- 26 Jan, 2016 16 commits
-
-
Taeung Song authored
Explain 'hist.percentage' variable. Signed-off-by:
Taeung Song <treeze.taeung@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: http://lkml.kernel.org/r/1452253193-30502-7-git-send-email-treeze.taeung@gmail.comSigned-off-by:
Arnaldo Carvalho de Melo <acme@redhat.com>
-
Taeung Song authored
Explain 'annotate' section and its variables. 'hide_src_code', 'use_offset', 'jump_arrows', 'show_linenr', 'show_nr_jump' and 'show_total_period'. Signed-off-by:
-
Taeung Song authored
Explain 'buildid.dir' variable. Signed-off-by:
-
Taeung Song authored
Explain 'tui' and 'gtk' sections and these variables. 'top', 'report' and 'annotate' Signed-off-by:
-
Taeung Song authored
Explain 'colors' section and its variables, used for The variables for customizing the colors used in the output for the 'report', 'top' and 'annotate' in the TUI, those are: 'top', 'medium', 'normal', 'selected', 'jump_arrows', 'addr' and 'root'. Signed-off-by:
-
Taeung Song authored
USe 'jump_arrows' config name instead of 'code' on 'colors' section. 'colors.code' config is only for jump arrows on assembly code listings i.e. │ ┌──jmp 1333 │ │ xchg %ax,%ax │ │ mov %r15,%r10 │ └─→cmp %r15,%r14 But this config name seems unfit. 'jump_arrows' is more descriptive than 'code'. Signed-off-by: -
Ben Hutchings authored
perf_event_paranoid was only documented in source code and a perf error message. Copy the documentation from the error message to Documentation/sysctl/kernel.txt. perf_cpu_time_max_percent was already documented but missing from the list at the top, so add it there. Signed-off-by:
Ben Hutchings <ben@decadent.org.uk> Cc: Peter Zijlstra <peterz@infradead.org> Cc: linux-doc@vger.kernel.org Link: http://lkml.kernel.org/r/20160119213515.GG2637@decadent.org.uk [ Remove reference to external Documentation file, provide info inline, as before ] Signed-off-by:
-
Namhyung Kim authored
The hists__filter_by_xxx functions share same logic with different filters. Factor out the common code into the hists__filter_by_type. Signed-off-by:
Namhyung Kim <namhyung@kernel.org> Acked-by:
Jiri Olsa <jolsa@kernel.org> Acked-by:
Pekka Enberg <penberg@kernel.org> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1453252521-24398-2-git-send-email-namhyung@kernel.orgSigned-off-by:
-
Namhyung Kim authored
The --exclude-other option sets HIST_FILTER__PARENT bit and it's only set when a hist entry was created. DSO filters don't change this so no need to have the check in hists__filter_by_dso() IMHO. Signed-off-by:
-
Jiri Olsa authored
There's no need for the following functions to be global: perf_evsel__reset_stat_priv perf_evsel__alloc_stat_priv perf_evsel__free_stat_priv perf_evsel__alloc_prev_raw_counts perf_evsel__free_prev_raw_counts perf_evsel__alloc_stats They all ended up in util/stat.c, and they no longer need to be called from outside this object. Signed-off-by:
-
Jiri Olsa authored
With mem sampling we could get data source within mapped device file. Processing such sample would block during report phase on trying to read the device file. Chacking for device files and skip the processing if it's detected. Signed-off-by:
-
Markus Trippelsdorf authored
One line in perf_pmu__parse_unit() is indented wrongly, leading to a warning (=> error) from gcc 6: util/pmu.c:156:3: error: statement is indented as if it were guarded by... [-Werror=misleading-indentation] sret = read(fd, alias->unit, UNIT_MAX_LEN); ^~~~ util/pmu.c:153:2: note: ...this 'if' clause, but it is not if (fd == -1) ^~ Signed-off-by:Markus Trippelsdorf <markus@trippelsdorf.de> Acked-by:
Ingo Molnar <mingo@kernel.org> Cc: Ben Hutchings <ben@decadent.org.uk> Cc: Matt Fleming <matt@codeblueprint.co.uk> Cc: Peter Zijlstra <peterz@infradead.org> Fixes: 410136f5 ("tools/perf/stat: Add event unit and scale support") Link: http://lkml.kernel.org/r/20151214154440.GC1409@x4Signed-off-by:
-
Jiri Olsa authored
Mel reported stddev reporting was broken due to following commit: 106a94a0 ("perf stat: Introduce read_counters function") This commit merged interval and overall counters reading into single read_counters function. The old interval code cleaned the stddev data for some reason (it's never displayed in interval mode) and the mentioned commit kept on cleaning the stddev data in merged function, which resulted in the stddev not being displayed. Removing the wrong stddev data cleanup init_stats call. Reported-and-Tested-by:
Mel Gorman <mgorman@techsingularity.net> Signed-off-by:
-
Jiri Olsa authored
Set correct width for unresolved mem_dcacheline addr. Signed-off-by:
-
Markus Trippelsdorf authored
The issue was pointed out by gcc-6's -Wmisleading-indentation. Signed-off-by:
-
Markus Trippelsdorf authored
The while loop was spinning. Fix by removing a semicolon. The issue was pointed out by gcc-6's -Wmisleading-indentation. Signed-off-by:
Matt Fleming <matt@codeblueprint.co.uk> Acked-by:
-
- 21 Jan, 2016 16 commits
-
-
Alexander Shishkin authored
We are currently using asynchronous deallocation in the error path in AUX mmap code, which is unnecessary and also presents a problem for users that wish to probe for the biggest possible buffer size they can get: they'll get -EINVAL on all subsequent attemts to allocate a smaller buffer before the asynchronous deallocation callback frees up the pages from the previous unsuccessful attempt. Currently, gdb does that for allocating AUX buffers for Intel PT traces. More specifically, overwrite mode of AUX pmus that don't support hardware sg (some implementations of Intel PT, for instance) is limited to only one contiguous high order allocation for its buffer and there is no way of knowing its size without trying. This patch changes error path freeing to be synchronous as there won't be any contenders for the AUX pages at that point. Reported-by:
Markus Metzger <markus.t.metzger@intel.com> Signed-off-by:
Alexander Shishkin <alexander.shishkin@linux.intel.com> 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: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Namhyung Kim <namhyung@kernel.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/1453216469-9509-1-git-send-email-alexander.shishkin@linux.intel.comSigned-off-by:
-
Stephane Eranian authored
This patch enables the uncore_imc PMU for Intel SkyLake Desktop processors (Core i7-6700, model 94). It is possible to compute memory read/write bandwidth using: $ perf stat -a -e uncore_imc/data_reads/,uncore_imc/data_writes/ .... Signed-off-by:
Stephane Eranian <eranian@google.com> Signed-off-by:
-
Peter Zijlstra authored
There is a race against perf_event_exit_task() vs event_function_call(),find_get_context(),perf_install_in_context() (iow, everyone). Since there is no permanent marker on a context that its dead, it is quite possible that we access (and even modify) a context after its passed through perf_event_exit_task(). For instance, find_get_context() might find the context still installed, but by the time we get to perf_install_in_context() it might already have passed through perf_event_exit_task() and be considered dead, we will however still add the event to it. Solve this by marking a ctx dead by setting its ctx->task value to -1, it must be !0 so we still know its a (former) task context. Signed-off-by:
-
Peter Zijlstra authored
Try to trigger warnings before races do damage. Signed-off-by:
-
Peter Zijlstra authored
There is one common bug left in all the event_function_call() users, between loading ctx->task and getting to the remote_function(), ctx->task can already have been changed. Therefore we need to double check and retry if ctx->task != current. Insert another trampoline specific to event_function_call() that checks for this and further validates state. This also allows getting rid of the active/inactive functions. Signed-off-by:
-
Peter Zijlstra authored
