diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2024-03-15 02:31:23 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2024-03-15 02:31:23 +0300 |
commit | 1bbeaf83dd7b5e3628b98bec66ff8fe2646e14aa (patch) | |
tree | a391eed8ae206613b48e02e56e6ad5c4432d8767 /tools/perf/arch | |
parent | 63bd30f249dcf0a7ce16967935cecee8feec24bb (diff) | |
parent | 0f66dfe7b91d2743cc71dfff37af503215b204ef (diff) | |
download | linux-1bbeaf83dd7b5e3628b98bec66ff8fe2646e14aa.tar.xz |
Merge tag 'perf-tools-for-v6.9-2024-03-13' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools
Pull perf tools updates from Namhyung Kim:
"perf stat:
- Support new 'cluster' aggregation mode for shared resources
depending on the hardware configuration:
$ sudo perf stat -a --per-cluster -e cycles,instructions sleep 1
Performance counter stats for 'system wide':
S0-D0-CLS0 2 85,051,822 cycles
S0-D0-CLS0 2 73,909,908 instructions # 0.87 insn per cycle
S0-D0-CLS2 2 93,365,918 cycles
S0-D0-CLS2 2 83,006,158 instructions # 0.89 insn per cycle
S0-D0-CLS4 2 104,157,523 cycles
S0-D0-CLS4 2 53,234,396 instructions # 0.51 insn per cycle
S0-D0-CLS6 2 65,891,079 cycles
S0-D0-CLS6 2 41,478,273 instructions # 0.63 insn per cycle
1.002407989 seconds time elapsed
- Various fixes and cleanups for event metrics including NaN handling
perf script:
- Use libcapstone if available to disassemble the instructions. This
enables 'perf script -F disasm' and 'perf script --insn-trace=disasm'
(for Intel-PT):
$ perf script -F event,ip,disasm
cycles:P: ffffffffa988d428 wrmsr
cycles:P: ffffffffa9839d25 movq %rax, %r14
cycles:P: ffffffffa9cdcaf0 endbr64
cycles:P: ffffffffa988d428 wrmsr
cycles:P: ffffffffa988d428 wrmsr
cycles:P: ffffffffaa401f86 iretq
cycles:P: ffffffffa99c4de5 movq 0x30(%rcx), %r8
cycles:P: ffffffffa988d428 wrmsr
cycles:P: ffffffffaa401f86 iretq
cycles:P: ffffffffa9907983 movl 0x68(%rbx), %eax
cycles:P: ffffffffa988d428 wrmsr
- Expose sample ID / stream ID to python scripts
perf test:
- Add more perf test cases from Redhat internal test suites. This
time it adds the base infra and a few perf probe tests. More to
come. :)
- Add 'perf test -p' for parallel execution and fix some issues found
by the parallel test
- Support symbol test to print symbols in given (active) module:
$ perf test -F -v Symbols --dso /lib/modules/$(uname -r)/kernel/fs/ext4/ext4.ko
--- start ---
Testing /lib/modules/6.5.13-1rodete2-amd64/kernel/fs/ext4/ext4.ko
Overlapping symbols:
7a990-7a9a0 l __pfx_ext4_exit_fs
7a990-7a9a0 g __pfx_cleanup_module
Overlapping symbols:
7a9a0-7aa1c l ext4_exit_fs
7a9a0-7aa1c g cleanup_module
...
JSON metric updates:
- A new round of Intel metric updates
- Support Power11 PVR (compatible to Power10)
- Fix cache latency events on Zen 4 to set SliceId properly
Internal:
- Fix reference counting for 'map' data structure, tireless work from
Ian!
- More memory optimization for struct thread and annotate histogram.
Now, 'perf report' (TUI) and 'perf annotate' should be much
lighter-weight in terms of memory footprint
- Support cross-arch perf register access. Clean up the build
configuration so that it can detect arch-register support at
runtime. This can allow to parse register data in sample which was
recorded in a different arch
Others:
- Sync task state in 'perf sched' to kernel using trace event fields.
The task states have been changed so tools cannot assume a fixed
encoding
- Clean up 'perf mem' to generalize the arch-specific events
- Add support for local and global variables to data type profiling.
