- 21 Mar, 2013 2 commits
-
-
Ingo Molnar authored
Merge tag 'perf-core-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core Conflicts: tools/Makefile Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo: . Honor parallel jobs, fix from Borislav Petkov . Introduce tools/lib/lk library, initially just removing duplication among tools/perf and tools/vm. from Borislav Petkov . Fix build on non-glibc systems due to libio.h absence, from Cody P Schafer. . Remove some perf_session and tracing dead code, from David Ahern. . Introduce perf stat --repeat forever, from Frederik Deweerdt. . Add perf test entries for checking --cpu in record and stat, from Jiri Olsa. . Add perf test entries for checking breakpoint overflow signal handler issues, from Jiri Olsa. . Add perf test entry for for checking number of EXIT events, from Namhyung Kim. . Simplify some perf_evlist methods and to allow 'stat' to share code with 'record' and 'trace'. . Remove dead code in related to libtraceevent integration, from Namhyung Kim. . Event group view for 'annotate' in --stdio, --tui and --gtk, from Namhyung Kim. Signed-off-by:
Arnaldo Carvalho de Melo <acme@redhat.com> [ resolved the trivial merge conflict with upstream ] Signed-off-by:
Ingo Molnar <mingo@kernel.org>
-
Ingo Molnar authored
Merge in all pending fixes, before pulling the latest development bits from Arnaldo - which will involve merge conflicts. Signed-off-by:
-
- 18 Mar, 2013 10 commits
-
-
Namhyung Kim authored
This test case checks frequency conversion of hrtimer-based software clock events (cpu-clock, task-clock) have valid (non-1) periods. Signed-off-by:
Namhyung Kim <namhyung@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1363574507-18808-2-git-send-email-namhyung@kernel.org [ committer note: Moved .sample_freq to outside named init block to cope with some gcc versions ] Signed-off-by:
-
Arnaldo Carvalho de Melo authored
Reducing the noise in the main logic. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-o219lnci04hlilxi6711wtcr@git.kernel.orgSigned-off-by:
-
Namhyung Kim authored
It's a per-cpu data structure but missed the __percpu annotation. Signed-off-by:
-
Stephane Eranian authored
Add scheduling constraints for SNB/SNB-EP CYCLE_ACTIVITY event as defined by SDM Jan 2013 edition. The STALLS umasks are combinations with the NO_DISPATCH umask. Signed-off-by:
Stephane Eranian <eranian@gmail.com> Cc: peterz@infradead.org Cc: ak@linux.intel.com Cc: jolsa@redhat.com Link: http://lkml.kernel.org/r/20130317134957.GA8550@quadSigned-off-by:
-
Masami Hiramatsu authored
Currently kprobes check whether the copied instruction modifies IF (interrupt flag) on each probe hit. This results not only in introducing overhead but also involving inat_get_opcode_attribute into the kprobes hot path, and it can cause an infinite recursive call (and kernel panic in the end). Actually, since the copied instruction itself can never be modified on the buffer, it is needless to analyze the instruction on every probe hit. To fix this issue, we check it only once when registering probe and store the result on ainsn->if_modifier. Reported-by:
Timo Juhani Lindfors <timo.lindfors@iki.fi> Signed-off-by:
Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Acked-by:
Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: yrl.pp-manager.tt@hitachi.com Cc: Steven Rostedt <rostedt@goodmis.org> Cc: David S. Miller <davem@davemloft.net> Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20130314115242.19690.33573.stgit@mhiramat-M0-7522Signed-off-by:
-
Masami Hiramatsu authored
Because hash_64() is called from the get_kprobe() inside int3 handler, kernel causes int3 recursion and crashes if kprobes user puts a probe on it. Usually hash_64() is inlined into caller function, but in some cases, it has instances by gcc's interprocedural constant propagation. This patch uses __always_inline instead of inline to prevent gcc from doing such things. Reported-by:
-
Ingo Molnar authored
Merge tag 'perf-urgent-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent Pull perf/urgent fixes from Arnaldo Carvalho de Melo: . perf probe: Fix segfault due to testing the wrong pointer for NULL, from Ananth N Mavinakayanahalli. . libtraceevent: Remove hard coded include to /usr/local/include in Makefile, which causes cross builds to include host header files, fix from Jack Mitchell. . perf record: Use the right target interface for synthesizing threads when --cpu/-C option is used, fix from Jiri Olsa. . Check if -DFORTIFY_SOURCE=2 is allowed, as gcc 4.7.2 defines it and then the build is broken when it is redefined in perf, fix from Marcin Slusarz. . Fix build with NO_NEWT=1, that can happen explicitely or when the newt-devel package is not installed, from Michael Ellerman. . perf/POWER7: Create a sysfs format entry for Power7 events, missing patch from a patchseries already merged, from Sukadev Bhattiprolu. . Fix LIBNUMA build with glibc 2.12 and older, from Vinson Lee. Signed-off-by:
-
Ingo Molnar authored
Merge branch 'tip/perf/urgent-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace into perf/urgent Pull tracing fixes from Steven Rostedt. Signed-off-by:
-
Namhyung Kim authored
perf_event_task_event() iterates pmu list and generate events for each eligible pmu context. But if task_event has task_ctx like in EXIT it'll generate events even though the pmu doesn't have an eligible one. Fix it by moving the code to proper places. Before this patch: $ perf record -n true [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.006 MB perf.data (~248 samples) ] $ perf report -D | tail Aggregated stats: TOTAL events: 73 MMAP events: 67 COMM events: 2 EXIT events: 4 cycles stats: TOTAL events: 73 MMAP events: 67 COMM events: 2 EXIT events: 4 After this patch: $ perf report -D | tail Aggregated stats: TOTAL events: 70 MMAP events: 67 COMM events: 2 EXIT events: 1 cycles stats: TOTAL events: 70 MMAP events: 67 COMM events: 2 EXIT events: 1 Signed-off-by: -
Namhyung Kim authored
When cpu/task clock events are initialized, their sampling frequencies are converted to have a fixed value. However it missed to update the hwc->last_period which was set to 1 for initial sampling frequency calibration. Because this hwc->last_period value is used as a period in perf_swevent_ hrtime(), every recorded sample will have an incorrected period of 1. $ perf record -e task-clock noploop 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.158 MB perf.data (~6919 samples) ] $ perf report -n --show-total-period --stdio # Samples: 4K of event 'task-clock' # Event count (approx.): 4000 # # Overhead Samples Period Command Shared Object Symbol # ........ ............ ............ ....... ............. .................. # 99.95% 3998 3998 noploop noploop [.] main 0.03% 1 1 noploop libc-2.15.so [.] init_cacheinfo 0.03% 1 1 noploop ld-2.15.so [.] open_verify Note that it doesn't affect the non-sampling event so that the perf stat still gets correct value with or without this patch. $ perf stat -e task-clock noploop 1 Performance counter stats for 'noploop 1': 1000.272525 task-clock # 1.000 CPUs utilized 1.000560605 seconds time elapsed Signed-off-by:
-
- 15 Mar, 2013 28 commits
-
-
Frederik Deweerdt authored
The following patch causes 'perf stat --repeat 0' to be interpreted as 'forever', displaying the stats for every run. We act as if a single run was asked, and reset the stats in each iteration. In this mode SIGINT is passed to perf to be able to stop the loop with Ctrl+C. Signed-off-by:
Frederik Deweerdt <frederik.deweerdt@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20130301180227.GA24385@ks398093.ip-192-95-24.netSigned-off-by:
-
Namhyung Kim authored
The new test__task_exit() test runs a simple "/usr/bin/true" workload and then checks whether the number of EXIT event is 1 or not. Signed-off-by:
-
Namhyung Kim authored
Add missing perf_evlist__close() function. Signed-off-by:
-
Namhyung Kim authored
Add missing evlist cleanup functions. Signed-off-by:
-
Namhyung Kim authored
The error path of calling perf_target__parse_uid wrongly went to out_free_fd. Also add missing evlist cleanup routines. Signed-off-by:
-
Namhyung Kim authored
The trace_run() function calls several evlist functions but misses some pair-wise cleanup routines on return path. Fix it. Signed-off-by:
-
Namhyung Kim authored
It's a pair of perf_evlist__open(). Signed-off-by:
-
Namhyung Kim authored
Use perf_evsel__free_* because they do the same thing and ensures the pointer has NULL value at the end. Signed-off-by:
-
Jiri Olsa authored
Adding automated test to check the exact number of breakpoint event overflows and counts. This test was originally done by Vince Weaver for perf_event_tests. Signed-off-by:
Jiri Olsa <jolsa@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vince Weaver <vincent.weaver@maine.edu> Link: http://lkml.kernel.org/r/1362940871-24486-7-git-send-email-jolsa@redhat.com [ committer note: s/pr_err/pr_debug/g i.e. print just OK or FAILED in non verbose mode ] Signed-off-by:
-
Jiri Olsa authored
Adding automated test for breakpoint event signal handler checking if it's executed properly. The test is related to the proper handling of the RF EFLAGS bit on x86_64, but it's generic for all archs. First we check the signal handler is properly called and that the following debug exception return to user space wouldn't trigger recursive breakpoint. This is related to x86_64 RF EFLAGS bit being managed in a wrong way. Second we check that we can set breakpoint in signal handler, which is not possible on x86_64 if the signal handler is executed with RF EFLAG set. This test is inpired by overflow tests done by Vince Weaver. Signed-off-by:
-
Namhyung Kim authored
It's defined in util/util.c and gets set from the begining of perf run. No need to duplicate it. Signed-off-by:
