kernel/git/stable/linux.git/tools/perf/Documentation/perf-top.txt, branch master

perf docs: Refine the description for the buffer size

2024-08-12T16:59:22+00:00

Current description for the AUX trace buffer size is misleading. When a user specifies the option '-m,512M', it represents a size value in bytes (512MiB) but not 512M pages (512M x 4KiB regard to a page of 4KiB). Make the document clear that the normal buffer and the AUX tracing buffer share the same semantics. Syncs the documents for consistent text. Reviewed-by: James Clark Signed-off-by: Leo Yan Cc: Adrian Hunter Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20240812093459.2575278-1-leo.yan@arm.com Signed-off-by: Arnaldo Carvalho de Melo

perf top: Allow filters on events

2024-05-30T17:05:57+00:00

Allow filters to be added to perf top events. One use is to workaround issues with: ``` $ perf top --uid="$(id -u)" ``` which tries to scan /proc find processes belonging to the uid and can fail in such a pid terminates between the scan and the perf_event_open reporting: ``` Error: The sys_perf_event_open() syscall returned with 3 (No such process) for event (cycles:P). /bin/dmesg | grep -i perf may provide additional information. ``` A similar filter: ``` $ perf top -e cycles:P --filter "uid == $(id -u)" ``` doesn't fail this way. Signed-off-by: Ian Rogers Acked-by: Namhyung Kim Cc: John Fastabend Cc: Changbin Du Cc: Yang Jihong Cc: Andrii Nakryiko Cc: bpf@vger.kernel.org Signed-off-by: Namhyung Kim Link: https://lore.kernel.org/r/20240524205227.244375-4-irogers@google.com

perf tools: Add -H short option for --hierarchy

2024-01-25T23:24:04+00:00

I found the hierarchy mode useful, but it's easy to make a typo when using it. Let's add a short option for that. Also update the documentation. :) Acked-by: Arnaldo Carvalho de Melo Link: https://lore.kernel.org/r/20240125055124.1579617-1-namhyung@kernel.org Signed-off-by: Namhyung Kim

perf top: Add --branch-history option

2023-04-04T12:39:56+00:00

Add --branch-history option, to act the same as that option does for perf report. Example: $ cat tcallf.c volatile a = 10000, b = 100000, c; __attribute__((noinline)) f2() { c = a / b; } __attribute__((noinline)) f1() { f2(); f2(); } main() { while (1) f1(); } $ gcc -w -g -o tcallf tcallf.c $ ./tcallf & [1] 29409 $ perf top -e cycles:u -t $(pidof tcallf) --stdio --no-children --branch-history PerfTop: 3819 irqs/sec kernel: 0.0% exact: 0.0% lost: 0/0 drop: 0/0 [4000Hz cycles:u], (target_tid: 29409) -------------------------------------------------------------------------------------------------------------------- 49.01% tcallf.c:5 [.] f2 tcallf | |--24.91%--f2 tcallf.c:4 | | | |--17.14%--f1 tcallf.c:11 (cycles:1) | | f1 tcallf.c:11 | | f2 tcallf.c:6 (cycles:3) | | f2 tcallf.c:4 | | f1 tcallf.c:10 (cycles:2) | | f1 tcallf.c:9 | | main tcallf.c:16 (cycles:1) | | main tcallf.c:16 | | main tcallf.c:16 (cycles:1) | | main tcallf.c:16 | | f1 tcallf.c:12 (cycles:1) | | f1 tcallf.c:12 | | f2 tcallf.c:6 (cycles:3) | | f2 tcallf.c:4 | | f1 tcallf.c:11 (cycles:1 iter:1 avg_cycles:12) | | f1 tcallf.c:11 | | f2 tcallf.c:6 (cycles:3 iter:1 avg_cycles:12) | | f2 tcallf.c:4 | | f1 tcallf.c:10 (cycles:2 iter:1 avg_cycles:12) | | | --7.78%--f1 tcallf.c:10 (cycles:2) | f1 tcallf.c:9 | main tcallf.c:16 (cycles:1) | main tcallf.c:16 | main tcallf.c:16 (cycles:1) | main tcallf.c:16 | f1 tcallf.c:12 (cycles:1) | f1 tcallf.c:12 | f2 tcallf.c:6 (cycles:3) | f2 tcallf.c:4 | f1 tcallf.c:11 (cycles:1) | f1 tcallf.c:11 | f2 tcallf.c:6 (cycles:3) | f2 tcallf.c:4 | f1 tcallf.c:10 (cycles:2 iter:1 avg_cycles:12) | f1 tcallf.c:9 | main tcallf.c:16 (cycles:1 iter:1 avg_cycles:12) | main tcallf.c:16 | main tcallf.c:16 (cycles:1 iter:1 avg_cycles:12) ... $ pkill tcallf [1]+ Terminated ./tcallf Signed-off-by: Adrian Hunter Cc: Andi Kleen Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Link: https://lore.kernel.org/r/20230330131833.12864-2-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo

perf symbol: Add command line support for addr2line path

2023-04-04T12:39:56+00:00

Allow addr2line to be set either on the command line or via the perfconfig file. This doesn't currently work with llvm-addr2line as the addr2line code emits two things: 1) the address to decode, 2) a bogus ',' value. The expectation is the bogus value will generate: ?? ??:0 that terminates the addr2line reading. However, the output from llvm-addr2line is a single line with just the input ',' locking up the addr2line reading that is expecting a second line. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andi Kleen Cc: Andres Freund Cc: German Gomez Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Peter Zijlstra Cc: Sandipan Das Cc: Tom Rix Cc: llvm@lists.linux.dev Link: https://lore.kernel.org/r/20230328235543.1082207-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo

perf tools: Fix foolproof typo

2023-01-22T21:10:53+00:00

In the context of LBR stitching documentation. Signed-off-by: Ian Rogers Acked-by: Kan Liang Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ali Saidi Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Link: https://lore.kernel.org/r/20230119201036.156441-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo

perf evlist: Remove group option.

2022-12-14T18:28:18+00:00

The group option predates grouping events using curly braces added in commit 89efb029502d7f2d ("perf tools: Add support to parse event group syntax"). The --group option was retained for legacy support (in August 2012) but keeping it adds complexity. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexey Bayduraev Cc: Andi Kleen Cc: Anshuman Khandual Cc: Athira Jajeev Cc: Eelco Chaudron Cc: German Gomez Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Kan Liang Cc: Kim Phillips Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Riccardo Mancini Cc: Sandipan Das Cc: Sean Christopherson Cc: Shaomin Deng Cc: Stephane Eranian Cc: Timothy Hayes Cc: Xing Zhengjun Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20221213232651.1269909-6-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo

perf docs: Correct typo of event_sources

2022-06-03T19:14:51+00:00

The sysfs directory is called event_source. Before: $ ls -la /sys/bus/event_sources/devices/cpu/format/ ls: cannot access '/sys/bus/event_sources/devices/cpu/format/': No such file or directory $ After: $ ls -la /sys/bus/event_source/devices/cpu/format/ total 0 drwxr-xr-x. 2 root root 0 Jun 2 15:36 . drwxr-xr-x. 6 root root 0 Jun 2 15:35 .. -r--r--r--. 1 root root 4096 Jun 2 15:36 any -r--r--r--. 1 root root 4096 Jun 2 15:36 cmask -r--r--r--. 1 root root 4096 Jun 2 15:36 edge -r--r--r--. 1 root root 4096 Jun 2 15:36 event -r--r--r--. 1 root root 4096 Jun 2 15:36 frontend -r--r--r--. 1 root root 4096 Jun 2 15:36 inv -r--r--r--. 1 root root 4096 Jun 2 15:36 ldlat -r--r--r--. 1 root root 4096 Jun 2 15:36 offcore_rsp -r--r--r--. 1 root root 4096 Jun 2 15:36 pc -r--r--r--. 1 root root 4096 Jun 2 15:36 umask $ Reviewed-by: Sandipan Das Signed-off-by: Ian Rogers Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Alexey Bayduraev Cc: Alyssa Ross Cc: German Gomez Cc: Ingo Molnar Cc: Jin Yao Cc: Jiri Olsa Cc: Joshua Martinez Cc: Kan Liang Cc: Like Xu Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Zhengjun Xing Link: https://lore.kernel.org/r/20220603045744.2815559-1-irogers@google.com Reported-by: Kevin Nomura Signed-off-by: Arnaldo Carvalho de Melo

perf docs: Add info on AMD raw event encoding

2021-12-08T01:18:24+00:00

AMD processors have events with event select codes and unit masks larger than a byte. The core PMU, for example, uses 12-bit event select codes split between bits 0-7 and 32-35 of the PERF_CTL MSRs as can be seen from /sys/bus/event_sources/devices/cpu/format/*. The Processor Programming Reference (PPR) lists the event codes as unified 12-bit hexadecimal values instead and the split between the bits is not apparent to someone who is not aware of the layout of the PERF_CTL MSRs. 8-bit event select codes continue to work as the layout matches that of the PERF_CTL MSRs i.e. bits 0-7 for event select and 8-15 for unit mask. This adds more details in the perf man pages about using /sys/bus/event_sources/devices/*/format/* for determining the correct raw event encoding scheme. E.g. the "op_cache_hit_miss.op_cache_hit" event with code 0x28f and umask 0x03 can be programmed using its symbolic name as: $ sudo perf --debug perf-event-open stat -e op_cache_hit_miss.op_cache_hit sleep 1 ------------------------------------------------------------ perf_event_attr: type 4 size 128 config 0x20000038f sample_type IDENTIFIER read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING disabled 1 inherit 1 enable_on_exec 1 exclude_guest 1 ------------------------------------------------------------ [...] One might use a simple eventsel+umask combination based on what the current man pages say and incorrectly program the event as: $ sudo perf --debug perf-event-open stat -e r0328f sleep 1 ------------------------------------------------------------ perf_event_attr: type 4 size 128 config 0x328f sample_type IDENTIFIER read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING disabled 1 inherit 1 enable_on_exec 1 exclude_guest 1 ------------------------------------------------------------ [...] When it should have been based on the format from sysfs: $ cat /sys/bus/event_source/devices/cpu/format/event config:0-7,32-35 $ sudo perf --debug perf-event-open stat -e r20000038f sleep 1 ------------------------------------------------------------ perf_event_attr: type 4 size 128 config 0x20000038f sample_type IDENTIFIER read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING disabled 1 inherit 1 enable_on_exec 1 exclude_guest 1 ------------------------------------------------------------ [...] Reviewed-by: Kajol Jain Signed-off-by: Sandipan Das Acked-by: Jiri Olsa Cc: Ananth Narayan Cc: Kim Phillips Cc: Ravi Bangoria Cc: Robert Richter Cc: Santosh Shukla Link: https://lore.kernel.org/r/20211123084613.243792-1-sandipan.das@amd.com Signed-off-by: Arnaldo Carvalho de Melo

perf top: Add cgroup support for perf top (-G)

2021-06-24T18:33:35+00:00

Added callback option (-G) to support cgroups for 'perf top'. Added condition to make sure -cgroup and --all-cgroups aren't both enabled. Example: $perf top -e cycles -G system.slice/docker-6b95a5eb649c0d671eba3835f0d93973d05a088f3ae8602246bde37affb1ba3e.scope -a --stdio PerfTop: 3330 irqs/sec kernel:68.2% exact: 0.0% lost: 0/0 drop: 0/11075 [4000Hz cpu-clock], (all, 4 CPUs) ------------------------------------------------------------------------------------------------------------------------------------------------------- 27.32% [unknown] [.] 0x00007f8ab7b69352 11.44% [kernel] [k] 0xffffffff968cd657 3.12% [kernel] [k] 0xffffffff96160e96 2.63% [kernel] [k] 0xffffffff96160eb0 1.96% [kernel] [k] 0xffffffff9615fcf6 1.42% [kernel] [k] 0xffffffff964ddfc7 1.09% [kernel] [k] 0xffffffff96160e90 0.81% [kernel] [k] 0xffffffff96160eb3 0.67% [kernel] [k] 0xffffffff9615fec1 0.57% [kernel] [k] 0xffffffff961ee1d0 0.53% [unknown] [.] 0x00007f8ab7b6666c 0.53% [kernel] [k] 0xffffffff96160e64 0.52% [kernel] [k] 0xffffffff9616c303 0.51% [kernel] [k] 0xffffffffc08e7d50 ... Signed-off-by: Joshua Martinez Reviewed-by: Ian Rogers Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: joshua martinez Link: http://lore.kernel.org/lkml/20210616231829.3735671-1-joshuamart@google.com Signed-off-by: Arnaldo Carvalho de Melo