- 19 Jul, 2017 40 commits
-
-
David Carrillo-Cisneros authored
There are three FEAT_OP* macros: - FEAT_OPA: for features without process record. - FEAT_OPP: for features with process record. - FEAT_OPF: like FEAT_OPP but to show only if show_full_info flags is set. To add pipe-mode headers we need yet another variation of the macros (one to specify whether a feature generates an auxiliar record). Instead, we redefine macros so that: - show_full_info is specified as an argument (to remove the FEAT_OPF variation) and, - it always sets "process" handler (to remove the FEAT_OPA variation). Individual process handlers can be NULLed individually. This allows to define two variations only: - FEAT_OPR: synthesizes auxiliar event record. - FEAT_OPN: doesn't synthesize an auxiliar event record. Signed-off-by:David Carrillo-Cisneros <davidcc@google.com> Acked-by:
David Ahern <dsahern@gmail.com> Acked-by:
Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: He Kuang <hekuang@huawei.com> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Turner <pjt@google.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Simon Que <sque@chromium.org> Cc: Stephane Eranian <eranian@google.com> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/20170718042549.145161-14-davidcc@google.comSigned-off-by:
Arnaldo Carvalho de Melo <acme@redhat.com>
-
David Carrillo-Cisneros authored
Extend struct feat_fd to use a temporal buffer in pipe-mode, instead of perf.data's file descriptor. The header features build_id and aux_trace already have logic to print in file-mode that heavily rely on lseek the file. For now, leave such features inactive in pipe-mode and print a warning if their functions are called in pipe-mode. Signed-off-by:
-
David Carrillo-Cisneros authored
In pipe-mode, we will operate over a buffer instead of a file descriptor but write_pmu_mappings uses lseek to move over the perf.data file. Refactor write_pmu_mappings to avoid the usage of lseek and allow reusing the same logic in pipe-mode (next patch). Signed-off-by:
-
David Carrillo-Cisneros authored
As preparation for using header records in-pipe mode, replace int fd with struct feat_fd ff in read functions for all header record types. This patch does not change behavior. Signed-off-by:
-
David Carrillo-Cisneros authored
struct perf_file_section is used in process_##_feat as container for size and offset in the file descriptor. These attributes are meaninful in pipe-mode but struct perf_file_section is not. Add offset and size variables to struct feat_fd to store perf_file_section's values in file-mode. Later on, the same variables can be reused for pipe-mode. This patch does not change behavior. Signed-off-by:
-
David Carrillo-Cisneros authored
As preparation for using header records in pipe-mode, replace int fd with struct feat_fd ff in process functions for all header record types. This patch does not change behavior. Signed-off-by:
-
David Carrillo-Cisneros authored
As preparation for using header records in pipe mode, replace int fd with struct feat_fd ff in print functions for all header record types. Signed-off-by:
-
David Carrillo-Cisneros authored
Introduce struct feat_fd. This patch uses it as a wrapper around fd in write_* functions for feature headers. Next patches will extend its functionality to other feature header functions. This patch does not change behavior. Signed-off-by:
-
David Carrillo-Cisneros authored
Now that writen takes a const buffer, use it in do_write instead of duplicating its functionality. Export do_write to use it consistently in header.c and build_id.c . Signed-off-by:
-
David Carrillo-Cisneros authored
Make buf in helper function "writen" constant to simplify the life of its callers. This requires to hack a cast of buf prior to passing it to "ion" which is simpler than the alternative of reworking the "ion" function to provide a read and a write paths, the latter with constant buf argument. Signed-off-by:
-
David Carrillo-Cisneros authored
Do not proceed if write_padded() error failed. Also, add comments to remind that the return value of write_* functions in util/header.c is an errno code and not the number of bytes written. Signed-off-by:
-
David Carrillo-Cisneros authored
Simplify code by adding a macro to handle the common case of processing header features that are a simple string. Signed-off-by:
-
David Carrillo-Cisneros authored
Most callers of readn() in perf header read either a 32 or a 64 bits number, error check it and swap it, if necessary. Create do_read_u32 and do_read_u64 to simplify these use cases. Signed-off-by:
-
Jin Yao authored
Currently perf supports a mode to query inline stack. It works well for finding user space inline functions but it doesn't work for kernel ones, due to some unnecessary check. This patch removes these unnecessary checks. Now kernel inline functions can be reported. For example: perf report --inline -g func --stdio |--46.19%--do_huge_pmd_anonymous_page | do_huge_pmd_anonymous_page (inline) | __do_huge_pmd_anonymous_page (inline) | __SetPageUptodate (inline) | __set_bit (inline) The result is compared with the output of addr2line. They match. Signed-off-by:
Yao Jin <yao.jin@linux.intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@intel.com> Cc: Milian Wolff <milian.wolff@kdab.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1500409892-15904-1-git-send-email-yao.jin@linux.intel.comSigned-off-by:
-
Arnaldo Carvalho de Melo authored
Removing syscall_fmt::err_msg and instead always formatting negative returns as errno values. With this we can remove a lot of entries that have no special handling besides the ones we can do by looking at the tracefs format files, i.e. the types for the fields (e.g. pid_t), well known names (e.g. fd). Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-rg9u7a3qqdnzo37d212vnz2o@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
Before: 77059.513 ( 0.005 ms): bash/6649 fcntl(fd: 1</dev/pts/12>, cmd: DUPFD, arg: 10) = 10</dev/pts/12> After: 77059.513 ( 0.005 ms): bash/6649 fcntl(fd: 1</dev/pts/12>, cmd: DUPFD, arg: 10</dev/pts/12>) = 10</dev/pts/12> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-0k8iszng0slcuw0rc6xq1x5l@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
Before: 77059.513 ( 0.005 ms): bash/6649 fcntl(fd: 1</dev/pts/12>, arg: 10) = 10</dev/pts/12> After: 77059.513 ( 0.005 ms): bash/6649 fcntl(fd: 1</dev/pts/12>, cmd: DUPFD, arg: 10) = 10</dev/pts/12> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-woois88uwcr4xu38xx1ihiwo@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
The 'perf trace' tool is suppressing args set to zero, with the exception of string tables (strarrays), which are kinda like enums, i.e. we have maps to go from numbers to strings. But the 'cmd' fcntl arg requires more specialized treatment, as its value will regulate if the next fcntl syscall arg, 'arg', should be ignored (not used) and also how to format the syscall return (fd, file flags, etc), so add a 'show_zero" bool to struct syscall_arg_fmt, to regulate this more explicitely. Will be used in a following patch with fcntl, here is just the mechanism. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-all738jctxets8ffyizp5lzo@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
Instead of having syscall_fmt.{arg_scnprintf,arg_parm}, introduce struct syscall_arg_fmt and have these two, paving the way for more state to change the formatting algorithms. For instance, in the 'fcntl' 'cmd' case it is better not to suppress it when being zero, showing instead its name "DUPFD". We had that in an ad-hoc way just for strarrays, but with more involved cases like fcntl, that can't be done with just a strarray, we'll need a ".show_zero" arg in the 'cmd' syscall_arg_fmt. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-ch06o2j72zbjx5xww4qp67au@git.kernel.orgSigned-off-by: -
Arnaldo Carvalho de Melo authored
One more looking prettier. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-ytr7idkese8sjtvn5g60130e@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
Like will be done with fcntl(fd, F_GETLEASE, F_RDLCK|F_WRLCK|F_UNLCK) Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-3p11bgirtntjfmbixfkz8i2m@git.kernel.orgSigned-off-by:
-
Jiri Olsa authored
Some of the stat events are quite rare to find on common machines (like front end cycles). Adding an 'optional' term to mark such events in attr tests. Event marked as optional will not fail the test case if it's not found in results. Signed-off-by:
-
Jiri Olsa authored
>From following commit: commit 4979d0c7 ("perf stat record: Add record command") we started to assign PERF_SAMPLE_IDENTIFIER to sample_type. Fixing the attr stat tests accordingly. Signed-off-by:
-
Jiri Olsa authored
We have a test to detect to highest precise possible, so test can't just predict precise_ip value. Signed-off-by:
-
Jiri Olsa authored
The final period can differ from what user specifies on command line due to the perf_event_max_sample_rate sysctl setup. Thus we can't predixt the sample_period value any more. Signed-off-by:
-
Jiri Olsa authored
The stat command creates all events disabled and enables them either manualy or via the enable_on_exec bit. Signed-off-by:
-
Jiri Olsa authored
The record command now properly returns the status of the tracee if there's any. We need to properly set the expected return value of the tracee in the attr tests. Signed-off-by:
-
Jiri Olsa authored
Following commit: commit 509051ea ("perf record: Rename --no-delay to --no-buffering") removed '-D' option and renamed --no-delay into --no-buffering. Fixing that in the attr tests. Signed-off-by:
-
Jiri Olsa authored
Following commit: commit 5c0cf224 ("perf record: Store data mmaps for dwarf unwind") have enabled address sampling for dwarf unwind, we need to reflect that in this test by adding ADDR sample_type and enabling mmap_data. Signed-off-by:
-
Jiri Olsa authored
There's an event open fallback which set exclude_kernel=1 in case use does not have enough privileges. Adding both 0|1 for this attribute, because we don't know what value it is. Signed-off-by:
-
Jiri Olsa authored
The data_equal name fits better to the return value of the function. It's true when the data is equal. Signed-off-by:
-
Jiri Olsa authored
Making compare_data global, so it could be used outside the Test class scope to compare command results. Signed-off-by:
-
Jiri Olsa authored
We create many test events before the real ones just to test specific features. But there's no way for attr tests to separate those test events from those it needs to check. Adding 'ready' call from the events open interface to trigger/start events collection for attr test. Signed-off-by:
-
Jiri Olsa authored
Do not mess up our temp space with files we don't need - failed event open attempts. Signed-off-by:
-
Arnaldo Carvalho de Melo authored
It can return NULL, in which case we should bail out and remove the directory created with mkdtemp(), which is stored in the "__tempdir" variable, not in "tempdir". Cc: Masami Hiramatsu <mhiramat@kernel.org> Fixes: 8e5dc848 ("perf test: Add a test case for SDT event") Signed-off-by:
-
Arnaldo Carvalho de Melo authored
When the user doesn't specify an event with -e/--event, 'perf record' will use as a default the "cycles" event with the highest level of precision in perf_event_attr.precise_ip, but --no-samples, if present, is incompatible with precise_ip != 0, so use the newly introduced __perf_event__add_default(precise = false) to fix that: Before: # perf record -n usleep 1 Please consider tweaking /proc/sys/kernel/perf_event_max_sample_rate. Error: The sys_perf_event_open() syscall returned with 22 (Invalid argument) for event (cycles:ppp). /bin/dmesg may provide additional information. No CONFIG_PERF_EVENTS=y kernel support configured? # After: # perf record -n usleep 1 Please consider tweaking /proc/sys/kernel/perf_event_max_sample_rate. [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.018 MB perf.data ] [root@jouet /]# perf evlist -v cycles: size: 112, sample_type: IP|TID|TIME|PERIOD, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1 [root@jouet /]# Reported-by:
-
Arnaldo Carvalho de Melo authored
There are cases where we want to leave attr.precise_ip as zero, such as when using 'perf record --no-samples', where this would make the kernel return -EINVAL. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-0u2m2a8rqw781r6m8svqyne8@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
There are cases where we want to leave attr.precise_ip as zero, such as when using 'perf record --no-samples', where this would make the kernel return -EINVAL. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-4zq1udecxa51gsapyfwej5fj@git.kernel.orgSigned-off-by:
-
Krister Johansen authored
If a stripped binary is placed in the cache, the user is in a situation where there's a cached elf file present, but it doesn't have any symtab to use for name resolution. Grab the debuginfo for binaries that don't end in .ko. This yields a better chance of resolving symbols from older traces. Signed-off-by:
Krister Johansen <kjlx@templeofstupid.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas-Mich Richter <tmricht@linux.vnet.ibm.com> Link: http://lkml.kernel.org/r/1499305693-1599-7-git-send-email-kjlx@templeofstupid.comSigned-off-by:
-
Krister Johansen authored
Teach buildid-cache how to add, remove, and update binary objects from other mount namespaces. Allow probe events tracing binaries in different namespaces to add their objects to the probe and build-id caches too. As a handy side effect, this also lets us access SDT probes in binaries from alternate mount namespaces. Signed-off-by:
Brendan Gregg <brendan.d.gregg@gmail.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas-Mich Richter <tmricht@linux.vnet.ibm.com> Link: http://lkml.kernel.org/r/1499305693-1599-5-git-send-email-kjlx@templeofstupid.com [ Add util/namespaces.c to tools/perf/util/python-ext-sources, to fix the python binding 'perf test' ] Signed-off-by:
-
