kernel/tools/perf/util, 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

perf report: Fix --ns time sort key output

2019-10-05T11:13:49Z

[ Upstream commit 3dab6ac080dcd7f71cb9ceb84ad7dafecd6f7c07 ] If the user specified --ns, the column to print the sort time stamp wasn't wide enough to actually print the full nanoseconds. Widen the time key column width when --ns is specified. Before: % perf record -a sleep 1 % perf report --sort time,overhead,symbol --stdio --ns ... 2.39% 187851.10000 [k] smp_call_function_single - - 1.53% 187851.10000 [k] intel_idle - - 0.59% 187851.10000 [.] __wcscmp_ifunc - - 0.33% 187851.10000 [.] 0000000000000000 - - 0.28% 187851.10000 [k] cpuidle_enter_state - - After: % perf report --sort time,overhead,symbol --stdio --ns ... 2.39% 187851.100000000 [k] smp_call_function_single - - 1.53% 187851.100000000 [k] intel_idle - - 0.59% 187851.100000000 [.] __wcscmp_ifunc - - 0.33% 187851.100000000 [.] 0000000000000000 - - 0.28% 187851.100000000 [k] cpuidle_enter_state - - Signed-off-by: Andi Kleen Tested-by: Arnaldo Carvalho de Melo Cc: Jiri Olsa Link: http://lkml.kernel.org/r/20190823210338.12360-2-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin

libperf: Fix alignment trap with xyarray contents in 'perf stat'

2019-10-05T11:13:45Z

[ Upstream commit d9c5c083416500e95da098c01be092b937def7fa ] Following the patch 'perf stat: Fix --no-scale', an alignment trap happens in process_counter_values() on ARMv7 platforms due to the attempt to copy non 64 bits aligned double words (pointed by 'count') via a NEON vectored instruction ('vld1' with 64 bits alignment constraint). This patch sets a 64 bits alignment constraint on 'contents[]' field in 'struct xyarray' since the 'count' pointer used above points to such a structure. Signed-off-by: Gerald Baeza Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andi Kleen Cc: Jiri Olsa Cc: Mathieu Poirier Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1566464769-16374-1-git-send-email-gerald.baeza@st.com Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin

perf record: Support aarch64 random socket_id assignment

2019-10-05T11:13:40Z

[ Upstream commit 0a4d8fb229dd78f9e0752817339e19e903b37a60 ] Same as in the commit 01766229533f ("perf record: Support s390 random socket_id assignment"), aarch64 also have this problem. Without this fix: [root@localhost perf]# ./perf report --header -I -v ... socket_id number is too big.You may need to upgrade the perf tool. # ======== # captured on : Thu Aug 1 22:58:38 2019 # header version : 1 ... # Core ID and Socket ID information is not available ... With this fix: [root@localhost perf]# ./perf report --header -I -v ... cpumask list: 0-31 cpumask list: 32-63 cpumask list: 64-95 cpumask list: 96-127 # ======== # captured on : Thu Aug 1 22:58:38 2019 # header version : 1 ... # CPU 0: Core ID 0, Socket ID 36 # CPU 1: Core ID 1, Socket ID 36 ... # CPU 126: Core ID 126, Socket ID 8442 # CPU 127: Core ID 127, Socket ID 8442 ... Signed-off-by: Tan Xiaojun Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Alexey Budankov Cc: Kan Liang Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Song Liu Cc: Steven Rostedt (VMware) Cc: Tzvetomir Stoyanov (VMware) Link: http://lkml.kernel.org/r/1564717737-21602-1-git-send-email-tanxiaojun@huawei.com Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin

perf unwind: Fix libunwind when tid != pid

2019-10-05T11:13:39Z

[ Upstream commit e8ba2906f6b9054102ad035ac9cafad9d4168589 ] Commit e5adfc3e7e77 ("perf map: Synthesize maps only for thread group leader") changed the recording side so that we no longer get mmap events for threads other than the thread group leader (when synthesising these events for threads which exist before perf is started). When a file recorded after this change is loaded, the lack of mmap records mean that unwinding is not set up for any other threads. This can be seen in a simple record/report scenario: perf record --call-graph=dwarf -t $TID perf report If $TID is a process ID then the report will show call graphs, but if $TID is a secondary thread the output is as if --call-graph=none was specified. Following the rationale in that commit, move the libunwind fields into struct map_groups and update the libunwind functions to take this instead of the struct thread. This is only required for unwind__finish_access which must now be called from map_groups__delete and the others are changed for symmetry. Note that unwind__get_entries keeps the thread argument since it is required for symbol lookup and the libdw unwind provider uses the thread ID. Signed-off-by: John Keeping Reviewed-by: Jiri Olsa Cc: Alexander Shishkin Cc: Konstantin Khlebnikov Cc: Namhyung Kim Cc: Peter Zijlstra Fixes: e5adfc3e7e77 ("perf map: Synthesize maps only for thread group leader") Link: http://lkml.kernel.org/r/20190815100146.28842-2-john@metanate.com Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin

perf cpumap: Fix writing to illegal memory in handling cpumap mask

2019-08-29T06:30:18Z

[ Upstream commit 5f5e25f1c7933a6e1673515c0b1d5acd82fea1ed ] cpu_map__snprint_mask() would write to illegal memory pointed by zalloc(0) when there is only one cpu. This patch fixes the calculation and adds sanity check against the input parameters. Signed-off-by: He Zhe Cc: Alexander Shishkin Cc: Alexey Budankov Cc: Jiri Olsa Cc: Kan Liang Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Fixes: 4400ac8a9a90 ("perf cpumap: Introduce cpu_map__snprint_mask()") Link: http://lkml.kernel.org/r/1564734592-15624-2-git-send-email-zhe.he@windriver.com Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin

perf header: Fix use of unitialized value warning

2019-08-25T14:10:28Z

[ Upstream commit 20f9781f491360e7459c589705a2e4b1f136bee9 ] When building our local version of perf with MSAN (Memory Sanitizer) and running the perf record command, MSAN throws a use of uninitialized value warning in "tools/perf/util/util.c:333:6". This warning stems from the "buf" variable being passed into "write". It originated as the variable "ev" with the type union perf_event* defined in the "perf_event__synthesize_attr" function in "tools/perf/util/header.c". In the "perf_event__synthesize_attr" function they allocate space with a malloc call using ev, then go on to only assign some of the member variables before passing "ev" on as a parameter to the "process" function therefore "ev" contains uninitialized memory. Changing the malloc call to zalloc to initialize all the members of "ev" which gets rid of the warning. To reproduce this warning, build perf by running: make -C tools/perf CLANG=1 CC=clang EXTRA_CFLAGS="-fsanitize=memory\ -fsanitize-memory-track-origins" (Additionally, llvm might have to be installed and clang might have to be specified as the compiler - export CC=/usr/bin/clang) then running: tools/perf/perf record -o - ls / | tools/perf/perf --no-pager annotate\ -i - --stdio Please see the cover letter for why false positive warnings may be generated. Signed-off-by: Numfor Mbiziwo-Tiapo Cc: Alexander Shishkin Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Drayton Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Song Liu Cc: Stephane Eranian Link: http://lkml.kernel.org/r/20190724234500.253358-2-nums@google.com Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin

perf header: Fix divide by zero error if f_header.attr_size==0

2019-08-25T14:10:28Z

[ Upstream commit 7622236ceb167aa3857395f9bdaf871442aa467e ] So I have been having lots of trouble with hand-crafted perf.data files causing segfaults and the like, so I have started fuzzing the perf tool. First issue found: If f_header.attr_size is 0 in the perf.data file, then perf will crash with a divide-by-zero error. Committer note: Added a pr_err() to tell the user why the command failed. Signed-off-by: Vince Weaver Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/alpine.DEB.2.21.1907231100440.14532@macbook-air Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin

perf session: Fix loading of compressed data split across adjacent records

2019-08-16T08:11:05Z

[ Upstream commit 872c8ee8f0f47222f7b10da96eea84d0486540a3 ] Fix decompression failure found during the loading of compressed trace collected on larger scale systems (>48 cores). The error happened due to lack of decompression space for a mmaped buffer data chunk split across adjacent PERF_RECORD_COMPRESSED records. $ perf report -i bt.16384.data --stats failed to decompress (B): 63869 -> 0 : Destination buffer is too small user stack dump failure Can't parse sample, err = -14 0x2637e436 [0x4080]: failed to process type: 9 Error: failed to process sample $ perf test 71 71: Zstd perf.data compression/decompression : Ok Signed-off-by: Alexey Budankov Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/4d839e1b-9c48-89c4-9702-a12217420611@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin

perf stat: Fix segfault for event group in repeat mode

2019-08-16T08:11:05Z

[ Upstream commit 08ef3af1579d0446db1c1bd08e2c42565addf10f ] Numfor Mbiziwo-Tiapo reported segfault on stat of event group in repeat mode: # perf stat -e '{cycles,instructions}' -r 10 ls It's caused by memory corruption due to not cleaned evsel's id array and index, which needs to be rebuilt in every stat iteration. Currently the ids index grows, while the array (which is also not freed) has the same size. Fixing this by releasing id array and zeroing ids index in perf_evsel__close function. We also need to keep the evsel_list alive for stat record (which is disabled in repeat mode). Reported-by: Numfor Mbiziwo-Tiapo Signed-off-by: Jiri Olsa Cc: Alexander Shishkin Cc: Ian Rogers Cc: Mark Drayton Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Song Liu Cc: Stephane Eranian Link: http://lkml.kernel.org/r/20190715142121.GC6032@krava Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin