From 4312f2ab136a5f1a7b247f6e4a75b95afaf9d23b Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 8 Oct 2018 12:04:51 -0300 Subject: [PATCH 01/11] tools arch uapi: Sync the x86 kvm.h copy To get the changes in: d1766202779e ("x86/kvm/lapic: always disable MMIO interface in x2APIC mode") That at this time will not generate changes in tools such as 'perf trace', that still needs more work in tools/perf/examples/bpf/augmented_syscalls.c to need such id -> string tables. This silences the following perf build warning: 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: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Paolo Bonzini Cc: Vitaly Kuznetsov Cc: Wang Nan Link: https://lkml.kernel.org/n/tip-yadntj2ok6zpzjwi656onuh0@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/x86/include/uapi/asm/kvm.h | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index 86299efa804a..fd23d5778ea1 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -377,6 +377,7 @@ struct kvm_sync_regs { #define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0) #define KVM_X86_QUIRK_CD_NW_CLEARED (1 << 1) +#define KVM_X86_QUIRK_LAPIC_MMIO_HOLE (1 << 2) #define KVM_STATE_NESTED_GUEST_MODE 0x00000001 #define KVM_STATE_NESTED_RUN_PENDING 0x00000002 From 25fe15e54fe5e15b4963fe101f7cd8bad4f11393 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 8 Oct 2018 12:09:14 -0300 Subject: [PATCH 02/11] tools headers uapi: Sync kvm.h copy To pick up the changes introduced in: 6fbbde9a1969 ("KVM: x86: Control guest reads of MSR_PLATFORM_INFO") That is not yet used in tools such as 'perf trace'. The type of the change in this file, a simple integer parameter to the KVM_CHECK_EXTENSION ioctl should be easier to implement tho, adding to the libbeauty TODO list. 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: David Ahern Cc: Drew Schmitt Cc: Jiri Olsa Cc: Namhyung Kim Cc: Paolo Bonzini Cc: Wang Nan Link: https://lkml.kernel.org/n/tip-67h1bio5bihi1q6dy7hgwwx8@git.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 07548de5c988..251be353f950 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -952,6 +952,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_S390_HPAGE_1M 156 #define KVM_CAP_NESTED_STATE 157 #define KVM_CAP_ARM_INJECT_SERROR_ESR 158 +#define KVM_CAP_MSR_PLATFORM_INFO 159 #ifdef KVM_CAP_IRQ_ROUTING From 1b9caa10b31dda0866f4028e4bfb923fb6e4072f Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 3 Oct 2018 09:20:46 +0200 Subject: [PATCH 03/11] Revert "perf tools: Fix PMU term format max value calculation" This reverts commit ac0e2cd555373ae6f8f3a3ad3fbbf5b6d1e7aaaa. Michael reported an issue with oversized terms values assignment and I noticed there was actually a misunderstanding of the max value check in the past. The above commit's changelog says: If bit 21 is set, there is parsing issues as below. $ perf stat -a -e uncore_qpi_0/event=0x200002,umask=0x8/ event syntax error: '..pi_0/event=0x200002,umask=0x8/' \___ value too big for format, maximum is 511 But there's no issue there, because the event value is distributed along the value defined by the format. Even if the format defines separated bit, the value is treated as a continual number, which should follow the format definition. In above case it's 9-bit value with last bit separated: $ cat uncore_qpi_0/format/event config:0-7,21 Hence the value 0x200002 is correctly reported as format violation, because it exceeds 9 bits. It should have been 0x102 instead, which sets the 9th bit - the bit 21 of the format. $ perf stat -vv -a -e uncore_qpi_0/event=0x102,umask=0x8/ Using CPUID GenuineIntel-6-2D ... ------------------------------------------------------------ perf_event_attr: type 10 size 112 config 0x200802 sample_type IDENTIFIER ... Reported-by: Michael Petlan Signed-off-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Kan Liang Cc: Namhyung Kim Cc: Peter Zijlstra Fixes: ac0e2cd55537 ("perf tools: Fix PMU term format max value calculation") Link: http://lkml.kernel.org/r/20181003072046.29276-1-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/pmu.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index afd68524ffa9..7799788f662f 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -930,13 +930,14 @@ static void pmu_format_value(unsigned long *format, __u64 value, __u64 *v, static __u64 pmu_format_max_value(const unsigned long *format) { - __u64 w = 0; - int fbit; + int w; - for_each_set_bit(fbit, format, PERF_PMU_FORMAT_BITS) - w |= (1ULL << fbit); - - return w; + w = bitmap_weight(format, PERF_PMU_FORMAT_BITS); + if (!w) + return 0; + if (w < 64) + return (1ULL << w) - 1; + return -1; } /* From 94aafb74cee0002e2f2eb6dc5376f54d5951ab4d Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 10 Oct 2018 10:03:39 +0200 Subject: [PATCH 04/11] perf vendor events intel: Fix wrong filter_band* values for uncore events Michael reported that he could not stat following event: $ perf stat -e unc_p_freq_ge_1200mhz_cycles -a -- ls event syntax error: '..e_1200mhz_cycles' \___ value too big for format, maximum is 255 Run 'perf list' for a list of valid events The event is unwrapped into: uncore_pcu/event=0xb,filter_band0=1200/ where filter_band0 format says it's one byte only: # cat uncore_pcu/format/filter_band0 config1:0-7 while JSON files specifies bigger number: "Filter": "filter_band0=1200", all the filter_band* formats show 1 byte width: # cat uncore_pcu/format/filter_band1 config1:8-15 # cat uncore_pcu/format/filter_band2 config1:16-23 # cat uncore_pcu/format/filter_band3 config1:24-31 The reason of the issue is that filter_band* values are supposed to be in 100Mhz units.. it's stated in the JSON help for the events, like: filter_band3=XXX, with XXX in 100Mhz units This patch divides the filter_band* values by 100, plus there's couple of changes that actually change the number completely, like: - "Filter": "edge=1,filter_band2=4000", + "Filter": "edge=1,filter_band2=30", Reported-by: Michael Petlan Signed-off-by: Jiri Olsa Acked-by: Andi Kleen Cc: Alexander Shishkin Cc: Kan Liang Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20181010080339.GB15790@krava Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/x86/ivytown/uncore-power.json | 16 ++++++++-------- .../arch/x86/jaketown/uncore-power.json | 16 ++++++++-------- 2 files changed, 16 insertions(+), 16 deletions(-) diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json index d40498f2cb1e..635c09fda1d9 100644 --- a/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json +++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json @@ -188,7 +188,7 @@ "Counter": "0,1,2,3", "EventCode": "0xb", "EventName": "UNC_P_FREQ_GE_1200MHZ_CYCLES", - "Filter": "filter_band0=1200", + "Filter": "filter_band0=12", "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", "MetricName": "freq_ge_1200mhz_cycles %", "PerPkg": "1", @@ -199,7 +199,7 @@ "Counter": "0,1,2,3", "EventCode": "0xc", "EventName": "UNC_P_FREQ_GE_2000MHZ_CYCLES", - "Filter": "filter_band1=2000", + "Filter": "filter_band1=20", "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", "MetricName": "freq_ge_2000mhz_cycles %", "PerPkg": "1", @@ -210,7 +210,7 @@ "Counter": "0,1,2,3", "EventCode": "0xd", "EventName": "UNC_P_FREQ_GE_3000MHZ_CYCLES", - "Filter": "filter_band2=3000", + "Filter": "filter_band2=30", "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", "MetricName": "freq_ge_3000mhz_cycles %", "PerPkg": "1", @@ -221,7 +221,7 @@ "Counter": "0,1,2,3", "EventCode": "0xe", "EventName": "UNC_P_FREQ_GE_4000MHZ_CYCLES", - "Filter": "filter_band3=4000", + "Filter": "filter_band3=40", "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", "MetricName": "freq_ge_4000mhz_cycles %", "PerPkg": "1", @@ -232,7 +232,7 @@ "Counter": "0,1,2,3", "EventCode": "0xb", "EventName": "UNC_P_FREQ_GE_1200MHZ_TRANSITIONS", - "Filter": "edge=1,filter_band0=1200", + "Filter": "edge=1,filter_band0=12", "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", "MetricName": "freq_ge_1200mhz_cycles %", "PerPkg": "1", @@ -243,7 +243,7 @@ "Counter": "0,1,2,3", "EventCode": "0xc", "EventName": "UNC_P_FREQ_GE_2000MHZ_TRANSITIONS", - "Filter": "edge=1,filter_band1=2000", + "Filter": "edge=1,filter_band1=20", "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", "MetricName": "freq_ge_2000mhz_cycles %", "PerPkg": "1", @@ -254,7 +254,7 @@ "Counter": "0,1,2,3", "EventCode": "0xd", "EventName": "UNC_P_FREQ_GE_3000MHZ_TRANSITIONS", - "Filter": "edge=1,filter_band2=4000", + "Filter": "edge=1,filter_band2=30", "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", "MetricName": "freq_ge_3000mhz_cycles %", "PerPkg": "1", @@ -265,7 +265,7 @@ "Counter": "0,1,2,3", "EventCode": "0xe", "EventName": "UNC_P_FREQ_GE_4000MHZ_TRANSITIONS", - "Filter": "edge=1,filter_band3=4000", + "Filter": "edge=1,filter_band3=40", "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", "MetricName": "freq_ge_4000mhz_cycles %", "PerPkg": "1", diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json index 16034bfd06dd..8755693d86c6 100644 --- a/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json +++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json @@ -187,7 +187,7 @@ "Counter": "0,1,2,3", "EventCode": "0xb", "EventName": "UNC_P_FREQ_GE_1200MHZ_CYCLES", - "Filter": "filter_band0=1200", + "Filter": "filter_band0=12", "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", "MetricName": "freq_ge_1200mhz_cycles %", "PerPkg": "1", @@ -198,7 +198,7 @@ "Counter": "0,1,2,3", "EventCode": "0xc", "EventName": "UNC_P_FREQ_GE_2000MHZ_CYCLES", - "Filter": "filter_band1=2000", + "Filter": "filter_band1=20", "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", "MetricName": "freq_ge_2000mhz_cycles %", "PerPkg": "1", @@ -209,7 +209,7 @@ "Counter": "0,1,2,3", "EventCode": "0xd", "EventName": "UNC_P_FREQ_GE_3000MHZ_CYCLES", - "Filter": "filter_band2=3000", + "Filter": "filter_band2=30", "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", "MetricName": "freq_ge_3000mhz_cycles %", "PerPkg": "1", @@ -220,7 +220,7 @@ "Counter": "0,1,2,3", "EventCode": "0xe", "EventName": "UNC_P_FREQ_GE_4000MHZ_CYCLES", - "Filter": "filter_band3=4000", + "Filter": "filter_band3=40", "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", "MetricName": "freq_ge_4000mhz_cycles %", "PerPkg": "1", @@ -231,7 +231,7 @@ "Counter": "0,1,2,3", "EventCode": "0xb", "EventName": "UNC_P_FREQ_GE_1200MHZ_TRANSITIONS", - "Filter": "edge=1,filter_band0=1200", + "Filter": "edge=1,filter_band0=12", "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", "MetricName": "freq_ge_1200mhz_cycles %", "PerPkg": "1", @@ -242,7 +242,7 @@ "Counter": "0,1,2,3", "EventCode": "0xc", "EventName": "UNC_P_FREQ_GE_2000MHZ_TRANSITIONS", - "Filter": "edge=1,filter_band1=2000", + "Filter": "edge=1,filter_band1=20", "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", "MetricName": "freq_ge_2000mhz_cycles %", "PerPkg": "1", @@ -253,7 +253,7 @@ "Counter": "0,1,2,3", "EventCode": "0xd", "EventName": "UNC_P_FREQ_GE_3000MHZ_TRANSITIONS", - "Filter": "edge=1,filter_band2=4000", + "Filter": "edge=1,filter_band2=30", "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", "MetricName": "freq_ge_3000mhz_cycles %", "PerPkg": "1", @@ -264,7 +264,7 @@ "Counter": "0,1,2,3", "EventCode": "0xe", "EventName": "UNC_P_FREQ_GE_4000MHZ_TRANSITIONS", - "Filter": "edge=1,filter_band3=4000", + "Filter": "edge=1,filter_band3=40", "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", "MetricName": "freq_ge_4000mhz_cycles %", "PerPkg": "1", From 4ab8455f8bd83298bf7f67ab9357e3b1cc765c7d Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 3 Oct 2018 23:20:52 +0200 Subject: [PATCH 05/11] perf evsel: Store ids for events with their own cpus perf_event__synthesize_event_update_cpus John reported crash when recording on an event under PMU with cpumask defined: root@localhost:~# ./perf_debug_ record -e armv8_pmuv3_0/br_mis_pred/ sleep 1 perf: Segmentation fault Obtained 9 stack frames. ./perf_debug_() [0x4c5ef8] [0xffff82ba267c] ./perf_debug_() [0x4bc5a8] ./perf_debug_() [0x419550] ./perf_debug_() [0x41a928] ./perf_debug_() [0x472f58] ./perf_debug_() [0x473210] ./perf_debug_() [0x4070f4] /lib/aarch64-linux-gnu/libc.so.6(__libc_start_main+0xe0) [0xffff8294c8a0] Segmentation fault (core dumped) We synthesize an update event that needs to touch the evsel id array, which is not defined at that time. Fixing this by forcing the id allocation for events with their own cpus. Reported-by: John Garry Signed-off-by: Jiri Olsa Tested-by: John Garry Cc: Alexander Shishkin Cc: Andi Kleen Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Will Deacon Cc: linux-arm-kernel@lists.infradead.org Cc: linuxarm@huawei.com Fixes: bfd8f72c2778 ("perf record: Synthesize unit/scale/... in event update") Link: http://lkml.kernel.org/r/20181003212052.GA32371@krava Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-report.c | 1 + tools/perf/util/evsel.c | 3 +++ 2 files changed, 4 insertions(+) diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 76e12bcd1765..b2188e623e22 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -981,6 +981,7 @@ int cmd_report(int argc, const char **argv) .id_index = perf_event__process_id_index, .auxtrace_info = perf_event__process_auxtrace_info, .auxtrace = perf_event__process_auxtrace, + .event_update = perf_event__process_event_update, .feature = process_feature_event, .ordered_events = true, .ordering_requires_timestamps = true, diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 1a61628a1c12..e596ae358c4d 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -1089,6 +1089,9 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, attr->exclude_user = 1; } + if (evsel->own_cpus) + evsel->attr.read_format |= PERF_FORMAT_ID; + /* * Apply event specific term settings, * it overloads any global configuration. From 36b8d4628d3cc8f5a748e508cce8673bc00fc63c Mon Sep 17 00:00:00 2001 From: Jarod Wilson Date: Thu, 6 Sep 2018 18:18:12 -0400 Subject: [PATCH 06/11] perf tools: Fix use of alternatives to find JDIR When a build is run from something like a cron job, the user's $PATH is rather minimal, of note, not including /usr/sbin in my own case. Because of that, an automated rpm package build ultimately fails to find libperf-jvmti.so, because somewhere within the build, this happens... /bin/sh: alternatives: command not found /bin/sh: alternatives: command not found Makefile.config:849: No openjdk development package found, please install JDK package, e.g. openjdk-8-jdk, java-1.8.0-openjdk-devel ...and while the build continues, libperf-jvmti.so isn't built, and things fall down when rpm tries to find all the %files specified. Exact same system builds everything just fine when the job is launched from a login shell instead of a cron job, since alternatives is in $PATH, so openjdk is actually found. The test required to get into this section of code actually specifies the full path, as does a block just above it, so let's do that here too. Signed-off-by: Jarod Wilson Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Cc: William Cohen Fixes: d4dfdf00d43e ("perf jvmti: Plug compilation into perf build") Link: http://lkml.kernel.org/r/20180906221812.11167-1-jarod@redhat.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.config | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index f6d1a03c7523..e30d20fb482d 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -833,7 +833,7 @@ ifndef NO_JVMTI JDIR=$(shell /usr/sbin/update-java-alternatives -l | head -1 | awk '{print $$3}') else ifneq (,$(wildcard /usr/sbin/alternatives)) - JDIR=$(shell alternatives --display java | tail -1 | cut -d' ' -f 5 | sed 's%/jre/bin/java.%%g') + JDIR=$(shell /usr/sbin/alternatives --display java | tail -1 | cut -d' ' -f 5 | sed 's%/jre/bin/java.%%g') endif endif ifndef JDIR From c458a6206d2a8600934617ccf88ba7d3a030faba Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 16 Oct 2018 13:48:18 +0200 Subject: [PATCH 07/11] perf tools: Fix tracing_path_mount proper path If there's no tracefs (RHEL7) support the tracing_path_mount returns debugfs path which results in following fail: # perf probe sys_write kprobe_events file does not exist - please rebuild kernel with CONFIG_KPROBE_EVENTS. Error: Failed to add events. In tracing_path_debugfs_mount function we need to return the 'tracing' path instead of just the mount to make it work: # perf probe sys_write Added new event: probe:sys_write (on sys_write) You can now use it in all perf tools, such as: perf record -e probe:sys_write -aR sleep 1 Adding the 'return tracing_path;' also to tracing_path_tracefs_mount function just for consistency with tracing_path_debugfs_mount. Upstream keeps working, because it has the tracefs support. Link: http://lkml.kernel.org/n/tip-yiwkzexq9fk1ey1xg3gnjlw4@git.kernel.org Signed-off-by: Jiri Olsa Cc: Alexander Shishkin Cc: Michael Petlan Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Steven Rostedt Fixes: 23773ca18b39 ("perf tools: Make perf aware of tracefs") Link: http://lkml.kernel.org/r/20181016114818.3595-1-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/api/fs/tracing_path.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/lib/api/fs/tracing_path.c b/tools/lib/api/fs/tracing_path.c index 120037496f77..5afb11b30fca 100644 --- a/tools/lib/api/fs/tracing_path.c +++ b/tools/lib/api/fs/tracing_path.c @@ -36,7 +36,7 @@ static const char *tracing_path_tracefs_mount(void) __tracing_path_set("", mnt); - return mnt; + return tracing_path; } static const char *tracing_path_debugfs_mount(void) @@ -49,7 +49,7 @@ static const char *tracing_path_debugfs_mount(void) __tracing_path_set("tracing/", mnt); - return mnt; + return tracing_path; } const char *tracing_path_mount(void) From 0ed149cf5239cc6e7e65bf00f769e8f1e91076c0 Mon Sep 17 00:00:00 2001 From: David Miller Date: Thu, 11 Oct 2018 22:46:55 -0700 Subject: [PATCH 08/11] perf cpu_map: Align cpu map synthesized events properly. The size of the resulting cpu map can be smaller than a multiple of sizeof(u64), resulting in SIGBUS on cpus like Sparc as the next event will not be aligned properly. Signed-off-by: David S. Miller Cc: Jiri Olsa Cc: Kan Liang Fixes: 6c872901af07 ("perf cpu_map: Add cpu_map event synthesize function") Link: http://lkml.kernel.org/r/20181011.224655.716771175766946817.davem@davemloft.net Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/event.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 0cd42150f712..0988eb3b844b 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -1081,6 +1081,7 @@ void *cpu_map_data__alloc(struct cpu_map *map, size_t *size, u16 *type, int *max } *size += sizeof(struct cpu_map_data); + *size = PERF_ALIGN(*size, sizeof(u64)); return zalloc(*size); } From d4046e8e17b9f378cb861982ef71c63911b5dff3 Mon Sep 17 00:00:00 2001 From: Milian Wolff Date: Wed, 26 Sep 2018 15:52:07 +0200 Subject: [PATCH 09/11] perf report: Don't crash on invalid inline debug information When the function name for an inline frame is invalid, we must not try to demangle this symbol, otherwise we crash with: #0 0x0000555555895c01 in bfd_demangle () #1 0x0000555555823262 in demangle_sym (dso=0x555555d92b90, elf_name=0x0, kmodule=0) at util/symbol-elf.c:215 #2 dso__demangle_sym (dso=dso@entry=0x555555d92b90, kmodule=, kmodule@entry=0, elf_name=elf_name@entry=0x0) at util/symbol-elf.c:400 #3 0x00005555557fef4b in new_inline_sym (funcname=0x0, base_sym=0x555555d92b90, dso=0x555555d92b90) at util/srcline.c:89 #4 inline_list__append_dso_a2l (dso=dso@entry=0x555555c7bb00, node=node@entry=0x555555e31810, sym=sym@entry=0x555555d92b90) at util/srcline.c:264 #5 0x00005555557ff27f in addr2line (dso_name=dso_name@entry=0x555555d92430 "/home/milian/.debug/.build-id/f7/186d14bb94f3c6161c010926da66033d24fce5/elf", addr=addr@entry=2888, file=file@entry=0x0, line=line@entry=0x0, dso=dso@entry=0x555555c7bb00, unwind_inlines=unwind_inlines@entry=true, node=0x555555e31810, sym=0x555555d92b90) at util/srcline.c:313 #6 0x00005555557ffe7c in addr2inlines (sym=0x555555d92b90, dso=0x555555c7bb00, addr=2888, dso_name=0x555555d92430 "/home/milian/.debug/.build-id/f7/186d14bb94f3c6161c010926da66033d24fce5/elf") at util/srcline.c:358 So instead handle the case where we get invalid function names for inlined frames and use a fallback '??' function name instead. While this crash was originally reported by Hadrien for rust code, I can now also reproduce it with trivial C++ code. Indeed, it seems like libbfd fails to interpret the debug information for the inline frame symbol name: $ addr2line -e /home/milian/.debug/.build-id/f7/186d14bb94f3c6161c010926da66033d24fce5/elf -if b48 main /usr/include/c++/8.2.1/complex:610 ?? /usr/include/c++/8.2.1/complex:618 ?? /usr/include/c++/8.2.1/complex:675 ?? /usr/include/c++/8.2.1/complex:685 main /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 I've reported this bug upstream and also attached a patch there which should fix this issue: https://sourceware.org/bugzilla/show_bug.cgi?id=23715 Reported-by: Hadrien Grasland Signed-off-by: Milian Wolff Cc: Jin Yao Cc: Jiri Olsa Cc: Namhyung Kim Fixes: a64489c56c30 ("perf report: Find the inline stack for a given address") [ The above 'Fixes:' cset is where originally the problem was introduced, i.e. using a2l->funcname without checking if it is NULL, but this current patch fixes the current codebase, i.e. multiple csets were applied after a64489c56c30 before the problem was reported by Hadrien ] Link: http://lkml.kernel.org/r/20180926135207.30263-3-milian.wolff@kdab.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/srcline.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c index 09d6746e6ec8..e767c4a9d4d2 100644 --- a/tools/perf/util/srcline.c +++ b/tools/perf/util/srcline.c @@ -85,6 +85,9 @@ static struct symbol *new_inline_sym(struct dso *dso, struct symbol *inline_sym; char *demangled = NULL; + if (!funcname) + funcname = "??"; + if (dso) { demangled = dso__demangle_sym(dso, 0, funcname); if (demangled) From 298faf53200fc02af38d32715697df6e661c1257 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 16 Oct 2018 17:06:07 +0200 Subject: [PATCH 10/11] perf tools: Pass build flags to traceevent build So the extra user build flags are propagated to libtraceevent. Signed-off-by: Jiri Olsa Cc: "Herton R. Krzesinski" Cc: Steven Rostedt (VMware) Cc: Tzvetomir Stoyanov (VMware) Cc: Yordan Karadzhov (VMware) Link: http://lkml.kernel.org/r/20181016150614.21260-3-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.perf | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 5224ade3d5af..0be411695379 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -635,7 +635,7 @@ $(LIBPERF_IN): prepare FORCE $(LIB_FILE): $(LIBPERF_IN) $(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $(LIBPERF_IN) $(LIB_OBJS) -LIBTRACEEVENT_FLAGS += plugin_dir=$(plugindir_SQ) +LIBTRACEEVENT_FLAGS += plugin_dir=$(plugindir_SQ) 'EXTRA_CFLAGS=$(EXTRA_CFLAGS)' 'LDFLAGS=$(LDFLAGS)' $(LIBTRACEEVENT): FORCE $(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) $(OUTPUT)libtraceevent.a From edeb0c90df3581b821a764052d185df985f8b8dc Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 16 Oct 2018 17:08:29 -0300 Subject: [PATCH 11/11] perf tools: Stop fallbacking to kallsyms for vdso symbols lookup David reports that: Perf has this hack where it uses the kernel symbol map as a backup when a symbol can't be found in the user's symbol table(s). This causes problems because the tests driving this code path use machine__kernel_ip(), and that is completely meaningless on Sparc. On sparc64 the kernel and user live in physically separate virtual address spaces, rather than a shared one. And the kernel lives at a virtual address that overlaps common userspace addresses. So this test passes almost all the time when a user symbol lookup fails. The consequence of this is that, if the unfound user virtual address in the sample doesn't match up to a kernel symbol either, we trigger things like this code in builtin-top.c: if (al.sym == NULL && al.map != NULL) { const char *msg = "Kernel samples will not be resolved.\n"; /* * As we do lazy loading of symtabs we only will know if the * specified vmlinux file is invalid when we actually have a * hit in kernel space and then try to load it. So if we get * here and there are _no_ symbols in the DSO backing the * kernel map, bail out. * * We may never get here, for instance, if we use -K/ * --hide-kernel-symbols, even if the user specifies an * invalid --vmlinux ;-) */ if (!machine->kptr_restrict_warned && !top->vmlinux_warned && __map__is_kernel(al.map) && map__has_symbols(al.map)) { if (symbol_conf.vmlinux_name) { char serr[256]; dso__strerror_load(al.map->dso, serr, sizeof(serr)); ui__warning("The %s file can't be used: %s\n%s", symbol_conf.vmlinux_name, serr, msg); } else { ui__warning("A vmlinux file was not found.\n%s", msg); } if (use_browser <= 0) sleep(5); top->vmlinux_warned = true; } } When I fire up a compilation on sparc, this triggers immediately. I'm trying to figure out what the "backup to kernel map" code is accomplishing. I see some language in the current code and in the changes that have happened in this area talking about vdso. Does that really happen? The vdso is mapped into userspace virtual addresses, not kernel ones. More history. This didn't cause problems on sparc some time ago, because the kernel IP check used to be "ip < 0" :-) Sparc kernel addresses are not negative. But now with machine__kernel_ip(), which works using the symbol table determined kernel address range, it does trigger. What it all boils down to is that on architectures like sparc, machine__kernel_ip() should always return false in this scenerio, and therefore this kind of logic: if (cpumode == PERF_RECORD_MISC_USER && machine && mg != &machine->kmaps && machine__kernel_ip(machine, al->addr)) { is basically invalid. PERF_RECORD_MISC_USER implies no kernel address can possibly match for the sample/event in question (no matter how hard you try!) :-) So, I thought something had changed and in the past we would somehow find that address in the kallsyms, but I couldn't find anything to back that up, the patch introducing this is over a decade old, lots of things changed, so I was just thinking I was missing something. I tried a gtod busy loop to generate vdso activity and added a 'perf probe' at that branch, on x86_64 to see if it ever gets hit: Made thread__find_map() noinline, as 'perf probe' in lines of inline functions seems to not be working, only at function start. (Masami?) # perf probe -x ~/bin/perf -L thread__find_map:57 57 if (cpumode == PERF_RECORD_MISC_USER && machine && 58 mg != &machine->kmaps && 59 machine__kernel_ip(machine, al->addr)) { 60 mg = &machine->kmaps; 61 load_map = true; 62 goto try_again; } } else { /* * Kernel maps might be changed when loading * symbols so loading * must be done prior to using kernel maps. */ 69 if (load_map) 70 map__load(al->map); 71 al->addr = al->map->map_ip(al->map, al->addr); # perf probe -x ~/bin/perf thread__find_map:60 Added new event: probe_perf:thread__find_map (on thread__find_map:60 in /home/acme/bin/perf) You can now use it in all perf tools, such as: perf record -e probe_perf:thread__find_map -aR sleep 1 # Then used this to see if, system wide, those probe points were being hit: # perf trace -e *perf:thread*/max-stack=8/ ^C[root@jouet ~]# No hits when running 'perf top' and: # cat gtod.c #include int main(void) { struct timeval tv; while (1) gettimeofday(&tv, 0); return 0; } [root@jouet c]# ./gtod ^C Pressed 'P' in 'perf top' and the [vdso] samples are there: 62.84% [vdso] [.] __vdso_gettimeofday 8.13% gtod [.] main 7.51% [vdso] [.] 0x0000000000000914 5.78% [vdso] [.] 0x0000000000000917 5.43% gtod [.] _init 2.71% [vdso] [.] 0x000000000000092d 0.35% [kernel] [k] native_io_delay 0.33% libc-2.26.so [.] __memmove_avx_unaligned_erms 0.20% [vdso] [.] 0x000000000000091d 0.17% [i2c_i801] [k] i801_access 0.06% firefox [.] free 0.06% libglib-2.0.so.0.5400.3 [.] g_source_iter_next 0.05% [vdso] [.] 0x0000000000000919 0.05% libpthread-2.26.so [.] __pthread_mutex_lock 0.05% libpixman-1.so.0.34.0 [.] 0x000000000006d3a7 0.04% [kernel] [k] entry_SYSCALL_64_trampoline 0.04% libxul.so [.] style::dom_apis::query_selector_slow 0.04% [kernel] [k] module_get_kallsym 0.04% firefox [.] malloc 0.04% [vdso] [.] 