diff options
Diffstat (limited to 'tools')
221 files changed, 6500 insertions, 1759 deletions
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index f4542d2718f4..29cb275a219d 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -198,6 +198,7 @@ #define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* Cache Allocation Technology L3 */ #define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* Cache Allocation Technology L2 */ #define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* Code and Data Prioritization L3 */ +#define X86_FEATURE_TDX_HOST_PLATFORM ( 7*32+ 7) /* Platform supports being a TDX host */ #define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ #define X86_FEATURE_XCOMPACTED ( 7*32+10) /* "" Use compacted XSTATE (XSAVES or XSAVEC) */ @@ -308,10 +309,14 @@ #define X86_FEATURE_SMBA (11*32+21) /* "" Slow Memory Bandwidth Allocation */ #define X86_FEATURE_BMEC (11*32+22) /* "" Bandwidth Monitoring Event Configuration */ #define X86_FEATURE_USER_SHSTK (11*32+23) /* Shadow stack support for user mode applications */ - #define X86_FEATURE_SRSO (11*32+24) /* "" AMD BTB untrain RETs */ #define X86_FEATURE_SRSO_ALIAS (11*32+25) /* "" AMD BTB untrain RETs through aliasing */ #define X86_FEATURE_IBPB_ON_VMEXIT (11*32+26) /* "" Issue an IBPB only on VMEXIT */ +#define X86_FEATURE_APIC_MSRS_FENCE (11*32+27) /* "" IA32_TSC_DEADLINE and X2APIC MSRs need fencing */ +#define X86_FEATURE_ZEN2 (11*32+28) /* "" CPU based on Zen2 microarchitecture */ +#define X86_FEATURE_ZEN3 (11*32+29) /* "" CPU based on Zen3 microarchitecture */ +#define X86_FEATURE_ZEN4 (11*32+30) /* "" CPU based on Zen4 microarchitecture */ +#define X86_FEATURE_ZEN1 (11*32+31) /* "" CPU based on Zen1 microarchitecture */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ @@ -495,6 +500,7 @@ #define X86_BUG_EIBRS_PBRSB X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */ #define X86_BUG_SMT_RSB X86_BUG(29) /* CPU is vulnerable to Cross-Thread Return Address Predictions */ #define X86_BUG_GDS X86_BUG(30) /* CPU is affected by Gather Data Sampling */ +#define X86_BUG_TDX_PW_MCE X86_BUG(31) /* CPU may incur #MC if non-TD software does partial write to TDX private memory */ /* BUG word 2 */ #define X86_BUG_SRSO X86_BUG(1*32 + 0) /* AMD SRSO bug */ diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index 1d51e1850ed0..f1bd7b91b3c6 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -237,6 +237,11 @@ #define LBR_INFO_CYCLES 0xffff #define LBR_INFO_BR_TYPE_OFFSET 56 #define LBR_INFO_BR_TYPE (0xfull << LBR_INFO_BR_TYPE_OFFSET) +#define LBR_INFO_BR_CNTR_OFFSET 32 +#define LBR_INFO_BR_CNTR_NUM 4 +#define LBR_INFO_BR_CNTR_BITS 2 +#define LBR_INFO_BR_CNTR_MASK GENMASK_ULL(LBR_INFO_BR_CNTR_BITS - 1, 0) +#define LBR_INFO_BR_CNTR_FULL_MASK GENMASK_ULL(LBR_INFO_BR_CNTR_NUM * LBR_INFO_BR_CNTR_BITS - 1, 0) #define MSR_ARCH_LBR_CTL 0x000014ce #define ARCH_LBR_CTL_LBREN BIT(0) @@ -536,6 +541,9 @@ #define MSR_RELOAD_PMC0 0x000014c1 #define MSR_RELOAD_FIXED_CTR0 0x00001309 +/* KeyID partitioning between MKTME and TDX */ +#define MSR_IA32_MKTME_KEYID_PARTITIONING 0x00000087 + /* * AMD64 MSRs. Not complete. See the architecture manual for a more * complete list. diff --git a/tools/arch/x86/include/asm/rmwcc.h b/tools/arch/x86/include/asm/rmwcc.h index 11ff975242ca..e2ff22b379a4 100644 --- a/tools/arch/x86/include/asm/rmwcc.h +++ b/tools/arch/x86/include/asm/rmwcc.h @@ -4,7 +4,7 @@ #define __GEN_RMWcc(fullop, var, cc, ...) \ do { \ - asm_volatile_goto (fullop "; j" cc " %l[cc_label]" \ + asm goto (fullop "; j" cc " %l[cc_label]" \ : : "m" (var), ## __VA_ARGS__ \ : "memory" : cc_label); \ return 0; \ diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index 1a6a1f987949..a448d0964fc0 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -562,4 +562,7 @@ struct kvm_pmu_event_filter { /* x86-specific KVM_EXIT_HYPERCALL flags. */ #define KVM_EXIT_HYPERCALL_LONG_MODE BIT(0) +#define KVM_X86_DEFAULT_VM 0 +#define KVM_X86_SW_PROTECTED_VM 1 + #endif /* _ASM_X86_KVM_H */ diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S index d055b82d22cc..59cf6f9065aa 100644 --- a/tools/arch/x86/lib/memcpy_64.S +++ b/tools/arch/x86/lib/memcpy_64.S @@ -1,11 +1,11 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* Copyright 2002 Andi Kleen */ +#include <linux/export.h> #include <linux/linkage.h> #include <asm/errno.h> #include <asm/cpufeatures.h> #include <asm/alternative.h> -#include <asm/export.h> .section .noinstr.text, "ax" @@ -39,7 +39,7 @@ SYM_TYPED_FUNC_START(__memcpy) SYM_FUNC_END(__memcpy) EXPORT_SYMBOL(__memcpy) -SYM_FUNC_ALIAS(memcpy, __memcpy) +SYM_FUNC_ALIAS_MEMFUNC(memcpy, __memcpy) EXPORT_SYMBOL(memcpy) SYM_FUNC_START_LOCAL(memcpy_orig) diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S index 7c59a704c458..0199d56cb479 100644 --- a/tools/arch/x86/lib/memset_64.S +++ b/tools/arch/x86/lib/memset_64.S @@ -1,10 +1,10 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright 2002 Andi Kleen, SuSE Labs */ +#include <linux/export.h> #include <linux/linkage.h> #include <asm/cpufeatures.h> #include <asm/alternative.h> -#include <asm/export.h> .section .noinstr.text, "ax" @@ -40,7 +40,7 @@ SYM_FUNC_START(__memset) SYM_FUNC_END(__memset) EXPORT_SYMBOL(__memset) -SYM_FUNC_ALIAS(memset, __memset) +SYM_FUNC_ALIAS_MEMFUNC(memset, __memset) EXPORT_SYMBOL(memset) SYM_FUNC_START_LOCAL(memset_orig) diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c index cb46667a6b2e..afde9d0c2ea1 100644 --- a/tools/bpf/bpftool/link.c +++ b/tools/bpf/bpftool/link.c @@ -249,18 +249,44 @@ 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) +struct addr_cookie { + __u64 addr; + __u64 cookie; +}; + +static int cmp_addr_cookie(const void *A, const void *B) { - const __u64 *a = A, *b = B; + const struct addr_cookie *a = A, *b = B; - return *a - *b; + if (a->addr == b->addr) + return 0; + return a->addr < b->addr ? -1 : 1; +} + +static struct addr_cookie * +get_addr_cookie_array(__u64 *addrs, __u64 *cookies, __u32 count) +{ + struct addr_cookie *data; + __u32 i; + + data = calloc(count, sizeof(data[0])); + if (!data) { + p_err("mem alloc failed"); + return NULL; + } + for (i = 0; i < count; i++) { + data[i].addr = addrs[i]; + data[i].cookie = cookies[i]; + } + qsort(data, count, sizeof(data[0]), cmp_addr_cookie); + return data; } static void show_kprobe_multi_json(struct bpf_link_info *info, json_writer_t *wtr) { + struct addr_cookie *data; __u32 i, j = 0; - __u64 *addrs; jsonw_bool_field(json_wtr, "retprobe", info->kprobe_multi.flags & BPF_F_KPROBE_MULTI_RETURN); @@ -268,14 +294,20 @@ show_kprobe_multi_json(struct bpf_link_info *info, json_writer_t *wtr) jsonw_uint_field(json_wtr, "missed", info->kprobe_multi.missed); 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); + data = get_addr_cookie_array(u64_to_ptr(info->kprobe_multi.addrs), + u64_to_ptr(info->kprobe_multi.cookies), + info->kprobe_multi.count); + if (!data) + return; /* Load it once for all. */ if (!dd.sym_count) kernel_syms_load(&dd); + if (!dd.sym_count) + goto error; + for (i = 0; i < dd.sym_count; i++) { - if (dd.sym_mapping[i].address != addrs[j]) + if (dd.sym_mapping[i].address != data[j].addr) continue; jsonw_start_object(json_wtr); jsonw_uint_field(json_wtr, "addr", dd.sym_mapping[i].address); @@ -287,11 +319,14 @@ show_kprobe_multi_json(struct bpf_link_info *info, json_writer_t *wtr) } else { jsonw_string_field(json_wtr, "module", dd.sym_mapping[i].module); } + jsonw_uint_field(json_wtr, "cookie", data[j].cookie); jsonw_end_object(json_wtr); if (j++ == info->kprobe_multi.count) break; } jsonw_end_array(json_wtr); +error: + free(data); } static __u64 *u64_to_arr(__u64 val) @@ -334,6 +369,7 @@ show_perf_event_kprobe_json(struct bpf_link_info *info, json_writer_t *wtr) u64_to_ptr(info->perf_event.kprobe.func_name)); jsonw_uint_field(wtr, "offset", info->perf_event.kprobe.offset); jsonw_uint_field(wtr, "missed", info->perf_event.kprobe.missed); + jsonw_uint_field(wtr, "cookie", info->perf_event.kprobe.cookie); } static void @@ -343,6 +379,7 @@ show_perf_event_uprobe_json(struct bpf_link_info *info, json_writer_t *wtr) jsonw_string_field(wtr, "file", u64_to_ptr(info->perf_event.uprobe.file_name)); jsonw_uint_field(wtr, "offset", info->perf_event.uprobe.offset); + jsonw_uint_field(wtr, "cookie", info->perf_event.uprobe.cookie); } static void @@ -350,6 +387,7 @@ 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)); + jsonw_uint_field(wtr, "cookie", info->perf_event.tracepoint.cookie); } static char *perf_config_hw_cache_str(__u64 config) @@ -426,6 +464,8 @@ show_perf_event_event_json(struct bpf_link_info *info, json_writer_t *wtr) else jsonw_uint_field(wtr, "event_config", config); + jsonw_uint_field(wtr, "cookie", info->perf_event.event.cookie); + if (type == PERF_TYPE_HW_CACHE && perf_config) free((void *)perf_config); } @@ -670,8 +710,8 @@ void netfilter_dump_plain(const struct bpf_link_info *info) static void show_kprobe_multi_plain(struct bpf_link_info *info) { + struct addr_cookie *data; __u32 i, j = 0; - __u64 *addrs; if (!info->kprobe_multi.count) return; @@ -683,21 +723,24 @@ static void show_kprobe_multi_plain(struct bpf_link_info *info) printf("func_cnt %u ", info->kprobe_multi.count); if (info->kprobe_multi.missed) printf("missed %llu ", info->kprobe_multi.missed); - addrs = (__u64 *)u64_to_ptr(info->kprobe_multi.addrs); - qsort(addrs, info->kprobe_multi.count, sizeof(__u64), cmp_u64); + data = get_addr_cookie_array(u64_to_ptr(info->kprobe_multi.addrs), + u64_to_ptr(info->kprobe_multi.cookies), + info->kprobe_multi.count); + if (!data) + return; /* Load it once for all. */ if (!dd.sym_count) kernel_syms_load(&dd); if (!dd.sym_count) - return; + goto error; - printf("\n\t%-16s %s", "addr", "func [module]"); + printf("\n\t%-16s %-16s %s", "addr", "cookie", "func [module]"); for (i = 0; i < dd.sym_count; i++) { - if (dd.sym_mapping[i].address != addrs[j]) + if (dd.sym_mapping[i].address != data[j].addr) continue; - printf("\n\t%016lx %s", - dd.sym_mapping[i].address, dd.sym_mapping[i].name); + printf("\n\t%016lx %-16llx %s", + dd.sym_mapping[i].address, data[j].cookie, dd.sym_mapping[i].name); if (dd.sym_mapping[i].module[0] != '\0') printf(" [%s] ", dd.sym_mapping[i].module); else @@ -706,6 +749,8 @@ static void show_kprobe_multi_plain(struct bpf_link_info *info) if (j++ == info->kprobe_multi.count) break; } +error: + free(data); } static void show_uprobe_multi_plain(struct bpf_link_info *info) @@ -754,6 +799,8 @@ static void show_perf_event_kprobe_plain(struct bpf_link_info *info) printf("+%#x", info->perf_event.kprobe.offset); if (info->perf_event.kprobe.missed) printf(" missed %llu", info->perf_event.kprobe.missed); + if (info->perf_event.kprobe.cookie) + printf(" cookie %llu", info->perf_event.kprobe.cookie); printf(" "); } @@ -770,6 +817,8 @@ static void show_perf_event_uprobe_plain(struct bpf_link_info *info) else printf("\n\tuprobe "); printf("%s+%#x ", buf, info->perf_event.uprobe.offset); + if (info->perf_event.uprobe.cookie) + printf("cookie %llu ", info->perf_event.uprobe.cookie); } static void show_perf_event_tracepoint_plain(struct bpf_link_info *info) @@ -781,6 +830,8 @@ static void show_perf_event_tracepoint_plain(struct bpf_link_info *info) return; printf("\n\ttracepoint %s ", buf); + if (info->perf_event.tracepoint.cookie) + printf("cookie %llu ", info->perf_event.tracepoint.cookie); } static void show_perf_event_event_plain(struct bpf_link_info *info) @@ -802,6 +853,9 @@ static void show_perf_event_event_plain(struct bpf_link_info *info) else printf("%llu ", config); + if (info->perf_event.event.cookie) + printf("cookie %llu ", info->perf_event.event.cookie); + if (type == PERF_TYPE_HW_CACHE && perf_config) free((void *)perf_config); } @@ -952,6 +1006,14 @@ again: return -ENOMEM; } info.kprobe_multi.addrs = ptr_to_u64(addrs); + cookies = calloc(count, sizeof(__u64)); + if (!cookies) { + p_err("mem alloc failed"); + free(addrs); + close(fd); + return -ENOMEM; + } + info.kprobe_multi.cookies = ptr_to_u64(cookies); goto again; } } @@ -977,7 +1039,7 @@ again: cookies = calloc(count, sizeof(__u64)); if (!cookies) { p_err("mem alloc failed"); - free(cookies); + free(ref_ctr_offsets); free(offsets); close(fd); return -ENOMEM; diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index feb8e305804f..9cb42a3366c0 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -2298,7 +2298,7 @@ static int profile_open_perf_events(struct profiler_bpf *obj) int map_fd; profile_perf_events = calloc( - sizeof(int), obj->rodata->num_cpu * obj->rodata->num_metric); + obj->rodata->num_cpu * obj->rodata->num_metric, sizeof(int)); if (!profile_perf_events) { p_err("failed to allocate memory for perf_event array: %s", strerror(errno)); diff --git a/tools/include/asm-generic/unaligned.h b/tools/include/asm-generic/unaligned.h index 2fd551915c20..cdd2fd078027 100644 --- a/tools/include/asm-generic/unaligned.h +++ b/tools/include/asm-generic/unaligned.h @@ -105,9 +105,9 @@ static inline u32 get_unaligned_le24(const void *p) static inline void __put_unaligned_be24(const u32 val, u8 *p) { - *p++ = val >> 16; - *p++ = val >> 8; - *p++ = val; + *p++ = (val >> 16) & 0xff; + *p++ = (val >> 8) & 0xff; + *p++ = val & 0xff; } static inline void put_unaligned_be24(const u32 val, void *p) @@ -117,9 +117,9 @@ static inline void put_unaligned_be24(const u32 val, void *p) static inline void __put_unaligned_le24(const u32 val, u8 *p) { - *p++ = val; - *p++ = val >> 8; - *p++ = val >> 16; + *p++ = val & 0xff; + *p++ = (val >> 8) & 0xff; + *p++ = (val >> 16) & 0xff; } static inline void put_unaligned_le24(const u32 val, void *p) @@ -129,12 +129,12 @@ static inline void put_unaligned_le24(const u32 val, void *p) static inline void __put_unaligned_be48(const u64 val, u8 *p) { - *p++ = val >> 40; - *p++ = val >> 32; - *p++ = val >> 24; - *p++ = val >> 16; - *p++ = val >> 8; - *p++ = val; + *p++ = (val >> 40) & 0xff; + *p++ = (val >> 32) & 0xff; + *p++ = (val >> 24) & 0xff; + *p++ = (val >> 16) & 0xff; + *p++ = (val >> 8) & 0xff; + *p++ = val & 0xff; } static inline void put_unaligned_be48(const u64 val, void *p) diff --git a/tools/include/linux/compiler_types.h b/tools/include/linux/compiler_types.h index 1bdd834bdd57..d09f9dc172a4 100644 --- a/tools/include/linux/compiler_types.h +++ b/tools/include/linux/compiler_types.h @@ -36,8 +36,8 @@ #include <linux/compiler-gcc.h> #endif -#ifndef asm_volatile_goto -#define asm_volatile_goto(x...) asm goto(x) +#ifndef asm_goto_output +#define asm_goto_output(x...) asm goto(x) #endif #endif /* __LINUX_COMPILER_TYPES_H */ diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index 756b013fb832..75f00965ab15 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -829,8 +829,21 @@ __SYSCALL(__NR_futex_wait, sys_futex_wait) #define __NR_futex_requeue 456 __SYSCALL(__NR_futex_requeue, sys_futex_requeue) +#define __NR_statmount 457 +__SYSCALL(__NR_statmount, sys_statmount) + +#define __NR_listmount 458 +__SYSCALL(__NR_listmount, sys_listmount) + +#define __NR_lsm_get_self_attr 459 +__SYSCALL(__NR_lsm_get_self_attr, sys_lsm_get_self_attr) +#define __NR_lsm_set_self_attr 460 +__SYSCALL(__NR_lsm_set_self_attr, sys_lsm_set_self_attr) +#define __NR_lsm_list_modules 461 +__SYSCALL(__NR_lsm_list_modules, sys_lsm_list_modules) + #undef __NR_syscalls -#define __NR_syscalls 457 +#define __NR_syscalls 462 /* * 32 bit systems traditionally used different diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h index de723566c5ae..16122819edfe 100644 --- a/tools/include/uapi/drm/drm.h +++ b/tools/include/uapi/drm/drm.h @@ -713,7 +713,8 @@ struct drm_gem_open { /** * DRM_CAP_ASYNC_PAGE_FLIP * - * If set to 1, the driver supports &DRM_MODE_PAGE_FLIP_ASYNC. + * If set to 1, the driver supports &DRM_MODE_PAGE_FLIP_ASYNC for legacy + * page-flips. */ #define DRM_CAP_ASYNC_PAGE_FLIP 0x7 /** @@ -773,6 +774,13 @@ struct drm_gem_open { * :ref:`drm_sync_objects`. */ #define DRM_CAP_SYNCOBJ_TIMELINE 0x14 +/** + * DRM_CAP_ATOMIC_ASYNC_PAGE_FLIP + * + * If set to 1, the driver supports &DRM_MODE_PAGE_FLIP_ASYNC for atomic + * commits. + */ +#define DRM_CAP_ATOMIC_ASYNC_PAGE_FLIP 0x15 /* DRM_IOCTL_GET_CAP ioctl argument type */ struct drm_get_cap { @@ -842,6 +850,31 @@ struct drm_get_cap { */ #define DRM_CLIENT_CAP_WRITEBACK_CONNECTORS 5 +/** + * DRM_CLIENT_CAP_CURSOR_PLANE_HOTSPOT + * + * Drivers for para-virtualized hardware (e.g. vmwgfx, qxl, virtio and + * virtualbox) have additional restrictions for cursor planes (thus + * making cursor planes on those drivers not truly universal,) e.g. + * they need cursor planes to act like one would expect from a mouse + * cursor and have correctly set hotspot properties. + * If this client cap is not set the DRM core will hide cursor plane on + * those virtualized drivers because not setting it implies that the + * client is not capable of dealing with those extra restictions. + * Clients which do set cursor hotspot and treat the cursor plane + * like a mouse cursor should set this property. + * The client must enable &DRM_CLIENT_CAP_ATOMIC first. + * + * Setting this property on drivers which do not special case + * cursor planes (i.e. non-virtualized drivers) will return + * EOPNOTSUPP, which can be used by userspace to gauge + * requirements of the hardware/drivers they're running on. + * + * This capability is always supported for atomic-capable virtualized + * drivers starting from kernel version 6.6. + */ +#define DRM_CLIENT_CAP_CURSOR_PLANE_HOTSPOT 6 + /* DRM_IOCTL_SET_CLIENT_CAP ioctl argument type */ struct drm_set_client_cap { __u64 capability; @@ -893,6 +926,7 @@ struct drm_syncobj_transfer { #define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_ALL (1 << 0) #define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT (1 << 1) #define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE (1 << 2) /* wait for time point to become available */ +#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_DEADLINE (1 << 3) /* set fence deadline to deadline_nsec */ struct drm_syncobj_wait { __u64 handles; /* absolute timeout */ @@ -901,6 +935,14 @@ struct drm_syncobj_wait { __u32 flags; __u32 first_signaled; /* only valid when not waiting all */ __u32 pad; + /** + * @deadline_nsec - fence deadline hint + * + * Deadline hint, in absolute CLOCK_MONOTONIC, to set on backing + * fence(s) if the DRM_SYNCOBJ_WAIT_FLAGS_WAIT_DEADLINE flag is + * set. + */ + __u64 deadline_nsec; }; struct drm_syncobj_timeline_wait { @@ -913,6 +955,14 @@ struct drm_syncobj_timeline_wait { __u32 flags; __u32 first_signaled; /* only valid when not waiting all */ __u32 pad; + /** + * @deadline_nsec - fence deadline hint + * + * Deadline hint, in absolute CLOCK_MONOTONIC, to set on backing + * fence(s) if the DRM_SYNCOBJ_WAIT_FLAGS_WAIT_DEADLINE flag is + * set. + */ + __u64 deadline_nsec; }; /** @@ -1218,6 +1268,26 @@ extern "C" { #define DRM_IOCTL_SYNCOBJ_EVENTFD DRM_IOWR(0xCF, struct drm_syncobj_eventfd) +/** + * DRM_IOCTL_MODE_CLOSEFB - Close a framebuffer. + * + * This closes a framebuffer previously added via ADDFB/ADDFB2. The IOCTL + * argument is a framebuffer object ID. + * + * This IOCTL is similar to &DRM_IOCTL_MODE_RMFB, except it doesn't disable + * planes and CRTCs. As long as the framebuffer is used by a plane, it's kept + * alive. When the plane no longer uses the framebuffer (because the + * framebuffer is replaced with another one, or the plane is disabled), the + * framebuffer is cleaned up. + * + * This is useful to implement flicker-free transitions between two processes. + * + * Depending on the threat model, user-space may want to ensure that the + * framebuffer doesn't expose any sensitive user information: closed + * framebuffers attached to a plane can be read back by the next DRM master. + */ +#define DRM_IOCTL_MODE_CLOSEFB DRM_IOWR(0xD0, struct drm_mode_closefb) + /* * Device specific ioctls should only be in their respective headers * The device specific ioctl range is from 0x40 to 0x9f. diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index 218edb0a96f8..fd4f9574d177 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -693,7 +693,7 @@ typedef struct drm_i915_irq_wait { #define I915_PARAM_HAS_EXEC_FENCE 44 /* Query whether DRM_I915_GEM_EXECBUFFER2 supports the ability to capture - * user specified bufffers for post-mortem debugging of GPU hangs. See + * user-specified buffers for post-mortem debugging of GPU hangs. See * EXEC_OBJECT_CAPTURE. */ #define I915_PARAM_HAS_EXEC_CAPTURE 45 @@ -1606,7 +1606,7 @@ struct drm_i915_gem_busy { * is accurate. * * The returned dword is split into two fields to indicate both - * the engine classess on which the object is being read, and the + * the engine classes on which the object is being read, and the * engine class on which it is currently being written (if any). * * The low word (bits 0:15) indicate if the object is being written @@ -1815,7 +1815,7 @@ struct drm_i915_gem_madvise { __u32 handle; /* Advice: either the buffer will be needed again in the near future, - * or wont be and could be discarded under memory pressure. + * or won't be and could be discarded under memory pressure. */ __u32 madv; @@ -3246,7 +3246,7 @@ struct drm_i915_query_topology_info { * // enough to hold our array of engines. The kernel will fill out the * // item.length for us, which is the number of bytes we need. * // - * // Alternatively a large buffer can be allocated straight away enabling + * // Alternatively a large buffer can be allocated straightaway enabling * // querying in one pass, in which case item.length should contain the * // length of the provided buffer. * err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query); @@ -3256,7 +3256,7 @@ struct drm_i915_query_topology_info { * // Now that we allocated the required number of bytes, we call the ioctl * // again, this time with the data_ptr pointing to our newly allocated * // blob, which the kernel can then populate with info on all engines. - * item.data_ptr = (uintptr_t)&info, + * item.data_ptr = (uintptr_t)&info; * * err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query); * if (err) ... @@ -3286,7 +3286,7 @@ struct drm_i915_query_topology_info { /** * struct drm_i915_engine_info * - * Describes one engine and it's capabilities as known to the driver. + * Describes one engine and its capabilities as known to the driver. */ struct drm_i915_engine_info { /** @engine: Engine class and instance. */ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 7f24d898efbb..d96708380e52 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -847,6 +847,36 @@ union bpf_iter_link_info { * Returns zero on success. On error, -1 is returned and *errno* * is set appropriately. * + * BPF_TOKEN_CREATE + * Description + * Create BPF token with embedded information about what + * BPF-related functionality it allows: + * - a set of allowed bpf() syscall commands; + * - a set of allowed BPF map types to be created with + * BPF_MAP_CREATE command, if BPF_MAP_CREATE itself is allowed; + * - a set of allowed BPF program types and BPF program attach + * types to be loaded with BPF_PROG_LOAD command, if + * BPF_PROG_LOAD itself is allowed. + * + * BPF token is created (derived) from an instance of BPF FS, + * assuming it has necessary delegation mount options specified. + * This BPF token can be passed as an extra parameter to various + * bpf() syscall commands to grant BPF subsystem functionality to + * unprivileged processes. + * + * When created, BPF token is "associated" with the owning + * user namespace of BPF FS instance (super block) that it was + * derived from, and subsequent BPF operations performed with + * BPF token would be performing capabilities checks (i.e., + * CAP_BPF, CAP_PERFMON, CAP_NET_ADMIN, CAP_SYS_ADMIN) within + * that user namespace. Without BPF token, such capabilities + * have to be granted in init user namespace, making bpf() + * syscall incompatible with user namespace, for the most part. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * * NOTES * eBPF objects (maps and programs) can be shared between processes. * @@ -901,6 +931,8 @@ enum bpf_cmd { BPF_ITER_CREATE, BPF_LINK_DETACH, BPF_PROG_BIND_MAP, + BPF_TOKEN_CREATE, + __MAX_BPF_CMD, }; enum bpf_map_type { @@ -951,6 +983,7 @@ enum bpf_map_type { BPF_MAP_TYPE_BLOOM_FILTER, BPF_MAP_TYPE_USER_RINGBUF, BPF_MAP_TYPE_CGRP_STORAGE, + __MAX_BPF_MAP_TYPE }; /* Note that tracing related programs such as @@ -995,6 +1028,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_SK_LOOKUP, BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */ BPF_PROG_TYPE_NETFILTER, + __MAX_BPF_PROG_TYPE }; enum bpf_attach_type { @@ -1330,6 +1364,12 @@ enum { /* Get path from provided FD in BPF_OBJ_PIN/BPF_OBJ_GET commands */ BPF_F_PATH_FD = (1U << 14), + +/* Flag for value_type_btf_obj_fd, the fd is available */ + BPF_F_VTYPE_BTF_OBJ_FD = (1U << 15), + +/* BPF token FD is passed in a corresponding command's token_fd field */ + BPF_F_TOKEN_FD = (1U << 16), }; /* Flags for BPF_PROG_QUERY. */ @@ -1403,6 +1443,15 @@ union bpf_attr { * to using 5 hash functions). */ __u64 map_extra; + + __s32 value_type_btf_obj_fd; /* fd pointing to a BTF + * type data for + * btf_vmlinux_value_type_id. + */ + /* BPF token FD to use with BPF_MAP_CREATE operation. + * If provided, map_flags should have BPF_F_TOKEN_FD flag set. + */ + __s32 map_token_fd; }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -1472,6 +1521,10 @@ union bpf_attr { * truncated), or smaller (if log buffer wasn't filled completely). */ __u32 log_true_size; + /* BPF token FD to use with BPF_PROG_LOAD operation. + * If provided, prog_flags should have BPF_F_TOKEN_FD flag set. + */ + __s32 prog_token_fd; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ @@ -1584,6 +1637,11 @@ union bpf_attr { * truncated), or smaller (if log buffer wasn't filled completely). */ __u32 btf_log_true_size; + __u32 btf_flags; + /* BPF token FD to use with BPF_BTF_LOAD operation. + * If provided, btf_flags should have BPF_F_TOKEN_FD flag set. + */ + __s32 btf_token_fd; }; struct { @@ -1714,6 +1772,11 @@ union bpf_attr { __u32 flags; /* extra flags */ } prog_bind_map; + struct { /* struct used by BPF_TOKEN_CREATE command */ + __u32 flags; + __u32 bpffs_fd; + } token_create; + } __attribute__((aligned(8))); /* The description below is an attempt at providing documentation to eBPF @@ -4839,9 +4902,9 @@ union bpf_attr { * going through the CPU's backlog queue. * * The *flags* argument is reserved and must be 0. The helper is - * currently only supported for tc BPF program types at the ingress - * hook and for veth device types. The peer device must reside in a - * different network namespace. + * currently only supported for tc BPF program types at the + * ingress hook and for veth and netkit target device types. The + * peer device must reside in a different network namespace. * Return * The helper returns **TC_ACT_REDIRECT** on success or * **TC_ACT_SHOT** on error. @@ -6487,7 +6550,7 @@ struct bpf_map_info { __u32 btf_id; __u32 btf_key_type_id; __u32 btf_value_type_id; - __u32 :32; /* alignment pad */ + __u32 btf_vmlinux_id; __u64 map_extra; } __attribute__((aligned(8))); @@ -6563,6 +6626,7 @@ struct bpf_link_info { __u32 count; /* in/out: kprobe_multi function count */ __u32 flags; __u64 missed; + __aligned_u64 cookies; } kprobe_multi; struct { __aligned_u64 path; @@ -6582,6 +6646,7 @@ struct bpf_link_info { __aligned_u64 file_name; /* in/out */ __u32 name_len; __u32 offset; /* offset from file_name */ + __u64 cookie; } uprobe; /* BPF_PERF_EVENT_UPROBE, BPF_PERF_EVENT_URETPROBE */ struct { __aligned_u64 func_name; /* in/out */ @@ -6589,14 +6654,19 @@ struct bpf_link_info { __u32 offset; /* offset from func_name */ __u64 addr; __u64 missed; + __u64 cookie; } kprobe; /* BPF_PERF_EVENT_KPROBE, BPF_PERF_EVENT_KRETPROBE */ struct { __aligned_u64 tp_name; /* in/out */ __u32 name_len; + __u32 :32; + __u64 cookie; } tracepoint; /* BPF_PERF_EVENT_TRACEPOINT */ struct { __u64 config; __u32 type; + __u32 :32; + __u64 cookie; } event; /* BPF_PERF_EVENT_EVENT */ }; } perf_event; @@ -6904,6 +6974,7 @@ enum { BPF_TCP_LISTEN, BPF_TCP_CLOSING, /* Now a valid state */ BPF_TCP_NEW_SYN_RECV, + BPF_TCP_BOUND_INACTIVE, BPF_TCP_MAX_STATES /* Leave at the end! */ }; diff --git a/tools/include/uapi/linux/fcntl.h b/tools/include/uapi/linux/fcntl.h index 6c80f96049bd..282e90aeb163 100644 --- a/tools/include/uapi/linux/fcntl.h +++ b/tools/include/uapi/linux/fcntl.h @@ -116,5 +116,8 @@ #define AT_HANDLE_FID AT_REMOVEDIR /* file handle is needed to compare object identity and may not be usable to open_by_handle_at(2) */ +#if defined(__KERNEL__) +#define AT_GETATTR_NOSEC 0x80000000 +#endif #endif /* _UAPI_LINUX_FCNTL_H */ diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index a0aa05a28cf2..f0d71b2a3f1e 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -974,6 +974,7 @@ enum { IFLA_BOND_AD_LACP_ACTIVE, IFLA_BOND_MISSED_MAX, IFLA_BOND_NS_IP6_TARGET, + IFLA_BOND_COUPLED_CONTROL, __IFLA_BOND_MAX, }; diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 211b86de35ac..c3308536482b 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -16,76 +16,6 @@ #define KVM_API_VERSION 12 -/* *** Deprecated interfaces *** */ - -#define KVM_TRC_SHIFT 16 - -#define KVM_TRC_ENTRYEXIT (1 << KVM_TRC_SHIFT) -#define KVM_TRC_HANDLER (1 << (KVM_TRC_SHIFT + 1)) - -#define KVM_TRC_VMENTRY (KVM_TRC_ENTRYEXIT + 0x01) -#define KVM_TRC_VMEXIT (KVM_TRC_ENTRYEXIT + 0x02) -#define KVM_TRC_PAGE_FAULT (KVM_TRC_HANDLER + 0x01) - -#define KVM_TRC_HEAD_SIZE 12 -#define KVM_TRC_CYCLE_SIZE 8 -#define KVM_TRC_EXTRA_MAX 7 - -#define KVM_TRC_INJ_VIRQ (KVM_TRC_HANDLER + 0x02) -#define KVM_TRC_REDELIVER_EVT (KVM_TRC_HANDLER + 0x03) -#define KVM_TRC_PEND_INTR (KVM_TRC_HANDLER + 0x04) -#define KVM_TRC_IO_READ (KVM_TRC_HANDLER + 0x05) -#define KVM_TRC_IO_WRITE (KVM_TRC_HANDLER + 0x06) -#define KVM_TRC_CR_READ (KVM_TRC_HANDLER + 0x07) -#define KVM_TRC_CR_WRITE (KVM_TRC_HANDLER + 0x08) -#define KVM_TRC_DR_READ (KVM_TRC_HANDLER + 0x09) -#define KVM_TRC_DR_WRITE (KVM_TRC_HANDLER + 0x0A) -#define KVM_TRC_MSR_READ (KVM_TRC_HANDLER + 0x0B) -#define KVM_TRC_MSR_WRITE (KVM_TRC_HANDLER + 0x0C) -#define KVM_TRC_CPUID (KVM_TRC_HANDLER + 0x0D) -#define KVM_TRC_INTR (KVM_TRC_HANDLER + 0x0E) -#define KVM_TRC_NMI (KVM_TRC_HANDLER + 0x0F) -#define KVM_TRC_VMMCALL (KVM_TRC_HANDLER + 0x10) -#define KVM_TRC_HLT (KVM_TRC_HANDLER + 0x11) -#define KVM_TRC_CLTS (KVM_TRC_HANDLER + 0x12) -#define KVM_TRC_LMSW (KVM_TRC_HANDLER + 0x13) -#define KVM_TRC_APIC_ACCESS (KVM_TRC_HANDLER + 0x14) -#define KVM_TRC_TDP_FAULT (KVM_TRC_HANDLER + 0x15) -#define KVM_TRC_GTLB_WRITE (KVM_TRC_HANDLER + 0x16) -#define KVM_TRC_STLB_WRITE (KVM_TRC_HANDLER + 0x17) -#define KVM_TRC_STLB_INVAL (KVM_TRC_HANDLER + 0x18) -#define KVM_TRC_PPC_INSTR (KVM_TRC_HANDLER + 0x19) - -struct kvm_user_trace_setup { - __u32 buf_size; - __u32 buf_nr; -}; - -#define __KVM_DEPRECATED_MAIN_W_0x06 \ - _IOW(KVMIO, 0x06, struct kvm_user_trace_setup) -#define __KVM_DEPRECATED_MAIN_0x07 _IO(KVMIO, 0x07) -#define __KVM_DEPRECATED_MAIN_0x08 _IO(KVMIO, 0x08) - -#define __KVM_DEPRECATED_VM_R_0x70 _IOR(KVMIO, 0x70, struct kvm_assigned_irq) - -struct kvm_breakpoint { - __u32 enabled; - __u32 padding; - __u64 address; -}; - -struct kvm_debug_guest { - __u32 enabled; - __u32 pad; - struct kvm_breakpoint breakpoints[4]; - __u32 singlestep; -}; - -#define __KVM_DEPRECATED_VCPU_W_0x87 _IOW(KVMIO, 0x87, struct kvm_debug_guest) - -/* *** End of deprecated interfaces *** */ - - /* for KVM_SET_USER_MEMORY_REGION */ struct kvm_userspace_memory_region { __u32 slot; @@ -95,6 +25,19 @@ struct kvm_userspace_memory_region { __u64 userspace_addr; /* start of the userspace allocated memory */ }; +/* for KVM_SET_USER_MEMORY_REGION2 */ +struct kvm_userspace_memory_region2 { + __u32 slot; + __u32 flags; + __u64 guest_phys_addr; + __u64 memory_size; + __u64 userspace_addr; + __u64 guest_memfd_offset; + __u32 guest_memfd; + __u32 pad1; + __u64 pad2[14]; +}; + /* * The bit 0 ~ bit 15 of kvm_userspace_memory_region::flags are visible for * userspace, other bits are reserved for kvm internal use which are defined @@ -102,6 +45,7 @@ struct kvm_userspace_memory_region { */ #define KVM_MEM_LOG_DIRTY_PAGES (1UL << 0) #define KVM_MEM_READONLY (1UL << 1) +#define KVM_MEM_GUEST_MEMFD (1UL << 2) /* for KVM_IRQ_LINE */ struct kvm_irq_level { @@ -265,6 +209,7 @@ struct kvm_xen_exit { #define KVM_EXIT_RISCV_CSR 36 #define KVM_EXIT_NOTIFY 37 #define KVM_EXIT_LOONGARCH_IOCSR 38 +#define KVM_EXIT_MEMORY_FAULT 39 /* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */ @@ -518,6 +463,13 @@ struct kvm_run { #define KVM_NOTIFY_CONTEXT_INVALID (1 << 0) __u32 flags; } notify; + /* KVM_EXIT_MEMORY_FAULT */ + struct { +#define KVM_MEMORY_EXIT_FLAG_PRIVATE (1ULL << 3) + __u64 flags; + __u64 gpa; + __u64 size; + } memory_fault; /* Fix the size of the union. */ char padding[256]; }; @@ -945,9 +897,6 @@ struct kvm_ppc_resize_hpt { */ #define KVM_GET_VCPU_MMAP_SIZE _IO(KVMIO, 0x04) /* in bytes */ #define KVM_GET_SUPPORTED_CPUID _IOWR(KVMIO, 0x05, struct kvm_cpuid2) -#define KVM_TRACE_ENABLE __KVM_DEPRECATED_MAIN_W_0x06 -#define KVM_TRACE_PAUSE __KVM_DEPRECATED_MAIN_0x07 -#define KVM_TRACE_DISABLE __KVM_DEPRECATED_MAIN_0x08 #define KVM_GET_EMULATED_CPUID _IOWR(KVMIO, 0x09, struct kvm_cpuid2) #define KVM_GET_MSR_FEATURE_INDEX_LIST _IOWR(KVMIO, 0x0a, struct kvm_msr_list) @@ -1201,6 +1150,11 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE 228 #define KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES 229 #define KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES 230 +#define KVM_CAP_USER_MEMORY2 231 +#define KVM_CAP_MEMORY_FAULT_INFO 232 +#define KVM_CAP_MEMORY_ATTRIBUTES 233 +#define KVM_CAP_GUEST_MEMFD 234 +#define KVM_CAP_VM_TYPES 235 #ifdef KVM_CAP_IRQ_ROUTING @@ -1291,6 +1245,7 @@ struct kvm_x86_mce { #define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL (1 << 4) #define KVM_XEN_HVM_CONFIG_EVTCHN_SEND (1 << 5) #define KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG (1 << 6) +#define KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE (1 << 7) struct kvm_xen_hvm_config { __u32 flags; @@ -1483,6 +1438,8 @@ struct kvm_vfio_spapr_tce { struct kvm_userspace_memory_region) #define KVM_SET_TSS_ADDR _IO(KVMIO, 0x47) #define KVM_SET_IDENTITY_MAP_ADDR _IOW(KVMIO, 0x48, __u64) +#define KVM_SET_USER_MEMORY_REGION2 _IOW(KVMIO, 0x49, \ + struct kvm_userspace_memory_region2) /* enable ucontrol for s390 */ struct kvm_s390_ucas_mapping { @@ -1507,20 +1464,8 @@ struct kvm_s390_ucas_mapping { _IOW(KVMIO, 0x67, struct kvm_coalesced_mmio_zone) #define KVM_UNREGISTER_COALESCED_MMIO \ _IOW(KVMIO, 0x68, struct kvm_coalesced_mmio_zone) -#define KVM_ASSIGN_PCI_DEVICE _IOR(KVMIO, 0x69, \ - struct kvm_assigned_pci_dev) #define KVM_SET_GSI_ROUTING _IOW(KVMIO, 0x6a, struct kvm_irq_routing) -/* deprecated, replaced by KVM_ASSIGN_DEV_IRQ */ -#define KVM_ASSIGN_IRQ __KVM_DEPRECATED_VM_R_0x70 -#define KVM_ASSIGN_DEV_IRQ _IOW(KVMIO, 0x70, struct kvm_assigned_irq) #define KVM_REINJECT_CONTROL _IO(KVMIO, 0x71) -#define KVM_DEASSIGN_PCI_DEVICE _IOW(KVMIO, 0x72, \ - struct kvm_assigned_pci_dev) -#define KVM_ASSIGN_SET_MSIX_NR _IOW(KVMIO, 0x73, \ - struct kvm_assigned_msix_nr) -#define KVM_ASSIGN_SET_MSIX_ENTRY _IOW(KVMIO, 0x74, \ - struct kvm_assigned_msix_entry) -#define KVM_DEASSIGN_DEV_IRQ _IOW(KVMIO, 0x75, struct kvm_assigned_irq) #define KVM_IRQFD _IOW(KVMIO, 0x76, struct kvm_irqfd) #define KVM_CREATE_PIT2 _IOW(KVMIO, 0x77, struct kvm_pit_config) #define KVM_SET_BOOT_CPU_ID _IO(KVMIO, 0x78) @@ -1537,9 +1482,6 @@ struct kvm_s390_ucas_mapping { * KVM_CAP_VM_TSC_CONTROL to set defaults for a VM */ #define KVM_SET_TSC_KHZ _IO(KVMIO, 0xa2) #define KVM_GET_TSC_KHZ _IO(KVMIO, 0xa3) -/* Available with KVM_CAP_PCI_2_3 */ -#define KVM_ASSIGN_SET_INTX_MASK _IOW(KVMIO, 0xa4, \ - struct kvm_assigned_pci_dev) /* Available with KVM_CAP_SIGNAL_MSI */ #define KVM_SIGNAL_MSI _IOW(KVMIO, 0xa5, struct kvm_msi) /* Available with KVM_CAP_PPC_GET_SMMU_INFO */ @@ -1592,8 +1534,6 @@ struct kvm_s390_ucas_mapping { #define KVM_SET_SREGS _IOW(KVMIO, 0x84, struct kvm_sregs) #define KVM_TRANSLATE _IOWR(KVMIO, 0x85, struct kvm_translation) #define KVM_INTERRUPT _IOW(KVMIO, 0x86, struct kvm_interrupt) -/* KVM_DEBUG_GUEST is no longer supported, use KVM_SET_GUEST_DEBUG instead */ -#define KVM_DEBUG_GUEST __KVM_DEPRECATED_VCPU_W_0x87 #define KVM_GET_MSRS _IOWR(KVMIO, 0x88, struct kvm_msrs) #define KVM_SET_MSRS _IOW(KVMIO, 0x89, struct kvm_msrs) #define KVM_SET_CPUID _IOW(KVMIO, 0x8a, struct kvm_cpuid) @@ -2267,4 +2207,24 @@ struct kvm_s390_zpci_op { /* flags for kvm_s390_zpci_op->u.reg_aen.flags */ #define KVM_S390_ZPCIOP_REGAEN_HOST (1 << 0) +/* Available with KVM_CAP_MEMORY_ATTRIBUTES */ +#define KVM_SET_MEMORY_ATTRIBUTES _IOW(KVMIO, 0xd2, struct kvm_memory_attributes) + +struct kvm_memory_attributes { + __u64 address; + __u64 size; + __u64 attributes; + __u64 flags; +}; + +#define KVM_MEMORY_ATTRIBUTE_PRIVATE (1ULL << 3) + +#define KVM_CREATE_GUEST_MEMFD _IOWR(KVMIO, 0xd4, struct kvm_create_guest_memfd) + +struct kvm_create_guest_memfd { + __u64 size; + __u64 flags; + __u64 reserved[6]; +}; + #endif /* __LINUX_KVM_H */ diff --git a/tools/include/uapi/linux/mount.h b/tools/include/uapi/linux/mount.h index bb242fdcfe6b..ad5478dbad00 100644 --- a/tools/include/uapi/linux/mount.h +++ b/tools/include/uapi/linux/mount.h @@ -138,4 +138,74 @@ struct mount_attr { /* List of all mount_attr versions. */ #define MOUNT_ATTR_SIZE_VER0 32 /* sizeof first published struct */ + +/* + * Structure for getting mount/superblock/filesystem info with statmount(2). + * + * The interface is similar to statx(2): individual fields or groups can be + * selected with the @mask argument of statmount(). Kernel will set the @mask + * field according to the supported fields. + * + * If string fields are selected, then the caller needs to pass a buffer that + * has space after the fixed part of the structure. Nul terminated strings are + * copied there and offsets relative to @str are stored in the relevant fields. + * If the buffer is too small, then EOVERFLOW is returned. The actually used + * size is returned in @size. + */ +struct statmount { + __u32 size; /* Total size, including strings */ + __u32 __spare1; + __u64 mask; /* What results were written */ + __u32 sb_dev_major; /* Device ID */ + __u32 sb_dev_minor; + __u64 sb_magic; /* ..._SUPER_MAGIC */ + __u32 sb_flags; /* SB_{RDONLY,SYNCHRONOUS,DIRSYNC,LAZYTIME} */ + __u32 fs_type; /* [str] Filesystem type */ + __u64 mnt_id; /* Unique ID of mount */ + __u64 mnt_parent_id; /* Unique ID of parent (for root == mnt_id) */ + __u32 mnt_id_old; /* Reused IDs used in proc/.../mountinfo */ + __u32 mnt_parent_id_old; + __u64 mnt_attr; /* MOUNT_ATTR_... */ + __u64 mnt_propagation; /* MS_{SHARED,SLAVE,PRIVATE,UNBINDABLE} */ + __u64 mnt_peer_group; /* ID of shared peer group */ + __u64 mnt_master; /* Mount receives propagation from this ID */ + __u64 propagate_from; /* Propagation from in current namespace */ + __u32 mnt_root; /* [str] Root of mount relative to root of fs */ + __u32 mnt_point; /* [str] Mountpoint relative to current root */ + __u64 __spare2[50]; + char str[]; /* Variable size part containing strings */ +}; + +/* + * Structure for passing mount ID and miscellaneous parameters to statmount(2) + * and listmount(2). + * + * For statmount(2) @param represents the request mask. + * For listmount(2) @param represents the last listed mount id (or zero). + */ +struct mnt_id_req { + __u32 size; + __u32 spare; + __u64 mnt_id; + __u64 param; +}; + +/* List of all mnt_id_req versions. */ +#define MNT_ID_REQ_SIZE_VER0 24 /* sizeof first published struct */ + +/* + * @mask bits for statmount(2) + */ +#define STATMOUNT_SB_BASIC 0x00000001U /* Want/got sb_... */ +#define STATMOUNT_MNT_BASIC 0x00000002U /* Want/got mnt_... */ +#define STATMOUNT_PROPAGATE_FROM 0x00000004U /* Want/got propagate_from */ +#define STATMOUNT_MNT_ROOT 0x00000008U /* Want/got mnt_root */ +#define STATMOUNT_MNT_POINT 0x00000010U /* Want/got mnt_point */ +#define STATMOUNT_FS_TYPE 0x00000020U /* Want/got fs_type */ + +/* + * Special @mnt_id values that can be passed to listmount + */ +#define LSMT_ROOT 0xffffffffffffffff /* root mount */ + #endif /* _UAPI_LINUX_MOUNT_H */ diff --git a/tools/include/uapi/linux/stat.h b/tools/include/uapi/linux/stat.h index 7cab2c65d3d7..2f2ee82d5517 100644 --- a/tools/include/uapi/linux/stat.h +++ b/tools/include/uapi/linux/stat.h @@ -154,6 +154,7 @@ struct statx { #define STATX_BTIME 0x00000800U /* Want/got stx_btime */ #define STATX_MNT_ID 0x00001000U /* Got stx_mnt_id */ #define STATX_DIOALIGN 0x00002000U /* Want/got direct I/O alignment info */ +#define STATX_MNT_ID_UNIQUE 0x00004000U /* Want/got extended stx_mount_id */ #define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */ diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build index 2d0c282c8588..b6619199a706 100644 --- a/tools/lib/bpf/Build +++ b/tools/lib/bpf/Build @@ -1,4 +1,4 @@ libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o \ netlink.o bpf_prog_linfo.o libbpf_probes.o hashmap.o \ btf_dump.o ringbuf.o strset.o linker.o gen_loader.o relo_core.o \ - usdt.o zip.o elf.o + usdt.o zip.o elf.o features.o diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 9dc9625651dc..97ec005c3c47 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -103,7 +103,7 @@ int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int attempts) * [0] https://lore.kernel.org/bpf/20201201215900.3569844-1-guro@fb.com/ * [1] d05512618056 ("bpf: Add bpf_ktime_get_coarse_ns helper") */ -int probe_memcg_account(void) +int probe_memcg_account(int token_fd) { const size_t attr_sz = offsetofend(union bpf_attr, attach_btf_obj_fd); struct bpf_insn insns[] = { @@ -120,6 +120,9 @@ int probe_memcg_account(void) attr.insns = ptr_to_u64(insns); attr.insn_cnt = insn_cnt; attr.license = ptr_to_u64("GPL"); + attr.prog_token_fd = token_fd; + if (token_fd) + attr.prog_flags |= BPF_F_TOKEN_FD; prog_fd = sys_bpf_fd(BPF_PROG_LOAD, &attr, attr_sz); if (prog_fd >= 0) { @@ -146,7 +149,7 @@ int bump_rlimit_memlock(void) struct rlimit rlim; /* if kernel supports memcg-based accounting, skip bumping RLIMIT_MEMLOCK */ - if (memlock_bumped || kernel_supports(NULL, FEAT_MEMCG_ACCOUNT)) + if (memlock_bumped || feat_supported(NULL, FEAT_MEMCG_ACCOUNT)) return 0; memlock_bumped = true; @@ -169,7 +172,7 @@ int bpf_map_create(enum bpf_map_type map_type, __u32 max_entries, const struct bpf_map_create_opts *opts) { - const size_t attr_sz = offsetofend(union bpf_attr, map_extra); + const size_t attr_sz = offsetofend(union bpf_attr, map_token_fd); union bpf_attr attr; int fd; @@ -181,7 +184,7 @@ int bpf_map_create(enum bpf_map_type map_type, return libbpf_err(-EINVAL); attr.map_type = map_type; - if (map_name && kernel_supports(NULL, FEAT_PROG_NAME)) + if (map_name && feat_supported(NULL, FEAT_PROG_NAME)) libbpf_strlcpy(attr.map_name, map_name, sizeof(attr.map_name)); attr.key_size = key_size; attr.value_size = value_size; @@ -191,6 +194,7 @@ int bpf_map_create(enum bpf_map_type map_type, attr.btf_key_type_id = OPTS_GET(opts, btf_key_type_id, 0); attr.btf_value_type_id = OPTS_GET(opts, btf_value_type_id, 0); attr.btf_vmlinux_value_type_id = OPTS_GET(opts, btf_vmlinux_value_type_id, 0); + attr.value_type_btf_obj_fd = OPTS_GET(opts, value_type_btf_obj_fd, 0); attr.inner_map_fd = OPTS_GET(opts, inner_map_fd, 0); attr.map_flags = OPTS_GET(opts, map_flags, 0); @@ -198,6 +202,8 @@ int bpf_map_create(enum bpf_map_type map_type, attr.numa_node = OPTS_GET(opts, numa_node, 0); attr.map_ifindex = OPTS_GET(opts, map_ifindex, 0); + attr.map_token_fd = OPTS_GET(opts, token_fd, 0); + fd = sys_bpf_fd(BPF_MAP_CREATE, &attr, attr_sz); return libbpf_err_errno(fd); } @@ -232,7 +238,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, size_t insn_cnt, struct bpf_prog_load_opts *opts) { - const size_t attr_sz = offsetofend(union bpf_attr, log_true_size); + const size_t attr_sz = offsetofend(union bpf_attr, prog_token_fd); void *finfo = NULL, *linfo = NULL; const char *func_info, *line_info; __u32 log_size, log_level, attach_prog_fd, attach_btf_obj_fd; @@ -261,8 +267,9 @@ int bpf_prog_load(enum bpf_prog_type prog_type, attr.prog_flags = OPTS_GET(opts, prog_flags, 0); attr.prog_ifindex = OPTS_GET(opts, prog_ifindex, 0); attr.kern_version = OPTS_GET(opts, kern_version, 0); + attr.prog_token_fd = OPTS_GET(opts, token_fd, 0); - if (prog_name && kernel_supports(NULL, FEAT_PROG_NAME)) + if (prog_name && feat_supported(NULL, FEAT_PROG_NAME)) libbpf_strlcpy(attr.prog_name, prog_name, sizeof(attr.prog_name)); attr.license = ptr_to_u64(license); @@ -1182,7 +1189,7 @@ int bpf_raw_tracepoint_open(const char *name, int prog_fd) int bpf_btf_load(const void *btf_data, size_t btf_size, struct bpf_btf_load_opts *opts) { - const size_t attr_sz = offsetofend(union bpf_attr, btf_log_true_size); + const size_t attr_sz = offsetofend(union bpf_attr, btf_token_fd); union bpf_attr attr; char *log_buf; size_t log_size; @@ -1207,6 +1214,10 @@ int bpf_btf_load(const void *btf_data, size_t btf_size, struct bpf_btf_load_opts attr.btf = ptr_to_u64(btf_data); attr.btf_size = btf_size; + + attr.btf_flags = OPTS_GET(opts, btf_flags, 0); + attr.btf_token_fd = OPTS_GET(opts, token_fd, 0); + /* log_level == 0 and log_buf != NULL means "try loading without * log_buf, but retry with log_buf and log_level=1 on error", which is * consistent across low-level and high-level BTF and program loading @@ -1287,3 +1298,20 @@ int bpf_prog_bind_map(int prog_fd, int map_fd, ret = sys_bpf(BPF_PROG_BIND_MAP, &attr, attr_sz); return libbpf_err_errno(ret); } + +int bpf_token_create(int bpffs_fd, struct bpf_token_create_opts *opts) +{ + const size_t attr_sz = offsetofend(union bpf_attr, token_create); + union bpf_attr attr; + int fd; + + if (!OPTS_VALID(opts, bpf_token_create_opts)) + return libbpf_err(-EINVAL); + + memset(&attr, 0, attr_sz); + attr.token_create.bpffs_fd = bpffs_fd; + attr.token_create.flags = OPTS_GET(opts, flags, 0); + + fd = sys_bpf_fd(BPF_TOKEN_CREATE, &attr, attr_sz); + return libbpf_err_errno(fd); +} diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index d0f53772bdc0..1441f642c563 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -51,8 +51,12 @@ struct bpf_map_create_opts { __u32 numa_node; __u32 map_ifindex; + __s32 value_type_btf_obj_fd; + + __u32 token_fd; + size_t :0; }; -#define bpf_map_create_opts__last_field map_ifindex +#define bpf_map_create_opts__last_field token_fd LIBBPF_API int bpf_map_create(enum bpf_map_type map_type, const char *map_name, @@ -102,9 +106,10 @@ struct bpf_prog_load_opts { * If kernel doesn't support this feature, log_size is left unchanged. */ __u32 log_true_size; + __u32 token_fd; size_t :0; }; -#define bpf_prog_load_opts__last_field log_true_size +#define bpf_prog_load_opts__last_field token_fd LIBBPF_API int bpf_prog_load(enum bpf_prog_type prog_type, const char *prog_name, const char *license, @@ -130,9 +135,12 @@ struct bpf_btf_load_opts { * If kernel doesn't support this feature, log_size is left unchanged. */ __u32 log_true_size; + + __u32 btf_flags; + __u32 token_fd; size_t :0; }; -#define bpf_btf_load_opts__last_field log_true_size +#define bpf_btf_load_opts__last_field token_fd LIBBPF_API int bpf_btf_load(const void *btf_data, size_t btf_size, struct bpf_btf_load_opts *opts); @@ -640,6 +648,30 @@ struct bpf_test_run_opts { LIBBPF_API int bpf_prog_test_run_opts(int prog_fd, struct bpf_test_run_opts *opts); +struct bpf_token_create_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + __u32 flags; + size_t :0; +}; +#define bpf_token_create_opts__last_field flags + +/** + * @brief **bpf_token_create()** creates a new instance of BPF token derived + * from specified BPF FS mount point. + * + * BPF token created with this API can be passed to bpf() syscall for + * commands like BPF_PROG_LOAD, BPF_MAP_CREATE, etc. + * + * @param bpffs_fd FD for BPF FS instance from which to derive a BPF token + * instance. + * @param opts optional BPF token creation options, can be NULL + * + * @return BPF token FD > 0, on success; negative error code, otherwise (errno + * is also set to the error code) + */ +LIBBPF_API int bpf_token_create(int bpffs_fd, + struct bpf_token_create_opts *opts); + #ifdef __cplusplus } /* extern "C" */ #endif diff --git a/tools/lib/bpf/bpf_core_read.h b/tools/lib/bpf/bpf_core_read.h index 7325a12692a3..5aec301e9585 100644 --- a/tools/lib/bpf/bpf_core_read.h +++ b/tools/lib/bpf/bpf_core_read.h @@ -268,7 +268,7 @@ enum bpf_enum_value_kind { * a relocation, which records BTF type ID describing root struct/union and an * accessor string which describes exact embedded field that was used to take * an address. See detailed description of this relocation format and - * semantics in comments to struct bpf_field_reloc in libbpf_internal.h. + * semantics in comments to struct bpf_core_relo in include/uapi/linux/bpf.h. * * This relocation allows libbpf to adjust BPF instruction to use correct * actual field offset, based on target kernel BTF type that matches original diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index ee95fd379d4d..ec92b87cae01 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -1317,7 +1317,9 @@ struct btf *btf__parse_split(const char *path, struct btf *base_btf) static void *btf_get_raw_data(const struct btf *btf, __u32 *size, bool swap_endian); -int btf_load_into_kernel(struct btf *btf, char *log_buf, size_t log_sz, __u32 log_level) +int btf_load_into_kernel(struct btf *btf, + char *log_buf, size_t log_sz, __u32 log_level, + int token_fd) { LIBBPF_OPTS(bpf_btf_load_opts, opts); __u32 buf_sz = 0, raw_size; @@ -1367,6 +1369,10 @@ retry_load: opts.log_level = log_level; } + opts.token_fd = token_fd; + if (token_fd) + opts.btf_flags |= BPF_F_TOKEN_FD; + btf->fd = bpf_btf_load(raw_data, raw_size, &opts); if (btf->fd < 0) { /* time to turn on verbose mode and try again */ @@ -1394,7 +1400,7 @@ done: int btf__load_into_kernel(struct btf *btf) { - return btf_load_into_kernel(btf, NULL, 0, 0); + return btf_load_into_kernel(btf, NULL, 0, 0, 0); } int btf__fd(const struct btf *btf) diff --git a/tools/lib/bpf/elf.c b/tools/lib/bpf/elf.c index b02faec748a5..c92e02394159 100644 --- a/tools/lib/bpf/elf.c +++ b/tools/lib/bpf/elf.c @@ -11,8 +11,6 @@ #include "libbpf_internal.h" #include "str_error.h" -#define STRERR_BUFSIZE 128 - /* A SHT_GNU_versym section holds 16-bit words. This bit is set if * the symbol is hidden and can only be seen when referenced using an * explicit version number. This is a GNU extension. diff --git a/tools/lib/bpf/features.c b/tools/lib/bpf/features.c new file mode 100644 index 000000000000..5a5c766bf615 --- /dev/null +++ b/tools/lib/bpf/features.c @@ -0,0 +1,503 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ +#include <linux/kernel.h> +#include <linux/filter.h> +#include "bpf.h" +#include "libbpf.h" +#include "libbpf_common.h" +#include "libbpf_internal.h" +#include "str_error.h" + +static inline __u64 ptr_to_u64(const void *ptr) +{ + return (__u64)(unsigned long)ptr; +} + +int probe_fd(int fd) +{ + if (fd >= 0) + close(fd); + return fd >= 0; +} + +static int probe_kern_prog_name(int token_fd) +{ + const size_t attr_sz = offsetofend(union bpf_attr, prog_name); + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + union bpf_attr attr; + int ret; + + memset(&attr, 0, attr_sz); + attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; + attr.license = ptr_to_u64("GPL"); + attr.insns = ptr_to_u64(insns); + attr.insn_cnt = (__u32)ARRAY_SIZE(insns); + attr.prog_token_fd = token_fd; + if (token_fd) + attr.prog_flags |= BPF_F_TOKEN_FD; + libbpf_strlcpy(attr.prog_name, "libbpf_nametest", sizeof(attr.prog_name)); + + /* make sure loading with name works */ + ret = sys_bpf_prog_load(&attr, attr_sz, PROG_LOAD_ATTEMPTS); + return probe_fd(ret); +} + +static int probe_kern_global_data(int token_fd) +{ + char *cp, errmsg[STRERR_BUFSIZE]; + struct bpf_insn insns[] = { + BPF_LD_MAP_VALUE(BPF_REG_1, 0, 16), + BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 42), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + LIBBPF_OPTS(bpf_map_create_opts, map_opts, + .token_fd = token_fd, + .map_flags = token_fd ? BPF_F_TOKEN_FD : 0, + ); + LIBBPF_OPTS(bpf_prog_load_opts, prog_opts, + .token_fd = token_fd, + .prog_flags = token_fd ? BPF_F_TOKEN_FD : 0, + ); + int ret, map, insn_cnt = ARRAY_SIZE(insns); + + map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_global", sizeof(int), 32, 1, &map_opts); + if (map < 0) { + ret = -errno; + cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); + pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n", + __func__, cp, -ret); + return ret; + } + + insns[0].imm = map; + + ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, &prog_opts); + close(map); + return probe_fd(ret); +} + +static int probe_kern_btf(int token_fd) +{ + static const char strs[] = "\0int"; + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs), token_fd)); +} + +static int probe_kern_btf_func(int token_fd) +{ + static const char strs[] = "\0int\0x\0a"; + /* void x(int a) {} */ + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* FUNC_PROTO */ /* [2] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0), + BTF_PARAM_ENC(7, 1), + /* FUNC x */ /* [3] */ + BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0), 2), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs), token_fd)); +} + +static int probe_kern_btf_func_global(int token_fd) +{ + static const char strs[] = "\0int\0x\0a"; + /* static void x(int a) {} */ + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* FUNC_PROTO */ /* [2] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0), + BTF_PARAM_ENC(7, 1), + /* FUNC x BTF_FUNC_GLOBAL */ /* [3] */ + BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 2), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs), token_fd)); +} + +static int probe_kern_btf_datasec(int token_fd) +{ + static const char strs[] = "\0x\0.data"; + /* static int a; */ + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* VAR x */ /* [2] */ + BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1), + BTF_VAR_STATIC, + /* DATASEC val */ /* [3] */ + BTF_TYPE_ENC(3, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4), + BTF_VAR_SECINFO_ENC(2, 0, 4), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs), token_fd)); +} + +static int probe_kern_btf_float(int token_fd) +{ + static const char strs[] = "\0float"; + __u32 types[] = { + /* float */ + BTF_TYPE_FLOAT_ENC(1, 4), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs), token_fd)); +} + +static int probe_kern_btf_decl_tag(int token_fd) +{ + static const char strs[] = "\0tag"; + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* VAR x */ /* [2] */ + BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1), + BTF_VAR_STATIC, + /* attr */ + BTF_TYPE_DECL_TAG_ENC(1, 2, -1), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs), token_fd)); +} + +static int probe_kern_btf_type_tag(int token_fd) +{ + static const char strs[] = "\0tag"; + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* attr */ + BTF_TYPE_TYPE_TAG_ENC(1, 1), /* [2] */ + /* ptr */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 2), /* [3] */ + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs), token_fd)); +} + +static int probe_kern_array_mmap(int token_fd) +{ + LIBBPF_OPTS(bpf_map_create_opts, opts, + .map_flags = BPF_F_MMAPABLE | (token_fd ? BPF_F_TOKEN_FD : 0), + .token_fd = token_fd, + ); + int fd; + + fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_mmap", sizeof(int), sizeof(int), 1, &opts); + return probe_fd(fd); +} + +static int probe_kern_exp_attach_type(int token_fd) +{ + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE, + .token_fd = token_fd, + .prog_flags = token_fd ? BPF_F_TOKEN_FD : 0, + ); + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + int fd, insn_cnt = ARRAY_SIZE(insns); + + /* use any valid combination of program type and (optional) + * non-zero expected attach type (i.e., not a BPF_CGROUP_INET_INGRESS) + * to see if kernel supports expected_attach_type field for + * BPF_PROG_LOAD command + */ + fd = bpf_prog_load(BPF_PROG_TYPE_CGROUP_SOCK, NULL, "GPL", insns, insn_cnt, &opts); + return probe_fd(fd); +} + +static int probe_kern_probe_read_kernel(int token_fd) +{ + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .token_fd = token_fd, + .prog_flags = token_fd ? BPF_F_TOKEN_FD : 0, + ); + struct bpf_insn insns[] = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), /* r1 = r10 (fp) */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), /* r1 += -8 */ + BPF_MOV64_IMM(BPF_REG_2, 8), /* r2 = 8 */ + BPF_MOV64_IMM(BPF_REG_3, 0), /* r3 = 0 */ + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_probe_read_kernel), + BPF_EXIT_INSN(), + }; + int fd, insn_cnt = ARRAY_SIZE(insns); + + fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, &opts); + return probe_fd(fd); +} + +static int probe_prog_bind_map(int token_fd) +{ + char *cp, errmsg[STRERR_BUFSIZE]; + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + LIBBPF_OPTS(bpf_map_create_opts, map_opts, + .token_fd = token_fd, + .map_flags = token_fd ? BPF_F_TOKEN_FD : 0, + ); + LIBBPF_OPTS(bpf_prog_load_opts, prog_opts, + .token_fd = token_fd, + .prog_flags = token_fd ? BPF_F_TOKEN_FD : 0, + ); + int ret, map, prog, insn_cnt = ARRAY_SIZE(insns); + + map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_det_bind", sizeof(int), 32, 1, &map_opts); + if (map < 0) { + ret = -errno; + cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); + pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n", + __func__, cp, -ret); + return ret; + } + + prog = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, &prog_opts); + if (prog < 0) { + close(map); + return 0; + } + + ret = bpf_prog_bind_map(prog, map, NULL); + + close(map); + close(prog); + + return ret >= 0; +} + +static int probe_module_btf(int token_fd) +{ + static const char strs[] = "\0int"; + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), + }; + struct bpf_btf_info info; + __u32 len = sizeof(info); + char name[16]; + int fd, err; + + fd = libbpf__load_raw_btf((char *)types, sizeof(types), strs, sizeof(strs), token_fd); + if (fd < 0) + return 0; /* BTF not supported at all */ + + memset(&info, 0, sizeof(info)); + info.name = ptr_to_u64(name); + info.name_len = sizeof(name); + + /* check that BPF_OBJ_GET_INFO_BY_FD supports specifying name pointer; + * kernel's module BTF support coincides with support for + * name/name_len fields in struct bpf_btf_info. + */ + err = bpf_btf_get_info_by_fd(fd, &info, &len); + close(fd); + return !err; +} + +static int probe_perf_link(int token_fd) +{ + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .token_fd = token_fd, + .prog_flags = token_fd ? BPF_F_TOKEN_FD : 0, + ); + int prog_fd, link_fd, err; + + prog_fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", + insns, ARRAY_SIZE(insns), &opts); + if (prog_fd < 0) + return -errno; + + /* use invalid perf_event FD to get EBADF, if link is supported; + * otherwise EINVAL should be returned + */ + link_fd = bpf_link_create(prog_fd, -1, BPF_PERF_EVENT, NULL); + err = -errno; /* close() can clobber errno */ + + if (link_fd >= 0) + close(link_fd); + close(prog_fd); + + return link_fd < 0 && err == -EBADF; +} + +static int probe_uprobe_multi_link(int token_fd) +{ + LIBBPF_OPTS(bpf_prog_load_opts, load_opts, + .expected_attach_type = BPF_TRACE_UPROBE_MULTI, + .token_fd = token_fd, + .prog_flags = token_fd ? BPF_F_TOKEN_FD : 0, + ); + LIBBPF_OPTS(bpf_link_create_opts, link_opts); + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + int prog_fd, link_fd, err; + unsigned long offset = 0; + + prog_fd = bpf_prog_load(BPF_PROG_TYPE_KPROBE, NULL, "GPL", + insns, ARRAY_SIZE(insns), &load_opts); + if (prog_fd < 0) + return -errno; + + /* Creating uprobe in '/' binary should fail with -EBADF. */ + link_opts.uprobe_multi.path = "/"; + link_opts.uprobe_multi.offsets = &offset; + link_opts.uprobe_multi.cnt = 1; + + link_fd = bpf_link_create(prog_fd, -1, BPF_TRACE_UPROBE_MULTI, &link_opts); + err = -errno; /* close() can clobber errno */ + + if (link_fd >= 0) + close(link_fd); + close(prog_fd); + + return link_fd < 0 && err == -EBADF; +} + +static int probe_kern_bpf_cookie(int token_fd) +{ + struct bpf_insn insns[] = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_attach_cookie), + BPF_EXIT_INSN(), + }; + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .token_fd = token_fd, + .prog_flags = token_fd ? BPF_F_TOKEN_FD : 0, + ); + int ret, insn_cnt = ARRAY_SIZE(insns); + + ret = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, &opts); + return probe_fd(ret); +} + +static int probe_kern_btf_enum64(int token_fd) +{ + static const char strs[] = "\0enum64"; + __u32 types[] = { + BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_ENUM64, 0, 0), 8), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs), token_fd)); +} + +typedef int (*feature_probe_fn)(int /* token_fd */); + +static struct kern_feature_cache feature_cache; + +static struct kern_feature_desc { + const char *desc; + feature_probe_fn probe; +} feature_probes[__FEAT_CNT] = { + [FEAT_PROG_NAME] = { + "BPF program name", probe_kern_prog_name, + }, + [FEAT_GLOBAL_DATA] = { + "global variables", probe_kern_global_data, + }, + [FEAT_BTF] = { + "minimal BTF", probe_kern_btf, + }, + [FEAT_BTF_FUNC] = { + "BTF functions", probe_kern_btf_func, + }, + [FEAT_BTF_GLOBAL_FUNC] = { + "BTF global function", probe_kern_btf_func_global, + }, + [FEAT_BTF_DATASEC] = { + "BTF data section and variable", probe_kern_btf_datasec, + }, + [FEAT_ARRAY_MMAP] = { + "ARRAY map mmap()", probe_kern_array_mmap, + }, + [FEAT_EXP_ATTACH_TYPE] = { + "BPF_PROG_LOAD expected_attach_type attribute", + probe_kern_exp_attach_type, + }, + [FEAT_PROBE_READ_KERN] = { + "bpf_probe_read_kernel() helper", probe_kern_probe_read_kernel, + }, + [FEAT_PROG_BIND_MAP] = { + "BPF_PROG_BIND_MAP support", probe_prog_bind_map, + }, + [FEAT_MODULE_BTF] = { + "module BTF support", probe_module_btf, + }, + [FEAT_BTF_FLOAT] = { + "BTF_KIND_FLOAT support", probe_kern_btf_float, + }, + [FEAT_PERF_LINK] = { + "BPF perf link support", probe_perf_link, + }, + [FEAT_BTF_DECL_TAG] = { + "BTF_KIND_DECL_TAG support", probe_kern_btf_decl_tag, + }, + [FEAT_BTF_TYPE_TAG] = { + "BTF_KIND_TYPE_TAG support", probe_kern_btf_type_tag, + }, + [FEAT_MEMCG_ACCOUNT] = { + "memcg-based memory accounting", probe_memcg_account, + }, + [FEAT_BPF_COOKIE] = { + "BPF cookie support", probe_kern_bpf_cookie, + }, + [FEAT_BTF_ENUM64] = { + "BTF_KIND_ENUM64 support", probe_kern_btf_enum64, + }, + [FEAT_SYSCALL_WRAPPER] = { + "Kernel using syscall wrapper", probe_kern_syscall_wrapper, + }, + [FEAT_UPROBE_MULTI_LINK] = { + "BPF multi-uprobe link support", probe_uprobe_multi_link, + }, +}; + +bool feat_supported(struct kern_feature_cache *cache, enum kern_feature_id feat_id) +{ + struct kern_feature_desc *feat = &feature_probes[feat_id]; + int ret; + + /* assume global feature cache, unless custom one is provided */ + if (!cache) + cache = &feature_cache; + + if (READ_ONCE(cache->res[feat_id]) == FEAT_UNKNOWN) { + ret = feat->probe(cache->token_fd); + if (ret > 0) { + WRITE_ONCE(cache->res[feat_id], FEAT_SUPPORTED); + } else if (ret == 0) { + WRITE_ONCE(cache->res[feat_id], FEAT_MISSING); + } else { + pr_warn("Detection of kernel %s support failed: %d\n", feat->desc, ret); + WRITE_ONCE(cache->res[feat_id], FEAT_MISSING); + } + } + + return READ_ONCE(cache->res[feat_id]) == FEAT_SUPPORTED; +} diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index afd09571c482..fa7094ff3e66 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -59,6 +59,8 @@ #define BPF_FS_MAGIC 0xcafe4a11 #endif +#define BPF_FS_DEFAULT_PATH "/sys/fs/bpf" + #define BPF_INSN_SZ (sizeof(struct bpf_insn)) /* vsprintf() in __base_pr() uses nonliteral format string. It may break @@ -70,6 +72,7 @@ static struct bpf_map *bpf_object__add_map(struct bpf_object *obj); static bool prog_is_subprog(const struct bpf_object *obj, const struct bpf_program *prog); +static int map_set_def_max_entries(struct bpf_map *map); static const char * const attach_type_name[] = { [BPF_CGROUP_INET_INGRESS] = "cgroup_inet_ingress", @@ -527,6 +530,7 @@ struct bpf_map { struct bpf_map_def def; __u32 numa_node; __u32 btf_var_idx; + int mod_btf_fd; __u32 btf_key_type_id; __u32 btf_value_type_id; __u32 btf_vmlinux_value_type_id; @@ -693,6 +697,10 @@ struct bpf_object { struct usdt_manager *usdt_man; + struct kern_feature_cache *feat_cache; + char *token_path; + int token_fd; + char path[]; }; @@ -930,22 +938,29 @@ find_member_by_name(const struct btf *btf, const struct btf_type *t, return NULL; } +static int find_ksym_btf_id(struct bpf_object *obj, const char *ksym_name, + __u16 kind, struct btf **res_btf, + struct module_btf **res_mod_btf); + #define STRUCT_OPS_VALUE_PREFIX "bpf_struct_ops_" static int find_btf_by_prefix_kind(const struct btf *btf, const char *prefix, const char *name, __u32 kind); static int -find_struct_ops_kern_types(const struct btf *btf, const char *tname, +find_struct_ops_kern_types(struct bpf_object *obj, const char *tname, + struct module_btf **mod_btf, const struct btf_type **type, __u32 *type_id, const struct btf_type **vtype, __u32 *vtype_id, const struct btf_member **data_member) { const struct btf_type *kern_type, *kern_vtype; const struct btf_member *kern_data_member; + struct btf *btf; __s32 kern_vtype_id, kern_type_id; __u32 i; - kern_type_id = btf__find_by_name_kind(btf, tname, BTF_KIND_STRUCT); + kern_type_id = find_ksym_btf_id(obj, tname, BTF_KIND_STRUCT, + &btf, mod_btf); if (kern_type_id < 0) { pr_warn("struct_ops init_kern: struct %s is not found in kernel BTF\n", tname); @@ -999,14 +1014,16 @@ static bool bpf_map__is_struct_ops(const struct bpf_map *map) } /* Init the map's fields that depend on kern_btf */ -static int bpf_map__init_kern_struct_ops(struct bpf_map *map, - const struct btf *btf, - const struct btf *kern_btf) +static int bpf_map__init_kern_struct_ops(struct bpf_map *map) { const struct btf_member *member, *kern_member, *kern_data_member; const struct btf_type *type, *kern_type, *kern_vtype; __u32 i, kern_type_id, kern_vtype_id, kern_data_off; + struct bpf_object *obj = map->obj; + const struct btf *btf = obj->btf; struct bpf_struct_ops *st_ops; + const struct btf *kern_btf; + struct module_btf *mod_btf; void *data, *kern_data; const char *tname; int err; @@ -1014,16 +1031,19 @@ static int bpf_map__init_kern_struct_ops(struct bpf_map *map, st_ops = map->st_ops; type = st_ops->type; tname = st_ops->tname; - err = find_struct_ops_kern_types(kern_btf, tname, + err = find_struct_ops_kern_types(obj, tname, &mod_btf, &kern_type, &kern_type_id, &kern_vtype, &kern_vtype_id, &kern_data_member); if (err) return err; + kern_btf = mod_btf ? mod_btf->btf : obj->btf_vmlinux; + pr_debug("struct_ops init_kern %s: type_id:%u kern_type_id:%u kern_vtype_id:%u\n", map->name, st_ops->type_id, kern_type_id, kern_vtype_id); + map->mod_btf_fd = mod_btf ? mod_btf->fd : -1; map->def.value_size = kern_vtype->size; map->btf_vmlinux_value_type_id = kern_vtype_id; @@ -1099,6 +1119,8 @@ static int bpf_map__init_kern_struct_ops(struct bpf_map *map, return -ENOTSUP; } + if (mod_btf) + prog->attach_btf_obj_fd = mod_btf->fd; prog->attach_btf_id = kern_type_id; prog->expected_attach_type = kern_member_idx; @@ -1141,8 +1163,7 @@ static int bpf_object__init_kern_struct_ops_maps(struct bpf_object *obj) if (!bpf_map__is_struct_ops(map)) continue; - err = bpf_map__init_kern_struct_ops(map, obj->btf, - obj->btf_vmlinux); + err = bpf_map__init_kern_struct_ops(map); if (err) return err; } @@ -2216,7 +2237,7 @@ static int build_map_pin_path(struct bpf_map *map, const char *path) int err; if (!path) - path = "/sys/fs/bpf"; + path = BPF_FS_DEFAULT_PATH; err = pathname_concat(buf, sizeof(buf), path, bpf_map__name(map)); if (err) @@ -3225,7 +3246,7 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) } else { /* currently BPF_BTF_LOAD only supports log_level 1 */ err = btf_load_into_kernel(kern_btf, obj->log_buf, obj->log_size, - obj->log_level ? 1 : 0); + obj->log_level ? 1 : 0, obj->token_fd); } if (sanitize) { if (!err) { @@ -4546,6 +4567,58 @@ int bpf_map__set_max_entries(struct bpf_map *map, __u32 max_entries) return 0; } +static int bpf_object_prepare_token(struct bpf_object *obj) +{ + const char *bpffs_path; + int bpffs_fd = -1, token_fd, err; + bool mandatory; + enum libbpf_print_level level; + + /* token is explicitly prevented */ + if (obj->token_path && obj->token_path[0] == '\0') { + pr_debug("object '%s': token is prevented, skipping...\n", obj->name); + return 0; + } + + mandatory = obj->token_path != NULL; + level = mandatory ? LIBBPF_WARN : LIBBPF_DEBUG; + + bpffs_path = obj->token_path ?: BPF_FS_DEFAULT_PATH; + bpffs_fd = open(bpffs_path, O_DIRECTORY, O_RDWR); + if (bpffs_fd < 0) { + err = -errno; + __pr(level, "object '%s': failed (%d) to open BPF FS mount at '%s'%s\n", + obj->name, err, bpffs_path, + mandatory ? "" : ", skipping optional step..."); + return mandatory ? err : 0; + } + + token_fd = bpf_token_create(bpffs_fd, 0); + close(bpffs_fd); + if (token_fd < 0) { + if (!mandatory && token_fd == -ENOENT) { + pr_debug("object '%s': BPF FS at '%s' doesn't have BPF token delegation set up, skipping...\n", + obj->name, bpffs_path); + return 0; + } + __pr(level, "object '%s': failed (%d) to create BPF token from '%s'%s\n", + obj->name, token_fd, bpffs_path, + mandatory ? "" : ", skipping optional step..."); + return mandatory ? token_fd : 0; + } + + obj->feat_cache = calloc(1, sizeof(*obj->feat_cache)); + if (!obj->feat_cache) { + close(token_fd); + return -ENOMEM; + } + + obj->token_fd = token_fd; + obj->feat_cache->token_fd = token_fd; + + return 0; +} + static int bpf_object__probe_loading(struct bpf_object *obj) { @@ -4555,6 +4628,10 @@ bpf_object__probe_loading(struct bpf_object *obj) BPF_EXIT_INSN(), }; int ret, insn_cnt = ARRAY_SIZE(insns); + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .token_fd = obj->token_fd, + .prog_flags = obj->token_fd ? BPF_F_TOKEN_FD : 0, + ); if (obj->gen_loader) return 0; @@ -4564,9 +4641,9 @@ bpf_object__probe_loading(struct bpf_object *obj) pr_warn("Failed to bump RLIMIT_MEMLOCK (err = %d), you might need to do it explicitly!\n", ret); /* make sure basic loading works */ - ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, NULL); + ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, &opts); if (ret < 0) - ret = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, NULL); + ret = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, &opts); if (ret < 0) { ret = errno; cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); @@ -4581,462 +4658,18 @@ bpf_object__probe_loading(struct bpf_object *obj) return 0; } -static int probe_fd(int fd) -{ - if (fd >= 0) - close(fd); - return fd >= 0; -} - -static int probe_kern_prog_name(void) -{ - const size_t attr_sz = offsetofend(union bpf_attr, prog_name); - struct bpf_insn insns[] = { - BPF_MOV64_IMM(BPF_REG_0, 0), - BPF_EXIT_INSN(), - }; - union bpf_attr attr; - int ret; - - memset(&attr, 0, attr_sz); - attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; - attr.license = ptr_to_u64("GPL"); - attr.insns = ptr_to_u64(insns); - attr.insn_cnt = (__u32)ARRAY_SIZE(insns); - libbpf_strlcpy(attr.prog_name, "libbpf_nametest", sizeof(attr.prog_name)); - - /* make sure loading with name works */ - ret = sys_bpf_prog_load(&attr, attr_sz, PROG_LOAD_ATTEMPTS); - return probe_fd(ret); -} - -static int probe_kern_global_data(void) -{ - char *cp, errmsg[STRERR_BUFSIZE]; - struct bpf_insn insns[] = { - BPF_LD_MAP_VALUE(BPF_REG_1, 0, 16), - BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 42), - BPF_MOV64_IMM(BPF_REG_0, 0), - BPF_EXIT_INSN(), - }; - int ret, map, insn_cnt = ARRAY_SIZE(insns); - - map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_global", sizeof(int), 32, 1, NULL); - if (map < 0) { - ret = -errno; - cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); - pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n", - __func__, cp, -ret); - return ret; - } - - insns[0].imm = map; - - ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, NULL); - close(map); - return probe_fd(ret); -} - -static int probe_kern_btf(void) -{ - static const char strs[] = "\0int"; - __u32 types[] = { - /* int */ - BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), - }; - - return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs))); -} - -static int probe_kern_btf_func(void) -{ - static const char strs[] = "\0int\0x\0a"; - /* void x(int a) {} */ - __u32 types[] = { - /* int */ - BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ - /* FUNC_PROTO */ /* [2] */ - BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0), - BTF_PARAM_ENC(7, 1), - /* FUNC x */ /* [3] */ - BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0), 2), - }; - - return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs))); -} - -static int probe_kern_btf_func_global(void) -{ - static const char strs[] = "\0int\0x\0a"; - /* static void x(int a) {} */ - __u32 types[] = { - /* int */ - BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ - /* FUNC_PROTO */ /* [2] */ - BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0), - BTF_PARAM_ENC(7, 1), - /* FUNC x BTF_FUNC_GLOBAL */ /* [3] */ - BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 2), - }; - - return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs))); -} - -static int probe_kern_btf_datasec(void) -{ - static const char strs[] = "\0x\0.data"; - /* static int a; */ - __u32 types[] = { - /* int */ - BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ - /* VAR x */ /* [2] */ - BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1), - BTF_VAR_STATIC, - /* DATASEC val */ /* [3] */ - BTF_TYPE_ENC(3, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4), - BTF_VAR_SECINFO_ENC(2, 0, 4), - }; - - return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs))); -} - -static int probe_kern_btf_float(void) -{ - static const char strs[] = "\0float"; - __u32 types[] = { - /* float */ - BTF_TYPE_FLOAT_ENC(1, 4), - }; - - return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs))); -} - -static int probe_kern_btf_decl_tag(void) -{ - static const char strs[] = "\0tag"; - __u32 types[] = { - /* int */ - BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ - /* VAR x */ /* [2] */ - BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1), - BTF_VAR_STATIC, - /* attr */ - BTF_TYPE_DECL_TAG_ENC(1, 2, -1), - }; - - return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs))); -} - -static int probe_kern_btf_type_tag(void) -{ - static const char strs[] = "\0tag"; - __u32 types[] = { - /* int */ - BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ - /* attr */ - BTF_TYPE_TYPE_TAG_ENC(1, 1), /* [2] */ - /* ptr */ - BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 2), /* [3] */ - }; - - return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs))); -} - -static int probe_kern_array_mmap(void) -{ - LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_MMAPABLE); - int fd; - - fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_mmap", sizeof(int), sizeof(int), 1, &opts); - return probe_fd(fd); -} - -static int probe_kern_exp_attach_type(void) -{ - LIBBPF_OPTS(bpf_prog_load_opts, opts, .expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE); - struct bpf_insn insns[] = { - BPF_MOV64_IMM(BPF_REG_0, 0), - BPF_EXIT_INSN(), - }; - int fd, insn_cnt = ARRAY_SIZE(insns); - - /* use any valid combination of program type and (optional) - * non-zero expected attach type (i.e., not a BPF_CGROUP_INET_INGRESS) - * to see if kernel supports expected_attach_type field for - * BPF_PROG_LOAD command - */ - fd = bpf_prog_load(BPF_PROG_TYPE_CGROUP_SOCK, NULL, "GPL", insns, insn_cnt, &opts); - return probe_fd(fd); -} - -static int probe_kern_probe_read_kernel(void) -{ - struct bpf_insn insns[] = { - BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), /* r1 = r10 (fp) */ - BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), /* r1 += -8 */ - BPF_MOV64_IMM(BPF_REG_2, 8), /* r2 = 8 */ - BPF_MOV64_IMM(BPF_REG_3, 0), /* r3 = 0 */ - BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_probe_read_kernel), - BPF_EXIT_INSN(), - }; - int fd, insn_cnt = ARRAY_SIZE(insns); - - fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, NULL); - return probe_fd(fd); -} - -static int probe_prog_bind_map(void) -{ - char *cp, errmsg[STRERR_BUFSIZE]; - struct bpf_insn insns[] = { - BPF_MOV64_IMM(BPF_REG_0, 0), - BPF_EXIT_INSN(), - }; - int ret, map, prog, insn_cnt = ARRAY_SIZE(insns); - - map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_det_bind", sizeof(int), 32, 1, NULL); - if (map < 0) { - ret = -errno; - cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); - pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n", - __func__, cp, -ret); - return ret; - } - - prog = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, NULL); - if (prog < 0) { - close(map); - return 0; - } - - ret = bpf_prog_bind_map(prog, map, NULL); - - close(map); - close(prog); - - return ret >= 0; -} - -static int probe_module_btf(void) -{ - static const char strs[] = "\0int"; - __u32 types[] = { - /* int */ - BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), - }; - struct bpf_btf_info info; - __u32 len = sizeof(info); - char name[16]; - int fd, err; - - fd = libbpf__load_raw_btf((char *)types, sizeof(types), strs, sizeof(strs)); - if (fd < 0) - return 0; /* BTF not supported at all */ - - memset(&info, 0, sizeof(info)); - info.name = ptr_to_u64(name); - info.name_len = sizeof(name); - - /* check that BPF_OBJ_GET_INFO_BY_FD supports specifying name pointer; - * kernel's module BTF support coincides with support for - * name/name_len fields in struct bpf_btf_info. - */ - err = bpf_btf_get_info_by_fd(fd, &info, &len); - close(fd); - return !err; -} - -static int probe_perf_link(void) -{ - struct bpf_insn insns[] = { - BPF_MOV64_IMM(BPF_REG_0, 0), - BPF_EXIT_INSN(), - }; - int prog_fd, link_fd, err; - - prog_fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", - insns, ARRAY_SIZE(insns), NULL); - if (prog_fd < 0) - return -errno; - - /* use invalid perf_event FD to get EBADF, if link is supported; - * otherwise EINVAL should be returned - */ - link_fd = bpf_link_create(prog_fd, -1, BPF_PERF_EVENT, NULL); - err = -errno; /* close() can clobber errno */ - - if (link_fd >= 0) - close(link_fd); - close(prog_fd); - - return link_fd < 0 && err == -EBADF; -} - -static int probe_uprobe_multi_link(void) -{ - LIBBPF_OPTS(bpf_prog_load_opts, load_opts, - .expected_attach_type = BPF_TRACE_UPROBE_MULTI, - ); - LIBBPF_OPTS(bpf_link_create_opts, link_opts); - struct bpf_insn insns[] = { - BPF_MOV64_IMM(BPF_REG_0, 0), - BPF_EXIT_INSN(), - }; - int prog_fd, link_fd, err; - unsigned long offset = 0; - - prog_fd = bpf_prog_load(BPF_PROG_TYPE_KPROBE, NULL, "GPL", - insns, ARRAY_SIZE(insns), &load_opts); - if (prog_fd < 0) - return -errno; - - /* Creating uprobe in '/' binary should fail with -EBADF. */ - link_opts.uprobe_multi.path = "/"; - link_opts.uprobe_multi.offsets = &offset; - link_opts.uprobe_multi.cnt = 1; - - link_fd = bpf_link_create(prog_fd, -1, BPF_TRACE_UPROBE_MULTI, &link_opts); - err = -errno; /* close() can clobber errno */ - - if (link_fd >= 0) - close(link_fd); - close(prog_fd); - - return link_fd < 0 && err == -EBADF; -} - -static int probe_kern_bpf_cookie(void) -{ - struct bpf_insn insns[] = { - BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_attach_cookie), - BPF_EXIT_INSN(), - }; - int ret, insn_cnt = ARRAY_SIZE(insns); - - ret = bpf_prog_load(BPF_PROG_TYPE_KPROBE, NULL, "GPL", insns, insn_cnt, NULL); - return probe_fd(ret); -} - -static int probe_kern_btf_enum64(void) -{ - static const char strs[] = "\0enum64"; - __u32 types[] = { - BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_ENUM64, 0, 0), 8), - }; - - return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs))); -} - -static int probe_kern_syscall_wrapper(void); - -enum kern_feature_result { - FEAT_UNKNOWN = 0, - FEAT_SUPPORTED = 1, - FEAT_MISSING = 2, -}; - -typedef int (*feature_probe_fn)(void); - -static struct kern_feature_desc { - const char *desc; - feature_probe_fn probe; - enum kern_feature_result res; -} feature_probes[__FEAT_CNT] = { - [FEAT_PROG_NAME] = { - "BPF program name", probe_kern_prog_name, - }, - [FEAT_GLOBAL_DATA] = { - "global variables", probe_kern_global_data, - }, - [FEAT_BTF] = { - "minimal BTF", probe_kern_btf, - }, - [FEAT_BTF_FUNC] = { - "BTF functions", probe_kern_btf_func, - }, - [FEAT_BTF_GLOBAL_FUNC] = { - "BTF global function", probe_kern_btf_func_global, - }, - [FEAT_BTF_DATASEC] = { - "BTF data section and variable", probe_kern_btf_datasec, - }, - [FEAT_ARRAY_MMAP] = { - "ARRAY map mmap()", probe_kern_array_mmap, - }, - [FEAT_EXP_ATTACH_TYPE] = { - "BPF_PROG_LOAD expected_attach_type attribute", - probe_kern_exp_attach_type, - }, - [FEAT_PROBE_READ_KERN] = { - "bpf_probe_read_kernel() helper", probe_kern_probe_read_kernel, - }, - [FEAT_PROG_BIND_MAP] = { - "BPF_PROG_BIND_MAP support", probe_prog_bind_map, - }, - [FEAT_MODULE_BTF] = { - "module BTF support", probe_module_btf, - }, - [FEAT_BTF_FLOAT] = { - "BTF_KIND_FLOAT support", probe_kern_btf_float, - }, - [FEAT_PERF_LINK] = { - "BPF perf link support", probe_perf_link, - }, - [FEAT_BTF_DECL_TAG] = { - "BTF_KIND_DECL_TAG support", probe_kern_btf_decl_tag, - }, - [FEAT_BTF_TYPE_TAG] = { - "BTF_KIND_TYPE_TAG support", probe_kern_btf_type_tag, - }, - [FEAT_MEMCG_ACCOUNT] = { - "memcg-based memory accounting", probe_memcg_account, - }, - [FEAT_BPF_COOKIE] = { - "BPF cookie support", probe_kern_bpf_cookie, - }, - [FEAT_BTF_ENUM64] = { - "BTF_KIND_ENUM64 support", probe_kern_btf_enum64, - }, - [FEAT_SYSCALL_WRAPPER] = { - "Kernel using syscall wrapper", probe_kern_syscall_wrapper, - }, - [FEAT_UPROBE_MULTI_LINK] = { - "BPF multi-uprobe link support", probe_uprobe_multi_link, - }, -}; - bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id) { - struct kern_feature_desc *feat = &feature_probes[feat_id]; - int ret; - if (obj && obj->gen_loader) /* To generate loader program assume the latest kernel * to avoid doing extra prog_load, map_create syscalls. */ return true; - if (READ_ONCE(feat->res) == FEAT_UNKNOWN) { - ret = feat->probe(); - if (ret > 0) { - WRITE_ONCE(feat->res, FEAT_SUPPORTED); - } else if (ret == 0) { - WRITE_ONCE(feat->res, FEAT_MISSING); - } else { - pr_warn("Detection of kernel %s support failed: %d\n", feat->desc, ret); - WRITE_ONCE(feat->res, FEAT_MISSING); - } - } + if (obj->token_fd) + return feat_supported(obj->feat_cache, feat_id); - return READ_ONCE(feat->res) == FEAT_SUPPORTED; + return feat_supported(NULL, feat_id); } static bool map_is_reuse_compat(const struct bpf_map *map, int map_fd) @@ -5160,9 +4793,17 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b create_attr.map_flags = def->map_flags; create_attr.numa_node = map->numa_node; create_attr.map_extra = map->map_extra; + create_attr.token_fd = obj->token_fd; + if (obj->token_fd) + create_attr.map_flags |= BPF_F_TOKEN_FD; - if (bpf_map__is_struct_ops(map)) + if (bpf_map__is_struct_ops(map)) { create_attr.btf_vmlinux_value_type_id = map->btf_vmlinux_value_type_id; + if (map->mod_btf_fd >= 0) { + create_attr.value_type_btf_obj_fd = map->mod_btf_fd; + create_attr.map_flags |= BPF_F_VTYPE_BTF_OBJ_FD; + } + } if (obj->btf && btf__fd(obj->btf) >= 0) { create_attr.btf_fd = btf__fd(obj->btf); @@ -5172,6 +4813,9 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b if (bpf_map_type__is_map_in_map(def->type)) { if (map->inner_map) { + err = map_set_def_max_entries(map->inner_map); + if (err) + return err; err = bpf_object__create_map(obj, map->inner_map, true); if (err) { pr_warn("map '%s': failed to create inner map: %d\n", @@ -6864,7 +6508,7 @@ static int probe_kern_arg_ctx_tag(void) if (cached_result >= 0) return cached_result; - btf_fd = libbpf__load_raw_btf((char *)types, sizeof(types), strs, sizeof(strs)); + btf_fd = libbpf__load_raw_btf((char *)types, sizeof(types), strs, sizeof(strs), 0); if (btf_fd < 0) return 0; @@ -7473,6 +7117,10 @@ static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog load_attr.prog_flags = prog->prog_flags; load_attr.fd_array = obj->fd_array; + load_attr.token_fd = obj->token_fd; + if (obj->token_fd) + load_attr.prog_flags |= BPF_F_TOKEN_FD; + /* adjust load_attr if sec_def provides custom preload callback */ if (prog->sec_def && prog->sec_def->prog_prepare_load_fn) { err = prog->sec_def->prog_prepare_load_fn(prog, &load_attr, prog->sec_def->cookie); @@ -7918,7 +7566,7 @@ static int bpf_object_init_progs(struct bpf_object *obj, const struct bpf_object static struct bpf_object *bpf_object_open(const char *path, const void *obj_buf, size_t obj_buf_sz, const struct bpf_object_open_opts *opts) { - const char *obj_name, *kconfig, *btf_tmp_path; + const char *obj_name, *kconfig, *btf_tmp_path, *token_path; struct bpf_object *obj; char tmp_name[64]; int err; @@ -7955,6 +7603,16 @@ static struct bpf_object *bpf_object_open(const char *path, const void *obj_buf, if (log_size && !log_buf) return ERR_PTR(-EINVAL); + token_path = OPTS_GET(opts, bpf_token_path, NULL); + /* if user didn't specify bpf_token_path explicitly, check if + * LIBBPF_BPF_TOKEN_PATH envvar was set and treat it as bpf_token_path + * option + */ + if (!token_path) + token_path = getenv("LIBBPF_BPF_TOKEN_PATH"); + if (token_path && strlen(token_path) >= PATH_MAX) + return ERR_PTR(-ENAMETOOLONG); + obj = bpf_object__new(path, obj_buf, obj_buf_sz, obj_name); if (IS_ERR(obj)) return obj; @@ -7963,6 +7621,14 @@ static struct bpf_object *bpf_object_open(const char *path, const void *obj_buf, obj->log_size = log_size; obj->log_level = log_level; + if (token_path) { + obj->token_path = strdup(token_path); + if (!obj->token_path) { + err = -ENOMEM; + goto out; + } + } + btf_tmp_path = OPTS_GET(opts, btf_custom_path, NULL); if (btf_tmp_path) { if (strlen(btf_tmp_path) >= PATH_MAX) { @@ -8473,7 +8139,8 @@ static int bpf_object_load(struct bpf_object *obj, int extra_log_level, const ch if (obj->gen_loader) bpf_gen__init(obj->gen_loader, extra_log_level, obj->nr_programs, obj->nr_maps); - err = bpf_object__probe_loading(obj); + err = bpf_object_prepare_token(obj); + err = err ? : bpf_object__probe_loading(obj); err = err ? : bpf_object__load_vmlinux_btf(obj, false); err = err ? : bpf_object__resolve_externs(obj, obj->kconfig); err = err ? : bpf_object__sanitize_maps(obj); @@ -9008,6 +8675,11 @@ void bpf_object__close(struct bpf_object *obj) } zfree(&obj->programs); + zfree(&obj->feat_cache); + zfree(&obj->token_path); + if (obj->token_fd > 0) + close(obj->token_fd); + free(obj); } @@ -9966,7 +9638,9 @@ static int libbpf_find_attach_btf_id(struct bpf_program *prog, const char *attac *btf_obj_fd = 0; *btf_type_id = 1; } else { - err = find_kernel_btf_id(prog->obj, attach_name, attach_type, btf_obj_fd, btf_type_id); + err = find_kernel_btf_id(prog->obj, attach_name, + attach_type, btf_obj_fd, + btf_type_id); } if (err) { pr_warn("prog '%s': failed to find kernel BTF type ID of '%s': %d\n", @@ -11028,7 +10702,7 @@ static const char *arch_specific_syscall_pfx(void) #endif } -static int probe_kern_syscall_wrapper(void) +int probe_kern_syscall_wrapper(int token_fd) { char syscall_name[64]; const char *ksys_pfx; diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 6cd9c501624f..5723cbbfcc41 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -177,10 +177,29 @@ struct bpf_object_open_opts { * logs through its print callback. */ __u32 kernel_log_level; + /* Path to BPF FS mount point to derive BPF token from. + * + * Created BPF token will be used for all bpf() syscall operations + * that accept BPF token (e.g., map creation, BTF and program loads, + * etc) automatically within instantiated BPF object. + * + * If bpf_token_path is not specified, libbpf will consult + * LIBBPF_BPF_TOKEN_PATH environment variable. If set, it will be + * taken as a value of bpf_token_path option and will force libbpf to + * either create BPF token from provided custom BPF FS path, or will + * disable implicit BPF token creation, if envvar value is an empty + * string. bpf_token_path overrides LIBBPF_BPF_TOKEN_PATH, if both are + * set at the same time. + * + * Setting bpf_token_path option to empty string disables libbpf's + * automatic attempt to create BPF token from default BPF FS mount + * point (/sys/fs/bpf), in case this default behavior is undesirable. + */ + const char *bpf_token_path; size_t :0; }; -#define bpf_object_open_opts__last_field kernel_log_level +#define bpf_object_open_opts__last_field bpf_token_path /** * @brief **bpf_object__open()** creates a bpf_object by opening diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index 91c5aef7dae7..d9e1f57534fa 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -411,4 +411,5 @@ LIBBPF_1.3.0 { } LIBBPF_1.2.0; LIBBPF_1.4.0 { + bpf_token_create; } LIBBPF_1.3.0; diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index 27e4e320e1a6..930cc9616527 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -15,6 +15,7 @@ #include <linux/err.h> #include <fcntl.h> #include <unistd.h> +#include <sys/syscall.h> #include <libelf.h> #include "relo_core.h" @@ -360,15 +361,32 @@ enum kern_feature_id { __FEAT_CNT, }; -int probe_memcg_account(void); +enum kern_feature_result { + FEAT_UNKNOWN = 0, + FEAT_SUPPORTED = 1, + FEAT_MISSING = 2, +}; + +struct kern_feature_cache { + enum kern_feature_result res[__FEAT_CNT]; + int token_fd; +}; + +bool feat_supported(struct kern_feature_cache *cache, enum kern_feature_id feat_id); bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id); + +int probe_kern_syscall_wrapper(int token_fd); +int probe_memcg_account(int token_fd); int bump_rlimit_memlock(void); int parse_cpu_mask_str(const char *s, bool **mask, int *mask_sz); int parse_cpu_mask_file(const char *fcpu, bool **mask, int *mask_sz); int libbpf__load_raw_btf(const char *raw_types, size_t types_len, - const char *str_sec, size_t str_len); -int btf_load_into_kernel(struct btf *btf, char *log_buf, size_t log_sz, __u32 log_level); + const char *str_sec, size_t str_len, + int token_fd); +int btf_load_into_kernel(struct btf *btf, + char *log_buf, size_t log_sz, __u32 log_level, + int token_fd); struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf); void btf_get_kernel_prefix_kind(enum bpf_attach_type attach_type, @@ -532,6 +550,17 @@ static inline bool is_ldimm64_insn(struct bpf_insn *insn) return insn->code == (BPF_LD | BPF_IMM | BPF_DW); } +/* Unconditionally dup FD, ensuring it doesn't use [0, 2] range. + * Original FD is not closed or altered in any other way. + * Preserves original FD value, if it's invalid (negative). + */ +static inline int dup_good_fd(int fd) +{ + if (fd < 0) + return fd; + return fcntl(fd, F_DUPFD_CLOEXEC, 3); +} + /* if fd is stdin, stdout, or stderr, dup to a fd greater than 2 * Takes ownership of the fd passed in, and closes it if calling * fcntl(fd, F_DUPFD_CLOEXEC, 3). @@ -543,7 +572,7 @@ static inline int ensure_good_fd(int fd) if (fd < 0) return fd; if (fd < 3) { - fd = fcntl(fd, F_DUPFD_CLOEXEC, 3); + fd = dup_good_fd(fd); saved_errno = errno; close(old_fd); errno = saved_errno; @@ -555,6 +584,15 @@ static inline int ensure_good_fd(int fd) return fd; } +static inline int sys_dup2(int oldfd, int newfd) +{ +#ifdef __NR_dup2 + return syscall(__NR_dup2, oldfd, newfd); +#else + return syscall(__NR_dup3, oldfd, newfd, 0); +#endif +} + /* Point *fixed_fd* to the same file that *tmp_fd* points to. * Regardless of success, *tmp_fd* is closed. * Whatever *fixed_fd* pointed to is closed silently. @@ -563,7 +601,7 @@ static inline int reuse_fd(int fixed_fd, int tmp_fd) { int err; - err = dup2(tmp_fd, fixed_fd); + err = sys_dup2(tmp_fd, fixed_fd); err = err < 0 ? -errno : 0; close(tmp_fd); /* clean up temporary FD */ return err; @@ -613,4 +651,6 @@ int elf_resolve_syms_offsets(const char *binary_path, int cnt, int elf_resolve_pattern_offsets(const char *binary_path, const char *pattern, unsigned long **poffsets, size_t *pcnt); +int probe_fd(int fd); + #endif /* __LIBBPF_LIBBPF_INTERNAL_H */ diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c index 9c4db90b92b6..ee9b1dbea9eb 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -219,7 +219,8 @@ int libbpf_probe_bpf_prog_type(enum bpf_prog_type prog_type, const void *opts) } int libbpf__load_raw_btf(const char *raw_types, size_t types_len, - const char *str_sec, size_t str_len) + const char *str_sec, size_t str_len, + int token_fd) { struct btf_header hdr = { .magic = BTF_MAGIC, @@ -229,6 +230,10 @@ int libbpf__load_raw_btf(const char *raw_types, size_t types_len, .str_off = types_len, .str_len = str_len, }; + LIBBPF_OPTS(bpf_btf_load_opts, opts, + .token_fd = token_fd, + .btf_flags = token_fd ? BPF_F_TOKEN_FD : 0, + ); int btf_fd, btf_len; __u8 *raw_btf; @@ -241,7 +246,7 @@ int libbpf__load_raw_btf(const char *raw_types, size_t types_len, memcpy(raw_btf + hdr.hdr_len, raw_types, hdr.type_len); memcpy(raw_btf + hdr.hdr_len + hdr.type_len, str_sec, hdr.str_len); - btf_fd = bpf_btf_load(raw_btf, btf_len, NULL); + btf_fd = bpf_btf_load(raw_btf, btf_len, &opts); free(raw_btf); return btf_fd; @@ -271,7 +276,7 @@ static int load_local_storage_btf(void) }; return libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs)); + strs, sizeof(strs), 0); } static int probe_map_create(enum bpf_map_type map_type) @@ -326,6 +331,7 @@ static int probe_map_create(enum bpf_map_type map_type) case BPF_MAP_TYPE_STRUCT_OPS: /* we'll get -ENOTSUPP for invalid BTF type ID for struct_ops */ opts.btf_vmlinux_value_type_id = 1; + opts.value_type_btf_obj_fd = -1; exp_err = -524; /* -ENOTSUPP */ break; case BPF_MAP_TYPE_BLOOM_FILTER: diff --git a/tools/lib/bpf/str_error.h b/tools/lib/bpf/str_error.h index a139334d57b6..626d7ffb03d6 100644 --- a/tools/lib/bpf/str_error.h +++ b/tools/lib/bpf/str_error.h @@ -2,5 +2,8 @@ #ifndef __LIBBPF_STR_ERROR_H #define __LIBBPF_STR_ERROR_H +#define STRERR_BUFSIZE 128 + char *libbpf_strerror_r(int err, char *dst, int len); + #endif /* __LIBBPF_STR_ERROR_H */ diff --git a/tools/net/ynl/Makefile.deps b/tools/net/ynl/Makefile.deps index 3110f84dd029..e6154a1255f8 100644 --- a/tools/net/ynl/Makefile.deps +++ b/tools/net/ynl/Makefile.deps @@ -15,7 +15,9 @@ UAPI_PATH:=../../../../include/uapi/ get_hdr_inc=-D$(1) -include $(UAPI_PATH)/linux/$(2) CFLAGS_devlink:=$(call get_hdr_inc,_LINUX_DEVLINK_H_,devlink.h) +CFLAGS_dpll:=$(call get_hdr_inc,_LINUX_DPLL_H_,dpll.h) CFLAGS_ethtool:=$(call get_hdr_inc,_LINUX_ETHTOOL_NETLINK_H_,ethtool_netlink.h) CFLAGS_handshake:=$(call get_hdr_inc,_LINUX_HANDSHAKE_H,handshake.h) +CFLAGS_mptcp_pm:=$(call get_hdr_inc,_LINUX_MPTCP_PM_H_,mptcp_pm.h) CFLAGS_netdev:=$(call get_hdr_inc,_LINUX_NETDEV_H,netdev.h) CFLAGS_nfsd:=$(call get_hdr_inc,_LINUX_NFSD_NETLINK_H,nfsd_netlink.h) diff --git a/tools/net/ynl/cli.py b/tools/net/ynl/cli.py index 2ad9ec0f5545..0f8239979670 100755 --- a/tools/net/ynl/cli.py +++ b/tools/net/ynl/cli.py @@ -9,6 +9,15 @@ import time from lib import YnlFamily, Netlink +class YnlEncoder(json.JSONEncoder): + def default(self, obj): + if isinstance(obj, bytes): + return bytes.hex(obj) + if isinstance(obj, set): + return list(obj) + return json.JSONEncoder.default(self, obj) + + def main(): parser = argparse.ArgumentParser(description='YNL CLI sample') parser.add_argument('--spec', dest='spec', type=str, required=True) @@ -28,8 +37,15 @@ def main(): parser.add_argument('--append', dest='flags', action='append_const', const=Netlink.NLM_F_APPEND) parser.add_argument('--process-unknown', action=argparse.BooleanOptionalAction) + parser.add_argument('--output-json', action='store_true') args = parser.parse_args() + def output(msg): + if args.output_json: + print(json.dumps(msg, cls=YnlEncoder)) + else: + pprint.PrettyPrinter().pprint(msg) + if args.no_schema: args.schema = '' @@ -47,14 +63,14 @@ def main(): if args.do: reply = ynl.do(args.do, attrs, args.flags) - pprint.PrettyPrinter().pprint(reply) + output(reply) if args.dump: reply = ynl.dump(args.dump, attrs) - pprint.PrettyPrinter().pprint(reply) + output(reply) if args.ntf: ynl.check_ntf() - pprint.PrettyPrinter().pprint(ynl.async_msg_queue) + output(ynl.async_msg_queue) if __name__ == "__main__": diff --git a/tools/net/ynl/generated/Makefile b/tools/net/ynl/generated/Makefile index 84cbabdd02a8..7135028cb449 100644 --- a/tools/net/ynl/generated/Makefile +++ b/tools/net/ynl/generated/Makefile @@ -14,7 +14,10 @@ YNL_GEN_ARG_ethtool:=--user-header linux/ethtool_netlink.h \ TOOL:=../ynl-gen-c.py -GENS:=ethtool devlink handshake fou netdev nfsd +GENS_PATHS=$(shell grep -nrI --files-without-match \ + 'protocol: netlink' \ + ../../../../Documentation/netlink/specs/) +GENS=$(patsubst ../../../../Documentation/netlink/specs/%.yaml,%,${GENS_PATHS}) SRCS=$(patsubst %,%-user.c,${GENS}) HDRS=$(patsubst %,%-user.h,${GENS}) OBJS=$(patsubst %,%-user.o,${GENS}) diff --git a/tools/net/ynl/lib/nlspec.py b/tools/net/ynl/lib/nlspec.py index 44f13e383e8a..fbce52395b3b 100644 --- a/tools/net/ynl/lib/nlspec.py +++ b/tools/net/ynl/lib/nlspec.py @@ -144,7 +144,7 @@ class SpecEnumSet(SpecElement): class SpecAttr(SpecElement): - """ Single Netlink atttribute type + """ Single Netlink attribute type Represents a single attribute type within an attr space. @@ -248,6 +248,7 @@ class SpecStructMember(SpecElement): len integer, optional byte length of binary types display_hint string, hint to help choose format specifier when displaying the value + struct string, name of nested struct type """ def __init__(self, family, yaml): super().__init__(family, yaml) @@ -256,6 +257,7 @@ class SpecStructMember(SpecElement): self.enum = yaml.get('enum') self.len = yaml.get('len') self.display_hint = yaml.get('display-hint') + self.struct = yaml.get('struct') class SpecStruct(SpecElement): @@ -306,10 +308,9 @@ class SpecSubMessage(SpecElement): class SpecSubMessageFormat(SpecElement): - """ Netlink sub-message definition + """ Netlink sub-message format definition - Represents a set of sub-message formats for polymorphic nlattrs - that contain type-specific sub messages. + Represents a single format for a sub-message. Attributes: value attribute value to match against type selector diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/lib/ynl.py index 1e10512b2117..f45ee5f29bed 100644 --- a/tools/net/ynl/lib/ynl.py +++ b/tools/net/ynl/lib/ynl.py @@ -113,20 +113,6 @@ class NlAttr: else format.little return format.native - @classmethod - def formatted_string(cls, raw, display_hint): - if display_hint == 'mac': - formatted = ':'.join('%02x' % b for b in raw) - elif display_hint == 'hex': - formatted = bytes.hex(raw, ' ') - elif display_hint in [ 'ipv4', 'ipv6' ]: - formatted = format(ipaddress.ip_address(raw)) - elif display_hint == 'uuid': - formatted = str(uuid.UUID(bytes=raw)) - else: - formatted = raw - return formatted - def as_scalar(self, attr_type, byte_order=None): format = self.get_format(attr_type, byte_order) return format.unpack(self.raw)[0] @@ -148,23 +134,6 @@ class NlAttr: format = self.get_format(type) return [ x[0] for x in format.iter_unpack(self.raw) ] - def as_struct(self, members): - value = dict() - offset = 0 - for m in members: - # TODO: handle non-scalar members - if m.type == 'binary': - decoded = self.raw[offset : offset + m['len']] - offset += m['len'] - elif m.type in NlAttr.type_formats: - format = self.get_format(m.type, m.byte_order) - [ decoded ] = format.unpack_from(self.raw, offset) - offset += format.size - if m.display_hint: - decoded = self.formatted_string(decoded, m.display_hint) - value[m.name] = decoded - return value - def __repr__(self): return f"[type:{self.type} len:{self._len}] {self.raw}" @@ -370,7 +339,7 @@ class NetlinkProtocol: fixed_header_size = 0 if ynl: op = ynl.rsp_by_value[msg.cmd()] - fixed_header_size = ynl._fixed_header_size(op.fixed_header) + fixed_header_size = ynl._struct_size(op.fixed_header) msg.raw_attrs = NlAttrs(msg.raw, fixed_header_size) return msg @@ -405,6 +374,26 @@ class GenlProtocol(NetlinkProtocol): return self.genl_family['mcast'][mcast_name] + +class SpaceAttrs: + SpecValuesPair = namedtuple('SpecValuesPair', ['spec', 'values']) + + def __init__(self, attr_space, attrs, outer = None): + outer_scopes = outer.scopes if outer else [] + inner_scope = self.SpecValuesPair(attr_space, attrs) + self.scopes = [inner_scope] + outer_scopes + + def lookup(self, name): + for scope in self.scopes: + if name in scope.spec: + if name in scope.values: + return scope.values[name] + spec_name = scope.spec.yaml['name'] + raise Exception( + f"No value for '{name}' in attribute space '{spec_name}'") + raise Exception(f"Attribute '{name}' not defined in any attribute-set") + + # # YNL implementation details. # @@ -449,17 +438,26 @@ class YnlFamily(SpecFamily): self.sock.setsockopt(Netlink.SOL_NETLINK, Netlink.NETLINK_ADD_MEMBERSHIP, mcast_id) - def _add_attr(self, space, name, value): + def _add_attr(self, space, name, value, search_attrs): try: attr = self.attr_sets[space][name] except KeyError: raise Exception(f"Space '{space}' has no attribute '{name}'") nl_type = attr.value + + if attr.is_multi and isinstance(value, list): + attr_payload = b'' + for subvalue in value: + attr_payload += self._add_attr(space, name, subvalue, search_attrs) + return attr_payload + if attr["type"] == 'nest': nl_type |= Netlink.NLA_F_NESTED attr_payload = b'' + sub_attrs = SpaceAttrs(self.attr_sets[space], value, search_attrs) for subname, subvalue in value.items(): - attr_payload += self._add_attr(attr['nested-attributes'], subname, subvalue) + attr_payload += self._add_attr(attr['nested-attributes'], + subname, subvalue, sub_attrs) elif attr["type"] == 'flag': attr_payload = b'' elif attr["type"] == 'string': @@ -469,6 +467,8 @@ class YnlFamily(SpecFamily): attr_payload = value elif isinstance(value, str): attr_payload = bytes.fromhex(value) + elif isinstance(value, dict) and attr.struct_name: + attr_payload = self._encode_struct(attr.struct_name, value) else: raise Exception(f'Unknown type for binary attribute, value: {value}') elif attr.is_auto_scalar: @@ -481,6 +481,20 @@ class YnlFamily(SpecFamily): attr_payload = format.pack(int(value)) elif attr['type'] in "bitfield32": attr_payload = struct.pack("II", int(value["value"]), int(value["selector"])) + elif attr['type'] == 'sub-message': + msg_format = self._resolve_selector(attr, search_attrs) + attr_payload = b'' + if msg_format.fixed_header: + attr_payload += self._encode_struct(msg_format.fixed_header, value) + if msg_format.attr_set: + if msg_format.attr_set in self.attr_sets: + nl_type |= Netlink.NLA_F_NESTED + sub_attrs = SpaceAttrs(msg_format.attr_set, value, search_attrs) + for subname, subvalue in value.items(): + attr_payload += self._add_attr(msg_format.attr_set, + subname, subvalue, sub_attrs) + else: + raise Exception(f"Unknown attribute-set '{msg_format.attr_set}'") else: raise Exception(f'Unknown type at {space} {name} {value} {attr["type"]}') @@ -503,17 +517,13 @@ class YnlFamily(SpecFamily): def _decode_binary(self, attr, attr_spec): if attr_spec.struct_name: - members = self.consts[attr_spec.struct_name] - decoded = attr.as_struct(members) - for m in members: - if m.enum: - decoded[m.name] = self._decode_enum(decoded[m.name], m) + decoded = self._decode_struct(attr.raw, attr_spec.struct_name) elif attr_spec.sub_type: decoded = attr.as_c_array(attr_spec.sub_type) else: decoded = attr.as_bin() if attr_spec.display_hint: - decoded = NlAttr.formatted_string(decoded, attr_spec.display_hint) + decoded = self._formatted_string(decoded, attr_spec.display_hint) return decoded def _decode_array_nest(self, attr, attr_spec): @@ -548,29 +558,27 @@ class YnlFamily(SpecFamily): else: rsp[name] = [decoded] - def _resolve_selector(self, attr_spec, vals): + def _resolve_selector(self, attr_spec, search_attrs): sub_msg = attr_spec.sub_message if sub_msg not in self.sub_msgs: raise Exception(f"No sub-message spec named {sub_msg} for {attr_spec.name}") sub_msg_spec = self.sub_msgs[sub_msg] selector = attr_spec.selector - if selector not in vals: - raise Exception(f"There is no value for {selector} to resolve '{attr_spec.name}'") - value = vals[selector] + value = search_attrs.lookup(selector) if value not in sub_msg_spec.formats: raise Exception(f"No message format for '{value}' in sub-message spec '{sub_msg}'") spec = sub_msg_spec.formats[value] return spec - def _decode_sub_msg(self, attr, attr_spec, rsp): - msg_format = self._resolve_selector(attr_spec, rsp) + def _decode_sub_msg(self, attr, attr_spec, search_attrs): + msg_format = self._resolve_selector(attr_spec, search_attrs) decoded = {} offset = 0 if msg_format.fixed_header: - decoded.update(self._decode_fixed_header(attr, msg_format.fixed_header)); - offset = self._fixed_header_size(msg_format.fixed_header) + decoded.update(self._decode_struct(attr.raw, msg_format.fixed_header)); + offset = self._struct_size(msg_format.fixed_header) if msg_format.attr_set: if msg_format.attr_set in self.attr_sets: subdict = self._decode(NlAttrs(attr.raw, offset), msg_format.attr_set) @@ -579,10 +587,12 @@ class YnlFamily(SpecFamily): raise Exception(f"Unknown attribute-set '{attr_space}' when decoding '{attr_spec.name}'") return decoded - def _decode(self, attrs, space): + def _decode(self, attrs, space, outer_attrs = None): + rsp = dict() if space: attr_space = self.attr_sets[space] - rsp = dict() + search_attrs = SpaceAttrs(attr_space, rsp, outer_attrs) + for attr in attrs: try: attr_spec = attr_space.attrs_by_val[attr.type] @@ -594,7 +604,7 @@ class YnlFamily(SpecFamily): continue if attr_spec["type"] == 'nest': - subdict = self._decode(NlAttrs(attr.raw), attr_spec['nested-attributes']) + subdict = self._decode(NlAttrs(attr.raw), attr_spec['nested-attributes'], search_attrs) decoded = subdict elif attr_spec["type"] == 'string': decoded = attr.as_strz() @@ -617,7 +627,7 @@ class YnlFamily(SpecFamily): selector = self._decode_enum(selector, attr_spec) decoded = {"value": value, "selector": selector} elif attr_spec["type"] == 'sub-message': - decoded = self._decode_sub_msg(attr, attr_spec, rsp) + decoded = self._decode_sub_msg(attr, attr_spec, search_attrs) else: if not self.process_unknown: raise Exception(f'Unknown {attr_spec["type"]} with name {attr_spec["name"]}') @@ -658,20 +668,23 @@ class YnlFamily(SpecFamily): return msg = self.nlproto.decode(self, NlMsg(request, 0, op.attr_set)) - offset = 20 + self._fixed_header_size(op.fixed_header) + offset = 20 + self._struct_size(op.fixed_header) path = self._decode_extack_path(msg.raw_attrs, op.attr_set, offset, extack['bad-attr-offs']) if path: del extack['bad-attr-offs'] extack['bad-attr'] = path - def _fixed_header_size(self, name): + def _struct_size(self, name): if name: - fixed_header_members = self.consts[name].members + members = self.consts[name].members size = 0 - for m in fixed_header_members: + for m in members: if m.type in ['pad', 'binary']: - size += m.len + if m.struct: + size += self._struct_size(m.struct) + else: + size += m.len else: format = NlAttr.get_format(m.type, m.byte_order) size += format.size @@ -679,26 +692,71 @@ class YnlFamily(SpecFamily): else: return 0 - def _decode_fixed_header(self, msg, name): - fixed_header_members = self.consts[name].members - fixed_header_attrs = dict() + def _decode_struct(self, data, name): + members = self.consts[name].members + attrs = dict() offset = 0 - for m in fixed_header_members: + for m in members: value = None if m.type == 'pad': offset += m.len elif m.type == 'binary': - value = msg.raw[offset : offset + m.len] - offset += m.len + if m.struct: + len = self._struct_size(m.struct) + value = self._decode_struct(data[offset : offset + len], + m.struct) + offset += len + else: + value = data[offset : offset + m.len] + offset += m.len else: format = NlAttr.get_format(m.type, m.byte_order) - [ value ] = format.unpack_from(msg.raw, offset) + [ value ] = format.unpack_from(data, offset) offset += format.size if value is not None: if m.enum: value = self._decode_enum(value, m) - fixed_header_attrs[m.name] = value - return fixed_header_attrs + elif m.display_hint: + value = self._formatted_string(value, m.display_hint) + attrs[m.name] = value + return attrs + + def _encode_struct(self, name, vals): + members = self.consts[name].members + attr_payload = b'' + for m in members: + value = vals.pop(m.name) if m.name in vals else None + if m.type == 'pad': + attr_payload += bytearray(m.len) + elif m.type == 'binary': + if m.struct: + if value is None: + value = dict() + attr_payload += self._encode_struct(m.struct, value) + else: + if value is None: + attr_payload += bytearray(m.len) + else: + attr_payload += bytes.fromhex(value) + else: + if value is None: + value = 0 + format = NlAttr.get_format(m.type, m.byte_order) + attr_payload += format.pack(value) + return attr_payload + + def _formatted_string(self, raw, display_hint): + if display_hint == 'mac': + formatted = ':'.join('%02x' % b for b in raw) + elif display_hint == 'hex': + formatted = bytes.hex(raw, ' ') + elif display_hint in [ 'ipv4', 'ipv6' ]: + formatted = format(ipaddress.ip_address(raw)) + elif display_hint == 'uuid': + formatted = str(uuid.UUID(bytes=raw)) + else: + formatted = raw + return formatted def handle_ntf(self, decoded): msg = dict() @@ -707,7 +765,7 @@ class YnlFamily(SpecFamily): op = self.rsp_by_value[decoded.cmd()] attrs = self._decode(decoded.raw_attrs, op.attr_set.name) if op.fixed_header: - attrs.update(self._decode_fixed_header(decoded, op.fixed_header)) + attrs.update(self._decode_struct(decoded.raw, op.fixed_header)) msg['name'] = op['name'] msg['msg'] = attrs @@ -759,20 +817,11 @@ class YnlFamily(SpecFamily): req_seq = random.randint(1024, 65535) msg = self.nlproto.message(nl_flags, op.req_value, 1, req_seq) - fixed_header_members = [] if op.fixed_header: - fixed_header_members = self.consts[op.fixed_header].members - for m in fixed_header_members: - value = vals.pop(m.name) if m.name in vals else 0 - if m.type == 'pad': - msg += bytearray(m.len) - elif m.type == 'binary': - msg += bytes.fromhex(value) - else: - format = NlAttr.get_format(m.type, m.byte_order) - msg += format.pack(value) + msg += self._encode_struct(op.fixed_header, vals) + search_attrs = SpaceAttrs(op.attr_set, vals) for name, value in vals.items(): - msg += self._add_attr(op.attr_set.name, name, value) + msg += self._add_attr(op.attr_set.name, name, value, search_attrs) msg = _genl_msg_finalize(msg) self.sock.send(msg, 0) @@ -808,7 +857,7 @@ class YnlFamily(SpecFamily): rsp_msg = self._decode(decoded.raw_attrs, op.attr_set.name) if op.fixed_header: - rsp_msg.update(self._decode_fixed_header(decoded, op.fixed_header)) + rsp_msg.update(self._decode_struct(decoded.raw, op.fixed_header)) rsp.append(rsp_msg) if not rsp: diff --git a/tools/net/ynl/samples/.gitignore b/tools/net/ynl/samples/.gitignore index 49637b26c482..dda6686257a7 100644 --- a/tools/net/ynl/samples/.gitignore +++ b/tools/net/ynl/samples/.gitignore @@ -1,4 +1,5 @@ ethtool devlink netdev +ovs page-pool
\ No newline at end of file diff --git a/tools/net/ynl/samples/ovs.c b/tools/net/ynl/samples/ovs.c new file mode 100644 index 000000000000..3e975c003d77 --- /dev/null +++ b/tools/net/ynl/samples/ovs.c @@ -0,0 +1,60 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdio.h> +#include <string.h> + +#include <ynl.h> + +#include "ovs_datapath-user.h" + +int main(int argc, char **argv) +{ + struct ynl_sock *ys; + int err; + + ys = ynl_sock_create(&ynl_ovs_datapath_family, NULL); + if (!ys) + return 1; + + if (argc > 1) { + struct ovs_datapath_new_req *req; + + req = ovs_datapath_new_req_alloc(); + if (!req) + goto err_close; + + ovs_datapath_new_req_set_upcall_pid(req, 1); + ovs_datapath_new_req_set_name(req, argv[1]); + + err = ovs_datapath_new(ys, req); + ovs_datapath_new_req_free(req); + if (err) + goto err_close; + } else { + struct ovs_datapath_get_req_dump *req; + struct ovs_datapath_get_list *dps; + + printf("Dump:\n"); + req = ovs_datapath_get_req_dump_alloc(); + + dps = ovs_datapath_get_dump(ys, req); + ovs_datapath_get_req_dump_free(req); + if (!dps) + goto err_close; + + ynl_dump_foreach(dps, dp) { + printf(" %s(%d): pid:%u cache:%u\n", + dp->name, dp->_hdr.dp_ifindex, + dp->upcall_pid, dp->masks_cache_size); + } + ovs_datapath_get_list_free(dps); + } + + ynl_sock_destroy(ys); + + return 0; + +err_close: + fprintf(stderr, "YNL (%d): %s\n", ys->err.code, ys->err.msg); + ynl_sock_destroy(ys); + return 2; +} diff --git a/tools/net/ynl/ynl-gen-rst.py b/tools/net/ynl/ynl-gen-rst.py index 262d88f88696..927407b3efb3 100755 --- a/tools/net/ynl/ynl-gen-rst.py +++ b/tools/net/ynl/ynl-gen-rst.py @@ -189,12 +189,19 @@ def parse_operations(operations: List[Dict[str, Any]]) -> str: def parse_entries(entries: List[Dict[str, Any]], level: int) -> str: """Parse a list of entries""" + ignored = ["pad"] lines = [] for entry in entries: if isinstance(entry, dict): # entries could be a list or a dictionary + field_name = entry.get("name", "") + if field_name in ignored: + continue + type_ = entry.get("type") + if type_: + field_name += f" ({inline(type_)})" lines.append( - rst_fields(entry.get("name", ""), sanitize(entry.get("doc", "")), level) + rst_fields(field_name, sanitize(entry.get("doc", "")), level) ) elif isinstance(entry, list): lines.append(rst_list_inline(entry, level)) diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt index 1b90575ee3c8..3b12595193c9 100644 --- a/tools/perf/Documentation/perf-list.txt +++ b/tools/perf/Documentation/perf-list.txt @@ -47,6 +47,10 @@ Print PMU events and metrics limited to the specific PMU name. --json:: Output in JSON format. +-o:: +--output=:: + Output file name. By default output is written to stdout. + [[EVENT_MODIFIERS]] EVENT MODIFIERS --------------- diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 27e7c478880f..f8774a9b1377 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -236,6 +236,16 @@ else SHELLCHECK := $(shell which shellcheck 2> /dev/null) endif +# shellcheck is using in tools/perf/tests/Build with option -a/--check-sourced ( +# introduced in v0.4.7) and -S/--severity (introduced in v0.6.0). So make the +# minimal shellcheck version as v0.6.0. +ifneq ($(SHELLCHECK),) + ifeq ($(shell expr $(shell $(SHELLCHECK) --version | grep version: | \ + sed -e 's/.\+ \([0-9]\+\).\([0-9]\+\).\([0-9]\+\)/\1\2\3/g') \< 060), 1) + SHELLCHECK := + endif +endif + export srctree OUTPUT RM CC CXX LD AR CFLAGS CXXFLAGS V BISON FLEX AWK export HOSTCC HOSTLD HOSTAR HOSTCFLAGS SHELLCHECK diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c index 61c2c96cc070..e27a1b1288c2 100644 --- a/tools/perf/builtin-list.c +++ b/tools/perf/builtin-list.c @@ -30,6 +30,8 @@ * functions. */ struct print_state { + /** @fp: File to write output to. */ + FILE *fp; /** * @pmu_glob: Optionally restrict PMU and metric matching to PMU or * debugfs subsystem name. @@ -66,13 +68,15 @@ static void default_print_start(void *ps) { struct print_state *print_state = ps; - if (!print_state->name_only && pager_in_use()) - printf("\nList of pre-defined events (to be used in -e or -M):\n\n"); + if (!print_state->name_only && pager_in_use()) { + fprintf(print_state->fp, + "\nList of pre-defined events (to be used in -e or -M):\n\n"); + } } static void default_print_end(void *print_state __maybe_unused) {} -static void wordwrap(const char *s, int start, int max, int corr) +static void wordwrap(FILE *fp, const char *s, int start, int max, int corr) { int column = start; int n; @@ -82,10 +86,10 @@ static void wordwrap(const char *s, int start, int max, int corr) int wlen = strcspn(s, " \t\n"); if ((column + wlen >= max && column > start) || saw_newline) { - printf("\n%*s", start, ""); + fprintf(fp, "\n%*s", start, ""); column = start + corr; } - n = printf("%s%.*s", column > start ? " " : "", wlen, s); + n = fprintf(fp, "%s%.*s", column > start ? " " : "", wlen, s); if (n <= 0) break; saw_newline = s[wlen] == '\n'; @@ -104,6 +108,7 @@ static void default_print_event(void *ps, const char *pmu_name, const char *topi { struct print_state *print_state = ps; int pos; + FILE *fp = print_state->fp; if (deprecated && !print_state->deprecated) return; @@ -119,30 +124,30 @@ static void default_print_event(void *ps, const char *pmu_name, const char *topi if (print_state->name_only) { if (event_alias && strlen(event_alias)) - printf("%s ", event_alias); + fprintf(fp, "%s ", event_alias); else - printf("%s ", event_name); + fprintf(fp, "%s ", event_name); return; } if (strcmp(print_state->last_topic, topic ?: "")) { if (topic) - printf("\n%s:\n", topic); + fprintf(fp, "\n%s:\n", topic); zfree(&print_state->last_topic); print_state->last_topic = strdup(topic ?: ""); } if (event_alias && strlen(event_alias)) - pos = printf(" %s OR %s", event_name, event_alias); + pos = fprintf(fp, " %s OR %s", event_name, event_alias); else - pos = printf(" %s", event_name); + pos = fprintf(fp, " %s", event_name); if (!topic && event_type_desc) { for (; pos < 53; pos++) - putchar(' '); - printf("[%s]\n", event_type_desc); + fputc(' ', fp); + fprintf(fp, "[%s]\n", event_type_desc); } else - putchar('\n'); + fputc('\n', fp); if (desc && print_state->desc) { char *desc_with_unit = NULL; @@ -155,22 +160,22 @@ static void default_print_event(void *ps, const char *pmu_name, const char *topi ? "%s. Unit: %s" : "%s Unit: %s", desc, pmu_name); } - printf("%*s", 8, "["); - wordwrap(desc_len > 0 ? desc_with_unit : desc, 8, pager_get_columns(), 0); - printf("]\n"); + fprintf(fp, "%*s", 8, "["); + wordwrap(fp, desc_len > 0 ? desc_with_unit : desc, 8, pager_get_columns(), 0); + fprintf(fp, "]\n"); free(desc_with_unit); } long_desc = long_desc ?: desc; if (long_desc && print_state->long_desc) { - printf("%*s", 8, "["); - wordwrap(long_desc, 8, pager_get_columns(), 0); - printf("]\n"); + fprintf(fp, "%*s", 8, "["); + wordwrap(fp, long_desc, 8, pager_get_columns(), 0); + fprintf(fp, "]\n"); } if (print_state->detailed && encoding_desc) { - printf("%*s", 8, ""); - wordwrap(encoding_desc, 8, pager_get_columns(), 0); - putchar('\n'); + fprintf(fp, "%*s", 8, ""); + wordwrap(fp, encoding_desc, 8, pager_get_columns(), 0); + fputc('\n', fp); } } @@ -184,6 +189,7 @@ static void default_print_metric(void *ps, const char *unit __maybe_unused) { struct print_state *print_state = ps; + FILE *fp = print_state->fp; if (print_state->event_glob && (!print_state->metrics || !name || !strglobmatch(name, print_state->event_glob)) && @@ -192,27 +198,27 @@ static void default_print_metric(void *ps, if (!print_state->name_only && !print_state->last_metricgroups) { if (print_state->metricgroups) { - printf("\nMetric Groups:\n"); + fprintf(fp, "\nMetric Groups:\n"); if (!print_state->metrics) - putchar('\n'); + fputc('\n', fp); } else { - printf("\nMetrics:\n\n"); + fprintf(fp, "\nMetrics:\n\n"); } } if (!print_state->last_metricgroups || strcmp(print_state->last_metricgroups, group ?: "")) { if (group && print_state->metricgroups) { if (print_state->name_only) - printf("%s ", group); + fprintf(fp, "%s ", group); else if (print_state->metrics) { const char *gdesc = describe_metricgroup(group); if (gdesc) - printf("\n%s: [%s]\n", group, gdesc); + fprintf(fp, "\n%s: [%s]\n", group, gdesc); else - printf("\n%s:\n", group); + fprintf(fp, "\n%s:\n", group); } else - printf("%s\n", group); + fprintf(fp, "%s\n", group); } zfree(&print_state->last_metricgroups); print_state->last_metricgroups = strdup(group ?: ""); @@ -223,53 +229,59 @@ static void default_print_metric(void *ps, if (print_state->name_only) { if (print_state->metrics && !strlist__has_entry(print_state->visited_metrics, name)) { - printf("%s ", name); + fprintf(fp, "%s ", name); strlist__add(print_state->visited_metrics, name); } return; } - printf(" %s\n", name); + fprintf(fp, " %s\n", name); if (desc && print_state->desc) { - printf("%*s", 8, "["); - wordwrap(desc, 8, pager_get_columns(), 0); - printf("]\n"); + fprintf(fp, "%*s", 8, "["); + wordwrap(fp, desc, 8, pager_get_columns(), 0); + fprintf(fp, "]\n"); } if (long_desc && print_state->long_desc) { - printf("%*s", 8, "["); - wordwrap(long_desc, 8, pager_get_columns(), 0); - printf("]\n"); + fprintf(fp, "%*s", 8, "["); + wordwrap(fp, long_desc, 8, pager_get_columns(), 0); + fprintf(fp, "]\n"); } if (expr && print_state->detailed) { - printf("%*s", 8, "["); - wordwrap(expr, 8, pager_get_columns(), 0); - printf("]\n"); + fprintf(fp, "%*s", 8, "["); + wordwrap(fp, expr, 8, pager_get_columns(), 0); + fprintf(fp, "]\n"); } if (threshold && print_state->detailed) { - printf("%*s", 8, "["); - wordwrap(threshold, 8, pager_get_columns(), 0); - printf("]\n"); + fprintf(fp, "%*s", 8, "["); + wordwrap(fp, threshold, 8, pager_get_columns(), 0); + fprintf(fp, "]\n"); } } struct json_print_state { + /** @fp: File to write output to. */ + FILE *fp; /** Should a separator be printed prior to the next item? */ bool need_sep; }; -static void json_print_start(void *print_state __maybe_unused) +static void json_print_start(void *ps) { - printf("[\n"); + struct json_print_state *print_state = ps; + FILE *fp = print_state->fp; + + fprintf(fp, "[\n"); } static void json_print_end(void *ps) { struct json_print_state *print_state = ps; + FILE *fp = print_state->fp; - printf("%s]\n", print_state->need_sep ? "\n" : ""); + fprintf(fp, "%s]\n", print_state->need_sep ? "\n" : ""); } -static void fix_escape_printf(struct strbuf *buf, const char *fmt, ...) +static void fix_escape_fprintf(FILE *fp, struct strbuf *buf, const char *fmt, ...) { va_list args; @@ -318,7 +330,7 @@ static void fix_escape_printf(struct strbuf *buf, const char *fmt, ...) } } va_end(args); - fputs(buf->buf, stdout); + fputs(buf->buf, fp); } static void json_print_event(void *ps, const char *pmu_name, const char *topic, @@ -330,60 +342,71 @@ static void json_print_event(void *ps, const char *pmu_name, const char *topic, { struct json_print_state *print_state = ps; bool need_sep = false; + FILE *fp = print_state->fp; struct strbuf buf; strbuf_init(&buf, 0); - printf("%s{\n", print_state->need_sep ? ",\n" : ""); + fprintf(fp, "%s{\n", print_state->need_sep ? ",\n" : ""); print_state->need_sep = true; if (pmu_name) { - fix_escape_printf(&buf, "\t\"Unit\": \"%S\"", pmu_name); + fix_escape_fprintf(fp, &buf, "\t\"Unit\": \"%S\"", pmu_name); need_sep = true; } if (topic) { - fix_escape_printf(&buf, "%s\t\"Topic\": \"%S\"", need_sep ? ",\n" : "", topic); + fix_escape_fprintf(fp, &buf, "%s\t\"Topic\": \"%S\"", + need_sep ? ",\n" : "", + topic); need_sep = true; } if (event_name) { - fix_escape_printf(&buf, "%s\t\"EventName\": \"%S\"", need_sep ? ",\n" : "", - event_name); + fix_escape_fprintf(fp, &buf, "%s\t\"EventName\": \"%S\"", + need_sep ? ",\n" : "", + event_name); need_sep = true; } if (event_alias && strlen(event_alias)) { - fix_escape_printf(&buf, "%s\t\"EventAlias\": \"%S\"", need_sep ? ",\n" : "", - event_alias); + fix_escape_fprintf(fp, &buf, "%s\t\"EventAlias\": \"%S\"", + need_sep ? ",\n" : "", + event_alias); need_sep = true; } if (scale_unit && strlen(scale_unit)) { - fix_escape_printf(&buf, "%s\t\"ScaleUnit\": \"%S\"", need_sep ? ",\n" : "", - scale_unit); + fix_escape_fprintf(fp, &buf, "%s\t\"ScaleUnit\": \"%S\"", + need_sep ? ",\n" : "", + scale_unit); need_sep = true; } if (event_type_desc) { - fix_escape_printf(&buf, "%s\t\"EventType\": \"%S\"", need_sep ? ",\n" : "", - event_type_desc); + fix_escape_fprintf(fp, &buf, "%s\t\"EventType\": \"%S\"", + need_sep ? ",\n" : "", + event_type_desc); need_sep = true; } if (deprecated) { - fix_escape_printf(&buf, "%s\t\"Deprecated\": \"%S\"", need_sep ? ",\n" : "", - deprecated ? "1" : "0"); + fix_escape_fprintf(fp, &buf, "%s\t\"Deprecated\": \"%S\"", + need_sep ? ",\n" : "", + deprecated ? "1" : "0"); need_sep = true; } if (desc) { - fix_escape_printf(&buf, "%s\t\"BriefDescription\": \"%S\"", need_sep ? ",\n" : "", - desc); + fix_escape_fprintf(fp, &buf, "%s\t\"BriefDescription\": \"%S\"", + need_sep ? ",\n" : "", + desc); need_sep = true; } if (long_desc) { - fix_escape_printf(&buf, "%s\t\"PublicDescription\": \"%S\"", need_sep ? ",\n" : "", - long_desc); + fix_escape_fprintf(fp, &buf, "%s\t\"PublicDescription\": \"%S\"", + need_sep ? ",\n" : "", + long_desc); need_sep = true; } if (encoding_desc) { - fix_escape_printf(&buf, "%s\t\"Encoding\": \"%S\"", need_sep ? ",\n" : "", - encoding_desc); + fix_escape_fprintf(fp, &buf, "%s\t\"Encoding\": \"%S\"", + need_sep ? ",\n" : "", + encoding_desc); need_sep = true; } - printf("%s}", need_sep ? "\n" : ""); + fprintf(fp, "%s}", need_sep ? "\n" : ""); strbuf_release(&buf); } @@ -394,43 +417,53 @@ static void json_print_metric(void *ps __maybe_unused, const char *group, { struct json_print_state *print_state = ps; bool need_sep = false; + FILE *fp = print_state->fp; struct strbuf buf; strbuf_init(&buf, 0); - printf("%s{\n", print_state->need_sep ? ",\n" : ""); + fprintf(fp, "%s{\n", print_state->need_sep ? ",\n" : ""); print_state->need_sep = true; if (group) { - fix_escape_printf(&buf, "\t\"MetricGroup\": \"%S\"", group); + fix_escape_fprintf(fp, &buf, "\t\"MetricGroup\": \"%S\"", group); need_sep = true; } if (name) { - fix_escape_printf(&buf, "%s\t\"MetricName\": \"%S\"", need_sep ? ",\n" : "", name); + fix_escape_fprintf(fp, &buf, "%s\t\"MetricName\": \"%S\"", + need_sep ? ",\n" : "", + name); need_sep = true; } if (expr) { - fix_escape_printf(&buf, "%s\t\"MetricExpr\": \"%S\"", need_sep ? ",\n" : "", expr); + fix_escape_fprintf(fp, &buf, "%s\t\"MetricExpr\": \"%S\"", + need_sep ? ",\n" : "", + expr); need_sep = true; } if (threshold) { - fix_escape_printf(&buf, "%s\t\"MetricThreshold\": \"%S\"", need_sep ? ",\n" : "", - threshold); + fix_escape_fprintf(fp, &buf, "%s\t\"MetricThreshold\": \"%S\"", + need_sep ? ",\n" : "", + threshold); need_sep = true; } if (unit) { - fix_escape_printf(&buf, "%s\t\"ScaleUnit\": \"%S\"", need_sep ? ",\n" : "", unit); + fix_escape_fprintf(fp, &buf, "%s\t\"ScaleUnit\": \"%S\"", + need_sep ? ",\n" : "", + unit); need_sep = true; } if (desc) { - fix_escape_printf(&buf, "%s\t\"BriefDescription\": \"%S\"", need_sep ? ",\n" : "", - desc); + fix_escape_fprintf(fp, &buf, "%s\t\"BriefDescription\": \"%S\"", + need_sep ? ",\n" : "", + desc); need_sep = true; } if (long_desc) { - fix_escape_printf(&buf, "%s\t\"PublicDescription\": \"%S\"", need_sep ? ",\n" : "", - long_desc); + fix_escape_fprintf(fp, &buf, "%s\t\"PublicDescription\": \"%S\"", + need_sep ? ",\n" : "", + long_desc); need_sep = true; } - printf("%s}", need_sep ? "\n" : ""); + fprintf(fp, "%s}", need_sep ? "\n" : ""); strbuf_release(&buf); } @@ -449,8 +482,12 @@ static bool default_skip_duplicate_pmus(void *ps) int cmd_list(int argc, const char **argv) { int i, ret = 0; - struct print_state default_ps = {}; - struct print_state json_ps = {}; + struct print_state default_ps = { + .fp = stdout, + }; + struct print_state json_ps = { + .fp = stdout, + }; void *ps = &default_ps; struct print_callbacks print_cb = { .print_start = default_print_start, @@ -461,6 +498,7 @@ int cmd_list(int argc, const char **argv) }; const char *cputype = NULL; const char *unit_name = NULL; + const char *output_path = NULL; bool json = false; struct option list_options[] = { OPT_BOOLEAN(0, "raw-dump", &default_ps.name_only, "Dump raw events"), @@ -471,6 +509,7 @@ int cmd_list(int argc, const char **argv) "Print longer event descriptions."), OPT_BOOLEAN(0, "details", &default_ps.detailed, "Print information on the perf event names and expressions used internally by events."), + OPT_STRING('o', "output", &output_path, "file", "output file name"), OPT_BOOLEAN(0, "deprecated", &default_ps.deprecated, "Print deprecated events."), OPT_STRING(0, "cputype", &cputype, "cpu type", @@ -497,6 +536,11 @@ int cmd_list(int argc, const char **argv) argc = parse_options(argc, argv, list_options, list_usage, PARSE_OPT_STOP_AT_NON_OPTION); + if (output_path) { + default_ps.fp = fopen(output_path, "w"); + json_ps.fp = default_ps.fp; + } + setup_pager(); if (!default_ps.name_only) @@ -618,5 +662,8 @@ out: free(default_ps.last_topic); free(default_ps.last_metricgroups); strlist__delete(default_ps.visited_metrics); + if (output_path) + fclose(default_ps.fp); + return ret; } diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 91e6828c38cc..86c910125172 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -4080,8 +4080,8 @@ int cmd_record(int argc, const char **argv) } if (rec->switch_output.num_files) { - rec->switch_output.filenames = calloc(sizeof(char *), - rec->switch_output.num_files); + rec->switch_output.filenames = calloc(rec->switch_output.num_files, + sizeof(char *)); if (!rec->switch_output.filenames) { err = -EINVAL; goto out_opts; diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index baf1ab083436..5301d1badd43 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -357,7 +357,7 @@ static void perf_top__print_sym_table(struct perf_top *top) static void prompt_integer(int *target, const char *msg) { - char *buf = malloc(0), *p; + char *buf = NULL, *p; size_t dummy = 0; int tmp; diff --git a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json index 35124a4ddcb2..bbfa3883e533 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json @@ -114,7 +114,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to certain allocation restrictions.", - "MetricExpr": "TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS / tma_info_core_slots", + "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS@ / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_alloc_restriction", "MetricThreshold": "tma_alloc_restriction > 0.1", @@ -124,7 +124,7 @@ { "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "TOPDOWN_BE_BOUND.ALL / tma_info_core_slots", + "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.ALL@ / tma_info_core_slots", "MetricGroup": "Default;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.1", @@ -169,7 +169,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend", - "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_DETECT / tma_info_core_slots", + "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.BRANCH_DETECT@ / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_detect", "MetricThreshold": "tma_branch_detect > 0.05", @@ -179,7 +179,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to branch mispredicts.", - "MetricExpr": "TOPDOWN_BAD_SPECULATION.MISPREDICT / tma_info_core_slots", + "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.MISPREDICT@ / tma_info_core_slots", "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.05", @@ -189,7 +189,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BTCLEARS, which occurs when the Branch Target Buffer (BTB) predicts a taken branch.", - "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_RESTEER / tma_info_core_slots", + "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.BRANCH_RESTEER@ / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteer", "MetricThreshold": "tma_branch_resteer > 0.05", @@ -198,7 +198,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to the microcode sequencer (MS).", - "MetricExpr": "TOPDOWN_FE_BOUND.CISC / tma_info_core_slots", + "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.CISC@ / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_cisc", "MetricThreshold": "tma_cisc > 0.05", @@ -217,7 +217,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to decode stalls.", - "MetricExpr": "TOPDOWN_FE_BOUND.DECODE / tma_info_core_slots", + "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.DECODE@ / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_decode", "MetricThreshold": "tma_decode > 0.05", @@ -235,7 +235,6 @@ }, { "BriefDescription": "Counts the number of cycles the core is stalled due to a demand load miss which hit in DRAM or MMIO (Non-DRAM).", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "cpu_atom@MEM_BOUND_STALLS.LOAD_DRAM_HIT@ / tma_info_core_clks - max((cpu_atom@MEM_BOUND_STALLS.LOAD@ - cpu_atom@LD_HEAD.L1_MISS_AT_RET@) / tma_info_core_clks, 0) * cpu_atom@MEM_BOUND_STALLS.LOAD_DRAM_HIT@ / cpu_atom@MEM_BOUND_STALLS.LOAD@", "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", @@ -245,7 +244,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to a machine clear classified as a fast nuke due to memory ordering, memory disambiguation and memory renaming.", - "MetricExpr": "TOPDOWN_BAD_SPECULATION.FASTNUKE / tma_info_core_slots", + "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.FASTNUKE@ / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_fast_nuke", "MetricThreshold": "tma_fast_nuke > 0.05", @@ -254,7 +253,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.", - "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH / tma_info_core_slots", + "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH@ / tma_info_core_slots", "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1", @@ -264,7 +263,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.", - "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_LATENCY / tma_info_core_slots", + "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.FRONTEND_LATENCY@ / tma_info_core_slots", "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.15", @@ -283,7 +282,7 @@ }, { "BriefDescription": "Counts the number of floating point divide operations per uop.", - "MetricExpr": "UOPS_RETIRED.FPDIV / tma_info_core_slots", + "MetricExpr": "cpu_atom@UOPS_RETIRED.FPDIV@ / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_base_group", "MetricName": "tma_fpdiv_uops", "MetricThreshold": "tma_fpdiv_uops > 0.2", @@ -293,7 +292,7 @@ { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to frontend stalls.", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "TOPDOWN_FE_BOUND.ALL / tma_info_core_slots", + "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ALL@ / tma_info_core_slots", "MetricGroup": "Default;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.2", @@ -303,7 +302,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to instruction cache misses.", - "MetricExpr": "TOPDOWN_FE_BOUND.ICACHE / tma_info_core_slots", + "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ICACHE@ / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", "MetricThreshold": "tma_icache_misses > 0.05", @@ -330,7 +329,7 @@ }, { "BriefDescription": "Instructions Per Cycle", - "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / tma_info_core_clks", "MetricName": "tma_info_core_ipc", "Unit": "cpu_atom" }, @@ -342,7 +341,7 @@ }, { "BriefDescription": "Uops Per Instruction", - "MetricExpr": "UOPS_RETIRED.ALL / INST_RETIRED.ANY", + "MetricExpr": "cpu_atom@UOPS_RETIRED.ALL@ / INST_RETIRED.ANY", "MetricName": "tma_info_core_upi", "Unit": "cpu_atom" }, @@ -366,13 +365,13 @@ }, { "BriefDescription": "Ratio of all branches which mispredict", - "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.ALL_BRANCHES", + "MetricExpr": "cpu_atom@BR_MISP_RETIRED.ALL_BRANCHES@ / BR_INST_RETIRED.ALL_BRANCHES", "MetricName": "tma_info_inst_mix_branch_mispredict_ratio", "Unit": "cpu_atom" }, { "BriefDescription": "Ratio between Mispredicted branches and unknown branches", - "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / BACLEARS.ANY", + "MetricExpr": "cpu_atom@BR_MISP_RETIRED.ALL_BRANCHES@ / BACLEARS.ANY", "MetricName": "tma_info_inst_mix_branch_mispredict_to_unknown_branch_ratio", "Unit": "cpu_atom" }, @@ -390,61 +389,61 @@ }, { "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / BR_INST_RETIRED.ALL_BRANCHES", "MetricName": "tma_info_inst_mix_ipbranch", "Unit": "cpu_atom" }, { "BriefDescription": "Instruction per (near) call (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.CALL", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / BR_INST_RETIRED.CALL", "MetricName": "tma_info_inst_mix_ipcall", "Unit": "cpu_atom" }, { "BriefDescription": "Instructions per Far Branch", - "MetricExpr": "INST_RETIRED.ANY / (cpu_atom@BR_INST_RETIRED.FAR_BRANCH@ / 2)", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / (cpu_atom@BR_INST_RETIRED.FAR_BRANCH@ / 2)", "MetricName": "tma_info_inst_mix_ipfarbranch", "Unit": "cpu_atom" }, { "BriefDescription": "Instructions per Load", - "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / MEM_UOPS_RETIRED.ALL_LOADS", "MetricName": "tma_info_inst_mix_ipload", "Unit": "cpu_atom" }, { "BriefDescription": "Instructions per retired conditional Branch Misprediction where the branch was not taken", - "MetricExpr": "INST_RETIRED.ANY / (cpu_atom@BR_MISP_RETIRED.COND@ - cpu_atom@BR_MISP_RETIRED.COND_TAKEN@)", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / (cpu_atom@BR_MISP_RETIRED.COND@ - cpu_atom@BR_MISP_RETIRED.COND_TAKEN@)", "MetricName": "tma_info_inst_mix_ipmisp_cond_ntaken", "Unit": "cpu_atom" }, { "BriefDescription": "Instructions per retired conditional Branch Misprediction where the branch was taken", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / BR_MISP_RETIRED.COND_TAKEN", "MetricName": "tma_info_inst_mix_ipmisp_cond_taken", "Unit": "cpu_atom" }, { "BriefDescription": "Instructions per retired indirect call or jump Branch Misprediction", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / BR_MISP_RETIRED.INDIRECT", "MetricName": "tma_info_inst_mix_ipmisp_indirect", "Unit": "cpu_atom" }, { "BriefDescription": "Instructions per retired return Branch Misprediction", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RETURN", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / BR_MISP_RETIRED.RETURN", "MetricName": "tma_info_inst_mix_ipmisp_ret", "Unit": "cpu_atom" }, { "BriefDescription": "Instructions per retired Branch Misprediction", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / BR_MISP_RETIRED.ALL_BRANCHES", "MetricName": "tma_info_inst_mix_ipmispredict", "Unit": "cpu_atom" }, { "BriefDescription": "Instructions per Store", - "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / MEM_UOPS_RETIRED.ALL_STORES", "MetricName": "tma_info_inst_mix_ipstore", "Unit": "cpu_atom" }, @@ -480,19 +479,19 @@ }, { "BriefDescription": "Cycle cost per DRAM hit", - "MetricExpr": "MEM_BOUND_STALLS.LOAD_DRAM_HIT / MEM_LOAD_UOPS_RETIRED.DRAM_HIT", + "MetricExpr": "cpu_atom@MEM_BOUND_STALLS.LOAD_DRAM_HIT@ / MEM_LOAD_UOPS_RETIRED.DRAM_HIT", "MetricName": "tma_info_memory_cycles_per_demand_load_dram_hit", "Unit": "cpu_atom" }, { "BriefDescription": "Cycle cost per L2 hit", - "MetricExpr": "MEM_BOUND_STALLS.LOAD_L2_HIT / MEM_LOAD_UOPS_RETIRED.L2_HIT", + "MetricExpr": "cpu_atom@MEM_BOUND_STALLS.LOAD_L2_HIT@ / MEM_LOAD_UOPS_RETIRED.L2_HIT", "MetricName": "tma_info_memory_cycles_per_demand_load_l2_hit", "Unit": "cpu_atom" }, { "BriefDescription": "Cycle cost per LLC hit", - "MetricExpr": "MEM_BOUND_STALLS.LOAD_LLC_HIT / MEM_LOAD_UOPS_RETIRED.L3_HIT", + "MetricExpr": "cpu_atom@MEM_BOUND_STALLS.LOAD_LLC_HIT@ / MEM_LOAD_UOPS_RETIRED.L3_HIT", "MetricName": "tma_info_memory_cycles_per_demand_load_l3_hit", "Unit": "cpu_atom" }, @@ -504,7 +503,7 @@ }, { "BriefDescription": "Average CPU Utilization", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.REF_TSC@ / TSC", "MetricName": "tma_info_system_cpu_utilization", "Unit": "cpu_atom" }, @@ -524,7 +523,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to Instruction Table Lookaside Buffer (ITLB) misses.", - "MetricExpr": "TOPDOWN_FE_BOUND.ITLB / tma_info_core_slots", + "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ITLB@ / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", "MetricThreshold": "tma_itlb_misses > 0.05", @@ -533,7 +532,7 @@ }, { "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a load block.", - "MetricExpr": "LD_HEAD.L1_BOUND_AT_RET / tma_info_core_clks", + "MetricExpr": "cpu_atom@LD_HEAD.L1_BOUND_AT_RET@ / tma_info_core_clks", "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l1_bound", "MetricThreshold": "tma_l1_bound > 0.1", @@ -542,7 +541,6 @@ }, { "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the L2 Cache.", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "cpu_atom@MEM_BOUND_STALLS.LOAD_L2_HIT@ / tma_info_core_clks - max((cpu_atom@MEM_BOUND_STALLS.LOAD@ - cpu_atom@LD_HEAD.L1_MISS_AT_RET@) / tma_info_core_clks, 0) * cpu_atom@MEM_BOUND_STALLS.LOAD_L2_HIT@ / cpu_atom@MEM_BOUND_STALLS.LOAD@", "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", @@ -552,7 +550,6 @@ }, { "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the Last Level Cache (LLC) or other core with HITE/F/M.", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "cpu_atom@MEM_BOUND_STALLS.LOAD_LLC_HIT@ / tma_info_core_clks - max((cpu_atom@MEM_BOUND_STALLS.LOAD@ - cpu_atom@LD_HEAD.L1_MISS_AT_RET@) / tma_info_core_clks, 0) * cpu_atom@MEM_BOUND_STALLS.LOAD_LLC_HIT@ / cpu_atom@MEM_BOUND_STALLS.LOAD@", "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", @@ -571,7 +568,7 @@ }, { "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a machine clear (nuke) of any kind including memory ordering and memory disambiguation.", - "MetricExpr": "TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS / tma_info_core_slots", + "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS@ / tma_info_core_slots", "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.05", @@ -581,7 +578,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to memory reservation stalls in which a scheduler is not able to accept uops.", - "MetricExpr": "TOPDOWN_BE_BOUND.MEM_SCHEDULER / tma_info_core_slots", + "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.MEM_SCHEDULER@ / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_mem_scheduler", "MetricThreshold": "tma_mem_scheduler > 0.1", @@ -590,7 +587,7 @@ }, { "BriefDescription": "Counts the number of cycles the core is stalled due to stores or loads.", - "MetricExpr": "min(cpu_atom@TOPDOWN_BE_BOUND.ALL@ / tma_info_core_slots, cpu_atom@LD_HEAD.ANY_AT_RET@ / tma_info_core_clks + tma_store_bound)", + "MetricExpr": "min(tma_backend_bound, cpu_atom@LD_HEAD.ANY_AT_RET@ / tma_info_core_clks + tma_store_bound)", "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2", @@ -609,7 +606,7 @@ }, { "BriefDescription": "Counts the number of uops that are from the complex flows issued by the micro-sequencer (MS)", - "MetricExpr": "UOPS_RETIRED.MS / tma_info_core_slots", + "MetricExpr": "cpu_atom@UOPS_RETIRED.MS@ / tma_info_core_slots", "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_ms_uops", "MetricThreshold": "tma_ms_uops > 0.05", @@ -620,7 +617,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to IEC or FPC RAT stalls, which can be due to FIQ or IEC reservation stalls in which the integer, floating point or SIMD scheduler is not able to accept uops.", - "MetricExpr": "TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER / tma_info_core_slots", + "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER@ / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_non_mem_scheduler", "MetricThreshold": "tma_non_mem_scheduler > 0.1", @@ -629,7 +626,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to a machine clear (slow nuke).", - "MetricExpr": "TOPDOWN_BAD_SPECULATION.NUKE / tma_info_core_slots", + "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.NUKE@ / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_nuke", "MetricThreshold": "tma_nuke > 0.05", @@ -638,7 +635,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to other common frontend stalls not categorized.", - "MetricExpr": "TOPDOWN_FE_BOUND.OTHER / tma_info_core_slots", + "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.OTHER@ / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_other_fb", "MetricThreshold": "tma_other_fb > 0.05", @@ -647,7 +644,7 @@ }, { "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a number of other load blocks.", - "MetricExpr": "LD_HEAD.OTHER_AT_RET / tma_info_core_clks", + "MetricExpr": "cpu_atom@LD_HEAD.OTHER_AT_RET@ / tma_info_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_other_l1", "MetricThreshold": "tma_other_l1 > 0.05", @@ -683,7 +680,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to wrong predecodes.", - "MetricExpr": "TOPDOWN_FE_BOUND.PREDECODE / tma_info_core_slots", + "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.PREDECODE@ / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_predecode", "MetricThreshold": "tma_predecode > 0.05", @@ -692,7 +689,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to the physical register file unable to accept an entry (marble stalls).", - "MetricExpr": "TOPDOWN_BE_BOUND.REGISTER / tma_info_core_slots", + "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.REGISTER@ / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_register", "MetricThreshold": "tma_register > 0.1", @@ -701,7 +698,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to the reorder buffer being full (ROB stalls).", - "MetricExpr": "TOPDOWN_BE_BOUND.REORDER_BUFFER / tma_info_core_slots", + "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.REORDER_BUFFER@ / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_reorder_buffer", "MetricThreshold": "tma_reorder_buffer > 0.1", @@ -722,7 +719,7 @@ { "BriefDescription": "Counts the number of issue slots that result in retirement slots.", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "TOPDOWN_RETIRING.ALL / tma_info_core_slots", + "MetricExpr": "cpu_atom@TOPDOWN_RETIRING.ALL@ / tma_info_core_slots", "MetricGroup": "Default;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.75", @@ -741,7 +738,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to scoreboards from the instruction queue (IQ), jump execution unit (JEU), or microcode sequencer (MS).", - "MetricExpr": "TOPDOWN_BE_BOUND.SERIALIZATION / tma_info_core_slots", + "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.SERIALIZATION@ / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_serialization", "MetricThreshold": "tma_serialization > 0.1", @@ -768,7 +765,7 @@ }, { "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a first level TLB miss.", - "MetricExpr": "LD_HEAD.DTLB_MISS_AT_RET / tma_info_core_clks", + "MetricExpr": "cpu_atom@LD_HEAD.DTLB_MISS_AT_RET@ / tma_info_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_stlb_hit", "MetricThreshold": "tma_stlb_hit > 0.05", @@ -777,7 +774,7 @@ }, { "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a second level TLB miss requiring a page walk.", - "MetricExpr": "LD_HEAD.PGWALK_AT_RET / tma_info_core_clks", + "MetricExpr": "cpu_atom@LD_HEAD.PGWALK_AT_RET@ / tma_info_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_stlb_miss", "MetricThreshold": "tma_stlb_miss > 0.05", @@ -795,8 +792,7 @@ }, { "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a store forward block.", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "LD_HEAD.ST_ADDR_AT_RET / tma_info_core_clks", + "MetricExpr": "cpu_atom@LD_HEAD.ST_ADDR_AT_RET@ / tma_info_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", "MetricThreshold": "tma_store_fwd_blk > 0.05", @@ -875,7 +871,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", - "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches", + "MetricExpr": "cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks + tma_unknown_branches", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -905,7 +901,6 @@ }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(25 * tma_info_system_average_frequency * (cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) + 24 * tma_info_system_average_frequency * cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", @@ -927,7 +922,6 @@ }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "24 * tma_info_system_average_frequency * (cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ + cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (1 - cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", @@ -948,7 +942,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", - "MetricExpr": "ARITH.DIV_ACTIVE / tma_info_thread_clks", + "MetricExpr": "cpu_core@ARITH.DIV_ACTIVE@ / tma_info_thread_clks", "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", @@ -958,7 +952,6 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "cpu_core@MEMORY_ACTIVITY.STALLS_L3_MISS@ / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", @@ -979,7 +972,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", + "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -1019,7 +1012,7 @@ }, { "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", - "MetricExpr": "L1D_PEND_MISS.FB_FULL / tma_info_thread_clks", + "MetricExpr": "cpu_core@L1D_PEND_MISS.FB_FULL@ / tma_info_thread_clks", "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", @@ -1154,7 +1147,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses", - "MetricExpr": "ICACHE_DATA.STALLS / tma_info_thread_clks", + "MetricExpr": "cpu_core@ICACHE_DATA.STALLS@ / tma_info_thread_clks", "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -1164,7 +1157,6 @@ }, { "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_thread_slots / BR_MISP_RETIRED.ALL_BRANCHES", "MetricGroup": "Bad;BrMispredicts;tma_issueBM", "MetricName": "tma_info_bad_spec_branch_misprediction_cost", @@ -1173,7 +1165,7 @@ }, { "BriefDescription": "Instructions per retired mispredicts for conditional non-taken branches (lower number means higher occurrence rate).", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_MISP_RETIRED.COND_NTAKEN", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken", "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_ntaken < 200", @@ -1181,7 +1173,7 @@ }, { "BriefDescription": "Instructions per retired mispredicts for conditional taken branches (lower number means higher occurrence rate).", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_MISP_RETIRED.COND_TAKEN", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_cond_taken", "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_taken < 200", @@ -1197,7 +1189,7 @@ }, { "BriefDescription": "Instructions per retired mispredicts for return branches (lower number means higher occurrence rate).", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_MISP_RETIRED.RET", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_ret", "MetricThreshold": "tma_info_bad_spec_ipmisp_ret < 500", @@ -1205,7 +1197,7 @@ }, { "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_MISP_RETIRED.ALL_BRANCHES", "MetricGroup": "Bad;BadSpec;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmispredict", "MetricThreshold": "tma_info_bad_spec_ipmispredict < 200", @@ -1213,7 +1205,6 @@ }, { "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(100 * (1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if tma_info_system_smt_2t_utilization > 0.5 else 0)", "MetricGroup": "Cor;SMT", "MetricName": "tma_info_botlnk_l0_core_bound_likely", @@ -1222,7 +1213,6 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_lsd + tma_mite))", "MetricGroup": "DSBmiss;Fed;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_misses", @@ -1232,7 +1222,6 @@ }, { "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", "MetricName": "tma_info_botlnk_l2_ic_misses", @@ -1242,7 +1231,6 @@ }, { "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", "MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB;tma_issueBC", "MetricName": "tma_info_bottleneck_big_code", @@ -1261,7 +1249,6 @@ }, { "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_bottleneck_big_code", "MetricGroup": "Fed;FetchBW;Frontend", "MetricName": "tma_info_bottleneck_instruction_fetch_bw", @@ -1270,7 +1257,6 @@ }, { "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))", "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW", "MetricName": "tma_info_bottleneck_memory_bandwidth", @@ -1280,7 +1266,6 @@ }, { "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "Mem;MemoryTLB;Offcore;tma_issueTLB", "MetricName": "tma_info_bottleneck_memory_data_tlbs", @@ -1290,7 +1275,6 @@ }, { "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound))", "MetricGroup": "Mem;MemoryLat;Offcore;tma_issueLat", "MetricName": "tma_info_bottleneck_memory_latency", @@ -1300,7 +1284,6 @@ }, { "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Bad;BadSpec;BrMispredicts;tma_issueBM", "MetricName": "tma_info_bottleneck_mispredictions", @@ -1317,14 +1300,14 @@ }, { "BriefDescription": "Fraction of branches that are non-taken conditionals", - "MetricExpr": "BR_INST_RETIRED.COND_NTAKEN / BR_INST_RETIRED.ALL_BRANCHES", + "MetricExpr": "cpu_core@BR_INST_RETIRED.COND_NTAKEN@ / BR_INST_RETIRED.ALL_BRANCHES", "MetricGroup": "Bad;Branches;CodeGen;PGO", "MetricName": "tma_info_branches_cond_nt", "Unit": "cpu_core" }, { "BriefDescription": "Fraction of branches that are taken conditionals", - "MetricExpr": "BR_INST_RETIRED.COND_TAKEN / BR_INST_RETIRED.ALL_BRANCHES", + "MetricExpr": "cpu_core@BR_INST_RETIRED.COND_TAKEN@ / BR_INST_RETIRED.ALL_BRANCHES", "MetricGroup": "Bad;Branches;CodeGen;PGO", "MetricName": "tma_info_branches_cond_tk", "Unit": "cpu_core" @@ -1352,7 +1335,7 @@ }, { "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / tma_info_core_core_clks", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / tma_info_core_core_clks", "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group", "MetricName": "tma_info_core_coreipc", "Unit": "cpu_core" @@ -1374,14 +1357,14 @@ }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@ / 2 if #SMT_on else cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@)", + "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / (cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@ / 2 if #SMT_on else cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@)", "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", "MetricName": "tma_info_core_ilp", "Unit": "cpu_core" }, { "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / cpu_core@UOPS_ISSUED.ANY@", + "MetricExpr": "cpu_core@IDQ.DSB_UOPS@ / cpu_core@UOPS_ISSUED.ANY@", "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", "MetricName": "tma_info_frontend_dsb_coverage", "MetricThreshold": "tma_info_frontend_dsb_coverage < 0.7 & tma_info_thread_ipc / 6 > 0.35", @@ -1390,28 +1373,28 @@ }, { "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@", + "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@", "MetricGroup": "DSBmiss", "MetricName": "tma_info_frontend_dsb_switch_cost", "Unit": "cpu_core" }, { "BriefDescription": "Average number of Uops issued by front-end when it issued something", - "MetricExpr": "UOPS_ISSUED.ANY / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=1@", + "MetricExpr": "cpu_core@UOPS_ISSUED.ANY@ / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=1@", "MetricGroup": "Fed;FetchBW", "MetricName": "tma_info_frontend_fetch_upc", "Unit": "cpu_core" }, { "BriefDescription": "Average Latency for L1 instruction cache misses", - "MetricExpr": "ICACHE_DATA.STALLS / cpu_core@ICACHE_DATA.STALLS\\,cmask\\=1\\,edge@", + "MetricExpr": "cpu_core@ICACHE_DATA.STALLS@ / cpu_core@ICACHE_DATA.STALLS\\,cmask\\=1\\,edge@", "MetricGroup": "Fed;FetchLat;IcMiss", "MetricName": "tma_info_frontend_icache_miss_latency", "Unit": "cpu_core" }, { "BriefDescription": "Instructions per non-speculative DSB miss (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / FRONTEND_RETIRED.ANY_DSB_MISS", "MetricGroup": "DSBmiss;Fed", "MetricName": "tma_info_frontend_ipdsb_miss_ret", "MetricThreshold": "tma_info_frontend_ipdsb_miss_ret < 50", @@ -1440,14 +1423,14 @@ }, { "BriefDescription": "Fraction of Uops delivered by the LSD (Loop Stream Detector; aka Loop Cache)", - "MetricExpr": "LSD.UOPS / cpu_core@UOPS_ISSUED.ANY@", + "MetricExpr": "cpu_core@LSD.UOPS@ / cpu_core@UOPS_ISSUED.ANY@", "MetricGroup": "Fed;LSD", "MetricName": "tma_info_frontend_lsd_coverage", "Unit": "cpu_core" }, { "BriefDescription": "Branch instructions per taken branch.", - "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "MetricExpr": "cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;PGO", "MetricName": "tma_info_inst_mix_bptkbranch", "Unit": "cpu_core" @@ -1462,7 +1445,7 @@ }, { "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (cpu_core@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@)", "MetricGroup": "Flops;InsType", "MetricName": "tma_info_inst_mix_iparith", "MetricThreshold": "tma_info_inst_mix_iparith < 10", @@ -1471,7 +1454,7 @@ }, { "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@)", "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx128", "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", @@ -1480,7 +1463,7 @@ }, { "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@)", "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx256", "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", @@ -1489,7 +1472,7 @@ }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_dp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", @@ -1498,7 +1481,7 @@ }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / FP_ARITH_INST_RETIRED.SCALAR_SINGLE", "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_sp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", @@ -1507,7 +1490,7 @@ }, { "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_INST_RETIRED.ALL_BRANCHES", "MetricGroup": "Branches;Fed;InsType", "MetricName": "tma_info_inst_mix_ipbranch", "MetricThreshold": "tma_info_inst_mix_ipbranch < 8", @@ -1515,7 +1498,7 @@ }, { "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_INST_RETIRED.NEAR_CALL", "MetricGroup": "Branches;Fed;PGO", "MetricName": "tma_info_inst_mix_ipcall", "MetricThreshold": "tma_info_inst_mix_ipcall < 200", @@ -1523,7 +1506,7 @@ }, { "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (cpu_core@FP_ARITH_INST_RETIRED.SCALAR_SINGLE@ + cpu_core@FP_ARITH_INST_RETIRED.SCALAR_DOUBLE@ + 2 * cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + 4 * (cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@) + 8 * cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_INST_RETIRED.SCALAR_SINGLE@ + cpu_core@FP_ARITH_INST_RETIRED.SCALAR_DOUBLE@ + 2 * cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + 4 * (cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@) + 8 * cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@)", "MetricGroup": "Flops;InsType", "MetricName": "tma_info_inst_mix_ipflop", "MetricThreshold": "tma_info_inst_mix_ipflop < 10", @@ -1531,7 +1514,7 @@ }, { "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / MEM_INST_RETIRED.ALL_LOADS", "MetricGroup": "InsType", "MetricName": "tma_info_inst_mix_ipload", "MetricThreshold": "tma_info_inst_mix_ipload < 3", @@ -1539,7 +1522,7 @@ }, { "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / MEM_INST_RETIRED.ALL_STORES", "MetricGroup": "InsType", "MetricName": "tma_info_inst_mix_ipstore", "MetricThreshold": "tma_info_inst_mix_ipstore < 8", @@ -1547,7 +1530,7 @@ }, { "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / cpu_core@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@", "MetricGroup": "Prefetches", "MetricName": "tma_info_inst_mix_ipswpf", "MetricThreshold": "tma_info_inst_mix_ipswpf < 100", @@ -1555,7 +1538,7 @@ }, { "BriefDescription": "Instruction per taken branch", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", "MetricName": "tma_info_inst_mix_iptb", "MetricThreshold": "tma_info_inst_mix_iptb < 13", @@ -1655,14 +1638,14 @@ }, { "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", - "MetricExpr": "L1D_PEND_MISS.PENDING / MEM_LOAD_COMPLETED.L1_MISS_ANY", + "MetricExpr": "cpu_core@L1D_PEND_MISS.PENDING@ / MEM_LOAD_COMPLETED.L1_MISS_ANY", "MetricGroup": "Mem;MemoryBound;MemoryLat", "MetricName": "tma_info_memory_load_miss_real_latency", "Unit": "cpu_core" }, { "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", - "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "MetricExpr": "cpu_core@L1D_PEND_MISS.PENDING@ / L1D_PEND_MISS.PENDING_CYCLES", "MetricGroup": "Mem;MemoryBW;MemoryBound", "MetricName": "tma_info_memory_mlp", "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)", @@ -1670,28 +1653,28 @@ }, { "BriefDescription": "Average Parallel L2 cache miss data reads", - "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD@ / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", "MetricGroup": "Memory_BW;Offcore", "MetricName": "tma_info_memory_oro_data_l2_mlp", "Unit": "cpu_core" }, { "BriefDescription": "Average Latency for L2 cache miss demand Loads", - "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", + "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD@ / OFFCORE_REQUESTS.DEMAND_DATA_RD", "MetricGroup": "Memory_Lat;Offcore", "MetricName": "tma_info_memory_oro_load_l2_miss_latency", "Unit": "cpu_core" }, { "BriefDescription": "Average Parallel L2 cache miss demand Loads", - "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@", + "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD@ / cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@", "MetricGroup": "Memory_BW;Offcore", "MetricName": "tma_info_memory_oro_load_l2_mlp", "Unit": "cpu_core" }, { "BriefDescription": "Average Latency for L3 cache miss demand Loads", - "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD / OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", + "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD@ / OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", "MetricGroup": "Memory_Lat;Offcore", "MetricName": "tma_info_memory_oro_load_l3_miss_latency", "Unit": "cpu_core" @@ -1755,14 +1738,14 @@ }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=1@", + "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=1@", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute", "Unit": "cpu_core" }, { "BriefDescription": "Instructions per a microcode Assist invocation", - "MetricExpr": "INST_RETIRED.ANY / cpu_core@ASSISTS.ANY\\,umask\\=0x1B@", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@ASSISTS.ANY\\,umask\\=0x1B@", "MetricGroup": "Pipeline;Ret;Retire", "MetricName": "tma_info_pipeline_ipassist", "MetricThreshold": "tma_info_pipeline_ipassist < 100e3", @@ -1778,7 +1761,7 @@ }, { "BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions", - "MetricExpr": "INST_RETIRED.REP_ITERATION / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@", + "MetricExpr": "cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@", "MetricGroup": "Pipeline;Ret", "MetricName": "tma_info_pipeline_strings_cycles", "MetricThreshold": "tma_info_pipeline_strings_cycles > 0.1", @@ -1793,7 +1776,7 @@ }, { "BriefDescription": "Average CPU Utilization", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.REF_TSC@ / TSC", "MetricGroup": "HPC;Summary", "MetricName": "tma_info_system_cpu_utilization", "Unit": "cpu_core" @@ -1816,7 +1799,7 @@ }, { "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", - "MetricExpr": "INST_RETIRED.ANY / cpu_core@BR_INST_RETIRED.FAR_BRANCH@u", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_INST_RETIRED.FAR_BRANCH@u", "MetricGroup": "Branches;OS", "MetricName": "tma_info_system_ipfarbranch", "MetricThreshold": "tma_info_system_ipfarbranch < 1e6", @@ -1847,6 +1830,7 @@ }, { "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(UNC_ARB_TRK_OCCUPANCY.RD + UNC_ARB_DAT_OCCUPANCY.RD) / UNC_ARB_TRK_REQUESTS.RD", "MetricGroup": "Mem;MemoryLat;SoC", "MetricName": "tma_info_system_mem_read_latency", @@ -1855,6 +1839,7 @@ }, { "BriefDescription": "Average latency of all requests to external memory (in Uncore cycles)", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(UNC_ARB_TRK_OCCUPANCY.ALL + UNC_ARB_DAT_OCCUPANCY.RD) / UNC_ARB_TRK_REQUESTS.ALL", "MetricGroup": "Mem;SoC", "MetricName": "tma_info_system_mem_request_latency", @@ -1897,7 +1882,7 @@ }, { "BriefDescription": "The ratio of Executed- by Issued-Uops", - "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", + "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / UOPS_ISSUED.ANY", "MetricGroup": "Cor;Pipeline", "MetricName": "tma_info_thread_execute_per_issue", "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage.", @@ -1905,7 +1890,7 @@ }, { "BriefDescription": "Instructions Per Cycle (per Logical Processor)", - "MetricExpr": "INST_RETIRED.ANY / tma_info_thread_clks", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / tma_info_thread_clks", "MetricGroup": "Ret;Summary", "MetricName": "tma_info_thread_ipc", "Unit": "cpu_core" @@ -1972,7 +1957,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", - "MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks", + "MetricExpr": "cpu_core@ICACHE_TAG.STALLS@ / tma_info_thread_clks", "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -1992,7 +1977,6 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(cpu_core@MEMORY_ACTIVITY.STALLS_L1D_MISS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L2_MISS@) / tma_info_thread_clks", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", @@ -2003,7 +1987,6 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "(cpu_core@MEMORY_ACTIVITY.STALLS_L2_MISS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L3_MISS@) / tma_info_thread_clks", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", @@ -2024,7 +2007,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", - "MetricExpr": "DECODE.LCP / tma_info_thread_clks", + "MetricExpr": "cpu_core@DECODE.LCP@ / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -2045,7 +2028,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", - "MetricExpr": "UOPS_DISPATCHED.PORT_2_3_10 / (3 * tma_info_core_core_clks)", + "MetricExpr": "cpu_core@UOPS_DISPATCHED.PORT_2_3_10@ / (3 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_load_op_utilization", "MetricThreshold": "tma_load_op_utilization > 0.6", @@ -2064,7 +2047,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by load accesses, performing a hardware page walk", - "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks", + "MetricExpr": "cpu_core@DTLB_LOAD_MISSES.WALK_ACTIVE@ / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_miss", "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", @@ -2073,7 +2056,6 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(16 * max(0, cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ - cpu_core@L2_RQSTS.ALL_RFO@) + cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@ * (10 * cpu_core@L2_RQSTS.RFO_HIT@ + min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO@))) / tma_info_thread_clks", "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", @@ -2136,6 +2118,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "13 * cpu_core@MISC2_RETIRED.LFENCE@ / tma_info_thread_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_serializing_operation_group", "MetricName": "tma_memory_fence", @@ -2145,7 +2128,6 @@ }, { "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "tma_light_operations * cpu_core@MEM_UOP_RETIRED.ANY@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_memory_operations", @@ -2155,7 +2137,7 @@ }, { "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", - "MetricExpr": "UOPS_RETIRED.MS / tma_info_thread_slots", + "MetricExpr": "cpu_core@UOPS_RETIRED.MS@ / tma_info_thread_slots", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", "MetricName": "tma_microcode_sequencer", "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", @@ -2225,7 +2207,6 @@ }, { "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "max(0, tma_light_operations - (tma_fp_arith + tma_int_operations + tma_memory_operations + tma_fused_instructions + tma_non_fused_branches + tma_nop_instructions))", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_other_light_ops", @@ -2246,7 +2227,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch)", - "MetricExpr": "UOPS_DISPATCHED.PORT_0 / tma_info_core_core_clks", + "MetricExpr": "cpu_core@UOPS_DISPATCHED.PORT_0@ / tma_info_core_core_clks", "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", "MetricThreshold": "tma_port_0 > 0.6", @@ -2256,7 +2237,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU)", - "MetricExpr": "UOPS_DISPATCHED.PORT_1 / tma_info_core_core_clks", + "MetricExpr": "cpu_core@UOPS_DISPATCHED.PORT_1@ / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", "MetricThreshold": "tma_port_1 > 0.6", @@ -2266,7 +2247,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU)", - "MetricExpr": "UOPS_DISPATCHED.PORT_6 / tma_info_core_core_clks", + "MetricExpr": "cpu_core@UOPS_DISPATCHED.PORT_6@ / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", "MetricThreshold": "tma_port_6 > 0.6", @@ -2296,7 +2277,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_thread_clks", + "MetricExpr": "cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -2306,7 +2287,8 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "cpu_core@EXE_ACTIVITY.2_PORTS_UTIL@ / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -2316,7 +2298,8 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "cpu_core@UOPS_EXECUTED.CYCLES_GE_3@ / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", "MetricThreshold": "tma_ports_utilized_3m > 0.7 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -2338,7 +2321,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations", - "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_thread_clks", + "MetricExpr": "cpu_core@RESOURCE_STALLS.SCOREBOARD@ / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL5;tma_L5_group;tma_issueSO;tma_ports_utilized_0_group", "MetricName": "tma_serializing_operation", "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)))", @@ -2348,7 +2331,7 @@ }, { "BriefDescription": "This metric represents Shuffle (cross \"vector lane\" data transfers) uops fraction the CPU has retired.", - "MetricExpr": "INT_VEC_RETIRED.SHUFFLES / (tma_retiring * tma_info_thread_slots)", + "MetricExpr": "cpu_core@INT_VEC_RETIRED.SHUFFLES@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "HPC;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group", "MetricName": "tma_shuffles", "MetricThreshold": "tma_shuffles > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)", @@ -2357,7 +2340,8 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions", - "MetricExpr": "CPU_CLK_UNHALTED.PAUSE / tma_info_thread_clks", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.PAUSE@ / tma_info_thread_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_serializing_operation_group", "MetricName": "tma_slow_pause", "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))))", @@ -2377,8 +2361,7 @@ }, { "BriefDescription": "This metric represents rate of split store accesses", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks", + "MetricExpr": "cpu_core@MEM_INST_RETIRED.SPLIT_STORES@ / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -2398,7 +2381,7 @@ }, { "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", - "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks", + "MetricExpr": "cpu_core@EXE_ACTIVITY.BOUND_ON_STORES@ / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -2408,7 +2391,6 @@ }, { "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "13 * cpu_core@LD_BLOCKS.STORE_FORWARD@ / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", @@ -2448,7 +2430,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles where the STLB was missed by store accesses, performing a hardware page walk", - "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks", + "MetricExpr": "cpu_core@DTLB_STORE_MISSES.WALK_ACTIVE@ / tma_info_core_core_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_miss", "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", @@ -2467,7 +2449,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears", - "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / tma_info_thread_clks", + "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / tma_info_thread_clks", "MetricGroup": "BigFoot;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", "MetricName": "tma_unknown_branches", "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json index c150c14ac6ed..a35edf7d86a9 100644 --- a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json +++ b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json @@ -195,7 +195,6 @@ }, { "BriefDescription": "Counts the number of cycles the core is stalled due to a demand load miss which hit in DRAM or MMIO (Non-DRAM).", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "MEM_BOUND_STALLS.LOAD_DRAM_HIT / tma_info_core_clks - max((MEM_BOUND_STALLS.LOAD - LD_HEAD.L1_MISS_AT_RET) / tma_info_core_clks, 0) * MEM_BOUND_STALLS.LOAD_DRAM_HIT / MEM_BOUND_STALLS.LOAD", "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", @@ -457,7 +456,6 @@ }, { "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the L2 Cache.", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "MEM_BOUND_STALLS.LOAD_L2_HIT / tma_info_core_clks - max((MEM_BOUND_STALLS.LOAD - LD_HEAD.L1_MISS_AT_RET) / tma_info_core_clks, 0) * MEM_BOUND_STALLS.LOAD_L2_HIT / MEM_BOUND_STALLS.LOAD", "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", @@ -466,7 +464,6 @@ }, { "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the Last Level Cache (LLC) or other core with HITE/F/M.", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "MEM_BOUND_STALLS.LOAD_LLC_HIT / tma_info_core_clks - max((MEM_BOUND_STALLS.LOAD - LD_HEAD.L1_MISS_AT_RET) / tma_info_core_clks, 0) * MEM_BOUND_STALLS.LOAD_LLC_HIT / MEM_BOUND_STALLS.LOAD", "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", @@ -683,7 +680,6 @@ }, { "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a store forward block.", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "LD_HEAD.ST_ADDR_AT_RET / tma_info_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json index e31a4aac9f20..56e54babcc26 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json @@ -400,7 +400,6 @@ }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(76 * tma_info_system_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + 75.5 * tma_info_system_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", @@ -421,7 +420,6 @@ }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "75.5 * tma_info_system_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", @@ -449,7 +447,6 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks - tma_pmm_bound if #has_pmem > 0 else MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks)", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", @@ -656,7 +653,6 @@ }, { "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_thread_slots / BR_MISP_RETIRED.ALL_BRANCHES", "MetricGroup": "Bad;BrMispredicts;tma_issueBM", "MetricName": "tma_info_bad_spec_branch_misprediction_cost", @@ -699,7 +695,6 @@ }, { "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(100 * (1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if tma_info_system_smt_2t_utilization > 0.5 else 0)", "MetricGroup": "Cor;SMT", "MetricName": "tma_info_botlnk_l0_core_bound_likely", @@ -707,7 +702,6 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite))", "MetricGroup": "DSBmiss;Fed;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_misses", @@ -716,7 +710,6 @@ }, { "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", "MetricName": "tma_info_botlnk_l2_ic_misses", @@ -725,7 +718,6 @@ }, { "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", "MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB;tma_issueBC", "MetricName": "tma_info_bottleneck_big_code", @@ -742,7 +734,6 @@ }, { "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_bottleneck_big_code", "MetricGroup": "Fed;FetchBW;Frontend", "MetricName": "tma_info_bottleneck_instruction_fetch_bw", @@ -750,7 +741,6 @@ }, { "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))", "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW", "MetricName": "tma_info_bottleneck_memory_bandwidth", @@ -759,7 +749,6 @@ }, { "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "Mem;MemoryTLB;Offcore;tma_issueTLB", "MetricName": "tma_info_bottleneck_memory_data_tlbs", @@ -768,7 +757,6 @@ }, { "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound))", "MetricGroup": "Mem;MemoryLat;Offcore;tma_issueLat", "MetricName": "tma_info_bottleneck_memory_latency", @@ -777,7 +765,6 @@ }, { "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Bad;BadSpec;BrMispredicts;tma_issueBM", "MetricName": "tma_info_bottleneck_mispredictions", @@ -1301,6 +1288,7 @@ }, { "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (tma_info_system_socket_clks / duration_time)", "MetricGroup": "Mem;MemoryLat;SoC", "MetricName": "tma_info_system_mem_read_latency", @@ -1455,7 +1443,6 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L1D_MISS - MEMORY_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", @@ -1465,7 +1452,6 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L2_MISS - MEMORY_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", @@ -1538,7 +1524,6 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks", "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", @@ -1596,6 +1581,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "13 * MISC2_RETIRED.LFENCE / tma_info_thread_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_serializing_operation_group", "MetricName": "tma_memory_fence", @@ -1604,7 +1590,6 @@ }, { "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "tma_light_operations * MEM_UOP_RETIRED.ANY / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_memory_operations", @@ -1676,7 +1661,6 @@ }, { "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "max(0, tma_light_operations - (tma_fp_arith + tma_int_operations + tma_memory_operations + tma_fused_instructions + tma_non_fused_branches + tma_nop_instructions))", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_other_light_ops", @@ -1758,6 +1742,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", @@ -1767,6 +1752,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", @@ -1822,6 +1808,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "CPU_CLK_UNHALTED.PAUSE / tma_info_thread_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_serializing_operation_group", "MetricName": "tma_slow_pause", @@ -1840,7 +1827,6 @@ }, { "BriefDescription": "This metric represents rate of split store accesses", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", @@ -1868,7 +1854,6 @@ }, { "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", diff --git a/tools/perf/tests/shell/daemon.sh b/tools/perf/tests/shell/daemon.sh index 4c598cfc5afa..e5fa8d6f9eb1 100755 --- a/tools/perf/tests/shell/daemon.sh +++ b/tools/perf/tests/shell/daemon.sh @@ -414,16 +414,30 @@ EOF # start daemon daemon_start ${config} test - # send 2 signals - perf daemon signal --config ${config} --session test - perf daemon signal --config ${config} - - # stop daemon - daemon_exit ${config} - - # count is 2 perf.data for signals and 1 for perf record finished - count=`ls ${base}/session-test/*perf.data* | wc -l` - if [ ${count} -ne 3 ]; then + # send 2 signals then exit. Do this in a loop watching the number of + # files to avoid races. If the loop retries more than 600 times then + # give up. + local retries=0 + local signals=0 + local success=0 + while [ ${retries} -lt 600 ] && [ ${success} -eq 0 ]; do + local files + files=`ls ${base}/session-test/*perf.data* 2> /dev/null | wc -l` + if [ ${signals} -eq 0 ]; then + perf daemon signal --config ${config} --session test + signals=1 + elif [ ${signals} -eq 1 ] && [ $files -ge 1 ]; then + perf daemon signal --config ${config} + signals=2 + elif [ ${signals} -eq 2 ] && [ $files -ge 2 ]; then + daemon_exit ${config} + signals=3 + elif [ ${signals} -eq 3 ] && [ $files -ge 3 ]; then + success=1 + fi + retries=$((${retries} +1)) + done + if [ ${success} -eq 0 ]; then error=1 echo "FAILED: perf data no generated" fi diff --git a/tools/perf/tests/shell/list.sh b/tools/perf/tests/shell/list.sh index 22b004f2b23e..8a868ae64560 100755 --- a/tools/perf/tests/shell/list.sh +++ b/tools/perf/tests/shell/list.sh @@ -3,17 +3,32 @@ # SPDX-License-Identifier: GPL-2.0 set -e -err=0 shelldir=$(dirname "$0") # shellcheck source=lib/setup_python.sh . "${shelldir}"/lib/setup_python.sh +list_output=$(mktemp /tmp/__perf_test.list_output.json.XXXXX) + +cleanup() { + rm -f "${list_output}" + + trap - EXIT TERM INT +} + +trap_cleanup() { + cleanup + exit 1 +} +trap trap_cleanup EXIT TERM INT + test_list_json() { echo "Json output test" - perf list -j | $PYTHON -m json.tool + perf list -j -o "${list_output}" + $PYTHON -m json.tool "${list_output}" echo "Json output test [Success]" } test_list_json -exit $err +cleanup +exit 0 diff --git a/tools/perf/tests/shell/script.sh b/tools/perf/tests/shell/script.sh index 5ae7bd0031a8..fa4d71e2e72a 100755 --- a/tools/perf/tests/shell/script.sh +++ b/tools/perf/tests/shell/script.sh @@ -36,8 +36,7 @@ test_db() echo "DB test" # Check if python script is supported - libpython=$(perf version --build-options | grep python | grep -cv OFF) - if [ "${libpython}" != "1" ] ; then + if perf version --build-options | grep python | grep -q OFF ; then echo "SKIP: python scripting is not supported" err=2 return @@ -54,7 +53,14 @@ def sample_table(*args): def call_path_table(*args): print(f'call_path_table({args}') _end_of_file_ - perf record -g -o "${perfdatafile}" true + case $(uname -m) + in s390x) + cmd_flags="--call-graph dwarf -e cpu-clock";; + *) + cmd_flags="-g";; + esac + + perf record $cmd_flags -o "${perfdatafile}" true perf script -i "${perfdatafile}" -s "${db_test}" echo "DB test [Success]" } diff --git a/tools/perf/trace/beauty/statx.c b/tools/perf/trace/beauty/statx.c index 5f5320f7c6e2..dc5943a6352d 100644 --- a/tools/perf/trace/beauty/statx.c +++ b/tools/perf/trace/beauty/statx.c @@ -67,6 +67,7 @@ size_t syscall_arg__scnprintf_statx_mask(char *bf, size_t size, struct syscall_a P_FLAG(BTIME); P_FLAG(MNT_ID); P_FLAG(DIOALIGN); + P_FLAG(MNT_ID_UNIQUE); #undef P_FLAG diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 95f25e9fb994..55a300a0977b 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -103,7 +103,14 @@ struct evlist *evlist__new_default(void) err = parse_event(evlist, can_profile_kernel ? "cycles:P" : "cycles:Pu"); if (err) { evlist__delete(evlist); - evlist = NULL; + return NULL; + } + + if (evlist->core.nr_entries > 1) { + struct evsel *evsel; + + evlist__for_each_entry(evlist, evsel) + evsel__set_sample_id(evsel, /*can_sample_identifier=*/false); } return evlist; diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 0888b7163b7c..fa359180ebf8 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -491,8 +491,8 @@ static int hist_entry__init(struct hist_entry *he, } if (symbol_conf.res_sample) { - he->res_samples = calloc(sizeof(struct res_sample), - symbol_conf.res_sample); + he->res_samples = calloc(symbol_conf.res_sample, + sizeof(struct res_sample)); if (!he->res_samples) goto err_srcline; } diff --git a/tools/perf/util/include/linux/linkage.h b/tools/perf/util/include/linux/linkage.h index 75e2248416f5..178b00205fe6 100644 --- a/tools/perf/util/include/linux/linkage.h +++ b/tools/perf/util/include/linux/linkage.h @@ -115,6 +115,10 @@ SYM_ALIAS(alias, name, SYM_T_FUNC, SYM_L_WEAK) #endif +#ifndef SYM_FUNC_ALIAS_MEMFUNC +#define SYM_FUNC_ALIAS_MEMFUNC SYM_FUNC_ALIAS +#endif + // In the kernel sources (include/linux/cfi_types.h), this has a different // definition when CONFIG_CFI_CLANG is used, for tools/ just use the !clang // definition: diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index ca3e0404f187..966cca5a3e88 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -286,7 +286,7 @@ static int setup_metric_events(const char *pmu, struct hashmap *ids, *out_metric_events = NULL; ids_size = hashmap__size(ids); - metric_events = calloc(sizeof(void *), ids_size + 1); + metric_events = calloc(ids_size + 1, sizeof(void *)); if (!metric_events) return -ENOMEM; diff --git a/tools/perf/util/print-events.c b/tools/perf/util/print-events.c index b0fc48be623f..9e47712507cc 100644 --- a/tools/perf/util/print-events.c +++ b/tools/perf/util/print-events.c @@ -66,7 +66,7 @@ void print_tracepoint_events(const struct print_callbacks *print_cb __maybe_unus put_tracing_file(events_path); if (events_fd < 0) { - printf("Error: failed to open tracing events directory\n"); + pr_err("Error: failed to open tracing events directory\n"); return; } diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index 3712186353fb..2a0289c14959 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -1055,11 +1055,11 @@ int perf_event__synthesize_threads(struct perf_tool *tool, if (thread_nr > n) thread_nr = n; - synthesize_threads = calloc(sizeof(pthread_t), thread_nr); + synthesize_threads = calloc(thread_nr, sizeof(pthread_t)); if (synthesize_threads == NULL) goto free_dirent; - args = calloc(sizeof(*args), thread_nr); + args = calloc(thread_nr, sizeof(*args)); if (args == NULL) goto free_threads; diff --git a/tools/power/cpupower/bench/Makefile b/tools/power/cpupower/bench/Makefile index d9d9923af85c..a4b902f9e1c4 100644 --- a/tools/power/cpupower/bench/Makefile +++ b/tools/power/cpupower/bench/Makefile @@ -15,7 +15,7 @@ LIBS = -L../ -L$(OUTPUT) -lm -lcpupower OBJS = $(OUTPUT)main.o $(OUTPUT)parse.o $(OUTPUT)system.o $(OUTPUT)benchmark.o endif -CFLAGS += -D_GNU_SOURCE -I../lib -DDEFAULT_CONFIG_FILE=\"$(confdir)/cpufreq-bench.conf\" +override CFLAGS += -D_GNU_SOURCE -I../lib -DDEFAULT_CONFIG_FILE=\"$(confdir)/cpufreq-bench.conf\" $(OUTPUT)%.o : %.c $(ECHO) " CC " $@ diff --git a/tools/testing/cxl/Kbuild b/tools/testing/cxl/Kbuild index 0b12c36902d8..caff3834671f 100644 --- a/tools/testing/cxl/Kbuild +++ b/tools/testing/cxl/Kbuild @@ -65,4 +65,6 @@ cxl_core-y += config_check.o cxl_core-y += cxl_core_test.o cxl_core-y += cxl_core_exports.o +KBUILD_CFLAGS := $(filter-out -Wmissing-prototypes -Wmissing-declarations, $(KBUILD_CFLAGS)) + obj-m += test/ diff --git a/tools/testing/cxl/test/Kbuild b/tools/testing/cxl/test/Kbuild index 61d5f7bcddf9..6b1927897856 100644 --- a/tools/testing/cxl/test/Kbuild +++ b/tools/testing/cxl/test/Kbuild @@ -8,3 +8,5 @@ obj-m += cxl_mock_mem.o cxl_test-y := cxl.o cxl_mock-y := mock.o cxl_mock_mem-y := mem.o + +KBUILD_CFLAGS := $(filter-out -Wmissing-prototypes -Wmissing-declarations, $(KBUILD_CFLAGS)) diff --git a/tools/testing/nvdimm/Kbuild b/tools/testing/nvdimm/Kbuild index 8153251ea389..91a3627f301a 100644 --- a/tools/testing/nvdimm/Kbuild +++ b/tools/testing/nvdimm/Kbuild @@ -82,4 +82,6 @@ libnvdimm-$(CONFIG_NVDIMM_KEYS) += $(NVDIMM_SRC)/security.o libnvdimm-y += libnvdimm_test.o libnvdimm-y += config_check.o +KBUILD_CFLAGS := $(filter-out -Wmissing-prototypes -Wmissing-declarations, $(KBUILD_CFLAGS)) + obj-m += test/ diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 15b6a111c3be..082db6b68060 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -191,6 +191,8 @@ run_tests: all @for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests \ + SRC_PATH=$(shell readlink -e $$(pwd)) \ + OBJ_PATH=$(BUILD) \ O=$(abs_objtree); \ done; @@ -241,7 +243,10 @@ ifdef INSTALL_PATH @ret=1; \ for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ - $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET INSTALL_PATH=$(INSTALL_PATH)/$$TARGET install \ + $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET install \ + INSTALL_PATH=$(INSTALL_PATH)/$$TARGET \ + SRC_PATH=$(shell readlink -e $$(pwd)) \ + OBJ_PATH=$(INSTALL_PATH) \ O=$(abs_objtree) \ $(if $(FORCE_TARGETS),|| exit); \ ret=$$((ret * $$?)); \ diff --git a/tools/testing/selftests/bpf/README.rst b/tools/testing/selftests/bpf/README.rst index 9af79c7a9b58..9b974e425af3 100644 --- a/tools/testing/selftests/bpf/README.rst +++ b/tools/testing/selftests/bpf/README.rst @@ -115,7 +115,7 @@ the insn 20 undoes map_value addition. It is currently impossible for the verifier to understand such speculative pointer arithmetic. Hence `this patch`__ addresses it on the compiler side. It was committed on llvm 12. -__ https://reviews.llvm.org/D85570 +__ https://github.com/llvm/llvm-project/commit/ddf1864ace484035e3cde5e83b3a31ac81e059c6 The corresponding C code @@ -165,7 +165,7 @@ This is due to a llvm BPF backend bug. `The fix`__ has been pushed to llvm 10.x release branch and will be available in 10.0.1. The patch is available in llvm 11.0.0 trunk. -__ https://reviews.llvm.org/D78466 +__ https://github.com/llvm/llvm-project/commit/3cb7e7bf959dcd3b8080986c62e10a75c7af43f0 bpf_verif_scale/loop6.bpf.o test failure with Clang 12 ====================================================== @@ -204,7 +204,7 @@ r5(w5) is eventually saved on stack at insn #24 for later use. This cause later verifier failure. The bug has been `fixed`__ in Clang 13. -__ https://reviews.llvm.org/D97479 +__ https://github.com/llvm/llvm-project/commit/1959ead525b8830cc8a345f45e1c3ef9902d3229 BPF CO-RE-based tests and Clang version ======================================= @@ -221,11 +221,11 @@ failures: - __builtin_btf_type_id() [0_, 1_, 2_]; - __builtin_preserve_type_info(), __builtin_preserve_enum_value() [3_, 4_]. -.. _0: https://reviews.llvm.org/D74572 -.. _1: https://reviews.llvm.org/D74668 -.. _2: https://reviews.llvm.org/D85174 -.. _3: https://reviews.llvm.org/D83878 -.. _4: https://reviews.llvm.org/D83242 +.. _0: https://github.com/llvm/llvm-project/commit/6b01b465388b204d543da3cf49efd6080db094a9 +.. _1: https://github.com/llvm/llvm-project/commit/072cde03aaa13a2c57acf62d79876bf79aa1919f +.. _2: https://github.com/llvm/llvm-project/commit/00602ee7ef0bf6c68d690a2bd729c12b95c95c99 +.. _3: https://github.com/llvm/llvm-project/commit/6d218b4adb093ff2e9764febbbc89f429412006c +.. _4: https://github.com/llvm/llvm-project/commit/6d6750696400e7ce988d66a1a00e1d0cb32815f8 Floating-point tests and Clang version ====================================== @@ -234,7 +234,7 @@ Certain selftests, e.g. core_reloc, require support for the floating-point types, which was introduced in `Clang 13`__. The older Clang versions will either crash when compiling these tests, or generate an incorrect BTF. -__ https://reviews.llvm.org/D83289 +__ https://github.com/llvm/llvm-project/commit/a7137b238a07d9399d3ae96c0b461571bd5aa8b2 Kernel function call test and Clang version =========================================== @@ -248,7 +248,7 @@ Without it, the error from compiling bpf selftests looks like: libbpf: failed to find BTF for extern 'tcp_slow_start' [25] section: -2 -__ https://reviews.llvm.org/D93563 +__ https://github.com/llvm/llvm-project/commit/886f9ff53155075bd5f1e994f17b85d1e1b7470c btf_tag test and Clang version ============================== @@ -264,8 +264,8 @@ Without them, the btf_tag selftest will be skipped and you will observe: #<test_num> btf_tag:SKIP -.. _0: https://reviews.llvm.org/D111588 -.. _1: https://reviews.llvm.org/D111199 +.. _0: https://github.com/llvm/llvm-project/commit/a162b67c98066218d0d00aa13b99afb95d9bb5e6 +.. _1: https://github.com/llvm/llvm-project/commit/3466e00716e12e32fdb100e3fcfca5c2b3e8d784 Clang dependencies for static linking tests =========================================== @@ -274,7 +274,7 @@ linked_vars, linked_maps, and linked_funcs tests depend on `Clang fix`__ to generate valid BTF information for weak variables. Please make sure you use Clang that contains the fix. -__ https://reviews.llvm.org/D100362 +__ https://github.com/llvm/llvm-project/commit/968292cb93198442138128d850fd54dc7edc0035 Clang relocation changes ======================== @@ -292,7 +292,7 @@ Here, ``type 2`` refers to new relocation type ``R_BPF_64_ABS64``. To fix this issue, user newer libbpf. .. Links -.. _clang reloc patch: https://reviews.llvm.org/D102712 +.. _clang reloc patch: https://github.com/llvm/llvm-project/commit/6a2ea84600ba4bd3b2733bd8f08f5115eb32164b .. _kernel llvm reloc: /Documentation/bpf/llvm_reloc.rst Clang dependencies for the u32 spill test (xdpwall) @@ -304,6 +304,6 @@ from running test_progs will look like: .. code-block:: console - test_xdpwall:FAIL:Does LLVM have https://reviews.llvm.org/D109073? unexpected error: -4007 + test_xdpwall:FAIL:Does LLVM have https://github.com/llvm/llvm-project/commit/ea72b0319d7b0f0c2fcf41d121afa5d031b319d5? unexpected error: -4007 -__ https://reviews.llvm.org/D109073 +__ https://github.com/llvm/llvm-project/commit/ea72b0319d7b0f0c2fcf41d121afa5d031b319d5 diff --git a/tools/testing/selftests/bpf/bpf_experimental.h b/tools/testing/selftests/bpf/bpf_experimental.h index f44875f8b367..0d749006d107 100644 --- a/tools/testing/selftests/bpf/bpf_experimental.h +++ b/tools/testing/selftests/bpf/bpf_experimental.h @@ -260,11 +260,11 @@ extern void bpf_throw(u64 cookie) __ksym; #define __is_signed_type(type) (((type)(-1)) < (type)1) -#define __bpf_cmp(LHS, OP, SIGN, PRED, RHS, DEFAULT) \ +#define __bpf_cmp(LHS, OP, PRED, RHS, DEFAULT) \ ({ \ __label__ l_true; \ bool ret = DEFAULT; \ - asm volatile goto("if %[lhs] " SIGN #OP " %[rhs] goto %l[l_true]" \ + asm volatile goto("if %[lhs] " OP " %[rhs] goto %l[l_true]" \ :: [lhs] "r"((short)LHS), [rhs] PRED (RHS) :: l_true); \ ret = !DEFAULT; \ l_true: \ @@ -276,7 +276,7 @@ l_true: \ * __lhs OP __rhs below will catch the mistake. * Be aware that we check only __lhs to figure out the sign of compare. */ -#define _bpf_cmp(LHS, OP, RHS, NOFLIP) \ +#define _bpf_cmp(LHS, OP, RHS, UNLIKELY) \ ({ \ typeof(LHS) __lhs = (LHS); \ typeof(RHS) __rhs = (RHS); \ @@ -285,14 +285,17 @@ l_true: \ (void)(__lhs OP __rhs); \ if (__cmp_cannot_be_signed(OP) || !__is_signed_type(typeof(__lhs))) { \ if (sizeof(__rhs) == 8) \ - ret = __bpf_cmp(__lhs, OP, "", "r", __rhs, NOFLIP); \ + /* "i" will truncate 64-bit constant into s32, \ + * so we have to use extra register via "r". \ + */ \ + ret = __bpf_cmp(__lhs, #OP, "r", __rhs, UNLIKELY); \ else \ - ret = __bpf_cmp(__lhs, OP, "", "i", __rhs, NOFLIP); \ + ret = __bpf_cmp(__lhs, #OP, "ri", __rhs, UNLIKELY); \ } else { \ if (sizeof(__rhs) == 8) \ - ret = __bpf_cmp(__lhs, OP, "s", "r", __rhs, NOFLIP); \ + ret = __bpf_cmp(__lhs, "s"#OP, "r", __rhs, UNLIKELY); \ else \ - ret = __bpf_cmp(__lhs, OP, "s", "i", __rhs, NOFLIP); \ + ret = __bpf_cmp(__lhs, "s"#OP, "ri", __rhs, UNLIKELY); \ } \ ret; \ }) @@ -304,7 +307,7 @@ l_true: \ #ifndef bpf_cmp_likely #define bpf_cmp_likely(LHS, OP, RHS) \ ({ \ - bool ret; \ + bool ret = 0; \ if (__builtin_strcmp(#OP, "==") == 0) \ ret = _bpf_cmp(LHS, !=, RHS, false); \ else if (__builtin_strcmp(#OP, "!=") == 0) \ @@ -318,7 +321,7 @@ l_true: \ else if (__builtin_strcmp(#OP, ">=") == 0) \ ret = _bpf_cmp(LHS, <, RHS, false); \ else \ - (void) "bug"; \ + asm volatile("r0 " #OP " invalid compare"); \ ret; \ }) #endif diff --git a/tools/testing/selftests/bpf/bpf_kfuncs.h b/tools/testing/selftests/bpf/bpf_kfuncs.h index b4e78c1eb37b..23c24f852f4f 100644 --- a/tools/testing/selftests/bpf/bpf_kfuncs.h +++ b/tools/testing/selftests/bpf/bpf_kfuncs.h @@ -51,6 +51,16 @@ extern int bpf_dynptr_clone(const struct bpf_dynptr *ptr, struct bpf_dynptr *clo extern int bpf_sock_addr_set_sun_path(struct bpf_sock_addr_kern *sa_kern, const __u8 *sun_path, __u32 sun_path__sz) __ksym; +/* Description + * Allocate and configure a reqsk and link it with a listener and skb. + * Returns + * Error code + */ +struct sock; +struct bpf_tcp_req_attrs; +extern int bpf_sk_assign_tcp_reqsk(struct __sk_buff *skb, struct sock *sk, + struct bpf_tcp_req_attrs *attrs, int attrs__sz) __ksym; + void *bpf_cast_to_kern_ctx(void *) __ksym; void *bpf_rdonly_cast(void *obj, __u32 btf_id) __ksym; diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c index 91907b321f91..8befaf17d454 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c @@ -1,7 +1,9 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2020 Facebook */ +#include <linux/bpf.h> #include <linux/btf.h> #include <linux/btf_ids.h> +#include <linux/delay.h> #include <linux/error-injection.h> #include <linux/init.h> #include <linux/module.h> @@ -520,11 +522,75 @@ BTF_ID_FLAGS(func, bpf_kfunc_call_test_static_unused_arg) BTF_ID_FLAGS(func, bpf_kfunc_call_test_offset) BTF_SET8_END(bpf_testmod_check_kfunc_ids) +static int bpf_testmod_ops_init(struct btf *btf) +{ + return 0; +} + +static bool bpf_testmod_ops_is_valid_access(int off, int size, + enum bpf_access_type type, + const struct bpf_prog *prog, + struct bpf_insn_access_aux *info) +{ + return bpf_tracing_btf_ctx_access(off, size, type, prog, info); +} + +static int bpf_testmod_ops_init_member(const struct btf_type *t, + const struct btf_member *member, + void *kdata, const void *udata) +{ + return 0; +} + static const struct btf_kfunc_id_set bpf_testmod_kfunc_set = { .owner = THIS_MODULE, .set = &bpf_testmod_check_kfunc_ids, }; +static const struct bpf_verifier_ops bpf_testmod_verifier_ops = { + .is_valid_access = bpf_testmod_ops_is_valid_access, +}; + +static int bpf_dummy_reg(void *kdata) +{ + struct bpf_testmod_ops *ops = kdata; + int r; + + r = ops->test_2(4, 3); + + return 0; +} + +static void bpf_dummy_unreg(void *kdata) +{ +} + +static int bpf_testmod_test_1(void) +{ + return 0; +} + +static int bpf_testmod_test_2(int a, int b) +{ + return 0; +} + +static struct bpf_testmod_ops __bpf_testmod_ops = { + .test_1 = bpf_testmod_test_1, + .test_2 = bpf_testmod_test_2, +}; + +struct bpf_struct_ops bpf_bpf_testmod_ops = { + .verifier_ops = &bpf_testmod_verifier_ops, + .init = bpf_testmod_ops_init, + .init_member = bpf_testmod_ops_init_member, + .reg = bpf_dummy_reg, + .unreg = bpf_dummy_unreg, + .cfi_stubs = &__bpf_testmod_ops, + .name = "bpf_testmod_ops", + .owner = THIS_MODULE, +}; + extern int bpf_fentry_test1(int a); static int bpf_testmod_init(void) @@ -535,6 +601,7 @@ static int bpf_testmod_init(void) ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_testmod_kfunc_set); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_testmod_kfunc_set); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SYSCALL, &bpf_testmod_kfunc_set); + ret = ret ?: register_bpf_struct_ops(&bpf_bpf_testmod_ops, bpf_testmod_ops); if (ret < 0) return ret; if (bpf_fentry_test1(0) < 0) @@ -544,6 +611,14 @@ static int bpf_testmod_init(void) static void bpf_testmod_exit(void) { + /* Need to wait for all references to be dropped because + * bpf_kfunc_call_test_release() which currently resides in kernel can + * be called after bpf_testmod is unloaded. Once release function is + * moved into the module this wait can be removed. + */ + while (refcount_read(&prog_test_struct.cnt) > 1) + msleep(20); + return sysfs_remove_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file); } diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h index f32793efe095..ca5435751c79 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h @@ -28,4 +28,9 @@ struct bpf_iter_testmod_seq { int cnt; }; +struct bpf_testmod_ops { + int (*test_1)(void); + int (*test_2)(int a, int b); +}; + #endif /* _BPF_TESTMOD_H */ diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index c125c441abc7..01f241ea2c67 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -81,6 +81,7 @@ CONFIG_NF_NAT=y CONFIG_RC_CORE=y CONFIG_SECURITY=y CONFIG_SECURITYFS=y +CONFIG_SYN_COOKIES=y CONFIG_TEST_BPF=m CONFIG_USERFAULTFD=y CONFIG_VSOCKETS=y diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c index e770912fc1d2..4c6ada5b270b 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c @@ -35,7 +35,7 @@ static int check_load(const char *file, enum bpf_prog_type type) } bpf_program__set_type(prog, type); - bpf_program__set_flags(prog, BPF_F_TEST_RND_HI32 | BPF_F_TEST_REG_INVARIANTS); + bpf_program__set_flags(prog, testing_prog_flags()); bpf_program__set_log_level(prog, 4 | extra_prog_load_log_flags); err = bpf_object__load(obj); diff --git a/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c b/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c index 4951aa978f33..3b7c57fe55a5 100644 --- a/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c +++ b/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c @@ -626,50 +626,6 @@ err: return false; } -/* Request BPF program instructions after all rewrites are applied, - * e.g. verifier.c:convert_ctx_access() is done. - */ -static int get_xlated_program(int fd_prog, struct bpf_insn **buf, __u32 *cnt) -{ - struct bpf_prog_info info = {}; - __u32 info_len = sizeof(info); - __u32 xlated_prog_len; - __u32 buf_element_size = sizeof(struct bpf_insn); - - if (bpf_prog_get_info_by_fd(fd_prog, &info, &info_len)) { - perror("bpf_prog_get_info_by_fd failed"); - return -1; - } - - xlated_prog_len = info.xlated_prog_len; - if (xlated_prog_len % buf_element_size) { - printf("Program length %d is not multiple of %d\n", - xlated_prog_len, buf_element_size); - return -1; - } - - *cnt = xlated_prog_len / buf_element_size; - *buf = calloc(*cnt, buf_element_size); - if (!buf) { - perror("can't allocate xlated program buffer"); - return -ENOMEM; - } - - bzero(&info, sizeof(info)); - info.xlated_prog_len = xlated_prog_len; - info.xlated_prog_insns = (__u64)(unsigned long)*buf; - if (bpf_prog_get_info_by_fd(fd_prog, &info, &info_len)) { - perror("second bpf_prog_get_info_by_fd failed"); - goto out_free_buf; - } - - return 0; - -out_free_buf: - free(*buf); - return -1; -} - static void print_insn(void *private_data, const char *fmt, ...) { va_list args; diff --git a/tools/testing/selftests/bpf/prog_tests/fill_link_info.c b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c index d4b1901f7879..f3932941bbaa 100644 --- a/tools/testing/selftests/bpf/prog_tests/fill_link_info.c +++ b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c @@ -19,6 +19,7 @@ static const char *kmulti_syms[] = { }; #define KMULTI_CNT ARRAY_SIZE(kmulti_syms) static __u64 kmulti_addrs[KMULTI_CNT]; +static __u64 kmulti_cookies[] = { 3, 1, 2 }; #define KPROBE_FUNC "bpf_fentry_test1" static __u64 kprobe_addr; @@ -31,6 +32,8 @@ static noinline void uprobe_func(void) asm volatile (""); } +#define PERF_EVENT_COOKIE 0xdeadbeef + static int verify_perf_link_info(int fd, enum bpf_perf_event_type type, long addr, ssize_t offset, ssize_t entry_offset) { @@ -62,6 +65,8 @@ again: ASSERT_EQ(info.perf_event.kprobe.addr, addr + entry_offset, "kprobe_addr"); + ASSERT_EQ(info.perf_event.kprobe.cookie, PERF_EVENT_COOKIE, "kprobe_cookie"); + if (!info.perf_event.kprobe.func_name) { ASSERT_EQ(info.perf_event.kprobe.name_len, 0, "name_len"); info.perf_event.kprobe.func_name = ptr_to_u64(&buf); @@ -81,6 +86,8 @@ again: goto again; } + ASSERT_EQ(info.perf_event.tracepoint.cookie, PERF_EVENT_COOKIE, "tracepoint_cookie"); + err = strncmp(u64_to_ptr(info.perf_event.tracepoint.tp_name), TP_NAME, strlen(TP_NAME)); ASSERT_EQ(err, 0, "cmp_tp_name"); @@ -96,10 +103,17 @@ again: goto again; } + ASSERT_EQ(info.perf_event.uprobe.cookie, PERF_EVENT_COOKIE, "uprobe_cookie"); + err = strncmp(u64_to_ptr(info.perf_event.uprobe.file_name), UPROBE_FILE, strlen(UPROBE_FILE)); ASSERT_EQ(err, 0, "cmp_file_name"); break; + case BPF_PERF_EVENT_EVENT: + ASSERT_EQ(info.perf_event.event.type, PERF_TYPE_SOFTWARE, "event_type"); + ASSERT_EQ(info.perf_event.event.config, PERF_COUNT_SW_PAGE_FAULTS, "event_config"); + ASSERT_EQ(info.perf_event.event.cookie, PERF_EVENT_COOKIE, "event_cookie"); + break; default: err = -1; break; @@ -139,6 +153,7 @@ static void test_kprobe_fill_link_info(struct test_fill_link_info *skel, DECLARE_LIBBPF_OPTS(bpf_kprobe_opts, opts, .attach_mode = PROBE_ATTACH_MODE_LINK, .retprobe = type == BPF_PERF_EVENT_KRETPROBE, + .bpf_cookie = PERF_EVENT_COOKIE, ); ssize_t entry_offset = 0; struct bpf_link *link; @@ -163,10 +178,13 @@ static void test_kprobe_fill_link_info(struct test_fill_link_info *skel, static void test_tp_fill_link_info(struct test_fill_link_info *skel) { + DECLARE_LIBBPF_OPTS(bpf_tracepoint_opts, opts, + .bpf_cookie = PERF_EVENT_COOKIE, + ); struct bpf_link *link; int link_fd, err; - link = bpf_program__attach_tracepoint(skel->progs.tp_run, TP_CAT, TP_NAME); + link = bpf_program__attach_tracepoint_opts(skel->progs.tp_run, TP_CAT, TP_NAME, &opts); if (!ASSERT_OK_PTR(link, "attach_tp")) return; @@ -176,16 +194,53 @@ static void test_tp_fill_link_info(struct test_fill_link_info *skel) bpf_link__destroy(link); } +static void test_event_fill_link_info(struct test_fill_link_info *skel) +{ + DECLARE_LIBBPF_OPTS(bpf_perf_event_opts, opts, + .bpf_cookie = PERF_EVENT_COOKIE, + ); + struct bpf_link *link; + int link_fd, err, pfd; + struct perf_event_attr attr = { + .type = PERF_TYPE_SOFTWARE, + .config = PERF_COUNT_SW_PAGE_FAULTS, + .freq = 1, + .sample_freq = 1, + .size = sizeof(struct perf_event_attr), + }; + + pfd = syscall(__NR_perf_event_open, &attr, -1 /* pid */, 0 /* cpu 0 */, + -1 /* group id */, 0 /* flags */); + if (!ASSERT_GE(pfd, 0, "perf_event_open")) + return; + + link = bpf_program__attach_perf_event_opts(skel->progs.event_run, pfd, &opts); + if (!ASSERT_OK_PTR(link, "attach_event")) + goto error; + + link_fd = bpf_link__fd(link); + err = verify_perf_link_info(link_fd, BPF_PERF_EVENT_EVENT, 0, 0, 0); + ASSERT_OK(err, "verify_perf_link_info"); + bpf_link__destroy(link); + +error: + close(pfd); +} + static void test_uprobe_fill_link_info(struct test_fill_link_info *skel, enum bpf_perf_event_type type) { + DECLARE_LIBBPF_OPTS(bpf_uprobe_opts, opts, + .retprobe = type == BPF_PERF_EVENT_URETPROBE, + .bpf_cookie = PERF_EVENT_COOKIE, + ); struct bpf_link *link; int link_fd, err; - link = bpf_program__attach_uprobe(skel->progs.uprobe_run, - type == BPF_PERF_EVENT_URETPROBE, - 0, /* self pid */ - UPROBE_FILE, uprobe_offset); + link = bpf_program__attach_uprobe_opts(skel->progs.uprobe_run, + 0, /* self pid */ + UPROBE_FILE, uprobe_offset, + &opts); if (!ASSERT_OK_PTR(link, "attach_uprobe")) return; @@ -195,11 +250,11 @@ static void test_uprobe_fill_link_info(struct test_fill_link_info *skel, bpf_link__destroy(link); } -static int verify_kmulti_link_info(int fd, bool retprobe) +static int verify_kmulti_link_info(int fd, bool retprobe, bool has_cookies) { + __u64 addrs[KMULTI_CNT], cookies[KMULTI_CNT]; struct bpf_link_info info; __u32 len = sizeof(info); - __u64 addrs[KMULTI_CNT]; int flags, i, err; memset(&info, 0, sizeof(info)); @@ -221,18 +276,22 @@ again: if (!info.kprobe_multi.addrs) { info.kprobe_multi.addrs = ptr_to_u64(addrs); + info.kprobe_multi.cookies = ptr_to_u64(cookies); goto again; } - for (i = 0; i < KMULTI_CNT; i++) + for (i = 0; i < KMULTI_CNT; i++) { ASSERT_EQ(addrs[i], kmulti_addrs[i], "kmulti_addrs"); + ASSERT_EQ(cookies[i], has_cookies ? kmulti_cookies[i] : 0, + "kmulti_cookies_value"); + } return 0; } static void verify_kmulti_invalid_user_buffer(int fd) { + __u64 addrs[KMULTI_CNT], cookies[KMULTI_CNT]; struct bpf_link_info info; __u32 len = sizeof(info); - __u64 addrs[KMULTI_CNT]; int err, i; memset(&info, 0, sizeof(info)); @@ -266,7 +325,20 @@ static void verify_kmulti_invalid_user_buffer(int fd) info.kprobe_multi.count = KMULTI_CNT; info.kprobe_multi.addrs = 0x1; /* invalid addr */ err = bpf_link_get_info_by_fd(fd, &info, &len); - ASSERT_EQ(err, -EFAULT, "invalid_buff"); + ASSERT_EQ(err, -EFAULT, "invalid_buff_addrs"); + + info.kprobe_multi.count = KMULTI_CNT; + info.kprobe_multi.addrs = ptr_to_u64(addrs); + info.kprobe_multi.cookies = 0x1; /* invalid addr */ + err = bpf_link_get_info_by_fd(fd, &info, &len); + ASSERT_EQ(err, -EFAULT, "invalid_buff_cookies"); + + /* cookies && !count */ + info.kprobe_multi.count = 0; + info.kprobe_multi.addrs = ptr_to_u64(NULL); + info.kprobe_multi.cookies = ptr_to_u64(cookies); + err = bpf_link_get_info_by_fd(fd, &info, &len); + ASSERT_EQ(err, -EINVAL, "invalid_cookies_count"); } static int symbols_cmp_r(const void *a, const void *b) @@ -278,13 +350,15 @@ static int symbols_cmp_r(const void *a, const void *b) } static void test_kprobe_multi_fill_link_info(struct test_fill_link_info *skel, - bool retprobe, bool invalid) + bool retprobe, bool cookies, + bool invalid) { LIBBPF_OPTS(bpf_kprobe_multi_opts, opts); struct bpf_link *link; int link_fd, err; opts.syms = kmulti_syms; + opts.cookies = cookies ? kmulti_cookies : NULL; opts.cnt = KMULTI_CNT; opts.retprobe = retprobe; link = bpf_program__attach_kprobe_multi_opts(skel->progs.kmulti_run, NULL, &opts); @@ -293,7 +367,7 @@ static void test_kprobe_multi_fill_link_info(struct test_fill_link_info *skel, link_fd = bpf_link__fd(link); if (!invalid) { - err = verify_kmulti_link_info(link_fd, retprobe); + err = verify_kmulti_link_info(link_fd, retprobe, cookies); ASSERT_OK(err, "verify_kmulti_link_info"); } else { verify_kmulti_invalid_user_buffer(link_fd); @@ -513,6 +587,8 @@ void test_fill_link_info(void) test_kprobe_fill_link_info(skel, BPF_PERF_EVENT_KPROBE, true); if (test__start_subtest("tracepoint_link_info")) test_tp_fill_link_info(skel); + if (test__start_subtest("event_link_info")) + test_event_fill_link_info(skel); uprobe_offset = get_uprobe_offset(&uprobe_func); if (test__start_subtest("uprobe_link_info")) @@ -523,12 +599,16 @@ void test_fill_link_info(void) qsort(kmulti_syms, KMULTI_CNT, sizeof(kmulti_syms[0]), symbols_cmp_r); for (i = 0; i < KMULTI_CNT; i++) kmulti_addrs[i] = ksym_get_addr(kmulti_syms[i]); - if (test__start_subtest("kprobe_multi_link_info")) - test_kprobe_multi_fill_link_info(skel, false, false); - if (test__start_subtest("kretprobe_multi_link_info")) - test_kprobe_multi_fill_link_info(skel, true, false); + if (test__start_subtest("kprobe_multi_link_info")) { + test_kprobe_multi_fill_link_info(skel, false, false, false); + test_kprobe_multi_fill_link_info(skel, false, true, false); + } + if (test__start_subtest("kretprobe_multi_link_info")) { + test_kprobe_multi_fill_link_info(skel, true, false, false); + test_kprobe_multi_fill_link_info(skel, true, true, false); + } if (test__start_subtest("kprobe_multi_invalid_ubuff")) - test_kprobe_multi_fill_link_info(skel, true, true); + test_kprobe_multi_fill_link_info(skel, true, true, true); if (test__start_subtest("uprobe_multi_link_info")) test_uprobe_multi_fill_link_info(skel, false, false); diff --git a/tools/testing/selftests/bpf/prog_tests/kptr_xchg_inline.c b/tools/testing/selftests/bpf/prog_tests/kptr_xchg_inline.c new file mode 100644 index 000000000000..15144943e88b --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/kptr_xchg_inline.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023. Huawei Technologies Co., Ltd */ +#include <test_progs.h> + +#include "linux/filter.h" +#include "kptr_xchg_inline.skel.h" + +void test_kptr_xchg_inline(void) +{ + struct kptr_xchg_inline *skel; + struct bpf_insn *insn = NULL; + struct bpf_insn exp; + unsigned int cnt; + int err; + +#if !(defined(__x86_64__) || defined(__aarch64__)) + test__skip(); + return; +#endif + + skel = kptr_xchg_inline__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_load")) + return; + + err = get_xlated_program(bpf_program__fd(skel->progs.kptr_xchg_inline), &insn, &cnt); + if (!ASSERT_OK(err, "prog insn")) + goto out; + + /* The original instructions are: + * r1 = map[id:xxx][0]+0 + * r2 = 0 + * call bpf_kptr_xchg#yyy + * + * call bpf_kptr_xchg#yyy will be inlined as: + * r0 = r2 + * r0 = atomic64_xchg((u64 *)(r1 +0), r0) + */ + if (!ASSERT_GT(cnt, 5, "insn cnt")) + goto out; + + exp = BPF_MOV64_REG(BPF_REG_0, BPF_REG_2); + if (!ASSERT_OK(memcmp(&insn[3], &exp, sizeof(exp)), "mov")) + goto out; + + exp = BPF_ATOMIC_OP(BPF_DW, BPF_XCHG, BPF_REG_1, BPF_REG_0, 0); + if (!ASSERT_OK(memcmp(&insn[4], &exp, sizeof(exp)), "xchg")) + goto out; +out: + free(insn); + kptr_xchg_inline__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c b/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c index 9f766ddd946a..4ed46ed58a7b 100644 --- a/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c +++ b/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c @@ -30,6 +30,8 @@ void test_libbpf_probe_prog_types(void) if (prog_type == BPF_PROG_TYPE_UNSPEC) continue; + if (strcmp(prog_type_name, "__MAX_BPF_PROG_TYPE") == 0) + continue; if (!test__start_subtest(prog_type_name)) continue; @@ -68,6 +70,8 @@ void test_libbpf_probe_map_types(void) if (map_type == BPF_MAP_TYPE_UNSPEC) continue; + if (strcmp(map_type_name, "__MAX_BPF_MAP_TYPE") == 0) + continue; if (!test__start_subtest(map_type_name)) continue; diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c index eb34d612d6f8..62ea855ec4d0 100644 --- a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c +++ b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c @@ -132,6 +132,9 @@ static void test_libbpf_bpf_map_type_str(void) const char *map_type_str; char buf[256]; + if (map_type == __MAX_BPF_MAP_TYPE) + continue; + map_type_name = btf__str_by_offset(btf, e->name_off); map_type_str = libbpf_bpf_map_type_str(map_type); ASSERT_OK_PTR(map_type_str, map_type_name); @@ -186,6 +189,9 @@ static void test_libbpf_bpf_prog_type_str(void) const char *prog_type_str; char buf[256]; + if (prog_type == __MAX_BPF_PROG_TYPE) + continue; + prog_type_name = btf__str_by_offset(btf, e->name_off); prog_type_str = libbpf_bpf_prog_type_str(prog_type); ASSERT_OK_PTR(prog_type_str, prog_type_name); diff --git a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c index 820d0bcfc474..eb74363f9f70 100644 --- a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c +++ b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c @@ -840,7 +840,7 @@ static int load_range_cmp_prog(struct range x, struct range y, enum op op, .log_level = 2, .log_buf = log_buf, .log_size = log_sz, - .prog_flags = BPF_F_TEST_REG_INVARIANTS, + .prog_flags = testing_prog_flags(), ); /* ; skip exit block below diff --git a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c index 518f143c5b0f..dbe06aeaa2b2 100644 --- a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c +++ b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c @@ -188,6 +188,7 @@ static int netns_setup_links_and_routes(struct netns_setup_result *result) { struct nstoken *nstoken = NULL; char src_fwd_addr[IFADDR_STR_LEN+1] = {}; + char src_addr[IFADDR_STR_LEN + 1] = {}; int err; if (result->dev_mode == MODE_VETH) { @@ -208,6 +209,9 @@ static int netns_setup_links_and_routes(struct netns_setup_result *result) if (get_ifaddr("src_fwd", src_fwd_addr)) goto fail; + if (get_ifaddr("src", src_addr)) + goto fail; + result->ifindex_src = if_nametoindex("src"); if (!ASSERT_GT(result->ifindex_src, 0, "ifindex_src")) goto fail; @@ -270,6 +274,13 @@ static int netns_setup_links_and_routes(struct netns_setup_result *result) SYS(fail, "ip route add " IP4_DST "/32 dev dst_fwd scope global"); SYS(fail, "ip route add " IP6_DST "/128 dev dst_fwd scope global"); + if (result->dev_mode == MODE_VETH) { + SYS(fail, "ip neigh add " IP4_SRC " dev src_fwd lladdr %s", src_addr); + SYS(fail, "ip neigh add " IP6_SRC " dev src_fwd lladdr %s", src_addr); + SYS(fail, "ip neigh add " IP4_DST " dev dst_fwd lladdr %s", MAC_DST); + SYS(fail, "ip neigh add " IP6_DST " dev dst_fwd lladdr %s", MAC_DST); + } + close_netns(nstoken); /** setup in 'dst' namespace */ @@ -280,6 +291,7 @@ static int netns_setup_links_and_routes(struct netns_setup_result *result) SYS(fail, "ip addr add " IP4_DST "/32 dev dst"); SYS(fail, "ip addr add " IP6_DST "/128 dev dst nodad"); SYS(fail, "ip link set dev dst up"); + SYS(fail, "ip link set dev lo up"); SYS(fail, "ip route add " IP4_SRC "/32 dev dst scope global"); SYS(fail, "ip route add " IP4_NET "/16 dev dst scope global"); @@ -457,7 +469,7 @@ static int set_forwarding(bool enable) return 0; } -static void rcv_tstamp(int fd, const char *expected, size_t s) +static int __rcv_tstamp(int fd, const char *expected, size_t s, __u64 *tstamp) { struct __kernel_timespec pkt_ts = {}; char ctl[CMSG_SPACE(sizeof(pkt_ts))]; @@ -478,7 +490,7 @@ static void rcv_tstamp(int fd, const char *expected, size_t s) ret = recvmsg(fd, &msg, 0); if (!ASSERT_EQ(ret, s, "recvmsg")) - return; + return -1; ASSERT_STRNEQ(data, expected, s, "expected rcv data"); cmsg = CMSG_FIRSTHDR(&msg); @@ -487,6 +499,12 @@ static void rcv_tstamp(int fd, const char *expected, size_t s) memcpy(&pkt_ts, CMSG_DATA(cmsg), sizeof(pkt_ts)); pkt_ns = pkt_ts.tv_sec * NSEC_PER_SEC + pkt_ts.tv_nsec; + if (tstamp) { + /* caller will check the tstamp itself */ + *tstamp = pkt_ns; + return 0; + } + ASSERT_NEQ(pkt_ns, 0, "pkt rcv tstamp"); ret = clock_gettime(CLOCK_REALTIME, &now_ts); @@ -496,6 +514,60 @@ static void rcv_tstamp(int fd, const char *expected, size_t s) if (ASSERT_GE(now_ns, pkt_ns, "check rcv tstamp")) ASSERT_LT(now_ns - pkt_ns, 5 * NSEC_PER_SEC, "check rcv tstamp"); + return 0; +} + +static void rcv_tstamp(int fd, const char *expected, size_t s) +{ + __rcv_tstamp(fd, expected, s, NULL); +} + +static int wait_netstamp_needed_key(void) +{ + int opt = 1, srv_fd = -1, cli_fd = -1, nretries = 0, err, n; + char buf[] = "testing testing"; + struct nstoken *nstoken; + __u64 tstamp = 0; + + nstoken = open_netns(NS_DST); + if (!nstoken) + return -1; + + srv_fd = start_server(AF_INET6, SOCK_DGRAM, "::1", 0, 0); + if (!ASSERT_GE(srv_fd, 0, "start_server")) + goto done; + + err = setsockopt(srv_fd, SOL_SOCKET, SO_TIMESTAMPNS_NEW, + &opt, sizeof(opt)); + if (!ASSERT_OK(err, "setsockopt(SO_TIMESTAMPNS_NEW)")) + goto done; + + cli_fd = connect_to_fd(srv_fd, TIMEOUT_MILLIS); + if (!ASSERT_GE(cli_fd, 0, "connect_to_fd")) + goto done; + +again: + n = write(cli_fd, buf, sizeof(buf)); + if (!ASSERT_EQ(n, sizeof(buf), "send to server")) + goto done; + err = __rcv_tstamp(srv_fd, buf, sizeof(buf), &tstamp); + if (!ASSERT_OK(err, "__rcv_tstamp")) + goto done; + if (!tstamp && nretries++ < 5) { + sleep(1); + printf("netstamp_needed_key retry#%d\n", nretries); + goto again; + } + +done: + if (!tstamp && srv_fd != -1) { + close(srv_fd); + srv_fd = -1; + } + if (cli_fd != -1) + close(cli_fd); + close_netns(nstoken); + return srv_fd; } static void snd_tstamp(int fd, char *b, size_t s) @@ -832,11 +904,20 @@ static void test_tc_redirect_dtime(struct netns_setup_result *setup_result) { struct test_tc_dtime *skel; struct nstoken *nstoken; - int err; + int hold_tstamp_fd, err; + + /* Hold a sk with the SOCK_TIMESTAMP set to ensure there + * is no delay in the kernel net_enable_timestamp(). + * This ensures the following tests must have + * non zero rcv tstamp in the recvmsg(). + */ + hold_tstamp_fd = wait_netstamp_needed_key(); + if (!ASSERT_GE(hold_tstamp_fd, 0, "wait_netstamp_needed_key")) + return; skel = test_tc_dtime__open(); if (!ASSERT_OK_PTR(skel, "test_tc_dtime__open")) - return; + goto done; skel->rodata->IFINDEX_SRC = setup_result->ifindex_src_fwd; skel->rodata->IFINDEX_DST = setup_result->ifindex_dst_fwd; @@ -881,6 +962,7 @@ static void test_tc_redirect_dtime(struct netns_setup_result *setup_result) done: test_tc_dtime__destroy(skel); + close(hold_tstamp_fd); } static void test_tc_redirect_neigh_fib(struct netns_setup_result *setup_result) diff --git a/tools/testing/selftests/bpf/prog_tests/tcp_custom_syncookie.c b/tools/testing/selftests/bpf/prog_tests/tcp_custom_syncookie.c new file mode 100644 index 000000000000..eaf441dc7e79 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/tcp_custom_syncookie.c @@ -0,0 +1,150 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright Amazon.com Inc. or its affiliates. */ + +#define _GNU_SOURCE +#include <sched.h> +#include <stdlib.h> +#include <net/if.h> + +#include "test_progs.h" +#include "cgroup_helpers.h" +#include "network_helpers.h" +#include "test_tcp_custom_syncookie.skel.h" + +static struct test_tcp_custom_syncookie_case { + int family, type; + char addr[16]; + char name[10]; +} test_cases[] = { + { + .name = "IPv4 TCP", + .family = AF_INET, + .type = SOCK_STREAM, + .addr = "127.0.0.1", + }, + { + .name = "IPv6 TCP", + .family = AF_INET6, + .type = SOCK_STREAM, + .addr = "::1", + }, +}; + +static int setup_netns(void) +{ + if (!ASSERT_OK(unshare(CLONE_NEWNET), "create netns")) + return -1; + + if (!ASSERT_OK(system("ip link set dev lo up"), "ip")) + goto err; + + if (!ASSERT_OK(write_sysctl("/proc/sys/net/ipv4/tcp_ecn", "1"), + "write_sysctl")) + goto err; + + return 0; +err: + return -1; +} + +static int setup_tc(struct test_tcp_custom_syncookie *skel) +{ + LIBBPF_OPTS(bpf_tc_hook, qdisc_lo, .attach_point = BPF_TC_INGRESS); + LIBBPF_OPTS(bpf_tc_opts, tc_attach, + .prog_fd = bpf_program__fd(skel->progs.tcp_custom_syncookie)); + + qdisc_lo.ifindex = if_nametoindex("lo"); + if (!ASSERT_OK(bpf_tc_hook_create(&qdisc_lo), "qdisc add dev lo clsact")) + goto err; + + if (!ASSERT_OK(bpf_tc_attach(&qdisc_lo, &tc_attach), + "filter add dev lo ingress")) + goto err; + + return 0; +err: + return -1; +} + +#define msg "Hello World" +#define msglen 11 + +static void transfer_message(int sender, int receiver) +{ + char buf[msglen]; + int ret; + + ret = send(sender, msg, msglen, 0); + if (!ASSERT_EQ(ret, msglen, "send")) + return; + + memset(buf, 0, sizeof(buf)); + + ret = recv(receiver, buf, msglen, 0); + if (!ASSERT_EQ(ret, msglen, "recv")) + return; + + ret = strncmp(buf, msg, msglen); + if (!ASSERT_EQ(ret, 0, "strncmp")) + return; +} + +static void create_connection(struct test_tcp_custom_syncookie_case *test_case) +{ + int server, client, child; + + server = start_server(test_case->family, test_case->type, test_case->addr, 0, 0); + if (!ASSERT_NEQ(server, -1, "start_server")) + return; + + client = connect_to_fd(server, 0); + if (!ASSERT_NEQ(client, -1, "connect_to_fd")) + goto close_server; + + child = accept(server, NULL, 0); + if (!ASSERT_NEQ(child, -1, "accept")) + goto close_client; + + transfer_message(client, child); + transfer_message(child, client); + + close(child); +close_client: + close(client); +close_server: + close(server); +} + +void test_tcp_custom_syncookie(void) +{ + struct test_tcp_custom_syncookie *skel; + int i; + + if (setup_netns()) + return; + + skel = test_tcp_custom_syncookie__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + return; + + if (setup_tc(skel)) + goto destroy_skel; + + for (i = 0; i < ARRAY_SIZE(test_cases); i++) { + if (!test__start_subtest(test_cases[i].name)) + continue; + + skel->bss->handled_syn = false; + skel->bss->handled_ack = false; + + create_connection(&test_cases[i]); + + ASSERT_EQ(skel->bss->handled_syn, true, "SYN is not handled at tc."); + ASSERT_EQ(skel->bss->handled_ack, true, "ACK is not handled at tc"); + } + +destroy_skel: + system("tc qdisc del dev lo clsact"); + + test_tcp_custom_syncookie__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/test_struct_ops_module.c b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_module.c new file mode 100644 index 000000000000..8d833f0c7580 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_module.c @@ -0,0 +1,75 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ +#include <test_progs.h> +#include <time.h> + +#include "struct_ops_module.skel.h" + +static void check_map_info(struct bpf_map_info *info) +{ + struct bpf_btf_info btf_info; + char btf_name[256]; + u32 btf_info_len = sizeof(btf_info); + int err, fd; + + fd = bpf_btf_get_fd_by_id(info->btf_vmlinux_id); + if (!ASSERT_GE(fd, 0, "get_value_type_btf_obj_fd")) + return; + + memset(&btf_info, 0, sizeof(btf_info)); + btf_info.name = ptr_to_u64(btf_name); + btf_info.name_len = sizeof(btf_name); + err = bpf_btf_get_info_by_fd(fd, &btf_info, &btf_info_len); + if (!ASSERT_OK(err, "get_value_type_btf_obj_info")) + goto cleanup; + + if (!ASSERT_EQ(strcmp(btf_name, "bpf_testmod"), 0, "get_value_type_btf_obj_name")) + goto cleanup; + +cleanup: + close(fd); +} + +static void test_struct_ops_load(void) +{ + DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts); + struct struct_ops_module *skel; + struct bpf_map_info info = {}; + struct bpf_link *link; + int err; + u32 len; + + skel = struct_ops_module__open_opts(&opts); + if (!ASSERT_OK_PTR(skel, "struct_ops_module_open")) + return; + + err = struct_ops_module__load(skel); + if (!ASSERT_OK(err, "struct_ops_module_load")) + goto cleanup; + + len = sizeof(info); + err = bpf_map_get_info_by_fd(bpf_map__fd(skel->maps.testmod_1), &info, + &len); + if (!ASSERT_OK(err, "bpf_map_get_info_by_fd")) + goto cleanup; + + link = bpf_map__attach_struct_ops(skel->maps.testmod_1); + ASSERT_OK_PTR(link, "attach_test_mod_1"); + + /* test_2() will be called from bpf_dummy_reg() in bpf_testmod.c */ + ASSERT_EQ(skel->bss->test_2_result, 7, "test_2_result"); + + bpf_link__destroy(link); + + check_map_info(&info); + +cleanup: + struct_ops_module__destroy(skel); +} + +void serial_test_struct_ops_module(void) +{ + if (test__start_subtest("test_struct_ops_load")) + test_struct_ops_load(); +} + diff --git a/tools/testing/selftests/bpf/prog_tests/token.c b/tools/testing/selftests/bpf/prog_tests/token.c new file mode 100644 index 000000000000..fc4a175d8d76 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/token.c @@ -0,0 +1,1052 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ +#define _GNU_SOURCE +#include <test_progs.h> +#include <bpf/btf.h> +#include "cap_helpers.h" +#include <fcntl.h> +#include <sched.h> +#include <signal.h> +#include <unistd.h> +#include <linux/filter.h> +#include <linux/unistd.h> +#include <linux/mount.h> +#include <sys/socket.h> +#include <sys/stat.h> +#include <sys/syscall.h> +#include <sys/un.h> +#include "priv_map.skel.h" +#include "priv_prog.skel.h" +#include "dummy_st_ops_success.skel.h" +#include "token_lsm.skel.h" + +static inline int sys_mount(const char *dev_name, const char *dir_name, + const char *type, unsigned long flags, + const void *data) +{ + return syscall(__NR_mount, dev_name, dir_name, type, flags, data); +} + +static inline int sys_fsopen(const char *fsname, unsigned flags) +{ + return syscall(__NR_fsopen, fsname, flags); +} + +static inline int sys_fspick(int dfd, const char *path, unsigned flags) +{ + return syscall(__NR_fspick, dfd, path, flags); +} + +static inline int sys_fsconfig(int fs_fd, unsigned cmd, const char *key, const void *val, int aux) +{ + return syscall(__NR_fsconfig, fs_fd, cmd, key, val, aux); +} + +static inline int sys_fsmount(int fs_fd, unsigned flags, unsigned ms_flags) +{ + return syscall(__NR_fsmount, fs_fd, flags, ms_flags); +} + +static inline int sys_move_mount(int from_dfd, const char *from_path, + int to_dfd, const char *to_path, + unsigned flags) +{ + return syscall(__NR_move_mount, from_dfd, from_path, to_dfd, to_path, flags); +} + +static int drop_priv_caps(__u64 *old_caps) +{ + return cap_disable_effective((1ULL << CAP_BPF) | + (1ULL << CAP_PERFMON) | + (1ULL << CAP_NET_ADMIN) | + (1ULL << CAP_SYS_ADMIN), old_caps); +} + +static int restore_priv_caps(__u64 old_caps) +{ + return cap_enable_effective(old_caps, NULL); +} + +static int set_delegate_mask(int fs_fd, const char *key, __u64 mask, const char *mask_str) +{ + char buf[32]; + int err; + + if (!mask_str) { + if (mask == ~0ULL) { + mask_str = "any"; + } else { + snprintf(buf, sizeof(buf), "0x%llx", (unsigned long long)mask); + mask_str = buf; + } + } + + err = sys_fsconfig(fs_fd, FSCONFIG_SET_STRING, key, + mask_str, 0); + if (err < 0) + err = -errno; + return err; +} + +#define zclose(fd) do { if (fd >= 0) close(fd); fd = -1; } while (0) + +struct bpffs_opts { + __u64 cmds; + __u64 maps; + __u64 progs; + __u64 attachs; + const char *cmds_str; + const char *maps_str; + const char *progs_str; + const char *attachs_str; +}; + +static int create_bpffs_fd(void) +{ + int fs_fd; + + /* create VFS context */ + fs_fd = sys_fsopen("bpf", 0); + ASSERT_GE(fs_fd, 0, "fs_fd"); + + return fs_fd; +} + +static int materialize_bpffs_fd(int fs_fd, struct bpffs_opts *opts) +{ + int mnt_fd, err; + + /* set up token delegation mount options */ + err = set_delegate_mask(fs_fd, "delegate_cmds", opts->cmds, opts->cmds_str); + if (!ASSERT_OK(err, "fs_cfg_cmds")) + return err; + err = set_delegate_mask(fs_fd, "delegate_maps", opts->maps, opts->maps_str); + if (!ASSERT_OK(err, "fs_cfg_maps")) + return err; + err = set_delegate_mask(fs_fd, "delegate_progs", opts->progs, opts->progs_str); + if (!ASSERT_OK(err, "fs_cfg_progs")) + return err; + err = set_delegate_mask(fs_fd, "delegate_attachs", opts->attachs, opts->attachs_str); + if (!ASSERT_OK(err, "fs_cfg_attachs")) + return err; + + /* instantiate FS object */ + err = sys_fsconfig(fs_fd, FSCONFIG_CMD_CREATE, NULL, NULL, 0); + if (err < 0) + return -errno; + + /* create O_PATH fd for detached mount */ + mnt_fd = sys_fsmount(fs_fd, 0, 0); + if (err < 0) + return -errno; + + return mnt_fd; +} + +/* send FD over Unix domain (AF_UNIX) socket */ +static int sendfd(int sockfd, int fd) +{ + struct msghdr msg = {}; + struct cmsghdr *cmsg; + int fds[1] = { fd }, err; + char iobuf[1]; + struct iovec io = { + .iov_base = iobuf, + .iov_len = sizeof(iobuf), + }; + union { + char buf[CMSG_SPACE(sizeof(fds))]; + struct cmsghdr align; + } u; + + msg.msg_iov = &io; + msg.msg_iovlen = 1; + msg.msg_control = u.buf; + msg.msg_controllen = sizeof(u.buf); + cmsg = CMSG_FIRSTHDR(&msg); + cmsg->cmsg_level = SOL_SOCKET; + cmsg->cmsg_type = SCM_RIGHTS; + cmsg->cmsg_len = CMSG_LEN(sizeof(fds)); + memcpy(CMSG_DATA(cmsg), fds, sizeof(fds)); + + err = sendmsg(sockfd, &msg, 0); + if (err < 0) + err = -errno; + if (!ASSERT_EQ(err, 1, "sendmsg")) + return -EINVAL; + + return 0; +} + +/* receive FD over Unix domain (AF_UNIX) socket */ +static int recvfd(int sockfd, int *fd) +{ + struct msghdr msg = {}; + struct cmsghdr *cmsg; + int fds[1], err; + char iobuf[1]; + struct iovec io = { + .iov_base = iobuf, + .iov_len = sizeof(iobuf), + }; + union { + char buf[CMSG_SPACE(sizeof(fds))]; + struct cmsghdr align; + } u; + + msg.msg_iov = &io; + msg.msg_iovlen = 1; + msg.msg_control = u.buf; + msg.msg_controllen = sizeof(u.buf); + + err = recvmsg(sockfd, &msg, 0); + if (err < 0) + err = -errno; + if (!ASSERT_EQ(err, 1, "recvmsg")) + return -EINVAL; + + cmsg = CMSG_FIRSTHDR(&msg); + if (!ASSERT_OK_PTR(cmsg, "cmsg_null") || + !ASSERT_EQ(cmsg->cmsg_len, CMSG_LEN(sizeof(fds)), "cmsg_len") || + !ASSERT_EQ(cmsg->cmsg_level, SOL_SOCKET, "cmsg_level") || + !ASSERT_EQ(cmsg->cmsg_type, SCM_RIGHTS, "cmsg_type")) + return -EINVAL; + + memcpy(fds, CMSG_DATA(cmsg), sizeof(fds)); + *fd = fds[0]; + + return 0; +} + +static ssize_t write_nointr(int fd, const void *buf, size_t count) +{ + ssize_t ret; + + do { + ret = write(fd, buf, count); + } while (ret < 0 && errno == EINTR); + + return ret; +} + +static int write_file(const char *path, const void *buf, size_t count) +{ + int fd; + ssize_t ret; + + fd = open(path, O_WRONLY | O_CLOEXEC | O_NOCTTY | O_NOFOLLOW); + if (fd < 0) + return -1; + + ret = write_nointr(fd, buf, count); + close(fd); + if (ret < 0 || (size_t)ret != count) + return -1; + + return 0; +} + +static int create_and_enter_userns(void) +{ + uid_t uid; + gid_t gid; + char map[100]; + + uid = getuid(); + gid = getgid(); + + if (unshare(CLONE_NEWUSER)) + return -1; + + if (write_file("/proc/self/setgroups", "deny", sizeof("deny") - 1) && + errno != ENOENT) + return -1; + + snprintf(map, sizeof(map), "0 %d 1", uid); + if (write_file("/proc/self/uid_map", map, strlen(map))) + return -1; + + + snprintf(map, sizeof(map), "0 %d 1", gid); + if (write_file("/proc/self/gid_map", map, strlen(map))) + return -1; + + if (setgid(0)) + return -1; + + if (setuid(0)) + return -1; + + return 0; +} + +typedef int (*child_callback_fn)(int bpffs_fd, struct token_lsm *lsm_skel); + +static void child(int sock_fd, struct bpffs_opts *opts, child_callback_fn callback) +{ + int mnt_fd = -1, fs_fd = -1, err = 0, bpffs_fd = -1, token_fd = -1; + struct token_lsm *lsm_skel = NULL; + + /* load and attach LSM "policy" before we go into unpriv userns */ + lsm_skel = token_lsm__open_and_load(); + if (!ASSERT_OK_PTR(lsm_skel, "lsm_skel_load")) { + err = -EINVAL; + goto cleanup; + } + lsm_skel->bss->my_pid = getpid(); + err = token_lsm__attach(lsm_skel); + if (!ASSERT_OK(err, "lsm_skel_attach")) + goto cleanup; + + /* setup userns with root mappings */ + err = create_and_enter_userns(); + if (!ASSERT_OK(err, "create_and_enter_userns")) + goto cleanup; + + /* setup mountns to allow creating BPF FS (fsopen("bpf")) from unpriv process */ + err = unshare(CLONE_NEWNS); + if (!ASSERT_OK(err, "create_mountns")) + goto cleanup; + + err = sys_mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, 0); + if (!ASSERT_OK(err, "remount_root")) + goto cleanup; + + fs_fd = create_bpffs_fd(); + if (!ASSERT_GE(fs_fd, 0, "create_bpffs_fd")) { + err = -EINVAL; + goto cleanup; + } + + /* ensure unprivileged child cannot set delegation options */ + err = set_delegate_mask(fs_fd, "delegate_cmds", 0x1, NULL); + ASSERT_EQ(err, -EPERM, "delegate_cmd_eperm"); + err = set_delegate_mask(fs_fd, "delegate_maps", 0x1, NULL); + ASSERT_EQ(err, -EPERM, "delegate_maps_eperm"); + err = set_delegate_mask(fs_fd, "delegate_progs", 0x1, NULL); + ASSERT_EQ(err, -EPERM, "delegate_progs_eperm"); + err = set_delegate_mask(fs_fd, "delegate_attachs", 0x1, NULL); + ASSERT_EQ(err, -EPERM, "delegate_attachs_eperm"); + + /* pass BPF FS context object to parent */ + err = sendfd(sock_fd, fs_fd); + if (!ASSERT_OK(err, "send_fs_fd")) + goto cleanup; + zclose(fs_fd); + + /* avoid mucking around with mount namespaces and mounting at + * well-known path, just get detach-mounted BPF FS fd back from parent + */ + err = recvfd(sock_fd, &mnt_fd); + if (!ASSERT_OK(err, "recv_mnt_fd")) + goto cleanup; + + /* try to fspick() BPF FS and try to add some delegation options */ + fs_fd = sys_fspick(mnt_fd, "", FSPICK_EMPTY_PATH); + if (!ASSERT_GE(fs_fd, 0, "bpffs_fspick")) { + err = -EINVAL; + goto cleanup; + } + + /* ensure unprivileged child cannot reconfigure to set delegation options */ + err = set_delegate_mask(fs_fd, "delegate_cmds", 0, "any"); + if (!ASSERT_EQ(err, -EPERM, "delegate_cmd_eperm_reconfig")) { + err = -EINVAL; + goto cleanup; + } + err = set_delegate_mask(fs_fd, "delegate_maps", 0, "any"); + if (!ASSERT_EQ(err, -EPERM, "delegate_maps_eperm_reconfig")) { + err = -EINVAL; + goto cleanup; + } + err = set_delegate_mask(fs_fd, "delegate_progs", 0, "any"); + if (!ASSERT_EQ(err, -EPERM, "delegate_progs_eperm_reconfig")) { + err = -EINVAL; + goto cleanup; + } + err = set_delegate_mask(fs_fd, "delegate_attachs", 0, "any"); + if (!ASSERT_EQ(err, -EPERM, "delegate_attachs_eperm_reconfig")) { + err = -EINVAL; + goto cleanup; + } + zclose(fs_fd); + + bpffs_fd = openat(mnt_fd, ".", 0, O_RDWR); + if (!ASSERT_GE(bpffs_fd, 0, "bpffs_open")) { + err = -EINVAL; + goto cleanup; + } + + /* create BPF token FD and pass it to parent for some extra checks */ + token_fd = bpf_token_create(bpffs_fd, NULL); + if (!ASSERT_GT(token_fd, 0, "child_token_create")) { + err = -EINVAL; + goto cleanup; + } + err = sendfd(sock_fd, token_fd); + if (!ASSERT_OK(err, "send_token_fd")) + goto cleanup; + zclose(token_fd); + + /* do custom test logic with customly set up BPF FS instance */ + err = callback(bpffs_fd, lsm_skel); + if (!ASSERT_OK(err, "test_callback")) + goto cleanup; + + err = 0; +cleanup: + zclose(sock_fd); + zclose(mnt_fd); + zclose(fs_fd); + zclose(bpffs_fd); + zclose(token_fd); + + lsm_skel->bss->my_pid = 0; + token_lsm__destroy(lsm_skel); + + exit(-err); +} + +static int wait_for_pid(pid_t pid) +{ + int status, ret; + +again: + ret = waitpid(pid, &status, 0); + if (ret == -1) { + if (errno == EINTR) + goto again; + + return -1; + } + + if (!WIFEXITED(status)) + return -1; + + return WEXITSTATUS(status); +} + +static void parent(int child_pid, struct bpffs_opts *bpffs_opts, int sock_fd) +{ + int fs_fd = -1, mnt_fd = -1, token_fd = -1, err; + + err = recvfd(sock_fd, &fs_fd); + if (!ASSERT_OK(err, "recv_bpffs_fd")) + goto cleanup; + + mnt_fd = materialize_bpffs_fd(fs_fd, bpffs_opts); + if (!ASSERT_GE(mnt_fd, 0, "materialize_bpffs_fd")) { + err = -EINVAL; + goto cleanup; + } + zclose(fs_fd); + + /* pass BPF FS context object to parent */ + err = sendfd(sock_fd, mnt_fd); + if (!ASSERT_OK(err, "send_mnt_fd")) + goto cleanup; + zclose(mnt_fd); + + /* receive BPF token FD back from child for some extra tests */ + err = recvfd(sock_fd, &token_fd); + if (!ASSERT_OK(err, "recv_token_fd")) + goto cleanup; + + err = wait_for_pid(child_pid); + ASSERT_OK(err, "waitpid_child"); + +cleanup: + zclose(sock_fd); + zclose(fs_fd); + zclose(mnt_fd); + zclose(token_fd); + + if (child_pid > 0) + (void)kill(child_pid, SIGKILL); +} + +static void subtest_userns(struct bpffs_opts *bpffs_opts, + child_callback_fn child_cb) +{ + int sock_fds[2] = { -1, -1 }; + int child_pid = 0, err; + + err = socketpair(AF_UNIX, SOCK_STREAM, 0, sock_fds); + if (!ASSERT_OK(err, "socketpair")) + goto cleanup; + + child_pid = fork(); + if (!ASSERT_GE(child_pid, 0, "fork")) + goto cleanup; + + if (child_pid == 0) { + zclose(sock_fds[0]); + return child(sock_fds[1], bpffs_opts, child_cb); + + } else { + zclose(sock_fds[1]); + return parent(child_pid, bpffs_opts, sock_fds[0]); + } + +cleanup: + zclose(sock_fds[0]); + zclose(sock_fds[1]); + if (child_pid > 0) + (void)kill(child_pid, SIGKILL); +} + +static int userns_map_create(int mnt_fd, struct token_lsm *lsm_skel) +{ + LIBBPF_OPTS(bpf_map_create_opts, map_opts); + int err, token_fd = -1, map_fd = -1; + __u64 old_caps = 0; + + /* create BPF token from BPF FS mount */ + token_fd = bpf_token_create(mnt_fd, NULL); + if (!ASSERT_GT(token_fd, 0, "token_create")) { + err = -EINVAL; + goto cleanup; + } + + /* while inside non-init userns, we need both a BPF token *and* + * CAP_BPF inside current userns to create privileged map; let's test + * that neither BPF token alone nor namespaced CAP_BPF is sufficient + */ + err = drop_priv_caps(&old_caps); + if (!ASSERT_OK(err, "drop_caps")) + goto cleanup; + + /* no token, no CAP_BPF -> fail */ + map_opts.map_flags = 0; + map_opts.token_fd = 0; + map_fd = bpf_map_create(BPF_MAP_TYPE_STACK, "wo_token_wo_bpf", 0, 8, 1, &map_opts); + if (!ASSERT_LT(map_fd, 0, "stack_map_wo_token_wo_cap_bpf_should_fail")) { + err = -EINVAL; + goto cleanup; + } + + /* token without CAP_BPF -> fail */ + map_opts.map_flags = BPF_F_TOKEN_FD; + map_opts.token_fd = token_fd; + map_fd = bpf_map_create(BPF_MAP_TYPE_STACK, "w_token_wo_bpf", 0, 8, 1, &map_opts); + if (!ASSERT_LT(map_fd, 0, "stack_map_w_token_wo_cap_bpf_should_fail")) { + err = -EINVAL; + goto cleanup; + } + + /* get back effective local CAP_BPF (and CAP_SYS_ADMIN) */ + err = restore_priv_caps(old_caps); + if (!ASSERT_OK(err, "restore_caps")) + goto cleanup; + + /* CAP_BPF without token -> fail */ + map_opts.map_flags = 0; + map_opts.token_fd = 0; + map_fd = bpf_map_create(BPF_MAP_TYPE_STACK, "wo_token_w_bpf", 0, 8, 1, &map_opts); + if (!ASSERT_LT(map_fd, 0, "stack_map_wo_token_w_cap_bpf_should_fail")) { + err = -EINVAL; + goto cleanup; + } + + /* finally, namespaced CAP_BPF + token -> success */ + map_opts.map_flags = BPF_F_TOKEN_FD; + map_opts.token_fd = token_fd; + map_fd = bpf_map_create(BPF_MAP_TYPE_STACK, "w_token_w_bpf", 0, 8, 1, &map_opts); + if (!ASSERT_GT(map_fd, 0, "stack_map_w_token_w_cap_bpf")) { + err = -EINVAL; + goto cleanup; + } + +cleanup: + zclose(token_fd); + zclose(map_fd); + return err; +} + +static int userns_btf_load(int mnt_fd, struct token_lsm *lsm_skel) +{ + LIBBPF_OPTS(bpf_btf_load_opts, btf_opts); + int err, token_fd = -1, btf_fd = -1; + const void *raw_btf_data; + struct btf *btf = NULL; + __u32 raw_btf_size; + __u64 old_caps = 0; + + /* create BPF token from BPF FS mount */ + token_fd = bpf_token_create(mnt_fd, NULL); + if (!ASSERT_GT(token_fd, 0, "token_create")) { + err = -EINVAL; + goto cleanup; + } + + /* while inside non-init userns, we need both a BPF token *and* + * CAP_BPF inside current userns to create privileged map; let's test + * that neither BPF token alone nor namespaced CAP_BPF is sufficient + */ + err = drop_priv_caps(&old_caps); + if (!ASSERT_OK(err, "drop_caps")) + goto cleanup; + + /* setup a trivial BTF data to load to the kernel */ + btf = btf__new_empty(); + if (!ASSERT_OK_PTR(btf, "empty_btf")) + goto cleanup; + + ASSERT_GT(btf__add_int(btf, "int", 4, 0), 0, "int_type"); + + raw_btf_data = btf__raw_data(btf, &raw_btf_size); + if (!ASSERT_OK_PTR(raw_btf_data, "raw_btf_data")) + goto cleanup; + + /* no token + no CAP_BPF -> failure */ + btf_opts.btf_flags = 0; + btf_opts.token_fd = 0; + btf_fd = bpf_btf_load(raw_btf_data, raw_btf_size, &btf_opts); + if (!ASSERT_LT(btf_fd, 0, "no_token_no_cap_should_fail")) + goto cleanup; + + /* token + no CAP_BPF -> failure */ + btf_opts.btf_flags = BPF_F_TOKEN_FD; + btf_opts.token_fd = token_fd; + btf_fd = bpf_btf_load(raw_btf_data, raw_btf_size, &btf_opts); + if (!ASSERT_LT(btf_fd, 0, "token_no_cap_should_fail")) + goto cleanup; + + /* get back effective local CAP_BPF (and CAP_SYS_ADMIN) */ + err = restore_priv_caps(old_caps); + if (!ASSERT_OK(err, "restore_caps")) + goto cleanup; + + /* token + CAP_BPF -> success */ + btf_opts.btf_flags = BPF_F_TOKEN_FD; + btf_opts.token_fd = token_fd; + btf_fd = bpf_btf_load(raw_btf_data, raw_btf_size, &btf_opts); + if (!ASSERT_GT(btf_fd, 0, "token_and_cap_success")) + goto cleanup; + + err = 0; +cleanup: + btf__free(btf); + zclose(btf_fd); + zclose(token_fd); + return err; +} + +static int userns_prog_load(int mnt_fd, struct token_lsm *lsm_skel) +{ + LIBBPF_OPTS(bpf_prog_load_opts, prog_opts); + int err, token_fd = -1, prog_fd = -1; + struct bpf_insn insns[] = { + /* bpf_jiffies64() requires CAP_BPF */ + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_jiffies64), + /* bpf_get_current_task() requires CAP_PERFMON */ + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_current_task), + /* r0 = 0; exit; */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + size_t insn_cnt = ARRAY_SIZE(insns); + __u64 old_caps = 0; + + /* create BPF token from BPF FS mount */ + token_fd = bpf_token_create(mnt_fd, NULL); + if (!ASSERT_GT(token_fd, 0, "token_create")) { + err = -EINVAL; + goto cleanup; + } + + /* validate we can successfully load BPF program with token; this + * being XDP program (CAP_NET_ADMIN) using bpf_jiffies64() (CAP_BPF) + * and bpf_get_current_task() (CAP_PERFMON) helpers validates we have + * BPF token wired properly in a bunch of places in the kernel + */ + prog_opts.prog_flags = BPF_F_TOKEN_FD; + prog_opts.token_fd = token_fd; + prog_opts.expected_attach_type = BPF_XDP; + prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, "token_prog", "GPL", + insns, insn_cnt, &prog_opts); + if (!ASSERT_GT(prog_fd, 0, "prog_fd")) { + err = -EPERM; + goto cleanup; + } + + /* no token + caps -> failure */ + prog_opts.prog_flags = 0; + prog_opts.token_fd = 0; + prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, "token_prog", "GPL", + insns, insn_cnt, &prog_opts); + if (!ASSERT_EQ(prog_fd, -EPERM, "prog_fd_eperm")) { + err = -EPERM; + goto cleanup; + } + + err = drop_priv_caps(&old_caps); + if (!ASSERT_OK(err, "drop_caps")) + goto cleanup; + + /* no caps + token -> failure */ + prog_opts.prog_flags = BPF_F_TOKEN_FD; + prog_opts.token_fd = token_fd; + prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, "token_prog", "GPL", + insns, insn_cnt, &prog_opts); + if (!ASSERT_EQ(prog_fd, -EPERM, "prog_fd_eperm")) { + err = -EPERM; + goto cleanup; + } + + /* no caps + no token -> definitely a failure */ + prog_opts.prog_flags = 0; + prog_opts.token_fd = 0; + prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, "token_prog", "GPL", + insns, insn_cnt, &prog_opts); + if (!ASSERT_EQ(prog_fd, -EPERM, "prog_fd_eperm")) { + err = -EPERM; + goto cleanup; + } + + err = 0; +cleanup: + zclose(prog_fd); + zclose(token_fd); + return err; +} + +static int userns_obj_priv_map(int mnt_fd, struct token_lsm *lsm_skel) +{ + LIBBPF_OPTS(bpf_object_open_opts, opts); + char buf[256]; + struct priv_map *skel; + int err; + + skel = priv_map__open_and_load(); + if (!ASSERT_ERR_PTR(skel, "obj_tokenless_load")) { + priv_map__destroy(skel); + return -EINVAL; + } + + /* use bpf_token_path to provide BPF FS path */ + snprintf(buf, sizeof(buf), "/proc/self/fd/%d", mnt_fd); + opts.bpf_token_path = buf; + skel = priv_map__open_opts(&opts); + if (!ASSERT_OK_PTR(skel, "obj_token_path_open")) + return -EINVAL; + + err = priv_map__load(skel); + priv_map__destroy(skel); + if (!ASSERT_OK(err, "obj_token_path_load")) + return -EINVAL; + + return 0; +} + +static int userns_obj_priv_prog(int mnt_fd, struct token_lsm *lsm_skel) +{ + LIBBPF_OPTS(bpf_object_open_opts, opts); + char buf[256]; + struct priv_prog *skel; + int err; + + skel = priv_prog__open_and_load(); + if (!ASSERT_ERR_PTR(skel, "obj_tokenless_load")) { + priv_prog__destroy(skel); + return -EINVAL; + } + + /* use bpf_token_path to provide BPF FS path */ + snprintf(buf, sizeof(buf), "/proc/self/fd/%d", mnt_fd); + opts.bpf_token_path = buf; + skel = priv_prog__open_opts(&opts); + if (!ASSERT_OK_PTR(skel, "obj_token_path_open")) + return -EINVAL; + err = priv_prog__load(skel); + priv_prog__destroy(skel); + if (!ASSERT_OK(err, "obj_token_path_load")) + return -EINVAL; + + /* provide BPF token, but reject bpf_token_capable() with LSM */ + lsm_skel->bss->reject_capable = true; + lsm_skel->bss->reject_cmd = false; + skel = priv_prog__open_opts(&opts); + if (!ASSERT_OK_PTR(skel, "obj_token_lsm_reject_cap_open")) + return -EINVAL; + err = priv_prog__load(skel); + priv_prog__destroy(skel); + if (!ASSERT_ERR(err, "obj_token_lsm_reject_cap_load")) + return -EINVAL; + + /* provide BPF token, but reject bpf_token_cmd() with LSM */ + lsm_skel->bss->reject_capable = false; + lsm_skel->bss->reject_cmd = true; + skel = priv_prog__open_opts(&opts); + if (!ASSERT_OK_PTR(skel, "obj_token_lsm_reject_cmd_open")) + return -EINVAL; + err = priv_prog__load(skel); + priv_prog__destroy(skel); + if (!ASSERT_ERR(err, "obj_token_lsm_reject_cmd_load")) + return -EINVAL; + + return 0; +} + +/* this test is called with BPF FS that doesn't delegate BPF_BTF_LOAD command, + * which should cause struct_ops application to fail, as BTF won't be uploaded + * into the kernel, even if STRUCT_OPS programs themselves are allowed + */ +static int validate_struct_ops_load(int mnt_fd, bool expect_success) +{ + LIBBPF_OPTS(bpf_object_open_opts, opts); + char buf[256]; + struct dummy_st_ops_success *skel; + int err; + + snprintf(buf, sizeof(buf), "/proc/self/fd/%d", mnt_fd); + opts.bpf_token_path = buf; + skel = dummy_st_ops_success__open_opts(&opts); + if (!ASSERT_OK_PTR(skel, "obj_token_path_open")) + return -EINVAL; + + err = dummy_st_ops_success__load(skel); + dummy_st_ops_success__destroy(skel); + if (expect_success) { + if (!ASSERT_OK(err, "obj_token_path_load")) + return -EINVAL; + } else /* expect failure */ { + if (!ASSERT_ERR(err, "obj_token_path_load")) + return -EINVAL; + } + + return 0; +} + +static int userns_obj_priv_btf_fail(int mnt_fd, struct token_lsm *lsm_skel) +{ + return validate_struct_ops_load(mnt_fd, false /* should fail */); +} + +static int userns_obj_priv_btf_success(int mnt_fd, struct token_lsm *lsm_skel) +{ + return validate_struct_ops_load(mnt_fd, true /* should succeed */); +} + +#define TOKEN_ENVVAR "LIBBPF_BPF_TOKEN_PATH" +#define TOKEN_BPFFS_CUSTOM "/bpf-token-fs" + +static int userns_obj_priv_implicit_token(int mnt_fd, struct token_lsm *lsm_skel) +{ + LIBBPF_OPTS(bpf_object_open_opts, opts); + struct dummy_st_ops_success *skel; + int err; + + /* before we mount BPF FS with token delegation, struct_ops skeleton + * should fail to load + */ + skel = dummy_st_ops_success__open_and_load(); + if (!ASSERT_ERR_PTR(skel, "obj_tokenless_load")) { + dummy_st_ops_success__destroy(skel); + return -EINVAL; + } + + /* mount custom BPF FS over /sys/fs/bpf so that libbpf can create BPF + * token automatically and implicitly + */ + err = sys_move_mount(mnt_fd, "", AT_FDCWD, "/sys/fs/bpf", MOVE_MOUNT_F_EMPTY_PATH); + if (!ASSERT_OK(err, "move_mount_bpffs")) + return -EINVAL; + + /* disable implicit BPF token creation by setting + * LIBBPF_BPF_TOKEN_PATH envvar to empty value, load should fail + */ + err = setenv(TOKEN_ENVVAR, "", 1 /*overwrite*/); + if (!ASSERT_OK(err, "setenv_token_path")) + return -EINVAL; + skel = dummy_st_ops_success__open_and_load(); + if (!ASSERT_ERR_PTR(skel, "obj_token_envvar_disabled_load")) { + unsetenv(TOKEN_ENVVAR); + dummy_st_ops_success__destroy(skel); + return -EINVAL; + } + unsetenv(TOKEN_ENVVAR); + + /* now the same struct_ops skeleton should succeed thanks to libppf + * creating BPF token from /sys/fs/bpf mount point + */ + skel = dummy_st_ops_success__open_and_load(); + if (!ASSERT_OK_PTR(skel, "obj_implicit_token_load")) + return -EINVAL; + + dummy_st_ops_success__destroy(skel); + + /* now disable implicit token through empty bpf_token_path, should fail */ + opts.bpf_token_path = ""; + skel = dummy_st_ops_success__open_opts(&opts); + if (!ASSERT_OK_PTR(skel, "obj_empty_token_path_open")) + return -EINVAL; + + err = dummy_st_ops_success__load(skel); + dummy_st_ops_success__destroy(skel); + if (!ASSERT_ERR(err, "obj_empty_token_path_load")) + return -EINVAL; + + return 0; +} + +static int userns_obj_priv_implicit_token_envvar(int mnt_fd, struct token_lsm *lsm_skel) +{ + LIBBPF_OPTS(bpf_object_open_opts, opts); + struct dummy_st_ops_success *skel; + int err; + + /* before we mount BPF FS with token delegation, struct_ops skeleton + * should fail to load + */ + skel = dummy_st_ops_success__open_and_load(); + if (!ASSERT_ERR_PTR(skel, "obj_tokenless_load")) { + dummy_st_ops_success__destroy(skel); + return -EINVAL; + } + + /* mount custom BPF FS over custom location, so libbpf can't create + * BPF token implicitly, unless pointed to it through + * LIBBPF_BPF_TOKEN_PATH envvar + */ + rmdir(TOKEN_BPFFS_CUSTOM); + if (!ASSERT_OK(mkdir(TOKEN_BPFFS_CUSTOM, 0777), "mkdir_bpffs_custom")) + goto err_out; + err = sys_move_mount(mnt_fd, "", AT_FDCWD, TOKEN_BPFFS_CUSTOM, MOVE_MOUNT_F_EMPTY_PATH); + if (!ASSERT_OK(err, "move_mount_bpffs")) + goto err_out; + + /* even though we have BPF FS with delegation, it's not at default + * /sys/fs/bpf location, so we still fail to load until envvar is set up + */ + skel = dummy_st_ops_success__open_and_load(); + if (!ASSERT_ERR_PTR(skel, "obj_tokenless_load2")) { + dummy_st_ops_success__destroy(skel); + goto err_out; + } + + err = setenv(TOKEN_ENVVAR, TOKEN_BPFFS_CUSTOM, 1 /*overwrite*/); + if (!ASSERT_OK(err, "setenv_token_path")) + goto err_out; + + /* now the same struct_ops skeleton should succeed thanks to libppf + * creating BPF token from custom mount point + */ + skel = dummy_st_ops_success__open_and_load(); + if (!ASSERT_OK_PTR(skel, "obj_implicit_token_load")) + goto err_out; + + dummy_st_ops_success__destroy(skel); + + /* now disable implicit token through empty bpf_token_path, envvar + * will be ignored, should fail + */ + opts.bpf_token_path = ""; + skel = dummy_st_ops_success__open_opts(&opts); + if (!ASSERT_OK_PTR(skel, "obj_empty_token_path_open")) + goto err_out; + + err = dummy_st_ops_success__load(skel); + dummy_st_ops_success__destroy(skel); + if (!ASSERT_ERR(err, "obj_empty_token_path_load")) + goto err_out; + + rmdir(TOKEN_BPFFS_CUSTOM); + unsetenv(TOKEN_ENVVAR); + return 0; +err_out: + rmdir(TOKEN_BPFFS_CUSTOM); + unsetenv(TOKEN_ENVVAR); + return -EINVAL; +} + +#define bit(n) (1ULL << (n)) + +void test_token(void) +{ + if (test__start_subtest("map_token")) { + struct bpffs_opts opts = { + .cmds_str = "map_create", + .maps_str = "stack", + }; + + subtest_userns(&opts, userns_map_create); + } + if (test__start_subtest("btf_token")) { + struct bpffs_opts opts = { + .cmds = 1ULL << BPF_BTF_LOAD, + }; + + subtest_userns(&opts, userns_btf_load); + } + if (test__start_subtest("prog_token")) { + struct bpffs_opts opts = { + .cmds_str = "PROG_LOAD", + .progs_str = "XDP", + .attachs_str = "xdp", + }; + + subtest_userns(&opts, userns_prog_load); + } + if (test__start_subtest("obj_priv_map")) { + struct bpffs_opts opts = { + .cmds = bit(BPF_MAP_CREATE), + .maps = bit(BPF_MAP_TYPE_QUEUE), + }; + + subtest_userns(&opts, userns_obj_priv_map); + } + if (test__start_subtest("obj_priv_prog")) { + struct bpffs_opts opts = { + .cmds = bit(BPF_PROG_LOAD), + .progs = bit(BPF_PROG_TYPE_KPROBE), + .attachs = ~0ULL, + }; + + subtest_userns(&opts, userns_obj_priv_prog); + } + if (test__start_subtest("obj_priv_btf_fail")) { + struct bpffs_opts opts = { + /* disallow BTF loading */ + .cmds = bit(BPF_MAP_CREATE) | bit(BPF_PROG_LOAD), + .maps = bit(BPF_MAP_TYPE_STRUCT_OPS), + .progs = bit(BPF_PROG_TYPE_STRUCT_OPS), + .attachs = ~0ULL, + }; + + subtest_userns(&opts, userns_obj_priv_btf_fail); + } + if (test__start_subtest("obj_priv_btf_success")) { + struct bpffs_opts opts = { + /* allow BTF loading */ + .cmds = bit(BPF_BTF_LOAD) | bit(BPF_MAP_CREATE) | bit(BPF_PROG_LOAD), + .maps = bit(BPF_MAP_TYPE_STRUCT_OPS), + .progs = bit(BPF_PROG_TYPE_STRUCT_OPS), + .attachs = ~0ULL, + }; + + subtest_userns(&opts, userns_obj_priv_btf_success); + } + if (test__start_subtest("obj_priv_implicit_token")) { + struct bpffs_opts opts = { + /* allow BTF loading */ + .cmds = bit(BPF_BTF_LOAD) | bit(BPF_MAP_CREATE) | bit(BPF_PROG_LOAD), + .maps = bit(BPF_MAP_TYPE_STRUCT_OPS), + .progs = bit(BPF_PROG_TYPE_STRUCT_OPS), + .attachs = ~0ULL, + }; + + subtest_userns(&opts, userns_obj_priv_implicit_token); + } + if (test__start_subtest("obj_priv_implicit_token_envvar")) { + struct bpffs_opts opts = { + /* allow BTF loading */ + .cmds = bit(BPF_BTF_LOAD) | bit(BPF_MAP_CREATE) | bit(BPF_PROG_LOAD), + .maps = bit(BPF_MAP_TYPE_STRUCT_OPS), + .progs = bit(BPF_PROG_TYPE_STRUCT_OPS), + .attachs = ~0ULL, + }; + + subtest_userns(&opts, userns_obj_priv_implicit_token_envvar); + } +} diff --git a/tools/testing/selftests/bpf/prog_tests/xdpwall.c b/tools/testing/selftests/bpf/prog_tests/xdpwall.c index f3927829a55a..4599154c8e9b 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdpwall.c +++ b/tools/testing/selftests/bpf/prog_tests/xdpwall.c @@ -9,7 +9,7 @@ void test_xdpwall(void) struct xdpwall *skel; skel = xdpwall__open_and_load(); - ASSERT_OK_PTR(skel, "Does LLMV have https://reviews.llvm.org/D109073?"); + ASSERT_OK_PTR(skel, "Does LLVM have https://github.com/llvm/llvm-project/commit/ea72b0319d7b0f0c2fcf41d121afa5d031b319d5?"); xdpwall__destroy(skel); } diff --git a/tools/testing/selftests/bpf/progs/bpf_misc.h b/tools/testing/selftests/bpf/progs/bpf_misc.h index 2fd59970c43a..fb2f5513e29e 100644 --- a/tools/testing/selftests/bpf/progs/bpf_misc.h +++ b/tools/testing/selftests/bpf/progs/bpf_misc.h @@ -80,7 +80,7 @@ #define __imm(name) [name]"i"(name) #define __imm_const(name, expr) [name]"i"(expr) #define __imm_addr(name) [name]"i"(&name) -#define __imm_ptr(name) [name]"p"(&name) +#define __imm_ptr(name) [name]"r"(&name) #define __imm_insn(name, expr) [name]"i"(*(long *)&(expr)) /* Magic constants used with __retval() */ diff --git a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h index e8bd4b7b5ef7..7001965d1cc3 100644 --- a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h +++ b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h @@ -51,9 +51,25 @@ #define ICSK_TIME_LOSS_PROBE 5 #define ICSK_TIME_REO_TIMEOUT 6 +#define ETH_ALEN 6 #define ETH_HLEN 14 +#define ETH_P_IP 0x0800 #define ETH_P_IPV6 0x86DD +#define NEXTHDR_TCP 6 + +#define TCPOPT_NOP 1 +#define TCPOPT_EOL 0 +#define TCPOPT_MSS 2 +#define TCPOPT_WINDOW 3 +#define TCPOPT_TIMESTAMP 8 +#define TCPOPT_SACK_PERM 4 + +#define TCPOLEN_MSS 4 +#define TCPOLEN_WINDOW 3 +#define TCPOLEN_TIMESTAMP 10 +#define TCPOLEN_SACK_PERM 2 + #define CHECKSUM_NONE 0 #define CHECKSUM_PARTIAL 3 diff --git a/tools/testing/selftests/bpf/progs/iters.c b/tools/testing/selftests/bpf/progs/iters.c index fe971992e635..225f02dd66d0 100644 --- a/tools/testing/selftests/bpf/progs/iters.c +++ b/tools/testing/selftests/bpf/progs/iters.c @@ -78,8 +78,8 @@ int iter_err_unsafe_asm_loop(const void *ctx) "*(u32 *)(r1 + 0) = r6;" /* invalid */ : : [it]"r"(&it), - [small_arr]"p"(small_arr), - [zero]"p"(zero), + [small_arr]"r"(small_arr), + [zero]"r"(zero), __imm(bpf_iter_num_new), __imm(bpf_iter_num_next), __imm(bpf_iter_num_destroy) diff --git a/tools/testing/selftests/bpf/progs/kptr_xchg_inline.c b/tools/testing/selftests/bpf/progs/kptr_xchg_inline.c new file mode 100644 index 000000000000..2414ac20b6d5 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/kptr_xchg_inline.c @@ -0,0 +1,48 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023. Huawei Technologies Co., Ltd */ +#include <linux/types.h> +#include <bpf/bpf_helpers.h> + +#include "bpf_experimental.h" +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +struct bin_data { + char blob[32]; +}; + +#define private(name) SEC(".bss." #name) __hidden __attribute__((aligned(8))) +private(kptr) struct bin_data __kptr * ptr; + +SEC("tc") +__naked int kptr_xchg_inline(void) +{ + asm volatile ( + "r1 = %[ptr] ll;" + "r2 = 0;" + "call %[bpf_kptr_xchg];" + "if r0 == 0 goto 1f;" + "r1 = r0;" + "r2 = 0;" + "call %[bpf_obj_drop_impl];" + "1:" + "r0 = 0;" + "exit;" + : + : __imm_addr(ptr), + __imm(bpf_kptr_xchg), + __imm(bpf_obj_drop_impl) + : __clobber_all + ); +} + +/* BTF FUNC records are not generated for kfuncs referenced + * from inline assembly. These records are necessary for + * libbpf to link the program. The function below is a hack + * to ensure that BTF FUNC records are generated. + */ +void __btf_root(void) +{ + bpf_obj_drop(NULL); +} diff --git a/tools/testing/selftests/bpf/progs/priv_map.c b/tools/testing/selftests/bpf/progs/priv_map.c new file mode 100644 index 000000000000..9085be50f03b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/priv_map.c @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_QUEUE); + __uint(max_entries, 1); + __type(value, __u32); +} priv_map SEC(".maps"); diff --git a/tools/testing/selftests/bpf/progs/priv_prog.c b/tools/testing/selftests/bpf/progs/priv_prog.c new file mode 100644 index 000000000000..3c7b2b618c8a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/priv_prog.c @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +SEC("kprobe") +int kprobe_prog(void *ctx) +{ + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/struct_ops_module.c b/tools/testing/selftests/bpf/progs/struct_ops_module.c new file mode 100644 index 000000000000..e44ac55195ca --- /dev/null +++ b/tools/testing/selftests/bpf/progs/struct_ops_module.c @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "../bpf_testmod/bpf_testmod.h" + +char _license[] SEC("license") = "GPL"; + +int test_2_result = 0; + +SEC("struct_ops/test_1") +int BPF_PROG(test_1) +{ + return 0xdeadbeef; +} + +SEC("struct_ops/test_2") +int BPF_PROG(test_2, int a, int b) +{ + test_2_result = a + b; + return a + b; +} + +SEC(".struct_ops.link") +struct bpf_testmod_ops testmod_1 = { + .test_1 = (void *)test_1, + .test_2 = (void *)test_2, +}; + diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_type_id.c b/tools/testing/selftests/bpf/progs/test_core_reloc_type_id.c index 22aba3f6e344..6fc8b9d66e34 100644 --- a/tools/testing/selftests/bpf/progs/test_core_reloc_type_id.c +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_type_id.c @@ -80,7 +80,7 @@ int test_core_type_id(void *ctx) * to detect whether this test has to be executed, however strange * that might look like. * - * [0] https://reviews.llvm.org/D85174 + * [0] https://github.com/llvm/llvm-project/commit/00602ee7ef0bf6c68d690a2bd729c12b95c95c99 */ #if __has_builtin(__builtin_preserve_type_info) struct core_reloc_type_id_output *out = (void *)&data.out; diff --git a/tools/testing/selftests/bpf/progs/test_fill_link_info.c b/tools/testing/selftests/bpf/progs/test_fill_link_info.c index 69509f8bb680..6afa834756e9 100644 --- a/tools/testing/selftests/bpf/progs/test_fill_link_info.c +++ b/tools/testing/selftests/bpf/progs/test_fill_link_info.c @@ -33,6 +33,12 @@ int BPF_PROG(tp_run) return 0; } +SEC("perf_event") +int event_run(void *ctx) +{ + return 0; +} + SEC("kprobe.multi") int BPF_PROG(kmulti_run) { diff --git a/tools/testing/selftests/bpf/progs/test_map_in_map.c b/tools/testing/selftests/bpf/progs/test_map_in_map.c index f416032ba858..b295f9b721bf 100644 --- a/tools/testing/selftests/bpf/progs/test_map_in_map.c +++ b/tools/testing/selftests/bpf/progs/test_map_in_map.c @@ -21,6 +21,32 @@ struct { __type(value, __u32); } mim_hash SEC(".maps"); +/* The following three maps are used to test + * perf_event_array map can be an inner + * map of hash/array_of_maps. + */ +struct perf_event_array { + __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); + __type(key, __u32); + __type(value, __u32); +} inner_map0 SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); + __uint(max_entries, 1); + __type(key, __u32); + __array(values, struct perf_event_array); +} mim_array_pe SEC(".maps") = { + .values = {&inner_map0}}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH_OF_MAPS); + __uint(max_entries, 1); + __type(key, __u32); + __array(values, struct perf_event_array); +} mim_hash_pe SEC(".maps") = { + .values = {&inner_map0}}; + SEC("xdp") int xdp_mimtest0(struct xdp_md *ctx) { diff --git a/tools/testing/selftests/bpf/progs/test_siphash.h b/tools/testing/selftests/bpf/progs/test_siphash.h new file mode 100644 index 000000000000..5d3a7ec36780 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_siphash.h @@ -0,0 +1,64 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright Amazon.com Inc. or its affiliates. */ + +#ifndef _TEST_SIPHASH_H +#define _TEST_SIPHASH_H + +/* include/linux/bitops.h */ +static inline u64 rol64(u64 word, unsigned int shift) +{ + return (word << (shift & 63)) | (word >> ((-shift) & 63)); +} + +/* include/linux/siphash.h */ +#define SIPHASH_PERMUTATION(a, b, c, d) ( \ + (a) += (b), (b) = rol64((b), 13), (b) ^= (a), (a) = rol64((a), 32), \ + (c) += (d), (d) = rol64((d), 16), (d) ^= (c), \ + (a) += (d), (d) = rol64((d), 21), (d) ^= (a), \ + (c) += (b), (b) = rol64((b), 17), (b) ^= (c), (c) = rol64((c), 32)) + +#define SIPHASH_CONST_0 0x736f6d6570736575ULL +#define SIPHASH_CONST_1 0x646f72616e646f6dULL +#define SIPHASH_CONST_2 0x6c7967656e657261ULL +#define SIPHASH_CONST_3 0x7465646279746573ULL + +/* lib/siphash.c */ +#define SIPROUND SIPHASH_PERMUTATION(v0, v1, v2, v3) + +#define PREAMBLE(len) \ + u64 v0 = SIPHASH_CONST_0; \ + u64 v1 = SIPHASH_CONST_1; \ + u64 v2 = SIPHASH_CONST_2; \ + u64 v3 = SIPHASH_CONST_3; \ + u64 b = ((u64)(len)) << 56; \ + v3 ^= key->key[1]; \ + v2 ^= key->key[0]; \ + v1 ^= key->key[1]; \ + v0 ^= key->key[0]; + +#define POSTAMBLE \ + v3 ^= b; \ + SIPROUND; \ + SIPROUND; \ + v0 ^= b; \ + v2 ^= 0xff; \ + SIPROUND; \ + SIPROUND; \ + SIPROUND; \ + SIPROUND; \ + return (v0 ^ v1) ^ (v2 ^ v3); + +static inline u64 siphash_2u64(const u64 first, const u64 second, const siphash_key_t *key) +{ + PREAMBLE(16) + v3 ^= first; + SIPROUND; + SIPROUND; + v0 ^= first; + v3 ^= second; + SIPROUND; + SIPROUND; + v0 ^= second; + POSTAMBLE +} +#endif diff --git a/tools/testing/selftests/bpf/progs/test_tcp_custom_syncookie.c b/tools/testing/selftests/bpf/progs/test_tcp_custom_syncookie.c new file mode 100644 index 000000000000..a5501b29979a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_tcp_custom_syncookie.c @@ -0,0 +1,572 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright Amazon.com Inc. or its affiliates. */ + +#include "vmlinux.h" + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> +#include "bpf_tracing_net.h" +#include "bpf_kfuncs.h" +#include "test_siphash.h" +#include "test_tcp_custom_syncookie.h" + +/* Hash is calculated for each client and split into ISN and TS. + * + * MSB LSB + * ISN: | 31 ... 8 | 7 6 | 5 | 4 | 3 2 1 0 | + * | Hash_1 | MSS | ECN | SACK | WScale | + * + * TS: | 31 ... 8 | 7 ... 0 | + * | Random | Hash_2 | + */ +#define COOKIE_BITS 8 +#define COOKIE_MASK (((__u32)1 << COOKIE_BITS) - 1) + +enum { + /* 0xf is invalid thus means that SYN did not have WScale. */ + BPF_SYNCOOKIE_WSCALE_MASK = (1 << 4) - 1, + BPF_SYNCOOKIE_SACK = (1 << 4), + BPF_SYNCOOKIE_ECN = (1 << 5), +}; + +#define MSS_LOCAL_IPV4 65495 +#define MSS_LOCAL_IPV6 65476 + +const __u16 msstab4[] = { + 536, + 1300, + 1460, + MSS_LOCAL_IPV4, +}; + +const __u16 msstab6[] = { + 1280 - 60, /* IPV6_MIN_MTU - 60 */ + 1480 - 60, + 9000 - 60, + MSS_LOCAL_IPV6, +}; + +static siphash_key_t test_key_siphash = { + { 0x0706050403020100ULL, 0x0f0e0d0c0b0a0908ULL } +}; + +struct tcp_syncookie { + struct __sk_buff *skb; + void *data_end; + struct ethhdr *eth; + struct iphdr *ipv4; + struct ipv6hdr *ipv6; + struct tcphdr *tcp; + union { + char *ptr; + __be32 *ptr32; + }; + struct bpf_tcp_req_attrs attrs; + u32 cookie; + u64 first; +}; + +bool handled_syn, handled_ack; + +static int tcp_load_headers(struct tcp_syncookie *ctx) +{ + ctx->data_end = (void *)(long)ctx->skb->data_end; + ctx->eth = (struct ethhdr *)(long)ctx->skb->data; + + if (ctx->eth + 1 > ctx->data_end) + goto err; + + switch (bpf_ntohs(ctx->eth->h_proto)) { + case ETH_P_IP: + ctx->ipv4 = (struct iphdr *)(ctx->eth + 1); + + if (ctx->ipv4 + 1 > ctx->data_end) + goto err; + + if (ctx->ipv4->ihl != sizeof(*ctx->ipv4) / 4) + goto err; + + if (ctx->ipv4->version != 4) + goto err; + + if (ctx->ipv4->protocol != IPPROTO_TCP) + goto err; + + ctx->tcp = (struct tcphdr *)(ctx->ipv4 + 1); + break; + case ETH_P_IPV6: + ctx->ipv6 = (struct ipv6hdr *)(ctx->eth + 1); + + if (ctx->ipv6 + 1 > ctx->data_end) + goto err; + + if (ctx->ipv6->version != 6) + goto err; + + if (ctx->ipv6->nexthdr != NEXTHDR_TCP) + goto err; + + ctx->tcp = (struct tcphdr *)(ctx->ipv6 + 1); + break; + default: + goto err; + } + + if (ctx->tcp + 1 > ctx->data_end) + goto err; + + return 0; +err: + return -1; +} + +static int tcp_reload_headers(struct tcp_syncookie *ctx) +{ + /* Without volatile, + * R3 32-bit pointer arithmetic prohibited + */ + volatile u64 data_len = ctx->skb->data_end - ctx->skb->data; + + if (ctx->tcp->doff < sizeof(*ctx->tcp) / 4) + goto err; + + /* Needed to calculate csum and parse TCP options. */ + if (bpf_skb_change_tail(ctx->skb, data_len + 60 - ctx->tcp->doff * 4, 0)) + goto err; + + ctx->data_end = (void *)(long)ctx->skb->data_end; + ctx->eth = (struct ethhdr *)(long)ctx->skb->data; + if (ctx->ipv4) { + ctx->ipv4 = (struct iphdr *)(ctx->eth + 1); + ctx->ipv6 = NULL; + ctx->tcp = (struct tcphdr *)(ctx->ipv4 + 1); + } else { + ctx->ipv4 = NULL; + ctx->ipv6 = (struct ipv6hdr *)(ctx->eth + 1); + ctx->tcp = (struct tcphdr *)(ctx->ipv6 + 1); + } + + if ((void *)ctx->tcp + 60 > ctx->data_end) + goto err; + + return 0; +err: + return -1; +} + +static __sum16 tcp_v4_csum(struct tcp_syncookie *ctx, __wsum csum) +{ + return csum_tcpudp_magic(ctx->ipv4->saddr, ctx->ipv4->daddr, + ctx->tcp->doff * 4, IPPROTO_TCP, csum); +} + +static __sum16 tcp_v6_csum(struct tcp_syncookie *ctx, __wsum csum) +{ + return csum_ipv6_magic(&ctx->ipv6->saddr, &ctx->ipv6->daddr, + ctx->tcp->doff * 4, IPPROTO_TCP, csum); +} + +static int tcp_validate_header(struct tcp_syncookie *ctx) +{ + s64 csum; + + if (tcp_reload_headers(ctx)) + goto err; + + csum = bpf_csum_diff(0, 0, (void *)ctx->tcp, ctx->tcp->doff * 4, 0); + if (csum < 0) + goto err; + + if (ctx->ipv4) { + /* check tcp_v4_csum(csum) is 0 if not on lo. */ + + csum = bpf_csum_diff(0, 0, (void *)ctx->ipv4, ctx->ipv4->ihl * 4, 0); + if (csum < 0) + goto err; + + if (csum_fold(csum) != 0) + goto err; + } else if (ctx->ipv6) { + /* check tcp_v6_csum(csum) is 0 if not on lo. */ + } + + return 0; +err: + return -1; +} + +static int tcp_parse_option(__u32 index, struct tcp_syncookie *ctx) +{ + char opcode, opsize; + + if (ctx->ptr + 1 > ctx->data_end) + goto stop; + + opcode = *ctx->ptr++; + + if (opcode == TCPOPT_EOL) + goto stop; + + if (opcode == TCPOPT_NOP) + goto next; + + if (ctx->ptr + 1 > ctx->data_end) + goto stop; + + opsize = *ctx->ptr++; + + if (opsize < 2) + goto stop; + + switch (opcode) { + case TCPOPT_MSS: + if (opsize == TCPOLEN_MSS && ctx->tcp->syn && + ctx->ptr + (TCPOLEN_MSS - 2) < ctx->data_end) + ctx->attrs.mss = get_unaligned_be16(ctx->ptr); + break; + case TCPOPT_WINDOW: + if (opsize == TCPOLEN_WINDOW && ctx->tcp->syn && + ctx->ptr + (TCPOLEN_WINDOW - 2) < ctx->data_end) { + ctx->attrs.wscale_ok = 1; + ctx->attrs.snd_wscale = *ctx->ptr; + } + break; + case TCPOPT_TIMESTAMP: + if (opsize == TCPOLEN_TIMESTAMP && + ctx->ptr + (TCPOLEN_TIMESTAMP - 2) < ctx->data_end) { + ctx->attrs.rcv_tsval = get_unaligned_be32(ctx->ptr); + ctx->attrs.rcv_tsecr = get_unaligned_be32(ctx->ptr + 4); + + if (ctx->tcp->syn && ctx->attrs.rcv_tsecr) + ctx->attrs.tstamp_ok = 0; + else + ctx->attrs.tstamp_ok = 1; + } + break; + case TCPOPT_SACK_PERM: + if (opsize == TCPOLEN_SACK_PERM && ctx->tcp->syn && + ctx->ptr + (TCPOLEN_SACK_PERM - 2) < ctx->data_end) + ctx->attrs.sack_ok = 1; + break; + } + + ctx->ptr += opsize - 2; +next: + return 0; +stop: + return 1; +} + +static void tcp_parse_options(struct tcp_syncookie *ctx) +{ + ctx->ptr = (char *)(ctx->tcp + 1); + + bpf_loop(40, tcp_parse_option, ctx, 0); +} + +static int tcp_validate_sysctl(struct tcp_syncookie *ctx) +{ + if ((ctx->ipv4 && ctx->attrs.mss != MSS_LOCAL_IPV4) || + (ctx->ipv6 && ctx->attrs.mss != MSS_LOCAL_IPV6)) + goto err; + + if (!ctx->attrs.wscale_ok || ctx->attrs.snd_wscale != 7) + goto err; + + if (!ctx->attrs.tstamp_ok) + goto err; + + if (!ctx->attrs.sack_ok) + goto err; + + if (!ctx->tcp->ece || !ctx->tcp->cwr) + goto err; + + return 0; +err: + return -1; +} + +static void tcp_prepare_cookie(struct tcp_syncookie *ctx) +{ + u32 seq = bpf_ntohl(ctx->tcp->seq); + u64 first = 0, second; + int mssind = 0; + u32 hash; + + if (ctx->ipv4) { + for (mssind = ARRAY_SIZE(msstab4) - 1; mssind; mssind--) + if (ctx->attrs.mss >= msstab4[mssind]) + break; + + ctx->attrs.mss = msstab4[mssind]; + + first = (u64)ctx->ipv4->saddr << 32 | ctx->ipv4->daddr; + } else if (ctx->ipv6) { + for (mssind = ARRAY_SIZE(msstab6) - 1; mssind; mssind--) + if (ctx->attrs.mss >= msstab6[mssind]) + break; + + ctx->attrs.mss = msstab6[mssind]; + + first = (u64)ctx->ipv6->saddr.in6_u.u6_addr8[0] << 32 | + ctx->ipv6->daddr.in6_u.u6_addr32[0]; + } + + second = (u64)seq << 32 | ctx->tcp->source << 16 | ctx->tcp->dest; + hash = siphash_2u64(first, second, &test_key_siphash); + + if (ctx->attrs.tstamp_ok) { + ctx->attrs.rcv_tsecr = bpf_get_prandom_u32(); + ctx->attrs.rcv_tsecr &= ~COOKIE_MASK; + ctx->attrs.rcv_tsecr |= hash & COOKIE_MASK; + } + + hash &= ~COOKIE_MASK; + hash |= mssind << 6; + + if (ctx->attrs.wscale_ok) + hash |= ctx->attrs.snd_wscale & BPF_SYNCOOKIE_WSCALE_MASK; + + if (ctx->attrs.sack_ok) + hash |= BPF_SYNCOOKIE_SACK; + + if (ctx->attrs.tstamp_ok && ctx->tcp->ece && ctx->tcp->cwr) + hash |= BPF_SYNCOOKIE_ECN; + + ctx->cookie = hash; +} + +static void tcp_write_options(struct tcp_syncookie *ctx) +{ + ctx->ptr32 = (__be32 *)(ctx->tcp + 1); + + *ctx->ptr32++ = bpf_htonl(TCPOPT_MSS << 24 | TCPOLEN_MSS << 16 | + ctx->attrs.mss); + + if (ctx->attrs.wscale_ok) + *ctx->ptr32++ = bpf_htonl(TCPOPT_NOP << 24 | + TCPOPT_WINDOW << 16 | + TCPOLEN_WINDOW << 8 | + ctx->attrs.snd_wscale); + + if (ctx->attrs.tstamp_ok) { + if (ctx->attrs.sack_ok) + *ctx->ptr32++ = bpf_htonl(TCPOPT_SACK_PERM << 24 | + TCPOLEN_SACK_PERM << 16 | + TCPOPT_TIMESTAMP << 8 | + TCPOLEN_TIMESTAMP); + else + *ctx->ptr32++ = bpf_htonl(TCPOPT_NOP << 24 | + TCPOPT_NOP << 16 | + TCPOPT_TIMESTAMP << 8 | + TCPOLEN_TIMESTAMP); + + *ctx->ptr32++ = bpf_htonl(ctx->attrs.rcv_tsecr); + *ctx->ptr32++ = bpf_htonl(ctx->attrs.rcv_tsval); + } else if (ctx->attrs.sack_ok) { + *ctx->ptr32++ = bpf_htonl(TCPOPT_NOP << 24 | + TCPOPT_NOP << 16 | + TCPOPT_SACK_PERM << 8 | + TCPOLEN_SACK_PERM); + } +} + +static int tcp_handle_syn(struct tcp_syncookie *ctx) +{ + s64 csum; + + if (tcp_validate_header(ctx)) + goto err; + + tcp_parse_options(ctx); + + if (tcp_validate_sysctl(ctx)) + goto err; + + tcp_prepare_cookie(ctx); + tcp_write_options(ctx); + + swap(ctx->tcp->source, ctx->tcp->dest); + ctx->tcp->check = 0; + ctx->tcp->ack_seq = bpf_htonl(bpf_ntohl(ctx->tcp->seq) + 1); + ctx->tcp->seq = bpf_htonl(ctx->cookie); + ctx->tcp->doff = ((long)ctx->ptr32 - (long)ctx->tcp) >> 2; + ctx->tcp->ack = 1; + if (!ctx->attrs.tstamp_ok || !ctx->tcp->ece || !ctx->tcp->cwr) + ctx->tcp->ece = 0; + ctx->tcp->cwr = 0; + + csum = bpf_csum_diff(0, 0, (void *)ctx->tcp, ctx->tcp->doff * 4, 0); + if (csum < 0) + goto err; + + if (ctx->ipv4) { + swap(ctx->ipv4->saddr, ctx->ipv4->daddr); + ctx->tcp->check = tcp_v4_csum(ctx, csum); + + ctx->ipv4->check = 0; + ctx->ipv4->tos = 0; + ctx->ipv4->tot_len = bpf_htons((long)ctx->ptr32 - (long)ctx->ipv4); + ctx->ipv4->id = 0; + ctx->ipv4->ttl = 64; + + csum = bpf_csum_diff(0, 0, (void *)ctx->ipv4, sizeof(*ctx->ipv4), 0); + if (csum < 0) + goto err; + + ctx->ipv4->check = csum_fold(csum); + } else if (ctx->ipv6) { + swap(ctx->ipv6->saddr, ctx->ipv6->daddr); + ctx->tcp->check = tcp_v6_csum(ctx, csum); + + *(__be32 *)ctx->ipv6 = bpf_htonl(0x60000000); + ctx->ipv6->payload_len = bpf_htons((long)ctx->ptr32 - (long)ctx->tcp); + ctx->ipv6->hop_limit = 64; + } + + swap_array(ctx->eth->h_source, ctx->eth->h_dest); + + if (bpf_skb_change_tail(ctx->skb, (long)ctx->ptr32 - (long)ctx->eth, 0)) + goto err; + + return bpf_redirect(ctx->skb->ifindex, 0); +err: + return TC_ACT_SHOT; +} + +static int tcp_validate_cookie(struct tcp_syncookie *ctx) +{ + u32 cookie = bpf_ntohl(ctx->tcp->ack_seq) - 1; + u32 seq = bpf_ntohl(ctx->tcp->seq) - 1; + u64 first = 0, second; + int mssind; + u32 hash; + + if (ctx->ipv4) + first = (u64)ctx->ipv4->saddr << 32 | ctx->ipv4->daddr; + else if (ctx->ipv6) + first = (u64)ctx->ipv6->saddr.in6_u.u6_addr8[0] << 32 | + ctx->ipv6->daddr.in6_u.u6_addr32[0]; + + second = (u64)seq << 32 | ctx->tcp->source << 16 | ctx->tcp->dest; + hash = siphash_2u64(first, second, &test_key_siphash); + + if (ctx->attrs.tstamp_ok) + hash -= ctx->attrs.rcv_tsecr & COOKIE_MASK; + else + hash &= ~COOKIE_MASK; + + hash -= cookie & ~COOKIE_MASK; + if (hash) + goto err; + + mssind = (cookie & (3 << 6)) >> 6; + if (ctx->ipv4) { + if (mssind > ARRAY_SIZE(msstab4)) + goto err; + + ctx->attrs.mss = msstab4[mssind]; + } else { + if (mssind > ARRAY_SIZE(msstab6)) + goto err; + + ctx->attrs.mss = msstab6[mssind]; + } + + ctx->attrs.snd_wscale = cookie & BPF_SYNCOOKIE_WSCALE_MASK; + ctx->attrs.rcv_wscale = ctx->attrs.snd_wscale; + ctx->attrs.wscale_ok = ctx->attrs.snd_wscale == BPF_SYNCOOKIE_WSCALE_MASK; + ctx->attrs.sack_ok = cookie & BPF_SYNCOOKIE_SACK; + ctx->attrs.ecn_ok = cookie & BPF_SYNCOOKIE_ECN; + + return 0; +err: + return -1; +} + +static int tcp_handle_ack(struct tcp_syncookie *ctx) +{ + struct bpf_sock_tuple tuple; + struct bpf_sock *skc; + int ret = TC_ACT_OK; + struct sock *sk; + u32 tuple_size; + + if (ctx->ipv4) { + tuple.ipv4.saddr = ctx->ipv4->saddr; + tuple.ipv4.daddr = ctx->ipv4->daddr; + tuple.ipv4.sport = ctx->tcp->source; + tuple.ipv4.dport = ctx->tcp->dest; + tuple_size = sizeof(tuple.ipv4); + } else if (ctx->ipv6) { + __builtin_memcpy(tuple.ipv6.saddr, &ctx->ipv6->saddr, sizeof(tuple.ipv6.saddr)); + __builtin_memcpy(tuple.ipv6.daddr, &ctx->ipv6->daddr, sizeof(tuple.ipv6.daddr)); + tuple.ipv6.sport = ctx->tcp->source; + tuple.ipv6.dport = ctx->tcp->dest; + tuple_size = sizeof(tuple.ipv6); + } else { + goto out; + } + + skc = bpf_skc_lookup_tcp(ctx->skb, &tuple, tuple_size, -1, 0); + if (!skc) + goto out; + + if (skc->state != TCP_LISTEN) + goto release; + + sk = (struct sock *)bpf_skc_to_tcp_sock(skc); + if (!sk) + goto err; + + if (tcp_validate_header(ctx)) + goto err; + + tcp_parse_options(ctx); + + if (tcp_validate_cookie(ctx)) + goto err; + + ret = bpf_sk_assign_tcp_reqsk(ctx->skb, sk, &ctx->attrs, sizeof(ctx->attrs)); + if (ret < 0) + goto err; + +release: + bpf_sk_release(skc); +out: + return ret; + +err: + ret = TC_ACT_SHOT; + goto release; +} + +SEC("tc") +int tcp_custom_syncookie(struct __sk_buff *skb) +{ + struct tcp_syncookie ctx = { + .skb = skb, + }; + + if (tcp_load_headers(&ctx)) + return TC_ACT_OK; + + if (ctx.tcp->rst) + return TC_ACT_OK; + + if (ctx.tcp->syn) { + if (ctx.tcp->ack) + return TC_ACT_OK; + + handled_syn = true; + + return tcp_handle_syn(&ctx); + } + + handled_ack = true; + + return tcp_handle_ack(&ctx); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tcp_custom_syncookie.h b/tools/testing/selftests/bpf/progs/test_tcp_custom_syncookie.h new file mode 100644 index 000000000000..29a6a53cf229 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_tcp_custom_syncookie.h @@ -0,0 +1,140 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright Amazon.com Inc. or its affiliates. */ + +#ifndef _TEST_TCP_SYNCOOKIE_H +#define _TEST_TCP_SYNCOOKIE_H + +#define __packed __attribute__((__packed__)) +#define __force + +#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0])) + +#define swap(a, b) \ + do { \ + typeof(a) __tmp = (a); \ + (a) = (b); \ + (b) = __tmp; \ + } while (0) + +#define swap_array(a, b) \ + do { \ + typeof(a) __tmp[sizeof(a)]; \ + __builtin_memcpy(__tmp, a, sizeof(a)); \ + __builtin_memcpy(a, b, sizeof(a)); \ + __builtin_memcpy(b, __tmp, sizeof(a)); \ + } while (0) + +/* asm-generic/unaligned.h */ +#define __get_unaligned_t(type, ptr) ({ \ + const struct { type x; } __packed * __pptr = (typeof(__pptr))(ptr); \ + __pptr->x; \ +}) + +#define get_unaligned(ptr) __get_unaligned_t(typeof(*(ptr)), (ptr)) + +static inline u16 get_unaligned_be16(const void *p) +{ + return bpf_ntohs(__get_unaligned_t(__be16, p)); +} + +static inline u32 get_unaligned_be32(const void *p) +{ + return bpf_ntohl(__get_unaligned_t(__be32, p)); +} + +/* lib/checksum.c */ +static inline u32 from64to32(u64 x) +{ + /* add up 32-bit and 32-bit for 32+c bit */ + x = (x & 0xffffffff) + (x >> 32); + /* add up carry.. */ + x = (x & 0xffffffff) + (x >> 32); + return (u32)x; +} + +static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr, + __u32 len, __u8 proto, __wsum sum) +{ + unsigned long long s = (__force u32)sum; + + s += (__force u32)saddr; + s += (__force u32)daddr; +#ifdef __BIG_ENDIAN + s += proto + len; +#else + s += (proto + len) << 8; +#endif + return (__force __wsum)from64to32(s); +} + +/* asm-generic/checksum.h */ +static inline __sum16 csum_fold(__wsum csum) +{ + u32 sum = (__force u32)csum; + + sum = (sum & 0xffff) + (sum >> 16); + sum = (sum & 0xffff) + (sum >> 16); + return (__force __sum16)~sum; +} + +static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr, __u32 len, + __u8 proto, __wsum sum) +{ + return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum)); +} + +/* net/ipv6/ip6_checksum.c */ +static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr, + const struct in6_addr *daddr, + __u32 len, __u8 proto, __wsum csum) +{ + int carry; + __u32 ulen; + __u32 uproto; + __u32 sum = (__force u32)csum; + + sum += (__force u32)saddr->in6_u.u6_addr32[0]; + carry = (sum < (__force u32)saddr->in6_u.u6_addr32[0]); + sum += carry; + + sum += (__force u32)saddr->in6_u.u6_addr32[1]; + carry = (sum < (__force u32)saddr->in6_u.u6_addr32[1]); + sum += carry; + + sum += (__force u32)saddr->in6_u.u6_addr32[2]; + carry = (sum < (__force u32)saddr->in6_u.u6_addr32[2]); + sum += carry; + + sum += (__force u32)saddr->in6_u.u6_addr32[3]; + carry = (sum < (__force u32)saddr->in6_u.u6_addr32[3]); + sum += carry; + + sum += (__force u32)daddr->in6_u.u6_addr32[0]; + carry = (sum < (__force u32)daddr->in6_u.u6_addr32[0]); + sum += carry; + + sum += (__force u32)daddr->in6_u.u6_addr32[1]; + carry = (sum < (__force u32)daddr->in6_u.u6_addr32[1]); + sum += carry; + + sum += (__force u32)daddr->in6_u.u6_addr32[2]; + carry = (sum < (__force u32)daddr->in6_u.u6_addr32[2]); + sum += carry; + + sum += (__force u32)daddr->in6_u.u6_addr32[3]; + carry = (sum < (__force u32)daddr->in6_u.u6_addr32[3]); + sum += carry; + + ulen = (__force u32)bpf_htonl((__u32)len); + sum += ulen; + carry = (sum < ulen); + sum += carry; + + uproto = (__force u32)bpf_htonl(proto); + sum += uproto; + carry = (sum < uproto); + sum += carry; + + return csum_fold((__force __wsum)sum); +} +#endif diff --git a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c index cf7ed8cbb1fe..a3f3f43fc195 100644 --- a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c @@ -59,7 +59,7 @@ int bpf_testcb(struct bpf_sock_ops *skops) asm volatile ( "%[op] = *(u32 *)(%[skops] +96)" - : [op] "+r"(op) + : [op] "=r"(op) : [skops] "r"(skops) :); diff --git a/tools/testing/selftests/bpf/progs/test_xdp_dynptr.c b/tools/testing/selftests/bpf/progs/test_xdp_dynptr.c index 78c368e71797..67a77944ef29 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_dynptr.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_dynptr.c @@ -18,11 +18,11 @@ #include "test_iptunnel_common.h" #include "bpf_kfuncs.h" -const size_t tcphdr_sz = sizeof(struct tcphdr); -const size_t udphdr_sz = sizeof(struct udphdr); -const size_t ethhdr_sz = sizeof(struct ethhdr); -const size_t iphdr_sz = sizeof(struct iphdr); -const size_t ipv6hdr_sz = sizeof(struct ipv6hdr); +#define tcphdr_sz sizeof(struct tcphdr) +#define udphdr_sz sizeof(struct udphdr) +#define ethhdr_sz sizeof(struct ethhdr) +#define iphdr_sz sizeof(struct iphdr) +#define ipv6hdr_sz sizeof(struct ipv6hdr) struct { __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); diff --git a/tools/testing/selftests/bpf/progs/token_lsm.c b/tools/testing/selftests/bpf/progs/token_lsm.c new file mode 100644 index 000000000000..e4d59b6ba743 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/token_lsm.c @@ -0,0 +1,32 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +int my_pid; +bool reject_capable; +bool reject_cmd; + +SEC("lsm/bpf_token_capable") +int BPF_PROG(token_capable, struct bpf_token *token, int cap) +{ + if (my_pid == 0 || my_pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + if (reject_capable) + return -1; + return 0; +} + +SEC("lsm/bpf_token_cmd") +int BPF_PROG(token_cmd, struct bpf_token *token, enum bpf_cmd cmd) +{ + if (my_pid == 0 || my_pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + if (reject_cmd) + return -1; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/verifier_direct_packet_access.c b/tools/testing/selftests/bpf/progs/verifier_direct_packet_access.c index be95570ab382..28b602ac9cbe 100644 --- a/tools/testing/selftests/bpf/progs/verifier_direct_packet_access.c +++ b/tools/testing/selftests/bpf/progs/verifier_direct_packet_access.c @@ -568,7 +568,7 @@ l0_%=: r0 = 0; \ SEC("tc") __description("direct packet access: test23 (x += pkt_ptr, 4)") -__failure __msg("invalid access to packet, off=0 size=8, R5(id=2,off=0,r=0)") +__failure __msg("invalid access to packet, off=0 size=8, R5(id=3,off=0,r=0)") __flag(BPF_F_ANY_ALIGNMENT) __naked void test23_x_pkt_ptr_4(void) { diff --git a/tools/testing/selftests/bpf/progs/verifier_loops1.c b/tools/testing/selftests/bpf/progs/verifier_loops1.c index 71735dbf33d4..e07b43b78fd2 100644 --- a/tools/testing/selftests/bpf/progs/verifier_loops1.c +++ b/tools/testing/selftests/bpf/progs/verifier_loops1.c @@ -259,4 +259,28 @@ l0_%=: r2 += r1; \ " ::: __clobber_all); } +SEC("xdp") +__success +__naked void not_an_inifinite_loop(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r0 &= 0xff; \ + *(u64 *)(r10 - 8) = r0; \ + r0 = 0; \ +loop_%=: \ + r0 = *(u64 *)(r10 - 8); \ + if r0 > 10 goto exit_%=; \ + r0 += 1; \ + *(u64 *)(r10 - 8) = r0; \ + r0 = 0; \ + goto loop_%=; \ +exit_%=: \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c index 39fe3372e0e0..7013a9694163 100644 --- a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c +++ b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c @@ -243,7 +243,7 @@ l0_%=: r0 = 0; \ SEC("tc") __description("Spill u32 const scalars. Refill as u64. Offset to skb->data") -__failure __msg("invalid access to packet") +__failure __msg("math between pkt pointer and register with unbounded min value is not allowed") __naked void u64_offset_to_skb_data(void) { asm volatile (" \ @@ -253,13 +253,11 @@ __naked void u64_offset_to_skb_data(void) w7 = 20; \ *(u32*)(r10 - 4) = r6; \ *(u32*)(r10 - 8) = r7; \ - r4 = *(u16*)(r10 - 8); \ + r4 = *(u64*)(r10 - 8); \ r0 = r2; \ - /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=umax=65535 */\ + /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4= */ \ r0 += r4; \ - /* if (r0 > r3) R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=umax=65535 */\ if r0 > r3 goto l0_%=; \ - /* r0 = *(u32 *)r2 R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=20 */\ r0 = *(u32*)(r2 + 0); \ l0_%=: r0 = 0; \ exit; \ @@ -495,14 +493,14 @@ char single_byte_buf[1] SEC(".data.single_byte_buf"); SEC("raw_tp") __log_level(2) __success -/* make sure fp-8 is all STACK_ZERO */ -__msg("2: (7a) *(u64 *)(r10 -8) = 0 ; R10=fp0 fp-8_w=00000000") +/* fp-8 is spilled IMPRECISE value zero (represented by a zero value fake reg) */ +__msg("2: (7a) *(u64 *)(r10 -8) = 0 ; R10=fp0 fp-8_w=0") /* but fp-16 is spilled IMPRECISE zero const reg */ __msg("4: (7b) *(u64 *)(r10 -16) = r0 ; R0_w=0 R10=fp0 fp-16_w=0") -/* validate that assigning R2 from STACK_ZERO doesn't mark register +/* validate that assigning R2 from STACK_SPILL with zero value doesn't mark register * precise immediately; if necessary, it will be marked precise later */ -__msg("6: (71) r2 = *(u8 *)(r10 -1) ; R2_w=0 R10=fp0 fp-8_w=00000000") +__msg("6: (71) r2 = *(u8 *)(r10 -1) ; R2_w=0 R10=fp0 fp-8_w=0") /* similarly, when R2 is assigned from spilled register, it is initially * imprecise, but will be marked precise later once it is used in precise context */ @@ -520,14 +518,14 @@ __msg("mark_precise: frame0: regs=r0 stack= before 3: (b7) r0 = 0") __naked void partial_stack_load_preserves_zeros(void) { asm volatile ( - /* fp-8 is all STACK_ZERO */ + /* fp-8 is value zero (represented by a zero value fake reg) */ ".8byte %[fp8_st_zero];" /* LLVM-18+: *(u64 *)(r10 -8) = 0; */ /* fp-16 is const zero register */ "r0 = 0;" "*(u64 *)(r10 -16) = r0;" - /* load single U8 from non-aligned STACK_ZERO slot */ + /* load single U8 from non-aligned spilled value zero slot */ "r1 = %[single_byte_buf];" "r2 = *(u8 *)(r10 -1);" "r1 += r2;" @@ -539,7 +537,7 @@ __naked void partial_stack_load_preserves_zeros(void) "r1 += r2;" "*(u8 *)(r1 + 0) = r2;" /* this should be fine */ - /* load single U16 from non-aligned STACK_ZERO slot */ + /* load single U16 from non-aligned spilled value zero slot */ "r1 = %[single_byte_buf];" "r2 = *(u16 *)(r10 -2);" "r1 += r2;" @@ -551,7 +549,7 @@ __naked void partial_stack_load_preserves_zeros(void) "r1 += r2;" "*(u8 *)(r1 + 0) = r2;" /* this should be fine */ - /* load single U32 from non-aligned STACK_ZERO slot */ + /* load single U32 from non-aligned spilled value zero slot */ "r1 = %[single_byte_buf];" "r2 = *(u32 *)(r10 -4);" "r1 += r2;" @@ -583,6 +581,47 @@ __naked void partial_stack_load_preserves_zeros(void) : __clobber_common); } +SEC("raw_tp") +__log_level(2) +__success +/* fp-4 is STACK_ZERO */ +__msg("2: (62) *(u32 *)(r10 -4) = 0 ; R10=fp0 fp-8=0000????") +__msg("4: (71) r2 = *(u8 *)(r10 -1) ; R2_w=0 R10=fp0 fp-8=0000????") +__msg("5: (0f) r1 += r2") +__msg("mark_precise: frame0: last_idx 5 first_idx 0 subseq_idx -1") +__msg("mark_precise: frame0: regs=r2 stack= before 4: (71) r2 = *(u8 *)(r10 -1)") +__naked void partial_stack_load_preserves_partial_zeros(void) +{ + asm volatile ( + /* fp-4 is value zero */ + ".8byte %[fp4_st_zero];" /* LLVM-18+: *(u32 *)(r10 -4) = 0; */ + + /* load single U8 from non-aligned stack zero slot */ + "r1 = %[single_byte_buf];" + "r2 = *(u8 *)(r10 -1);" + "r1 += r2;" + "*(u8 *)(r1 + 0) = r2;" /* this should be fine */ + + /* load single U16 from non-aligned stack zero slot */ + "r1 = %[single_byte_buf];" + "r2 = *(u16 *)(r10 -2);" + "r1 += r2;" + "*(u8 *)(r1 + 0) = r2;" /* this should be fine */ + + /* load single U32 from non-aligned stack zero slot */ + "r1 = %[single_byte_buf];" + "r2 = *(u32 *)(r10 -4);" + "r1 += r2;" + "*(u8 *)(r1 + 0) = r2;" /* this should be fine */ + + "r0 = 0;" + "exit;" + : + : __imm_ptr(single_byte_buf), + __imm_insn(fp4_st_zero, BPF_ST_MEM(BPF_W, BPF_REG_FP, -4, 0)) + : __clobber_common); +} + char two_byte_buf[2] SEC(".data.two_byte_buf"); SEC("raw_tp") @@ -737,4 +776,168 @@ __naked void stack_load_preserves_const_precision_subreg(void) : __clobber_common); } +SEC("xdp") +__description("32-bit spilled reg range should be tracked") +__success __retval(0) +__naked void spill_32bit_range_track(void) +{ + asm volatile(" \ + call %[bpf_ktime_get_ns]; \ + /* Make r0 bounded. */ \ + r0 &= 65535; \ + /* Assign an ID to r0. */ \ + r1 = r0; \ + /* 32-bit spill r0 to stack. */ \ + *(u32*)(r10 - 8) = r0; \ + /* Boundary check on r0. */ \ + if r0 < 1 goto l0_%=; \ + /* 32-bit fill r1 from stack. */ \ + r1 = *(u32*)(r10 - 8); \ + /* r1 == r0 => r1 >= 1 always. */ \ + if r1 >= 1 goto l0_%=; \ + /* Dead branch: the verifier should prune it. \ + * Do an invalid memory access if the verifier \ + * follows it. \ + */ \ + r0 = *(u64*)(r9 + 0); \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +SEC("xdp") +__description("64-bit spill of 64-bit reg should assign ID") +__success __retval(0) +__naked void spill_64bit_of_64bit_ok(void) +{ + asm volatile (" \ + /* Roll one bit to make the register inexact. */\ + call %[bpf_get_prandom_u32]; \ + r0 &= 0x80000000; \ + r0 <<= 32; \ + /* 64-bit spill r0 to stack - should assign an ID. */\ + *(u64*)(r10 - 8) = r0; \ + /* 64-bit fill r1 from stack - should preserve the ID. */\ + r1 = *(u64*)(r10 - 8); \ + /* Compare r1 with another register to trigger find_equal_scalars.