Add missing dso__put for the dso created in maps__split_kallsyms.
Signed-off-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
In dso__process_kernel_symbol if inserting a map fails, probably
ENOMEM, then the reference count puts were missing on the dso and map.
Signed-off-by: Ian Rogers <irogers@google.com>
Reviewed-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
The '-o' option exists for the SVG creation but not for `perf
timechart record`. Add to better allow testing.
Signed-off-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
There are 2 slots left for kvm_add_default_arch_event, fix the
assertion so that debug builds don't fail the assert and to agree with
the comment.
Fixes: 45ff39f6e7 ("perf tools kvm: Fix the potential out of range memory access issue")
Signed-off-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
In 754187ad73 ("perf build: Remove NO_AUXTRACE build option")
sys/types.h was removed, which broke the build in all Alpine Linux
releases, as musl libc has pid_t defined via sys/types.h, add it back.
Fixes: 754187ad73 ("perf build: Remove NO_AUXTRACE build option")
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Create a fake root directory for /proc/{version,modules,kallsyms} in
/tmp for testing. The kallsyms has a bad symbol in the module and it
causes the main map splitted. The test ensures it only has two maps -
kernel and the module and it finds the initial map after the module
without creating the split maps like [kernel].0 and so on.
$ perf test -vv "split kallsyms"
69: split kallsyms:
--- start ---
test child forked, pid 1016196
try to create fake root directory
create kernel maps from the fake root directory
maps__set_modules_path_dir: cannot open /tmp/perf-test.Zrv6Sy/lib/modules/X.Y.Z dir
Problems setting modules path maps, continuing anyway...
Failed to open /tmp/perf-test.Zrv6Sy/proc/kcore. Note /proc/kcore requires CAP_SYS_RAWIO capability to access.
Using /tmp/perf-test.Zrv6Sy/proc/kallsyms for symbols
kernel map loaded - check symbol and map
---- end(0) ----
69: split kallsyms : Ok
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
This is for test functions to find the kallsyms correctly. It can find
the machine from the kernel maps and use its root_dir. This is helpful
to setup fake /proc directory for testing.
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
In maps__split_kallsyms(), it assumes new kernel map when it finds a
symbol without module after any module and the initial kernel map has
some symbols. Because it expects modules are out of the kernel map so
modules should not have symbols in the kernel map.
For example, the following memory map shows symbols and maps. Any
symbols in the module 1 area will go to the module 1. The main kernel
map starts at 0xffffffffbc200000. But if any symbol has a module
between the symbols in that area, next symbols after 0xffffffffbd008000
will generate new kernel maps like [kernel].1.
kernel address | |
| |
0xffffffffc0000000 |---------------------|
| (symbols) |
| ... | <--- [kernel].N
0xffffffffbc400000 |---------------------|
| (symbols) |
| module 2 | <--- bad?
0xffffffffbc380000 |---------------------|
| ... |
| (symbols) |
| [kernel.kallsyms] | <--- initial map
0xffffffffbc200000 |---------------------|
| |
| |
0xffffffffabcde000 |---------------------|
| (symbols) |
| module 1 |
0xffffffffabcd0000 |---------------------|
This is very fragile when the module has a symbol that falls into the
main kernel map for some reason. My system has a livepatch module with
such symbols. And it created a lot of new kernel maps after those
symbols. But the symbol may have broken addresses and the later symbols
can still be found in the initial kernel map.
Let's check the symbol address in the initial map and use it if found.
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
It's counted twice as it's increased after calling maps__insert(). I
guess we want to increase it only after it's added properly.
Reviewed-by: Ian Rogers <irogers@google.com>
Fixes: 2e538c4a18 ("perf tools: Improve kernel/modules symbol lookup")
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
The maps__split_kallsyms() will split symbols to module DSOs if it comes
from a module. It also handled some unusual kernel symbols after modules
by creating new kernel maps like "[kernel].0".
But they are pseudo DSOs to have those unexpected symbols. They should
not be considered as unloaded kernel DSOs. Otherwise the dso__load()
for them will end up calling dso__load_kallsyms() and then
maps__split_kallsyms() again and again.
Reviewed-by: Ian Rogers <irogers@google.com>
Fixes: 2e538c4a18 ("perf tools: Improve kernel/modules symbol lookup")
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
It's possible that some kernel samples don't have matching deferred
callchain records when the profiling session was ended before the
threads came back to userspace. Let's flush the samples before
finish the session.
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Save samples with deferred callchains in a separate list and deliver
them after merging the user callchains. If users don't want to merge
they can set tool->merge_deferred_callchains to false to prevent the
behavior.
With previous result, now perf script will show the merged callchains.
$ perf script
...
pwd 2312 121.163435: 249113 cpu/cycles/P:
ffffffff845b78d8 __build_id_parse.isra.0+0x218 ([kernel.kallsyms])
ffffffff83bb5bf6 perf_event_mmap+0x2e6 ([kernel.kallsyms])
ffffffff83c31959 mprotect_fixup+0x1e9 ([kernel.kallsyms])
ffffffff83c31dc5 do_mprotect_pkey+0x2b5 ([kernel.kallsyms])
ffffffff83c3206f __x64_sys_mprotect+0x1f ([kernel.kallsyms])
ffffffff845e6692 do_syscall_64+0x62 ([kernel.kallsyms])
ffffffff8360012f entry_SYSCALL_64_after_hwframe+0x76 ([kernel.kallsyms])
7f18fe337fa7 mprotect+0x7 (/lib/x86_64-linux-gnu/ld-linux-x86-64.so.2)
7f18fe330e0f _dl_sysdep_start+0x7f (/lib/x86_64-linux-gnu/ld-linux-x86-64.so.2)
7f18fe331448 _dl_start_user+0x0 (/lib/x86_64-linux-gnu/ld-linux-x86-64.so.2)
...
The old output can be get using --no-merge-callchain option.
Also perf report can get the user callchain entry at the end.
$ perf report --no-children --stdio -q -S __build_id_parse.isra.0
# symbol: __build_id_parse.isra.0
8.40% pwd [kernel.kallsyms]
|
---__build_id_parse.isra.0
perf_event_mmap
mprotect_fixup
do_mprotect_pkey
__x64_sys_mprotect
do_syscall_64
entry_SYSCALL_64_after_hwframe
mprotect
_dl_sysdep_start
_dl_start_user
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Add a new callchain record mode option for deferred callchains. For now
it only works with FP (frame-pointer) mode.
And add the missing feature detection logic to clear the flag on old
kernels.
$ perf record --call-graph fp,defer -vv true
...
------------------------------------------------------------
perf_event_attr:
type 0 (PERF_TYPE_HARDWARE)
size 136
config 0 (PERF_COUNT_HW_CPU_CYCLES)
{ sample_period, sample_freq } 4000
sample_type IP|TID|TIME|CALLCHAIN|PERIOD
read_format ID|LOST
disabled 1
inherit 1
mmap 1
comm 1
freq 1
enable_on_exec 1
task 1
sample_id_all 1
mmap2 1
comm_exec 1
ksymbol 1
bpf_event 1
defer_callchain 1
defer_output 1
------------------------------------------------------------
sys_perf_event_open: pid 162755 cpu 0 group_fd -1 flags 0x8
sys_perf_event_open failed, error -22
switching off deferred callchain support
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Add a new event type for deferred callchains and a new callback for the
struct perf_tool. For now it doesn't actually handle the deferred
callchains but it just marks the sample if it has the PERF_CONTEXT_
USER_DEFFERED in the callchain array.
At least, perf report can dump the raw data with this change. Actually
this requires the next commit to enable attr.defer_callchain, but if you
already have a data file, it'll show the following result.
$ perf report -D
...
0x2158@perf.data [0x40]: event: 22
.
. ... raw event: size 64 bytes
. 0000: 16 00 00 00 02 00 40 00 06 00 00 00 0b 00 00 00 ......@.........
. 0010: 03 00 00 00 00 00 00 00 a7 7f 33 fe 18 7f 00 00 ..........3.....
. 0020: 0f 0e 33 fe 18 7f 00 00 48 14 33 fe 18 7f 00 00 ..3.....H.3.....
. 0030: 08 09 00 00 08 09 00 00 e6 7a e7 35 1c 00 00 00 .........z.5....
