- 11 Dec, 2015 6 commits
-
-
Wang Nan authored
Namhyung Kim pointed out a potential problem in original code that it fetches names of maps from section header string table, which is used to store section names. Original code doesn't cause error because of a LLVM behavior that, it combines shstrtab into strtab. For example: $ echo 'int func() {return 0;}' | x86_64-oe-linux-clang -x c -o temp.o -c - $ readelf -h ./temp.o ELF Header: Magic: 7f 45 4c 46 02 01 01 03 00 00 00 00 00 00 00 00 ... Section header string table index: 1 $ readelf -S ./temp.o There are 10 section headers, starting at offset 0x288: Section Headers: [Nr] Name Type Address Offset Size EntSize Flags Link Info Align [ 0] NULL 0000000000000000 00000000 0000000000000000 0000000000000000 0 0 0 [ 1] .strtab STRTAB 0000000000000000 00000230 0000000000000051 0000000000000000 0 0 1 ... $ readelf -p .strtab ./temp.o String dump of section '.strtab': [ 1] .text [ 7] .comment [ 10] .bss [ 15] .note.GNU-stack [ 25] .rela.eh_frame [ 34] func [ 39] .strtab [ 41] .symtab [ 49] .data [ 4f] - $ readelf -p .shstrtab ./temp.o readelf: Warning: Section '.shstrtab' was not dumped because it does not exist! Where, 'section header string table index' points to '.strtab', and symbol names are also stored there. However, in case of gcc: $ echo 'int func() {return 0;}' | gcc -x c -o temp.o -c - $ readelf -p .shstrtab ./temp.o String dump of section '.shstrtab': [ 1] .symtab [ 9] .strtab [ 11] .shstrtab [ 1b] .text [ 21] .data [ 27] .bss [ 2c] .comment [ 35] .note.GNU-stack [ 45] .rela.eh_frame $ readelf -p .strtab ./temp.o String dump of section '.strtab': [ 1] func They are separated sections. Although original code doesn't cause error, we'd better use canonical method for fetching symbol names to avoid potential behavior changing. This patch learns from readelf's code, fetches string from sh_link of .symbol section. Signed-off-by:Wang Nan <wangnan0@huawei.com> Reported-and-Acked-by:
Namhyung Kim <namhyung@kernel.org> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1449541544-67621-3-git-send-email-wangnan0@huawei.comSigned-off-by:
Arnaldo Carvalho de Melo <acme@redhat.com>
-
Wang Nan authored
Commit 561bbcca ("tools lib bpf: Extract and collect map names from BPF object file") forgets checking return value of strdup(). This patch fixes it. It also checks names pointer before strcmp() for safety. Signed-off-by:
-
Namhyung Kim authored
The 'he' cannot be NULL since it's caller hist_iter__top_callback() is called only if iter->he is not NULL (see hist_entry_iter__add). So setting 'sym' before the condition to simplify the code. Also make it clearer that the top->symbol_filter_entry check is only meaningful on stdio mode (i.e. when use_browser is 0). Signed-off-by:
-
Namhyung Kim authored
The ui__has_annotation() inside perf_top__record_precise_ip() should be removed since it returns true only for TUI (and when sort key has symbol). However the 'perf top --stdio' also supports annotation for a symbol which was specified by 's' key action. Actually it already does the necessary checks before calling the function. So it's ok to get rid of the check here. Signed-off-by:
-
Namhyung Kim authored
The perf_top__record_precise_ip() releases and regrabs the he->hists->lock because it can sleep if there's an error. But it should be done conditionally as it slows down the fast path. Signed-off-by:
-
Namhyung Kim authored
We call map->unmap_ip() before the function and call map->map_ip() inside the function. This is meaningless and look strange since only one of the two checks 'map'. Let's use al->addr directly. Signed-off-by:
-
- 10 Dec, 2015 12 commits
-
-
Masami Hiramatsu authored
Fix dso__load_sym to put dso because dsos__add already got it. Refcnt debugger explain the problem: ---- ==== [0] ==== Unreclaimed dso: 0x19dd200 Refcount +1 => 1 at ./perf(dso__new+0x1ff) [0x4a62df] ./perf(dso__load_sym+0xe89) [0x503509] ./perf(dso__load_vmlinux+0xbf) [0x4aa77f] ./perf(dso__load_vmlinux_path+0x8c) [0x4aa8dc] ./perf() [0x50539a] ./perf(convert_perf_probe_events+0xd79) [0x50ad39] ./perf() [0x45600f] ./perf(cmd_probe+0x6c) [0x4566bc] ./perf() [0x47abc5] ./perf(main+0x610) [0x421f90] /lib64/libc.so.6(__libc_start_main+0xf5) [0x7f74dd0efaf5] ./perf() [0x4220a9] Refcount +1 => 2 at ./perf(dso__get+0x34) [0x4a65f4] ./perf(map__new2+0x76) [0x4be216] ./perf(dso__load_sym+0xee1) [0x503561] ./perf(dso__load_vmlinux+0xbf) [0x4aa77f] ./perf(dso__load_vmlinux_path+0x8c) [0x4aa8dc] ./perf() [0x50539a] ./perf(convert_perf_probe_events+0xd79) [0x50ad39] ./perf() [0x45600f] ./perf(cmd_probe+0x6c) [0x4566bc] ./perf() [0x47abc5] ./perf(main+0x610) [0x421f90] /lib64/libc.so.6(__libc_start_main+0xf5) [0x7f74dd0efaf5] ./perf() [0x4220a9] Refcount +1 => 3 at ./perf(dsos__add+0xf3) [0x4a6bc3] ./perf(dso__load_sym+0xfc1) [0x503641] ./perf(dso__load_vmlinux+0xbf) [0x4aa77f] ./perf(dso__load_vmlinux_path+0x8c) [0x4aa8dc] ./perf() [0x50539a] ./perf(convert_perf_probe_events+0xd79) [0x50ad39] ./perf() [0x45600f] ./perf(cmd_probe+0x6c) [0x4566bc] ./perf() [0x47abc5] ./perf(main+0x610) [0x421f90] /lib64/libc.so.6(__libc_start_main+0xf5) [0x7f74dd0efaf5] ./perf() [0x4220a9] Refcount -1 => 2 at ./perf(dso__put+0x2f) [0x4a664f] ./perf(map_groups__exit+0xb9) [0x4bee29] ./perf(machine__delete+0xb0) [0x4b93d0] ./perf(exit_probe_symbol_maps+0x28) [0x506718] ./perf() [0x45628a] ./perf(cmd_probe+0x6c) [0x4566bc] ./perf() [0x47abc5] ./perf(main+0x610) [0x421f90] /lib64/libc.so.6(__libc_start_main+0xf5) [0x7f74dd0efaf5] ./perf() [0x4220a9] Refcount -1 => 1 at ./perf(dso__put+0x2f) [0x4a664f] ./perf(machine__delete+0xfe) [0x4b941e] ./perf(exit_probe_symbol_maps+0x28) [0x506718] ./perf() [0x45628a] ./perf(cmd_probe+0x6c) [0x4566bc] ./perf() [0x47abc5] ./perf(main+0x610) [0x421f90] /lib64/libc.so.6(__libc_start_main+0xf5) [0x7f74dd0efaf5] ./perf() [0x4220a9] ---- So, in the dso__load_sym, dso is gotten 3 times, by dso__new, map__new2, and dsos__add. The last 2 is actually released by map_groups and machine__delete correspondingly. However, the first reference by dso__new, is never released. Committer note: Changed the place where the reference count is dropped to: Fix it by dropping it right after creating curr_map, since we know that either that operation failed and we need to drop the dso refcount or that it succeed and we have it referenced via curr_map->dso. Then only drop the curr_map refcount after we call dsos__add() to make sure we hold a reference to it via curr_map->dso. 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/20151209021118.10245.49869.stgit@localhost.localdomainSigned-off-by:
-
Masami Hiramatsu authored
Note that since the thread was already inserted to the session list, it will be released when the session is released. Also, in perf_session__register_idle_thread() failure path, the thread should be put before returning. Refcnt debugger shows that the perf_session__register_idle_thread gets the returned thread, but the caller (__cmd_top) does not put the returned idle thread. ---- ==== [0] ==== Unreclaimed thread@0x24e6240 Refcount +1 => 0 at ./perf(thread__new+0xe5) [0x4c8a75] ./perf(machine__findnew_thread+0x9a) [0x4bbdba] ./perf(perf_session__register_idle_thread+0x28) [0x4c63c8] ./perf(cmd_top+0xd7d) [0x43cf6d] ./perf() [0x47ba35] ./perf(main+0x617) [0x4225b7] /lib64/libc.so.6(__libc_start_main+0xf5) [0x7f06027c5af5] ./perf() [0x42272d] Refcount +1 => 1 at ./perf(thread__get+0x2c) [0x4c8bcc] ./perf(machine__findnew_thread+0xee) [0x4bbe0e] ./perf(perf_session__register_idle_thread+0x28) [0x4c63c8] ./perf(cmd_top+0xd7d) [0x43cf6d] ./perf() [0x47ba35] ./perf(main+0x617) [0x4225b7] /lib64/libc.so.6(__libc_start_main+0xf5) [0x7f06027c5af5] ./perf() [0x42272d] Refcount +1 => 2 at ./perf(thread__get+0x2c) [0x4c8bcc] ./perf(machine__findnew_thread+0x112) [0x4bbe32] ./perf(perf_session__register_idle_thread+0x28) [0x4c63c8] ./perf(cmd_top+0xd7d) [0x43cf6d] ./perf() [0x47ba35] ./perf(main+0x617) [0x4225b7] /lib64/libc.so.6(__libc_start_main+0xf5) [0x7f06027c5af5] ./perf() [0x42272d] ---- Signed-off-by: -
Arnaldo Carvalho de Melo authored
This reverts commit e8b7ea43. Martin created a gcc PR: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=68836Reported-by:
Jiri Olsa <jolsa@redhat.com> Acked-by:
Ingo Molnar <mingo@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Martin Liska <mliska@suse.cz> Cc: Namhyung Kim <namhyung@kernel.org>, Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20151202164827.GA21124@krava.brq.redhat.comSigned-off-by:
-
Namhyung Kim authored
After sample processing is done, hist entries are in both of hists->entries and hists->entries_in (or hists->entries_collapsed). So I guess perf report does not have leaks on hists. But for perf top, it's possible to have half-processed entries which are only in hists->entries_in. Eventually they will go to the hists->entries and get freed but they cannot be deleted by current hists__delete_entries(). This patch adds hists__delete_all_entries function to delete those entries. Signed-off-by:
-
Namhyung Kim authored
Since all of its users call before setup_browser(), there's no need to call exit_browser() inside of the function. Signed-off-by:
Josh Poimboeuf <jpoimboe@redhat.com> Tested-by:
-
Namhyung Kim authored
Signed-off-by:
-
Arnaldo Carvalho de Melo authored
This is necessary to get rid of the browser dependency from usage_with_options() and its friends. Because we validate the targets which are used to create the cpu/thread maps and inform the user about any override performed via the chosen UI, we don't need to call the usage routine for that. Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/n/tip-slu7lj7buzpwgop1vo9la8ma@git.kernel.orgSigned-off-by:
-
Namhyung Kim authored
This is necessary to get rid of the browser dependency from usage_with_options() and its friends. Because there's no code changing the argc and argv, it'd be ok to check it early. Signed-off-by:
-
Namhyung Kim authored
Calling setup_browser(false) with use_browser = 0 is meaningless. Just get rid of it. This is necessary to remove the browser dependency from usage_with_options() and friends. Signed-off-by:
-
Namhyung Kim authored
Move setup_browser after all necessary initialization is done. This is to remove the browser dependency from usage_with_options and friends. Signed-off-by:
-
Namhyung Kim authored
This is necessary to get rid of the browser dependency from usage_with_options() and its friends. Because there's no code changing the argc and argv, it'd be ok to check it early. 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: User visible changes: - Change default selection TUI background color to yellow (Ingo Molnar) Infrastructure changes: - Start paving the way to reuse some cmdline functions with other tools/ living utilities (Josh Poimboeuf) - Reference count fixes using the refcount debugger, unleaking some objects (Masami Hiramatsu) Signed-off-by:
-
- 09 Dec, 2015 11 commits
-
-
Josh Poimboeuf authored
Move cmd_version() to its own file so that help.c can be moved to a library. Signed-off-by:
-
Josh Poimboeuf authored
perf_env__set_cmdline() only saves the arguments the first time it's called. It doesn't need to be called every time the options and suboptions are parsed. Instead it can just be called once. This also has the advantage of making the option parsing code less perf-specific so it can be moved out to a library. Signed-off-by:
-
Josh Poimboeuf authored
The term functions are needed by help.c which is going to be moved into a separate library. Move them out of util.c and into their own file. Signed-off-by:
-
Josh Poimboeuf authored
Signed-off-by:
-
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 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:
-
- 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 8 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:
-