This would increase the success rate of type resolution with DWARF
- Add short option -H for --hierarchy in 'perf report' and 'perf top'"
* tag 'perf-tools-for-v6.9-2024-03-13' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools: (154 commits)
perf annotate: Add comments in the data structures
perf annotate: Remove sym_hist.addr[] array
perf annotate: Calculate instruction overhead using hashmap
perf annotate: Add a hashmap for symbol histogram
perf threads: Reduce table size from 256 to 8
perf threads: Switch from rbtree to hashmap
perf threads: Move threads to its own files
perf machine: Move machine's threads into its own abstraction
perf machine: Move fprintf to for_each loop and a callback
perf trace: Ignore thread hashing in summary
perf report: Sort child tasks by tid
perf vendor events amd: Fix Zen 4 cache latency events
perf version: Display availability of OpenCSD support
perf vendor events intel: Add umasks/occ_sel to PCU events.
perf map: Fix map reference count issues
libperf evlist: Avoid out-of-bounds access
perf lock contention: Account contending locks too
perf metrics: Fix segv for metrics with no events
perf metrics: Fix metric matching
perf pmu: Fix a potential memory leak in perf_pmu__lookup()
...
Diffstat (limited to 'tools/perf/arch')
30 files changed, 150 insertions, 152 deletions
diff --git a/tools/perf/arch/arm/util/perf_regs.c b/tools/perf/arch/arm/util/perf_regs.c index 2c56e8b56ddf..f94a0210c7b7 100644 --- a/tools/perf/arch/arm/util/perf_regs.c +++ b/tools/perf/arch/arm/util/perf_regs.c @@ -2,7 +2,7 @@ #include "perf_regs.h" #include "../../../util/perf_regs.h" -const struct sample_reg sample_reg_masks[] = { +static const struct sample_reg sample_reg_masks[] = { SMPL_REG_END }; @@ -15,3 +15,8 @@ uint64_t arch__user_reg_mask(void) { return PERF_REGS_MASK; } + +const struct sample_reg *arch__sample_reg_masks(void) +{ + return sample_reg_masks; +} diff --git a/tools/perf/arch/arm/util/pmu.c b/tools/perf/arch/arm/util/pmu.c index 7f3af3b97f3b..8b7cb68ba1a8 100644 --- a/tools/perf/arch/arm/util/pmu.c +++ b/tools/perf/arch/arm/util/pmu.c @@ -13,6 +13,7 @@ #include "hisi-ptt.h" #include "../../../util/pmu.h" #include "../../../util/cs-etm.h" +#include "../../arm64/util/mem-events.h" void perf_pmu__arch_init(struct perf_pmu *pmu __maybe_unused) { @@ -26,6 +27,8 @@ void perf_pmu__arch_init(struct perf_pmu *pmu __maybe_unused) pmu->selectable = true; pmu->is_uncore = false; pmu->perf_event_attr_init_default = arm_spe_pmu_default_config; + if (!strcmp(pmu->name, "arm_spe_0")) + pmu->mem_events = perf_mem_events_arm; } else if (strstarts(pmu->name, HISI_PTT_PMU_NAME)) { pmu->selectable = true; #endif diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile index fab3095fb5d0..5735ed4479bb 100644 --- a/tools/perf/arch/arm64/Makefile +++ b/tools/perf/arch/arm64/Makefile @@ -18,7 +18,7 @@ sysprf := $(srctree)/tools/perf/arch/arm64/entry/syscalls/ systbl := $(sysprf)/mksyscalltbl # Create output directory if not already present -_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') +$(shell [ -d '$(out)' ] || mkdir -p '$(out)') $(header): $(sysdef) $(systbl) $(Q)$(SHELL) '$(systbl)' '$(CC)' '$(HOSTCC)' $(incpath) $(sysdef) > $@ diff --git a/tools/perf/arch/arm64/util/machine.c b/tools/perf/arch/arm64/util/machine.c index ba1144366e85..aab1cc2bc283 100644 --- a/tools/perf/arch/arm64/util/machine.c +++ b/tools/perf/arch/arm64/util/machine.c @@ -12,5 +12,7 @@ void arch__add_leaf_frame_record_opts(struct record_opts *opts) { + const struct sample_reg *sample_reg_masks = arch__sample_reg_masks(); + opts->sample_user_regs |= sample_reg_masks[PERF_REG_ARM64_LR].mask; } diff --git a/tools/perf/arch/arm64/util/mem-events.c b/tools/perf/arch/arm64/util/mem-events.c index 3bcc5c7035c2..9f8da7937255 100644 --- a/tools/perf/arch/arm64/util/mem-events.c +++ b/tools/perf/arch/arm64/util/mem-events.c @@ -1,37 +1,12 @@ // SPDX-License-Identifier: GPL-2.0 -#include "map_symbol.h" +#include "util/map_symbol.h" +#include "util/mem-events.h" #include "mem-events.h" -#define E(t, n, s) { .tag = t, .name = n, .sysfs_name = s } +#define E(t, n, s, l, a) { .tag = t, .name = n, .event_name = s, .ldlat = l, .aux_event = a } -static struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = { - E("spe-load", "arm_spe_0/ts_enable=1,pa_enable=1,load_filter=1,store_filter=0,min_latency=%u/", "arm_spe_0"), - E("spe-store", "arm_spe_0/ts_enable=1,pa_enable=1,load_filter=0,store_filter=1/", "arm_spe_0"), - E("spe-ldst", "arm_spe_0/ts_enable=1,pa_enable=1,load_filter=1,store_filter=1,min_latency=%u/", "arm_spe_0"), +struct perf_mem_event perf_mem_events_arm[PERF_MEM_EVENTS__MAX] = { + E("spe-load", "%s/ts_enable=1,pa_enable=1,load_filter=1,store_filter=0,min_latency=%u/", NULL, true, 0), + E("spe-store", "%s/ts_enable=1,pa_enable=1,load_filter=0,store_filter=1/", NULL, false, 0), + E("spe-ldst", "%s/ts_enable=1,pa_enable=1,load_filter=1,store_filter=1,min_latency=%u/", NULL, true, 0), }; - -static char mem_ev_name[100]; - -struct perf_mem_event *perf_mem_events__ptr(int i) -{ - if (i >= PERF_MEM_EVENTS__MAX) - return NULL; - - return &perf_mem_events[i]; -} - -const char *perf_mem_events__name(int i, const char *pmu_name __maybe_unused) -{ - struct perf_mem_event *e = perf_mem_events__ptr(i); - - if (i >= PERF_MEM_EVENTS__MAX) - return NULL; - - if (i == PERF_MEM_EVENTS__LOAD || i == PERF_MEM_EVENTS__LOAD_STORE) - scnprintf(mem_ev_name, sizeof(mem_ev_name), - e->name, perf_mem_events__loads_ldlat); - else /* PERF_MEM_EVENTS__STORE */ - scnprintf(mem_ev_name, sizeof(mem_ev_name), e->name); - - return mem_ev_name; -} diff --git a/tools/perf/arch/arm64/util/mem-events.h b/tools/perf/arch/arm64/util/mem-events.h new file mode 100644 index 000000000000..5fc50be4be38 --- /dev/null +++ b/tools/perf/arch/arm64/util/mem-events.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ARM64_MEM_EVENTS_H +#define _ARM64_MEM_EVENTS_H + +extern struct perf_mem_event perf_mem_events_arm[PERF_MEM_EVENTS__MAX]; + +#endif /* _ARM64_MEM_EVENTS_H */ diff --git a/tools/perf/arch/arm64/util/perf_regs.c b/tools/perf/arch/arm64/util/perf_regs.c index 1b79d8eab22f..09308665e28a 100644 --- a/tools/perf/arch/arm64/util/perf_regs.c +++ b/tools/perf/arch/arm64/util/perf_regs.c @@ -16,7 +16,7 @@ #define HWCAP_SVE (1 << 22) #endif -const struct sample_reg sample_reg_masks[] = { +static const struct sample_reg sample_reg_masks[] = { SMPL_REG(x0, PERF_REG_ARM64_X0), SMPL_REG(x1, PERF_REG_ARM64_X1), SMPL_REG(x2, PERF_REG_ARM64_X2), @@ -175,3 +175,8 @@ uint64_t arch__user_reg_mask(void) } return PERF_REGS_MASK; } + +const struct sample_reg *arch__sample_reg_masks(void) +{ + return sample_reg_masks; +} diff --git a/tools/perf/arch/csky/util/perf_regs.c b/tools/perf/arch/csky/util/perf_regs.c index c0877c264d49..6b1665f41180 100644 --- a/tools/perf/arch/csky/util/perf_regs.c +++ b/tools/perf/arch/csky/util/perf_regs.c @@ -2,7 +2,7 @@ #include "perf_regs.h" #include "../../util/perf_regs.h" -const struct sample_reg sample_reg_masks[] = { +static const struct sample_reg sample_reg_masks[] = { SMPL_REG_END }; @@ -15,3 +15,8 @@ uint64_t arch__user_reg_mask(void) { return PERF_REGS_MASK; } + +const struct sample_reg *arch__sample_reg_masks(void) +{ + return sample_reg_masks; +} diff --git a/tools/perf/arch/loongarch/Makefile b/tools/perf/arch/loongarch/Makefile index c392e7af4743..3992a67a87d9 100644 --- a/tools/perf/arch/loongarch/Makefile +++ b/tools/perf/arch/loongarch/Makefile @@ -17,7 +17,7 @@ sysprf := $(srctree)/tools/perf/arch/loongarch/entry/syscalls/ systbl := $(sysprf)/mksyscalltbl # Create output directory if not already present -_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') +$(shell [ -d '$(out)' ] || mkdir -p '$(out)') $(header): $(sysdef) $(systbl) $(Q)$(SHELL) '$(systbl)' '$(CC)' '$(HOSTCC)' $(incpath) $(sysdef) > $@ diff --git a/tools/perf/arch/loongarch/util/perf_regs.c b/tools/perf/arch/loongarch/util/perf_regs.c index 2c56e8b56ddf..f94a0210c7b7 100644 --- a/tools/perf/arch/loongarch/util/perf_regs.c +++ b/tools/perf/arch/loongarch/util/perf_regs.c @@ -2,7 +2,7 @@ #include "perf_regs.h" #include "../../../util/perf_regs.h" -const struct sample_reg sample_reg_masks[] = { +static const struct sample_reg sample_reg_masks[] = { SMPL_REG_END }; @@ -15,3 +15,8 @@ uint64_t arch__user_reg_mask(void) { return PERF_REGS_MASK; } + +const struct sample_reg *arch__sample_reg_masks(void) +{ + return sample_reg_masks; +} diff --git a/tools/perf/arch/mips/Makefile b/tools/perf/arch/mips/Makefile index 8bc09072e3d6..cd0b011b3be5 100644 --- a/tools/perf/arch/mips/Makefile +++ b/tools/perf/arch/mips/Makefile @@ -11,7 +11,7 @@ sysdef := $(sysprf)/syscall_n64.tbl systbl := $(sysprf)/mksyscalltbl # Create output directory if not already present -_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') +$(shell [ -d '$(out)' ] || mkdir -p '$(out)') $(header): $(sysdef) $(systbl) $(Q)$(SHELL) '$(systbl)' $(sysdef) > $@ diff --git a/tools/perf/arch/mips/util/perf_regs.c b/tools/perf/arch/mips/util/perf_regs.c index c0877c264d49..6b1665f41180 100644 --- a/tools/perf/arch/mips/util/perf_regs.c +++ b/tools/perf/arch/mips/util/perf_regs.c @@ -2,7 +2,7 @@ #include "perf_regs.h" #include "../../util/perf_regs.h" -const struct sample_reg sample_reg_masks[] = { +static const struct sample_reg sample_reg_masks[] = { SMPL_REG_END }; @@ -15,3 +15,8 @@ uint64_t arch__user_reg_mask(void) { return PERF_REGS_MASK; } + +const struct sample_reg *arch__sample_reg_masks(void) +{ + return sample_reg_masks; +} diff --git a/tools/perf/arch/powerpc/Makefile b/tools/perf/arch/powerpc/Makefile index 840ea0e59287..bf6d323574f6 100644 --- a/tools/perf/arch/powerpc/Makefile +++ b/tools/perf/arch/powerpc/Makefile @@ -19,7 +19,7 @@ sysdef := $(sysprf)/syscall.tbl systbl := $(sysprf)/mksyscalltbl # Create output directory if not already present -_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') +$(shell [ -d '$(out)' ] || mkdir -p '$(out)') $(header64): $(sysdef) $(systbl) $(Q)$(SHELL) '$(systbl)' '64' $(sysdef) > $@ diff --git a/tools/perf/arch/powerpc/util/Build b/tools/perf/arch/powerpc/util/Build index 9889245c555c..1d323f3a3322 100644 --- a/tools/perf/arch/powerpc/util/Build +++ b/tools/perf/arch/powerpc/util/Build @@ -2,6 +2,7 @@ perf-y += header.o perf-$(CONFIG_LIBTRACEEVENT) += kvm-stat.o perf-y += perf_regs.o perf-y += mem-events.o +perf-y += pmu.o perf-y += sym-handling.o perf-y += evsel.o perf-y += event.o diff --git a/tools/perf/arch/powerpc/util/kvm-stat.c b/tools/perf/arch/powerpc/util/kvm-stat.c index d9a0ac1cdf30..c8357b571ccf 100644 --- a/tools/perf/arch/powerpc/util/kvm-stat.c +++ b/tools/perf/arch/powerpc/util/kvm-stat.c @@ -114,7 +114,7 @@ static int is_tracepoint_available(const char *str, struct evlist *evlist) parse_events_error__init(&err); ret = parse_events(evlist, str, &err); - if (err.str) + if (ret) parse_events_error__print(&err, "tracepoint"); parse_events_error__exit(&err); return ret; diff --git a/tools/perf/arch/powerpc/util/mem-events.c b/tools/perf/arch/powerpc/util/mem-events.c index 78b986e5268d..765d4a054b0a 100644 --- a/tools/perf/arch/powerpc/util/mem-events.c +++ b/tools/perf/arch/powerpc/util/mem-events.c @@ -1,12 +1,12 @@ // SPDX-License-Identifier: GPL-2.0 -#include "map_symbol.h" +#include "util/map_symbol.h" +#include "util/mem-events.h" #include "mem-events.h" -/* PowerPC does not support 'ldlat' parameter. */ -const char *perf_mem_events__name(int i, const char *pmu_name __maybe_unused) -{ - if (i == PERF_MEM_EVENTS__LOAD) - return "cpu/mem-loads/"; +#define E(t, n, s, l, a) { .tag = t, .name = n, .event_name = s, .ldlat = l, .aux_event = a } - return "cpu/mem-stores/"; -} +struct perf_mem_event perf_mem_events_power[PERF_MEM_EVENTS__MAX] = { + E("ldlat-loads", "%s/mem-loads/", "mem-loads", false, 0), + E("ldlat-stores", "%s/mem-stores/", "mem-stores", false, 0), + E(NULL, NULL, NULL, false, 0), +}; diff --git a/tools/perf/arch/powerpc/util/mem-events.h b/tools/perf/arch/powerpc/util/mem-events.h new file mode 100644 index 000000000000..6acc3d1b6873 --- /dev/null +++ b/tools/perf/arch/powerpc/util/mem-events.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _POWER_MEM_EVENTS_H +#define _POWER_MEM_EVENTS_H + +extern struct perf_mem_event perf_mem_events_power[PERF_MEM_EVENTS__MAX]; + +#endif /* _POWER_MEM_EVENTS_H */ diff --git a/tools/perf/arch/powerpc/util/perf_regs.c b/tools/perf/arch/powerpc/util/perf_regs.c index b38aa056eea0..e8e6e6fc6f17 100644 --- a/tools/perf/arch/powerpc/util/perf_regs.c +++ b/tools/perf/arch/powerpc/util/perf_regs.c @@ -17,7 +17,7 @@ #define PVR_POWER9 0x004E #define PVR_POWER10 0x0080 -const struct sample_reg sample_reg_masks[] = { +static const struct sample_reg sample_reg_masks[] = { SMPL_REG(r0, PERF_REG_POWERPC_R0), SMPL_REG(r1, PERF_REG_POWERPC_R1), SMPL_REG(r2, PERF_REG_POWERPC_R2), @@ -232,3 +232,8 @@ uint64_t arch__user_reg_mask(void) { return PERF_REGS_MASK; } + +const struct sample_reg *arch__sample_reg_masks(void) +{ + return sample_reg_masks; +} diff --git a/tools/perf/arch/powerpc/util/pmu.c b/tools/perf/arch/powerpc/util/pmu.c new file mode 100644 index 000000000000..554675deef7b --- /dev/null +++ b/tools/perf/arch/powerpc/util/pmu.c @@ -0,0 +1,12 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <string.h> + +#include "../../../util/pmu.h" +#include "mem-events.h" + +void perf_pmu__arch_init(struct perf_pmu *pmu) +{ + if (pmu->is_core) + pmu->mem_events = perf_mem_events_power; +} diff --git a/tools/perf/arch/riscv/util/perf_regs.c b/tools/perf/arch/riscv/util/perf_regs.c index c0877c264d49..6b1665f41180 100644 --- a/tools/perf/arch/riscv/util/perf_regs.c +++ b/tools/perf/arch/riscv/util/perf_regs.c @@ -2,7 +2,7 @@ #include "perf_regs.h" #include "../../util/perf_regs.h" -const struct sample_reg sample_reg_masks[] = { +static const struct sample_reg sample_reg_masks[] = { SMPL_REG_END }; @@ -15,3 +15,8 @@ uint64_t arch__user_reg_mask(void) { return PERF_REGS_MASK; } + +const struct sample_reg *arch__sample_reg_masks(void) +{ + return sample_reg_masks; +} diff --git a/tools/perf/arch/s390/Makefile b/tools/perf/arch/s390/Makefile index 74bffbea03e2..56994e63b43a 100644 --- a/tools/perf/arch/s390/Makefile +++ b/tools/perf/arch/s390/Makefile @@ -17,7 +17,7 @@ sysdef := $(sysprf)/syscall.tbl systbl := $(sysprf)/mksyscalltbl # Create output directory if not already present -_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') +$(shell [ -d '$(out)' ] || mkdir -p '$(out)') $(header): $(sysdef) $(systbl) $(Q)$(SHELL) '$(systbl)' $(sysdef) > $@ diff --git a/tools/perf/arch/s390/util/perf_regs.c b/tools/perf/arch/s390/util/perf_regs.c index c0877c264d49..6b1665f41180 100644 --- a/tools/perf/arch/s390/util/perf_regs.c +++ b/tools/perf/arch/s390/util/perf_regs.c @@ -2,7 +2,7 @@ #include "perf_regs.h" #include "../../util/perf_regs.h" -const struct sample_reg sample_reg_masks[] = { +static const struct sample_reg sample_reg_masks[] = { SMPL_REG_END }; @@ -15,3 +15,8 @@ uint64_t arch__user_reg_mask(void) { return PERF_REGS_MASK; } + +const struct sample_reg *arch__sample_reg_masks(void) +{ + return sample_reg_masks; +} diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile index 5a9f9a7bf07d..8952e00f9b60 100644 --- a/tools/perf/arch/x86/Makefile +++ b/tools/perf/arch/x86/Makefile @@ -17,7 +17,7 @@ sys := $(srctree)/tools/perf/arch/x86/entry/syscalls systbl := $(sys)/syscalltbl.sh # Create output directory if not already present -_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') +$(shell [ -d '$(out)' ] || mkdir -p '$(out)') $(header): $(sys)/syscall_64.tbl $(systbl) $(Q)$(SHELL) '$(systbl)' $(sys)/syscall_64.tbl 'x86_64' > $@ diff --git a/tools/perf/arch/x86/tests/dwarf-unwind.c b/tools/perf/arch/x86/tests/dwarf-unwind.c index 5bfec3345d59..c05c0a85dad4 100644 --- a/tools/perf/arch/x86/tests/dwarf-unwind.c +++ b/tools/perf/arch/x86/tests/dwarf-unwind.c @@ -34,6 +34,7 @@ static int sample_ustack(struct perf_sample *sample, } stack_size = map__end(map) - sp; + map__put(map); stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size; memcpy(buf, (void *) sp, stack_size); diff --git a/tools/perf/arch/x86/tests/hybrid.c b/tools/perf/arch/x86/tests/hybrid.c index 40f5d17fedab..e221ea104174 100644 --- a/tools/perf/arch/x86/tests/hybrid.c +++ b/tools/perf/arch/x86/tests/hybrid.c @@ -259,11 +259,10 @@ static int test_event(const struct evlist_test *e) parse_events_error__init(&err); ret = parse_events(evlist, e->name, &err); if (ret) { - pr_debug("failed to parse event '%s', err %d, str '%s'\n", - e->name, ret, err.str); + pr_debug("failed to parse event '%s', err %d\n", e->name, ret); parse_events_error__print(&err, e->name); ret = TEST_FAIL; - if (strstr(err.str, "can't access trace events")) + if (parse_events_error__contains(&err, "can't access trace events")) ret = TEST_SKIP; } else { ret = e->check(evlist); diff --git a/tools/perf/arch/x86/util/mem-events.c b/tools/perf/arch/x86/util/mem-events.c index 191b372f9a2d..62df03e91c7e 100644 --- a/tools/perf/arch/x86/util/mem-events.c +++ b/tools/perf/arch/x86/util/mem-events.c @@ -1,93 +1,28 @@ // SPDX-License-Identifier: GPL-2.0 -#include "util/pmu.h" -#include "util/pmus.h" -#include "util/env.h" -#include "map_symbol.h" -#include "mem-events.h" #include "linux/string.h" -#include "env.h" +#include "util/map_symbol.h" +#include "util/mem-events.h" +#include "mem-events.h" -static char mem_loads_name[100]; -static bool mem_loads_name__init; -static char mem_stores_name[100]; #define MEM_LOADS_AUX 0x8203 -#define MEM_LOADS_AUX_NAME "{%s/mem-loads-aux/,%s/mem-loads,ldlat=%u/}:P" -#define E(t, n, s) { .tag = t, .name = n, .sysfs_name = s } +#define E(t, n, s, l, a) { .tag = t, .name = n, .event_name = s, .ldlat = l, .aux_event = a } -static struct perf_mem_event perf_mem_events_intel[PERF_MEM_EVENTS__MAX] = { - E("ldlat-loads", "%s/mem-loads,ldlat=%u/P", "%s/events/mem-loads"), - E("ldlat-stores", "%s/mem-stores/P", "%s/events/mem-stores"), - E(NULL, NULL, NULL), +struct perf_mem_event perf_mem_events_intel[PERF_MEM_EVENTS__MAX] = { + E("ldlat-loads", "%s/mem-loads,ldlat=%u/P", "mem-loads", true, 0), + E("ldlat-stores", "%s/mem-stores/P", "mem-stores", false, 0), + E(NULL, NULL, NULL, false, 0), }; -static struct perf_mem_event perf_mem_events_amd[PERF_MEM_EVENTS__MAX] = { - E(NULL, NULL, NULL), - E(NULL, NULL, NULL), - E("mem-ldst", "ibs_op//", "ibs_op"), +struct perf_mem_event perf_mem_events_intel_aux[PERF_MEM_EVENTS__MAX] = { + E("ldlat-loads", "{%s/mem-loads-aux/,%s/mem-loads,ldlat=%u/}:P", "mem-loads", true, MEM_LOADS_AUX), + E("ldlat-stores", "%s/mem-stores/P", "mem-stores", false, 0), + E(NULL, NULL, NULL, false, 0), }; -struct perf_mem_event *perf_mem_events__ptr(int i) -{ - if (i >= PERF_MEM_EVENTS__MAX) - return NULL; - - if (x86__is_amd_cpu()) - return &perf_mem_events_amd[i]; - - return &perf_mem_events_intel[i]; -} - -bool is_mem_loads_aux_event(struct evsel *leader) -{ - struct perf_pmu *pmu = perf_pmus__find("cpu"); - - if (!pmu) - pmu = perf_pmus__find("cpu_core"); - - if (pmu && !perf_pmu__have_event(pmu, "mem-loads-aux")) - return false; - - return leader->core.attr.config == MEM_LOADS_AUX; -} - -const char *perf_mem_events__name(int i, const char *pmu_name) -{ - struct perf_mem_event *e = perf_mem_events__ptr(i); - - if (!e) - return NULL; - - if (i == PERF_MEM_EVENTS__LOAD) { - if (mem_loads_name__init && !pmu_name) - return mem_loads_name; - - if (!pmu_name) { - mem_loads_name__init = true; - pmu_name = "cpu"; - } - - if (perf_pmus__have_event(pmu_name, "mem-loads-aux")) { - scnprintf(mem_loads_name, sizeof(mem_loads_name), - MEM_LOADS_AUX_NAME, pmu_name, pmu_name, - perf_mem_events__loads_ldlat); - } else { - scnprintf(mem_loads_name, sizeof(mem_loads_name), - e->name, pmu_name, - perf_mem_events__loads_ldlat); - } - return mem_loads_name; - } - - if (i == PERF_MEM_EVENTS__STORE) { - if (!pmu_name) - pmu_name = "cpu"; - - scnprintf(mem_stores_name, sizeof(mem_stores_name), - e->name, pmu_name); - return mem_stores_name; - } - - return e->name; -} +struct perf_mem_event perf_mem_events_amd[PERF_MEM_EVENTS__MAX] = { + E(NULL, NULL, NULL, false, 0), + E(NULL, NULL, NULL, false, 0), + E("mem-ldst", "%s//", NULL, false, 0), +}; diff --git a/tools/perf/arch/x86/util/mem-events.h b/tools/perf/arch/x86/util/mem-events.h new file mode 100644 index 000000000000..f55c8d3b7d59 --- /dev/null +++ b/tools/perf/arch/x86/util/mem-events.