1 perf-intel-pt(1) 1 perf-intel-pt(1)
2 ================ 2 ================
3 3
4 NAME 4 NAME
5 ---- 5 ----
6 perf-intel-pt - Support for Intel Processor Tr 6 perf-intel-pt - Support for Intel Processor Trace within perf tools
7 7
8 SYNOPSIS 8 SYNOPSIS
9 -------- 9 --------
10 [verse] 10 [verse]
11 'perf record' -e intel_pt// 11 'perf record' -e intel_pt//
12 12
13 DESCRIPTION 13 DESCRIPTION
14 ----------- 14 -----------
15 15
16 Intel Processor Trace (Intel PT) is an extensi 16 Intel Processor Trace (Intel PT) is an extension of Intel Architecture that
17 collects information about software execution 17 collects information about software execution such as control flow, execution
18 modes and timings and formats it into highly c 18 modes and timings and formats it into highly compressed binary packets.
19 Technical details are documented in the Intel 19 Technical details are documented in the Intel 64 and IA-32 Architectures
20 Software Developer Manuals, Chapter 36 Intel P 20 Software Developer Manuals, Chapter 36 Intel Processor Trace.
21 21
22 Intel PT is first supported in Intel Core M an 22 Intel PT is first supported in Intel Core M and 5th generation Intel Core
23 processors that are based on the Intel micro-a 23 processors that are based on the Intel micro-architecture code name Broadwell.
24 24
25 Trace data is collected by 'perf record' and s 25 Trace data is collected by 'perf record' and stored within the perf.data file.
26 See below for options to 'perf record'. 26 See below for options to 'perf record'.
27 27
28 Trace data must be 'decoded' which involves wa 28 Trace data must be 'decoded' which involves walking the object code and matching
29 the trace data packets. For example a TNT pack 29 the trace data packets. For example a TNT packet only tells whether a
30 conditional branch was taken or not taken, so 30 conditional branch was taken or not taken, so to make use of that packet the
31 decoder must know precisely which instruction 31 decoder must know precisely which instruction was being executed.
32 32
33 Decoding is done on-the-fly. The decoder outp 33 Decoding is done on-the-fly. The decoder outputs samples in the same format as
34 samples output by perf hardware events, for ex 34 samples output by perf hardware events, for example as though the "instructions"
35 or "branches" events had been recorded. Prese 35 or "branches" events had been recorded. Presently 3 tools support this:
36 'perf script', 'perf report' and 'perf inject' 36 'perf script', 'perf report' and 'perf inject'. See below for more information
37 on using those tools. 37 on using those tools.
38 38
39 The main distinguishing feature of Intel PT is 39 The main distinguishing feature of Intel PT is that the decoder can determine
40 the exact flow of software execution. Intel P 40 the exact flow of software execution. Intel PT can be used to understand why
41 and how did software get to a certain point, o 41 and how did software get to a certain point, or behave a certain way. The
42 software does not have to be recompiled, so In 42 software does not have to be recompiled, so Intel PT works with debug or release
43 builds, however the executed images are needed 43 builds, however the executed images are needed - which makes use in JIT-compiled
44 environments, or with self-modified code, a ch 44 environments, or with self-modified code, a challenge. Also symbols need to be
45 provided to make sense of addresses. 45 provided to make sense of addresses.
46 46
47 A limitation of Intel PT is that it produces h 47 A limitation of Intel PT is that it produces huge amounts of trace data
48 (hundreds of megabytes per second per core) wh 48 (hundreds of megabytes per second per core) which takes a long time to decode,
49 for example two or three orders of magnitude l 49 for example two or three orders of magnitude longer than it took to collect.
50 Another limitation is the performance impact o 50 Another limitation is the performance impact of tracing, something that will
51 vary depending on the use-case and architectur 51 vary depending on the use-case and architecture.
52 52
53 53
54 Quickstart 54 Quickstart
55 ---------- 55 ----------
56 56
57 It is important to start small. That is becau 57 It is important to start small. That is because it is easy to capture vastly
58 more data than can possibly be processed. 58 more data than can possibly be processed.
59 59
60 The simplest thing to do with Intel PT is user 60 The simplest thing to do with Intel PT is userspace profiling of small programs.
61 Data is captured with 'perf record' e.g. to tr 61 Data is captured with 'perf record' e.g. to trace 'ls' userspace-only:
62 62
63 perf record -e intel_pt//u ls 63 perf record -e intel_pt//u ls
64 64
65 And profiled with 'perf report' e.g. 65 And profiled with 'perf report' e.g.
66 66
67 perf report 67 perf report
68 68
69 To also trace kernel space presents a problem, 69 To also trace kernel space presents a problem, namely kernel self-modifying
70 code. A fairly good kernel image is available 70 code. A fairly good kernel image is available in /proc/kcore but to get an
71 accurate image a copy of /proc/kcore needs to 71 accurate image a copy of /proc/kcore needs to be made under the same conditions
72 as the data capture. 'perf record' can make a 72 as the data capture. 'perf record' can make a copy of /proc/kcore if the option
73 --kcore is used, but access to /proc/kcore is 73 --kcore is used, but access to /proc/kcore is restricted e.g.
74 74
75 sudo perf record -o pt_ls --kcore -e i 75 sudo perf record -o pt_ls --kcore -e intel_pt// -- ls
76 76
77 which will create a directory named 'pt_ls' an 77 which will create a directory named 'pt_ls' and put the perf.data file (named
78 simply 'data') and copies of /proc/kcore, /pro 78 simply 'data') and copies of /proc/kcore, /proc/kallsyms and /proc/modules into
79 it. The other tools understand the directory 79 it. The other tools understand the directory format, so to use 'perf report'
80 becomes: 80 becomes:
81 81
82 sudo perf report -i pt_ls 82 sudo perf report -i pt_ls
83 83
84 Because samples are synthesized after-the-fact 84 Because samples are synthesized after-the-fact, the sampling period can be
85 selected for reporting. e.g. sample every micr 85 selected for reporting. e.g. sample every microsecond
86 86
87 sudo perf report pt_ls --itrace=i1usge 87 sudo perf report pt_ls --itrace=i1usge
88 88
89 See the sections below for more information ab 89 See the sections below for more information about the --itrace option.
90 90
91 Beware the smaller the period, the more sample 91 Beware the smaller the period, the more samples that are produced, and the
92 longer it takes to process them. 92 longer it takes to process them.
93 93
94 Also note that the coarseness of Intel PT timi 94 Also note that the coarseness of Intel PT timing information will start to
95 distort the statistical value of the sampling 95 distort the statistical value of the sampling as the sampling period becomes
96 smaller. 96 smaller.
97 97
98 To represent software control flow, "branches" 98 To represent software control flow, "branches" samples are produced. By default
99 a branch sample is synthesized for every singl 99 a branch sample is synthesized for every single branch. To get an idea what
100 data is available you can use the 'perf script 100 data is available you can use the 'perf script' tool with all itrace sampling
101 options, which will list all the samples. 101 options, which will list all the samples.
102 102
103 perf record -e intel_pt//u ls 103 perf record -e intel_pt//u ls
104 perf script --itrace=iybxwpe !! 104 perf script --itrace=ibxwpe
105 105
106 An interesting field that is not printed by de 106 An interesting field that is not printed by default is 'flags' which can be
107 displayed as follows: 107 displayed as follows:
108 108
109 perf script --itrace=iybxwpe -F+flags !! 109 perf script --itrace=ibxwpe -F+flags
110 110
111 The flags are "bcrosyiABExghDt" which stand fo !! 111 The flags are "bcrosyiABExgh" which stand for branch, call, return, conditional,
112 system, asynchronous, interrupt, transaction a 112 system, asynchronous, interrupt, transaction abort, trace begin, trace end,
113 in transaction, VM-entry, VM-exit, interrupt d !! 113 in transaction, VM-entry, and VM-exit respectively.
114 toggle respectively. <<
115 114
116 perf script also supports higher level ways to 115 perf script also supports higher level ways to dump instruction traces:
117 116
118 perf script --insn-trace=disasm <<
119 <<
120 or to use the xed disassembler, which requires <<
121 (see XED below): <<
122 <<
123 perf script --insn-trace --xed 117 perf script --insn-trace --xed
124 118
>> 119 Dump all instructions. This requires installing the xed tool (see XED below)
125 Dumping all instructions in a long trace can b 120 Dumping all instructions in a long trace can be fairly slow. It is usually better
126 to start with higher level decoding, like 121 to start with higher level decoding, like
127 122
128 perf script --call-trace 123 perf script --call-trace
129 124
130 or 125 or
131 126
132 perf script --call-ret-trace 127 perf script --call-ret-trace
133 128
134 and then select a time range of interest. The 129 and then select a time range of interest. The time range can then be examined
135 in detail with 130 in detail with
136 131
137 perf script --time starttime,stoptime !! 132 perf script --time starttime,stoptime --insn-trace --xed
138 133
139 While examining the trace it's also useful to 134 While examining the trace it's also useful to filter on specific CPUs using
140 the -C option 135 the -C option
141 136
142 perf script --time starttime,stoptime !! 137 perf script --time starttime,stoptime --insn-trace --xed -C 1
143 138
144 Dump all instructions in time range on CPU 1. 139 Dump all instructions in time range on CPU 1.
145 140
146 Another interesting field that is not printed 141 Another interesting field that is not printed by default is 'ipc' which can be
147 displayed as follows: 142 displayed as follows:
148 143
149 perf script --itrace=be -F+ipc 144 perf script --itrace=be -F+ipc
150 145
151 There are two ways that instructions-per-cycle 146 There are two ways that instructions-per-cycle (IPC) can be calculated depending
152 on the recording. 147 on the recording.
153 148
154 If the 'cyc' config term (see config terms sec !! 149 If the 'cyc' config term (see config terms section below) was used, then IPC is
155 and cycle events are calculated using the cycl !! 150 calculated using the cycle count from CYC packets, otherwise MTC packets are
156 MTC packets are used - refer to the 'mtc' conf !! 151 used - refer to the 'mtc' config term. When MTC is used, however, the values
157 the values are less accurate because the timin !! 152 are less accurate because the timing is less accurate.
158 153
159 Because Intel PT does not update the cycle cou 154 Because Intel PT does not update the cycle count on every branch or instruction,
160 the values will often be zero. When there are 155 the values will often be zero. When there are values, they will be the number
161 of instructions and number of cycles since the 156 of instructions and number of cycles since the last update, and thus represent
162 the average IPC cycle count since the last IPC !! 157 the average IPC since the last IPC for that event type. Note IPC for "branches"
163 Note IPC for "branches" events is calculated s !! 158 events is calculated separately from IPC for "instructions" events.
164 events. <<
165 <<
166 Even with the 'cyc' config term, it is possibl <<
167 every change of timestamp, but at the expense <<
168 specifying the itrace 'A' option. Due to the <<
169 actual number of cycles increases even though <<
170 The number of instructions is known, but if IP <<
171 low and so IPC is too high. Note that inaccur <<
172 sampling increases i.e. if the number of cycle <<
173 that becomes less significant if the number of <<
174 useful to use the 'A' option in conjunction wi <<
175 provide higher granularity cycle information. <<
176 159
177 Also note that the IPC instruction count may o 160 Also note that the IPC instruction count may or may not include the current
178 instruction. If the cycle count is associated 161 instruction. If the cycle count is associated with an asynchronous branch
179 (e.g. page fault or interrupt), then the instr 162 (e.g. page fault or interrupt), then the instruction count does not include the
180 current instruction, otherwise it does. That 163 current instruction, otherwise it does. That is consistent with whether or not
181 that instruction has retired when the cycle co 164 that instruction has retired when the cycle count is updated.
182 165
183 Another note, in the case of "branches" events 166 Another note, in the case of "branches" events, non-taken branches are not
184 presently sampled, so IPC values for them do n 167 presently sampled, so IPC values for them do not appear e.g. a CYC packet with a
185 TNT packet that starts with a non-taken branch 168 TNT packet that starts with a non-taken branch. To see every possible IPC
186 value, "instructions" events can be used e.g. 169 value, "instructions" events can be used e.g. --itrace=i0ns
187 170
188 While it is possible to create scripts to anal 171 While it is possible to create scripts to analyze the data, an alternative
189 approach is available to export the data to a 172 approach is available to export the data to a sqlite or postgresql database.
190 Refer to script export-to-sqlite.py or export- 173 Refer to script export-to-sqlite.py or export-to-postgresql.py for more details,
191 and to script exported-sql-viewer.py for an ex 174 and to script exported-sql-viewer.py for an example of using the database.
192 175
193 There is also script intel-pt-events.py which 176 There is also script intel-pt-events.py which provides an example of how to
194 unpack the raw data for power events and PTWRI 177 unpack the raw data for power events and PTWRITE. The script also displays
195 branches, and supports 2 additional modes sele 178 branches, and supports 2 additional modes selected by option:
196 179
197 - --insn-trace - instruction trace !! 180 --insn-trace - instruction trace
198 - --src-trace - source trace !! 181 --src-trace - source trace
199 <<
200 The intel-pt-events.py script also has options <<
201 <<
202 - --all-switch-events - display all switch ev <<
203 - --interleave [<n>] - interleave sample outp <<
204 no more than n samples for a CPU are displaye <<
205 Note this only affects the order of output, a <<
206 same. <<
207 182
208 As mentioned above, it is easy to capture too 183 As mentioned above, it is easy to capture too much data. One way to limit the
209 data captured is to use 'snapshot' mode which 184 data captured is to use 'snapshot' mode which is explained further below.
210 Refer to 'new snapshot option' and 'Intel PT m 185 Refer to 'new snapshot option' and 'Intel PT modes of operation' further below.
211 186
212 Another problem that will be experienced is de 187 Another problem that will be experienced is decoder errors. They can be caused
213 by inability to access the executed image, sel 188 by inability to access the executed image, self-modified or JIT-ed code, or the
214 inability to match side-band information (such 189 inability to match side-band information (such as context switches and mmaps)
215 which results in the decoder not knowing what 190 which results in the decoder not knowing what code was executed.
216 191
217 There is also the problem of perf not being ab 192 There is also the problem of perf not being able to copy the data fast enough,
218 resulting in data lost because the buffer was 193 resulting in data lost because the buffer was full. See 'Buffer handling' below
219 for more details. 194 for more details.
220 195
221 196
222 perf record 197 perf record
223 ----------- 198 -----------
224 199
225 new event 200 new event
226 ~~~~~~~~~ 201 ~~~~~~~~~
227 202
228 The Intel PT kernel driver creates a new PMU f 203 The Intel PT kernel driver creates a new PMU for Intel PT. PMU events are
229 selected by providing the PMU name followed by 204 selected by providing the PMU name followed by the "config" separated by slashes.
230 An enhancement has been made to allow default 205 An enhancement has been made to allow default "config" e.g. the option
231 206
232 -e intel_pt// 207 -e intel_pt//
233 208
234 will use a default config value. Currently th 209 will use a default config value. Currently that is the same as
235 210
236 -e intel_pt/tsc,noretcomp=0/ 211 -e intel_pt/tsc,noretcomp=0/
237 212
238 which is the same as 213 which is the same as
239 214
240 -e intel_pt/tsc=1,noretcomp=0/ 215 -e intel_pt/tsc=1,noretcomp=0/
241 216
242 Note there are now new config terms - see sect 217 Note there are now new config terms - see section 'config terms' further below.
243 218
244 The config terms are listed in /sys/devices/in 219 The config terms are listed in /sys/devices/intel_pt/format. They are bit
245 fields within the config member of the struct 220 fields within the config member of the struct perf_event_attr which is
246 passed to the kernel by the perf_event_open sy 221 passed to the kernel by the perf_event_open system call. They correspond to bit
247 fields in the IA32_RTIT_CTL MSR. Here is a li 222 fields in the IA32_RTIT_CTL MSR. Here is a list of them and their definitions:
248 223
249 $ grep -H . /sys/bus/event_source/devi 224 $ grep -H . /sys/bus/event_source/devices/intel_pt/format/*
250 /sys/bus/event_source/devices/intel_pt 225 /sys/bus/event_source/devices/intel_pt/format/cyc:config:1
251 /sys/bus/event_source/devices/intel_pt 226 /sys/bus/event_source/devices/intel_pt/format/cyc_thresh:config:19-22
252 /sys/bus/event_source/devices/intel_pt 227 /sys/bus/event_source/devices/intel_pt/format/mtc:config:9
253 /sys/bus/event_source/devices/intel_pt 228 /sys/bus/event_source/devices/intel_pt/format/mtc_period:config:14-17
254 /sys/bus/event_source/devices/intel_pt 229 /sys/bus/event_source/devices/intel_pt/format/noretcomp:config:11
255 /sys/bus/event_source/devices/intel_pt 230 /sys/bus/event_source/devices/intel_pt/format/psb_period:config:24-27
256 /sys/bus/event_source/devices/intel_pt 231 /sys/bus/event_source/devices/intel_pt/format/tsc:config:10
257 232
258 Note that the default config must be overridde 233 Note that the default config must be overridden for each term i.e.
259 234
260 -e intel_pt/noretcomp=0/ 235 -e intel_pt/noretcomp=0/
261 236
262 is the same as: 237 is the same as:
263 238
264 -e intel_pt/tsc=1,noretcomp=0/ 239 -e intel_pt/tsc=1,noretcomp=0/
265 240
266 So, to disable TSC packets use: 241 So, to disable TSC packets use:
267 242
268 -e intel_pt/tsc=0/ 243 -e intel_pt/tsc=0/
269 244
270 It is also possible to specify the config valu 245 It is also possible to specify the config value explicitly:
271 246
272 -e intel_pt/config=0x400/ 247 -e intel_pt/config=0x400/
273 248
274 Note that, as with all events, the event is su 249 Note that, as with all events, the event is suffixed with event modifiers:
275 250
276 u userspace 251 u userspace
277 k kernel 252 k kernel
278 h hypervisor 253 h hypervisor
279 G guest 254 G guest
280 H host 255 H host
281 p precise ip 256 p precise ip
282 257
283 'h', 'G' and 'H' are for virtualization which !! 258 'h', 'G' and 'H' are for virtualization which is not supported by Intel PT.
284 'p' is also not relevant to Intel PT. So only 259 'p' is also not relevant to Intel PT. So only options 'u' and 'k' are
285 meaningful for Intel PT. 260 meaningful for Intel PT.
286 261
287 perf_event_attr is displayed if the -vv option 262 perf_event_attr is displayed if the -vv option is used e.g.
288 263
289 -------------------------------------- 264 ------------------------------------------------------------
290 perf_event_attr: 265 perf_event_attr:
291 type 6 266 type 6
292 size 112 267 size 112
293 config 0x400 268 config 0x400
294 { sample_period, sample_freq } 1 269 { sample_period, sample_freq } 1
295 sample_type IP|TI 270 sample_type IP|TID|TIME|CPU|IDENTIFIER
296 read_format ID 271 read_format ID
297 disabled 1 272 disabled 1
298 inherit 1 273 inherit 1
299 exclude_kernel 1 274 exclude_kernel 1
300 exclude_hv 1 275 exclude_hv 1
301 enable_on_exec 1 276 enable_on_exec 1
302 sample_id_all 1 277 sample_id_all 1
303 -------------------------------------- 278 ------------------------------------------------------------
304 sys_perf_event_open: pid 31104 cpu 0 279 sys_perf_event_open: pid 31104 cpu 0 group_fd -1 flags 0x8
305 sys_perf_event_open: pid 31104 cpu 1 280 sys_perf_event_open: pid 31104 cpu 1 group_fd -1 flags 0x8
306 sys_perf_event_open: pid 31104 cpu 2 281 sys_perf_event_open: pid 31104 cpu 2 group_fd -1 flags 0x8
307 sys_perf_event_open: pid 31104 cpu 3 282 sys_perf_event_open: pid 31104 cpu 3 group_fd -1 flags 0x8
308 -------------------------------------- 283 ------------------------------------------------------------
309 284
310 285
311 config terms 286 config terms
312 ~~~~~~~~~~~~ 287 ~~~~~~~~~~~~
313 288
314 The June 2015 version of Intel 64 and IA-32 Ar 289 The June 2015 version of Intel 64 and IA-32 Architectures Software Developer
315 Manuals, Chapter 36 Intel Processor Trace, def 290 Manuals, Chapter 36 Intel Processor Trace, defined new Intel PT features.
316 Some of the features are reflect in new config 291 Some of the features are reflect in new config terms. All the config terms are
317 described below. 292 described below.
318 293
319 tsc Always supported. Produces TS 294 tsc Always supported. Produces TSC timestamp packets to provide
320 timing information. In some c 295 timing information. In some cases it is possible to decode
321 without timing information, fo 296 without timing information, for example a per-thread context
322 that does not overlap executab 297 that does not overlap executable memory maps.
323 298
324 The default config selects tsc 299 The default config selects tsc (i.e. tsc=1).
325 300
326 noretcomp Always supported. Disables "r 301 noretcomp Always supported. Disables "return compression" so a TIP packet
327 is produced when a function re 302 is produced when a function returns. Causes more packets to be
328 produced but might make decodi 303 produced but might make decoding more reliable.
329 304
330 The default config does not se 305 The default config does not select noretcomp (i.e. noretcomp=0).
331 306
332 psb_period Allows the frequency of PSB pa 307 psb_period Allows the frequency of PSB packets to be specified.
333 308
334 The PSB packet is a synchroniz 309 The PSB packet is a synchronization packet that provides a
335 starting point for decoding or 310 starting point for decoding or recovery from errors.
336 311
337 Support for psb_period is indi 312 Support for psb_period is indicated by:
338 313
339 /sys/bus/event_source/ 314 /sys/bus/event_source/devices/intel_pt/caps/psb_cyc
340 315
341 which contains "1" if the feat 316 which contains "1" if the feature is supported and "0"
342 otherwise. 317 otherwise.
343 318
344 Valid values are given by: 319 Valid values are given by:
345 320
346 /sys/bus/event_source/ 321 /sys/bus/event_source/devices/intel_pt/caps/psb_periods
347 322
348 which contains a hexadecimal v 323 which contains a hexadecimal value, the bits of which represent
349 valid values e.g. bit 2 set me 324 valid values e.g. bit 2 set means value 2 is valid.
350 325
351 The psb_period value is conver 326 The psb_period value is converted to the approximate number of
352 trace bytes between PSB packet 327 trace bytes between PSB packets as:
353 328
354 2 ^ (value + 11) 329 2 ^ (value + 11)
355 330
356 e.g. value 3 means 16KiB bytes 331 e.g. value 3 means 16KiB bytes between PSBs
357 332
358 If an invalid value is entered 333 If an invalid value is entered, the error message
359 will give a list of valid valu 334 will give a list of valid values e.g.
360 335
361 $ perf record -e intel 336 $ perf record -e intel_pt/psb_period=15/u uname
362 Invalid psb_period for 337 Invalid psb_period for intel_pt. Valid values are: 0-5
363 338
364 If MTC packets are selected, t 339 If MTC packets are selected, the default config selects a value
365 of 3 (i.e. psb_period=3) or th 340 of 3 (i.e. psb_period=3) or the nearest lower value that is
366 supported (0 is always support 341 supported (0 is always supported). Otherwise the default is 0.
367 342
368 If decoding is expected to be 343 If decoding is expected to be reliable and the buffer is large
369 then a large PSB period can be 344 then a large PSB period can be used.
370 345
371 Because a TSC packet is produc 346 Because a TSC packet is produced with PSB, the PSB period can
372 also affect the granularity to 347 also affect the granularity to timing information in the absence
373 of MTC or CYC. 348 of MTC or CYC.
374 349
375 mtc Produces MTC timing packets. 350 mtc Produces MTC timing packets.
