- 09 Dec, 2015 7 commits
-
-
Masami Hiramatsu authored
Fix write_numa_topology to put cpu_map instead of free because cpu_map is managed based on refcnt. Signed-off-by:
Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20151209021135.10245.79046.stgit@localhost.localdomainSigned-off-by:
Arnaldo Carvalho de Melo <acme@redhat.com>
-
Masami Hiramatsu authored
Fix machine.vmlinux_maps to make sure to clear the old one if it is renewal. This can leak the previous maps on the vmlinux_maps because those are just overwritten. Signed-off-by:
-
Masami Hiramatsu authored
Since the __map_groups__insert got the given map, we don't need to keep it. So put the maps. Refcnt debugger shows that map_groups__fixup_overlappings() got a map twice but the group released it just once. This pattern usually indicates the leak happens in caller site. ---- ==== [0] ==== Unreclaimed map@0x39d3ae0 Refcount +1 => 1 at ./perf(map_groups__fixup_overlappings+0x335) [0x4c1865] ./perf(thread__insert_map+0x30) [0x4c8e00] ./perf(machine__process_mmap2_event+0x106) [0x4bd876] ./perf() [0x4c378e] ./perf() [0x4c4393] ./perf(perf_session__process_events+0x38a) [0x4c654a] ./perf(cmd_record+0xe24) [0x42fc94] ./perf() [0x47b745] ./perf(main+0x617) [0x422547] /lib64/libc.so.6(__libc_start_main+0xf5) [0x7f2eca2deaf5] ./perf() [0x4226bd] Refcount +1 => 2 at ./perf(map_groups__fixup_overlappings+0x3c5) [0x4c18f5] ./perf(thread__insert_map+0x30) [0x4c8e00] ./perf(machine__process_mmap2_event+0x106) [0x4bd876] ./perf() [0x4c378e] ./perf() [0x4c4393] ./perf(perf_session__process_events+0x38a) [0x4c654a] ./perf(cmd_record+0xe24) [0x42fc94] ./perf() [0x47b745] ./perf(main+0x617) [0x422547] /lib64/libc.so.6(__libc_start_main+0xf5) [0x7f2eca2deaf5] ./perf() [0x4226bd] Refcount -1 => 1 at ./perf(map_groups__exit+0x92) [0x4c0962] ./perf(map_groups__put+0x60) [0x4c0bc0] ./perf(thread__put+0x90) [0x4c8a40] ./perf(machine__delete_threads+0x7e) [0x4bad9e] ./perf(perf_session__delete+0x4f) [0x4c499f] ./perf(cmd_record+0xb6d) [0x42f9dd] ./perf() [0x47b745] ./perf(main+0x617) [0x422547] /lib64/libc.so.6(__libc_start_main+0xf5) [0x7f2eca2deaf5] ./perf() [0x4226bd] ---- Signed-off-by: -
Masami Hiramatsu authored
Since hists__init doesn't set the destructor of hists_evsel (which is an extended evsel structure), when hists_evsel is released, the extended part of the hists_evsel is not deleted (note that the hists_evsel object itself is freed). This fixes it to add a destructor for hists__evsel and to set it up. Signed-off-by:
-
Masami Hiramatsu authored
Fix cmd_stat() to release cpu_map objects (aggr_map and cpus_aggr_map) afterwards. refcnt debugger shows that the cmd_stat initializes cpu_map but not puts it. ---- # ./perf stat -v ls .... REFCNT: BUG: Unreclaimed objects found. ==== [0] ==== Unreclaimed cpu_map@0x29339c0 Refcount +1 => 1 at ./perf(cpu_map__empty_new+0x6d) [0x4e64bd] ./perf(cmd_stat+0x5fe) [0x43594e] ./perf() [0x47b785] ./perf(main+0x617) [0x422587] /lib64/libc.so.6(__libc_start_main+0xf5) [0x7f2dff420af5] ./perf() [0x4226fd] REFCNT: Total 1 objects are not reclaimed. "cpu_map" leaks 1 objects ---- Signed-off-by: -
Masami Hiramatsu authored
Fix map_groups__clone to put cloned map after inserting it to the map_groups. Refcnt debugger shows: ---- ==== [0] ==== Unreclaimed map: 0x2a27ee0 Refcount +1 => 1 at ./perf(map_groups__clone+0x8d) [0x4bb7ed] ./perf(thread__fork+0xbe) [0x4c1f9e] ./perf(machine__process_fork_event+0x216) [0x4b79a6] ./perf(perf_event__synthesize_threads+0x38b) [0x48135b] ./perf(cmd_top+0xdc6) [0x43cb76] ./perf() [0x477223] ./perf(main+0x617) [0x422077] /lib64/libc.so.6(__libc_start_main+0xf0) [0x7ff806af8fe0] ./perf() [0x4221ed] Refcount +1 => 2 at ./perf(map_groups__clone+0x128) [0x4bb888] ./perf(thread__fork+0xbe) [0x4c1f9e] ./perf(machine__process_fork_event+0x216) [0x4b79a6] ./perf(perf_event__synthesize_threads+0x38b) [0x48135b] ./perf(cmd_top+0xdc6) [0x43cb76] ./perf() [0x477223] ./perf(main+0x617) [0x422077] /lib64/libc.so.6(__libc_start_main+0xf0) [0x7ff806af8fe0] ./perf() [0x4221ed] Refcount -1 => 1 at ./perf(map_groups__exit+0x87) [0x4ba757] ./perf(map_groups__put+0x68) [0x4ba9a8] ./perf(thread__put+0x8b) [0x4c1aeb] ./perf(machine__delete_threads+0x81) [0x4b48f1] ./perf(perf_session__delete+0x4f) [0x4be63f] ./perf(cmd_top+0x1094) [0x43ce44] ./perf() [0x477223] ./perf(main+0x617) [0x422077] /lib64/libc.so.6(__libc_start_main+0xf0) [0x7ff806af8fe0] ./perf() [0x4221ed] ---- This shows map_groups__clone get the map twice and put it when map_groups__exit. Signed-off-by: -
Ingo Molnar authored
Boris reported that 'perf top' is unusable on his default 'black on white' terminal, which uses (eye friendly) light-grey as a background color. The reason is that the TUI cursor for the current selection line uses HE_COLORSET_SELECTED, and that has a default background color of 'lightgrey' - which is a common terminal background choice and thus the colors conflict. Use yellow as the background color instead: that should be an uncommon terminal background, yet it's still ergonomic on both black and white/grey terminals. [ It would be a better solution to straight out detect color collisions and resolve them reasonably by converting them to RGB and calculating color space distances, but I was unable to find proper documentation for SLtt_get_color_object() to recover the current color scheme so I gave up ... Yellow works well enough. ] Reported-and-Tested-by:
Borislav Petkov <bp@alien8.de> Signed-off-by:
Ingo Molnar <mingo@kernel.org> Tested-by:
-
- 08 Dec, 2015 3 commits
-
-
Ingo Molnar authored
Signed-off-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: User visible fixes: - Fix showing the running kernel build id using: (Michael Petlan) $ perf buildid-list -k 03c2a89c595616188f02f0282762a75b47069bc0 - hists browser (report, top) symbol filter segfault fixes (Wang Nan) Signed-off-by:
-
Ingo Molnar authored
Merge tag 'perf-core-for-mingo' 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: User visible changes: - Fixes and improvements for supporting annotating ARM binaries, support ARM call and jump instructions, more work needed to have arch specific stuff separated into tools/perf/arch/*/annotate/ (Russell King) - Fix several 'perf test' entries broken by recent perf/core changes (Jiri Olsa) Infrastructure changes: - Consolidate perf_ev{list,sel}__{enable,disable}() calls (Jiri Olsa) - Pass correct string to dso__adjust_kmod_long_name() (Wang Nan) Signed-off-by:
-
- 07 Dec, 2015 19 commits
-
-
Russell King authored
Add basic support to parse ARM assembly. This: * enables perf to correctly show the disassembly, rather than chopping some constants off at the '#' (which is not a comment character on ARM). * allows perf to identify ARM instructions that branch to other parts within the same function, thereby properly annotating them. * allows perf to identify function calls, allowing called functions to be followed in the annotated view. Signed-off-by:
Russell King <rmk+kernel@arm.linux.org.uk> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Will Deacon <will.deacon@arm.com> Link: http://lkml.kernel.org/n/tip-owp1uj0nmcgfrlppfyeetuyf@git.kernel.orgSigned-off-by:
-
Jiri Olsa authored
It's more readable this way and we can save one perf_evsel__is_group_leader condition in current code. Signed-off-by:
Jiri Olsa <jolsa@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1449133606-14429-7-git-send-email-jolsa@kernel.orgSigned-off-by:
-
Jiri Olsa authored
Currently we have 2 kinds of stat counters based on when the event is enabled: 1) tracee command events, which are enable once the tracee executes exec syscall (enable_on_exec bit) 2) all other events which get alive within the perf_event_open syscall And 2) case could raise a problem in case we want additional filter to be attached for event. In this case we want the event to be enabled after it's configured with filter. Changing the behaviour of 2) events, so they all are created as disabled (disabled bit). Adding extra enable call to make them alive once they finish setup. Signed-off-by: -
