kernel/linux.git/tools, branch v5.2.19

libtraceevent: Change users plugin directory

2019-10-05T11:13:52+00:00

[ Upstream commit e97fd1383cd77c467d2aed7fa4e596789df83977 ] To be compliant with XDG user directory layout, the user's plugin directory is changed from ~/.traceevent/plugins to ~/.local/lib/traceevent/plugins/ Suggested-by: Patrick McLean Signed-off-by: Tzvetomir Stoyanov Cc: Andrew Morton Cc: Jiri Olsa Cc: Namhyung Kim Cc: Patrick McLean Cc: linux-trace-devel@vger.kernel.org Link: https://lore.kernel.org/linux-trace-devel/20190313144206.41e75cf8@patrickm/ Link: http://lore.kernel.org/linux-trace-devel/20190801074959.22023-4-tz.stoyanov@gmail.com Link: http://lore.kernel.org/lkml/20190805204355.344622683@goodmis.org Signed-off-by: Steven Rostedt (VMware) Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin

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

2019-10-05T11:13:50+00:00

[ 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 script: Fix memory leaks in list_scripts()

2019-10-05T11:13:49+00:00

[ Upstream commit 3b4acbb92dbda4829e021e5c6d5410658849fa1c ] In case memory resources for *buf* and *paths* were allocated, jump to *out* and release them before return. Signed-off-by: Gustavo A. R. Silva Cc: Alexander Shishkin Cc: Andi Kleen Cc: Gustavo A. R. Silva Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Addresses-Coverity-ID: 1444328 ("Resource leak") Fixes: 6f3da20e151f ("perf report: Support builtin perf script in scripts menu") Link: http://lkml.kernel.org/r/20190408162748.GA21008@embeddedor Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin

perf report: Fix --ns time sort key output

2019-10-05T11:13:49+00:00

[ 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

perf trace beauty ioctl: Fix off-by-one error in cmd->string table

2019-10-05T11:13:49+00:00

[ Upstream commit b92675f4a9c02dd78052645597dac9e270679ddf ] While tracing a program that calls isatty(3), I noticed that strace reported TCGETS for the request argument of the underlying ioctl(2) syscall while perf trace reported TCSETS. strace is corrrect. The bug in perf was due to the tty ioctl beauty table starting at 0x5400 rather than 0x5401. Committer testing: Using augmented_raw_syscalls.o and settings to make 'perf trace' use strace formatting, i.e. with this in ~/.perfconfig # cat ~/.perfconfig [trace] add_events = /home/acme/git/linux/tools/perf/examples/bpf/augmented_raw_syscalls.c show_zeros = yes show_duration = no no_inherit = yes show_timestamp = no show_arg_names = no args_alignment = 40 show_prefix = yes # strace -e ioctl stty > /dev/null ioctl(0, TCGETS, {B38400 opost isig icanon echo ...}) = 0 ioctl(1, TIOCGWINSZ, 0x7fff8a9b0860) = -1 ENOTTY (Inappropriate ioctl for device) ioctl(1, TCGETS, 0x7fff8a9b0540) = -1 ENOTTY (Inappropriate ioctl for device) +++ exited with 0 +++ # Before: # perf trace -e ioctl stty > /dev/null ioctl(0, TCSETS, 0x7fff2cf79f20) = 0 ioctl(1, TIOCSWINSZ, 0x7fff2cf79f40) = -1 ENOTTY (Inappropriate ioctl for device) ioctl(1, TCSETS, 0x7fff2cf79c20) = -1 ENOTTY (Inappropriate ioctl for device) # After: # perf trace -e ioctl stty > /dev/null ioctl(0, TCGETS, 0x7ffed0763920) = 0 ioctl(1, TIOCGWINSZ, 0x7ffed0763940) = -1 ENOTTY (Inappropriate ioctl for device) ioctl(1, TCGETS, 0x7ffed0763620) = -1 ENOTTY (Inappropriate ioctl for device) # Signed-off-by: Benjamin Peterson Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Fixes: 1cc47f2d46206d67285aea0ca7e8450af571da13 ("perf trace beauty ioctl: Improve 'cmd' beautifier") Link: http://lkml.kernel.org/r/20190823033625.18814-1-benjamin@python.org Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin

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

2019-10-05T11:13:45+00:00

[ 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

tools headers: Fixup bitsperlong per arch includes

2019-10-05T11:13:42+00:00

[ Upstream commit 42fc2e9ef9603a7948aaa4ffd8dfb94b30294ad8 ] We were getting the file by luck, from one of the paths in -I, fix it to get it from the proper place: $ cd tools/include/uapi/asm/ [acme@quaco asm]$ grep include bitsperlong.h #include "../../arch/x86/include/uapi/asm/bitsperlong.h" #include "../../arch/arm64/include/uapi/asm/bitsperlong.h" #include "../../arch/powerpc/include/uapi/asm/bitsperlong.h" #include "../../arch/s390/include/uapi/asm/bitsperlong.h" #include "../../arch/sparc/include/uapi/asm/bitsperlong.h" #include "../../arch/mips/include/uapi/asm/bitsperlong.h" #include "../../arch/ia64/include/uapi/asm/bitsperlong.h" #include "../../arch/riscv/include/uapi/asm/bitsperlong.h" #include "../../arch/alpha/include/uapi/asm/bitsperlong.h" #include $ ls -la ../../arch/x86/include/uapi/asm/bitsperlong.h ls: cannot access '../../arch/x86/include/uapi/asm/bitsperlong.h': No such file or directory $ ls -la ../../../arch/*/include/uapi/asm/bitsperlong.h -rw-rw-r--. 1 237 ../../../arch/alpha/include/uapi/asm/bitsperlong.h -rw-rw-r--. 1 841 ../../../arch/arm64/include/uapi/asm/bitsperlong.h -rw-rw-r--. 1 966 ../../../arch/hexagon/include/uapi/asm/bitsperlong.h -rw-rw-r--. 1 234 ../../../arch/ia64/include/uapi/asm/bitsperlong.h -rw-rw-r--. 1 100 ../../../arch/microblaze/include/uapi/asm/bitsperlong.h -rw-rw-r--. 1 244 ../../../arch/mips/include/uapi/asm/bitsperlong.h -rw-rw-r--. 1 352 ../../../arch/parisc/include/uapi/asm/bitsperlong.h -rw-rw-r--. 1 312 ../../../arch/powerpc/include/uapi/asm/bitsperlong.h -rw-rw-r--. 1 353 ../../../arch/riscv/include/uapi/asm/bitsperlong.h -rw-rw-r--. 1 292 ../../../arch/s390/include/uapi/asm/bitsperlong.h -rw-rw-r--. 1 323 ../../../arch/sparc/include/uapi/asm/bitsperlong.h -rw-rw-r--. 1 320 ../../../arch/x86/include/uapi/asm/bitsperlong.h $ Found while fixing some other problem, before it was escaping the tools/ chroot and using stuff in the kernel sources: CC /tmp/build/perf/util/find_bit.o In file included from /git/linux/tools/include/../../arch/x86/include/uapi/asm/bitsperlong.h:11, from /git/linux/tools/include/uapi/asm/bitsperlong.h:3, from /git/linux/tools/include/linux/bits.h:6, from /git/linux/tools/include/linux/bitops.h:13, from ../lib/find_bit.c:17: # cd /git/linux/tools/include/../../arch/x86/include/uapi/asm/ # pwd /git/linux/arch/x86/include/uapi/asm # Now it is getting the one we want it to, i.e. the one inside tools/: CC /tmp/build/perf/util/find_bit.o In file included from /git/linux/tools/arch/x86/include/uapi/asm/bitsperlong.h:11, from /git/linux/tools/include/linux/bits.h:6, from /git/linux/tools/include/linux/bitops.h:13, Cc: Adrian Hunter Cc: Jiri Olsa Cc: Namhyung Kim Link: https://lkml.kernel.org/n/tip-8f8cfqywmf6jk8a3ucr0ixhu@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin

perf record: Support aarch64 random socket_id assignment

2019-10-05T11:13:40+00:00

[ 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

2019-10-05T11:13:39+00:00

[ 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 test vfs_getname: Disable ~/.perfconfig to get default output

2019-10-05T11:13:38+00:00

[ Upstream commit 4fe94ce1c6ba678b5f12b94bb9996eea4fc99e85 ] To get the expected output we have to ignore whatever changes the user has in its ~/.perfconfig file, so set PERF_CONFIG to /dev/null to achieve that. Before: # egrep 'trace|show_' ~/.perfconfig [trace] show_zeros = yes show_duration = no show_timestamp = no show_arg_names = no show_prefix = yes # echo $PERF_CONFIG # perf test "trace + vfs_getname" 70: Check open filename arg using perf trace + vfs_getname: FAILED! # export PERF_CONFIG=/dev/null # perf test "trace + vfs_getname" 70: Check open filename arg using perf trace + vfs_getname: Ok # After: # egrep 'trace|show_' ~/.perfconfig [trace] show_zeros = yes show_duration = no show_timestamp = no show_arg_names = no show_prefix = yes # echo $PERF_CONFIG # perf test "trace + vfs_getname" 70: Check open filename arg using perf trace + vfs_getname: Ok # Cc: Adrian Hunter Cc: Jiri Olsa Cc: Luis Cláudio Gonçalves Cc: Namhyung Kim Cc: Taeung Song Link: https://lkml.kernel.org/n/tip-3up27pexg5i3exuzqrvt4m8u@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin