diff options
Diffstat (limited to 'tools/perf/arch')
30 files changed, 392 insertions, 37 deletions
diff --git a/tools/perf/arch/arm/include/perf_regs.h b/tools/perf/arch/arm/include/perf_regs.h index ed20e0253e25..4085419283d0 100644 --- a/tools/perf/arch/arm/include/perf_regs.h +++ b/tools/perf/arch/arm/include/perf_regs.h @@ -15,7 +15,7 @@ void perf_regs_load(u64 *regs); #define PERF_REG_IP PERF_REG_ARM_PC #define PERF_REG_SP PERF_REG_ARM_SP -static inline const char *perf_reg_name(int id) +static inline const char *__perf_reg_name(int id) { switch (id) { case PERF_REG_ARM_R0: diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index bd446aba64f7..c25c878fd06c 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -156,6 +156,10 @@ out: return err; } +#define ETM_SET_OPT_CTXTID (1 << 0) +#define ETM_SET_OPT_TS (1 << 1) +#define ETM_SET_OPT_MASK (ETM_SET_OPT_CTXTID | ETM_SET_OPT_TS) + static int cs_etm_set_option(struct auxtrace_record *itr, struct evsel *evsel, u32 option) { @@ -169,17 +173,17 @@ static int cs_etm_set_option(struct auxtrace_record *itr, !cpu_map__has(online_cpus, i)) continue; - if (option & ETM_OPT_CTXTID) { + if (option & ETM_SET_OPT_CTXTID) { err = cs_etm_set_context_id(itr, evsel, i); if (err) goto out; } - if (option & ETM_OPT_TS) { + if (option & ETM_SET_OPT_TS) { err = cs_etm_set_timestamp(itr, evsel, i); if (err) goto out; } - if (option & ~(ETM_OPT_CTXTID | ETM_OPT_TS)) + if (option & ~(ETM_SET_OPT_MASK)) /* Nothing else is currently supported */ goto out; } @@ -406,7 +410,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, evsel__set_sample_bit(cs_etm_evsel, CPU); err = cs_etm_set_option(itr, cs_etm_evsel, - ETM_OPT_CTXTID | ETM_OPT_TS); + ETM_SET_OPT_CTXTID | ETM_SET_OPT_TS); if (err) goto out; } diff --git a/tools/perf/arch/arm64/include/perf_regs.h b/tools/perf/arch/arm64/include/perf_regs.h index baaa5e64a3fb..fa3e07459f76 100644 --- a/tools/perf/arch/arm64/include/perf_regs.h +++ b/tools/perf/arch/arm64/include/perf_regs.h @@ -15,7 +15,7 @@ void perf_regs_load(u64 *regs); #define PERF_REG_IP PERF_REG_ARM64_PC #define PERF_REG_SP PERF_REG_ARM64_SP -static inline const char *perf_reg_name(int id) +static inline const char *__perf_reg_name(int id) { switch (id) { case PERF_REG_ARM64_X0: diff --git a/tools/perf/arch/arm64/util/machine.c b/tools/perf/arch/arm64/util/machine.c index d41b27e781d3..40c5e0b5bda8 100644 --- a/tools/perf/arch/arm64/util/machine.c +++ b/tools/perf/arch/arm64/util/machine.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 +#include <inttypes.h> #include <stdio.h> #include <string.h> #include "debug.h" @@ -23,5 +24,5 @@ void arch__symbols__fixup_end(struct symbol *p, struct symbol *c) p->end += SYMBOL_LIMIT; else p->end = c->start; - pr_debug4("%s sym:%s end:%#lx\n", __func__, p->name, p->end); + pr_debug4("%s sym:%s end:%#" PRIx64 "\n", __func__, p->name, p->end); } diff --git a/tools/perf/arch/arm64/util/perf_regs.c b/tools/perf/arch/arm64/util/perf_regs.c index 54efa12fdbea..2518cde18b34 100644 --- a/tools/perf/arch/arm64/util/perf_regs.c +++ b/tools/perf/arch/arm64/util/perf_regs.c @@ -1,4 +1,12 @@ // SPDX-License-Identifier: GPL-2.0 +#include <errno.h> +#include <regex.h> +#include <string.h> +#include <linux/kernel.h> +#include <linux/zalloc.h> + +#include "../../../util/debug.h" +#include "../../../util/event.h" #include "../../../util/perf_regs.h" const struct sample_reg sample_reg_masks[] = { @@ -37,3 +45,89 @@ const struct sample_reg sample_reg_masks[] = { SMPL_REG(pc, PERF_REG_ARM64_PC), SMPL_REG_END }; + +/* %xNUM */ +#define SDT_OP_REGEX1 "^(x[1-2]?[0-9]|3[0-1])$" + +/* [sp], [sp, NUM] */ +#define SDT_OP_REGEX2 "^\\[sp(, )?([0-9]+)?\\]$" + +static regex_t sdt_op_regex1, sdt_op_regex2; + +static int sdt_init_op_regex(void) +{ + static int initialized; + int ret = 0; + + if (initialized) + return 0; + + ret = regcomp(&sdt_op_regex1, SDT_OP_REGEX1, REG_EXTENDED); + if (ret) + goto error; + + ret = regcomp(&sdt_op_regex2, SDT_OP_REGEX2, REG_EXTENDED); + if (ret) + goto free_regex1; + + initialized = 1; + return 0; + +free_regex1: + regfree(&sdt_op_regex1); +error: + pr_debug4("Regex compilation error.\n"); + return ret; +} + +/* + * SDT marker arguments on Arm64 uses %xREG or [sp, NUM], currently + * support these two formats. + */ +int arch_sdt_arg_parse_op(char *old_op, char **new_op) +{ + int ret, new_len; + regmatch_t rm[5]; + + ret = sdt_init_op_regex(); + if (ret < 0) + return ret; + + if (!regexec(&sdt_op_regex1, old_op, 3, rm, 0)) { + /* Extract xNUM */ + new_len = 2; /* % NULL */ + new_len += (int)(rm[1].rm_eo - rm[1].rm_so); + + *new_op = zalloc(new_len); + if (!*new_op) + return -ENOMEM; + + scnprintf(*new_op, new_len, "%%%.*s", + (int)(rm[1].rm_eo - rm[1].rm_so), old_op + rm[1].rm_so); + } else if (!regexec(&sdt_op_regex2, old_op, 5, rm, 0)) { + /* [sp], [sp, NUM] or [sp,NUM] */ + new_len = 7; /* + ( % s p ) NULL */ + + /* If the arugment is [sp], need to fill offset '0' */ + if (rm[2].rm_so == -1) + new_len += 1; + else + new_len += (int)(rm[2].rm_eo - rm[2].rm_so); + + *new_op = zalloc(new_len); + if (!*new_op) + return -ENOMEM; + + if (rm[2].rm_so == -1) + scnprintf(*new_op, new_len, "+0(%%sp)"); + else + scnprintf(*new_op, new_len, "+%.*s(%%sp)", + (int)(rm[2].rm_eo - rm[2].rm_so), + old_op + rm[2].rm_so); + } else { + pr_debug4("Skipping unsupported SDT argument: %s\n", old_op); + return SDT_ARG_SKIP; + } + + return SDT_ARG_VALID; +} diff --git a/tools/perf/arch/csky/include/perf_regs.h b/tools/perf/arch/csky/include/perf_regs.h index 8f336ea1161a..25ac3bdcb9d1 100644 --- a/tools/perf/arch/csky/include/perf_regs.h +++ b/tools/perf/arch/csky/include/perf_regs.h @@ -15,7 +15,7 @@ #define PERF_REG_IP PERF_REG_CSKY_PC #define PERF_REG_SP PERF_REG_CSKY_SP -static inline const char *perf_reg_name(int id) +static inline const char *__perf_reg_name(int id) { switch (id) { case PERF_REG_CSKY_A0: diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl index f744eb5cba88..0b2480cf3e47 100644 --- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl @@ -9,9 +9,7 @@ # 0 nospu restart_syscall sys_restart_syscall 1 nospu exit sys_exit -2 32 fork ppc_fork sys_fork -2 64 fork sys_fork -2 spu fork sys_ni_syscall +2 nospu fork sys_fork 3 common read sys_read 4 common write sys_write 5 common open sys_open compat_sys_open @@ -160,9 +158,7 @@ 119 32 sigreturn sys_sigreturn compat_sys_sigreturn 119 64 sigreturn sys_ni_syscall 119 spu sigreturn sys_ni_syscall -120 32 clone ppc_clone sys_clone -120 64 clone sys_clone -120 spu clone sys_ni_syscall +120 nospu clone sys_clone 121 common setdomainname sys_setdomainname 122 common uname sys_newuname 123 common modify_ldt sys_ni_syscall @@ -244,9 +240,7 @@ 186 spu sendfile sys_sendfile64 187 common getpmsg sys_ni_syscall 188 common putpmsg sys_ni_syscall -189 32 vfork ppc_vfork sys_vfork -189 64 vfork sys_vfork -189 spu vfork sys_ni_syscall +189 nospu vfork sys_vfork 190 common ugetrlimit sys_getrlimit compat_sys_getrlimit 191 common readahead sys_readahead compat_sys_readahead 192 32 mmap2 sys_mmap2 compat_sys_mmap2 @@ -322,9 +316,7 @@ 248 32 clock_nanosleep sys_clock_nanosleep_time32 248 64 clock_nanosleep sys_clock_nanosleep 248 spu clock_nanosleep sys_clock_nanosleep -249 32 swapcontext ppc_swapcontext compat_sys_swapcontext -249 64 swapcontext sys_swapcontext -249 spu swapcontext sys_ni_syscall +249 nospu swapcontext sys_swapcontext compat_sys_swapcontext 250 common tgkill sys_tgkill 251 32 utimes sys_utimes_time32 251 64 utimes sys_utimes @@ -522,12 +514,11 @@ 432 common fsmount sys_fsmount 433 common fspick sys_fspick 434 common pidfd_open sys_pidfd_open -435 32 clone3 ppc_clone3 sys_clone3 -435 64 clone3 sys_clone3 -435 spu clone3 sys_ni_syscall +435 nospu clone3 sys_clone3 436 common close_range sys_close_range 437 common openat2 sys_openat2 438 common pidfd_getfd sys_pidfd_getfd 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr diff --git a/tools/perf/arch/powerpc/include/perf_regs.h b/tools/perf/arch/powerpc/include/perf_regs.h index 63f3ac91049f..04e5dc07e93f 100644 --- a/tools/perf/arch/powerpc/include/perf_regs.h +++ b/tools/perf/arch/powerpc/include/perf_regs.h @@ -71,9 +71,15 @@ static const char *reg_names[] = { [PERF_REG_POWERPC_MMCR3] = "mmcr3", [PERF_REG_POWERPC_SIER2] = "sier2", [PERF_REG_POWERPC_SIER3] = "sier3", + [PERF_REG_POWERPC_PMC1] = "pmc1", + [PERF_REG_POWERPC_PMC2] = "pmc2", + [PERF_REG_POWERPC_PMC3] = "pmc3", + [PERF_REG_POWERPC_PMC4] = "pmc4", + [PERF_REG_POWERPC_PMC5] = "pmc5", + [PERF_REG_POWERPC_PMC6] = "pmc6", }; -static inline const char *perf_reg_name(int id) +static inline const char *__perf_reg_name(int id) { return reg_names[id]; } diff --git a/tools/perf/arch/powerpc/util/Build b/tools/perf/arch/powerpc/util/Build index e86e210bf514..b7945e5a543b 100644 --- a/tools/perf/arch/powerpc/util/Build +++ b/tools/perf/arch/powerpc/util/Build @@ -1,4 +1,5 @@ perf-y += header.o +perf-y += machine.o perf-y += kvm-stat.o perf-y += perf_regs.o perf-y += mem-events.o diff --git a/tools/perf/arch/powerpc/util/machine.c b/tools/perf/arch/powerpc/util/machine.c new file mode 100644 index 000000000000..e652a1aa8132 --- /dev/null +++ b/tools/perf/arch/powerpc/util/machine.c @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <inttypes.h> +#include <stdio.h> +#include <string.h> +#include <internal/lib.h> // page_size +#include "debug.h" +#include "symbol.h" + +/* On powerpc kernel text segment start at memory addresses, 0xc000000000000000 + * whereas the modules are located at very high memory addresses, + * for example 0xc00800000xxxxxxx. The gap between end of kernel text segment + * and beginning of first module's text segment is very high. + * Therefore do not fill this gap and do not assign it to the kernel dso map. + */ + +void arch__symbols__fixup_end(struct symbol *p, struct symbol *c) +{ + if (strchr(p->name, '[') == NULL && strchr(c->name, '[')) + /* Limit the range of last kernel symbol */ + p->end += page_size; + else + p->end = c->start; + pr_debug4("%s sym:%s end:%#" PRIx64 "\n", __func__, p->name, p->end); +} diff --git a/tools/perf/arch/powerpc/util/perf_regs.c b/tools/perf/arch/powerpc/util/perf_regs.c index 2b6d4704e3aa..8116a253f91f 100644 --- a/tools/perf/arch/powerpc/util/perf_regs.c +++ b/tools/perf/arch/powerpc/util/perf_regs.c @@ -68,6 +68,12 @@ const struct sample_reg sample_reg_masks[] = { SMPL_REG(mmcr3, PERF_REG_POWERPC_MMCR3), SMPL_REG(sier2, PERF_REG_POWERPC_SIER2), SMPL_REG(sier3, PERF_REG_POWERPC_SIER3), + SMPL_REG(pmc1, PERF_REG_POWERPC_PMC1), + SMPL_REG(pmc2, PERF_REG_POWERPC_PMC2), + SMPL_REG(pmc3, PERF_REG_POWERPC_PMC3), + SMPL_REG(pmc4, PERF_REG_POWERPC_PMC4), + SMPL_REG(pmc5, PERF_REG_POWERPC_PMC5), + SMPL_REG(pmc6, PERF_REG_POWERPC_PMC6), SMPL_REG_END }; diff --git a/tools/perf/arch/riscv/include/perf_regs.h b/tools/perf/arch/riscv/include/perf_regs.h index 7a8bcde7a2b1..6b02a767c918 100644 --- a/tools/perf/arch/riscv/include/perf_regs.h +++ b/tools/perf/arch/riscv/include/perf_regs.h @@ -19,7 +19,7 @@ #define PERF_REG_IP PERF_REG_RISCV_PC #define PERF_REG_SP PERF_REG_RISCV_SP -static inline const char *perf_reg_name(int id) +static inline const char *__perf_reg_name(int id) { switch (id) { case PERF_REG_RISCV_PC: diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl index d443423495e5..3abef2144dac 100644 --- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl @@ -444,3 +444,4 @@ 439 common faccessat2 sys_faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr sys_mount_setattr diff --git a/tools/perf/arch/s390/include/perf_regs.h b/tools/perf/arch/s390/include/perf_regs.h index bcfbaed78cc2..ce3031526623 100644 --- a/tools/perf/arch/s390/include/perf_regs.h +++ b/tools/perf/arch/s390/include/perf_regs.h @@ -14,7 +14,7 @@ void perf_regs_load(u64 *regs); #define PERF_REG_IP PERF_REG_S390_PC #define PERF_REG_SP PERF_REG_S390_R15 -static inline const char *perf_reg_name(int id) +static inline const char *__perf_reg_name(int id) { switch (id) { case PERF_REG_S390_R0: diff --git a/tools/perf/arch/s390/util/machine.c b/tools/perf/arch/s390/util/machine.c index 724efb2d842d..7644a4f6d4a4 100644 --- a/tools/perf/arch/s390/util/machine.c +++ b/tools/perf/arch/s390/util/machine.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#include <inttypes.h> #include <unistd.h> #include <stdio.h> #include <string.h> @@ -48,5 +49,5 @@ void arch__symbols__fixup_end(struct symbol *p, struct symbol *c) p->end = roundup(p->end, page_size); else p->end = c->start; - pr_debug4("%s sym:%s end:%#lx\n", __func__, p->name, p->end); + pr_debug4("%s sym:%s end:%#" PRIx64 "\n", __func__, p->name, p->end); } diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile index 8cc6642fce7a..5a9f9a7bf07d 100644 --- a/tools/perf/arch/x86/Makefile +++ b/tools/perf/arch/x86/Makefile @@ -10,10 +10,11 @@ PERF_HAVE_JITDUMP := 1 # Syscall table generation # -out := $(OUTPUT)arch/x86/include/generated/asm -header := $(out)/syscalls_64.c -sys := $(srctree)/tools/perf/arch/x86/entry/syscalls -systbl := $(sys)/syscalltbl.sh +generated := $(OUTPUT)arch/x86/include/generated +out := $(generated)/asm +header := $(out)/syscalls_64.c +sys := $(srctree)/tools/perf/arch/x86/entry/syscalls +systbl := $(sys)/syscalltbl.sh # Create output directory if not already present _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') @@ -22,6 +23,6 @@ $(header): $(sys)/syscall_64.tbl $(systbl) $(Q)$(SHELL) '$(systbl)' $(sys)/syscall_64.tbl 'x86_64' > $@ clean:: - $(call QUIET_CLEAN, x86) $(RM) $(header) + $(call QUIET_CLEAN, x86) $(RM) -r $(header) $(generated) archheaders: $(header) diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index 78672124d28b..7bf01cbe582f 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -363,6 +363,7 @@ 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr # # Due to a historical design error, certain syscalls are numbered differently diff --git a/tools/perf/arch/x86/include/arch-tests.h b/tools/perf/arch/x86/include/arch-tests.h index 6a54b94f1c25..0e20f3dc69f3 100644 --- a/tools/perf/arch/x86/include/arch-tests.h +++ b/tools/perf/arch/x86/include/arch-tests.h @@ -10,6 +10,7 @@ int test__rdpmc(struct test *test __maybe_unused, int subtest); int test__insn_x86(struct test *test __maybe_unused, int subtest); int test__intel_pt_pkt_decoder(struct test *test, int subtest); int test__bp_modify(struct test *test, int subtest); +int test__x86_sample_parsing(struct test *test, int subtest); #ifdef HAVE_DWARF_UNWIND_SUPPORT struct thread; diff --git a/tools/perf/arch/x86/include/perf_regs.h b/tools/perf/arch/x86/include/perf_regs.h index b7321337d100..cddc4cdc0d9b 100644 --- a/tools/perf/arch/x86/include/perf_regs.h +++ b/tools/perf/arch/x86/include/perf_regs.h @@ -23,7 +23,7 @@ void perf_regs_load(u64 *regs); #define PERF_REG_IP PERF_REG_X86_IP #define PERF_REG_SP PERF_REG_X86_SP -static inline const char *perf_reg_name(int id) +static inline const char *__perf_reg_name(int id) { switch (id) { case PERF_REG_X86_AX: diff --git a/tools/perf/arch/x86/tests/Build b/tools/perf/arch/x86/tests/Build index 36d4f248b51d..28d793390198 100644 --- a/tools/perf/arch/x86/tests/Build +++ b/tools/perf/arch/x86/tests/Build @@ -3,5 +3,6 @@ perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o perf-y += arch-tests.o perf-y += rdpmc.o +perf-y += sample-parsing.o perf-$(CONFIG_AUXTRACE) += insn-x86.o intel-pt-pkt-decoder-test.o perf-$(CONFIG_X86_64) += bp-modify.o diff --git a/tools/perf/arch/x86/tests/arch-tests.c b/tools/perf/arch/x86/tests/arch-tests.c index bc25d727b4e9..71aa67367ad6 100644 --- a/tools/perf/arch/x86/tests/arch-tests.c +++ b/tools/perf/arch/x86/tests/arch-tests.c @@ -31,6 +31,10 @@ struct test arch_tests[] = { }, #endif { + .desc = "x86 Sample parsing", + .func = test__x86_sample_parsing, + }, + { .func = NULL, }, diff --git a/tools/perf/arch/x86/tests/insn-x86.c b/tools/perf/arch/x86/tests/insn-x86.c index 745f29adb14b..4f75ae990140 100644 --- a/tools/perf/arch/x86/tests/insn-x86.c +++ b/tools/perf/arch/x86/tests/insn-x86.c @@ -1,11 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/types.h> -#include "../../../../arch/x86/include/asm/insn.h" #include <string.h> #include "debug.h" #include "tests/tests.h" #include "arch-tests.h" +#include "../../../../arch/x86/include/asm/insn.h" #include "intel-pt-decoder/intel-pt-insn-decoder.h" @@ -48,6 +48,7 @@ static int get_op(const char *op_str) {"int", INTEL_PT_OP_INT}, {"syscall", INTEL_PT_OP_SYSCALL}, {"sysret", INTEL_PT_OP_SYSRET}, + {"vmentry", INTEL_PT_OP_VMENTRY}, {NULL, 0}, }; struct val_data *val; diff --git a/tools/perf/arch/x86/tests/intel-pt-pkt-decoder-test.c b/tools/perf/arch/x86/tests/intel-pt-pkt-decoder-test.c index 901bf1f449c4..c933e3dcd0a8 100644 --- a/tools/perf/arch/x86/tests/intel-pt-pkt-decoder-test.c +++ b/tools/perf/arch/x86/tests/intel-pt-pkt-decoder-test.c @@ -66,8 +66,8 @@ struct test_data { {7, {0x9d, 1, 2, 3, 4, 5, 6}, 0, {INTEL_PT_FUP, 4, 0x60504030201}, 0, 0 }, {9, {0xdd, 1, 2, 3, 4, 5, 6, 7, 8}, 0, {INTEL_PT_FUP, 6, 0x807060504030201}, 0, 0 }, /* Paging Information Packet */ - {8, {0x02, 0x43, 2, 4, 6, 8, 10, 12}, 0, {INTEL_PT_PIP, 0, 0x60504030201}, 0, 0 }, - {8, {0x02, 0x43, 3, 4, 6, 8, 10, 12}, 0, {INTEL_PT_PIP, 0, 0x60504030201 | (1ULL << 63)}, 0, 0 }, + {8, {0x02, 0x43, 2, 4, 6, 8, 10, 12}, 0, {INTEL_PT_PIP, 0, 0xC0A08060402}, 0, 0 }, + {8, {0x02, 0x43, 3, 4, 6, 8, 10, 12}, 0, {INTEL_PT_PIP, 0, 0xC0A08060403}, 0, 0 }, /* Mode Exec Packet */ {2, {0x99, 0x00}, 0, {INTEL_PT_MODE_EXEC, 0, 16}, 0, 0 }, {2, {0x99, 0x01}, 0, {INTEL_PT_MODE_EXEC, 0, 64}, 0, 0 }, diff --git a/tools/perf/arch/x86/tests/sample-parsing.c b/tools/perf/arch/x86/tests/sample-parsing.c new file mode 100644 index 000000000000..c92db87e4479 --- /dev/null +++ b/tools/perf/arch/x86/tests/sample-parsing.c @@ -0,0 +1,121 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <stdbool.h> +#include <inttypes.h> +#include <stdlib.h> +#include <string.h> +#include <linux/bitops.h> +#include <linux/kernel.h> +#include <linux/types.h> + +#include "event.h" +#include "evsel.h" +#include "debug.h" +#include "util/synthetic-events.h" + +#include "tests/tests.h" +#include "arch-tests.h" + +#define COMP(m) do { \ + if (s1->m != s2->m) { \ + pr_debug("Samples differ at '"#m"'\n"); \ + return false; \ + } \ +} while (0) + +static bool samples_same(const struct perf_sample *s1, + const struct perf_sample *s2, + u64 type) +{ + if (type & PERF_SAMPLE_WEIGHT_STRUCT) + COMP(ins_lat); + + return true; +} + +static int do_test(u64 sample_type) +{ + struct evsel evsel = { + .needs_swap = false, + .core = { + . attr = { + .sample_type = sample_type, + .read_format = 0, + }, + }, + }; + union perf_event *event; + struct perf_sample sample = { + .weight = 101, + .ins_lat = 102, + }; + struct perf_sample sample_out; + size_t i, sz, bufsz; + int err, ret = -1; + + sz = perf_event__sample_event_size(&sample, sample_type, 0); + bufsz = sz + 4096; /* Add a bit for overrun checking */ + event = malloc(bufsz); + if (!event) { + pr_debug("malloc failed\n"); + return -1; + } + + memset(event, 0xff, bufsz); + event->header.type = PERF_RECORD_SAMPLE; + event->header.misc = 0; + event->header.size = sz; + + err = perf_event__synthesize_sample(event, sample_type, 0, &sample); + if (err) { + pr_debug("%s failed for sample_type %#"PRIx64", error %d\n", + "perf_event__synthesize_sample", sample_type, err); + goto out_free; + } + + /* The data does not contain 0xff so we use that to check the size */ + for (i = bufsz; i > 0; i--) { + if (*(i - 1 + (u8 *)event) != 0xff) + break; + } + if (i != sz) { + pr_debug("Event size mismatch: actual %zu vs expected %zu\n", + i, sz); + goto out_free; + } + + evsel.sample_size = __evsel__sample_size(sample_type); + + err = evsel__parse_sample(&evsel, event, &sample_out); + if (err) { + pr_debug("%s failed for sample_type %#"PRIx64", error %d\n", + "evsel__parse_sample", sample_type, err); + goto out_free; + } + + if (!samples_same(&sample, &sample_out, sample_type)) { + pr_debug("parsing failed for sample_type %#"PRIx64"\n", + sample_type); + goto out_free; + } + + ret = 0; +out_free: + free(event); + + return ret; +} + +/** + * test__x86_sample_parsing - test X86 specific sample parsing + * + * This function implements a test that synthesizes a sample event, parses it + * and then checks that the parsed sample matches the original sample. If the + * test passes %0 is returned, otherwise %-1 is returned. + * + * For now, the PERF_SAMPLE_WEIGHT_STRUCT is the only X86 specific sample type. + * The test only checks the PERF_SAMPLE_WEIGHT_STRUCT type. + */ +int test__x86_sample_parsing(struct test *test __maybe_unused, int subtest __maybe_unused) +{ + return do_test(PERF_SAMPLE_WEIGHT_STRUCT); +} diff --git a/tools/perf/arch/x86/util/Build b/tools/perf/arch/x86/util/Build index 347c39b960eb..0c72d418932e 100644 --- a/tools/perf/arch/x86/util/Build +++ b/tools/perf/arch/x86/util/Build @@ -6,6 +6,9 @@ perf-y += perf_regs.o perf-y += topdown.o perf-y += machine.o perf-y += event.o +perf-y += evlist.o +perf-y += mem-events.o +perf-y += evsel.o perf-$(CONFIG_DWARF) += dwarf-regs.o perf-$(CONFIG_BPF_PROLOGUE) += dwarf-regs.o diff --git a/tools/perf/arch/x86/util/archinsn.c b/tools/perf/arch/x86/util/archinsn.c index 3e6791531ca5..34d600c51044 100644 --- a/tools/perf/arch/x86/util/archinsn.c +++ b/tools/perf/arch/x86/util/archinsn.c @@ -1,10 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 -#include "../../../../arch/x86/include/asm/insn.h" #include "archinsn.h" #include "event.h" #include "machine.h" #include "thread.h" #include "symbol.h" +#include "../../../../arch/x86/include/asm/insn.h" void arch_fetch_insn(struct perf_sample *sample, struct thread *thread, diff --git a/tools/perf/arch/x86/util/event.c b/tools/perf/arch/x86/util/event.c index 047dc00eafa6..9b31734ee968 100644 --- a/tools/perf/arch/x86/util/event.c +++ b/tools/perf/arch/x86/util/event.c @@ -75,3 +75,28 @@ int perf_event__synthesize_extra_kmaps(struct perf_tool *tool, } #endif + +void arch_perf_parse_sample_weight(struct perf_sample *data, + const __u64 *array, u64 type) +{ + union perf_sample_weight weight; + + weight.full = *array; + if (type & PERF_SAMPLE_WEIGHT) + data->weight = weight.full; + else { + data->weight = weight.var1_dw; + data->ins_lat = weight.var2_w; + } +} + +void arch_perf_synthesize_sample_weight(const struct perf_sample *data, + __u64 *array, u64 type) +{ + *array = data->weight; + + if (type & PERF_SAMPLE_WEIGHT_STRUCT) { + *array &= 0xffffffff; + *array |= ((u64)data->ins_lat << 32); + } +} diff --git a/tools/perf/arch/x86/util/evlist.c b/tools/perf/arch/x86/util/evlist.c new file mode 100644 index 000000000000..8c6732cc7794 --- /dev/null +++ b/tools/perf/arch/x86/util/evlist.c @@ -0,0 +1,15 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdio.h> +#include "util/pmu.h" +#include "util/evlist.h" +#include "util/parse-events.h" + +#define TOPDOWN_L1_EVENTS "{slots,topdown-retiring,topdown-bad-spec,topdown-fe-bound,topdown-be-bound}" + +int arch_evlist__add_default_attrs(struct evlist *evlist) +{ + if (!pmu_have_event("cpu", "slots")) + return 0; + + return parse_events(evlist, TOPDOWN_L1_EVENTS, NULL); +} diff --git a/tools/perf/arch/x86/util/evsel.c b/tools/perf/arch/x86/util/evsel.c new file mode 100644 index 000000000000..2f733cdc8dbb --- /dev/null +++ b/tools/perf/arch/x86/util/evsel.c @@ -0,0 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdio.h> +#include "util/evsel.h" + +void arch_evsel__set_sample_weight(struct evsel *evsel) +{ + evsel__set_sample_bit(evsel, WEIGHT_STRUCT); +} diff --git a/tools/perf/arch/x86/util/mem-events.c b/tools/perf/arch/x86/util/mem-events.c new file mode 100644 index 000000000000..588110fd8904 --- /dev/null +++ b/tools/perf/arch/x86/util/mem-events.c @@ -0,0 +1,44 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "util/pmu.h" +#include "map_symbol.h" +#include "mem-events.h" + +static char mem_loads_name[100]; +static bool mem_loads_name__init; + +#define MEM_LOADS_AUX 0x8203 +#define MEM_LOADS_AUX_NAME "{cpu/mem-loads-aux/,cpu/mem-loads,ldlat=%u/pp}:S" + +bool is_mem_loads_aux_event(struct evsel *leader) +{ + if (!pmu_have_event("cpu", "mem-loads-aux")) + return false; + + return leader->core.attr.config == MEM_LOADS_AUX; +} + +char *perf_mem_events__name(int i) +{ + struct perf_mem_event *e = perf_mem_events__ptr(i); + + if (!e) + return NULL; + + if (i == PERF_MEM_EVENTS__LOAD) { + if (mem_loads_name__init) + return mem_loads_name; + + mem_loads_name__init = true; + + if (pmu_have_event("cpu", "mem-loads-aux")) { + scnprintf(mem_loads_name, sizeof(mem_loads_name), + MEM_LOADS_AUX_NAME, perf_mem_events__loads_ldlat); + } else { + scnprintf(mem_loads_name, sizeof(mem_loads_name), + e->name, perf_mem_events__loads_ldlat); + } + return mem_loads_name; + } + + return (char *)e->name; +} |