\ + * Having one random bit is important here, otherwise the verifier cuts\ + * the corners. \ + */ \ + r2 = 0; \ + if r1 != r2 goto l0_%=; \ + /* The result of this comparison is predefined. */\ + if r0 == r2 goto l0_%=; \ + /* Dead branch: the verifier should prune it. Do an invalid memory\ + * access if the verifier follows it. \ + */ \ + r0 = *(u64*)(r9 + 0); \ + exit; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("xdp") +__description("32-bit spill of 32-bit reg should assign ID") +__success __retval(0) +__naked void spill_32bit_of_32bit_ok(void) +{ + asm volatile (" \ + /* Roll one bit to make the register inexact. */\ + call %[bpf_get_prandom_u32]; \ + w0 &= 0x80000000; \ + /* 32-bit spill r0 to stack - should assign an ID. */\ + *(u32*)(r10 - 8) = r0; \ + /* 32-bit fill r1 from stack - should preserve the ID. */\ + r1 = *(u32*)(r10 - 8); \ + /* Compare r1 with another register to trigger find_equal_scalars.\ + * Having one random bit is important here, otherwise the verifier cuts\ + * the corners. \ + */ \ + r2 = 0; \ + if r1 != r2 goto l0_%=; \ + /* The result of this comparison is predefined. */\ + if r0 == r2 goto l0_%=; \ + /* Dead branch: the verifier should prune it. Do an invalid memory\ + * access if the verifier follows it. \ + */ \ + r0 = *(u64*)(r9 + 0); \ + exit; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("xdp") +__description("16-bit spill of 16-bit reg should assign ID") +__success __retval(0) +__naked void spill_16bit_of_16bit_ok(void) +{ + asm volatile (" \ + /* Roll one bit to make the register inexact. */\ + call %[bpf_get_prandom_u32]; \ + r0 &= 0x8000; \ + /* 16-bit spill r0 to stack - should assign an ID. */\ + *(u16*)(r10 - 8) = r0; \ + /* 16-bit fill r1 from stack - should preserve the ID. */\ + r1 = *(u16*)(r10 - 8); \ + /* Compare r1 with another register to trigger find_equal_scalars.\ + * Having one random bit is important here, otherwise the verifier cuts\ + * the corners. \ + */ \ + r2 = 0; \ + if r1 != r2 goto l0_%=; \ + /* The result of this comparison is predefined. */\ + if r0 == r2 goto l0_%=; \ + /* Dead branch: the verifier should prune it. Do an invalid memory\ + * access if the verifier follows it. \ + */ \ + r0 = *(u64*)(r9 + 0); \ + exit; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("xdp") +__description("8-bit spill of 8-bit reg should assign ID") +__success __retval(0) +__naked void spill_8bit_of_8bit_ok(void) +{ + asm volatile (" \ + /* Roll one bit to make the register inexact. */\ + call %[bpf_get_prandom_u32]; \ + r0 &= 0x80; \ + /* 8-bit spill r0 to stack - should assign an ID. */\ + *(u8*)(r10 - 8) = r0; \ + /* 8-bit fill r1 from stack - should preserve the ID. */\ + r1 = *(u8*)(r10 - 8); \ + /* Compare r1 with another register to trigger find_equal_scalars.\ + * Having one random bit is important here, otherwise the verifier cuts\ + * the corners. \ + */ \ + r2 = 0; \ + if r1 != r2 goto l0_%=; \ + /* The result of this comparison is predefined. */\ + if r0 == r2 goto l0_%=; \ + /* Dead branch: the verifier should prune it. Do an invalid memory\ + * access if the verifier follows it. \ + */ \ + r0 = *(u64*)(r9 + 0); \ + exit; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_loader.c b/tools/testing/selftests/bpf/test_loader.c index f01391021218..ba57601c2a4d 100644 --- a/tools/testing/selftests/bpf/test_loader.c +++ b/tools/testing/selftests/bpf/test_loader.c @@ -181,7 +181,7 @@ static int parse_test_spec(struct test_loader *tester, memset(spec, 0, sizeof(*spec)); spec->prog_name = bpf_program__name(prog); - spec->prog_flags = BPF_F_TEST_REG_INVARIANTS; /* by default be strict */ + spec->prog_flags = testing_prog_flags(); btf = bpf_object__btf(obj); if (!btf) { @@ -688,7 +688,7 @@ static void process_subtest(struct test_loader *tester, ++nr_progs; specs = calloc(nr_progs, sizeof(struct test_spec)); - if (!ASSERT_OK_PTR(specs, "Can't alloc specs array")) + if (!ASSERT_OK_PTR(specs, "specs_alloc")) return; i = 0; diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index 767e0693df10..dfbab214f4d1 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -1190,7 +1190,11 @@ static void test_map_in_map(void) goto out_map_in_map; } - bpf_object__load(obj); + err = bpf_object__load(obj); + if (err) { + printf("Failed to load test prog\n"); + goto out_map_in_map; + } map = bpf_object__find_map_by_name(obj, "mim_array"); if (!map) { diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index 1b9387890148..808550986f30 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -547,24 +547,6 @@ int bpf_find_map(const char *test, struct bpf_object *obj, const char *name) return bpf_map__fd(map); } -static bool is_jit_enabled(void) -{ - const char *jit_sysctl = "/proc/sys/net/core/bpf_jit_enable"; - bool enabled = false; - int sysctl_fd; - - sysctl_fd = open(jit_sysctl, 0, O_RDONLY); - if (sysctl_fd != -1) { - char tmpc; - - if (read(sysctl_fd, &tmpc, sizeof(tmpc)) == 1) - enabled = (tmpc != '0'); - close(sysctl_fd); - } - - return enabled; -} - int compare_map_keys(int map1_fd, int map2_fd) { __u32 key, next_key; diff --git a/tools/testing/selftests/bpf/test_sock_addr.c b/tools/testing/selftests/bpf/test_sock_addr.c index b0068a9d2cfe..80c42583f597 100644 --- a/tools/testing/selftests/bpf/test_sock_addr.c +++ b/tools/testing/selftests/bpf/test_sock_addr.c @@ -19,6 +19,7 @@ #include <bpf/libbpf.h> #include "cgroup_helpers.h" +#include "testing_helpers.h" #include "bpf_util.h" #ifndef ENOTSUPP @@ -679,7 +680,7 @@ static int load_path(const struct sock_addr_test *test, const char *path) bpf_program__set_type(prog, BPF_PROG_TYPE_CGROUP_SOCK_ADDR); bpf_program__set_expected_attach_type(prog, test->expected_attach_type); - bpf_program__set_flags(prog, BPF_F_TEST_RND_HI32 | BPF_F_TEST_REG_INVARIANTS); + bpf_program__set_flags(prog, testing_prog_flags()); err = bpf_object__load(obj); if (err) { diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index f36e41435be7..df04bda1c927 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -67,6 +67,7 @@ #define F_NEEDS_EFFICIENT_UNALIGNED_ACCESS (1 << 0) #define F_LOAD_WITH_STRICT_ALIGNMENT (1 << 1) +#define F_NEEDS_JIT_ENABLED (1 << 2) /* need CAP_BPF, CAP_NET_ADMIN, CAP_PERFMON to load progs */ #define ADMIN_CAPS (1ULL << CAP_NET_ADMIN | \ @@ -74,6 +75,7 @@ 1ULL << CAP_BPF) #define UNPRIV_SYSCTL "kernel/unprivileged_bpf_disabled" static bool unpriv_disabled = false; +static bool jit_disabled; static int skips; static bool verbose = false; static int verif_log_level = 0; @@ -1341,48 +1343,6 @@ static bool cmp_str_seq(const char *log, const char *exp) return true; } -static struct bpf_insn *get_xlated_program(int fd_prog, int *cnt) -{ - __u32 buf_element_size = sizeof(struct bpf_insn); - struct bpf_prog_info info = {}; - __u32 info_len = sizeof(info); - __u32 xlated_prog_len; - struct bpf_insn *buf; - - if (bpf_prog_get_info_by_fd(fd_prog, &info, &info_len)) { - perror("bpf_prog_get_info_by_fd failed"); - return NULL; - } - - xlated_prog_len = info.xlated_prog_len; - if (xlated_prog_len % buf_element_size) { - printf("Program length %d is not multiple of %d\n", - xlated_prog_len, buf_element_size); - return NULL; - } - - *cnt = xlated_prog_len / buf_element_size; - buf = calloc(*cnt, buf_element_size); - if (!buf) { - perror("can't allocate xlated program buffer"); - return NULL; - } - - bzero(&info, sizeof(info)); - info.xlated_prog_len = xlated_prog_len; - info.xlated_prog_insns = (__u64)(unsigned long)buf; - if (bpf_prog_get_info_by_fd(fd_prog, &info, &info_len)) { - perror("second bpf_prog_get_info_by_fd failed"); - goto out_free_buf; - } - - return buf; - -out_free_buf: - free(buf); - return NULL; -} - static bool is_null_insn(struct bpf_insn *insn) { struct bpf_insn null_insn = {}; @@ -1505,7 +1465,7 @@ static void print_insn(struct bpf_insn *buf, int cnt) static bool check_xlated_program(struct bpf_test *test, int fd_prog) { struct bpf_insn *buf; - int cnt; + unsigned int cnt; bool result = true; bool check_expected = !is_null_insn(test->expected_insns); bool check_unexpected = !is_null_insn(test->unexpected_insns); @@ -1513,8 +1473,7 @@ static bool check_xlated_program(struct bpf_test *test, int fd_prog) if (!check_expected && !check_unexpected) goto out; - buf = get_xlated_program(fd_prog, &cnt); - if (!buf) { + if (get_xlated_program(fd_prog, &buf, &cnt)) { printf("FAIL: can't get xlated program\n"); result = false; goto out; @@ -1567,6 +1526,13 @@ static void do_test_single(struct bpf_test *test, bool unpriv, __u32 pflags; int i, err; + if ((test->flags & F_NEEDS_JIT_ENABLED) && jit_disabled) { + printf("SKIP (requires BPF JIT)\n"); + skips++; + sched_yield(); + return; + } + fd_prog = -1; for (i = 0; i < MAX_NR_MAPS; i++) map_fds[i] = -1; @@ -1588,7 +1554,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv, if (fixup_skips != skips) return; - pflags = BPF_F_TEST_RND_HI32 | BPF_F_TEST_REG_INVARIANTS; + pflags = testing_prog_flags(); if (test->flags & F_LOAD_WITH_STRICT_ALIGNMENT) pflags |= BPF_F_STRICT_ALIGNMENT; if (test->flags & F_NEEDS_EFFICIENT_UNALIGNED_ACCESS) @@ -1887,6 +1853,8 @@ int main(int argc, char **argv) return EXIT_FAILURE; } + jit_disabled = !is_jit_enabled(); + /* Use libbpf 1.0 API mode */ libbpf_set_strict_mode(LIBBPF_STRICT_ALL); diff --git a/tools/testing/selftests/bpf/testing_helpers.c b/tools/testing/selftests/bpf/testing_helpers.c index d2458c1b1671..a59e56d804ee 100644 --- a/tools/testing/selftests/bpf/testing_helpers.c +++ b/tools/testing/selftests/bpf/testing_helpers.c @@ -252,6 +252,34 @@ __u32 link_info_prog_id(const struct bpf_link *link, struct bpf_link_info *info) int extra_prog_load_log_flags = 0; +int testing_prog_flags(void) +{ + static int cached_flags = -1; + static int prog_flags[] = { BPF_F_TEST_RND_HI32, BPF_F_TEST_REG_INVARIANTS }; + static struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + int insn_cnt = ARRAY_SIZE(insns), i, fd, flags = 0; + LIBBPF_OPTS(bpf_prog_load_opts, opts); + + if (cached_flags >= 0) + return cached_flags; + + for (i = 0; i < ARRAY_SIZE(prog_flags); i++) { + opts.prog_flags = prog_flags[i]; + fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, "flag-test", "GPL", + insns, insn_cnt, &opts); + if (fd >= 0) { + flags |= prog_flags[i]; + close(fd); + } + } + + cached_flags = flags; + return cached_flags; +} + int bpf_prog_test_load(const char *file, enum bpf_prog_type type, struct bpf_object **pobj, int *prog_fd) { @@ -276,7 +304,7 @@ int bpf_prog_test_load(const char *file, enum bpf_prog_type type, if (type != BPF_PROG_TYPE_UNSPEC && bpf_program__type(prog) != type) bpf_program__set_type(prog, type); - flags = bpf_program__flags(prog) | BPF_F_TEST_RND_HI32 | BPF_F_TEST_REG_INVARIANTS; + flags = bpf_program__flags(prog) | testing_prog_flags(); bpf_program__set_flags(prog, flags); err = bpf_object__load(obj); @@ -299,7 +327,7 @@ int bpf_test_load_program(enum bpf_prog_type type, const struct bpf_insn *insns, { LIBBPF_OPTS(bpf_prog_load_opts, opts, .kern_version = kern_version, - .prog_flags = BPF_F_TEST_RND_HI32 | BPF_F_TEST_REG_INVARIANTS, + .prog_flags = testing_prog_flags(), .log_level = extra_prog_load_log_flags, .log_buf = log_buf, .log_size = log_buf_sz, @@ -387,3 +415,63 @@ int kern_sync_rcu(void) { return syscall(__NR_membarrier, MEMBARRIER_CMD_SHARED, 0, 0); } + +int get_xlated_program(int fd_prog, struct bpf_insn **buf, __u32 *cnt) +{ + __u32 buf_element_size = sizeof(struct bpf_insn); + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); + __u32 xlated_prog_len; + + if (bpf_prog_get_info_by_fd(fd_prog, &info, &info_len)) { + perror("bpf_prog_get_info_by_fd failed"); + return -1; + } + + xlated_prog_len = info.xlated_prog_len; + if (xlated_prog_len % buf_element_size) { + printf("Program length %u is not multiple of %u\n", + xlated_prog_len, buf_element_size); + return -1; + } + + *cnt = xlated_prog_len / buf_element_size; + *buf = calloc(*cnt, buf_element_size); + if (!buf) { + perror("can't allocate xlated program buffer"); + return -ENOMEM; + } + + bzero(&info, sizeof(info)); + info.xlated_prog_len = xlated_prog_len; + info.xlated_prog_insns = (__u64)(unsigned long)*buf; + if (bpf_prog_get_info_by_fd(fd_prog, &info, &info_len)) { + perror("second bpf_prog_get_info_by_fd failed"); + goto out_free_buf; + } + + return 0; + +out_free_buf: + free(*buf); + *buf = NULL; + return -1; +} + +bool is_jit_enabled(void) +{ + const char *jit_sysctl = "/proc/sys/net/core/bpf_jit_enable"; + bool enabled = false; + int sysctl_fd; + + sysctl_fd = open(jit_sysctl, O_RDONLY); + if (sysctl_fd != -1) { + char tmpc; + + if (read(sysctl_fd, &tmpc, sizeof(tmpc)) == 1) + enabled = (tmpc != '0'); + close(sysctl_fd); + } + + return enabled; +} diff --git a/tools/testing/selftests/bpf/testing_helpers.h b/tools/testing/selftests/bpf/testing_helpers.h index 35284faff4f2..d14de81727e6 100644 --- a/tools/testing/selftests/bpf/testing_helpers.h +++ b/tools/testing/selftests/bpf/testing_helpers.h @@ -46,4 +46,12 @@ static inline __u64 get_time_ns(void) return (u64)t.tv_sec * 1000000000 + t.tv_nsec; } +struct bpf_insn; +/* Request BPF program instructions after all rewrites are applied, + * e.g. verifier.c:convert_ctx_access() is done. + */ +int get_xlated_program(int fd_prog, struct bpf_insn **buf, __u32 *cnt); +int testing_prog_flags(void); +bool is_jit_enabled(void); + #endif /* __TESTING_HELPERS_H */ diff --git a/tools/testing/selftests/bpf/verifier/bpf_loop_inline.c b/tools/testing/selftests/bpf/verifier/bpf_loop_inline.c index a535d41dc20d..59125b22ae39 100644 --- a/tools/testing/selftests/bpf/verifier/bpf_loop_inline.c +++ b/tools/testing/selftests/bpf/verifier/bpf_loop_inline.c @@ -57,6 +57,7 @@ .expected_insns = { PSEUDO_CALL_INSN() }, .unexpected_insns = { HELPER_CALL_INSN() }, .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .flags = F_NEEDS_JIT_ENABLED, .result = ACCEPT, .runs = 0, .func_info = { { 0, MAIN_TYPE }, { 12, CALLBACK_TYPE } }, @@ -90,6 +91,7 @@ .expected_insns = { HELPER_CALL_INSN() }, .unexpected_insns = { PSEUDO_CALL_INSN() }, .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .flags = F_NEEDS_JIT_ENABLED, .result = ACCEPT, .runs = 0, .func_info = { { 0, MAIN_TYPE }, { 16, CALLBACK_TYPE } }, @@ -127,6 +129,7 @@ .expected_insns = { HELPER_CALL_INSN() }, .unexpected_insns = { PSEUDO_CALL_INSN() }, .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .flags = F_NEEDS_JIT_ENABLED, .result = ACCEPT, .runs = 0, .func_info = { @@ -165,6 +168,7 @@ .expected_insns = { PSEUDO_CALL_INSN() }, .unexpected_insns = { HELPER_CALL_INSN() }, .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .flags = F_NEEDS_JIT_ENABLED, .result = ACCEPT, .runs = 0, .func_info = { @@ -235,6 +239,7 @@ }, .unexpected_insns = { HELPER_CALL_INSN() }, .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .flags = F_NEEDS_JIT_ENABLED, .result = ACCEPT, .func_info = { { 0, MAIN_TYPE }, @@ -252,6 +257,7 @@ .unexpected_insns = { HELPER_CALL_INSN() }, .result = ACCEPT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .flags = F_NEEDS_JIT_ENABLED, .func_info = { { 0, MAIN_TYPE }, { 16, CALLBACK_TYPE } }, .func_info_cnt = 2, BTF_TYPES diff --git a/tools/testing/selftests/bpf/verifier/precise.c b/tools/testing/selftests/bpf/verifier/precise.c index 8a2ff81d8350..0a9293a57211 100644 --- a/tools/testing/selftests/bpf/verifier/precise.c +++ b/tools/testing/selftests/bpf/verifier/precise.c @@ -183,10 +183,10 @@ .prog_type = BPF_PROG_TYPE_XDP, .flags = BPF_F_TEST_STATE_FREQ, .errstr = "mark_precise: frame0: last_idx 7 first_idx 7\ - mark_precise: frame0: parent state regs=r4 stack=:\ + mark_precise: frame0: parent state regs=r4 stack=-8:\ mark_precise: frame0: last_idx 6 first_idx 4\ - mark_precise: frame0: regs=r4 stack= before 6: (b7) r0 = -1\ - mark_precise: frame0: regs=r4 stack= before 5: (79) r4 = *(u64 *)(r10 -8)\ + mark_precise: frame0: regs=r4 stack=-8 before 6: (b7) r0 = -1\ + mark_precise: frame0: regs=r4 stack=-8 before 5: (79) r4 = *(u64 *)(r10 -8)\ mark_precise: frame0: regs= stack=-8 before 4: (7b) *(u64 *)(r3 -8) = r0\ mark_precise: frame0: parent state regs=r0 stack=:\ mark_precise: frame0: last_idx 3 first_idx 3\ diff --git a/tools/testing/selftests/core/close_range_test.c b/tools/testing/selftests/core/close_range_test.c index 534576f06df1..c59e4adb905d 100644 --- a/tools/testing/selftests/core/close_range_test.c +++ b/tools/testing/selftests/core/close_range_test.c @@ -12,6 +12,7 @@ #include <syscall.h> #include <unistd.h> #include <sys/resource.h> +#include <linux/close_range.h> #include "../kselftest_harness.h" #include "../clone3/clone3_selftests.h" diff --git a/tools/testing/selftests/drivers/net/bonding/Makefile b/tools/testing/selftests/drivers/net/bonding/Makefile index 8a72bb7de70f..03a089165d3f 100644 --- a/tools/testing/selftests/drivers/net/bonding/Makefile +++ b/tools/testing/selftests/drivers/net/bonding/Makefile @@ -15,7 +15,10 @@ TEST_PROGS := \ TEST_FILES := \ lag_lib.sh \ bond_topo_2d1c.sh \ - bond_topo_3d1c.sh \ - net_forwarding_lib.sh + bond_topo_3d1c.sh + +TEST_INCLUDES := \ + ../../../net/forwarding/lib.sh \ + ../../../net/lib.sh include ../../../lib.mk diff --git a/tools/testing/selftests/drivers/net/bonding/bond-break-lacpdu-tx.sh b/tools/testing/selftests/drivers/net/bonding/bond-break-lacpdu-tx.sh index 6358df5752f9..1ec7f59db7f4 100755 --- a/tools/testing/selftests/drivers/net/bonding/bond-break-lacpdu-tx.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond-break-lacpdu-tx.sh @@ -20,21 +20,21 @@ # +------+ +------+ # # We use veths instead of physical interfaces +REQUIRE_MZ=no +NUM_NETIFS=0 +lib_dir=$(dirname "$0") +source "$lib_dir"/../../../net/forwarding/lib.sh set -e -tmp=$(mktemp -q dump.XXXXXX) cleanup() { ip link del fab-br0 >/dev/null 2>&1 || : ip link del fbond >/dev/null 2>&1 || : ip link del veth1-bond >/dev/null 2>&1 || : ip link del veth2-bond >/dev/null 2>&1 || : - modprobe -r bonding >/dev/null 2>&1 || : - rm -f -- ${tmp} } trap cleanup 0 1 2 cleanup -sleep 1 # create the bridge ip link add fab-br0 address 52:54:00:3B:7C:A6 mtu 1500 type bridge \ @@ -67,13 +67,12 @@ ip link set fab-br0 up ip link set fbond up ip addr add dev fab-br0 10.0.0.3 -tcpdump -n -i veth1-end -e ether proto 0x8809 >${tmp} 2>&1 & -sleep 15 -pkill tcpdump >/dev/null 2>&1 rc=0 -num=$(grep "packets captured" ${tmp} | awk '{print $1}') -if test "$num" -gt 0; then - echo "PASS, captured ${num}" +tc qdisc add dev veth1-end clsact +tc filter add dev veth1-end ingress protocol 0x8809 pref 1 handle 101 flower skip_hw action pass +if slowwait_for_counter 15 2 \ + tc_rule_handle_stats_get "dev veth1-end ingress" 101 ".packets" "" &> /dev/null; then + echo "PASS, captured 2" else echo "FAIL" rc=1 diff --git a/tools/testing/selftests/drivers/net/bonding/bond-eth-type-change.sh b/tools/testing/selftests/drivers/net/bonding/bond-eth-type-change.sh index 862e947e17c7..8293dbc7c18f 100755 --- a/tools/testing/selftests/drivers/net/bonding/bond-eth-type-change.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond-eth-type-change.sh @@ -11,7 +11,7 @@ ALL_TESTS=" REQUIRE_MZ=no NUM_NETIFS=0 lib_dir=$(dirname "$0") -source "$lib_dir"/net_forwarding_lib.sh +source "$lib_dir"/../../../net/forwarding/lib.sh bond_check_flags() { diff --git a/tools/testing/selftests/drivers/net/bonding/bond-lladdr-target.sh b/tools/testing/selftests/drivers/net/bonding/bond-lladdr-target.sh index 89af402fabbe..78d3e0fe6604 100755 --- a/tools/testing/selftests/drivers/net/bonding/bond-lladdr-target.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond-lladdr-target.sh @@ -17,6 +17,11 @@ # +----------------+ # # We use veths instead of physical interfaces +REQUIRE_MZ=no +NUM_NETIFS=0 +lib_dir=$(dirname "$0") +source "$lib_dir"/../../../net/forwarding/lib.sh + sw="sw-$(mktemp -u XXXXXX)" host="ns-$(mktemp -u XXXXXX)" @@ -26,6 +31,16 @@ cleanup() ip netns del $host } +wait_lladdr_dad() +{ + $@ | grep fe80 | grep -qv tentative +} + +wait_bond_up() +{ + $@ | grep -q 'state UP' +} + trap cleanup 0 1 2 ip netns add $sw @@ -37,8 +52,8 @@ ip -n $host link add veth1 type veth peer name veth1 netns $sw ip -n $sw link add br0 type bridge ip -n $sw link set br0 up sw_lladdr=$(ip -n $sw addr show br0 | awk '/fe80/{print $2}' | cut -d'/' -f1) -# sleep some time to make sure bridge lladdr pass DAD -sleep 2 +# wait some time to make sure bridge lladdr pass DAD +slowwait 2 wait_lladdr_dad ip -n $sw addr show br0 ip -n $host link add bond0 type bond mode 1 ns_ip6_target ${sw_lladdr} \ arp_validate 3 arp_interval 1000 @@ -53,7 +68,7 @@ ip -n $sw link set veth1 master br0 ip -n $sw link set veth0 up ip -n $sw link set veth1 up -sleep 5 +slowwait 5 wait_bond_up ip -n $host link show bond0 rc=0 if ip -n $host link show bond0 | grep -q LOWER_UP; then diff --git a/tools/testing/selftests/drivers/net/bonding/bond_options.sh b/tools/testing/selftests/drivers/net/bonding/bond_options.sh index d508486cc0bd..644ea5769e81 100755 --- a/tools/testing/selftests/drivers/net/bonding/bond_options.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond_options.sh @@ -45,15 +45,23 @@ skip_ns() } active_slave="" +active_slave_changed() +{ + local old_active_slave=$1 + local new_active_slave=$(cmd_jq "ip -n ${s_ns} -d -j link show bond0" \ + ".[].linkinfo.info_data.active_slave") + [ "$new_active_slave" != "$old_active_slave" -a "$new_active_slave" != "null" ] +} + check_active_slave() { local target_active_slave=$1 + slowwait 5 active_slave_changed $active_slave active_slave=$(cmd_jq "ip -n ${s_ns} -d -j link show bond0" ".[].linkinfo.info_data.active_slave") test "$active_slave" = "$target_active_slave" check_err $? "Current active slave is $active_slave but not $target_active_slave" } - # Test bonding prio option prio_test() { @@ -84,13 +92,13 @@ prio_test() # active slave should be the higher prio slave ip -n ${s_ns} link set $active_slave down - bond_check_connection "fail over" check_active_slave eth2 + bond_check_connection "fail over" # when only 1 slave is up ip -n ${s_ns} link set $active_slave down - bond_check_connection "only 1 slave up" check_active_slave eth0 + bond_check_connection "only 1 slave up" # when a higher prio slave change to up ip -n ${s_ns} link set eth2 up @@ -140,8 +148,8 @@ prio_test() check_active_slave "eth1" ip -n ${s_ns} link set $active_slave down - bond_check_connection "change slave prio" check_active_slave "eth0" + bond_check_connection "change slave prio" fi } @@ -199,6 +207,15 @@ prio() prio_ns "active-backup" } +wait_mii_up() +{ + for i in $(seq 0 2); do + mii_status=$(cmd_jq "ip -n ${s_ns} -j -d link show eth$i" ".[].linkinfo.info_slave_data.mii_status") + [ ${mii_status} != "UP" ] && return 1 + done + return 0 +} + arp_validate_test() { local param="$1" @@ -211,7 +228,7 @@ arp_validate_test() [ $RET -ne 0 ] && log_test "arp_validate" "$retmsg" # wait for a while to make sure the mii status stable - sleep 5 + slowwait 5 wait_mii_up for i in $(seq 0 2); do mii_status=$(cmd_jq "ip -n ${s_ns} -j -d link show eth$i" ".[].linkinfo.info_slave_data.mii_status") if [ ${mii_status} != "UP" ]; then @@ -276,10 +293,13 @@ garp_test() active_slave=$(cmd_jq "ip -n ${s_ns} -d -j link show bond0" ".[].linkinfo.info_data.active_slave") ip -n ${s_ns} link set ${active_slave} down - exp_num=$(echo "${param}" | cut -f6 -d ' ') - sleep $((exp_num + 2)) + # wait for active link change + slowwait 2 active_slave_changed $active_slave + exp_num=$(echo "${param}" | cut -f6 -d ' ') active_slave=$(cmd_jq "ip -n ${s_ns} -d -j link show bond0" ".[].linkinfo.info_data.active_slave") + slowwait_for_counter $((exp_num + 5)) $exp_num \ + tc_rule_handle_stats_get "dev s${active_slave#eth} ingress" 101 ".packets" "-n ${g_ns}" # check result real_num=$(tc_rule_handle_stats_get "dev s${active_slave#eth} ingress" 101 ".packets" "-n ${g_ns}") @@ -296,8 +316,8 @@ garp_test() num_grat_arp() { local val - for val in 10 20 30 50; do - garp_test "mode active-backup miimon 100 num_grat_arp $val peer_notify_delay 1000" + for val in 10 20 30; do + garp_test "mode active-backup miimon 10 num_grat_arp $val peer_notify_delay 100" log_test "num_grat_arp" "active-backup miimon num_grat_arp $val" done } diff --git a/tools/testing/selftests/drivers/net/bonding/bond_topo_2d1c.sh b/tools/testing/selftests/drivers/net/bonding/bond_topo_2d1c.sh index a509ef949dcf..195ef83cfbf1 100644 --- a/tools/testing/selftests/drivers/net/bonding/bond_topo_2d1c.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond_topo_2d1c.sh @@ -28,7 +28,7 @@ REQUIRE_MZ=no NUM_NETIFS=0 lib_dir=$(dirname "$0") -source ${lib_dir}/net_forwarding_lib.sh +source "$lib_dir"/../../../net/forwarding/lib.sh s_ns="s-$(mktemp -u XXXXXX)" c_ns="c-$(mktemp -u XXXXXX)" @@ -73,7 +73,6 @@ server_create() ip -n ${s_ns} link set bond0 up ip -n ${s_ns} addr add ${s_ip4}/24 dev bond0 ip -n ${s_ns} addr add ${s_ip6}/24 dev bond0 - sleep 2 } # Reset bond with new mode and options @@ -96,7 +95,8 @@ bond_reset() ip -n ${s_ns} link set bond0 up ip -n ${s_ns} addr add ${s_ip4}/24 dev bond0 ip -n ${s_ns} addr add ${s_ip6}/24 dev bond0 - sleep 2 + # Wait for IPv6 address ready as it needs DAD + slowwait 2 ip netns exec ${s_ns} ping6 ${c_ip6} -c 1 -W 0.1 &> /dev/null } server_destroy() @@ -150,7 +150,7 @@ bond_check_connection() { local msg=${1:-"check connection"} - sleep 2 + slowwait 2 ip netns exec ${s_ns} ping ${c_ip4} -c 1 -W 0.1 &> /dev/null ip netns exec ${s_ns} ping ${c_ip4} -c5 -i 0.1 &>/dev/null check_err $? "${msg}: ping failed" ip netns exec ${s_ns} ping6 ${c_ip6} -c5 -i 0.1 &>/dev/null diff --git a/tools/testing/selftests/drivers/net/bonding/dev_addr_lists.sh b/tools/testing/selftests/drivers/net/bonding/dev_addr_lists.sh index 5cfe7d8ebc25..e6fa24eded5b 100755 --- a/tools/testing/selftests/drivers/net/bonding/dev_addr_lists.sh +++ b/tools/testing/selftests/drivers/net/bonding/dev_addr_lists.sh @@ -14,7 +14,7 @@ ALL_TESTS=" REQUIRE_MZ=no NUM_NETIFS=0 lib_dir=$(dirname "$0") -source "$lib_dir"/net_forwarding_lib.sh +source "$lib_dir"/../../../net/forwarding/lib.sh source "$lib_dir"/lag_lib.sh diff --git a/tools/testing/selftests/drivers/net/bonding/lag_lib.sh b/tools/testing/selftests/drivers/net/bonding/lag_lib.sh index 2a268b17b61f..bf9bcd1b5ec0 100644 --- a/tools/testing/selftests/drivers/net/bonding/lag_lib.sh +++ b/tools/testing/selftests/drivers/net/bonding/lag_lib.sh @@ -48,6 +48,17 @@ test_LAG_cleanup() ip link add mv0 link "$name" up address "$ucaddr" type macvlan # Used to test dev->mc handling ip address add "$addr6" dev "$name" + + # Check that addresses were added as expected + (grep_bridge_fdb "$ucaddr" bridge fdb show dev dummy1 || + grep_bridge_fdb "$ucaddr" bridge fdb show dev dummy2) >/dev/null + check_err $? "macvlan unicast address not found on a slave" + + # mcaddr is added asynchronously by addrconf_dad_work(), use busywait + (busywait 10000 grep_bridge_fdb "$mcaddr" bridge fdb show dev dummy1 || + grep_bridge_fdb "$mcaddr" bridge fdb show dev dummy2) >/dev/null + check_err $? "IPv6 solicited-node multicast mac address not found on a slave" + ip link set dev "$name" down ip link del "$name" @@ -96,13 +107,12 @@ lag_setup2x2() NAMESPACES="${namespaces}" } -# cleanup all lag related namespaces and remove the bonding module +# cleanup all lag related namespaces lag_cleanup() { for n in ${NAMESPACES}; do ip netns delete ${n} >/dev/null 2>&1 || true done - modprobe -r bonding } SWITCH="lag_node1" @@ -148,7 +158,7 @@ test_bond_recovery() create_bond $@ # verify connectivity - ip netns exec ${CLIENT} ping ${SWITCHIP} -c 2 >/dev/null 2>&1 + slowwait 2 ip netns exec ${CLIENT} ping ${SWITCHIP} -c 2 -W 0.1 &> /dev/null check_err $? "No connectivity" # force the links of the bond down @@ -158,7 +168,7 @@ test_bond_recovery() ip netns exec ${SWITCH} ip link set eth1 down # re-verify connectivity - ip netns exec ${CLIENT} ping ${SWITCHIP} -c 2 >/dev/null 2>&1 + slowwait 2 ip netns exec ${CLIENT} ping ${SWITCHIP} -c 2 -W 0.1 &> /dev/null local rc=$? check_err $rc "Bond failed to recover" diff --git a/tools/testing/selftests/drivers/net/bonding/mode-1-recovery-updelay.sh b/tools/testing/selftests/drivers/net/bonding/mode-1-recovery-updelay.sh index b76bf5030952..9d26ab4cad0b 100755 --- a/tools/testing/selftests/drivers/net/bonding/mode-1-recovery-updelay.sh +++ b/tools/testing/selftests/drivers/net/bonding/mode-1-recovery-updelay.sh @@ -23,7 +23,7 @@ REQUIRE_MZ=no REQUIRE_JQ=no NUM_NETIFS=0 lib_dir=$(dirname "$0") -source "$lib_dir"/net_forwarding_lib.sh +source "$lib_dir"/../../../net/forwarding/lib.sh source "$lib_dir"/lag_lib.sh cleanup() diff --git a/tools/testing/selftests/drivers/net/bonding/mode-2-recovery-updelay.sh b/tools/testing/selftests/drivers/net/bonding/mode-2-recovery-updelay.sh index 8c2619002147..2d275b3e47dd 100755 --- a/tools/testing/selftests/drivers/net/bonding/mode-2-recovery-updelay.sh +++ b/tools/testing/selftests/drivers/net/bonding/mode-2-recovery-updelay.sh @@ -23,7 +23,7 @@ REQUIRE_MZ=no REQUIRE_JQ=no NUM_NETIFS=0 lib_dir=$(dirname "$0") -source "$lib_dir"/net_forwarding_lib.sh +source "$lib_dir"/../../../net/forwarding/lib.sh source "$lib_dir"/lag_lib.sh cleanup() diff --git a/tools/testing/selftests/drivers/net/bonding/net_forwarding_lib.sh b/tools/testing/selftests/drivers/net/bonding/net_forwarding_lib.sh deleted file mode 120000 index 39c96828c5ef..000000000000 --- a/tools/testing/selftests/drivers/net/bonding/net_forwarding_lib.sh +++ /dev/null @@ -1 +0,0 @@ -../../../net/forwarding/lib.sh
\ No newline at end of file diff --git a/tools/testing/selftests/drivers/net/dsa/Makefile b/tools/testing/selftests/drivers/net/dsa/Makefile index c393e7b73805..cd6817fe5be6 100644 --- a/tools/testing/selftests/drivers/net/dsa/Makefile +++ b/tools/testing/selftests/drivers/net/dsa/Makefile @@ -11,8 +11,22 @@ TEST_PROGS = bridge_locked_port.sh \ tc_actions.sh \ test_bridge_fdb_stress.sh -TEST_PROGS_EXTENDED := lib.sh tc_common.sh +TEST_FILES := \ + run_net_forwarding_test.sh \ + forwarding.config -TEST_FILES := forwarding.config +TEST_INCLUDES := \ + ../../../net/forwarding/bridge_locked_port.sh \ + ../../../net/forwarding/bridge_mdb.sh \ + ../../../net/forwarding/bridge_mld.sh \ + ../../../net/forwarding/bridge_vlan_aware.sh \ + ../../../net/forwarding/bridge_vlan_mcast.sh \ + ../../../net/forwarding/bridge_vlan_unaware.sh \ + ../../../net/forwarding/lib.sh \ + ../../../net/forwarding/local_termination.sh \ + ../../../net/forwarding/no_forwarding.sh \ + ../../../net/forwarding/tc_actions.sh \ + ../../../net/forwarding/tc_common.sh \ + ../../../net/lib.sh include ../../../lib.mk diff --git a/tools/testing/selftests/drivers/net/dsa/bridge_locked_port.sh b/tools/testing/selftests/drivers/net/dsa/bridge_locked_port.sh index f5eb940c4c7c..d16a65e7595d 120000 --- a/tools/testing/selftests/drivers/net/dsa/bridge_locked_port.sh +++ b/tools/testing/selftests/drivers/net/dsa/bridge_locked_port.sh @@ -1 +1 @@ -../../../net/forwarding/bridge_locked_port.sh
\ No newline at end of file +run_net_forwarding_test.sh
\ No newline at end of file diff --git a/tools/testing/selftests/drivers/net/dsa/bridge_mdb.sh b/tools/testing/selftests/drivers/net/dsa/bridge_mdb.sh index 76492da525f7..d16a65e7595d 120000 --- a/tools/testing/selftests/drivers/net/dsa/bridge_mdb.sh +++ b/tools/testing/selftests/drivers/net/dsa/bridge_mdb.sh @@ -1 +1 @@ -../../../net/forwarding/bridge_mdb.sh
\ No newline at end of file +run_net_forwarding_test.sh
\ No newline at end of file diff --git a/tools/testing/selftests/drivers/net/dsa/bridge_mld.sh b/tools/testing/selftests/drivers/net/dsa/bridge_mld.sh index 81a7e0df0474..d16a65e7595d 120000 --- a/tools/testing/selftests/drivers/net/dsa/bridge_mld.sh +++ b/tools/testing/selftests/drivers/net/dsa/bridge_mld.sh @@ -1 +1 @@ -../../../net/forwarding/bridge_mld.sh
\ No newline at end of file +run_net_forwarding_test.sh
\ No newline at end of file diff --git a/tools/testing/selftests/drivers/net/dsa/bridge_vlan_aware.sh b/tools/testing/selftests/drivers/net/dsa/bridge_vlan_aware.sh index 9831ed74376a..d16a65e7595d 120000 --- a/tools/testing/selftests/drivers/net/dsa/bridge_vlan_aware.sh +++ b/tools/testing/selftests/drivers/net/dsa/bridge_vlan_aware.sh @@ -1 +1 @@ -../../../net/forwarding/bridge_vlan_aware.sh
\ No newline at end of file +run_net_forwarding_test.sh
\ No newline at end of file diff --git a/tools/testing/selftests/drivers/net/dsa/bridge_vlan_mcast.sh b/tools/testing/selftests/drivers/net/dsa/bridge_vlan_mcast.sh index 7f3c3f0bf719..d16a65e7595d 120000 --- a/tools/testing/selftests/drivers/net/dsa/bridge_vlan_mcast.sh +++ b/tools/testing/selftests/drivers/net/dsa/bridge_vlan_mcast.sh @@ -1 +1 @@ -../../../net/forwarding/bridge_vlan_mcast.sh
\ No newline at end of file +run_net_forwarding_test.sh
\ No newline at end of file diff --git a/tools/testing/selftests/drivers/net/dsa/bridge_vlan_unaware.sh b/tools/testing/selftests/drivers/net/dsa/bridge_vlan_unaware.sh index bf1a57e6bde1..d16a65e7595d 120000 --- a/tools/testing/selftests/drivers/net/dsa/bridge_vlan_unaware.sh +++ b/tools/testing/selftests/drivers/net/dsa/bridge_vlan_unaware.sh @@ -1 +1 @@ -../../../net/forwarding/bridge_vlan_unaware.sh
\ No newline at end of file +run_net_forwarding_test.sh
\ No newline at end of file diff --git a/tools/testing/selftests/drivers/net/dsa/lib.sh b/tools/testing/selftests/drivers/net/dsa/lib.sh deleted file mode 120000 index 39c96828c5ef..000000000000 --- a/tools/testing/selftests/drivers/net/dsa/lib.sh +++ /dev/null @@ -1 +0,0 @@ -../../../net/forwarding/lib.sh
\ No newline at end of file diff --git a/tools/testing/selftests/drivers/net/dsa/local_termination.sh b/tools/testing/selftests/drivers/net/dsa/local_termination.sh index c08166f84501..d16a65e7595d 120000 --- a/tools/testing/selftests/drivers/net/dsa/local_termination.sh +++ b/tools/testing/selftests/drivers/net/dsa/local_termination.sh @@ -1 +1 @@ -../../../net/forwarding/local_termination.sh
\ No newline at end of file +run_net_forwarding_test.sh
\ No newline at end of file diff --git a/tools/testing/selftests/drivers/net/dsa/no_forwarding.sh b/tools/testing/selftests/drivers/net/dsa/no_forwarding.sh index b9757466bc97..d16a65e7595d 120000 --- a/tools/testing/selftests/drivers/net/dsa/no_forwarding.sh +++ b/tools/testing/selftests/drivers/net/dsa/no_forwarding.sh @@ -1 +1 @@ -../../../net/forwarding/no_forwarding.sh
\ No newline at end of file +run_net_forwarding_test.sh
\ No newline at end of file diff --git a/tools/testing/selftests/drivers/net/dsa/run_net_forwarding_test.sh b/tools/testing/selftests/drivers/net/dsa/run_net_forwarding_test.sh new file mode 100755 index 000000000000..4106c0a102ea --- /dev/null +++ b/tools/testing/selftests/drivers/net/dsa/run_net_forwarding_test.sh @@ -0,0 +1,9 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +libdir=$(dirname "$(readlink -f "${BASH_SOURCE[0]}")") +testname=$(basename "${BASH_SOURCE[0]}") + +source "$libdir"/forwarding.config +cd "$libdir"/../../../net/forwarding/ || exit 1 +source "./$testname" "$@" diff --git a/tools/testing/selftests/drivers/net/dsa/tc_actions.sh b/tools/testing/selftests/drivers/net/dsa/tc_actions.sh index 306213d9430e..d16a65e7595d 120000 --- a/tools/testing/selftests/drivers/net/dsa/tc_actions.sh +++ b/tools/testing/selftests/drivers/net/dsa/tc_actions.sh @@ -1 +1 @@ -../../../net/forwarding/tc_actions.sh
\ No newline at end of file +run_net_forwarding_test.sh
\ No newline at end of file diff --git a/tools/testing/selftests/drivers/net/dsa/tc_common.sh b/tools/testing/selftests/drivers/net/dsa/tc_common.sh deleted file mode 120000 index bc3465bdc36b..000000000000 --- a/tools/testing/selftests/drivers/net/dsa/tc_common.sh +++ /dev/null @@ -1 +0,0 @@ -../../../net/forwarding/tc_common.sh
\ No newline at end of file diff --git a/tools/testing/selftests/drivers/net/dsa/test_bridge_fdb_stress.sh b/tools/testing/selftests/drivers/net/dsa/test_bridge_fdb_stress.sh index 92acab83fbe2..74682151d04d 100755 --- a/tools/testing/selftests/drivers/net/dsa/test_bridge_fdb_stress.sh +++ b/tools/testing/selftests/drivers/net/dsa/test_bridge_fdb_stress.sh @@ -19,7 +19,7 @@ REQUIRE_JQ="no" REQUIRE_MZ="no" NETIF_CREATE="no" lib_dir=$(dirname "$0") -source "$lib_dir"/lib.sh +source "$lib_dir"/../../../net/forwarding/lib.sh cleanup() { echo "Cleaning up" diff --git a/tools/testing/selftests/drivers/net/netdevsim/Makefile b/tools/testing/selftests/drivers/net/netdevsim/Makefile new file mode 100644 index 000000000000..7a29a05bea8b --- /dev/null +++ b/tools/testing/selftests/drivers/net/netdevsim/Makefile @@ -0,0 +1,17 @@ +# SPDX-License-Identifier: GPL-2.0+ OR MIT + +TEST_PROGS = devlink.sh \ + devlink_in_netns.sh \ + devlink_trap.sh \ + ethtool-coalesce.sh \ + ethtool-fec.sh \ + ethtool-pause.sh \ + ethtool-ring.sh \ + fib.sh \ + hw_stats_l3.sh \ + nexthop.sh \ + psample.sh \ + tc-mq-visibility.sh \ + udp_tunnel_nic.sh \ + +include ../../../lib.mk diff --git a/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh index f98435c502f6..384cfa3d38a6 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh @@ -270,7 +270,7 @@ for port in 0 1; do echo 1 > $NSIM_DEV_SYS/new_port fi NSIM_NETDEV=`get_netdev_name old_netdevs` - ifconfig $NSIM_NETDEV up + ip link set dev $NSIM_NETDEV up msg="new NIC device created" exp0=( 0 0 0 0 ) @@ -284,8 +284,8 @@ for port in 0 1; do msg="VxLAN v4 devices go down" exp0=( 0 0 0 0 ) - ifconfig vxlan1 down - ifconfig vxlan0 down + ip link set dev vxlan1 down + ip link set dev vxlan0 down check_tables msg="VxLAN v6 devices" @@ -293,7 +293,7 @@ for port in 0 1; do new_vxlan vxlanA 4789 $NSIM_NETDEV 6 for ifc in vxlan0 vxlan1; do - ifconfig $ifc up + ip link set dev $ifc up done new_vxlan vxlanB 4789 $NSIM_NETDEV 6 @@ -307,14 +307,14 @@ for port in 0 1; do new_geneve gnv0 6081 msg="NIC device goes down" - ifconfig $NSIM_NETDEV down + ip link set dev $NSIM_NETDEV down if [ $port -eq 1 ]; then exp0=( 0 0 0 0 ) exp1=( 0 0 0 0 ) fi check_tables msg="NIC device goes up again" - ifconfig $NSIM_NETDEV up + ip link set dev $NSIM_NETDEV up exp0=( `mke 4789 1` `mke 4790 1` 0 0 ) exp1=( `mke 6081 2` 0 0 0 ) check_tables @@ -433,7 +433,7 @@ for port in 0 1; do echo $port > $NSIM_DEV_SYS/new_port NSIM_NETDEV=`get_netdev_name old_netdevs` - ifconfig $NSIM_NETDEV up + ip link set dev $NSIM_NETDEV up overflow_table0 "overflow NIC table" overflow_table1 "overflow NIC table" @@ -491,7 +491,7 @@ for port in 0 1; do echo $port > $NSIM_DEV_SYS/new_port NSIM_NETDEV=`get_netdev_name old_netdevs` - ifconfig $NSIM_NETDEV up + ip link set dev $NSIM_NETDEV up overflow_table0 "overflow NIC table" overflow_table1 "overflow NIC table" @@ -548,7 +548,7 @@ for port in 0 1; do echo $port > $NSIM_DEV_SYS/new_port NSIM_NETDEV=`get_netdev_name old_netdevs` - ifconfig $NSIM_NETDEV up + ip link set dev $NSIM_NETDEV up overflow_table0 "destroy NIC" overflow_table1 "destroy NIC" @@ -578,7 +578,7 @@ for port in 0 1; do echo $port > $NSIM_DEV_SYS/new_port NSIM_NETDEV=`get_netdev_name old_netdevs` - ifconfig $NSIM_NETDEV up + ip link set dev $NSIM_NETDEV up msg="create VxLANs v6" new_vxlan vxlanA0 10000 $NSIM_NETDEV 6 @@ -639,7 +639,7 @@ for port in 0 1; do echo $port > $NSIM_DEV_SYS/new_port NSIM_NETDEV=`get_netdev_name old_netdevs` - ifconfig $NSIM_NETDEV up + ip link set dev $NSIM_NETDEV up echo 110 > $NSIM_DEV_DFS/ports/$port/udp_ports_inject_error @@ -695,7 +695,7 @@ for port in 0 1; do echo $port > $NSIM_DEV_SYS/new_port NSIM_NETDEV=`get_netdev_name old_netdevs` - ifconfig $NSIM_NETDEV up + ip link set dev $NSIM_NETDEV up msg="create VxLANs v6" exp0=( `mke 10000 1` 0 0 0 ) @@ -755,7 +755,7 @@ for port in 0 1; do echo $port > $NSIM_DEV_SYS/new_port NSIM_NETDEV=`get_netdev_name old_netdevs` - ifconfig $NSIM_NETDEV up + ip link set dev $NSIM_NETDEV up msg="create VxLANs v6" exp0=( `mke 10000 1` 0 0 0 ) @@ -768,7 +768,7 @@ for port in 0 1; do check_tables msg="NIC device goes down" - ifconfig $NSIM_NETDEV down + ip link set dev $NSIM_NETDEV down if [ $port -eq 1 ]; then exp0=( 0 0 0 0 ) exp1=( 0 0 0 0 ) @@ -779,7 +779,7 @@ for port in 0 1; do check_tables msg="NIC device goes up again" - ifconfig $NSIM_NETDEV up + ip link set dev $NSIM_NETDEV up exp0=( `mke 10000 1` 0 0 0 ) check_tables @@ -827,12 +827,12 @@ new_vxlan vxlan1 4789 $NSIM_NETDEV2 msg="VxLAN v4 devices go down" exp0=( 0 0 0 0 ) -ifconfig vxlan1 down -ifconfig vxlan0 down +ip link set dev vxlan1 down +ip link set dev vxlan0 down check_tables for ifc in vxlan0 vxlan1; do - ifconfig $ifc up + ip link set dev $ifc up done msg="VxLAN v6 device" @@ -844,11 +844,11 @@ exp1=( `mke 6081 2` 0 0 0 ) new_geneve gnv0 6081 msg="NIC device goes down" -ifconfig $NSIM_NETDEV down +ip link set dev $NSIM_NETDEV down check_tables msg="NIC device goes up again" -ifconfig $NSIM_NETDEV up +ip link set dev $NSIM_NETDEV up check_tables for i in `seq 2`; do diff --git a/tools/testing/selftests/drivers/net/team/Makefile b/tools/testing/selftests/drivers/net/team/Makefile index 6a86e61e8bfe..2d5a76d99181 100644 --- a/tools/testing/selftests/drivers/net/team/Makefile +++ b/tools/testing/selftests/drivers/net/team/Makefile @@ -3,8 +3,9 @@ TEST_PROGS := dev_addr_lists.sh -TEST_FILES := \ - lag_lib.sh \ - net_forwarding_lib.sh +TEST_INCLUDES := \ + ../bonding/lag_lib.sh \ + ../../../net/forwarding/lib.sh \ + ../../../net/lib.sh include ../../../lib.mk diff --git a/tools/testing/selftests/drivers/net/team/config b/tools/testing/selftests/drivers/net/team/config index 265b6882cc21..b5e3a3aad4bf 100644 --- a/tools/testing/selftests/drivers/net/team/config +++ b/tools/testing/selftests/drivers/net/team/config @@ -1,3 +1,5 @@ +CONFIG_DUMMY=y +CONFIG_IPV6=y +CONFIG_MACVLAN=y CONFIG_NET_TEAM=y CONFIG_NET_TEAM_MODE_LOADBALANCE=y -CONFIG_MACVLAN=y diff --git a/tools/testing/selftests/drivers/net/team/dev_addr_lists.sh b/tools/testing/selftests/drivers/net/team/dev_addr_lists.sh index 33913112d5ca..b1ec7755b783 100755 --- a/tools/testing/selftests/drivers/net/team/dev_addr_lists.sh +++ b/tools/testing/selftests/drivers/net/team/dev_addr_lists.sh @@ -11,9 +11,9 @@ ALL_TESTS=" REQUIRE_MZ=no NUM_NETIFS=0 lib_dir=$(dirname "$0") -source "$lib_dir"/net_forwarding_lib.sh +source "$lib_dir"/../../../net/forwarding/lib.sh -source "$lib_dir"/lag_lib.sh +source "$lib_dir"/../bonding/lag_lib.sh destroy() diff --git a/tools/testing/selftests/drivers/net/team/lag_lib.sh b/tools/testing/selftests/drivers/net/team/lag_lib.sh deleted file mode 120000 index e1347a10afde..000000000000 --- a/tools/testing/selftests/drivers/net/team/lag_lib.sh +++ /dev/null @@ -1 +0,0 @@ -../bonding/lag_lib.sh
\ No newline at end of file diff --git a/tools/testing/selftests/drivers/net/team/net_forwarding_lib.sh b/tools/testing/selftests/drivers/net/team/net_forwarding_lib.sh deleted file mode 120000 index 39c96828c5ef..000000000000 --- a/tools/testing/selftests/drivers/net/team/net_forwarding_lib.sh +++ /dev/null @@ -1 +0,0 @@ -../../../net/forwarding/lib.sh
\ No newline at end of file diff --git a/tools/testing/selftests/dt/test_unprobed_devices.sh b/tools/testing/selftests/dt/test_unprobed_devices.sh index b07af2a4c4de..7fae90293a9d 100755 --- a/tools/testing/selftests/dt/test_unprobed_devices.sh +++ b/tools/testing/selftests/dt/test_unprobed_devices.sh @@ -33,8 +33,8 @@ if [[ ! -d "${PDT}" ]]; then fi nodes_compatible=$( - for node_compat in $(find ${PDT} -name compatible); do - node=$(dirname "${node_compat}") + for node in $(find ${PDT} -type d); do + [ ! -f "${node}"/compatible ] && continue # Check if node is available if [[ -e "${node}"/status ]]; then status=$(tr -d '\000' < "${node}"/status) @@ -46,10 +46,11 @@ nodes_compatible=$( nodes_dev_bound=$( IFS=$'\n' - for uevent in $(find /sys/devices -name uevent); do - if [[ -d "$(dirname "${uevent}")"/driver ]]; then - grep '^OF_FULLNAME=' "${uevent}" | sed -e 's|OF_FULLNAME=||' - fi + for dev_dir in $(find /sys/devices -type d); do + [ ! -f "${dev_dir}"/uevent ] && continue + [ ! -d "${dev_dir}"/driver ] && continue + + grep '^OF_FULLNAME=' "${dev_dir}"/uevent | sed -e 's|OF_FULLNAME=||' done ) diff --git a/tools/testing/selftests/hid/tests/test_wacom_generic.py b/tools/testing/selftests/hid/tests/test_wacom_generic.py index 352fc39f3c6c..b62c7dba6777 100644 --- a/tools/testing/selftests/hid/tests/test_wacom_generic.py +++ b/tools/testing/selftests/hid/tests/test_wacom_generic.py @@ -880,8 +880,8 @@ class TestDTH2452Tablet(test_multitouch.BaseTest.TestMultitouch, TouchTabletTest does not overlap with other contacts. The value of `t` may be incremented over time to move the point along a linear path. """ - x = 50 + 10 * contact_id + t - y = 100 + 100 * contact_id + t + x = 50 + 10 * contact_id + t * 11 + y = 100 + 100 * contact_id + t * 11 return test_multitouch.Touch(contact_id, x, y) def make_contacts(self, n, t=0): @@ -902,8 +902,8 @@ class TestDTH2452Tablet(test_multitouch.BaseTest.TestMultitouch, TouchTabletTest tracking_id = contact_ids.tracking_id slot_num = contact_ids.slot_num - x = 50 + 10 * contact_id + t - y = 100 + 100 * contact_id + t + x = 50 + 10 * contact_id + t * 11 + y = 100 + 100 * contact_id + t * 11 # If the data isn't supposed to be stored in any slots, there is # nothing we can check for in the evdev stream. diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c index 6652108816db..4fd0f8951574 100644 --- a/tools/testing/selftests/kvm/riscv/get-reg-list.c +++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c @@ -49,15 +49,42 @@ bool filter_reg(__u64 reg) case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVPBMT: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBA: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBB: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBC: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBKB: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBKC: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBKX: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBS: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZFA: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZFH: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZFHMIN: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOM: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOZ: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICNTR: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICOND: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICSR: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZIFENCEI: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZIHINTNTL: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZIHINTPAUSE: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZIHPM: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKND: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKNE: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKNH: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKR: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKSED: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKSH: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKT: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVBB: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVBC: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVFH: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVFHMIN: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKB: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKG: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKNED: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKNHA: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKNHB: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKSED: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKSH: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKT: /* * Like ISA_EXT registers, SBI_EXT registers are only visible when the * host supports them and disabling them does not affect the visibility @@ -394,15 +421,42 @@ static const char *isa_ext_single_id_to_str(__u64 reg_off) KVM_ISA_EXT_ARR(SVPBMT), KVM_ISA_EXT_ARR(ZBA), KVM_ISA_EXT_ARR(ZBB), + KVM_ISA_EXT_ARR(ZBC), + KVM_ISA_EXT_ARR(ZBKB), + KVM_ISA_EXT_ARR(ZBKC), + KVM_ISA_EXT_ARR(ZBKX), KVM_ISA_EXT_ARR(ZBS), + KVM_ISA_EXT_ARR(ZFA), + KVM_ISA_EXT_ARR(ZFH), + KVM_ISA_EXT_ARR(ZFHMIN), KVM_ISA_EXT_ARR(ZICBOM), KVM_ISA_EXT_ARR(ZICBOZ), KVM_ISA_EXT_ARR(ZICNTR), KVM_ISA_EXT_ARR(ZICOND), KVM_ISA_EXT_ARR(ZICSR), KVM_ISA_EXT_ARR(ZIFENCEI), + KVM_ISA_EXT_ARR(ZIHINTNTL), KVM_ISA_EXT_ARR(ZIHINTPAUSE), KVM_ISA_EXT_ARR(ZIHPM), + KVM_ISA_EXT_ARR(ZKND), + KVM_ISA_EXT_ARR(ZKNE), + KVM_ISA_EXT_ARR(ZKNH), + KVM_ISA_EXT_ARR(ZKR), + KVM_ISA_EXT_ARR(ZKSED), + KVM_ISA_EXT_ARR(ZKSH), + KVM_ISA_EXT_ARR(ZKT), + KVM_ISA_EXT_ARR(ZVBB), + KVM_ISA_EXT_ARR(ZVBC), + KVM_ISA_EXT_ARR(ZVFH), + KVM_ISA_EXT_ARR(ZVFHMIN), + KVM_ISA_EXT_ARR(ZVKB), + KVM_ISA_EXT_ARR(ZVKG), + KVM_ISA_EXT_ARR(ZVKNED), + KVM_ISA_EXT_ARR(ZVKNHA), + KVM_ISA_EXT_ARR(ZVKNHB), + KVM_ISA_EXT_ARR(ZVKSED), + KVM_ISA_EXT_ARR(ZVKSH), + KVM_ISA_EXT_ARR(ZVKT), }; if (reg_off >= ARRAY_SIZE(kvm_isa_ext_reg_name)) @@ -888,15 +942,42 @@ KVM_ISA_EXT_SIMPLE_CONFIG(svnapot, SVNAPOT); KVM_ISA_EXT_SIMPLE_CONFIG(svpbmt, SVPBMT); KVM_ISA_EXT_SIMPLE_CONFIG(zba, ZBA); KVM_ISA_EXT_SIMPLE_CONFIG(zbb, ZBB); +KVM_ISA_EXT_SIMPLE_CONFIG(zbc, ZBC); +KVM_ISA_EXT_SIMPLE_CONFIG(zbkb, ZBKB); +KVM_ISA_EXT_SIMPLE_CONFIG(zbkc, ZBKC); +KVM_ISA_EXT_SIMPLE_CONFIG(zbkx, ZBKX); KVM_ISA_EXT_SIMPLE_CONFIG(zbs, ZBS); +KVM_ISA_EXT_SIMPLE_CONFIG(zfa, ZFA); +KVM_ISA_EXT_SIMPLE_CONFIG(zfh, ZFH); +KVM_ISA_EXT_SIMPLE_CONFIG(zfhmin, ZFHMIN); KVM_ISA_EXT_SUBLIST_CONFIG(zicbom, ZICBOM); KVM_ISA_EXT_SUBLIST_CONFIG(zicboz, ZICBOZ); KVM_ISA_EXT_SIMPLE_CONFIG(zicntr, ZICNTR); KVM_ISA_EXT_SIMPLE_CONFIG(zicond, ZICOND); KVM_ISA_EXT_SIMPLE_CONFIG(zicsr, ZICSR); KVM_ISA_EXT_SIMPLE_CONFIG(zifencei, ZIFENCEI); +KVM_ISA_EXT_SIMPLE_CONFIG(zihintntl, ZIHINTNTL); KVM_ISA_EXT_SIMPLE_CONFIG(zihintpause, ZIHINTPAUSE); KVM_ISA_EXT_SIMPLE_CONFIG(zihpm, ZIHPM); +KVM_ISA_EXT_SIMPLE_CONFIG(zknd, ZKND); +KVM_ISA_EXT_SIMPLE_CONFIG(zkne, ZKNE); +KVM_ISA_EXT_SIMPLE_CONFIG(zknh, ZKNH); +KVM_ISA_EXT_SIMPLE_CONFIG(zkr, ZKR); +KVM_ISA_EXT_SIMPLE_CONFIG(zksed, ZKSED); +KVM_ISA_EXT_SIMPLE_CONFIG(zksh, ZKSH); +KVM_ISA_EXT_SIMPLE_CONFIG(zkt, ZKT); +KVM_ISA_EXT_SIMPLE_CONFIG(zvbb, ZVBB); +KVM_ISA_EXT_SIMPLE_CONFIG(zvbc, ZVBC); +KVM_ISA_EXT_SIMPLE_CONFIG(zvfh, ZVFH); +KVM_ISA_EXT_SIMPLE_CONFIG(zvfhmin, ZVFHMIN); +KVM_ISA_EXT_SIMPLE_CONFIG(zvkb, ZVKB); +KVM_ISA_EXT_SIMPLE_CONFIG(zvkg, ZVKG); +KVM_ISA_EXT_SIMPLE_CONFIG(zvkned, ZVKNED); +KVM_ISA_EXT_SIMPLE_CONFIG(zvknha, ZVKNHA); +KVM_ISA_EXT_SIMPLE_CONFIG(zvknhb, ZVKNHB); +KVM_ISA_EXT_SIMPLE_CONFIG(zvksed, ZVKSED); +KVM_ISA_EXT_SIMPLE_CONFIG(zvksh, ZVKSH); +KVM_ISA_EXT_SIMPLE_CONFIG(zvkt, ZVKT); struct vcpu_reg_list *vcpu_configs[] = { &config_sbi_base, @@ -914,14 +995,41 @@ struct vcpu_reg_list *vcpu_configs[] = { &config_svpbmt, &config_zba, &config_zbb, + &config_zbc, + &config_zbkb, + &config_zbkc, + &config_zbkx, &config_zbs, + &config_zfa, + &config_zfh, + &config_zfhmin, &config_zicbom, &config_zicboz, &config_zicntr, &config_zicond, &config_zicsr, &config_zifencei, + &config_zihintntl, &config_zihintpause, &config_zihpm, + &config_zknd, + &config_zkne, + &config_zknh, + &config_zkr, + &config_zksed, + &config_zksh, + &config_zkt, + &config_zvbb, + &config_zvbc, + &config_zvfh, + &config_zvfhmin, + &config_zvkb, + &config_zvkg, + &config_zvkned, + &config_zvknha, + &config_zvknhb, + &config_zvksed, + &config_zvksh, + &config_zvkt, }; int vcpu_configs_n = ARRAY_SIZE(vcpu_configs); diff --git a/tools/testing/selftests/landlock/common.h b/tools/testing/selftests/landlock/common.h index 5b79758cae62..e64bbdf0e86e 100644 --- a/tools/testing/selftests/landlock/common.h +++ b/tools/testing/selftests/landlock/common.h @@ -9,6 +9,7 @@ #include <errno.h> #include <linux/landlock.h> +#include <linux/securebits.h> #include <sys/capability.h> #include <sys/socket.h> #include <sys/syscall.h> @@ -115,11 +116,16 @@ static void _init_caps(struct __test_metadata *const _metadata, bool drop_all) /* clang-format off */ CAP_DAC_OVERRIDE, CAP_MKNOD, + CAP_NET_ADMIN, + CAP_NET_BIND_SERVICE, CAP_SYS_ADMIN, CAP_SYS_CHROOT, - CAP_NET_BIND_SERVICE, /* clang-format on */ }; + const unsigned int noroot = SECBIT_NOROOT | SECBIT_NOROOT_LOCKED; + + if ((cap_get_secbits() & noroot) != noroot) + EXPECT_EQ(0, cap_set_secbits(noroot)); cap_p = cap_get_proc(); EXPECT_NE(NULL, cap_p) @@ -137,6 +143,8 @@ static void _init_caps(struct __test_metadata *const _metadata, bool drop_all) TH_LOG("Failed to cap_set_flag: %s", strerror(errno)); } } + + /* Automatically resets ambient capabilities. */ EXPECT_NE(-1, cap_set_proc(cap_p)) { TH_LOG("Failed to cap_set_proc: %s", strerror(errno)); @@ -145,6 +153,9 @@ static void _init_caps(struct __test_metadata *const _metadata, bool drop_all) { TH_LOG("Failed to cap_free: %s", strerror(errno)); } + + /* Quickly checks that ambient capabilities are cleared. */ + EXPECT_NE(-1, cap_get_ambient(caps[0])); } /* We cannot put such helpers in a library because of kselftest_harness.h . */ @@ -158,8 +169,9 @@ static void __maybe_unused drop_caps(struct __test_metadata *const _metadata) _init_caps(_metadata, true); } -static void _effective_cap(struct __test_metadata *const _metadata, - const cap_value_t caps, const cap_flag_value_t value) +static void _change_cap(struct __test_metadata *const _metadata, + const cap_flag_t flag, const cap_value_t cap, + const cap_flag_value_t value) { cap_t cap_p; @@ -168,7 +180,7 @@ static void _effective_cap(struct __test_metadata *const _metadata, { TH_LOG("Failed to cap_get_proc: %s", strerror(errno)); } - EXPECT_NE(-1, cap_set_flag(cap_p, CAP_EFFECTIVE, 1, &caps, value)) + EXPECT_NE(-1, cap_set_flag(cap_p, flag, 1, &cap, value)) { TH_LOG("Failed to cap_set_flag: %s", strerror(errno)); } @@ -183,15 +195,35 @@ static void _effective_cap(struct __test_metadata *const _metadata, } static void __maybe_unused set_cap(struct __test_metadata *const _metadata, - const cap_value_t caps) + const cap_value_t cap) { - _effective_cap(_metadata, caps, CAP_SET); + _change_cap(_metadata, CAP_EFFECTIVE, cap, CAP_SET); } static void __maybe_unused clear_cap(struct __test_metadata *const _metadata, - const cap_value_t caps) + const cap_value_t cap) +{ + _change_cap(_metadata, CAP_EFFECTIVE, cap, CAP_CLEAR); +} + +static void __maybe_unused +set_ambient_cap(struct __test_metadata *const _metadata, const cap_value_t cap) +{ + _change_cap(_metadata, CAP_INHERITABLE, cap, CAP_SET); + + EXPECT_NE(-1, cap_set_ambient(cap, CAP_SET)) + { + TH_LOG("Failed to set ambient capability %d: %s", cap, + strerror(errno)); + } +} + +static void __maybe_unused clear_ambient_cap( + struct __test_metadata *const _metadata, const cap_value_t cap) { - _effective_cap(_metadata, caps, CAP_CLEAR); + EXPECT_EQ(1, cap_get_ambient(cap)); + _change_cap(_metadata, CAP_INHERITABLE, cap, CAP_CLEAR); + EXPECT_EQ(0, cap_get_ambient(cap)); } /* Receives an FD from a UNIX socket. Returns the received FD, or -errno. */ diff --git a/tools/testing/selftests/landlock/fs_test.c b/tools/testing/selftests/landlock/fs_test.c index 50818904397c..2d6d9b43d958 100644 --- a/tools/testing/selftests/landlock/fs_test.c +++ b/tools/testing/selftests/landlock/fs_test.c @@ -241,9 +241,11 @@ struct mnt_opt { const char *const data; }; -const struct mnt_opt mnt_tmp = { +#define MNT_TMP_DATA "size=4m,mode=700" + +static const struct mnt_opt mnt_tmp = { .type = "tmpfs", - .data = "size=4m,mode=700", + .data = MNT_TMP_DATA, }; static int mount_opt(const struct mnt_opt *const mnt, const char *const target) @@ -4632,7 +4634,10 @@ FIXTURE_VARIANT(layout3_fs) /* clang-format off */ FIXTURE_VARIANT_ADD(layout3_fs, tmpfs) { /* clang-format on */ - .mnt = mnt_tmp, + .mnt = { + .type = "tmpfs", + .data = MNT_TMP_DATA, + }, .file_path = file1_s1d1, }; diff --git a/tools/testing/selftests/landlock/net_test.c b/tools/testing/selftests/landlock/net_test.c index ea5f727dd257..936cfc879f1d 100644 --- a/tools/testing/selftests/landlock/net_test.c +++ b/tools/testing/selftests/landlock/net_test.c @@ -17,6 +17,7 @@ #include <string.h> #include <sys/prctl.h> #include <sys/socket.h> +#include <sys/syscall.h> #include <sys/un.h> #include "common.h" @@ -54,6 +55,11 @@ struct service_fixture { }; }; +static pid_t sys_gettid(void) +{ + return syscall(__NR_gettid); +} + static int set_service(struct service_fixture *const srv, const struct protocol_variant prot, const unsigned short index) @@ -88,7 +94,7 @@ static int set_service(struct service_fixture *const srv, case AF_UNIX: srv->unix_addr.sun_family = prot.domain; sprintf(srv->unix_addr.sun_path, - "_selftests-landlock-net-tid%d-index%d", gettid(), + "_selftests-landlock-net-tid%d-index%d", sys_gettid(), index); srv->unix_addr_len = SUN_LEN(&srv->unix_addr); srv->unix_addr.sun_path[0] = '\0'; @@ -101,8 +107,11 @@ static void setup_loopback(struct __test_metadata *const _metadata) { set_cap(_metadata, CAP_SYS_ADMIN); ASSERT_EQ(0, unshare(CLONE_NEWNET)); - ASSERT_EQ(0, system("ip link set dev lo up")); clear_cap(_metadata, CAP_SYS_ADMIN); + + set_ambient_cap(_metadata, CAP_NET_ADMIN); + ASSERT_EQ(0, system("ip link set dev lo up")); + clear_ambient_cap(_metadata, CAP_NET_ADMIN); } static bool is_restricted(const struct protocol_variant *const prot, diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index aa646e0661f3..087fee22dd53 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -69,11 +69,29 @@ define RUN_TESTS run_many $(1) endef +define INSTALL_INCLUDES + $(if $(TEST_INCLUDES), \ + relative_files=""; \ + for entry in $(TEST_INCLUDES); do \ + entry_dir=$$(readlink -e "$$(dirname "$$entry")"); \ + entry_name=$$(basename "$$entry"); \ + relative_dir=$${entry_dir#"$$SRC_PATH"/}; \ + if [ "$$relative_dir" = "$$entry_dir" ]; then \ + echo "Error: TEST_INCLUDES entry \"$$entry\" not located inside selftests directory ($$SRC_PATH)" >&2; \ + exit 1; \ + fi; \ + relative_files="$$relative_files $$relative_dir/$$entry_name"; \ + done; \ + cd $(SRC_PATH) && rsync -aR $$relative_files $(OBJ_PATH)/ \ + ) +endef + run_tests: all ifdef building_out_of_srctree @if [ "X$(TEST_PROGS)$(TEST_PROGS_EXTENDED)$(TEST_FILES)" != "X" ]; then \ rsync -aq --copy-unsafe-links $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(OUTPUT); \ fi + @$(INSTALL_INCLUDES) @if [ "X$(TEST_PROGS)" != "X" ]; then \ $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) \ $(addprefix $(OUTPUT)/,$(TEST_PROGS))) ; \ @@ -103,6 +121,7 @@ endef install: all ifdef INSTALL_PATH $(INSTALL_RULE) + $(INSTALL_INCLUDES) else $(error Error: set INSTALL_PATH to use install) endif diff --git a/tools/testing/selftests/livepatch/functions.sh b/tools/testing/selftests/livepatch/functions.sh index c8416c54b463..b1fd7362c2fe 100644 --- a/tools/testing/selftests/livepatch/functions.sh +++ b/tools/testing/selftests/livepatch/functions.sh @@ -42,17 +42,6 @@ function die() { exit 1 } -# save existing dmesg so we can detect new content -function save_dmesg() { - SAVED_DMESG=$(mktemp --tmpdir -t klp-dmesg-XXXXXX) - dmesg > "$SAVED_DMESG" -} - -# cleanup temporary dmesg file from save_dmesg() -function cleanup_dmesg_file() { - rm -f "$SAVED_DMESG" -} - function push_config() { DYNAMIC_DEBUG=$(grep '^kernel/livepatch' /sys/kernel/debug/dynamic_debug/control | \ awk -F'[: ]' '{print "file " $1 " line " $2 " " $4}') @@ -99,7 +88,6 @@ function set_ftrace_enabled() { function cleanup() { pop_config - cleanup_dmesg_file } # setup_config - save the current config and set a script exit trap that @@ -280,7 +268,15 @@ function set_pre_patch_ret { function start_test { local test="$1" - save_dmesg + # Dump something unique into the dmesg log, then stash the entry + # in LAST_DMESG. The check_result() function will use it to + # find new kernel messages since the test started. + local last_dmesg_msg="livepatch kselftest timestamp: $(date --rfc-3339=ns)" + log "$last_dmesg_msg" + loop_until 'dmesg | grep -q "$last_dmesg_msg"' || + die "buffer busy? can't find canary dmesg message: $last_dmesg_msg" + LAST_DMESG=$(dmesg | grep "$last_dmesg_msg") + echo -n "TEST: $test ... " log "===== TEST: $test =====" } @@ -291,23 +287,24 @@ function check_result { local expect="$*" local result - # Note: when comparing dmesg output, the kernel log timestamps - # help differentiate repeated testing runs. Remove them with a - # post-comparison sed filter. - - result=$(dmesg | comm --nocheck-order -13 "$SAVED_DMESG" - | \ + # Test results include any new dmesg entry since LAST_DMESG, then: + # - include lines matching keywords + # - exclude lines matching keywords + # - filter out dmesg timestamp prefixes + result=$(dmesg | awk -v last_dmesg="$LAST_DMESG" 'p; $0 == last_dmesg { p=1 }' | \ grep -e 'livepatch:' -e 'test_klp' | \ grep -v '\(tainting\|taints\) kernel' | \ sed 's/^\[[ 0-9.]