- 21 Mar, 2017 12 commits
-
-
Andi Kleen authored
Factor out the PMU name matching in the event parser into a separate function, to use the same code for other grammar rules later. Signed-off-by:
Andi Kleen <ak@linux.intel.com> Acked-by:
Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170320201711.14142-5-andi@firstfloor.orgSigned-off-by:
Arnaldo Carvalho de Melo <acme@redhat.com>
-
Andi Kleen authored
When any result that is being merged is bad, mark them all bad to give consistent output in interval mode. No before/after, because the issue was only found in theoretical review and it is hard to reproduce Signed-off-by:
-
Andi Kleen authored
The uncore PMU has a lot of duplicated PMUs for different subsystems. When expanding an uncore alias we usually end up with a large number of identically named aliases, which makes perf stat output difficult to read. Automatically sum them up in perf stat, unless --no-merge is specified. This can be default because only the uncores generally have duplicated aliases. Other PMUs have unique names. Before: % perf stat --no-merge -a -e unc_c_llc_lookup.any sleep 1 Performance counter stats for 'system wide': 694,976 Bytes unc_c_llc_lookup.any 706,304 Bytes unc_c_llc_lookup.any 956,608 Bytes unc_c_llc_lookup.any 782,720 Bytes unc_c_llc_lookup.any 605,696 Bytes unc_c_llc_lookup.any 442,816 Bytes unc_c_llc_lookup.any 659,328 Bytes unc_c_llc_lookup.any 509,312 Bytes unc_c_llc_lookup.any 263,936 Bytes unc_c_llc_lookup.any 592,448 Bytes unc_c_llc_lookup.any 672,448 Bytes unc_c_llc_lookup.any 608,640 Bytes unc_c_llc_lookup.any 641,024 Bytes unc_c_llc_lookup.any 856,896 Bytes unc_c_llc_lookup.any 808,832 Bytes unc_c_llc_lookup.any 684,864 Bytes unc_c_llc_lookup.any 710,464 Bytes unc_c_llc_lookup.any 538,304 Bytes unc_c_llc_lookup.any 1.002577660 seconds time elapsed After: % perf stat -a -e unc_c_llc_lookup.any sleep 1 Performance counter stats for 'system wide': 2,685,120 Bytes unc_c_llc_lookup.any 1.002648032 seconds time elapsed v2: Split collect_aliases. Rename alias flag. v3: Make sure unsupported/not counted is always printed. v4: Factor out callback change into separate patch. v5: Move check for bad results here Move merged check into collect_data Signed-off-by: -
Andi Kleen authored
To be used in next patch to support automatic summing of alias events. v2: Move check for bad results to next patch v3: Remove trivial addition. v4: Use perf_evsel__cpus instead of evsel->cpus Signed-off-by:
-
Arnaldo Carvalho de Melo authored
The source code line number (lineno) needs to be kept in accross calls to symbol__parse_objdump_line() when parsing the output of 'objdump -l -dS', so that it can associate it with the instructions till the next line. See disasm_line__new() and struct disasm_line::line_nr. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Taeung Song <treeze.taeung@gmail.com> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-7hpx8f8ybdpiujceysaj229w@git.kernel.orgSigned-off-by:
-
Taeung Song authored
The 'grep -v "filename"' applied to the objdump command output cause a side effect eliminating filename:linenr of output of 'objdump -l' if the object file name and source file name are the same, fix it. E.g. the output of the following objdump command in symbol__disassemble(): $ objdump -l -d -S -C /home/taeung/hello --start-address=... /home/taeung/hello: file format elf64-x86-64 Disassembly of section .text: 0000000000400526 <main>: main(): /home/taeung/hello.c:4 void main() { 400526: 55 push %rbp 400527: 48 89 e5 mov %rsp,%rbp /home/taeung/hello.c:5 ... But it uses grep -v "filename" e.g. "/home/taeung/hello" in the objdump command to remove the first line containing file name and file format ("/home/taeung/hello: file format elf64-x86-64"): Before: $ objdump -l -d -S -C /home/taeung/hello | grep /home/taeung/hello But this causes a side effect, removing filename:linenr too, because the object file and source file have the same name e.g. "/home/taueng/hello", "/home/taeung/hello.c" So more do a better match by using grep -v as below to correctly remove that first line: "/home/taeung/hello: file format elf64-x86-64" After: $ objdump -l -d -S -C /home/taeung/hello | grep /home/taeung/hello: Signed-off-by:Taeung Song <treeze.taeung@gmail.com> Tested-by:
-
Ravi Bangoria authored
'perf probe' is failing for sdt markers whose arguments has rNN (with postfix b/w/d), %rsp, %esp, %sil etc. registers. Add renaming logic for these registers. Signed-off-by:
Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com> Acked-by:
Masami Hiramatsu <mhiramat@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexis Berlemont <alexis.berlemont@gmail.com> Cc: Madhavan Srinivasan <maddy@linux.vnet.ibm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20170202111143.14319-3-ravi.bangoria@linux.vnet.ibm.comSigned-off-by:
-
Alexis Berlemont authored
An sdt probe can be associated with arguments but they were not passed to the user probe tracing interface (uprobe_events); this patch adapts the sdt argument descriptors according to the uprobe input format. As the uprobe parser does not support scaled address mode, perf will skip arguments which cannot be adapted to the uprobe format. Here are the results: $ perf buildid-cache -v --add test_sdt $ perf probe -x test_sdt sdt_libfoo:table_frob $ perf probe -x test_sdt sdt_libfoo:table_diddle $ perf record -e sdt_libfoo:table_frob -e sdt_libfoo:table_diddle test_sdt $ perf script test_sdt ... 666.255678: sdt_libfoo:table_frob: (4004d7) arg0=0 arg1=0 test_sdt ... 666.255683: sdt_libfoo:table_diddle: (40051a) arg0=0 arg1=0 test_sdt ... 666.255686: sdt_libfoo:table_frob: (4004d7) arg0=1 arg1=2 test_sdt ... 666.255689: sdt_libfoo:table_diddle: (40051a) arg0=3 arg1=4 test_sdt ... 666.255692: sdt_libfoo:table_frob: (4004d7) arg0=2 arg1=4 test_sdt ... 666.255694: sdt_libfoo:table_diddle: (40051a) arg0=6 arg1=8 Signed-off-by:
Alexis Berlemont <alexis.berlemont@gmail.com> Acked-by:
-
Alexis Berlemont authored
During a "perf buildid-cache --add" command, the section ".note.stapsdt" of the "added" binary is scanned in order to list the available SDT markers available in a binary. The parts containing the probes arguments were left unscanned. The whole section is now parsed; the probe arguments are extracted for later use. Signed-off-by:
-
Kefeng Wang authored
On old perf, when using 'perf probe -d' to delete an inexistent event, it returns errno, eg, -bash-4.3# perf probe -d xxx || echo $? Info: Event "*:xxx" does not exist. Error: Failed to delete events. 255 But now perf_del_probe_events() will always set ret = 0, different from previous del_perf_probe_events(). After this, it returns errno again, eg, -bash-4.3# ./perf probe -d xxx || echo $? "xxx" does not hit any event. Error: Failed to delete events. 254 And it is more appropriate to return -ENOENT instead of -EPERM. Signed-off-by:Kefeng Wang <wangkefeng.wang@huawei.com> Acked-by:
-
Ravi Bangoria authored
There are many SDT markers in powerpc whose uprobe definition goes beyond current MAX_CMDLEN, especially when target filename is long and sdt marker has long list of arguments. For example, definition of sdt marker method__compile__end: 8@17 8@9 8@10 -4@8 8@7 -4@6 8@5 -4@4 1@37(28) from file /usr/lib/jvm/java-1.8.0-openjdk-1.8.0.91-2.b14.fc22.ppc64/jre/lib/ppc64/server/libjvm.so is p:sdt_hotspot/method__compile__end /usr/lib/jvm/java-1.8.0-openjdk-\ 1.8.0.91-2.b14.fc22.ppc64/jre/lib/ppc64/server/libjvm.so:0x4c4e00\ arg1=%gpr17:u64 arg2=%gpr9:u64 arg3=%gpr10:u64 arg4=%gpr8:s32\ arg5=%gpr7:u64 arg6=%gpr6:s32 arg7=%gpr5:u64 arg8=%gpr4:s32\ arg9=+37(%gpr28):u8 'perf probe' fails with segfault for such markers. As the uprobe_events file accepts definitions up to 4094 characters(4096 - 2 (\n\0)), increase value of MAX_CMDLEN match that. Signed-off-by: -
Ingo Molnar authored
Merge tag 'perf-core-for-mingo-4.12-20170320' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo: Fixes: - Fix concat_probe_trace_events() in 'perf probe', it should dereference a pointer, not test its value (Ravi Bangoria) User visible changes: - Handle partial AUX records, checking if 'kvm_intel.ko' is loaded and if its 'vmm_exclusive' parameter is set to 0, suggesting tweaking it to reduce gaps (Alexander Shishkin) Infrastructure changes: - Sync the kvm.h, cpufeatures.h and perf_event.h tools/ headers copies with the kernel (Arnaldo Carvalho de Melo, Alexander Shishkin) - 'perf lock' subcommands should include common options, using OPT_PARENT() (Changbin Du) - Ditto for 'perf timechart' (Arnaldo Carvalho de Melo) Documentation changes: Correct 'perf stat --no-aggr' description (Ravi Bangoria) Signed-off-by:
Ingo Molnar <mingo@kernel.org>
-
- 20 Mar, 2017 4 commits
-
-
Arnaldo Carvalho de Melo authored
The changes in the following csets are not relevant for what is used in tools/perf/arch/powerpc/util/kvm-stat.c, but lets sync it to silence the diff detector in the tools build system: c9270132 ("KVM: PPC: Book3S HV: Add userspace interfaces for POWER9 MMU") 17d48610 ("KVM: PPC: Book 3S: XICS: Implement ICS P/Q states") Cc: Alexander Yarygin <yarygin@linux.vnet.ibm.com> Cc: David Ahern <dsahern@gmail.com> Cc: Li Zhong <zhong@linux.vnet.ibm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Scott Wood <scottwood@freescale.com> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Link: http://lkml.kernel.org/n/tip-nsqxpyzcv4ywesikhhhrgfgc@git.kernel.orgSigned-off-by:
-
Ravi Bangoria authored
'*ntevs' contains number of elements present in 'tevs' array. If there are no elements in array, 'tevs2' can be directly assigned to 'tevs' without allocating more space. So the condition should be '*ntevs == 0' not 'ntevs == 0'. Signed-off-by:
-
Ravi Bangoria authored
Description of --no-aggr in perf-stat man page is outdated. --no-aggr can also be used while profiling specific set of cpus. For ex, $ perf stat -e cycles,instructions -C 1-2 --no-aggr -- sleep 1 Performance counter stats for 'CPU(s) 1-2': CPU1 5,94,92,795 cycles CPU2 2,69,72,403 cycles CPU1 2,02,08,327 instructions # 0.34 insn per cycle CPU2 73,17,123 instructions # 0.12 insn per cycle 1.000989132 seconds time elapsed Signed-off-by: -
Arnaldo Carvalho de Melo authored
The changes in the following csets are not relevant for 'perf kvm' usage but lets sync it to silence the diff detector in the tools build system: e96a006c ("KVM: arm/arm64: vgic: Implement KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO ioctl") d017d7b0 ("KVM: arm/arm64: vgic: Implement VGICv3 CPU interface access") 94574c94 ("KVM: arm/arm64: vgic: Add distributor and redistributor access") Cc: Hemant Kumar <hemant@linux.vnet.ibm.com> Cc: Marc Zyngier <marc.zyngier@arm.com> Cc: Vijaya Kumar K <Vijaya.Kumar@cavium.com> Cc: Yunlong Song <yunlong.song@huawei.com> Link: http://lkml.kernel.org/n/tip-nsqxpyzcv4ywesikhhhrgfgc@git.kernel.orgSigned-off-by:
-
- 17 Mar, 2017 7 commits
-
-
Arnaldo Carvalho de Melo authored
We use those in tools/arch/x86/lib/mem{cpy,set}_64.S, in turn used in the 'perf bench mem' benchmarks. The changes in the following csets are not relevant for this usecase, but lets sync it to silence the diff detector in the tools build system: 6fb89569 ("x86/cpufeature: Add 5-level paging detection") Link: http://lkml.kernel.org/n/tip-nsqxpyzcv4ywesikhhhrgfgc@git.kernel.orgSigned-off-by: -
Alexander Shishkin authored
This patch decodes the 'partial' flag in AUX records and prints a warning to the user, so that they don't have to guess why their PT traces contain gaps (or missing altogether): Warning: AUX data had gaps in it 8 times out of 8! Are you running a KVM guest in the background? Trying to be even more helpful, we will detect if the user's kvm driver sets up exclusive VMX root mode for the entire lifespan of the kvm process: Reloading kvm_intel module with vmm_exclusive=0 will reduce the gaps to only guest's timeslices. Note however, that you'll still have gaps in cpu-wide traces even with vmm_exclusive=0, but the number of gaps will be below 100% (as opposed to the above example). Currently this is the only reason for partial records. Signed-off-by:
Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Cc: Vince Weaver <vince@deater.net> Link: http://lkml.kernel.org/r/8760j941ig.fsf@ashishki-desk.ger.corp.intel.comSigned-off-by:
-
Alexander Shishkin authored
To get PERF_AUX_FLAG_PARTIAL, introduced in: ae0c2d99 ("perf/core: Add a flag for partial AUX records") and that will be used to warn the user about gaps in AUX records due to VMX being used in KVM guests. Silences the kernel/tools file copy detector: Warning: include/uapi/linux/perf_event.h differs from kernel Signed-off-by:
-
Alexander Shishkin authored
Will be used in a upcoming patch warning about PERF_RECORD_AUX data gaps, reading the "module/kvm_intel/parameters/vmm_exclusive" sysfs entry. Signed-off-by:
-
Arnaldo Carvalho de Melo authored
Move -T/--tasks-only and -P/--power-only options to a separate options array that then gets referenced via OPT_PARENT from the 'perf timechart' and 'perf timechart record' option arrays. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Changbin Du <changbin.du@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-j80lol9wj1i6556ibh48iebe@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
All options need the -f/--force option, so move it to the array referenced via OPT_PARENT. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Changbin Du <changbin.du@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-unbeionpi58rioh4e9w8kp4n@git.kernel.orgSigned-off-by:
-
Changbin Du authored
When I use -i option for report subcommand, it doesn't accept it. We need add common options using OPT_PARENT macro. perf lock report -i lock_perf.data Error: unknown switch `i' Usage: perf lock report [<options>] -f, --force don't complain, do it -k, --key <acquired> key for sorting ... Signed-off-by:Changbin Du <changbin.du@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20170317055342.8284-1-changbin.du@intel.comSigned-off-by:
-
- 16 Mar, 2017 9 commits
-
-
Ingo Molnar authored
Merge tag 'perf-core-for-mingo-4.12-20170316' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo: New features: - Add 'brstackinsn' field in 'perf script' to reuse the x86 instruction decoder used in the Intel PT code to study hot paths to samples (Andi Kleen) Kernel changes: - Default UPROBES_EVENTS to Y (Alexei Starovoitov) - Fix check for kretprobe offset within function entry (Naveen N. Rao) Infrastructure changes: - Introduce util func is_sdt_event() (Ravi Bangoria) - Make perf_event__synthesize_mmap_events() scale on older kernels where reading /proc/pid/maps is way slower than reading /proc/pid/task/pid/maps (Stephane Eranian) Signed-off-by:
-
Arnaldo Carvalho de Melo authored
As it is already turned on by most distros, so just flip the default to Y. Suggested-by:
Alexei Starovoitov <alexei.starovoitov@gmail.com> Acked-by:
David Ahern <dsahern@gmail.com> Acked-by:
Namhyung Kim <namhyung@kernel.org> Acked-by:
Srikar Dronamraju <srikar@linux.vnet.ibm.com> Acked-by:
Wang Nan <wangnan0@huawei.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Anton Blanchard <anton@ozlabs.org> Cc: David Miller <davem@davemloft.net> Cc: Hemant Kumar <hemant@linux.vnet.ibm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/20170316005817.GA6805@ast-mbp.thefacebook.comSigned-off-by:
-
Andi Kleen authored
Implement printing instruction sequences as hex dump for branch stacks. This relies on the x86 instruction decoder used by the PT decoder to find the lengths of instructions to dump them individually. This is good enough for pattern matching. This allows to study hot paths for individual samples, together with branch misprediction and cycle count / IPC information if available (on Skylake systems). % perf record -b ... % perf script -F brstackinsn ... read_hpet+67: ffffffff9905b843 insn: 74 ea # PRED ffffffff9905b82f insn: 85 c9 ffffffff9905b831 insn: 74 12 ffffffff9905b833 insn: f3 90 ffffffff9905b835 insn: 48 8b 0f ffffffff9905b838 insn: 48 89 ca ffffffff9905b83b insn: 48 c1 ea 20 ffffffff9905b83f insn: 39 f2 ffffffff9905b841 insn: 89 d0 ffffffff9905b843 insn: 74 ea # PRED Only works when no special branch filters are specified. Occasionally the path does not reach up to the sample IP, as the LBRs may be frozen before executing a final jump. In this case we print a special message. The instruction dumper piggy backs on the existing infrastructure from the IP PT decoder. An earlier iteration of this patch relied on a disassembler, but this version only uses the existing instruction decoder. Committer note: Added hint about how to get suitable perf.data files for use with '-F brstackinsm': $ perf record usleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.018 MB perf.data (8 samples) ] $ $ perf script -F brstackinsn Display of branch stack assembler requested, but non all-branch filter set Hint: run 'perf record -b ...' $ Signed-off-by: -