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _X86_MEM_EVENTS_H +#define _X86_MEM_EVENTS_H + +extern struct perf_mem_event perf_mem_events_intel[PERF_MEM_EVENTS__MAX]; +extern struct perf_mem_event perf_mem_events_intel_aux[PERF_MEM_EVENTS__MAX]; + +extern struct perf_mem_event perf_mem_events_amd[PERF_MEM_EVENTS__MAX]; + +#endif /* _X86_MEM_EVENTS_H */ diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c index b813502a2727..12fd93f04802 100644 --- a/tools/perf/arch/x86/util/perf_regs.c +++ b/tools/perf/arch/x86/util/perf_regs.c @@ -13,7 +13,7 @@ #include "../../../util/pmu.h" #include "../../../util/pmus.h" -const struct sample_reg sample_reg_masks[] = { +static const struct sample_reg sample_reg_masks[] = { SMPL_REG(AX, PERF_REG_X86_AX), SMPL_REG(BX, PERF_REG_X86_BX), SMPL_REG(CX, PERF_REG_X86_CX), @@ -276,6 +276,11 @@ int arch_sdt_arg_parse_op(char *old_op, char **new_op) return SDT_ARG_VALID; } +const struct sample_reg *arch__sample_reg_masks(void) +{ + return sample_reg_masks; +} + uint64_t arch__intr_reg_mask(void) { struct perf_event_attr attr = { diff --git a/tools/perf/arch/x86/util/pmu.c b/tools/perf/arch/x86/util/pmu.c index 469555ae9b3c..c3d89d6ba1bf 100644 --- a/tools/perf/arch/x86/util/pmu.c +++ b/tools/perf/arch/x86/util/pmu.c @@ -15,6 +15,7 @@ #include "../../../util/pmu.h" #include "../../../util/fncache.h" #include "../../../util/pmus.h" +#include "mem-events.h" #include "env.h" void perf_pmu__arch_init(struct perf_pmu *pmu __maybe_unused) @@ -30,14 +31,14 @@ void perf_pmu__arch_init(struct perf_pmu *pmu __maybe_unused) pmu->selectable = true; } #endif -} - -int perf_pmus__num_mem_pmus(void) -{ - /* AMD uses IBS OP pmu and not a core PMU for perf mem/c2c */ - if (x86__is_amd_cpu()) - return 1; - /* Intel uses core pmus for perf mem/c2c */ - return perf_pmus__num_core_pmus(); + if (x86__is_amd_cpu()) { + if (!strcmp(pmu->name, "ibs_op")) + pmu->mem_events = perf_mem_events_amd; + } else if (pmu->is_core) { + if (perf_pmu__have_event(pmu, "mem-loads-aux")) + pmu->mem_events = perf_mem_events_intel_aux; + else + pmu->mem_events = perf_mem_events_intel; + } } diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c index 9b99f48b923c..e2d6cfe21057 100644 --- a/tools/perf/arch/x86/util/tsc.c +++ b/tools/perf/arch/x86/util/tsc.c @@ -33,7 +33,7 @@ static double cpuinfo_tsc_freq(void) cpuinfo = fopen("/proc/cpuinfo", "r"); if (!cpuinfo) { - pr_err("Failed to read /proc/cpuinfo for TSC frequency"); + pr_err("Failed to read /proc/cpuinfo for TSC frequency\n"); return NAN; } while (getline(&line, &len, cpuinfo) > 0) { @@ -48,7 +48,7 @@ static double cpuinfo_tsc_freq(void) } out: if (fpclassify(result) == FP_ZERO) - pr_err("Failed to find TSC frequency in /proc/cpuinfo"); + pr_err("Failed to find TSC frequency in /proc/cpuinfo\n"); free(line); fclose(cpuinfo); |