376 351
377 MTC packets provide finer grai 352 MTC packets provide finer grain timestamp information than TSC
378 packets. MTC packets record t 353 packets. MTC packets record time using the hardware crystal
379 clock (CTC) which is related t 354 clock (CTC) which is related to TSC packets using a TMA packet.
380 355
381 Support for this feature is in 356 Support for this feature is indicated by:
382 357
383 /sys/bus/event_source/ 358 /sys/bus/event_source/devices/intel_pt/caps/mtc
384 359
385 which contains "1" if the feat 360 which contains "1" if the feature is supported and
386 "0" otherwise. 361 "0" otherwise.
387 362
388 The frequency of MTC packets c 363 The frequency of MTC packets can also be specified - see
389 mtc_period below. 364 mtc_period below.
390 365
391 mtc_period Specifies how frequently MTC p 366 mtc_period Specifies how frequently MTC packets are produced - see mtc
392 above for how to determine if 367 above for how to determine if MTC packets are supported.
393 368
394 Valid values are given by: 369 Valid values are given by:
395 370
396 /sys/bus/event_source/ 371 /sys/bus/event_source/devices/intel_pt/caps/mtc_periods
397 372
398 which contains a hexadecimal v 373 which contains a hexadecimal value, the bits of which represent
399 valid values e.g. bit 2 set me 374 valid values e.g. bit 2 set means value 2 is valid.
400 375
401 The mtc_period value is conver 376 The mtc_period value is converted to the MTC frequency as:
402 377
403 CTC-frequency / (2 ^ v 378 CTC-frequency / (2 ^ value)
404 379
405 e.g. value 3 means one eighth 380 e.g. value 3 means one eighth of CTC-frequency
406 381
407 Where CTC is the hardware crys 382 Where CTC is the hardware crystal clock, the frequency of which
408 can be related to TSC via valu 383 can be related to TSC via values provided in cpuid leaf 0x15.
409 384
410 If an invalid value is entered 385 If an invalid value is entered, the error message
411 will give a list of valid valu 386 will give a list of valid values e.g.
412 387
413 $ perf record -e intel 388 $ perf record -e intel_pt/mtc_period=15/u uname
414 Invalid mtc_period for 389 Invalid mtc_period for intel_pt. Valid values are: 0,3,6,9
415 390
416 The default value is 3 or the 391 The default value is 3 or the nearest lower value
417 that is supported (0 is always 392 that is supported (0 is always supported).
418 393
419 cyc Produces CYC timing packets. 394 cyc Produces CYC timing packets.
420 395
421 CYC packets provide even finer 396 CYC packets provide even finer grain timestamp information than
422 MTC and TSC packets. A CYC pa 397 MTC and TSC packets. A CYC packet contains the number of CPU
423 cycles since the last CYC pack 398 cycles since the last CYC packet. Unlike MTC and TSC packets,
424 CYC packets are only sent when 399 CYC packets are only sent when another packet is also sent.
425 400
426 Support for this feature is in 401 Support for this feature is indicated by:
427 402
428 /sys/bus/event_source/ 403 /sys/bus/event_source/devices/intel_pt/caps/psb_cyc
429 404
430 which contains "1" if the feat 405 which contains "1" if the feature is supported and
431 "0" otherwise. 406 "0" otherwise.
432 407
433 The number of CYC packets prod 408 The number of CYC packets produced can be reduced by specifying
434 a threshold - see cyc_thresh b 409 a threshold - see cyc_thresh below.
435 410
436 cyc_thresh Specifies how frequently CYC p 411 cyc_thresh Specifies how frequently CYC packets are produced - see cyc
437 above for how to determine if 412 above for how to determine if CYC packets are supported.
438 413
439 Valid cyc_thresh values are gi 414 Valid cyc_thresh values are given by:
440 415
441 /sys/bus/event_source/ 416 /sys/bus/event_source/devices/intel_pt/caps/cycle_thresholds
442 417
443 which contains a hexadecimal v 418 which contains a hexadecimal value, the bits of which represent
444 valid values e.g. bit 2 set me 419 valid values e.g. bit 2 set means value 2 is valid.
445 420
446 The cyc_thresh value represent 421 The cyc_thresh value represents the minimum number of CPU cycles
447 that must have passed before a 422 that must have passed before a CYC packet can be sent. The
448 number of CPU cycles is: 423 number of CPU cycles is:
449 424
450 2 ^ (value - 1) 425 2 ^ (value - 1)
451 426
452 e.g. value 4 means 8 CPU cycle 427 e.g. value 4 means 8 CPU cycles must pass before a CYC packet
453 can be sent. Note a CYC packe 428 can be sent. Note a CYC packet is still only sent when another
454 packet is sent, not at, e.g. e 429 packet is sent, not at, e.g. every 8 CPU cycles.
455 430
456 If an invalid value is entered 431 If an invalid value is entered, the error message
457 will give a list of valid valu 432 will give a list of valid values e.g.
458 433
459 $ perf record -e intel 434 $ perf record -e intel_pt/cyc,cyc_thresh=15/u uname
460 Invalid cyc_thresh for 435 Invalid cyc_thresh for intel_pt. Valid values are: 0-12
461 436
462 CYC packets are not requested 437 CYC packets are not requested by default.
463 438
464 pt Specifies pass-through which e 439 pt Specifies pass-through which enables the 'branch' config term.
465 440
466 The default config selects 'pt 441 The default config selects 'pt' if it is available, so a user will
467 never need to specify this ter 442 never need to specify this term.
468 443
469 branch Enable branch tracing. Branch 444 branch Enable branch tracing. Branch tracing is enabled by default so to
470 disable branch tracing use 'br 445 disable branch tracing use 'branch=0'.
471 446
472 The default config selects 'br 447 The default config selects 'branch' if it is available.
473 448
474 ptw Enable PTWRITE packets which a 449 ptw Enable PTWRITE packets which are produced when a ptwrite instruction
475 is executed. 450 is executed.
476 451
477 Support for this feature is in 452 Support for this feature is indicated by:
478 453
479 /sys/bus/event_source/ 454 /sys/bus/event_source/devices/intel_pt/caps/ptwrite
480 455
481 which contains "1" if the feat 456 which contains "1" if the feature is supported and
482 "0" otherwise. 457 "0" otherwise.
483 458
484 As an alternative, refer to "E <<
485 <<
486 fup_on_ptw Enable a FUP packet to follow 459 fup_on_ptw Enable a FUP packet to follow the PTWRITE packet. The FUP packet
487 provides the address of the pt 460 provides the address of the ptwrite instruction. In the absence of
488 fup_on_ptw, the decoder will u 461 fup_on_ptw, the decoder will use the address of the previous branch
489 if branch tracing is enabled, 462 if branch tracing is enabled, otherwise the address will be zero.
490 Note that fup_on_ptw will work 463 Note that fup_on_ptw will work even when branch tracing is disabled.
491 464
492 pwr_evt Enable power events. The powe 465 pwr_evt Enable power events. The power events provide information about
493 changes to the CPU C-state. 466 changes to the CPU C-state.
494 467
495 Support for this feature is in 468 Support for this feature is indicated by:
496 469
497 /sys/bus/event_source/ 470 /sys/bus/event_source/devices/intel_pt/caps/power_event_trace
498 471
499 which contains "1" if the feat 472 which contains "1" if the feature is supported and
500 "0" otherwise. 473 "0" otherwise.
501 474
502 event Enable Event Trace. The event <<
503 events. <<
504 <<
505 Support for this feature is in <<
506 <<
507 /sys/bus/event_source/ <<
508 <<
509 which contains "1" if the feat <<
510 "0" otherwise. <<
511 <<
512 notnt Disable TNT packets. Without <<
513 executable code to reconstruct <<
514 and TIP.PGD packets still indi <<
515 return compression is disabled <<
516 The advantage of eliminating T <<
517 trace and corresponding tracin <<
518 <<
519 Support for this feature is in <<
520 <<
521 /sys/bus/event_source/ <<
522 <<
523 which contains "1" if the feat <<
524 "0" otherwise. <<
525 <<
526 475
527 AUX area sampling option 476 AUX area sampling option
528 ~~~~~~~~~~~~~~~~~~~~~~~~ 477 ~~~~~~~~~~~~~~~~~~~~~~~~
529 478
530 To select Intel PT "sampling" the AUX area sam 479 To select Intel PT "sampling" the AUX area sampling option can be used:
531 480
532 --aux-sample 481 --aux-sample
533 482
534 Optionally it can be followed by the sample si 483 Optionally it can be followed by the sample size in bytes e.g.
535 484
536 --aux-sample=8192 485 --aux-sample=8192
537 486
538 In addition, the Intel PT event to sample must 487 In addition, the Intel PT event to sample must be defined e.g.
539 488
540 -e intel_pt//u 489 -e intel_pt//u
541 490
542 Samples on other events will be created contai 491 Samples on other events will be created containing Intel PT data e.g. the
543 following will create Intel PT samples on the 492 following will create Intel PT samples on the branch-misses event, note the
544 events must be grouped using {}: 493 events must be grouped using {}:
545 494
546 perf record --aux-sample -e '{intel_pt 495 perf record --aux-sample -e '{intel_pt//u,branch-misses:u}'
547 496
548 An alternative to '--aux-sample' is to add the 497 An alternative to '--aux-sample' is to add the config term 'aux-sample-size' to
549 events. In this case, the grouping is implied 498 events. In this case, the grouping is implied e.g.
550 499
551 perf record -e intel_pt//u -e branch-m 500 perf record -e intel_pt//u -e branch-misses/aux-sample-size=8192/u
552 501
553 is the same as: 502 is the same as:
554 503
555 perf record -e '{intel_pt//u,branch-mi 504 perf record -e '{intel_pt//u,branch-misses/aux-sample-size=8192/u}'
556 505
557 but allows for also using an address filter e. 506 but allows for also using an address filter e.g.:
558 507
559 perf record -e intel_pt//u --filter 'f 508 perf record -e intel_pt//u --filter 'filter * @/bin/ls' -e branch-misses/aux-sample-size=8192/u -- ls
560 509
561 It is important to select a sample size that i 510 It is important to select a sample size that is big enough to contain at least
562 one PSB packet. If not a warning will be disp 511 one PSB packet. If not a warning will be displayed:
563 512
564 Intel PT sample size (%zu) may be too 513 Intel PT sample size (%zu) may be too small for PSB period (%zu)
565 514
566 The calculation used for that is: if sample_si 515 The calculation used for that is: if sample_size <= psb_period + 256 display the
567 warning. When sampling is used, psb_period de 516 warning. When sampling is used, psb_period defaults to 0 (2KiB).
568 517
569 The default sample size is 4KiB. 518 The default sample size is 4KiB.
570 519
571 The sample size is passed in aux_sample_size i 520 The sample size is passed in aux_sample_size in struct perf_event_attr. The
572 sample size is limited by the maximum event si 521 sample size is limited by the maximum event size which is 64KiB. It is
573 difficult to know how big the event might be w 522 difficult to know how big the event might be without the trace sample attached,
574 but the tool validates that the sample size is 523 but the tool validates that the sample size is not greater than 60KiB.
575 524
576 525
577 new snapshot option 526 new snapshot option
578 ~~~~~~~~~~~~~~~~~~~ 527 ~~~~~~~~~~~~~~~~~~~
579 528
580 The difference between full trace and snapshot 529 The difference between full trace and snapshot from the kernel's perspective is
581 that in full trace we don't overwrite trace da 530 that in full trace we don't overwrite trace data that the user hasn't collected
582 yet (and indicated that by advancing aux_tail) 531 yet (and indicated that by advancing aux_tail), whereas in snapshot mode we let
583 the trace run and overwrite older data in the 532 the trace run and overwrite older data in the buffer so that whenever something
584 interesting happens, we can stop it and grab a 533 interesting happens, we can stop it and grab a snapshot of what was going on
585 around that interesting moment. 534 around that interesting moment.
586 535
587 To select snapshot mode a new option has been 536 To select snapshot mode a new option has been added:
588 537
589 -S 538 -S
590 539
591 Optionally it can be followed by the snapshot 540 Optionally it can be followed by the snapshot size e.g.
592 541
593 -S0x100000 542 -S0x100000
594 543
595 The default snapshot size is the auxtrace mmap 544 The default snapshot size is the auxtrace mmap size. If neither auxtrace mmap size
596 nor snapshot size is specified, then the defau 545 nor snapshot size is specified, then the default is 4MiB for privileged users
597 (or if /proc/sys/kernel/perf_event_paranoid < 546 (or if /proc/sys/kernel/perf_event_paranoid < 0), 128KiB for unprivileged users.
598 If an unprivileged user does not specify mmap 547 If an unprivileged user does not specify mmap pages, the mmap pages will be
599 reduced as described in the 'new auxtrace mmap 548 reduced as described in the 'new auxtrace mmap size option' section below.
600 549
601 The snapshot size is displayed if the option - 550 The snapshot size is displayed if the option -vv is used e.g.
602 551
603 Intel PT snapshot size: %zu 552 Intel PT snapshot size: %zu
604 553
605 554
606 new auxtrace mmap size option 555 new auxtrace mmap size option
607 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 556 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
608 557
609 Intel PT buffer size is specified by an additi 558 Intel PT buffer size is specified by an addition to the -m option e.g.
610 559
611 -m,16 560 -m,16
612 561
613 selects a buffer size of 16 pages i.e. 64KiB. 562 selects a buffer size of 16 pages i.e. 64KiB.
614 563
615 Note that the existing functionality of -m is 564 Note that the existing functionality of -m is unchanged. The auxtrace mmap size
616 is specified by the optional addition of a com 565 is specified by the optional addition of a comma and the value.
617 566
618 The default auxtrace mmap size for Intel PT is 567 The default auxtrace mmap size for Intel PT is 4MiB/page_size for privileged users
619 (or if /proc/sys/kernel/perf_event_paranoid < 568 (or if /proc/sys/kernel/perf_event_paranoid < 0), 128KiB for unprivileged users.
620 If an unprivileged user does not specify mmap 569 If an unprivileged user does not specify mmap pages, the mmap pages will be
621 reduced from the default 512KiB/page_size to 2 570 reduced from the default 512KiB/page_size to 256KiB/page_size, otherwise the
622 user is likely to get an error as they exceed 571 user is likely to get an error as they exceed their mlock limit (Max locked
623 memory as shown in /proc/self/limits). Note t 572 memory as shown in /proc/self/limits). Note that perf does not count the first
624 512KiB (actually /proc/sys/kernel/perf_event_m 573 512KiB (actually /proc/sys/kernel/perf_event_mlock_kb minus 1 page) per cpu
625 against the mlock limit so an unprivileged use 574 against the mlock limit so an unprivileged user is allowed 512KiB per cpu plus
626 their mlock limit (which defaults to 64KiB but 575 their mlock limit (which defaults to 64KiB but is not multiplied by the number
627 of cpus). 576 of cpus).
628 577
629 In full-trace mode, powers of two are allowed 578 In full-trace mode, powers of two are allowed for buffer size, with a minimum
630 size of 2 pages. In snapshot mode or sampling 579 size of 2 pages. In snapshot mode or sampling mode, it is the same but the
631 minimum size is 1 page. 580 minimum size is 1 page.
632 581
633 The mmap size and auxtrace mmap size are displ 582 The mmap size and auxtrace mmap size are displayed if the -vv option is used e.g.
634 583
635 mmap length 528384 584 mmap length 528384
636 auxtrace mmap length 4198400 585 auxtrace mmap length 4198400
637 586
638 587
639 Intel PT modes of operation 588 Intel PT modes of operation
640 ~~~~~~~~~~~~~~~~~~~~~~~~~~~ 589 ~~~~~~~~~~~~~~~~~~~~~~~~~~~
641 590
642 Intel PT can be used in 3 modes: 591 Intel PT can be used in 3 modes:
643 full-trace mode 592 full-trace mode
644 sample mode 593 sample mode
645 snapshot mode 594 snapshot mode
646 595
647 Full-trace mode traces continuously e.g. 596 Full-trace mode traces continuously e.g.
648 597
649 perf record -e intel_pt//u uname 598 perf record -e intel_pt//u uname
650 599
651 Sample mode attaches a Intel PT sample to othe 600 Sample mode attaches a Intel PT sample to other events e.g.
652 601
653 perf record --aux-sample -e intel_pt// 602 perf record --aux-sample -e intel_pt//u -e branch-misses:u
654 603
655 Snapshot mode captures the available data when 604 Snapshot mode captures the available data when a signal is sent or "snapshot"
656 control command is issued. e.g. using a signal 605 control command is issued. e.g. using a signal
657 606
658 perf record -v -e intel_pt//u -S ./loo 607 perf record -v -e intel_pt//u -S ./loopy 1000000000 &
659 [1] 11435 608 [1] 11435
660 kill -USR2 11435 609 kill -USR2 11435
661 Recording AUX area tracing snapshot 610 Recording AUX area tracing snapshot
662 611
663 Note that the signal sent is SIGUSR2. 612 Note that the signal sent is SIGUSR2.
664 Note that "Recording AUX area tracing snapshot 613 Note that "Recording AUX area tracing snapshot" is displayed because the -v
665 option is used. 614 option is used.
666 615
667 The advantage of using "snapshot" control comm 616 The advantage of using "snapshot" control command is that the access is
668 controlled by access to a FIFO e.g. 617 controlled by access to a FIFO e.g.
669 618
670 $ mkfifo perf.control 619 $ mkfifo perf.control
671 $ mkfifo perf.ack 620 $ mkfifo perf.ack
672 $ cat perf.ack & 621 $ cat perf.ack &
673 [1] 15235 622 [1] 15235
674 $ sudo ~/bin/perf record --control fif 623 $ sudo ~/bin/perf record --control fifo:perf.control,perf.ack -S -e intel_pt//u -- sleep 60 &
675 [2] 15243 624 [2] 15243
676 $ ps -e | grep perf 625 $ ps -e | grep perf
677 15244 pts/1 00:00:00 perf 626 15244 pts/1 00:00:00 perf
678 $ kill -USR2 15244 627 $ kill -USR2 15244
679 bash: kill: (15244) - Operation not pe 628 bash: kill: (15244) - Operation not permitted
680 $ echo snapshot > perf.control 629 $ echo snapshot > perf.control
681 ack 630 ack
682 631
683 The 3 Intel PT modes of operation cannot be us 632 The 3 Intel PT modes of operation cannot be used together.
684 633
685 634
686 Buffer handling 635 Buffer handling
687 ~~~~~~~~~~~~~~~ 636 ~~~~~~~~~~~~~~~
688 637
689 There may be buffer limitations (i.e. single T 638 There may be buffer limitations (i.e. single ToPa entry) which means that actual
690 buffer sizes are limited to powers of 2 up to !! 639 buffer sizes are limited to powers of 2 up to 4MiB (MAX_ORDER). In order to
691 provide other sizes, and in particular an arbi 640 provide other sizes, and in particular an arbitrarily large size, multiple
692 buffers are logically concatenated. However a 641 buffers are logically concatenated. However an interrupt must be used to switch
693 between buffers. That has two potential probl 642 between buffers. That has two potential problems:
694 a) the interrupt may not be handled in 643 a) the interrupt may not be handled in time so that the current buffer
695 becomes full and some trace data is lo 644 becomes full and some trace data is lost.
696 b) the interrupts may slow the system 645 b) the interrupts may slow the system and affect the performance
697 results. 646 results.
698 647
699 If trace data is lost, the driver sets 'trunca 648 If trace data is lost, the driver sets 'truncated' in the PERF_RECORD_AUX event
700 which the tools report as an error. 649 which the tools report as an error.
701 650
702 In full-trace mode, the driver waits for data 651 In full-trace mode, the driver waits for data to be copied out before allowing
703 the (logical) buffer to wrap-around. If data 652 the (logical) buffer to wrap-around. If data is not copied out quickly enough,
704 again 'truncated' is set in the PERF_RECORD_AU 653 again 'truncated' is set in the PERF_RECORD_AUX event. If the driver has to
705 wait, the intel_pt event gets disabled. Becau 654 wait, the intel_pt event gets disabled. Because it is difficult to know when
706 that happens, perf tools always re-enable the 655 that happens, perf tools always re-enable the intel_pt event after copying out
707 data. 656 data.
708 657
709 658
710 Intel PT and build ids 659 Intel PT and build ids
711 ~~~~~~~~~~~~~~~~~~~~~~ 660 ~~~~~~~~~~~~~~~~~~~~~~
712 661
713 By default "perf record" post-processes the ev 662 By default "perf record" post-processes the event stream to find all build ids
714 for executables for all addresses sampled. De 663 for executables for all addresses sampled. Deliberately, Intel PT is not
715 decoded for that purpose (it would take too lo 664 decoded for that purpose (it would take too long). Instead the build ids for
716 all executables encountered (due to mmap, comm 665 all executables encountered (due to mmap, comm or task events) are included
717 in the perf.data file. 666 in the perf.data file.
718 667
719 To see buildids included in the perf.data file 668 To see buildids included in the perf.data file use the command:
720 669
721 perf buildid-list 670 perf buildid-list
722 671
723 If the perf.data file contains Intel PT data, 672 If the perf.data file contains Intel PT data, that is the same as:
724 673
725 perf buildid-list --with-hits 674 perf buildid-list --with-hits
726 675
727 676
728 Snapshot mode and event disabling 677 Snapshot mode and event disabling
729 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 678 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
730 679
731 In order to make a snapshot, the intel_pt even 680 In order to make a snapshot, the intel_pt event is disabled using an IOCTL,
732 namely PERF_EVENT_IOC_DISABLE. However doing 681 namely PERF_EVENT_IOC_DISABLE. However doing that can also disable the
733 collection of side-band information. In order 682 collection of side-band information. In order to prevent that, a dummy
734 software event has been introduced that permit 683 software event has been introduced that permits tracking events (like mmaps) to
735 continue to be recorded while intel_pt is disa 684 continue to be recorded while intel_pt is disabled. That is important to ensure
736 there is complete side-band information to all 685 there is complete side-band information to allow the decoding of subsequent
737 snapshots. 686 snapshots.
738 687
739 A test has been created for that. To find the 688 A test has been created for that. To find the test:
740 689
741 perf test list 690 perf test list
742 ... 691 ...
743 23: Test using a dummy software event 692 23: Test using a dummy software event to keep tracking
744 693
745 To run the test: 694 To run the test:
746 695
747 perf test 23 696 perf test 23
748 23: Test using a dummy software event 697 23: Test using a dummy software event to keep tracking : Ok
749 698
750 699
751 perf record modes (nothing new here) 700 perf record modes (nothing new here)
752 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 701 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
753 702
754 perf record essentially operates in one of thr 703 perf record essentially operates in one of three modes:
755 per thread 704 per thread
756 per cpu 705 per cpu
757 workload only 706 workload only
758 707
759 "per thread" mode is selected by -t or by --pe 708 "per thread" mode is selected by -t or by --per-thread (with -p or -u or just a
760 workload). 709 workload).
761 "per cpu" is selected by -C or -a. 710 "per cpu" is selected by -C or -a.
762 "workload only" mode is selected by not using 711 "workload only" mode is selected by not using the other options but providing a
763 command to run (i.e. the workload). 712 command to run (i.e. the workload).
764 713
765 In per-thread mode an exact list of threads is 714 In per-thread mode an exact list of threads is traced. There is no inheritance.
766 Each thread has its own event buffer. 715 Each thread has its own event buffer.
767 716
768 In per-cpu mode all processes (or processes fr 717 In per-cpu mode all processes (or processes from the selected cgroup i.e. -G
769 option, or processes selected with -p or -u) a 718 option, or processes selected with -p or -u) are traced. Each cpu has its own
770 buffer. Inheritance is allowed. 719 buffer. Inheritance is allowed.
771 720
772 In workload-only mode, the workload is traced 721 In workload-only mode, the workload is traced but with per-cpu buffers.
773 Inheritance is allowed. Note that you can now 722 Inheritance is allowed. Note that you can now trace a workload in per-thread
774 mode by using the --per-thread option. 723 mode by using the --per-thread option.
775 724
776 725
777 Privileged vs non-privileged users 726 Privileged vs non-privileged users
778 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 727 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
779 728
780 Unless /proc/sys/kernel/perf_event_paranoid is 729 Unless /proc/sys/kernel/perf_event_paranoid is set to -1, unprivileged users
781 have memory limits imposed upon them. That af 730 have memory limits imposed upon them. That affects what buffer sizes they can
782 have as outlined above. 731 have as outlined above.
783 732
784 The v4.2 kernel introduced support for a conte 733 The v4.2 kernel introduced support for a context switch metadata event,
785 PERF_RECORD_SWITCH, which allows unprivileged 734 PERF_RECORD_SWITCH, which allows unprivileged users to see when their processes
786 are scheduled out and in, just not by whom, wh 735 are scheduled out and in, just not by whom, which is left for the
787 PERF_RECORD_SWITCH_CPU_WIDE, that is only acce 736 PERF_RECORD_SWITCH_CPU_WIDE, that is only accessible in system wide context,
788 which in turn requires CAP_PERFMON or CAP_SYS_ 737 which in turn requires CAP_PERFMON or CAP_SYS_ADMIN.
789 738
790 Please see the 45ac1403f564 ("perf: Add PERF_R 739 Please see the 45ac1403f564 ("perf: Add PERF_RECORD_SWITCH to indicate context
791 switches") commit, that introduces these metad 740 switches") commit, that introduces these metadata events for further info.
792 741
793 When working with kernels < v4.2, the followin 742 When working with kernels < v4.2, the following considerations must be taken,
794 as the sched:sched_switch tracepoints will be 743 as the sched:sched_switch tracepoints will be used to receive such information:
795 744
796 Unless /proc/sys/kernel/perf_event_paranoid is 745 Unless /proc/sys/kernel/perf_event_paranoid is set to -1, unprivileged users are
797 not permitted to use tracepoints which means t 746 not permitted to use tracepoints which means there is insufficient side-band
798 information to decode Intel PT in per-cpu mode 747 information to decode Intel PT in per-cpu mode, and potentially workload-only
799 mode too if the workload creates new processes 748 mode too if the workload creates new processes.
800 749
801 Note also, that to use tracepoints, read-acces 750 Note also, that to use tracepoints, read-access to debugfs is required. So if
802 debugfs is not mounted or the user does not ha 751 debugfs is not mounted or the user does not have read-access, it will again not
803 be possible to decode Intel PT in per-cpu mode 752 be possible to decode Intel PT in per-cpu mode.
804 753
805 754
806 sched_switch tracepoint 755 sched_switch tracepoint
807 ~~~~~~~~~~~~~~~~~~~~~~~ 756 ~~~~~~~~~~~~~~~~~~~~~~~
808 757
809 The sched_switch tracepoint is used to provide 758 The sched_switch tracepoint is used to provide side-band data for Intel PT
810 decoding in kernels where the PERF_RECORD_SWIT 759 decoding in kernels where the PERF_RECORD_SWITCH metadata event isn't
811 available. 760 available.
812 761
813 The sched_switch events are automatically adde 762 The sched_switch events are automatically added. e.g. the second event shown
814 below: 763 below:
815 764
816 $ perf record -vv -e intel_pt//u uname 765 $ perf record -vv -e intel_pt//u uname
817 -------------------------------------- 766 ------------------------------------------------------------
818 perf_event_attr: 767 perf_event_attr:
819 type 6 768 type 6
820 size 112 769 size 112
821 config 0x400 770 config 0x400
822 { sample_period, sample_freq } 1 771 { sample_period, sample_freq } 1
823 sample_type IP|TI 772 sample_type IP|TID|TIME|CPU|IDENTIFIER
824 read_format ID 773 read_format ID
825 disabled 1 774 disabled 1
826 inherit 1 775 inherit 1
827 exclude_kernel 1 776 exclude_kernel 1
828 exclude_hv 1 777 exclude_hv 1
829 enable_on_exec 1 778 enable_on_exec 1
830 sample_id_all 1 779 sample_id_all 1
831 -------------------------------------- 780 ------------------------------------------------------------
832 sys_perf_event_open: pid 31104 cpu 0 781 sys_perf_event_open: pid 31104 cpu 0 group_fd -1 flags 0x8
833 sys_perf_event_open: pid 31104 cpu 1 782 sys_perf_event_open: pid 31104 cpu 1 group_fd -1 flags 0x8
834 sys_perf_event_open: pid 31104 cpu 2 783 sys_perf_event_open: pid 31104 cpu 2 group_fd -1 flags 0x8
835 sys_perf_event_open: pid 31104 cpu 3 784 sys_perf_event_open: pid 31104 cpu 3 group_fd -1 flags 0x8
836 -------------------------------------- 785 ------------------------------------------------------------
837 perf_event_attr: 786 perf_event_attr:
838 type 2 787 type 2
839 size 112 788 size 112
840 config 0x108 789 config 0x108
841 { sample_period, sample_freq } 1 790 { sample_period, sample_freq } 1
842 sample_type IP|TI 791 sample_type IP|TID|TIME|CPU|PERIOD|RAW|IDENTIFIER
843 read_format ID 792 read_format ID
844 inherit 1 793 inherit 1
845 sample_id_all 1 794 sample_id_all 1
846 exclude_guest 1 795 exclude_guest 1
847 -------------------------------------- 796 ------------------------------------------------------------
848 sys_perf_event_open: pid -1 cpu 0 gr 797 sys_perf_event_open: pid -1 cpu 0 group_fd -1 flags 0x8
849 sys_perf_event_open: pid -1 cpu 1 gr 798 sys_perf_event_open: pid -1 cpu 1 group_fd -1 flags 0x8
850 sys_perf_event_open: pid -1 cpu 2 gr 799 sys_perf_event_open: pid -1 cpu 2 group_fd -1 flags 0x8
851 sys_perf_event_open: pid -1 cpu 3 gr 800 sys_perf_event_open: pid -1 cpu 3 group_fd -1 flags 0x8
852 -------------------------------------- 801 ------------------------------------------------------------
853 perf_event_attr: 802 perf_event_attr:
854 type 1 803 type 1
855 size 112 804 size 112
856 config 0x9 805 config 0x9
857 { sample_period, sample_freq } 1 806 { sample_period, sample_freq } 1
858 sample_type IP|TI 807 sample_type IP|TID|TIME|IDENTIFIER
859 read_format ID 808 read_format ID
860 disabled 1 809 disabled 1
861 inherit 1 810 inherit 1
862 exclude_kernel 1 811 exclude_kernel 1
863 exclude_hv 1 812 exclude_hv 1
864 mmap 1 813 mmap 1
865 comm 1 814 comm 1
866 enable_on_exec 1 815 enable_on_exec 1
867 task 1 816 task 1
868 sample_id_all 1 817 sample_id_all 1
869 mmap2 1 818 mmap2 1
870 comm_exec 1 819 comm_exec 1
871 -------------------------------------- 820 ------------------------------------------------------------
872 sys_perf_event_open: pid 31104 cpu 0 821 sys_perf_event_open: pid 31104 cpu 0 group_fd -1 flags 0x8
873 sys_perf_event_open: pid 31104 cpu 1 822 sys_perf_event_open: pid 31104 cpu 1 group_fd -1 flags 0x8
874 sys_perf_event_open: pid 31104 cpu 2 823 sys_perf_event_open: pid 31104 cpu 2 group_fd -1 flags 0x8
875 sys_perf_event_open: pid 31104 cpu 3 824 sys_perf_event_open: pid 31104 cpu 3 group_fd -1 flags 0x8
876 mmap size 528384B 825 mmap size 528384B
877 AUX area mmap length 4194304 826 AUX area mmap length 4194304
878 perf event ring buffer mmapped per cpu 827 perf event ring buffer mmapped per cpu
879 Synthesizing auxtrace information 828 Synthesizing auxtrace information
880 Linux 829 Linux
881 [ perf record: Woken up 1 times to wri 830 [ perf record: Woken up 1 times to write data ]
882 [ perf record: Captured and wrote 0.04 831 [ perf record: Captured and wrote 0.042 MB perf.data ]
883 832
884 Note, the sched_switch event is only added if 833 Note, the sched_switch event is only added if the user is permitted to use it
885 and only in per-cpu mode. 834 and only in per-cpu mode.
886 835
887 Note also, the sched_switch event is only adde 836 Note also, the sched_switch event is only added if TSC packets are requested.
888 That is because, in the absence of timing info 837 That is because, in the absence of timing information, the sched_switch events
889 cannot be matched against the Intel PT trace. 838 cannot be matched against the Intel PT trace.
890 839
891 840
892 perf script 841 perf script
893 ----------- 842 -----------
894 843
895 By default, perf script will decode trace data 844 By default, perf script will decode trace data found in the perf.data file.
896 This can be further controlled by new option - 845 This can be further controlled by new option --itrace.
897 846
898 847
899 New --itrace option 848 New --itrace option
900 ~~~~~~~~~~~~~~~~~~~ 849 ~~~~~~~~~~~~~~~~~~~
901 850
902 Having no option is the same as 851 Having no option is the same as
903 852
904 --itrace 853 --itrace
905 854
906 which, in turn, is the same as 855 which, in turn, is the same as
907 856
908 --itrace=cepwxy !! 857 --itrace=cepwx
909 858
910 The letters are: 859 The letters are:
911 860
912 i synthesize "instructions" even 861 i synthesize "instructions" events
913 y synthesize "cycles" events <<
914 b synthesize "branches" events 862 b synthesize "branches" events
915 x synthesize "transactions" even 863 x synthesize "transactions" events
916 w synthesize "ptwrite" events 864 w synthesize "ptwrite" events
917 p synthesize "power" events (inc 865 p synthesize "power" events (incl. PSB events)
918 c synthesize branches events (ca 866 c synthesize branches events (calls only)
919 r synthesize branches events (re 867 r synthesize branches events (returns only)
920 o synthesize PEBS-via-PT events <<
921 I synthesize Event Trace events <<
922 e synthesize tracing error event 868 e synthesize tracing error events
923 d create a debug log 869 d create a debug log
924 g synthesize a call chain (use w 870 g synthesize a call chain (use with i or x)
925 G synthesize a call chain on exi 871 G synthesize a call chain on existing event records
926 l synthesize last branch entries 872 l synthesize last branch entries (use with i or x)
927 L synthesize last branch entries 873 L synthesize last branch entries on existing event records
928 s skip initial number of events 874 s skip initial number of events
929 q quicker (less detailed) decodi 875 q quicker (less detailed) decoding
930 A approximate IPC <<
931 Z prefer to ignore timestamps (s 876 Z prefer to ignore timestamps (so-called "timeless" decoding)
932 877
933 "Instructions" events look like they were reco 878 "Instructions" events look like they were recorded by "perf record -e
934 instructions". 879 instructions".
935 880
936 "Cycles" events look like they were recorded b <<
937 (ie., the default). Note that even with CYC pa <<
938 these are not fully accurate, since CYC packet <<
939 instruction, only when some other event (like <<
940 TNT packet representing multiple branches) hap <<
941 be emitted. Thus, it is more effective for att <<
942 (and possibly basic blocks) than to individual <<
943 is not even perfect for functions (although it <<
944 option is active). <<
945 <<
946 "Branches" events look like they were recorded 881 "Branches" events look like they were recorded by "perf record -e branches". "c"
947 and "r" can be combined to get calls and retur 882 and "r" can be combined to get calls and returns.
948 883
949 "Transactions" events correspond to the start 884 "Transactions" events correspond to the start or end of transactions. The
950 'flags' field can be used in perf script to de 885 'flags' field can be used in perf script to determine whether the event is a
951 transaction start, commit or abort. !! 886 tranasaction start, commit or abort.