0x0000000000000910 I added a 'perf probe' to thread__find_map:69, and that surely got tons of hits, i.e. for every map found, just to make sure the 'perf probe' command was really working. In the process I noticed a bug, we're only have records for '[vdso]' for pre-existing commands, i.e. ones that are running when we start 'perf top', when we will generate the PERF_RECORD_MMAP by looking at /perf/PID/maps. I.e. like this, for preexisting processes with a vdso map, again, tracing for all the system, only pre-existing processes get a [vdso] map (when having one): [root@jouet ~]# perf probe -x ~/bin/perf __machine__addnew_vdso Added new event: probe_perf:__machine__addnew_vdso (on __machine__addnew_vdso in /home/acme/bin/perf) You can now use it in all perf tools, such as: perf record -e probe_perf:__machine__addnew_vdso -aR sleep 1 [root@jouet ~]# perf trace -e probe_perf:__machine__addnew_vdso/max-stack=8/ 0.000 probe_perf:__machine__addnew_vdso:(568eb3) __machine__addnew_vdso (/home/acme/bin/perf) map__new (/home/acme/bin/perf) machine__process_mmap2_event (/home/acme/bin/perf) machine__process_event (/home/acme/bin/perf) perf_event__process (/home/acme/bin/perf) perf_tool__process_synth_event (/home/acme/bin/perf) perf_event__synthesize_mmap_events (/home/acme/bin/perf) __event__synthesize_thread (/home/acme/bin/perf) The kernel is generating a PERF_RECORD_MMAP for vDSOs, but somehow 'perf top' is not getting those records while 'perf record' is: # perf record ~acme/c/gtod ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.076 MB perf.data (1499 samples) ] # perf report -D | grep PERF_RECORD_MMAP2 71293612401913 0x11b48 [0x70]: PERF_RECORD_MMAP2 25484/25484: [0x400000(0x1000) @ 0 fd:02 1137 541179306]: r-xp /home/acme/c/gtod 71293612419012 0x11be0 [0x70]: PERF_RECORD_MMAP2 25484/25484: [0x7fa4a2783000(0x227000) @ 0 fd:00 3146370 854107250]: r-xp /usr/lib64/ld-2.26.so 71293612432110 0x11c50 [0x60]: PERF_RECORD_MMAP2 25484/25484: [0x7ffcdb53a000(0x2000) @ 0 00:00 0 0]: r-xp [vdso] 71293612509944 0x11cb0 [0x70]: PERF_RECORD_MMAP2 25484/25484: [0x7fa4a23cd000(0x3b6000) @ 0 fd:00 3149723 262067164]: r-xp /usr/lib64/libc-2.26.so # # perf script | grep vdso | head gtod 25484 71293.612768: 2485554 cycles:ppp: 7ffcdb53a914 [unknown] ([vdso]) gtod 25484 71293.613576: 2149343 cycles:ppp: 7ffcdb53a917 [unknown] ([vdso]) gtod 25484 71293.614274: 1814652 cycles:ppp: 7ffcdb53aca8 __vdso_gettimeofday+0x98 ([vdso]) gtod 25484 71293.614862: 1669070 cycles:ppp: 7ffcdb53acc5 __vdso_gettimeofday+0xb5 ([vdso]) gtod 25484 71293.615404: 1451589 cycles:ppp: 7ffcdb53acc5 __vdso_gettimeofday+0xb5 ([vdso]) gtod 25484 71293.615999: 1269941 cycles:ppp: 7ffcdb53ace6 __vdso_gettimeofday+0xd6 ([vdso]) gtod 25484 71293.616405: 1177946 cycles:ppp: 7ffcdb53a914 [unknown] ([vdso]) gtod 25484 71293.616775: 1121290 cycles:ppp: 7ffcdb53ac47 __vdso_gettimeofday+0x37 ([vdso]) gtod 25484 71293.617150: 1037721 cycles:ppp: 7ffcdb53ace6 __vdso_gettimeofday+0xd6 ([vdso]) gtod 25484 71293.617478: 994526 cycles:ppp: 7ffcdb53ace6 __vdso_gettimeofday+0xd6 ([vdso]) # The patch is the obvious one and with it we also continue to resolve vdso symbols for pre-existing processes in 'perf top' and for all processes in 'perf record' + 'perf report/script'. Suggested-by: David Miller Acked-by: David Miller Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: https://lkml.kernel.org/n/tip-cs7skq9pp0kjypiju6o7trse@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/event.c | 21 ++------------------- 1 file changed, 2 insertions(+), 19 deletions(-) diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 0988eb3b844b..bc646185f8d9 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -1561,26 +1561,9 @@ struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr, return NULL; } -try_again: + al->map = map_groups__find(mg, al->addr); - if (al->map == NULL) { - /* - * If this is outside of all known maps, and is a negative - * address, try to look it up in the kernel dso, as it might be - * a vsyscall or vdso (which executes in user-mode). - * - * XXX This is nasty, we should have a symbol list in the - * "[vdso]" dso, but for now lets use the old trick of looking - * in the whole kernel symbol list. - */ - if (cpumode == PERF_RECORD_MISC_USER && machine && - mg != &machine->kmaps && - machine__kernel_ip(machine, al->addr)) { - mg = &machine->kmaps; - load_map = true; - goto try_again; - } - } else { + if (al->map != NULL) { /* * Kernel maps might be changed when loading symbols so loading * must be done prior to using kernel maps.