*\] //') if [[ "$expect" == "$result" ]] ; then echo "ok" + elif [[ "$result" == "" ]] ; then + echo -e "not ok\n\nbuffer overrun? can't find canary dmesg entry: $LAST_DMESG\n" + die "livepatch kselftest(s) failed" else echo -e "not ok\n\n$(diff -upr --label expected --label result <(echo "$expect") <(echo "$result"))\n" die "livepatch kselftest(s) failed" fi - - cleanup_dmesg_file } # check_sysfs_rights(modname, rel_path, expected_rights) - check sysfs diff --git a/tools/testing/selftests/mm/charge_reserved_hugetlb.sh b/tools/testing/selftests/mm/charge_reserved_hugetlb.sh index 0899019a7fcb..e14bdd4455f2 100755 --- a/tools/testing/selftests/mm/charge_reserved_hugetlb.sh +++ b/tools/testing/selftests/mm/charge_reserved_hugetlb.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # SPDX-License-Identifier: GPL-2.0 # Kselftest framework requirement - SKIP code is 4. diff --git a/tools/testing/selftests/mm/ksm_tests.c b/tools/testing/selftests/mm/ksm_tests.c index 380b691d3eb9..b748c48908d9 100644 --- a/tools/testing/selftests/mm/ksm_tests.c +++ b/tools/testing/selftests/mm/ksm_tests.c @@ -566,7 +566,7 @@ static int ksm_merge_hugepages_time(int merge_type, int mapping, int prot, if (map_ptr_orig == MAP_FAILED) err(2, "initial mmap"); - if (madvise(map_ptr, len + HPAGE_SIZE, MADV_HUGEPAGE)) + if (madvise(map_ptr, len, MADV_HUGEPAGE)) err(2, "MADV_HUGEPAGE"); pagemap_fd = open("/proc/self/pagemap", O_RDONLY); diff --git a/tools/testing/selftests/mm/map_hugetlb.c b/tools/testing/selftests/mm/map_hugetlb.c index 193281560b61..86e8f2048a40 100644 --- a/tools/testing/selftests/mm/map_hugetlb.c +++ b/tools/testing/selftests/mm/map_hugetlb.c @@ -15,6 +15,7 @@ #include <unistd.h> #include <sys/mman.h> #include <fcntl.h> +#include "vm_util.h" #define LENGTH (256UL*1024*1024) #define PROTECTION (PROT_READ | PROT_WRITE) @@ -58,10 +59,16 @@ int main(int argc, char **argv) { void *addr; int ret; + size_t hugepage_size; size_t length = LENGTH; int flags = FLAGS; int shift = 0; + hugepage_size = default_huge_page_size(); + /* munmap with fail if the length is not page aligned */ + if (hugepage_size > length) + length = hugepage_size; + if (argc > 1) length = atol(argv[1]) << 20; if (argc > 2) { diff --git a/tools/testing/selftests/mm/mremap_test.c b/tools/testing/selftests/mm/mremap_test.c index 1d4c1589c305..2f8b991f78cb 100644 --- a/tools/testing/selftests/mm/mremap_test.c +++ b/tools/testing/selftests/mm/mremap_test.c @@ -360,7 +360,8 @@ static long long remap_region(struct config c, unsigned int threshold_mb, char pattern_seed) { void *addr, *src_addr, *dest_addr, *dest_preamble_addr; - unsigned long long i; + int d; + unsigned long long t; struct timespec t_start = {0, 0}, t_end = {0, 0}; long long start_ns, end_ns, align_mask, ret, offset; unsigned long long threshold; @@ -378,8 +379,8 @@ static long long remap_region(struct config c, unsigned int threshold_mb, /* Set byte pattern for source block. */ srand(pattern_seed); - for (i = 0; i < threshold; i++) - memset((char *) src_addr + i, (char) rand(), 1); + for (t = 0; t < threshold; t++) + memset((char *) src_addr + t, (char) rand(), 1); /* Mask to zero out lower bits of address for alignment */ align_mask = ~(c.dest_alignment - 1); @@ -420,8 +421,8 @@ static long long remap_region(struct config c, unsigned int threshold_mb, /* Set byte pattern for the dest preamble block. */ srand(pattern_seed); - for (i = 0; i < c.dest_preamble_size; i++) - memset((char *) dest_preamble_addr + i, (char) rand(), 1); + for (d = 0; d < c.dest_preamble_size; d++) + memset((char *) dest_preamble_addr + d, (char) rand(), 1); } clock_gettime(CLOCK_MONOTONIC, &t_start); @@ -437,14 +438,14 @@ static long long remap_region(struct config c, unsigned int threshold_mb, /* Verify byte pattern after remapping */ srand(pattern_seed); - for (i = 0; i < threshold; i++) { + for (t = 0; t < threshold; t++) { char c = (char) rand(); - if (((char *) dest_addr)[i] != c) { + if (((char *) dest_addr)[t] != c) { ksft_print_msg("Data after remap doesn't match at offset %llu\n", - i); + t); ksft_print_msg("Expected: %#x\t Got: %#x\n", c & 0xff, - ((char *) dest_addr)[i] & 0xff); + ((char *) dest_addr)[t] & 0xff); ret = -1; goto clean_up_dest; } @@ -453,14 +454,14 @@ static long long remap_region(struct config c, unsigned int threshold_mb, /* Verify the dest preamble byte pattern after remapping */ if (c.dest_preamble_size) { srand(pattern_seed); - for (i = 0; i < c.dest_preamble_size; i++) { + for (d = 0; d < c.dest_preamble_size; d++) { char c = (char) rand(); - if (((char *) dest_preamble_addr)[i] != c) { + if (((char *) dest_preamble_addr)[d] != c) { ksft_print_msg("Preamble data after remap doesn't match at offset %d\n", - i); + d); ksft_print_msg("Expected: %#x\t Got: %#x\n", c & 0xff, - ((char *) dest_preamble_addr)[i] & 0xff); + ((char *) dest_preamble_addr)[d] & 0xff); ret = -1; goto clean_up_dest; } diff --git a/tools/testing/selftests/mm/va_high_addr_switch.sh b/tools/testing/selftests/mm/va_high_addr_switch.sh index 45cae7cab27e..a0a75f302904 100755 --- a/tools/testing/selftests/mm/va_high_addr_switch.sh +++ b/tools/testing/selftests/mm/va_high_addr_switch.sh @@ -29,9 +29,15 @@ check_supported_x86_64() # See man 1 gzip under '-f'. local pg_table_levels=$(gzip -dcfq "${config}" | grep PGTABLE_LEVELS | cut -d'=' -f 2) + local cpu_supports_pl5=$(awk '/^flags/ {if (/la57/) {print 0;} + else {print 1}; exit}' /proc/cpuinfo 2>/dev/null) + if [[ "${pg_table_levels}" -lt 5 ]]; then echo "$0: PGTABLE_LEVELS=${pg_table_levels}, must be >= 5 to run this test" exit $ksft_skip + elif [[ "${cpu_supports_pl5}" -ne 0 ]]; then + echo "$0: CPU does not have the necessary la57 flag to support page table level 5" + exit $ksft_skip fi } diff --git a/tools/testing/selftests/mm/write_hugetlb_memory.sh b/tools/testing/selftests/mm/write_hugetlb_memory.sh index 70a02301f4c2..3d2d2eb9d6ff 100755 --- a/tools/testing/selftests/mm/write_hugetlb_memory.sh +++ b/tools/testing/selftests/mm/write_hugetlb_memory.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # SPDX-License-Identifier: GPL-2.0 set -e diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 50818075e566..7b6918d5f4af 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -53,8 +53,7 @@ TEST_PROGS += bind_bhash.sh TEST_PROGS += ip_local_port_range.sh TEST_PROGS += rps_default_mask.sh TEST_PROGS += big_tcp.sh -TEST_PROGS_EXTENDED := in_netns.sh setup_loopback.sh setup_veth.sh -TEST_PROGS_EXTENDED += toeplitz_client.sh toeplitz.sh lib.sh +TEST_PROGS_EXTENDED := toeplitz_client.sh toeplitz.sh TEST_GEN_FILES = socket nettest TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any TEST_GEN_FILES += tcp_mmap tcp_inq psock_snd txring_overwrite @@ -84,6 +83,7 @@ TEST_PROGS += sctp_vrf.sh TEST_GEN_FILES += sctp_hello TEST_GEN_FILES += csum TEST_GEN_FILES += nat6to4.o +TEST_GEN_FILES += xdp_dummy.o TEST_GEN_FILES += ip_local_port_range TEST_GEN_FILES += bind_wildcard TEST_PROGS += test_vxlan_mdb.sh @@ -95,6 +95,9 @@ TEST_PROGS += fq_band_pktlimit.sh TEST_PROGS += vlan_hw_filter.sh TEST_FILES := settings +TEST_FILES += in_netns.sh lib.sh net_helper.sh setup_loopback.sh setup_veth.sh + +TEST_INCLUDES := forwarding/lib.sh include ../lib.mk @@ -104,7 +107,7 @@ $(OUTPUT)/tcp_inq: LDLIBS += -lpthread $(OUTPUT)/bind_bhash: LDLIBS += -lpthread $(OUTPUT)/io_uring_zerocopy_tx: CFLAGS += -I../../../include/ -# Rules to generate bpf obj nat6to4.o +# Rules to generate bpf objs CLANG ?= clang SCRATCH_DIR := $(OUTPUT)/tools BUILD_DIR := $(SCRATCH_DIR)/build @@ -139,7 +142,7 @@ endif CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG),$(CLANG_TARGET_ARCH)) -$(OUTPUT)/nat6to4.o: nat6to4.c $(BPFOBJ) | $(MAKE_DIRS) +$(OUTPUT)/nat6to4.o $(OUTPUT)/xdp_dummy.o: $(OUTPUT)/%.o : %.c $(BPFOBJ) | $(MAKE_DIRS) $(CLANG) -O2 --target=bpf -c $< $(CCINCLUDE) $(CLANG_SYS_INCLUDES) -o $@ $(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile) \ diff --git a/tools/testing/selftests/net/big_tcp.sh b/tools/testing/selftests/net/big_tcp.sh index cde9a91c4797..2db9d15cd45f 100755 --- a/tools/testing/selftests/net/big_tcp.sh +++ b/tools/testing/selftests/net/big_tcp.sh @@ -122,7 +122,9 @@ do_netperf() { local netns=$1 [ "$NF" = "6" ] && serip=$SERVER_IP6 - ip net exec $netns netperf -$NF -t TCP_STREAM -H $serip 2>&1 >/dev/null + + # use large write to be sure to generate big tcp packets + ip net exec $netns netperf -$NF -t TCP_STREAM -l 1 -H $serip -- -m 262144 2>&1 >/dev/null } do_test() { diff --git a/tools/testing/selftests/net/cmsg_ipv6.sh b/tools/testing/selftests/net/cmsg_ipv6.sh index f30bd57d5e38..8bc23fb4c82b 100755 --- a/tools/testing/selftests/net/cmsg_ipv6.sh +++ b/tools/testing/selftests/net/cmsg_ipv6.sh @@ -89,7 +89,7 @@ for ovr in setsock cmsg both diff; do check_result $? 0 "TCLASS $prot $ovr - pass" while [ -d /proc/$BG ]; do - $NSEXE ./cmsg_sender -6 -p u $TGT6 1234 + $NSEXE ./cmsg_sender -6 -p $p $m $((TOS2)) $TGT6 1234 done tcpdump -r $TMPF -v 2>&1 | grep "class $TOS2" >> /dev/null @@ -126,7 +126,7 @@ for ovr in setsock cmsg both diff; do check_result $? 0 "HOPLIMIT $prot $ovr - pass" while [ -d /proc/$BG ]; do - $NSEXE ./cmsg_sender -6 -p u $TGT6 1234 + $NSEXE ./cmsg_sender -6 -p $p $m $LIM $TGT6 1234 done tcpdump -r $TMPF -v 2>&1 | grep "hlim $LIM[^0-9]" >> /dev/null diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index 19ff75051660..5e4390cac17e 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -19,17 +19,27 @@ CONFIG_BRIDGE_VLAN_FILTERING=y CONFIG_BRIDGE=y CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_VLAN_8021Q=y +CONFIG_GENEVE=m CONFIG_IFB=y CONFIG_INET_DIAG=y +CONFIG_INET_ESP=y +CONFIG_INET_ESP_OFFLOAD=y +CONFIG_NET_FOU=y +CONFIG_NET_FOU_IP_TUNNELS=y CONFIG_IP_GRE=m CONFIG_NETFILTER=y CONFIG_NETFILTER_ADVANCED=y CONFIG_NF_CONNTRACK=m +CONFIG_IPV6_SIT=y +CONFIG_IP_DCCP=m CONFIG_NF_NAT=m CONFIG_IP6_NF_IPTABLES=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP6_NF_NAT=m +CONFIG_IP6_NF_RAW=m CONFIG_IP_NF_NAT=m +CONFIG_IP_NF_RAW=m +CONFIG_IP_NF_TARGET_TTL=m CONFIG_IPV6_GRE=m CONFIG_IPV6_SEG6_LWTUNNEL=y CONFIG_L2TP_ETH=m @@ -45,16 +55,26 @@ CONFIG_NF_TABLES=m CONFIG_NF_TABLES_IPV6=y CONFIG_NF_TABLES_IPV4=y CONFIG_NFT_NAT=m +CONFIG_NETFILTER_XT_MATCH_LENGTH=m +CONFIG_NET_ACT_CSUM=m +CONFIG_NET_ACT_CT=m CONFIG_NET_ACT_GACT=m +CONFIG_NET_ACT_PEDIT=m CONFIG_NET_CLS_BASIC=m +CONFIG_NET_CLS_BPF=m +CONFIG_NET_CLS_MATCHALL=m CONFIG_NET_CLS_U32=m CONFIG_NET_IPGRE_DEMUX=m CONFIG_NET_IPGRE=m +CONFIG_NET_IPIP=y CONFIG_NET_SCH_FQ_CODEL=m CONFIG_NET_SCH_HTB=m CONFIG_NET_SCH_FQ=m CONFIG_NET_SCH_ETF=m CONFIG_NET_SCH_NETEM=y +CONFIG_NET_SCH_PRIO=m +CONFIG_NFT_COMPAT=m +CONFIG_NF_FLOW_TABLE=m CONFIG_PSAMPLE=m CONFIG_TCP_MD5SIG=y CONFIG_TEST_BLACKHOLE_DEV=m @@ -63,7 +83,6 @@ CONFIG_TLS=m CONFIG_TRACEPOINTS=y CONFIG_NET_DROP_MONITOR=m CONFIG_NETDEVSIM=m -CONFIG_NET_FOU=m CONFIG_MPLS_ROUTING=m CONFIG_MPLS_IPTUNNEL=m CONFIG_NET_SCH_INGRESS=m @@ -80,3 +99,4 @@ CONFIG_IP_SCTP=m CONFIG_NETFILTER_XT_MATCH_POLICY=m CONFIG_CRYPTO_ARIA=y CONFIG_XFRM_INTERFACE=m +CONFIG_XFRM_USER=m diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index d7cfb7c2b427..386ebd829df5 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -100,6 +100,7 @@ log_test() local rc=$1 local expected=$2 local msg="$3" + local ans [ "${VERBOSE}" = "1" ] && echo @@ -113,16 +114,16 @@ log_test() if [ "${PAUSE_ON_FAIL}" = "yes" ]; then echo echo "hit enter to continue, 'q' to quit" - read a - [ "$a" = "q" ] && exit 1 + read ans + [ "$ans" = "q" ] && exit 1 fi fi if [ "${PAUSE}" = "yes" ]; then echo echo "hit enter to continue, 'q' to quit" - read a - [ "$a" = "q" ] && exit 1 + read ans + [ "$ans" = "q" ] && exit 1 fi kill_procs diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index b3ecccbbfcd2..3ec1050e47a2 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -743,6 +743,43 @@ fib_notify_test() cleanup &> /dev/null } +# Create a new dummy_10 to remove all associated routes. +reset_dummy_10() +{ + $IP link del dev dummy_10 + + $IP link add dummy_10 type dummy + $IP link set dev dummy_10 up + $IP -6 address add 2001:10::1/64 dev dummy_10 +} + +check_rt_num() +{ + local expected=$1 + local num=$2 + + if [ $num -ne $expected ]; then + echo "FAIL: Expected $expected routes, got $num" + ret=1 + else + ret=0 + fi +} + +check_rt_num_clean() +{ + local expected=$1 + local num=$2 + + if [ $num -ne $expected ]; then + log_test 1 0 "expected $expected routes, got $num" + set +e + cleanup &> /dev/null + return 1 + fi + return 0 +} + fib6_gc_test() { setup @@ -751,7 +788,7 @@ fib6_gc_test() echo "Fib6 garbage collection test" set -e - EXPIRE=3 + EXPIRE=5 # Check expiration of routes every $EXPIRE seconds (GC) $NS_EXEC sysctl -wq net.ipv6.route.gc_interval=$EXPIRE @@ -763,44 +800,114 @@ fib6_gc_test() $NS_EXEC sysctl -wq net.ipv6.route.flush=1 # Temporary routes - for i in $(seq 1 1000); do + for i in $(seq 1 5); do # Expire route after $EXPIRE seconds $IP -6 route add 2001:20::$i \ via 2001:10::2 dev dummy_10 expires $EXPIRE done - sleep $(($EXPIRE * 2)) - N_EXP_SLEEP=$($IP -6 route list |grep expires|wc -l) - if [ $N_EXP_SLEEP -ne 0 ]; then - echo "FAIL: expected 0 routes with expires, got $N_EXP_SLEEP" - ret=1 - else - ret=0 - fi + sleep $(($EXPIRE * 2 + 1)) + $NS_EXEC sysctl -wq net.ipv6.route.flush=1 + check_rt_num 0 $($IP -6 route list |grep expires|wc -l) + log_test $ret 0 "ipv6 route garbage collection" + + reset_dummy_10 # Permanent routes - for i in $(seq 1 5000); do + for i in $(seq 1 5); do $IP -6 route add 2001:30::$i \ via 2001:10::2 dev dummy_10 done # Temporary routes - for i in $(seq 1 1000); do + for i in $(seq 1 5); do # Expire route after $EXPIRE seconds $IP -6 route add 2001:20::$i \ via 2001:10::2 dev dummy_10 expires $EXPIRE done - sleep $(($EXPIRE * 2)) - N_EXP_SLEEP=$($IP -6 route list |grep expires|wc -l) - if [ $N_EXP_SLEEP -ne 0 ]; then - echo "FAIL: expected 0 routes with expires," \ - "got $N_EXP_SLEEP (5000 permanent routes)" - ret=1 - else - ret=0 + sleep $(($EXPIRE * 2 + 1)) + check_rt_num 0 $($IP -6 route list |grep expires|wc -l) + log_test $ret 0 "ipv6 route garbage collection (with permanent routes)" + + reset_dummy_10 + + # Permanent routes + for i in $(seq 1 5); do + $IP -6 route add 2001:20::$i \ + via 2001:10::2 dev dummy_10 + done + # Replace with temporary routes + for i in $(seq 1 5); do + # Expire route after $EXPIRE seconds + $IP -6 route replace 2001:20::$i \ + via 2001:10::2 dev dummy_10 expires $EXPIRE + done + check_rt_num_clean 5 $($IP -6 route list |grep expires|wc -l) || return + # Wait for GC + sleep $(($EXPIRE * 2 + 1)) + $NS_EXEC sysctl -wq net.ipv6.route.flush=1 + check_rt_num 0 $($IP -6 route list |grep expires|wc -l) + log_test $ret 0 "ipv6 route garbage collection (replace with expires)" + + reset_dummy_10 + + # Temporary routes + for i in $(seq 1 5); do + # Expire route after $EXPIRE seconds + $IP -6 route add 2001:20::$i \ + via 2001:10::2 dev dummy_10 expires $EXPIRE + done + # Replace with permanent routes + for i in $(seq 1 5); do + $IP -6 route replace 2001:20::$i \ + via 2001:10::2 dev dummy_10 + done + check_rt_num_clean 0 $($IP -6 route list |grep expires|wc -l) || return + + # Wait for GC + sleep $(($EXPIRE * 2 + 1)) + + check_rt_num 5 $($IP -6 route list |grep -v expires|grep 2001:20::|wc -l) + log_test $ret 0 "ipv6 route garbage collection (replace with permanent)" + + # ra6 is required for the next test. (ipv6toolkit) + if [ ! -x "$(command -v ra6)" ]; then + echo "SKIP: ra6 not found." + set +e + cleanup &> /dev/null + return fi - set +e + # Delete dummy_10 and remove all routes + $IP link del dev dummy_10 - log_test $ret 0 "ipv6 route garbage collection" + # Create a pair of veth devices to send a RA message from one + # device to another. + $IP link add veth1 type veth peer name veth2 + $IP link set dev veth1 up + $IP link set dev veth2 up + $IP -6 address add 2001:10::1/64 dev veth1 nodad + $IP -6 address add 2001:10::2/64 dev veth2 nodad + + # Make veth1 ready to receive RA messages. + $NS_EXEC sysctl -wq net.ipv6.conf.veth1.accept_ra=2 + + # Send a RA message with a route from veth2 to veth1. + $NS_EXEC ra6 -i veth2 -d 2001:10::1 -t $EXPIRE + + # Wait for the RA message. + sleep 1 + + # systemd may mess up the test. You syould make sure that + # systemd-networkd.service and systemd-networkd.socket are stopped. + check_rt_num_clean 1 $($IP -6 route list|grep expires|wc -l) || return + + # Wait for GC + sleep $(($EXPIRE * 2 + 1)) + + $NS_EXEC sysctl -wq net.ipv6.route.flush=1 + check_rt_num 0 $($IP -6 route list |grep expires|wc -l) + log_test $ret 0 "ipv6 route garbage collection (RA message)" + + set +e cleanup &> /dev/null } diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile index 452693514be4..cdefc9a5ec34 100644 --- a/tools/testing/selftests/net/forwarding/Makefile +++ b/tools/testing/selftests/net/forwarding/Makefile @@ -112,7 +112,7 @@ TEST_PROGS = bridge_fdb_learning_limit.sh \ vxlan_symmetric_ipv6.sh \ vxlan_symmetric.sh -TEST_PROGS_EXTENDED := devlink_lib.sh \ +TEST_FILES := devlink_lib.sh \ ethtool_lib.sh \ fib_offload_lib.sh \ forwarding.config.sample \ @@ -129,4 +129,7 @@ TEST_PROGS_EXTENDED := devlink_lib.sh \ sch_tbf_etsprio.sh \ tc_common.sh +TEST_INCLUDES := \ + ../lib.sh + include ../../lib.mk diff --git a/tools/testing/selftests/net/forwarding/bridge_locked_port.sh b/tools/testing/selftests/net/forwarding/bridge_locked_port.sh index 9af9f6964808..c62331b2e006 100755 --- a/tools/testing/selftests/net/forwarding/bridge_locked_port.sh +++ b/tools/testing/selftests/net/forwarding/bridge_locked_port.sh @@ -327,10 +327,10 @@ locked_port_mab_redirect() RET=0 check_port_mab_support || return 0 - bridge link set dev $swp1 learning on locked on mab on tc qdisc add dev $swp1 clsact tc filter add dev $swp1 ingress protocol all pref 1 handle 101 flower \ action mirred egress redirect dev $swp2 + bridge link set dev $swp1 learning on locked on mab on ping_do $h1 192.0.2.2 check_err $? "Ping did not work with redirection" @@ -349,8 +349,8 @@ locked_port_mab_redirect() check_err $? "Locked entry not created after deleting filter" bridge fdb del `mac_get $h1` vlan 1 dev $swp1 master - tc qdisc del dev $swp1 clsact bridge link set dev $swp1 learning off locked off mab off + tc qdisc del dev $swp1 clsact log_test "Locked port MAB redirect" } diff --git a/tools/testing/selftests/net/forwarding/bridge_mdb.sh b/tools/testing/selftests/net/forwarding/bridge_mdb.sh index 61348f71728c..d9d587454d20 100755 --- a/tools/testing/selftests/net/forwarding/bridge_mdb.sh +++ b/tools/testing/selftests/net/forwarding/bridge_mdb.sh @@ -329,7 +329,7 @@ __cfg_test_port_ip_star_g() bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q " 0.00" check_err $? "(*, G) \"permanent\" entry has a pending group timer" - bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q "\/0.00" + bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q "/0.00" check_err $? "\"permanent\" source entry has a pending source timer" bridge mdb del dev br0 port $swp1 grp $grp vid 10 @@ -346,7 +346,7 @@ __cfg_test_port_ip_star_g() bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q " 0.00" check_fail $? "(*, G) EXCLUDE entry does not have a pending group timer" - bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q "\/0.00" + bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q "/0.00" check_err $? "\"blocked\" source entry has a pending source timer" bridge mdb del dev br0 port $swp1 grp $grp vid 10 @@ -363,7 +363,7 @@ __cfg_test_port_ip_star_g() bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q " 0.00" check_err $? "(*, G) INCLUDE entry has a pending group timer" - bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q "\/0.00" + bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q "/0.00" check_fail $? "Source entry does not have a pending source timer" bridge mdb del dev br0 port $swp1 grp $grp vid 10 @@ -1252,14 +1252,17 @@ fwd_test() echo log_info "# Forwarding tests" + # Set the Max Response Delay to 100 centiseconds (1 second) so that the + # bridge will start forwarding according to its MDB soon after a + # multicast querier is enabled. + ip link set dev br0 type bridge mcast_query_response_interval 100 + # Forwarding according to MDB entries only takes place when the bridge # detects that there is a valid querier in the network. Set the bridge # as the querier and assign it a valid IPv6 link-local address to be # used as the source address for MLD queries. ip -6 address add fe80::1/64 nodad dev br0 ip link set dev br0 type bridge mcast_querier 1 - # Wait the default Query Response Interval (10 seconds) for the bridge - # to determine that there are no other queriers in the network. sleep 10 fwd_test_host @@ -1267,6 +1270,7 @@ fwd_test() ip link set dev br0 type bridge mcast_querier 0 ip -6 address del fe80::1/64 dev br0 + ip link set dev br0 type bridge mcast_query_response_interval 1000 } ctrl_igmpv3_is_in_test() diff --git a/tools/testing/selftests/net/forwarding/config b/tools/testing/selftests/net/forwarding/config index 697994a9278b..8d7a1a004b7c 100644 --- a/tools/testing/selftests/net/forwarding/config +++ b/tools/testing/selftests/net/forwarding/config @@ -6,14 +6,49 @@ CONFIG_IPV6_MULTIPLE_TABLES=y CONFIG_NET_VRF=m CONFIG_BPF_SYSCALL=y CONFIG_CGROUP_BPF=y +CONFIG_DUMMY=m +CONFIG_IPV6=y +CONFIG_IPV6_GRE=m +CONFIG_IPV6_MROUTE=y +CONFIG_IPV6_MROUTE_MULTIPLE_TABLES=y +CONFIG_IPV6_PIMSM_V2=y +CONFIG_IP_MROUTE=y +CONFIG_IP_MROUTE_MULTIPLE_TABLES=y +CONFIG_IP_PIMSM_V1=y +CONFIG_IP_PIMSM_V2=y +CONFIG_MACVLAN=m CONFIG_NET_ACT_CT=m CONFIG_NET_ACT_MIRRED=m CONFIG_NET_ACT_MPLS=m +CONFIG_NET_ACT_PEDIT=m +CONFIG_NET_ACT_POLICE=m +CONFIG_NET_ACT_SAMPLE=m +CONFIG_NET_ACT_SKBEDIT=m +CONFIG_NET_ACT_TUNNEL_KEY=m CONFIG_NET_ACT_VLAN=m CONFIG_NET_CLS_FLOWER=m CONFIG_NET_CLS_MATCHALL=m +CONFIG_NET_CLS_BASIC=m +CONFIG_NET_EMATCH=y +CONFIG_NET_EMATCH_META=m +CONFIG_NET_IPGRE=m +CONFIG_NET_IPGRE_DEMUX=m +CONFIG_NET_IPIP=m +CONFIG_NET_SCH_ETS=m CONFIG_NET_SCH_INGRESS=m CONFIG_NET_ACT_GACT=m +CONFIG_NET_SCH_PRIO=m +CONFIG_NET_SCH_RED=m +CONFIG_NET_SCH_TBF=m +CONFIG_NET_TC_SKB_EXT=y +CONFIG_NET_TEAM=y +CONFIG_NET_TEAM_MODE_LOADBALANCE=y +CONFIG_NETFILTER=y +CONFIG_NF_CONNTRACK=m +CONFIG_NF_FLOW_TABLE=m +CONFIG_NF_TABLES=m CONFIG_VETH=m CONFIG_NAMESPACES=y CONFIG_NET_NS=y +CONFIG_VXLAN=m +CONFIG_XFRM_USER=m diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 8a61464ab6eb..db3688f52888 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -29,23 +29,20 @@ STABLE_MAC_ADDRS=${STABLE_MAC_ADDRS:=no} TCPDUMP_EXTRA_FLAGS=${TCPDUMP_EXTRA_FLAGS:=} TROUTE6=${TROUTE6:=traceroute6} -relative_path="${BASH_SOURCE%/*}" -if [[ "$relative_path" == "${BASH_SOURCE}" ]]; then - relative_path="." -fi +net_forwarding_dir=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")") -if [[ -f $relative_path/forwarding.config ]]; then - source "$relative_path/forwarding.config" +if [[ -f $net_forwarding_dir/forwarding.config ]]; then + source "$net_forwarding_dir/forwarding.config" fi -# Kselftest framework requirement - SKIP code is 4. -ksft_skip=4 +source "$net_forwarding_dir/../lib.sh" -busywait() +# timeout in seconds +slowwait() { local timeout=$1; shift - local start_time="$(date -u +%s%3N)" + local start_time="$(date -u +%s)" while true do local out @@ -56,11 +53,13 @@ busywait() return 0 fi - local current_time="$(date -u +%s%3N)" + local current_time="$(date -u +%s)" if ((current_time - start_time > timeout)); then echo -n "$out" return 1 fi + + sleep 0.1 done } @@ -505,6 +504,15 @@ busywait_for_counter() busywait "$timeout" until_counter_is ">= $((base + delta))" "$@" } +slowwait_for_counter() +{ + local timeout=$1; shift + local delta=$1; shift + + local base=$("$@") + slowwait "$timeout" until_counter_is ">= $((base + delta))" "$@" +} + setup_wait_dev() { local dev=$1; shift diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_lib.sh b/tools/testing/selftests/net/forwarding/mirror_gre_lib.sh index fac486178ef7..0c36546e131e 100644 --- a/tools/testing/selftests/net/forwarding/mirror_gre_lib.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_lib.sh @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 -source "$relative_path/mirror_lib.sh" +source "$net_forwarding_dir/mirror_lib.sh" quick_test_span_gre_dir_ips() { diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_topo_lib.sh b/tools/testing/selftests/net/forwarding/mirror_gre_topo_lib.sh index 39c03e2867f4..6e615fffa4ef 100644 --- a/tools/testing/selftests/net/forwarding/mirror_gre_topo_lib.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_topo_lib.sh @@ -33,7 +33,7 @@ # | | # +-------------------------------------------------------------------------+ -source "$relative_path/mirror_topo_lib.sh" +source "$net_forwarding_dir/mirror_topo_lib.sh" mirror_gre_topo_h3_create() { diff --git a/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh b/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh index 20a7cb7222b8..c2420bb72c12 100755 --- a/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh +++ b/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh @@ -209,14 +209,17 @@ test_l2_miss_multicast() # both registered and unregistered multicast traffic. bridge link set dev $swp2 mcast_router 2 + # Set the Max Response Delay to 100 centiseconds (1 second) so that the + # bridge will start forwarding according to its MDB soon after a + # multicast querier is enabled. + ip link set dev br1 type bridge mcast_query_response_interval 100 + # Forwarding according to MDB entries only takes place when the bridge # detects that there is a valid querier in the network. Set the bridge # as the querier and assign it a valid IPv6 link-local address to be # used as the source address for MLD queries. ip link set dev br1 type bridge mcast_querier 1 ip -6 address add fe80::1/64 nodad dev br1 - # Wait the default Query Response Interval (10 seconds) for the bridge - # to determine that there are no other queriers in the network. sleep 10 test_l2_miss_multicast_ipv4 @@ -224,6 +227,7 @@ test_l2_miss_multicast() ip -6 address del fe80::1/64 dev br1 ip link set dev br1 type bridge mcast_querier 0 + ip link set dev br1 type bridge mcast_query_response_interval 1000 bridge link set dev $swp2 mcast_router 1 } diff --git a/tools/testing/selftests/net/fq_band_pktlimit.sh b/tools/testing/selftests/net/fq_band_pktlimit.sh index 24b77bdf41ff..977070ed42b3 100755 --- a/tools/testing/selftests/net/fq_band_pktlimit.sh +++ b/tools/testing/selftests/net/fq_band_pktlimit.sh @@ -8,7 +8,7 @@ # 3. send 20 pkts on band A: verify that 0 are queued, 20 dropped # 4. send 20 pkts on band B: verify that 10 are queued, 10 dropped # -# Send packets with a 100ms delay to ensure that previously sent +# Send packets with a delay to ensure that previously sent # packets are still queued when later ones are sent. # Use SO_TXTIME for this. @@ -29,19 +29,21 @@ ip -6 addr add fdaa::1/128 dev dummy0 ip -6 route add fdaa::/64 dev dummy0 tc qdisc replace dev dummy0 root handle 1: fq quantum 1514 initial_quantum 1514 limit 10 -./cmsg_sender -6 -p u -d 100000 -n 20 fdaa::2 8000 +DELAY=400000 + +./cmsg_sender -6 -p u -d "${DELAY}" -n 20 fdaa::2 8000 OUT1="$(tc -s qdisc show dev dummy0 | grep '^\ Sent')" -./cmsg_sender -6 -p u -d 100000 -n 20 fdaa::2 8000 +./cmsg_sender -6 -p u -d "${DELAY}" -n 20 fdaa::2 8000 OUT2="$(tc -s qdisc show dev dummy0 | grep '^\ Sent')" -./cmsg_sender -6 -p u -d 100000 -n 20 -P 7 fdaa::2 8000 +./cmsg_sender -6 -p u -d "${DELAY}" -n 20 -P 7 fdaa::2 8000 OUT3="$(tc -s qdisc show dev dummy0 | grep '^\ Sent')" # Initial stats will report zero sent, as all packets are still -# queued in FQ. Sleep for the delay period (100ms) and see that +# queued in FQ. Sleep for at least the delay period and see that # twenty are now sent. -sleep 0.1 +sleep 0.6 OUT4="$(tc -s qdisc show dev dummy0 | grep '^\ Sent')" # Log the output after the test diff --git a/tools/testing/selftests/net/gro.sh b/tools/testing/selftests/net/gro.sh index 19352f106c1d..02c21ff4ca81 100755 --- a/tools/testing/selftests/net/gro.sh +++ b/tools/testing/selftests/net/gro.sh @@ -31,6 +31,11 @@ run_test() { 1>>log.txt wait "${server_pid}" exit_code=$? + if [[ ${test} == "large" && -n "${KSFT_MACHINE_SLOW}" && \ + ${exit_code} -ne 0 ]]; then + echo "Ignoring errors due to slow environment" 1>&2 + exit_code=0 + fi if [[ "${exit_code}" -eq 0 ]]; then break; fi diff --git a/tools/testing/selftests/net/ip_local_port_range.c b/tools/testing/selftests/net/ip_local_port_range.c index 0f217a1cc837..6ebd58869a63 100644 --- a/tools/testing/selftests/net/ip_local_port_range.c +++ b/tools/testing/selftests/net/ip_local_port_range.c @@ -16,6 +16,10 @@ #define IP_LOCAL_PORT_RANGE 51 #endif +#ifndef IPPROTO_MPTCP +#define IPPROTO_MPTCP 262 +#endif + static __u32 pack_port_range(__u16 lo, __u16 hi) { return (hi << 16) | (lo << 0); diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index dca549443801..f9fe182dfbd4 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -4,6 +4,9 @@ ############################################################################## # Defines +WAIT_TIMEOUT=${WAIT_TIMEOUT:=20} +BUSYWAIT_TIMEOUT=$((WAIT_TIMEOUT * 1000)) # ms + # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 # namespace list created by setup_ns @@ -48,7 +51,7 @@ cleanup_ns() for ns in "$@"; do ip netns delete "${ns}" &> /dev/null - if ! busywait 2 ip netns list \| grep -vq "^$ns$" &> /dev/null; then + if ! busywait $BUSYWAIT_TIMEOUT ip netns list \| grep -vq "^$ns$" &> /dev/null; then echo "Warn: Failed to remove namespace $ns" ret=1 fi diff --git a/tools/testing/selftests/net/mptcp/config b/tools/testing/selftests/net/mptcp/config index e317c2e44dae..4f80014cae49 100644 --- a/tools/testing/selftests/net/mptcp/config +++ b/tools/testing/selftests/net/mptcp/config @@ -22,8 +22,11 @@ CONFIG_NFT_TPROXY=m CONFIG_NFT_SOCKET=m CONFIG_IP_ADVANCED_ROUTER=y CONFIG_IP_MULTIPLE_TABLES=y +CONFIG_IP_NF_FILTER=m +CONFIG_IP_NF_MANGLE=m CONFIG_IP_NF_TARGET_REJECT=m CONFIG_IPV6_MULTIPLE_TABLES=y +CONFIG_IP6_NF_FILTER=m CONFIG_NET_ACT_CSUM=m CONFIG_NET_ACT_PEDIT=m CONFIG_NET_CLS_ACT=y diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 3a5b63026191..c07386e21e0a 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -643,13 +643,6 @@ kill_events_pids() mptcp_lib_kill_wait $evts_ns2_pid } -kill_tests_wait() -{ - #shellcheck disable=SC2046 - kill -SIGUSR1 $(ip netns pids $ns2) $(ip netns pids $ns1) - wait -} - pm_nl_set_limits() { local ns=$1 @@ -3453,7 +3446,7 @@ userspace_tests() chk_mptcp_info subflows 0 subflows 0 chk_subflows_total 1 1 kill_events_pids - wait $tests_pid + mptcp_lib_kill_wait $tests_pid fi # userspace pm create destroy subflow @@ -3475,7 +3468,7 @@ userspace_tests() chk_mptcp_info subflows 0 subflows 0 chk_subflows_total 1 1 kill_events_pids - wait $tests_pid + mptcp_lib_kill_wait $tests_pid fi # userspace pm create id 0 subflow @@ -3494,7 +3487,7 @@ userspace_tests() chk_mptcp_info subflows 1 subflows 1 chk_subflows_total 2 2 kill_events_pids - wait $tests_pid + mptcp_lib_kill_wait $tests_pid fi # userspace pm remove initial subflow @@ -3518,7 +3511,7 @@ userspace_tests() chk_mptcp_info subflows 1 subflows 1 chk_subflows_total 1 1 kill_events_pids - wait $tests_pid + mptcp_lib_kill_wait $tests_pid fi # userspace pm send RM_ADDR for ID 0 @@ -3544,7 +3537,7 @@ userspace_tests() chk_mptcp_info subflows 1 subflows 1 chk_subflows_total 1 1 kill_events_pids - wait $tests_pid + mptcp_lib_kill_wait $tests_pid fi } @@ -3558,7 +3551,8 @@ endpoint_tests() pm_nl_set_limits $ns2 2 2 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal speed=slow \ - run_tests $ns1 $ns2 10.0.1.1 2>/dev/null & + run_tests $ns1 $ns2 10.0.1.1 & + local tests_pid=$! wait_mpj $ns1 pm_nl_check_endpoint "creation" \ @@ -3573,7 +3567,7 @@ endpoint_tests() pm_nl_add_endpoint $ns2 10.0.2.2 flags signal pm_nl_check_endpoint "modif is allowed" \ $ns2 10.0.2.2 id 1 flags signal - kill_tests_wait + mptcp_lib_kill_wait $tests_pid fi if reset "delete and re-add" && @@ -3582,7 +3576,8 @@ endpoint_tests() 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 speed=20 \ - run_tests $ns1 $ns2 10.0.1.1 2>/dev/null & + run_tests $ns1 $ns2 10.0.1.1 & + local tests_pid=$! wait_mpj $ns2 chk_subflow_nr "before delete" 2 @@ -3597,7 +3592,7 @@ endpoint_tests() wait_mpj $ns2 chk_subflow_nr "after re-add" 2 chk_mptcp_info subflows 1 subflows 1 - kill_tests_wait + mptcp_lib_kill_wait $tests_pid fi } diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh index 022262a2cfe0..3a2abae5993e 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -6,7 +6,7 @@ readonly KSFT_FAIL=1 readonly KSFT_SKIP=4 # shellcheck disable=SC2155 # declare and assign separately -readonly KSFT_TEST=$(basename "${0}" | sed 's/\.sh$//g') +readonly KSFT_TEST="${MPTCP_LIB_KSFT_TEST:-$(basename "${0}" .sh)}" MPTCP_LIB_SUBTESTS=() diff --git a/tools/testing/selftests/net/mptcp/settings b/tools/testing/selftests/net/mptcp/settings index 79b65bdf05db..abc5648b59ab 100644 --- a/tools/testing/selftests/net/mptcp/settings +++ b/tools/testing/selftests/net/mptcp/settings @@ -1 +1 @@ -timeout=1200 +timeout=1800 diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh index ae8ad5d6fb9d..0cc964e6f2c1 100755 --- a/tools/testing/selftests/net/mptcp/simult_flows.sh +++ b/tools/testing/selftests/net/mptcp/simult_flows.sh @@ -284,12 +284,12 @@ done setup run_test 10 10 0 0 "balanced bwidth" -run_test 10 10 1 50 "balanced bwidth with unbalanced delay" +run_test 10 10 1 25 "balanced bwidth with unbalanced delay" # we still need some additional infrastructure to pass the following test-cases -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" +run_test 10 3 0 0 "unbalanced bwidth" +run_test 10 3 1 25 "unbalanced bwidth with unbalanced delay" +run_test 10 3 25 1 "unbalanced bwidth with opposed, unbalanced delay" mptcp_lib_result_print_all_tap exit $ret diff --git a/tools/testing/selftests/net/net_helper.sh b/tools/testing/selftests/net/net_helper.sh index 4fe0befa13fb..6596fe03c77f 100755..100644 --- a/tools/testing/selftests/net/net_helper.sh +++ b/tools/testing/selftests/net/net_helper.sh @@ -8,13 +8,16 @@ wait_local_port_listen() local listener_ns="${1}" local port="${2}" local protocol="${3}" - local port_hex + local pattern local i - port_hex="$(printf "%04X" "${port}")" + pattern=":$(printf "%04X" "${port}") " + + # for tcp protocol additionally check the socket state + [ ${protocol} = "tcp" ] && pattern="${pattern}0A" for i in $(seq 10); do - if ip netns exec "${listener_ns}" cat /proc/net/"${protocol}"* | \ - grep -q "${port_hex}"; then + if ip netns exec "${listener_ns}" awk '{print $2" "$4}' \ + /proc/net/"${protocol}"* | grep -q "${pattern}"; then break fi sleep 0.1 diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh index f8499d4c87f3..5cae53543849 100755 --- a/tools/testing/selftests/net/openvswitch/openvswitch.sh +++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh @@ -17,6 +17,7 @@ tests=" ct_connect_v4 ip4-ct-xon: Basic ipv4 tcp connection using ct connect_v4 ip4-xon: Basic ipv4 ping between two NS nat_connect_v4 ip4-nat-xon: Basic ipv4 tcp connection via NAT + nat_related_v4 ip4-nat-related: ICMP related matches work with SNAT netlink_checks ovsnl: validate netlink attrs and settings upcall_interfaces ovs: test the upcall interfaces drop_reason drop: test drop reasons are emitted" @@ -473,6 +474,67 @@ test_nat_connect_v4 () { return 0 } +# nat_related_v4 test +# - client->server ip packets go via SNAT +# - client solicits ICMP destination unreachable packet from server +# - undo NAT for ICMP reply and test dst ip has been updated +test_nat_related_v4 () { + which nc >/dev/null 2>/dev/null || return $ksft_skip + + sbx_add "test_nat_related_v4" || return $? + + ovs_add_dp "test_nat_related_v4" natrelated4 || return 1 + info "create namespaces" + for ns in client server; do + ovs_add_netns_and_veths "test_nat_related_v4" "natrelated4" "$ns" \ + "${ns:0:1}0" "${ns:0:1}1" || return 1 + done + + ip netns exec client ip addr add 172.31.110.10/24 dev c1 + ip netns exec client ip link set c1 up + ip netns exec server ip addr add 172.31.110.20/24 dev s1 + ip netns exec server ip link set s1 up + + ip netns exec server ip route add 192.168.0.20/32 via 172.31.110.10 + + # Allow ARP + ovs_add_flow "test_nat_related_v4" natrelated4 \ + "in_port(1),eth(),eth_type(0x0806),arp()" "2" || return 1 + ovs_add_flow "test_nat_related_v4" natrelated4 \ + "in_port(2),eth(),eth_type(0x0806),arp()" "1" || return 1 + + # Allow IP traffic from client->server, rewrite source IP with SNAT to 192.168.0.20 + ovs_add_flow "test_nat_related_v4" natrelated4 \ + "ct_state(-trk),in_port(1),eth(),eth_type(0x0800),ipv4(dst=172.31.110.20)" \ + "ct(commit,nat(src=192.168.0.20)),recirc(0x1)" || return 1 + ovs_add_flow "test_nat_related_v4" natrelated4 \ + "recirc_id(0x1),ct_state(+trk-inv),in_port(1),eth(),eth_type(0x0800),ipv4()" \ + "2" || return 1 + + # Allow related ICMP responses back from server and undo NAT to restore original IP + # Drop any ICMP related packets where dst ip hasn't been restored back to original IP + ovs_add_flow "test_nat_related_v4" natrelated4 \ + "ct_state(-trk),in_port(2),eth(),eth_type(0x0800),ipv4()" \ + "ct(commit,nat),recirc(0x2)" || return 1 + ovs_add_flow "test_nat_related_v4" natrelated4 \ + "recirc_id(0x2),ct_state(+rel+trk),in_port(2),eth(),eth_type(0x0800),ipv4(src=172.31.110.20,dst=172.31.110.10,proto=1),icmp()" \ + "1" || return 1 + ovs_add_flow "test_nat_related_v4" natrelated4 \ + "recirc_id(0x2),ct_state(+rel+trk),in_port(2),eth(),eth_type(0x0800),ipv4(dst=192.168.0.20,proto=1),icmp()" \ + "drop" || return 1 + + # Solicit destination unreachable response from server + ovs_sbx "test_nat_related_v4" ip netns exec client \ + bash -c "echo a | nc -u -w 1 172.31.110.20 10000" + + # Check to make sure no packets matched the drop rule with incorrect dst ip + python3 "$ovs_base/ovs-dpctl.py" dump-flows natrelated4 \ + | grep "drop" | grep "packets:0" >/dev/null || return 1 + + info "done..." + return 0 +} + # netlink_validation # - Create a dp # - check no warning with "old version" simulation @@ -502,9 +564,22 @@ test_netlink_checks () { wc -l) == 2 ] || \ return 1 + info "Checking clone depth" ERR_MSG="Flow actions may not be safe on all matching packets" PRE_TEST=$(dmesg | grep -c "${ERR_MSG}") ovs_add_flow "test_netlink_checks" nv0 \ + 'in_port(1),eth(),eth_type(0x800),ipv4()' \ + 'clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(drop)))))))))))))))))' \ + >/dev/null 2>&1 && return 1 + POST_TEST=$(dmesg | grep -c "${ERR_MSG}") + + if [ "$PRE_TEST" == "$POST_TEST" ]; then + info "failed - clone depth too large" + return 1 + fi + + PRE_TEST=$(dmesg | grep -c "${ERR_MSG}") + ovs_add_flow "test_netlink_checks" nv0 \ 'in_port(1),eth(),eth_type(0x0806),arp()' 'drop(0),2' \ &> /dev/null && return 1 POST_TEST=$(dmesg | grep -c "${ERR_MSG}") diff --git a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py index b97e621face9..5e0e539a323d 100644 --- a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py +++ b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py @@ -299,7 +299,7 @@ class ovsactions(nla): ("OVS_ACTION_ATTR_PUSH_NSH", "none"), ("OVS_ACTION_ATTR_POP_NSH", "flag"), ("OVS_ACTION_ATTR_METER", "none"), - ("OVS_ACTION_ATTR_CLONE", "none"), + ("OVS_ACTION_ATTR_CLONE", "recursive"), ("OVS_ACTION_ATTR_CHECK_PKT_LEN", "none"), ("OVS_ACTION_ATTR_ADD_MPLS", "none"), ("OVS_ACTION_ATTR_DEC_TTL", "none"), @@ -465,29 +465,42 @@ class ovsactions(nla): print_str += "pop_mpls" else: datum = self.get_attr(field[0]) - print_str += datum.dpstr(more) + if field[0] == "OVS_ACTION_ATTR_CLONE": + print_str += "clone(" + print_str += datum.dpstr(more) + print_str += ")" + else: + print_str += datum.dpstr(more) return print_str def parse(self, actstr): + totallen = len(actstr) while len(actstr) != 0: parsed = False + parencount = 0 if actstr.startswith("drop"): # If no reason is provided, the implicit drop is used (i.e no # action). If some reason is given, an explicit action is used. - actstr, reason = parse_extract_field( - actstr, - "drop(", - "([0-9]+)", - lambda x: int(x, 0), - False, - None, - ) + reason = None + if actstr.startswith("drop("): + parencount += 1 + + actstr, reason = parse_extract_field( + actstr, + "drop(", + "([0-9]+)", + lambda x: int(x, 0), + False, + None, + ) + if reason is not None: self["attrs"].append(["OVS_ACTION_ATTR_DROP", reason]) parsed = True else: - return + actstr = actstr[len("drop"): ] + return (totallen - len(actstr)) elif parse_starts_block(actstr, "^(\d+)", False, True): actstr, output = parse_extract_field( @@ -504,6 +517,7 @@ class ovsactions(nla): False, 0, ) + parencount += 1 self["attrs"].append(["OVS_ACTION_ATTR_RECIRC", recircid]) parsed = True @@ -516,12 +530,22 @@ class ovsactions(nla): for flat_act in parse_flat_map: if parse_starts_block(actstr, flat_act[0], False): - actstr += len(flat_act[0]) + actstr = actstr[len(flat_act[0]):] self["attrs"].append([flat_act[1]]) actstr = actstr[strspn(actstr, ", ") :] parsed = True - if parse_starts_block(actstr, "ct(", False): + if parse_starts_block(actstr, "clone(", False): + parencount += 1 + subacts = ovsactions() + actstr = actstr[len("clone("):] + parsedLen = subacts.parse(actstr) + lst = [] + self["attrs"].append(("OVS_ACTION_ATTR_CLONE", subacts)) + actstr = actstr[parsedLen:] + parsed = True + elif parse_starts_block(actstr, "ct(", False): + parencount += 1 actstr = actstr[len("ct(") :] ctact = ovsactions.ctact() @@ -553,6 +577,7 @@ class ovsactions(nla): natact = ovsactions.ctact.natattr() if actstr.startswith("("): + parencount += 1 t = None actstr = actstr[1:] if actstr.startswith("src"): @@ -607,15 +632,29 @@ class ovsactions(nla): actstr = actstr[strspn(actstr, ", ") :] ctact["attrs"].append(["OVS_CT_ATTR_NAT", natact]) - actstr = actstr[strspn(actstr, ",) ") :] + actstr = actstr[strspn(actstr, ", ") :] self["attrs"].append(["OVS_ACTION_ATTR_CT", ctact]) parsed = True - actstr = actstr[strspn(actstr, "), ") :] + actstr = actstr[strspn(actstr, ", ") :] + while parencount > 0: + parencount -= 1 + actstr = actstr[strspn(actstr, " "):] + if len(actstr) and actstr[0] != ")": + raise ValueError("Action str: '%s' unbalanced" % actstr) + actstr = actstr[1:] + + if len(actstr) and actstr[0] == ")": + return (totallen - len(actstr)) + + actstr = actstr[strspn(actstr, ", ") :] + if not parsed: raise ValueError("Action str: '%s' not supported" % actstr) + return (totallen - len(actstr)) + class ovskey(nla): nla_flags = NLA_F_NESTED @@ -2111,6 +2150,8 @@ def main(argv): ovsflow = OvsFlow() ndb = NDB() + sys.setrecursionlimit(100000) + if hasattr(args, "showdp"): found = False for iface in ndb.interfaces: diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index f10879788f61..cfc84958025a 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -199,6 +199,7 @@ # Same as above but with IPv6 source lib.sh +source net_helper.sh PAUSE_ON_FAIL=no VERBOSE=0 @@ -707,23 +708,23 @@ setup_xfrm6() { } setup_xfrm4udp() { - setup_xfrm 4 ${veth4_a_addr} ${veth4_b_addr} "encap espinudp 4500 4500 0.0.0.0" - setup_nettest_xfrm 4 4500 + setup_xfrm 4 ${veth4_a_addr} ${veth4_b_addr} "encap espinudp 4500 4500 0.0.0.0" && \ + setup_nettest_xfrm 4 4500 } setup_xfrm6udp() { - setup_xfrm 6 ${veth6_a_addr} ${veth6_b_addr} "encap espinudp 4500 4500 0.0.0.0" - setup_nettest_xfrm 6 4500 + setup_xfrm 6 ${veth6_a_addr} ${veth6_b_addr} "encap espinudp 4500 4500 0.0.0.0" && \ + setup_nettest_xfrm 6 4500 } setup_xfrm4udprouted() { - setup_xfrm 4 ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 "encap espinudp 4500 4500 0.0.0.0" - setup_nettest_xfrm 4 4500 + setup_xfrm 4 ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 "encap espinudp 4500 4500 0.0.0.0" && \ + setup_nettest_xfrm 4 4500 } setup_xfrm6udprouted() { - setup_xfrm 6 ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 "encap espinudp 4500 4500 0.0.0.0" - setup_nettest_xfrm 6 4500 + setup_xfrm 6 ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 "encap espinudp 4500 4500 0.0.0.0" && \ + setup_nettest_xfrm 6 4500 } setup_routing_old() { @@ -1335,12 +1336,14 @@ test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception() { else TCPDST="TCP:[${dst}]:50000" fi - ${ns_b} socat -T 3 -u -6 TCP-LISTEN:50000 STDOUT > $tmpoutfile & + ${ns_b} socat -T 3 -u -6 TCP-LISTEN:50000,reuseaddr STDOUT > $tmpoutfile & + local socat_pid=$! - sleep 1 + wait_local_port_listen ${NS_B} 50000 tcp - dd if=/dev/zero of=/dev/stdout status=none bs=1M count=1 | ${target} socat -T 3 -u STDIN $TCPDST,connect-timeout=3 + dd if=/dev/zero status=none bs=1M count=1 | ${target} socat -T 3 -u STDIN $TCPDST,connect-timeout=3 + wait ${socat_pid} size=$(du -sb $tmpoutfile) size=${size%%/tmp/*} @@ -1954,6 +1957,13 @@ check_command() { return 0 } +check_running() { + pid=${1} + cmd=${2} + + [ "$(cat /proc/${pid}/cmdline 2>/dev/null | tr -d '\0')" = "{cmd}" ] +} + test_cleanup_vxlanX_exception() { outer="${1}" encap="vxlan" @@ -1984,11 +1994,12 @@ test_cleanup_vxlanX_exception() { ${ns_a} ip link del dev veth_A-R1 & iplink_pid=$! - sleep 1 - if [ "$(cat /proc/${iplink_pid}/cmdline 2>/dev/null | tr -d '\0')" = "iplinkdeldevveth_A-R1" ]; then - err " can't delete veth device in a timely manner, PMTU dst likely leaked" - return 1 - fi + for i in $(seq 1 20); do + check_running ${iplink_pid} "iplinkdeldevveth_A-R1" || return 0 + sleep 0.1 + done + err " can't delete veth device in a timely manner, PMTU dst likely leaked" + return 1 } test_cleanup_ipv6_exception() { diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index 4667d74579d1..874a2952aa8e 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -440,7 +440,6 @@ kci_test_encap_vxlan() local ret=0 vxlan="test-vxlan0" vlan="test-vlan0" - testns="$1" run_cmd ip -netns "$testns" link add "$vxlan" type vxlan id 42 group 239.1.1.1 \ dev "$devdummy" dstport 4789 if [ $? -ne 0 ]; then @@ -485,7 +484,6 @@ kci_test_encap_fou() { local ret=0 name="test-fou" - testns="$1" run_cmd_grep 'Usage: ip fou' ip fou help if [ $? -ne 0 ];then end_test "SKIP: fou: iproute2 too old" @@ -526,8 +524,8 @@ kci_test_encap() run_cmd ip -netns "$testns" link set lo up run_cmd ip -netns "$testns" link add name "$devdummy" type dummy run_cmd ip -netns "$testns" link set "$devdummy" up - run_cmd kci_test_encap_vxlan "$testns" - run_cmd kci_test_encap_fou "$testns" + run_cmd kci_test_encap_vxlan + run_cmd kci_test_encap_fou ip netns del "$testns" return $ret diff --git a/tools/testing/selftests/net/setup_loopback.sh b/tools/testing/selftests/net/setup_loopback.sh index 2070b57849de..2070b57849de 100755..100644 --- a/tools/testing/selftests/net/setup_loopback.sh +++ b/tools/testing/selftests/net/setup_loopback.sh diff --git a/tools/testing/selftests/net/setup_veth.sh b/tools/testing/selftests/net/setup_veth.sh index a9a1759e035c..1f78a87f6f37 100644 --- a/tools/testing/selftests/net/setup_veth.sh +++ b/tools/testing/selftests/net/setup_veth.sh @@ -11,7 +11,7 @@ setup_veth_ns() { local -r ns_mac="$4" [[ -e /var/run/netns/"${ns_name}" ]] || ip netns add "${ns_name}" - echo 100000 > "/sys/class/net/${ns_dev}/gro_flush_timeout" + echo 1000000 > "/sys/class/net/${ns_dev}/gro_flush_timeout" ip link set dev "${ns_dev}" netns "${ns_name}" mtu 65535 ip -netns "${ns_name}" link set dev "${ns_dev}" up diff --git a/tools/testing/selftests/net/so_txtime.c b/tools/testing/selftests/net/so_txtime.c index 2672ac0b6d1f..8457b7ccbc09 100644 --- a/tools/testing/selftests/net/so_txtime.c +++ b/tools/testing/selftests/net/so_txtime.c @@ -134,8 +134,11 @@ static void do_recv_one(int fdr, struct timed_send *ts) if (rbuf[0] != ts->data) error(1, 0, "payload mismatch. expected %c", ts->data); - if (llabs(tstop - texpect) > cfg_variance_us) - error(1, 0, "exceeds variance (%d us)", cfg_variance_us); + if (llabs(tstop - texpect) > cfg_variance_us) { + fprintf(stderr, "exceeds variance (%d us)\n", cfg_variance_us); + if (!getenv("KSFT_MACHINE_SLOW")) + exit(1); + } } static void do_recv_verify_empty(int fdr) diff --git a/tools/testing/selftests/net/so_txtime.sh b/tools/testing/selftests/net/so_txtime.sh index 3f06f4d286a9..5e861ad32a42 100755 --- a/tools/testing/selftests/net/so_txtime.sh +++ b/tools/testing/selftests/net/so_txtime.sh @@ -5,6 +5,7 @@ set -e +readonly ksft_skip=4 readonly DEV="veth0" readonly BIN="./so_txtime" @@ -46,7 +47,7 @@ ip -netns "${NS2}" addr add 192.168.1.2/24 dev "${DEV}" ip -netns "${NS1}" addr add fd::1/64 dev "${DEV}" nodad ip -netns "${NS2}" addr add fd::2/64 dev "${DEV}" nodad -do_test() { +run_test() { local readonly IP="$1" local readonly CLOCK="$2" local readonly TXARGS="$3" @@ -64,12 +65,25 @@ do_test() { fi local readonly START="$(date +%s%N --date="+ 0.1 seconds")" + ip netns exec "${NS2}" "${BIN}" -"${IP}" -c "${CLOCK}" -t "${START}" -S "${SADDR}" -D "${DADDR}" "${RXARGS}" -r & ip netns exec "${NS1}" "${BIN}" -"${IP}" -c "${CLOCK}" -t "${START}" -S "${SADDR}" -D "${DADDR}" "${TXARGS}" wait "$!" } +do_test() { + run_test $@ + [ $? -ne 0 ] && ret=1 +} + +do_fail_test() { + run_test $@ + [ $? -eq 0 ] && ret=1 +} + ip netns exec "${NS1}" tc qdisc add dev "${DEV}" root fq +set +e +ret=0 do_test 4 mono a,-1 a,-1 do_test 6 mono a,0 a,0 do_test 6 mono a,10 a,10 @@ -77,13 +91,20 @@ do_test 4 mono a,10,b,20 a,10,b,20 do_test 6 mono a,20,b,10 b,20,a,20 if ip netns exec "${NS1}" tc qdisc replace dev "${DEV}" root etf clockid CLOCK_TAI delta 400000; then - ! do_test 4 tai a,-1 a,-1 - ! do_test 6 tai a,0 a,0 + do_fail_test 4 tai a,-1 a,-1 + do_fail_test 6 tai a,0 a,0 do_test 6 tai a,10 a,10 do_test 4 tai a,10,b,20 a,10,b,20 do_test 6 tai a,20,b,10 b,10,a,20 else echo "tc ($(tc -V)) does not support qdisc etf. skipping" + [ $ret -eq 0 ] && ret=$ksft_skip fi -echo OK. All tests passed +if [ $ret -eq 0 ]; then + echo OK. All tests passed +elif [[ $ret -ne $ksft_skip && -n "$KSFT_MACHINE_SLOW" ]]; then + echo "Ignoring errors due to slow environment" 1>&2 + ret=0 +fi +exit $ret diff --git a/tools/testing/selftests/net/tcp_ao/config b/tools/testing/selftests/net/tcp_ao/config new file mode 100644 index 000000000000..d3277a9de987 --- /dev/null +++ b/tools/testing/selftests/net/tcp_ao/config @@ -0,0 +1,10 @@ +CONFIG_CRYPTO_HMAC=y +CONFIG_CRYPTO_RMD160=y +CONFIG_CRYPTO_SHA1=y +CONFIG_IPV6_MULTIPLE_TABLES=y +CONFIG_IPV6=y +CONFIG_NET_L3_MASTER_DEV=y +CONFIG_NET_VRF=y +CONFIG_TCP_AO=y +CONFIG_TCP_MD5SIG=y +CONFIG_VETH=m diff --git a/tools/testing/selftests/net/tcp_ao/key-management.c b/tools/testing/selftests/net/tcp_ao/key-management.c index c48b4970ca17..24e62120b792 100644 --- a/tools/testing/selftests/net/tcp_ao/key-management.c +++ b/tools/testing/selftests/net/tcp_ao/key-management.c @@ -417,9 +417,9 @@ struct test_key { matches_vrf : 1, is_current : 1, is_rnext : 1, - used_on_handshake : 1, - used_after_accept : 1, - used_on_client : 1; + used_on_server_tx : 1, + used_on_client_tx : 1, + skip_counters_checks : 1; }; struct key_collection { @@ -609,16 +609,14 @@ static int key_collection_socket(bool server, unsigned int port) addr = &this_ip_dest; sndid = key->client_keyid; rcvid = key->server_keyid; - set_current = key->is_current; - set_rnext = key->is_rnext; + key->used_on_client_tx = set_current = key->is_current; + key->used_on_server_tx = set_rnext = key->is_rnext; } if (test_add_key_cr(sk, key->password, key->len, *addr, vrf, sndid, rcvid, key->maclen, key->alg, set_current, set_rnext)) test_key_error("setsockopt(TCP_AO_ADD_KEY)", key); - if (set_current || set_rnext) - key->used_on_handshake = 1; #ifdef DEBUG test_print("%s [%u/%u] key: { %s, %u:%u, %u, %u:%u:%u:%u (%u)}", server ? "server" : "client", i, collection.nr_keys, @@ -640,22 +638,22 @@ static void verify_counters(const char *tst_name, bool is_listen_sk, bool server for (i = 0; i < collection.nr_keys; i++) { struct test_key *key = &collection.keys[i]; uint8_t sndid, rcvid; - bool was_used; + bool rx_cnt_expected; + if (key->skip_counters_checks) + continue; if (server) { sndid = key->server_keyid; rcvid = key->client_keyid; - if (is_listen_sk) - was_used = key->used_on_handshake; - else - was_used = key->used_after_accept; + rx_cnt_expected = key->used_on_client_tx; } else { sndid = key->client_keyid; rcvid = key->server_keyid; - was_used = key->used_on_client; + rx_cnt_expected = key->used_on_server_tx; } - test_tcp_ao_key_counters_cmp(tst_name, a, b, was_used, + test_tcp_ao_key_counters_cmp(tst_name, a, b, + rx_cnt_expected ? TEST_CNT_KEY_GOOD : 0, sndid, rcvid); } test_tcp_ao_counters_free(a); @@ -843,7 +841,7 @@ static void end_server(const char *tst_name, int sk, synchronize_threads(); /* 4: verified => closed */ close(sk); - verify_counters(tst_name, true, false, begin, &end); + verify_counters(tst_name, false, true, begin, &end); synchronize_threads(); /* 5: counters */ } @@ -916,9 +914,8 @@ static int run_client(const char *tst_name, unsigned int port, current_index = nr_keys - 1; if (rnext_index < 0) rnext_index = nr_keys - 1; - collection.keys[current_index].used_on_handshake = 1; - collection.keys[rnext_index].used_after_accept = 1; - collection.keys[rnext_index].used_on_client = 1; + collection.keys[current_index].used_on_client_tx = 1; + collection.keys[rnext_index].used_on_server_tx = 1; synchronize_threads(); /* 3: accepted => send data */ if (test_client_verify(sk, msg_sz, msg_nr, TEST_TIMEOUT_SEC)) { @@ -1059,7 +1056,16 @@ static void check_current_back(const char *tst_name, unsigned int port, test_error("Can't change the current key"); if (test_client_verify(sk, msg_len, nr_packets, TEST_TIMEOUT_SEC)) test_fail("verify failed"); - collection.keys[rotate_to_index].used_after_accept = 1; + /* There is a race here: between setting the current_key with + * setsockopt(TCP_AO_INFO) and