT46 behavior on the received +# packet. It is worth noting that the SRv6 End.DT46 behavior does not require +# the presence of the SRH: it is fully capable to operate properly on +# IPv4/IPv6-in-IPv6 encapsulations. +# At the end of the decap operation, the packet is sent to the host hs-2. +# +# ### ii) double SID +# +# The router rt-1 is configured to enforce the given Policy through the SRv6 +# H.Encaps.Red. As a result, the first SID fcbb:0:0300:: is stored into the +# IPv6 DA, while the SRH pushed into the packet is made of only one SID, i.e. +# fcff:2::d46. Hence, the packet sent by hs-1 to hs-2 is encapsulated in an +# outer IPv6 header plus the SRH. +# +# As the packet reaches the node rt-3, the router applies the enabled NEXT-C-SID +# SRv6 End.X behavior. +# +# +-----------------------------------------------------------------+ +# | Before applying the rt-3 enabled NEXT-C-SID SRv6 End.X behavior | +# +-----------------------------------------------------------------+ +# | +---------- Argument | +# | vvvv (Argument is all filled with zeros) | +# | IPv6 DA fcbb:0:0300:: | +# | ^^^^ | +# | | | +# | Locator-Node Function | +# +-----------------------------------------------------------------+ +# | After applying the rt-3 enabled NEXT-C-SID SRv6 End.X behavior | +# +-----------------------------------------------------------------+ +# | | +# | IPv6 DA fcff:2::d46 | +# | ^^^^^^^^^^^ | +# | | | +# | SID copied from the SID List contained in the SRH | +# +-----------------------------------------------------------------+ +# +# Since the Argument of the C-SID container is zero, the behavior can not +# update the Locator-Node function with the next C-SID carried in the Argument +# itself. Thus, the enabled NEXT-C-SID SRv6 End.X behavior operates as the +# traditional End.X behavior: it updates the IPv6 DA by copying the next +# available SID in the SID List carried by the SRH. Next, the packet is +# forwarded to the rt-4 node using the L3 adjacency fcf0:3:4::4 previously +# configured for this behavior. +# +# The node rt-4 performs a plain IPv6 forward to the rt-2 router according to +# its Local SID table and using the IPv6 DA fcff:2::d46. +# +# Once the packet is received by rt-2, the router decapsulates the inner IPv4 +# packet using the SRv6 End.DT46 behavior (associated with the SID fcff:2::d46) +# and sends it to the host hs-2. +# +# Traffic from hs-2 to hs-1 +# ------------------------- +# +# Packets generated from hs-2 and directed towards hs-1 are handled by rt-2 +# which applies the SRv6 Policies as follows: +# +# i) IPv6 DA=cafe::1, SID List=fcbb:0:0400:0100:d46:: +# ii) IPv4 DA=10.0.0.1, SID List=fcbb:0:0300::,fcff:1::d46 +# +# ### i) single SID +# +# The node hs-2 sends an IPv6 packet directed to node hs-1. The router rt-2 is +# directly connected to hs-2 and receives the packet. Rt-2 applies the +# H.Encap.Red behavior with policy i) described above. Since there is only one +# SID, the SRH header is omitted and the policy is inserted directly into the DA +# of IPv6 packet. +# +# The packet reaches the router rt-4 and the enabled NEXT-C-SID SRv6 End.X +# behavior (associated with fcbb:0:0400::/48) is triggered. This behavior +# analyzes the IPv6 DA and checks whether the Argument of the C-SID container +# is zero or not. The Argument is *NOT* zero and the C-SID in the IPv6 DA is +# advanced. At this point, the current IPv6 DA is fcbb:0:0100:d46:: . +# The enabled NEXT-C-SID SRv6 End.X behavior is configured with the L3 adjacency +# fcf0:0:1:4::1, used to route traffic to the rt-1 node. +# +# The router rt-1 is configured for decapsulating the inner packet. It applies +# the SRv6 End.DT46 behavior on the received packet. Decapsulation does not +# require the presence of the SRH. At the end of the decap operation, the packet +# is sent to the host hs-1. +# +# ### ii) double SID +# +# The router rt-2 is configured to enforce the given Policy through the SRv6 +# H.Encaps.Red. As a result, the first SID fcbb:0:0300:: is stored into the +# IPv6 DA, while the SRH pushed into the packet is made of only one SID, i.e. +# fcff:1::d46. Hence, the packet sent by hs-2 to hs-1 is encapsulated in an +# outer IPv6 header plus the SRH. +# +# As the packet reaches the node rt-3, the enabled NEXT-C-SID SRv6 End.X +# behavior bound to the SID fcbb:0:0300::/48 is triggered. +# Since the Argument of the C-SID container is zero, the behavior can not +# update the Locator-Node function with the next C-SID carried in the Argument +# itself. Thus, the enabled NEXT-C-SID SRv6 End-X behavior operates as the +# traditional End.X behavior: it updates the IPv6 DA by copying the next +# available SID in the SID List carried by the SRH. After that, the packet is +# forwarded to the rt-4 node using the L3 adjacency (fcf0:3:4::4) previously +# configured for this behavior. +# +# The node rt-4 performs a plain IPv6 forward to the rt-1 router according to +# its Local SID table, considering the IPv6 DA fcff:1::d46. +# +# Once the packet is received by rt-1, the router decapsulates the inner IPv4 +# packet using the SRv6 End.DT46 behavior (associated with the SID fcff:1::d46) +# and sends it to the host hs-1. + +# Kselftest framework requirement - SKIP code is 4. +readonly ksft_skip=4 + +readonly RDMSUFF="$(mktemp -u XXXXXXXX)" +readonly DUMMY_DEVNAME="dum0" +readonly VRF_TID=100 +readonly VRF_DEVNAME="vrf-${VRF_TID}" +readonly RT2HS_DEVNAME="veth-t${VRF_TID}" +readonly LOCALSID_TABLE_ID=90 +readonly IPv6_RT_NETWORK=fcf0:0 +readonly IPv6_HS_NETWORK=cafe +readonly IPv4_HS_NETWORK=10.0.0 +readonly VPN_LOCATOR_SERVICE=fcff +readonly DT46_FUNC=0d46 +readonly HEADEND_ENCAP="encap.red" + +# do not add ':' as separator +readonly LCBLOCK_ADDR=fcbb0000 +readonly LCBLOCK_BLEN=32 +# do not add ':' as separator +readonly LCNODEFUNC_FMT="0%d00" +readonly LCNODEFUNC_BLEN=16 + +readonly LCBLOCK_NODEFUNC_BLEN=$((LCBLOCK_BLEN + LCNODEFUNC_BLEN)) + +readonly CSID_CNTR_PREFIX="dead:beaf::/32" +# ID of the router used for testing the C-SID container cfgs +readonly CSID_CNTR_RT_ID_TEST=1 +# Routing table used for testing the C-SID container cfgs +readonly CSID_CNTR_RT_TABLE=91 + +# C-SID container configurations to be tested +# +# An entry of the array is defined as "a,b,c" where: +# - 'a' and 'b' elements represent respectively the Locator-Block length +# (lblen) in bits and the Locator-Node Function length (nflen) in bits. +# 'a' and 'b' can be set to default values using the placeholder "d" which +# indicates the default kernel values (32 for lblen and 16 for nflen); +# otherwise, any numeric value is accepted; +# - 'c' indicates whether the C-SID configuration provided by the values 'a' +# and 'b' should be considered valid ("y") or invalid ("n"). +declare -ra CSID_CONTAINER_CFGS=( + "d,d,y" + "d,16,y" + "16,d,y" + "16,32,y" + "32,16,y" + "48,8,y" + "8,48,y" + "d,0,n" + "0,d,n" + "32,0,n" + "0,32,n" + "17,d,n" + "d,17,n" + "120,16,n" + "16,120,n" + "0,128,n" + "128,0,n" + "130,0,n" + "0,130,n" + "0,0,n" +) + +PING_TIMEOUT_SEC=4 +PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no} + +# IDs of routers and hosts are initialized during the setup of the testing +# network +ROUTERS='' +HOSTS='' + +SETUP_ERR=1 + +ret=${ksft_skip} +nsuccess=0 +nfail=0 + +log_test() +{ + local rc="$1" + local expected="$2" + local msg="$3" + + if [ "${rc}" -eq "${expected}" ]; then + nsuccess=$((nsuccess+1)) + printf "\n TEST: %-60s [ OK ]\n" "${msg}" + else + ret=1 + nfail=$((nfail+1)) + printf "\n TEST: %-60s [FAIL]\n" "${msg}" + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi + fi +} + +print_log_test_results() +{ + printf "\nTests passed: %3d\n" "${nsuccess}" + printf "Tests failed: %3d\n" "${nfail}" + + # when a test fails, the value of 'ret' is set to 1 (error code). + # Conversely, when all tests are passed successfully, the 'ret' value + # is set to 0 (success code). + if [ "${ret}" -ne 1 ]; then + ret=0 + fi +} + +log_section() +{ + echo + echo "################################################################################" + echo "TEST SECTION: $*" + echo "################################################################################" +} + +test_command_or_ksft_skip() +{ + local cmd="$1" + + if [ ! -x "$(command -v "${cmd}")" ]; then + echo "SKIP: Could not run test without \"${cmd}\" tool"; + exit "${ksft_skip}" + fi +} + +get_nodename() +{ + local name="$1" + + echo "${name}-${RDMSUFF}" +} + +get_rtname() +{ + local rtid="$1" + + get_nodename "rt-${rtid}" +} + +get_hsname() +{ + local hsid="$1" + + get_nodename "hs-${hsid}" +} + +__create_namespace() +{ + local name="$1" + + ip netns add "${name}" +} + +create_router() +{ + local rtid="$1" + local nsname + + nsname="$(get_rtname "${rtid}")" + + __create_namespace "${nsname}" + + ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.all.accept_dad=0 + ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.default.accept_dad=0 + ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.all.forwarding=1 + + ip netns exec "${nsname}" sysctl -wq net.ipv4.conf.all.rp_filter=0 + ip netns exec "${nsname}" sysctl -wq net.ipv4.conf.default.rp_filter=0 + ip netns exec "${nsname}" sysctl -wq net.ipv4.ip_forward=1 +} + +create_host() +{ + local hsid="$1" + local nsname + + nsname="$(get_hsname "${hsid}")" + + __create_namespace "${nsname}" +} + +cleanup() +{ + local nsname + local i + + # destroy routers + for i in ${ROUTERS}; do + nsname="$(get_rtname "${i}")" + + ip netns del "${nsname}" &>/dev/null || true + done + + # destroy hosts + for i in ${HOSTS}; do + nsname="$(get_hsname "${i}")" + + ip netns del "${nsname}" &>/dev/null || true + done + + # check whether the setup phase was completed successfully or not. In + # case of an error during the setup phase of the testing environment, + # the selftest is considered as "skipped". + if [ "${SETUP_ERR}" -ne 0 ]; then + echo "SKIP: Setting up the testing environment failed" + exit "${ksft_skip}" + fi + + exit "${ret}" +} + +add_link_rt_pairs() +{ + local rt="$1" + local rt_neighs="$2" + local neigh + local nsname + local neigh_nsname + + nsname="$(get_rtname "${rt}")" + + for neigh in ${rt_neighs}; do + neigh_nsname="$(get_rtname "${neigh}")" + + ip link add "veth-rt-${rt}-${neigh}" netns "${nsname}" \ + type veth peer name "veth-rt-${neigh}-${rt}" \ + netns "${neigh_nsname}" + done +} + +get_network_prefix() +{ + local rt="$1" + local neigh="$2" + local p="${rt}" + local q="${neigh}" + + if [ "${p}" -gt "${q}" ]; then + p="${q}"; q="${rt}" + fi + + echo "${IPv6_RT_NETWORK}:${p}:${q}" +} + +# Setup the basic networking for the routers +setup_rt_networking() +{ + local rt="$1" + local rt_neighs="$2" + local nsname + local net_prefix + local devname + local neigh + + nsname="$(get_rtname "${rt}")" + + for neigh in ${rt_neighs}; do + devname="veth-rt-${rt}-${neigh}" + + net_prefix="$(get_network_prefix "${rt}" "${neigh}")" + + ip -netns "${nsname}" addr \ + add "${net_prefix}::${rt}/64" dev "${devname}" nodad + + ip -netns "${nsname}" link set "${devname}" up + done + + ip -netns "${nsname}" link add "${DUMMY_DEVNAME}" type dummy + + ip -netns "${nsname}" link set "${DUMMY_DEVNAME}" up + ip -netns "${nsname}" link set lo up +} + +# build an ipv6 prefix/address based on the input string +# Note that the input string does not contain ':' and '::' which are considered +# to be implicit. +# e.g.: +# - input: fbcc00000400300 +# - output: fbcc:0000:0400:0300:0000:0000:0000:0000 +# ^^^^^^^^^^^^^^^^^^^ +# fill the address with 0s +build_ipv6_addr() +{ + local addr="$1" + local out="" + local strlen="${#addr}" + local padn + local i + + # add ":" every 4 digits (16 bits) + for (( i = 0; i < strlen; i++ )); do + if (( i > 0 && i < 32 && (i % 4) == 0 )); then + out="${out}:" + fi + + out="${out}${addr:$i:1}" + done + + # fill the remaining bits of the address with 0s + padn=$((32 - strlen)) + for (( i = padn; i > 0; i-- )); do + if (( i > 0 && i < 32 && (i % 4) == 0 )); then + out="${out}:" + fi + + out="${out}0" + done + + printf "${out}" +} + +build_csid() +{ + local nodeid="$1" + + printf "${LCNODEFUNC_FMT}" "${nodeid}" +} + +build_lcnode_func_prefix() +{ + local nodeid="$1" + local lcnodefunc + local prefix + local out + + lcnodefunc="$(build_csid "${nodeid}")" + prefix="$(build_ipv6_addr "${LCBLOCK_ADDR}${lcnodefunc}")" + + out="${prefix}/${LCBLOCK_NODEFUNC_BLEN}" + + echo "${out}" +} + +set_end_x_nextcsid() +{ + local rt="$1" + local adj="$2" + + nsname="$(get_rtname "${rt}")" + net_prefix="$(get_network_prefix "${rt}" "${adj}")" + lcnode_func_prefix="$(build_lcnode_func_prefix "${rt}")" + + # enabled NEXT-C-SID SRv6 End.X behavior (note that "dev" is the dummy + # dum0 device chosen for the sake of simplicity). + ip -netns "${nsname}" -6 route \ + replace "${lcnode_func_prefix}" \ + table "${LOCALSID_TABLE_ID}" \ + encap seg6local action End.X nh6 "${net_prefix}::${adj}" \ + flavors next-csid lblen "${LCBLOCK_BLEN}" \ + nflen "${LCNODEFUNC_BLEN}" dev "${DUMMY_DEVNAME}" +} + +set_underlay_sids_reachability() +{ + local rt="$1" + local rt_neighs="$2" + + nsname="$(get_rtname "${rt}")" + + for neigh in ${rt_neighs}; do + devname="veth-rt-${rt}-${neigh}" + + net_prefix="$(get_network_prefix "${rt}" "${neigh}")" + + # set underlay network routes for SIDs reachability + ip -netns "${nsname}" -6 route \ + replace "${VPN_LOCATOR_SERVICE}:${neigh}::/32" \ + table "${LOCALSID_TABLE_ID}" \ + via "${net_prefix}::${neigh}" dev "${devname}" + + # set the underlay network for C-SIDs reachability + lcnode_func_prefix="$(build_lcnode_func_prefix "${neigh}")" + + ip -netns "${nsname}" -6 route \ + replace "${lcnode_func_prefix}" \ + table "${LOCALSID_TABLE_ID}" \ + via "${net_prefix}::${neigh}" dev "${devname}" + done +} + +# Setup local SIDs for an SRv6 router +setup_rt_local_sids() +{ + local rt="$1" + local rt_neighs="$2" + local net_prefix + local devname + local nsname + local neigh + local lcnode_func_prefix + local lcblock_prefix + + nsname="$(get_rtname "${rt}")" + + set_underlay_sids_reachability "${rt}" "${rt_neighs}" + + # all SIDs for VPNs start with a common locator. Routes and SRv6 + # Endpoint behavior instaces are grouped together in the 'localsid' + # table. + ip -netns "${nsname}" -6 rule \ + add to "${VPN_LOCATOR_SERVICE}::/16" \ + lookup "${LOCALSID_TABLE_ID}" prio 999 + + # common locator block for NEXT-C-SIDS compression mechanism. + lcblock_prefix="$(build_ipv6_addr "${LCBLOCK_ADDR}")" + ip -netns "${nsname}" -6 rule \ + add to "${lcblock_prefix}/${LCBLOCK_BLEN}" \ + lookup "${LOCALSID_TABLE_ID}" prio 999 +} + +# build and install the SRv6 policy into the ingress SRv6 router as well as the +# decap SID in the egress one. +# args: +# $1 - src host (evaluate automatically the ingress router) +# $2 - dst host (evaluate automatically the egress router) +# $3 - SRv6 routers configured for steering traffic (End.X behaviors) +# $4 - single SID or double SID +# $5 - traffic type (IPv6 or IPv4) +__setup_l3vpn() +{ + local src="$1" + local dst="$2" + local end_rts="$3" + local mode="$4" + local traffic="$5" + local nsname + local policy + local container + local decapsid + local lcnfunc + local dt + local n + local rtsrc_nsname + local rtdst_nsname + + rtsrc_nsname="$(get_rtname "${src}")" + rtdst_nsname="$(get_rtname "${dst}")" + + container="${LCBLOCK_ADDR}" + + # build first SID (C-SID container) + for n in ${end_rts}; do + lcnfunc="$(build_csid "${n}")" + + container="${container}${lcnfunc}" + done + + if [ "${mode}" -eq 1 ]; then + # single SID policy + dt="$(build_csid "${dst}")${DT46_FUNC}" + container="${container}${dt}" + # build the full ipv6 address for the container + policy="$(build_ipv6_addr "${container}")" + + # build the decap SID used in the decap node + container="${LCBLOCK_ADDR}${dt}" + decapsid="$(build_ipv6_addr "${container}")" + else + # double SID policy + decapsid="${VPN_LOCATOR_SERVICE}:${dst}::${DT46_FUNC}" + + policy="$(build_ipv6_addr "${container}"),${decapsid}" + fi + + # apply encap policy + if [ "${traffic}" -eq 6 ]; then + ip -netns "${rtsrc_nsname}" -6 route \ + add "${IPv6_HS_NETWORK}::${dst}" vrf "${VRF_DEVNAME}" \ + encap seg6 mode "${HEADEND_ENCAP}" segs "${policy}" \ + dev "${VRF_DEVNAME}" + + ip -netns "${rtsrc_nsname}" -6 neigh \ + add proxy "${IPv6_HS_NETWORK}::${dst}" \ + dev "${RT2HS_DEVNAME}" + else + # "dev" must be different from the one where the packet is + # received, otherwise the proxy arp does not work. + ip -netns "${rtsrc_nsname}" -4 route \ + add "${IPv4_HS_NETWORK}.${dst}" vrf "${VRF_DEVNAME}" \ + encap seg6 mode "${HEADEND_ENCAP}" segs "${policy}" \ + dev "${VRF_DEVNAME}" + fi + + # apply decap + # Local End.DT46 behavior (decap) + ip -netns "${rtdst_nsname}" -6 route \ + add "${decapsid}" \ + table "${LOCALSID_TABLE_ID}" \ + encap seg6local action End.DT46 vrftable "${VRF_TID}" \ + dev "${VRF_DEVNAME}" +} + +# see __setup_l3vpn() +setup_ipv4_vpn_2sids() +{ + __setup_l3vpn "$1" "$2" "$3" 2 4 +} + +# see __setup_l3vpn() +setup_ipv6_vpn_1sid() +{ + __setup_l3vpn "$1" "$2" "$3" 1 6 +} + +setup_hs() +{ + local hs="$1" + local rt="$2" + local hsname + local rtname + + hsname="$(get_hsname "${hs}")" + rtname="$(get_rtname "${rt}")" + + ip netns exec "${hsname}" sysctl -wq net.ipv6.conf.all.accept_dad=0 + ip netns exec "${hsname}" sysctl -wq net.ipv6.conf.default.accept_dad=0 + + ip -netns "${hsname}" link add veth0 type veth \ + peer name "${RT2HS_DEVNAME}" netns "${rtname}" + + ip -netns "${hsname}" addr \ + add "${IPv6_HS_NETWORK}::${hs}/64" dev veth0 nodad + ip -netns "${hsname}" addr add "${IPv4_HS_NETWORK}.${hs}/24" dev veth0 + + ip -netns "${hsname}" link set veth0 up + ip -netns "${hsname}" link set lo up + + # configure the VRF on the router which is directly connected to the + # source host. + ip -netns "${rtname}" link \ + add "${VRF_DEVNAME}" type vrf table "${VRF_TID}" + ip -netns "${rtname}" link set "${VRF_DEVNAME}" up + + # enslave the veth interface connecting the router with the host to the + # VRF in the access router + ip -netns "${rtname}" link \ + set "${RT2HS_DEVNAME}" master "${VRF_DEVNAME}" + + # set default routes to unreachable for both ipv6 and ipv4 + ip -netns "${rtname}" -6 route \ + add unreachable default metric 4278198272 \ + vrf "${VRF_DEVNAME}" + ip -netns "${rtname}" -4 route \ + add unreachable default metric 4278198272 \ + vrf "${VRF_DEVNAME}" + + ip -netns "${rtname}" addr \ + add "${IPv6_HS_NETWORK}::254/64" dev "${RT2HS_DEVNAME}" nodad + ip -netns "${rtname}" addr \ + add "${IPv4_HS_NETWORK}.254/24" dev "${RT2HS_DEVNAME}" + + ip -netns "${rtname}" link set "${RT2HS_DEVNAME}" up + + ip netns exec "${rtname}" \ + sysctl -wq net.ipv6.conf."${RT2HS_DEVNAME}".proxy_ndp=1 + ip netns exec "${rtname}" \ + sysctl -wq net.ipv4.conf."${RT2HS_DEVNAME}".proxy_arp=1 + + # disable the rp_filter otherwise the kernel gets confused about how + # to route decap ipv4 packets. + ip netns exec "${rtname}" \ + sysctl -wq net.ipv4.conf."${RT2HS_DEVNAME}".rp_filter=0 + + ip netns exec "${rtname}" sh -c "echo 1 > /proc/sys/net/vrf/strict_mode" +} + +setup() +{ + local i + + # create routers + ROUTERS="1 2 3 4"; readonly ROUTERS + for i in ${ROUTERS}; do + create_router "${i}" + done + + # create hosts + HOSTS="1 2"; readonly HOSTS + for i in ${HOSTS}; do + create_host "${i}" + done + + # set up the links for connecting routers + add_link_rt_pairs 1 "2 3 4" + add_link_rt_pairs 2 "3 4" + add_link_rt_pairs 3 "4" + + # set up the basic connectivity of routers and routes required for + # reachability of SIDs. + setup_rt_networking 1 "2 3 4" + setup_rt_networking 2 "1 3 4" + setup_rt_networking 3 "1 2 4" + setup_rt_networking 4 "1 2 3" + + # set up the hosts connected to routers + setup_hs 1 1 + setup_hs 2 2 + + # set up default SRv6 Endpoints (i.e. SRv6 End and SRv6 End.DT46) + setup_rt_local_sids 1 "2 3 4" + setup_rt_local_sids 2 "1 3 4" + setup_rt_local_sids 3 "1 2 4" + setup_rt_local_sids 4 "1 2 3" + + # set up SRv6 Policies + + # create an IPv6 VPN between hosts hs-1 and hs-2. + # + # Direction hs-1 -> hs-2 + # - rt-1 encap (H.Encaps.Red) + # - rt-3 SRv6 End.X behavior adj rt-4 (NEXT-C-SID flavor) + # - rt-4 Plain IPv6 Forwarding to rt-2 + # - rt-2 SRv6 End.DT46 behavior + setup_ipv6_vpn_1sid 1 2 "3" + + # Direction hs2 -> hs-1 + # - rt-2 encap (H.Encaps.Red) + # - rt-4 SRv6 End.X behavior adj rt-1 (NEXT-C-SID flavor) + # - rt-1 SRv6 End.DT46 behavior + setup_ipv6_vpn_1sid 2 1 "4" + + # create an IPv4 VPN between hosts hs-1 and hs-2 + # + # Direction hs-1 -> hs-2 + # - rt-1 encap (H.Encaps.Red) + # - rt-3 SRv6 End.X behavior adj rt-4 (NEXT-C-SID flavor) + # - rt-4 Plain IPv6 Forwarding to rt-2 + # - rt-2 SRv6 End.DT46 behavior + setup_ipv4_vpn_2sids 1 2 "3" + + # Direction hs-2 -> hs-1 + # - rt-2 encap (H.Encaps.Red) + # - rt-3 SRv6 End.X behavior adj rt-4 (NEXT-C-SID flavor) + # - rt-4 Plain IPv6 Forwarding to rt-1 + # - rt-1 SRv6 End.DT46 behavior + setup_ipv4_vpn_2sids 2 1 "3" + + # Setup the adjacencies in the SRv6 aware routers + # - rt-3 SRv6 End.X adjacency with rt-4 + # - rt-4 SRv6 End.X adjacency with rt-1 + set_end_x_nextcsid 3 4 + set_end_x_nextcsid 4 1 + + # testing environment was set up successfully + SETUP_ERR=0 +} + +check_rt_connectivity() +{ + local rtsrc="$1" + local rtdst="$2" + local prefix + local rtsrc_nsname + + rtsrc_nsname="$(get_rtname "${rtsrc}")" + + prefix="$(get_network_prefix "${rtsrc}" "${rtdst}")" + + ip netns exec "${rtsrc_nsname}" ping -c 1 -W "${PING_TIMEOUT_SEC}" \ + "${prefix}::${rtdst}" >/dev/null 2>&1 +} + +check_and_log_rt_connectivity() +{ + local rtsrc="$1" + local rtdst="$2" + + check_rt_connectivity "${rtsrc}" "${rtdst}" + log_test $? 0 "Routers connectivity: rt-${rtsrc} -> rt-${rtdst}" +} + +check_hs_ipv6_connectivity() +{ + local hssrc="$1" + local hsdst="$2" + local hssrc_nsname + + hssrc_nsname="$(get_hsname "${hssrc}")" + + ip netns exec "${hssrc_nsname}" ping -c 1 -W "${PING_TIMEOUT_SEC}" \ + "${IPv6_HS_NETWORK}::${hsdst}" >/dev/null 2>&1 +} + +check_hs_ipv4_connectivity() +{ + local hssrc="$1" + local hsdst="$2" + local hssrc_nsname + + hssrc_nsname="$(get_hsname "${hssrc}")" + + ip netns exec "${hssrc_nsname}" ping -c 1 -W "${PING_TIMEOUT_SEC}" \ + "${IPv4_HS_NETWORK}.${hsdst}" >/dev/null 2>&1 +} + +check_and_log_hs2gw_connectivity() +{ + local hssrc="$1" + + check_hs_ipv6_connectivity "${hssrc}" 254 + log_test $? 0 "IPv6 Hosts connectivity: hs-${hssrc} -> gw" + + check_hs_ipv4_connectivity "${hssrc}" 254 + log_test $? 0 "IPv4 Hosts connectivity: hs-${hssrc} -> gw" +} + +check_and_log_hs_ipv6_connectivity() +{ + local hssrc="$1" + local hsdst="$2" + + check_hs_ipv6_connectivity "${hssrc}" "${hsdst}" + log_test $? 0 "IPv6 Hosts connectivity: hs-${hssrc} -> hs-${hsdst}" +} + +check_and_log_hs_ipv4_connectivity() +{ + local hssrc="$1" + local hsdst="$2" + + check_hs_ipv4_connectivity "${hssrc}" "${hsdst}" + log_test $? 0 "IPv4 Hosts connectivity: hs-${hssrc} -> hs-${hsdst}" +} + +router_tests() +{ + local i + local j + + log_section "IPv6 routers connectivity test" + + for i in ${ROUTERS}; do + for j in ${ROUTERS}; do + if [ "${i}" -eq "${j}" ]; then + continue + fi + + check_and_log_rt_connectivity "${i}" "${j}" + done + done +} + +host2gateway_tests() +{ + local hs + + log_section "IPv4/IPv6 connectivity test among hosts and gateways" + + for hs in ${HOSTS}; do + check_and_log_hs2gw_connectivity "${hs}" + done +} + +host_vpn_tests() +{ + log_section "SRv6 VPN connectivity test hosts (h1 <-> h2, IPv6)" + + check_and_log_hs_ipv6_connectivity 1 2 + check_and_log_hs_ipv6_connectivity 2 1 + + log_section "SRv6 VPN connectivity test hosts (h1 <-> h2, IPv4)" + + check_and_log_hs_ipv4_connectivity 1 2 + check_and_log_hs_ipv4_connectivity 2 1 +} + +__nextcsid_end_x_behavior_test() +{ + local nsname="$1" + local cmd="$2" + local blen="$3" + local flen="$4" + local layout="" + + if [ "${blen}" != "d" ]; then + layout="${layout} lblen ${blen}" + fi + + if [ "${flen}" != "d" ]; then + layout="${layout} nflen ${flen}" + fi + + ip -netns "${nsname}" -6 route \ + "${cmd}" "${CSID_CNTR_PREFIX}" \ + table "${CSID_CNTR_RT_TABLE}" \ + encap seg6local action End.X nh6 :: \ + flavors next-csid ${layout} \ + dev "${DUMMY_DEVNAME}" &>/dev/null + + return "$?" +} + +rt_x_nextcsid_end_x_behavior_test() +{ + local rt="$1" + local blen="$2" + local flen="$3" + local nsname + local ret + + nsname="$(get_rtname "${rt}")" + + __nextcsid_end_x_behavior_test "${nsname}" "add" "${blen}" "${flen}" + ret="$?" + __nextcsid_end_x_behavior_test "${nsname}" "del" "${blen}" "${flen}" + + return "${ret}" +} + +__parse_csid_container_cfg() +{ + local cfg="$1" + local index="$2" + local out + + echo "${cfg}" | cut -d',' -f"${index}" +} + +csid_container_cfg_tests() +{ + local valid + local blen + local flen + local cfg + local ret + + log_section "C-SID Container config tests (legend: d='kernel default')" + + for cfg in "${CSID_CONTAINER_CFGS[@]}"; do + blen="$(__parse_csid_container_cfg "${cfg}" 1)" + flen="$(__parse_csid_container_cfg "${cfg}" 2)" + valid="$(__parse_csid_container_cfg "${cfg}" 3)" + + rt_x_nextcsid_end_x_behavior_test \ + "${CSID_CNTR_RT_ID_TEST}" \ + "${blen}" \ + "${flen}" + ret="$?" + + if [ "${valid}" == "y" ]; then + log_test "${ret}" 0 \ + "Accept valid C-SID container cfg (lblen=${blen}, nflen=${flen})" + else + log_test "${ret}" 2 \ + "Reject invalid C-SID container cfg (lblen=${blen}, nflen=${flen})" + fi + done +} + +test_iproute2_supp_or_ksft_skip() +{ + if ! ip route help 2>&1 | grep -qo "next-csid"; then + echo "SKIP: Missing SRv6 NEXT-C-SID flavor support in iproute2" + exit "${ksft_skip}" + fi +} + +test_dummy_dev_or_ksft_skip() +{ + local test_netns + + test_netns="dummy-$(mktemp -u XXXXXXXX)" + + if ! ip netns add "${test_netns}"; then + echo "SKIP: Cannot set up netns for testing dummy dev support" + exit "${ksft_skip}" + fi + + modprobe dummy &>/dev/null || true + if ! ip -netns "${test_netns}" link \ + add "${DUMMY_DEVNAME}" type dummy; then + echo "SKIP: dummy dev not supported" + + ip netns del "${test_netns}" + exit "${ksft_skip}" + fi + + ip netns del "${test_netns}" +} + +test_vrf_or_ksft_skip() +{ + modprobe vrf &>/dev/null || true + if [ ! -e /proc/sys/net/vrf/strict_mode ]; then + echo "SKIP: vrf sysctl does not exist" + exit "${ksft_skip}" + fi +} + +if [ "$(id -u)" -ne 0 ]; then + echo "SKIP: Need root privileges" + exit "${ksft_skip}" +fi + +# required programs to carry out this selftest +test_command_or_ksft_skip ip +test_command_or_ksft_skip ping +test_command_or_ksft_skip sysctl +test_command_or_ksft_skip grep +test_command_or_ksft_skip cut + +test_iproute2_supp_or_ksft_skip +test_dummy_dev_or_ksft_skip +test_vrf_or_ksft_skip + +set -e +trap cleanup EXIT + +setup +set +e + +csid_container_cfg_tests + +router_tests +host2gateway_tests +host_vpn_tests + +print_log_test_results diff --git a/tools/testing/selftests/net/tcp_mmap.c b/tools/testing/selftests/net/tcp_mmap.c index 6e59b1461dcc..4fcce5150850 100644 --- a/tools/testing/selftests/net/tcp_mmap.c +++ b/tools/testing/selftests/net/tcp_mmap.c @@ -153,6 +153,19 @@ static void *mmap_large_buffer(size_t need, size_t *allocated) return buffer; } +static uint32_t tcp_info_get_rcv_mss(int fd) +{ + socklen_t sz = sizeof(struct tcp_info); + struct tcp_info info; + + if (getsockopt(fd, IPPROTO_TCP, TCP_INFO, &info, &sz)) { + fprintf(stderr, "Error fetching TCP_INFO\n"); + return 0; + } + + return info.tcpi_rcv_mss; +} + void *child_thread(void *arg) { unsigned char digest[SHA256_DIGEST_LENGTH]; @@ -288,7 +301,7 @@ end: total_usec = 1000000*ru.ru_utime.tv_sec + ru.ru_utime.tv_usec + 1000000*ru.ru_stime.tv_sec + ru.ru_stime.tv_usec; printf("received %lg MB (%lg %% mmap'ed) in %lg s, %lg Gbit\n" - " cpu usage user:%lg sys:%lg, %lg usec per MB, %lu c-switches\n", + " cpu usage user:%lg sys:%lg, %lg usec per MB, %lu c-switches, rcv_mss %u\n", total / (1024.0 * 1024.0), 100.0*total_mmap/total, (double)delta_usec / 1000000.0, @@ -296,7 +309,8 @@ end: (double)ru.ru_utime.tv_sec + (double)ru.ru_utime.tv_usec / 1000000.0, (double)ru.ru_stime.tv_sec + (double)ru.ru_stime.tv_usec / 1000000.0, (double)total_usec/mb, - ru.ru_nvcsw); + ru.ru_nvcsw, + tcp_info_get_rcv_mss(fd)); } error: munmap(buffer, buffer_sz); diff --git a/tools/testing/selftests/net/test_bridge_backup_port.sh b/tools/testing/selftests/net/test_bridge_backup_port.sh new file mode 100755 index 000000000000..112cfd8a10ad --- /dev/null +++ b/tools/testing/selftests/net/test_bridge_backup_port.sh @@ -0,0 +1,759 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# This test is for checking bridge backup port and backup nexthop ID +# functionality. The topology consists of two bridge (VTEPs) connected using +# VXLAN. The test checks that when the switch port (swp1) is down, traffic is +# redirected to the VXLAN port (vx0). When a backup nexthop ID is configured, +# the test checks that traffic is redirected with the correct nexthop +# information. +# +# +------------------------------------+ +------------------------------------+ +# | + swp1 + vx0 | | + swp1 + vx0 | +# | | | | | | | | +# | | br0 | | | | | | +# | +------------+-----------+ | | +------------+-----------+ | +# | | | | | | +# | | | | | | +# | + | | + | +# | br0 | | br0 | +# | + | | + | +# | | | | | | +# | | | | | | +# | + | | + | +# | br0.10 | | br0.10 | +# | 192.0.2.65/28 | | 192.0.2.66/28 | +# | | | | +# | | | | +# | 192.0.2.33 | | 192.0.2.34 | +# | + lo | | + lo | +# | | | | +# | | | | +# | 192.0.2.49/28 | | 192.0.2.50/28 | +# | veth0 +-------+ veth0 | +# | | | | +# | sw1 | | sw2 | +# +------------------------------------+ +------------------------------------+ + +ret=0 +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +# All tests in this script. Can be overridden with -t option. +TESTS=" + backup_port + backup_nhid + backup_nhid_invalid + backup_nhid_ping + backup_nhid_torture +" +VERBOSE=0 +PAUSE_ON_FAIL=no +PAUSE=no +PING_TIMEOUT=5 + +################################################################################ +# Utilities + +log_test() +{ + local rc=$1 + local expected=$2 + local msg="$3" + + if [ ${rc} -eq ${expected} ]; then + printf "TEST: %-60s [ OK ]\n" "${msg}" + nsuccess=$((nsuccess+1)) + else + ret=1 + nfail=$((nfail+1)) + printf "TEST: %-60s [FAIL]\n" "${msg}" + if [ "$VERBOSE" = "1" ]; then + echo " rc=$rc, expected $expected" + fi + + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi + fi + + if [ "${PAUSE}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi + + [ "$VERBOSE" = "1" ] && echo +} + +run_cmd() +{ + local cmd="$1" + local out + local stderr="2>/dev/null" + + if [ "$VERBOSE" = "1" ]; then + printf "COMMAND: $cmd\n" + stderr= + fi + + out=$(eval $cmd $stderr) + rc=$? + if [ "$VERBOSE" = "1" -a -n "$out" ]; then + echo " $out" + fi + + return $rc +} + +tc_check_packets() +{ + local ns=$1; shift + local id=$1; shift + local handle=$1; shift + local count=$1; shift + local pkts + + sleep 0.1 + pkts=$(tc -n $ns -j -s filter show $id \ + | jq ".[] | select(.options.handle == $handle) | \ + .options.actions[0].stats.packets") + [[ $pkts == $count ]] +} + +################################################################################ +# Setup + +setup_topo_ns() +{ + local ns=$1; shift + + ip netns add $ns + ip -n $ns link set dev lo up + + ip netns exec $ns sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1 + ip netns exec $ns sysctl -qw net.ipv6.conf.default.ignore_routes_with_linkdown=1 + ip netns exec $ns sysctl -qw net.ipv6.conf.all.accept_dad=0 + ip netns exec $ns sysctl -qw net.ipv6.conf.default.accept_dad=0 +} + +setup_topo() +{ + local ns + + for ns in sw1 sw2; do + setup_topo_ns $ns + done + + ip link add name veth0 type veth peer name veth1 + ip link set dev veth0 netns sw1 name veth0 + ip link set dev veth1 netns sw2 name veth0 +} + +setup_sw_common() +{ + local ns=$1; shift + local local_addr=$1; shift + local remote_addr=$1; shift + local veth_addr=$1; shift + local gw_addr=$1; shift + local br_addr=$1; shift + + ip -n $ns address add $local_addr/32 dev lo + + ip -n $ns link set dev veth0 up + ip -n $ns address add $veth_addr/28 dev veth0 + ip -n $ns route add default via $gw_addr + + ip -n $ns link add name br0 up type bridge vlan_filtering 1 \ + vlan_default_pvid 0 mcast_snooping 0 + + ip -n $ns link add link br0 name br0.10 up type vlan id 10 + bridge -n $ns vlan add vid 10 dev br0 self + ip -n $ns address add $br_addr/28 dev br0.10 + + ip -n $ns link add name swp1 up type dummy + ip -n $ns link set dev swp1 master br0 + bridge -n $ns vlan add vid 10 dev swp1 untagged + + ip -n $ns link add name vx0 up master br0 type vxlan \ + local $local_addr dstport 4789 nolearning external + bridge -n $ns link set dev vx0 vlan_tunnel on learning off + + bridge -n $ns vlan add vid 10 dev vx0 + bridge -n $ns vlan add vid 10 dev vx0 tunnel_info id 10010 +} + +setup_sw1() +{ + local ns=sw1 + local local_addr=192.0.2.33 + local remote_addr=192.0.2.34 + local veth_addr=192.0.2.49 + local gw_addr=192.0.2.50 + local br_addr=192.0.2.65 + + setup_sw_common $ns $local_addr $remote_addr $veth_addr $gw_addr \ + $br_addr +} + +setup_sw2() +{ + local ns=sw2 + local local_addr=192.0.2.34 + local remote_addr=192.0.2.33 + local veth_addr=192.0.2.50 + local gw_addr=192.0.2.49 + local br_addr=192.0.2.66 + + setup_sw_common $ns $local_addr $remote_addr $veth_addr $gw_addr \ + $br_addr +} + +setup() +{ + set -e + + setup_topo + setup_sw1 + setup_sw2 + + sleep 5 + + set +e +} + +cleanup() +{ + local ns + + for ns in h1 h2 sw1 sw2; do + ip netns del $ns &> /dev/null + done +} + +################################################################################ +# Tests + +backup_port() +{ + local dmac=00:11:22:33:44:55 + local smac=00:aa:bb:cc:dd:ee + + echo + echo "Backup port" + echo "-----------" + + run_cmd "tc -n sw1 qdisc replace dev swp1 clsact" + run_cmd "tc -n sw1 filter replace dev swp1 egress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac action pass" + + run_cmd "tc -n sw1 qdisc replace dev vx0 clsact" + run_cmd "tc -n sw1 filter replace dev vx0 egress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac action pass" + + run_cmd "bridge -n sw1 fdb replace $dmac dev swp1 master static vlan 10" + + # Initial state - check that packets are forwarded out of swp1 when it + # has a carrier and not forwarded out of any port when it does not have + # a carrier. + run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" + tc_check_packets sw1 "dev swp1 egress" 101 1 + log_test $? 0 "Forwarding out of swp1" + tc_check_packets sw1 "dev vx0 egress" 101 0 + log_test $? 0 "No forwarding out of vx0" + + run_cmd "ip -n sw1 link set dev swp1 carrier off" + log_test $? 0 "swp1 carrier off" + + run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" + tc_check_packets sw1 "dev swp1 egress" 101 1 + log_test $? 0 "No forwarding out of swp1" + tc_check_packets sw1 "dev vx0 egress" 101 0 + log_test $? 0 "No forwarding out of vx0" + + run_cmd "ip -n sw1 link set dev swp1 carrier on" + log_test $? 0 "swp1 carrier on" + + # Configure vx0 as the backup port of swp1 and check that packets are + # forwarded out of swp1 when it has a carrier and out of vx0 when swp1 + # does not have a carrier. + run_cmd "bridge -n sw1 link set dev swp1 backup_port vx0" + run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_port vx0\"" + log_test $? 0 "vx0 configured as backup port of swp1" + + run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" + tc_check_packets sw1 "dev swp1 egress" 101 2 + log_test $? 0 "Forwarding out of swp1" + tc_check_packets sw1 "dev vx0 egress" 101 0 + log_test $? 0 "No forwarding out of vx0" + + run_cmd "ip -n sw1 link set dev swp1 carrier off" + log_test $? 0 "swp1 carrier off" + + run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" + tc_check_packets sw1 "dev swp1 egress" 101 2 + log_test $? 0 "No forwarding out of swp1" + tc_check_packets sw1 "dev vx0 egress" 101 1 + log_test $? 0 "Forwarding out of vx0" + + run_cmd "ip -n sw1 link set dev swp1 carrier on" + log_test $? 0 "swp1 carrier on" + + run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" + tc_check_packets sw1 "dev swp1 egress" 101 3 + log_test $? 0 "Forwarding out of swp1" + tc_check_packets sw1 "dev vx0 egress" 101 1 + log_test $? 0 "No forwarding out of vx0" + + # Remove vx0 as the backup port of swp1 and check that packets are no + # longer forwarded out of vx0 when swp1 does not have a carrier. + run_cmd "bridge -n sw1 link set dev swp1 nobackup_port" + run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_port vx0\"" + log_test $? 1 "vx0 not configured as backup port of swp1" + + run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" + tc_check_packets sw1 "dev swp1 egress" 101 4 + log_test $? 0 "Forwarding out of swp1" + tc_check_packets sw1 "dev vx0 egress" 101 1 + log_test $? 0 "No forwarding out of vx0" + + run_cmd "ip -n sw1 link set dev swp1 carrier off" + log_test $? 0 "swp1 carrier off" + + run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" + tc_check_packets sw1 "dev swp1 egress" 101 4 + log_test $? 0 "No forwarding out of swp1" + tc_check_packets sw1 "dev vx0 egress" 101 1 + log_test $? 0 "No forwarding out of vx0" +} + +backup_nhid() +{ + local dmac=00:11:22:33:44:55 + local smac=00:aa:bb:cc:dd:ee + + echo + echo "Backup nexthop ID" + echo "-----------------" + + run_cmd "tc -n sw1 qdisc replace dev swp1 clsact" + run_cmd "tc -n sw1 filter replace dev swp1 egress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac action pass" + + run_cmd "tc -n sw1 qdisc replace dev vx0 clsact" + run_cmd "tc -n sw1 filter replace dev vx0 egress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac action pass" + + run_cmd "ip -n sw1 nexthop replace id 1 via 192.0.2.34 fdb" + run_cmd "ip -n sw1 nexthop replace id 2 via 192.0.2.34 fdb" + run_cmd "ip -n sw1 nexthop replace id 10 group 1/2 fdb" + + run_cmd "bridge -n sw1 fdb replace $dmac dev swp1 master static vlan 10" + run_cmd "bridge -n sw1 fdb replace $dmac dev vx0 self static dst 192.0.2.36 src_vni 10010" + + run_cmd "ip -n sw2 address replace 192.0.2.36/32 dev lo" + + # The first filter matches on packets forwarded using the backup + # nexthop ID and the second filter matches on packets forwarded using a + # regular VXLAN FDB entry. + run_cmd "tc -n sw2 qdisc replace dev vx0 clsact" + run_cmd "tc -n sw2 filter replace dev vx0 ingress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac enc_key_id 10010 enc_dst_ip 192.0.2.34 action pass" + run_cmd "tc -n sw2 filter replace dev vx0 ingress pref 1 handle 102 proto ip flower src_mac $smac dst_mac $dmac enc_key_id 10010 enc_dst_ip 192.0.2.36 action pass" + + # Configure vx0 as the backup port of swp1 and check that packets are + # forwarded out of swp1 when it has a carrier and out of vx0 when swp1 + # does not have a carrier. When packets are forwarded out of vx0, check + # that they are forwarded by the VXLAN FDB entry. + run_cmd "bridge -n sw1 link set dev swp1 backup_port vx0" + run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_port vx0\"" + log_test $? 0 "vx0 configured as backup port of swp1" + + run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" + tc_check_packets sw1 "dev swp1 egress" 101 1 + log_test $? 0 "Forwarding out of swp1" + tc_check_packets sw1 "dev vx0 egress" 101 0 + log_test $? 0 "No forwarding out of vx0" + + run_cmd "ip -n sw1 link set dev swp1 carrier off" + log_test $? 0 "swp1 carrier off" + + run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" + tc_check_packets sw1 "dev swp1 egress" 101 1 + log_test $? 0 "No forwarding out of swp1" + tc_check_packets sw1 "dev vx0 egress" 101 1 + log_test $? 0 "Forwarding out of vx0" + tc_check_packets sw2 "dev vx0 ingress" 101 0 + log_test $? 0 "No forwarding using backup nexthop ID" + tc_check_packets sw2 "dev vx0 ingress" 102 1 + log_test $? 0 "Forwarding using VXLAN FDB entry" + + run_cmd "ip -n sw1 link set dev swp1 carrier on" + log_test $? 0 "swp1 carrier on" + + # Configure nexthop ID 10 as the backup nexthop ID of swp1 and check + # that when packets are forwarded out of vx0, they are forwarded using + # the backup nexthop ID. + run_cmd "bridge -n sw1 link set dev swp1 backup_nhid 10" + run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_nhid 10\"" + log_test $? 0 "nexthop ID 10 configured as backup nexthop ID of swp1" + + run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" + tc_check_packets sw1 "dev swp1 egress" 101 2 + log_test $? 0 "Forwarding out of swp1" + tc_check_packets sw1 "dev vx0 egress" 101 1 + log_test $? 0 "No forwarding out of vx0" + + run_cmd "ip -n sw1 link set dev swp1 carrier off" + log_test $? 0 "swp1 carrier off" + + run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" + tc_check_packets sw1 "dev swp1 egress" 101 2 + log_test $? 0 "No forwarding out of swp1" + tc_check_packets sw1 "dev vx0 egress" 101 2 + log_test $? 0 "Forwarding out of vx0" + tc_check_packets sw2 "dev vx0 ingress" 101 1 + log_test $? 0 "Forwarding using backup nexthop ID" + tc_check_packets sw2 "dev vx0 ingress" 102 1 + log_test $? 0 "No forwarding using VXLAN FDB entry" + + run_cmd "ip -n sw1 link set dev swp1 carrier on" + log_test $? 0 "swp1 carrier on" + + run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" + tc_check_packets sw1 "dev swp1 egress" 101 3 + log_test $? 0 "Forwarding out of swp1" + tc_check_packets sw1 "dev vx0 egress" 101 2 + log_test $? 0 "No forwarding out of vx0" + tc_check_packets sw2 "dev vx0 ingress" 101 1 + log_test $? 0 "No forwarding using backup nexthop ID" + tc_check_packets sw2 "dev vx0 ingress" 102 1 + log_test $? 0 "No forwarding using VXLAN FDB entry" + + # Reset the backup nexthop ID to 0 and check that packets are no longer + # forwarded using the backup nexthop ID when swp1 does not have a + # carrier and are instead forwarded by the VXLAN FDB. + run_cmd "bridge -n sw1 link set dev swp1 backup_nhid 0" + run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_nhid\"" + log_test $? 1 "No backup nexthop ID configured for swp1" + + run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" + tc_check_packets sw1 "dev swp1 egress" 101 4 + log_test $? 0 "Forwarding out of swp1" + tc_check_packets sw1 "dev vx0 egress" 101 2 + log_test $? 0 "No forwarding out of vx0" + tc_check_packets sw2 "dev vx0 ingress" 101 1 + log_test $? 0 "No forwarding using backup nexthop ID" + tc_check_packets sw2 "dev vx0 ingress" 102 1 + log_test $? 0 "No forwarding using VXLAN FDB entry" + + run_cmd "ip -n sw1 link set dev swp1 carrier off" + log_test $? 0 "swp1 carrier off" + + run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" + tc_check_packets sw1 "dev swp1 egress" 101 4 + log_test $? 0 "No forwarding out of swp1" + tc_check_packets sw1 "dev vx0 egress" 101 3 + log_test $? 0 "Forwarding out of vx0" + tc_check_packets sw2 "dev vx0 ingress" 101 1 + log_test $? 0 "No forwarding using backup nexthop ID" + tc_check_packets sw2 "dev vx0 ingress" 102 2 + log_test $? 0 "Forwarding using VXLAN FDB entry" +} + +backup_nhid_invalid() +{ + local dmac=00:11:22:33:44:55 + local smac=00:aa:bb:cc:dd:ee + local tx_drop + + echo + echo "Backup nexthop ID - invalid IDs" + echo "-------------------------------" + + # Check that when traffic is redirected with an invalid nexthop ID, it + # is forwarded out of the VXLAN port, but dropped by the VXLAN driver + # and does not crash the host. + + run_cmd "tc -n sw1 qdisc replace dev swp1 clsact" + run_cmd "tc -n sw1 filter replace dev swp1 egress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac action pass" + + run_cmd "tc -n sw1 qdisc replace dev vx0 clsact" + run_cmd "tc -n sw1 filter replace dev vx0 egress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac action pass" + # Drop all other Tx traffic to avoid changes to Tx drop counter. + run_cmd "tc -n sw1 filter replace dev vx0 egress pref 2 handle 102 proto all matchall action drop" + + tx_drop=$(ip -n sw1 -s -j link show dev vx0 | jq '.[]["stats64"]["tx"]["dropped"]') + + run_cmd "ip -n sw1 nexthop replace id 1 via 192.0.2.34 fdb" + run_cmd "ip -n sw1 nexthop replace id 2 via 192.0.2.34 fdb" + run_cmd "ip -n sw1 nexthop replace id 10 group 1/2 fdb" + + run_cmd "bridge -n sw1 fdb replace $dmac dev swp1 master static vlan 10" + + run_cmd "tc -n sw2 qdisc replace dev vx0 clsact" + run_cmd "tc -n sw2 filter replace dev vx0 ingress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac enc_key_id 10010 enc_dst_ip 192.0.2.34 action pass" + + # First, check that redirection works. + run_cmd "bridge -n sw1 link set dev swp1 backup_port vx0" + run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_port vx0\"" + log_test $? 0 "vx0 configured as backup port of swp1" + + run_cmd "bridge -n sw1 link set dev swp1 backup_nhid 10" + run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_nhid 10\"" + log_test $? 0 "Valid nexthop as backup nexthop" + + run_cmd "ip -n sw1 link set dev swp1 carrier off" + log_test $? 0 "swp1 carrier off" + + run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" + tc_check_packets sw1 "dev swp1 egress" 101 0 + log_test $? 0 "No forwarding out of swp1" + tc_check_packets sw1 "dev vx0 egress" 101 1 + log_test $? 0 "Forwarding out of vx0" + tc_check_packets sw2 "dev vx0 ingress" 101 1 + log_test $? 0 "Forwarding using backup nexthop ID" + run_cmd "ip -n sw1 -s -j link show dev vx0 | jq -e '.[][\"stats64\"][\"tx\"][\"dropped\"] == $tx_drop'" + log_test $? 0 "No Tx drop increase" + + # Use a non-existent nexthop ID. + run_cmd "bridge -n sw1 link set dev swp1 backup_nhid 20" + run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_nhid 20\"" + log_test $? 0 "Non-existent nexthop as backup nexthop" + + run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" + tc_check_packets sw1 "dev swp1 egress" 101 0 + log_test $? 0 "No forwarding out of swp1" + tc_check_packets sw1 "dev vx0 egress" 101 2 + log_test $? 0 "Forwarding out of vx0" + tc_check_packets sw2 "dev vx0 ingress" 101 1 + log_test $? 0 "No forwarding using backup nexthop ID" + run_cmd "ip -n sw1 -s -j link show dev vx0 | jq -e '.[][\"stats64\"][\"tx\"][\"dropped\"] == $((tx_drop + 1))'" + log_test $? 0 "Tx drop increased" + + # Use a blckhole nexthop. + run_cmd "ip -n sw1 nexthop replace id 30 blackhole" + run_cmd "bridge -n sw1 link set dev swp1 backup_nhid 30" + run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_nhid 30\"" + log_test $? 0 "Blackhole nexthop as backup nexthop" + + run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" + tc_check_packets sw1 "dev swp1 egress" 101 0 + log_test $? 0 "No forwarding out of swp1" + tc_check_packets sw1 "dev vx0 egress" 101 3 + log_test $? 0 "Forwarding out of vx0" + tc_check_packets sw2 "dev vx0 ingress" 101 1 + log_test $? 0 "No forwarding using backup nexthop ID" + run_cmd "ip -n sw1 -s -j link show dev vx0 | jq -e '.[][\"stats64\"][\"tx\"][\"dropped\"] == $((tx_drop + 2))'" + log_test $? 0 "Tx drop increased" + + # Non-group FDB nexthop. + run_cmd "bridge -n sw1 link set dev swp1 backup_nhid 1" + run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_nhid 1\"" + log_test $? 0 "Non-group FDB nexthop as backup nexthop" + + run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" + tc_check_packets sw1 "dev swp1 egress" 101 0 + log_test $? 0 "No forwarding out of swp1" + tc_check_packets sw1 "dev vx0 egress" 101 4 + log_test $? 0 "Forwarding out of vx0" + tc_check_packets sw2 "dev vx0 ingress" 101 1 + log_test $? 0 "No forwarding using backup nexthop ID" + run_cmd "ip -n sw1 -s -j link show dev vx0 | jq -e '.[][\"stats64\"][\"tx\"][\"dropped\"] == $((tx_drop + 3))'" + log_test $? 0 "Tx drop increased" + + # IPv6 address family nexthop. + run_cmd "ip -n sw1 nexthop replace id 100 via 2001:db8:100::1 fdb" + run_cmd "ip -n sw1 nexthop replace id 200 via 2001:db8:100::1 fdb" + run_cmd "ip -n sw1 nexthop replace id 300 group 100/200 fdb" + run_cmd "bridge -n sw1 link set dev swp1 backup_nhid 300" + run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_nhid 300\"" + log_test $? 0 "IPv6 address family nexthop as backup nexthop" + + run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" + tc_check_packets sw1 "dev swp1 egress" 101 0 + log_test $? 0 "No forwarding out of swp1" + tc_check_packets sw1 "dev vx0 egress" 101 5 + log_test $? 0 "Forwarding out of vx0" + tc_check_packets sw2 "dev vx0 ingress" 101 1 + log_test $? 0 "No forwarding using backup nexthop ID" + run_cmd "ip -n sw1 -s -j link show dev vx0 | jq -e '.[][\"stats64\"][\"tx\"][\"dropped\"] == $((tx_drop + 4))'" + log_test $? 0 "Tx drop increased" +} + +backup_nhid_ping() +{ + local sw1_mac + local sw2_mac + + echo + echo "Backup nexthop ID - ping" + echo "------------------------" + + # Test bidirectional traffic when traffic is redirected in both VTEPs. + sw1_mac=$(ip -n sw1 -j -p link show br0.10 | jq -r '.[]["address"]') + sw2_mac=$(ip -n sw2 -j -p link show br0.10 | jq -r '.[]["address"]') + + run_cmd "bridge -n sw1 fdb replace $sw2_mac dev swp1 master static vlan 10" + run_cmd "bridge -n sw2 fdb replace $sw1_mac dev swp1 master static vlan 10" + + run_cmd "ip -n sw1 neigh replace 192.0.2.66 lladdr $sw2_mac nud perm dev br0.10" + run_cmd "ip -n sw2 neigh replace 192.0.2.65 lladdr $sw1_mac nud perm dev br0.10" + + run_cmd "ip -n sw1 nexthop replace id 1 via 192.0.2.34 fdb" + run_cmd "ip -n sw2 nexthop replace id 1 via 192.0.2.33 fdb" + run_cmd "ip -n sw1 nexthop replace id 10 group 1 fdb" + run_cmd "ip -n sw2 nexthop replace id 10 group 1 fdb" + + run_cmd "bridge -n sw1 link set dev swp1 backup_port vx0" + run_cmd "bridge -n sw2 link set dev swp1 backup_port vx0" + run_cmd "bridge -n sw1 link set dev swp1 backup_nhid 10" + run_cmd "bridge -n sw2 link set dev swp1 backup_nhid 10" + + run_cmd "ip -n sw1 link set dev swp1 carrier off" + run_cmd "ip -n sw2 link set dev swp1 carrier off" + + run_cmd "ip netns exec sw1 ping -i 0.1 -c 10 -w $PING_TIMEOUT 192.0.2.66" + log_test $? 0 "Ping with backup nexthop ID" + + # Reset the backup nexthop ID to 0 and check that ping fails. + run_cmd "bridge -n sw1 link set dev swp1 backup_nhid 0" + run_cmd "bridge -n sw2 link set dev swp1 backup_nhid 0" + + run_cmd "ip netns exec sw1 ping -i 0.1 -c 10 -w $PING_TIMEOUT 192.0.2.66" + log_test $? 1 "Ping after disabling backup nexthop ID" +} + +backup_nhid_add_del_loop() +{ + while true; do + ip -n sw1 nexthop del id 10 + ip -n sw1 nexthop replace id 10 group 1/2 fdb + done >/dev/null 2>&1 +} + +backup_nhid_torture() +{ + local dmac=00:11:22:33:44:55 + local smac=00:aa:bb:cc:dd:ee + local pid1 + local pid2 + local pid3 + + echo + echo "Backup nexthop ID - torture test" + echo "--------------------------------" + + # Continuously send traffic through the backup nexthop while adding and + # deleting the group. The test is considered successful if nothing + # crashed. + + run_cmd "ip -n sw1 nexthop replace id 1 via 192.0.2.34 fdb" + run_cmd "ip -n sw1 nexthop replace id 2 via 192.0.2.34 fdb" + run_cmd "ip -n sw1 nexthop replace id 10 group 1/2 fdb" + + run_cmd "bridge -n sw1 fdb replace $dmac dev swp1 master static vlan 10" + + run_cmd "bridge -n sw1 link set dev swp1 backup_port vx0" + run_cmd "bridge -n sw1 link set dev swp1 backup_nhid 10" + run_cmd "ip -n sw1 link set dev swp1 carrier off" + + backup_nhid_add_del_loop & + pid1=$! + ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 0 & + pid2=$! + + sleep 30 + kill -9 $pid1 $pid2 + wait $pid1 $pid2 2>/dev/null + + log_test 0 0 "Torture test" +} + +################################################################################ +# Usage + +usage() +{ + cat <<EOF +usage: ${0##*/} OPTS + + -t <test> Test(s) to run (default: all) + (options: $TESTS) + -p Pause on fail + -P Pause after each test before cleanup + -v Verbose mode (show commands and output) + -w Timeout for ping +EOF +} + +################################################################################ +# Main + +trap cleanup EXIT + +while getopts ":t:pPvhw:" opt; do + case $opt in + t) TESTS=$OPTARG;; + p) PAUSE_ON_FAIL=yes;; + P) PAUSE=yes;; + v) VERBOSE=$(($VERBOSE + 1));; + w) PING_TIMEOUT=$OPTARG;; + h) usage; exit 0;; + *) usage; exit 1;; + esac +done + +# Make sure we don't pause twice. +[ "${PAUSE}" = "yes" ] && PAUSE_ON_FAIL=no + +if [ "$(id -u)" -ne 0 ];then + echo "SKIP: Need root privileges" + exit $ksft_skip; +fi + +if [ ! -x "$(command -v ip)" ]; then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +if [ ! -x "$(command -v bridge)" ]; then + echo "SKIP: Could not run test without bridge tool" + exit $ksft_skip +fi + +if [ ! -x "$(command -v tc)" ]; then + echo "SKIP: Could not run test without tc tool" + exit $ksft_skip +fi + +if [ ! -x "$(command -v mausezahn)" ]; then + echo "SKIP: Could not run test without mausezahn tool" + exit $ksft_skip +fi + +if [ ! -x "$(command -v jq)" ]; then + echo "SKIP: Could not run test without jq tool" + exit $ksft_skip +fi + +bridge link help 2>&1 | grep -q "backup_nhid" +if [ $? -ne 0 ]; then + echo "SKIP: iproute2 bridge too old, missing backup nexthop ID support" + exit $ksft_skip +fi + +# Start clean. +cleanup + +for t in $TESTS +do + setup; $t; cleanup; +done + +if [ "$TESTS" != "none" ]; then + printf "\nTests passed: %3d\n" ${nsuccess} + printf "Tests failed: %3d\n" ${nfail} +fi + +exit $ret diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index a3c57004344c..297d972558fb 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -30,12 +30,15 @@ static int fips_enabled; struct tls_crypto_info_keys { union { + struct tls_crypto_info crypto_info; struct tls12_crypto_info_aes_gcm_128 aes128; struct tls12_crypto_info_chacha20_poly1305 chacha20; struct tls12_crypto_info_sm4_gcm sm4gcm; struct tls12_crypto_info_sm4_ccm sm4ccm; struct tls12_crypto_info_aes_ccm_128 aesccm128; struct tls12_crypto_info_aes_gcm_256 aesgcm256; + struct tls12_crypto_info_aria_gcm_128 ariagcm128; + struct tls12_crypto_info_aria_gcm_256 ariagcm256; }; size_t len; }; @@ -76,6 +79,16 @@ static void tls_crypto_info_init(uint16_t tls_version, uint16_t cipher_type, tls12->aesgcm256.info.version = tls_version; tls12->aesgcm256.info.cipher_type = cipher_type; break; + case TLS_CIPHER_ARIA_GCM_128: + tls12->len = sizeof(struct tls12_crypto_info_aria_gcm_128); + tls12->ariagcm128.info.version = tls_version; + tls12->ariagcm128.info.cipher_type = cipher_type; + break; + case TLS_CIPHER_ARIA_GCM_256: + tls12->len = sizeof(struct tls12_crypto_info_aria_gcm_256); + tls12->ariagcm256.info.version = tls_version; + tls12->ariagcm256.info.cipher_type = cipher_type; + break; default: break; } @@ -228,6 +241,31 @@ TEST_F(tls_basic, base_base) EXPECT_EQ(memcmp(buf, test_str, send_len), 0); }; +TEST_F(tls_basic, bad_cipher) +{ + struct tls_crypto_info_keys tls12; + + tls12.crypto_info.version = 200; + tls12.crypto_info.cipher_type = TLS_CIPHER_AES_GCM_128; + EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, sizeof(struct tls12_crypto_info_aes_gcm_128)), -1); + + tls12.crypto_info.version = TLS_1_2_VERSION; + tls12.crypto_info.cipher_type = 50; + EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, sizeof(struct tls12_crypto_info_aes_gcm_128)), -1); + + tls12.crypto_info.version = TLS_1_2_VERSION; + tls12.crypto_info.cipher_type = 59; + EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, sizeof(struct tls12_crypto_info_aes_gcm_128)), -1); + + tls12.crypto_info.version = TLS_1_2_VERSION; + tls12.crypto_info.cipher_type = 10; + EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, sizeof(struct tls12_crypto_info_aes_gcm_128)), -1); + + tls12.crypto_info.version = TLS_1_2_VERSION; + tls12.crypto_info.cipher_type = 70; + EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, sizeof(struct tls12_crypto_info_aes_gcm_128)), -1); +} + FIXTURE(tls) { int fd, cfd; @@ -312,6 +350,18 @@ FIXTURE_VARIANT_ADD(tls, 13_nopad) .nopad = true, }; +FIXTURE_VARIANT_ADD(tls, 12_aria_gcm) +{ + .tls_version = TLS_1_2_VERSION, + .cipher_type = TLS_CIPHER_ARIA_GCM_128, +}; + +FIXTURE_VARIANT_ADD(tls, 12_aria_gcm_256) +{ + .tls_version = TLS_1_2_VERSION, + .cipher_type = TLS_CIPHER_ARIA_GCM_256, +}; + FIXTURE_SETUP(tls) { struct tls_crypto_info_keys tls12; @@ -486,6 +536,17 @@ TEST_F(tls, msg_more_unsent) EXPECT_EQ(recv(self->cfd, buf, send_len, MSG_DONTWAIT), -1); } +TEST_F(tls, msg_eor) +{ + char const *test_str = "test_read"; + int send_len = 10; + char buf[10]; + + EXPECT_EQ(send(self->fd, test_str, send_len, MSG_EOR), send_len); + EXPECT_EQ(recv(self->cfd, buf, send_len, MSG_WAITALL), send_len); + EXPECT_EQ(memcmp(buf, test_str, send_len), 0); +} + TEST_F(tls, sendmsg_single) { struct msghdr msg; @@ -1461,6 +1522,40 @@ TEST_F(tls, shutdown_reuse) EXPECT_EQ(errno, EISCONN); } +TEST_F(tls, getsockopt) +{ + struct tls_crypto_info_keys expect, get; + socklen_t len; + + /* get only the version/cipher */ + len = sizeof(struct tls_crypto_info); + memrnd(&get, sizeof(get)); + EXPECT_EQ(getsockopt(self->fd, SOL_TLS, TLS_TX, &get, &len), 0); + EXPECT_EQ(len, sizeof(struct tls_crypto_info)); + EXPECT_EQ(get.crypto_info.version, variant->tls_version); + EXPECT_EQ(get.crypto_info.cipher_type, variant->cipher_type); + + /* get the full crypto_info */ + tls_crypto_info_init(variant->tls_version, variant->cipher_type, &expect); + len = expect.len; + memrnd(&get, sizeof(get)); + EXPECT_EQ(getsockopt(self->fd, SOL_TLS, TLS_TX, &get, &len), 0); + EXPECT_EQ(len, expect.len); + EXPECT_EQ(get.crypto_info.version, variant->tls_version); + EXPECT_EQ(get.crypto_info.cipher_type, variant->cipher_type); + EXPECT_EQ(memcmp(&get, &expect, expect.len), 0); + + /* short get should fail */ + len = sizeof(struct tls_crypto_info) - 1; + EXPECT_EQ(getsockopt(self->fd, SOL_TLS, TLS_TX, &get, &len), -1); + EXPECT_EQ(errno, EINVAL); + + /* partial get of the cipher data should fail */ + len = expect.len - 1; + EXPECT_EQ(getsockopt(self->fd, SOL_TLS, TLS_TX, &get, &len), -1); + EXPECT_EQ(errno, EINVAL); +} + FIXTURE(tls_err) { int fd, cfd; diff --git a/tools/testing/selftests/net/vrf_route_leaking.sh b/tools/testing/selftests/net/vrf_route_leaking.sh index 23cf924754a5..dedc52562b4f 100755 --- a/tools/testing/selftests/net/vrf_route_leaking.sh +++ b/tools/testing/selftests/net/vrf_route_leaking.sh @@ -565,7 +565,7 @@ EOF command -v ping6 > /dev/null 2>&1 && ping6=$(command -v ping6) || ping6=$(command -v ping) TESTS_IPV4="ipv4_ping_ttl ipv4_traceroute ipv4_ping_frag ipv4_ping_ttl_asym ipv4_traceroute_asym" -TESTS_IPV6="ipv6_ping_ttl ipv6_traceroute ipv6_ping_frag ipv6_ping_ttl_asym ipv6_traceroute_asym" +TESTS_IPV6="ipv6_ping_ttl ipv6_traceroute ipv6_ping_ttl_asym ipv6_traceroute_asym" ret=0 nsuccess=0 diff --git a/tools/testing/selftests/nolibc/Makefile b/tools/testing/selftests/nolibc/Makefile index 1b7b3c82f8ad..dfe66776a331 100644 --- a/tools/testing/selftests/nolibc/Makefile +++ b/tools/testing/selftests/nolibc/Makefile @@ -14,6 +14,31 @@ include $(srctree)/scripts/subarch.include ARCH = $(SUBARCH) endif +# XARCH extends the kernel's ARCH with a few variants of the same +# architecture that only differ by the configuration, the toolchain +# and the Qemu program used. It is copied as-is into ARCH except for +# a few specific values which are mapped like this: +# +# XARCH | ARCH | config +# -------------|-----------|------------------------- +# ppc | powerpc | 32 bits +# ppc64 | powerpc | 64 bits big endian +# ppc64le | powerpc | 64 bits little endian +# +# It is recommended to only use XARCH, though it does not harm if +# ARCH is already set. For simplicity, ARCH is sufficient for all +# architectures where both are equal. + +# configure default variants for target kernel supported architectures +XARCH_powerpc = ppc +XARCH = $(or $(XARCH_$(ARCH)),$(ARCH)) + +# map from user input variants to their kernel supported architectures +ARCH_ppc = powerpc +ARCH_ppc64 = powerpc +ARCH_ppc64le = powerpc +ARCH := $(or $(ARCH_$(XARCH)),$(XARCH)) + # kernel image names by architecture IMAGE_i386 = arch/x86/boot/bzImage IMAGE_x86_64 = arch/x86/boot/bzImage @@ -21,10 +46,13 @@ IMAGE_x86 = arch/x86/boot/bzImage IMAGE_arm64 = arch/arm64/boot/Image IMAGE_arm = arch/arm/boot/zImage IMAGE_mips = vmlinuz +IMAGE_ppc = vmlinux +IMAGE_ppc64 = vmlinux +IMAGE_ppc64le = arch/powerpc/boot/zImage IMAGE_riscv = arch/riscv/boot/Image IMAGE_s390 = arch/s390/boot/bzImage IMAGE_loongarch = arch/loongarch/boot/vmlinuz.efi -IMAGE = $(IMAGE_$(ARCH)) +IMAGE = $(IMAGE_$(XARCH)) IMAGE_NAME = $(notdir $(IMAGE)) # default kernel configurations that appear to be usable @@ -34,10 +62,13 @@ DEFCONFIG_x86 = defconfig DEFCONFIG_arm64 = defconfig DEFCONFIG_arm = multi_v7_defconfig DEFCONFIG_mips = malta_defconfig +DEFCONFIG_ppc = pmac32_defconfig +DEFCONFIG_ppc64 = powernv_be_defconfig +DEFCONFIG_ppc64le = powernv_defconfig DEFCONFIG_riscv = defconfig DEFCONFIG_s390 = defconfig DEFCONFIG_loongarch = defconfig -DEFCONFIG = $(DEFCONFIG_$(ARCH)) +DEFCONFIG = $(DEFCONFIG_$(XARCH)) # optional tests to run (default = all) TEST = @@ -49,10 +80,13 @@ QEMU_ARCH_x86 = x86_64 QEMU_ARCH_arm64 = aarch64 QEMU_ARCH_arm = arm QEMU_ARCH_mips = mipsel # works with malta_defconfig +QEMU_ARCH_ppc = ppc +QEMU_ARCH_ppc64 = ppc64 +QEMU_ARCH_ppc64le = ppc64le QEMU_ARCH_riscv = riscv64 QEMU_ARCH_s390 = s390x QEMU_ARCH_loongarch = loongarch64 -QEMU_ARCH = $(QEMU_ARCH_$(ARCH)) +QEMU_ARCH = $(QEMU_ARCH_$(XARCH)) # QEMU_ARGS : some arch-specific args to pass to qemu QEMU_ARGS_i386 = -M pc -append "console=ttyS0,9600 i8042.noaux panic=-1 $(TEST:%=NOLIBC_TEST=%)" @@ -61,10 +95,13 @@ QEMU_ARGS_x86 = -M pc -append "console=ttyS0,9600 i8042.noaux panic=-1 $( QEMU_ARGS_arm64 = -M virt -cpu cortex-a53 -append "panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS_arm = -M virt -append "panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS_mips = -M malta -append "panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_ppc = -M g3beige -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_ppc64 = -M powernv -append "console=hvc0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_ppc64le = -M powernv -append "console=hvc0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS_riscv = -M virt -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS_s390 = -M s390-ccw-virtio -m 1G -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS_loongarch = -M virt -append "console=ttyS0,115200 panic=-1 $(TEST:%=NOLIBC_TEST=%)" -QEMU_ARGS = $(QEMU_ARGS_$(ARCH)) $(QEMU_ARGS_EXTRA) +QEMU_ARGS = $(QEMU_ARGS_$(XARCH)) $(QEMU_ARGS_EXTRA) # OUTPUT is only set when run from the main makefile, otherwise # it defaults to this nolibc directory. @@ -76,13 +113,21 @@ else Q=@ endif +CFLAGS_ppc = -m32 -mbig-endian -mno-vsx $(call cc-option,-mmultiple) +CFLAGS_ppc64 = -m64 -mbig-endian -mno-vsx $(call cc-option,-mmultiple) +CFLAGS_ppc64le = -m64 -mlittle-endian -mno-vsx $(call cc-option,-mabi=elfv2) CFLAGS_s390 = -m64 CFLAGS_mips = -EL CFLAGS_STACKPROTECTOR ?= $(call cc-option,-mstack-protector-guard=global $(call cc-option,-fstack-protector-all)) -CFLAGS ?= -Os -fno-ident -fno-asynchronous-unwind-tables -std=c89 \ +CFLAGS ?= -Os -fno-ident -fno-asynchronous-unwind-tables -std=c89 -W -Wall -Wextra \ $(call cc-option,-fno-stack-protector) \ - $(CFLAGS_$(ARCH)) $(CFLAGS_STACKPROTECTOR) -LDFLAGS := -s + $(CFLAGS_$(XARCH)) $(CFLAGS_STACKPROTECTOR) +LDFLAGS := + +REPORT ?= awk '/\[OK\][\r]*$$/{p++} /\[FAIL\][\r]*$$/{if (!f) printf("\n"); f++; print;} /\[SKIPPED\][\r]*$$/{s++} \ + END{ printf("\n%3d test(s): %3d passed, %3d skipped, %3d failed => status: ", p+s+f, p, s, f); \ + if (f) printf("failure\n"); else if (s) printf("warning\n"); else printf("success\n");; \ + printf("\nSee all results in %s\n", ARGV[1]); }' help: @echo "Supported targets under selftests/nolibc:" @@ -91,24 +136,25 @@ help: @echo " sysroot create the nolibc sysroot here (uses \$$ARCH)" @echo " nolibc-test build the executable (uses \$$CC and \$$CROSS_COMPILE)" @echo " libc-test build an executable using the compiler's default libc instead" - @echo " run-user runs the executable under QEMU (uses \$$ARCH, \$$TEST)" + @echo " run-user runs the executable under QEMU (uses \$$XARCH, \$$TEST)" @echo " initramfs prepare the initramfs with nolibc-test" - @echo " defconfig create a fresh new default config (uses \$$ARCH)" - @echo " kernel (re)build the kernel with the initramfs (uses \$$ARCH)" - @echo " run runs the kernel in QEMU after building it (uses \$$ARCH, \$$TEST)" - @echo " rerun runs a previously prebuilt kernel in QEMU (uses \$$ARCH, \$$TEST)" + @echo " defconfig create a fresh new default config (uses \$$XARCH)" + @echo " kernel (re)build the kernel with the initramfs (uses \$$XARCH)" + @echo " run runs the kernel in QEMU after building it (uses \$$XARCH, \$$TEST)" + @echo " rerun runs a previously prebuilt kernel in QEMU (uses \$$XARCH, \$$TEST)" @echo " clean clean the sysroot, initramfs, build and output files" @echo "" @echo "The output file is \"run.out\". Test ranges may be passed using \$$TEST." @echo "" @echo "Currently using the following variables:" @echo " ARCH = $(ARCH)" + @echo " XARCH = $(XARCH)" @echo " CROSS_COMPILE = $(CROSS_COMPILE)" @echo " CC = $(CC)" @echo " OUTPUT = $(OUTPUT)" @echo " TEST = $(TEST)" - @echo " QEMU_ARCH = $(if $(QEMU_ARCH),$(QEMU_ARCH),UNKNOWN_ARCH) [determined from \$$ARCH]" - @echo " IMAGE_NAME = $(if $(IMAGE_NAME),$(IMAGE_NAME),UNKNOWN_ARCH) [determined from \$$ARCH]" + @echo " QEMU_ARCH = $(if $(QEMU_ARCH),$(QEMU_ARCH),UNKNOWN_ARCH) [determined from \$$XARCH]" + @echo " IMAGE_NAME = $(if $(IMAGE_NAME),$(IMAGE_NAME),UNKNOWN_ARCH) [determined from \$$XARCH]" @echo "" all: run @@ -121,20 +167,33 @@ sysroot/$(ARCH)/include: $(Q)$(MAKE) -C ../../../include/nolibc ARCH=$(ARCH) OUTPUT=$(CURDIR)/sysroot/ headers_standalone $(Q)mv sysroot/sysroot sysroot/$(ARCH) +ifneq ($(NOLIBC_SYSROOT),0) nolibc-test: nolibc-test.c sysroot/$(ARCH)/include $(QUIET_CC)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ \ -nostdlib -static -Isysroot/$(ARCH)/include $< -lgcc +else +nolibc-test: nolibc-test.c + $(QUIET_CC)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ \ + -nostdlib -static -include ../../../include/nolibc/nolibc.h $< -lgcc +endif libc-test: nolibc-test.c - $(QUIET_CC)$(CC) -o $@ $< + $(QUIET_CC)$(HOSTCC) -o $@ $< + +# local libc-test +run-libc-test: libc-test + $(Q)./libc-test > "$(CURDIR)/run.out" || : + $(Q)$(REPORT) $(CURDIR)/run.out + +# local nolibc-test +run-nolibc-test: nolibc-test + $(Q)./nolibc-test > "$(CURDIR)/run.out" || : + $(Q)$(REPORT) $(CURDIR)/run.out # qemu user-land test run-user: nolibc-test $(Q)qemu-$(QEMU_ARCH) ./nolibc-test > "$(CURDIR)/run.out" || : - $(Q)awk '/\[OK\][\r]*$$/{p++} /\[FAIL\][\r]*$$/{f++} /\[SKIPPED\][\r]*$$/{s++} \ - END{ printf("%d test(s) passed, %d skipped, %d failed.", p, s, f); \ - if (s+f > 0) printf(" See all results in %s\n", ARGV[1]); else print; }' \ - $(CURDIR)/run.out + $(Q)$(REPORT) $(CURDIR)/run.out initramfs: nolibc-test $(QUIET_MKDIR)mkdir -p initramfs @@ -150,18 +209,16 @@ kernel: initramfs # run the tests after building the kernel run: kernel $(Q)qemu-system-$(QEMU_ARCH) -display none -no-reboot -kernel "$(srctree)/$(IMAGE)" -serial stdio $(QEMU_ARGS) > "$(CURDIR)/run.out" - $(Q)awk '/\[OK\][\r]*$$/{p++} /\[FAIL\][\r]*$$/{f++} /\[SKIPPED\][\r]*$$/{s++} \ - END{ printf("%d test(s) passed, %d skipped, %d failed.", p, s, f); \ - if (s+f > 0) printf(" See all results in %s\n", ARGV[1]); else print; }' \ - $(CURDIR)/run.out + $(Q)$(REPORT) $(CURDIR)/run.out # re-run the tests from an existing kernel rerun: $(Q)qemu-system-$(QEMU_ARCH) -display none -no-reboot -kernel "$(srctree)/$(IMAGE)" -serial stdio $(QEMU_ARGS) > "$(CURDIR)/run.out" - $(Q)awk '/\[OK\][\r]*$$/{p++} /\[FAIL\][\r]*$$/{f++} /\[SKIPPED\][\r]*$$/{s++} \ - END{ printf("%d test(s) passed, %d skipped, %d failed.", p, s, f); \ - if (s+f > 0) printf(" See all results in %s\n", ARGV[1]); else print; }' \ - $(CURDIR)/run.out + $(Q)$(REPORT) $(CURDIR)/run.out + +# report with existing test log +report: + $(Q)$(REPORT) $(CURDIR)/run.out clean: $(call QUIET_CLEAN, sysroot) diff --git a/tools/testing/selftests/nolibc/nolibc-test.c b/tools/testing/selftests/nolibc/nolibc-test.c index 486334981e60..fb3bf91462e2 100644 --- a/tools/testing/selftests/nolibc/nolibc-test.c +++ b/tools/testing/selftests/nolibc/nolibc-test.c @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ #define _GNU_SOURCE +#define _LARGEFILE64_SOURCE /* libc-specific include files * The program may be built in 3 ways: @@ -14,7 +15,7 @@ #include <string.h> #ifndef _NOLIBC_STDIO_H /* standard libcs need more includes */ -#include <linux/reboot.h> +#include <sys/auxv.h> #include <sys/io.h> #include <sys/ioctl.h> #include <sys/mman.h> @@ -40,8 +41,21 @@ #endif #endif -/* will be used by nolibc by getenv() */ -char **environ; +/* for the type of int_fast16_t and int_fast32_t, musl differs from glibc and nolibc */ +#define SINT_MAX_OF_TYPE(type) (((type)1 << (sizeof(type) * 8 - 2)) - (type)1 + ((type)1 << (sizeof(type) * 8 - 2))) +#define SINT_MIN_OF_TYPE(type) (-SINT_MAX_OF_TYPE(type) - 1) + +/* will be used to test initialization of environ */ +static char **test_envp; + +/* will be used to test initialization of argv */ +static char **test_argv; + +/* will be used to test initialization of argc */ +static int test_argc; + +/* will be used by some test cases as readable file, please don't write it */ +static const char *argv0; /* definition of a series of tests */ struct test { @@ -66,7 +80,7 @@ char *itoa(int i) /* returns the error name (e.g. "ENOENT") for common errors, "SUCCESS" for 0, * or the decimal value for less common ones. */ -const char *errorname(int err) +static const char *errorname(int err) { switch (err) { case 0: return "SUCCESS"; @@ -120,17 +134,26 @@ static void putcharn(char c, size_t n) fputs(buf, stdout); } -static int pad_spc(int llen, int cnt, const char *fmt, ...) -{ - va_list args; - int ret; - - putcharn(' ', cnt - llen); +enum RESULT { + OK, + FAIL, + SKIPPED, +}; - va_start(args, fmt); - ret = vfprintf(stdout, fmt, args); - va_end(args); - return ret < 0 ? ret : ret + cnt - llen; +static void result(int llen, enum RESULT r) +{ + const char *msg; + + if (r == OK) + msg = " [OK]"; + else if (r == SKIPPED) + msg = "[SKIPPED]"; + else + msg = "[FAIL]"; + + if (llen < 64) + putcharn(' ', 64 - llen); + puts(msg); } /* The tests below are intended to be used by the macroes, which evaluate @@ -140,173 +163,185 @@ static int pad_spc(int llen, int cnt, const char *fmt, ...) */ #define EXPECT_ZR(cond, expr) \ - do { if (!cond) pad_spc(llen, 64, "[SKIPPED]\n"); else ret += expect_zr(expr, llen); } while (0) + do { if (!(cond)) result(llen, SKIPPED); else ret += expect_zr(expr, llen); } while (0) -static int expect_zr(int expr, int llen) +static __attribute__((unused)) +int expect_zr(int expr, int llen) { int ret = !(expr == 0); llen += printf(" = %d ", expr); - pad_spc(llen, 64, ret ? "[FAIL]\n" : " [OK]\n"); + result(llen, ret ? FAIL : OK); return ret; } #define EXPECT_NZ(cond, expr, val) \ - do { if (!cond) pad_spc(llen, 64, "[SKIPPED]\n"); else ret += expect_nz(expr, llen; } while (0) + do { if (!(cond)) result(llen, SKIPPED); else ret += expect_nz(expr, llen; } while (0) -static int expect_nz(int expr, int llen) +static __attribute__((unused)) +int expect_nz(int expr, int llen) { int ret = !(expr != 0); llen += printf(" = %d ", expr); - pad_spc(llen, 64, ret ? "[FAIL]\n" : " [OK]\n"); + result(llen, ret ? FAIL : OK); return ret; } #define EXPECT_EQ(cond, expr, val) \ - do { if (!cond) pad_spc(llen, 64, "[SKIPPED]\n"); else ret += expect_eq(expr, llen, val); } while (0) + do { if (!(cond)) result(llen, SKIPPED); else ret += expect_eq(expr, llen, val); } while (0) -static int expect_eq(uint64_t expr, int llen, uint64_t val) +static __attribute__((unused)) +int expect_eq(uint64_t expr, int llen, uint64_t val) { int ret = !(expr == val); llen += printf(" = %lld ", (long long)expr); - pad_spc(llen, 64, ret ? "[FAIL]\n" : " [OK]\n"); + result(llen, ret ? FAIL : OK); return ret; } #define EXPECT_NE(cond, expr, val) \ - do { if (!cond) pad_spc(llen, 64, "[SKIPPED]\n"); else ret += expect_ne(expr, llen, val); } while (0) + do { if (!(cond)) result(llen, SKIPPED); else ret += expect_ne(expr, llen, val); } while (0) -static int expect_ne(int expr, int llen, int val) +static __attribute__((unused)) +int expect_ne(int expr, int llen, int val) { int ret = !(expr != val); llen += printf(" = %d ", expr); - pad_spc(llen, 64, ret ? "[FAIL]\n" : " [OK]\n"); + result(llen, ret ? FAIL : OK); return ret; } #define EXPECT_GE(cond, expr, val) \ - do { if (!cond) pad_spc(llen, 64, "[SKIPPED]\n"); else ret += expect_ge(expr, llen, val); } while (0) + do { if (!(cond)) result(llen, SKIPPED); else ret += expect_ge(expr, llen, val); } while (0) -static int expect_ge(int expr, int llen, int val) +static __attribute__((unused)) +int expect_ge(int expr, int llen, int val) { int ret = !(expr >= val); llen += printf(" = %d ", expr); - pad_spc(llen, 64, ret ? "[FAIL]\n" : " [OK]\n"); + result(llen, ret ? FAIL : OK); return ret; } #define EXPECT_GT(cond, expr, val) \ - do { if (!cond) pad_spc(llen, 64, "[SKIPPED]\n"); else ret += expect_gt(expr, llen, val); } while (0) + do { if (!(cond)) result(llen, SKIPPED); else ret += expect_gt(expr, llen, val); } while (0) -static int expect_gt(int expr, int llen, int val) +static __attribute__((unused)) +int expect_gt(int expr, int llen, int val) { int ret = !(expr > val); llen += printf(" = %d ", expr); - pad_spc(llen, 64, ret ? "[FAIL]\n" : " [OK]\n"); + result(llen, ret ? FAIL : OK); return ret; } #define EXPECT_LE(cond, expr, val) \ - do { if (!cond) pad_spc(llen, 64, "[SKIPPED]\n"); else ret += expect_le(expr, llen, val); } while (0) + do { if (!(cond)) result(llen, SKIPPED); else ret += expect_le(expr, llen, val); } while (0) -static int expect_le(int expr, int llen, int val) +static __attribute__((unused)) +int expect_le(int expr, int llen, int val) { int ret = !(expr <= val); llen += printf(" = %d ", expr); - pad_spc(llen, 64, ret ? "[FAIL]\n" : " [OK]\n"); + result(llen, ret ? FAIL : OK); return ret; } #define EXPECT_LT(cond, expr, val) \ - do { if (!cond) pad_spc(llen, 64, "[SKIPPED]\n"); else ret += expect_lt(expr, llen, val); } while (0) + do { if (!(cond)) result(llen, SKIPPED); else ret += expect_lt(expr, llen, val); } while (0) -static int expect_lt(int expr, int llen, int val) +static __attribute__((unused)) +int expect_lt(int expr, int llen, int val) { int ret = !(expr < val); llen += printf(" = %d ", expr); - pad_spc(llen, 64, ret ? "[FAIL]\n" : " [OK]\n"); + result(llen, ret ? FAIL : OK); return ret; } #define EXPECT_SYSZR(cond, expr) \ - do { if (!cond) pad_spc(llen, 64, "[SKIPPED]\n"); else ret += expect_syszr(expr, llen); } while (0) + do { if (!(cond)) result(llen, SKIPPED); else ret += expect_syszr(expr, llen); } while (0) -static int expect_syszr(int expr, int llen) +static __attribute__((unused)) +int expect_syszr(int expr, int llen) { int ret = 0; if (expr) { ret = 1; llen += printf(" = %d %s ", expr, errorname(errno)); - llen += pad_spc(llen, 64, "[FAIL]\n"); + result(llen, FAIL); } else { llen += printf(" = %d ", expr); - llen += pad_spc(llen, 64, " [OK]\n"); + result(llen, OK); } return ret; } #define EXPECT_SYSEQ(cond, expr, val) \ - do { if (!cond) pad_spc(llen, 64, "[SKIPPED]\n"); else ret += expect_syseq(expr, llen, val); } while (0) + do { if (!(cond)) result(llen, SKIPPED); else ret += expect_syseq(expr, llen, val); } while (0) -static int expect_syseq(int expr, int llen, int val) +static __attribute__((unused)) +int expect_syseq(int expr, int llen, int val) { int ret = 0; if (expr != val) { ret = 1; llen += printf(" = %d %s ", expr, errorname(errno)); - llen += pad_spc(llen, 64, "[FAIL]\n"); + result(llen, FAIL); } else { llen += printf(" = %d ", expr); - llen += pad_spc(llen, 64, " [OK]\n"); + result(llen, OK); } return ret; } #define EXPECT_SYSNE(cond, expr, val) \ - do { if (!cond) pad_spc(llen, 64, "[SKIPPED]\n"); else ret += expect_sysne(expr, llen, val); } while (0) + do { if (!(cond)) result(llen, SKIPPED); else ret += expect_sysne(expr, llen, val); } while (0) -static int expect_sysne(int expr, int llen, int val) +static __attribute__((unused)) +int expect_sysne(int expr, int llen, int val) { int ret = 0; if (expr == val) { ret = 1; llen += printf(" = %d %s ", expr, errorname(errno)); - llen += pad_spc(llen, 64, "[FAIL]\n"); + result(llen, FAIL); } else { llen += printf(" = %d ", expr); - llen += pad_spc(llen, 64, " [OK]\n"); + result(llen, OK); } return ret; } #define EXPECT_SYSER2(cond, expr, expret, experr1, experr2) \ - do { if (!cond) pad_spc(llen, 64, "[SKIPPED]\n"); else ret += expect_syserr2(expr, expret, experr1, experr2, llen); } while (0) + do { if (!(cond)) result(llen, SKIPPED); else ret += expect_syserr2(expr, expret, experr1, experr2, llen); } while (0) #define EXPECT_SYSER(cond, expr, expret, experr) \ EXPECT_SYSER2(cond, expr, expret, experr, 0) -static int expect_syserr2(int expr, int expret, int experr1, int experr2, int llen) +static __attribute__((unused)) +int expect_syserr2(int expr, int expret, int experr1, int experr2, int llen) { int ret = 0; int _errno = errno; @@ -318,117 +353,238 @@ static int expect_syserr2(int expr, int expret, int experr1, int experr2, int ll llen += printf(" != (%d %s) ", expret, errorname(experr1)); else llen += printf(" != (%d %s %s) ", expret, errorname(experr1), errorname(experr2)); - llen += pad_spc(llen, 64, "[FAIL]\n"); + result(llen, FAIL); } else { - llen += pad_spc(llen, 64, " [OK]\n"); + result(llen, OK); } return ret; } #define EXPECT_PTRZR(cond, expr) \ - do { if (!cond) pad_spc(llen, 64, "[SKIPPED]\n"); else ret += expect_ptrzr(expr, llen); } while (0) + do { if (!(cond)) result(llen, SKIPPED); else ret += expect_ptrzr(expr, llen); } while (0) -static int expect_ptrzr(const void *expr, int llen) +static __attribute__((unused)) +int expect_ptrzr(const void *expr, int llen) { int ret = 0; llen += printf(" = <%p> ", expr); if (expr) { ret = 1; - llen += pad_spc(llen, 64, "[FAIL]\n"); + result(llen, FAIL); } else { - llen += pad_spc(llen, 64, " [OK]\n"); + result(llen, OK); } return ret; } #define EXPECT_PTRNZ(cond, expr) \ - do { if (!cond) pad_spc(llen, 64, "[SKIPPED]\n"); else ret += expect_ptrnz(expr, llen); } while (0) + do { if (!(cond)) result(llen, SKIPPED); else ret += expect_ptrnz(expr, llen); } while (0) -static int expect_ptrnz(const void *expr, int llen) +static __attribute__((unused)) +int expect_ptrnz(const void *expr, int llen) { int ret = 0; llen += printf(" = <%p> ", expr); if (!expr) { ret = 1; - llen += pad_spc(llen, 64, "[FAIL]\n"); + result(llen, FAIL); + } else { + result(llen, OK); + } + return ret; +} + +#define EXPECT_PTREQ(cond, expr, cmp) \ + do { if (!(cond)) result(llen, SKIPPED); else ret += expect_ptreq(expr, llen, cmp); } while (0) + +static __attribute__((unused)) +int expect_ptreq(const void *expr, int llen, const void *cmp) +{ + int ret = 0; + + llen += printf(" = <%p> ", expr); + if (expr != cmp) { + ret = 1; + result(llen, FAIL); + } else { + result(llen, OK); + } + return ret; +} + +#define EXPECT_PTRNE(cond, expr, cmp) \ + do { if (!(cond)) result(llen, SKIPPED); else ret += expect_ptrne(expr, llen, cmp); } while (0) + +static __attribute__((unused)) +int expect_ptrne(const void *expr, int llen, const void *cmp) +{ + int ret = 0; + + llen += printf(" = <%p> ", expr); + if (expr == cmp) { + ret = 1; + result(llen, FAIL); } else { - llen += pad_spc(llen, 64, " [OK]\n"); + result(llen, OK); } return ret; } +#define EXPECT_PTRGE(cond, expr, cmp) \ + do { if (!(cond)) result(llen, SKIPPED); else ret += expect_ptrge(expr, llen, cmp); } while (0) + +static __attribute__((unused)) +int expect_ptrge(const void *expr, int llen, const void *cmp) +{ + int ret = !(expr >= cmp); + + llen += printf(" = <%p> ", expr); + result(llen, ret ? FAIL : OK); + return ret; +} + +#define EXPECT_PTRGT(cond, expr, cmp) \ + do { if (!(cond)) result(llen, SKIPPED); else ret += expect_ptrgt(expr, llen, cmp); } while (0) + +static __attribute__((unused)) +int expect_ptrgt(const void *expr, int llen, const void *cmp) +{ + int ret = !(expr > cmp); + + llen += printf(" = <%p> ", expr); + result(llen, ret ? FAIL : OK); + return ret; +} + + +#define EXPECT_PTRLE(cond, expr, cmp) \ + do { if (!(cond)) result(llen, SKIPPED); else ret += expect_ptrle(expr, llen, cmp); } while (0) + +static __attribute__((unused)) +int expect_ptrle(const void *expr, int llen, const void *cmp) +{ + int ret = !(expr <= cmp); + + llen += printf(" = <%p> ", expr); + result(llen, ret ? FAIL : OK); + return ret; +} + + +#define EXPECT_PTRLT(cond, expr, cmp) \ + do { if (!(cond)) result(llen, SKIPPED); else ret += expect_ptrlt(expr, llen, cmp); } while (0) + +static __attribute__((unused)) +int expect_ptrlt(const void *expr, int llen, const void *cmp) +{ + int ret = !(expr < cmp); + + llen += printf(" = <%p> ", expr); + result(llen, ret ? FAIL : OK); + return ret; +} + +#define EXPECT_PTRER2(cond, expr, expret, experr1, experr2) \ + do { if (!(cond)) result(llen, SKIPPED); else ret += expect_ptrerr2(expr, expret, experr1, experr2, llen); } while (0) + +#define EXPECT_PTRER(cond, expr, expret, experr) \ + EXPECT_PTRER2(cond, expr, expret, experr, 0) + +static __attribute__((unused)) +int expect_ptrerr2(const void *expr, const void *expret, int experr1, int experr2, int llen) +{ + int ret = 0; + int _errno = errno; + + llen += printf(" = <%p> %s ", expr, errorname(_errno)); + if (expr != expret || (_errno != experr1 && _errno != experr2)) { + ret = 1; + if (experr2 == 0) + llen += printf(" != (<%p> %s) ", expret, errorname(experr1)); + else + llen += printf(" != (<%p> %s %s) ", expret, errorname(experr1), errorname(experr2)); + result(llen, FAIL); + } else { + result(llen, OK); + } + return ret; +} #define EXPECT_STRZR(cond, expr) \ - do { if (!cond) pad_spc(llen, 64, "[SKIPPED]\n"); else ret += expect_strzr(expr, llen); } while (0) + do { if (!(cond)) result(llen, SKIPPED); else ret += expect_strzr(expr, llen); } while (0) -static int expect_strzr(const char *expr, int llen) +static __attribute__((unused)) +int expect_strzr(const char *expr, int llen) { int ret = 0; llen += printf(" = <%s> ", expr); if (expr) { ret = 1; - llen += pad_spc(llen, 64, "[FAIL]\n"); + result(llen, FAIL); } else { - llen += pad_spc(llen, 64, " [OK]\n"); + result(llen, OK); } return ret; } #define EXPECT_STRNZ(cond, expr) \ - do { if (!cond) pad_spc(llen, 64, "[SKIPPED]\n"); else ret += expect_strnz(expr, llen); } while (0) + do { if (!(cond)) result(llen, SKIPPED); else ret += expect_strnz(expr, llen); } while (0) -static int expect_strnz(const char *expr, int llen) +static __attribute__((unused)) +int expect_strnz(const char *expr, int llen) { int ret = 0; llen += printf(" = <%s> ", expr); if (!expr) { ret = 1; - llen += pad_spc(llen, 64, "[FAIL]\n"); + result(llen, FAIL); } else { - llen += pad_spc(llen, 64, " [OK]\n"); + result(llen, OK); } return ret; } #define EXPECT_STREQ(cond, expr, cmp) \ - do { if (!cond) pad_spc(llen, 64, "[SKIPPED]\n"); else ret += expect_streq(expr, llen, cmp); } while (0) + do { if (!(cond)) result(llen, SKIPPED); else ret += expect_streq(expr, llen, cmp); } while (0) -static int expect_streq(const char *expr, int llen, const char *cmp) +static __attribute__((unused)) +int expect_streq(const char *expr, int llen, const char *cmp) { int ret = 0; llen += printf(" = <%s> ", expr); if (strcmp(expr, cmp) != 0) { ret = 1; - llen += pad_spc(llen, 64, "[FAIL]\n"); + result(llen, FAIL); } else { - llen += pad_spc(llen, 64, " [OK]\n"); + result(llen, OK); } return ret; } #define EXPECT_STRNE(cond, expr, cmp) \ - do { if (!cond) pad_spc(llen, 64, "[SKIPPED]\n"); else ret += expect_strne(expr, llen, cmp); } while (0) + do { if (!(cond)) result(llen, SKIPPED); else ret += expect_strne(expr, llen, cmp); } while (0) -static int expect_strne(const char *expr, int llen, const char *cmp) +static __attribute__((unused)) +int expect_strne(const char *expr, int llen, const char *cmp) { int ret = 0; llen += printf(" = <%s> ", expr); if (strcmp(expr, cmp) == 0) { ret = 1; - llen += pad_spc(llen, 64, "[FAIL]\n"); + result(llen, FAIL); } else { - llen += pad_spc(llen, 64, " [OK]\n"); + result(llen, OK); } return ret; } @@ -438,6 +594,51 @@ static int expect_strne(const char *expr, int llen, const char *cmp) #define CASE_TEST(name) \ case __LINE__: llen += printf("%d %s", test, #name); +int run_startup(int min, int max) +{ + int test; + int ret = 0; + /* kernel at least passes HOME and TERM, shell passes more */ + int env_total = 2; + /* checking NULL for argv/argv0, environ and _auxv is not enough, let's compare with sbrk(0) or &end */ + extern char end; + char *brk = sbrk(0) != (void *)-1 ? sbrk(0) : &end; + /* differ from nolibc, both glibc and musl have no global _auxv */ + const unsigned long *test_auxv = (void *)-1; +#ifdef NOLIBC + test_auxv = _auxv; +#endif + + for (test = min; test >= 0 && test <= max; test++) { + int llen = 0; /* line length */ + + /* avoid leaving empty lines below, this will insert holes into + * test numbers. + */ + switch (test + __LINE__ + 1) { + CASE_TEST(argc); EXPECT_GE(1, test_argc, 1); break; + CASE_TEST(argv_addr); EXPECT_PTRGT(1, test_argv, brk); break; + CASE_TEST(argv_environ); EXPECT_PTRLT(1, test_argv, environ); break; + CASE_TEST(argv_total); EXPECT_EQ(1, environ - test_argv - 1, test_argc ?: 1); break; + CASE_TEST(argv0_addr); EXPECT_PTRGT(1, argv0, brk); break; + CASE_TEST(argv0_str); EXPECT_STRNZ(1, argv0 > brk ? argv0 : NULL); break; + CASE_TEST(argv0_len); EXPECT_GE(1, argv0 > brk ? strlen(argv0) : 0, 1); break; + CASE_TEST(environ_addr); EXPECT_PTRGT(1, environ, brk); break; + CASE_TEST(environ_envp); EXPECT_PTREQ(1, environ, test_envp); break; + CASE_TEST(environ_auxv); EXPECT_PTRLT(test_auxv != (void *)-1, environ, test_auxv); break; + CASE_TEST(environ_total); EXPECT_GE(test_auxv != (void *)-1, (void *)test_auxv - (void *)environ - 1, env_total); break; + CASE_TEST(environ_HOME); EXPECT_PTRNZ(1, getenv("HOME")); break; + CASE_TEST(auxv_addr); EXPECT_PTRGT(test_auxv != (void *)-1, test_auxv, brk); break; + CASE_TEST(auxv_AT_UID); EXPECT_EQ(1, getauxval(AT_UID), getuid()); break; + CASE_TEST(auxv_AT_PAGESZ); EXPECT_GE(1, getauxval(AT_PAGESZ), 4096); break; + case __LINE__: + return ret; /* must be last */ + /* note: do not set any defaults so as to permit holes above */ + } + } + return ret; +} + /* used by some syscall tests below */ int test_getdents64(const char *dir) @@ -458,9 +659,9 @@ int test_getdents64(const char *dir) return ret; } -static int test_getpagesize(void) +int test_getpagesize(void) { - long x = getpagesize(); + int x = getpagesize(); int c; if (x < 0) @@ -487,7 +688,7 @@ static int test_getpagesize(void) return !c; } -static int test_fork(void) +int test_fork(void) { int status; pid_t pid; @@ -512,14 +713,14 @@ static int test_fork(void) } } -static int test_stat_timestamps(void) +int test_stat_timestamps(void) { struct stat st; if (sizeof(st.st_atim.tv_sec) != sizeof(st.st_atime)) return 1; - if (stat("/proc/self/", &st)) + if (stat("/proc/self/", &st) && stat(argv0, &st) && stat("/", &st)) return 1; if (st.st_atim.tv_sec != st.st_atime || st.st_atim.tv_nsec > 1000000000) @@ -534,6 +735,86 @@ static int test_stat_timestamps(void) return 0; } +int test_mmap_munmap(void) +{ + int ret, fd, i, page_size; + void *mem; + size_t file_size, length; + off_t offset, pa_offset; + struct stat stat_buf; + const char * const files[] = { + "/dev/zero", + "/proc/1/exe", "/proc/self/exe", + argv0, + NULL + }; + + page_size = getpagesize(); + if (page_size < 0) + return 1; + + /* find a right file to mmap, existed and accessible */ + for (i = 0; files[i] != NULL; i++) { + ret = fd = open(files[i], O_RDONLY); + if (ret == -1) + continue; + else + break; + } + if (ret == -1) + return 1; + + ret = stat(files[i], &stat_buf); + if (ret == -1) + goto end; + + /* file size of the special /dev/zero is 0, let's assign one manually */ + if (i == 0) + file_size = 3*page_size; + else + file_size = stat_buf.st_size; + + offset = file_size - 1; + if (offset < 0) + offset = 0; + length = file_size - offset; + pa_offset = offset & ~(page_size - 1); + + mem = mmap(NULL, length + offset - pa_offset, PROT_READ, MAP_SHARED, fd, pa_offset); + if (mem == MAP_FAILED) { + ret = 1; + goto end; + } + + ret = munmap(mem, length + offset - pa_offset); + +end: + close(fd); + return !!ret; +} + +int test_pipe(void) +{ + const char *const msg = "hello, nolibc"; + int pipefd[2]; + char buf[32]; + size_t len; + + if (pipe(pipefd) == -1) + return 1; + + write(pipefd[1], msg, strlen(msg)); + close(pipefd[1]); + len = read(pipefd[0], buf, sizeof(buf)); + close(pipefd[0]); + + if (len != strlen(msg)) + return 1; + + return !!memcmp(buf, msg, len); +} + + /* Run syscall tests between IDs <min> and <max>. * Return 0 on success, non-zero on failure. */ @@ -548,6 +829,7 @@ int run_syscall(int min, int max) int tmp; int ret = 0; void *p1, *p2; + int has_gettid = 1; /* <proc> indicates whether or not /proc is mounted */ proc = stat("/proc", &stat_buf) == 0; @@ -555,6 +837,11 @@ int run_syscall(int min, int max) /* this will be used to skip certain tests that can't be run unprivileged */ euid0 = geteuid() == 0; + /* from 2.30, glibc provides gettid() */ +#if defined(__GLIBC_MINOR__) && defined(__GLIBC__) + has_gettid = __GLIBC__ > 2 || (__GLIBC__ == 2 && __GLIBC_MINOR__ >= 30); +#endif + for (test = min; test >= 0 && test <= max; test++) { int llen = 0; /* line length */ @@ -564,25 +851,24 @@ int run_syscall(int min, int max) switch (test + __LINE__ + 1) { CASE_TEST(getpid); EXPECT_SYSNE(1, getpid(), -1); break; CASE_TEST(getppid); EXPECT_SYSNE(1, getppid(), -1); break; -#ifdef NOLIBC - CASE_TEST(gettid); EXPECT_SYSNE(1, gettid(), -1); break; -#endif + CASE_TEST(gettid); EXPECT_SYSNE(has_gettid, gettid(), -1); break; CASE_TEST(getpgid_self); EXPECT_SYSNE(1, getpgid(0), -1); break; CASE_TEST(getpgid_bad); EXPECT_SYSER(1, getpgid(-1), -1, ESRCH); break; CASE_TEST(kill_0); EXPECT_SYSZR(1, kill(getpid(), 0)); break; CASE_TEST(kill_CONT); EXPECT_SYSZR(1, kill(getpid(), 0)); break; CASE_TEST(kill_BADPID); EXPECT_SYSER(1, kill(INT_MAX, 0), -1, ESRCH); break; + CASE_TEST(sbrk_0); EXPECT_PTRNE(1, sbrk(0), (void *)-1); break; CASE_TEST(sbrk); if ((p1 = p2 = sbrk(4096)) != (void *)-1) p2 = sbrk(-4096); EXPECT_SYSZR(1, (p2 == (void *)-1) || p2 == p1); break; CASE_TEST(brk); EXPECT_SYSZR(1, brk(sbrk(0))); break; - CASE_TEST(chdir_root); EXPECT_SYSZR(1, chdir("/")); break; + CASE_TEST(chdir_root); EXPECT_SYSZR(1, chdir("/")); chdir(getenv("PWD")); break; CASE_TEST(chdir_dot); EXPECT_SYSZR(1, chdir(".")); break; CASE_TEST(chdir_blah); EXPECT_SYSER(1, chdir("/blah"), -1, ENOENT); break; - CASE_TEST(chmod_net); EXPECT_SYSZR(proc, chmod("/proc/self/net", 0555)); break; + CASE_TEST(chmod_argv0); EXPECT_SYSZR(1, chmod(argv0, 0555)); break; CASE_TEST(chmod_self); EXPECT_SYSER(proc, chmod("/proc/self", 0555), -1, EPERM); break; CASE_TEST(chown_self); EXPECT_SYSER(proc, chown("/proc/self", 0, 0), -1, EPERM); break; CASE_TEST(chroot_root); EXPECT_SYSZR(euid0, chroot("/")); break; CASE_TEST(chroot_blah); EXPECT_SYSER(1, chroot("/proc/self/blah"), -1, ENOENT); break; - CASE_TEST(chroot_exe); EXPECT_SYSER(proc, chroot("/proc/self/exe"), -1, ENOTDIR); break; + CASE_TEST(chroot_exe); EXPECT_SYSER(1, chroot(argv0), -1, ENOTDIR); break; CASE_TEST(close_m1); EXPECT_SYSER(1, close(-1), -1, EBADF); break; CASE_TEST(close_dup); EXPECT_SYSZR(1, close(dup(0))); break; CASE_TEST(dup_0); tmp = dup(0); EXPECT_SYSNE(1, tmp, -1); close(tmp); break; @@ -603,23 +889,28 @@ int run_syscall(int min, int max) CASE_TEST(link_root1); EXPECT_SYSER(1, link("/", "/"), -1, EEXIST); break; CASE_TEST(link_blah); EXPECT_SYSER(1, link("/proc/self/blah", "/blah"), -1, ENOENT); break; CASE_TEST(link_dir); EXPECT_SYSER(euid0, link("/", "/blah"), -1, EPERM); break; - CASE_TEST(link_cross); EXPECT_SYSER(proc, link("/proc/self/net", "/blah"), -1, EXDEV); break; + CASE_TEST(link_cross); EXPECT_SYSER(proc, link("/proc/self/cmdline", "/blah"), -1, EXDEV); break; CASE_TEST(lseek_m1); EXPECT_SYSER(1, lseek(-1, 0, SEEK_SET), -1, EBADF); break; CASE_TEST(lseek_0); EXPECT_SYSER(1, lseek(0, 0, SEEK_SET), -1, ESPIPE); break; CASE_TEST(mkdir_root); EXPECT_SYSER(1, mkdir("/", 0755), -1, EEXIST); break; + CASE_TEST(mmap_bad); EXPECT_PTRER(1, mmap(NULL, 0, PROT_READ, MAP_PRIVATE, 0, 0), MAP_FAILED, EINVAL); break; + CASE_TEST(munmap_bad); EXPECT_SYSER(1, munmap((void *)1, 0), -1, EINVAL); break; + CASE_TEST(mmap_munmap_good); EXPECT_SYSZR(1, test_mmap_munmap()); break; CASE_TEST(open_tty); EXPECT_SYSNE(1, tmp = open("/dev/null", 0), -1); if (tmp != -1) close(tmp); break; CASE_TEST(open_blah); EXPECT_SYSER(1, tmp = open("/proc/self/blah", 0), -1, ENOENT); if (tmp != -1) close(tmp); break; + CASE_TEST(pipe); EXPECT_SYSZR(1, test_pipe()); break; CASE_TEST(poll_null); EXPECT_SYSZR(1, poll(NULL, 0, 0)); break; CASE_TEST(poll_stdout); EXPECT_SYSNE(1, ({ struct pollfd fds = { 1, POLLOUT, 0}; poll(&fds, 1, 0); }), -1); break; CASE_TEST(poll_fault); EXPECT_SYSER(1, poll((void *)1, 1, 0), -1, EFAULT); break; CASE_TEST(prctl); EXPECT_SYSER(1, prctl(PR_SET_NAME, (unsigned long)NULL, 0, 0, 0), -1, EFAULT); break; CASE_TEST(read_badf); EXPECT_SYSER(1, read(-1, &tmp, 1), -1, EBADF); break; + CASE_TEST(rmdir_blah); EXPECT_SYSER(1, rmdir("/blah"), -1, ENOENT); break; CASE_TEST(sched_yield); EXPECT_SYSZR(1, sched_yield()); break; CASE_TEST(select_null); EXPECT_SYSZR(1, ({ struct timeval tv = { 0 }; select(0, NULL, NULL, NULL, &tv); })); break; CASE_TEST(select_stdout); EXPECT_SYSNE(1, ({ fd_set fds; FD_ZERO(&fds); FD_SET(1, &fds); select(2, NULL, &fds, NULL, NULL); }), -1); break; CASE_TEST(select_fault); EXPECT_SYSER(1, select(1, (void *)1, NULL, NULL, 0), -1, EFAULT); break; CASE_TEST(stat_blah); EXPECT_SYSER(1, stat("/proc/self/blah", &stat_buf), -1, ENOENT); break; - CASE_TEST(stat_fault); EXPECT_SYSER(1, stat(NULL, &stat_buf), -1, EFAULT); break; + CASE_TEST(stat_fault); EXPECT_SYSER(1, stat((void *)1, &stat_buf), -1, EFAULT); break; CASE_TEST(stat_timestamps); EXPECT_SYSZR(1, test_stat_timestamps()); break; CASE_TEST(symlink_root); EXPECT_SYSER(1, symlink("/", "/"), -1, EEXIST); break; CASE_TEST(unlink_root); EXPECT_SYSER(1, unlink("/"), -1, EISDIR); break; @@ -642,9 +933,7 @@ int run_syscall(int min, int max) int run_stdlib(int min, int max) { int test; - int tmp; int ret = 0; - void *p1, *p2; for (test = min; test >= 0 && test <= max; test++) { int llen = 0; /* line length */ @@ -699,32 +988,23 @@ int run_stdlib(int min, int max) CASE_TEST(limit_int_fast8_max); EXPECT_EQ(1, INT_FAST8_MAX, (int_fast8_t) 0x7f); break; CASE_TEST(limit_int_fast8_min); EXPECT_EQ(1, INT_FAST8_MIN, (int_fast8_t) 0x80); break; CASE_TEST(limit_uint_fast8_max); EXPECT_EQ(1, UINT_FAST8_MAX, (uint_fast8_t) 0xff); break; - CASE_TEST(limit_int_fast16_min); EXPECT_EQ(1, INT_FAST16_MIN, (int_fast16_t) INTPTR_MIN); break; - CASE_TEST(limit_int_fast16_max); EXPECT_EQ(1, INT_FAST16_MAX, (int_fast16_t) INTPTR_MAX); break; + CASE_TEST(limit_int_fast16_min); EXPECT_EQ(1, INT_FAST16_MIN, (int_fast16_t) SINT_MIN_OF_TYPE(int_fast16_t)); break; + CASE_TEST(limit_int_fast16_max); EXPECT_EQ(1, INT_FAST16_MAX, (int_fast16_t) SINT_MAX_OF_TYPE(int_fast16_t)); break; CASE_TEST(limit_uint_fast16_max); EXPECT_EQ(1, UINT_FAST16_MAX, (uint_fast16_t) UINTPTR_MAX); break; - CASE_TEST(limit_int_fast32_min); EXPECT_EQ(1, INT_FAST32_MIN, (int_fast32_t) INTPTR_MIN); break; - CASE_TEST(limit_int_fast32_max); EXPECT_EQ(1, INT_FAST32_MAX, (int_fast32_t) INTPTR_MAX); break; + CASE_TEST(limit_int_fast32_min); EXPECT_EQ(1, INT_FAST32_MIN, (int_fast32_t) SINT_MIN_OF_TYPE(int_fast32_t)); break; + CASE_TEST(limit_int_fast32_max); EXPECT_EQ(1, INT_FAST32_MAX, (int_fast32_t) SINT_MAX_OF_TYPE(int_fast32_t)); break; CASE_TEST(limit_uint_fast32_max); EXPECT_EQ(1, UINT_FAST32_MAX, (uint_fast32_t) UINTPTR_MAX); break; CASE_TEST(limit_int_fast64_min); EXPECT_EQ(1, INT_FAST64_MIN, (int_fast64_t) INT64_MIN); break; CASE_TEST(limit_int_fast64_max); EXPECT_EQ(1, INT_FAST64_MAX, (int_fast64_t) INT64_MAX); break; CASE_TEST(limit_uint_fast64_max); EXPECT_EQ(1, UINT_FAST64_MAX, (uint_fast64_t) UINT64_MAX); break; -#if __SIZEOF_LONG__ == 8 - CASE_TEST(limit_intptr_min); EXPECT_EQ(1, INTPTR_MIN, (intptr_t) 0x8000000000000000LL); break; - CASE_TEST(limit_intptr_max); EXPECT_EQ(1, INTPTR_MAX, (intptr_t) 0x7fffffffffffffffLL); break; - CASE_TEST(limit_uintptr_max); EXPECT_EQ(1, UINTPTR_MAX, (uintptr_t) 0xffffffffffffffffULL); break; - CASE_TEST(limit_ptrdiff_min); EXPECT_EQ(1, PTRDIFF_MIN, (ptrdiff_t) 0x8000000000000000LL); break; - CASE_TEST(limit_ptrdiff_max); EXPECT_EQ(1, PTRDIFF_MAX, (ptrdiff_t) 0x7fffffffffffffffLL); break; - CASE_TEST(limit_size_max); EXPECT_EQ(1, SIZE_MAX, (size_t) 0xffffffffffffffffULL); break; -#elif __SIZEOF_LONG__ == 4 - CASE_TEST(limit_intptr_min); EXPECT_EQ(1, INTPTR_MIN, (intptr_t) 0x80000000); break; - CASE_TEST(limit_intptr_max); EXPECT_EQ(1, INTPTR_MAX, (intptr_t) 0x7fffffff); break; - CASE_TEST(limit_uintptr_max); EXPECT_EQ(1, UINTPTR_MAX, (uintptr_t) 0xffffffffU); break; - CASE_TEST(limit_ptrdiff_min); EXPECT_EQ(1, PTRDIFF_MIN, (ptrdiff_t) 0x80000000); break; - CASE_TEST(limit_ptrdiff_max); EXPECT_EQ(1, PTRDIFF_MAX, (ptrdiff_t) 0x7fffffff); break; - CASE_TEST(limit_size_max); EXPECT_EQ(1, SIZE_MAX, (size_t) 0xffffffffU); break; -#else -# warning "__SIZEOF_LONG__ is undefined" -#endif /* __SIZEOF_LONG__ */ + CASE_TEST(sizeof_long_sane); EXPECT_EQ(1, sizeof(long) == 8 || sizeof(long) == 4, 1); break; + CASE_TEST(limit_intptr_min); EXPECT_EQ(1, INTPTR_MIN, sizeof(long) == 8 ? (intptr_t) 0x8000000000000000LL : (intptr_t) 0x80000000); break; + CASE_TEST(limit_intptr_max); EXPECT_EQ(1, INTPTR_MAX, sizeof(long) == 8 ? (intptr_t) 0x7fffffffffffffffLL : (intptr_t) 0x7fffffff); break; + CASE_TEST(limit_uintptr_max); EXPECT_EQ(1, UINTPTR_MAX, sizeof(long) == 8 ? (uintptr_t) 0xffffffffffffffffULL : (uintptr_t) 0xffffffffU); break; + CASE_TEST(limit_ptrdiff_min); EXPECT_EQ(1, PTRDIFF_MIN, sizeof(long) == 8 ? (ptrdiff_t) 0x8000000000000000LL : (ptrdiff_t) 0x80000000); break; + CASE_TEST(limit_ptrdiff_max); EXPECT_EQ(1, PTRDIFF_MAX, sizeof(long) == 8 ? (ptrdiff_t) 0x7fffffffffffffffLL : (ptrdiff_t) 0x7fffffff); break; + CASE_TEST(limit_size_max); EXPECT_EQ(1, SIZE_MAX, sizeof(long) == 8 ? (size_t) 0xffffffffffffffffULL : (size_t) 0xffffffffU); break; + case __LINE__: return ret; /* must be last */ /* note: do not set any defaults so as to permit holes above */ @@ -736,22 +1016,23 @@ int run_stdlib(int min, int max) #define EXPECT_VFPRINTF(c, expected, fmt, ...) \ ret += expect_vfprintf(llen, c, expected, fmt, ##__VA_ARGS__) -static int expect_vfprintf(int llen, size_t c, const char *expected, const char *fmt, ...) +static int expect_vfprintf(int llen, int c, const char *expected, const char *fmt, ...) { - int ret, fd, w, r; + int ret, fd; + ssize_t w, r; char buf[100]; FILE *memfile; va_list args; - fd = memfd_create("vfprintf", 0); + fd = open("/tmp", O_TMPFILE | O_EXCL | O_RDWR, 0600); if (fd == -1) { - pad_spc(llen, 64, "[FAIL]\n"); - return 1; + result(llen, SKIPPED); + return 0; } memfile = fdopen(fd, "w+"); if (!memfile) { - pad_spc(llen, 64, "[FAIL]\n"); + result(llen, FAIL); return 1; } @@ -760,8 +1041,8 @@ static int expect_vfprintf(int llen, size_t c, const char *expected, const char va_end(args); if (w != c) { - llen += printf(" written(%d) != %d", w, (int) c); - pad_spc(llen, 64, "[FAIL]\n"); + llen += printf(" written(%d) != %d", (int)w, c); + result(llen, FAIL); return 1; } @@ -769,29 +1050,27 @@ static int expect_vfprintf(int llen, size_t c, const char *expected, const char lseek(fd, 0, SEEK_SET); r = read(fd, buf, sizeof(buf) - 1); - buf[r] = '\0'; fclose(memfile); if (r != w) { - llen += printf(" written(%d) != read(%d)", w, r); - pad_spc(llen, 64, "[FAIL]\n"); + llen += printf(" written(%d) != read(%d)", (int)w, (int)r); + result(llen, FAIL); return 1; } + buf[r] = '\0'; llen += printf(" \"%s\" = \"%s\"", expected, buf); ret = strncmp(expected, buf, c); - pad_spc(llen, 64, ret ? "[FAIL]\n" : " [OK]\n"); + result(llen, ret ? FAIL : OK); return ret; } static int run_vfprintf(int min, int max) { int test; - int tmp; int ret = 0; - void *p1, *p2; for (test = min; test >= 0 && test <= max; test++) { int llen = 0; /* line length */ @@ -829,7 +1108,8 @@ static int smash_stack(void) return 1; } -static int run_protection(int min, int max) +static int run_protection(int min __attribute__((unused)), + int max __attribute__((unused))) { pid_t pid; int llen = 0, status; @@ -838,14 +1118,14 @@ static int run_protection(int min, int max) #if !defined(_NOLIBC_STACKPROTECTOR) llen += printf("not supported"); - pad_spc(llen, 64, "[SKIPPED]\n"); + result(llen, SKIPPED); return 0; #endif #if defined(_NOLIBC_STACKPROTECTOR) if (!__stack_chk_guard) { llen += printf("__stack_chk_guard not initialized"); - pad_spc(llen, 64, "[FAIL]\n"); + result(llen, FAIL); return 1; } #endif @@ -856,7 +1136,7 @@ static int run_protection(int min, int max) switch (pid) { case -1: llen += printf("fork()"); - pad_spc(llen, 64, "[FAIL]\n"); + result(llen, FAIL); return 1; case 0: @@ -872,10 +1152,10 @@ static int run_protection(int min, int max) if (pid == -1 || !WIFSIGNALED(status) || WTERMSIG(status) != SIGABRT) { llen += printf("waitpid()"); - pad_spc(llen, 64, "[FAIL]\n"); + result(llen, FAIL); return 1; } - pad_spc(llen, 64, " [OK]\n"); + result(llen, OK); return 0; } } @@ -891,11 +1171,13 @@ int prepare(void) */ if (stat("/dev/.", &stat_buf) == 0 || mkdir("/dev", 0755) == 0) { if (stat("/dev/console", &stat_buf) != 0 || - stat("/dev/null", &stat_buf) != 0) { + stat("/dev/null", &stat_buf) != 0 || + stat("/dev/zero", &stat_buf) != 0) { /* try devtmpfs first, otherwise fall back to manual creation */ if (mount("/dev", "/dev", "devtmpfs", 0, 0) != 0) { mknod("/dev/console", 0600 | S_IFCHR, makedev(5, 1)); mknod("/dev/null", 0666 | S_IFCHR, makedev(1, 3)); + mknod("/dev/zero", 0666 | S_IFCHR, makedev(1, 5)); } } } @@ -922,16 +1204,23 @@ int prepare(void) /* try to mount /proc if not mounted. Silently fail otherwise */ if (stat("/proc/.", &stat_buf) == 0 || mkdir("/proc", 0755) == 0) { - if (stat("/proc/self", &stat_buf) != 0) - mount("/proc", "/proc", "proc", 0, 0); + if (stat("/proc/self", &stat_buf) != 0) { + /* If not mountable, remove /proc completely to avoid misuse */ + if (mount("none", "/proc", "proc", 0, 0) != 0) + rmdir("/proc"); + } } + /* some tests rely on a writable /tmp */ + mkdir("/tmp", 0755); + return 0; } /* This is the definition of known test names, with their functions */ static const struct test test_names[] = { /* add new tests here */ + { .name = "startup", .func = run_startup }, { .name = "syscall", .func = run_syscall }, { .name = "stdlib", .func = run_stdlib }, { .name = "vfprintf", .func = run_vfprintf }, @@ -939,6 +1228,35 @@ static const struct test test_names[] = { { 0 } }; +static int is_setting_valid(char *test) +{ + int idx, len, test_len, valid = 0; + char delimiter; + + if (!test) + return valid; + + test_len = strlen(test); + + for (idx = 0; test_names[idx].name; idx++) { + len = strlen(test_names[idx].name); + if (test_len < len) + continue; + + if (strncmp(test, test_names[idx].name, len) != 0) + continue; + + delimiter = test[len]; + if (delimiter != ':' && delimiter != ',' && delimiter != '\0') + continue; + + valid = 1; + break; + } + + return valid; +} + int main(int argc, char **argv, char **envp) { int min = 0; @@ -948,7 +1266,10 @@ int main(int argc, char **argv, char **envp) int idx; char *test; - environ = envp; + argv0 = argv[0]; + test_argc = argc; + test_argv = argv; + test_envp = envp; /* when called as init, it's possible that no console was opened, for * example if no /dev file system was provided. We'll check that fd#1 @@ -964,10 +1285,10 @@ int main(int argc, char **argv, char **envp) * syscall:5-15[:.*],stdlib:8-10 */ test = argv[1]; - if (!test) + if (!is_setting_valid(test)) test = getenv("NOLIBC_TEST"); - if (test) { + if (is_setting_valid(test)) { char *comma, *colon, *dash, *value; do { @@ -1045,17 +1366,13 @@ int main(int argc, char **argv, char **envp) */ printf("Leaving init with final status: %d\n", !!ret); if (ret == 0) - reboot(LINUX_REBOOT_CMD_POWER_OFF); + reboot(RB_POWER_OFF); #if defined(__x86_64__) /* QEMU started with "-device isa-debug-exit -no-reboot" will * exit with status code 2N+1 when N is written to 0x501. We * hard-code the syscall here as it's arch-dependent. */ -#if defined(_NOLIBC_SYS_H) - else if (my_syscall3(__NR_ioperm, 0x501, 1, 1) == 0) -#else - else if (ioperm(0x501, 1, 1) == 0) -#endif + else if (syscall(__NR_ioperm, 0x501, 1, 1) == 0) __asm__ volatile ("outb %%al, %%dx" :: "d"(0x501), "a"(0)); /* if it does nothing, fall back to the regular panic */ #endif diff --git a/tools/testing/selftests/powerpc/copyloops/asm/export.h b/tools/testing/selftests/powerpc/copyloops/linux/export.h index e6b80d5fbd14..e6b80d5fbd14 100644 --- a/tools/testing/selftests/powerpc/copyloops/asm/export.h +++ b/tools/testing/selftests/powerpc/copyloops/linux/export.h diff --git a/tools/testing/selftests/powerpc/harness.c b/tools/testing/selftests/powerpc/harness.c index 0ad4f12b3d43..5876220d8ff2 100644 --- a/tools/testing/selftests/powerpc/harness.c +++ b/tools/testing/selftests/powerpc/harness.c @@ -24,7 +24,7 @@ /* Setting timeout to -1 disables the alarm */ static uint64_t timeout = 120; -int run_test(int (test_function)(void), char *name) +int run_test(int (test_function)(void), const char *name) { bool terminated; int rc, status; @@ -101,7 +101,7 @@ void test_harness_set_timeout(uint64_t time) timeout = time; } -int test_harness(int (test_function)(void), char *name) +int test_harness(int (test_function)(void), const char *name) { int rc; diff --git a/tools/testing/selftests/powerpc/include/subunit.h b/tools/testing/selftests/powerpc/include/subunit.h index 068d55fdf80f..b0bb774617c9 100644 --- a/tools/testing/selftests/powerpc/include/subunit.h +++ b/tools/testing/selftests/powerpc/include/subunit.h @@ -6,37 +6,37 @@ #ifndef _SELFTESTS_POWERPC_SUBUNIT_H #define _SELFTESTS_POWERPC_SUBUNIT_H -static inline void test_start(char *name) +static inline void test_start(const char *name) { printf("test: %s\n", name); } -static inline void test_failure_detail(char *name, char *detail) +static inline void test_failure_detail(const char *name, const char *detail) { printf("failure: %s [%s]\n", name, detail); } -static inline void test_failure(char *name) +static inline void test_failure(const char *name) { printf("failure: %s\n", name); } -static inline void test_error(char *name) +static inline void test_error(const char *name) { printf("error: %s\n", name); } -static inline void test_skip(char *name) +static inline void test_skip(const char *name) { printf("skip: %s\n", name); } -static inline void test_success(char *name) +static inline void test_success(const char *name) { printf("success: %s\n", name); } -static inline void test_finish(char *name, int status) +static inline void test_finish(const char *name, int status) { if (status) test_failure(name); @@ -44,7 +44,7 @@ static inline void test_finish(char *name, int status) test_success(name); } -static inline void test_set_git_version(char *value) +static inline void test_set_git_version(const char *value) { printf("tags: git_version:%s\n", value); } diff --git a/tools/testing/selftests/powerpc/include/utils.h b/tools/testing/selftests/powerpc/include/utils.h index 36c30c611457..66d7b2368dd4 100644 --- a/tools/testing/selftests/powerpc/include/utils.h +++ b/tools/testing/selftests/powerpc/include/utils.h @@ -32,7 +32,7 @@ typedef uint16_t u16; typedef uint8_t u8; void test_harness_set_timeout(uint64_t time); -int test_harness(int (test_function)(void), char *name); +int test_harness(int (test_function)(void), const char *name); int read_auxv(char *buf, ssize_t buf_size); void *find_auxv_entry(int type, char *auxv); diff --git a/tools/testing/selftests/powerpc/mm/.gitignore b/tools/testing/selftests/powerpc/mm/.gitignore index 4e1a294eec35..0df1a3afc5e2 100644 --- a/tools/testing/selftests/powerpc/mm/.gitignore +++ b/tools/testing/selftests/powerpc/mm/.gitignore @@ -1,15 +1,16 @@ # SPDX-License-Identifier: GPL-2.0-only +bad_accesses +exec_prot hugetlb_vs_thp_test -subpage_prot -tempfile -prot_sao -segv_errors -wild_bctr large_vm_fork_separation -bad_accesses -tlbie_test +large_vm_gpr_corruption pkey_exec_prot pkey_siginfo +prot_sao +segv_errors stack_expansion_ldst stack_expansion_signal -large_vm_gpr_corruption +subpage_prot +tempfile +tlbie_test +wild_bctr diff --git a/tools/testing/selftests/powerpc/ptrace/Makefile b/tools/testing/selftests/powerpc/ptrace/Makefile index cbeeaeae8837..1b39b86849da 100644 --- a/tools/testing/selftests/powerpc/ptrace/Makefile +++ b/tools/testing/selftests/powerpc/ptrace/Makefile @@ -36,6 +36,7 @@ $(TM_TESTS): CFLAGS += -I../tm -mhtm CFLAGS += $(KHDR_INCLUDES) -fno-pie $(OUTPUT)/ptrace-gpr: ptrace-gpr.S +$(OUTPUT)/ptrace-perf-hwbreak: ptrace-perf-asm.S $(OUTPUT)/ptrace-pkey $(OUTPUT)/core-pkey: LDLIBS += -pthread $(TEST_GEN_PROGS): ../harness.c ../utils.c ../lib/reg.S diff --git a/tools/testing/selftests/powerpc/ptrace/child.h b/tools/testing/selftests/powerpc/ptrace/child.h index d7275b7b33dc..df62ff0735f7 100644 --- a/tools/testing/selftests/powerpc/ptrace/child.h +++ b/tools/testing/selftests/powerpc/ptrace/child.h @@ -48,12 +48,12 @@ struct child_sync { } \ } while (0) -#define PARENT_SKIP_IF_UNSUPPORTED(x, sync) \ +#define PARENT_SKIP_IF_UNSUPPORTED(x, sync, msg) \ do { \ if ((x) == -1 && (errno == ENODEV || errno == EINVAL)) { \ (sync)->parent_gave_up = true; \ prod_child(sync); \ - SKIP_IF(1); \ + SKIP_IF_MSG(1, msg); \ } \ } while (0) diff --git a/tools/testing/selftests/powerpc/ptrace/core-pkey.c b/tools/testing/selftests/powerpc/ptrace/core-pkey.c index f6f8596ce8e1..f6da4cb30cd6 100644 --- a/tools/testing/selftests/powerpc/ptrace/core-pkey.c +++ b/tools/testing/selftests/powerpc/ptrace/core-pkey.c @@ -266,7 +266,7 @@ static int parent(struct shared_info *info, pid_t pid) * to the child. */ ret = ptrace_read_regs(pid, NT_PPC_PKEY, regs, 3); - PARENT_SKIP_IF_UNSUPPORTED(ret, &info->child_sync); + PARENT_SKIP_IF_UNSUPPORTED(ret, &info->child_sync, "PKEYs not supported"); PARENT_FAIL_IF(ret, &info->child_sync); info->amr = regs[0]; diff --git a/tools/testing/selftests/powerpc/ptrace/perf-hwbreak.c b/tools/testing/selftests/powerpc/ptrace/perf-hwbreak.c index f75739bbad28..e374c6b7ace6 100644 --- a/tools/testing/selftests/powerpc/ptrace/perf-hwbreak.c +++ b/tools/testing/selftests/powerpc/ptrace/perf-hwbreak.c @@ -884,7 +884,7 @@ static int perf_hwbreak(void) { srand ( time(NULL) ); - SKIP_IF(!perf_breakpoint_supported()); + SKIP_IF_MSG(!perf_breakpoint_supported(), "Perf breakpoints not supported"); return runtest(); } diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-hwbreak.c b/tools/testing/selftests/powerpc/ptrace/ptrace-hwbreak.c index 1345e9b9af0f..75d30d61ab0e 100644 --- a/tools/testing/selftests/powerpc/ptrace/ptrace-hwbreak.c +++ b/tools/testing/selftests/powerpc/ptrace/ptrace-hwbreak.c @@ -64,26 +64,26 @@ static bool dawr_present(struct ppc_debug_info *dbginfo) static void write_var(int len) { - __u8 *pcvar; - __u16 *psvar; - __u32 *pivar; - __u64 *plvar; + volatile __u8 *pcvar; + volatile __u16 *psvar; + volatile __u32 *pivar; + volatile __u64 *plvar; switch (len) { case 1: - pcvar = (__u8 *)&glvar; + pcvar = (volatile __u8 *)&glvar; *pcvar = 0xff; break; case 2: - psvar = (__u16 *)&glvar; + psvar = (volatile __u16 *)&glvar; *psvar = 0xffff; break; case 4: - pivar = (__u32 *)&glvar; + pivar = (volatile __u32 *)&glvar; *pivar = 0xffffffff; break; case 8: - plvar = (__u64 *)&glvar; + plvar = (volatile __u64 *)&glvar; *plvar = 0xffffffffffffffffLL; break; } @@ -98,16 +98,16 @@ static void read_var(int len) switch (len) { case 1: - cvar = (__u8)glvar; + cvar = (volatile __u8)glvar; break; case 2: - svar = (__u16)glvar; + svar = (volatile __u16)glvar; break; case 4: - ivar = (__u32)glvar; + ivar = (volatile __u32)glvar; break; case 8: - lvar = (__u64)glvar; + lvar = (volatile __u64)glvar; break; } } @@ -603,7 +603,7 @@ static int ptrace_hwbreak(void) wait(NULL); get_dbginfo(child_pid, &dbginfo); - SKIP_IF(dbginfo.num_data_bps == 0); + SKIP_IF_MSG(dbginfo.num_data_bps == 0, "No data breakpoints present"); dawr = dawr_present(&dbginfo); run_tests(child_pid, &dbginfo, dawr); diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-perf-asm.S b/tools/testing/selftests/powerpc/ptrace/ptrace-perf-asm.S new file mode 100644 index 000000000000..9aa2e58f3189 --- /dev/null +++ b/tools/testing/selftests/powerpc/ptrace/ptrace-perf-asm.S @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#include <ppc-asm.h> + +.global same_watch_addr_load +.global same_watch_addr_trap + +FUNC_START(same_watch_addr_child) + nop +same_watch_addr_load: + ld 0,0(3) + nop +same_watch_addr_trap: + trap + blr +FUNC_END(same_watch_addr_child) + + +.global perf_then_ptrace_load1 +.global perf_then_ptrace_load2 +.global perf_then_ptrace_trap + +FUNC_START(perf_then_ptrace_child) + nop +perf_then_ptrace_load1: + ld 0,0(3) +perf_then_ptrace_load2: + ld 0,0(4) + nop +perf_then_ptrace_trap: + trap + blr +FUNC_END(perf_then_ptrace_child) diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-perf-hwbreak.c b/tools/testing/selftests/powerpc/ptrace/ptrace-perf-hwbreak.c index 3344e74a97b4..a0a0b9bb5854 100644 --- a/tools/testing/selftests/powerpc/ptrace/ptrace-perf-hwbreak.c +++ b/tools/testing/selftests/powerpc/ptrace/ptrace-perf-hwbreak.c @@ -1,659 +1,445 @@ // SPDX-License-Identifier: GPL-2.0+ -#include <stdio.h> -#include <string.h> -#include <signal.h> -#include <stdlib.h> -#include <unistd.h> -#include <errno.h> -#include <linux/hw_breakpoint.h> -#include <linux/perf_event.h> + #include <asm/unistd.h> -#include <sys/ptrace.h> +#include <linux/hw_breakpoint.h> +#include <linux/ptrace.h> +#include <memory.h> +#include <stdlib.h> #include <sys/wait.h> -#include "ptrace.h" -char data[16]; +#include "utils.h" -/* Overlapping address range */ -volatile __u64 *ptrace_data1 = (__u64 *)&data[0]; -volatile __u64 *perf_data1 = (__u64 *)&data[4]; +/* + * Child subroutine that performs a load on the address, then traps + */ +void same_watch_addr_child(unsigned long *addr); -/* Non-overlapping address range */ -volatile __u64 *ptrace_data2 = (__u64 *)&data[0]; -volatile __u64 *perf_data2 = (__u64 *)&data[8]; +/* Address of the ld instruction in same_watch_addr_child() */ +extern char same_watch_addr_load[]; -static unsigned long pid_max_addr(void) -{ - FILE *fp; - char *line, *c; - char addr[100]; - size_t len = 0; - - fp = fopen("/proc/kallsyms", "r"); - if (!fp) { - printf("Failed to read /proc/kallsyms. Exiting..\n"); - exit(EXIT_FAILURE); - } +/* Address of the end trap instruction in same_watch_addr_child() */ +extern char same_watch_addr_trap[]; - while (getline(&line, &len, fp) != -1) { - if (!strstr(line, "pid_max") || strstr(line, "pid_max_max") || - strstr(line, "pid_max_min")) - continue; +/* + * Child subroutine that performs a load on the first address, then a load on + * the second address (with no instructions separating this from the first + * load), then traps. + */ +void perf_then_ptrace_child(unsigned long *first_addr, unsigned long *second_addr); - strncpy(addr, line, len < 100 ? len : 100); - c = strchr(addr, ' '); - *c = '\0'; - return strtoul(addr, &c, 16); - } - fclose(fp); - printf("Could not find pix_max. Exiting..