diff options
Diffstat (limited to 'tools')
122 files changed, 11128 insertions, 573 deletions
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..65a168df63bc 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) >= 0 && (id) < ARRAY_SIZE(array)) \ + event_str = array[id]; \ + event_str; \ +}) static int link_parse_fd(int *argc, char ***argv) { @@ -166,6 +237,154 @@ 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; @@ -218,6 +437,29 @@ static int show_link_close_json(int fd, struct bpf_link_info *info) 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; } @@ -351,6 +593,113 @@ 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 +745,29 @@ 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_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 +789,13 @@ 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 +806,67 @@ 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 +891,8 @@ 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 +931,9 @@ 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/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/feature/Makefile b/tools/build/feature/Makefile index 2cd6dbbee088..f0c5de018a95 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -372,7 +372,7 @@ $(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/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 60a9d59beeab..739c15906a65 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1036,6 +1036,8 @@ enum bpf_attach_type { BPF_LSM_CGROUP, BPF_STRUCT_OPS, BPF_NETFILTER, + BPF_TCX_INGRESS, + BPF_TCX_EGRESS, __MAX_BPF_ATTACH_TYPE }; @@ -1053,10 +1055,20 @@ 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, 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 +1115,12 @@ 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 @@ -1434,14 +1451,19 @@ 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 +1509,26 @@ 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 +1571,13 @@ 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 +1611,13 @@ union bpf_attr { __s32 priority; __u32 flags; } netfilter; + struct { + union { + __u32 relative_fd; + __u32 relative_id; + }; + __u64 expected_revision; + } tcx; }; } link_create; @@ -6187,6 +6226,19 @@ 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 +6491,40 @@ 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 +7098,7 @@ struct bpf_list_head { struct bpf_list_node { __u64 :64; __u64 :64; + __u64 :64; } __attribute__((aligned(8))); struct bpf_rb_root { @@ -7023,6 +7110,7 @@ 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..bf71698a1e82 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -41,6 +41,7 @@ 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/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index ed86b37d8024..c9b6b311a441 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); @@ -741,6 +775,30 @@ 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 +891,7 @@ 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 +902,20 @@ 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..044a74ffc38a 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 */ @@ -349,6 +395,17 @@ struct bpf_link_create_opts { 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; }; @@ -489,13 +546,31 @@ 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/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..17883f5a44b9 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -118,6 +118,8 @@ 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", }; static const char * const link_type_name[] = { @@ -132,6 +134,7 @@ 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", }; static const char * const map_type_name[] = { @@ -5471,6 +5474,10 @@ 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 +6164,11 @@ 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, @@ -8528,7 +8539,8 @@ 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 +8570,31 @@ 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; } @@ -8669,9 +8699,13 @@ static const struct bpf_sec_def section_defs[] = { 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("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 +8774,6 @@ 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 +8853,11 @@ 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 +10255,18 @@ 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) { @@ -10539,25 +10582,158 @@ 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 +10770,12 @@ 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; } @@ -11680,11 +11855,10 @@ 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 +11876,7 @@ 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 +11892,54 @@ 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 +11961,16 @@ 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 +12025,48 @@ 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..55b97b208754 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -718,6 +718,36 @@ 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 +1120,10 @@ 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..9c7538dd5835 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -395,4 +395,7 @@ LIBBPF_1.2.0 { LIBBPF_1.3.0 { global: bpf_obj_pin_opts; + bpf_prog_detach_opts; + bpf_program__attach_netfilter; + bpf_program__attach_tcx; } 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/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/usdt.c b/tools/lib/bpf/usdt.c index f1a141555f08..37455d00b239 100644 --- a/tools/lib/bpf/usdt.c +++ b/tools/lib/bpf/usdt.c @@ -852,8 +852,11 @@ 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; diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/lib/ynl.py index 1b3a36fbb1c3..3ca28d4bcb18 100644 --- a/tools/net/ynl/lib/ynl.py +++ b/tools/net/ynl/lib/ynl.py @@ -417,11 +417,10 @@ class YnlFamily(SpecFamily): pad = b'\x00' * ((4 - len(attr_payload) % 4) % 4) return struct.pack('HH', len(attr_payload) + 4, nl_type) + attr_payload + pad - def _decode_enum(self, rsp, attr_spec): - raw = rsp[attr_spec['name']] + def _decode_enum(self, raw, attr_spec): enum = self.consts[attr_spec['enum']] - i = attr_spec.get('value-start', 0) if 'enum-as-flags' in attr_spec and attr_spec['enum-as-flags']: + i = 0 value = set() while raw: if raw & 1: @@ -429,8 +428,8 @@ class YnlFamily(SpecFamily): raw >>= 1 i += 1 else: - value = enum.entries_by_val[raw - i].name - rsp[attr_spec['name']] = value + value = enum.entries_by_val[raw].name + return value def _decode_binary(self, attr, attr_spec): if attr_spec.struct_name: @@ -438,7 +437,7 @@ class YnlFamily(SpecFamily): decoded = attr.as_struct(members) for m in members: if m.enum: - self._decode_enum(decoded, m) + decoded[m.name] = self._decode_enum(decoded[m.name], m) elif attr_spec.sub_type: decoded = attr.as_c_array(attr_spec.sub_type) else: @@ -466,6 +465,9 @@ class YnlFamily(SpecFamily): else: raise Exception(f'Unknown {attr_spec["type"]} with name {attr_spec["name"]}') + if 'enum' in attr_spec: + decoded = self._decode_enum(decoded, attr_spec) + if not attr_spec.is_multi: rsp[attr_spec['name']] = decoded elif attr_spec.name in rsp: @@ -473,8 +475,6 @@ class YnlFamily(SpecFamily): else: rsp[attr_spec.name] = [decoded] - if 'enum' in attr_spec: - self._decode_enum(rsp, attr_spec) return rsp def _decode_extack_path(self, attrs, attr_set, offset, target): diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 666b56f22a41..5c60a7cea732 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -8,6 +8,7 @@ TARGETS += cachestat TARGETS += capabilities TARGETS += cgroup TARGETS += clone3 +TARGETS += connector TARGETS += core TARGETS += cpufreq TARGETS += cpu-hotplug diff --git a/tools/testing/selftests/bpf/DENYLIST.aarch64 b/tools/testing/selftests/bpf/DENYLIST.aarch64 index 08adc805878b..3b61e8b35d62 100644 --- a/tools/testing/selftests/bpf/DENYLIST.aarch64 +++ b/tools/testing/selftests/bpf/DENYLIST.aarch64 @@ -10,3 +10,5 @@ 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 diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 538df8fb8c42..882be03b179f 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 @@ -331,7 +335,7 @@ $(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 +376,12 @@ $(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 # Build BPF object using GCC define GCC_BPF_BUILD_RULE @@ -644,11 +648,13 @@ $(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 +667,7 @@ $(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 $@ 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/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/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c index aaf6ef1201c7..a6f991b56345 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 +80,24 @@ 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; +} + __bpf_kfunc void bpf_testmod_test_mod_kfunc(int i) { @@ -191,6 +214,20 @@ 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 @@ -206,6 +243,7 @@ bpf_testmod_test_read(struct file *file, struct kobject *kobj, struct bpf_testmod_struct_arg_1 struct_arg1 = {10}; 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 +254,11 @@ 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); + struct_arg3 = kmalloc((sizeof(struct bpf_testmod_struct_arg_3) + sizeof(int)), GFP_KERNEL); @@ -243,7 +286,11 @@ 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/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/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/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/cgroup_tcp_skb.c b/tools/testing/selftests/bpf/prog_tests/cgroup_tcp_skb.c new file mode 100644 index 000000000000..95bab61a1e57 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_tcp_skb.c @@ -0,0 +1,402 @@ +// 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" + +#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; +} + +static int create_server_sock_v6(void) +{ + struct sockaddr_in6 addr = { + .sin6_family = AF_INET6, + .sin6_port = htons(0), + .sin6_addr = IN6ADDR_LOOPBACK_INIT, + }; + int fd, err; + + fd = socket(AF_INET6, SOCK_STREAM, 0); + if (fd < 0) { + perror("socket"); + return -1; + } + + err = bind(fd, (struct sockaddr *)&addr, sizeof(addr)); + if (err < 0) { + perror("bind"); + return -1; + } + + err = listen(fd, 1); + if (err < 0) { + perror("listen"); + return -1; + } + + return fd; +} + +static int get_sock_port_v6(int fd) +{ + struct sockaddr_in6 addr; + socklen_t len; + int err; + + len = sizeof(addr); + err = getsockname(fd, (struct sockaddr *)&addr, &len); + if (err < 0) { + perror("getsockname"); + return -1; + } + + return ntohs(addr.sin6_port); +} + +static int connect_client_server_v6(int client_fd, int listen_fd) +{ + struct sockaddr_in6 addr = { + .sin6_family = AF_INET6, + .sin6_addr = IN6ADDR_LOOPBACK_INIT, + }; + int err; + + addr.sin6_port = htons(get_sock_port_v6(listen_fd)); + if (addr.sin6_port < 0) + return -1; + + err = connect(client_fd, (struct sockaddr *)&addr, sizeof(addr)); + if (err < 0) { + perror("connect"); + return -1; + } + + return 0; +} + +/* 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]; + + /* 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 = create_server_sock_v6(); + if (!ASSERT_GE(*listen_fd, 0, "listen_fd")) + return -1; + skel->bss->g_sock_port = get_sock_port_v6(*listen_fd); + + /* Connect client to server */ + err = connect_client_server_v6(*client_fd, *listen_fd); + if (!ASSERT_OK(err, "connect_client_server_v6")) + 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]; + + /* Create client & server socket */ + err = join_root_cgroup(); + if (!ASSERT_OK(err, "join_root_cgroup")) + return -1; + *listen_fd = create_server_sock_v6(); + 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; + skel->bss->g_sock_port = get_sock_port_v6(*listen_fd); + + /* Connect client to server */ + err = connect_client_server_v6(*client_fd, *listen_fd); + if (!ASSERT_OK(err, "connect_client_server_v6")) + 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/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/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/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/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/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/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..7423983472c7 100644 --- a/tools/testing/selftests/bpf/prog_tests/refcounted_kptr.c +++ b/tools/testing/selftests/bpf/prog_tests/refcounted_kptr.c @@ -14,3 +14,7 @@ void test_refcounted_kptr(void) void test_refcounted_kptr_fail(void) { } + +void test_refcounted_kptr_wrong_owner(void) +{ +} 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..81eea5f10742 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/tc_links.c @@ -0,0 +1,1583 @@ +// 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_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); +} 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..7914100f9b46 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/tc_opts.c @@ -0,0 +1,2239 @@ +// 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); +} 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/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/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c index 070a13833c3f..c375e59ff28d 100644 --- a/tools/testing/selftests/bpf/prog_tests/verifier.c +++ b/tools/testing/selftests/bpf/prog_tests/verifier.c @@ -58,6 +58,7 @@ #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" @@ -159,6 +160,7 @@ 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/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/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/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/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/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..c55652fdc63a 100644 --- a/tools/testing/selftests/bpf/progs/refcounted_kptr.c +++ b/tools/testing/selftests/bpf/progs/refcounted_kptr.c @@ -24,7 +24,7 @@ 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 +42,9 @@ 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 +408,93 @@ 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; +} + 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_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_link.c b/tools/testing/selftests/bpf/progs/test_tc_link.c new file mode 100644 index 000000000000..ed1fd0e9cee9 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_tc_link.c @@ -0,0 +1,40 @@ +// 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; + +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; +} 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/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/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/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/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..3ff436706640 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 querrying 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/connector/Makefile b/tools/testing/selftests/connector/Makefile new file mode 100644 index 000000000000..21c9f3a973a0 --- /dev/null +++ b/tools/testing/selftests/connector/Makefile @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0 +CFLAGS += -Wall + +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..4fe8c6763fd8 --- /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(1); + } + + if (argc == 2) { + if (strcmp(argv[1], "-f") == 0) { + filter = 1; + } else { + printf("Valid option : -f (for filter feature)\n"); + exit(1); + } + } + + 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/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/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/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/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/net/Makefile b/tools/testing/selftests/net/Makefile index 7f3ab2a93ed6..04341e1b38f0 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 @@ -85,6 +87,7 @@ 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 +116,7 @@ $(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 +134,7 @@ 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/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 0f5e88c8f4ff..54ec2b7b7b8c 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/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile index 770efbe24f0d..2d8bb72762a4 100644 --- a/tools/testing/selftests/net/forwarding/Makefile +++ b/tools/testing/selftests/net/forwarding/Makefile @@ -65,6 +65,8 @@ TEST_PROGS = bridge_igmp.sh \ q_in_vni.sh \ router_bridge.sh \ router_bridge_vlan.