- 28 Dec, 2018 2 commits
-
-
Jiri Olsa authored
Ondřej reported that when compiled with python3, the python extension regresses in evlist.get_pollfd function behaviour. The evlist.get_pollfd function creates file objects from evlist's fds and returns them in a list. The python3 version also sets them to 'close the original descriptor' when the object dies (is closed), by passing True via the 'closefd' arg in the PyFile_FromFd call. The python's closefd doc says: If closefd is False, the underlying file descriptor will be kept open when the file is closed. That's why the following line in python3 closes all evlist fds: evlist.get_pollfd() the returned list is immediately destroyed and that takes down the original events fds. Passing closefd as False to PyFile_FromFd to fix this. Reported-by:
Ondřej Lysoněk <olysonek@redhat.com> Signed-off-by:
Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Jaroslav Škarvada <jskarvad@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Fixes: 66dfdff0 ("perf tools: Add Python 3 support") Link: http://lkml.kernel.org/r/20181226112121.5285-1-jolsa@kernel.orgSigned-off-by:
Arnaldo Carvalho de Melo <acme@redhat.com>
-
Colin Ian King authored
The spelling of the SECCOMP is incorrect, fix these. Signed-off-by:
Colin King <colin.king@canonical.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: kernel-janitors@vger.kernel.org Fixes: c65c83ff ("perf trace: Allow asking for not suppressing common string prefixes") Link: http://lkml.kernel.org/r/20181221084809.6108-1-colin.king@canonical.comSigned-off-by:
-
- 21 Dec, 2018 4 commits
-
-
Arnaldo Carvalho de Melo authored
We shouldn't hardcode the size of the tracepoint common_ fields, use the offset of the 'id'/'__syscallnr' field in the sys_enter event instead. This caused the augmented syscalls code to fail on a particular build of a PREEMPT_RT_FULL kernel where these extra 'common_migrate_disable' and 'common_padding' fields were before the syscall id one: # cat /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/format name: sys_enter ID: 22 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 short common_migrate_disable; offset:8; size:2; signed:0; field:unsigned short common_padding; offset:10; size:2; signed:0; field:long id; offset:16; size:8; signed:1; field:unsigned long args[6]; offset:24; size:48; signed:0; print fmt: "NR %ld (%lx, %lx, %lx, %lx, %lx, %lx)", REC->id, REC->args[0], REC->args[1], REC->args[2], REC->args[3], REC->args[4], REC->args[5] # All those 'common_' prefixed fields are zeroed when they hit a BPF tracepoint hook, we better just discard those, i.e. somehow pass an offset to the BPF program from the start of the ctx and make adjustments in the 'perf trace' handlers to adjust the offset of the syscall arg offsets obtained from tracefs. Till then, fix it the quick way and add this to the augmented_raw_syscalls.c to bet it to work in such kernels: diff --git a/tools/perf/examples/bpf/augmented_raw_syscalls.c b/tools/perf/examples/bpf/augmented_raw_syscalls.c index 53c233370fae..1f746f931e13 100644 --- a/tools/perf/examples/bpf/augmented_raw_syscalls.c +++ b/tools/perf/examples/bpf/augmented_raw_syscalls.c @@ -38,12 +38,14 @@ struct bpf_map SEC("maps") syscalls = { struct syscall_enter_args { unsigned long long common_tp_fields; + long rt_common_tp_fields; long syscall_nr; unsigned long args[6]; }; struct syscall_exit_args { unsigned long long common_tp_fields; + long rt_common_tp_fields; long syscall_nr; long ret; }; Just to check that this was the case. Fix it properly later, for now remove the hardcoding of the offset in the 'perf trace' side and document the situation with this patch. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-2pqavrktqkliu5b9nzouio21@git.kernel.orgSigned-off-by: -
Stanislav Fomichev authored
Current libbfd feature test unconditionally links against -liberty and -lz. While it's required on some systems (e.g. opensuse), it's completely unnecessary on the others, where only -lbdf is sufficient (debian). This patch streamlines (and renames) the following feature checks: feature-libbfd - only link against -lbfd (debian), see commit 2cf90407 ("perf tools: Fix bfd dependency libraries detection") feature-libbfd-liberty - link against -lbfd and -liberty feature-libbfd-liberty-z - link against -lbfd, -liberty and -lz (opensuse), see commit 280e7c48 ("perf tools: fix BFD detection on opensuse") (feature-liberty{,-z} were renamed to feature-libbfd-liberty{,z} for clarity) The main motivation is to fix this feature test for bpftool which is currently broken on debian (libbfd feature shows OFF, but we still unconditionally link against -lbfd and it works). Tested on debian with only -lbfd installed (without -liberty); I'd appreciate if somebody on the other systems can test this new detection method. Signed-off-by:Stanislav Fomichev <sdf@google.com> Acked-by:
-
Arnaldo Carvalho de Melo authored
To match strace output: # cat mmap.c #include <sys/mman.h> int main(void) { mmap(0, 4096, PROT_READ|PROT_WRITE|PROT_EXEC, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0); return 0; } # strace -e mmap ./mmap |& grep -v ^+++ mmap(NULL, 103484, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7f5bae400000 mmap(NULL, 8192, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0x7f5bae3fe000 mmap(NULL, 3889792, PROT_READ|PROT_EXEC, MAP_PRIVATE|MAP_DENYWRITE, 3, 0) = 0x7f5bade40000 mmap(0x7f5bae1ec000, 24576, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 0x1ac000) = 0x7f5bae1ec000 mmap(0x7f5bae1f2000, 14976, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_ANONYMOUS, -1, 0) = 0x7f5bae1f2000 mmap(NULL, 4096, PROT_READ|PROT_WRITE|PROT_EXEC, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0x7f5bae419000 # trace -e mmap ./mmap |& grep -v ^+++ mmap(NULL, 103484, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7f6646c25000 mmap(NULL, 8192, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS) = 0x7f6646c23000 mmap(NULL, 3889792, PROT_READ|PROT_EXEC, MAP_PRIVATE|MAP_DENYWRITE, 3, 0) = 0x7f6646665000 mmap(0x7f6646a11000, 24576, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 0x1ac000) = 0x7f6646a11000 mmap(0x7f6646a17000, 14976, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_ANONYMOUS) = 0x7f6646a17000 mmap(NULL, 4096, PROT_READ|PROT_WRITE|PROT_EXEC, MAP_PRIVATE|MAP_ANONYMOUS) = 0x7f6646c3e000 # Reported-by:Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-nt49d6iqle80cw8f529ovaqi@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
While updating 'perf trace' on an machine with an old precompiled augmented_raw_syscalls.o that didn't setup the syscall map the new 'perf trace' codebase notices the augmented_raw_syscalls.o eBPF event, decides to use it instead of the old raw_syscalls:sys_{enter,exit} method, but then because we don't have the syscall map tries to set the tracepoint filter on the sys_{enter,exit} evsels, that are NULL, segfaulting. Make the code more robust by checking it those tracepoints have their respective evsels in place before trying to set the tp filter. With this we still get everything to work, just not setting up the syscall filters, which is better than a segfault. Now to update the precompiled augmented_raw_syscalls.o and continue development :-) Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-3ft5rjdl05wgz2pwpx2z8btu@git.kernel.orgSigned-off-by:
-
- 20 Dec, 2018 1 commit
-
-
Ingo Molnar authored
Merge tag 'perf-core-for-mingo-4.21-20181218' 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: - Implement BPF based syscall filtering in 'perf trace', using BPF maps and the augmented_raw_syscalls.c BPF proggie (Arnaldo Carvalho de Melo) - Allow specifying in .perfconfig a set of events use in 'perf trace' in addition to any other specified from the command line. This initially will be used to always use the augmented_raw_syscalls.o precompiled BPF program for getting pointer contents. (Arnaldo Carvalho de Melo) - Allow fine grained control about how the syscall output should be formatted. This will be used to allow producing the same output produced by the 'strace' tool, to then use in regression tests comparing the output of 'perf trace' with the one produced from 'strace' (Arnaldo Carvalho de Melo) - Beautify the renameat2 olddirfd, newdirfd and flags arguments (Arnaldo Carvalho de Melo) - Beautify arch_prctl 'code' syscall arg (Arnaldo Carvalho de Melo) - Beautify fadvise64 'advice' syscall arg (Arnaldo Carvalho de Melo) - Relax checks on perf-PID.map ownership, resulting in symbols in executable anonymous maps setup by JITs in things like node.js to be resolved in a 'perf top' session run by root without the need for --force to be used (Arnaldo Carvalho de Melo) - Update asm-generic/unistd.h copy (Arnaldo Carvalho de Melo) - Do not use the first and last symbols when setting up address filters in auxtrace, this fails when we don't have a symbol table, filter the entire area based on the dso size. (Adrian Hunter) - Do not use kernel headers to build libsubcmd, we shouldn't use anything from outside tools/, fixes the build with the Android NDK (Arnaldo Carvalho de Melo) - Add several prototypes for systems lacking those, such as open_memstream(), sigqueue(), fixing warnings building with Android's bionic libc that were preventing the use of -Werror there (Arnaldo Carvalho de Melo) - Use LDFLAGS in the libtraceevent build commands, allowing developers to override its values (Jiri Olsa) - Link libperf-jvmti.so with LDFLAGS variable, allowing distro packages to propagate its settings when building this library (Jiri Olsa) - cs-etm (ARM CoreSight) fixes: (Leo Yan) - Correct packets swapping in cs_etm__flush() - Avoid stale branch samples when flush packet - Remove unused 'trace_on' in cs_etm_decoder - Refactor enumeration cs_etm_sample_type - Rename CS_ETM_TRACE_ON to CS_ETM_DISCONTINUITY - Treat NO_SYNC element as trace discontinuity - Treat EO_TRACE element as trace discontinuity - Generate branch sample for exception packet - Use shebangs in the 'perf test' shell scripts, making them identifiable as shell scripts (Michael Petlan) - Avoid segfaults caused by negated options in 'perf stat' (Michael Petlan) - Fix processing of dereferenced args in bprintk events in libtracevent (Steven Rostedt) Signed-off-by:
Ingo Molnar <mingo@kernel.org>
-
- 18 Dec, 2018 33 commits
-
-
Arnaldo Carvalho de Melo authored
To get the change in: b7d624ab ("asm-generic: unistd.h: fixup broken macro include.") That doesn't imply in any changes in the tools. This silences the following perf build warning: Warning: Kernel ABI header at 'tools/include/uapi/asm-generic/unistd.h' differs from latest version at 'include/uapi/asm-generic/unistd.h' diff -u tools/include/uapi/asm-generic/unistd.h include/uapi/asm-generic/unistd.h Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Guo Ren <ren_guo@c-sky.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lkml.kernel.org/n/tip-2e7xwm5i2qcc88jp2lyawdyd@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
Those are simple enough, and usually not produced by root, instead by whatever user is running java, rust, Node.js JIT code that end up generating those /tmp/perf-PID.map for resolution of symbols in the anonymous executable maps. Having to use --force to resolve symbols in 'perf top' is a distraction, as recently I experienced when node.js symbols were not being resolved by 'perf top'. Acked-by:
-
Arnaldo Carvalho de Melo authored
That ends up generating this: $ cat /tmp/build/perf/trace/beauty/generated/fadvise_advice_array.c static const char *fadvise_advices[] = { [0] = "NORMAL", [1] = "RANDOM", [2] = "SEQUENTIAL", [3] = "WILLNEED", [4] = "DONTNEED", [5] = "NOREUSE", }; $ Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-zwbslubagram8a8zdc003u8h@git.kernel.orgSigned-off-by: -
Arnaldo Carvalho de Melo authored
$ tools/perf/trace/beauty/fadvise.sh static const char *fadvise_advices[] = { [0] = "NORMAL", [1] = "RANDOM", [2] = "SEQUENTIAL", [3] = "WILLNEED", [4] = "DONTNEED", [5] = "NOREUSE", }; $ This has a hack wrt the s390 difference. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-tb7jguv01u8p570piq13eioh@git.kernel.orgSigned-off-by: -
Arnaldo Carvalho de Melo authored
Will be used to generate the string table for fadvise64's 'advice' argument. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-muswpnft8q9krktv052yrgsc@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
Also to make it match 'strace' output, for regression testing. Both now produce this option, when 'perf trace' uses a .perfconfig asking for the strace like output: mmap(0x7faf66e6a000, 1363968, PROT_READ|PROT_EXEC, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 0x22000) = 0x7faf66e6a000 Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-27qhouo1kaac2iyl85nfnsf5@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
Helps with comparing 'strace' and 'perf trace' output, for mutual regression testing. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-va0qe95xbhep5hy52aq5qe0v@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
This actually so far, AFAIK is available only in x86, so the code was put in place with x86 prefixes, in arches where it is not available it will just not be called, so no further mechanisms are needed at this time. Later, when other arches wire this up, we'll just look at the uname (live sessions) or perf_env data in the perf.data header to auto-wire the right beautifier. With this the output is the same as produced by 'strace' when used with the following ~/.perfconfig: # cat ~/.perfconfig [llvm] dump-obj = true [trace] add_events = /home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o show_zeros = yes show_duration = no no_inherit = yes show_timestamp = no show_arg_names = no args_alignment = -40 show_prefix = yes # And, on fedora 29, since the string tables are generated from the kernel sources, we don't know about 0x3001, just like strace: --- /tmp/strace 2018-12-17 11:22:08.707586721 -0300 +++ /tmp/trace 2018-12-18 11:11:32.037512729 -0300 @@ -1,49 +1,49 @@ -arch_prctl(0x3001 /* ARCH_??? */, 0x7ffc8a92dc80) = -1 EINVAL (Invalid argument) +arch_prctl(0x3001 /* ARCH_??? */, 0x7ffe4eb93ae0) = -1 EINVAL (Invalid argument) -arch_prctl(ARCH_SET_FS, 0x7faf6700f540) = 0 +arch_prctl(ARCH_SET_FS, 0x7fb507364540) = 0 And that seems to be related to the CET/Shadow Stack feature, that userland in Fedora 29 (glibc 2.28) are querying the kernel about, that 0x3001 seems to be ARCH_CET_STATUS, I'll check the situation and test with a fedora 29 kernel to see if the other codes are used. A diff that ignores the different pointers for different runs needs to be put in place in the upcoming regression tests comparing 'perf trace's output to strace's. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-73a9prs8ktkrt97trtdmdjs8@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
To match 'strace' output, like in: arch_prctl(0x3001 /* ARCH_??? */, 0x7ffc8a92dc80) = -1 EINVAL (Invalid argument) Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-kx59j2dk5l1x04ou57mt99ck@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
We'll use it in the upcoming arch_prctl() 'code' arg beautifier. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-6e4tj2fjen8qa73gy4u49vav@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
$ cat /tmp/build/perf/trace/beauty/generated/x86_arch_prctl_code_array.c #define x86_arch_prctl_codes_1_offset 0x1001 static const char *x86_arch_prctl_codes_1[] = { [0x1001 - 0x1001]= "SET_GS", [0x1002 - 0x1001]= "SET_FS", [0x1003 - 0x1001]= "GET_FS", [0x1004 - 0x1001]= "GET_GS", [0x1011 - 0x1001]= "GET_CPUID", [0x1012 - 0x1001]= "SET_CPUID", }; #define x86_arch_prctl_codes_2_offset 0x2001 static const char *x86_arch_prctl_codes_2[] = { [0x2001 - 0x2001]= "MAP_VDSO_X32", [0x2002 - 0x2001]= "MAP_VDSO_32", [0x2003 - 0x2001]= "MAP_VDSO_64", }; $ Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-3r9blij6n8wdlsyd5dujx86r@git.kernel.orgSigned-off-by: -
Arnaldo Carvalho de Melo authored
$ tools/perf/trace/beauty/x86_arch_prctl.sh #define x86_arch_prctl_codes_1_offset 0x1001 static const char *x86_arch_prctl_codes_1[] = { [0x1001 - 0x1001]= "SET_GS", [0x1002 - 0x1001]= "SET_FS", [0x1003 - 0x1001]= "GET_FS", [0x1004 - 0x1001]= "GET_GS", [0x1011 - 0x1001]= "GET_CPUID", [0x1012 - 0x1001]= "SET_CPUID", }; #define x86_arch_prctl_codes_2_offset 0x2001 static const char *x86_arch_prctl_codes_2[] = { [0x2001 - 0x2001]= "MAP_VDSO_X32", [0x2002 - 0x2001]= "MAP_VDSO_32", [0x2003 - 0x2001]= "MAP_VDSO_64", }; $ Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-w0fux1psivphhx6rve8kn3vq@git.kernel.orgSigned-off-by: -
Arnaldo Carvalho de Melo authored
We need it to generate the tables for the 'code' arch_prctl's syscall argument. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-vu890pi18fpd4eyz61cazckj@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
Matching strace's output format. The 'format' file for the syscall tracepoints have an indication if the arg is a pointer, with some exceptions like 'mmap' that has its first arg as an 'unsigned long', so use a heuristic using the argument name, i.e. if it contains the 'addr' substring, format it with the pointer formatter. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-ddghemr8qrm6i0sb8awznbze@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
To match strace, now both emit the same line for calls like: access("/etc/ld.so.preload", R_OK) = -1 ENOENT (No such file or directory) Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-krxl6klsqc9qyktoaxyih942@git.kernel.orgSigned-off-by: -
Arnaldo Carvalho de Melo authored
This will all come from userspace, but to test the changes to make 'perf trace' output similar to strace's, do this one more now manually. To update the precompiled augmented_raw_syscalls.o binary I just run: # perf record -e ~acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.c sleep 1 LLVM: dumping /home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.022 MB perf.data ] # Because to have augmented_raw_syscalls to be always used and a fast startup and remove the need to have the llvm toolchain installed, I'm using: # perf config | grep add_events trace.add_events=/home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o # So when doing changes to augmented_raw_syscals.c one needs to rebuild the .o file. This will be done automagically later, i.e. have a 'make' behaviour of recompiling when the .c gets changed. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-lw3i2atyq8549fpqwmszn3qp@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
To use strace's style, helping in comparing the output of 'perf trace' with the one from 'strace', to help in upcoming regression tests. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-mw6peotz4n84rga0fk78buff@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
And there are more flags, to match strace's output. openat(AT_FDCWD, "/etc/ld.so.cache", O_RDONLY|O_CLOEXEC) = 3 Also to help with regression tests. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-ofovpmvdli3bwch30936xn7t@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
So far we've been suppressing common stuff such as "MAP_" in the mmap flags, showing "SHARED" instead of "MAP_SHARED", allow for those prefixes (and a few suffixes) to be shown: # trace -e *map,open*,*seek sleep 1 openat("/etc/ld.so.cache", CLOEXEC) = 3 mmap(0, 109093, READ, PRIVATE, 3, 0) = 0x7ff61c695000 openat("/lib64/libc.so.6", CLOEXEC) = 3 lseek(3, 792, SET) = 792 mmap(0, 8192, READ|WRITE, PRIVATE|ANONYMOUS) = 0x7ff61c693000 lseek(3, 792, SET) = 792 lseek(3, 864, SET) = 864 mmap(0, 1857568, READ, PRIVATE|DENYWRITE, 3, 0) = 0x7ff61c4cd000 mmap(0x7ff61c4ef000, 1363968, EXEC|READ, PRIVATE|FIXED|DENYWRITE, 3, 139264) = 0x7ff61c4ef000 mmap(0x7ff61c63c000, 311296, READ, PRIVATE|FIXED|DENYWRITE, 3, 1503232) = 0x7ff61c63c000 mmap(0x7ff61c689000, 24576, READ|WRITE, PRIVATE|FIXED|DENYWRITE, 3, 1814528) = 0x7ff61c689000 mmap(0x7ff61c68f000, 14368, READ|WRITE, PRIVATE|FIXED|ANONYMOUS) = 0x7ff61c68f000 munmap(0x7ff61c695000, 109093) = 0 openat("/usr/lib/locale/locale-archive", CLOEXEC) = 3 mmap(0, 217749968, READ, PRIVATE, 3, 0) = 0x7ff60f523000 # # vim ~/.perfconfig # # perf config llvm.dump-obj=true trace.add_events=/home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o trace.show_zeros=yes trace.show_duration=no trace.no_inherit=yes trace.show_timestamp=no trace.show_arg_names=no trace.args_alignment=0 trace.string_quote=" trace.show_prefix=yes # # # trace -e *map,open*,*seek sleep 1 openat(AT_FDCWD, "/etc/ld.so.cache", O_CLOEXEC) = 3 mmap(0, 109093, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7f7ebbe59000 openat(AT_FDCWD, "/lib64/libc.so.6", O_CLOEXEC) = 3 lseek(3, 792, SEEK_SET) = 792 mmap(0, 8192, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS) = 0x7f7ebbe57000 lseek(3, 792, SEEK_SET) = 792 lseek(3, 864, SEEK_SET) = 864 mmap(0, 1857568, PROT_READ, MAP_PRIVATE|MAP_DENYWRITE, 3, 0) = 0x7f7ebbc91000 mmap(0x7f7ebbcb3000, 1363968, PROT_EXEC|PROT_READ, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 139264) = 0x7f7ebbcb3000 mmap(0x7f7ebbe00000, 311296, PROT_READ, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 1503232) = 0x7f7ebbe00000 mmap(0x7f7ebbe4d000, 24576, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 1814528) = 0x7f7ebbe4d000 mmap(0x7f7ebbe53000, 14368, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_ANONYMOUS) = 0x7f7ebbe53000 munmap(0x7f7ebbe59000, 109093) = 0 openat(AT_FDCWD, "/usr/lib/locale/locale-archive", O_CLOEXEC) = 3 mmap(0, 217749968, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7f7eaece7000 # Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-mtn1i4rjowjl72trtnbmvjd4@git.kernel.orgSigned-off-by: -
Arnaldo Carvalho de Melo authored
So that the user, in an upcoming patch, can select printing it to get the full string as used in the source code, not one with a common prefix chopped off so as to make the output more compact. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-zypczc88gzbmeqx7b372s138@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
To match 'strace' output, helping with upcoming regression tests comparing both outputs. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-jab52t1dcuh6vlztqle9g7u9@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
Since the start 'perf trace' aligns the parens enclosing the list of syscall args to align the syscall results, allow this to be configurable, keeping the default of 70. Using: # perf config llvm.dump-obj=true trace.add_events=/home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o trace.show_zeros=yes trace.show_duration=no trace.no_inherit=yes trace.show_timestamp=no trace.show_arg_names=no trace.args_alignment=0 # trace -e open*,close,*sleep sleep 1 openat(CWD, /etc/ld.so.cache, CLOEXEC) = 3 close(3) = 0 openat(CWD, /lib64/libc.so.6, CLOEXEC) = 3 close(3) = 0 openat(CWD, /usr/lib/locale/locale-archive, CLOEXEC) = 3 close(3) = 0 nanosleep(0x7ffc00de66f0, 0) = 0 close(1) = 0 close(2) = 0 # Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-r8cbhoz1lr5npq9tutpvoigr@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
To show just the values: Default: # trace -e open*,close,*sleep sleep 1 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC ) = 3 close(fd: 3 ) = 0 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC ) = 3 close(fd: 3 ) = 0 openat(dfd: CWD, filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3 close(fd: 3 ) = 0 nanosleep(rqtp: 0x7ffc0c4ea0d0, rmtp: 0 ) = 0 close(fd: 1 ) = 0 close(fd: 2 ) = 0 # Remove it: # perf config trace.show_arg_names=no # trace -e open*,close,*sleep sleep 1 openat(CWD, /etc/ld.so.cache, CLOEXEC ) = 3 close(3 ) = 0 openat(CWD, /lib64/libc.so.6, CLOEXEC ) = 3 close(3 ) = 0 openat(CWD, /usr/lib/locale/locale-archive, CLOEXEC ) = 3 close(3 ) = 0 nanosleep(0x7ffced3a8c40, 0 ) = 0 close(1 ) = 0 close(2 ) = 0 # Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-ta9tbdwgodpw719sr2bjm8eb@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
# trace -e open*,close,*sleep sleep 1 0.000 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC ) = 3 0.016 close(fd: 3 ) = 0 0.024 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC ) = 3 0.074 close(fd: 3 ) = 0 0.235 openat(dfd: CWD, filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3 0.251 close(fd: 3 ) = 0 0.285 nanosleep(rqtp: 0x7ffd68e6d620, rmtp: 0 ) = 0 1000.386 close(fd: 1 ) = 0 1000.395 close(fd: 2 ) = 0 # # perf config trace.show_timestamp=no # trace -e open*,close,*sleep sleep 1 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC ) = 3 close(fd: 3 ) = 0 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC ) = 3 close(fd: 3 ) = 0 openat(dfd: CWD, filename: , flags: CLOEXEC ) = 3 close(fd: 3 ) = 0 nanosleep(rqtp: 0x7fffa79c38e0, rmtp: 0 ) = 0 close(fd: 1 ) = 0 close(fd: 2 ) = 0 # Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-mjjnicy48367jah6ls4k0nk8@git.kernel.orgSigned-off-by: -
Arnaldo Carvalho de Melo authored
I.f. if children should inherit the parent perf_event configuration, i.e. if we should trace children as well or just the parent. The default is to follow children, to disable this and have a behaviour similar to strace, set this config option or use the --no_inherit 'perf trace' option. E.g.: Default: # perf config trace.no_inherit # trace -e clone,*sleep time sleep 1 0.000 time/21107 clone(clone_flags: CHILD_CLEARTID|CHILD_SETTID|0x11, newsp: 0, child_tidptr: 0x7f7b8f9ae810) = 21108 (time) ? time/21108 ... [continued]: clone() 0.691 sleep/21108 nanosleep(rqtp: 0x7ffed01d0540, rmtp: 0 ) = 0 0.00user 0.00system 0:01.00elapsed 0%CPU (0avgtext+0avgdata 1988maxresident)k 0inputs+0outputs (0major+76minor)pagefaults 0swaps # Disable it: # trace -e clone,*sleep time sleep 1 0.000 clone(clone_flags: CHILD_CLEARTID|CHILD_SETTID|0x11, newsp: 0, child_tidptr: 0x7ff41e100810) = 21414 (time) 0.00user 0.00system 0:01.00elapsed 0%CPU (0avgtext+0avgdata 1964maxresident)k 0inputs+0outputs (0major+76minor)pagefaults 0swaps # Notice that since there is just one thread, the "comm/TID" column is suppressed. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-thd8s16pagyza71ufi5vjlan@git.kernel.orgSigned-off-by: -
Arnaldo Carvalho de Melo authored
More convenient thah having to recall what letter is about showing/listing/dumping the configuration, i.e. no arguments means -l/--list: # perf config llvm.dump-obj=true trace.default_events=/home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o trace.show_zeros=yes trace.show_duration=no # perf config -l llvm.dump-obj=true trace.default_events=/home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o trace.show_zeros=yes trace.show_duration=no # perf config -h Usage: perf config [<file-option>] [options] [section.name[=value] ...] -l, --list show current config variables --system use system config file --user use user config file # Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Taeung Song <treeze.taeung@gmail.com> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-z2n63avz6tliqb5gmu4l1dti@git.kernel.orgSigned-off-by: -
Arnaldo Carvalho de Melo authored
# perf config trace.show_duration=no # perf config -l | grep trace trace.default_events=/home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o trace.show_zeros=true trace.show_duration=no # trace -e *sleep sleep 1 0.000 sleep/8729 nanosleep(rqtp: 0x7ffcb0b4c940, rmtp: 0) = 0 # perf config trace.show_duration=yes # trace -e *sleep sleep 1 0.000 (1000.212 ms): sleep/8735 nanosleep(rqtp: 0x7ffca15fa770, rmtp: 0) = 0 # Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-2c7h1m8fhzb9puxtj9nlevi8@git.kernel.orgSigned-off-by: -
Arnaldo Carvalho de Melo authored
The default so far, since we show argument names followed by its values, was to make the output more compact by suppressing most zeroed args. Make this configurable so that users can choose what best suit their needs. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-q0gxws02ygodh94o0hzim5xd@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
To add augmented_raw_syscalls to the events speficied by the user, or be the only one if no events were specified by the user, one can add this to perfconfig: # cat ~/.perfconfig [trace] add_events = /home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o # I.e. pre-compile the augmented_raw_syscalls.c BPF program and make it always load, this way: # perf trace -e open* cat /etc/passwd > /dev/null 0.000 ( 0.013 ms): cat/31557 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3 0.035 ( 0.007 ms): cat/31557 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC) = 3 0.353 ( 0.009 ms): cat/31557 openat(dfd: CWD, filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3 0.424 ( 0.006 ms): cat/31557 openat(dfd: CWD, filename: /etc/passwd) = 3 # Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-0lgj7vh64hg3ce44gsmvj7ud@git.kernel.orgSigned-off-by: -
Arnaldo Carvalho de Melo authored
We're not using that puts() thing, and thus we don't need to define the __bpf_stdout__ map, reducing the setup time. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-3452xgatncpil7v22minkwbo@git.kernel.orgSigned-off-by:
-
Leo Yan authored
The exception packet appears as one element with 'elem_type' == OCSD_GEN_TRC_ELEM_EXCEPTION or OCSD_GEN_TRC_ELEM_EXCEPTION_RET, which is present for exception entry and exit respectively. The decoder sets the packet fields 'packet->exc' and 'packet->exc_ret' to indicate the exception packets; but exception packets don't have a dedicated sample type and shares the same sample type CS_ETM_RANGE with normal instruction packets. As a result, the exception packets are taken as normal instruction packets and this introduces confusion in mixing different packet types. Furthermore, these instruction range packets will be processed for branch samples only when 'packet->last_instr_taken_branch' is true, otherwise they will be omitted, this can introduce a mess for exception and exception returning due to not having the complete address range info for context switching. To process exception packets properly, this patch introduces two new sample types: CS_ETM_EXCEPTION and CS_ETM_EXCEPTION_RET; these two types of packets will be handled by cs_etm__exception(). The function cs_etm__exception() forces setting the previous CS_ETM_RANGE packet flag 'prev_packet->last_instr_taken_branch' to true, this matches well with the program flow when the exception is trapped from user space to kernel space, no matter if the most recent flow has branch taken or not; this is also safe for returning to user space after exception handling. After exception packets have their own sample type, the packet fields 'packet->exc' and 'packet->exc_ret' aren't needed anymore, so remove them. Signed-off-by:
Leo Yan <leo.yan@linaro.org> Reviewed-by:
Mathieu Poirier <mathieu.poirier@linaro.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Leach <mike.leach@linaro.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Robert Walker <robert.walker@arm.com> Cc: coresight ml <coresight@lists.linaro.org> Cc: linux-arm-kernel@lists.infradead.org Link: http://lkml.kernel.org/r/1544513908-16805-9-git-send-email-leo.yan@linaro.orgSigned-off-by:
-
Leo Yan authored
If the decoder outputs an EO_TRACE element, it means the end of the trace buffer; this is a discontinuity and in this case the end of trace data needs to be saved. This patch generates a CS_ETM_DISCONTINUITY packet for the EO_TRACE element hereby flushing the end of trace data in cs-etm.c. Signed-off-by:
-
Leo Yan authored
The CoreSight tracer driver might insert barrier packets between different buffers, thus the decoder can spot the boundaries based on the barrier packet; it is possible for the decoder to hit a barrier packet and emit a NO_SYNC element, then the decoder will find a periodic synchronisation point inside that next trace block that starts the trace again but does not have the TRACE_ON element as indicator - usually because this trace block has wrapped the buffer so we have lost the original point when the trace was enabled. In the first case it causes the insertion of a OCSD_GEN_TRC_ELEM_NO_SYNC in the middle of the tracing stream, but as we were not handling the NO_SYNC element properly this ends up making users miss the discontinuity indications. Though OCSD_GEN_TRC_ELEM_NO_SYNC is different from CS_ETM_TRACE_ON when output from the decoder, both indicate that the trace data is discontinuous; this patch treats OCSD_GEN_TRC_ELEM_NO_SYNC as a trace discontinuity and generates a CS_ETM_DISCONTINUITY packet for it, so cs-etm can handle the discontinuity for this case, finally it saves the last trace data for the previous trace block and restart samples for the new block. Signed-off-by:
-
