diff options
33 files changed, 629 insertions, 187 deletions
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index da6780122786..8a10a045b57b 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1153,7 +1153,6 @@ static void setup_pebs_sample_data(struct perf_event *event, if (pebs == NULL) return; - regs->flags &= ~PERF_EFLAGS_EXACT; sample_type = event->attr.sample_type; dsrc = sample_type & PERF_SAMPLE_DATA_SRC; @@ -1197,7 +1196,13 @@ static void setup_pebs_sample_data(struct perf_event *event, * and PMI. */ *regs = *iregs; - regs->flags = pebs->flags; + + /* + * Initialize regs_>flags from PEBS, + * Clear exact bit (which uses x86 EFLAGS Reserved bit 3), + * i.e., do not rely on it being zero: + */ + regs->flags = pebs->flags & ~PERF_EFLAGS_EXACT; if (sample_type & PERF_SAMPLE_REGS_INTR) { regs->ax = pebs->ax; @@ -1217,10 +1222,6 @@ static void setup_pebs_sample_data(struct perf_event *event, regs->sp = pebs->sp; } - /* - * Preserve PERF_EFLAGS_VM from set_linear_ip(). - */ - regs->flags = pebs->flags | (regs->flags & PERF_EFLAGS_VM); #ifndef CONFIG_X86_32 regs->r8 = pebs->r8; regs->r9 = pebs->r9; @@ -1234,20 +1235,33 @@ static void setup_pebs_sample_data(struct perf_event *event, } if (event->attr.precise_ip > 1) { - /* Haswell and later have the eventing IP, so use it: */ + /* + * Haswell and later processors have an 'eventing IP' + * (real IP) which fixes the off-by-1 skid in hardware. + * Use it when precise_ip >= 2 : + */ if (x86_pmu.intel_cap.pebs_format >= 2) { set_linear_ip(regs, pebs->real_ip); regs->flags |= PERF_EFLAGS_EXACT; } else { - /* Otherwise use PEBS off-by-1 IP: */ + /* Otherwise, use PEBS off-by-1 IP: */ set_linear_ip(regs, pebs->ip); - /* ... and try to fix it up using the LBR entries: */ + /* + * With precise_ip >= 2, try to fix up the off-by-1 IP + * using the LBR. If successful, the fixup function + * corrects regs->ip and calls set_linear_ip() on regs: + */ if (intel_pmu_pebs_fixup_ip(regs)) regs->flags |= PERF_EFLAGS_EXACT; } - } else + } else { + /* + * When precise_ip == 1, return the PEBS off-by-1 IP, + * no fixup attempted: + */ set_linear_ip(regs, pebs->ip); + } if ((sample_type & (PERF_SAMPLE_ADDR | PERF_SAMPLE_PHYS_ADDR)) && diff --git a/kernel/events/core.c b/kernel/events/core.c index fc1c330c6bd6..2d5fe26551f8 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -4447,6 +4447,9 @@ static void _free_event(struct perf_event *event) if (event->ctx) put_ctx(event->ctx); + if (event->hw.target) + put_task_struct(event->hw.target); + exclusive_event_destroy(event); module_put(event->pmu->module); @@ -8397,6 +8400,10 @@ static int perf_kprobe_event_init(struct perf_event *event) if (event->attr.type != perf_kprobe.type) return -ENOENT; + + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; + /* * no branch sampling for probe events */ @@ -8434,6 +8441,10 @@ static int perf_uprobe_event_init(struct perf_event *event) if (event->attr.type != perf_uprobe.type) return -ENOENT; + + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; + /* * no branch sampling for probe events */ @@ -9955,6 +9966,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, * and we cannot use the ctx information because we need the * pmu before we get a ctx. */ + get_task_struct(task); event->hw.target = task; } @@ -10070,6 +10082,8 @@ err_ns: perf_detach_cgroup(event); if (event->ns) put_pid_ns(event->ns); + if (event->hw.target) + put_task_struct(event->hw.target); kfree(event); return ERR_PTR(err); diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index 2c416509b834..c79193e598f5 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -252,6 +252,8 @@ int perf_kprobe_init(struct perf_event *p_event, bool is_retprobe) ret = strncpy_from_user( func, u64_to_user_ptr(p_event->attr.kprobe_func), KSYM_NAME_LEN); + if (ret == KSYM_NAME_LEN) + ret = -E2BIG; if (ret < 0) goto out; @@ -300,6 +302,8 @@ int perf_uprobe_init(struct perf_event *p_event, bool is_retprobe) return -ENOMEM; ret = strncpy_from_user( path, u64_to_user_ptr(p_event->attr.uprobe_path), PATH_MAX); + if (ret == PATH_MAX) + return -E2BIG; if (ret < 0) goto out; if (path[0] == '\0') { diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 469ba7ecd14b..34fd0e0ec51d 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -151,6 +151,8 @@ static void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs, return; ret = strncpy_from_user(dst, src, maxlen); + if (ret == maxlen) + dst[--ret] = '\0'; if (ret < 0) { /* Failed to fetch string */ ((u8 *)get_rloc_data(dest))[0] = '\0'; diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index f41079da38c5..d554c11e01ff 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -316,6 +316,7 @@ #define X86_FEATURE_VPCLMULQDQ (16*32+10) /* Carry-Less Multiplication Double Quadword */ #define X86_FEATURE_AVX512_VNNI (16*32+11) /* Vector Neural Network Instructions */ #define X86_FEATURE_AVX512_BITALG (16*32+12) /* Support for VPOPCNT[B,W] and VPSHUF-BITQMB instructions */ +#define X86_FEATURE_TME (16*32+13) /* Intel Total Memory Encryption */ #define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */ #define X86_FEATURE_LA57 (16*32+16) /* 5-level page tables */ #define X86_FEATURE_RDPID (16*32+22) /* RDPID instruction */ @@ -328,6 +329,7 @@ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */ #define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */ #define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */ +#define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */ #define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */ #define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */ #define X86_FEATURE_ARCH_CAPABILITIES (18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */ diff --git a/tools/include/tools/config.h b/tools/include/tools/config.h new file mode 100644 index 000000000000..08ade7df8132 --- /dev/null +++ b/tools/include/tools/config.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _TOOLS_CONFIG_H +#define _TOOLS_CONFIG_H + +/* Subset of include/linux/kconfig.h */ + +#define __ARG_PLACEHOLDER_1 0, +#define __take_second_arg(__ignored, val, ...) val + +/* + * Helper macros to use CONFIG_ options in C/CPP expressions. Note that + * these only work with boolean and tristate options. + */ + +/* + * Getting something that works in C and CPP for an arg that may or may + * not be defined is tricky. Here, if we have "#define CONFIG_BOOGER 1" + * we match on the placeholder define, insert the "0," for arg1 and generate + * the triplet (0, 1, 0). Then the last step cherry picks the 2nd arg (a one). + * When CONFIG_BOOGER is not defined, we generate a (... 1, 0) pair, and when + * the last step cherry picks the 2nd arg, we get a zero. + */ +#define __is_defined(x) ___is_defined(x) +#define ___is_defined(val) ____is_defined(__ARG_PLACEHOLDER_##val) +#define ____is_defined(arg1_or_junk) __take_second_arg(arg1_or_junk 1, 0) + +/* + * IS_BUILTIN(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'y', 0 + * otherwise. For boolean options, this is equivalent to + * IS_ENABLED(CONFIG_FOO). + */ +#define IS_BUILTIN(option) __is_defined(option) + +#endif /* _TOOLS_CONFIG_H */ diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index 536ee4febd74..7f5634ce8e88 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -318,6 +318,7 @@ typedef struct _drm_i915_sarea { #define DRM_I915_PERF_OPEN 0x36 #define DRM_I915_PERF_ADD_CONFIG 0x37 #define DRM_I915_PERF_REMOVE_CONFIG 0x38 +#define DRM_I915_QUERY 0x39 #define DRM_IOCTL_I915_INIT DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT, drm_i915_init_t) #define DRM_IOCTL_I915_FLUSH DRM_IO ( DRM_COMMAND_BASE + DRM_I915_FLUSH) @@ -375,6 +376,7 @@ typedef struct _drm_i915_sarea { #define DRM_IOCTL_I915_PERF_OPEN DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_OPEN, struct drm_i915_perf_open_param) #define DRM_IOCTL_I915_PERF_ADD_CONFIG DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_ADD_CONFIG, struct drm_i915_perf_oa_config) #define DRM_IOCTL_I915_PERF_REMOVE_CONFIG DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_REMOVE_CONFIG, __u64) +#define DRM_IOCTL_I915_QUERY DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_QUERY, struct drm_i915_query) /* Allow drivers to submit batchbuffers directly to hardware, relying * on the security mechanisms provided by hardware. @@ -1358,7 +1360,9 @@ struct drm_intel_overlay_attrs { * active on a given plane. */ -#define I915_SET_COLORKEY_NONE (1<<0) /* disable color key matching */ +#define I915_SET_COLORKEY_NONE (1<<0) /* Deprecated. Instead set + * flags==0 to disable colorkeying. + */ #define I915_SET_COLORKEY_DESTINATION (1<<1) #define I915_SET_COLORKEY_SOURCE (1<<2) struct drm_intel_sprite_colorkey { @@ -1604,15 +1608,115 @@ struct drm_i915_perf_oa_config { __u32 n_flex_regs; /* - * These fields are pointers to tuples of u32 values (register - * address, value). For example the expected length of the buffer - * pointed by mux_regs_ptr is (2 * sizeof(u32) * n_mux_regs). + * These fields are pointers to tuples of u32 values (register address, + * value). For example the expected length of the buffer pointed by + * mux_regs_ptr is (2 * sizeof(u32) * n_mux_regs). */ __u64 mux_regs_ptr; __u64 boolean_regs_ptr; __u64 flex_regs_ptr; }; +struct drm_i915_query_item { + __u64 query_id; +#define DRM_I915_QUERY_TOPOLOGY_INFO 1 + + /* + * When set to zero by userspace, this is filled with the size of the + * data to be written at the data_ptr pointer. The kernel sets this + * value to a negative value to signal an error on a particular query + * item. + */ + __s32 length; + + /* + * Unused for now. Must be cleared to zero. + */ + __u32 flags; + + /* + * Data will be written at the location pointed by data_ptr when the + * value of length matches the length of the data to be written by the + * kernel. + */ + __u64 data_ptr; +}; + +struct drm_i915_query { + __u32 num_items; + + /* + * Unused for now. Must be cleared to zero. + */ + __u32 flags; + + /* + * This points to an array of num_items drm_i915_query_item structures. + */ + __u64 items_ptr; +}; + +/* + * Data written by the kernel with query DRM_I915_QUERY_TOPOLOGY_INFO : + * + * data: contains the 3 pieces of information : + * + * - the slice mask with one bit per slice telling whether a slice is + * available. The availability of slice X can be queried with the following + * formula : + * + * (data[X / 8] >> (X % 8)) & 1 + * + * - the subslice mask for each slice with one bit per subslice telling + * whether a subslice is available. The availability of subslice Y in slice + * X can be queried with the following formula : + * + * (data[subslice_offset + + * X * subslice_stride + + * Y / 8] >> (Y % 8)) & 1 + * + * - the EU mask for each subslice in each slice with one bit per EU telling + * whether an EU is available. The availability of EU Z in subslice Y in + * slice X can be queried with the following formula : + * + * (data[eu_offset + + * (X * max_subslices + Y) * eu_stride + + * Z / 8] >> (Z % 8)) & 1 + */ +struct drm_i915_query_topology_info { + /* + * Unused for now. Must be cleared to zero. + */ + __u16 flags; + + __u16 max_slices; + __u16 max_subslices; + __u16 max_eus_per_subslice; + + /* + * Offset in data[] at which the subslice masks are stored. + */ + __u16 subslice_offset; + + /* + * Stride at which each of the subslice masks for each slice are + * stored. + */ + __u16 subslice_stride; + + /* + * Offset in data[] at which the EU masks are stored. + */ + __u16 eu_offset; + + /* + * Stride at which each of the EU masks for each subslice are stored. + */ + __u16 eu_stride; + + __u8 data[]; +}; + #if defined(__cplusplus) } #endif diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index e1a660e60849..917e36fde6d8 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -80,6 +80,7 @@ OPTIONS - comm: command (name) of the task which can be read via /proc/<pid>/comm - pid: command and tid of the task - dso: name of library or module executed at the time of sample + - dso_size: size of library or module executed at the time of sample - symbol: name of function executed at the time of sample - symbol_size: size of function executed at the time of sample - parent: name of function matched to the parent regex filter. Unmatched diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt index 5a7035c5c523..115db9e06ecd 100644 --- a/tools/perf/Documentation/perf-trace.txt +++ b/tools/perf/Documentation/perf-trace.txt @@ -117,6 +117,9 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs. --sched:: Accrue thread runtime and provide a summary at the end of the