\n"); - exit(EXIT_FAILURE); - return -1; -} +/* Address of the first ld instruction in perf_then_ptrace_child() */ +extern char perf_then_ptrace_load1[]; -static void perf_user_event_attr_set(struct perf_event_attr *attr, __u64 addr, __u64 len) -{ - memset(attr, 0, sizeof(struct perf_event_attr)); - attr->type = PERF_TYPE_BREAKPOINT; - attr->size = sizeof(struct perf_event_attr); - attr->bp_type = HW_BREAKPOINT_R; - attr->bp_addr = addr; - attr->bp_len = len; - attr->exclude_kernel = 1; - attr->exclude_hv = 1; -} +/* Address of the second ld instruction in perf_then_ptrace_child() */ +extern char perf_then_ptrace_load2[]; -static void perf_kernel_event_attr_set(struct perf_event_attr *attr) +/* Address of the end trap instruction in perf_then_ptrace_child() */ +extern char perf_then_ptrace_trap[]; + +static inline long sys_ptrace(long request, pid_t pid, unsigned long addr, unsigned long data) { - memset(attr, 0, sizeof(struct perf_event_attr)); - attr->type = PERF_TYPE_BREAKPOINT; - attr->size = sizeof(struct perf_event_attr); - attr->bp_type = HW_BREAKPOINT_R; - attr->bp_addr = pid_max_addr(); - attr->bp_len = sizeof(unsigned long); - attr->exclude_user = 1; - attr->exclude_hv = 1; + return syscall(__NR_ptrace, request, pid, addr, data); } -static int perf_cpu_event_open(int cpu, __u64 addr, __u64 len) +static long ptrace_traceme(void) { - struct perf_event_attr attr; - - perf_user_event_attr_set(&attr, addr, len); - return syscall(__NR_perf_event_open, &attr, -1, cpu, -1, 0); + return sys_ptrace(PTRACE_TRACEME, 0, 0, 0); } -static int perf_thread_event_open(pid_t child_pid, __u64 addr, __u64 len) +static long ptrace_getregs(pid_t pid, struct pt_regs *result) { - struct perf_event_attr attr; - - perf_user_event_attr_set(&attr, addr, len); - return syscall(__NR_perf_event_open, &attr, child_pid, -1, -1, 0); + return sys_ptrace(PTRACE_GETREGS, pid, 0, (unsigned long)result); } -static int perf_thread_cpu_event_open(pid_t child_pid, int cpu, __u64 addr, __u64 len) +static long ptrace_setregs(pid_t pid, struct pt_regs *result) { - struct perf_event_attr attr; - - perf_user_event_attr_set(&attr, addr, len); - return syscall(__NR_perf_event_open, &attr, child_pid, cpu, -1, 0); + return sys_ptrace(PTRACE_SETREGS, pid, 0, (unsigned long)result); } -static int perf_thread_kernel_event_open(pid_t child_pid) +static long ptrace_cont(pid_t pid, long signal) { - struct perf_event_attr attr; - - perf_kernel_event_attr_set(&attr); - return syscall(__NR_perf_event_open, &attr, child_pid, -1, -1, 0); + return sys_ptrace(PTRACE_CONT, pid, 0, signal); } -static int perf_cpu_kernel_event_open(int cpu) +static long ptrace_singlestep(pid_t pid, long signal) { - struct perf_event_attr attr; - - perf_kernel_event_attr_set(&attr); - return syscall(__NR_perf_event_open, &attr, -1, cpu, -1, 0); + return sys_ptrace(PTRACE_SINGLESTEP, pid, 0, signal); } -static int child(void) +static long ppc_ptrace_gethwdbginfo(pid_t pid, struct ppc_debug_info *dbginfo) { - int ret; - - ret = ptrace(PTRACE_TRACEME, 0, NULL, 0); - if (ret) { - printf("Error: PTRACE_TRACEME failed\n"); - return 0; - } - kill(getpid(), SIGUSR1); /* --> parent (SIGUSR1) */ - - return 0; + return sys_ptrace(PPC_PTRACE_GETHWDBGINFO, pid, 0, (unsigned long)dbginfo); } -static void ptrace_ppc_hw_breakpoint(struct ppc_hw_breakpoint *info, int type, - __u64 addr, int len) +static long ppc_ptrace_sethwdbg(pid_t pid, struct ppc_hw_breakpoint *bp_info) { - info->version = 1; - info->trigger_type = type; - info->condition_mode = PPC_BREAKPOINT_CONDITION_NONE; - info->addr = addr; - info->addr2 = addr + len; - info->condition_value = 0; - if (!len) - info->addr_mode = PPC_BREAKPOINT_MODE_EXACT; - else - info->addr_mode = PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE; + return sys_ptrace(PPC_PTRACE_SETHWDEBUG, pid, 0, (unsigned long)bp_info); } -static int ptrace_open(pid_t child_pid, __u64 wp_addr, int len) +static long ppc_ptrace_delhwdbg(pid_t pid, int bp_id) { - struct ppc_hw_breakpoint info; - - ptrace_ppc_hw_breakpoint(&info, PPC_BREAKPOINT_TRIGGER_RW, wp_addr, len); - return ptrace(PPC_PTRACE_SETHWDEBUG, child_pid, 0, &info); + return sys_ptrace(PPC_PTRACE_DELHWDEBUG, pid, 0L, bp_id); } -static int test1(pid_t child_pid) +static long ptrace_getreg_pc(pid_t pid, void **pc) { - int perf_fd; - int ptrace_fd; - int ret = 0; - - /* Test: - * if (new per thread event by ptrace) - * if (existing cpu event by perf) - * if (addr range overlaps) - * fail; - */ + struct pt_regs regs; + long err; - perf_fd = perf_cpu_event_open(0, (__u64)perf_data1, sizeof(*perf_data1)); - if (perf_fd < 0) - return -1; + err = ptrace_getregs(pid, ®s); + if (err) + return err; - ptrace_fd = ptrace_open(child_pid, (__u64)ptrace_data1, sizeof(*ptrace_data1)); - if (ptrace_fd > 0 || errno != ENOSPC) - ret = -1; + *pc = (void *)regs.nip; - close(perf_fd); - return ret; + return 0; } -static int test2(pid_t child_pid) +static long ptrace_setreg_pc(pid_t pid, void *pc) { - int perf_fd; - int ptrace_fd; - int ret = 0; - - /* Test: - * if (new per thread event by ptrace) - * if (existing cpu event by perf) - * if (addr range does not overlaps) - * allow; - */ + struct pt_regs regs; + long err; - perf_fd = perf_cpu_event_open(0, (__u64)perf_data2, sizeof(*perf_data2)); - if (perf_fd < 0) - return -1; - - ptrace_fd = ptrace_open(child_pid, (__u64)ptrace_data2, sizeof(*ptrace_data2)); - if (ptrace_fd < 0) { - ret = -1; - goto perf_close; - } - ptrace(PPC_PTRACE_DELHWDEBUG, child_pid, 0, ptrace_fd); - -perf_close: - close(perf_fd); - return ret; -} + err = ptrace_getregs(pid, ®s); + if (err) + return err; -static int test3(pid_t child_pid) -{ - int perf_fd; - int ptrace_fd; - int ret = 0; - - /* Test: - * if (new per thread event by ptrace) - * if (existing thread event by perf on the same thread) - * if (addr range overlaps) - * fail; - */ - perf_fd = perf_thread_event_open(child_pid, (__u64)perf_data1, - sizeof(*perf_data1)); - if (perf_fd < 0) - return -1; + regs.nip = (unsigned long)pc; - ptrace_fd = ptrace_open(child_pid, (__u64)ptrace_data1, sizeof(*ptrace_data1)); - if (ptrace_fd > 0 || errno != ENOSPC) - ret = -1; + err = ptrace_setregs(pid, ®s); + if (err) + return err; - close(perf_fd); - return ret; + return 0; } -static int test4(pid_t child_pid) +static int perf_event_open(struct perf_event_attr *attr, pid_t pid, int cpu, + int group_fd, unsigned long flags) { - int perf_fd; - int ptrace_fd; - int ret = 0; - - /* Test: - * if (new per thread event by ptrace) - * if (existing thread event by perf on the same thread) - * if (addr range does not overlaps) - * fail; - */ - perf_fd = perf_thread_event_open(child_pid, (__u64)perf_data2, - sizeof(*perf_data2)); - if (perf_fd < 0) - return -1; - - ptrace_fd = ptrace_open(child_pid, (__u64)ptrace_data2, sizeof(*ptrace_data2)); - if (ptrace_fd < 0) { - ret = -1; - goto perf_close; - } - ptrace(PPC_PTRACE_DELHWDEBUG, child_pid, 0, ptrace_fd); - -perf_close: - close(perf_fd); - return ret; + return syscall(__NR_perf_event_open, attr, pid, cpu, group_fd, flags); } -static int test5(pid_t child_pid) +static void perf_user_event_attr_set(struct perf_event_attr *attr, void *addr, u64 len) { - int perf_fd; - int ptrace_fd; - int cpid; - int ret = 0; - - /* Test: - * if (new per thread event by ptrace) - * if (existing thread event by perf on the different thread) - * allow; - */ - cpid = fork(); - if (!cpid) { - /* Temporary Child */ - pause(); - exit(EXIT_SUCCESS); - } - - perf_fd = perf_thread_event_open(cpid, (__u64)perf_data1, sizeof(*perf_data1)); - if (perf_fd < 0) { - ret = -1; - goto kill_child; - } - - ptrace_fd = ptrace_open(child_pid, (__u64)ptrace_data1, sizeof(*ptrace_data1)); - if (ptrace_fd < 0) { - ret = -1; - goto perf_close; - } + memset(attr, 0, sizeof(struct perf_event_attr)); - ptrace(PPC_PTRACE_DELHWDEBUG, child_pid, 0, ptrace_fd); -perf_close: - close(perf_fd); -kill_child: - kill(cpid, SIGINT); - return ret; + attr->type = PERF_TYPE_BREAKPOINT; + attr->size = sizeof(struct perf_event_attr); + attr->bp_type = HW_BREAKPOINT_R; + attr->bp_addr = (u64)addr; + attr->bp_len = len; + attr->exclude_kernel = 1; + attr->exclude_hv = 1; } -static int test6(pid_t child_pid) +static int perf_watchpoint_open(pid_t child_pid, void *addr, u64 len) { - int perf_fd; - int ptrace_fd; - int ret = 0; - - /* Test: - * if (new per thread kernel event by perf) - * if (existing thread event by ptrace on the same thread) - * allow; - * -- OR -- - * if (new per cpu kernel event by perf) - * if (existing thread event by ptrace) - * allow; - */ - ptrace_fd = ptrace_open(child_pid, (__u64)ptrace_data1, sizeof(*ptrace_data1)); - if (ptrace_fd < 0) - return -1; - - perf_fd = perf_thread_kernel_event_open(child_pid); - if (perf_fd < 0) { - ret = -1; - goto ptrace_close; - } - close(perf_fd); - - perf_fd = perf_cpu_kernel_event_open(0); - if (perf_fd < 0) { - ret = -1; - goto ptrace_close; - } - close(perf_fd); + struct perf_event_attr attr; -ptrace_close: - ptrace(PPC_PTRACE_DELHWDEBUG, child_pid, 0, ptrace_fd); - return ret; + perf_user_event_attr_set(&attr, addr, len); + return perf_event_open(&attr, child_pid, -1, -1, 0); } -static int test7(pid_t child_pid) +static int perf_read_counter(int perf_fd, u64 *count) { - int perf_fd; - int ptrace_fd; - int ret = 0; - - /* Test: - * if (new per thread event by perf) - * if (existing thread event by ptrace on the same thread) - * if (addr range overlaps) - * fail; + /* + * A perf counter is retrieved by the read() syscall. It contains + * the current count as 8 bytes that are interpreted as a u64 */ - ptrace_fd = ptrace_open(child_pid, (__u64)ptrace_data1, sizeof(*ptrace_data1)); - if (ptrace_fd < 0) - return -1; + ssize_t len = read(perf_fd, count, sizeof(*count)); - perf_fd = perf_thread_event_open(child_pid, (__u64)perf_data1, - sizeof(*perf_data1)); - if (perf_fd > 0 || errno != ENOSPC) - ret = -1; + if (len != sizeof(*count)) + return -1; - ptrace(PPC_PTRACE_DELHWDEBUG, child_pid, 0, ptrace_fd); - return ret; + return 0; } -static int test8(pid_t child_pid) +static void ppc_ptrace_init_breakpoint(struct ppc_hw_breakpoint *info, + int type, void *addr, int len) { - int perf_fd; - int ptrace_fd; - int ret = 0; - - /* Test: - * if (new per thread event by perf) - * if (existing thread event by ptrace on the same thread) - * if (addr range does not overlaps) - * allow; - */ - ptrace_fd = ptrace_open(child_pid, (__u64)ptrace_data2, sizeof(*ptrace_data2)); - if (ptrace_fd < 0) - return -1; - - perf_fd = perf_thread_event_open(child_pid, (__u64)perf_data2, - sizeof(*perf_data2)); - if (perf_fd < 0) { - ret = -1; - goto ptrace_close; - } - close(perf_fd); - -ptrace_close: - ptrace(PPC_PTRACE_DELHWDEBUG, child_pid, 0, ptrace_fd); - return ret; + info->version = 1; + info->trigger_type = type; + info->condition_mode = PPC_BREAKPOINT_CONDITION_NONE; + info->addr = (u64)addr; + info->addr2 = (u64)addr + len; + info->condition_value = 0; + if (!len) + info->addr_mode = PPC_BREAKPOINT_MODE_EXACT; + else + info->addr_mode = PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE; } -static int test9(pid_t child_pid) +/* + * Checks if we can place at least 2 watchpoints on the child process + */ +static int check_watchpoints(pid_t pid) { - int perf_fd; - int ptrace_fd; - int cpid; - int ret = 0; - - /* Test: - * if (new per thread event by perf) - * if (existing thread event by ptrace on the other thread) - * allow; - */ - ptrace_fd = ptrace_open(child_pid, (__u64)ptrace_data1, sizeof(*ptrace_data1)); - if (ptrace_fd < 0) - return -1; - - cpid = fork(); - if (!cpid) { - /* Temporary Child */ - pause(); - exit(EXIT_SUCCESS); - } + struct ppc_debug_info dbginfo; - perf_fd = perf_thread_event_open(cpid, (__u64)perf_data1, sizeof(*perf_data1)); - if (perf_fd < 0) { - ret = -1; - goto kill_child; - } - close(perf_fd); + FAIL_IF_MSG(ppc_ptrace_gethwdbginfo(pid, &dbginfo), "PPC_PTRACE_GETHWDBGINFO failed"); + SKIP_IF_MSG(dbginfo.num_data_bps <= 1, "Not enough data watchpoints (need at least 2)"); -kill_child: - kill(cpid, SIGINT); - ptrace(PPC_PTRACE_DELHWDEBUG, child_pid, 0, ptrace_fd); - return ret; + return 0; } -static int test10(pid_t child_pid) +/* + * Wrapper around a plain fork() call that sets up the child for + * ptrace-ing. Both the parent and child return from this, though + * the child is stopped until ptrace_cont(pid) is run by the parent. + */ +static int ptrace_fork_child(pid_t *pid) { - int perf_fd; - int ptrace_fd; - int ret = 0; - - /* Test: - * if (new per cpu event by perf) - * if (existing thread event by ptrace on the same thread) - * if (addr range overlaps) - * fail; - */ - ptrace_fd = ptrace_open(child_pid, (__u64)ptrace_data1, sizeof(*ptrace_data1)); - if (ptrace_fd < 0) - return -1; + int status; - perf_fd = perf_cpu_event_open(0, (__u64)perf_data1, sizeof(*perf_data1)); - if (perf_fd > 0 || errno != ENOSPC) - ret = -1; - - ptrace(PPC_PTRACE_DELHWDEBUG, child_pid, 0, ptrace_fd); - return ret; -} + *pid = fork(); -static int test11(pid_t child_pid) -{ - int perf_fd; - int ptrace_fd; - int ret = 0; - - /* Test: - * if (new per cpu event by perf) - * if (existing thread event by ptrace on the same thread) - * if (addr range does not overlap) - * allow; - */ - ptrace_fd = ptrace_open(child_pid, (__u64)ptrace_data2, sizeof(*ptrace_data2)); - if (ptrace_fd < 0) - return -1; + if (*pid < 0) + FAIL_IF_MSG(1, "Failed to fork child"); - perf_fd = perf_cpu_event_open(0, (__u64)perf_data2, sizeof(*perf_data2)); - if (perf_fd < 0) { - ret = -1; - goto ptrace_close; + if (!*pid) { + FAIL_IF_EXIT_MSG(ptrace_traceme(), "PTRACE_TRACEME failed"); + FAIL_IF_EXIT_MSG(raise(SIGSTOP), "Child failed to raise SIGSTOP"); + } else { + /* Synchronise on child SIGSTOP */ + FAIL_IF_MSG(waitpid(*pid, &status, 0) == -1, "Failed to wait for child"); + FAIL_IF_MSG(!WIFSTOPPED(status), "Child is not stopped"); } - close(perf_fd); -ptrace_close: - ptrace(PPC_PTRACE_DELHWDEBUG, child_pid, 0, ptrace_fd); - return ret; + return 0; } -static int test12(pid_t child_pid) +/* + * Tests the interaction between ptrace and perf watching the same data. + * + * We expect ptrace to take 'priority', as it is has before-execute + * semantics. + * + * The perf counter should not be incremented yet because perf has after-execute + * semantics. E.g., if ptrace changes the child PC, we don't even execute the + * instruction at all. + * + * When the child is stopped for ptrace, we test both continue and single step. + * Both should increment the perf counter. We also test changing the PC somewhere + * different and stepping, which should not increment the perf counter. + */ +int same_watch_addr_test(void) { - int perf_fd; - int ptrace_fd; - int ret = 0; - - /* Test: - * if (new per thread and per cpu event by perf) - * if (existing thread event by ptrace on the same thread) - * if (addr range overlaps) - * fail; - */ - ptrace_fd = ptrace_open(child_pid, (__u64)ptrace_data1, sizeof(*ptrace_data1)); - if (ptrace_fd < 0) - return -1; + struct ppc_hw_breakpoint bp_info; /* ptrace breakpoint info */ + int bp_id; /* Breakpoint handle of ptrace watchpoint */ + int perf_fd; /* File descriptor of perf performance counter */ + u64 perf_count; /* Most recently fetched perf performance counter value */ + pid_t pid; /* PID of child process */ + void *pc; /* Most recently fetched child PC value */ + int status; /* Stop status of child after waitpid */ + unsigned long value; /* Dummy value to be read/written to by child */ + int err; + + err = ptrace_fork_child(&pid); + if (err) + return err; + + if (!pid) { + same_watch_addr_child(&value); + exit(1); + } - perf_fd = perf_thread_cpu_event_open(child_pid, 0, (__u64)perf_data1, sizeof(*perf_data1)); - if (perf_fd > 0 || errno != ENOSPC) - ret = -1; + err = check_watchpoints(pid); + if (err) + return err; - ptrace(PPC_PTRACE_DELHWDEBUG, child_pid, 0, ptrace_fd); - return ret; -} + /* Place a perf watchpoint counter on value */ + perf_fd = perf_watchpoint_open(pid, &value, sizeof(value)); + FAIL_IF_MSG(perf_fd < 0, "Failed to open perf performance counter"); -static int test13(pid_t child_pid) -{ - int perf_fd; - int ptrace_fd; - int ret = 0; - - /* Test: - * if (new per thread and per cpu event by perf) - * if (existing thread event by ptrace on the same thread) - * if (addr range does not overlap) - * allow; - */ - ptrace_fd = ptrace_open(child_pid, (__u64)ptrace_data2, sizeof(*ptrace_data2)); - if (ptrace_fd < 0) - return -1; + /* Place a ptrace watchpoint on value */ + ppc_ptrace_init_breakpoint(&bp_info, PPC_BREAKPOINT_TRIGGER_READ, &value, sizeof(value)); + bp_id = ppc_ptrace_sethwdbg(pid, &bp_info); + FAIL_IF_MSG(bp_id < 0, "Failed to set ptrace watchpoint"); - perf_fd = perf_thread_cpu_event_open(child_pid, 0, (__u64)perf_data2, sizeof(*perf_data2)); - if (perf_fd < 0) { - ret = -1; - goto ptrace_close; - } - close(perf_fd); + /* Let the child run. It should stop on the ptrace watchpoint */ + FAIL_IF_MSG(ptrace_cont(pid, 0), "Failed to continue child"); -ptrace_close: - ptrace(PPC_PTRACE_DELHWDEBUG, child_pid, 0, ptrace_fd); - return ret; -} + FAIL_IF_MSG(waitpid(pid, &status, 0) == -1, "Failed to wait for child"); + FAIL_IF_MSG(!WIFSTOPPED(status), "Child is not stopped"); + FAIL_IF_MSG(ptrace_getreg_pc(pid, &pc), "Failed to get child PC"); + FAIL_IF_MSG(pc != same_watch_addr_load, "Child did not stop on load instruction"); -static int test14(pid_t child_pid) -{ - int perf_fd; - int ptrace_fd; - int cpid; - int ret = 0; - - /* Test: - * if (new per thread and per cpu event by perf) - * if (existing thread event by ptrace on the other thread) - * allow; + /* + * We stopped before executing the load, so perf should not have + * recorded any events yet */ - ptrace_fd = ptrace_open(child_pid, (__u64)ptrace_data1, sizeof(*ptrace_data1)); - if (ptrace_fd < 0) - return -1; - - cpid = fork(); - if (!cpid) { - /* Temporary Child */ - pause(); - exit(EXIT_SUCCESS); - } - - perf_fd = perf_thread_cpu_event_open(cpid, 0, (__u64)perf_data1, - sizeof(*perf_data1)); - if (perf_fd < 0) { - ret = -1; - goto kill_child; - } - close(perf_fd); - -kill_child: - kill(cpid, SIGINT); - ptrace(PPC_PTRACE_DELHWDEBUG, child_pid, 0, ptrace_fd); - return ret; -} + FAIL_IF_MSG(perf_read_counter(perf_fd, &perf_count), "Failed to read perf counter"); + FAIL_IF_MSG(perf_count != 0, "perf recorded unexpected event"); + + /* Single stepping over the load should increment the perf counter */ + FAIL_IF_MSG(ptrace_singlestep(pid, 0), "Failed to single step child"); + + FAIL_IF_MSG(waitpid(pid, &status, 0) == -1, "Failed to wait for child"); + FAIL_IF_MSG(!WIFSTOPPED(status), "Child is not stopped"); + FAIL_IF_MSG(ptrace_getreg_pc(pid, &pc), "Failed to get child PC"); + FAIL_IF_MSG(pc != same_watch_addr_load + 4, "Failed to single step load instruction"); + FAIL_IF_MSG(perf_read_counter(perf_fd, &perf_count), "Failed to read perf counter"); + FAIL_IF_MSG(perf_count != 1, "perf counter did not increment"); + + /* + * Set up a ptrace watchpoint on the value again and trigger it. + * The perf counter should not have incremented because we do not + * execute the load yet. + */ + FAIL_IF_MSG(ppc_ptrace_delhwdbg(pid, bp_id), "Failed to remove old ptrace watchpoint"); + bp_id = ppc_ptrace_sethwdbg(pid, &bp_info); + FAIL_IF_MSG(bp_id < 0, "Failed to set ptrace watchpoint"); + FAIL_IF_MSG(ptrace_setreg_pc(pid, same_watch_addr_load), "Failed to set child PC"); + FAIL_IF_MSG(ptrace_cont(pid, 0), "Failed to continue child"); + + FAIL_IF_MSG(waitpid(pid, &status, 0) == -1, "Failed to wait for child"); + FAIL_IF_MSG(!WIFSTOPPED(status), "Child is not stopped"); + FAIL_IF_MSG(ptrace_getreg_pc(pid, &pc), "Failed to get child PC"); + FAIL_IF_MSG(pc != same_watch_addr_load, "Child did not stop on load trap"); + FAIL_IF_MSG(perf_read_counter(perf_fd, &perf_count), "Failed to read perf counter"); + FAIL_IF_MSG(perf_count != 1, "perf counter should not have changed"); + + /* Continuing over the load should increment the perf counter */ + FAIL_IF_MSG(ptrace_cont(pid, 0), "Failed to continue child"); + + FAIL_IF_MSG(waitpid(pid, &status, 0) == -1, "Failed to wait for child"); + FAIL_IF_MSG(!WIFSTOPPED(status), "Child is not stopped"); + FAIL_IF_MSG(ptrace_getreg_pc(pid, &pc), "Failed to get child PC"); + FAIL_IF_MSG(pc != same_watch_addr_trap, "Child did not stop on end trap"); + FAIL_IF_MSG(perf_read_counter(perf_fd, &perf_count), "Failed to read perf counter"); + FAIL_IF_MSG(perf_count != 2, "perf counter did not increment"); + + /* + * If we set the child PC back to the load instruction, then continue, + * we should reach the end trap (because ptrace is one-shot) and have + * another perf event. + */ + FAIL_IF_MSG(ptrace_setreg_pc(pid, same_watch_addr_load), "Failed to set child PC"); + FAIL_IF_MSG(ptrace_cont(pid, 0), "Failed to continue child"); + + FAIL_IF_MSG(waitpid(pid, &status, 0) == -1, "Failed to wait for child"); + FAIL_IF_MSG(!WIFSTOPPED(status), "Child is not stopped"); + FAIL_IF_MSG(ptrace_getreg_pc(pid, &pc), "Failed to get child PC"); + FAIL_IF_MSG(pc != same_watch_addr_trap, "Child did not stop on end trap"); + FAIL_IF_MSG(perf_read_counter(perf_fd, &perf_count), "Failed to read perf counter"); + FAIL_IF_MSG(perf_count != 3, "perf counter did not increment"); + + /* + * If we set the child PC back to the load instruction, set a ptrace + * watchpoint on the load, then continue, we should immediately get + * the ptrace trap without incrementing the perf counter + */ + FAIL_IF_MSG(ppc_ptrace_delhwdbg(pid, bp_id), "Failed to remove old ptrace watchpoint"); + bp_id = ppc_ptrace_sethwdbg(pid, &bp_info); + FAIL_IF_MSG(bp_id < 0, "Failed to set ptrace watchpoint"); + FAIL_IF_MSG(ptrace_setreg_pc(pid, same_watch_addr_load), "Failed to set child PC"); + FAIL_IF_MSG(ptrace_cont(pid, 0), "Failed to continue child"); + + FAIL_IF_MSG(waitpid(pid, &status, 0) == -1, "Failed to wait for child"); + FAIL_IF_MSG(!WIFSTOPPED(status), "Child is not stopped"); + FAIL_IF_MSG(ptrace_getreg_pc(pid, &pc), "Failed to get child PC"); + FAIL_IF_MSG(pc != same_watch_addr_load, "Child did not stop on load instruction"); + FAIL_IF_MSG(perf_read_counter(perf_fd, &perf_count), "Failed to read perf counter"); + FAIL_IF_MSG(perf_count != 3, "perf counter should not have changed"); + + /* + * If we change the PC while stopped on the load instruction, we should + * not increment the perf counter (because ptrace is before-execute, + * perf is after-execute). + */ + FAIL_IF_MSG(ptrace_setreg_pc(pid, same_watch_addr_load + 4), "Failed to set child PC"); + FAIL_IF_MSG(ptrace_cont(pid, 0), "Failed to continue child"); -static int do_test(const char *msg, int (*fun)(pid_t arg), pid_t arg) -{ - int ret; + FAIL_IF_MSG(waitpid(pid, &status, 0) == -1, "Failed to wait for child"); + FAIL_IF_MSG(!WIFSTOPPED(status), "Child is not stopped"); + FAIL_IF_MSG(ptrace_getreg_pc(pid, &pc), "Failed to get child PC"); + FAIL_IF_MSG(pc != same_watch_addr_trap, "Child did not stop on end trap"); + FAIL_IF_MSG(perf_read_counter(perf_fd, &perf_count), "Failed to read perf counter"); + FAIL_IF_MSG(perf_count != 3, "perf counter should not have changed"); - ret = fun(arg); - if (ret) - printf("%s: Error\n", msg); - else - printf("%s: Ok\n", msg); - return ret; -} + /* Clean up child */ + FAIL_IF_MSG(kill(pid, SIGKILL) != 0, "Failed to kill child"); -char *desc[14] = { - "perf cpu event -> ptrace thread event (Overlapping)", - "perf cpu event -> ptrace thread event (Non-overlapping)", - "perf thread event -> ptrace same thread event (Overlapping)", - "perf thread event -> ptrace same thread event (Non-overlapping)", - "perf thread event -> ptrace other thread event", - "ptrace thread event -> perf kernel event", - "ptrace thread event -> perf same thread event (Overlapping)", - "ptrace thread event -> perf same thread event (Non-overlapping)", - "ptrace thread event -> perf other thread event", - "ptrace thread event -> perf cpu event (Overlapping)", - "ptrace thread event -> perf cpu event (Non-overlapping)", - "ptrace thread event -> perf same thread & cpu event (Overlapping)", - "ptrace thread event -> perf same thread & cpu event (Non-overlapping)", - "ptrace thread event -> perf other thread & cpu event", -}; - -static int test(pid_t child_pid) -{ - int ret = TEST_PASS; - - ret |= do_test(desc[0], test1, child_pid); - ret |= do_test(desc[1], test2, child_pid); - ret |= do_test(desc[2], test3, child_pid); - ret |= do_test(desc[3], test4, child_pid); - ret |= do_test(desc[4], test5, child_pid); - ret |= do_test(desc[5], test6, child_pid); - ret |= do_test(desc[6], test7, child_pid); - ret |= do_test(desc[7], test8, child_pid); - ret |= do_test(desc[8], test9, child_pid); - ret |= do_test(desc[9], test10, child_pid); - ret |= do_test(desc[10], test11, child_pid); - ret |= do_test(desc[11], test12, child_pid); - ret |= do_test(desc[12], test13, child_pid); - ret |= do_test(desc[13], test14, child_pid); - - return ret; + return 0; } -static void get_dbginfo(pid_t child_pid, struct ppc_debug_info *dbginfo) +/* + * Tests the interaction between ptrace and perf when: + * 1. perf watches a value + * 2. ptrace watches a different value + * 3. The perf value is read, then the ptrace value is read immediately after + * + * A breakpoint implementation may accidentally misattribute/skip one of + * the ptrace or perf handlers, as interrupt based work is done after perf + * and before ptrace. + * + * We expect the perf counter to increment before the ptrace watchpoint + * triggers. + */ +int perf_then_ptrace_test(void) { - if (ptrace(PPC_PTRACE_GETHWDBGINFO, child_pid, NULL, dbginfo)) { - perror("Can't get breakpoint info"); - exit(-1); + struct ppc_hw_breakpoint bp_info; /* ptrace breakpoint info */ + int bp_id; /* Breakpoint handle of ptrace watchpoint */ + int perf_fd; /* File descriptor of perf performance counter */ + u64 perf_count; /* Most recently fetched perf performance counter value */ + pid_t pid; /* PID of child process */ + void *pc; /* Most recently fetched child PC value */ + int status; /* Stop status of child after waitpid */ + unsigned long perf_value; /* Dummy value to be watched by perf */ + unsigned long ptrace_value; /* Dummy value to be watched by ptrace */ + int err; + + err = ptrace_fork_child(&pid); + if (err) + return err; + + /* + * If we are the child, run a subroutine that reads the perf value, + * then reads the ptrace value with consecutive load instructions + */ + if (!pid) { + perf_then_ptrace_child(&perf_value, &ptrace_value); + exit(0); } -} -static int ptrace_perf_hwbreak(void) -{ - int ret; - pid_t child_pid; - struct ppc_debug_info dbginfo; + err = check_watchpoints(pid); + if (err) + return err; - child_pid = fork(); - if (!child_pid) - return child(); + /* Place a perf watchpoint counter */ + perf_fd = perf_watchpoint_open(pid, &perf_value, sizeof(perf_value)); + FAIL_IF_MSG(perf_fd < 0, "Failed to open perf performance counter"); - /* parent */ - wait(NULL); /* <-- child (SIGUSR1) */ + /* Place a ptrace watchpoint */ + ppc_ptrace_init_breakpoint(&bp_info, PPC_BREAKPOINT_TRIGGER_READ, + &ptrace_value, sizeof(ptrace_value)); + bp_id = ppc_ptrace_sethwdbg(pid, &bp_info); + FAIL_IF_MSG(bp_id < 0, "Failed to set ptrace watchpoint"); - get_dbginfo(child_pid, &dbginfo); - SKIP_IF(dbginfo.num_data_bps <= 1); + /* Let the child run. It should stop on the ptrace watchpoint */ + FAIL_IF_MSG(ptrace_cont(pid, 0), "Failed to continue child"); - ret = perf_cpu_event_open(0, (__u64)perf_data1, sizeof(*perf_data1)); - SKIP_IF(ret < 0); - close(ret); + FAIL_IF_MSG(waitpid(pid, &status, 0) == -1, "Failed to wait for child"); + FAIL_IF_MSG(!WIFSTOPPED(status), "Child is not stopped"); + FAIL_IF_MSG(ptrace_getreg_pc(pid, &pc), "Failed to get child PC"); + FAIL_IF_MSG(pc != perf_then_ptrace_load2, "Child did not stop on ptrace load"); - ret = test(child_pid); + /* perf should have recorded the first load */ + FAIL_IF_MSG(perf_read_counter(perf_fd, &perf_count), "Failed to read perf counter"); + FAIL_IF_MSG(perf_count != 1, "perf counter did not increment"); - ptrace(PTRACE_CONT, child_pid, NULL, 0); - return ret; + /* Clean up child */ + FAIL_IF_MSG(kill(pid, SIGKILL) != 0, "Failed to kill child"); + + return 0; } int main(int argc, char *argv[]) { - return test_harness(ptrace_perf_hwbreak, "ptrace-perf-hwbreak"); + int err = 0; + + err |= test_harness(same_watch_addr_test, "same_watch_addr"); + err |= test_harness(perf_then_ptrace_test, "perf_then_ptrace"); + + return err; } diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c b/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c index bc454f899124..d89474377f11 100644 --- a/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c +++ b/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c @@ -192,7 +192,7 @@ static int parent(struct shared_info *info, pid_t pid) * to the child. */ ret = ptrace_read_regs(pid, NT_PPC_PKEY, regs, 3); - PARENT_SKIP_IF_UNSUPPORTED(ret, &info->child_sync); + PARENT_SKIP_IF_UNSUPPORTED(ret, &info->child_sync, "PKEYs not supported"); PARENT_FAIL_IF(ret, &info->child_sync); info->amr1 = info->amr2 = regs[0]; diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-tar.c b/tools/testing/selftests/powerpc/ptrace/ptrace-tar.c index 4436ca9d3caf..14726c77a6ce 100644 --- a/tools/testing/selftests/powerpc/ptrace/ptrace-tar.c +++ b/tools/testing/selftests/powerpc/ptrace/ptrace-tar.c @@ -79,7 +79,7 @@ int ptrace_tar(void) int ret, status; // TAR was added in v2.07 - SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_2_07)); + SKIP_IF_MSG(!have_hwcap2(PPC_FEATURE2_ARCH_2_07), "TAR requires ISA 2.07 compatible hardware"); shm_id = shmget(IPC_PRIVATE, sizeof(int) * 3, 0777|IPC_CREAT); pid = fork(); diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-gpr.c b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-gpr.c index 5dc152b162df..7c70d62587c2 100644 --- a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-gpr.c +++ b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-gpr.c @@ -112,8 +112,8 @@ int ptrace_tm_gpr(void) pid_t pid; int ret, status; - SKIP_IF(!have_htm()); - SKIP_IF(htm_is_synthetic()); + SKIP_IF_MSG(!have_htm(), "Don't have transactional memory"); + SKIP_IF_MSG(htm_is_synthetic(), "Transactional memory is synthetic"); shm_id = shmget(IPC_PRIVATE, sizeof(int) * 2, 0777|IPC_CREAT); pid = fork(); if (pid < 0) { diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-gpr.c b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-gpr.c index 458cc1a70ccf..6c17ed099969 100644 --- a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-gpr.c +++ b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-gpr.c @@ -118,8 +118,8 @@ int ptrace_tm_spd_gpr(void) pid_t pid; int ret, status; - SKIP_IF(!have_htm()); - SKIP_IF(htm_is_synthetic()); + SKIP_IF_MSG(!have_htm(), "Don't have transactional memory"); + SKIP_IF_MSG(htm_is_synthetic(), "Transactional memory is synthetic"); shm_id = shmget(IPC_PRIVATE, sizeof(int) * 3, 0777|IPC_CREAT); pid = fork(); if (pid < 0) { diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-tar.c b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-tar.c index e112a34fbe59..afd8dc2e2097 100644 --- a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-tar.c +++ b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-tar.c @@ -128,8 +128,8 @@ int ptrace_tm_spd_tar(void) pid_t pid; int ret, status; - SKIP_IF(!have_htm()); - SKIP_IF(htm_is_synthetic()); + SKIP_IF_MSG(!have_htm(), "Don't have transactional memory"); + SKIP_IF_MSG(htm_is_synthetic(), "Transactional memory is synthetic"); shm_id = shmget(IPC_PRIVATE, sizeof(int) * 3, 0777|IPC_CREAT); pid = fork(); if (pid == 0) diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-vsx.c b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-vsx.c index 40133d49fe39..14d2fac8f237 100644 --- a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-vsx.c +++ b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-vsx.c @@ -128,8 +128,8 @@ int ptrace_tm_spd_vsx(void) pid_t pid; int ret, status, i; - SKIP_IF(!have_htm()); - SKIP_IF(htm_is_synthetic()); + SKIP_IF_MSG(!have_htm(), "Don't have transactional memory"); + SKIP_IF_MSG(htm_is_synthetic(), "Transactional memory is synthetic"); shm_id = shmget(IPC_PRIVATE, sizeof(int) * 3, 0777|IPC_CREAT); for (i = 0; i < 128; i++) { diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spr.c b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spr.c index 880ba6a29a48..e64cdb04cecf 100644 --- a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spr.c +++ b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spr.c @@ -113,8 +113,8 @@ int ptrace_tm_spr(void) pid_t pid; int ret, status; - SKIP_IF(!have_htm()); - SKIP_IF(htm_is_synthetic()); + SKIP_IF_MSG(!have_htm(), "Don't have transactional memory"); + SKIP_IF_MSG(htm_is_synthetic(), "Transactional memory is synthetic"); shm_id = shmget(IPC_PRIVATE, sizeof(struct shared), 0777|IPC_CREAT); shm_id1 = shmget(IPC_PRIVATE, sizeof(int), 0777|IPC_CREAT); pid = fork(); diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-tar.c b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-tar.c index d0db6df0f0ea..3963d4b0429f 100644 --- a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-tar.c +++ b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-tar.c @@ -116,8 +116,8 @@ int ptrace_tm_tar(void) pid_t pid; int ret, status; - SKIP_IF(!have_htm()); - SKIP_IF(htm_is_synthetic()); + SKIP_IF_MSG(!have_htm(), "Don't have transactional memory"); + SKIP_IF_MSG(htm_is_synthetic(), "Transactional memory is synthetic"); shm_id = shmget(IPC_PRIVATE, sizeof(int) * 2, 0777|IPC_CREAT); pid = fork(); if (pid == 0) diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-vsx.c b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-vsx.c index 4f05ce4fd282..8c925d734a72 100644 --- a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-vsx.c +++ b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-vsx.c @@ -112,8 +112,8 @@ int ptrace_tm_vsx(void) pid_t pid; int ret, status, i; - SKIP_IF(!have_htm()); - SKIP_IF(htm_is_synthetic()); + SKIP_IF_MSG(!have_htm(), "Don't have transactional memory"); + SKIP_IF_MSG(htm_is_synthetic(), "Transactional memory is synthetic"); shm_id = shmget(IPC_PRIVATE, sizeof(int) * 2, 0777|IPC_CREAT); for (i = 0; i < 128; i++) { diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-vsx.c b/tools/testing/selftests/powerpc/ptrace/ptrace-vsx.c index cb9875f764ca..11bc624574fe 100644 --- a/tools/testing/selftests/powerpc/ptrace/ptrace-vsx.c +++ b/tools/testing/selftests/powerpc/ptrace/ptrace-vsx.c @@ -61,7 +61,7 @@ int ptrace_vsx(void) pid_t pid; int ret, status, i; - SKIP_IF(!have_hwcap(PPC_FEATURE_HAS_VSX)); + SKIP_IF_MSG(!have_hwcap(PPC_FEATURE_HAS_VSX), "Don't have VSX"); shm_id = shmget(IPC_PRIVATE, sizeof(int) * 2, 0777|IPC_CREAT); diff --git a/tools/testing/selftests/powerpc/stringloops/asm/export.h b/tools/testing/selftests/powerpc/stringloops/linux/export.h index 2d14a9b4248c..2d14a9b4248c 100644 --- a/tools/testing/selftests/powerpc/stringloops/asm/export.h +++ b/tools/testing/selftests/powerpc/stringloops/linux/export.h diff --git a/tools/testing/selftests/powerpc/vphn/asm/lppaca.h b/tools/testing/selftests/powerpc/vphn/asm/lppaca.h deleted file mode 120000 index 942b1d00999c..000000000000 --- a/tools/testing/selftests/powerpc/vphn/asm/lppaca.h +++ /dev/null @@ -1 +0,0 @@ -../../../../../../arch/powerpc/include/asm/lppaca.h
\ No newline at end of file diff --git a/tools/testing/selftests/powerpc/vphn/asm/vphn.h b/tools/testing/selftests/powerpc/vphn/asm/vphn.h new file mode 120000 index 000000000000..3a0b2a00171c --- /dev/null +++ b/tools/testing/selftests/powerpc/vphn/asm/vphn.h @@ -0,0 +1 @@ +../../../../../../arch/powerpc/include/asm/vphn.h
\ No newline at end of file diff --git a/tools/testing/selftests/prctl/.gitignore b/tools/testing/selftests/prctl/.gitignore index 7a657b25f686..05d5e31661df 100644 --- a/tools/testing/selftests/prctl/.gitignore +++ b/tools/testing/selftests/prctl/.gitignore @@ -3,3 +3,4 @@ disable-tsc-ctxt-sw-stress-test disable-tsc-on-off-stress-test disable-tsc-test set-anon-vma-name-test +set-process-name diff --git a/tools/testing/selftests/prctl/Makefile b/tools/testing/selftests/prctl/Makefile index c058b81eeb41..01dc90fbb509 100644 --- a/tools/testing/selftests/prctl/Makefile +++ b/tools/testing/selftests/prctl/Makefile @@ -5,12 +5,10 @@ ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/) ifeq ($(ARCH),x86) TEST_PROGS := disable-tsc-ctxt-sw-stress-test disable-tsc-on-off-stress-test \ - disable-tsc-test set-anon-vma-name-test + disable-tsc-test set-anon-vma-name-test set-process-name all: $(TEST_PROGS) include ../lib.mk -clean: - rm -fr $(TEST_PROGS) endif endif diff --git a/tools/testing/selftests/prctl/set-process-name.c b/tools/testing/selftests/prctl/set-process-name.c new file mode 100644 index 000000000000..3bc5e0e09eb9 --- /dev/null +++ b/tools/testing/selftests/prctl/set-process-name.c @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This test covers the PR_SET_NAME functionality of prctl calls + */ + +#include <errno.h> +#include <sys/prctl.h> +#include <string.h> + +#include "../kselftest_harness.h" + +#define CHANGE_NAME "changename" +#define EMPTY_NAME "" +#define TASK_COMM_LEN 16 + +int set_name(char *name) +{ + int res; + + res = prctl(PR_SET_NAME, name, NULL, NULL, NULL); + + if (res < 0) + return -errno; + return res; +} + +int check_is_name_correct(char *check_name) +{ + char name[TASK_COMM_LEN]; + int res; + + res = prctl(PR_GET_NAME, name, NULL, NULL, NULL); + + if (res < 0) + return -errno; + + return !strcmp(name, check_name); +} + +int check_null_pointer(char *check_name) +{ + char *name = NULL; + int res; + + res = prctl(PR_GET_NAME, name, NULL, NULL, NULL); + + return res; +} + +TEST(rename_process) { + + EXPECT_GE(set_name(CHANGE_NAME), 0); + EXPECT_TRUE(check_is_name_correct(CHANGE_NAME)); + + EXPECT_GE(set_name(EMPTY_NAME), 0); + EXPECT_TRUE(check_is_name_correct(EMPTY_NAME)); + + EXPECT_GE(set_name(CHANGE_NAME), 0); + EXPECT_LT(check_null_pointer(CHANGE_NAME), 0); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/proc/proc-empty-vm.c b/tools/testing/selftests/proc/proc-empty-vm.c index 7588428b8fcd..b16c13688b88 100644 --- a/tools/testing/selftests/proc/proc-empty-vm.c +++ b/tools/testing/selftests/proc/proc-empty-vm.c @@ -1,3 +1,4 @@ +#if defined __amd64__ || defined __i386__ /* * Copyright (c) 2022 Alexey Dobriyan <adobriyan@gmail.com> * @@ -37,6 +38,10 @@ #include <sys/wait.h> #include <unistd.h> +#ifdef __amd64__ +#define TEST_VSYSCALL +#endif + /* * 0: vsyscall VMA doesn't exist vsyscall=none * 1: vsyscall VMA is --xp vsyscall=xonly @@ -77,7 +82,7 @@ static const char proc_pid_smaps_vsyscall_1[] = "Swap: 0 kB\n" "SwapPss: 0 kB\n" "Locked: 0 kB\n" -"THPeligible: 0\n" +"THPeligible: 0\n" /* * "ProtectionKey:" field is conditional. It is possible to check it as well, * but I don't have such machine. @@ -107,7 +112,7 @@ static const char proc_pid_smaps_vsyscall_2[] = "Swap: 0 kB\n" "SwapPss: 0 kB\n" "Locked: 0 kB\n" -"THPeligible: 0\n" +"THPeligible: 0\n" /* * "ProtectionKey:" field is conditional. It is possible to check it as well, * but I'm too tired. @@ -119,6 +124,7 @@ static void sigaction_SIGSEGV(int _, siginfo_t *__, void *___) _exit(EXIT_FAILURE); } +#ifdef TEST_VSYSCALL static void sigaction_SIGSEGV_vsyscall(int _, siginfo_t *__, void *___) { _exit(g_vsyscall); @@ -170,6 +176,7 @@ static void vsyscall(void) exit(1); } } +#endif static int test_proc_pid_maps(pid_t pid) { @@ -299,7 +306,9 @@ int main(void) { int rv = EXIT_SUCCESS; +#ifdef TEST_VSYSCALL vsyscall(); +#endif switch (g_vsyscall) { case 0: @@ -346,6 +355,14 @@ int main(void) #ifdef __amd64__ munmap(NULL, ((size_t)1 << 47) - 4096); +#elif defined __i386__ + { + size_t len; + + for (len = -4096;; len -= 4096) { + munmap(NULL, len); + } + } #else #error "implement 'unmap everything'" #endif @@ -386,3 +403,9 @@ int main(void) return rv; } +#else +int main(void) +{ + return 4; +} +#endif diff --git a/tools/testing/selftests/ptp/testptp.c b/tools/testing/selftests/ptp/testptp.c index e9438a1862ad..c9f6cca4feb4 100644 --- a/tools/testing/selftests/ptp/testptp.c +++ b/tools/testing/selftests/ptp/testptp.c @@ -143,8 +143,10 @@ static void usage(char *progname) " -S set the system time from the ptp clock time\n" " -t val shift the ptp clock time by 'val' seconds\n" " -T val set the ptp clock time to 'val' seconds\n" + " -x val get an extended ptp clock time with the desired number of samples (up to %d)\n" + " -X get a ptp clock cross timestamp\n" " -z test combinations of rising/falling external time stamp flags\n", - progname); + progname, PTP_MAX_SAMPLES); } int main(int argc, char *argv[]) @@ -158,6 +160,8 @@ int main(int argc, char *argv[]) struct timex tx; struct ptp_clock_time *pct; struct ptp_sys_offset *sysoff; + struct ptp_sys_offset_extended *soe; + struct ptp_sys_offset_precise *xts; char *progname; unsigned int i; @@ -176,6 +180,8 @@ int main(int argc, char *argv[]) int index = 0; int list_pins = 0; int pct_offset = 0; + int getextended = 0; + int getcross = 0; int n_samples = 0; int pin_index = -1, pin_func; int pps = -1; @@ -190,7 +196,7 @@ int main(int argc, char *argv[]) progname = strrchr(argv[0], '/'); progname = progname ? 1+progname : argv[0]; - while (EOF != (c = getopt(argc, argv, "cd:e:f:ghH:i:k:lL:n:o:p:P:sSt:T:w:z"))) { + while (EOF != (c = getopt(argc, argv, "cd:e:f:ghH:i:k:lL:n:o:p:P:sSt:T:w:x:Xz"))) { switch (c) { case 'c': capabilities = 1; @@ -255,6 +261,18 @@ int main(int argc, char *argv[]) case 'w': pulsewidth = atoi(optarg); break; + case 'x': + getextended = atoi(optarg); + if (getextended < 1 || getextended > PTP_MAX_SAMPLES) { + fprintf(stderr, + "number of extended timestamp samples must be between 1 and %d; was asked for %d\n", + PTP_MAX_SAMPLES, getextended); + return -1; + } + break; + case 'X': + getcross = 1; + break; case 'z': flagtest = 1; break; @@ -535,6 +553,57 @@ int main(int argc, char *argv[]) free(sysoff); } + if (getextended) { + soe = calloc(1, sizeof(*soe)); + if (!soe) { + perror("calloc"); + return -1; + } + + soe->n_samples = getextended; + + if (ioctl(fd, PTP_SYS_OFFSET_EXTENDED, soe)) { + perror("PTP_SYS_OFFSET_EXTENDED"); + } else { + printf("extended timestamp request returned %d samples\n", + getextended); + + for (i = 0; i < getextended; i++) { + printf("sample #%2d: system time before: %lld.%09u\n", + i, soe->ts[i][0].sec, soe->ts[i][0].nsec); + printf(" phc time: %lld.%09u\n", + soe->ts[i][1].sec, soe->ts[i][1].nsec); + printf(" system time after: %lld.%09u\n", + soe->ts[i][2].sec, soe->ts[i][2].nsec); + } + } + + free(soe); + } + + if (getcross) { + xts = calloc(1, sizeof(*xts)); + if (!xts) { + perror("calloc"); + return -1; + } + + if (ioctl(fd, PTP_SYS_OFFSET_PRECISE, xts)) { + perror("PTP_SYS_OFFSET_PRECISE"); + } else { + puts("system and phc crosstimestamping request okay"); + + printf("device time: %lld.%09u\n", + xts->device.sec, xts->device.nsec); + printf("system time: %lld.%09u\n", + xts->sys_realtime.sec, xts->sys_realtime.nsec); + printf("monoraw time: %lld.%09u\n", + xts->sys_monoraw.sec, xts->sys_monoraw.nsec); + } + + free(xts); + } + close(fd); return 0; } diff --git a/tools/testing/selftests/rcutorture/bin/configcheck.sh b/tools/testing/selftests/rcutorture/bin/configcheck.sh index b92dfeb7fbbf..99162d18bad3 100755 --- a/tools/testing/selftests/rcutorture/bin/configcheck.sh +++ b/tools/testing/selftests/rcutorture/bin/configcheck.sh @@ -3,6 +3,8 @@ # # Usage: configcheck.sh .config .config-template # +# Non-empty output if errors detected. +# # Copyright (C) IBM Corporation, 2011 # # Authors: Paul E. McKenney <paulmck@linux.ibm.com> @@ -10,32 +12,35 @@ T="`mktemp -d ${TMPDIR-/tmp}/configcheck.sh.XXXXXX`" trap 'rm -rf $T' 0 -sed -e 's/"//g' < $1 > $T/.config +# function test_kconfig_enabled ( Kconfig-var=val ) +function test_kconfig_enabled () { + if ! grep -q "^$1$" $T/.config + then + echo :$1: improperly set + return 1 + fi + return 0 +} -sed -e 's/"//g' -e 's/\(.*\)=n/# \1 is not set/' -e 's/^#CHECK#//' < $2 | -awk ' -{ - print "if grep -q \"" $0 "\" < '"$T/.config"'"; - print "then"; - print "\t:"; - print "else"; - if ($1 == "#") { - print "\tif grep -q \"" $2 "\" < '"$T/.config"'"; - print "\tthen"; - print "\t\tif test \"$firsttime\" = \"\"" - print "\t\tthen" - print "\t\t\tfirsttime=1" - print "\t\tfi" - print "\t\techo \":" $2 ": improperly set\""; - print "\telse"; - print "\t\t:"; - print "\tfi"; - } else { - print "\tif test \"$firsttime\" = \"\"" - print "\tthen" - print "\t\tfirsttime=1" - print "\tfi" - print "\techo \":" $0 ": improperly set\""; - } - print "fi"; - }' | sh +# function test_kconfig_disabled ( Kconfig-var ) +function test_kconfig_disabled () { + if grep -q "^$1=n$" $T/.config + then + return 0 + fi + if grep -q "^$1=" $T/.config + then + echo :$1=n: improperly set + return 1 + fi + return 0 +} + +sed -e 's/"//g' < $1 > $T/.config +sed -e 's/^#CHECK#//' < $2 > $T/ConfigFragment +grep '^CONFIG_.*=n$' $T/ConfigFragment | + sed -e 's/^/test_kconfig_disabled /' -e 's/=n$//' > $T/kconfig-n.sh +. $T/kconfig-n.sh +grep -v '^CONFIG_.*=n$' $T/ConfigFragment | grep '^CONFIG_' | + sed -e 's/^/test_kconfig_enabled /' > $T/kconfig-not-n.sh +. $T/kconfig-not-n.sh diff --git a/tools/testing/selftests/rcutorture/bin/functions.sh b/tools/testing/selftests/rcutorture/bin/functions.sh index 48b9147e8c91..b8e2ea23cb3f 100644 --- a/tools/testing/selftests/rcutorture/bin/functions.sh +++ b/tools/testing/selftests/rcutorture/bin/functions.sh @@ -45,7 +45,7 @@ checkarg () { configfrag_boot_params () { if test -r "$2.boot" then - echo $1 `grep -v '^#' "$2.boot" | tr '\012' ' '` + echo `grep -v '^#' "$2.boot" | tr '\012' ' '` $1 else echo $1 fi diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuscale.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuscale.sh index b582113178ac..f683e424ddd5 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuscale.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuscale.sh @@ -40,6 +40,10 @@ awk ' sum += $5 / 1000.; } +/rcu_scale: Grace-period kthread CPU time/ { + cputime = $6; +} + END { newNR = asort(gptimes); if (newNR <= 0) { @@ -78,6 +82,8 @@ END { print "90th percentile grace-period duration: " gptimes[pct90]; print "99th percentile grace-period duration: " gptimes[pct99]; print "Maximum grace-period duration: " gptimes[newNR]; - print "Grace periods: " ngps + 0 " Batches: " nbatches + 0 " Ratio: " ngps / nbatches; + if (cputime != "") + cpustr = " CPU: " cputime; + print "Grace periods: " ngps + 0 " Batches: " nbatches + 0 " Ratio: " ngps / nbatches cpustr; print "Computed from rcuscale printk output."; }' diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh index 1df7e695edf7..5be670dd4009 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh @@ -16,6 +16,8 @@ T=/tmp/kvm-recheck.sh.$$ trap 'rm -f $T' 0 2 +configerrors=0 + PATH=`pwd`/tools/testing/selftests/rcutorture/bin:$PATH; export PATH . functions.sh for rd in "$@" @@ -32,7 +34,7 @@ do fi TORTURE_SUITE="`cat $i/../torture_suite`" ; export TORTURE_SUITE configfile=`echo $i | sed -e 's,^.*/,,'` - rm -f $i/console.log.*.diags + rm -f $i/console.log.*.diags $i/ConfigFragment.diags case "${TORTURE_SUITE}" in X*) ;; @@ -49,8 +51,21 @@ do then echo QEMU killed fi - configcheck.sh $i/.config $i/ConfigFragment > $T 2>&1 - cat $T + configcheck.sh $i/.config $i/ConfigFragment > $i/ConfigFragment.diags 2>&1 + if grep -q '^CONFIG_KCSAN=y$' $i/ConfigFragment.input + then + # KCSAN forces a number of Kconfig options, so remove + # complaints about those Kconfig options in KCSAN runs. + mv $i/ConfigFragment.diags $i/ConfigFragment.diags.kcsan + grep -v -E 'CONFIG_PROVE_RCU|CONFIG_PREEMPT_COUNT' $i/ConfigFragment.diags.kcsan > $i/ConfigFragment.diags + fi + if test -s $i/ConfigFragment.diags + then + cat $i/ConfigFragment.diags + configerrors=$((configerrors+1)) + else + rm $i/ConfigFragment.diags + fi if test -r $i/Make.oldconfig.err then cat $i/Make.oldconfig.err @@ -65,7 +80,14 @@ do if test -f "$i/buildonly" then echo Build-only run, no boot/test - configcheck.sh $i/.config $i/ConfigFragment + configcheck.sh $i/.config $i/ConfigFragment > $i/ConfigFragment.diags 2>&1 + if test -s $i/ConfigFragment.diags + then + cat $i/ConfigFragment.diags + configerrors=$((configerrors+1)) + else + rm $i/ConfigFragment.diags + fi parse-build.sh $i/Make.out $configfile elif test -f "$i/qemu-cmd" then @@ -79,10 +101,10 @@ do done if test -f "$rd/kcsan.sum" then - if ! test -f $T + if ! test -f $i/ConfigFragment.diags then : - elif grep -q CONFIG_KCSAN=y $T + elif grep -q CONFIG_KCSAN=y $i/ConfigFragment.diags then echo "Compiler or architecture does not support KCSAN!" echo Did you forget to switch your compiler with '--kmake-arg CC=<cc-that-supports-kcsan>'? @@ -94,17 +116,23 @@ do fi fi done + +if test "$configerrors" -gt 0 +then + echo $configerrors runs with .config errors. + ret=1 +fi EDITOR=echo kvm-find-errors.sh "${@: -1}" > $T 2>&1 builderrors="`tr ' ' '\012' < $T | grep -c '/Make.out.diags'`" if test "$builderrors" -gt 0 then echo $builderrors runs with build errors. - ret=1 + ret=2 fi runerrors="`tr ' ' '\012' < $T | grep -c '/console.log.diags'`" if test "$runerrors" -gt 0 then echo $runerrors runs with runtime errors. - ret=2 + ret=3 fi exit $ret diff --git a/tools/testing/selftests/rcutorture/bin/kvm-remote.sh b/tools/testing/selftests/rcutorture/bin/kvm-remote.sh index a2328163eba1..134cdef5a6e0 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-remote.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-remote.sh @@ -137,14 +137,20 @@ chmod +x $T/bin/kvm-remote-*.sh # Check first to avoid the need for cleanup for system-name typos for i in $systems do - ncpus="`ssh -o BatchMode=yes $i getconf _NPROCESSORS_ONLN 2> /dev/null`" + ssh -o BatchMode=yes $i getconf _NPROCESSORS_ONLN > $T/ssh.stdout 2> $T/ssh.stderr ret=$? if test "$ret" -ne 0 then - echo System $i unreachable, giving up. | tee -a "$oldrun/remote-log" + echo "System $i unreachable ($ret), giving up." | tee -a "$oldrun/remote-log" + echo ' --- ssh stdout: vvv' | tee -a "$oldrun/remote-log" + cat $T/ssh.stdout | tee -a "$oldrun/remote-log" + echo ' --- ssh stdout: ^^^' | tee -a "$oldrun/remote-log" + echo ' --- ssh stderr: vvv' | tee -a "$oldrun/remote-log" + cat $T/ssh.stderr | tee -a "$oldrun/remote-log" + echo ' --- ssh stderr: ^^^' | tee -a "$oldrun/remote-log" exit 4 fi - echo $i: $ncpus CPUs " " `date` | tee -a "$oldrun/remote-log" + echo $i: `cat $T/ssh.stdout` CPUs " " `date` | tee -a "$oldrun/remote-log" done # Download and expand the tarball on all systems. diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh index d2a3710a5f2a..b33cd8753689 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh @@ -9,9 +9,10 @@ # # Usage: kvm-test-1-run.sh config resdir seconds qemu-args boot_args_in # -# qemu-args defaults to "-enable-kvm -nographic", along with arguments -# specifying the number of CPUs and other options -# generated from the underlying CPU architecture. +# qemu-args defaults to "-enable-kvm -display none -no-reboot", along +# with arguments specifying the number of CPUs +# and other options generated from the underlying +# CPU architecture. # boot_args_in defaults to value returned by the per_version_boot_params # shell function. # @@ -57,7 +58,6 @@ config_override_param () { cat $T/Kconfig_args >> $resdir/ConfigFragment.input config_override.sh $T/$2 $T/Kconfig_args > $T/$2.tmp mv $T/$2.tmp $T/$2 - # Note that "#CHECK#" is not permitted on commandline. fi } @@ -140,7 +140,7 @@ then fi # Generate -smp qemu argument. -qemu_args="-enable-kvm -nographic $qemu_args" +qemu_args="-enable-kvm -display none -no-reboot $qemu_args" cpu_count=`configNR_CPUS.sh $resdir/ConfigFragment` cpu_count=`configfrag_boot_cpus "$boot_args_in" "$config_template" "$cpu_count"` if test "$cpu_count" -gt "$TORTURE_ALLOTED_CPUS" @@ -163,7 +163,7 @@ boot_args="`configfrag_boot_params "$boot_args_in" "$config_template"`" boot_args="`per_version_boot_params "$boot_args" $resdir/.config $seconds`" if test -n "$TORTURE_BOOT_GDB_ARG" then - boot_args="$boot_args $TORTURE_BOOT_GDB_ARG" + boot_args="$TORTURE_BOOT_GDB_ARG $boot_args" fi # Give bare-metal advice diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh index d3cdc2d33d4b..b0f36a638a69 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm.sh @@ -186,7 +186,7 @@ do fi ;; --kconfig|--kconfigs) - checkarg --kconfig "(Kconfig options)" $# "$2" '^CONFIG_[A-Z0-9_]\+=\([ynm]\|[0-9]\+\|"[^"]*"\)\( CONFIG_[A-Z0-9_]\+=\([ynm]\|[0-9]\+\|"[^"]*"\)\)*$' '^error$' + checkarg --kconfig "(Kconfig options)" $# "$2" '^\(#CHECK#\)\?CONFIG_[A-Z0-9_]\+=\([ynm]\|[0-9]\+\|"[^"]*"\)\( \(#CHECK#\)\?CONFIG_[A-Z0-9_]\+=\([ynm]\|[0-9]\+\|"[^"]*"\)\)*$' '^error$' TORTURE_KCONFIG_ARG="`echo "$TORTURE_KCONFIG_ARG $2" | sed -e 's/^ *//' -e 's/ *$//'`" shift ;; diff --git a/tools/testing/selftests/rcutorture/bin/mkinitrd.sh b/tools/testing/selftests/rcutorture/bin/mkinitrd.sh index 71f0dfbb2a6d..212c52ca90b5 100755 --- a/tools/testing/selftests/rcutorture/bin/mkinitrd.sh +++ b/tools/testing/selftests/rcutorture/bin/mkinitrd.sh @@ -10,7 +10,6 @@ D=tools/testing/selftests/rcutorture # Prerequisite checks -[ -z "$D" ] && echo >&2 "No argument supplied" && exit 1 if [ ! -d "$D" ]; then echo >&2 "$D does not exist: Malformed kernel source tree?" exit 1 @@ -34,12 +33,16 @@ cat > init.c << '___EOF___' volatile unsigned long delaycount; -int main(int argc, int argv[]) +int main(int argc, char *argv[]) { int i; struct timeval tv; struct timeval tvb; + printf("Torture-test rudimentary init program started, command line:\n"); + for (i = 0; i < argc; i++) + printf(" %s", argv[i]); + printf("\n"); for (;;) { sleep(1); /* Need some userspace time. */ @@ -64,15 +67,23 @@ ___EOF___ # build using nolibc on supported archs (smaller executable) and fall # back to regular glibc on other ones. if echo -e "#if __x86_64__||__i386__||__i486__||__i586__||__i686__" \ - "||__ARM_EABI__||__aarch64__||__s390x__\nyes\n#endif" \ + "||__ARM_EABI__||__aarch64__||__s390x__||__loongarch__\nyes\n#endif" \ | ${CROSS_COMPILE}gcc -E -nostdlib -xc - \ | grep -q '^yes'; then # architecture supported by nolibc ${CROSS_COMPILE}gcc -fno-asynchronous-unwind-tables -fno-ident \ -nostdlib -include ../../../../include/nolibc/nolibc.h \ -s -static -Os -o init init.c -lgcc + ret=$? else ${CROSS_COMPILE}gcc -s -static -Os -o init init.c + ret=$? +fi + +if [ "$ret" -ne 0 ] +then + echo "Failed to create a statically linked C-language initrd" + exit "$ret" fi rm init.c diff --git a/tools/testing/selftests/rcutorture/bin/torture.sh b/tools/testing/selftests/rcutorture/bin/torture.sh index 5a2ae2264403..12b50a4a881a 100755 --- a/tools/testing/selftests/rcutorture/bin/torture.sh +++ b/tools/testing/selftests/rcutorture/bin/torture.sh @@ -55,6 +55,8 @@ do_kasan=yes do_kcsan=no do_clocksourcewd=yes do_rt=yes +do_rcutasksflavors=yes +do_srcu_lockdep=yes # doyesno - Helper function for yes/no arguments function doyesno () { @@ -73,18 +75,20 @@ usage () { echo " --configs-locktorture \"config-file list w/ repeat factor (10*LOCK01)\"" echo " --configs-scftorture \"config-file list w/ repeat factor (2*CFLIST)\"" echo " --do-all" - echo " --do-allmodconfig / --do-no-allmodconfig" - echo " --do-clocksourcewd / --do-no-clocksourcewd" - echo " --do-kasan / --do-no-kasan" - echo " --do-kcsan / --do-no-kcsan" - echo " --do-kvfree / --do-no-kvfree" - echo " --do-locktorture / --do-no-locktorture" + echo " --do-allmodconfig / --do-no-allmodconfig / --no-allmodconfig" + echo " --do-clocksourcewd / --do-no-clocksourcewd / --no-clocksourcewd" + echo " --do-kasan / --do-no-kasan / --no-kasan" + echo " --do-kcsan / --do-no-kcsan / --no-kcsan" + echo " --do-kvfree / --do-no-kvfree / --no-kvfree" + echo " --do-locktorture / --do-no-locktorture / --no-locktorture" echo " --do-none" - echo " --do-rcuscale / --do-no-rcuscale" - echo " --do-rcutorture / --do-no-rcutorture" - echo " --do-refscale / --do-no-refscale" - echo " --do-rt / --do-no-rt" - echo " --do-scftorture / --do-no-scftorture" + echo " --do-rcuscale / --do-no-rcuscale / --no-rcuscale" + echo " --do-rcutasksflavors / --do-no-rcutasksflavors / --no-rcutasksflavors" + echo " --do-rcutorture / --do-no-rcutorture / --no-rcutorture" + echo " --do-refscale / --do-no-refscale / --no-refscale" + echo " --do-rt / --do-no-rt / --no-rt" + echo " --do-scftorture / --do-no-scftorture / --no-scftorture" + echo " --do-srcu-lockdep / --do-no-srcu-lockdep / --no-srcu-lockdep" echo " --duration [ <minutes> | <hours>h | <days>d ]" echo " --kcsan-kmake-arg kernel-make-arguments" exit 1 @@ -115,6 +119,7 @@ do ;; --do-all|--doall) do_allmodconfig=yes + do_rcutasksflavor=yes do_rcutorture=yes do_locktorture=yes do_scftorture=yes @@ -125,27 +130,29 @@ do do_kasan=yes do_kcsan=yes do_clocksourcewd=yes + do_srcu_lockdep=yes ;; - --do-allmodconfig|--do-no-allmodconfig) + --do-allmodconfig|--do-no-allmodconfig|--no-allmodconfig) do_allmodconfig=`doyesno "$1" --do-allmodconfig` ;; - --do-clocksourcewd|--do-no-clocksourcewd) + --do-clocksourcewd|--do-no-clocksourcewd|--no-clocksourcewd) do_clocksourcewd=`doyesno "$1" --do-clocksourcewd` ;; - --do-kasan|--do-no-kasan) + --do-kasan|--do-no-kasan|--no-kasan) do_kasan=`doyesno "$1" --do-kasan` ;; - --do-kcsan|--do-no-kcsan) + --do-kcsan|--do-no-kcsan|--no-kcsan) do_kcsan=`doyesno "$1" --do-kcsan` ;; - --do-kvfree|--do-no-kvfree) + --do-kvfree|--do-no-kvfree|--no-kvfree) do_kvfree=`doyesno "$1" --do-kvfree` ;; - --do-locktorture|--do-no-locktorture) + --do-locktorture|--do-no-locktorture|--no-locktorture) do_locktorture=`doyesno "$1" --do-locktorture` ;; --do-none|--donone) do_allmodconfig=no + do_rcutasksflavors=no do_rcutorture=no do_locktorture=no do_scftorture=no @@ -156,22 +163,29 @@ do do_kasan=no do_kcsan=no do_clocksourcewd=no + do_srcu_lockdep=no ;; - --do-rcuscale|--do-no-rcuscale) + --do-rcuscale|--do-no-rcuscale|--no-rcuscale) do_rcuscale=`doyesno "$1" --do-rcuscale` ;; - --do-rcutorture|--do-no-rcutorture) + --do-rcutasksflavors|--do-no-rcutasksflavors|--no-rcutasksflavors) + do_rcutasksflavors=`doyesno "$1" --do-rcutasksflavors` + ;; + --do-rcutorture|--do-no-rcutorture|--no-rcutorture) do_rcutorture=`doyesno "$1" --do-rcutorture` ;; - --do-refscale|--do-no-refscale) + --do-refscale|--do-no-refscale|--no-refscale) do_refscale=`doyesno "$1" --do-refscale` ;; - --do-rt|--do-no-rt) + --do-rt|--do-no-rt|--no-rt) do_rt=`doyesno "$1" --do-rt` ;; - --do-scftorture|--do-no-scftorture) + --do-scftorture|--do-no-scftorture|--no-scftorture) do_scftorture=`doyesno "$1" --do-scftorture` ;; + --do-srcu-lockdep|--do-no-srcu-lockdep|--no-srcu-lockdep) + do_srcu_lockdep=`doyesno "$1" --do-srcu-lockdep` + ;; --duration) checkarg --duration "(minutes)" $# "$2" '^[0-9][0-9]*\(m\|h\|d\|\)$' '^error' mult=1 @@ -361,6 +375,40 @@ then fi fi +# Test building RCU Tasks flavors in isolation, both SMP and !SMP +if test "$do_rcutasksflavors" = "yes" +then + echo " --- rcutasksflavors:" Start `date` | tee -a $T/log + rtfdir="tools/testing/selftests/rcutorture/res/$ds/results-rcutasksflavors" + mkdir -p "$rtfdir" + cat > $T/rcutasksflavors << __EOF__ +#CHECK#CONFIG_TASKS_RCU=n +#CHECK#CONFIG_TASKS_RUDE_RCU=n +#CHECK#CONFIG_TASKS_TRACE_RCU=n +__EOF__ + for flavor in CONFIG_TASKS_RCU CONFIG_TASKS_RUDE_RCU CONFIG_TASKS_TRACE_RCU + do + forceflavor="`echo $flavor | sed -e 's/^CONFIG/CONFIG_FORCE/'`" + deselectedflavors="`grep -v $flavor $T/rcutasksflavors | tr '\012' ' ' | tr -s ' ' | sed -e 's/ *$//'`" + echo " --- Running RCU Tasks Trace flavor $flavor `date`" >> $rtfdir/log + tools/testing/selftests/rcutorture/bin/kvm.sh --datestamp "$ds/results-rcutasksflavors/$flavor" --buildonly --configs "TINY01 TREE04" --kconfig "CONFIG_RCU_EXPERT=y CONFIG_RCU_SCALE_TEST=y $forceflavor=y $deselectedflavors" --trust-make > $T/$flavor.out 2>&1 + retcode=$? + if test "$retcode" -ne 0 + then + break + fi + done + if test "$retcode" -eq 0 + then + echo "rcutasksflavors($retcode)" $rtfdir >> $T/successes + echo Success >> $rtfdir/log + else + echo "rcutasksflavors($retcode)" $rtfdir >> $T/failures + echo " --- rcutasksflavors Test summary:" >> $rtfdir/log + echo " --- Summary: Exit code $retcode from $flavor, see Make.out" >> $rtfdir/log + fi +fi + # --torture rcu if test "$do_rcutorture" = "yes" then @@ -376,8 +424,10 @@ fi if test "$do_scftorture" = "yes" then + # Scale memory based on the number of CPUs. + scfmem=$((2+HALF_ALLOTED_CPUS/16)) torture_bootargs="scftorture.nthreads=$HALF_ALLOTED_CPUS torture.disable_onoff_at_boot csdlock_debug=1" - torture_set "scftorture" tools/testing/selftests/rcutorture/bin/kvm.sh --torture scf --allcpus --duration "$duration_scftorture" --configs "$configs_scftorture" --kconfig "CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --memory 2G --trust-make + torture_set "scftorture" tools/testing/selftests/rcutorture/bin/kvm.sh --torture scf --allcpus --duration "$duration_scftorture" --configs "$configs_scftorture" --kconfig "CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --memory ${scfmem}G --trust-make fi if test "$do_rt" = "yes" @@ -391,6 +441,23 @@ then torture_set "rcurttorture-exp" tools/testing/selftests/rcutorture/bin/kvm.sh --allcpus --duration "$duration_rcutorture" --configs "TREE03" --trust-make fi +if test "$do_srcu_lockdep" = "yes" +then + echo " --- do-srcu-lockdep:" Start `date` | tee -a $T/log + tools/testing/selftests/rcutorture/bin/srcu_lockdep.sh --datestamp "$ds/results-srcu-lockdep" > $T/srcu_lockdep.sh.out 2>&1 + retcode=$? + cp $T/srcu_lockdep.sh.out "tools/testing/selftests/rcutorture/res/$ds/results-srcu-lockdep/log" + if test "$retcode" -eq 0 + then + echo "srcu_lockdep($retcode)" "tools/testing/selftests/rcutorture/res/$ds/results-srcu-lockdep" >> $T/successes + echo Success >> "tools/testing/selftests/rcutorture/res/$ds/results-srcu-lockdep/log" + else + echo "srcu_lockdep($retcode)" "tools/testing/selftests/rcutorture/res/$ds/results-srcu-lockdep" >> $T/failures + echo " --- srcu_lockdep Test Summary:" >> "tools/testing/selftests/rcutorture/res/$ds/results-srcu-lockdep/log" + echo " --- Summary: Exit code $retcode from srcu_lockdep.sh, see ds/results-srcu-lockdep" >> "tools/testing/selftests/rcutorture/res/$ds/results-srcu-lockdep/log" + fi +fi + if test "$do_refscale" = yes then primlist="`grep '\.name[ ]*=' kernel/rcu/refscale.c | sed -e 's/^[^"]*"//' -e 's/".*$//'`" @@ -541,11 +608,23 @@ then fi echo Started at $startdate, ended at `date`, duration `get_starttime_duration $starttime`. | tee -a $T/log echo Summary: Successes: $nsuccesses Failures: $nfailures. | tee -a $T/log +tdir="`cat $T/successes $T/failures | head -1 | awk '{ print $NF }' | sed -e 's,/[^/]\+/*$,,'`" +find "$tdir" -name 'ConfigFragment.diags' -print > $T/configerrors +find "$tdir" -name 'Make.out.diags' -print > $T/builderrors +if test -s "$T/configerrors" +then + echo " Scenarios with .config errors: `wc -l "$T/configerrors" | awk '{ print $1 }'`" + nonkcsanbug="yes" +fi +if test -s "$T/builderrors" +then + echo " Scenarios with build errors: `wc -l "$T/builderrors" | awk '{ print $1 }'`" + nonkcsanbug="yes" +fi if test -z "$nonkcsanbug" && test -s "$T/failuresum" then echo " All bugs were KCSAN failures." fi -tdir="`cat $T/successes $T/failures | head -1 | awk '{ print $NF }' | sed -e 's,/[^/]\+/*$,,'`" if test -n "$tdir" && test $compress_concurrency -gt 0 then # KASAN vmlinux files can approach 1GB in size, so compress them. diff --git a/tools/testing/selftests/rcutorture/configs/lock/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/lock/ver_functions.sh index d3e4b2971f92..e7bb32709d78 100644 --- a/tools/testing/selftests/rcutorture/configs/lock/ver_functions.sh +++ b/tools/testing/selftests/rcutorture/configs/lock/ver_functions.sh @@ -22,8 +22,9 @@ locktorture_param_onoff () { # # Adds per-version torture-module parameters to kernels supporting them. per_version_boot_params () { - echo $1 `locktorture_param_onoff "$1" "$2"` \ + echo `locktorture_param_onoff "$1" "$2"` \ locktorture.stat_interval=15 \ locktorture.shutdown_secs=$3 \ - locktorture.verbose=1 + locktorture.verbose=1 \ + $1 } diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS03 b/tools/testing/selftests/rcutorture/configs/rcu/TASKS03 index dea26c568678..2ef2fb69c360 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TASKS03 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS03 @@ -6,6 +6,5 @@ CONFIG_PREEMPT=y CONFIG_HZ_PERIODIC=n CONFIG_NO_HZ_IDLE=n CONFIG_NO_HZ_FULL=y -#CHECK#CONFIG_RCU_EXPERT=n CONFIG_TASKS_RCU=y CONFIG_RCU_EXPERT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE01 b/tools/testing/selftests/rcutorture/configs/rcu/TREE01 index 04831ef1f9b5..8ae41d5f81a3 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE01 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE01 @@ -15,4 +15,3 @@ CONFIG_DEBUG_LOCK_ALLOC=n CONFIG_RCU_BOOST=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y -CONFIG_BOOTPARAM_HOTPLUG_CPU0=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh index e2bc99c785e7..c044df386876 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh +++ b/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh @@ -46,10 +46,11 @@ rcutorture_param_stat_interval () { # # Adds per-version torture-module parameters to kernels supporting them. per_version_boot_params () { - echo $1 `rcutorture_param_onoff "$1" "$2"` \ + echo `rcutorture_param_onoff "$1" "$2"` \ `rcutorture_param_n_barrier_cbs "$1"` \ `rcutorture_param_stat_interval "$1"` \ rcutorture.shutdown_secs=$3 \ rcutorture.test_no_idle_hz=1 \ - rcutorture.verbose=1 + rcutorture.verbose=1 \ + $1 } diff --git a/tools/testing/selftests/rcutorture/configs/rcuscale/CFcommon b/tools/testing/selftests/rcutorture/configs/rcuscale/CFcommon index 6a00157bee5b..b1ffd7c67604 100644 --- a/tools/testing/selftests/rcutorture/configs/rcuscale/CFcommon +++ b/tools/testing/selftests/rcutorture/configs/rcuscale/CFcommon @@ -2,5 +2,7 @@ CONFIG_RCU_SCALE_TEST=y CONFIG_PRINTK_TIME=y CONFIG_FORCE_TASKS_RCU=y #CHECK#CONFIG_TASKS_RCU=y +CONFIG_FORCE_TASKS_RUDE_RCU=y +#CHECK#CONFIG_TASKS_RUDE_RCU=y CONFIG_FORCE_TASKS_TRACE_RCU=y #CHECK#CONFIG_TASKS_TRACE_RCU=y diff --git a/tools/testing/selftests/rcutorture/configs/rcuscale/TRACE01 b/tools/testing/selftests/rcutorture/configs/rcuscale/TRACE01 index 227aba7783af..0059592c7408 100644 --- a/tools/testing/selftests/rcutorture/configs/rcuscale/TRACE01 +++ b/tools/testing/selftests/rcutorture/configs/rcuscale/TRACE01 @@ -2,6 +2,8 @@ CONFIG_SMP=y CONFIG_PREEMPT_NONE=y CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n +CONFIG_PREEMPT_DYNAMIC=n +#CHECK#CONFIG_TREE_RCU=y CONFIG_HZ_PERIODIC=n CONFIG_NO_HZ_IDLE=y CONFIG_NO_HZ_FULL=n diff --git a/tools/testing/selftests/rcutorture/configs/rcuscale/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/rcuscale/ver_functions.sh index ffbe15109f0d..28070b43f017 100644 --- a/tools/testing/selftests/rcutorture/configs/rcuscale/ver_functions.sh +++ b/tools/testing/selftests/rcutorture/configs/rcuscale/ver_functions.sh @@ -11,6 +11,7 @@ # # Adds per-version torture-module parameters to kernels supporting them. per_version_boot_params () { - echo $1 rcuscale.shutdown=1 \ - rcuscale.verbose=0 + echo rcuscale.shutdown=1 \ + rcuscale.verbose=0 \ + $1 } diff --git a/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT b/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT index ef2b501a6971..67f9d2998afd 100644 --- a/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT +++ b/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT @@ -2,6 +2,7 @@ CONFIG_SMP=y CONFIG_PREEMPT_NONE=y CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n +CONFIG_PREEMPT_DYNAMIC=n #CHECK#CONFIG_PREEMPT_RCU=n CONFIG_HZ_PERIODIC=n CONFIG_NO_HZ_IDLE=y diff --git a/tools/testing/selftests/rcutorture/configs/refscale/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/refscale/ver_functions.sh index f81fa2c541a6..748465627601 100644 --- a/tools/testing/selftests/rcutorture/configs/refscale/ver_functions.sh +++ b/tools/testing/selftests/rcutorture/configs/refscale/ver_functions.sh @@ -11,6 +11,7 @@ # # Adds per-version torture-module parameters to kernels supporting them. per_version_boot_params () { - echo $1 refscale.shutdown=1 \ - refscale.verbose=0 + echo refscale.shutdown=1 \ + refscale.verbose=0 \ + $1 } diff --git a/tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT b/tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT index 3a59346b3de7..6133f54ce2a7 100644 --- a/tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT +++ b/tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT @@ -2,6 +2,8 @@ CONFIG_SMP=y CONFIG_PREEMPT_NONE=y CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n +CONFIG_PREEMPT_DYNAMIC=n +#CHECK#CONFIG_PREEMPT_RCU=n CONFIG_HZ_PERIODIC=n CONFIG_NO_HZ_IDLE=n CONFIG_NO_HZ_FULL=y diff --git a/tools/testing/selftests/rcutorture/configs/scf/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/scf/ver_functions.sh index 2d949e58f5a5..7637f68ef0ce 100644 --- a/tools/testing/selftests/rcutorture/configs/scf/ver_functions.sh +++ b/tools/testing/selftests/rcutorture/configs/scf/ver_functions.sh @@ -22,8 +22,9 @@ scftorture_param_onoff () { # # Adds per-version torture-module parameters to kernels supporting them. per_version_boot_params () { - echo $1 `scftorture_param_onoff "$1" "$2"` \ + echo `scftorture_param_onoff "$1" "$2"` \ scftorture.stat_interval=15 \ scftorture.shutdown_secs=$3 \ - scftorture.verbose=1 + scftorture.verbose=1 \ + $1 } diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/.gitignore b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/.gitignore deleted file mode 100644 index 24e27957efcc..000000000000 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/.gitignore +++ /dev/null @@ -1,2 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -srcu.c diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/Makefile b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/Makefile deleted file mode 100644 index 4bed0b678f8b..000000000000 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/Makefile +++ /dev/null @@ -1,17 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -all: srcu.c store_buffering - -LINUX_SOURCE = ../../../../../.. - -modified_srcu_input = $(LINUX_SOURCE)/include/linux/srcu.h \ - $(LINUX_SOURCE)/kernel/rcu/srcu.c - -modified_srcu_output = include/linux/srcu.h srcu.c - -include/linux/srcu.h: srcu.c - -srcu.c: modify_srcu.awk Makefile $(modified_srcu_input) - awk -f modify_srcu.awk $(modified_srcu_input) $(modified_srcu_output) - -store_buffering: - @cd tests/store_buffering; make diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/delay.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/delay.h deleted file mode 100644 index e69de29bb2d1..000000000000 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/delay.h +++ /dev/null diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/export.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/export.h deleted file mode 100644 index e69de29bb2d1..000000000000 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/export.h +++ /dev/null diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/mutex.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/mutex.h deleted file mode 100644 index e69de29bb2d1..000000000000 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/mutex.h +++ /dev/null diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/percpu.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/percpu.h deleted file mode 100644 index e69de29bb2d1..000000000000 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/percpu.h +++ /dev/null diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/preempt.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/preempt.h deleted file mode 100644 index e69de29bb2d1..000000000000 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/preempt.h +++ /dev/null diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/rcupdate.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/rcupdate.h deleted file mode 100644 index e69de29bb2d1..000000000000 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/rcupdate.h +++ /dev/null diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/sched.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/sched.h deleted file mode 100644 index e69de29bb2d1..000000000000 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/sched.h +++ /dev/null diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/smp.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/smp.h deleted file mode 100644 index e69de29bb2d1..000000000000 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/smp.h +++ /dev/null diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/workqueue.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/workqueue.h deleted file mode 100644 index e69de29bb2d1..000000000000 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/workqueue.h +++ /dev/null diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/uapi/linux/types.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/uapi/linux/types.h deleted file mode 100644 index e69de29bb2d1..000000000000 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/uapi/linux/types.h +++ /dev/null diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/.gitignore b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/.gitignore deleted file mode 100644 index 57d296341304..000000000000 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/.gitignore +++ /dev/null @@ -1,2 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -srcu.h diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/kconfig.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/kconfig.h deleted file mode 100644 index f2860dd1b407..000000000000 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/kconfig.h +++ /dev/null @@ -1 +0,0 @@ -#include <LINUX_SOURCE/linux/kconfig.h> diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/types.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/types.h deleted file mode 100644 index 8bc960e5e713..000000000000 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/types.h +++ /dev/null @@ -1,152 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * This header has been modifies to remove definitions of types that - * are defined in standard userspace headers or are problematic for some - * other reason. - */ - -#ifndef _LINUX_TYPES_H -#define _LINUX_TYPES_H - -#define __EXPORTED_HEADERS__ -#include <uapi/linux/types.h> - -#ifndef __ASSEMBLY__ - -#define DECLARE_BITMAP(name, bits) \ - unsigned long name[BITS_TO_LONGS(bits)] - -typedef __u32 __kernel_dev_t; - -/* bsd */ -typedef unsigned char u_char; -typedef unsigned short u_short; -typedef unsigned int u_int; -typedef unsigned long u_long; - -/* sysv */ -typedef unsigned char unchar; -typedef unsigned short ushort; -typedef unsigned int uint; -typedef unsigned long ulong; - -#ifndef __BIT_TYPES_DEFINED__ -#define __BIT_TYPES_DEFINED__ - -typedef __u8 u_int8_t; -typedef __s8 int8_t; -typedef __u16 u_int16_t; -typedef __s16 int16_t; -typedef __u32 u_int32_t; -typedef __s32 int32_t; - -#endif /* !(__BIT_TYPES_DEFINED__) */ - -typedef __u8 uint8_t; -typedef __u16 uint16_t; -typedef __u32 uint32_t; - -/* this is a special 64bit data type that is 8-byte aligned */ -#define aligned_u64 __u64 __attribute__((aligned(8))) -#define aligned_be64 __be64 __attribute__((aligned(8))) -#define aligned_le64 __le64 __attribute__((aligned(8))) - -/** - * The type used for indexing onto a disc or disc partition. - * - * Linux always considers sectors to be 512 bytes long independently - * of the devices real block size. - * - * blkcnt_t is the type of the inode's block count. - */ -typedef u64 sector_t; - -/* - * The type of an index into the pagecache. - */ -#define pgoff_t unsigned long - -/* - * A dma_addr_t can hold any valid DMA address, i.e., any address returned - * by the DMA API. - * - * If the DMA API only uses 32-bit addresses, dma_addr_t need only be 32 - * bits wide. Bus addresses, e.g., PCI BARs, may be wider than 32 bits, - * but drivers do memory-mapped I/O to ioremapped kernel virtual addresses, - * so they don't care about the size of the actual bus addresses. - */ -#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT -typedef u64 dma_addr_t; -#else -typedef u32 dma_addr_t; -#endif - -#ifdef CONFIG_PHYS_ADDR_T_64BIT -typedef u64 phys_addr_t; -#else -typedef u32 phys_addr_t; -#endif - -typedef phys_addr_t resource_size_t; - -/* - * This type is the placeholder for a hardware interrupt number. It has to be - * big enough to enclose whatever representation is used by a given platform. - */ -typedef unsigned long irq_hw_number_t; - -typedef struct { - int counter; -} atomic_t; - -#ifdef CONFIG_64BIT -typedef struct { - long counter; -} atomic64_t; -#endif - -struct list_head { - struct list_head *next, *prev; -}; - -struct hlist_head { - struct hlist_node *first; -}; - -struct hlist_node { - struct hlist_node *next, **pprev; -}; - -/** - * struct callback_head - callback structure for use with RCU and task_work - * @next: next update requests in a list - * @func: actual update function to call after the grace period. - * - * The struct is aligned to size of pointer. On most architectures it happens - * naturally due ABI requirements, but some architectures (like CRIS) have - * weird ABI and we need to ask it explicitly. - * - * The alignment is required to guarantee that bits 0 and 1 of @next will be - * clear under normal conditions -- as long as we use call_rcu() or - * call_srcu() to queue callback. - * - * This guarantee is important for few reasons: - * - future call_rcu_lazy() will make use of lower bits in the pointer; - * - the structure shares storage spacer in struct page with @compound_head, - * which encode PageTail() in bit 0. The guarantee is needed to avoid - * false-positive PageTail(). - */ -struct callback_head { - struct callback_head *next; - void (*func)(struct callback_head *head); -} __attribute__((aligned(sizeof(void *)))); -#define rcu_head callback_head - -typedef void (*rcu_callback_t)(struct rcu_head *head); -typedef void (*call_rcu_func_t)(struct rcu_head *head, rcu_callback_t func); - -/* clocksource cycle base type */ -typedef u64 cycle_t; - -#endif /* __ASSEMBLY__ */ -#endif /* _LINUX_TYPES_H */ diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/modify_srcu.awk b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/modify_srcu.awk deleted file mode 100755 index e05182d3e47d..000000000000 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/modify_srcu.awk +++ /dev/null @@ -1,376 +0,0 @@ -#!/usr/bin/awk -f -# SPDX-License-Identifier: GPL-2.0 - -# Modify SRCU for formal verification. The first argument should be srcu.h and -# the second should be srcu.c. Outputs modified srcu.h and srcu.c into the -# current directory. - -BEGIN { - if (ARGC != 5) { - print "Usange: input.h input.c output.h output.c" > "/dev/stderr"; - exit 1; - } - h_output = ARGV[3]; - c_output = ARGV[4]; - ARGC = 3; - - # Tokenize using FS and not RS as FS supports regular expressions. Each - # record is one line of source, except that backslashed lines are - # combined. Comments are treated as field separators, as are quotes. - quote_regexp="\"([^\\\\\"]|\\\\.)*\""; - comment_regexp="\\/\\*([^*]|\\*+[^*/])*\\*\\/|\\/\\/.*(\n|$)"; - FS="([ \\\\\t\n\v\f;,.=(){}+*/<>&|^-]|\\[|\\]|" comment_regexp "|" quote_regexp ")+"; - - inside_srcu_struct = 0; - inside_srcu_init_def = 0; - srcu_init_param_name = ""; - in_macro = 0; - brace_nesting = 0; - paren_nesting = 0; - - # Allow the manipulation of the last field separator after has been - # seen. - last_fs = ""; - # Whether the last field separator was intended to be output. - last_fs_print = 0; - - # rcu_batches stores the initialization for each instance of struct - # rcu_batch - - in_comment = 0; - - outputfile = ""; -} - -{ - prev_outputfile = outputfile; - if (FILENAME ~ /\.h$/) { - outputfile = h_output; - if (FNR != NR) { - print "Incorrect file order" > "/dev/stderr"; - exit 1; - } - } - else - outputfile = c_output; - - if (prev_outputfile && outputfile != prev_outputfile) { - new_outputfile = outputfile; - outputfile = prev_outputfile; - update_fieldsep("", 0); - outputfile = new_outputfile; - } -} - -# Combine the next line into $0. -function combine_line() { - ret = getline next_line; - if (ret == 0) { - # Don't allow two consecutive getlines at the end of the file - if (eof_found) { - print "Error: expected more input." > "/dev/stderr"; - exit 1; - } else { - eof_found = 1; - } - } else if (ret == -1) { - print "Error reading next line of file" FILENAME > "/dev/stderr"; - exit 1; - } - $0 = $0 "\n" next_line; -} - -# Combine backslashed lines and multiline comments. -function combine_backslashes() { - while (/\\$|\/\*([^*]|\*+[^*\/])*\**$/) { - combine_line(); - } -} - -function read_line() { - combine_line(); - combine_backslashes(); -} - -# Print out field separators and update variables that depend on them. Only -# print if p is true. Call with sep="" and p=0 to print out the last field -# separator. -function update_fieldsep(sep, p) { - # Count braces - sep_tmp = sep; - gsub(quote_regexp "|" comment_regexp, "", sep_tmp); - while (1) - { - if (sub("[^{}()]*\\{", "", sep_tmp)) { - brace_nesting++; - continue; - } - if (sub("[^{}()]*\\}", "", sep_tmp)) { - brace_nesting--; - if (brace_nesting < 0) { - print "Unbalanced braces!" > "/dev/stderr"; - exit 1; - } - continue; - } - if (sub("[^{}()]*\\(", "", sep_tmp)) { - paren_nesting++; - continue; - } - if (sub("[^{}()]*\\)", "", sep_tmp)) { - paren_nesting--; - if (paren_nesting < 0) { - print "Unbalanced parenthesis!" > "/dev/stderr"; - exit 1; - } - continue; - } - - break; - } - - if (last_fs_print) - printf("%s", last_fs) > outputfile; - last_fs = sep; - last_fs_print = p; -} - -# Shifts the fields down by n positions. Calls next if there are no more. If p -# is true then print out field separators. -function shift_fields(n, p) { - do { - if (match($0, FS) > 0) { - update_fieldsep(substr($0, RSTART, RLENGTH), p); - if (RSTART + RLENGTH <= length()) - $0 = substr($0, RSTART + RLENGTH); - else - $0 = ""; - } else { - update_fieldsep("", 0); - print "" > outputfile; - next; - } - } while (--n > 0); -} - -# Shifts and prints the first n fields. -function print_fields(n) { - do { - update_fieldsep("", 0); - printf("%s", $1) > outputfile; - shift_fields(1, 1); - } while (--n > 0); -} - -{ - combine_backslashes(); -} - -# Print leading FS -{ - if (match($0, "^(" FS ")+") > 0) { - update_fieldsep(substr($0, RSTART, RLENGTH), 1); - if (RSTART + RLENGTH <= length()) - $0 = substr($0, RSTART + RLENGTH); - else - $0 = ""; - } -} - -# Parse the line. -{ - while (NF > 0) { - if ($1 == "struct" && NF < 3) { - read_line(); - continue; - } - - if (FILENAME ~ /\.h$/ && !inside_srcu_struct && - brace_nesting == 0 && paren_nesting == 0 && - $1 == "struct" && $2 == "srcu_struct" && - $0 ~ "^struct(" FS ")+srcu_struct(" FS ")+\\{") { - inside_srcu_struct = 1; - print_fields(2); - continue; - } - if (inside_srcu_struct && brace_nesting == 0 && - paren_nesting == 0) { - inside_srcu_struct = 0; - update_fieldsep("", 0); - for (name in rcu_batches) - print "extern struct rcu_batch " name ";" > outputfile; - } - - if (inside_srcu_struct && $1 == "struct" && $2 == "rcu_batch") { - # Move rcu_batches outside of the struct. - rcu_batches[$3] = ""; - shift_fields(3, 1); - sub(/;[[:space:]]*$/, "", last_fs); - continue; - } - - if (FILENAME ~ /\.h$/ && !inside_srcu_init_def && - $1 == "#define" && $2 == "__SRCU_STRUCT_INIT") { - inside_srcu_init_def = 1; - srcu_init_param_name = $3; - in_macro = 1; - print_fields(3); - continue; - } - if (inside_srcu_init_def && brace_nesting == 0 && - paren_nesting == 0) { - inside_srcu_init_def = 0; - in_macro = 0; - continue; - } - - if (inside_srcu_init_def && brace_nesting == 1 && - paren_nesting == 0 && last_fs ~ /\.[[:space:]]*$/ && - $1 ~ /^[[:alnum:]_]+$/) { - name = $1; - if (name in rcu_batches) { - # Remove the dot. - sub(/\.[[:space:]]*$/, "", last_fs); - - old_record = $0; - do - shift_fields(1, 0); - while (last_fs !~ /,/ || paren_nesting > 0); - end_loc = length(old_record) - length($0); - end_loc += index(last_fs, ",") - length(last_fs); - - last_fs = substr(last_fs, index(last_fs, ",") + 1); - last_fs_print = 1; - - match(old_record, "^"name"("FS")+="); - start_loc = RSTART + RLENGTH; - - len = end_loc - start_loc; - initializer = substr(old_record, start_loc, len); - gsub(srcu_init_param_name "\\.", "", initializer); - rcu_batches[name] = initializer; - continue; - } - } - - # Don't include a nonexistent file - if (!in_macro && $1 == "#include" && /^#include[[:space:]]+"rcu\.h"/) { - update_fieldsep("", 0); - next; - } - - # Ignore most preprocessor stuff. - if (!in_macro && $1 ~ /#/) { - break; - } - - if (brace_nesting > 0 && $1 ~ "^[[:alnum:]_]+$" && NF < 2) { - read_line(); - continue; - } - if (brace_nesting > 0 && - $0 ~ "^[[:alnum:]_]+[[:space:]]*(\\.|->)[[:space:]]*[[:alnum:]_]+" && - $2 in rcu_batches) { - # Make uses of rcu_batches global. Somewhat unreliable. - shift_fields(1, 0); - print_fields(1); - continue; - } - - if ($1 == "static" && NF < 3) { - read_line(); - continue; - } - if ($1 == "static" && ($2 == "bool" && $3 == "try_check_zero" || - $2 == "void" && $3 == "srcu_flip")) { - shift_fields(1, 1); - print_fields(2); - continue; - } - - # Distinguish between read-side and write-side memory barriers. - if ($1 == "smp_mb" && NF < 2) { - read_line(); - continue; - } - if (match($0, /^smp_mb[[:space:]();\/*]*[[:alnum:]]/)) { - barrier_letter = substr($0, RLENGTH, 1); - if (barrier_letter ~ /A|D/) - new_barrier_name = "sync_smp_mb"; - else if (barrier_letter ~ /B|C/) - new_barrier_name = "rs_smp_mb"; - else { - print "Unrecognized memory barrier." > "/dev/null"; - exit 1; - } - - shift_fields(1, 1); - printf("%s", new_barrier_name) > outputfile; - continue; - } - - # Skip definition of rcu_synchronize, since it is already - # defined in misc.h. Only present in old versions of srcu. - if (brace_nesting == 0 && paren_nesting == 0 && - $1 == "struct" && $2 == "rcu_synchronize" && - $0 ~ "^struct(" FS ")+rcu_synchronize(" FS ")+\\{") { - shift_fields(2, 0); - while (brace_nesting) { - if (NF < 2) - read_line(); - shift_fields(1, 0); - } - } - - # Skip definition of wakeme_after_rcu for the same reason - if (brace_nesting == 0 && $1 == "static" && $2 == "void" && - $3 == "wakeme_after_rcu") { - while (NF < 5) - read_line(); - shift_fields(3, 0); - do { - while (NF < 3) - read_line(); - shift_fields(1, 0); - } while (paren_nesting || brace_nesting); - } - - if ($1 ~ /^(unsigned|long)$/ && NF < 3) { - read_line(); - continue; - } - - # Give srcu_batches_completed the correct type for old SRCU. - if (brace_nesting == 0 && $1 == "long" && - $2 == "srcu_batches_completed") { - update_fieldsep("", 0); - printf("unsigned ") > outputfile; - print_fields(2); - continue; - } - if (brace_nesting == 0 && $1 == "unsigned" && $2 == "long" && - $3 == "srcu_batches_completed") { - print_fields(3); - continue; - } - - # Just print out the input code by default. - print_fields(1); - } - update_fieldsep("", 0); - print > outputfile; - next; -} - -END { - update_fieldsep("", 0); - - if (brace_nesting != 0) { - print "Unbalanced braces!" > "/dev/stderr"; - exit 1; - } - - # Define the rcu_batches - for (name in rcu_batches) - print "struct rcu_batch " name " = " rcu_batches[name] ";" > c_output; -} diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/assume.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/assume.h deleted file mode 100644 index 570a49d9da7e..000000000000 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/assume.h +++ /dev/null @@ -1,17 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef ASSUME_H -#define ASSUME_H - -/* Provide an assumption macro that can be disabled for gcc. */ -#ifdef RUN -#define assume(x) \ - do { \ - /* Evaluate x to suppress warnings. */ \ - (void) (x); \ - } while (0) - -#else -#define assume(x) __CPROVER_assume(x) -#endif - -#endif diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/barriers.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/barriers.h deleted file mode 100644 index 3f95a768a03b..000000000000 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/barriers.h +++ /dev/null @@ -1,41 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef BARRIERS_H -#define BARRIERS_H - -#define barrier() __asm__ __volatile__("" : : : "memory") - -#ifdef RUN -#define smp_mb() __sync_synchronize() -#define smp_mb__after_unlock_lock() __sync_synchronize() -#else -/* - * Copied from CBMC's implementation of __sync_synchronize(), which - * seems to be disabled by default. - */ -#define smp_mb() __CPROVER_fence("WWfence", "RRfence", "RWfence", "WRfence", \ - "WWcumul", "RRcumul", "RWcumul", "WRcumul") -#define smp_mb__after_unlock_lock() __CPROVER_fence("WWfence", "RRfence", "RWfence", "WRfence", \ - "WWcumul", "RRcumul", "RWcumul", "WRcumul") -#endif - -/* - * Allow memory barriers to be disabled in either the read or write side - * of SRCU individually. - */ - -#ifndef NO_SYNC_SMP_MB -#define sync_smp_mb() smp_mb() -#else -#define sync_smp_mb() do {} while (0) -#endif - -#ifndef NO_READ_SIDE_SMP_MB -#define rs_smp_mb() smp_mb() -#else -#define rs_smp_mb() do {} while (0) -#endif - -#define READ_ONCE(x) (*(volatile typeof(x) *) &(x)) -#define WRITE_ONCE(x) ((*(volatile typeof(x) *) &(x)) = (val)) - -#endif diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/bug_on.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/bug_on.h deleted file mode 100644 index 5e7912c6a521..000000000000 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/bug_on.h +++ /dev/null @@ -1,14 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef BUG_ON_H -#define BUG_ON_H - -#include <assert.h> - -#define BUG() assert(0) -#define BUG_ON(x) assert(!(x)) - -/* Does it make sense to treat warnings as errors? */ -#define WARN() BUG() -#define WARN_ON(x) (BUG_ON(x), false) - -#endif diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/combined_source.c b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/combined_source.c deleted file mode 100644 index e67ee5b3dd7c..000000000000 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/combined_source.c +++ /dev/null @@ -1,14 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <config.h> - -/* Include all source files. */ - -#include "include_srcu.c" - -#include "preempt.c" -#include "misc.c" - -/* Used by test.c files */ -#include <pthread.h> -#include <stdlib.h> -#include <linux/srcu.h> diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/config.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/config.h deleted file mode 100644 index 283d7103334f..000000000000 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/config.h +++ /dev/null @@ -1,28 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* "Cheater" definitions based on restricted Kconfig choices. */ - -#undef CONFIG_TINY_RCU -#undef __CHECKER__ -#undef CONFIG_DEBUG_LOCK_ALLOC -#undef CONFIG_DEBUG_OBJECTS_RCU_HEAD -#undef CONFIG_HOTPLUG_CPU -#undef CONFIG_MODULES -#undef CONFIG_NO_HZ_FULL_SYSIDLE -#undef CONFIG_PREEMPT_COUNT -#undef CONFIG_PREEMPT_RCU -#undef CONFIG_PROVE_RCU -#undef CONFIG_RCU_NOCB_CPU -#undef CONFIG_RCU_NOCB_CPU_ALL -#undef CONFIG_RCU_STALL_COMMON -#undef CONFIG_RCU_TRACE -#undef CONFIG_RCU_USER_QS -#undef CONFIG_TASKS_RCU -#define CONFIG_TREE_RCU - -#define CONFIG_GENERIC_ATOMIC64 - -#if NR_CPUS > 1 -#define CONFIG_SMP -#else -#undef CONFIG_SMP -#endif diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/include_srcu.c b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/include_srcu.c deleted file mode 100644 index e5202d4cff30..000000000000 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/include_srcu.c +++ /dev/null @@ -1,32 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <config.h> - -#include <assert.h> -#include <errno.h> -#include <inttypes.h> -#include <pthread.h> -#include <stddef.h> -#include <string.h> -#include <sys/types.h> - -#include "int_typedefs.h" - -#include "barriers.h" -#include "bug_on.h" -#include "locks.h" -#include "misc.h" -#include "preempt.h" -#include "percpu.h" -#include "workqueues.h" - -#ifdef USE_SIMPLE_SYNC_SRCU -#define synchronize_srcu(sp) synchronize_srcu_original(sp) -#endif - -#include <srcu.c> - -#ifdef USE_SIMPLE_SYNC_SRCU -#undef synchronize_srcu - -#include "simple_sync_srcu.c" -#endif diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/int_typedefs.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/int_typedefs.h deleted file mode 100644 index 0dd27aa517a7..000000000000 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/int_typedefs.h +++ /dev/null @@ -1,34 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef INT_TYPEDEFS_H -#define INT_TYPEDEFS_H - -#include <inttypes.h> - -typedef int8_t s8; -typedef uint8_t u8; -typedef int16_t s16; -typedef uint16_t u16; -typedef int32_t s32; -typedef uint32_t u32; -typedef int64_t s64; -typedef uint64_t u64; - -typedef int8_t __s8; -typedef uint8_t __u8; -typedef int16_t __s16; -typedef uint16_t __u16; -typedef int32_t __s32; -typedef uint32_t __u32; -typedef int64_t __s64; -typedef uint64_t __u64; - -#define S8_C(x) INT8_C(x) -#define U8_C(x) UINT8_C(x) -#define S16_C(x) INT16_C(x) -#define U16_C(x) UINT16_C(x) -#define S32_C(x) INT32_C(x) -#define U32_C(x) UINT32_C(x) -#define S64_C(x) INT64_C(x) -#define U64_C(x) UINT64_C(x) - -#endif diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/locks.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/locks.h deleted file mode 100644 index 1e24827f96f1..000000000000 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/locks.h +++ /dev/null @@ -1,221 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef LOCKS_H -#define LOCKS_H - -#include <limits.h> -#include <pthread.h> -#include <stdbool.h> - -#include "assume.h" -#include "bug_on.h" -#include "preempt.h" - -int nondet_int(void); - -#define __acquire(x) -#define __acquires(x) -#define __release(x) -#define __releases(x) - -/* Only use one lock mechanism. Select which one. */ -#ifdef PTHREAD_LOCK -struct lock_impl { - pthread_mutex_t mutex; -}; - -static inline void lock_impl_lock(struct lock_impl *lock) -{ - BUG_ON(pthread_mutex_lock(&lock->mutex)); -} - -static inline void lock_impl_unlock(struct lock_impl *lock) -{ - BUG_ON(pthread_mutex_unlock(&lock->mutex)); -} - -static inline bool lock_impl_trylock(struct lock_impl *lock) -{ - int err = pthread_mutex_trylock(&lock->mutex); - - if (!err) - return true; - else if (err == EBUSY) - return false; - BUG(); -} - -static inline void lock_impl_init(struct lock_impl *lock) -{ - pthread_mutex_init(&lock->mutex, NULL); -} - -#define LOCK_IMPL_INITIALIZER {.mutex = PTHREAD_MUTEX_INITIALIZER} - -#else /* !defined(PTHREAD_LOCK) */ -/* Spinlock that assumes that it always gets the lock immediately. */ - -struct lock_impl { - bool locked; -}; - -static inline bool lock_impl_trylock(struct lock_impl *lock) -{ -#ifdef RUN - /* TODO: Should this be a test and set? */ - return __sync_bool_compare_and_swap(&lock->locked, false, true); -#else - __CPROVER_atomic_begin(); - bool old_locked = lock->locked; - lock->locked = true; - __CPROVER_atomic_end(); - - /* Minimal barrier to prevent accesses leaking out of lock. */ - __CPROVER_fence("RRfence", "RWfence"); - - return !old_locked; -#endif -} - -static inline void lock_impl_lock(struct lock_impl *lock) -{ - /* - * CBMC doesn't support busy waiting, so just assume that the - * lock is available. - */ - assume(lock_impl_trylock(lock)); - - /* - * If the lock was already held by this thread then the assumption - * is unsatisfiable (deadlock). - */ -} - -static inline void lock_impl_unlock(struct lock_impl *lock) -{ -#ifdef RUN - BUG_ON(!__sync_bool_compare_and_swap(&lock->locked, true, false)); -#else - /* Minimal barrier to prevent accesses leaking out of lock. */ - __CPROVER_fence("RWfence", "WWfence"); - - __CPROVER_atomic_begin(); - bool old_locked = lock->locked; - lock->locked = false; - __CPROVER_atomic_end(); - - BUG_ON(!old_locked); -#endif -} - -static inline void lock_impl_init(struct lock_impl *lock) -{ - lock->locked = false; -} - -#define LOCK_IMPL_INITIALIZER {.locked = false} - -#endif /* !defined(PTHREAD_LOCK) */ - -/* - * Implement spinlocks using the lock mechanism. Wrap the lock to prevent mixing - * locks of different types. - */ -typedef struct { - struct lock_impl internal_lock; -} spinlock_t; - -#define SPIN_LOCK_UNLOCKED {.internal_lock = LOCK_IMPL_INITIALIZER} -#define __SPIN_LOCK_UNLOCKED(x) SPIN_LOCK_UNLOCKED -#define DEFINE_SPINLOCK(x) spinlock_t x = SPIN_LOCK_UNLOCKED - -static inline void spin_lock_init(spinlock_t *lock) -{ - lock_impl_init(&lock->internal_lock); -} - -static inline void spin_lock(spinlock_t *lock) -{ - /* - * Spin locks also need to be removed in order to eliminate all - * memory barriers. They are only used by the write side anyway. - */ -#ifndef NO_SYNC_SMP_MB - preempt_disable(); - lock_impl_lock(&lock->internal_lock); -#endif -} - -static inline void spin_unlock(spinlock_t *lock) -{ -#ifndef NO_SYNC_SMP_MB - lock_impl_unlock(&lock->internal_lock); - preempt_enable(); -#endif -} - -/* Don't bother with interrupts */ -#define spin_lock_irq(lock) spin_lock(lock) -#define spin_unlock_irq(lock) spin_unlock(lock) -#define spin_lock_irqsave(lock, flags) spin_lock(lock) -#define spin_unlock_irqrestore(lock, flags) spin_unlock(lock) - -/* - * This is supposed to return an int, but I think that a bool should work as - * well. - */ -static inline bool spin_trylock(spinlock_t *lock) -{ -#ifndef NO_SYNC_SMP_MB - preempt_disable(); - return lock_impl_trylock(&lock->internal_lock); -#else - return true; -#endif -} - -struct completion { - /* Hopefully this won't overflow. */ - unsigned int count; -}; - -#define COMPLETION_INITIALIZER(x) {.count = 0} -#define DECLARE_COMPLETION(x) struct completion x = COMPLETION_INITIALIZER(x) -#define DECLARE_COMPLETION_ONSTACK(x) DECLARE_COMPLETION(x) - -static inline void init_completion(struct completion *c) -{ - c->count = 0; -} - -static inline void wait_for_completion(struct completion *c) -{ - unsigned int prev_count = __sync_fetch_and_sub(&c->count, 1); - - assume(prev_count); -} - -static inline void complete(struct completion *c) -{ - unsigned int prev_count = __sync_fetch_and_add(&c->count, 1); - - BUG_ON(prev_count == UINT_MAX); -} - -/* This function probably isn't very useful for CBMC. */ -static inline bool try_wait_for_completion(struct completion *c) -{ - BUG(); -} - -static inline bool completion_done(struct completion *c) -{ - return c->count; -} - -/* TODO: Implement complete_all */ -static inline void complete_all(struct completion *c) -{ - BUG(); -} - -#endif diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/misc.c b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/misc.c deleted file mode 100644 index 9440cc39e3c6..000000000000 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/misc.c +++ /dev/null @@ -1,12 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <config.h> - -#include "misc.h" -#include "bug_on.h" - -struct rcu_head; - -void wakeme_after_rcu(struct rcu_head *head) -{ - BUG(); -} diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/misc.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/misc.h deleted file mode 100644 index aca50030f954..000000000000 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/misc.h +++ /dev/null @@ -1,58 +0,0 @@ -#ifndef MISC_H -#define MISC_H - -#include "assume.h" -#include "int_typedefs.h" -#include "locks.h" - -#include <linux/types.h> - -/* Probably won't need to deal with bottom halves. */ -static inline void local_bh_disable(void) {} -static inline void local_bh_enable(void) {} - -#define MODULE_ALIAS(X) -#define module_param(...) -#define EXPORT_SYMBOL_GPL(x) - -#define container_of(ptr, type, member) ({ \ - const typeof(((type *)0)->member) *__mptr = (ptr); \ - (type *)((char *)__mptr - offsetof(type, member)); \ -}) - -#ifndef USE_SIMPLE_SYNC_SRCU -/* Abuse udelay to make sure that busy loops terminate. */ -#define udelay(x) assume(0) - -#else - -/* The simple custom synchronize_srcu is ok with try_check_zero failing. */ -#define udelay(x) do { } while (0) -#endif - -#define trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c) \ - do { } while (0) - -#define notrace - -/* Avoid including rcupdate.h */ -struct rcu_synchronize { - struct rcu_head head; - struct completion completion; -}; - -void wakeme_after_rcu(struct rcu_head *head); - -#define rcu_lock_acquire(a) do { } while (0) -#define rcu_lock_release(a) do { } while (0) -#define rcu_lockdep_assert(c, s) do { } while (0) -#define RCU_LOCKDEP_WARN(c, s) do { } while (0) - -/* Let CBMC non-deterministically choose switch between normal and expedited. */ -bool rcu_gp_is_normal(void); -bool rcu_gp_is_expedited(void); - -/* Do the same for old versions of rcu. */ -#define rcu_expedited (rcu_gp_is_expedited()) - -#endif diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/percpu.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/percpu.h deleted file mode 100644 index 27e67a3f291f..000000000000 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/percpu.h +++ /dev/null @@ -1,93 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef PERCPU_H -#define PERCPU_H - -#include <stddef.h> -#include "bug_on.h" -#include "preempt.h" - -#define __percpu - -/* Maximum size of any percpu data. */ -#define PERCPU_OFFSET (4 * sizeof(long)) - -/* Ignore alignment, as CBMC doesn't care about false sharing. */ -#define alloc_percpu(type) __alloc_percpu(sizeof(type), 1) - -static inline void *__alloc_percpu(size_t size, size_t align) -{ - BUG(); - return NULL; -} - -static inline void free_percpu(void *ptr) -{ - BUG(); -} - -#define per_cpu_ptr(ptr, cpu) \ - ((typeof(ptr)) ((char *) (ptr) + PERCPU_OFFSET * cpu)) - -#define __this_cpu_inc(pcp) __this_cpu_add(pcp, 1) -#define __this_cpu_dec(pcp) __this_cpu_sub(pcp, 1) -#define __this_cpu_sub(pcp, n) __this_cpu_add(pcp, -(typeof(pcp)) (n)) - -#define this_cpu_inc(pcp) this_cpu_add(pcp, 1) -#define this_cpu_dec(pcp) this_cpu_sub(pcp, 1) -#define this_cpu_sub(pcp, n) this_cpu_add(pcp, -(typeof(pcp)) (n)) - -/* Make CBMC use atomics to work around bug. */ -#ifdef RUN -#define THIS_CPU_ADD_HELPER(ptr, x) (*(ptr) += (x)) -#else -/* - * Split the atomic into a read and a write so that it has the least - * possible ordering. - */ -#define THIS_CPU_ADD_HELPER(ptr, x) \ - do { \ - typeof(ptr) this_cpu_add_helper_ptr = (ptr); \ - typeof(ptr) this_cpu_add_helper_x = (x); \ - typeof(*ptr) this_cpu_add_helper_temp; \ - __CPROVER_atomic_begin(); \ - this_cpu_add_helper_temp = *(this_cpu_add_helper_ptr); \ - __CPROVER_atomic_end(); \ - this_cpu_add_helper_temp += this_cpu_add_helper_x; \ - __CPROVER_atomic_begin(); \ - *(this_cpu_add_helper_ptr) = this_cpu_add_helper_temp; \ - __CPROVER_atomic_end(); \ - } while (0) -#endif - -/* - * For some reason CBMC needs an atomic operation even though this is percpu - * data. - */ -#define __this_cpu_add(pcp, n) \ - do { \ - BUG_ON(preemptible()); \ - THIS_CPU_ADD_HELPER(per_cpu_ptr(&(pcp), thread_cpu_id), \ - (typeof(pcp)) (n)); \ - } while (0) - -#define this_cpu_add(pcp, n) \ - do { \ - int this_cpu_add_impl_cpu = get_cpu(); \ - THIS_CPU_ADD_HELPER(per_cpu_ptr(&(pcp), this_cpu_add_impl_cpu), \ - (typeof(pcp)) (n)); \ - put_cpu(); \ - } while (0) - -/* - * This will cause a compiler warning because of the cast from char[][] to - * type*. This will cause a compile time error if type is too big. - */ -#define DEFINE_PER_CPU(type, name) \ - char name[NR_CPUS][PERCPU_OFFSET]; \ - typedef char percpu_too_big_##name \ - [sizeof(type) > PERCPU_OFFSET ? -1 : 1] - -#define for_each_possible_cpu(cpu) \ - for ((cpu) = 0; (cpu) < NR_CPUS; ++(cpu)) - -#endif diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/preempt.c b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/preempt.c deleted file mode 100644 index b4083ae348fb..000000000000 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/preempt.c +++ /dev/null @@ -1,79 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <config.h> - -#include "preempt.h" - -#include "assume.h" -#include "locks.h" - -/* Support NR_CPUS of at most 64 */ -#define CPU_PREEMPTION_LOCKS_INIT0 LOCK_IMPL_INITIALIZER -#define CPU_PREEMPTION_LOCKS_INIT1 \ - CPU_PREEMPTION_LOCKS_INIT0, CPU_PREEMPTION_LOCKS_INIT0 -#define CPU_PREEMPTION_LOCKS_INIT2 \ - CPU_PREEMPTION_LOCKS_INIT1, CPU_PREEMPTION_LOCKS_INIT1 -#define CPU_PREEMPTION_LOCKS_INIT3 \ - CPU_PREEMPTION_LOCKS_INIT2, CPU_PREEMPTION_LOCKS_INIT2 -#define CPU_PREEMPTION_LOCKS_INIT4 \ - CPU_PREEMPTION_LOCKS_INIT3, CPU_PREEMPTION_LOCKS_INIT3 -#define CPU_PREEMPTION_LOCKS_INIT5 \ - CPU_PREEMPTION_LOCKS_INIT4, CPU_PREEMPTION_LOCKS_INIT4 - -/* - * Simulate disabling preemption by locking a particular cpu. NR_CPUS - * should be the actual number of cpus, not just the maximum. - */ -struct lock_impl cpu_preemption_locks[NR_CPUS] = { - CPU_PREEMPTION_LOCKS_INIT0 -#if (NR_CPUS - 1) & 1 - , CPU_PREEMPTION_LOCKS_INIT0 -#endif -#if (NR_CPUS - 1) & 2 - , CPU_PREEMPTION_LOCKS_INIT1 -#endif -#if (NR_CPUS - 1) & 4 - , CPU_PREEMPTION_LOCKS_INIT2 -#endif -#if (NR_CPUS - 1) & 8 - , CPU_PREEMPTION_LOCKS_INIT3 -#endif -#if (NR_CPUS - 1) & 16 - , CPU_PREEMPTION_LOCKS_INIT4 -#endif -#if (NR_CPUS - 1) & 32 - , CPU_PREEMPTION_LOCKS_INIT5 -#endif -}; - -#undef CPU_PREEMPTION_LOCKS_INIT0 -#undef CPU_PREEMPTION_LOCKS_INIT1 -#undef CPU_PREEMPTION_LOCKS_INIT2 -#undef CPU_PREEMPTION_LOCKS_INIT3 -#undef CPU_PREEMPTION_LOCKS_INIT4 -#undef CPU_PREEMPTION_LOCKS_INIT5 - -__thread int thread_cpu_id; -__thread int preempt_disable_count; - -void preempt_disable(void) -{ - BUG_ON(preempt_disable_count < 0 || preempt_disable_count == INT_MAX); - - if (preempt_disable_count++) - return; - - thread_cpu_id = nondet_int(); - assume(thread_cpu_id >= 0); - assume(thread_cpu_id < NR_CPUS); - lock_impl_lock(&cpu_preemption_locks[thread_cpu_id]); -} - -void preempt_enable(void) -{ - BUG_ON(preempt_disable_count < 1); - - if (--preempt_disable_count) - return; - - lock_impl_unlock(&cpu_preemption_locks[thread_cpu_id]); -} diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/preempt.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/preempt.h deleted file mode 100644 index f8b762cd214c..000000000000 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/preempt.h +++ /dev/null @@ -1,59 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef PREEMPT_H -#define PREEMPT_H - -#include <stdbool.h> - -#include "bug_on.h" - -/* This flag contains garbage if preempt_disable_count is 0. */ -extern __thread int thread_cpu_id; - -/* Support recursive preemption disabling. */ -extern __thread int preempt_disable_count; - -void preempt_disable(void); -void preempt_enable(void); - -static inline void preempt_disable_notrace(void) -{ - preempt_disable(); -} - -static inline void preempt_enable_no_resched(void) -{ - preempt_enable(); -} - -static inline void preempt_enable_notrace(void) -{ - preempt_enable(); -} - -static inline int preempt_count(void) -{ - return preempt_disable_count; -} - -static inline bool preemptible(void) -{ - return !preempt_count(); -} - -static inline int get_cpu(void) -{ - preempt_disable(); - return thread_cpu_id; -} - -static inline void put_cpu(void) -{ - preempt_enable(); -} - -static inline void might_sleep(void) -{ - BUG_ON(preempt_disable_count); -} - -#endif diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/simple_sync_srcu.c b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/simple_sync_srcu.c deleted file mode 100644 index 97f592048e0b..000000000000 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/simple_sync_srcu.c +++ /dev/null @@ -1,51 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <config.h> - -#include <assert.h> -#include <errno.h> -#include <inttypes.h> -#include <pthread.h> -#include <stddef.h> -#include <string.h> -#include <sys/types.h> - -#include "int_typedefs.h" - -#include "barriers.h" -#include "bug_on.h" -#include "locks.h" -#include "misc.h" -#include "preempt.h" -#include "percpu.h" -#include "workqueues.h" - -#include <linux/srcu.h> - -/* Functions needed from modify_srcu.c */ -bool try_check_zero(struct srcu_struct *sp, int idx, int trycount); -void srcu_flip(struct srcu_struct *sp); - -/* Simpler implementation of synchronize_srcu that ignores batching. */ -void synchronize_srcu(struct srcu_struct *sp) -{ - int idx; - /* - * This code assumes that try_check_zero will succeed anyway, - * so there is no point in multiple tries. - */ - const int trycount = 1; - - might_sleep(); - - /* Ignore the lock, as multiple writers aren't working yet anyway. */ - - idx = 1 ^ (sp->completed & 1); - - /* For comments see srcu_advance_batches. */ - - assume(try_check_zero(sp, idx, trycount)); - - srcu_flip(sp); - - assume(try_check_zero(sp, idx^1, trycount)); -} diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/workqueues.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/workqueues.h deleted file mode 100644 index 28b960300971..000000000000 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/workqueues.h +++ /dev/null @@ -1,103 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef WORKQUEUES_H -#define WORKQUEUES_H - -#include <stdbool.h> - -#include "barriers.h" -#include "bug_on.h" -#include "int_typedefs.h" - -#include <linux/types.h> - -/* Stub workqueue implementation. */ - -struct work_struct; -typedef void (*work_func_t)(struct work_struct *work); -void delayed_work_timer_fn(unsigned long __data); - -struct work_struct { -/* atomic_long_t data; */ - unsigned long data; - - struct list_head entry; - work_func_t func; -#ifdef CONFIG_LOCKDEP - struct lockdep_map lockdep_map; -#endif -}; - -struct timer_list { - struct hlist_node entry; - unsigned long expires; - void (*function)(unsigned long); - unsigned long data; - u32 flags; - int slack; -}; - -struct delayed_work { - struct work_struct work; - struct timer_list timer; - - /* target workqueue and CPU ->timer uses to queue ->work */ - struct workqueue_struct *wq; - int cpu; -}; - - -static inline bool schedule_work(struct work_struct *work) -{ - BUG(); - return true; -} - -static inline bool schedule_work_on(int cpu, struct work_struct *work) -{ - BUG(); - return true; -} - -static inline bool queue_work(struct workqueue_struct *wq, - struct work_struct *work) -{ - BUG(); - return true; -} - -static inline bool queue_delayed_work(struct workqueue_struct *wq, - struct delayed_work *dwork, - unsigned long delay) -{ - BUG(); - return true; -} - -#define INIT_WORK(w, f) \ - do { \ - (w)->data = 0; \ - (w)->func = (f); \ - } while (0) - -#define INIT_DELAYED_WORK(w, f) INIT_WORK(&(w)->work, (f)) - -#define __WORK_INITIALIZER(n, f) { \ - .data = 0, \ - .entry = { &(n).entry, &(n).entry }, \ - .func = f \ - } - -/* Don't bother initializing timer. */ -#define __DELAYED_WORK_INITIALIZER(n, f, tflags) { \ - .work = __WORK_INITIALIZER((n).work, (f)), \ - } - -#define DECLARE_WORK(n, f) \ - struct workqueue_struct n = __WORK_INITIALIZER - -#define DECLARE_DELAYED_WORK(n, f) \ - struct delayed_work n = __DELAYED_WORK_INITIALIZER(n, f, 0) - -#define system_power_efficient_wq ((struct workqueue_struct *) NULL) - -#endif diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/Makefile b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/Makefile deleted file mode 100644 index ad21b925fbb4..000000000000 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/Makefile +++ /dev/null @@ -1,12 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -CBMC_FLAGS = -I../.. -I../../src -I../../include -I../../empty_includes -32 -pointer-check -mm pso - -all: - for i in ./*.pass; do \ - echo $$i ; \ - CBMC_FLAGS="$(CBMC_FLAGS)" sh ../test_script.sh --should-pass $$i > $$i.out 2>&1 ; \ - done - for i in ./*.fail; do \ - echo $$i ; \ - CBMC_FLAGS="$(CBMC_FLAGS)" sh ../test_script.sh --should-fail $$i > $$i.out 2>&1 ; \ - done diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/assert_end.fail b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/assert_end.fail deleted file mode 100644 index 40c8075919d1..000000000000 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/assert_end.fail +++ /dev/null @@ -1 +0,0 @@ -test_cbmc_options="-DASSERT_END" diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force.fail b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force.fail deleted file mode 100644 index ada5baf0b60d..000000000000 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force.fail +++ /dev/null @@ -1 +0,0 @@ -test_cbmc_options="-DFORCE_FAILURE" diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force2.fail b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force2.fail deleted file mode 100644 index 8fe00c8db466..000000000000 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force2.fail +++ /dev/null @@ -1 +0,0 @@ -test_cbmc_options="-DFORCE_FAILURE_2" diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force3.fail b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force3.fail deleted file mode 100644 index 612ed6772844..000000000000 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force3.fail +++ /dev/null @@ -1 +0,0 @@ -test_cbmc_options="-DFORCE_FAILURE_3" diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/main.pass b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/main.pass deleted file mode 100644 index e69de29bb2d1..000000000000 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/main.pass +++ /dev/null diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/test.c b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/test.c deleted file mode 100644 index 2ce2016f7871..000000000000 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/test.c +++ /dev/null @@ -1,73 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <src/combined_source.c> - -int x; -int y; - -int __unbuffered_tpr_x; -int __unbuffered_tpr_y; - -DEFINE_SRCU(ss); - -void rcu_reader(void) -{ - int idx; - -#ifndef FORCE_FAILURE_3 - idx = srcu_read_lock(&ss); -#endif - might_sleep(); - - __unbuffered_tpr_y = READ_ONCE(y); -#ifdef FORCE_FAILURE - srcu_read_unlock(&ss, idx); - idx = srcu_read_lock(&ss); -#endif - WRITE_ONCE(x, 1); - -#ifndef FORCE_FAILURE_3 - srcu_read_unlock(&ss, idx); -#endif - might_sleep(); -} - -void *thread_update(void *arg) -{ - WRITE_ONCE(y, 1); -#ifndef FORCE_FAILURE_2 - synchronize_srcu(&ss); -#endif - might_sleep(); - __unbuffered_tpr_x = READ_ONCE(x); - - return NULL; -} - -void *thread_process_reader(void *arg) -{ - rcu_reader(); - - return NULL; -} - -int main(int argc, char *argv[]) -{ - pthread_t tu; - pthread_t tpr; - - if (pthread_create(&tu, NULL, thread_update, NULL)) - abort(); - if (pthread_create(&tpr, NULL, thread_process_reader, NULL)) - abort(); - if (pthread_join(tu, NULL)) - abort(); - if (pthread_join(tpr, NULL)) - abort(); - assert(__unbuffered_tpr_y != 0 || __unbuffered_tpr_x != 0); - -#ifdef ASSERT_END - assert(0); -#endif - - return 0; -} diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/test_script.sh b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/test_script.sh deleted file mode 100755 index 2fe1f0339b4f..000000000000 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/test_script.sh +++ /dev/null @@ -1,103 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0 - -# This script expects a mode (either --should-pass or --should-fail) followed by -# an input file. The script uses the following environment variables. The test C -# source file is expected to be named test.c in the directory containing the -# input file. -# -# CBMC: The command to run CBMC. Default: cbmc -# CBMC_FLAGS: Additional flags to pass to CBMC -# NR_CPUS: Number of cpus to run tests with. Default specified by the test -# SYNC_SRCU_MODE: Choose implementation of synchronize_srcu. Defaults to simple. -# kernel: Version included in the linux kernel source. -# simple: Use try_check_zero directly. -# -# The input file is a script that is sourced by this file. It can define any of -# the following variables to configure the test. -# -# test_cbmc_options: Extra options to pass to CBMC. -# min_cpus_fail: Minimum number of CPUs (NR_CPUS) for verification to fail. -# The test is expected to pass if it is run with fewer. (Only -# useful for .fail files) -# default_cpus: Quantity of CPUs to use for the test, if not specified on the -# command line. Default: Larger of 2 and MIN_CPUS_FAIL. - -set -e - -if test "$#" -ne 2; then - echo "Expected one option followed by an input file" 1>&2 - exit 99 -fi - -if test "x$1" = "x--should-pass"; then - should_pass="yes" -elif test "x$1" = "x--should-fail"; then - should_pass="no" -else - echo "Unrecognized argument '$1'" 1>&2 - - # Exit code 99 indicates a hard error. - exit 99 -fi - -CBMC=${CBMC:-cbmc} - -SYNC_SRCU_MODE=${SYNC_SRCU_MODE:-simple} - -case ${SYNC_SRCU_MODE} in -kernel) sync_srcu_mode_flags="" ;; -simple) sync_srcu_mode_flags="-DUSE_SIMPLE_SYNC_SRCU" ;; - -*) - echo "Unrecognized argument '${SYNC_SRCU_MODE}'" 1>&2 - exit 99 - ;; -esac - -min_cpus_fail=1 - -c_file=`dirname "$2"`/test.c - -# Source the input file. -. $2 - -if test ${min_cpus_fail} -gt 2; then - default_default_cpus=${min_cpus_fail} -else - default_default_cpus=2 -fi -default_cpus=${default_cpus:-${default_default_cpus}} -cpus=${NR_CPUS:-${default_cpus}} - -# Check if there are two few cpus to make the test fail. -if test $cpus -lt ${min_cpus_fail:-0}; then - should_pass="yes" -fi - -cbmc_opts="-DNR_CPUS=${cpus} ${sync_srcu_mode_flags} ${test_cbmc_options} ${CBMC_FLAGS}" - -echo "Running CBMC: ${CBMC} ${cbmc_opts} ${c_file}" -if ${CBMC} ${cbmc_opts} "${c_file}"; then - # Verification successful. Make sure that it was supposed to verify. - test "x${should_pass}" = xyes -else - cbmc_exit_status=$? - - # An exit status of 10 indicates a failed verification. - # (see cbmc_parse_optionst::do_bmc in the CBMC source code) - if test ${cbmc_exit_status} -eq 10 && test "x${should_pass}" = xno; then - : - else - echo "CBMC returned ${cbmc_exit_status} exit status" 1>&2 - - # Parse errors have exit status 6. Any other type of error - # should be considered a hard error. - if test ${cbmc_exit_status} -ne 6 && \ - test ${cbmc_exit_status} -ne 10; then - exit 99 - else - exit 1 - fi - fi -fi diff --git a/tools/testing/selftests/resctrl/Makefile b/tools/testing/selftests/resctrl/Makefile index 73d53257df42..5073dbc96125 100644 --- a/tools/testing/selftests/resctrl/Makefile +++ b/tools/testing/selftests/resctrl/Makefile @@ -7,4 +7,4 @@ TEST_GEN_PROGS := resctrl_tests include ../lib.mk -$(OUTPUT)/resctrl_tests: $(wildcard *.c) +$(OUTPUT)/resctrl_tests: $(wildcard *.