aboutsummaryrefslogtreecommitdiff
path: root/tools/perf
AgeCommit message (Collapse)AuthorFilesLines
2021-09-11perf tools: Factor out copy_config_terms() and free_config_terms()Adrian Hunter3-13/+19
Factor out copy_config_terms() and free_config_terms() so that they can be reused. Signed-off-by: Adrian Hunter <[email protected]> Acked-by: Jiri Olsa <[email protected]> Cc: Jin Yao <[email protected]> Cc: Kan Liang <[email protected]> Link: https //lore.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-09-11perf tools: Fix perf_event_attr__fprintf() missing/dupl. fieldsAdrian Hunter1-1/+4
Some fields are missing and text_poke is duplicated. Fix that up. Signed-off-by: Adrian Hunter <[email protected]> Cc: Jiri Olsa <[email protected]> Link: http://lore.kernel.org/lkml/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-09-11perf tools: Ignore Documentation dependency fileIan Rogers1-0/+1
When building directly on the checked out repository the build process produces a file that should be ignored, so add it to .gitignore. Fixes: a81df63a5df3e195 ("perf doc: Fix doc.dep") Reported-by: Linus Torvalds <[email protected]> Signed-off-by: Ian Rogers <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: http://lore.kernel.org/lkml/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-09-10perf bpf: Provide a weak btf__load_from_kernel_by_id() for older libbpf versionsArnaldo Carvalho de Melo1-0/+8
The btf__get_from_id() function was deprecated in favour of btf__load_from_kernel_by_id(), but it is still avaiable, so use it to provide a weak function btf__load_from_kernel_by_id() for older libbpf when building perf with LIBBPF_DYNAMIC=1, i.e. using the system's libbpf package. Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-09-10perf beauty: Cover more flags in the move_mount syscall argument beautifierArnaldo Carvalho de Melo1-1/+1
Previously the regext expected MOVE_MOUNT_[FT]_*, but in the next patch a flag that doesn't match that expression will be added, MOVE_MOUNT_SET_GROUP To make this more future proof, take advantage of the fact that the only one we don't need to cover is MOVE_MOUNT__MASK and use MOVE_MOUNT_[^_]+_*_. Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-09-10perf report: Add support to print a textual representation of IBS raw sample ↵Kim Phillips4-1/+303
data Perf records IBS (Instruction Based Sampling) extra sample data when 'perf record --raw-samples' is used with an IBS-compatible event, on a machine that supports IBS. IBS support is indicated in CPUID_Fn80000001_ECX bit #10. Up until now, users have been able to see the extra sample data solely in raw hex format using 'perf report --dump-raw-trace'. From there, users could decode the data either manually, or by using an external script. Enable the built-in 'perf report --dump-raw-trace' to do the decoding of the extra sample data bits, so manual or external script decoding isn't necessary. Example usage: $ sudo perf record -c 10000001 -a --raw-samples -e ibs_fetch/rand_en=1/,ibs_op/cnt_ctl=1/ -C 0,1 taskset -c 0,1 7za b -mmt2 | perf report --dump-raw-trace Stdout contains IBS Fetch samples, e.g.: ibs_fetch_ctl: 02170007ffffffff MaxCnt 1048560 Cnt 1048560 Lat 7 En 1 Val 1 Comp 1 IcMiss 0 PhyAddrValid 1 L1TlbPgSz 4KB L1TlbMiss 0 L2TlbMiss 0 RandEn 1 L2Miss 0 IbsFetchLinAd: 000056016b2ead40 IbsFetchPhysAd: 000000115cedfd40 c_ibs_ext_ctl: 0000000000000000 IbsItlbRefillLat 0 ..and IBS Op samples, e.g.: ibs_op_ctl: 0000009e009e8968 MaxCnt 10000000 En 1 Val 1 CntCtl 1=uOps CurCnt 158 IbsOpRip: 000056016b2ea73d ibs_op_data: 00000000000b0002 CompToRetCtr 2 TagToRetCtr 11 BrnRet 0 RipInvalid 0 BrnFuse 0 Microcode 0 ibs_op_data2: 0000000000000002 CacheHitSt 0=M-state RmtNode 0 DataSrc 2=Local node cache ibs_op_data3: 0000000000c60002 LdOp 0 StOp 1 DcL1TlbMiss 0 DcL2TlbMiss 0 DcL1TlbHit2M 0 DcL1TlbHit1G 0 DcL2TlbHit2M 0 DcMiss 0 DcMisAcc 0 DcWcMemAcc 0 DcUcMemAcc 0 DcLockedOp 0 DcMissNoMabAlloc 0 DcLinAddrValid 1 DcPhyAddrValid 1 DcL2TlbHit1G 0 L2Miss 0 SwPf 0 OpMemWidth 4 bytes OpDcMissOpenMemReqs 0 DcMissLat 0 TlbRefillLat 0 IbsDCLinAd: 00007f133c319ce0 IbsDCPhysAd: 0000000270485ce0 Committer notes: Fixed up this: util/amd-sample-raw.c: In function ‘evlist__amd_sample_raw’: util/amd-sample-raw.c:125:42: error: ‘ bytes’ directive output may be truncated writing 6 bytes into a region of size between 4 and 7 [-Werror=format-truncation=] 125 | " OpMemWidth %2d bytes", 1 << (reg.op_mem_width - 1)); | ^~~~~~ In file included from /usr/include/stdio.h:866, from util/amd-sample-raw.c:7: /usr/include/bits/stdio2.h:71:10: note: ‘__builtin___snprintf_chk’ output between 21 and 24 bytes into a destination of size 21 71 | return __builtin___snprintf_chk (__s, __n, __USE_FORTIFY_LEVEL - 1, | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 72 | __glibc_objsize (__s), __fmt, | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 73 | __va_arg_pack ()); | ~~~~~~~~~~~~~~~~~ cc1: all warnings being treated as errors As that %2d won't limit the number of chars to 2, just state that 2 is the minimal width: $ cat printf.c #include <stdio.h> #include <stdlib.h> int main(int argc, char *argv[]) { char bf[64]; int len = snprintf(bf, sizeof(bf), "%2d", atoi(argv[1])); printf("strlen(%s): %u\n", bf, len); return 0; } $ ./printf 1 strlen( 1): 2 $ ./printf 12 strlen(12): 2 $ ./printf 123 strlen(123): 3 $ ./printf 1234 strlen(1234): 4 $ ./printf 12345 strlen(12345): 5 $ ./printf 123456 strlen(123456): 6 $ And since we probably don't want that output to be truncated, just assume the worst case, as the compiler did, and add a few more chars to that buffer. Also use sizeof(var) instead of sizeof(dup-of-wanted-format-string) to avoid bugs when changing one but not the other. I also had to change this: -#include <asm/amd-ibs.h> +#include "../../arch/x86/include/asm/amd-ibs.h" To make it build on other architectures, just like intel-pt does. Signed-off-by: Kim Phillips <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Boris Ostrovsky <[email protected]> Cc: Ian Rogers <[email protected]> Cc: Ingo Molnar <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Joao Martins <[email protected]> Cc: Konrad Rzeszutek Wilk <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Michael Petlan <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: Robert Richter <[email protected]> Cc: Stephane Eranian <[email protected]> Link: https //lore.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-09-10perf report: Add tools/arch/x86/include/asm/amd-ibs.hKim Phillips1-0/+1
This is a tools/-side patch for the patch that adds the original copy of the IBS header file, in arch/x86/include/asm/. We also add an entry to check-headers.sh, so future changes continue to be copied. Committer notes: Had to add this -#include <asm/msr-index.h> +#include "msr-index.h" And change the check-headers.sh entry to ignore this line when diffing with the original kernel header. This is needed so that we can use 'perf report' on a perf.data with IBS data on a !x86 system, i.e. building on ARM fails without this as there is no asm/msr-index.h there. This was done on the next patch in this series and is done for things like Intel PT and ARM CoreSight. Signed-off-by: Kim Phillips <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Boris Ostrovsky <[email protected]> Cc: Ian Rogers <[email protected]> Cc: Ingo Molnar <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Joao Martins <[email protected]> Cc: Konrad Rzeszutek Wilk <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Michael Petlan <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: Robert Richter <[email protected]> Cc: Stephane Eranian <[email protected]> Link: https //lore.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-09-10perf env: Add perf_env__cpuid, perf_env__{nr_}pmu_mappingsKim Phillips2-0/+83
To be used by IBS raw data display: It needs the recorder's cpuid in order to determine which errata workarounds to apply to the data, and the pmu_mappings are needed in order to figure out which PMU sample type is IBS Fetch vs. IBS Op. When not available from perf.data, we assume local operation, and retrieve cpuid and pmu mappings directly from the running system. Signed-off-by: Kim Phillips <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Boris Ostrovsky <[email protected]> Cc: Ian Rogers <[email protected]> Cc: Ingo Molnar <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Joao Martins <[email protected]> Cc: Konrad Rzeszutek Wilk <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Michael Petlan <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: Robert Richter <[email protected]> Cc: Stephane Eranian <[email protected]> Link: https //lore.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-09-10perf symbol: Look for ImageBase in PE file to compute .text offsetRemi Bernon1-4/+16
Instead of using the file offset in the debug file. This fixes a regression from 00a3423492bc90be ("perf symbols: Make dso__load_bfd_symbols() load PE files from debug cache only"), causing incorrect symbol resolution when debug file have been stripped from non-debug sections (in which case its .text section is empty and doesn't have any file position). The debug files could also be created with a different file alignment, and have different file positions from the mmap-ed binary, or have the section reordered. This instead looks for the file image base, using the corresponding bfd *ABS* symbols. As PE symbols only have 4 bytes, it also needs to keep .text section vma high bits. Signed-off-by: Remi Bernon <[email protected]> Fixes: 00a3423492bc90be ("perf symbols: Make dso__load_bfd_symbols() load PE files from debug cache only") Cc: Alexander Shishkin <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Nicholas Fraser <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: http://lore.kernel.org/lkml/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-09-10perf scripts python: Fix passing arguments to stackcollapse reportMichael Petlan1-1/+1
The '--' prevented arguments from being passed to the script, such as: $ perf script report stackcollapse -i my_perf.data Signed-off-by: Michael Petlan <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Paolo Bonzini <[email protected]> LPU-Reference: [email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-09-10perf test: Fix bpf test sample mismatch reportingMichael Petlan1-1/+1
When the expected sample count in the condition changed, the message needs to be changed too, otherwise we'll get: 0x1001f2091d8: mmap mask[0]: BPF filter result incorrect, expected 56, got 56 samples Fixes: 4b04e0decd2518e5 ("perf test: Fix basic bpf filtering test") Signed-off-by: Michael Petlan <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Sumanth Korikkar <[email protected]> Link: https //lore.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-09-10tools headers UAPI: Sync files changed by new process_mrelease syscall and ↵Arnaldo Carvalho de Melo4-12/+19
the removal of some compat entry points To pick the changes in these csets: 59ab844eed9c6b01 ("compat: remove some compat entry points") dce49103962840dd ("mm: wire up syscall process_mrelease") b48c7236b13cb5ef ("exit/bdflush: Remove the deprecated bdflush system call") That add support for this new syscall in tools such as 'perf trace'. For instance, this is now possible: # perf trace -v -e process_mrelease event qualifier tracepoint filter: (common_pid != 19351 && common_pid != 9112) && (id == 448) ^C# That is the filter expression attached to the raw_syscalls:sys_{enter,exit} tracepoints. $ grep process_mrelease tools/perf/arch/x86/entry/syscalls/syscall_64.tbl 448 common process_mrelease sys_process_mrelease $ This addresses these perf build warnings: Warning: Kernel ABI header at 'tools/include/uapi/asm-generic/unistd.h' differs from latest version at 'include/uapi/asm-generic/unistd.h' diff -u tools/include/uapi/asm-generic/unistd.h include/uapi/asm-generic/unistd.h Warning: Kernel ABI header at 'tools/perf/arch/x86/entry/syscalls/syscall_64.tbl' differs from latest version at 'arch/x86/entry/syscalls/syscall_64.tbl' diff -u tools/perf/arch/x86/entry/syscalls/syscall_64.tbl arch/x86/entry/syscalls/syscall_64.tbl Warning: Kernel ABI header at 'tools/perf/arch/powerpc/entry/syscalls/syscall.tbl' differs from latest version at 'arch/powerpc/kernel/syscalls/syscall.tbl' diff -u tools/perf/arch/powerpc/entry/syscalls/syscall.tbl arch/powerpc/kernel/syscalls/syscall.tbl Warning: Kernel ABI header at 'tools/perf/arch/s390/entry/syscalls/syscall.tbl' differs from latest version at 'arch/s390/kernel/syscalls/syscall.tbl' diff -u tools/perf/arch/s390/entry/syscalls/syscall.tbl arch/s390/kernel/syscalls/syscall.tbl Warning: Kernel ABI header at 'tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl' differs from latest version at 'arch/mips/kernel/syscalls/syscall_n64.tbl' diff -u tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl arch/mips/kernel/syscalls/syscall_n64.tbl Cc: Arnd Bergmann <[email protected]> Cc: Eric W. Biederman <[email protected]> Cc: Linus Torvalds <[email protected]> Cc: Suren Baghdasaryan <[email protected]> Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-09-10perf beauty: Update copy of linux/socket.h with the kernel sourcesArnaldo Carvalho de Melo1-1/+8
To pick the changes in: Fixes: d32f89da7fa8ccc8 ("net: add accept helper not installing fd") Fixes: bc49d8169aa72295 ("mctp: Add MCTP base") This automagically adds support for the AF_MCTP protocol domain: $ tools/perf/trace/beauty/socket.sh > before $ cp include/linux/socket.h tools/perf/trace/beauty/include/linux/socket.h $ tools/perf/trace/beauty/socket.sh > after $ diff -u before after --- before 2021-09-06 11:57:14.972747200 -0300 +++ after 2021-09-06 11:57:30.541920222 -0300 @@ -44,4 +44,5 @@ [42] = "QIPCRTR", [43] = "SMC", [44] = "XDP", + [45] = "MCTP", }; $ This will allow 'perf trace' to translate 45 into "MCTP" as is done with the other domains: # perf trace -e socket* 0.000 chronyd/1029 socket(family: INET, type: DGRAM|CLOEXEC|NONBLOCK, protocol: IP) = 4 ^C# This addresses this perf build warning: Warning: Kernel ABI header at 'tools/perf/trace/beauty/include/linux/socket.h' differs from latest version at 'include/linux/socket.h' diff -u tools/perf/trace/beauty/include/linux/socket.h include/linux/socket.h Cc: David S. Miller <[email protected]> Cc: Jens Axboe <[email protected]> Cc: Jeremy Kerr <[email protected]> Cc: Pavel Begunkov <[email protected]> Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-09-08Merge branch 'akpm' (patches from Andrew)Linus Torvalds9-14/+14
Merge more updates from Andrew Morton: "147 patches, based on 7d2a07b769330c34b4deabeed939325c77a7ec2f. Subsystems affected by this patch series: mm (memory-hotplug, rmap, ioremap, highmem, cleanups, secretmem, kfence, damon, and vmscan), alpha, percpu, procfs, misc, core-kernel, MAINTAINERS, lib, checkpatch, epoll, init, nilfs2, coredump, fork, pids, criu, kconfig, selftests, ipc, and scripts" * emailed patches from Andrew Morton <[email protected]>: (94 commits) scripts: check_extable: fix typo in user error message mm/workingset: correct kernel-doc notations ipc: replace costly bailout check in sysvipc_find_ipc() selftests/memfd: remove unused variable Kconfig.debug: drop selecting non-existing HARDLOCKUP_DETECTOR_ARCH configs: remove the obsolete CONFIG_INPUT_POLLDEV prctl: allow to setup brk for et_dyn executables pid: cleanup the stale comment mentioning pidmap_init(). kernel/fork.c: unexport get_{mm,task}_exe_file coredump: fix memleak in dump_vma_snapshot() fs/coredump.c: log if a core dump is aborted due to changed file permissions nilfs2: use refcount_dec_and_lock() to fix potential UAF nilfs2: fix memory leak in nilfs_sysfs_delete_snapshot_group nilfs2: fix memory leak in nilfs_sysfs_create_snapshot_group nilfs2: fix memory leak in nilfs_sysfs_delete_##name##_group nilfs2: fix memory leak in nilfs_sysfs_create_##name##_group nilfs2: fix NULL pointer in nilfs_##name##_attr_release nilfs2: fix memory leak in nilfs_sysfs_create_device_group trap: cleanup trap_init() init: move usermodehelper_enable() to populate_rootfs() ...
2021-09-08tools: rename bitmap_alloc() to bitmap_zalloc()Andy Shevchenko9-14/+14
Rename bitmap_alloc() to bitmap_zalloc() in tools to follow the bitmap API in the kernel. No functional changes intended. Link: https://lkml.kernel.org/r/[email protected] Signed-off-by: Andy Shevchenko <[email protected]> Signed-off-by: Yury Norov <[email protected]> Suggested-by: Yury Norov <[email protected]> Acked-by: Yury Norov <[email protected]> Tested-by: Wolfram Sang <[email protected]> Acked-by: Jiri Olsa <[email protected]> Cc: Alexander Lobakin <[email protected]> Cc: Alexey Klimov <[email protected]> Cc: Dennis Zhou <[email protected]> Cc: Ulf Hansson <[email protected]> Cc: Will Deacon <[email protected]> Signed-off-by: Andrew Morton <[email protected]> Signed-off-by: Linus Torvalds <[email protected]>
2021-09-05Merge tag 'perf-tools-for-v5.15-2021-09-04' of ↵Linus Torvalds151-12426/+19967
git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux Pull perf tool updates from Arnaldo Carvalho de Melo: "New features: - Improvements for the flamegraph python script, including: - Display perf.data header - Display PIDs of user stacks - Added option to change color scheme - Default to blue/green color scheme to improve accessibility - Correctly identify kernel stacks when debuginfo is available - Improvements for 'perf bench futex': - Add --mlockall parameter - Add --broadcast and --pi to the 'requeue' sub benchmark - Add support for PMU aliases. - Introduce an ARM Coresight ETE decoder. - Add a 'perf bench' entry for evlist open/close operations, to help quantify improvements with multithreading 'perf record'. - Allow reporting the [un]throttle PERF_RECORD_ meta event in 'perf script's python scripting. - Add a 'perf test' entry for PMU aliases. - Add a 'perf test' entry for 'perf record/perf report/perf script' pipe mode. Fixes: - perf script dlfilter (API for filtering via dynamically loaded shared object introduced in v5.14) fixes and a 'perf test' entry for it. - Fix get_current_dir_name() compilation on Android. - Fix issues with asciidoc and double dashes uses. - Fix memory leaks in the BTF handling code. - Fix leftover problems in the Documentation from the infrastructure originally lifted from the git codebase. - Fix *probe_vfs_getname.sh 'perf test' failures. - Handle fd gaps in 'perf test's test__dso_data_reopen(). - Make sure to show disasembly warnings for 'perf annotate --stdio'. - Fix output from pipe to file and vice-versa in 'perf record/report/script'. - Correct 'perf data -h' output. - Fix wrong comm in system-wide mode with 'perf record --delay'. - Do not allow --for-each-cgroup without cpu in 'perf stat' - Make 'perf test --skip' work on shell tests. - Fix libperf's verbose printing. Misc improvements: - Preparatory patches for multithreading various 'perf record' phases (synthesizing, opening, recording, etc). - Add sparse context/locking annotations in compiler-types.h, also to help with the multithreading effort. - Optimize the generation of the arch specific erno tables used in 'perf trace'. - Optimize libperf's perf_cpu_map__max(). - Improve ARM's CoreSight warnings. - Report collisions in AUX records. - Improve warnings for the LLVM 'perf test' entry. - Improve the PMU events 'perf test' codebase. - perf test: Do not compare overheads in the zstd comp test - Better support annotation on ARM. - Update 'perf trace's cmd string table to decode sys_bpf() first arg. Vendor events: - Add JSON events and metrics for Intel's Ice Lake, Tiger Lake and Elhart Lake. - Update JSON eventsand metrics for Intel's Cascade Lake and Sky Lake servers. Hardware tracing: - Improvements for the ARM hardware tracing auxtrace support" * tag 'perf-tools-for-v5.15-2021-09-04' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (130 commits) perf tests: Add test for PMU aliases perf pmu: Add PMU alias support perf session: Report collisions in AUX records perf script python: Allow reporting the [un]throttle PERF_RECORD_ meta event perf build: Report failure for testing feature libopencsd perf cs-etm: Show a warning for an unknown magic number perf cs-etm: Print the decoder name perf cs-etm: Create ETE decoder perf cs-etm: Update OpenCSD decoder for ETE perf cs-etm: Fix typo perf cs-etm: Save TRCDEVARCH register perf cs-etm: Refactor out ETMv4 header saving perf cs-etm: Initialise architecture based on TRCIDR1 perf cs-etm: Refactor initialisation of decoder params. tools build: Fix feature detect clean for out of source builds perf evlist: Add evlist__for_each_entry_from() macro perf evsel: Handle precise_ip fallback in evsel__open_cpu() perf evsel: Move bpf_counter__install_pe() to success path in evsel__open_cpu() perf evsel: Move test_attr__open() to success path in evsel__open_cpu() perf evsel: Move ignore_missing_thread() to fallback code ...
2021-09-03perf tests: Add test for PMU aliasesJin Yao1-0/+92
A perf uncore PMU may have two PMU names, a real name and an alias. Add one test case to verify that the real and alias names have the same effect. Iterate sysfs to get one event which has an alias and create an evlist by adding two evsels. Evsel1 is created by event and evsel2 is created by alias. Test asserts: evsel1->core.attr.type == evsel2->core.attr.type evsel1->core.attr.config == evsel2->core.attr.config Signed-off-by: Jin Yao <[email protected]> Reviewed-by: Andi Kleen <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Jin Yao <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: John Garry <[email protected]> Cc: Kan Liang <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: Riccardo Mancini <[email protected]> Link: http://lore.kernel.org/lkml/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-09-03perf pmu: Add PMU alias supportKan Liang4-5/+198
A perf uncore PMU may have two PMU names, a real name and an alias. The alias is exported at /sys/bus/event_source/devices/uncore_*/alias. The perf tool should support the alias as well. Add alias_name in the struct perf_pmu to store the alias. For the PMU which doesn't have an alias. It's NULL. Introduce two X86 specific functions to retrieve the real name and the alias separately. Only go through the sysfs to retrieve the mapping between the real name and the alias once. The result is cached in a list, uncore_pmu_list. Nothing changed for the other ARCHs. With the patch, the perf tool can monitor the PMU with either the real name or the alias. Use the real name, $ perf stat -e uncore_cha_2/event=1/ -x, 4044879584,,uncore_cha_2/event=1/,2528059205,100.00,, Use the alias, $ perf stat -e uncore_type_0_2/event=1/ -x, 3659675336,,uncore_type_0_2/event=1/,2287306455,100.00,, Committer notes: Rename 'struct perf_pmu_alias_name' to 'pmu_alias', the 'perf_' prefix should be used for libperf, things inside just tools/perf/ are being moved away from that prefix. Also 'pmu_alias' is shorter and reflects the abstraction. Also don't use 'pmu' as the name for variables for that type, we should use that for the 'struct perf_pmu' variables, avoiding confusion. Use 'pmu_alias' for 'struct pmu_alias' variables. Co-developed-by: Jin Yao <[email protected]> Co-developed-by: Arnaldo Carvalho de Melo <[email protected]> Signed-off-by: Kan Liang <[email protected]> Reviewed-by: Andi Kleen <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: John Garry <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: Riccardo Mancini <[email protected]> Link: http://lore.kernel.org/lkml/[email protected] Signed-off-by: Jin Yao <[email protected]> Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-09-03perf session: Report collisions in AUX recordsSuzuki K Poulose2-0/+10
Just like the other flags in the AUX records, report a summary of the Collisions if there were any. Signed-off-by: Suzuki Poulouse <[email protected]> Reviewed-by: Leo Yan <[email protected]> Reviewed-by: Mathieu Poirier <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: James Clark <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Mike Leach <[email protected]> Cc: Suzuki Poulouse <[email protected]> Cc: [email protected] Cc: [email protected] LPU-Reference: [email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-09-03perf script python: Allow reporting the [un]throttle PERF_RECORD_ meta eventStephen Brennan3-0/+48
perf_events may sometimes throttle an event due to creating too many samples during a given timer tick. As of now, the perf tool will not report on throttling, which means this is a silent error. Implement a callback for the throttle and unthrottle events within the Python scripting engine, which can allow scripts to detect and report when events may have been lost due to throttling. The simplest script to report throttle events is: def throttle(*args): print("throttle" + repr(args)) def unthrottle(*args): print("unthrottle" + repr(args)) Signed-off-by: Stephen Brennan <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: http://lore.kernel.org/lkml/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-09-03perf build: Report failure for testing feature libopencsdLeo Yan1-0/+2
When build perf tool with passing option 'CORESIGHT=1' explicitly, if the feature test fails for library libopencsd, the build doesn't complain the feature failure and continue to build the tool with disabling the CoreSight feature insteadly. This patch changes the building behaviour, when build perf tool with the option 'CORESIGHT=1' and detect the failure for testing feature libopencsd, the build process will be aborted and it shows the complaint info. Committer testing: First make sure there is no opencsd library installed: $ rpm -qa | grep -i csd $ sudo rm -rf `find /usr/local -name "*csd*"` $ find /usr/local -name "*csd*" $ Then cleanup the perf build output directory: $ rm -rf /tmp/build/perf ; mkdir -p /tmp/build/perf ; $ And try to build explicitely asking for coresight: $ make O=/tmp/build/perf CORESIGHT=1 O=/tmp/build/perf -C tools/perf install-bin make: Entering directory '/var/home/acme/git/perf/tools/perf' BUILD: Doing 'make -j24' parallel build HOSTCC /tmp/build/perf/fixdep.o HOSTLD /tmp/build/perf/fixdep-in.o LINK /tmp/build/perf/fixdep Makefile.config:493: *** Error: No libopencsd library found or the version is not up-to-date. Please install recent libopencsd to build with CORESIGHT=1. Stop. make[1]: *** [Makefile.perf:238: sub-make] Error 2 make: *** [Makefile:113: install-bin] Error 2 make: Leaving directory '/var/home/acme/git/perf/tools/perf' $ Now install the opencsd library present in Fedora 34: $ sudo dnf install opencsd-devel <SNIP> Installed: opencsd-1.0.0-1.fc34.x86_64 opencsd-devel-1.0.0-1.fc34.x86_64 Complete! $ Try again building with coresight: $ make O=/tmp/build/perf CORESIGHT=1 O=/tmp/build/perf -C tools/perf install-bin make: Entering directory '/var/home/acme/git/perf/tools/perf' BUILD: Doing 'make -j24' parallel build Makefile.config:493: *** Error: No libopencsd library found or the version is not up-to-date. Please install recent libopencsd to build with CORESIGHT=1. Stop. make[1]: *** [Makefile.perf:238: sub-make] Error 2 make: *** [Makefile:113: install-bin] Error 2 make: Leaving directory '/var/home/acme/git/perf/tools/perf' $ Since Fedora 34 is pretty recent, one assumes we need to get it from its upstream git repository, use rpm to find where that is: $ rpm -q --qf "%{URL}\n" opencsd https://github.com/Linaro/OpenCSD $ Go there, clone the repo, build it and install into /usr/local, then try again: $ cd ~acme/git/perf $ make O=/tmp/build/perf VF=1 CORESIGHT=1 O=/tmp/build/perf -C tools/perf install-bin | grep -i opencsd ... libopencsd: [ on ] PERF_VERSION = 5.14.g454719f67a3d $ export LD_LIBRARY_PATH=/usr/local/lib $ ldd ~/bin/perf | grep opencsd libopencsd_c_api.so.1 => /usr/local/lib/libopencsd_c_api.so.1 (0x00007f28f78a4000) libopencsd.so.1 => /usr/local/lib/libopencsd.so.1 (0x00007f28f6a2e000) $ Now it works. Requested-by: Arnaldo Carvalho de Melo <[email protected]> Signed-off-by: Leo Yan <[email protected]> Tested-by: Arnaldo Carvalho de Melo <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: James Clark <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Mathieu Poirier <[email protected]> Cc: Mike Leach <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: Suzuki Poulouse <[email protected]> Cc: [email protected] Link: http://lore.kernel.org/lkml/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-09-03perf cs-etm: Show a warning for an unknown magic numberJames Clark1-0/+5
Currently perf reports "Cannot allocate memory" which isn't very helpful for a potentially user facing issue. If we add a new magic number in the future, perf will be able to report unrecognised magic numbers. Reviewed-by: Leo Yan <[email protected]> Signed-off-by: James Clark <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: John Garry <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Mathieu Poirier <[email protected]> Cc: Mike Leach <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Suzuki Poulouse <[email protected]> Cc: Will Deacon <[email protected]> Cc: [email protected] Cc: [email protected] Link: https //lore.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-09-03perf cs-etm: Print the decoder nameJames Clark3-8/+14
Use the real name of the decoder instead of hard-coding "ETM" to avoid confusion when the trace is ETE. This also now distinguishes between ETMv3 and ETMv4. Reviewed-by: Leo Yan <[email protected]> Reviewed-by: Suzuki Poulouse <[email protected]> Signed-off-by: James Clark <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: John Garry <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Mathieu Poirier <[email protected]> Cc: Mike Leach <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Will Deacon <[email protected]> Cc: [email protected] Cc: [email protected] Link: https //lore.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-09-03perf cs-etm: Create ETE decoderJames Clark3-0/+50
If the magic number indicates ETE instantiate a OCSD_BUILTIN_DCD_ETE decoder instead of OCSD_BUILTIN_DCD_ETMV4I. ETE is the new trace feature for Armv9. Testing performed ================= * Old files with v0 and v1 headers for ETMv4 still open correctly * New files with new magic number open on new versions of perf * New files with new magic number fail to open on old versions of perf * Decoding with the ETE decoder results in the same output as the ETMv4 decoder as long as there are no new ETE packet types Reviewed-by: Leo Yan <[email protected]> Signed-off-by: James Clark <[email protected]> Acked-by: Suzuki Poulouse <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: John Garry <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Mathieu Poirier <[email protected]> Cc: Mike Leach <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Will Deacon <[email protected]> Cc: [email protected] Cc: [email protected] Link: https //lore.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-09-03perf cs-etm: Update OpenCSD decoder for ETEJames Clark1-2/+0
OpenCSD v1.1.1 has a bug fix for the installation of the ETE decoder headers. This also means that including headers separately for each decoder is unnecessary so remove these. Reviewed-by: Leo Yan <[email protected]> Signed-off-by: James Clark <[email protected]> Acked-by: Suzuki Poulouse <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: John Garry <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Mathieu Poirier <[email protected]> Cc: Mike Leach <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Will Deacon <[email protected]> Cc: [email protected] Cc: [email protected] Link: https //lore.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-09-03perf cs-etm: Fix typoJames Clark1-1/+1
TRCIRD2 should be TRCIDR2 Reviewed-by: Leo Yan <[email protected]> Signed-off-by: James Clark <[email protected]> Acked-by: Suzuki Poulouse <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: John Garry <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Mathieu Poirier <[email protected]> Cc: Mike Leach <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Will Deacon <[email protected]> Cc: [email protected] Cc: [email protected] Link: https //lore.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-09-03perf cs-etm: Save TRCDEVARCH registerJames Clark3-7/+68
When ETE is present save the TRCDEVARCH register and set a new magic number. It will be used to configure the decoder in a later commit. Old versions of perf will not be able to open files with this new magic number, but old files will still work with newer versions of perf. Reviewed-by: Leo Yan <[email protected]> Signed-off-by: James Clark <[email protected]> Acked-by: Suzuki Poulouse <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: John Garry <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Mathieu Poirier <[email protected]> Cc: Mike Leach <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Will Deacon <[email protected]> Cc: [email protected] Cc: [email protected] Link: https //lore.kernel.org/r/[email protected] [ Addressed some cosmetic suggestions by Suzuki Poulouse ] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-09-03perf cs-etm: Refactor out ETMv4 header savingJames Clark1-23/+23
Extract a function for saving the ETMv4 header because this will be used for ETE in a later commit. Reviewed-by: Leo Yan <[email protected]> Signed-off-by: James Clark <[email protected]> Acked-by: Suzuki Poulouse <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: John Garry <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Mathieu Poirier <[email protected]> Cc: Mike Leach <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Will Deacon <[email protected]> Cc: [email protected] Cc: [email protected] Link: https //lore.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-09-03perf cs-etm: Initialise architecture based on TRCIDR1James Clark1-1/+16
Currently the architecture is hard coded as ARCH_V8, but from ETMv4.4 onwards this should be ARCH_AA64. Reviewed-by: Leo Yan <[email protected]> Signed-off-by: James Clark <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: John Garry <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Mathieu Poirier <[email protected]> Cc: Mike Leach <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Suzuki Poulouse <[email protected]> Cc: Will Deacon <[email protected]> Cc: [email protected] Cc: [email protected] Link: https //lore.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-09-03perf cs-etm: Refactor initialisation of decoder params.James Clark1-74/+25
The initialisation of the decoder params is duplicated between creation of the packet printer and packet decoder. Put them both into one function so that future changes only need to be made in one place. Reviewed-by: Leo Yan <[email protected]> Signed-off-by: James Clark <[email protected]> Acked-by: Suzuki Poulouse <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: John Garry <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Mathieu Poirier <[email protected]> Cc: Mike Leach <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Will Deacon <[email protected]> Cc: [email protected] Cc: [email protected] Link: https //lore.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-09-01Merge branch 'exit-cleanups-for-v5.15' of ↵Linus Torvalds2-2/+2
git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace Pull exit cleanups from Eric Biederman: "In preparation of doing something about PTRACE_EVENT_EXIT I have started cleaning up various pieces of code related to do_exit. Most of that code I did not manage to get tested and reviewed before the merge window opened but a handful of very useful cleanups are ready to be merged. The first change is simply the removal of the bdflush system call. The code has now been disabled long enough that even the oldest userspace working userspace setups anyone can find to test are fine with the bdflush system call being removed. Changing m68k fsp040_die to use force_sigsegv(SIGSEGV) instead of calling do_exit directly is interesting only in that it is nearly the most difficult of the incorrect uses of do_exit to remove. The change to the seccomp code to simply send a signal instead of calling do_coredump directly is a very nice little cleanup made possible by realizing the existing signal sending helpers were missing a little bit of functionality that is easy to provide" * 'exit-cleanups-for-v5.15' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace: signal/seccomp: Dump core when there is only one live thread signal/seccomp: Refactor seccomp signal and coredump generation signal/m68k: Use force_sigsegv(SIGSEGV) in fpsp040_die exit/bdflush: Remove the deprecated bdflush system call
2021-09-01perf evlist: Add evlist__for_each_entry_from() macroRiccardo Mancini1-0/+16
This patch adds a new iteration macro for evlist that resumes iteration from a given evsel in the evlist. This macro will be used in the workqueue series. Signed-off-by: Riccardo Mancini <[email protected]> Cc: Ian Rogers <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: http://lore.kernel.org/lkml/2386505f8b598adf0dbcd04ec21804c6bcf00826.1629490974.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-08-31perf evsel: Handle precise_ip fallback in evsel__open_cpu()Riccardo Mancini2-33/+28
This is another patch in the effort to separate the fallback mechanisms from the open itself. In case of precise_ip fallback, the original precise_ip will be stored in the evsel (it was stored in a local variable) and the open will be retried. Since the precise_ip fallback will be the first in the chain of fallbacks, there should be no functional change with this patch. Signed-off-by: Riccardo Mancini <[email protected]> Cc: Ian Rogers <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: http://lore.kernel.org/lkml/74208c433d2024a6c4af9c0b140b54ed6b5ea810.1629490974.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-08-31perf evsel: Move bpf_counter__install_pe() to success path in evsel__open_cpu()Riccardo Mancini1-2/+2
I don't see why bpf_counter__install_pe() should get called even if fd = -1, so I'm moving it to the success path. This will be useful in following patches to separate the actual open and the related operations from the fallback mechanisms. Signed-off-by: Riccardo Mancini <[email protected]> Cc: Ian Rogers <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: Song Liu <[email protected]> Link: http://lore.kernel.org/lkml/64f8a1b0a838a6e6049cd43c1beafd432999ae57.1629490974.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-08-31perf evsel: Move test_attr__open() to success path in evsel__open_cpu()Riccardo Mancini1-5/+5
test_attr__open() ignores the fd if -1, therefore it is safe to move it to the success path (fd >= 0). Signed-off-by: Riccardo Mancini <[email protected]> Cc: Ian Rogers <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: http://lore.kernel.org/lkml/b3baf11360ca96541c9631730614fd7d217496fc.1629490974.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-08-31perf evsel: Move ignore_missing_thread() to fallback codeRiccardo Mancini2-16/+18
This patch moves ignore_missing_thread outside the perf_event_open loop. Doing so, we need to move the retry_open flag a few places higher, with minimal impact. Furthermore, thread need not be decreased since it won't get increased by the for loop (since we're jumping back inside), but we need to check that the nthreads decrease didn't put thread out of range. The goal is to have fallbacks handled in one place only, since in the future parallel code, these would be handled separately. Signed-off-by: Riccardo Mancini <[email protected]> Cc: Ian Rogers <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: http://lore.kernel.org/lkml/4eca51443c786baaf6811b7cd8e73aafd97f7606.1629490974.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-08-31perf evsel: Separate rlimit increase from evsel__open_cpu()Riccardo Mancini2-20/+33
This is a preparatory patch for the workqueue patches with the goal to separate from evlist__open_cpu() the actual opening (which could be performed in parallel), from the existing fallback mechanisms, which should be handled sequentially. This patch separates the rlimit increase from evsel__open_cpu(). Signed-off-by: Riccardo Mancini <[email protected]> Cc: Ian Rogers <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: http://lore.kernel.org/lkml/2f256de8ec37b9809a5cef73c2fa7bce416af5d3.1629490974.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-08-31perf evsel: Separate missing feature detection from evsel__open_cpu()Riccardo Mancini2-83/+92
This is a preparatory patch for the workqueue patches with the goal to separate in evlist__open_cpu() the actual opening, which could be performed in parallel, from the existing fallback mechanisms, which should be handled sequentially. This patch separates the missing feature detection in evsel__open_cpu() into a new evsel__detect_missing_features() function. Signed-off-by: Riccardo Mancini <[email protected]> Cc: Ian Rogers <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: http://lore.kernel.org/lkml/cba0b7d939862473662adeedb0f9c9b69566ee9a.1629490974.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-08-31perf evsel: Add evsel__prepare_open()Riccardo Mancini2-0/+16
This function will prepare the evsel and disable the missing features. It will be used in one of the following patches. Signed-off-by: Riccardo Mancini <[email protected]> Cc: Ian Rogers <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: http://lore.kernel.org/lkml/fa5e78bbb92c848226f044278fdcf777b3ce4583.1629490974.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-08-31perf evsel: Separate missing feature disabling from evsel__open_cpuRiccardo Mancini1-26/+31
This is a preparatory patch for the patches in the workqueue series with the goal to separate in evlist__open_cpu() the actual opening, which could be performed in parallel, from the existing fallback mechanisms, which should be handled sequentially. This patch separates the disabling of missing features from evlist__open_cpu() into a new function evsel__disable_missing_features((). Signed-off-by: Riccardo Mancini <[email protected]> Cc: Ian Rogers <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: http://lore.kernel.org/lkml/48138bd2932646dde315505da733c2ca635ad2ee.1629490974.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-08-31perf evsel: Save open flags in evsel in prepare_open()Riccardo Mancini2-12/+13
This patch caches the flags used in perf_event_open() inside evsel, so that they can be set in __evsel__prepare_open() (this will be useful in patches in the workqueue series, when the fallback mechanisms will be handled outside the open itself). This also optimizes the code, by not having to recompute them everytime. Since flags are now saved in evsel, the flags argument in perf_event_open() is removed. Signed-off-by: Riccardo Mancini <[email protected]> Cc: Ian Rogers <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: http://lore.kernel.org/lkml/d9f63159098e56fa518eecf25171d72e6f74df37.1629490974.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-08-31perf evsel: Separate open preparation from open itselfRiccardo Mancini1-11/+34
This is a preparatory patch for the following patches with the goal to separate in evlist__open_cpu the actual perf_event_open, which could be performed in parallel, from the existing fallback mechanisms, which should be handled sequentially. This patch separates the first lines of evsel__open_cpu into a new __evsel__prepare_open function. Signed-off-by: Riccardo Mancini <[email protected]> Cc: Ian Rogers <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: http://lore.kernel.org/lkml/e14118b934c338dbbf68b8677f20d0d7dbf9359a.1629490974.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-08-31perf evsel: Remove retry_sample_id goto labelRiccardo Mancini1-2/+1
As far as I can tell, there is no good reason, apart from optimization to have the retry_sample_id separate from fallback_missing_features. Probably, this label was added to avoid reapplying patches for missing features that had already been applied. However, missing features that have been added later have not used this optimization, always jumping to fallback_missing_features and reapplying all missing features. This patch removes that label, replacing it with fallback_missing_features. Signed-off-by: Riccardo Mancini <[email protected]> Cc: Ian Rogers <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: http://lore.kernel.org/lkml/340af0d03408d6621fd9c742e311db18b3585b3b.1629490974.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-08-31perf mmap: Add missing bitops.h headerRiccardo Mancini1-0/+1
MMAP_CPU_MASK_BYTES uses the BITS_TO_LONGS macro, which is defined in linux/bitops.h. However, this header is not included directly, but gets imported indirectly in files using the macro. This patch adds the missing include. Signed-off-by: Riccardo Mancini <[email protected]> Cc: Ian Rogers <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: http://lore.kernel.org/lkml/c5b91ee432a2e28e7f16337c740b43b4d0b0e86c.1629490974.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-08-31perf tools: Fix LLVM download hint linkJames Clark1-1/+1
http://llvm.org/apt returns 404, it has moved to https://apt.llvm.org/ Signed-off-by: James Clark <[email protected]> Tested-by: Arnaldo Carvalho de Melo <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: [email protected] Link: http://lore.kernel.org/lkml/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-08-31perf tools: Fix LLVM test failure when running in verbose modeJames Clark2-5/+4
A CI system might want to run all tests in verbose mode so that there is enough information to diagnose issues. This LLVM test is the only test that uses "-v" to signify to not skip the test if the preconditions aren't met (LLVM isn't installed). This means that running the test in verbose mode without LLVM installed causes a test failure. For consistency with the other tests, remove this verbose/skip check. An alternate solution would be to make _all_ tests not skip when run in verbose mode, but I don't think that would be intuitive. Also change the search_program() call to search_program_and_warn(). Previously the hint about installing LLVM was only printed by the actual test because this check was skipped in verbose mode. To maintain the old behaviour, the precondition check must also print the full warning. Previous output: $ ./perf test llvm 40: LLVM search and compile : 40.1: Basic BPF llvm compile : Skip $ ./perf test -v llvm 40: LLVM search and compile : 40.1: Basic BPF llvm compile : --- start --- test child forked, pid 2085835 ERROR: unable to find clang. Hint: Try to install latest clang/llvm to support BPF. Check your $PATH ... test child finished with -1 ---- end ---- LLVM search and compile subtest 1: FAILED! New output (non verbose mode is identical, verbose changes from fail to skip): $ ./perf test llvm 40: LLVM search and compile : 40.1: Basic BPF llvm compile : Skip $ ./perf test -v llvm 40: LLVM search and compile : 40.1: Basic BPF llvm compile : --- start --- test child forked, pid 2087680 ERROR: unable to find clang. Hint: Try to install latest clang/llvm to support BPF. Check your $PATH ... No clang, skip this test test child finished with -2 ---- end ---- LLVM search and compile subtest 1: Skip Signed-off-by: James Clark <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: [email protected] Link: http://lore.kernel.org/lkml/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-08-31perf tools: Refactor LLVM test warning for missing binaryJames Clark1-15/+21
The same warning is duplicated in two places so refactor it into a single function "search_program_and_warn". This will be used a third time in a later commit. Signed-off-by: James Clark <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: [email protected] Link: http://lore.kernel.org/lkml/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-08-31perf auxtrace arm: Support compat_auxtrace_mmap__{read_head|write_tail}Leo Yan1-0/+32
When the tool runs with compat mode on Arm platform, the kernel is in 64-bit mode and user space is in 32-bit mode; the user space can use instructions "ldrd" and "strd" for 64-bit value atomicity. This patch adds compat_auxtrace_mmap__{read_head|write_tail} for arm building, it uses "ldrd" and "strd" instructions to ensure accessing atomicity for aux head and tail. The file arch/arm/util/auxtrace.c is built for arm and arm64 building, these two functions are not needed for arm64, so check the compiler macro "__arm__" to only include them for arm building. Signed-off-by: Leo Yan <[email protected]> Reviewed-by: James Clark <[email protected]> Tested-by: James Clark <[email protected]> Cc: Adrian Hunter <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Andi Kleen <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: John Garry <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Mathieu Poirier <[email protected]> Cc: Mike Leach <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: "Russell King (oracle)" <[email protected]> Cc: Suzuki Poulouse <[email protected]> Cc: Will Deacon <[email protected]> Cc: [email protected] Cc: [email protected] Link: http://lore.kernel.org/lkml/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-08-31perf auxtrace: Add compat_auxtrace_mmap__{read_head|write_tail}Leo Yan2-7/+103
When perf runs in compat mode (kernel in 64-bit mode and the perf is in 32-bit mode), the 64-bit value atomicity in the user space cannot be assured, E.g. on some architectures, the 64-bit value accessing is split into two instructions, one is for the low 32-bit word accessing and another is for the high 32-bit word. This patch introduces weak functions compat_auxtrace_mmap__read_head() and compat_auxtrace_mmap__write_tail(), as their naming indicates, when perf tool works in compat mode, it uses these two functions to access the AUX head and tail. These two functions can allow the perf tool to work properly in certain conditions, e.g. when perf tool works in snapshot mode with only using AUX head pointer, or perf tool uses the AUX buffer and the incremented tail is not bigger than 4GB. When perf tool cannot handle the case when the AUX tail is bigger than 4GB, the function compat_auxtrace_mmap__write_tail() returns -1 and tells the caller to bail out for the error. These two functions are declared as weak attribute, this allows to implement arch specific functions if any arch can support the 64-bit value atomicity in compat mode. Suggested-by: Adrian Hunter <[email protected]> Signed-off-by: Leo Yan <[email protected]> Acked-by: Adrian Hunter <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Andi Kleen <[email protected]> Cc: James Clark <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: John Garry <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Mathieu Poirier <[email protected]> Cc: Mike Leach <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: "Russell King (oracle)" <[email protected]> Cc: Suzuki Poulouse <[email protected]> Cc: Will Deacon <[email protected]> Cc: [email protected] Cc: [email protected] Link: http://lore.kernel.org/lkml/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2021-08-31perf bpf: Fix memory leaks relating to BTF.Ian Rogers2-3/+3
BTF needs to be freed with btf__free(). Signed-off-by: Ian Rogers <[email protected]> Reviewed-by: Kajol Jain <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: Stephane Eranian <[email protected]> Link: http://lore.kernel.org/lkml/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
Powered by cgit, Gruvboxed by Blaster4385.