Powerpc has Global Entry Point and Local Entry Point for functions. LEP
catches call from both the GEP and the LEP. Symbol table of ELF contains
GEP and Offset from which we can calculate LEP, but debuginfo does not
have LEP info.
Currently, perf prioritize symbol table over dwarf to probe on LEP for
ppc64le. But when user tries to probe with function parameter, we fall
back to using dwarf(i.e. GEP) and when function called via LEP, probe
will never hit.
For example:
$ objdump -d vmlinux
...
do_sys_open():
c0000000002eb4a0: e8 00 4c 3c addis r2,r12,232
c0000000002eb4a4: 60 00 42 38 addi r2,r2,96
c0000000002eb4a8: a6 02 08 7c mflr r0
c0000000002eb4ac: d0 ff 41 fb std r26,-48(r1)
$ sudo ./perf probe do_sys_open
$ sudo cat /sys/kernel/debug/tracing/kprobe_events
p:probe/do_sys_open _text+3060904
$ sudo ./perf probe 'do_sys_open filename:string'
$ sudo cat /sys/kernel/debug/tracing/kprobe_events
p:probe/do_sys_open _text+3060896 filename_string=+0(%gpr4):string
For second case, perf probed on GEP. So when function will be called via
LEP, probe won't hit.
$ sudo ./perf record -a -e probe:do_sys_open ls
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.195 MB perf.data ]
To resolve this issue, let's not prioritize symbol table, let perf
decide what it wants to use. Perf is already converting GEP to LEP when
it uses symbol table. When perf uses debuginfo, let it find LEP offset
form symbol table. This way we fall back to probe on LEP for all cases.
After patch:
$ sudo ./perf probe 'do_sys_open filename:string'
$ sudo cat /sys/kernel/debug/tracing/kprobe_events
p:probe/do_sys_open _text+3060904 filename_string=+0(%gpr4):string
$ sudo ./perf record -a -e probe:do_sys_open ls
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.197 MB perf.data (11 samples) ]
Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1470723805-5081-2-git-send-email-ravi.bangoria@linux.vnet.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The 'perf probe' tool detects a variable's type and use the detected
type to add a new probe. Then, kprobes prints its variable in
hexadecimal format if the variable is unsigned and prints in decimal if
it is signed.
We sometimes want to see unsigned variable in decimal format (i.e.
sector_t or size_t). In that case, we need to investigate the variable's
size manually to specify just signedness.
This patch add signedness casting support. By specifying "s" or "u" as a
type, perf-probe will investigate variable size as usual and use the
specified signedness.
E.g. without this:
$ perf probe -a 'submit_bio bio->bi_iter.bi_sector'
Added new event:
probe:submit_bio (on submit_bio with bi_sector=bio->bi_iter.bi_sector)
You can now use it in all perf tools, such as:
perf record -e probe:submit_bio -aR sleep 1
$ cat trace_pipe|head
dbench-9692 [003] d..1 971.096633: submit_bio: (submit_bio+0x0/0x140) bi_sector=0x3a3d00
dbench-9692 [003] d..1 971.096685: submit_bio: (submit_bio+0x0/0x140) bi_sector=0x1a3d80
dbench-9692 [003] d..1 971.096687: submit_bio: (submit_bio+0x0/0x140) bi_sector=0x3a3d80
...
// need to investigate the variable size
$ perf probe -a 'submit_bio bio->bi_iter.bi_sector:s64'
Added new event:
probe:submit_bio (on submit_bio with bi_sector=bio->bi_iter.bi_sector:s64)
You can now use it in all perf tools, such as:
perf record -e probe:submit_bio -aR sleep 1
With this:
// just use "s" to cast its signedness
$ perf probe -v -a 'submit_bio bio->bi_iter.bi_sector:s'
Added new event:
probe:submit_bio (on submit_bio with bi_sector=bio->bi_iter.bi_sector:s)
You can now use it in all perf tools, such as:
perf record -e probe:submit_bio -aR sleep 1
$ cat trace_pipe|head
dbench-9689 [001] d..1 1212.391237: submit_bio: (submit_bio+0x0/0x140) bi_sector=128
dbench-9689 [001] d..1 1212.391252: submit_bio: (submit_bio+0x0/0x140) bi_sector=131072
dbench-9697 [006] d..1 1212.398611: submit_bio: (submit_bio+0x0/0x140) bi_sector=30208
This commit also update perf-probe.txt to describe "types". Most parts
are based on existing documentation: Documentation/trace/kprobetrace.txt
Committer note:
Testing using 'perf trace':
# perf probe -a 'submit_bio bio->bi_iter.bi_sector'
Added new event:
probe:submit_bio (on submit_bio with bi_sector=bio->bi_iter.bi_sector)
You can now use it in all perf tools, such as:
perf record -e probe:submit_bio -aR sleep 1
# trace --no-syscalls --ev probe:submit_bio
0.000 probe:submit_bio:(ffffffffac3aee00) bi_sector=0xc133c0)
3181.861 probe:submit_bio:(ffffffffac3aee00) bi_sector=0x6cffb8)
3181.881 probe:submit_bio:(ffffffffac3aee00) bi_sector=0x6cffc0)
3184.488 probe:submit_bio:(ffffffffac3aee00) bi_sector=0x6cffc8)
<SNIP>
4717.927 probe:submit_bio:(ffffffffac3aee00) bi_sector=0x4dc7a88)
4717.970 probe:submit_bio:(ffffffffac3aee00) bi_sector=0x4dc7880)
^C[root@jouet ~]#
Now, using this new feature:
[root@jouet ~]# perf probe -a 'submit_bio bio->bi_iter.bi_sector:s'
Added new event:
probe:submit_bio (on submit_bio with bi_sector=bio->bi_iter.bi_sector:s)
You can now use it in all perf tools, such as:
perf record -e probe:submit_bio -aR sleep 1
[root@jouet ~]# trace --no-syscalls --ev probe:submit_bio
0.000 probe:submit_bio:(ffffffffac3aee00) bi_sector=7145704)
0.017 probe:submit_bio:(ffffffffac3aee00) bi_sector=7145712)
0.019 probe:submit_bio:(ffffffffac3aee00) bi_sector=7145720)
2.567 probe:submit_bio:(ffffffffac3aee00) bi_sector=7145728)
5631.919 probe:submit_bio:(ffffffffac3aee00) bi_sector=0)
5631.941 probe:submit_bio:(ffffffffac3aee00) bi_sector=8)
5631.945 probe:submit_bio:(ffffffffac3aee00) bi_sector=16)
5631.948 probe:submit_bio:(ffffffffac3aee00) bi_sector=24)
^C#
With callchains:
# trace --no-syscalls --ev probe:submit_bio/max-stack=10/
0.000 probe:submit_bio:(ffffffffac3aee00) bi_sector=50662544)
submit_bio+0xa8200001 ([kernel.kallsyms])
submit_bh+0xa8200013 ([kernel.kallsyms])
jbd2_journal_commit_transaction+0xa8200691 ([kernel.kallsyms])
kjournald2+0xa82000ca ([kernel.kallsyms])
kthread+0xa82000d8 ([kernel.kallsyms])
ret_from_fork+0xa820001f ([kernel.kallsyms])
0.023 probe:submit_bio:(ffffffffac3aee00) bi_sector=50662552)
submit_bio+0xa8200001 ([kernel.kallsyms])
submit_bh+0xa8200013 ([kernel.kallsyms])
jbd2_journal_commit_transaction+0xa8200691 ([kernel.kallsyms])
kjournald2+0xa82000ca ([kernel.kallsyms])
kthread+0xa82000d8 ([kernel.kallsyms])
ret_from_fork+0xa820001f ([kernel.kallsyms])
0.027 probe:submit_bio:(ffffffffac3aee00) bi_sector=50662560)
submit_bio+0xa8200001 ([kernel.kallsyms])
submit_bh+0xa8200013 ([kernel.kallsyms])
jbd2_journal_commit_transaction+0xa8200691 ([kernel.kallsyms])
kjournald2+0xa82000ca ([kernel.kallsyms])
kthread+0xa82000d8 ([kernel.kallsyms])
ret_from_fork+0xa820001f ([kernel.kallsyms])
2.593 probe:submit_bio:(ffffffffac3aee00) bi_sector=50662568)
submit_bio+0xa8200001 ([kernel.kallsyms])
submit_bh+0xa8200013 ([kernel.kallsyms])
journal_submit_commit_record+0xa82001ac ([kernel.kallsyms])
jbd2_journal_commit_transaction+0xa82012e8 ([kernel.kallsyms])
kjournald2+0xa82000ca ([kernel.kallsyms])
kthread+0xa82000d8 ([kernel.kallsyms])
ret_from_fork+0xa820001f ([kernel.kallsyms])
^C#
Signed-off-by: Naohiro Aota <naohiro.aota@hgst.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Hemant Kumar <hemant@linux.vnet.ibm.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1470710408-23515-1-git-send-email-naohiro.aota@hgst.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
When we don't have a tracee (i.e. we're attaching to a task or CPU),
counters can still be running after our workload finishes, and can still
be running as we read their values. As we read events one-by-one, there
can be arbitrary skew between values of events, even within a group.
This means that ratios within an event group are not reliable.
This skew can be seen if measuring a group of identical events, e.g:
# perf stat -a -C0 -e '{cycles,cycles}' sleep 1
To avoid this, we must stop groups from counting before we read the
values of any constituent events. This patch adds and makes use of a new
disable_counters() helper, which disables group leaders (and thus each
group as a whole). This mirrors the use of enable_counters() for
starting event groups in the absence of a tracee.
Closing a group leader splits the group, and without a disabled group
leader the newly split events will begin counting. Thus to ensure counts
are reliable we must defer closing group leaders until all counts have
been read. To do so this patch removes the event closing logic from the
read_counters() helper, explicitly closes the events using
perf_evlist__close(), which also aids legibility.
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1470747869-3567-1-git-send-email-mark.rutland@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:
New features:
- Add --sample-cpu to 'perf record', to explicitely ask for sampling
the CPU (Jiri Olsa)
Fixes:
- Fix processing of multi byte chunks in objdump output, fixing
disassemble processing for annotation on at least ARM64 (Jan Stancek)
- Use SyS_epoll_wait in a BPF 'perf test' entry instead of sys_epoll_wait, that
is not present in the DWARF info in vmlinux files (Arnaldo Carvalho de Melo)
- Add -wno-shadow when processing files using perl headers, fixing
the build on Fedora Rawhide and Arch Linux (Namhyung Kim)
Infrastructure changes:
- Annotate prep work to better catch and report errors related to
using objdump to disassemble DSOs (Arnaldo Carvalho de Melo)
- Add 'alloc', 'scnprintf' and 'and' methods for bitmap processing (Jiri Olsa)
- Add nested output resorting callback in hists processing (Jiri Olsa)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Something made the sys_epoll_wait() function alias not to be found in
the vmlinux DWARF info, being found only in /proc/kallsyms, which made
the BPF perf tests to fail:
[root@jouet ~]# perf test BPF
37: Test BPF filter :
37.1: Test basic BPF filtering : FAILED!
37.2: Test BPF prologue generation : Skip
37.3: Test BPF relocation checker : Skip
[root@jouet ~]#
Using -v we can see it is failing to find DWARF info for the probed function,
sys_epoll_wait, which we can find in /proc/kallsyms but not in vmlinux with
CONFIG_DEBUG_INFO:
[root@jouet ~]# grep -w sys_epoll_wait /proc/kallsyms
ffffffffbd295b50 T sys_epoll_wait
[root@jouet ~]#
[root@jouet ~]# readelf -wi /lib/modules/4.7.0+/build/vmlinux | grep -w sys_epoll_wait
[root@jouet ~]#
If we try to use perf probe:
[root@jouet ~]# perf probe sys_epoll_wait
Failed to find debug information for address ffffffffbd295b50
Probe point 'sys_epoll_wait' not found.
Error: Failed to add events.
[root@jouet ~]#
It all works if we use SyS_epoll_wait, that is just an alias to the probed
function:
[root@jouet ~]# grep -i sys_epoll_wait /proc/kallsyms
ffffffffbd295b50 T SyS_epoll_wait
ffffffffbd295b50 T sys_epoll_wait
[root@jouet ~]#
So use it:
[root@jouet ~]# perf test BPF
37: Test BPF filter :
37.1: Test basic BPF filtering : Ok
37.2: Test BPF prologue generation : Ok
37.3: Test BPF relocation checker : Ok
[root@jouet ~]#
Further info:
[root@jouet ~]# gcc --version
gcc (GCC) 6.1.1 20160621 (Red Hat 6.1.1-3)
[acme@jouet linux]$ cat /etc/fedora-release
Fedora release 24 (Twenty Four)
Investigation as to why it fails is still underway, but it was always
going from sys_epoll_wait to SyS_epoll_wait when looking up the DWARF
info in vmlinux, and this is what is breaking now.
Switching to use SyS_epoll_wait allows this test to proceed and test the
BPF code it was designed for, so lets have this in to allow passing this
test while we fix the root cause.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexei Starovoitov <alexei.starovoitov@gmail.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-7hekjp0bodwjbb419sl2b55h@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
On my Archlinux machine, perf faild to build like below:
CC scripts/perl/Perf-Trace-Util/Context.o
In file included from /usr/lib/perl5/core/perl/CORE/perl.h:3905:0,
from Context.xs:23:
/usr/lib/perl5/core/perl/CORE/inline.h: In function :
/usr/lib/perl5/core/perl/CORE/cop.h:612:13: warning: declaration of 'av'
shadows a previous local [-Werror-shadow]
AV *av =3D GvAV(PL_defgv);
^
/usr/lib/perl5/core/perl/CORE/inline.h:526:5: note: in expansion of
macro 'CX_POP_SAVEARRAY'
CX_POP_SAVEARRAY(cx);
^~~~~~~~~~~~~~~~
In file included from /usr/lib/perl5/core/perl/CORE/perl.h:5853:0,
from Context.xs:23:
/usr/lib/perl5/core/perl/CORE/inline.h:518:9: note:
shadowed declaration is here
AV *av;
^~
What I did to fix is adding '-Wno-shadow' as the error message said it's
the cause of the failure. Since it's from the perl (not perf) code
base, we don't have the control so I just wanted to ignore the warning
when compiling perl scripting code.
Committer note:
This also fixes the build on Fedora Rawhide.
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20160802024317.31725-1-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
If dso__build_id_filename(..., NULL, ...) returns !NULL its because it
allocated it, so, when reaching the 'if (dso__is_kcore()) test, we
already checked that and were just "fallbacking" to using
dso->long_name, but without freeing filename, thus leaking it.
Fix it by adding the dso__is_kcore() test to the 'or' group just after
it, the one containing the full fallback code, including freeing the
filename.
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>
Fixes: ee205503f2 ("perf tools: Fix annotation with kcore")
Link: http://lkml.kernel.org/n/tip-qi4rpjq8yo6myvg99kkgt0xz@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
We were just using pr_error() which makes it difficult for non stdio UIs
to provide errors using its widgets, as they need to somehow catch what
was passed to pr_error().
Fix it by introducing a __strerror() interface like the ones used
elsewhere, for instance target__strerror().
This is just the initial step, more work will be done, but first some
error handling bugs noticed while working on this need to be dealt with.
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-dgd22zl2xg7x4vcnoa83jxfb@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Pull perf fixes from Thomas Gleixner:
"This update contains:
- a fix for the bpf tools to use the new EM_BPF code
- a fix for the module parser of perf to retrieve the
proper text start address
- add str_error_c to libapi to avoid linking against
tools/lib/str_error_r.o"
* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
tools lib api: Add str_error_c to libapi
perf s390: Fix 'start' address of module's map
tools lib bpf: Use official ELF e_machine value
Pull libnvdimm updates from Dan Williams:
- Replace pcommit with ADR / directed-flushing.
The pcommit instruction, which has not shipped on any product, is
deprecated. Instead, the requirement is that platforms implement
either ADR, or provide one or more flush addresses per nvdimm.
ADR (Asynchronous DRAM Refresh) flushes data in posted write buffers
to the memory controller on a power-fail event.
Flush addresses are defined in ACPI 6.x as an NVDIMM Firmware
Interface Table (NFIT) sub-structure: "Flush Hint Address Structure".
A flush hint is an mmio address that when written and fenced assures
that all previous posted writes targeting a given dimm have been
flushed to media.
- On-demand ARS (address range scrub).
Linux uses the results of the ACPI ARS commands to track bad blocks
in pmem devices. When latent errors are detected we re-scrub the
media to refresh the bad block list, userspace can also request a
re-scrub at any time.
- Support for the Microsoft DSM (device specific method) command
format.
- Support for EDK2/OVMF virtual disk device memory ranges.
- Various fixes and cleanups across the subsystem.
* tag 'libnvdimm-for-4.8' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (41 commits)
libnvdimm-btt: Delete an unnecessary check before the function call "__nd_device_register"
nfit: do an ARS scrub on hitting a latent media error
nfit: move to nfit/ sub-directory
nfit, libnvdimm: allow an ARS scrub to be triggered on demand
libnvdimm: register nvdimm_bus devices with an nd_bus driver
pmem: clarify a debug print in pmem_clear_poison
x86/insn: remove pcommit
Revert "KVM: x86: add pcommit support"
nfit, tools/testing/nvdimm/: unify shutdown paths
libnvdimm: move ->module to struct nvdimm_bus_descriptor
nfit: cleanup acpi_nfit_init calling convention
nfit: fix _FIT evaluation memory leak + use after free
tools/testing/nvdimm: add manufacturing_{date|location} dimm properties
tools/testing/nvdimm: add virtual ramdisk range
acpi, nfit: treat virtual ramdisk SPA as pmem region
pmem: kill __pmem address space
pmem: kill wmb_pmem()
libnvdimm, pmem: use nvdimm_flush() for namespace I/O writes
fs/dax: remove wmb_pmem()
libnvdimm, pmem: flush posted-write queues on shutdown
...
After the previous patch, we can distinguish costly allocations that
should be really lightweight, such as THP page faults, with
__GFP_NORETRY. This means we don't need to recognize khugepaged
allocations via PF_KTHREAD anymore. We can also change THP page faults
in areas where madvise(MADV_HUGEPAGE) was used to try as hard as
khugepaged, as the process has indicated that it benefits from THP's and
is willing to pay some initial latency costs.
We can also make the flags handling less cryptic by distinguishing
GFP_TRANSHUGE_LIGHT (no reclaim at all, default mode in page fault) from
GFP_TRANSHUGE (only direct reclaim, khugepaged default). Adding
__GFP_NORETRY or __GFP_KSWAPD_RECLAIM is done where needed.
The patch effectively changes the current GFP_TRANSHUGE users as
follows:
* get_huge_zero_page() - the zero page lifetime should be relatively
long and it's shared by multiple users, so it's worth spending some
effort on it. We use GFP_TRANSHUGE, and __GFP_NORETRY is not added.
This also restores direct reclaim to this allocation, which was
unintentionally removed by commit e4a49efe4e7e ("mm: thp: set THP defrag
by default to madvise and add a stall-free defrag option")
* alloc_hugepage_khugepaged_gfpmask() - this is khugepaged, so latency
is not an issue. So if khugepaged "defrag" is enabled (the default), do
reclaim via GFP_TRANSHUGE without __GFP_NORETRY. We can remove the
PF_KTHREAD check from page alloc.
As a side-effect, khugepaged will now no longer check if the initial
compaction was deferred or contended. This is OK, as khugepaged sleep
times between collapsion attempts are long enough to prevent noticeable
disruption, so we should allow it to spend some effort.
* migrate_misplaced_transhuge_page() - already was masking out
__GFP_RECLAIM, so just convert to GFP_TRANSHUGE_LIGHT which is
equivalent.
* alloc_hugepage_direct_gfpmask() - vma's with VM_HUGEPAGE (via madvise)
are now allocating without __GFP_NORETRY. Other vma's keep using
__GFP_NORETRY if direct reclaim/compaction is at all allowed (by default
it's allowed only for madvised vma's). The rest is conversion to
GFP_TRANSHUGE(_LIGHT).
[mhocko@suse.com: suggested GFP_TRANSHUGE_LIGHT]
Link: http://lkml.kernel.org/r/20160721073614.24395-7-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
