From c67d734975a25ba7b6e8f820c13e0d8eb4a2a77c Mon Sep 17 00:00:00 2001 From: Milian Wolff Date: Thu, 29 Apr 2021 20:57:59 +0200 Subject: perf buildid-list: Initialize zstd_data Fixes segmentation fault when trying to obtain buildid list (e.g. via perf-archive) from a zstd-compressed `perf.data` file: ``` $ perf record -z ls ... [ perf record: Captured and wrote 0,010 MB perf.data, compressed (original 0,001 MB, ratio is 2,190) ] $ memcheck perf buildid-list ... ==57268== Invalid read of size 4 ==57268== at 0x5260D88: ZSTD_decompressStream (in /usr/lib/libzstd.so.1.4.9) ==57268== by 0x4BB51B: zstd_decompress_stream (zstd.c:100) ==57268== by 0x425C6C: perf_session__process_compressed_event (session.c:73) ==57268== by 0x427450: perf_session__process_user_event (session.c:1631) ==57268== by 0x42A609: reader__process_events (session.c:2207) ==57268== by 0x42A609: __perf_session__process_events (session.c:2264) ==57268== by 0x42A609: perf_session__process_events (session.c:2297) ==57268== by 0x343A62: perf_session__list_build_ids (builtin-buildid-list.c:88) ==57268== by 0x343A62: cmd_buildid_list (builtin-buildid-list.c:120) ==57268== by 0x3C7732: run_builtin (perf.c:313) ==57268== by 0x331157: handle_internal_command (perf.c:365) ==57268== by 0x331157: run_argv (perf.c:409) ==57268== by 0x331157: main (perf.c:539) ==57268== Address 0x7470 is not stack'd, malloc'd or (recently) free'd ``` Signed-off-by: Milian Wolff Cc: Alexey Budankov Link: http://lore.kernel.org/lkml/20210429185759.59870-1-milian.wolff@kdab.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-buildid-list.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'tools') diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c index 87f5b1a4a7fa..833405c27dae 100644 --- a/tools/perf/builtin-buildid-list.c +++ b/tools/perf/builtin-buildid-list.c @@ -80,6 +80,9 @@ static int perf_session__list_build_ids(bool force, bool with_hits) if (!perf_header__has_feat(&session->header, HEADER_BUILD_ID)) with_hits = true; + if (zstd_init(&(session->zstd_data), 0) < 0) + pr_warning("Decompression initialization failed. Reported data may be incomplete.\n"); + /* * in pipe-mode, the only way to get the buildids is to parse * the record stream. Buildids are stored as RECORD_HEADER_BUILD_ID -- cgit v1.2.3 From 3c91e8efaf4838e4c8e465656e9707b5de26f3db Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 12 May 2021 12:35:07 -0300 Subject: tools arch kvm: Sync kvm headers with the kernel sources To pick up the changes from: 70f094f4f01dc4d6 ("KVM: nVMX: Properly pad 'struct kvm_vmx_nested_state_hdr'") That don't entail changes in tooling. This silences these tools/perf build warnings: Warning: Kernel ABI header at 'tools/arch/x86/include/uapi/asm/kvm.h' differs from latest version at 'arch/x86/include/uapi/asm/kvm.h' diff -u tools/arch/x86/include/uapi/asm/kvm.h arch/x86/include/uapi/asm/kvm.h Cc: Paolo Bonzini Cc: Vitaly Kuznetsov Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/x86/include/uapi/asm/kvm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'tools') diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index 5a3022c8af82..0662f644aad9 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -437,6 +437,8 @@ struct kvm_vmx_nested_state_hdr { __u16 flags; } smm; + __u16 pad; + __u32 flags; __u64 preemption_timer_deadline; }; -- cgit v1.2.3 From 316a76a58c3f30735e5e416a6dc304d6bb86312d Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Mon, 17 May 2021 16:09:31 +0200 Subject: perf test: Fix libpfm4 support (63) test error for nested event groups Compiling perf with make LIBPFM4=1 includes libpfm support and enables test case 63 'Test libpfm4 support'. This test reports an error on all platforms for subtest 63.2 'test groups of --pfm-events'. The reported error message is 'nested event groups not supported' # ./perf test -F 63 63: Test libpfm4 support : 63.1: test of individual --pfm-events : Error: failed to parse event stereolab : event not found Error: failed to parse event stereolab,instructions : event not found Error: failed to parse event instructions,stereolab : event not found Ok 63.2: test groups of --pfm-events : Error: nested event groups not supported <------ Error message here Error: failed to parse event {stereolab} : event not found Error: failed to parse event {instructions,cycles},{instructions,stereolab} :\ event not found Ok # This patch addresses the error message 'nested event groups not supported'. The root cause is function parse_libpfm_events_option() which parses the event string '{},{instructions}' and can not handle a leading empty group notation '{},...'. The code detects the first (empty) group indicator '{' but does not terminate group processing on the following group closing character '}'. So when the second group indicator '{' is detected, the code assumes a nested group and returns an error. With the error message fixed, also change the expected event number to one for the test case to succeed. While at it also fix a memory leak. In good case the function does not free the duplicated string given as first parameter. Output after: # ./perf test -F 63 63: Test libpfm4 support : 63.1: test of individual --pfm-events : Error: failed to parse event stereolab : event not found Error: failed to parse event stereolab,instructions : event not found Error: failed to parse event instructions,stereolab : event not found Ok 63.2: test groups of --pfm-events : Error: failed to parse event {stereolab} : event not found Error: failed to parse event {instructions,cycles},{instructions,stereolab} : \ event not found Ok # Error message 'nested event groups not supported' is gone. Signed-off-by: Thomas Richter Acked-By: Ian Rogers Acked-by: Sumanth Korikkar Cc: Heiko Carstens Cc: Stephane Eranian Cc: Sven Schnelle Cc: Vasily Gorbik Link: http://lore.kernel.org/lkml/20210517140931.2559364-1-tmricht@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/pfm.c | 4 ++-- tools/perf/util/pfm.c | 11 ++++++++++- 2 files changed, 12 insertions(+), 3 deletions(-) (limited to 'tools') diff --git a/tools/perf/tests/pfm.c b/tools/perf/tests/pfm.c index 76a53126efdf..d4b0ef74defc 100644 --- a/tools/perf/tests/pfm.c +++ b/tools/perf/tests/pfm.c @@ -131,8 +131,8 @@ static int test__pfm_group(void) }, { .events = "{},{instructions}", - .nr_events = 0, - .nr_groups = 0, + .nr_events = 1, + .nr_groups = 1, }, { .events = "{instructions},{instructions}", diff --git a/tools/perf/util/pfm.c b/tools/perf/util/pfm.c index d735acb6c29c..6eef6dfeaa57 100644 --- a/tools/perf/util/pfm.c +++ b/tools/perf/util/pfm.c @@ -62,8 +62,16 @@ int parse_libpfm_events_option(const struct option *opt, const char *str, } /* no event */ - if (*q == '\0') + if (*q == '\0') { + if (*sep == '}') { + if (grp_evt < 0) { + ui__error("cannot close a non-existing event group\n"); + goto error; + } + grp_evt--; + } continue; + } memset(&attr, 0, sizeof(attr)); event_attr_init(&attr); @@ -107,6 +115,7 @@ int parse_libpfm_events_option(const struct option *opt, const char *str, grp_evt = -1; } } + free(p_orig); return 0; error: free(p_orig); -- cgit v1.2.3 From cb7987837c31b217b28089bbc78922d5c9187869 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Wed, 19 May 2021 10:45:13 +0300 Subject: perf intel-pt: Fix transaction abort handling When adding support for power events, some handling of FUP packets was unified. That resulted in breaking reporting of TSX aborts, by not considering the associated TIP packet. Fix that. Example: A machine that supports TSX is required. It will have flag "rtm". Kernel parameter tsx=on may be required. # for w in `cat /proc/cpuinfo | grep -m1 flags `;do echo $w | grep rtm ; done rtm Test program: #include #include int main() { int x = 0; if (_xbegin() == _XBEGIN_STARTED) { x = 1; _xabort(1); } else { printf("x = %d\n", x); } return 0; } Compile with -mrtm i.e. gcc -Wall -Wextra -mrtm xabort.c -o xabort Record: perf record -e intel_pt/cyc/u --filter 'filter main @ ./xabort' ./xabort Before: # perf script --itrace=be -F+flags,+addr,-period,-event --ns xabort 1478 [007] 92161.431348552: tr strt 0 [unknown] ([unknown]) => 400b6d main+0x0 (/root/xabort) xabort 1478 [007] 92161.431348624: jmp 400b96 main+0x29 (/root/xabort) => 400bae main+0x41 (/root/xabort) xabort 1478 [007] 92161.431348624: return 400bb4 main+0x47 (/root/xabort) => 400b87 main+0x1a (/root/xabort) xabort 1478 [007] 92161.431348637: jcc 400b8a main+0x1d (/root/xabort) => 400b98 main+0x2b (/root/xabort) xabort 1478 [007] 92161.431348644: tr end call 400ba9 main+0x3c (/root/xabort) => 40f690 printf+0x0 (/root/xabort) xabort 1478 [007] 92161.431360859: tr strt 0 [unknown] ([unknown]) => 400bae main+0x41 (/root/xabort) xabort 1478 [007] 92161.431360882: tr end return 400bb4 main+0x47 (/root/xabort) => 401139 __libc_start_main+0x309 (/root/xabort) After: # perf script --itrace=be -F+flags,+addr,-period,-event --ns xabort 1478 [007] 92161.431348552: tr strt 0 [unknown] ([unknown]) => 400b6d main+0x0 (/root/xabort) xabort 1478 [007] 92161.431348624: tx abrt 400b93 main+0x26 (/root/xabort) => 400b87 main+0x1a (/root/xabort) xabort 1478 [007] 92161.431348637: jcc 400b8a main+0x1d (/root/xabort) => 400b98 main+0x2b (/root/xabort) xabort 1478 [007] 92161.431348644: tr end call 400ba9 main+0x3c (/root/xabort) => 40f690 printf+0x0 (/root/xabort) xabort 1478 [007] 92161.431360859: tr strt 0 [unknown] ([unknown]) => 400bae main+0x41 (/root/xabort) xabort 1478 [007] 92161.431360882: tr end return 400bb4 main+0x47 (/root/xabort) => 401139 __libc_start_main+0x309 (/root/xabort) Fixes: a472e65fc490a ("perf intel-pt: Add decoder support for ptwrite and power event packets") Signed-off-by: Adrian Hunter Cc: Andi Kleen Cc: Jiri Olsa Cc: stable@vger.kernel.org Link: http://lore.kernel.org/lkml/20210519074515.9262-2-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/intel-pt-decoder/intel-pt-decoder.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c index 8c59677bee13..20ad663978cc 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -1146,6 +1146,8 @@ static bool intel_pt_fup_event(struct intel_pt_decoder *decoder) decoder->set_fup_tx_flags = false; decoder->tx_flags = decoder->fup_tx_flags; decoder->state.type = INTEL_PT_TRANSACTION; + if (decoder->fup_tx_flags & INTEL_PT_ABORT_TX) + decoder->state.type |= INTEL_PT_BRANCH; decoder->state.from_ip = decoder->ip; decoder->state.to_ip = 0; decoder->state.flags = decoder->fup_tx_flags; @@ -1220,8 +1222,10 @@ static int intel_pt_walk_fup(struct intel_pt_decoder *decoder) return 0; if (err == -EAGAIN || intel_pt_fup_with_nlip(decoder, &intel_pt_insn, ip, err)) { + bool no_tip = decoder->pkt_state != INTEL_PT_STATE_FUP; + decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; - if (intel_pt_fup_event(decoder)) + if (intel_pt_fup_event(decoder) && no_tip) return 0; return -EAGAIN; } -- cgit v1.2.3 From c954eb72b31a9dc56c99b450253ec5b121add320 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Wed, 19 May 2021 10:45:14 +0300 Subject: perf intel-pt: Fix sample instruction bytes The decoder reports the current instruction if it was decoded. In some cases the current instruction is not decoded, in which case the instruction bytes length must be set to zero. Ensure that is always done. Note perf script can anyway get the instruction bytes for any samples where they are not present. Also note, that there is a redundant "ptq->insn_len = 0" statement which is not removed until a subsequent patch in order to make this patch apply cleanly to stable branches. Example: A machne that supports TSX is required. It will have flag "rtm". Kernel parameter tsx=on may be required. # for w in `cat /proc/cpuinfo | grep -m1 flags `;do echo $w | grep rtm ; done rtm Test program: #include #include int main() { int x = 0; if (_xbegin() == _XBEGIN_STARTED) { x = 1; _xabort(1); } else { printf("x = %d\n", x); } return 0; } Compile with -mrtm i.e. gcc -Wall -Wextra -mrtm xabort.c -o xabort Record: perf record -e intel_pt/cyc/u --filter 'filter main @ ./xabort' ./xabort Before: # perf script --itrace=xe -F+flags,+insn,-period --xed --ns xabort 1478 [007] 92161.431348581: transactions: x 400b81 main+0x14 (/root/xabort) mov $0xffffffff, %eax xabort 1478 [007] 92161.431348624: transactions: tx abrt 400b93 main+0x26 (/root/xabort) mov $0xffffffff, %eax After: # perf script --itrace=xe -F+flags,+insn,-period --xed --ns xabort 1478 [007] 92161.431348581: transactions: x 400b81 main+0x14 (/root/xabort) xbegin 0x6 xabort 1478 [007] 92161.431348624: transactions: tx abrt 400b93 main+0x26 (/root/xabort) xabort $0x1 Fixes: faaa87680b25d ("perf intel-pt/bts: Report instruction bytes and length in sample") Signed-off-by: Adrian Hunter Cc: Andi Kleen Cc: Jiri Olsa Cc: stable@vger.kernel.org Link: http://lore.kernel.org/lkml/20210519074515.9262-3-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/intel-pt.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 8658d42ce57a..beae5cbe9cc2 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -707,8 +707,10 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn, *ip += intel_pt_insn->length; - if (to_ip && *ip == to_ip) + if (to_ip && *ip == to_ip) { + intel_pt_insn->length = 0; goto out_no_cache; + } if (*ip >= al.map->end) break; @@ -1198,6 +1200,7 @@ static void intel_pt_set_pid_tid_cpu(struct intel_pt *pt, static void intel_pt_sample_flags(struct intel_pt_queue *ptq) { + ptq->insn_len = 0; if (ptq->state->flags & INTEL_PT_ABORT_TX) { ptq->flags = PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TX_ABORT; } else if (ptq->state->flags & INTEL_PT_ASYNC) { -- cgit v1.2.3 From 0a0c59724516fabf9705c0d9927fa12319908852 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Wed, 19 May 2021 10:45:15 +0300 Subject: perf intel-pt: Remove redundant setting of ptq->insn_len Remove redundant "ptq->insn_len = 0" statement. Signed-off-by: Adrian Hunter Cc: Andi Kleen Cc: Jiri Olsa Link: http://lore.kernel.org/lkml/20210519074515.9262-4-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/intel-pt.c | 1 - 1 file changed, 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index beae5cbe9cc2..0dfec8761b9a 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -1214,7 +1214,6 @@ static void intel_pt_sample_flags(struct intel_pt_queue *ptq) ptq->flags = PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_ASYNC | PERF_IP_FLAG_INTERRUPT; - ptq->insn_len = 0; } else { if (ptq->state->from_ip) ptq->flags = intel_pt_insn_type(ptq->state->insn_op); -- cgit v1.2.3 From fb6c79d7261afb7e942251254ea47951c2a9a706 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 10 Feb 2021 17:33:27 +0900 Subject: perf tools: Add 'cgroup-switches' software event It counts how often cgroups are changed actually during the context switches. # perf stat -a -e context-switches,cgroup-switches -a sleep 1 Performance counter stats for 'system wide': 11,267 context-switches 10,950 cgroup-switches 1.015634369 seconds time elapsed Committer notes: The kernel patches landed in v5.13, but this entry wasn't filled in perf's parse-events tables, which was leading to a segfault when running 'perf list' on a kernel with that feature, as reported by Thomas Richter. Also removed the part touching tools/include/uapi/linux/perf_event.h as it was updated in the usual sync with the kernel UAPI headers, in a previous, already upstream, patch. Signed-off-by: Namhyung Kim Cc: Alexander Shishkin Cc: Andi Kleen Cc: Heiko Carstens Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Richter Link: http://lore.kernel.org/lkml/20210210083327.22726-3-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/parse-events.c | 4 ++++ tools/perf/util/parse-events.l | 1 + 2 files changed, 5 insertions(+) (limited to 'tools') diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 4dad14265b81..269997066f6e 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -150,6 +150,10 @@ struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = { .symbol = "bpf-output", .alias = "", }, + [PERF_COUNT_SW_CGROUP_SWITCHES] = { + .symbol = "cgroup-switches", + .alias = "", + }, }; #define __PERF_EVENT_FIELD(config, name) \ diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index fb8646cc3e83..923849024b15 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -347,6 +347,7 @@ emulation-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EM dummy { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); } duration_time { return tool(yyscanner, PERF_TOOL_DURATION_TIME); } bpf-output { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_BPF_OUTPUT); } +cgroup-switches { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CGROUP_SWITCHES); } /* * We have to handle the kernel PMU event cycles-ct/cycles-t/mem-loads/mem-stores separately. -- cgit v1.2.3 From 3b2f17ad1770e51b8b4e68b5069c4f1ee477eff8 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 19 May 2021 13:50:31 -0300 Subject: perf parse-events: Check if the software events array slots are populated To avoid a NULL pointer dereference when the kernel supports the new feature but the tooling still hasn't an entry for it. This happened with the recently added PERF_COUNT_SW_CGROUP_SWITCHES software event. Reported-by: Thomas Richter Cc: Adrian Hunter Cc: Heiko Carstens Cc: Jiri Olsa Cc: Namhyung Kim Cc: Sumanth Korikkar Link: https://lore.kernel.org/linux-perf-users/YKVESEKRjKtILhog@kernel.org/ Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/parse-events.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 269997066f6e..84108c17f48d 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -2932,9 +2932,14 @@ restart: } for (i = 0; i < max; i++, syms++) { + /* + * New attr.config still not supported here, the latest + * example was PERF_COUNT_SW_CGROUP_SWITCHES + */ + if (syms->symbol == NULL) + continue; - if (event_glob != NULL && syms->symbol != NULL && - !(strglobmatch(syms->symbol, event_glob) || + if (event_glob != NULL && !(strglobmatch(syms->symbol, event_glob) || (syms->alias && strglobmatch(syms->alias, event_glob)))) continue; -- cgit v1.2.3 From ec347b7c319156c3b488681d1813d08d88499cc6 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 21 May 2021 16:00:31 -0300 Subject: tools headers UAPI: Sync linux/fs.h with the kernel sources To pick the trivial change in: 63c8af5687f6b1b7 ("block: uapi: fix comment about block device ioctl") This silences this perf build warning: Warning: Kernel ABI header at 'tools/include/uapi/linux/fs.h' differs from latest version at 'include/uapi/linux/fs.h' diff -u tools/include/uapi/linux/fs.h include/uapi/linux/fs.h Cc: Damien Le Moal Cc: Jens Axboe Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h index f44eb0a04afd..4c32e97dcdf0 100644 --- a/tools/include/uapi/linux/fs.h +++ b/tools/include/uapi/linux/fs.h @@ -185,7 +185,7 @@ struct fsxattr { #define BLKROTATIONAL _IO(0x12,126) #define BLKZEROOUT _IO(0x12,127) /* - * A jump here: 130-131 are reserved for zoned block devices + * A jump here: 130-136 are reserved for zoned block devices * (see uapi/linux/blkzoned.h) */ -- cgit v1.2.3 From 4224680ee7aaf0f13ab762ffb2a77373737dce5e Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 21 May 2021 16:00:31 -0300 Subject: tools headers UAPI: Sync linux/perf_event.h with the kernel sources To pick the trivial change in: 0683b53197b55343 ("signal: Deliver all of the siginfo perf data in _perf") This silences this perf build warning: Warning: Kernel ABI header at 'tools/include/uapi/linux/perf_event.h' differs from latest version at 'include/uapi/linux/perf_event.h' diff -u tools/include/uapi/linux/perf_event.h include/uapi/linux/perf_event.h Cc: Eric W. Biederman Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/linux/perf_event.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index bf8143505c49..f92880a15645 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -464,7 +464,7 @@ struct perf_event_attr { /* * User provided data if sigtrap=1, passed back to user via - * siginfo_t::si_perf, e.g. to permit user to identify the event. + * siginfo_t::si_perf_data, e.g. to permit user to identify the event. */ __u64 sig_data; }; -- cgit v1.2.3 From bffcbe79370e8fda7f1d19899de83aa2a833bf69 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 21 May 2021 16:14:00 -0300 Subject: tools headers UAPI: Sync files changed by the quotactl_path unwiring To pick the changes in this csets: 5b9fedb31e476693 ("quota: Disable quotactl_path syscall") That silences these perf build warnings: Warning: Kernel ABI header at 'tools/include/uapi/asm-generic/unistd.h' differs from latest version at 'include/uapi/asm-generic/unistd.h' diff -u tools/include/uapi/asm-generic/unistd.h include/uapi/asm-generic/unistd.h Warning: Kernel ABI header at 'tools/perf/arch/x86/entry/syscalls/syscall_64.tbl' differs from latest version at 'arch/x86/entry/syscalls/syscall_64.tbl' diff -u tools/perf/arch/x86/entry/syscalls/syscall_64.tbl arch/x86/entry/syscalls/syscall_64.tbl Warning: Kernel ABI header at 'tools/perf/arch/powerpc/entry/syscalls/syscall.tbl' differs from latest version at 'arch/powerpc/kernel/syscalls/syscall.tbl' diff -u tools/perf/arch/powerpc/entry/syscalls/syscall.tbl arch/powerpc/kernel/syscalls/syscall.tbl Warning: Kernel ABI header at 'tools/perf/arch/s390/entry/syscalls/syscall.tbl' differs from latest version at 'arch/s390/kernel/syscalls/syscall.tbl' diff -u tools/perf/arch/s390/entry/syscalls/syscall.tbl arch/s390/kernel/syscalls/syscall.tbl Warning: Kernel ABI header at 'tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl' differs from latest version at 'arch/mips/kernel/syscalls/syscall_n64.tbl' diff -u tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl arch/mips/kernel/syscalls/syscall_n64.tbl Cc: Jan Kara Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl | 2 +- tools/perf/arch/powerpc/entry/syscalls/syscall.tbl | 2 +- tools/perf/arch/s390/entry/syscalls/syscall.tbl | 2 +- tools/perf/arch/x86/entry/syscalls/syscall_64.tbl | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) (limited to 'tools') diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl index 9974f5f8e49b..9cd1c34f31b5 100644 --- a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl +++ b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl @@ -357,7 +357,7 @@ 440 n64 process_madvise sys_process_madvise 441 n64 epoll_pwait2 sys_epoll_pwait2 442 n64 mount_setattr sys_mount_setattr -443 n64 quotactl_path sys_quotactl_path +# 443 reserved for quotactl_path 444 n64 landlock_create_ruleset sys_landlock_create_ruleset 445 n64 landlock_add_rule sys_landlock_add_rule 446 n64 landlock_restrict_self sys_landlock_restrict_self diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl index 2e68fbb57cc6..8f052ff4058c 100644 --- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl @@ -522,7 +522,7 @@ 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 442 common mount_setattr sys_mount_setattr -443 common quotactl_path sys_quotactl_path +# 443 reserved for quotactl_path 444 common landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl index 7e4a2aba366d..0690263df1dd 100644 --- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl @@ -445,7 +445,7 @@ 440 common process_madvise sys_process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 442 common mount_setattr sys_mount_setattr sys_mount_setattr -443 common quotactl_path sys_quotactl_path sys_quotactl_path +# 443 reserved for quotactl_path 444 common landlock_create_ruleset sys_landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self sys_landlock_restrict_self diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index ecd551b08d05..ce18119ea0d0 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -364,7 +364,7 @@ 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 442 common mount_setattr sys_mount_setattr -443 common quotactl_path sys_quotactl_path +# 443 reserved for quotactl_path 444 common landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self -- cgit v1.2.3 From a6172059758ba1b496ae024cece7d5bdc8d017db Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 21 May 2021 12:20:51 +0300 Subject: perf scripts python: exported-sql-viewer.py: Fix copy to clipboard from Top Calls by elapsed Time report Provide missing argument to prevent following error when copying a selection to the clipboard: Traceback (most recent call last): File "tools/perf/scripts/python/exported-sql-viewer.py", line 4041, in menu.addAction(CreateAction("&Copy selection", "Copy to clipboard", lambda: CopyCellsToClipboardHdr(self.view), self.view)) File "tools/perf/scripts/python/exported-sql-viewer.py", line 4021, in CopyCellsToClipboardHdr CopyCellsToClipboard(view, False, True) File "tools/perf/scripts/python/exported-sql-viewer.py", line 4018, in CopyCellsToClipboard view.CopyCellsToClipboard(view, as_csv, with_hdr) File "tools/perf/scripts/python/exported-sql-viewer.py", line 3871, in CopyTableCellsToClipboard val = model.headerData(col, Qt.Horizontal) TypeError: headerData() missing 1 required positional argument: 'role' Fixes: 96c43b9a7ab3b ("perf scripts python: exported-sql-viewer.py: Add copy to clipboard") Signed-off-by: Adrian Hunter Cc: Jiri Olsa Cc: stable@vger.kernel.org Link: http://lore.kernel.org/lkml/20210521092053.25683-2-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/scripts/python/exported-sql-viewer.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py index 7daa8bb70a5a..b5078d65704e 100755 --- a/tools/perf/scripts/python/exported-sql-viewer.py +++ b/tools/perf/scripts/python/exported-sql-viewer.py @@ -3868,7 +3868,7 @@ def CopyTableCellsToClipboard(view, as_csv=False, with_hdr=False): if with_hdr: model = indexes[0].model() for col in range(min_col, max_col + 1): - val = model.headerData(col, Qt.Horizontal) + val = model.headerData(col, Qt.Horizontal, Qt.DisplayRole) if as_csv: text += sep + ToCSValue(val) sep = "," -- cgit v1.2.3 From fd931b2e234a7cc451a7bbb1965d6ce623189158 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 21 May 2021 12:20:52 +0300 Subject: perf scripts python: exported-sql-viewer.py: Fix Array TypeError The 'Array' class is present in more than one python standard library. In some versions of Python 3, the following error occurs: Traceback (most recent call last): File "tools/perf/scripts/python/exported-sql-viewer.py", line 4702, in reports_menu.addAction(CreateAction(label, "Create a new window displaying branch events", lambda a=None,x=dbid: self.NewBranchView(x), self)) File "tools/perf/scripts/python/exported-sql-viewer.py", line 4727, in NewBranchView BranchWindow(self.glb, event_id, ReportVars(), self) File "tools/perf/scripts/python/exported-sql-viewer.py", line 3208, in __init__ self.model = LookupCreateModel(model_name, lambda: BranchModel(glb, event_id, report_vars.where_clause)) File "tools/perf/scripts/python/exported-sql-viewer.py", line 343, in LookupCreateModel model = create_fn() File "tools/perf/scripts/python/exported-sql-viewer.py", line 3208, in self.model = LookupCreateModel(model_name, lambda: BranchModel(glb, event_id, report_vars.where_clause)) File "tools/perf/scripts/python/exported-sql-viewer.py", line 3124, in __init__ self.fetcher = SQLFetcher(glb, sql, prep, self.AddSample) File "tools/perf/scripts/python/exported-sql-viewer.py", line 2658, in __init__ self.buffer = Array(c_char, self.buffer_size, lock=False) TypeError: abstract class This apparently happens because Python can be inconsistent about which class of the name 'Array' gets imported. Fix by importing explicitly by name so that only the desired 'Array' gets imported. Fixes: 8392b74b575c3 ("perf scripts python: exported-sql-viewer.py: Add ability to display all the database tables") Signed-off-by: Adrian Hunter Cc: Jiri Olsa Cc: stable@vger.kernel.org Link: http://lore.kernel.org/lkml/20210521092053.25683-3-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/scripts/python/exported-sql-viewer.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py index b5078d65704e..4a63843f623c 100755 --- a/tools/perf/scripts/python/exported-sql-viewer.py +++ b/tools/perf/scripts/python/exported-sql-viewer.py @@ -125,8 +125,9 @@ if pyside_version_1: from PySide.QtGui import * from PySide.QtSql import * -from decimal import * -from ctypes import * +from decimal import Decimal, ROUND_HALF_UP +from ctypes import CDLL, Structure, create_string_buffer, addressof, sizeof, \ + c_void_p, c_bool, c_byte, c_char, c_int, c_uint, c_longlong, c_ulonglong from multiprocessing import Process, Array, Value, Event # xrange is range in Python3 -- cgit v1.2.3 From f56299a9c998e0bfbd4ab07cafe9eb8444512448 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 21 May 2021 12:20:53 +0300 Subject: perf scripts python: exported-sql-viewer.py: Fix warning display Deprecation warnings are useful only for the developer, not an end user. Display warnings only when requested using the python -W option. This stops the display of warnings like: tools/perf/scripts/python/exported-sql-viewer.py:5102: DeprecationWarning: an integer is required (got type PySide2.QtCore.Qt.AlignmentFlag). Implicit conversion to integers using __int__ is deprecated, and may be removed in a future version of Python. err = app.exec_() Since the warning can be fixed only in PySide2, we must wait for it to be finally fixed there. Signed-off-by: Adrian Hunter Cc: Jiri Olsa Cc: stable@vger.kernel.org # v5.3+ Link: http://lore.kernel.org/lkml/20210521092053.25683-4-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/scripts/python/exported-sql-viewer.py | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'tools') diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py index 4a63843f623c..711d4f9f5645 100755 --- a/tools/perf/scripts/python/exported-sql-viewer.py +++ b/tools/perf/scripts/python/exported-sql-viewer.py @@ -91,6 +91,11 @@ from __future__ import print_function import sys +# Only change warnings if the python -W option was not used +if not sys.warnoptions: + import warnings + # PySide2 causes deprecation warnings, ignore them. + warnings.filterwarnings("ignore", category=DeprecationWarning) import argparse import weakref import threading -- cgit v1.2.3 From f42907e8a4515635615a6ffd44242454ef843c04 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 21 May 2021 20:51:27 +0300 Subject: perf script: Add missing PERF_IP_FLAG_CHARS for VM-Entry and VM-Exit Add 'g' (guest) for VM-Entry and 'h' (host) for VM-Exit. Fixes: c025d46cd932c ("perf script: Add branch types for VM-Entry and VM-Exit") Signed-off-by: Adrian Hunter Cc: Jiri Olsa Link: http://lore.kernel.org/lkml/20210521175127.27264-1-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-intel-pt.txt | 6 +++--- tools/perf/Documentation/perf-script.txt | 7 ++++--- tools/perf/util/event.h | 2 +- 3 files changed, 8 insertions(+), 7 deletions(-) (limited to 'tools') diff --git a/tools/perf/Documentation/perf-intel-pt.txt b/tools/perf/Documentation/perf-intel-pt.txt index 1dcec73c910c..bcf3eca5afbe 100644 --- a/tools/perf/Documentation/perf-intel-pt.txt +++ b/tools/perf/Documentation/perf-intel-pt.txt @@ -108,9 +108,9 @@ displayed as follows: perf script --itrace=ibxwpe -F+flags -The flags are "bcrosyiABEx" which stand for branch, call, return, conditional, -system, asynchronous, interrupt, transaction abort, trace begin, trace end, and -in transaction, respectively. +The flags are "bcrosyiABExgh" which stand for branch, call, return, conditional, +system, asynchronous, interrupt, transaction abort, trace begin, trace end, +in transaction, VM-entry, and VM-exit respectively. perf script also supports higher level ways to dump instruction traces: diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index 5b8b61075039..48a5f5b26dd4 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -183,14 +183,15 @@ OPTIONS At this point usage is displayed, and perf-script exits. The flags field is synthesized and may have a value when Instruction - Trace decoding. The flags are "bcrosyiABEx" which stand for branch, + Trace decoding. The flags are "bcrosyiABExgh" which stand for branch, call, return, conditional, system, asynchronous, interrupt, - transaction abort, trace begin, trace end, and in transaction, + transaction abort, trace begin, trace end, in transaction, VM-Entry, and VM-Exit respectively. Known combinations of flags are printed more nicely e.g. "call" for "bc", "return" for "br", "jcc" for "bo", "jmp" for "b", "int" for "bci", "iret" for "bri", "syscall" for "bcs", "sysret" for "brs", "async" for "by", "hw int" for "bcyi", "tx abrt" for "bA", "tr strt" for "bB", - "tr end" for "bE". However the "x" flag will be display separately in those + "tr end" for "bE", "vmentry" for "bcg", "vmexit" for "bch". + However the "x" flag will be displayed separately in those cases e.g. "jcc (x)" for a condition branch within a transaction. The callindent field is synthesized and may have a value when diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 8a62fb39e365..19ad64f2bd83 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -100,7 +100,7 @@ enum { PERF_IP_FLAG_VMEXIT = 1ULL << 12, }; -#define PERF_IP_FLAG_CHARS "bcrosyiABEx" +#define PERF_IP_FLAG_CHARS "bcrosyiABExgh" #define PERF_BRANCH_MASK (\ PERF_IP_FLAG_BRANCH |\ -- cgit v1.2.3 From f8b61bd20479c094fb421da42fef6b4ff22a589e Mon Sep 17 00:00:00 2001 From: Song Liu Date: Tue, 11 May 2021 23:51:16 -0700 Subject: perf stat: Skip evlist__[enable|disable] when all events uses BPF When all events of a perf-stat session use BPF, it is not necessary to call evlist__enable() and evlist__disable(). Skip them when all_counters_use_bpf is true. Signed-off-by: Song Liu Reported-by: Jiri Olsa Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 13 ++++++++++--- tools/perf/util/evlist.c | 3 --- 2 files changed, 10 insertions(+), 6 deletions(-) (limited to 'tools') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 5a830ae09418..f9f74a514315 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -572,7 +572,8 @@ static int enable_counters(void) * - we have initial delay configured */ if (!target__none(&target) || stat_config.initial_delay) { - evlist__enable(evsel_list); + if (!all_counters_use_bpf) + evlist__enable(evsel_list); if (stat_config.initial_delay > 0) pr_info(EVLIST_ENABLED_MSG); } @@ -581,13 +582,19 @@ static int enable_counters(void) static void disable_counters(void) { + struct evsel *counter; + /* * If we don't have tracee (attaching to task or cpu), counters may * still be running. To get accurate group ratios, we must stop groups * from counting before reading their constituent counters. */ - if (!target__none(&target)) - evlist__disable(evsel_list); + if (!target__none(&target)) { + evlist__for_each_entry(evsel_list, counter) + bpf_counter__disable(counter); + if (!all_counters_use_bpf) + evlist__disable(evsel_list); + } } static volatile int workload_exec_errno; diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 6e5c41528c7d..6ea3e677dc1e 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -425,9 +425,6 @@ static void __evlist__disable(struct evlist *evlist, char *evsel_name) if (affinity__setup(&affinity) < 0) return; - evlist__for_each_entry(evlist, pos) - bpf_counter__disable(pos); - /* Disable 'immediate' events last */ for (imm = 0; imm <= 1; imm++) { evlist__for_each_cpu(evlist, i, cpu) { -- cgit v1.2.3