Pull perf tools updates from Namhyung Kim:
"Build:
- Compile BPF programs by default if clang (>= 12.0.1) is available
to enable more features like kernel lock contention, off-cpu
profiling, kwork, sample filtering and so on.
This can be disabled by passing BUILD_BPF_SKEL=0 to make.
- Produce better error messages for bison on debug build (make
DEBUG=1) by defining YYDEBUG symbol internally.
perf record:
- Track sideband events (like FORK/MMAP) from all CPUs even if perf
record targets a subset of CPUs only (using -C option). Otherwise
it may lose some information happened on a CPU out of the target
list.
- Fix checking raw sched_switch tracepoint argument using system BTF.
This affects off-cpu profiling which attaches a BPF program to the
raw tracepoint.
perf lock contention:
- Add --lock-cgroup option to see contention by cgroups. This should
be used with BPF only (using -b option).
$ sudo perf lock con -ab --lock-cgroup -- sleep 1
contended total wait max wait avg wait cgroup
835 14.06 ms 41.19 us 16.83 us /system.slice/led.service
25 122.38 us 13.77 us 4.89 us /
44 23.73 us 3.87 us 539 ns /user.slice/user-657345.slice/session-c4.scope
1 491 ns 491 ns 491 ns /system.slice/connectd.service
- Add -G/--cgroup-filter option to see contention only for given
cgroups.
This can be useful when you identified a cgroup in the above
command and want to investigate more on it. It also works with
other output options like -t/--threads and -l/--lock-addr.
$ sudo perf lock con -ab -G /user.slice/user-657345.slice/session-c4.scope -- sleep 1
contended total wait max wait avg wait type caller
8 77.11 us 17.98 us 9.64 us spinlock futex_wake+0xc8
2 24.56 us 14.66 us 12.28 us spinlock tick_do_update_jiffies64+0x25
1 4.97 us 4.97 us 4.97 us spinlock futex_q_lock+0x2a
- Use per-cpu array for better spinlock tracking. This is to improve
performance of the BPF program and to avoid nested contention on a
lock in the BPF hash map.
- Update callstack check for PowerPC. To find a representative caller
of a lock, it needs to look up the call stacks. It ends the lookup
when it sees 0 in the call stack buffer. However, PowerPC call
stacks can have 0 values in the beginning so skip them when it
expects valid call stacks after.
perf kwork:
- Support 'sched' class (for -k option) so that it can see task
scheduling event (using sched_switch tracepoint) as well as irq and
workqueue items.
- Add perf kwork top subcommand to show more accurate cpu utilization
with sched class above. It works both with a recorded data (using
perf kwork record command) and BPF (using -b option). Unlike perf
top command, it does not support interactive mode (yet).
$ sudo perf kwork top -b -k sched
Starting trace, Hit <Ctrl+C> to stop and report
^C
Total : 160702.425 ms, 8 cpus
%Cpu(s): 36.00% id, 0.00% hi, 0.00% si
%Cpu0 [|||||||||||||||||| 61.66%]
%Cpu1 [|||||||||||||||||| 61.27%]
%Cpu2 [||||||||||||||||||| 66.40%]
%Cpu3 [|||||||||||||||||| 61.28%]
%Cpu4 [|||||||||||||||||| 61.82%]
%Cpu5 [||||||||||||||||||||||| 77.41%]
%Cpu6 [|||||||||||||||||| 61.73%]
%Cpu7 [|||||||||||||||||| 63.25%]
PID SPID %CPU RUNTIME COMMMAND
-------------------------------------------------------------
0 0 38.72 8089.463 ms [swapper/1]
0 0 38.71 8084.547 ms [swapper/3]
0 0 38.33 8007.532 ms [swapper/0]
0 0 38.26 7992.985 ms [swapper/6]
0 0 38.17 7971.865 ms [swapper/4]
0 0 36.74 7447.765 ms [swapper/7]
0 0 33.59 6486.942 ms [swapper/2]
0 0 22.58 3771.268 ms [swapper/5]
9545 9351 2.48 447.136 ms sched-messaging
9574 9351 2.09 418.583 ms sched-messaging
9724 9351 2.05 372.407 ms sched-messaging
9531 9351 2.01 368.804 ms sched-messaging
9512 9351 2.00 362.250 ms sched-messaging
9514 9351 1.95 357.767 ms sched-messaging
9538 9351 1.86 384.476 ms sched-messaging
9712 9351 1.84 386.490 ms sched-messaging
9723 9351 1.83 380.021 ms sched-messaging
9722 9351 1.82 382.738 ms sched-messaging
9517 9351 1.81 354.794 ms sched-messaging
9559 9351 1.79 344.305 ms sched-messaging
9725 9351 1.77 365.315 ms sched-messaging
<SNIP>
- Add hard/soft-irq statistics to perf kwork top. This will show the
total CPU utilization with IRQ stats like below:
$ sudo perf kwork top -b -k sched,irq,softirq
Starting trace, Hit <Ctrl+C> to stop and report
^C
Total : 12554.889 ms, 8 cpus
%Cpu(s): 96.23% id, 0.10% hi, 0.19% si <---- here
%Cpu0 [| 4.60%]
%Cpu1 [| 4.59%]
%Cpu2 [ 2.73%]
%Cpu3 [| 3.81%]
<SNIP>
perf bench:
- Add -G/--cgroups option to perf bench sched pipe. The pipe bench is
good to measure context switch overhead. With this option, it puts
the reader and writer tasks in separate cgroups to enforce context
switch between two different cgroups.
