summaryrefslogtreecommitdiff
path: root/include/uapi
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2015-08-31 19:49:05 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2015-08-31 19:49:05 -0700
commit41d859a83c567a9c9f50a34082cc64aab0abb0cd (patch)
treeab911ea521701401413d041e1b92225f3dbdab41 /include/uapi
parent4658000955d1864b54890214434e171949c7f1c5 (diff)
parentbac2e4a96d1c0bcce5e9654dcc902f75576b9b03 (diff)
Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf updates from Ingo Molnar: "Main perf kernel side changes: - uprobes updates/fixes. (Oleg Nesterov) - Add PERF_RECORD_SWITCH to indicate context switches and use it in tooling. (Adrian Hunter) - Support BPF programs attached to uprobes and first steps for BPF tooling support. (Wang Nan) - x86 generic x86 MSR-to-perf PMU driver. (Andy Lutomirski) - x86 Intel PT, LBR and BTS updates. (Alexander Shishkin) - x86 Intel Skylake support. (Andi Kleen) - x86 Intel Knights Landing (KNL) RAPL support. (Dasaratharaman Chandramouli) - x86 Intel Broadwell-DE uncore support. (Kan Liang) - x86 hw breakpoints robustization (Andy Lutomirski) Main perf tooling side changes: - Support Intel PT in several tools, enabling the use of the processor trace feature introduced in Intel Broadwell processors: (Adrian Hunter) # dmesg | grep Performance # [0.188477] Performance Events: PEBS fmt2+, 16-deep LBR, Broadwell events, full-width counters, Intel PMU driver. # perf record -e intel_pt//u -a sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.216 MB perf.data ] # perf script # then navigate in the tool output to some area, like this one: 184 1030 dl_main (/usr/lib64/ld-2.17.so) => 7f21ba661440 dl_main (/usr/lib64/ld-2.17.so) 185 1457 dl_main (/usr/lib64/ld-2.17.so) => 7f21ba669f10 _dl_new_object (/usr/lib64/ld-2.17.so) 186 9f37 _dl_new_object (/usr/lib64/ld-2.17.so) => 7f21ba677b90 strlen (/usr/lib64/ld-2.17.so) 187 7ba3 strlen (/usr/lib64/ld-2.17.so) => 7f21ba677c75 strlen (/usr/lib64/ld-2.17.so) 188 7c78 strlen (/usr/lib64/ld-2.17.so) => 7f21ba669f3c _dl_new_object (/usr/lib64/ld-2.17.so) 189 9f8a _dl_new_object (/usr/lib64/ld-2.17.so) => 7f21ba65fab0 calloc@plt (/usr/lib64/ld-2.17.so) 190 fab0 calloc@plt (/usr/lib64/ld-2.17.so) => 7f21ba675e70 calloc (/usr/lib64/ld-2.17.so) 191 5e87 calloc (/usr/lib64/ld-2.17.so) => 7f21ba65fa90 malloc@plt (/usr/lib64/ld-2.17.so) 192 fa90 malloc@plt (/usr/lib64/ld-2.17.so) => 7f21ba675e60 malloc (/usr/lib64/ld-2.17.so) 193 5e68 malloc (/usr/lib64/ld-2.17.so) => 7f21ba65fa80 __libc_memalign@plt (/usr/lib64/ld-2.17.so) 194 fa80 __libc_memalign@plt (/usr/lib64/ld-2.17.so) => 7f21ba675d50 __libc_memalign (/usr/lib64/ld-2.17.so) 195 5d63 __libc_memalign (/usr/lib64/ld-2.17.so) => 7f21ba675e20 __libc_memalign (/usr/lib64/ld-2.17.so) 196 5e40 __libc_memalign (/usr/lib64/ld-2.17.so) => 7f21ba675d73 __libc_memalign (/usr/lib64/ld-2.17.so) 197 5d97 __libc_memalign (/usr/lib64/ld-2.17.so) => 7f21ba675e18 __libc_memalign (/usr/lib64/ld-2.17.so) 198 5e1e __libc_memalign (/usr/lib64/ld-2.17.so) => 7f21ba675df9 __libc_memalign (/usr/lib64/ld-2.17.so) 199 5e10 __libc_memalign (/usr/lib64/ld-2.17.so) => 7f21ba669f8f _dl_new_object (/usr/lib64/ld-2.17.so) 200 9fc2 _dl_new_object (/usr/lib64/ld-2.17.so) => 7f21ba678e70 memcpy (/usr/lib64/ld-2.17.so) 201 8e8c memcpy (/usr/lib64/ld-2.17.so) => 7f21ba678ea0 memcpy (/usr/lib64/ld-2.17.so) - Add support for using several Intel PT features (CYC, MTC packets), the relevant documentation was updated in: tools/perf/Documentation/intel-pt.txt briefly describing those packets, its purposes, how to configure them in the event config terms and relevant external documentation for further reading. (Adrian Hunter) - Introduce support for probing at an absolute address, for user and kernel 'perf probe's, useful when one have the symbol maps on a developer machine but not on an embedded system. (Wang Nan) - Add Intel BTS support, with a call-graph script to show it and PT in use in a GUI using 'perf script' python scripting with postgresql and Qt. (Adrian Hunter) - Allow selecting the type of callchains per event, including disabling callchains in all but one entry in an event list, to save space, and also to ask for the callchains collected in one event to be used in other events. (Kan Liang) - Beautify more syscall arguments in 'perf trace': (Arnaldo Carvalho de Melo) * A bunch more translate file/pathnames from pointers to strings. * Convert numbers to strings for the 'keyctl' syscall 'option' arg. * Add missing 'clockid' entries. - Introduce 'srcfile' sort key: (Andi Kleen) # perf record -F 10000 usleep 1 # perf report --stdio --dsos '[kernel.vmlinux]' -s srcfile <SNIP> # Overhead Source File 26.49% copy_page_64.S 5.49% signal.c 0.51% msr.h # It can be combined with other fields, for instance, experiment with '-s srcfile,symbol'. There are some oddities in some distros and with some specific DSOs, being investigated, so your mileage may vary. - Support per-event 'freq' term: (Namhyung Kim) $ perf record -e 'cpu/instructions,freq=1234/',cycles -c 1000 sleep 1 $ perf evlist -F cpu/instructions,freq=1234/: sample_freq=1234 cycles: sample_period=1000 $ - Deref sys_enter pointer args with contents from probe:vfs_getname, showing pathnames instead of pointers in many syscalls in 'perf trace'. (Arnaldo Carvalho de Melo) - Stop collecting /proc/kallsyms in perf.data files, saving about 4.5MB on a typical x86-64 system, use the the symbol resolution routines used in all the other tools (report, top, etc) now that we can ask libtraceevent to use perf's symbol resolution code. (Arnaldo Carvalho de Melo) - Allow filtering out of perf's PID via 'perf record --exclude-perf'. (Wang Nan) - 'perf trace' now supports syscall groups, like strace, i.e: $ trace -e file touch file Will expand 'file' into multiple, file related, syscalls. More work needed to add extra groups for other syscall groups, and also to complement what was added for the 'file' group, included as a proof of concept. (Arnaldo Carvalho de Melo) - Add lock_pi stresser to 'perf bench futex', to test the kernel code related to FUTEX_(UN)LOCK_PI. (Davidlohr Bueso) - Let user have timestamps with per-thread recording in 'perf record' (Adrian Hunter) - ... and tons of other changes, see the shortlog and the Git log for details" * 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (240 commits) perf evlist: Add backpointer for perf_env to evlist perf tools: Rename perf_session_env to perf_env perf tools: Do not change lib/api/fs/debugfs directly perf tools: Add tracing_path and remove unneeded functions perf buildid: Introduce sysfs/filename__sprintf_build_id perf evsel: Add a backpointer to the evlist a evsel is in perf trace: Add header with copyright and background info perf scripts python: Add new compaction-times script perf stat: Get correct cpu id for print_aggr tools lib traceeveent: Allow for negative numbers in print format perf script: Add --[no-]-demangle/--[no-]-demangle-kernel tracing/uprobes: Do not print '0x (null)' when offset is 0 perf probe: Support probing at absolute address perf probe: Fix error reported when offset without function perf probe: Fix list result when address is zero perf probe: Fix list result when symbol can't be found tools build: Allow duplicate objects in the object list perf tools: Remove export.h from MANIFEST perf probe: Prevent segfault when reading probe point with absolute address perf tools: Update Intel PT documentation ...
Diffstat (limited to 'include/uapi')
-rw-r--r--include/uapi/linux/perf_event.h35
1 files changed, 33 insertions, 2 deletions
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index d97f84c080da..2881145cda86 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -330,7 +330,8 @@ struct perf_event_attr {
mmap2 : 1, /* include mmap with inode data */
comm_exec : 1, /* flag comm events that are due to an exec */
use_clockid : 1, /* use @clockid for time fields */
- __reserved_1 : 38;
+ context_switch : 1, /* context switch data */
+ __reserved_1 : 37;
union {
__u32 wakeup_events; /* wakeup every n events */
@@ -572,9 +573,11 @@ struct perf_event_mmap_page {
/*
* PERF_RECORD_MISC_MMAP_DATA and PERF_RECORD_MISC_COMM_EXEC are used on
* different events so can reuse the same bit position.
+ * Ditto PERF_RECORD_MISC_SWITCH_OUT.
*/
#define PERF_RECORD_MISC_MMAP_DATA (1 << 13)
#define PERF_RECORD_MISC_COMM_EXEC (1 << 13)
+#define PERF_RECORD_MISC_SWITCH_OUT (1 << 13)
/*
* Indicates that the content of PERF_SAMPLE_IP points to
* the actual instruction that triggered the event. See also
@@ -818,6 +821,32 @@ enum perf_event_type {
*/
PERF_RECORD_LOST_SAMPLES = 13,
+ /*
+ * Records a context switch in or out (flagged by
+ * PERF_RECORD_MISC_SWITCH_OUT). See also
+ * PERF_RECORD_SWITCH_CPU_WIDE.
+ *
+ * struct {
+ * struct perf_event_header header;
+ * struct sample_id sample_id;
+ * };
+ */
+ PERF_RECORD_SWITCH = 14,
+
+ /*
+ * CPU-wide version of PERF_RECORD_SWITCH with next_prev_pid and
+ * next_prev_tid that are the next (switching out) or previous
+ * (switching in) pid/tid.
+ *
+ * struct {
+ * struct perf_event_header header;
+ * u32 next_prev_pid;
+ * u32 next_prev_tid;
+ * struct sample_id sample_id;
+ * };
+ */
+ PERF_RECORD_SWITCH_CPU_WIDE = 15,
+
PERF_RECORD_MAX, /* non-ABI */
};
@@ -922,6 +951,7 @@ union perf_mem_data_src {
*
* in_tx: running in a hardware transaction
* abort: aborting a hardware transaction
+ * cycles: cycles from last branch (or 0 if not supported)
*/
struct perf_branch_entry {
__u64 from;
@@ -930,7 +960,8 @@ struct perf_branch_entry {
predicted:1,/* target predicted */
in_tx:1, /* in transaction */
abort:1, /* transaction abort */
- reserved:60;
+ cycles:16, /* cycle count to last branch */
+ reserved:44;
};
#endif /* _UAPI_LINUX_PERF_EVENT_H */