Arnaldo Carvalho de Melo authored
We use those in tools/arch/x86/lib/mem{cpy,set}_64.S, in turn used in the 'perf bench mem' benchmarks. The changes in the following csets are not relevant for this usecase, but lets sync it to silence the diff detector in the tools build system: 78d1b296 ("x86/cpu: Add X86_FEATURE_CPUID") 3bba73b1 ("x86/cpufeature: Move RING3MWAIT feature to avoid conflicts") Cc: Borislav Petkov <bp@suse.de> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/n/tip-nsqxpyzcv4ywesikhhhrgfgc@git.kernel.orgSigned-off-by: -
Alexander Shishkin authored
Since commit: 1c5ac21a ("perf/x86/intel/pt: Don't die on VMXON") ... PT events depend on re-scheduling to get enabled after a VMX session has taken place. This is, in particular, a problem for CPU context events, which don't normally get re-scheduled, unless there is a reason. This patch changes the VMX handling so that PT event gets re-enabled when VMX root mode exits. Also, notify the user when there's a gap in PT data due to VMX root mode by flagging AUX records as partial. In combination with vmm_exclusive=0 parameter of the kvm_intel driver, this will result in trace gaps only for the duration of the guest's timeslices. Signed-off-by:
Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vince Weaver <vincent.weaver@maine.edu> Cc: vince@deater.net Link: http://lkml.kernel.org/r/20170220133352.17995-5-alexander.shishkin@linux.intel.comSigned-off-by:
-
Alexander Shishkin authored
The Intel PT driver needs to be able to communicate partial AUX transactions, that is, transactions with gaps in data for reasons other than no room left in the buffer (i.e. truncated transactions). Therefore, this condition does not imply a wakeup for the consumer. To this end, add a new "partial" AUX flag. Signed-off-by:
-
Will Deacon authored
In preparation for adding more flags to perf AUX records, introduce a separate API for setting the flags for a session, rather than appending more bool arguments to perf_aux_output_end. This allows to set each flag at the time a corresponding condition is detected, instead of tracking it in each driver's private state. Signed-off-by:
Will Deacon <will.deacon@arm.com> Signed-off-by:
-
Kan Liang authored
Goldmont supports full Top Down level 1 metrics (FrontendBound, Retiring, Backend Bound and Bad Speculation). It has 3 wide pipeline. Signed-off-by:
Kan Liang <kan.liang@intel.com> Signed-off-by:
-
Ingo Molnar authored
Signed-off-by:
-
- 15 Mar, 2017 8 commits
-
-
git://git.kernel.dk/linux-blockLinus Torvalds authored
Pull block fixes from Jens Axboe: "Four small fixes for this cycle: - followup fix from Neil for a fix that went in before -rc2, ensuring that we always see the full per-task bio_list. - fix for blk-mq-sched from me that ensures that we retain similar direct-to-issue behavior on running the queue. - fix from Sagi fixing a potential NULL pointer dereference in blk-mq on spurious CPU unplug. - a memory leak fix in writeback from Tahsin, fixing a case where device removal of a mounted device can leak a struct wb_writeback_work" * 'for-linus' of git://git.kernel.dk/linux-block: blk-mq-sched: don't run the queue async from blk_mq_try_issue_directly() writeback: fix memory leak in wb_queue_work() blk-mq: Fix tagset reinit in the presence of cpu hot-unplug blk: Ensure users for current->bio_list can see the full list. -
Stephane Eranian authored
