From eee51fe38e372b89317f3950d2dc3e3ea7bace12 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Sun, 9 May 2021 09:39:02 -0300 Subject: tools headers UAPI: Sync linux/kvm.h with the kernel sources To pick the changes in: 1b870fa5573e260b ("kvm: stats: tell userspace which values are boolean") That just rebuilds perf, as these patches don't add any new KVM ioctl to be harvested for the the 'perf trace' ioctl syscall argument beautifiers. This is also by now used by tools/testing/selftests/kvm/, a simple test build succeeded. This silences this perf build warning: Warning: Kernel ABI header at 'tools/include/uapi/linux/kvm.h' differs from latest version at 'include/uapi/linux/kvm.h' diff -u tools/include/uapi/linux/kvm.h include/uapi/linux/kvm.h Cc: Adrian Hunter Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Cc: Paolo Bonzini Link: http://lore.kernel.org/lkml/YtQLDvQrBhJNl3n5@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/linux/kvm.h | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 5088bd9f1922..811897dadcae 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -2083,6 +2083,7 @@ struct kvm_stats_header { #define KVM_STATS_UNIT_BYTES (0x1 << KVM_STATS_UNIT_SHIFT) #define KVM_STATS_UNIT_SECONDS (0x2 << KVM_STATS_UNIT_SHIFT) #define KVM_STATS_UNIT_CYCLES (0x3 << KVM_STATS_UNIT_SHIFT) +#define KVM_STATS_UNIT_BOOLEAN (0x4 << KVM_STATS_UNIT_SHIFT) #define KVM_STATS_UNIT_MAX KVM_STATS_UNIT_CYCLES #define KVM_STATS_BASE_SHIFT 8 -- cgit v1.2.3-58-ga151 From f098addbdb44c8a565367f5162f3ab170ed9404a Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 1 Jul 2021 13:39:15 -0300 Subject: tools headers cpufeatures: Sync with the kernel sources To pick the changes from: f43b9876e857c739 ("x86/retbleed: Add fine grained Kconfig knobs") a149180fbcf336e9 ("x86: Add magic AMD return-thunk") 15e67227c49a5783 ("x86: Undo return-thunk damage") 369ae6ffc41a3c11 ("x86/retpoline: Cleanup some #ifdefery") 4ad3278df6fe2b08 x86/speculation: Disable RRSBA behavior 26aae8ccbc197223 x86/cpu/amd: Enumerate BTC_NO 9756bba28470722d x86/speculation: Fill RSB on vmexit for IBRS 3ebc170068885b6f x86/bugs: Add retbleed=ibpb 2dbb887e875b1de3 x86/entry: Add kernel IBRS implementation 6b80b59b35557065 x86/bugs: Report AMD retbleed vulnerability a149180fbcf336e9 x86: Add magic AMD return-thunk 15e67227c49a5783 x86: Undo return-thunk damage a883d624aed463c8 x86/cpufeatures: Move RETPOLINE flags to word 11 51802186158c74a0 x86/speculation/mmio: Enumerate Processor MMIO Stale Data bug This only causes these perf files to be rebuilt: CC /tmp/build/perf/bench/mem-memcpy-x86-64-asm.o CC /tmp/build/perf/bench/mem-memset-x86-64-asm.o And addresses this perf build warning: Warning: Kernel ABI header at 'tools/arch/x86/include/asm/cpufeatures.h' differs from latest version at 'arch/x86/include/asm/cpufeatures.h' diff -u tools/arch/x86/include/asm/cpufeatures.h arch/x86/include/asm/cpufeatures.h Warning: Kernel ABI header at 'tools/arch/x86/include/asm/disabled-features.h' differs from latest version at 'arch/x86/include/asm/disabled-features.h' diff -u tools/arch/x86/include/asm/disabled-features.h arch/x86/include/asm/disabled-features.h Cc: Adrian Hunter Cc: Borislav Petkov Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra --- tools/arch/x86/include/asm/cpufeatures.h | 12 ++++++++++-- tools/arch/x86/include/asm/disabled-features.h | 21 ++++++++++++++++++++- 2 files changed, 30 insertions(+), 3 deletions(-) diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 03acc823838a..00f5227c8459 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -203,8 +203,8 @@ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ #define X86_FEATURE_XCOMPACTED ( 7*32+10) /* "" Use compacted XSTATE (XSAVES or XSAVEC) */ #define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */ -#define X86_FEATURE_RETPOLINE ( 7*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */ -#define X86_FEATURE_RETPOLINE_LFENCE ( 7*32+13) /* "" Use LFENCE for Spectre variant 2 */ +#define X86_FEATURE_KERNEL_IBRS ( 7*32+12) /* "" Set/clear IBRS on kernel entry/exit */ +#define X86_FEATURE_RSB_VMEXIT ( 7*32+13) /* "" Fill RSB on VM-Exit */ #define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ #define X86_FEATURE_CDP_L2 ( 7*32+15) /* Code and Data Prioritization L2 */ #define X86_FEATURE_MSR_SPEC_CTRL ( 7*32+16) /* "" MSR SPEC_CTRL is implemented */ @@ -296,6 +296,12 @@ #define X86_FEATURE_PER_THREAD_MBA (11*32+ 7) /* "" Per-thread Memory Bandwidth Allocation */ #define X86_FEATURE_SGX1 (11*32+ 8) /* "" Basic SGX */ #define X86_FEATURE_SGX2 (11*32+ 9) /* "" SGX Enclave Dynamic Memory Management (EDMM) */ +#define X86_FEATURE_ENTRY_IBPB (11*32+10) /* "" Issue an IBPB on kernel entry */ +#define X86_FEATURE_RRSBA_CTRL (11*32+11) /* "" RET prediction control */ +#define X86_FEATURE_RETPOLINE (11*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */ +#define X86_FEATURE_RETPOLINE_LFENCE (11*32+13) /* "" Use LFENCE for Spectre variant 2 */ +#define X86_FEATURE_RETHUNK (11*32+14) /* "" Use REturn THUNK */ +#define X86_FEATURE_UNRET (11*32+15) /* "" AMD BTB untrain return */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ @@ -316,6 +322,7 @@ #define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */ #define X86_FEATURE_AMD_SSB_NO (13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */ #define X86_FEATURE_CPPC (13*32+27) /* Collaborative Processor Performance Control */ +#define X86_FEATURE_BTC_NO (13*32+29) /* "" Not vulnerable to Branch Type Confusion */ #define X86_FEATURE_BRS (13*32+31) /* Branch Sampling available */ /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */ @@ -447,5 +454,6 @@ #define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */ #define X86_BUG_SRBDS X86_BUG(24) /* CPU may leak RNG bits if not mitigated */ #define X86_BUG_MMIO_STALE_DATA X86_BUG(25) /* CPU is affected by Processor MMIO Stale Data vulnerabilities */ +#define X86_BUG_RETBLEED X86_BUG(26) /* CPU is affected by RETBleed */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index 36369e76cc63..33d2cd04d254 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -50,6 +50,25 @@ # define DISABLE_PTI (1 << (X86_FEATURE_PTI & 31)) #endif +#ifdef CONFIG_RETPOLINE +# define DISABLE_RETPOLINE 0 +#else +# define DISABLE_RETPOLINE ((1 << (X86_FEATURE_RETPOLINE & 31)) | \ + (1 << (X86_FEATURE_RETPOLINE_LFENCE & 31))) +#endif + +#ifdef CONFIG_RETHUNK +# define DISABLE_RETHUNK 0 +#else +# define DISABLE_RETHUNK (1 << (X86_FEATURE_RETHUNK & 31)) +#endif + +#ifdef CONFIG_CPU_UNRET_ENTRY +# define DISABLE_UNRET 0 +#else +# define DISABLE_UNRET (1 << (X86_FEATURE_UNRET & 31)) +#endif + #ifdef CONFIG_INTEL_IOMMU_SVM # define DISABLE_ENQCMD 0 #else @@ -82,7 +101,7 @@ #define DISABLED_MASK8 (DISABLE_TDX_GUEST) #define DISABLED_MASK9 (DISABLE_SGX) #define DISABLED_MASK10 0 -#define DISABLED_MASK11 0 +#define DISABLED_MASK11 (DISABLE_RETPOLINE|DISABLE_RETHUNK|DISABLE_UNRET) #define DISABLED_MASK12 0 #define DISABLED_MASK13 0 #define DISABLED_MASK14 0 -- cgit v1.2.3-58-ga151 From 91d248c3b903b46a58cbc7e8d38d684d3e4007c2 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 1 Jul 2021 13:32:18 -0300 Subject: tools arch x86: Sync the msr-index.h copy with the kernel sources To pick up the changes from these csets: 4ad3278df6fe2b08 ("x86/speculation: Disable RRSBA behavior") d7caac991feeef1b ("x86/cpu/amd: Add Spectral Chicken") That cause no changes to tooling: $ tools/perf/trace/beauty/tracepoints/x86_msr.sh > before $ cp arch/x86/include/asm/msr-index.h tools/arch/x86/include/asm/msr-index.h $ tools/perf/trace/beauty/tracepoints/x86_msr.sh > after $ diff -u before after $ Just silences this perf build warning: Warning: Kernel ABI header at 'tools/arch/x86/include/asm/msr-index.h' differs from latest version at 'arch/x86/include/asm/msr-index.h' diff -u tools/arch/x86/include/asm/msr-index.h arch/x86/include/asm/msr-index.h Cc: Adrian Hunter Cc: Borislav Petkov Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Cc: Pawan Gupta Cc: Peter Zijlstra Link: https://lore.kernel.org/lkml/YtQTm9wsB3hxQWvy@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/x86/include/asm/msr-index.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index 2eab6a3a8a8c..cc615be27a54 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -95,6 +95,7 @@ #define MSR_IA32_ARCH_CAPABILITIES 0x0000010a #define ARCH_CAP_RDCL_NO BIT(0) /* Not susceptible to Meltdown */ #define ARCH_CAP_IBRS_ALL BIT(1) /* Enhanced IBRS support */ +#define ARCH_CAP_RSBA BIT(2) /* RET may use alternative branch predictors */ #define ARCH_CAP_SKIP_VMENTRY_L1DFLUSH BIT(3) /* Skip L1D flush on vmentry */ #define ARCH_CAP_SSB_NO BIT(4) /* * Not susceptible to Speculative Store Bypass @@ -576,6 +577,9 @@ /* Fam 17h MSRs */ #define MSR_F17H_IRPERF 0xc00000e9 +#define MSR_ZEN2_SPECTRAL_CHICKEN 0xc00110e3 +#define MSR_ZEN2_SPECTRAL_CHICKEN_BIT BIT_ULL(1) + /* Fam 16h MSRs */ #define MSR_F16H_L2I_PERF_CTL 0xc0010230 #define MSR_F16H_L2I_PERF_CTR 0xc0010231 -- cgit v1.2.3-58-ga151 From 498c7a54f169b2699104d3060604d840424f15d2 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Wed, 13 Jul 2022 15:34:58 +0300 Subject: perf tests: Stop Convert perf time to TSC test opening events twice Do not call evlist__open() twice. Fixes: 5bb017d4b97a0f13 ("perf test: Fix error message for test case 71 on s390, where it is not supported") Reviewed-by: Kan Liang Signed-off-by: Adrian Hunter Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Cc: Thomas Richter Link: https://lore.kernel.org/r/20220713123459.24145-2-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/perf-time-to-tsc.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c index 4ad0dfbc8b21..8d6d60173693 100644 --- a/tools/perf/tests/perf-time-to-tsc.c +++ b/tools/perf/tests/perf-time-to-tsc.c @@ -123,11 +123,14 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su evsel->core.attr.enable_on_exec = 0; } - if (evlist__open(evlist) == -ENOENT) { - err = TEST_SKIP; + ret = evlist__open(evlist); + if (ret < 0) { + if (ret == -ENOENT) + err = TEST_SKIP; + else + pr_debug("evlist__open() failed\n"); goto out_err; } - CHECK__(evlist__open(evlist)); CHECK__(evlist__mmap(evlist, UINT_MAX)); -- cgit v1.2.3-58-ga151 From deb44a6249f696106645c63c0603eab08a6122af Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Wed, 13 Jul 2022 15:34:59 +0300 Subject: perf tests: Fix Convert perf time to TSC test for hybrid The test does not always correctly determine the number of events for hybrids, nor allow for more than 1 evsel when parsing. Fix by iterating the events actually created and getting the correct evsel for the events processed. Fixes: d9da6f70eb235110 ("perf tests: Support 'Convert perf time to TSC' test for hybrid") Reviewed-by: Kan Liang Signed-off-by: Adrian Hunter Cc: Ian Rogers Cc: Jin Yao Cc: Jiri Olsa Cc: Namhyung Kim Cc: Thomas Richter Link: https://lore.kernel.org/r/20220713123459.24145-3-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/perf-time-to-tsc.c | 18 ++++-------------- 1 file changed, 4 insertions(+), 14 deletions(-) diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c index 8d6d60173693..7c7d20fc503a 100644 --- a/tools/perf/tests/perf-time-to-tsc.c +++ b/tools/perf/tests/perf-time-to-tsc.c @@ -20,8 +20,6 @@ #include "tsc.h" #include "mmap.h" #include "tests.h" -#include "pmu.h" -#include "pmu-hybrid.h" /* * Except x86_64/i386 and Arm64, other archs don't support TSC in perf. Just @@ -106,18 +104,8 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su evlist__config(evlist, &opts, NULL); - evsel = evlist__first(evlist); - - evsel->core.attr.comm = 1; - evsel->core.attr.disabled = 1; - evsel->core.attr.enable_on_exec = 0; - - /* - * For hybrid "cycles:u", it creates two events. - * Init the second evsel here. - */ - if (perf_pmu__has_hybrid() && perf_pmu__hybrid_mounted("cpu_atom")) { - evsel = evsel__next(evsel); + /* For hybrid "cycles:u", it creates two events */ + evlist__for_each_entry(evlist, evsel) { evsel->core.attr.comm = 1; evsel->core.attr.disabled = 1; evsel->core.attr.enable_on_exec = 0; @@ -170,10 +158,12 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su goto next_event; if (strcmp(event->comm.comm, comm1) == 0) { + CHECK_NOT_NULL__(evsel = evlist__event2evsel(evlist, event)); CHECK__(evsel__parse_sample(evsel, event, &sample)); comm1_time = sample.time; } if (strcmp(event->comm.comm, comm2) == 0) { + CHECK_NOT_NULL__(evsel = evlist__event2evsel(evlist, event)); CHECK__(evsel__parse_sample(evsel, event, &sample)); comm2_time = sample.time; } -- cgit v1.2.3-58-ga151 From 4b335e1e0d6f8fa91dac615a44b123c9f26e93d3 Mon Sep 17 00:00:00 2001 From: "Naveen N. Rao" Date: Thu, 7 Jul 2022 14:39:00 +0530 Subject: perf trace: Fix SIGSEGV when processing syscall args On powerpc, 'perf trace' is crashing with a SIGSEGV when trying to process a perf.data file created with 'perf trace record -p': #0 0x00000001225b8988 in syscall_arg__scnprintf_augmented_string at builtin-trace.c:1492 #1 syscall_arg__scnprintf_filename at builtin-trace.c:1492 #2 syscall_arg__scnprintf_filename at builtin-trace.c:1486 #3 0x00000001225bdd9c in syscall_arg_fmt__scnprintf_val at builtin-trace.c:1973 #4 syscall__scnprintf_args at builtin-trace.c:2041 #5 0x00000001225bff04 in trace__sys_enter at builtin-trace.c:2319 That points to the below code in tools/perf/builtin-trace.c: /* * If this is raw_syscalls.sys_enter, then it always comes with the 6 possible * arguments, even if the syscall being handled, say "openat", uses only 4 arguments * this breaks syscall__augmented_args() check for augmented args, as we calculate * syscall->args_size using each syscalls:sys_enter_NAME tracefs format file, * so when handling, say the openat syscall, we end up getting 6 args for the * raw_syscalls:sys_enter event, when we expected just 4, we end up mistakenly * thinking that the extra 2 u64 args are the augmented filename, so just check * here and avoid using augmented syscalls when the evsel is the raw_syscalls one. */ if (evsel != trace->syscalls.events.sys_enter) augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size, trace->raw_augmented_syscalls_args_size); As the comment points out, we should not be trying to augment the args for raw_syscalls. However, when processing a perf.data file, we are not initializing those properly. Fix the same. Reported-by: Claudio Carvalho Signed-off-by: Naveen N. Rao Cc: Jiri Olsa Cc: Namhyung Kim Link: http://lore.kernel.org/lkml/20220707090900.572584-1-naveen.n.rao@linux.vnet.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-trace.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 897fc504918b..f075cf37a65e 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -4280,6 +4280,7 @@ static int trace__replay(struct trace *trace) goto out; evsel = evlist__find_tracepoint_by_name(session->evlist, "raw_syscalls:sys_enter"); + trace->syscalls.events.sys_enter = evsel; /* older kernels have syscalls tp versus raw_syscalls */ if (evsel == NULL) evsel = evlist__find_tracepoint_by_name(session->evlist, "syscalls:sys_enter"); @@ -4292,6 +4293,7 @@ static int trace__replay(struct trace *trace) } evsel = evlist__find_tracepoint_by_name(session->evlist, "raw_syscalls:sys_exit"); + trace->syscalls.events.sys_exit = evsel; if (evsel == NULL) evsel = evlist__find_tracepoint_by_name(session->evlist, "syscalls:sys_exit"); if (evsel && -- cgit v1.2.3-58-ga151