starting to send some data - there + * might have been a segment received with the desired + * RNext_key set. In turn that would mean that the first outgoing + * segment will have the desired current_key (flipped back). + * Which is what the user/test wants. As it's racy, skip checking + * the counters, yet check what are the resulting current/rnext + * keys on both sides. + */ + collection.keys[rotate_to_index].skip_counters_checks = 1; end_client(tst_name, sk, nr_keys, current_index, rnext_index, &tmp); } @@ -1089,7 +1095,7 @@ static void roll_over_keys(const char *tst_name, unsigned int port, } verify_current_rnext(tst_name, sk, -1, collection.keys[i].server_keyid); - collection.keys[i].used_on_client = 1; + collection.keys[i].used_on_server_tx = 1; synchronize_threads(); /* verify current/rnext */ } end_client(tst_name, sk, nr_keys, current_index, rnext_index, &tmp); diff --git a/tools/testing/selftests/net/tcp_ao/lib/sock.c b/tools/testing/selftests/net/tcp_ao/lib/sock.c index c75d82885a2e..15aeb0963058 100644 --- a/tools/testing/selftests/net/tcp_ao/lib/sock.c +++ b/tools/testing/selftests/net/tcp_ao/lib/sock.c @@ -62,7 +62,9 @@ int test_wait_fd(int sk, time_t sec, bool write) return -ETIMEDOUT; } - if (getsockopt(sk, SOL_SOCKET, SO_ERROR, &ret, &slen) || ret) + if (getsockopt(sk, SOL_SOCKET, SO_ERROR, &ret, &slen)) + return -errno; + if (ret) return -ret; return 0; } @@ -584,9 +586,11 @@ int test_client_verify(int sk, const size_t msg_len, const size_t nr, { size_t buf_sz = msg_len * nr; char *buf = alloca(buf_sz); + ssize_t ret; randomize_buffer(buf, buf_sz); - if (test_client_loop(sk, buf, buf_sz, msg_len, timeout_sec) != buf_sz) - return -1; - return 0; + ret = test_client_loop(sk, buf, buf_sz, msg_len, timeout_sec); + if (ret < 0) + return (int)ret; + return ret != buf_sz ? -1 : 0; } diff --git a/tools/testing/selftests/net/tcp_ao/rst.c b/tools/testing/selftests/net/tcp_ao/rst.c index ac06009a7f5f..7df8b8700e39 100644 --- a/tools/testing/selftests/net/tcp_ao/rst.c +++ b/tools/testing/selftests/net/tcp_ao/rst.c @@ -1,10 +1,33 @@ // SPDX-License-Identifier: GPL-2.0 -/* Author: Dmitry Safonov <dima@arista.com> */ +/* + * The test checks that both active and passive reset have correct TCP-AO + * signature. An "active" reset (abort) here is procured from closing + * listen() socket with non-accepted connections in the queue: + * inet_csk_listen_stop() => inet_child_forget() => + * => tcp_disconnect() => tcp_send_active_reset() + * + * The passive reset is quite hard to get on established TCP connections. + * It could be procured from non-established states, but the synchronization + * part from userspace in order to reliably get RST seems uneasy. + * So, instead it's procured by corrupting SEQ number on TIMED-WAIT state. + * + * It's important to test both passive and active RST as they go through + * different code-paths: + * - tcp_send_active_reset() makes no-data skb, sends it with tcp_transmit_skb() + * - tcp_v*_send_reset() create their reply skbs and send them with + * ip_send_unicast_reply() + * + * In both cases TCP-AO signatures have to be correct, which is verified by + * (1) checking that the TCP-AO connection was reset and (2) TCP-AO counters. + * + * Author: Dmitry Safonov <dima@arista.com> + */ #include <inttypes.h> #include "../../../../include/linux/kernel.h" #include "aolib.h" const size_t quota = 1000; +const size_t packet_sz = 100; /* * Backlog == 0 means 1 connection in queue, see: * commit 64a146513f8f ("[NET]: Revert incorrect accept queue...") @@ -59,26 +82,6 @@ static void close_forced(int sk) close(sk); } -static int test_wait_for_exception(int sk, time_t sec) -{ - struct timeval tv = { .tv_sec = sec }; - struct timeval *ptv = NULL; - fd_set efds; - int ret; - - FD_ZERO(&efds); - FD_SET(sk, &efds); - - if (sec) - ptv = &tv; - - errno = 0; - ret = select(sk + 1, NULL, NULL, &efds, ptv); - if (ret < 0) - return -errno; - return ret ? sk : 0; -} - static void test_server_active_rst(unsigned int port) { struct tcp_ao_counters cnt1, cnt2; @@ -155,17 +158,16 @@ static void test_server_passive_rst(unsigned int port) test_fail("server returned %zd", bytes); } - synchronize_threads(); /* 3: chekpoint/restore the connection */ + synchronize_threads(); /* 3: checkpoint the client */ + synchronize_threads(); /* 4: close the server, creating twsk */ if (test_get_tcp_ao_counters(sk, &ao2)) test_error("test_get_tcp_ao_counters()"); - - synchronize_threads(); /* 4: terminate server + send more on client */ - bytes = test_server_run(sk, quota, TEST_RETRANSMIT_SEC); close(sk); + + synchronize_threads(); /* 5: restore the socket, send more data */ test_tcp_ao_counters_cmp("passive RST server", &ao1, &ao2, TEST_CNT_GOOD); - synchronize_threads(); /* 5: verified => closed */ - close(sk); + synchronize_threads(); /* 6: server exits */ } static void *server_fn(void *arg) @@ -284,7 +286,7 @@ static void test_client_active_rst(unsigned int port) test_error("test_wait_fds(): %d", err); synchronize_threads(); /* 3: close listen socket */ - if (test_client_verify(sk[0], 100, quota / 100, TEST_TIMEOUT_SEC)) + if (test_client_verify(sk[0], packet_sz, quota / packet_sz, TEST_TIMEOUT_SEC)) test_fail("Failed to send data on connected socket"); else test_ok("Verified established tcp connection"); @@ -323,7 +325,6 @@ static void test_client_passive_rst(unsigned int port) struct tcp_sock_state img; sockaddr_af saddr; int sk, err; - socklen_t slen = sizeof(err); sk = socket(test_family, SOCK_STREAM, IPPROTO_TCP); if (sk < 0) @@ -337,18 +338,51 @@ static void test_client_passive_rst(unsigned int port) test_error("failed to connect()"); synchronize_threads(); /* 2: accepted => send data */ - if (test_client_verify(sk, 100, quota / 100, TEST_TIMEOUT_SEC)) + if (test_client_verify(sk, packet_sz, quota / packet_sz, TEST_TIMEOUT_SEC)) test_fail("Failed to send data on connected socket"); else test_ok("Verified established tcp connection"); - synchronize_threads(); /* 3: chekpoint/restore the connection */ + synchronize_threads(); /* 3: checkpoint the client */ test_enable_repair(sk); test_sock_checkpoint(sk, &img, &saddr); test_ao_checkpoint(sk, &ao_img); - test_kill_sk(sk); + test_disable_repair(sk); - img.out.seq += quota; + synchronize_threads(); /* 4: close the server, creating twsk */ + + /* + * The "corruption" in SEQ has to be small enough to fit into TCP + * window, see tcp_timewait_state_process() for out-of-window + * segments. + */ + img.out.seq += 5; /* 5 is more noticeable in tcpdump than 1 */ + + /* + * FIXME: This is kind-of ugly and dirty, but it works. + * + * At this moment, the server has close'ed(sk). + * The passive RST that is being targeted here is new data after + * half-duplex close, see tcp_timewait_state_process() => TCP_TW_RST + * + * What is needed here is: + * (1) wait for FIN from the server + * (2) make sure that the ACK from the client went out + * (3) make sure that the ACK was received and processed by the server + * + * Otherwise, the data that will be sent from "repaired" socket + * post SEQ corruption may get to the server before it's in + * TCP_FIN_WAIT2. + * + * (1) is easy with select()/poll() + * (2) is possible by polling tcpi_state from TCP_INFO + * (3) is quite complex: as server's socket was already closed, + * probably the way to do it would be tcp-diag. + */ + sleep(TEST_RETRANSMIT_SEC); + + synchronize_threads(); /* 5: restore the socket, send more data */ + test_kill_sk(sk); sk = socket(test_family, SOCK_STREAM, IPPROTO_TCP); if (sk < 0) @@ -366,25 +400,33 @@ static void test_client_passive_rst(unsigned int port) test_disable_repair(sk); test_sock_state_free(&img); - synchronize_threads(); /* 4: terminate server + send more on client */ - if (test_client_verify(sk, 100, quota / 100, 2 * TEST_TIMEOUT_SEC)) - test_ok("client connection broken post-seq-adjust"); - else - test_fail("client connection still works post-seq-adjust"); - - test_wait_for_exception(sk, TEST_TIMEOUT_SEC); - - if (getsockopt(sk, SOL_SOCKET, SO_ERROR, &err, &slen)) - test_error("getsockopt()"); - if (err != ECONNRESET && err != EPIPE) - test_fail("client connection was not reset: %d", err); + /* + * This is how "passive reset" is acquired in this test from TCP_TW_RST: + * + * IP 10.0.254.1.7011 > 10.0.1.1.59772: Flags [P.], seq 901:1001, ack 1001, win 249, + * options [tcp-ao keyid 100 rnextkeyid 100 mac 0x10217d6c36a22379086ef3b1], length 100 + * IP 10.0.254.1.7011 > 10.0.1.1.59772: Flags [F.], seq 1001, ack 1001, win 249, + * options [tcp-ao keyid 100 rnextkeyid 100 mac 0x104ffc99b98c10a5298cc268], length 0 + * IP 10.0.1.1.59772 > 10.0.254.1.7011: Flags [.], ack 1002, win 251, + * options [tcp-ao keyid 100 rnextkeyid 100 mac 0xe496dd4f7f5a8a66873c6f93,nop,nop,sack 1 {1001:1002}], length 0 + * IP 10.0.1.1.59772 > 10.0.254.1.7011: Flags [P.], seq 1006:1106, ack 1001, win 251, + * options [tcp-ao keyid 100 rnextkeyid 100 mac 0x1b5f3330fb23fbcd0c77d0ca], length 100 + * IP 10.0.254.1.7011 > 10.0.1.1.59772: Flags [R], seq 3215596252, win 0, + * options [tcp-ao keyid 100 rnextkeyid 100 mac 0x0bcfbbf497bce844312304b2], length 0 + */ + err = test_client_verify(sk, packet_sz, quota / packet_sz, 2 * TEST_TIMEOUT_SEC); + /* Make sure that the connection was reset, not timeouted */ + if (err && err == -ECONNRESET) + test_ok("client sock was passively reset post-seq-adjust"); + else if (err) + test_fail("client sock was not reset post-seq-adjust: %d", err); else - test_ok("client connection was reset"); + test_fail("client sock is yet connected post-seq-adjust"); if (test_get_tcp_ao_counters(sk, &ao2)) test_error("test_get_tcp_ao_counters()"); - synchronize_threads(); /* 5: verified => closed */ + synchronize_threads(); /* 6: server exits */ close(sk); test_tcp_ao_counters_cmp("client passive RST", &ao1, &ao2, TEST_CNT_GOOD); } @@ -410,6 +452,6 @@ static void *client_fn(void *arg) int main(int argc, char *argv[]) { - test_init(15, server_fn, client_fn); + test_init(14, server_fn, client_fn); return 0; } diff --git a/tools/testing/selftests/net/tcp_ao/settings b/tools/testing/selftests/net/tcp_ao/settings new file mode 100644 index 000000000000..6091b45d226b --- /dev/null +++ b/tools/testing/selftests/net/tcp_ao/settings @@ -0,0 +1 @@ +timeout=120 diff --git a/tools/testing/selftests/net/tcp_ao/unsigned-md5.c b/tools/testing/selftests/net/tcp_ao/unsigned-md5.c index c5b568cd7d90..6b59a652159f 100644 --- a/tools/testing/selftests/net/tcp_ao/unsigned-md5.c +++ b/tools/testing/selftests/net/tcp_ao/unsigned-md5.c @@ -110,9 +110,9 @@ static void try_accept(const char *tst_name, unsigned int port, test_tcp_ao_counters_cmp(tst_name, &ao_cnt1, &ao_cnt2, cnt_expected); out: - synchronize_threads(); /* close() */ + synchronize_threads(); /* test_kill_sk() */ if (sk > 0) - close(sk); + test_kill_sk(sk); } static void server_add_routes(void) @@ -302,10 +302,10 @@ static void try_connect(const char *tst_name, unsigned int port, test_ok("%s: connected", tst_name); out: - synchronize_threads(); /* close() */ + synchronize_threads(); /* test_kill_sk() */ /* _test_connect_socket() cleans up on failure */ if (ret > 0) - close(sk); + test_kill_sk(sk); } #define PREINSTALL_MD5_FIRST BIT(0) @@ -486,10 +486,10 @@ static void try_to_add(const char *tst_name, unsigned int port, } out: - synchronize_threads(); /* close() */ + synchronize_threads(); /* test_kill_sk() */ /* _test_connect_socket() cleans up on failure */ if (ret > 0) - close(sk); + test_kill_sk(sk); } static void client_add_ip(union tcp_addr *client, const char *ip) diff --git a/tools/testing/selftests/net/test_bridge_backup_port.sh b/tools/testing/selftests/net/test_bridge_backup_port.sh index 70a7d87ba2d2..1b3f89e2b86e 100755 --- a/tools/testing/selftests/net/test_bridge_backup_port.sh +++ b/tools/testing/selftests/net/test_bridge_backup_port.sh @@ -124,6 +124,16 @@ tc_check_packets() [[ $pkts == $count ]] } +bridge_link_check() +{ + local ns=$1; shift + local dev=$1; shift + local state=$1; shift + + bridge -n $ns -d -j link show dev $dev | \ + jq -e ".[][\"state\"] == \"$state\"" &> /dev/null +} + ################################################################################ # Setup @@ -259,6 +269,7 @@ backup_port() log_test $? 0 "No forwarding out of vx0" run_cmd "ip -n $sw1 link set dev swp1 carrier off" + busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled 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" @@ -268,6 +279,7 @@ backup_port() log_test $? 0 "No forwarding out of vx0" run_cmd "ip -n $sw1 link set dev swp1 carrier on" + busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 forwarding log_test $? 0 "swp1 carrier on" # Configure vx0 as the backup port of swp1 and check that packets are @@ -284,6 +296,7 @@ backup_port() log_test $? 0 "No forwarding out of vx0" run_cmd "ip -n $sw1 link set dev swp1 carrier off" + busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled 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" @@ -293,6 +306,7 @@ backup_port() log_test $? 0 "Forwarding out of vx0" run_cmd "ip -n $sw1 link set dev swp1 carrier on" + busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 forwarding 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" @@ -314,6 +328,7 @@ backup_port() log_test $? 0 "No forwarding out of vx0" run_cmd "ip -n $sw1 link set dev swp1 carrier off" + busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled 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" @@ -369,6 +384,7 @@ backup_nhid() log_test $? 0 "No forwarding out of vx0" run_cmd "ip -n $sw1 link set dev swp1 carrier off" + busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled 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" @@ -382,6 +398,7 @@ backup_nhid() log_test $? 0 "Forwarding using VXLAN FDB entry" run_cmd "ip -n $sw1 link set dev swp1 carrier on" + busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 forwarding log_test $? 0 "swp1 carrier on" # Configure nexthop ID 10 as the backup nexthop ID of swp1 and check @@ -398,6 +415,7 @@ backup_nhid() log_test $? 0 "No forwarding out of vx0" run_cmd "ip -n $sw1 link set dev swp1 carrier off" + busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled 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" @@ -411,6 +429,7 @@ backup_nhid() log_test $? 0 "No forwarding using VXLAN FDB entry" run_cmd "ip -n $sw1 link set dev swp1 carrier on" + busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 forwarding 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" @@ -441,6 +460,7 @@ backup_nhid() log_test $? 0 "No forwarding using VXLAN FDB entry" run_cmd "ip -n $sw1 link set dev swp1 carrier off" + busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled 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" @@ -497,6 +517,7 @@ backup_nhid_invalid() log_test $? 0 "Valid nexthop as backup nexthop" run_cmd "ip -n $sw1 link set dev swp1 carrier off" + busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled 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" @@ -604,7 +625,9 @@ backup_nhid_ping() run_cmd "bridge -n $sw2 link set dev swp1 backup_nhid 10" run_cmd "ip -n $sw1 link set dev swp1 carrier off" + busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled run_cmd "ip -n $sw2 link set dev swp1 carrier off" + busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw2 swp1 disabled 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" diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 7799e042a971..49c84602707f 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -1002,12 +1002,12 @@ TEST_F(tls, recv_partial) memset(recv_mem, 0, sizeof(recv_mem)); EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len); - EXPECT_NE(recv(self->cfd, recv_mem, strlen(test_str_first), - MSG_WAITALL), -1); + EXPECT_EQ(recv(self->cfd, recv_mem, strlen(test_str_first), + MSG_WAITALL), strlen(test_str_first)); EXPECT_EQ(memcmp(test_str_first, recv_mem, strlen(test_str_first)), 0); memset(recv_mem, 0, sizeof(recv_mem)); - EXPECT_NE(recv(self->cfd, recv_mem, strlen(test_str_second), - MSG_WAITALL), -1); + EXPECT_EQ(recv(self->cfd, recv_mem, strlen(test_str_second), + MSG_WAITALL), strlen(test_str_second)); EXPECT_EQ(memcmp(test_str_second, recv_mem, strlen(test_str_second)), 0); } @@ -1874,13 +1874,13 @@ TEST_F(tls_err, poll_partial_rec_async) /* Child should sleep in poll(), never get a wake */ pfd.fd = self->cfd2; pfd.events = POLLIN; - EXPECT_EQ(poll(&pfd, 1, 5), 0); + EXPECT_EQ(poll(&pfd, 1, 20), 0); EXPECT_EQ(write(p[1], &token, 1), 1); /* Barrier #1 */ pfd.fd = self->cfd2; pfd.events = POLLIN; - EXPECT_EQ(poll(&pfd, 1, 5), 1); + EXPECT_EQ(poll(&pfd, 1, 20), 1); exit(!_metadata->passed); } diff --git a/tools/testing/selftests/net/txtimestamp.c b/tools/testing/selftests/net/txtimestamp.c index 10f2fde3686b..ec60a16c9307 100644 --- a/tools/testing/selftests/net/txtimestamp.c +++ b/tools/testing/selftests/net/txtimestamp.c @@ -163,7 +163,8 @@ static void validate_timestamp(struct timespec *cur, int min_delay) if (cur64 < start64 + min_delay || cur64 > start64 + max_delay) { fprintf(stderr, "ERROR: %" PRId64 " us expected between %d and %d\n", cur64 - start64, min_delay, max_delay); - test_failed = true; + if (!getenv("KSFT_MACHINE_SLOW")) + test_failed = true; } } diff --git a/tools/testing/selftests/net/txtimestamp.sh b/tools/testing/selftests/net/txtimestamp.sh index 31637769f59f..25baca4b148e 100755 --- a/tools/testing/selftests/net/txtimestamp.sh +++ b/tools/testing/selftests/net/txtimestamp.sh @@ -8,13 +8,13 @@ set -e setup() { # set 1ms delay on lo egress - tc qdisc add dev lo root netem delay 1ms + tc qdisc add dev lo root netem delay 10ms # set 2ms delay on ifb0 egress modprobe ifb ip link add ifb_netem0 type ifb ip link set dev ifb_netem0 up - tc qdisc add dev ifb_netem0 root netem delay 2ms + tc qdisc add dev ifb_netem0 root netem delay 20ms # redirect lo ingress through ifb0 egress tc qdisc add dev lo handle ffff: ingress @@ -24,9 +24,11 @@ setup() { } run_test_v4v6() { - # SND will be delayed 1000us - # ACK will be delayed 6000us: 1 + 2 ms round-trip - local -r args="$@ -v 1000 -V 6000" + # SND will be delayed 10ms + # ACK will be delayed 60ms: 10 + 20 ms round-trip + # allow +/- tolerance of 8ms + # wait for ACK to be queued + local -r args="$@ -v 10000 -V 60000 -t 8000 -S 80000" ./txtimestamp ${args} -4 -L 127.0.0.1 ./txtimestamp ${args} -6 -L ::1 diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh index af5dc57c8ce9..8802604148dd 100755 --- a/tools/testing/selftests/net/udpgro.sh +++ b/tools/testing/selftests/net/udpgro.sh @@ -7,7 +7,7 @@ source net_helper.sh readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)" -BPF_FILE="../bpf/xdp_dummy.bpf.o" +BPF_FILE="xdp_dummy.o" # set global exit status, but never reset nonzero one. check_err() @@ -197,7 +197,7 @@ run_all() { } if [ ! -f ${BPF_FILE} ]; then - echo "Missing ${BPF_FILE}. Build bpf selftest first" + echo "Missing ${BPF_FILE}. Run 'make' first" exit -1 fi diff --git a/tools/testing/selftests/net/udpgro_bench.sh b/tools/testing/selftests/net/udpgro_bench.sh index cb664679b434..7080eae5312b 100755 --- a/tools/testing/selftests/net/udpgro_bench.sh +++ b/tools/testing/selftests/net/udpgro_bench.sh @@ -7,7 +7,7 @@ source net_helper.sh readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)" -BPF_FILE="../bpf/xdp_dummy.bpf.o" +BPF_FILE="xdp_dummy.o" cleanup() { local -r jobs="$(jobs -p)" @@ -84,7 +84,7 @@ run_all() { } if [ ! -f ${BPF_FILE} ]; then - echo "Missing ${BPF_FILE}. Build bpf selftest first" + echo "Missing ${BPF_FILE}. Run 'make' first" exit -1 fi diff --git a/tools/testing/selftests/net/udpgro_frglist.sh b/tools/testing/selftests/net/udpgro_frglist.sh index dd47fa96f6b3..e1ff645bd3d1 100755 --- a/tools/testing/selftests/net/udpgro_frglist.sh +++ b/tools/testing/selftests/net/udpgro_frglist.sh @@ -7,7 +7,7 @@ source net_helper.sh readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)" -BPF_FILE="../bpf/xdp_dummy.bpf.o" +BPF_FILE="xdp_dummy.o" cleanup() { local -r jobs="$(jobs -p)" @@ -85,12 +85,12 @@ run_all() { } if [ ! -f ${BPF_FILE} ]; then - echo "Missing ${BPF_FILE}. Build bpf selftest first" + echo "Missing ${BPF_FILE}. Run 'make' first" exit -1 fi if [ ! -f nat6to4.o ]; then - echo "Missing nat6to4 helper. Build bpf nat6to4.o selftest first" + echo "Missing nat6to4 helper. Run 'make' first" exit -1 fi diff --git a/tools/testing/selftests/net/udpgro_fwd.sh b/tools/testing/selftests/net/udpgro_fwd.sh index c079565add39..9cd5e885e91f 100755 --- a/tools/testing/selftests/net/udpgro_fwd.sh +++ b/tools/testing/selftests/net/udpgro_fwd.sh @@ -1,7 +1,9 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 -BPF_FILE="../bpf/xdp_dummy.bpf.o" +source net_helper.sh + +BPF_FILE="xdp_dummy.o" readonly BASE="ns-$(mktemp -u XXXXXX)" readonly SRC=2 readonly DST=1 @@ -37,6 +39,10 @@ create_ns() { for ns in $NS_SRC $NS_DST; do ip netns add $ns ip -n $ns link set dev lo up + + # disable route solicitations to decrease 'noise' traffic + ip netns exec $ns sysctl -qw net.ipv6.conf.default.router_solicitations=0 + ip netns exec $ns sysctl -qw net.ipv6.conf.all.router_solicitations=0 done ip link add name veth$SRC type veth peer name veth$DST @@ -78,6 +84,12 @@ create_vxlan_pair() { create_vxlan_endpoint $BASE$ns veth$ns $BM_NET_V6$((3 - $ns)) vxlan6$ns 6 ip -n $BASE$ns addr add dev vxlan6$ns $OL_NET_V6$ns/24 nodad done + + # preload neighbur cache, do avoid some noisy traffic + local addr_dst=$(ip -j -n $BASE$DST link show dev vxlan6$DST |jq -r '.[]["address"]') + local addr_src=$(ip -j -n $BASE$SRC link show dev vxlan6$SRC |jq -r '.[]["address"]') + ip -n $BASE$DST neigh add dev vxlan6$DST lladdr $addr_src $OL_NET_V6$SRC + ip -n $BASE$SRC neigh add dev vxlan6$SRC lladdr $addr_dst $OL_NET_V6$DST } is_ipv6() { @@ -117,9 +129,9 @@ run_test() { # not enable GRO ip netns exec $NS_DST $ipt -A INPUT -p udp --dport 4789 ip netns exec $NS_DST $ipt -A INPUT -p udp --dport 8000 - ip netns exec $NS_DST ./udpgso_bench_rx -C 1000 -R 10 -n 10 -l 1300 $rx_args & + ip netns exec $NS_DST ./udpgso_bench_rx -C 2000 -R 100 -n 10 -l 1300 $rx_args & local spid=$! - sleep 0.1 + wait_local_port_listen "$NS_DST" 8000 udp ip netns exec $NS_SRC ./udpgso_bench_tx $family -M 1 -s 13000 -S 1300 -D $dst local retc=$? wait $spid @@ -166,9 +178,9 @@ run_bench() { # bind the sender and the receiver to different CPUs to try # get reproducible results ip netns exec $NS_DST bash -c "echo 2 > /sys/class/net/veth$DST/queues/rx-0/rps_cpus" - ip netns exec $NS_DST taskset 0x2 ./udpgso_bench_rx -C 1000 -R 10 & + ip netns exec $NS_DST taskset 0x2 ./udpgso_bench_rx -C 2000 -R 100 & local spid=$! - sleep 0.1 + wait_local_port_listen "$NS_DST" 8000 udp ip netns exec $NS_SRC taskset 0x1 ./udpgso_bench_tx $family -l 3 -S 1300 -D $dst local retc=$? wait $spid diff --git a/tools/testing/selftests/net/udpgso.c b/tools/testing/selftests/net/udpgso.c index 7badaf215de2..1d975bf52af3 100644 --- a/tools/testing/selftests/net/udpgso.c +++ b/tools/testing/selftests/net/udpgso.c @@ -56,7 +56,6 @@ static bool cfg_do_msgmore; static bool cfg_do_setsockopt; static int cfg_specific_test_id = -1; -static const char cfg_ifname[] = "lo"; static unsigned short cfg_port = 9000; static char buf[ETH_MAX_MTU]; @@ -69,8 +68,13 @@ struct testcase { int r_len_last; /* recv(): size of last non-mss dgram, if any */ }; -const struct in6_addr addr6 = IN6ADDR_LOOPBACK_INIT; -const struct in_addr addr4 = { .s_addr = __constant_htonl(INADDR_LOOPBACK + 2) }; +const struct in6_addr addr6 = { + { { 0xfd, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1 } }, /* fd00::1 */ +}; + +const struct in_addr addr4 = { + __constant_htonl(0x0a000001), /* 10.0.0.1 */ +}; struct testcase testcases_v4[] = { { @@ -274,48 +278,6 @@ struct testcase testcases_v6[] = { } }; -static unsigned int get_device_mtu(int fd, const char *ifname) -{ - struct ifreq ifr; - - memset(&ifr, 0, sizeof(ifr)); - - strcpy(ifr.ifr_name, ifname); - - if (ioctl(fd, SIOCGIFMTU, &ifr)) - error(1, errno, "ioctl get mtu"); - - return ifr.ifr_mtu; -} - -static void __set_device_mtu(int fd, const char *ifname, unsigned int mtu) -{ - struct ifreq ifr; - - memset(&ifr, 0, sizeof(ifr)); - - ifr.ifr_mtu = mtu; - strcpy(ifr.ifr_name, ifname); - - if (ioctl(fd, SIOCSIFMTU, &ifr)) - error(1, errno, "ioctl set mtu"); -} - -static void set_device_mtu(int fd, int mtu) -{ - int val; - - val = get_device_mtu(fd, cfg_ifname); - fprintf(stderr, "device mtu (orig): %u\n", val); - - __set_device_mtu(fd, cfg_ifname, mtu); - val = get_device_mtu(fd, cfg_ifname); - if (val != mtu) - error(1, 0, "unable to set device mtu to %u\n", val); - - fprintf(stderr, "device mtu (test): %u\n", val); -} - static void set_pmtu_discover(int fd, bool is_ipv4) { int level, name, val; @@ -354,81 +316,6 @@ static unsigned int get_path_mtu(int fd, bool is_ipv4) return mtu; } -/* very wordy version of system("ip route add dev lo mtu 1500 127.0.0.3/32") */ -static void set_route_mtu(int mtu, bool is_ipv4) -{ - struct sockaddr_nl nladdr = { .nl_family = AF_NETLINK }; - struct nlmsghdr *nh; - struct rtattr *rta; - struct rtmsg *rt; - char data[NLMSG_ALIGN(sizeof(*nh)) + - NLMSG_ALIGN(sizeof(*rt)) + - NLMSG_ALIGN(RTA_LENGTH(sizeof(addr6))) + - NLMSG_ALIGN(RTA_LENGTH(sizeof(int))) + - NLMSG_ALIGN(RTA_LENGTH(0) + RTA_LENGTH(sizeof(int)))]; - int fd, ret, alen, off = 0; - - alen = is_ipv4 ? sizeof(addr4) : sizeof(addr6); - - fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE); - if (fd == -1) - error(1, errno, "socket netlink"); - - memset(data, 0, sizeof(data)); - - nh = (void *)data; - nh->nlmsg_type = RTM_NEWROUTE; - nh->nlmsg_flags = NLM_F_REQUEST | NLM_F_CREATE; - off += NLMSG_ALIGN(sizeof(*nh)); - - rt = (void *)(data + off); - rt->rtm_family = is_ipv4 ? AF_INET : AF_INET6; - rt->rtm_table = RT_TABLE_MAIN; - rt->rtm_dst_len = alen << 3; - rt->rtm_protocol = RTPROT_BOOT; - rt->rtm_scope = RT_SCOPE_UNIVERSE; - rt->rtm_type = RTN_UNICAST; - off += NLMSG_ALIGN(sizeof(*rt)); - - rta = (void *)(data + off); - rta->rta_type = RTA_DST; - rta->rta_len = RTA_LENGTH(alen); - if (is_ipv4) - memcpy(RTA_DATA(rta), &addr4, alen); - else - memcpy(RTA_DATA(rta), &addr6, alen); - off += NLMSG_ALIGN(rta->rta_len); - - rta = (void *)(data + off); - rta->rta_type = RTA_OIF; - rta->rta_len = RTA_LENGTH(sizeof(int)); - *((int *)(RTA_DATA(rta))) = 1; //if_nametoindex("lo"); - off += NLMSG_ALIGN(rta->rta_len); - - /* MTU is a subtype in a metrics type */ - rta = (void *)(data + off); - rta->rta_type = RTA_METRICS; - rta->rta_len = RTA_LENGTH(0) + RTA_LENGTH(sizeof(int)); - off += NLMSG_ALIGN(rta->rta_len); - - /* now fill MTU subtype. Note that it fits within above rta_len */ - rta = (void *)(((char *) rta) + RTA_LENGTH(0)); - rta->rta_type = RTAX_MTU; - rta->rta_len = RTA_LENGTH(sizeof(int)); - *((int *)(RTA_DATA(rta))) = mtu; - - nh->nlmsg_len = off; - - ret = sendto(fd, data, off, 0, (void *)&nladdr, sizeof(nladdr)); - if (ret != off) - error(1, errno, "send netlink: %uB != %uB\n", ret, off); - - if (close(fd)) - error(1, errno, "close netlink"); - - fprintf(stderr, "route mtu (test): %u\n", mtu); -} - static bool __send_one(int fd, struct msghdr *msg, int flags) { int ret; @@ -591,15 +478,10 @@ static void run_test(struct sockaddr *addr, socklen_t alen) /* Do not fragment these datagrams: only succeed if GSO works */ set_pmtu_discover(fdt, addr->sa_family == AF_INET); - if (cfg_do_connectionless) { - set_device_mtu(fdt, CONST_MTU_TEST); + if (cfg_do_connectionless) run_all(fdt, fdr, addr, alen); - } if (cfg_do_connected) { - set_device_mtu(fdt, CONST_MTU_TEST + 100); - set_route_mtu(CONST_MTU_TEST, addr->sa_family == AF_INET); - if (connect(fdt, addr, alen)) error(1, errno, "connect"); diff --git a/tools/testing/selftests/net/udpgso.sh b/tools/testing/selftests/net/udpgso.sh index fec24f584fe9..6c63178086b0 100755 --- a/tools/testing/selftests/net/udpgso.sh +++ b/tools/testing/selftests/net/udpgso.sh @@ -3,27 +3,56 @@ # # Run a series of udpgso regression tests +set -o errexit +set -o nounset + +setup_loopback() { + ip addr add dev lo 10.0.0.1/32 + ip addr add dev lo fd00::1/128 nodad noprefixroute +} + +test_dev_mtu() { + setup_loopback + # Reduce loopback MTU + ip link set dev lo mtu 1500 +} + +test_route_mtu() { + setup_loopback + # Remove default local routes + ip route del local 10.0.0.1/32 table local dev lo + ip route del local fd00::1/128 table local dev lo + # Install local routes with reduced MTU + ip route add local 10.0.0.1/32 table local dev lo mtu 1500 + ip route add local fd00::1/128 table local dev lo mtu 1500 +} + +if [ "$#" -gt 0 ]; then + "$1" + shift 2 # pop "test_*" arg and "--" delimiter + exec "$@" +fi + echo "ipv4 cmsg" -./in_netns.sh ./udpgso -4 -C +./in_netns.sh "$0" test_dev_mtu -- ./udpgso -4 -C echo "ipv4 setsockopt" -./in_netns.sh ./udpgso -4 -C -s +./in_netns.sh "$0" test_dev_mtu -- ./udpgso -4 -C -s echo "ipv6 cmsg" -./in_netns.sh ./udpgso -6 -C +./in_netns.sh "$0" test_dev_mtu -- ./udpgso -6 -C echo "ipv6 setsockopt" -./in_netns.sh ./udpgso -6 -C -s +./in_netns.sh "$0" test_dev_mtu -- ./udpgso -6 -C -s echo "ipv4 connected" -./in_netns.sh ./udpgso -4 -c +./in_netns.sh "$0" test_route_mtu -- ./udpgso -4 -c -# blocked on 2nd loopback address -# echo "ipv6 connected" -# ./in_netns.sh ./udpgso -6 -c +echo "ipv6 connected" +./in_netns.sh "$0" test_route_mtu -- ./udpgso -6 -c echo "ipv4 msg_more" -./in_netns.sh ./udpgso -4 -C -m +./in_netns.sh "$0" test_dev_mtu -- ./udpgso -4 -C -m echo "ipv6 msg_more" -./in_netns.sh ./udpgso -6 -C -m +./in_netns.sh "$0" test_dev_mtu -- ./udpgso -6 -C -m diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c index f35a924d4a30..1cbadd267c96 100644 --- a/tools/testing/selftests/net/udpgso_bench_rx.c +++ b/tools/testing/selftests/net/udpgso_bench_rx.c @@ -375,7 +375,7 @@ static void do_recv(void) do_flush_udp(fd); tnow = gettimeofday_ms(); - if (tnow > treport) { + if (!cfg_expected_pkt_nr && tnow > treport) { if (packets) fprintf(stderr, "%s rx: %6lu MB/s %8lu calls/s\n", diff --git a/tools/testing/selftests/net/veth.sh b/tools/testing/selftests/net/veth.sh index 2d073595c620..27574bbf2d63 100755 --- a/tools/testing/selftests/net/veth.sh +++ b/tools/testing/selftests/net/veth.sh @@ -1,7 +1,7 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 -BPF_FILE="../bpf/xdp_dummy.bpf.o" +BPF_FILE="xdp_dummy.o" readonly STATS="$(mktemp -p /tmp ns-XXXXXX)" readonly BASE=`basename $STATS` readonly SRC=2 @@ -218,7 +218,7 @@ while getopts "hs:" option; do done if [ ! -f ${BPF_FILE} ]; then - echo "Missing ${BPF_FILE}. Build bpf selftest first" + echo "Missing ${BPF_FILE}. Run 'make' first" exit 1 fi diff --git a/tools/testing/selftests/net/xdp_dummy.c b/tools/testing/selftests/net/xdp_dummy.c new file mode 100644 index 000000000000..d988b2e0cee8 --- /dev/null +++ b/tools/testing/selftests/net/xdp_dummy.c @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define KBUILD_MODNAME "xdp_dummy" +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +SEC("xdp") +int xdp_dummy_prog(struct xdp_md *ctx) +{ + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/netfilter/conntrack_dump_flush.c b/tools/testing/selftests/netfilter/conntrack_dump_flush.c index f18c6db13bbf..b11ea8ee6719 100644 --- a/tools/testing/selftests/netfilter/conntrack_dump_flush.c +++ b/tools/testing/selftests/netfilter/conntrack_dump_flush.c @@ -13,7 +13,7 @@ #include "../kselftest_harness.h" #define TEST_ZONE_ID 123 -#define CTA_FILTER_F_CTA_TUPLE_ZONE (1 << 2) +#define NF_CT_DEFAULT_ZONE_ID 0 static int reply_counter; @@ -336,6 +336,9 @@ FIXTURE_SETUP(conntrack_dump_flush) ret = conntrack_data_generate_v4(self->sock, 0xf4f4f4f4, 0xf5f5f5f5, TEST_ZONE_ID + 2); EXPECT_EQ(ret, 0); + ret = conntrack_data_generate_v4(self->sock, 0xf6f6f6f6, 0xf7f7f7f7, + NF_CT_DEFAULT_ZONE_ID); + EXPECT_EQ(ret, 0); src = (struct in6_addr) {{ .__u6_addr32 = { @@ -395,6 +398,26 @@ FIXTURE_SETUP(conntrack_dump_flush) TEST_ZONE_ID + 2); EXPECT_EQ(ret, 0); + src = (struct in6_addr) {{ + .__u6_addr32 = { + 0xb80d0120, + 0x00000000, + 0x00000000, + 0x07000000 + } + }}; + dst = (struct in6_addr) {{ + .__u6_addr32 = { + 0xb80d0120, + 0x00000000, + 0x00000000, + 0x08000000 + } + }}; + ret = conntrack_data_generate_v6(self->sock, src, dst, + NF_CT_DEFAULT_ZONE_ID); + EXPECT_EQ(ret, 0); + ret = conntracK_count_zone(self->sock, TEST_ZONE_ID); EXPECT_GE(ret, 2); if (ret > 2) @@ -425,6 +448,24 @@ TEST_F(conntrack_dump_flush, test_flush_by_zone) EXPECT_EQ(ret, 2); ret = conntracK_count_zone(self->sock, TEST_ZONE_ID + 2); EXPECT_EQ(ret, 2); + ret = conntracK_count_zone(self->sock, NF_CT_DEFAULT_ZONE_ID); + EXPECT_EQ(ret, 2); +} + +TEST_F(conntrack_dump_flush, test_flush_by_zone_default) +{ + int ret; + + ret = conntrack_flush_zone(self->sock, NF_CT_DEFAULT_ZONE_ID); + EXPECT_EQ(ret, 0); + ret = conntracK_count_zone(self->sock, TEST_ZONE_ID); + EXPECT_EQ(ret, 2); + ret = conntracK_count_zone(self->sock, TEST_ZONE_ID + 1); + EXPECT_EQ(ret, 2); + ret = conntracK_count_zone(self->sock, TEST_ZONE_ID + 2); + EXPECT_EQ(ret, 2); + ret = conntracK_count_zone(self->sock, NF_CT_DEFAULT_ZONE_ID); + EXPECT_EQ(ret, 0); } TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/rseq/basic_percpu_ops_test.c b/tools/testing/selftests/rseq/basic_percpu_ops_test.c index 887542961968..2348d2c20d0a 100644 --- a/tools/testing/selftests/rseq/basic_percpu_ops_test.c +++ b/tools/testing/selftests/rseq/basic_percpu_ops_test.c @@ -24,6 +24,11 @@ bool rseq_validate_cpu_id(void) { return rseq_mm_cid_available(); } +static +bool rseq_use_cpu_index(void) +{ + return false; /* Use mm_cid */ +} #else # define RSEQ_PERCPU RSEQ_PERCPU_CPU_ID static @@ -36,6 +41,11 @@ bool rseq_validate_cpu_id(void) { return rseq_current_cpu_raw() >= 0; } +static +bool rseq_use_cpu_index(void) +{ + return true; /* Use cpu_id as index. */ +} #endif struct percpu_lock_entry { @@ -274,7 +284,7 @@ void test_percpu_list(void) /* Generate list entries for every usable cpu. */ sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus); for (i = 0; i < CPU_SETSIZE; i++) { - if (!CPU_ISSET(i, &allowed_cpus)) + if (rseq_use_cpu_index() && !CPU_ISSET(i, &allowed_cpus)) continue; for (j = 1; j <= 100; j++) { struct percpu_list_node *node; @@ -299,7 +309,7 @@ void test_percpu_list(void) for (i = 0; i < CPU_SETSIZE; i++) { struct percpu_list_node *node; - if (!CPU_ISSET(i, &allowed_cpus)) + if (rseq_use_cpu_index() && !CPU_ISSET(i, &allowed_cpus)) continue; while ((node = __percpu_list_pop(&list, i))) { diff --git a/tools/testing/selftests/rseq/param_test.c b/tools/testing/selftests/rseq/param_test.c index 20403d58345c..2f37961240ca 100644 --- a/tools/testing/selftests/rseq/param_test.c +++ b/tools/testing/selftests/rseq/param_test.c @@ -288,6 +288,11 @@ bool rseq_validate_cpu_id(void) { return rseq_mm_cid_available(); } +static +bool rseq_use_cpu_index(void) +{ + return false; /* Use mm_cid */ +} # ifdef TEST_MEMBARRIER /* * Membarrier does not currently support targeting a mm_cid, so @@ -312,6 +317,11 @@ bool rseq_validate_cpu_id(void) { return rseq_current_cpu_raw() >= 0; } +static +bool rseq_use_cpu_index(void) +{ + return true; /* Use cpu_id as index. */ +} # ifdef TEST_MEMBARRIER static int rseq_membarrier_expedited(int cpu) @@ -715,7 +725,7 @@ void test_percpu_list(void) /* Generate list entries for every usable cpu. */ sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus); for (i = 0; i < CPU_SETSIZE; i++) { - if (!CPU_ISSET(i, &allowed_cpus)) + if (rseq_use_cpu_index() && !CPU_ISSET(i, &allowed_cpus)) continue; for (j = 1; j <= 100; j++) { struct percpu_list_node *node; @@ -752,7 +762,7 @@ void test_percpu_list(void) for (i = 0; i < CPU_SETSIZE; i++) { struct percpu_list_node *node; - if (!CPU_ISSET(i, &allowed_cpus)) + if (rseq_use_cpu_index() && !CPU_ISSET(i, &allowed_cpus)) continue; while ((node = __percpu_list_pop(&list, i))) { @@ -902,7 +912,7 @@ void test_percpu_buffer(void) /* Generate list entries for every usable cpu. */ sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus); for (i = 0; i < CPU_SETSIZE; i++) { - if (!CPU_ISSET(i, &allowed_cpus)) + if (rseq_use_cpu_index() && !CPU_ISSET(i, &allowed_cpus)) continue; /* Worse-case is every item in same CPU. */ buffer.c[i].array = @@ -952,7 +962,7 @@ void test_percpu_buffer(void) for (i = 0; i < CPU_SETSIZE; i++) { struct percpu_buffer_node *node; - if (!CPU_ISSET(i, &allowed_cpus)) + if (rseq_use_cpu_index() && !CPU_ISSET(i, &allowed_cpus)) continue; while ((node = __percpu_buffer_pop(&buffer, i))) { @@ -1113,7 +1123,7 @@ void test_percpu_memcpy_buffer(void) /* Generate list entries for every usable cpu. */ sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus); for (i = 0; i < CPU_SETSIZE; i++) { - if (!CPU_ISSET(i, &allowed_cpus)) + if (rseq_use_cpu_index() && !CPU_ISSET(i, &allowed_cpus)) continue; /* Worse-case is every item in same CPU. */ buffer.c[i].array = @@ -1160,7 +1170,7 @@ void test_percpu_memcpy_buffer(void) for (i = 0; i < CPU_SETSIZE; i++) { struct percpu_memcpy_buffer_node item; - if (!CPU_ISSET(i, &allowed_cpus)) + if (rseq_use_cpu_index() && !CPU_ISSET(i, &allowed_cpus)) continue; while (__percpu_memcpy_buffer_pop(&buffer, &item, i)) { diff --git a/tools/testing/selftests/seccomp/seccomp_benchmark.c b/tools/testing/selftests/seccomp/seccomp_benchmark.c index 5b5c9d558dee..97b86980b768 100644 --- a/tools/testing/selftests/seccomp/seccomp_benchmark.c +++ b/tools/testing/selftests/seccomp/seccomp_benchmark.c @@ -38,10 +38,10 @@ unsigned long long timing(clockid_t clk_id, unsigned long long samples) i *= 1000000000ULL; i += finish.tv_nsec - start.tv_nsec; - printf("%lu.%09lu - %lu.%09lu = %llu (%.1fs)\n", - finish.tv_sec, finish.tv_nsec, - start.tv_sec, start.tv_nsec, - i, (double)i / 1000000000.0); + ksft_print_msg("%lu.%09lu - %lu.%09lu = %llu (%.1fs)\n", + finish.tv_sec, finish.tv_nsec, + start.tv_sec, start.tv_nsec, + i, (double)i / 1000000000.0); return i; } @@ -53,7 +53,7 @@ unsigned long long calibrate(void) pid_t pid, ret; int seconds = 15; - printf("Calibrating sample size for %d seconds worth of syscalls ...\n", seconds); + ksft_print_msg("Calibrating sample size for %d seconds worth of syscalls ...\n", seconds); samples = 0; pid = getpid(); @@ -98,24 +98,36 @@ bool le(int i_one, int i_two) } long compare(const char *name_one, const char *name_eval, const char *name_two, - unsigned long long one, bool (*eval)(int, int), unsigned long long two) + unsigned long long one, bool (*eval)(int, int), unsigned long long two, + bool skip) { bool good; - printf("\t%s %s %s (%lld %s %lld): ", name_one, name_eval, name_two, - (long long)one, name_eval, (long long)two); + if (skip) { + ksft_test_result_skip("%s %s %s\n", name_one, name_eval, + name_two); + return 0; + } + + ksft_print_msg("\t%s %s %s (%lld %s %lld): ", name_one, name_eval, name_two, + (long long)one, name_eval, (long long)two); if (one > INT_MAX) { - printf("Miscalculation! Measurement went negative: %lld\n", (long long)one); - return 1; + ksft_print_msg("Miscalculation! Measurement went negative: %lld\n", (long long)one); + good = false; + goto out; } if (two > INT_MAX) { - printf("Miscalculation! Measurement went negative: %lld\n", (long long)two); - return 1; + ksft_print_msg("Miscalculation! Measurement went negative: %lld\n", (long long)two); + good = false; + goto out; } good = eval(one, two); printf("%s\n", good ? "✔️" : "❌"); +out: + ksft_test_result(good, "%s %s %s\n", name_one, name_eval, name_two); + return good ? 0 : 1; } @@ -142,15 +154,22 @@ int main(int argc, char *argv[]) unsigned long long samples, calc; unsigned long long native, filter1, filter2, bitmap1, bitmap2; unsigned long long entry, per_filter1, per_filter2; + bool skip = false; setbuf(stdout, NULL); - printf("Running on:\n"); + ksft_print_header(); + ksft_set_plan(7); + + ksft_print_msg("Running on:\n"); + ksft_print_msg(""); system("uname -a"); - printf("Current BPF sysctl settings:\n"); + ksft_print_msg("Current BPF sysctl settings:\n"); /* Avoid using "sysctl" which may not be installed. */ + ksft_print_msg(""); system("grep -H . /proc/sys/net/core/bpf_jit_enable"); + ksft_print_msg(""); system("grep -H . /proc/sys/net/core/bpf_jit_harden"); if (argc > 1) @@ -158,11 +177,11 @@ int main(int argc, char *argv[]) else samples = calibrate(); - printf("Benchmarking %llu syscalls...\n", samples); + ksft_print_msg("Benchmarking %llu syscalls...\n", samples); /* Native call */ native = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples; - printf("getpid native: %llu ns\n", native); + ksft_print_msg("getpid native: %llu ns\n", native); ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); assert(ret == 0); @@ -172,35 +191,37 @@ int main(int argc, char *argv[]) assert(ret == 0); bitmap1 = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples; - printf("getpid RET_ALLOW 1 filter (bitmap): %llu ns\n", bitmap1); + ksft_print_msg("getpid RET_ALLOW 1 filter (bitmap): %llu ns\n", bitmap1); /* Second filter resulting in a bitmap */ ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &bitmap_prog); assert(ret == 0); bitmap2 = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples; - printf("getpid RET_ALLOW 2 filters (bitmap): %llu ns\n", bitmap2); + ksft_print_msg("getpid RET_ALLOW 2 filters (bitmap): %llu ns\n", bitmap2); /* Third filter, can no longer be converted to bitmap */ ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog); assert(ret == 0); filter1 = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples; - printf("getpid RET_ALLOW 3 filters (full): %llu ns\n", filter1); + ksft_print_msg("getpid RET_ALLOW 3 filters (full): %llu ns\n", filter1); /* Fourth filter, can not be converted to bitmap because of filter 3 */ ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &bitmap_prog); assert(ret == 0); filter2 = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples; - printf("getpid RET_ALLOW 4 filters (full): %llu ns\n", filter2); + ksft_print_msg("getpid RET_ALLOW 4 filters (full): %llu ns\n", filter2); /* Estimations */ #define ESTIMATE(fmt, var, what) do { \ var = (what); \ - printf("Estimated " fmt ": %llu ns\n", var); \ - if (var > INT_MAX) \ - goto more_samples; \ + ksft_print_msg("Estimated " fmt ": %llu ns\n", var); \ + if (var > INT_MAX) { \ + skip = true; \ + ret |= 1; \ + } \ } while (0) ESTIMATE("total seccomp overhead for 1 bitmapped filter", calc, @@ -218,31 +239,34 @@ int main(int argc, char *argv[]) ESTIMATE("seccomp per-filter overhead (filters / 4)", per_filter2, (filter2 - native - entry) / 4); - printf("Expectations:\n"); - ret |= compare("native", "≤", "1 bitmap", native, le, bitmap1); - bits = compare("native", "≤", "1 filter", native, le, filter1); + ksft_print_msg("Expectations:\n"); + ret |= compare("native", "≤", "1 bitmap", native, le, bitmap1, + skip); + bits = compare("native", "≤", "1 filter", native, le, filter1, + skip); if (bits) - goto more_samples; + skip = true; ret |= compare("per-filter (last 2 diff)", "≈", "per-filter (filters / 4)", - per_filter1, approx, per_filter2); + per_filter1, approx, per_filter2, skip); bits = compare("1 bitmapped", "≈", "2 bitmapped", - bitmap1 - native, approx, bitmap2 - native); + bitmap1 - native, approx, bitmap2 - native, skip); if (bits) { - printf("Skipping constant action bitmap expectations: they appear unsupported.\n"); - goto out; + ksft_print_msg("Skipping constant action bitmap expectations: they appear unsupported.\n"); + skip = true; } - ret |= compare("entry", "≈", "1 bitmapped", entry, approx, bitmap1 - native); - ret |= compare("entry", "≈", "2 bitmapped", entry, approx, bitmap2 - native); + ret |= compare("entry", "≈", "1 bitmapped", entry, approx, + bitmap1 - native, skip); + ret |= compare("entry", "≈", "2 bitmapped", entry, approx, + bitmap2 - native, skip); ret |= compare("native + entry + (per filter * 4)", "≈", "4 filters total", - entry + (per_filter1 * 4) + native, approx, filter2); - if (ret == 0) - goto out; + entry + (per_filter1 * 4) + native, approx, filter2, + skip); -more_samples: - printf("Saw unexpected benchmark result. Try running again with more samples?\n"); -out: - return 0; + if (ret) + ksft_print_msg("Saw unexpected benchmark result. Try running again with more samples?\n"); + + ksft_finished(); } diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json b/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json index b53d12909962..795cf1ce8af0 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json @@ -649,5 +649,401 @@ "teardown": [ "$TC actions flush action mirred" ] + }, + { + "id": "456d", + "name": "Add mirred mirror to egress block action", + "category": [ + "actions", + "mirred" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + [ + "$TC actions flush action mirred", + 0, + 1, + 255 + ], + [ + "$TC qdisc add dev $DEV1 egress_block 21 clsact", + 0 + ] + ], + "cmdUnderTest": "$TC actions add action mirred egress mirror index 1 blockid 21", + "expExitCode": "0", + "verifyCmd": "$TC -j actions get action mirred index 1", + "matchJSON": [ + { + "total acts": 0 + }, + { + "actions": [ + { + "order": 1, + "kind": "mirred", + "mirred_action": "mirror", + "direction": "egress", + "to_blockid": 21, + "control_action": { + "type": "pipe" + }, + "index": 1, + "ref": 1, + "bind": 0, + "not_in_hw": true + } + ] + } + ], + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 egress_block 21 clsact", + "$TC actions flush action mirred" + ] + }, + { + "id": "2358", + "name": "Add mirred mirror to ingress block action", + "category": [ + "actions", + "mirred" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + [ + "$TC actions flush action mirred", + 0, + 1, + 255 + ], + [ + "$TC qdisc add dev $DEV1 ingress_block 21 clsact", + 0 + ] + ], + "cmdUnderTest": "$TC actions add action mirred ingress mirror index 1 blockid 21", + "expExitCode": "0", + "verifyCmd": "$TC -j actions get action mirred index 1", + "matchJSON": [ + { + "total acts": 0 + }, + { + "actions": [ + { + "order": 1, + "kind": "mirred", + "mirred_action": "mirror", + "direction": "ingress", + "to_blockid": 21, + "control_action": { + "type": "pipe" + }, + "index": 1, + "ref": 1, + "bind": 0, + "not_in_hw": true + } + ] + } + ], + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress_block 21 clsact", + "$TC actions flush action mirred" + ] + }, + { + "id": "fdb1", + "name": "Add mirred redirect to egress block action", + "category": [ + "actions", + "mirred" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + [ + "$TC actions flush action mirred", + 0, + 1, + 255 + ], + [ + "$TC qdisc add dev $DEV1 ingress_block 21 clsact", + 0 + ] + ], + "cmdUnderTest": "$TC actions add action mirred egress redirect index 1 blockid 21", + "expExitCode": "0", + "verifyCmd": "$TC -j actions get action mirred index 1", + "matchJSON": [ + { + "total acts": 0 + }, + { + "actions": [ + { + "order": 1, + "kind": "mirred", + "mirred_action": "redirect", + "direction": "egress", + "to_blockid": 21, + "control_action": { + "type": "stolen" + }, + "index": 1, + "ref": 1, + "bind": 0, + "not_in_hw": true + } + ] + } + ], + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress_block 21 clsact", + "$TC actions flush action mirred" + ] + }, + { + "id": "20cc", + "name": "Add mirred redirect to ingress block action", + "category": [ + "actions", + "mirred" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + [ + "$TC actions flush action mirred", + 0, + 1, + 255 + ], + [ + "$TC qdisc add dev $DEV1 ingress_block 21 clsact", + 0 + ] + ], + "cmdUnderTest": "$TC actions add action mirred ingress redirect index 1 blockid 21", + "expExitCode": "0", + "verifyCmd": "$TC -j actions get action mirred index 1", + "matchJSON": [ + { + "total acts": 0 + }, + { + "actions": [ + { + "order": 1, + "kind": "mirred", + "mirred_action": "redirect", + "direction": "ingress", + "to_blockid": 21, + "control_action": { + "type": "stolen" + }, + "index": 1, + "ref": 1, + "bind": 0, + "not_in_hw": true + } + ] + } + ], + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress_block 21 clsact", + "$TC actions flush action mirred" + ] + }, + { + "id": "e739", + "name": "Try to add mirred action with both dev and block", + "category": [ + "actions", + "mirred" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + [ + "$TC actions flush action mirred", + 0, + 1, + 255 + ], + [ + "$TC qdisc add dev $DEV1 ingress_block 21 clsact", + 0 + ] + ], + "cmdUnderTest": "$TC actions add action mirred ingress redirect index 1 blockid 21 dev $DEV1", + "expExitCode": "255", + "verifyCmd": "$TC -j actions list action mirred", + "matchJSON": [], + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress_block 21 clsact", + "$TC actions flush action mirred" + ] + }, + { + "id": "2f47", + "name": "Try to add mirred action without specifying neither dev nor block", + "category": [ + "actions", + "mirred" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + [ + "$TC actions flush action mirred", + 0, + 1, + 255 + ], + [ + "$TC qdisc add dev $DEV1 ingress_block 21 clsact", + 0 + ] + ], + "cmdUnderTest": "$TC actions add action mirred ingress redirect index 1", + "expExitCode": "255", + "verifyCmd": "$TC -j actions list action mirred", + "matchJSON": [], + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress_block 21 clsact", + "$TC actions flush action mirred" + ] + }, + { + "id": "3188", + "name": "Replace mirred redirect to dev action with redirect to block", + "category": [ + "actions", + "mirred" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + [ + "$TC actions flush action mirred", + 0, + 1, + 255 + ], + [ + "$TC qdisc add dev $DEV1 ingress_block 21 clsact", + 0 + ], + [ + "$TC actions add action mirred ingress redirect index 1 dev $DEV1", + 0 + ] + ], + "cmdUnderTest": "$TC actions replace action mirred egress redirect index 1 blockid 21", + "expExitCode": "0", + "verifyCmd": "$TC -j actions get action mirred index 1", + "matchJSON": [ + { + "total acts": 0 + }, + { + "actions": [ + { + "order": 1, + "kind": "mirred", + "mirred_action": "redirect", + "direction": "egress", + "to_blockid": 21, + "control_action": { + "type": "stolen" + }, + "index": 1, + "ref": 1, + "bind": 0, + "not_in_hw": true + } + ] + } + ], + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress_block 21 clsact", + "$TC actions flush action mirred" + ] + }, + { + "id": "83cc", + "name": "Replace mirred redirect to block action with mirror to dev", + "category": [ + "actions", + "mirred" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + [ + "$TC actions flush action mirred", + 0, + 1, + 255 + ], + [ + "$TC qdisc add dev $DEV1 ingress_block 21 clsact", + 0 + ], + [ + "$TC actions add action mirred egress redirect index 1 blockid 21", + 0 + ] + ], + "cmdUnderTest": "$TC actions replace action mirred ingress mirror index 1 dev lo", + "expExitCode": "0", + "verifyCmd": "$TC -j actions get action mirred index 1", + "matchJSON": [ + { + "total acts": 0 + }, + { + "actions": [ + { + "order": 1, + "kind": "mirred", + "mirred_action": "mirror", + "direction": "ingress", + "to_dev": "lo", + "control_action": { + "type": "pipe" + }, + "index": 1, + "ref": 1, + "bind": 0, + "not_in_hw": true + } + ] + } + ], + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress_block 21 clsact", + "$TC actions flush action mirred" + ] } ] diff --git a/tools/tracing/rtla/Makefile b/tools/tracing/rtla/Makefile index 2456a399eb9a..afd18c678ff5 100644 --- a/tools/tracing/rtla/Makefile +++ b/tools/tracing/rtla/Makefile @@ -28,10 +28,15 @@ FOPTS := -flto=auto -ffat-lto-objects -fexceptions -fstack-protector-strong \ -fasynchronous-unwind-tables -fstack-clash-protection WOPTS := -Wall -Werror=format-security -Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS -Wno-maybe-uninitialized +ifeq ($(CC),clang) + FOPTS := $(filter-out -ffat-lto-objects, $(FOPTS)) + WOPTS := $(filter-out -Wno-maybe-uninitialized, $(WOPTS)) +endif + TRACEFS_HEADERS := $$($(PKG_CONFIG) --cflags libtracefs) CFLAGS := -O -g -DVERSION=\"$(VERSION)\" $(FOPTS) $(MOPTS) $(WOPTS) $(TRACEFS_HEADERS) $(EXTRA_CFLAGS) -LDFLAGS := -ggdb $(EXTRA_LDFLAGS) +LDFLAGS := -flto=auto -ggdb $(EXTRA_LDFLAGS) LIBS := $$($(PKG_CONFIG) --libs libtracefs) SRC := $(wildcard src/*.c) diff --git a/tools/tracing/rtla/src/osnoise_hist.c b/tools/tracing/rtla/src/osnoise_hist.c index 8f81fa007364..01870d50942a 100644 --- a/tools/tracing/rtla/src/osnoise_hist.c +++ b/tools/tracing/rtla/src/osnoise_hist.c @@ -135,8 +135,7 @@ static void osnoise_hist_update_multiple(struct osnoise_tool *tool, int cpu, if (params->output_divisor) duration = duration / params->output_divisor; - if (data->bucket_size) - bucket = duration / data->bucket_size; + bucket = duration / data->bucket_size; total_duration = duration * count; @@ -480,7 +479,11 @@ static void osnoise_hist_usage(char *usage) for (i = 0; msg[i]; i++) fprintf(stderr, "%s\n", msg[i]); - exit(1); + + if (usage) + exit(EXIT_FAILURE); + + exit(EXIT_SUCCESS); } /* diff --git a/tools/tracing/rtla/src/osnoise_top.c b/tools/tracing/rtla/src/osnoise_top.c index f7c959be8677..457360db0767 100644 --- a/tools/tracing/rtla/src/osnoise_top.c +++ b/tools/tracing/rtla/src/osnoise_top.c @@ -331,7 +331,11 @@ static void osnoise_top_usage(struct osnoise_top_params *params, char *usage) for (i = 0; msg[i]; i++) fprintf(stderr, "%s\n", msg[i]); - exit(1); + + if (usage) + exit(EXIT_FAILURE); + + exit(EXIT_SUCCESS); } /* diff --git a/tools/tracing/rtla/src/timerlat_hist.c b/tools/tracing/rtla/src/timerlat_hist.c index 47d3d8b53cb2..dbf154082f95 100644 --- a/tools/tracing/rtla/src/timerlat_hist.c +++ b/tools/tracing/rtla/src/timerlat_hist.c @@ -178,8 +178,7 @@ timerlat_hist_update(struct osnoise_tool *tool, int cpu, if (params->output_divisor) latency = latency / params->output_divisor; - if (data->bucket_size) - bucket = latency / data->bucket_size; + bucket = latency / data->bucket_size; if (!context) { hist = data->hist[cpu].irq; @@ -546,7 +545,11 @@ static void timerlat_hist_usage(char *usage) for (i = 0; msg[i]; i++) fprintf(stderr, "%s\n", msg[i]); - exit(1); + + if (usage) + exit(EXIT_FAILURE); + + exit(EXIT_SUCCESS); } /* diff --git a/tools/tracing/rtla/src/timerlat_top.c b/tools/tracing/rtla/src/timerlat_top.c index 1640f121baca..3e9af2c38688 100644 --- a/tools/tracing/rtla/src/timerlat_top.c +++ b/tools/tracing/rtla/src/timerlat_top.c @@ -375,7 +375,11 @@ static void timerlat_top_usage(char *usage) for (i = 0; msg[i]; i++) fprintf(stderr, "%s\n", msg[i]); - exit(1); + + if (usage) + exit(EXIT_FAILURE); + + exit(EXIT_SUCCESS); } /* diff --git a/tools/tracing/rtla/src/utils.c b/tools/tracing/rtla/src/utils.c index c769d7b3842c..9ac71a66840c 100644 --- a/tools/tracing/rtla/src/utils.c +++ b/tools/tracing/rtla/src/utils.c @@ -238,12 +238,6 @@ static inline int sched_setattr(pid_t pid, const struct sched_attr *attr, return syscall(__NR_sched_setattr, pid, attr, flags); } -static inline int sched_getattr(pid_t pid, struct sched_attr *attr, - unsigned int size, unsigned int flags) -{ - return syscall(__NR_sched_getattr, pid, attr, size, flags); -} - int __set_sched_attr(int pid, struct sched_attr *attr) { int flags = 0; @@ -479,13 +473,13 @@ int parse_prio(char *arg, struct sched_attr *sched_param) if (prio == INVALID_VAL) return -1; - if (prio < sched_get_priority_min(SCHED_OTHER)) + if (prio < MIN_NICE) return -1; - if (prio > sched_get_priority_max(SCHED_OTHER)) + if (prio > MAX_NICE) return -1; sched_param->sched_policy = SCHED_OTHER; - sched_param->sched_priority = prio; + sched_param->sched_nice = prio; break; default: return -1; @@ -536,7 +530,7 @@ int set_cpu_dma_latency(int32_t latency) */ static const int find_mount(const char *fs, char *mp, int sizeof_mp) { - char mount_point[MAX_PATH]; + char mount_point[MAX_PATH+1]; char type[100]; int found = 0; FILE *fp; diff --git a/tools/tracing/rtla/src/utils.h b/tools/tracing/rtla/src/utils.h index 04ed1e650495..d44513e6c66a 100644 --- a/tools/tracing/rtla/src/utils.h +++ b/tools/tracing/rtla/src/utils.h @@ -9,6 +9,8 @@ */ #define BUFF_U64_STR_SIZE 24 #define MAX_PATH 1024 +#define MAX_NICE 20 +#define MIN_NICE -19 #define container_of(ptr, type, member)({ \ const typeof(((type *)0)->member) *__mptr = (ptr); \ diff --git a/tools/verification/rv/Makefile b/tools/verification/rv/Makefile index 3d0f3888a58c..485f8aeddbe0 100644 --- a/tools/verification/rv/Makefile +++ b/tools/verification/rv/Makefile @@ -28,10 +28,15 @@ FOPTS := -flto=auto -ffat-lto-objects -fexceptions -fstack-protector-strong \ -fasynchronous-unwind-tables -fstack-clash-protection WOPTS := -Wall -Werror=format-security -Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS -Wno-maybe-uninitialized +ifeq ($(CC),clang) + FOPTS := $(filter-out -ffat-lto-objects, $(FOPTS)) + WOPTS := $(filter-out -Wno-maybe-uninitialized, $(WOPTS)) +endif + TRACEFS_HEADERS := $$($(PKG_CONFIG) --cflags libtracefs) CFLAGS := -O -g -DVERSION=\"$(VERSION)\" $(FOPTS) $(MOPTS) $(WOPTS) $(TRACEFS_HEADERS) $(EXTRA_CFLAGS) -I include -LDFLAGS := -ggdb $(EXTRA_LDFLAGS) +LDFLAGS := -flto=auto -ggdb $(EXTRA_LDFLAGS) LIBS := $$($(PKG_CONFIG) --libs libtracefs) SRC := $(wildcard src/*.c) diff --git a/tools/verification/rv/src/in_kernel.c b/tools/verification/rv/src/in_kernel.c index ad28582bcf2b..f04479ecc96c 100644 --- a/tools/verification/rv/src/in_kernel.c +++ b/tools/verification/rv/src/in_kernel.c @@ -210,9 +210,9 @@ static char *ikm_read_reactor(char *monitor_name) static char *ikm_get_current_reactor(char *monitor_name) { char *reactors = ikm_read_reactor(monitor_name); + char *curr_reactor = NULL; char *start; char *end; - char *curr_reactor; if (!reactors) return NULL; |