We were using a copy of uapi/linux/fs.h to create the mount syscall
'flags' string table to use in 'perf trace', to convert from the number
obtained via the raw_syscalls:sys_enter into a string, using
tools/perf/trace/beauty/mount_flags.sh, but in e262e32d6b ("vfs:
Suppress MS_* flag defs within the kernel unless explicitly enabled")
those defines got moved to linux/mount.h, so grab a copy of mount.h too.
Keep the uapi/linux/fs.h as we'll use it for the SEEK_ constants.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Howells <dhowells@redhat.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-i2ricmpwpdrpukfq3298jr1z@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This restriction is not present in 'perf report' and since 'perf top'
uses the same hists browser, remove it from it as well.
With this we create per event buckets with callchain trees, so that
# perf top --sort dso -g --no-children
Bucketizes samples by DSO and below it shows the callchains leading to
functions in this DSO.
Try also:
# perf top -e sched:*switch -g --no-children
To see the callchains leading to sched switches, pressing 'E' to expand
all one can quickly see the most common scheduler switches and what
leads to them, for instance, calls to IO, futexes, etc.
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Link: https://lkml.kernel.org/r/20190107140854.GA28965@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
When we get the sys_enter for a syscall we check if the last one is
still waiting for its matching sys_exit, if so we print this:
468.753 ( ): firefox/32382 poll(ufds: 0x7f3988d3dd00, nfds: 7, timeout_msecs: 4294967295) ...
449.575 ( 0.004 ms): Softwar~cThrea/32434 futex(uaddr: 0x7f39a18a9b70, op: WAKE|PRIVATE_FLAG, val: 1) = 0
At some point we'll get that poll sys_exit event and will print a "[continued]" line.
While making the sizing of the alignment after the syscall arg list and
its result configurable, so that we can mimic strace, which uses a
smaller alingment by default, a bug was introduced where the closing
parens appeared before the syscall name and its arg list, fix it.
Fixes: 4b8a240ed5 ("perf trace: Add alignment spaces after the closing parens")
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-oi45i54s59h1w1kmgpzrfuum@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:
perf annotate:
Ivan Krylov:
- Pass filename to objdump via execl, fixing usage with filenames
with special characters.
perf report:
Jin Yao:
Fix wrong iteration count in --branch-history
perf stat:
Jin Yao:
- Fix endless wait for child process
perf test:
Arnaldo Carvalho de Melo:
- Use a fallback to get the pathname in vfs_getname in
tools build:
Jiri Olsa:
- Allow overriding CFLAGS assignments.
Misc:
Arnaldo Carvalho de Melo:
- Syncronize UAPI headers
Mattias Jacobsson:
- Remove redundant va_end() in strbuf_addv()
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Pull perf tooling updates form Ingo Molnar:
"A final batch of perf tooling changes: mostly fixes and small
improvements"
* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (29 commits)
perf session: Add comment for perf_session__register_idle_thread()
perf thread-stack: Fix thread stack processing for the idle task
perf thread-stack: Allocate an array of thread stacks
perf thread-stack: Factor out thread_stack__init()
perf thread-stack: Allow for a thread stack array
perf thread-stack: Avoid direct reference to the thread's stack
perf thread-stack: Tidy thread_stack__bottom() usage
perf thread-stack: Simplify some code in thread_stack__process()
tools gpio: Allow overriding CFLAGS
tools power turbostat: Override CFLAGS assignments and add LDFLAGS to build command
tools thermal tmon: Allow overriding CFLAGS assignments
tools power x86_energy_perf_policy: Override CFLAGS assignments and add LDFLAGS to build command
perf c2c: Increase the HITM ratio limit for displayed cachelines
perf c2c: Change the default coalesce setup
perf trace beauty ioctl: Beautify USBDEVFS_ commands
perf trace beauty: Export function to get the files for a thread
perf trace: Wire up ioctl's USBDEBFS_ cmd table generator
perf beauty ioctl: Add generator for USBDEVFS_ ioctl commands
tools headers uapi: Grab a copy of usbdevice_fs.h
perf trace: Store the major number for a file when storing its pathname
...
Some kernels, like 4.19.13-300.fc29.x86_64 in fedora 29, fail with the
existing probe definition asking for the contents of result->name,
working when we ask for the 'filename' variable instead, so add a
fallback to that.
Now those tests are back working on fedora 29 systems with that kernel:
# perf test vfs_getname
65: Use vfs_getname probe to get syscall args filenames : Ok
66: Add vfs_getname probe to get syscall args filenames : Ok
67: Check open filename arg using perf trace + vfs_getname: Ok
#
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-klt3n0i58dfqttveti09q3fi@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The symbol__disassemble() function uses shell to launch objdump and
filter its output via grep. Passing filenames by interpolating them into
the command line via "%s" may lead to problems if said filenames contain
special characters.
Instead, pass the filename as a command line argument where it is not
subject to any kind of interpretation, then use quoted shell
interpolation to build the strings we need safely.
Signed-off-by: Ivan Krylov <krylov.r00t@gmail.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20181014111803.5d83b806@Tarkus
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
By calculating the removed loops, we can get the iteration count.
But the iteration count could be reported incorrectly, reporting
impossibly high counts.
That's because previous code uses the number of removed LBR entries for
the iteration count. That's not good. Fix this by increasing the
iteration count when a loop is detected.
When matching the chain, the iteration count would be added up, finally we need
to compute the average value when printing out.
For example,
$ perf report --branch-history --stdio --no-children
Before:
---f2 +0
|
|--33.62%--f1 +9 (cycles:1)
| f1 +0
| main +22 (cycles:1)
| main +17
| main +38 (cycles:1)
| main +27
| f1 +26 (cycles:1)
| f1 +24
| f2 +27 (cycles:7)
| f2 +0
| f1 +19 (cycles:1)
| f1 +14
| f2 +27 (cycles:11)
| f2 +0
| f1 +9 (cycles:1 iter:2968 avg_cycles:3)
| f1 +0
| main +22 (cycles:1 iter:2968 avg_cycles:3)
| main +17
| main +38 (cycles:1 iter:2968 avg_cycles:3)
2968 is an impossible high iteration count and avg_cycles is too small.
After:
---f2 +0
|
|--33.62%--f1 +9 (cycles:1)
| f1 +0
| main +22 (cycles:1)
| main +17
| main +38 (cycles:1)
| main +27
| f1 +26 (cycles:1)
| f1 +24
| f2 +27 (cycles:7)
| f2 +0
| f1 +19 (cycles:1)
| f1 +14
| f2 +27 (cycles:11)
| f2 +0
| f1 +9 (cycles:1 iter:1 avg_cycles:23)
| f1 +0
| main +22 (cycles:1 iter:1 avg_cycles:23)
| main +17
| main +38 (cycles:1 iter:1 avg_cycles:23)
avg_cycles:23 is the average cycles of this iteration.
Fixes: c4ee06251d ("perf report: Calculate the average cycles of iterations")
Signed-off-by: Jin Yao <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@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1546582230-17507-1-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Nobody has actually used the type (VERIFY_READ vs VERIFY_WRITE) argument
of the user address range verification function since we got rid of the
old racy i386-only code to walk page tables by hand.
It existed because the original 80386 would not honor the write protect
bit when in kernel mode, so you had to do COW by hand before doing any
user access. But we haven't supported that in a long time, and these
days the 'type' argument is a purely historical artifact.
A discussion about extending 'user_access_begin()' to do the range
checking resulted this patch, because there is no way we're going to
move the old VERIFY_xyz interface to that model. And it's best done at
the end of the merge window when I've done most of my merges, so let's
just get this done once and for all.
This patch was mostly done with a sed-script, with manual fix-ups for
the cases that weren't of the trivial 'access_ok(VERIFY_xyz' form.
There were a couple of notable cases:
- csky still had the old "verify_area()" name as an alias.
- the iter_iov code had magical hardcoded knowledge of the actual
values of VERIFY_{READ,WRITE} (not that they mattered, since nothing
really used it)
- microblaze used the type argument for a debug printout
but other than those oddities this should be a total no-op patch.
I tried to fix up all architectures, did fairly extensive grepping for
access_ok() uses, and the changes are trivial, but I may have missed
something. Any missed conversion should be trivially fixable, though.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
We hit a 'perf stat' issue by using following script:
#!/bin/bash
sleep 1000 &
exec perf stat -a -e cycles -I1000 -- sleep 5
Since "perf stat" is launched by exec, the "sleep 1000" would be the
child process of "perf stat". The wait4() call will not return because
it's waiting for the child process "sleep 1000" to end. So 'perf stat'
doesn't return even after 5s passes.
This patch lets 'perf stat' return when the specified child process ends
(in this case, the specified child process is "sleep 5").
Committer testing:
# cat test.sh
#!/bin/bash
sleep 10 &
exec perf stat -a -e cycles -I1000 -- sleep 5
#
Before:
# time ./test.sh
# time counts unit events
1.001113090 108,453,351 cycles
2.002062196 142,075,435 cycles
3.002896194 164,801,068 cycles
4.003731666 107,062,140 cycles
5.002068867 112,241,832 cycles
real 0m10.066s
user 0m0.016s
sys 0m0.101s
#
After:
# time ./test.sh
# time counts unit events
1.001016096 91,412,027 cycles
2.002014963 124,063,708 cycles
3.002883964 125,993,929 cycles
4.003706470 120,465,734 cycles
5.002006778 163,560,355 cycles
real 0m5.123s
user 0m0.014s
sys 0m0.105s
#
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1546501245-4512-1-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Add a comment to perf_session__register_idle_thread() to bring attention to
a pitfall with the idle task thread structure. The pitfall is that there
should really be a 'struct thread' for the idle task of each cpu, but there
is only one that can have pid == tid == 0.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20181221120620.9659-9-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
perf creates a single 'struct thread' to represent the idle task. That
is because threads are identified by PID and TID, and the idle task
always has PID == TID == 0.
However, there are actually separate idle tasks for each CPU. That
creates a problem for thread stack processing which assumes that each
thread has a single stack, not one stack per CPU.
Fix that by passing through the CPU number, and in the case of the idle
"thread", pick the thread stack from an array based on the CPU number.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20181221120620.9659-8-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Ravi Bangoria
Arnaldo Carvalho de Melo
Florian Fainelli
Ingo Molnar
Linus Torvalds
Mattias Jacobsson
Ivan Krylov
Jin Yao
Adrian Hunter