diff options
263 files changed, 10506 insertions, 4265 deletions
diff --git a/tools/Makefile b/tools/Makefile index 68defd7ecf5d..7e42f7b8bfa7 100644 --- a/tools/Makefile +++ b/tools/Makefile @@ -10,6 +10,7 @@ help: @echo 'Possible targets:' @echo '' @echo ' acpi - ACPI tools' + @echo ' bpf - misc BPF tools' @echo ' cgroup - cgroup tools' @echo ' cpupower - a tool for all things x86 CPU power' @echo ' debugging - tools for debugging' @@ -23,12 +24,11 @@ help: @echo ' kvm_stat - top-like utility for displaying kvm statistics' @echo ' leds - LEDs tools' @echo ' liblockdep - user-space wrapper for kernel locking-validator' - @echo ' bpf - misc BPF tools' + @echo ' objtool - an ELF object analysis tool' @echo ' pci - PCI tools' @echo ' perf - Linux performance measurement and analysis tool' @echo ' selftests - various kernel selftests' @echo ' spi - spi tools' - @echo ' objtool - an ELF object analysis tool' @echo ' tmon - thermal monitoring and tuning tool' @echo ' turbostat - Intel CPU idle stats and freq reporting tool' @echo ' usb - USB testing tools' diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 998c2cc08363..e880f2408e29 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -281,6 +281,8 @@ #define X86_FEATURE_CQM_OCCUP_LLC (11*32+ 1) /* LLC occupancy monitoring */ #define X86_FEATURE_CQM_MBM_TOTAL (11*32+ 2) /* LLC Total MBM monitoring */ #define X86_FEATURE_CQM_MBM_LOCAL (11*32+ 3) /* LLC Local MBM monitoring */ +#define X86_FEATURE_FENCE_SWAPGS_USER (11*32+ 4) /* "" LFENCE in user entry SWAPGS path */ +#define X86_FEATURE_FENCE_SWAPGS_KERNEL (11*32+ 5) /* "" LFENCE in kernel entry SWAPGS path */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ @@ -394,5 +396,6 @@ #define X86_BUG_L1TF X86_BUG(18) /* CPU is affected by L1 Terminal Fault */ #define X86_BUG_MDS X86_BUG(19) /* CPU is affected by Microarchitectural data sampling */ #define X86_BUG_MSBDS_ONLY X86_BUG(20) /* CPU is only affected by the MSDBS variant of BUG_MDS */ +#define X86_BUG_SWAPGS X86_BUG(21) /* CPU is affected by speculation through SWAPGS */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature index 86b793dffbc4..8a19753cc26a 100644 --- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -42,6 +42,7 @@ FEATURE_TESTS_BASIC := \ gtk2-infobar \ libaudit \ libbfd \ + libcap \ libelf \ libelf-getphdrnum \ libelf-gelf_getnote \ @@ -110,6 +111,7 @@ FEATURE_DISPLAY ?= \ gtk2 \ libaudit \ libbfd \ + libcap \ libelf \ libnuma \ numa_num_possible_cpus \ diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index 0658b8cd0e53..8499385365c0 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -20,6 +20,7 @@ FILES= \ test-libbfd-liberty.bin \ test-libbfd-liberty-z.bin \ test-cplus-demangle.bin \ + test-libcap.bin \ test-libelf.bin \ test-libelf-getphdrnum.bin \ test-libelf-gelf_getnote.bin \ @@ -105,6 +106,9 @@ $(OUTPUT)test-fortify-source.bin: $(OUTPUT)test-bionic.bin: $(BUILD) +$(OUTPUT)test-libcap.bin: + $(BUILD) -lcap + $(OUTPUT)test-libelf.bin: $(BUILD) -lelf diff --git a/tools/build/feature/test-libcap.c b/tools/build/feature/test-libcap.c new file mode 100644 index 000000000000..d2a2e152195f --- /dev/null +++ b/tools/build/feature/test-libcap.c @@ -0,0 +1,20 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <sys/capability.h> +#include <linux/capability.h> + +int main(void) +{ + cap_flag_value_t val; + cap_t caps = cap_get_proc(); + + if (!caps) + return 1; + + if (cap_get_flag(caps, CAP_SYS_ADMIN, CAP_EFFECTIVE, &val) != 0) + return 1; + + if (cap_free(caps) != 0) + return 1; + + return 0; +} diff --git a/tools/include/linux/bitops.h b/tools/include/linux/bitops.h index 0b0ef3abc966..140c8362f113 100644 --- a/tools/include/linux/bitops.h +++ b/tools/include/linux/bitops.h @@ -3,6 +3,7 @@ #define _TOOLS_LINUX_BITOPS_H_ #include <asm/types.h> +#include <limits.h> #ifndef __WORDSIZE #define __WORDSIZE (__SIZEOF_LONG__ * 8) #endif diff --git a/tools/include/linux/bits.h b/tools/include/linux/bits.h index 2b7b532c1d51..669d69441a62 100644 --- a/tools/include/linux/bits.h +++ b/tools/include/linux/bits.h @@ -1,13 +1,15 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_BITS_H #define __LINUX_BITS_H + +#include <linux/const.h> #include <asm/bitsperlong.h> -#define BIT(nr) (1UL << (nr)) -#define BIT_ULL(nr) (1ULL << (nr)) -#define BIT_MASK(nr) (1UL << ((nr) % BITS_PER_LONG)) +#define BIT(nr) (UL(1) << (nr)) +#define BIT_ULL(nr) (ULL(1) << (nr)) +#define BIT_MASK(nr) (UL(1) << ((nr) % BITS_PER_LONG)) #define BIT_WORD(nr) ((nr) / BITS_PER_LONG) -#define BIT_ULL_MASK(nr) (1ULL << ((nr) % BITS_PER_LONG_LONG)) +#define BIT_ULL_MASK(nr) (ULL(1) << ((nr) % BITS_PER_LONG_LONG)) #define BIT_ULL_WORD(nr) ((nr) / BITS_PER_LONG_LONG) #define BITS_PER_BYTE 8 @@ -17,10 +19,11 @@ * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000. */ #define GENMASK(h, l) \ - (((~0UL) - (1UL << (l)) + 1) & (~0UL >> (BITS_PER_LONG - 1 - (h)))) + (((~UL(0)) - (UL(1) << (l)) + 1) & \ + (~UL(0) >> (BITS_PER_LONG - 1 - (h)))) #define GENMASK_ULL(h, l) \ - (((~0ULL) - (1ULL << (l)) + 1) & \ - (~0ULL >> (BITS_PER_LONG_LONG - 1 - (h)))) + (((~ULL(0)) - (ULL(1) << (l)) + 1) & \ + (~ULL(0) >> (BITS_PER_LONG_LONG - 1 - (h)))) #endif /* __LINUX_BITS_H */ diff --git a/tools/include/linux/const.h b/tools/include/linux/const.h new file mode 100644 index 000000000000..7b55a55f5911 --- /dev/null +++ b/tools/include/linux/const.h @@ -0,0 +1,9 @@ +#ifndef _LINUX_CONST_H +#define _LINUX_CONST_H + +#include <uapi/linux/const.h> + +#define UL(x) (_UL(x)) +#define ULL(x) (_ULL(x)) + +#endif /* _LINUX_CONST_H */ diff --git a/tools/include/linux/ring_buffer.h b/tools/include/linux/ring_buffer.h index 9a083ae60473..6c02617377c2 100644 --- a/tools/include/linux/ring_buffer.h +++ b/tools/include/linux/ring_buffer.h @@ -2,6 +2,7 @@ #define _TOOLS_LINUX_RING_BUFFER_H_ #include <asm/barrier.h> +#include <linux/perf_event.h> /* * Contract with kernel for walking the perf ring buffer from diff --git a/tools/include/uapi/asm/bitsperlong.h b/tools/include/uapi/asm/bitsperlong.h index 57aaeaf8e192..edba4d93e9e6 100644 --- a/tools/include/uapi/asm/bitsperlong.h +++ b/tools/include/uapi/asm/bitsperlong.h @@ -1,22 +1,22 @@ /* SPDX-License-Identifier: GPL-2.0 */ #if defined(__i386__) || defined(__x86_64__) -#include "../../arch/x86/include/uapi/asm/bitsperlong.h" +#include "../../../arch/x86/include/uapi/asm/bitsperlong.h" #elif defined(__aarch64__) -#include "../../arch/arm64/include/uapi/asm/bitsperlong.h" +#include "../../../arch/arm64/include/uapi/asm/bitsperlong.h" #elif defined(__powerpc__) -#include "../../arch/powerpc/include/uapi/asm/bitsperlong.h" +#include "../../../arch/powerpc/include/uapi/asm/bitsperlong.h" #elif defined(__s390__) -#include "../../arch/s390/include/uapi/asm/bitsperlong.h" +#include "../../../arch/s390/include/uapi/asm/bitsperlong.h" #elif defined(__sparc__) -#include "../../arch/sparc/include/uapi/asm/bitsperlong.h" +#include "../../../arch/sparc/include/uapi/asm/bitsperlong.h" #elif defined(__mips__) -#include "../../arch/mips/include/uapi/asm/bitsperlong.h" +#include "../../../arch/mips/include/uapi/asm/bitsperlong.h" #elif defined(__ia64__) -#include "../../arch/ia64/include/uapi/asm/bitsperlong.h" +#include "../../../arch/ia64/include/uapi/asm/bitsperlong.h" #elif defined(__riscv) -#include "../../arch/riscv/include/uapi/asm/bitsperlong.h" +#include "../../../arch/riscv/include/uapi/asm/bitsperlong.h" #elif defined(__alpha__) -#include "../../arch/alpha/include/uapi/asm/bitsperlong.h" +#include "../../../arch/alpha/include/uapi/asm/bitsperlong.h" #else #include <asm-generic/bitsperlong.h> #endif diff --git a/tools/include/uapi/linux/const.h b/tools/include/uapi/linux/const.h new file mode 100644 index 000000000000..5ed721ad5b19 --- /dev/null +++ b/tools/include/uapi/linux/const.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* const.h: Macros for dealing with constants. */ + +#ifndef _UAPI_LINUX_CONST_H +#define _UAPI_LINUX_CONST_H + +/* Some constant macros are used in both assembler and + * C code. Therefore we cannot annotate them always with + * 'UL' and other type specifiers unilaterally. We + * use the following macros to deal with this. + * + * Similarly, _AT() will cast an expression with a type in C, but + * leave it unchanged in asm. + */ + +#ifdef __ASSEMBLY__ +#define _AC(X,Y) X +#define _AT(T,X) X +#else +#define __AC(X,Y) (X##Y) +#define _AC(X,Y) __AC(X,Y) +#define _AT(T,X) ((T)(X)) +#endif + +#define _UL(x) (_AC(x, UL)) +#define _ULL(x) (_AC(x, ULL)) + +#define _BITUL(x) (_UL(1) << (x)) +#define _BITULL(x) (_ULL(1) << (x)) + +#endif /* _UAPI_LINUX_CONST_H */ diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index 7198ddd0c6b1..bb7b271397a6 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -374,7 +374,8 @@ struct perf_event_attr { namespaces : 1, /* include namespaces data */ ksymbol : 1, /* include ksymbol events */ bpf_event : 1, /* include bpf events */ - __reserved_1 : 33; + aux_output : 1, /* generate AUX records instead of events */ + __reserved_1 : 32; union { __u32 wakeup_events; /* wakeup every n events */ diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile index 3292c290654f..8352d53dcb5a 100644 --- a/tools/lib/traceevent/Makefile +++ b/tools/lib/traceevent/Makefile @@ -266,8 +266,8 @@ endef define do_generate_dynamic_list_file symbol_type=`$(NM) -u -D $1 | awk 'NF>1 {print $$1}' | \ - xargs echo "U W w" | tr ' ' '\n' | sort -u | xargs echo`;\ - if [ "$$symbol_type" = "U W w" ];then \ + xargs echo "U w W" | tr 'w ' 'W\n' | sort -u | xargs echo`;\ + if [ "$$symbol_type" = "U W" ];then \ (echo '{'; \ $(NM) -u -D $1 | awk 'NF>1 {print "\t"$$2";"}' | sort -u;\ echo '};'; \ diff --git a/tools/perf/Documentation/intel-pt.txt b/tools/perf/Documentation/intel-pt.txt index 50c5b60101bd..e0d9e7dd4f17 100644 --- a/tools/perf/Documentation/intel-pt.txt +++ b/tools/perf/Documentation/intel-pt.txt @@ -919,3 +919,18 @@ amended to take the number of elements as a parameter. Note there is currently no advantage to using Intel PT instead of LBR, but that may change in the future if greater use is made of the data. + + +PEBS via Intel PT +================= + +Some hardware has the feature to redirect PEBS records to the Intel PT trace. +Recording is selected by using the aux-output config term e.g. + + perf record -c 10000 -e '{intel_pt/branch=0/,cycles/aux-output/ppp}' uname + +Note that currently, software only supports redirecting at most one PEBS event. + +To display PEBS events from the Intel PT trace, use the itrace 'o' option e.g. + + perf script --itrace=oe diff --git a/tools/perf/Documentation/itrace.txt b/tools/perf/Documentation/itrace.txt index c2182cbabde3..82ff7dad40c2 100644 --- a/tools/perf/Documentation/itrace.txt +++ b/tools/perf/Documentation/itrace.txt @@ -5,6 +5,8 @@ x synthesize transactions events w synthesize ptwrite events p synthesize power events + o synthesize other events recorded due to the use + of aux-output (refer to perf record) e synthesize error events d create a debug log g synthesize a call chain (use with i or x) diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt index e4aa268d2e38..c599623a1f3d 100644 --- a/tools/perf/Documentation/perf-config.txt +++ b/tools/perf/Documentation/perf-config.txt @@ -40,6 +40,10 @@ The '$HOME/.perfconfig' file is used to store a per-user configuration. The file '$(sysconfdir)/perfconfig' can be used to store a system-wide default configuration. +One an disable reading config files by setting the PERF_CONFIG environment +variable to /dev/null, or provide an alternate config file by setting that +variable. + When reading or writing, the values are read from the system and user configuration files by default, and options '--system' and '--user' can be used to tell the command to read from or write to only that location. diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 15e0fa87241b..c6f9f31b6039 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -60,6 +60,8 @@ OPTIONS - 'name' : User defined event name. Single quotes (') may be used to escape symbols in the name from parsing by shell and tool like this: name=\'CPU_CLK_UNHALTED.THREAD:cmask=0x1\'. + - 'aux-output': Generate AUX records instead of events. This requires + that an AUX area event is also provided. See the linkperf:perf-list[1] man page for more parameters. @@ -422,9 +424,14 @@ CLOCK_BOOTTIME, CLOCK_REALTIME and CLOCK_TAI. -S:: --snapshot:: Select AUX area tracing Snapshot Mode. This option is valid only with an -AUX area tracing event. Optionally the number of bytes to capture per -snapshot can be specified. In Snapshot Mode, trace data is captured only when -signal SIGUSR2 is received. +AUX area tracing event. Optionally, certain snapshot capturing parameters +can be specified in a string that follows this option: + 'e': take one last snapshot on exit; guarantees that there is at least one + snapshot in the output file; + <size>: if the PMU supports this, specify the desired snapshot size. + +In Snapshot Mode trace data is captured only when signal SIGUSR2 is received +and on exit if the above 'e' option is given. --proc-map-timeout:: When processing pre-existing threads /proc/XXX/mmap, it may take a long time, diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index 987261d158d4..7315f155803f 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -438,6 +438,23 @@ OPTIONS perf report --time 0%-10%,30%-40% +--switch-on EVENT_NAME:: + Only consider events after this event is found. + + This may be interesting to measure a workload only after some initialization + phase is over, i.e. insert a perf probe at that point and then using this + option with that probe. + +--switch-off EVENT_NAME:: + Stop considering events after this event is found. + +--show-on-off-events:: + Show the --switch-on/off events too. This has no effect in 'perf report' now + but probably we'll make the default not to show the switch-on/off events + on the --group mode and if there is only one event besides the off/on ones, + go straight to the histogram browser, just like 'perf report' with no events + explicitely specified does. + --itrace:: Options for decoding instruction tracing data. The options are: diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index caaab28f8400..2599b057e47b 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -417,6 +417,15 @@ include::itrace.txt[] For itrace only show specified functions and their callees for itrace. Multiple functions can be separated by comma. +--switch-on EVENT_NAME:: + Only consider events after this event is found. + +--switch-off EVENT_NAME:: + Stop considering events after this event is found. + +--show-on-off-events:: + Show the --switch-on/off events too. + SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-script-perl[1], diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt index cfea87c6f38e..5596129a71cf 100644 --- a/tools/perf/Documentation/perf-top.txt +++ b/tools/perf/Documentation/perf-top.txt @@ -266,6 +266,44 @@ Default is to monitor all CPUS. Record events of type PERF_RECORD_NAMESPACES and display it with the 'cgroup_id' sort key. +--switch-on EVENT_NAME:: + Only consider events after this event is found. + + E.g.: + + Find out where broadcast packets are handled + + perf probe -L icmp_rcv + + Insert a probe there: + + perf probe icmp_rcv:59 + + Start perf top and ask it to only consider the cycles events when a + broadcast packet arrives This will show a menu with two entries and + will start counting when a broadcast packet arrives: + + perf top -e cycles,probe:icmp_rcv --switch-on=probe:icmp_rcv + + Alternatively one can ask for --group and then two overhead columns + will appear, the first for cycles and the second for the switch-on event. + + perf top --group -e cycles,probe:icmp_rcv --switch-on=probe:icmp_rcv + + This may be interesting to measure a workload only after some initialization + phase is over, i.e. insert a perf probe at that point and use the above + examples replacing probe:icmp_rcv with the just-after-init probe. + +--switch-off EVENT_NAME:: + Stop considering events after this event is found. + +--show-on-off-events:: + Show the --switch-on/off events too. This has no effect in 'perf top' now + but probably we'll make the default not to show the switch-on/off events + on the --group mode and if there is only one event besides the off/on ones, + go straight to the histogram browser, just like 'perf top' with no events + explicitely specified does. + INTERACTIVE PROMPTING KEYS -------------------------- diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt index fc6e43262c41..25b74fdb36fa 100644 --- a/tools/perf/Documentation/perf-trace.txt +++ b/tools/perf/Documentation/perf-trace.txt @@ -176,6 +176,15 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs. only at exit time or when a syscall is interrupted, i.e. in those cases this option is equivalent to the number of lines printed. +--switch-on EVENT_NAME:: + Only consider events after this event is found. + +--switch-off EVENT_NAME:: + Stop considering events after this event is found. + +--show-on-off-events:: + Show the --switch-on/off events too. + --max-stack:: Set the stack depth limit when parsing the callchain, anything beyond the specified depth will be ignored. Note that at this point diff --git a/tools/perf/Documentation/perf.data-file-format.txt b/tools/perf/Documentation/perf.data-file-format.txt index d030c87ed9f5..b0152e1095c5 100644 --- a/tools/perf/Documentation/perf.data-file-format.txt +++ b/tools/perf/Documentation/perf.data-file-format.txt @@ -298,16 +298,21 @@ Physical memory map and its node assignments. The format of data in MEM_TOPOLOGY is as follows: - 0 - version | for future changes - 8 - block_size_bytes | /sys/devices/system/memory/block_size_bytes - 16 - count | number of nodes - -For each node we store map of physical indexes: - - 32 - node id | node index - 40 - size | size of bitmap - 48 - bitmap | bitmap of memory indexes that belongs to node - | /sys/devices/system/node/node<NODE>/memory<INDEX> + u64 version; // Currently 1 + u64 block_size_bytes; // /sys/devices/system/memory/block_size_bytes + u64 count; // number of nodes + +struct memory_node { + u64 node_id; // node index + u64 size; // size of bitmap + struct bitmap { + /* size of bitmap again */ + u64 bitmapsize; + /* bitmap of memory indexes that belongs to node */ + /* /sys/devices/system/node/node<NODE>/memory<INDEX> */ + u64 entries[(bitmapsize/64)+1]; + } +}[count]; The MEM_TOPOLOGY can be displayed with following command: diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 89ac5a1f1550..bf8caa7d17f6 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -277,11 +277,12 @@ ifeq ($(DEBUG),0) endif endif +INC_FLAGS += -I$(src-perf)/lib/include INC_FLAGS += -I$(src-perf)/util/include INC_FLAGS += -I$(src-perf)/arch/$(SRCARCH)/include -INC_FLAGS += -I$(srctree)/tools/include/uapi INC_FLAGS += -I$(srctree)/tools/include/ INC_FLAGS += -I$(srctree)/tools/arch/$(SRCARCH)/include/uapi +INC_FLAGS += -I$(srctree)/tools/include/uapi INC_FLAGS += -I$(srctree)/tools/arch/$(SRCARCH)/include/ INC_FLAGS += -I$(srctree)/tools/arch/$(SRCARCH)/ @@ -823,6 +824,17 @@ ifndef NO_LIBZSTD endif endif +ifndef NO_LIBCAP + ifeq ($(feature-libcap), 1) + CFLAGS += -DHAVE_LIBCAP_SUPPORT + EXTLIBS += -lcap + $(call detected,CONFIG_LIBCAP) + else + msg := $(warning No libcap found, disables capability support, please install libcap-devel/libcap-dev); + NO_LIBCAP := 1 + endif +endif + ifndef NO_BACKTRACE ifeq ($(feature-backtrace), 1) CFLAGS += -DHAVE_BACKTRACE_SUPPORT diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 0fffd2bb6cd9..f9807d8c005b 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -88,6 +88,8 @@ include ../scripts/utilities.mak # # Define NO_LIBBPF if you do not want BPF support # +# Define NO_LIBCAP if you do not want process capabilities considered by perf +# # Define NO_SDT if you do not want to define SDT event in perf tools, # note that it doesn't disable SDT scanning support. # @@ -224,6 +226,7 @@ LIB_DIR = $(srctree)/tools/lib/api/ TRACE_EVENT_DIR = $(srctree)/tools/lib/traceevent/ BPF_DIR = $(srctree)/tools/lib/bpf/ SUBCMD_DIR = $(srctree)/tools/lib/subcmd/ +LIBPERF_DIR = $(srctree)/tools/perf/lib/ # Set FEATURE_TESTS to 'all' so all possible feature checkers are executed. # Without this setting the output feature dump file misses some features, for @@ -272,6 +275,7 @@ ifneq ($(OUTPUT),) TE_PATH=$(OUTPUT) BPF_PATH=$(OUTPUT) SUBCMD_PATH=$(OUTPUT) + LIBPERF_PATH=$(OUTPUT) ifneq ($(subdir),) API_PATH=$(OUTPUT)/../lib/api/ else @@ -282,6 +286,7 @@ else API_PATH=$(LIB_DIR) BPF_PATH=$(BPF_DIR) SUBCMD_PATH=$(SUBCMD_DIR) + LIBPERF_PATH=$(LIBPERF_DIR) endif LIBTRACEEVENT = $(TE_PATH)libtraceevent.a @@ -303,6 +308,9 @@ LIBBPF = $(BPF_PATH)libbpf.a LIBSUBCMD = $(SUBCMD_PATH)libsubcmd.a +LIBPERF = $(LIBPERF_PATH)libperf.a +export LIBPERF + # python extension build directories PYTHON_EXTBUILD := $(OUTPUT)python_ext_build/ PYTHON_EXTBUILD_LIB := $(PYTHON_EXTBUILD)lib/ @@ -348,9 +356,7 @@ endif export PERL_PATH -LIBPERF_A=$(OUTPUT)libperf.a - -PERFLIBS = $(LIBAPI) $(LIBTRACEEVENT) $(LIBSUBCMD) +PERFLIBS = $(LIBAPI) $(LIBTRACEEVENT) $(LIBSUBCMD) $(LIBPERF) ifndef NO_LIBBPF PERFLIBS += $(LIBBPF) endif @@ -583,8 +589,6 @@ JEVENTS_IN := $(OUTPUT)pmu-events/jevents-in.o PMU_EVENTS_IN := $(OUTPUT)pmu-events/pmu-events-in.o -LIBPERF_IN := $(OUTPUT)libperf-in.o - export JEVENTS build := -f $(srctree)/tools/build/Makefile.build dir=. obj @@ -601,12 +605,9 @@ $(JEVENTS): $(JEVENTS_IN) $(PMU_EVENTS_IN): $(JEVENTS) FORCE $(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=pmu-events obj=pmu-events -$(LIBPERF_IN): prepare FORCE - $(Q)$(MAKE) $(build)=libperf - -$(OUTPUT)perf: $(PERFLIBS) $(PERF_IN) $(PMU_EVENTS_IN) $(LIBPERF_IN) $(LIBTRACEEVENT_DYNAMIC_LIST) +$(OUTPUT)perf: $(PERFLIBS) $(PERF_IN) $(PMU_EVENTS_IN) $(LIBTRACEEVENT_DYNAMIC_LIST) $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $(LIBTRACEEVENT_DYNAMIC_LIST_LDFLAGS) \ - $(PERF_IN) $(PMU_EVENTS_IN) $(LIBPERF_IN) $(LIBS) -o $@ + $(PERF_IN) $(PMU_EVENTS_IN) $(LIBS) -o $@ $(GTK_IN): FORCE $(Q)$(MAKE) $(build)=gtk @@ -727,9 +728,6 @@ endif $(patsubst perf-%,%.o,$(PROGRAMS)): $(wildcard */*.h) -$(LIBPERF_A): $(LIBPERF_IN) - $(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $(LIBPERF_IN) $(LIB_OBJS) - LIBTRACEEVENT_FLAGS += plugin_dir=$(plugindir_SQ) 'EXTRA_CFLAGS=$(EXTRA_CFLAGS)' 'LDFLAGS=$(LDFLAGS)' $(LIBTRACEEVENT): FORCE @@ -762,6 +760,13 @@ $(LIBBPF)-clean: $(call QUIET_CLEAN, libbpf) $(Q)$(MAKE) -C $(BPF_DIR) O=$(OUTPUT) clean >/dev/null +$(LIBPERF): FORCE + $(Q)$(MAKE) -C $(LIBPERF_DIR) O=$(OUTPUT) $(OUTPUT)libperf.a + +$(LIBPERF)-clean: + $(call QUIET_CLEAN, libperf) + $(Q)$(MAKE) -C $(LIBPERF_DIR) O=$(OUTPUT) clean >/dev/null + $(LIBSUBCMD): FORCE $(Q)$(MAKE) -C $(SUBCMD_DIR) O=$(OUTPUT) $(OUTPUT)libsubcmd.a @@ -948,7 +953,7 @@ config-clean: python-clean: $(python-clean) -clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean config-clean fixdep-clean python-clean +clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean $(LIBPERF)-clean config-clean fixdep-clean python-clean $(call QUIET_CLEAN, core-objs) $(RM) $(LIBPERF_A) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(LANG_BINDINGS) $(Q)find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete $(Q)$(RM) $(OUTPUT).config-detected diff --git a/tools/perf/arch/arm/util/auxtrace.c b/tools/perf/arch/arm/util/auxtrace.c index 02014740a1aa..41b78f74599f 100644 --- a/tools/perf/arch/arm/util/auxtrace.c +++ b/tools/perf/arch/arm/util/auxtrace.c @@ -50,10 +50,10 @@ static struct perf_pmu **find_all_arm_spe_pmus(int *nr_spes, int *err) } struct auxtrace_record -*auxtrace_record__init(struct perf_evlist *evlist, int *err) +*auxtrace_record__init(struct evlist *evlist, int *err) { struct perf_pmu *cs_etm_pmu; - struct perf_evsel *evsel; + struct evsel *evsel; bool found_etm = false; bool found_spe = false; static struct perf_pmu **arm_spe_pmus = NULL; @@ -70,14 +70,14 @@ struct auxtrace_record evlist__for_each_entry(evlist, evsel) { if (cs_etm_pmu && - evsel->attr.type == cs_etm_pmu->type) + evsel->core.attr.type == cs_etm_pmu->type) found_etm = true; if (!nr_spes) continue; for (i = 0; i < nr_spes; i++) { - if (evsel->attr.type == arm_spe_pmus[i]->type) { + if (evsel->core.attr.type == arm_spe_pmus[i]->type) { found_spe = true; break; } diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index 4208974c24f8..c73da3245b67 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -32,7 +32,7 @@ struct cs_etm_recording { struct auxtrace_record itr; struct perf_pmu *cs_etm_pmu; - struct perf_evlist *evlist; + struct evlist *evlist; int wrapped_cnt; bool *wrapped; bool snapshot_mode; @@ -55,7 +55,7 @@ static const char *metadata_etmv4_ro[CS_ETMV4_PRIV_MAX] = { static bool cs_etm_is_etmv4(struct auxtrace_record *itr, int cpu); static int cs_etm_set_context_id(struct auxtrace_record *itr, - struct perf_evsel *evsel, int cpu) + struct evsel *evsel, int cpu) { struct cs_etm_recording *ptr; struct perf_pmu *cs_etm_pmu; @@ -95,7 +95,7 @@ static int cs_etm_set_context_id(struct auxtrace_record *itr, } /* All good, let the kernel know */ - evsel->attr.config |= (1 << ETM_OPT_CTXTID); + evsel->core.attr.config |= (1 << ETM_OPT_CTXTID); err = 0; out: @@ -104,7 +104,7 @@ out: } static int cs_etm_set_timestamp(struct auxtrace_record *itr, - struct perf_evsel *evsel, int cpu) + struct evsel *evsel, int cpu) { struct cs_etm_recording *ptr; struct perf_pmu *cs_etm_pmu; @@ -144,7 +144,7 @@ static int cs_etm_set_timestamp(struct auxtrace_record *itr, } /* All good, let the kernel know */ - evsel->attr.config |= (1 << ETM_OPT_TS); + evsel->core.attr.config |= (1 << ETM_OPT_TS); err = 0; out: @@ -152,11 +152,11 @@ out: } static int cs_etm_set_option(struct auxtrace_record *itr, - struct perf_evsel *evsel, u32 option) + struct evsel *evsel, u32 option) { int i, err = -EINVAL; - struct cpu_map *event_cpus = evsel->evlist->cpus; - struct cpu_map *online_cpus = cpu_map__new(NULL); + struct perf_cpu_map *event_cpus = evsel->evlist->core.cpus; + struct perf_cpu_map *online_cpus = perf_cpu_map__new(NULL); /* Set option of each CPU we have */ for (i = 0; i < cpu__max_cpu(); i++) { @@ -181,7 +181,7 @@ static int cs_etm_set_option(struct auxtrace_record *itr, err = 0; out: - cpu_map__put(online_cpus); + perf_cpu_map__put(online_cpus); return err; } @@ -208,14 +208,14 @@ static int cs_etm_parse_snapshot_options(struct auxtrace_record *itr, } static int cs_etm_set_sink_attr(struct perf_pmu *pmu, - struct perf_evsel *evsel) + struct evsel *evsel) { char msg[BUFSIZ], path[PATH_MAX], *sink; struct perf_evsel_config_term *term; int ret = -EINVAL; u32 hash; - if (evsel->attr.config2 & GENMASK(31, 0)) + if (evsel->core.attr.config2 & GENMASK(31, 0)) return 0; list_for_each_entry(term, &evsel->config_terms, list) { @@ -233,7 +233,7 @@ static int cs_etm_set_sink_attr(struct perf_pmu *pmu, return ret; } - evsel->attr.config2 |= hash; + evsel->core.attr.config2 |= hash; return 0; } @@ -245,15 +245,15 @@ static int cs_etm_set_sink_attr(struct perf_pmu *pmu, } static int cs_etm_recording_options(struct auxtrace_record *itr, - struct perf_evlist *evlist, + struct evlist *evlist, struct record_opts *opts) { int ret; struct cs_etm_recording *ptr = container_of(itr, struct cs_etm_recording, itr); struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu; - struct perf_evsel *evsel, *cs_etm_evsel = NULL; - struct cpu_map *cpus = evlist->cpus; + struct evsel *evsel, *cs_etm_evsel = NULL; + struct perf_cpu_map *cpus = evlist->core.cpus; bool privileged = (geteuid() == 0 || perf_event_paranoid() < 0); int err = 0; @@ -264,14 +264,14 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, opts->record_switch_events = true; evlist__for_each_entry(evlist, evsel) { - if (evsel->attr.type == cs_etm_pmu->type) { + if (evsel->core.attr.type == cs_etm_pmu->type) { if (cs_etm_evsel) { pr_err("There may be only one %s event\n", CORESIGHT_ETM_PMU_NAME); return -EINVAL; } - evsel->attr.freq = 0; - evsel->attr.sample_period = 1; + evsel->core.attr.freq = 0; + evsel->core.attr.sample_period = 1; cs_etm_evsel = evsel; opts->full_auxtrace = true; } @@ -396,7 +396,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, * AUX event. We also need the contextID in order to be notified * when a context switch happened. */ - if (!cpu_map__empty(cpus)) { + if (!perf_cpu_map__empty(cpus)) { perf_evsel__set_sample_bit(cs_etm_evsel, CPU); err = cs_etm_set_option(itr, cs_etm_evsel, @@ -407,7 +407,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, /* Add dummy event to keep tracking */ if (opts->full_auxtrace) { - struct perf_evsel *tracking_evsel; + struct evsel *tracking_evsel; err = parse_events(evlist, "dummy:u", NULL); if (err) @@ -416,11 +416,11 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, tracking_evsel = perf_evlist__last(evlist); perf_evlist__set_tracking_event(evlist, tracking_evsel); - tracking_evsel->attr.freq = 0; - tracking_evsel->attr.sample_period = 1; + tracking_evsel->core.attr.freq = 0; + tracking_evsel->core.attr.sample_period = 1; /* In per-cpu case, always need the time of mmap events etc */ - if (!cpu_map__empty(cpus)) + if (!perf_cpu_map__empty(cpus)) perf_evsel__set_sample_bit(tracking_evsel, TIME); } @@ -434,11 +434,11 @@ static u64 cs_etm_get_config(struct auxtrace_record *itr) struct cs_etm_recording *ptr = container_of(itr, struct cs_etm_recording, itr); struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu; - struct perf_evlist *evlist = ptr->evlist; - struct perf_evsel *evsel; + struct evlist *evlist = ptr->evlist; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { - if (evsel->attr.type == cs_etm_pmu->type) { + if (evsel->core.attr.type == cs_etm_pmu->type) { /* * Variable perf_event_attr::config is assigned to * ETMv3/PTM. The bit fields have been made to match @@ -447,7 +447,7 @@ static u64 cs_etm_get_config(struct auxtrace_record *itr) * drivers/hwtracing/coresight/coresight-perf.c for * details. */ - config = evsel->attr.config; + config = evsel->core.attr.config; break; } } @@ -485,15 +485,15 @@ static u64 cs_etmv4_get_config(struct auxtrace_record *itr) static size_t cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { int i; int etmv3 = 0, etmv4 = 0; - struct cpu_map *event_cpus = evlist->cpus; - struct cpu_map *online_cpus = cpu_map__new(NULL); + struct perf_cpu_map *event_cpus = evlist->core.cpus; + struct perf_cpu_map *online_cpus = perf_cpu_map__new(NULL); /* cpu map is not empty, we have specific CPUs to work with */ - if (!cpu_map__empty(event_cpus)) { + if (!perf_cpu_map__empty(event_cpus)) { for (i = 0; i < cpu__max_cpu(); i++) { if (!cpu_map__has(event_cpus, i) || !cpu_map__has(online_cpus, i)) @@ -517,7 +517,7 @@ cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused, } } - cpu_map__put(online_cpus); + perf_cpu_map__put(online_cpus); return (CS_ETM_HEADER_SIZE + (etmv4 * CS_ETMV4_PRIV_SIZE) + @@ -635,9 +635,9 @@ static int cs_etm_info_fill(struct auxtrace_record *itr, int i; u32 offset; u64 nr_cpu, type; - struct cpu_map *cpu_map; - struct cpu_map *event_cpus = session->evlist->cpus; - struct cpu_map *online_cpus = cpu_map__new(NULL); + struct perf_cpu_map *cpu_map; + struct perf_cpu_map *event_cpus = session->evlist->core.cpus; + struct perf_cpu_map *online_cpus = perf_cpu_map__new(NULL); struct cs_etm_recording *ptr = container_of(itr, struct cs_etm_recording, itr); struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu; @@ -649,11 +649,11 @@ static int cs_etm_info_fill(struct auxtrace_record *itr, return -EINVAL; /* If the cpu_map is empty all online CPUs are involved */ - if (cpu_map__empty(event_cpus)) { + if (perf_cpu_map__empty(event_cpus)) { cpu_map = online_cpus; } else { /* Make sure all specified CPUs are online */ - for (i = 0; i < cpu_map__nr(event_cpus); i++) { + for (i = 0; i < perf_cpu_map__nr(event_cpus); i++) { if (cpu_map__has(event_cpus, i) && !cpu_map__has(online_cpus, i)) return -EINVAL; @@ -662,7 +662,7 @@ static int cs_etm_info_fill(struct auxtrace_record *itr, cpu_map = event_cpus; } - nr_cpu = cpu_map__nr(cpu_map); + nr_cpu = perf_cpu_map__nr(cpu_map); /* Get PMU type as dynamically assigned by the core */ type = cs_etm_pmu->type; @@ -679,7 +679,7 @@ static int cs_etm_info_fill(struct auxtrace_record *itr, if (cpu_map__has(cpu_map, i)) cs_etm_get_metadata(i, &offset, itr, info); - cpu_map__put(online_cpus); + perf_cpu_map__put(online_cpus); return 0; } @@ -817,11 +817,11 @@ static int cs_etm_snapshot_start(struct auxtrace_record *itr) { struct cs_etm_recording *ptr = container_of(itr, struct cs_etm_recording, itr); - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(ptr->evlist, evsel) { - if (evsel->attr.type == ptr->cs_etm_pmu->type) - return perf_evsel__disable(evsel); + if (evsel->core.attr.type == ptr->cs_etm_pmu->type) + return evsel__disable(evsel); } return -EINVAL; } @@ -830,11 +830,11 @@ static int cs_etm_snapshot_finish(struct auxtrace_record *itr) { struct cs_etm_recording *ptr = container_of(itr, struct cs_etm_recording, itr); - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(ptr->evlist, evsel) { - if (evsel->attr.type == ptr->cs_etm_pmu->type) - return perf_evsel__enable(evsel); + if (evsel->core.attr.type == ptr->cs_etm_pmu->type) + return evsel__enable(evsel); } return -EINVAL; } @@ -858,10 +858,10 @@ static int cs_etm_read_finish(struct auxtrace_record *itr, int idx) { struct cs_etm_recording *ptr = container_of(itr, struct cs_etm_recording, itr); - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(ptr->evlist, evsel) { - if (evsel->attr.type == ptr->cs_etm_pmu->type) + if (evsel->core.attr.type == ptr->cs_etm_pmu->type) return perf_evlist__enable_event_idx(ptr->evlist, evsel, idx); } diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c index 2c009aa74633..00915b8fd05b 100644 --- a/tools/perf/arch/arm64/util/arm-spe.c +++ b/tools/perf/arch/arm64/util/arm-spe.c @@ -27,12 +27,12 @@ struct arm_spe_recording { struct auxtrace_record itr; struct perf_pmu *arm_spe_pmu; - struct perf_evlist *evlist; + struct evlist *evlist; }; static size_t arm_spe_info_priv_size(struct auxtrace_record *itr __maybe_unused, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { return ARM_SPE_AUXTRACE_PRIV_SIZE; } @@ -59,27 +59,27 @@ static int arm_spe_info_fill(struct auxtrace_record *itr, } static int arm_spe_recording_options(struct auxtrace_record *itr, - struct perf_evlist *evlist, + struct evlist *evlist, struct record_opts *opts) { struct arm_spe_recording *sper = container_of(itr, struct arm_spe_recording, itr); struct perf_pmu *arm_spe_pmu = sper->arm_spe_pmu; - struct perf_evsel *evsel, *arm_spe_evsel = NULL; + struct evsel *evsel, *arm_spe_evsel = NULL; bool privileged = geteuid() == 0 || perf_event_paranoid() < 0; - struct perf_evsel *tracking_evsel; + struct evsel *tracking_evsel; int err; sper->evlist = evlist; evlist__for_each_entry(evlist, evsel) { - if (evsel->attr.type == arm_spe_pmu->type) { + if (evsel->core.attr.type == arm_spe_pmu->type) { if (arm_spe_evsel) { pr_err("There may be only one " ARM_SPE_PMU_NAME "x event\n"); return -EINVAL; } - evsel->attr.freq = 0; - evsel->attr.sample_period = 1; + evsel->core.attr.freq = 0; + evsel->core.attr.sample_period = 1; arm_spe_evsel = evsel; opts->full_auxtrace = true; } @@ -130,8 +130,8 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, tracking_evsel = perf_evlist__last(evlist); perf_evlist__set_tracking_event(evlist, tracking_evsel); - tracking_evsel->attr.freq = 0; - tracking_evsel->attr.sample_period = 1; + tracking_evsel->core.attr.freq = 0; + tracking_evsel->core.attr.sample_period = 1; perf_evsel__set_sample_bit(tracking_evsel, TIME); perf_evsel__set_sample_bit(tracking_evsel, CPU); perf_evsel__reset_sample_bit(tracking_evsel, BRANCH_STACK); @@ -160,10 +160,10 @@ static int arm_spe_read_finish(struct auxtrace_record *itr, int idx) { struct arm_spe_recording *sper = container_of(itr, struct arm_spe_recording, itr); - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(sper->evlist, evsel) { - if (evsel->attr.type == sper->arm_spe_pmu->type) + if (evsel->core.attr.type == sper->arm_spe_pmu->type) return perf_evlist__enable_event_idx(sper->evlist, evsel, idx); } diff --git a/tools/perf/arch/arm64/util/header.c b/tools/perf/arch/arm64/util/header.c index 534cd2507d83..e41defaaa2e6 100644 --- a/tools/perf/arch/arm64/util/header.c +++ b/tools/perf/arch/arm64/util/header.c @@ -1,6 +1,7 @@ #include <stdio.h> #include <stdlib.h> #include <api/fs/fs.h> +#include "debug.h" #include "header.h" #define MIDR "/regs/identification/midr_el1" @@ -16,7 +17,7 @@ char *get_cpuid_str(struct perf_pmu *pmu) const char *sysfs = sysfs__mountpoint(); int cpu; u64 midr = 0; - struct cpu_map *cpus; + struct perf_cpu_map *cpus; FILE *file; if (!sysfs || !pmu || !pmu->cpus) @@ -27,7 +28,7 @@ char *get_cpuid_str(struct perf_pmu *pmu) return NULL; /* read midr from list of cpus mapped to this pmu */ - cpus = cpu_map__get(pmu->cpus); + cpus = perf_cpu_map__get(pmu->cpus); for (cpu = 0; cpu < cpus->nr; cpu++) { scnprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d"MIDR, sysfs, cpus->map[cpu]); @@ -60,6 +61,6 @@ char *get_cpuid_str(struct perf_pmu *pmu) buf = NULL; } - cpu_map__put(cpus); + perf_cpu_map__put(cpus); return buf; } diff --git a/tools/perf/arch/powerpc/util/kvm-stat.c b/tools/perf/arch/powerpc/util/kvm-stat.c index f9db341c47b6..f0dbf7b075c8 100644 --- a/tools/perf/arch/powerpc/util/kvm-stat.c +++ b/tools/perf/arch/powerpc/util/kvm-stat.c @@ -32,7 +32,7 @@ const char *ppc_book3s_hv_kvm_tp[] = { const char *kvm_events_tp[NR_TPS + 1]; const char *kvm_exit_reason; -static void hcall_event_get_key(struct perf_evsel *evsel, +static void hcall_event_get_key(struct evsel *evsel, struct perf_sample *sample, struct event_key *key) { @@ -55,14 +55,14 @@ static const char *get_hcall_exit_reason(u64 exit_code) return "UNKNOWN"; } -static bool hcall_event_end(struct perf_evsel *evsel, +static bool hcall_event_end(struct evsel *evsel, struct perf_sample *sample __maybe_unused, struct event_key *key __maybe_unused) { return (!strcmp(evsel->name, kvm_events_tp[3])); } -static bool hcall_event_begin(struct perf_evsel *evsel, +static bool hcall_event_begin(struct evsel *evsel, struct perf_sample *sample, struct event_key *key) { if (!strcmp(evsel->name, kvm_events_tp[2])) { @@ -106,7 +106,7 @@ const char * const kvm_skip_events[] = { }; -static int is_tracepoint_available(const char *str, struct perf_evlist *evlist) +static int is_tracepoint_available(const char *str, struct evlist *evlist) { struct parse_events_error err; int ret; @@ -119,7 +119,7 @@ static int is_tracepoint_available(const char *str, struct perf_evlist *evlist) } static int ppc__setup_book3s_hv(struct perf_kvm_stat *kvm, - struct perf_evlist *evlist) + struct evlist *evlist) { const char **events_ptr; int i, nr_tp = 0, err = -1; @@ -146,7 +146,7 @@ static int ppc__setup_book3s_hv(struct perf_kvm_stat *kvm, /* Wrapper to setup kvm tracepoints */ static int ppc__setup_kvm_tp(struct perf_kvm_stat *kvm) { - struct perf_evlist *evlist = perf_evlist__new(); + struct evlist *evlist = evlist__new(); if (evlist == NULL) return -ENOMEM; diff --git a/tools/perf/arch/s390/util/auxtrace.c b/tools/perf/arch/s390/util/auxtrace.c index 0fe1be93f375..cab46f517b83 100644 --- a/tools/perf/arch/s390/util/auxtrace.c +++ b/tools/perf/arch/s390/util/auxtrace.c @@ -20,7 +20,7 @@ static void cpumsf_free(struct auxtrace_record *itr) } static size_t cpumsf_info_priv_size(struct auxtrace_record *itr __maybe_unused, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { return 0; } @@ -43,7 +43,7 @@ cpumsf_reference(struct auxtrace_record *itr __maybe_unused) static int cpumsf_recording_options(struct auxtrace_record *ar __maybe_unused, - struct perf_evlist *evlist __maybe_unused, + struct evlist *evlist __maybe_unused, struct record_opts *opts) { unsigned int factor = 1; @@ -82,19 +82,19 @@ cpumsf_parse_snapshot_options(struct auxtrace_record *itr __maybe_unused, * auxtrace_record__init is called when perf record * check if the event really need auxtrace */ -struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist, +struct auxtrace_record *auxtrace_record__init(struct evlist *evlist, int *err) { struct auxtrace_record *aux; - struct perf_evsel *pos; + struct evsel *pos; int diagnose = 0; *err = 0; - if (evlist->nr_entries == 0) + if (evlist->core.nr_entries == 0) return NULL; evlist__for_each_entry(evlist, pos) { - if (pos->attr.config == PERF_EVENT_CPUM_SF_DIAG) { + if (pos->core.attr.config == PERF_EVENT_CPUM_SF_DIAG) { diagnose = 1; break; } diff --git a/tools/perf/arch/s390/util/kvm-stat.c b/tools/perf/arch/s390/util/kvm-stat.c index f852f2a77e0a..0fd4e9f49ed0 100644 --- a/tools/perf/arch/s390/util/kvm-stat.c +++ b/tools/perf/arch/s390/util/kvm-stat.c @@ -7,6 +7,7 @@ */ #include <errno.h> +#include <string.h> #include "../../util/kvm-stat.h" #include "../../util/evsel.h" #include <asm/sie.h> @@ -23,7 +24,7 @@ const char *kvm_exit_reason = "icptcode"; const char *kvm_entry_trace = "kvm:kvm_s390_sie_enter"; const char *kvm_exit_trace = "kvm:kvm_s390_sie_exit"; -static void event_icpt_insn_get_key(struct perf_evsel *evsel, +static void event_icpt_insn_get_key(struct evsel *evsel, struct perf_sample *sample, struct event_key *key) { @@ -34,7 +35,7 @@ static void event_icpt_insn_get_key(struct perf_evsel *evsel, key->exit_reasons = sie_icpt_insn_codes; } -static void event_sigp_get_key(struct perf_evsel *evsel, +static void event_sigp_get_key(struct evsel *evsel, struct perf_sample *sample, struct event_key *key) { @@ -42,7 +43,7 @@ static void event_sigp_get_key(struct perf_evsel *evsel, key->exit_reasons = sie_sigp_order_codes; } -static void event_diag_get_key(struct perf_evsel *evsel, +static void event_diag_get_key(struct evsel *evsel, struct perf_sample *sample, struct event_key *key) { @@ -50,7 +51,7 @@ static void event_diag_get_key(struct perf_evsel *evsel, key->exit_reasons = sie_diagnose_codes; } -static void event_icpt_prog_get_key(struct perf_evsel *evsel, +static void event_icpt_prog_get_key(struct evsel *evsel, struct perf_sample *sample, struct event_key *key) { diff --git a/tools/perf/arch/x86/tests/intel-cqm.c b/tools/perf/arch/x86/tests/intel-cqm.c index 94aa0b673b7f..2a105e3b2ad1 100644 --- a/tools/perf/arch/x86/tests/intel-cqm.c +++ b/tools/perf/arch/x86/tests/intel-cqm.c @@ -40,8 +40,8 @@ static pid_t spawn(void) */ int test__intel_cqm_count_nmi_context(struct test *test __maybe_unused, int subtest __maybe_unused) { - struct perf_evlist *evlist = NULL; - struct perf_evsel *evsel = NULL; + struct evlist *evlist = NULL; + struct evsel *evsel = NULL; struct perf_event_attr pe; int i, fd[2], flag, ret; size_t mmap_len; @@ -51,7 +51,7 @@ int test__intel_cqm_count_nmi_context(struct test *test __maybe_unused, int subt flag = perf_event_open_cloexec_flag(); - evlist = perf_evlist__new(); + evlist = evlist__new(); if (!evlist) { pr_debug("perf_evlist__new failed\n"); return TEST_FAIL; @@ -124,6 +124,6 @@ int test__intel_cqm_count_nmi_context(struct test *test __maybe_unused, int subt kill(pid, SIGKILL); wait(NULL); out: - perf_evlist__delete(evlist); + evlist__delete(evlist); return err; } diff --git a/tools/perf/arch/x86/tests/perf-time-to-tsc.c b/tools/perf/arch/x86/tests/perf-time-to-tsc.c index 7a7721604b86..582182d98a7f 100644 --- a/tools/perf/arch/x86/tests/perf-time-to-tsc.c +++ b/tools/perf/arch/x86/tests/perf-time-to-tsc.c @@ -5,6 +5,8 @@ #include <unistd.h> #include <linux/types.h> #include <sys/prctl.h> +#include <perf/cpumap.h> +#include <perf/evlist.h> #include "parse-events.h" #include "evlist.h" @@ -49,10 +51,10 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe }, .sample_time = true, }; - struct thread_map *threads = NULL; - struct cpu_map *cpus = NULL; - struct perf_evlist *evlist = NULL; - struct perf_evsel *evsel = NULL; + struct perf_thread_map *threads = NULL; + struct perf_cpu_map *cpus = NULL; + struct evlist *evlist = NULL; + struct evsel *evsel = NULL; int err = -1, ret, i; const char *comm1, *comm2; struct perf_tsc_conversion tc; @@ -65,13 +67,13 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe threads = thread_map__new(-1, getpid(), UINT_MAX); CHECK_NOT_NULL__(threads); - cpus = cpu_map__new(NULL); + cpus = perf_cpu_map__new(NULL); CHECK_NOT_NULL__(cpus); - evlist = perf_evlist__new(); + evlist = evlist__new(); CHECK_NOT_NULL__(evlist); - perf_evlist__set_maps(evlist, cpus, threads); + perf_evlist__set_maps(&evlist->core, cpus, threads); CHECK__(parse_events(evlist, "cycles:u", NULL)); @@ -79,11 +81,11 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe evsel = perf_evlist__first(evlist); - evsel->attr.comm = 1; - evsel->attr.disabled = 1; - evsel->attr.enable_on_exec = 0; + evsel->core.attr.comm = 1; + evsel->core.attr.disabled = 1; + evsel->core.attr.enable_on_exec = 0; - CHECK__(perf_evlist__open(evlist)); + CHECK__(evlist__open(evlist)); CHECK__(perf_evlist__mmap(evlist, UINT_MAX)); @@ -97,7 +99,7 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe goto out_err; } - perf_evlist__enable(evlist); + evlist__enable(evlist); comm1 = "Test COMM 1"; CHECK__(prctl(PR_SET_NAME, (unsigned long)comm1, 0, 0, 0)); @@ -107,7 +109,7 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe comm2 = "Test COMM 2"; CHECK__(prctl(PR_SET_NAME, (unsigned long)comm2, 0, 0, 0)); - perf_evlist__disable(evlist); + evlist__disable(evlist); for (i = 0; i < evlist->nr_mmaps; i++) { md = &evlist->mmap[i]; @@ -163,6 +165,6 @@ next_event: err = 0; out_err: - perf_evlist__delete(evlist); + evlist__delete(evlist); return err; } diff --git a/tools/perf/arch/x86/util/auxtrace.c b/tools/perf/arch/x86/util/auxtrace.c index d711268af330..96f4a2c11893 100644 --- a/tools/perf/arch/x86/util/auxtrace.c +++ b/tools/perf/arch/x86/util/auxtrace.c @@ -16,12 +16,12 @@ #include "../../util/evlist.h" static -struct auxtrace_record *auxtrace_record__init_intel(struct perf_evlist *evlist, +struct auxtrace_record *auxtrace_record__init_intel(struct evlist *evlist, int *err) { struct perf_pmu *intel_pt_pmu; struct perf_pmu *intel_bts_pmu; - struct perf_evsel *evsel; + struct evsel *evsel; bool found_pt = false; bool found_bts = false; @@ -29,9 +29,9 @@ struct auxtrace_record *auxtrace_record__init_intel(struct perf_evlist *evlist, intel_bts_pmu = perf_pmu__find(INTEL_BTS_PMU_NAME); evlist__for_each_entry(evlist, evsel) { - if (intel_pt_pmu && evsel->attr.type == intel_pt_pmu->type) + if (intel_pt_pmu && evsel->core.attr.type == intel_pt_pmu->type) found_pt = true; - if (intel_bts_pmu && evsel->attr.type == intel_bts_pmu->type) + if (intel_bts_pmu && evsel->core.attr.type == intel_bts_pmu->type) found_bts = true; } @@ -50,7 +50,7 @@ struct auxtrace_record *auxtrace_record__init_intel(struct perf_evlist *evlist, return NULL; } -struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist, +struct auxtrace_record *auxtrace_record__init(struct evlist *evlist, int *err) { char buffer[64]; diff --git a/tools/perf/arch/x86/util/header.c b/tools/perf/arch/x86/util/header.c index af9a9f2600be..662ecf84a421 100644 --- a/tools/perf/arch/x86/util/header.c +++ b/tools/perf/arch/x86/util/header.c @@ -6,6 +6,7 @@ #include <string.h> #include <regex.h> +#include "../../util/debug.h" #include "../../util/header.h" static inline void diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c index ec5c1bb84095..2d5d8a12dd1f 100644 --- a/tools/perf/arch/x86/util/intel-bts.c +++ b/tools/perf/arch/x86/util/intel-bts.c @@ -35,7 +35,7 @@ struct intel_bts_snapshot_ref { struct intel_bts_recording { struct auxtrace_record itr; struct perf_pmu *intel_bts_pmu; - struct perf_evlist *evlist; + struct evlist *evlist; bool snapshot_mode; size_t snapshot_size; int snapshot_ref_cnt; @@ -50,7 +50,7 @@ struct branch { static size_t intel_bts_info_priv_size(struct auxtrace_record *itr __maybe_unused, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { return INTEL_BTS_AUXTRACE_PRIV_SIZE; } @@ -99,27 +99,27 @@ static int intel_bts_info_fill(struct auxtrace_record *itr, } static int intel_bts_recording_options(struct auxtrace_record *itr, - struct perf_evlist *evlist, + struct evlist *evlist, struct record_opts *opts) { struct intel_bts_recording *btsr = container_of(itr, struct intel_bts_recording, itr); struct perf_pmu *intel_bts_pmu = btsr->intel_bts_pmu; - struct perf_evsel *evsel, *intel_bts_evsel = NULL; - const struct cpu_map *cpus = evlist->cpus; + struct evsel *evsel, *intel_bts_evsel = NULL; + const struct perf_cpu_map *cpus = evlist->core.cpus; bool privileged = geteuid() == 0 || perf_event_paranoid() < 0; btsr->evlist = evlist; btsr->snapshot_mode = opts->auxtrace_snapshot_mode; evlist__for_each_entry(evlist, evsel) { - if (evsel->attr.type == intel_bts_pmu->type) { + if (evsel->core.attr.type == intel_bts_pmu->type) { if (intel_bts_evsel) { pr_err("There may be only one " INTEL_BTS_PMU_NAME " event\n"); return -EINVAL; } - evsel->attr.freq = 0; - evsel->attr.sample_period = 1; + evsel->core.attr.freq = 0; + evsel->core.attr.sample_period = 1; intel_bts_evsel = evsel; opts->full_auxtrace = true; } @@ -133,7 +133,7 @@ static int intel_bts_recording_options(struct auxtrace_record *itr, if (!opts->full_auxtrace) return 0; - if (opts->full_auxtrace && !cpu_map__empty(cpus)) { + if (opts->full_auxtrace && !perf_cpu_map__empty(cpus)) { pr_err(INTEL_BTS_PMU_NAME " does not support per-cpu recording\n"); return -EINVAL; } @@ -214,13 +214,13 @@ static int intel_bts_recording_options(struct auxtrace_record *itr, * In the case of per-cpu mmaps, we need the CPU on the * AUX event. */ - if (!cpu_map__empty(cpus)) + if (!perf_cpu_map__empty(cpus)) perf_evsel__set_sample_bit(intel_bts_evsel, CPU); } /* Add dummy event to keep tracking */ if (opts->full_auxtrace) { - struct perf_evsel *tracking_evsel; + struct evsel *tracking_evsel; int err; err = parse_events(evlist, "dummy:u", NULL); @@ -231,8 +231,8 @@ static int intel_bts_recording_options(struct auxtrace_record *itr, perf_evlist__set_tracking_event(evlist, tracking_evsel); - tracking_evsel->attr.freq = 0; - tracking_evsel->attr.sample_period = 1; + tracking_evsel->core.attr.freq = 0; + tracking_evsel->core.attr.sample_period = 1; } return 0; @@ -313,11 +313,11 @@ static int intel_bts_snapshot_start(struct auxtrace_record *itr) { struct intel_bts_recording *btsr = container_of(itr, struct intel_bts_recording, itr); - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(btsr->evlist, evsel) { - if (evsel->attr.type == btsr->intel_bts_pmu->type) - return perf_evsel__disable(evsel); + if (evsel->core.attr.type == btsr->intel_bts_pmu->type) + return evsel__disable(evsel); } return -EINVAL; } @@ -326,11 +326,11 @@ static int intel_bts_snapshot_finish(struct auxtrace_record *itr) { struct intel_bts_recording *btsr = container_of(itr, struct intel_bts_recording, itr); - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(btsr->evlist, evsel) { - if (evsel->attr.type == btsr->intel_bts_pmu->type) - return perf_evsel__enable(evsel); + if (evsel->core.attr.type == btsr->intel_bts_pmu->type) + return evsel__enable(evsel); } return -EINVAL; } @@ -408,10 +408,10 @@ static int intel_bts_read_finish(struct auxtrace_record *itr, int idx) { struct intel_bts_recording *btsr = container_of(itr, struct intel_bts_recording, itr); - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(btsr->evlist, evsel) { - if (evsel->attr.type == btsr->intel_bts_pmu->type) + if (evsel->core.attr.type == btsr->intel_bts_pmu->type) return perf_evlist__enable_event_idx(btsr->evlist, evsel, idx); } diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c index 609088c01e3a..c72a77a82b39 100644 --- a/tools/perf/arch/x86/util/intel-pt.c +++ b/tools/perf/arch/x86/util/intel-pt.c @@ -44,7 +44,7 @@ struct intel_pt_recording { struct auxtrace_record itr; struct perf_pmu *intel_pt_pmu; int have_sched_switch; - struct perf_evlist *evlist; + struct evlist *evlist; bool snapshot_mode; bool snapshot_init_done; size_t snapshot_size; @@ -110,9 +110,9 @@ static u64 intel_pt_masked_bits(u64 mask, u64 bits) } static int intel_pt_read_config(struct perf_pmu *intel_pt_pmu, const char *str, - struct perf_evlist *evlist, u64 *res) + struct evlist *evlist, u64 *res) { - struct perf_evsel *evsel; + struct evsel *evsel; u64 mask; *res = 0; @@ -122,8 +122,8 @@ static int intel_pt_read_config(struct perf_pmu *intel_pt_pmu, const char *str, return -EINVAL; evlist__for_each_entry(evlist, evsel) { - if (evsel->attr.type == intel_pt_pmu->type) { - *res = intel_pt_masked_bits(mask, evsel->attr.config); + if (evsel->core.attr.type == intel_pt_pmu->type) { + *res = intel_pt_masked_bits(mask, evsel->core.attr.config); return 0; } } @@ -132,7 +132,7 @@ static int intel_pt_read_config(struct perf_pmu *intel_pt_pmu, const char *str, } static size_t intel_pt_psb_period(struct perf_pmu *intel_pt_pmu, - struct perf_evlist *evlist) + struct evlist *evlist) { u64 val; int err, topa_multiple_entries; @@ -268,13 +268,13 @@ intel_pt_pmu_default_config(struct perf_pmu *intel_pt_pmu) return attr; } -static const char *intel_pt_find_filter(struct perf_evlist *evlist, +static const char *intel_pt_find_filter(struct evlist *evlist, struct perf_pmu *intel_pt_pmu) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { - if (evsel->attr.type == intel_pt_pmu->type) + if (evsel->core.attr.type == intel_pt_pmu->type) return evsel->filter; } @@ -289,7 +289,7 @@ static size_t intel_pt_filter_bytes(const char *filter) } static size_t -intel_pt_info_priv_size(struct auxtrace_record *itr, struct perf_evlist *evlist) +intel_pt_info_priv_size(struct auxtrace_record *itr, struct evlist *evlist) { struct intel_pt_recording *ptr = container_of(itr, struct intel_pt_recording, itr); @@ -365,7 +365,7 @@ static int intel_pt_info_fill(struct auxtrace_record *itr, ui__warning("Intel Processor Trace: TSC not available\n"); } - per_cpu_mmaps = !cpu_map__empty(session->evlist->cpus); + per_cpu_mmaps = !perf_cpu_map__empty(session->evlist->core.cpus); auxtrace_info->type = PERF_AUXTRACE_INTEL_PT; auxtrace_info->priv[INTEL_PT_PMU_TYPE] = intel_pt_pmu->type; @@ -398,10 +398,10 @@ static int intel_pt_info_fill(struct auxtrace_record *itr, return 0; } -static int intel_pt_track_switches(struct perf_evlist *evlist) +static int intel_pt_track_switches(struct evlist *evlist) { const char *sched_switch = "sched:sched_switch"; - struct perf_evsel *evsel; + struct evsel *evsel; int err; if (!perf_evlist__can_select_event(evlist, sched_switch)) @@ -513,7 +513,7 @@ out_err: } static int intel_pt_validate_config(struct perf_pmu *intel_pt_pmu, - struct perf_evsel *evsel) + struct evsel *evsel) { int err; char c; @@ -526,38 +526,58 @@ static int intel_pt_validate_config(struct perf_pmu *intel_pt_pmu, * sets pt=0, which avoids senseless kernel errors. */ if (perf_pmu__scan_file(intel_pt_pmu, "format/pt", "%c", &c) == 1 && - !(evsel->attr.config & 1)) { + !(evsel->core.attr.config & 1)) { pr_warning("pt=0 doesn't make sense, forcing pt=1\n"); - evsel->attr.config |= 1; + evsel->core.attr.config |= 1; } err = intel_pt_val_config_term(intel_pt_pmu, "caps/cycle_thresholds", "cyc_thresh", "caps/psb_cyc", - evsel->attr.config); + evsel->core.attr.config); if (err) return err; err = intel_pt_val_config_term(intel_pt_pmu, "caps/mtc_periods", "mtc_period", "caps/mtc", - evsel->attr.config); + evsel->core.attr.config); if (err) return err; return intel_pt_val_config_term(intel_pt_pmu, "caps/psb_periods", "psb_period", "caps/psb_cyc", - evsel->attr.config); + evsel->core.attr.config); +} + +/* + * Currently, there is not enough information to disambiguate different PEBS + * events, so only allow one. + */ +static bool intel_pt_too_many_aux_output(struct evlist *evlist) +{ + struct evsel *evsel; + int aux_output_cnt = 0; + + evlist__for_each_entry(evlist, evsel) + aux_output_cnt += !!evsel->core.attr.aux_output; + + if (aux_output_cnt > 1) { + pr_err(INTEL_PT_PMU_NAME " supports at most one event with aux-output\n"); + return true; + } + + return false; } static int intel_pt_recording_options(struct auxtrace_record *itr, - struct perf_evlist *evlist, + struct evlist *evlist, struct record_opts *opts) { struct intel_pt_recording *ptr = container_of(itr, struct intel_pt_recording, itr); struct perf_pmu *intel_pt_pmu = ptr->intel_pt_pmu; bool have_timing_info, need_immediate = false; - struct perf_evsel *evsel, *intel_pt_evsel = NULL; - const struct cpu_map *cpus = evlist->cpus; + struct evsel *evsel, *intel_pt_evsel = NULL; + const struct perf_cpu_map *cpus = evlist->core.cpus; bool privileged = geteuid() == 0 || perf_event_paranoid() < 0; u64 tsc_bit; int err; @@ -566,13 +586,13 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, ptr->snapshot_mode = opts->auxtrace_snapshot_mode; evlist__for_each_entry(evlist, evsel) { - if (evsel->attr.type == intel_pt_pmu->type) { + if (evsel->core.attr.type == intel_pt_pmu->type) { if (intel_pt_evsel) { pr_err("There may be only one " INTEL_PT_PMU_NAME " event\n"); return -EINVAL; } - evsel->attr.freq = 0; - evsel->attr.sample_period = 1; + evsel->core.attr.freq = 0; + evsel->core.attr.sample_period = 1; intel_pt_evsel = evsel; opts->full_auxtrace = true; } @@ -588,6 +608,9 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, return -EINVAL; } + if (intel_pt_too_many_aux_output(evlist)) + return -EINVAL; + if (!opts->full_auxtrace) return 0; @@ -670,7 +693,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, intel_pt_parse_terms(&intel_pt_pmu->format, "tsc", &tsc_bit); - if (opts->full_auxtrace && (intel_pt_evsel->attr.config & tsc_bit)) + if (opts->full_auxtrace && (intel_pt_evsel->core.attr.config & tsc_bit)) have_timing_info = true; else have_timing_info = false; @@ -679,13 +702,13 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, * Per-cpu recording needs sched_switch events to distinguish different * threads. */ - if (have_timing_info && !cpu_map__empty(cpus)) { + if (have_timing_info && !perf_cpu_map__empty(cpus)) { if (perf_can_record_switch_events()) { bool cpu_wide = !target__none(&opts->target) && !target__has_task(&opts->target); if (!cpu_wide && perf_can_record_cpu_wide()) { - struct perf_evsel *switch_evsel; + struct evsel *switch_evsel; err = parse_events(evlist, "dummy:u", NULL); if (err) @@ -693,9 +716,9 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, switch_evsel = perf_evlist__last(evlist); - switch_evsel->attr.freq = 0; - switch_evsel->attr.sample_period = 1; - switch_evsel->attr.context_switch = 1; + switch_evsel->core.attr.freq = 0; + switch_evsel->core.attr.sample_period = 1; + switch_evsel->core.attr.context_switch = 1; switch_evsel->system_wide = true; switch_evsel->no_aux_samples = true; @@ -737,13 +760,13 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, * In the case of per-cpu mmaps, we need the CPU on the * AUX event. */ - if (!cpu_map__empty(cpus)) + if (!perf_cpu_map__empty(cpus)) perf_evsel__set_sample_bit(intel_pt_evsel, CPU); } /* Add dummy event to keep tracking */ if (opts->full_auxtrace) { - struct perf_evsel *tracking_evsel; + struct evsel *tracking_evsel; err = parse_events(evlist, "dummy:u", NULL); if (err) @@ -753,15 +776,15 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, perf_evlist__set_tracking_event(evlist, tracking_evsel); - tracking_evsel->attr.freq = 0; - tracking_evsel->attr.sample_period = 1; + tracking_evsel->core.attr.freq = 0; + tracking_evsel->core.attr.sample_period = 1; tracking_evsel->no_aux_samples = true; if (need_immediate) tracking_evsel->immediate = true; /* In per-cpu case, always need the time of mmap events etc */ - if (!cpu_map__empty(cpus)) { + if (!perf_cpu_map__empty(cpus)) { perf_evsel__set_sample_bit(tracking_evsel, TIME); /* And the CPU for switch events */ perf_evsel__set_sample_bit(tracking_evsel, CPU); @@ -773,7 +796,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, * Warn the user when we do not have enough information to decode i.e. * per-cpu with no sched_switch (except workload-only). */ - if (!ptr->have_sched_switch && !cpu_map__empty(cpus) && + if (!ptr->have_sched_switch && !perf_cpu_map__empty(cpus) && !target__none(&opts->target)) ui__warning("Intel Processor Trace decoding will not be possible except for kernel tracing!\n"); @@ -784,11 +807,11 @@ static int intel_pt_snapshot_start(struct auxtrace_record *itr) { struct intel_pt_recording *ptr = container_of(itr, struct intel_pt_recording, itr); - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(ptr->evlist, evsel) { - if (evsel->attr.type == ptr->intel_pt_pmu->type) - return perf_evsel__disable(evsel); + if (evsel->core.attr.type == ptr->intel_pt_pmu->type) + return evsel__disable(evsel); } return -EINVAL; } @@ -797,11 +820,11 @@ static int intel_pt_snapshot_finish(struct auxtrace_record *itr) { struct intel_pt_recording *ptr = container_of(itr, struct intel_pt_recording, itr); - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(ptr->evlist, evsel) { - if (evsel->attr.type == ptr->intel_pt_pmu->type) - return perf_evsel__enable(evsel); + if (evsel->core.attr.type == ptr->intel_pt_pmu->type) + return evsel__enable(evsel); } return -EINVAL; } @@ -1070,10 +1093,10 @@ static int intel_pt_read_finish(struct auxtrace_record *itr, int idx) { struct intel_pt_recording *ptr = container_of(itr, struct intel_pt_recording, itr); - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(ptr->evlist, evsel) { - if (evsel->attr.type == ptr->intel_pt_pmu->type) + if (evsel->core.attr.type == ptr->intel_pt_pmu->type) return perf_evlist__enable_event_idx(ptr->evlist, evsel, idx); } diff --git a/tools/perf/arch/x86/util/kvm-stat.c b/tools/perf/arch/x86/util/kvm-stat.c index 865a9762f22e..c0775c39227f 100644 --- a/tools/perf/arch/x86/util/kvm-stat.c +++ b/tools/perf/arch/x86/util/kvm-stat.c @@ -1,7 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 #include <errno.h> -#include "../../util/kvm-stat.h" -#include "../../util/evsel.h" +#include <string.h> +#include "../../../util/kvm-stat.h" +#include "../../../util/evsel.h" #include <asm/svm.h> #include <asm/vmx.h> #include <asm/kvm.h> @@ -27,7 +28,7 @@ const char *kvm_exit_trace = "kvm:kvm_exit"; * the time of MMIO write: kvm_mmio(KVM_TRACE_MMIO_WRITE...) -> kvm_entry * the time of MMIO read: kvm_exit -> kvm_mmio(KVM_TRACE_MMIO_READ...). */ -static void mmio_event_get_key(struct perf_evsel *evsel, struct perf_sample *sample, +static void mmio_event_get_key(struct evsel *evsel, struct perf_sample *sample, struct event_key *key) { key->key = perf_evsel__intval(evsel, sample, "gpa"); @@ -38,7 +39,7 @@ static void mmio_event_get_key(struct perf_evsel *evsel, struct perf_sample *sam #define KVM_TRACE_MMIO_READ 1 #define KVM_TRACE_MMIO_WRITE 2 -static bool mmio_event_begin(struct perf_evsel *evsel, +static bool mmio_event_begin(struct evsel *evsel, struct perf_sample *sample, struct event_key *key) { /* MMIO read begin event in kernel. */ @@ -55,7 +56,7 @@ static bool mmio_event_begin(struct perf_evsel *evsel, return false; } -static bool mmio_event_end(struct perf_evsel *evsel, struct perf_sample *sample, +static bool mmio_event_end(struct evsel *evsel, struct perf_sample *sample, struct event_key *key) { /* MMIO write end event in kernel. */ @@ -89,7 +90,7 @@ static struct kvm_events_ops mmio_events = { }; /* The time of emulation pio access is from kvm_pio to kvm_entry. */ -static void ioport_event_get_key(struct perf_evsel *evsel, +static void ioport_event_get_key(struct evsel *evsel, struct perf_sample *sample, struct event_key *key) { @@ -97,7 +98,7 @@ static void ioport_event_get_key(struct perf_evsel *evsel, key->info = perf_evsel__intval(evsel, sample, "rw"); } -static bool ioport_event_begin(struct perf_evsel *evsel, +static bool ioport_event_begin(struct evsel *evsel, struct perf_sample *sample, struct event_key *key) { @@ -109,7 +110,7 @@ static bool ioport_event_begin(struct perf_evsel *evsel, return false; } -static bool ioport_event_end(struct perf_evsel *evsel, +static bool ioport_event_end(struct evsel *evsel, struct perf_sample *sample __maybe_unused, struct event_key *key __maybe_unused) { diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c index 950539f9a4f7..b1eb963b4a6e 100644 --- a/tools/perf/arch/x86/util/tsc.c +++ b/tools/perf/arch/x86/util/tsc.c @@ -5,10 +5,10 @@ #include <linux/stddef.h> #include <linux/perf_event.h> -#include "../../perf.h" +#include "../../../perf.h" #include <linux/types.h> -#include "../../util/debug.h" -#include "../../util/tsc.h" +#include "../../../util/debug.h" +#include "../../../util/tsc.h" int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc, struct perf_tsc_conversion *tc) diff --git a/tools/perf/bench/epoll-ctl.c b/tools/perf/bench/epoll-ctl.c index 2af067859966..84658d45f349 100644 --- a/tools/perf/bench/epoll-ctl.c +++ b/tools/perf/bench/epoll-ctl.c @@ -20,6 +20,7 @@ #include <sys/resource.h> #include <sys/epoll.h> #include <sys/eventfd.h> +#include <perf/cpumap.h> #include "../util/stat.h" #include <subcmd/parse-options.h> @@ -219,7 +220,7 @@ static void init_fdmaps(struct worker *w, int pct) } } -static int do_threads(struct worker *worker, struct cpu_map *cpu) +static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) { pthread_attr_t thread_attr, *attrp = NULL; cpu_set_t cpuset; @@ -301,7 +302,7 @@ int bench_epoll_ctl(int argc, const char **argv) int j, ret = 0; struct sigaction act; struct worker *worker = NULL; - struct cpu_map *cpu; + struct perf_cpu_map *cpu; struct rlimit rl, prevrl; unsigned int i; @@ -315,7 +316,7 @@ int bench_epoll_ctl(int argc, const char **argv) act.sa_sigaction = toggle_done; sigaction(SIGINT, &act, NULL); - cpu = cpu_map__new(NULL); + cpu = perf_cpu_map__new(NULL); if (!cpu) goto errmem; diff --git a/tools/perf/bench/epoll-wait.c b/tools/perf/bench/epoll-wait.c index fe85448abd45..c27a65639cfb 100644 --- a/tools/perf/bench/epoll-wait.c +++ b/tools/perf/bench/epoll-wait.c @@ -75,6 +75,7 @@ #include <sys/epoll.h> #include <sys/eventfd.h> #include <sys/types.h> +#include <perf/cpumap.h> #include "../util/stat.h" #include <subcmd/parse-options.h> @@ -288,7 +289,7 @@ static void print_summary(void) (int) runtime.tv_sec); } -static int do_threads(struct worker *worker, struct cpu_map *cpu) +static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) { pthread_attr_t thread_attr, *attrp = NULL; cpu_set_t cpuset; @@ -415,7 +416,7 @@ int bench_epoll_wait(int argc, const char **argv) struct sigaction act; unsigned int i; struct worker *worker = NULL; - struct cpu_map *cpu; + struct perf_cpu_map *cpu; pthread_t wthread; struct rlimit rl, prevrl; @@ -429,7 +430,7 @@ int bench_epoll_wait(int argc, const char **argv) act.sa_sigaction = toggle_done; sigaction(SIGINT, &act, NULL); - cpu = cpu_map__new(NULL); + cpu = perf_cpu_map__new(NULL); if (!cpu) goto errmem; diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c index a80797763e1f..80e138904c66 100644 --- a/tools/perf/bench/futex-hash.c +++ b/tools/perf/bench/futex-hash.c @@ -20,6 +20,7 @@ #include <linux/kernel.h> #include <linux/zalloc.h> #include <sys/time.h> +#include <perf/cpumap.h> #include "../util/stat.h" #include <subcmd/parse-options.h> @@ -124,7 +125,7 @@ int bench_futex_hash(int argc, const char **argv) unsigned int i; pthread_attr_t thread_attr; struct worker *worker = NULL; - struct cpu_map *cpu; + struct perf_cpu_map *cpu; argc = parse_options(argc, argv, options, bench_futex_hash_usage, 0); if (argc) { @@ -132,7 +133,7 @@ int bench_futex_hash(int argc, const char **argv) exit(EXIT_FAILURE); } - cpu = cpu_map__new(NULL); + cpu = perf_cpu_map__new(NULL); if (!cpu) goto errmem; diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c index d02330a69745..c5d6d0abbaa9 100644 --- a/tools/perf/bench/futex-lock-pi.c +++ b/tools/perf/bench/futex-lock-pi.c @@ -14,6 +14,7 @@ #include <linux/kernel.h> #include <linux/zalloc.h> #include <errno.h> +#include <perf/cpumap.h> #include "bench.h" #include "futex.h" #include "cpumap.h" @@ -116,7 +117,7 @@ static void *workerfn(void *arg) } static void create_threads(struct worker *w, pthread_attr_t thread_attr, - struct cpu_map *cpu) + struct perf_cpu_map *cpu) { cpu_set_t cpuset; unsigned int i; @@ -150,13 +151,13 @@ int bench_futex_lock_pi(int argc, const char **argv) unsigned int i; struct sigaction act; pthread_attr_t thread_attr; - struct cpu_map *cpu; + struct perf_cpu_map *cpu; argc = parse_options(argc, argv, options, bench_futex_lock_pi_usage, 0); if (argc) goto err; - cpu = cpu_map__new(NULL); + cpu = perf_cpu_map__new(NULL); if (!cpu) err(EXIT_FAILURE, "calloc"); diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c index fc692efa0c05..75d3418c1a88 100644 --- a/tools/perf/bench/futex-requeue.c +++ b/tools/perf/bench/futex-requeue.c @@ -20,6 +20,7 @@ #include <linux/kernel.h> #include <linux/time64.h> #include <errno.h> +#include <perf/cpumap.h> #include "bench.h" #include "futex.h" #include "cpumap.h" @@ -84,7 +85,7 @@ static void *workerfn(void *arg __maybe_unused) } static void block_threads(pthread_t *w, - pthread_attr_t thread_attr, struct cpu_map *cpu) + pthread_attr_t thread_attr, struct perf_cpu_map *cpu) { cpu_set_t cpuset; unsigned int i; @@ -117,13 +118,13 @@ int bench_futex_requeue(int argc, const char **argv) unsigned int i, j; struct sigaction act; pthread_attr_t thread_attr; - struct cpu_map *cpu; + struct perf_cpu_map *cpu; argc = parse_options(argc, argv, options, bench_futex_requeue_usage, 0); if (argc) goto err; - cpu = cpu_map__new(NULL); + cpu = perf_cpu_map__new(NULL); if (!cpu) err(EXIT_FAILURE, "cpu_map__new"); diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c index 69d8fdc87315..163fe16c275a 100644 --- a/tools/perf/bench/futex-wake-parallel.c +++ b/tools/perf/bench/futex-wake-parallel.c @@ -138,7 +138,7 @@ static void *blocked_workerfn(void *arg __maybe_unused) } static void block_threads(pthread_t *w, pthread_attr_t thread_attr, - struct cpu_map *cpu) + struct perf_cpu_map *cpu) { cpu_set_t cpuset; unsigned int i; @@ -224,7 +224,7 @@ int bench_futex_wake_parallel(int argc, const char **argv) struct sigaction act; pthread_attr_t thread_attr; struct thread_data *waking_worker; - struct cpu_map *cpu; + struct perf_cpu_map *cpu; argc = parse_options(argc, argv, options, bench_futex_wake_parallel_usage, 0); @@ -237,7 +237,7 @@ int bench_futex_wake_parallel(int argc, const char **argv) act.sa_sigaction = toggle_done; sigaction(SIGINT, &act, NULL); - cpu = cpu_map__new(NULL); + cpu = perf_cpu_map__new(NULL); if (!cpu) err(EXIT_FAILURE, "calloc"); diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c index e8181ad7d088..77dcdc13618a 100644 --- a/tools/perf/bench/futex-wake.c +++ b/tools/perf/bench/futex-wake.c @@ -20,6 +20,7 @@ #include <linux/kernel.h> #include <linux/time64.h> #include <errno.h> +#include <perf/cpumap.h> #include "bench.h" #include "futex.h" #include "cpumap.h" @@ -90,7 +91,7 @@ static void print_summary(void) } static void block_threads(pthread_t *w, - pthread_attr_t thread_attr, struct cpu_map *cpu) + pthread_attr_t thread_attr, struct perf_cpu_map *cpu) { cpu_set_t cpuset; unsigned int i; @@ -123,7 +124,7 @@ int bench_futex_wake(int argc, const char **argv) unsigned int i, j; struct sigaction act; pthread_attr_t thread_attr; - struct cpu_map *cpu; + struct perf_cpu_map *cpu; argc = parse_options(argc, argv, options, bench_futex_wake_usage, 0); if (argc) { @@ -131,7 +132,7 @@ int bench_futex_wake(int argc, const char **argv) exit(EXIT_FAILURE); } - cpu = cpu_map__new(NULL); + cpu = perf_cpu_map__new(NULL); if (!cpu) err(EXIT_FAILURE, "calloc"); diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index e0aa14faf2b5..9bb637165bf9 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -156,7 +156,7 @@ static int hist_iter__branch_callback(struct hist_entry_iter *iter, struct hist_entry *he = iter->he; struct branch_info *bi; struct perf_sample *sample = iter->sample; - struct perf_evsel *evsel = iter->evsel; + struct evsel *evsel = iter->evsel; int err; bi = he->branch_info; @@ -171,7 +171,7 @@ out: return err; } -static int process_branch_callback(struct perf_evsel *evsel, +static int process_branch_callback(struct evsel *evsel, struct perf_sample *sample, struct addr_location *al __maybe_unused, struct perf_annotate *ann, @@ -208,7 +208,7 @@ static bool has_annotation(struct perf_annotate *ann) return ui__has_annotation() || ann->use_stdio2; } -static int perf_evsel__add_sample(struct perf_evsel *evsel, +static int perf_evsel__add_sample(struct evsel *evsel, struct perf_sample *sample, struct addr_location *al, struct perf_annotate *ann, @@ -257,7 +257,7 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel, static int process_sample_event(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct machine *machine) { struct perf_annotate *ann = container_of(tool, struct perf_annotate, tool); @@ -293,7 +293,7 @@ static int process_feature_event(struct perf_session *session, } static int hist_entry__tty_annotate(struct hist_entry *he, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_annotate *ann) { if (!ann->use_stdio2) @@ -303,7 +303,7 @@ static int hist_entry__tty_annotate(struct hist_entry *he, } static void hists__find_annotations(struct hists *hists, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_annotate *ann) { struct rb_node *nd = rb_first_cached(&hists->entries), *next; @@ -333,7 +333,7 @@ find_next: if (use_browser == 2) { int ret; int (*annotate)(struct hist_entry *he, - struct perf_evsel *evsel, + struct evsel *evsel, struct hist_browser_timer *hbt); annotate = dlsym(perf_gtk_handle, @@ -387,7 +387,7 @@ static int __cmd_annotate(struct perf_annotate *ann) { int ret; struct perf_session *session = ann->session; - struct perf_evsel *pos; + struct evsel *pos; u64 total_nr_samples; if (ann->cpu_list) { diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index e3776f5c2e01..211143720078 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -248,7 +248,7 @@ static void compute_stats(struct c2c_hist_entry *c2c_he, static int process_sample_event(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct machine *machine) { struct c2c_hists *c2c_hists = &c2c.hists; @@ -2027,7 +2027,7 @@ static int setup_nodes(struct perf_session *session) c2c.node_info = 2; c2c.nodes_cnt = session->header.env.nr_numa_nodes; - c2c.cpus_cnt = session->header.env.nr_cpus_online; + c2c.cpus_cnt = session->header.env.nr_cpus_avail; n = session->header.env.numa_nodes; if (!n) @@ -2049,7 +2049,7 @@ static int setup_nodes(struct perf_session *session) c2c.cpu2node = cpu2node; for (node = 0; node < c2c.nodes_cnt; node++) { - struct cpu_map *map = n[node].map; + struct perf_cpu_map *map = n[node].map; unsigned long *set; set = bitmap_alloc(c2c.cpus_cnt); @@ -2059,7 +2059,7 @@ static int setup_nodes(struct perf_session *session) nodes[node] = set; /* empty node, skip */ - if (cpu_map__empty(map)) + if (perf_cpu_map__empty(map)) continue; for (cpu = 0; cpu < map->nr; cpu++) { @@ -2236,8 +2236,8 @@ static void print_pareto(FILE *out) static void print_c2c_info(FILE *out, struct perf_session *session) { - struct perf_evlist *evlist = session->evlist; - struct perf_evsel *evsel; + struct evlist *evlist = session->evlist; + struct evsel *evsel; bool first = true; fprintf(out, "=================================================\n"); @@ -2567,7 +2567,7 @@ parse_callchain_opt(const struct option *opt, const char *arg, int unset) return parse_callchain_report_opt(arg); } -static int setup_callchain(struct perf_evlist *evlist) +static int setup_callchain(struct evlist *evlist) { u64 sample_type = perf_evlist__combined_sample_type(evlist); enum perf_call_graph_mode mode = CALLCHAIN_NONE; diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index f6f5dd15bea7..e91c0d798181 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -376,7 +376,7 @@ struct hist_entry_ops block_hist_ops = { static int diff__process_sample_event(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct machine *machine) { struct perf_diff *pdiff = container_of(tool, struct perf_diff, tool); @@ -448,10 +448,10 @@ static struct perf_diff pdiff = { }, }; -static struct perf_evsel *evsel_match(struct perf_evsel *evsel, - struct perf_evlist *evlist) +static struct evsel *evsel_match(struct evsel *evsel, + struct evlist *evlist) { - struct perf_evsel *e; + struct evsel *e; evlist__for_each_entry(evlist, e) { if (perf_evsel__match2(evsel, e)) @@ -461,9 +461,9 @@ static struct perf_evsel *evsel_match(struct perf_evsel *evsel, return NULL; } -static void perf_evlist__collapse_resort(struct perf_evlist *evlist) +static void perf_evlist__collapse_resort(struct evlist *evlist) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { struct hists *hists = evsel__hists(evsel); @@ -1009,8 +1009,8 @@ static void data__fprintf(void) static void data_process(void) { - struct perf_evlist *evlist_base = data__files[0].session->evlist; - struct perf_evsel *evsel_base; + struct evlist *evlist_base = data__files[0].session->evlist; + struct evsel *evsel_base; bool first = true; evlist__for_each_entry(evlist_base, evsel_base) { @@ -1019,8 +1019,8 @@ static void data_process(void) int i; data__for_each_file_new(i, d) { - struct perf_evlist *evlist = d->session->evlist; - struct perf_evsel *evsel; + struct evlist *evlist = d->session->evlist; + struct evsel *evsel; struct hists *hists; evsel = evsel_match(evsel_base, evlist); diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c index 6e4f63b0da4a..238fa3876805 100644 --- a/tools/perf/builtin-evlist.c +++ b/tools/perf/builtin-evlist.c @@ -21,7 +21,7 @@ static int __cmd_evlist(const char *file_name, struct perf_attr_details *details) { struct perf_session *session; - struct perf_evsel *pos; + struct evsel *pos; struct perf_data data = { .path = file_name, .mode = PERF_DATA_MODE_READ, @@ -36,7 +36,7 @@ static int __cmd_evlist(const char *file_name, struct perf_attr_details *details evlist__for_each_entry(session->evlist, pos) { perf_evsel__fprintf(pos, details, stdout); - if (pos->attr.type == PERF_TYPE_TRACEPOINT) + if (pos->core.attr.type == PERF_TYPE_TRACEPOINT) has_tracepoint = true; } diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c index 019312810405..565db782c1b9 100644 --- a/tools/perf/builtin-ftrace.c +++ b/tools/perf/builtin-ftrace.c @@ -13,6 +13,7 @@ #include <signal.h> #include <fcntl.h> #include <poll.h> +#include <linux/capability.h> #include "debug.h" #include <subcmd/parse-options.h> @@ -21,13 +22,14 @@ #include "target.h" #include "cpumap.h" #include "thread_map.h" +#include "util/cap.h" #include "util/config.h" #define DEFAULT_TRACER "function_graph" struct perf_ftrace { - struct perf_evlist *evlist; + struct evlist *evlist; struct target target; const char *tracer; struct list_head filters; @@ -156,16 +158,16 @@ static int set_tracing_pid(struct perf_ftrace *ftrace) if (target__has_cpu(&ftrace->target)) return 0; - for (i = 0; i < thread_map__nr(ftrace->evlist->threads); i++) { + for (i = 0; i < perf_thread_map__nr(ftrace->evlist->core.threads); i++) { scnprintf(buf, sizeof(buf), "%d", - ftrace->evlist->threads->map[i]); + ftrace->evlist->core.threads->map[i]); if (append_tracing_file("set_ftrace_pid", buf) < 0) return -1; } return 0; } -static int set_tracing_cpumask(struct cpu_map *cpumap) +static int set_tracing_cpumask(struct perf_cpu_map *cpumap) { char *cpumask; size_t mask_size; @@ -192,7 +194,7 @@ static int set_tracing_cpumask(struct cpu_map *cpumap) static int set_tracing_cpu(struct perf_ftrace *ftrace) { - struct cpu_map *cpumap = ftrace->evlist->cpus; + struct perf_cpu_map *cpumap = ftrace->evlist->core.cpus; if (!target__has_cpu(&ftrace->target)) return 0; @@ -202,11 +204,11 @@ static int set_tracing_cpu(struct perf_ftrace *ftrace) static int reset_tracing_cpu(void) { - struct cpu_map *cpumap = cpu_map__new(NULL); + struct perf_cpu_map *cpumap = perf_cpu_map__new(NULL); int ret; ret = set_tracing_cpumask(cpumap); - cpu_map__put(cpumap); + perf_cpu_map__put(cpumap); return ret; } @@ -281,8 +283,14 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv) .events = POLLIN, }; - if (geteuid() != 0) { - pr_err("ftrace only works for root!\n"); + if (!perf_cap__capable(CAP_SYS_ADMIN)) { + pr_err("ftrace only works for %s!\n", +#ifdef HAVE_LIBCAP_SUPPORT + "users with the SYS_ADMIN capability" +#else + "root" +#endif + ); return -1; } @@ -495,7 +503,7 @@ int cmd_ftrace(int argc, const char **argv) goto out_delete_filters; } - ftrace.evlist = perf_evlist__new(); + ftrace.evlist = evlist__new(); if (ftrace.evlist == NULL) { ret = -ENOMEM; goto out_delete_filters; @@ -508,7 +516,7 @@ int cmd_ftrace(int argc, const char **argv) ret = __cmd_ftrace(&ftrace, argc, argv); out_delete_evlist: - perf_evlist__delete(ftrace.evlist); + evlist__delete(ftrace.evlist); out_delete_filters: delete_filter_func(&ftrace.filters); diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index f4591a1438b4..040142581d20 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -96,7 +96,7 @@ static int perf_event__repipe_op2_synth(struct perf_session *session, static int perf_event__repipe_attr(struct perf_tool *tool, union perf_event *event, - struct perf_evlist **pevlist) + struct evlist **pevlist) { struct perf_inject *inject = container_of(tool, struct perf_inject, tool); @@ -215,13 +215,13 @@ static int perf_event__drop_aux(struct perf_tool *tool, typedef int (*inject_handler)(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct machine *machine); static int perf_event__repipe_sample(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct machine *machine) { if (evsel && evsel->handler) { @@ -424,7 +424,7 @@ static int dso__inject_build_id(struct dso *dso, struct perf_tool *tool, static int perf_event__inject_buildid(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, - struct perf_evsel *evsel __maybe_unused, + struct evsel *evsel __maybe_unused, struct machine *machine) { struct addr_location al; @@ -465,7 +465,7 @@ repipe: static int perf_inject__sched_process_exit(struct perf_tool *tool, union perf_event *event __maybe_unused, struct perf_sample *sample, - struct perf_evsel *evsel __maybe_unused, + struct evsel *evsel __maybe_unused, struct machine *machine __maybe_unused) { struct perf_inject *inject = container_of(tool, struct perf_inject, tool); @@ -485,7 +485,7 @@ static int perf_inject__sched_process_exit(struct perf_tool *tool, static int perf_inject__sched_switch(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct machine *machine) { struct perf_inject *inject = container_of(tool, struct perf_inject, tool); @@ -509,7 +509,7 @@ static int perf_inject__sched_switch(struct perf_tool *tool, static int perf_inject__sched_stat(struct perf_tool *tool, union perf_event *event __maybe_unused, struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct machine *machine) { struct event_entry *ent; @@ -530,8 +530,8 @@ found: sample_sw.period = sample->period; sample_sw.time = sample->time; - perf_event__synthesize_sample(event_sw, evsel->attr.sample_type, - evsel->attr.read_format, &sample_sw); + perf_event__synthesize_sample(event_sw, evsel->core.attr.sample_type, + evsel->core.attr.read_format, &sample_sw); build_id__mark_dso_hit(tool, event_sw, &sample_sw, evsel, machine); return perf_event__repipe(tool, event_sw, &sample_sw, machine); } @@ -541,10 +541,10 @@ static void sig_handler(int sig __maybe_unused) session_done = 1; } -static int perf_evsel__check_stype(struct perf_evsel *evsel, +static int perf_evsel__check_stype(struct evsel *evsel, u64 sample_type, const char *sample_msg) { - struct perf_event_attr *attr = &evsel->attr; + struct perf_event_attr *attr = &evsel->core.attr; const char *name = perf_evsel__name(evsel); if (!(attr->sample_type & sample_type)) { @@ -559,7 +559,7 @@ static int perf_evsel__check_stype(struct perf_evsel *evsel, static int drop_sample(struct perf_tool *tool __maybe_unused, union perf_event *event __maybe_unused, struct perf_sample *sample __maybe_unused, - struct perf_evsel *evsel __maybe_unused, + struct evsel *evsel __maybe_unused, struct machine *machine __maybe_unused) { return 0; @@ -567,8 +567,8 @@ static int drop_sample(struct perf_tool *tool __maybe_unused, static void strip_init(struct perf_inject *inject) { - struct perf_evlist *evlist = inject->session->evlist; - struct perf_evsel *evsel; + struct evlist *evlist = inject->session->evlist; + struct evsel *evsel; inject->tool.context_switch = perf_event__drop; @@ -576,10 +576,10 @@ static void strip_init(struct perf_inject *inject) evsel->handler = drop_sample; } -static bool has_tracking(struct perf_evsel *evsel) +static bool has_tracking(struct evsel *evsel) { - return evsel->attr.mmap || evsel->attr.mmap2 || evsel->attr.comm || - evsel->attr.task; + return evsel->core.attr.mmap || evsel->core.attr.mmap2 || evsel->core.attr.comm || + evsel->core.attr.task; } #define COMPAT_MASK (PERF_SAMPLE_ID | PERF_SAMPLE_TID | PERF_SAMPLE_TIME | \ @@ -590,10 +590,10 @@ static bool has_tracking(struct perf_evsel *evsel) * their selected event to exist, except if there is only 1 selected event left * and it has a compatible sample type. */ -static bool ok_to_remove(struct perf_evlist *evlist, - struct perf_evsel *evsel_to_remove) +static bool ok_to_remove(struct evlist *evlist, + struct evsel *evsel_to_remove) { - struct perf_evsel *evsel; + struct evsel *evsel; int cnt = 0; bool ok = false; @@ -603,8 +603,8 @@ static bool ok_to_remove(struct perf_evlist *evlist, evlist__for_each_entry(evlist, evsel) { if (evsel->handler != drop_sample) { cnt += 1; - if ((evsel->attr.sample_type & COMPAT_MASK) == - (evsel_to_remove->attr.sample_type & COMPAT_MASK)) + if ((evsel->core.attr.sample_type & COMPAT_MASK) == + (evsel_to_remove->core.attr.sample_type & COMPAT_MASK)) ok = true; } } @@ -614,16 +614,16 @@ static bool ok_to_remove(struct perf_evlist *evlist, static void strip_fini(struct perf_inject *inject) { - struct perf_evlist *evlist = inject->session->evlist; - struct perf_evsel *evsel, *tmp; + struct evlist *evlist = inject->session->evlist; + struct evsel *evsel, *tmp; /* Remove non-synthesized evsels if possible */ evlist__for_each_entry_safe(evlist, tmp, evsel) { if (evsel->handler == drop_sample && ok_to_remove(evlist, evsel)) { pr_debug("Deleting %s\n", perf_evsel__name(evsel)); - perf_evlist__remove(evlist, evsel); - perf_evsel__delete(evsel); + evlist__remove(evlist, evsel); + evsel__delete(evsel); } } } @@ -651,7 +651,7 @@ static int __cmd_inject(struct perf_inject *inject) if (inject->build_ids) { inject->tool.sample = perf_event__inject_buildid; } else if (inject->sched_stat) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(session->evlist, evsel) { const char *name = perf_evsel__name(evsel); @@ -712,7 +712,7 @@ static int __cmd_inject(struct perf_inject *inject) * remove the evsel. */ if (inject->itrace_synth_opts.set) { - struct perf_evsel *evsel; + struct evsel *evsel; perf_header__clear_feat(&session->header, HEADER_AUXTRACE); @@ -724,8 +724,8 @@ static int __cmd_inject(struct perf_inject *inject) if (evsel) { pr_debug("Deleting %s\n", perf_evsel__name(evsel)); - perf_evlist__remove(session->evlist, evsel); - perf_evsel__delete(evsel); + evlist__remove(session->evlist, evsel); + evsel__delete(evsel); } if (inject->strip) strip_fini(inject); diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index 9e5e60898083..46f828936120 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -166,7 +166,7 @@ static int insert_caller_stat(unsigned long call_site, return 0; } -static int perf_evsel__process_alloc_event(struct perf_evsel *evsel, +static int perf_evsel__process_alloc_event(struct evsel *evsel, struct perf_sample *sample) { unsigned long ptr = perf_evsel__intval(evsel, sample, "ptr"), @@ -185,7 +185,7 @@ static int perf_evsel__process_alloc_event(struct perf_evsel *evsel, return 0; } -static int perf_evsel__process_alloc_node_event(struct perf_evsel *evsel, +static int perf_evsel__process_alloc_node_event(struct evsel *evsel, struct perf_sample *sample) { int ret = perf_evsel__process_alloc_event(evsel, sample); @@ -229,7 +229,7 @@ static struct alloc_stat *search_alloc_stat(unsigned long ptr, return NULL; } -static int perf_evsel__process_free_event(struct perf_evsel *evsel, +static int perf_evsel__process_free_event(struct evsel *evsel, struct perf_sample *sample) { unsigned long ptr = perf_evsel__intval(evsel, sample, "ptr"); @@ -381,7 +381,7 @@ static int build_alloc_func_list(void) * Find first non-memory allocation function from callchain. * The allocation functions are in the 'alloc_func_list'. */ -static u64 find_callsite(struct perf_evsel *evsel, struct perf_sample *sample) +static u64 find_callsite(struct evsel *evsel, struct perf_sample *sample) { struct addr_location al; struct machine *machine = &kmem_session->machines.host; @@ -728,7 +728,7 @@ static char *compact_gfp_string(unsigned long gfp_flags) return NULL; } -static int parse_gfp_flags(struct perf_evsel *evsel, struct perf_sample *sample, +static int parse_gfp_flags(struct evsel *evsel, struct perf_sample *sample, unsigned int gfp_flags) { struct tep_record record = { @@ -779,7 +779,7 @@ static int parse_gfp_flags(struct perf_evsel *evsel, struct perf_sample *sample, return 0; } -static int perf_evsel__process_page_alloc_event(struct perf_evsel *evsel, +static int perf_evsel__process_page_alloc_event(struct evsel *evsel, struct perf_sample *sample) { u64 page; @@ -852,7 +852,7 @@ static int perf_evsel__process_page_alloc_event(struct perf_evsel *evsel, return 0; } -static int perf_evsel__process_page_free_event(struct perf_evsel *evsel, +static int perf_evsel__process_page_free_event(struct evsel *evsel, struct perf_sample *sample) { u64 page; @@ -930,13 +930,13 @@ static bool perf_kmem__skip_sample(struct perf_sample *sample) return false; } -typedef int (*tracepoint_handler)(struct perf_evsel *evsel, +typedef int (*tracepoint_handler)(struct evsel *evsel, struct perf_sample *sample); static int process_sample_event(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct machine *machine) { int err = 0; @@ -1363,8 +1363,8 @@ static void sort_result(void) static int __cmd_kmem(struct perf_session *session) { int err = -EINVAL; - struct perf_evsel *evsel; - const struct perf_evsel_str_handler kmem_tracepoints[] = { + struct evsel *evsel; + const struct evsel_str_handler kmem_tracepoints[] = { /* slab allocator */ { "kmem:kmalloc", perf_evsel__process_alloc_event, }, { "kmem:kmem_cache_alloc", perf_evsel__process_alloc_event, }, @@ -1967,7 +1967,7 @@ int cmd_kmem(int argc, const char **argv) } if (kmem_page) { - struct perf_evsel *evsel; + struct evsel *evsel; evsel = perf_evlist__find_tracepoint_by_name(session->evlist, "kmem:mm_page_alloc"); diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index b33c83489120..69d16ac852c3 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -57,7 +57,7 @@ static const char *get_filename_for_perf_kvm(void) #ifdef HAVE_KVM_STAT_SUPPORT #include "util/kvm-stat.h" -void exit_event_get_key(struct perf_evsel *evsel, +void exit_event_get_key(struct evsel *evsel, struct perf_sample *sample, struct event_key *key) { @@ -65,12 +65,12 @@ void exit_event_get_key(struct perf_evsel *evsel, key->key = perf_evsel__intval(evsel, sample, kvm_exit_reason); } -bool kvm_exit_event(struct perf_evsel *evsel) +bool kvm_exit_event(struct evsel *evsel) { return !strcmp(evsel->name, kvm_exit_trace); } -bool exit_event_begin(struct perf_evsel *evsel, +bool exit_event_begin(struct evsel *evsel, struct perf_sample *sample, struct event_key *key) { if (kvm_exit_event(evsel)) { @@ -81,12 +81,12 @@ bool exit_event_begin(struct perf_evsel *evsel, return false; } -bool kvm_entry_event(struct perf_evsel *evsel) +bool kvm_entry_event(struct evsel *evsel) { return !strcmp(evsel->name, kvm_entry_trace); } -bool exit_event_end(struct perf_evsel *evsel, +bool exit_event_end(struct evsel *evsel, struct perf_sample *sample __maybe_unused, struct event_key *key __maybe_unused) { @@ -286,7 +286,7 @@ static bool update_kvm_event(struct kvm_event *event, int vcpu_id, } static bool is_child_event(struct perf_kvm_stat *kvm, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample, struct event_key *key) { @@ -396,7 +396,7 @@ static bool handle_end_event(struct perf_kvm_stat *kvm, static struct vcpu_event_record *per_vcpu_record(struct thread *thread, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample) { /* Only kvm_entry records vcpu id. */ @@ -419,7 +419,7 @@ struct vcpu_event_record *per_vcpu_record(struct thread *thread, static bool handle_kvm_event(struct perf_kvm_stat *kvm, struct thread *thread, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample) { struct vcpu_event_record *vcpu_record; @@ -672,7 +672,7 @@ static bool skip_sample(struct perf_kvm_stat *kvm, static int process_sample_event(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct machine *machine) { int err = 0; @@ -743,7 +743,7 @@ static bool verify_vcpu(int vcpu) static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx, u64 *mmap_time) { - struct perf_evlist *evlist = kvm->evlist; + struct evlist *evlist = kvm->evlist; union perf_event *event; struct perf_mmap *md; u64 timestamp; @@ -972,7 +972,7 @@ static int kvm_events_live_report(struct perf_kvm_stat *kvm) goto out; /* everything is good - enable the events and process */ - perf_evlist__enable(kvm->evlist); + evlist__enable(kvm->evlist); while (!done) { struct fdarray *fda = &kvm->evlist->pollfd; @@ -993,7 +993,7 @@ static int kvm_events_live_report(struct perf_kvm_stat *kvm) err = fdarray__poll(fda, 100); } - perf_evlist__disable(kvm->evlist); + evlist__disable(kvm->evlist); if (err == 0) { sort_result(kvm); @@ -1011,8 +1011,8 @@ out: static int kvm_live_open_events(struct perf_kvm_stat *kvm) { int err, rc = -1; - struct perf_evsel *pos; - struct perf_evlist *evlist = kvm->evlist; + struct evsel *pos; + struct evlist *evlist = kvm->evlist; char sbuf[STRERR_BUFSIZE]; perf_evlist__config(evlist, &kvm->opts, NULL); @@ -1022,7 +1022,7 @@ static int kvm_live_open_events(struct perf_kvm_stat *kvm) * This command processes KVM tracepoints from host only */ evlist__for_each_entry(evlist, pos) { - struct perf_event_attr *attr = &pos->attr; + struct perf_event_attr *attr = &pos->core.attr; /* make sure these *are* set */ perf_evsel__set_sample_bit(pos, TID); @@ -1048,7 +1048,7 @@ static int kvm_live_open_events(struct perf_kvm_stat *kvm) attr->disabled = 1; } - err = perf_evlist__open(evlist); + err = evlist__open(evlist); if (err < 0) { printf("Couldn't create the events: %s\n", str_error_r(errno, sbuf, sizeof(sbuf))); @@ -1058,7 +1058,7 @@ static int kvm_live_open_events(struct perf_kvm_stat *kvm) if (perf_evlist__mmap(evlist, kvm->opts.mmap_pages) < 0) { ui__error("Failed to mmap the events: %s\n", str_error_r(errno, sbuf, sizeof(sbuf))); - perf_evlist__close(evlist); + evlist__close(evlist); goto out; } @@ -1283,14 +1283,14 @@ kvm_events_report(struct perf_kvm_stat *kvm, int argc, const char **argv) } #ifdef HAVE_TIMERFD_SUPPORT -static struct perf_evlist *kvm_live_event_list(void) +static struct evlist *kvm_live_event_list(void) { - struct perf_evlist *evlist; + struct evlist *evlist; char *tp, *name, *sys; int err = -1; const char * const *events_tp; - evlist = perf_evlist__new(); + evlist = evlist__new(); if (evlist == NULL) return NULL; @@ -1325,7 +1325,7 @@ static struct perf_evlist *kvm_live_event_list(void) out: if (err) { - perf_evlist__delete(evlist); + evlist__delete(evlist); evlist = NULL; } @@ -1450,7 +1450,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm, perf_session__set_id_hdr_size(kvm->session); ordered_events__set_copy_on_queue(&kvm->session->ordered_events, true); machine__synthesize_threads(&kvm->session->machines.host, &kvm->opts.target, - kvm->evlist->threads, false, 1); + kvm->evlist->core.threads, false, 1); err = kvm_live_open_events(kvm); if (err) goto out; @@ -1460,7 +1460,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm, out: perf_session__delete(kvm->session); kvm->session = NULL; - perf_evlist__delete(kvm->evlist); + evlist__delete(kvm->evlist); return err; } diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index 574e30ec6d7c..38500bff4423 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -347,16 +347,16 @@ alloc_failed: } struct trace_lock_handler { - int (*acquire_event)(struct perf_evsel *evsel, + int (*acquire_event)(struct evsel *evsel, struct perf_sample *sample); - int (*acquired_event)(struct perf_evsel *evsel, + int (*acquired_event)(struct evsel *evsel, struct perf_sample *sample); - int (*contended_event)(struct perf_evsel *evsel, + int (*contended_event)(struct evsel *evsel, struct perf_sample *sample); - int (*release_event)(struct perf_evsel *evsel, + int (*release_event)(struct evsel *evsel, struct perf_sample *sample); }; @@ -396,7 +396,7 @@ enum acquire_flags { READ_LOCK = 2, }; -static int report_lock_acquire_event(struct perf_evsel *evsel, +static int report_lock_acquire_event(struct evsel *evsel, struct perf_sample *sample) { void *addr; @@ -468,7 +468,7 @@ end: return 0; } -static int report_lock_acquired_event(struct perf_evsel *evsel, +static int report_lock_acquired_event(struct evsel *evsel, struct perf_sample *sample) { void *addr; @@ -531,7 +531,7 @@ end: return 0; } -static int report_lock_contended_event(struct perf_evsel *evsel, +static int report_lock_contended_event(struct evsel *evsel, struct perf_sample *sample) { void *addr; @@ -586,7 +586,7 @@ end: return 0; } -static int report_lock_release_event(struct perf_evsel *evsel, +static int report_lock_release_event(struct evsel *evsel, struct perf_sample *sample) { void *addr; @@ -656,7 +656,7 @@ static struct trace_lock_handler report_lock_ops = { static struct trace_lock_handler *trace_handler; -static int perf_evsel__process_lock_acquire(struct perf_evsel *evsel, +static int perf_evsel__process_lock_acquire(struct evsel *evsel, struct perf_sample *sample) { if (trace_handler->acquire_event) @@ -664,7 +664,7 @@ static int perf_evsel__process_lock_acquire(struct perf_evsel *evsel, return 0; } -static int perf_evsel__process_lock_acquired(struct perf_evsel *evsel, +static int perf_evsel__process_lock_acquired(struct evsel *evsel, struct perf_sample *sample) { if (trace_handler->acquired_event) @@ -672,7 +672,7 @@ static int perf_evsel__process_lock_acquired(struct perf_evsel *evsel, return 0; } -static int perf_evsel__process_lock_contended(struct perf_evsel *evsel, +static int perf_evsel__process_lock_contended(struct evsel *evsel, struct perf_sample *sample) { if (trace_handler->contended_event) @@ -680,7 +680,7 @@ static int perf_evsel__process_lock_contended(struct perf_evsel *evsel, return 0; } -static int perf_evsel__process_lock_release(struct perf_evsel *evsel, +static int perf_evsel__process_lock_release(struct evsel *evsel, struct perf_sample *sample) { if (trace_handler->release_event) @@ -806,13 +806,13 @@ static int dump_info(void) return rc; } -typedef int (*tracepoint_handler)(struct perf_evsel *evsel, +typedef int (*tracepoint_handler)(struct evsel *evsel, struct perf_sample *sample); static int process_sample_event(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct machine *machine) { int err = 0; @@ -847,7 +847,7 @@ static void sort_result(void) } } -static const struct perf_evsel_str_handler lock_tracepoints[] = { +static const struct evsel_str_handler lock_tracepoints[] = { { "lock:lock_acquire", perf_evsel__process_lock_acquire, }, /* CONFIG_LOCKDEP */ { "lock:lock_acquired", perf_evsel__process_lock_acquired, }, /* CONFIG_LOCKDEP, CONFIG_LOCK_STAT */ { "lock:lock_contended", perf_evsel__process_lock_contended, }, /* CONFIG_LOCKDEP, CONFIG_LOCK_STAT */ diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c index f45c8b502f63..9e60eda9297d 100644 --- a/tools/perf/builtin-mem.c +++ b/tools/perf/builtin-mem.c @@ -230,7 +230,7 @@ out_put: static int process_sample_event(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, - struct perf_evsel *evsel __maybe_unused, + struct evsel *evsel __maybe_unused, struct machine *machine) { return dump_raw_samples(tool, event, sample, machine); diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 8779cee58185..f71631f2bcb5 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -73,7 +73,7 @@ struct record { u64 bytes_written; struct perf_data data; struct auxtrace_record *itr; - struct perf_evlist *evlist; + struct evlist *evlist; struct perf_session *session; int realtime_prio; bool no_buildid; @@ -346,7 +346,7 @@ static void record__aio_set_pos(int trace_fd, off_t pos) static void record__aio_mmap_read_sync(struct record *rec) { int i; - struct perf_evlist *evlist = rec->evlist; + struct evlist *evlist = rec->evlist; struct perf_mmap *maps = evlist->mmap; if (!record__aio_enabled(rec)) @@ -613,19 +613,35 @@ out: return rc; } -static void record__read_auxtrace_snapshot(struct record *rec) +static void record__read_auxtrace_snapshot(struct record *rec, bool on_exit) { pr_debug("Recording AUX area tracing snapshot\n"); if (record__auxtrace_read_snapshot_all(rec) < 0) { trigger_error(&auxtrace_snapshot_trigger); } else { - if (auxtrace_record__snapshot_finish(rec->itr)) + if (auxtrace_record__snapshot_finish(rec->itr, on_exit)) trigger_error(&auxtrace_snapshot_trigger); else trigger_ready(&auxtrace_snapshot_trigger); } } +static int record__auxtrace_snapshot_exit(struct record *rec) +{ + if (trigger_is_error(&auxtrace_snapshot_trigger)) + return 0; + + if (!auxtrace_record__snapshot_started && + auxtrace_record__snapshot_start(rec->itr)) + return -1; + + record__read_auxtrace_snapshot(rec, true); + if (trigger_is_error(&auxtrace_snapshot_trigger)) + return -1; + + return 0; +} + static int record__auxtrace_init(struct record *rec) { int err; @@ -654,7 +670,8 @@ int record__auxtrace_mmap_read(struct record *rec __maybe_unused, } static inline -void record__read_auxtrace_snapshot(struct record *rec __maybe_unused) +void record__read_auxtrace_snapshot(struct record *rec __maybe_unused, + bool on_exit __maybe_unused) { } @@ -664,6 +681,12 @@ int auxtrace_record__snapshot_start(struct auxtrace_record *itr __maybe_unused) return 0; } +static inline +int record__auxtrace_snapshot_exit(struct record *rec __maybe_unused) +{ + return 0; +} + static int record__auxtrace_init(struct record *rec __maybe_unused) { return 0; @@ -672,7 +695,7 @@ static int record__auxtrace_init(struct record *rec __maybe_unused) #endif static int record__mmap_evlist(struct record *rec, - struct perf_evlist *evlist) + struct evlist *evlist) { struct record_opts *opts = &rec->opts; char msg[512]; @@ -713,8 +736,8 @@ static int record__mmap(struct record *rec) static int record__open(struct record *rec) { char msg[BUFSIZ]; - struct perf_evsel *pos; - struct perf_evlist *evlist = rec->evlist; + struct evsel *pos; + struct evlist *evlist = rec->evlist; struct perf_session *session = rec->session; struct record_opts *opts = &rec->opts; int rc = 0; @@ -732,14 +755,14 @@ static int record__open(struct record *rec) pos->tracking = 0; pos = perf_evlist__last(evlist); pos->tracking = 1; - pos->attr.enable_on_exec = 1; + pos->core.attr.enable_on_exec = 1; } perf_evlist__config(evlist, opts, &callchain_param); evlist__for_each_entry(evlist, pos) { try_again: - if (perf_evsel__open(pos, pos->cpus, pos->threads) < 0) { + if (evsel__open(pos, pos->core.cpus, pos->core.threads) < 0) { if (perf_evsel__fallback(pos, errno, msg, sizeof(msg))) { if (verbose > 0) ui__warning("%s\n", msg); @@ -782,7 +805,7 @@ out: static int process_sample_event(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct machine *machine) { struct record *rec = container_of(tool, struct record, tool); @@ -904,7 +927,7 @@ static size_t zstd_compress(struct perf_session *session, void *dst, size_t dst_ return compressed; } -static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evlist, +static int record__mmap_read_evlist(struct record *rec, struct evlist *evlist, bool overwrite, bool synch) { u64 bytes_written = rec->bytes_written; @@ -1002,7 +1025,7 @@ static void record__init_features(struct record *rec) if (rec->no_buildid) perf_header__clear_feat(&session->header, HEADER_BUILD_ID); - if (!have_tracepoints(&rec->evlist->entries)) + if (!have_tracepoints(&rec->evlist->core.entries)) perf_header__clear_feat(&session->header, HEADER_TRACING_DATA); if (!rec->opts.branch_stack) @@ -1047,7 +1070,7 @@ record__finish_output(struct record *rec) static int record__synthesize_workload(struct record *rec, bool tail) { int err; - struct thread_map *thread_map; + struct perf_thread_map *thread_map; if (rec->opts.tail_synthesize != tail) return 0; @@ -1060,7 +1083,7 @@ static int record__synthesize_workload(struct record *rec, bool tail) process_synthesized_event, &rec->session->machines.host, rec->opts.sample_address); - thread_map__put(thread_map); + perf_thread_map__put(thread_map); return err; } @@ -1165,7 +1188,7 @@ perf_event__synth_time_conv(const struct perf_event_mmap_page *pc __maybe_unused } static const struct perf_event_mmap_page * -perf_evlist__pick_pc(struct perf_evlist *evlist) +perf_evlist__pick_pc(struct evlist *evlist) { if (evlist) { if (evlist->mmap && evlist->mmap[0].base) @@ -1218,7 +1241,7 @@ static int record__synthesize(struct record *rec, bool tail) return err; } - if (have_tracepoints(&rec->evlist->entries)) { + if (have_tracepoints(&rec->evlist->core.entries)) { /* * FIXME err <= 0 here actually means that * there were no tracepoints so its not really @@ -1275,7 +1298,7 @@ static int record__synthesize(struct record *rec, bool tail) if (err) goto out; - err = perf_event__synthesize_thread_map2(&rec->tool, rec->evlist->threads, + err = perf_event__synthesize_thread_map2(&rec->tool, rec->evlist->core.threads, process_synthesized_event, NULL); if (err < 0) { @@ -1283,7 +1306,7 @@ static int record__synthesize(struct record *rec, bool tail) return err; } - err = perf_event__synthesize_cpu_map(&rec->tool, rec->evlist->cpus, + err = perf_event__synthesize_cpu_map(&rec->tool, rec->evlist->core.cpus, process_synthesized_event, NULL); if (err < 0) { pr_err("Couldn't synthesize cpu map.\n"); @@ -1295,7 +1318,7 @@ static int record__synthesize(struct record *rec, bool tail) if (err < 0) pr_warning("Couldn't synthesize bpf events.\n"); - err = __machine__synthesize_threads(machine, tool, &opts->target, rec->evlist->threads, + err = __machine__synthesize_threads(machine, tool, &opts->target, rec->evlist->core.threads, process_synthesized_event, opts->sample_address, 1); out: @@ -1313,7 +1336,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) struct perf_data *data = &rec->data; struct perf_session *session; bool disabled = false, draining = false; - struct perf_evlist *sb_evlist = NULL; + struct evlist *sb_evlist = NULL; int fd; float ratio = 0; @@ -1375,7 +1398,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) * because we synthesize event name through the pipe * and need the id for that. */ - if (data->is_pipe && rec->evlist->nr_entries == 1) + if (data->is_pipe && rec->evlist->core.nr_entries == 1) rec->opts.sample_id = true; if (record__open(rec) != 0) { @@ -1453,7 +1476,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) * so don't spoil it by prematurely enabling them. */ if (!target__none(&opts->target) && !opts->initial_delay) - perf_evlist__enable(rec->evlist); + evlist__enable(rec->evlist); /* * Let the child rip @@ -1506,7 +1529,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) if (opts->initial_delay) { usleep(opts->initial_delay * USEC_PER_MSEC); - perf_evlist__enable(rec->evlist); + evlist__enable(rec->evlist); } trigger_ready(&auxtrace_snapshot_trigger); @@ -1536,7 +1559,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) if (auxtrace_record__snapshot_started) { auxtrace_record__snapshot_started = 0; if (!trigger_is_error(&auxtrace_snapshot_trigger)) - record__read_auxtrace_snapshot(rec); + record__read_auxtrace_snapshot(rec, false); if (trigger_is_error(&auxtrace_snapshot_trigger)) { pr_err("AUX area tracing snapshot failed\n"); err = -1; @@ -1605,13 +1628,17 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) */ if (done && !disabled && !target__none(&opts->target)) { trigger_off(&auxtrace_snapshot_trigger); - perf_evlist__disable(rec->evlist); + evlist__disable(rec->evlist); disabled = true; } } + trigger_off(&auxtrace_snapshot_trigger); trigger_off(&switch_output_trigger); + if (opts->auxtrace_snapshot_on_exit) + record__auxtrace_snapshot_exit(rec); + if (forks && workload_exec_errno) { char msg[STRERR_BUFSIZE]; const char *emsg = str_error_r(workload_exec_errno, msg, sizeof(msg)); @@ -2265,7 +2292,7 @@ int cmd_record(int argc, const char **argv) CPU_ZERO(&rec->affinity_mask); rec->opts.affinity = PERF_AFFINITY_SYS; - rec->evlist = perf_evlist__new(); + rec->evlist = evlist__new(); if (rec->evlist == NULL) return -ENOMEM; @@ -2386,7 +2413,7 @@ int cmd_record(int argc, const char **argv) if (record.opts.overwrite) record.opts.tail_synthesize = true; - if (rec->evlist->nr_entries == 0 && + if (rec->evlist->core.nr_entries == 0 && __perf_evlist__add_default(rec->evlist, !record.opts.no_samples) < 0) { pr_err("Not enough memory for event selector list\n"); goto out; @@ -2449,7 +2476,7 @@ int cmd_record(int argc, const char **argv) err = __cmd_record(&record, argc, argv); out: - perf_evlist__delete(rec->evlist); + evlist__delete(rec->evlist); symbol__exit(); auxtrace_record__free(rec->itr); return err; diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index abf0b9b8f566..79dfb1139f94 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -25,6 +25,7 @@ #include "util/debug.h" #include "util/evlist.h" #include "util/evsel.h" +#include "util/evswitch.h" #include "util/header.h" #include "util/session.h" #include "util/tool.h" @@ -60,6 +61,7 @@ struct report { struct perf_tool tool; struct perf_session *session; + struct evswitch evswitch; bool use_tui, use_gtk, use_stdio; bool show_full_info; bool show_threads; @@ -128,7 +130,7 @@ static int hist_iter__report_callback(struct hist_entry_iter *iter, int err = 0; struct report *rep = arg; struct hist_entry *he = iter->he; - struct perf_evsel *evsel = iter->evsel; + struct evsel *evsel = iter->evsel; struct perf_sample *sample = iter->sample; struct mem_info *mi; struct branch_info *bi; @@ -172,7 +174,7 @@ static int hist_iter__branch_callback(struct hist_entry_iter *iter, struct report *rep = arg; struct branch_info *bi; struct perf_sample *sample = iter->sample; - struct perf_evsel *evsel = iter->evsel; + struct evsel *evsel = iter->evsel; int err; if (!ui__has_annotation() && !rep->symbol_ipc) @@ -193,7 +195,7 @@ out: } static void setup_forced_leader(struct report *report, - struct perf_evlist *evlist) + struct evlist *evlist) { if (report->group_set) perf_evlist__force_leader(evlist); @@ -225,7 +227,7 @@ static int process_feature_event(struct perf_session *session, static int process_sample_event(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct machine *machine) { struct report *rep = container_of(tool, struct report, tool); @@ -243,6 +245,9 @@ static int process_sample_event(struct perf_tool *tool, return 0; } + if (evswitch__discard(&rep->evswitch, evsel)) + return 0; + if (machine__resolve(machine, &al, sample) < 0) { pr_debug("problem processing %d event, skipping it.\n", event->header.type); @@ -292,7 +297,7 @@ out_put: static int process_read_event(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample __maybe_unused, - struct perf_evsel *evsel, + struct evsel *evsel, struct machine *machine __maybe_unused) { struct report *rep = container_of(tool, struct report, tool); @@ -400,7 +405,7 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report char unit; 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); + struct evsel *evsel = hists_to_evsel(hists); char buf[512]; size_t size = sizeof(buf); int socked_id = hists->socket_filter; @@ -414,7 +419,7 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report } if (perf_evsel__is_group_event(evsel)) { - struct perf_evsel *pos; + struct evsel *pos; perf_evsel__group_desc(evsel, buf, size); evname = buf; @@ -436,7 +441,7 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report ret = fprintf(fp, "# Samples: %lu%c", nr_samples, unit); if (evname != NULL) { ret += fprintf(fp, " of event%s '%s'", - evsel->nr_members > 1 ? "s" : "", evname); + evsel->core.nr_members > 1 ? "s" : "", evname); } if (rep->time_str) @@ -459,11 +464,11 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report return ret + fprintf(fp, "\n#\n"); } -static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist, +static int perf_evlist__tty_browse_hists(struct evlist *evlist, struct report *rep, const char *help) { - struct perf_evsel *pos; + struct evsel *pos; if (!quiet) { fprintf(stdout, "#\n# Total Lost Samples: %" PRIu64 "\n#\n", @@ -532,7 +537,7 @@ static void report__warn_kptr_restrict(const struct report *rep) static int report__gtk_browse_hists(struct report *rep, const char *help) { - int (*hist_browser)(struct perf_evlist *evlist, const char *help, + int (*hist_browser)(struct evlist *evlist, const char *help, struct hist_browser_timer *timer, float min_pcnt); hist_browser = dlsym(perf_gtk_handle, "perf_evlist__gtk_browse_hists"); @@ -549,7 +554,7 @@ static int report__browse_hists(struct report *rep) { int ret; struct perf_session *session = rep->session; - struct perf_evlist *evlist = session->evlist; + struct evlist *evlist = session->evlist; const char *help = perf_tip(system_path(TIPDIR)); if (help == NULL) { @@ -586,7 +591,7 @@ static int report__browse_hists(struct report *rep) static int report__collapse_hists(struct report *rep) { struct ui_progress prog; - struct perf_evsel *pos; + struct evsel *pos; int ret = 0; ui_progress__init(&prog, rep->nr_entries, "Merging related events..."); @@ -623,7 +628,7 @@ static int hists__resort_cb(struct hist_entry *he, void *arg) struct symbol *sym = he->ms.sym; if (rep->symbol_ipc && sym && !sym->annotate2) { - struct perf_evsel *evsel = hists_to_evsel(he->hists); + struct evsel *evsel = hists_to_evsel(he->hists); symbol__annotate2(sym, he->ms.map, evsel, &annotation__default_options, NULL); @@ -635,7 +640,7 @@ static int hists__resort_cb(struct hist_entry *he, void *arg) static void report__output_resort(struct report *rep) { struct ui_progress prog; - struct perf_evsel *pos; + struct evsel *pos; ui_progress__init(&prog, rep->nr_entries, "Sorting events for output..."); @@ -818,7 +823,7 @@ static int __cmd_report(struct report *rep) { int ret; struct perf_session *session = rep->session; - struct perf_evsel *pos; + struct evsel *pos; struct perf_data *data = session->data; signal(SIGINT, sig_handler); @@ -1189,6 +1194,7 @@ int cmd_report(int argc, const char **argv) OPT_CALLBACK(0, "time-quantum", &symbol_conf.time_quantum, "time (ms|us|ns|s)", "Set time quantum for time sort key (default 100ms)", parse_time_quantum), + OPTS_EVSWITCH(&report.evswitch), OPT_END() }; struct perf_data data = { @@ -1257,6 +1263,10 @@ repeat: if (session == NULL) return -1; + ret = evswitch__init(&report.evswitch, session->evlist, stderr); + if (ret) + return ret; + if (zstd_init(&(session->zstd_data), 0) < 0) pr_warning("Decompression initialization failed. Reported data may be incomplete.\n"); @@ -1271,6 +1281,8 @@ repeat: has_br_stack = perf_header__has_feat(&session->header, HEADER_BRANCH_STACK); + if (perf_evlist__combined_sample_type(session->evlist) & PERF_SAMPLE_STACK_USER) + has_br_stack = false; setup_forced_leader(&report, session->evlist); diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 56d1907b1215..0d6b4c3b1a51 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -133,13 +133,13 @@ typedef int (*sort_fn_t)(struct work_atoms *, struct work_atoms *); struct perf_sched; struct trace_sched_handler { - int (*switch_event)(struct perf_sched *sched, struct perf_evsel *evsel, + int (*switch_event)(struct perf_sched *sched, struct evsel *evsel, struct perf_sample *sample, struct machine *machine); - int (*runtime_event)(struct perf_sched *sched, struct perf_evsel *evsel, + int (*runtime_event)(struct perf_sched *sched, struct evsel *evsel, struct perf_sample *sample, struct machine *machine); - int (*wakeup_event)(struct perf_sched *sched, struct perf_evsel *evsel, + int (*wakeup_event)(struct perf_sched *sched, struct evsel *evsel, struct perf_sample *sample, struct machine *machine); /* PERF_RECORD_FORK event, not sched_process_fork tracepoint */ @@ -147,7 +147,7 @@ struct trace_sched_handler { struct machine *machine); int (*migrate_task_event)(struct perf_sched *sched, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample, struct machine *machine); }; @@ -159,11 +159,11 @@ struct perf_sched_map { DECLARE_BITMAP(comp_cpus_mask, MAX_CPUS); int *comp_cpus; bool comp; - struct thread_map *color_pids; + struct perf_thread_map *color_pids; const char *color_pids_str; - struct cpu_map *color_cpus; + struct perf_cpu_map *color_cpus; const char *color_cpus_str; - struct cpu_map *cpus; + struct perf_cpu_map *cpus; const char *cpus_str; }; @@ -799,7 +799,7 @@ static void test_calibrations(struct perf_sched *sched) static int replay_wakeup_event(struct perf_sched *sched, - struct perf_evsel *evsel, struct perf_sample *sample, + struct evsel *evsel, struct perf_sample *sample, struct machine *machine __maybe_unused) { const char *comm = perf_evsel__strval(evsel, sample, "comm"); @@ -820,7 +820,7 @@ replay_wakeup_event(struct perf_sched *sched, } static int replay_switch_event(struct perf_sched *sched, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample, struct machine *machine __maybe_unused) { @@ -1093,7 +1093,7 @@ add_sched_in_event(struct work_atoms *atoms, u64 timestamp) } static int latency_switch_event(struct perf_sched *sched, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample, struct machine *machine) { @@ -1163,7 +1163,7 @@ out_put: } static int latency_runtime_event(struct perf_sched *sched, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample, struct machine *machine) { @@ -1198,7 +1198,7 @@ out_put: } static int latency_wakeup_event(struct perf_sched *sched, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample, struct machine *machine) { @@ -1259,7 +1259,7 @@ out_put: } static int latency_migrate_task_event(struct perf_sched *sched, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample, struct machine *machine) { @@ -1470,7 +1470,7 @@ again: } static int process_sched_wakeup_event(struct perf_tool *tool, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample, struct machine *machine) { @@ -1514,7 +1514,7 @@ map__findnew_thread(struct perf_sched *sched, struct machine *machine, pid_t pid return thread; } -static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel, +static int map_switch_event(struct perf_sched *sched, struct evsel *evsel, struct perf_sample *sample, struct machine *machine) { const u32 next_pid = perf_evsel__intval(evsel, sample, "next_pid"); @@ -1655,7 +1655,7 @@ out: } static int process_sched_switch_event(struct perf_tool *tool, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample, struct machine *machine) { @@ -1681,7 +1681,7 @@ static int process_sched_switch_event(struct perf_tool *tool, } static int process_sched_runtime_event(struct perf_tool *tool, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample, struct machine *machine) { @@ -1711,7 +1711,7 @@ static int perf_sched__process_fork_event(struct perf_tool *tool, } static int process_sched_migrate_task_event(struct perf_tool *tool, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample, struct machine *machine) { @@ -1724,14 +1724,14 @@ static int process_sched_migrate_task_event(struct perf_tool *tool, } typedef int (*tracepoint_handler)(struct perf_tool *tool, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample, struct machine *machine); static int perf_sched__process_tracepoint_sample(struct perf_tool *tool __maybe_unused, union perf_event *event __maybe_unused, struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct machine *machine) { int err = 0; @@ -1777,7 +1777,7 @@ static int perf_sched__process_comm(struct perf_tool *tool __maybe_unused, static int perf_sched__read_events(struct perf_sched *sched) { - const struct perf_evsel_str_handler handlers[] = { + const struct evsel_str_handler handlers[] = { { "sched:sched_switch", process_sched_switch_event, }, { "sched:sched_stat_runtime", process_sched_runtime_event, }, { "sched:sched_wakeup", process_sched_wakeup_event, }, @@ -1839,7 +1839,7 @@ static inline void print_sched_time(unsigned long long nsecs, int width) * returns runtime data for event, allocating memory for it the * first time it is used. */ -static struct evsel_runtime *perf_evsel__get_runtime(struct perf_evsel *evsel) +static struct evsel_runtime *perf_evsel__get_runtime(struct evsel *evsel) { struct evsel_runtime *r = evsel->priv; @@ -1854,7 +1854,7 @@ static struct evsel_runtime *perf_evsel__get_runtime(struct perf_evsel *evsel) /* * save last time event was seen per cpu */ -static void perf_evsel__save_time(struct perf_evsel *evsel, +static void perf_evsel__save_time(struct evsel *evsel, u64 timestamp, u32 cpu) { struct evsel_runtime *r = perf_evsel__get_runtime(evsel); @@ -1881,7 +1881,7 @@ static void perf_evsel__save_time(struct perf_evsel *evsel, } /* returns last time this event was seen on the given cpu */ -static u64 perf_evsel__get_time(struct perf_evsel *evsel, u32 cpu) +static u64 perf_evsel__get_time(struct evsel *evsel, u32 cpu) { struct evsel_runtime *r = perf_evsel__get_runtime(evsel); @@ -1988,7 +1988,7 @@ static char task_state_char(struct thread *thread, int state) } static void timehist_print_sample(struct perf_sched *sched, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample, struct addr_location *al, struct thread *thread, @@ -2121,7 +2121,7 @@ static void timehist_update_runtime_stats(struct thread_runtime *r, } static bool is_idle_sample(struct perf_sample *sample, - struct perf_evsel *evsel) + struct evsel *evsel) { /* pid 0 == swapper == idle task */ if (strcmp(perf_evsel__name(evsel), "sched:sched_switch") == 0) @@ -2132,7 +2132,7 @@ static bool is_idle_sample(struct perf_sample *sample, static void save_task_callchain(struct perf_sched *sched, struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct machine *machine) { struct callchain_cursor *cursor = &callchain_cursor; @@ -2286,7 +2286,7 @@ static void save_idle_callchain(struct perf_sched *sched, static struct thread *timehist_get_thread(struct perf_sched *sched, struct perf_sample *sample, struct machine *machine, - struct perf_evsel *evsel) + struct evsel *evsel) { struct thread *thread; @@ -2332,7 +2332,7 @@ static struct thread *timehist_get_thread(struct perf_sched *sched, static bool timehist_skip_sample(struct perf_sched *sched, struct thread *thread, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample) { bool rc = false; @@ -2354,7 +2354,7 @@ static bool timehist_skip_sample(struct perf_sched *sched, } static void timehist_print_wakeup_event(struct perf_sched *sched, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample, struct machine *machine, struct thread *awakened) @@ -2389,7 +2389,7 @@ static void timehist_print_wakeup_event(struct perf_sched *sched, static int timehist_sched_wakeup_event(struct perf_tool *tool, union perf_event *event __maybe_unused, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample, struct machine *machine) { @@ -2419,7 +2419,7 @@ static int timehist_sched_wakeup_event(struct perf_tool *tool, } static void timehist_print_migration_event(struct perf_sched *sched, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample, struct machine *machine, struct thread *migrated) @@ -2473,7 +2473,7 @@ static void timehist_print_migration_event(struct perf_sched *sched, static int timehist_migrate_task_event(struct perf_tool *tool, union perf_event *event __maybe_unused, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample, struct machine *machine) { @@ -2501,7 +2501,7 @@ static int timehist_migrate_task_event(struct perf_tool *tool, static int timehist_sched_change_event(struct perf_tool *tool, union perf_event *event, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample, struct machine *machine) { @@ -2627,7 +2627,7 @@ out: static int timehist_sched_switch_event(struct perf_tool *tool, union perf_event *event, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample, struct machine *machine __maybe_unused) { @@ -2897,14 +2897,14 @@ static void timehist_print_summary(struct perf_sched *sched, typedef int (*sched_handler)(struct perf_tool *tool, union perf_event *event, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample, struct machine *machine); static int perf_timehist__process_sample(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct machine *machine) { struct perf_sched *sched = container_of(tool, struct perf_sched, tool); @@ -2924,12 +2924,12 @@ static int perf_timehist__process_sample(struct perf_tool *tool, } static int timehist_check_attr(struct perf_sched *sched, - struct perf_evlist *evlist) + struct evlist *evlist) { - struct perf_evsel *evsel; + struct evsel *evsel; struct evsel_runtime *er; - list_for_each_entry(evsel, &evlist->entries, node) { + list_for_each_entry(evsel, &evlist->core.entries, core.node) { er = perf_evsel__get_runtime(evsel); if (er == NULL) { pr_err("Failed to allocate memory for evsel runtime data\n"); @@ -2948,12 +2948,12 @@ static int timehist_check_attr(struct perf_sched *sched, static int perf_sched__timehist(struct perf_sched *sched) { - const struct perf_evsel_str_handler handlers[] = { + const struct evsel_str_handler handlers[] = { { "sched:sched_switch", timehist_sched_switch_event, }, { "sched:sched_wakeup", timehist_sched_wakeup_event, }, { "sched:sched_wakeup_new", timehist_sched_wakeup_event, }, }; - const struct perf_evsel_str_handler migrate_handlers[] = { + const struct evsel_str_handler migrate_handlers[] = { { "sched:sched_migrate_task", timehist_migrate_task_event, }, }; struct perf_data data = { @@ -2963,7 +2963,7 @@ static int perf_sched__timehist(struct perf_sched *sched) }; struct perf_session *session; - struct perf_evlist *evlist; + struct evlist *evlist; int err = -1; /* @@ -3170,7 +3170,7 @@ static int perf_sched__lat(struct perf_sched *sched) static int setup_map_cpus(struct perf_sched *sched) { - struct cpu_map *map; + struct perf_cpu_map *map; sched->max_cpu = sysconf(_SC_NPROCESSORS_CONF); @@ -3183,7 +3183,7 @@ static int setup_map_cpus(struct perf_sched *sched) if (!sched->map.cpus_str) return 0; - map = cpu_map__new(sched->map.cpus_str); + map = perf_cpu_map__new(sched->map.cpus_str); if (!map) { pr_err("failed to get cpus map from %s\n", sched->map.cpus_str); return -1; @@ -3195,7 +3195,7 @@ static int setup_map_cpus(struct perf_sched *sched) static int setup_color_pids(struct perf_sched *sched) { - struct thread_map *map; + struct perf_thread_map *map; if (!sched->map.color_pids_str) return 0; @@ -3212,12 +3212,12 @@ static int setup_color_pids(struct perf_sched *sched) static int setup_color_cpus(struct perf_sched *sched) { - struct cpu_map *map; + struct perf_cpu_map *map; if (!sched->map.color_cpus_str) return 0; - map = cpu_map__new(sched->map.color_cpus_str); + map = perf_cpu_map__new(sched->map.color_cpus_str); if (!map) { pr_err("failed to get thread map from %s\n", sched->map.color_cpus_str); return -1; diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 0140ddb8dd0b..9b93ddeaeafa 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -3,6 +3,7 @@ #include "perf.h" #include "util/cache.h" +#include "util/counts.h" #include "util/debug.h" #include <subcmd/exec-cmd.h> #include "util/header.h" @@ -16,6 +17,7 @@ #include "util/trace-event.h" #include "util/evlist.h" #include "util/evsel.h" +#include "util/evswitch.h" #include "util/sort.h" #include "util/data.h" #include "util/auxtrace.h" @@ -48,6 +50,7 @@ #include <fcntl.h> #include <unistd.h> #include <subcmd/pager.h> +#include <perf/evlist.h> #include <linux/ctype.h> @@ -242,7 +245,7 @@ static struct { }, }; -struct perf_evsel_script { +struct evsel_script { char *filename; FILE *fp; u64 samples; @@ -251,15 +254,15 @@ struct perf_evsel_script { int gnum; }; -static inline struct perf_evsel_script *evsel_script(struct perf_evsel *evsel) +static inline struct evsel_script *evsel_script(struct evsel *evsel) { - return (struct perf_evsel_script *)evsel->priv; + return (struct evsel_script *)evsel->priv; } -static struct perf_evsel_script *perf_evsel_script__new(struct perf_evsel *evsel, +static struct evsel_script *perf_evsel_script__new(struct evsel *evsel, struct perf_data *data) { - struct perf_evsel_script *es = zalloc(sizeof(*es)); + struct evsel_script *es = zalloc(sizeof(*es)); if (es != NULL) { if (asprintf(&es->filename, "%s.%s.dump", data->file.path, perf_evsel__name(evsel)) < 0) @@ -277,7 +280,7 @@ out_free: return NULL; } -static void perf_evsel_script__delete(struct perf_evsel_script *es) +static void perf_evsel_script__delete(struct evsel_script *es) { zfree(&es->filename); fclose(es->fp); @@ -285,7 +288,7 @@ static void perf_evsel_script__delete(struct perf_evsel_script *es) free(es); } -static int perf_evsel_script__fprintf(struct perf_evsel_script *es, FILE *fp) +static int perf_evsel_script__fprintf(struct evsel_script *es, FILE *fp) { struct stat st; @@ -340,12 +343,12 @@ static const char *output_field2str(enum perf_output_field field) #define PRINT_FIELD(x) (output[output_type(attr->type)].fields & PERF_OUTPUT_##x) -static int perf_evsel__do_check_stype(struct perf_evsel *evsel, +static int perf_evsel__do_check_stype(struct evsel *evsel, u64 sample_type, const char *sample_msg, enum perf_output_field field, bool allow_user_set) { - struct perf_event_attr *attr = &evsel->attr; + struct perf_event_attr *attr = &evsel->core.attr; int type = output_type(attr->type); const char *evname; @@ -372,7 +375,7 @@ static int perf_evsel__do_check_stype(struct perf_evsel *evsel, return 0; } -static int perf_evsel__check_stype(struct perf_evsel *evsel, +static int perf_evsel__check_stype(struct evsel *evsel, u64 sample_type, const char *sample_msg, enum perf_output_field field) { @@ -380,10 +383,10 @@ static int perf_evsel__check_stype(struct perf_evsel *evsel, false); } -static int perf_evsel__check_attr(struct perf_evsel *evsel, +static int perf_evsel__check_attr(struct evsel *evsel, struct perf_session *session) { - struct perf_event_attr *attr = &evsel->attr; + struct perf_event_attr *attr = &evsel->core.attr; bool allow_user_set; if (perf_header__has_feat(&session->header, HEADER_STAT)) @@ -418,7 +421,7 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel, return -EINVAL; if (PRINT_FIELD(SYM) && - !(evsel->attr.sample_type & (PERF_SAMPLE_IP|PERF_SAMPLE_ADDR))) { + !(evsel->core.attr.sample_type & (PERF_SAMPLE_IP|PERF_SAMPLE_ADDR))) { pr_err("Display of symbols requested but neither sample IP nor " "sample address\navailable. Hence, no addresses to convert " "to symbols.\n"); @@ -430,7 +433,7 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel, return -EINVAL; } if (PRINT_FIELD(DSO) && - !(evsel->attr.sample_type & (PERF_SAMPLE_IP|PERF_SAMPLE_ADDR))) { + !(evsel->core.attr.sample_type & (PERF_SAMPLE_IP|PERF_SAMPLE_ADDR))) { pr_err("Display of DSO requested but no address to convert.\n"); return -EINVAL; } @@ -507,7 +510,7 @@ static void set_print_ip_opts(struct perf_event_attr *attr) static int perf_session__check_output_opt(struct perf_session *session) { unsigned int j; - struct perf_evsel *evsel; + struct evsel *evsel; for (j = 0; j < OUTPUT_TYPE_MAX; ++j) { evsel = perf_session__find_first_evtype(session, attr_type(j)); @@ -531,7 +534,7 @@ static int perf_session__check_output_opt(struct perf_session *session) if (evsel == NULL) continue; - set_print_ip_opts(&evsel->attr); + set_print_ip_opts(&evsel->core.attr); } if (!no_callchain) { @@ -558,7 +561,7 @@ static int perf_session__check_output_opt(struct perf_session *session) j = PERF_TYPE_TRACEPOINT; evlist__for_each_entry(session->evlist, evsel) { - if (evsel->attr.type != j) + if (evsel->core.attr.type != j) continue; if (evsel__has_callchain(evsel)) { @@ -566,7 +569,7 @@ static int perf_session__check_output_opt(struct perf_session *session) output[j].fields |= PERF_OUTPUT_SYM; output[j].fields |= PERF_OUTPUT_SYMOFFSET; output[j].fields |= PERF_OUTPUT_DSO; - set_print_ip_opts(&evsel->attr); + set_print_ip_opts(&evsel->core.attr); goto out; } } @@ -614,10 +617,10 @@ static int perf_sample__fprintf_uregs(struct perf_sample *sample, static int perf_sample__fprintf_start(struct perf_sample *sample, struct thread *thread, - struct perf_evsel *evsel, + struct evsel *evsel, u32 type, FILE *fp) { - struct perf_event_attr *attr = &evsel->attr; + struct perf_event_attr *attr = &evsel->core.attr; unsigned long secs; unsigned long long nsecs; int printed = 0; @@ -1162,13 +1165,13 @@ out: } static const char *resolve_branch_sym(struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct thread *thread, struct addr_location *al, u64 *ip) { struct addr_location addr_al; - struct perf_event_attr *attr = &evsel->attr; + struct perf_event_attr *attr = &evsel->core.attr; const char *name = NULL; if (sample->flags & (PERF_IP_FLAG_CALL | PERF_IP_FLAG_TRACE_BEGIN)) { @@ -1191,11 +1194,11 @@ static const char *resolve_branch_sym(struct perf_sample *sample, } static int perf_sample__fprintf_callindent(struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct thread *thread, struct addr_location *al, FILE *fp) { - struct perf_event_attr *attr = &evsel->attr; + struct perf_event_attr *attr = &evsel->core.attr; size_t depth = thread_stack__depth(thread, sample->cpu); const char *name = NULL; static int spacing; @@ -1285,12 +1288,12 @@ static int perf_sample__fprintf_ipc(struct perf_sample *sample, } static int perf_sample__fprintf_bts(struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct thread *thread, struct addr_location *al, struct machine *machine, FILE *fp) { - struct perf_event_attr *attr = &evsel->attr; + struct perf_event_attr *attr = &evsel->core.attr; unsigned int type = output_type(attr->type); bool print_srcline_last = false; int printed = 0; @@ -1322,7 +1325,7 @@ static int perf_sample__fprintf_bts(struct perf_sample *sample, /* print branch_to information */ if (PRINT_FIELD(ADDR) || - ((evsel->attr.sample_type & PERF_SAMPLE_ADDR) && + ((evsel->core.attr.sample_type & PERF_SAMPLE_ADDR) && !output[type].user_set)) { printed += fprintf(fp, " => "); printed += perf_sample__fprintf_addr(sample, thread, attr, fp); @@ -1593,9 +1596,9 @@ static int perf_sample__fprintf_synth_cbr(struct perf_sample *sample, FILE *fp) } static int perf_sample__fprintf_synth(struct perf_sample *sample, - struct perf_evsel *evsel, FILE *fp) + struct evsel *evsel, FILE *fp) { - switch (evsel->attr.config) { + switch (evsel->core.attr.config) { case PERF_SYNTH_INTEL_PTWRITE: return perf_sample__fprintf_synth_ptwrite(sample, fp); case PERF_SYNTH_INTEL_MWAIT: @@ -1627,8 +1630,9 @@ struct perf_script { bool show_bpf_events; bool allocated; bool per_event_dump; - struct cpu_map *cpus; - struct thread_map *threads; + struct evswitch evswitch; + struct perf_cpu_map *cpus; + struct perf_thread_map *threads; int name_width; const char *time_str; struct perf_time_interval *ptime_range; @@ -1636,9 +1640,9 @@ struct perf_script { int range_num; }; -static int perf_evlist__max_name_len(struct perf_evlist *evlist) +static int perf_evlist__max_name_len(struct evlist *evlist) { - struct perf_evsel *evsel; + struct evsel *evsel; int max = 0; evlist__for_each_entry(evlist, evsel) { @@ -1670,7 +1674,7 @@ static int data_src__fprintf(u64 data_src, FILE *fp) struct metric_ctx { struct perf_sample *sample; struct thread *thread; - struct perf_evsel *evsel; + struct evsel *evsel; FILE *fp; }; @@ -1705,7 +1709,7 @@ static void script_new_line(struct perf_stat_config *config __maybe_unused, static void perf_sample__fprint_metric(struct perf_script *script, struct thread *thread, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample, FILE *fp) { @@ -1720,7 +1724,7 @@ static void perf_sample__fprint_metric(struct perf_script *script, }, .force_header = false, }; - struct perf_evsel *ev2; + struct evsel *ev2; u64 val; if (!evsel->stats) @@ -1733,7 +1737,7 @@ static void perf_sample__fprint_metric(struct perf_script *script, sample->cpu, &rt_stat); evsel_script(evsel)->val = val; - if (evsel_script(evsel->leader)->gnum == evsel->leader->nr_members) { + if (evsel_script(evsel->leader)->gnum == evsel->leader->core.nr_members) { for_each_group_member (ev2, evsel->leader) { perf_stat__print_shadow_stats(&stat_config, ev2, evsel_script(ev2)->val, @@ -1747,7 +1751,7 @@ static void perf_sample__fprint_metric(struct perf_script *script, } static bool show_event(struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct thread *thread, struct addr_location *al) { @@ -1788,14 +1792,14 @@ static bool show_event(struct perf_sample *sample, } static void process_event(struct perf_script *script, - struct perf_sample *sample, struct perf_evsel *evsel, + struct perf_sample *sample, struct evsel *evsel, struct addr_location *al, struct machine *machine) { struct thread *thread = al->thread; - struct perf_event_attr *attr = &evsel->attr; + struct perf_event_attr *attr = &evsel->core.attr; unsigned int type = output_type(attr->type); - struct perf_evsel_script *es = evsel->priv; + struct evsel_script *es = evsel->priv; FILE *fp = es->fp; if (output[type].fields == 0) @@ -1804,6 +1808,9 @@ static void process_event(struct perf_script *script, if (!show_event(sample, evsel, thread, al)) return; + if (evswitch__discard(&script->evswitch, evsel)) + return; + ++es->samples; perf_sample__fprintf_start(sample, thread, evsel, @@ -1897,9 +1904,9 @@ static void process_event(struct perf_script *script, static struct scripting_ops *scripting_ops; -static void __process_stat(struct perf_evsel *counter, u64 tstamp) +static void __process_stat(struct evsel *counter, u64 tstamp) { - int nthreads = thread_map__nr(counter->threads); + int nthreads = perf_thread_map__nr(counter->core.threads); int ncpus = perf_evsel__nr_cpus(counter); int cpu, thread; static int header_printed; @@ -1920,8 +1927,8 @@ static void __process_stat(struct perf_evsel *counter, u64 tstamp) counts = perf_counts(counter->counts, cpu, thread); printf("%3d %8d %15" PRIu64 " %15" PRIu64 " %15" PRIu64 " %15" PRIu64 " %s\n", - counter->cpus->map[cpu], - thread_map__pid(counter->threads, thread), + counter->core.cpus->map[cpu], + perf_thread_map__pid(counter->core.threads, thread), counts->val, counts->ena, counts->run, @@ -1931,7 +1938,7 @@ static void __process_stat(struct perf_evsel *counter, u64 tstamp) } } -static void process_stat(struct perf_evsel *counter, u64 tstamp) +static void process_stat(struct evsel *counter, u64 tstamp) { if (scripting_ops && scripting_ops->process_stat) scripting_ops->process_stat(&stat_config, counter, tstamp); @@ -1973,7 +1980,7 @@ static bool filter_cpu(struct perf_sample *sample) static int process_sample_event(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct machine *machine) { struct perf_script *scr = container_of(tool, struct perf_script, tool); @@ -2018,13 +2025,13 @@ out_put: } static int process_attr(struct perf_tool *tool, union perf_event *event, - struct perf_evlist **pevlist) + struct evlist **pevlist) { struct perf_script *scr = container_of(tool, struct perf_script, tool); - struct perf_evlist *evlist; - struct perf_evsel *evsel, *pos; + struct evlist *evlist; + struct evsel *evsel, *pos; int err; - static struct perf_evsel_script *es; + static struct evsel_script *es; err = perf_event__process_attr(tool, event, pevlist); if (err) @@ -2046,18 +2053,18 @@ static int process_attr(struct perf_tool *tool, union perf_event *event, } } - if (evsel->attr.type >= PERF_TYPE_MAX && - evsel->attr.type != PERF_TYPE_SYNTH) + if (evsel->core.attr.type >= PERF_TYPE_MAX && + evsel->core.attr.type != PERF_TYPE_SYNTH) return 0; evlist__for_each_entry(evlist, pos) { - if (pos->attr.type == evsel->attr.type && pos != evsel) + if (pos->core.attr.type == evsel->core.attr.type && pos != evsel) return 0; } - set_print_ip_opts(&evsel->attr); + set_print_ip_opts(&evsel->core.attr); - if (evsel->attr.sample_type) + if (evsel->core.attr.sample_type) err = perf_evsel__check_attr(evsel, scr->session); return err; @@ -2071,7 +2078,7 @@ static int process_comm_event(struct perf_tool *tool, struct thread *thread; struct perf_script *script = container_of(tool, struct perf_script, tool); struct perf_session *session = script->session; - struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); + struct evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); int ret = -1; thread = machine__findnew_thread(machine, event->comm.pid, event->comm.tid); @@ -2083,7 +2090,7 @@ static int process_comm_event(struct perf_tool *tool, if (perf_event__process_comm(tool, event, sample, machine) < 0) goto out; - if (!evsel->attr.sample_id_all) { + if (!evsel->core.attr.sample_id_all) { sample->cpu = 0; sample->time = 0; sample->tid = event->comm.tid; @@ -2108,7 +2115,7 @@ static int process_namespaces_event(struct perf_tool *tool, struct thread *thread; struct perf_script *script = container_of(tool, struct perf_script, tool); struct perf_session *session = script->session; - struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); + struct evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); int ret = -1; thread = machine__findnew_thread(machine, event->namespaces.pid, @@ -2121,7 +2128,7 @@ static int process_namespaces_event(struct perf_tool *tool, if (perf_event__process_namespaces(tool, event, sample, machine) < 0) goto out; - if (!evsel->attr.sample_id_all) { + if (!evsel->core.attr.sample_id_all) { sample->cpu = 0; sample->time = 0; sample->tid = event->namespaces.tid; @@ -2146,7 +2153,7 @@ static int process_fork_event(struct perf_tool *tool, struct thread *thread; struct perf_script *script = container_of(tool, struct perf_script, tool); struct perf_session *session = script->session; - struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); + struct evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); if (perf_event__process_fork(tool, event, sample, machine) < 0) return -1; @@ -2157,7 +2164,7 @@ static int process_fork_event(struct perf_tool *tool, return -1; } - if (!evsel->attr.sample_id_all) { + if (!evsel->core.attr.sample_id_all) { sample->cpu = 0; sample->time = event->fork.time; sample->tid = event->fork.tid; @@ -2181,7 +2188,7 @@ static int process_exit_event(struct perf_tool *tool, struct thread *thread; struct perf_script *script = container_of(tool, struct perf_script, tool); struct perf_session *session = script->session; - struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); + struct evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); thread = machine__findnew_thread(machine, event->fork.pid, event->fork.tid); if (thread == NULL) { @@ -2189,7 +2196,7 @@ static int process_exit_event(struct perf_tool *tool, return -1; } - if (!evsel->attr.sample_id_all) { + if (!evsel->core.attr.sample_id_all) { sample->cpu = 0; sample->time = 0; sample->tid = event->fork.tid; @@ -2216,7 +2223,7 @@ static int process_mmap_event(struct perf_tool *tool, struct thread *thread; struct perf_script *script = container_of(tool, struct perf_script, tool); struct perf_session *session = script->session; - struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); + struct evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); if (perf_event__process_mmap(tool, event, sample, machine) < 0) return -1; @@ -2227,7 +2234,7 @@ static int process_mmap_event(struct perf_tool *tool, return -1; } - if (!evsel->attr.sample_id_all) { + if (!evsel->core.attr.sample_id_all) { sample->cpu = 0; sample->time = 0; sample->tid = event->mmap.tid; @@ -2250,7 +2257,7 @@ static int process_mmap2_event(struct perf_tool *tool, struct thread *thread; struct perf_script *script = container_of(tool, struct perf_script, tool); struct perf_session *session = script->session; - struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); + struct evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); if (perf_event__process_mmap2(tool, event, sample, machine) < 0) return -1; @@ -2261,7 +2268,7 @@ static int process_mmap2_event(struct perf_tool *tool, return -1; } - if (!evsel->attr.sample_id_all) { + if (!evsel->core.attr.sample_id_all) { sample->cpu = 0; sample->time = 0; sample->tid = event->mmap2.tid; @@ -2284,7 +2291,7 @@ static int process_switch_event(struct perf_tool *tool, struct thread *thread; struct perf_script *script = container_of(tool, struct perf_script, tool); struct perf_session *session = script->session; - struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); + struct evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); if (perf_event__process_switch(tool, event, sample, machine) < 0) return -1; @@ -2319,7 +2326,7 @@ process_lost_event(struct perf_tool *tool, { struct perf_script *script = container_of(tool, struct perf_script, tool); struct perf_session *session = script->session; - struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); + struct evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); struct thread *thread; thread = machine__findnew_thread(machine, sample->pid, @@ -2355,12 +2362,12 @@ process_bpf_events(struct perf_tool *tool __maybe_unused, struct thread *thread; struct perf_script *script = container_of(tool, struct perf_script, tool); struct perf_session *session = script->session; - struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); + struct evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); if (machine__process_ksymbol(machine, event, sample) < 0) return -1; - if (!evsel->attr.sample_id_all) { + if (!evsel->core.attr.sample_id_all) { perf_event__fprintf(event, stdout); return 0; } @@ -2388,8 +2395,8 @@ static void sig_handler(int sig __maybe_unused) static void perf_script__fclose_per_event_dump(struct perf_script *script) { - struct perf_evlist *evlist = script->session->evlist; - struct perf_evsel *evsel; + struct evlist *evlist = script->session->evlist; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { if (!evsel->priv) @@ -2401,7 +2408,7 @@ static void perf_script__fclose_per_event_dump(struct perf_script *script) static int perf_script__fopen_per_event_dump(struct perf_script *script) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(script->session->evlist, evsel) { /* @@ -2428,8 +2435,8 @@ out_err_fclose: static int perf_script__setup_per_event_dump(struct perf_script *script) { - struct perf_evsel *evsel; - static struct perf_evsel_script es_stdout; + struct evsel *evsel; + static struct evsel_script es_stdout; if (script->per_event_dump) return perf_script__fopen_per_event_dump(script); @@ -2444,10 +2451,10 @@ static int perf_script__setup_per_event_dump(struct perf_script *script) static void perf_script__exit_per_event_dump_stats(struct perf_script *script) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(script->session->evlist, evsel) { - struct perf_evsel_script *es = evsel->priv; + struct evsel_script *es = evsel->priv; perf_evsel_script__fprintf(es, stdout); perf_evsel_script__delete(es); @@ -3003,7 +3010,7 @@ static int check_ev_match(char *dir_name, char *scriptname, { char filename[MAXPATHLEN], evname[128]; char line[BUFSIZ], *p; - struct perf_evsel *pos; + struct evsel *pos; int match, len; FILE *fp; @@ -3236,7 +3243,7 @@ static int process_stat_round_event(struct perf_session *session, union perf_event *event) { struct stat_round_event *round = &event->stat_round; - struct perf_evsel *counter; + struct evsel *counter; evlist__for_each_entry(session->evlist, counter) { perf_stat_process_counter(&stat_config, counter); @@ -3256,7 +3263,7 @@ static int process_stat_config_event(struct perf_session *session __maybe_unused static int set_maps(struct perf_script *script) { - struct perf_evlist *evlist = script->session->evlist; + struct evlist *evlist = script->session->evlist; if (!script->cpus || !script->threads) return 0; @@ -3264,7 +3271,7 @@ static int set_maps(struct perf_script *script) if (WARN_ONCE(script->allocated, "stats double allocation\n")) return -EINVAL; - perf_evlist__set_maps(evlist, script->cpus, script->threads); + perf_evlist__set_maps(&evlist->core, script->cpus, script->threads); if (perf_evlist__alloc_stats(evlist, true)) return -ENOMEM; @@ -3537,6 +3544,7 @@ int cmd_script(int argc, const char **argv) "file", "file saving guest os /proc/kallsyms"), OPT_STRING(0, "guestmodules", &symbol_conf.default_guest_modules, "file", "file saving guest os /proc/modules"), + OPTS_EVSWITCH(&script.evswitch), OPT_END() }; const char * const script_subcommands[] = { "record", "report", NULL }; @@ -3861,6 +3869,10 @@ int cmd_script(int argc, const char **argv) script.range_num); } + err = evswitch__init(&script.evswitch, session->evlist, stderr); + if (err) + goto out_delete; + err = __cmd_script(&script); flush_scripting(); diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 352cf39d7c2f..8a4f1a7d0cba 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -83,6 +83,7 @@ #include <sys/resource.h> #include <linux/ctype.h> +#include <perf/evlist.h> #define DEFAULT_SEPARATOR " " #define FREEZE_ON_SMI_PATH "devices/cpu/freeze_on_smi" @@ -130,7 +131,7 @@ static const char *smi_cost_attrs = { "}" }; -static struct perf_evlist *evsel_list; +static struct evlist *evsel_list; static struct target target = { .uid = UINT_MAX, @@ -164,8 +165,8 @@ struct perf_stat { u64 bytes_written; struct perf_tool tool; bool maps_allocated; - struct cpu_map *cpus; - struct thread_map *threads; + struct perf_cpu_map *cpus; + struct perf_thread_map *threads; enum aggr_mode aggr_mode; }; @@ -234,7 +235,7 @@ static int write_stat_round_event(u64 tm, u64 type) #define SID(e, x, y) xyarray__entry(e->sample_id, x, y) static int -perf_evsel__write_stat_event(struct perf_evsel *counter, u32 cpu, u32 thread, +perf_evsel__write_stat_event(struct evsel *counter, u32 cpu, u32 thread, struct perf_counts_values *count) { struct perf_sample_id *sid = SID(counter, cpu, thread); @@ -243,7 +244,7 @@ perf_evsel__write_stat_event(struct perf_evsel *counter, u32 cpu, u32 thread, process_synthesized_event, NULL); } -static int read_single_counter(struct perf_evsel *counter, int cpu, +static int read_single_counter(struct evsel *counter, int cpu, int thread, struct timespec *rs) { if (counter->tool_event == PERF_TOOL_DURATION_TIME) { @@ -261,9 +262,9 @@ static int read_single_counter(struct perf_evsel *counter, int cpu, * Read out the results of a single counter: * do not aggregate counts across CPUs in system-wide mode */ -static int read_counter(struct perf_evsel *counter, struct timespec *rs) +static int read_counter(struct evsel *counter, struct timespec *rs) { - int nthreads = thread_map__nr(evsel_list->threads); + int nthreads = perf_thread_map__nr(evsel_list->core.threads); int ncpus, cpu, thread; if (target__has_cpu(&target) && !target__has_per_thread(&target)) @@ -287,7 +288,7 @@ static int read_counter(struct perf_evsel *counter, struct timespec *rs) * The leader's group read loads data into its group members * (via perf_evsel__read_counter) and sets threir count->loaded. */ - if (!count->loaded && + if (!perf_counts__is_loaded(counter->counts, cpu, thread) && read_single_counter(counter, cpu, thread, rs)) { counter->counts->scaled = -1; perf_counts(counter->counts, cpu, thread)->ena = 0; @@ -295,7 +296,7 @@ static int read_counter(struct perf_evsel *counter, struct timespec *rs) return -1; } - count->loaded = false; + perf_counts__set_loaded(counter->counts, cpu, thread, false); if (STAT_RECORD) { if (perf_evsel__write_stat_event(counter, cpu, thread, count)) { @@ -319,7 +320,7 @@ static int read_counter(struct perf_evsel *counter, struct timespec *rs) static void read_counters(struct timespec *rs) { - struct perf_evsel *counter; + struct evsel *counter; int ret; evlist__for_each_entry(evsel_list, counter) { @@ -362,7 +363,7 @@ static void enable_counters(void) * - we have initial delay configured */ if (!target__none(&target) || stat_config.initial_delay) - perf_evlist__enable(evsel_list); + evlist__enable(evsel_list); } static void disable_counters(void) @@ -373,7 +374,7 @@ static void disable_counters(void) * from counting before reading their constituent counters. */ if (!target__none(&target)) - perf_evlist__disable(evsel_list); + evlist__disable(evsel_list); } static volatile int workload_exec_errno; @@ -389,13 +390,13 @@ static void workload_exec_failed_signal(int signo __maybe_unused, siginfo_t *inf workload_exec_errno = info->si_value.sival_int; } -static bool perf_evsel__should_store_id(struct perf_evsel *counter) +static bool perf_evsel__should_store_id(struct evsel *counter) { - return STAT_RECORD || counter->attr.read_format & PERF_FORMAT_ID; + return STAT_RECORD || counter->core.attr.read_format & PERF_FORMAT_ID; } static bool is_target_alive(struct target *_target, - struct thread_map *threads) + struct perf_thread_map *threads) { struct stat st; int i; @@ -423,7 +424,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx) int timeout = stat_config.timeout; char msg[BUFSIZ]; unsigned long long t0, t1; - struct perf_evsel *counter; + struct evsel *counter; struct timespec ts; size_t l; int status = 0; @@ -478,22 +479,22 @@ try_again: counter->supported = false; if ((counter->leader != counter) || - !(counter->leader->nr_members > 1)) + !(counter->leader->core.nr_members > 1)) continue; } else if (perf_evsel__fallback(counter, errno, msg, sizeof(msg))) { if (verbose > 0) ui__warning("%s\n", msg); goto try_again; } else if (target__has_per_thread(&target) && - evsel_list->threads && - evsel_list->threads->err_thread != -1) { + evsel_list->core.threads && + evsel_list->core.threads->err_thread != -1) { /* * For global --per-thread case, skip current * error thread. */ - if (!thread_map__remove(evsel_list->threads, - evsel_list->threads->err_thread)) { - evsel_list->threads->err_thread = -1; + if (!thread_map__remove(evsel_list->core.threads, + evsel_list->core.threads->err_thread)) { + evsel_list->core.threads->err_thread = -1; goto try_again; } } @@ -579,7 +580,7 @@ try_again: enable_counters(); while (!done) { nanosleep(&ts, NULL); - if (!is_target_alive(&target, evsel_list->threads)) + if (!is_target_alive(&target, evsel_list->core.threads)) break; if (timeout) break; @@ -613,7 +614,7 @@ try_again: * later the evsel_list will be closed after. */ if (!STAT_RECORD) - perf_evlist__close(evsel_list); + evlist__close(evsel_list); return WEXITSTATUS(status); } @@ -803,24 +804,24 @@ static struct option stat_options[] = { }; static int perf_stat__get_socket(struct perf_stat_config *config __maybe_unused, - struct cpu_map *map, int cpu) + struct perf_cpu_map *map, int cpu) { return cpu_map__get_socket(map, cpu, NULL); } static int perf_stat__get_die(struct perf_stat_config *config __maybe_unused, - struct cpu_map *map, int cpu) + struct perf_cpu_map *map, int cpu) { return cpu_map__get_die(map, cpu, NULL); } static int perf_stat__get_core(struct perf_stat_config *config __maybe_unused, - struct cpu_map *map, int cpu) + struct perf_cpu_map *map, int cpu) { return cpu_map__get_core(map, cpu, NULL); } -static int cpu_map__get_max(struct cpu_map *map) +static int cpu_map__get_max(struct perf_cpu_map *map) { int i, max = -1; @@ -833,7 +834,7 @@ static int cpu_map__get_max(struct cpu_map *map) } static int perf_stat__get_aggr(struct perf_stat_config *config, - aggr_get_id_t get_id, struct cpu_map *map, int idx) + aggr_get_id_t get_id, struct perf_cpu_map *map, int idx) { int cpu; @@ -849,26 +850,26 @@ static int perf_stat__get_aggr(struct perf_stat_config *config, } static int perf_stat__get_socket_cached(struct perf_stat_config *config, - struct cpu_map *map, int idx) + struct perf_cpu_map *map, int idx) { return perf_stat__get_aggr(config, perf_stat__get_socket, map, idx); } static int perf_stat__get_die_cached(struct perf_stat_config *config, - struct cpu_map *map, int idx) + struct perf_cpu_map *map, int idx) { return perf_stat__get_aggr(config, perf_stat__get_die, map, idx); } static int perf_stat__get_core_cached(struct perf_stat_config *config, - struct cpu_map *map, int idx) + struct perf_cpu_map *map, int idx) { return perf_stat__get_aggr(config, perf_stat__get_core, map, idx); } static bool term_percore_set(void) { - struct perf_evsel *counter; + struct evsel *counter; evlist__for_each_entry(evsel_list, counter) { if (counter->percore) @@ -884,21 +885,21 @@ static int perf_stat_init_aggr_mode(void) switch (stat_config.aggr_mode) { case AGGR_SOCKET: - if (cpu_map__build_socket_map(evsel_list->cpus, &stat_config.aggr_map)) { + if (cpu_map__build_socket_map(evsel_list->core.cpus, &stat_config.aggr_map)) { perror("cannot build socket map"); return -1; } stat_config.aggr_get_id = perf_stat__get_socket_cached; break; case AGGR_DIE: - if (cpu_map__build_die_map(evsel_list->cpus, &stat_config.aggr_map)) { + if (cpu_map__build_die_map(evsel_list->core.cpus, &stat_config.aggr_map)) { perror("cannot build die map"); return -1; } stat_config.aggr_get_id = perf_stat__get_die_cached; break; case AGGR_CORE: - if (cpu_map__build_core_map(evsel_list->cpus, &stat_config.aggr_map)) { + if (cpu_map__build_core_map(evsel_list->core.cpus, &stat_config.aggr_map)) { perror("cannot build core map"); return -1; } @@ -906,7 +907,7 @@ static int perf_stat_init_aggr_mode(void) break; case AGGR_NONE: if (term_percore_set()) { - if (cpu_map__build_core_map(evsel_list->cpus, + if (cpu_map__build_core_map(evsel_list->core.cpus, &stat_config.aggr_map)) { perror("cannot build core map"); return -1; @@ -926,20 +927,20 @@ static int perf_stat_init_aggr_mode(void) * taking the highest cpu number to be the size of * the aggregation translate cpumap. */ - nr = cpu_map__get_max(evsel_list->cpus); - stat_config.cpus_aggr_map = cpu_map__empty_new(nr + 1); + nr = cpu_map__get_max(evsel_list->core.cpus); + stat_config.cpus_aggr_map = perf_cpu_map__empty_new(nr + 1); return stat_config.cpus_aggr_map ? 0 : -ENOMEM; } static void perf_stat__exit_aggr_mode(void) { - cpu_map__put(stat_config.aggr_map); - cpu_map__put(stat_config.cpus_aggr_map); + perf_cpu_map__put(stat_config.aggr_map); + perf_cpu_map__put(stat_config.cpus_aggr_map); stat_config.aggr_map = NULL; stat_config.cpus_aggr_map = NULL; } -static inline int perf_env__get_cpu(struct perf_env *env, struct cpu_map *map, int idx) +static inline int perf_env__get_cpu(struct perf_env *env, struct perf_cpu_map *map, int idx) { int cpu; @@ -954,7 +955,7 @@ static inline int perf_env__get_cpu(struct perf_env *env, struct cpu_map *map, i return cpu; } -static int perf_env__get_socket(struct cpu_map *map, int idx, void *data) +static int perf_env__get_socket(struct perf_cpu_map *map, int idx, void *data) { struct perf_env *env = data; int cpu = perf_env__get_cpu(env, map, idx); @@ -962,7 +963,7 @@ static int perf_env__get_socket(struct cpu_map *map, int idx, void *data) return cpu == -1 ? -1 : env->cpu[cpu].socket_id; } -static int perf_env__get_die(struct cpu_map *map, int idx, void *data) +static int perf_env__get_die(struct perf_cpu_map *map, int idx, void *data) { struct perf_env *env = data; int die_id = -1, cpu = perf_env__get_cpu(env, map, idx); @@ -986,7 +987,7 @@ static int perf_env__get_die(struct cpu_map *map, int idx, void *data) return die_id; } -static int perf_env__get_core(struct cpu_map *map, int idx, void *data) +static int perf_env__get_core(struct perf_cpu_map *map, int idx, void *data) { struct perf_env *env = data; int core = -1, cpu = perf_env__get_cpu(env, map, idx); @@ -1016,37 +1017,37 @@ static int perf_env__get_core(struct cpu_map *map, int idx, void *data) return core; } -static int perf_env__build_socket_map(struct perf_env *env, struct cpu_map *cpus, - struct cpu_map **sockp) +static int perf_env__build_socket_map(struct perf_env *env, struct perf_cpu_map *cpus, + struct perf_cpu_map **sockp) { return cpu_map__build_map(cpus, sockp, perf_env__get_socket, env); } -static int perf_env__build_die_map(struct perf_env *env, struct cpu_map *cpus, - struct cpu_map **diep) +static int perf_env__build_die_map(struct perf_env *env, struct perf_cpu_map *cpus, + struct perf_cpu_map **diep) { return cpu_map__build_map(cpus, diep, perf_env__get_die, env); } -static int perf_env__build_core_map(struct perf_env *env, struct cpu_map *cpus, - struct cpu_map **corep) +static int perf_env__build_core_map(struct perf_env *env, struct perf_cpu_map *cpus, + struct perf_cpu_map **corep) { return cpu_map__build_map(cpus, corep, perf_env__get_core, env); } static int perf_stat__get_socket_file(struct perf_stat_config *config __maybe_unused, - struct cpu_map *map, int idx) + struct perf_cpu_map *map, int idx) { return perf_env__get_socket(map, idx, &perf_stat.session->header.env); } static int perf_stat__get_die_file(struct perf_stat_config *config __maybe_unused, - struct cpu_map *map, int idx) + struct perf_cpu_map *map, int idx) { return perf_env__get_die(map, idx, &perf_stat.session->header.env); } static int perf_stat__get_core_file(struct perf_stat_config *config __maybe_unused, - struct cpu_map *map, int idx) + struct perf_cpu_map *map, int idx) { return perf_env__get_core(map, idx, &perf_stat.session->header.env); } @@ -1057,21 +1058,21 @@ static int perf_stat_init_aggr_mode_file(struct perf_stat *st) switch (stat_config.aggr_mode) { case AGGR_SOCKET: - if (perf_env__build_socket_map(env, evsel_list->cpus, &stat_config.aggr_map)) { + if (perf_env__build_socket_map(env, evsel_list->core.cpus, &stat_config.aggr_map)) { perror("cannot build socket map"); return -1; } stat_config.aggr_get_id = perf_stat__get_socket_file; break; case AGGR_DIE: - if (perf_env__build_die_map(env, evsel_list->cpus, &stat_config.aggr_map)) { + if (perf_env__build_die_map(env, evsel_list->core.cpus, &stat_config.aggr_map)) { perror("cannot build die map"); return -1; } stat_config.aggr_get_id = perf_stat__get_die_file; break; case AGGR_CORE: - if (perf_env__build_core_map(env, evsel_list->cpus, &stat_config.aggr_map)) { + if (perf_env__build_core_map(env, evsel_list->core.cpus, &stat_config.aggr_map)) { perror("cannot build core map"); return -1; } @@ -1366,7 +1367,7 @@ static int add_default_attributes(void) free(str); } - if (!evsel_list->nr_entries) { + if (!evsel_list->core.nr_entries) { if (target__has_cpu(&target)) default_attrs0[0].config = PERF_COUNT_SW_CPU_CLOCK; @@ -1462,7 +1463,7 @@ static int process_stat_round_event(struct perf_session *session, union perf_event *event) { struct stat_round_event *stat_round = &event->stat_round; - struct perf_evsel *counter; + struct evsel *counter; struct timespec tsh, *ts = NULL; const char **argv = session->header.env.cmdline_argv; int argc = session->header.env.nr_cmdline; @@ -1492,7 +1493,7 @@ int process_stat_config_event(struct perf_session *session, perf_event__read_stat_config(&stat_config, &event->stat_config); - if (cpu_map__empty(st->cpus)) { + if (perf_cpu_map__empty(st->cpus)) { if (st->aggr_mode != AGGR_UNSET) pr_warning("warning: processing task data, aggregation mode not set\n"); return 0; @@ -1517,7 +1518,7 @@ static int set_maps(struct perf_stat *st) if (WARN_ONCE(st->maps_allocated, "stats double allocation\n")) return -EINVAL; - perf_evlist__set_maps(evsel_list, st->cpus, st->threads); + perf_evlist__set_maps(&evsel_list->core, st->cpus, st->threads); if (perf_evlist__alloc_stats(evsel_list, true)) return -ENOMEM; @@ -1551,7 +1552,7 @@ int process_cpu_map_event(struct perf_session *session, { struct perf_tool *tool = session->tool; struct perf_stat *st = container_of(tool, struct perf_stat, tool); - struct cpu_map *cpus; + struct perf_cpu_map *cpus; if (st->cpus) { pr_warning("Extra cpu map event, ignoring.\n"); @@ -1676,14 +1677,14 @@ static void setup_system_wide(int forks) if (!forks) target.system_wide = true; else { - struct perf_evsel *counter; + struct evsel *counter; evlist__for_each_entry(evsel_list, counter) { if (!counter->system_wide) return; } - if (evsel_list->nr_entries) + if (evsel_list->core.nr_entries) target.system_wide = true; } } @@ -1702,7 +1703,7 @@ int cmd_stat(int argc, const char **argv) setlocale(LC_ALL, ""); - evsel_list = perf_evlist__new(); + evsel_list = evlist__new(); if (evsel_list == NULL) return -ENOMEM; @@ -1889,10 +1890,10 @@ int cmd_stat(int argc, const char **argv) * so we could print it out on output. */ if (stat_config.aggr_mode == AGGR_THREAD) { - thread_map__read_comms(evsel_list->threads); + thread_map__read_comms(evsel_list->core.threads); if (target.system_wide) { if (runtime_stat_new(&stat_config, - thread_map__nr(evsel_list->threads))) { + perf_thread_map__nr(evsel_list->core.threads))) { goto out; } } @@ -2003,7 +2004,7 @@ int cmd_stat(int argc, const char **argv) perf_session__write_header(perf_stat.session, evsel_list, fd, true); } - perf_evlist__close(evsel_list); + evlist__close(evsel_list); perf_session__delete(perf_stat.session); } @@ -2015,7 +2016,7 @@ out: if (smi_cost && smi_reset) sysfs__write_int(FREEZE_ON_SMI_PATH, 0); - perf_evlist__delete(evsel_list); + evlist__delete(evsel_list); runtime_stat_delete(&stat_config); diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c index 4bde3fa245d1..7d6a6ecf4e02 100644 --- a/tools/perf/builtin-timechart.c +++ b/tools/perf/builtin-timechart.c @@ -545,19 +545,19 @@ exit: } typedef int (*tracepoint_handler)(struct timechart *tchart, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample, const char *backtrace); static int process_sample_event(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct machine *machine) { struct timechart *tchart = container_of(tool, struct timechart, tool); - if (evsel->attr.sample_type & PERF_SAMPLE_TIME) { + if (evsel->core.attr.sample_type & PERF_SAMPLE_TIME) { if (!tchart->first_time || tchart->first_time > sample->time) tchart->first_time = sample->time; if (tchart->last_time < sample->time) @@ -575,7 +575,7 @@ static int process_sample_event(struct perf_tool *tool, static int process_sample_cpu_idle(struct timechart *tchart __maybe_unused, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample, const char *backtrace __maybe_unused) { @@ -591,7 +591,7 @@ process_sample_cpu_idle(struct timechart *tchart __maybe_unused, static int process_sample_cpu_frequency(struct timechart *tchart, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample, const char *backtrace __maybe_unused) { @@ -604,7 +604,7 @@ process_sample_cpu_frequency(struct timechart *tchart, static int process_sample_sched_wakeup(struct timechart *tchart, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample, const char *backtrace) { @@ -618,7 +618,7 @@ process_sample_sched_wakeup(struct timechart *tchart, static int process_sample_sched_switch(struct timechart *tchart, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample, const char *backtrace) { @@ -634,7 +634,7 @@ process_sample_sched_switch(struct timechart *tchart, #ifdef SUPPORT_OLD_POWER_EVENTS static int process_sample_power_start(struct timechart *tchart __maybe_unused, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample, const char *backtrace __maybe_unused) { @@ -647,7 +647,7 @@ process_sample_power_start(struct timechart *tchart __maybe_unused, static int process_sample_power_end(struct timechart *tchart, - struct perf_evsel *evsel __maybe_unused, + struct evsel *evsel __maybe_unused, struct perf_sample *sample, const char *backtrace __maybe_unused) { @@ -657,7 +657,7 @@ process_sample_power_end(struct timechart *tchart, static int process_sample_power_frequency(struct timechart *tchart, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample, const char *backtrace __maybe_unused) { @@ -840,7 +840,7 @@ static int pid_end_io_sample(struct timechart *tchart, int pid, int type, static int process_enter_read(struct timechart *tchart, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample) { long fd = perf_evsel__intval(evsel, sample, "fd"); @@ -850,7 +850,7 @@ process_enter_read(struct timechart *tchart, static int process_exit_read(struct timechart *tchart, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample) { long ret = perf_evsel__intval(evsel, sample, "ret"); @@ -860,7 +860,7 @@ process_exit_read(struct timechart *tchart, static int process_enter_write(struct timechart *tchart, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample) { long fd = perf_evsel__intval(evsel, sample, "fd"); @@ -870,7 +870,7 @@ process_enter_write(struct timechart *tchart, static int process_exit_write(struct timechart *tchart, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample) { long ret = perf_evsel__intval(evsel, sample, "ret"); @@ -880,7 +880,7 @@ process_exit_write(struct timechart *tchart, static int process_enter_sync(struct timechart *tchart, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample) { long fd = perf_evsel__intval(evsel, sample, "fd"); @@ -890,7 +890,7 @@ process_enter_sync(struct timechart *tchart, static int process_exit_sync(struct timechart *tchart, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample) { long ret = perf_evsel__intval(evsel, sample, "ret"); @@ -900,7 +900,7 @@ process_exit_sync(struct timechart *tchart, static int process_enter_tx(struct timechart *tchart, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample) { long fd = perf_evsel__intval(evsel, sample, "fd"); @@ -910,7 +910,7 @@ process_enter_tx(struct timechart *tchart, static int process_exit_tx(struct timechart *tchart, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample) { long ret = perf_evsel__intval(evsel, sample, "ret"); @@ -920,7 +920,7 @@ process_exit_tx(struct timechart *tchart, static int process_enter_rx(struct timechart *tchart, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample) { long fd = perf_evsel__intval(evsel, sample, "fd"); @@ -930,7 +930,7 @@ process_enter_rx(struct timechart *tchart, static int process_exit_rx(struct timechart *tchart, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample) { long ret = perf_evsel__intval(evsel, sample, "ret"); @@ -940,7 +940,7 @@ process_exit_rx(struct timechart *tchart, static int process_enter_poll(struct timechart *tchart, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample) { long fd = perf_evsel__intval(evsel, sample, "fd"); @@ -950,7 +950,7 @@ process_enter_poll(struct timechart *tchart, static int process_exit_poll(struct timechart *tchart, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample) { long ret = perf_evsel__intval(evsel, sample, "ret"); @@ -1534,7 +1534,7 @@ static int process_header(struct perf_file_section *section __maybe_unused, static int __cmd_timechart(struct timechart *tchart, const char *output_name) { - const struct perf_evsel_str_handler power_tracepoints[] = { + const struct evsel_str_handler power_tracepoints[] = { { "power:cpu_idle", process_sample_cpu_idle }, { "power:cpu_frequency", process_sample_cpu_frequency }, { "sched:sched_wakeup", process_sample_sched_wakeup }, diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index b46b3c9f57a0..5970723cd55a 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -38,7 +38,6 @@ #include <subcmd/parse-options.h> #include "util/parse-events.h" #include "util/cpumap.h" -#include "util/xyarray.h" #include "util/sort.h" #include "util/string2.h" #include "util/term.h" @@ -101,7 +100,7 @@ static void perf_top__resize(struct perf_top *top) static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he) { - struct perf_evsel *evsel; + struct evsel *evsel; struct symbol *sym; struct annotation *notes; struct map *map; @@ -129,7 +128,7 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he) notes = symbol__annotation(sym); pthread_mutex_lock(¬es->lock); - if (!symbol__hists(sym, top->evlist->nr_entries)) { + if (!symbol__hists(sym, top->evlist->core.nr_entries)) { pthread_mutex_unlock(¬es->lock); pr_err("Not enough memory for annotating '%s' symbol!\n", sym->name); @@ -186,7 +185,7 @@ static void ui__warn_map_erange(struct map *map, struct symbol *sym, u64 ip) static void perf_top__record_precise_ip(struct perf_top *top, struct hist_entry *he, struct perf_sample *sample, - struct perf_evsel *evsel, u64 ip) + struct evsel *evsel, u64 ip) { struct annotation *notes; struct symbol *sym = he->ms.sym; @@ -228,7 +227,7 @@ static void perf_top__record_precise_ip(struct perf_top *top, static void perf_top__show_details(struct perf_top *top) { struct hist_entry *he = top->sym_filter_entry; - struct perf_evsel *evsel; + struct evsel *evsel; struct annotation *notes; struct symbol *symbol; int more; @@ -265,12 +264,36 @@ out_unlock: pthread_mutex_unlock(¬es->lock); } +static void evlist__resort_hists(struct evlist *evlist) +{ + struct evsel *pos; + + evlist__for_each_entry(evlist, pos) { + struct hists *hists = evsel__hists(pos); + + hists__collapse_resort(hists, NULL); + + /* Non-group events are considered as leader */ + if (symbol_conf.event_group && + !perf_evsel__is_group_leader(pos)) { + struct hists *leader_hists = evsel__hists(pos->leader); + + hists__match(leader_hists, hists); + hists__link(leader_hists, hists); + } + } + + evlist__for_each_entry(evlist, pos) { + perf_evsel__output_resort(pos, NULL); + } +} + static void perf_top__print_sym_table(struct perf_top *top) { char bf[160]; int printed = 0; const int win_width = top->winsize.ws_col - 1; - struct perf_evsel *evsel = top->sym_evsel; + struct evsel *evsel = top->sym_evsel; struct hists *hists = evsel__hists(evsel); puts(CONSOLE_CLEAR); @@ -305,8 +328,7 @@ static void perf_top__print_sym_table(struct perf_top *top) } } - hists__collapse_resort(hists, NULL); - perf_evsel__output_resort(evsel, NULL); + evlist__resort_hists(top->evlist); hists__output_recalc_col_len(hists, top->print_entries - printed); putchar('\n'); @@ -404,7 +426,7 @@ static void perf_top__print_mapped_keys(struct perf_top *top) fprintf(stdout, "\t[d] display refresh delay. \t(%d)\n", top->delay_secs); fprintf(stdout, "\t[e] display entries (lines). \t(%d)\n", top->print_entries); - if (top->evlist->nr_entries > 1) + if (top->evlist->core.nr_entries > 1) fprintf(stdout, "\t[E] active event counter. \t(%s)\n", perf_evsel__name(top->sym_evsel)); fprintf(stdout, "\t[f] profile display filter (count). \t(%d)\n", top->count_filter); @@ -439,7 +461,7 @@ static int perf_top__key_mapped(struct perf_top *top, int c) case 'S': return 1; case 'E': - return top->evlist->nr_entries > 1 ? 1 : 0; + return top->evlist->core.nr_entries > 1 ? 1 : 0; default: break; } @@ -485,7 +507,7 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c) } break; case 'E': - if (top->evlist->nr_entries > 1) { + if (top->evlist->core.nr_entries > 1) { /* Select 0 as the default event: */ int counter = 0; @@ -496,7 +518,7 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c) prompt_integer(&counter, "Enter details event counter"); - if (counter >= top->evlist->nr_entries) { + if (counter >= top->evlist->core.nr_entries) { top->sym_evsel = perf_evlist__first(top->evlist); fprintf(stderr, "Sorry, no such event, using %s.\n", perf_evsel__name(top->sym_evsel)); sleep(1); @@ -554,7 +576,7 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c) static void perf_top__sort_new_samples(void *arg) { struct perf_top *t = arg; - struct perf_evsel *evsel = t->sym_evsel; + struct evsel *evsel = t->sym_evsel; struct hists *hists; if (t->evlist->selected != NULL) @@ -571,8 +593,7 @@ static void perf_top__sort_new_samples(void *arg) } } - hists__collapse_resort(hists, NULL); - perf_evsel__output_resort(evsel, NULL); + evlist__resort_hists(t->evlist); if (t->lost || t->drop) pr_warning("Too slow to read ring buffer (change period (-c/-F) or limit CPUs (-C)\n"); @@ -586,7 +607,7 @@ static void stop_top(void) static void *display_thread_tui(void *arg) { - struct perf_evsel *pos; + struct evsel *pos; struct perf_top *top = arg; const char *help = "For a higher level overview, try: perf top --sort comm,dso"; struct hist_browser_timer hbt = { @@ -602,6 +623,8 @@ static void *display_thread_tui(void *arg) */ unshare(CLONE_FS); + prctl(PR_SET_NAME, "perf-top-UI", 0, 0, 0); + perf_top__sort_new_samples(top); /* @@ -652,6 +675,8 @@ static void *display_thread(void *arg) */ unshare(CLONE_FS); + prctl(PR_SET_NAME, "perf-top-UI", 0, 0, 0); + display_setup_sig(); pthread__unblock_sigwinch(); repeat: @@ -693,7 +718,7 @@ static int hist_iter__top_callback(struct hist_entry_iter *iter, { struct perf_top *top = arg; struct hist_entry *he = iter->he; - struct perf_evsel *evsel = iter->evsel; + struct evsel *evsel = iter->evsel; if (perf_hpp_list.sym && single) perf_top__record_precise_ip(top, he, iter->sample, evsel, al->addr); @@ -705,7 +730,7 @@ static int hist_iter__top_callback(struct hist_entry_iter *iter, static void perf_event__process_sample(struct perf_tool *tool, const union perf_event *event, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample, struct machine *machine) { @@ -813,7 +838,7 @@ static void perf_event__process_sample(struct perf_tool *tool, static void perf_top__process_lost(struct perf_top *top, union perf_event *event, - struct perf_evsel *evsel) + struct evsel *evsel) { struct hists *hists = evsel__hists(evsel); @@ -825,7 +850,7 @@ perf_top__process_lost(struct perf_top *top, union perf_event *event, static void perf_top__process_lost_samples(struct perf_top *top, union perf_event *event, - struct perf_evsel *evsel) + struct evsel *evsel) { struct hists *hists = evsel__hists(evsel); @@ -839,7 +864,7 @@ static u64 last_timestamp; static void perf_top__mmap_read_idx(struct perf_top *top, int idx) { struct record_opts *opts = &top->record_opts; - struct perf_evlist *evlist = top->evlist; + struct evlist *evlist = top->evlist; struct perf_mmap *md; union perf_event *event; @@ -874,7 +899,7 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx) static void perf_top__mmap_read(struct perf_top *top) { bool overwrite = top->record_opts.overwrite; - struct perf_evlist *evlist = top->evlist; + struct evlist *evlist = top->evlist; int i; if (overwrite) @@ -909,10 +934,10 @@ static void perf_top__mmap_read(struct perf_top *top) static int perf_top__overwrite_check(struct perf_top *top) { struct record_opts *opts = &top->record_opts; - struct perf_evlist *evlist = top->evlist; + struct evlist *evlist = top->evlist; struct perf_evsel_config_term *term; struct list_head *config_terms; - struct perf_evsel *evsel; + struct evsel *evsel; int set, overwrite = -1; evlist__for_each_entry(evlist, evsel) { @@ -952,11 +977,11 @@ static int perf_top__overwrite_check(struct perf_top *top) } static int perf_top_overwrite_fallback(struct perf_top *top, - struct perf_evsel *evsel) + struct evsel *evsel) { struct record_opts *opts = &top->record_opts; - struct perf_evlist *evlist = top->evlist; - struct perf_evsel *counter; + struct evlist *evlist = top->evlist; + struct evsel *counter; if (!opts->overwrite) return 0; @@ -966,7 +991,7 @@ static int perf_top_overwrite_fallback(struct perf_top *top, return 0; evlist__for_each_entry(evlist, counter) - counter->attr.write_backward = false; + counter->core.attr.write_backward = false; opts->overwrite = false; pr_debug2("fall back to non-overwrite mode\n"); return 1; @@ -975,8 +1000,8 @@ static int perf_top_overwrite_fallback(struct perf_top *top, static int perf_top__start_counters(struct perf_top *top) { char msg[BUFSIZ]; - struct perf_evsel *counter; - struct perf_evlist *evlist = top->evlist; + struct evsel *counter; + struct evlist *evlist = top->evlist; struct record_opts *opts = &top->record_opts; if (perf_top__overwrite_check(top)) { @@ -989,8 +1014,8 @@ static int perf_top__start_counters(struct perf_top *top) evlist__for_each_entry(evlist, counter) { try_again: - if (perf_evsel__open(counter, top->evlist->cpus, - top->evlist->threads) < 0) { + if (evsel__open(counter, top->evlist->core.cpus, + top->evlist->core.threads) < 0) { /* * Specially handle overwrite fall back. @@ -1100,11 +1125,11 @@ static int deliver_event(struct ordered_events *qe, struct ordered_event *qevent) { struct perf_top *top = qe->data; - struct perf_evlist *evlist = top->evlist; + struct evlist *evlist = top->evlist; struct perf_session *session = top->session; union perf_event *event = qevent->event; struct perf_sample sample; - struct perf_evsel *evsel; + struct evsel *evsel; struct machine *machine; int ret = -1; @@ -1123,8 +1148,11 @@ static int deliver_event(struct ordered_events *qe, evsel = perf_evlist__id2evsel(session->evlist, sample.id); assert(evsel != NULL); - if (event->header.type == PERF_RECORD_SAMPLE) + if (event->header.type == PERF_RECORD_SAMPLE) { + if (evswitch__discard(&top->evswitch, evsel)) + return 0; ++top->samples; + } switch (sample.cpumode) { case PERF_RECORD_MISC_USER: @@ -1222,7 +1250,7 @@ static int __cmd_top(struct perf_top *top) pr_debug("Couldn't synthesize BPF events: Pre-existing BPF programs won't have symbols resolved.\n"); machine__synthesize_threads(&top->session->machines.host, &opts->target, - top->evlist->threads, false, + top->evlist->core.threads, false, top->nr_threads_synthesize); if (top->nr_threads_synthesize > 1) @@ -1255,7 +1283,7 @@ static int __cmd_top(struct perf_top *top) * so leave the check here. */ if (!target__none(&opts->target)) - perf_evlist__enable(top->evlist); + evlist__enable(top->evlist); ret = -1; if (pthread_create(&thread_process, NULL, process_thread, top)) { @@ -1509,9 +1537,10 @@ int cmd_top(int argc, const char **argv) "number of thread to run event synthesize"), OPT_BOOLEAN(0, "namespaces", &opts->record_namespaces, "Record namespaces events"), + OPTS_EVSWITCH(&top.evswitch), OPT_END() }; - struct perf_evlist *sb_evlist = NULL; + struct evlist *sb_evlist = NULL; const char * const top_usage[] = { "perf top [<options>]", NULL @@ -1524,7 +1553,7 @@ int cmd_top(int argc, const char **argv) top.annotation_opts.min_pcnt = 5; top.annotation_opts.context = 4; - top.evlist = perf_evlist__new(); + top.evlist = evlist__new(); if (top.evlist == NULL) return -ENOMEM; @@ -1536,12 +1565,16 @@ int cmd_top(int argc, const char **argv) if (argc) usage_with_options(top_usage, options); - if (!top.evlist->nr_entries && + if (!top.evlist->core.nr_entries && perf_evlist__add_default(top.evlist) < 0) { pr_err("Not enough memory for event selector list\n"); goto out_delete_evlist; } + status = evswitch__init(&top.evswitch, top.evlist, stderr); + if (status) + goto out_delete_evlist; + if (symbol_conf.report_hierarchy) { /* disable incompatible options */ symbol_conf.event_group = false; @@ -1661,7 +1694,7 @@ int cmd_top(int argc, const char **argv) perf_evlist__stop_sb_thread(sb_evlist); out_delete_evlist: - perf_evlist__delete(top.evlist); + evlist__delete(top.evlist); perf_session__delete(top.session); return status; diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 4f0bbffee05f..de126258ca10 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -1,4 +1,3 @@ -// SPDX-License-Identifier: GPL-2.0-only /* * builtin-trace.c * @@ -28,6 +27,7 @@ #include "util/env.h" #include "util/event.h" #include "util/evlist.h" +#include "util/evswitch.h" #include <subcmd/exec-cmd.h> #include "util/machine.h" #include "util/map.h" @@ -80,28 +80,34 @@ struct trace { struct perf_tool tool; struct syscalltbl *sctbl; struct { - int max; struct syscall *table; struct bpf_map *map; + struct { // per syscall BPF_MAP_TYPE_PROG_ARRAY + struct bpf_map *sys_enter, + *sys_exit; + } prog_array; struct { - struct perf_evsel *sys_enter, + struct evsel *sys_enter, *sys_exit, *augmented; } events; + struct bpf_program *unaugmented_prog; } syscalls; struct { struct bpf_map *map; } dump; struct record_opts opts; - struct perf_evlist *evlist; + struct evlist *evlist; struct machine *host; struct thread *current; + struct bpf_object *bpf_obj; struct cgroup *cgroup; u64 base_time; FILE *output; unsigned long nr_events; unsigned long nr_events_printed; unsigned long max_events; + struct evswitch evswitch; struct strlist *ev_qualifier; struct { size_t nr; @@ -122,6 +128,7 @@ struct trace { unsigned int min_stack; int raw_augmented_syscalls_args_size; bool raw_augmented_syscalls; + bool fd_path_disabled; bool sort_events; bool not_ev_qualifier; bool live; @@ -237,7 +244,7 @@ struct syscall_tp { }; }; -static int perf_evsel__init_tp_uint_field(struct perf_evsel *evsel, +static int perf_evsel__init_tp_uint_field(struct evsel *evsel, struct tp_field *field, const char *name) { @@ -253,7 +260,7 @@ static int perf_evsel__init_tp_uint_field(struct perf_evsel *evsel, ({ struct syscall_tp *sc = evsel->priv;\ perf_evsel__init_tp_uint_field(evsel, &sc->name, #name); }) -static int perf_evsel__init_tp_ptr_field(struct perf_evsel *evsel, +static int perf_evsel__init_tp_ptr_field(struct evsel *evsel, struct tp_field *field, const char *name) { @@ -269,13 +276,13 @@ static int perf_evsel__init_tp_ptr_field(struct perf_evsel *evsel, ({ struct syscall_tp *sc = evsel->priv;\ perf_evsel__init_tp_ptr_field(evsel, &sc->name, #name); }) -static void perf_evsel__delete_priv(struct perf_evsel *evsel) +static void evsel__delete_priv(struct evsel *evsel) { zfree(&evsel->priv); - perf_evsel__delete(evsel); + evsel__delete(evsel); } -static int perf_evsel__init_syscall_tp(struct perf_evsel *evsel) +static int perf_evsel__init_syscall_tp(struct evsel *evsel) { struct syscall_tp *sc = evsel->priv = malloc(sizeof(struct syscall_tp)); @@ -292,7 +299,7 @@ out_delete: return -ENOENT; } -static int perf_evsel__init_augmented_syscall_tp(struct perf_evsel *evsel, struct perf_evsel *tp) +static int perf_evsel__init_augmented_syscall_tp(struct evsel *evsel, struct evsel *tp) { struct syscall_tp *sc = evsel->priv = malloc(sizeof(struct syscall_tp)); @@ -314,21 +321,21 @@ out_delete: return -EINVAL; } -static int perf_evsel__init_augmented_syscall_tp_args(struct perf_evsel *evsel) +static int perf_evsel__init_augmented_syscall_tp_args(struct evsel *evsel) { struct syscall_tp *sc = evsel->priv; return __tp_field__init_ptr(&sc->args, sc->id.offset + sizeof(u64)); } -static int perf_evsel__init_augmented_syscall_tp_ret(struct perf_evsel *evsel) +static int perf_evsel__init_augmented_syscall_tp_ret(struct evsel *evsel) { struct syscall_tp *sc = evsel->priv; return __tp_field__init_uint(&sc->ret, sizeof(u64), sc->id.offset + sizeof(u64), evsel->needs_swap); } -static int perf_evsel__init_raw_syscall_tp(struct perf_evsel *evsel, void *handler) +static int perf_evsel__init_raw_syscall_tp(struct evsel *evsel, void *handler) { evsel->priv = malloc(sizeof(struct syscall_tp)); if (evsel->priv != NULL) { @@ -346,9 +353,9 @@ out_delete: return -ENOENT; } -static struct perf_evsel *perf_evsel__raw_syscall_newtp(const char *direction, void *handler) +static struct evsel *perf_evsel__raw_syscall_newtp(const char *direction, void *handler) { - struct perf_evsel *evsel = perf_evsel__newtp("raw_syscalls", direction); + struct evsel *evsel = perf_evsel__newtp("raw_syscalls", direction); /* older kernel (e.g., RHEL6) use syscalls:{enter,exit} */ if (IS_ERR(evsel)) @@ -363,7 +370,7 @@ static struct perf_evsel *perf_evsel__raw_syscall_newtp(const char *direction, v return evsel; out_delete: - perf_evsel__delete_priv(evsel); + evsel__delete_priv(evsel); return NULL; } @@ -688,6 +695,10 @@ struct syscall_arg_fmt { static struct syscall_fmt { const char *name; const char *alias; + struct { + const char *sys_enter, + *sys_exit; + } bpf_prog_name; struct syscall_arg_fmt arg[6]; u8 nr_args; bool errpid; @@ -700,7 +711,9 @@ static struct syscall_fmt { .arg = { [0] = { .scnprintf = SCA_X86_ARCH_PRCTL_CODE, /* code */ }, [1] = { .scnprintf = SCA_PTR, /* arg2 */ }, }, }, { .name = "bind", - .arg = { [1] = { .scnprintf = SCA_SOCKADDR, /* umyaddr */ }, }, }, + .arg = { [0] = { .scnprintf = SCA_INT, /* fd */ }, + [1] = { .scnprintf = SCA_SOCKADDR, /* umyaddr */ }, + [2] = { .scnprintf = SCA_INT, /* addrlen */ }, }, }, { .name = "bpf", .arg = { [0] = STRARRAY(cmd, bpf_cmd), }, }, { .name = "brk", .hexret = true, @@ -716,7 +729,9 @@ static struct syscall_fmt { { .name = "close", .arg = { [0] = { .scnprintf = SCA_CLOSE_FD, /* fd */ }, }, }, { .name = "connect", - .arg = { [1] = { .scnprintf = SCA_SOCKADDR, /* servaddr */ }, }, }, + .arg = { [0] = { .scnprintf = SCA_INT, /* fd */ }, + [1] = { .scnprintf = SCA_SOCKADDR, /* servaddr */ }, + [2] = { .scnprintf = SCA_INT, /* addrlen */ }, }, }, { .name = "epoll_ctl", .arg = { [1] = STRARRAY(op, epoll_ctl_ops), }, }, { .name = "eventfd2", @@ -882,6 +897,7 @@ static struct syscall_fmt { .arg = { [0] = { .scnprintf = SCA_SECCOMP_OP, /* op */ }, [1] = { .scnprintf = SCA_SECCOMP_FLAGS, /* flags */ }, }, }, { .name = "select", .timeout = true, }, + { .name = "sendfile", .alias = "sendfile64", }, { .name = "sendmmsg", .arg = { [3] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, }, }, { .name = "sendmsg", @@ -960,13 +976,19 @@ static struct syscall_fmt *syscall_fmt__find_by_alias(const char *alias) * is_exit: is this "exit" or "exit_group"? * is_open: is this "open" or "openat"? To associate the fd returned in sys_exit with the pathname in sys_enter. * args_size: sum of the sizes of the syscall arguments, anything after that is augmented stuff: pathname for openat, etc. + * nonexistent: Just a hole in the syscall table, syscall id not allocated */ struct syscall { struct tep_event *tp_format; int nr_args; int args_size; + struct { + struct bpf_program *sys_enter, + *sys_exit; + } bpf_prog; bool is_exit; bool is_open; + bool nonexistent; struct tep_format_field *args; const char *name; struct syscall_fmt *fmt; @@ -1163,7 +1185,7 @@ static const char *thread__fd_path(struct thread *thread, int fd, { struct thread_trace *ttrace = thread__priv(thread); - if (ttrace == NULL) + if (ttrace == NULL || trace->fd_path_disabled) return NULL; if (fd < 0) @@ -1368,7 +1390,7 @@ static char *trace__machine__resolve_kernel_addr(void *vmachine, unsigned long l return machine__resolve_kernel_addr(vmachine, addrp, modp); } -static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist) +static int trace__symbols_init(struct trace *trace, struct evlist *evlist) { int err = symbol__init(NULL); @@ -1384,7 +1406,7 @@ static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist) goto out; err = __machine__synthesize_threads(trace->host, &trace->tool, &trace->opts.target, - evlist->threads, trace__tool_process, false, + evlist->core.threads, trace__tool_process, false, 1); out: if (err) @@ -1471,29 +1493,22 @@ static int trace__read_syscall_info(struct trace *trace, int id) struct syscall *sc; const char *name = syscalltbl__name(trace->sctbl, id); - if (name == NULL) - return -1; - - if (id > trace->syscalls.max) { - struct syscall *nsyscalls = realloc(trace->syscalls.table, (id + 1) * sizeof(*sc)); - - if (nsyscalls == NULL) - return -1; + if (trace->syscalls.table == NULL) { + trace->syscalls.table = calloc(trace->sctbl->syscalls.max_id + 1, sizeof(*sc)); + if (trace->syscalls.table == NULL) + return -ENOMEM; + } - if (trace->syscalls.max != -1) { - memset(nsyscalls + trace->syscalls.max + 1, 0, - (id - trace->syscalls.max) * sizeof(*sc)); - } else { - memset(nsyscalls, 0, (id + 1) * sizeof(*sc)); - } + sc = trace->syscalls.table + id; + if (sc->nonexistent) + return 0; - trace->syscalls.table = nsyscalls; - trace->syscalls.max = id; + if (name == NULL) { + sc->nonexistent = true; + return 0; } - sc = trace->syscalls.table + id; sc->name = name; - sc->fmt = syscall_fmt__find(sc->name); snprintf(tp_name, sizeof(tp_name), "sys_enter_%s", sc->name); @@ -1505,10 +1520,10 @@ static int trace__read_syscall_info(struct trace *trace, int id) } if (syscall__alloc_arg_fmts(sc, IS_ERR(sc->tp_format) ? 6 : sc->tp_format->format.nr_fields)) - return -1; + return -ENOMEM; if (IS_ERR(sc->tp_format)) - return -1; + return PTR_ERR(sc->tp_format); sc->args = sc->tp_format->format.fields; /* @@ -1527,6 +1542,13 @@ static int trace__read_syscall_info(struct trace *trace, int id) return syscall__set_arg_fmts(sc); } +static int intcmp(const void *a, const void *b) +{ + const int *one = a, *another = b; + + return *one - *another; +} + static int trace__validate_ev_qualifier(struct trace *trace) { int err = 0; @@ -1590,6 +1612,7 @@ matches: } trace->ev_qualifier_ids.nr = nr_used; + qsort(trace->ev_qualifier_ids.entries, nr_used, sizeof(int), intcmp); out: if (printed_invalid_prefix) pr_debug("\n"); @@ -1600,6 +1623,22 @@ out_free: goto out; } +static __maybe_unused bool trace__syscall_enabled(struct trace *trace, int id) +{ + bool in_ev_qualifier; + + if (trace->ev_qualifier_ids.nr == 0) + return true; + + in_ev_qualifier = bsearch(&id, trace->ev_qualifier_ids.entries, + trace->ev_qualifier_ids.nr, sizeof(int), intcmp) != NULL; + + if (in_ev_qualifier) + return !trace->not_ev_qualifier; + + return trace->not_ev_qualifier; +} + /* * args is to be interpreted as a series of longs but we need to handle * 8-byte unaligned accesses. args points to raw_data within the event @@ -1738,13 +1777,14 @@ next_arg: return printed; } -typedef int (*tracepoint_handler)(struct trace *trace, struct perf_evsel *evsel, +typedef int (*tracepoint_handler)(struct trace *trace, struct evsel *evsel, union perf_event *event, struct perf_sample *sample); static struct syscall *trace__syscall_info(struct trace *trace, - struct perf_evsel *evsel, int id) + struct evsel *evsel, int id) { + int err = 0; if (id < 0) { @@ -1766,19 +1806,28 @@ static struct syscall *trace__syscall_info(struct trace *trace, return NULL; } - if ((id > trace->syscalls.max || trace->syscalls.table[id].name == NULL) && - trace__read_syscall_info(trace, id)) + err = -EINVAL; + + if (id > trace->sctbl->syscalls.max_id) + goto out_cant_read; + + if ((trace->syscalls.table == NULL || trace->syscalls.table[id].name == NULL) && + (err = trace__read_syscall_info(trace, id)) != 0) goto out_cant_read; - if ((id > trace->syscalls.max || trace->syscalls.table[id].name == NULL)) + if (trace->syscalls.table[id].name == NULL) { + if (trace->syscalls.table[id].nonexistent) + return NULL; goto out_cant_read; + } return &trace->syscalls.table[id]; out_cant_read: if (verbose > 0) { - fprintf(trace->output, "Problems reading syscall %d", id); - if (id <= trace->syscalls.max && trace->syscalls.table[id].name != NULL) + char sbuf[STRERR_BUFSIZE]; + fprintf(trace->output, "Problems reading syscall %d: %d (%s)", id, -err, str_error_r(-err, sbuf, sizeof(sbuf))); + if (id <= trace->sctbl->syscalls.max_id && trace->syscalls.table[id].name != NULL) fprintf(trace->output, "(%s)", trace->syscalls.table[id].name); fputs(" information\n", trace->output); } @@ -1839,7 +1888,7 @@ static int trace__printf_interrupted_entry(struct trace *trace) return printed; } -static int trace__fprintf_sample(struct trace *trace, struct perf_evsel *evsel, +static int trace__fprintf_sample(struct trace *trace, struct evsel *evsel, struct perf_sample *sample, struct thread *thread) { int printed = 0; @@ -1882,7 +1931,7 @@ static void *syscall__augmented_args(struct syscall *sc, struct perf_sample *sam return augmented_args; } -static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel, +static int trace__sys_enter(struct trace *trace, struct evsel *evsel, union perf_event *event __maybe_unused, struct perf_sample *sample) { @@ -1961,7 +2010,7 @@ out_put: return err; } -static int trace__fprintf_sys_enter(struct trace *trace, struct perf_evsel *evsel, +static int trace__fprintf_sys_enter(struct trace *trace, struct evsel *evsel, struct perf_sample *sample) { struct thread_trace *ttrace; @@ -1994,13 +2043,13 @@ out_put: return err; } -static int trace__resolve_callchain(struct trace *trace, struct perf_evsel *evsel, +static int trace__resolve_callchain(struct trace *trace, struct evsel *evsel, struct perf_sample *sample, struct callchain_cursor *cursor) { struct addr_location al; - int max_stack = evsel->attr.sample_max_stack ? - evsel->attr.sample_max_stack : + int max_stack = evsel->core.attr.sample_max_stack ? + evsel->core.attr.sample_max_stack : trace->max_stack; int err; @@ -2022,7 +2071,7 @@ static int trace__fprintf_callchain(struct trace *trace, struct perf_sample *sam return sample__fprintf_callchain(sample, 38, print_opts, &callchain_cursor, trace->output); } -static const char *errno_to_name(struct perf_evsel *evsel, int err) +static const char *errno_to_name(struct evsel *evsel, int err) { struct perf_env *env = perf_evsel__env(evsel); const char *arch_name = perf_env__arch(env); @@ -2030,7 +2079,7 @@ static const char *errno_to_name(struct perf_evsel *evsel, int err) return arch_syscalls__strerrno(arch_name, err); } -static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel, +static int trace__sys_exit(struct trace *trace, struct evsel *evsel, union perf_event *event __maybe_unused, struct perf_sample *sample) { @@ -2058,7 +2107,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel, ret = perf_evsel__sc_tp_uint(evsel, ret, sample); - if (sc->is_open && ret >= 0 && ttrace->filename.pending_open) { + if (!trace->fd_path_disabled && sc->is_open && ret >= 0 && ttrace->filename.pending_open) { trace__set_fd_pathname(thread, ret, ttrace->filename.name); ttrace->filename.pending_open = false; ++trace->stats.vfs_getname; @@ -2164,7 +2213,7 @@ out_put: return err; } -static int trace__vfs_getname(struct trace *trace, struct perf_evsel *evsel, +static int trace__vfs_getname(struct trace *trace, struct evsel *evsel, union perf_event *event __maybe_unused, struct perf_sample *sample) { @@ -2225,7 +2274,7 @@ out: return 0; } -static int trace__sched_stat_runtime(struct trace *trace, struct perf_evsel *evsel, +static int trace__sched_stat_runtime(struct trace *trace, struct evsel *evsel, union perf_event *event __maybe_unused, struct perf_sample *sample) { @@ -2287,7 +2336,7 @@ static void bpf_output__fprintf(struct trace *trace, ++trace->nr_events_printed; } -static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel, +static int trace__event_handler(struct trace *trace, struct evsel *evsel, union perf_event *event __maybe_unused, struct perf_sample *sample) { @@ -2353,8 +2402,8 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel, ++trace->nr_events_printed; if (evsel->max_events != ULONG_MAX && ++evsel->nr_events_printed == evsel->max_events) { - perf_evsel__disable(evsel); - perf_evsel__close(evsel); + evsel__disable(evsel); + evsel__close(evsel); } } } @@ -2389,7 +2438,7 @@ static void print_location(FILE *f, struct perf_sample *sample, } static int trace__pgfault(struct trace *trace, - struct perf_evsel *evsel, + struct evsel *evsel, union perf_event *event __maybe_unused, struct perf_sample *sample) { @@ -2415,7 +2464,7 @@ static int trace__pgfault(struct trace *trace, if (ttrace == NULL) goto out_put; - if (evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MAJ) + if (evsel->core.attr.config == PERF_COUNT_SW_PAGE_FAULTS_MAJ) ttrace->pfmaj++; else ttrace->pfmin++; @@ -2428,7 +2477,7 @@ static int trace__pgfault(struct trace *trace, trace__fprintf_entry_head(trace, thread, 0, true, sample->time, trace->output); fprintf(trace->output, "%sfault [", - evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MAJ ? + evsel->core.attr.config == PERF_COUNT_SW_PAGE_FAULTS_MAJ ? "maj" : "min"); print_location(trace->output, sample, &al, false, true); @@ -2464,7 +2513,7 @@ out_put: } static void trace__set_base_time(struct trace *trace, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample) { /* @@ -2476,14 +2525,14 @@ static void trace__set_base_time(struct trace *trace, * appears in our event stream (vfs_getname comes to mind). */ if (trace->base_time == 0 && !trace->full_time && - (evsel->attr.sample_type & PERF_SAMPLE_TIME)) + (evsel->core.attr.sample_type & PERF_SAMPLE_TIME)) trace->base_time = sample->time; } static int trace__process_sample(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct machine *machine __maybe_unused) { struct trace *trace = container_of(tool, struct trace, tool); @@ -2569,10 +2618,10 @@ static int trace__record(struct trace *trace, int argc, const char **argv) static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp); -static bool perf_evlist__add_vfs_getname(struct perf_evlist *evlist) +static bool evlist__add_vfs_getname(struct evlist *evlist) { bool found = false; - struct perf_evsel *evsel, *tmp; + struct evsel *evsel, *tmp; struct parse_events_error err = { .idx = 0, }; int ret = parse_events(evlist, "probe:vfs_getname*", &err); @@ -2589,17 +2638,17 @@ static bool perf_evlist__add_vfs_getname(struct perf_evlist *evlist) continue; } - list_del_init(&evsel->node); + list_del_init(&evsel->core.node); evsel->evlist = NULL; - perf_evsel__delete(evsel); + evsel__delete(evsel); } return found; } -static struct perf_evsel *perf_evsel__new_pgfault(u64 config) +static struct evsel *perf_evsel__new_pgfault(u64 config) { - struct perf_evsel *evsel; + struct evsel *evsel; struct perf_event_attr attr = { .type = PERF_TYPE_SOFTWARE, .mmap_data = 1, @@ -2610,7 +2659,7 @@ static struct perf_evsel *perf_evsel__new_pgfault(u64 config) event_attr_init(&attr); - evsel = perf_evsel__new(&attr); + evsel = evsel__new(&attr); if (evsel) evsel->handler = trace__pgfault; @@ -2620,7 +2669,7 @@ static struct perf_evsel *perf_evsel__new_pgfault(u64 config) static void trace__handle_event(struct trace *trace, union perf_event *event, struct perf_sample *sample) { const u32 type = event->header.type; - struct perf_evsel *evsel; + struct evsel *evsel; if (type != PERF_RECORD_SAMPLE) { trace__process_event(trace, trace->host, event, sample); @@ -2633,9 +2682,12 @@ static void trace__handle_event(struct trace *trace, union perf_event *event, st return; } + if (evswitch__discard(&trace->evswitch, evsel)) + return; + trace__set_base_time(trace, evsel, sample); - if (evsel->attr.type == PERF_TYPE_TRACEPOINT && + if (evsel->core.attr.type == PERF_TYPE_TRACEPOINT && sample->raw_data == NULL) { fprintf(trace->output, "%s sample with no payload for tid: %d, cpu %d, raw_size=%d, skipping...\n", perf_evsel__name(evsel), sample->tid, @@ -2652,8 +2704,8 @@ static void trace__handle_event(struct trace *trace, union perf_event *event, st static int trace__add_syscall_newtp(struct trace *trace) { int ret = -1; - struct perf_evlist *evlist = trace->evlist; - struct perf_evsel *sys_enter, *sys_exit; + struct evlist *evlist = trace->evlist; + struct evsel *sys_enter, *sys_exit; sys_enter = perf_evsel__raw_syscall_newtp("sys_enter", trace__sys_enter); if (sys_enter == NULL) @@ -2672,8 +2724,8 @@ static int trace__add_syscall_newtp(struct trace *trace) perf_evsel__config_callchain(sys_enter, &trace->opts, &callchain_param); perf_evsel__config_callchain(sys_exit, &trace->opts, &callchain_param); - perf_evlist__add(evlist, sys_enter); - perf_evlist__add(evlist, sys_exit); + evlist__add(evlist, sys_enter); + evlist__add(evlist, sys_exit); if (callchain_param.enabled && !trace->kernel_syscallchains) { /* @@ -2681,7 +2733,7 @@ static int trace__add_syscall_newtp(struct trace *trace) * leading to the syscall, allow overriding that for * debugging reasons using --kernel_syscall_callchains */ - sys_exit->attr.exclude_callchain_kernel = 1; + sys_exit->core.attr.exclude_callchain_kernel = 1; } trace->syscalls.events.sys_enter = sys_enter; @@ -2692,16 +2744,16 @@ out: return ret; out_delete_sys_exit: - perf_evsel__delete_priv(sys_exit); + evsel__delete_priv(sys_exit); out_delete_sys_enter: - perf_evsel__delete_priv(sys_enter); + evsel__delete_priv(sys_enter); goto out; } static int trace__set_ev_qualifier_tp_filter(struct trace *trace) { int err = -1; - struct perf_evsel *sys_exit; + struct evsel *sys_exit; char *filter = asprintf_expr_inout_ints("id", !trace->not_ev_qualifier, trace->ev_qualifier_ids.nr, trace->ev_qualifier_ids.entries); @@ -2724,6 +2776,70 @@ out_enomem: } #ifdef HAVE_LIBBPF_SUPPORT +static struct bpf_program *trace__find_bpf_program_by_title(struct trace *trace, const char *name) +{ + if (trace->bpf_obj == NULL) + return NULL; + + return bpf_object__find_program_by_title(trace->bpf_obj, name); +} + +static struct bpf_program *trace__find_syscall_bpf_prog(struct trace *trace, struct syscall *sc, + const char *prog_name, const char *type) +{ + struct bpf_program *prog; + + if (prog_name == NULL) { + char default_prog_name[256]; + scnprintf(default_prog_name, sizeof(default_prog_name), "!syscalls:sys_%s_%s", type, sc->name); + prog = trace__find_bpf_program_by_title(trace, default_prog_name); + if (prog != NULL) + goto out_found; + if (sc->fmt && sc->fmt->alias) { + scnprintf(default_prog_name, sizeof(default_prog_name), "!syscalls:sys_%s_%s", type, sc->fmt->alias); + prog = trace__find_bpf_program_by_title(trace, default_prog_name); + if (prog != NULL) + goto out_found; + } + goto out_unaugmented; + } + + prog = trace__find_bpf_program_by_title(trace, prog_name); + + if (prog != NULL) { +out_found: + return prog; + } + + pr_debug("Couldn't find BPF prog \"%s\" to associate with syscalls:sys_%s_%s, not augmenting it\n", + prog_name, type, sc->name); +out_unaugmented: + return trace->syscalls.unaugmented_prog; +} + +static void trace__init_syscall_bpf_progs(struct trace *trace, int id) +{ + struct syscall *sc = trace__syscall_info(trace, NULL, id); + + if (sc == NULL) + return; + + sc->bpf_prog.sys_enter = trace__find_syscall_bpf_prog(trace, sc, sc->fmt ? sc->fmt->bpf_prog_name.sys_enter : NULL, "enter"); + sc->bpf_prog.sys_exit = trace__find_syscall_bpf_prog(trace, sc, sc->fmt ? sc->fmt->bpf_prog_name.sys_exit : NULL, "exit"); +} + +static int trace__bpf_prog_sys_enter_fd(struct trace *trace, int id) +{ + struct syscall *sc = trace__syscall_info(trace, NULL, id); + return sc ? bpf_program__fd(sc->bpf_prog.sys_enter) : bpf_program__fd(trace->syscalls.unaugmented_prog); +} + +static int trace__bpf_prog_sys_exit_fd(struct trace *trace, int id) +{ + struct syscall *sc = trace__syscall_info(trace, NULL, id); + return sc ? bpf_program__fd(sc->bpf_prog.sys_exit) : bpf_program__fd(trace->syscalls.unaugmented_prog); +} + static void trace__init_bpf_map_syscall_args(struct trace *trace, int id, struct bpf_map_syscall_entry *entry) { struct syscall *sc = trace__syscall_info(trace, NULL, id); @@ -2755,8 +2871,10 @@ static int trace__set_ev_qualifier_bpf_filter(struct trace *trace) for (i = 0; i < trace->ev_qualifier_ids.nr; ++i) { int key = trace->ev_qualifier_ids.entries[i]; - if (value.enabled) + if (value.enabled) { trace__init_bpf_map_syscall_args(trace, key, &value); + trace__init_syscall_bpf_progs(trace, key); + } err = bpf_map_update_elem(fd, &key, &value, BPF_EXIST); if (err) @@ -2795,6 +2913,186 @@ static int trace__init_syscalls_bpf_map(struct trace *trace) return __trace__init_syscalls_bpf_map(trace, enabled); } + +static struct bpf_program *trace__find_usable_bpf_prog_entry(struct trace *trace, struct syscall *sc) +{ + struct tep_format_field *field, *candidate_field; + int id; + + /* + * We're only interested in syscalls that have a pointer: + */ + for (field = sc->args; field; field = field->next) { + if (field->flags & TEP_FIELD_IS_POINTER) + goto try_to_find_pair; + } + + return NULL; + +try_to_find_pair: + for (id = 0; id < trace->sctbl->syscalls.nr_entries; ++id) { + struct syscall *pair = trace__syscall_info(trace, NULL, id); + struct bpf_program *pair_prog; + bool is_candidate = false; + + if (pair == NULL || pair == sc || + pair->bpf_prog.sys_enter == trace->syscalls.unaugmented_prog) + continue; + + for (field = sc->args, candidate_field = pair->args; + field && candidate_field; field = field->next, candidate_field = candidate_field->next) { + bool is_pointer = field->flags & TEP_FIELD_IS_POINTER, + candidate_is_pointer = candidate_field->flags & TEP_FIELD_IS_POINTER; + + if (is_pointer) { + if (!candidate_is_pointer) { + // The candidate just doesn't copies our pointer arg, might copy other pointers we want. + continue; + } + } else { + if (candidate_is_pointer) { + // The candidate might copy a pointer we don't have, skip it. + goto next_candidate; + } + continue; + } + + if (strcmp(field->type, candidate_field->type)) + goto next_candidate; + + is_candidate = true; + } + + if (!is_candidate) + goto next_candidate; + + /* + * Check if the tentative pair syscall augmenter has more pointers, if it has, + * then it may be collecting that and we then can't use it, as it would collect + * more than what is common to the two syscalls. + */ + if (candidate_field) { + for (candidate_field = candidate_field->next; candidate_field; candidate_field = candidate_field->next) + if (candidate_field->flags & TEP_FIELD_IS_POINTER) + goto next_candidate; + } + + pair_prog = pair->bpf_prog.sys_enter; + /* + * If the pair isn't enabled, then its bpf_prog.sys_enter will not + * have been searched for, so search it here and if it returns the + * unaugmented one, then ignore it, otherwise we'll reuse that BPF + * program for a filtered syscall on a non-filtered one. + * + * For instance, we have "!syscalls:sys_enter_renameat" and that is + * useful for "renameat2". + */ + if (pair_prog == NULL) { + pair_prog = trace__find_syscall_bpf_prog(trace, pair, pair->fmt ? pair->fmt->bpf_prog_name.sys_enter : NULL, "enter"); + if (pair_prog == trace->syscalls.unaugmented_prog) + goto next_candidate; + } + + pr_debug("Reusing \"%s\" BPF sys_enter augmenter for \"%s\"\n", pair->name, sc->name); + return pair_prog; + next_candidate: + continue; + } + + return NULL; +} + +static int trace__init_syscalls_bpf_prog_array_maps(struct trace *trace) +{ + int map_enter_fd = bpf_map__fd(trace->syscalls.prog_array.sys_enter), + map_exit_fd = bpf_map__fd(trace->syscalls.prog_array.sys_exit); + int err = 0, key; + + for (key = 0; key < trace->sctbl->syscalls.nr_entries; ++key) { + int prog_fd; + + if (!trace__syscall_enabled(trace, key)) + continue; + + trace__init_syscall_bpf_progs(trace, key); + + // It'll get at least the "!raw_syscalls:unaugmented" + prog_fd = trace__bpf_prog_sys_enter_fd(trace, key); + err = bpf_map_update_elem(map_enter_fd, &key, &prog_fd, BPF_ANY); + if (err) + break; + prog_fd = trace__bpf_prog_sys_exit_fd(trace, key); + err = bpf_map_update_elem(map_exit_fd, &key, &prog_fd, BPF_ANY); + if (err) + break; + } + + /* + * Now lets do a second pass looking for enabled syscalls without + * an augmenter that have a signature that is a superset of another + * syscall with an augmenter so that we can auto-reuse it. + * + * I.e. if we have an augmenter for the "open" syscall that has + * this signature: + * + * int open(const char *pathname, int flags, mode_t mode); + * + * I.e. that will collect just the first string argument, then we + * can reuse it for the 'creat' syscall, that has this signature: + * + * int creat(const char *pathname, mode_t mode); + * + * and for: + * + * int stat(const char *pathname, struct stat *statbuf); + * int lstat(const char *pathname, struct stat *statbuf); + * + * Because the 'open' augmenter will collect the first arg as a string, + * and leave alone all the other args, which already helps with + * beautifying 'stat' and 'lstat''s pathname arg. + * + * Then, in time, when 'stat' gets an augmenter that collects both + * first and second arg (this one on the raw_syscalls:sys_exit prog + * array tail call, then that one will be used. + */ + for (key = 0; key < trace->sctbl->syscalls.nr_entries; ++key) { + struct syscall *sc = trace__syscall_info(trace, NULL, key); + struct bpf_program *pair_prog; + int prog_fd; + + if (sc == NULL || sc->bpf_prog.sys_enter == NULL) + continue; + + /* + * For now we're just reusing the sys_enter prog, and if it + * already has an augmenter, we don't need to find one. + */ + if (sc->bpf_prog.sys_enter != trace->syscalls.unaugmented_prog) + continue; + + /* + * Look at all the other syscalls for one that has a signature + * that is close enough that we can share: + */ + pair_prog = trace__find_usable_bpf_prog_entry(trace, sc); + if (pair_prog == NULL) + continue; + + sc->bpf_prog.sys_enter = pair_prog; + + /* + * Update the BPF_MAP_TYPE_PROG_SHARED for raw_syscalls:sys_enter + * with the fd for the program we're reusing: + */ + prog_fd = bpf_program__fd(sc->bpf_prog.sys_enter); + err = bpf_map_update_elem(map_enter_fd, &key, &prog_fd, BPF_ANY); + if (err) + break; + } + + + return err; +} #else static int trace__set_ev_qualifier_bpf_filter(struct trace *trace __maybe_unused) { @@ -2805,6 +3103,17 @@ static int trace__init_syscalls_bpf_map(struct trace *trace __maybe_unused) { return 0; } + +static struct bpf_program *trace__find_bpf_program_by_title(struct trace *trace __maybe_unused, + const char *name __maybe_unused) +{ + return NULL; +} + +static int trace__init_syscalls_bpf_prog_array_maps(struct trace *trace __maybe_unused) +{ + return 0; +} #endif // HAVE_LIBBPF_SUPPORT static int trace__set_ev_qualifier_filter(struct trace *trace) @@ -2879,7 +3188,7 @@ static int trace__set_filter_pids(struct trace *trace) err = bpf_map__set_filter_pids(trace->filter_pids.map, trace->filter_pids.nr, trace->filter_pids.entries); } - } else if (thread_map__pid(trace->evlist->threads, 0) == -1) { + } else if (perf_thread_map__pid(trace->evlist->core.threads, 0) == -1) { err = trace__set_filter_loop_pids(trace); } @@ -2888,7 +3197,7 @@ static int trace__set_filter_pids(struct trace *trace) static int __trace__deliver_event(struct trace *trace, union perf_event *event) { - struct perf_evlist *evlist = trace->evlist; + struct evlist *evlist = trace->evlist; struct perf_sample sample; int err; @@ -2946,8 +3255,8 @@ static int ordered_events__deliver_event(struct ordered_events *oe, static int trace__run(struct trace *trace, int argc, const char **argv) { - struct perf_evlist *evlist = trace->evlist; - struct perf_evsel *evsel, *pgfault_maj = NULL, *pgfault_min = NULL; + struct evlist *evlist = trace->evlist; + struct evsel *evsel, *pgfault_maj = NULL, *pgfault_min = NULL; int err = -1, i; unsigned long before; const bool forks = argc > 0; @@ -2960,7 +3269,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv) goto out_error_raw_syscalls; if (trace->trace_syscalls) - trace->vfs_getname = perf_evlist__add_vfs_getname(evlist); + trace->vfs_getname = evlist__add_vfs_getname(evlist); } if ((trace->trace_pgfaults & TRACE_PFMAJ)) { @@ -2968,7 +3277,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv) if (pgfault_maj == NULL) goto out_error_mem; perf_evsel__config_callchain(pgfault_maj, &trace->opts, &callchain_param); - perf_evlist__add(evlist, pgfault_maj); + evlist__add(evlist, pgfault_maj); } if ((trace->trace_pgfaults & TRACE_PFMIN)) { @@ -2976,7 +3285,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv) if (pgfault_min == NULL) goto out_error_mem; perf_evsel__config_callchain(pgfault_min, &trace->opts, &callchain_param); - perf_evlist__add(evlist, pgfault_min); + evlist__add(evlist, pgfault_min); } if (trace->sched && @@ -3038,7 +3347,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv) } } - err = perf_evlist__open(evlist); + err = evlist__open(evlist); if (err < 0) goto out_error_open; @@ -3059,6 +3368,9 @@ static int trace__run(struct trace *trace, int argc, const char **argv) if (trace->syscalls.map) trace__init_syscalls_bpf_map(trace); + if (trace->syscalls.prog_array.sys_enter) + trace__init_syscalls_bpf_prog_array_maps(trace); + if (trace->ev_qualifier_ids.nr > 0) { err = trace__set_ev_qualifier_filter(trace); if (err < 0) @@ -3070,6 +3382,19 @@ static int trace__run(struct trace *trace, int argc, const char **argv) } } + /* + * If the "close" syscall is not traced, then we will not have the + * opportunity to, in syscall_arg__scnprintf_close_fd() invalidate the + * fd->pathname table and were ending up showing the last value set by + * syscalls opening a pathname and associating it with a descriptor or + * reading it from /proc/pid/fd/ in cases where that doesn't make + * sense. + * + * So just disable this beautifier (SCA_FD, SCA_FDAT) when 'close' is + * not in use. + */ + trace->fd_path_disabled = !trace__syscall_enabled(trace, syscalltbl__id(trace->sctbl, "close")); + err = perf_evlist__apply_filters(evlist, &evsel); if (err < 0) goto out_error_apply_filters; @@ -3082,30 +3407,30 @@ static int trace__run(struct trace *trace, int argc, const char **argv) goto out_error_mmap; if (!target__none(&trace->opts.target) && !trace->opts.initial_delay) - perf_evlist__enable(evlist); + evlist__enable(evlist); if (forks) perf_evlist__start_workload(evlist); if (trace->opts.initial_delay) { usleep(trace->opts.initial_delay * 1000); - perf_evlist__enable(evlist); + evlist__enable(evlist); } - trace->multiple_threads = thread_map__pid(evlist->threads, 0) == -1 || - evlist->threads->nr > 1 || - perf_evlist__first(evlist)->attr.inherit; + trace->multiple_threads = perf_thread_map__pid(evlist->core.threads, 0) == -1 || + evlist->core.threads->nr > 1 || + perf_evlist__first(evlist)->core.attr.inherit; /* - * Now that we already used evsel->attr to ask the kernel to setup the - * events, lets reuse evsel->attr.sample_max_stack as the limit in + * Now that we already used evsel->core.attr to ask the kernel to setup the + * events, lets reuse evsel->core.attr.sample_max_stack as the limit in * trace__resolve_callchain(), allowing per-event max-stack settings * to override an explicitly set --max-stack global setting. */ evlist__for_each_entry(evlist, evsel) { if (evsel__has_callchain(evsel) && - evsel->attr.sample_max_stack == 0) - evsel->attr.sample_max_stack = trace->max_stack; + evsel->core.attr.sample_max_stack == 0) + evsel->core.attr.sample_max_stack = trace->max_stack; } again: before = trace->nr_events; @@ -3131,7 +3456,7 @@ again: goto out_disable; if (done && !draining) { - perf_evlist__disable(evlist); + evlist__disable(evlist); draining = true; } } @@ -3157,7 +3482,7 @@ again: out_disable: thread__zput(trace->current); - perf_evlist__disable(evlist); + evlist__disable(evlist); if (trace->sort_events) ordered_events__flush(&trace->oe.data, OE_FLUSH__FINAL); @@ -3178,7 +3503,7 @@ out_disable: out_delete_evlist: trace__symbols__exit(trace); - perf_evlist__delete(evlist); + evlist__delete(evlist); cgroup__put(trace->cgroup); trace->evlist = NULL; trace->live = false; @@ -3223,7 +3548,7 @@ out_errno: static int trace__replay(struct trace *trace) { - const struct perf_evsel_str_handler handlers[] = { + const struct evsel_str_handler handlers[] = { { "probe:vfs_getname", trace__vfs_getname, }, }; struct perf_data data = { @@ -3232,7 +3557,7 @@ static int trace__replay(struct trace *trace) .force = trace->force, }; struct perf_session *session; - struct perf_evsel *evsel; + struct evsel *evsel; int err = -1; trace->tool.sample = trace__process_sample; @@ -3298,10 +3623,10 @@ static int trace__replay(struct trace *trace) } evlist__for_each_entry(session->evlist, evsel) { - if (evsel->attr.type == PERF_TYPE_SOFTWARE && - (evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MAJ || - evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MIN || - evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS)) + if (evsel->core.attr.type == PERF_TYPE_SOFTWARE && + (evsel->core.attr.config == PERF_COUNT_SW_PAGE_FAULTS_MAJ || + evsel->core.attr.config == PERF_COUNT_SW_PAGE_FAULTS_MIN || + evsel->core.attr.config == PERF_COUNT_SW_PAGE_FAULTS)) evsel->handler = trace__pgfault; } @@ -3523,17 +3848,17 @@ static int parse_pagefaults(const struct option *opt, const char *str, return 0; } -static void evlist__set_evsel_handler(struct perf_evlist *evlist, void *handler) +static void evlist__set_evsel_handler(struct evlist *evlist, void *handler) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) evsel->handler = handler; } -static int evlist__set_syscall_tp_fields(struct perf_evlist *evlist) +static int evlist__set_syscall_tp_fields(struct evlist *evlist) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { if (evsel->priv || !evsel->tp_format) @@ -3660,7 +3985,7 @@ static int trace__parse_cgroups(const struct option *opt, const char *str, int u { struct trace *trace = opt->value; - if (!list_empty(&trace->evlist->entries)) + if (!list_empty(&trace->evlist->core.entries)) return parse_cgroups(opt, str, unset); trace->cgroup = evlist__findnew_cgroup(trace->evlist, str); @@ -3668,28 +3993,24 @@ static int trace__parse_cgroups(const struct option *opt, const char *str, int u return 0; } -static struct bpf_map *bpf__find_map_by_name(const char *name) +static struct bpf_map *trace__find_bpf_map_by_name(struct trace *trace, const char *name) { - struct bpf_object *obj, *tmp; - - bpf_object__for_each_safe(obj, tmp) { - struct bpf_map *map = bpf_object__find_map_by_name(obj, name); - if (map) - return map; - - } + if (trace->bpf_obj == NULL) + return NULL; - return NULL; + return bpf_object__find_map_by_name(trace->bpf_obj, name); } static void trace__set_bpf_map_filtered_pids(struct trace *trace) { - trace->filter_pids.map = bpf__find_map_by_name("pids_filtered"); + trace->filter_pids.map = trace__find_bpf_map_by_name(trace, "pids_filtered"); } static void trace__set_bpf_map_syscalls(struct trace *trace) { - trace->syscalls.map = bpf__find_map_by_name("syscalls"); + trace->syscalls.map = trace__find_bpf_map_by_name(trace, "syscalls"); + trace->syscalls.prog_array.sys_enter = trace__find_bpf_map_by_name(trace, "syscalls_sys_enter"); + trace->syscalls.prog_array.sys_exit = trace__find_bpf_map_by_name(trace, "syscalls_sys_exit"); } static int trace__config(const char *var, const char *value, void *arg) @@ -3745,9 +4066,6 @@ int cmd_trace(int argc, const char **argv) NULL }; struct trace trace = { - .syscalls = { - . max = -1, - }, .opts = { .target = { .uid = UINT_MAX, @@ -3844,11 +4162,12 @@ int cmd_trace(int argc, const char **argv) OPT_UINTEGER('D', "delay", &trace.opts.initial_delay, "ms to wait before starting measurement after program " "start"), + OPTS_EVSWITCH(&trace.evswitch), OPT_END() }; bool __maybe_unused max_stack_user_set = true; bool mmap_pages_user_set = true; - struct perf_evsel *evsel; + struct evsel *evsel; const char * const trace_subcommands[] = { "record", NULL }; int err = -1; char bf[BUFSIZ]; @@ -3856,7 +4175,7 @@ int cmd_trace(int argc, const char **argv) signal(SIGSEGV, sighandler_dump_stack); signal(SIGFPE, sighandler_dump_stack); - trace.evlist = perf_evlist__new(); + trace.evlist = evlist__new(); trace.sctbl = syscalltbl__new(); if (trace.evlist == NULL || trace.sctbl == NULL) { @@ -3895,8 +4214,23 @@ int cmd_trace(int argc, const char **argv) if (evsel) { trace.syscalls.events.augmented = evsel; + + evsel = perf_evlist__find_tracepoint_by_name(trace.evlist, "raw_syscalls:sys_enter"); + if (evsel == NULL) { + pr_err("ERROR: raw_syscalls:sys_enter not found in the augmented BPF object\n"); + goto out; + } + + if (evsel->bpf_obj == NULL) { + pr_err("ERROR: raw_syscalls:sys_enter not associated to a BPF object\n"); + goto out; + } + + trace.bpf_obj = evsel->bpf_obj; + trace__set_bpf_map_filtered_pids(&trace); trace__set_bpf_map_syscalls(&trace); + trace.syscalls.unaugmented_prog = trace__find_bpf_program_by_title(&trace, "!raw_syscalls:unaugmented"); } err = bpf__setup_stdout(trace.evlist); @@ -3909,7 +4243,7 @@ int cmd_trace(int argc, const char **argv) err = -1; if (map_dump_str) { - trace.dump.map = bpf__find_map_by_name(map_dump_str); + trace.dump.map = trace__find_bpf_map_by_name(&trace, map_dump_str); if (trace.dump.map == NULL) { pr_err("ERROR: BPF map \"%s\" not found\n", map_dump_str); goto out; @@ -3942,7 +4276,7 @@ int cmd_trace(int argc, const char **argv) symbol_conf.use_callchain = true; } - if (trace.evlist->nr_entries > 0) { + if (trace.evlist->core.nr_entries > 0) { evlist__set_evsel_handler(trace.evlist, trace__event_handler); if (evlist__set_syscall_tp_fields(trace.evlist)) { perror("failed to set syscalls:* tracepoint fields"); @@ -3977,11 +4311,26 @@ int cmd_trace(int argc, const char **argv) if (trace.syscalls.events.augmented->priv == NULL && strstr(perf_evsel__name(evsel), "syscalls:sys_enter")) { - struct perf_evsel *augmented = trace.syscalls.events.augmented; + struct evsel *augmented = trace.syscalls.events.augmented; if (perf_evsel__init_augmented_syscall_tp(augmented, evsel) || perf_evsel__init_augmented_syscall_tp_args(augmented)) goto out; + /* + * Augmented is __augmented_syscalls__ BPF_OUTPUT event + * Above we made sure we can get from the payload the tp fields + * that we get from syscalls:sys_enter tracefs format file. + */ augmented->handler = trace__sys_enter; + /* + * Now we do the same for the *syscalls:sys_enter event so that + * if we handle it directly, i.e. if the BPF prog returns 0 so + * as not to filter it, then we'll handle it just like we would + * for the BPF_OUTPUT one: + */ + if (perf_evsel__init_augmented_syscall_tp(evsel, evsel) || + perf_evsel__init_augmented_syscall_tp_args(evsel)) + goto out; + evsel->handler = trace__sys_enter; } if (strstarts(perf_evsel__name(evsel), "syscalls:sys_exit_")) { @@ -4025,7 +4374,7 @@ init_augmented_syscall_tp: trace.summary = trace.summary_only; if (!trace.trace_syscalls && !trace.trace_pgfaults && - trace.evlist->nr_entries == 0 /* Was --events used? */) { + trace.evlist->core.nr_entries == 0 /* Was --events used? */) { trace.trace_syscalls = true; } @@ -4037,6 +4386,10 @@ init_augmented_syscall_tp: } } + err = evswitch__init(&trace.evswitch, trace.evlist, stderr); + if (err) + goto out_close; + err = target__validate(&trace.opts.target); if (err) { target__strerror(&trace.opts.target, err, bf, sizeof(bf)); diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index f211c015cb76..5308b3836278 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -2,6 +2,7 @@ # SPDX-License-Identifier: GPL-2.0 HEADERS=' +include/uapi/linux/const.h include/uapi/drm/drm.h include/uapi/drm/i915_drm.h include/uapi/linux/fadvise.h @@ -19,6 +20,7 @@ include/uapi/linux/usbdevice_fs.h include/uapi/linux/vhost.h include/uapi/sound/asound.h include/linux/bits.h +include/linux/const.h include/linux/hash.h include/uapi/linux/hw_breakpoint.h arch/x86/include/asm/disabled-features.h diff --git a/tools/perf/examples/bpf/augmented_raw_syscalls.c b/tools/perf/examples/bpf/augmented_raw_syscalls.c index 2f822bb51717..79787cf4fce9 100644 --- a/tools/perf/examples/bpf/augmented_raw_syscalls.c +++ b/tools/perf/examples/bpf/augmented_raw_syscalls.c @@ -16,6 +16,7 @@ #include <unistd.h> #include <linux/limits.h> +#include <linux/socket.h> #include <pid_filter.h> /* bpf-output associated map */ @@ -33,6 +34,20 @@ struct syscall { bpf_map(syscalls, ARRAY, int, struct syscall, 512); +/* + * What to augment at entry? + * + * Pointer arg payloads (filenames, etc) passed from userspace to the kernel + */ +bpf_map(syscalls_sys_enter, PROG_ARRAY, u32, u32, 512); + +/* + * What to augment at exit? + * + * Pointer arg payloads returned from the kernel (struct stat, etc) to userspace. + */ +bpf_map(syscalls_sys_exit, PROG_ARRAY, u32, u32, 512); + struct syscall_enter_args { unsigned long long common_tp_fields; long syscall_nr; @@ -53,12 +68,18 @@ struct augmented_filename { pid_filter(pids_filtered); -struct augmented_args_filename { +struct augmented_args_payload { struct syscall_enter_args args; - struct augmented_filename filename; + union { + struct { + struct augmented_filename filename, + filename2; + }; + struct sockaddr_storage saddr; + }; }; -bpf_map(augmented_filename_map, PERCPU_ARRAY, int, struct augmented_args_filename, 1); +bpf_map(augmented_args_tmp, PERCPU_ARRAY, int, struct augmented_args_payload, 1); static inline unsigned int augmented_filename__read(struct augmented_filename *augmented_filename, @@ -88,10 +109,136 @@ unsigned int augmented_filename__read(struct augmented_filename *augmented_filen return len; } +SEC("!raw_syscalls:unaugmented") +int syscall_unaugmented(struct syscall_enter_args *args) +{ + return 1; +} + +/* + * These will be tail_called from SEC("raw_syscalls:sys_enter"), so will find in + * augmented_args_tmp what was read by that raw_syscalls:sys_enter and go + * on from there, reading the first syscall arg as a string, i.e. open's + * filename. + */ +SEC("!syscalls:sys_enter_connect") +int sys_enter_connect(struct syscall_enter_args *args) +{ + int key = 0; + struct augmented_args_payload *augmented_args = bpf_map_lookup_elem(&augmented_args_tmp, &key); + const void *sockaddr_arg = (const void *)args->args[1]; + unsigned int socklen = args->args[2]; + unsigned int len = sizeof(augmented_args->args); + + if (augmented_args == NULL) + return 1; /* Failure: don't filter */ + + if (socklen > sizeof(augmented_args->saddr)) + socklen = sizeof(augmented_args->saddr); + + probe_read(&augmented_args->saddr, socklen, sockaddr_arg); + + /* If perf_event_output fails, return non-zero so that it gets recorded unaugmented */ + return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, augmented_args, len + socklen); +} + +SEC("!syscalls:sys_enter_sendto") +int sys_enter_sendto(struct syscall_enter_args *args) +{ + int key = 0; + struct augmented_args_payload *augmented_args = bpf_map_lookup_elem(&augmented_args_tmp, &key); + const void *sockaddr_arg = (const void *)args->args[4]; + unsigned int socklen = args->args[5]; + unsigned int len = sizeof(augmented_args->args); + + if (augmented_args == NULL) + return 1; /* Failure: don't filter */ + + if (socklen > sizeof(augmented_args->saddr)) + socklen = sizeof(augmented_args->saddr); + + probe_read(&augmented_args->saddr, socklen, sockaddr_arg); + + /* If perf_event_output fails, return non-zero so that it gets recorded unaugmented */ + return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, augmented_args, len + socklen); +} + +SEC("!syscalls:sys_enter_open") +int sys_enter_open(struct syscall_enter_args *args) +{ + int key = 0; + struct augmented_args_payload *augmented_args = bpf_map_lookup_elem(&augmented_args_tmp, &key); + const void *filename_arg = (const void *)args->args[0]; + unsigned int len = sizeof(augmented_args->args); + + if (augmented_args == NULL) + return 1; /* Failure: don't filter */ + + len += augmented_filename__read(&augmented_args->filename, filename_arg, sizeof(augmented_args->filename.value)); + + /* If perf_event_output fails, return non-zero so that it gets recorded unaugmented */ + return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, augmented_args, len); +} + +SEC("!syscalls:sys_enter_openat") +int sys_enter_openat(struct syscall_enter_args *args) +{ + int key = 0; + struct augmented_args_payload *augmented_args = bpf_map_lookup_elem(&augmented_args_tmp, &key); + const void *filename_arg = (const void *)args->args[1]; + unsigned int len = sizeof(augmented_args->args); + + if (augmented_args == NULL) + return 1; /* Failure: don't filter */ + + len += augmented_filename__read(&augmented_args->filename, filename_arg, sizeof(augmented_args->filename.value)); + + /* If perf_event_output fails, return non-zero so that it gets recorded unaugmented */ + return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, augmented_args, len); +} + +SEC("!syscalls:sys_enter_rename") +int sys_enter_rename(struct syscall_enter_args *args) +{ + int key = 0; + struct augmented_args_payload *augmented_args = bpf_map_lookup_elem(&augmented_args_tmp, &key); + const void *oldpath_arg = (const void *)args->args[0], + *newpath_arg = (const void *)args->args[1]; + unsigned int len = sizeof(augmented_args->args), oldpath_len; + + if (augmented_args == NULL) + return 1; /* Failure: don't filter */ + + oldpath_len = augmented_filename__read(&augmented_args->filename, oldpath_arg, sizeof(augmented_args->filename.value)); + len += oldpath_len + augmented_filename__read((void *)(&augmented_args->filename) + oldpath_len, newpath_arg, sizeof(augmented_args->filename.value)); + + /* If perf_event_output fails, return non-zero so that it gets recorded unaugmented */ + return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, augmented_args, len); +} + +SEC("!syscalls:sys_enter_renameat") +int sys_enter_renameat(struct syscall_enter_args *args) +{ + int key = 0; + struct augmented_args_payload *augmented_args = bpf_map_lookup_elem(&augmented_args_tmp, &key); + const void *oldpath_arg = (const void *)args->args[1], + *newpath_arg = (const void *)args->args[3]; + unsigned int len = sizeof(augmented_args->args), oldpath_len; + + if (augmented_args == NULL) + return 1; /* Failure: don't filter */ + + oldpath_len = augmented_filename__read(&augmented_args->filename, oldpath_arg, sizeof(augmented_args->filename.value)); + len += oldpath_len + augmented_filename__read((void *)(&augmented_args->filename) + oldpath_len, newpath_arg, sizeof(augmented_args->filename.value)); + + /* If perf_event_output fails, return non-zero so that it gets recorded unaugmented */ + return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, augmented_args, len); +} + SEC("raw_syscalls:sys_enter") int sys_enter(struct syscall_enter_args *args) { - struct augmented_args_filename *augmented_args; + struct augmented_args_payload *augmented_args; /* * We start len, the amount of data that will be in the perf ring * buffer, if this is not filtered out by one of pid_filter__has(), @@ -105,7 +252,7 @@ int sys_enter(struct syscall_enter_args *args) struct syscall *syscall; int key = 0; - augmented_args = bpf_map_lookup_elem(&augmented_filename_map, &key); + augmented_args = bpf_map_lookup_elem(&augmented_args_tmp, &key); if (augmented_args == NULL) return 1; @@ -114,131 +261,36 @@ int sys_enter(struct syscall_enter_args *args) probe_read(&augmented_args->args, sizeof(augmented_args->args), args); - syscall = bpf_map_lookup_elem(&syscalls, &augmented_args->args.syscall_nr); - if (syscall == NULL || !syscall->enabled) - return 0; /* - * Yonghong and Edward Cree sayz: - * - * https://www.spinics.net/lists/netdev/msg531645.html - * - * >> R0=inv(id=0) R1=inv2 R6=ctx(id=0,off=0,imm=0) R7=inv64 R10=fp0,call_-1 - * >> 10: (bf) r1 = r6 - * >> 11: (07) r1 += 16 - * >> 12: (05) goto pc+2 - * >> 15: (79) r3 = *(u64 *)(r1 +0) - * >> dereference of modified ctx ptr R1 off=16 disallowed - * > Aha, we at least got a different error message this time. - * > And indeed llvm has done that optimisation, rather than the more obvious - * > 11: r3 = *(u64 *)(r1 +16) - * > because it wants to have lots of reads share a single insn. You may be able - * > to defeat that optimisation by adding compiler barriers, idk. Maybe someone - * > with llvm knowledge can figure out how to stop it (ideally, llvm would know - * > when it's generating for bpf backend and not do that). -O0? ¯\_(ツ)_/¯ - * - * The optimization mostly likes below: - * - * br1: - * ... - * r1 += 16 - * goto merge - * br2: - * ... - * r1 += 20 - * goto merge - * merge: - * *(u64 *)(r1 + 0) - * - * The compiler tries to merge common loads. There is no easy way to - * stop this compiler optimization without turning off a lot of other - * optimizations. The easiest way is to add barriers: - * - * __asm__ __volatile__("": : :"memory") - * - * after the ctx memory access to prevent their down stream merging. + * Jump to syscall specific augmenter, even if the default one, + * "!raw_syscalls:unaugmented" that will just return 1 to return the + * unagmented tracepoint payload. */ - /* - * For now copy just the first string arg, we need to improve the protocol - * and have more than one. - * - * Using the unrolled loop is not working, only when we do it manually, - * check this out later... - - u8 arg; -#pragma clang loop unroll(full) - for (arg = 0; arg < 6; ++arg) { - if (syscall->string_args_len[arg] != 0) { - filename_len = syscall->string_args_len[arg]; - filename_arg = (const void *)args->args[arg]; - __asm__ __volatile__("": : :"memory"); - break; - } - } + bpf_tail_call(args, &syscalls_sys_enter, augmented_args->args.syscall_nr); - verifier log: - -; if (syscall->string_args_len[arg] != 0) { -37: (69) r3 = *(u16 *)(r0 +2) - R0=map_value(id=0,off=0,ks=4,vs=14,imm=0) R1_w=inv0 R2_w=map_value(id=0,off=2,ks=4,vs=14,imm=0) R6=ctx(id=0,off=0,imm=0) R7=map_value(id=0,off=0,ks=4,vs=4168,imm=0) R10=fp0,call_-1 fp-8=mmmmmmmm -; if (syscall->string_args_len[arg] != 0) { -38: (55) if r3 != 0x0 goto pc+5 - R0=map_value(id=0,off=0,ks=4,vs=14,imm=0) R1=inv0 R2=map_value(id=0,off=2,ks=4,vs=14,imm=0) R3=inv0 R6=ctx(id=0,off=0,imm=0) R7=map_value(id=0,off=0,ks=4,vs=4168,imm=0) R10=fp0,call_-1 fp-8=mmmmmmmm -39: (b7) r1 = 1 -; if (syscall->string_args_len[arg] != 0) { -40: (bf) r2 = r0 -41: (07) r2 += 4 -42: (69) r3 = *(u16 *)(r0 +4) - R0=map_value(id=0,off=0,ks=4,vs=14,imm=0) R1_w=inv1 R2_w=map_value(id=0,off=4,ks=4,vs=14,imm=0) R3_w=inv0 R6=ctx(id=0,off=0,imm=0) R7=map_value(id=0,off=0,ks=4,vs=4168,imm=0) R10=fp0,call_-1 fp-8=mmmmmmmm -; if (syscall->string_args_len[arg] != 0) { -43: (15) if r3 == 0x0 goto pc+32 - R0=map_value(id=0,off=0,ks=4,vs=14,imm=0) R1=inv1 R2=map_value(id=0,off=4,ks=4,vs=14,imm=0) R3=inv(id=0,umax_value=65535,var_off=(0x0; 0xffff)) R6=ctx(id=0,off=0,imm=0) R7=map_value(id=0,off=0,ks=4,vs=4168,imm=0) R10=fp0,call_-1 fp-8=mmmmmmmm -; filename_arg = (const void *)args->args[arg]; -44: (67) r1 <<= 3 -45: (bf) r3 = r6 -46: (0f) r3 += r1 -47: (b7) r5 = 64 -48: (79) r3 = *(u64 *)(r3 +16) -dereference of modified ctx ptr R3 off=8 disallowed -processed 46 insns (limit 1000000) max_states_per_insn 0 total_states 12 peak_states 12 mark_read 7 - */ - -#define __loop_iter(arg) \ - if (syscall->string_args_len[arg] != 0) { \ - unsigned int filename_len = syscall->string_args_len[arg]; \ - const void *filename_arg = (const void *)args->args[arg]; \ - if (filename_len <= sizeof(augmented_args->filename.value)) \ - len += augmented_filename__read(&augmented_args->filename, filename_arg, filename_len); -#define loop_iter_first() __loop_iter(0); } -#define loop_iter(arg) else __loop_iter(arg); } -#define loop_iter_last(arg) else __loop_iter(arg); __asm__ __volatile__("": : :"memory"); } - - loop_iter_first() - loop_iter(1) - loop_iter(2) - loop_iter(3) - loop_iter(4) - loop_iter_last(5) - - /* If perf_event_output fails, return non-zero so that it gets recorded unaugmented */ - return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, augmented_args, len); + // If not found on the PROG_ARRAY syscalls map, then we're filtering it: + return 0; } SEC("raw_syscalls:sys_exit") int sys_exit(struct syscall_exit_args *args) { struct syscall_exit_args exit_args; - struct syscall *syscall; if (pid_filter__has(&pids_filtered, getpid())) return 0; probe_read(&exit_args, sizeof(exit_args), args); - - syscall = bpf_map_lookup_elem(&syscalls, &exit_args.syscall_nr); - if (syscall == NULL || !syscall->enabled) - return 0; - - return 1; + /* + * Jump to syscall specific return augmenter, even if the default one, + * "!raw_syscalls:unaugmented" that will just return 1 to return the + * unagmented tracepoint payload. + */ + bpf_tail_call(args, &syscalls_sys_exit, exit_args.syscall_nr); + /* + * If not found on the PROG_ARRAY syscalls map, then we're filtering it: + */ + return 0; } license(GPL); diff --git a/tools/perf/include/bpf/bpf.h b/tools/perf/include/bpf/bpf.h index 2eac6d804b2d..b422aeef5339 100644 --- a/tools/perf/include/bpf/bpf.h +++ b/tools/perf/include/bpf/bpf.h @@ -45,6 +45,8 @@ struct ____btf_map_##name __attribute__((section(".maps." #name), used)) \ static int (*bpf_map_update_elem)(struct bpf_map *map, void *key, void *value, u64 flags) = (void *)BPF_FUNC_map_update_elem; static void *(*bpf_map_lookup_elem)(struct bpf_map *map, void *key) = (void *)BPF_FUNC_map_lookup_elem; +static void (*bpf_tail_call)(void *ctx, void *map, int index) = (void *)BPF_FUNC_tail_call; + #define SEC(NAME) __attribute__((section(NAME), used)) #define probe(function, vars) \ diff --git a/tools/perf/lib/Build b/tools/perf/lib/Build new file mode 100644 index 000000000000..c31f1c111f8f --- /dev/null +++ b/tools/perf/lib/Build @@ -0,0 +1,12 @@ +libperf-y += core.o +libperf-y += cpumap.o +libperf-y += threadmap.o +libperf-y += evsel.o +libperf-y += evlist.o +libperf-y += zalloc.o +libperf-y += xyarray.o +libperf-y += lib.o + +$(OUTPUT)zalloc.o: ../../lib/zalloc.c FORCE + $(call rule_mkdir) + $(call if_changed_dep,cc_o_c) diff --git a/tools/perf/lib/Documentation/Makefile b/tools/perf/lib/Documentation/Makefile new file mode 100644 index 000000000000..586425a88795 --- /dev/null +++ b/tools/perf/lib/Documentation/Makefile @@ -0,0 +1,7 @@ +all: + rst2man man/libperf.rst > man/libperf.7 + rst2pdf tutorial/tutorial.rst + +clean: + rm -f man/libperf.7 + rm -f tutorial/tutorial.pdf diff --git a/tools/perf/lib/Documentation/man/libperf.rst b/tools/perf/lib/Documentation/man/libperf.rst new file mode 100644 index 000000000000..09a270fccb9c --- /dev/null +++ b/tools/perf/lib/Documentation/man/libperf.rst @@ -0,0 +1,100 @@ +.. SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +libperf + +The libperf library provides an API to access the linux kernel perf +events subsystem. It provides the following high level objects: + + - struct perf_cpu_map + - struct perf_thread_map + - struct perf_evlist + - struct perf_evsel + +reference +========= +Function reference by header files: + +perf/core.h +----------- +.. code-block:: c + + typedef int (\*libperf_print_fn_t)(enum libperf_print_level level, + const char \*, va_list ap); + + void libperf_set_print(libperf_print_fn_t fn); + +perf/cpumap.h +------------- +.. code-block:: c + + struct perf_cpu_map \*perf_cpu_map__dummy_new(void); + struct perf_cpu_map \*perf_cpu_map__new(const char \*cpu_list); + struct perf_cpu_map \*perf_cpu_map__read(FILE \*file); + struct perf_cpu_map \*perf_cpu_map__get(struct perf_cpu_map \*map); + void perf_cpu_map__put(struct perf_cpu_map \*map); + int perf_cpu_map__cpu(const struct perf_cpu_map \*cpus, int idx); + int perf_cpu_map__nr(const struct perf_cpu_map \*cpus); + perf_cpu_map__for_each_cpu(cpu, idx, cpus) + +perf/threadmap.h +---------------- +.. code-block:: c + + struct perf_thread_map \*perf_thread_map__new_dummy(void); + void perf_thread_map__set_pid(struct perf_thread_map \*map, int thread, pid_t pid); + char \*perf_thread_map__comm(struct perf_thread_map \*map, int thread); + struct perf_thread_map \*perf_thread_map__get(struct perf_thread_map \*map); + void perf_thread_map__put(struct perf_thread_map \*map); + +perf/evlist.h +------------- +.. code-block:: + + void perf_evlist__init(struct perf_evlist \*evlist); + void perf_evlist__add(struct perf_evlist \*evlist, + struct perf_evsel \*evsel); + void perf_evlist__remove(struct perf_evlist \*evlist, + struct perf_evsel \*evsel); + struct perf_evlist \*perf_evlist__new(void); + void perf_evlist__delete(struct perf_evlist \*evlist); + struct perf_evsel\* perf_evlist__next(struct perf_evlist \*evlist, + struct perf_evsel \*evsel); + int perf_evlist__open(struct perf_evlist \*evlist); + void perf_evlist__close(struct perf_evlist \*evlist); + void perf_evlist__enable(struct perf_evlist \*evlist); + void perf_evlist__disable(struct perf_evlist \*evlist); + perf_evlist__for_each_evsel(evlist, pos) + void perf_evlist__set_maps(struct perf_evlist \*evlist, + struct perf_cpu_map \*cpus, + struct perf_thread_map \*threads); + +perf/evsel.h +------------ +.. code-block:: c + + struct perf_counts_values { + union { + struct { + uint64_t val; + uint64_t ena; + uint64_t run; + }; + uint64_t values[3]; + }; + }; + + void perf_evsel__init(struct perf_evsel \*evsel, + struct perf_event_attr \*attr); + struct perf_evsel \*perf_evsel__new(struct perf_event_attr \*attr); + void perf_evsel__delete(struct perf_evsel \*evsel); + int perf_evsel__open(struct perf_evsel \*evsel, struct perf_cpu_map \*cpus, + struct perf_thread_map \*threads); + void perf_evsel__close(struct perf_evsel \*evsel); + int perf_evsel__read(struct perf_evsel \*evsel, int cpu, int thread, + struct perf_counts_values \*count); + int perf_evsel__enable(struct perf_evsel \*evsel); + int perf_evsel__disable(struct perf_evsel \*evsel); + int perf_evsel__apply_filter(struct perf_evsel \*evsel, const char \*filter); + struct perf_cpu_map \*perf_evsel__cpus(struct perf_evsel \*evsel); + struct perf_thread_map \*perf_evsel__threads(struct perf_evsel \*evsel); + struct perf_event_attr \*perf_evsel__attr(struct perf_evsel \*evsel); diff --git a/tools/perf/lib/Documentation/tutorial/tutorial.rst b/tools/perf/lib/Documentation/tutorial/tutorial.rst new file mode 100644 index 000000000000..7be7bc27b385 --- /dev/null +++ b/tools/perf/lib/Documentation/tutorial/tutorial.rst @@ -0,0 +1,123 @@ +.. SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +libperf tutorial +================ + +Compile and install libperf from kernel sources +=============================================== +.. code-block:: bash + + git clone git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git + cd linux/tools/perf/lib + make + sudo make install prefix=/usr + +Libperf object +============== +The libperf library provides several high level objects: + +struct perf_cpu_map + Provides a cpu list abstraction. + +struct perf_thread_map + Provides a thread list abstraction. + +struct perf_evsel + Provides an abstraction for single a perf event. + +struct perf_evlist + Gathers several struct perf_evsel object and performs functions on all of them. + +The exported API binds these objects together, +for full reference see the libperf.7 man page. + +Examples +======== +Examples aim to explain libperf functionality on simple use cases. +They are based in on a checked out linux kernel git tree: + +.. code-block:: bash + + $ cd tools/perf/lib/Documentation/tutorial/ + $ ls -d ex-* + ex-1-compile ex-2-evsel-stat ex-3-evlist-stat + +ex-1-compile example +==================== +This example shows the basic usage of *struct perf_cpu_map*, +how to create it and display its cpus: + +.. code-block:: bash + + $ cd ex-1-compile/ + $ make + gcc -o test test.c -lperf + $ ./test + 0 1 2 3 4 5 6 7 + + +The full code listing is here: + +.. code-block:: c + + 1 #include <perf/cpumap.h> + 2 + 3 int main(int argc, char **Argv) + 4 { + 5 struct perf_cpu_map *cpus; + 6 int cpu, tmp; + 7 + 8 cpus = perf_cpu_map__new(NULL); + 9 + 10 perf_cpu_map__for_each_cpu(cpu, tmp, cpus) + 11 fprintf(stdout, "%d ", cpu); + 12 + 13 fprintf(stdout, "\n"); + 14 + 15 perf_cpu_map__put(cpus); + 16 return 0; + 17 } + + +First you need to include the proper header to have *struct perf_cpumap* +declaration and functions: + +.. code-block:: c + + 1 #include <perf/cpumap.h> + + +The *struct perf_cpumap* object is created by *perf_cpu_map__new* call. +The *NULL* argument asks it to populate the object with the current online CPUs list: + +.. code-block:: c + + 8 cpus = perf_cpu_map__new(NULL); + +This is paired with a *perf_cpu_map__put*, that drops its reference at the end, possibly deleting it. + +.. code-block:: c + + 15 perf_cpu_map__put(cpus); + +The iteration through the *struct perf_cpumap* CPUs is done using the *perf_cpu_map__for_each_cpu* +macro which requires 3 arguments: + +- cpu - the cpu numer +- tmp - iteration helper variable +- cpus - the *struct perf_cpumap* object + +.. code-block:: c + + 10 perf_cpu_map__for_each_cpu(cpu, tmp, cpus) + 11 fprintf(stdout, "%d ", cpu); + +ex-2-evsel-stat example +======================= + +TBD + +ex-3-evlist-stat example +======================== + +TBD diff --git a/tools/perf/lib/Makefile b/tools/perf/lib/Makefile new file mode 100644 index 000000000000..a67efb8d9d39 --- /dev/null +++ b/tools/perf/lib/Makefile @@ -0,0 +1,158 @@ +# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +# Most of this file is copied from tools/lib/bpf/Makefile + +LIBPERF_VERSION = 0 +LIBPERF_PATCHLEVEL = 0 +LIBPERF_EXTRAVERSION = 1 + +MAKEFLAGS += --no-print-directory + +ifeq ($(srctree),) +srctree := $(patsubst %/,%,$(dir $(CURDIR))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +#$(info Determined 'srctree' to be $(srctree)) +endif + +INSTALL = install + +# Use DESTDIR for installing into a different root directory. +# This is useful for building a package. The program will be +# installed in this directory as if it was the root directory. +# Then the build tool can move it later. +DESTDIR ?= +DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))' + +include $(srctree)/tools/scripts/Makefile.include +include $(srctree)/tools/scripts/Makefile.arch + +ifeq ($(LP64), 1) + libdir_relative = lib64 +else + libdir_relative = lib +endif + +prefix ?= +libdir = $(prefix)/$(libdir_relative) + +# Shell quotes +libdir_SQ = $(subst ','\'',$(libdir)) +libdir_relative_SQ = $(subst ','\'',$(libdir_relative)) + +ifeq ("$(origin V)", "command line") + VERBOSE = $(V) +endif +ifndef VERBOSE + VERBOSE = 0 +endif + +ifeq ($(VERBOSE),1) + Q = +else + Q = @ +endif + +# Set compile option CFLAGS +ifdef EXTRA_CFLAGS + CFLAGS := $(EXTRA_CFLAGS) +else + CFLAGS := -g -Wall +endif + +INCLUDES = -I$(srctree)/tools/perf/lib/include -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(SRCARCH)/include/ -I$(srctree)/tools/arch/$(SRCARCH)/include/uapi -I$(srctree)/tools/include/uapi + +# Append required CFLAGS +override CFLAGS += $(EXTRA_WARNINGS) +override CFLAGS += -Werror -Wall +override CFLAGS += -fPIC +override CFLAGS += $(INCLUDES) +override CFLAGS += -fvisibility=hidden + +all: + +export srctree OUTPUT CC LD CFLAGS V +export DESTDIR DESTDIR_SQ + +include $(srctree)/tools/build/Makefile.include + +VERSION_SCRIPT := libperf.map + +PATCHLEVEL = $(LIBPERF_PATCHLEVEL) +EXTRAVERSION = $(LIBPERF_EXTRAVERSION) +VERSION = $(LIBPERF_VERSION).$(LIBPERF_PATCHLEVEL).$(LIBPERF_EXTRAVERSION) + +LIBPERF_SO := $(OUTPUT)libperf.so.$(VERSION) +LIBPERF_A := $(OUTPUT)libperf.a +LIBPERF_IN := $(OUTPUT)libperf-in.o +LIBPERF_PC := $(OUTPUT)libperf.pc + +LIBPERF_ALL := $(LIBPERF_A) $(OUTPUT)libperf.so* + +$(LIBPERF_IN): FORCE + $(Q)$(MAKE) $(build)=libperf + +$(LIBPERF_A): $(LIBPERF_IN) + $(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $(LIBPERF_IN) + +$(LIBPERF_SO): $(LIBPERF_IN) + $(QUIET_LINK)$(CC) --shared -Wl,-soname,libperf.so \ + -Wl,--version-script=$(VERSION_SCRIPT) $^ -o $@ + @ln -sf $(@F) $(OUTPUT)libperf.so + @ln -sf $(@F) $(OUTPUT)libperf.so.$(LIBPERF_VERSION) + + +libs: $(LIBPERF_A) $(LIBPERF_SO) $(LIBPERF_PC) + +all: fixdep + $(Q)$(MAKE) libs + +clean: + $(call QUIET_CLEAN, libperf) $(RM) $(LIBPERF_A) \ + *.o *~ *.a *.so *.so.$(VERSION) *.so.$(LIBPERF_VERSION) .*.d .*.cmd LIBPERF-CFLAGS $(LIBPERF_PC) + $(Q)$(MAKE) -C tests clean + +tests: + $(Q)$(MAKE) -C tests + $(Q)$(MAKE) -C tests run + +$(LIBPERF_PC): + $(QUIET_GEN)sed -e "s|@PREFIX@|$(prefix)|" \ + -e "s|@LIBDIR@|$(libdir_SQ)|" \ + -e "s|@VERSION@|$(VERSION)|" \ + < libperf.pc.template > $@ + +define do_install_mkdir + if [ ! -d '$(DESTDIR_SQ)$1' ]; then \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$1'; \ + fi +endef + +define do_install + if [ ! -d '$(DESTDIR_SQ)$2' ]; then \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$2'; \ + fi; \ + $(INSTALL) $1 $(if $3,-m $3,) '$(DESTDIR_SQ)$2' +endef + +install_lib: libs + $(call QUIET_INSTALL, $(LIBPERF_ALL)) \ + $(call do_install_mkdir,$(libdir_SQ)); \ + cp -fpR $(LIBPERF_ALL) $(DESTDIR)$(libdir_SQ) + +install_headers: + $(call QUIET_INSTALL, headers) \ + $(call do_install,include/perf/core.h,$(prefix)/include/perf,644); \ + $(call do_install,include/perf/cpumap.h,$(prefix)/include/perf,644); \ + $(call do_install,include/perf/threadmap.h,$(prefix)/include/perf,644); \ + $(call do_install,include/perf/evlist.h,$(prefix)/include/perf,644); \ + $(call do_install,include/perf/evsel.h,$(prefix)/include/perf,644); + +install_pkgconfig: $(LIBPERF_PC) + $(call QUIET_INSTALL, $(LIBPERF_PC)) \ + $(call do_install,$(LIBPERF_PC),$(libdir_SQ)/pkgconfig,644) + +install: install_lib install_headers install_pkgconfig + +FORCE: + +.PHONY: all install clean tests FORCE diff --git a/tools/perf/lib/core.c b/tools/perf/lib/core.c new file mode 100644 index 000000000000..29d5e3348718 --- /dev/null +++ b/tools/perf/lib/core.c @@ -0,0 +1,34 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#define __printf(a, b) __attribute__((format(printf, a, b))) + +#include <stdio.h> +#include <stdarg.h> +#include <perf/core.h> +#include "internal.h" + +static int __base_pr(enum libperf_print_level level, const char *format, + va_list args) +{ + return vfprintf(stderr, format, args); +} + +static libperf_print_fn_t __libperf_pr = __base_pr; + +void libperf_set_print(libperf_print_fn_t fn) +{ + __libperf_pr = fn; +} + +__printf(2, 3) +void libperf_print(enum libperf_print_level level, const char *format, ...) +{ + va_list args; + + if (!__libperf_pr) + return; + + va_start(args, format); + __libperf_pr(level, format, args); + va_end(args); +} diff --git a/tools/perf/lib/cpumap.c b/tools/perf/lib/cpumap.c new file mode 100644 index 000000000000..2834753576b2 --- /dev/null +++ b/tools/perf/lib/cpumap.c @@ -0,0 +1,256 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <perf/cpumap.h> +#include <stdlib.h> +#include <linux/refcount.h> +#include <internal/cpumap.h> +#include <asm/bug.h> +#include <stdio.h> +#include <string.h> +#include <unistd.h> +#include <ctype.h> +#include <limits.h> + +struct perf_cpu_map *perf_cpu_map__dummy_new(void) +{ + struct perf_cpu_map *cpus = malloc(sizeof(*cpus) + sizeof(int)); + + if (cpus != NULL) { + cpus->nr = 1; + cpus->map[0] = -1; + refcount_set(&cpus->refcnt, 1); + } + + return cpus; +} + +static void cpu_map__delete(struct perf_cpu_map *map) +{ + if (map) { + WARN_ONCE(refcount_read(&map->refcnt) != 0, + "cpu_map refcnt unbalanced\n"); + free(map); + } +} + +struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map) +{ + if (map) + refcount_inc(&map->refcnt); + return map; +} + +void perf_cpu_map__put(struct perf_cpu_map *map) +{ + if (map && refcount_dec_and_test(&map->refcnt)) + cpu_map__delete(map); +} + +static struct perf_cpu_map *cpu_map__default_new(void) +{ + struct perf_cpu_map *cpus; + int nr_cpus; + + nr_cpus = sysconf(_SC_NPROCESSORS_ONLN); + if (nr_cpus < 0) + return NULL; + + cpus = malloc(sizeof(*cpus) + nr_cpus * sizeof(int)); + if (cpus != NULL) { + int i; + + for (i = 0; i < nr_cpus; ++i) + cpus->map[i] = i; + + cpus->nr = nr_cpus; + refcount_set(&cpus->refcnt, 1); + } + + return cpus; +} + +static struct perf_cpu_map *cpu_map__trim_new(int nr_cpus, int *tmp_cpus) +{ + size_t payload_size = nr_cpus * sizeof(int); + struct perf_cpu_map *cpus = malloc(sizeof(*cpus) + payload_size); + + if (cpus != NULL) { + cpus->nr = nr_cpus; + memcpy(cpus->map, tmp_cpus, payload_size); + refcount_set(&cpus->refcnt, 1); + } + + return cpus; +} + +struct perf_cpu_map *perf_cpu_map__read(FILE *file) +{ + struct perf_cpu_map *cpus = NULL; + int nr_cpus = 0; + int *tmp_cpus = NULL, *tmp; + int max_entries = 0; + int n, cpu, prev; + char sep; + + sep = 0; + prev = -1; + for (;;) { + n = fscanf(file, "%u%c", &cpu, &sep); + if (n <= 0) + break; + if (prev >= 0) { + int new_max = nr_cpus + cpu - prev - 1; + + if (new_max >= max_entries) { + max_entries = new_max + MAX_NR_CPUS / 2; + tmp = realloc(tmp_cpus, max_entries * sizeof(int)); + if (tmp == NULL) + goto out_free_tmp; + tmp_cpus = tmp; + } + + while (++prev < cpu) + tmp_cpus[nr_cpus++] = prev; + } + if (nr_cpus == max_entries) { + max_entries += MAX_NR_CPUS; + tmp = realloc(tmp_cpus, max_entries * sizeof(int)); + if (tmp == NULL) + goto out_free_tmp; + tmp_cpus = tmp; + } + + tmp_cpus[nr_cpus++] = cpu; + if (n == 2 && sep == '-') + prev = cpu; + else + prev = -1; + if (n == 1 || sep == '\n') + break; + } + + if (nr_cpus > 0) + cpus = cpu_map__trim_new(nr_cpus, tmp_cpus); + else + cpus = cpu_map__default_new(); +out_free_tmp: + free(tmp_cpus); + return cpus; +} + +static struct perf_cpu_map *cpu_map__read_all_cpu_map(void) +{ + struct perf_cpu_map *cpus = NULL; + FILE *onlnf; + + onlnf = fopen("/sys/devices/system/cpu/online", "r"); + if (!onlnf) + return cpu_map__default_new(); + + cpus = perf_cpu_map__read(onlnf); + fclose(onlnf); + return cpus; +} + +struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list) +{ + struct perf_cpu_map *cpus = NULL; + unsigned long start_cpu, end_cpu = 0; + char *p = NULL; + int i, nr_cpus = 0; + int *tmp_cpus = NULL, *tmp; + int max_entries = 0; + + if (!cpu_list) + return cpu_map__read_all_cpu_map(); + + /* + * must handle the case of empty cpumap to cover + * TOPOLOGY header for NUMA nodes with no CPU + * ( e.g., because of CPU hotplug) + */ + if (!isdigit(*cpu_list) && *cpu_list != '\0') + goto out; + + while (isdigit(*cpu_list)) { + p = NULL; + start_cpu = strtoul(cpu_list, &p, 0); + if (start_cpu >= INT_MAX + || (*p != '\0' && *p != ',' && *p != '-')) + goto invalid; + + if (*p == '-') { + cpu_list = ++p; + p = NULL; + end_cpu = strtoul(cpu_list, &p, 0); + + if (end_cpu >= INT_MAX || (*p != '\0' && *p != ',')) + goto invalid; + + if (end_cpu < start_cpu) + goto invalid; + } else { + end_cpu = start_cpu; + } + + for (; start_cpu <= end_cpu; start_cpu++) { + /* check for duplicates */ + for (i = 0; i < nr_cpus; i++) + if (tmp_cpus[i] == (int)start_cpu) + goto invalid; + + if (nr_cpus == max_entries) { + max_entries += MAX_NR_CPUS; + tmp = realloc(tmp_cpus, max_entries * sizeof(int)); + if (tmp == NULL) + goto invalid; + tmp_cpus = tmp; + } + tmp_cpus[nr_cpus++] = (int)start_cpu; + } + if (*p) + ++p; + + cpu_list = p; + } + + if (nr_cpus > 0) + cpus = cpu_map__trim_new(nr_cpus, tmp_cpus); + else if (*cpu_list != '\0') + cpus = cpu_map__default_new(); + else + cpus = perf_cpu_map__dummy_new(); +invalid: + free(tmp_cpus); +out: + return cpus; +} + +int perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx) +{ + if (idx < cpus->nr) + return cpus->map[idx]; + + return -1; +} + +int perf_cpu_map__nr(const struct perf_cpu_map *cpus) +{ + return cpus ? cpus->nr : 1; +} + +bool perf_cpu_map__empty(const struct perf_cpu_map *map) +{ + return map ? map->map[0] == -1 : true; +} + +int perf_cpu_map__idx(struct perf_cpu_map *cpus, int cpu) +{ + int i; + + for (i = 0; i < cpus->nr; ++i) { + if (cpus->map[i] == cpu) + return i; + } + + return -1; +} diff --git a/tools/perf/lib/evlist.c b/tools/perf/lib/evlist.c new file mode 100644 index 000000000000..f4dc9a208332 --- /dev/null +++ b/tools/perf/lib/evlist.c @@ -0,0 +1,159 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <perf/evlist.h> +#include <perf/evsel.h> +#include <linux/list.h> +#include <internal/evlist.h> +#include <internal/evsel.h> +#include <linux/zalloc.h> +#include <stdlib.h> +#include <perf/cpumap.h> +#include <perf/threadmap.h> + +void perf_evlist__init(struct perf_evlist *evlist) +{ + INIT_LIST_HEAD(&evlist->entries); + evlist->nr_entries = 0; +} + +static void __perf_evlist__propagate_maps(struct perf_evlist *evlist, + struct perf_evsel *evsel) +{ + /* + * We already have cpus for evsel (via PMU sysfs) so + * keep it, if there's no target cpu list defined. + */ + if (!evsel->own_cpus || evlist->has_user_cpus) { + perf_cpu_map__put(evsel->cpus); + evsel->cpus = perf_cpu_map__get(evlist->cpus); + } else if (evsel->cpus != evsel->own_cpus) { + perf_cpu_map__put(evsel->cpus); + evsel->cpus = perf_cpu_map__get(evsel->own_cpus); + } + + perf_thread_map__put(evsel->threads); + evsel->threads = perf_thread_map__get(evlist->threads); +} + +static void perf_evlist__propagate_maps(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + + perf_evlist__for_each_evsel(evlist, evsel) + __perf_evlist__propagate_maps(evlist, evsel); +} + +void perf_evlist__add(struct perf_evlist *evlist, + struct perf_evsel *evsel) +{ + list_add_tail(&evsel->node, &evlist->entries); + evlist->nr_entries += 1; + __perf_evlist__propagate_maps(evlist, evsel); +} + +void perf_evlist__remove(struct perf_evlist *evlist, + struct perf_evsel *evsel) +{ + list_del_init(&evsel->node); + evlist->nr_entries -= 1; +} + +struct perf_evlist *perf_evlist__new(void) +{ + struct perf_evlist *evlist = zalloc(sizeof(*evlist)); + + if (evlist != NULL) + perf_evlist__init(evlist); + + return evlist; +} + +struct perf_evsel * +perf_evlist__next(struct perf_evlist *evlist, struct perf_evsel *prev) +{ + struct perf_evsel *next; + + if (!prev) { + next = list_first_entry(&evlist->entries, + struct perf_evsel, + node); + } else { + next = list_next_entry(prev, node); + } + + /* Empty list is noticed here so don't need checking on entry. */ + if (&next->node == &evlist->entries) + return NULL; + + return next; +} + +void perf_evlist__delete(struct perf_evlist *evlist) +{ + free(evlist); +} + +void perf_evlist__set_maps(struct perf_evlist *evlist, + struct perf_cpu_map *cpus, + struct perf_thread_map *threads) +{ + /* + * Allow for the possibility that one or another of the maps isn't being + * changed i.e. don't put it. Note we are assuming the maps that are + * being applied are brand new and evlist is taking ownership of the + * original reference count of 1. If that is not the case it is up to + * the caller to increase the reference count. + */ + if (cpus != evlist->cpus) { + perf_cpu_map__put(evlist->cpus); + evlist->cpus = perf_cpu_map__get(cpus); + } + + if (threads != evlist->threads) { + perf_thread_map__put(evlist->threads); + evlist->threads = perf_thread_map__get(threads); + } + + perf_evlist__propagate_maps(evlist); +} + +int perf_evlist__open(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + int err; + + perf_evlist__for_each_entry(evlist, evsel) { + err = perf_evsel__open(evsel, evsel->cpus, evsel->threads); + if (err < 0) + goto out_err; + } + + return 0; + +out_err: + perf_evlist__close(evlist); + return err; +} + +void perf_evlist__close(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + + perf_evlist__for_each_entry_reverse(evlist, evsel) + perf_evsel__close(evsel); +} + +void perf_evlist__enable(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + + perf_evlist__for_each_entry(evlist, evsel) + perf_evsel__enable(evsel); +} + +void perf_evlist__disable(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + + perf_evlist__for_each_entry(evlist, evsel) + perf_evsel__disable(evsel); +} diff --git a/tools/perf/lib/evsel.c b/tools/perf/lib/evsel.c new file mode 100644 index 000000000000..24abc80dd767 --- /dev/null +++ b/tools/perf/lib/evsel.c @@ -0,0 +1,232 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <errno.h> +#include <unistd.h> +#include <sys/syscall.h> +#include <perf/evsel.h> +#include <perf/cpumap.h> +#include <perf/threadmap.h> +#include <linux/list.h> +#include <internal/evsel.h> +#include <linux/zalloc.h> +#include <stdlib.h> +#include <internal/xyarray.h> +#include <internal/cpumap.h> +#include <internal/threadmap.h> +#include <internal/lib.h> +#include <linux/string.h> +#include <sys/ioctl.h> + +void perf_evsel__init(struct perf_evsel *evsel, struct perf_event_attr *attr) +{ + INIT_LIST_HEAD(&evsel->node); + evsel->attr = *attr; +} + +struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr) +{ + struct perf_evsel *evsel = zalloc(sizeof(*evsel)); + + if (evsel != NULL) + perf_evsel__init(evsel, attr); + + return evsel; +} + +void perf_evsel__delete(struct perf_evsel *evsel) +{ + free(evsel); +} + +#define FD(e, x, y) (*(int *) xyarray__entry(e->fd, x, y)) + +int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads) +{ + evsel->fd = xyarray__new(ncpus, nthreads, sizeof(int)); + + if (evsel->fd) { + int cpu, thread; + for (cpu = 0; cpu < ncpus; cpu++) { + for (thread = 0; thread < nthreads; thread++) { + FD(evsel, cpu, thread) = -1; + } + } + } + + return evsel->fd != NULL ? 0 : -ENOMEM; +} + +static int +sys_perf_event_open(struct perf_event_attr *attr, + pid_t pid, int cpu, int group_fd, + unsigned long flags) +{ + return syscall(__NR_perf_event_open, attr, pid, cpu, group_fd, flags); +} + +int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus, + struct perf_thread_map *threads) +{ + int cpu, thread, err = 0; + + if (cpus == NULL) { + static struct perf_cpu_map *empty_cpu_map; + + if (empty_cpu_map == NULL) { + empty_cpu_map = perf_cpu_map__dummy_new(); + if (empty_cpu_map == NULL) + return -ENOMEM; + } + + cpus = empty_cpu_map; + } + + if (threads == NULL) { + static struct perf_thread_map *empty_thread_map; + + if (empty_thread_map == NULL) { + empty_thread_map = perf_thread_map__new_dummy(); + if (empty_thread_map == NULL) + return -ENOMEM; + } + + threads = empty_thread_map; + } + + if (evsel->fd == NULL && + perf_evsel__alloc_fd(evsel, cpus->nr, threads->nr) < 0) + return -ENOMEM; + + for (cpu = 0; cpu < cpus->nr; cpu++) { + for (thread = 0; thread < threads->nr; thread++) { + int fd; + + fd = sys_perf_event_open(&evsel->attr, + threads->map[thread].pid, + cpus->map[cpu], -1, 0); + + if (fd < 0) + return -errno; + + FD(evsel, cpu, thread) = fd; + } + } + + return err; +} + +void perf_evsel__close_fd(struct perf_evsel *evsel) +{ + int cpu, thread; + + for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) + for (thread = 0; thread < xyarray__max_y(evsel->fd); ++thread) { + close(FD(evsel, cpu, thread)); + FD(evsel, cpu, thread) = -1; + } +} + +void perf_evsel__free_fd(struct perf_evsel *evsel) +{ + xyarray__delete(evsel->fd); + evsel->fd = NULL; +} + +void perf_evsel__close(struct perf_evsel *evsel) +{ + if (evsel->fd == NULL) + return; + + perf_evsel__close_fd(evsel); + perf_evsel__free_fd(evsel); +} + +int perf_evsel__read_size(struct perf_evsel *evsel) +{ + u64 read_format = evsel->attr.read_format; + int entry = sizeof(u64); /* value */ + int size = 0; + int nr = 1; + + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + size += sizeof(u64); + + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + size += sizeof(u64); + + if (read_format & PERF_FORMAT_ID) + entry += sizeof(u64); + + if (read_format & PERF_FORMAT_GROUP) { + nr = evsel->nr_members; + size += sizeof(u64); + } + + size += entry * nr; + return size; +} + +int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread, + struct perf_counts_values *count) +{ + size_t size = perf_evsel__read_size(evsel); + + memset(count, 0, sizeof(*count)); + + if (FD(evsel, cpu, thread) < 0) + return -EINVAL; + + if (readn(FD(evsel, cpu, thread), count->values, size) <= 0) + return -errno; + + return 0; +} + +static int perf_evsel__run_ioctl(struct perf_evsel *evsel, + int ioc, void *arg) +{ + int cpu, thread; + + for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) { + for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) { + int fd = FD(evsel, cpu, thread), + err = ioctl(fd, ioc, arg); + + if (err) + return err; + } + } + + return 0; +} + +int perf_evsel__enable(struct perf_evsel *evsel) +{ + return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, 0); +} + +int perf_evsel__disable(struct perf_evsel *evsel) +{ + return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, 0); +} + +int perf_evsel__apply_filter(struct perf_evsel *evsel, const char *filter) +{ + return perf_evsel__run_ioctl(evsel, + PERF_EVENT_IOC_SET_FILTER, + (void *)filter); +} + +struct perf_cpu_map *perf_evsel__cpus(struct perf_evsel *evsel) +{ + return evsel->cpus; +} + +struct perf_thread_map *perf_evsel__threads(struct perf_evsel *evsel) +{ + return evsel->threads; +} + +struct perf_event_attr *perf_evsel__attr(struct perf_evsel *evsel) +{ + return &evsel->attr; +} diff --git a/tools/perf/lib/include/internal/cpumap.h b/tools/perf/lib/include/internal/cpumap.h new file mode 100644 index 000000000000..840d4032587b --- /dev/null +++ b/tools/perf/lib/include/internal/cpumap.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LIBPERF_INTERNAL_CPUMAP_H +#define __LIBPERF_INTERNAL_CPUMAP_H + +#include <linux/refcount.h> + +struct perf_cpu_map { + refcount_t refcnt; + int nr; + int map[]; +}; + +#ifndef MAX_NR_CPUS +#define MAX_NR_CPUS 2048 +#endif + +int perf_cpu_map__idx(struct perf_cpu_map *cpus, int cpu); + +#endif /* __LIBPERF_INTERNAL_CPUMAP_H */ diff --git a/tools/perf/lib/include/internal/evlist.h b/tools/perf/lib/include/internal/evlist.h new file mode 100644 index 000000000000..448891f06e3e --- /dev/null +++ b/tools/perf/lib/include/internal/evlist.h @@ -0,0 +1,50 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LIBPERF_INTERNAL_EVLIST_H +#define __LIBPERF_INTERNAL_EVLIST_H + +#include <linux/list.h> + +struct perf_cpu_map; +struct perf_thread_map; + +struct perf_evlist { + struct list_head entries; + int nr_entries; + bool has_user_cpus; + struct perf_cpu_map *cpus; + struct perf_thread_map *threads; +}; + +/** + * __perf_evlist__for_each_entry - iterate thru all the evsels + * @list: list_head instance to iterate + * @evsel: struct perf_evsel iterator + */ +#define __perf_evlist__for_each_entry(list, evsel) \ + list_for_each_entry(evsel, list, node) + +/** + * evlist__for_each_entry - iterate thru all the evsels + * @evlist: perf_evlist instance to iterate + * @evsel: struct perf_evsel iterator + */ +#define perf_evlist__for_each_entry(evlist, evsel) \ + __perf_evlist__for_each_entry(&(evlist)->entries, evsel) + +/** + * __perf_evlist__for_each_entry_reverse - iterate thru all the evsels in reverse order + * @list: list_head instance to iterate + * @evsel: struct evsel iterator + */ +#define __perf_evlist__for_each_entry_reverse(list, evsel) \ + list_for_each_entry_reverse(evsel, list, node) + +/** + * perf_evlist__for_each_entry_reverse - iterate thru all the evsels in reverse order + * @evlist: evlist instance to iterate + * @evsel: struct evsel iterator + */ +#define perf_evlist__for_each_entry_reverse(evlist, evsel) \ + __perf_evlist__for_each_entry_reverse(&(evlist)->entries, evsel) + +#endif /* __LIBPERF_INTERNAL_EVLIST_H */ diff --git a/tools/perf/lib/include/internal/evsel.h b/tools/perf/lib/include/internal/evsel.h new file mode 100644 index 000000000000..8b854d1c9b45 --- /dev/null +++ b/tools/perf/lib/include/internal/evsel.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LIBPERF_INTERNAL_EVSEL_H +#define __LIBPERF_INTERNAL_EVSEL_H + +#include <linux/types.h> +#include <linux/perf_event.h> + +struct perf_cpu_map; +struct perf_thread_map; + +struct perf_evsel { + struct list_head node; + struct perf_event_attr attr; + struct perf_cpu_map *cpus; + struct perf_cpu_map *own_cpus; + struct perf_thread_map *threads; + struct xyarray *fd; + + /* parse modifier helper */ + int nr_members; +}; + +int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads); +void perf_evsel__close_fd(struct perf_evsel *evsel); +void perf_evsel__free_fd(struct perf_evsel *evsel); +int perf_evsel__read_size(struct perf_evsel *evsel); +int perf_evsel__apply_filter(struct perf_evsel *evsel, const char *filter); + +#endif /* __LIBPERF_INTERNAL_EVSEL_H */ diff --git a/tools/perf/lib/include/internal/lib.h b/tools/perf/lib/include/internal/lib.h new file mode 100644 index 000000000000..0b56f1201dc9 --- /dev/null +++ b/tools/perf/lib/include/internal/lib.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LIBPERF_INTERNAL_LIB_H +#define __LIBPERF_INTERNAL_LIB_H + +#include <unistd.h> + +ssize_t readn(int fd, void *buf, size_t n); +ssize_t writen(int fd, const void *buf, size_t n); + +#endif /* __LIBPERF_INTERNAL_CPUMAP_H */ diff --git a/tools/perf/lib/include/internal/tests.h b/tools/perf/lib/include/internal/tests.h new file mode 100644 index 000000000000..b7a20cd24ee1 --- /dev/null +++ b/tools/perf/lib/include/internal/tests.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LIBPERF_INTERNAL_TESTS_H +#define __LIBPERF_INTERNAL_TESTS_H + +#include <stdio.h> + +#define __T_START fprintf(stdout, "- running %s...", __FILE__) +#define __T_OK fprintf(stdout, "OK\n") +#define __T_FAIL fprintf(stdout, "FAIL\n") + +#define __T(text, cond) \ +do { \ + if (!(cond)) { \ + fprintf(stderr, "FAILED %s:%d %s\n", __FILE__, __LINE__, text); \ + return -1; \ + } \ +} while (0) + +#endif /* __LIBPERF_INTERNAL_TESTS_H */ diff --git a/tools/perf/lib/include/internal/threadmap.h b/tools/perf/lib/include/internal/threadmap.h new file mode 100644 index 000000000000..df748baf9eda --- /dev/null +++ b/tools/perf/lib/include/internal/threadmap.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LIBPERF_INTERNAL_THREADMAP_H +#define __LIBPERF_INTERNAL_THREADMAP_H + +#include <linux/refcount.h> +#include <sys/types.h> +#include <unistd.h> + +struct thread_map_data { + pid_t pid; + char *comm; +}; + +struct perf_thread_map { + refcount_t refcnt; + int nr; + int err_thread; + struct thread_map_data map[]; +}; + +struct perf_thread_map *perf_thread_map__realloc(struct perf_thread_map *map, int nr); + +#endif /* __LIBPERF_INTERNAL_THREADMAP_H */ diff --git a/tools/perf/util/xyarray.h b/tools/perf/lib/include/internal/xyarray.h index 7ffe562e7ae7..51e35d6c8ec4 100644 --- a/tools/perf/util/xyarray.h +++ b/tools/perf/lib/include/internal/xyarray.h @@ -1,7 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _PERF_XYARRAY_H_ -#define _PERF_XYARRAY_H_ 1 +#ifndef __LIBPERF_INTERNAL_XYARRAY_H +#define __LIBPERF_INTERNAL_XYARRAY_H +#include <linux/compiler.h> #include <sys/types.h> struct xyarray { @@ -10,7 +11,7 @@ struct xyarray { size_t entries; size_t max_x; size_t max_y; - char contents[]; + char contents[] __aligned(8); }; struct xyarray *xyarray__new(int xlen, int ylen, size_t entry_size); @@ -32,4 +33,4 @@ static inline int xyarray__max_x(struct xyarray *xy) return xy->max_x; } -#endif /* _PERF_XYARRAY_H_ */ +#endif /* __LIBPERF_INTERNAL_XYARRAY_H */ diff --git a/tools/perf/lib/include/perf/core.h b/tools/perf/lib/include/perf/core.h new file mode 100644 index 000000000000..c341a7b2c874 --- /dev/null +++ b/tools/perf/lib/include/perf/core.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LIBPERF_CORE_H +#define __LIBPERF_CORE_H + +#include <stdarg.h> + +#ifndef LIBPERF_API +#define LIBPERF_API __attribute__((visibility("default"))) +#endif + +enum libperf_print_level { + LIBPERF_WARN, + LIBPERF_INFO, + LIBPERF_DEBUG, +}; + +typedef int (*libperf_print_fn_t)(enum libperf_print_level level, + const char *, va_list ap); + +LIBPERF_API void libperf_set_print(libperf_print_fn_t fn); + +#endif /* __LIBPERF_CORE_H */ diff --git a/tools/perf/lib/include/perf/cpumap.h b/tools/perf/lib/include/perf/cpumap.h new file mode 100644 index 000000000000..8aa995c59498 --- /dev/null +++ b/tools/perf/lib/include/perf/cpumap.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LIBPERF_CPUMAP_H +#define __LIBPERF_CPUMAP_H + +#include <perf/core.h> +#include <stdio.h> +#include <stdbool.h> + +struct perf_cpu_map; + +LIBPERF_API struct perf_cpu_map *perf_cpu_map__dummy_new(void); +LIBPERF_API struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list); +LIBPERF_API struct perf_cpu_map *perf_cpu_map__read(FILE *file); +LIBPERF_API struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map); +LIBPERF_API void perf_cpu_map__put(struct perf_cpu_map *map); +LIBPERF_API int perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx); +LIBPERF_API int perf_cpu_map__nr(const struct perf_cpu_map *cpus); +LIBPERF_API bool perf_cpu_map__empty(const struct perf_cpu_map *map); + +#define perf_cpu_map__for_each_cpu(cpu, idx, cpus) \ + for ((idx) = 0, (cpu) = perf_cpu_map__cpu(cpus, idx); \ + (idx) < perf_cpu_map__nr(cpus); \ + (idx)++, (cpu) = perf_cpu_map__cpu(cpus, idx)) + +#endif /* __LIBPERF_CPUMAP_H */ diff --git a/tools/perf/lib/include/perf/evlist.h b/tools/perf/lib/include/perf/evlist.h new file mode 100644 index 000000000000..38365f8f3fba --- /dev/null +++ b/tools/perf/lib/include/perf/evlist.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LIBPERF_EVLIST_H +#define __LIBPERF_EVLIST_H + +#include <perf/core.h> + +struct perf_evlist; +struct perf_evsel; +struct perf_cpu_map; +struct perf_thread_map; + +LIBPERF_API void perf_evlist__init(struct perf_evlist *evlist); +LIBPERF_API void perf_evlist__add(struct perf_evlist *evlist, + struct perf_evsel *evsel); +LIBPERF_API void perf_evlist__remove(struct perf_evlist *evlist, + struct perf_evsel *evsel); +LIBPERF_API struct perf_evlist *perf_evlist__new(void); +LIBPERF_API void perf_evlist__delete(struct perf_evlist *evlist); +LIBPERF_API struct perf_evsel* perf_evlist__next(struct perf_evlist *evlist, + struct perf_evsel *evsel); +LIBPERF_API int perf_evlist__open(struct perf_evlist *evlist); +LIBPERF_API void perf_evlist__close(struct perf_evlist *evlist); +LIBPERF_API void perf_evlist__enable(struct perf_evlist *evlist); +LIBPERF_API void perf_evlist__disable(struct perf_evlist *evlist); + +#define perf_evlist__for_each_evsel(evlist, pos) \ + for ((pos) = perf_evlist__next((evlist), NULL); \ + (pos) != NULL; \ + (pos) = perf_evlist__next((evlist), (pos))) + +LIBPERF_API void perf_evlist__set_maps(struct perf_evlist *evlist, + struct perf_cpu_map *cpus, + struct perf_thread_map *threads); + +#endif /* __LIBPERF_EVLIST_H */ diff --git a/tools/perf/lib/include/perf/evsel.h b/tools/perf/lib/include/perf/evsel.h new file mode 100644 index 000000000000..4388667f265c --- /dev/null +++ b/tools/perf/lib/include/perf/evsel.h @@ -0,0 +1,39 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LIBPERF_EVSEL_H +#define __LIBPERF_EVSEL_H + +#include <stdint.h> +#include <perf/core.h> + +struct perf_evsel; +struct perf_event_attr; +struct perf_cpu_map; +struct perf_thread_map; + +struct perf_counts_values { + union { + struct { + uint64_t val; + uint64_t ena; + uint64_t run; + }; + uint64_t values[3]; + }; +}; + +LIBPERF_API void perf_evsel__init(struct perf_evsel *evsel, + struct perf_event_attr *attr); +LIBPERF_API struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr); +LIBPERF_API void perf_evsel__delete(struct perf_evsel *evsel); +LIBPERF_API int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus, + struct perf_thread_map *threads); +LIBPERF_API void perf_evsel__close(struct perf_evsel *evsel); +LIBPERF_API int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread, + struct perf_counts_values *count); +LIBPERF_API int perf_evsel__enable(struct perf_evsel *evsel); +LIBPERF_API int perf_evsel__disable(struct perf_evsel *evsel); +LIBPERF_API struct perf_cpu_map *perf_evsel__cpus(struct perf_evsel *evsel); +LIBPERF_API struct perf_thread_map *perf_evsel__threads(struct perf_evsel *evsel); +LIBPERF_API struct perf_event_attr *perf_evsel__attr(struct perf_evsel *evsel); + +#endif /* __LIBPERF_EVSEL_H */ diff --git a/tools/perf/lib/include/perf/threadmap.h b/tools/perf/lib/include/perf/threadmap.h new file mode 100644 index 000000000000..a7c50de8d010 --- /dev/null +++ b/tools/perf/lib/include/perf/threadmap.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LIBPERF_THREADMAP_H +#define __LIBPERF_THREADMAP_H + +#include <perf/core.h> +#include <sys/types.h> + +struct perf_thread_map; + +LIBPERF_API struct perf_thread_map *perf_thread_map__new_dummy(void); + +LIBPERF_API void perf_thread_map__set_pid(struct perf_thread_map *map, int thread, pid_t pid); +LIBPERF_API char *perf_thread_map__comm(struct perf_thread_map *map, int thread); +LIBPERF_API int perf_thread_map__nr(struct perf_thread_map *threads); +LIBPERF_API pid_t perf_thread_map__pid(struct perf_thread_map *map, int thread); + +LIBPERF_API struct perf_thread_map *perf_thread_map__get(struct perf_thread_map *map); +LIBPERF_API void perf_thread_map__put(struct perf_thread_map *map); + +#endif /* __LIBPERF_THREADMAP_H */ diff --git a/tools/perf/lib/internal.h b/tools/perf/lib/internal.h new file mode 100644 index 000000000000..dc92f241732e --- /dev/null +++ b/tools/perf/lib/internal.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LIBPERF_INTERNAL_H +#define __LIBPERF_INTERNAL_H + +void libperf_print(enum libperf_print_level level, + const char *format, ...) + __attribute__((format(printf, 2, 3))); + +#define __pr(level, fmt, ...) \ +do { \ + libperf_print(level, "libperf: " fmt, ##__VA_ARGS__); \ +} while (0) + +#define pr_warning(fmt, ...) __pr(LIBPERF_WARN, fmt, ##__VA_ARGS__) +#define pr_info(fmt, ...) __pr(LIBPERF_INFO, fmt, ##__VA_ARGS__) +#define pr_debug(fmt, ...) __pr(LIBPERF_DEBUG, fmt, ##__VA_ARGS__) + +#endif /* __LIBPERF_INTERNAL_H */ diff --git a/tools/perf/lib/lib.c b/tools/perf/lib/lib.c new file mode 100644 index 000000000000..2a81819c3b8c --- /dev/null +++ b/tools/perf/lib/lib.c @@ -0,0 +1,46 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <unistd.h> +#include <stdbool.h> +#include <errno.h> +#include <linux/kernel.h> +#include <internal/lib.h> + +static ssize_t ion(bool is_read, int fd, void *buf, size_t n) +{ + void *buf_start = buf; + size_t left = n; + + while (left) { + /* buf must be treated as const if !is_read. */ + ssize_t ret = is_read ? read(fd, buf, left) : + write(fd, buf, left); + + if (ret < 0 && errno == EINTR) + continue; + if (ret <= 0) + return ret; + + left -= ret; + buf += ret; + } + + BUG_ON((size_t)(buf - buf_start) != n); + return n; +} + +/* + * Read exactly 'n' bytes or return an error. + */ +ssize_t readn(int fd, void *buf, size_t n) +{ + return ion(true, fd, buf, n); +} + +/* + * Write exactly 'n' bytes or return an error. + */ +ssize_t writen(int fd, const void *buf, size_t n) +{ + /* ion does not modify buf. */ + return ion(false, fd, (void *)buf, n); +} diff --git a/tools/perf/lib/libperf.map b/tools/perf/lib/libperf.map new file mode 100644 index 000000000000..dc4d66363bc4 --- /dev/null +++ b/tools/perf/lib/libperf.map @@ -0,0 +1,43 @@ +LIBPERF_0.0.1 { + global: + libperf_set_print; + perf_cpu_map__dummy_new; + perf_cpu_map__get; + perf_cpu_map__put; + perf_cpu_map__new; + perf_cpu_map__read; + perf_cpu_map__nr; + perf_cpu_map__cpu; + perf_cpu_map__empty; + perf_thread_map__new_dummy; + perf_thread_map__set_pid; + perf_thread_map__comm; + perf_thread_map__nr; + perf_thread_map__pid; + perf_thread_map__get; + perf_thread_map__put; + perf_evsel__new; + perf_evsel__delete; + perf_evsel__enable; + perf_evsel__disable; + perf_evsel__init; + perf_evsel__open; + perf_evsel__close; + perf_evsel__read; + perf_evsel__cpus; + perf_evsel__threads; + perf_evsel__attr; + perf_evlist__new; + perf_evlist__delete; + perf_evlist__open; + perf_evlist__close; + perf_evlist__enable; + perf_evlist__disable; + perf_evlist__init; + perf_evlist__add; + perf_evlist__remove; + perf_evlist__next; + perf_evlist__set_maps; + local: + *; +}; diff --git a/tools/perf/lib/libperf.pc.template b/tools/perf/lib/libperf.pc.template new file mode 100644 index 000000000000..117e4a237b55 --- /dev/null +++ b/tools/perf/lib/libperf.pc.template @@ -0,0 +1,11 @@ +# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +prefix=@PREFIX@ +libdir=@LIBDIR@ +includedir=${prefix}/include + +Name: libperf +Description: perf library +Version: @VERSION@ +Libs: -L${libdir} -lperf +Cflags: -I${includedir} diff --git a/tools/perf/lib/tests/Makefile b/tools/perf/lib/tests/Makefile new file mode 100644 index 000000000000..1ee4e9ba848b --- /dev/null +++ b/tools/perf/lib/tests/Makefile @@ -0,0 +1,38 @@ +# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +TESTS = test-cpumap test-threadmap test-evlist test-evsel + +TESTS_SO := $(addsuffix -so,$(TESTS)) +TESTS_A := $(addsuffix -a,$(TESTS)) + +# Set compile option CFLAGS +ifdef EXTRA_CFLAGS + CFLAGS := $(EXTRA_CFLAGS) +else + CFLAGS := -g -Wall +endif + +all: + +include $(srctree)/tools/scripts/Makefile.include + +INCLUDE = -I$(srctree)/tools/perf/lib/include -I$(srctree)/tools/include + +$(TESTS_A): FORCE + $(QUIET_LINK)$(CC) $(INCLUDE) $(CFLAGS) -o $@ $(subst -a,.c,$@) ../libperf.a + +$(TESTS_SO): FORCE + $(QUIET_LINK)$(CC) $(INCLUDE) $(CFLAGS) -L.. -o $@ $(subst -so,.c,$@) -lperf + +all: $(TESTS_A) $(TESTS_SO) + +run: + @echo "running static:" + @for i in $(TESTS_A); do ./$$i; done + @echo "running dynamic:" + @for i in $(TESTS_SO); do LD_LIBRARY_PATH=../ ./$$i; done + +clean: + $(call QUIET_CLEAN, tests)$(RM) $(TESTS_A) $(TESTS_SO) + +.PHONY: all clean FORCE diff --git a/tools/perf/lib/tests/test-cpumap.c b/tools/perf/lib/tests/test-cpumap.c new file mode 100644 index 000000000000..76a43cfb83a1 --- /dev/null +++ b/tools/perf/lib/tests/test-cpumap.c @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <perf/cpumap.h> +#include <internal/tests.h> + +int main(int argc, char **argv) +{ + struct perf_cpu_map *cpus; + + __T_START; + + cpus = perf_cpu_map__dummy_new(); + if (!cpus) + return -1; + + perf_cpu_map__get(cpus); + perf_cpu_map__put(cpus); + perf_cpu_map__put(cpus); + + __T_OK; + return 0; +} diff --git a/tools/perf/lib/tests/test-evlist.c b/tools/perf/lib/tests/test-evlist.c new file mode 100644 index 000000000000..4e1407f20ffd --- /dev/null +++ b/tools/perf/lib/tests/test-evlist.c @@ -0,0 +1,186 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/perf_event.h> +#include <perf/cpumap.h> +#include <perf/threadmap.h> +#include <perf/evlist.h> +#include <perf/evsel.h> +#include <internal/tests.h> + +static int test_stat_cpu(void) +{ + struct perf_cpu_map *cpus; + struct perf_evlist *evlist; + struct perf_evsel *evsel; + struct perf_event_attr attr1 = { + .type = PERF_TYPE_SOFTWARE, + .config = PERF_COUNT_SW_CPU_CLOCK, + }; + struct perf_event_attr attr2 = { + .type = PERF_TYPE_SOFTWARE, + .config = PERF_COUNT_SW_TASK_CLOCK, + }; + int err, cpu, tmp; + + cpus = perf_cpu_map__new(NULL); + __T("failed to create cpus", cpus); + + evlist = perf_evlist__new(); + __T("failed to create evlist", evlist); + + evsel = perf_evsel__new(&attr1); + __T("failed to create evsel1", evsel); + + perf_evlist__add(evlist, evsel); + + evsel = perf_evsel__new(&attr2); + __T("failed to create evsel2", evsel); + + perf_evlist__add(evlist, evsel); + + perf_evlist__set_maps(evlist, cpus, NULL); + + err = perf_evlist__open(evlist); + __T("failed to open evsel", err == 0); + + perf_evlist__for_each_evsel(evlist, evsel) { + cpus = perf_evsel__cpus(evsel); + + perf_cpu_map__for_each_cpu(cpu, tmp, cpus) { + struct perf_counts_values counts = { .val = 0 }; + + perf_evsel__read(evsel, cpu, 0, &counts); + __T("failed to read value for evsel", counts.val != 0); + } + } + + perf_evlist__close(evlist); + perf_evlist__delete(evlist); + + perf_cpu_map__put(cpus); + return 0; +} + +static int test_stat_thread(void) +{ + struct perf_counts_values counts = { .val = 0 }; + struct perf_thread_map *threads; + struct perf_evlist *evlist; + struct perf_evsel *evsel; + struct perf_event_attr attr1 = { + .type = PERF_TYPE_SOFTWARE, + .config = PERF_COUNT_SW_CPU_CLOCK, + }; + struct perf_event_attr attr2 = { + .type = PERF_TYPE_SOFTWARE, + .config = PERF_COUNT_SW_TASK_CLOCK, + }; + int err; + + threads = perf_thread_map__new_dummy(); + __T("failed to create threads", threads); + + perf_thread_map__set_pid(threads, 0, 0); + + evlist = perf_evlist__new(); + __T("failed to create evlist", evlist); + + evsel = perf_evsel__new(&attr1); + __T("failed to create evsel1", evsel); + + perf_evlist__add(evlist, evsel); + + evsel = perf_evsel__new(&attr2); + __T("failed to create evsel2", evsel); + + perf_evlist__add(evlist, evsel); + + perf_evlist__set_maps(evlist, NULL, threads); + + err = perf_evlist__open(evlist); + __T("failed to open evsel", err == 0); + + perf_evlist__for_each_evsel(evlist, evsel) { + perf_evsel__read(evsel, 0, 0, &counts); + __T("failed to read value for evsel", counts.val != 0); + } + + perf_evlist__close(evlist); + perf_evlist__delete(evlist); + + perf_thread_map__put(threads); + return 0; +} + +static int test_stat_thread_enable(void) +{ + struct perf_counts_values counts = { .val = 0 }; + struct perf_thread_map *threads; + struct perf_evlist *evlist; + struct perf_evsel *evsel; + struct perf_event_attr attr1 = { + .type = PERF_TYPE_SOFTWARE, + .config = PERF_COUNT_SW_CPU_CLOCK, + .disabled = 1, + }; + struct perf_event_attr attr2 = { + .type = PERF_TYPE_SOFTWARE, + .config = PERF_COUNT_SW_TASK_CLOCK, + .disabled = 1, + }; + int err; + + threads = perf_thread_map__new_dummy(); + __T("failed to create threads", threads); + + perf_thread_map__set_pid(threads, 0, 0); + + evlist = perf_evlist__new(); + __T("failed to create evlist", evlist); + + evsel = perf_evsel__new(&attr1); + __T("failed to create evsel1", evsel); + + perf_evlist__add(evlist, evsel); + + evsel = perf_evsel__new(&attr2); + __T("failed to create evsel2", evsel); + + perf_evlist__add(evlist, evsel); + + perf_evlist__set_maps(evlist, NULL, threads); + + err = perf_evlist__open(evlist); + __T("failed to open evsel", err == 0); + + perf_evlist__for_each_evsel(evlist, evsel) { + perf_evsel__read(evsel, 0, 0, &counts); + __T("failed to read value for evsel", counts.val == 0); + } + + perf_evlist__enable(evlist); + + perf_evlist__for_each_evsel(evlist, evsel) { + perf_evsel__read(evsel, 0, 0, &counts); + __T("failed to read value for evsel", counts.val != 0); + } + + perf_evlist__disable(evlist); + + perf_evlist__close(evlist); + perf_evlist__delete(evlist); + + perf_thread_map__put(threads); + return 0; +} + +int main(int argc, char **argv) +{ + __T_START; + + test_stat_cpu(); + test_stat_thread(); + test_stat_thread_enable(); + + __T_OK; + return 0; +} diff --git a/tools/perf/lib/tests/test-evsel.c b/tools/perf/lib/tests/test-evsel.c new file mode 100644 index 000000000000..2c648fe5617e --- /dev/null +++ b/tools/perf/lib/tests/test-evsel.c @@ -0,0 +1,125 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/perf_event.h> +#include <perf/cpumap.h> +#include <perf/threadmap.h> +#include <perf/evsel.h> +#include <internal/tests.h> + +static int test_stat_cpu(void) +{ + struct perf_cpu_map *cpus; + struct perf_evsel *evsel; + struct perf_event_attr attr = { + .type = PERF_TYPE_SOFTWARE, + .config = PERF_COUNT_SW_CPU_CLOCK, + }; + int err, cpu, tmp; + + cpus = perf_cpu_map__new(NULL); + __T("failed to create cpus", cpus); + + evsel = perf_evsel__new(&attr); + __T("failed to create evsel", evsel); + + err = perf_evsel__open(evsel, cpus, NULL); + __T("failed to open evsel", err == 0); + + perf_cpu_map__for_each_cpu(cpu, tmp, cpus) { + struct perf_counts_values counts = { .val = 0 }; + + perf_evsel__read(evsel, cpu, 0, &counts); + __T("failed to read value for evsel", counts.val != 0); + } + + perf_evsel__close(evsel); + perf_evsel__delete(evsel); + + perf_cpu_map__put(cpus); + return 0; +} + +static int test_stat_thread(void) +{ + struct perf_counts_values counts = { .val = 0 }; + struct perf_thread_map *threads; + struct perf_evsel *evsel; + struct perf_event_attr attr = { + .type = PERF_TYPE_SOFTWARE, + .config = PERF_COUNT_SW_TASK_CLOCK, + }; + int err; + + threads = perf_thread_map__new_dummy(); + __T("failed to create threads", threads); + + perf_thread_map__set_pid(threads, 0, 0); + + evsel = perf_evsel__new(&attr); + __T("failed to create evsel", evsel); + + err = perf_evsel__open(evsel, NULL, threads); + __T("failed to open evsel", err == 0); + + perf_evsel__read(evsel, 0, 0, &counts); + __T("failed to read value for evsel", counts.val != 0); + + perf_evsel__close(evsel); + perf_evsel__delete(evsel); + + perf_thread_map__put(threads); + return 0; +} + +static int test_stat_thread_enable(void) +{ + struct perf_counts_values counts = { .val = 0 }; + struct perf_thread_map *threads; + struct perf_evsel *evsel; + struct perf_event_attr attr = { + .type = PERF_TYPE_SOFTWARE, + .config = PERF_COUNT_SW_TASK_CLOCK, + .disabled = 1, + }; + int err; + + threads = perf_thread_map__new_dummy(); + __T("failed to create threads", threads); + + perf_thread_map__set_pid(threads, 0, 0); + + evsel = perf_evsel__new(&attr); + __T("failed to create evsel", evsel); + + err = perf_evsel__open(evsel, NULL, threads); + __T("failed to open evsel", err == 0); + + perf_evsel__read(evsel, 0, 0, &counts); + __T("failed to read value for evsel", counts.val == 0); + + err = perf_evsel__enable(evsel); + __T("failed to enable evsel", err == 0); + + perf_evsel__read(evsel, 0, 0, &counts); + __T("failed to read value for evsel", counts.val != 0); + + err = perf_evsel__disable(evsel); + __T("failed to enable evsel", err == 0); + + perf_evsel__close(evsel); + perf_evsel__delete(evsel); + + perf_thread_map__put(threads); + return 0; +} + +int main(int argc, char **argv) +{ + __T_START; + + test_stat_cpu(); + test_stat_thread(); + test_stat_thread_enable(); + + __T_OK; + return 0; +} diff --git a/tools/perf/lib/tests/test-threadmap.c b/tools/perf/lib/tests/test-threadmap.c new file mode 100644 index 000000000000..10a4f4cbbdd5 --- /dev/null +++ b/tools/perf/lib/tests/test-threadmap.c @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <perf/threadmap.h> +#include <internal/tests.h> + +int main(int argc, char **argv) +{ + struct perf_thread_map *threads; + + __T_START; + + threads = perf_thread_map__new_dummy(); + if (!threads) + return -1; + + perf_thread_map__get(threads); + perf_thread_map__put(threads); + perf_thread_map__put(threads); + + __T_OK; + return 0; +} diff --git a/tools/perf/lib/threadmap.c b/tools/perf/lib/threadmap.c new file mode 100644 index 000000000000..e92c368b0a6c --- /dev/null +++ b/tools/perf/lib/threadmap.c @@ -0,0 +1,91 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <perf/threadmap.h> +#include <stdlib.h> +#include <linux/refcount.h> +#include <internal/threadmap.h> +#include <string.h> +#include <asm/bug.h> +#include <stdio.h> + +static void perf_thread_map__reset(struct perf_thread_map *map, int start, int nr) +{ + size_t size = (nr - start) * sizeof(map->map[0]); + + memset(&map->map[start], 0, size); + map->err_thread = -1; +} + +struct perf_thread_map *perf_thread_map__realloc(struct perf_thread_map *map, int nr) +{ + size_t size = sizeof(*map) + sizeof(map->map[0]) * nr; + int start = map ? map->nr : 0; + + map = realloc(map, size); + /* + * We only realloc to add more items, let's reset new items. + */ + if (map) + perf_thread_map__reset(map, start, nr); + + return map; +} + +#define thread_map__alloc(__nr) perf_thread_map__realloc(NULL, __nr) + +void perf_thread_map__set_pid(struct perf_thread_map *map, int thread, pid_t pid) +{ + map->map[thread].pid = pid; +} + +char *perf_thread_map__comm(struct perf_thread_map *map, int thread) +{ + return map->map[thread].comm; +} + +struct perf_thread_map *perf_thread_map__new_dummy(void) +{ + struct perf_thread_map *threads = thread_map__alloc(1); + + if (threads != NULL) { + perf_thread_map__set_pid(threads, 0, -1); + threads->nr = 1; + refcount_set(&threads->refcnt, 1); + } + return threads; +} + +static void perf_thread_map__delete(struct perf_thread_map *threads) +{ + if (threads) { + int i; + + WARN_ONCE(refcount_read(&threads->refcnt) != 0, + "thread map refcnt unbalanced\n"); + for (i = 0; i < threads->nr; i++) + free(perf_thread_map__comm(threads, i)); + free(threads); + } +} + +struct perf_thread_map *perf_thread_map__get(struct perf_thread_map *map) +{ + if (map) + refcount_inc(&map->refcnt); + return map; +} + +void perf_thread_map__put(struct perf_thread_map *map) +{ + if (map && refcount_dec_and_test(&map->refcnt)) + perf_thread_map__delete(map); +} + +int perf_thread_map__nr(struct perf_thread_map *threads) +{ + return threads ? threads->nr : 1; +} + +pid_t perf_thread_map__pid(struct perf_thread_map *map, int thread) +{ + return map->map[thread].pid; +} diff --git a/tools/perf/lib/xyarray.c b/tools/perf/lib/xyarray.c new file mode 100644 index 000000000000..dcd901d154bb --- /dev/null +++ b/tools/perf/lib/xyarray.c @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <internal/xyarray.h> +#include <linux/zalloc.h> +#include <stdlib.h> +#include <string.h> + +struct xyarray *xyarray__new(int xlen, int ylen, size_t entry_size) +{ + size_t row_size = ylen * entry_size; + struct xyarray *xy = zalloc(sizeof(*xy) + xlen * row_size); + + if (xy != NULL) { + xy->entry_size = entry_size; + xy->row_size = row_size; + xy->entries = xlen * ylen; + xy->max_x = xlen; + xy->max_y = ylen; + } + + return xy; +} + +void xyarray__reset(struct xyarray *xy) +{ + size_t n = xy->entries * xy->entry_size; + + memset(xy->contents, 0, n); +} + +void xyarray__delete(struct xyarray *xy) +{ + free(xy); +} diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 97e2628ea5dd..d4e4d53e8b44 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -441,6 +441,9 @@ int main(int argc, const char **argv) srandom(time(NULL)); + /* Setting $PERF_CONFIG makes perf read _only_ the given config file. */ + config_exclusive_filename = getenv("PERF_CONFIG"); + err = perf_config(perf_default_config, NULL); if (err) return err; diff --git a/tools/perf/perf.h b/tools/perf/perf.h index 74d0124d38f3..dc0a7a237887 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -57,6 +57,7 @@ struct record_opts { bool running_time; bool full_auxtrace; bool auxtrace_snapshot_mode; + bool auxtrace_snapshot_on_exit; bool record_namespaces; bool record_switch_events; bool all_kernel; diff --git a/tools/perf/pmu-events/arch/powerpc/power9/memory.json b/tools/perf/pmu-events/arch/powerpc/power9/memory.json index 2e2ebc700c74..c3bb283e37e9 100644 --- a/tools/perf/pmu-events/arch/powerpc/power9/memory.json +++ b/tools/perf/pmu-events/arch/powerpc/power9/memory.json @@ -52,7 +52,7 @@ {, "EventCode": "0x4D02C", "EventName": "PM_PMC1_REWIND", - "BriefDescription": "" + "BriefDescription": "PMC1 rewind event" }, {, "EventCode": "0x15158", diff --git a/tools/perf/pmu-events/arch/powerpc/power9/other.json b/tools/perf/pmu-events/arch/powerpc/power9/other.json index 48cf4f920b3f..62b864269623 100644 --- a/tools/perf/pmu-events/arch/powerpc/power9/other.json +++ b/tools/perf/pmu-events/arch/powerpc/power9/other.json @@ -237,7 +237,7 @@ {, "EventCode": "0xD0B0", "EventName": "PM_HWSYNC", - "BriefDescription": "" + "BriefDescription": "A hwsync instruction was decoded and transferred" }, {, "EventCode": "0x168B0", @@ -1232,7 +1232,7 @@ {, "EventCode": "0xD8AC", "EventName": "PM_LWSYNC", - "BriefDescription": "" + "BriefDescription": "An lwsync instruction was decoded and transferred" }, {, "EventCode": "0x2094", @@ -1747,7 +1747,7 @@ {, "EventCode": "0xD8B0", "EventName": "PM_PTESYNC", - "BriefDescription": "" + "BriefDescription": "A ptesync instruction was counted when the instruction is decoded and transmitted" }, {, "EventCode": "0x26086", @@ -2107,7 +2107,7 @@ {, "EventCode": "0xF080", "EventName": "PM_LSU_STCX_FAIL", - "BriefDescription": "" + "BriefDescription": "The LSU detects the condition that a stcx instruction failed. No requirement to wait for a response from the nest" }, {, "EventCode": "0x30038", diff --git a/tools/perf/pmu-events/arch/x86/icelake/cache.json b/tools/perf/pmu-events/arch/x86/icelake/cache.json new file mode 100644 index 000000000000..3529fc338c17 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/icelake/cache.json @@ -0,0 +1,552 @@ +[ + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of demand Data Read requests that miss L2 cache. Only not rejected loads are counted.", + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0x21", + "PEBScounters": "0,1,2,3", + "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS", + "SampleAfterValue": "200003", + "BriefDescription": "Demand Data Read miss L2, no rejects" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.", + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0x22", + "PEBScounters": "0,1,2,3", + "EventName": "L2_RQSTS.RFO_MISS", + "SampleAfterValue": "200003", + "BriefDescription": "RFO requests that miss L2 cache" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts L2 cache misses when fetching instructions.", + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0x24", + "PEBScounters": "0,1,2,3", + "EventName": "L2_RQSTS.CODE_RD_MISS", + "SampleAfterValue": "200003", + "BriefDescription": "L2 cache misses when fetching instructions" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts demand requests that miss L2 cache.", + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0x27", + "PEBScounters": "0,1,2,3", + "EventName": "L2_RQSTS.ALL_DEMAND_MISS", + "SampleAfterValue": "200003", + "BriefDescription": "Demand requests that miss L2 cache" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. This event accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions.", + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0x28", + "PEBScounters": "0,1,2,3", + "EventName": "L2_RQSTS.SWPF_MISS", + "SampleAfterValue": "200003", + "BriefDescription": "SW prefetch requests that miss L2 cache." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache.", + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0xc1", + "PEBScounters": "0,1,2,3", + "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", + "SampleAfterValue": "200003", + "BriefDescription": "Demand Data Read requests that hit L2 cache" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.", + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0xc2", + "PEBScounters": "0,1,2,3", + "EventName": "L2_RQSTS.RFO_HIT", + "SampleAfterValue": "200003", + "BriefDescription": "RFO requests that hit L2 cache" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.", + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0xc4", + "PEBScounters": "0,1,2,3", + "EventName": "L2_RQSTS.CODE_RD_HIT", + "SampleAfterValue": "200003", + "BriefDescription": "L2 cache hits when fetching instructions, code reads." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. This event accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions.", + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0xc8", + "PEBScounters": "0,1,2,3", + "EventName": "L2_RQSTS.SWPF_HIT", + "SampleAfterValue": "200003", + "BriefDescription": "SW prefetch requests that hit L2 cache." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of demand Data Read requests (including requests from L1D hardware prefetchers). These loads may hit or miss L2 cache. Only non rejected loads are counted.", + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0xe1", + "PEBScounters": "0,1,2,3", + "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD", + "SampleAfterValue": "200003", + "BriefDescription": "Demand Data Read requests" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches.", + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0xe2", + "PEBScounters": "0,1,2,3", + "EventName": "L2_RQSTS.ALL_RFO", + "SampleAfterValue": "200003", + "BriefDescription": "RFO requests to L2 cache" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the total number of L2 code requests.", + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0xe4", + "PEBScounters": "0,1,2,3", + "EventName": "L2_RQSTS.ALL_CODE_RD", + "SampleAfterValue": "200003", + "BriefDescription": "L2 code requests" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts demand requests to L2 cache.", + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0xe7", + "PEBScounters": "0,1,2,3", + "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES", + "SampleAfterValue": "200003", + "BriefDescription": "Demand requests to L2 cache" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.", + "EventCode": "0x48", + "Counter": "0,1,2,3", + "UMask": "0x1", + "PEBScounters": "0,1,2,3", + "EventName": "L1D_PEND_MISS.PENDING", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of L1D misses that are outstanding" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts duration of L1D miss outstanding in cycles.", + "EventCode": "0x48", + "Counter": "0,1,2,3", + "UMask": "0x1", + "PEBScounters": "0,1,2,3", + "EventName": "L1D_PEND_MISS.PENDING_CYCLES", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles with L1D load Misses outstanding.", + "CounterMask": "1" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailablability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", + "EventCode": "0x48", + "Counter": "0,1,2,3", + "UMask": "0x2", + "PEBScounters": "0,1,2,3", + "EventName": "L1D_PEND_MISS.FB_FULL", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailablability." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailablability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", + "EventCode": "0x48", + "Counter": "0,1,2,3", + "UMask": "0x2", + "PEBScounters": "0,1,2,3", + "EventName": "L1D_PEND_MISS.FB_FULL_PERIODS", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailablability.", + "CounterMask": "1", + "EdgeDetect": "1" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", + "EventCode": "0x48", + "Counter": "0,1,2,3", + "UMask": "0x4", + "PEBScounters": "0,1,2,3", + "EventName": "L1D_PEND_MISS.L2_STALL", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of cycles a demand request has waited due to L1D due to lack of L2 resources." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.", + "EventCode": "0x51", + "Counter": "0,1,2,3", + "UMask": "0x1", + "PEBScounters": "0,1,2,3", + "EventName": "L1D.REPLACEMENT", + "SampleAfterValue": "2000003", + "BriefDescription": "Counts the number of cache lines replaced in L1 data cache." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "EventCode": "0x60", + "Counter": "0,1,2,3", + "UMask": "0x4", + "PEBScounters": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles with offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore.", + "CounterMask": "1" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of offcore outstanding cacheable Core Data Read transactions in the super queue every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", + "EventCode": "0x60", + "Counter": "0,1,2,3", + "UMask": "0x8", + "PEBScounters": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD", + "SampleAfterValue": "2000003", + "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", + "EventCode": "0x60", + "Counter": "0,1,2,3", + "UMask": "0x8", + "PEBScounters": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.", + "CounterMask": "1" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.", + "EventCode": "0xB0", + "Counter": "0,1,2,3", + "UMask": "0x1", + "PEBScounters": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD", + "SampleAfterValue": "100003", + "BriefDescription": "Demand Data Read requests sent to uncore" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.", + "EventCode": "0xB0", + "Counter": "0,1,2,3", + "UMask": "0x4", + "PEBScounters": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS.DEMAND_RFO", + "SampleAfterValue": "100003", + "BriefDescription": "Demand RFO requests including regular RFOs, locks, ItoM" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.", + "EventCode": "0xB0", + "Counter": "0,1,2,3", + "UMask": "0x8", + "PEBScounters": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS.ALL_DATA_RD", + "SampleAfterValue": "100003", + "BriefDescription": "Demand and prefetch data reads" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts memory transactions reached the super queue including requests initiated by the core, all L3 prefetches, page walks, etc..", + "EventCode": "0xB0", + "Counter": "0,1,2,3", + "UMask": "0x80", + "PEBScounters": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS", + "SampleAfterValue": "100003", + "BriefDescription": "Any memory transaction that reached the SQ." + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired load instructions that true miss the STLB.", + "EventCode": "0xD0", + "Counter": "0,1,2,3", + "UMask": "0x11", + "PEBScounters": "0,1,2,3", + "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS", + "SampleAfterValue": "100003", + "BriefDescription": "Retired load instructions that miss the STLB.", + "Data_LA": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired store instructions that true miss the STLB.", + "EventCode": "0xD0", + "Counter": "0,1,2,3", + "UMask": "0x12", + "PEBScounters": "0,1,2,3", + "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES", + "SampleAfterValue": "100003", + "BriefDescription": "Retired store instructions that miss the STLB.", + "Data_LA": "1", + "L1_Hit_Indication": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired load instructions with locked access.", + "EventCode": "0xD0", + "Counter": "0,1,2,3", + "UMask": "0x21", + "PEBScounters": "0,1,2,3", + "EventName": "MEM_INST_RETIRED.LOCK_LOADS", + "SampleAfterValue": "100007", + "BriefDescription": "Retired load instructions with locked access.", + "Data_LA": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.", + "EventCode": "0xD0", + "Counter": "0,1,2,3", + "UMask": "0x41", + "PEBScounters": "0,1,2,3", + "EventName": "MEM_INST_RETIRED.SPLIT_LOADS", + "SampleAfterValue": "100003", + "BriefDescription": "Retired load instructions that split across a cacheline boundary.", + "Data_LA": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.", + "EventCode": "0xD0", + "Counter": "0,1,2,3", + "UMask": "0x42", + "PEBScounters": "0,1,2,3", + "EventName": "MEM_INST_RETIRED.SPLIT_STORES", + "SampleAfterValue": "100003", + "BriefDescription": "Retired store instructions that split across a cacheline boundary.", + "Data_LA": "1", + "L1_Hit_Indication": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions for loads.", + "EventCode": "0xD0", + "Counter": "0,1,2,3", + "UMask": "0x81", + "PEBScounters": "0,1,2,3", + "EventName": "MEM_INST_RETIRED.ALL_LOADS", + "SampleAfterValue": "2000003", + "BriefDescription": "All retired load instructions.", + "Data_LA": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts all retired store instructions. This event account for SW prefetch instructions and PREFETCHW instruction for stores.", + "EventCode": "0xD0", + "Counter": "0,1,2,3", + "UMask": "0x82", + "PEBScounters": "0,1,2,3", + "EventName": "MEM_INST_RETIRED.ALL_STORES", + "SampleAfterValue": "2000003", + "BriefDescription": "All retired store instructions.", + "Data_LA": "1", + "L1_Hit_Indication": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.", + "EventCode": "0xD1", + "Counter": "0,1,2,3", + "UMask": "0x1", + "PEBScounters": "0,1,2,3", + "EventName": "MEM_LOAD_RETIRED.L1_HIT", + "SampleAfterValue": "2000003", + "BriefDescription": "Retired load instructions with L1 cache hits as data sources", + "Data_LA": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources.", + "EventCode": "0xD1", + "Counter": "0,1,2,3", + "UMask": "0x2", + "PEBScounters": "0,1,2,3", + "EventName": "MEM_LOAD_RETIRED.L2_HIT", + "SampleAfterValue": "100003", + "BriefDescription": "Retired load instructions with L2 cache hits as data sources", + "Data_LA": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.", + "EventCode": "0xD1", + "Counter": "0,1,2,3", + "UMask": "0x4", + "PEBScounters": "0,1,2,3", + "EventName": "MEM_LOAD_RETIRED.L3_HIT", + "SampleAfterValue": "50021", + "BriefDescription": "Retired load instructions with L3 cache hits as data sources", + "Data_LA": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.", + "EventCode": "0xD1", + "Counter": "0,1,2,3", + "UMask": "0x8", + "PEBScounters": "0,1,2,3", + "EventName": "MEM_LOAD_RETIRED.L1_MISS", + "SampleAfterValue": "100003", + "BriefDescription": "Retired load instructions missed L1 cache as data sources", + "Data_LA": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired load instructions missed L2 cache as data sources.", + "EventCode": "0xD1", + "Counter": "0,1,2,3", + "UMask": "0x10", + "PEBScounters": "0,1,2,3", + "EventName": "MEM_LOAD_RETIRED.L2_MISS", + "SampleAfterValue": "50021", + "BriefDescription": "Retired load instructions missed L2 cache as data sources", + "Data_LA": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.", + "EventCode": "0xD1", + "Counter": "0,1,2,3", + "UMask": "0x20", + "PEBScounters": "0,1,2,3", + "EventName": "MEM_LOAD_RETIRED.L3_MISS", + "SampleAfterValue": "100007", + "BriefDescription": "Retired load instructions missed L3 cache as data sources", + "Data_LA": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.", + "EventCode": "0xd1", + "Counter": "0,1,2,3", + "UMask": "0x40", + "PEBScounters": "0,1,2,3", + "EventName": "MEM_LOAD_RETIRED.FB_HIT", + "SampleAfterValue": "100007", + "BriefDescription": "Number of completed demand load requests that missed the L1, but hit the FB(fill buffer), because a preceding miss to the same cacheline initiated the line to be brought into L1, but data is not yet ready in L1.", + "Data_LA": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", + "EventCode": "0xd2", + "Counter": "0,1,2,3", + "UMask": "0x1", + "PEBScounters": "0,1,2,3", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS", + "SampleAfterValue": "20011", + "BriefDescription": "Retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", + "Data_LA": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.", + "EventCode": "0xd2", + "Counter": "0,1,2,3", + "UMask": "0x2", + "PEBScounters": "0,1,2,3", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT", + "SampleAfterValue": "20011", + "BriefDescription": "Retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache", + "Data_LA": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3.", + "EventCode": "0xd2", + "Counter": "0,1,2,3", + "UMask": "0x4", + "PEBScounters": "0,1,2,3", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM", + "SampleAfterValue": "20011", + "BriefDescription": "Retired load instructions whose data sources were HitM responses from shared L3", + "Data_LA": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required.", + "EventCode": "0xd2", + "Counter": "0,1,2,3", + "UMask": "0x8", + "PEBScounters": "0,1,2,3", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE", + "SampleAfterValue": "100003", + "BriefDescription": "Retired load instructions whose data sources were hits in L3 without snoops required", + "Data_LA": "1" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.", + "EventCode": "0xF1", + "Counter": "0,1,2,3", + "UMask": "0x1f", + "PEBScounters": "0,1,2,3", + "EventName": "L2_LINES_IN.ALL", + "SampleAfterValue": "100003", + "BriefDescription": "L2 cache lines filling L2" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the cycles for which the thread is active and the superQ cannot take any more entries.", + "EventCode": "0xF4", + "Counter": "0,1,2,3", + "UMask": "0x4", + "PEBScounters": "0,1,2,3", + "EventName": "SQ_MISC.SQ_FULL", + "SampleAfterValue": "100003", + "BriefDescription": "Cycles the thread is active and superQ cannot take any more entries." + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/icelake/floating-point.json b/tools/perf/pmu-events/arch/x86/icelake/floating-point.json new file mode 100644 index 000000000000..594c5551f610 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/icelake/floating-point.json @@ -0,0 +1,102 @@ +[ + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts all microcode Floating Point assists.", + "EventCode": "0xC1", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x2", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "ASSISTS.FP", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all microcode FP assists.", + "CounterMask": "1" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "EventCode": "0xc7", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 RANGE SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "EventCode": "0xc7", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x2", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 RANGE SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "EventCode": "0xc7", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x4", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT14 RCP14 RANGE DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "EventCode": "0xc7", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x8", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "EventCode": "0xc7", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x10", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 RANGE SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "EventCode": "0xc7", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x20", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 RANGE SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 RANGE FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "EventCode": "0xc7", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x40", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 16 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 RANGE FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 16 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 RANGE FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "EventCode": "0xc7", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x80", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 RANGE FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element." + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/icelake/frontend.json b/tools/perf/pmu-events/arch/x86/icelake/frontend.json new file mode 100644 index 000000000000..9c3cfbfcec0f --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/icelake/frontend.json @@ -0,0 +1,424 @@ +[ + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).", + "EventCode": "0x79", + "Counter": "0,1,2,3", + "UMask": "0x4", + "PEBScounters": "0,1,2,3", + "EventName": "IDQ.MITE_UOPS", + "SampleAfterValue": "2000003", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "EventCode": "0x79", + "Counter": "0,1,2,3", + "UMask": "0x4", + "PEBScounters": "0,1,2,3", + "EventName": "IDQ.MITE_CYCLES_OK", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles MITE is delivering optimal number of Uops", + "CounterMask": "5" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "EventCode": "0x79", + "Counter": "0,1,2,3", + "UMask": "0x4", + "PEBScounters": "0,1,2,3", + "EventName": "IDQ.MITE_CYCLES_ANY", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles MITE is delivering any Uop", + "CounterMask": "1" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.", + "EventCode": "0x79", + "Counter": "0,1,2,3", + "UMask": "0x8", + "PEBScounters": "0,1,2,3", + "EventName": "IDQ.DSB_UOPS", + "SampleAfterValue": "2000003", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "EventCode": "0x79", + "Counter": "0,1,2,3", + "UMask": "0x8", + "PEBScounters": "0,1,2,3", + "EventName": "IDQ.DSB_CYCLES_OK", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles DSB is delivering optimal number of Uops", + "CounterMask": "5" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.", + "EventCode": "0x79", + "Counter": "0,1,2,3", + "UMask": "0x8", + "PEBScounters": "0,1,2,3", + "EventName": "IDQ.DSB_CYCLES_ANY", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop", + "CounterMask": "1" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.", + "EventCode": "0x79", + "Counter": "0,1,2,3", + "UMask": "0x30", + "PEBScounters": "0,1,2,3", + "EventName": "IDQ.MS_SWITCHES", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of switches from DSB or MITE to the MS", + "CounterMask": "1", + "EdgeDetect": "1" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Any instruction over 4 uops will be delivered by the MS. Some instructions such as transcendentals may additionally generate uops from the MS.", + "EventCode": "0x79", + "Counter": "0,1,2,3", + "UMask": "0x30", + "PEBScounters": "0,1,2,3", + "EventName": "IDQ.MS_UOPS", + "SampleAfterValue": "2000003", + "BriefDescription": "Uops delivered to IDQ while MS is busy" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.", + "EventCode": "0x79", + "Counter": "0,1,2,3", + "UMask": "0x30", + "PEBScounters": "0,1,2,3", + "EventName": "IDQ.MS_CYCLES_ANY", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles when uops are being delivered to IDQ while MS is busy", + "CounterMask": "1" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The legacy decode pipeline works at a 16 Byte granularity.", + "EventCode": "0x80", + "Counter": "0,1,2,3", + "UMask": "0x4", + "PEBScounters": "0,1,2,3", + "EventName": "ICACHE_16B.IFDATA_STALL", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts instruction fetch tag lookups that hit in the instruction cache (L1I). Counts at 64-byte cache-line granularity. Accounts for both cacheable and uncacheable accesses.", + "EventCode": "0x83", + "Counter": "0,1,2,3", + "UMask": "0x1", + "PEBScounters": "0,1,2,3", + "EventName": "ICACHE_64B.IFTAG_HIT", + "SampleAfterValue": "200003", + "BriefDescription": "Instruction fetch tag lookups that hit in the instruction cache (L1I). Counts at 64-byte cache-line granularity." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts instruction fetch tag lookups that miss in the instruction cache (L1I). Counts at 64-byte cache-line granularity. Accounts for both cacheable and uncacheable accesses.", + "EventCode": "0x83", + "Counter": "0,1,2,3", + "UMask": "0x2", + "PEBScounters": "0,1,2,3", + "EventName": "ICACHE_64B.IFTAG_MISS", + "SampleAfterValue": "200003", + "BriefDescription": "Instruction fetch tag lookups that miss in the instruction cache (L1I). Counts at 64-byte cache-line granularity." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss.", + "EventCode": "0x83", + "Counter": "0,1,2,3", + "UMask": "0x4", + "PEBScounters": "0,1,2,3", + "EventName": "ICACHE_64B.IFTAG_STALL", + "SampleAfterValue": "200003", + "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle.", + "EventCode": "0x9C", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", + "SampleAfterValue": "2000003", + "BriefDescription": "Uops not delivered by IDQ when backend of the machine is not stalled" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle.", + "EventCode": "0x9c", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles when no uops are not delivered by the IDQ when backend of the machine is not stalled", + "CounterMask": "5" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle.", + "EventCode": "0x9C", + "Invert": "1", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles when optimal number of uops was delivered to the back-end when the back-end is not stalled", + "CounterMask": "1" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE.", + "EventCode": "0xAB", + "Counter": "0,1,2,3", + "UMask": "0x2", + "PEBScounters": "0,1,2,3", + "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", + "SampleAfterValue": "2000003", + "BriefDescription": "DSB-to-MITE switch true penalty cycles." + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.", + "EventCode": "0xC6", + "MSRValue": "0x11", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "FRONTEND_RETIRED.DSB_MISS", + "MSRIndex": "0x3F7", + "SampleAfterValue": "100007", + "BriefDescription": "Retired Instructions who experienced DSB miss.", + "TakenAlone": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.", + "EventCode": "0xC6", + "MSRValue": "0x12", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "FRONTEND_RETIRED.L1I_MISS", + "MSRIndex": "0x3F7", + "SampleAfterValue": "100007", + "BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss.", + "TakenAlone": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.", + "EventCode": "0xC6", + "MSRValue": "0x13", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "FRONTEND_RETIRED.L2_MISS", + "MSRIndex": "0x3F7", + "SampleAfterValue": "100007", + "BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss.", + "TakenAlone": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.", + "EventCode": "0xC6", + "MSRValue": "0x14", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "FRONTEND_RETIRED.ITLB_MISS", + "MSRIndex": "0x3F7", + "SampleAfterValue": "100007", + "BriefDescription": "Retired Instructions who experienced iTLB true miss.", + "TakenAlone": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.", + "EventCode": "0xC6", + "MSRValue": "0x15", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "FRONTEND_RETIRED.STLB_MISS", + "MSRIndex": "0x3F7", + "SampleAfterValue": "100007", + "BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss.", + "TakenAlone": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 2 cycles which was not interrupted by a back-end stall.", + "EventCode": "0xC6", + "MSRValue": "0x500206", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2", + "MSRIndex": "0x3F7", + "SampleAfterValue": "100007", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 2 cycles which was not interrupted by a back-end stall.", + "TakenAlone": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.", + "EventCode": "0xC6", + "MSRValue": "0x500406", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_4", + "MSRIndex": "0x3F7", + "SampleAfterValue": "100007", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.", + "TakenAlone": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.", + "EventCode": "0xC6", + "MSRValue": "0x500806", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_8", + "MSRIndex": "0x3F7", + "SampleAfterValue": "100007", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 8 cycles which was not interrupted by a back-end stall.", + "TakenAlone": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.", + "EventCode": "0xC6", + "MSRValue": "0x501006", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_16", + "MSRIndex": "0x3F7", + "SampleAfterValue": "100007", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 16 cycles which was not interrupted by a back-end stall.", + "TakenAlone": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.", + "EventCode": "0xC6", + "MSRValue": "0x502006", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_32", + "MSRIndex": "0x3F7", + "SampleAfterValue": "100007", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 32 cycles which was not interrupted by a back-end stall.", + "TakenAlone": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.", + "EventCode": "0xC6", + "MSRValue": "0x504006", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_64", + "MSRIndex": "0x3F7", + "SampleAfterValue": "100007", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.", + "TakenAlone": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.", + "EventCode": "0xC6", + "MSRValue": "0x508006", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_128", + "MSRIndex": "0x3F7", + "SampleAfterValue": "100007", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.", + "TakenAlone": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.", + "EventCode": "0xC6", + "MSRValue": "0x510006", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_256", + "MSRIndex": "0x3F7", + "SampleAfterValue": "100007", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.", + "TakenAlone": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.", + "EventCode": "0xC6", + "MSRValue": "0x520006", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_512", + "MSRIndex": "0x3F7", + "SampleAfterValue": "100007", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.", + "TakenAlone": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.", + "EventCode": "0xC6", + "MSRValue": "0x100206", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1", + "MSRIndex": "0x3F7", + "SampleAfterValue": "100007", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 1 bubble-slot for a period of 2 cycles which was not interrupted by a back-end stall.", + "TakenAlone": "1" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/icelake/memory.json b/tools/perf/pmu-events/arch/x86/icelake/memory.json new file mode 100644 index 000000000000..f158366b9dd6 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/icelake/memory.json @@ -0,0 +1,410 @@ +[ + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of times a TSX line had a cache conflict.", + "EventCode": "0x54", + "Counter": "0,1,2,3", + "UMask": "0x1", + "PEBScounters": "0,1,2,3", + "EventName": "TX_MEM.ABORT_CONFLICT", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of times a transactional abort was signaled due to a data conflict on a transactionally accessed address" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Speculatively counts the number Transactional Synchronization Extensions (TSX) Aborts due to a data capacity limitation for transactional writes.", + "EventCode": "0x54", + "Counter": "0,1,2,3", + "UMask": "0x2", + "PEBScounters": "0,1,2,3", + "EventName": "TX_MEM.ABORT_CAPACITY_WRITE", + "SampleAfterValue": "2000003", + "BriefDescription": "Speculatively counts the number TSX Aborts due to a data capacity limitation for transactional writes." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of times a TSX Abort was triggered due to a non-release/commit store to lock.", + "EventCode": "0x54", + "Counter": "0,1,2,3", + "UMask": "0x4", + "PEBScounters": "0,1,2,3", + "EventName": "TX_MEM.ABORT_HLE_STORE_TO_ELIDED_LOCK", + "SampleAfterValue": "100003", + "BriefDescription": "Number of times a HLE transactional region aborted due to a non XRELEASE prefixed instruction writing to an elided lock in the elision buffer" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of times a TSX Abort was triggered due to commit but Lock Buffer not empty.", + "EventCode": "0x54", + "Counter": "0,1,2,3", + "UMask": "0x8", + "PEBScounters": "0,1,2,3", + "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_NOT_EMPTY", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of times an HLE transactional execution aborted due to NoAllocatedElisionBuffer being non-zero." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of times a TSX Abort was triggered due to release/commit but data and address mismatch.", + "EventCode": "0x54", + "Counter": "0,1,2,3", + "UMask": "0x10", + "PEBScounters": "0,1,2,3", + "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_MISMATCH", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of times an HLE transactional execution aborted due to XRELEASE lock not satisfying the address and value requirements in the elision buffer" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of times a TSX Abort was triggered due to attempting an unsupported alignment from Lock Buffer.", + "EventCode": "0x54", + "Counter": "0,1,2,3", + "UMask": "0x20", + "PEBScounters": "0,1,2,3", + "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_UNSUPPORTED_ALIGNMENT", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of times an HLE transactional execution aborted due to an unsupported read alignment from the elision buffer." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of times we could not allocate Lock Buffer.", + "EventCode": "0x54", + "Counter": "0,1,2,3", + "UMask": "0x40", + "PEBScounters": "0,1,2,3", + "EventName": "TX_MEM.HLE_ELISION_BUFFER_FULL", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of times HLE lock could not be elided due to ElisionBufferAvailable being zero." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts Unfriendly TSX abort triggered by a vzeroupper instruction.", + "EventCode": "0x5d", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x2", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "TX_EXEC.MISC2", + "SampleAfterValue": "2000003", + "BriefDescription": "Counts the number of times a class of instructions that may cause a transactional abort was executed inside a transactional region" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts Unfriendly TSX abort triggered by a nest count that is too deep.", + "EventCode": "0x5d", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x4", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "TX_EXEC.MISC3", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of times an instruction execution caused the transactional nest count supported to be exceeded" + }, + { + "CollectPEBSRecord": "2", + "EventCode": "0xA3", + "Counter": "0,1,2,3", + "UMask": "0x2", + "PEBScounters": "0,1,2,3", + "EventName": "CYCLE_ACTIVITY.CYCLES_L3_MISS", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles while L3 cache miss demand load is outstanding.", + "CounterMask": "2" + }, + { + "CollectPEBSRecord": "2", + "EventCode": "0xA3", + "Counter": "0,1,2,3", + "UMask": "0x6", + "PEBScounters": "0,1,2,3", + "EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS", + "SampleAfterValue": "2000003", + "BriefDescription": "Execution stalls while L3 cache miss demand load is outstanding.", + "CounterMask": "6" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Demand Data Read requests who miss L3 cache.", + "EventCode": "0xB0", + "Counter": "0,1,2,3", + "UMask": "0x10", + "PEBScounters": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", + "SampleAfterValue": "100003", + "BriefDescription": "Demand Data Read requests who miss L3 cache" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture", + "EventCode": "0xc3", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x2", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", + "SampleAfterValue": "100003", + "BriefDescription": "Number of machine clears due to memory ordering conflicts." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of times we entered an HLE region. Does not count nested transactions.", + "EventCode": "0xC8", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "HLE_RETIRED.START", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of times an HLE execution started." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of times HLE commit succeeded.", + "EventCode": "0xC8", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x2", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "HLE_RETIRED.COMMIT", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of times an HLE execution successfully committed", + "Data_LA": "1" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of times HLE abort was triggered.", + "EventCode": "0xc8", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x4", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "HLE_RETIRED.ABORTED", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of times an HLE execution aborted due to any reasons (multiple categories may count as one)." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of times an HLE execution aborted due to various memory events (e.g., read/write capacity and conflicts).", + "EventCode": "0xC8", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x8", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "HLE_RETIRED.ABORTED_MEM", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of times an HLE execution aborted due to various memory events (e.g., read/write capacity and conflicts)." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).", + "EventCode": "0xC8", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x20", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "HLE_RETIRED.ABORTED_UNFRIENDLY", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.)." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of times an HLE execution aborted due to unfriendly events (such as interrupts).", + "EventCode": "0xC8", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x80", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "HLE_RETIRED.ABORTED_EVENTS", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of times an HLE execution aborted due to unfriendly events (such as interrupts)." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of times we entered an RTM region. Does not count nested transactions.", + "EventCode": "0xC9", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "RTM_RETIRED.START", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of times an RTM execution started." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of times RTM commit succeeded.", + "EventCode": "0xC9", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x2", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "RTM_RETIRED.COMMIT", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of times an RTM execution successfully committed" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of times RTM abort was triggered.", + "EventCode": "0xc9", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x4", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "RTM_RETIRED.ABORTED", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of times an RTM execution aborted.", + "Data_LA": "1" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts).", + "EventCode": "0xC9", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x8", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "RTM_RETIRED.ABORTED_MEM", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts)" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of times an RTM execution aborted due to HLE-unfriendly instructions.", + "EventCode": "0xC9", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x20", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "RTM_RETIRED.ABORTED_UNFRIENDLY", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of times an RTM execution aborted due to HLE-unfriendly instructions" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of times an RTM execution aborted due to incompatible memory type.", + "EventCode": "0xC9", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x40", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "RTM_RETIRED.ABORTED_MEMTYPE", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of times an RTM execution aborted due to incompatible memory type" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt).", + "EventCode": "0xC9", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x80", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "RTM_RETIRED.ABORTED_EVENTS", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt)" + }, + { + "PEBS": "2", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.", + "EventCode": "0xcd", + "MSRValue": "0x4", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", + "MSRIndex": "0x3F6", + "SampleAfterValue": "100003", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.", + "TakenAlone": "1" + }, + { + "PEBS": "2", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.", + "EventCode": "0xcd", + "MSRValue": "0x8", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", + "MSRIndex": "0x3F6", + "SampleAfterValue": "50021", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.", + "TakenAlone": "1" + }, + { + "PEBS": "2", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.", + "EventCode": "0xcd", + "MSRValue": "0x10", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", + "MSRIndex": "0x3F6", + "SampleAfterValue": "20011", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.", + "TakenAlone": "1" + }, + { + "PEBS": "2", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.", + "EventCode": "0xcd", + "MSRValue": "0x20", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", + "MSRIndex": "0x3F6", + "SampleAfterValue": "100007", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.", + "TakenAlone": "1" + }, + { + "PEBS": "2", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.", + "EventCode": "0xcd", + "MSRValue": "0x40", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", + "MSRIndex": "0x3F6", + "SampleAfterValue": "2003", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.", + "TakenAlone": "1" + }, + { + "PEBS": "2", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.", + "EventCode": "0xcd", + "MSRValue": "0x80", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", + "MSRIndex": "0x3F6", + "SampleAfterValue": "1009", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.", + "TakenAlone": "1" + }, + { + "PEBS": "2", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.", + "EventCode": "0xcd", + "MSRValue": "0x100", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", + "MSRIndex": "0x3F6", + "SampleAfterValue": "503", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.", + "TakenAlone": "1" + }, + { + "PEBS": "2", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.", + "EventCode": "0xcd", + "MSRValue": "0x200", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", + "MSRIndex": "0x3F6", + "SampleAfterValue": "101", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.", + "TakenAlone": "1" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/icelake/other.json b/tools/perf/pmu-events/arch/x86/icelake/other.json new file mode 100644 index 000000000000..f8dfdb847224 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/icelake/other.json @@ -0,0 +1,121 @@ +[ + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core. Software can use this event as the denominator for the top-level metrics of the Top-down Microarchitecture Analysis method. This event is counted on a designated fixed counter (Fixed Counter 3) and is an architectural event.", + "Counter": "35", + "UMask": "0x4", + "PEBScounters": "35", + "EventName": "TOPDOWN.SLOTS", + "SampleAfterValue": "10000003", + "BriefDescription": "Counts the number of available slots for an unhalted logical processor." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes.", + "EventCode": "0x28", + "Counter": "0,1,2,3", + "UMask": "0x7", + "PEBScounters": "0,1,2,3", + "EventName": "CORE_POWER.LVL0_TURBO_LICENSE", + "SampleAfterValue": "200003", + "BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the Non-AVX turbo schedule." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions.", + "EventCode": "0x28", + "Counter": "0,1,2,3", + "UMask": "0x18", + "PEBScounters": "0,1,2,3", + "EventName": "CORE_POWER.LVL1_TURBO_LICENSE", + "SampleAfterValue": "200003", + "BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the AVX2 turbo schedule." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Core cycles where the core was running with power-delivery for license level 2 (introduced in Skylake Server microarchtecture). This includes high current AVX 512-bit instructions.", + "EventCode": "0x28", + "Counter": "0,1,2,3", + "UMask": "0x20", + "PEBScounters": "0,1,2,3", + "EventName": "CORE_POWER.LVL2_TURBO_LICENSE", + "SampleAfterValue": "200003", + "BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the AVX512 turbo schedule." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of PREFETCHNTA instructions executed.", + "EventCode": "0x32", + "Counter": "0,1,2,3", + "UMask": "0x1", + "PEBScounters": "0,1,2,3", + "EventName": "SW_PREFETCH_ACCESS.NTA", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of PREFETCHNTA instructions executed." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of PREFETCHT0 instructions executed.", + "EventCode": "0x32", + "Counter": "0,1,2,3", + "UMask": "0x2", + "PEBScounters": "0,1,2,3", + "EventName": "SW_PREFETCH_ACCESS.T0", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of PREFETCHT0 instructions executed." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed.", + "EventCode": "0x32", + "Counter": "0,1,2,3", + "UMask": "0x4", + "PEBScounters": "0,1,2,3", + "EventName": "SW_PREFETCH_ACCESS.T1_T2", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of PREFETCHT1 or PREFETCHT2 instructions executed." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of PREFETCHW instructions executed.", + "EventCode": "0x32", + "Counter": "0,1,2,3", + "UMask": "0x8", + "PEBScounters": "0,1,2,3", + "EventName": "SW_PREFETCH_ACCESS.PREFETCHW", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of PREFETCHW instructions executed." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core.", + "EventCode": "0xa4", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "TOPDOWN.SLOTS_P", + "SampleAfterValue": "10000003", + "BriefDescription": "Counts the number of available slots for an unhalted logical processor." + }, + { + "CollectPEBSRecord": "2", + "EventCode": "0xA4", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x2", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "TOPDOWN.BACKEND_BOUND_SLOTS", + "SampleAfterValue": "10000003", + "BriefDescription": "Issue slots where no uops were being issued due to lack of back end resources." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware Examples include AD (page Access Dirty), FP and AVX related assists.", + "EventCode": "0xc1", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x7", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "ASSISTS.ANY", + "SampleAfterValue": "100003", + "BriefDescription": "Number of occurrences where a microcode assist is invoked by hardware." + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/icelake/pipeline.json b/tools/perf/pmu-events/arch/x86/icelake/pipeline.json new file mode 100644 index 000000000000..6d8311e634aa --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/icelake/pipeline.json @@ -0,0 +1,892 @@ +[ + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", + "Counter": "32", + "UMask": "0x1", + "PEBScounters": "32", + "EventName": "INST_RETIRED.ANY", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event" + }, + { + "PEBS": "2", + "CollectPEBSRecord": "3", + "PublicDescription": "A version of INST_RETIRED that allows for a more unbiased distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR) feature to mitigate some bias in how retired instructions get sampled. Use on Fixed Counter 0.", + "Counter": "32", + "UMask": "0x1", + "PEBScounters": "32", + "EventName": "INST_RETIRED.PREC_DIST", + "SampleAfterValue": "2000003", + "BriefDescription": "Precise instruction retired event with a reduced effect of PEBS shadow in IP distribution" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.", + "Counter": "33", + "UMask": "0x2", + "PEBScounters": "33", + "EventName": "CPU_CLK_UNHALTED.THREAD", + "SampleAfterValue": "2000003", + "BriefDescription": "Core cycles when the thread is not in halt state" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", + "Counter": "34", + "UMask": "0x3", + "PEBScounters": "34", + "EventName": "CPU_CLK_UNHALTED.REF_TSC", + "SampleAfterValue": "2000003", + "BriefDescription": "Reference cycles when the core is not in halt state." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of times the load operation got the true Block-on-Store blocking code preventing store forwarding. This includes cases when: a. preceding store conflicts with the load (incomplete overlap),b. store forwarding is impossible due to u-arch limitations, c. preceding lock RMW operations are not forwarded, d. store has the no-forward bit set (uncacheable/page-split/masked stores), e. all-blocking stores are used (mostly, fences and port I/O), and others. The most common case is a load blocked due to its address range overlapping with a preceding smaller uncompleted store. Note: This event does not take into account cases of out-of-SW-control (for example, SbTailHit), unknown physical STA, and cases of blocking loads on store due to being non-WB memory type or a lock. These cases are covered by other events. See the table of not supported store forwards in the Optimization Guide.", + "EventCode": "0x03", + "Counter": "0,1,2,3", + "UMask": "0x2", + "PEBScounters": "0,1,2,3", + "EventName": "LD_BLOCKS.STORE_FORWARD", + "SampleAfterValue": "100003", + "BriefDescription": "Loads blocked by overlapping with store buffer that cannot be forwarded." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.", + "EventCode": "0x03", + "Counter": "0,1,2,3", + "UMask": "0x8", + "PEBScounters": "0,1,2,3", + "EventName": "LD_BLOCKS.NO_SR", + "SampleAfterValue": "100003", + "BriefDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address.", + "EventCode": "0x07", + "Counter": "0,1,2,3", + "UMask": "0x1", + "PEBScounters": "0,1,2,3", + "EventName": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS", + "SampleAfterValue": "100003", + "BriefDescription": "False dependencies in MOB due to partial compare on address." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.", + "EventCode": "0x0D", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "INT_MISC.RECOVERY_CYCLES", + "SampleAfterValue": "2000003", + "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for this thread" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts cycles the Backend cluster is recovering after a miss-speculation or a Store Buffer or Load Buffer drain stall.", + "EventCode": "0x0D", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x3", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "INT_MISC.ALL_RECOVERY_CYCLES", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles the Backend cluster is recovering after a miss-speculation or a Store Buffer or Load Buffer drain stall.", + "CounterMask": "1" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.", + "EventCode": "0x0d", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x80", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES", + "SampleAfterValue": "2000003", + "BriefDescription": "Counts cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).", + "EventCode": "0x0E", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "UOPS_ISSUED.ANY", + "SampleAfterValue": "2000003", + "BriefDescription": "Uops that RAT issues to RS" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts cycles during which the Resource Allocation Table (RAT) does not issue any Uops to the reservation station (RS) for the current thread.", + "EventCode": "0x0E", + "Invert": "1", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "UOPS_ISSUED.STALL_CYCLES", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles when RAT does not issue Uops to RS for the thread", + "CounterMask": "1" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.", + "EventCode": "0x14", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x9", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "ARITH.DIVIDER_ACTIVE", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles when divide unit is busy executing divide or square root operations.", + "CounterMask": "1" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.", + "EventCode": "0x3C", + "Counter": "0,1,2,3,4,5,6,7", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "CPU_CLK_UNHALTED.THREAD_P", + "SampleAfterValue": "2000003", + "BriefDescription": "Thread cycles when thread is not in halt state" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts core crystal clock cycles when the thread is unhalted.", + "EventCode": "0x3C", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "CPU_CLK_UNHALTED.REF_XCLK", + "SampleAfterValue": "25003", + "BriefDescription": "Core crystal clock cycles when the thread is unhalted." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts Core crystal clock cycles when current thread is unhalted and the other thread is halted.", + "EventCode": "0x3C", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x2", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE", + "SampleAfterValue": "25003", + "BriefDescription": "Core crystal clock cycles when this thread is unhalted and the other thread is halted." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions.", + "EventCode": "0x4c", + "Counter": "0,1,2,3", + "UMask": "0x1", + "PEBScounters": "0,1,2,3", + "EventName": "LOAD_HIT_PREFETCH.SWPF", + "SampleAfterValue": "100003", + "BriefDescription": "Counts the number of demand load dispatches that hit L1D fill buffer (FB) allocated for software prefetch." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into stravation periods (e.g. branch mispredictions or i-cache misses)", + "EventCode": "0x5E", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "RS_EVENTS.EMPTY_CYCLES", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events)", + "EventCode": "0x5E", + "Invert": "1", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "RS_EVENTS.EMPTY_END", + "SampleAfterValue": "2000003", + "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.", + "CounterMask": "1", + "EdgeDetect": "1" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.", + "EventCode": "0x87", + "Counter": "0,1,2,3", + "UMask": "0x1", + "PEBScounters": "0,1,2,3", + "EventName": "ILD_STALL.LCP", + "SampleAfterValue": "2000003", + "BriefDescription": "Stalls caused by changing prefix length of the instruction." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 0.", + "EventCode": "0xa1", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "UOPS_DISPATCHED.PORT_0", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of uops executed on port 0" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 1.", + "EventCode": "0xa1", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x2", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "UOPS_DISPATCHED.PORT_1", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of uops executed on port 1" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to ports 2 and 3.", + "EventCode": "0xa1", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x4", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "UOPS_DISPATCHED.PORT_2_3", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of uops executed on port 2 and 3" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to ports 5 and 9.", + "EventCode": "0xa1", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x10", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "UOPS_DISPATCHED.PORT_4_9", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of uops executed on port 4 and 9" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 5.", + "EventCode": "0xa1", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x20", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "UOPS_DISPATCHED.PORT_5", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of uops executed on port 5" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 6.", + "EventCode": "0xa1", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x40", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "UOPS_DISPATCHED.PORT_6", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of uops executed on port 6" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to ports 7 and 8.", + "EventCode": "0xa1", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x80", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "UOPS_DISPATCHED.PORT_7_8", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of uops executed on port 7 and 8" + }, + { + "CollectPEBSRecord": "2", + "EventCode": "0xa2", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x2", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "RESOURCE_STALLS.SCOREBOARD", + "SampleAfterValue": "2000003", + "BriefDescription": "Counts cycles where the pipeline is stalled due to serializing operations." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.", + "EventCode": "0xA2", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x8", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "RESOURCE_STALLS.SB", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles stalled due to no store buffers available. (not including draining form sync)." + }, + { + "CollectPEBSRecord": "2", + "EventCode": "0xA3", + "Counter": "0,1,2,3", + "UMask": "0x1", + "PEBScounters": "0,1,2,3", + "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles while L2 cache miss demand load is outstanding.", + "CounterMask": "1" + }, + { + "CollectPEBSRecord": "2", + "EventCode": "0xA3", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x4", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL", + "SampleAfterValue": "2000003", + "BriefDescription": "Total execution stalls.", + "CounterMask": "4" + }, + { + "CollectPEBSRecord": "2", + "EventCode": "0xA3", + "Counter": "0,1,2,3", + "UMask": "0x5", + "PEBScounters": "0,1,2,3", + "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS", + "SampleAfterValue": "2000003", + "BriefDescription": "Execution stalls while L2 cache miss demand load is outstanding.", + "CounterMask": "5" + }, + { + "CollectPEBSRecord": "2", + "EventCode": "0xA3", + "Counter": "0,1,2,3", + "UMask": "0x8", + "PEBScounters": "0,1,2,3", + "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.", + "CounterMask": "8" + }, + { + "CollectPEBSRecord": "2", + "EventCode": "0xA3", + "Counter": "0,1,2,3", + "UMask": "0xc", + "PEBScounters": "0,1,2,3", + "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS", + "SampleAfterValue": "2000003", + "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.", + "CounterMask": "12" + }, + { + "CollectPEBSRecord": "2", + "EventCode": "0xA3", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x10", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles while memory subsystem has an outstanding load.", + "CounterMask": "16" + }, + { + "CollectPEBSRecord": "2", + "EventCode": "0xA3", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x14", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "CYCLE_ACTIVITY.STALLS_MEM_ANY", + "SampleAfterValue": "2000003", + "BriefDescription": "Execution stalls while memory subsystem has an outstanding load.", + "CounterMask": "20" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty.", + "EventCode": "0xa6", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x2", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "EXE_ACTIVITY.1_PORTS_UTIL", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles total of 1 uop is executed on all ports and Reservation Station was not empty." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty.", + "EventCode": "0xa6", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x4", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "EXE_ACTIVITY.2_PORTS_UTIL", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles total of 2 uops are executed on all ports and Reservation Station was not empty." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall.", + "EventCode": "0xA6", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x40", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "EXE_ACTIVITY.BOUND_ON_STORES", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles where the Store Buffer was full and no loads caused an execution stall.", + "CounterMask": "2" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts cycles during which no uops were executed on all ports and Reservation Station (RS) was not empty.", + "EventCode": "0xa6", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x80", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles where no uops were executed, the Reservation Station was not empty, the Store Buffer was full and there was no outstanding load." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector).", + "EventCode": "0xA8", + "Counter": "0,1,2,3", + "UMask": "0x1", + "PEBScounters": "0,1,2,3", + "EventName": "LSD.UOPS", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of Uops delivered by the LSD." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector).", + "EventCode": "0xA8", + "Counter": "0,1,2,3", + "UMask": "0x1", + "PEBScounters": "0,1,2,3", + "EventName": "LSD.CYCLES_ACTIVE", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.", + "CounterMask": "1" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector).", + "EventCode": "0xa8", + "Counter": "0,1,2,3", + "UMask": "0x1", + "PEBScounters": "0,1,2,3", + "EventName": "LSD.CYCLES_OK", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles optimal number of Uops delivered by the LSD, but did not come from the decoder.", + "CounterMask": "5" + }, + { + "CollectPEBSRecord": "2", + "EventCode": "0xB1", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "UOPS_EXECUTED.THREAD", + "SampleAfterValue": "2000003", + "BriefDescription": "Counts the number of uops to be executed per-thread each cycle." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.", + "EventCode": "0xB1", + "Invert": "1", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "UOPS_EXECUTED.STALL_CYCLES", + "SampleAfterValue": "2000003", + "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.", + "CounterMask": "1" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Cycles where at least 1 uop was executed per-thread.", + "EventCode": "0xb1", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "UOPS_EXECUTED.CYCLES_GE_1", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles where at least 1 uop was executed per-thread", + "CounterMask": "1" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Cycles where at least 2 uops were executed per-thread.", + "EventCode": "0xb1", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "UOPS_EXECUTED.CYCLES_GE_2", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles where at least 2 uops were executed per-thread", + "CounterMask": "2" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Cycles where at least 3 uops were executed per-thread.", + "EventCode": "0xb1", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "UOPS_EXECUTED.CYCLES_GE_3", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles where at least 3 uops were executed per-thread", + "CounterMask": "3" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Cycles where at least 4 uops were executed per-thread.", + "EventCode": "0xb1", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "UOPS_EXECUTED.CYCLES_GE_4", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles where at least 4 uops were executed per-thread", + "CounterMask": "4" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of uops executed from any thread.", + "EventCode": "0xB1", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x2", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "UOPS_EXECUTED.CORE", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of uops executed on the core." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts cycles when at least 1 micro-op is executed from any thread on physical core.", + "EventCode": "0xB1", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x2", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.", + "CounterMask": "1" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts cycles when at least 2 micro-ops are executed from any thread on physical core.", + "EventCode": "0xB1", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x2", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.", + "CounterMask": "2" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts cycles when at least 3 micro-ops are executed from any thread on physical core.", + "EventCode": "0xB1", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x2", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.", + "CounterMask": "3" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts cycles when at least 4 micro-ops are executed from any thread on physical core.", + "EventCode": "0xB1", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x2", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.", + "CounterMask": "4" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of x87 uops executed.", + "EventCode": "0xB1", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x10", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "UOPS_EXECUTED.X87", + "SampleAfterValue": "2000003", + "BriefDescription": "Counts the number of x87 uops dispatched." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", + "EventCode": "0xC0", + "Counter": "0,1,2,3,4,5,6,7", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "INST_RETIRED.ANY_P", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of instructions retired. General Counter - architectural event" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of cycles using always true condition (uops_ret &lt; 16) applied to non PEBS uops retired event.", + "EventCode": "0xC2", + "Invert": "1", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x2", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "UOPS_RETIRED.TOTAL_CYCLES", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles with less than 10 actually retired uops.", + "CounterMask": "10" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the retirement slots used each cycle.", + "EventCode": "0xc2", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x2", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "UOPS_RETIRED.SLOTS", + "SampleAfterValue": "2000003", + "BriefDescription": "Retirement slots used." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of machine clears (nukes) of any type.", + "EventCode": "0xC3", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "MACHINE_CLEARS.COUNT", + "SampleAfterValue": "100003", + "BriefDescription": "Number of machine clears (nukes) of any type.", + "CounterMask": "1", + "EdgeDetect": "1" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.", + "EventCode": "0xC3", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x4", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "MACHINE_CLEARS.SMC", + "SampleAfterValue": "100003", + "BriefDescription": "Self-modifying code (SMC) detected." + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts all branch instructions retired.", + "EventCode": "0xC4", + "Counter": "0,1,2,3,4,5,6,7", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "BR_INST_RETIRED.ALL_BRANCHES", + "SampleAfterValue": "400009", + "BriefDescription": "All branch instructions retired." + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts taken conditional branch instructions retired.", + "EventCode": "0xc4", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "BR_INST_RETIRED.COND_TAKEN", + "SampleAfterValue": "400009", + "BriefDescription": "Taken conditional branch instructions retired." + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts both direct and indirect near call instructions retired.", + "EventCode": "0xC4", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x2", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "BR_INST_RETIRED.NEAR_CALL", + "SampleAfterValue": "100007", + "BriefDescription": "Direct and indirect near call instructions retired." + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts return instructions retired.", + "EventCode": "0xC4", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x8", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "BR_INST_RETIRED.NEAR_RETURN", + "SampleAfterValue": "100007", + "BriefDescription": "Return instructions retired." + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts not taken branch instructions retired.", + "EventCode": "0xC4", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x10", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "BR_INST_RETIRED.COND_NTAKEN", + "SampleAfterValue": "400009", + "BriefDescription": "Not taken branch instructions retired." + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts conditional branch instructions retired.", + "EventCode": "0xc4", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x11", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "BR_INST_RETIRED.COND", + "SampleAfterValue": "400009", + "BriefDescription": "Conditional branch instructions retired." + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts taken branch instructions retired.", + "EventCode": "0xC4", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x20", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "BR_INST_RETIRED.NEAR_TAKEN", + "SampleAfterValue": "400009", + "BriefDescription": "Taken branch instructions retired." + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts far branch instructions retired.", + "EventCode": "0xC4", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x40", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "BR_INST_RETIRED.FAR_BRANCH", + "SampleAfterValue": "100007", + "BriefDescription": "Far branch instructions retired." + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts all indirect branch instructions retired (excluding RETs. TSX aborts is considered indirect branch).", + "EventCode": "0xc4", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x80", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "BR_INST_RETIRED.INDIRECT", + "SampleAfterValue": "100003", + "BriefDescription": "All indirect branch instructions retired (excluding RETs. TSX aborts are considered indirect branch)." + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.", + "EventCode": "0xC5", + "Counter": "0,1,2,3,4,5,6,7", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", + "SampleAfterValue": "400009", + "BriefDescription": "All mispredicted branch instructions retired.", + "Data_LA": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts taken conditional mispredicted branch instructions retired.", + "EventCode": "0xc5", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "BR_MISP_RETIRED.COND_TAKEN", + "SampleAfterValue": "400009", + "BriefDescription": "number of branch instructions retired that were mispredicted and taken. Non PEBS", + "Data_LA": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts mispredicted conditional branch instructions retired.", + "EventCode": "0xc5", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x11", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "BR_MISP_RETIRED.COND", + "SampleAfterValue": "400009", + "BriefDescription": "Mispredicted conditional branch instructions retired.", + "Data_LA": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken.", + "EventCode": "0xC5", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x20", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", + "SampleAfterValue": "400009", + "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken.", + "Data_LA": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts all miss-predicted indirect branch instructions retired (excluding RETs. TSX aborts is considered indirect branch).", + "EventCode": "0xC5", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x80", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "BR_MISP_RETIRED.INDIRECT", + "SampleAfterValue": "100003", + "BriefDescription": "All miss-predicted indirect branch instructions retired (excluding RETs. TSX aborts is considered indirect branch).", + "Data_LA": "1" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT.", + "EventCode": "0xcc", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x20", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "MISC_RETIRED.LBR_INSERTS", + "SampleAfterValue": "2000003", + "BriefDescription": "Increments whenever there is an update to the LBR array." + }, + { + "PublicDescription": "Counts number of retired PAUSE instructions (that do not end up with a VMExit to the VMM; TSX aborted Instructions may be counted).", + "EventCode": "0xcc", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x40", + "EventName": "MISC_RETIRED.PAUSE_INST", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of retired PAUSE instructions." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of times the front-end is resteered when it finds a branch instruction in a fetch line. This occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.", + "EventCode": "0xE6", + "Counter": "0,1,2,3", + "UMask": "0x1", + "PEBScounters": "0,1,2,3", + "EventName": "BACLEARS.ANY", + "SampleAfterValue": "100003", + "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "This event distributes cycle counts between active hyperthreads, i.e., those in C0. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If all other hyperthreads are inactive (or disabled or do not exist), all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.", + "EventCode": "0xec", + "Counter": "0,1,2,3,4,5,6,7", + "UMask": "0x2", + "PEBScounters": "0,1,2,3,4,5,6,7", + "EventName": "CPU_CLK_UNHALTED.DISTRIBUTED", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycle counts are evenly distributed between active threads in the Core." + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/icelake/virtual-memory.json b/tools/perf/pmu-events/arch/x86/icelake/virtual-memory.json new file mode 100644 index 000000000000..7180a900c175 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/icelake/virtual-memory.json @@ -0,0 +1,236 @@ +[ + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts page walks completed due to demand data loads whose address translations missed in the TLB and were mapped to 4K pages. The page walks can end with or without a page fault.", + "EventCode": "0x08", + "Counter": "0,1,2,3", + "UMask": "0x2", + "PEBScounters": "0,1,2,3", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K", + "SampleAfterValue": "2000003", + "BriefDescription": "Page walks completed due to a demand data load to a 4K page." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts page walks completed due to demand data loads whose address translations missed in the TLB and were mapped to 2M/4M pages. The page walks can end with or without a page fault.", + "EventCode": "0x08", + "Counter": "0,1,2,3", + "UMask": "0x4", + "PEBScounters": "0,1,2,3", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M", + "SampleAfterValue": "2000003", + "BriefDescription": "Page walks completed due to a demand data load to a 2M/4M page." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts demand data loads that caused a completed page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels. The page walk can end with or without a fault.", + "EventCode": "0x08", + "Counter": "0,1,2,3", + "UMask": "0xe", + "PEBScounters": "0,1,2,3", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", + "SampleAfterValue": "100003", + "BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (All page sizes)" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle.", + "EventCode": "0x08", + "Counter": "0,1,2,3", + "UMask": "0x10", + "PEBScounters": "0,1,2,3", + "EventName": "DTLB_LOAD_MISSES.WALK_PENDING", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of page walks outstanding for a demand load in the PMH each cycle." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load.", + "EventCode": "0x08", + "Counter": "0,1,2,3", + "UMask": "0x10", + "PEBScounters": "0,1,2,3", + "EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE", + "SampleAfterValue": "100003", + "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a demand load.", + "CounterMask": "1" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).", + "EventCode": "0x08", + "Counter": "0,1,2,3", + "UMask": "0x20", + "PEBScounters": "0,1,2,3", + "EventName": "DTLB_LOAD_MISSES.STLB_HIT", + "SampleAfterValue": "2000003", + "BriefDescription": "Loads that miss the DTLB and hit the STLB." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 4K pages. The page walks can end with or without a page fault.", + "EventCode": "0x49", + "Counter": "0,1,2,3", + "UMask": "0x2", + "PEBScounters": "0,1,2,3", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K", + "SampleAfterValue": "100003", + "BriefDescription": "Page walks completed due to a demand data store to a 4K page." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 2M/4M pages. The page walks can end with or without a page fault.", + "EventCode": "0x49", + "Counter": "0,1,2,3", + "UMask": "0x4", + "PEBScounters": "0,1,2,3", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M", + "SampleAfterValue": "100003", + "BriefDescription": "Page walks completed due to a demand data store to a 2M/4M page." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts demand data stores that caused a completed page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels. The page walk can end with or without a fault.", + "EventCode": "0x49", + "Counter": "0,1,2,3", + "UMask": "0xe", + "PEBScounters": "0,1,2,3", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", + "SampleAfterValue": "100003", + "BriefDescription": "Store misses in all TLB levels causes a page walk that completes. (All page sizes)" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle.", + "EventCode": "0x49", + "Counter": "0,1,2,3", + "UMask": "0x10", + "PEBScounters": "0,1,2,3", + "EventName": "DTLB_STORE_MISSES.WALK_PENDING", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of page walks outstanding for a store in the PMH each cycle." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.", + "EventCode": "0x49", + "Counter": "0,1,2,3", + "UMask": "0x10", + "PEBScounters": "0,1,2,3", + "EventName": "DTLB_STORE_MISSES.WALK_ACTIVE", + "SampleAfterValue": "100003", + "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a store.", + "CounterMask": "1" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).", + "EventCode": "0x49", + "Counter": "0,1,2,3", + "UMask": "0x20", + "PEBScounters": "0,1,2,3", + "EventName": "DTLB_STORE_MISSES.STLB_HIT", + "SampleAfterValue": "100003", + "BriefDescription": "Stores that miss the DTLB and hit the STLB." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts completed page walks (4K page size) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB. The page walk can end with or without a fault.", + "EventCode": "0x85", + "Counter": "0,1,2,3", + "UMask": "0x2", + "PEBScounters": "0,1,2,3", + "EventName": "ITLB_MISSES.WALK_COMPLETED_4K", + "SampleAfterValue": "100003", + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts code misses in all ITLB (Instruction TLB) levels that caused a completed page walk (2M and 4M page sizes). The page walk can end with or without a fault.", + "EventCode": "0x85", + "Counter": "0,1,2,3", + "UMask": "0x4", + "PEBScounters": "0,1,2,3", + "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M", + "SampleAfterValue": "100003", + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts completed page walks (2M and 4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", + "EventCode": "0x85", + "Counter": "0,1,2,3", + "UMask": "0xe", + "PEBScounters": "0,1,2,3", + "EventName": "ITLB_MISSES.WALK_COMPLETED", + "SampleAfterValue": "100003", + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (All page sizes)" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle.", + "EventCode": "0x85", + "Counter": "0,1,2,3", + "UMask": "0x10", + "PEBScounters": "0,1,2,3", + "EventName": "ITLB_MISSES.WALK_PENDING", + "SampleAfterValue": "100003", + "BriefDescription": "Number of page walks outstanding for an outstanding code request in the PMH each cycle." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request.", + "EventCode": "0x85", + "Counter": "0,1,2,3", + "UMask": "0x10", + "PEBScounters": "0,1,2,3", + "EventName": "ITLB_MISSES.WALK_ACTIVE", + "SampleAfterValue": "100003", + "BriefDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request.", + "CounterMask": "1" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB).", + "EventCode": "0x85", + "Counter": "0,1,2,3", + "UMask": "0x20", + "PEBScounters": "0,1,2,3", + "EventName": "ITLB_MISSES.STLB_HIT", + "SampleAfterValue": "100003", + "BriefDescription": "Instruction fetch requests that miss the ITLB and hit the STLB." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of flushes of the big or small ITLB pages. Counting include both TLB Flush (covering all sets) and TLB Set Clear (set-specific).", + "EventCode": "0xAE", + "Counter": "0,1,2,3", + "UMask": "0x1", + "PEBScounters": "0,1,2,3", + "EventName": "ITLB.ITLB_FLUSH", + "SampleAfterValue": "100007", + "BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of DTLB flush attempts of the thread-specific entries.", + "EventCode": "0xBD", + "Counter": "0,1,2,3", + "UMask": "0x1", + "PEBScounters": "0,1,2,3", + "EventName": "TLB_FLUSH.DTLB_THREAD", + "SampleAfterValue": "100007", + "BriefDescription": "DTLB flush attempts of the thread-specific entries" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of any STLB flush attempts (such as entire, VPID, PCID, InvPage, CR3 write, etc.).", + "EventCode": "0xBD", + "Counter": "0,1,2,3", + "UMask": "0x20", + "PEBScounters": "0,1,2,3", + "EventName": "TLB_FLUSH.STLB_ANY", + "SampleAfterValue": "100007", + "BriefDescription": "STLB flush attempts" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index d6984a3017e0..745ced083844 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -33,4 +33,7 @@ GenuineIntel-6-25,v2,westmereep-sp,core GenuineIntel-6-2F,v2,westmereex,core GenuineIntel-6-55-[01234],v1,skylakex,core GenuineIntel-6-55-[56789ABCDEF],v1,cascadelakex,core +GenuineIntel-6-7D,v1,icelake,core +GenuineIntel-6-7E,v1,icelake,core +GenuineIntel-6-86,v1,tremontx,core AuthenticAMD-23-[[:xdigit:]]+,v1,amdfam17h,core diff --git a/tools/perf/pmu-events/arch/x86/tremontx/cache.json b/tools/perf/pmu-events/arch/x86/tremontx/cache.json new file mode 100644 index 000000000000..f88040171b4d --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/tremontx/cache.json @@ -0,0 +1,111 @@ +[ + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts cacheable memory requests that miss in the the Last Level Cache. Requests include Demand Loads, Reads for Ownership(RFO), Instruction fetches and L1 HW prefetches. If the platform has an L3 cache, last level cache is the L3, otherwise it is the L2.", + "EventCode": "0x2e", + "Counter": "0,1,2,3", + "UMask": "0x41", + "PEBScounters": "0,1,2,3", + "EventName": "LONGEST_LAT_CACHE.MISS", + "PDIR_COUNTER": "na", + "SampleAfterValue": "200003", + "BriefDescription": "Counts memory requests originating from the core that miss in the last level cache. If the platform has an L3 cache, last level cache is the L3, otherwise it is the L2." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts cacheable memory requests that access the Last Level Cache. Requests include Demand Loads, Reads for Ownership(RFO), Instruction fetches and L1 HW prefetches. If the platform has an L3 cache, last level cache is the L3, otherwise it is the L2.", + "EventCode": "0x2e", + "Counter": "0,1,2,3", + "UMask": "0x4f", + "PEBScounters": "0,1,2,3", + "EventName": "LONGEST_LAT_CACHE.REFERENCE", + "PDIR_COUNTER": "na", + "SampleAfterValue": "200003", + "BriefDescription": "Counts memory requests originating from the core that reference a cache line in the last level cache. If the platform has an L3 cache, last level cache is the L3, otherwise it is the L2." + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of load uops retired. This event is Precise Event capable", + "EventCode": "0xd0", + "Counter": "0,1,2,3", + "UMask": "0x81", + "PEBScounters": "0,1,2,3", + "EventName": "MEM_UOPS_RETIRED.ALL_LOADS", + "SampleAfterValue": "200003", + "BriefDescription": "Counts the number of load uops retired.", + "Data_LA": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of store uops retired. This event is Precise Event capable", + "EventCode": "0xd0", + "Counter": "0,1,2,3", + "UMask": "0x82", + "PEBScounters": "0,1,2,3", + "EventName": "MEM_UOPS_RETIRED.ALL_STORES", + "SampleAfterValue": "200003", + "BriefDescription": "Counts the number of store uops retired.", + "Data_LA": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "EventCode": "0xd1", + "Counter": "0,1,2,3", + "UMask": "0x1", + "PEBScounters": "0,1,2,3", + "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT", + "SampleAfterValue": "200003", + "BriefDescription": "Counts the number of load uops retired that hit the level 1 data cache", + "Data_LA": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "EventCode": "0xd1", + "Counter": "0,1,2,3", + "UMask": "0x2", + "PEBScounters": "0,1,2,3", + "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT", + "SampleAfterValue": "200003", + "BriefDescription": "Counts the number of load uops retired that hit in the level 2 cache", + "Data_LA": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "EventCode": "0xd1", + "Counter": "0,1,2,3", + "UMask": "0x4", + "PEBScounters": "0,1,2,3", + "EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT", + "SampleAfterValue": "200003", + "BriefDescription": "Counts the number of load uops retired that miss in the level 3 cache" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "EventCode": "0xd1", + "Counter": "0,1,2,3", + "UMask": "0x8", + "PEBScounters": "0,1,2,3", + "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS", + "SampleAfterValue": "200003", + "BriefDescription": "Counts the number of load uops retired that miss in the level 1 data cache", + "Data_LA": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "EventCode": "0xd1", + "Counter": "0,1,2,3", + "UMask": "0x10", + "PEBScounters": "0,1,2,3", + "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS", + "SampleAfterValue": "200003", + "BriefDescription": "Counts the number of load uops retired that miss in the level 2 cache", + "Data_LA": "1" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/tremontx/frontend.json b/tools/perf/pmu-events/arch/x86/tremontx/frontend.json new file mode 100644 index 000000000000..73b0a1ed5756 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/tremontx/frontend.json @@ -0,0 +1,26 @@ +[ + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts requests to the Instruction Cache (ICache) for one or more bytes in an ICache Line and that cache line is not in the ICache (miss). The event strives to count on a cache line basis, so that multiple accesses which miss in a single cache line count as one ICACHE.MISS. Specifically, the event counts when straight line code crosses the cache line boundary, or when a branch target is to a new line, and that cache line is not in the ICache.", + "EventCode": "0x80", + "Counter": "0,1,2,3", + "UMask": "0x2", + "PEBScounters": "0,1,2,3", + "EventName": "ICACHE.MISSES", + "PDIR_COUNTER": "na", + "SampleAfterValue": "200003", + "BriefDescription": "Counts requests to the Instruction Cache (ICache) for one or more bytes in a cache line and they do not hit in the ICache (miss)." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts requests to the Instruction Cache (ICache) for one or more bytes in an ICache Line. The event strives to count on a cache line basis, so that multiple fetches to a single cache line count as one ICACHE.ACCESS. Specifically, the event counts when accesses from straight line code crosses the cache line boundary, or when a branch target is to a new line.", + "EventCode": "0x80", + "Counter": "0,1,2,3", + "UMask": "0x3", + "PEBScounters": "0,1,2,3", + "EventName": "ICACHE.ACCESSES", + "PDIR_COUNTER": "na", + "SampleAfterValue": "200003", + "BriefDescription": "Counts requests to the Instruction Cache (ICache) for one or more bytes cache Line." + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/tremontx/memory.json b/tools/perf/pmu-events/arch/x86/tremontx/memory.json new file mode 100644 index 000000000000..65469e84f35b --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/tremontx/memory.json @@ -0,0 +1,26 @@ +[ + { + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventCode": "0XB7", + "MSRValue": "0x000000003F04000001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OCR.DEMAND_DATA_RD.L3_MISS", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads that was not supplied by the L3 cache.", + "Offcore": "1" + }, + { + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventCode": "0XB7", + "MSRValue": "0x000000003F04000002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OCR.DEMAND_RFO.L3_MISS", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand reads for ownership (RFO) requests and software based prefetches for exclusive ownership (PREFETCHW) that was not supplied by the L3 cache.", + "Offcore": "1" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/tremontx/other.json b/tools/perf/pmu-events/arch/x86/tremontx/other.json new file mode 100644 index 000000000000..85bf3c8f3914 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/tremontx/other.json @@ -0,0 +1,26 @@ +[ + { + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventCode": "0XB7", + "MSRValue": "0x000000000000010001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads that have any response type.", + "Offcore": "1" + }, + { + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventCode": "0XB7", + "MSRValue": "0x000000000000010002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand reads for ownership (RFO) requests and software based prefetches for exclusive ownership (PREFETCHW) that have any response type.", + "Offcore": "1" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/tremontx/pipeline.json b/tools/perf/pmu-events/arch/x86/tremontx/pipeline.json new file mode 100644 index 000000000000..05a8f6a7d9c0 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/tremontx/pipeline.json @@ -0,0 +1,111 @@ +[ + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of instructions that retire. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. The counter continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses fixed counter 0.", + "Counter": "32", + "UMask": "0x1", + "PEBScounters": "32", + "EventName": "INST_RETIRED.ANY", + "SampleAfterValue": "2000003", + "BriefDescription": "Counts the number of instructions retired. (Fixed event)" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of core cycles while the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. The core frequency may change from time to time. For this reason this event may have a changing ratio with regards to time. This event uses fixed counter 1.", + "Counter": "33", + "UMask": "0x2", + "PEBScounters": "33", + "EventName": "CPU_CLK_UNHALTED.CORE", + "PDIR_COUNTER": "na", + "SampleAfterValue": "2000003", + "BriefDescription": "Counts the number of unhalted core clock cycles. (Fixed event)" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of reference cycles that the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. The core frequency may change from time. This event is not affected by core frequency changes and at a fixed frequency. This event uses fixed counter 2.", + "Counter": "34", + "UMask": "0x3", + "PEBScounters": "34", + "EventName": "CPU_CLK_UNHALTED.REF_TSC", + "PDIR_COUNTER": "na", + "SampleAfterValue": "2000003", + "BriefDescription": "Counts the number of unhalted reference clock cycles at TSC frequency. (Fixed event)" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of core cycles while the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. The core frequency may change from time to time. For this reason this event may have a changing ratio with regards to time. This event uses a programmable general purpose performance counter.", + "EventCode": "0x3c", + "Counter": "0,1,2,3", + "PEBScounters": "0,1,2,3", + "EventName": "CPU_CLK_UNHALTED.CORE_P", + "PDIR_COUNTER": "na", + "SampleAfterValue": "2000003", + "BriefDescription": "Counts the number of unhalted core clock cycles." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts reference cycles (at TSC frequency) when core is not halted. This event uses a programmable general purpose perfmon counter.", + "EventCode": "0x3c", + "Counter": "0,1,2,3", + "UMask": "0x1", + "PEBScounters": "0,1,2,3", + "EventName": "CPU_CLK_UNHALTED.REF", + "PDIR_COUNTER": "na", + "SampleAfterValue": "2000003", + "BriefDescription": "Counts the number of unhalted reference clock cycles at TSC frequency." + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of instructions that retire execution. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. The event continues counting during hardware interrupts, traps, and inside interrupt handlers. This is an architectural performance event. This event uses a Programmable general purpose perfmon counter. *This event is Precise Event capable: The EventingRIP field in the PEBS record is precise to the address of the instruction which caused the event.", + "EventCode": "0xc0", + "Counter": "0,1,2,3", + "PEBScounters": "0,1,2,3", + "EventName": "INST_RETIRED.ANY_P", + "SampleAfterValue": "2000003", + "BriefDescription": "Counts the number of instructions retired." + }, + { + "CollectPEBSRecord": "2", + "EventCode": "0xc3", + "Counter": "0,1,2,3", + "PEBScounters": "0,1,2,3", + "EventName": "MACHINE_CLEARS.ANY", + "PDIR_COUNTER": "na", + "SampleAfterValue": "20003", + "BriefDescription": "Counts all machine clears due to, but not limited to memory ordering, memory disambiguation, SMC, page faults and FP assist." + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts branch instructions retired for all branch types. This event is Precise Event capable. This is an architectural event.", + "EventCode": "0xc4", + "Counter": "0,1,2,3", + "PEBScounters": "0,1,2,3", + "EventName": "BR_INST_RETIRED.ALL_BRANCHES", + "SampleAfterValue": "200003", + "BriefDescription": "Counts the number of branch instructions retired for all branch types." + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts mispredicted branch instructions retired for all branch types. This event is Precise Event capable. This is an architectural event.", + "EventCode": "0xc5", + "Counter": "0,1,2,3", + "PEBScounters": "0,1,2,3", + "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", + "SampleAfterValue": "200003", + "BriefDescription": "Counts the number of mispredicted branch instructions retired." + }, + { + "CollectPEBSRecord": "2", + "EventCode": "0xcd", + "Counter": "0,1,2,3", + "PEBScounters": "0,1,2,3", + "EventName": "CYCLES_DIV_BUSY.ANY", + "PDIR_COUNTER": "na", + "SampleAfterValue": "2000003", + "BriefDescription": "Counts cycles the floating point divider or integer divider or both are busy. Does not imply a stall waiting for either divider." + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/tremontx/uncore-memory.json b/tools/perf/pmu-events/arch/x86/tremontx/uncore-memory.json new file mode 100644 index 000000000000..15376f2cf052 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/tremontx/uncore-memory.json @@ -0,0 +1,73 @@ +[ + { + "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x04", + "EventName": "LLC_MISSES.MEM_READ", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x0f", + "Unit": "iMC" + }, + { + "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x04", + "EventName": "LLC_MISSES.MEM_WRITE", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x30", + "Unit": "iMC" + }, + { + "BriefDescription": "Memory controller clock ticks", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventName": "UNC_M_CLOCKTICKS", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Pre-charge for reads", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x02", + "EventName": "UNC_M_PRE_COUNT.RD", + "PerPkg": "1", + "UMask": "0x04", + "Unit": "iMC" + }, + { + "BriefDescription": "Pre-charge for writes", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x02", + "EventName": "UNC_M_PRE_COUNT.WR", + "PerPkg": "1", + "UMask": "0x08", + "Unit": "iMC" + }, + { + "BriefDescription": "Precharge due to read on page miss, write on page miss or PGT", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x02", + "EventName": "UNC_M_PRE_COUNT.ALL", + "PerPkg": "1", + "UMask": "0x1c", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Precharge commands. : Precharge due to page table", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x02", + "EventName": "UNC_M_PRE_COUNT.PGT", + "PerPkg": "1", + "PublicDescription": "DRAM Precharge commands. : Precharge due to page table : Counts the number of DRAM Precharge commands sent on this channel.", + "UMask": "0x10", + "Unit": "iMC" + } +] diff --git a/tools/perf/pmu-events/arch/x86/tremontx/uncore-other.json b/tools/perf/pmu-events/arch/x86/tremontx/uncore-other.json new file mode 100644 index 000000000000..6deff1fe89e3 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/tremontx/uncore-other.json @@ -0,0 +1,431 @@ +[ + { + "BriefDescription": "Uncore cache clock ticks", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventName": "UNC_CHA_CLOCKTICKS", + "PerPkg": "1", + "Unit": "CHA" + }, + { + "BriefDescription": "LLC misses - Uncacheable reads (from cpu) . Derived from unc_cha_tor_inserts.ia_miss", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "LLC_MISSES.UNCACHEABLE", + "Filter": "config1=0x40e33", + "PerPkg": "1", + "UMask": "0xC001FE01", + "UMaskExt": "0xC001FE", + "Unit": "CHA" + }, + { + "BriefDescription": "MMIO reads. Derived from unc_cha_tor_inserts.ia_miss", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "LLC_MISSES.MMIO_READ", + "Filter": "config1=0x40040e33", + "PerPkg": "1", + "UMask": "0xC001FE01", + "UMaskExt": "0xC001FE", + "Unit": "CHA" + }, + { + "BriefDescription": "MMIO writes. Derived from unc_cha_tor_inserts.ia_miss", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "LLC_MISSES.MMIO_WRITE", + "Filter": "config1=0x40041e33", + "PerPkg": "1", + "UMask": "0xC001FE01", + "UMaskExt": "0xC001FE", + "Unit": "CHA" + }, + { + "BriefDescription": "Streaming stores (full cache line). Derived from unc_cha_tor_inserts.ia_miss", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_FULL", + "Filter": "config1=0x41833", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0xC001FE01", + "UMaskExt": "0xC001FE", + "Unit": "CHA" + }, + { + "BriefDescription": "Streaming stores (partial cache line). Derived from unc_cha_tor_inserts.ia_miss", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_PARTIAL", + "Filter": "config1=0x41a33", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0xC001FE01", + "UMaskExt": "0xC001FE", + "Unit": "CHA" + }, + { + "BriefDescription": "PCI Express bandwidth reading at IIO. Derived from unc_iio_data_req_of_cpu.mem_read.part0", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "LLC_MISSES.PCIE_READ", + "FCMask": "0x07", + "Filter": "ch_mask=0x1f", + "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 +UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 +UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 +UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3", + "MetricName": "LLC_MISSES.PCIE_READ", + "PerPkg": "1", + "PortMask": "0x01", + "ScaleUnit": "4Bytes", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth writing at IIO. Derived from unc_iio_data_req_of_cpu.mem_write.part0", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "LLC_MISSES.PCIE_WRITE", + "FCMask": "0x07", + "Filter": "ch_mask=0x1f", + "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3", + "MetricName": "LLC_MISSES.PCIE_WRITE", + "PerPkg": "1", + "PortMask": "0x01", + "ScaleUnit": "4Bytes", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth writing at IIO, part 1", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "ScaleUnit": "4Bytes", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth writing at IIO, part 2", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "ScaleUnit": "4Bytes", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth writing at IIO, part 3", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "ScaleUnit": "4Bytes", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth reading at IIO, part 1", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "ScaleUnit": "4Bytes", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth reading at IIO, part 2", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "ScaleUnit": "4Bytes", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth reading at IIO, part 3", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "ScaleUnit": "4Bytes", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "TOR Inserts; CRd misses from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Code read from local IA that misses in the snoop filter", + "UMask": "0xC80FFE01", + "UMaskExt": "0xC80FFE", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; CRd Pref misses from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Code read prefetch from local IA that misses in the snoop filter", + "UMask": "0xC88FFE01", + "UMaskExt": "0xC88FFE", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; DRd Opt misses from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Data read opt from local IA that misses in the snoop filter", + "UMask": "0xC827FE01", + "UMaskExt": "0xC827FE", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; DRd Opt Pref misses from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Data read opt prefetch from local IA that misses in the snoop filter", + "UMask": "0xC8A7FE01", + "UMaskExt": "0xC8A7FE", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RFO misses from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Read for ownership from local IA that misses in the snoop filter", + "UMask": "0xC807FE01", + "UMaskExt": "0xC807FE", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RFO pref misses from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Read for ownership prefetch from local IA that misses in the snoop filter", + "UMask": "0xC887FE01", + "UMaskExt": "0xC887FE", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; WCiL misses from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WCIL", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Data read from local IA that misses in the snoop filter", + "UMask": "0xC86FFE01", + "UMaskExt": "0xC86FFE", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; WCiLF misses from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WCILF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Data read from local IA that misses in the snoop filter", + "UMask": "0xC867FE01", + "UMaskExt": "0xC867FE", + "Unit": "CHA" + }, + { + "BriefDescription": "Clockticks of the integrated IO (IIO) traffic controller", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x01", + "EventName": "UNC_IIO_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Clockticks of the integrated IO (IIO) traffic controller", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card reading from DRAM", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card reading from DRAM", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card reading from DRAM", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card reading from DRAM", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to DRAM", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to DRAM", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to DRAM", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to DRAM", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "Clockticks of the IO coherency tracker (IRP)", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x01", + "EventName": "UNC_I_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Clockticks of the IO coherency tracker (IRP)", + "Unit": "IRP" + }, + { + "BriefDescription": "Clockticks of the mesh to memory (M2M)", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventName": "UNC_M2M_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Clockticks of the mesh to memory (M2M)", + "Unit": "M2M" + }, + { + "BriefDescription": "Clockticks of the mesh to PCI (M2P)", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x01", + "EventName": "UNC_M2P_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Clockticks of the mesh to PCI (M2P)", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Clockticks in the UBOX using a dedicated 48-bit Fixed Counter", + "Counter": "FIXED", + "CounterType": "PGMABLE", + "EventCode": "0xff", + "EventName": "UNC_U_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Clockticks in the UBOX using a dedicated 48-bit Fixed Counter", + "Unit": "UBOX" + } +] diff --git a/tools/perf/pmu-events/arch/x86/tremontx/uncore-power.json b/tools/perf/pmu-events/arch/x86/tremontx/uncore-power.json new file mode 100644 index 000000000000..ea62c092b43f --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/tremontx/uncore-power.json @@ -0,0 +1,11 @@ +[ + { + "BriefDescription": "Clockticks of the power control unit (PCU)", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventName": "UNC_P_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Clockticks of the power control unit (PCU)", + "Unit": "PCU" + } +] diff --git a/tools/perf/pmu-events/arch/x86/tremontx/virtual-memory.json b/tools/perf/pmu-events/arch/x86/tremontx/virtual-memory.json new file mode 100644 index 000000000000..93e407a0f645 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/tremontx/virtual-memory.json @@ -0,0 +1,86 @@ +[ + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts page walks completed due to demand data loads (including SW prefetches) whose address translations missed in all TLB levels and were mapped to 4K pages. The page walks can end with or without a page fault.", + "EventCode": "0x08", + "Counter": "0,1,2,3", + "UMask": "0x2", + "PEBScounters": "0,1,2,3", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K", + "PDIR_COUNTER": "na", + "SampleAfterValue": "200003", + "BriefDescription": "Page walk completed due to a demand load to a 4K page." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts page walks completed due to demand data loads (including SW prefetches) whose address translations missed in all TLB levels and were mapped to 2M or 4M pages. The page walks can end with or without a page fault.", + "EventCode": "0x08", + "Counter": "0,1,2,3", + "UMask": "0x4", + "PEBScounters": "0,1,2,3", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M", + "PDIR_COUNTER": "na", + "SampleAfterValue": "200003", + "BriefDescription": "Page walk completed due to a demand load to a 2M or 4M page." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 4K pages. The page walks can end with or without a page fault.", + "EventCode": "0x49", + "Counter": "0,1,2,3", + "UMask": "0x2", + "PEBScounters": "0,1,2,3", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K", + "PDIR_COUNTER": "na", + "SampleAfterValue": "2000003", + "BriefDescription": "Page walk completed due to a demand data store to a 4K page." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 2M or 4M pages. The page walks can end with or without a page fault.", + "EventCode": "0x49", + "Counter": "0,1,2,3", + "UMask": "0x4", + "PEBScounters": "0,1,2,3", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M", + "PDIR_COUNTER": "na", + "SampleAfterValue": "2000003", + "BriefDescription": "Page walk completed due to a demand data store to a 2M or 4M page." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of times the machine was unable to find a translation in the Instruction Translation Lookaside Buffer (ITLB) and new translation was filled into the ITLB. The event is speculative in nature, but will not count translations (page walks) that are begun and not finished, or translations that are finished but not filled into the ITLB.", + "EventCode": "0x81", + "Counter": "0,1,2,3", + "UMask": "0x4", + "PEBScounters": "0,1,2,3", + "EventName": "ITLB.FILLS", + "PDIR_COUNTER": "na", + "SampleAfterValue": "200003", + "BriefDescription": "Counts the number of times there was an ITLB miss and a new translation was filled into the ITLB." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts page walks completed due to instruction fetches whose address translations missed in the TLB and were mapped to 4K pages. The page walks can end with or without a page fault.", + "EventCode": "0x85", + "Counter": "0,1,2,3", + "UMask": "0x2", + "PEBScounters": "0,1,2,3", + "EventName": "ITLB_MISSES.WALK_COMPLETED_4K", + "PDIR_COUNTER": "na", + "SampleAfterValue": "2000003", + "BriefDescription": "Page walk completed due to an instruction fetch in a 4K page." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts page walks completed due to instruction fetches whose address translations missed in the TLB and were mapped to 2M or 4M pages. The page walks can end with or without a page fault.", + "EventCode": "0x85", + "Counter": "0,1,2,3", + "UMask": "0x4", + "PEBScounters": "0,1,2,3", + "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M", + "PDIR_COUNTER": "na", + "SampleAfterValue": "2000003", + "BriefDescription": "Page walk completed due to an instruction fetch in a 2M or 4M page." + } +]
\ No newline at end of file diff --git a/tools/perf/tests/backward-ring-buffer.c b/tools/perf/tests/backward-ring-buffer.c index 1a9c3becf5ff..9bdf66139099 100644 --- a/tools/perf/tests/backward-ring-buffer.c +++ b/tools/perf/tests/backward-ring-buffer.c @@ -25,7 +25,7 @@ static void testcase(void) } } -static int count_samples(struct perf_evlist *evlist, int *sample_count, +static int count_samples(struct evlist *evlist, int *sample_count, int *comm_count) { int i; @@ -55,7 +55,7 @@ static int count_samples(struct perf_evlist *evlist, int *sample_count, return TEST_OK; } -static int do_test(struct perf_evlist *evlist, int mmap_pages, +static int do_test(struct evlist *evlist, int mmap_pages, int *sample_count, int *comm_count) { int err; @@ -68,9 +68,9 @@ static int do_test(struct perf_evlist *evlist, int mmap_pages, return TEST_FAIL; } - perf_evlist__enable(evlist); + evlist__enable(evlist); testcase(); - perf_evlist__disable(evlist); + evlist__disable(evlist); err = count_samples(evlist, sample_count, comm_count); perf_evlist__munmap(evlist); @@ -82,8 +82,8 @@ int test__backward_ring_buffer(struct test *test __maybe_unused, int subtest __m { int ret = TEST_SKIP, err, sample_count = 0, comm_count = 0; char pid[16], sbuf[STRERR_BUFSIZE]; - struct perf_evlist *evlist; - struct perf_evsel *evsel __maybe_unused; + struct evlist *evlist; + struct evsel *evsel __maybe_unused; struct parse_events_error parse_error; struct record_opts opts = { .target = { @@ -99,7 +99,7 @@ int test__backward_ring_buffer(struct test *test __maybe_unused, int subtest __m pid[sizeof(pid) - 1] = '\0'; opts.target.tid = opts.target.pid = pid; - evlist = perf_evlist__new(); + evlist = evlist__new(); if (!evlist) { pr_debug("Not enough memory to create evlist\n"); return TEST_FAIL; @@ -125,7 +125,7 @@ int test__backward_ring_buffer(struct test *test __maybe_unused, int subtest __m perf_evlist__config(evlist, &opts, NULL); - err = perf_evlist__open(evlist); + err = evlist__open(evlist); if (err < 0) { pr_debug("perf_evlist__open: %s\n", str_error_r(errno, sbuf, sizeof(sbuf))); @@ -150,6 +150,6 @@ int test__backward_ring_buffer(struct test *test __maybe_unused, int subtest __m ret = TEST_OK; out_delete_evlist: - perf_evlist__delete(evlist); + evlist__delete(evlist); return ret; } diff --git a/tools/perf/tests/bitmap.c b/tools/perf/tests/bitmap.c index 96e7fc1ad3f9..db2aadff3708 100644 --- a/tools/perf/tests/bitmap.c +++ b/tools/perf/tests/bitmap.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/compiler.h> #include <linux/bitmap.h> +#include <perf/cpumap.h> #include "tests.h" #include "cpumap.h" #include "debug.h" @@ -9,7 +10,7 @@ static unsigned long *get_bitmap(const char *str, int nbits) { - struct cpu_map *map = cpu_map__new(str); + struct perf_cpu_map *map = perf_cpu_map__new(str); unsigned long *bm = NULL; int i; @@ -21,7 +22,7 @@ static unsigned long *get_bitmap(const char *str, int nbits) } if (map) - cpu_map__put(map); + perf_cpu_map__put(map); return bm; } diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c index c9e4cdc4c9c8..e16f927f38b6 100644 --- a/tools/perf/tests/bpf.c +++ b/tools/perf/tests/bpf.c @@ -118,7 +118,7 @@ static int do_test(struct bpf_object *obj, int (*func)(void), char pid[16]; char sbuf[STRERR_BUFSIZE]; - struct perf_evlist *evlist; + struct evlist *evlist; int i, ret = TEST_FAIL, err = 0, count = 0; struct parse_events_state parse_state; @@ -140,7 +140,7 @@ static int do_test(struct bpf_object *obj, int (*func)(void), opts.target.tid = opts.target.pid = pid; /* Instead of perf_evlist__new_default, don't add default events */ - evlist = perf_evlist__new(); + evlist = evlist__new(); if (!evlist) { pr_debug("Not enough memory to create evlist\n"); return TEST_FAIL; @@ -157,7 +157,7 @@ static int do_test(struct bpf_object *obj, int (*func)(void), perf_evlist__config(evlist, &opts, NULL); - err = perf_evlist__open(evlist); + err = evlist__open(evlist); if (err < 0) { pr_debug("perf_evlist__open: %s\n", str_error_r(errno, sbuf, sizeof(sbuf))); @@ -171,9 +171,9 @@ static int do_test(struct bpf_object *obj, int (*func)(void), goto out_delete_evlist; } - perf_evlist__enable(evlist); + evlist__enable(evlist); (*func)(); - perf_evlist__disable(evlist); + evlist__disable(evlist); for (i = 0; i < evlist->nr_mmaps; i++) { union perf_event *event; @@ -200,7 +200,7 @@ static int do_test(struct bpf_object *obj, int (*func)(void), ret = TEST_OK; out_delete_evlist: - perf_evlist__delete(evlist); + evlist__delete(evlist); return ret; } diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index aa6df122b175..e45df0736261 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -8,6 +8,8 @@ #include <stdio.h> #include <string.h> #include <sys/param.h> +#include <perf/cpumap.h> +#include <perf/evlist.h> #include "parse-events.h" #include "evlist.h" @@ -362,7 +364,7 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode, } static int process_sample_event(struct machine *machine, - struct perf_evlist *evlist, + struct evlist *evlist, union perf_event *event, struct state *state) { struct perf_sample sample; @@ -385,7 +387,7 @@ static int process_sample_event(struct machine *machine, return ret; } -static int process_event(struct machine *machine, struct perf_evlist *evlist, +static int process_event(struct machine *machine, struct evlist *evlist, union perf_event *event, struct state *state) { if (event->header.type == PERF_RECORD_SAMPLE) @@ -408,7 +410,7 @@ static int process_event(struct machine *machine, struct perf_evlist *evlist, return 0; } -static int process_events(struct machine *machine, struct perf_evlist *evlist, +static int process_events(struct machine *machine, struct evlist *evlist, struct state *state) { union perf_event *event; @@ -552,10 +554,10 @@ static int do_test_code_reading(bool try_kcore) struct state state = { .done_cnt = 0, }; - struct thread_map *threads = NULL; - struct cpu_map *cpus = NULL; - struct perf_evlist *evlist = NULL; - struct perf_evsel *evsel = NULL; + struct perf_thread_map *threads = NULL; + struct perf_cpu_map *cpus = NULL; + struct evlist *evlist = NULL; + struct evsel *evsel = NULL; int err = -1, ret; pid_t pid; struct map *map; @@ -613,22 +615,22 @@ static int do_test_code_reading(bool try_kcore) goto out_put; } - cpus = cpu_map__new(NULL); + cpus = perf_cpu_map__new(NULL); if (!cpus) { - pr_debug("cpu_map__new failed\n"); + pr_debug("perf_cpu_map__new failed\n"); goto out_put; } while (1) { const char *str; - evlist = perf_evlist__new(); + evlist = evlist__new(); if (!evlist) { pr_debug("perf_evlist__new failed\n"); goto out_put; } - perf_evlist__set_maps(evlist, cpus, threads); + perf_evlist__set_maps(&evlist->core, cpus, threads); str = do_determine_event(excl_kernel); pr_debug("Parsing event '%s'\n", str); @@ -642,11 +644,11 @@ static int do_test_code_reading(bool try_kcore) evsel = perf_evlist__first(evlist); - evsel->attr.comm = 1; - evsel->attr.disabled = 1; - evsel->attr.enable_on_exec = 0; + evsel->core.attr.comm = 1; + evsel->core.attr.disabled = 1; + evsel->core.attr.enable_on_exec = 0; - ret = perf_evlist__open(evlist); + ret = evlist__open(evlist); if (ret < 0) { if (!excl_kernel) { excl_kernel = true; @@ -655,10 +657,10 @@ static int do_test_code_reading(bool try_kcore) * and will be freed by following perf_evlist__set_maps * call. Getting refference to keep them alive. */ - cpu_map__get(cpus); - thread_map__get(threads); - perf_evlist__set_maps(evlist, NULL, NULL); - perf_evlist__delete(evlist); + perf_cpu_map__get(cpus); + perf_thread_map__get(threads); + perf_evlist__set_maps(&evlist->core, NULL, NULL); + evlist__delete(evlist); evlist = NULL; continue; } @@ -680,11 +682,11 @@ static int do_test_code_reading(bool try_kcore) goto out_put; } - perf_evlist__enable(evlist); + evlist__enable(evlist); do_something(); - perf_evlist__disable(evlist); + evlist__disable(evlist); ret = process_events(machine, evlist, &state); if (ret < 0) @@ -703,10 +705,10 @@ out_put: out_err: if (evlist) { - perf_evlist__delete(evlist); + evlist__delete(evlist); } else { - cpu_map__put(cpus); - thread_map__put(threads); + perf_cpu_map__put(cpus); + perf_thread_map__put(threads); } machine__delete_threads(machine); machine__delete(machine); diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c index e78b897677bd..b71fe09a8087 100644 --- a/tools/perf/tests/cpumap.c +++ b/tools/perf/tests/cpumap.c @@ -5,6 +5,7 @@ #include "event.h" #include <string.h> #include <linux/bitops.h> +#include <perf/cpumap.h> #include "debug.h" struct machine; @@ -17,7 +18,7 @@ static int process_event_mask(struct perf_tool *tool __maybe_unused, struct cpu_map_event *map_event = &event->cpu_map; struct cpu_map_mask *mask; struct cpu_map_data *data; - struct cpu_map *map; + struct perf_cpu_map *map; int i; data = &map_event->data; @@ -39,7 +40,7 @@ static int process_event_mask(struct perf_tool *tool __maybe_unused, TEST_ASSERT_VAL("wrong cpu", map->map[i] == i); } - cpu_map__put(map); + perf_cpu_map__put(map); return 0; } @@ -51,7 +52,7 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused, struct cpu_map_event *map_event = &event->cpu_map; struct cpu_map_entries *cpus; struct cpu_map_data *data; - struct cpu_map *map; + struct perf_cpu_map *map; data = &map_event->data; @@ -68,36 +69,36 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused, TEST_ASSERT_VAL("wrong cpu", map->map[0] == 1); TEST_ASSERT_VAL("wrong cpu", map->map[1] == 256); TEST_ASSERT_VAL("wrong refcnt", refcount_read(&map->refcnt) == 1); - cpu_map__put(map); + perf_cpu_map__put(map); return 0; } int test__cpu_map_synthesize(struct test *test __maybe_unused, int subtest __maybe_unused) { - struct cpu_map *cpus; + struct perf_cpu_map *cpus; /* This one is better stores in mask. */ - cpus = cpu_map__new("0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19"); + cpus = perf_cpu_map__new("0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19"); TEST_ASSERT_VAL("failed to synthesize map", !perf_event__synthesize_cpu_map(NULL, cpus, process_event_mask, NULL)); - cpu_map__put(cpus); + perf_cpu_map__put(cpus); /* This one is better stores in cpu values. */ - cpus = cpu_map__new("1,256"); + cpus = perf_cpu_map__new("1,256"); TEST_ASSERT_VAL("failed to synthesize map", !perf_event__synthesize_cpu_map(NULL, cpus, process_event_cpus, NULL)); - cpu_map__put(cpus); + perf_cpu_map__put(cpus); return 0; } static int cpu_map_print(const char *str) { - struct cpu_map *map = cpu_map__new(str); + struct perf_cpu_map *map = perf_cpu_map__new(str); char buf[100]; if (!map) diff --git a/tools/perf/tests/event-times.c b/tools/perf/tests/event-times.c index 1a2686f1fcf0..714e3611352c 100644 --- a/tools/perf/tests/event-times.c +++ b/tools/perf/tests/event-times.c @@ -4,6 +4,7 @@ #include <inttypes.h> #include <string.h> #include <sys/wait.h> +#include <perf/cpumap.h> #include "tests.h" #include "evlist.h" #include "evsel.h" @@ -12,9 +13,9 @@ #include "thread_map.h" #include "target.h" -static int attach__enable_on_exec(struct perf_evlist *evlist) +static int attach__enable_on_exec(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__last(evlist); + struct evsel *evsel = perf_evlist__last(evlist); struct target target = { .uid = UINT_MAX, }; @@ -36,9 +37,9 @@ static int attach__enable_on_exec(struct perf_evlist *evlist) return err; } - evsel->attr.enable_on_exec = 1; + evsel->core.attr.enable_on_exec = 1; - err = perf_evlist__open(evlist); + err = evlist__open(evlist); if (err < 0) { pr_debug("perf_evlist__open: %s\n", str_error_r(errno, sbuf, sizeof(sbuf))); @@ -48,16 +49,16 @@ static int attach__enable_on_exec(struct perf_evlist *evlist) return perf_evlist__start_workload(evlist) == 1 ? TEST_OK : TEST_FAIL; } -static int detach__enable_on_exec(struct perf_evlist *evlist) +static int detach__enable_on_exec(struct evlist *evlist) { waitpid(evlist->workload.pid, NULL, 0); return 0; } -static int attach__current_disabled(struct perf_evlist *evlist) +static int attach__current_disabled(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__last(evlist); - struct thread_map *threads; + struct evsel *evsel = perf_evlist__last(evlist); + struct perf_thread_map *threads; int err; pr_debug("attaching to current thread as disabled\n"); @@ -68,7 +69,7 @@ static int attach__current_disabled(struct perf_evlist *evlist) return -1; } - evsel->attr.disabled = 1; + evsel->core.attr.disabled = 1; err = perf_evsel__open_per_thread(evsel, threads); if (err) { @@ -76,14 +77,14 @@ static int attach__current_disabled(struct perf_evlist *evlist) return err; } - thread_map__put(threads); - return perf_evsel__enable(evsel) == 0 ? TEST_OK : TEST_FAIL; + perf_thread_map__put(threads); + return evsel__enable(evsel) == 0 ? TEST_OK : TEST_FAIL; } -static int attach__current_enabled(struct perf_evlist *evlist) +static int attach__current_enabled(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__last(evlist); - struct thread_map *threads; + struct evsel *evsel = perf_evlist__last(evlist); + struct perf_thread_map *threads; int err; pr_debug("attaching to current thread as enabled\n"); @@ -96,32 +97,32 @@ static int attach__current_enabled(struct perf_evlist *evlist) err = perf_evsel__open_per_thread(evsel, threads); - thread_map__put(threads); + perf_thread_map__put(threads); return err == 0 ? TEST_OK : TEST_FAIL; } -static int detach__disable(struct perf_evlist *evlist) +static int detach__disable(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__last(evlist); + struct evsel *evsel = perf_evlist__last(evlist); - return perf_evsel__enable(evsel); + return evsel__enable(evsel); } -static int attach__cpu_disabled(struct perf_evlist *evlist) +static int attach__cpu_disabled(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__last(evlist); - struct cpu_map *cpus; + struct evsel *evsel = perf_evlist__last(evlist); + struct perf_cpu_map *cpus; int err; pr_debug("attaching to CPU 0 as enabled\n"); - cpus = cpu_map__new("0"); + cpus = perf_cpu_map__new("0"); if (cpus == NULL) { - pr_debug("failed to call cpu_map__new\n"); + pr_debug("failed to call perf_cpu_map__new\n"); return -1; } - evsel->attr.disabled = 1; + evsel->core.attr.disabled = 1; err = perf_evsel__open_per_cpu(evsel, cpus); if (err) { @@ -132,21 +133,21 @@ static int attach__cpu_disabled(struct perf_evlist *evlist) return err; } - cpu_map__put(cpus); - return perf_evsel__enable(evsel); + perf_cpu_map__put(cpus); + return evsel__enable(evsel); } -static int attach__cpu_enabled(struct perf_evlist *evlist) +static int attach__cpu_enabled(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__last(evlist); - struct cpu_map *cpus; + struct evsel *evsel = perf_evlist__last(evlist); + struct perf_cpu_map *cpus; int err; pr_debug("attaching to CPU 0 as enabled\n"); - cpus = cpu_map__new("0"); + cpus = perf_cpu_map__new("0"); if (cpus == NULL) { - pr_debug("failed to call cpu_map__new\n"); + pr_debug("failed to call perf_cpu_map__new\n"); return -1; } @@ -154,19 +155,19 @@ static int attach__cpu_enabled(struct perf_evlist *evlist) if (err == -EACCES) return TEST_SKIP; - cpu_map__put(cpus); + perf_cpu_map__put(cpus); return err ? TEST_FAIL : TEST_OK; } -static int test_times(int (attach)(struct perf_evlist *), - int (detach)(struct perf_evlist *)) +static int test_times(int (attach)(struct evlist *), + int (detach)(struct evlist *)) { struct perf_counts_values count; - struct perf_evlist *evlist = NULL; - struct perf_evsel *evsel; + struct evlist *evlist = NULL; + struct evsel *evsel; int err = -1, i; - evlist = perf_evlist__new(); + evlist = evlist__new(); if (!evlist) { pr_debug("failed to create event list\n"); goto out_err; @@ -179,7 +180,7 @@ static int test_times(int (attach)(struct perf_evlist *), } evsel = perf_evlist__last(evlist); - evsel->attr.read_format |= + evsel->core.attr.read_format |= PERF_FORMAT_TOTAL_TIME_ENABLED | PERF_FORMAT_TOTAL_TIME_RUNNING; @@ -195,7 +196,7 @@ static int test_times(int (attach)(struct perf_evlist *), TEST_ASSERT_VAL("failed to detach", !detach(evlist)); - perf_evsel__read(evsel, 0, 0, &count); + perf_evsel__read(&evsel->core, 0, 0, &count); err = !(count.ena == count.run); @@ -204,7 +205,7 @@ static int test_times(int (attach)(struct perf_evlist *), count.ena, count.run); out_err: - perf_evlist__delete(evlist); + evlist__delete(evlist); return !err ? TEST_OK : TEST_FAIL; } diff --git a/tools/perf/tests/event_update.c b/tools/perf/tests/event_update.c index f14dcd613438..c37ff49c07c7 100644 --- a/tools/perf/tests/event_update.c +++ b/tools/perf/tests/event_update.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/compiler.h> +#include <perf/cpumap.h> #include "evlist.h" #include "evsel.h" #include "machine.h" @@ -61,7 +62,7 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused, { struct event_update_event *ev = (struct event_update_event*) event; struct event_update_event_cpus *ev_data; - struct cpu_map *map; + struct perf_cpu_map *map; ev_data = (struct event_update_event_cpus*) ev->data; @@ -73,14 +74,14 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused, TEST_ASSERT_VAL("wrong cpus", map->map[0] == 1); TEST_ASSERT_VAL("wrong cpus", map->map[1] == 2); TEST_ASSERT_VAL("wrong cpus", map->map[2] == 3); - cpu_map__put(map); + perf_cpu_map__put(map); return 0; } int test__event_update(struct test *test __maybe_unused, int subtest __maybe_unused) { - struct perf_evlist *evlist; - struct perf_evsel *evsel; + struct evlist *evlist; + struct evsel *evsel; struct event_name tmp; evlist = perf_evlist__new_default(); @@ -108,11 +109,11 @@ int test__event_update(struct test *test __maybe_unused, int subtest __maybe_unu TEST_ASSERT_VAL("failed to synthesize attr update name", !perf_event__synthesize_event_update_name(&tmp.tool, evsel, process_event_name)); - evsel->own_cpus = cpu_map__new("1,2,3"); + evsel->core.own_cpus = perf_cpu_map__new("1,2,3"); TEST_ASSERT_VAL("failed to synthesize attr update cpus", !perf_event__synthesize_event_update_cpus(&tmp.tool, evsel, process_event_cpus)); - cpu_map__put(evsel->own_cpus); + perf_cpu_map__put(evsel->core.own_cpus); return 0; } diff --git a/tools/perf/tests/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c index a104728ebf25..5330f106a6ee 100644 --- a/tools/perf/tests/evsel-roundtrip-name.c +++ b/tools/perf/tests/evsel-roundtrip-name.c @@ -11,8 +11,8 @@ static int perf_evsel__roundtrip_cache_name_test(void) { char name[128]; int type, op, err = 0, ret = 0, i, idx; - struct perf_evsel *evsel; - struct perf_evlist *evlist = perf_evlist__new(); + struct evsel *evsel; + struct evlist *evlist = evlist__new(); if (evlist == NULL) return -ENOMEM; @@ -60,15 +60,15 @@ static int perf_evsel__roundtrip_cache_name_test(void) } } - perf_evlist__delete(evlist); + evlist__delete(evlist); return ret; } static int __perf_evsel__name_array_test(const char *names[], int nr_names) { int i, err; - struct perf_evsel *evsel; - struct perf_evlist *evlist = perf_evlist__new(); + struct evsel *evsel; + struct evlist *evlist = evlist__new(); if (evlist == NULL) return -ENOMEM; @@ -91,7 +91,7 @@ static int __perf_evsel__name_array_test(const char *names[], int nr_names) } out_delete_evlist: - perf_evlist__delete(evlist); + evlist__delete(evlist); return err; } diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c index 71f60c0f9faa..261e6eaaee99 100644 --- a/tools/perf/tests/evsel-tp-sched.c +++ b/tools/perf/tests/evsel-tp-sched.c @@ -5,7 +5,7 @@ #include "tests.h" #include "debug.h" -static int perf_evsel__test_field(struct perf_evsel *evsel, const char *name, +static int perf_evsel__test_field(struct evsel *evsel, const char *name, int size, bool should_be_signed) { struct tep_format_field *field = perf_evsel__field(evsel, name); @@ -35,7 +35,7 @@ static int perf_evsel__test_field(struct perf_evsel *evsel, const char *name, int test__perf_evsel__tp_sched_test(struct test *test __maybe_unused, int subtest __maybe_unused) { - struct perf_evsel *evsel = perf_evsel__newtp("sched", "sched_switch"); + struct evsel *evsel = perf_evsel__newtp("sched", "sched_switch"); int ret = 0; if (IS_ERR(evsel)) { @@ -64,7 +64,7 @@ int test__perf_evsel__tp_sched_test(struct test *test __maybe_unused, int subtes if (perf_evsel__test_field(evsel, "next_prio", 4, true)) ret = -1; - perf_evsel__delete(evsel); + evsel__delete(evsel); evsel = perf_evsel__newtp("sched", "sched_wakeup"); @@ -85,6 +85,6 @@ int test__perf_evsel__tp_sched_test(struct test *test __maybe_unused, int subtes if (perf_evsel__test_field(evsel, "target_cpu", 4, true)) ret = -1; - perf_evsel__delete(evsel); + evsel__delete(evsel); return ret; } diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c index 7a2eed6c783e..1f3de85ae18b 100644 --- a/tools/perf/tests/hists_cumulate.c +++ b/tools/perf/tests/hists_cumulate.c @@ -80,7 +80,7 @@ static u64 fake_callchains[][10] = { static int add_hist_entries(struct hists *hists, struct machine *machine) { struct addr_location al; - struct perf_evsel *evsel = hists_to_evsel(hists); + struct evsel *evsel = hists_to_evsel(hists); struct perf_sample sample = { .period = 1000, }; size_t i; @@ -147,7 +147,7 @@ static void del_hist_entries(struct hists *hists) } } -typedef int (*test_fn_t)(struct perf_evsel *, struct machine *); +typedef int (*test_fn_t)(struct evsel *, struct machine *); #define COMM(he) (thread__comm_str(he->thread)) #define DSO(he) (he->ms.map->dso->short_name) @@ -247,7 +247,7 @@ static int do_test(struct hists *hists, struct result *expected, size_t nr_expec } /* NO callchain + NO children */ -static int test1(struct perf_evsel *evsel, struct machine *machine) +static int test1(struct evsel *evsel, struct machine *machine) { int err; struct hists *hists = evsel__hists(evsel); @@ -298,7 +298,7 @@ out: } /* callcain + NO children */ -static int test2(struct perf_evsel *evsel, struct machine *machine) +static int test2(struct evsel *evsel, struct machine *machine) { int err; struct hists *hists = evsel__hists(evsel); @@ -446,7 +446,7 @@ out: } /* NO callchain + children */ -static int test3(struct perf_evsel *evsel, struct machine *machine) +static int test3(struct evsel *evsel, struct machine *machine) { int err; struct hists *hists = evsel__hists(evsel); @@ -503,7 +503,7 @@ out: } /* callchain + children */ -static int test4(struct perf_evsel *evsel, struct machine *machine) +static int test4(struct evsel *evsel, struct machine *machine) { int err; struct hists *hists = evsel__hists(evsel); @@ -694,8 +694,8 @@ int test__hists_cumulate(struct test *test __maybe_unused, int subtest __maybe_u int err = TEST_FAIL; struct machines machines; struct machine *machine; - struct perf_evsel *evsel; - struct perf_evlist *evlist = perf_evlist__new(); + struct evsel *evsel; + struct evlist *evlist = evlist__new(); size_t i; test_fn_t testcases[] = { test1, @@ -731,7 +731,7 @@ int test__hists_cumulate(struct test *test __maybe_unused, int subtest __maybe_u out: /* tear down everything */ - perf_evlist__delete(evlist); + evlist__delete(evlist); machines__exit(&machines); return err; diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c index 975844807fe2..a274716fc438 100644 --- a/tools/perf/tests/hists_filter.c +++ b/tools/perf/tests/hists_filter.c @@ -47,10 +47,10 @@ static struct sample fake_samples[] = { { .pid = FAKE_PID_BASH, .ip = FAKE_IP_KERNEL_PAGE_FAULT, .socket = 3 }, }; -static int add_hist_entries(struct perf_evlist *evlist, +static int add_hist_entries(struct evlist *evlist, struct machine *machine) { - struct perf_evsel *evsel; + struct evsel *evsel; struct addr_location al; struct perf_sample sample = { .period = 100, }; size_t i; @@ -108,8 +108,8 @@ int test__hists_filter(struct test *test __maybe_unused, int subtest __maybe_unu int err = TEST_FAIL; struct machines machines; struct machine *machine; - struct perf_evsel *evsel; - struct perf_evlist *evlist = perf_evlist__new(); + struct evsel *evsel; + struct evlist *evlist = evlist__new(); TEST_ASSERT_VAL("No memory", evlist); @@ -321,7 +321,7 @@ int test__hists_filter(struct test *test __maybe_unused, int subtest __maybe_unu out: /* tear down everything */ - perf_evlist__delete(evlist); + evlist__delete(evlist); reset_output_field(); machines__exit(&machines); diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c index af633db63f4d..b25383aa2e6e 100644 --- a/tools/perf/tests/hists_link.c +++ b/tools/perf/tests/hists_link.c @@ -62,9 +62,9 @@ static struct sample fake_samples[][5] = { }, }; -static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine) +static int add_hist_entries(struct evlist *evlist, struct machine *machine) { - struct perf_evsel *evsel; + struct evsel *evsel; struct addr_location al; struct hist_entry *he; struct perf_sample sample = { .period = 1, .weight = 1, }; @@ -271,8 +271,8 @@ int test__hists_link(struct test *test __maybe_unused, int subtest __maybe_unuse struct hists *hists, *first_hists; struct machines machines; struct machine *machine = NULL; - struct perf_evsel *evsel, *first; - struct perf_evlist *evlist = perf_evlist__new(); + struct evsel *evsel, *first; + struct evlist *evlist = evlist__new(); if (evlist == NULL) return -ENOMEM; @@ -334,7 +334,7 @@ int test__hists_link(struct test *test __maybe_unused, int subtest __maybe_unuse out: /* tear down everything */ - perf_evlist__delete(evlist); + evlist__delete(evlist); reset_output_field(); machines__exit(&machines); diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c index 0a510c524a5d..009888adf4b3 100644 --- a/tools/perf/tests/hists_output.c +++ b/tools/perf/tests/hists_output.c @@ -50,7 +50,7 @@ static struct sample fake_samples[] = { static int add_hist_entries(struct hists *hists, struct machine *machine) { struct addr_location al; - struct perf_evsel *evsel = hists_to_evsel(hists); + struct evsel *evsel = hists_to_evsel(hists); struct perf_sample sample = { .period = 100, }; size_t i; @@ -113,7 +113,7 @@ static void del_hist_entries(struct hists *hists) } } -typedef int (*test_fn_t)(struct perf_evsel *, struct machine *); +typedef int (*test_fn_t)(struct evsel *, struct machine *); #define COMM(he) (thread__comm_str(he->thread)) #define DSO(he) (he->ms.map->dso->short_name) @@ -122,7 +122,7 @@ typedef int (*test_fn_t)(struct perf_evsel *, struct machine *); #define PID(he) (he->thread->tid) /* default sort keys (no field) */ -static int test1(struct perf_evsel *evsel, struct machine *machine) +static int test1(struct evsel *evsel, struct machine *machine) { int err; struct hists *hists = evsel__hists(evsel); @@ -224,7 +224,7 @@ out: } /* mixed fields and sort keys */ -static int test2(struct perf_evsel *evsel, struct machine *machine) +static int test2(struct evsel *evsel, struct machine *machine) { int err; struct hists *hists = evsel__hists(evsel); @@ -280,7 +280,7 @@ out: } /* fields only (no sort key) */ -static int test3(struct perf_evsel *evsel, struct machine *machine) +static int test3(struct evsel *evsel, struct machine *machine) { int err; struct hists *hists = evsel__hists(evsel); @@ -354,7 +354,7 @@ out: } /* handle duplicate 'dso' field */ -static int test4(struct perf_evsel *evsel, struct machine *machine) +static int test4(struct evsel *evsel, struct machine *machine) { int err; struct hists *hists = evsel__hists(evsel); @@ -456,7 +456,7 @@ out: } /* full sort keys w/o overhead field */ -static int test5(struct perf_evsel *evsel, struct machine *machine) +static int test5(struct evsel *evsel, struct machine *machine) { int err; struct hists *hists = evsel__hists(evsel); @@ -580,8 +580,8 @@ int test__hists_output(struct test *test __maybe_unused, int subtest __maybe_unu int err = TEST_FAIL; struct machines machines; struct machine *machine; - struct perf_evsel *evsel; - struct perf_evlist *evlist = perf_evlist__new(); + struct evsel *evsel; + struct evlist *evlist = evlist__new(); size_t i; test_fn_t testcases[] = { test1, @@ -618,7 +618,7 @@ int test__hists_output(struct test *test __maybe_unused, int subtest __maybe_unu out: /* tear down everything */ - perf_evlist__delete(evlist); + evlist__delete(evlist); machines__exit(&machines); return err; diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c index 17c46f3e6f1e..0ce5ce33bac4 100644 --- a/tools/perf/tests/keep-tracking.c +++ b/tools/perf/tests/keep-tracking.c @@ -2,6 +2,8 @@ #include <linux/types.h> #include <unistd.h> #include <sys/prctl.h> +#include <perf/cpumap.h> +#include <perf/evlist.h> #include "parse-events.h" #include "evlist.h" @@ -24,7 +26,7 @@ } \ } -static int find_comm(struct perf_evlist *evlist, const char *comm) +static int find_comm(struct evlist *evlist, const char *comm) { union perf_event *event; struct perf_mmap *md; @@ -65,23 +67,23 @@ int test__keep_tracking(struct test *test __maybe_unused, int subtest __maybe_un .uses_mmap = true, }, }; - struct thread_map *threads = NULL; - struct cpu_map *cpus = NULL; - struct perf_evlist *evlist = NULL; - struct perf_evsel *evsel = NULL; + struct perf_thread_map *threads = NULL; + struct perf_cpu_map *cpus = NULL; + struct evlist *evlist = NULL; + struct evsel *evsel = NULL; int found, err = -1; const char *comm; threads = thread_map__new(-1, getpid(), UINT_MAX); CHECK_NOT_NULL__(threads); - cpus = cpu_map__new(NULL); + cpus = perf_cpu_map__new(NULL); CHECK_NOT_NULL__(cpus); - evlist = perf_evlist__new(); + evlist = evlist__new(); CHECK_NOT_NULL__(evlist); - perf_evlist__set_maps(evlist, cpus, threads); + perf_evlist__set_maps(&evlist->core, cpus, threads); CHECK__(parse_events(evlist, "dummy:u", NULL)); CHECK__(parse_events(evlist, "cycles:u", NULL)); @@ -90,11 +92,11 @@ int test__keep_tracking(struct test *test __maybe_unused, int subtest __maybe_un evsel = perf_evlist__first(evlist); - evsel->attr.comm = 1; - evsel->attr.disabled = 1; - evsel->attr.enable_on_exec = 0; + evsel->core.attr.comm = 1; + evsel->core.attr.disabled = 1; + evsel->core.attr.enable_on_exec = 0; - if (perf_evlist__open(evlist) < 0) { + if (evlist__open(evlist) < 0) { pr_debug("Unable to open dummy and cycles event\n"); err = TEST_SKIP; goto out_err; @@ -107,12 +109,12 @@ int test__keep_tracking(struct test *test __maybe_unused, int subtest __maybe_un * enabled. */ - perf_evlist__enable(evlist); + evlist__enable(evlist); comm = "Test COMM 1"; CHECK__(prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0)); - perf_evlist__disable(evlist); + evlist__disable(evlist); found = find_comm(evlist, comm); if (found != 1) { @@ -125,16 +127,16 @@ int test__keep_tracking(struct test *test __maybe_unused, int subtest __maybe_un * disabled with the dummy event still enabled. */ - perf_evlist__enable(evlist); + evlist__enable(evlist); evsel = perf_evlist__last(evlist); - CHECK__(perf_evsel__disable(evsel)); + CHECK__(evsel__disable(evsel)); comm = "Test COMM 2"; CHECK__(prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0)); - perf_evlist__disable(evlist); + evlist__disable(evlist); found = find_comm(evlist, comm); if (found != 1) { @@ -146,11 +148,11 @@ int test__keep_tracking(struct test *test __maybe_unused, int subtest __maybe_un out_err: if (evlist) { - perf_evlist__disable(evlist); - perf_evlist__delete(evlist); + evlist__disable(evlist); + evlist__delete(evlist); } else { - cpu_map__put(cpus); - thread_map__put(threads); + perf_cpu_map__put(cpus); + perf_thread_map__put(threads); } return err; diff --git a/tools/perf/tests/make b/tools/perf/tests/make index 5363a12a8b9b..70c48475896d 100644 --- a/tools/perf/tests/make +++ b/tools/perf/tests/make @@ -108,6 +108,7 @@ make_minimal += NO_DEMANGLE=1 NO_LIBELF=1 NO_LIBUNWIND=1 NO_BACKTRACE=1 make_minimal += NO_LIBNUMA=1 NO_LIBAUDIT=1 NO_LIBBIONIC=1 make_minimal += NO_LIBDW_DWARF_UNWIND=1 NO_AUXTRACE=1 NO_LIBBPF=1 make_minimal += NO_LIBCRYPTO=1 NO_SDT=1 NO_JVMTI=1 NO_LIBZSTD=1 +make_minimal += NO_LIBCAP=1 # $(run) contains all available tests run := make_pure diff --git a/tools/perf/tests/mem2node.c b/tools/perf/tests/mem2node.c index 520cc91af256..73b2855acaf4 100644 --- a/tools/perf/tests/mem2node.c +++ b/tools/perf/tests/mem2node.c @@ -2,7 +2,9 @@ #include <linux/compiler.h> #include <linux/bitmap.h> #include <linux/zalloc.h> +#include <perf/cpumap.h> #include "cpumap.h" +#include "debug.h" #include "mem2node.h" #include "tests.h" @@ -19,7 +21,7 @@ static struct node { static unsigned long *get_bitmap(const char *str, int nbits) { - struct cpu_map *map = cpu_map__new(str); + struct perf_cpu_map *map = perf_cpu_map__new(str); unsigned long *bm = NULL; int i; @@ -32,7 +34,7 @@ static unsigned long *get_bitmap(const char *str, int nbits) } if (map) - cpu_map__put(map); + perf_cpu_map__put(map); else free(bm); diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c index 0919b0793e5b..7327694fbde0 100644 --- a/tools/perf/tests/mmap-basic.c +++ b/tools/perf/tests/mmap-basic.c @@ -3,6 +3,7 @@ #include <inttypes.h> /* For the CLR_() macros */ #include <pthread.h> +#include <perf/cpumap.h> #include "evlist.h" #include "evsel.h" @@ -11,6 +12,7 @@ #include "tests.h" #include <linux/err.h> #include <linux/kernel.h> +#include <perf/evlist.h> /* * This test will generate random numbers of calls to some getpid syscalls, @@ -27,16 +29,16 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse { int err = -1; union perf_event *event; - struct thread_map *threads; - struct cpu_map *cpus; - struct perf_evlist *evlist; + struct perf_thread_map *threads; + struct perf_cpu_map *cpus; + struct evlist *evlist; cpu_set_t cpu_set; const char *syscall_names[] = { "getsid", "getppid", "getpgid", }; pid_t (*syscalls[])(void) = { (void *)getsid, getppid, (void*)getpgid }; #define nsyscalls ARRAY_SIZE(syscall_names) unsigned int nr_events[nsyscalls], expected_nr_events[nsyscalls], i, j; - struct perf_evsel *evsels[nsyscalls], *evsel; + struct evsel *evsels[nsyscalls], *evsel; char sbuf[STRERR_BUFSIZE]; struct perf_mmap *md; @@ -46,7 +48,7 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse return -1; } - cpus = cpu_map__new(NULL); + cpus = perf_cpu_map__new(NULL); if (cpus == NULL) { pr_debug("cpu_map__new\n"); goto out_free_threads; @@ -61,13 +63,13 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse goto out_free_cpus; } - evlist = perf_evlist__new(); + evlist = evlist__new(); if (evlist == NULL) { pr_debug("perf_evlist__new\n"); goto out_free_cpus; } - perf_evlist__set_maps(evlist, cpus, threads); + perf_evlist__set_maps(&evlist->core, cpus, threads); for (i = 0; i < nsyscalls; ++i) { char name[64]; @@ -79,12 +81,12 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse goto out_delete_evlist; } - evsels[i]->attr.wakeup_events = 1; + evsels[i]->core.attr.wakeup_events = 1; perf_evsel__set_sample_id(evsels[i], false); - perf_evlist__add(evlist, evsels[i]); + evlist__add(evlist, evsels[i]); - if (perf_evsel__open(evsels[i], cpus, threads) < 0) { + if (evsel__open(evsels[i], cpus, threads) < 0) { pr_debug("failed to open counter: %s, " "tweak /proc/sys/kernel/perf_event_paranoid?\n", str_error_r(errno, sbuf, sizeof(sbuf))); @@ -151,12 +153,12 @@ out_init: } out_delete_evlist: - perf_evlist__delete(evlist); + evlist__delete(evlist); cpus = NULL; threads = NULL; out_free_cpus: - cpu_map__put(cpus); + perf_cpu_map__put(cpus); out_free_threads: - thread_map__put(threads); + perf_thread_map__put(threads); return err; } diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c index 0a4301a5155c..360d70deb855 100644 --- a/tools/perf/tests/mmap-thread-lookup.c +++ b/tools/perf/tests/mmap-thread-lookup.c @@ -138,7 +138,7 @@ static int synth_all(struct machine *machine) static int synth_process(struct machine *machine) { - struct thread_map *map; + struct perf_thread_map *map; int err; map = thread_map__new_by_pid(getpid()); @@ -147,7 +147,7 @@ static int synth_process(struct machine *machine) perf_event__process, machine, 0); - thread_map__put(map); + perf_thread_map__put(map); return err; } diff --git a/tools/perf/tests/openat-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c index 493ecb611540..4ae4dea07466 100644 --- a/tools/perf/tests/openat-syscall-all-cpus.c +++ b/tools/perf/tests/openat-syscall-all-cpus.c @@ -16,15 +16,16 @@ #include "cpumap.h" #include "debug.h" #include "stat.h" +#include "util/counts.h" int test__openat_syscall_event_on_all_cpus(struct test *test __maybe_unused, int subtest __maybe_unused) { int err = -1, fd, cpu; - struct cpu_map *cpus; - struct perf_evsel *evsel; + struct perf_cpu_map *cpus; + struct evsel *evsel; unsigned int nr_openat_calls = 111, i; cpu_set_t cpu_set; - struct thread_map *threads = thread_map__new(-1, getpid(), UINT_MAX); + struct perf_thread_map *threads = thread_map__new(-1, getpid(), UINT_MAX); char sbuf[STRERR_BUFSIZE]; char errbuf[BUFSIZ]; @@ -33,7 +34,7 @@ int test__openat_syscall_event_on_all_cpus(struct test *test __maybe_unused, int return -1; } - cpus = cpu_map__new(NULL); + cpus = perf_cpu_map__new(NULL); if (cpus == NULL) { pr_debug("cpu_map__new\n"); goto out_thread_map_delete; @@ -48,7 +49,7 @@ int test__openat_syscall_event_on_all_cpus(struct test *test __maybe_unused, int goto out_cpu_map_delete; } - if (perf_evsel__open(evsel, cpus, threads) < 0) { + if (evsel__open(evsel, cpus, threads) < 0) { pr_debug("failed to open counter: %s, " "tweak /proc/sys/kernel/perf_event_paranoid?\n", str_error_r(errno, sbuf, sizeof(sbuf))); @@ -116,12 +117,12 @@ int test__openat_syscall_event_on_all_cpus(struct test *test __maybe_unused, int perf_evsel__free_counts(evsel); out_close_fd: - perf_evsel__close_fd(evsel); + perf_evsel__close_fd(&evsel->core); out_evsel_delete: - perf_evsel__delete(evsel); + evsel__delete(evsel); out_cpu_map_delete: - cpu_map__put(cpus); + perf_cpu_map__put(cpus); out_thread_map_delete: - thread_map__put(threads); + perf_thread_map__put(threads); return err; } diff --git a/tools/perf/tests/openat-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c index 344dc3ac2469..9c06130d37be 100644 --- a/tools/perf/tests/openat-syscall-tp-fields.c +++ b/tools/perf/tests/openat-syscall-tp-fields.c @@ -32,8 +32,8 @@ int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest }; const char *filename = "/etc/passwd"; int flags = O_RDONLY | O_DIRECTORY; - struct perf_evlist *evlist = perf_evlist__new(); - struct perf_evsel *evsel; + struct evlist *evlist = evlist__new(); + struct evsel *evsel; int err = -1, i, nr_events = 0, nr_polls = 0; char sbuf[STRERR_BUFSIZE]; @@ -48,7 +48,7 @@ int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest goto out_delete_evlist; } - perf_evlist__add(evlist, evsel); + evlist__add(evlist, evsel); err = perf_evlist__create_maps(evlist, &opts.target); if (err < 0) { @@ -58,9 +58,9 @@ int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest perf_evsel__config(evsel, &opts, NULL); - thread_map__set_pid(evlist->threads, 0, getpid()); + perf_thread_map__set_pid(evlist->core.threads, 0, getpid()); - err = perf_evlist__open(evlist); + err = evlist__open(evlist); if (err < 0) { pr_debug("perf_evlist__open: %s\n", str_error_r(errno, sbuf, sizeof(sbuf))); @@ -74,7 +74,7 @@ int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest goto out_delete_evlist; } - perf_evlist__enable(evlist); + evlist__enable(evlist); /* * Generate the event: @@ -134,7 +134,7 @@ int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest out_ok: err = 0; out_delete_evlist: - perf_evlist__delete(evlist); + evlist__delete(evlist); out: return err; } diff --git a/tools/perf/tests/openat-syscall.c b/tools/perf/tests/openat-syscall.c index 00cd63f90b92..58df4bda5e12 100644 --- a/tools/perf/tests/openat-syscall.c +++ b/tools/perf/tests/openat-syscall.c @@ -10,13 +10,14 @@ #include "evsel.h" #include "debug.h" #include "tests.h" +#include "util/counts.h" int test__openat_syscall_event(struct test *test __maybe_unused, int subtest __maybe_unused) { int err = -1, fd; - struct perf_evsel *evsel; + struct evsel *evsel; unsigned int nr_openat_calls = 111, i; - struct thread_map *threads = thread_map__new(-1, getpid(), UINT_MAX); + struct perf_thread_map *threads = thread_map__new(-1, getpid(), UINT_MAX); char sbuf[STRERR_BUFSIZE]; char errbuf[BUFSIZ]; @@ -57,10 +58,10 @@ int test__openat_syscall_event(struct test *test __maybe_unused, int subtest __m err = 0; out_close_fd: - perf_evsel__close_fd(evsel); + perf_evsel__close_fd(&evsel->core); out_evsel_delete: - perf_evsel__delete(evsel); + evsel__delete(evsel); out_thread_map_delete: - thread_map__put(threads); + perf_thread_map__put(threads); return err; } diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index 8f3c80e13584..49f52e4de41b 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -44,549 +44,549 @@ static bool kvm_s390_create_vm_valid(void) } #endif -static int test__checkevent_tracepoint(struct perf_evlist *evlist) +static int test__checkevent_tracepoint(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong number of groups", 0 == evlist->nr_groups); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_TRACEPOINT == evsel->attr.type); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_TRACEPOINT == evsel->core.attr.type); TEST_ASSERT_VAL("wrong sample_type", - PERF_TP_SAMPLE_TYPE == evsel->attr.sample_type); - TEST_ASSERT_VAL("wrong sample_period", 1 == evsel->attr.sample_period); + PERF_TP_SAMPLE_TYPE == evsel->core.attr.sample_type); + TEST_ASSERT_VAL("wrong sample_period", 1 == evsel->core.attr.sample_period); return 0; } -static int test__checkevent_tracepoint_multi(struct perf_evlist *evlist) +static int test__checkevent_tracepoint_multi(struct evlist *evlist) { - struct perf_evsel *evsel; + struct evsel *evsel; - TEST_ASSERT_VAL("wrong number of entries", evlist->nr_entries > 1); + TEST_ASSERT_VAL("wrong number of entries", evlist->core.nr_entries > 1); TEST_ASSERT_VAL("wrong number of groups", 0 == evlist->nr_groups); evlist__for_each_entry(evlist, evsel) { TEST_ASSERT_VAL("wrong type", - PERF_TYPE_TRACEPOINT == evsel->attr.type); + PERF_TYPE_TRACEPOINT == evsel->core.attr.type); TEST_ASSERT_VAL("wrong sample_type", - PERF_TP_SAMPLE_TYPE == evsel->attr.sample_type); + PERF_TP_SAMPLE_TYPE == evsel->core.attr.sample_type); TEST_ASSERT_VAL("wrong sample_period", - 1 == evsel->attr.sample_period); + 1 == evsel->core.attr.sample_period); } return 0; } -static int test__checkevent_raw(struct perf_evlist *evlist) +static int test__checkevent_raw(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type); - TEST_ASSERT_VAL("wrong config", 0x1a == evsel->attr.config); + TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type); + TEST_ASSERT_VAL("wrong config", 0x1a == evsel->core.attr.config); return 0; } -static int test__checkevent_numeric(struct perf_evlist *evlist) +static int test__checkevent_numeric(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries); - TEST_ASSERT_VAL("wrong type", 1 == evsel->attr.type); - TEST_ASSERT_VAL("wrong config", 1 == evsel->attr.config); + TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); + TEST_ASSERT_VAL("wrong type", 1 == evsel->core.attr.type); + TEST_ASSERT_VAL("wrong config", 1 == evsel->core.attr.config); return 0; } -static int test__checkevent_symbolic_name(struct perf_evlist *evlist) +static int test__checkevent_symbolic_name(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_INSTRUCTIONS == evsel->attr.config); + PERF_COUNT_HW_INSTRUCTIONS == evsel->core.attr.config); return 0; } -static int test__checkevent_symbolic_name_config(struct perf_evlist *evlist) +static int test__checkevent_symbolic_name_config(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config); + PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config); /* * The period value gets configured within perf_evlist__config, * while this test executes only parse events method. */ TEST_ASSERT_VAL("wrong period", - 0 == evsel->attr.sample_period); + 0 == evsel->core.attr.sample_period); TEST_ASSERT_VAL("wrong config1", - 0 == evsel->attr.config1); + 0 == evsel->core.attr.config1); TEST_ASSERT_VAL("wrong config2", - 1 == evsel->attr.config2); + 1 == evsel->core.attr.config2); return 0; } -static int test__checkevent_symbolic_alias(struct perf_evlist *evlist) +static int test__checkevent_symbolic_alias(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_SOFTWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_SOFTWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", - PERF_COUNT_SW_PAGE_FAULTS == evsel->attr.config); + PERF_COUNT_SW_PAGE_FAULTS == evsel->core.attr.config); return 0; } -static int test__checkevent_genhw(struct perf_evlist *evlist) +static int test__checkevent_genhw(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HW_CACHE == evsel->attr.type); - TEST_ASSERT_VAL("wrong config", (1 << 16) == evsel->attr.config); + TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HW_CACHE == evsel->core.attr.type); + TEST_ASSERT_VAL("wrong config", (1 << 16) == evsel->core.attr.config); return 0; } -static int test__checkevent_breakpoint(struct perf_evlist *evlist) +static int test__checkevent_breakpoint(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_BREAKPOINT == evsel->attr.type); - TEST_ASSERT_VAL("wrong config", 0 == evsel->attr.config); + TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_BREAKPOINT == evsel->core.attr.type); + TEST_ASSERT_VAL("wrong config", 0 == evsel->core.attr.config); TEST_ASSERT_VAL("wrong bp_type", (HW_BREAKPOINT_R | HW_BREAKPOINT_W) == - evsel->attr.bp_type); + evsel->core.attr.bp_type); TEST_ASSERT_VAL("wrong bp_len", HW_BREAKPOINT_LEN_4 == - evsel->attr.bp_len); + evsel->core.attr.bp_len); return 0; } -static int test__checkevent_breakpoint_x(struct perf_evlist *evlist) +static int test__checkevent_breakpoint_x(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_BREAKPOINT == evsel->attr.type); - TEST_ASSERT_VAL("wrong config", 0 == evsel->attr.config); + TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_BREAKPOINT == evsel->core.attr.type); + TEST_ASSERT_VAL("wrong config", 0 == evsel->core.attr.config); TEST_ASSERT_VAL("wrong bp_type", - HW_BREAKPOINT_X == evsel->attr.bp_type); - TEST_ASSERT_VAL("wrong bp_len", sizeof(long) == evsel->attr.bp_len); + HW_BREAKPOINT_X == evsel->core.attr.bp_type); + TEST_ASSERT_VAL("wrong bp_len", sizeof(long) == evsel->core.attr.bp_len); return 0; } -static int test__checkevent_breakpoint_r(struct perf_evlist *evlist) +static int test__checkevent_breakpoint_r(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong type", - PERF_TYPE_BREAKPOINT == evsel->attr.type); - TEST_ASSERT_VAL("wrong config", 0 == evsel->attr.config); + PERF_TYPE_BREAKPOINT == evsel->core.attr.type); + TEST_ASSERT_VAL("wrong config", 0 == evsel->core.attr.config); TEST_ASSERT_VAL("wrong bp_type", - HW_BREAKPOINT_R == evsel->attr.bp_type); + HW_BREAKPOINT_R == evsel->core.attr.bp_type); TEST_ASSERT_VAL("wrong bp_len", - HW_BREAKPOINT_LEN_4 == evsel->attr.bp_len); + HW_BREAKPOINT_LEN_4 == evsel->core.attr.bp_len); return 0; } -static int test__checkevent_breakpoint_w(struct perf_evlist *evlist) +static int test__checkevent_breakpoint_w(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong type", - PERF_TYPE_BREAKPOINT == evsel->attr.type); - TEST_ASSERT_VAL("wrong config", 0 == evsel->attr.config); + PERF_TYPE_BREAKPOINT == evsel->core.attr.type); + TEST_ASSERT_VAL("wrong config", 0 == evsel->core.attr.config); TEST_ASSERT_VAL("wrong bp_type", - HW_BREAKPOINT_W == evsel->attr.bp_type); + HW_BREAKPOINT_W == evsel->core.attr.bp_type); TEST_ASSERT_VAL("wrong bp_len", - HW_BREAKPOINT_LEN_4 == evsel->attr.bp_len); + HW_BREAKPOINT_LEN_4 == evsel->core.attr.bp_len); return 0; } -static int test__checkevent_breakpoint_rw(struct perf_evlist *evlist) +static int test__checkevent_breakpoint_rw(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong type", - PERF_TYPE_BREAKPOINT == evsel->attr.type); - TEST_ASSERT_VAL("wrong config", 0 == evsel->attr.config); + PERF_TYPE_BREAKPOINT == evsel->core.attr.type); + TEST_ASSERT_VAL("wrong config", 0 == evsel->core.attr.config); TEST_ASSERT_VAL("wrong bp_type", - (HW_BREAKPOINT_R|HW_BREAKPOINT_W) == evsel->attr.bp_type); + (HW_BREAKPOINT_R|HW_BREAKPOINT_W) == evsel->core.attr.bp_type); TEST_ASSERT_VAL("wrong bp_len", - HW_BREAKPOINT_LEN_4 == evsel->attr.bp_len); + HW_BREAKPOINT_LEN_4 == evsel->core.attr.bp_len); return 0; } -static int test__checkevent_tracepoint_modifier(struct perf_evlist *evlist) +static int test__checkevent_tracepoint_modifier(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); return test__checkevent_tracepoint(evlist); } static int -test__checkevent_tracepoint_multi_modifier(struct perf_evlist *evlist) +test__checkevent_tracepoint_multi_modifier(struct evlist *evlist) { - struct perf_evsel *evsel; + struct evsel *evsel; - TEST_ASSERT_VAL("wrong number of entries", evlist->nr_entries > 1); + TEST_ASSERT_VAL("wrong number of entries", evlist->core.nr_entries > 1); evlist__for_each_entry(evlist, evsel) { TEST_ASSERT_VAL("wrong exclude_user", - !evsel->attr.exclude_user); + !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", - evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); } return test__checkevent_tracepoint_multi(evlist); } -static int test__checkevent_raw_modifier(struct perf_evlist *evlist) +static int test__checkevent_raw_modifier(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong precise_ip", evsel->core.attr.precise_ip); return test__checkevent_raw(evlist); } -static int test__checkevent_numeric_modifier(struct perf_evlist *evlist) +static int test__checkevent_numeric_modifier(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong precise_ip", evsel->core.attr.precise_ip); return test__checkevent_numeric(evlist); } -static int test__checkevent_symbolic_name_modifier(struct perf_evlist *evlist) +static int test__checkevent_symbolic_name_modifier(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); return test__checkevent_symbolic_name(evlist); } -static int test__checkevent_exclude_host_modifier(struct perf_evlist *evlist) +static int test__checkevent_exclude_host_modifier(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); - TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", evsel->core.attr.exclude_host); return test__checkevent_symbolic_name(evlist); } -static int test__checkevent_exclude_guest_modifier(struct perf_evlist *evlist) +static int test__checkevent_exclude_guest_modifier(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest); - TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); + TEST_ASSERT_VAL("wrong exclude guest", evsel->core.attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host); return test__checkevent_symbolic_name(evlist); } -static int test__checkevent_symbolic_alias_modifier(struct perf_evlist *evlist) +static int test__checkevent_symbolic_alias_modifier(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); return test__checkevent_symbolic_alias(evlist); } -static int test__checkevent_genhw_modifier(struct perf_evlist *evlist) +static int test__checkevent_genhw_modifier(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong precise_ip", evsel->core.attr.precise_ip); return test__checkevent_genhw(evlist); } -static int test__checkevent_exclude_idle_modifier(struct perf_evlist *evlist) +static int test__checkevent_exclude_idle_modifier(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong exclude idle", evsel->attr.exclude_idle); - TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); - TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); - TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong exclude idle", evsel->core.attr.exclude_idle); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); return test__checkevent_symbolic_name(evlist); } -static int test__checkevent_exclude_idle_modifier_1(struct perf_evlist *evlist) +static int test__checkevent_exclude_idle_modifier_1(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong exclude idle", evsel->attr.exclude_idle); - TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); - TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host); - TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong exclude idle", evsel->core.attr.exclude_idle); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", evsel->core.attr.exclude_host); + TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); return test__checkevent_symbolic_name(evlist); } -static int test__checkevent_breakpoint_modifier(struct perf_evlist *evlist) +static int test__checkevent_breakpoint_modifier(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); TEST_ASSERT_VAL("wrong name", !strcmp(perf_evsel__name(evsel), "mem:0:u")); return test__checkevent_breakpoint(evlist); } -static int test__checkevent_breakpoint_x_modifier(struct perf_evlist *evlist) +static int test__checkevent_breakpoint_x_modifier(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); TEST_ASSERT_VAL("wrong name", !strcmp(perf_evsel__name(evsel), "mem:0:x:k")); return test__checkevent_breakpoint_x(evlist); } -static int test__checkevent_breakpoint_r_modifier(struct perf_evlist *evlist) +static int test__checkevent_breakpoint_r_modifier(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong precise_ip", evsel->core.attr.precise_ip); TEST_ASSERT_VAL("wrong name", !strcmp(perf_evsel__name(evsel), "mem:0:r:hp")); return test__checkevent_breakpoint_r(evlist); } -static int test__checkevent_breakpoint_w_modifier(struct perf_evlist *evlist) +static int test__checkevent_breakpoint_w_modifier(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong precise_ip", evsel->core.attr.precise_ip); TEST_ASSERT_VAL("wrong name", !strcmp(perf_evsel__name(evsel), "mem:0:w:up")); return test__checkevent_breakpoint_w(evlist); } -static int test__checkevent_breakpoint_rw_modifier(struct perf_evlist *evlist) +static int test__checkevent_breakpoint_rw_modifier(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong precise_ip", evsel->core.attr.precise_ip); TEST_ASSERT_VAL("wrong name", !strcmp(perf_evsel__name(evsel), "mem:0:rw:kp")); return test__checkevent_breakpoint_rw(evlist); } -static int test__checkevent_pmu(struct perf_evlist *evlist) +static int test__checkevent_pmu(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type); - TEST_ASSERT_VAL("wrong config", 10 == evsel->attr.config); - TEST_ASSERT_VAL("wrong config1", 1 == evsel->attr.config1); - TEST_ASSERT_VAL("wrong config2", 3 == evsel->attr.config2); + TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type); + TEST_ASSERT_VAL("wrong config", 10 == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config1", 1 == evsel->core.attr.config1); + TEST_ASSERT_VAL("wrong config2", 3 == evsel->core.attr.config2); /* * The period value gets configured within perf_evlist__config, * while this test executes only parse events method. */ - TEST_ASSERT_VAL("wrong period", 0 == evsel->attr.sample_period); + TEST_ASSERT_VAL("wrong period", 0 == evsel->core.attr.sample_period); return 0; } -static int test__checkevent_list(struct perf_evlist *evlist) +static int test__checkevent_list(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong number of entries", 3 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong number of entries", 3 == evlist->core.nr_entries); /* r1 */ - TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type); - TEST_ASSERT_VAL("wrong config", 1 == evsel->attr.config); - TEST_ASSERT_VAL("wrong config1", 0 == evsel->attr.config1); - TEST_ASSERT_VAL("wrong config2", 0 == evsel->attr.config2); - TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type); + TEST_ASSERT_VAL("wrong config", 1 == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config1", 0 == evsel->core.attr.config1); + TEST_ASSERT_VAL("wrong config2", 0 == evsel->core.attr.config2); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); /* syscalls:sys_enter_openat:k */ evsel = perf_evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_TRACEPOINT == evsel->attr.type); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_TRACEPOINT == evsel->core.attr.type); TEST_ASSERT_VAL("wrong sample_type", - PERF_TP_SAMPLE_TYPE == evsel->attr.sample_type); - TEST_ASSERT_VAL("wrong sample_period", 1 == evsel->attr.sample_period); - TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + PERF_TP_SAMPLE_TYPE == evsel->core.attr.sample_type); + TEST_ASSERT_VAL("wrong sample_period", 1 == evsel->core.attr.sample_period); + TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); /* 1:1:hp */ evsel = perf_evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", 1 == evsel->attr.type); - TEST_ASSERT_VAL("wrong config", 1 == evsel->attr.config); - TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong type", 1 == evsel->core.attr.type); + TEST_ASSERT_VAL("wrong config", 1 == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong precise_ip", evsel->core.attr.precise_ip); return 0; } -static int test__checkevent_pmu_name(struct perf_evlist *evlist) +static int test__checkevent_pmu_name(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); /* cpu/config=1,name=krava/u */ - TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type); - TEST_ASSERT_VAL("wrong config", 1 == evsel->attr.config); + TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type); + TEST_ASSERT_VAL("wrong config", 1 == evsel->core.attr.config); TEST_ASSERT_VAL("wrong name", !strcmp(perf_evsel__name(evsel), "krava")); /* cpu/config=2/u" */ evsel = perf_evsel__next(evsel); - TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type); - TEST_ASSERT_VAL("wrong config", 2 == evsel->attr.config); + TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type); + TEST_ASSERT_VAL("wrong config", 2 == evsel->core.attr.config); TEST_ASSERT_VAL("wrong name", !strcmp(perf_evsel__name(evsel), "cpu/config=2/u")); return 0; } -static int test__checkevent_pmu_partial_time_callgraph(struct perf_evlist *evlist) +static int test__checkevent_pmu_partial_time_callgraph(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); /* cpu/config=1,call-graph=fp,time,period=100000/ */ - TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type); - TEST_ASSERT_VAL("wrong config", 1 == evsel->attr.config); + TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type); + TEST_ASSERT_VAL("wrong config", 1 == evsel->core.attr.config); /* * The period, time and callgraph value gets configured * within perf_evlist__config, * while this test executes only parse events method. */ - TEST_ASSERT_VAL("wrong period", 0 == evsel->attr.sample_period); + TEST_ASSERT_VAL("wrong period", 0 == evsel->core.attr.sample_period); TEST_ASSERT_VAL("wrong callgraph", !evsel__has_callchain(evsel)); - TEST_ASSERT_VAL("wrong time", !(PERF_SAMPLE_TIME & evsel->attr.sample_type)); + TEST_ASSERT_VAL("wrong time", !(PERF_SAMPLE_TIME & evsel->core.attr.sample_type)); /* cpu/config=2,call-graph=no,time=0,period=2000/ */ evsel = perf_evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type); - TEST_ASSERT_VAL("wrong config", 2 == evsel->attr.config); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type); + TEST_ASSERT_VAL("wrong config", 2 == evsel->core.attr.config); /* * The period, time and callgraph value gets configured * within perf_evlist__config, * while this test executes only parse events method. */ - TEST_ASSERT_VAL("wrong period", 0 == evsel->attr.sample_period); + TEST_ASSERT_VAL("wrong period", 0 == evsel->core.attr.sample_period); TEST_ASSERT_VAL("wrong callgraph", !evsel__has_callchain(evsel)); - TEST_ASSERT_VAL("wrong time", !(PERF_SAMPLE_TIME & evsel->attr.sample_type)); + TEST_ASSERT_VAL("wrong time", !(PERF_SAMPLE_TIME & evsel->core.attr.sample_type)); return 0; } -static int test__checkevent_pmu_events(struct perf_evlist *evlist) +static int test__checkevent_pmu_events(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type); + TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type); TEST_ASSERT_VAL("wrong exclude_user", - !evsel->attr.exclude_user); + !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", - evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); - TEST_ASSERT_VAL("wrong pinned", !evsel->attr.pinned); + evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); + TEST_ASSERT_VAL("wrong pinned", !evsel->core.attr.pinned); return 0; } -static int test__checkevent_pmu_events_mix(struct perf_evlist *evlist) +static int test__checkevent_pmu_events_mix(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); /* pmu-event:u */ - TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong exclude_user", - !evsel->attr.exclude_user); + !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", - evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); - TEST_ASSERT_VAL("wrong pinned", !evsel->attr.pinned); + evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); + TEST_ASSERT_VAL("wrong pinned", !evsel->core.attr.pinned); /* cpu/pmu-event/u*/ evsel = perf_evsel__next(evsel); - TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type); + TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type); TEST_ASSERT_VAL("wrong exclude_user", - !evsel->attr.exclude_user); + !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", - evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); - TEST_ASSERT_VAL("wrong pinned", !evsel->attr.pinned); + evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); + TEST_ASSERT_VAL("wrong pinned", !evsel->core.attr.pinned); return 0; } @@ -634,41 +634,41 @@ static int test__checkterms_simple(struct list_head *terms) return 0; } -static int test__group1(struct perf_evlist *evlist) +static int test__group1(struct evlist *evlist) { - struct perf_evsel *evsel, *leader; + struct evsel *evsel, *leader; - TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups); /* instructions:k */ evsel = leader = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_INSTRUCTIONS == evsel->attr.config); - TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); - TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); - TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + PERF_COUNT_HW_INSTRUCTIONS == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); - TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2); + TEST_ASSERT_VAL("wrong core.nr_members", evsel->core.nr_members == 2); TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0); TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read); /* cycles:upp */ evsel = perf_evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config); - TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); + PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); /* use of precise requires exclude_guest */ - TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest); - TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); - TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 2); + TEST_ASSERT_VAL("wrong exclude guest", evsel->core.attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", evsel->core.attr.precise_ip == 2); TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1); TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read); @@ -676,99 +676,99 @@ static int test__group1(struct perf_evlist *evlist) return 0; } -static int test__group2(struct perf_evlist *evlist) +static int test__group2(struct evlist *evlist) { - struct perf_evsel *evsel, *leader; + struct evsel *evsel, *leader; - TEST_ASSERT_VAL("wrong number of entries", 3 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong number of entries", 3 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups); /* faults + :ku modifier */ evsel = leader = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_SOFTWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_SOFTWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", - PERF_COUNT_SW_PAGE_FAULTS == evsel->attr.config); - TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); - TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); - TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + PERF_COUNT_SW_PAGE_FAULTS == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); - TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2); + TEST_ASSERT_VAL("wrong core.nr_members", evsel->core.nr_members == 2); TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0); TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read); /* cache-references + :u modifier */ evsel = perf_evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CACHE_REFERENCES == evsel->attr.config); - TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest); - TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); - TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + PERF_COUNT_HW_CACHE_REFERENCES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", evsel->core.attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1); TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read); /* cycles:k */ evsel = perf_evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config); - TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); - TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); - TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read); return 0; } -static int test__group3(struct perf_evlist *evlist __maybe_unused) +static int test__group3(struct evlist *evlist __maybe_unused) { - struct perf_evsel *evsel, *leader; + struct evsel *evsel, *leader; - TEST_ASSERT_VAL("wrong number of entries", 5 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong number of entries", 5 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong number of groups", 2 == evlist->nr_groups); /* group1 syscalls:sys_enter_openat:H */ evsel = leader = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_TRACEPOINT == evsel->attr.type); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_TRACEPOINT == evsel->core.attr.type); TEST_ASSERT_VAL("wrong sample_type", - PERF_TP_SAMPLE_TYPE == evsel->attr.sample_type); - TEST_ASSERT_VAL("wrong sample_period", 1 == evsel->attr.sample_period); - TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest); - TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); - TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + PERF_TP_SAMPLE_TYPE == evsel->core.attr.sample_type); + TEST_ASSERT_VAL("wrong sample_period", 1 == evsel->core.attr.sample_period); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", evsel->core.attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); TEST_ASSERT_VAL("wrong group name", !strcmp(leader->group_name, "group1")); - TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2); + TEST_ASSERT_VAL("wrong core.nr_members", evsel->core.nr_members == 2); TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0); TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read); /* group1 cycles:kppp */ evsel = perf_evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config); - TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); + PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); /* use of precise requires exclude_guest */ - TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest); - TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); - TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 3); + TEST_ASSERT_VAL("wrong exclude guest", evsel->core.attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", evsel->core.attr.precise_ip == 3); TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); TEST_ASSERT_VAL("wrong group name", !evsel->group_name); TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1); @@ -776,90 +776,90 @@ static int test__group3(struct perf_evlist *evlist __maybe_unused) /* group2 cycles + G modifier */ evsel = leader = perf_evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config); - TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); - TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host); - TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", evsel->core.attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); TEST_ASSERT_VAL("wrong group name", !strcmp(leader->group_name, "group2")); - TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2); + TEST_ASSERT_VAL("wrong core.nr_members", evsel->core.nr_members == 2); TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0); TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read); /* group2 1:3 + G modifier */ evsel = perf_evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", 1 == evsel->attr.type); - TEST_ASSERT_VAL("wrong config", 3 == evsel->attr.config); - TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); - TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host); - TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong type", 1 == evsel->core.attr.type); + TEST_ASSERT_VAL("wrong config", 3 == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", evsel->core.attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1); TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read); /* instructions:u */ evsel = perf_evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_INSTRUCTIONS == evsel->attr.config); - TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); - TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); - TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + PERF_COUNT_HW_INSTRUCTIONS == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read); return 0; } -static int test__group4(struct perf_evlist *evlist __maybe_unused) +static int test__group4(struct evlist *evlist __maybe_unused) { - struct perf_evsel *evsel, *leader; + struct evsel *evsel, *leader; - TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups); /* cycles:u + p */ evsel = leader = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config); - TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); + PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); /* use of precise requires exclude_guest */ - TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest); - TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); - TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 1); + TEST_ASSERT_VAL("wrong exclude guest", evsel->core.attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", evsel->core.attr.precise_ip == 1); TEST_ASSERT_VAL("wrong group name", !evsel->group_name); TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); - TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2); + TEST_ASSERT_VAL("wrong core.nr_members", evsel->core.nr_members == 2); TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0); TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read); /* instructions:kp + p */ evsel = perf_evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_INSTRUCTIONS == evsel->attr.config); - TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); + PERF_COUNT_HW_INSTRUCTIONS == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); /* use of precise requires exclude_guest */ - TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest); - TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); - TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 2); + TEST_ASSERT_VAL("wrong exclude guest", evsel->core.attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", evsel->core.attr.precise_ip == 2); TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1); TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read); @@ -867,298 +867,298 @@ static int test__group4(struct perf_evlist *evlist __maybe_unused) return 0; } -static int test__group5(struct perf_evlist *evlist __maybe_unused) +static int test__group5(struct evlist *evlist __maybe_unused) { - struct perf_evsel *evsel, *leader; + struct evsel *evsel, *leader; - TEST_ASSERT_VAL("wrong number of entries", 5 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong number of entries", 5 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong number of groups", 2 == evlist->nr_groups); /* cycles + G */ evsel = leader = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config); - TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); - TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host); - TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", evsel->core.attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); TEST_ASSERT_VAL("wrong group name", !evsel->group_name); TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); - TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2); + TEST_ASSERT_VAL("wrong core.nr_members", evsel->core.nr_members == 2); TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0); TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read); /* instructions + G */ evsel = perf_evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_INSTRUCTIONS == evsel->attr.config); - TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); - TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host); - TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + PERF_COUNT_HW_INSTRUCTIONS == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", evsel->core.attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1); TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read); /* cycles:G */ evsel = leader = perf_evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config); - TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); - TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host); - TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", evsel->core.attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); TEST_ASSERT_VAL("wrong group name", !evsel->group_name); TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); - TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2); + TEST_ASSERT_VAL("wrong core.nr_members", evsel->core.nr_members == 2); TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0); TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read); /* instructions:G */ evsel = perf_evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_INSTRUCTIONS == evsel->attr.config); - TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); - TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host); - TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + PERF_COUNT_HW_INSTRUCTIONS == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", evsel->core.attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1); /* cycles */ evsel = perf_evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config); - TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest); - TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); - TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", evsel->core.attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); return 0; } -static int test__group_gh1(struct perf_evlist *evlist) +static int test__group_gh1(struct evlist *evlist) { - struct perf_evsel *evsel, *leader; + struct evsel *evsel, *leader; - TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups); /* cycles + :H group modifier */ evsel = leader = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config); - TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest); - TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); - TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", evsel->core.attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); TEST_ASSERT_VAL("wrong group name", !evsel->group_name); TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); - TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2); + TEST_ASSERT_VAL("wrong core.nr_members", evsel->core.nr_members == 2); TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0); /* cache-misses:G + :H group modifier */ evsel = perf_evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CACHE_MISSES == evsel->attr.config); - TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); - TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); - TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + PERF_COUNT_HW_CACHE_MISSES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1); return 0; } -static int test__group_gh2(struct perf_evlist *evlist) +static int test__group_gh2(struct evlist *evlist) { - struct perf_evsel *evsel, *leader; + struct evsel *evsel, *leader; - TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups); /* cycles + :G group modifier */ evsel = leader = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config); - TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); - TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host); - TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", evsel->core.attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); TEST_ASSERT_VAL("wrong group name", !evsel->group_name); TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); - TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2); + TEST_ASSERT_VAL("wrong core.nr_members", evsel->core.nr_members == 2); TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0); /* cache-misses:H + :G group modifier */ evsel = perf_evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CACHE_MISSES == evsel->attr.config); - TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); - TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); - TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + PERF_COUNT_HW_CACHE_MISSES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1); return 0; } -static int test__group_gh3(struct perf_evlist *evlist) +static int test__group_gh3(struct evlist *evlist) { - struct perf_evsel *evsel, *leader; + struct evsel *evsel, *leader; - TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups); /* cycles:G + :u group modifier */ evsel = leader = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config); - TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); - TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host); - TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", evsel->core.attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); TEST_ASSERT_VAL("wrong group name", !evsel->group_name); TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); - TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2); + TEST_ASSERT_VAL("wrong core.nr_members", evsel->core.nr_members == 2); TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0); /* cache-misses:H + :u group modifier */ evsel = perf_evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CACHE_MISSES == evsel->attr.config); - TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest); - TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); - TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + PERF_COUNT_HW_CACHE_MISSES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", evsel->core.attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1); return 0; } -static int test__group_gh4(struct perf_evlist *evlist) +static int test__group_gh4(struct evlist *evlist) { - struct perf_evsel *evsel, *leader; + struct evsel *evsel, *leader; - TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups); /* cycles:G + :uG group modifier */ evsel = leader = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config); - TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); - TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host); - TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", evsel->core.attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); TEST_ASSERT_VAL("wrong group name", !evsel->group_name); TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); - TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2); + TEST_ASSERT_VAL("wrong core.nr_members", evsel->core.nr_members == 2); TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0); /* cache-misses:H + :uG group modifier */ evsel = perf_evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CACHE_MISSES == evsel->attr.config); - TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); - TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); - TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + PERF_COUNT_HW_CACHE_MISSES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1); return 0; } -static int test__leader_sample1(struct perf_evlist *evlist) +static int test__leader_sample1(struct evlist *evlist) { - struct perf_evsel *evsel, *leader; + struct evsel *evsel, *leader; - TEST_ASSERT_VAL("wrong number of entries", 3 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong number of entries", 3 == evlist->core.nr_entries); /* cycles - sampling group leader */ evsel = leader = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config); - TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest); - TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); - TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", evsel->core.attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); TEST_ASSERT_VAL("wrong group name", !evsel->group_name); TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); TEST_ASSERT_VAL("wrong sample_read", evsel->sample_read); /* cache-misses - not sampling */ evsel = perf_evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CACHE_MISSES == evsel->attr.config); - TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest); - TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); - TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + PERF_COUNT_HW_CACHE_MISSES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", evsel->core.attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); TEST_ASSERT_VAL("wrong sample_read", evsel->sample_read); /* branch-misses - not sampling */ evsel = perf_evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_BRANCH_MISSES == evsel->attr.config); - TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest); - TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); - TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + PERF_COUNT_HW_BRANCH_MISSES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", evsel->core.attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); TEST_ASSERT_VAL("wrong group name", !evsel->group_name); TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); TEST_ASSERT_VAL("wrong sample_read", evsel->sample_read); @@ -1166,38 +1166,38 @@ static int test__leader_sample1(struct perf_evlist *evlist) return 0; } -static int test__leader_sample2(struct perf_evlist *evlist __maybe_unused) +static int test__leader_sample2(struct evlist *evlist __maybe_unused) { - struct perf_evsel *evsel, *leader; + struct evsel *evsel, *leader; - TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries); /* instructions - sampling group leader */ evsel = leader = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_INSTRUCTIONS == evsel->attr.config); - TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest); - TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); - TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + PERF_COUNT_HW_INSTRUCTIONS == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", evsel->core.attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); TEST_ASSERT_VAL("wrong group name", !evsel->group_name); TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); TEST_ASSERT_VAL("wrong sample_read", evsel->sample_read); /* branch-misses - not sampling */ evsel = perf_evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_BRANCH_MISSES == evsel->attr.config); - TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest); - TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); - TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + PERF_COUNT_HW_BRANCH_MISSES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", evsel->core.attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); TEST_ASSERT_VAL("wrong group name", !evsel->group_name); TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); TEST_ASSERT_VAL("wrong sample_read", evsel->sample_read); @@ -1205,131 +1205,131 @@ static int test__leader_sample2(struct perf_evlist *evlist __maybe_unused) return 0; } -static int test__checkevent_pinned_modifier(struct perf_evlist *evlist) +static int test__checkevent_pinned_modifier(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip); - TEST_ASSERT_VAL("wrong pinned", evsel->attr.pinned); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong precise_ip", evsel->core.attr.precise_ip); + TEST_ASSERT_VAL("wrong pinned", evsel->core.attr.pinned); return test__checkevent_symbolic_name(evlist); } -static int test__pinned_group(struct perf_evlist *evlist) +static int test__pinned_group(struct evlist *evlist) { - struct perf_evsel *evsel, *leader; + struct evsel *evsel, *leader; - TEST_ASSERT_VAL("wrong number of entries", 3 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong number of entries", 3 == evlist->core.nr_entries); /* cycles - group leader */ evsel = leader = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config); + PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config); TEST_ASSERT_VAL("wrong group name", !evsel->group_name); TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); - TEST_ASSERT_VAL("wrong pinned", evsel->attr.pinned); + TEST_ASSERT_VAL("wrong pinned", evsel->core.attr.pinned); /* cache-misses - can not be pinned, but will go on with the leader */ evsel = perf_evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CACHE_MISSES == evsel->attr.config); - TEST_ASSERT_VAL("wrong pinned", !evsel->attr.pinned); + PERF_COUNT_HW_CACHE_MISSES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong pinned", !evsel->core.attr.pinned); /* branch-misses - ditto */ evsel = perf_evsel__next(evsel); TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_BRANCH_MISSES == evsel->attr.config); - TEST_ASSERT_VAL("wrong pinned", !evsel->attr.pinned); + PERF_COUNT_HW_BRANCH_MISSES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong pinned", !evsel->core.attr.pinned); return 0; } -static int test__checkevent_breakpoint_len(struct perf_evlist *evlist) +static int test__checkevent_breakpoint_len(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_BREAKPOINT == evsel->attr.type); - TEST_ASSERT_VAL("wrong config", 0 == evsel->attr.config); + TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_BREAKPOINT == evsel->core.attr.type); + TEST_ASSERT_VAL("wrong config", 0 == evsel->core.attr.config); TEST_ASSERT_VAL("wrong bp_type", (HW_BREAKPOINT_R | HW_BREAKPOINT_W) == - evsel->attr.bp_type); + evsel->core.attr.bp_type); TEST_ASSERT_VAL("wrong bp_len", HW_BREAKPOINT_LEN_1 == - evsel->attr.bp_len); + evsel->core.attr.bp_len); return 0; } -static int test__checkevent_breakpoint_len_w(struct perf_evlist *evlist) +static int test__checkevent_breakpoint_len_w(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_BREAKPOINT == evsel->attr.type); - TEST_ASSERT_VAL("wrong config", 0 == evsel->attr.config); + TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_BREAKPOINT == evsel->core.attr.type); + TEST_ASSERT_VAL("wrong config", 0 == evsel->core.attr.config); TEST_ASSERT_VAL("wrong bp_type", HW_BREAKPOINT_W == - evsel->attr.bp_type); + evsel->core.attr.bp_type); TEST_ASSERT_VAL("wrong bp_len", HW_BREAKPOINT_LEN_2 == - evsel->attr.bp_len); + evsel->core.attr.bp_len); return 0; } static int -test__checkevent_breakpoint_len_rw_modifier(struct perf_evlist *evlist) +test__checkevent_breakpoint_len_rw_modifier(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); return test__checkevent_breakpoint_rw(evlist); } -static int test__checkevent_precise_max_modifier(struct perf_evlist *evlist) +static int test__checkevent_precise_max_modifier(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_SOFTWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_SOFTWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", - PERF_COUNT_SW_TASK_CLOCK == evsel->attr.config); + PERF_COUNT_SW_TASK_CLOCK == evsel->core.attr.config); return 0; } -static int test__checkevent_config_symbol(struct perf_evlist *evlist) +static int test__checkevent_config_symbol(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "insn") == 0); return 0; } -static int test__checkevent_config_raw(struct perf_evlist *evlist) +static int test__checkevent_config_raw(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "rawpmu") == 0); return 0; } -static int test__checkevent_config_num(struct perf_evlist *evlist) +static int test__checkevent_config_num(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "numpmu") == 0); return 0; } -static int test__checkevent_config_cache(struct perf_evlist *evlist) +static int test__checkevent_config_cache(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "cachepmu") == 0); return 0; @@ -1340,39 +1340,39 @@ static bool test__intel_pt_valid(void) return !!perf_pmu__find("intel_pt"); } -static int test__intel_pt(struct perf_evlist *evlist) +static int test__intel_pt(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "intel_pt//u") == 0); return 0; } -static int test__checkevent_complex_name(struct perf_evlist *evlist) +static int test__checkevent_complex_name(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); TEST_ASSERT_VAL("wrong complex name parsing", strcmp(evsel->name, "COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks") == 0); return 0; } -static int test__sym_event_slash(struct perf_evlist *evlist) +static int test__sym_event_slash(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong type", evsel->attr.type == PERF_TYPE_HARDWARE); - TEST_ASSERT_VAL("wrong config", evsel->attr.config == PERF_COUNT_HW_CPU_CYCLES); - TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong type", evsel->core.attr.type == PERF_TYPE_HARDWARE); + TEST_ASSERT_VAL("wrong config", evsel->core.attr.config == PERF_COUNT_HW_CPU_CYCLES); + TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); return 0; } -static int test__sym_event_dc(struct perf_evlist *evlist) +static int test__sym_event_dc(struct evlist *evlist) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = perf_evlist__first(evlist); - TEST_ASSERT_VAL("wrong type", evsel->attr.type == PERF_TYPE_HARDWARE); - TEST_ASSERT_VAL("wrong config", evsel->attr.config == PERF_COUNT_HW_CPU_CYCLES); - TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong type", evsel->core.attr.type == PERF_TYPE_HARDWARE); + TEST_ASSERT_VAL("wrong config", evsel->core.attr.config == PERF_COUNT_HW_CPU_CYCLES); + TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user); return 0; } @@ -1422,10 +1422,10 @@ static int count_tracepoints(void) return cnt; } -static int test__all_tracepoints(struct perf_evlist *evlist) +static int test__all_tracepoints(struct evlist *evlist) { TEST_ASSERT_VAL("wrong events count", - count_tracepoints() == evlist->nr_entries); + count_tracepoints() == evlist->core.nr_entries); return test__checkevent_tracepoint_multi(evlist); } @@ -1435,7 +1435,7 @@ struct evlist_test { __u32 type; const int id; bool (*valid)(void); - int (*check)(struct perf_evlist *evlist); + int (*check)(struct evlist *evlist); }; static struct evlist_test test__events[] = { @@ -1769,7 +1769,7 @@ static struct terms_test test__terms[] = { static int test_event(struct evlist_test *e) { struct parse_events_error err = { .idx = 0, }; - struct perf_evlist *evlist; + struct evlist *evlist; int ret; if (e->valid && !e->valid()) { @@ -1777,7 +1777,7 @@ static int test_event(struct evlist_test *e) return 0; } - evlist = perf_evlist__new(); + evlist = evlist__new(); if (evlist == NULL) return -ENOMEM; @@ -1790,7 +1790,7 @@ static int test_event(struct evlist_test *e) ret = e->check(evlist); } - perf_evlist__delete(evlist); + evlist__delete(evlist); return ret; } diff --git a/tools/perf/tests/parse-no-sample-id-all.c b/tools/perf/tests/parse-no-sample-id-all.c index 2196d1497c0c..396e40d68922 100644 --- a/tools/perf/tests/parse-no-sample-id-all.c +++ b/tools/perf/tests/parse-no-sample-id-all.c @@ -11,7 +11,7 @@ #include "util.h" #include "debug.h" -static int process_event(struct perf_evlist **pevlist, union perf_event *event) +static int process_event(struct evlist **pevlist, union perf_event *event) { struct perf_sample sample; @@ -39,14 +39,14 @@ static int process_event(struct perf_evlist **pevlist, union perf_event *event) static int process_events(union perf_event **events, size_t count) { - struct perf_evlist *evlist = NULL; + struct evlist *evlist = NULL; int err = 0; size_t i; for (i = 0; i < count && !err; i++) err = process_event(&evlist, events[i]); - perf_evlist__delete(evlist); + evlist__delete(evlist); return err; } diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c index 07f6bd8ed719..67b388e92cba 100644 --- a/tools/perf/tests/perf-record.c +++ b/tools/perf/tests/perf-record.c @@ -50,8 +50,8 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus }; cpu_set_t cpu_mask; size_t cpu_mask_size = sizeof(cpu_mask); - struct perf_evlist *evlist = perf_evlist__new_dummy(); - struct perf_evsel *evsel; + struct evlist *evlist = perf_evlist__new_dummy(); + struct evsel *evsel; struct perf_sample sample; const char *cmd = "sleep"; const char *argv[] = { cmd, "1", NULL, }; @@ -130,7 +130,7 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus * Call sys_perf_event_open on all the fds on all the evsels, * grouping them if asked to. */ - err = perf_evlist__open(evlist); + err = evlist__open(evlist); if (err < 0) { pr_debug("perf_evlist__open: %s\n", str_error_r(errno, sbuf, sizeof(sbuf))); @@ -153,7 +153,7 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus * Now that all is properly set up, enable the events, they will * count just on workload.pid, which will start... */ - perf_evlist__enable(evlist); + evlist__enable(evlist); /* * Now! @@ -325,7 +325,7 @@ found_exit: ++errs; } out_delete_evlist: - perf_evlist__delete(evlist); + evlist__delete(evlist); out: return (err < 0 || errs > 0) ? -1 : 0; } diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c index 361714e2583c..a8ca29fe172b 100644 --- a/tools/perf/tests/sample-parsing.c +++ b/tools/perf/tests/sample-parsing.c @@ -153,11 +153,13 @@ static bool samples_same(const struct perf_sample *s1, static int do_test(u64 sample_type, u64 sample_regs, u64 read_format) { - struct perf_evsel evsel = { + struct evsel evsel = { .needs_swap = false, - .attr = { - .sample_type = sample_type, - .read_format = read_format, + .core = { + . attr = { + .sample_type = sample_type, + .read_format = read_format, + }, }, }; union perf_event *event; @@ -221,10 +223,10 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format) int err, ret = -1; if (sample_type & PERF_SAMPLE_REGS_USER) - evsel.attr.sample_regs_user = sample_regs; + evsel.core.attr.sample_regs_user = sample_regs; if (sample_type & PERF_SAMPLE_REGS_INTR) - evsel.attr.sample_regs_intr = sample_regs; + evsel.core.attr.sample_regs_intr = sample_regs; for (i = 0; i < sizeof(regs); i++) *(i + (u8 *)regs) = i & 0xfe; diff --git a/tools/perf/tests/shell/trace+probe_vfs_getname.sh b/tools/perf/tests/shell/trace+probe_vfs_getname.sh index 45d269b0157e..11cc2af13f2b 100755 --- a/tools/perf/tests/shell/trace+probe_vfs_getname.sh +++ b/tools/perf/tests/shell/trace+probe_vfs_getname.sh @@ -32,6 +32,10 @@ if [ $err -ne 0 ] ; then exit $err fi +# Do not use whatever ~/.perfconfig file, it may change the output +# via trace.{show_timestamp,show_prefix,etc} +export PERF_CONFIG=/dev/null + trace_open_vfs_getname err=$? rm -f ${file} diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c index f9490b237893..c5f1a9f83380 100644 --- a/tools/perf/tests/sw-clock.c +++ b/tools/perf/tests/sw-clock.c @@ -11,6 +11,7 @@ #include "util/evlist.h" #include "util/cpumap.h" #include "util/thread_map.h" +#include <perf/evlist.h> #define NR_LOOPS 10000000 @@ -27,8 +28,8 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id) int nr_samples = 0; char sbuf[STRERR_BUFSIZE]; union perf_event *event; - struct perf_evsel *evsel; - struct perf_evlist *evlist; + struct evsel *evsel; + struct evlist *evlist; struct perf_event_attr attr = { .type = PERF_TYPE_SOFTWARE, .config = clock_id, @@ -37,26 +38,26 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id) .disabled = 1, .freq = 1, }; - struct cpu_map *cpus; - struct thread_map *threads; + struct perf_cpu_map *cpus; + struct perf_thread_map *threads; struct perf_mmap *md; attr.sample_freq = 500; - evlist = perf_evlist__new(); + evlist = evlist__new(); if (evlist == NULL) { - pr_debug("perf_evlist__new\n"); + pr_debug("evlist__new\n"); return -1; } - evsel = perf_evsel__new(&attr); + evsel = evsel__new(&attr); if (evsel == NULL) { pr_debug("perf_evsel__new\n"); goto out_delete_evlist; } - perf_evlist__add(evlist, evsel); + evlist__add(evlist, evsel); - cpus = cpu_map__dummy_new(); + cpus = perf_cpu_map__dummy_new(); threads = thread_map__new_by_tid(getpid()); if (!cpus || !threads) { err = -ENOMEM; @@ -64,12 +65,12 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id) goto out_free_maps; } - perf_evlist__set_maps(evlist, cpus, threads); + perf_evlist__set_maps(&evlist->core, cpus, threads); cpus = NULL; threads = NULL; - if (perf_evlist__open(evlist)) { + if (evlist__open(evlist)) { const char *knob = "/proc/sys/kernel/perf_event_max_sample_rate"; err = -errno; @@ -86,13 +87,13 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id) goto out_delete_evlist; } - perf_evlist__enable(evlist); + evlist__enable(evlist); /* collect samples */ for (i = 0; i < NR_LOOPS; i++) tmp++; - perf_evlist__disable(evlist); + evlist__disable(evlist); md = &evlist->mmap[0]; if (perf_mmap__read_init(md) < 0) @@ -125,10 +126,10 @@ out_init: } out_free_maps: - cpu_map__put(cpus); - thread_map__put(threads); + perf_cpu_map__put(cpus); + perf_thread_map__put(threads); out_delete_evlist: - perf_evlist__delete(evlist); + evlist__delete(evlist); return err; } diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c index 6cdab5f4812a..e3cee69f6ea2 100644 --- a/tools/perf/tests/switch-tracking.c +++ b/tools/perf/tests/switch-tracking.c @@ -5,6 +5,8 @@ #include <time.h> #include <stdlib.h> #include <linux/zalloc.h> +#include <perf/cpumap.h> +#include <perf/evlist.h> #include "parse-events.h" #include "evlist.h" @@ -52,8 +54,8 @@ static int spin_sleep(void) } struct switch_tracking { - struct perf_evsel *switch_evsel; - struct perf_evsel *cycles_evsel; + struct evsel *switch_evsel; + struct evsel *cycles_evsel; pid_t *tids; int nr_tids; int comm_seen[4]; @@ -113,12 +115,12 @@ static int check_cpu(struct switch_tracking *switch_tracking, int cpu) return 0; } -static int process_sample_event(struct perf_evlist *evlist, +static int process_sample_event(struct evlist *evlist, union perf_event *event, struct switch_tracking *switch_tracking) { struct perf_sample sample; - struct perf_evsel *evsel; + struct evsel *evsel; pid_t next_tid, prev_tid; int cpu, err; @@ -163,7 +165,7 @@ static int process_sample_event(struct perf_evlist *evlist, return 0; } -static int process_event(struct perf_evlist *evlist, union perf_event *event, +static int process_event(struct evlist *evlist, union perf_event *event, struct switch_tracking *switch_tracking) { if (event->header.type == PERF_RECORD_SAMPLE) @@ -203,7 +205,7 @@ struct event_node { u64 event_time; }; -static int add_event(struct perf_evlist *evlist, struct list_head *events, +static int add_event(struct evlist *evlist, struct list_head *events, union perf_event *event) { struct perf_sample sample; @@ -252,7 +254,7 @@ static int compar(const void *a, const void *b) return cmp; } -static int process_events(struct perf_evlist *evlist, +static int process_events(struct evlist *evlist, struct switch_tracking *switch_tracking) { union perf_event *event; @@ -327,11 +329,11 @@ int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_ .uses_mmap = true, }, }; - struct thread_map *threads = NULL; - struct cpu_map *cpus = NULL; - struct perf_evlist *evlist = NULL; - struct perf_evsel *evsel, *cpu_clocks_evsel, *cycles_evsel; - struct perf_evsel *switch_evsel, *tracking_evsel; + struct perf_thread_map *threads = NULL; + struct perf_cpu_map *cpus = NULL; + struct evlist *evlist = NULL; + struct evsel *evsel, *cpu_clocks_evsel, *cycles_evsel; + struct evsel *switch_evsel, *tracking_evsel; const char *comm; int err = -1; @@ -341,19 +343,19 @@ int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_ goto out_err; } - cpus = cpu_map__new(NULL); + cpus = perf_cpu_map__new(NULL); if (!cpus) { - pr_debug("cpu_map__new failed!\n"); + pr_debug("perf_cpu_map__new failed!\n"); goto out_err; } - evlist = perf_evlist__new(); + evlist = evlist__new(); if (!evlist) { - pr_debug("perf_evlist__new failed!\n"); + pr_debug("evlist__new failed!\n"); goto out_err; } - perf_evlist__set_maps(evlist, cpus, threads); + perf_evlist__set_maps(&evlist->core, cpus, threads); /* First event */ err = parse_events(evlist, "cpu-clock:u", NULL); @@ -420,8 +422,8 @@ int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_ perf_evlist__set_tracking_event(evlist, tracking_evsel); - tracking_evsel->attr.freq = 0; - tracking_evsel->attr.sample_period = 1; + tracking_evsel->core.attr.freq = 0; + tracking_evsel->core.attr.sample_period = 1; perf_evsel__set_sample_bit(tracking_evsel, TIME); @@ -435,7 +437,7 @@ int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_ } /* Check tracking event is tracking */ - if (!tracking_evsel->attr.mmap || !tracking_evsel->attr.comm) { + if (!tracking_evsel->core.attr.mmap || !tracking_evsel->core.attr.comm) { pr_debug("Tracking event not tracking\n"); goto out_err; } @@ -443,14 +445,14 @@ int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_ /* Check non-tracking events are not tracking */ evlist__for_each_entry(evlist, evsel) { if (evsel != tracking_evsel) { - if (evsel->attr.mmap || evsel->attr.comm) { + if (evsel->core.attr.mmap || evsel->core.attr.comm) { pr_debug("Non-tracking event is tracking\n"); goto out_err; } } } - if (perf_evlist__open(evlist) < 0) { + if (evlist__open(evlist) < 0) { pr_debug("Not supported\n"); err = 0; goto out; @@ -462,9 +464,9 @@ int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_ goto out_err; } - perf_evlist__enable(evlist); + evlist__enable(evlist); - err = perf_evsel__disable(cpu_clocks_evsel); + err = evsel__disable(cpu_clocks_evsel); if (err) { pr_debug("perf_evlist__disable_event failed!\n"); goto out_err; @@ -483,7 +485,7 @@ int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_ goto out_err; } - err = perf_evsel__disable(cycles_evsel); + err = evsel__disable(cycles_evsel); if (err) { pr_debug("perf_evlist__disable_event failed!\n"); goto out_err; @@ -509,7 +511,7 @@ int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_ goto out_err; } - err = perf_evsel__enable(cycles_evsel); + err = evsel__enable(cycles_evsel); if (err) { pr_debug("perf_evlist__disable_event failed!\n"); goto out_err; @@ -528,7 +530,7 @@ int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_ goto out_err; } - perf_evlist__disable(evlist); + evlist__disable(evlist); switch_tracking.switch_evsel = switch_evsel; switch_tracking.cycles_evsel = cycles_evsel; @@ -566,11 +568,11 @@ int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_ } out: if (evlist) { - perf_evlist__disable(evlist); - perf_evlist__delete(evlist); + evlist__disable(evlist); + evlist__delete(evlist); } else { - cpu_map__put(cpus); - thread_map__put(threads); + perf_cpu_map__put(cpus); + perf_thread_map__put(threads); } return err; diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c index e92fa6029ac7..4ca38fd0379a 100644 --- a/tools/perf/tests/task-exit.c +++ b/tools/perf/tests/task-exit.c @@ -7,6 +7,7 @@ #include <errno.h> #include <signal.h> +#include <perf/evlist.h> static int exited; static int nr_exit; @@ -37,16 +38,16 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused { int err = -1; union perf_event *event; - struct perf_evsel *evsel; - struct perf_evlist *evlist; + struct evsel *evsel; + struct evlist *evlist; struct target target = { .uid = UINT_MAX, .uses_mmap = true, }; const char *argv[] = { "true", NULL }; char sbuf[STRERR_BUFSIZE]; - struct cpu_map *cpus; - struct thread_map *threads; + struct perf_cpu_map *cpus; + struct perf_thread_map *threads; struct perf_mmap *md; signal(SIGCHLD, sig_handler); @@ -63,7 +64,7 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused * perf_evlist__prepare_workload we'll fill in the only thread * we're monitoring, the one forked there. */ - cpus = cpu_map__dummy_new(); + cpus = perf_cpu_map__dummy_new(); threads = thread_map__new_by_tid(-1); if (!cpus || !threads) { err = -ENOMEM; @@ -71,7 +72,7 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused goto out_free_maps; } - perf_evlist__set_maps(evlist, cpus, threads); + perf_evlist__set_maps(&evlist->core, cpus, threads); cpus = NULL; threads = NULL; @@ -84,18 +85,18 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused } evsel = perf_evlist__first(evlist); - evsel->attr.task = 1; + evsel->core.attr.task = 1; #ifdef __s390x__ - evsel->attr.sample_freq = 1000000; + evsel->core.attr.sample_freq = 1000000; #else - evsel->attr.sample_freq = 1; + evsel->core.attr.sample_freq = 1; #endif - evsel->attr.inherit = 0; - evsel->attr.watermark = 0; - evsel->attr.wakeup_events = 1; - evsel->attr.exclude_kernel = 1; + evsel->core.attr.inherit = 0; + evsel->core.attr.watermark = 0; + evsel->core.attr.wakeup_events = 1; + evsel->core.attr.exclude_kernel = 1; - err = perf_evlist__open(evlist); + err = evlist__open(evlist); if (err < 0) { pr_debug("Couldn't open the evlist: %s\n", str_error_r(-err, sbuf, sizeof(sbuf))); @@ -135,9 +136,9 @@ out_init: } out_free_maps: - cpu_map__put(cpus); - thread_map__put(threads); + perf_cpu_map__put(cpus); + perf_thread_map__put(threads); out_delete_evlist: - perf_evlist__delete(evlist); + evlist__delete(evlist); return err; } diff --git a/tools/perf/tests/thread-map.c b/tools/perf/tests/thread-map.c index ccc17aced49e..d803eafedc60 100644 --- a/tools/perf/tests/thread-map.c +++ b/tools/perf/tests/thread-map.c @@ -13,7 +13,7 @@ int test__thread_map(struct test *test __maybe_unused, int subtest __maybe_unused) { - struct thread_map *map; + struct perf_thread_map *map; TEST_ASSERT_VAL("failed to set process name", !prctl(PR_SET_NAME, NAMEUL, 0, 0, 0)); @@ -26,28 +26,28 @@ int test__thread_map(struct test *test __maybe_unused, int subtest __maybe_unuse TEST_ASSERT_VAL("wrong nr", map->nr == 1); TEST_ASSERT_VAL("wrong pid", - thread_map__pid(map, 0) == getpid()); + perf_thread_map__pid(map, 0) == getpid()); TEST_ASSERT_VAL("wrong comm", - thread_map__comm(map, 0) && - !strcmp(thread_map__comm(map, 0), NAME)); + perf_thread_map__comm(map, 0) && + !strcmp(perf_thread_map__comm(map, 0), NAME)); TEST_ASSERT_VAL("wrong refcnt", refcount_read(&map->refcnt) == 1); - thread_map__put(map); + perf_thread_map__put(map); /* test dummy pid */ - map = thread_map__new_dummy(); + map = perf_thread_map__new_dummy(); TEST_ASSERT_VAL("failed to alloc map", map); thread_map__read_comms(map); TEST_ASSERT_VAL("wrong nr", map->nr == 1); - TEST_ASSERT_VAL("wrong pid", thread_map__pid(map, 0) == -1); + TEST_ASSERT_VAL("wrong pid", perf_thread_map__pid(map, 0) == -1); TEST_ASSERT_VAL("wrong comm", - thread_map__comm(map, 0) && - !strcmp(thread_map__comm(map, 0), "dummy")); + perf_thread_map__comm(map, 0) && + !strcmp(perf_thread_map__comm(map, 0), "dummy")); TEST_ASSERT_VAL("wrong refcnt", refcount_read(&map->refcnt) == 1); - thread_map__put(map); + perf_thread_map__put(map); return 0; } @@ -57,7 +57,7 @@ static int process_event(struct perf_tool *tool __maybe_unused, struct machine *machine __maybe_unused) { struct thread_map_event *map = &event->thread_map; - struct thread_map *threads; + struct perf_thread_map *threads; TEST_ASSERT_VAL("wrong nr", map->nr == 1); TEST_ASSERT_VAL("wrong pid", map->entries[0].pid == (u64) getpid()); @@ -68,19 +68,19 @@ static int process_event(struct perf_tool *tool __maybe_unused, TEST_ASSERT_VAL("wrong nr", threads->nr == 1); TEST_ASSERT_VAL("wrong pid", - thread_map__pid(threads, 0) == getpid()); + perf_thread_map__pid(threads, 0) == getpid()); TEST_ASSERT_VAL("wrong comm", - thread_map__comm(threads, 0) && - !strcmp(thread_map__comm(threads, 0), NAME)); + perf_thread_map__comm(threads, 0) && + !strcmp(perf_thread_map__comm(threads, 0), NAME)); TEST_ASSERT_VAL("wrong refcnt", refcount_read(&threads->refcnt) == 1); - thread_map__put(threads); + perf_thread_map__put(threads); return 0; } int test__thread_map_synthesize(struct test *test __maybe_unused, int subtest __maybe_unused) { - struct thread_map *threads; + struct perf_thread_map *threads; TEST_ASSERT_VAL("failed to set process name", !prctl(PR_SET_NAME, NAMEUL, 0, 0, 0)); @@ -99,7 +99,7 @@ int test__thread_map_synthesize(struct test *test __maybe_unused, int subtest __ int test__thread_map_remove(struct test *test __maybe_unused, int subtest __maybe_unused) { - struct thread_map *threads; + struct perf_thread_map *threads; char *str; int i; diff --git a/tools/perf/tests/time-utils-test.c b/tools/perf/tests/time-utils-test.c index 4f53006233a1..fe57ca3b6e54 100644 --- a/tools/perf/tests/time-utils-test.c +++ b/tools/perf/tests/time-utils-test.c @@ -69,7 +69,7 @@ struct test_data { static bool test__perf_time__parse_for_ranges(struct test_data *d) { - struct perf_evlist evlist = { + struct evlist evlist = { .first_sample_time = d->first, .last_sample_time = d->last, }; diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c index 9497d02f69e6..a4f9f5182b47 100644 --- a/tools/perf/tests/topology.c +++ b/tools/perf/tests/topology.c @@ -2,6 +2,7 @@ #include <string.h> #include <stdlib.h> #include <stdio.h> +#include <perf/cpumap.h> #include "tests.h" #include "util.h" #include "session.h" @@ -57,7 +58,7 @@ static int session_write_header(char *path) return 0; } -static int check_cpu_topology(char *path, struct cpu_map *map) +static int check_cpu_topology(char *path, struct perf_cpu_map *map) { struct perf_session *session; struct perf_data data = { @@ -116,7 +117,7 @@ static int check_cpu_topology(char *path, struct cpu_map *map) int test__session_topology(struct test *test __maybe_unused, int subtest __maybe_unused) { char path[PATH_MAX]; - struct cpu_map *map; + struct perf_cpu_map *map; int ret = TEST_FAIL; TEST_ASSERT_VAL("can't get templ file", !get_temp(path)); @@ -126,14 +127,14 @@ int test__session_topology(struct test *test __maybe_unused, int subtest __maybe if (session_write_header(path)) goto free_path; - map = cpu_map__new(NULL); + map = perf_cpu_map__new(NULL); if (map == NULL) { pr_debug("failed to get system cpumap\n"); goto free_path; } ret = check_cpu_topology(path, map); - cpu_map__put(map); + perf_cpu_map__put(map); free_path: unlink(path); diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c index d227d74b28f8..c797a853d3a0 100644 --- a/tools/perf/ui/browser.c +++ b/tools/perf/ui/browser.c @@ -347,6 +347,8 @@ static int __ui_browser__refresh(struct ui_browser *browser) SLsmg_fill_region(browser->y + row + browser->extra_title_lines, browser->x, browser->rows - row, width, ' '); + if (browser->nr_entries == 0 && browser->no_samples_msg) + __ui__info_window(NULL, browser->no_samples_msg, NULL); return 0; } diff --git a/tools/perf/ui/browser.h b/tools/perf/ui/browser.h index dc1444136658..3678eb88f119 100644 --- a/tools/perf/ui/browser.h +++ b/tools/perf/ui/browser.h @@ -23,6 +23,7 @@ struct ui_browser { void *priv; const char *title; char *helpline; + const char *no_samples_msg; void (*refresh_dimensions)(struct ui_browser *browser); unsigned int (*refresh)(struct ui_browser *browser); void (*write)(struct ui_browser *browser, void *entry, int row); diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index e67880bf1efe..e633eb42550d 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -299,7 +299,7 @@ static void annotate_browser__set_rb_top(struct annotate_browser *browser, } static void annotate_browser__calc_percent(struct annotate_browser *browser, - struct perf_evsel *evsel) + struct evsel *evsel) { struct map_symbol *ms = browser->b.priv; struct symbol *sym = ms->sym; @@ -406,7 +406,7 @@ static int sym_title(struct symbol *sym, struct map *map, char *title, * to the calling function. */ static bool annotate_browser__callq(struct annotate_browser *browser, - struct perf_evsel *evsel, + struct evsel *evsel, struct hist_browser_timer *hbt) { struct map_symbol *ms = browser->b.priv; @@ -422,7 +422,7 @@ static bool annotate_browser__callq(struct annotate_browser *browser, notes = symbol__annotation(dl->ops.target.sym); pthread_mutex_lock(¬es->lock); - if (!symbol__hists(dl->ops.target.sym, evsel->evlist->nr_entries)) { + if (!symbol__hists(dl->ops.target.sym, evsel->evlist->core.nr_entries)) { pthread_mutex_unlock(¬es->lock); ui__warning("Not enough memory for annotating '%s' symbol!\n", dl->ops.target.sym->name); @@ -455,7 +455,7 @@ struct disasm_line *annotate_browser__find_offset(struct annotate_browser *brows } static bool annotate_browser__jump(struct annotate_browser *browser, - struct perf_evsel *evsel, + struct evsel *evsel, struct hist_browser_timer *hbt) { struct disasm_line *dl = disasm_line(browser->selection); @@ -656,7 +656,7 @@ switch_percent_type(struct annotation_options *opts, bool base) } static int annotate_browser__run(struct annotate_browser *browser, - struct perf_evsel *evsel, + struct evsel *evsel, struct hist_browser_timer *hbt) { struct rb_node *nd = NULL; @@ -869,14 +869,14 @@ out: return key; } -int map_symbol__tui_annotate(struct map_symbol *ms, struct perf_evsel *evsel, +int map_symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel, struct hist_browser_timer *hbt, struct annotation_options *opts) { return symbol__tui_annotate(ms->sym, ms->map, evsel, hbt, opts); } -int hist_entry__tui_annotate(struct hist_entry *he, struct perf_evsel *evsel, +int hist_entry__tui_annotate(struct hist_entry *he, struct evsel *evsel, struct hist_browser_timer *hbt, struct annotation_options *opts) { @@ -888,7 +888,7 @@ int hist_entry__tui_annotate(struct hist_entry *he, struct perf_evsel *evsel, } int symbol__tui_annotate(struct symbol *sym, struct map *map, - struct perf_evsel *evsel, + struct evsel *evsel, struct hist_browser_timer *hbt, struct annotation_options *opts) { diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index a94eb0755e8b..30547fdb0787 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -2187,7 +2187,7 @@ struct hist_browser *hist_browser__new(struct hists *hists) } static struct hist_browser * -perf_evsel_browser__new(struct perf_evsel *evsel, +perf_evsel_browser__new(struct evsel *evsel, struct hist_browser_timer *hbt, struct perf_env *env, struct annotation_options *annotation_opts) @@ -2352,7 +2352,7 @@ struct popup_action { struct thread *thread; struct map_symbol ms; int socket; - struct perf_evsel *evsel; + struct evsel *evsel; enum rstype rstype; int (*fn)(struct hist_browser *browser, struct popup_action *act); @@ -2361,7 +2361,7 @@ struct popup_action { static int do_annotate(struct hist_browser *browser, struct popup_action *act) { - struct perf_evsel *evsel; + struct evsel *evsel; struct annotation *notes; struct hist_entry *he; int err; @@ -2596,7 +2596,7 @@ static int add_script_opt_2(struct hist_browser *browser __maybe_unused, struct popup_action *act, char **optstr, struct thread *thread, struct symbol *sym, - struct perf_evsel *evsel, const char *tstr) + struct evsel *evsel, const char *tstr) { if (thread) { @@ -2623,7 +2623,7 @@ static int add_script_opt(struct hist_browser *browser, struct popup_action *act, char **optstr, struct thread *thread, struct symbol *sym, - struct perf_evsel *evsel) + struct evsel *evsel) { int n, j; struct hist_entry *he; @@ -2653,7 +2653,7 @@ static int add_res_sample_opt(struct hist_browser *browser __maybe_unused, struct popup_action *act, char **optstr, struct res_sample *res_sample, - struct perf_evsel *evsel, + struct evsel *evsel, enum rstype type) { if (!res_sample) @@ -2814,7 +2814,7 @@ next: } } -static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, +static int perf_evsel__hists_browse(struct evsel *evsel, int nr_events, const char *helpline, bool left_exits, struct hist_browser_timer *hbt, @@ -2894,6 +2894,9 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, if (symbol_conf.col_width_list_str) perf_hpp__set_user_width(symbol_conf.col_width_list_str); + if (!is_report_browser(hbt)) + browser->b.no_samples_msg = "Collecting samples..."; + while (1) { struct thread *thread = NULL; struct map *map = NULL; @@ -3198,9 +3201,9 @@ out: return key; } -struct perf_evsel_menu { +struct evsel_menu { struct ui_browser b; - struct perf_evsel *selection; + struct evsel *selection; struct annotation_options *annotation_opts; bool lost_events, lost_events_warned; float min_pcnt; @@ -3210,9 +3213,9 @@ struct perf_evsel_menu { static void perf_evsel_menu__write(struct ui_browser *browser, void *entry, int row) { - struct perf_evsel_menu *menu = container_of(browser, - struct perf_evsel_menu, b); - struct perf_evsel *evsel = list_entry(entry, struct perf_evsel, node); + struct evsel_menu *menu = container_of(browser, + struct evsel_menu, b); + struct evsel *evsel = list_entry(entry, struct evsel, core.node); struct hists *hists = evsel__hists(evsel); bool current_entry = ui_browser__is_current_entry(browser, row); unsigned long nr_events = hists->stats.nr_events[PERF_RECORD_SAMPLE]; @@ -3225,7 +3228,7 @@ static void perf_evsel_menu__write(struct ui_browser *browser, HE_COLORSET_NORMAL); if (perf_evsel__is_group_event(evsel)) { - struct perf_evsel *pos; + struct evsel *pos; ev_name = perf_evsel__group_name(evsel); @@ -3257,13 +3260,13 @@ static void perf_evsel_menu__write(struct ui_browser *browser, menu->selection = evsel; } -static int perf_evsel_menu__run(struct perf_evsel_menu *menu, +static int perf_evsel_menu__run(struct evsel_menu *menu, int nr_events, const char *help, struct hist_browser_timer *hbt, bool warn_lost_event) { - struct perf_evlist *evlist = menu->b.priv; - struct perf_evsel *pos; + struct evlist *evlist = menu->b.priv; + struct evsel *pos; const char *title = "Available samples"; int delay_secs = hbt ? hbt->refresh : 0; int key; @@ -3309,13 +3312,13 @@ browse_hists: ui_browser__show_title(&menu->b, title); switch (key) { case K_TAB: - if (pos->node.next == &evlist->entries) + if (pos->core.node.next == &evlist->core.entries) pos = perf_evlist__first(evlist); else pos = perf_evsel__next(pos); goto browse_hists; case K_UNTAB: - if (pos->node.prev == &evlist->entries) + if (pos->core.node.prev == &evlist->core.entries) pos = perf_evlist__last(evlist); else pos = perf_evsel__prev(pos); @@ -3351,7 +3354,7 @@ out: static bool filter_group_entries(struct ui_browser *browser __maybe_unused, void *entry) { - struct perf_evsel *evsel = list_entry(entry, struct perf_evsel, node); + struct evsel *evsel = list_entry(entry, struct evsel, core.node); if (symbol_conf.event_group && !perf_evsel__is_group_leader(evsel)) return true; @@ -3359,7 +3362,7 @@ static bool filter_group_entries(struct ui_browser *browser __maybe_unused, return false; } -static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist, +static int __perf_evlist__tui_browse_hists(struct evlist *evlist, int nr_entries, const char *help, struct hist_browser_timer *hbt, float min_pcnt, @@ -3367,10 +3370,10 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist, bool warn_lost_event, struct annotation_options *annotation_opts) { - struct perf_evsel *pos; - struct perf_evsel_menu menu = { + struct evsel *pos; + struct evsel_menu menu = { .b = { - .entries = &evlist->entries, + .entries = &evlist->core.entries, .refresh = ui_browser__list_head_refresh, .seek = ui_browser__list_head_seek, .write = perf_evsel_menu__write, @@ -3397,18 +3400,18 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist, hbt, warn_lost_event); } -int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help, +int perf_evlist__tui_browse_hists(struct evlist *evlist, const char *help, struct hist_browser_timer *hbt, float min_pcnt, struct perf_env *env, bool warn_lost_event, struct annotation_options *annotation_opts) { - int nr_entries = evlist->nr_entries; + int nr_entries = evlist->core.nr_entries; single_entry: if (nr_entries == 1) { - struct perf_evsel *first = perf_evlist__first(evlist); + struct evsel *first = perf_evlist__first(evlist); return perf_evsel__hists_browse(first, nr_entries, help, false, hbt, min_pcnt, @@ -3417,7 +3420,7 @@ single_entry: } if (symbol_conf.event_group) { - struct perf_evsel *pos; + struct evsel *pos; nr_entries = 0; evlist__for_each_entry(evlist, pos) { diff --git a/tools/perf/ui/browsers/res_sample.c b/tools/perf/ui/browsers/res_sample.c index 8aa3547bb9ff..08897bd5eb0f 100644 --- a/tools/perf/ui/browsers/res_sample.c +++ b/tools/perf/ui/browsers/res_sample.c @@ -24,7 +24,7 @@ void res_sample_init(void) } int res_sample_browse(struct res_sample *res_samples, int num_res, - struct perf_evsel *evsel, enum rstype rstype) + struct evsel *evsel, enum rstype rstype) { char **names; int i, n; @@ -66,7 +66,7 @@ int res_sample_browse(struct res_sample *res_samples, int num_res, timestamp__scnprintf_nsec(r->time, tsample, sizeof tsample); - attr_to_script(extra_format, &evsel->attr); + attr_to_script(extra_format, &evsel->core.attr); if (asprintf(&cmd, "%s script %s%s --time %s %s%s %s%s --ns %s %s %s %s %s | less +/%s", perf, diff --git a/tools/perf/ui/browsers/scripts.c b/tools/perf/ui/browsers/scripts.c index 4d565cc14076..04f9aff5621e 100644 --- a/tools/perf/ui/browsers/scripts.c +++ b/tools/perf/ui/browsers/scripts.c @@ -78,7 +78,7 @@ static int scripts_config(const char *var, const char *value, void *data) * Return -1 on failure. */ static int list_scripts(char *script_name, bool *custom, - struct perf_evsel *evsel) + struct evsel *evsel) { char *buf, *paths[SCRIPT_MAX_NO], *names[SCRIPT_MAX_NO]; int i, num, choice; @@ -100,7 +100,7 @@ static int list_scripts(char *script_name, bool *custom, return -1; if (evsel) - attr_to_script(scriptc.extra_format, &evsel->attr); + attr_to_script(scriptc.extra_format, &evsel->core.attr); add_script_option("Show individual samples", "", &scriptc); add_script_option("Show individual samples with assembler", "-F +insn --xed", &scriptc); @@ -162,7 +162,7 @@ void run_script(char *cmd) SLsmg_refresh(); } -int script_browse(const char *script_opt, struct perf_evsel *evsel) +int script_browse(const char *script_opt, struct evsel *evsel) { char *cmd, script_name[SCRIPT_FULLPATH_LEN]; bool custom = false; diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c index 3af87c18a914..d7f984436dec 100644 --- a/tools/perf/ui/gtk/annotate.c +++ b/tools/perf/ui/gtk/annotate.c @@ -91,7 +91,7 @@ static int perf_gtk__get_line(char *buf, size_t size, struct disasm_line *dl) } static int perf_gtk__annotate_symbol(GtkWidget *window, struct symbol *sym, - struct map *map, struct perf_evsel *evsel, + struct map *map, struct evsel *evsel, struct hist_browser_timer *hbt __maybe_unused) { struct disasm_line *pos, *n; @@ -129,7 +129,7 @@ static int perf_gtk__annotate_symbol(GtkWidget *window, struct symbol *sym, gtk_list_store_append(store, &iter); if (perf_evsel__is_group_event(evsel)) { - for (i = 0; i < evsel->nr_members; i++) { + for (i = 0; i < evsel->core.nr_members; i++) { ret += perf_gtk__get_percent(s + ret, sizeof(s) - ret, sym, pos, @@ -160,7 +160,7 @@ static int perf_gtk__annotate_symbol(GtkWidget *window, struct symbol *sym, } static int symbol__gtk_annotate(struct symbol *sym, struct map *map, - struct perf_evsel *evsel, + struct evsel *evsel, struct hist_browser_timer *hbt) { GtkWidget *window; @@ -238,7 +238,7 @@ static int symbol__gtk_annotate(struct symbol *sym, struct map *map, } int hist_entry__gtk_annotate(struct hist_entry *he, - struct perf_evsel *evsel, + struct evsel *evsel, struct hist_browser_timer *hbt) { return symbol__gtk_annotate(he->ms.sym, he->ms.map, evsel, hbt); diff --git a/tools/perf/ui/gtk/gtk.h b/tools/perf/ui/gtk/gtk.h index 9846ea5c831b..a9563932fa04 100644 --- a/tools/perf/ui/gtk/gtk.h +++ b/tools/perf/ui/gtk/gtk.h @@ -52,16 +52,16 @@ static inline GtkWidget *perf_gtk__setup_info_bar(void) } #endif -struct perf_evsel; -struct perf_evlist; +struct evsel; +struct evlist; struct hist_entry; struct hist_browser_timer; -int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist, const char *help, +int perf_evlist__gtk_browse_hists(struct evlist *evlist, const char *help, struct hist_browser_timer *hbt, float min_pcnt); int hist_entry__gtk_annotate(struct hist_entry *he, - struct perf_evsel *evsel, + struct evsel *evsel, struct hist_browser_timer *hbt); void perf_gtk__show_annotations(void); diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c index 3955ed1d1bd9..0efdb226d1a7 100644 --- a/tools/perf/ui/gtk/hists.c +++ b/tools/perf/ui/gtk/hists.c @@ -590,12 +590,12 @@ static void perf_gtk__show_hierarchy(GtkWidget *window, struct hists *hists, gtk_container_add(GTK_CONTAINER(window), view); } -int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist, +int perf_evlist__gtk_browse_hists(struct evlist *evlist, const char *help, struct hist_browser_timer *hbt __maybe_unused, float min_pcnt) { - struct perf_evsel *pos; + struct evsel *pos; GtkWidget *vbox; GtkWidget *notebook; GtkWidget *info_bar; @@ -645,7 +645,7 @@ int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist, if (!perf_evsel__is_group_leader(pos)) continue; - if (pos->nr_members > 1) { + if (pos->core.nr_members > 1) { perf_evsel__group_desc(pos, buf, size); evname = buf; } diff --git a/tools/perf/ui/helpline.c b/tools/perf/ui/helpline.c index b3c421429ed4..54bcd08df87e 100644 --- a/tools/perf/ui/helpline.c +++ b/tools/perf/ui/helpline.c @@ -3,10 +3,10 @@ #include <stdlib.h> #include <string.h> -#include "../debug.h" +#include "../util/debug.h" #include "helpline.h" #include "ui.h" -#include "../util.h" +#include "../util/util.h" char ui_helpline__current[512]; diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c index 412d6f1626e3..e5fb64347b2c 100644 --- a/tools/perf/ui/hist.c +++ b/tools/perf/ui/hist.c @@ -25,7 +25,7 @@ static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he, { int ret; struct hists *hists = he->hists; - struct perf_evsel *evsel = hists_to_evsel(hists); + struct evsel *evsel = hists_to_evsel(hists); char *buf = hpp->buf; size_t size = hpp->size; @@ -43,7 +43,7 @@ static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he, if (perf_evsel__is_group_event(evsel)) { int prev_idx, idx_delta; struct hist_entry *pair; - int nr_members = evsel->nr_members; + int nr_members = evsel->core.nr_members; prev_idx = perf_evsel__group_idx(evsel); @@ -153,7 +153,7 @@ static int __hpp__sort(struct hist_entry *a, struct hist_entry *b, { s64 ret; int i, nr_members; - struct perf_evsel *evsel; + struct evsel *evsel; struct hist_entry *pair; u64 *fields_a, *fields_b; @@ -165,7 +165,7 @@ static int __hpp__sort(struct hist_entry *a, struct hist_entry *b, if (!perf_evsel__is_group_event(evsel)) return ret; - nr_members = evsel->nr_members; + nr_members = evsel->core.nr_members; fields_a = calloc(nr_members, sizeof(*fields_a)); fields_b = calloc(nr_members, sizeof(*fields_b)); @@ -223,10 +223,10 @@ static int hpp__width_fn(struct perf_hpp_fmt *fmt, struct hists *hists) { int len = fmt->user_len ?: fmt->len; - struct perf_evsel *evsel = hists_to_evsel(hists); + struct evsel *evsel = hists_to_evsel(hists); if (symbol_conf.event_group) - len = max(len, evsel->nr_members * fmt->len); + len = max(len, evsel->core.nr_members * fmt->len); if (len < (int)strlen(fmt->name)) len = strlen(fmt->name); @@ -795,9 +795,9 @@ static int add_hierarchy_fmt(struct hists *hists, struct perf_hpp_fmt *fmt) } int perf_hpp__setup_hists_formats(struct perf_hpp_list *list, - struct perf_evlist *evlist) + struct evlist *evlist) { - struct perf_evsel *evsel; + struct evsel *evsel; struct perf_hpp_fmt *fmt; struct hists *hists; int ret; diff --git a/tools/perf/ui/setup.c b/tools/perf/ui/setup.c index 44fe824e96cd..3bc7c9a6fae9 100644 --- a/tools/perf/ui/setup.c +++ b/tools/perf/ui/setup.c @@ -89,9 +89,9 @@ void setup_browser(bool fallback_to_pager) printf("GTK browser requested but could not find %s\n", PERF_GTK_DSO); sleep(1); + use_browser = 1; /* fall through */ case 1: - use_browser = 1; if (ui__init() == 0) break; /* fall through */ diff --git a/tools/perf/ui/tui/util.c b/tools/perf/ui/tui/util.c index fe5e571816fc..1163df8b6f06 100644 --- a/tools/perf/ui/tui/util.c +++ b/tools/perf/ui/tui/util.c @@ -162,8 +162,7 @@ next_key: return key; } -int ui__question_window(const char *title, const char *text, - const char *exit_msg, int delay_secs) +void __ui__info_window(const char *title, const char *text, const char *exit_msg) { int x, y; int max_len = 0, nr_lines = 0; @@ -185,10 +184,10 @@ int ui__question_window(const char *title, const char *text, t = sep + 1; } - pthread_mutex_lock(&ui__lock); - max_len += 2; - nr_lines += 4; + nr_lines += 2; + if (exit_msg) + nr_lines += 2; y = SLtt_Screen_Rows / 2 - nr_lines / 2, x = SLtt_Screen_Cols / 2 - max_len / 2; @@ -199,18 +198,34 @@ int ui__question_window(const char *title, const char *text, SLsmg_write_string((char *)title); } SLsmg_gotorc(++y, x); - nr_lines -= 2; + if (exit_msg) + nr_lines -= 2; max_len -= 2; SLsmg_write_wrapped_string((unsigned char *)text, y, x, nr_lines, max_len, 1); - SLsmg_gotorc(y + nr_lines - 2, x); - SLsmg_write_nstring((char *)" ", max_len); - SLsmg_gotorc(y + nr_lines - 1, x); - SLsmg_write_nstring((char *)exit_msg, max_len); - SLsmg_refresh(); + if (exit_msg) { + SLsmg_gotorc(y + nr_lines - 2, x); + SLsmg_write_nstring((char *)" ", max_len); + SLsmg_gotorc(y + nr_lines - 1, x); + SLsmg_write_nstring((char *)exit_msg, max_len); + } +} +void ui__info_window(const char *title, const char *text) +{ + pthread_mutex_lock(&ui__lock); + __ui__info_window(title, text, NULL); + SLsmg_refresh(); pthread_mutex_unlock(&ui__lock); +} +int ui__question_window(const char *title, const char *text, + const char *exit_msg, int delay_secs) +{ + pthread_mutex_lock(&ui__lock); + __ui__info_window(title, text, exit_msg); + SLsmg_refresh(); + pthread_mutex_unlock(&ui__lock); return ui__getch(delay_secs); } diff --git a/tools/perf/ui/util.c b/tools/perf/ui/util.c index 63bf06e80ab9..9ed76e88a3e4 100644 --- a/tools/perf/ui/util.c +++ b/tools/perf/ui/util.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include "util.h" -#include "../debug.h" +#include "../util/debug.h" /* diff --git a/tools/perf/ui/util.h b/tools/perf/ui/util.h index 5e44223b56fa..40891942f465 100644 --- a/tools/perf/ui/util.h +++ b/tools/perf/ui/util.h @@ -8,6 +8,8 @@ int ui__getch(int delay_secs); int ui__popup_menu(int argc, char * const argv[]); int ui__help_window(const char *text); int ui__dialog_yesno(const char *msg); +void __ui__info_window(const char *title, const char *text, const char *exit_msg); +void ui__info_window(const char *title, const char *text); int ui__question_window(const char *title, const char *text, const char *exit_msg, int delay_secs); diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 14f812bb07a7..b922c8c297ca 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -9,6 +9,7 @@ perf-y += event.o perf-y += evlist.o perf-y += evsel.o perf-y += evsel_fprintf.o +perf-y += evswitch.o perf-y += find_bit.o perf-y += get_current_dir_name.o perf-y += kallsyms.o @@ -26,7 +27,6 @@ perf-y += rbtree.o perf-y += libstring.o perf-y += bitmap.o perf-y += hweight.o -perf-y += zalloc.o perf-y += smt.o perf-y += strbuf.o perf-y += string.o @@ -70,7 +70,6 @@ perf-y += svghelper.o perf-y += sort.o perf-y += hist.o perf-y += util.o -perf-y += xyarray.o perf-y += cpumap.o perf-y += cputopo.o perf-y += cgroup.o @@ -150,6 +149,8 @@ perf-$(CONFIG_ZLIB) += zlib.o perf-$(CONFIG_LZMA) += lzma.o perf-$(CONFIG_ZSTD) += zstd.o +perf-$(CONFIG_LIBCAP) += cap.o + perf-y += demangle-java.o perf-y += demangle-rust.o @@ -243,7 +244,3 @@ $(OUTPUT)util/hweight.o: ../lib/hweight.c FORCE $(OUTPUT)util/vsprintf.o: ../lib/vsprintf.c FORCE $(call rule_mkdir) $(call if_changed_dep,cc_o_c) - -$(OUTPUT)util/zalloc.o: ../lib/zalloc.c FORCE - $(call rule_mkdir) - $(call if_changed_dep,cc_o_c) diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 163536720149..e0518dc4c4d2 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -929,14 +929,14 @@ alloc_histograms: } static int symbol__inc_addr_samples(struct symbol *sym, struct map *map, - struct perf_evsel *evsel, u64 addr, + struct evsel *evsel, u64 addr, struct perf_sample *sample) { struct annotated_source *src; if (sym == NULL) return 0; - src = symbol__hists(sym, evsel->evlist->nr_entries); + src = symbol__hists(sym, evsel->evlist->core.nr_entries); return (src) ? __symbol__inc_addr_samples(sym, map, src, evsel->idx, addr, sample) : 0; } @@ -1080,13 +1080,13 @@ void annotation__compute_ipc(struct annotation *notes, size_t size) } int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, struct perf_sample *sample, - struct perf_evsel *evsel) + struct evsel *evsel) { return symbol__inc_addr_samples(ams->sym, ams->map, evsel, ams->al_addr, sample); } int hist_entry__inc_addr_samples(struct hist_entry *he, struct perf_sample *sample, - struct perf_evsel *evsel, u64 ip) + struct evsel *evsel, u64 ip) { return symbol__inc_addr_samples(he->ms.sym, he->ms.map, evsel, ip, sample); } @@ -1134,7 +1134,7 @@ struct annotate_args { size_t privsize; struct arch *arch; struct map_symbol ms; - struct perf_evsel *evsel; + struct evsel *evsel; struct annotation_options *options; s64 offset; char *line; @@ -1165,12 +1165,12 @@ static struct annotation_line * annotation_line__new(struct annotate_args *args, size_t privsize) { struct annotation_line *al; - struct perf_evsel *evsel = args->evsel; + struct evsel *evsel = args->evsel; size_t size = privsize + sizeof(*al); int nr = 1; if (perf_evsel__is_group_event(evsel)) - nr = evsel->nr_members; + nr = evsel->core.nr_members; size += sizeof(al->data[0]) * nr; @@ -1359,7 +1359,7 @@ static int disasm_line__print(struct disasm_line *dl, u64 start, int addr_fmt_wi static int annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start, - struct perf_evsel *evsel, u64 len, int min_pcnt, int printed, + struct evsel *evsel, u64 len, int min_pcnt, int printed, int max_lines, struct annotation_line *queue, int addr_fmt_width, int percent_type) { @@ -1448,7 +1448,7 @@ annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start return -1; if (perf_evsel__is_group_event(evsel)) - width *= evsel->nr_members; + width *= evsel->core.nr_members; if (!*al->line) printf(" %*s:\n", width, " "); @@ -2011,10 +2011,10 @@ static void calc_percent(struct sym_hist *sym_hist, } static void annotation__calc_percent(struct annotation *notes, - struct perf_evsel *leader, s64 len) + struct evsel *leader, s64 len) { struct annotation_line *al, *next; - struct perf_evsel *evsel; + struct evsel *evsel; list_for_each_entry(al, ¬es->src->source, node) { s64 end; @@ -2041,7 +2041,7 @@ static void annotation__calc_percent(struct annotation *notes, } } -void symbol__calc_percent(struct symbol *sym, struct perf_evsel *evsel) +void symbol__calc_percent(struct symbol *sym, struct evsel *evsel) { struct annotation *notes = symbol__annotation(sym); @@ -2049,7 +2049,7 @@ void symbol__calc_percent(struct symbol *sym, struct perf_evsel *evsel) } int symbol__annotate(struct symbol *sym, struct map *map, - struct perf_evsel *evsel, size_t privsize, + struct evsel *evsel, size_t privsize, struct annotation_options *options, struct arch **parch) { @@ -2214,7 +2214,7 @@ static void print_summary(struct rb_root *root, const char *filename) } } -static void symbol__annotate_hits(struct symbol *sym, struct perf_evsel *evsel) +static void symbol__annotate_hits(struct symbol *sym, struct evsel *evsel) { struct annotation *notes = symbol__annotation(sym); struct sym_hist *h = annotation__histogram(notes, evsel->idx); @@ -2241,7 +2241,7 @@ static int annotated_source__addr_fmt_width(struct list_head *lines, u64 start) } int symbol__annotate_printf(struct symbol *sym, struct map *map, - struct perf_evsel *evsel, + struct evsel *evsel, struct annotation_options *opts) { struct dso *dso = map->dso; @@ -2272,7 +2272,7 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map, len = symbol__size(sym); if (perf_evsel__is_group_event(evsel)) { - width *= evsel->nr_members; + width *= evsel->core.nr_members; perf_evsel__group_desc(evsel, buf, sizeof(buf)); evsel_name = buf; } @@ -2405,7 +2405,7 @@ static int symbol__annotate_fprintf2(struct symbol *sym, FILE *fp, return 0; } -int map_symbol__annotation_dump(struct map_symbol *ms, struct perf_evsel *evsel, +int map_symbol__annotation_dump(struct map_symbol *ms, struct evsel *evsel, struct annotation_options *opts) { const char *ev_name = perf_evsel__name(evsel); @@ -2657,7 +2657,7 @@ static void symbol__calc_lines(struct symbol *sym, struct map *map, } int symbol__tty_annotate2(struct symbol *sym, struct map *map, - struct perf_evsel *evsel, + struct evsel *evsel, struct annotation_options *opts) { struct dso *dso = map->dso; @@ -2685,7 +2685,7 @@ int symbol__tty_annotate2(struct symbol *sym, struct map *map, } int symbol__tty_annotate(struct symbol *sym, struct map *map, - struct perf_evsel *evsel, + struct evsel *evsel, struct annotation_options *opts) { struct dso *dso = map->dso; @@ -2956,7 +2956,7 @@ void annotation_line__write(struct annotation_line *al, struct annotation *notes wops->write_graph); } -int symbol__annotate2(struct symbol *sym, struct map *map, struct perf_evsel *evsel, +int symbol__annotate2(struct symbol *sym, struct map *map, struct evsel *evsel, struct annotation_options *options, struct arch **parch) { struct annotation *notes = symbol__annotation(sym); @@ -2968,7 +2968,7 @@ int symbol__annotate2(struct symbol *sym, struct map *map, struct perf_evsel *ev return -1; if (perf_evsel__is_group_event(evsel)) - nr_pcnt = evsel->nr_members; + nr_pcnt = evsel->core.nr_members; err = symbol__annotate(sym, map, evsel, 0, options, parch); if (err) diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index 5bc0cf655d37..d94be9140e31 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -20,7 +20,7 @@ struct map_symbol; struct addr_map_symbol; struct option; struct perf_sample; -struct perf_evsel; +struct evsel; struct symbol; struct ins { @@ -216,12 +216,12 @@ void annotation_line__write(struct annotation_line *al, struct annotation *notes int __annotation__scnprintf_samples_period(struct annotation *notes, char *bf, size_t size, - struct perf_evsel *evsel, + struct evsel *evsel, bool show_freq); int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw, int max_ins_name); size_t disasm__fprintf(struct list_head *head, FILE *fp); -void symbol__calc_percent(struct symbol *sym, struct perf_evsel *evsel); +void symbol__calc_percent(struct symbol *sym, struct evsel *evsel); struct sym_hist { u64 nr_samples; @@ -245,7 +245,7 @@ struct cyc_hist { /** struct annotated_source - symbols with hits have this attached as in sannotation * * @histograms: Array of addr hit histograms per event being monitored - * nr_histograms: This may not be the same as evsel->evlist->nr_entries if + * nr_histograms: This may not be the same as evsel->evlist->core.nr_entries if * we have more than a group in a evlist, where we will want * to see each group separately, that is why symbol__annotate2() * sets src->nr_histograms to evsel->nr_members. @@ -335,24 +335,24 @@ static inline struct annotation *symbol__annotation(struct symbol *sym) } int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, struct perf_sample *sample, - struct perf_evsel *evsel); + struct evsel *evsel); int addr_map_symbol__account_cycles(struct addr_map_symbol *ams, struct addr_map_symbol *start, unsigned cycles); int hist_entry__inc_addr_samples(struct hist_entry *he, struct perf_sample *sample, - struct perf_evsel *evsel, u64 addr); + struct evsel *evsel, u64 addr); struct annotated_source *symbol__hists(struct symbol *sym, int nr_hists); void symbol__annotate_zero_histograms(struct symbol *sym); int symbol__annotate(struct symbol *sym, struct map *map, - struct perf_evsel *evsel, size_t privsize, + struct evsel *evsel, size_t privsize, struct annotation_options *options, struct arch **parch); int symbol__annotate2(struct symbol *sym, struct map *map, - struct perf_evsel *evsel, + struct evsel *evsel, struct annotation_options *options, struct arch **parch); @@ -378,32 +378,32 @@ int symbol__strerror_disassemble(struct symbol *sym, struct map *map, int errnum, char *buf, size_t buflen); int symbol__annotate_printf(struct symbol *sym, struct map *map, - struct perf_evsel *evsel, + struct evsel *evsel, struct annotation_options *options); void symbol__annotate_zero_histogram(struct symbol *sym, int evidx); void symbol__annotate_decay_histogram(struct symbol *sym, int evidx); void annotated_source__purge(struct annotated_source *as); -int map_symbol__annotation_dump(struct map_symbol *ms, struct perf_evsel *evsel, +int map_symbol__annotation_dump(struct map_symbol *ms, struct evsel *evsel, struct annotation_options *opts); bool ui__has_annotation(void); int symbol__tty_annotate(struct symbol *sym, struct map *map, - struct perf_evsel *evsel, struct annotation_options *opts); + struct evsel *evsel, struct annotation_options *opts); int symbol__tty_annotate2(struct symbol *sym, struct map *map, - struct perf_evsel *evsel, struct annotation_options *opts); + struct evsel *evsel, struct annotation_options *opts); #ifdef HAVE_SLANG_SUPPORT int symbol__tui_annotate(struct symbol *sym, struct map *map, - struct perf_evsel *evsel, + struct evsel *evsel, struct hist_browser_timer *hbt, struct annotation_options *opts); #else static inline int symbol__tui_annotate(struct symbol *sym __maybe_unused, struct map *map __maybe_unused, - struct perf_evsel *evsel __maybe_unused, + struct evsel *evsel __maybe_unused, struct hist_browser_timer *hbt __maybe_unused, struct annotation_options *opts __maybe_unused) { diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index ec0af36697c4..094e6ceb3cf2 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -124,20 +124,20 @@ void auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp, } void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp, - struct perf_evlist *evlist, int idx, + struct evlist *evlist, int idx, bool per_cpu) { mp->idx = idx; if (per_cpu) { - mp->cpu = evlist->cpus->map[idx]; - if (evlist->threads) - mp->tid = thread_map__pid(evlist->threads, 0); + mp->cpu = evlist->core.cpus->map[idx]; + if (evlist->core.threads) + mp->tid = perf_thread_map__pid(evlist->core.threads, 0); else mp->tid = -1; } else { mp->cpu = -1; - mp->tid = thread_map__pid(evlist->threads, idx); + mp->tid = perf_thread_map__pid(evlist->core.threads, idx); } } @@ -503,7 +503,7 @@ void auxtrace_heap__pop(struct auxtrace_heap *heap) } size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr, - struct perf_evlist *evlist) + struct evlist *evlist) { if (itr) return itr->info_priv_size(itr, evlist); @@ -539,9 +539,9 @@ int auxtrace_record__snapshot_start(struct auxtrace_record *itr) return 0; } -int auxtrace_record__snapshot_finish(struct auxtrace_record *itr) +int auxtrace_record__snapshot_finish(struct auxtrace_record *itr, bool on_exit) { - if (itr && itr->snapshot_finish) + if (!on_exit && itr && itr->snapshot_finish) return itr->snapshot_finish(itr); return 0; } @@ -556,7 +556,7 @@ int auxtrace_record__find_snapshot(struct auxtrace_record *itr, int idx, } int auxtrace_record__options(struct auxtrace_record *itr, - struct perf_evlist *evlist, + struct evlist *evlist, struct record_opts *opts) { if (itr) @@ -577,6 +577,16 @@ int auxtrace_parse_snapshot_options(struct auxtrace_record *itr, if (!str) return 0; + /* PMU-agnostic options */ + switch (*str) { + case 'e': + opts->auxtrace_snapshot_on_exit = true; + str++; + break; + default: + break; + } + if (itr) return itr->parse_snapshot_options(itr, opts, str); @@ -585,7 +595,7 @@ int auxtrace_parse_snapshot_options(struct auxtrace_record *itr, } struct auxtrace_record *__weak -auxtrace_record__init(struct perf_evlist *evlist __maybe_unused, int *err) +auxtrace_record__init(struct evlist *evlist __maybe_unused, int *err) { *err = 0; return NULL; @@ -964,6 +974,7 @@ void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts, synth_opts->transactions = true; synth_opts->ptwrites = true; synth_opts->pwr_events = true; + synth_opts->other_events = true; synth_opts->errors = true; if (no_sample) { synth_opts->period_type = PERF_ITRACE_PERIOD_INSTRUCTIONS; @@ -1061,6 +1072,9 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str, case 'p': synth_opts->pwr_events = true; break; + case 'o': + synth_opts->other_events = true; + break; case 'e': synth_opts->errors = true; break; @@ -2084,7 +2098,7 @@ static char *addr_filter__to_str(struct addr_filter *filt) return err < 0 ? NULL : filter; } -static int parse_addr_filter(struct perf_evsel *evsel, const char *filter, +static int parse_addr_filter(struct evsel *evsel, const char *filter, int max_nr) { struct addr_filters filts; @@ -2135,19 +2149,19 @@ out_exit: return err; } -static struct perf_pmu *perf_evsel__find_pmu(struct perf_evsel *evsel) +static struct perf_pmu *perf_evsel__find_pmu(struct evsel *evsel) { struct perf_pmu *pmu = NULL; while ((pmu = perf_pmu__scan(pmu)) != NULL) { - if (pmu->type == evsel->attr.type) + if (pmu->type == evsel->core.attr.type) break; } return pmu; } -static int perf_evsel__nr_addr_filter(struct perf_evsel *evsel) +static int perf_evsel__nr_addr_filter(struct evsel *evsel) { struct perf_pmu *pmu = perf_evsel__find_pmu(evsel); int nr_addr_filters = 0; @@ -2160,9 +2174,9 @@ static int perf_evsel__nr_addr_filter(struct perf_evsel *evsel) return nr_addr_filters; } -int auxtrace_parse_filters(struct perf_evlist *evlist) +int auxtrace_parse_filters(struct evlist *evlist) { - struct perf_evsel *evsel; + struct evsel *evsel; char *filter; int err, max_nr; diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h index e9b4c5edf78b..8e637ac3918e 100644 --- a/tools/perf/util/auxtrace.h +++ b/tools/perf/util/auxtrace.h @@ -23,7 +23,7 @@ union perf_event; struct perf_session; -struct perf_evlist; +struct evlist; struct perf_tool; struct perf_mmap; struct option; @@ -60,6 +60,8 @@ enum itrace_period_type { * @transactions: whether to synthesize events for transactions * @ptwrites: whether to synthesize events for ptwrites * @pwr_events: whether to synthesize power events + * @other_events: whether to synthesize other events recorded due to the use of + * aux_output * @errors: whether to synthesize decoder error events * @dont_decode: whether to skip decoding entirely * @log: write a decoding log @@ -86,6 +88,7 @@ struct itrace_synth_opts { bool transactions; bool ptwrites; bool pwr_events; + bool other_events; bool errors; bool dont_decode; bool log; @@ -309,10 +312,10 @@ struct auxtrace_mmap_params { */ struct auxtrace_record { int (*recording_options)(struct auxtrace_record *itr, - struct perf_evlist *evlist, + struct evlist *evlist, struct record_opts *opts); size_t (*info_priv_size)(struct auxtrace_record *itr, - struct perf_evlist *evlist); + struct evlist *evlist); int (*info_fill)(struct auxtrace_record *itr, struct perf_session *session, struct auxtrace_info_event *auxtrace_info, @@ -432,7 +435,7 @@ void auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp, unsigned int auxtrace_pages, bool auxtrace_overwrite); void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp, - struct perf_evlist *evlist, int idx, + struct evlist *evlist, int idx, bool per_cpu); typedef int (*process_auxtrace_t)(struct perf_tool *tool, @@ -482,24 +485,24 @@ int auxtrace_cache__add(struct auxtrace_cache *c, u32 key, struct auxtrace_cache_entry *entry); void *auxtrace_cache__lookup(struct auxtrace_cache *c, u32 key); -struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist, +struct auxtrace_record *auxtrace_record__init(struct evlist *evlist, int *err); int auxtrace_parse_snapshot_options(struct auxtrace_record *itr, struct record_opts *opts, const char *str); int auxtrace_record__options(struct auxtrace_record *itr, - struct perf_evlist *evlist, + struct evlist *evlist, struct record_opts *opts); size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr, - struct perf_evlist *evlist); + struct evlist *evlist); int auxtrace_record__info_fill(struct auxtrace_record *itr, struct perf_session *session, struct auxtrace_info_event *auxtrace_info, size_t priv_size); void auxtrace_record__free(struct auxtrace_record *itr); int auxtrace_record__snapshot_start(struct auxtrace_record *itr); -int auxtrace_record__snapshot_finish(struct auxtrace_record *itr); +int auxtrace_record__snapshot_finish(struct auxtrace_record *itr, bool on_exit); int auxtrace_record__find_snapshot(struct auxtrace_record *itr, int idx, struct auxtrace_mmap *mm, unsigned char *data, u64 *head, u64 *old); @@ -540,7 +543,7 @@ void addr_filters__init(struct addr_filters *filts); void addr_filters__exit(struct addr_filters *filts); int addr_filters__parse_bare_filter(struct addr_filters *filts, const char *filter); -int auxtrace_parse_filters(struct perf_evlist *evlist); +int auxtrace_parse_filters(struct evlist *evlist); static inline int auxtrace__process_event(struct perf_session *session, union perf_event *event, @@ -613,7 +616,7 @@ void itrace_synth_opts__clear_time_range(struct itrace_synth_opts *opts) #else static inline struct auxtrace_record * -auxtrace_record__init(struct perf_evlist *evlist __maybe_unused, +auxtrace_record__init(struct evlist *evlist __maybe_unused, int *err) { *err = 0; @@ -636,7 +639,7 @@ perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr __maybe_unused, static inline int auxtrace_record__options(struct auxtrace_record *itr __maybe_unused, - struct perf_evlist *evlist __maybe_unused, + struct evlist *evlist __maybe_unused, struct record_opts *opts __maybe_unused) { return 0; @@ -733,7 +736,7 @@ void auxtrace_index__free(struct list_head *head __maybe_unused) } static inline -int auxtrace_parse_filters(struct perf_evlist *evlist __maybe_unused) +int auxtrace_parse_filters(struct evlist *evlist __maybe_unused) { return 0; } @@ -747,7 +750,7 @@ void auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp, unsigned int auxtrace_pages, bool auxtrace_overwrite); void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp, - struct perf_evlist *evlist, int idx, + struct evlist *evlist, int idx, bool per_cpu); #define ITRACE_HELP "" diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c index 2a4a0da35632..5a5dcc6d8f85 100644 --- a/tools/perf/util/bpf-event.c +++ b/tools/perf/util/bpf-event.c @@ -418,7 +418,7 @@ static int bpf_event__sb_cb(union perf_event *event, void *data) return 0; } -int bpf_event__add_sb_event(struct perf_evlist **evlist, +int bpf_event__add_sb_event(struct evlist **evlist, struct perf_env *env) { struct perf_event_attr attr = { diff --git a/tools/perf/util/bpf-event.h b/tools/perf/util/bpf-event.h index 04c33b3bfe28..26ab9239f986 100644 --- a/tools/perf/util/bpf-event.h +++ b/tools/perf/util/bpf-event.h @@ -37,7 +37,7 @@ int perf_event__synthesize_bpf_events(struct perf_session *session, perf_event__handler_t process, struct machine *machine, struct record_opts *opts); -int bpf_event__add_sb_event(struct perf_evlist **evlist, +int bpf_event__add_sb_event(struct evlist **evlist, struct perf_env *env); void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info, struct perf_env *env, @@ -58,7 +58,7 @@ static inline int perf_event__synthesize_bpf_events(struct perf_session *session return 0; } -static inline int bpf_event__add_sb_event(struct perf_evlist **evlist __maybe_unused, +static inline int bpf_event__add_sb_event(struct evlist **evlist __maybe_unused, struct perf_env *env __maybe_unused) { return 0; diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c index c61974a50aa5..e20d7c5e1925 100644 --- a/tools/perf/util/bpf-loader.c +++ b/tools/perf/util/bpf-loader.c @@ -26,6 +26,8 @@ #include "llvm-utils.h" #include "c++/clang-c.h" +#include <internal/xyarray.h> + static int libbpf_perf_print(enum libbpf_print_level level __attribute__((unused)), const char *fmt, va_list args) { @@ -763,7 +765,7 @@ int bpf__foreach_event(struct bpf_object *obj, if (priv->is_tp) { fd = bpf_program__fd(prog); - err = (*func)(priv->sys_name, priv->evt_name, fd, arg); + err = (*func)(priv->sys_name, priv->evt_name, fd, obj, arg); if (err) { pr_debug("bpf: tracepoint call back failed, stop iterate\n"); return err; @@ -788,7 +790,7 @@ int bpf__foreach_event(struct bpf_object *obj, return fd; } - err = (*func)(tev->group, tev->event, fd, arg); + err = (*func)(tev->group, tev->event, fd, obj, arg); if (err) { pr_debug("bpf: call back failed, stop iterate\n"); return err; @@ -817,7 +819,7 @@ struct bpf_map_op { } k; union { u64 value; - struct perf_evsel *evsel; + struct evsel *evsel; } v; }; @@ -1043,7 +1045,7 @@ __bpf_map__config_value(struct bpf_map *map, static int bpf_map__config_value(struct bpf_map *map, struct parse_events_term *term, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { if (!term->err_val) { pr_debug("Config value not set\n"); @@ -1061,9 +1063,9 @@ bpf_map__config_value(struct bpf_map *map, static int __bpf_map__config_event(struct bpf_map *map, struct parse_events_term *term, - struct perf_evlist *evlist) + struct evlist *evlist) { - struct perf_evsel *evsel; + struct evsel *evsel; const struct bpf_map_def *def; struct bpf_map_op *op; const char *map_name = bpf_map__name(map); @@ -1103,7 +1105,7 @@ __bpf_map__config_event(struct bpf_map *map, static int bpf_map__config_event(struct bpf_map *map, struct parse_events_term *term, - struct perf_evlist *evlist) + struct evlist *evlist) { if (!term->err_val) { pr_debug("Config value not set\n"); @@ -1121,7 +1123,7 @@ bpf_map__config_event(struct bpf_map *map, struct bpf_obj_config__map_func { const char *config_opt; int (*config_func)(struct bpf_map *, struct parse_events_term *, - struct perf_evlist *); + struct evlist *); }; struct bpf_obj_config__map_func bpf_obj_config__map_funcs[] = { @@ -1169,7 +1171,7 @@ config_map_indices_range_check(struct parse_events_term *term, static int bpf__obj_config_map(struct bpf_object *obj, struct parse_events_term *term, - struct perf_evlist *evlist, + struct evlist *evlist, int *key_scan_pos) { /* key is "map:<mapname>.<config opt>" */ @@ -1228,7 +1230,7 @@ out: int bpf__config_obj(struct bpf_object *obj, struct parse_events_term *term, - struct perf_evlist *evlist, + struct evlist *evlist, int *error_pos) { int key_scan_pos = 0; @@ -1401,9 +1403,9 @@ apply_config_value_for_key(int map_fd, void *pkey, static int apply_config_evsel_for_key(const char *name, int map_fd, void *pkey, - struct perf_evsel *evsel) + struct evsel *evsel) { - struct xyarray *xy = evsel->fd; + struct xyarray *xy = evsel->core.fd; struct perf_event_attr *attr; unsigned int key, events; bool check_pass = false; @@ -1421,7 +1423,7 @@ apply_config_evsel_for_key(const char *name, int map_fd, void *pkey, return -BPF_LOADER_ERRNO__OBJCONF_MAP_EVTDIM; } - attr = &evsel->attr; + attr = &evsel->core.attr; if (attr->inherit) { pr_debug("ERROR: Can't put inherit event into map %s\n", name); return -BPF_LOADER_ERRNO__OBJCONF_MAP_EVTINH; @@ -1523,11 +1525,11 @@ int bpf__apply_obj_config(void) (strcmp(name, \ bpf_map__name(pos)) == 0)) -struct perf_evsel *bpf__setup_output_event(struct perf_evlist *evlist, const char *name) +struct evsel *bpf__setup_output_event(struct evlist *evlist, const char *name) { struct bpf_map_priv *tmpl_priv = NULL; struct bpf_object *obj, *tmp; - struct perf_evsel *evsel = NULL; + struct evsel *evsel = NULL; struct bpf_map *map; int err; bool need_init = false; @@ -1600,9 +1602,9 @@ struct perf_evsel *bpf__setup_output_event(struct perf_evlist *evlist, const cha return evsel; } -int bpf__setup_stdout(struct perf_evlist *evlist) +int bpf__setup_stdout(struct evlist *evlist) { - struct perf_evsel *evsel = bpf__setup_output_event(evlist, "__bpf_stdout__"); + struct evsel *evsel = bpf__setup_output_event(evlist, "__bpf_stdout__"); return PTR_ERR_OR_ZERO(evsel); } @@ -1756,7 +1758,7 @@ int bpf__strerror_load(struct bpf_object *obj, int bpf__strerror_config_obj(struct bpf_object *obj __maybe_unused, struct parse_events_term *term __maybe_unused, - struct perf_evlist *evlist __maybe_unused, + struct evlist *evlist __maybe_unused, int *error_pos __maybe_unused, int err, char *buf, size_t size) { @@ -1780,7 +1782,7 @@ int bpf__strerror_apply_obj_config(int err, char *buf, size_t size) return 0; } -int bpf__strerror_setup_output_event(struct perf_evlist *evlist __maybe_unused, +int bpf__strerror_setup_output_event(struct evlist *evlist __maybe_unused, int err, char *buf, size_t size) { bpf__strerror_head(err, buf, size); diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h index 3f46856e3330..25251d63164c 100644 --- a/tools/perf/util/bpf-loader.h +++ b/tools/perf/util/bpf-loader.h @@ -39,14 +39,14 @@ enum bpf_loader_errno { __BPF_LOADER_ERRNO__END, }; -struct perf_evsel; -struct perf_evlist; +struct evsel; +struct evlist; struct bpf_object; struct parse_events_term; #define PERF_BPF_PROBE_GROUP "perf_bpf_probe" typedef int (*bpf_prog_iter_callback_t)(const char *group, const char *event, - int fd, void *arg); + int fd, struct bpf_object *obj, void *arg); #ifdef HAVE_LIBBPF_SUPPORT struct bpf_object *bpf__prepare_load(const char *filename, bool source); @@ -70,18 +70,18 @@ int bpf__foreach_event(struct bpf_object *obj, bpf_prog_iter_callback_t func, void *arg); int bpf__config_obj(struct bpf_object *obj, struct parse_events_term *term, - struct perf_evlist *evlist, int *error_pos); + struct evlist *evlist, int *error_pos); int bpf__strerror_config_obj(struct bpf_object *obj, struct parse_events_term *term, - struct perf_evlist *evlist, + struct evlist *evlist, int *error_pos, int err, char *buf, size_t size); int bpf__apply_obj_config(void); int bpf__strerror_apply_obj_config(int err, char *buf, size_t size); -int bpf__setup_stdout(struct perf_evlist *evlist); -struct perf_evsel *bpf__setup_output_event(struct perf_evlist *evlist, const char *name); -int bpf__strerror_setup_output_event(struct perf_evlist *evlist, int err, char *buf, size_t size); +int bpf__setup_stdout(struct evlist *evlist); +struct evsel *bpf__setup_output_event(struct evlist *evlist, const char *name); +int bpf__strerror_setup_output_event(struct evlist *evlist, int err, char *buf, size_t size); #else #include <errno.h> #include <string.h> @@ -119,7 +119,7 @@ bpf__foreach_event(struct bpf_object *obj __maybe_unused, static inline int bpf__config_obj(struct bpf_object *obj __maybe_unused, struct parse_events_term *term __maybe_unused, - struct perf_evlist *evlist __maybe_unused, + struct evlist *evlist __maybe_unused, int *error_pos __maybe_unused) { return 0; @@ -132,13 +132,13 @@ bpf__apply_obj_config(void) } static inline int -bpf__setup_stdout(struct perf_evlist *evlist __maybe_unused) +bpf__setup_stdout(struct evlist *evlist __maybe_unused) { return 0; } -static inline struct perf_evsel * -bpf__setup_output_event(struct perf_evlist *evlist __maybe_unused, const char *name __maybe_unused) +static inline struct evsel * +bpf__setup_output_event(struct evlist *evlist __maybe_unused, const char *name __maybe_unused) { return NULL; } @@ -182,7 +182,7 @@ static inline int bpf__strerror_load(struct bpf_object *obj __maybe_unused, static inline int bpf__strerror_config_obj(struct bpf_object *obj __maybe_unused, struct parse_events_term *term __maybe_unused, - struct perf_evlist *evlist __maybe_unused, + struct evlist *evlist __maybe_unused, int *error_pos __maybe_unused, int err __maybe_unused, char *buf, size_t size) @@ -198,7 +198,7 @@ bpf__strerror_apply_obj_config(int err __maybe_unused, } static inline int -bpf__strerror_setup_output_event(struct perf_evlist *evlist __maybe_unused, +bpf__strerror_setup_output_event(struct evlist *evlist __maybe_unused, int err __maybe_unused, char *buf, size_t size) { return __bpf_strerror(buf, size); @@ -206,7 +206,7 @@ bpf__strerror_setup_output_event(struct perf_evlist *evlist __maybe_unused, #endif -static inline int bpf__strerror_setup_stdout(struct perf_evlist *evlist, int err, char *buf, size_t size) +static inline int bpf__strerror_setup_stdout(struct evlist *evlist, int err, char *buf, size_t size) { return bpf__strerror_setup_output_event(evlist, err, buf, size); } diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index f1abfab7aa8c..b98754863de9 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -37,7 +37,7 @@ static bool no_buildid_cache; int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample, - struct perf_evsel *evsel __maybe_unused, + struct evsel *evsel __maybe_unused, struct machine *machine) { struct addr_location al; diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h index 93668f38f1ed..aad419bb165c 100644 --- a/tools/perf/util/build-id.h +++ b/tools/perf/util/build-id.h @@ -24,7 +24,7 @@ char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size, bool is_debug); int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event, - struct perf_sample *sample, struct perf_evsel *evsel, + struct perf_sample *sample, struct evsel *evsel, struct machine *machine); int dsos__hit_all(struct perf_session *session); diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 8d7d8f62fcca..d077704f9afa 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -1077,7 +1077,7 @@ int callchain_cursor_append(struct callchain_cursor *cursor, int sample__resolve_callchain(struct perf_sample *sample, struct callchain_cursor *cursor, struct symbol **parent, - struct perf_evsel *evsel, struct addr_location *al, + struct evsel *evsel, struct addr_location *al, int max_stack) { if (sample->callchain == NULL && !symbol_conf.show_branchflag_count) diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index 80e056a3d882..45b9ed49e2b1 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -236,7 +236,7 @@ int record_opts__parse_callchain(struct record_opts *record, int sample__resolve_callchain(struct perf_sample *sample, struct callchain_cursor *cursor, struct symbol **parent, - struct perf_evsel *evsel, struct addr_location *al, + struct evsel *evsel, struct addr_location *al, int max_stack); int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *sample); int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *node, diff --git a/tools/perf/util/cap.c b/tools/perf/util/cap.c new file mode 100644 index 000000000000..c3ba841bbf37 --- /dev/null +++ b/tools/perf/util/cap.c @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Capability utilities + */ + +#ifdef HAVE_LIBCAP_SUPPORT + +#include "cap.h" +#include <stdbool.h> +#include <sys/capability.h> + +bool perf_cap__capable(cap_value_t cap) +{ + cap_flag_value_t val; + cap_t caps = cap_get_proc(); + + if (!caps) + return false; + + if (cap_get_flag(caps, cap, CAP_EFFECTIVE, &val) != 0) + val = CAP_CLEAR; + + if (cap_free(caps) != 0) + return false; + + return val == CAP_SET; +} + +#endif /* HAVE_LIBCAP_SUPPORT */ diff --git a/tools/perf/util/cap.h b/tools/perf/util/cap.h new file mode 100644 index 000000000000..051dc590ceee --- /dev/null +++ b/tools/perf/util/cap.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PERF_CAP_H +#define __PERF_CAP_H + +#include <stdbool.h> +#include <linux/capability.h> +#include <linux/compiler.h> + +#ifdef HAVE_LIBCAP_SUPPORT + +#include <sys/capability.h> + +bool perf_cap__capable(cap_value_t cap); + +#else + +#include <unistd.h> +#include <sys/types.h> + +static inline bool perf_cap__capable(int cap __maybe_unused) +{ + return geteuid() == 0; +} + +#endif /* HAVE_LIBCAP_SUPPORT */ + +/* For older systems */ +#ifndef CAP_SYSLOG +#define CAP_SYSLOG 34 +#endif + +#endif /* __PERF_CAP_H */ diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c index 484c29830a81..f73599f271ff 100644 --- a/tools/perf/util/cgroup.c +++ b/tools/perf/util/cgroup.c @@ -90,9 +90,9 @@ static int open_cgroup(const char *name) return fd; } -static struct cgroup *evlist__find_cgroup(struct perf_evlist *evlist, const char *str) +static struct cgroup *evlist__find_cgroup(struct evlist *evlist, const char *str) { - struct perf_evsel *counter; + struct evsel *counter; /* * check if cgrp is already defined, if so we reuse it */ @@ -130,16 +130,16 @@ out_err: return NULL; } -struct cgroup *evlist__findnew_cgroup(struct perf_evlist *evlist, const char *name) +struct cgroup *evlist__findnew_cgroup(struct evlist *evlist, const char *name) { struct cgroup *cgroup = evlist__find_cgroup(evlist, name); return cgroup ?: cgroup__new(name); } -static int add_cgroup(struct perf_evlist *evlist, const char *str) +static int add_cgroup(struct evlist *evlist, const char *str) { - struct perf_evsel *counter; + struct evsel *counter; struct cgroup *cgrp = evlist__findnew_cgroup(evlist, str); int n; @@ -184,15 +184,15 @@ struct cgroup *cgroup__get(struct cgroup *cgroup) return cgroup; } -static void evsel__set_default_cgroup(struct perf_evsel *evsel, struct cgroup *cgroup) +static void evsel__set_default_cgroup(struct evsel *evsel, struct cgroup *cgroup) { if (evsel->cgrp == NULL) evsel->cgrp = cgroup__get(cgroup); } -void evlist__set_default_cgroup(struct perf_evlist *evlist, struct cgroup *cgroup) +void evlist__set_default_cgroup(struct evlist *evlist, struct cgroup *cgroup) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) evsel__set_default_cgroup(evsel, cgroup); @@ -201,14 +201,14 @@ void evlist__set_default_cgroup(struct perf_evlist *evlist, struct cgroup *cgrou int parse_cgroups(const struct option *opt, const char *str, int unset __maybe_unused) { - struct perf_evlist *evlist = *(struct perf_evlist **)opt->value; - struct perf_evsel *counter; + struct evlist *evlist = *(struct evlist **)opt->value; + struct evsel *counter; struct cgroup *cgrp = NULL; const char *p, *e, *eos = str + strlen(str); char *s; int ret, i; - if (list_empty(&evlist->entries)) { + if (list_empty(&evlist->core.entries)) { fprintf(stderr, "must define events before cgroups\n"); return -1; } diff --git a/tools/perf/util/cgroup.h b/tools/perf/util/cgroup.h index f033a80c1b14..2ec11f01090d 100644 --- a/tools/perf/util/cgroup.h +++ b/tools/perf/util/cgroup.h @@ -18,11 +18,11 @@ extern int nr_cgroups; /* number of explicit cgroups defined */ struct cgroup *cgroup__get(struct cgroup *cgroup); void cgroup__put(struct cgroup *cgroup); -struct perf_evlist; +struct evlist; -struct cgroup *evlist__findnew_cgroup(struct perf_evlist *evlist, const char *name); +struct cgroup *evlist__findnew_cgroup(struct evlist *evlist, const char *name); -void evlist__set_default_cgroup(struct perf_evlist *evlist, struct cgroup *cgroup); +void evlist__set_default_cgroup(struct evlist *evlist, struct cgroup *cgroup); int parse_cgroups(const struct option *opt, const char *str, int unset); diff --git a/tools/perf/util/counts.c b/tools/perf/util/counts.c index 88be9c4365e0..f94e1a23dad6 100644 --- a/tools/perf/util/counts.c +++ b/tools/perf/util/counts.c @@ -19,6 +19,15 @@ struct perf_counts *perf_counts__new(int ncpus, int nthreads) } counts->values = values; + + values = xyarray__new(ncpus, nthreads, sizeof(bool)); + if (!values) { + xyarray__delete(counts->values); + free(counts); + return NULL; + } + + counts->loaded = values; } return counts; @@ -27,6 +36,7 @@ struct perf_counts *perf_counts__new(int ncpus, int nthreads) void perf_counts__delete(struct perf_counts *counts) { if (counts) { + xyarray__delete(counts->loaded); xyarray__delete(counts->values); free(counts); } @@ -34,21 +44,22 @@ void perf_counts__delete(struct perf_counts *counts) static void perf_counts__reset(struct perf_counts *counts) { + xyarray__reset(counts->loaded); xyarray__reset(counts->values); } -void perf_evsel__reset_counts(struct perf_evsel *evsel) +void perf_evsel__reset_counts(struct evsel *evsel) { perf_counts__reset(evsel->counts); } -int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus, int nthreads) +int perf_evsel__alloc_counts(struct evsel *evsel, int ncpus, int nthreads) { evsel->counts = perf_counts__new(ncpus, nthreads); return evsel->counts != NULL ? 0 : -ENOMEM; } -void perf_evsel__free_counts(struct perf_evsel *evsel) +void perf_evsel__free_counts(struct evsel *evsel) { perf_counts__delete(evsel->counts); evsel->counts = NULL; diff --git a/tools/perf/util/counts.h b/tools/perf/util/counts.h index 0d1050ccc586..92196df4945f 100644 --- a/tools/perf/util/counts.h +++ b/tools/perf/util/counts.h @@ -2,24 +2,18 @@ #ifndef __PERF_COUNTS_H #define __PERF_COUNTS_H -#include "xyarray.h" - -struct perf_counts_values { - union { - struct { - u64 val; - u64 ena; - u64 run; - }; - u64 values[3]; - }; - bool loaded; -}; +#include <linux/types.h> +#include <internal/xyarray.h> +#include <perf/evsel.h> +#include <stdbool.h> + +struct evsel; struct perf_counts { s8 scaled; struct perf_counts_values aggr; struct xyarray *values; + struct xyarray *loaded; }; @@ -29,11 +23,23 @@ perf_counts(struct perf_counts *counts, int cpu, int thread) return xyarray__entry(counts->values, cpu, thread); } +static inline bool +perf_counts__is_loaded(struct perf_counts *counts, int cpu, int thread) +{ + return *((bool *) xyarray__entry(counts->loaded, cpu, thread)); +} + +static inline void +perf_counts__set_loaded(struct perf_counts *counts, int cpu, int thread, bool loaded) +{ + *((bool *) xyarray__entry(counts->loaded, cpu, thread)) = loaded; +} + struct perf_counts *perf_counts__new(int ncpus, int nthreads); void perf_counts__delete(struct perf_counts *counts); -void perf_evsel__reset_counts(struct perf_evsel *evsel); -int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus, int nthreads); -void perf_evsel__free_counts(struct perf_evsel *evsel); +void perf_evsel__reset_counts(struct evsel *evsel); +int perf_evsel__alloc_counts(struct evsel *evsel, int ncpus, int nthreads); +void perf_evsel__free_counts(struct evsel *evsel); #endif /* __PERF_COUNTS_H */ diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 39cce66b4ebc..f5c21184e1fc 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -2,6 +2,8 @@ #include <api/fs/fs.h> #include "../perf.h" #include "cpumap.h" +#include "debug.h" +#include "event.h" #include <assert.h> #include <dirent.h> #include <stdio.h> @@ -17,190 +19,11 @@ static int max_present_cpu_num; static int max_node_num; static int *cpunode_map; -static struct cpu_map *cpu_map__default_new(void) +static struct perf_cpu_map *cpu_map__from_entries(struct cpu_map_entries *cpus) { - struct cpu_map *cpus; - int nr_cpus; + struct perf_cpu_map *map; - nr_cpus = sysconf(_SC_NPROCESSORS_ONLN); - if (nr_cpus < 0) - return NULL; - - cpus = malloc(sizeof(*cpus) + nr_cpus * sizeof(int)); - if (cpus != NULL) { - int i; - for (i = 0; i < nr_cpus; ++i) - cpus->map[i] = i; - - cpus->nr = nr_cpus; - refcount_set(&cpus->refcnt, 1); - } - - return cpus; -} - -static struct cpu_map *cpu_map__trim_new(int nr_cpus, int *tmp_cpus) -{ - size_t payload_size = nr_cpus * sizeof(int); - struct cpu_map *cpus = malloc(sizeof(*cpus) + payload_size); - - if (cpus != NULL) { - cpus->nr = nr_cpus; - memcpy(cpus->map, tmp_cpus, payload_size); - refcount_set(&cpus->refcnt, 1); - } - - return cpus; -} - -struct cpu_map *cpu_map__read(FILE *file) -{ - struct cpu_map *cpus = NULL; - int nr_cpus = 0; - int *tmp_cpus = NULL, *tmp; - int max_entries = 0; - int n, cpu, prev; - char sep; - - sep = 0; - prev = -1; - for (;;) { - n = fscanf(file, "%u%c", &cpu, &sep); - if (n <= 0) - break; - if (prev >= 0) { - int new_max = nr_cpus + cpu - prev - 1; - - if (new_max >= max_entries) { - max_entries = new_max + MAX_NR_CPUS / 2; - tmp = realloc(tmp_cpus, max_entries * sizeof(int)); - if (tmp == NULL) - goto out_free_tmp; - tmp_cpus = tmp; - } - - while (++prev < cpu) - tmp_cpus[nr_cpus++] = prev; - } - if (nr_cpus == max_entries) { - max_entries += MAX_NR_CPUS; - tmp = realloc(tmp_cpus, max_entries * sizeof(int)); - if (tmp == NULL) - goto out_free_tmp; - tmp_cpus = tmp; - } - - tmp_cpus[nr_cpus++] = cpu; - if (n == 2 && sep == '-') - prev = cpu; - else - prev = -1; - if (n == 1 || sep == '\n') - break; - } - - if (nr_cpus > 0) - cpus = cpu_map__trim_new(nr_cpus, tmp_cpus); - else - cpus = cpu_map__default_new(); -out_free_tmp: - free(tmp_cpus); - return cpus; -} - -static struct cpu_map *cpu_map__read_all_cpu_map(void) -{ - struct cpu_map *cpus = NULL; - FILE *onlnf; - - onlnf = fopen("/sys/devices/system/cpu/online", "r"); - if (!onlnf) - return cpu_map__default_new(); - - cpus = cpu_map__read(onlnf); - fclose(onlnf); - return cpus; -} - -struct cpu_map *cpu_map__new(const char *cpu_list) -{ - struct cpu_map *cpus = NULL; - unsigned long start_cpu, end_cpu = 0; - char *p = NULL; - int i, nr_cpus = 0; - int *tmp_cpus = NULL, *tmp; - int max_entries = 0; - - if (!cpu_list) - return cpu_map__read_all_cpu_map(); - - /* - * must handle the case of empty cpumap to cover - * TOPOLOGY header for NUMA nodes with no CPU - * ( e.g., because of CPU hotplug) - */ - if (!isdigit(*cpu_list) && *cpu_list != '\0') - goto out; - - while (isdigit(*cpu_list)) { - p = NULL; - start_cpu = strtoul(cpu_list, &p, 0); - if (start_cpu >= INT_MAX - || (*p != '\0' && *p != ',' && *p != '-')) - goto invalid; - - if (*p == '-') { - cpu_list = ++p; - p = NULL; - end_cpu = strtoul(cpu_list, &p, 0); - - if (end_cpu >= INT_MAX || (*p != '\0' && *p != ',')) - goto invalid; - - if (end_cpu < start_cpu) - goto invalid; - } else { - end_cpu = start_cpu; - } - - for (; start_cpu <= end_cpu; start_cpu++) { - /* check for duplicates */ - for (i = 0; i < nr_cpus; i++) - if (tmp_cpus[i] == (int)start_cpu) - goto invalid; - - if (nr_cpus == max_entries) { - max_entries += MAX_NR_CPUS; - tmp = realloc(tmp_cpus, max_entries * sizeof(int)); - if (tmp == NULL) - goto invalid; - tmp_cpus = tmp; - } - tmp_cpus[nr_cpus++] = (int)start_cpu; - } - if (*p) - ++p; - - cpu_list = p; - } - - if (nr_cpus > 0) - cpus = cpu_map__trim_new(nr_cpus, tmp_cpus); - else if (*cpu_list != '\0') - cpus = cpu_map__default_new(); - else - cpus = cpu_map__dummy_new(); -invalid: - free(tmp_cpus); -out: - return cpus; -} - -static struct cpu_map *cpu_map__from_entries(struct cpu_map_entries *cpus) -{ - struct cpu_map *map; - - map = cpu_map__empty_new(cpus->nr); + map = perf_cpu_map__empty_new(cpus->nr); if (map) { unsigned i; @@ -220,14 +43,14 @@ static struct cpu_map *cpu_map__from_entries(struct cpu_map_entries *cpus) return map; } -static struct cpu_map *cpu_map__from_mask(struct cpu_map_mask *mask) +static struct perf_cpu_map *cpu_map__from_mask(struct cpu_map_mask *mask) { - struct cpu_map *map; + struct perf_cpu_map *map; int nr, nbits = mask->nr * mask->long_size * BITS_PER_BYTE; nr = bitmap_weight(mask->mask, nbits); - map = cpu_map__empty_new(nr); + map = perf_cpu_map__empty_new(nr); if (map) { int cpu, i = 0; @@ -238,7 +61,7 @@ static struct cpu_map *cpu_map__from_mask(struct cpu_map_mask *mask) } -struct cpu_map *cpu_map__new_data(struct cpu_map_data *data) +struct perf_cpu_map *cpu_map__new_data(struct cpu_map_data *data) { if (data->type == PERF_CPU_MAP__CPUS) return cpu_map__from_entries((struct cpu_map_entries *)data->data); @@ -246,7 +69,7 @@ struct cpu_map *cpu_map__new_data(struct cpu_map_data *data) return cpu_map__from_mask((struct cpu_map_mask *)data->data); } -size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp) +size_t cpu_map__fprintf(struct perf_cpu_map *map, FILE *fp) { #define BUFSIZE 1024 char buf[BUFSIZE]; @@ -256,22 +79,9 @@ size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp) #undef BUFSIZE } -struct cpu_map *cpu_map__dummy_new(void) +struct perf_cpu_map *perf_cpu_map__empty_new(int nr) { - struct cpu_map *cpus = malloc(sizeof(*cpus) + sizeof(int)); - - if (cpus != NULL) { - cpus->nr = 1; - cpus->map[0] = -1; - refcount_set(&cpus->refcnt, 1); - } - - return cpus; -} - -struct cpu_map *cpu_map__empty_new(int nr) -{ - struct cpu_map *cpus = malloc(sizeof(*cpus) + sizeof(int) * nr); + struct perf_cpu_map *cpus = malloc(sizeof(*cpus) + sizeof(int) * nr); if (cpus != NULL) { int i; @@ -286,28 +96,6 @@ struct cpu_map *cpu_map__empty_new(int nr) return cpus; } -static void cpu_map__delete(struct cpu_map *map) -{ - if (map) { - WARN_ONCE(refcount_read(&map->refcnt) != 0, - "cpu_map refcnt unbalanced\n"); - free(map); - } -} - -struct cpu_map *cpu_map__get(struct cpu_map *map) -{ - if (map) - refcount_inc(&map->refcnt); - return map; -} - -void cpu_map__put(struct cpu_map *map) -{ - if (map && refcount_dec_and_test(&map->refcnt)) - cpu_map__delete(map); -} - static int cpu__get_topology_int(int cpu, const char *name, int *value) { char path[PATH_MAX]; @@ -324,7 +112,7 @@ int cpu_map__get_socket_id(int cpu) return ret ?: value; } -int cpu_map__get_socket(struct cpu_map *map, int idx, void *data __maybe_unused) +int cpu_map__get_socket(struct perf_cpu_map *map, int idx, void *data __maybe_unused) { int cpu; @@ -341,11 +129,11 @@ static int cmp_ids(const void *a, const void *b) return *(int *)a - *(int *)b; } -int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res, - int (*f)(struct cpu_map *map, int cpu, void *data), +int cpu_map__build_map(struct perf_cpu_map *cpus, struct perf_cpu_map **res, + int (*f)(struct perf_cpu_map *map, int cpu, void *data), void *data) { - struct cpu_map *c; + struct perf_cpu_map *c; int nr = cpus->nr; int cpu, s1, s2; @@ -380,7 +168,7 @@ int cpu_map__get_die_id(int cpu) return ret ?: value; } -int cpu_map__get_die(struct cpu_map *map, int idx, void *data) +int cpu_map__get_die(struct perf_cpu_map *map, int idx, void *data) { int cpu, die_id, s; @@ -419,7 +207,7 @@ int cpu_map__get_core_id(int cpu) return ret ?: value; } -int cpu_map__get_core(struct cpu_map *map, int idx, void *data) +int cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data) { int cpu, s_die; @@ -448,17 +236,17 @@ int cpu_map__get_core(struct cpu_map *map, int idx, void *data) return (s_die << 16) | (cpu & 0xffff); } -int cpu_map__build_socket_map(struct cpu_map *cpus, struct cpu_map **sockp) +int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct perf_cpu_map **sockp) { return cpu_map__build_map(cpus, sockp, cpu_map__get_socket, NULL); } -int cpu_map__build_die_map(struct cpu_map *cpus, struct cpu_map **diep) +int cpu_map__build_die_map(struct perf_cpu_map *cpus, struct perf_cpu_map **diep) { return cpu_map__build_map(cpus, diep, cpu_map__get_die, NULL); } -int cpu_map__build_core_map(struct cpu_map *cpus, struct cpu_map **corep) +int cpu_map__build_core_map(struct perf_cpu_map *cpus, struct perf_cpu_map **corep) { return cpu_map__build_map(cpus, corep, cpu_map__get_core, NULL); } @@ -670,29 +458,17 @@ int cpu__setup_cpunode_map(void) return 0; } -bool cpu_map__has(struct cpu_map *cpus, int cpu) +bool cpu_map__has(struct perf_cpu_map *cpus, int cpu) { - return cpu_map__idx(cpus, cpu) != -1; -} - -int cpu_map__idx(struct cpu_map *cpus, int cpu) -{ - int i; - - for (i = 0; i < cpus->nr; ++i) { - if (cpus->map[i] == cpu) - return i; - } - - return -1; + return perf_cpu_map__idx(cpus, cpu) != -1; } -int cpu_map__cpu(struct cpu_map *cpus, int idx) +int cpu_map__cpu(struct perf_cpu_map *cpus, int idx) { return cpus->map[idx]; } -size_t cpu_map__snprint(struct cpu_map *map, char *buf, size_t size) +size_t cpu_map__snprint(struct perf_cpu_map *map, char *buf, size_t size) { int i, cpu, start = -1; bool first = true; @@ -744,7 +520,7 @@ static char hex_char(unsigned char val) return '?'; } -size_t cpu_map__snprint_mask(struct cpu_map *map, char *buf, size_t size) +size_t cpu_map__snprint_mask(struct perf_cpu_map *map, char *buf, size_t size) { int i, cpu; char *ptr = buf; @@ -784,12 +560,12 @@ size_t cpu_map__snprint_mask(struct cpu_map *map, char *buf, size_t size) return ptr - buf; } -const struct cpu_map *cpu_map__online(void) /* thread unsafe */ +const struct perf_cpu_map *cpu_map__online(void) /* thread unsafe */ { - static const struct cpu_map *online = NULL; + static const struct perf_cpu_map *online = NULL; if (!online) - online = cpu_map__new(NULL); /* from /sys/devices/system/cpu/online */ + online = perf_cpu_map__new(NULL); /* from /sys/devices/system/cpu/online */ return online; } diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h index 1265f0e33920..d0c5bbfd91af 100644 --- a/tools/perf/util/cpumap.h +++ b/tools/perf/util/cpumap.h @@ -4,40 +4,30 @@ #include <stdio.h> #include <stdbool.h> -#include <linux/refcount.h> +#include <internal/cpumap.h> +#include <perf/cpumap.h> #include "perf.h" -#include "util/debug.h" -struct cpu_map { - refcount_t refcnt; - int nr; - int map[]; -}; +struct cpu_map_data; -struct cpu_map *cpu_map__new(const char *cpu_list); -struct cpu_map *cpu_map__empty_new(int nr); -struct cpu_map *cpu_map__dummy_new(void); -struct cpu_map *cpu_map__new_data(struct cpu_map_data *data); -struct cpu_map *cpu_map__read(FILE *file); -size_t cpu_map__snprint(struct cpu_map *map, char *buf, size_t size); -size_t cpu_map__snprint_mask(struct cpu_map *map, char *buf, size_t size); -size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp); +struct perf_cpu_map *perf_cpu_map__empty_new(int nr); +struct perf_cpu_map *cpu_map__new_data(struct cpu_map_data *data); +size_t cpu_map__snprint(struct perf_cpu_map *map, char *buf, size_t size); +size_t cpu_map__snprint_mask(struct perf_cpu_map *map, char *buf, size_t size); +size_t cpu_map__fprintf(struct perf_cpu_map *map, FILE *fp); int cpu_map__get_socket_id(int cpu); -int cpu_map__get_socket(struct cpu_map *map, int idx, void *data); +int cpu_map__get_socket(struct perf_cpu_map *map, int idx, void *data); int cpu_map__get_die_id(int cpu); -int cpu_map__get_die(struct cpu_map *map, int idx, void *data); +int cpu_map__get_die(struct perf_cpu_map *map, int idx, void *data); int cpu_map__get_core_id(int cpu); -int cpu_map__get_core(struct cpu_map *map, int idx, void *data); -int cpu_map__build_socket_map(struct cpu_map *cpus, struct cpu_map **sockp); -int cpu_map__build_die_map(struct cpu_map *cpus, struct cpu_map **diep); -int cpu_map__build_core_map(struct cpu_map *cpus, struct cpu_map **corep); -const struct cpu_map *cpu_map__online(void); /* thread unsafe */ +int cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data); +int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct perf_cpu_map **sockp); +int cpu_map__build_die_map(struct perf_cpu_map *cpus, struct perf_cpu_map **diep); +int cpu_map__build_core_map(struct perf_cpu_map *cpus, struct perf_cpu_map **corep); +const struct perf_cpu_map *cpu_map__online(void); /* thread unsafe */ -struct cpu_map *cpu_map__get(struct cpu_map *map); -void cpu_map__put(struct cpu_map *map); - -static inline int cpu_map__socket(struct cpu_map *sock, int s) +static inline int cpu_map__socket(struct perf_cpu_map *sock, int s) { if (!sock || s > sock->nr || s < 0) return 0; @@ -59,16 +49,6 @@ static inline int cpu_map__id_to_cpu(int id) return id & 0xffff; } -static inline int cpu_map__nr(const struct cpu_map *map) -{ - return map ? map->nr : 1; -} - -static inline bool cpu_map__empty(const struct cpu_map *map) -{ - return map ? map->map[0] == -1 : true; -} - int cpu__setup_cpunode_map(void); int cpu__max_node(void); @@ -76,11 +56,10 @@ int cpu__max_cpu(void); int cpu__max_present_cpu(void); int cpu__get_node(int cpu); -int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res, - int (*f)(struct cpu_map *map, int cpu, void *data), +int cpu_map__build_map(struct perf_cpu_map *cpus, struct perf_cpu_map **res, + int (*f)(struct perf_cpu_map *map, int cpu, void *data), void *data); -int cpu_map__cpu(struct cpu_map *cpus, int idx); -bool cpu_map__has(struct cpu_map *cpus, int cpu); -int cpu_map__idx(struct cpu_map *cpus, int cpu); +int cpu_map__cpu(struct perf_cpu_map *cpus, int idx); +bool cpu_map__has(struct perf_cpu_map *cpus, int cpu); #endif /* __PERF_CPUMAP_H */ diff --git a/tools/perf/util/cputopo.c b/tools/perf/util/cputopo.c index 64336a280967..1b52402a8923 100644 --- a/tools/perf/util/cputopo.c +++ b/tools/perf/util/cputopo.c @@ -3,11 +3,14 @@ #include <sys/utsname.h> #include <inttypes.h> #include <stdlib.h> +#include <string.h> #include <api/fs/fs.h> #include <linux/zalloc.h> +#include <perf/cpumap.h> #include "cputopo.h" #include "cpumap.h" +#include "debug.h" #include "env.h" #define CORE_SIB_FMT \ @@ -176,13 +179,13 @@ struct cpu_topology *cpu_topology__new(void) size_t sz; long ncpus; int ret = -1; - struct cpu_map *map; + struct perf_cpu_map *map; bool has_die = has_die_topology(); ncpus = cpu__max_present_cpu(); /* build online CPU map */ - map = cpu_map__new(NULL); + map = perf_cpu_map__new(NULL); if (map == NULL) { pr_debug("failed to get system cpumap\n"); return NULL; @@ -219,7 +222,7 @@ struct cpu_topology *cpu_topology__new(void) } out_free: - cpu_map__put(map); + perf_cpu_map__put(map); if (ret) { cpu_topology__delete(tp); tp = NULL; @@ -289,7 +292,7 @@ err: struct numa_topology *numa_topology__new(void) { - struct cpu_map *node_map = NULL; + struct perf_cpu_map *node_map = NULL; struct numa_topology *tp = NULL; char path[MAXPATHLEN]; char *buf = NULL; @@ -312,7 +315,7 @@ struct numa_topology *numa_topology__new(void) if (c) *c = '\0'; - node_map = cpu_map__new(buf); + node_map = perf_cpu_map__new(buf); if (!node_map) goto out; @@ -335,7 +338,7 @@ struct numa_topology *numa_topology__new(void) out: free(buf); fclose(fp); - cpu_map__put(node_map); + perf_cpu_map__put(node_map); return tp; } diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 3d1c34fc4d68..b3a5daaf1a8f 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -1076,6 +1076,35 @@ bool cs_etm__etmq_is_timeless(struct cs_etm_queue *etmq) return !!etmq->etm->timeless_decoding; } +static void cs_etm__copy_insn(struct cs_etm_queue *etmq, + u64 trace_chan_id, + const struct cs_etm_packet *packet, + struct perf_sample *sample) +{ + /* + * It's pointless to read instructions for the CS_ETM_DISCONTINUITY + * packet, so directly bail out with 'insn_len' = 0. + */ + if (packet->sample_type == CS_ETM_DISCONTINUITY) { + sample->insn_len = 0; + return; + } + + /* + * T32 instruction size might be 32-bit or 16-bit, decide by calling + * cs_etm__t32_instr_size(). + */ + if (packet->isa == CS_ETM_ISA_T32) + sample->insn_len = cs_etm__t32_instr_size(etmq, trace_chan_id, + sample->ip); + /* Otherwise, A64 and A32 instruction size are always 32-bit. */ + else + sample->insn_len = 4; + + cs_etm__mem_access(etmq, trace_chan_id, sample->ip, + sample->insn_len, (void *)sample->insn); +} + static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq, struct cs_etm_traceid_queue *tidq, u64 addr, u64 period) @@ -1097,9 +1126,10 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq, sample.period = period; sample.cpu = tidq->packet->cpu; sample.flags = tidq->prev_packet->flags; - sample.insn_len = 1; sample.cpumode = event->sample.header.misc; + cs_etm__copy_insn(etmq, tidq->trace_chan_id, tidq->packet, &sample); + if (etm->synth_opts.last_branch) { cs_etm__copy_last_branch_rb(etmq, tidq); sample.branch_stack = tidq->last_branch; @@ -1159,6 +1189,9 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq, sample.flags = tidq->prev_packet->flags; sample.cpumode = event->sample.header.misc; + cs_etm__copy_insn(etmq, tidq->trace_chan_id, tidq->prev_packet, + &sample); + /* * perf report cannot handle events without a branch stack */ @@ -1222,15 +1255,15 @@ static int cs_etm__synth_event(struct perf_session *session, static int cs_etm__synth_events(struct cs_etm_auxtrace *etm, struct perf_session *session) { - struct perf_evlist *evlist = session->evlist; - struct perf_evsel *evsel; + struct evlist *evlist = session->evlist; + struct evsel *evsel; struct perf_event_attr attr; bool found = false; u64 id; int err; evlist__for_each_entry(evlist, evsel) { - if (evsel->attr.type == etm->pmu_type) { + if (evsel->core.attr.type == etm->pmu_type) { found = true; break; } @@ -1244,7 +1277,7 @@ static int cs_etm__synth_events(struct cs_etm_auxtrace *etm, memset(&attr, 0, sizeof(struct perf_event_attr)); attr.size = sizeof(struct perf_event_attr); attr.type = PERF_TYPE_HARDWARE; - attr.sample_type = evsel->attr.sample_type & PERF_SAMPLE_MASK; + attr.sample_type = evsel->core.attr.sample_type & PERF_SAMPLE_MASK; attr.sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_PERIOD; if (etm->timeless_decoding) @@ -1252,13 +1285,13 @@ static int cs_etm__synth_events(struct cs_etm_auxtrace *etm, else attr.sample_type |= PERF_SAMPLE_TIME; - attr.exclude_user = evsel->attr.exclude_user; - attr.exclude_kernel = evsel->attr.exclude_kernel; - attr.exclude_hv = evsel->attr.exclude_hv; - attr.exclude_host = evsel->attr.exclude_host; - attr.exclude_guest = evsel->attr.exclude_guest; - attr.sample_id_all = evsel->attr.sample_id_all; - attr.read_format = evsel->attr.read_format; + attr.exclude_user = evsel->core.attr.exclude_user; + attr.exclude_kernel = evsel->core.attr.exclude_kernel; + attr.exclude_hv = evsel->core.attr.exclude_hv; + attr.exclude_host = evsel->core.attr.exclude_host; + attr.exclude_guest = evsel->core.attr.exclude_guest; + attr.sample_id_all = evsel->core.attr.sample_id_all; + attr.read_format = evsel->core.attr.read_format; /* create new id val to be a fixed offset from evsel id */ id = evsel->id[0] + 1000000000; @@ -2294,8 +2327,8 @@ static int cs_etm__process_auxtrace_event(struct perf_session *session, static bool cs_etm__is_timeless_decoding(struct cs_etm_auxtrace *etm) { - struct perf_evsel *evsel; - struct perf_evlist *evlist = etm->session->evlist; + struct evsel *evsel; + struct evlist *evlist = etm->session->evlist; bool timeless_decoding = true; /* @@ -2303,7 +2336,7 @@ static bool cs_etm__is_timeless_decoding(struct cs_etm_auxtrace *etm) * with the time bit set. */ evlist__for_each_entry(evlist, evsel) { - if ((evsel->attr.sample_type & PERF_SAMPLE_TIME)) + if ((evsel->core.attr.sample_type & PERF_SAMPLE_TIME)) timeless_decoding = false; } diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c index ddbcd59f2d9b..0c268449959c 100644 --- a/tools/perf/util/data-convert-bt.c +++ b/tools/perf/util/data-convert-bt.c @@ -413,7 +413,7 @@ static int add_tracepoint_fields_values(struct ctf_writer *cw, static int add_tracepoint_values(struct ctf_writer *cw, struct bt_ctf_event_class *event_class, struct bt_ctf_event *event, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample) { struct tep_format_field *common_fields = evsel->tp_format->format.common_fields; @@ -584,10 +584,10 @@ put_len_type: static int add_generic_values(struct ctf_writer *cw, struct bt_ctf_event *event, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample) { - u64 type = evsel->attr.sample_type; + u64 type = evsel->core.attr.sample_type; int ret; /* @@ -753,11 +753,11 @@ static struct ctf_stream *ctf_stream(struct ctf_writer *cw, int cpu) } static int get_sample_cpu(struct ctf_writer *cw, struct perf_sample *sample, - struct perf_evsel *evsel) + struct evsel *evsel) { int cpu = 0; - if (evsel->attr.sample_type & PERF_SAMPLE_CPU) + if (evsel->core.attr.sample_type & PERF_SAMPLE_CPU) cpu = sample->cpu; if (cpu > cw->stream_cnt) { @@ -785,7 +785,7 @@ static bool is_flush_needed(struct ctf_stream *cs) static int process_sample_event(struct perf_tool *tool, union perf_event *_event, struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct machine *machine __maybe_unused) { struct convert *c = container_of(tool, struct convert, tool); @@ -795,7 +795,7 @@ static int process_sample_event(struct perf_tool *tool, struct bt_ctf_event_class *event_class; struct bt_ctf_event *event; int ret; - unsigned long type = evsel->attr.sample_type; + unsigned long type = evsel->core.attr.sample_type; if (WARN_ONCE(!priv, "Failed to setup all events.\n")) return 0; @@ -820,7 +820,7 @@ static int process_sample_event(struct perf_tool *tool, if (ret) return -1; - if (evsel->attr.type == PERF_TYPE_TRACEPOINT) { + if (evsel->core.attr.type == PERF_TYPE_TRACEPOINT) { ret = add_tracepoint_values(cw, event_class, event, evsel, sample); if (ret) @@ -1051,7 +1051,7 @@ static int add_tracepoint_fields_types(struct ctf_writer *cw, } static int add_tracepoint_types(struct ctf_writer *cw, - struct perf_evsel *evsel, + struct evsel *evsel, struct bt_ctf_event_class *class) { struct tep_format_field *common_fields = evsel->tp_format->format.common_fields; @@ -1084,10 +1084,10 @@ static int add_bpf_output_types(struct ctf_writer *cw, return bt_ctf_event_class_add_field(class, seq_type, "raw_data"); } -static int add_generic_types(struct ctf_writer *cw, struct perf_evsel *evsel, +static int add_generic_types(struct ctf_writer *cw, struct evsel *evsel, struct bt_ctf_event_class *event_class) { - u64 type = evsel->attr.sample_type; + u64 type = evsel->core.attr.sample_type; /* * missing: @@ -1150,14 +1150,14 @@ static int add_generic_types(struct ctf_writer *cw, struct perf_evsel *evsel, return 0; } -static int add_event(struct ctf_writer *cw, struct perf_evsel *evsel) +static int add_event(struct ctf_writer *cw, struct evsel *evsel) { struct bt_ctf_event_class *event_class; struct evsel_priv *priv; const char *name = perf_evsel__name(evsel); int ret; - pr("Adding event '%s' (type %d)\n", name, evsel->attr.type); + pr("Adding event '%s' (type %d)\n", name, evsel->core.attr.type); event_class = bt_ctf_event_class_create(name); if (!event_class) @@ -1167,7 +1167,7 @@ static int add_event(struct ctf_writer *cw, struct perf_evsel *evsel) if (ret) goto err; - if (evsel->attr.type == PERF_TYPE_TRACEPOINT) { + if (evsel->core.attr.type == PERF_TYPE_TRACEPOINT) { ret = add_tracepoint_types(cw, evsel, event_class); if (ret) goto err; @@ -1201,8 +1201,8 @@ err: static int setup_events(struct ctf_writer *cw, struct perf_session *session) { - struct perf_evlist *evlist = session->evlist; - struct perf_evsel *evsel; + struct evlist *evlist = session->evlist; + struct evsel *evsel; int ret; evlist__for_each_entry(evlist, evsel) { @@ -1308,8 +1308,8 @@ static int setup_non_sample_events(struct ctf_writer *cw, static void cleanup_events(struct perf_session *session) { - struct perf_evlist *evlist = session->evlist; - struct perf_evsel *evsel; + struct evlist *evlist = session->evlist; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { struct evsel_priv *priv; @@ -1319,7 +1319,7 @@ static void cleanup_events(struct perf_session *session) zfree(&evsel->priv); } - perf_evlist__delete(evlist); + evlist__delete(evlist); session->evlist = NULL; } diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c index ffbb3e7d3288..701e9f814313 100644 --- a/tools/perf/util/db-export.c +++ b/tools/perf/util/db-export.c @@ -32,7 +32,7 @@ void db_export__exit(struct db_export *dbe) dbe->crp = NULL; } -int db_export__evsel(struct db_export *dbe, struct perf_evsel *evsel) +int db_export__evsel(struct db_export *dbe, struct evsel *evsel) { if (evsel->db_id) return 0; @@ -209,7 +209,7 @@ static struct call_path *call_path_from_sample(struct db_export *dbe, struct machine *machine, struct thread *thread, struct perf_sample *sample, - struct perf_evsel *evsel) + struct evsel *evsel) { u64 kernel_start = machine__kernel_start(machine); struct call_path *current = &dbe->cpr->call_path; @@ -341,7 +341,7 @@ static int db_export__threads(struct db_export *dbe, struct thread *thread, } int db_export__sample(struct db_export *dbe, union perf_event *event, - struct perf_sample *sample, struct perf_evsel *evsel, + struct perf_sample *sample, struct evsel *evsel, struct addr_location *al) { struct thread *thread = al->thread; @@ -388,8 +388,8 @@ int db_export__sample(struct db_export *dbe, union perf_event *event, } } - if ((evsel->attr.sample_type & PERF_SAMPLE_ADDR) && - sample_addr_correlates_sym(&evsel->attr)) { + if ((evsel->core.attr.sample_type & PERF_SAMPLE_ADDR) && + sample_addr_correlates_sym(&evsel->core.attr)) { struct addr_location addr_al; thread__resolve(thread, &addr_al, sample); diff --git a/tools/perf/util/db-export.h b/tools/perf/util/db-export.h index ba1f62a5fe10..9c3d38f5a40d 100644 --- a/tools/perf/util/db-export.h +++ b/tools/perf/util/db-export.h @@ -10,7 +10,7 @@ #include <linux/types.h> #include <linux/list.h> -struct perf_evsel; +struct evsel; struct machine; struct thread; struct comm; @@ -25,7 +25,7 @@ struct call_return; struct export_sample { union perf_event *event; struct perf_sample *sample; - struct perf_evsel *evsel; + struct evsel *evsel; struct addr_location *al; u64 db_id; u64 comm_db_id; @@ -39,7 +39,7 @@ struct export_sample { }; struct db_export { - int (*export_evsel)(struct db_export *dbe, struct perf_evsel *evsel); + int (*export_evsel)(struct db_export *dbe, struct evsel *evsel); int (*export_machine)(struct db_export *dbe, struct machine *machine); int (*export_thread)(struct db_export *dbe, struct thread *thread, u64 main_thread_db_id, struct machine *machine); @@ -79,7 +79,7 @@ struct db_export { int db_export__init(struct db_export *dbe); void db_export__exit(struct db_export *dbe); -int db_export__evsel(struct db_export *dbe, struct perf_evsel *evsel); +int db_export__evsel(struct db_export *dbe, struct evsel *evsel); int db_export__machine(struct db_export *dbe, struct machine *machine); int db_export__thread(struct db_export *dbe, struct thread *thread, struct machine *machine, struct thread *main_thread); @@ -96,7 +96,7 @@ int db_export__symbol(struct db_export *dbe, struct symbol *sym, int db_export__branch_type(struct db_export *dbe, u32 branch_type, const char *name); int db_export__sample(struct db_export *dbe, union perf_event *event, - struct perf_sample *sample, struct perf_evsel *evsel, + struct perf_sample *sample, struct evsel *evsel, struct addr_location *al); int db_export__branch_types(struct db_export *dbe); diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index 9909ec40c6d2..571efb4f0351 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include "cpumap.h" +#include "debug.h" #include "env.h" #include <linux/ctype.h> #include <linux/zalloc.h> @@ -179,7 +180,7 @@ void perf_env__exit(struct perf_env *env) zfree(&env->cpu); for (i = 0; i < env->nr_numa_nodes; i++) - cpu_map__put(env->numa_nodes[i].map); + perf_cpu_map__put(env->numa_nodes[i].map); zfree(&env->numa_nodes); for (i = 0; i < env->caches_cnt; i++) diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h index d5d9865aa812..d8e083d42610 100644 --- a/tools/perf/util/env.h +++ b/tools/perf/util/env.h @@ -27,7 +27,7 @@ struct numa_node { u32 node; u64 mem_total; u64 mem_free; - struct cpu_map *map; + struct perf_cpu_map *map; }; struct memory_node { diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index f1f4848947ce..332edef8d394 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -616,7 +616,7 @@ static int __event__synthesize_thread(union perf_event *comm_event, } int perf_event__synthesize_thread_map(struct perf_tool *tool, - struct thread_map *threads, + struct perf_thread_map *threads, perf_event__handler_t process, struct machine *machine, bool mmap_data) @@ -647,7 +647,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool, for (thread = 0; thread < threads->nr; ++thread) { if (__event__synthesize_thread(comm_event, mmap_event, fork_event, namespaces_event, - thread_map__pid(threads, thread), 0, + perf_thread_map__pid(threads, thread), 0, process, tool, machine, mmap_data)) { err = -1; @@ -658,12 +658,12 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool, * comm.pid is set to thread group id by * perf_event__synthesize_comm */ - if ((int) comm_event->comm.pid != thread_map__pid(threads, thread)) { + if ((int) comm_event->comm.pid != perf_thread_map__pid(threads, thread)) { bool need_leader = true; /* is thread group leader in thread_map? */ for (j = 0; j < threads->nr; ++j) { - if ((int) comm_event->comm.pid == thread_map__pid(threads, j)) { + if ((int) comm_event->comm.pid == perf_thread_map__pid(threads, j)) { need_leader = false; break; } @@ -972,7 +972,7 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, } int perf_event__synthesize_thread_map2(struct perf_tool *tool, - struct thread_map *threads, + struct perf_thread_map *threads, perf_event__handler_t process, struct machine *machine) { @@ -992,12 +992,12 @@ int perf_event__synthesize_thread_map2(struct perf_tool *tool, for (i = 0; i < threads->nr; i++) { struct thread_map_event_entry *entry = &event->thread_map.entries[i]; - char *comm = thread_map__comm(threads, i); + char *comm = perf_thread_map__comm(threads, i); if (!comm) comm = (char *) ""; - entry->pid = thread_map__pid(threads, i); + entry->pid = perf_thread_map__pid(threads, i); strncpy((char *) &entry->comm, comm, sizeof(entry->comm)); } @@ -1008,7 +1008,7 @@ int perf_event__synthesize_thread_map2(struct perf_tool *tool, } static void synthesize_cpus(struct cpu_map_entries *cpus, - struct cpu_map *map) + struct perf_cpu_map *map) { int i; @@ -1019,7 +1019,7 @@ static void synthesize_cpus(struct cpu_map_entries *cpus, } static void synthesize_mask(struct cpu_map_mask *mask, - struct cpu_map *map, int max) + struct perf_cpu_map *map, int max) { int i; @@ -1030,12 +1030,12 @@ static void synthesize_mask(struct cpu_map_mask *mask, set_bit(map->map[i], mask->mask); } -static size_t cpus_size(struct cpu_map *map) +static size_t cpus_size(struct perf_cpu_map *map) { return sizeof(struct cpu_map_entries) + map->nr * sizeof(u16); } -static size_t mask_size(struct cpu_map *map, int *max) +static size_t mask_size(struct perf_cpu_map *map, int *max) { int i; @@ -1052,10 +1052,10 @@ static size_t mask_size(struct cpu_map *map, int *max) return sizeof(struct cpu_map_mask) + BITS_TO_LONGS(*max) * sizeof(long); } -void *cpu_map_data__alloc(struct cpu_map *map, size_t *size, u16 *type, int *max) +void *cpu_map_data__alloc(struct perf_cpu_map *map, size_t *size, u16 *type, int *max) { size_t size_cpus, size_mask; - bool is_dummy = cpu_map__empty(map); + bool is_dummy = perf_cpu_map__empty(map); /* * Both array and mask data have variable size based @@ -1086,7 +1086,7 @@ void *cpu_map_data__alloc(struct cpu_map *map, size_t *size, u16 *type, int *max return zalloc(*size); } -void cpu_map_data__synthesize(struct cpu_map_data *data, struct cpu_map *map, +void cpu_map_data__synthesize(struct cpu_map_data *data, struct perf_cpu_map *map, u16 type, int max) { data->type = type; @@ -1102,7 +1102,7 @@ void cpu_map_data__synthesize(struct cpu_map_data *data, struct cpu_map *map, }; } -static struct cpu_map_event* cpu_map_event__new(struct cpu_map *map) +static struct cpu_map_event* cpu_map_event__new(struct perf_cpu_map *map) { size_t size = sizeof(struct cpu_map_event); struct cpu_map_event *event; @@ -1122,7 +1122,7 @@ static struct cpu_map_event* cpu_map_event__new(struct cpu_map *map) } int perf_event__synthesize_cpu_map(struct perf_tool *tool, - struct cpu_map *map, + struct perf_cpu_map *map, perf_event__handler_t process, struct machine *machine) { @@ -1377,7 +1377,7 @@ size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp) size_t perf_event__fprintf_thread_map(union perf_event *event, FILE *fp) { - struct thread_map *threads = thread_map__new_event(&event->thread_map); + struct perf_thread_map *threads = thread_map__new_event(&event->thread_map); size_t ret; ret = fprintf(fp, " nr: "); @@ -1387,13 +1387,13 @@ size_t perf_event__fprintf_thread_map(union perf_event *event, FILE *fp) else ret += fprintf(fp, "failed to get threads from event\n"); - thread_map__put(threads); + perf_thread_map__put(threads); return ret; } size_t perf_event__fprintf_cpu_map(union perf_event *event, FILE *fp) { - struct cpu_map *cpus = cpu_map__new_data(&event->cpu_map.data); + struct perf_cpu_map *cpus = cpu_map__new_data(&event->cpu_map.data); size_t ret; ret = fprintf(fp, ": "); @@ -1403,7 +1403,7 @@ size_t perf_event__fprintf_cpu_map(union perf_event *event, FILE *fp) else ret += fprintf(fp, "failed to get cpumap from event\n"); - cpu_map__put(cpus); + perf_cpu_map__put(cpus); return ret; } diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 1f1da6082806..0e164e8ae28d 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -674,8 +674,8 @@ union perf_event { void perf_event__print_totals(void); struct perf_tool; -struct thread_map; -struct cpu_map; +struct perf_thread_map; +struct perf_cpu_map; struct perf_stat_config; struct perf_counts_values; @@ -685,15 +685,15 @@ typedef int (*perf_event__handler_t)(struct perf_tool *tool, struct machine *machine); int perf_event__synthesize_thread_map(struct perf_tool *tool, - struct thread_map *threads, + struct perf_thread_map *threads, perf_event__handler_t process, struct machine *machine, bool mmap_data); int perf_event__synthesize_thread_map2(struct perf_tool *tool, - struct thread_map *threads, + struct perf_thread_map *threads, perf_event__handler_t process, struct machine *machine); int perf_event__synthesize_cpu_map(struct perf_tool *tool, - struct cpu_map *cpus, + struct perf_cpu_map *cpus, perf_event__handler_t process, struct machine *machine); int perf_event__synthesize_threads(struct perf_tool *tool, @@ -844,13 +844,14 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp); int kallsyms__get_function_start(const char *kallsyms_filename, const char *symbol_name, u64 *addr); -void *cpu_map_data__alloc(struct cpu_map *map, size_t *size, u16 *type, int *max); -void cpu_map_data__synthesize(struct cpu_map_data *data, struct cpu_map *map, +void *cpu_map_data__alloc(struct perf_cpu_map *map, size_t *size, u16 *type, int *max); +void cpu_map_data__synthesize(struct cpu_map_data *data, struct perf_cpu_map *map, u16 type, int max); void event_attr_init(struct perf_event_attr *attr); int perf_event_paranoid(void); +bool perf_event_paranoid_check(int max_level); extern int sysctl_perf_event_max_stack; extern int sysctl_perf_event_max_contexts_per_stack; diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index b0364d923f76..ff415680fe0a 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -33,56 +33,61 @@ #include <linux/log2.h> #include <linux/err.h> #include <linux/zalloc.h> +#include <perf/evlist.h> +#include <perf/evsel.h> +#include <perf/cpumap.h> + +#include <internal/xyarray.h> #ifdef LACKS_SIGQUEUE_PROTOTYPE int sigqueue(pid_t pid, int sig, const union sigval value); #endif -#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y)) +#define FD(e, x, y) (*(int *)xyarray__entry(e->core.fd, x, y)) #define SID(e, x, y) xyarray__entry(e->sample_id, x, y) -void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus, - struct thread_map *threads) +void evlist__init(struct evlist *evlist, struct perf_cpu_map *cpus, + struct perf_thread_map *threads) { int i; for (i = 0; i < PERF_EVLIST__HLIST_SIZE; ++i) INIT_HLIST_HEAD(&evlist->heads[i]); - INIT_LIST_HEAD(&evlist->entries); - perf_evlist__set_maps(evlist, cpus, threads); + perf_evlist__init(&evlist->core); + perf_evlist__set_maps(&evlist->core, cpus, threads); fdarray__init(&evlist->pollfd, 64); evlist->workload.pid = -1; evlist->bkw_mmap_state = BKW_MMAP_NOTREADY; } -struct perf_evlist *perf_evlist__new(void) +struct evlist *evlist__new(void) { - struct perf_evlist *evlist = zalloc(sizeof(*evlist)); + struct evlist *evlist = zalloc(sizeof(*evlist)); if (evlist != NULL) - perf_evlist__init(evlist, NULL, NULL); + evlist__init(evlist, NULL, NULL); return evlist; } -struct perf_evlist *perf_evlist__new_default(void) +struct evlist *perf_evlist__new_default(void) { - struct perf_evlist *evlist = perf_evlist__new(); + struct evlist *evlist = evlist__new(); if (evlist && perf_evlist__add_default(evlist)) { - perf_evlist__delete(evlist); + evlist__delete(evlist); evlist = NULL; } return evlist; } -struct perf_evlist *perf_evlist__new_dummy(void) +struct evlist *perf_evlist__new_dummy(void) { - struct perf_evlist *evlist = perf_evlist__new(); + struct evlist *evlist = evlist__new(); if (evlist && perf_evlist__add_dummy(evlist)) { - perf_evlist__delete(evlist); + evlist__delete(evlist); evlist = NULL; } @@ -96,17 +101,17 @@ struct perf_evlist *perf_evlist__new_dummy(void) * Events with compatible sample types all have the same id_pos * and is_pos. For convenience, put a copy on evlist. */ -void perf_evlist__set_id_pos(struct perf_evlist *evlist) +void perf_evlist__set_id_pos(struct evlist *evlist) { - struct perf_evsel *first = perf_evlist__first(evlist); + struct evsel *first = perf_evlist__first(evlist); evlist->id_pos = first->id_pos; evlist->is_pos = first->is_pos; } -static void perf_evlist__update_id_pos(struct perf_evlist *evlist) +static void perf_evlist__update_id_pos(struct evlist *evlist) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) perf_evsel__calc_id_pos(evsel); @@ -114,161 +119,132 @@ static void perf_evlist__update_id_pos(struct perf_evlist *evlist) perf_evlist__set_id_pos(evlist); } -static void perf_evlist__purge(struct perf_evlist *evlist) +static void perf_evlist__purge(struct evlist *evlist) { - struct perf_evsel *pos, *n; + struct evsel *pos, *n; evlist__for_each_entry_safe(evlist, n, pos) { - list_del_init(&pos->node); + list_del_init(&pos->core.node); pos->evlist = NULL; - perf_evsel__delete(pos); + evsel__delete(pos); } - evlist->nr_entries = 0; + evlist->core.nr_entries = 0; } -void perf_evlist__exit(struct perf_evlist *evlist) +void perf_evlist__exit(struct evlist *evlist) { zfree(&evlist->mmap); zfree(&evlist->overwrite_mmap); fdarray__exit(&evlist->pollfd); } -void perf_evlist__delete(struct perf_evlist *evlist) +void evlist__delete(struct evlist *evlist) { if (evlist == NULL) return; perf_evlist__munmap(evlist); - perf_evlist__close(evlist); - cpu_map__put(evlist->cpus); - thread_map__put(evlist->threads); - evlist->cpus = NULL; - evlist->threads = NULL; + evlist__close(evlist); + perf_cpu_map__put(evlist->core.cpus); + perf_thread_map__put(evlist->core.threads); + evlist->core.cpus = NULL; + evlist->core.threads = NULL; perf_evlist__purge(evlist); perf_evlist__exit(evlist); free(evlist); } -static void __perf_evlist__propagate_maps(struct perf_evlist *evlist, - struct perf_evsel *evsel) -{ - /* - * We already have cpus for evsel (via PMU sysfs) so - * keep it, if there's no target cpu list defined. - */ - if (!evsel->own_cpus || evlist->has_user_cpus) { - cpu_map__put(evsel->cpus); - evsel->cpus = cpu_map__get(evlist->cpus); - } else if (evsel->cpus != evsel->own_cpus) { - cpu_map__put(evsel->cpus); - evsel->cpus = cpu_map__get(evsel->own_cpus); - } - - thread_map__put(evsel->threads); - evsel->threads = thread_map__get(evlist->threads); -} - -static void perf_evlist__propagate_maps(struct perf_evlist *evlist) -{ - struct perf_evsel *evsel; - - evlist__for_each_entry(evlist, evsel) - __perf_evlist__propagate_maps(evlist, evsel); -} - -void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry) +void evlist__add(struct evlist *evlist, struct evsel *entry) { entry->evlist = evlist; - list_add_tail(&entry->node, &evlist->entries); - entry->idx = evlist->nr_entries; + entry->idx = evlist->core.nr_entries; entry->tracking = !entry->idx; - if (!evlist->nr_entries++) - perf_evlist__set_id_pos(evlist); + perf_evlist__add(&evlist->core, &entry->core); - __perf_evlist__propagate_maps(evlist, entry); + if (evlist->core.nr_entries == 1) + perf_evlist__set_id_pos(evlist); } -void perf_evlist__remove(struct perf_evlist *evlist, struct perf_evsel *evsel) +void evlist__remove(struct evlist *evlist, struct evsel *evsel) { evsel->evlist = NULL; - list_del_init(&evsel->node); - evlist->nr_entries -= 1; + perf_evlist__remove(&evlist->core, &evsel->core); } -void perf_evlist__splice_list_tail(struct perf_evlist *evlist, +void perf_evlist__splice_list_tail(struct evlist *evlist, struct list_head *list) { - struct perf_evsel *evsel, *temp; + struct evsel *evsel, *temp; __evlist__for_each_entry_safe(list, temp, evsel) { - list_del_init(&evsel->node); - perf_evlist__add(evlist, evsel); + list_del_init(&evsel->core.node); + evlist__add(evlist, evsel); } } void __perf_evlist__set_leader(struct list_head *list) { - struct perf_evsel *evsel, *leader; + struct evsel *evsel, *leader; - leader = list_entry(list->next, struct perf_evsel, node); - evsel = list_entry(list->prev, struct perf_evsel, node); + leader = list_entry(list->next, struct evsel, core.node); + evsel = list_entry(list->prev, struct evsel, core.node); - leader->nr_members = evsel->idx - leader->idx + 1; + leader->core.nr_members = evsel->idx - leader->idx + 1; __evlist__for_each_entry(list, evsel) { evsel->leader = leader; } } -void perf_evlist__set_leader(struct perf_evlist *evlist) +void perf_evlist__set_leader(struct evlist *evlist) { - if (evlist->nr_entries) { - evlist->nr_groups = evlist->nr_entries > 1 ? 1 : 0; - __perf_evlist__set_leader(&evlist->entries); + if (evlist->core.nr_entries) { + evlist->nr_groups = evlist->core.nr_entries > 1 ? 1 : 0; + __perf_evlist__set_leader(&evlist->core.entries); } } -int __perf_evlist__add_default(struct perf_evlist *evlist, bool precise) +int __perf_evlist__add_default(struct evlist *evlist, bool precise) { - struct perf_evsel *evsel = perf_evsel__new_cycles(precise); + struct evsel *evsel = perf_evsel__new_cycles(precise); if (evsel == NULL) return -ENOMEM; - perf_evlist__add(evlist, evsel); + evlist__add(evlist, evsel); return 0; } -int perf_evlist__add_dummy(struct perf_evlist *evlist) +int perf_evlist__add_dummy(struct evlist *evlist) { struct perf_event_attr attr = { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_DUMMY, .size = sizeof(attr), /* to capture ABI version */ }; - struct perf_evsel *evsel = perf_evsel__new_idx(&attr, evlist->nr_entries); + struct evsel *evsel = perf_evsel__new_idx(&attr, evlist->core.nr_entries); if (evsel == NULL) return -ENOMEM; - perf_evlist__add(evlist, evsel); + evlist__add(evlist, evsel); return 0; } -static int perf_evlist__add_attrs(struct perf_evlist *evlist, +static int evlist__add_attrs(struct evlist *evlist, struct perf_event_attr *attrs, size_t nr_attrs) { - struct perf_evsel *evsel, *n; + struct evsel *evsel, *n; LIST_HEAD(head); size_t i; for (i = 0; i < nr_attrs; i++) { - evsel = perf_evsel__new_idx(attrs + i, evlist->nr_entries + i); + evsel = perf_evsel__new_idx(attrs + i, evlist->core.nr_entries + i); if (evsel == NULL) goto out_delete_partial_list; - list_add_tail(&evsel->node, &head); + list_add_tail(&evsel->core.node, &head); } perf_evlist__splice_list_tail(evlist, &head); @@ -277,11 +253,11 @@ static int perf_evlist__add_attrs(struct perf_evlist *evlist, out_delete_partial_list: __evlist__for_each_entry_safe(&head, n, evsel) - perf_evsel__delete(evsel); + evsel__delete(evsel); return -1; } -int __perf_evlist__add_default_attrs(struct perf_evlist *evlist, +int __perf_evlist__add_default_attrs(struct evlist *evlist, struct perf_event_attr *attrs, size_t nr_attrs) { size_t i; @@ -289,31 +265,31 @@ int __perf_evlist__add_default_attrs(struct perf_evlist *evlist, for (i = 0; i < nr_attrs; i++) event_attr_init(attrs + i); - return perf_evlist__add_attrs(evlist, attrs, nr_attrs); + return evlist__add_attrs(evlist, attrs, nr_attrs); } -struct perf_evsel * -perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id) +struct evsel * +perf_evlist__find_tracepoint_by_id(struct evlist *evlist, int id) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { - if (evsel->attr.type == PERF_TYPE_TRACEPOINT && - (int)evsel->attr.config == id) + if (evsel->core.attr.type == PERF_TYPE_TRACEPOINT && + (int)evsel->core.attr.config == id) return evsel; } return NULL; } -struct perf_evsel * -perf_evlist__find_tracepoint_by_name(struct perf_evlist *evlist, +struct evsel * +perf_evlist__find_tracepoint_by_name(struct evlist *evlist, const char *name) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { - if ((evsel->attr.type == PERF_TYPE_TRACEPOINT) && + if ((evsel->core.attr.type == PERF_TYPE_TRACEPOINT) && (strcmp(evsel->name, name) == 0)) return evsel; } @@ -321,66 +297,66 @@ perf_evlist__find_tracepoint_by_name(struct perf_evlist *evlist, return NULL; } -int perf_evlist__add_newtp(struct perf_evlist *evlist, +int perf_evlist__add_newtp(struct evlist *evlist, const char *sys, const char *name, void *handler) { - struct perf_evsel *evsel = perf_evsel__newtp(sys, name); + struct evsel *evsel = perf_evsel__newtp(sys, name); if (IS_ERR(evsel)) return -1; evsel->handler = handler; - perf_evlist__add(evlist, evsel); + evlist__add(evlist, evsel); return 0; } -static int perf_evlist__nr_threads(struct perf_evlist *evlist, - struct perf_evsel *evsel) +static int perf_evlist__nr_threads(struct evlist *evlist, + struct evsel *evsel) { if (evsel->system_wide) return 1; else - return thread_map__nr(evlist->threads); + return perf_thread_map__nr(evlist->core.threads); } -void perf_evlist__disable(struct perf_evlist *evlist) +void evlist__disable(struct evlist *evlist) { - struct perf_evsel *pos; + struct evsel *pos; evlist__for_each_entry(evlist, pos) { - if (pos->disabled || !perf_evsel__is_group_leader(pos) || !pos->fd) + if (pos->disabled || !perf_evsel__is_group_leader(pos) || !pos->core.fd) continue; - perf_evsel__disable(pos); + evsel__disable(pos); } evlist->enabled = false; } -void perf_evlist__enable(struct perf_evlist *evlist) +void evlist__enable(struct evlist *evlist) { - struct perf_evsel *pos; + struct evsel *pos; evlist__for_each_entry(evlist, pos) { - if (!perf_evsel__is_group_leader(pos) || !pos->fd) + if (!perf_evsel__is_group_leader(pos) || !pos->core.fd) continue; - perf_evsel__enable(pos); + evsel__enable(pos); } evlist->enabled = true; } -void perf_evlist__toggle_enable(struct perf_evlist *evlist) +void perf_evlist__toggle_enable(struct evlist *evlist) { - (evlist->enabled ? perf_evlist__disable : perf_evlist__enable)(evlist); + (evlist->enabled ? evlist__disable : evlist__enable)(evlist); } -static int perf_evlist__enable_event_cpu(struct perf_evlist *evlist, - struct perf_evsel *evsel, int cpu) +static int perf_evlist__enable_event_cpu(struct evlist *evlist, + struct evsel *evsel, int cpu) { int thread; int nr_threads = perf_evlist__nr_threads(evlist, evsel); - if (!evsel->fd) + if (!evsel->core.fd) return -EINVAL; for (thread = 0; thread < nr_threads; thread++) { @@ -391,14 +367,14 @@ static int perf_evlist__enable_event_cpu(struct perf_evlist *evlist, return 0; } -static int perf_evlist__enable_event_thread(struct perf_evlist *evlist, - struct perf_evsel *evsel, +static int perf_evlist__enable_event_thread(struct evlist *evlist, + struct evsel *evsel, int thread) { int cpu; - int nr_cpus = cpu_map__nr(evlist->cpus); + int nr_cpus = perf_cpu_map__nr(evlist->core.cpus); - if (!evsel->fd) + if (!evsel->core.fd) return -EINVAL; for (cpu = 0; cpu < nr_cpus; cpu++) { @@ -409,10 +385,10 @@ static int perf_evlist__enable_event_thread(struct perf_evlist *evlist, return 0; } -int perf_evlist__enable_event_idx(struct perf_evlist *evlist, - struct perf_evsel *evsel, int idx) +int perf_evlist__enable_event_idx(struct evlist *evlist, + struct evsel *evsel, int idx) { - bool per_cpu_mmaps = !cpu_map__empty(evlist->cpus); + bool per_cpu_mmaps = !perf_cpu_map__empty(evlist->core.cpus); if (per_cpu_mmaps) return perf_evlist__enable_event_cpu(evlist, evsel, idx); @@ -420,12 +396,12 @@ int perf_evlist__enable_event_idx(struct perf_evlist *evlist, return perf_evlist__enable_event_thread(evlist, evsel, idx); } -int perf_evlist__alloc_pollfd(struct perf_evlist *evlist) +int perf_evlist__alloc_pollfd(struct evlist *evlist) { - int nr_cpus = cpu_map__nr(evlist->cpus); - int nr_threads = thread_map__nr(evlist->threads); + int nr_cpus = perf_cpu_map__nr(evlist->core.cpus); + int nr_threads = perf_thread_map__nr(evlist->core.threads); int nfds = 0; - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { if (evsel->system_wide) @@ -441,7 +417,7 @@ int perf_evlist__alloc_pollfd(struct perf_evlist *evlist) return 0; } -static int __perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd, +static int __perf_evlist__add_pollfd(struct evlist *evlist, int fd, struct perf_mmap *map, short revent) { int pos = fdarray__add(&evlist->pollfd, fd, revent | POLLERR | POLLHUP); @@ -458,7 +434,7 @@ static int __perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd, return pos; } -int perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd) +int perf_evlist__add_pollfd(struct evlist *evlist, int fd) { return __perf_evlist__add_pollfd(evlist, fd, NULL, POLLIN); } @@ -472,19 +448,19 @@ static void perf_evlist__munmap_filtered(struct fdarray *fda, int fd, perf_mmap__put(map); } -int perf_evlist__filter_pollfd(struct perf_evlist *evlist, short revents_and_mask) +int perf_evlist__filter_pollfd(struct evlist *evlist, short revents_and_mask) { return fdarray__filter(&evlist->pollfd, revents_and_mask, perf_evlist__munmap_filtered, NULL); } -int perf_evlist__poll(struct perf_evlist *evlist, int timeout) +int perf_evlist__poll(struct evlist *evlist, int timeout) { return fdarray__poll(&evlist->pollfd, timeout); } -static void perf_evlist__id_hash(struct perf_evlist *evlist, - struct perf_evsel *evsel, +static void perf_evlist__id_hash(struct evlist *evlist, + struct evsel *evsel, int cpu, int thread, u64 id) { int hash; @@ -496,15 +472,15 @@ static void perf_evlist__id_hash(struct perf_evlist *evlist, hlist_add_head(&sid->node, &evlist->heads[hash]); } -void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel, +void perf_evlist__id_add(struct evlist *evlist, struct evsel *evsel, int cpu, int thread, u64 id) { perf_evlist__id_hash(evlist, evsel, cpu, thread, id); evsel->id[evsel->ids++] = id; } -int perf_evlist__id_add_fd(struct perf_evlist *evlist, - struct perf_evsel *evsel, +int perf_evlist__id_add_fd(struct evlist *evlist, + struct evsel *evsel, int cpu, int thread, int fd) { u64 read_data[4] = { 0, }; @@ -528,13 +504,13 @@ int perf_evlist__id_add_fd(struct perf_evlist *evlist, if (perf_evlist__read_format(evlist) & PERF_FORMAT_GROUP) return -1; - if (!(evsel->attr.read_format & PERF_FORMAT_ID) || + if (!(evsel->core.attr.read_format & PERF_FORMAT_ID) || read(fd, &read_data, sizeof(read_data)) == -1) return -1; - if (evsel->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + if (evsel->core.attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) ++id_idx; - if (evsel->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + if (evsel->core.attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) ++id_idx; id = read_data[id_idx]; @@ -544,23 +520,23 @@ int perf_evlist__id_add_fd(struct perf_evlist *evlist, return 0; } -static void perf_evlist__set_sid_idx(struct perf_evlist *evlist, - struct perf_evsel *evsel, int idx, int cpu, +static void perf_evlist__set_sid_idx(struct evlist *evlist, + struct evsel *evsel, int idx, int cpu, int thread) { struct perf_sample_id *sid = SID(evsel, cpu, thread); sid->idx = idx; - if (evlist->cpus && cpu >= 0) - sid->cpu = evlist->cpus->map[cpu]; + if (evlist->core.cpus && cpu >= 0) + sid->cpu = evlist->core.cpus->map[cpu]; else sid->cpu = -1; - if (!evsel->system_wide && evlist->threads && thread >= 0) - sid->tid = thread_map__pid(evlist->threads, thread); + if (!evsel->system_wide && evlist->core.threads && thread >= 0) + sid->tid = perf_thread_map__pid(evlist->core.threads, thread); else sid->tid = -1; } -struct perf_sample_id *perf_evlist__id2sid(struct perf_evlist *evlist, u64 id) +struct perf_sample_id *perf_evlist__id2sid(struct evlist *evlist, u64 id) { struct hlist_head *head; struct perf_sample_id *sid; @@ -576,11 +552,11 @@ struct perf_sample_id *perf_evlist__id2sid(struct perf_evlist *evlist, u64 id) return NULL; } -struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id) +struct evsel *perf_evlist__id2evsel(struct evlist *evlist, u64 id) { struct perf_sample_id *sid; - if (evlist->nr_entries == 1 || !id) + if (evlist->core.nr_entries == 1 || !id) return perf_evlist__first(evlist); sid = perf_evlist__id2sid(evlist, id); @@ -593,7 +569,7 @@ struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id) return NULL; } -struct perf_evsel *perf_evlist__id2evsel_strict(struct perf_evlist *evlist, +struct evsel *perf_evlist__id2evsel_strict(struct evlist *evlist, u64 id) { struct perf_sample_id *sid; @@ -608,7 +584,7 @@ struct perf_evsel *perf_evlist__id2evsel_strict(struct perf_evlist *evlist, return NULL; } -static int perf_evlist__event2id(struct perf_evlist *evlist, +static int perf_evlist__event2id(struct evlist *evlist, union perf_event *event, u64 *id) { const u64 *array = event->sample.array; @@ -629,19 +605,19 @@ static int perf_evlist__event2id(struct perf_evlist *evlist, return 0; } -struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist, +struct evsel *perf_evlist__event2evsel(struct evlist *evlist, union perf_event *event) { - struct perf_evsel *first = perf_evlist__first(evlist); + struct evsel *first = perf_evlist__first(evlist); struct hlist_head *head; struct perf_sample_id *sid; int hash; u64 id; - if (evlist->nr_entries == 1) + if (evlist->core.nr_entries == 1) return first; - if (!first->attr.sample_id_all && + if (!first->core.attr.sample_id_all && event->header.type != PERF_RECORD_SAMPLE) return first; @@ -662,7 +638,7 @@ struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist, return NULL; } -static int perf_evlist__set_paused(struct perf_evlist *evlist, bool value) +static int perf_evlist__set_paused(struct evlist *evlist, bool value) { int i; @@ -682,17 +658,17 @@ static int perf_evlist__set_paused(struct perf_evlist *evlist, bool value) return 0; } -static int perf_evlist__pause(struct perf_evlist *evlist) +static int perf_evlist__pause(struct evlist *evlist) { return perf_evlist__set_paused(evlist, true); } -static int perf_evlist__resume(struct perf_evlist *evlist) +static int perf_evlist__resume(struct evlist *evlist) { return perf_evlist__set_paused(evlist, false); } -static void perf_evlist__munmap_nofree(struct perf_evlist *evlist) +static void perf_evlist__munmap_nofree(struct evlist *evlist) { int i; @@ -705,22 +681,22 @@ static void perf_evlist__munmap_nofree(struct perf_evlist *evlist) perf_mmap__munmap(&evlist->overwrite_mmap[i]); } -void perf_evlist__munmap(struct perf_evlist *evlist) +void perf_evlist__munmap(struct evlist *evlist) { perf_evlist__munmap_nofree(evlist); zfree(&evlist->mmap); zfree(&evlist->overwrite_mmap); } -static struct perf_mmap *perf_evlist__alloc_mmap(struct perf_evlist *evlist, +static struct perf_mmap *perf_evlist__alloc_mmap(struct evlist *evlist, bool overwrite) { int i; struct perf_mmap *map; - evlist->nr_mmaps = cpu_map__nr(evlist->cpus); - if (cpu_map__empty(evlist->cpus)) - evlist->nr_mmaps = thread_map__nr(evlist->threads); + evlist->nr_mmaps = perf_cpu_map__nr(evlist->core.cpus); + if (perf_cpu_map__empty(evlist->core.cpus)) + evlist->nr_mmaps = perf_thread_map__nr(evlist->core.threads); map = zalloc(evlist->nr_mmaps * sizeof(struct perf_mmap)); if (!map) return NULL; @@ -743,21 +719,21 @@ static struct perf_mmap *perf_evlist__alloc_mmap(struct perf_evlist *evlist, } static bool -perf_evlist__should_poll(struct perf_evlist *evlist __maybe_unused, - struct perf_evsel *evsel) +perf_evlist__should_poll(struct evlist *evlist __maybe_unused, + struct evsel *evsel) { - if (evsel->attr.write_backward) + if (evsel->core.attr.write_backward) return false; return true; } -static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx, +static int perf_evlist__mmap_per_evsel(struct evlist *evlist, int idx, struct mmap_params *mp, int cpu_idx, int thread, int *_output, int *_output_overwrite) { - struct perf_evsel *evsel; + struct evsel *evsel; int revent; - int evlist_cpu = cpu_map__cpu(evlist->cpus, cpu_idx); + int evlist_cpu = cpu_map__cpu(evlist->core.cpus, cpu_idx); evlist__for_each_entry(evlist, evsel) { struct perf_mmap *maps = evlist->mmap; @@ -766,7 +742,7 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx, int cpu; mp->prot = PROT_READ | PROT_WRITE; - if (evsel->attr.write_backward) { + if (evsel->core.attr.write_backward) { output = _output_overwrite; maps = evlist->overwrite_mmap; @@ -784,7 +760,7 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx, if (evsel->system_wide && thread) continue; - cpu = cpu_map__idx(evsel->cpus, evlist_cpu); + cpu = perf_cpu_map__idx(evsel->core.cpus, evlist_cpu); if (cpu == -1) continue; @@ -817,7 +793,7 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx, return -1; } - if (evsel->attr.read_format & PERF_FORMAT_ID) { + if (evsel->core.attr.read_format & PERF_FORMAT_ID) { if (perf_evlist__id_add_fd(evlist, evsel, cpu, thread, fd) < 0) return -1; @@ -829,12 +805,12 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx, return 0; } -static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, +static int perf_evlist__mmap_per_cpu(struct evlist *evlist, struct mmap_params *mp) { int cpu, thread; - int nr_cpus = cpu_map__nr(evlist->cpus); - int nr_threads = thread_map__nr(evlist->threads); + int nr_cpus = perf_cpu_map__nr(evlist->core.cpus); + int nr_threads = perf_thread_map__nr(evlist->core.threads); pr_debug2("perf event ring buffer mmapped per cpu\n"); for (cpu = 0; cpu < nr_cpus; cpu++) { @@ -858,11 +834,11 @@ out_unmap: return -1; } -static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, +static int perf_evlist__mmap_per_thread(struct evlist *evlist, struct mmap_params *mp) { int thread; - int nr_threads = thread_map__nr(evlist->threads); + int nr_threads = perf_thread_map__nr(evlist->core.threads); pr_debug2("perf event ring buffer mmapped per thread\n"); for (thread = 0; thread < nr_threads; thread++) { @@ -1006,14 +982,14 @@ int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str, * * Return: %0 on success, negative error code otherwise. */ -int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages, +int perf_evlist__mmap_ex(struct evlist *evlist, unsigned int pages, unsigned int auxtrace_pages, bool auxtrace_overwrite, int nr_cblocks, int affinity, int flush, int comp_level) { - struct perf_evsel *evsel; - const struct cpu_map *cpus = evlist->cpus; - const struct thread_map *threads = evlist->threads; + struct evsel *evsel; + const struct perf_cpu_map *cpus = evlist->core.cpus; + const struct perf_thread_map *threads = evlist->core.threads; /* * Delay setting mp.prot: set it before calling perf_mmap__mmap. * Its value is decided by evsel's write_backward. @@ -1038,28 +1014,28 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages, auxtrace_pages, auxtrace_overwrite); evlist__for_each_entry(evlist, evsel) { - if ((evsel->attr.read_format & PERF_FORMAT_ID) && + if ((evsel->core.attr.read_format & PERF_FORMAT_ID) && evsel->sample_id == NULL && - perf_evsel__alloc_id(evsel, cpu_map__nr(cpus), threads->nr) < 0) + perf_evsel__alloc_id(evsel, perf_cpu_map__nr(cpus), threads->nr) < 0) return -ENOMEM; } - if (cpu_map__empty(cpus)) + if (perf_cpu_map__empty(cpus)) return perf_evlist__mmap_per_thread(evlist, &mp); return perf_evlist__mmap_per_cpu(evlist, &mp); } -int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages) +int perf_evlist__mmap(struct evlist *evlist, unsigned int pages) { return perf_evlist__mmap_ex(evlist, pages, 0, false, 0, PERF_AFFINITY_SYS, 1, 0); } -int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target) +int perf_evlist__create_maps(struct evlist *evlist, struct target *target) { bool all_threads = (target->per_thread && target->system_wide); - struct cpu_map *cpus; - struct thread_map *threads; + struct perf_cpu_map *cpus; + struct perf_thread_map *threads; /* * If specify '-a' and '--per-thread' to perf record, perf record @@ -1086,68 +1062,45 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target) return -1; if (target__uses_dummy_map(target)) - cpus = cpu_map__dummy_new(); + cpus = perf_cpu_map__dummy_new(); else - cpus = cpu_map__new(target->cpu_list); + cpus = perf_cpu_map__new(target->cpu_list); if (!cpus) goto out_delete_threads; - evlist->has_user_cpus = !!target->cpu_list; + evlist->core.has_user_cpus = !!target->cpu_list; - perf_evlist__set_maps(evlist, cpus, threads); + perf_evlist__set_maps(&evlist->core, cpus, threads); return 0; out_delete_threads: - thread_map__put(threads); + perf_thread_map__put(threads); return -1; } -void perf_evlist__set_maps(struct perf_evlist *evlist, struct cpu_map *cpus, - struct thread_map *threads) -{ - /* - * Allow for the possibility that one or another of the maps isn't being - * changed i.e. don't put it. Note we are assuming the maps that are - * being applied are brand new and evlist is taking ownership of the - * original reference count of 1. If that is not the case it is up to - * the caller to increase the reference count. - */ - if (cpus != evlist->cpus) { - cpu_map__put(evlist->cpus); - evlist->cpus = cpu_map__get(cpus); - } - - if (threads != evlist->threads) { - thread_map__put(evlist->threads); - evlist->threads = thread_map__get(threads); - } - - perf_evlist__propagate_maps(evlist); -} - -void __perf_evlist__set_sample_bit(struct perf_evlist *evlist, +void __perf_evlist__set_sample_bit(struct evlist *evlist, enum perf_event_sample_format bit) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) __perf_evsel__set_sample_bit(evsel, bit); } -void __perf_evlist__reset_sample_bit(struct perf_evlist *evlist, +void __perf_evlist__reset_sample_bit(struct evlist *evlist, enum perf_event_sample_format bit) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) __perf_evsel__reset_sample_bit(evsel, bit); } -int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **err_evsel) +int perf_evlist__apply_filters(struct evlist *evlist, struct evsel **err_evsel) { - struct perf_evsel *evsel; + struct evsel *evsel; int err = 0; evlist__for_each_entry(evlist, evsel) { @@ -1158,7 +1111,7 @@ int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **e * filters only work for tracepoint event, which doesn't have cpu limit. * So evlist and evsel should always be same. */ - err = perf_evsel__apply_filter(evsel, evsel->filter); + err = perf_evsel__apply_filter(&evsel->core, evsel->filter); if (err) { *err_evsel = evsel; break; @@ -1168,13 +1121,13 @@ int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **e return err; } -int perf_evlist__set_tp_filter(struct perf_evlist *evlist, const char *filter) +int perf_evlist__set_tp_filter(struct evlist *evlist, const char *filter) { - struct perf_evsel *evsel; + struct evsel *evsel; int err = 0; evlist__for_each_entry(evlist, evsel) { - if (evsel->attr.type != PERF_TYPE_TRACEPOINT) + if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT) continue; err = perf_evsel__set_filter(evsel, filter); @@ -1185,7 +1138,7 @@ int perf_evlist__set_tp_filter(struct perf_evlist *evlist, const char *filter) return err; } -int perf_evlist__set_tp_filter_pids(struct perf_evlist *evlist, size_t npids, pid_t *pids) +int perf_evlist__set_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids) { char *filter; int ret = -1; @@ -1212,16 +1165,16 @@ out_free: return ret; } -int perf_evlist__set_tp_filter_pid(struct perf_evlist *evlist, pid_t pid) +int perf_evlist__set_tp_filter_pid(struct evlist *evlist, pid_t pid) { return perf_evlist__set_tp_filter_pids(evlist, 1, &pid); } -bool perf_evlist__valid_sample_type(struct perf_evlist *evlist) +bool perf_evlist__valid_sample_type(struct evlist *evlist) { - struct perf_evsel *pos; + struct evsel *pos; - if (evlist->nr_entries == 1) + if (evlist->core.nr_entries == 1) return true; if (evlist->id_pos < 0 || evlist->is_pos < 0) @@ -1236,43 +1189,43 @@ bool perf_evlist__valid_sample_type(struct perf_evlist *evlist) return true; } -u64 __perf_evlist__combined_sample_type(struct perf_evlist *evlist) +u64 __perf_evlist__combined_sample_type(struct evlist *evlist) { - struct perf_evsel *evsel; + struct evsel *evsel; if (evlist->combined_sample_type) return evlist->combined_sample_type; evlist__for_each_entry(evlist, evsel) - evlist->combined_sample_type |= evsel->attr.sample_type; + evlist->combined_sample_type |= evsel->core.attr.sample_type; return evlist->combined_sample_type; } -u64 perf_evlist__combined_sample_type(struct perf_evlist *evlist) +u64 perf_evlist__combined_sample_type(struct evlist *evlist) { evlist->combined_sample_type = 0; return __perf_evlist__combined_sample_type(evlist); } -u64 perf_evlist__combined_branch_type(struct perf_evlist *evlist) +u64 perf_evlist__combined_branch_type(struct evlist *evlist) { - struct perf_evsel *evsel; + struct evsel *evsel; u64 branch_type = 0; evlist__for_each_entry(evlist, evsel) - branch_type |= evsel->attr.branch_sample_type; + branch_type |= evsel->core.attr.branch_sample_type; return branch_type; } -bool perf_evlist__valid_read_format(struct perf_evlist *evlist) +bool perf_evlist__valid_read_format(struct evlist *evlist) { - struct perf_evsel *first = perf_evlist__first(evlist), *pos = first; - u64 read_format = first->attr.read_format; - u64 sample_type = first->attr.sample_type; + struct evsel *first = perf_evlist__first(evlist), *pos = first; + u64 read_format = first->core.attr.read_format; + u64 sample_type = first->core.attr.sample_type; evlist__for_each_entry(evlist, pos) { - if (read_format != pos->attr.read_format) + if (read_format != pos->core.attr.read_format) return false; } @@ -1285,23 +1238,23 @@ bool perf_evlist__valid_read_format(struct perf_evlist *evlist) return true; } -u64 perf_evlist__read_format(struct perf_evlist *evlist) +u64 perf_evlist__read_format(struct evlist *evlist) { - struct perf_evsel *first = perf_evlist__first(evlist); - return first->attr.read_format; + struct evsel *first = perf_evlist__first(evlist); + return first->core.attr.read_format; } -u16 perf_evlist__id_hdr_size(struct perf_evlist *evlist) +u16 perf_evlist__id_hdr_size(struct evlist *evlist) { - struct perf_evsel *first = perf_evlist__first(evlist); + struct evsel *first = perf_evlist__first(evlist); struct perf_sample *data; u64 sample_type; u16 size = 0; - if (!first->attr.sample_id_all) + if (!first->core.attr.sample_id_all) goto out; - sample_type = first->attr.sample_type; + sample_type = first->core.attr.sample_type; if (sample_type & PERF_SAMPLE_TID) size += sizeof(data->tid) * 2; @@ -1324,42 +1277,42 @@ out: return size; } -bool perf_evlist__valid_sample_id_all(struct perf_evlist *evlist) +bool perf_evlist__valid_sample_id_all(struct evlist *evlist) { - struct perf_evsel *first = perf_evlist__first(evlist), *pos = first; + struct evsel *first = perf_evlist__first(evlist), *pos = first; evlist__for_each_entry_continue(evlist, pos) { - if (first->attr.sample_id_all != pos->attr.sample_id_all) + if (first->core.attr.sample_id_all != pos->core.attr.sample_id_all) return false; } return true; } -bool perf_evlist__sample_id_all(struct perf_evlist *evlist) +bool perf_evlist__sample_id_all(struct evlist *evlist) { - struct perf_evsel *first = perf_evlist__first(evlist); - return first->attr.sample_id_all; + struct evsel *first = perf_evlist__first(evlist); + return first->core.attr.sample_id_all; } -void perf_evlist__set_selected(struct perf_evlist *evlist, - struct perf_evsel *evsel) +void perf_evlist__set_selected(struct evlist *evlist, + struct evsel *evsel) { evlist->selected = evsel; } -void perf_evlist__close(struct perf_evlist *evlist) +void evlist__close(struct evlist *evlist) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry_reverse(evlist, evsel) - perf_evsel__close(evsel); + evsel__close(evsel); } -static int perf_evlist__create_syswide_maps(struct perf_evlist *evlist) +static int perf_evlist__create_syswide_maps(struct evlist *evlist) { - struct cpu_map *cpus; - struct thread_map *threads; + struct perf_cpu_map *cpus; + struct perf_thread_map *threads; int err = -ENOMEM; /* @@ -1371,32 +1324,32 @@ static int perf_evlist__create_syswide_maps(struct perf_evlist *evlist) * error, and we may not want to do that fallback to a * default cpu identity map :-\ */ - cpus = cpu_map__new(NULL); + cpus = perf_cpu_map__new(NULL); if (!cpus) goto out; - threads = thread_map__new_dummy(); + threads = perf_thread_map__new_dummy(); if (!threads) goto out_put; - perf_evlist__set_maps(evlist, cpus, threads); + perf_evlist__set_maps(&evlist->core, cpus, threads); out: return err; out_put: - cpu_map__put(cpus); + perf_cpu_map__put(cpus); goto out; } -int perf_evlist__open(struct perf_evlist *evlist) +int evlist__open(struct evlist *evlist) { - struct perf_evsel *evsel; + struct evsel *evsel; int err; /* * Default: one fd per CPU, all threads, aka systemwide * as sys_perf_event_open(cpu = -1, thread = -1) is EINVAL */ - if (evlist->threads == NULL && evlist->cpus == NULL) { + if (evlist->core.threads == NULL && evlist->core.cpus == NULL) { err = perf_evlist__create_syswide_maps(evlist); if (err < 0) goto out_err; @@ -1405,19 +1358,19 @@ int perf_evlist__open(struct perf_evlist *evlist) perf_evlist__update_id_pos(evlist); evlist__for_each_entry(evlist, evsel) { - err = perf_evsel__open(evsel, evsel->cpus, evsel->threads); + err = evsel__open(evsel, evsel->core.cpus, evsel->core.threads); if (err < 0) goto out_err; } return 0; out_err: - perf_evlist__close(evlist); + evlist__close(evlist); errno = -err; return err; } -int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct target *target, +int perf_evlist__prepare_workload(struct evlist *evlist, struct target *target, const char *argv[], bool pipe_output, void (*exec_error)(int signo, siginfo_t *info, void *ucontext)) { @@ -1499,12 +1452,12 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct target *tar } if (target__none(target)) { - if (evlist->threads == NULL) { + if (evlist->core.threads == NULL) { fprintf(stderr, "FATAL: evlist->threads need to be set at this point (%s:%d).\n", __func__, __LINE__); goto out_close_pipes; } - thread_map__set_pid(evlist->threads, 0, evlist->workload.pid); + perf_thread_map__set_pid(evlist->core.threads, 0, evlist->workload.pid); } close(child_ready_pipe[1]); @@ -1531,7 +1484,7 @@ out_close_ready_pipe: return -1; } -int perf_evlist__start_workload(struct perf_evlist *evlist) +int perf_evlist__start_workload(struct evlist *evlist) { if (evlist->workload.cork_fd > 0) { char bf = 0; @@ -1550,30 +1503,30 @@ int perf_evlist__start_workload(struct perf_evlist *evlist) return 0; } -int perf_evlist__parse_sample(struct perf_evlist *evlist, union perf_event *event, +int perf_evlist__parse_sample(struct evlist *evlist, union perf_event *event, struct perf_sample *sample) { - struct perf_evsel *evsel = perf_evlist__event2evsel(evlist, event); + struct evsel *evsel = perf_evlist__event2evsel(evlist, event); if (!evsel) return -EFAULT; return perf_evsel__parse_sample(evsel, event, sample); } -int perf_evlist__parse_sample_timestamp(struct perf_evlist *evlist, +int perf_evlist__parse_sample_timestamp(struct evlist *evlist, union perf_event *event, u64 *timestamp) { - struct perf_evsel *evsel = perf_evlist__event2evsel(evlist, event); + struct evsel *evsel = perf_evlist__event2evsel(evlist, event); if (!evsel) return -EFAULT; return perf_evsel__parse_sample_timestamp(evsel, event, timestamp); } -size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp) +size_t perf_evlist__fprintf(struct evlist *evlist, FILE *fp) { - struct perf_evsel *evsel; + struct evsel *evsel; size_t printed = 0; evlist__for_each_entry(evlist, evsel) { @@ -1584,7 +1537,7 @@ size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp) return printed + fprintf(fp, "\n"); } -int perf_evlist__strerror_open(struct perf_evlist *evlist, +int perf_evlist__strerror_open(struct evlist *evlist, int err, char *buf, size_t size) { int printed, value; @@ -1613,20 +1566,20 @@ int perf_evlist__strerror_open(struct perf_evlist *evlist, "Hint:\tThe current value is %d.", value); break; case EINVAL: { - struct perf_evsel *first = perf_evlist__first(evlist); + struct evsel *first = perf_evlist__first(evlist); int max_freq; if (sysctl__read_int("kernel/perf_event_max_sample_rate", &max_freq) < 0) goto out_default; - if (first->attr.sample_freq < (u64)max_freq) + if (first->core.attr.sample_freq < (u64)max_freq) goto out_default; printed = scnprintf(buf, size, "Error:\t%s.\n" "Hint:\tCheck /proc/sys/kernel/perf_event_max_sample_rate.\n" "Hint:\tThe current value is %d and %" PRIu64 " is being requested.", - emsg, max_freq, first->attr.sample_freq); + emsg, max_freq, first->core.attr.sample_freq); break; } default: @@ -1638,7 +1591,7 @@ out_default: return 0; } -int perf_evlist__strerror_mmap(struct perf_evlist *evlist, int err, char *buf, size_t size) +int perf_evlist__strerror_mmap(struct evlist *evlist, int err, char *buf, size_t size) { char sbuf[STRERR_BUFSIZE], *emsg = str_error_r(err, sbuf, sizeof(sbuf)); int pages_attempted = evlist->mmap_len / 1024, pages_max_per_user, printed = 0; @@ -1669,10 +1622,10 @@ int perf_evlist__strerror_mmap(struct perf_evlist *evlist, int err, char *buf, s return 0; } -void perf_evlist__to_front(struct perf_evlist *evlist, - struct perf_evsel *move_evsel) +void perf_evlist__to_front(struct evlist *evlist, + struct evsel *move_evsel) { - struct perf_evsel *evsel, *n; + struct evsel *evsel, *n; LIST_HEAD(move); if (move_evsel == perf_evlist__first(evlist)) @@ -1680,16 +1633,16 @@ void perf_evlist__to_front(struct perf_evlist *evlist, evlist__for_each_entry_safe(evlist, n, evsel) { if (evsel->leader == move_evsel->leader) - list_move_tail(&evsel->node, &move); + list_move_tail(&evsel->core.node, &move); } - list_splice(&move, &evlist->entries); + list_splice(&move, &evlist->core.entries); } -void perf_evlist__set_tracking_event(struct perf_evlist *evlist, - struct perf_evsel *tracking_evsel) +void perf_evlist__set_tracking_event(struct evlist *evlist, + struct evsel *tracking_evsel) { - struct perf_evsel *evsel; + struct evsel *evsel; if (tracking_evsel->tracking) return; @@ -1702,11 +1655,11 @@ void perf_evlist__set_tracking_event(struct perf_evlist *evlist, tracking_evsel->tracking = true; } -struct perf_evsel * -perf_evlist__find_evsel_by_str(struct perf_evlist *evlist, +struct evsel * +perf_evlist__find_evsel_by_str(struct evlist *evlist, const char *str) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { if (!evsel->name) @@ -1718,7 +1671,7 @@ perf_evlist__find_evsel_by_str(struct perf_evlist *evlist, return NULL; } -void perf_evlist__toggle_bkw_mmap(struct perf_evlist *evlist, +void perf_evlist__toggle_bkw_mmap(struct evlist *evlist, enum bkw_mmap_state state) { enum bkw_mmap_state old_state = evlist->bkw_mmap_state; @@ -1776,12 +1729,12 @@ state_err: return; } -bool perf_evlist__exclude_kernel(struct perf_evlist *evlist) +bool perf_evlist__exclude_kernel(struct evlist *evlist) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { - if (!evsel->attr.exclude_kernel) + if (!evsel->core.attr.exclude_kernel) return false; } @@ -1793,25 +1746,25 @@ bool perf_evlist__exclude_kernel(struct perf_evlist *evlist) * the group display. Set the artificial group and set the leader's * forced_leader flag to notify the display code. */ -void perf_evlist__force_leader(struct perf_evlist *evlist) +void perf_evlist__force_leader(struct evlist *evlist) { if (!evlist->nr_groups) { - struct perf_evsel *leader = perf_evlist__first(evlist); + struct evsel *leader = perf_evlist__first(evlist); perf_evlist__set_leader(evlist); leader->forced_leader = true; } } -struct perf_evsel *perf_evlist__reset_weak_group(struct perf_evlist *evsel_list, - struct perf_evsel *evsel) +struct evsel *perf_evlist__reset_weak_group(struct evlist *evsel_list, + struct evsel *evsel) { - struct perf_evsel *c2, *leader; + struct evsel *c2, *leader; bool is_open = true; leader = evsel->leader; pr_debug("Weak group for %s/%d failed\n", - leader->name, leader->nr_members); + leader->name, leader->core.nr_members); /* * for_each_group_member doesn't work here because it doesn't @@ -1822,24 +1775,24 @@ struct perf_evsel *perf_evlist__reset_weak_group(struct perf_evlist *evsel_list, is_open = false; if (c2->leader == leader) { if (is_open) - perf_evsel__close(c2); + evsel__close(c2); c2->leader = c2; - c2->nr_members = 0; + c2->core.nr_members = 0; } } return leader; } -int perf_evlist__add_sb_event(struct perf_evlist **evlist, +int perf_evlist__add_sb_event(struct evlist **evlist, struct perf_event_attr *attr, perf_evsel__sb_cb_t cb, void *data) { - struct perf_evsel *evsel; + struct evsel *evsel; bool new_evlist = (*evlist) == NULL; if (*evlist == NULL) - *evlist = perf_evlist__new(); + *evlist = evlist__new(); if (*evlist == NULL) return -1; @@ -1848,18 +1801,18 @@ int perf_evlist__add_sb_event(struct perf_evlist **evlist, attr->sample_id_all = 1; } - evsel = perf_evsel__new_idx(attr, (*evlist)->nr_entries); + evsel = perf_evsel__new_idx(attr, (*evlist)->core.nr_entries); if (!evsel) goto out_err; evsel->side_band.cb = cb; evsel->side_band.data = data; - perf_evlist__add(*evlist, evsel); + evlist__add(*evlist, evsel); return 0; out_err: if (new_evlist) { - perf_evlist__delete(*evlist); + evlist__delete(*evlist); *evlist = NULL; } return -1; @@ -1867,7 +1820,7 @@ out_err: static void *perf_evlist__poll_thread(void *arg) { - struct perf_evlist *evlist = arg; + struct evlist *evlist = arg; bool draining = false; int i, done = 0; @@ -1887,7 +1840,7 @@ static void *perf_evlist__poll_thread(void *arg) if (perf_mmap__read_init(map)) continue; while ((event = perf_mmap__read_event(map)) != NULL) { - struct perf_evsel *evsel = perf_evlist__event2evsel(evlist, event); + struct evsel *evsel = perf_evlist__event2evsel(evlist, event); if (evsel && evsel->side_band.cb) evsel->side_band.cb(event, evsel->side_band.data); @@ -1906,10 +1859,10 @@ static void *perf_evlist__poll_thread(void *arg) return NULL; } -int perf_evlist__start_sb_thread(struct perf_evlist *evlist, +int perf_evlist__start_sb_thread(struct evlist *evlist, struct target *target) { - struct perf_evsel *counter; + struct evsel *counter; if (!evlist) return 0; @@ -1918,8 +1871,8 @@ int perf_evlist__start_sb_thread(struct perf_evlist *evlist, goto out_delete_evlist; evlist__for_each_entry(evlist, counter) { - if (perf_evsel__open(counter, evlist->cpus, - evlist->threads) < 0) + if (evsel__open(counter, evlist->core.cpus, + evlist->core.threads) < 0) goto out_delete_evlist; } @@ -1927,7 +1880,7 @@ int perf_evlist__start_sb_thread(struct perf_evlist *evlist, goto out_delete_evlist; evlist__for_each_entry(evlist, counter) { - if (perf_evsel__enable(counter)) + if (evsel__enable(counter)) goto out_delete_evlist; } @@ -1938,16 +1891,16 @@ int perf_evlist__start_sb_thread(struct perf_evlist *evlist, return 0; out_delete_evlist: - perf_evlist__delete(evlist); + evlist__delete(evlist); evlist = NULL; return -1; } -void perf_evlist__stop_sb_thread(struct perf_evlist *evlist) +void perf_evlist__stop_sb_thread(struct evlist *evlist) { if (!evlist) return; evlist->thread.done = 1; pthread_join(evlist->thread.th, NULL); - perf_evlist__delete(evlist); + evlist__delete(evlist); } diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 49354fe24d5f..e31ddcc058f2 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -8,6 +8,7 @@ #include <linux/list.h> #include <api/fd/array.h> #include <stdio.h> +#include <internal/evlist.h> #include "../perf.h" #include "event.h" #include "evsel.h" @@ -18,20 +19,18 @@ struct pollfd; struct thread_map; -struct cpu_map; +struct perf_cpu_map; struct record_opts; #define PERF_EVLIST__HLIST_BITS 8 #define PERF_EVLIST__HLIST_SIZE (1 << PERF_EVLIST__HLIST_BITS) -struct perf_evlist { - struct list_head entries; +struct evlist { + struct perf_evlist core; struct hlist_head heads[PERF_EVLIST__HLIST_SIZE]; - int nr_entries; int nr_groups; int nr_mmaps; bool enabled; - bool has_user_cpus; size_t mmap_len; int id_pos; int is_pos; @@ -44,12 +43,10 @@ struct perf_evlist { struct fdarray pollfd; struct perf_mmap *mmap; struct perf_mmap *overwrite_mmap; - struct thread_map *threads; - struct cpu_map *cpus; - struct perf_evsel *selected; + struct evsel *selected; struct events_stats stats; struct perf_env *env; - void (*trace_event_sample_raw)(struct perf_evlist *evlist, + void (*trace_event_sample_raw)(struct evlist *evlist, union perf_event *event, struct perf_sample *sample); u64 first_sample_time; @@ -60,51 +57,51 @@ struct perf_evlist { } thread; }; -struct perf_evsel_str_handler { +struct evsel_str_handler { const char *name; void *handler; }; -struct perf_evlist *perf_evlist__new(void); -struct perf_evlist *perf_evlist__new_default(void); -struct perf_evlist *perf_evlist__new_dummy(void); -void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus, - struct thread_map *threads); -void perf_evlist__exit(struct perf_evlist *evlist); -void perf_evlist__delete(struct perf_evlist *evlist); +struct evlist *evlist__new(void); +struct evlist *perf_evlist__new_default(void); +struct evlist *perf_evlist__new_dummy(void); +void evlist__init(struct evlist *evlist, struct perf_cpu_map *cpus, + struct perf_thread_map *threads); +void perf_evlist__exit(struct evlist *evlist); +void evlist__delete(struct evlist *evlist); -void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry); -void perf_evlist__remove(struct perf_evlist *evlist, struct perf_evsel *evsel); +void evlist__add(struct evlist *evlist, struct evsel *entry); +void evlist__remove(struct evlist *evlist, struct evsel *evsel); -int __perf_evlist__add_default(struct perf_evlist *evlist, bool precise); +int __perf_evlist__add_default(struct evlist *evlist, bool precise); -static inline int perf_evlist__add_default(struct perf_evlist *evlist) +static inline int perf_evlist__add_default(struct evlist *evlist) { return __perf_evlist__add_default(evlist, true); } -int __perf_evlist__add_default_attrs(struct perf_evlist *evlist, +int __perf_evlist__add_default_attrs(struct evlist *evlist, struct perf_event_attr *attrs, size_t nr_attrs); #define perf_evlist__add_default_attrs(evlist, array) \ __perf_evlist__add_default_attrs(evlist, array, ARRAY_SIZE(array)) -int perf_evlist__add_dummy(struct perf_evlist *evlist); +int perf_evlist__add_dummy(struct evlist *evlist); -int perf_evlist__add_sb_event(struct perf_evlist **evlist, +int perf_evlist__add_sb_event(struct evlist **evlist, struct perf_event_attr *attr, perf_evsel__sb_cb_t cb, void *data); -int perf_evlist__start_sb_thread(struct perf_evlist *evlist, +int perf_evlist__start_sb_thread(struct evlist *evlist, struct target *target); -void perf_evlist__stop_sb_thread(struct perf_evlist *evlist); +void perf_evlist__stop_sb_thread(struct evlist *evlist); -int perf_evlist__add_newtp(struct perf_evlist *evlist, +int perf_evlist__add_newtp(struct evlist *evlist, const char *sys, const char *name, void *handler); -void __perf_evlist__set_sample_bit(struct perf_evlist *evlist, +void __perf_evlist__set_sample_bit(struct evlist *evlist, enum perf_event_sample_format bit); -void __perf_evlist__reset_sample_bit(struct perf_evlist *evlist, +void __perf_evlist__reset_sample_bit(struct evlist *evlist, enum perf_event_sample_format bit); #define perf_evlist__set_sample_bit(evlist, bit) \ @@ -113,58 +110,58 @@ void __perf_evlist__reset_sample_bit(struct perf_evlist *evlist, #define perf_evlist__reset_sample_bit(evlist, bit) \ __perf_evlist__reset_sample_bit(evlist, PERF_SAMPLE_##bit) -int perf_evlist__set_tp_filter(struct perf_evlist *evlist, const char *filter); -int perf_evlist__set_tp_filter_pid(struct perf_evlist *evlist, pid_t pid); -int perf_evlist__set_tp_filter_pids(struct perf_evlist *evlist, size_t npids, pid_t *pids); +int perf_evlist__set_tp_filter(struct evlist *evlist, const char *filter); +int perf_evlist__set_tp_filter_pid(struct evlist *evlist, pid_t pid); +int perf_evlist__set_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids); -struct perf_evsel * -perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id); +struct evsel * +perf_evlist__find_tracepoint_by_id(struct evlist *evlist, int id); -struct perf_evsel * -perf_evlist__find_tracepoint_by_name(struct perf_evlist *evlist, +struct evsel * +perf_evlist__find_tracepoint_by_name(struct evlist *evlist, const char *name); -void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel, +void perf_evlist__id_add(struct evlist *evlist, struct evsel *evsel, int cpu, int thread, u64 id); -int perf_evlist__id_add_fd(struct perf_evlist *evlist, - struct perf_evsel *evsel, +int perf_evlist__id_add_fd(struct evlist *evlist, + struct evsel *evsel, int cpu, int thread, int fd); -int perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd); -int perf_evlist__alloc_pollfd(struct perf_evlist *evlist); -int perf_evlist__filter_pollfd(struct perf_evlist *evlist, short revents_and_mask); +int perf_evlist__add_pollfd(struct evlist *evlist, int fd); +int perf_evlist__alloc_pollfd(struct evlist *evlist); +int perf_evlist__filter_pollfd(struct evlist *evlist, short revents_and_mask); -int perf_evlist__poll(struct perf_evlist *evlist, int timeout); +int perf_evlist__poll(struct evlist *evlist, int timeout); -struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id); -struct perf_evsel *perf_evlist__id2evsel_strict(struct perf_evlist *evlist, +struct evsel *perf_evlist__id2evsel(struct evlist *evlist, u64 id); +struct evsel *perf_evlist__id2evsel_strict(struct evlist *evlist, u64 id); -struct perf_sample_id *perf_evlist__id2sid(struct perf_evlist *evlist, u64 id); +struct perf_sample_id *perf_evlist__id2sid(struct evlist *evlist, u64 id); -void perf_evlist__toggle_bkw_mmap(struct perf_evlist *evlist, enum bkw_mmap_state state); +void perf_evlist__toggle_bkw_mmap(struct evlist *evlist, enum bkw_mmap_state state); -void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx); +void perf_evlist__mmap_consume(struct evlist *evlist, int idx); -int perf_evlist__open(struct perf_evlist *evlist); -void perf_evlist__close(struct perf_evlist *evlist); +int evlist__open(struct evlist *evlist); +void evlist__close(struct evlist *evlist); struct callchain_param; -void perf_evlist__set_id_pos(struct perf_evlist *evlist); +void perf_evlist__set_id_pos(struct evlist *evlist); bool perf_can_sample_identifier(void); bool perf_can_record_switch_events(void); bool perf_can_record_cpu_wide(void); -void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts, +void perf_evlist__config(struct evlist *evlist, struct record_opts *opts, struct callchain_param *callchain); int record_opts__config(struct record_opts *opts); -int perf_evlist__prepare_workload(struct perf_evlist *evlist, +int perf_evlist__prepare_workload(struct evlist *evlist, struct target *target, const char *argv[], bool pipe_output, void (*exec_error)(int signo, siginfo_t *info, void *ucontext)); -int perf_evlist__start_workload(struct perf_evlist *evlist); +int perf_evlist__start_workload(struct evlist *evlist); struct option; @@ -175,77 +172,75 @@ int perf_evlist__parse_mmap_pages(const struct option *opt, unsigned long perf_event_mlock_kb_in_pages(void); -int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages, +int perf_evlist__mmap_ex(struct evlist *evlist, unsigned int pages, unsigned int auxtrace_pages, bool auxtrace_overwrite, int nr_cblocks, int affinity, int flush, int comp_level); -int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages); -void perf_evlist__munmap(struct perf_evlist *evlist); +int perf_evlist__mmap(struct evlist *evlist, unsigned int pages); +void perf_evlist__munmap(struct evlist *evlist); size_t perf_evlist__mmap_size(unsigned long pages); -void perf_evlist__disable(struct perf_evlist *evlist); -void perf_evlist__enable(struct perf_evlist *evlist); -void perf_evlist__toggle_enable(struct perf_evlist *evlist); +void evlist__disable(struct evlist *evlist); +void evlist__enable(struct evlist *evlist); +void perf_evlist__toggle_enable(struct evlist *evlist); -int perf_evlist__enable_event_idx(struct perf_evlist *evlist, - struct perf_evsel *evsel, int idx); +int perf_evlist__enable_event_idx(struct evlist *evlist, + struct evsel *evsel, int idx); -void perf_evlist__set_selected(struct perf_evlist *evlist, - struct perf_evsel *evsel); +void perf_evlist__set_selected(struct evlist *evlist, + struct evsel *evsel); -void perf_evlist__set_maps(struct perf_evlist *evlist, struct cpu_map *cpus, - struct thread_map *threads); -int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target); -int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **err_evsel); +int perf_evlist__create_maps(struct evlist *evlist, struct target *target); +int perf_evlist__apply_filters(struct evlist *evlist, struct evsel **err_evsel); void __perf_evlist__set_leader(struct list_head *list); -void perf_evlist__set_leader(struct perf_evlist *evlist); +void perf_evlist__set_leader(struct evlist *evlist); -u64 perf_evlist__read_format(struct perf_evlist *evlist); -u64 __perf_evlist__combined_sample_type(struct perf_evlist *evlist); -u64 perf_evlist__combined_sample_type(struct perf_evlist *evlist); -u64 perf_evlist__combined_branch_type(struct perf_evlist *evlist); -bool perf_evlist__sample_id_all(struct perf_evlist *evlist); -u16 perf_evlist__id_hdr_size(struct perf_evlist *evlist); +u64 perf_evlist__read_format(struct evlist *evlist); +u64 __perf_evlist__combined_sample_type(struct evlist *evlist); +u64 perf_evlist__combined_sample_type(struct evlist *evlist); +u64 perf_evlist__combined_branch_type(struct evlist *evlist); +bool perf_evlist__sample_id_all(struct evlist *evlist); +u16 perf_evlist__id_hdr_size(struct evlist *evlist); -int perf_evlist__parse_sample(struct perf_evlist *evlist, union perf_event *event, +int perf_evlist__parse_sample(struct evlist *evlist, union perf_event *event, struct perf_sample *sample); -int perf_evlist__parse_sample_timestamp(struct perf_evlist *evlist, +int perf_evlist__parse_sample_timestamp(struct evlist *evlist, union perf_event *event, u64 *timestamp); -bool perf_evlist__valid_sample_type(struct perf_evlist *evlist); -bool perf_evlist__valid_sample_id_all(struct perf_evlist *evlist); -bool perf_evlist__valid_read_format(struct perf_evlist *evlist); +bool perf_evlist__valid_sample_type(struct evlist *evlist); +bool perf_evlist__valid_sample_id_all(struct evlist *evlist); +bool perf_evlist__valid_read_format(struct evlist *evlist); -void perf_evlist__splice_list_tail(struct perf_evlist *evlist, +void perf_evlist__splice_list_tail(struct evlist *evlist, struct list_head *list); -static inline bool perf_evlist__empty(struct perf_evlist *evlist) +static inline bool perf_evlist__empty(struct evlist *evlist) { - return list_empty(&evlist->entries); + return list_empty(&evlist->core.entries); } -static inline struct perf_evsel *perf_evlist__first(struct perf_evlist *evlist) +static inline struct evsel *perf_evlist__first(struct evlist *evlist) { - return list_entry(evlist->entries.next, struct perf_evsel, node); + return list_entry(evlist->core.entries.next, struct evsel, core.node); } -static inline struct perf_evsel *perf_evlist__last(struct perf_evlist *evlist) +static inline struct evsel *perf_evlist__last(struct evlist *evlist) { - return list_entry(evlist->entries.prev, struct perf_evsel, node); + return list_entry(evlist->core.entries.prev, struct evsel, core.node); } -size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp); +size_t perf_evlist__fprintf(struct evlist *evlist, FILE *fp); -int perf_evlist__strerror_open(struct perf_evlist *evlist, int err, char *buf, size_t size); -int perf_evlist__strerror_mmap(struct perf_evlist *evlist, int err, char *buf, size_t size); +int perf_evlist__strerror_open(struct evlist *evlist, int err, char *buf, size_t size); +int perf_evlist__strerror_mmap(struct evlist *evlist, int err, char *buf, size_t size); -bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str); -void perf_evlist__to_front(struct perf_evlist *evlist, - struct perf_evsel *move_evsel); +bool perf_evlist__can_select_event(struct evlist *evlist, const char *str); +void perf_evlist__to_front(struct evlist *evlist, + struct evsel *move_evsel); /** * __evlist__for_each_entry - iterate thru all the evsels @@ -253,7 +248,7 @@ void perf_evlist__to_front(struct perf_evlist *evlist, * @evsel: struct evsel iterator */ #define __evlist__for_each_entry(list, evsel) \ - list_for_each_entry(evsel, list, node) + list_for_each_entry(evsel, list, core.node) /** * evlist__for_each_entry - iterate thru all the evsels @@ -261,7 +256,7 @@ void perf_evlist__to_front(struct perf_evlist *evlist, * @evsel: struct evsel iterator */ #define evlist__for_each_entry(evlist, evsel) \ - __evlist__for_each_entry(&(evlist)->entries, evsel) + __evlist__for_each_entry(&(evlist)->core.entries, evsel) /** * __evlist__for_each_entry_continue - continue iteration thru all the evsels @@ -269,7 +264,7 @@ void perf_evlist__to_front(struct perf_evlist *evlist, * @evsel: struct evsel iterator */ #define __evlist__for_each_entry_continue(list, evsel) \ - list_for_each_entry_continue(evsel, list, node) + list_for_each_entry_continue(evsel, list, core.node) /** * evlist__for_each_entry_continue - continue iteration thru all the evsels @@ -277,7 +272,7 @@ void perf_evlist__to_front(struct perf_evlist *evlist, * @evsel: struct evsel iterator */ #define evlist__for_each_entry_continue(evlist, evsel) \ - __evlist__for_each_entry_continue(&(evlist)->entries, evsel) + __evlist__for_each_entry_continue(&(evlist)->core.entries, evsel) /** * __evlist__for_each_entry_reverse - iterate thru all the evsels in reverse order @@ -285,7 +280,7 @@ void perf_evlist__to_front(struct perf_evlist *evlist, * @evsel: struct evsel iterator */ #define __evlist__for_each_entry_reverse(list, evsel) \ - list_for_each_entry_reverse(evsel, list, node) + list_for_each_entry_reverse(evsel, list, core.node) /** * evlist__for_each_entry_reverse - iterate thru all the evsels in reverse order @@ -293,7 +288,7 @@ void perf_evlist__to_front(struct perf_evlist *evlist, * @evsel: struct evsel iterator */ #define evlist__for_each_entry_reverse(evlist, evsel) \ - __evlist__for_each_entry_reverse(&(evlist)->entries, evsel) + __evlist__for_each_entry_reverse(&(evlist)->core.entries, evsel) /** * __evlist__for_each_entry_safe - safely iterate thru all the evsels @@ -302,7 +297,7 @@ void perf_evlist__to_front(struct perf_evlist *evlist, * @evsel: struct evsel iterator */ #define __evlist__for_each_entry_safe(list, tmp, evsel) \ - list_for_each_entry_safe(evsel, tmp, list, node) + list_for_each_entry_safe(evsel, tmp, list, core.node) /** * evlist__for_each_entry_safe - safely iterate thru all the evsels @@ -311,21 +306,21 @@ void perf_evlist__to_front(struct perf_evlist *evlist, * @tmp: struct evsel temp iterator */ #define evlist__for_each_entry_safe(evlist, tmp, evsel) \ - __evlist__for_each_entry_safe(&(evlist)->entries, tmp, evsel) + __evlist__for_each_entry_safe(&(evlist)->core.entries, tmp, evsel) -void perf_evlist__set_tracking_event(struct perf_evlist *evlist, - struct perf_evsel *tracking_evsel); +void perf_evlist__set_tracking_event(struct evlist *evlist, + struct evsel *tracking_evsel); -struct perf_evsel * -perf_evlist__find_evsel_by_str(struct perf_evlist *evlist, const char *str); +struct evsel * +perf_evlist__find_evsel_by_str(struct evlist *evlist, const char *str); -struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist, +struct evsel *perf_evlist__event2evsel(struct evlist *evlist, union perf_event *event); -bool perf_evlist__exclude_kernel(struct perf_evlist *evlist); +bool perf_evlist__exclude_kernel(struct evlist *evlist); -void perf_evlist__force_leader(struct perf_evlist *evlist); +void perf_evlist__force_leader(struct evlist *evlist); -struct perf_evsel *perf_evlist__reset_weak_group(struct perf_evlist *evlist, - struct perf_evsel *evsel); +struct evsel *perf_evlist__reset_weak_group(struct evlist *evlist, + struct evsel *evsel); #endif /* __PERF_EVLIST_H */ diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 52459dd5ad0c..e983e721beca 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -22,9 +22,11 @@ #include <sys/resource.h> #include <sys/types.h> #include <dirent.h> +#include <perf/evsel.h> #include "asm/bug.h" #include "callchain.h" #include "cgroup.h" +#include "counts.h" #include "event.h" #include "evsel.h" #include "evlist.h" @@ -38,6 +40,7 @@ #include "string2.h" #include "memswap.h" #include "util/parse-branch-options.h" +#include <internal/xyarray.h> #include <linux/ctype.h> @@ -45,30 +48,30 @@ struct perf_missing_features perf_missing_features; static clockid_t clockid; -static int perf_evsel__no_extra_init(struct perf_evsel *evsel __maybe_unused) +static int perf_evsel__no_extra_init(struct evsel *evsel __maybe_unused) { return 0; } void __weak test_attr__ready(void) { } -static void perf_evsel__no_extra_fini(struct perf_evsel *evsel __maybe_unused) +static void perf_evsel__no_extra_fini(struct evsel *evsel __maybe_unused) { } static struct { size_t size; - int (*init)(struct perf_evsel *evsel); - void (*fini)(struct perf_evsel *evsel); + int (*init)(struct evsel *evsel); + void (*fini)(struct evsel *evsel); } perf_evsel__object = { - .size = sizeof(struct perf_evsel), + .size = sizeof(struct evsel), .init = perf_evsel__no_extra_init, .fini = perf_evsel__no_extra_fini, }; int perf_evsel__object_config(size_t object_size, - int (*init)(struct perf_evsel *evsel), - void (*fini)(struct perf_evsel *evsel)) + int (*init)(struct evsel *evsel), + void (*fini)(struct evsel *evsel)) { if (object_size == 0) @@ -89,7 +92,7 @@ set_methods: return 0; } -#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y)) +#define FD(e, x, y) (*(int *)xyarray__entry(e->core.fd, x, y)) int __perf_evsel__sample_size(u64 sample_type) { @@ -167,33 +170,33 @@ static int __perf_evsel__calc_is_pos(u64 sample_type) return idx; } -void perf_evsel__calc_id_pos(struct perf_evsel *evsel) +void perf_evsel__calc_id_pos(struct evsel *evsel) { - evsel->id_pos = __perf_evsel__calc_id_pos(evsel->attr.sample_type); - evsel->is_pos = __perf_evsel__calc_is_pos(evsel->attr.sample_type); + evsel->id_pos = __perf_evsel__calc_id_pos(evsel->core.attr.sample_type); + evsel->is_pos = __perf_evsel__calc_is_pos(evsel->core.attr.sample_type); } -void __perf_evsel__set_sample_bit(struct perf_evsel *evsel, +void __perf_evsel__set_sample_bit(struct evsel *evsel, enum perf_event_sample_format bit) { - if (!(evsel->attr.sample_type & bit)) { - evsel->attr.sample_type |= bit; + if (!(evsel->core.attr.sample_type & bit)) { + evsel->core.attr.sample_type |= bit; evsel->sample_size += sizeof(u64); perf_evsel__calc_id_pos(evsel); } } -void __perf_evsel__reset_sample_bit(struct perf_evsel *evsel, +void __perf_evsel__reset_sample_bit(struct evsel *evsel, enum perf_event_sample_format bit) { - if (evsel->attr.sample_type & bit) { - evsel->attr.sample_type &= ~bit; + if (evsel->core.attr.sample_type & bit) { + evsel->core.attr.sample_type &= ~bit; evsel->sample_size -= sizeof(u64); perf_evsel__calc_id_pos(evsel); } } -void perf_evsel__set_sample_id(struct perf_evsel *evsel, +void perf_evsel__set_sample_id(struct evsel *evsel, bool can_sample_identifier) { if (can_sample_identifier) { @@ -202,7 +205,7 @@ void perf_evsel__set_sample_id(struct perf_evsel *evsel, } else { perf_evsel__set_sample_bit(evsel, ID); } - evsel->attr.read_format |= PERF_FORMAT_ID; + evsel->core.attr.read_format |= PERF_FORMAT_ID; } /** @@ -213,7 +216,7 @@ void perf_evsel__set_sample_id(struct perf_evsel *evsel, * * Return %true if event is function trace event */ -bool perf_evsel__is_function_event(struct perf_evsel *evsel) +bool perf_evsel__is_function_event(struct evsel *evsel) { #define FUNCTION_EVENT "ftrace:function" @@ -223,19 +226,19 @@ bool perf_evsel__is_function_event(struct perf_evsel *evsel) #undef FUNCTION_EVENT } -void perf_evsel__init(struct perf_evsel *evsel, - struct perf_event_attr *attr, int idx) +void evsel__init(struct evsel *evsel, + struct perf_event_attr *attr, int idx) { + perf_evsel__init(&evsel->core, attr); evsel->idx = idx; evsel->tracking = !idx; - evsel->attr = *attr; evsel->leader = evsel; evsel->unit = ""; evsel->scale = 1.0; evsel->max_events = ULONG_MAX; evsel->evlist = NULL; + evsel->bpf_obj = NULL; evsel->bpf_fd = -1; - INIT_LIST_HEAD(&evsel->node); INIT_LIST_HEAD(&evsel->config_terms); perf_evsel__object.init(evsel); evsel->sample_size = __perf_evsel__sample_size(attr->sample_type); @@ -248,18 +251,18 @@ void perf_evsel__init(struct perf_evsel *evsel, evsel->pmu_name = NULL; } -struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx) +struct evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx) { - struct perf_evsel *evsel = zalloc(perf_evsel__object.size); + struct evsel *evsel = zalloc(perf_evsel__object.size); if (!evsel) return NULL; - perf_evsel__init(evsel, attr, idx); + evsel__init(evsel, attr, idx); if (perf_evsel__is_bpf_output(evsel)) { - evsel->attr.sample_type |= (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | + evsel->core.attr.sample_type |= (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD), - evsel->attr.sample_period = 1; + evsel->core.attr.sample_period = 1; } if (perf_evsel__is_clock(evsel)) { @@ -281,14 +284,14 @@ static bool perf_event_can_profile_kernel(void) return geteuid() == 0 || perf_event_paranoid() == -1; } -struct perf_evsel *perf_evsel__new_cycles(bool precise) +struct evsel *perf_evsel__new_cycles(bool precise) { struct perf_event_attr attr = { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES, .exclude_kernel = !perf_event_can_profile_kernel(), }; - struct perf_evsel *evsel; + struct evsel *evsel; event_attr_init(&attr); @@ -300,7 +303,7 @@ struct perf_evsel *perf_evsel__new_cycles(bool precise) * to kick in when we return and before perf_evsel__open() is called. */ new_event: - evsel = perf_evsel__new(&attr); + evsel = evsel__new(&attr); if (evsel == NULL) goto out; @@ -315,7 +318,7 @@ new_event: out: return evsel; error_free: - perf_evsel__delete(evsel); + evsel__delete(evsel); evsel = NULL; goto out; } @@ -323,9 +326,9 @@ error_free: /* * Returns pointer with encoded error via <linux/err.h> interface. */ -struct perf_evsel *perf_evsel__newtp_idx(const char *sys, const char *name, int idx) +struct evsel *perf_evsel__newtp_idx(const char *sys, const char *name, int idx) { - struct perf_evsel *evsel = zalloc(perf_evsel__object.size); + struct evsel *evsel = zalloc(perf_evsel__object.size); int err = -ENOMEM; if (evsel == NULL) { @@ -349,7 +352,7 @@ struct perf_evsel *perf_evsel__newtp_idx(const char *sys, const char *name, int event_attr_init(&attr); attr.config = evsel->tp_format->id; attr.sample_period = 1; - perf_evsel__init(evsel, &attr, idx); + evsel__init(evsel, &attr, idx); } return evsel; @@ -382,10 +385,10 @@ static const char *__perf_evsel__hw_name(u64 config) return "unknown-hardware"; } -static int perf_evsel__add_modifiers(struct perf_evsel *evsel, char *bf, size_t size) +static int perf_evsel__add_modifiers(struct evsel *evsel, char *bf, size_t size) { int colon = 0, r = 0; - struct perf_event_attr *attr = &evsel->attr; + struct perf_event_attr *attr = &evsel->core.attr; bool exclude_guest_default = false; #define MOD_PRINT(context, mod) do { \ @@ -418,9 +421,9 @@ static int perf_evsel__add_modifiers(struct perf_evsel *evsel, char *bf, size_t return r; } -static int perf_evsel__hw_name(struct perf_evsel *evsel, char *bf, size_t size) +static int perf_evsel__hw_name(struct evsel *evsel, char *bf, size_t size) { - int r = scnprintf(bf, size, "%s", __perf_evsel__hw_name(evsel->attr.config)); + int r = scnprintf(bf, size, "%s", __perf_evsel__hw_name(evsel->core.attr.config)); return r + perf_evsel__add_modifiers(evsel, bf + r, size - r); } @@ -444,9 +447,9 @@ static const char *__perf_evsel__sw_name(u64 config) return "unknown-software"; } -static int perf_evsel__sw_name(struct perf_evsel *evsel, char *bf, size_t size) +static int perf_evsel__sw_name(struct evsel *evsel, char *bf, size_t size) { - int r = scnprintf(bf, size, "%s", __perf_evsel__sw_name(evsel->attr.config)); + int r = scnprintf(bf, size, "%s", __perf_evsel__sw_name(evsel->core.attr.config)); return r + perf_evsel__add_modifiers(evsel, bf + r, size - r); } @@ -468,9 +471,9 @@ static int __perf_evsel__bp_name(char *bf, size_t size, u64 addr, u64 type) return r; } -static int perf_evsel__bp_name(struct perf_evsel *evsel, char *bf, size_t size) +static int perf_evsel__bp_name(struct evsel *evsel, char *bf, size_t size) { - struct perf_event_attr *attr = &evsel->attr; + struct perf_event_attr *attr = &evsel->core.attr; int r = __perf_evsel__bp_name(bf, size, attr->bp_addr, attr->bp_type); return r + perf_evsel__add_modifiers(evsel, bf + r, size - r); } @@ -568,15 +571,15 @@ out_err: return scnprintf(bf, size, "%s", err); } -static int perf_evsel__hw_cache_name(struct perf_evsel *evsel, char *bf, size_t size) +static int perf_evsel__hw_cache_name(struct evsel *evsel, char *bf, size_t size) { - int ret = __perf_evsel__hw_cache_name(evsel->attr.config, bf, size); + int ret = __perf_evsel__hw_cache_name(evsel->core.attr.config, bf, size); return ret + perf_evsel__add_modifiers(evsel, bf + ret, size - ret); } -static int perf_evsel__raw_name(struct perf_evsel *evsel, char *bf, size_t size) +static int perf_evsel__raw_name(struct evsel *evsel, char *bf, size_t size) { - int ret = scnprintf(bf, size, "raw 0x%" PRIx64, evsel->attr.config); + int ret = scnprintf(bf, size, "raw 0x%" PRIx64, evsel->core.attr.config); return ret + perf_evsel__add_modifiers(evsel, bf + ret, size - ret); } @@ -586,7 +589,7 @@ static int perf_evsel__tool_name(char *bf, size_t size) return ret; } -const char *perf_evsel__name(struct perf_evsel *evsel) +const char *perf_evsel__name(struct evsel *evsel) { char bf[128]; @@ -596,7 +599,7 @@ const char *perf_evsel__name(struct perf_evsel *evsel) if (evsel->name) return evsel->name; - switch (evsel->attr.type) { + switch (evsel->core.attr.type) { case PERF_TYPE_RAW: perf_evsel__raw_name(evsel, bf, sizeof(bf)); break; @@ -626,7 +629,7 @@ const char *perf_evsel__name(struct perf_evsel *evsel) default: scnprintf(bf, sizeof(bf), "unknown attr type: %d", - evsel->attr.type); + evsel->core.attr.type); break; } @@ -638,7 +641,7 @@ out_unknown: return "unknown"; } -const char *perf_evsel__group_name(struct perf_evsel *evsel) +const char *perf_evsel__group_name(struct evsel *evsel) { return evsel->group_name ?: "anon group"; } @@ -653,10 +656,10 @@ const char *perf_evsel__group_name(struct perf_evsel *evsel) * For record -e 'cycles,instructions' and report --group * 'cycles:u, instructions:u' */ -int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size) +int perf_evsel__group_desc(struct evsel *evsel, char *buf, size_t size) { int ret = 0; - struct perf_evsel *pos; + struct evsel *pos; const char *group_name = perf_evsel__group_name(evsel); if (!evsel->forced_leader) @@ -675,12 +678,12 @@ int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size) return ret; } -static void __perf_evsel__config_callchain(struct perf_evsel *evsel, +static void __perf_evsel__config_callchain(struct evsel *evsel, struct record_opts *opts, struct callchain_param *param) { bool function = perf_evsel__is_function_event(evsel); - struct perf_event_attr *attr = &evsel->attr; + struct perf_event_attr *attr = &evsel->core.attr; perf_evsel__set_sample_bit(evsel, CALLCHAIN); @@ -734,7 +737,7 @@ static void __perf_evsel__config_callchain(struct perf_evsel *evsel, } } -void perf_evsel__config_callchain(struct perf_evsel *evsel, +void perf_evsel__config_callchain(struct evsel *evsel, struct record_opts *opts, struct callchain_param *param) { @@ -743,10 +746,10 @@ void perf_evsel__config_callchain(struct perf_evsel *evsel, } static void -perf_evsel__reset_callgraph(struct perf_evsel *evsel, +perf_evsel__reset_callgraph(struct evsel *evsel, struct callchain_param *param) { - struct perf_event_attr *attr = &evsel->attr; + struct perf_event_attr *attr = &evsel->core.attr; perf_evsel__reset_sample_bit(evsel, CALLCHAIN); if (param->record_mode == CALLCHAIN_LBR) { @@ -760,12 +763,12 @@ perf_evsel__reset_callgraph(struct perf_evsel *evsel, } } -static void apply_config_terms(struct perf_evsel *evsel, +static void apply_config_terms(struct evsel *evsel, struct record_opts *opts, bool track) { struct perf_evsel_config_term *term; struct list_head *config_terms = &evsel->config_terms; - struct perf_event_attr *attr = &evsel->attr; + struct perf_event_attr *attr = &evsel->core.attr; /* callgraph default */ struct callchain_param param = { .record_mode = callchain_param.record_mode, @@ -832,6 +835,9 @@ static void apply_config_terms(struct perf_evsel *evsel, break; case PERF_EVSEL__CONFIG_TERM_PERCORE: break; + case PERF_EVSEL__CONFIG_TERM_AUX_OUTPUT: + attr->aux_output = term->val.aux_output ? 1 : 0; + break; default: break; } @@ -878,17 +884,17 @@ static void apply_config_terms(struct perf_evsel *evsel, if (sample_address) { perf_evsel__set_sample_bit(evsel, ADDR); perf_evsel__set_sample_bit(evsel, DATA_SRC); - evsel->attr.mmap_data = track; + evsel->core.attr.mmap_data = track; } perf_evsel__config_callchain(evsel, opts, ¶m); } } } -static bool is_dummy_event(struct perf_evsel *evsel) +static bool is_dummy_event(struct evsel *evsel) { - return (evsel->attr.type == PERF_TYPE_SOFTWARE) && - (evsel->attr.config == PERF_COUNT_SW_DUMMY); + return (evsel->core.attr.type == PERF_TYPE_SOFTWARE) && + (evsel->core.attr.config == PERF_COUNT_SW_DUMMY); } /* @@ -919,11 +925,11 @@ static bool is_dummy_event(struct perf_evsel *evsel) * enable/disable events specifically, as there's no * initial traced exec call. */ -void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, +void perf_evsel__config(struct evsel *evsel, struct record_opts *opts, struct callchain_param *callchain) { - struct perf_evsel *leader = evsel->leader; - struct perf_event_attr *attr = &evsel->attr; + struct evsel *leader = evsel->leader; + struct perf_event_attr *attr = &evsel->core.attr; int track = evsel->tracking; bool per_cpu = opts->target.default_per_cpu && !opts->target.per_thread; @@ -947,7 +953,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, * Apply group format only if we belong to group * with more than one members. */ - if (leader->nr_members > 1) { + if (leader->core.nr_members > 1) { attr->read_format |= PERF_FORMAT_GROUP; attr->inherit = 0; } @@ -984,14 +990,14 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, * event to follow the master sample_type to ease up * report. */ - attr->sample_type = leader->attr.sample_type; + attr->sample_type = leader->core.attr.sample_type; } if (opts->no_samples) attr->sample_freq = 0; if (opts->inherit_stat) { - evsel->attr.read_format |= + evsel->core.attr.read_format |= PERF_FORMAT_TOTAL_TIME_ENABLED | PERF_FORMAT_TOTAL_TIME_RUNNING | PERF_FORMAT_ID; @@ -1009,7 +1015,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, * fault handler and its overall trickiness nature. */ if (perf_evsel__is_function_event(evsel)) - evsel->attr.exclude_callchain_user = 1; + evsel->core.attr.exclude_callchain_user = 1; if (callchain && callchain->enabled && !evsel->no_aux_samples) perf_evsel__config_callchain(evsel, opts, callchain); @@ -1078,7 +1084,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, perf_evsel__set_sample_bit(evsel, TRANSACTION); if (opts->running_time) { - evsel->attr.read_format |= + evsel->core.attr.read_format |= PERF_FORMAT_TOTAL_TIME_ENABLED | PERF_FORMAT_TOTAL_TIME_RUNNING; } @@ -1124,8 +1130,8 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, attr->exclude_user = 1; } - if (evsel->own_cpus || evsel->unit) - evsel->attr.read_format |= PERF_FORMAT_ID; + if (evsel->core.own_cpus || evsel->unit) + evsel->core.attr.read_format |= PERF_FORMAT_ID; /* * Apply event specific term settings, @@ -1152,48 +1158,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, perf_evsel__reset_sample_bit(evsel, BRANCH_STACK); } -static int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads) -{ - evsel->fd = xyarray__new(ncpus, nthreads, sizeof(int)); - - if (evsel->fd) { - int cpu, thread; - for (cpu = 0; cpu < ncpus; cpu++) { - for (thread = 0; thread < nthreads; thread++) { - FD(evsel, cpu, thread) = -1; - } - } - } - - return evsel->fd != NULL ? 0 : -ENOMEM; -} - -static int perf_evsel__run_ioctl(struct perf_evsel *evsel, - int ioc, void *arg) -{ - int cpu, thread; - - for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) { - for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) { - int fd = FD(evsel, cpu, thread), - err = ioctl(fd, ioc, arg); - - if (err) - return err; - } - } - - return 0; -} - -int perf_evsel__apply_filter(struct perf_evsel *evsel, const char *filter) -{ - return perf_evsel__run_ioctl(evsel, - PERF_EVENT_IOC_SET_FILTER, - (void *)filter); -} - -int perf_evsel__set_filter(struct perf_evsel *evsel, const char *filter) +int perf_evsel__set_filter(struct evsel *evsel, const char *filter) { char *new_filter = strdup(filter); @@ -1206,7 +1171,7 @@ int perf_evsel__set_filter(struct perf_evsel *evsel, const char *filter) return -1; } -static int perf_evsel__append_filter(struct perf_evsel *evsel, +static int perf_evsel__append_filter(struct evsel *evsel, const char *fmt, const char *filter) { char *new_filter; @@ -1223,19 +1188,19 @@ static int perf_evsel__append_filter(struct perf_evsel *evsel, return -1; } -int perf_evsel__append_tp_filter(struct perf_evsel *evsel, const char *filter) +int perf_evsel__append_tp_filter(struct evsel *evsel, const char *filter) { return perf_evsel__append_filter(evsel, "(%s) && (%s)", filter); } -int perf_evsel__append_addr_filter(struct perf_evsel *evsel, const char *filter) +int perf_evsel__append_addr_filter(struct evsel *evsel, const char *filter) { return perf_evsel__append_filter(evsel, "%s,%s", filter); } -int perf_evsel__enable(struct perf_evsel *evsel) +int evsel__enable(struct evsel *evsel) { - int err = perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, 0); + int err = perf_evsel__enable(&evsel->core); if (!err) evsel->disabled = false; @@ -1243,9 +1208,9 @@ int perf_evsel__enable(struct perf_evsel *evsel) return err; } -int perf_evsel__disable(struct perf_evsel *evsel) +int evsel__disable(struct evsel *evsel) { - int err = perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, 0); + int err = perf_evsel__disable(&evsel->core); /* * We mark it disabled here so that tools that disable a event can * ignore events after they disable it. I.e. the ring buffer may have @@ -1258,7 +1223,7 @@ int perf_evsel__disable(struct perf_evsel *evsel) return err; } -int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads) +int perf_evsel__alloc_id(struct evsel *evsel, int ncpus, int nthreads) { if (ncpus == 0 || nthreads == 0) return 0; @@ -1280,13 +1245,7 @@ int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads) return 0; } -static void perf_evsel__free_fd(struct perf_evsel *evsel) -{ - xyarray__delete(evsel->fd); - evsel->fd = NULL; -} - -static void perf_evsel__free_id(struct perf_evsel *evsel) +static void perf_evsel__free_id(struct evsel *evsel) { xyarray__delete(evsel->sample_id); evsel->sample_id = NULL; @@ -1294,7 +1253,7 @@ static void perf_evsel__free_id(struct perf_evsel *evsel) evsel->ids = 0; } -static void perf_evsel__free_config_terms(struct perf_evsel *evsel) +static void perf_evsel__free_config_terms(struct evsel *evsel) { struct perf_evsel_config_term *term, *h; @@ -1304,41 +1263,30 @@ static void perf_evsel__free_config_terms(struct perf_evsel *evsel) } } -void perf_evsel__close_fd(struct perf_evsel *evsel) +void perf_evsel__exit(struct evsel *evsel) { - int cpu, thread; - - for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) - for (thread = 0; thread < xyarray__max_y(evsel->fd); ++thread) { - close(FD(evsel, cpu, thread)); - FD(evsel, cpu, thread) = -1; - } -} - -void perf_evsel__exit(struct perf_evsel *evsel) -{ - assert(list_empty(&evsel->node)); + assert(list_empty(&evsel->core.node)); assert(evsel->evlist == NULL); perf_evsel__free_counts(evsel); - perf_evsel__free_fd(evsel); + perf_evsel__free_fd(&evsel->core); perf_evsel__free_id(evsel); perf_evsel__free_config_terms(evsel); cgroup__put(evsel->cgrp); - cpu_map__put(evsel->cpus); - cpu_map__put(evsel->own_cpus); - thread_map__put(evsel->threads); + perf_cpu_map__put(evsel->core.cpus); + perf_cpu_map__put(evsel->core.own_cpus); + perf_thread_map__put(evsel->core.threads); zfree(&evsel->group_name); zfree(&evsel->name); perf_evsel__object.fini(evsel); } -void perf_evsel__delete(struct perf_evsel *evsel) +void evsel__delete(struct evsel *evsel) { perf_evsel__exit(evsel); free(evsel); } -void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu, int thread, +void perf_evsel__compute_deltas(struct evsel *evsel, int cpu, int thread, struct perf_counts_values *count) { struct perf_counts_values tmp; @@ -1378,57 +1326,16 @@ void perf_counts_values__scale(struct perf_counts_values *count, *pscaled = scaled; } -static int perf_evsel__read_size(struct perf_evsel *evsel) -{ - u64 read_format = evsel->attr.read_format; - int entry = sizeof(u64); /* value */ - int size = 0; - int nr = 1; - - if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) - size += sizeof(u64); - - if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) - size += sizeof(u64); - - if (read_format & PERF_FORMAT_ID) - entry += sizeof(u64); - - if (read_format & PERF_FORMAT_GROUP) { - nr = evsel->nr_members; - size += sizeof(u64); - } - - size += entry * nr; - return size; -} - -int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread, - struct perf_counts_values *count) -{ - size_t size = perf_evsel__read_size(evsel); - - memset(count, 0, sizeof(*count)); - - if (FD(evsel, cpu, thread) < 0) - return -EINVAL; - - if (readn(FD(evsel, cpu, thread), count->values, size) <= 0) - return -errno; - - return 0; -} - static int -perf_evsel__read_one(struct perf_evsel *evsel, int cpu, int thread) +perf_evsel__read_one(struct evsel *evsel, int cpu, int thread) { struct perf_counts_values *count = perf_counts(evsel->counts, cpu, thread); - return perf_evsel__read(evsel, cpu, thread, count); + return perf_evsel__read(&evsel->core, cpu, thread, count); } static void -perf_evsel__set_count(struct perf_evsel *counter, int cpu, int thread, +perf_evsel__set_count(struct evsel *counter, int cpu, int thread, u64 val, u64 ena, u64 run) { struct perf_counts_values *count; @@ -1438,20 +1345,21 @@ perf_evsel__set_count(struct perf_evsel *counter, int cpu, int thread, count->val = val; count->ena = ena; count->run = run; - count->loaded = true; + + perf_counts__set_loaded(counter->counts, cpu, thread, true); } static int -perf_evsel__process_group_data(struct perf_evsel *leader, +perf_evsel__process_group_data(struct evsel *leader, int cpu, int thread, u64 *data) { - u64 read_format = leader->attr.read_format; + u64 read_format = leader->core.attr.read_format; struct sample_read_value *v; u64 nr, ena = 0, run = 0, i; nr = *data++; - if (nr != (u64) leader->nr_members) + if (nr != (u64) leader->core.nr_members) return -EINVAL; if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) @@ -1466,7 +1374,7 @@ perf_evsel__process_group_data(struct perf_evsel *leader, v[0].value, ena, run); for (i = 1; i < nr; i++) { - struct perf_evsel *counter; + struct evsel *counter; counter = perf_evlist__id2evsel(leader->evlist, v[i].id); if (!counter) @@ -1480,11 +1388,11 @@ perf_evsel__process_group_data(struct perf_evsel *leader, } static int -perf_evsel__read_group(struct perf_evsel *leader, int cpu, int thread) +perf_evsel__read_group(struct evsel *leader, int cpu, int thread) { struct perf_stat_evsel *ps = leader->stats; - u64 read_format = leader->attr.read_format; - int size = perf_evsel__read_size(leader); + u64 read_format = leader->core.attr.read_format; + int size = perf_evsel__read_size(&leader->core); u64 *data = ps->group_data; if (!(read_format & PERF_FORMAT_ID)) @@ -1510,9 +1418,9 @@ perf_evsel__read_group(struct perf_evsel *leader, int cpu, int thread) return perf_evsel__process_group_data(leader, cpu, thread, data); } -int perf_evsel__read_counter(struct perf_evsel *evsel, int cpu, int thread) +int perf_evsel__read_counter(struct evsel *evsel, int cpu, int thread) { - u64 read_format = evsel->attr.read_format; + u64 read_format = evsel->core.attr.read_format; if (read_format & PERF_FORMAT_GROUP) return perf_evsel__read_group(evsel, cpu, thread); @@ -1520,7 +1428,7 @@ int perf_evsel__read_counter(struct perf_evsel *evsel, int cpu, int thread) return perf_evsel__read_one(evsel, cpu, thread); } -int __perf_evsel__read_on_cpu(struct perf_evsel *evsel, +int __perf_evsel__read_on_cpu(struct evsel *evsel, int cpu, int thread, bool scale) { struct perf_counts_values count; @@ -1541,9 +1449,9 @@ int __perf_evsel__read_on_cpu(struct perf_evsel *evsel, return 0; } -static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread) +static int get_group_fd(struct evsel *evsel, int cpu, int thread) { - struct perf_evsel *leader = evsel->leader; + struct evsel *leader = evsel->leader; int fd; if (perf_evsel__is_group_leader(evsel)) @@ -1553,7 +1461,7 @@ static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread) * Leader must be already processed/open, * if not it's a bug. */ - BUG_ON(!leader->fd); + BUG_ON(!leader->core.fd); fd = FD(leader, cpu, thread); BUG_ON(fd == -1); @@ -1684,6 +1592,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr, PRINT_ATTRf(namespaces, p_unsigned); PRINT_ATTRf(ksymbol, p_unsigned); PRINT_ATTRf(bpf_event, p_unsigned); + PRINT_ATTRf(aux_output, p_unsigned); PRINT_ATTRn("{ wakeup_events, wakeup_watermark }", wakeup_events, p_unsigned); PRINT_ATTRf(bp_type, p_unsigned); @@ -1706,7 +1615,7 @@ static int __open_attr__fprintf(FILE *fp, const char *name, const char *val, return fprintf(fp, " %-32s %s\n", name, val); } -static void perf_evsel__remove_fd(struct perf_evsel *pos, +static void perf_evsel__remove_fd(struct evsel *pos, int nr_cpus, int nr_threads, int thread_idx) { @@ -1715,11 +1624,11 @@ static void perf_evsel__remove_fd(struct perf_evsel *pos, FD(pos, cpu, thread) = FD(pos, cpu, thread + 1); } -static int update_fds(struct perf_evsel *evsel, +static int update_fds(struct evsel *evsel, int nr_cpus, int cpu_idx, int nr_threads, int thread_idx) { - struct perf_evsel *pos; + struct evsel *pos; if (cpu_idx >= nr_cpus || thread_idx >= nr_threads) return -EINVAL; @@ -1739,12 +1648,12 @@ static int update_fds(struct perf_evsel *evsel, return 0; } -static bool ignore_missing_thread(struct perf_evsel *evsel, +static bool ignore_missing_thread(struct evsel *evsel, int nr_cpus, int cpu, - struct thread_map *threads, + struct perf_thread_map *threads, int thread, int err) { - pid_t ignore_pid = thread_map__pid(threads, thread); + pid_t ignore_pid = perf_thread_map__pid(threads, thread); if (!evsel->ignore_missing_thread) return false; @@ -1786,18 +1695,18 @@ static void display_attr(struct perf_event_attr *attr) } } -static int perf_event_open(struct perf_evsel *evsel, +static int perf_event_open(struct evsel *evsel, pid_t pid, int cpu, int group_fd, unsigned long flags) { - int precise_ip = evsel->attr.precise_ip; + int precise_ip = evsel->core.attr.precise_ip; int fd; while (1) { pr_debug2("sys_perf_event_open: pid %d cpu %d group_fd %d flags %#lx", pid, cpu, group_fd, flags); - fd = sys_perf_event_open(&evsel->attr, pid, cpu, group_fd, flags); + fd = sys_perf_event_open(&evsel->core.attr, pid, cpu, group_fd, flags); if (fd >= 0) break; @@ -1809,36 +1718,37 @@ static int perf_event_open(struct perf_evsel *evsel, * We tried all the precise_ip values, and it's * still failing, so leave it to standard fallback. */ - if (!evsel->attr.precise_ip) { - evsel->attr.precise_ip = precise_ip; + if (!evsel->core.attr.precise_ip) { + evsel->core.attr.precise_ip = precise_ip; break; } pr_debug2("\nsys_perf_event_open failed, error %d\n", -ENOTSUP); - evsel->attr.precise_ip--; - pr_debug2("decreasing precise_ip by one (%d)\n", evsel->attr.precise_ip); - display_attr(&evsel->attr); + evsel->core.attr.precise_ip--; + pr_debug2("decreasing precise_ip by one (%d)\n", evsel->core.attr.precise_ip); + display_attr(&evsel->core.attr); } return fd; } -int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, - struct thread_map *threads) +int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus, + struct perf_thread_map *threads) { int cpu, thread, nthreads; unsigned long flags = PERF_FLAG_FD_CLOEXEC; int pid = -1, err; enum { NO_CHANGE, SET_TO_MAX, INCREASED_MAX } set_rlimit = NO_CHANGE; - if (perf_missing_features.write_backward && evsel->attr.write_backward) + if ((perf_missing_features.write_backward && evsel->core.attr.write_backward) || + (perf_missing_features.aux_output && evsel->core.attr.aux_output)) return -EINVAL; if (cpus == NULL) { - static struct cpu_map *empty_cpu_map; + static struct perf_cpu_map *empty_cpu_map; if (empty_cpu_map == NULL) { - empty_cpu_map = cpu_map__dummy_new(); + empty_cpu_map = perf_cpu_map__dummy_new(); if (empty_cpu_map == NULL) return -ENOMEM; } @@ -1847,7 +1757,7 @@ int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, } if (threads == NULL) { - static struct thread_map *empty_thread_map; + static struct perf_thread_map *empty_thread_map; if (empty_thread_map == NULL) { empty_thread_map = thread_map__new_by_tid(-1); @@ -1863,8 +1773,8 @@ int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, else nthreads = threads->nr; - if (evsel->fd == NULL && - perf_evsel__alloc_fd(evsel, cpus->nr, nthreads) < 0) + if (evsel->core.fd == NULL && + perf_evsel__alloc_fd(&evsel->core, cpus->nr, nthreads) < 0) return -ENOMEM; if (evsel->cgrp) { @@ -1874,31 +1784,31 @@ int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, fallback_missing_features: if (perf_missing_features.clockid_wrong) - evsel->attr.clockid = CLOCK_MONOTONIC; /* should always work */ + evsel->core.attr.clockid = CLOCK_MONOTONIC; /* should always work */ if (perf_missing_features.clockid) { - evsel->attr.use_clockid = 0; - evsel->attr.clockid = 0; + evsel->core.attr.use_clockid = 0; + evsel->core.attr.clockid = 0; } if (perf_missing_features.cloexec) flags &= ~(unsigned long)PERF_FLAG_FD_CLOEXEC; if (perf_missing_features.mmap2) - evsel->attr.mmap2 = 0; + evsel->core.attr.mmap2 = 0; if (perf_missing_features.exclude_guest) - evsel->attr.exclude_guest = evsel->attr.exclude_host = 0; + evsel->core.attr.exclude_guest = evsel->core.attr.exclude_host = 0; if (perf_missing_features.lbr_flags) - evsel->attr.branch_sample_type &= ~(PERF_SAMPLE_BRANCH_NO_FLAGS | + evsel->core.attr.branch_sample_type &= ~(PERF_SAMPLE_BRANCH_NO_FLAGS | PERF_SAMPLE_BRANCH_NO_CYCLES); - if (perf_missing_features.group_read && evsel->attr.inherit) - evsel->attr.read_format &= ~(PERF_FORMAT_GROUP|PERF_FORMAT_ID); + if (perf_missing_features.group_read && evsel->core.attr.inherit) + evsel->core.attr.read_format &= ~(PERF_FORMAT_GROUP|PERF_FORMAT_ID); if (perf_missing_features.ksymbol) - evsel->attr.ksymbol = 0; + evsel->core.attr.ksymbol = 0; if (perf_missing_features.bpf_event) - evsel->attr.bpf_event = 0; + evsel->core.attr.bpf_event = 0; retry_sample_id: if (perf_missing_features.sample_id_all) - evsel->attr.sample_id_all = 0; + evsel->core.attr.sample_id_all = 0; - display_attr(&evsel->attr); + display_attr(&evsel->core.attr); for (cpu = 0; cpu < cpus->nr; cpu++) { @@ -1906,7 +1816,7 @@ retry_sample_id: int fd, group_fd; if (!evsel->cgrp && !evsel->system_wide) - pid = thread_map__pid(threads, thread); + pid = perf_thread_map__pid(threads, thread); group_fd = get_group_fd(evsel, cpu, thread); retry_open: @@ -2005,23 +1915,27 @@ try_fallback: * Must probe features in the order they were added to the * perf_event_attr interface. */ - if (!perf_missing_features.bpf_event && evsel->attr.bpf_event) { + if (!perf_missing_features.aux_output && evsel->core.attr.aux_output) { + perf_missing_features.aux_output = true; + pr_debug2("Kernel has no attr.aux_output support, bailing out\n"); + goto out_close; + } else if (!perf_missing_features.bpf_event && evsel->core.attr.bpf_event) { perf_missing_features.bpf_event = true; pr_debug2("switching off bpf_event\n"); goto fallback_missing_features; - } else if (!perf_missing_features.ksymbol && evsel->attr.ksymbol) { + } else if (!perf_missing_features.ksymbol && evsel->core.attr.ksymbol) { perf_missing_features.ksymbol = true; pr_debug2("switching off ksymbol\n"); goto fallback_missing_features; - } else if (!perf_missing_features.write_backward && evsel->attr.write_backward) { + } else if (!perf_missing_features.write_backward && evsel->core.attr.write_backward) { perf_missing_features.write_backward = true; pr_debug2("switching off write_backward\n"); goto out_close; - } else if (!perf_missing_features.clockid_wrong && evsel->attr.use_clockid) { + } else if (!perf_missing_features.clockid_wrong && evsel->core.attr.use_clockid) { perf_missing_features.clockid_wrong = true; pr_debug2("switching off clockid\n"); goto fallback_missing_features; - } else if (!perf_missing_features.clockid && evsel->attr.use_clockid) { + } else if (!perf_missing_features.clockid && evsel->core.attr.use_clockid) { perf_missing_features.clockid = true; pr_debug2("switching off use_clockid\n"); goto fallback_missing_features; @@ -2029,12 +1943,12 @@ try_fallback: perf_missing_features.cloexec = true; pr_debug2("switching off cloexec flag\n"); goto fallback_missing_features; - } else if (!perf_missing_features.mmap2 && evsel->attr.mmap2) { + } else if (!perf_missing_features.mmap2 && evsel->core.attr.mmap2) { perf_missing_features.mmap2 = true; pr_debug2("switching off mmap2\n"); goto fallback_missing_features; } else if (!perf_missing_features.exclude_guest && - (evsel->attr.exclude_guest || evsel->attr.exclude_host)) { + (evsel->core.attr.exclude_guest || evsel->core.attr.exclude_host)) { perf_missing_features.exclude_guest = true; pr_debug2("switching off exclude_guest, exclude_host\n"); goto fallback_missing_features; @@ -2043,15 +1957,15 @@ try_fallback: pr_debug2("switching off sample_id_all\n"); goto retry_sample_id; } else if (!perf_missing_features.lbr_flags && - (evsel->attr.branch_sample_type & + (evsel->core.attr.branch_sample_type & (PERF_SAMPLE_BRANCH_NO_CYCLES | PERF_SAMPLE_BRANCH_NO_FLAGS))) { perf_missing_features.lbr_flags = true; pr_debug2("switching off branch sample type no (cycles/flags)\n"); goto fallback_missing_features; } else if (!perf_missing_features.group_read && - evsel->attr.inherit && - (evsel->attr.read_format & PERF_FORMAT_GROUP) && + evsel->core.attr.inherit && + (evsel->core.attr.read_format & PERF_FORMAT_GROUP) && perf_evsel__is_group_leader(evsel)) { perf_missing_features.group_read = true; pr_debug2("switching off group read\n"); @@ -2071,33 +1985,29 @@ out_close: return err; } -void perf_evsel__close(struct perf_evsel *evsel) +void evsel__close(struct evsel *evsel) { - if (evsel->fd == NULL) - return; - - perf_evsel__close_fd(evsel); - perf_evsel__free_fd(evsel); + perf_evsel__close(&evsel->core); perf_evsel__free_id(evsel); } -int perf_evsel__open_per_cpu(struct perf_evsel *evsel, - struct cpu_map *cpus) +int perf_evsel__open_per_cpu(struct evsel *evsel, + struct perf_cpu_map *cpus) { - return perf_evsel__open(evsel, cpus, NULL); + return evsel__open(evsel, cpus, NULL); } -int perf_evsel__open_per_thread(struct perf_evsel *evsel, - struct thread_map *threads) +int perf_evsel__open_per_thread(struct evsel *evsel, + struct perf_thread_map *threads) { - return perf_evsel__open(evsel, NULL, threads); + return evsel__open(evsel, NULL, threads); } -static int perf_evsel__parse_id_sample(const struct perf_evsel *evsel, +static int perf_evsel__parse_id_sample(const struct evsel *evsel, const union perf_event *event, struct perf_sample *sample) { - u64 type = evsel->attr.sample_type; + u64 type = evsel->core.attr.sample_type; const u64 *array = event->sample.array; bool swapped = evsel->needs_swap; union u64_swap u; @@ -2183,10 +2093,10 @@ perf_event__check_size(union perf_event *event, unsigned int sample_size) return 0; } -int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, +int perf_evsel__parse_sample(struct evsel *evsel, union perf_event *event, struct perf_sample *data) { - u64 type = evsel->attr.sample_type; + u64 type = evsel->core.attr.sample_type; bool swapped = evsel->needs_swap; const u64 *array; u16 max_size = event->header.size; @@ -2202,14 +2112,14 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, memset(data, 0, sizeof(*data)); data->cpu = data->pid = data->tid = -1; data->stream_id = data->id = data->time = -1ULL; - data->period = evsel->attr.sample_period; + data->period = evsel->core.attr.sample_period; data->cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; data->misc = event->header.misc; data->id = -1ULL; data->data_src = PERF_MEM_DATA_SRC_NONE; if (event->header.type != PERF_RECORD_SAMPLE) { - if (!evsel->attr.sample_id_all) + if (!evsel->core.attr.sample_id_all) return 0; return perf_evsel__parse_id_sample(evsel, event, data); } @@ -2282,7 +2192,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, } if (type & PERF_SAMPLE_READ) { - u64 read_format = evsel->attr.read_format; + u64 read_format = evsel->core.attr.read_format; OVERFLOW_CHECK_u64(array); if (read_format & PERF_FORMAT_GROUP) @@ -2387,7 +2297,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, array++; if (data->user_regs.abi) { - u64 mask = evsel->attr.sample_regs_user; + u64 mask = evsel->core.attr.sample_regs_user; sz = hweight64(mask) * sizeof(u64); OVERFLOW_CHECK(array, sz, max_size); @@ -2443,7 +2353,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, array++; if (data->intr_regs.abi != PERF_SAMPLE_REGS_ABI_NONE) { - u64 mask = evsel->attr.sample_regs_intr; + u64 mask = evsel->core.attr.sample_regs_intr; sz = hweight64(mask) * sizeof(u64); OVERFLOW_CHECK(array, sz, max_size); @@ -2462,11 +2372,11 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, return 0; } -int perf_evsel__parse_sample_timestamp(struct perf_evsel *evsel, +int perf_evsel__parse_sample_timestamp(struct evsel *evsel, union perf_event *event, u64 *timestamp) { - u64 type = evsel->attr.sample_type; + u64 type = evsel->core.attr.sample_type; const u64 *array; if (!(type & PERF_SAMPLE_TIME)) @@ -2477,7 +2387,7 @@ int perf_evsel__parse_sample_timestamp(struct perf_evsel *evsel, .time = -1ULL, }; - if (!evsel->attr.sample_id_all) + if (!evsel->core.attr.sample_id_all) return -1; if (perf_evsel__parse_id_sample(evsel, event, &data)) return -1; @@ -2783,12 +2693,12 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, return 0; } -struct tep_format_field *perf_evsel__field(struct perf_evsel *evsel, const char *name) +struct tep_format_field *perf_evsel__field(struct evsel *evsel, const char *name) { return tep_find_field(evsel->tp_format, name); } -void *perf_evsel__rawptr(struct perf_evsel *evsel, struct perf_sample *sample, +void *perf_evsel__rawptr(struct evsel *evsel, struct perf_sample *sample, const char *name) { struct tep_format_field *field = perf_evsel__field(evsel, name); @@ -2846,7 +2756,7 @@ u64 format_field__intval(struct tep_format_field *field, struct perf_sample *sam return 0; } -u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample, +u64 perf_evsel__intval(struct evsel *evsel, struct perf_sample *sample, const char *name) { struct tep_format_field *field = perf_evsel__field(evsel, name); @@ -2857,14 +2767,14 @@ u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample, return field ? format_field__intval(field, sample, evsel->needs_swap) : 0; } -bool perf_evsel__fallback(struct perf_evsel *evsel, int err, +bool perf_evsel__fallback(struct evsel *evsel, int err, char *msg, size_t msgsize) { int paranoid; if ((err == ENOENT || err == ENXIO || err == ENODEV) && - evsel->attr.type == PERF_TYPE_HARDWARE && - evsel->attr.config == PERF_COUNT_HW_CPU_CYCLES) { + evsel->core.attr.type == PERF_TYPE_HARDWARE && + evsel->core.attr.config == PERF_COUNT_HW_CPU_CYCLES) { /* * If it's cycles then fall back to hrtimer based * cpu-clock-tick sw counter, which is always available even if @@ -2876,12 +2786,12 @@ bool perf_evsel__fallback(struct perf_evsel *evsel, int err, scnprintf(msg, msgsize, "%s", "The cycles event is not supported, trying to fall back to cpu-clock-ticks"); - evsel->attr.type = PERF_TYPE_SOFTWARE; - evsel->attr.config = PERF_COUNT_SW_CPU_CLOCK; + evsel->core.attr.type = PERF_TYPE_SOFTWARE; + evsel->core.attr.config = PERF_COUNT_SW_CPU_CLOCK; zfree(&evsel->name); return true; - } else if (err == EACCES && !evsel->attr.exclude_kernel && + } else if (err == EACCES && !evsel->core.attr.exclude_kernel && (paranoid = perf_event_paranoid()) > 1) { const char *name = perf_evsel__name(evsel); char *new_name; @@ -2900,7 +2810,7 @@ bool perf_evsel__fallback(struct perf_evsel *evsel, int err, evsel->name = new_name; scnprintf(msg, msgsize, "kernel.perf_event_paranoid=%d, trying to fall back to excluding kernel samples", paranoid); - evsel->attr.exclude_kernel = 1; + evsel->core.attr.exclude_kernel = 1; return true; } @@ -2944,7 +2854,7 @@ static bool find_process(const char *name) return ret ? false : true; } -int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, +int perf_evsel__open_strerror(struct evsel *evsel, struct target *target, int err, char *msg, size_t size) { char sbuf[STRERR_BUFSIZE]; @@ -2997,15 +2907,15 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, "No such device - did you specify an out-of-range profile CPU?"); break; case EOPNOTSUPP: - if (evsel->attr.sample_period != 0) + if (evsel->core.attr.sample_period != 0) return scnprintf(msg, size, "%s: PMU Hardware doesn't support sampling/overflow-interrupts. Try 'perf stat'", perf_evsel__name(evsel)); - if (evsel->attr.precise_ip) + if (evsel->core.attr.precise_ip) return scnprintf(msg, size, "%s", "\'precise\' request may not be supported. Try removing 'p' modifier."); #if defined(__i386__) || defined(__x86_64__) - if (evsel->attr.type == PERF_TYPE_HARDWARE) + if (evsel->core.attr.type == PERF_TYPE_HARDWARE) return scnprintf(msg, size, "%s", "No hardware sampling interrupt available.\n"); #endif @@ -3017,12 +2927,14 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, "We found oprofile daemon running, please stop it and try again."); break; case EINVAL: - if (evsel->attr.write_backward && perf_missing_features.write_backward) + if (evsel->core.attr.write_backward && perf_missing_features.write_backward) return scnprintf(msg, size, "Reading from overwrite event is not supported by this kernel."); if (perf_missing_features.clockid) return scnprintf(msg, size, "clockid feature not supported."); if (perf_missing_features.clockid_wrong) return scnprintf(msg, size, "wrong clockid (%d).", clockid); + if (perf_missing_features.aux_output) + return scnprintf(msg, size, "The 'aux_output' feature is not supported, update the kernel."); break; default: break; @@ -3035,19 +2947,19 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, perf_evsel__name(evsel)); } -struct perf_env *perf_evsel__env(struct perf_evsel *evsel) +struct perf_env *perf_evsel__env(struct evsel *evsel) { if (evsel && evsel->evlist) return evsel->evlist->env; return NULL; } -static int store_evsel_ids(struct perf_evsel *evsel, struct perf_evlist *evlist) +static int store_evsel_ids(struct evsel *evsel, struct evlist *evlist) { int cpu, thread; - for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) { - for (thread = 0; thread < xyarray__max_y(evsel->fd); + for (cpu = 0; cpu < xyarray__max_x(evsel->core.fd); cpu++) { + for (thread = 0; thread < xyarray__max_y(evsel->core.fd); thread++) { int fd = FD(evsel, cpu, thread); @@ -3060,10 +2972,10 @@ static int store_evsel_ids(struct perf_evsel *evsel, struct perf_evlist *evlist) return 0; } -int perf_evsel__store_ids(struct perf_evsel *evsel, struct perf_evlist *evlist) +int perf_evsel__store_ids(struct evsel *evsel, struct evlist *evlist) { - struct cpu_map *cpus = evsel->cpus; - struct thread_map *threads = evsel->threads; + struct perf_cpu_map *cpus = evsel->core.cpus; + struct perf_thread_map *threads = evsel->core.threads; if (perf_evsel__alloc_id(evsel, cpus->nr, threads->nr)) return -ENOMEM; diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index cad54e8ba522..5a351cae66df 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -4,15 +4,18 @@ #include <linux/list.h> #include <stdbool.h> -#include <stddef.h> +#include <stdio.h> +#include <sys/types.h> #include <linux/perf_event.h> #include <linux/types.h> -#include "xyarray.h" +#include <internal/evsel.h> +#include <perf/evsel.h> #include "symbol_conf.h" -#include "cpumap.h" -#include "counts.h" +#include <internal/cpumap.h> -struct perf_evsel; +struct addr_location; +struct evsel; +union perf_event; /* * Per fd, to map back from PERF_SAMPLE_ID to evsel, only used when there are @@ -21,7 +24,14 @@ struct perf_evsel; struct perf_sample_id { struct hlist_node node; u64 id; - struct perf_evsel *evsel; + struct evsel *evsel; + /* + * 'idx' will be used for AUX area sampling. A sample will have AUX area + * data that will be queued for decoding, where there are separate + * queues for each CPU (per-cpu tracing) or task (per-thread tracing). + * The sample ID can be used to lookup 'idx' which is effectively the + * queue number. + */ int idx; int cpu; pid_t tid; @@ -51,6 +61,7 @@ enum term_type { PERF_EVSEL__CONFIG_TERM_DRV_CFG, PERF_EVSEL__CONFIG_TERM_BRANCH, PERF_EVSEL__CONFIG_TERM_PERCORE, + PERF_EVSEL__CONFIG_TERM_AUX_OUTPUT, }; struct perf_evsel_config_term { @@ -69,6 +80,7 @@ struct perf_evsel_config_term { char *branch; unsigned long max_events; bool percore; + bool aux_output; } val; bool weak; }; @@ -82,11 +94,14 @@ enum perf_tool_event { PERF_TOOL_DURATION_TIME = 1, }; -/** struct perf_evsel - event selector +struct bpf_object; +struct perf_counts; +struct xyarray; + +/** struct evsel - event selector * * @evlist - evlist this evsel is in, if it is in one. - * @node - To insert it into evlist->entries or in other list_heads, say in - * the event parsing routines. + * @core - libperf evsel object * @name - Can be set to retain the original event name passed by the user, * so that when showing results in tools such as 'perf stat', we * show the name used, not some alias. @@ -98,12 +113,10 @@ enum perf_tool_event { * is used there is an id sample appended to non-sample events * @priv: And what is in its containing unnamed union are tool specific */ -struct perf_evsel { - struct list_head node; - struct perf_evlist *evlist; - struct perf_event_attr attr; +struct evsel { + struct perf_evsel core; + struct evlist *evlist; char *filter; - struct xyarray *fd; struct xyarray *sample_id; u64 *id; struct perf_counts *counts; @@ -122,9 +135,6 @@ struct perf_evsel { u64 db_id; struct cgroup *cgrp; void *handler; - struct cpu_map *cpus; - struct cpu_map *own_cpus; - struct thread_map *threads; unsigned int sample_size; int id_pos; int is_pos; @@ -145,19 +155,19 @@ struct perf_evsel { bool use_uncore_alias; /* parse modifier helper */ int exclude_GH; - int nr_members; int sample_read; unsigned long *per_pkg_mask; - struct perf_evsel *leader; + struct evsel *leader; char *group_name; bool cmdline_group_boundary; struct list_head config_terms; + struct bpf_object *bpf_obj; int bpf_fd; bool auto_merge_stats; bool merged_stat; const char * metric_expr; const char * metric_name; - struct perf_evsel **metric_events; + struct evsel **metric_events; bool collect_stat; bool weak_group; bool percore; @@ -185,72 +195,72 @@ struct perf_missing_features { bool group_read; bool ksymbol; bool bpf_event; + bool aux_output; }; extern struct perf_missing_features perf_missing_features; -struct cpu_map; +struct perf_cpu_map; struct target; struct thread_map; struct record_opts; -static inline struct cpu_map *perf_evsel__cpus(struct perf_evsel *evsel) +static inline struct perf_cpu_map *evsel__cpus(struct evsel *evsel) { - return evsel->cpus; + return perf_evsel__cpus(&evsel->core); } -static inline int perf_evsel__nr_cpus(struct perf_evsel *evsel) +static inline int perf_evsel__nr_cpus(struct evsel *evsel) { - return perf_evsel__cpus(evsel)->nr; + return evsel__cpus(evsel)->nr; } void perf_counts_values__scale(struct perf_counts_values *count, bool scale, s8 *pscaled); -void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu, int thread, +void perf_evsel__compute_deltas(struct evsel *evsel, int cpu, int thread, struct perf_counts_values *count); int perf_evsel__object_config(size_t object_size, - int (*init)(struct perf_evsel *evsel), - void (*fini)(struct perf_evsel *evsel)); + int (*init)(struct evsel *evsel), + void (*fini)(struct evsel *evsel)); -struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx); +struct evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx); -static inline struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr) +static inline struct evsel *evsel__new(struct perf_event_attr *attr) { return perf_evsel__new_idx(attr, 0); } -struct perf_evsel *perf_evsel__newtp_idx(const char *sys, const char *name, int idx); +struct evsel *perf_evsel__newtp_idx(const char *sys, const char *name, int idx); /* * Returns pointer with encoded error via <linux/err.h> interface. */ -static inline struct perf_evsel *perf_evsel__newtp(const char *sys, const char *name) +static inline struct evsel *perf_evsel__newtp(const char *sys, const char *name) { return perf_evsel__newtp_idx(sys, name, 0); } -struct perf_evsel *perf_evsel__new_cycles(bool precise); +struct evsel *perf_evsel__new_cycles(bool precise); struct tep_event *event_format__new(const char *sys, const char *name); -void perf_evsel__init(struct perf_evsel *evsel, - struct perf_event_attr *attr, int idx); -void perf_evsel__exit(struct perf_evsel *evsel); -void perf_evsel__delete(struct perf_evsel *evsel); +void evsel__init(struct evsel *evsel, struct perf_event_attr *attr, int idx); +void perf_evsel__exit(struct evsel *evsel); +void evsel__delete(struct evsel *evsel); struct callchain_param; -void perf_evsel__config(struct perf_evsel *evsel, +void perf_evsel__config(struct evsel *evsel, struct record_opts *opts, struct callchain_param *callchain); -void perf_evsel__config_callchain(struct perf_evsel *evsel, +void perf_evsel__config_callchain(struct evsel *evsel, struct record_opts *opts, struct callchain_param *callchain); int __perf_evsel__sample_size(u64 sample_type); -void perf_evsel__calc_id_pos(struct perf_evsel *evsel); +void perf_evsel__calc_id_pos(struct evsel *evsel); bool perf_evsel__is_cache_op_valid(u8 type, u8 op); @@ -266,17 +276,16 @@ extern const char *perf_evsel__hw_names[PERF_COUNT_HW_MAX]; extern const char *perf_evsel__sw_names[PERF_COUNT_SW_MAX]; int __perf_evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result, char *bf, size_t size); -const char *perf_evsel__name(struct perf_evsel *evsel); +const char *perf_evsel__name(struct evsel *evsel); -const char *perf_evsel__group_name(struct perf_evsel *evsel); -int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size); +const char *perf_evsel__group_name(struct evsel *evsel); +int perf_evsel__group_desc(struct evsel *evsel, char *buf, size_t size); -int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads); -void perf_evsel__close_fd(struct perf_evsel *evsel); +int perf_evsel__alloc_id(struct evsel *evsel, int ncpus, int nthreads); -void __perf_evsel__set_sample_bit(struct perf_evsel *evsel, +void __perf_evsel__set_sample_bit(struct evsel *evsel, enum perf_event_sample_format bit); -void __perf_evsel__reset_sample_bit(struct perf_evsel *evsel, +void __perf_evsel__reset_sample_bit(struct evsel *evsel, enum perf_event_sample_format bit); #define perf_evsel__set_sample_bit(evsel, bit) \ @@ -285,33 +294,32 @@ void __perf_evsel__reset_sample_bit(struct perf_evsel *evsel, #define perf_evsel__reset_sample_bit(evsel, bit) \ __perf_evsel__reset_sample_bit(evsel, PERF_SAMPLE_##bit) -void perf_evsel__set_sample_id(struct perf_evsel *evsel, +void perf_evsel__set_sample_id(struct evsel *evsel, bool use_sample_identifier); -int perf_evsel__set_filter(struct perf_evsel *evsel, const char *filter); -int perf_evsel__append_tp_filter(struct perf_evsel *evsel, const char *filter); -int perf_evsel__append_addr_filter(struct perf_evsel *evsel, +int perf_evsel__set_filter(struct evsel *evsel, const char *filter); +int perf_evsel__append_tp_filter(struct evsel *evsel, const char *filter); +int perf_evsel__append_addr_filter(struct evsel *evsel, const char *filter); -int perf_evsel__apply_filter(struct perf_evsel *evsel, const char *filter); -int perf_evsel__enable(struct perf_evsel *evsel); -int perf_evsel__disable(struct perf_evsel *evsel); - -int perf_evsel__open_per_cpu(struct perf_evsel *evsel, - struct cpu_map *cpus); -int perf_evsel__open_per_thread(struct perf_evsel *evsel, - struct thread_map *threads); -int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, - struct thread_map *threads); -void perf_evsel__close(struct perf_evsel *evsel); +int evsel__enable(struct evsel *evsel); +int evsel__disable(struct evsel *evsel); + +int perf_evsel__open_per_cpu(struct evsel *evsel, + struct perf_cpu_map *cpus); +int perf_evsel__open_per_thread(struct evsel *evsel, + struct perf_thread_map *threads); +int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus, + struct perf_thread_map *threads); +void evsel__close(struct evsel *evsel); struct perf_sample; -void *perf_evsel__rawptr(struct perf_evsel *evsel, struct perf_sample *sample, +void *perf_evsel__rawptr(struct evsel *evsel, struct perf_sample *sample, const char *name); -u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample, +u64 perf_evsel__intval(struct evsel *evsel, struct perf_sample *sample, const char *name); -static inline char *perf_evsel__strval(struct perf_evsel *evsel, +static inline char *perf_evsel__strval(struct evsel *evsel, struct perf_sample *sample, const char *name) { @@ -322,31 +330,28 @@ struct tep_format_field; u64 format_field__intval(struct tep_format_field *field, struct perf_sample *sample, bool needs_swap); -struct tep_format_field *perf_evsel__field(struct perf_evsel *evsel, const char *name); +struct tep_format_field *perf_evsel__field(struct evsel *evsel, const char *name); #define perf_evsel__match(evsel, t, c) \ - (evsel->attr.type == PERF_TYPE_##t && \ - evsel->attr.config == PERF_COUNT_##c) + (evsel->core.attr.type == PERF_TYPE_##t && \ + evsel->core.attr.config == PERF_COUNT_##c) -static inline bool perf_evsel__match2(struct perf_evsel *e1, - struct perf_evsel *e2) +static inline bool perf_evsel__match2(struct evsel *e1, + struct evsel *e2) { - return (e1->attr.type == e2->attr.type) && - (e1->attr.config == e2->attr.config); + return (e1->core.attr.type == e2->core.attr.type) && + (e1->core.attr.config == e2->core.attr.config); } #define perf_evsel__cmp(a, b) \ ((a) && \ (b) && \ - (a)->attr.type == (b)->attr.type && \ - (a)->attr.config == (b)->attr.config) - -int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread, - struct perf_counts_values *count); + (a)->core.attr.type == (b)->core.attr.type && \ + (a)->core.attr.config == (b)->core.attr.config) -int perf_evsel__read_counter(struct perf_evsel *evsel, int cpu, int thread); +int perf_evsel__read_counter(struct evsel *evsel, int cpu, int thread); -int __perf_evsel__read_on_cpu(struct perf_evsel *evsel, +int __perf_evsel__read_on_cpu(struct evsel *evsel, int cpu, int thread, bool scale); /** @@ -356,7 +361,7 @@ int __perf_evsel__read_on_cpu(struct perf_evsel *evsel, * @cpu - CPU of interest * @thread - thread of interest */ -static inline int perf_evsel__read_on_cpu(struct perf_evsel *evsel, +static inline int perf_evsel__read_on_cpu(struct evsel *evsel, int cpu, int thread) { return __perf_evsel__read_on_cpu(evsel, cpu, thread, false); @@ -369,27 +374,27 @@ static inline int perf_evsel__read_on_cpu(struct perf_evsel *evsel, * @cpu - CPU of interest * @thread - thread of interest */ -static inline int perf_evsel__read_on_cpu_scaled(struct perf_evsel *evsel, +static inline int perf_evsel__read_on_cpu_scaled(struct evsel *evsel, int cpu, int thread) { return __perf_evsel__read_on_cpu(evsel, cpu, thread, true); } -int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, +int perf_evsel__parse_sample(struct evsel *evsel, union perf_event *event, struct perf_sample *sample); -int perf_evsel__parse_sample_timestamp(struct perf_evsel *evsel, +int perf_evsel__parse_sample_timestamp(struct evsel *evsel, union perf_event *event, u64 *timestamp); -static inline struct perf_evsel *perf_evsel__next(struct perf_evsel *evsel) +static inline struct evsel *perf_evsel__next(struct evsel *evsel) { - return list_entry(evsel->node.next, struct perf_evsel, node); + return list_entry(evsel->core.node.next, struct evsel, core.node); } -static inline struct perf_evsel *perf_evsel__prev(struct perf_evsel *evsel) +static inline struct evsel *perf_evsel__prev(struct evsel *evsel) { - return list_entry(evsel->node.prev, struct perf_evsel, node); + return list_entry(evsel->core.node.prev, struct evsel, core.node); } /** @@ -399,7 +404,7 @@ static inline struct perf_evsel *perf_evsel__prev(struct perf_evsel *evsel) * * Return %true if @evsel is a group leader or a stand-alone event */ -static inline bool perf_evsel__is_group_leader(const struct perf_evsel *evsel) +static inline bool perf_evsel__is_group_leader(const struct evsel *evsel) { return evsel->leader == evsel; } @@ -412,22 +417,22 @@ static inline bool perf_evsel__is_group_leader(const struct perf_evsel *evsel) * Return %true iff event group view is enabled and @evsel is a actual group * leader which has other members in the group */ -static inline bool perf_evsel__is_group_event(struct perf_evsel *evsel) +static inline bool perf_evsel__is_group_event(struct evsel *evsel) { if (!symbol_conf.event_group) return false; - return perf_evsel__is_group_leader(evsel) && evsel->nr_members > 1; + return perf_evsel__is_group_leader(evsel) && evsel->core.nr_members > 1; } -bool perf_evsel__is_function_event(struct perf_evsel *evsel); +bool perf_evsel__is_function_event(struct evsel *evsel); -static inline bool perf_evsel__is_bpf_output(struct perf_evsel *evsel) +static inline bool perf_evsel__is_bpf_output(struct evsel *evsel) { return perf_evsel__match(evsel, SOFTWARE, SW_BPF_OUTPUT); } -static inline bool perf_evsel__is_clock(struct perf_evsel *evsel) +static inline bool perf_evsel__is_clock(struct evsel *evsel) { return perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK) || perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK); @@ -441,7 +446,7 @@ struct perf_attr_details { bool trace_fields; }; -int perf_evsel__fprintf(struct perf_evsel *evsel, +int perf_evsel__fprintf(struct evsel *evsel, struct perf_attr_details *details, FILE *fp); #define EVSEL__PRINT_IP (1<<0) @@ -464,36 +469,36 @@ int sample__fprintf_sym(struct perf_sample *sample, struct addr_location *al, int left_alignment, unsigned int print_opts, struct callchain_cursor *cursor, FILE *fp); -bool perf_evsel__fallback(struct perf_evsel *evsel, int err, +bool perf_evsel__fallback(struct evsel *evsel, int err, char *msg, size_t msgsize); -int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, +int perf_evsel__open_strerror(struct evsel *evsel, struct target *target, int err, char *msg, size_t size); -static inline int perf_evsel__group_idx(struct perf_evsel *evsel) +static inline int perf_evsel__group_idx(struct evsel *evsel) { return evsel->idx - evsel->leader->idx; } /* Iterates group WITHOUT the leader. */ #define for_each_group_member(_evsel, _leader) \ -for ((_evsel) = list_entry((_leader)->node.next, struct perf_evsel, node); \ +for ((_evsel) = list_entry((_leader)->core.node.next, struct evsel, core.node); \ (_evsel) && (_evsel)->leader == (_leader); \ - (_evsel) = list_entry((_evsel)->node.next, struct perf_evsel, node)) + (_evsel) = list_entry((_evsel)->core.node.next, struct evsel, core.node)) /* Iterates group WITH the leader. */ #define for_each_group_evsel(_evsel, _leader) \ for ((_evsel) = _leader; \ (_evsel) && (_evsel)->leader == (_leader); \ - (_evsel) = list_entry((_evsel)->node.next, struct perf_evsel, node)) + (_evsel) = list_entry((_evsel)->core.node.next, struct evsel, core.node)) -static inline bool perf_evsel__has_branch_callstack(const struct perf_evsel *evsel) +static inline bool perf_evsel__has_branch_callstack(const struct evsel *evsel) { - return evsel->attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK; + return evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK; } -static inline bool evsel__has_callchain(const struct perf_evsel *evsel) +static inline bool evsel__has_callchain(const struct evsel *evsel) { - return (evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN) != 0; + return (evsel->core.attr.sample_type & PERF_SAMPLE_CALLCHAIN) != 0; } typedef int (*attr__fprintf_f)(FILE *, const char *, const char *, void *); @@ -501,7 +506,7 @@ typedef int (*attr__fprintf_f)(FILE *, const char *, const char *, void *); int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr, attr__fprintf_f attr__fprintf, void *priv); -struct perf_env *perf_evsel__env(struct perf_evsel *evsel); +struct perf_env *perf_evsel__env(struct evsel *evsel); -int perf_evsel__store_ids(struct perf_evsel *evsel, struct perf_evlist *evlist); +int perf_evsel__store_ids(struct evsel *evsel, struct evlist *evlist); #endif /* __PERF_EVSEL_H */ diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c index 95ea147f9e18..496fec01f5d1 100644 --- a/tools/perf/util/evsel_fprintf.c +++ b/tools/perf/util/evsel_fprintf.c @@ -33,26 +33,26 @@ static int __print_attr__fprintf(FILE *fp, const char *name, const char *val, vo return comma_fprintf(fp, (bool *)priv, " %s: %s", name, val); } -int perf_evsel__fprintf(struct perf_evsel *evsel, +int perf_evsel__fprintf(struct evsel *evsel, struct perf_attr_details *details, FILE *fp) { bool first = true; int printed = 0; if (details->event_group) { - struct perf_evsel *pos; + struct evsel *pos; if (!perf_evsel__is_group_leader(evsel)) return 0; - if (evsel->nr_members > 1) + if (evsel->core.nr_members > 1) printed += fprintf(fp, "%s{", evsel->group_name ?: ""); printed += fprintf(fp, "%s", perf_evsel__name(evsel)); for_each_group_member(pos, evsel) printed += fprintf(fp, ",%s", perf_evsel__name(pos)); - if (evsel->nr_members > 1) + if (evsel->core.nr_members > 1) printed += fprintf(fp, "}"); goto out; } @@ -60,22 +60,22 @@ int perf_evsel__fprintf(struct perf_evsel *evsel, printed += fprintf(fp, "%s", perf_evsel__name(evsel)); if (details->verbose) { - printed += perf_event_attr__fprintf(fp, &evsel->attr, + printed += perf_event_attr__fprintf(fp, &evsel->core.attr, __print_attr__fprintf, &first); } else if (details->freq) { const char *term = "sample_freq"; - if (!evsel->attr.freq) + if (!evsel->core.attr.freq) term = "sample_period"; printed += comma_fprintf(fp, &first, " %s=%" PRIu64, - term, (u64)evsel->attr.sample_freq); + term, (u64)evsel->core.attr.sample_freq); } if (details->trace_fields) { struct tep_format_field *field; - if (evsel->attr.type != PERF_TYPE_TRACEPOINT) { + if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT) { printed += comma_fprintf(fp, &first, " (not a tracepoint)"); goto out; } diff --git a/tools/perf/util/evswitch.c b/tools/perf/util/evswitch.c new file mode 100644 index 000000000000..3ba72f743d3c --- /dev/null +++ b/tools/perf/util/evswitch.c @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright (C) 2019, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com> + +#include "evswitch.h" +#include "evlist.h" + +bool evswitch__discard(struct evswitch *evswitch, struct evsel *evsel) +{ + if (evswitch->on && evswitch->discarding) { + if (evswitch->on != evsel) + return true; + + evswitch->discarding = false; + + if (!evswitch->show_on_off_events) + return true; + + return false; + } + + if (evswitch->off && !evswitch->discarding) { + if (evswitch->off != evsel) + return false; + + evswitch->discarding = true; + + if (!evswitch->show_on_off_events) + return true; + } + + return false; +} + +static int evswitch__fprintf_enoent(FILE *fp, const char *evtype, const char *evname) +{ + int printed = fprintf(fp, "ERROR: switch-%s event not found (%s)\n", evtype, evname); + + return printed += fprintf(fp, "HINT: use 'perf evlist' to see the available event names\n"); +} + +int evswitch__init(struct evswitch *evswitch, struct evlist *evlist, FILE *fp) +{ + if (evswitch->on_name) { + evswitch->on = perf_evlist__find_evsel_by_str(evlist, evswitch->on_name); + if (evswitch->on == NULL) { + evswitch__fprintf_enoent(fp, "on", evswitch->on_name); + return -ENOENT; + } + evswitch->discarding = true; + } + + if (evswitch->off_name) { + evswitch->off = perf_evlist__find_evsel_by_str(evlist, evswitch->off_name); + if (evswitch->off == NULL) { + evswitch__fprintf_enoent(fp, "off", evswitch->off_name); + return -ENOENT; + } + } + + return 0; +} diff --git a/tools/perf/util/evswitch.h b/tools/perf/util/evswitch.h new file mode 100644 index 000000000000..fd30460b6218 --- /dev/null +++ b/tools/perf/util/evswitch.h @@ -0,0 +1,31 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright (C) 2019, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com> +#ifndef __PERF_EVSWITCH_H +#define __PERF_EVSWITCH_H 1 + +#include <stdbool.h> +#include <stdio.h> + +struct evsel; +struct evlist; + +struct evswitch { + struct evsel *on, *off; + const char *on_name, *off_name; + bool discarding; + bool show_on_off_events; +}; + +int evswitch__init(struct evswitch *evswitch, struct evlist *evlist, FILE *fp); + +bool evswitch__discard(struct evswitch *evswitch, struct evsel *evsel); + +#define OPTS_EVSWITCH(evswitch) \ + OPT_STRING(0, "switch-on", &(evswitch)->on_name, \ + "event", "Consider events after the ocurrence of this event"), \ + OPT_STRING(0, "switch-off", &(evswitch)->off_name, \ + "event", "Stop considering events after the ocurrence of this event"), \ + OPT_BOOLEAN(0, "show-on-off-events", &(evswitch)->show_on_off_events, \ + "Show the on/off switch events, used with --switch-on and --switch-off") + +#endif /* __PERF_EVSWITCH_H */ diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 1903d7ec9797..1f2965a07bef 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -20,6 +20,7 @@ #include <linux/time64.h> #include <dirent.h> #include <bpf/libbpf.h> +#include <perf/cpumap.h> #include "evlist.h" #include "evsel.h" @@ -74,7 +75,7 @@ struct feat_fd { void *buf; /* Either buf != NULL or fd >= 0 */ ssize_t offset; size_t size; - struct perf_evsel *events; + struct evsel *events; }; void perf_header__set_feat(struct perf_header *header, int feat) @@ -299,16 +300,16 @@ static int do_read_bitmap(struct feat_fd *ff, unsigned long **pset, u64 *psize) } static int write_tracing_data(struct feat_fd *ff, - struct perf_evlist *evlist) + struct evlist *evlist) { if (WARN(ff->buf, "Error: calling %s in pipe-mode.\n", __func__)) return -1; - return read_tracing_data(ff->fd, &evlist->entries); + return read_tracing_data(ff->fd, &evlist->core.entries); } static int write_build_id(struct feat_fd *ff, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { struct perf_session *session; int err; @@ -332,7 +333,7 @@ static int write_build_id(struct feat_fd *ff, } static int write_hostname(struct feat_fd *ff, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { struct utsname uts; int ret; @@ -345,7 +346,7 @@ static int write_hostname(struct feat_fd *ff, } static int write_osrelease(struct feat_fd *ff, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { struct utsname uts; int ret; @@ -358,7 +359,7 @@ static int write_osrelease(struct feat_fd *ff, } static int write_arch(struct feat_fd *ff, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { struct utsname uts; int ret; @@ -371,7 +372,7 @@ static int write_arch(struct feat_fd *ff, } static int write_version(struct feat_fd *ff, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { return do_write_string(ff, perf_version_string); } @@ -432,7 +433,7 @@ done: } static int write_cpudesc(struct feat_fd *ff, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { const char *cpuinfo_procs[] = CPUINFO_PROC; unsigned int i; @@ -448,7 +449,7 @@ static int write_cpudesc(struct feat_fd *ff, static int write_nrcpus(struct feat_fd *ff, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { long nr; u32 nrc, nra; @@ -470,13 +471,13 @@ static int write_nrcpus(struct feat_fd *ff, } static int write_event_desc(struct feat_fd *ff, - struct perf_evlist *evlist) + struct evlist *evlist) { - struct perf_evsel *evsel; + struct evsel *evsel; u32 nre, nri, sz; int ret; - nre = evlist->nr_entries; + nre = evlist->core.nr_entries; /* * write number of events @@ -488,13 +489,13 @@ static int write_event_desc(struct feat_fd *ff, /* * size of perf_event_attr struct */ - sz = (u32)sizeof(evsel->attr); + sz = (u32)sizeof(evsel->core.attr); ret = do_write(ff, &sz, sizeof(sz)); if (ret < 0) return ret; evlist__for_each_entry(evlist, evsel) { - ret = do_write(ff, &evsel->attr, sz); + ret = do_write(ff, &evsel->core.attr, sz); if (ret < 0) return ret; /* @@ -526,7 +527,7 @@ static int write_event_desc(struct feat_fd *ff, } static int write_cmdline(struct feat_fd *ff, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { char pbuf[MAXPATHLEN], *buf; int i, ret, n; @@ -555,7 +556,7 @@ static int write_cmdline(struct feat_fd *ff, static int write_cpu_topology(struct feat_fd *ff, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { struct cpu_topology *tp; u32 i; @@ -627,7 +628,7 @@ done: static int write_total_mem(struct feat_fd *ff, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { char *buf = NULL; FILE *fp; @@ -656,7 +657,7 @@ static int write_total_mem(struct feat_fd *ff, } static int write_numa_topology(struct feat_fd *ff, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { struct numa_topology *tp; int ret = -1; @@ -710,7 +711,7 @@ err: */ static int write_pmu_mappings(struct feat_fd *ff, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { struct perf_pmu *pmu = NULL; u32 pmu_num = 0; @@ -759,10 +760,10 @@ static int write_pmu_mappings(struct feat_fd *ff, * }; */ static int write_group_desc(struct feat_fd *ff, - struct perf_evlist *evlist) + struct evlist *evlist) { u32 nr_groups = evlist->nr_groups; - struct perf_evsel *evsel; + struct evsel *evsel; int ret; ret = do_write(ff, &nr_groups, sizeof(nr_groups)); @@ -771,10 +772,10 @@ static int write_group_desc(struct feat_fd *ff, evlist__for_each_entry(evlist, evsel) { if (perf_evsel__is_group_leader(evsel) && - evsel->nr_members > 1) { + evsel->core.nr_members > 1) { const char *name = evsel->group_name ?: "{anon_group}"; u32 leader_idx = evsel->idx; - u32 nr_members = evsel->nr_members; + u32 nr_members = evsel->core.nr_members; ret = do_write_string(ff, name); if (ret < 0) @@ -841,7 +842,7 @@ int __weak get_cpuid(char *buffer __maybe_unused, size_t sz __maybe_unused) } static int write_cpuid(struct feat_fd *ff, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { char buffer[64]; int ret; @@ -854,13 +855,13 @@ static int write_cpuid(struct feat_fd *ff, } static int write_branch_stack(struct feat_fd *ff __maybe_unused, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { return 0; } static int write_auxtrace(struct feat_fd *ff, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { struct perf_session *session; int err; @@ -877,14 +878,14 @@ static int write_auxtrace(struct feat_fd *ff, } static int write_clockid(struct feat_fd *ff, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { return do_write(ff, &ff->ph->env.clockid_res_ns, sizeof(ff->ph->env.clockid_res_ns)); } static int write_dir_format(struct feat_fd *ff, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { struct perf_session *session; struct perf_data *data; @@ -900,7 +901,7 @@ static int write_dir_format(struct feat_fd *ff, #ifdef HAVE_LIBBPF_SUPPORT static int write_bpf_prog_info(struct feat_fd *ff, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { struct perf_env *env = &ff->ph->env; struct rb_root *root; @@ -942,14 +943,14 @@ out: } #else // HAVE_LIBBPF_SUPPORT static int write_bpf_prog_info(struct feat_fd *ff __maybe_unused, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { return 0; } #endif // HAVE_LIBBPF_SUPPORT static int write_bpf_btf(struct feat_fd *ff, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { struct perf_env *env = &ff->ph->env; struct rb_root *root; @@ -1123,7 +1124,7 @@ static int build_caches(struct cpu_cache_level caches[], u32 size, u32 *cntp) #define MAX_CACHES (MAX_NR_CPUS * 4) static int write_cache(struct feat_fd *ff, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { struct cpu_cache_level caches[MAX_CACHES]; u32 cnt = 0, i, version = 1; @@ -1175,13 +1176,13 @@ out: } static int write_stat(struct feat_fd *ff __maybe_unused, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { return 0; } static int write_sample_time(struct feat_fd *ff, - struct perf_evlist *evlist) + struct evlist *evlist) { int ret; @@ -1315,7 +1316,7 @@ static int build_mem_topology(struct memory_node *nodes, u64 size, u64 *cntp) * 48 - bitmap | bitmap of memory indexes that belongs to node */ static int write_mem_topology(struct feat_fd *ff __maybe_unused, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { static struct memory_node nodes[MAX_MEMORY_NODES]; u64 bsize, version = 1, i, nr; @@ -1365,7 +1366,7 @@ out: } static int write_compressed(struct feat_fd *ff __maybe_unused, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { int ret; @@ -1568,14 +1569,14 @@ static void print_bpf_btf(struct feat_fd *ff, FILE *fp) up_read(&env->bpf_progs.lock); } -static void free_event_desc(struct perf_evsel *events) +static void free_event_desc(struct evsel *events) { - struct perf_evsel *evsel; + struct evsel *evsel; if (!events) return; - for (evsel = events; evsel->attr.size; evsel++) { + for (evsel = events; evsel->core.attr.size; evsel++) { zfree(&evsel->name); zfree(&evsel->id); } @@ -1583,9 +1584,9 @@ static void free_event_desc(struct perf_evsel *events) free(events); } -static struct perf_evsel *read_event_desc(struct feat_fd *ff) +static struct evsel *read_event_desc(struct feat_fd *ff) { - struct perf_evsel *evsel, *events = NULL; + struct evsel *evsel, *events = NULL; u64 *id; void *buf = NULL; u32 nre, sz, nr, i, j; @@ -1603,12 +1604,12 @@ static struct perf_evsel *read_event_desc(struct feat_fd *ff) if (!buf) goto error; - /* the last event terminates with evsel->attr.size == 0: */ + /* the last event terminates with evsel->core.attr.size == 0: */ events = calloc(nre + 1, sizeof(*events)); if (!events) goto error; - msz = sizeof(evsel->attr); + msz = sizeof(evsel->core.attr); if (sz < msz) msz = sz; @@ -1625,7 +1626,7 @@ static struct perf_evsel *read_event_desc(struct feat_fd *ff) if (ff->ph->needs_swap) perf_event__attr_swap(buf); - memcpy(&evsel->attr, buf, msz); + memcpy(&evsel->core.attr, buf, msz); if (do_read_u32(ff, &nr)) goto error; @@ -1669,7 +1670,7 @@ static int __desc_attr__fprintf(FILE *fp, const char *name, const char *val, static void print_event_desc(struct feat_fd *ff, FILE *fp) { - struct perf_evsel *evsel, *events; + struct evsel *evsel, *events; u32 j; u64 *id; @@ -1683,7 +1684,7 @@ static void print_event_desc(struct feat_fd *ff, FILE *fp) return; } - for (evsel = events; evsel->attr.size; evsel++) { + for (evsel = events; evsel->core.attr.size; evsel++) { fprintf(fp, "# event : name = %s, ", evsel->name); if (evsel->ids) { @@ -1696,7 +1697,7 @@ static void print_event_desc(struct feat_fd *ff, FILE *fp) fprintf(fp, " }"); } - perf_event_attr__fprintf(fp, &evsel->attr, __desc_attr__fprintf, NULL); + perf_event_attr__fprintf(fp, &evsel->core.attr, __desc_attr__fprintf, NULL); fputc('\n', fp); } @@ -1804,18 +1805,18 @@ error: static void print_group_desc(struct feat_fd *ff, FILE *fp) { struct perf_session *session; - struct perf_evsel *evsel; + struct evsel *evsel; u32 nr = 0; session = container_of(ff->ph, struct perf_session, header); evlist__for_each_entry(session->evlist, evsel) { if (perf_evsel__is_group_leader(evsel) && - evsel->nr_members > 1) { + evsel->core.nr_members > 1) { fprintf(fp, "# group: %s{%s", evsel->group_name ?: "", perf_evsel__name(evsel)); - nr = evsel->nr_members - 1; + nr = evsel->core.nr_members - 1; } else if (nr) { fprintf(fp, ",%s", perf_evsel__name(evsel)); @@ -2089,10 +2090,10 @@ static int process_total_mem(struct feat_fd *ff, void *data __maybe_unused) return 0; } -static struct perf_evsel * -perf_evlist__find_by_index(struct perf_evlist *evlist, int idx) +static struct evsel * +perf_evlist__find_by_index(struct evlist *evlist, int idx) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { if (evsel->idx == idx) @@ -2103,10 +2104,10 @@ perf_evlist__find_by_index(struct perf_evlist *evlist, int idx) } static void -perf_evlist__set_event_name(struct perf_evlist *evlist, - struct perf_evsel *event) +perf_evlist__set_event_name(struct evlist *evlist, + struct evsel *event) { - struct perf_evsel *evsel; + struct evsel *evsel; if (!event->name) return; @@ -2125,7 +2126,7 @@ static int process_event_desc(struct feat_fd *ff, void *data __maybe_unused) { struct perf_session *session; - struct perf_evsel *evsel, *events = read_event_desc(ff); + struct evsel *evsel, *events = read_event_desc(ff); if (!events) return 0; @@ -2138,7 +2139,7 @@ process_event_desc(struct feat_fd *ff, void *data __maybe_unused) ff->events = events; } - for (evsel = events; evsel->attr.size; evsel++) + for (evsel = events; evsel->core.attr.size; evsel++) perf_evlist__set_event_name(session->evlist, evsel); if (!session->data->is_pipe) @@ -2251,8 +2252,10 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused) /* On s390 the socket_id number is not related to the numbers of cpus. * The socket_id number might be higher than the numbers of cpus. * This depends on the configuration. + * AArch64 is the same. */ - if (ph->env.arch && !strncmp(ph->env.arch, "s390", 4)) + if (ph->env.arch && (!strncmp(ph->env.arch, "s390", 4) + || !strncmp(ph->env.arch, "aarch64", 7))) do_core_id_test = false; for (i = 0; i < (u32)cpu_nr; i++) { @@ -2348,7 +2351,7 @@ static int process_numa_topology(struct feat_fd *ff, void *data __maybe_unused) if (!str) goto error; - n->map = cpu_map__new(str); + n->map = perf_cpu_map__new(str); if (!n->map) goto error; @@ -2415,7 +2418,7 @@ static int process_group_desc(struct feat_fd *ff, void *data __maybe_unused) size_t ret = -1; u32 i, nr, nr_groups; struct perf_session *session; - struct perf_evsel *evsel, *leader = NULL; + struct evsel *evsel, *leader = NULL; struct group_desc { char *name; u32 leader_idx; @@ -2462,7 +2465,7 @@ static int process_group_desc(struct feat_fd *ff, void *data __maybe_unused) evsel->group_name = desc[i].name; desc[i].name = NULL; } - evsel->nr_members = desc[i].nr_members; + evsel->core.nr_members = desc[i].nr_members; if (i >= nr_groups || nr > 0) { pr_debug("invalid group desc\n"); @@ -2470,7 +2473,7 @@ static int process_group_desc(struct feat_fd *ff, void *data __maybe_unused) } leader = evsel; - nr = evsel->nr_members - 1; + nr = evsel->core.nr_members - 1; i++; } else if (nr) { /* This is a group member */ @@ -2801,7 +2804,7 @@ static int process_compressed(struct feat_fd *ff, } struct feature_ops { - int (*write)(struct feat_fd *ff, struct perf_evlist *evlist); + int (*write)(struct feat_fd *ff, struct evlist *evlist); void (*print)(struct feat_fd *ff, FILE *fp); int (*process)(struct feat_fd *ff, void *data); const char *name; @@ -2946,7 +2949,7 @@ int perf_header__fprintf_info(struct perf_session *session, FILE *fp, bool full) static int do_write_feat(struct feat_fd *ff, int type, struct perf_file_section **p, - struct perf_evlist *evlist) + struct evlist *evlist) { int err; int ret = 0; @@ -2976,7 +2979,7 @@ static int do_write_feat(struct feat_fd *ff, int type, } static int perf_header__adds_write(struct perf_header *header, - struct perf_evlist *evlist, int fd) + struct evlist *evlist, int fd) { int nr_sections; struct feat_fd ff; @@ -3044,13 +3047,13 @@ int perf_header__write_pipe(int fd) } int perf_session__write_header(struct perf_session *session, - struct perf_evlist *evlist, + struct evlist *evlist, int fd, bool at_exit) { struct perf_file_header f_header; struct perf_file_attr f_attr; struct perf_header *header = &session->header; - struct perf_evsel *evsel; + struct evsel *evsel; struct feat_fd ff; u64 attr_offset; int err; @@ -3071,7 +3074,7 @@ int perf_session__write_header(struct perf_session *session, evlist__for_each_entry(evlist, evsel) { f_attr = (struct perf_file_attr){ - .attr = evsel->attr, + .attr = evsel->core.attr, .ids = { .offset = evsel->id_offset, .size = evsel->ids * sizeof(u64), @@ -3100,7 +3103,7 @@ int perf_session__write_header(struct perf_session *session, .attr_size = sizeof(f_attr), .attrs = { .offset = attr_offset, - .size = evlist->nr_entries * sizeof(f_attr), + .size = evlist->core.nr_entries * sizeof(f_attr), }, .data = { .offset = header->data_offset, @@ -3479,7 +3482,7 @@ static int read_attr(int fd, struct perf_header *ph, return ret <= 0 ? -1 : 0; } -static int perf_evsel__prepare_tracepoint_event(struct perf_evsel *evsel, +static int perf_evsel__prepare_tracepoint_event(struct evsel *evsel, struct tep_handle *pevent) { struct tep_event *event; @@ -3494,9 +3497,9 @@ static int perf_evsel__prepare_tracepoint_event(struct perf_evsel *evsel, return -1; } - event = tep_find_event(pevent, evsel->attr.config); + event = tep_find_event(pevent, evsel->core.attr.config); if (event == NULL) { - pr_debug("cannot find event format for %d\n", (int)evsel->attr.config); + pr_debug("cannot find event format for %d\n", (int)evsel->core.attr.config); return -1; } @@ -3511,13 +3514,13 @@ static int perf_evsel__prepare_tracepoint_event(struct perf_evsel *evsel, return 0; } -static int perf_evlist__prepare_tracepoint_events(struct perf_evlist *evlist, +static int perf_evlist__prepare_tracepoint_events(struct evlist *evlist, struct tep_handle *pevent) { - struct perf_evsel *pos; + struct evsel *pos; evlist__for_each_entry(evlist, pos) { - if (pos->attr.type == PERF_TYPE_TRACEPOINT && + if (pos->core.attr.type == PERF_TYPE_TRACEPOINT && perf_evsel__prepare_tracepoint_event(pos, pevent)) return -1; } @@ -3535,7 +3538,7 @@ int perf_session__read_header(struct perf_session *session) int nr_attrs, nr_ids, i, j; int fd = perf_data__fd(data); - session->evlist = perf_evlist__new(); + session->evlist = evlist__new(); if (session->evlist == NULL) return -ENOMEM; @@ -3570,7 +3573,7 @@ int perf_session__read_header(struct perf_session *session) lseek(fd, f_header.attrs.offset, SEEK_SET); for (i = 0; i < nr_attrs; i++) { - struct perf_evsel *evsel; + struct evsel *evsel; off_t tmp; if (read_attr(fd, header, &f_attr) < 0) @@ -3583,7 +3586,7 @@ int perf_session__read_header(struct perf_session *session) } tmp = lseek(fd, 0, SEEK_CUR); - evsel = perf_evsel__new(&f_attr.attr); + evsel = evsel__new(&f_attr.attr); if (evsel == NULL) goto out_delete_evlist; @@ -3591,9 +3594,9 @@ int perf_session__read_header(struct perf_session *session) evsel->needs_swap = header->needs_swap; /* * Do it before so that if perf_evsel__alloc_id fails, this - * entry gets purged too at perf_evlist__delete(). + * entry gets purged too at evlist__delete(). */ - perf_evlist__add(session->evlist, evsel); + evlist__add(session->evlist, evsel); nr_ids = f_attr.ids.size / sizeof(u64); /* @@ -3628,7 +3631,7 @@ out_errno: return -errno; out_delete_evlist: - perf_evlist__delete(session->evlist); + evlist__delete(session->evlist); session->evlist = NULL; return -ENOMEM; } @@ -3669,7 +3672,7 @@ int perf_event__synthesize_attr(struct perf_tool *tool, int perf_event__synthesize_features(struct perf_tool *tool, struct perf_session *session, - struct perf_evlist *evlist, + struct evlist *evlist, perf_event__handler_t process) { struct perf_header *header = &session->header; @@ -3794,7 +3797,7 @@ event_update_event__new(size_t size, u64 type, u64 id) int perf_event__synthesize_event_update_unit(struct perf_tool *tool, - struct perf_evsel *evsel, + struct evsel *evsel, perf_event__handler_t process) { struct event_update_event *ev; @@ -3813,7 +3816,7 @@ perf_event__synthesize_event_update_unit(struct perf_tool *tool, int perf_event__synthesize_event_update_scale(struct perf_tool *tool, - struct perf_evsel *evsel, + struct evsel *evsel, perf_event__handler_t process) { struct event_update_event *ev; @@ -3833,7 +3836,7 @@ perf_event__synthesize_event_update_scale(struct perf_tool *tool, int perf_event__synthesize_event_update_name(struct perf_tool *tool, - struct perf_evsel *evsel, + struct evsel *evsel, perf_event__handler_t process) { struct event_update_event *ev; @@ -3852,7 +3855,7 @@ perf_event__synthesize_event_update_name(struct perf_tool *tool, int perf_event__synthesize_event_update_cpus(struct perf_tool *tool, - struct perf_evsel *evsel, + struct evsel *evsel, perf_event__handler_t process) { size_t size = sizeof(struct event_update_event); @@ -3860,10 +3863,10 @@ perf_event__synthesize_event_update_cpus(struct perf_tool *tool, int max, err; u16 type; - if (!evsel->own_cpus) + if (!evsel->core.own_cpus) return 0; - ev = cpu_map_data__alloc(evsel->own_cpus, &size, &type, &max); + ev = cpu_map_data__alloc(evsel->core.own_cpus, &size, &type, &max); if (!ev) return -ENOMEM; @@ -3873,7 +3876,7 @@ perf_event__synthesize_event_update_cpus(struct perf_tool *tool, ev->id = evsel->id[0]; cpu_map_data__synthesize((struct cpu_map_data *) ev->data, - evsel->own_cpus, + evsel->core.own_cpus, type, max); err = process(tool, (union perf_event*) ev, NULL, NULL); @@ -3886,7 +3889,7 @@ size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp) struct event_update_event *ev = &event->event_update; struct event_update_event_scale *ev_scale; struct event_update_event_cpus *ev_cpus; - struct cpu_map *map; + struct perf_cpu_map *map; size_t ret; ret = fprintf(fp, "\n... id: %" PRIu64 "\n", ev->id); @@ -3921,14 +3924,14 @@ size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp) } int perf_event__synthesize_attrs(struct perf_tool *tool, - struct perf_evlist *evlist, + struct evlist *evlist, perf_event__handler_t process) { - struct perf_evsel *evsel; + struct evsel *evsel; int err = 0; evlist__for_each_entry(evlist, evsel) { - err = perf_event__synthesize_attr(tool, &evsel->attr, evsel->ids, + err = perf_event__synthesize_attr(tool, &evsel->core.attr, evsel->ids, evsel->id, process); if (err) { pr_debug("failed to create perf header attribute\n"); @@ -3939,22 +3942,22 @@ int perf_event__synthesize_attrs(struct perf_tool *tool, return err; } -static bool has_unit(struct perf_evsel *counter) +static bool has_unit(struct evsel *counter) { return counter->unit && *counter->unit; } -static bool has_scale(struct perf_evsel *counter) +static bool has_scale(struct evsel *counter) { return counter->scale != 1; } int perf_event__synthesize_extra_attr(struct perf_tool *tool, - struct perf_evlist *evsel_list, + struct evlist *evsel_list, perf_event__handler_t process, bool is_pipe) { - struct perf_evsel *counter; + struct evsel *counter; int err; /* @@ -3984,7 +3987,7 @@ int perf_event__synthesize_extra_attr(struct perf_tool *tool, } } - if (counter->own_cpus) { + if (counter->core.own_cpus) { err = perf_event__synthesize_event_update_cpus(tool, counter, process); if (err < 0) { pr_err("Couldn't synthesize evsel cpus.\n"); @@ -4009,23 +4012,23 @@ int perf_event__synthesize_extra_attr(struct perf_tool *tool, int perf_event__process_attr(struct perf_tool *tool __maybe_unused, union perf_event *event, - struct perf_evlist **pevlist) + struct evlist **pevlist) { u32 i, ids, n_ids; - struct perf_evsel *evsel; - struct perf_evlist *evlist = *pevlist; + struct evsel *evsel; + struct evlist *evlist = *pevlist; if (evlist == NULL) { - *pevlist = evlist = perf_evlist__new(); + *pevlist = evlist = evlist__new(); if (evlist == NULL) return -ENOMEM; } - evsel = perf_evsel__new(&event->attr.attr); + evsel = evsel__new(&event->attr.attr); if (evsel == NULL) return -ENOMEM; - perf_evlist__add(evlist, evsel); + evlist__add(evlist, evsel); ids = event->header.size; ids -= (void *)&event->attr.id - (void *)event; @@ -4047,14 +4050,14 @@ int perf_event__process_attr(struct perf_tool *tool __maybe_unused, int perf_event__process_event_update(struct perf_tool *tool __maybe_unused, union perf_event *event, - struct perf_evlist **pevlist) + struct evlist **pevlist) { struct event_update_event *ev = &event->event_update; struct event_update_event_scale *ev_scale; struct event_update_event_cpus *ev_cpus; - struct perf_evlist *evlist; - struct perf_evsel *evsel; - struct cpu_map *map; + struct evlist *evlist; + struct evsel *evsel; + struct perf_cpu_map *map; if (!pevlist || *pevlist == NULL) return -EINVAL; @@ -4081,7 +4084,7 @@ int perf_event__process_event_update(struct perf_tool *tool __maybe_unused, map = cpu_map__new_data(&ev_cpus->cpus); if (map) - evsel->own_cpus = map; + evsel->core.own_cpus = map; else pr_err("failed to get event_update cpus\n"); default: @@ -4092,7 +4095,7 @@ int perf_event__process_event_update(struct perf_tool *tool __maybe_unused, } int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd, - struct perf_evlist *evlist, + struct evlist *evlist, perf_event__handler_t process) { union perf_event ev; @@ -4112,7 +4115,7 @@ int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd, * - write the tracing data from the temp file * to the pipe */ - tdata = tracing_data_get(&evlist->entries, fd, true); + tdata = tracing_data_get(&evlist->core.entries, fd, true); if (!tdata) return -1; diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index 5b3abe4172e2..3e48ae3c49b1 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -92,12 +92,12 @@ struct perf_header { struct perf_env env; }; -struct perf_evlist; +struct evlist; struct perf_session; int perf_session__read_header(struct perf_session *session); int perf_session__write_header(struct perf_session *session, - struct perf_evlist *evlist, + struct evlist *evlist, int fd, bool at_exit); int perf_header__write_pipe(int fd); @@ -117,11 +117,11 @@ int perf_header__fprintf_info(struct perf_session *s, FILE *fp, bool full); int perf_event__synthesize_features(struct perf_tool *tool, struct perf_session *session, - struct perf_evlist *evlist, + struct evlist *evlist, perf_event__handler_t process); int perf_event__synthesize_extra_attr(struct perf_tool *tool, - struct perf_evlist *evsel_list, + struct evlist *evsel_list, perf_event__handler_t process, bool is_pipe); @@ -132,29 +132,29 @@ int perf_event__synthesize_attr(struct perf_tool *tool, struct perf_event_attr *attr, u32 ids, u64 *id, perf_event__handler_t process); int perf_event__synthesize_attrs(struct perf_tool *tool, - struct perf_evlist *evlist, + struct evlist *evlist, perf_event__handler_t process); int perf_event__synthesize_event_update_unit(struct perf_tool *tool, - struct perf_evsel *evsel, + struct evsel *evsel, perf_event__handler_t process); int perf_event__synthesize_event_update_scale(struct perf_tool *tool, - struct perf_evsel *evsel, + struct evsel *evsel, perf_event__handler_t process); int perf_event__synthesize_event_update_name(struct perf_tool *tool, - struct perf_evsel *evsel, + struct evsel *evsel, perf_event__handler_t process); int perf_event__synthesize_event_update_cpus(struct perf_tool *tool, - struct perf_evsel *evsel, + struct evsel *evsel, perf_event__handler_t process); int perf_event__process_attr(struct perf_tool *tool, union perf_event *event, - struct perf_evlist **pevlist); + struct evlist **pevlist); int perf_event__process_event_update(struct perf_tool *tool, union perf_event *event, - struct perf_evlist **pevlist); + struct evlist **pevlist); size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp); int perf_event__synthesize_tracing_data(struct perf_tool *tool, - int fd, struct perf_evlist *evlist, + int fd, struct evlist *evlist, perf_event__handler_t process); int perf_event__process_tracing_data(struct perf_session *session, union perf_event *event); diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index f24fd1954f6c..8efbf58dc3d0 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -816,7 +816,7 @@ static int iter_finish_mem_entry(struct hist_entry_iter *iter, struct addr_location *al __maybe_unused) { - struct perf_evsel *evsel = iter->evsel; + struct evsel *evsel = iter->evsel; struct hists *hists = evsel__hists(evsel); struct hist_entry *he = iter->he; int err = -EINVAL; @@ -886,7 +886,7 @@ static int iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *al) { struct branch_info *bi; - struct perf_evsel *evsel = iter->evsel; + struct evsel *evsel = iter->evsel; struct hists *hists = evsel__hists(evsel); struct perf_sample *sample = iter->sample; struct hist_entry *he = NULL; @@ -938,7 +938,7 @@ iter_prepare_normal_entry(struct hist_entry_iter *iter __maybe_unused, static int iter_add_single_normal_entry(struct hist_entry_iter *iter, struct addr_location *al) { - struct perf_evsel *evsel = iter->evsel; + struct evsel *evsel = iter->evsel; struct perf_sample *sample = iter->sample; struct hist_entry *he; @@ -956,7 +956,7 @@ iter_finish_normal_entry(struct hist_entry_iter *iter, struct addr_location *al __maybe_unused) { struct hist_entry *he = iter->he; - struct perf_evsel *evsel = iter->evsel; + struct evsel *evsel = iter->evsel; struct perf_sample *sample = iter->sample; if (he == NULL) @@ -996,7 +996,7 @@ static int iter_add_single_cumulative_entry(struct hist_entry_iter *iter, struct addr_location *al) { - struct perf_evsel *evsel = iter->evsel; + struct evsel *evsel = iter->evsel; struct hists *hists = evsel__hists(evsel); struct perf_sample *sample = iter->sample; struct hist_entry **he_cache = iter->priv; @@ -1041,7 +1041,7 @@ static int iter_add_next_cumulative_entry(struct hist_entry_iter *iter, struct addr_location *al) { - struct perf_evsel *evsel = iter->evsel; + struct evsel *evsel = iter->evsel; struct perf_sample *sample = iter->sample; struct hist_entry **he_cache = iter->priv; struct hist_entry *he; @@ -1873,7 +1873,7 @@ static void output_resort(struct hists *hists, struct ui_progress *prog, } } -void perf_evsel__output_resort_cb(struct perf_evsel *evsel, struct ui_progress *prog, +void perf_evsel__output_resort_cb(struct evsel *evsel, struct ui_progress *prog, hists__resort_cb_t cb, void *cb_arg) { bool use_callchain; @@ -1888,7 +1888,7 @@ void perf_evsel__output_resort_cb(struct perf_evsel *evsel, struct ui_progress * output_resort(evsel__hists(evsel), prog, use_callchain, cb, cb_arg); } -void perf_evsel__output_resort(struct perf_evsel *evsel, struct ui_progress *prog) +void perf_evsel__output_resort(struct evsel *evsel, struct ui_progress *prog) { return perf_evsel__output_resort_cb(evsel, prog, NULL, NULL); } @@ -2436,7 +2436,7 @@ void hists__match(struct hists *leader, struct hists *other) { struct rb_root_cached *root; struct rb_node *nd; - struct hist_entry *pos, *pair; + struct hist_entry *pos, *pair, *pos_pair, *tmp_pair; if (symbol_conf.report_hierarchy) { /* hierarchy report always collapses entries */ @@ -2453,8 +2453,24 @@ void hists__match(struct hists *leader, struct hists *other) pos = rb_entry(nd, struct hist_entry, rb_node_in); pair = hists__find_entry(other, pos); - if (pair) + if (pair && list_empty(&pair->pairs.node)) { + list_for_each_entry_safe(pos_pair, tmp_pair, &pos->pairs.head, pairs.node) { + if (pos_pair->hists == other) { + /* + * XXX maybe decayed entries can appear + * here? but then we would have use + * after free, as decayed entries are + * freed see hists__delete_entry + */ + BUG_ON(!pos_pair->dummy); + list_del_init(&pos_pair->pairs.node); + hist_entry__delete(pos_pair); + break; + } + } + hist_entry__add_pair(pair, pos); + } } } @@ -2573,9 +2589,9 @@ void hist__account_cycles(struct branch_stack *bs, struct addr_location *al, } } -size_t perf_evlist__fprintf_nr_events(struct perf_evlist *evlist, FILE *fp) +size_t perf_evlist__fprintf_nr_events(struct evlist *evlist, FILE *fp) { - struct perf_evsel *pos; + struct evsel *pos; size_t ret = 0; evlist__for_each_entry(evlist, pos) { @@ -2602,7 +2618,7 @@ int __hists__scnprintf_title(struct hists *hists, char *bf, size_t size, bool sh 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); + struct 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); @@ -2615,7 +2631,7 @@ int __hists__scnprintf_title(struct hists *hists, char *bf, size_t size, bool sh } if (perf_evsel__is_group_event(evsel)) { - struct perf_evsel *pos; + struct evsel *pos; perf_evsel__group_desc(evsel, buf, buflen); ev_name = buf; @@ -2638,12 +2654,12 @@ int __hists__scnprintf_title(struct hists *hists, char *bf, size_t size, bool sh enable_ref = true; if (show_freq) - scnprintf(sample_freq_str, sizeof(sample_freq_str), " %d Hz,", evsel->attr.sample_freq); + scnprintf(sample_freq_str, sizeof(sample_freq_str), " %d Hz,", evsel->core.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" : "", + nr_samples, unit, evsel->core.nr_members > 1 ? "s" : "", ev_name, sample_freq_str, enable_ref ? ref : " ", nr_events); @@ -2731,7 +2747,7 @@ static void hists__delete_all_entries(struct hists *hists) hists__delete_remaining_entries(&hists->entries_collapsed); } -static void hists_evsel__exit(struct perf_evsel *evsel) +static void hists_evsel__exit(struct evsel *evsel) { struct hists *hists = evsel__hists(evsel); struct perf_hpp_fmt *fmt, *pos; @@ -2749,7 +2765,7 @@ static void hists_evsel__exit(struct perf_evsel *evsel) } } -static int hists_evsel__init(struct perf_evsel *evsel) +static int hists_evsel__init(struct evsel *evsel) { struct hists *hists = evsel__hists(evsel); diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 24635f36148d..83d5fc15429c 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -116,7 +116,7 @@ struct hist_entry_iter { bool hide_unresolved; - struct perf_evsel *evsel; + struct evsel *evsel; struct perf_sample *sample; struct hist_entry *he; struct symbol *parent; @@ -171,9 +171,9 @@ void hist_entry__delete(struct hist_entry *he); typedef int (*hists__resort_cb_t)(struct hist_entry *he, void *arg); -void perf_evsel__output_resort_cb(struct perf_evsel *evsel, struct ui_progress *prog, +void perf_evsel__output_resort_cb(struct evsel *evsel, struct ui_progress *prog, hists__resort_cb_t cb, void *cb_arg); -void perf_evsel__output_resort(struct perf_evsel *evsel, struct ui_progress *prog); +void perf_evsel__output_resort(struct evsel *evsel, struct ui_progress *prog); void hists__output_resort(struct hists *hists, struct ui_progress *prog); void hists__output_resort_cb(struct hists *hists, struct ui_progress *prog, hists__resort_cb_t cb); @@ -196,7 +196,7 @@ size_t events_stats__fprintf(struct events_stats *stats, FILE *fp); size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, int max_cols, float min_pcnt, FILE *fp, bool ignore_callchains); -size_t perf_evlist__fprintf_nr_events(struct perf_evlist *evlist, FILE *fp); +size_t perf_evlist__fprintf_nr_events(struct evlist *evlist, FILE *fp); void hists__filter_by_dso(struct hists *hists); void hists__filter_by_thread(struct hists *hists); @@ -219,17 +219,17 @@ void hists__match(struct hists *leader, struct hists *other); int hists__link(struct hists *leader, struct hists *other); struct hists_evsel { - struct perf_evsel evsel; + struct evsel evsel; struct hists hists; }; -static inline struct perf_evsel *hists_to_evsel(struct hists *hists) +static inline struct evsel *hists_to_evsel(struct hists *hists) { struct hists_evsel *hevsel = container_of(hists, struct hists_evsel, hists); return &hevsel->evsel; } -static inline struct hists *evsel__hists(struct perf_evsel *evsel) +static inline struct hists *evsel__hists(struct evsel *evsel) { struct hists_evsel *hevsel = (struct hists_evsel *)evsel; return &hevsel->hists; @@ -367,7 +367,7 @@ void perf_hpp__setup_output_field(struct perf_hpp_list *list); void perf_hpp__reset_output_field(struct perf_hpp_list *list); void perf_hpp__append_sort_keys(struct perf_hpp_list *list); int perf_hpp__setup_hists_formats(struct perf_hpp_list *list, - struct perf_evlist *evlist); + struct evlist *evlist); bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format); @@ -432,7 +432,7 @@ static inline size_t perf_hpp__color_overhead(void) : 0; } -struct perf_evlist; +struct evlist; struct hist_browser_timer { void (*timer)(void *arg); @@ -453,30 +453,30 @@ enum rstype { #include "../ui/keysyms.h" void attr_to_script(char *buf, struct perf_event_attr *attr); -int map_symbol__tui_annotate(struct map_symbol *ms, struct perf_evsel *evsel, +int map_symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel, struct hist_browser_timer *hbt, struct annotation_options *annotation_opts); -int hist_entry__tui_annotate(struct hist_entry *he, struct perf_evsel *evsel, +int hist_entry__tui_annotate(struct hist_entry *he, struct evsel *evsel, struct hist_browser_timer *hbt, struct annotation_options *annotation_opts); -int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help, +int perf_evlist__tui_browse_hists(struct evlist *evlist, const char *help, struct hist_browser_timer *hbt, float min_pcnt, struct perf_env *env, bool warn_lost_event, struct annotation_options *annotation_options); -int script_browse(const char *script_opt, struct perf_evsel *evsel); +int script_browse(const char *script_opt, struct evsel *evsel); void run_script(char *cmd); int res_sample_browse(struct res_sample *res_samples, int num_res, - struct perf_evsel *evsel, enum rstype rstype); + struct evsel *evsel, enum rstype rstype); void res_sample_init(void); #else static inline -int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __maybe_unused, +int perf_evlist__tui_browse_hists(struct evlist *evlist __maybe_unused, const char *help __maybe_unused, struct hist_browser_timer *hbt __maybe_unused, float min_pcnt __maybe_unused, @@ -487,7 +487,7 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __maybe_unused, return 0; } static inline int map_symbol__tui_annotate(struct map_symbol *ms __maybe_unused, - struct perf_evsel *evsel __maybe_unused, + struct evsel *evsel __maybe_unused, struct hist_browser_timer *hbt __maybe_unused, struct annotation_options *annotation_options __maybe_unused) { @@ -495,7 +495,7 @@ static inline int map_symbol__tui_annotate(struct map_symbol *ms __maybe_unused, } static inline int hist_entry__tui_annotate(struct hist_entry *he __maybe_unused, - struct perf_evsel *evsel __maybe_unused, + struct evsel *evsel __maybe_unused, struct hist_browser_timer *hbt __maybe_unused, struct annotation_options *annotation_opts __maybe_unused) { @@ -503,14 +503,14 @@ static inline int hist_entry__tui_annotate(struct hist_entry *he __maybe_unused, } static inline int script_browse(const char *script_opt __maybe_unused, - struct perf_evsel *evsel __maybe_unused) + struct evsel *evsel __maybe_unused) { return 0; } static inline int res_sample_browse(struct res_sample *res_samples __maybe_unused, int num_res __maybe_unused, - struct perf_evsel *evsel __maybe_unused, + struct evsel *evsel __maybe_unused, enum rstype rstype __maybe_unused) { return 0; diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c index 5560e95afdda..7eb9e6dc27dd 100644 --- a/tools/perf/util/intel-bts.c +++ b/tools/perf/util/intel-bts.c @@ -760,15 +760,15 @@ static int intel_bts_synth_event(struct perf_session *session, static int intel_bts_synth_events(struct intel_bts *bts, struct perf_session *session) { - struct perf_evlist *evlist = session->evlist; - struct perf_evsel *evsel; + struct evlist *evlist = session->evlist; + struct evsel *evsel; struct perf_event_attr attr; bool found = false; u64 id; int err; evlist__for_each_entry(evlist, evsel) { - if (evsel->attr.type == bts->pmu_type && evsel->ids) { + if (evsel->core.attr.type == bts->pmu_type && evsel->ids) { found = true; break; } @@ -782,18 +782,18 @@ static int intel_bts_synth_events(struct intel_bts *bts, memset(&attr, 0, sizeof(struct perf_event_attr)); attr.size = sizeof(struct perf_event_attr); attr.type = PERF_TYPE_HARDWARE; - attr.sample_type = evsel->attr.sample_type & PERF_SAMPLE_MASK; + attr.sample_type = evsel->core.attr.sample_type & PERF_SAMPLE_MASK; attr.sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_PERIOD; attr.sample_type &= ~(u64)PERF_SAMPLE_TIME; attr.sample_type &= ~(u64)PERF_SAMPLE_CPU; - attr.exclude_user = evsel->attr.exclude_user; - attr.exclude_kernel = evsel->attr.exclude_kernel; - attr.exclude_hv = evsel->attr.exclude_hv; - attr.exclude_host = evsel->attr.exclude_host; - attr.exclude_guest = evsel->attr.exclude_guest; - attr.sample_id_all = evsel->attr.sample_id_all; - attr.read_format = evsel->attr.read_format; + attr.exclude_user = evsel->core.attr.exclude_user; + attr.exclude_kernel = evsel->core.attr.exclude_kernel; + attr.exclude_hv = evsel->core.attr.exclude_hv; + attr.exclude_host = evsel->core.attr.exclude_host; + attr.exclude_guest = evsel->core.attr.exclude_guest; + attr.sample_id_all = evsel->core.attr.sample_id_all; + attr.read_format = evsel->core.attr.read_format; id = evsel->id[0] + 1000000000; if (!id) diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index df061599fef4..ea504fa9b623 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -56,7 +56,7 @@ struct intel_pt { u32 auxtrace_type; struct perf_session *session; struct machine *machine; - struct perf_evsel *switch_evsel; + struct evsel *switch_evsel; struct thread *unknown_thread; bool timeless_decoding; bool sampling_mode; @@ -104,7 +104,7 @@ struct intel_pt { u64 cbr_id; bool sample_pebs; - struct perf_evsel *pebs_evsel; + struct evsel *pebs_evsel; u64 tsc_bit; u64 mtc_bit; @@ -723,11 +723,11 @@ static bool intel_pt_get_config(struct intel_pt *pt, static bool intel_pt_exclude_kernel(struct intel_pt *pt) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(pt->session->evlist, evsel) { - if (intel_pt_get_config(pt, &evsel->attr, NULL) && - !evsel->attr.exclude_kernel) + if (intel_pt_get_config(pt, &evsel->core.attr, NULL) && + !evsel->core.attr.exclude_kernel) return false; } return true; @@ -735,14 +735,14 @@ static bool intel_pt_exclude_kernel(struct intel_pt *pt) static bool intel_pt_return_compression(struct intel_pt *pt) { - struct perf_evsel *evsel; + struct evsel *evsel; u64 config; if (!pt->noretcomp_bit) return true; evlist__for_each_entry(pt->session->evlist, evsel) { - if (intel_pt_get_config(pt, &evsel->attr, &config) && + if (intel_pt_get_config(pt, &evsel->core.attr, &config) && (config & pt->noretcomp_bit)) return false; } @@ -751,11 +751,11 @@ static bool intel_pt_return_compression(struct intel_pt *pt) static bool intel_pt_branch_enable(struct intel_pt *pt) { - struct perf_evsel *evsel; + struct evsel *evsel; u64 config; evlist__for_each_entry(pt->session->evlist, evsel) { - if (intel_pt_get_config(pt, &evsel->attr, &config) && + if (intel_pt_get_config(pt, &evsel->core.attr, &config) && (config & 1) && !(config & 0x2000)) return false; } @@ -764,7 +764,7 @@ static bool intel_pt_branch_enable(struct intel_pt *pt) static unsigned int intel_pt_mtc_period(struct intel_pt *pt) { - struct perf_evsel *evsel; + struct evsel *evsel; unsigned int shift; u64 config; @@ -775,7 +775,7 @@ static unsigned int intel_pt_mtc_period(struct intel_pt *pt) config >>= 1; evlist__for_each_entry(pt->session->evlist, evsel) { - if (intel_pt_get_config(pt, &evsel->attr, &config)) + if (intel_pt_get_config(pt, &evsel->core.attr, &config)) return (config & pt->mtc_freq_bits) >> shift; } return 0; @@ -783,7 +783,7 @@ static unsigned int intel_pt_mtc_period(struct intel_pt *pt) static bool intel_pt_timeless_decoding(struct intel_pt *pt) { - struct perf_evsel *evsel; + struct evsel *evsel; bool timeless_decoding = true; u64 config; @@ -791,9 +791,9 @@ static bool intel_pt_timeless_decoding(struct intel_pt *pt) return true; evlist__for_each_entry(pt->session->evlist, evsel) { - if (!(evsel->attr.sample_type & PERF_SAMPLE_TIME)) + if (!(evsel->core.attr.sample_type & PERF_SAMPLE_TIME)) return true; - if (intel_pt_get_config(pt, &evsel->attr, &config)) { + if (intel_pt_get_config(pt, &evsel->core.attr, &config)) { if (config & pt->tsc_bit) timeless_decoding = false; else @@ -805,11 +805,11 @@ static bool intel_pt_timeless_decoding(struct intel_pt *pt) static bool intel_pt_tracing_kernel(struct intel_pt *pt) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(pt->session->evlist, evsel) { - if (intel_pt_get_config(pt, &evsel->attr, NULL) && - !evsel->attr.exclude_kernel) + if (intel_pt_get_config(pt, &evsel->core.attr, NULL) && + !evsel->core.attr.exclude_kernel) return true; } return false; @@ -817,7 +817,7 @@ static bool intel_pt_tracing_kernel(struct intel_pt *pt) static bool intel_pt_have_tsc(struct intel_pt *pt) { - struct perf_evsel *evsel; + struct evsel *evsel; bool have_tsc = false; u64 config; @@ -825,7 +825,7 @@ static bool intel_pt_have_tsc(struct intel_pt *pt) return false; evlist__for_each_entry(pt->session->evlist, evsel) { - if (intel_pt_get_config(pt, &evsel->attr, &config)) { + if (intel_pt_get_config(pt, &evsel->core.attr, &config)) { if (config & pt->tsc_bit) have_tsc = true; else @@ -1702,8 +1702,8 @@ static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq) struct perf_sample sample = { .ip = 0, }; union perf_event *event = ptq->event_buf; struct intel_pt *pt = ptq->pt; - struct perf_evsel *evsel = pt->pebs_evsel; - u64 sample_type = evsel->attr.sample_type; + struct evsel *evsel = pt->pebs_evsel; + u64 sample_type = evsel->core.attr.sample_type; u64 id = evsel->id[0]; u8 cpumode; @@ -1715,8 +1715,8 @@ static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq) sample.id = id; sample.stream_id = id; - if (!evsel->attr.freq) - sample.period = evsel->attr.sample_period; + if (!evsel->core.attr.freq) + sample.period = evsel->core.attr.sample_period; /* No support for non-zero CS base */ if (items->has_ip) @@ -1757,7 +1757,7 @@ static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq) if (sample_type & PERF_SAMPLE_REGS_INTR && items->mask[INTEL_PT_GP_REGS_POS]) { u64 regs[sizeof(sample.intr_regs.mask)]; - u64 regs_mask = evsel->attr.sample_regs_intr; + u64 regs_mask = evsel->core.attr.sample_regs_intr; u64 *pos; sample.intr_regs.abi = items->is_32_bit ? @@ -2401,7 +2401,7 @@ static int intel_pt_sync_switch(struct intel_pt *pt, int cpu, pid_t tid, static int intel_pt_process_switch(struct intel_pt *pt, struct perf_sample *sample) { - struct perf_evsel *evsel; + struct evsel *evsel; pid_t tid; int cpu, ret; @@ -2713,10 +2713,10 @@ static int intel_pt_synth_event(struct perf_session *session, const char *name, return err; } -static void intel_pt_set_event_name(struct perf_evlist *evlist, u64 id, +static void intel_pt_set_event_name(struct evlist *evlist, u64 id, const char *name) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { if (evsel->id && evsel->id[0] == id) { @@ -2728,13 +2728,13 @@ static void intel_pt_set_event_name(struct perf_evlist *evlist, u64 id, } } -static struct perf_evsel *intel_pt_evsel(struct intel_pt *pt, - struct perf_evlist *evlist) +static struct evsel *intel_pt_evsel(struct intel_pt *pt, + struct evlist *evlist) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { - if (evsel->attr.type == pt->pmu_type && evsel->ids) + if (evsel->core.attr.type == pt->pmu_type && evsel->ids) return evsel; } @@ -2744,8 +2744,8 @@ static struct perf_evsel *intel_pt_evsel(struct intel_pt *pt, static int intel_pt_synth_events(struct intel_pt *pt, struct perf_session *session) { - struct perf_evlist *evlist = session->evlist; - struct perf_evsel *evsel = intel_pt_evsel(pt, evlist); + struct evlist *evlist = session->evlist; + struct evsel *evsel = intel_pt_evsel(pt, evlist); struct perf_event_attr attr; u64 id; int err; @@ -2758,7 +2758,7 @@ static int intel_pt_synth_events(struct intel_pt *pt, memset(&attr, 0, sizeof(struct perf_event_attr)); attr.size = sizeof(struct perf_event_attr); attr.type = PERF_TYPE_HARDWARE; - attr.sample_type = evsel->attr.sample_type & PERF_SAMPLE_MASK; + attr.sample_type = evsel->core.attr.sample_type & PERF_SAMPLE_MASK; attr.sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_PERIOD; if (pt->timeless_decoding) @@ -2767,13 +2767,13 @@ static int intel_pt_synth_events(struct intel_pt *pt, attr.sample_type |= PERF_SAMPLE_TIME; if (!pt->per_cpu_mmaps) attr.sample_type &= ~(u64)PERF_SAMPLE_CPU; - attr.exclude_user = evsel->attr.exclude_user; - attr.exclude_kernel = evsel->attr.exclude_kernel; - attr.exclude_hv = evsel->attr.exclude_hv; - attr.exclude_host = evsel->attr.exclude_host; - attr.exclude_guest = evsel->attr.exclude_guest; - attr.sample_id_all = evsel->attr.sample_id_all; - attr.read_format = evsel->attr.read_format; + attr.exclude_user = evsel->core.attr.exclude_user; + attr.exclude_kernel = evsel->core.attr.exclude_kernel; + attr.exclude_hv = evsel->core.attr.exclude_hv; + attr.exclude_host = evsel->core.attr.exclude_host; + attr.exclude_guest = evsel->core.attr.exclude_guest; + attr.sample_id_all = evsel->core.attr.sample_id_all; + attr.read_format = evsel->core.attr.read_format; id = evsel->id[0] + 1000000000; if (!id) @@ -2857,7 +2857,7 @@ static int intel_pt_synth_events(struct intel_pt *pt, id += 1; } - if (pt->synth_opts.pwr_events && (evsel->attr.config & 0x10)) { + if (pt->synth_opts.pwr_events && (evsel->core.attr.config & 0x10)) { attr.config = PERF_SYNTH_INTEL_MWAIT; err = intel_pt_synth_event(session, "mwait", &attr, id); if (err) @@ -2894,9 +2894,25 @@ static int intel_pt_synth_events(struct intel_pt *pt, return 0; } -static struct perf_evsel *intel_pt_find_sched_switch(struct perf_evlist *evlist) +static void intel_pt_setup_pebs_events(struct intel_pt *pt) { - struct perf_evsel *evsel; + struct evsel *evsel; + + if (!pt->synth_opts.other_events) + return; + + evlist__for_each_entry(pt->session->evlist, evsel) { + if (evsel->core.attr.aux_output && evsel->id) { + pt->sample_pebs = true; + pt->pebs_evsel = evsel; + return; + } + } +} + +static struct evsel *intel_pt_find_sched_switch(struct evlist *evlist) +{ + struct evsel *evsel; evlist__for_each_entry_reverse(evlist, evsel) { const char *name = perf_evsel__name(evsel); @@ -2908,12 +2924,12 @@ static struct perf_evsel *intel_pt_find_sched_switch(struct perf_evlist *evlist) return NULL; } -static bool intel_pt_find_switch(struct perf_evlist *evlist) +static bool intel_pt_find_switch(struct evlist *evlist) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { - if (evsel->attr.context_switch) + if (evsel->core.attr.context_switch) return true; } @@ -3263,6 +3279,8 @@ int intel_pt_process_auxtrace_info(union perf_event *event, if (err) goto err_delete_thread; + intel_pt_setup_pebs_events(pt); + err = auxtrace_queues__process_index(&pt->queues, session); if (err) goto err_delete_thread; diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c index 18c34f0c1966..bbeac4f66402 100644 --- a/tools/perf/util/jitdump.c +++ b/tools/perf/util/jitdump.c @@ -118,13 +118,13 @@ jit_close(struct jit_buf_desc *jd) static int jit_validate_events(struct perf_session *session) { - struct perf_evsel *evsel; + struct evsel *evsel; /* * check that all events use CLOCK_MONOTONIC */ evlist__for_each_entry(session->evlist, evsel) { - if (evsel->attr.use_clockid == 0 || evsel->attr.clockid != CLOCK_MONOTONIC) + if (evsel->core.attr.use_clockid == 0 || evsel->core.attr.clockid != CLOCK_MONOTONIC) return -1; } return 0; @@ -758,7 +758,7 @@ jit_process(struct perf_session *session, pid_t pid, u64 *nbytes) { - struct perf_evsel *first; + struct evsel *first; struct jit_buf_desc jd; int ret; @@ -779,7 +779,7 @@ jit_process(struct perf_session *session, * perf sets the same sample type to all events as of now */ first = perf_evlist__first(session->evlist); - jd.sample_type = first->attr.sample_type; + jd.sample_type = first->core.attr.sample_type; *nbytes = 0; diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h index 1403dec189b4..a09c495f866b 100644 --- a/tools/perf/util/kvm-stat.h +++ b/tools/perf/util/kvm-stat.h @@ -6,8 +6,8 @@ #include "tool.h" #include "stat.h" -struct perf_evsel; -struct perf_evlist; +struct evsel; +struct evlist; struct perf_session; struct event_key { @@ -45,17 +45,17 @@ struct kvm_event_key { struct perf_kvm_stat; struct child_event_ops { - void (*get_key)(struct perf_evsel *evsel, + void (*get_key)(struct evsel *evsel, struct perf_sample *sample, struct event_key *key); const char *name; }; struct kvm_events_ops { - bool (*is_begin_event)(struct perf_evsel *evsel, + bool (*is_begin_event)(struct evsel *evsel, struct perf_sample *sample, struct event_key *key); - bool (*is_end_event)(struct perf_evsel *evsel, + bool (*is_end_event)(struct evsel *evsel, struct perf_sample *sample, struct event_key *key); struct child_event_ops *child_ops; void (*decode_key)(struct perf_kvm_stat *kvm, struct event_key *key, @@ -74,7 +74,7 @@ struct exit_reasons_table { struct perf_kvm_stat { struct perf_tool tool; struct record_opts opts; - struct perf_evlist *evlist; + struct evlist *evlist; struct perf_session *session; const char *file_name; @@ -109,21 +109,21 @@ struct kvm_reg_events_ops { struct kvm_events_ops *ops; }; -void exit_event_get_key(struct perf_evsel *evsel, +void exit_event_get_key(struct evsel *evsel, struct perf_sample *sample, struct event_key *key); -bool exit_event_begin(struct perf_evsel *evsel, +bool exit_event_begin(struct evsel *evsel, struct perf_sample *sample, struct event_key *key); -bool exit_event_end(struct perf_evsel *evsel, +bool exit_event_end(struct evsel *evsel, struct perf_sample *sample, struct event_key *key); void exit_event_decode_key(struct perf_kvm_stat *kvm, struct event_key *key, char *decode); -bool kvm_exit_event(struct perf_evsel *evsel); -bool kvm_entry_event(struct perf_evsel *evsel); +bool kvm_exit_event(struct evsel *evsel); +bool kvm_entry_event(struct evsel *evsel); int setup_kvm_events_tp(struct perf_kvm_stat *kvm); #define define_exit_reasons_table(name, symbols) \ diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 83b2fbbeeb90..5734460fc89e 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -2288,7 +2288,7 @@ static int find_prev_cpumode(struct ip_callchain *chain, struct thread *thread, static int thread__resolve_callchain_sample(struct thread *thread, struct callchain_cursor *cursor, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample, struct symbol **parent, struct addr_location *root_al, @@ -2494,13 +2494,13 @@ static int unwind_entry(struct unwind_entry *entry, void *arg) static int thread__resolve_callchain_unwind(struct thread *thread, struct callchain_cursor *cursor, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample, int max_stack) { /* Can we do dwarf post unwind? */ - if (!((evsel->attr.sample_type & PERF_SAMPLE_REGS_USER) && - (evsel->attr.sample_type & PERF_SAMPLE_STACK_USER))) + if (!((evsel->core.attr.sample_type & PERF_SAMPLE_REGS_USER) && + (evsel->core.attr.sample_type & PERF_SAMPLE_STACK_USER))) return 0; /* Bail out if nothing was captured. */ @@ -2514,7 +2514,7 @@ static int thread__resolve_callchain_unwind(struct thread *thread, int thread__resolve_callchain(struct thread *thread, struct callchain_cursor *cursor, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample, struct symbol **parent, struct addr_location *root_al, @@ -2600,7 +2600,7 @@ int machines__for_each_thread(struct machines *machines, } int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool, - struct target *target, struct thread_map *threads, + struct target *target, struct perf_thread_map *threads, perf_event__handler_t process, bool data_mmap, unsigned int nr_threads_synthesize) { diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index 7aa38da26427..8b9d7157276d 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -11,7 +11,7 @@ struct addr_location; struct branch_stack; -struct perf_evsel; +struct evsel; struct perf_sample; struct symbol; struct thread; @@ -175,7 +175,7 @@ struct callchain_cursor; int thread__resolve_callchain(struct thread *thread, struct callchain_cursor *cursor, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample, struct symbol **parent, struct addr_location *root_al, @@ -251,12 +251,12 @@ int machines__for_each_thread(struct machines *machines, void *priv); int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool, - struct target *target, struct thread_map *threads, + struct target *target, struct perf_thread_map *threads, perf_event__handler_t process, bool data_mmap, unsigned int nr_threads_synthesize); static inline int machine__synthesize_threads(struct machine *machine, struct target *target, - struct thread_map *threads, bool data_mmap, + struct perf_thread_map *threads, bool data_mmap, unsigned int nr_threads_synthesize) { return __machine__synthesize_threads(machine, NULL, target, threads, diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 668410b1d426..27b7b102e4a2 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -636,7 +636,7 @@ bool map_groups__empty(struct map_groups *mg) struct map_groups *map_groups__new(struct machine *machine) { - struct map_groups *mg = malloc(sizeof(*mg)); + struct map_groups *mg = zalloc(sizeof(*mg)); if (mg != NULL) map_groups__init(mg, machine); @@ -647,6 +647,7 @@ struct map_groups *map_groups__new(struct machine *machine) void map_groups__delete(struct map_groups *mg) { map_groups__exit(mg); + unwind__finish_access(mg); free(mg); } @@ -887,7 +888,7 @@ int map_groups__clone(struct thread *thread, struct map_groups *parent) if (new == NULL) goto out_unlock; - err = unwind__prepare_access(thread, new, NULL); + err = unwind__prepare_access(mg, new, NULL); if (err) goto out_unlock; diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index dc93787c74f0..c3614195ddc7 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -16,7 +16,7 @@ struct ip_callchain; struct ref_reloc_sym; struct map_groups; struct machine; -struct perf_evsel; +struct evsel; struct map { union { diff --git a/tools/perf/util/map_groups.h b/tools/perf/util/map_groups.h index 5f25efa6d6bc..77252e14008f 100644 --- a/tools/perf/util/map_groups.h +++ b/tools/perf/util/map_groups.h @@ -31,6 +31,10 @@ struct map_groups { struct maps maps; struct machine *machine; refcount_t refcnt; +#ifdef HAVE_LIBUNWIND_SUPPORT + void *addr_space; + struct unwind_libunwind_ops *unwind_libunwind_ops; +#endif }; #define KMAP_NAME_LEN 256 diff --git a/tools/perf/util/mem2node.c b/tools/perf/util/mem2node.c index cacc2fc4dcbd..14fb9e72aeeb 100644 --- a/tools/perf/util/mem2node.c +++ b/tools/perf/util/mem2node.c @@ -2,6 +2,7 @@ #include <inttypes.h> #include <linux/bitmap.h> #include <linux/zalloc.h> +#include "debug.h" #include "mem2node.h" struct phys_entry { diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index 416a9015405e..aaf55444f81b 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -7,21 +7,22 @@ #include "metricgroup.h" #include "evlist.h" +#include "evsel.h" #include "strbuf.h" #include "pmu.h" #include "expr.h" #include "rblist.h" #include <string.h> -#include <stdbool.h> #include <errno.h> #include "pmu-events/pmu-events.h" #include "strlist.h" #include <assert.h> #include <linux/ctype.h> #include <linux/zalloc.h> +#include <subcmd/parse-options.h> struct metric_event *metricgroup__lookup(struct rblist *metric_events, - struct perf_evsel *evsel, + struct evsel *evsel, bool create) { struct rb_node *nd; @@ -86,10 +87,10 @@ struct egroup { const char *metric_expr; }; -static bool record_evsel(int *ind, struct perf_evsel **start, +static bool record_evsel(int *ind, struct evsel **start, int idnum, - struct perf_evsel **metric_events, - struct perf_evsel *ev) + struct evsel **metric_events, + struct evsel *ev) { metric_events[*ind] = ev; if (*ind == 0) @@ -101,12 +102,12 @@ static bool record_evsel(int *ind, struct perf_evsel **start, return false; } -static struct perf_evsel *find_evsel_group(struct perf_evlist *perf_evlist, - const char **ids, - int idnum, - struct perf_evsel **metric_events) +static struct evsel *find_evsel_group(struct evlist *perf_evlist, + const char **ids, + int idnum, + struct evsel **metric_events) { - struct perf_evsel *ev, *start = NULL; + struct evsel *ev, *start = NULL; int ind = 0; evlist__for_each_entry (perf_evlist, ev) { @@ -140,7 +141,7 @@ static struct perf_evsel *find_evsel_group(struct perf_evlist *perf_evlist, } static int metricgroup__setup_events(struct list_head *groups, - struct perf_evlist *perf_evlist, + struct evlist *perf_evlist, struct rblist *metric_events_list) { struct metric_event *me; @@ -148,10 +149,10 @@ static int metricgroup__setup_events(struct list_head *groups, int i = 0; int ret = 0; struct egroup *eg; - struct perf_evsel *evsel; + struct evsel *evsel; list_for_each_entry (eg, groups, nd) { - struct perf_evsel **metric_events; + struct evsel **metric_events; metric_events = calloc(sizeof(void *), eg->idnum + 1); if (!metric_events) { @@ -502,7 +503,7 @@ int metricgroup__parse_groups(const struct option *opt, struct rblist *metric_events) { struct parse_events_error parse_error; - struct perf_evlist *perf_evlist = *(struct perf_evlist **)opt->value; + struct evlist *perf_evlist = *(struct evlist **)opt->value; struct strbuf extra_events; LIST_HEAD(group_list); int ret; diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h index 5c52097a5c63..e5092f6404ae 100644 --- a/tools/perf/util/metricgroup.h +++ b/tools/perf/util/metricgroup.h @@ -1,15 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0-only #ifndef METRICGROUP_H #define METRICGROUP_H 1 -#include "linux/list.h" -#include "rblist.h" -#include <subcmd/parse-options.h> -#include "evlist.h" -#include "strbuf.h" +#include <linux/list.h> +#include <linux/rbtree.h> +#include <stdbool.h> + +struct evsel; +struct option; +struct rblist; struct metric_event { struct rb_node nd; - struct perf_evsel *evsel; + struct evsel *evsel; struct list_head head; /* list of metric_expr */ }; @@ -17,11 +20,11 @@ struct metric_expr { struct list_head nd; const char *metric_expr; const char *metric_name; - struct perf_evsel **metric_events; + struct evsel **metric_events; }; struct metric_event *metricgroup__lookup(struct rblist *metric_events, - struct perf_evsel *evsel, + struct evsel *evsel, bool create); int metricgroup__parse_groups(const struct option *opt, const char *str, diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c index 9f0b6391af33..5f3532e51ec9 100644 --- a/tools/perf/util/mmap.c +++ b/tools/perf/util/mmap.c @@ -150,7 +150,7 @@ void __weak auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp __maybe_u } void __weak auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp __maybe_unused, - struct perf_evlist *evlist __maybe_unused, + struct evlist *evlist __maybe_unused, int idx __maybe_unused, bool per_cpu __maybe_unused) { @@ -325,13 +325,13 @@ void perf_mmap__munmap(struct perf_mmap *map) static void build_node_mask(int node, cpu_set_t *mask) { int c, cpu, nr_cpus; - const struct cpu_map *cpu_map = NULL; + const struct perf_cpu_map *cpu_map = NULL; cpu_map = cpu_map__online(); if (!cpu_map) return; - nr_cpus = cpu_map__nr(cpu_map); + nr_cpus = perf_cpu_map__nr(cpu_map); for (c = 0; c < nr_cpus; c++) { cpu = cpu_map->map[c]; /* map c index to online cpu index */ if (cpu__get_node(cpu) == node) diff --git a/tools/perf/util/parse-branch-options.c b/tools/perf/util/parse-branch-options.c index 726e8d9e8c54..4ed20c833d44 100644 --- a/tools/perf/util/parse-branch-options.c +++ b/tools/perf/util/parse-branch-options.c @@ -30,6 +30,7 @@ static const struct branch_mode branch_modes[] = { BRANCH_OPT("ind_jmp", PERF_SAMPLE_BRANCH_IND_JUMP), BRANCH_OPT("call", PERF_SAMPLE_BRANCH_CALL), BRANCH_OPT("save_type", PERF_SAMPLE_BRANCH_TYPE_SAVE), + BRANCH_OPT("stack", PERF_SAMPLE_BRANCH_CALL_STACK), BRANCH_END }; diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 371ff3aee769..9101568946d2 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -24,6 +24,7 @@ #include "bpf-loader.h" #include "debug.h" #include <api/fs/tracing_path.h> +#include <perf/cpumap.h> #include "parse-events-bison.h" #define YY_EXTRA_TYPE int #include "parse-events-flex.h" @@ -314,16 +315,16 @@ static char *get_config_name(struct list_head *head_terms) return NULL; } -static struct perf_evsel * +static struct evsel * __add_event(struct list_head *list, int *idx, struct perf_event_attr *attr, char *name, struct perf_pmu *pmu, struct list_head *config_terms, bool auto_merge_stats, const char *cpu_list) { - struct perf_evsel *evsel; - struct cpu_map *cpus = pmu ? pmu->cpus : - cpu_list ? cpu_map__new(cpu_list) : NULL; + struct evsel *evsel; + struct perf_cpu_map *cpus = pmu ? pmu->cpus : + cpu_list ? perf_cpu_map__new(cpu_list) : NULL; event_attr_init(attr); @@ -332,8 +333,8 @@ __add_event(struct list_head *list, int *idx, return NULL; (*idx)++; - evsel->cpus = cpu_map__get(cpus); - evsel->own_cpus = cpu_map__get(cpus); + evsel->core.cpus = perf_cpu_map__get(cpus); + evsel->core.own_cpus = perf_cpu_map__get(cpus); evsel->system_wide = pmu ? pmu->is_uncore : false; evsel->auto_merge_stats = auto_merge_stats; @@ -343,7 +344,7 @@ __add_event(struct list_head *list, int *idx, if (config_terms) list_splice(config_terms, &evsel->config_terms); - list_add_tail(&evsel->node, list); + list_add_tail(&evsel->core.node, list); return evsel; } @@ -357,7 +358,7 @@ static int add_event(struct list_head *list, int *idx, static int add_event_tool(struct list_head *list, int *idx, enum perf_tool_event tool_event) { - struct perf_evsel *evsel; + struct evsel *evsel; struct perf_event_attr attr = { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_DUMMY, @@ -510,7 +511,7 @@ static int add_tracepoint(struct list_head *list, int *idx, struct parse_events_error *err, struct list_head *head_config) { - struct perf_evsel *evsel; + struct evsel *evsel; evsel = perf_evsel__newtp_idx(sys_name, evt_name, (*idx)++); if (IS_ERR(evsel)) { @@ -526,7 +527,7 @@ static int add_tracepoint(struct list_head *list, int *idx, list_splice(&config_terms, &evsel->config_terms); } - list_add_tail(&evsel->node, list); + list_add_tail(&evsel->core.node, list); return 0; } @@ -630,15 +631,24 @@ struct __add_bpf_event_param { struct list_head *head_config; }; -static int add_bpf_event(const char *group, const char *event, int fd, +static int add_bpf_event(const char *group, const char *event, int fd, struct bpf_object *obj, void *_param) { LIST_HEAD(new_evsels); struct __add_bpf_event_param *param = _param; struct parse_events_state *parse_state = param->parse_state; struct list_head *list = param->list; - struct perf_evsel *pos; + struct evsel *pos; int err; + /* + * Check if we should add the event, i.e. if it is a TP but starts with a '!', + * then don't add the tracepoint, this will be used for something else, like + * adding to a BPF_MAP_TYPE_PROG_ARRAY. + * + * See tools/perf/examples/bpf/augmented_raw_syscalls.c + */ + if (group[0] == '!') + return 0; pr_debug("add bpf event %s:%s and attach bpf program %d\n", group, event, fd); @@ -647,22 +657,23 @@ static int add_bpf_event(const char *group, const char *event, int fd, event, parse_state->error, param->head_config); if (err) { - struct perf_evsel *evsel, *tmp; + struct evsel *evsel, *tmp; pr_debug("Failed to add BPF event %s:%s\n", group, event); - list_for_each_entry_safe(evsel, tmp, &new_evsels, node) { - list_del_init(&evsel->node); - perf_evsel__delete(evsel); + list_for_each_entry_safe(evsel, tmp, &new_evsels, core.node) { + list_del_init(&evsel->core.node); + evsel__delete(evsel); } return err; } pr_debug("adding %s:%s\n", group, event); - list_for_each_entry(pos, &new_evsels, node) { + list_for_each_entry(pos, &new_evsels, core.node) { pr_debug("adding %s:%s to %p\n", group, event, pos); pos->bpf_fd = fd; + pos->bpf_obj = obj; } list_splice(&new_evsels, list); return 0; @@ -952,6 +963,7 @@ static const char *config_term_names[__PARSE_EVENTS__TERM_TYPE_NR] = { [PARSE_EVENTS__TERM_TYPE_NOOVERWRITE] = "no-overwrite", [PARSE_EVENTS__TERM_TYPE_DRV_CFG] = "driver-config", [PARSE_EVENTS__TERM_TYPE_PERCORE] = "percore", + [PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT] = "aux-output", }; static bool config_term_shrinked; @@ -1072,6 +1084,9 @@ do { \ return -EINVAL; } break; + case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT: + CHECK_TYPE_VAL(NUM); + break; default: err->str = strdup("unknown term"); err->idx = term->err_term; @@ -1122,6 +1137,7 @@ static int config_term_tracepoint(struct perf_event_attr *attr, case PARSE_EVENTS__TERM_TYPE_MAX_EVENTS: case PARSE_EVENTS__TERM_TYPE_OVERWRITE: case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE: + case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT: return config_term_common(attr, term, err); default: if (err) { @@ -1214,6 +1230,9 @@ do { \ ADD_CONFIG_TERM(PERCORE, percore, term->val.num ? true : false); break; + case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT: + ADD_CONFIG_TERM(AUX_OUTPUT, aux_output, term->val.num ? 1 : 0); + break; default: break; } @@ -1296,7 +1315,7 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, struct perf_event_attr attr; struct perf_pmu_info info; struct perf_pmu *pmu; - struct perf_evsel *evsel; + struct evsel *evsel; struct parse_events_error *err = parse_state->error; bool use_uncore_alias; LIST_HEAD(config_terms); @@ -1443,13 +1462,13 @@ static int parse_events__set_leader_for_uncore_aliase(char *name, struct list_head *list, struct parse_events_state *parse_state) { - struct perf_evsel *evsel, *leader; + struct evsel *evsel, *leader; uintptr_t *leaders; bool is_leader = true; int i, nr_pmu = 0, total_members, ret = 0; - leader = list_first_entry(list, struct perf_evsel, node); - evsel = list_last_entry(list, struct perf_evsel, node); + leader = list_first_entry(list, struct evsel, core.node); + evsel = list_last_entry(list, struct evsel, core.node); total_members = evsel->idx - leader->idx + 1; leaders = calloc(total_members, sizeof(uintptr_t)); @@ -1511,13 +1530,13 @@ parse_events__set_leader_for_uncore_aliase(char *name, struct list_head *list, __evlist__for_each_entry(list, evsel) { if (i >= nr_pmu) i = 0; - evsel->leader = (struct perf_evsel *) leaders[i++]; + evsel->leader = (struct evsel *) leaders[i++]; } /* The number of members and group name are same for each group */ for (i = 0; i < nr_pmu; i++) { - evsel = (struct perf_evsel *) leaders[i]; - evsel->nr_members = total_members / nr_pmu; + evsel = (struct evsel *) leaders[i]; + evsel->core.nr_members = total_members / nr_pmu; evsel->group_name = name ? strdup(name) : NULL; } @@ -1534,7 +1553,7 @@ out: void parse_events__set_leader(char *name, struct list_head *list, struct parse_events_state *parse_state) { - struct perf_evsel *leader; + struct evsel *leader; if (list_empty(list)) { WARN_ONCE(true, "WARNING: failed to set leader: empty list"); @@ -1545,7 +1564,7 @@ void parse_events__set_leader(char *name, struct list_head *list, return; __perf_evlist__set_leader(list); - leader = list_entry(list->next, struct perf_evsel, node); + leader = list_entry(list->next, struct evsel, core.node); leader->group_name = name ? strdup(name) : NULL; } @@ -1578,18 +1597,18 @@ struct event_modifier { }; static int get_event_modifier(struct event_modifier *mod, char *str, - struct perf_evsel *evsel) -{ - int eu = evsel ? evsel->attr.exclude_user : 0; - int ek = evsel ? evsel->attr.exclude_kernel : 0; - int eh = evsel ? evsel->attr.exclude_hv : 0; - int eH = evsel ? evsel->attr.exclude_host : 0; - int eG = evsel ? evsel->attr.exclude_guest : 0; - int eI = evsel ? evsel->attr.exclude_idle : 0; - int precise = evsel ? evsel->attr.precise_ip : 0; + struct evsel *evsel) +{ + int eu = evsel ? evsel->core.attr.exclude_user : 0; + int ek = evsel ? evsel->core.attr.exclude_kernel : 0; + int eh = evsel ? evsel->core.attr.exclude_hv : 0; + int eH = evsel ? evsel->core.attr.exclude_host : 0; + int eG = evsel ? evsel->core.attr.exclude_guest : 0; + int eI = evsel ? evsel->core.attr.exclude_idle : 0; + int precise = evsel ? evsel->core.attr.precise_ip : 0; int precise_max = 0; int sample_read = 0; - int pinned = evsel ? evsel->attr.pinned : 0; + int pinned = evsel ? evsel->core.attr.pinned : 0; int exclude = eu | ek | eh; int exclude_GH = evsel ? evsel->exclude_GH : 0; @@ -1691,7 +1710,7 @@ static int check_modifier(char *str) int parse_events__modifier_event(struct list_head *list, char *str, bool add) { - struct perf_evsel *evsel; + struct evsel *evsel; struct event_modifier mod; if (str == NULL) @@ -1707,20 +1726,20 @@ int parse_events__modifier_event(struct list_head *list, char *str, bool add) if (add && get_event_modifier(&mod, str, evsel)) return -EINVAL; - evsel->attr.exclude_user = mod.eu; - evsel->attr.exclude_kernel = mod.ek; - evsel->attr.exclude_hv = mod.eh; - evsel->attr.precise_ip = mod.precise; - evsel->attr.exclude_host = mod.eH; - evsel->attr.exclude_guest = mod.eG; - evsel->attr.exclude_idle = mod.eI; + evsel->core.attr.exclude_user = mod.eu; + evsel->core.attr.exclude_kernel = mod.ek; + evsel->core.attr.exclude_hv = mod.eh; + evsel->core.attr.precise_ip = mod.precise; + evsel->core.attr.exclude_host = mod.eH; + evsel->core.attr.exclude_guest = mod.eG; + evsel->core.attr.exclude_idle = mod.eI; evsel->exclude_GH = mod.exclude_GH; evsel->sample_read = mod.sample_read; evsel->precise_max = mod.precise_max; evsel->weak_group = mod.weak; if (perf_evsel__is_group_leader(evsel)) - evsel->attr.pinned = mod.pinned; + evsel->core.attr.pinned = mod.pinned; } return 0; @@ -1728,7 +1747,7 @@ int parse_events__modifier_event(struct list_head *list, char *str, bool add) int parse_events_name(struct list_head *list, char *name) { - struct perf_evsel *evsel; + struct evsel *evsel; __evlist__for_each_entry(list, evsel) { if (!evsel->name) @@ -1894,12 +1913,12 @@ int parse_events_terms(struct list_head *terms, const char *str) return ret; } -int parse_events(struct perf_evlist *evlist, const char *str, +int parse_events(struct evlist *evlist, const char *str, struct parse_events_error *err) { struct parse_events_state parse_state = { .list = LIST_HEAD_INIT(parse_state.list), - .idx = evlist->nr_entries, + .idx = evlist->core.nr_entries, .error = err, .evlist = evlist, }; @@ -1908,7 +1927,7 @@ int parse_events(struct perf_evlist *evlist, const char *str, ret = parse_events__scanner(str, &parse_state, PE_START_EVENTS); perf_pmu__parse_cleanup(); if (!ret) { - struct perf_evsel *last; + struct evsel *last; if (list_empty(&parse_state.list)) { WARN_ONCE(true, "WARNING: event parser found nothing\n"); @@ -1925,7 +1944,7 @@ int parse_events(struct perf_evlist *evlist, const char *str, /* * There are 2 users - builtin-record and builtin-test objects. - * Both call perf_evlist__delete in case of error, so we dont + * Both call evlist__delete in case of error, so we dont * need to bother. */ return ret; @@ -2003,7 +2022,7 @@ void parse_events_print_error(struct parse_events_error *err, int parse_events_option(const struct option *opt, const char *str, int unset __maybe_unused) { - struct perf_evlist *evlist = *(struct perf_evlist **)opt->value; + struct evlist *evlist = *(struct evlist **)opt->value; struct parse_events_error err = { .idx = 0, }; int ret = parse_events(evlist, str, &err); @@ -2016,12 +2035,12 @@ int parse_events_option(const struct option *opt, const char *str, } static int -foreach_evsel_in_last_glob(struct perf_evlist *evlist, - int (*func)(struct perf_evsel *evsel, +foreach_evsel_in_last_glob(struct evlist *evlist, + int (*func)(struct evsel *evsel, const void *arg), const void *arg) { - struct perf_evsel *last = NULL; + struct evsel *last = NULL; int err; /* @@ -2030,7 +2049,7 @@ foreach_evsel_in_last_glob(struct perf_evlist *evlist, * * So no need to WARN here, let *func do this. */ - if (evlist->nr_entries > 0) + if (evlist->core.nr_entries > 0) last = perf_evlist__last(evlist); do { @@ -2040,15 +2059,15 @@ foreach_evsel_in_last_glob(struct perf_evlist *evlist, if (!last) return 0; - if (last->node.prev == &evlist->entries) + if (last->core.node.prev == &evlist->core.entries) return 0; - last = list_entry(last->node.prev, struct perf_evsel, node); + last = list_entry(last->core.node.prev, struct evsel, core.node); } while (!last->cmdline_group_boundary); return 0; } -static int set_filter(struct perf_evsel *evsel, const void *arg) +static int set_filter(struct evsel *evsel, const void *arg) { const char *str = arg; bool found = false; @@ -2061,7 +2080,7 @@ static int set_filter(struct perf_evsel *evsel, const void *arg) return -1; } - if (evsel->attr.type == PERF_TYPE_TRACEPOINT) { + if (evsel->core.attr.type == PERF_TYPE_TRACEPOINT) { if (perf_evsel__append_tp_filter(evsel, str) < 0) { fprintf(stderr, "not enough memory to hold filter string\n"); @@ -2072,7 +2091,7 @@ static int set_filter(struct perf_evsel *evsel, const void *arg) } while ((pmu = perf_pmu__scan(pmu)) != NULL) - if (pmu->type == evsel->attr.type) { + if (pmu->type == evsel->core.attr.type) { found = true; break; } @@ -2099,18 +2118,18 @@ static int set_filter(struct perf_evsel *evsel, const void *arg) int parse_filter(const struct option *opt, const char *str, int unset __maybe_unused) { - struct perf_evlist *evlist = *(struct perf_evlist **)opt->value; + struct evlist *evlist = *(struct evlist **)opt->value; return foreach_evsel_in_last_glob(evlist, set_filter, (const void *)str); } -static int add_exclude_perf_filter(struct perf_evsel *evsel, +static int add_exclude_perf_filter(struct evsel *evsel, const void *arg __maybe_unused) { char new_filter[64]; - if (evsel == NULL || evsel->attr.type != PERF_TYPE_TRACEPOINT) { + if (evsel == NULL || evsel->core.attr.type != PERF_TYPE_TRACEPOINT) { fprintf(stderr, "--exclude-perf option should follow a -e tracepoint option\n"); return -1; @@ -2131,7 +2150,7 @@ int exclude_perf(const struct option *opt, const char *arg __maybe_unused, int unset __maybe_unused) { - struct perf_evlist *evlist = *(struct perf_evlist **)opt->value; + struct evlist *evlist = *(struct evlist **)opt->value; return foreach_evsel_in_last_glob(evlist, add_exclude_perf_filter, NULL); @@ -2297,20 +2316,20 @@ static bool is_event_supported(u8 type, unsigned config) { bool ret = true; int open_return; - struct perf_evsel *evsel; + struct evsel *evsel; struct perf_event_attr attr = { .type = type, .config = config, .disabled = 1, }; - struct thread_map *tmap = thread_map__new_by_tid(0); + struct perf_thread_map *tmap = thread_map__new_by_tid(0); if (tmap == NULL) return false; - evsel = perf_evsel__new(&attr); + evsel = evsel__new(&attr); if (evsel) { - open_return = perf_evsel__open(evsel, NULL, tmap); + open_return = evsel__open(evsel, NULL, tmap); ret = open_return >= 0; if (open_return == -EACCES) { @@ -2321,13 +2340,13 @@ static bool is_event_supported(u8 type, unsigned config) * by default as some ARM machines do not support it. * */ - evsel->attr.exclude_kernel = 1; - ret = perf_evsel__open(evsel, NULL, tmap) >= 0; + evsel->core.attr.exclude_kernel = 1; + ret = evsel__open(evsel, NULL, tmap) >= 0; } - perf_evsel__delete(evsel); + evsel__delete(evsel); } - thread_map__put(tmap); + perf_thread_map__put(tmap); return ret; } diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index f7139e1a2fd3..616ca1eda0eb 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -12,8 +12,8 @@ #include <string.h> struct list_head; -struct perf_evsel; -struct perf_evlist; +struct evsel; +struct evlist; struct parse_events_error; struct option; @@ -31,7 +31,7 @@ bool have_tracepoints(struct list_head *evlist); const char *event_type(int type); int parse_events_option(const struct option *opt, const char *str, int unset); -int parse_events(struct perf_evlist *evlist, const char *str, +int parse_events(struct evlist *evlist, const char *str, struct parse_events_error *error); int parse_events_terms(struct list_head *terms, const char *str); int parse_filter(const struct option *opt, const char *str, int unset); @@ -76,6 +76,7 @@ enum { PARSE_EVENTS__TERM_TYPE_OVERWRITE, PARSE_EVENTS__TERM_TYPE_DRV_CFG, PARSE_EVENTS__TERM_TYPE_PERCORE, + PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT, __PARSE_EVENTS__TERM_TYPE_NR, }; @@ -119,7 +120,7 @@ struct parse_events_state { int idx; int nr_groups; struct parse_events_error *error; - struct perf_evlist *evlist; + struct evlist *evlist; struct list_head *terms; }; diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index ca6098874fe2..7469497cd28e 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -284,6 +284,7 @@ no-inherit { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOINHERIT); } overwrite { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_OVERWRITE); } no-overwrite { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOOVERWRITE); } percore { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_PERCORE); } +aux-output { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT); } , { return ','; } "/" { BEGIN(INITIAL); return '/'; } {name_minus} { return str(yyscanner, PE_NAME); } diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index f32b710347db..9807be6f09bb 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -15,6 +15,8 @@ #include <api/fs/fs.h> #include <locale.h> #include <regex.h> +#include <perf/cpumap.h> +#include "debug.h" #include "pmu.h" #include "parse-events.h" #include "cpumap.h" @@ -572,16 +574,16 @@ static void pmu_read_sysfs(void) closedir(dir); } -static struct cpu_map *__pmu_cpumask(const char *path) +static struct perf_cpu_map *__pmu_cpumask(const char *path) { FILE *file; - struct cpu_map *cpus; + struct perf_cpu_map *cpus; file = fopen(path, "r"); if (!file) return NULL; - cpus = cpu_map__read(file); + cpus = perf_cpu_map__read(file); fclose(file); return cpus; } @@ -593,10 +595,10 @@ static struct cpu_map *__pmu_cpumask(const char *path) #define CPUS_TEMPLATE_UNCORE "%s/bus/event_source/devices/%s/cpumask" #define CPUS_TEMPLATE_CPU "%s/bus/event_source/devices/%s/cpus" -static struct cpu_map *pmu_cpumask(const char *name) +static struct perf_cpu_map *pmu_cpumask(const char *name) { char path[PATH_MAX]; - struct cpu_map *cpus; + struct perf_cpu_map *cpus; const char *sysfs = sysfs__mountpoint(); const char *templates[] = { CPUS_TEMPLATE_UNCORE, @@ -621,12 +623,12 @@ static struct cpu_map *pmu_cpumask(const char *name) static bool pmu_is_uncore(const char *name) { char path[PATH_MAX]; - struct cpu_map *cpus; + struct perf_cpu_map *cpus; const char *sysfs = sysfs__mountpoint(); snprintf(path, PATH_MAX, CPUS_TEMPLATE_UNCORE, sysfs, name); cpus = __pmu_cpumask(path); - cpu_map__put(cpus); + perf_cpu_map__put(cpus); return !!cpus; } diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index bd9ec2704a57..3f8b79b1dd85 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -28,7 +28,7 @@ struct perf_pmu { bool is_uncore; int max_precise; struct perf_event_attr *default_config; - struct cpu_map *cpus; + struct perf_cpu_map *cpus; struct list_head format; /* HEAD struct perf_pmu_format -> list */ struct list_head aliases; /* HEAD struct perf_pmu_alias -> list */ struct list_head list; /* ELEM */ diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index ceb8afdf9a89..c6dd478956f1 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -7,6 +7,7 @@ util/python.c ../lib/ctype.c +util/cap.c util/evlist.c util/evsel.c util/cpumap.c @@ -18,10 +19,8 @@ util/namespaces.c ../lib/hweight.c ../lib/string.c ../lib/vsprintf.c -../lib/zalloc.c util/thread_map.c util/util.c -util/xyarray.c util/cgroup.c util/parse-branch-options.c util/rblist.c diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 1e5b6718dcea..75ecc32a4427 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -4,6 +4,7 @@ #include <inttypes.h> #include <poll.h> #include <linux/err.h> +#include <perf/cpumap.h> #include "evlist.h" #include "callchain.h" #include "evsel.h" @@ -93,7 +94,7 @@ PyMODINIT_FUNC PyInit_perf(void); struct pyrf_event { PyObject_HEAD - struct perf_evsel *evsel; + struct evsel *evsel; struct perf_sample sample; union perf_event event; }; @@ -337,7 +338,7 @@ static PyObject *pyrf_sample_event__repr(struct pyrf_event *pevent) static bool is_tracepoint(struct pyrf_event *pevent) { - return pevent->evsel->attr.type == PERF_TYPE_TRACEPOINT; + return pevent->evsel->core.attr.type == PERF_TYPE_TRACEPOINT; } static PyObject* @@ -383,13 +384,13 @@ static PyObject* get_tracepoint_field(struct pyrf_event *pevent, PyObject *attr_name) { const char *str = _PyUnicode_AsString(PyObject_Str(attr_name)); - struct perf_evsel *evsel = pevent->evsel; + struct evsel *evsel = pevent->evsel; struct tep_format_field *field; if (!evsel->tp_format) { struct tep_event *tp_format; - tp_format = trace_event__tp_format_id(evsel->attr.config); + tp_format = trace_event__tp_format_id(evsel->core.attr.config); if (!tp_format) return NULL; @@ -536,7 +537,7 @@ static PyObject *pyrf_event__new(union perf_event *event) struct pyrf_cpu_map { PyObject_HEAD - struct cpu_map *cpus; + struct perf_cpu_map *cpus; }; static int pyrf_cpu_map__init(struct pyrf_cpu_map *pcpus, @@ -549,7 +550,7 @@ static int pyrf_cpu_map__init(struct pyrf_cpu_map *pcpus, kwlist, &cpustr)) return -1; - pcpus->cpus = cpu_map__new(cpustr); + pcpus->cpus = perf_cpu_map__new(cpustr); if (pcpus->cpus == NULL) return -1; return 0; @@ -557,7 +558,7 @@ static int pyrf_cpu_map__init(struct pyrf_cpu_map *pcpus, static void pyrf_cpu_map__delete(struct pyrf_cpu_map *pcpus) { - cpu_map__put(pcpus->cpus); + perf_cpu_map__put(pcpus->cpus); Py_TYPE(pcpus)->tp_free((PyObject*)pcpus); } @@ -605,7 +606,7 @@ static int pyrf_cpu_map__setup_types(void) struct pyrf_thread_map { PyObject_HEAD - struct thread_map *threads; + struct perf_thread_map *threads; }; static int pyrf_thread_map__init(struct pyrf_thread_map *pthreads, @@ -626,7 +627,7 @@ static int pyrf_thread_map__init(struct pyrf_thread_map *pthreads, static void pyrf_thread_map__delete(struct pyrf_thread_map *pthreads) { - thread_map__put(pthreads->threads); + perf_thread_map__put(pthreads->threads); Py_TYPE(pthreads)->tp_free((PyObject*)pthreads); } @@ -674,7 +675,7 @@ static int pyrf_thread_map__setup_types(void) struct pyrf_evsel { PyObject_HEAD - struct perf_evsel evsel; + struct evsel evsel; }; static int pyrf_evsel__init(struct pyrf_evsel *pevsel, @@ -782,7 +783,7 @@ static int pyrf_evsel__init(struct pyrf_evsel *pevsel, attr.sample_id_all = sample_id_all; attr.size = sizeof(attr); - perf_evsel__init(&pevsel->evsel, &attr, idx); + evsel__init(&pevsel->evsel, &attr, idx); return 0; } @@ -795,9 +796,9 @@ static void pyrf_evsel__delete(struct pyrf_evsel *pevsel) static PyObject *pyrf_evsel__open(struct pyrf_evsel *pevsel, PyObject *args, PyObject *kwargs) { - struct perf_evsel *evsel = &pevsel->evsel; - struct cpu_map *cpus = NULL; - struct thread_map *threads = NULL; + struct evsel *evsel = &pevsel->evsel; + struct perf_cpu_map *cpus = NULL; + struct perf_thread_map *threads = NULL; PyObject *pcpus = NULL, *pthreads = NULL; int group = 0, inherit = 0; static char *kwlist[] = { "cpus", "threads", "group", "inherit", NULL }; @@ -812,12 +813,12 @@ static PyObject *pyrf_evsel__open(struct pyrf_evsel *pevsel, if (pcpus != NULL) cpus = ((struct pyrf_cpu_map *)pcpus)->cpus; - evsel->attr.inherit = inherit; + evsel->core.attr.inherit = inherit; /* * This will group just the fds for this single evsel, to group * multiple events, use evlist.open(). */ - if (perf_evsel__open(evsel, cpus, threads) < 0) { + if (evsel__open(evsel, cpus, threads) < 0) { PyErr_SetFromErrno(PyExc_OSError); return NULL; } @@ -858,22 +859,22 @@ static int pyrf_evsel__setup_types(void) struct pyrf_evlist { PyObject_HEAD - struct perf_evlist evlist; + struct evlist evlist; }; static int pyrf_evlist__init(struct pyrf_evlist *pevlist, PyObject *args, PyObject *kwargs __maybe_unused) { PyObject *pcpus = NULL, *pthreads = NULL; - struct cpu_map *cpus; - struct thread_map *threads; + struct perf_cpu_map *cpus; + struct perf_thread_map *threads; if (!PyArg_ParseTuple(args, "OO", &pcpus, &pthreads)) return -1; threads = ((struct pyrf_thread_map *)pthreads)->threads; cpus = ((struct pyrf_cpu_map *)pcpus)->cpus; - perf_evlist__init(&pevlist->evlist, cpus, threads); + evlist__init(&pevlist->evlist, cpus, threads); return 0; } @@ -886,7 +887,7 @@ static void pyrf_evlist__delete(struct pyrf_evlist *pevlist) static PyObject *pyrf_evlist__mmap(struct pyrf_evlist *pevlist, PyObject *args, PyObject *kwargs) { - struct perf_evlist *evlist = &pevlist->evlist; + struct evlist *evlist = &pevlist->evlist; static char *kwlist[] = { "pages", "overwrite", NULL }; int pages = 128, overwrite = false; @@ -906,7 +907,7 @@ static PyObject *pyrf_evlist__mmap(struct pyrf_evlist *pevlist, static PyObject *pyrf_evlist__poll(struct pyrf_evlist *pevlist, PyObject *args, PyObject *kwargs) { - struct perf_evlist *evlist = &pevlist->evlist; + struct evlist *evlist = &pevlist->evlist; static char *kwlist[] = { "timeout", NULL }; int timeout = -1, n; @@ -926,7 +927,7 @@ static PyObject *pyrf_evlist__get_pollfd(struct pyrf_evlist *pevlist, PyObject *args __maybe_unused, PyObject *kwargs __maybe_unused) { - struct perf_evlist *evlist = &pevlist->evlist; + struct evlist *evlist = &pevlist->evlist; PyObject *list = PyList_New(0); int i; @@ -964,22 +965,22 @@ static PyObject *pyrf_evlist__add(struct pyrf_evlist *pevlist, PyObject *args, PyObject *kwargs __maybe_unused) { - struct perf_evlist *evlist = &pevlist->evlist; + struct evlist *evlist = &pevlist->evlist; PyObject *pevsel; - struct perf_evsel *evsel; + struct evsel *evsel; if (!PyArg_ParseTuple(args, "O", &pevsel)) return NULL; Py_INCREF(pevsel); evsel = &((struct pyrf_evsel *)pevsel)->evsel; - evsel->idx = evlist->nr_entries; - perf_evlist__add(evlist, evsel); + evsel->idx = evlist->core.nr_entries; + evlist__add(evlist, evsel); - return Py_BuildValue("i", evlist->nr_entries); + return Py_BuildValue("i", evlist->core.nr_entries); } -static struct perf_mmap *get_md(struct perf_evlist *evlist, int cpu) +static struct perf_mmap *get_md(struct evlist *evlist, int cpu) { int i; @@ -996,7 +997,7 @@ static struct perf_mmap *get_md(struct perf_evlist *evlist, int cpu) static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist, PyObject *args, PyObject *kwargs) { - struct perf_evlist *evlist = &pevlist->evlist; + struct evlist *evlist = &pevlist->evlist; union perf_event *event; int sample_id_all = 1, cpu; static char *kwlist[] = { "cpu", "sample_id_all", NULL }; @@ -1018,7 +1019,7 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist, if (event != NULL) { PyObject *pyevent = pyrf_event__new(event); struct pyrf_event *pevent = (struct pyrf_event *)pyevent; - struct perf_evsel *evsel; + struct evsel *evsel; if (pyevent == NULL) return PyErr_NoMemory(); @@ -1049,7 +1050,7 @@ end: static PyObject *pyrf_evlist__open(struct pyrf_evlist *pevlist, PyObject *args, PyObject *kwargs) { - struct perf_evlist *evlist = &pevlist->evlist; + struct evlist *evlist = &pevlist->evlist; int group = 0; static char *kwlist[] = { "group", NULL }; @@ -1059,7 +1060,7 @@ static PyObject *pyrf_evlist__open(struct pyrf_evlist *pevlist, if (group) perf_evlist__set_leader(evlist); - if (perf_evlist__open(evlist) < 0) { + if (evlist__open(evlist) < 0) { PyErr_SetFromErrno(PyExc_OSError); return NULL; } @@ -1112,15 +1113,15 @@ static Py_ssize_t pyrf_evlist__length(PyObject *obj) { struct pyrf_evlist *pevlist = (void *)obj; - return pevlist->evlist.nr_entries; + return pevlist->evlist.core.nr_entries; } static PyObject *pyrf_evlist__item(PyObject *obj, Py_ssize_t i) { struct pyrf_evlist *pevlist = (void *)obj; - struct perf_evsel *pos; + struct evsel *pos; - if (i >= pevlist->evlist.nr_entries) + if (i >= pevlist->evlist.core.nr_entries) return NULL; evlist__for_each_entry(&pevlist->evlist, pos) { diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c index 9cfc7bf16531..51bbd0714e6d 100644 --- a/tools/perf/util/record.c +++ b/tools/perf/util/record.c @@ -6,20 +6,21 @@ #include <errno.h> #include <api/fs/fs.h> #include <subcmd/parse-options.h> +#include <perf/cpumap.h> #include "util.h" #include "cloexec.h" -typedef void (*setup_probe_fn_t)(struct perf_evsel *evsel); +typedef void (*setup_probe_fn_t)(struct evsel *evsel); static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str) { - struct perf_evlist *evlist; - struct perf_evsel *evsel; + struct evlist *evlist; + struct evsel *evsel; unsigned long flags = perf_event_open_cloexec_flag(); int err = -EAGAIN, fd; static pid_t pid = -1; - evlist = perf_evlist__new(); + evlist = evlist__new(); if (!evlist) return -ENOMEM; @@ -29,7 +30,7 @@ static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str) evsel = perf_evlist__first(evlist); while (1) { - fd = sys_perf_event_open(&evsel->attr, pid, cpu, -1, flags); + fd = sys_perf_event_open(&evsel->core.attr, pid, cpu, -1, flags); if (fd < 0) { if (pid == -1 && errno == EACCES) { pid = 0; @@ -43,7 +44,7 @@ static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str) fn(evsel); - fd = sys_perf_event_open(&evsel->attr, pid, cpu, -1, flags); + fd = sys_perf_event_open(&evsel->core.attr, pid, cpu, -1, flags); if (fd < 0) { if (errno == EINVAL) err = -EINVAL; @@ -53,21 +54,21 @@ static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str) err = 0; out_delete: - perf_evlist__delete(evlist); + evlist__delete(evlist); return err; } static bool perf_probe_api(setup_probe_fn_t fn) { const char *try[] = {"cycles:u", "instructions:u", "cpu-clock:u", NULL}; - struct cpu_map *cpus; + struct perf_cpu_map *cpus; int cpu, ret, i = 0; - cpus = cpu_map__new(NULL); + cpus = perf_cpu_map__new(NULL); if (!cpus) return false; cpu = cpus->map[0]; - cpu_map__put(cpus); + perf_cpu_map__put(cpus); do { ret = perf_do_probe_api(fn, cpu, try[i++]); @@ -78,19 +79,19 @@ static bool perf_probe_api(setup_probe_fn_t fn) return false; } -static void perf_probe_sample_identifier(struct perf_evsel *evsel) +static void perf_probe_sample_identifier(struct evsel *evsel) { - evsel->attr.sample_type |= PERF_SAMPLE_IDENTIFIER; + evsel->core.attr.sample_type |= PERF_SAMPLE_IDENTIFIER; } -static void perf_probe_comm_exec(struct perf_evsel *evsel) +static void perf_probe_comm_exec(struct evsel *evsel) { - evsel->attr.comm_exec = 1; + evsel->core.attr.comm_exec = 1; } -static void perf_probe_context_switch(struct perf_evsel *evsel) +static void perf_probe_context_switch(struct evsel *evsel) { - evsel->attr.context_switch = 1; + evsel->core.attr.context_switch = 1; } bool perf_can_sample_identifier(void) @@ -115,14 +116,14 @@ bool perf_can_record_cpu_wide(void) .config = PERF_COUNT_SW_CPU_CLOCK, .exclude_kernel = 1, }; - struct cpu_map *cpus; + struct perf_cpu_map *cpus; int cpu, fd; - cpus = cpu_map__new(NULL); + cpus = perf_cpu_map__new(NULL); if (!cpus) return false; cpu = cpus->map[0]; - cpu_map__put(cpus); + perf_cpu_map__put(cpus); fd = sys_perf_event_open(&attr, -1, cpu, -1, 0); if (fd < 0) @@ -132,10 +133,10 @@ bool perf_can_record_cpu_wide(void) return true; } -void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts, +void perf_evlist__config(struct evlist *evlist, struct record_opts *opts, struct callchain_param *callchain) { - struct perf_evsel *evsel; + struct evsel *evsel; bool use_sample_identifier = false; bool use_comm_exec; bool sample_id = opts->sample_id; @@ -147,7 +148,7 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts, if (opts->group) perf_evlist__set_leader(evlist); - if (evlist->cpus->map[0] < 0) + if (evlist->core.cpus->map[0] < 0) opts->no_inherit = true; use_comm_exec = perf_can_comm_exec(); @@ -155,7 +156,7 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts, evlist__for_each_entry(evlist, evsel) { perf_evsel__config(evsel, opts, callchain); if (evsel->tracking && use_comm_exec) - evsel->attr.comm_exec = 1; + evsel->core.attr.comm_exec = 1; } if (opts->full_auxtrace) { @@ -166,11 +167,11 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts, */ use_sample_identifier = perf_can_sample_identifier(); sample_id = true; - } else if (evlist->nr_entries > 1) { - struct perf_evsel *first = perf_evlist__first(evlist); + } else if (evlist->core.nr_entries > 1) { + struct evsel *first = perf_evlist__first(evlist); evlist__for_each_entry(evlist, evsel) { - if (evsel->attr.sample_type == first->attr.sample_type) + if (evsel->core.attr.sample_type == first->core.attr.sample_type) continue; use_sample_identifier = perf_can_sample_identifier(); break; @@ -256,15 +257,15 @@ int record_opts__config(struct record_opts *opts) return record_opts__config_freq(opts); } -bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str) +bool perf_evlist__can_select_event(struct evlist *evlist, const char *str) { - struct perf_evlist *temp_evlist; - struct perf_evsel *evsel; + struct evlist *temp_evlist; + struct evsel *evsel; int err, fd, cpu; bool ret = false; pid_t pid = -1; - temp_evlist = perf_evlist__new(); + temp_evlist = evlist__new(); if (!temp_evlist) return false; @@ -274,17 +275,17 @@ bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str) evsel = perf_evlist__last(temp_evlist); - if (!evlist || cpu_map__empty(evlist->cpus)) { - struct cpu_map *cpus = cpu_map__new(NULL); + if (!evlist || perf_cpu_map__empty(evlist->core.cpus)) { + struct perf_cpu_map *cpus = perf_cpu_map__new(NULL); cpu = cpus ? cpus->map[0] : 0; - cpu_map__put(cpus); + perf_cpu_map__put(cpus); } else { - cpu = evlist->cpus->map[0]; + cpu = evlist->core.cpus->map[0]; } while (1) { - fd = sys_perf_event_open(&evsel->attr, pid, cpu, -1, + fd = sys_perf_event_open(&evsel->core.attr, pid, cpu, -1, perf_event_open_cloexec_flag()); if (fd < 0) { if (pid == -1 && errno == EACCES) { @@ -299,7 +300,7 @@ bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str) ret = true; out_delete: - perf_evlist__delete(temp_evlist); + evlist__delete(temp_evlist); return ret; } diff --git a/tools/perf/util/s390-cpumsf.c b/tools/perf/util/s390-cpumsf.c index 83d2e149ef19..d078ae8353c8 100644 --- a/tools/perf/util/s390-cpumsf.c +++ b/tools/perf/util/s390-cpumsf.c @@ -918,7 +918,7 @@ s390_cpumsf_process_event(struct perf_session *session, struct s390_cpumsf, auxtrace); u64 timestamp = sample->time; - struct perf_evsel *ev_bc000; + struct evsel *ev_bc000; int err = 0; @@ -935,7 +935,7 @@ s390_cpumsf_process_event(struct perf_session *session, /* Handle event with raw data */ ev_bc000 = perf_evlist__event2evsel(session->evlist, event); if (ev_bc000 && - ev_bc000->attr.config == PERF_EVENT_CPUM_CF_DIAG) + ev_bc000->core.attr.config == PERF_EVENT_CPUM_CF_DIAG) err = s390_cpumcf_dumpctr(sf, sample); return err; } diff --git a/tools/perf/util/s390-sample-raw.c b/tools/perf/util/s390-sample-raw.c index 6650f599ed9c..d311c81464e5 100644 --- a/tools/perf/util/s390-sample-raw.c +++ b/tools/perf/util/s390-sample-raw.c @@ -200,17 +200,17 @@ static void s390_cpumcfdg_dump(struct perf_sample *sample) * its raw data. * The function is only invoked when the dump flag -D is set. */ -void perf_evlist__s390_sample_raw(struct perf_evlist *evlist, union perf_event *event, +void perf_evlist__s390_sample_raw(struct evlist *evlist, union perf_event *event, struct perf_sample *sample) { - struct perf_evsel *ev_bc000; + struct evsel *ev_bc000; if (event->header.type != PERF_RECORD_SAMPLE) return; ev_bc000 = perf_evlist__event2evsel(evlist, event); if (ev_bc000 == NULL || - ev_bc000->attr.config != PERF_EVENT_CPUM_CF_DIAG) + ev_bc000->core.attr.config != PERF_EVENT_CPUM_CF_DIAG) return; /* Display raw data on screen */ diff --git a/tools/perf/util/sample-raw.c b/tools/perf/util/sample-raw.c index c21e1311fb0f..e84bbe0e441a 100644 --- a/tools/perf/util/sample-raw.c +++ b/tools/perf/util/sample-raw.c @@ -9,7 +9,7 @@ * Check platform the perf data file was created on and perform platform * specific interpretation. */ -void perf_evlist__init_trace_event_sample_raw(struct perf_evlist *evlist) +void perf_evlist__init_trace_event_sample_raw(struct evlist *evlist) { const char *arch_pf = perf_env__arch(evlist->env); diff --git a/tools/perf/util/sample-raw.h b/tools/perf/util/sample-raw.h index 95d445c87e93..afe1491a117e 100644 --- a/tools/perf/util/sample-raw.h +++ b/tools/perf/util/sample-raw.h @@ -2,13 +2,13 @@ #ifndef __SAMPLE_RAW_H #define __SAMPLE_RAW_H 1 -struct perf_evlist; +struct evlist; union perf_event; struct perf_sample; -void perf_evlist__s390_sample_raw(struct perf_evlist *evlist, +void perf_evlist__s390_sample_raw(struct evlist *evlist, union perf_event *event, struct perf_sample *sample); -void perf_evlist__init_trace_event_sample_raw(struct perf_evlist *evlist); +void perf_evlist__init_trace_event_sample_raw(struct evlist *evlist); #endif /* __PERF_EVLIST_H */ diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index 61aa7f3df915..01ebf10b8bf4 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -258,7 +258,7 @@ static void define_event_symbols(struct tep_event *event, } static SV *perl_process_callchain(struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct addr_location *al) { AV *list; @@ -336,7 +336,7 @@ exit: } static void perl_process_tracepoint(struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct addr_location *al) { struct thread *thread = al->thread; @@ -353,11 +353,11 @@ static void perl_process_tracepoint(struct perf_sample *sample, dSP; - if (evsel->attr.type != PERF_TYPE_TRACEPOINT) + if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT) return; if (!event) { - pr_debug("ug! no event found for type %" PRIu64, (u64)evsel->attr.config); + pr_debug("ug! no event found for type %" PRIu64, (u64)evsel->core.attr.config); return; } @@ -431,7 +431,7 @@ static void perl_process_tracepoint(struct perf_sample *sample, static void perl_process_event_generic(union perf_event *event, struct perf_sample *sample, - struct perf_evsel *evsel) + struct evsel *evsel) { dSP; @@ -442,7 +442,7 @@ static void perl_process_event_generic(union perf_event *event, SAVETMPS; PUSHMARK(SP); XPUSHs(sv_2mortal(newSVpvn((const char *)event, event->header.size))); - XPUSHs(sv_2mortal(newSVpvn((const char *)&evsel->attr, sizeof(evsel->attr)))); + XPUSHs(sv_2mortal(newSVpvn((const char *)&evsel->core.attr, sizeof(evsel->core.attr)))); XPUSHs(sv_2mortal(newSVpvn((const char *)sample, sizeof(*sample)))); XPUSHs(sv_2mortal(newSVpvn((const char *)sample->raw_data, sample->raw_size))); PUTBACK; @@ -455,7 +455,7 @@ static void perl_process_event_generic(union perf_event *event, static void perl_process_event(union perf_event *event, struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct addr_location *al) { perl_process_tracepoint(sample, evsel, al); diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 25dc1d765553..78c8bc9380bd 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -32,6 +32,7 @@ #include <linux/time64.h> #include "../../perf.h" +#include "../counts.h" #include "../debug.h" #include "../callchain.h" #include "../evsel.h" @@ -392,7 +393,7 @@ static const char *get_dsoname(struct map *map) } static PyObject *python_process_callchain(struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct addr_location *al) { PyObject *pylist; @@ -634,9 +635,9 @@ static PyObject *get_sample_value_as_tuple(struct sample_read_value *value) static void set_sample_read_in_dict(PyObject *dict_sample, struct perf_sample *sample, - struct perf_evsel *evsel) + struct evsel *evsel) { - u64 read_format = evsel->attr.read_format; + u64 read_format = evsel->core.attr.read_format; PyObject *values; unsigned int i; @@ -705,9 +706,9 @@ static int regs_map(struct regs_dump *regs, uint64_t mask, char *bf, int size) static void set_regs_in_dict(PyObject *dict, struct perf_sample *sample, - struct perf_evsel *evsel) + struct evsel *evsel) { - struct perf_event_attr *attr = &evsel->attr; + struct perf_event_attr *attr = &evsel->core.attr; char bf[512]; regs_map(&sample->intr_regs, attr->sample_regs_intr, bf, sizeof(bf)); @@ -722,7 +723,7 @@ static void set_regs_in_dict(PyObject *dict, } static PyObject *get_perf_sample_dict(struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct addr_location *al, PyObject *callchain) { @@ -737,7 +738,7 @@ static PyObject *get_perf_sample_dict(struct perf_sample *sample, Py_FatalError("couldn't create Python dictionary"); pydict_set_item_string_decref(dict, "ev_name", _PyUnicode_FromString(perf_evsel__name(evsel))); - pydict_set_item_string_decref(dict, "attr", _PyBytes_FromStringAndSize((const char *)&evsel->attr, sizeof(evsel->attr))); + pydict_set_item_string_decref(dict, "attr", _PyBytes_FromStringAndSize((const char *)&evsel->core.attr, sizeof(evsel->core.attr))); pydict_set_item_string_decref(dict_sample, "pid", _PyLong_FromLong(sample->pid)); @@ -790,7 +791,7 @@ static PyObject *get_perf_sample_dict(struct perf_sample *sample, } static void python_process_tracepoint(struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct addr_location *al) { struct tep_event *event = evsel->tp_format; @@ -809,7 +810,7 @@ static void python_process_tracepoint(struct perf_sample *sample, if (!event) { snprintf(handler_name, sizeof(handler_name), - "ug! no event found for type %" PRIu64, (u64)evsel->attr.config); + "ug! no event found for type %" PRIu64, (u64)evsel->core.attr.config); Py_FatalError(handler_name); } @@ -955,7 +956,7 @@ static int tuple_set_bytes(PyObject *t, unsigned int pos, void *bytes, return PyTuple_SetItem(t, pos, _PyBytes_FromStringAndSize(bytes, sz)); } -static int python_export_evsel(struct db_export *dbe, struct perf_evsel *evsel) +static int python_export_evsel(struct db_export *dbe, struct evsel *evsel) { struct tables *tables = container_of(dbe, struct tables, dbe); PyObject *t; @@ -1163,7 +1164,7 @@ static void python_export_synth(struct db_export *dbe, struct export_sample *es) t = tuple_new(3); tuple_set_u64(t, 0, es->db_id); - tuple_set_u64(t, 1, es->evsel->attr.config); + tuple_set_u64(t, 1, es->evsel->core.attr.config); tuple_set_bytes(t, 2, es->sample->raw_data, es->sample->raw_size); call_object(tables->synth_handler, t, "synth_data"); @@ -1178,7 +1179,7 @@ static int python_export_sample(struct db_export *dbe, python_export_sample_table(dbe, es); - if (es->evsel->attr.type == PERF_TYPE_SYNTH && tables->synth_handler) + if (es->evsel->core.attr.type == PERF_TYPE_SYNTH && tables->synth_handler) python_export_synth(dbe, es); return 0; @@ -1275,7 +1276,7 @@ static int python_process_call_return(struct call_return *cr, u64 *parent_db_id, } static void python_process_general_event(struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct addr_location *al) { PyObject *handler, *t, *dict, *callchain; @@ -1311,12 +1312,12 @@ static void python_process_general_event(struct perf_sample *sample, static void python_process_event(union perf_event *event, struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct addr_location *al) { struct tables *tables = &tables_global; - switch (evsel->attr.type) { + switch (evsel->core.attr.type) { case PERF_TYPE_TRACEPOINT: python_process_tracepoint(sample, evsel, al); break; @@ -1340,7 +1341,7 @@ static void python_process_switch(union perf_event *event, } static void get_handler_name(char *str, size_t size, - struct perf_evsel *evsel) + struct evsel *evsel) { char *p = str; @@ -1353,7 +1354,7 @@ static void get_handler_name(char *str, size_t size, } static void -process_stat(struct perf_evsel *counter, int cpu, int thread, u64 tstamp, +process_stat(struct evsel *counter, int cpu, int thread, u64 tstamp, struct perf_counts_values *count) { PyObject *handler, *t; @@ -1390,10 +1391,10 @@ process_stat(struct perf_evsel *counter, int cpu, int thread, u64 tstamp, } static void python_process_stat(struct perf_stat_config *config, - struct perf_evsel *counter, u64 tstamp) + struct evsel *counter, u64 tstamp) { - struct thread_map *threads = counter->threads; - struct cpu_map *cpus = counter->cpus; + struct perf_thread_map *threads = counter->core.threads; + struct perf_cpu_map *cpus = counter->core.cpus; int cpu, thread; if (config->aggr_mode == AGGR_GLOBAL) { @@ -1405,7 +1406,7 @@ static void python_process_stat(struct perf_stat_config *config, for (thread = 0; thread < threads->nr; thread++) { for (cpu = 0; cpu < cpus->nr; cpu++) { process_stat(counter, cpus->map[cpu], - thread_map__pid(threads, thread), tstamp, + perf_thread_map__pid(threads, thread), tstamp, perf_counts(counter->counts, cpu, thread)); } } diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 37efa1f43d8b..82e0438a9160 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <errno.h> #include <inttypes.h> +#include <linux/err.h> #include <linux/kernel.h> #include <linux/zalloc.h> #include <traceevent/event-parse.h> @@ -10,6 +11,7 @@ #include <unistd.h> #include <sys/types.h> #include <sys/mman.h> +#include <perf/cpumap.h> #include "evlist.h" #include "evsel.h" @@ -151,10 +153,10 @@ static void perf_session__destroy_kernel_maps(struct perf_session *session) static bool perf_session__has_comm_exec(struct perf_session *session) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(session->evlist, evsel) { - if (evsel->attr.comm_exec) + if (evsel->core.attr.comm_exec) return true; } @@ -300,7 +302,7 @@ static int process_event_synth_tracing_data_stub(struct perf_session *session static int process_event_synth_attr_stub(struct perf_tool *tool __maybe_unused, union perf_event *event __maybe_unused, - struct perf_evlist **pevlist + struct evlist **pevlist __maybe_unused) { dump_printf(": unhandled!\n"); @@ -309,7 +311,7 @@ static int process_event_synth_attr_stub(struct perf_tool *tool __maybe_unused, static int process_event_synth_event_update_stub(struct perf_tool *tool __maybe_unused, union perf_event *event __maybe_unused, - struct perf_evlist **pevlist + struct evlist **pevlist __maybe_unused) { if (dump_trace) @@ -322,7 +324,7 @@ static int process_event_synth_event_update_stub(struct perf_tool *tool __maybe_ static int process_event_sample_stub(struct perf_tool *tool __maybe_unused, union perf_event *event __maybe_unused, struct perf_sample *sample __maybe_unused, - struct perf_evsel *evsel __maybe_unused, + struct evsel *evsel __maybe_unused, struct machine *machine __maybe_unused) { dump_printf(": unhandled!\n"); @@ -1033,7 +1035,7 @@ static void callchain__lbr_callstack_printf(struct perf_sample *sample) } } -static void callchain__printf(struct perf_evsel *evsel, +static void callchain__printf(struct evsel *evsel, struct perf_sample *sample) { unsigned int i; @@ -1049,23 +1051,30 @@ static void callchain__printf(struct perf_evsel *evsel, i, callchain->ips[i]); } -static void branch_stack__printf(struct perf_sample *sample) +static void branch_stack__printf(struct perf_sample *sample, bool callstack) { uint64_t i; - printf("... branch stack: nr:%" PRIu64 "\n", sample->branch_stack->nr); + printf("%s: nr:%" PRIu64 "\n", + !callstack ? "... branch stack" : "... branch callstack", + sample->branch_stack->nr); for (i = 0; i < sample->branch_stack->nr; i++) { struct branch_entry *e = &sample->branch_stack->entries[i]; - printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 " %hu cycles %s%s%s%s %x\n", - i, e->from, e->to, - (unsigned short)e->flags.cycles, - e->flags.mispred ? "M" : " ", - e->flags.predicted ? "P" : " ", - e->flags.abort ? "A" : " ", - e->flags.in_tx ? "T" : " ", - (unsigned)e->flags.reserved); + if (!callstack) { + printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 " %hu cycles %s%s%s%s %x\n", + i, e->from, e->to, + (unsigned short)e->flags.cycles, + e->flags.mispred ? "M" : " ", + e->flags.predicted ? "P" : " ", + e->flags.abort ? "A" : " ", + e->flags.in_tx ? "T" : " ", + (unsigned)e->flags.reserved); + } else { + printf("..... %2"PRIu64": %016" PRIx64 "\n", + i, i > 0 ? e->from : e->to); + } } } @@ -1129,7 +1138,7 @@ static void stack_user__printf(struct stack_dump *dump) dump->size, dump->offset); } -static void perf_evlist__print_tstamp(struct perf_evlist *evlist, +static void perf_evlist__print_tstamp(struct evlist *evlist, union perf_event *event, struct perf_sample *sample) { @@ -1178,7 +1187,7 @@ static void sample_read__printf(struct perf_sample *sample, u64 read_format) sample->read.one.id, sample->read.one.value); } -static void dump_event(struct perf_evlist *evlist, union perf_event *event, +static void dump_event(struct evlist *evlist, union perf_event *event, u64 file_offset, struct perf_sample *sample) { if (!dump_trace) @@ -1198,7 +1207,7 @@ static void dump_event(struct perf_evlist *evlist, union perf_event *event, event->header.size, perf_event__name(event->header.type)); } -static void dump_sample(struct perf_evsel *evsel, union perf_event *event, +static void dump_sample(struct evsel *evsel, union perf_event *event, struct perf_sample *sample) { u64 sample_type; @@ -1210,13 +1219,13 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event, event->header.misc, sample->pid, sample->tid, sample->ip, sample->period, sample->addr); - sample_type = evsel->attr.sample_type; + sample_type = evsel->core.attr.sample_type; if (evsel__has_callchain(evsel)) callchain__printf(evsel, sample); - if ((sample_type & PERF_SAMPLE_BRANCH_STACK) && !perf_evsel__has_branch_callstack(evsel)) - branch_stack__printf(sample); + if (sample_type & PERF_SAMPLE_BRANCH_STACK) + branch_stack__printf(sample, perf_evsel__has_branch_callstack(evsel)); if (sample_type & PERF_SAMPLE_REGS_USER) regs_user__printf(sample); @@ -1240,10 +1249,10 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event, printf("... transaction: %" PRIx64 "\n", sample->transaction); if (sample_type & PERF_SAMPLE_READ) - sample_read__printf(sample, evsel->attr.read_format); + sample_read__printf(sample, evsel->core.attr.read_format); } -static void dump_read(struct perf_evsel *evsel, union perf_event *event) +static void dump_read(struct evsel *evsel, union perf_event *event) { struct read_event *read_event = &event->read; u64 read_format; @@ -1258,7 +1267,7 @@ static void dump_read(struct perf_evsel *evsel, union perf_event *event) if (!evsel) return; - read_format = evsel->attr.read_format; + read_format = evsel->core.attr.read_format; if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) printf("... time enabled : %" PRIu64 "\n", read_event->time_enabled); @@ -1296,7 +1305,7 @@ static struct machine *machines__find_for_cpumode(struct machines *machines, return &machines->host; } -static int deliver_sample_value(struct perf_evlist *evlist, +static int deliver_sample_value(struct evlist *evlist, struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -1326,7 +1335,7 @@ static int deliver_sample_value(struct perf_evlist *evlist, return tool->sample(tool, event, sample, sid->evsel, machine); } -static int deliver_sample_group(struct perf_evlist *evlist, +static int deliver_sample_group(struct evlist *evlist, struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -1347,16 +1356,16 @@ static int deliver_sample_group(struct perf_evlist *evlist, } static int - perf_evlist__deliver_sample(struct perf_evlist *evlist, + perf_evlist__deliver_sample(struct evlist *evlist, struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct machine *machine) { /* We know evsel != NULL. */ - u64 sample_type = evsel->attr.sample_type; - u64 read_format = evsel->attr.read_format; + u64 sample_type = evsel->core.attr.sample_type; + u64 read_format = evsel->core.attr.read_format; /* Standard sample delivery. */ if (!(sample_type & PERF_SAMPLE_READ)) @@ -1372,12 +1381,12 @@ static int } static int machines__deliver_event(struct machines *machines, - struct perf_evlist *evlist, + struct evlist *evlist, union perf_event *event, struct perf_sample *sample, struct perf_tool *tool, u64 file_offset) { - struct perf_evsel *evsel; + struct evsel *evsel; struct machine *machine; dump_event(evlist, event, file_offset, sample); @@ -1553,7 +1562,7 @@ int perf_session__deliver_synth_event(struct perf_session *session, union perf_event *event, struct perf_sample *sample) { - struct perf_evlist *evlist = session->evlist; + struct evlist *evlist = session->evlist; struct perf_tool *tool = session->tool; events_stats__inc(&evlist->stats, event->header.type); @@ -1631,7 +1640,7 @@ out_parse_sample: static s64 perf_session__process_event(struct perf_session *session, union perf_event *event, u64 file_offset) { - struct perf_evlist *evlist = session->evlist; + struct evlist *evlist = session->evlist; struct perf_tool *tool = session->tool; int ret; @@ -1705,11 +1714,11 @@ static void perf_session__warn_order(const struct perf_session *session) { const struct ordered_events *oe = &session->ordered_events; - struct perf_evsel *evsel; + struct evsel *evsel; bool should_warn = true; evlist__for_each_entry(session->evlist, evsel) { - if (evsel->attr.write_backward) + if (evsel->core.attr.write_backward) should_warn = false; } @@ -1954,7 +1963,9 @@ fetch_mmaped_event(struct perf_session *session, /* We're not fetching the event so swap back again */ if (session->header.needs_swap) perf_event_header__bswap(&event->header); - return NULL; + pr_debug("%s: head=%#" PRIx64 " event->header_size=%#x, mmap_size=%#zx: fuzzed perf.data?\n", + __func__, head, event->header.size, mmap_size); + return ERR_PTR(-EINVAL); } return event; @@ -1972,6 +1983,9 @@ static int __perf_session__process_decomp_events(struct perf_session *session) while (decomp->head < decomp->size && !session_done()) { union perf_event *event = fetch_mmaped_event(session, decomp->head, decomp->size, decomp->data); + if (IS_ERR(event)) + return PTR_ERR(event); + if (!event) break; @@ -2071,6 +2085,9 @@ remap: more: event = fetch_mmaped_event(session, head, mmap_size, buf); + if (IS_ERR(event)) + return PTR_ERR(event); + if (!event) { if (mmaps[map_idx]) { munmap(mmaps[map_idx], mmap_size); @@ -2183,10 +2200,10 @@ int perf_session__process_events(struct perf_session *session) bool perf_session__has_traces(struct perf_session *session, const char *msg) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(session->evlist, evsel) { - if (evsel->attr.type == PERF_TYPE_TRACEPOINT) + if (evsel->core.attr.type == PERF_TYPE_TRACEPOINT) return true; } @@ -2257,13 +2274,13 @@ size_t perf_session__fprintf(struct perf_session *session, FILE *fp) return machine__fprintf(&session->machines.host, fp); } -struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session, +struct evsel *perf_session__find_first_evtype(struct perf_session *session, unsigned int type) { - struct perf_evsel *pos; + struct evsel *pos; evlist__for_each_entry(session->evlist, pos) { - if (pos->attr.type == type) + if (pos->core.attr.type == type) return pos; } return NULL; @@ -2273,23 +2290,23 @@ int perf_session__cpu_bitmap(struct perf_session *session, const char *cpu_list, unsigned long *cpu_bitmap) { int i, err = -1; - struct cpu_map *map; + struct perf_cpu_map *map; for (i = 0; i < PERF_TYPE_MAX; ++i) { - struct perf_evsel *evsel; + struct evsel *evsel; evsel = perf_session__find_first_evtype(session, i); if (!evsel) continue; - if (!(evsel->attr.sample_type & PERF_SAMPLE_CPU)) { + if (!(evsel->core.attr.sample_type & PERF_SAMPLE_CPU)) { pr_err("File does not contain CPU events. " "Remove -C option to proceed.\n"); return -1; } } - map = cpu_map__new(cpu_list); + map = perf_cpu_map__new(cpu_list); if (map == NULL) { pr_err("Invalid cpu_list\n"); return -1; @@ -2310,7 +2327,7 @@ int perf_session__cpu_bitmap(struct perf_session *session, err = 0; out_delete_map: - cpu_map__put(map); + perf_cpu_map__put(map); return err; } @@ -2327,10 +2344,10 @@ void perf_session__fprintf_info(struct perf_session *session, FILE *fp, int __perf_session__set_tracepoints_handlers(struct perf_session *session, - const struct perf_evsel_str_handler *assocs, + const struct evsel_str_handler *assocs, size_t nr_assocs) { - struct perf_evsel *evsel; + struct evsel *evsel; size_t i; int err; @@ -2357,7 +2374,7 @@ out: int perf_event__process_id_index(struct perf_session *session, union perf_event *event) { - struct perf_evlist *evlist = session->evlist; + struct evlist *evlist = session->evlist; struct id_index_event *ie = &event->id_index; size_t i, nr, max_nr; @@ -2393,11 +2410,11 @@ int perf_event__process_id_index(struct perf_session *session, int perf_event__synthesize_id_index(struct perf_tool *tool, perf_event__handler_t process, - struct perf_evlist *evlist, + struct evlist *evlist, struct machine *machine) { union perf_event *ev; - struct perf_evsel *evsel; + struct evsel *evsel; size_t nr = 0, i = 0, sz, max_nr, n; int err; diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index 863dbad87849..79e97d17ea04 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -23,7 +23,7 @@ struct itrace_synth_opts; struct perf_session { struct perf_header header; struct machines machines; - struct perf_evlist *evlist; + struct evlist *evlist; struct auxtrace *auxtrace; struct itrace_synth_opts *itrace_synth_opts; struct list_head auxtrace_index; @@ -73,7 +73,7 @@ int perf_session__queue_event(struct perf_session *s, union perf_event *event, void perf_tool__fill_defaults(struct perf_tool *tool); int perf_session__resolve_callchain(struct perf_session *session, - struct perf_evsel *evsel, + struct evsel *evsel, struct thread *thread, struct ip_callchain *chain, struct symbol **parent); @@ -110,7 +110,7 @@ size_t perf_session__fprintf_dsos_buildid(struct perf_session *session, FILE *fp size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp); -struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session, +struct evsel *perf_session__find_first_evtype(struct perf_session *session, unsigned int type); int perf_session__cpu_bitmap(struct perf_session *session, @@ -118,10 +118,10 @@ int perf_session__cpu_bitmap(struct perf_session *session, void perf_session__fprintf_info(struct perf_session *s, FILE *fp, bool full); -struct perf_evsel_str_handler; +struct evsel_str_handler; int __perf_session__set_tracepoints_handlers(struct perf_session *session, - const struct perf_evsel_str_handler *assocs, + const struct evsel_str_handler *assocs, size_t nr_assocs); #define perf_session__set_tracepoints_handlers(session, array) \ @@ -140,7 +140,7 @@ int perf_event__process_id_index(struct perf_session *session, int perf_event__synthesize_id_index(struct perf_tool *tool, perf_event__handler_t process, - struct perf_evlist *evlist, + struct evlist *evlist, struct machine *machine); #endif /* __PERF_SESSION_H */ diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py index a1a68a2fa917..aa344a163eaf 100644 --- a/tools/perf/util/setup.py +++ b/tools/perf/util/setup.py @@ -48,6 +48,7 @@ build_lib = getenv('PYTHON_EXTBUILD_LIB') build_tmp = getenv('PYTHON_EXTBUILD_TMP') libtraceevent = getenv('LIBTRACEEVENT') libapikfs = getenv('LIBAPI') +libperf = getenv('LIBPERF') ext_sources = [f.strip() for f in open('util/python-ext-sources') if len(f.strip()) > 0 and f[0] != '#'] @@ -58,13 +59,15 @@ ext_sources = list(map(lambda x: '%s/%s' % (src_perf, x) , ext_sources)) extra_libraries = [] if '-DHAVE_LIBNUMA_SUPPORT' in cflags: extra_libraries = [ 'numa' ] +if '-DHAVE_LIBCAP_SUPPORT' in cflags: + extra_libraries += [ 'cap' ] perf = Extension('perf', sources = ext_sources, include_dirs = ['util/include'], libraries = extra_libraries, extra_compile_args = cflags, - extra_objects = [libtraceevent, libapikfs], + extra_objects = [libtraceevent, libapikfs, libperf], ) setup(name='perf', diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 5d2518e89fc4..f9a38a1dd4d1 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -698,7 +698,7 @@ struct sort_entry sort_time = { static char *get_trace_output(struct hist_entry *he) { struct trace_seq seq; - struct perf_evsel *evsel; + struct evsel *evsel; struct tep_record rec = { .data = he->raw_data, .size = he->raw_size, @@ -723,10 +723,10 @@ static char *get_trace_output(struct hist_entry *he) static int64_t sort__trace_cmp(struct hist_entry *left, struct hist_entry *right) { - struct perf_evsel *evsel; + struct evsel *evsel; evsel = hists_to_evsel(left->hists); - if (evsel->attr.type != PERF_TYPE_TRACEPOINT) + if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT) return 0; if (left->trace_output == NULL) @@ -740,10 +740,10 @@ sort__trace_cmp(struct hist_entry *left, struct hist_entry *right) static int hist_entry__trace_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - struct perf_evsel *evsel; + struct evsel *evsel; evsel = hists_to_evsel(he->hists); - if (evsel->attr.type != PERF_TYPE_TRACEPOINT) + if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT) return scnprintf(bf, size, "%-.*s", width, "N/A"); if (he->trace_output == NULL) @@ -1984,7 +1984,7 @@ static int __sort_dimension__add_hpp_output(struct sort_dimension *sd, struct hpp_dynamic_entry { struct perf_hpp_fmt hpp; - struct perf_evsel *evsel; + struct evsel *evsel; struct tep_format_field *field; unsigned dynamic_len; bool raw_trace; @@ -2218,7 +2218,7 @@ static void hde_free(struct perf_hpp_fmt *fmt) } static struct hpp_dynamic_entry * -__alloc_dynamic_entry(struct perf_evsel *evsel, struct tep_format_field *field, +__alloc_dynamic_entry(struct evsel *evsel, struct tep_format_field *field, int level) { struct hpp_dynamic_entry *hde; @@ -2313,17 +2313,17 @@ static int parse_field_name(char *str, char **event, char **field, char **opt) * 2. full event name (e.g. sched:sched_switch) * 3. partial event name (should not contain ':') */ -static struct perf_evsel *find_evsel(struct perf_evlist *evlist, char *event_name) +static struct evsel *find_evsel(struct evlist *evlist, char *event_name) { - struct perf_evsel *evsel = NULL; - struct perf_evsel *pos; + struct evsel *evsel = NULL; + struct evsel *pos; bool full_name; /* case 1 */ if (event_name[0] == '%') { int nr = strtol(event_name+1, NULL, 0); - if (nr > evlist->nr_entries) + if (nr > evlist->core.nr_entries) return NULL; evsel = perf_evlist__first(evlist); @@ -2352,7 +2352,7 @@ static struct perf_evsel *find_evsel(struct perf_evlist *evlist, char *event_nam return evsel; } -static int __dynamic_dimension__add(struct perf_evsel *evsel, +static int __dynamic_dimension__add(struct evsel *evsel, struct tep_format_field *field, bool raw_trace, int level) { @@ -2368,7 +2368,7 @@ static int __dynamic_dimension__add(struct perf_evsel *evsel, return 0; } -static int add_evsel_fields(struct perf_evsel *evsel, bool raw_trace, int level) +static int add_evsel_fields(struct evsel *evsel, bool raw_trace, int level) { int ret; struct tep_format_field *field; @@ -2384,14 +2384,14 @@ static int add_evsel_fields(struct perf_evsel *evsel, bool raw_trace, int level) return 0; } -static int add_all_dynamic_fields(struct perf_evlist *evlist, bool raw_trace, +static int add_all_dynamic_fields(struct evlist *evlist, bool raw_trace, int level) { int ret; - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { - if (evsel->attr.type != PERF_TYPE_TRACEPOINT) + if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT) continue; ret = add_evsel_fields(evsel, raw_trace, level); @@ -2401,15 +2401,15 @@ static int add_all_dynamic_fields(struct perf_evlist *evlist, bool raw_trace, return 0; } -static int add_all_matching_fields(struct perf_evlist *evlist, +static int add_all_matching_fields(struct evlist *evlist, char *field_name, bool raw_trace, int level) { int ret = -ESRCH; - struct perf_evsel *evsel; + struct evsel *evsel; struct tep_format_field *field; evlist__for_each_entry(evlist, evsel) { - if (evsel->attr.type != PERF_TYPE_TRACEPOINT) + if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT) continue; field = tep_find_any_field(evsel->tp_format, field_name); @@ -2423,11 +2423,11 @@ static int add_all_matching_fields(struct perf_evlist *evlist, return ret; } -static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok, +static int add_dynamic_entry(struct evlist *evlist, const char *tok, int level) { char *str, *event_name, *field_name, *opt_name; - struct perf_evsel *evsel; + struct evsel *evsel; struct tep_format_field *field; bool raw_trace = symbol_conf.raw_trace; int ret = 0; @@ -2470,7 +2470,7 @@ static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok, goto out; } - if (evsel->attr.type != PERF_TYPE_TRACEPOINT) { + if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT) { pr_debug("%s is not a tracepoint event\n", event_name); ret = -EINVAL; goto out; @@ -2567,7 +2567,7 @@ int hpp_dimension__add_output(unsigned col) } int sort_dimension__add(struct perf_hpp_list *list, const char *tok, - struct perf_evlist *evlist, + struct evlist *evlist, int level) { unsigned int i; @@ -2663,7 +2663,7 @@ int sort_dimension__add(struct perf_hpp_list *list, const char *tok, } static int setup_sort_list(struct perf_hpp_list *list, char *str, - struct perf_evlist *evlist) + struct evlist *evlist) { char *tmp, *tok; int ret = 0; @@ -2709,7 +2709,7 @@ static int setup_sort_list(struct perf_hpp_list *list, char *str, return ret; } -static const char *get_default_sort_order(struct perf_evlist *evlist) +static const char *get_default_sort_order(struct evlist *evlist) { const char *default_sort_orders[] = { default_sort_order, @@ -2720,7 +2720,7 @@ static const char *get_default_sort_order(struct perf_evlist *evlist) default_tracepoint_sort_order, }; bool use_trace = true; - struct perf_evsel *evsel; + struct evsel *evsel; BUG_ON(sort__mode >= ARRAY_SIZE(default_sort_orders)); @@ -2728,7 +2728,7 @@ static const char *get_default_sort_order(struct perf_evlist *evlist) goto out_no_evlist; evlist__for_each_entry(evlist, evsel) { - if (evsel->attr.type != PERF_TYPE_TRACEPOINT) { + if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT) { use_trace = false; break; } @@ -2743,7 +2743,7 @@ out_no_evlist: return default_sort_orders[sort__mode]; } -static int setup_sort_order(struct perf_evlist *evlist) +static int setup_sort_order(struct evlist *evlist) { char *new_sort_order; @@ -2804,7 +2804,7 @@ static char *setup_overhead(char *keys) return keys; } -static int __setup_sorting(struct perf_evlist *evlist) +static int __setup_sorting(struct evlist *evlist) { char *str; const char *sort_keys; @@ -3057,7 +3057,7 @@ out: return ret; } -int setup_sorting(struct perf_evlist *evlist) +int setup_sorting(struct evlist *evlist) { int err; diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index a0f232151d6f..5e34676a98e8 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -301,9 +301,9 @@ struct block_hist { extern struct sort_entry sort_thread; extern struct list_head hist_entry__sort_list; -struct perf_evlist; +struct evlist; struct tep_handle; -int setup_sorting(struct perf_evlist *evlist); +int setup_sorting(struct evlist *evlist); int setup_output_field(void); void reset_output_field(void); void sort__setup_elide(FILE *fp); @@ -318,7 +318,7 @@ bool is_strict_order(const char *order); int hpp_dimension__add_output(unsigned col); void reset_dimensions(void); int sort_dimension__add(struct perf_hpp_list *list, const char *tok, - struct perf_evlist *evlist, + struct evlist *evlist, int level); int output_field_add(struct perf_hpp_list *list, char *tok); int64_t diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 58df6a0dbb9f..51d6781aa90d 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -4,6 +4,7 @@ #include <linux/time64.h> #include <math.h> #include "color.h" +#include "counts.h" #include "evlist.h" #include "evsel.h" #include "stat.h" @@ -45,7 +46,7 @@ static void print_noise_pct(struct perf_stat_config *config, } static void print_noise(struct perf_stat_config *config, - struct perf_evsel *evsel, double avg) + struct evsel *evsel, double avg) { struct perf_stat_evsel *ps; @@ -56,7 +57,7 @@ static void print_noise(struct perf_stat_config *config, print_noise_pct(config, stddev_stats(&ps->res_stats[0]), avg); } -static void print_cgroup(struct perf_stat_config *config, struct perf_evsel *evsel) +static void print_cgroup(struct perf_stat_config *config, struct evsel *evsel) { if (nr_cgroups) { const char *cgrp_name = evsel->cgrp ? evsel->cgrp->name : ""; @@ -66,7 +67,7 @@ static void print_cgroup(struct perf_stat_config *config, struct perf_evsel *evs static void aggr_printout(struct perf_stat_config *config, - struct perf_evsel *evsel, int id, int nr) + struct evsel *evsel, int id, int nr) { switch (config->aggr_mode) { case AGGR_CORE: @@ -109,16 +110,16 @@ static void aggr_printout(struct perf_stat_config *config, } else { fprintf(config->output, "CPU%*d%s ", config->csv_output ? 0 : -5, - perf_evsel__cpus(evsel)->map[id], + evsel__cpus(evsel)->map[id], config->csv_sep); } break; case AGGR_THREAD: fprintf(config->output, "%*s-%*d%s", config->csv_output ? 0 : 16, - thread_map__comm(evsel->threads, id), + perf_thread_map__comm(evsel->core.threads, id), config->csv_output ? 0 : -8, - thread_map__pid(evsel->threads, id), + perf_thread_map__pid(evsel->core.threads, id), config->csv_sep); break; case AGGR_GLOBAL: @@ -134,7 +135,7 @@ struct outstate { const char *prefix; int nfields; int id, nr; - struct perf_evsel *evsel; + struct evsel *evsel; }; #define METRIC_LEN 35 @@ -233,7 +234,7 @@ static bool valid_only_metric(const char *unit) return true; } -static const char *fixunit(char *buf, struct perf_evsel *evsel, +static const char *fixunit(char *buf, struct evsel *evsel, const char *unit) { if (!strncmp(unit, "of all", 6)) { @@ -310,9 +311,9 @@ static void print_metric_header(struct perf_stat_config *config, } static int first_shadow_cpu(struct perf_stat_config *config, - struct perf_evsel *evsel, int id) + struct evsel *evsel, int id) { - struct perf_evlist *evlist = evsel->evlist; + struct evlist *evlist = evsel->evlist; int i; if (!config->aggr_get_id) @@ -325,16 +326,16 @@ static int first_shadow_cpu(struct perf_stat_config *config, return 0; for (i = 0; i < perf_evsel__nr_cpus(evsel); i++) { - int cpu2 = perf_evsel__cpus(evsel)->map[i]; + int cpu2 = evsel__cpus(evsel)->map[i]; - if (config->aggr_get_id(config, evlist->cpus, cpu2) == id) + if (config->aggr_get_id(config, evlist->core.cpus, cpu2) == id) return cpu2; } return 0; } static void abs_printout(struct perf_stat_config *config, - int id, int nr, struct perf_evsel *evsel, double avg) + int id, int nr, struct evsel *evsel, double avg) { FILE *output = config->output; double sc = evsel->scale; @@ -363,24 +364,24 @@ static void abs_printout(struct perf_stat_config *config, print_cgroup(config, evsel); } -static bool is_mixed_hw_group(struct perf_evsel *counter) +static bool is_mixed_hw_group(struct evsel *counter) { - struct perf_evlist *evlist = counter->evlist; - u32 pmu_type = counter->attr.type; - struct perf_evsel *pos; + struct evlist *evlist = counter->evlist; + u32 pmu_type = counter->core.attr.type; + struct evsel *pos; - if (counter->nr_members < 2) + if (counter->core.nr_members < 2) return false; evlist__for_each_entry(evlist, pos) { /* software events can be part of any hardware group */ - if (pos->attr.type == PERF_TYPE_SOFTWARE) + if (pos->core.attr.type == PERF_TYPE_SOFTWARE) continue; if (pmu_type == PERF_TYPE_SOFTWARE) { - pmu_type = pos->attr.type; + pmu_type = pos->core.attr.type; continue; } - if (pmu_type != pos->attr.type) + if (pmu_type != pos->core.attr.type) return true; } @@ -388,7 +389,7 @@ static bool is_mixed_hw_group(struct perf_evsel *counter) } static void printout(struct perf_stat_config *config, int id, int nr, - struct perf_evsel *counter, double uval, + struct evsel *counter, double uval, char *prefix, u64 run, u64 ena, double noise, struct runtime_stat *st) { @@ -489,18 +490,18 @@ static void printout(struct perf_stat_config *config, int id, int nr, } static void aggr_update_shadow(struct perf_stat_config *config, - struct perf_evlist *evlist) + struct evlist *evlist) { int cpu, s2, id, s; u64 val; - struct perf_evsel *counter; + struct evsel *counter; for (s = 0; s < config->aggr_map->nr; s++) { id = config->aggr_map->map[s]; evlist__for_each_entry(evlist, counter) { val = 0; for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) { - s2 = config->aggr_get_id(config, evlist->cpus, cpu); + s2 = config->aggr_get_id(config, evlist->core.cpus, cpu); if (s2 != id) continue; val += perf_counts(counter->counts, cpu, 0)->val; @@ -512,7 +513,7 @@ static void aggr_update_shadow(struct perf_stat_config *config, } } -static void uniquify_event_name(struct perf_evsel *counter) +static void uniquify_event_name(struct evsel *counter) { char *new_name; char *config; @@ -540,16 +541,16 @@ static void uniquify_event_name(struct perf_evsel *counter) counter->uniquified_name = true; } -static void collect_all_aliases(struct perf_stat_config *config, struct perf_evsel *counter, - void (*cb)(struct perf_stat_config *config, struct perf_evsel *counter, void *data, +static void collect_all_aliases(struct perf_stat_config *config, struct evsel *counter, + void (*cb)(struct perf_stat_config *config, struct evsel *counter, void *data, bool first), void *data) { - struct perf_evlist *evlist = counter->evlist; - struct perf_evsel *alias; + struct evlist *evlist = counter->evlist; + struct evsel *alias; - alias = list_prepare_entry(counter, &(evlist->entries), node); - list_for_each_entry_continue (alias, &evlist->entries, node) { + alias = list_prepare_entry(counter, &(evlist->core.entries), core.node); + list_for_each_entry_continue (alias, &evlist->core.entries, core.node) { if (strcmp(perf_evsel__name(alias), perf_evsel__name(counter)) || alias->scale != counter->scale || alias->cgrp != counter->cgrp || @@ -562,8 +563,8 @@ static void collect_all_aliases(struct perf_stat_config *config, struct perf_evs } } -static bool collect_data(struct perf_stat_config *config, struct perf_evsel *counter, - void (*cb)(struct perf_stat_config *config, struct perf_evsel *counter, void *data, +static bool collect_data(struct perf_stat_config *config, struct evsel *counter, + void (*cb)(struct perf_stat_config *config, struct evsel *counter, void *data, bool first), void *data) { @@ -585,7 +586,7 @@ struct aggr_data { }; static void aggr_cb(struct perf_stat_config *config, - struct perf_evsel *counter, void *data, bool first) + struct evsel *counter, void *data, bool first) { struct aggr_data *ad = data; int cpu, s2; @@ -593,7 +594,7 @@ static void aggr_cb(struct perf_stat_config *config, for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) { struct perf_counts_values *counts; - s2 = config->aggr_get_id(config, perf_evsel__cpus(counter), cpu); + s2 = config->aggr_get_id(config, evsel__cpus(counter), cpu); if (s2 != ad->id) continue; if (first) @@ -616,7 +617,7 @@ static void aggr_cb(struct perf_stat_config *config, } static void print_counter_aggrdata(struct perf_stat_config *config, - struct perf_evsel *counter, int s, + struct evsel *counter, int s, char *prefix, bool metric_only, bool *first) { @@ -651,12 +652,12 @@ static void print_counter_aggrdata(struct perf_stat_config *config, } static void print_aggr(struct perf_stat_config *config, - struct perf_evlist *evlist, + struct evlist *evlist, char *prefix) { bool metric_only = config->metric_only; FILE *output = config->output; - struct perf_evsel *counter; + struct evsel *counter; int s; bool first; @@ -691,7 +692,7 @@ static int cmp_val(const void *a, const void *b) } static struct perf_aggr_thread_value *sort_aggr_thread( - struct perf_evsel *counter, + struct evsel *counter, int nthreads, int ncpus, int *ret, struct target *_target) @@ -741,11 +742,11 @@ static struct perf_aggr_thread_value *sort_aggr_thread( static void print_aggr_thread(struct perf_stat_config *config, struct target *_target, - struct perf_evsel *counter, char *prefix) + struct evsel *counter, char *prefix) { FILE *output = config->output; - int nthreads = thread_map__nr(counter->threads); - int ncpus = cpu_map__nr(counter->cpus); + int nthreads = perf_thread_map__nr(counter->core.threads); + int ncpus = perf_cpu_map__nr(counter->core.cpus); int thread, sorted_threads, id; struct perf_aggr_thread_value *buf; @@ -779,7 +780,7 @@ struct caggr_data { }; static void counter_aggr_cb(struct perf_stat_config *config __maybe_unused, - struct perf_evsel *counter, void *data, + struct evsel *counter, void *data, bool first __maybe_unused) { struct caggr_data *cd = data; @@ -795,7 +796,7 @@ static void counter_aggr_cb(struct perf_stat_config *config __maybe_unused, * aggregated counts in system-wide mode */ static void print_counter_aggr(struct perf_stat_config *config, - struct perf_evsel *counter, char *prefix) + struct evsel *counter, char *prefix) { bool metric_only = config->metric_only; FILE *output = config->output; @@ -816,7 +817,7 @@ static void print_counter_aggr(struct perf_stat_config *config, } static void counter_cb(struct perf_stat_config *config __maybe_unused, - struct perf_evsel *counter, void *data, + struct evsel *counter, void *data, bool first __maybe_unused) { struct aggr_data *ad = data; @@ -831,7 +832,7 @@ static void counter_cb(struct perf_stat_config *config __maybe_unused, * does not use aggregated count in system-wide */ static void print_counter(struct perf_stat_config *config, - struct perf_evsel *counter, char *prefix) + struct evsel *counter, char *prefix) { FILE *output = config->output; u64 ena, run, val; @@ -859,16 +860,16 @@ static void print_counter(struct perf_stat_config *config, } static void print_no_aggr_metric(struct perf_stat_config *config, - struct perf_evlist *evlist, + struct evlist *evlist, char *prefix) { int cpu; int nrcpus = 0; - struct perf_evsel *counter; + struct evsel *counter; u64 ena, run, val; double uval; - nrcpus = evlist->cpus->nr; + nrcpus = evlist->core.cpus->nr; for (cpu = 0; cpu < nrcpus; cpu++) { bool first = true; @@ -910,11 +911,11 @@ static const char *aggr_header_csv[] = { }; static void print_metric_headers(struct perf_stat_config *config, - struct perf_evlist *evlist, + struct evlist *evlist, const char *prefix, bool no_indent) { struct perf_stat_output_ctx out; - struct perf_evsel *counter; + struct evsel *counter; struct outstate os = { .fh = config->output }; @@ -949,7 +950,7 @@ static void print_metric_headers(struct perf_stat_config *config, } static void print_interval(struct perf_stat_config *config, - struct perf_evlist *evlist, + struct evlist *evlist, char *prefix, struct timespec *ts) { bool metric_only = config->metric_only; @@ -1132,7 +1133,7 @@ static void print_footer(struct perf_stat_config *config) } static void print_percore(struct perf_stat_config *config, - struct perf_evsel *counter, char *prefix) + struct evsel *counter, char *prefix) { bool metric_only = config->metric_only; FILE *output = config->output; @@ -1156,7 +1157,7 @@ static void print_percore(struct perf_stat_config *config, } void -perf_evlist__print_counters(struct perf_evlist *evlist, +perf_evlist__print_counters(struct evlist *evlist, struct perf_stat_config *config, struct target *_target, struct timespec *ts, @@ -1164,7 +1165,7 @@ perf_evlist__print_counters(struct perf_evlist *evlist, { bool metric_only = config->metric_only; int interval = config->interval; - struct perf_evsel *counter; + struct evsel *counter; char buf[64], *prefix = NULL; if (interval) diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index accb1bf1cfd8..2ed5e0066c70 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -25,7 +25,7 @@ struct stats walltime_nsecs_stats; struct saved_value { struct rb_node rb_node; - struct perf_evsel *evsel; + struct evsel *evsel; enum stat_type type; int ctx; int cpu; @@ -94,7 +94,7 @@ static void saved_value_delete(struct rblist *rblist __maybe_unused, free(v); } -static struct saved_value *saved_value_lookup(struct perf_evsel *evsel, +static struct saved_value *saved_value_lookup(struct evsel *evsel, int cpu, bool create, enum stat_type type, @@ -146,19 +146,19 @@ void perf_stat__init_shadow_stats(void) runtime_stat__init(&rt_stat); } -static int evsel_context(struct perf_evsel *evsel) +static int evsel_context(struct evsel *evsel) { int ctx = 0; - if (evsel->attr.exclude_kernel) + if (evsel->core.attr.exclude_kernel) ctx |= CTX_BIT_KERNEL; - if (evsel->attr.exclude_user) + if (evsel->core.attr.exclude_user) ctx |= CTX_BIT_USER; - if (evsel->attr.exclude_hv) + if (evsel->core.attr.exclude_hv) ctx |= CTX_BIT_HV; - if (evsel->attr.exclude_host) + if (evsel->core.attr.exclude_host) ctx |= CTX_BIT_HOST; - if (evsel->attr.exclude_idle) + if (evsel->core.attr.exclude_idle) ctx |= CTX_BIT_IDLE; return ctx; @@ -207,7 +207,7 @@ static void update_runtime_stat(struct runtime_stat *st, * more semantic information such as miss/hit ratios, * instruction rates, etc: */ -void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 count, +void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, int cpu, struct runtime_stat *st) { int ctx = evsel_context(counter); @@ -299,10 +299,10 @@ static const char *get_ratio_color(enum grc_type type, double ratio) return color; } -static struct perf_evsel *perf_stat__find_event(struct perf_evlist *evsel_list, +static struct evsel *perf_stat__find_event(struct evlist *evsel_list, const char *name) { - struct perf_evsel *c2; + struct evsel *c2; evlist__for_each_entry (evsel_list, c2) { if (!strcasecmp(c2->name, name) && !c2->collect_stat) @@ -312,9 +312,9 @@ static struct perf_evsel *perf_stat__find_event(struct perf_evlist *evsel_list, } /* Mark MetricExpr target events and link events using them to them. */ -void perf_stat__collect_metric_expr(struct perf_evlist *evsel_list) +void perf_stat__collect_metric_expr(struct evlist *evsel_list) { - struct perf_evsel *counter, *leader, **metric_events, *oc; + struct evsel *counter, *leader, **metric_events, *oc; bool found; const char **metric_names; int i; @@ -332,7 +332,7 @@ void perf_stat__collect_metric_expr(struct perf_evlist *evsel_list) &metric_names, &num_metric_names) < 0) continue; - metric_events = calloc(sizeof(struct perf_evsel *), + metric_events = calloc(sizeof(struct evsel *), num_metric_names + 1); if (!metric_events) return; @@ -415,7 +415,7 @@ static double runtime_stat_n(struct runtime_stat *st, static void print_stalled_cycles_frontend(struct perf_stat_config *config, int cpu, - struct perf_evsel *evsel, double avg, + struct evsel *evsel, double avg, struct perf_stat_output_ctx *out, struct runtime_stat *st) { @@ -439,7 +439,7 @@ static void print_stalled_cycles_frontend(struct perf_stat_config *config, static void print_stalled_cycles_backend(struct perf_stat_config *config, int cpu, - struct perf_evsel *evsel, double avg, + struct evsel *evsel, double avg, struct perf_stat_output_ctx *out, struct runtime_stat *st) { @@ -459,7 +459,7 @@ static void print_stalled_cycles_backend(struct perf_stat_config *config, static void print_branch_misses(struct perf_stat_config *config, int cpu, - struct perf_evsel *evsel, + struct evsel *evsel, double avg, struct perf_stat_output_ctx *out, struct runtime_stat *st) @@ -480,7 +480,7 @@ static void print_branch_misses(struct perf_stat_config *config, static void print_l1_dcache_misses(struct perf_stat_config *config, int cpu, - struct perf_evsel *evsel, + struct evsel *evsel, double avg, struct perf_stat_output_ctx *out, struct runtime_stat *st) @@ -502,7 +502,7 @@ static void print_l1_dcache_misses(struct perf_stat_config *config, static void print_l1_icache_misses(struct perf_stat_config *config, int cpu, - struct perf_evsel *evsel, + struct evsel *evsel, double avg, struct perf_stat_output_ctx *out, struct runtime_stat *st) @@ -523,7 +523,7 @@ static void print_l1_icache_misses(struct perf_stat_config *config, static void print_dtlb_cache_misses(struct perf_stat_config *config, int cpu, - struct perf_evsel *evsel, + struct evsel *evsel, double avg, struct perf_stat_output_ctx *out, struct runtime_stat *st) @@ -543,7 +543,7 @@ static void print_dtlb_cache_misses(struct perf_stat_config *config, static void print_itlb_cache_misses(struct perf_stat_config *config, int cpu, - struct perf_evsel *evsel, + struct evsel *evsel, double avg, struct perf_stat_output_ctx *out, struct runtime_stat *st) @@ -563,7 +563,7 @@ static void print_itlb_cache_misses(struct perf_stat_config *config, static void print_ll_cache_misses(struct perf_stat_config *config, int cpu, - struct perf_evsel *evsel, + struct evsel *evsel, double avg, struct perf_stat_output_ctx *out, struct runtime_stat *st) @@ -686,7 +686,7 @@ static double td_be_bound(int ctx, int cpu, struct runtime_stat *st) } static void print_smi_cost(struct perf_stat_config *config, - int cpu, struct perf_evsel *evsel, + int cpu, struct evsel *evsel, struct perf_stat_output_ctx *out, struct runtime_stat *st) { @@ -712,7 +712,7 @@ static void print_smi_cost(struct perf_stat_config *config, static void generic_metric(struct perf_stat_config *config, const char *metric_expr, - struct perf_evsel **metric_events, + struct evsel **metric_events, char *name, const char *metric_name, double avg, @@ -780,7 +780,7 @@ static void generic_metric(struct perf_stat_config *config, } void perf_stat__print_shadow_stats(struct perf_stat_config *config, - struct perf_evsel *evsel, + struct evsel *evsel, double avg, int cpu, struct perf_stat_output_ctx *out, struct rblist *metric_events, @@ -829,8 +829,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, else print_metric(config, ctxp, NULL, NULL, "of all branches", 0); } else if ( - evsel->attr.type == PERF_TYPE_HW_CACHE && - evsel->attr.config == ( PERF_COUNT_HW_CACHE_L1D | + evsel->core.attr.type == PERF_TYPE_HW_CACHE && + evsel->core.attr.config == ( PERF_COUNT_HW_CACHE_L1D | ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { @@ -839,8 +839,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, else print_metric(config, ctxp, NULL, NULL, "of all L1-dcache hits", 0); } else if ( - evsel->attr.type == PERF_TYPE_HW_CACHE && - evsel->attr.config == ( PERF_COUNT_HW_CACHE_L1I | + evsel->core.attr.type == PERF_TYPE_HW_CACHE && + evsel->core.attr.config == ( PERF_COUNT_HW_CACHE_L1I | ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { @@ -849,8 +849,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, else print_metric(config, ctxp, NULL, NULL, "of all L1-icache hits", 0); } else if ( - evsel->attr.type == PERF_TYPE_HW_CACHE && - evsel->attr.config == ( PERF_COUNT_HW_CACHE_DTLB | + evsel->core.attr.type == PERF_TYPE_HW_CACHE && + evsel->core.attr.config == ( PERF_COUNT_HW_CACHE_DTLB | ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { @@ -859,8 +859,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, else print_metric(config, ctxp, NULL, NULL, "of all dTLB cache hits", 0); } else if ( - evsel->attr.type == PERF_TYPE_HW_CACHE && - evsel->attr.config == ( PERF_COUNT_HW_CACHE_ITLB | + evsel->core.attr.type == PERF_TYPE_HW_CACHE && + evsel->core.attr.config == ( PERF_COUNT_HW_CACHE_ITLB | ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { @@ -869,8 +869,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, else print_metric(config, ctxp, NULL, NULL, "of all iTLB cache hits", 0); } else if ( - evsel->attr.type == PERF_TYPE_HW_CACHE && - evsel->attr.config == ( PERF_COUNT_HW_CACHE_LL | + evsel->core.attr.type == PERF_TYPE_HW_CACHE && + evsel->core.attr.config == ( PERF_COUNT_HW_CACHE_LL | ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index db8a6cf336be..0cbfd1eca1dd 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -2,6 +2,7 @@ #include <errno.h> #include <inttypes.h> #include <math.h> +#include "counts.h" #include "stat.h" #include "evlist.h" #include "evsel.h" @@ -68,7 +69,7 @@ double rel_stddev_stats(double stddev, double avg) return pct; } -bool __perf_evsel_stat__is(struct perf_evsel *evsel, +bool __perf_evsel_stat__is(struct evsel *evsel, enum perf_stat_evsel_id id) { struct perf_stat_evsel *ps = evsel->stats; @@ -93,7 +94,7 @@ static const char *id_str[PERF_STAT_EVSEL_ID__MAX] = { }; #undef ID -static void perf_stat_evsel_id_init(struct perf_evsel *evsel) +static void perf_stat_evsel_id_init(struct evsel *evsel) { struct perf_stat_evsel *ps = evsel->stats; int i; @@ -108,7 +109,7 @@ static void perf_stat_evsel_id_init(struct perf_evsel *evsel) } } -static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel) +static void perf_evsel__reset_stat_priv(struct evsel *evsel) { int i; struct perf_stat_evsel *ps = evsel->stats; @@ -119,7 +120,7 @@ static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel) perf_stat_evsel_id_init(evsel); } -static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel) +static int perf_evsel__alloc_stat_priv(struct evsel *evsel) { evsel->stats = zalloc(sizeof(struct perf_stat_evsel)); if (evsel->stats == NULL) @@ -128,7 +129,7 @@ static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel) return 0; } -static void perf_evsel__free_stat_priv(struct perf_evsel *evsel) +static void perf_evsel__free_stat_priv(struct evsel *evsel) { struct perf_stat_evsel *ps = evsel->stats; @@ -137,7 +138,7 @@ static void perf_evsel__free_stat_priv(struct perf_evsel *evsel) zfree(&evsel->stats); } -static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel, +static int perf_evsel__alloc_prev_raw_counts(struct evsel *evsel, int ncpus, int nthreads) { struct perf_counts *counts; @@ -149,16 +150,16 @@ static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel, return counts ? 0 : -ENOMEM; } -static void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel) +static void perf_evsel__free_prev_raw_counts(struct evsel *evsel) { perf_counts__delete(evsel->prev_raw_counts); evsel->prev_raw_counts = NULL; } -static int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw) +static int perf_evsel__alloc_stats(struct evsel *evsel, bool alloc_raw) { int ncpus = perf_evsel__nr_cpus(evsel); - int nthreads = thread_map__nr(evsel->threads); + int nthreads = perf_thread_map__nr(evsel->core.threads); if (perf_evsel__alloc_stat_priv(evsel) < 0 || perf_evsel__alloc_counts(evsel, ncpus, nthreads) < 0 || @@ -168,9 +169,9 @@ static int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw) return 0; } -int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw) +int perf_evlist__alloc_stats(struct evlist *evlist, bool alloc_raw) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { if (perf_evsel__alloc_stats(evsel, alloc_raw)) @@ -184,9 +185,9 @@ out_free: return -1; } -void perf_evlist__free_stats(struct perf_evlist *evlist) +void perf_evlist__free_stats(struct evlist *evlist) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { perf_evsel__free_stat_priv(evsel); @@ -195,9 +196,9 @@ void perf_evlist__free_stats(struct perf_evlist *evlist) } } -void perf_evlist__reset_stats(struct perf_evlist *evlist) +void perf_evlist__reset_stats(struct evlist *evlist) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { perf_evsel__reset_stat_priv(evsel); @@ -205,17 +206,17 @@ void perf_evlist__reset_stats(struct perf_evlist *evlist) } } -static void zero_per_pkg(struct perf_evsel *counter) +static void zero_per_pkg(struct evsel *counter) { if (counter->per_pkg_mask) memset(counter->per_pkg_mask, 0, MAX_NR_CPUS); } -static int check_per_pkg(struct perf_evsel *counter, +static int check_per_pkg(struct evsel *counter, struct perf_counts_values *vals, int cpu, bool *skip) { unsigned long *mask = counter->per_pkg_mask; - struct cpu_map *cpus = perf_evsel__cpus(counter); + struct perf_cpu_map *cpus = evsel__cpus(counter); int s; *skip = false; @@ -223,7 +224,7 @@ static int check_per_pkg(struct perf_evsel *counter, if (!counter->per_pkg) return 0; - if (cpu_map__empty(cpus)) + if (perf_cpu_map__empty(cpus)) return 0; if (!mask) { @@ -254,7 +255,7 @@ static int check_per_pkg(struct perf_evsel *counter, } static int -process_counter_values(struct perf_stat_config *config, struct perf_evsel *evsel, +process_counter_values(struct perf_stat_config *config, struct evsel *evsel, int cpu, int thread, struct perf_counts_values *count) { @@ -306,9 +307,9 @@ process_counter_values(struct perf_stat_config *config, struct perf_evsel *evsel } static int process_counter_maps(struct perf_stat_config *config, - struct perf_evsel *counter) + struct evsel *counter) { - int nthreads = thread_map__nr(counter->threads); + int nthreads = perf_thread_map__nr(counter->core.threads); int ncpus = perf_evsel__nr_cpus(counter); int cpu, thread; @@ -327,7 +328,7 @@ static int process_counter_maps(struct perf_stat_config *config, } int perf_stat_process_counter(struct perf_stat_config *config, - struct perf_evsel *counter) + struct evsel *counter) { struct perf_counts_values *aggr = &counter->counts->aggr; struct perf_stat_evsel *ps = counter->stats; @@ -381,7 +382,7 @@ int perf_event__process_stat_event(struct perf_session *session, { struct perf_counts_values count; struct stat_event *st = &event->stat; - struct perf_evsel *counter; + struct evsel *counter; count.val = st->val; count.ena = st->ena; @@ -437,12 +438,12 @@ size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp) return ret; } -int create_perf_stat_counter(struct perf_evsel *evsel, +int create_perf_stat_counter(struct evsel *evsel, struct perf_stat_config *config, struct target *target) { - struct perf_event_attr *attr = &evsel->attr; - struct perf_evsel *leader = evsel->leader; + struct perf_event_attr *attr = &evsel->core.attr; + struct evsel *leader = evsel->leader; attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED | PERF_FORMAT_TOTAL_TIME_RUNNING; @@ -452,7 +453,7 @@ int create_perf_stat_counter(struct perf_evsel *evsel, * the group read (for leader) and ID retrieval for all * members. */ - if (leader->nr_members > 1) + if (leader->core.nr_members > 1) attr->read_format |= PERF_FORMAT_ID|PERF_FORMAT_GROUP; attr->inherit = !config->no_inherit; @@ -483,14 +484,14 @@ int create_perf_stat_counter(struct perf_evsel *evsel, } if (target__has_cpu(target) && !target__has_per_thread(target)) - return perf_evsel__open_per_cpu(evsel, perf_evsel__cpus(evsel)); + return perf_evsel__open_per_cpu(evsel, evsel__cpus(evsel)); - return perf_evsel__open_per_thread(evsel, evsel->threads); + return perf_evsel__open_per_thread(evsel, evsel->core.threads); } int perf_stat_synthesize_config(struct perf_stat_config *config, struct perf_tool *tool, - struct perf_evlist *evlist, + struct evlist *evlist, perf_event__handler_t process, bool attrs) { @@ -507,14 +508,14 @@ int perf_stat_synthesize_config(struct perf_stat_config *config, err = perf_event__synthesize_extra_attr(tool, evlist, process, attrs); - err = perf_event__synthesize_thread_map2(tool, evlist->threads, + err = perf_event__synthesize_thread_map2(tool, evlist->core.threads, process, NULL); if (err < 0) { pr_err("Couldn't synthesize thread map.\n"); return err; } - err = perf_event__synthesize_cpu_map(tool, evlist->cpus, + err = perf_event__synthesize_cpu_map(tool, evlist->core.cpus, process, NULL); if (err < 0) { pr_err("Couldn't synthesize thread map.\n"); diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index 7032dd1eeac2..bcb376e1b3a7 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -8,7 +8,6 @@ #include <sys/time.h> #include <sys/resource.h> #include <sys/wait.h> -#include "xyarray.h" #include "rblist.h" #include "perf.h" #include "event.h" @@ -92,7 +91,7 @@ struct runtime_stat { }; typedef int (*aggr_get_id_t)(struct perf_stat_config *config, - struct cpu_map *m, int cpu); + struct perf_cpu_map *m, int cpu); struct perf_stat_config { enum aggr_mode aggr_mode; @@ -122,9 +121,9 @@ struct perf_stat_config { const char *csv_sep; struct stats *walltime_nsecs_stats; struct rusage ru_data; - struct cpu_map *aggr_map; + struct perf_cpu_map *aggr_map; aggr_get_id_t aggr_get_id; - struct cpu_map *cpus_aggr_map; + struct perf_cpu_map *cpus_aggr_map; u64 *walltime_run; struct rblist metric_events; }; @@ -143,11 +142,11 @@ static inline void init_stats(struct stats *stats) stats->max = 0; } -struct perf_evsel; -struct perf_evlist; +struct evsel; +struct evlist; struct perf_aggr_thread_value { - struct perf_evsel *counter; + struct evsel *counter; int id; double uval; u64 val; @@ -155,7 +154,7 @@ struct perf_aggr_thread_value { u64 ena; }; -bool __perf_evsel_stat__is(struct perf_evsel *evsel, +bool __perf_evsel_stat__is(struct evsel *evsel, enum perf_stat_evsel_id id); #define perf_stat_evsel__is(evsel, id) \ @@ -174,7 +173,7 @@ void runtime_stat__exit(struct runtime_stat *st); void perf_stat__init_shadow_stats(void); void perf_stat__reset_shadow_stats(void); void perf_stat__reset_shadow_per_stat(struct runtime_stat *st); -void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 count, +void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, int cpu, struct runtime_stat *st); struct perf_stat_output_ctx { void *ctx; @@ -184,19 +183,19 @@ struct perf_stat_output_ctx { }; void perf_stat__print_shadow_stats(struct perf_stat_config *config, - struct perf_evsel *evsel, + struct evsel *evsel, double avg, int cpu, struct perf_stat_output_ctx *out, struct rblist *metric_events, struct runtime_stat *st); -void perf_stat__collect_metric_expr(struct perf_evlist *); +void perf_stat__collect_metric_expr(struct evlist *); -int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw); -void perf_evlist__free_stats(struct perf_evlist *evlist); -void perf_evlist__reset_stats(struct perf_evlist *evlist); +int perf_evlist__alloc_stats(struct evlist *evlist, bool alloc_raw); +void perf_evlist__free_stats(struct evlist *evlist); +void perf_evlist__reset_stats(struct evlist *evlist); int perf_stat_process_counter(struct perf_stat_config *config, - struct perf_evsel *counter); + struct evsel *counter); struct perf_tool; union perf_event; struct perf_session; @@ -207,16 +206,16 @@ size_t perf_event__fprintf_stat(union perf_event *event, FILE *fp); size_t perf_event__fprintf_stat_round(union perf_event *event, FILE *fp); size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp); -int create_perf_stat_counter(struct perf_evsel *evsel, +int create_perf_stat_counter(struct evsel *evsel, struct perf_stat_config *config, struct target *target); int perf_stat_synthesize_config(struct perf_stat_config *config, struct perf_tool *tool, - struct perf_evlist *evlist, + struct evlist *evlist, perf_event__handler_t process, bool attrs); void -perf_evlist__print_counters(struct perf_evlist *evlist, +perf_evlist__print_counters(struct evlist *evlist, struct perf_stat_config *config, struct target *_target, struct timespec *ts, diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c index 76cc54000483..bbdd87163285 100644 --- a/tools/perf/util/svghelper.c +++ b/tools/perf/util/svghelper.c @@ -14,8 +14,10 @@ #include <unistd.h> #include <string.h> #include <linux/bitmap.h> +#include <linux/string.h> #include <linux/time64.h> #include <linux/zalloc.h> +#include <perf/cpumap.h> #include "perf.h" #include "svghelper.h" @@ -728,10 +730,10 @@ static int str_to_bitmap(char *s, cpumask_t *b) { int i; int ret = 0; - struct cpu_map *m; + struct perf_cpu_map *m; int c; - m = cpu_map__new(s); + m = perf_cpu_map__new(s); if (!m) return -1; @@ -745,7 +747,7 @@ static int str_to_bitmap(char *s, cpumask_t *b) set_bit(c, cpumask_bits(b)); } - cpu_map__put(m); + perf_cpu_map__put(m); return ret; } diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c index 022a9c670338..820fceeb19a9 100644 --- a/tools/perf/util/syscalltbl.c +++ b/tools/perf/util/syscalltbl.c @@ -79,6 +79,7 @@ static int syscalltbl__init_native(struct syscalltbl *tbl) qsort(tbl->syscalls.entries, nr_entries, sizeof(struct syscall), syscallcmp); tbl->syscalls.nr_entries = nr_entries; + tbl->syscalls.max_id = syscalltbl_native_max_id; return 0; } diff --git a/tools/perf/util/syscalltbl.h b/tools/perf/util/syscalltbl.h index c8e7e9ce0f01..9172613028d0 100644 --- a/tools/perf/util/syscalltbl.h +++ b/tools/perf/util/syscalltbl.h @@ -6,6 +6,7 @@ struct syscalltbl { union { int audit_machine; struct { + int max_id; int nr_entries; void *entries; } syscalls; diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 590793cc5142..bbf7816cba31 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -105,7 +105,6 @@ void thread__delete(struct thread *thread) } up_write(&thread->comm_lock); - unwind__finish_access(thread); nsinfo__zput(thread->nsinfo); srccode_state_free(&thread->srccode_state); @@ -252,7 +251,7 @@ static int ____thread__set_comm(struct thread *thread, const char *str, list_add(&new->list, &thread->comm_list); if (exec) - unwind__flush_access(thread); + unwind__flush_access(thread->mg); } thread->comm_set = true; @@ -332,7 +331,7 @@ int thread__insert_map(struct thread *thread, struct map *map) { int ret; - ret = unwind__prepare_access(thread, map, NULL); + ret = unwind__prepare_access(thread->mg, map, NULL); if (ret) return ret; @@ -352,7 +351,7 @@ static int __thread__prepare_access(struct thread *thread) down_read(&maps->lock); for (map = maps__first(maps); map; map = map__next(map)) { - err = unwind__prepare_access(thread, map, &initialized); + err = unwind__prepare_access(thread->mg, map, &initialized); if (err || initialized) break; } diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index e97ef6977eb9..bf06113be4f3 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -44,10 +44,6 @@ struct thread { struct thread_stack *ts; struct nsinfo *nsinfo; struct srccode_state srccode_state; -#ifdef HAVE_LIBUNWIND_SUPPORT - void *addr_space; - struct unwind_libunwind_ops *unwind_libunwind_ops; -#endif bool filter; int filter_entry_depth; }; diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c index 5b3511f2b6b1..3e64525bf604 100644 --- a/tools/perf/util/thread_map.c +++ b/tools/perf/util/thread_map.c @@ -28,34 +28,11 @@ static int filter(const struct dirent *dir) return 1; } -static void thread_map__reset(struct thread_map *map, int start, int nr) -{ - size_t size = (nr - start) * sizeof(map->map[0]); - - memset(&map->map[start], 0, size); - map->err_thread = -1; -} +#define thread_map__alloc(__nr) perf_thread_map__realloc(NULL, __nr) -static struct thread_map *thread_map__realloc(struct thread_map *map, int nr) +struct perf_thread_map *thread_map__new_by_pid(pid_t pid) { - size_t size = sizeof(*map) + sizeof(map->map[0]) * nr; - int start = map ? map->nr : 0; - - map = realloc(map, size); - /* - * We only realloc to add more items, let's reset new items. - */ - if (map) - thread_map__reset(map, start, nr); - - return map; -} - -#define thread_map__alloc(__nr) thread_map__realloc(NULL, __nr) - -struct thread_map *thread_map__new_by_pid(pid_t pid) -{ - struct thread_map *threads; + struct perf_thread_map *threads; char name[256]; int items; struct dirent **namelist = NULL; @@ -69,7 +46,7 @@ struct thread_map *thread_map__new_by_pid(pid_t pid) threads = thread_map__alloc(items); if (threads != NULL) { for (i = 0; i < items; i++) - thread_map__set_pid(threads, i, atoi(namelist[i]->d_name)); + perf_thread_map__set_pid(threads, i, atoi(namelist[i]->d_name)); threads->nr = items; refcount_set(&threads->refcnt, 1); } @@ -81,12 +58,12 @@ struct thread_map *thread_map__new_by_pid(pid_t pid) return threads; } -struct thread_map *thread_map__new_by_tid(pid_t tid) +struct perf_thread_map *thread_map__new_by_tid(pid_t tid) { - struct thread_map *threads = thread_map__alloc(1); + struct perf_thread_map *threads = thread_map__alloc(1); if (threads != NULL) { - thread_map__set_pid(threads, 0, tid); + perf_thread_map__set_pid(threads, 0, tid); threads->nr = 1; refcount_set(&threads->refcnt, 1); } @@ -94,13 +71,13 @@ struct thread_map *thread_map__new_by_tid(pid_t tid) return threads; } -static struct thread_map *__thread_map__new_all_cpus(uid_t uid) +static struct perf_thread_map *__thread_map__new_all_cpus(uid_t uid) { DIR *proc; int max_threads = 32, items, i; char path[NAME_MAX + 1 + 6]; struct dirent *dirent, **namelist = NULL; - struct thread_map *threads = thread_map__alloc(max_threads); + struct perf_thread_map *threads = thread_map__alloc(max_threads); if (threads == NULL) goto out; @@ -140,9 +117,9 @@ static struct thread_map *__thread_map__new_all_cpus(uid_t uid) } if (grow) { - struct thread_map *tmp; + struct perf_thread_map *tmp; - tmp = thread_map__realloc(threads, max_threads); + tmp = perf_thread_map__realloc(threads, max_threads); if (tmp == NULL) goto out_free_namelist; @@ -150,8 +127,8 @@ static struct thread_map *__thread_map__new_all_cpus(uid_t uid) } for (i = 0; i < items; i++) { - thread_map__set_pid(threads, threads->nr + i, - atoi(namelist[i]->d_name)); + perf_thread_map__set_pid(threads, threads->nr + i, + atoi(namelist[i]->d_name)); } for (i = 0; i < items; i++) @@ -180,17 +157,17 @@ out_free_closedir: goto out_closedir; } -struct thread_map *thread_map__new_all_cpus(void) +struct perf_thread_map *thread_map__new_all_cpus(void) { return __thread_map__new_all_cpus(UINT_MAX); } -struct thread_map *thread_map__new_by_uid(uid_t uid) +struct perf_thread_map *thread_map__new_by_uid(uid_t uid) { return __thread_map__new_all_cpus(uid); } -struct thread_map *thread_map__new(pid_t pid, pid_t tid, uid_t uid) +struct perf_thread_map *thread_map__new(pid_t pid, pid_t tid, uid_t uid) { if (pid != -1) return thread_map__new_by_pid(pid); @@ -201,9 +178,9 @@ struct thread_map *thread_map__new(pid_t pid, pid_t tid, uid_t uid) return thread_map__new_by_tid(tid); } -static struct thread_map *thread_map__new_by_pid_str(const char *pid_str) +static struct perf_thread_map *thread_map__new_by_pid_str(const char *pid_str) { - struct thread_map *threads = NULL, *nt; + struct perf_thread_map *threads = NULL, *nt; char name[256]; int items, total_tasks = 0; struct dirent **namelist = NULL; @@ -233,14 +210,14 @@ static struct thread_map *thread_map__new_by_pid_str(const char *pid_str) goto out_free_threads; total_tasks += items; - nt = thread_map__realloc(threads, total_tasks); + nt = perf_thread_map__realloc(threads, total_tasks); if (nt == NULL) goto out_free_namelist; threads = nt; for (i = 0; i < items; i++) { - thread_map__set_pid(threads, j++, atoi(namelist[i]->d_name)); + perf_thread_map__set_pid(threads, j++, atoi(namelist[i]->d_name)); zfree(&namelist[i]); } threads->nr = total_tasks; @@ -263,21 +240,9 @@ out_free_threads: goto out; } -struct thread_map *thread_map__new_dummy(void) -{ - struct thread_map *threads = thread_map__alloc(1); - - if (threads != NULL) { - thread_map__set_pid(threads, 0, -1); - threads->nr = 1; - refcount_set(&threads->refcnt, 1); - } - return threads; -} - -struct thread_map *thread_map__new_by_tid_str(const char *tid_str) +struct perf_thread_map *thread_map__new_by_tid_str(const char *tid_str) { - struct thread_map *threads = NULL, *nt; + struct perf_thread_map *threads = NULL, *nt; int ntasks = 0; pid_t tid, prev_tid = INT_MAX; char *end_ptr; @@ -287,7 +252,7 @@ struct thread_map *thread_map__new_by_tid_str(const char *tid_str) /* perf-stat expects threads to be generated even if tid not given */ if (!tid_str) - return thread_map__new_dummy(); + return perf_thread_map__new_dummy(); slist = strlist__new(tid_str, &slist_config); if (!slist) @@ -304,13 +269,13 @@ struct thread_map *thread_map__new_by_tid_str(const char *tid_str) continue; ntasks++; - nt = thread_map__realloc(threads, ntasks); + nt = perf_thread_map__realloc(threads, ntasks); if (nt == NULL) goto out_free_threads; threads = nt; - thread_map__set_pid(threads, ntasks - 1, tid); + perf_thread_map__set_pid(threads, ntasks - 1, tid); threads->nr = ntasks; } out: @@ -324,7 +289,7 @@ out_free_threads: goto out; } -struct thread_map *thread_map__new_str(const char *pid, const char *tid, +struct perf_thread_map *thread_map__new_str(const char *pid, const char *tid, uid_t uid, bool all_threads) { if (pid) @@ -339,39 +304,13 @@ struct thread_map *thread_map__new_str(const char *pid, const char *tid, return thread_map__new_by_tid_str(tid); } -static void thread_map__delete(struct thread_map *threads) -{ - if (threads) { - int i; - - WARN_ONCE(refcount_read(&threads->refcnt) != 0, - "thread map refcnt unbalanced\n"); - for (i = 0; i < threads->nr; i++) - free(thread_map__comm(threads, i)); - free(threads); - } -} - -struct thread_map *thread_map__get(struct thread_map *map) -{ - if (map) - refcount_inc(&map->refcnt); - return map; -} - -void thread_map__put(struct thread_map *map) -{ - if (map && refcount_dec_and_test(&map->refcnt)) - thread_map__delete(map); -} - -size_t thread_map__fprintf(struct thread_map *threads, FILE *fp) +size_t thread_map__fprintf(struct perf_thread_map *threads, FILE *fp) { int i; size_t printed = fprintf(fp, "%d thread%s: ", threads->nr, threads->nr > 1 ? "s" : ""); for (i = 0; i < threads->nr; ++i) - printed += fprintf(fp, "%s%d", i ? ", " : "", thread_map__pid(threads, i)); + printed += fprintf(fp, "%s%d", i ? ", " : "", perf_thread_map__pid(threads, i)); return printed + fprintf(fp, "\n"); } @@ -400,9 +339,9 @@ static int get_comm(char **comm, pid_t pid) return err; } -static void comm_init(struct thread_map *map, int i) +static void comm_init(struct perf_thread_map *map, int i) { - pid_t pid = thread_map__pid(map, i); + pid_t pid = perf_thread_map__pid(map, i); char *comm = NULL; /* dummy pid comm initialization */ @@ -421,7 +360,7 @@ static void comm_init(struct thread_map *map, int i) map->map[i].comm = comm; } -void thread_map__read_comms(struct thread_map *threads) +void thread_map__read_comms(struct perf_thread_map *threads) { int i; @@ -429,7 +368,7 @@ void thread_map__read_comms(struct thread_map *threads) comm_init(threads, i); } -static void thread_map__copy_event(struct thread_map *threads, +static void thread_map__copy_event(struct perf_thread_map *threads, struct thread_map_event *event) { unsigned i; @@ -437,16 +376,16 @@ static void thread_map__copy_event(struct thread_map *threads, threads->nr = (int) event->nr; for (i = 0; i < event->nr; i++) { - thread_map__set_pid(threads, i, (pid_t) event->entries[i].pid); + perf_thread_map__set_pid(threads, i, (pid_t) event->entries[i].pid); threads->map[i].comm = strndup(event->entries[i].comm, 16); } refcount_set(&threads->refcnt, 1); } -struct thread_map *thread_map__new_event(struct thread_map_event *event) +struct perf_thread_map *thread_map__new_event(struct thread_map_event *event) { - struct thread_map *threads; + struct perf_thread_map *threads; threads = thread_map__alloc(event->nr); if (threads) @@ -455,7 +394,7 @@ struct thread_map *thread_map__new_event(struct thread_map_event *event) return threads; } -bool thread_map__has(struct thread_map *threads, pid_t pid) +bool thread_map__has(struct perf_thread_map *threads, pid_t pid) { int i; @@ -467,7 +406,7 @@ bool thread_map__has(struct thread_map *threads, pid_t pid) return false; } -int thread_map__remove(struct thread_map *threads, int idx) +int thread_map__remove(struct perf_thread_map *threads, int idx) { int i; diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h index 2f689c90a8c6..ca165fdf6cb0 100644 --- a/tools/perf/util/thread_map.h +++ b/tools/perf/util/thread_map.h @@ -5,61 +5,27 @@ #include <sys/types.h> #include <stdio.h> #include <linux/refcount.h> - -struct thread_map_data { - pid_t pid; - char *comm; -}; - -struct thread_map { - refcount_t refcnt; - int nr; - int err_thread; - struct thread_map_data map[]; -}; +#include <internal/threadmap.h> +#include <perf/threadmap.h> struct thread_map_event; -struct thread_map *thread_map__new_dummy(void); -struct thread_map *thread_map__new_by_pid(pid_t pid); -struct thread_map *thread_map__new_by_tid(pid_t tid); -struct thread_map *thread_map__new_by_uid(uid_t uid); -struct thread_map *thread_map__new_all_cpus(void); -struct thread_map *thread_map__new(pid_t pid, pid_t tid, uid_t uid); -struct thread_map *thread_map__new_event(struct thread_map_event *event); +struct perf_thread_map *thread_map__new_dummy(void); +struct perf_thread_map *thread_map__new_by_pid(pid_t pid); +struct perf_thread_map *thread_map__new_by_tid(pid_t tid); +struct perf_thread_map *thread_map__new_by_uid(uid_t uid); +struct perf_thread_map *thread_map__new_all_cpus(void); +struct perf_thread_map *thread_map__new(pid_t pid, pid_t tid, uid_t uid); +struct perf_thread_map *thread_map__new_event(struct thread_map_event *event); -struct thread_map *thread_map__get(struct thread_map *map); -void thread_map__put(struct thread_map *map); - -struct thread_map *thread_map__new_str(const char *pid, +struct perf_thread_map *thread_map__new_str(const char *pid, const char *tid, uid_t uid, bool all_threads); -struct thread_map *thread_map__new_by_tid_str(const char *tid_str); - -size_t thread_map__fprintf(struct thread_map *threads, FILE *fp); - -static inline int thread_map__nr(struct thread_map *threads) -{ - return threads ? threads->nr : 1; -} - -static inline pid_t thread_map__pid(struct thread_map *map, int thread) -{ - return map->map[thread].pid; -} - -static inline void -thread_map__set_pid(struct thread_map *map, int thread, pid_t pid) -{ - map->map[thread].pid = pid; -} +struct perf_thread_map *thread_map__new_by_tid_str(const char *tid_str); -static inline char *thread_map__comm(struct thread_map *map, int thread) -{ - return map->map[thread].comm; -} +size_t thread_map__fprintf(struct perf_thread_map *threads, FILE *fp); -void thread_map__read_comms(struct thread_map *threads); -bool thread_map__has(struct thread_map *threads, pid_t pid); -int thread_map__remove(struct thread_map *threads, int idx); +void thread_map__read_comms(struct perf_thread_map *threads); +bool thread_map__has(struct perf_thread_map *threads, pid_t pid); +int thread_map__remove(struct perf_thread_map *threads, int idx); #endif /* __PERF_THREAD_MAP_H */ diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h index 9096a6e3de59..7f95dd1d6883 100644 --- a/tools/perf/util/tool.h +++ b/tools/perf/util/tool.h @@ -8,8 +8,8 @@ struct perf_session; union perf_event; -struct perf_evlist; -struct perf_evsel; +struct evlist; +struct evsel; struct perf_sample; struct perf_tool; struct machine; @@ -17,14 +17,14 @@ struct ordered_events; typedef int (*event_sample)(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, - struct perf_evsel *evsel, struct machine *machine); + struct evsel *evsel, struct machine *machine); typedef int (*event_op)(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine); typedef int (*event_attr_op)(struct perf_tool *tool, union perf_event *event, - struct perf_evlist **pevlist); + struct evlist **pevlist); typedef int (*event_op2)(struct perf_session *session, union perf_event *event); typedef s64 (*event_op3)(struct perf_session *session, union perf_event *event); diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c index 251bbf124fb0..e5b690cf2898 100644 --- a/tools/perf/util/top.c +++ b/tools/perf/util/top.c @@ -70,10 +70,10 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size) esamples_percent); } - if (top->evlist->nr_entries == 1) { - struct perf_evsel *first = perf_evlist__first(top->evlist); + if (top->evlist->core.nr_entries == 1) { + struct evsel *first = perf_evlist__first(top->evlist); ret += SNPRINTF(bf + ret, size - ret, "%" PRIu64 "%s ", - (uint64_t)first->attr.sample_period, + (uint64_t)first->core.attr.sample_period, opts->freq ? "Hz" : ""); } @@ -95,15 +95,15 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size) if (target->cpu_list) ret += SNPRINTF(bf + ret, size - ret, ", CPU%s: %s)", - top->evlist->cpus->nr > 1 ? "s" : "", + top->evlist->core.cpus->nr > 1 ? "s" : "", target->cpu_list); else { if (target->tid) ret += SNPRINTF(bf + ret, size - ret, ")"); else ret += SNPRINTF(bf + ret, size - ret, ", %d CPU%s)", - top->evlist->cpus->nr, - top->evlist->cpus->nr > 1 ? "s" : ""); + top->evlist->core.cpus->nr, + top->evlist->core.cpus->nr > 1 ? "s" : ""); } perf_top__reset_sample_counters(top); diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h index 19f95eaf75c8..dc4bb6e52a83 100644 --- a/tools/perf/util/top.h +++ b/tools/perf/util/top.h @@ -3,21 +3,23 @@ #define __PERF_TOP_H 1 #include "tool.h" +#include "evswitch.h" #include "annotate.h" #include <linux/types.h> #include <stddef.h> #include <stdbool.h> #include <sys/ioctl.h> -struct perf_evlist; -struct perf_evsel; +struct evlist; +struct evsel; struct perf_session; struct perf_top { struct perf_tool tool; - struct perf_evlist *evlist; + struct evlist *evlist; struct record_opts record_opts; struct annotation_options annotation_opts; + struct evswitch evswitch; /* * Symbols will be added here in perf_event__process_sample and will * get out after decayed. @@ -33,7 +35,7 @@ struct perf_top { bool vmlinux_warned; bool dump_symtab; struct hist_entry *sym_filter_entry; - struct perf_evsel *sym_evsel; + struct evsel *sym_evsel; struct perf_session *session; struct winsize winsize; int realtime_prio; diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c index 4550015b9d5d..2f8a0601a546 100644 --- a/tools/perf/util/trace-event-info.c +++ b/tools/perf/util/trace-event-info.c @@ -405,11 +405,11 @@ static struct tracepoint_path * get_tracepoints_path(struct list_head *pattrs) { struct tracepoint_path path, *ppath = &path; - struct perf_evsel *pos; + struct evsel *pos; int nr_tracepoints = 0; - list_for_each_entry(pos, pattrs, node) { - if (pos->attr.type != PERF_TYPE_TRACEPOINT) + list_for_each_entry(pos, pattrs, core.node) { + if (pos->core.attr.type != PERF_TYPE_TRACEPOINT) continue; ++nr_tracepoints; @@ -425,7 +425,7 @@ get_tracepoints_path(struct list_head *pattrs) } try_id: - ppath->next = tracepoint_id_to_path(pos->attr.config); + ppath->next = tracepoint_id_to_path(pos->core.attr.config); if (!ppath->next) { error: pr_debug("No memory to alloc tracepoints list\n"); @@ -441,10 +441,10 @@ next: bool have_tracepoints(struct list_head *pattrs) { - struct perf_evsel *pos; + struct evsel *pos; - list_for_each_entry(pos, pattrs, node) - if (pos->attr.type == PERF_TYPE_TRACEPOINT) + list_for_each_entry(pos, pattrs, core.node) + if (pos->core.attr.type == PERF_TYPE_TRACEPOINT) return true; return false; diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c index ba58f69777a1..dfd2640c763a 100644 --- a/tools/perf/util/trace-event-scripting.c +++ b/tools/perf/util/trace-event-scripting.c @@ -29,7 +29,7 @@ static int stop_script_unsupported(void) static void process_event_unsupported(union perf_event *event __maybe_unused, struct perf_sample *sample __maybe_unused, - struct perf_evsel *evsel __maybe_unused, + struct evsel *evsel __maybe_unused, struct addr_location *al __maybe_unused) { } diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h index c7002fe11673..258d79071d81 100644 --- a/tools/perf/util/trace-event.h +++ b/tools/perf/util/trace-event.h @@ -79,13 +79,13 @@ struct scripting_ops { int (*stop_script) (void); void (*process_event) (union perf_event *event, struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct addr_location *al); void (*process_switch)(union perf_event *event, struct perf_sample *sample, struct machine *machine); void (*process_stat)(struct perf_stat_config *config, - struct perf_evsel *evsel, u64 tstamp); + struct evsel *evsel, u64 tstamp); void (*process_stat_interval)(u64 tstamp); int (*generate_script) (struct tep_handle *pevent, const char *outfile); }; diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index 71a788921b62..ebdbb056510c 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -616,26 +616,26 @@ static unw_accessors_t accessors = { .get_proc_name = get_proc_name, }; -static int _unwind__prepare_access(struct thread *thread) +static int _unwind__prepare_access(struct map_groups *mg) { - thread->addr_space = unw_create_addr_space(&accessors, 0); - if (!thread->addr_space) { + mg->addr_space = unw_create_addr_space(&accessors, 0); + if (!mg->addr_space) { pr_err("unwind: Can't create unwind address space.\n"); return -ENOMEM; } - unw_set_caching_policy(thread->addr_space, UNW_CACHE_GLOBAL); + unw_set_caching_policy(mg->addr_space, UNW_CACHE_GLOBAL); return 0; } -static void _unwind__flush_access(struct thread *thread) +static void _unwind__flush_access(struct map_groups *mg) { - unw_flush_cache(thread->addr_space, 0, 0); + unw_flush_cache(mg->addr_space, 0, 0); } -static void _unwind__finish_access(struct thread *thread) +static void _unwind__finish_access(struct map_groups *mg) { - unw_destroy_addr_space(thread->addr_space); + unw_destroy_addr_space(mg->addr_space); } static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, @@ -660,7 +660,7 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, */ if (max_stack - 1 > 0) { WARN_ONCE(!ui->thread, "WARNING: ui->thread is NULL"); - addr_space = ui->thread->addr_space; + addr_space = ui->thread->mg->addr_space; if (addr_space == NULL) return -1; diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c index c0811977d7d5..6499b22b158b 100644 --- a/tools/perf/util/unwind-libunwind.c +++ b/tools/perf/util/unwind-libunwind.c @@ -11,13 +11,13 @@ struct unwind_libunwind_ops __weak *local_unwind_libunwind_ops; struct unwind_libunwind_ops __weak *x86_32_unwind_libunwind_ops; struct unwind_libunwind_ops __weak *arm64_unwind_libunwind_ops; -static void unwind__register_ops(struct thread *thread, +static void unwind__register_ops(struct map_groups *mg, struct unwind_libunwind_ops *ops) { - thread->unwind_libunwind_ops = ops; + mg->unwind_libunwind_ops = ops; } -int unwind__prepare_access(struct thread *thread, struct map *map, +int unwind__prepare_access(struct map_groups *mg, struct map *map, bool *initialized) { const char *arch; @@ -28,7 +28,7 @@ int unwind__prepare_access(struct thread *thread, struct map *map, if (!dwarf_callchain_users) return 0; - if (thread->addr_space) { + if (mg->addr_space) { pr_debug("unwind: thread map already set, dso=%s\n", map->dso->name); if (initialized) @@ -37,14 +37,14 @@ int unwind__prepare_access(struct thread *thread, struct map *map, } /* env->arch is NULL for live-mode (i.e. perf top) */ - if (!thread->mg->machine->env || !thread->mg->machine->env->arch) + if (!mg->machine->env || !mg->machine->env->arch) goto out_register; - dso_type = dso__type(map->dso, thread->mg->machine); + dso_type = dso__type(map->dso, mg->machine); if (dso_type == DSO__TYPE_UNKNOWN) return 0; - arch = perf_env__arch(thread->mg->machine->env); + arch = perf_env__arch(mg->machine->env); if (!strcmp(arch, "x86")) { if (dso_type != DSO__TYPE_64BIT) @@ -59,37 +59,31 @@ int unwind__prepare_access(struct thread *thread, struct map *map, return 0; } out_register: - unwind__register_ops(thread, ops); + unwind__register_ops(mg, ops); - err = thread->unwind_libunwind_ops->prepare_access(thread); + err = mg->unwind_libunwind_ops->prepare_access(mg); if (initialized) *initialized = err ? false : true; return err; } -void unwind__flush_access(struct thread *thread) +void unwind__flush_access(struct map_groups *mg) { - if (!dwarf_callchain_users) - return; - - if (thread->unwind_libunwind_ops) - thread->unwind_libunwind_ops->flush_access(thread); + if (mg->unwind_libunwind_ops) + mg->unwind_libunwind_ops->flush_access(mg); } -void unwind__finish_access(struct thread *thread) +void unwind__finish_access(struct map_groups *mg) { - if (!dwarf_callchain_users) - return; - - if (thread->unwind_libunwind_ops) - thread->unwind_libunwind_ops->finish_access(thread); + if (mg->unwind_libunwind_ops) + mg->unwind_libunwind_ops->finish_access(mg); } int unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct thread *thread, struct perf_sample *data, int max_stack) { - if (thread->unwind_libunwind_ops) - return thread->unwind_libunwind_ops->get_entries(cb, arg, thread, data, max_stack); + if (thread->mg->unwind_libunwind_ops) + return thread->mg->unwind_libunwind_ops->get_entries(cb, arg, thread, data, max_stack); return 0; } diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h index 8a44a1569a21..3a7d00c20d86 100644 --- a/tools/perf/util/unwind.h +++ b/tools/perf/util/unwind.h @@ -6,6 +6,7 @@ #include <linux/types.h> struct map; +struct map_groups; struct perf_sample; struct symbol; struct thread; @@ -19,9 +20,9 @@ struct unwind_entry { typedef int (*unwind_entry_cb_t)(struct unwind_entry *entry, void *arg); struct unwind_libunwind_ops { - int (*prepare_access)(struct thread *thread); - void (*flush_access)(struct thread *thread); - void (*finish_access)(struct thread *thread); + int (*prepare_access)(struct map_groups *mg); + void (*flush_access)(struct map_groups *mg); + void (*finish_access)(struct map_groups *mg); int (*get_entries)(unwind_entry_cb_t cb, void *arg, struct thread *thread, struct perf_sample *data, int max_stack); @@ -46,20 +47,20 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg, #endif int LIBUNWIND__ARCH_REG_ID(int regnum); -int unwind__prepare_access(struct thread *thread, struct map *map, +int unwind__prepare_access(struct map_groups *mg, struct map *map, bool *initialized); -void unwind__flush_access(struct thread *thread); -void unwind__finish_access(struct thread *thread); +void unwind__flush_access(struct map_groups *mg); +void unwind__finish_access(struct map_groups *mg); #else -static inline int unwind__prepare_access(struct thread *thread __maybe_unused, +static inline int unwind__prepare_access(struct map_groups *mg __maybe_unused, struct map *map __maybe_unused, bool *initialized __maybe_unused) { return 0; } -static inline void unwind__flush_access(struct thread *thread __maybe_unused) {} -static inline void unwind__finish_access(struct thread *thread __maybe_unused) {} +static inline void unwind__flush_access(struct map_groups *mg __maybe_unused) {} +static inline void unwind__finish_access(struct map_groups *mg __maybe_unused) {} #endif #else static inline int @@ -72,14 +73,14 @@ unwind__get_entries(unwind_entry_cb_t cb __maybe_unused, return 0; } -static inline int unwind__prepare_access(struct thread *thread __maybe_unused, +static inline int unwind__prepare_access(struct map_groups *mg __maybe_unused, struct map *map __maybe_unused, bool *initialized __maybe_unused) { return 0; } -static inline void unwind__flush_access(struct thread *thread __maybe_unused) {} -static inline void unwind__finish_access(struct thread *thread __maybe_unused) {} +static inline void unwind__flush_access(struct map_groups *mg __maybe_unused) {} +static inline void unwind__finish_access(struct map_groups *mg __maybe_unused) {} #endif /* HAVE_DWARF_UNWIND_SUPPORT */ #endif /* __UNWIND_H */ diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index a61535cf1bca..6fd130a5d8f2 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -16,10 +16,12 @@ #include <string.h> #include <errno.h> #include <limits.h> +#include <linux/capability.h> #include <linux/kernel.h> #include <linux/log2.h> #include <linux/time64.h> #include <unistd.h> +#include "cap.h" #include "strlist.h" #include "string2.h" @@ -384,46 +386,6 @@ int copyfile(const char *from, const char *to) return copyfile_mode(from, to, 0755); } -static ssize_t ion(bool is_read, int fd, void *buf, size_t n) -{ - void *buf_start = buf; - size_t left = n; - - while (left) { - /* buf must be treated as const if !is_read. */ - ssize_t ret = is_read ? read(fd, buf, left) : - write(fd, buf, left); - - if (ret < 0 && errno == EINTR) - continue; - if (ret <= 0) - return ret; - - left -= ret; - buf += ret; - } - - BUG_ON((size_t)(buf - buf_start) != n); - return n; -} - -/* - * Read exactly 'n' bytes or return an error. - */ -ssize_t readn(int fd, void *buf, size_t n) -{ - return ion(true, fd, buf, n); -} - -/* - * Write exactly 'n' bytes or return an error. - */ -ssize_t writen(int fd, const void *buf, size_t n) -{ - /* ion does not modify buf. */ - return ion(false, fd, (void *)buf, n); -} - size_t hex_width(u64 v) { size_t n = 1; @@ -443,6 +405,13 @@ int perf_event_paranoid(void) return value; } + +bool perf_event_paranoid_check(int max_level) +{ + return perf_cap__capable(CAP_SYS_ADMIN) || + perf_event_paranoid() <= max_level; +} + static int fetch_ubuntu_kernel_version(unsigned int *puint) { diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index dc7a469921e9..0dab140c6517 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -11,6 +11,7 @@ #include <stddef.h> #include <linux/compiler.h> #include <sys/types.h> +#include <internal/lib.h> /* General helper functions */ void usage(const char *err) __noreturn; @@ -30,9 +31,6 @@ int copyfile_mode(const char *from, const char *to, mode_t mode); int copyfile_ns(const char *from, const char *to, struct nsinfo *nsi); int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size); -ssize_t readn(int fd, void *buf, size_t n); -ssize_t writen(int fd, const void *buf, size_t n); - size_t hex_width(u64 v); extern unsigned int page_size; |