- 22 Nov, 2019 15 commits
-
-
Hewenliang authored
It is necessary to free the memory that we have allocated when error occurs. Fixes: ef3072cd ("tools lib traceevent: Get rid of die in add_filter_type()") Signed-off-by:
Hewenliang <hewenliang4@huawei.com> Reviewed-by:
Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Tzvetomir Stoyanov <tstoyanov@vmware.com> Link: http://lore.kernel.org/lkml/20191119014415.57210-1-hewenliang4@huawei.comSigned-off-by:
Arnaldo Carvalho de Melo <acme@redhat.com>
-
Sudip Mukherjee authored
When we passed some location in DESTDIR, install_headers called do_install with DESTDIR as part of the second argument. But do_install is again using '$(DESTDIR_SQ)$2', so as a result the headers were installed in a location $DESTDIR/$DESTDIR. In my testing I passed DESTDIR=/home/sudip/test and the headers were installed in: /home/sudip/test/home/sudip/test/usr/include/traceevent. Lets remove DESTDIR from the second argument of do_install so that the headers are installed in the correct location. Signed-off-by:
Sudipm Mukherjee <sudipm.mukherjee@gmail.com> Reviewed-by:
-
Adrian Hunter authored
Add an error message because Intel BTS does not support AUX area sampling. Signed-off-by:
Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Link: http://lore.kernel.org/lkml/20191115124225.5247-16-adrian.hunter@intel.comSigned-off-by:
-
Adrian Hunter authored
Add support for dumping, queuing and decoding AUX area samples. Decoding samples is the same as regular decoding, except in the case where there are no timestamps, in which case buffers are decoded immediately before the sample event. Signed-off-by:
-
Adrian Hunter authored
Set up the default number of mmap pages, default sample size and default psb_period for AUX area sampling. Add documentation also. Signed-off-by:
-
Adrian Hunter authored
Default config for a PMU is defined before selected events are parsed. That allows the user-entered config to override the default config. However that does not allow for changing the default config based on other options. For example, if the user chooses AUX area sampling mode, in the case of Intel PT, the psb_period needs to be small for sampling, so there is a need to set the default psb_period to 0 (2 KiB) in that case. However that should not override a value set by the user. To allow for that, when using default config, record which bits of config were changed by the user. Signed-off-by:
-
Adrian Hunter authored
Add functions to queue AUX area samples in advance (auxtrace_queue_data()) or individually (auxtrace_queues__add_sample()) or find out what queue a sample belongs on (auxtrace_queues__sample_queue()). auxtrace_queue_data() can also queue snapshot data which keeps snapshots and samples ordered with respect to each other in case support for that is desired. Signed-off-by:
-
Adrian Hunter authored
AUX area samples are not limited in how far back in time the sample could start. Consequently samples must be queued in advance to allow for time-ordered processing. To achieve that, add perf_session__peek_events() that walks and peeks at all the events. Signed-off-by:
-
Adrian Hunter authored
Add support for dumping AUX area samples i.e. via the perf script/report -D (--dump-raw-trace) option. Committer notes: Add __maybe_unused to the two args for auxtrace__dump_auxtrace_sample() for when we don't HAVE_AUXTRACE_SUPPORT. Signed-off-by:
-
Adrian Hunter authored
After decoding AUX area samples, the AUX area data is no longer needed (having been replaced by synthesized events) so cut it out. Signed-off-by:
-
Adrian Hunter authored
To allow individual events to be selected for AUX area sampling, add aux-sample-size config term. attr.aux_sample_size is updated by auxtrace_parse_sample_options() so that the existing validation will see the value. Any event that has a non-zero aux_sample_size will cause AUX area sampling to be configured, irrespective of the --aux-sample option. Signed-off-by:
-
Adrian Hunter authored
Add a 'perf record' option '--aux-sample' to request AUX area sampling. AUX area sampling uses an overwriting buffer much like snapshot mode, so adjust the AUX buffer mmapping accordingly. To make it easy to queue samples for decoding, synthesize an ID index. Signed-off-by:
-
Adrian Hunter authored
Add support for parsing and validating AUX area sample options. At present, the only option is the sample size, but it is also necessary to ensure that events are in a group with an AUX area event as the leader. Committer note: Add missing 'static inline' in front of auxtrace_parse_sample_options() for when we don't HAVE_AUXTRACE_SUPPORT. Signed-off-by:
-
Adrian Hunter authored
Move perf_evsel__find_pmu() so it can be used without forward declaration. Signed-off-by:
-
Adrian Hunter authored
Architectures are expected to know if AUX area sampling is supported by the hardware. Add a function perf_can_aux_sample() which will determine whether the kernel supports it. Committer notes: I reported that this message was taking place on a kernel without the required bits: # perf record --aux-sample -e '{intel_pt//u,branch-misses:u}' Error: The sys_perf_event_open() syscall returned with 7 (Argument list too long) for event (branch-misses:u). /bin/dmesg | grep -i perf may provide additional information. Adrian sent a patch addressing it, with this explanation: ---- perf_can_aux_sample_size() always returned true because it did not pass the attribute size to sys_perf_event_open, nor correctly check the return value and errno. ---- After applying it I get, later in the series, when --aux-sample is added: # perf record --aux-sample -e '{intel_pt//u,branch-misses:u}' AUX area sampling is not supported by kernel Signed-off-by:
-
- 21 Nov, 2019 1 commit
-
-
Adrian Hunter authored
Add kernel AUX area sampling definitions, which brings perf_event.h into line with the kernel version. New sample type PERF_SAMPLE_AUX requests a sample of the AUX area buffer. New perf_event_attr member 'aux_sample_size' specifies the desired size of the sample. Also add support for parsing samples containing AUX area data i.e. PERF_SAMPLE_AUX. Committer notes: I squashed the first two patches in this series to avoid breaking automatic bisection, i.e. after applying only the original first patch in this series we would have: # perf test -v parsing 26: Sample parsing : --- start --- test child forked, pid 17018 sample format has changed, some new PERF_SAMPLE_ bit was introduced - test needs updating test child finished with -1 ---- end ---- Sample parsing: FAILED! # With the two paches combined: # perf test parsing 26: Sample parsing : Ok # Signed-off-by:
-
- 19 Nov, 2019 9 commits
-
-
Jin Yao authored
This patch supports jumping from tui total cycles view to symbol source view. For example, perf record -b ./div perf report --total-cycles In total cycles view, we can select one entry and press 'a' or press ENTER key to jump to symbol source view. This patch also sets sort_order to NULL in cmd_report() which will use the default branch sort order. The percent value in new annotate view will be consistent with the percent in annotate view switched from perf report (we observed the original percent gap with previous patches). v2: --- Fix the 'make NO_SLANG=1' error. (set __maybe_unused to annotation_opts in block_hists_tui_browse()). Signed-off-by:
Jin Yao <yao.jin@linux.intel.com> Acked-by:
Jiri Olsa <jolsa@kernel.org> Tested-by:
-
Jin Yao authored
It would be nice if we could jump to the assembler/source view (like the normal perf report) from total cycles view. This patch moves the block_hists_tui_browse from block-info.c to ui/browsers/hists.c in order to reuse some browser codes (i.e do_annotate) for implementing new annotation view. v2: --- Fix the 'make NO_SLANG=1' error. (Change 'int block_hists_tui_browse()' to 'static inline int block_hists_tui_browse()') Signed-off-by:
-
Alexey Budankov authored
Avoid termination of trace loading in case the last record in the decompressed buffer partly resides in the following mmaped PERF_RECORD_COMPRESSED record. In this case NULL value returned by fetch_mmaped_event() means to proceed to the next mmaped record then decompress it and load compressed events. The issue can be reproduced like this: $ perf record -z -- some_long_running_workload $ perf report --stdio -vv decomp (B): 44519 to 163000 decomp (B): 48119 to 174800 decomp (B): 65527 to 131072 fetch_mmaped_event: head=0x1ffe0 event->header_size=0x28, mmap_size=0x20000: fuzzed perf.data? Error: failed to process sample ... Testing: 71: Zstd perf.data compression/decompression : Ok $ tools/perf/perf report -vv --stdio decomp (B): 59593 to 262160 decomp (B): 4438 to 16512 decomp (B): 285 to 880 Looking at the vmlinux_path (8 entries long) Using vmlinux for symbols decomp (B): 57474 to 261248 prefetch_event: head=0x3fc78 event->header_size=0x28, mmap_size=0x3fc80: fuzzed or compressed perf.data? decomp (B): 25 to 32 decomp (B): 52 to 120 ... Fixes: 57fc032a ("perf session: Avoid infinite loop when seeing invalid header.size") Link: https://marc.info/?l=linux-kernel&m=156580812427554&w=2Co-developed-by:
Alexey Budankov <alexey.budankov@linux.intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/cf782c34-f3f8-2f9f-d6ab-145cee0d5322@linux.intel.comSigned-off-by:
-
Arnaldo Carvalho de Melo authored
And take it into account when looking up DSOs when we have the dso_id fields obtained from somewhere, like from PERF_RECORD_MMAP2 records. Instances of struct map pointing to the same DSO pathname but with anything in dso_id different are in fact different DSOs, so better have different 'struct dso' instances to reflect that. At some point we may want to get copies of the contents of the different objects if we want to do correct annotation or other analysis. With this we get 'struct map' 24 bytes leaner: $ pahole -C map ~/bin/perf struct map { union { struct rb_node rb_node __attribute__((__aligned__(8))); /* 0 24 */ struct list_head node; /* 0 16 */ } __attribute__((__aligned__(8))); /* 0 24 */ u64 start; /* 24 8 */ u64 end; /* 32 8 */ _Bool erange_warned:1; /* 40: 0 1 */ _Bool priv:1; /* 40: 1 1 */ /* XXX 6 bits hole, try to pack */ /* XXX 3 bytes hole, try to pack */ u32 prot; /* 44 4 */ u64 pgoff; /* 48 8 */ u64 reloc; /* 56 8 */ /* --- cacheline 1 boundary (64 bytes) --- */ u64 (*map_ip)(struct map *, u64); /* 64 8 */ u64 (*unmap_ip)(struct map *, u64); /* 72 8 */ struct dso * dso; /* 80 8 */ refcount_t refcnt; /* 88 4 */ u32 flags; /* 92 4 */ /* size: 96, cachelines: 2, members: 13 */ /* sum members: 92, holes: 1, sum holes: 3 */ /* sum bitfield members: 2 bits, bit holes: 1, sum bit holes: 6 bits */ /* forced alignments: 1 */ /* last cacheline: 32 bytes */ } __attribute__((__aligned__(8))); $ Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lkml.kernel.org/n/tip-g4hxxmraplo7wfjmk384mfsb@git.kernel.orgSigned-off-by: -
Arnaldo Carvalho de Melo authored
Not used anywhere, nuke it. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lkml.kernel.org/n/tip-teqz0eqcw43mnt7i3me44esw@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
We'll use it when doing DSO lookups using dso_ids. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lkml.kernel.org/n/tip-u2nr1oq03o0i29w2ay9jx03s@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
Instead of the 4 fields, a step in the direction of moving this to struct dso. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lkml.kernel.org/n/tip-gp5s1xgxacurmih5d1l94ymy@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
And this patch highlights where these fields are being used: in the sort order where it uses it to compare maps and classify samples taking into account not just the DSO, but those DSO id fields. I think these should be used to differentiate DSOs with the same name but different 'struct dso_id' fields, i.e. these fields should move to 'struct dso' and then be used as part of the key when doing lookups for DSOs, in addition to the DSO name. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lkml.kernel.org/n/tip-8v5isitqy0dup47nnwkpc80f@git.kernel.orgSigned-off-by:
-
Ingo Molnar authored
Merge tag 'perf-core-for-mingo-5.5-20191119' 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: x86/insn: Adrian Hunter: - Add some more Intel instructions to the opcode map: cldemote, encls, enclu, enclv, enqcmd, enqcmds, movdir64b, movdiri, pconfig, tpause, umonitor, umwait, wbnoinvd. - The instruction decoding can be tested using the perf tools' "x86 instruction decoder - new instructions" test as folllows: $ perf test -v "new " 2>&1 | grep -i cldemote Decoded ok: 0f 1c 00 cldemote (%eax) Decoded ok: 0f 1c 05 78 56 34 12 cldemote 0x12345678 Decoded ok: 0f 1c 84 c8 78 56 34 12 cldemote 0x12345678(%eax,%ecx,8) Decoded ok: 0f 1c 00 cldemote (%rax) Decoded ok: 41 0f 1c 00 cldemote (%r8) Decoded ok: 0f 1c 04 25 78 56 34 12 cldemote 0x12345678 Decoded ok: 0f 1c 84 c8 78 56 34 12 cldemote 0x12345678(%rax,%rcx,8) Decoded ok: 41 0f 1c 84 c8 78 56 34 12 cldemote 0x12345678(%r8,%rcx,8) $ perf test -v "new " 2>&1 | grep -i tpause Decoded ok: 66 0f ae f3 tpause %ebx Decoded ok: 66 0f ae f3 tpause %ebx Decoded ok: 66 41 0f ae f0 tpause %r8d callchains: Adrian Hunter: - Fix segfault in thread__resolve_callchain_sample(). perf probe: - Line fixes to show only lines where probes can be used with 'perf probe -L', and when reporting them via 'perf probe -l'. - Support multiprobe events. perf scripts python: Adrian Hunter: - Fix use of TRUE with SQLite < 3.23 in exported-sql-viewer.py. perf maps: - Trim 'struct map' by removing the rb_node member for sorting by map name, as that is only needed for processing kernel maps, and only when classifying symbols by section at load time. Sort them by name using qsort() and do lookups using bsearch() when map_groups__find_by_name() is used. perf parse: Ian Rogers: - Report initial event parsing error, providing a less cryptic message to state that a PMU wasn't found in the system. perf vendor events: James Clark: - Fix commas so that PMU event files for arm64, power8 and power nine become valid JSON. libtraceevent: Konstantin Khlebnikov: - Fix parsing of event %o and %X argument types. Signed-off-by:
Ingo Molnar <mingo@kernel.org>
-
- 18 Nov, 2019 15 commits
-
-
Ian Rogers authored
Record the first event parsing error and report. Implementing feedback from Jiri Olsa: https://lkml.org/lkml/2019/10/28/680 An example error is: $ tools/perf/perf stat -e c/c/ WARNING: multiple event parsing errors event syntax error: 'c/c/' \___ unknown term valid terms: event,filter_rem,filter_opc0,edge,filter_isoc,filter_tid,filter_loc,filter_nc,inv,umask,filter_opc1,tid_en,thresh,filter_all_op,filter_not_nm,filter_state,filter_nm,config,config1,config2,name,period,percore Initial error: event syntax error: 'c/c/' \___ Cannot find PMU `c'. Missing kernel support? Run 'perf list' for a list of valid events Usage: perf stat [<options>] [<command>] -e, --event <event> event selector. use 'perf list' to list available events Signed-off-by:
Ian Rogers <irogers@google.com> Tested-by:
-
Masami Hiramatsu authored
Trace a magic number as immediate value if the target variable is not found at some probe points which is based on one probe event. This feature is good for the case if you trace a source code line with some local variables, which is compiled into several instructions and some of the variables are optimized out on some instructions. Even if so, with this feature, perf probe trace a magic number instead of such disappeared variables and fold those probes on one event. E.g. without this patch: # perf probe -D "pud_page_vaddr pud" Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. p:probe/pud_page_vaddr _text+23480787 pud=%ax:x64 p:probe/pud_page_vaddr _text+23808453 pud=%bp:x64 p:probe/pud_page_vaddr _text+23558082 pud=%ax:x64 p:probe/pud_page_vaddr _text+328373 pud=%r8:x64 p:probe/pud_page_vaddr _text+348448 pud=%bx:x64 p:probe/pud_page_vaddr _text+23816818 pud=%bx:x64 With this patch: # perf probe -D "pud_page_vaddr pud" | head spurious_kernel_fault is blacklisted function, skip it. vmalloc_fault is blacklisted function, skip it. p:probe/pud_page_vaddr _text+23480787 pud=%ax:x64 p:probe/pud_page_vaddr _text+149051 pud=\deade12d:x64 p:probe/pud_page_vaddr _text+23808453 pud=%bp:x64 p:probe/pud_page_vaddr _text+315926 pud=\deade12d:x64 p:probe/pud_page_vaddr _text+23807209 pud=\deade12d:x64 p:probe/pud_page_vaddr _text+23557365 pud=%ax:x64 p:probe/pud_page_vaddr _text+314097 pud=%di:x64 p:probe/pud_page_vaddr _text+314015 pud=\deade12d:x64 p:probe/pud_page_vaddr _text+313893 pud=\deade12d:x64 p:probe/pud_page_vaddr _text+324083 pud=\deade12d:x64 Signed-off-by:
Masami Hiramatsu <mhiramat@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Cc: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Tom Zanussi <tom.zanussi@linux.intel.com> Link: http://lore.kernel.org/lkml/157406476931.24476.6261475888681844285.stgit@devnote2Signed-off-by:
-
Masami Hiramatsu authored
Support DW_AT_const_value for variable assignment instead of location. Note that this requires ftrace supporting immediate value. Signed-off-by:
-
Masami Hiramatsu authored
Support multiprobe event if the event is based on function and lines and kernel supports it. In this case, perf probe creates the first probe with an event, and tries to append following probes on that event, since those probes must be on the same source code line. Before this patch; # perf probe -a vfs_read:18 Added new events: probe:vfs_read_L18 (on vfs_read:18) probe:vfs_read_L18_1 (on vfs_read:18) You can now use it in all perf tools, such as: perf record -e probe:vfs_read_L18_1 -aR sleep 1 # After this patch (on multiprobe supported kernel) # perf probe -a vfs_read:18 Added new events: probe:vfs_read_L18 (on vfs_read:18) probe:vfs_read_L18 (on vfs_read:18) You can now use it in all perf tools, such as: perf record -e probe:vfs_read_L18 -aR sleep 1 # Committer testing: On a kernel that doesn't support multiprobe events, after this patch: # uname -a Linux quaco 5.3.8-200.fc30.x86_64 #1 SMP Tue Oct 29 14:46:22 UTC 2019 x86_64 x86_64 x86_64 GNU/Linux # grep append /sys/kernel/debug/tracing/README be modified by appending '.descending' or '.ascending' to a can be modified by appending any of the following modifiers # # perf probe -a vfs_read:18 Added new events: probe:vfs_read_L18 (on vfs_read:18) probe:vfs_read_L18_1 (on vfs_read:18) You can now use it in all perf tools, such as: perf record -e probe:vfs_read_L18_1 -aR sleep 1 # perf probe -l probe:vfs_read_L18 (on vfs_read:18@fs/read_write.c) probe:vfs_read_L18_1 (on vfs_read:18@fs/read_write.c) # Signed-off-by: -
Masami Hiramatsu authored
Generate event name from function name with line number as <function>_L<line_number>. Note that this is only for the new event which is defined by the line number of function (except for line 0). If there is another event on same line, you have to use "-f" option. In that case, the new event has "_1" suffix. e.g. # perf probe -a kernel_read:2 Added new event: probe:kernel_read_L2 (on kernel_read:2) You can now use it in all perf tools, such as: perf record -e probe:kernel_read_L2 -aR sleep 1 But if we omit the line number or 0th line, it will have no suffix. # perf probe -a kernel_read:0 Added new event: probe:kernel_read (on kernel_read) You can now use it in all perf tools, such as: perf record -e probe:kernel_read -aR sleep 1 probe:kernel_read (on kernel_read@linux-5.0.0/fs/read_write.c) probe:kernel_read_L2 (on kernel_read:2@linux-5.0.0/fs/read_write.c) Signed-off-by: -
Masami Hiramatsu authored
Since perf probe -L shows non representive lines, it can be mislead users where user can put probes. This prevents to show such non representive lines so that user can understand which lines user can probe. # perf probe -L kernel_read <kernel_read@/build/linux-pvZVvI/linux-5.0.0/fs/read_write.c:0> 0 ssize_t kernel_read(struct file *file, void *buf, size_t count, loff_t *pos) { 2 mm_segment_t old_fs; ssize_t result; old_fs = get_fs(); 6 set_fs(get_ds()); /* The cast to a user pointer is valid due to the set_fs() */ 8 result = vfs_read(file, (void __user *)buf, count, pos); 9 set_fs(old_fs); 10 return result; } EXPORT_SYMBOL(kernel_read); Committer testing: Before: # perf probe -L kernel_read <kernel_read@/usr/src/debug/kernel-5.3.fc30/linux-5.3.8-200.fc30.x86_64/fs/read_write.c:0> 0 ssize_t kernel_read(struct file *file, void *buf, size_t count, loff_t *pos) 1 { 2 mm_segment_t old_fs; 3 ssize_t result; 5 old_fs = get_fs(); 6 set_fs(KERNEL_DS); /* The cast to a user pointer is valid due to the set_fs() */ 8 result = vfs_read(file, (void __user *)buf, count, pos); 9 set_fs(old_fs); 10 return result; } EXPORT_SYMBOL(kernel_read); # See the 1, 3, 5 lines? They shouldn't be there, after this patch: # perf probe -L kernel_read <kernel_read@/usr/src/debug/kernel-5.3.fc30/linux-5.3.8-200.fc30.x86_64/fs/read_write.c:0> 0 ssize_t kernel_read(struct file *file, void *buf, size_t count, loff_t *pos) { 2 mm_segment_t old_fs; ssize_t result; old_fs = get_fs(); 6 set_fs(KERNEL_DS); /* The cast to a user pointer is valid due to the set_fs() */ 8 result = vfs_read(file, (void __user *)buf, count, pos); 9 set_fs(old_fs); 10 return result; } EXPORT_SYMBOL(kernel_read); # Signed-off-by: -
Masami Hiramatsu authored
Verify user given probe line is a representive line (which doesn't share the address with other lines or the line is the least line among the lines which shares same address), and if not, it shows what is the representive line. Without this fix, user can put a probe on the lines which is not a a representive line. But since this is not a representive line, perf probe -l shows a representive line number instead of user given line number. e.g. (put kernel_read:3, but listed as kernel_read:2) # perf probe -a kernel_read:3 Added new event: probe:kernel_read (on kernel_read:3) You can now use it in all perf tools, such as: perf record -e probe:kernel_read -aR sleep 1 # perf probe -l probe:kernel_read (on kernel_read:2@linux-5.0.0/fs/read_write.c) With this fix, perf probe doesn't allow user to put a probe on a representive line, and tell what is the representive line. # perf probe -a kernel_read:3 This line is sharing the addrees with other lines. Please try to probe at kernel_read:2 instead. Error: Failed to add events. Signed-off-by: -
Masami Hiramatsu authored
The dwarf_getsrc_die() can return the line which is not a statement nor the least line number among the lines which shares same address. This can lead perf probe --list shows incorrect line number for probed address. To fix this, this introduces cu_getsrc_die() which returns only a statement line and which is the least line number (we call it the representive line for an address), and use it in cu_find_lineinfo(). Also, if the given address is the entry address of a real function, cu_find_lineinfo() returns the function declared line number instead of the start line number of the function body. For example, without this change perf probe -l shows incorrect line as below. # perf probe -a kernel_read:2 Added new event: probe:kernel_read (on kernel_read:2) You can now use it in all perf tools, such as: perf record -e probe:kernel_read -aR sleep 1 # perf probe -l probe:kernel_read (on kernel_read:1@linux-5.0.0/fs/read_write.c) With this fix, it shows correct line number as below; # perf probe -l probe:kernel_read (on kernel_read:2@linux-5.0.0/fs/read_write.c) Reported-by: -
Adrian Hunter authored
Add to the opcode map the following instructions: cldemote tpause umonitor umwait movdiri movdir64b enqcmd enqcmds encls enclu enclv pconfig wbnoinvd For information about the instructions, refer Intel SDM May 2019 (325462-070US) and Intel Architecture Instruction Set Extensions May 2019 (319433-037). The instruction decoding can be tested using the perf tools' "x86 instruction decoder - new instructions" test as folllows: $ perf test -v "new " 2>&1 | grep -i cldemote Decoded ok: 0f 1c 00 cldemote (%eax) Decoded ok: 0f 1c 05 78 56 34 12 cldemote 0x12345678 Decoded ok: 0f 1c 84 c8 78 56 34 12 cldemote 0x12345678(%eax,%ecx,8) Decoded ok: 0f 1c 00 cldemote (%rax) Decoded ok: 41 0f 1c 00 cldemote (%r8) Decoded ok: 0f 1c 04 25 78 56 34 12 cldemote 0x12345678 Decoded ok: 0f 1c 84 c8 78 56 34 12 cldemote 0x12345678(%rax,%rcx,8) Decoded ok: 41 0f 1c 84 c8 78 56 34 12 cldemote 0x12345678(%r8,%rcx,8) $ perf test -v "new " 2>&1 | grep -i tpause Decoded ok: 66 0f ae f3 tpause %ebx Decoded ok: 66 0f ae f3 tpause %ebx Decoded ok: 66 41 0f ae f0 tpause %r8d $ perf test -v "new " 2>&1 | grep -i umonitor Decoded ok: 67 f3 0f ae f0 umonitor %ax Decoded ok: f3 0f ae f0 umonitor %eax Decoded ok: 67 f3 0f ae f0 umonitor %eax Decoded ok: f3 0f ae f0 umonitor %rax Decoded ok: 67 f3 41 0f ae f0 umonitor %r8d $ perf test -v "new " 2>&1 | grep -i umwait Decoded ok: f2 0f ae f0 umwait %eax Decoded ok: f2 0f ae f0 umwait %eax Decoded ok: f2 41 0f ae f0 umwait %r8d $ perf test -v "new " 2>&1 | grep -i movdiri Decoded ok: 0f 38 f9 03 movdiri %eax,(%ebx) Decoded ok: 0f 38 f9 88 78 56 34 12 movdiri %ecx,0x12345678(%eax) Decoded ok: 48 0f 38 f9 03 movdiri %rax,(%rbx) Decoded ok: 48 0f 38 f9 88 78 56 34 12 movdiri %rcx,0x12345678(%rax) $ perf test -v "new " 2>&1 | grep -i movdir64b Decoded ok: 66 0f 38 f8 18 movdir64b (%eax),%ebx Decoded ok: 66 0f 38 f8 88 78 56 34 12 movdir64b 0x12345678(%eax),%ecx Decoded ok: 67 66 0f 38 f8 1c movdir64b (%si),%bx Decoded ok: 67 66 0f 38 f8 8c 34 12 movdir64b 0x1234(%si),%cx Decoded ok: 66 0f 38 f8 18 movdir64b (%rax),%rbx Decoded ok: 66 0f 38 f8 88 78 56 34 12 movdir64b 0x12345678(%rax),%rcx Decoded ok: 67 66 0f 38 f8 18 movdir64b (%eax),%ebx Decoded ok: 67 66 0f 38 f8 88 78 56 34 12 movdir64b 0x12345678(%eax),%ecx $ perf test -v "new " 2>&1 | grep -i enqcmd Decoded ok: f2 0f 38 f8 18 enqcmd (%eax),%ebx Decoded ok: f2 0f 38 f8 88 78 56 34 12 enqcmd 0x12345678(%eax),%ecx Decoded ok: 67 f2 0f 38 f8 1c enqcmd (%si),%bx Decoded ok: 67 f2 0f 38 f8 8c 34 12 enqcmd 0x1234(%si),%cx Decoded ok: f3 0f 38 f8 18 enqcmds (%eax),%ebx Decoded ok: f3 0f 38 f8 88 78 56 34 12 enqcmds 0x12345678(%eax),%ecx Decoded ok: 67 f3 0f 38 f8 1c enqcmds (%si),%bx Decoded ok: 67 f3 0f 38 f8 8c 34 12 enqcmds 0x1234(%si),%cx Decoded ok: f2 0f 38 f8 18 enqcmd (%rax),%rbx Decoded ok: f2 0f 38 f8 88 78 56 34 12 enqcmd 0x12345678(%rax),%rcx Decoded ok: 67 f2 0f 38 f8 18 enqcmd (%eax),%ebx Decoded ok: 67 f2 0f 38 f8 88 78 56 34 12 enqcmd 0x12345678(%eax),%ecx Decoded ok: f3 0f 38 f8 18 enqcmds (%rax),%rbx Decoded ok: f3 0f 38 f8 88 78 56 34 12 enqcmds 0x12345678(%rax),%rcx Decoded ok: 67 f3 0f 38 f8 18 enqcmds (%eax),%ebx Decoded ok: 67 f3 0f 38 f8 88 78 56 34 12 enqcmds 0x12345678(%eax),%ecx $ perf test -v "new " 2>&1 | grep -i enqcmds Decoded ok: f3 0f 38 f8 18 enqcmds (%eax),%ebx Decoded ok: f3 0f 38 f8 88 78 56 34 12 enqcmds 0x12345678(%eax),%ecx Decoded ok: 67 f3 0f 38 f8 1c enqcmds (%si),%bx Decoded ok: 67 f3 0f 38 f8 8c 34 12 enqcmds 0x1234(%si),%cx Decoded ok: f3 0f 38 f8 18 enqcmds (%rax),%rbx Decoded ok: f3 0f 38 f8 88 78 56 34 12 enqcmds 0x12345678(%rax),%rcx Decoded ok: 67 f3 0f 38 f8 18 enqcmds (%eax),%ebx Decoded ok: 67 f3 0f 38 f8 88 78 56 34 12 enqcmds 0x12345678(%eax),%ecx $ perf test -v "new " 2>&1 | grep -i encls Decoded ok: 0f 01 cf encls Decoded ok: 0f 01 cf encls $ perf test -v "new " 2>&1 | grep -i enclu Decoded ok: 0f 01 d7 enclu Decoded ok: 0f 01 d7 enclu $ perf test -v "new " 2>&1 | grep -i enclv Decoded ok: 0f 01 c0 enclv Decoded ok: 0f 01 c0 enclv $ perf test -v "new " 2>&1 | grep -i pconfig Decoded ok: 0f 01 c5 pconfig Decoded ok: 0f 01 c5 pconfig $ perf test -v "new " 2>&1 | grep -i wbnoinvd Decoded ok: f3 0f 09 wbnoinvd Decoded ok: f3 0f 09 wbnoinvd Signed-off-by:Andi Kleen <ak@linux.intel.com> Acked-by:
-
Adrian Hunter authored
Add to the "x86 instruction decoder - new instructions" test the following instructions: cldemote tpause umonitor umwait movdiri movdir64b enqcmd enqcmds encls enclu enclv pconfig wbnoinvd For information about the instructions, refer Intel SDM May 2019 (325462-070US) and Intel Architecture Instruction Set Extensions May 2019 (319433-037). Signed-off-by:
-
Arnaldo Carvalho de Melo authored
So we start with: $ pahole -C map ~/bin/perf struct map { union { struct rb_node rb_node __attribute__((__aligned__(8))); /* 0 24 */ struct list_head node; /* 0 16 */ } __attribute__((__aligned__(8))); /* 0 24 */ u64 start; /* 24 8 */ u64 end; /* 32 8 */ _Bool erange_warned:1; /* 40: 0 1 */ _Bool priv:1; /* 40: 1 1 */ /* XXX 6 bits hole, try to pack */ /* XXX 3 bytes hole, try to pack */ u32 prot; /* 44 4 */ u32 flags; /* 48 4 */ /* XXX 4 bytes hole, try to pack */ u64 pgoff; /* 56 8 */ /* --- cacheline 1 boundary (64 bytes) --- */ u64 reloc; /* 64 8 */ u32 maj; /* 72 4 */ u32 min; /* 76 4 */ u64 ino; /* 80 8 */ u64 ino_generation; /* 88 8 */ u64 (*map_ip)(struct map *, u64); /* 96 8 */ u64 (*unmap_ip)(struct map *, u64); /* 104 8 */ struct dso * dso; /* 112 8 */ refcount_t refcnt; /* 120 4 */ /* size: 128, cachelines: 2, members: 17 */ /* sum members: 116, holes: 2, sum holes: 7 */ /* sum bitfield members: 2 bits, bit holes: 1, sum bit holes: 6 bits */ /* padding: 4 */ /* forced alignments: 1 */ } __attribute__((__aligned__(8))); $ and 'flags' is seldom used when printing details about the map or with the "cacheline" sort order, we can move them it to the second cacheline, that will allow combining it with 'refcnt', that is only four bytes: $ pahole -C map ~/bin/perf struct map { union { struct rb_node rb_node __attribute__((__aligned__(8))); /* 0 24 */ struct list_head node; /* 0 16 */ } __attribute__((__aligned__(8))); /* 0 24 */ u64 start; /* 24 8 */ u64 end; /* 32 8 */ _Bool erange_warned:1; /* 40: 0 1 */ _Bool priv:1; /* 40: 1 1 */ /* XXX 6 bits hole, try to pack */ /* XXX 3 bytes hole, try to pack */ u32 prot; /* 44 4 */ u64 pgoff; /* 48 8 */ u64 reloc; /* 56 8 */ /* --- cacheline 1 boundary (64 bytes) --- */ u32 maj; /* 64 4 */ u32 min; /* 68 4 */ u64 ino; /* 72 8 */ u64 ino_generation; /* 80 8 */ u64 (*map_ip)(struct map *, u64); /* 88 8 */ u64 (*unmap_ip)(struct map *, u64); /* 96 8 */ struct dso * dso; /* 104 8 */ refcount_t refcnt; /* 112 4 */ u32 flags; /* 116 4 */ /* size: 120, cachelines: 2, members: 17 */ /* sum members: 116, holes: 1, sum holes: 3 */ /* sum bitfield members: 2 bits, bit holes: 1, sum bit holes: 6 bits */ /* forced alignments: 1 */ /* last cacheline: 56 bytes */ } __attribute__((__aligned__(8))); $ Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lkml.kernel.org/n/tip-2cdw3zlw1mkamaf7nqtdlxfi@git.kernel.orgSigned-off-by: -
Arnaldo Carvalho de Melo authored
The map->priv and map->erange_warned are seldom used, the first only in tests/vmlinux-kallsyms.c, the later only when hist_entry__inc_addr_samples() returns -ERANGE in 'perf top', which are really rare occasions, so make them a bool bitfield. This will open up space for other members on the first cacheline. $ pahole -C map ~/bin/perf struct map { union { struct rb_node rb_node __attribute__((__aligned__(8))); /* 0 24 */ struct list_head node; /* 0 16 */ } __attribute__((__aligned__(8))); /* 0 24 */ u64 start; /* 24 8 */ u64 end; /* 32 8 */ _Bool erange_warned:1; /* 40: 0 1 */ _Bool priv:1; /* 40: 1 1 */ /* XXX 6 bits hole, try to pack */ /* XXX 3 bytes hole, try to pack */ u32 prot; /* 44 4 */ u32 flags; /* 48 4 */ /* XXX 4 bytes hole, try to pack */ u64 pgoff; /* 56 8 */ /* --- cacheline 1 boundary (64 bytes) --- */ u64 reloc; /* 64 8 */ u32 maj; /* 72 4 */ u32 min; /* 76 4 */ u64 ino; /* 80 8 */ u64 ino_generation; /* 88 8 */ u64 (*map_ip)(struct map *, u64); /* 96 8 */ u64 (*unmap_ip)(struct map *, u64); /* 104 8 */ struct dso * dso; /* 112 8 */ refcount_t refcnt; /* 120 4 */ /* size: 128, cachelines: 2, members: 17 */ /* sum members: 116, holes: 2, sum holes: 7 */ /* sum bitfield members: 2 bits, bit holes: 1, sum bit holes: 6 bits */ /* padding: 4 */ /* forced alignments: 1 */ } __attribute__((__aligned__(8))); $ Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lkml.kernel.org/n/tip-g5545pcq4ff0wr17tfb1piqt@git.kernel.orgSigned-off-by: -
