6 perf-list - List all symbolic event types
11 'perf list' [hw|sw|cache|tracepoint|pmu|event_glob]
15 This command displays the symbolic event types which can be selected in the
16 various perf commands with the -e option.
22 Events can optionally have a modifier by appending a colon and one or
23 more modifiers. Modifiers allow the user to restrict the events to be
24 counted. The following modifiers exist:
26 u - user-space counting
28 h - hypervisor counting
30 G - guest counting (in KVM guests)
31 H - host counting (not in KVM guests)
33 P - use maximum detected precise level
34 S - read sample value (PERF_SAMPLE_READ)
35 D - pin the event to the PMU
37 The 'p' modifier can be used for specifying how precise the instruction
38 address should be. The 'p' modifier can be specified multiple times:
40 0 - SAMPLE_IP can have arbitrary skid
41 1 - SAMPLE_IP must have constant skid
42 2 - SAMPLE_IP requested to have 0 skid
43 3 - SAMPLE_IP must have 0 skid
45 For Intel systems precise event sampling is implemented with PEBS
46 which supports up to precise-level 2.
48 On AMD systems it is implemented using IBS (up to precise-level 2).
49 The precise modifier works with event types 0x76 (cpu-cycles, CPU
50 clocks not halted) and 0xC1 (micro-ops retired). Both events map to
51 IBS execution sampling (IBS op) with the IBS Op Counter Control bit
52 (IbsOpCntCtl) set respectively (see AMD64 Architecture Programmer’s
53 Manual Volume 2: System Programming, 13.3 Instruction-Based
54 Sampling). Examples to use IBS:
56 perf record -a -e cpu-cycles:p ... # use ibs op counting cycles
57 perf record -a -e r076:p ... # same as -e cpu-cycles:p
58 perf record -a -e r0C1:p ... # use ibs op counting micro-ops
60 RAW HARDWARE EVENT DESCRIPTOR
61 -----------------------------
62 Even when an event is not available in a symbolic form within perf right now,
63 it can be encoded in a per processor specific way.
65 For instance For x86 CPUs NNN represents the raw register encoding with the
66 layout of IA32_PERFEVTSELx MSRs (see [Intel® 64 and IA-32 Architectures Software Developer's Manual Volume 3B: System Programming Guide] Figure 30-1 Layout
67 of IA32_PERFEVTSELx MSRs) or AMD's PerfEvtSeln (see [AMD64 Architecture Programmer’s Manual Volume 2: System Programming], Page 344,
68 Figure 13-7 Performance Event-Select Register (PerfEvtSeln)).
70 Note: Only the following bit fields can be set in x86 counter
71 registers: event, umask, edge, inv, cmask. Esp. guest/host only and
72 OS/user mode flags must be setup using <<EVENT_MODIFIERS, EVENT
77 If the Intel docs for a QM720 Core i7 describe an event as:
79 Event Umask Event Mask
80 Num. Value Mnemonic Description Comment
82 A8H 01H LSD.UOPS Counts the number of micro-ops Use cmask=1 and
83 delivered by loop stream detector invert to count
86 raw encoding of 0x1A8 can be used:
88 perf stat -e r1a8 -a sleep 1
89 perf record -e r1a8 ...
91 You should refer to the processor specific documentation for getting these
92 details. Some of them are referenced in the SEE ALSO section below.
97 Some pmu events listed by 'perf-list' will be displayed with '?' in them. For
100 hv_gpci/dtbp_ptitc,phys_processor_idx=?/
102 This means that when provided as an event, a value for '?' must
103 also be supplied. For example:
105 perf stat -C 0 -e 'hv_gpci/dtbp_ptitc,phys_processor_idx=0x2/' ...
110 Without options all known events will be listed.
112 To limit the list use:
114 . 'hw' or 'hardware' to list hardware events such as cache-misses, etc.
116 . 'sw' or 'software' to list software events such as context switches, etc.
118 . 'cache' or 'hwcache' to list hardware cache events such as L1-dcache-loads, etc.
120 . 'tracepoint' to list all tracepoint events, alternatively use
121 'subsys_glob:event_glob' to filter by tracepoint subsystems such as sched,
124 . 'pmu' to print the kernel supplied PMU events.
126 . If none of the above is matched, it will apply the supplied glob to all
127 events, printing the ones that match.
129 . As a last resort, it will do a substring search in all event names.
131 One or more types can be used at the same time, listing the events for the
136 . '--raw-dump', shows the raw-dump of all the events.
137 . '--raw-dump [hw|sw|cache|tracepoint|pmu|event_glob]', shows the raw-dump of
138 a certain kind of events.
142 linkperf:perf-stat[1], linkperf:perf-top[1],
143 linkperf:perf-record[1],
144 http://www.intel.com/Assets/PDF/manual/253669.pdf[Intel® 64 and IA-32 Architectures Software Developer's Manual Volume 3B: System Programming Guide],
145 http://support.amd.com/us/Processor_TechDocs/24593_APM_v2.pdf[AMD64 Architecture Programmer’s Manual Volume 2: System Programming]