The perf_remove_from_context() usage in __perf_event_exit_task() is different from the other usages in that this site has already detached and scheduled out the task context. This will stand in the way of stronger assertions checking the (task) context scheduling invariants. Signed-off-by:
-
Peter Zijlstra authored
There is a very nasty problem wrt disabling the perf task scheduling hooks. Currently we {set,clear} ctx->is_active on every __perf_event_task_sched_{in,out}, _however_ this means that if we disable these calls we'll have task contexts with ->is_active set that are not active and 'active' task contexts without ->is_active set. This can result in event_function_call() looping on the ctx->is_active condition basically indefinitely. Resolve this by changing things such that contexts without events do not set ->is_active like we used to. From this invariant it trivially follows that if there are no (task) events, every task ctx is inactive and disabling the context switch hooks is harmless. This leaves two places that need attention (and already had accumulated weird and wonderful hacks to work around, without recognising this actual problem). Namely: - perf_install_in_context() will need to deal with installing events in an inactive context, meaning it cannot rely on ctx-is_active for its IPIs. - perf_remove_from_context() will have to mark a context as inactive when it removes the last event. For specific detail, see the patch/comments. Signed-off-by: -
Peter Zijlstra authored
For no apparent reason and to great confusion the rules for ctx->is_active and cpuctx->task_ctx are different. This means that its not always possible to find all active (task) contexts. Fix this such that if ctx->is_active gets set, we also set (or verify) cpuctx->task_ctx. Signed-off-by:
-
Peter Zijlstra authored
It doesn't make sense to take up-to _4_ references on perf_sched_events() per event, avoid doing this. Signed-off-by:
-
Peter Zijlstra authored
Like perf_enable_on_exec(), perf_event_enable() event scheduling has problems respecting the context hierarchy when trying to schedule events (for example, it will try and add a pinned event without first removing existing flexible events). So simplify it by using the new ctx_resched() call which will DTRT. Signed-off-by:
-
Peter Zijlstra authored
We have a function that does exactly what we want here, use it. This reduces the amount of cpuctx->task_ctx muckery. Signed-off-by:
-
Peter Zijlstra authored
There are two problems with the current perf_enable_on_exec() event scheduling: - the newly enabled events will be immediately scheduled irrespective of their ctx event list order. - there's a hole in the ctx->lock between scheduling the events out and putting them back on. Esp. the latter issue is a real problem because a hole in event scheduling leaves the thing in an observable inconsistent state, confusing things. Fix both issues by first doing the enable iteration and at the end, when there are newly enabled events, reschedule the ctx in one go. Signed-off-by: -
Peter Zijlstra authored
The comment here is horribly out of date, remove it. Signed-off-by:
-
Peter Zijlstra authored
There is a comment that states that perf_event_context_sched_in() will also switch in the cgroup events, I cannot find it does so. Therefore all the resulting logic goes out the window too. Clean that up. Signed-off-by:
-
Peter Zijlstra authored
There appears to be a problem in __perf_event_task_sched_in() wrt cgroup event scheduling. The normal event scheduling order is: CPU pinned Task pinned CPU flexible Task flexible And since perf_cgroup_sched*() only schedules the cpu context, we must call this _before_ adding the task events. Note: double check what happens on the ctx switch optimization where the task ctx isn't scheduled. Signed-off-by:
-
Peter Zijlstra authored
Make various bugs easier to see. Signed-off-by:
-
- 19 Jan, 2016 1 commit
-
-
Ingo Molnar authored
Merge tag 'perf-core-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent Pull perf tools improvements and fixes from Arnaldo Carvalho de Melo: User visible bug fixes: - Fix reading of build-id from vDSO (Ben Hutchings) - Fix processing samples for guests, noticed with 'perf kvm', but noticeable as well via other tools, such as 'perf top' (Ravi Bangoria) Build infrastructure: - Add feature-dump target and FEATURES_DUMP make variable, to allow reusing the feature detection results among multiple tools/ living codebases, such as perf and lib/bpf (Jiri Olsa) - 'make -C tools/perf build-test' improvements, making it more paralelizable and allowing building it outside of the source tree, using O= (Wang Nan) Signed-off-by:
-
- 15 Jan, 2016 7 commits
-
-
Jiri Olsa authored
Introducing FEATURES_DUMP make variable to provide features detection dump file and bypass the feature detection. The intention is to use this during build tests to skip repeated features detection, like: Get feature dump static build into /tmp/fd file: $ make feature-dump FEATURE_DUMP_COPY=/tmp/fd LDFLAGS=-static BUILD: Doing 'make -j4' parallel build Auto-detecting system features: ... dwarf: [ OFF ] SNIP FEATURE-DUMP file copied into /tmp/fd Use /tmp/fd to build perf: $ make FEATURES_DUMP=/tmp/fd LDFLAGS=-static $ file perf perf: ELF 64-bit LSB executable, x86-64, version 1 (GNU/Linux), statically linked, for ... Suggested-by:Wang Nan <wangnan0@huawei.com> Signed-off-by:
-
Jiri Olsa authored
To provide FEATURE-DUMP into $(FEATURE_DUMP_COPY) if defined, with no further action. Get feature dump of the current build: $ make feature-dump BUILD: Doing 'make -j4' parallel build Auto-detecting system features: ... dwarf: [ on ] FEATURE-DUMP file available in FEATURE-DUMP Get feature dump static build into /tmp/fd file: $ make feature-dump FEATURE_DUMP_COPY=/tmp/fd LDFLAGS=-static BUILD: Doing 'make -j4' parallel build Auto-detecting system features: ... dwarf: [ OFF ] SNIP FEATURE-DUMP file copied into /tmp/fd Suggested-by: -
Wang Nan authored
Kernel makefile only follows an 'O' option passed from command line explicitely. In build-test with 'O' option set, kernel makefile contaminate kernel source directory. Build test also fail if we don't create output directory manually. K_O_OPT is added and passed to kernel makefile if 'O' is passed to build-test. Signed-off-by:
-
Wang Nan authored
If an 'O' is passed to 'make build-test', many 'test -x' and 'test -f' will fail because perf resides in a different directory. Fix this by computing PERF_OUT according to 'O' and test correct output files. For make_kernelsrc and make_kernelsrc_tools, set KBUILD_OUTPUT_DIR instead because the path is different from others ($(O)/perf vs $(O)/tools/perf). Signed-off-by:
-
Wang Nan authored
Unlike tools/perf/Makefile, tools/perf/Makefile.perf obey 'O' option when it is passed through cmdline only, due to code in tools/scripts/Makefile.include: ifneq ($(O),) ifeq ($(origin O), command line) ... ABSOLUTE_O := $(shell cd $(O) ; pwd) OUTPUT := $(ABSOLUTE_O)/$(if $(subdir),$(subdir)/) endif endif This patch passes 'O' to Makefile.perf through cmdline explicitly to make it follow O variable during build-test. 'make clean' should have identical 'O' option with 'make'. If not, config-clean may error. Signed-off-by:
-
Wang Nan authored
'make build-test' is painful because of time consuming. In a full test, all test cases are built twice with tools/perf/Makefile and tools/perf/Makefile.perf. 'Makefile' automatically computes parallel options for make, but 'Makefile.perf' not, so all test cases is built with one job. It is very slow. This patch adds '-j' options to Makefile.perf testing. It computes parallel building options like what tools/perf/Makefile does, and pass '-j' option to Makefile.perf test. Signed-off-by:
-
Ben Hutchings authored
We need to use the long name (the filename) when reading the build-id from a DSO. Using the short name doesn't work for (at least) vDSOs. Signed-off-by:
-