[ch]) diff --git a/tools/testing/selftests/resctrl/cache.c b/tools/testing/selftests/resctrl/cache.c index 8a4fe8693be6..d3cbb829ff6a 100644 --- a/tools/testing/selftests/resctrl/cache.c +++ b/tools/testing/selftests/resctrl/cache.c @@ -87,21 +87,19 @@ static int reset_enable_llc_perf(pid_t pid, int cpu_no) static int get_llc_perf(unsigned long *llc_perf_miss) { __u64 total_misses; + int ret; /* Stop counters after one span to get miss rate */ ioctl(fd_lm, PERF_EVENT_IOC_DISABLE, 0); - if (read(fd_lm, &rf_cqm, sizeof(struct read_format)) == -1) { + ret = read(fd_lm, &rf_cqm, sizeof(struct read_format)); + if (ret == -1) { perror("Could not get llc misses through perf"); - return -1; } total_misses = rf_cqm.values[0].value; - - close(fd_lm); - *llc_perf_miss = total_misses; return 0; @@ -212,7 +210,7 @@ int measure_cache_vals(struct resctrl_val_param *param, int bm_pid) */ int cat_val(struct resctrl_val_param *param) { - int malloc_and_init_memory = 1, memflush = 1, operation = 0, ret = 0; + int memflush = 1, operation = 0, ret = 0; char *resctrl_val = param->resctrl_val; pid_t bm_pid; @@ -232,40 +230,38 @@ int cat_val(struct resctrl_val_param *param) if (ret) return ret; - if (!strncmp(resctrl_val, CAT_STR, sizeof(CAT_STR))) - initialize_llc_perf(); + initialize_llc_perf(); /* Test runs until the callback setup() tells the test to stop. */ while (1) { - if (!strncmp(resctrl_val, CAT_STR, sizeof(CAT_STR))) { - ret = param->setup(1, param); - if (ret == END_OF_TESTS) { - ret = 0; - break; - } - if (ret < 0) - break; - ret = reset_enable_llc_perf(bm_pid, param->cpu_no); - if (ret) - break; - - if (run_fill_buf(param->span, malloc_and_init_memory, - memflush, operation, resctrl_val)) { - fprintf(stderr, "Error-running fill buffer\n"); - ret = -1; - break; - } - - sleep(1); - ret = measure_cache_vals(param, bm_pid); - if (ret) - break; - } else { + ret = param->setup(param); + if (ret == END_OF_TESTS) { + ret = 0; + break; + } + if (ret < 0) + break; + ret = reset_enable_llc_perf(bm_pid, param->cpu_no); + if (ret) break; + + if (run_fill_buf(param->span, memflush, operation, true)) { + fprintf(stderr, "Error-running fill buffer\n"); + ret = -1; + goto pe_close; } + + sleep(1); + ret = measure_cache_vals(param, bm_pid); + if (ret) + goto pe_close; } return ret; + +pe_close: + close(fd_lm); + return ret; } /* @@ -282,7 +278,7 @@ int cat_val(struct resctrl_val_param *param) * Return: 0 on success. non-zero on failure. */ int show_cache_info(unsigned long sum_llc_val, int no_of_bits, - unsigned long cache_span, unsigned long max_diff, + size_t cache_span, unsigned long max_diff, unsigned long max_diff_percent, unsigned long num_of_runs, bool platform, bool cmt) { @@ -291,7 +287,7 @@ int show_cache_info(unsigned long sum_llc_val, int no_of_bits, long avg_diff = 0; int ret; - avg_llc_val = sum_llc_val / (num_of_runs - 1); + avg_llc_val = sum_llc_val / num_of_runs; avg_diff = (long)abs(cache_span - avg_llc_val); diff_percent = ((float)cache_span - avg_llc_val) / cache_span * 100; @@ -304,7 +300,7 @@ int show_cache_info(unsigned long sum_llc_val, int no_of_bits, ksft_print_msg("Percent diff=%d\n", abs((int)diff_percent)); ksft_print_msg("Number of bits: %d\n", no_of_bits); ksft_print_msg("Average LLC val: %lu\n", avg_llc_val); - ksft_print_msg("Cache span (%s): %lu\n", cmt ? "bytes" : "lines", + ksft_print_msg("Cache span (%s): %zu\n", cmt ? "bytes" : "lines", cache_span); return ret; diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c index fb1443f888c4..3848dfb46aba 100644 --- a/tools/testing/selftests/resctrl/cat_test.c +++ b/tools/testing/selftests/resctrl/cat_test.c @@ -17,27 +17,16 @@ #define MAX_DIFF_PERCENT 4 #define MAX_DIFF 1000000 -static int count_of_bits; -static char cbm_mask[256]; -static unsigned long long_mask; -static unsigned long cache_size; - /* * Change schemata. Write schemata to specified * con_mon grp, mon_grp in resctrl FS. * Run 5 times in order to get average values. */ -static int cat_setup(int num, ...) +static int cat_setup(struct resctrl_val_param *p) { - struct resctrl_val_param *p; char schemata[64]; - va_list param; int ret = 0; - va_start(param, num); - p = va_arg(param, struct resctrl_val_param *); - va_end(param); - /* Run NUM_OF_RUNS times */ if (p->num_of_runs >= NUM_OF_RUNS) return END_OF_TESTS; @@ -88,7 +77,7 @@ static int check_results(struct resctrl_val_param *param) no_of_bits = count_bits(param->mask); return show_cache_info(sum_llc_perf_miss, no_of_bits, param->span / 64, - MAX_DIFF, MAX_DIFF_PERCENT, NUM_OF_RUNS, + MAX_DIFF, MAX_DIFF_PERCENT, runs - 1, get_vendor() == ARCH_INTEL, false); } @@ -102,14 +91,12 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type) { unsigned long l_mask, l_mask_1; int ret, pipefd[2], sibling_cpu_no; + unsigned long cache_size = 0; + unsigned long long_mask; + char cbm_mask[256]; + int count_of_bits; char pipe_message; - cache_size = 0; - - ret = remount_resctrlfs(true); - if (ret) - return ret; - /* Get default cbm mask for L3/L2 cache */ ret = get_cbm_mask(cache_type, cbm_mask); if (ret) @@ -144,7 +131,6 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type) struct resctrl_val_param param = { .resctrl_val = CAT_STR, .cpu_no = cpu_no, - .mum_resctrlfs = false, .setup = cat_setup, }; @@ -227,8 +213,6 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type) out: cat_test_cleanup(); - if (bm_pid) - umount_resctrlfs(); return ret; } diff --git a/tools/testing/selftests/resctrl/cmt_test.c b/tools/testing/selftests/resctrl/cmt_test.c index af71b2141271..cb2197647c6c 100644 --- a/tools/testing/selftests/resctrl/cmt_test.c +++ b/tools/testing/selftests/resctrl/cmt_test.c @@ -16,20 +16,8 @@ #define MAX_DIFF 2000000 #define MAX_DIFF_PERCENT 15 -static int count_of_bits; -static char cbm_mask[256]; -static unsigned long long_mask; -static unsigned long cache_size; - -static int cmt_setup(int num, ...) +static int cmt_setup(struct resctrl_val_param *p) { - struct resctrl_val_param *p; - va_list param; - - va_start(param, num); - p = va_arg(param, struct resctrl_val_param *); - va_end(param); - /* Run NUM_OF_RUNS times */ if (p->num_of_runs >= NUM_OF_RUNS) return END_OF_TESTS; @@ -71,7 +59,7 @@ static int check_results(struct resctrl_val_param *param, int no_of_bits) fclose(fp); return show_cache_info(sum_llc_occu_resc, no_of_bits, param->span, - MAX_DIFF, MAX_DIFF_PERCENT, NUM_OF_RUNS, + MAX_DIFF, MAX_DIFF_PERCENT, runs - 1, true, true); } @@ -82,14 +70,12 @@ void cmt_test_cleanup(void) int cmt_resctrl_val(int cpu_no, int n, char **benchmark_cmd) { + unsigned long cache_size = 0; + unsigned long long_mask; + char cbm_mask[256]; + int count_of_bits; int ret; - cache_size = 0; - - ret = remount_resctrlfs(true); - if (ret) - return ret; - if (!validate_resctrl_feature_request(CMT_STR)) return -1; @@ -117,7 +103,6 @@ int cmt_resctrl_val(int cpu_no, int n, char **benchmark_cmd) .ctrlgrp = "c1", .mongrp = "m1", .cpu_no = cpu_no, - .mum_resctrlfs = false, .filename = RESULT_FILE_NAME, .mask = ~(long_mask << n) & long_mask, .span = cache_size * n / count_of_bits, @@ -126,7 +111,7 @@ int cmt_resctrl_val(int cpu_no, int n, char **benchmark_cmd) }; if (strcmp(benchmark_cmd[0], "fill_buf") == 0) - sprintf(benchmark_cmd[1], "%lu", param.span); + sprintf(benchmark_cmd[1], "%zu", param.span); remove(RESULT_FILE_NAME); diff --git a/tools/testing/selftests/resctrl/fill_buf.c b/tools/testing/selftests/resctrl/fill_buf.c index 341cc93ca84c..0d425f26583a 100644 --- a/tools/testing/selftests/resctrl/fill_buf.c +++ b/tools/testing/selftests/resctrl/fill_buf.c @@ -22,8 +22,6 @@ #define PAGE_SIZE (4 * 1024) #define MB (1024 * 1024) -static unsigned char *startptr; - static void sb(void) { #if defined(__i386) || defined(__x86_64) @@ -40,32 +38,32 @@ static void cl_flush(void *p) #endif } -static void mem_flush(void *p, size_t s) +static void mem_flush(unsigned char *buf, size_t buf_size) { - char *cp = (char *)p; + unsigned char *cp = buf; size_t i = 0; - s = s / CL_SIZE; /* mem size in cache llines */ + buf_size = buf_size / CL_SIZE; /* mem size in cache lines */ - for (i = 0; i < s; i++) + for (i = 0; i < buf_size; i++) cl_flush(&cp[i * CL_SIZE]); sb(); } -static void *malloc_and_init_memory(size_t s) +static void *malloc_and_init_memory(size_t buf_size) { void *p = NULL; uint64_t *p64; size_t s64; int ret; - ret = posix_memalign(&p, PAGE_SIZE, s); + ret = posix_memalign(&p, PAGE_SIZE, buf_size); if (ret < 0) return NULL; p64 = (uint64_t *)p; - s64 = s / sizeof(uint64_t); + s64 = buf_size / sizeof(uint64_t); while (s64 > 0) { *p64 = (uint64_t)rand(); @@ -76,12 +74,13 @@ static void *malloc_and_init_memory(size_t s) return p; } -static int fill_one_span_read(unsigned char *start_ptr, unsigned char *end_ptr) +static int fill_one_span_read(unsigned char *buf, size_t buf_size) { + unsigned char *end_ptr = buf + buf_size; unsigned char sum, *p; sum = 0; - p = start_ptr; + p = buf; while (p < end_ptr) { sum += *p; p += (CL_SIZE / 2); @@ -90,27 +89,26 @@ static int fill_one_span_read(unsigned char *start_ptr, unsigned char *end_ptr) return sum; } -static -void fill_one_span_write(unsigned char *start_ptr, unsigned char *end_ptr) +static void fill_one_span_write(unsigned char *buf, size_t buf_size) { + unsigned char *end_ptr = buf + buf_size; unsigned char *p; - p = start_ptr; + p = buf; while (p < end_ptr) { *p = '1'; p += (CL_SIZE / 2); } } -static int fill_cache_read(unsigned char *start_ptr, unsigned char *end_ptr, - char *resctrl_val) +static int fill_cache_read(unsigned char *buf, size_t buf_size, bool once) { int ret = 0; FILE *fp; while (1) { - ret = fill_one_span_read(start_ptr, end_ptr); - if (!strncmp(resctrl_val, CAT_STR, sizeof(CAT_STR))) + ret = fill_one_span_read(buf, buf_size); + if (once) break; } @@ -126,75 +124,52 @@ static int fill_cache_read(unsigned char *start_ptr, unsigned char *end_ptr, return 0; } -static int fill_cache_write(unsigned char *start_ptr, unsigned char *end_ptr, - char *resctrl_val) +static int fill_cache_write(unsigned char *buf, size_t buf_size, bool once) { while (1) { - fill_one_span_write(start_ptr, end_ptr); - if (!strncmp(resctrl_val, CAT_STR, sizeof(CAT_STR))) + fill_one_span_write(buf, buf_size); + if (once) break; } return 0; } -static int -fill_cache(unsigned long long buf_size, int malloc_and_init, int memflush, - int op, char *resctrl_val) +static int fill_cache(size_t buf_size, int memflush, int op, bool once) { - unsigned char *start_ptr, *end_ptr; - unsigned long long i; + unsigned char *buf; int ret; - if (malloc_and_init) - start_ptr = malloc_and_init_memory(buf_size); - else - start_ptr = malloc(buf_size); - - if (!start_ptr) + buf = malloc_and_init_memory(buf_size); + if (!buf) return -1; - startptr = start_ptr; - end_ptr = start_ptr + buf_size; - - /* - * It's better to touch the memory once to avoid any compiler - * optimizations - */ - if (!malloc_and_init) { - for (i = 0; i < buf_size; i++) - *start_ptr++ = (unsigned char)rand(); - } - - start_ptr = startptr; - /* Flush the memory before using to avoid "cache hot pages" effect */ if (memflush) - mem_flush(start_ptr, buf_size); + mem_flush(buf, buf_size); if (op == 0) - ret = fill_cache_read(start_ptr, end_ptr, resctrl_val); + ret = fill_cache_read(buf, buf_size, once); else - ret = fill_cache_write(start_ptr, end_ptr, resctrl_val); + ret = fill_cache_write(buf, buf_size, once); + + free(buf); if (ret) { printf("\n Error in fill cache read/write...\n"); return -1; } - free(startptr); return 0; } -int run_fill_buf(unsigned long span, int malloc_and_init_memory, - int memflush, int op, char *resctrl_val) +int run_fill_buf(size_t span, int memflush, int op, bool once) { - unsigned long long cache_size = span; + size_t cache_size = span; int ret; - ret = fill_cache(cache_size, malloc_and_init_memory, memflush, op, - resctrl_val); + ret = fill_cache(cache_size, memflush, op, once); if (ret) { printf("\n Error in fill cache\n"); return -1; diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c index cde3781a9ab0..4d2f145804b8 100644 --- a/tools/testing/selftests/resctrl/mba_test.c +++ b/tools/testing/selftests/resctrl/mba_test.c @@ -22,18 +22,12 @@ * con_mon grp, mon_grp in resctrl FS. * For each allocation, run 5 times in order to get average values. */ -static int mba_setup(int num, ...) +static int mba_setup(struct resctrl_val_param *p) { static int runs_per_allocation, allocation = 100; - struct resctrl_val_param *p; char allocation_str[64]; - va_list param; int ret; - va_start(param, num); - p = va_arg(param, struct resctrl_val_param *); - va_end(param); - if (runs_per_allocation >= NUM_OF_RUNS) runs_per_allocation = 0; @@ -154,7 +148,6 @@ int mba_schemata_change(int cpu_no, char *bw_report, char **benchmark_cmd) .ctrlgrp = "c1", .mongrp = "m1", .cpu_no = cpu_no, - .mum_resctrlfs = true, .filename = RESULT_FILE_NAME, .bw_report = bw_report, .setup = mba_setup diff --git a/tools/testing/selftests/resctrl/mbm_test.c b/tools/testing/selftests/resctrl/mbm_test.c index 538d35a6485a..c7de6f5977f6 100644 --- a/tools/testing/selftests/resctrl/mbm_test.c +++ b/tools/testing/selftests/resctrl/mbm_test.c @@ -15,7 +15,7 @@ #define NUM_OF_RUNS 5 static int -show_bw_info(unsigned long *bw_imc, unsigned long *bw_resc, int span) +show_bw_info(unsigned long *bw_imc, unsigned long *bw_resc, size_t span) { unsigned long avg_bw_imc = 0, avg_bw_resc = 0; unsigned long sum_bw_imc = 0, sum_bw_resc = 0; @@ -40,14 +40,14 @@ show_bw_info(unsigned long *bw_imc, unsigned long *bw_resc, int span) ksft_print_msg("%s Check MBM diff within %d%%\n", ret ? "Fail:" : "Pass:", MAX_DIFF_PERCENT); ksft_print_msg("avg_diff_per: %d%%\n", avg_diff_per); - ksft_print_msg("Span (MB): %d\n", span); + ksft_print_msg("Span (MB): %zu\n", span / MB); ksft_print_msg("avg_bw_imc: %lu\n", avg_bw_imc); ksft_print_msg("avg_bw_resc: %lu\n", avg_bw_resc); return ret; } -static int check_results(int span) +static int check_results(size_t span) { unsigned long bw_imc[NUM_OF_RUNS], bw_resc[NUM_OF_RUNS]; char temp[1024], *token_array[8]; @@ -86,16 +86,10 @@ static int check_results(int span) return ret; } -static int mbm_setup(int num, ...) +static int mbm_setup(struct resctrl_val_param *p) { - struct resctrl_val_param *p; - va_list param; int ret = 0; - va_start(param, num); - p = va_arg(param, struct resctrl_val_param *); - va_end(param); - /* Run NUM_OF_RUNS times */ if (p->num_of_runs >= NUM_OF_RUNS) return END_OF_TESTS; @@ -115,7 +109,7 @@ void mbm_test_cleanup(void) remove(RESULT_FILE_NAME); } -int mbm_bw_change(int span, int cpu_no, char *bw_report, char **benchmark_cmd) +int mbm_bw_change(size_t span, int cpu_no, char *bw_report, char **benchmark_cmd) { struct resctrl_val_param param = { .resctrl_val = MBM_STR, @@ -123,7 +117,6 @@ int mbm_bw_change(int span, int cpu_no, char *bw_report, char **benchmark_cmd) .mongrp = "m1", .span = span, .cpu_no = cpu_no, - .mum_resctrlfs = true, .filename = RESULT_FILE_NAME, .bw_report = bw_report, .setup = mbm_setup diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h index 87e39456dee0..838d1a438f33 100644 --- a/tools/testing/selftests/resctrl/resctrl.h +++ b/tools/testing/selftests/resctrl/resctrl.h @@ -3,7 +3,6 @@ #ifndef RESCTRL_H #define RESCTRL_H #include <stdio.h> -#include <stdarg.h> #include <math.h> #include <errno.h> #include <sched.h> @@ -43,6 +42,7 @@ do { \ perror(err_msg); \ kill(ppid, SIGKILL); \ + umount_resctrlfs(); \ exit(EXIT_FAILURE); \ } while (0) @@ -53,7 +53,6 @@ * @mongrp: Name of the monitor group (mon grp) * @cpu_no: CPU number to which the benchmark would be binded * @span: Memory bytes accessed in each benchmark iteration - * @mum_resctrlfs: Should the resctrl FS be remounted? * @filename: Name of file to which the o/p should be written * @bw_report: Bandwidth report type (reads vs writes) * @setup: Call back function to setup test environment @@ -63,13 +62,12 @@ struct resctrl_val_param { char ctrlgrp[64]; char mongrp[64]; int cpu_no; - unsigned long span; - bool mum_resctrlfs; + size_t span; char filename[64]; char *bw_report; unsigned long mask; int num_of_runs; - int (*setup)(int num, ...); + int (*setup)(struct resctrl_val_param *param); }; #define MBM_STR "mbm" @@ -84,8 +82,8 @@ extern char llc_occup_path[1024]; int get_vendor(void); bool check_resctrlfs_support(void); int filter_dmesg(void); -int remount_resctrlfs(bool mum_resctrlfs); int get_resource_id(int cpu_no, int *resource_id); +int mount_resctrlfs(void); int umount_resctrlfs(void); int validate_bw_report_request(char *bw_report); bool validate_resctrl_feature_request(const char *resctrl_val); @@ -98,10 +96,9 @@ int write_bm_pid_to_resctrl(pid_t bm_pid, char *ctrlgrp, char *mongrp, char *resctrl_val); int perf_event_open(struct perf_event_attr *hw_event, pid_t pid, int cpu, int group_fd, unsigned long flags); -int run_fill_buf(unsigned long span, int malloc_and_init_memory, int memflush, - int op, char *resctrl_va); +int run_fill_buf(size_t span, int memflush, int op, bool once); int resctrl_val(char **benchmark_cmd, struct resctrl_val_param *param); -int mbm_bw_change(int span, int cpu_no, char *bw_report, char **benchmark_cmd); +int mbm_bw_change(size_t span, int cpu_no, char *bw_report, char **benchmark_cmd); void tests_cleanup(void); void mbm_test_cleanup(void); int mba_schemata_change(int cpu_no, char *bw_report, char **benchmark_cmd); @@ -120,7 +117,7 @@ void cmt_test_cleanup(void); int get_core_sibling(int cpu_no); int measure_cache_vals(struct resctrl_val_param *param, int bm_pid); int show_cache_info(unsigned long sum_llc_val, int no_of_bits, - unsigned long cache_span, unsigned long max_diff, + size_t cache_span, unsigned long max_diff, unsigned long max_diff_percent, unsigned long num_of_runs, bool platform, bool cmt); diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c index 9b9751206e1c..d511daeb6851 100644 --- a/tools/testing/selftests/resctrl/resctrl_tests.c +++ b/tools/testing/selftests/resctrl/resctrl_tests.c @@ -70,60 +70,81 @@ void tests_cleanup(void) cat_test_cleanup(); } -static void run_mbm_test(bool has_ben, char **benchmark_cmd, int span, +static void run_mbm_test(char **benchmark_cmd, size_t span, int cpu_no, char *bw_report) { int res; ksft_print_msg("Starting MBM BW change ...\n"); + res = mount_resctrlfs(); + if (res) { + ksft_exit_fail_msg("Failed to mount resctrl FS\n"); + return; + } + if (!validate_resctrl_feature_request(MBM_STR) || (get_vendor() != ARCH_INTEL)) { ksft_test_result_skip("Hardware does not support MBM or MBM is disabled\n"); - return; + goto umount; } - if (!has_ben) - sprintf(benchmark_cmd[5], "%s", MBA_STR); res = mbm_bw_change(span, cpu_no, bw_report, benchmark_cmd); ksft_test_result(!res, "MBM: bw change\n"); if ((get_vendor() == ARCH_INTEL) && res) ksft_print_msg("Intel MBM may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n"); + +umount: + umount_resctrlfs(); } -static void run_mba_test(bool has_ben, char **benchmark_cmd, int span, - int cpu_no, char *bw_report) +static void run_mba_test(char **benchmark_cmd, int cpu_no, char *bw_report) { int res; ksft_print_msg("Starting MBA Schemata change ...\n"); + res = mount_resctrlfs(); + if (res) { + ksft_exit_fail_msg("Failed to mount resctrl FS\n"); + return; + } + if (!validate_resctrl_feature_request(MBA_STR) || (get_vendor() != ARCH_INTEL)) { ksft_test_result_skip("Hardware does not support MBA or MBA is disabled\n"); - return; + goto umount; } - if (!has_ben) - sprintf(benchmark_cmd[1], "%d", span); res = mba_schemata_change(cpu_no, bw_report, benchmark_cmd); ksft_test_result(!res, "MBA: schemata change\n"); + +umount: + umount_resctrlfs(); } -static void run_cmt_test(bool has_ben, char **benchmark_cmd, int cpu_no) +static void run_cmt_test(char **benchmark_cmd, int cpu_no) { int res; ksft_print_msg("Starting CMT test ...\n"); + + res = mount_resctrlfs(); + if (res) { + ksft_exit_fail_msg("Failed to mount resctrl FS\n"); + return; + } + if (!validate_resctrl_feature_request(CMT_STR)) { ksft_test_result_skip("Hardware does not support CMT or CMT is disabled\n"); - return; + goto umount; } - if (!has_ben) - sprintf(benchmark_cmd[5], "%s", CMT_STR); res = cmt_resctrl_val(cpu_no, 5, benchmark_cmd); ksft_test_result(!res, "CMT: test\n"); if ((get_vendor() == ARCH_INTEL) && res) ksft_print_msg("Intel CMT may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n"); + +umount: + umount_resctrlfs(); } static void run_cat_test(int cpu_no, int no_of_bits) @@ -132,22 +153,32 @@ static void run_cat_test(int cpu_no, int no_of_bits) ksft_print_msg("Starting CAT test ...\n"); + res = mount_resctrlfs(); + if (res) { + ksft_exit_fail_msg("Failed to mount resctrl FS\n"); + return; + } + if (!validate_resctrl_feature_request(CAT_STR)) { ksft_test_result_skip("Hardware does not support CAT or CAT is disabled\n"); - return; + goto umount; } res = cat_perf_miss_val(cpu_no, no_of_bits, "L3"); ksft_test_result(!res, "CAT: test\n"); + +umount: + umount_resctrlfs(); } int main(int argc, char **argv) { bool has_ben = false, mbm_test = true, mba_test = true, cmt_test = true; - int c, cpu_no = 1, span = 250, argc_new = argc, i, no_of_bits = 0; char *benchmark_cmd[BENCHMARK_ARGS], bw_report[64], bm_type[64]; char benchmark_cmd_area[BENCHMARK_ARGS][BENCHMARK_ARG_SIZE]; + int c, cpu_no = 1, argc_new = argc, i, no_of_bits = 0; int ben_ind, ben_count, tests = 0; + size_t span = 250 * MB; bool cat_test = true; for (i = 0; i < argc; i++) { @@ -232,16 +263,15 @@ int main(int argc, char **argv) benchmark_cmd[ben_count] = NULL; } else { /* If no benchmark is given by "-b" argument, use fill_buf. */ - for (i = 0; i < 6; i++) + for (i = 0; i < 5; i++) benchmark_cmd[i] = benchmark_cmd_area[i]; strcpy(benchmark_cmd[0], "fill_buf"); - sprintf(benchmark_cmd[1], "%d", span); + sprintf(benchmark_cmd[1], "%zu", span); strcpy(benchmark_cmd[2], "1"); - strcpy(benchmark_cmd[3], "1"); - strcpy(benchmark_cmd[4], "0"); - strcpy(benchmark_cmd[5], ""); - benchmark_cmd[6] = NULL; + strcpy(benchmark_cmd[3], "0"); + strcpy(benchmark_cmd[4], "false"); + benchmark_cmd[5] = NULL; } sprintf(bw_report, "reads"); @@ -250,23 +280,24 @@ int main(int argc, char **argv) if (!check_resctrlfs_support()) return ksft_exit_skip("resctrl FS does not exist. Enable X86_CPU_RESCTRL config option.\n"); + if (umount_resctrlfs()) + return ksft_exit_skip("resctrl FS unmount failed.\n"); + filter_dmesg(); ksft_set_plan(tests ? : 4); if (mbm_test) - run_mbm_test(has_ben, benchmark_cmd, span, cpu_no, bw_report); + run_mbm_test(benchmark_cmd, span, cpu_no, bw_report); if (mba_test) - run_mba_test(has_ben, benchmark_cmd, span, cpu_no, bw_report); + run_mba_test(benchmark_cmd, cpu_no, bw_report); if (cmt_test) - run_cmt_test(has_ben, benchmark_cmd, cpu_no); + run_cmt_test(benchmark_cmd, cpu_no); if (cat_test) run_cat_test(cpu_no, no_of_bits); - umount_resctrlfs(); - ksft_finished(); } diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c index ab1eab1e7ff6..f0f6c5f6e98b 100644 --- a/tools/testing/selftests/resctrl/resctrl_val.c +++ b/tools/testing/selftests/resctrl/resctrl_val.c @@ -648,10 +648,6 @@ int resctrl_val(char **benchmark_cmd, struct resctrl_val_param *param) return ret; } - ret = remount_resctrlfs(param->mum_resctrlfs); - if (ret) - return ret; - /* * If benchmark wasn't successfully started by child, then child should * kill parent, so save parent's pid @@ -763,7 +759,7 @@ int resctrl_val(char **benchmark_cmd, struct resctrl_val_param *param) /* Test runs until the callback setup() tells the test to stop. */ while (1) { - ret = param->setup(1, param); + ret = param->setup(param); if (ret == END_OF_TESTS) { ret = 0; break; @@ -788,7 +784,6 @@ unregister: signal_handler_unregister(); out: kill(bm_pid, SIGKILL); - umount_resctrlfs(); return ret; } diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c index fb00245dee92..bd36ee206602 100644 --- a/tools/testing/selftests/resctrl/resctrlfs.c +++ b/tools/testing/selftests/resctrl/resctrlfs.c @@ -48,29 +48,20 @@ static int find_resctrl_mount(char *buffer) } /* - * remount_resctrlfs - Remount resctrl FS at /sys/fs/resctrl - * @mum_resctrlfs: Should the resctrl FS be remounted? + * mount_resctrlfs - Mount resctrl FS at /sys/fs/resctrl * - * If not mounted, mount it. - * If mounted and mum_resctrlfs then remount resctrl FS. - * If mounted and !mum_resctrlfs then noop + * Mounts resctrl FS. Fails if resctrl FS is already mounted to avoid + * pre-existing settings interfering with the test results. * * Return: 0 on success, non-zero on failure */ -int remount_resctrlfs(bool mum_resctrlfs) +int mount_resctrlfs(void) { - char mountpoint[256]; int ret; - ret = find_resctrl_mount(mountpoint); - if (ret) - strcpy(mountpoint, RESCTRL_PATH); - - if (!ret && mum_resctrlfs && umount(mountpoint)) - ksft_print_msg("Fail: unmounting \"%s\"\n", mountpoint); - - if (!ret && !mum_resctrlfs) - return 0; + ret = find_resctrl_mount(NULL); + if (ret != -ENOENT) + return -1; ksft_print_msg("Mounting resctrl to \"%s\"\n", RESCTRL_PATH); ret = mount("resctrl", RESCTRL_PATH, "resctrl", 0, NULL); @@ -82,10 +73,16 @@ int remount_resctrlfs(bool mum_resctrlfs) int umount_resctrlfs(void) { - if (find_resctrl_mount(NULL)) + char mountpoint[256]; + int ret; + + ret = find_resctrl_mount(mountpoint); + if (ret == -ENOENT) return 0; + if (ret) + return ret; - if (umount(RESCTRL_PATH)) { + if (umount(mountpoint)) { perror("# Unable to umount resctrl"); return errno; @@ -305,10 +302,10 @@ int taskset_benchmark(pid_t bm_pid, int cpu_no) */ void run_benchmark(int signum, siginfo_t *info, void *ucontext) { - int operation, ret, malloc_and_init_memory, memflush; - unsigned long span, buffer_span; + int operation, ret, memflush; char **benchmark_cmd; - char resctrl_val[64]; + size_t span; + bool once; FILE *fp; benchmark_cmd = info->si_ptr; @@ -324,18 +321,16 @@ void run_benchmark(int signum, siginfo_t *info, void *ucontext) if (strcmp(benchmark_cmd[0], "fill_buf") == 0) { /* Execute default fill_buf benchmark */ span = strtoul(benchmark_cmd[1], NULL, 10); - malloc_and_init_memory = atoi(benchmark_cmd[2]); - memflush = atoi(benchmark_cmd[3]); - operation = atoi(benchmark_cmd[4]); - sprintf(resctrl_val, "%s", benchmark_cmd[5]); - - if (strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR))) - buffer_span = span * MB; + memflush = atoi(benchmark_cmd[2]); + operation = atoi(benchmark_cmd[3]); + if (!strcmp(benchmark_cmd[4], "true")) + once = true; + else if (!strcmp(benchmark_cmd[4], "false")) + once = false; else - buffer_span = span; + PARENT_EXIT("Invalid once parameter"); - if (run_fill_buf(buffer_span, malloc_and_init_memory, memflush, - operation, resctrl_val)) + if (run_fill_buf(span, memflush, operation, once)) fprintf(stderr, "Error in running fill buffer\n"); } else { /* Execute specified benchmark */ @@ -611,7 +606,8 @@ char *fgrep(FILE *inf, const char *str) * validate_resctrl_feature_request - Check if requested feature is valid. * @resctrl_val: Requested feature * - * Return: True if the feature is supported, else false + * Return: True if the feature is supported, else false. False is also + * returned if resctrl FS is not mounted. */ bool validate_resctrl_feature_request(const char *resctrl_val) { @@ -619,11 +615,13 @@ bool validate_resctrl_feature_request(const char *resctrl_val) bool found = false; char *res; FILE *inf; + int ret; if (!resctrl_val) return false; - if (remount_resctrlfs(false)) + ret = find_resctrl_mount(NULL); + if (ret) return false; if (!strncmp(resctrl_val, CAT_STR, sizeof(CAT_STR))) { diff --git a/tools/testing/selftests/riscv/Makefile b/tools/testing/selftests/riscv/Makefile index f4b3d5c9af5b..4a9ff515a3a0 100644 --- a/tools/testing/selftests/riscv/Makefile +++ b/tools/testing/selftests/riscv/Makefile @@ -5,7 +5,7 @@ ARCH ?= $(shell uname -m 2>/dev/null || echo not) ifneq (,$(filter $(ARCH),riscv)) -RISCV_SUBTARGETS ?= hwprobe vector +RISCV_SUBTARGETS ?= hwprobe vector mm else RISCV_SUBTARGETS := endif diff --git a/tools/testing/selftests/riscv/mm/.gitignore b/tools/testing/selftests/riscv/mm/.gitignore new file mode 100644 index 000000000000..5c2c57cb950c --- /dev/null +++ b/tools/testing/selftests/riscv/mm/.gitignore @@ -0,0 +1,2 @@ +mmap_bottomup +mmap_default diff --git a/tools/testing/selftests/riscv/mm/Makefile b/tools/testing/selftests/riscv/mm/Makefile new file mode 100644 index 000000000000..11e0f0568923 --- /dev/null +++ b/tools/testing/selftests/riscv/mm/Makefile @@ -0,0 +1,15 @@ +# SPDX-License-Identifier: GPL-2.0 +# Copyright (C) 2021 ARM Limited +# Originally tools/testing/arm64/abi/Makefile + +# Additional include paths needed by kselftest.h and local headers +CFLAGS += -D_GNU_SOURCE -std=gnu99 -I. + +TEST_GEN_FILES := testcases/mmap_default testcases/mmap_bottomup + +TEST_PROGS := testcases/run_mmap.sh + +include ../../lib.mk + +$(OUTPUT)/mm: testcases/mmap_default.c testcases/mmap_bottomup.c testcases/mmap_tests.h + $(CC) -o$@ $(CFLAGS) $(LDFLAGS) $^ diff --git a/tools/testing/selftests/riscv/mm/testcases/mmap_bottomup.c b/tools/testing/selftests/riscv/mm/testcases/mmap_bottomup.c new file mode 100644 index 000000000000..b29379f7e478 --- /dev/null +++ b/tools/testing/selftests/riscv/mm/testcases/mmap_bottomup.c @@ -0,0 +1,35 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <sys/mman.h> +#include <testcases/mmap_test.h> + +#include "../../kselftest_harness.h" + +TEST(infinite_rlimit) +{ +// Only works on 64 bit +#if __riscv_xlen == 64 + struct addresses mmap_addresses; + + EXPECT_EQ(BOTTOM_UP, memory_layout()); + + do_mmaps(&mmap_addresses); + + EXPECT_NE(MAP_FAILED, mmap_addresses.no_hint); + EXPECT_NE(MAP_FAILED, mmap_addresses.on_37_addr); + EXPECT_NE(MAP_FAILED, mmap_addresses.on_38_addr); + EXPECT_NE(MAP_FAILED, mmap_addresses.on_46_addr); + EXPECT_NE(MAP_FAILED, mmap_addresses.on_47_addr); + EXPECT_NE(MAP_FAILED, mmap_addresses.on_55_addr); + EXPECT_NE(MAP_FAILED, mmap_addresses.on_56_addr); + + EXPECT_GT(1UL << 47, (unsigned long)mmap_addresses.no_hint); + EXPECT_GT(1UL << 38, (unsigned long)mmap_addresses.on_37_addr); + EXPECT_GT(1UL << 38, (unsigned long)mmap_addresses.on_38_addr); + EXPECT_GT(1UL << 38, (unsigned long)mmap_addresses.on_46_addr); + EXPECT_GT(1UL << 47, (unsigned long)mmap_addresses.on_47_addr); + EXPECT_GT(1UL << 47, (unsigned long)mmap_addresses.on_55_addr); + EXPECT_GT(1UL << 56, (unsigned long)mmap_addresses.on_56_addr); +#endif +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/riscv/mm/testcases/mmap_default.c b/tools/testing/selftests/riscv/mm/testcases/mmap_default.c new file mode 100644 index 000000000000..d1accb91b726 --- /dev/null +++ b/tools/testing/selftests/riscv/mm/testcases/mmap_default.c @@ -0,0 +1,35 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <sys/mman.h> +#include <testcases/mmap_test.h> + +#include "../../kselftest_harness.h" + +TEST(default_rlimit) +{ +// Only works on 64 bit +#if __riscv_xlen == 64 + struct addresses mmap_addresses; + + EXPECT_EQ(TOP_DOWN, memory_layout()); + + do_mmaps(&mmap_addresses); + + EXPECT_NE(MAP_FAILED, mmap_addresses.no_hint); + EXPECT_NE(MAP_FAILED, mmap_addresses.on_37_addr); + EXPECT_NE(MAP_FAILED, mmap_addresses.on_38_addr); + EXPECT_NE(MAP_FAILED, mmap_addresses.on_46_addr); + EXPECT_NE(MAP_FAILED, mmap_addresses.on_47_addr); + EXPECT_NE(MAP_FAILED, mmap_addresses.on_55_addr); + EXPECT_NE(MAP_FAILED, mmap_addresses.on_56_addr); + + EXPECT_GT(1UL << 47, (unsigned long)mmap_addresses.no_hint); + EXPECT_GT(1UL << 38, (unsigned long)mmap_addresses.on_37_addr); + EXPECT_GT(1UL << 38, (unsigned long)mmap_addresses.on_38_addr); + EXPECT_GT(1UL << 38, (unsigned long)mmap_addresses.on_46_addr); + EXPECT_GT(1UL << 47, (unsigned long)mmap_addresses.on_47_addr); + EXPECT_GT(1UL << 47, (unsigned long)mmap_addresses.on_55_addr); + EXPECT_GT(1UL << 56, (unsigned long)mmap_addresses.on_56_addr); +#endif +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/riscv/mm/testcases/mmap_test.h b/tools/testing/selftests/riscv/mm/testcases/mmap_test.h new file mode 100644 index 000000000000..9b8434f62f57 --- /dev/null +++ b/tools/testing/selftests/riscv/mm/testcases/mmap_test.h @@ -0,0 +1,64 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _TESTCASES_MMAP_TEST_H +#define _TESTCASES_MMAP_TEST_H +#include <sys/mman.h> +#include <sys/resource.h> +#include <stddef.h> + +#define TOP_DOWN 0 +#define BOTTOM_UP 1 + +struct addresses { + int *no_hint; + int *on_37_addr; + int *on_38_addr; + int *on_46_addr; + int *on_47_addr; + int *on_55_addr; + int *on_56_addr; +}; + +static inline void do_mmaps(struct addresses *mmap_addresses) +{ + /* + * Place all of the hint addresses on the boundaries of mmap + * sv39, sv48, sv57 + * User addresses end at 1<<38, 1<<47, 1<<56 respectively + */ + void *on_37_bits = (void *)(1UL << 37); + void *on_38_bits = (void *)(1UL << 38); + void *on_46_bits = (void *)(1UL << 46); + void *on_47_bits = (void *)(1UL << 47); + void *on_55_bits = (void *)(1UL << 55); + void *on_56_bits = (void *)(1UL << 56); + + int prot = PROT_READ | PROT_WRITE; + int flags = MAP_PRIVATE | MAP_ANONYMOUS; + + mmap_addresses->no_hint = + mmap(NULL, 5 * sizeof(int), prot, flags, 0, 0); + mmap_addresses->on_37_addr = + mmap(on_37_bits, 5 * sizeof(int), prot, flags, 0, 0); + mmap_addresses->on_38_addr = + mmap(on_38_bits, 5 * sizeof(int), prot, flags, 0, 0); + mmap_addresses->on_46_addr = + mmap(on_46_bits, 5 * sizeof(int), prot, flags, 0, 0); + mmap_addresses->on_47_addr = + mmap(on_47_bits, 5 * sizeof(int), prot, flags, 0, 0); + mmap_addresses->on_55_addr = + mmap(on_55_bits, 5 * sizeof(int), prot, flags, 0, 0); + mmap_addresses->on_56_addr = + mmap(on_56_bits, 5 * sizeof(int), prot, flags, 0, 0); +} + +static inline int memory_layout(void) +{ + int prot = PROT_READ | PROT_WRITE; + int flags = MAP_PRIVATE | MAP_ANONYMOUS; + + void *value1 = mmap(NULL, sizeof(int), prot, flags, 0, 0); + void *value2 = mmap(NULL, sizeof(int), prot, flags, 0, 0); + + return value2 > value1; +} +#endif /* _TESTCASES_MMAP_TEST_H */ diff --git a/tools/testing/selftests/riscv/mm/testcases/run_mmap.sh b/tools/testing/selftests/riscv/mm/testcases/run_mmap.sh new file mode 100755 index 000000000000..ca5ad7c48bad --- /dev/null +++ b/tools/testing/selftests/riscv/mm/testcases/run_mmap.sh @@ -0,0 +1,12 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 + +original_stack_limit=$(ulimit -s) + +./mmap_default + +# Force mmap_bottomup to be ran with bottomup memory due to +# the unlimited stack +ulimit -s unlimited +./mmap_bottomup +ulimit -s $original_stack_limit diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile index 7a957c7d459a..5a3432fceb58 100644 --- a/tools/testing/selftests/rseq/Makefile +++ b/tools/testing/selftests/rseq/Makefile @@ -33,7 +33,7 @@ $(OUTPUT)/%: %.c $(TEST_GEN_PROGS_EXTENDED) rseq.h rseq-*.h $(CC) $(CFLAGS) $< $(LDLIBS) -lrseq -o $@ $(OUTPUT)/basic_percpu_ops_mm_cid_test: basic_percpu_ops_test.c $(TEST_GEN_PROGS_EXTENDED) rseq.h rseq-*.h - $(CC) $(CFLAGS) -DBUILDOPT_RSEQ_PERCPU_MM_CID_ID $< $(LDLIBS) -lrseq -o $@ + $(CC) $(CFLAGS) -DBUILDOPT_RSEQ_PERCPU_MM_CID $< $(LDLIBS) -lrseq -o $@ $(OUTPUT)/param_test_benchmark: param_test.c $(TEST_GEN_PROGS_EXTENDED) \ rseq.h rseq-*.h diff --git a/tools/testing/selftests/rseq/compiler.h b/tools/testing/selftests/rseq/compiler.h index f47092bddeba..49d62fbd6dda 100644 --- a/tools/testing/selftests/rseq/compiler.h +++ b/tools/testing/selftests/rseq/compiler.h @@ -33,4 +33,30 @@ #define RSEQ_COMBINE_TOKENS(_tokena, _tokenb) \ RSEQ__COMBINE_TOKENS(_tokena, _tokenb) +#ifdef __cplusplus +#define rseq_unqual_scalar_typeof(x) \ + std::remove_cv<std::remove_reference<decltype(x)>::type>::type +#else +#define rseq_scalar_type_to_expr(type) \ + unsigned type: (unsigned type)0, \ + signed type: (signed type)0 + +/* + * Use C11 _Generic to express unqualified type from expression. This removes + * volatile qualifier from expression type. + */ +#define rseq_unqual_scalar_typeof(x) \ + __typeof__( \ + _Generic((x), \ + char: (char)0, \ + rseq_scalar_type_to_expr(char), \ + rseq_scalar_type_to_expr(short), \ + rseq_scalar_type_to_expr(int), \ + rseq_scalar_type_to_expr(long), \ + rseq_scalar_type_to_expr(long long), \ + default: (x) \ + ) \ + ) +#endif + #endif /* RSEQ_COMPILER_H_ */ diff --git a/tools/testing/selftests/rseq/rseq-arm.h b/tools/testing/selftests/rseq/rseq-arm.h index 8414fc3eac15..d887b3bbe257 100644 --- a/tools/testing/selftests/rseq/rseq-arm.h +++ b/tools/testing/selftests/rseq/rseq-arm.h @@ -66,7 +66,7 @@ #define rseq_smp_load_acquire(p) \ __extension__ ({ \ - __typeof(*p) ____p1 = RSEQ_READ_ONCE(*p); \ + rseq_unqual_scalar_typeof(*(p)) ____p1 = RSEQ_READ_ONCE(*(p)); \ rseq_smp_mb(); \ ____p1; \ }) @@ -76,7 +76,7 @@ __extension__ ({ \ #define rseq_smp_store_release(p, v) \ do { \ rseq_smp_mb(); \ - RSEQ_WRITE_ONCE(*p, v); \ + RSEQ_WRITE_ONCE(*(p), v); \ } while (0) #define __RSEQ_ASM_DEFINE_TABLE(label, version, flags, start_ip, \ diff --git a/tools/testing/selftests/rseq/rseq-arm64.h b/tools/testing/selftests/rseq/rseq-arm64.h index 85b90977e7e6..21e1626a7235 100644 --- a/tools/testing/selftests/rseq/rseq-arm64.h +++ b/tools/testing/selftests/rseq/rseq-arm64.h @@ -27,59 +27,61 @@ #define rseq_smp_load_acquire(p) \ __extension__ ({ \ - __typeof(*p) ____p1; \ - switch (sizeof(*p)) { \ + union { rseq_unqual_scalar_typeof(*(p)) __val; char __c[sizeof(*(p))]; } __u; \ + switch (sizeof(*(p))) { \ case 1: \ - asm volatile ("ldarb %w0, %1" \ - : "=r" (*(__u8 *)p) \ - : "Q" (*p) : "memory"); \ + __asm__ __volatile__ ("ldarb %w0, %1" \ + : "=r" (*(__u8 *)__u.__c) \ + : "Q" (*(p)) : "memory"); \ break; \ case 2: \ - asm volatile ("ldarh %w0, %1" \ - : "=r" (*(__u16 *)p) \ - : "Q" (*p) : "memory"); \ + __asm__ __volatile__ ("ldarh %w0, %1" \ + : "=r" (*(__u16 *)__u.__c) \ + : "Q" (*(p)) : "memory"); \ break; \ case 4: \ - asm volatile ("ldar %w0, %1" \ - : "=r" (*(__u32 *)p) \ - : "Q" (*p) : "memory"); \ + __asm__ __volatile__ ("ldar %w0, %1" \ + : "=r" (*(__u32 *)__u.__c) \ + : "Q" (*(p)) : "memory"); \ break; \ case 8: \ - asm volatile ("ldar %0, %1" \ - : "=r" (*(__u64 *)p) \ - : "Q" (*p) : "memory"); \ + __asm__ __volatile__ ("ldar %0, %1" \ + : "=r" (*(__u64 *)__u.__c) \ + : "Q" (*(p)) : "memory"); \ break; \ } \ - ____p1; \ + (rseq_unqual_scalar_typeof(*(p)))__u.__val; \ }) #define rseq_smp_acquire__after_ctrl_dep() rseq_smp_rmb() #define rseq_smp_store_release(p, v) \ do { \ - switch (sizeof(*p)) { \ + union { rseq_unqual_scalar_typeof(*(p)) __val; char __c[sizeof(*(p))]; } __u = \ + { .__val = (rseq_unqual_scalar_typeof(*(p))) (v) }; \ + switch (sizeof(*(p))) { \ case 1: \ - asm volatile ("stlrb %w1, %0" \ - : "=Q" (*p) \ - : "r" ((__u8)v) \ + __asm__ __volatile__ ("stlrb %w1, %0" \ + : "=Q" (*(p)) \ + : "r" (*(__u8 *)__u.__c) \ : "memory"); \ break; \ case 2: \ - asm volatile ("stlrh %w1, %0" \ - : "=Q" (*p) \ - : "r" ((__u16)v) \ + __asm__ __volatile__ ("stlrh %w1, %0" \ + : "=Q" (*(p)) \ + : "r" (*(__u16 *)__u.__c) \ : "memory"); \ break; \ case 4: \ - asm volatile ("stlr %w1, %0" \ - : "=Q" (*p) \ - : "r" ((__u32)v) \ + __asm__ __volatile__ ("stlr %w1, %0" \ + : "=Q" (*(p)) \ + : "r" (*(__u32 *)__u.__c) \ : "memory"); \ break; \ case 8: \ - asm volatile ("stlr %1, %0" \ - : "=Q" (*p) \ - : "r" ((__u64)v) \ + __asm__ __volatile__ ("stlr %1, %0" \ + : "=Q" (*(p)) \ + : "r" (*(__u64 *)__u.__c) \ : "memory"); \ break; \ } \ diff --git a/tools/testing/selftests/rseq/rseq-mips.h b/tools/testing/selftests/rseq/rseq-mips.h index 50b950cf9585..42ef8e946693 100644 --- a/tools/testing/selftests/rseq/rseq-mips.h +++ b/tools/testing/selftests/rseq/rseq-mips.h @@ -45,7 +45,7 @@ #define rseq_smp_load_acquire(p) \ __extension__ ({ \ - __typeof(*p) ____p1 = RSEQ_READ_ONCE(*p); \ + rseq_unqual_scalar_typeof(*(p)) ____p1 = RSEQ_READ_ONCE(*(p)); \ rseq_smp_mb(); \ ____p1; \ }) @@ -55,7 +55,7 @@ __extension__ ({ \ #define rseq_smp_store_release(p, v) \ do { \ rseq_smp_mb(); \ - RSEQ_WRITE_ONCE(*p, v); \ + RSEQ_WRITE_ONCE(*(p), v); \ } while (0) #if _MIPS_SZLONG == 64 diff --git a/tools/testing/selftests/rseq/rseq-ppc.h b/tools/testing/selftests/rseq/rseq-ppc.h index dc9190facee9..57b160597189 100644 --- a/tools/testing/selftests/rseq/rseq-ppc.h +++ b/tools/testing/selftests/rseq/rseq-ppc.h @@ -23,7 +23,7 @@ #define rseq_smp_load_acquire(p) \ __extension__ ({ \ - __typeof(*p) ____p1 = RSEQ_READ_ONCE(*p); \ + rseq_unqual_scalar_typeof(*(p)) ____p1 = RSEQ_READ_ONCE(*(p)); \ rseq_smp_lwsync(); \ ____p1; \ }) @@ -33,7 +33,7 @@ __extension__ ({ \ #define rseq_smp_store_release(p, v) \ do { \ rseq_smp_lwsync(); \ - RSEQ_WRITE_ONCE(*p, v); \ + RSEQ_WRITE_ONCE(*(p), v); \ } while (0) /* diff --git a/tools/testing/selftests/rseq/rseq-riscv.h b/tools/testing/selftests/rseq/rseq-riscv.h index 17932a79e066..37e598d0a365 100644 --- a/tools/testing/selftests/rseq/rseq-riscv.h +++ b/tools/testing/selftests/rseq/rseq-riscv.h @@ -36,8 +36,8 @@ #define rseq_smp_load_acquire(p) \ __extension__ ({ \ - __typeof(*(p)) ____p1 = RSEQ_READ_ONCE(*(p)); \ - RISCV_FENCE(r, rw) \ + rseq_unqual_scalar_typeof(*(p)) ____p1 = RSEQ_READ_ONCE(*(p)); \ + RISCV_FENCE(r, rw); \ ____p1; \ }) @@ -46,7 +46,7 @@ __extension__ ({ \ #define rseq_smp_store_release(p, v) \ do { \ RISCV_FENCE(rw, w); \ - RSEQ_WRITE_ONCE(*(p), v); \ + RSEQ_WRITE_ONCE(*(p), v); \ } while (0) #define __RSEQ_ASM_DEFINE_TABLE(label, version, flags, start_ip, \ diff --git a/tools/testing/selftests/rseq/rseq-s390.h b/tools/testing/selftests/rseq/rseq-s390.h index 46c92598acc7..33baaa9f9997 100644 --- a/tools/testing/selftests/rseq/rseq-s390.h +++ b/tools/testing/selftests/rseq/rseq-s390.h @@ -15,7 +15,7 @@ #define rseq_smp_load_acquire(p) \ __extension__ ({ \ - __typeof(*p) ____p1 = RSEQ_READ_ONCE(*p); \ + rseq_unqual_scalar_typeof(*(p)) ____p1 = RSEQ_READ_ONCE(*(p)); \ rseq_barrier(); \ ____p1; \ }) @@ -25,7 +25,7 @@ __extension__ ({ \ #define rseq_smp_store_release(p, v) \ do { \ rseq_barrier(); \ - RSEQ_WRITE_ONCE(*p, v); \ + RSEQ_WRITE_ONCE(*(p), v); \ } while (0) #ifdef __s390x__ diff --git a/tools/testing/selftests/rseq/rseq-x86.h b/tools/testing/selftests/rseq/rseq-x86.h index fb65ef54b0fb..a2aa428ba151 100644 --- a/tools/testing/selftests/rseq/rseq-x86.h +++ b/tools/testing/selftests/rseq/rseq-x86.h @@ -42,7 +42,7 @@ #define rseq_smp_load_acquire(p) \ __extension__ ({ \ - __typeof(*p) ____p1 = RSEQ_READ_ONCE(*p); \ + rseq_unqual_scalar_typeof(*(p)) ____p1 = RSEQ_READ_ONCE(*(p)); \ rseq_barrier(); \ ____p1; \ }) @@ -52,7 +52,7 @@ __extension__ ({ \ #define rseq_smp_store_release(p, v) \ do { \ rseq_barrier(); \ - RSEQ_WRITE_ONCE(*p, v); \ + RSEQ_WRITE_ONCE(*(p), v); \ } while (0) #define __RSEQ_ASM_DEFINE_TABLE(label, version, flags, \ diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 43ec36b179dc..38f651469968 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -2184,6 +2184,9 @@ FIXTURE_TEARDOWN(TRACE_syscall) TEST(negative_ENOSYS) { +#if defined(__arm__) + SKIP(return, "arm32 does not support calling syscall -1"); +#endif /* * There should be no difference between an "internal" skip * and userspace asking for syscall "-1". @@ -3072,7 +3075,8 @@ TEST(syscall_restart) timeout.tv_sec = 1; errno = 0; EXPECT_EQ(0, nanosleep(&timeout, NULL)) { - TH_LOG("Call to nanosleep() failed (errno %d)", errno); + TH_LOG("Call to nanosleep() failed (errno %d: %s)", + errno, strerror(errno)); } /* Read final sync from parent. */ @@ -3908,6 +3912,9 @@ TEST(user_notification_filter_empty) TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); } + if (__NR_clone3 < 0) + SKIP(return, "Test not built with clone3 support"); + pid = sys_clone3(&args, sizeof(args)); ASSERT_GE(pid, 0); @@ -3962,6 +3969,9 @@ TEST(user_notification_filter_empty_threaded) TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); } + if (__NR_clone3 < 0) + SKIP(return, "Test not built with clone3 support"); + pid = sys_clone3(&args, sizeof(args)); ASSERT_GE(pid, 0); @@ -4255,6 +4265,61 @@ TEST(user_notification_addfd_rlimit) close(memfd); } +#ifndef SECCOMP_USER_NOTIF_FD_SYNC_WAKE_UP +#define SECCOMP_USER_NOTIF_FD_SYNC_WAKE_UP (1UL << 0) +#define SECCOMP_IOCTL_NOTIF_SET_FLAGS SECCOMP_IOW(4, __u64) +#endif + +TEST(user_notification_sync) +{ + struct seccomp_notif req = {}; + struct seccomp_notif_resp resp = {}; + int status, listener; + pid_t pid; + long ret; + + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret) { + TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); + } + + listener = user_notif_syscall(__NR_getppid, + SECCOMP_FILTER_FLAG_NEW_LISTENER); + ASSERT_GE(listener, 0); + + /* Try to set invalid flags. */ + EXPECT_SYSCALL_RETURN(-EINVAL, + ioctl(listener, SECCOMP_IOCTL_NOTIF_SET_FLAGS, 0xffffffff, 0)); + + ASSERT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SET_FLAGS, + SECCOMP_USER_NOTIF_FD_SYNC_WAKE_UP, 0), 0); + + pid = fork(); + ASSERT_GE(pid, 0); + if (pid == 0) { + ret = syscall(__NR_getppid); + ASSERT_EQ(ret, USER_NOTIF_MAGIC) { + _exit(1); + } + _exit(0); + } + + req.pid = 0; + ASSERT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0); + + ASSERT_EQ(req.data.nr, __NR_getppid); + + resp.id = req.id; + resp.error = 0; + resp.val = USER_NOTIF_MAGIC; + resp.flags = 0; + ASSERT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0); + + ASSERT_EQ(waitpid(pid, &status, 0), pid); + ASSERT_EQ(status, 0); +} + + /* Make sure PTRACE_O_SUSPEND_SECCOMP requires CAP_SYS_ADMIN. */ FIXTURE(O_SUSPEND_SECCOMP) { pid_t pid; diff --git a/tools/testing/selftests/tc-testing/Makefile b/tools/testing/selftests/tc-testing/Makefile index cb553eac9f41..3c4b7fa05075 100644 --- a/tools/testing/selftests/tc-testing/Makefile +++ b/tools/testing/selftests/tc-testing/Makefile @@ -24,7 +24,7 @@ CLANG_FLAGS = -I. -I$(APIDIR) \ $(OUTPUT)/%.o: %.c $(CLANG) $(CLANG_FLAGS) \ - -O2 -target bpf -emit-llvm -c $< -o - | \ + -O2 --target=bpf -emit-llvm -c $< -o - | \ $(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@ TEST_PROGS += ./tdc.sh diff --git a/tools/testing/selftests/tc-testing/config b/tools/testing/selftests/tc-testing/config index 71706197ba0f..5aa8705751f0 100644 --- a/tools/testing/selftests/tc-testing/config +++ b/tools/testing/selftests/tc-testing/config @@ -96,10 +96,11 @@ CONFIG_NET_SCH_FIFO=y CONFIG_NET_SCH_ETS=m CONFIG_NET_SCH_RED=m CONFIG_NET_SCH_FQ_PIE=m -CONFIG_NETDEVSIM=m # ## Network testing # CONFIG_CAN=m CONFIG_ATM=y +CONFIG_NETDEVSIM=m +CONFIG_PTP_1588_CLOCK_MOCK=m diff --git a/tools/testing/selftests/tc-testing/taprio_wait_for_admin.sh b/tools/testing/selftests/tc-testing/taprio_wait_for_admin.sh new file mode 100755 index 000000000000..f5335e8ad6b4 --- /dev/null +++ b/tools/testing/selftests/tc-testing/taprio_wait_for_admin.sh @@ -0,0 +1,16 @@ +#!/bin/bash + +TC="$1"; shift +ETH="$1"; shift + +# The taprio architecture changes the admin schedule from a hrtimer and not +# from process context, so we need to wait in order to make sure that any +# schedule change actually took place. +while :; do + has_admin="$($TC -j qdisc show dev $ETH root | jq '.[].options | has("admin")')" + if [ "$has_admin" = "false" ]; then + break; + fi + + sleep 1 +done diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json index 08d4861c2e78..0599635c4bc6 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json @@ -104,7 +104,7 @@ "cmdUnderTest": "$TC qdisc add dev $ETH root handle 1: taprio num_tc 3 map 2 2 1 0 2 2 2 2 2 2 2 2 2 2 2 2 queues 1@0 1@0 1@0 base-time 1000000000 sched-entry S 01 300000 flags 0x1 clockid CLOCK_TAI", "expExitCode": "0", "verifyCmd": "$TC class show dev $ETH", - "matchPattern": "class taprio 1:[0-9]+ root leaf 1:", + "matchPattern": "class taprio 1:[0-9]+ root", "matchCount": "8", "teardown": [ "echo \"1\" > /sys/bus/netdevsim/del_device" @@ -156,5 +156,105 @@ "teardown": [ "echo \"1\" > /sys/bus/netdevsim/del_device" ] + }, + { + "id": "39b4", + "name": "Reject grafting taprio as child qdisc of software taprio", + "category": [ + "qdisc", + "taprio" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "echo \"1 1 8\" > /sys/bus/netdevsim/new_device", + "$TC qdisc replace dev $ETH handle 8001: parent root stab overhead 24 taprio num_tc 8 map 0 1 2 3 4 5 6 7 queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 base-time 0 sched-entry S ff 20000000 clockid CLOCK_TAI", + "./taprio_wait_for_admin.sh $TC $ETH" + ], + "cmdUnderTest": "$TC qdisc replace dev $ETH parent 8001:7 taprio num_tc 8 map 0 1 2 3 4 5 6 7 queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 base-time 200 sched-entry S ff 20000000 clockid CLOCK_TAI", + "expExitCode": "2", + "verifyCmd": "bash -c \"./taprio_wait_for_admin.sh $TC $ETH && $TC -j qdisc show dev $ETH root | jq '.[].options.base_time'\"", + "matchPattern": "0", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $ETH root", + "echo \"1\" > /sys/bus/netdevsim/del_device" + ] + }, + { + "id": "e8a1", + "name": "Reject grafting taprio as child qdisc of offloaded taprio", + "category": [ + "qdisc", + "taprio" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "echo \"1 1 8\" > /sys/bus/netdevsim/new_device", + "$TC qdisc replace dev $ETH handle 8001: parent root stab overhead 24 taprio num_tc 8 map 0 1 2 3 4 5 6 7 queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 base-time 0 sched-entry S ff 20000000 flags 0x2", + "./taprio_wait_for_admin.sh $TC $ETH" + ], + "cmdUnderTest": "$TC qdisc replace dev $ETH parent 8001:7 taprio num_tc 8 map 0 1 2 3 4 5 6 7 queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 base-time 200 sched-entry S ff 20000000 flags 0x2", + "expExitCode": "2", + "verifyCmd": "bash -c \"./taprio_wait_for_admin.sh $TC $ETH && $TC -j qdisc show dev $ETH root | jq '.[].options.base_time'\"", + "matchPattern": "0", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $ETH root", + "echo \"1\" > /sys/bus/netdevsim/del_device" + ] + }, + { + "id": "a7bf", + "name": "Graft cbs as child of software taprio", + "category": [ + "qdisc", + "taprio", + "cbs" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "echo \"1 1 8\" > /sys/bus/netdevsim/new_device", + "$TC qdisc replace dev $ETH handle 8001: parent root stab overhead 24 taprio num_tc 8 map 0 1 2 3 4 5 6 7 queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 base-time 0 sched-entry S ff 20000000 clockid CLOCK_TAI" + ], + "cmdUnderTest": "$TC qdisc replace dev $ETH handle 8002: parent 8001:8 cbs idleslope 20000 sendslope -980000 hicredit 30 locredit -1470", + "expExitCode": "0", + "verifyCmd": "$TC -d qdisc show dev $ETH", + "matchPattern": "qdisc cbs 8002: parent 8001:8 hicredit 30 locredit -1470 sendslope -980000 idleslope 20000 offload 0", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $ETH root", + "echo \"1\" > /sys/bus/netdevsim/del_device" + ] + }, + { + "id": "6a83", + "name": "Graft cbs as child of offloaded taprio", + "category": [ + "qdisc", + "taprio", + "cbs" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "echo \"1 1 8\" > /sys/bus/netdevsim/new_device", + "$TC qdisc replace dev $ETH handle 8001: parent root stab overhead 24 taprio num_tc 8 map 0 1 2 3 4 5 6 7 queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 base-time 0 sched-entry S ff 20000000 flags 0x2" + ], + "cmdUnderTest": "$TC qdisc replace dev $ETH handle 8002: parent 8001:8 cbs idleslope 20000 sendslope -980000 hicredit 30 locredit -1470", + "expExitCode": "0", + "verifyCmd": "$TC -d qdisc show dev $ETH", + "matchPattern": "qdisc cbs 8002: parent 8001:8 refcnt 2 hicredit 30 locredit -1470 sendslope -980000 idleslope 20000 offload 0", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $ETH root", + "echo \"1\" > /sys/bus/netdevsim/del_device" + ] } ] diff --git a/tools/testing/selftests/user_events/Makefile b/tools/testing/selftests/user_events/Makefile index 9e95bd41b0b4..10fcd0066203 100644 --- a/tools/testing/selftests/user_events/Makefile +++ b/tools/testing/selftests/user_events/Makefile @@ -2,14 +2,6 @@ CFLAGS += -Wl,-no-as-needed -Wall $(KHDR_INCLUDES) LDLIBS += -lrt -lpthread -lm -# Note: -# This test depends on <linux/user_events.h> exported in uapi -# The following commit removed user_events.h out of uapi: -# commit 5cfff569cab8bf544bab62c911c5d6efd5af5e05 -# tracing: Move user_events.h temporarily out of include/uapi -# This test will not compile until user_events.h is added -# back to uapi. - TEST_GEN_PROGS = ftrace_test dyn_test perf_test abi_test TEST_FILES := settings diff --git a/tools/testing/selftests/wireguard/qemu/kernel.config b/tools/testing/selftests/wireguard/qemu/kernel.config index 6327c9c400e0..507555714b1d 100644 --- a/tools/testing/selftests/wireguard/qemu/kernel.config +++ b/tools/testing/selftests/wireguard/qemu/kernel.config @@ -41,7 +41,6 @@ CONFIG_KALLSYMS=y CONFIG_BUG=y CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE=y CONFIG_JUMP_LABEL=y -CONFIG_EMBEDDED=n CONFIG_BASE_FULL=y CONFIG_FUTEX=y CONFIG_SHMEM=y diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index 598135d3162b..7e8c937627dd 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -18,7 +18,7 @@ TARGETS_C_32BIT_ONLY := entry_from_vm86 test_syscall_vdso unwind_vdso \ test_FCMOV test_FCOMI test_FISTTP \ vdso_restorer TARGETS_C_64BIT_ONLY := fsgsbase sysret_rip syscall_numbering \ - corrupt_xstate_header amx lam + corrupt_xstate_header amx lam test_shadow_stack # Some selftests require 32bit support enabled also on 64bit systems TARGETS_C_32BIT_NEEDED := ldt_gdt ptrace_syscall diff --git a/tools/testing/selftests/x86/test_shadow_stack.c b/tools/testing/selftests/x86/test_shadow_stack.c new file mode 100644 index 000000000000..757e6527f67e --- /dev/null +++ b/tools/testing/selftests/x86/test_shadow_stack.c @@ -0,0 +1,884 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This program test's basic kernel shadow stack support. It enables shadow + * stack manual via the arch_prctl(), instead of relying on glibc. It's + * Makefile doesn't compile with shadow stack support, so it doesn't rely on + * any particular glibc. As a result it can't do any operations that require + * special glibc shadow stack support (longjmp(), swapcontext(), etc). Just + * stick to the basics and hope the compiler doesn't do anything strange. + */ + +#define _GNU_SOURCE + +#include <sys/syscall.h> +#include <asm/mman.h> +#include <sys/mman.h> +#include <sys/stat.h> +#include <sys/wait.h> +#include <stdio.h> +#include <stdlib.h> +#include <fcntl.h> +#include <unistd.h> +#include <string.h> +#include <errno.h> +#include <stdbool.h> +#include <x86intrin.h> +#include <asm/prctl.h> +#include <sys/prctl.h> +#include <stdint.h> +#include <signal.h> +#include <pthread.h> +#include <sys/ioctl.h> +#include <linux/userfaultfd.h> +#include <setjmp.h> +#include <sys/ptrace.h> +#include <sys/signal.h> +#include <linux/elf.h> + +/* + * Define the ABI defines if needed, so people can run the tests + * without building the headers. + */ +#ifndef __NR_map_shadow_stack +#define __NR_map_shadow_stack 453 + +#define SHADOW_STACK_SET_TOKEN (1ULL << 0) + +#define ARCH_SHSTK_ENABLE 0x5001 +#define ARCH_SHSTK_DISABLE 0x5002 +#define ARCH_SHSTK_LOCK 0x5003 +#define ARCH_SHSTK_UNLOCK 0x5004 +#define ARCH_SHSTK_STATUS 0x5005 + +#define ARCH_SHSTK_SHSTK (1ULL << 0) +#define ARCH_SHSTK_WRSS (1ULL << 1) + +#define NT_X86_SHSTK 0x204 +#endif + +#define SS_SIZE 0x200000 +#define PAGE_SIZE 0x1000 + +#if (__GNUC__ < 8) || (__GNUC__ == 8 && __GNUC_MINOR__ < 5) +int main(int argc, char *argv[]) +{ + printf("[SKIP]\tCompiler does not support CET.\n"); + return 0; +} +#else +void write_shstk(unsigned long *addr, unsigned long val) +{ + asm volatile("wrssq %[val], (%[addr])\n" + : "=m" (addr) + : [addr] "r" (addr), [val] "r" (val)); +} + +static inline unsigned long __attribute__((always_inline)) get_ssp(void) +{ + unsigned long ret = 0; + + asm volatile("xor %0, %0; rdsspq %0" : "=r" (ret)); + return ret; +} + +/* + * For use in inline enablement of shadow stack. + * + * The program can't return from the point where shadow stack gets enabled + * because there will be no address on the shadow stack. So it can't use + * syscall() for enablement, since it is a function. + * + * Based on code from nolibc.h. Keep a copy here because this can't pull in all + * of nolibc.h. + */ +#define ARCH_PRCTL(arg1, arg2) \ +({ \ + long _ret; \ + register long _num asm("eax") = __NR_arch_prctl; \ + register long _arg1 asm("rdi") = (long)(arg1); \ + register long _arg2 asm("rsi") = (long)(arg2); \ + \ + asm volatile ( \ + "syscall\n" \ + : "=a"(_ret) \ + : "r"(_arg1), "r"(_arg2), \ + "0"(_num) \ + : "rcx", "r11", "memory", "cc" \ + ); \ + _ret; \ +}) + +void *create_shstk(void *addr) +{ + return (void *)syscall(__NR_map_shadow_stack, addr, SS_SIZE, SHADOW_STACK_SET_TOKEN); +} + +void *create_normal_mem(void *addr) +{ + return mmap(addr, SS_SIZE, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, 0, 0); +} + +void free_shstk(void *shstk) +{ + munmap(shstk, SS_SIZE); +} + +int reset_shstk(void *shstk) +{ + return madvise(shstk, SS_SIZE, MADV_DONTNEED); +} + +void try_shstk(unsigned long new_ssp) +{ + unsigned long ssp; + + printf("[INFO]\tnew_ssp = %lx, *new_ssp = %lx\n", + new_ssp, *((unsigned long *)new_ssp)); + + ssp = get_ssp(); + printf("[INFO]\tchanging ssp from %lx to %lx\n", ssp, new_ssp); + + asm volatile("rstorssp (%0)\n":: "r" (new_ssp)); + asm volatile("saveprevssp"); + printf("[INFO]\tssp is now %lx\n", get_ssp()); + + /* Switch back to original shadow stack */ + ssp -= 8; + asm volatile("rstorssp (%0)\n":: "r" (ssp)); + asm volatile("saveprevssp"); +} + +int test_shstk_pivot(void) +{ + void *shstk = create_shstk(0); + + if (shstk == MAP_FAILED) { + printf("[FAIL]\tError creating shadow stack: %d\n", errno); + return 1; + } + try_shstk((unsigned long)shstk + SS_SIZE - 8); + free_shstk(shstk); + + printf("[OK]\tShadow stack pivot\n"); + return 0; +} + +int test_shstk_faults(void) +{ + unsigned long *shstk = create_shstk(0); + + /* Read shadow stack, test if it's zero to not get read optimized out */ + if (*shstk != 0) + goto err; + + /* Wrss memory that was already read. */ + write_shstk(shstk, 1); + if (*shstk != 1) + goto err; + + /* Page out memory, so we can wrss it again. */ + if (reset_shstk((void *)shstk)) + goto err; + + write_shstk(shstk, 1); + if (*shstk != 1) + goto err; + + printf("[OK]\tShadow stack faults\n"); + return 0; + +err: + return 1; +} + +unsigned long saved_ssp; +unsigned long saved_ssp_val; +volatile bool segv_triggered; + +void __attribute__((noinline)) violate_ss(void) +{ + saved_ssp = get_ssp(); + saved_ssp_val = *(unsigned long *)saved_ssp; + + /* Corrupt shadow stack */ + printf("[INFO]\tCorrupting shadow stack\n"); + write_shstk((void *)saved_ssp, 0); +} + +void segv_handler(int signum, siginfo_t *si, void *uc) +{ + printf("[INFO]\tGenerated shadow stack violation successfully\n"); + + segv_triggered = true; + + /* Fix shadow stack */ + write_shstk((void *)saved_ssp, saved_ssp_val); +} + +int test_shstk_violation(void) +{ + struct sigaction sa = {}; + + sa.sa_sigaction = segv_handler; + sa.sa_flags = SA_SIGINFO; + if (sigaction(SIGSEGV, &sa, NULL)) + return 1; + + segv_triggered = false; + + /* Make sure segv_triggered is set before violate_ss() */ + asm volatile("" : : : "memory"); + + violate_ss(); + + signal(SIGSEGV, SIG_DFL); + + printf("[OK]\tShadow stack violation test\n"); + + return !segv_triggered; +} + +/* Gup test state */ +#define MAGIC_VAL 0x12345678 +bool is_shstk_access; +void *shstk_ptr; +int fd; + +void reset_test_shstk(void *addr) +{ + if (shstk_ptr) + free_shstk(shstk_ptr); + shstk_ptr = create_shstk(addr); +} + +void test_access_fix_handler(int signum, siginfo_t *si, void *uc) +{ + printf("[INFO]\tViolation from %s\n", is_shstk_access ? "shstk access" : "normal write"); + + segv_triggered = true; + + /* Fix shadow stack */ + if (is_shstk_access) { + reset_test_shstk(shstk_ptr); + return; + } + + free_shstk(shstk_ptr); + create_normal_mem(shstk_ptr); +} + +bool test_shstk_access(void *ptr) +{ + is_shstk_access = true; + segv_triggered = false; + write_shstk(ptr, MAGIC_VAL); + + asm volatile("" : : : "memory"); + + return segv_triggered; +} + +bool test_write_access(void *ptr) +{ + is_shstk_access = false; + segv_triggered = false; + *(unsigned long *)ptr = MAGIC_VAL; + + asm volatile("" : : : "memory"); + + return segv_triggered; +} + +bool gup_write(void *ptr) +{ + unsigned long val; + + lseek(fd, (unsigned long)ptr, SEEK_SET); + if (write(fd, &val, sizeof(val)) < 0) + return 1; + + return 0; +} + +bool gup_read(void *ptr) +{ + unsigned long val; + + lseek(fd, (unsigned long)ptr, SEEK_SET); + if (read(fd, &val, sizeof(val)) < 0) + return 1; + + return 0; +} + +int test_gup(void) +{ + struct sigaction sa = {}; + int status; + pid_t pid; + + sa.sa_sigaction = test_access_fix_handler; + sa.sa_flags = SA_SIGINFO; + if (sigaction(SIGSEGV, &sa, NULL)) + return 1; + + segv_triggered = false; + + fd = open("/proc/self/mem", O_RDWR); + if (fd == -1) + return 1; + + reset_test_shstk(0); + if (gup_read(shstk_ptr)) + return 1; + if (test_shstk_access(shstk_ptr)) + return 1; + printf("[INFO]\tGup read -> shstk access success\n"); + + reset_test_shstk(0); + if (gup_write(shstk_ptr)) + return 1; + if (test_shstk_access(shstk_ptr)) + return 1; + printf("[INFO]\tGup write -> shstk access success\n"); + + reset_test_shstk(0); + if (gup_read(shstk_ptr)) + return 1; + if (!test_write_access(shstk_ptr)) + return 1; + printf("[INFO]\tGup read -> write access success\n"); + + reset_test_shstk(0); + if (gup_write(shstk_ptr)) + return 1; + if (!test_write_access(shstk_ptr)) + return 1; + printf("[INFO]\tGup write -> write access success\n"); + + close(fd); + + /* COW/gup test */ + reset_test_shstk(0); + pid = fork(); + if (!pid) { + fd = open("/proc/self/mem", O_RDWR); + if (fd == -1) + exit(1); + + if (gup_write(shstk_ptr)) { + close(fd); + exit(1); + } + close(fd); + exit(0); + } + waitpid(pid, &status, 0); + if (WEXITSTATUS(status)) { + printf("[FAIL]\tWrite in child failed\n"); + return 1; + } + if (*(unsigned long *)shstk_ptr == MAGIC_VAL) { + printf("[FAIL]\tWrite in child wrote through to shared memory\n"); + return 1; + } + + printf("[INFO]\tCow gup write -> write access success\n"); + + free_shstk(shstk_ptr); + + signal(SIGSEGV, SIG_DFL); + + printf("[OK]\tShadow gup test\n"); + + return 0; +} + +int test_mprotect(void) +{ + struct sigaction sa = {}; + + sa.sa_sigaction = test_access_fix_handler; + sa.sa_flags = SA_SIGINFO; + if (sigaction(SIGSEGV, &sa, NULL)) + return 1; + + segv_triggered = false; + + /* mprotect a shadow stack as read only */ + reset_test_shstk(0); + if (mprotect(shstk_ptr, SS_SIZE, PROT_READ) < 0) { + printf("[FAIL]\tmprotect(PROT_READ) failed\n"); + return 1; + } + + /* try to wrss it and fail */ + if (!test_shstk_access(shstk_ptr)) { + printf("[FAIL]\tShadow stack access to read-only memory succeeded\n"); + return 1; + } + + /* + * The shadow stack was reset above to resolve the fault, make the new one + * read-only. + */ + if (mprotect(shstk_ptr, SS_SIZE, PROT_READ) < 0) { + printf("[FAIL]\tmprotect(PROT_READ) failed\n"); + return 1; + } + + /* then back to writable */ + if (mprotect(shstk_ptr, SS_SIZE, PROT_WRITE | PROT_READ) < 0) { + printf("[FAIL]\tmprotect(PROT_WRITE) failed\n"); + return 1; + } + + /* then wrss to it and succeed */ + if (test_shstk_access(shstk_ptr)) { + printf("[FAIL]\tShadow stack access to mprotect() writable memory failed\n"); + return 1; + } + + free_shstk(shstk_ptr); + + signal(SIGSEGV, SIG_DFL); + + printf("[OK]\tmprotect() test\n"); + + return 0; +} + +char zero[4096]; + +static void *uffd_thread(void *arg) +{ + struct uffdio_copy req; + int uffd = *(int *)arg; + struct uffd_msg msg; + int ret; + + while (1) { + ret = read(uffd, &msg, sizeof(msg)); + if (ret > 0) + break; + else if (errno == EAGAIN) + continue; + return (void *)1; + } + + req.dst = msg.arg.pagefault.address; + req.src = (__u64)zero; + req.len = 4096; + req.mode = 0; + + if (ioctl(uffd, UFFDIO_COPY, &req)) + return (void *)1; + + return (void *)0; +} + +int test_userfaultfd(void) +{ + struct uffdio_register uffdio_register; + struct uffdio_api uffdio_api; + struct sigaction sa = {}; + pthread_t thread; + void *res; + int uffd; + + sa.sa_sigaction = test_access_fix_handler; + sa.sa_flags = SA_SIGINFO; + if (sigaction(SIGSEGV, &sa, NULL)) + return 1; + + uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK); + if (uffd < 0) { + printf("[SKIP]\tUserfaultfd unavailable.\n"); + return 0; + } + + reset_test_shstk(0); + + uffdio_api.api = UFFD_API; + uffdio_api.features = 0; + if (ioctl(uffd, UFFDIO_API, &uffdio_api)) + goto err; + + uffdio_register.range.start = (__u64)shstk_ptr; + uffdio_register.range.len = 4096; + uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING; + if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) + goto err; + + if (pthread_create(&thread, NULL, &uffd_thread, &uffd)) + goto err; + + reset_shstk(shstk_ptr); + test_shstk_access(shstk_ptr); + + if (pthread_join(thread, &res)) + goto err; + + if (test_shstk_access(shstk_ptr)) + goto err; + + free_shstk(shstk_ptr); + + signal(SIGSEGV, SIG_DFL); + + if (!res) + printf("[OK]\tUserfaultfd test\n"); + return !!res; +err: + free_shstk(shstk_ptr); + close(uffd); + signal(SIGSEGV, SIG_DFL); + return 1; +} + +/* Simple linked list for keeping track of mappings in test_guard_gap() */ +struct node { + struct node *next; + void *mapping; +}; + +/* + * This tests whether mmap will place other mappings in a shadow stack's guard + * gap. The steps are: + * 1. Finds an empty place by mapping and unmapping something. + * 2. Map a shadow stack in the middle of the known empty area. + * 3. Map a bunch of PAGE_SIZE mappings. These will use the search down + * direction, filling any gaps until it encounters the shadow stack's + * guard gap. + * 4. When a mapping lands below the shadow stack from step 2, then all + * of the above gaps are filled. The search down algorithm will have + * looked at the shadow stack gaps. + * 5. See if it landed in the gap. + */ +int test_guard_gap(void) +{ + void *free_area, *shstk, *test_map = (void *)0xFFFFFFFFFFFFFFFF; + struct node *head = NULL, *cur; + + free_area = mmap(0, SS_SIZE * 3, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + munmap(free_area, SS_SIZE * 3); + + shstk = create_shstk(free_area + SS_SIZE); + if (shstk == MAP_FAILED) + return 1; + + while (test_map > shstk) { + test_map = mmap(0, PAGE_SIZE, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + if (test_map == MAP_FAILED) + return 1; + cur = malloc(sizeof(*cur)); + cur->mapping = test_map; + + cur->next = head; + head = cur; + } + + while (head) { + cur = head; + head = cur->next; + munmap(cur->mapping, PAGE_SIZE); + free(cur); + } + + free_shstk(shstk); + + if (shstk - test_map - PAGE_SIZE != PAGE_SIZE) + return 1; + + printf("[OK]\tGuard gap test\n"); + + return 0; +} + +/* + * Too complicated to pull it out of the 32 bit header, but also get the + * 64 bit one needed above. Just define a copy here. + */ +#define __NR_compat_sigaction 67 + +/* + * Call 32 bit signal handler to get 32 bit signals ABI. Make sure + * to push the registers that will get clobbered. + */ +int sigaction32(int signum, const struct sigaction *restrict act, + struct sigaction *restrict oldact) +{ + register long syscall_reg asm("eax") = __NR_compat_sigaction; + register long signum_reg asm("ebx") = signum; + register long act_reg asm("ecx") = (long)act; + register long oldact_reg asm("edx") = (long)oldact; + int ret = 0; + + asm volatile ("int $0x80;" + : "=a"(ret), "=m"(oldact) + : "r"(syscall_reg), "r"(signum_reg), "r"(act_reg), + "r"(oldact_reg) + : "r8", "r9", "r10", "r11" + ); + + return ret; +} + +sigjmp_buf jmp_buffer; + +void segv_gp_handler(int signum, siginfo_t *si, void *uc) +{ + segv_triggered = true; + + /* + * To work with old glibc, this can't rely on siglongjmp working with + * shadow stack enabled, so disable shadow stack before siglongjmp(). + */ + ARCH_PRCTL(ARCH_SHSTK_DISABLE, ARCH_SHSTK_SHSTK); + siglongjmp(jmp_buffer, -1); +} + +/* + * Transition to 32 bit mode and check that a #GP triggers a segfault. + */ +int test_32bit(void) +{ + struct sigaction sa = {}; + struct sigaction *sa32; + + /* Create sigaction in 32 bit address range */ + sa32 = mmap(0, 4096, PROT_READ | PROT_WRITE, + MAP_32BIT | MAP_PRIVATE | MAP_ANONYMOUS, 0, 0); + sa32->sa_flags = SA_SIGINFO; + + sa.sa_sigaction = segv_gp_handler; + sa.sa_flags = SA_SIGINFO; + if (sigaction(SIGSEGV, &sa, NULL)) + return 1; + + + segv_triggered = false; + + /* Make sure segv_triggered is set before triggering the #GP */ + asm volatile("" : : : "memory"); + + /* + * Set handler to somewhere in 32 bit address space + */ + sa32->sa_handler = (void *)sa32; + if (sigaction32(SIGUSR1, sa32, NULL)) + return 1; + + if (!sigsetjmp(jmp_buffer, 1)) + raise(SIGUSR1); + + if (segv_triggered) + printf("[OK]\t32 bit test\n"); + + return !segv_triggered; +} + +void segv_handler_ptrace(int signum, siginfo_t *si, void *uc) +{ + /* The SSP adjustment caused a segfault. */ + exit(0); +} + +int test_ptrace(void) +{ + unsigned long saved_ssp, ssp = 0; + struct sigaction sa= {}; + struct iovec iov; + int status; + int pid; + + iov.iov_base = &ssp; + iov.iov_len = sizeof(ssp); + + pid = fork(); + if (!pid) { + ssp = get_ssp(); + + sa.sa_sigaction = segv_handler_ptrace; + sa.sa_flags = SA_SIGINFO; + if (sigaction(SIGSEGV, &sa, NULL)) + return 1; + + ptrace(PTRACE_TRACEME, NULL, NULL, NULL); + /* + * The parent will tweak the SSP and return from this function + * will #CP. + */ + raise(SIGTRAP); + + exit(1); + } + + while (waitpid(pid, &status, 0) != -1 && WSTOPSIG(status) != SIGTRAP); + + if (ptrace(PTRACE_GETREGSET, pid, NT_X86_SHSTK, &iov)) { + printf("[INFO]\tFailed to PTRACE_GETREGS\n"); + goto out_kill; + } + + if (!ssp) { + printf("[INFO]\tPtrace child SSP was 0\n"); + goto out_kill; + } + + saved_ssp = ssp; + + iov.iov_len = 0; + if (!ptrace(PTRACE_SETREGSET, pid, NT_X86_SHSTK, &iov)) { + printf("[INFO]\tToo small size accepted via PTRACE_SETREGS\n"); + goto out_kill; + } + + iov.iov_len = sizeof(ssp) + 1; + if (!ptrace(PTRACE_SETREGSET, pid, NT_X86_SHSTK, &iov)) { + printf("[INFO]\tToo large size accepted via PTRACE_SETREGS\n"); + goto out_kill; + } + + ssp += 1; + if (!ptrace(PTRACE_SETREGSET, pid, NT_X86_SHSTK, &iov)) { + printf("[INFO]\tUnaligned SSP written via PTRACE_SETREGS\n"); + goto out_kill; + } + + ssp = 0xFFFFFFFFFFFF0000; + if (!ptrace(PTRACE_SETREGSET, pid, NT_X86_SHSTK, &iov)) { + printf("[INFO]\tKernel range SSP written via PTRACE_SETREGS\n"); + goto out_kill; + } + + /* + * Tweak the SSP so the child with #CP when it resumes and returns + * from raise() + */ + ssp = saved_ssp + 8; + iov.iov_len = sizeof(ssp); + if (ptrace(PTRACE_SETREGSET, pid, NT_X86_SHSTK, &iov)) { + printf("[INFO]\tFailed to PTRACE_SETREGS\n"); + goto out_kill; + } + + if (ptrace(PTRACE_DETACH, pid, NULL, NULL)) { + printf("[INFO]\tFailed to PTRACE_DETACH\n"); + goto out_kill; + } + + waitpid(pid, &status, 0); + if (WEXITSTATUS(status)) + return 1; + + printf("[OK]\tPtrace test\n"); + return 0; + +out_kill: + kill(pid, SIGKILL); + return 1; +} + +int main(int argc, char *argv[]) +{ + int ret = 0; + + if (ARCH_PRCTL(ARCH_SHSTK_ENABLE, ARCH_SHSTK_SHSTK)) { + printf("[SKIP]\tCould not enable Shadow stack\n"); + return 1; + } + + if (ARCH_PRCTL(ARCH_SHSTK_DISABLE, ARCH_SHSTK_SHSTK)) { + ret = 1; + printf("[FAIL]\tDisabling shadow stack failed\n"); + } + + if (ARCH_PRCTL(ARCH_SHSTK_ENABLE, ARCH_SHSTK_SHSTK)) { + printf("[SKIP]\tCould not re-enable Shadow stack\n"); + return 1; + } + + if (ARCH_PRCTL(ARCH_SHSTK_ENABLE, ARCH_SHSTK_WRSS)) { + printf("[SKIP]\tCould not enable WRSS\n"); + ret = 1; + goto out; + } + + /* Should have succeeded if here, but this is a test, so double check. */ + if (!get_ssp()) { + printf("[FAIL]\tShadow stack disabled\n"); + return 1; + } + + if (test_shstk_pivot()) { + ret = 1; + printf("[FAIL]\tShadow stack pivot\n"); + goto out; + } + + if (test_shstk_faults()) { + ret = 1; + printf("[FAIL]\tShadow stack fault test\n"); + goto out; + } + + if (test_shstk_violation()) { + ret = 1; + printf("[FAIL]\tShadow stack violation test\n"); + goto out; + } + + if (test_gup()) { + ret = 1; + printf("[FAIL]\tShadow shadow stack gup\n"); + goto out; + } + + if (test_mprotect()) { + ret = 1; + printf("[FAIL]\tShadow shadow mprotect test\n"); + goto out; + } + + if (test_userfaultfd()) { + ret = 1; + printf("[FAIL]\tUserfaultfd test\n"); + goto out; + } + + if (test_guard_gap()) { + ret = 1; + printf("[FAIL]\tGuard gap test\n"); + goto out; + } + + if (test_ptrace()) { + ret = 1; + printf("[FAIL]\tptrace test\n"); + } + + if (test_32bit()) { + ret = 1; + printf("[FAIL]\t32 bit test\n"); + goto out; + } + + return ret; + +out: + /* + * Disable shadow stack before the function returns, or there will be a + * shadow stack violation. + */ + if (ARCH_PRCTL(ARCH_SHSTK_DISABLE, ARCH_SHSTK_SHSTK)) { + ret = 1; + printf("[FAIL]\tDisabling shadow stack failed\n"); + } + + return ret; +} +#endif diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c index ac1bd3ac1533..90718c2fd4ea 100644 --- a/tools/testing/vsock/vsock_test.c +++ b/tools/testing/vsock/vsock_test.c @@ -255,35 +255,142 @@ static void test_stream_multiconn_server(const struct test_opts *opts) close(fds[i]); } -static void test_stream_msg_peek_client(const struct test_opts *opts) +#define MSG_PEEK_BUF_LEN 64 + +static void test_msg_peek_client(const struct test_opts *opts, + bool seqpacket) { + unsigned char buf[MSG_PEEK_BUF_LEN]; + ssize_t send_size; int fd; + int i; + + if (seqpacket) + fd = vsock_seqpacket_connect(opts->peer_cid, 1234); + else + fd = vsock_stream_connect(opts->peer_cid, 1234); - fd = vsock_stream_connect(opts->peer_cid, 1234); if (fd < 0) { perror("connect"); exit(EXIT_FAILURE); } - send_byte(fd, 1, 0); + for (i = 0; i < sizeof(buf); i++) + buf[i] = rand() & 0xFF; + + control_expectln("SRVREADY"); + + send_size = send(fd, buf, sizeof(buf), 0); + + if (send_size < 0) { + perror("send"); + exit(EXIT_FAILURE); + } + + if (send_size != sizeof(buf)) { + fprintf(stderr, "Invalid send size %zi\n", send_size); + exit(EXIT_FAILURE); + } + close(fd); } -static void test_stream_msg_peek_server(const struct test_opts *opts) +static void test_msg_peek_server(const struct test_opts *opts, + bool seqpacket) { + unsigned char buf_half[MSG_PEEK_BUF_LEN / 2]; + unsigned char buf_normal[MSG_PEEK_BUF_LEN]; + unsigned char buf_peek[MSG_PEEK_BUF_LEN]; + ssize_t res; int fd; - fd = vsock_stream_accept(VMADDR_CID_ANY, 1234, NULL); + if (seqpacket) + fd = vsock_seqpacket_accept(VMADDR_CID_ANY, 1234, NULL); + else + fd = vsock_stream_accept(VMADDR_CID_ANY, 1234, NULL); + if (fd < 0) { perror("accept"); exit(EXIT_FAILURE); } - recv_byte(fd, 1, MSG_PEEK); - recv_byte(fd, 1, 0); + /* Peek from empty socket. */ + res = recv(fd, buf_peek, sizeof(buf_peek), MSG_PEEK | MSG_DONTWAIT); + if (res != -1) { + fprintf(stderr, "expected recv(2) failure, got %zi\n", res); + exit(EXIT_FAILURE); + } + + if (errno != EAGAIN) { + perror("EAGAIN expected"); + exit(EXIT_FAILURE); + } + + control_writeln("SRVREADY"); + + /* Peek part of data. */ + res = recv(fd, buf_half, sizeof(buf_half), MSG_PEEK); + if (res != sizeof(buf_half)) { + fprintf(stderr, "recv(2) + MSG_PEEK, expected %zu, got %zi\n", + sizeof(buf_half), res); + exit(EXIT_FAILURE); + } + + /* Peek whole data. */ + res = recv(fd, buf_peek, sizeof(buf_peek), MSG_PEEK); + if (res != sizeof(buf_peek)) { + fprintf(stderr, "recv(2) + MSG_PEEK, expected %zu, got %zi\n", + sizeof(buf_peek), res); + exit(EXIT_FAILURE); + } + + /* Compare partial and full peek. */ + if (memcmp(buf_half, buf_peek, sizeof(buf_half))) { + fprintf(stderr, "Partial peek data mismatch\n"); + exit(EXIT_FAILURE); + } + + if (seqpacket) { + /* This type of socket supports MSG_TRUNC flag, + * so check it with MSG_PEEK. We must get length + * of the message. + */ + res = recv(fd, buf_half, sizeof(buf_half), MSG_PEEK | + MSG_TRUNC); + if (res != sizeof(buf_peek)) { + fprintf(stderr, + "recv(2) + MSG_PEEK | MSG_TRUNC, exp %zu, got %zi\n", + sizeof(buf_half), res); + exit(EXIT_FAILURE); + } + } + + res = recv(fd, buf_normal, sizeof(buf_normal), 0); + if (res != sizeof(buf_normal)) { + fprintf(stderr, "recv(2), expected %zu, got %zi\n", + sizeof(buf_normal), res); + exit(EXIT_FAILURE); + } + + /* Compare full peek and normal read. */ + if (memcmp(buf_peek, buf_normal, sizeof(buf_peek))) { + fprintf(stderr, "Full peek data mismatch\n"); + exit(EXIT_FAILURE); + } + close(fd); } +static void test_stream_msg_peek_client(const struct test_opts *opts) +{ + return test_msg_peek_client(opts, false); +} + +static void test_stream_msg_peek_server(const struct test_opts *opts) +{ + return test_msg_peek_server(opts, false); +} + #define SOCK_BUF_SIZE (2 * 1024 * 1024) #define MAX_MSG_SIZE (32 * 1024) @@ -1053,6 +1160,16 @@ static void test_stream_virtio_skb_merge_server(const struct test_opts *opts) close(fd); } +static void test_seqpacket_msg_peek_client(const struct test_opts *opts) +{ + return test_msg_peek_client(opts, true); +} + +static void test_seqpacket_msg_peek_server(const struct test_opts *opts) +{ + return test_msg_peek_server(opts, true); +} + static struct test_case test_cases[] = { { .name = "SOCK_STREAM connection reset", @@ -1128,6 +1245,11 @@ static struct test_case test_cases[] = { .run_client = test_stream_virtio_skb_merge_client, .run_server = test_stream_virtio_skb_merge_server, }, + { + .name = "SOCK_SEQPACKET MSG_PEEK", + .run_client = test_seqpacket_msg_peek_client, + .run_server = test_seqpacket_msg_peek_server, + }, {}, }; diff --git a/tools/workqueue/wq_dump.py b/tools/workqueue/wq_dump.py new file mode 100644 index 000000000000..d0df5833f2c1 --- /dev/null +++ b/tools/workqueue/wq_dump.py @@ -0,0 +1,177 @@ +#!/usr/bin/env drgn +# +# Copyright (C) 2023 Tejun Heo <tj@kernel.org> +# Copyright (C) 2023 Meta Platforms, Inc. and affiliates. + +desc = """ +This is a drgn script to show the current workqueue configuration. For more +info on drgn, visit https://github.com/osandov/drgn. + +Affinity Scopes +=============== + +Shows the CPUs that can be used for unbound workqueues and how they will be +grouped by each available affinity type. For each type: + + nr_pods number of CPU pods in the affinity type + pod_cpus CPUs in each pod + pod_node NUMA node for memory allocation for each pod + cpu_pod pod that each CPU is associated to + +Worker Pools +============ + +Lists all worker pools indexed by their ID. For each pool: + + ref number of pool_workqueue's associated with this pool + nice nice value of the worker threads in the pool + idle number of idle workers + workers number of all workers + cpu CPU the pool is associated with (per-cpu pool) + cpus CPUs the workers in the pool can run on (unbound pool) + +Workqueue CPU -> pool +===================== + +Lists all workqueues along with their type and worker pool association. For +each workqueue: + + NAME TYPE[,FLAGS] POOL_ID... + + NAME name of the workqueue + TYPE percpu, unbound or ordered + FLAGS S: strict affinity scope + POOL_ID worker pool ID associated with each possible CPU +""" + +import sys + +import drgn +from drgn.helpers.linux.list import list_for_each_entry,list_empty +from drgn.helpers.linux.percpu import per_cpu_ptr +from drgn.helpers.linux.cpumask import for_each_cpu,for_each_possible_cpu +from drgn.helpers.linux.idr import idr_for_each + +import argparse +parser = argparse.ArgumentParser(description=desc, + formatter_class=argparse.RawTextHelpFormatter) +args = parser.parse_args() + +def err(s): + print(s, file=sys.stderr, flush=True) + sys.exit(1) + +def cpumask_str(cpumask): + output = "" + base = 0 + v = 0 + for cpu in for_each_cpu(cpumask[0]): + while cpu - base >= 32: + output += f'{hex(v)} ' + base += 32 + v = 0 + v |= 1 << (cpu - base) + if v > 0: + output += f'{v:08x}' + return output.strip() + +worker_pool_idr = prog['worker_pool_idr'] +workqueues = prog['workqueues'] +wq_unbound_cpumask = prog['wq_unbound_cpumask'] +wq_pod_types = prog['wq_pod_types'] +wq_affn_dfl = prog['wq_affn_dfl'] +wq_affn_names = prog['wq_affn_names'] + +WQ_UNBOUND = prog['WQ_UNBOUND'] +WQ_ORDERED = prog['__WQ_ORDERED'] +WQ_MEM_RECLAIM = prog['WQ_MEM_RECLAIM'] + +WQ_AFFN_CPU = prog['WQ_AFFN_CPU'] +WQ_AFFN_SMT = prog['WQ_AFFN_SMT'] +WQ_AFFN_CACHE = prog['WQ_AFFN_CACHE'] +WQ_AFFN_NUMA = prog['WQ_AFFN_NUMA'] +WQ_AFFN_SYSTEM = prog['WQ_AFFN_SYSTEM'] + +print('Affinity Scopes') +print('===============') + +print(f'wq_unbound_cpumask={cpumask_str(wq_unbound_cpumask)}') + +def print_pod_type(pt): + print(f' nr_pods {pt.nr_pods.value_()}') + + print(' pod_cpus', end='') + for pod in range(pt.nr_pods): + print(f' [{pod}]={cpumask_str(pt.pod_cpus[pod])}', end='') + print('') + + print(' pod_node', end='') + for pod in range(pt.nr_pods): + print(f' [{pod}]={pt.pod_node[pod].value_()}', end='') + print('') + + print(f' cpu_pod ', end='') + for cpu in for_each_possible_cpu(prog): + print(f' [{cpu}]={pt.cpu_pod[cpu].value_()}', end='') + print('') + +for affn in [WQ_AFFN_CPU, WQ_AFFN_SMT, WQ_AFFN_CACHE, WQ_AFFN_NUMA, WQ_AFFN_SYSTEM]: + print('') + print(f'{wq_affn_names[affn].string_().decode().upper()}{" (default)" if affn == wq_affn_dfl else ""}') + print_pod_type(wq_pod_types[affn]) + +print('') +print('Worker Pools') +print('============') + +max_pool_id_len = 0 +max_ref_len = 0 +for pi, pool in idr_for_each(worker_pool_idr): + pool = drgn.Object(prog, 'struct worker_pool', address=pool) + max_pool_id_len = max(max_pool_id_len, len(f'{pi}')) + max_ref_len = max(max_ref_len, len(f'{pool.refcnt.value_()}')) + +for pi, pool in idr_for_each(worker_pool_idr): + pool = drgn.Object(prog, 'struct worker_pool', address=pool) + print(f'pool[{pi:0{max_pool_id_len}}] ref={pool.refcnt.value_():{max_ref_len}} nice={pool.attrs.nice.value_():3} ', end='') + print(f'idle/workers={pool.nr_idle.value_():3}/{pool.nr_workers.value_():3} ', end='') + if pool.cpu >= 0: + print(f'cpu={pool.cpu.value_():3}', end='') + else: + print(f'cpus={cpumask_str(pool.attrs.cpumask)}', end='') + print(f' pod_cpus={cpumask_str(pool.attrs.__pod_cpumask)}', end='') + if pool.attrs.affn_strict: + print(' strict', end='') + print('') + +print('') +print('Workqueue CPU -> pool') +print('=====================') + +print('[ workqueue \ type CPU', end='') +for cpu in for_each_possible_cpu(prog): + print(f' {cpu:{max_pool_id_len}}', end='') +print(' dfl]') + +for wq in list_for_each_entry('struct workqueue_struct', workqueues.address_of_(), 'list'): + print(f'{wq.name.string_().decode()[-24:]:24}', end='') + if wq.flags & WQ_UNBOUND: + if wq.flags & WQ_ORDERED: + print(' ordered ', end='') + else: + print(' unbound', end='') + if wq.unbound_attrs.affn_strict: + print(',S ', end='') + else: + print(' ', end='') + else: + print(' percpu ', end='') + + for cpu in for_each_possible_cpu(prog): + pool_id = per_cpu_ptr(wq.cpu_pwq, cpu)[0].pool.id.value_() + field_len = max(len(str(cpu)), max_pool_id_len) + print(f' {pool_id:{field_len}}', end='') + + if wq.flags & WQ_UNBOUND: + print(f' {wq.dfl_pwq.pool.id.value_():{max_pool_id_len}}', end='') + print('') diff --git a/tools/workqueue/wq_monitor.py b/tools/workqueue/wq_monitor.py index 6e258d123e8c..a8856a9c45dc 100644 --- a/tools/workqueue/wq_monitor.py +++ b/tools/workqueue/wq_monitor.py @@ -20,8 +20,11 @@ https://github.com/osandov/drgn. and got excluded from concurrency management to avoid stalling other work items. - CMwake The number of concurrency-management wake-ups while executing a - work item of the workqueue. + CMW/RPR For per-cpu workqueues, the number of concurrency-management + wake-ups while executing a work item of the workqueue. For + unbound workqueues, the number of times a worker was repatriated + to its affinity scope after being migrated to an off-scope CPU by + the scheduler. mayday The number of times the rescuer was requested while waiting for new worker creation. @@ -65,6 +68,7 @@ PWQ_STAT_COMPLETED = prog['PWQ_STAT_COMPLETED'] # work items completed exec PWQ_STAT_CPU_TIME = prog['PWQ_STAT_CPU_TIME'] # total CPU time consumed PWQ_STAT_CPU_INTENSIVE = prog['PWQ_STAT_CPU_INTENSIVE'] # wq_cpu_intensive_thresh_us violations PWQ_STAT_CM_WAKEUP = prog['PWQ_STAT_CM_WAKEUP'] # concurrency-management worker wakeups +PWQ_STAT_REPATRIATED = prog['PWQ_STAT_REPATRIATED'] # unbound workers brought back into scope PWQ_STAT_MAYDAY = prog['PWQ_STAT_MAYDAY'] # maydays to rescuer PWQ_STAT_RESCUED = prog['PWQ_STAT_RESCUED'] # linked work items executed by rescuer PWQ_NR_STATS = prog['PWQ_NR_STATS'] @@ -89,22 +93,25 @@ class WqStats: 'cpu_time' : self.stats[PWQ_STAT_CPU_TIME], 'cpu_intensive' : self.stats[PWQ_STAT_CPU_INTENSIVE], 'cm_wakeup' : self.stats[PWQ_STAT_CM_WAKEUP], + 'repatriated' : self.stats[PWQ_STAT_REPATRIATED], 'mayday' : self.stats[PWQ_STAT_MAYDAY], 'rescued' : self.stats[PWQ_STAT_RESCUED], } def table_header_str(): return f'{"":>24} {"total":>8} {"infl":>5} {"CPUtime":>8} '\ - f'{"CPUitsv":>7} {"CMwake":>7} {"mayday":>7} {"rescued":>7}' + f'{"CPUitsv":>7} {"CMW/RPR":>7} {"mayday":>7} {"rescued":>7}' def table_row_str(self): cpu_intensive = '-' - cm_wakeup = '-' + cmw_rpr = '-' mayday = '-' rescued = '-' - if not self.unbound: + if self.unbound: + cmw_rpr = str(self.stats[PWQ_STAT_REPATRIATED]); + else: cpu_intensive = str(self.stats[PWQ_STAT_CPU_INTENSIVE]) - cm_wakeup = str(self.stats[PWQ_STAT_CM_WAKEUP]) + cmw_rpr = str(self.stats[PWQ_STAT_CM_WAKEUP]) if self.mem_reclaim: mayday = str(self.stats[PWQ_STAT_MAYDAY]) @@ -115,7 +122,7 @@ class WqStats: f'{max(self.stats[PWQ_STAT_STARTED] - self.stats[PWQ_STAT_COMPLETED], 0):5} ' \ f'{self.stats[PWQ_STAT_CPU_TIME] / 1000000:8.1f} ' \ f'{cpu_intensive:>7} ' \ - f'{cm_wakeup:>7} ' \ + f'{cmw_rpr:>7} ' \ f'{mayday:>7} ' \ f'{rescued:>7} ' return out.rstrip(':') |