Konstantin Khlebnikov authored
Add missing "%o" and "%X". Ext4 events use "%o" for printing i_mode. Signed-off-by:
Konstantin Khlebnikov <khlebnikov@yandex-team.ru> Reviewed-by:
-
Adrian Hunter authored
Do not dereference 'chain' when it is NULL. $ perf record -e intel_pt//u -e branch-misses:u uname $ perf report --itrace=l --branch-history perf: Segmentation fault Fixes: e9024d51 ("perf callchain: Honour the ordering of PERF_CONTEXT_{USER,KERNEL,etc}") Signed-off-by:
-
Arnaldo Carvalho de Melo authored
There are still lots of lookups by name, even if just when loading vmlinux, till that code is studied to figure out if its possible to do away with those map lookup by names, provide a way to sort it using libc's qsort/bsearch. Doing it at the first lookup defers the sorting a bit, and as the code stands now, is never done for user maps, just for the kernel ones. # perf probe -l # perf probe -x ~/bin/perf -L __map_groups__find_by_name <__map_groups__find_by_name@/home/acme/git/perf/tools/perf/util/symbol.c:0> 0 static struct map *__map_groups__find_by_name(struct map_groups *mg, const char *name) 1 { struct map **mapp; 4 if (mg->maps_by_name == NULL && 5 map__groups__sort_by_name_from_rbtree(mg)) 6 return NULL; 8 mapp = bsearch(name, mg->maps_by_name, mg->nr_maps, sizeof(*mapp), map__strcmp_name); 9 if (mapp) 10 return *mapp; 11 return NULL; 12 } struct map *map_groups__find_by_name(struct map_groups *mg, const char *name) { # perf probe -x ~/bin/perf 'found=__map_groups__find_by_name:10 name:string' Added new event: probe_perf:found (on __map_groups__find_by_name:10 in /home/acme/bin/perf with name:string) You can now use it in all perf tools, such as: perf record -e probe_perf:found -aR sleep 1 # # perf probe -x ~/bin/perf -L map_groups__find_by_name <map_groups__find_by_name@/home/acme/git/perf/tools/perf/util/symbol.c:0> 0 struct map *map_groups__find_by_name(struct map_groups *mg, const char *name) 1 { 2 struct maps *maps = &mg->maps; struct map *map; 5 down_read(&maps->lock); 7 if (mg->last_search_by_name && strcmp(mg->last_search_by_name->dso->short_name, name) == 0) { 8 map = mg->last_search_by_name; 9 goto out_unlock; } /* * If we have mg->maps_by_name, then the name isn't in the rbtree, * as mg->maps_by_name mirrors the rbtree when lookups by name are * made. */ 16 map = __map_groups__find_by_name(mg, name); 17 if (map || mg->maps_by_name != NULL) 18 goto out_unlock; /* Fallback to traversing the rbtree... */ 21 maps__for_each_entry(maps, map) 22 if (strcmp(map->dso->short_name, name) == 0) { 23 mg->last_search_by_name = map; 24 goto out_unlock; } 27 map = NULL; out_unlock: 30 up_read(&maps->lock); 31 return map; 32 } int dso__load_vmlinux(struct dso *dso, struct map *map, const char *vmlinux, bool vmlinux_allocated) # perf probe -x ~/bin/perf 'fallback=map_groups__find_by_name:21 name:string' Added new events: probe_perf:fallback (on map_groups__find_by_name:21 in /home/acme/bin/perf with name:string) probe_perf:fallback_1 (on map_groups__find_by_name:21 in /home/acme/bin/perf with name:string) You can now use it in all perf tools, such as: perf record -e probe_perf:fallback_1 -aR sleep 1 # # perf probe -l probe_perf:fallback (on map_groups__find_by_name:21@util/symbol.c in /home/acme/bin/perf with name_string) probe_perf:fallback_1 (on map_groups__find_by_name:21@util/symbol.c in /home/acme/bin/perf with name_string) probe_perf:found (on __map_groups__find_by_name:10@util/symbol.c in /home/acme/bin/perf with name_string) # # perf stat -e probe_perf:* Now run 'perf top' in another term and then, after a while, stop 'perf stat': Furthermore, if we ask for interval printing, we can see that that is done just at the start of the workload: # perf stat -I1000 -e probe_perf:* # time counts unit events 1.000319513 0 probe_perf:found 1.000319513 0 probe_perf:fallback_1 1.000319513 0 probe_perf:fallback 2.001868092 23,251 probe_perf:found 2.001868092 0 probe_perf:fallback_1 2.001868092 0 probe_perf:fallback 3.002901597 0 probe_perf:found 3.002901597 0 probe_perf:fallback_1 3.002901597 0 probe_perf:fallback 4.003358591 0 probe_perf:found 4.003358591 0 probe_perf:fallback_1 4.003358591 0 probe_perf:fallback ^C # Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lkml.kernel.org/n/tip-c5lmbyr14x448rcfii7y6t3k@git.kernel.orgSigned-off-by:
-