121163447014 0x2158 [0x40]: PERF_RECORD_CALLCHAIN_DEFERRED(IP, 0x2): 2312/2312: 0xb00000006
... FP chain: nr:3
..... 0: 00007f18fe337fa7
..... 1: 00007f18fe330e0f
..... 2: 00007f18fe331448
: unhandled!
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
It needs to sync with the kernel to support user space changes for the
deferred callchains.
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
For metric groups, skip metrics in the list that are None. This allows
functions to better optionally return metrics.
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Thomas Falcon <thomas.falcon@intel.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Drop adding a pending metric if there is an existing one. Ensure the
PMUs differ for hybrid systems.
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Thomas Falcon <thomas.falcon@intel.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Have dedicated encode functions rather than having them embedded in
MetricGroup. This is to provide some uniformity in the Metric ToXXX
routines.
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Thomas Falcon <thomas.falcon@intel.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Support negative exponents when parsing from a json metric string by
making the numbers after the 'e' optional in the 'Event' insertion fix
up.
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Thomas Falcon <thomas.falcon@intel.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
It can be convenient to have unnamed metric groups for the sake of
organizing other metrics and metric groups. An unspecified name
shouldn't contribute to the MetricGroup json value, so don't record
it.
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Thomas Falcon <thomas.falcon@intel.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Previous metric constraints were binary, either none or don't group
when the NMI watchdog is present. Update to match the definitions in
'enum metric_event_groups' in pmu-events.h.
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Thomas Falcon <thomas.falcon@intel.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Allow multiple metricgroups.json files by handling any file ending
with metricgroups.json as a metricgroups file.
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Thomas Falcon <thomas.falcon@intel.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
This happens on hybrid machine metrics. Be tolerant and don't cause
the ilist application to crash with an exception.
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Thomas Falcon <thomas.falcon@intel.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Ensure the metric_leader is copied and set up correctly. In
compute_metric determine the correct metric_leader event to match the
requested CPU. Fixes the handling of metrics particularly on hybrid
machines.
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Thomas Falcon <thomas.falcon@intel.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Add a test case for the python interpreter like below so that we can
make sure it won't break again. To validate the effect of build-ID
generation, it adds and removes the JIT'ed DSOs to/from the build-ID
cache for the test.
$ perf test -vv jitdump
84: python profiling with jitdump:
--- start ---
test child forked, pid 214316
Run python with -Xperf_jit
[ perf record: Woken up 5 times to write data ]
[ perf record: Captured and wrote 1.180 MB /tmp/__perf_test.perf.data.XbqZNm (140 samples) ]
Generate JIT-ed DSOs using perf inject
Add JIT-ed DSOs to the build-ID cache
Check the symbol containing the script name
Found 108 matching lines
Remove JIT-ed DSOs from the build-ID cache
---- end(0) ----
84: python profiling with jitdump : Ok
Cc: Pablo Galindo <pablogsal@gmail.com>
Link: https://docs.python.org/3/howto/perf_profiling.html#how-to-work-without-frame-pointers
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
It was reported that python backtrace with JIT dump was broken after the
change to built-in SHA-1 implementation. It seems python generates the
same JIT code for each function. They will become separate DSOs but the
contents are the same. Only difference is in the symbol name.
But this caused a problem that every JIT'ed DSOs will have the same
build-ID which makes perf confused. And it resulted in no python
symbols (from JIT) in the output.
Looking back at the original code before the conversion, it used the
load_addr as well as the code section to distinguish each DSO. But it'd
be better to use contents of symtab and strtab instead as it aligns with
some linker behaviors.
This patch adds a buffer to save all the contents in a single place for
SHA-1 calculation. Probably we need to add sha1_update() or similar to
update the existing hash value with different contents and use it here.
But it's out of scope for this change and I'd like something that can be
backported to the stable trees easily.
Reviewed-by: Ian Rogers <irogers@google.com>
Cc: Eric Biggers <ebiggers@kernel.org>
Cc: Pablo Galindo <pablogsal@gmail.com>
Cc: Fangrui Song <maskray@sourceware.org>
Link: https://github.com/python/cpython/issues/139544
Fixes: e3f612c1d8 ("perf genelf: Remove libcrypto dependency and use built-in sha1()")
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
The mem-loads-aux event exists on hybrid systems but the "cpu" PMU
does not. This causes an event parsing error which erroneously makes
the test look like it is failing. Avoid naming the PMU to avoid
this. Rather than cleaning up perf.data in the directory the test is
run, explicitly send the 'perf record' output to /dev/null and avoid
any cleanup scripts.
Fixes: fc9c17b223 ("perf test: Add a perf event fallback test")
Signed-off-by: Ian Rogers <irogers@google.com>
Reviewed-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
So that it can show the correct encoding info in the JSON output.
$ perf list -j hw
[
{
"Unit": "cpu",
"Topic": "legacy hardware",
"EventName": "branch-instructions",
"EventType": "Kernel PMU event",
"BriefDescription": "Retired branch instructions [This event is an alias of branches]",
"Encoding": "cpu/event=0xc4/"
},
...
Reviewed-by: Ian Rogers <irogers@google.com>
Suggested-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Recent changes in the linux-next kernel will add new field for syscalls
to have contents in the userspace like below.
# cat /sys/kernel/tracing/events/syscalls/sys_enter_write/format
name: sys_enter_write
ID: 758
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:int __syscall_nr; offset:8; size:4; signed:1;
field:unsigned int fd; offset:16; size:8; signed:0;
field:const char * buf; offset:24; size:8; signed:0;
field:size_t count; offset:32; size:8; signed:0;
field:__data_loc char[] __buf_val; offset:40; size:4; signed:0;
print fmt: "fd: 0x%08lx, buf: 0x%08lx (%s), count: 0x%08lx", ((unsigned long)(REC->fd)),
((unsigned long)(REC->buf)), __print_dynamic_array(__buf_val, 1),
((unsigned long)(REC->count))
We have a different way to handle those arguments and this change
confuses perf trace then make some tests failing. Fix it by skipping
the new fields that have "__data_loc char[]" type.
Maybe we can switch to this instead of the BPF augmentation later.
Reviewed-by: Howard Chu <howardchu95@gmail.com>
Tested-by: Thomas Richter <tmricht@linux.ibm.com>
Tested-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Howard Chu <howardchu95@gmail.com>
Reported-by: Thomas Richter <tmricht@linux.ibm.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Simplify the build ID reading code by removing the non-blocking option.
Having to pass the correct option to this function was fragile and a
mistake would result in a hang, see the linked fix. Furthermore,
compressed files are always opened blocking anyway, ignoring the
non-blocking option.
We also don't expect to read build IDs from non-regular files. The only
hits to this function that are non-regular are devices that won't be elf
files with build IDs, for example "/dev/dri/renderD129".
Now instead of opening these as non-blocking and failing to read, we
skip them. Even if something like a pipe or character device did have a
build ID, I don't think it would have worked because you need to call
read() in a loop, check for -EAGAIN and handle timeouts to make
non-blocking reads work.
Link: https://lore.kernel.org/linux-perf-users/20251022-james-perf-fix-dso-block-v1-1-c4faab150546@linaro.org/
Signed-off-by: James Clark <james.clark@linaro.org>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
T-HEAD C920 has a V2 iteration, which supports Sscompmf. The V2
iteration supports the same perf events as V1.
Reuse T-HEAD c900-legacy JSON file for T-HEAD C920V2.
Signed-off-by: Inochi Amaoto <inochiama@gmail.com>
Acked-by: Paul Walmsley <pjw@kernel.org>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
FEAT_SPE_EFT and FEAT_SPE_FDS etc have new user facing format attributes
so document them. Also document existing 'event_filter' bits that were
missing from the doc and the fact that latency values are stored in the
weight field.
Reviewed-by: Leo Yan <leo.yan@arm.com>
Tested-by: Leo Yan <leo.yan@arm.com>
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: James Clark <james.clark@linaro.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Usage of strcpy() can lead to buffer overflows. Therefore, it has been
replaced with strncpy(). The output file path is provided as a parameter
and might be restricted by command-line by default. But this defensive
patch will prevent any potential overflow, making the code more robust
against future changes in input handling.
Testing:
- ran perf test from tools/perf and did not observe any regression with
the earlier code
Signed-off-by: Hrishikesh Suresh <hrishikesh123s@gmail.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Ian Rogers
Leo Yan
Arnaldo Carvalho de Melo
Namhyung Kim
James Clark
Inochi Amaoto
Anubhav Shelat
Hrishikesh Suresh