- 08 May, 2015 11 commits
-
-
Arnaldo Carvalho de Melo authored
We will need it for atomic.h, so move it from the ad-hoc tools/perf/ place to a tools/ subset of the kernel arch/ hierarchy. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Borislav Petkov <bp@suse.de> Cc: David Ahern <dsahern@gmail.com> Cc: Don Zickus <dzickus@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-zv4x77074resrkl4ayzf5e7d@git.kernel.orgSigned-off-by:
Arnaldo Carvalho de Melo <acme@redhat.com>
-
Arnaldo Carvalho de Melo authored
We will need it for atomic.h, so move it from the ad-hoc tools/perf/ place to a tools/ subset of the kernel arch/ hierarchy. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Borislav Petkov <bp@suse.de> Cc: David Ahern <dsahern@gmail.com> Cc: Don Zickus <dzickus@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-pk6f5x9vh8k2ebzhh9uj5wo2@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
We will need it for atomic.h, so move it from the ad-hoc tools/perf/ place to a tools/ subset of the kernel arch/ hierarchy. Other aches will follow, each in a cset. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Borislav Petkov <bp@suse.de> Cc: David Ahern <dsahern@gmail.com> Cc: Don Zickus <dzickus@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-vy6bqmsvm6puibpay2cy4wid@git.kernel.orgSigned-off-by:
-
Masami Hiramatsu authored
$params is similar to $vars but matches only function parameters not local variables. Thus, this is useful for tracing function parameter changing or tracing function call with parameters. Testing it: # perf probe tcp_sendmsg '$params' Added new event: probe:tcp_sendmsg (on tcp_sendmsg with $params) You can now use it in all perf tools, such as: perf record -e probe:tcp_sendmsg -aR sleep 1 # perf probe -l probe:tcp_sendmsg (on tcp_sendmsg@acme/git/linux/net/ipv4/tcp.c with iocb sk msg size) # perf record -a -e probe:* press some random letters to generate TCP (sshd) traffic... ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.223 MB perf.data (6 samples) ] # perf script sshd 6385 [2] 3.907529: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24 sshd 6385 [2] 4.138973: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24 sshd 6385 [2] 4.378966: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24 sshd 6385 [2] 4.603681: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24 sshd 6385 [2] 4.818455: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24 sshd 6385 [2] 5.043603: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24 # cat /sys/kernel/debug/tracing/events/probe/tcp_sendmsg/format name: tcp_sendmsg ID: 1927 format: field:unsigned short common_type; offset:0; size:2; signed:0; field:unsigned char common_flags; offset:2; size:1; signed:0; field:unsigned char common_preempt_count; offset:3; size:1; signed:0; field:int common_pid; offset:4; size:4; signed:1; field:unsigned long __probe_ip; offset:8; size:8; signed:0; field:u64 iocb; offset:16; size:8; signed:0; field:u64 sk; offset:24; size:8; signed:0; field:u64 msg; offset:32; size:8; signed:0; field:u64 size; offset:40; size:8; signed:0; print fmt: "(%lx) iocb=0x%Lx sk=0x%Lx msg=0x%Lx size=0x%Lx", REC->__probe_ip, REC->iocb, REC->sk, REC->msg, REC->size # Do some system wide tracing of this probe + write syscalls: # perf trace -e write --ev probe:* --filter-pids 6385 462.612 (0.010 ms): bash/19153 write(fd: 1</dev/pts/1>, buf: 0x7f7556c78000, count: 29 ) = 29 462.701 (0.027 ms): sshd/19152 write(fd: 3<socket:[63117]>, buf: 0x7f78dd12e160, count: 68 ) ... 462.701 ( ): probe:tcp_sendmsg:(ffffffff8163db30) iocb=0xffff8803ebec7e70 sk=0xffff88042196ab80 msg=0xffff8803ebec7da8 size=0x44) 462.710 (0.035 ms): sshd/19152 ... [continued]: write()) = 68 462.787 (0.009 ms): bash/19153 write(fd: 2</dev/pts/1>, buf: 0x7f7556c77000, count: 22 ) = 22 462.865 (0.002 ms): sshd/19152 write(fd: 3<socket:[63117]>, buf: 0x7f78dd12e160, count: 68 ) ... 462.865 ( ): probe:tcp_sendmsg:(ffffffff8163db30) iocb=0xffff8803ebec7e70 sk=0xffff88042196ab80 msg=0xffff8803ebec7da8 size=0x44) 462.873 (0.010 ms): sshd/19152 ... [continued]: write()) = 68 Signed-off-by:
Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Tested-by:
-
Masami Hiramatsu authored
Skip the kernel symbols which is out of .text, e.g. the functions in .inittext. Those are found in debuginfo/kallsyms, but already freed from memory. e.g. ---- # perf probe vfs_caches_init vfs_caches_init+0 is out of .text, skip it. Probe point 'vfs_caches_init' not found. Error: Failed to add events. ---- Signed-off-by: -
Masami Hiramatsu authored
Fix --line to check valid C-style function name and returns a semantic error if it is not. For example, previously, --line doesn't support lazy pattern but it doesn't recognized as a semantic error. ---- # perf probe -L 'func;return*:0-10' Specified source line is not found. Error: Failed to show lines. ---- With this patch, it is correctly handled as a semantic error. ---- # perf probe -L 'func;return*:0-10' Semantic error :'func;return*' is not a valid function name. ... ---- Signed-off-by: -
Masami Hiramatsu authored
Fix to return 0 when positive value returned from probe command. At least --vars can returns a positive value if it found a point. ---- # perf probe --vars vfs_read && echo succeeded! || echo failed! Available variables at vfs_read @<vfs_read+0> char* buf loff_t* pos size_t count struct file* file failed! ---- This fixes above problem. ---- # perf probe --vars vfs_read && echo succeeded! || echo failed! Available variables at vfs_read @<vfs_read+0> char* buf loff_t* pos size_t count struct file* file succeeded! ---- Signed-off-by: -
Masami Hiramatsu authored
Fix to pass O_APPEND by using bit-or with other flags, instead of passing it as mode. Signed-off-by:
-
Masami Hiramatsu authored
Fix perf-probe to close probe_events file if it failed to get existing probe's name. This also fix the return error code to -ENOMEM. Signed-off-by:
-
Michael Ellerman authored
On powerpc the perf event interrupt is not masked when interrupts are disabled, allowing it to function as an NMI. This causes problems if perf is using vmalloc. If we take a page fault on the vmalloc region the fault handler will fail the page fault because it detects we are coming in from an NMI (see do_hash_page()). We don't actually need or want vmalloc backed perf so just disable it on powerpc. Signed-off-by:
Michael Ellerman <mpe@ellerman.id.au> Signed-off-by:
Peter Zijlstra (Intel) <peterz@infradead.org> Cc: <linuxppc-dev@ozlabs.org> Cc: Andrew Morton <akpm@osdl.org> Cc: Anton Blanchard <anton@samba.org> Cc: Borislav Petkov <bp@alien8.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: acme@ghostprotocols.net Cc: sukadev@linux.vnet.ibm.com Link: http://lkml.kernel.org/r/1430720799-18426-1-git-send-email-mpe@ellerman.id.auSigned-off-by:
Ingo Molnar <mingo@kernel.org>
-
Peter Zijlstra authored
Stephane asked about PERF_COUNT_SW_CPU_MIGRATIONS and I realized it was borken: > The problem is that the task isn't actually scheduled while its being > migrated (obviously), and if its not scheduled, the counters aren't > scheduled either, so there's no observing of the fact. > > A further problem with migrations is that many migrations happen from > softirq context, which is nested inside the 'random' task context of > whoemever happens to run at that time, similarly for the wakeup > migrations triggered from (soft)irq context. All those end up being > accounted in the task that's currently running, eg. your 'ls'. The below cures this by marking a task as migrated and accounting it on the subsequent sched_in(). Signed-off-by:
-
- 06 May, 2015 1 commit
-
-
Ingo Molnar authored
Merge tag 'perf-core-for-mingo-3' 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: - Improve --filter support for 'perf probe', allowing using its arguments on other commands, as --add, --del, etc (Masami Hiramatsu) - Show warning when running 'perf kmem stat' on a unsuitable perf.data file, i.e. one with events that are not the ones required for the stat variant used (Namhyung Kim). Infrastructure changes: - Auxtrace support patches, paving the way to support Intel PT and BTS (Adrian Hunter) - hists browser (top, report) refactorings (Namhyung Kim) Signed-off-by:
-
- 05 May, 2015 22 commits
-
-
Namhyung Kim authored
The has_children and unfolded fields don't belong to the struct map_symbol since they're used by the TUI only. Move those fields out of map_symbol since the struct is also used by other places. This will also help to compact the sizeof struct hist_entry. Signed-off-by:
Namhyung Kim <namhyung@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1429687101-4360-11-git-send-email-namhyung@kernel.org Link: http://lkml.kernel.org/r/1430837746-5439-1-git-send-email-namhyung@kernel.orgSigned-off-by:
-
Namhyung Kim authored
Now LEFT key press action can just use do_zoom_dso/thread() code to get out of the current filter. Signed-off-by:
Jiri Olsa <jolsa@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1429838133-14001-2-git-send-email-namhyung@kernel.orgSigned-off-by:
-
Namhyung Kim authored
The pstack_peek() is to get the topmost entry without removing it. Signed-off-by:
-
Namhyung Kim authored
Currently perf_evsel__hists_browse() function spins on a huge loop and handles many key actions. Since it's hard to read and modify, let's split it out into small helper functions. The add_XXX_opt() functions are to register popup menu item on the selected entry. When it adds an item, it also saves related data into struct popup_action and returns 1 so that it can increase the number of items (nr_options). With this change, we can simplify the code just to call selected callback function without considering various conditions. A callback function named do_XXX is called with saved data when the item is selected by user. No functional change intended. Signed-off-by:
Jiri Olsa <jolsa@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1429687101-4360-9-git-send-email-namhyung@kernel.orgSigned-off-by:
-
Namhyung Kim authored
Currently perf_evsel__hists_browse() function spins on a huge loop and handles many key actions. Since it's hard to read and modify, let's split it out into small helper functions. This patch introduces do_XXX() functions which corresponds to each goto label. This way we can call such functions both from key press actions and popup menu actions. No functional change intended. Signed-off-by:
-
Namhyung Kim authored
The perf_session_env is to save system informantion at the recording time to be refered in the hist browser. So it'd be better to keep in the struct hist_browser. This is a preparation to later change. Signed-off-by:
-
Namhyung Kim authored
The struct pstack is to save currently applied thread and/or dso filters in the browser. So it'd be better to keep in the struct hist_browser. This is a preparation to later change. Suggested-by:
Arnaldo Carvalho de Melo <acme@kernel.org> Signed-off-by:
-
Namhyung Kim authored
The struct hist_browser_timer is to carry perf-top related info throughout the hist browser code. So it'd be better to keep in the struct hist_browser. This is a preparation to later change. Suggested-by:
-
Namhyung Kim authored
The options array saves strings for each popup menu item. The number of items can be vary according to the currently selected item. So it can leak some memory if it's exited from a small item. Fix it by freeing all items when loop terminates. Signed-off-by:
-
Namhyung Kim authored
The init_have_children is used to init callchain info only for TUI. So it'd be better to move it to the TUI-specific unnamed union member. Signed-off-by:
-
Namhyung Kim authored
Since perf diff only supports stdio output, TUI fields are only accessed from perf report (or perf top). So add a new unnamed union and move struct hist_entry_tui and those TUI-specific fields. Signed-off-by:
-
Namhyung Kim authored
Sometimes one can mistakenly run 'perf kmem stat' without running 'perf kmem record' before or with a different configuration like recording --slab and stat --page. Show a warning message like the one below to inform the user: # perf kmem stat --page --caller No page allocation events found. Have you run 'perf kmem record --page'? Signed-off-by:
Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1430837572-31395-1-git-send-email-namhyung@kernel.orgSigned-off-by:
-
Masami Hiramatsu authored
To simplify the 'perf probe' command code, consolidate some similar functions and use command short-name for command classification, instead of separate booleans. Signed-off-by:
-
Masami Hiramatsu authored
Since params.filter will be released in cleanup_params, we don't need to clear it in each command. Signed-off-by:
-
Masami Hiramatsu authored
This allows the user to pass the filter pattern directly to the --funcs option as below: ---- # ./perf probe -F *kmalloc __kmalloc devm_kmalloc mempool_kmalloc sg_kmalloc sock_kmalloc ---- We previously needed to use the --filter option for that. Signed-off-by:
-
Masami Hiramatsu authored
This makes perf-probe --del option to accept filter rules not only simple glob pattern. This simplifies the code and improve the flexibility. E.g. if we remove 2 different pattern events, we need 2 -d options. ---- # ./perf probe -d vfs\* -d malloc Removed event: probe_libc:malloc Removed event: probe:vfs_read ---- This allows you to joint the 2 patterns with '|'. ---- # ./perf probe -d 'vfs*|malloc' Removed event: probe:vfs_read Removed event: probe_libc:malloc ---- Signed-off-by: -
Adrian Hunter authored
Add a new option and support for Instruction Tracing Snapshot Mode. When the new option is selected, no AUX area tracing data is captured until a signal (SIGUSR2) is received. Signed-off-by:
Adrian Hunter <adrian.hunter@intel.com> Acked-by:
-
Adrian Hunter authored
Add support for making snapshots of AUX area tracing data. Signed-off-by:
-
Adrian Hunter authored
Add support for the PERF_RECORD_ITRACE_START event type. This event can be used to determine the pid and tid that are running when Instruction Tracing starts. Generally that information would come from a sched_switch event but, at the start, no sched_switch events may yet have been recorded. Signed-off-by:
-
Adrian Hunter authored
Add support for the PERF_RECORD_AUX event type. PERF_RECORD_AUX is a new kernel event that records when new data lands in the AUX buffer. Currently it is assumed that AUX data follows the same ring buffer conventions used by the perf events buffer, and consequently the AUX event is not processed during recording. It is processed during session processing so that the information in the 'flags' member is made available. The format of PERF_RECORD_AUX is outlined in the linux/perf_events.h header file. The 'flags' are also enumerated. Intel PT and Intel BTS use the flag named PERF_AUX_FLAG_TRUNCATED to determine if data has been lost because the buffer became full as perf was not able to empty it fast enough. Signed-off-by:
-
Adrian Hunter authored
Add AUX area tracing option 'x' to synthesize events for transactions. This will be used by Intel PT to synthesize an event record for each TSX start, commit or abort. Signed-off-by:
-
Adrian Hunter authored
Add build option NO_AUXTRACE to exclude compiling support for AUX area tracing. Support for both recording and processing is excluded and by implication any future additions such as Intel PT and Intel BTS will also not be compiled in with this option. Signed-off-by:
-
- 04 May, 2015 6 commits
-
-
Adrian Hunter authored
We need to include all buildids when a perf.data file contains AUX area tracing data because we do not decode the trace for that purpose because it would take too long. Signed-off-by:
-
Adrian Hunter authored
Add an index of AUX area tracing events within a perf.data file. perf record uses a special user event PERF_RECORD_FINISHED_ROUND to enable sorting of events in chunks instead of having to sort all events altogether. AUX area tracing events contain data that can span back to the very beginning of the recording period. i.e. they do not obey the rules of PERF_RECORD_FINISHED_ROUND. By adding an index, AUX area tracing events can be found in advance and the PERF_RECORD_FINISHED_ROUND approach works as usual. The index is recorded with the auxtrace feature in the perf.data file. A session reads the index but does not process it. An AUX area decoder can queue all the AUX area data in advance using auxtrace_queues__process_index() or otherwise process the index in some custom manner. Signed-off-by:
-
Adrian Hunter authored
Unwittingly the itrace options for perf report ended up below the Overhead Calculation section. Move it back with the other options. Signed-off-by:
-
Namhyung Kim authored
Currently perf kmem command will select --slab if neither --slab nor --page is given for backward compatibility. Add kmem.default config option to select the default value ('page' or 'slab'). # cat ~/.perfconfig [kmem] default = page # perf kmem stat SUMMARY (page allocator) ======================== Total allocation requests : 1,518 [ 6,096 KB ] Total free requests : 1,431 [ 5,748 KB ] Total alloc+freed requests : 1,330 [ 5,344 KB ] Total alloc-only requests : 188 [ 752 KB ] Total free-only requests : 101 [ 404 KB ] Total allocation failures : 0 [ 0 KB ] ... Signed-off-by: -
Namhyung Kim authored
Save libtraceevent output and print it in the header. # perf kmem stat --page --caller # # GFP flags # --------- # 00000010: NI: GFP_NOIO # 000000d0: K: GFP_KERNEL # 00000200: NWR: GFP_NOWARN # 000084d0: K|R|Z: GFP_KERNEL|GFP_REPEAT|GFP_ZERO # 000200d2: HU: GFP_HIGHUSER # 000200da: HUM: GFP_HIGHUSER_MOVABLE # 000280da: HUM|Z: GFP_HIGHUSER_MOVABLE|GFP_ZERO # 002084d0: K|R|Z|NT: GFP_KERNEL|GFP_REPEAT|GFP_ZERO|GFP_NOTRACK # 0102005a: NF|HW|M: GFP_NOFS|GFP_HARDWALL|GFP_MOVABLE --------------------------------------------------------------------------------------------------------- Total alloc (KB) | Hits | Order | Mig.type | GFP flags | Callsite --------------------------------------------------------------------------------------------------------- 60 | 15 | 0 | UNMOVABL | K|R|Z|NT | pte_alloc_one 40 | 10 | 0 | MOVABLE | HUM|Z | handle_mm_fault 24 | 6 | 0 | MOVABLE | HUM | do_wp_page 24 | 6 | 0 | UNMOVABL | K | __pollwait ... Requested-by:Joonsoo Kim <js1304@gmail.com> Suggested-by:
Minchan Kim <minchan@kernel.org> Signed-off-by:
-
Namhyung Kim authored
Currently 'perf kmem stat --page' shows total (page) allocation stat by default, but sometimes one might want to see live (total alloc-only) requests/pages only. The new --live option does this by subtracting freed allocation from the stat. E.g.: # perf kmem stat --page SUMMARY (page allocator) ======================== Total allocation requests : 988,858 [ 4,045,368 KB ] Total free requests : 886,484 [ 3,624,996 KB ] Total alloc+freed requests : 885,969 [ 3,622,628 KB ] Total alloc-only requests : 102,889 [ 422,740 KB ] Total free-only requests : 515 [ 2,368 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 172,173 3,083 806,686 . . 1 284 . . . . 2 6,124 58 . . . 3 114 335 . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . 1 . . 10 . . . . . # perf kmem stat --page --live SUMMARY (page allocator) ======================== Total allocation requests : 988,858 [ 4,045,368 KB ] Total free requests : 886,484 [ 3,624,996 KB ] Total alloc+freed requests : 885,969 [ 3,622,628 KB ] Total alloc-only requests : 102,889 [ 422,740 KB ] Total free-only requests : 515 [ 2,368 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 2,214 3,025 97,156 . . 1 59 . . . . 2 19 58 . . . 3 23 335 . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . # Signed-off-by:
-