session. +--failure:: + Show only syscalls that failed, i.e. that returned < 0. + -i:: --input:: Process events from a given perf data file. diff --git a/tools/perf/Documentation/perf-version.txt b/tools/perf/Documentation/perf-version.txt new file mode 100644 index 000000000000..e207b7cfca26 --- /dev/null +++ b/tools/perf/Documentation/perf-version.txt @@ -0,0 +1,24 @@ +perf-version(1) +=============== + +NAME +---- +perf-version - display the version of perf binary + +SYNOPSIS +-------- +'perf version' [--build-options] + +DESCRIPTION +----------- +With no options given, the 'perf version' prints the perf version +on the standard output. + +If the option '--build-options' is given, then the status of +compiled-in libraries are printed on the standard output. + +OPTIONS +------- +--build-options:: + Prints the status of compiled-in libraries on the + standard output. diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 98ff73648b51..c7abd83a8e19 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -346,12 +346,16 @@ else ifneq ($(feature-dwarf_getlocations), 1) msg := $(warning Old libdw.h, finding variables at given 'perf probe' point will not work, install elfutils-devel/libdw-dev >= 0.157); else - CFLAGS += -DHAVE_DWARF_GETLOCATIONS + CFLAGS += -DHAVE_DWARF_GETLOCATIONS_SUPPORT endif # dwarf_getlocations endif # Dwarf support endif # libelf support endif # NO_LIBELF +ifeq ($(feature-glibc), 1) + CFLAGS += -DHAVE_GLIBC_SUPPORT +endif + ifdef NO_DWARF NO_LIBDW_DWARF_UNWIND := 1 endif @@ -635,6 +639,7 @@ else else LDFLAGS += $(PERL_EMBED_LDFLAGS) EXTLIBS += $(PERL_EMBED_LIBADD) + CFLAGS += -DHAVE_LIBPERL_SUPPORT $(call detected,CONFIG_LIBPERL) endif endif @@ -671,6 +676,7 @@ else LDFLAGS += $(PYTHON_EMBED_LDFLAGS) EXTLIBS += $(PYTHON_EMBED_LIBADD) LANG_BINDINGS += $(obj-perf)python/perf.so + CFLAGS += -DHAVE_LIBPYTHON_SUPPORT $(call detected,CONFIG_LIBPYTHON) endif endif diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index f7517e1b73f8..83e453de36f8 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -364,7 +364,8 @@ LIBS = -Wl,--whole-archive $(PERFLIBS) $(EXTRA_PERFLIBS) -Wl,--no-whole-archive ifeq ($(USE_CLANG), 1) CLANGLIBS_LIST = AST Basic CodeGen Driver Frontend Lex Tooling Edit Sema Analysis Parse Serialization - LIBCLANG = $(foreach l,$(CLANGLIBS_LIST),$(wildcard $(shell $(LLVM_CONFIG) --libdir)/libclang$(l).a)) + CLANGLIBS_NOEXT_LIST = $(foreach l,$(CLANGLIBS_LIST),$(shell $(LLVM_CONFIG) --libdir)/libclang$(l)) + LIBCLANG = $(foreach l,$(CLANGLIBS_NOEXT_LIST),$(wildcard $(l).a $(l).so)) LIBS += -Wl,--start-group $(LIBCLANG) -Wl,--end-group endif diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 87b95c9410b4..3ad17ee89403 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -112,6 +112,7 @@ struct trace { bool multiple_threads; bool summary; bool summary_only; + bool failure_only; bool show_comm; bool print_sample; bool show_tool_stats; @@ -1565,7 +1566,7 @@ static int trace__printf_interrupted_entry(struct trace *trace) struct thread_trace *ttrace; size_t printed; - if (trace->current == NULL) + if (trace->failure_only || trace->current == NULL) return 0; ttrace = thread__priv(trace->current); @@ -1638,7 +1639,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel, args, trace, thread); if (sc->is_exit) { - if (!(trace->duration_filter || trace->summary_only || trace->min_stack)) { + if (!(trace->duration_filter || trace->summary_only || trace->failure_only || trace->min_stack)) { trace__fprintf_entry_head(trace, thread, 0, false, ttrace->entry_time, trace->output); fprintf(trace->output, "%-70s)\n", ttrace->entry_str); } @@ -1742,7 +1743,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel, } } - if (trace->summary_only) + if (trace->summary_only || (ret >= 0 && trace->failure_only)) goto out; trace__fprintf_entry_head(trace, thread, duration, duration_calculated, ttrace->entry_time, trace->output); @@ -1961,7 +1962,7 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel, trace->output); } - fprintf(trace->output, ")\n"); + fprintf(trace->output, "\n"); if (callchain_ret > 0) trace__fprintf_callchain(trace, sample); @@ -3087,6 +3088,8 @@ int cmd_trace(int argc, const char **argv) OPT_INCR('v', "verbose", &verbose, "be more verbose"), OPT_BOOLEAN('T', "time", &trace.full_time, "Show full timestamp, not time relative to first start"), + OPT_BOOLEAN(0, "failure", &trace.failure_only, + "Show only syscalls that failed"), OPT_BOOLEAN('s', "summary", &trace.summary_only, "Show only syscall summary with statistics"), OPT_BOOLEAN('S', "with-summary", &trace.summary, diff --git a/tools/perf/builtin-version.c b/tools/perf/builtin-version.c index 37019c5d675f..2abe3910d6b6 100644 --- a/tools/perf/builtin-version.c +++ b/tools/perf/builtin-version.c @@ -1,11 +1,91 @@ // SPDX-License-Identifier: GPL-2.0 #include "builtin.h" #include "perf.h" +#include "color.h" #include <linux/compiler.h> +#include <tools/config.h> #include <stdio.h> +#include <string.h> +#include <subcmd/parse-options.h> -int cmd_version(int argc __maybe_unused, const char **argv __maybe_unused) +int version_verbose; + +struct version { + bool build_options; +}; + +static struct version version; + +static struct option version_options[] = { + OPT_BOOLEAN(0, "build-options", &version.build_options, + "display the build options"), +}; + +static const char * const version_usage[] = { + "perf version [<options>]", + NULL +}; + +static void on_off_print(const char *status) +{ + printf("[ "); + + if (!strcmp(status, "OFF")) + color_fprintf(stdout, PERF_COLOR_RED, "%-3s", status); + else + color_fprintf(stdout, PERF_COLOR_GREEN, "%-3s", status); + + printf(" ]"); +} + +static void status_print(const char *name, const char *macro, + const char *status) { + printf("%22s: ", name); + on_off_print(status); + printf(" # %s\n", macro); +} + +#define STATUS(__d, __m) \ +do { \ + if (IS_BUILTIN(__d)) \ + status_print(#__m, #__d, "on"); \ + else \ + status_print(#__m, #__d, "OFF"); \ +} while (0) + +static void library_status(void) +{ + STATUS(HAVE_DWARF_SUPPORT, dwarf); + STATUS(HAVE_DWARF_GETLOCATIONS_SUPPORT, dwarf_getlocations); + STATUS(HAVE_GLIBC_SUPPORT, glibc); + STATUS(HAVE_GTK2_SUPPORT, gtk2); + STATUS(HAVE_LIBAUDIT_SUPPORT, libaudit); + STATUS(HAVE_LIBBFD_SUPPORT, libbfd); + STATUS(HAVE_LIBELF_SUPPORT, libelf); + STATUS(HAVE_LIBNUMA_SUPPORT, libnuma); + STATUS(HAVE_LIBNUMA_SUPPORT, numa_num_possible_cpus); + STATUS(HAVE_LIBPERL_SUPPORT, libperl); + STATUS(HAVE_LIBPYTHON_SUPPORT, libpython); + STATUS(HAVE_SLANG_SUPPORT, libslang); + STATUS(HAVE_LIBCRYPTO_SUPPORT, libcrypto); + STATUS(HAVE_LIBUNWIND_SUPPORT, libunwind); + STATUS(HAVE_DWARF_SUPPORT, libdw-dwarf-unwind); + STATUS(HAVE_ZLIB_SUPPORT, zlib); + STATUS(HAVE_LZMA_SUPPORT, lzma); + STATUS(HAVE_AUXTRACE_SUPPORT, get_cpuid); + STATUS(HAVE_LIBBPF_SUPPORT, bpf); +} + +int cmd_version(int argc, const char **argv) +{ + argc = parse_options(argc, argv, version_options, version_usage, + PARSE_OPT_STOP_AT_NON_OPTION); + printf("perf version %s\n", perf_version_string); + + if (version.build_options || version_verbose == 1) + library_status(); + return 0; } diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 1b3fc8ec0fa2..1659029d03fc 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -190,6 +190,12 @@ static int handle_options(const char ***argv, int *argc, int *envchanged) break; } + if (!strcmp(cmd, "-vv")) { + (*argv)[0] = "version"; + version_verbose = 1; + break; + } + /* * Check remaining flags. */ diff --git a/tools/perf/perf.h b/tools/perf/perf.h index 8fec1abd0f1f..a1a97956136f 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -84,6 +84,7 @@ struct record_opts { struct option; extern const char * const *record_usage; extern struct option *record_options; +extern int version_verbose; int record__parse_freq(const struct option *opt, const char *str, int unset); #endif diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c index 9f6ce29b83b4..4f75561424ed 100644 --- a/tools/perf/ui/browser.c +++ b/tools/perf/ui/browser.c @@ -45,11 +45,16 @@ void ui_browser__set_percent_color(struct ui_browser *browser, ui_browser__set_color(browser, color); } -void ui_browser__gotorc(struct ui_browser *browser, int y, int x) +void ui_browser__gotorc_title(struct ui_browser *browser, int y, int x) { SLsmg_gotorc(browser->y + y, browser->x + x); } +void ui_browser__gotorc(struct ui_browser *browser, int y, int x) +{ + SLsmg_gotorc(browser->y + y + browser->extra_title_lines, browser->x + x); +} + void ui_browser__write_nstring(struct ui_browser *browser __maybe_unused, const char *msg, unsigned int width) { @@ -191,6 +196,7 @@ void ui_browser__refresh_dimensions(struct ui_browser *browser) { browser->width = SLtt_Screen_Cols - 1; browser->height = browser->rows = SLtt_Screen_Rows - 2; + browser->rows -= browser->extra_title_lines; browser->y = 1; browser->x = 0; } @@ -337,8 +343,8 @@ static int __ui_browser__refresh(struct ui_browser *browser) else width += 1; - SLsmg_fill_region(browser->y + row, browser->x, - browser->height - row, width, ' '); + SLsmg_fill_region(browser->y + row + browser->extra_title_lines, browser->x, + browser->rows - row, width, ' '); return 0; } diff --git a/tools/perf/ui/browser.h b/tools/perf/ui/browser.h index 70057178ee34..aa5932e1d62e 100644 --- a/tools/perf/ui/browser.h +++ b/tools/perf/ui/browser.h @@ -17,6 +17,7 @@ struct ui_browser { u64 index, top_idx; void *top, *entries; u16 y, x, width, height, rows, columns, horiz_scroll; + u8 extra_title_lines; int current_color; void *priv; const char *title; @@ -38,6 +39,7 @@ bool ui_browser__is_current_entry(struct ui_browser *browser, unsigned row); void ui_browser__refresh_dimensions(struct ui_browser *browser); void ui_browser__reset_index(struct ui_browser *browser); +void ui_browser__gotorc_title(struct ui_browser *browser, int y, int x); void ui_browser__gotorc(struct ui_browser *browser, int y, int x); void ui_browser__write_nstring(struct ui_browser *browser, const char *msg, unsigned int width); diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index c02fb437ac8e..12c099a87f8b 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -218,7 +218,7 @@ static unsigned int annotate_browser__refresh(struct ui_browser *browser) annotate_browser__draw_current_jump(browser); ui_browser__set_color(browser, HE_COLORSET_NORMAL); - __ui_browser__vline(browser, pcnt_width, 0, browser->height - 1); + __ui_browser__vline(browser, pcnt_width, 0, browser->rows - 1); return ret; } @@ -592,21 +592,40 @@ bool annotate_browser__continue_search_reverse(struct annotate_browser *browser, return __annotate_browser__search_reverse(browser); } +static int annotate_browser__show(struct ui_browser *browser, char *title, const char *help) +{ + struct map_symbol *ms = browser->priv; + struct symbol *sym = ms->sym; + char symbol_dso[SYM_TITLE_MAX_SIZE]; + + if (ui_browser__show(browser, title, help) < 0) + return -1; + + sym_title(sym, ms->map, symbol_dso, sizeof(symbol_dso)); + + ui_browser__gotorc_title(browser, 0, 0); + ui_browser__set_color(browser, HE_COLORSET_ROOT); + ui_browser__write_nstring(browser, symbol_dso, browser->width + 1); + return 0; +} + static int annotate_browser__run(struct annotate_browser *browser, struct perf_evsel *evsel, struct hist_browser_timer *hbt) { struct rb_node *nd = NULL; + struct hists *hists = evsel__hists(evsel); struct map_symbol *ms = browser->b.priv; struct symbol *sym = ms->sym; struct annotation *notes = symbol__annotation(ms->sym); const char *help = "Press 'h' for help on key bindings"; int delay_secs = hbt ? hbt->refresh : 0; + char title[256]; int key; - char title[SYM_TITLE_MAX_SIZE]; - sym_title(sym, ms->map, title, sizeof(title)); - if (ui_browser__show(&browser->b, title, help) < 0) + annotation__scnprintf_samples_period(notes, title, sizeof(title), evsel); + + if (annotate_browser__show(&browser->b, title, help) < 0) return -1; annotate_browser__calc_percent(browser, evsel); @@ -637,8 +656,11 @@ static int annotate_browser__run(struct annotate_browser *browser, if (hbt) hbt->timer(hbt->arg); - if (delay_secs != 0) + if (delay_secs != 0) { symbol__annotate_decay_histogram(sym, evsel->idx); + hists__scnprintf_title(hists, title, sizeof(title)); + annotate_browser__show(&browser->b, title, help); + } continue; case K_TAB: if (nd != NULL) { @@ -812,6 +834,7 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, .seek = ui_browser__list_head_seek, .write = annotate_browser__write, .filter = disasm_line__filter, + .extra_title_lines = 1, /* for hists__scnprintf_title() */ .priv = &ms, .use_navkeypressed = true, }, diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index 8b4e82548f8e..0eec06c105c6 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -32,8 +32,7 @@ extern void hist_browser__init_hpp(void); -static int perf_evsel_browser_title(struct hist_browser *browser, - char *bf, size_t size); +static int hists_browser__scnprintf_title(struct hist_browser *browser, char *bf, size_t size); static void hist_browser__update_nr_entries(struct hist_browser *hb); static struct rb_node *hists__filter_entries(struct rb_node *nd, @@ -62,6 +61,15 @@ static int hist_browser__get_folding(struct hist_browser *browser) return unfolded_rows; } +static void hist_browser__set_title_space(struct hist_browser *hb) +{ + struct ui_browser *browser = &hb->b; + struct hists *hists = hb->hists; + struct perf_hpp_list *hpp_list = hists->hpp_list; + + browser->extra_title_lines = hb->show_headers ? hpp_list->nr_header_lines : 0; +} + static u32 hist_browser__nr_entries(struct hist_browser *hb) { u32 nr_entries; @@ -82,10 +90,16 @@ static void hist_browser__update_rows(struct hist_browser *hb) struct ui_browser *browser = &hb->b; struct hists *hists = hb->hists; struct perf_hpp_list *hpp_list = hists->hpp_list; - u16 header_offset, index_row; + u16 index_row; - header_offset = hb->show_headers ? hpp_list->nr_header_lines : 0; - browser->rows = browser->height - header_offset; + if (!hb->show_headers) { + browser->rows += browser->extra_title_lines; + browser->extra_title_lines = 0; + return; + } + + browser->extra_title_lines = hpp_list->nr_header_lines; + browser->rows -= browser->extra_title_lines; /* * Verify if we were at the last line and that line isn't * visibe because we now show the header line(s). @@ -108,17 +122,6 @@ static void hist_browser__refresh_dimensions(struct ui_browser *browser) * changeset. */ ui_browser__refresh_dimensions(browser); - hist_browser__update_rows(hb); -} - -static void hist_browser__gotorc(struct hist_browser *browser, int row, int column) -{ - struct hists *hists = browser->hists; - struct perf_hpp_list *hpp_list = hists->hpp_list; - u16 header_offset; - - header_offset = browser->show_headers ? hpp_list->nr_header_lines : 0; - ui_browser__gotorc(&browser->b, row + header_offset, column); } static void hist_browser__reset(struct hist_browser *browser) @@ -656,9 +659,10 @@ int hist_browser__run(struct hist_browser *browser, const char *help, struct hist_entry *h = rb_entry(browser->b.top, struct hist_entry, rb_node); ui_helpline__pop(); - ui_helpline__fpush("%d: nr_ent=(%d,%d), rows=%d, idx=%d, fve: idx=%d, row_off=%d, nrows=%d", + ui_helpline__fpush("%d: nr_ent=(%d,%d), etl: %d, rows=%d, idx=%d, fve: idx=%d, row_off=%d, nrows=%d", seq++, browser->b.nr_entries, browser->hists->nr_entries, + browser->b.extra_title_lines, browser->b.rows, browser->b.index, browser->b.top_idx, @@ -733,7 +737,7 @@ static void hist_browser__show_callchain_entry(struct hist_browser *browser, } ui_browser__set_color(&browser->b, color); - hist_browser__gotorc(browser, row, 0); + ui_browser__gotorc(&browser->b, row, 0); ui_browser__write_nstring(&browser->b, " ", offset); ui_browser__printf(&browser->b, "%c", folded_sign); ui_browser__write_graph(&browser->b, show_annotated ? SLSMG_RARROW_CHAR : ' '); @@ -1249,7 +1253,7 @@ static int hist_browser__show_entry(struct hist_browser *browser, }; int column = 0; - hist_browser__gotorc(browser, row, 0); + ui_browser__gotorc(&browser->b, row, 0); hists__for_each_format(browser->hists, fmt) { char s[2048]; @@ -1358,7 +1362,7 @@ static int hist_browser__show_hierarchy_entry(struct hist_browser *browser, goto show_callchain; } - hist_browser__gotorc(browser, row, 0); + ui_browser__gotorc(&browser->b, row, 0); if (current_entry && browser->b.navkeypressed) ui_browser__set_color(&browser->b, HE_COLORSET_SELECTED); @@ -1507,7 +1511,7 @@ static int hist_browser__show_no_entry(struct hist_browser *browser, browser->selection = NULL; } - hist_browser__gotorc(browser, row, 0); + ui_browser__gotorc(&browser->b, row, 0); if (current_entry && browser->b.navkeypressed) ui_browser__set_color(&browser->b, HE_COLORSET_SELECTED); @@ -1713,7 +1717,7 @@ static void hists_browser__headers(struct hist_browser *browser) hists_browser__scnprintf_headers(browser, headers, sizeof(headers), line); - ui_browser__gotorc(&browser->b, line, 0); + ui_browser__gotorc_title(&browser->b, line, 0); ui_browser__set_color(&browser->b, HE_COLORSET_ROOT); ui_browser__write_nstring(&browser->b, headers, browser->b.width + 1); } @@ -1740,17 +1744,11 @@ static void ui_browser__hists_init_top(struct ui_browser *browser) static unsigned int hist_browser__refresh(struct ui_browser *browser) { unsigned row = 0; - u16 header_offset = 0; struct rb_node *nd; struct hist_browser *hb = container_of(browser, struct hist_browser, b); - struct hists *hists = hb->hists; - - if (hb->show_headers) { - struct perf_hpp_list *hpp_list = hists->hpp_list; + if (hb->show_headers) hist_browser__show_headers(hb); - header_offset = hpp_list->nr_header_lines; - } ui_browser__hists_init_top(browser); hb->he_selection = NULL; @@ -1788,7 +1786,7 @@ static unsigned int hist_browser__refresh(struct ui_browser *browser) break; } - return row + header_offset; + return row; } static struct rb_node *hists__filter_entries(struct rb_node *nd, @@ -2143,6 +2141,7 @@ void hist_browser__init(struct hist_browser *browser, browser->b.seek = ui_browser__hists_seek; browser->b.use_navkeypressed = true; browser->show_headers = symbol_conf.show_hist_headers; + hist_browser__set_title_space(browser); if (symbol_conf.report_hierarchy) { struct perf_hpp_list_node *fmt_node; @@ -2183,7 +2182,7 @@ perf_evsel_browser__new(struct perf_evsel *evsel, if (browser) { browser->hbt = hbt; browser->env = env; - browser->title = perf_evsel_browser_title; + browser->title = hists_browser__scnprintf_title; } return browser; } @@ -2209,84 +2208,11 @@ static inline bool is_report_browser(void *timer) return timer == NULL; } -static int perf_evsel_browser_title(struct hist_browser *browser, - char *bf, size_t size) +static int hists_browser__scnprintf_title(struct hist_browser *browser, char *bf, size_t size) { struct hist_browser_timer *hbt = browser->hbt; - struct hists *hists = browser->hists; - char unit; - int printed; - const struct dso *dso = hists->dso_filter; - const struct thread *thread = hists->thread_filter; - int socket_id = hists->socket_filter; - unsigned long nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE]; - u64 nr_events = hists->stats.total_period; - struct perf_evsel *evsel = hists_to_evsel(hists); - const char *ev_name = perf_evsel__name(evsel); - char buf[512], sample_freq_str[64] = ""; - size_t buflen = sizeof(buf); - char ref[30] = " show reference callgraph, "; - bool enable_ref = false; + int printed = __hists__scnprintf_title(browser->hists, bf, size, !is_report_browser(hbt)); - if (symbol_conf.filter_relative) { - nr_samples = hists->stats.nr_non_filtered_samples; - nr_events = hists->stats.total_non_filtered_period; - } - - if (perf_evsel__is_group_event(evsel)) { - struct perf_evsel *pos; - - perf_evsel__group_desc(evsel, buf, buflen); - ev_name = buf; - - for_each_group_member(pos, evsel) { - struct hists *pos_hists = evsel__hists(pos); - - if (symbol_conf.filter_relative) { - nr_samples += pos_hists->stats.nr_non_filtered_samples; - nr_events += pos_hists->stats.total_non_filtered_period; - } else { - nr_samples += pos_hists->stats.nr_events[PERF_RECORD_SAMPLE]; - nr_events += pos_hists->stats.total_period; - } - } - } - - if (symbol_conf.show_ref_callgraph && - strstr(ev_name, "call-graph=no")) - enable_ref = true; - - if (!is_report_browser(hbt)) - scnprintf(sample_freq_str, sizeof(sample_freq_str), " %d Hz,", evsel->attr.sample_freq); - - nr_samples = convert_unit(nr_samples, &unit); - printed = scnprintf(bf, size, - "Samples: %lu%c of event%s '%s',%s%sEvent count (approx.): %" PRIu64, - nr_samples, unit, evsel->nr_members > 1 ? "s" : "", - ev_name, sample_freq_str, enable_ref ? ref : " ", nr_events); - - - if (hists->uid_filter_str) - printed += snprintf(bf + printed, size - printed, - ", UID: %s", hists->uid_filter_str); - if (thread) { - if (hists__has(hists, thread)) { - printed += scnprintf(bf + printed, size - printed, - ", Thread: %s(%d)", - (thread->comm_set ? thread__comm_str(thread) : ""), - thread->tid); - } else { - printed += scnprintf(bf + printed, size - printed, - ", Thread: %s", - (thread->comm_set ? thread__comm_str(thread) : "")); - } - } - if (dso) - printed += scnprintf(bf + printed, size - printed, - ", DSO: %s", dso->short_name); - if (socket_id > -1) - printed += scnprintf(bf + printed, size - printed, - ", Processor Socket: %d", socket_id); if (!is_report_browser(hbt)) { struct perf_top *top = hbt->arg; diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 3a428d7c59b9..fbad8dfbb186 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -17,6 +17,7 @@ #include "config.h" #include "cache.h" #include "symbol.h" +#include "units.h" #include "debug.h" #include "annotate.h" #include "evsel.h" @@ -2324,7 +2325,7 @@ int symbol__tty_annotate2(struct symbol *sym, struct map *map, struct dso *dso = map->dso; struct rb_root source_line = RB_ROOT; struct annotation_options opts = annotation__default_options; - const char *ev_name = perf_evsel__name(evsel); + struct annotation *notes = symbol__annotation(sym); char buf[1024]; if (symbol__annotate2(sym, map, evsel, &opts, NULL) < 0) @@ -2336,12 +2337,8 @@ int symbol__tty_annotate2(struct symbol *sym, struct map *map, print_summary(&source_line, dso->long_name); } - if (perf_evsel__is_group_event(evsel)) { - perf_evsel__group_desc(evsel, buf, sizeof(buf)); - ev_name = buf; - } - - fprintf(stdout, "%s() %s\nEvent: %s\n\n", sym->name, dso->long_name, ev_name); + annotation__scnprintf_samples_period(notes, buf, sizeof(buf), evsel); + fprintf(stdout, "%s\n%s() %s\n", buf, sym->name, dso->long_name); symbol__annotate_fprintf2(sym, stdout); annotated_source__purge(symbol__annotation(sym)->src); @@ -2597,6 +2594,46 @@ out_free_offsets: return -1; } +int __annotation__scnprintf_samples_period(struct annotation *notes, + char *bf, size_t size, + struct perf_evsel *evsel, + bool show_freq) +{ + const char *ev_name = perf_evsel__name(evsel); + char buf[1024], ref[30] = " show reference callgraph, "; + char sample_freq_str[64] = ""; + unsigned long nr_samples = 0; + int nr_members = 1; + bool enable_ref = false; + u64 nr_events = 0; + char unit; + int i; + + if (perf_evsel__is_group_event(evsel)) { + perf_evsel__group_desc(evsel, buf, sizeof(buf)); + ev_name = buf; + nr_members = evsel->nr_members; + } + + for (i = 0; i < nr_members; i++) { + struct sym_hist *ah = annotation__histogram(notes, evsel->idx + i); + + nr_samples += ah->nr_samples; + nr_events += ah->period; + } + + if (symbol_conf.show_ref_callgraph && strstr(ev_name, "call-graph=no")) + enable_ref = true; + + if (show_freq) + scnprintf(sample_freq_str, sizeof(sample_freq_str), " %d Hz,", evsel->attr.sample_freq); + + nr_samples = convert_unit(nr_samples, &unit); + return scnprintf(bf, size, "Samples: %lu%c of event%s '%s',%s%sEvent count (approx.): %" PRIu64, + nr_samples, unit, evsel->nr_members > 1 ? "s" : "", + ev_name, sample_freq_str, enable_ref ? ref : " ", nr_events); +} + #define ANNOTATION__CFG(n) \ { .name = #n, .value = &annotation__default_options.n, } diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index ff7e3df31efa..db8d09bea07e 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -151,6 +151,18 @@ double annotation_line__max_percent(struct annotation_line *al, struct annotatio void annotation_line__write(struct annotation_line *al, struct annotation *notes, struct annotation_write_ops *ops); +int __annotation__scnprintf_samples_period(struct annotation *notes, + char *bf, size_t size, + struct perf_evsel *evsel, + bool show_freq); + +static inline int annotation__scnprintf_samples_period(struct annotation *notes, + char *bf, size_t size, + struct perf_evsel *evsel) +{ + return __annotation__scnprintf_samples_period(notes, bf, size, evsel, true); +} + int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw); size_t disasm__fprintf(struct list_head *head, FILE *fp); void symbol__calc_percent(struct symbol *sym, struct perf_evsel *evsel); diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index fb357a00dd86..857de69a5361 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -302,13 +302,27 @@ static int auxtrace_queues__split_buffer(struct auxtrace_queues *queues, return 0; } +static bool filter_cpu(struct perf_session *session, int cpu) +{ + unsigned long *cpu_bitmap = session->itrace_synth_opts->cpu_bitmap; + + return cpu_bitmap && cpu != -1 && !test_bit(cpu, cpu_bitmap); +} + static int auxtrace_queues__add_buffer(struct auxtrace_queues *queues, struct perf_session *session, unsigned int idx, struct auxtrace_buffer *buffer, struct auxtrace_buffer **buffer_ptr) { - int err; + int err = -ENOMEM; + + if (filter_cpu(session, buffer->cpu)) + return 0; + + buffer = memdup(buffer, sizeof(*buffer)); + if (!buffer) + return -ENOMEM; if (session->one_mmap) { buffer->data = buffer->data_offset - session->one_mmap_offset + @@ -316,31 +330,28 @@ static int auxtrace_queues__add_buffer(struct auxtrace_queues *queues, } else if (perf_data__is_pipe(session->data)) { buffer->data = auxtrace_copy_data(buffer->size, session); if (!buffer->data) - return -ENOMEM; + goto out_free; buffer->data_needs_freeing = true; } else if (BITS_PER_LONG == 32 && buffer->size > BUFFER_LIMIT_FOR_32_BIT) { err = auxtrace_queues__split_buffer(queues, idx, buffer); if (err) - return err; + goto out_free; } err = auxtrace_queues__queue_buffer(queues, idx, buffer); if (err) - return err; + goto out_free; /* FIXME: Doesn't work for split buffer */ if (buffer_ptr) *buffer_ptr = buffer; return 0; -} -static bool filter_cpu(struct perf_session *session, int cpu) -{ - unsigned long *cpu_bitmap = session->itrace_synth_opts->cpu_bitmap; - - return cpu_bitmap && cpu != -1 && !test_bit(cpu, cpu_bitmap); +out_free: + auxtrace_buffer__free(buffer); + return err; } int auxtrace_queues__add_event(struct auxtrace_queues *queues, @@ -348,36 +359,19 @@ int auxtrace_queues__add_event(struct auxtrace_queues *queues, union perf_event *event, off_t data_offset, struct auxtrace_buffer **buffer_ptr) { - struct auxtrace_buffer *buffer; - unsigned int idx; - int err; - - if (filter_cpu(session, event->auxtrace.cpu)) - return 0; - - buffer = zalloc(sizeof(struct auxtrace_buffer)); - if (!buffer) - return -ENOMEM; - - buffer->pid = -1; - buffer->tid = event->auxtrace.tid; - buffer->cpu = event->auxtrace.cpu; - buffer->data_offset = data_offset; - buffer->offset = event->auxtrace.offset; - buffer->reference = event->auxtrace.reference; - buffer->size = event->auxtrace.size; - idx = event->auxtrace.idx; - - err = auxtrace_queues__add_buffer(queues, session, idx, buffer, - buffer_ptr); - if (err) - goto out_err; - - return 0; + struct auxtrace_buffer buffer = { + .pid = -1, + .tid = event->auxtrace.tid, + .cpu = event->auxtrace.cpu, + .data_offset = data_offset, + .offset = event->auxtrace.offset, + .reference = event->auxtrace.reference, + .size = event->auxtrace.size, + }; + unsigned int idx = event->auxtrace.idx; -out_err: - auxtrace_buffer__free(buffer); - return err; + return auxtrace_queues__add_buffer(queues, session, idx, &buffer, + buffer_ptr); } static int auxtrace_queues__add_indexed_event(struct auxtrace_queues *queues, diff --git a/tools/perf/util/c++/clang-test.cpp b/tools/perf/util/c++/clang-test.cpp index a4014d786676..7b042a5ebc68 100644 --- a/tools/perf/util/c++/clang-test.cpp +++ b/tools/perf/util/c++/clang-test.cpp @@ -41,7 +41,7 @@ int test__clang_to_IR(void) if (!M) return -1; for (llvm::Function& F : *M) - if (F.getName() == "bpf_func__SyS_epoll_wait") + if (F.getName() == "bpf_func__SyS_epoll_pwait") return 0; return -1; } diff --git a/tools/perf/util/c++/clang.cpp b/tools/perf/util/c++/clang.cpp index 1bfc946e37dc..bf31ceab33bd 100644 --- a/tools/perf/util/c++/clang.cpp +++ b/tools/perf/util/c++/clang.cpp @@ -9,6 +9,7 @@ * Copyright (C) 2016 Huawei Inc. */ +#include "clang/Basic/Version.h" #include "clang/CodeGen/CodeGenAction.h" #include "clang/Frontend/CompilerInvocation.h" #include "clang/Frontend/CompilerInstance.h" @@ -58,7 +59,8 @@ createCompilerInvocation(llvm::opt::ArgStringList CFlags, StringRef& Path, FrontendOptions& Opts = CI->getFrontendOpts(); Opts.Inputs.clear(); - Opts.Inputs.emplace_back(Path, IK_C); + Opts.Inputs.emplace_back(Path, + FrontendOptions::getInputKindForExtension("c")); return CI; } @@ -71,10 +73,17 @@ getModuleFromSource(llvm::opt::ArgStringList CFlags, Clang.setVirtualFileSystem(&*VFS); +#if CLANG_VERSION_MAJOR < 4 IntrusiveRefCntPtr<CompilerInvocation> CI = createCompilerInvocation(std::move(CFlags), Path, Clang.getDiagnostics()); Clang.setInvocation(&*CI); +#else + std::shared_ptr<CompilerInvocation> CI( + createCompilerInvocation(std::move(CFlags), Path, + Clang.getDiagnostics())); + Clang.setInvocation(CI); +#endif std::unique_ptr<CodeGenAction> Act(new EmitLLVMOnlyAction(&*LLVMCtx)); if (!Clang.ExecuteAction(*Act)) diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c index f5acda13dcfa..7eb7de5aee44 100644 --- a/tools/perf/util/dwarf-aux.c +++ b/tools/perf/util/dwarf-aux.c @@ -979,7 +979,7 @@ int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf) return ret < 0 ? ret : strbuf_addf(buf, "\t%s", dwarf_diename(vr_die)); } -#ifdef HAVE_DWARF_GETLOCATIONS +#ifdef HAVE_DWARF_GETLOCATIONS_SUPPORT /** * die_get_var_innermost_scope - Get innermost scope range of given variable DIE * @sp_die: a subprogram DIE diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 7d968892ee39..4d602fba40b2 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -6,6 +6,7 @@ #include "session.h" #include "namespaces.h" #include "sort.h" +#include "units.h" #include "evlist.h" #include "evsel.h" #include "annotate.h" @@ -14,6 +15,7 @@ #include "ui/progress.h" #include <errno.h> #include <math.h> +#include <inttypes.h> #include <sys/param.h> static bool hists__filter_entry_by_dso(struct hists *hists, @@ -2454,6 +2456,85 @@ u64 hists__total_period(struct hists *hists) hists->stats.total_period; } +int __hists__scnprintf_title(struct hists *hists, char *bf, size_t size, bool show_freq) +{ + char unit; + int printed; + const struct dso *dso = hists->dso_filter; + const struct thread *thread = hists->thread_filter; + int socket_id = hists->socket_filter; + unsigned long nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE]; + u64 nr_events = hists->stats.total_period; + struct perf_evsel *evsel = hists_to_evsel(hists); + const char *ev_name = perf_evsel__name(evsel); + char buf[512], sample_freq_str[64] = ""; + size_t buflen = sizeof(buf); + char ref[30] = " show reference callgraph, "; + bool enable_ref = false; + + if (symbol_conf.filter_relative) { + nr_samples = hists->stats.nr_non_filtered_samples; + nr_events = hists->stats.total_non_filtered_period; + } + + if (perf_evsel__is_group_event(evsel)) { + struct perf_evsel *pos; + + perf_evsel__group_desc(evsel, buf, buflen); + ev_name = buf; + + for_each_group_member(pos, evsel) { + struct hists *pos_hists = evsel__hists(pos); + + if (symbol_conf.filter_relative) { + nr_samples += pos_hists->stats.nr_non_filtered_samples; + nr_events += pos_hists->stats.total_non_filtered_period; + } else { + nr_samples += pos_hists->stats.nr_events[PERF_RECORD_SAMPLE]; + nr_events += pos_hists->stats.total_period; + } + } + } + + if (symbol_conf.show_ref_callgraph && + strstr(ev_name, "call-graph=no")) + enable_ref = true; + + if (show_freq) + scnprintf(sample_freq_str, sizeof(sample_freq_str), " %d Hz,", evsel->attr.sample_freq); + + nr_samples = convert_unit(nr_samples, &unit); + printed = scnprintf(bf, size, + "Samples: %lu%c of event%s '%s',%s%sEvent count (approx.): %" PRIu64, + nr_samples, unit, evsel->nr_members > 1 ? "s" : "", + ev_name, sample_freq_str, enable_ref ? ref : " ", nr_events); + + + if (hists->uid_filter_str) + printed += snprintf(bf + printed, size - printed, + ", UID: %s", hists->uid_filter_str); + if (thread) { + if (hists__has(hists, thread)) { + printed += scnprintf(bf + printed, size - printed, + ", Thread: %s(%d)", + (thread->comm_set ? thread__comm_str(thread) : ""), + thread->tid); + } else { + printed += scnprintf(bf + printed, size - printed, + ", Thread: %s", + (thread->comm_set ? thread__comm_str(thread) : "")); + } + } + if (dso) + printed += scnprintf(bf + printed, size - printed, + ", DSO: %s", dso->short_name); + if (socket_id > -1) + printed += scnprintf(bf + printed, size - printed, + ", Processor Socket: %d", socket_id); + + return printed; +} + int parse_filter_percentage(const struct option *opt __maybe_unused, const char *arg, int unset __maybe_unused) { diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index e869cad4d89f..fbabfd8a215d 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -61,6 +61,7 @@ enum hist_column { HISTC_SRCLINE_TO, HISTC_TRACE, HISTC_SYM_SIZE, + HISTC_DSO_SIZE, HISTC_NR_COLS, /* Last entry */ }; @@ -503,5 +504,11 @@ int __hpp__slsmg_color_printf(struct perf_hpp *hpp, const char *fmt, ...); int __hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp, struct perf_hpp_list *hpp_list); int hists__fprintf_headers(struct hists *hists, FILE *fp); +int __hists__scnprintf_title(struct hists *hists, char *bf, size_t size, bool show_freq); + +static inline int hists__scnprintf_title(struct hists *hists, char *bf, size_t size) +{ + return __hists__scnprintf_title(hists, bf, size, true); +} #endif /* __PERF_HIST_H */ diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index edeb7291c8e1..0e9bbe01b0ab 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -103,6 +103,10 @@ static inline u64 identity__map_ip(struct map *map __maybe_unused, u64 ip) return ip; } +static inline size_t map__size(const struct map *map) +{ + return map->end - map->start; +} /* rip/ip <-> addr suitable for passing to `objdump --start-address=` */ u64 map__rip_2objdump(struct map *map, u64 rip); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index c71ced7db152..f4a7a437ee87 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1591,7 +1591,7 @@ static void perf_session__warn_about_errors(const struct perf_session *session) drop_rate = (double)stats->total_lost_samples / (double) (stats->nr_events[PERF_RECORD_SAMPLE] + stats->total_lost_samples); if (drop_rate > 0.05) { - ui__warning("Processed %" PRIu64 " samples and lost %3.2f%% samples!\n\n", + ui__warning("Processed %" PRIu64 " samples and lost %3.2f%%!\n\n", stats->nr_events[PERF_RECORD_SAMPLE] + stats->total_lost_samples, drop_rate * 100.0); } diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index e8514f651865..26a68dfd8a4f 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -1545,6 +1545,46 @@ struct sort_entry sort_sym_size = { .se_width_idx = HISTC_SYM_SIZE, }; +/* --sort dso_size */ + +static int64_t _sort__dso_size_cmp(struct map *map_l, struct map *map_r) +{ + int64_t size_l = map_l != NULL ? map__size(map_l) : 0; + int64_t size_r = map_r != NULL ? map__size(map_r) : 0; + + return size_l < size_r ? -1 : + size_l == size_r ? 0 : 1; +} + +static int64_t +sort__dso_size_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return _sort__dso_size_cmp(right->ms.map, left->ms.map); +} + +static int _hist_entry__dso_size_snprintf(struct map *map, char *bf, + size_t bf_size, unsigned int width) +{ + if (map && map->dso) + return repsep_snprintf(bf, bf_size, "%*d", width, + map__size(map)); + + return repsep_snprintf(bf, bf_size, "%*s", width, "unknown"); +} + +static int hist_entry__dso_size_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + return _hist_entry__dso_size_snprintf(he->ms.map, bf, size, width); +} + +struct sort_entry sort_dso_size = { + .se_header = "DSO size", + .se_cmp = sort__dso_size_cmp, + .se_snprintf = hist_entry__dso_size_snprintf, + .se_width_idx = HISTC_DSO_SIZE, +}; + struct sort_dimension { const char *name; @@ -1569,6 +1609,7 @@ static struct sort_dimension common_sort_dimensions[] = { DIM(SORT_TRANSACTION, "transaction", sort_transaction), DIM(SORT_TRACE, "trace", sort_trace), DIM(SORT_SYM_SIZE, "symbol_size", sort_sym_size), + DIM(SORT_DSO_SIZE, "dso_size", sort_dso_size), DIM(SORT_CGROUP_ID, "cgroup_id", sort_cgroup_id), }; diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index f5901c10a563..035b62e2c60b 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -220,6 +220,7 @@ enum sort_type { SORT_TRANSACTION, SORT_TRACE, SORT_SYM_SIZE, + SORT_DSO_SIZE, SORT_CGROUP_ID, /* branch stack specific sort keys */ diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 9496365da3d7..c9626c206208 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -11,8 +11,7 @@ #include <stdlib.h> #include <stdarg.h> #include <linux/compiler.h> -#include <linux/types.h> -#include "namespaces.h" +#include <sys/types.h> /* General helper functions */ void usage(const char *err) __noreturn; @@ -26,6 +25,7 @@ static inline void *zalloc(size_t size) #define zfree(ptr) ({ free(*ptr); *ptr = NULL; }) struct dirent; +struct nsinfo; struct strlist; int mkdir_p(char *path, mode_t mode); |