952 887
953 Note that "instructions", "cycles", "branches" !! 888 Note that "instructions", "branches" and "transactions" events depend on code
954 depend on code flow packets which can be disab !! 889 flow packets which can be disabled by using the config term "branch=0". Refer
955 "branch=0". Refer to the config terms section !! 890 to the config terms section above.
956 891
957 "ptwrite" events record the payload of the ptw 892 "ptwrite" events record the payload of the ptwrite instruction and whether
958 "fup_on_ptw" was used. "ptwrite" events depen 893 "fup_on_ptw" was used. "ptwrite" events depend on PTWRITE packets which are
959 recorded only if the "ptw" config term was use 894 recorded only if the "ptw" config term was used. Refer to the config terms
960 section above. perf script "synth" field disp 895 section above. perf script "synth" field displays "ptwrite" information like
961 this: "ip: 0 payload: 0x123456789abcdef0" whe 896 this: "ip: 0 payload: 0x123456789abcdef0" where "ip" is 1 if "fup_on_ptw" was
962 used. 897 used.
963 898
964 "Power" events correspond to power event packe 899 "Power" events correspond to power event packets and CBR (core-to-bus ratio)
965 packets. While CBR packets are always recorde 900 packets. While CBR packets are always recorded when tracing is enabled, power
966 event packets are recorded only if the "pwr_ev 901 event packets are recorded only if the "pwr_evt" config term was used. Refer to
967 the config terms section above. The power eve 902 the config terms section above. The power events record information about
968 C-state changes, whereas CBR is indicative of 903 C-state changes, whereas CBR is indicative of CPU frequency. perf script
969 "event,synth" fields display information like 904 "event,synth" fields display information like this:
970 <<
971 cbr: cbr: 22 freq: 2189 MHz (200%) 905 cbr: cbr: 22 freq: 2189 MHz (200%)
972 mwait: hints: 0x60 extensions: 0x1 906 mwait: hints: 0x60 extensions: 0x1
973 pwre: hw: 0 cstate: 2 sub-cstate: 0 907 pwre: hw: 0 cstate: 2 sub-cstate: 0
974 exstop: ip: 1 908 exstop: ip: 1
975 pwrx: deepest cstate: 2 last cstate: 909 pwrx: deepest cstate: 2 last cstate: 2 wake reason: 0x4
976 <<
977 Where: 910 Where:
978 <<
979 "cbr" includes the frequency and the p 911 "cbr" includes the frequency and the percentage of maximum non-turbo
980 "mwait" shows mwait hints and extensio 912 "mwait" shows mwait hints and extensions
981 "pwre" shows C-state transitions (to a 913 "pwre" shows C-state transitions (to a C-state deeper than C0) and
982 whether initiated by hardware 914 whether initiated by hardware
983 "exstop" indicates execution stopped a 915 "exstop" indicates execution stopped and whether the IP was recorded
984 exactly, 916 exactly,
985 "pwrx" indicates return to C0 917 "pwrx" indicates return to C0
986 <<
987 For more details refer to the Intel 64 and IA- 918 For more details refer to the Intel 64 and IA-32 Architectures Software
988 Developer Manuals. 919 Developer Manuals.
989 920
990 PSB events show when a PSB+ occurred and also 921 PSB events show when a PSB+ occurred and also the byte-offset in the trace.
991 Emitting a PSB+ can cause a CPU a slight delay 922 Emitting a PSB+ can cause a CPU a slight delay. When doing timing analysis
992 of code with Intel PT, it is useful to know if 923 of code with Intel PT, it is useful to know if a timing bubble was caused
993 by Intel PT or not. 924 by Intel PT or not.
994 925
995 Error events show where the decoder lost the t 926 Error events show where the decoder lost the trace. Error events
996 are quite important. Users must know if what 927 are quite important. Users must know if what they are seeing is a complete
997 picture or not. The "e" option may be followed 928 picture or not. The "e" option may be followed by flags which affect what errors
998 will or will not be reported. Each flag must 929 will or will not be reported. Each flag must be preceded by either '+' or '-'.
999 The flags supported by Intel PT are: 930 The flags supported by Intel PT are:
1000 <<
1001 -o Suppress overflow err 931 -o Suppress overflow errors
1002 -l Suppress trace data l 932 -l Suppress trace data lost errors
1003 <<
1004 For example, for errors but not overflow or d 933 For example, for errors but not overflow or data lost errors:
1005 934
1006 --itrace=e-o-l 935 --itrace=e-o-l
1007 936
1008 The "d" option will cause the creation of a f 937 The "d" option will cause the creation of a file "intel_pt.log" containing all
1009 decoded packets and instructions. Note that 938 decoded packets and instructions. Note that this option slows down the decoder
1010 and that the resulting file may be very large 939 and that the resulting file may be very large. The "d" option may be followed
1011 by flags which affect what debug messages wil 940 by flags which affect what debug messages will or will not be logged. Each flag
1012 must be preceded by either '+' or '-'. The fl 941 must be preceded by either '+' or '-'. The flags support by Intel PT are:
1013 <<
1014 -a Suppress logging of p 942 -a Suppress logging of perf events
1015 +a Log all perf events 943 +a Log all perf events
1016 +e Output only on decodi <<
1017 +o Output to stdout inst <<
1018 <<
1019 By default, logged perf events are filtered b 944 By default, logged perf events are filtered by any specified time ranges, but
1020 flag +a overrides that. The +e flag can be u !! 945 flag +a overrides that.
1021 default, the log size in that case is 16384 b <<
1022 linkperf:perf-config[1] e.g. perf config itra <<
1023 946
1024 In addition, the period of the "instructions" 947 In addition, the period of the "instructions" event can be specified. e.g.
1025 948
1026 --itrace=i10us 949 --itrace=i10us
1027 950
1028 sets the period to 10us i.e. one instruction 951 sets the period to 10us i.e. one instruction sample is synthesized for each 10
1029 microseconds of trace. Alternatives to "us" 952 microseconds of trace. Alternatives to "us" are "ms" (milliseconds),
1030 "ns" (nanoseconds), "t" (TSC ticks) or "i" (i 953 "ns" (nanoseconds), "t" (TSC ticks) or "i" (instructions).
1031 954
1032 "ms", "us" and "ns" are converted to TSC tick 955 "ms", "us" and "ns" are converted to TSC ticks.
1033 956
1034 The timing information included with Intel PT 957 The timing information included with Intel PT does not give the time of every
1035 instruction. Consequently, for the purpose o 958 instruction. Consequently, for the purpose of sampling, the decoder estimates
1036 the time since the last timing packet based o 959 the time since the last timing packet based on 1 tick per instruction. The time
1037 on the sample is *not* adjusted and reflects 960 on the sample is *not* adjusted and reflects the last known value of TSC.
1038 961
1039 For Intel PT, the default period is 100us. 962 For Intel PT, the default period is 100us.
1040 963
1041 Setting it to a zero period means "as often a 964 Setting it to a zero period means "as often as possible".
1042 965
1043 In the case of Intel PT that is the same as a 966 In the case of Intel PT that is the same as a period of 1 and a unit of
1044 'instructions' (i.e. --itrace=i1i). 967 'instructions' (i.e. --itrace=i1i).
1045 968
1046 Also the call chain size (default 16, max. 10 969 Also the call chain size (default 16, max. 1024) for instructions or
1047 transactions events can be specified. e.g. 970 transactions events can be specified. e.g.
1048 971
1049 --itrace=ig32 972 --itrace=ig32
1050 --itrace=xg32 973 --itrace=xg32
1051 974
1052 Also the number of last branch entries (defau 975 Also the number of last branch entries (default 64, max. 1024) for instructions or
1053 transactions events can be specified. e.g. 976 transactions events can be specified. e.g.
1054 977
1055 --itrace=il10 978 --itrace=il10
1056 --itrace=xl10 979 --itrace=xl10
1057 980
1058 Note that last branch entries are cleared for 981 Note that last branch entries are cleared for each sample, so there is no overlap
1059 from one sample to the next. 982 from one sample to the next.
1060 983
1061 The G and L options are designed in particula 984 The G and L options are designed in particular for sample mode, and work much
1062 like g and l but add call chain and branch st 985 like g and l but add call chain and branch stack to the other selected events
1063 instead of synthesized events. For example, t 986 instead of synthesized events. For example, to record branch-misses events for
1064 'ls' and then add a call chain derived from t 987 'ls' and then add a call chain derived from the Intel PT trace:
1065 988
1066 perf record --aux-sample -e '{intel_p 989 perf record --aux-sample -e '{intel_pt//u,branch-misses:u}' -- ls
1067 perf report --itrace=Ge 990 perf report --itrace=Ge
1068 991
1069 Although in fact G is a default for perf repo 992 Although in fact G is a default for perf report, so that is the same as just:
1070 993
1071 perf report 994 perf report
1072 995
1073 One caveat with the G and L options is that t 996 One caveat with the G and L options is that they work poorly with "Large PEBS".
1074 Large PEBS means PEBS records will be accumul 997 Large PEBS means PEBS records will be accumulated by hardware and the written
1075 into the event buffer in one go. That reduce 998 into the event buffer in one go. That reduces interrupts, but can give very
1076 late timestamps. Because the Intel PT trace 999 late timestamps. Because the Intel PT trace is synchronized by timestamps,
1077 the PEBS events do not match the trace. Curr 1000 the PEBS events do not match the trace. Currently, Large PEBS is used only in
1078 certain circumstances: 1001 certain circumstances:
1079 - hardware supports it 1002 - hardware supports it
1080 - PEBS is used 1003 - PEBS is used
1081 - event period is specified, instead 1004 - event period is specified, instead of frequency
1082 - the sample type is limited to the f 1005 - the sample type is limited to the following flags:
1083 PERF_SAMPLE_IP | PERF_SAMPLE_ 1006 PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_ADDR |
1084 PERF_SAMPLE_ID | PERF_SAMPLE_ 1007 PERF_SAMPLE_ID | PERF_SAMPLE_CPU | PERF_SAMPLE_STREAM_ID |
1085 PERF_SAMPLE_DATA_SRC | PERF_S 1008 PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER |
1086 PERF_SAMPLE_TRANSACTION | PER 1009 PERF_SAMPLE_TRANSACTION | PERF_SAMPLE_PHYS_ADDR |
1087 PERF_SAMPLE_REGS_INTR | PERF_ 1010 PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER |
1088 PERF_SAMPLE_PERIOD (and somet 1011 PERF_SAMPLE_PERIOD (and sometimes) | PERF_SAMPLE_TIME
1089 Because Intel PT sample mode uses a different 1012 Because Intel PT sample mode uses a different sample type to the list above,
1090 Large PEBS is not used with Intel PT sample m 1013 Large PEBS is not used with Intel PT sample mode. To avoid Large PEBS in other
1091 cases, avoid specifying the event period i.e. 1014 cases, avoid specifying the event period i.e. avoid the 'perf record' -c option,
1092 --count option, or 'period' config term. 1015 --count option, or 'period' config term.
1093 1016
1094 To disable trace decoding entirely, use the o 1017 To disable trace decoding entirely, use the option --no-itrace.
1095 1018
1096 It is also possible to skip events generated 1019 It is also possible to skip events generated (instructions, branches, transactions)
1097 at the beginning. This is useful to ignore in 1020 at the beginning. This is useful to ignore initialization code.
1098 1021
1099 --itrace=i0nss1000000 1022 --itrace=i0nss1000000
1100 1023
1101 skips the first million instructions. 1024 skips the first million instructions.
1102 1025
1103 The q option changes the way the trace is dec 1026 The q option changes the way the trace is decoded. The decoding is much faster
1104 but much less detailed. Specifically, with t 1027 but much less detailed. Specifically, with the q option, the decoder does not
1105 decode TNT packets, and does not walk object 1028 decode TNT packets, and does not walk object code, but gets the ip from FUP and
1106 TIP packets. The q option can be used with t 1029 TIP packets. The q option can be used with the b and i options but the period
1107 is not used. The q option decodes more quick 1030 is not used. The q option decodes more quickly, but is useful only if the
1108 control flow of interest is represented or in 1031 control flow of interest is represented or indicated by FUP, TIP, TIP.PGE, or
1109 TIP.PGD packets (refer below). However the q 1032 TIP.PGD packets (refer below). However the q option could be used to find time
1110 ranges that could then be decoded fully using 1033 ranges that could then be decoded fully using the --time option.
1111 1034
1112 What will *not* be decoded with the (single) 1035 What will *not* be decoded with the (single) q option:
1113 1036
1114 - direct calls and jmps 1037 - direct calls and jmps
1115 - conditional branches 1038 - conditional branches
1116 - non-branch instructions 1039 - non-branch instructions
1117 1040
1118 What *will* be decoded with the (single) q op 1041 What *will* be decoded with the (single) q option:
1119 1042
1120 - asynchronous branches such as inter 1043 - asynchronous branches such as interrupts
1121 - indirect branches 1044 - indirect branches
1122 - function return target address *if* 1045 - function return target address *if* the noretcomp config term (refer
1123 config terms section) was used 1046 config terms section) was used
1124 - start of (control-flow) tracing 1047 - start of (control-flow) tracing
1125 - end of (control-flow) tracing, if i 1048 - end of (control-flow) tracing, if it is not out of context
1126 - power events, ptwrite, transaction 1049 - power events, ptwrite, transaction start and abort
1127 - instruction pointer associated with 1050 - instruction pointer associated with PSB packets
1128 1051
1129 Note the q option does not specify what event 1052 Note the q option does not specify what events will be synthesized e.g. the p
1130 option must be used also to show power events 1053 option must be used also to show power events.
1131 1054
1132 Repeating the q option (double-q i.e. qq) res 1055 Repeating the q option (double-q i.e. qq) results in even faster decoding and even
1133 less detail. The decoder decodes only extend 1056 less detail. The decoder decodes only extended PSB (PSB+) packets, getting the
1134 instruction pointer if there is a FUP packet 1057 instruction pointer if there is a FUP packet within PSB+ (i.e. between PSB and
1135 PSBEND). Note PSB packets occur regularly in 1058 PSBEND). Note PSB packets occur regularly in the trace based on the psb_period
1136 config term (refer config terms section). Th 1059 config term (refer config terms section). There will be a FUP packet if the
1137 PSB+ occurs while control flow is being trace 1060 PSB+ occurs while control flow is being traced.
1138 1061
1139 What will *not* be decoded with the qq option 1062 What will *not* be decoded with the qq option:
1140 1063
1141 - everything except instruction point 1064 - everything except instruction pointer associated with PSB packets
1142 1065
1143 What *will* be decoded with the qq option: 1066 What *will* be decoded with the qq option:
1144 1067
1145 - instruction pointer associated with 1068 - instruction pointer associated with PSB packets
1146 1069
1147 The Z option is equivalent to having recorded 1070 The Z option is equivalent to having recorded a trace without TSC
1148 (i.e. config term tsc=0). It can be useful to 1071 (i.e. config term tsc=0). It can be useful to avoid timestamp issues when
1149 decoding a trace of a virtual machine. 1072 decoding a trace of a virtual machine.
1150 1073
1151 1074
1152 dlfilter-show-cycles.so <<
1153 ~~~~~~~~~~~~~~~~~~~~~~~ <<
1154 <<
1155 Cycles can be displayed using dlfilter-show-c <<
1156 option can be useful to provide higher granul <<
1157 <<
1158 perf script --itrace=A --call-trace - <<
1159 <<
1160 To see a list of dlfilters: <<
1161 <<
1162 perf script -v --list-dlfilters <<
1163 <<
1164 See also linkperf:perf-dlfilters[1] <<
1165 <<
1166 <<
1167 dump option 1075 dump option
1168 ~~~~~~~~~~~ 1076 ~~~~~~~~~~~
1169 1077
1170 perf script has an option (-D) to "dump" the 1078 perf script has an option (-D) to "dump" the events i.e. display the binary
1171 data. 1079 data.
1172 1080
1173 When -D is used, Intel PT packets are display 1081 When -D is used, Intel PT packets are displayed. The packet decoder does not
1174 pay attention to PSB packets, but just decode 1082 pay attention to PSB packets, but just decodes the bytes - so the packets seen
1175 by the actual decoder may not be identical in 1083 by the actual decoder may not be identical in places where the data is corrupt.
1176 One example of that would be when the buffer- 1084 One example of that would be when the buffer-switching interrupt has been too
1177 slow, and the buffer has been filled complete 1085 slow, and the buffer has been filled completely. In that case, the last packet
1178 in the buffer might be truncated and immediat 1086 in the buffer might be truncated and immediately followed by a PSB as the trace
1179 continues in the next buffer. 1087 continues in the next buffer.
1180 1088
1181 To disable the display of Intel PT packets, c 1089 To disable the display of Intel PT packets, combine the -D option with
1182 --no-itrace. 1090 --no-itrace.
1183 1091
1184 1092
1185 perf report 1093 perf report
1186 ----------- 1094 -----------
1187 1095
1188 By default, perf report will decode trace dat 1096 By default, perf report will decode trace data found in the perf.data file.
1189 This can be further controlled by new option 1097 This can be further controlled by new option --itrace exactly the same as
1190 perf script, with the exception that the defa 1098 perf script, with the exception that the default is --itrace=igxe.
1191 1099
1192 1100
1193 perf inject 1101 perf inject
1194 ----------- 1102 -----------
1195 1103
1196 perf inject also accepts the --itrace option 1104 perf inject also accepts the --itrace option in which case tracing data is
1197 removed and replaced with the synthesized eve 1105 removed and replaced with the synthesized events. e.g.
1198 1106
1199 perf inject --itrace -i perf.data -o 1107 perf inject --itrace -i perf.data -o perf.data.new
1200 1108
1201 Below is an example of using Intel PT with au 1109 Below is an example of using Intel PT with autofdo. It requires autofdo
1202 (https://github.com/google/autofdo) and gcc v 1110 (https://github.com/google/autofdo) and gcc version 5. The bubble
1203 sort example is from the AutoFDO tutorial (ht 1111 sort example is from the AutoFDO tutorial (https://gcc.gnu.org/wiki/AutoFDO/Tutorial)
1204 amended to take the number of elements as a p 1112 amended to take the number of elements as a parameter.
1205 1113
1206 $ gcc-5 -O3 sort.c -o sort_optimized 1114 $ gcc-5 -O3 sort.c -o sort_optimized
1207 $ ./sort_optimized 30000 1115 $ ./sort_optimized 30000
1208 Bubble sorting array of 30000 element 1116 Bubble sorting array of 30000 elements
1209 2254 ms 1117 2254 ms
1210 1118
1211 $ cat ~/.perfconfig 1119 $ cat ~/.perfconfig
1212 [intel-pt] 1120 [intel-pt]
1213 mispred-all = on 1121 mispred-all = on
1214 1122
1215 $ perf record -e intel_pt//u ./sort 3 1123 $ perf record -e intel_pt//u ./sort 3000
1216 Bubble sorting array of 3000 elements 1124 Bubble sorting array of 3000 elements
1217 58 ms 1125 58 ms
1218 [ perf record: Woken up 2 times to wr 1126 [ perf record: Woken up 2 times to write data ]
1219 [ perf record: Captured and wrote 3.9 1127 [ perf record: Captured and wrote 3.939 MB perf.data ]
1220 $ perf inject -i perf.data -o inj --i 1128 $ perf inject -i perf.data -o inj --itrace=i100usle --strip
1221 $ ./create_gcov --binary=./sort --pro 1129 $ ./create_gcov --binary=./sort --profile=inj --gcov=sort.gcov -gcov_version=1
1222 $ gcc-5 -O3 -fauto-profile=sort.gcov 1130 $ gcc-5 -O3 -fauto-profile=sort.gcov sort.c -o sort_autofdo
1223 $ ./sort_autofdo 30000 1131 $ ./sort_autofdo 30000
1224 Bubble sorting array of 30000 element 1132 Bubble sorting array of 30000 elements
1225 2155 ms 1133 2155 ms
1226 1134
1227 Note there is currently no advantage to using 1135 Note there is currently no advantage to using Intel PT instead of LBR, but
1228 that may change in the future if greater use 1136 that may change in the future if greater use is made of the data.
1229 1137
1230 1138
1231 PEBS via Intel PT 1139 PEBS via Intel PT
1232 ----------------- 1140 -----------------
1233 1141
1234 Some hardware has the feature to redirect PEB 1142 Some hardware has the feature to redirect PEBS records to the Intel PT trace.
1235 Recording is selected by using the aux-output 1143 Recording is selected by using the aux-output config term e.g.
1236 1144
1237 perf record -c 10000 -e '{intel_pt/br 1145 perf record -c 10000 -e '{intel_pt/branch=0/,cycles/aux-output/ppp}' uname
1238 1146
1239 Originally, software only supported redirecti !! 1147 Note that currently, software only supports redirecting at most one PEBS event.
1240 was not able to differentiate one event from <<
1241 kernels and perf tools add support for the PE <<
1242 To check for the presence of that event in a <<
1243 <<
1244 perf script -D --no-itrace | grep PER <<
1245 1148
1246 To display PEBS events from the Intel PT trac 1149 To display PEBS events from the Intel PT trace, use the itrace 'o' option e.g.
1247 1150
1248 perf script --itrace=oe 1151 perf script --itrace=oe
1249 1152
1250 XED 1153 XED
1251 --- 1154 ---
1252 1155
1253 include::build-xed.txt[] 1156 include::build-xed.txt[]
1254 1157
1255 1158
1256 Tracing Virtual Machines (kernel only) !! 1159 Tracing Virtual Machines
1257 -------------------------------------- !! 1160 ------------------------
1258 1161
1259 Currently, kernel tracing is supported with e !! 1162 Currently, only kernel tracing is supported and only with either "timeless" decoding
1260 (i.e. no TSC timestamps) or VM Time Correlati 1163 (i.e. no TSC timestamps) or VM Time Correlation. VM Time Correlation is an extra step
1261 using 'perf inject' and requires unchanging V 1164 using 'perf inject' and requires unchanging VMX TSC Offset and no VMX TSC Scaling.
1262 1165
1263 Other limitations and caveats 1166 Other limitations and caveats
1264 1167
1265 VMX controls may suppress packets needed for 1168 VMX controls may suppress packets needed for decoding resulting in decoding errors
1266 VMX controls may block the perf NMI to the h 1169 VMX controls may block the perf NMI to the host potentially resulting in lost trace data
1267 Guest kernel self-modifying code (e.g. jump 1170 Guest kernel self-modifying code (e.g. jump labels or JIT-compiled eBPF) will result in decoding errors
1268 Guest thread information is unknown 1171 Guest thread information is unknown
1269 Guest VCPU is unknown but may be able to be 1172 Guest VCPU is unknown but may be able to be inferred from the host thread
1270 Callchains are not supported 1173 Callchains are not supported
1271 1174
1272 Example using "timeless" decoding 1175 Example using "timeless" decoding
1273 1176
1274 Start VM 1177 Start VM
1275 1178
1276 $ sudo virsh start kubuntu20.04 1179 $ sudo virsh start kubuntu20.04
1277 Domain kubuntu20.04 started 1180 Domain kubuntu20.04 started
1278 1181
1279 Mount the guest file system. Note sshfs need 1182 Mount the guest file system. Note sshfs needs -o direct_io to enable reading of proc files. root access is needed to read /proc/kcore.
