kernel/tools/perf/util/evlist.c, branch linux-5.2.y

perf evlist: Use unshare(CLONE_FS) in sb threads to let setns(CLONE_NEWNS) work

2019-10-05T11:13:50Z

[ Upstream commit b397f8468fa27f08b83b348ffa56a226f72453af ] When we started using a thread to catch the PERF_RECORD_BPF_EVENT meta data events to then ask the kernel for further info (BTF, etc) for BPF programs shortly after they get loaded, we forgot to use unshare(CLONE_FS) as was done in: 868a832918f6 ("perf top: Support lookup of symbols in other mount namespaces.") Do it so that we can enter the namespaces to read the build-ids at the end of a 'perf record' session for the DSOs that had hits. Before: Starting a 'stress-ng --cpus 8' inside a container and then, outside the container running: # perf record -a --namespaces sleep 5 # perf buildid-list | grep stress-ng # We would end up with a 'perf.data' file that had no entry in its build-id table for the /usr/bin/stress-ng binary inside the container that got tons of PERF_RECORD_SAMPLEs. After: # perf buildid-list | grep stress-ng f2ed02c68341183a124b9b0f6e2e6c493c465b29 /usr/bin/stress-ng # Then its just a matter of making sure that that binary debuginfo package gets available in a place that 'perf report' will look at build-id keyed ELF files, which, in my case, on a f30 notebook, was a matter of installing the debuginfo file for the distro used in the container, fedora 31: # rpm -ivh http://fedora.c3sl.ufpr.br/linux/development/31/Everything/x86_64/debug/tree/Packages/s/stress-ng-debuginfo-0.07.29-10.fc31.x86_64.rpm Then, because perf currently looks for those debuginfo files (richer ELF symtab) inside that namespace (look at the setns calls): openat(AT_FDCWD, "/proc/self/ns/mnt", O_RDONLY) = 137 openat(AT_FDCWD, "/proc/13169/ns/mnt", O_RDONLY) = 139 setns(139, CLONE_NEWNS) = 0 stat("/usr/bin/stress-ng", {st_mode=S_IFREG|0755, st_size=3065416, ...}) = 0 openat(AT_FDCWD, "/usr/bin/stress-ng", O_RDONLY) = 140 fcntl(140, F_GETFD) = 0 fstat(140, {st_mode=S_IFREG|0755, st_size=3065416, ...}) = 0 mmap(NULL, 3065416, PROT_READ, MAP_PRIVATE, 140, 0) = 0x7ff2fdc5b000 munmap(0x7ff2fdc5b000, 3065416) = 0 close(140) = 0 stat("stress-ng-0.07.29-10.fc31.x86_64.debug", 0x7fff45d71260) = -1 ENOENT (No such file or directory) stat("/usr/bin/stress-ng-0.07.29-10.fc31.x86_64.debug", 0x7fff45d71260) = -1 ENOENT (No such file or directory) stat("/usr/bin/.debug/stress-ng-0.07.29-10.fc31.x86_64.debug", 0x7fff45d71260) = -1 ENOENT (No such file or directory) stat("/usr/lib/debug/usr/bin/stress-ng-0.07.29-10.fc31.x86_64.debug", 0x7fff45d71260) = -1 ENOENT (No such file or directory) stat("/root/.debug/.build-id/f2/ed02c68341183a124b9b0f6e2e6c493c465b29", 0x7fff45d711e0) = -1 ENOENT (No such file or directory) To only then go back to the "host" namespace to look just in the users's ~/.debug cache: setns(137, CLONE_NEWNS) = 0 chdir("/root") = 0 close(137) = 0 close(139) = 0 stat("/root/.debug/.build-id/f2/ed02c68341183a124b9b0f6e2e6c493c465b29/elf", 0x7fff45d732e0) = -1 ENOENT (No such file or directory) It continues to fail to resolve symbols: # perf report | grep stress-ng | head -5 9.50% stress-ng-cpu stress-ng [.] 0x0000000000021ac1 8.58% stress-ng-cpu stress-ng [.] 0x0000000000021ab4 8.51% stress-ng-cpu stress-ng [.] 0x0000000000021489 7.17% stress-ng-cpu stress-ng [.] 0x00000000000219b6 3.93% stress-ng-cpu stress-ng [.] 0x0000000000021478 # To overcome that we use: # perf buildid-cache -v --add /usr/lib/debug/usr/bin/stress-ng-0.07.29-10.fc31.x86_64.debug Adding f2ed02c68341183a124b9b0f6e2e6c493c465b29 /usr/lib/debug/usr/bin/stress-ng-0.07.29-10.fc31.x86_64.debug: Ok # # ls -la /root/.debug/.build-id/f2/ed02c68341183a124b9b0f6e2e6c493c465b29/elf -rw-r--r--. 3 root root 2401184 Jul 27 07:03 /root/.debug/.build-id/f2/ed02c68341183a124b9b0f6e2e6c493c465b29/elf # file /root/.debug/.build-id/f2/ed02c68341183a124b9b0f6e2e6c493c465b29/elf /root/.debug/.build-id/f2/ed02c68341183a124b9b0f6e2e6c493c465b29/elf: ELF 64-bit LSB shared object, x86-64, version 1 (SYSV), dynamically linked, interpreter \004, BuildID[sha1]=f2ed02c68341183a124b9b0f6e2e6c493c465b29, for GNU/Linux 3.2.0, with debug_info, not stripped, too many notes (256) # Now it finally works: # perf report | grep stress-ng | head -5 23.59% stress-ng-cpu stress-ng [.] ackermann 23.33% stress-ng-cpu stress-ng [.] is_prime 17.36% stress-ng-cpu stress-ng [.] stress_cpu_sieve 6.08% stress-ng-cpu stress-ng [.] stress_cpu_correlate 3.55% stress-ng-cpu stress-ng [.] queens_try # I'll make sure that it looks for the build-id keyed files in both the "host" namespace (the namespace the user running 'perf record' was a the time of the recording) and in the container namespace, as it shouldn't matter where a content based key lookup finds the ELF file to use in resolving symbols, etc. Reported-by: Karl Rister Cc: Alexander Shishkin Cc: Alexei Starovoitov Cc: Brendan Gregg Cc: Daniel Borkmann Cc: Krister Johansen Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Song Liu Cc: Stanislav Fomichev Cc: Thomas-Mich Richter Fixes: 657ee5531903 ("perf evlist: Introduce side band thread") Link: https://lkml.kernel.org/n/tip-g79k0jz41adiaeuqud742t2l@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin

treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 251

2019-06-05T15:30:26Z

Based on 1 normalized pattern(s): released under the gpl v2 and only v2 not any later version extracted by the scancode license scanner the SPDX license identifier GPL-2.0-only has been chosen to replace the boilerplate/reference in 12 file(s). Signed-off-by: Thomas Gleixner Reviewed-by: Steve Winslow Reviewed-by: Alexios Zavras Reviewed-by: Kate Stewart Reviewed-by: Allison Randal Cc: linux-spdx@vger.kernel.org Link: https://lkml.kernel.org/r/20190529141332.526460839@linutronix.de Signed-off-by: Greg Kroah-Hartman

perf mmap: Implement dedicated memory buffer for data compression

2019-05-15T19:36:49Z

Implemented mmap data buffer that is used as the memory to operate on when compressing data in case of serial trace streaming. Signed-off-by: Alexey Budankov Reviewed-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/49b31321-0f70-392b-9a4f-649d3affe090@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo

Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

2019-05-06T21:16:36Z

Pull perf updates from Ingo Molnar: "The main kernel changes were: - add support for Intel's "adaptive PEBS v4" - which embedds LBS data in PEBS records and can thus batch up and reduce the IRQ (NMI) rate significantly - reducing overhead and making call-graph profiling less intrusive. - add Intel CPU core and uncore support updates for Tremont, Icelake, - extend the x86 PMU constraints scheduler with 'constraint ranges' to better support Icelake hw constraints, - make x86 call-chain support work better with CONFIG_FRAME_POINTER=y - misc other changes Tooling changes: - updates to the main tools: 'perf record', 'perf trace', 'perf stat' - updated Intel and S/390 vendor events - libtraceevent updates - misc other updates and fixes" * 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (69 commits) perf/x86: Make perf callchains work without CONFIG_FRAME_POINTER watchdog: Fix typo in comment perf/x86/intel: Add Tremont core PMU support perf/x86/intel/uncore: Add Intel Icelake uncore support perf/x86/msr: Add Icelake support perf/x86/intel/rapl: Add Icelake support perf/x86/intel/cstate: Add Icelake support perf/x86/intel: Add Icelake support perf/x86: Support constraint ranges perf/x86/lbr: Avoid reading the LBRs when adaptive PEBS handles them perf/x86/intel: Support adaptive PEBS v4 perf/x86/intel/ds: Extract code of event update in short period perf/x86/intel: Extract memory code PEBS parser for reuse perf/x86: Support outputting XMM registers perf/x86/intel: Force resched when TFA sysctl is modified perf/core: Add perf_pmu_resched() as global function perf/headers: Fix stale comment for struct perf_addr_filter perf/core: Make perf_swevent_init_cpu() static perf/x86: Add sanity checks to x86_schedule_events() perf/x86: Optimize x86_schedule_events() ...

perf evlist: Fix side band thread draining

2019-04-17T17:30:11Z

Current perf_evlist__poll_thread() code could finish without draining the data. Adding the logic that makes sure we won't finish before the drain. Signed-off-by: Jiri Olsa Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexei Starovoitov Cc: Andi Kleen Cc: Daniel Borkmann Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Song Liu Fixes: 657ee5531903 ("perf evlist: Introduce side band thread") Link: http://lkml.kernel.org/r/20190416160127.30203-9-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo

perf record: Implement --mmap-flush= option

2019-04-01T18:18:10Z

Implement a --mmap-flush option that specifies minimal number of bytes that is extracted from mmaped kernel buffer to store into a trace. The default option value is 1 byte what means every time trace writing thread finds some new data in the mmaped buffer the data is extracted, possibly compressed and written to a trace. $ tools/perf/perf record --mmap-flush 1024 -e cycles -- matrix.gcc $ tools/perf/perf record --aio --mmap-flush 1K -e cycles -- matrix.gcc The option is independent from -z setting, doesn't vary with compression level and can serve two purposes. The first purpose is to increase the compression ratio of a trace data. Larger data chunks are compressed more effectively so the implemented option allows specifying data chunk size to compress. Also at some cases executing more write syscalls with smaller data size can take longer than executing less write syscalls with bigger data size due to syscall overhead so extracting bigger data chunks specified by the option value could additionally decrease runtime overhead. The second purpose is to avoid self monitoring live-lock issue in system wide (-a) profiling mode. Profiling in system wide mode with compression (-a -z) can additionally induce data into the kernel buffers along with the data from monitored processes. If performance data rate and volume from the monitored processes is high then trace streaming and compression activity in the tool is also high. High tool process activity can lead to subtle live-lock effect when compression of single new byte from some of mmaped kernel buffer leads to generation of the next single byte at some mmaped buffer. So perf tool process ends up in endless self monitoring. Implemented synch parameter is the mean to force data move independently from the specified flush threshold value. Despite the provided flush value the tool needs capability to unconditionally drain memory buffers, at least in the end of the collection. Committer testing: Running with the default value, i.e. as soon as there is something to read go on consuming, we first write the synthesized events, small chunks of about 128 bytes: # perf trace -m 2048 --call-graph dwarf -e write -- perf record 101.142 ( 0.004 ms): perf/25821 write(fd: 3, buf: 0x210db60, count: 120) = 120 __libc_write (/usr/lib64/libpthread-2.28.so) ion (/home/acme/bin/perf) record__write (inlined) process_synthesized_event (/home/acme/bin/perf) perf_tool__process_synth_event (inlined) perf_event__synthesize_mmap_events (/home/acme/bin/perf) Then we move to reading the mmap buffers consuming the events put there by the kernel perf infrastructure: 107.561 ( 0.005 ms): perf/25821 write(fd: 3, buf: 0x7f1befc02000, count: 336) = 336 __libc_write (/usr/lib64/libpthread-2.28.so) ion (/home/acme/bin/perf) record__write (inlined) record__pushfn (/home/acme/bin/perf) perf_mmap__push (/home/acme/bin/perf) record__mmap_read_evlist (inlined) record__mmap_read_all (inlined) __cmd_record (inlined) cmd_record (/home/acme/bin/perf) 12919.953 ( 0.136 ms): perf/25821 write(fd: 3, buf: 0x7f1befc83150, count: 184984) = 184984 12920.094 ( 0.155 ms): perf/25821 write(fd: 3, buf: 0x7f1befc02150, count: 261816) = 261816 12920.253 ( 0.093 ms): perf/25821 write(fd: 3, buf: 0x7f1befb81120, count: 170832) = 170832 If we limit it to write only when more than 16MB are available for reading, it throttles that to a quarter of the --mmap-pages set for 'perf record', which by default get to 528384 bytes, found out using 'record -v': mmap flush: 132096 mmap size 528384B With that in place all the writes coming from record__mmap_read_evlist(), i.e. from the mmap buffers setup by the kernel perf infrastructure were at least 132096 bytes long. Trying with a bigger mmap size: perf trace -e write perf record -v -m 2048 --mmap-flush 16M 74982.928 ( 2.471 ms): perf/26500 write(fd: 3, buf: 0x7ff94a6cc000, count: 3580888) = 3580888 74985.406 ( 2.353 ms): perf/26500 write(fd: 3, buf: 0x7ff949ecb000, count: 3453256) = 3453256 74987.764 ( 2.629 ms): perf/26500 write(fd: 3, buf: 0x7ff9496ca000, count: 3859232) = 3859232 74990.399 ( 2.341 ms): perf/26500 write(fd: 3, buf: 0x7ff948ec9000, count: 3769032) = 3769032 74992.744 ( 2.064 ms): perf/26500 write(fd: 3, buf: 0x7ff9486c8000, count: 3310520) = 3310520 74994.814 ( 2.619 ms): perf/26500 write(fd: 3, buf: 0x7ff947ec7000, count: 4194688) = 4194688 74997.439 ( 2.787 ms): perf/26500 write(fd: 3, buf: 0x7ff9476c6000, count: 4029760) = 4029760 Was again limited to a quarter of the mmap size: mmap flush: 2098176 mmap size 8392704B A warning about that would be good to have but can be added later, something like: "max flush is a quarter of the mmap size, if wanting to bump the mmap flush further, bump the mmap size as well using -m/--mmap-pages" Also rename the 'sync' parameters to 'synch' to keep tools/perf building with older glibcs: cc1: warnings being treated as errors builtin-record.c: In function 'record__mmap_read_evlist': builtin-record.c:775: warning: declaration of 'sync' shadows a global declaration /usr/include/unistd.h:933: warning: shadowed declaration is here builtin-record.c: In function 'record__mmap_read_all': builtin-record.c:856: warning: declaration of 'sync' shadows a global declaration /usr/include/unistd.h:933: warning: shadowed declaration is here Signed-off-by: Alexey Budankov Reviewed-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Andi Kleen Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/f6600d72-ecfa-2eb7-7e51-f6954547d500@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo

perf evsel: Fix max perf_event_attr.precise_ip detection

2019-03-28T17:31:56Z

After a discussion with Andi, move the perf_event_attr.precise_ip detection for maximum precise config (via :P modifier or for default cycles event) to perf_evsel__open(). The current detection in perf_event_attr__set_max_precise_ip() is tricky, because precise_ip config is specific for given event and it currently checks only hw cycles. We now check for valid precise_ip value right after failing sys_perf_event_open() for specific event, before any of the perf_event_attr fallback code gets executed. This way we get the proper config in perf_event_attr together with allowed precise_ip settings. We can see that code activity with -vv, like: $ perf record -vv ls ... ------------------------------------------------------------ perf_event_attr: size 112 { sample_period, sample_freq } 4000 ... precise_ip 3 sample_id_all 1 exclude_guest 1 mmap2 1 comm_exec 1 ksymbol 1 ------------------------------------------------------------ sys_perf_event_open: pid 9926 cpu 0 group_fd -1 flags 0x8 sys_perf_event_open failed, error -95 decreasing precise_ip by one (2) ------------------------------------------------------------ perf_event_attr: size 112 { sample_period, sample_freq } 4000 ... precise_ip 2 sample_id_all 1 exclude_guest 1 mmap2 1 comm_exec 1 ksymbol 1 ------------------------------------------------------------ sys_perf_event_open: pid 9926 cpu 0 group_fd -1 flags 0x8 = 4 ... Suggested-by: Andi Kleen Signed-off-by: Jiri Olsa Link: http://lkml.kernel.org/n/tip-dkvxxbeg7lu74155d4jhlmc9@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo

perf evlist: Introduce side band thread

2019-03-21T14:27:03Z

This patch introduces side band thread that captures extended information for events like PERF_RECORD_BPF_EVENT. This new thread uses its own evlist that uses ring buffer with very low watermark for lower latency. To use side band thread, we need to: 1. add side band event(s) by calling perf_evlist__add_sb_event(); 2. calls perf_evlist__start_sb_thread(); 3. at the end of perf run, perf_evlist__stop_sb_thread(). In the next patch, we use this thread to handle PERF_RECORD_BPF_EVENT. Committer notes: Add fix by Jiri Olsa for when te sb_tread can't get started and then at the end the stop_sb_thread() segfaults when joining the (non-existing) thread. That can happen when running 'perf top' or 'perf record' as a normal user, for instance. Further checks need to be done on top of this to more graciously handle these possible failure scenarios. Signed-off-by: Song Liu Reviewed-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stanislav Fomichev Link: http://lkml.kernel.org/r/20190312053051.2690567-15-songliubraving@fb.com Signed-off-by: Arnaldo Carvalho de Melo

perf evsel: Probe for precise_ip with simple attr

2019-03-06T21:19:45Z

Currently we probe for precise_ip with user specified perf_event_attr, which might fail because of unsupported kernel features, which would get disabled during the open time anyway. Switching the probe to take place on simple hw cycles, so the following record sets proper precise_ip: # perf record -e cycles:P ls # perf evlist -v cycles:P: size: 112, ... precise_ip: 3, ... Signed-off-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Jonas Rabenstein Cc: Nageswara R Sastry Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Ravi Bangoria Link: http://lkml.kernel.org/r/20190305152536.21035-7-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo

perf record: Allocate affinity masks

2019-02-06T13:00:39Z

Allocate affinity option and masks for mmap data buffers and record thread as well as initialize allocated objects. Signed-off-by: Alexey Budankov Reviewed-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/526fa2b0-07de-6dbd-a7e9-26ba875593c9@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo