diff options
46 files changed, 1931 insertions, 287 deletions
diff --git a/kernel/events/core.c b/kernel/events/core.c index 1032a16bd186..72d06e302e99 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -7189,6 +7189,7 @@ static void perf_event_mmap_output(struct perf_event *event, struct perf_output_handle handle; struct perf_sample_data sample; int size = mmap_event->event_id.header.size; + u32 type = mmap_event->event_id.header.type; int ret; if (!perf_event_mmap_match(event, data)) @@ -7232,6 +7233,7 @@ static void perf_event_mmap_output(struct perf_event *event, perf_output_end(&handle); out: mmap_event->event_id.header.size = size; + mmap_event->event_id.header.type = type; } static void perf_event_mmap_event(struct perf_mmap_event *mmap_event) diff --git a/tools/arch/arm64/include/uapi/asm/unistd.h b/tools/arch/arm64/include/uapi/asm/unistd.h index dae1584cf017..4703d218663a 100644 --- a/tools/arch/arm64/include/uapi/asm/unistd.h +++ b/tools/arch/arm64/include/uapi/asm/unistd.h @@ -17,5 +17,7 @@ #define __ARCH_WANT_RENAMEAT #define __ARCH_WANT_NEW_STAT +#define __ARCH_WANT_SET_GET_RLIMIT +#define __ARCH_WANT_TIME32_SYSCALLS #include <asm-generic/unistd.h> diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index d90127298f12..12cdf611d217 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -38,8 +38,10 @@ __SYSCALL(__NR_io_destroy, sys_io_destroy) __SC_COMP(__NR_io_submit, sys_io_submit, compat_sys_io_submit) #define __NR_io_cancel 3 __SYSCALL(__NR_io_cancel, sys_io_cancel) +#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 #define __NR_io_getevents 4 -__SC_COMP(__NR_io_getevents, sys_io_getevents, compat_sys_io_getevents) +__SC_3264(__NR_io_getevents, sys_io_getevents_time32, sys_io_getevents) +#endif /* fs/xattr.c */ #define __NR_setxattr 5 @@ -179,7 +181,7 @@ __SYSCALL(__NR_fchownat, sys_fchownat) #define __NR_fchown 55 __SYSCALL(__NR_fchown, sys_fchown) #define __NR_openat 56 -__SC_COMP(__NR_openat, sys_openat, compat_sys_openat) +__SYSCALL(__NR_openat, sys_openat) #define __NR_close 57 __SYSCALL(__NR_close, sys_close) #define __NR_vhangup 58 @@ -222,10 +224,12 @@ __SC_COMP(__NR_pwritev, sys_pwritev, compat_sys_pwritev) __SYSCALL(__NR3264_sendfile, sys_sendfile64) /* fs/select.c */ +#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 #define __NR_pselect6 72 -__SC_COMP(__NR_pselect6, sys_pselect6, compat_sys_pselect6) +__SC_COMP_3264(__NR_pselect6, sys_pselect6_time32, sys_pselect6, compat_sys_pselect6_time32) #define __NR_ppoll 73 -__SC_COMP(__NR_ppoll, sys_ppoll, compat_sys_ppoll) +__SC_COMP_3264(__NR_ppoll, sys_ppoll_time32, sys_ppoll, compat_sys_ppoll_time32) +#endif /* fs/signalfd.c */ #define __NR_signalfd4 74 @@ -269,16 +273,20 @@ __SC_COMP(__NR_sync_file_range, sys_sync_file_range, \ /* fs/timerfd.c */ #define __NR_timerfd_create 85 __SYSCALL(__NR_timerfd_create, sys_timerfd_create) +#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 #define __NR_timerfd_settime 86 -__SC_COMP(__NR_timerfd_settime, sys_timerfd_settime, \ - compat_sys_timerfd_settime) +__SC_3264(__NR_timerfd_settime, sys_timerfd_settime32, \ + sys_timerfd_settime) #define __NR_timerfd_gettime 87 -__SC_COMP(__NR_timerfd_gettime, sys_timerfd_gettime, \ - compat_sys_timerfd_gettime) +__SC_3264(__NR_timerfd_gettime, sys_timerfd_gettime32, \ + sys_timerfd_gettime) +#endif /* fs/utimes.c */ +#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 #define __NR_utimensat 88 -__SC_COMP(__NR_utimensat, sys_utimensat, compat_sys_utimensat) +__SC_3264(__NR_utimensat, sys_utimensat_time32, sys_utimensat) +#endif /* kernel/acct.c */ #define __NR_acct 89 @@ -309,8 +317,10 @@ __SYSCALL(__NR_set_tid_address, sys_set_tid_address) __SYSCALL(__NR_unshare, sys_unshare) /* kernel/futex.c */ +#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 #define __NR_futex 98 -__SC_COMP(__NR_futex, sys_futex, compat_sys_futex) +__SC_3264(__NR_futex, sys_futex_time32, sys_futex) +#endif #define __NR_set_robust_list 99 __SC_COMP(__NR_set_robust_list, sys_set_robust_list, \ compat_sys_set_robust_list) @@ -319,8 +329,10 @@ __SC_COMP(__NR_get_robust_list, sys_get_robust_list, \ compat_sys_get_robust_list) /* kernel/hrtimer.c */ +#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 #define __NR_nanosleep 101 -__SC_COMP(__NR_nanosleep, sys_nanosleep, compat_sys_nanosleep) +__SC_3264(__NR_nanosleep, sys_nanosleep_time32, sys_nanosleep) +#endif /* kernel/itimer.c */ #define __NR_getitimer 102 @@ -341,23 +353,29 @@ __SYSCALL(__NR_delete_module, sys_delete_module) /* kernel/posix-timers.c */ #define __NR_timer_create 107 __SC_COMP(__NR_timer_create, sys_timer_create, compat_sys_timer_create) +#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 #define __NR_timer_gettime 108 -__SC_COMP(__NR_timer_gettime, sys_timer_gettime, compat_sys_timer_gettime) +__SC_3264(__NR_timer_gettime, sys_timer_gettime32, sys_timer_gettime) +#endif #define __NR_timer_getoverrun 109 __SYSCALL(__NR_timer_getoverrun, sys_timer_getoverrun) +#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 #define __NR_timer_settime 110 -__SC_COMP(__NR_timer_settime, sys_timer_settime, compat_sys_timer_settime) +__SC_3264(__NR_timer_settime, sys_timer_settime32, sys_timer_settime) +#endif #define __NR_timer_delete 111 __SYSCALL(__NR_timer_delete, sys_timer_delete) +#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 #define __NR_clock_settime 112 -__SC_COMP(__NR_clock_settime, sys_clock_settime, compat_sys_clock_settime) +__SC_3264(__NR_clock_settime, sys_clock_settime32, sys_clock_settime) #define __NR_clock_gettime 113 -__SC_COMP(__NR_clock_gettime, sys_clock_gettime, compat_sys_clock_gettime) +__SC_3264(__NR_clock_gettime, sys_clock_gettime32, sys_clock_gettime) #define __NR_clock_getres 114 -__SC_COMP(__NR_clock_getres, sys_clock_getres, compat_sys_clock_getres) +__SC_3264(__NR_clock_getres, sys_clock_getres_time32, sys_clock_getres) #define __NR_clock_nanosleep 115 -__SC_COMP(__NR_clock_nanosleep, sys_clock_nanosleep, \ - compat_sys_clock_nanosleep) +__SC_3264(__NR_clock_nanosleep, sys_clock_nanosleep_time32, \ + sys_clock_nanosleep) +#endif /* kernel/printk.c */ #define __NR_syslog 116 @@ -388,9 +406,11 @@ __SYSCALL(__NR_sched_yield, sys_sched_yield) __SYSCALL(__NR_sched_get_priority_max, sys_sched_get_priority_max) #define __NR_sched_get_priority_min 126 __SYSCALL(__NR_sched_get_priority_min, sys_sched_get_priority_min) +#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 #define __NR_sched_rr_get_interval 127 -__SC_COMP(__NR_sched_rr_get_interval, sys_sched_rr_get_interval, \ - compat_sys_sched_rr_get_interval) +__SC_3264(__NR_sched_rr_get_interval, sys_sched_rr_get_interval_time32, \ + sys_sched_rr_get_interval) +#endif /* kernel/signal.c */ #define __NR_restart_syscall 128 @@ -411,9 +431,11 @@ __SC_COMP(__NR_rt_sigaction, sys_rt_sigaction, compat_sys_rt_sigaction) __SC_COMP(__NR_rt_sigprocmask, sys_rt_sigprocmask, compat_sys_rt_sigprocmask) #define __NR_rt_sigpending 136 __SC_COMP(__NR_rt_sigpending, sys_rt_sigpending, compat_sys_rt_sigpending) +#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 #define __NR_rt_sigtimedwait 137 -__SC_COMP(__NR_rt_sigtimedwait, sys_rt_sigtimedwait, \ - compat_sys_rt_sigtimedwait) +__SC_COMP_3264(__NR_rt_sigtimedwait, sys_rt_sigtimedwait_time32, \ + sys_rt_sigtimedwait, compat_sys_rt_sigtimedwait_time32) +#endif #define __NR_rt_sigqueueinfo 138 __SC_COMP(__NR_rt_sigqueueinfo, sys_rt_sigqueueinfo, \ compat_sys_rt_sigqueueinfo) @@ -467,10 +489,15 @@ __SYSCALL(__NR_uname, sys_newuname) __SYSCALL(__NR_sethostname, sys_sethostname) #define __NR_setdomainname 162 __SYSCALL(__NR_setdomainname, sys_setdomainname) + +#ifdef __ARCH_WANT_SET_GET_RLIMIT +/* getrlimit and setrlimit are superseded with prlimit64 */ #define __NR_getrlimit 163 __SC_COMP(__NR_getrlimit, sys_getrlimit, compat_sys_getrlimit) #define __NR_setrlimit 164 __SC_COMP(__NR_setrlimit, sys_setrlimit, compat_sys_setrlimit) +#endif + #define __NR_getrusage 165 __SC_COMP(__NR_getrusage, sys_getrusage, compat_sys_getrusage) #define __NR_umask 166 @@ -481,12 +508,14 @@ __SYSCALL(__NR_prctl, sys_prctl) __SYSCALL(__NR_getcpu, sys_getcpu) /* kernel/time.c */ +#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 #define __NR_gettimeofday 169 __SC_COMP(__NR_gettimeofday, sys_gettimeofday, compat_sys_gettimeofday) #define __NR_settimeofday 170 __SC_COMP(__NR_settimeofday, sys_settimeofday, compat_sys_settimeofday) #define __NR_adjtimex 171 -__SC_COMP(__NR_adjtimex, sys_adjtimex, compat_sys_adjtimex) +__SC_3264(__NR_adjtimex, sys_adjtimex_time32, sys_adjtimex) +#endif /* kernel/timer.c */ #define __NR_getpid 172 @@ -511,11 +540,13 @@ __SC_COMP(__NR_sysinfo, sys_sysinfo, compat_sys_sysinfo) __SC_COMP(__NR_mq_open, sys_mq_open, compat_sys_mq_open) #define __NR_mq_unlink 181 __SYSCALL(__NR_mq_unlink, sys_mq_unlink) +#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 #define __NR_mq_timedsend 182 -__SC_COMP(__NR_mq_timedsend, sys_mq_timedsend, compat_sys_mq_timedsend) +__SC_3264(__NR_mq_timedsend, sys_mq_timedsend_time32, sys_mq_timedsend) #define __NR_mq_timedreceive 183 -__SC_COMP(__NR_mq_timedreceive, sys_mq_timedreceive, \ - compat_sys_mq_timedreceive) +__SC_3264(__NR_mq_timedreceive, sys_mq_timedreceive_time32, \ + sys_mq_timedreceive) +#endif #define __NR_mq_notify 184 __SC_COMP(__NR_mq_notify, sys_mq_notify, compat_sys_mq_notify) #define __NR_mq_getsetattr 185 @@ -536,8 +567,10 @@ __SC_COMP(__NR_msgsnd, sys_msgsnd, compat_sys_msgsnd) __SYSCALL(__NR_semget, sys_semget) #define __NR_semctl 191 __SC_COMP(__NR_semctl, sys_semctl, compat_sys_semctl) +#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 #define __NR_semtimedop 192 -__SC_COMP(__NR_semtimedop, sys_semtimedop, compat_sys_semtimedop) +__SC_COMP(__NR_semtimedop, sys_semtimedop, sys_semtimedop_time32) +#endif #define __NR_semop 193 __SYSCALL(__NR_semop, sys_semop) @@ -658,8 +691,10 @@ __SC_COMP(__NR_rt_tgsigqueueinfo, sys_rt_tgsigqueueinfo, \ __SYSCALL(__NR_perf_event_open, sys_perf_event_open) #define __NR_accept4 242 __SYSCALL(__NR_accept4, sys_accept4) +#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 #define __NR_recvmmsg 243 -__SC_COMP(__NR_recvmmsg, sys_recvmmsg, compat_sys_recvmmsg) +__SC_COMP_3264(__NR_recvmmsg, sys_recvmmsg_time32, sys_recvmmsg, compat_sys_recvmmsg_time32) +#endif /* * Architectures may provide up to 16 syscalls of their own @@ -667,8 +702,10 @@ __SC_COMP(__NR_recvmmsg, sys_recvmmsg, compat_sys_recvmmsg) */ #define __NR_arch_specific_syscall 244 +#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 #define __NR_wait4 260 __SC_COMP(__NR_wait4, sys_wait4, compat_sys_wait4) +#endif #define __NR_prlimit64 261 __SYSCALL(__NR_prlimit64, sys_prlimit64) #define __NR_fanotify_init 262 @@ -678,10 +715,11 @@ __SYSCALL(__NR_fanotify_mark, sys_fanotify_mark) #define __NR_name_to_handle_at 264 __SYSCALL(__NR_name_to_handle_at, sys_name_to_handle_at) #define __NR_open_by_handle_at 265 -__SC_COMP(__NR_open_by_handle_at, sys_open_by_handle_at, \ - compat_sys_open_by_handle_at) +__SYSCALL(__NR_open_by_handle_at, sys_open_by_handle_at) +#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 #define __NR_clock_adjtime 266 -__SC_COMP(__NR_clock_adjtime, sys_clock_adjtime, compat_sys_clock_adjtime) +__SC_3264(__NR_clock_adjtime, sys_clock_adjtime32, sys_clock_adjtime) +#endif #define __NR_syncfs 267 __SYSCALL(__NR_syncfs, sys_syncfs) #define __NR_setns 268 @@ -734,15 +772,60 @@ __SYSCALL(__NR_pkey_alloc, sys_pkey_alloc) __SYSCALL(__NR_pkey_free, sys_pkey_free) #define __NR_statx 291 __SYSCALL(__NR_statx, sys_statx) +#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 #define __NR_io_pgetevents 292 -__SC_COMP(__NR_io_pgetevents, sys_io_pgetevents, compat_sys_io_pgetevents) +__SC_COMP_3264(__NR_io_pgetevents, sys_io_pgetevents_time32, sys_io_pgetevents, compat_sys_io_pgetevents) +#endif #define __NR_rseq 293 __SYSCALL(__NR_rseq, sys_rseq) #define __NR_kexec_file_load 294 __SYSCALL(__NR_kexec_file_load, sys_kexec_file_load) +/* 295 through 402 are unassigned to sync up with generic numbers, don't use */ +#if __BITS_PER_LONG == 32 +#define __NR_clock_gettime64 403 +__SYSCALL(__NR_clock_gettime64, sys_clock_gettime) +#define __NR_clock_settime64 404 +__SYSCALL(__NR_clock_settime64, sys_clock_settime) +#define __NR_clock_adjtime64 405 +__SYSCALL(__NR_clock_adjtime64, sys_clock_adjtime) +#define __NR_clock_getres_time64 406 +__SYSCALL(__NR_clock_getres_time64, sys_clock_getres) +#define __NR_clock_nanosleep_time64 407 +__SYSCALL(__NR_clock_nanosleep_time64, sys_clock_nanosleep) +#define __NR_timer_gettime64 408 +__SYSCALL(__NR_timer_gettime64, sys_timer_gettime) +#define __NR_timer_settime64 409 +__SYSCALL(__NR_timer_settime64, sys_timer_settime) +#define __NR_timerfd_gettime64 410 +__SYSCALL(__NR_timerfd_gettime64, sys_timerfd_gettime) +#define __NR_timerfd_settime64 411 +__SYSCALL(__NR_timerfd_settime64, sys_timerfd_settime) +#define __NR_utimensat_time64 412 +__SYSCALL(__NR_utimensat_time64, sys_utimensat) +#define __NR_pselect6_time64 413 +__SC_COMP(__NR_pselect6_time64, sys_pselect6, compat_sys_pselect6_time64) +#define __NR_ppoll_time64 414 +__SC_COMP(__NR_ppoll_time64, sys_ppoll, compat_sys_ppoll_time64) +#define __NR_io_pgetevents_time64 416 +__SYSCALL(__NR_io_pgetevents_time64, sys_io_pgetevents) +#define __NR_recvmmsg_time64 417 +__SC_COMP(__NR_recvmmsg_time64, sys_recvmmsg, compat_sys_recvmmsg_time64) +#define __NR_mq_timedsend_time64 418 +__SYSCALL(__NR_mq_timedsend_time64, sys_mq_timedsend) +#define __NR_mq_timedreceive_time64 419 +__SYSCALL(__NR_mq_timedreceive_time64, sys_mq_timedreceive) +#define __NR_semtimedop_time64 420 +__SYSCALL(__NR_semtimedop_time64, sys_semtimedop) +#define __NR_rt_sigtimedwait_time64 421 +__SC_COMP(__NR_rt_sigtimedwait_time64, sys_rt_sigtimedwait, compat_sys_rt_sigtimedwait_time64) +#define __NR_futex_time64 422 +__SYSCALL(__NR_futex_time64, sys_futex) +#define __NR_sched_rr_get_interval_time64 423 +__SYSCALL(__NR_sched_rr_get_interval_time64, sys_sched_rr_get_interval) +#endif #undef __NR_syscalls -#define __NR_syscalls 295 +#define __NR_syscalls 424 /* * 32 bit systems traditionally used different diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h index a55cb8b10165..e7ad9d350a28 100644 --- a/tools/include/uapi/linux/in.h +++ b/tools/include/uapi/linux/in.h @@ -292,10 +292,11 @@ struct sockaddr_in { #define IN_LOOPBACK(a) ((((long int) (a)) & 0xff000000) == 0x7f000000) /* Defines for Multicast INADDR */ -#define INADDR_UNSPEC_GROUP 0xe0000000U /* 224.0.0.0 */ -#define INADDR_ALLHOSTS_GROUP 0xe0000001U /* 224.0.0.1 */ -#define INADDR_ALLRTRS_GROUP 0xe0000002U /* 224.0.0.2 */ -#define INADDR_MAX_LOCAL_GROUP 0xe00000ffU /* 224.0.0.255 */ +#define INADDR_UNSPEC_GROUP 0xe0000000U /* 224.0.0.0 */ +#define INADDR_ALLHOSTS_GROUP 0xe0000001U /* 224.0.0.1 */ +#define INADDR_ALLRTRS_GROUP 0xe0000002U /* 224.0.0.2 */ +#define INADDR_ALLSNOOPERS_GROUP 0xe000006aU /* 224.0.0.106 */ +#define INADDR_MAX_LOCAL_GROUP 0xe00000ffU /* 224.0.0.255 */ #endif /* <asm/byteorder.h> contains the htonl type stuff.. */ diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index b4652aa1a58a..aa1521a51687 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -10,6 +10,7 @@ #ifndef __LIBBPF_LIBBPF_H #define __LIBBPF_LIBBPF_H +#include <stdarg.h> #include <stdio.h> #include <stdint.h> #include <stdbool.h> diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt index 86f3dcc15f83..95054a8176a2 100644 --- a/tools/perf/Documentation/perf-config.txt +++ b/tools/perf/Documentation/perf-config.txt @@ -584,6 +584,20 @@ llvm.*:: llvm.opts:: Options passed to llc. +samples.*:: + + samples.context:: + Define how many ns worth of time to show + around samples in perf report sample context browser. + +scripts.*:: + + Any option defines a script that is added to the scripts menu + in the interactive perf browser and whose output is displayed. + The name of the option is the name, the value is a script command line. + The script gets the same options passed as a full perf script, + in particular -i perfdata file, --cpu, --tid + SEE ALSO -------- linkperf:perf[1] diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index 1a27bfe05039..f441baa794ce 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -105,6 +105,8 @@ OPTIONS guest machine - sample: Number of sample - period: Raw number of event count of sample + - time: Separate the samples by time stamp with the resolution specified by + --time-quantum (default 100ms). Specify with overhead and before it. By default, comm, dso and symbol keys are used. (i.e. --sort comm,dso,symbol) @@ -459,6 +461,10 @@ include::itrace.txt[] --socket-filter:: Only report the samples on the processor socket that match with this filter +--samples=N:: + Save N individual samples for each histogram entry to show context in perf + report tui browser. + --raw-trace:: When displaying traceevent output, do not use print fmt or plugins. @@ -477,6 +483,9 @@ include::itrace.txt[] Please note that not all mmaps are stored, options affecting which ones are include 'perf record --data', for instance. +--ns:: + Show time stamps in nanoseconds. + --stats:: Display overall events statistics without any further processing. (like the one at the end of the perf report -D command) @@ -494,6 +503,10 @@ include::itrace.txt[] The period/hits keywords set the base the percentage is computed on - the samples period or the number of samples (hits). +--time-quantum:: + Configure time quantum for time sort key. Default 100ms. + Accepts s, us, ms, ns units. + include::callchain-overhead-calculation.txt[] SEE ALSO diff --git a/tools/perf/Documentation/tips.txt b/tools/perf/Documentation/tips.txt index 849599f39c5e..869965d629ce 100644 --- a/tools/perf/Documentation/tips.txt +++ b/tools/perf/Documentation/tips.txt @@ -15,6 +15,7 @@ To see callchains in a more compact form: perf report -g folded Show individual samples with: perf script Limit to show entries above 5% only: perf report --percent-limit 5 Profiling branch (mis)predictions with: perf record -b / perf report +To show assembler sample contexts use perf record -b / perf script -F +brstackinsn --xed Treat branches as callchains: perf report --branch-history To count events in every 1000 msec: perf stat -I 1000 Print event counts in CSV format with: perf stat -x, @@ -34,3 +35,9 @@ Show current config key-value pairs: perf config --list Show user configuration overrides: perf config --user --list To add Node.js USDT(User-Level Statically Defined Tracing): perf buildid-cache --add `which node` To report cacheline events from previous recording: perf c2c report +To browse sample contexts use perf report --sample 10 and select in context menu +To separate samples by time use perf report --sort time,overhead,sym +To set sample time separation other than 100ms with --sort time use --time-quantum +Add -I to perf report to sample register values visible in perf report context. +To show IPC for sampling periods use perf record -e '{cycles,instructions}:S' and then browse context +To show context switches in perf report sample context add --switch-events to perf record. diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index f0b1709a5ffb..2ae92fddb6d5 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -343,6 +343,8 @@ 332 common statx __x64_sys_statx 333 common io_pgetevents __x64_sys_io_pgetevents 334 common rseq __x64_sys_rseq +# don't use numbers 387 through 423, add new calls after the last +# 'common' entry # # x32-specific system call numbers start at 512 to avoid cache impact @@ -361,7 +363,7 @@ 520 x32 execve __x32_compat_sys_execve/ptregs 521 x32 ptrace __x32_compat_sys_ptrace 522 x32 rt_sigpending __x32_compat_sys_rt_sigpending -523 x32 rt_sigtimedwait __x32_compat_sys_rt_sigtimedwait +523 x32 rt_sigtimedwait __x32_compat_sys_rt_sigtimedwait_time64 524 x32 rt_sigqueueinfo __x32_compat_sys_rt_sigqueueinfo 525 x32 sigaltstack __x32_compat_sys_sigaltstack 526 x32 timer_create __x32_compat_sys_timer_create @@ -375,7 +377,7 @@ 534 x32 preadv __x32_compat_sys_preadv64 535 x32 pwritev __x32_compat_sys_pwritev64 536 x32 rt_tgsigqueueinfo __x32_compat_sys_rt_tgsigqueueinfo -537 x32 recvmmsg __x32_compat_sys_recvmmsg +537 x32 recvmmsg __x32_compat_sys_recvmmsg_time64 538 x32 sendmmsg __x32_compat_sys_sendmmsg 539 x32 process_vm_readv __x32_compat_sys_process_vm_readv 540 x32 process_vm_writev __x32_compat_sys_process_vm_writev diff --git a/tools/perf/arch/x86/util/Build b/tools/perf/arch/x86/util/Build index 7aab0be5fc5f..47f9c56e744f 100644 --- a/tools/perf/arch/x86/util/Build +++ b/tools/perf/arch/x86/util/Build @@ -14,5 +14,6 @@ perf-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o perf-$(CONFIG_AUXTRACE) += auxtrace.o +perf-$(CONFIG_AUXTRACE) += archinsn.o perf-$(CONFIG_AUXTRACE) += intel-pt.o perf-$(CONFIG_AUXTRACE) += intel-bts.o diff --git a/tools/perf/arch/x86/util/archinsn.c b/tools/perf/arch/x86/util/archinsn.c new file mode 100644 index 000000000000..4237bb2e7fa2 --- /dev/null +++ b/tools/perf/arch/x86/util/archinsn.c @@ -0,0 +1,26 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "perf.h" +#include "archinsn.h" +#include "util/intel-pt-decoder/insn.h" +#include "machine.h" +#include "thread.h" +#include "symbol.h" + +void arch_fetch_insn(struct perf_sample *sample, + struct thread *thread, + struct machine *machine) +{ + struct insn insn; + int len; + bool is64bit = false; + + if (!sample->ip) + return; + len = thread__memcpy(thread, machine, sample->insn, sample->ip, sizeof(sample->insn), &is64bit); + if (len <= 0) + return; + insn_init(&insn, sample->insn, len, is64bit); + insn_get_length(&insn); + if (insn_complete(&insn) && insn.length <= len) + sample->insn_len = insn.length; +} diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index f3f7f3100336..a468d882e74f 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -392,7 +392,7 @@ static int record__process_auxtrace(struct perf_tool *tool, size_t padding; u8 pad[8] = {0}; - if (!perf_data__is_pipe(data)) { + if (!perf_data__is_pipe(data) && !perf_data__is_dir(data)) { off_t file_offset; int fd = perf_data__fd(data); int err; @@ -837,6 +837,8 @@ static void record__init_features(struct record *rec) if (!(rec->opts.use_clockid && rec->opts.clockid_res_ns)) perf_header__clear_feat(&session->header, HEADER_CLOCKID); + perf_header__clear_feat(&session->header, HEADER_DIR_FORMAT); + perf_header__clear_feat(&session->header, HEADER_STAT); } diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index ee93c18a6685..1921aaa9cece 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -47,9 +47,11 @@ #include <errno.h> #include <inttypes.h> #include <regex.h> +#include "sane_ctype.h" #include <signal.h> #include <linux/bitmap.h> #include <linux/stringify.h> +#include <linux/time64.h> #include <sys/types.h> #include <sys/stat.h> #include <unistd.h> @@ -926,6 +928,43 @@ report_parse_callchain_opt(const struct option *opt, const char *arg, int unset) return parse_callchain_report_opt(arg); } +static int +parse_time_quantum(const struct option *opt, const char *arg, + int unset __maybe_unused) +{ + unsigned long *time_q = opt->value; + char *end; + + *time_q = strtoul(arg, &end, 0); + if (end == arg) + goto parse_err; + if (*time_q == 0) { + pr_err("time quantum cannot be 0"); + return -1; + } + while (isspace(*end)) + end++; + if (*end == 0) + return 0; + if (!strcmp(end, "s")) { + *time_q *= NSEC_PER_SEC; + return 0; + } + if (!strcmp(end, "ms")) { + *time_q *= NSEC_PER_MSEC; + return 0; + } + if (!strcmp(end, "us")) { + *time_q *= NSEC_PER_USEC; + return 0; + } + if (!strcmp(end, "ns")) + return 0; +parse_err: + pr_err("Cannot parse time quantum `%s'\n", arg); + return -1; +} + int report_parse_ignore_callees_opt(const struct option *opt __maybe_unused, const char *arg, int unset __maybe_unused) @@ -1120,6 +1159,8 @@ int cmd_report(int argc, const char **argv) OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel, "Enable kernel symbol demangling"), OPT_BOOLEAN(0, "mem-mode", &report.mem_mode, "mem access profile"), + OPT_INTEGER(0, "samples", &symbol_conf.res_sample, + "Number of samples to save per histogram entry for individual browsing"), OPT_CALLBACK(0, "percent-limit", &report, "percent", "Don't show entries under that percent", parse_percent_limit), OPT_CALLBACK(0, "percentage", NULL, "relative|absolute", @@ -1147,6 +1188,10 @@ int cmd_report(int argc, const char **argv) OPT_CALLBACK(0, "percent-type", &report.annotation_opts, "local-period", "Set percent type local/global-period/hits", annotate_parse_percent_type), + OPT_BOOLEAN(0, "ns", &symbol_conf.nanosecs, "Show times in nanosecs"), + 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), OPT_END() }; struct perf_data data = { diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 53f78cf3113f..2f93d60c5a17 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -29,10 +29,12 @@ #include "util/time-utils.h" #include "util/path.h" #include "print_binary.h" +#include "archinsn.h" #include <linux/bitmap.h> #include <linux/kernel.h> #include <linux/stringify.h> #include <linux/time64.h> +#include <sys/utsname.h> #include "asm/bug.h" #include "util/mem-events.h" #include "util/dump-insn.h" @@ -58,11 +60,11 @@ static bool no_callchain; static bool latency_format; static bool system_wide; static bool print_flags; -static bool nanosecs; static const char *cpu_list; static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); static struct perf_stat_config stat_config; static int max_blocks; +static bool native_arch; unsigned int scripting_max_stack = PERF_MAX_STACK_DEPTH; @@ -688,7 +690,7 @@ static int perf_sample__fprintf_start(struct perf_sample *sample, secs = nsecs / NSEC_PER_SEC; nsecs -= secs * NSEC_PER_SEC; - if (nanosecs) + if (symbol_conf.nanosecs) printed += fprintf(fp, "%5lu.%09llu: ", secs, nsecs); else { char sample_time[32]; @@ -1227,6 +1229,12 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample, return len + dlen; } +__weak void arch_fetch_insn(struct perf_sample *sample __maybe_unused, + struct thread *thread __maybe_unused, + struct machine *machine __maybe_unused) +{ +} + static int perf_sample__fprintf_insn(struct perf_sample *sample, struct perf_event_attr *attr, struct thread *thread, @@ -1234,9 +1242,12 @@ static int perf_sample__fprintf_insn(struct perf_sample *sample, { int printed = 0; + if (sample->insn_len == 0 && native_arch) + arch_fetch_insn(sample, thread, machine); + if (PRINT_FIELD(INSNLEN)) printed += fprintf(fp, " ilen: %d", sample->insn_len); - if (PRINT_FIELD(INSN)) { + if (PRINT_FIELD(INSN) && sample->insn_len) { int i; printed += fprintf(fp, " insn:"); @@ -1922,6 +1933,13 @@ static int cleanup_scripting(void) return scripting_ops ? scripting_ops->stop_script() : 0; } +static bool filter_cpu(struct perf_sample *sample) +{ + if (cpu_list) + return !test_bit(sample->cpu, cpu_bitmap); + return false; +} + static int process_sample_event(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -1956,7 +1974,7 @@ static int process_sample_event(struct perf_tool *tool, if (al.filtered) goto out_put; - if (cpu_list && !test_bit(sample->cpu, cpu_bitmap)) + if (filter_cpu(sample)) goto out_put; if (scripting_ops) @@ -2041,9 +2059,11 @@ static int process_comm_event(struct perf_tool *tool, sample->tid = event->comm.tid; sample->pid = event->comm.pid; } - perf_sample__fprintf_start(sample, thread, evsel, + if (!filter_cpu(sample)) { + perf_sample__fprintf_start(sample, thread, evsel, PERF_RECORD_COMM, stdout); - perf_event__fprintf(event, stdout); + perf_event__fprintf(event, stdout); + } ret = 0; out: thread__put(thread); @@ -2077,9 +2097,11 @@ static int process_namespaces_event(struct perf_tool *tool, sample->tid = event->namespaces.tid; sample->pid = event->namespaces.pid; } - perf_sample__fprintf_start(sample, thread, evsel, - PERF_RECORD_NAMESPACES, stdout); - perf_event__fprintf(event, stdout); + if (!filter_cpu(sample)) { + perf_sample__fprintf_start(sample, thread, evsel, + PERF_RECORD_NAMESPACES, stdout); + perf_event__fprintf(event, stdout); + } ret = 0; out: thread__put(thread); @@ -2111,9 +2133,11 @@ static int process_fork_event(struct perf_tool *tool, sample->tid = event->fork.tid; sample->pid = event->fork.pid; } - perf_sample__fprintf_start(sample, thread, evsel, - PERF_RECORD_FORK, stdout); - perf_event__fprintf(event, stdout); + if (!filter_cpu(sample)) { + perf_sample__fprintf_start(sample, thread, evsel, + PERF_RECORD_FORK, stdout); + perf_event__fprintf(event, stdout); + } thread__put(thread); return 0; @@ -2141,9 +2165,11 @@ static int process_exit_event(struct perf_tool *tool, sample->tid = event->fork.tid; sample->pid = event->fork.pid; } - perf_sample__fprintf_start(sample, thread, evsel, - PERF_RECORD_EXIT, stdout); - perf_event__fprintf(event, stdout); + if (!filter_cpu(sample)) { + perf_sample__fprintf_start(sample, thread, evsel, + PERF_RECORD_EXIT, stdout); + perf_event__fprintf(event, stdout); + } if (perf_event__process_exit(tool, event, sample, machine) < 0) err = -1; @@ -2177,9 +2203,11 @@ static int process_mmap_event(struct perf_tool *tool, sample->tid = event->mmap.tid; sample->pid = event->mmap.pid; } - perf_sample__fprintf_start(sample, thread, evsel, - PERF_RECORD_MMAP, stdout); - perf_event__fprintf(event, stdout); + if (!filter_cpu(sample)) { + perf_sample__fprintf_start(sample, thread, evsel, + PERF_RECORD_MMAP, stdout); + perf_event__fprintf(event, stdout); + } thread__put(thread); return 0; } @@ -2209,9 +2237,11 @@ static int process_mmap2_event(struct perf_tool *tool, sample->tid = event->mmap2.tid; sample->pid = event->mmap2.pid; } - perf_sample__fprintf_start(sample, thread, evsel, - PERF_RECORD_MMAP2, stdout); - perf_event__fprintf(event, stdout); + if (!filter_cpu(sample)) { + perf_sample__fprintf_start(sample, thread, evsel, + PERF_RECORD_MMAP2, stdout); + perf_event__fprintf(event, stdout); + } thread__put(thread); return 0; } @@ -2236,9 +2266,11 @@ static int process_switch_event(struct perf_tool *tool, return -1; } - perf_sample__fprintf_start(sample, thread, evsel, - PERF_RECORD_SWITCH, stdout); - perf_event__fprintf(event, stdout); + if (!filter_cpu(sample)) { + perf_sample__fprintf_start(sample, thread, evsel, + PERF_RECORD_SWITCH, stdout); + perf_event__fprintf(event, stdout); + } thread__put(thread); return 0; } @@ -2259,9 +2291,11 @@ process_lost_event(struct perf_tool *tool, if (thread == NULL) return -1; - perf_sample__fprintf_start(sample, thread, evsel, - PERF_RECORD_LOST, stdout); - perf_event__fprintf(event, stdout); + if (!filter_cpu(sample)) { + perf_sample__fprintf_start(sample, thread, evsel, + PERF_RECORD_LOST, stdout); + perf_event__fprintf(event, stdout); + } thread__put(thread); return 0; } @@ -2948,7 +2982,8 @@ static int check_ev_match(char *dir_name, char *scriptname, * will list all statically runnable scripts, select one, execute it and * show the output in a perf browser. */ -int find_scripts(char **scripts_array, char **scripts_path_array) +int find_scripts(char **scripts_array, char **scripts_path_array, int num, + int pathlen) { struct dirent *script_dirent, *lang_dirent; char scripts_path[MAXPATHLEN], lang_path[MAXPATHLEN]; @@ -2993,7 +3028,10 @@ int find_scripts(char **scripts_array, char **scripts_path_array) /* Skip those real time scripts: xxxtop.p[yl] */ if (strstr(script_dirent->d_name, "top.")) continue; - sprintf(scripts_path_array[i], "%s/%s", lang_path, + if (i >= num) + break; + snprintf(scripts_path_array[i], pathlen, "%s/%s", + lang_path, script_dirent->d_name); temp = strchr(script_dirent->d_name, '.'); snprintf(scripts_array[i], @@ -3232,7 +3270,7 @@ static int parse_insn_trace(const struct option *opt __maybe_unused, { parse_output_fields(NULL, "+insn,-event,-period", 0); itrace_parse_synth_opts(opt, "i0ns", 0); - nanosecs = true; + symbol_conf.nanosecs = true; return 0; } @@ -3250,7 +3288,7 @@ static int parse_call_trace(const struct option *opt __maybe_unused, { parse_output_fields(NULL, "-ip,-addr,-event,-period,+callindent", 0); itrace_parse_synth_opts(opt, "cewp", 0); - nanosecs = true; + symbol_conf.nanosecs = true; return 0; } @@ -3260,7 +3298,7 @@ static int parse_callret_trace(const struct option *opt __maybe_unused, { parse_output_fields(NULL, "-ip,-addr,-event,-period,+callindent,+flags", 0); itrace_parse_synth_opts(opt, "crewp", 0); - nanosecs = true; + symbol_conf.nanosecs = true; return 0; } @@ -3277,6 +3315,7 @@ int cmd_script(int argc, const char **argv) .set = false, .default_no_sample = true, }; + struct utsname uts; char *script_path = NULL; const char **__argv; int i, j, err = 0; @@ -3395,7 +3434,7 @@ int cmd_script(int argc, const char **argv) OPT_BOOLEAN('f', "force", &symbol_conf.force, "don't complain, do it"), OPT_INTEGER(0, "max-blocks", &max_blocks, "Maximum number of code blocks to dump with brstackinsn"), - OPT_BOOLEAN(0, "ns", &nanosecs, + OPT_BOOLEAN(0, "ns", &symbol_conf.nanosecs, "Use 9 decimal places when displaying time"), OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts", "Instruction Tracing options\n" ITRACE_HELP, @@ -3615,6 +3654,12 @@ int cmd_script(int argc, const char **argv) if (symbol__init(&session->header.env) < 0) goto out_delete; + uname(&uts); + if (!strcmp(uts.machine, session->header.env.arch) || + (!strcmp(uts.machine, "x86_64") && + !strcmp(session->header.env.arch, "i386"))) + native_arch = true; + script.session = session; script__setup_sample_type(&script); diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h index 05745f3ce912..999fe9170122 100644 --- a/tools/perf/builtin.h +++ b/tools/perf/builtin.h @@ -40,5 +40,6 @@ int cmd_mem(int argc, const char **argv); int cmd_data(int argc, const char **argv); int cmd_ftrace(int argc, const char **argv); -int find_scripts(char **scripts_array, char **scripts_path_array); +int find_scripts(char **scripts_array, char **scripts_path_array, int num, + int pathlen); #endif diff --git a/tools/perf/pmu-events/arch/x86/amdfam17h/branch.json b/tools/perf/pmu-events/arch/x86/amdfam17h/branch.json new file mode 100644 index 000000000000..93ddfd8053ca --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/amdfam17h/branch.json @@ -0,0 +1,12 @@ +[ + { + "EventName": "bp_l1_btb_correct", + "EventCode": "0x8a", + "BriefDescription": "L1 BTB Correction." + }, + { + "EventName": "bp_l2_btb_correct", + "EventCode": "0x8b", + "BriefDescription": "L2 BTB Correction." + } +] diff --git a/tools/perf/pmu-events/arch/x86/amdfam17h/cache.json b/tools/perf/pmu-events/arch/x86/amdfam17h/cache.json new file mode 100644 index 000000000000..fad4af9142cb --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/amdfam17h/cache.json @@ -0,0 +1,287 @@ +[ + { + "EventName": "ic_fw32", + "EventCode": "0x80", + "BriefDescription": "The number of 32B fetch windows transferred from IC pipe to DE instruction decoder (includes non-cacheable and cacheable fill responses)." + }, + { + "EventName": "ic_fw32_miss", + "EventCode": "0x81", + "BriefDescription": "The number of 32B fetch windows tried to read the L1 IC and missed in the full tag." + }, + { + "EventName": "ic_cache_fill_l2", + "EventCode": "0x82", + "BriefDescription": "The number of 64 byte instruction cache line was fulfilled from the L2 cache." + }, + { + "EventName": "ic_cache_fill_sys", + "EventCode": "0x83", + "BriefDescription": "The number of 64 byte instruction cache line fulfilled from system memory or another cache." + }, + { + "EventName": "bp_l1_tlb_miss_l2_hit", + "EventCode": "0x84", + "BriefDescription": "The number of instruction fetches that miss in the L1 ITLB but hit in the L2 ITLB." + }, + { + "EventName": "bp_l1_tlb_miss_l2_miss", + "EventCode": "0x85", + "BriefDescription": "The number of instruction fetches that miss in both the L1 and L2 TLBs." + }, + { + "EventName": "bp_snp_re_sync", + "EventCode": "0x86", + "BriefDescription": "The number of pipeline restarts caused by invalidating probes that hit on the instruction stream currently being executed. This would happen if the active instruction stream was being modified by another processor in an MP system - typically a highly unlikely event." + }, + { + "EventName": "ic_fetch_stall.ic_stall_any", + "EventCode": "0x87", + "BriefDescription": "IC pipe was stalled during this clock cycle for any reason (nothing valid in pipe ICM1).", + "PublicDescription": "Instruction Pipe Stall. IC pipe was stalled during this clock cycle for any reason (nothing valid in pipe ICM1).", + "UMask": "0x4" + }, + { + "EventName": "ic_fetch_stall.ic_stall_dq_empty", + "EventCode": "0x87", + "BriefDescription": "IC pipe was stalled during this clock cycle (including IC to OC fetches) due to DQ empty.", + "PublicDescription": "Instruction Pipe Stall. IC pipe was stalled during this clock cycle (including IC to OC fetches) due to DQ empty.", + "UMask": "0x2" + }, + { + "EventName": "ic_fetch_stall.ic_stall_back_pressure", + "EventCode": "0x87", + "BriefDescription": "IC pipe was stalled during this clock cycle (including IC to OC fetches) due to back-pressure.", + "PublicDescription": "Instruction Pipe Stall. IC pipe was stalled during this clock cycle (including IC to OC fetches) due to back-pressure.", + "UMask": "0x1" + }, + { + "EventName": "ic_cache_inval.l2_invalidating_probe", + "EventCode": "0x8c", + "BriefDescription": "IC line invalidated due to L2 invalidating probe (external or LS).", + "PublicDescription": "The number of instruction cache lines invalidated. A non-SMC event is CMC (cross modifying code), either from the other thread of the core or another core. IC line invalidated due to L2 invalidating probe (external or LS).", + "UMask": "0x2" + }, + { + "EventName": "ic_cache_inval.fill_invalidated", + "EventCode": "0x8c", + "BriefDescription": "IC line invalidated due to overwriting fill response.", + "PublicDescription": "The number of instruction cache lines invalidated. A non-SMC event is CMC (cross modifying code), either from the other thread of the core or another core. IC line invalidated due to overwriting fill response.", + "UMask": "0x1" + }, + { + "EventName": "bp_tlb_rel", + "EventCode": "0x99", + "BriefDescription": "The number of ITLB reload requests." + }, + { + "EventName": "l2_request_g1.rd_blk_l", + "EventCode": "0x60", + "BriefDescription": "Requests to L2 Group1.", + "PublicDescription": "Requests to L2 Group1.", + "UMask": "0x80" + }, + { + "EventName": "l2_request_g1.rd_blk_x", + "EventCode": "0x60", + "BriefDescription": "Requests to L2 Group1.", + "PublicDescription": "Requests to L2 Group1.", + "UMask": "0x40" + }, + { + "EventName": "l2_request_g1.ls_rd_blk_c_s", + "EventCode": "0x60", + "BriefDescription": "Requests to L2 Group1.", + "PublicDescription": "Requests to L2 Group1.", + "UMask": "0x20" + }, + { + "EventName": "l2_request_g1.cacheable_ic_read", + "EventCode": "0x60", + "BriefDescription": "Requests to L2 Group1.", + "PublicDescription": "Requests to L2 Group1.", + "UMask": "0x10" + }, + { + "EventName": "l2_request_g1.change_to_x", + "EventCode": "0x60", + "BriefDescription": "Requests to L2 Group1.", + "PublicDescription": "Requests to L2 Group1.", + "UMask": "0x8" + }, + { + "EventName": "l2_request_g1.prefetch_l2", + "EventCode": "0x60", + "BriefDescription": "Requests to L2 Group1.", + "PublicDescription": "Requests to L2 Group1.", + "UMask": "0x4" + }, + { + "EventName": "l2_request_g1.l2_hw_pf", + "EventCode": "0x60", + "BriefDescription": "Requests to L2 Group1.", + "PublicDescription": "Requests to L2 Group1.", + "UMask": "0x2" + }, + { + "EventName": "l2_request_g1.other_requests", + "EventCode": "0x60", + "BriefDescription": "Events covered by l2_request_g2.", + "PublicDescription": "Requests to L2 Group1. Events covered by l2_request_g2.", + "UMask": "0x1" + }, + { + "EventName": "l2_request_g2.group1", + "EventCode": "0x61", + "BriefDescription": "All Group 1 commands not in unit0.", + "PublicDescription": "Multi-events in that LS and IF requests can be received simultaneous. All Group 1 commands not in unit0.", + "UMask": "0x80" + }, + { + "EventName": "l2_request_g2.ls_rd_sized", + "EventCode": "0x61", + "BriefDescription": "RdSized, RdSized32, RdSized64.", + "PublicDescription": "Multi-events in that LS and IF requests can be received simultaneous. RdSized, RdSized32, RdSized64.", + "UMask": "0x40" + }, + { + "EventName": "l2_request_g2.ls_rd_sized_nc", + "EventCode": "0x61", + "BriefDescription": "RdSizedNC, RdSized32NC, RdSized64NC.", + "PublicDescription": "Multi-events in that LS and IF requests can be received simultaneous. RdSizedNC, RdSized32NC, RdSized64NC.", + "UMask": "0x20" + }, + { + "EventName": "l2_request_g2.ic_rd_sized", + "EventCode": "0x61", + "BriefDescription": "Multi-events in that LS and IF requests can be received simultaneous.", + "PublicDescription": "Multi-events in that LS and IF requests can be received simultaneous.", + "UMask": "0x10" + }, + { + "EventName": "l2_request_g2.ic_rd_sized_nc", + "EventCode": "0x61", + "BriefDescription": "Multi-events in that LS and IF requests can be received simultaneous.", + "PublicDescription": "Multi-events in that LS and IF requests can be received simultaneous.", + "UMask": "0x8" + }, + { + "EventName": "l2_request_g2.smc_inval", + "EventCode": "0x61", + "BriefDescription": "Multi-events in that LS and IF requests can be received simultaneous.", + "PublicDescription": "Multi-events in that LS and IF requests can be received simultaneous.", + "UMask": "0x4" + }, + { + "EventName": "l2_request_g2.bus_locks_originator", + "EventCode": "0x61", + "BriefDescription": "Multi-events in that LS and IF requests can be received simultaneous.", + "PublicDescription": "Multi-events in that LS and IF requests can be received simultaneous.", + "UMask": "0x2" + }, + { + "EventName": "l2_request_g2.bus_locks_responses", + "EventCode": "0x61", + "BriefDescription": "Multi-events in that LS and IF requests can be received simultaneous.", + "PublicDescription": "Multi-events in that LS and IF requests can be received simultaneous.", + "UMask": "0x1" + }, + { + "EventName": "l2_latency.l2_cycles_waiting_on_fills", + "EventCode": "0x62", + "BriefDescription": "Total cycles spent waiting for L2 fills to complete from L3 or memory, divided by four. Event counts are for both threads. To calculate average latency, the number of fills from both threads must be used.", + "PublicDescription": "Total cycles spent waiting for L2 fills to complete from L3 or memory, divided by four. Event counts are for both threads. To calculate average latency, the number of fills from both threads must be used.", + "UMask": "0x1" + }, + { + "EventName": "l2_wcb_req.wcb_write", + "EventCode": "0x63", + "PublicDescription": "LS (Load/Store unit) to L2 WCB (Write Combining Buffer) write requests.", + "BriefDescription": "LS to L2 WCB write requests.", + "UMask": "0x40" + }, + { + "EventName": "l2_wcb_req.wcb_close", + "EventCode": "0x63", + "BriefDescription": "LS to L2 WCB close requests.", + "PublicDescription": "LS (Load/Store unit) to L2 WCB (Write Combining Buffer) close requests.", + "UMask": "0x20" + }, + { + "EventName": "l2_wcb_req.zero_byte_store", + "EventCode": "0x63", + "BriefDescription": "LS to L2 WCB zero byte store requests.", + "PublicDescription": "LS (Load/Store unit) to L2 WCB (Write Combining Buffer) zero byte store requests.", + "UMask": "0x4" + }, + { + "EventName": "l2_wcb_req.cl_zero", + "EventCode": "0x63", + "PublicDescription": "LS to L2 WCB cache line zeroing requests.", + "BriefDescription": "LS (Load/Store unit) to L2 WCB (Write Combining Buffer) cache line zeroing requests.", + "UMask": "0x1" + }, + { + "EventName": "l2_cache_req_stat.ls_rd_blk_cs", + "EventCode": "0x64", + "BriefDescription": "LS ReadBlock C/S Hit.", + "PublicDescription": "This event does not count accesses to the L2 cache by the L2 prefetcher, but it does count accesses by the L1 prefetcher. LS ReadBlock C/S Hit.", + "UMask": "0x80" + }, + { + "EventName": "l2_cache_req_stat.ls_rd_blk_l_hit_x", + "EventCode": "0x64", + "BriefDescription": "LS Read Block L Hit X.", + "PublicDescription": "This event does not count accesses to the L2 cache by the L2 prefetcher, but it does count accesses by the L1 prefetcher. LS Read Block L Hit X.", + "UMask": "0x40" + }, + { + "EventName": "l2_cache_req_stat.ls_rd_blk_l_hit_s", + "EventCode": "0x64", + "BriefDescription": "LsRdBlkL Hit Shared.", + "PublicDescription": "This event does not count accesses to the L2 cache by the L2 prefetcher, but it does count accesses by the L1 prefetcher. LsRdBlkL Hit Shared.", + "UMask": "0x20" + }, + { + "EventName": "l2_cache_req_stat.ls_rd_blk_x", + "EventCode": "0x64", + "BriefDescription": "LsRdBlkX/ChgToX Hit X. Count RdBlkX finding Shared as a Miss.", + "PublicDescription": "This event does not count accesses to the L2 cache by the L2 prefetcher, but it does count accesses by the L1 prefetcher. LsRdBlkX/ChgToX Hit X. Count RdBlkX finding Shared as a Miss.", + "UMask": "0x10" + }, + { + "EventName": "l2_cache_req_stat.ls_rd_blk_c", + "EventCode": "0x64", + "BriefDescription": "LS Read Block C S L X Change to X Miss.", + "PublicDescription": "This event does not count accesses to the L2 cache by the L2 prefetcher, but it does count accesses by the L1 prefetcher. LS Read Block C S L X Change to X Miss.", + "UMask": "0x8" + }, + { + "EventName": "l2_cache_req_stat.ic_fill_hit_x", + "EventCode": "0x64", + "BriefDescription": "IC Fill Hit Exclusive Stale.", + "PublicDescription": "This event does not count accesses to the L2 cache by the L2 prefetcher, but it does count accesses by the L1 prefetcher. IC Fill Hit Exclusive Stale.", + "UMask": "0x4" + }, + { + "EventName": "l2_cache_req_stat.ic_fill_hit_s", + "EventCode": "0x64", + "BriefDescription": "IC Fill Hit Shared.", + "PublicDescription": "This event does not count accesses to the L2 cache by the L2 prefetcher, but it does count accesses by the L1 prefetcher. IC Fill Hit Shared.", + "UMask": "0x2" + }, + { + "EventName": "l2_cache_req_stat.ic_fill_miss", + "EventCode": "0x64", + "BriefDescription": "IC Fill Miss.", + "PublicDescription": "This event does not count accesses to the L2 cache by the L2 prefetcher, but it does count accesses by the L1 prefetcher. IC Fill Miss.", + "UMask": "0x1" + }, + { + "EventName": "l2_fill_pending.l2_fill_busy", + "EventCode": "0x6d", + "BriefDescription": "Total cycles spent with one or more fill requests in flight from L2.", + "PublicDescription": "Total cycles spent with one or more fill requests in flight from L2.", + "UMask": "0x1" + } +] diff --git a/tools/perf/pmu-events/arch/x86/amdfam17h/core.json b/tools/perf/pmu-events/arch/x86/amdfam17h/core.json new file mode 100644 index 000000000000..7b285b0a7f35 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/amdfam17h/core.json @@ -0,0 +1,134 @@ +[ + { + "EventName": "ex_ret_instr", + "EventCode": "0xc0", + "BriefDescription": "Retired Instructions." + }, + { + "EventName": "ex_ret_cops", + "EventCode": "0xc1", + "BriefDescription": "Retired Uops.", + "PublicDescription": "The number of uOps retired. This includes all processor activity (instructions, exceptions, interrupts, microcode assists, etc.). The number of events logged per cycle can vary from 0 to 4." + }, + { + "EventName": "ex_ret_brn", + "EventCode": "0xc2", + "BriefDescription": "[Retired Branch Instructions.", + "PublicDescription": "The number of branch instructions retired. This includes all types of architectural control flow changes, including exceptions and interrupts." + }, + { + "EventName": "ex_ret_brn_misp", + "EventCode": "0xc3", + "BriefDescription": "Retired Branch Instructions Mispredicted.", + "PublicDescription": "The number of branch instructions retired, of any type, that were not correctly predicted. This includes those for which prediction is not attempted (far control transfers, exceptions and interrupts)." + }, + { + "EventName": "ex_ret_brn_tkn", + "EventCode": "0xc4", + "BriefDescription": "Retired Taken Branch Instructions.", + "PublicDescription": "The number of taken branches that were retired. This includes all types of architectural control flow changes, including exceptions and interrupts." + }, + { + "EventName": "ex_ret_brn_tkn_misp", + "EventCode": "0xc5", + "BriefDescription": "Retired Taken Branch Instructions Mispredicted.", + "PublicDescription": "The number of retired taken branch instructions that were mispredicted." + }, + { + "EventName": "ex_ret_brn_far", + "EventCode": "0xc6", + "BriefDescription": "Retired Far Control Transfers.", + "PublicDescription": "The number of far control transfers retired including far call/jump/return, IRET, SYSCALL and SYSRET, plus exceptions and interrupts. Far control transfers are not subject to branch prediction." + }, + { + "EventName": "ex_ret_brn_resync", + "EventCode": "0xc7", + "BriefDescription": "Retired Branch Resyncs.", + "PublicDescription": "The number of resync branches. These reflect pipeline restarts due to certain microcode assists and events such as writes to the active instruction stream, among other things. Each occurrence reflects a restart penalty similar to a branch mispredict. This is relatively rare." + }, + { + "EventName": "ex_ret_near_ret", + "EventCode": "0xc8", + "BriefDescription": "Retired Near Returns.", + "PublicDescription": "The number of near return instructions (RET or RET Iw) retired." + }, + { + "EventName": "ex_ret_near_ret_mispred", + "EventCode": "0xc9", + "BriefDescription": "Retired Near Returns Mispredicted.", + "PublicDescription": "The number of near returns retired that were not correctly predicted by the return address predictor. Each such mispredict incurs the same penalty as a mispredicted conditional branch instruction." + }, + { + "EventName": "ex_ret_brn_ind_misp", + "EventCode": "0xca", + "BriefDescription": "Retired Indirect Branch Instructions Mispredicted.", + "PublicDescription": "Retired Indirect Branch Instructions Mispredicted." + }, + { + "EventName": "ex_ret_mmx_fp_instr.sse_instr", + "EventCode": "0xcb", + "BriefDescription": "SSE instructions (SSE, SSE2, SSE3, SSSE3, SSE4A, SSE41, SSE42, AVX).", + "PublicDescription": "The number of MMX, SSE or x87 instructions retired. The UnitMask allows the selection of the individual classes of instructions as given in the table. Each increment represents one complete instruction. Since this event includes non-numeric instructions it is not suitable for measuring MFLOPS. SSE instructions (SSE, SSE2, SSE3, SSSE3, SSE4A, SSE41, SSE42, AVX).", + "UMask": "0x4" + }, + { + "EventName": "ex_ret_mmx_fp_instr.mmx_instr", + "EventCode": "0xcb", + "BriefDescription": "MMX instructions.", + "PublicDescription": "The number of MMX, SSE or x87 instructions retired. The UnitMask allows the selection of the individual classes of instructions as given in the table. Each increment represents one complete instruction. Since this event includes non-numeric instructions it is not suitable for measuring MFLOPS. MMX instructions.", + "UMask": "0x2" + }, + { + "EventName": "ex_ret_mmx_fp_instr.x87_instr", + "EventCode": "0xcb", + "BriefDescription": "x87 instructions.", + "PublicDescription": "The number of MMX, SSE or x87 instructions retired. The UnitMask allows the selection of the individual classes of instructions as given in the table. Each increment represents one complete instruction. Since this event includes non-numeric instructions it is not suitable for measuring MFLOPS. x87 instructions.", + "UMask": "0x1" + }, + { + "EventName": "ex_ret_cond", + "EventCode": "0xd1", + "BriefDescription": "Retired Conditional Branch Instructions." + }, + { + "EventName": "ex_ret_cond_misp", + "EventCode": "0xd2", + "BriefDescription": "Retired Conditional Branch Instructions Mispredicted." + }, + { + "EventName": "ex_div_busy", + "EventCode": "0xd3", + "BriefDescription": "Div Cycles Busy count." + }, + { + "EventName": "ex_div_count", + "EventCode": "0xd4", + "BriefDescription": "Div Op Count." + }, + { + "EventName": "ex_tagged_ibs_ops.ibs_count_rollover", + "EventCode": "0x1cf", + "BriefDescription": "Number of times an op could not be tagged by IBS because of a previous tagged op that has not retired.", + "PublicDescription": "Tagged IBS Ops. Number of times an op could not be tagged by IBS because of a previous tagged op that has not retired.", + "UMask": "0x4" + }, + { + "EventName": "ex_tagged_ibs_ops.ibs_tagged_ops_ret", + "EventCode": "0x1cf", + "BriefDescription": "Number of Ops tagged by IBS that retired.", + "PublicDescription": "Tagged IBS Ops. Number of Ops tagged by IBS that retired.", + "UMask": "0x2" + }, + { + "EventName": "ex_tagged_ibs_ops.ibs_tagged_ops", + "EventCode": "0x1cf", + "BriefDescription": "Number of Ops tagged by IBS.", + "PublicDescription": "Tagged IBS Ops. Number of Ops tagged by IBS.", + "UMask": "0x1" + }, + { + "EventName": "ex_ret_fus_brnch_inst", + "EventCode": "0x1d0", + "BriefDescription": "The number of fused retired branch instructions retired per cycle. The number of events logged per cycle can vary from 0 to 3." + } +] diff --git a/tools/perf/pmu-events/arch/x86/amdfam17h/floating-point.json b/tools/perf/pmu-events/arch/x86/amdfam17h/floating-point.json new file mode 100644 index 000000000000..ea4711983d1d --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/amdfam17h/floating-point.json @@ -0,0 +1,168 @@ +[ + { + "EventName": "fpu_pipe_assignment.dual", + "EventCode": "0x00", + "BriefDescription": "Total number multi-pipe uOps.", + "PublicDescription": "The number of operations (uOps) and dual-pipe uOps dispatched to each of the 4 FPU execution pipelines. This event reflects how busy the FPU pipelines are and may be used for workload characterization. This includes all operations performed by x87, MMX, and SSE instructions, including moves. Each increment represents a one- cycle dispatch event. This event is a speculative event. Since this event includes non-numeric operations it is not suitable for measuring MFLOPS. Total number multi-pipe uOps assigned to Pipe 3.", + "UMask": "0xf0" + }, + { + "EventName": "fpu_pipe_assignment.total", + "EventCode": "0x00", + "BriefDescription": "Total number uOps.", + "PublicDescription": "The number of operations (uOps) and dual-pipe uOps dispatched to each of the 4 FPU execution pipelines. This event reflects how busy the FPU pipelines are and may be used for workload characterization. This includes all operations performed by x87, MMX, and SSE instructions, including moves. Each increment represents a one- cycle dispatch event. This event is a speculative event. Since this event includes non-numeric operations it is not suitable for measuring MFLOPS. Total number uOps assigned to Pipe 3.", + "UMask": "0xf" + }, + { + "EventName": "fp_sched_empty", + "EventCode": "0x01", + "BriefDescription": "This is a speculative event. The number of cycles in which the FPU scheduler is empty. Note that some Ops like FP loads bypass the scheduler." + }, + { + "EventName": "fp_retx87_fp_ops.all", + "EventCode": "0x02", + "BriefDescription": "All Ops.", + "PublicDescription": "The number of x87 floating-point Ops that have retired. The number of events logged per cycle can vary from 0 to 8.", + "UMask": "0x7" + }, + { + "EventName": "fp_retx87_fp_ops.div_sqr_r_ops", + "EventCode": "0x02", + "BriefDescription": "Divide and square root Ops.", + "PublicDescription": "The number of x87 floating-point Ops that have retired. The number of events logged per cycle can vary from 0 to 8. Divide and square root Ops.", + "UMask": "0x4" + }, + { + "EventName": "fp_retx87_fp_ops.mul_ops", + "EventCode": "0x02", + "BriefDescription": "Multiply Ops.", + "PublicDescription": "The number of x87 floating-point Ops that have retired. The number of events logged per cycle can vary from 0 to 8. Multiply Ops.", + "UMask": "0x2" + }, + { + "EventName": "fp_retx87_fp_ops.add_sub_ops", + "EventCode": "0x02", + "BriefDescription": "Add/subtract Ops.", + "PublicDescription": "The number of x87 floating-point Ops that have retired. The number of events logged per cycle can vary from 0 to 8. Add/subtract Ops.", + "UMask": "0x1" + }, + { + "EventName": "fp_ret_sse_avx_ops.all", + "EventCode": "0x03", + "BriefDescription": "All FLOPS.", + "PublicDescription": "This is a retire-based event. The number of retired SSE/AVX FLOPS. The number of events logged per cycle can vary from 0 to 64. This event can count above 15.", + "UMask": "0xff" + }, + { + "EventName": "fp_ret_sse_avx_ops.dp_mult_add_flops", + "EventCode": "0x03", + "BriefDescription": "Double precision multiply-add FLOPS. Multiply-add counts as 2 FLOPS.", + "PublicDescription": "This is a retire-based event. The number of retired SSE/AVX FLOPS. The number of events logged per cycle can vary from 0 to 64. This event can count above 15. Double precision multiply-add FLOPS. Multiply-add counts as 2 FLOPS.", + "UMask": "0x80" + }, + { + "EventName": "fp_ret_sse_avx_ops.dp_div_flops", + "EventCode": "0x03", + "BriefDescription": "Double precision divide/square root FLOPS.", + "PublicDescription": "This is a retire-based event. The number of retired SSE/AVX FLOPS. The number of events logged per cycle can vary from 0 to 64. This event can count above 15. Double precision divide/square root FLOPS.", + "UMask": "0x40" + }, + { + "EventName": "fp_ret_sse_avx_ops.dp_mult_flops", + "EventCode": "0x03", + "BriefDescription": "Double precision multiply FLOPS.", + "PublicDescription": "This is a retire-based event. The number of retired SSE/AVX FLOPS. The number of events logged per cycle can vary from 0 to 64. This event can count above 15. Double precision multiply FLOPS.", + "UMask": "0x20" + }, + { + "EventName": "fp_ret_sse_avx_ops.dp_add_sub_flops", + "EventCode": "0x03", + "BriefDescription": "Double precision add/subtract FLOPS.", + "PublicDescription": "This is a retire-based event. The number of retired SSE/AVX FLOPS. The number of events logged per cycle can vary from 0 to 64. This event can count above 15. Double precision add/subtract FLOPS.", + "UMask": "0x10" + }, + { + "EventName": "fp_ret_sse_avx_ops.sp_mult_add_flops", + "EventCode": "0x03", + "BriefDescription": "Single precision multiply-add FLOPS. Multiply-add counts as 2 FLOPS.", + "PublicDescription": "This is a retire-based event. The number of retired SSE/AVX FLOPS. The number of events logged per cycle can vary from 0 to 64. This event can count above 15. Single precision multiply-add FLOPS. Multiply-add counts as 2 FLOPS.", + "UMask": "0x8" + }, + { + "EventName": "fp_ret_sse_avx_ops.sp_div_flops", + "EventCode": "0x03", + "BriefDescription": "Single-precision divide/square root FLOPS.", + "PublicDescription": "This is a retire-based event. The number of retired SSE/AVX FLOPS. The number of events logged per cycle can vary from 0 to 64. This event can count above 15. Single-precision divide/square root FLOPS.", + "UMask": "0x4" + }, + { + "EventName": "fp_ret_sse_avx_ops.sp_mult_flops", + "EventCode": "0x03", + "BriefDescription": "Single-precision multiply FLOPS.", + "PublicDescription": "This is a retire-based event. The number of retired SSE/AVX FLOPS. The number of events logged per cycle can vary from 0 to 64. This event can count above 15. Single-precision multiply FLOPS.", + "UMask": "0x2" + }, + { + "EventName": "fp_ret_sse_avx_ops.sp_add_sub_flops", + "EventCode": "0x03", + "BriefDescription": "Single-precision add/subtract FLOPS.", + "PublicDescription": "This is a retire-based event. The number of retired SSE/AVX FLOPS. The number of events logged per cycle can vary from 0 to 64. This event can count above 15. Single-precision add/subtract FLOPS.", + "UMask": "0x1" + }, + { + "EventName": "fp_num_mov_elim_scal_op.optimized", + "EventCode": "0x04", + "BriefDescription": "Number of Scalar Ops optimized.", + "PublicDescription": "This is a dispatch based speculative event, and is useful for measuring the effectiveness of the Move elimination and Scalar code optimization schemes. Number of Scalar Ops optimized.", + "UMask": "0x8" + }, + { + "EventName": "fp_num_mov_elim_scal_op.opt_potential", + "EventCode": "0x04", + "BriefDescription": "Number of Ops that are candidates for optimization (have Z-bit either set or pass).", + "PublicDescription": "This is a dispatch based speculative event, and is useful for measuring the effectiveness of the Move elimination and Scalar code optimization schemes. Number of Ops that are candidates for optimization (have Z-bit either set or pass).", + "UMask": "0x4" + }, + { + "EventName": "fp_num_mov_elim_scal_op.sse_mov_ops_elim", + "EventCode": "0x04", + "BriefDescription": "Number of SSE Move Ops eliminated.", + "PublicDescription": "This is a dispatch based speculative event, and is useful for measuring the effectiveness of the Move elimination and Scalar code optimization schemes. Number of SSE Move Ops eliminated.", + "UMask": "0x2" + }, + { + "EventName": "fp_num_mov_elim_scal_op.sse_mov_ops", + "EventCode": "0x04", + "BriefDescription": "Number of SSE Move Ops.", + "PublicDescription": "This is a dispatch based speculative event, and is useful for measuring the effectiveness of the Move elimination and Scalar code optimization schemes. Number of SSE Move Ops.", + "UMask": "0x1" + }, + { + "EventName": "fp_retired_ser_ops.x87_ctrl_ret", + "EventCode": "0x05", + "BriefDescription": "x87 control word mispredict traps due to mispredictions in RC or PC, or changes in mask bits.", + "PublicDescription": "The number of serializing Ops retired. x87 control word mispredict traps due to mispredictions in RC or PC, or changes in mask bits.", + "UMask": "0x8" + }, + { + "EventName": "fp_retired_ser_ops.x87_bot_ret", + "EventCode": "0x05", + "BriefDescription": "x87 bottom-executing uOps retired.", + "PublicDescription": "The number of serializing Ops retired. x87 bottom-executing uOps retired.", + "UMask": "0x4" + }, + { + "EventName": "fp_retired_ser_ops.sse_ctrl_ret", + "EventCode": "0x05", + "BriefDescription": "SSE control word mispredict traps due to mispredictions in RC, FTZ or DAZ, or changes in mask bits.", + "PublicDescription": "The number of serializing Ops retired. SSE control word mispredict traps due to mispredictions in RC, FTZ or DAZ, or changes in mask bits.", + "UMask": "0x2" + }, + { + "EventName": "fp_retired_ser_ops.sse_bot_ret", + "EventCode": "0x05", + "BriefDescription": "SSE bottom-executing uOps retired.", + "PublicDescription": "The number of serializing Ops retired. SSE bottom-executing uOps retired.", + "UMask": "0x1" + } +] diff --git a/tools/perf/pmu-events/arch/x86/amdfam17h/memory.json b/tools/perf/pmu-events/arch/x86/amdfam17h/memory.json new file mode 100644 index 000000000000..fa2d60d4def0 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/amdfam17h/memory.json @@ -0,0 +1,162 @@ +[ + { + "EventName": "ls_locks.bus_lock", + "EventCode": "0x25", + "BriefDescription": "Bus lock when a locked operations crosses a cache boundary or is done on an uncacheable memory type.", + "PublicDescription": "Bus lock when a locked operations crosses a cache boundary or is done on an uncacheable memory type.", + "UMask": "0x1" + }, + { + "EventName": "ls_dispatch.ld_st_dispatch", + "EventCode": "0x29", + "BriefDescription": "Load-op-Stores.", + "PublicDescription": "Counts the number of operations dispatched to the LS unit. Unit Masks ADDed. Load-op-Stores.", + "UMask": "0x4" + }, + { + "EventName": "ls_dispatch.store_dispatch", + "EventCode": "0x29", + "BriefDescription": "Counts the number of operations dispatched to the LS unit. Unit Masks ADDed.", + "PublicDescription": "Counts the number of operations dispatched to the LS unit. Unit Masks ADDed.", + "UMask": "0x2" + }, + { + "EventName": "ls_dispatch.ld_dispatch", + "EventCode": "0x29", + "BriefDescription": "Counts the number of operations dispatched to the LS unit. Unit Masks ADDed.", + "PublicDescription": "Counts the number of operations dispatched to the LS unit. Unit Masks ADDed.", + "UMask": "0x1" + }, + { + "EventName": "ls_stlf", + "EventCode": "0x35", + "BriefDescription": "Number of STLF hits." + }, + { + "EventName": "ls_dc_accesses", + "EventCode": "0x40", + "BriefDescription": "The number of accesses to the data cache for load and store references. This may include certain microcode scratchpad accesses, although these are generally rare. Each increment represents an eight-byte access, although the instruction may only be accessing a portion of that. This event is a speculative event." + }, + { + "EventName": "ls_l1_d_tlb_miss.all", + "EventCode": "0x45", + "BriefDescription": "L1 DTLB Miss or Reload off all sizes.", + "PublicDescription": "L1 DTLB Miss or Reload off all sizes.", + "UMask": "0xff" + }, + { + "EventName": "ls_l1_d_tlb_miss.tlb_reload_1g_l2_miss", + "EventCode": "0x45", + "BriefDescription": "L1 DTLB Miss of a page of 1G size.", + "PublicDescription": "L1 DTLB Miss of a page of 1G size.", + "UMask": "0x80" + }, + { + "EventName": "ls_l1_d_tlb_miss.tlb_reload_2m_l2_miss", + "EventCode": "0x45", + "BriefDescription": "L1 DTLB Miss of a page of 2M size.", + "PublicDescription": "L1 DTLB Miss of a page of 2M size.", + "UMask": "0x40" + }, + { + "EventName": "ls_l1_d_tlb_miss.tlb_reload_32k_l2_miss", + "EventCode": "0x45", + "BriefDescription": "L1 DTLB Miss of a page of 32K size.", + "PublicDescription": "L1 DTLB Miss of a page of 32K size.", + "UMask": "0x20" + }, + { + "EventName": "ls_l1_d_tlb_miss.tlb_reload_4k_l2_miss", + "EventCode": "0x45", + "BriefDescription": "L1 DTLB Miss of a page of 4K size.", + "PublicDescription": "L1 DTLB Miss of a page of 4K size.", + "UMask": "0x10" + }, + { + "EventName": "ls_l1_d_tlb_miss.tlb_reload_1g_l2_hit", + "EventCode": "0x45", + "BriefDescription": "L1 DTLB Reload of a page of 1G size.", + "PublicDescription": "L1 DTLB Reload of a page of 1G size.", + "UMask": "0x8" + }, + { + "EventName": "ls_l1_d_tlb_miss.tlb_reload_2m_l2_hit", + "EventCode": "0x45", + "BriefDescription": "L1 DTLB Reload of a page of 2M size.", + "PublicDescription": "L1 DTLB Reload of a page of 2M size.", + "UMask": "0x4" + }, + { + "EventName": "ls_l1_d_tlb_miss.tlb_reload_32k_l2_hit", + "EventCode": "0x45", + "BriefDescription": "L1 DTLB Reload of a page of 32K size.", + "PublicDescription": "L1 DTLB Reload of a page of 32K size.", + "UMask": "0x2" + }, + { + "EventName": "ls_l1_d_tlb_miss.tlb_reload_4k_l2_hit", + "EventCode": "0x45", + "BriefDescription": "L1 DTLB Reload of a page of 4K size.", + "PublicDescription": "L1 DTLB Reload of a page of 4K size.", + "UMask": "0x1" + }, + { + "EventName": "ls_tablewalker.perf_mon_tablewalk_alloc_iside", + "EventCode": "0x46", + "BriefDescription": "Tablewalker allocation.", + "PublicDescription": "Tablewalker allocation.", + "UMask": "0xc" + }, + { + "EventName": "ls_tablewalker.perf_mon_tablewalk_alloc_dside", + "EventCode": "0x46", + "BriefDescription": "Tablewalker allocation.", + "PublicDescription": "Tablewalker allocation.", + "UMask": "0x3" + }, + { + "EventName": "ls_misal_accesses", + "EventCode": "0x47", + "BriefDescription": "Misaligned loads." + }, + { + "EventName": "ls_pref_instr_disp.prefetch_nta", + "EventCode": "0x4b", + "BriefDescription": "Software Prefetch Instructions (PREFETCHNTA instruction) Dispatched.", + "PublicDescription": "Software Prefetch Instructions (PREFETCHNTA instruction) Dispatched.", + "UMask": "0x4" + }, + { + "EventName": "ls_pref_instr_disp.store_prefetch_w", + "EventCode": "0x4b", + "BriefDescription": "Software Prefetch Instructions (3DNow PREFETCHW instruction) Dispatched.", + "PublicDescription": "Software Prefetch Instructions (3DNow PREFETCHW instruction) Dispatched.", + "UMask": "0x2" + }, + { + "EventName": "ls_pref_instr_disp.load_prefetch_w", + "EventCode": "0x4b", + "BriefDescription": "Prefetch, Prefetch_T0_T1_T2.", + "PublicDescription": "Software Prefetch Instructions Dispatched. Prefetch, Prefetch_T0_T1_T2.", + "UMask": "0x1" + }, + { + "EventName": "ls_inef_sw_pref.mab_mch_cnt", + "EventCode": "0x52", + "BriefDescription": "The number of software prefetches that did not fetch data outside of the processor core.", + "PublicDescription": "The number of software prefetches that did not fetch data outside of the processor core.", + "UMask": "0x2" + }, + { + "EventName": "ls_inef_sw_pref.data_pipe_sw_pf_dc_hit", + "EventCode": "0x52", + "BriefDescription": "The number of software prefetches that did not fetch data outside of the processor core.", + "PublicDescription": "The number of software prefetches that did not fetch data outside of the processor core.", + "UMask": "0x1" + }, + { + "EventName": "ls_not_halted_cyc", + "EventCode": "0x76", + "BriefDescription": "Cycles not in Halt." + } +] diff --git a/tools/perf/pmu-events/arch/x86/amdfam17h/other.json b/tools/perf/pmu-events/arch/x86/amdfam17h/other.json new file mode 100644 index 000000000000..b26a00d05a2e --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/amdfam17h/other.json @@ -0,0 +1,65 @@ +[ + { + "EventName": "ic_oc_mode_switch.oc_ic_mode_switch", + "EventCode": "0x28a", + "BriefDescription": "OC to IC mode switch.", + "PublicDescription": "OC Mode Switch. OC to IC mode switch.", + "UMask": "0x2" + }, + { + "EventName": "ic_oc_mode_switch.ic_oc_mode_switch", + "EventCode": "0x28a", + "BriefDescription": "IC to OC mode switch.", + "PublicDescription": "OC Mode Switch. IC to OC mode switch.", + "UMask": "0x1" + }, + { + "EventName": "de_dis_dispatch_token_stalls0.retire_token_stall", + "EventCode": "0xaf", + "BriefDescription": "RETIRE Tokens unavailable.", + "PublicDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. RETIRE Tokens unavailable.", + "UMask": "0x40" + }, + { + "EventName": "de_dis_dispatch_token_stalls0.agsq_token_stall", + "EventCode": "0xaf", + "BriefDescription": "AGSQ Tokens unavailable.", + "PublicDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. AGSQ Tokens unavailable.", + "UMask": "0x20" + }, + { + "EventName": "de_dis_dispatch_token_stalls0.alu_token_stall", + "EventCode": "0xaf", + "BriefDescription": "ALU tokens total unavailable.", + "PublicDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. ALU tokens total unavailable.", + "UMask": "0x10" + }, + { + "EventName": "de_dis_dispatch_token_stalls0.alsq3_0_token_stall", + "EventCode": "0xaf", + "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall.", + "PublicDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall.", + "UMask": "0x8" + }, + { + "EventName": "de_dis_dispatch_token_stalls0.alsq3_token_stall", + "EventCode": "0xaf", + "BriefDescription": "ALSQ 3 Tokens unavailable.", + "PublicDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. ALSQ 3 Tokens unavailable.", + "UMask": "0x4" + }, + { + "EventName": "de_dis_dispatch_token_stalls0.alsq2_token_stall", + "EventCode": "0xaf", + "BriefDescription": "ALSQ 2 Tokens unavailable.", + "PublicDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. ALSQ 2 Tokens unavailable.", + "UMask": "0x2" + }, + { + "EventName": "de_dis_dispatch_token_stalls0.alsq1_token_stall", + "EventCode": "0xaf", + "BriefDescription": "ALSQ 1 Tokens unavailable.", + "PublicDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. ALSQ 1 Tokens unavailable.", + "UMask": "0x1" + } +] diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index e05c2c8458fc..d6984a3017e0 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -33,3 +33,4 @@ 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 +AuthenticAMD-23-[[:xdigit:]]+,v1,amdfam17h,core diff --git a/tools/perf/scripts/python/export-to-postgresql.py b/tools/perf/scripts/python/export-to-postgresql.py index 390a351d15ea..c3eae1d77d36 100644 --- a/tools/perf/scripts/python/export-to-postgresql.py +++ b/tools/perf/scripts/python/export-to-postgresql.py @@ -10,6 +10,8 @@ # FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for # more details. +from __future__ import print_function + import os import sys import struct @@ -199,6 +201,18 @@ import datetime from PySide.QtSql import * +if sys.version_info < (3, 0): + def toserverstr(str): + return str + def toclientstr(str): + return str +else: + # Assume UTF-8 server_encoding and client_encoding + def toserverstr(str): + return bytes(str, "UTF_8") + def toclientstr(str): + return bytes(str, "UTF_8") + # Need to access PostgreSQL C library directly to use COPY FROM STDIN from ctypes import * libpq = CDLL("libpq.so.5") @@ -234,12 +248,17 @@ perf_db_export_mode = True perf_db_export_calls = False perf_db_export_callchains = False +def printerr(*args, **kw_args): + print(*args, file=sys.stderr, **kw_args) + +def printdate(*args, **kw_args): + print(datetime.datetime.today(), *args, sep=' ', **kw_args) def usage(): - print >> sys.stderr, "Usage is: export-to-postgresql.py <database name> [<columns>] [<calls>] [<callchains>]" - print >> sys.stderr, "where: columns 'all' or 'branches'" - print >> sys.stderr, " calls 'calls' => create calls and call_paths table" - print >> sys.stderr, " callchains 'callchains' => create call_paths table" + printerr("Usage is: export-to-postgresql.py <database name> [<columns>] [<calls>] [<callchains>]") + printerr("where: columns 'all' or 'branches'") + printerr(" calls 'calls' => create calls and call_paths table") + printerr(" callchains 'callchains' => create call_paths table") raise Exception("Too few arguments") if (len(sys.argv) < 2): @@ -273,7 +292,7 @@ def do_query(q, s): return raise Exception("Query failed: " + q.lastError().text()) -print datetime.datetime.today(), "Creating database..." +printdate("Creating database...") db = QSqlDatabase.addDatabase('QPSQL') query = QSqlQuery(db) @@ -506,12 +525,12 @@ do_query(query, 'CREATE VIEW samples_view AS ' ' FROM samples') -file_header = struct.pack("!11sii", "PGCOPY\n\377\r\n\0", 0, 0) -file_trailer = "\377\377" +file_header = struct.pack("!11sii", b"PGCOPY\n\377\r\n\0", 0, 0) +file_trailer = b"\377\377" def open_output_file(file_name): path_name = output_dir_name + "/" + file_name - file = open(path_name, "w+") + file = open(path_name, "wb+") file.write(file_header) return file @@ -526,13 +545,13 @@ def copy_output_file_direct(file, table_name): # Use COPY FROM STDIN because security may prevent postgres from accessing the files directly def copy_output_file(file, table_name): - conn = PQconnectdb("dbname = " + dbname) + conn = PQconnectdb(toclientstr("dbname = " + dbname)) if (PQstatus(conn)): raise Exception("COPY FROM STDIN PQconnectdb failed") file.write(file_trailer) file.seek(0) sql = "COPY " + table_name + " FROM STDIN (FORMAT 'binary')" - res = PQexec(conn, sql) + res = PQexec(conn, toclientstr(sql)) if (PQresultStatus(res) != 4): raise Exception("COPY FROM STDIN PQexec failed") data = file.read(65536) @@ -566,7 +585,7 @@ if perf_db_export_calls: call_file = open_output_file("call_table.bin") def trace_begin(): - print datetime.datetime.today(), "Writing to intermediate files..." + printdate("Writing to intermediate files...") # id == 0 means unknown. It is easier to create records for them than replace the zeroes with NULLs evsel_table(0, "unknown") machine_table(0, 0, "unknown") @@ -582,7 +601,7 @@ def trace_begin(): unhandled_count = 0 def trace_end(): - print datetime.datetime.today(), "Copying to database..." + printdate("Copying to database...") copy_output_file(evsel_file, "selected_events") copy_output_file(machine_file, "machines") copy_output_file(thread_file, "threads") @@ -597,7 +616,7 @@ def trace_end(): if perf_db_export_calls: copy_output_file(call_file, "calls") - print datetime.datetime.today(), "Removing intermediate files..." + printdate("Removing intermediate files...") remove_output_file(evsel_file) remove_output_file(machine_file) remove_output_file(thread_file) @@ -612,7 +631,7 @@ def trace_end(): if perf_db_export_calls: remove_output_file(call_file) os.rmdir(output_dir_name) - print datetime.datetime.today(), "Adding primary keys" + printdate("Adding primary keys") do_query(query, 'ALTER TABLE selected_events ADD PRIMARY KEY (id)') do_query(query, 'ALTER TABLE machines ADD PRIMARY KEY (id)') do_query(query, 'ALTER TABLE threads ADD PRIMARY KEY (id)') @@ -627,7 +646,7 @@ def trace_end(): if perf_db_export_calls: do_query(query, 'ALTER TABLE calls ADD PRIMARY KEY (id)') - print datetime.datetime.today(), "Adding foreign keys" + printdate("Adding foreign keys") do_query(query, 'ALTER TABLE threads ' 'ADD CONSTRAINT machinefk FOREIGN KEY (machine_id) REFERENCES machines (id),' 'ADD CONSTRAINT processfk FOREIGN KEY (process_id) REFERENCES threads (id)') @@ -663,8 +682,8 @@ def trace_end(): do_query(query, 'CREATE INDEX pid_idx ON calls (parent_id)') if (unhandled_count): - print datetime.datetime.today(), "Warning: ", unhandled_count, " unhandled events" - print datetime.datetime.today(), "Done" + printdate("Warning: ", unhandled_count, " unhandled events") + printdate("Done") def trace_unhandled(event_name, context, event_fields_dict): global unhandled_count @@ -674,12 +693,14 @@ def sched__sched_switch(*x): pass def evsel_table(evsel_id, evsel_name, *x): + evsel_name = toserverstr(evsel_name) n = len(evsel_name) fmt = "!hiqi" + str(n) + "s" value = struct.pack(fmt, 2, 8, evsel_id, n, evsel_name) evsel_file.write(value) def machine_table(machine_id, pid, root_dir, *x): + root_dir = toserverstr(root_dir) n = len(root_dir) fmt = "!hiqiii" + str(n) + "s" value = struct.pack(fmt, 3, 8, machine_id, 4, pid, n, root_dir) @@ -690,6 +711,7 @@ def thread_table(thread_id, machine_id, process_id, pid, tid, *x): thread_file.write(value) def comm_table(comm_id, comm_str, *x): + comm_str = toserverstr(comm_str) n = len(comm_str) fmt = "!hiqi" + str(n) + "s" value = struct.pack(fmt, 2, 8, comm_id, n, comm_str) @@ -701,6 +723,9 @@ def comm_thread_table(comm_thread_id, comm_id, thread_id, *x): comm_thread_file.write(value) def dso_table(dso_id, machine_id, short_name, long_name, build_id, *x): + short_name = toserverstr(short_name) + long_name = toserverstr(long_name) + build_id = toserverstr(build_id) n1 = len(short_name) n2 = len(long_name) n3 = len(build_id) @@ -709,12 +734,14 @@ def dso_table(dso_id, machine_id, short_name, long_name, build_id, *x): dso_file.write(value) def symbol_table(symbol_id, dso_id, sym_start, sym_end, binding, symbol_name, *x): + symbol_name = toserverstr(symbol_name) n = len(symbol_name) fmt = "!hiqiqiqiqiii" + str(n) + "s" value = struct.pack(fmt, 6, 8, symbol_id, 8, dso_id, 8, sym_start, 8, sym_end, 4, binding, n, symbol_name) symbol_file.write(value) def branch_type_table(branch_type, name, *x): + name = toserverstr(name) n = len(name) fmt = "!hiii" + str(n) + "s" value = struct.pack(fmt, 2, 4, branch_type, n, name) diff --git a/tools/perf/scripts/python/export-to-sqlite.py b/tools/perf/scripts/python/export-to-sqlite.py index eb63e6c7107f..3b71902a5a21 100644 --- a/tools/perf/scripts/python/export-to-sqlite.py +++ b/tools/perf/scripts/python/export-to-sqlite.py @@ -10,6 +10,8 @@ # FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for # more details. +from __future__ import print_function + import os import sys import struct @@ -60,11 +62,17 @@ perf_db_export_mode = True perf_db_export_calls = False perf_db_export_callchains = False +def printerr(*args, **keyword_args): + print(*args, file=sys.stderr, **keyword_args) + +def printdate(*args, **kw_args): + print(datetime.datetime.today(), *args, sep=' ', **kw_args) + def usage(): - print >> sys.stderr, "Usage is: export-to-sqlite.py <database name> [<columns>] [<calls>] [<callchains>]" - print >> sys.stderr, "where: columns 'all' or 'branches'" - print >> sys.stderr, " calls 'calls' => create calls and call_paths table" - print >> sys.stderr, " callchains 'callchains' => create call_paths table" + printerr("Usage is: export-to-sqlite.py <database name> [<columns>] [<calls>] [<callchains>]"); + printerr("where: columns 'all' or 'branches'"); + printerr(" calls 'calls' => create calls and call_paths table"); + printerr(" callchains 'callchains' => create call_paths table"); raise Exception("Too few arguments") if (len(sys.argv) < 2): @@ -100,7 +108,7 @@ def do_query_(q): return raise Exception("Query failed: " + q.lastError().text()) -print datetime.datetime.today(), "Creating database..." +printdate("Creating database ...") db_exists = False try: @@ -378,7 +386,7 @@ if perf_db_export_calls: call_query.prepare("INSERT INTO calls VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)") def trace_begin(): - print datetime.datetime.today(), "Writing records..." + printdate("Writing records...") do_query(query, 'BEGIN TRANSACTION') # id == 0 means unknown. It is easier to create records for them than replace the zeroes with NULLs evsel_table(0, "unknown") @@ -397,14 +405,14 @@ unhandled_count = 0 def trace_end(): do_query(query, 'END TRANSACTION') - print datetime.datetime.today(), "Adding indexes" + printdate("Adding indexes") if perf_db_export_calls: do_query(query, 'CREATE INDEX pcpid_idx ON calls (parent_call_path_id)') do_query(query, 'CREATE INDEX pid_idx ON calls (parent_id)') if (unhandled_count): - print datetime.datetime.today(), "Warning: ", unhandled_count, " unhandled events" - print datetime.datetime.today(), "Done" + printdate("Warning: ", unhandled_count, " unhandled events") + printdate("Done") def trace_unhandled(event_name, context, event_fields_dict): global unhandled_count diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py index afec9479ca7f..e38518cdcbc3 100755 --- a/tools/perf/scripts/python/exported-sql-viewer.py +++ b/tools/perf/scripts/python/exported-sql-viewer.py @@ -88,11 +88,20 @@ # 7fab593ea956 48 89 15 3b 13 22 00 movq %rdx, 0x22133b(%rip) # 8107675243232 2 ls 22011 22011 hardware interrupt No 7fab593ea956 _dl_start+0x26 (ld-2.19.so) -> ffffffff86a012e0 page_fault ([kernel]) +from __future__ import print_function + import sys import weakref import threading import string -import cPickle +try: + # Python2 + import cPickle as pickle + # size of pickled integer big enough for record size + glb_nsz = 8 +except ImportError: + import pickle + glb_nsz = 16 import re import os from PySide.QtCore import * @@ -102,6 +111,15 @@ from decimal import * from ctypes import * from multiprocessing import Process, Array, Value, Event +# xrange is range in Python3 +try: + xrange +except NameError: + xrange = range + +def printerr(*args, **keyword_args): + print(*args, file=sys.stderr, **keyword_args) + # Data formatting helpers def tohex(ip): @@ -1004,10 +1022,6 @@ class ChildDataItemFinder(): glb_chunk_sz = 10000 -# size of pickled integer big enough for record size - -glb_nsz = 8 - # Background process for SQL data fetcher class SQLFetcherProcess(): @@ -1066,7 +1080,7 @@ class SQLFetcherProcess(): return True if space >= glb_nsz: # Use 0 (or space < glb_nsz) to mean there is no more at the top of the buffer - nd = cPickle.dumps(0, cPickle.HIGHEST_PROTOCOL) + nd = pickle.dumps(0, pickle.HIGHEST_PROTOCOL) self.buffer[self.local_head : self.local_head + len(nd)] = nd self.local_head = 0 if self.local_tail - self.local_head > sz: @@ -1084,9 +1098,9 @@ class SQLFetcherProcess(): self.wait_event.wait() def AddToBuffer(self, obj): - d = cPickle.dumps(obj, cPickle.HIGHEST_PROTOCOL) + d = pickle.dumps(obj, pickle.HIGHEST_PROTOCOL) n = len(d) - nd = cPickle.dumps(n, cPickle.HIGHEST_PROTOCOL) + nd = pickle.dumps(n, pickle.HIGHEST_PROTOCOL) sz = n + glb_nsz self.WaitForSpace(sz) pos = self.local_head @@ -1198,12 +1212,12 @@ class SQLFetcher(QObject): pos = self.local_tail if len(self.buffer) - pos < glb_nsz: pos = 0 - n = cPickle.loads(self.buffer[pos : pos + glb_nsz]) + n = pickle.loads(self.buffer[pos : pos + glb_nsz]) if n == 0: pos = 0 - n = cPickle.loads(self.buffer[0 : glb_nsz]) + n = pickle.loads(self.buffer[0 : glb_nsz]) pos += glb_nsz - obj = cPickle.loads(self.buffer[pos : pos + n]) + obj = pickle.loads(self.buffer[pos : pos + n]) self.local_tail = pos + n return obj @@ -2973,7 +2987,7 @@ class DBRef(): def Main(): if (len(sys.argv) < 2): - print >> sys.stderr, "Usage is: exported-sql-viewer.py {<database name> | --help-only}" + printerr("Usage is: exported-sql-viewer.py {<database name> | --help-only}"); raise Exception("Too few arguments") dbname = sys.argv[1] @@ -2986,8 +3000,8 @@ def Main(): is_sqlite3 = False try: - f = open(dbname) - if f.read(15) == "SQLite format 3": + f = open(dbname, "rb") + if f.read(15) == b'SQLite format 3': is_sqlite3 = True f.close() except: diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c index 4f75561424ed..4ad37d8c7d6a 100644 --- a/tools/perf/ui/browser.c +++ b/tools/perf/ui/browser.c @@ -611,14 +611,16 @@ void ui_browser__argv_seek(struct ui_browser *browser, off_t offset, int whence) browser->top = browser->entries; break; case SEEK_CUR: - browser->top = browser->top + browser->top_idx + offset; + browser->top = (char **)browser->top + offset; break; case SEEK_END: - browser->top = browser->top + browser->nr_entries - 1 + offset; + browser->top = (char **)browser->entries + browser->nr_entries - 1 + offset; break; default: return; } + assert((char **)browser->top < (char **)browser->entries + browser->nr_entries); + assert((char **)browser->top >= (char **)browser->entries); } unsigned int ui_browser__argv_refresh(struct ui_browser *browser) @@ -630,7 +632,9 @@ unsigned int ui_browser__argv_refresh(struct ui_browser *browser) browser->top = browser->entries; pos = (char **)browser->top; - while (idx < browser->nr_entries) { + while (idx < browser->nr_entries && + row < (unsigned)SLtt_Screen_Rows - 1) { + assert(pos < (char **)browser->entries + browser->nr_entries); if (!browser->filter || !browser->filter(browser, *pos)) { ui_browser__gotorc(browser, row, 0); browser->write(browser, pos, row); diff --git a/tools/perf/ui/browsers/Build b/tools/perf/ui/browsers/Build index 8fee56b46502..fdf86f7981ca 100644 --- a/tools/perf/ui/browsers/Build +++ b/tools/perf/ui/browsers/Build @@ -3,6 +3,7 @@ perf-y += hists.o perf-y += map.o perf-y += scripts.o perf-y += header.o +perf-y += res_sample.o CFLAGS_annotate.o += -DENABLE_SLFUTURE_CONST CFLAGS_hists.o += -DENABLE_SLFUTURE_CONST diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index 35bdfd8b1e71..98d934a36d86 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -750,7 +750,7 @@ static int annotate_browser__run(struct annotate_browser *browser, continue; case 'r': { - script_browse(NULL); + script_browse(NULL, NULL); continue; } case 'k': diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index aef800d97ea1..3421ecbdd3f0 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -7,6 +7,7 @@ #include <string.h> #include <linux/rbtree.h> #include <sys/ttydefaults.h> +#include <linux/time64.h> #include "../../util/callchain.h" #include "../../util/evsel.h" @@ -30,6 +31,7 @@ #include "srcline.h" #include "string2.h" #include "units.h" +#include "time-utils.h" #include "sane_ctype.h" @@ -1224,6 +1226,8 @@ void hist_browser__init_hpp(void) hist_browser__hpp_color_overhead_guest_us; perf_hpp__format[PERF_HPP__OVERHEAD_ACC].color = hist_browser__hpp_color_overhead_acc; + + res_sample_init(); } static int hist_browser__show_entry(struct hist_browser *browser, @@ -2338,9 +2342,12 @@ close_file_and_continue: } struct popup_action { + unsigned long time; struct thread *thread; struct map_symbol ms; int socket; + struct perf_evsel *evsel; + enum rstype rstype; int (*fn)(struct hist_browser *browser, struct popup_action *act); }; @@ -2527,46 +2534,137 @@ static int do_run_script(struct hist_browser *browser __maybe_unused, struct popup_action *act) { - char script_opt[64]; - memset(script_opt, 0, sizeof(script_opt)); + char *script_opt; + int len; + int n = 0; + len = 100; + if (act->thread) + len += strlen(thread__comm_str(act->thread)); + else if (act->ms.sym) + len += strlen(act->ms.sym->name); + script_opt = malloc(len); + if (!script_opt) + return -1; + + script_opt[0] = 0; if (act->thread) { - scnprintf(script_opt, sizeof(script_opt), " -c %s ", + n = scnprintf(script_opt, len, " -c %s ", thread__comm_str(act->thread)); } else if (act->ms.sym) { - scnprintf(script_opt, sizeof(script_opt), " -S %s ", + n = scnprintf(script_opt, len, " -S %s ", act->ms.sym->name); } - script_browse(script_opt); + if (act->time) { + char start[32], end[32]; + unsigned long starttime = act->time; + unsigned long endtime = act->time + symbol_conf.time_quantum; + + if (starttime == endtime) { /* Display 1ms as fallback */ + starttime -= 1*NSEC_PER_MSEC; + endtime += 1*NSEC_PER_MSEC; + } + timestamp__scnprintf_usec(starttime, start, sizeof start); + timestamp__scnprintf_usec(endtime, end, sizeof end); + n += snprintf(script_opt + n, len - n, " --time %s,%s", start, end); + } + + script_browse(script_opt, act->evsel); + free(script_opt); return 0; } static int -add_script_opt(struct hist_browser *browser __maybe_unused, +do_res_sample_script(struct hist_browser *browser __maybe_unused, + struct popup_action *act) +{ + struct hist_entry *he; + + he = hist_browser__selected_entry(browser); + res_sample_browse(he->res_samples, he->num_res, act->evsel, act->rstype); + return 0; +} + +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 thread *thread, struct symbol *sym, + struct perf_evsel *evsel, const char *tstr) { + if (thread) { - if (asprintf(optstr, "Run scripts for samples of thread [%s]", - thread__comm_str(thread)) < 0) + if (asprintf(optstr, "Run scripts for samples of thread [%s]%s", + thread__comm_str(thread), tstr) < 0) return 0; } else if (sym) { - if (asprintf(optstr, "Run scripts for samples of symbol [%s]", - sym->name) < 0) + if (asprintf(optstr, "Run scripts for samples of symbol [%s]%s", + sym->name, tstr) < 0) return 0; } else { - if (asprintf(optstr, "Run scripts for all samples") < 0) + if (asprintf(optstr, "Run scripts for all samples%s", tstr) < 0) return 0; } act->thread = thread; act->ms.sym = sym; + act->evsel = evsel; act->fn = do_run_script; return 1; } 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) +{ + int n, j; + struct hist_entry *he; + + n = add_script_opt_2(browser, act, optstr, thread, sym, evsel, ""); + + he = hist_browser__selected_entry(browser); + if (sort_order && strstr(sort_order, "time")) { + char tstr[128]; + + optstr++; + act++; + j = sprintf(tstr, " in "); + j += timestamp__scnprintf_usec(he->time, tstr + j, + sizeof tstr - j); + j += sprintf(tstr + j, "-"); + timestamp__scnprintf_usec(he->time + symbol_conf.time_quantum, + tstr + j, sizeof tstr - j); + n += add_script_opt_2(browser, act, optstr, thread, sym, + evsel, tstr); + act->time = he->time; + } + return n; +} + +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, + enum rstype type) +{ + if (!res_sample) + return 0; + + if (asprintf(optstr, "Show context for individual samples %s", + type == A_ASM ? "with assembler" : + type == A_SOURCE ? "with source" : "") < 0) + return 0; + + act->fn = do_res_sample_script; + act->evsel = evsel; + act->rstype = type; + return 1; +} + +static int do_switch_data(struct hist_browser *browser __maybe_unused, struct popup_action *act __maybe_unused) { @@ -3031,7 +3129,7 @@ skip_annotation: nr_options += add_script_opt(browser, &actions[nr_options], &options[nr_options], - thread, NULL); + thread, NULL, evsel); } /* * Note that browser->selection != NULL @@ -3046,11 +3144,24 @@ skip_annotation: nr_options += add_script_opt(browser, &actions[nr_options], &options[nr_options], - NULL, browser->selection->sym); + NULL, browser->selection->sym, + evsel); } } nr_options += add_script_opt(browser, &actions[nr_options], - &options[nr_options], NULL, NULL); + &options[nr_options], NULL, NULL, evsel); + nr_options += add_res_sample_opt(browser, &actions[nr_options], + &options[nr_options], + hist_browser__selected_entry(browser)->res_samples, + evsel, A_NORMAL); + nr_options += add_res_sample_opt(browser, &actions[nr_options], + &options[nr_options], + hist_browser__selected_entry(browser)->res_samples, + evsel, A_ASM); + nr_options += add_res_sample_opt(browser, &actions[nr_options], + &options[nr_options], + hist_browser__selected_entry(browser)->res_samples, + evsel, A_SOURCE); nr_options += add_switch_opt(browser, &actions[nr_options], &options[nr_options]); skip_scripting: diff --git a/tools/perf/ui/browsers/res_sample.c b/tools/perf/ui/browsers/res_sample.c new file mode 100644 index 000000000000..c0dd73176d42 --- /dev/null +++ b/tools/perf/ui/browsers/res_sample.c @@ -0,0 +1,91 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Display a menu with individual samples to browse with perf script */ +#include "util.h" +#include "hist.h" +#include "evsel.h" +#include "hists.h" +#include "sort.h" +#include "config.h" +#include "time-utils.h" +#include <linux/time64.h> + +static u64 context_len = 10 * NSEC_PER_MSEC; + +static int res_sample_config(const char *var, const char *value, void *data __maybe_unused) +{ + if (!strcmp(var, "samples.context")) + return perf_config_u64(&context_len, var, value); + return 0; +} + +void res_sample_init(void) +{ + perf_config(res_sample_config, NULL); +} + +int res_sample_browse(struct res_sample *res_samples, int num_res, + struct perf_evsel *evsel, enum rstype rstype) +{ + char **names; + int i, n; + int choice; + char *cmd; + char pbuf[256], tidbuf[32], cpubuf[32]; + const char *perf = perf_exe(pbuf, sizeof pbuf); + char trange[128], tsample[64]; + struct res_sample *r; + char extra_format[256]; + + names = calloc(num_res, sizeof(char *)); + if (!names) + return -1; + for (i = 0; i < num_res; i++) { + char tbuf[64]; + + timestamp__scnprintf_nsec(res_samples[i].time, tbuf, sizeof tbuf); + if (asprintf(&names[i], "%s: CPU %d tid %d", tbuf, + res_samples[i].cpu, res_samples[i].tid) < 0) { + while (--i >= 0) + free(names[i]); + free(names); + return -1; + } + } + choice = ui__popup_menu(num_res, names); + for (i = 0; i < num_res; i++) + free(names[i]); + free(names); + + if (choice < 0 || choice >= num_res) + return -1; + r = &res_samples[choice]; + + n = timestamp__scnprintf_nsec(r->time - context_len, trange, sizeof trange); + trange[n++] = ','; + timestamp__scnprintf_nsec(r->time + context_len, trange + n, sizeof trange - n); + + timestamp__scnprintf_nsec(r->time, tsample, sizeof tsample); + + attr_to_script(extra_format, &evsel->attr); + + if (asprintf(&cmd, "%s script %s%s --time %s %s%s %s%s --ns %s %s %s %s %s | less +/%s", + perf, + input_name ? "-i " : "", + input_name ? input_name : "", + trange, + r->cpu >= 0 ? "--cpu " : "", + r->cpu >= 0 ? (sprintf(cpubuf, "%d", r->cpu), cpubuf) : "", + r->tid ? "--tid " : "", + r->tid ? (sprintf(tidbuf, "%d", r->tid), tidbuf) : "", + extra_format, + rstype == A_ASM ? "-F +insn --xed" : + rstype == A_SOURCE ? "-F +srcline,+srccode" : "", + symbol_conf.inline_name ? "--inline" : "", + "--show-lost-events ", + r->tid ? "--show-switch-events --show-task-events " : "", + tsample) < 0) + return -1; + run_script(cmd); + free(cmd); + return 0; +} diff --git a/tools/perf/ui/browsers/scripts.c b/tools/perf/ui/browsers/scripts.c index 90a32ac69e76..27cf3ab88d13 100644 --- a/tools/perf/ui/browsers/scripts.c +++ b/tools/perf/ui/browsers/scripts.c @@ -1,34 +1,12 @@ // SPDX-License-Identifier: GPL-2.0 -#include <elf.h> -#include <inttypes.h> -#include <sys/ttydefaults.h> -#include <string.h> #include "../../util/sort.h" #include "../../util/util.h" #include "../../util/hist.h" #include "../../util/debug.h" #include "../../util/symbol.h" #include "../browser.h" -#include "../helpline.h" #include "../libslang.h" - -/* 2048 lines should be enough for a script output */ -#define MAX_LINES 2048 - -/* 160 bytes for one output line */ -#define AVERAGE_LINE_LEN 160 - -struct script_line { - struct list_head node; - char line[AVERAGE_LINE_LEN]; -}; - -struct perf_script_browser { - struct ui_browser b; - struct list_head entries; - const char *script_name; - int nr_lines; -}; +#include "config.h" #define SCRIPT_NAMELEN 128 #define SCRIPT_MAX_NO 64 @@ -40,149 +18,169 @@ struct perf_script_browser { */ #define SCRIPT_FULLPATH_LEN 256 +struct script_config { + const char **names; + char **paths; + int index; + const char *perf; + char extra_format[256]; +}; + +void attr_to_script(char *extra_format, struct perf_event_attr *attr) +{ + extra_format[0] = 0; + if (attr->read_format & PERF_FORMAT_GROUP) + strcat(extra_format, " -F +metric"); + if (attr->sample_type & PERF_SAMPLE_BRANCH_STACK) + strcat(extra_format, " -F +brstackinsn --xed"); + if (attr->sample_type & PERF_SAMPLE_REGS_INTR) + strcat(extra_format, " -F +iregs"); + if (attr->sample_type & PERF_SAMPLE_REGS_USER) + strcat(extra_format, " -F +uregs"); + if (attr->sample_type & PERF_SAMPLE_PHYS_ADDR) + strcat(extra_format, " -F +phys_addr"); +} + +static int add_script_option(const char *name, const char *opt, + struct script_config *c) +{ + c->names[c->index] = name; + if (asprintf(&c->paths[c->index], + "%s script %s -F +metric %s %s", + c->perf, opt, symbol_conf.inline_name ? " --inline" : "", + c->extra_format) < 0) + return -1; + c->index++; + return 0; +} + +static int scripts_config(const char *var, const char *value, void *data) +{ + struct script_config *c = data; + + if (!strstarts(var, "scripts.")) + return -1; + if (c->index >= SCRIPT_MAX_NO) + return -1; + c->names[c->index] = strdup(var + 7); + if (!c->names[c->index]) + return -1; + if (asprintf(&c->paths[c->index], "%s %s", value, + c->extra_format) < 0) + return -1; + c->index++; + return 0; +} + /* * When success, will copy the full path of the selected script * into the buffer pointed by script_name, and return 0. * Return -1 on failure. */ -static int list_scripts(char *script_name) +static int list_scripts(char *script_name, bool *custom, + struct perf_evsel *evsel) { - char *buf, *names[SCRIPT_MAX_NO], *paths[SCRIPT_MAX_NO]; - int i, num, choice, ret = -1; + char *buf, *paths[SCRIPT_MAX_NO], *names[SCRIPT_MAX_NO]; + int i, num, choice; + int ret = 0; + int max_std, custom_perf; + char pbuf[256]; + const char *perf = perf_exe(pbuf, sizeof pbuf); + struct script_config scriptc = { + .names = (const char **)names, + .paths = paths, + .perf = perf + }; + + script_name[0] = 0; /* Preset the script name to SCRIPT_NAMELEN */ buf = malloc(SCRIPT_MAX_NO * (SCRIPT_NAMELEN + SCRIPT_FULLPATH_LEN)); if (!buf) - return ret; + return -1; - for (i = 0; i < SCRIPT_MAX_NO; i++) { - names[i] = buf + i * (SCRIPT_NAMELEN + SCRIPT_FULLPATH_LEN); + if (evsel) + attr_to_script(scriptc.extra_format, &evsel->attr); + add_script_option("Show individual samples", "", &scriptc); + add_script_option("Show individual samples with assembler", "-F +insn --xed", + &scriptc); + add_script_option("Show individual samples with source", "-F +srcline,+srccode", + &scriptc); + perf_config(scripts_config, &scriptc); + custom_perf = scriptc.index; + add_script_option("Show samples with custom perf script arguments", "", &scriptc); + i = scriptc.index; + max_std = i; + + for (; i < SCRIPT_MAX_NO; i++) { + names[i] = buf + (i - max_std) * (SCRIPT_NAMELEN + SCRIPT_FULLPATH_LEN); paths[i] = names[i] + SCRIPT_NAMELEN; } - num = find_scripts(names, paths); - if (num > 0) { - choice = ui__popup_menu(num, names); - if (choice < num && choice >= 0) { - strcpy(script_name, paths[choice]); - ret = 0; - } + num = find_scripts(names + max_std, paths + max_std, SCRIPT_MAX_NO - max_std, + SCRIPT_FULLPATH_LEN); + if (num < 0) + num = 0; + choice = ui__popup_menu(num + max_std, (char * const *)names); + if (choice < 0) { + ret = -1; + goto out; } + if (choice == custom_perf) { + char script_args[50]; + int key = ui_browser__input_window("perf script command", + "Enter perf script command line (without perf script prefix)", + script_args, "", 0); + if (key != K_ENTER) + return -1; + sprintf(script_name, "%s script %s", perf, script_args); + } else if (choice < num + max_std) { + strcpy(script_name, paths[choice]); + } + *custom = choice >= max_std; +out: free(buf); + for (i = 0; i < max_std; i++) + free(paths[i]); return ret; } -static void script_browser__write(struct ui_browser *browser, - void *entry, int row) +void run_script(char *cmd) { - struct script_line *sline = list_entry(entry, struct script_line, node); - bool current_entry = ui_browser__is_current_entry(browser, row); - - ui_browser__set_color(browser, current_entry ? HE_COLORSET_SELECTED : - HE_COLORSET_NORMAL); - - ui_browser__write_nstring(browser, sline->line, browser->width); + pr_debug("Running %s\n", cmd); + SLang_reset_tty(); + if (system(cmd) < 0) + pr_warning("Cannot run %s\n", cmd); + /* + * SLang doesn't seem to reset the whole terminal, so be more + * forceful to get back to the original state. + */ + printf("\033[c\033[H\033[J"); + fflush(stdout); + SLang_init_tty(0, 0, 0); + SLsmg_refresh(); } -static int script_browser__run(struct perf_script_browser *browser) +int script_browse(const char *script_opt, struct perf_evsel *evsel) { - int key; + char *cmd, script_name[SCRIPT_FULLPATH_LEN]; + bool custom = false; - if (ui_browser__show(&browser->b, browser->script_name, - "Press ESC to exit") < 0) + memset(script_name, 0, SCRIPT_FULLPATH_LEN); + if (list_scripts(script_name, &custom, evsel)) return -1; - while (1) { - key = ui_browser__run(&browser->b, 0); - - /* We can add some special key handling here if needed */ - break; - } - - ui_browser__hide(&browser->b); - return key; -} - - -int script_browse(const char *script_opt) -{ - char cmd[SCRIPT_FULLPATH_LEN*2], script_name[SCRIPT_FULLPATH_LEN]; - char *line = NULL; - size_t len = 0; - ssize_t retlen; - int ret = -1, nr_entries = 0; - FILE *fp; - void *buf; - struct script_line *sline; - - struct perf_script_browser script = { - .b = { - .refresh = ui_browser__list_head_refresh, - .seek = ui_browser__list_head_seek, - .write = script_browser__write, - }, - .script_name = script_name, - }; - - INIT_LIST_HEAD(&script.entries); - - /* Save each line of the output in one struct script_line object. */ - buf = zalloc((sizeof(*sline)) * MAX_LINES); - if (!buf) + if (asprintf(&cmd, "%s%s %s %s%s 2>&1 | less", + custom ? "perf script -s " : "", + script_name, + script_opt ? script_opt : "", + input_name ? "-i " : "", + input_name ? input_name : "") < 0) return -1; - sline = buf; - - memset(script_name, 0, SCRIPT_FULLPATH_LEN); - if (list_scripts(script_name)) - goto exit; - - sprintf(cmd, "perf script -s %s ", script_name); - if (script_opt) - strcat(cmd, script_opt); + run_script(cmd); + free(cmd); - if (input_name) { - strcat(cmd, " -i "); - strcat(cmd, input_name); - } - - strcat(cmd, " 2>&1"); - - fp = popen(cmd, "r"); - if (!fp) - goto exit; - - while ((retlen = getline(&line, &len, fp)) != -1) { - strncpy(sline->line, line, AVERAGE_LINE_LEN); - - /* If one output line is very large, just cut it short */ - if (retlen >= AVERAGE_LINE_LEN) { - sline->line[AVERAGE_LINE_LEN - 1] = '\0'; - sline->line[AVERAGE_LINE_LEN - 2] = '\n'; - } - list_add_tail(&sline->node, &script.entries); - - if (script.b.width < retlen) - script.b.width = retlen; - - if (nr_entries++ >= MAX_LINES - 1) - break; - sline++; - } - - if (script.b.width > AVERAGE_LINE_LEN) - script.b.width = AVERAGE_LINE_LEN; - - free(line); - pclose(fp); - - script.nr_lines = nr_entries; - script.b.nr_entries = nr_entries; - script.b.entries = &script.entries; - - ret = script_browser__run(&script); -exit: - free(buf); - return ret; + return 0; } diff --git a/tools/perf/util/archinsn.h b/tools/perf/util/archinsn.h new file mode 100644 index 000000000000..448cbb6b8d7e --- /dev/null +++ b/tools/perf/util/archinsn.h @@ -0,0 +1,12 @@ +#ifndef INSN_H +#define INSN_H 1 + +struct perf_sample; +struct machine; +struct thread; + +void arch_fetch_insn(struct perf_sample *sample, + struct thread *thread, + struct machine *machine); + +#endif diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index e098e189f93e..c6b67efea11a 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -14,6 +14,7 @@ #include "data.h" #include "util.h" #include "debug.h" +#include "header.h" static void close_dir(struct perf_data_file *files, int nr) { @@ -34,12 +35,16 @@ int perf_data__create_dir(struct perf_data *data, int nr) struct perf_data_file *files = NULL; int i, ret = -1; + if (WARN_ON(!data->is_dir)) + return -EINVAL; + files = zalloc(nr * sizeof(*files)); if (!files) return -ENOMEM; - data->dir.files = files; - data->dir.nr = nr; + data->dir.version = PERF_DIR_VERSION; + data->dir.files = files; + data->dir.nr = nr; for (i = 0; i < nr; i++) { struct perf_data_file *file = &files[i]; @@ -69,6 +74,13 @@ int perf_data__open_dir(struct perf_data *data) DIR *dir; int nr = 0; + if (WARN_ON(!data->is_dir)) + return -EINVAL; + + /* The version is provided by DIR_FORMAT feature. */ + if (WARN_ON(data->dir.version != PERF_DIR_VERSION)) + return -1; + dir = opendir(data->path); if (!dir) return -EINVAL; @@ -118,6 +130,26 @@ out_err: return ret; } +int perf_data__update_dir(struct perf_data *data) +{ + int i; + + if (WARN_ON(!data->is_dir)) + return -EINVAL; + + for (i = 0; i < data->dir.nr; i++) { + struct perf_data_file *file = &data->dir.files[i]; + struct stat st; + + if (fstat(file->fd, &st)) + return -1; + + file->size = st.st_size; + } + + return 0; +} + static bool check_pipe(struct perf_data *data) { struct stat st; @@ -173,6 +205,16 @@ static int check_backup(struct perf_data *data) return 0; } +static bool is_dir(struct perf_data *data) +{ + struct stat st; + + if (stat(data->path, &st)) + return false; + + return (st.st_mode & S_IFMT) == S_IFDIR; +} + static int open_file_read(struct perf_data *data) { struct stat st; @@ -254,6 +296,30 @@ static int open_file_dup(struct perf_data *data) return open_file(data); } +static int open_dir(struct perf_data *data) +{ + int ret; + + /* + * So far we open only the header, so we can read the data version and + * layout. + */ + if (asprintf(&data->file.path, "%s/header", data->path) < 0) + return -1; + + if (perf_data__is_write(data) && + mkdir(data->path, S_IRWXU) < 0) + return -1; + + ret = open_file(data); + + /* Cleanup whatever we managed to create so far. */ + if (ret && perf_data__is_write(data)) + rm_rf_perf_data(data->path); + + return ret; +} + int perf_data__open(struct perf_data *data) { if (check_pipe(data)) @@ -265,11 +331,18 @@ int perf_data__open(struct perf_data *data) if (check_backup(data)) return -1; - return open_file_dup(data); + if (perf_data__is_read(data)) + data->is_dir = is_dir(data); + + return perf_data__is_dir(data) ? + open_dir(data) : open_file_dup(data); } void perf_data__close(struct perf_data *data) { + if (perf_data__is_dir(data)) + perf_data__close_dir(data); + zfree(&data->file.path); close(data->file.fd); } @@ -326,3 +399,20 @@ out: free(new_filepath); return ret; } + +unsigned long perf_data__size(struct perf_data *data) +{ + u64 size = data->file.size; + int i; + + if (!data->is_dir) + return size; + + for (i = 0; i < data->dir.nr; i++) { + struct perf_data_file *file = &data->dir.files[i]; + + size += file->size; + } + + return size; +} diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h index 14b47be2bd69..6aef8746469f 100644 --- a/tools/perf/util/data.h +++ b/tools/perf/util/data.h @@ -19,10 +19,12 @@ struct perf_data { const char *path; struct perf_data_file file; bool is_pipe; + bool is_dir; bool force; enum perf_data_mode mode; struct { + u64 version; struct perf_data_file *files; int nr; } dir; @@ -43,14 +45,14 @@ static inline int perf_data__is_pipe(struct perf_data *data) return data->is_pipe; } -static inline int perf_data__fd(struct perf_data *data) +static inline bool perf_data__is_dir(struct perf_data *data) { - return data->file.fd; + return data->is_dir; } -static inline unsigned long perf_data__size(struct perf_data *data) +static inline int perf_data__fd(struct perf_data *data) { - return data->file.size; + return data->file.fd; } int perf_data__open(struct perf_data *data); @@ -73,4 +75,6 @@ int perf_data__switch(struct perf_data *data, int perf_data__create_dir(struct perf_data *data, int nr); int perf_data__open_dir(struct perf_data *data); void perf_data__close_dir(struct perf_data *data); +int perf_data__update_dir(struct perf_data *data); +unsigned long perf_data__size(struct perf_data *data); #endif /* __PERF_DATA_H */ diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 01b324c275b9..b0683bf4d9f3 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -861,6 +861,21 @@ static int write_clockid(struct feat_fd *ff, sizeof(ff->ph->env.clockid_res_ns)); } +static int write_dir_format(struct feat_fd *ff, + struct perf_evlist *evlist __maybe_unused) +{ + struct perf_session *session; + struct perf_data *data; + + session = container_of(ff->ph, struct perf_session, header); + data = session->data; + + if (WARN_ON(!perf_data__is_dir(data))) + return -1; + + return do_write(ff, &data->dir.version, sizeof(data->dir.version)); +} + static int cpu_cache_level__sort(const void *a, const void *b) { struct cpu_cache_level *cache_a = (struct cpu_cache_level *)a; @@ -1341,6 +1356,17 @@ static void print_clockid(struct feat_fd *ff, FILE *fp) ff->ph->env.clockid_res_ns * 1000); } +static void print_dir_format(struct feat_fd *ff, FILE *fp) +{ + struct perf_session *session; + struct perf_data *data; + + session = container_of(ff->ph, struct perf_session, header); + data = session->data; + + fprintf(fp, "# directory data version : %"PRIu64"\n", data->dir.version); +} + static void free_event_desc(struct perf_evsel *events) { struct perf_evsel *evsel; @@ -2373,6 +2399,21 @@ static int process_clockid(struct feat_fd *ff, return 0; } +static int process_dir_format(struct feat_fd *ff, + void *_data __maybe_unused) +{ + struct perf_session *session; + struct perf_data *data; + + session = container_of(ff->ph, struct perf_session, header); + data = session->data; + + if (WARN_ON(!perf_data__is_dir(data))) + return -1; + + return do_read_u64(ff, &data->dir.version); +} + struct feature_ops { int (*write)(struct feat_fd *ff, struct perf_evlist *evlist); void (*print)(struct feat_fd *ff, FILE *fp); @@ -2432,7 +2473,8 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = { FEAT_OPN(CACHE, cache, true), FEAT_OPR(SAMPLE_TIME, sample_time, false), FEAT_OPR(MEM_TOPOLOGY, mem_topology, true), - FEAT_OPR(CLOCKID, clockid, false) + FEAT_OPR(CLOCKID, clockid, false), + FEAT_OPN(DIR_FORMAT, dir_format, false) }; struct header_print_data { diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index 0d553ddca0a3..6a231340238d 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -39,6 +39,7 @@ enum { HEADER_SAMPLE_TIME, HEADER_MEM_TOPOLOGY, HEADER_CLOCKID, + HEADER_DIR_FORMAT, HEADER_LAST_FEATURE, HEADER_FEAT_BITS = 256, }; @@ -48,6 +49,10 @@ enum perf_header_version { PERF_HEADER_VERSION_2, }; +enum perf_dir_version { + PERF_DIR_VERSION = 1, +}; + struct perf_file_section { u64 offset; u64 size; diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index f9eb95bf3938..1f230285d78a 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -19,6 +19,7 @@ #include <math.h> #include <inttypes.h> #include <sys/param.h> +#include <linux/time64.h> static bool hists__filter_entry_by_dso(struct hists *hists, struct hist_entry *he); @@ -192,6 +193,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) hists__new_col_len(hists, HISTC_MEM_LVL, 21 + 3); hists__new_col_len(hists, HISTC_LOCAL_WEIGHT, 12); hists__new_col_len(hists, HISTC_GLOBAL_WEIGHT, 12); + hists__new_col_len(hists, HISTC_TIME, 12); if (h->srcline) { len = MAX(strlen(h->srcline), strlen(sort_srcline.se_header)); @@ -246,6 +248,14 @@ static void he_stat__add_cpumode_period(struct he_stat *he_stat, } } +static long hist_time(unsigned long htime) +{ + unsigned long time_quantum = symbol_conf.time_quantum; + if (time_quantum) + return (htime / time_quantum) * time_quantum; + return htime; +} + static void he_stat__add_period(struct he_stat *he_stat, u64 period, u64 weight) { @@ -426,6 +436,13 @@ static int hist_entry__init(struct hist_entry *he, goto err_rawdata; } + if (symbol_conf.res_sample) { + he->res_samples = calloc(sizeof(struct res_sample), + symbol_conf.res_sample); + if (!he->res_samples) + goto err_srcline; + } + INIT_LIST_HEAD(&he->pairs.node); thread__get(he->thread); he->hroot_in = RB_ROOT_CACHED; @@ -436,6 +453,9 @@ static int hist_entry__init(struct hist_entry *he, return 0; +err_srcline: + free(he->srcline); + err_rawdata: free(he->raw_data); @@ -593,6 +613,32 @@ out: return he; } +static unsigned random_max(unsigned high) +{ + unsigned thresh = -high % high; + for (;;) { + unsigned r = random(); + if (r >= thresh) + return r % high; + } +} + +static void hists__res_sample(struct hist_entry *he, struct perf_sample *sample) +{ + struct res_sample *r; + int j; + + if (he->num_res < symbol_conf.res_sample) { + j = he->num_res++; + } else { + j = random_max(symbol_conf.res_sample); + } + r = &he->res_samples[j]; + r->time = sample->time; + r->cpu = sample->cpu; + r->tid = sample->tid; +} + static struct hist_entry* __hists__add_entry(struct hists *hists, struct addr_location *al, @@ -635,10 +681,13 @@ __hists__add_entry(struct hists *hists, .raw_data = sample->raw_data, .raw_size = sample->raw_size, .ops = ops, + .time = hist_time(sample->time), }, *he = hists__findnew_entry(hists, &entry, al, sample_self); if (!hists->has_callchains && he && he->callchain_size != 0) hists->has_callchains = true; + if (he && symbol_conf.res_sample) + hists__res_sample(he, sample); return he; } @@ -1162,6 +1211,7 @@ void hist_entry__delete(struct hist_entry *he) mem_info__zput(he->mem_info); } + zfree(&he->res_samples); zfree(&he->stat_acc); free_srcline(he->srcline); if (he->srcfile && he->srcfile[0]) diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 4af27fbab24f..76ff6c6d03b8 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -31,6 +31,7 @@ enum hist_filter { enum hist_column { HISTC_SYMBOL, + HISTC_TIME, HISTC_DSO, HISTC_THREAD, HISTC_COMM, @@ -432,9 +433,18 @@ struct hist_browser_timer { }; struct annotation_options; +struct res_sample; + +enum rstype { + A_NORMAL, + A_ASM, + A_SOURCE +}; #ifdef HAVE_SLANG_SUPPORT #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, struct hist_browser_timer *hbt, struct annotation_options *annotation_opts); @@ -449,7 +459,13 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help, struct perf_env *env, bool warn_lost_event, struct annotation_options *annotation_options); -int script_browse(const char *script_opt); + +int script_browse(const char *script_opt, struct perf_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); +void res_sample_init(void); #else static inline int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __maybe_unused, @@ -478,11 +494,22 @@ static inline int hist_entry__tui_annotate(struct hist_entry *he __maybe_unused, return 0; } -static inline int script_browse(const char *script_opt __maybe_unused) +static inline int script_browse(const char *script_opt __maybe_unused, + struct perf_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, + enum rstype rstype __maybe_unused) +{ + return 0; +} + +static inline void res_sample_init(void) {} + #define K_LEFT -1000 #define K_RIGHT -2000 #define K_SWITCH_INPUT_DATA -3000 diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index a1b8d9649ca7..198e09ff611e 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -160,8 +160,10 @@ static struct map *kernel_get_module_map(const char *module) if (module && strchr(module, '/')) return dso__new_map(module); - if (!module) - module = "kernel"; + if (!module) { + pos = machine__kernel_map(host_machine); + return map__get(pos); + } for (pos = maps__first(maps); pos; pos = map__next(pos)) { /* short_name is "[module]" */ diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index db643f3c2b95..0ec34227bd60 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -152,6 +152,10 @@ struct perf_session *perf_session__new(struct perf_data *data, } perf_evlist__init_trace_event_sample_raw(session->evlist); + + /* Open the directory data. */ + if (data->is_dir && perf_data__open_dir(data)) + goto out_delete; } } else { session->machines.host.env = &perf_env; @@ -1843,10 +1847,17 @@ fetch_mmaped_event(struct perf_session *session, #define NUM_MMAPS 128 #endif +struct reader; + +typedef s64 (*reader_cb_t)(struct perf_session *session, + union perf_event *event, + u64 file_offset); + struct reader { - int fd; - u64 data_size; - u64 data_offset; + int fd; + u64 data_size; + u64 data_offset; + reader_cb_t process; }; static int @@ -1917,7 +1928,7 @@ more: size = event->header.size; if (size < sizeof(struct perf_event_header) || - (skip = perf_session__process_event(session, event, file_pos)) < 0) { + (skip = rd->process(session, event, file_pos)) < 0) { pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n", file_offset + head, event->header.size, event->header.type); @@ -1943,12 +1954,20 @@ out: return err; } +static s64 process_simple(struct perf_session *session, + union perf_event *event, + u64 file_offset) +{ + return perf_session__process_event(session, event, file_offset); +} + static int __perf_session__process_events(struct perf_session *session) { struct reader rd = { .fd = perf_data__fd(session->data), .data_size = session->header.data_size, .data_offset = session->header.data_offset, + .process = process_simple, }; struct ordered_events *oe = &session->ordered_events; struct perf_tool *tool = session->tool; diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index d2299e912e59..bdd30cab51cb 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -3,6 +3,7 @@ #include <inttypes.h> #include <regex.h> #include <linux/mman.h> +#include <linux/time64.h> #include "sort.h" #include "hist.h" #include "comm.h" @@ -15,6 +16,7 @@ #include <traceevent/event-parse.h> #include "mem-events.h" #include "annotate.h" +#include "time-utils.h" #include <linux/kernel.h> regex_t parent_regex; @@ -654,6 +656,42 @@ struct sort_entry sort_socket = { .se_width_idx = HISTC_SOCKET, }; +/* --sort time */ + +static int64_t +sort__time_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return right->time - left->time; +} + +static int hist_entry__time_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + unsigned long secs; + unsigned long long nsecs; + char he_time[32]; + + nsecs = he->time; + secs = nsecs / NSEC_PER_SEC; + nsecs -= secs * NSEC_PER_SEC; + + if (symbol_conf.nanosecs) + snprintf(he_time, sizeof he_time, "%5lu.%09llu: ", + secs, nsecs); + else + timestamp__scnprintf_usec(he->time, he_time, + sizeof(he_time)); + + return repsep_snprintf(bf, size, "%-.*s", width, he_time); +} + +struct sort_entry sort_time = { + .se_header = "Time", + .se_cmp = sort__time_cmp, + .se_snprintf = hist_entry__time_snprintf, + .se_width_idx = HISTC_TIME, +}; + /* --sort trace */ static char *get_trace_output(struct hist_entry *he) @@ -1634,6 +1672,7 @@ static struct sort_dimension common_sort_dimensions[] = { DIM(SORT_DSO_SIZE, "dso_size", sort_dso_size), DIM(SORT_CGROUP_ID, "cgroup_id", sort_cgroup_id), DIM(SORT_SYM_IPC_NULL, "ipc_null", sort_sym_ipc_null), + DIM(SORT_TIME, "time", sort_time), }; #undef DIM diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 2fbee0b1011c..bb9442ab7a0c 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -47,6 +47,12 @@ extern struct sort_entry sort_srcline; extern enum sort_type sort__first_dimension; extern const char default_mem_sort_order[]; +struct res_sample { + u64 time; + int cpu; + int tid; +}; + struct he_stat { u64 period; u64 period_sys; @@ -135,10 +141,13 @@ struct hist_entry { char *srcfile; struct symbol *parent; struct branch_info *branch_info; + long time; struct hists *hists; struct mem_info *mem_info; void *raw_data; u32 raw_size; + int num_res; + struct res_sample *res_samples; void *trace_output; struct perf_hpp_list *hpp_list; struct hist_entry *parent_he; @@ -231,6 +240,7 @@ enum sort_type { SORT_DSO_SIZE, SORT_CGROUP_ID, SORT_SYM_IPC_NULL, + SORT_TIME, /* branch stack specific sort keys */ __SORT_BRANCH_STACK, diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 758bf5f74e6e..58442ca5e3c4 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -6,6 +6,7 @@ #include <string.h> #include <linux/kernel.h> #include <linux/mman.h> +#include <linux/time64.h> #include <sys/types.h> #include <sys/stat.h> #include <sys/param.h> @@ -39,15 +40,18 @@ int vmlinux_path__nr_entries; char **vmlinux_path; struct symbol_conf symbol_conf = { + .nanosecs = false, .use_modules = true, .try_vmlinux_path = true, .demangle = true, .demangle_kernel = false, .cumulate_callchain = true, + .time_quantum = 100 * NSEC_PER_MSEC, /* 100ms */ .show_hist_headers = true, .symfs = "", .event_group = true, .inline_name = true, + .res_sample = 0, }; static enum dso_binary_type binary_type_symtab[] = { diff --git a/tools/perf/util/symbol_conf.h b/tools/perf/util/symbol_conf.h index fffea68c1203..6c55fa6fccec 100644 --- a/tools/perf/util/symbol_conf.h +++ b/tools/perf/util/symbol_conf.h @@ -8,6 +8,7 @@ struct strlist; struct intlist; struct symbol_conf { + bool nanosecs; unsigned short priv_size; bool try_vmlinux_path, init_annotation, @@ -55,6 +56,7 @@ struct symbol_conf { *sym_list_str, *col_width_list_str, *bt_stop_list_str; + unsigned long time_quantum; struct strlist *dso_list, *comm_list, *sym_list, @@ -66,6 +68,7 @@ struct symbol_conf { struct intlist *pid_list, *tid_list; const char *symfs; + int res_sample; }; extern struct symbol_conf symbol_conf; diff --git a/tools/perf/util/time-utils.c b/tools/perf/util/time-utils.c index 0f53baec660e..20663a460df3 100644 --- a/tools/perf/util/time-utils.c +++ b/tools/perf/util/time-utils.c @@ -453,6 +453,14 @@ int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz) return scnprintf(buf, sz, "%"PRIu64".%06"PRIu64, sec, usec); } +int timestamp__scnprintf_nsec(u64 timestamp, char *buf, size_t sz) +{ + u64 sec = timestamp / NSEC_PER_SEC, + nsec = timestamp % NSEC_PER_SEC; + + return scnprintf(buf, sz, "%" PRIu64 ".%09" PRIu64, sec, nsec); +} + int fetch_current_timestamp(char *buf, size_t sz) { struct timeval tv; diff --git a/tools/perf/util/time-utils.h b/tools/perf/util/time-utils.h index b923de44e36f..72a42ea1d513 100644 --- a/tools/perf/util/time-utils.h +++ b/tools/perf/util/time-utils.h @@ -30,6 +30,7 @@ int perf_time__parse_for_ranges(const char *str, struct perf_session *session, int *range_size, int *range_num); int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz); +int timestamp__scnprintf_nsec(u64 timestamp, char *buf, size_t sz); int fetch_current_timestamp(char *buf, size_t sz); |