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 +87,7 @@ 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/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 9ddb68dd6a08..71f7c0c49677 100755 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -1215,6 +1215,15 @@ 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 @@ -1237,6 +1246,15 @@ 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..4f33db04699d 100755 --- a/tools/testing/selftests/net/forwarding/router_bridge.sh +++ b/tools/testing/selftests/net/forwarding/router_bridge.sh @@ -1,9 +1,33 @@ #!/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 | +# | | + $swp1 BR1 (802.1q) | 192.0.2.129/28 | +# | | 192.0.2.2/28 | 2001:db8:2::1/64 | +# | | 2001:db8:1::1/64 | | +# | | | | +# | +--------------------------------+ | +# +---------------------------------------------------------------------------+ + ALL_TESTS=" ping_ipv4 ping_ipv6 + config_remove_pvid + ping_ipv4_fails + ping_ipv6_fails + config_add_pvid + ping_ipv4 + ping_ipv6 " NUM_NETIFS=4 source lib.sh @@ -62,6 +86,22 @@ router_destroy() ip link del dev br1 } +config_remove_pvid() +{ + log_info "Remove PVID from the bridge" + + bridge vlan add dev br1 vid 1 self + sleep 2 +} + +config_add_pvid() +{ + log_info "Add PVID to the bridge" + + bridge vlan add dev br1 vid 1 self pvid untagged + sleep 2 +} + setup_prepare() { h1=${NETIFS[p1]} @@ -104,6 +144,16 @@ 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_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_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 ${final_ret} diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index e6c9d5451c5b..1640749750d4 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -39,7 +39,9 @@ evts_ns1="" evts_ns2="" evts_ns1_pid=0 evts_ns2_pid=0 -stats_dumped=0 +last_test_failed=0 +last_test_skipped=0 +last_test_ignored=1 declare -A all_tests declare -a only_tests_ids @@ -49,11 +51,15 @@ TEST_COUNT=0 TEST_NAME="" nr_blank=40 -export FAILING_LINKS="" -export test_linkfail=0 -export addr_nr_ns1=0 -export addr_nr_ns2=0 -export sflags="" +# These var are used only in some tests, make sure they are not already set +unset FAILING_LINKS +unset test_linkfail +unset addr_nr_ns1 +unset addr_nr_ns2 +unset sflags +unset fastclose +unset fullmesh +unset speed # generated using "nfbpf_compile '(ip && (ip[54] & 0xf0) == 0x30) || # (ip6 && (ip6[74] & 0xf0) == 0x30)'" @@ -97,10 +103,8 @@ init_partial() fi done - stats_dumped=0 check_invert=0 validate_checksum=$checksum - FAILING_LINKS="" # ns1 ns2 # ns1eth1 ns2eth1 @@ -162,9 +166,7 @@ check_tools() elif ! iptables -V &> /dev/null; then echo "SKIP: Could not run all tests without iptables tool" exit $ksft_skip - fi - - if ! ip6tables -V &> /dev/null; then + elif ! ip6tables -V &> /dev/null; then echo "SKIP: Could not run all tests without ip6tables tool" exit $ksft_skip fi @@ -213,6 +215,8 @@ mark_as_skipped() print_title "[ skip ] ${msg}" printf "\n" + + last_test_skipped=1 } # $@: condition @@ -245,14 +249,32 @@ 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=$((TEST_COUNT+1)) if skip_test; then + last_test_ignored=1 return 1 fi @@ -439,10 +461,13 @@ reset_with_tcp_filter() fail_test() { ret=1 - failed_tests[${TEST_COUNT}]="${TEST_NAME}" - [ "${stats_dumped}" = 0 ] && dump_stats - stats_dumped=1 + # 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() @@ -828,6 +853,17 @@ 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 +1011,12 @@ 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" @@ -1011,15 +1049,14 @@ 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 [ ${test_linkfail} -le 1 ]; then echo "fastclose tests need test_linkfail argument" fail_test @@ -1028,7 +1065,7 @@ do_transfer() # disconnect trunc_size=${test_linkfail} - local side=${addr_nr_ns2:10} + local side=${fastclose} if [ ${side} = "client" ]; then extra_cl_args="-f ${test_linkfail}" @@ -1041,10 +1078,6 @@ do_transfer() fail_test return 1 fi - addr_nr_ns2=0 - elif [[ "${addr_nr_ns2}" = "fullmesh_"* ]]; then - flags="${flags},fullmesh" - addr_nr_ns2=${addr_nr_ns2:9} fi extra_srv_args="$extra_args $extra_srv_args" @@ -1155,9 +1188,9 @@ run_tests() local listener_ns="$1" local connector_ns="$2" local connect_addr="$3" - local speed="${4:-fast}" local size + local test_linkfail=${test_linkfail:-0} # The values above 2 are reused to make test files # with the given sizes (KB) @@ -1199,7 +1232,7 @@ run_tests() make_file "$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() @@ -1988,7 +2021,8 @@ 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 +2033,8 @@ 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 +2045,8 @@ 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 +2058,8 @@ 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 +2158,8 @@ 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 +2269,8 @@ 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 +2281,8 @@ 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 +2293,8 @@ 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 +2305,8 @@ 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 +2319,8 @@ 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 +2332,8 @@ 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 +2343,8 @@ 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 +2356,8 @@ 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 +2370,8 @@ 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 +2384,8 @@ 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 +2398,8 @@ 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 +2412,8 @@ 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 +2426,8 @@ 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 +2445,8 @@ 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 +2459,8 @@ 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 +2471,8 @@ 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 +2482,8 @@ 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 +2496,8 @@ 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 +2505,8 @@ 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 +2515,8 @@ 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 +2524,8 @@ 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 +2533,8 @@ 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 +2547,16 @@ 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 +2566,8 @@ 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 +2577,8 @@ 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 +2590,8 @@ 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 +2692,8 @@ 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 +2703,8 @@ 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 +2715,8 @@ 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 +2728,8 @@ 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 +2742,8 @@ 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 +2754,8 @@ 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 +2767,8 @@ 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 $ns2 10.0.1.1 chk_join_nr 1 1 1 chk_add_nr 1 1 chk_prio_nr 1 1 @@ -2729,7 +2777,8 @@ backup_tests() if reset "mpc backup" && continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; 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 $ns2 10.0.1.1 chk_join_nr 0 0 0 chk_prio_nr 0 1 fi @@ -2738,7 +2787,8 @@ backup_tests() continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then pm_nl_add_endpoint $ns1 10.0.1.1 flags subflow,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 $ns2 10.0.1.1 chk_join_nr 0 0 0 chk_prio_nr 1 1 fi @@ -2746,8 +2796,8 @@ backup_tests() if reset "mpc switch to backup" && continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; 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 $ns2 10.0.1.1 chk_join_nr 0 0 0 chk_prio_nr 0 1 fi @@ -2756,8 +2806,8 @@ backup_tests() continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; 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 @@ -2846,8 +2896,8 @@ 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 +2913,8 @@ 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 +2927,8 @@ 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 +3130,8 @@ 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 +3143,8 @@ 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 +3156,8 @@ 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 +3170,8 @@ 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 +3182,8 @@ 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 +3194,8 @@ 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 +3206,8 @@ 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 +3219,8 @@ 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 +3230,7 @@ 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 +3238,7 @@ 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 +3395,8 @@ 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 +3409,8 @@ 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 +3420,8 @@ 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 +3441,8 @@ 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 @@ -3413,7 +3465,8 @@ 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" \ @@ -3436,8 +3489,8 @@ 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 @@ -3568,4 +3621,7 @@ if [ ${ret} -ne 0 ]; then echo fi +append_prev_results +mptcp_lib_result_print_all_tap + exit $ret diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh index f32045b23b89..b1a0fdd0408b 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -1,8 +1,12 @@ #! /bin/bash # SPDX-License-Identifier: GPL-2.0 +readonly KSFT_PASS=0 readonly KSFT_FAIL=1 readonly KSFT_SKIP=4 +readonly KSFT_TEST=$(basename "${0}" | sed 's/\.sh$//g') + +MPTCP_LIB_SUBTESTS=() # 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 @@ -102,3 +106,65 @@ 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 $ret diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh index d02e0d63a8f9..f32038fe1ee5 100755 --- a/tools/testing/selftests/net/mptcp/pm_netlink.sh +++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh @@ -58,16 +58,19 @@ check() local out=`$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 } @@ -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 $ret diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh index 36a3c9d92e20..ce9203b817f8 100755 --- a/tools/testing/selftests/net/mptcp/simult_flows.sh +++ b/tools/testing/selftests/net/mptcp/simult_flows.sh @@ -261,6 +261,7 @@ run_test() printf "%-60s" "$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 $ret diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh index b180133a30af..23f8959a8ea8 100755 --- a/tools/testing/selftests/net/mptcp/userspace_pm.sh +++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh @@ -1,6 +1,13 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +# Double quotes to prevent globbing and word splitting is recommended in new +# code but we accept it. +#shellcheck disable=SC2086 + +# Some variables are used below but indirectly, see check_expected_one() +#shellcheck disable=SC2034 + . "$(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 [ ${rc} -eq 0 ] then - stdbuf -o0 -e0 printf "[OK]\n" + test_pass return 0 fi - exit 1 + return 1 } verify_announce_event() @@ -317,13 +368,12 @@ test_announce() local type type=$(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: ${type}" fi # ADD_ADDR from the client to server machine reusing the subflow port @@ -331,7 +381,7 @@ test_announce() ip netns exec "$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" $client_addr_id + print_test "ADD_ADDR id:${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" @@ -340,7 +390,7 @@ test_announce() :>"$server_evts" ip netns exec "$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" $client_addr_id + print_test "ADD_ADDR6 id:${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" "$client6_port" "v6" @@ -350,7 +400,7 @@ test_announce() client_addr_id=$((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" $client_addr_id + print_test "ADD_ADDR id:${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" "$new4_port" @@ -361,7 +411,7 @@ test_announce() # ADD_ADDR from the server to client machine reusing the subflow port ip netns exec "$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" $server_addr_id + print_test "ADD_ADDR id:${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" "$app4_port" @@ -370,7 +420,7 @@ test_announce() :>"$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" $server_addr_id + print_test "ADD_ADDR6 id:${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" "$app6_port" "v6" @@ -380,7 +430,7 @@ test_announce() server_addr_id=$((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" $server_addr_id + print_test "ADD_ADDR id:${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"\ - $client_addr_id + print_test "RM_ADDR id:${client_addr_id} ns2 => ns1" sleep 0.5 verify_remove_event "$server_evts" "$REMOVED" "$server4_token" "$client_addr_id" @@ -455,8 +500,7 @@ test_remove() 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"\ - $client_addr_id + print_test "RM_ADDR id:${client_addr_id} ns2 => ns1" sleep 0.5 verify_remove_event "$server_evts" "$REMOVED" "$server4_token" "$client_addr_id" @@ -464,8 +508,7 @@ test_remove() :>"$server_evts" ip netns exec "$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"\ - $client_addr_id + print_test "RM_ADDR6 id:${client_addr_id} ns2 => ns1" sleep 0.5 verify_remove_event "$server_evts" "$REMOVED" "$server6_token" "$client_addr_id" @@ -475,8 +518,7 @@ 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"\ - $server_addr_id + print_test "RM_ADDR id:${server_addr_id} ns1 => ns2" sleep 0.5 verify_remove_event "$client_evts" "$REMOVED" "$client4_token" "$server_addr_id" @@ -485,7 +527,7 @@ test_remove() 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" $server_addr_id + print_test "RM_ADDR id:${server_addr_id} ns1 => ns2" sleep 0.5 verify_remove_event "$client_evts" "$REMOVED" "$client4_token" "$server_addr_id" @@ -493,7 +535,7 @@ test_remove() :>"$client_evts" ip netns exec "$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" $server_addr_id + print_test "RM_ADDR6 id:${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 ${info}" fi fi @@ -809,7 +850,7 @@ test_subflows_v4_v6_mix() :>"$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" $server_addr_id + print_test "ADD_ADDR4 id:${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" "$app6_port" @@ -854,25 +895,23 @@ test_prio() sleep 0.5 # Check TX - stdbuf -o0 -e0 printf "MP_PRIO TX \t" + print_test "MP_PRIO TX" count=$(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 @@ -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/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/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 $ret diff --git a/tools/testing/selftests/tc-testing/Makefile b/tools/testing/selftests/tc-testing/Makefile index cb553eac9f41..3c4b7fa05075 100644 --- a/tools/testing/selftests/tc-testing/Makefile +++ b/tools/testing/selftests/tc-testing/Makefile @@ -24,7 +24,7 @@ CLANG_FLAGS = -I. -I$(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/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, + }, {}, }; |