- 10 Jul, 2019 21 commits
-
-
Adrian Hunter authored
Export switch events to a new table 'context_switches' and create a view 'context_switches_view'. The table and view will show automatically in the exported-sql-viewer.py script. If the table ends up empty, then it and the view are dropped. Signed-off-by:
Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Link: http://lkml.kernel.org/r/20190710085810.1650-22-adrian.hunter@intel.comSigned-off-by:
Arnaldo Carvalho de Melo <acme@redhat.com>
-
Adrian Hunter authored
Export switch events to a new table 'context_switches' and create a view 'context_switches_view'. The table and view will show automatically in the exported-sql-viewer.py script. If the table ends up empty, then it and the view are dropped. Committer testing: Use the exported-sql-viewer.py and look at "Tables" -> "context_switches": id machine_id time cpu thread_out_id comm_out_id thread_in_id comm_in_id flags 1 1 187836111885918 7 1 1 2 2 3 2 1 187836111889369 7 1 1 2 2 0 3 1 187836112464618 7 2 3 1 1 1 4 1 187836112465511 7 2 3 1 1 0 Signed-off-by:
-
Adrian Hunter authored
Export details of switch events including the threads and their current comms. Signed-off-by:
-
Adrian Hunter authored
In preparation for exporting switch events, factor out db_export__threads(). Signed-off-by:
-
Adrian Hunter authored
Add scripting operation process_switch() to process switch events. Signed-off-by:
-
Adrian Hunter authored
If the new 'has_calls' column is present, use it with the call graph and call tree to select only comms that have calls. Committer testing: Just started the exported-sql-view.py and accessed all the reports, no backtraces. Signed-off-by:
-
Adrian Hunter authored
Remove redundant semi-colons added inadvertently. Signed-off-by:
-
Adrian Hunter authored
Now that a thread's current comm is exported, it shows up in the call graph and call tree even if it has no calls. That can happen because the calls are recorded against the main thread's initial comm. Add a table column to make it easy for the exported-sql-viewer.py script to select only comms with calls. Committer testing: $ rm -f simple-retpoline.db $ sudo ~acme/bin/perf script -i simple-retpoline.perf.data --itrace=be -s ~/libexec/perf-core/scripts/python/export-to-sqlite.py simple-retpoline.db branches calls 2019-07-10 12:25:33.200529 Creating database ... 2019-07-10 12:25:33.211548 Writing records... 2019-07-10 12:25:33.549630 Adding indexes 2019-07-10 12:25:33.560715 Dropping unused tables 2019-07-10 12:25:33.580201 Done $ sha256sum tools/perf/scripts/python/export-to-sqlite.py ~/libexec/perf-core/scripts/python/export-to-sqlite.py 2922b642c392004dffa1d8789296478c85904623f5895bcb9b6cbf33e3ca999f tools/perf/scripts/python/export-to-sqlite.py 2922b642c392004dffa1d8789296478c85904623f5895bcb9b6cbf33e3ca999f /home/acme/libexec/perf-core/scripts/python/export-to-sqlite.py $ $ sqlite3 simple-retpoline.db SQLite version 3.26.0 2018-12-01 12:34:55 Enter ".help" for usage hints. sqlite> .schema comms CREATE TABLE comms (id integer NOT NULL PRIMARY KEY,comm varchar(16),c_thread_id bigint,c_time bigint,exec_flag boolean, has_calls boolean); sqlite> select id,has_calls from comms; 0|1 1|1 sqlite> select distinct comm_id from calls; 0 1 sqlite> Signed-off-by:
-
Adrian Hunter authored
Now that a thread's current comm is exported, it shows up in the call graph and call tree even if it has no calls. That can happen because the calls are recorded against the main thread's initial comm. Add a table column to make it easy for the exported-sql-viewer.py script to select only comms with calls. Committer notes: Running the export-to-sqlite.py worked without warnings and using the exported-sql-viewer.py worked as before. Signed-off-by:
-
Adrian Hunter authored
Currently, the initial comm of the main thread is exported. Export also a thread's current comm. That better supports the tracing of multi-threaded applications that set different comms for different threads to make it easier to distinguish them. Signed-off-by:
-
Adrian Hunter authored
In preparation for exporting the current comm for a thread, factor out db_export__comm(). Signed-off-by:
-
Adrian Hunter authored
Add table columns for thread id, comm start time and exec flag. Signed-off-by:
-
Adrian Hunter authored
Add table columns for thread id, comm start time and exec flag. Signed-off-by:
-
Adrian Hunter authored
In preparation for exporting the current comm for a thread, export comm thread id, start time and exec flag. Signed-off-by:
-
Adrian Hunter authored
Fix a white space issue in db_export__sample() Signed-off-by:
-
Adrian Hunter authored
Move call to db_export__comm_thread() from db_export__thread() into db_export__sample() because it makes the code easier to understand, and add explanatory comments. Signed-off-by:
-
Adrian Hunter authored
Export comm before exporting the non-main thread because db_export__thread() also exports the comm_thread. Signed-off-by:
-
Adrian Hunter authored
Export main_thread in db_export__sample() because it makes the code easier to understand, and prepares db_export__thread() for further simplification. Signed-off-by:
-
Adrian Hunter authored
Calls to db_export__thread() already have main_thread so there is no reason to get it again, instead pass it as a parameter. Note that one difference in this approach is that the main thread is not created if it does not exist. It is better if it is not created because: - If main_thread is being traced it will have been created already. - If it is not being traced, there will be no other information about it, and it will never get deleted because there will be no EXIT event. Signed-off-by: -
Adrian Hunter authored
Rename db_export__comm() to db_export__exec_comm() to better reflect what it does and add explanatory comments. Signed-off-by:
-
Adrian Hunter authored
db_export__deferred() deferred the export of comms if the comm string had not been "set" (changed from :<pid>) however that problem was fixed a long time ago by commit e803cf97 ("perf record: Synthesize COMM event for a command line workload"), so get rid of db_export__deferred(). Signed-off-by:
-
- 09 Jul, 2019 19 commits
-
-
Arnaldo Carvalho de Melo authored
Circa v5.2 this started to fail: # perf trace -e /wb/augmented_raw_syscalls.o event syntax error: '/wb/augmented_raw_syscalls.o' \___ Operation not permitted (add -v to see detail) Run 'perf list' for a list of valid events Usage: perf trace [<options>] [<command>] or: perf trace [<options>] -- <command> [<options>] or: perf trace record [<options>] [<command>] or: perf trace record [<options>] -- <command> [<options>] -e, --event <event> event/syscall selector. use 'perf list' to list available events # In verbose mode we some -EPERM when creating a BPF map: # perf trace -v -e /wb/augmented_raw_syscalls.o <SNIP> libbpf: failed to create map (name: '__augmented_syscalls__'): Operation not permitted libbpf: failed to load object '/wb/augmented_raw_syscalls.o' bpf: load objects failed: err=-1: (Operation not permitted) event syntax error: '/wb/augmented_raw_syscalls.o' \___ Operation not permitted (add -v to see detail) Run 'perf list' for a list of valid events Usage: perf trace [<options>] [<command>] or: perf trace [<options>] -- <command> [<options>] or: perf trace record [<options>] [<command>] or: perf trace record [<options>] -- <command> [<options>] -e, --event <event> event/syscall selector. use 'perf list' to list available events # If we bumped 'ulimit -l 128' to get it from the 64k default to double that, it worked, so use the recently added rlimit__bump_memlock() helper: # perf trace -e /wb/augmented_raw_syscalls.o -e open*,*sleep sleep 1 0.000 ( 0.007 ms): sleep/28042 openat(dfd: CWD, filename: "/etc/ld.so.cache", flags: RDONLY|CLOEXEC) = 3 0.022 ( 0.004 ms): sleep/28042 openat(dfd: CWD, filename: "/lib64/libc.so.6", flags: RDONLY|CLOEXEC) = 3 0.201 ( 0.007 ms): sleep/28042 openat(dfd: CWD, filename: "", flags: RDONLY|CLOEXEC) = 3 0.241 (1000.421 ms): sleep/28042 nanosleep(rqtp: 0x7ffd6c3e6ed0) = 0 # Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lkml.kernel.org/n/tip-j6f2ioa6hj9dinzpjvlhcjoc@git.kernel.orgSigned-off-by: -
Arnaldo Carvalho de Melo authored
I noticed that the 'perf test bpf' was failing: # perf test bpf 41: BPF filter : 41.1: Basic BPF filtering : Skip 41.2: BPF pinning : Skip 41.3: BPF prologue generation : Skip 41.4: BPF relocation checker : Skip # ulimit -l 64 # Using verbose mode we get just a line bout -EPERF being returned from libbpf's bpf_load_program_xattr(), that ends up being used in 'perf test bpf' initial program loading capability query: Missing basic BPF support, skip this test: Operation not permitted Not that informative, but on a separate problem when creating BPF maps bumping rlimit(MEMLOCK) helped, so I tried it here as well, works: # ulimit -l 128 # perf test bpf 41: BPF filter : 41.1: Basic BPF filtering : Ok 41.2: BPF pinning : Ok 41.3: BPF prologue generation : Ok 41.4: BPF relocation checker : Ok # So use the recently added rlimit__bump_memlock() helper: # ulimit -l 64 # perf test bpf 41: BPF filter : 41.1: Basic BPF filtering : Ok 41.2: BPF pinning : Ok 41.3: BPF prologue generation : Ok 41.4: BPF relocation checker : Ok # ulimit -l 64 # I.e. the bumping of memlock is restricted to the 'perf test' instance, not changing the global value. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lkml.kernel.org/n/tip-b9fubkhr4jm192lu7y8hgjvo@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
Just like the BPF guys did when faced with failures with map creation, etc, i.e. their solution is: tools/testing/selftests/bpf/bpf_rlimit.h For perf use this function in 'perf test' and in 'perf trace'. Make it bump to 4 times the current value, if it fails twice the current value and if it still fails, warn that things like BPF map creation may fail, to help in diagnosing the problem. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lkml.kernel.org/n/tip-muvqef2i7n6pzqbmu7tn2d2y@git.kernel.orgSigned-off-by:
-
Leo Yan authored
Based on the following report from Smatch, fix the potential NULL pointer dereference check. tools/perf/util/intel-pt.c:3200 intel_pt_process_auxtrace_info() error: we previously assumed 'session->itrace_synth_opts' could be null (see line 3196) tools/perf/util/intel-pt.c:3206 intel_pt_process_auxtrace_info() warn: variable dereferenced before check 'session->itrace_synth_opts' (see line 3200) tools/perf/util/intel-pt.c 3196 if (session->itrace_synth_opts && session->itrace_synth_opts->set) { 3197 pt->synth_opts = *session->itrace_synth_opts; 3198 } else { 3199 itrace_synth_opts__set_default(&pt->synth_opts, 3200 session->itrace_synth_opts->default_no_sample); ^^^^^^^^^^^^^^^^^^^^^^^^^^ 3201 if (!session->itrace_synth_opts->default_no_sample && 3202 !session->itrace_synth_opts->inject) { 3203 pt->synth_opts.branches = false; 3204 pt->synth_opts.callchain = true; 3205 } 3206 if (session->itrace_synth_opts) ^^^^^^^^^^^^^^^^^^^^^^^^^^ 3207 pt->synth_opts.thread_stack = 3208 session->itrace_synth_opts->thread_stack; 3209 } 'session->itrace_synth_opts' is impossible to be a NULL pointer in intel_pt_process_auxtrace_info(), thus this patch removes the NULL test for 'session->itrace_synth_opts'. Signed-off-by:Leo Yan <leo.yan@linaro.org> Acked-by:
-
Leo Yan authored
Based on the following report from Smatch, fix the potential NULL pointer dereference check. tools/perf/util/intel-bts.c:898 intel_bts_process_auxtrace_info() error: we previously assumed 'session->itrace_synth_opts' could be null (see line 894) tools/perf/util/intel-bts.c:899 intel_bts_process_auxtrace_info() warn: variable dereferenced before check 'session->itrace_synth_opts' (see line 898) tools/perf/util/intel-bts.c 894 if (session->itrace_synth_opts && session->itrace_synth_opts->set) { 895 bts->synth_opts = *session->itrace_synth_opts; 896 } else { 897 itrace_synth_opts__set_default(&bts->synth_opts, 898 session->itrace_synth_opts->default_no_sample); ^^^^^^^^^^^^^^^^^^^^^^^^^^ 899 if (session->itrace_synth_opts) ^^^^^^^^^^^^^^^^^^^^^^^^^^ 900 bts->synth_opts.thread_stack = 901 session->itrace_synth_opts->thread_stack; 902 } 'session->itrace_synth_opts' is impossible to be a NULL pointer in intel_bts_process_auxtrace_info(), thus this patch removes the NULL test for 'session->itrace_synth_opts'. Signed-off-by: -
Song Liu authored
In pipe mode, session->header.env.arch is not populated until the events are processed. Therefore, the following command crashes: perf record -o - | perf script (gdb) bt It fails when we try to compare env.arch against uts.machine: if (!strcmp(uts.machine, session->header.env.arch) || (!strcmp(uts.machine, "x86_64") && !strcmp(session->header.env.arch, "i386"))) native_arch = true; In pipe mode, it is tricky to find env.arch at this stage. To keep it simple, let's just assume native_arch is always true for pipe mode. Reported-by:David Carrillo Cisneros <davidca@fb.com> Signed-off-by:
Song Liu <songliubraving@fb.com> Tested-by:
-
Adrian Hunter authored
Drop power_events_view before its dependent tables. SQLite does not seem to mind but the fix was needed for PostgreSQL (export-to-postgresql.py script), so do the same fix for the SQLite. It is more logical and keeps the 2 scripts following the same approach. Signed-off-by:
-
Adrian Hunter authored
PostgreSQL can error if power_events_view is not dropped before its dependent tables e.g. Exception: Query failed: ERROR: cannot drop table mwait because other objects depend on it DETAIL: view power_events_view depends on table mwait Signed-off-by:
-
Leo Yan authored
Based on the following report from Smatch, fix the potential NULL pointer dereference check. tools/perf/ui/browsers/hists.c:641 hist_browser__run() error: we previously assumed 'hbt' could be null (see line 625) tools/perf/ui/browsers/hists.c:3088 perf_evsel__hists_browse() error: we previously assumed 'browser->he_selection' could be null (see line 2902) tools/perf/ui/browsers/hists.c:3272 perf_evsel_menu__run() error: we previously assumed 'hbt' could be null (see line 3260) This patch firstly validating the pointers before access them, so can fix potential NULL pointer dereference. Signed-off-by:
Jiri Olsa <jolsa@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Mathieu Poirier <mathieu.poirier@linaro.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: linux-arm-kernel@lists.infradead.org Link: http://lkml.kernel.org/r/20190708143937.7722-2-leo.yan@linaro.orgSigned-off-by:
-
Leo Yan authored
tool Based on the following report from Smatch, fix the potential NULL pointer dereference check. tools/perf/util/cs-etm.c:2545 cs_etm__process_auxtrace_info() error: we previously assumed 'session->itrace_synth_opts' could be null (see line 2541) tools/perf/util/cs-etm.c 2541 if (session->itrace_synth_opts && session->itrace_synth_opts->set) { 2542 etm->synth_opts = *session->itrace_synth_opts; 2543 } else { 2544 itrace_synth_opts__set_default(&etm->synth_opts, 2545 session->itrace_synth_opts->default_no_sample); ^^^^^^^^^^^^^^^^^^^^^^^^^^ 2546 etm->synth_opts.callchain = false; 2547 } 'session->itrace_synth_opts' is impossible to be a NULL pointer in cs_etm__process_auxtrace_info(), thus this patch removes the NULL test for 'session->itrace_synth_opts'. Signed-off-by:Mathieu Poirier <mathieu.poirier@linaro.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: linux-arm-kernel@lists.infradead.org Link: http://lkml.kernel.org/r/20190708143937.7722-5-leo.yan@linaro.orgSigned-off-by:
-
Luke Mujica authored
Remove the 'error' variable because it is declared but not used in parse-events.y or in the generated parse-events.c. Signed-off-by:
Luke Mujica <lukemujica@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/20190703222509.109616-2-lukemujica@google.comSigned-off-by:
-
Luke Mujica authored
Remove the 'int i' because it is declared but not used in parse-events.y or in the generated parse-events.c. Signed-off-by:
-
Arnaldo Carvalho de Melo authored
So that at the end each of the entries have its list node struct cleared and the egroup list head ends emptied. 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-dxzj1ah350fy9ec0xbhb15b6@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
To allow for destructors to check if they're operating on a object still in a list, and to avoid going from use after free list entries into still valid, or even also other already removed from list entries. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lkml.kernel.org/n/tip-deh17ub44atyox3j90e6rksu@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
In places where the equivalent was already being done, i.e.: free(a); a = NULL; And in placs where struct members are being freed so that if we have some erroneous reference to its struct, then accesses to freed members will result in segfaults, which we can detect faster than use after free to areas that may still have something seemingly valid. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lkml.kernel.org/n/tip-jatyoofo5boc1bsvoig6bb6i@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
Eroding a bit more the tools/perf/util/util.h hodpodge header. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lkml.kernel.org/n/tip-natazosyn9rwjka25tvcnyi0@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
And in a separate header, so that we erode util.h a bit more. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lkml.kernel.org/n/tip-xpzvuu9d0gei9jl9bkzgobln@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
Out of util.h, to reduce its scope, and since we have a namespaces.h header, much better to have it there, where it is related to. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lkml.kernel.org/n/tip-zlu81bbtccuzygh7m8nmgybc@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
Part of the erosion of util/util.h, that will lose its include stdlib.h, we need to add it to places where it is needed but was getting it indirectly. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lkml.kernel.org/n/tip-1imnqezw99ahc07fjeb51qby@git.kernel.orgSigned-off-by:
-