Also it needs to set CPU affinity of the tasks in a CPU to
accurately measure the impact of cgroup context switches.
$ sudo perf stat -e context-switches,cgroup-switches -- \
> taskset -c 0 perf bench sched pipe -l 100000
# Running 'sched/pipe' benchmark:
# Executed 100000 pipe operations between two processes
Total time: 0.307 [sec]
3.078180 usecs/op
324867 ops/sec
Performance counter stats for 'taskset -c 0 perf bench sched pipe -l 100000':
200,026 context-switches
63 cgroup-switches
0.321637922 seconds time elapsed
You can see small number of cgroup-switches because both write and
read tasks are in the same cgroup.
$ sudo mkdir /sys/fs/cgroup/{AAA,BBB}
$ sudo perf stat -e context-switches,cgroup-switches -- \
> taskset -c 0 perf bench sched pipe -l 100000 -G AAA,BBB
# Running 'sched/pipe' benchmark:
# Executed 100000 pipe operations between two processes
Total time: 0.351 [sec]
3.512990 usecs/op
284657 ops/sec
Performance counter stats for 'taskset -c 0 perf bench sched pipe -l 100000 -G AAA,BBB':
200,020 context-switches
200,019 cgroup-switches
0.365034567 seconds time elapsed
Now context-switches and cgroup-switches are almost same. And you
can see the pipe operation took little more.
- Kill child processes when perf bench sched messaging exited
abnormally. Otherwise it'd leave the child doing unnecessary work.
perf test:
- Fix various shellcheck issues on the tests written in shell script.
- Skip tests when condition is not satisfied:
- object code reading test for non-text section addresses.
- CoreSight test if cs_etm// event is not available.
- lock contention test if not enough CPUs.
Event parsing:
- Make PMU alias name loading lazy to reduce the startup time in the
event parsing code for perf record, stat and others in the general
case.
- Lazily compute PMU default config. In the same sense, delay PMU
initialization until it's really needed to reduce the startup cost.
- Fix event term values that are raw events. The event specification
can have several terms including event name. But sometimes it
clashes with raw event encoding which starts with 'r' and has
hex-digits.
For example, an event named 'read' should be processed as a normal
event but it was mis-treated as a raw encoding and caused a
failure.
$ perf stat -e 'uncore_imc_free_running/event=read/' -a sleep 1
event syntax error: '..nning/event=read/'
\___ parser error
Run 'perf list' for a list of valid events
Usage: perf stat [<options>] [<command>]
-e, --event <event> event selector. use 'perf list' to list available events
Event metrics:
- Add "Compat" regex to match event with multiple identifiers.
- Usual updates for Intel, Power10, Arm telemetry/CMN and AmpereOne.
Misc:
- Assorted memory leak fixes and footprint reduction.
- Add "bpf_skeletons" to perf version --build-options so that users
can check whether their perf tools have BPF support easily.
- Fix unaligned access in Intel-PT packet decoder found by
undefined-behavior sanitizer.
- Avoid frequency mode for the dummy event. Surprisingly it'd impact
kernel timer tick handler performance by force iterating all PMU
events.
- Update bash shell completion for events and metrics"
* tag 'perf-tools-for-v6.7-1-2023-11-01' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools: (187 commits)
perf vendor events intel: Update tsx_cycles_per_elision metrics
perf vendor events intel: Update bonnell version number to v5
perf vendor events intel: Update westmereex events to v4
perf vendor events intel: Update meteorlake events to v1.06
perf vendor events intel: Update knightslanding events to v16
perf vendor events intel: Add typo fix for ivybridge FP
perf vendor events intel: Update a spelling in haswell/haswellx
perf vendor events intel: Update emeraldrapids to v1.01
perf vendor events intel: Update alderlake/alderlake events to v1.23
perf build: Disable BPF skeletons if clang version is < 12.0.1
perf callchain: Fix spelling mistake "statisitcs" -> "statistics"
perf report: Fix spelling mistake "heirachy" -> "hierarchy"
perf python: Fix binding linkage due to rename and move of evsel__increase_rlimit()
perf tests: test_arm_coresight: Simplify source iteration
perf vendor events intel: Add tigerlake two metrics
perf vendor events intel: Add broadwellde two metrics
perf vendor events intel: Fix broadwellde tma_info_system_dram_bw_use metric
perf mem_info: Add and use map_symbol__exit and addr_map_symbol__exit
perf callchain: Minor layout changes to callchain_list
perf callchain: Make brtype_stat in callchain_list optional
...
This adds bpf_program__attach_netkit() API to libbpf. Overall it is very
similar to tcx. The API looks as following:
LIBBPF_API struct bpf_link *
bpf_program__attach_netkit(const struct bpf_program *prog, int ifindex,
const struct bpf_netkit_opts *opts);
The struct bpf_netkit_opts is done in similar way as struct bpf_tcx_opts
for supporting bpf_mprog control parameters. The attach location for the
primary and peer device is derived from the program section "netkit/primary"
and "netkit/peer", respectively.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://lore.kernel.org/r/20231024214904.29825-4-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Fix too eager assumption that SHT_GNU_verdef ELF section is going to be
present whenever binary has SHT_GNU_versym section. It seems like either
SHT_GNU_verdef or SHT_GNU_verneed can be used, so failing on missing
SHT_GNU_verdef actually breaks use cases in production.
One specific reported issue, which was used to manually test this fix,
was trying to attach to `readline` function in BASH binary.
Fixes: bb7fa09399 ("libbpf: Support symbol versioning for uprobe")
Reported-by: Liam Wisehart <liamwisehart@meta.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Manu Bretelle <chantr4@gmail.com>
Reviewed-by: Fangrui Song <maskray@google.com>
Acked-by: Hengqi Chen <hengqi.chen@gmail.com>
Link: https://lore.kernel.org/bpf/20231016182840.4033346-1-andrii@kernel.org
Golang symbols in ELF files are different from C/C++
which contains special characters like '*', '(' and ')'.
With generics, things get more complicated, there are
symbols like:
github.com/cilium/ebpf/internal.(*Deque[go.shape.interface { Format(fmt.State, int32); TypeName() string;github.com/cilium/ebpf/btf.copy() github.com/cilium/ebpf/btf.Type}]).Grow
Matching such symbols using `%m[^\n]` in sscanf, this
excludes newline which typically does not appear in ELF
symbols. This should work in most use-cases and also
work for unicode letters in identifiers. If newline do
show up in ELF symbols, users can still attach to such
symbol by specifying bpf_uprobe_opts::func_name.
A working example can be found at this repo ([0]).
[0]: https://github.com/chenhengqi/libbpf-go-symbols
Suggested-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Hengqi Chen <hengqi.chen@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20230929155954.92448-1-hengqi.chen@gmail.com
Switch rb->rings to be an array of pointers instead of a contiguous
block. This allows for each ring pointer to be stable after
ring_buffer__add is called, which allows us to expose struct ring * to
the user without gotchas. Without this change, the realloc in
ring_buffer__add could invalidate a struct ring *, making it unsafe to
give to the user.
Signed-off-by: Martin Kelly <martin.kelly@crowdstrike.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20230925215045.2375758-3-martin.kelly@crowdstrike.com
In current implementation, we assume that symbol found in .dynsym section
would have a version suffix and use it to compare with symbol user supplied.
According to the spec ([0]), this assumption is incorrect, the version info
of dynamic symbols are stored in .gnu.version and .gnu.version_d sections
of ELF objects. For example:
$ nm -D /lib/x86_64-linux-gnu/libc.so.6 | grep rwlock_wrlock
000000000009b1a0 T __pthread_rwlock_wrlock@GLIBC_2.2.5
000000000009b1a0 T pthread_rwlock_wrlock@@GLIBC_2.34
000000000009b1a0 T pthread_rwlock_wrlock@GLIBC_2.2.5
$ readelf -W --dyn-syms /lib/x86_64-linux-gnu/libc.so.6 | grep rwlock_wrlock
706: 000000000009b1a0 878 FUNC GLOBAL DEFAULT 15 __pthread_rwlock_wrlock@GLIBC_2.2.5
2568: 000000000009b1a0 878 FUNC GLOBAL DEFAULT 15 pthread_rwlock_wrlock@@GLIBC_2.34
2571: 000000000009b1a0 878 FUNC GLOBAL DEFAULT 15 pthread_rwlock_wrlock@GLIBC_2.2.5
In this case, specify pthread_rwlock_wrlock@@GLIBC_2.34 or
pthread_rwlock_wrlock@GLIBC_2.2.5 in bpf_uprobe_opts::func_name won't work.
Because the qualified name does NOT match `pthread_rwlock_wrlock` (without
version suffix) in .dynsym sections.
This commit implements the symbol versioning for dynsym and allows user to
specify symbol in the following forms:
- func
- func@LIB_VERSION
- func@@LIB_VERSION
In case of symbol conflicts, error out and users should resolve it by
specifying a qualified name.
[0]: https://refspecs.linuxfoundation.org/LSB_5.0.0/LSB-Core-generic/LSB-Core-generic/symversion.html
Signed-off-by: Hengqi Chen <hengqi.chen@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Reviewed-by: Alan Maguire <alan.maguire@oracle.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/bpf/20230918024813.237475-3-hengqi.chen@gmail.com
Dynamic symbols in shared library may have the same name, for example:
$ nm -D /lib/x86_64-linux-gnu/libc.so.6 | grep rwlock_wrlock
000000000009b1a0 T __pthread_rwlock_wrlock@GLIBC_2.2.5
000000000009b1a0 T pthread_rwlock_wrlock@@GLIBC_2.34
000000000009b1a0 T pthread_rwlock_wrlock@GLIBC_2.2.5
$ readelf -W --dyn-syms /lib/x86_64-linux-gnu/libc.so.6 | grep rwlock_wrlock
706: 000000000009b1a0 878 FUNC GLOBAL DEFAULT 15 __pthread_rwlock_wrlock@GLIBC_2.2.5
2568: 000000000009b1a0 878 FUNC GLOBAL DEFAULT 15 pthread_rwlock_wrlock@@GLIBC_2.34
2571: 000000000009b1a0 878 FUNC GLOBAL DEFAULT 15 pthread_rwlock_wrlock@GLIBC_2.2.5
Currently, users can't attach a uprobe to pthread_rwlock_wrlock because
there are two symbols named pthread_rwlock_wrlock and both are global
bind. And libbpf considers it as a conflict.
Since both of them are at the same offset we could accept one of them
harmlessly. Note that we already does this in elf_resolve_syms_offsets.
Signed-off-by: Hengqi Chen <hengqi.chen@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Reviewed-by: Alan Maguire <alan.maguire@oracle.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/bpf/20230918024813.237475-2-hengqi.chen@gmail.com
Alexei Starovoitov says:
====================
The following pull-request contains BPF updates for your *net-next* tree.
We've added 73 non-merge commits during the last 9 day(s) which contain
a total of 79 files changed, 5275 insertions(+), 600 deletions(-).
The main changes are:
1) Basic BTF validation in libbpf, from Andrii Nakryiko.
2) bpf_assert(), bpf_throw(), exceptions in bpf progs, from Kumar Kartikeya Dwivedi.
3) next_thread cleanups, from Oleg Nesterov.
4) Add mcpu=v4 support to arm32, from Puranjay Mohan.
5) Add support for __percpu pointers in bpf progs, from Yonghong Song.
6) Fix bpf tailcall interaction with bpf trampoline, from Leon Hwang.
7) Raise irq_work in bpf_mem_alloc while irqs are disabled to improve refill probabablity, from Hou Tao.
Please consider pulling these changes from:
git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git
Thanks a lot!
Also thanks to reporters, reviewers and testers of commits in this pull-request:
Alan Maguire, Andrey Konovalov, Dave Marchevsky, "Eric W. Biederman",
Jiri Olsa, Maciej Fijalkowski, Quentin Monnet, Russell King (Oracle),
Song Liu, Stanislav Fomichev, Yonghong Song
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Add support to libbpf to append exception callbacks when loading a
program. The exception callback is found by discovering the declaration
tag 'exception_callback:<value>' and finding the callback in the value
of the tag.
The process is done in two steps. First, for each main program, the
bpf_object__sanitize_and_load_btf function finds and marks its
corresponding exception callback as defined by the declaration tag on
it. Second, bpf_object__reloc_code is modified to append the indicated
exception callback at the end of the instruction iteration (since
exception callback will never be appended in that loop, as it is not
directly referenced).
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20230912233214.1518551-16-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