-
Namhyung Kim authored
They're never used and looks like leftovers from the porting of trace-cmd code. Signed-off-by:
-
Namhyung Kim authored
It's not set from anywhere so no need to keep it. Looks like an unneeded copy of the same variable in trace-event-read.c Signed-off-by:
-
Namhyung Kim authored
struct event_list and struct events are never used. Just get rid of them. Signed-off-by:
-
Namhyung Kim authored
And functions that called only from the trace_read_data(). Signed-off-by:
-
Wei Yongjun authored
Signed-off-by:
Wei Yongjun <yongjun_wei@trendmicro.com.cn> Cc: Ingo Molnar <mingo@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/CAPgLHd9=EXaH1hv4jeVvTa4tZFsjnx+8+g3zqmmUKqQ5qRqTEA@mail.gmail.comSigned-off-by:
-
David Ahern authored
As the now only user, machine__process_exit_event, that is what tools use to process PERF_RECORD_EXIT events, is on the same object file. Signed-off-by:
David Ahern <dsahern@gmail.com> Link: http://lkml.kernel.org/r/1363151248-16674-5-git-send-email-dsahern@gmail.comSigned-off-by:
-
David Ahern authored
Should have been removed on this changeset, that removed the last user of it: 743eb868 perf tools: Resolve machine earlier and pass it to perf_event_ops Signed-off-by:
-
David Ahern authored
Leftovers from before libtraceevent integration. Signed-off-by:
-
Namhyung Kim authored
Checking of sample.raw_data is duplicated and seems an artifact of some git auto merging stuff. Kill it. Signed-off-by:
-
Namhyung Kim authored
Dynamically allocate browser_disasm_line according to a number of group members. This way we can handle multiple events in a general manner. Signed-off-by:
-
Namhyung Kim authored
Add support for event group view to GTK annotation browser. Signed-off-by:
-
Namhyung Kim authored
The disasm_line__calc_percent() which was used by annotate browser code almost duplicates disasm__calc_percent. Let's get rid of the code duplication. Signed-off-by:
-
Namhyung Kim authored
Make percent field of struct browser_disasm_line an array and move it to the last. This is a preparation of event group view feature. Signed-off-by:
-
Namhyung Kim authored
Dynamically allocate source_line_percent according to a number of group members and save nr_pcnt to the struct source_line. This way we can handle multiple events in a general manner. However since the size of struct source_line is not fixed anymore, iterating whole source_line should care about its size. $ perf annotate --group --stdio --print-line Sorted summary for file /lib/ld-2.11.1.so ---------------------------------------------- 33.33 0.00 /build/buildd/eglibc-2.11.1/elf/rtld.c:381 33.33 0.00 /build/buildd/eglibc-2.11.1/elf/dynamic-link.h:128 33.33 0.00 /build/buildd/eglibc-2.11.1/elf/do-rel.h:105 0.00 75.00 /build/buildd/eglibc-2.11.1/elf/dynamic-link.h:137 0.00 25.00 /build/buildd/eglibc-2.11.1/elf/dynamic-link.h:187 ... Signed-off-by: -
Namhyung Kim authored
The source_line_percent struct contains percentage value of the symbol histogram. This is a preparation of event group view change. Signed-off-by:
-
Namhyung Kim authored
The perf_evsel__is_group_event function is for checking whether given evsel needs event group view support or not. Please note that it's different to the existing perf_evsel__is_group_leader() which checks only the given evsel is a leader or a standalone (i.e. non-group) event regardless of event group feature. Signed-off-by:
-
Namhyung Kim authored
Add --group option to enable event grouping. When enabled, all the group members information will be shown with the leader so skip non-leader events. It only supports --stdio output currently. Later patches will extend additional features. $ perf annotate --group --stdio ... Percent | Source code & Disassembly of libpthread-2.15.so -------------------------------------------------------------------------------- : : : : Disassembly of section .text: : : 000000387dc0aa50 <__pthread_mutex_unlock_usercnt>: 8.08 2.40 5.29 : 387dc0aa50: mov %rdi,%rdx 0.00 0.00 0.00 : 387dc0aa53: mov 0x10(%rdi),%edi 0.00 0.00 0.00 : 387dc0aa56: mov %edi,%eax 0.00 0.80 0.00 : 387dc0aa58: and $0x7f,%eax 3.03 2.40 3.53 : 387dc0aa5b: test $0x7c,%dil 0.00 0.00 0.00 : 387dc0aa5f: jne 387dc0aaa9 <__pthread_mutex_unlock_use 0.00 0.00 0.00 : 387dc0aa61: test %eax,%eax 0.00 0.00 0.00 : 387dc0aa63: jne 387dc0aa85 <__pthread_mutex_unlock_use 0.00 0.00 0.00 : 387dc0aa65: and $0x80,%edi 0.00 0.00 0.00 : 387dc0aa6b: test %esi,%esi 3.03 5.60 7.06 : 387dc0aa6d: movl $0x0,0x8(%rdx) 0.00 0.00 0.59 : 387dc0aa74: je 387dc0aa7a <__pthread_mutex_unlock_use 0.00 0.00 0.00 : 387dc0aa76: subl $0x1,0xc(%rdx) 2.02 5.60 1.18 : 387dc0aa7a: mov %edi,%esi 0.00 0.00 0.00 : 387dc0aa7c: lock decl (%rdx) 83.84 83.20 82.35 : 387dc0aa7f: jne 387dc0aada <_L_unlock_586> 0.00 0.00 0.00 : 387dc0aa81: nop 0.00 0.00 0.00 : 387dc0aa82: xor %eax,%eax 0.00 0.00 0.00 : 387dc0aa84: retq ... Signed-off-by:
-