Jiri Olsa authored
No need to mimic the behaviour of perf_evlist__enable, we can use it directly. Signed-off-by:
-
Jiri Olsa authored
Use perf_evsel__(enable|disable) functions in perf_evlist__(enable|disable) functions in order to centralize ioctl enable/disable calls. This way we eliminate 2 places calling directly ioctl. Signed-off-by:
-
Jiri Olsa authored
Adding perf_evsel__disable function to have complement for perf_evsel__enable function. Both will be used in following patch to factor perf_evlist__(enable|disable). Signed-off-by:
-
Jiri Olsa authored
All events now share proper cpu and thread maps. There's no need to pass those maps from evlist, it's safe to use evsel maps for enabling event. Signed-off-by:
-
Jiri Olsa authored
It fixes segfault within machine__exit, that's caused but not creating kernel maps for machine.. We're calling machine__destroy_kernel_maps in machine__exit since commit: ebe9729c perf machine: Fix to destroy kernel maps when machine exits Signed-off-by:
Namhyung Kim <namhyung@kernel.org> Tested-by:
-
Jiri Olsa authored
The bpf-output is added under software events, but is not parse-able within parse_events, which is what round trip test is expecting. Checking software events only until dummy event. Signed-off-by:
-
Jiri Olsa authored
In error path to try user space event, both cpus and threads map now owned by evlist and freed by perf_evlist__set_maps call. Getting reference to keep them alive. Signed-off-by:
-
Jiri Olsa authored
This is more straightforward than what we have now. It also fixes a segfault within machine__exit, that's caused by not creating kernel maps for machine.. We're calling machine__destroy_kernel_maps in machine__exit since commit: ebe9729c perf machine: Fix to destroy kernel maps when machine exits Signed-off-by:
-
Jiri Olsa authored
This is more straightforward than what we have now. It also fixes a segfault within machine__exit, that's caused by not creating kernel maps for machine.. We're calling machine__destroy_kernel_maps in machine__exit since commit: ebe9729c perf machine: Fix to destroy kernel maps when machine exits Signed-off-by:
-
Jiri Olsa authored
This is more straightforward than what we have now. It also fixes a segfault within machine__exit, that's caused by not creating kernel maps for machine.. We're calling machine__destroy_kernel_maps in machine__exit since commit: ebe9729c perf machine: Fix to destroy kernel maps when machine exits Signed-off-by:
-
Wang Nan authored
There's a mistake in dso__adjust_kmod_long_name() that it use strdup() to dup the new long_name of a dso, but passes the original string to dso__set_long_name(). Which causes random crash during cleanup. Signed-off-by:
Wang Nan <wangnan0@huawei.com> Reviewed-by:
-
Wang Nan authored
If feed perf a symbol filter in cmdline and the result is empty, pressing 'Enter' in the hist browser causes crash: # ./perf report perf.data <-- Common mistake for beginners Then press 'Enter': perf: Segmentation fault -------- backtrace -------- /home/wangnan/perf[0x53e578] /lib64/libc.so.6(+0x3545f)[0x7f76bafe045f] /home/wangnan/perf[0x539dd4] /home/wangnan/perf(perf_evlist__tui_browse_hists+0x96)[0x53d216] /home/wangnan/perf(cmd_report+0x1b9f)[0x442c7f] /home/wangnan/perf[0x47efa2] /home/wangnan/perf(main+0x5f5)[0x432fa5] /lib64/libc.so.6(__libc_start_main+0xf4)[0x7f76bafccbd4] /home/wangnan/perf[0x4330d4] This is because 'perf.data' is interpreted as a symbol filter, and the result is empty, so selection is empty. However, hist_browser__toggle_fold() forgets to check it. This patch simply return false when selection is NULL. Signed-off-by:
-
Wang Nan authored
With the following steps: Step 1: perf report Step 2: Use UP/DOWN to select an entry, don't press 'ENTER' Step 3: Use '/' to filter symbols, use a filter which returns empty result Step 4: Press 'ENTER' We see that, even if we have filtered all the symbols (and the main interface is empty), pressing 'ENTER' still selects one symbol. This behavior surprises the user. This patch resets browser->{he_,}selection in hist_browser__refresh() and lets it choose default selection. In this case browser->{he_,}selection keeps NULL so user won't see annotation item in menu. Signed-off-by: -
Wang Nan authored
Before this patch we can trigger a segfault by following steps: Step 0: Use 'perf record' to generate a perf.data without callchain Step 1: perf report Step 2: Use UP/DOWN to select an entry, don't press 'ENTER' Step 3: Use '/' to filter symbols, use a filter which returns empty result Step 4: Press 'ENTER' (notice here that the old selection is still there. This is another problem) Step 5: Press 'ENTER' to annotate that symbol Step 6: Press 'LEFT' to go out. Result: segfault: perf: Segmentation fault -------- backtrace -------- /home/wangnan/perf[0x53e568] /lib64/libc.so.6(+0x3545f)[0x7fba75d3245f] /home/wangnan/perf[0x537516] /home/wangnan/perf[0x533fef] /home/wangnan/perf[0x53b347] /home/wangnan/perf(perf_evlist__tui_browse_hists+0x96)[0x53d206] /home/wangnan/perf(cmd_report+0x1b9f)[0x442c7f] /home/wangnan/perf[0x47efa2] /home/wangnan/perf(main+0x5f5)[0x432fa5] /lib64/libc.so.6(__libc_start_main+0xf4)[0x7fba75d1ebd4] /home/wangnan/perf[0x4330d4] This is because in this case 'nd' could be NULL in ui_browser__hists_seek(), but that function never checks it. This patch adds checker for potential NULL pointer in that function. After this patch the above steps won't segfault. Signed-off-by: -
Michael Petlan authored
The buildid string length is returned by perf buildid-list -k command. Since a non-zero return value means an error, perf buildid-list -k cmd should return 0 when successful instead. Before: # perf buildid-list -k 39356d74e96e02346fe0ec1f3f162b6c522bac62 # echo $? 41 After: # perf buildid-list -k 39356d74e96e02346fe0ec1f3f162b6c522bac62 # echo $? 0 Signed-off-by:
Michael Petlan <mpetlan@redhat.com> Tested-by:
-
Michael Petlan authored
The --kernel option of perf buildid-list tool should show the running kernel buildid. The functionality has been lost during other changes of the related code. The build_id__sprintf() function should return length of the build-id string, but it was the length of the build-id raw data instead. Due to that, some return value checking caused that the final string was not printed out. With this patch the build_id__sprintf() returns the correct value, so the --kernel option works again. Before: # perf buildid-list --kernel # After: # perf buildid-list --kernel 972c1edab5bdc06cc224af45d510af662a3c6972 # Signed-off-by:
-
- 06 Dec, 2015 10 commits
-
-
Andi Kleen authored
Now that we have generic MSR trace points we can remove the old hackish perf MSR read tracing code. Signed-off-by:
Andi Kleen <ak@linux.intel.com> Signed-off-by:
Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> 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: rostedt@goodmis.org Link: http://lkml.kernel.org/r/1449018060-1742-4-git-send-email-andi@firstfloor.orgSigned-off-by:
-
Andi Kleen authored
For debugging low level code interacting with the CPU it is often useful to trace the MSR read/writes. This gives a concise summary of PMU and other operations. perf has an ad-hoc way to do this using trace_printk, but it's somewhat limited (and also now spews ugly boot messages when enabled) Instead define real trace points for all MSR accesses. This adds three new trace points: read_msr and write_msr and rdpmc. They also report if the access faulted (if *_safe is used) This allows filtering and triggering on specific MSR values, which allows various more advanced debugging techniques. All the values are well defined in the CPU documentation. The trace can be post processed with Documentation/trace/postprocess/decode_msr.py to add symbolic MSR names to the trace. I only added it to native MSR accesses in C, not paravirtualized or in entry*.S (which is not too interesting) Originally the patch kit moved the MSRs out of line. This uses an alternative approach recommended by Steven Rostedt of only moving the trace calls out of line, but open coding the access to the jump label. Signed-off-by:
Steven Rostedt <rostedt@goodmis.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> 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> Link: http://lkml.kernel.org/r/1449018060-1742-3-git-send-email-andi@firstfloor.orgSigned-off-by:
-
Andi Kleen authored
Steven recommended open coding access to tracepoint->key to add trace points to headers. Unfortunately this is difficult for some headers (such as x86 asm/msr.h) because including tracepoint.h includes so many other headers that it causes include loops. The main problem is the include of linux/rcupdate.h, which pulls in a lot of other headers. The rcu header is only needed when actually defining trace points. Move the struct tracepoint into a separate tracepoint-defs.h header that can be included without pulling in all of RCU. Signed-off-by:
-
Andi Kleen authored
asm/atomic.h doesn't really need asm/processor.h anymore. Everything it uses has moved to other header files. So remove that include. processor.h is a nasty header that includes lots of other headers and makes it prone to include loops. Removing the include here makes asm/atomic.h a "leaf" header that can be safely included in most other headers. The only fallout is in the lib/atomic tester which relied on this implicit include. Give it an explicit include. (the include is in ifdef because the user is also in ifdef) Signed-off-by:
-
Andi Kleen authored
Fix a definition in the perf rapl driver. __initconst must be applied to a const object, but to declare a const pointer you need to use * const ..., not const ... * This fixes a section attribute conflict with LTO builds. Signed-off-by:
-
Peter Zijlstra authored
Various functions implement the same pattern to send IPIs to an event's CPU. Collapse the easy ones in a common helper function to reduce duplication. Signed-off-by:
-
Ingo Molnar authored
Signed-off-by: -
Jiri Olsa authored
In case we monitor events system wide, we get EXIT event (when configured) twice for each task that exited. Note doubled lines with same pid/tid in following example: $ sudo ./perf record -a ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.480 MB perf.data (2518 samples) ] $ sudo ./perf report -D | grep EXIT 0 60290687567581 0x59910 [0x38]: PERF_RECORD_EXIT(1250:1250):(1250:1250) 0 60290687568354 0x59948 [0x38]: PERF_RECORD_EXIT(1250:1250):(1250:1250) 0 60290687988744 0x59ad8 [0x38]: PERF_RECORD_EXIT(1250:1250):(1250:1250) 0 60290687989198 0x59b10 [0x38]: PERF_RECORD_EXIT(1250:1250):(1250:1250) 1 60290692567895 0x62af0 [0x38]: PERF_RECORD_EXIT(1253:1253):(1253:1253) 1 60290692568322 0x62b28 [0x38]: PERF_RECORD_EXIT(1253:1253):(1253:1253) 2 60290692739276 0x69a18 [0x38]: PERF_RECORD_EXIT(1252:1252):(1252:1252) 2 60290692739910 0x69a50 [0x38]: PERF_RECORD_EXIT(1252:1252):(1252:1252) The reason is that the cpu contexts are processes each time we call perf_event_task. I'm changing the perf_event_aux logic to serve task_ctx and cpu contexts separately, which ensure we don't get EXIT event generated twice on same cpu context. This does not affect other auxiliary events, as they don't use task_ctx at all. Signed-off-by:
-
Jiri Olsa authored
We need to add rest of the flags to the constraint mask instead of another INTEL_ARCH_EVENT_MASK, fixing a typo. Signed-off-by:
-
Yuanfang Chen authored
There was a mistake in the Haswell constraints table. Signed-off-by:
Yuanfang Chen <cheny@udel.edu> Signed-off-by:
-
- 04 Dec, 2015 1 commit
-
-
Peter Zijlstra authored
Dmitry reported a fairly silly recursive lock deadlock for PERF_EVENT_IOC_PERIOD, fix this by explicitly doing the inactive part of __perf_event_period() instead of calling that function. Reported-by:
Dmitry Vyukov <dvyukov@google.com> Signed-off-by:
-