This patch significantly improves the execution time of perf_event__synthesize_mmap_events() when running perf record on systems where processes have lots of threads. It just happens that cat /proc/pid/maps support uses a O(N^2) algorithm to generate each map line in the maps file. If you have 1000 threads, then you have necessarily 1000 stacks. For each vma, you need to check if it corresponds to a thread's stack. With a large number of threads, this can take a very long time. I have seen latencies >> 10mn. As of today, perf does not use the fact that a mapping is a stack, therefore we can work around the issue by using /proc/pid/tasks/pid/maps. This entry does not try to map a vma to stack and is thus much faster with no loss of functonality. The proc-map-timeout logic is kept in case users still want some upper limit. In V2, we fix the file path from /proc/pid/tasks/pid/maps to actual /proc/pid/task/pid/maps, tasks -> task. Thanks Arnaldo for catching this. Committer note: This problem seems to have been elliminated in the kernel since commit : b18cb64e ("fs/proc: Stop trying to report thread stacks"). Signed-off-by:
Stephane Eranian <eranian@google.com> Acked-by:
Jiri Olsa <jolsa@redhat.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20170315135059.GC2177@redhat.com Link: http://lkml.kernel.org/r/1489598233-25586-1-git-send-email-eranian@google.comSigned-off-by:
-
Naveen N. Rao authored
perf specifies an offset from _text and since this offset is fed directly into the arch-specific helper, kprobes tracer rejects installation of kretprobes through perf. Fix this by looking up the actual offset from a function for the specified sym+offset. Refactor and reuse existing routines to limit code duplication -- we repurpose kprobe_addr() for determining final kprobe address and we split out the function entry offset determination into a separate generic helper. Before patch: naveen@ubuntu:~/linux/tools/perf$ sudo ./perf probe -v do_open%return probe-definition(0): do_open%return symbol:do_open file:(null) line:0 offset:0 return:1 lazy:(null) 0 arguments Looking at the vmlinux_path (8 entries long) Using /boot/vmlinux for symbols Open Debuginfo file: /boot/vmlinux Try to find probe point from debuginfo. Matched function: do_open [2d0c7ff] Probe point found: do_open+0 Matched function: do_open [35d76dc] found inline addr: 0xc0000000004ba9c4 Failed to find "do_open%return", because do_open is an inlined function and has no return point. An error occurred in debuginfo analysis (-22). Trying to use symbols. Opening /sys/kernel/debug/tracing//README write=0 Opening /sys/kernel/debug/tracing//kprobe_events write=1 Writing event: r:probe/do_open _text+4469776 Failed to write event: Invalid argument Error: Failed to add events. Reason: Invalid argument (Code: -22) naveen@ubuntu:~/linux/tools/perf$ dmesg | tail <snip> [ 33.568656] Given offset is not valid for return probe. After patch: naveen@ubuntu:~/linux/tools/perf$ sudo ./perf probe -v do_open%return probe-definition(0): do_open%return symbol:do_open file:(null) line:0 offset:0 return:1 lazy:(null) 0 arguments Looking at the vmlinux_path (8 entries long) Using /boot/vmlinux for symbols Open Debuginfo file: /boot/vmlinux Try to find probe point from debuginfo. Matched function: do_open [2d0c7d6] Probe point found: do_open+0 Matched function: do_open [35d76b3] found inline addr: 0xc0000000004ba9e4 Failed to find "do_open%return", because do_open is an inlined function and has no return point. An error occurred in debuginfo analysis (-22). Trying to use symbols. Opening /sys/kernel/debug/tracing//README write=0 Opening /sys/kernel/debug/tracing//kprobe_events write=1 Writing event: r:probe/do_open _text+4469808 Writing event: r:probe/do_open_1 _text+4956344 Added new events: probe:do_open (on do_open%return) probe:do_open_1 (on do_open%return) You can now use it in all perf tools, such as: perf record -e probe:do_open_1 -aR sleep 1 naveen@ubuntu:~/linux/tools/perf$ sudo cat /sys/kernel/debug/kprobes/list c000000000041370 k kretprobe_trampoline+0x0 [OPTIMIZED] c0000000004ba0b8 r do_open+0x8 [DISABLED] c000000000443430 r do_open+0x0 [DISABLED] Signed-off-by:Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> Acked-by:
-
Ravi Bangoria authored
Factor out the SDT event name checking routine as is_sdt_event(). Signed-off-by:
-
Ingo Molnar authored
Merge tag 'perf-core-for-mingo-4.12-20170314' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo: New features: - Add PERF_RECORD_NAMESPACES so that the kernel can record information required to associate samples to namespaces, helping in container problem characterization. Now the 'perf record has a --namespace' option to ask for such info, and when present, it can be used, initially, via a new sort order, 'cgroup_id', allowing histogram entry bucketization by a (device, inode) based cgroup identifier (Hari Bathini) - Add --next option to 'perf sched timehist', showing what is the next thread to run (Brendan Gregg) Fixes: - Fix segfault with basic block 'cycles' sort dimension (Changbin Du) - Add c2c to command-list.txt, making it appear in the 'perf help' output (Changbin Du) - Fix zeroing of 'abs_path' variable in the perf hists browser switch file code (Changbin Du) - Hide tips messages when -q/--quiet is given to 'perf report' (Namhyung Kim) Infrastructure changes: - Use ref_reloc_sym + offset to setup kretprobes (Naveen Rao) - Ignore generated files pmu-events/{jevents,pmu-events.c} for git (Changbin Du) Documentation changes: - Document +field style argument support for --field option (Changbin Du) - Clarify 'perf c2c --stats' help message (Namhyung Kim) Signed-off-by:
-
git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsiLinus Torvalds authored
Pull SCSI fixes from James Bottomley: "This is a rather large set of fixes. The bulk are for lpfc correcting a lot of issues in the new NVME driver code which just went in in the merge window. The others are: - fix a hang in the vmware paravirt driver caused by incorrect handling of the new MSI vector allocation - long standing bug in storvsc, which recent block changes turned from being a harmless annoyance into a hang - yet more fallout (in mpt3sas) from the changes to device blocking The remainder are small fixes and updates" * tag 'scsi-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi: (34 commits) scsi: lpfc: Add shutdown method for kexec scsi: storvsc: Workaround for virtual DVD SCSI version scsi: lpfc: revise version number to 11.2.0.10 scsi: lpfc: code cleanups in NVME initiator discovery scsi: lpfc: code cleanups in NVME initiator base scsi: lpfc: correct rdp diag portnames scsi: lpfc: remove dead sli3 nvme code scsi: lpfc: correct double print scsi: lpfc: Rename LPFC_MAX_EQ_DELAY to LPFC_MAX_EQ_DELAY_EQID_CNT scsi: lpfc: Rework lpfc Kconfig for NVME options scsi: lpfc: add transport eh_timed_out reference scsi: lpfc: Fix eh_deadline setting for sli3 adapters. scsi: lpfc: add NVME exchange aborts scsi: lpfc: Fix nvme allocation bug on failed nvme_fc_register_localport scsi: lpfc: Fix IO submission if WQ is full scsi: lpfc: Fix NVME CMD IU byte swapped word 1 problem scsi: lpfc: Fix RCTL value on NVME LS request and response scsi: lpfc: Fix crash during Hardware error recovery on SLI3 adapters scsi: lpfc: fix missing spin_unlock on sql_list_lock scsi: lpfc: don't dereference dma_buf->iocbq before null check ... -
git://git.kernel.org/pub/scm/linux/kernel/git/gfs2/linux-gfs2Linus Torvalds authored
Pull gfs2 fix from Bob Peterson: "This is an emergency patch for 4.11-rc3 The GFS2 developers uncovered a really nasty problem that can lead to random corruption and kernel panic, much like the last one. Andreas Gruenbacher wrote a simple one-line patch to fix the problem." * tag 'gfs2-4.11-rc3.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/gfs2/linux-gfs2: gfs2: Avoid alignment hole in struct lm_lockname
-
git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6Linus Torvalds authored
Pull crypto fixes from Herbert Xu: - self-test failure of crc32c on powerpc - regressions of ecb(aes) when used with xts/lrw in s5p-sss - a number of bugs in the omap RNG driver * 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: crypto: s5p-sss - Fix spinlock recursion on LRW(AES) hwrng: omap - Do not access INTMASK_REG on EIP76 hwrng: omap - use devm_clk_get() instead of of_clk_get() hwrng: omap - write registers after enabling the clock crypto: s5p-sss - Fix completing crypto request in IRQ handler crypto: powerpc - Fix initialisation of crc32c context
-