1280 1183
1281 $ mkdir vm0 1184 $ mkdir vm0
1282 $ sshfs -o direct_io root@vm0:/ vm0 1185 $ sshfs -o direct_io root@vm0:/ vm0
1283 1186
1284 Copy the guest /proc/kallsyms, /proc/modules 1187 Copy the guest /proc/kallsyms, /proc/modules and /proc/kcore
1285 1188
1286 $ perf buildid-cache -v --kcore vm0/proc/kco 1189 $ perf buildid-cache -v --kcore vm0/proc/kcore
1287 kcore added to build-id cache directory /hom 1190 kcore added to build-id cache directory /home/user/.debug/[kernel.kcore]/9600f316a53a0f54278885e8d9710538ec5f6a08/2021021807494306
1288 $ KALLSYMS=/home/user/.debug/[kernel.kcore]/ 1191 $ KALLSYMS=/home/user/.debug/[kernel.kcore]/9600f316a53a0f54278885e8d9710538ec5f6a08/2021021807494306/kallsyms
1289 1192
1290 Find the VM process 1193 Find the VM process
1291 1194
1292 $ ps -eLl | grep 'KVM\|PID' 1195 $ ps -eLl | grep 'KVM\|PID'
1293 F S UID PID PPID LWP C PRI NI 1196 F S UID PID PPID LWP C PRI NI ADDR SZ WCHAN TTY TIME CMD
1294 3 S 64055 1430 1 1440 1 80 0 1197 3 S 64055 1430 1 1440 1 80 0 - 1921718 - ? 00:02:47 CPU 0/KVM
1295 3 S 64055 1430 1 1441 1 80 0 1198 3 S 64055 1430 1 1441 1 80 0 - 1921718 - ? 00:02:41 CPU 1/KVM
1296 3 S 64055 1430 1 1442 1 80 0 1199 3 S 64055 1430 1 1442 1 80 0 - 1921718 - ? 00:02:38 CPU 2/KVM
1297 3 S 64055 1430 1 1443 2 80 0 1200 3 S 64055 1430 1 1443 2 80 0 - 1921718 - ? 00:03:18 CPU 3/KVM
1298 1201
1299 Start an open-ended perf record, tracing the 1202 Start an open-ended perf record, tracing the VM process, do something on the VM, and then ctrl-C to stop.
1300 TSC is not supported and tsc=0 must be specif 1203 TSC is not supported and tsc=0 must be specified. That means mtc is useless, so add mtc=0.
1301 However, IPC can still be determined, hence c 1204 However, IPC can still be determined, hence cyc=1 can be added.
1302 Only kernel decoding is supported, so 'k' mus 1205 Only kernel decoding is supported, so 'k' must be specified.
1303 Intel PT traces both the host and the guest s 1206 Intel PT traces both the host and the guest so --guest and --host need to be specified.
1304 Without timestamps, --per-thread must be spec 1207 Without timestamps, --per-thread must be specified to distinguish threads.
1305 1208
1306 $ sudo perf kvm --guest --host --guestkallsy 1209 $ sudo perf kvm --guest --host --guestkallsyms $KALLSYMS record --kcore -e intel_pt/tsc=0,mtc=0,cyc=1/k -p 1430 --per-thread
1307 ^C 1210 ^C
1308 [ perf record: Woken up 1 times to write dat 1211 [ perf record: Woken up 1 times to write data ]
1309 [ perf record: Captured and wrote 5.829 MB ] 1212 [ perf record: Captured and wrote 5.829 MB ]
1310 1213
1311 perf script can be used to provide an instruc 1214 perf script can be used to provide an instruction trace
1312 1215
1313 $ perf script --guestkallsyms $KALLSYMS --in !! 1216 $ perf script --guestkallsyms $KALLSYMS --insn-trace --xed -F+ipc | grep -C10 vmresume | head -21
1314 CPU 0/KVM 1440 ffffffff82133cdd __vm 1217 CPU 0/KVM 1440 ffffffff82133cdd __vmx_vcpu_run+0x3d ([kernel.kallsyms]) movq 0x48(%rax), %r9
1315 CPU 0/KVM 1440 ffffffff82133ce1 __vm 1218 CPU 0/KVM 1440 ffffffff82133ce1 __vmx_vcpu_run+0x41 ([kernel.kallsyms]) movq 0x50(%rax), %r10
1316 CPU 0/KVM 1440 ffffffff82133ce5 __vm 1219 CPU 0/KVM 1440 ffffffff82133ce5 __vmx_vcpu_run+0x45 ([kernel.kallsyms]) movq 0x58(%rax), %r11
1317 CPU 0/KVM 1440 ffffffff82133ce9 __vm 1220 CPU 0/KVM 1440 ffffffff82133ce9 __vmx_vcpu_run+0x49 ([kernel.kallsyms]) movq 0x60(%rax), %r12
1318 CPU 0/KVM 1440 ffffffff82133ced __vm 1221 CPU 0/KVM 1440 ffffffff82133ced __vmx_vcpu_run+0x4d ([kernel.kallsyms]) movq 0x68(%rax), %r13
1319 CPU 0/KVM 1440 ffffffff82133cf1 __vm 1222 CPU 0/KVM 1440 ffffffff82133cf1 __vmx_vcpu_run+0x51 ([kernel.kallsyms]) movq 0x70(%rax), %r14
1320 CPU 0/KVM 1440 ffffffff82133cf5 __vm 1223 CPU 0/KVM 1440 ffffffff82133cf5 __vmx_vcpu_run+0x55 ([kernel.kallsyms]) movq 0x78(%rax), %r15
1321 CPU 0/KVM 1440 ffffffff82133cf9 __vm 1224 CPU 0/KVM 1440 ffffffff82133cf9 __vmx_vcpu_run+0x59 ([kernel.kallsyms]) movq (%rax), %rax
1322 CPU 0/KVM 1440 ffffffff82133cfc __vm 1225 CPU 0/KVM 1440 ffffffff82133cfc __vmx_vcpu_run+0x5c ([kernel.kallsyms]) callq 0xffffffff82133c40
1323 CPU 0/KVM 1440 ffffffff82133c40 vmx_ 1226 CPU 0/KVM 1440 ffffffff82133c40 vmx_vmenter+0x0 ([kernel.kallsyms]) jz 0xffffffff82133c46
1324 CPU 0/KVM 1440 ffffffff82133c42 vmx_ 1227 CPU 0/KVM 1440 ffffffff82133c42 vmx_vmenter+0x2 ([kernel.kallsyms]) vmresume IPC: 0.11 (50/445)
1325 :1440 1440 ffffffffbb678b06 nati 1228 :1440 1440 ffffffffbb678b06 native_write_msr+0x6 ([guest.kernel.kallsyms]) nopl %eax, (%rax,%rax,1)
1326 :1440 1440 ffffffffbb678b0b nati 1229 :1440 1440 ffffffffbb678b0b native_write_msr+0xb ([guest.kernel.kallsyms]) retq IPC: 0.04 (2/41)
1327 :1440 1440 ffffffffbb666646 lapi 1230 :1440 1440 ffffffffbb666646 lapic_next_deadline+0x26 ([guest.kernel.kallsyms]) data16 nop
1328 :1440 1440 ffffffffbb666648 lapi 1231 :1440 1440 ffffffffbb666648 lapic_next_deadline+0x28 ([guest.kernel.kallsyms]) xor %eax, %eax
1329 :1440 1440 ffffffffbb66664a lapi 1232 :1440 1440 ffffffffbb66664a lapic_next_deadline+0x2a ([guest.kernel.kallsyms]) popq %rbp
1330 :1440 1440 ffffffffbb66664b lapi 1233 :1440 1440 ffffffffbb66664b lapic_next_deadline+0x2b ([guest.kernel.kallsyms]) retq IPC: 0.16 (4/25)
1331 :1440 1440 ffffffffbb74607f cloc 1234 :1440 1440 ffffffffbb74607f clockevents_program_event+0x8f ([guest.kernel.kallsyms]) test %eax, %eax
1332 :1440 1440 ffffffffbb746081 cloc 1235 :1440 1440 ffffffffbb746081 clockevents_program_event+0x91 ([guest.kernel.kallsyms]) jz 0xffffffffbb74603c IPC: 0.06 (2/30)
1333 :1440 1440 ffffffffbb74603c cloc 1236 :1440 1440 ffffffffbb74603c clockevents_program_event+0x4c ([guest.kernel.kallsyms]) popq %rbx
1334 :1440 1440 ffffffffbb74603d cloc 1237 :1440 1440 ffffffffbb74603d clockevents_program_event+0x4d ([guest.kernel.kallsyms]) popq %r12
1335 1238
1336 Example using VM Time Correlation 1239 Example using VM Time Correlation
1337 1240
1338 Start VM 1241 Start VM
1339 1242
1340 $ sudo virsh start kubuntu20.04 1243 $ sudo virsh start kubuntu20.04
1341 Domain kubuntu20.04 started 1244 Domain kubuntu20.04 started
1342 1245
1343 Mount the guest file system. Note sshfs need 1246 Mount the guest file system. Note sshfs needs -o direct_io to enable reading of proc files. root access is needed to read /proc/kcore.
1344 1247
1345 $ mkdir -p vm0 1248 $ mkdir -p vm0
1346 $ sshfs -o direct_io root@vm0:/ vm0 1249 $ sshfs -o direct_io root@vm0:/ vm0
1347 1250
1348 Copy the guest /proc/kallsyms, /proc/modules 1251 Copy the guest /proc/kallsyms, /proc/modules and /proc/kcore
1349 1252
1350 $ perf buildid-cache -v --kcore vm0/proc/kco 1253 $ perf buildid-cache -v --kcore vm0/proc/kcore
1351 same kcore found in /home/user/.debug/[kerne 1254 same kcore found in /home/user/.debug/[kernel.kcore]/cc9c55a98c5e4ec0aeda69302554aabed5cd6491/2021021312450777
1352 $ KALLSYMS=/home/user/.debug/\[kernel.kcore\ 1255 $ KALLSYMS=/home/user/.debug/\[kernel.kcore\]/cc9c55a98c5e4ec0aeda69302554aabed5cd6491/2021021312450777/kallsyms
1353 1256
1354 Find the VM process 1257 Find the VM process
1355 1258
1356 $ ps -eLl | grep 'KVM\|PID' 1259 $ ps -eLl | grep 'KVM\|PID'
1357 F S UID PID PPID LWP C PRI NI 1260 F S UID PID PPID LWP C PRI NI ADDR SZ WCHAN TTY TIME CMD
1358 3 S 64055 16998 1 17005 13 80 0 1261 3 S 64055 16998 1 17005 13 80 0 - 1818189 - ? 00:00:16 CPU 0/KVM
1359 3 S 64055 16998 1 17006 4 80 0 1262 3 S 64055 16998 1 17006 4 80 0 - 1818189 - ? 00:00:05 CPU 1/KVM
1360 3 S 64055 16998 1 17007 3 80 0 1263 3 S 64055 16998 1 17007 3 80 0 - 1818189 - ? 00:00:04 CPU 2/KVM
1361 3 S 64055 16998 1 17008 4 80 0 1264 3 S 64055 16998 1 17008 4 80 0 - 1818189 - ? 00:00:05 CPU 3/KVM
1362 1265
1363 Start an open-ended perf record, tracing the 1266 Start an open-ended perf record, tracing the VM process, do something on the VM, and then ctrl-C to stop.
1364 IPC can be determined, hence cyc=1 can be add 1267 IPC can be determined, hence cyc=1 can be added.
1365 Only kernel decoding is supported, so 'k' mus 1268 Only kernel decoding is supported, so 'k' must be specified.
1366 Intel PT traces both the host and the guest s 1269 Intel PT traces both the host and the guest so --guest and --host need to be specified.
1367 1270
1368 $ sudo perf kvm --guest --host --guestkallsy 1271 $ sudo perf kvm --guest --host --guestkallsyms $KALLSYMS record --kcore -e intel_pt/cyc=1/k -p 16998
1369 ^C[ perf record: Woken up 1 times to write d 1272 ^C[ perf record: Woken up 1 times to write data ]
1370 [ perf record: Captured and wrote 9.041 MB p 1273 [ perf record: Captured and wrote 9.041 MB perf.data.kvm ]
1371 1274
1372 Now 'perf inject' can be used to determine th 1275 Now 'perf inject' can be used to determine the VMX TCS Offset. Note, Intel PT TSC packets are
1373 only 7-bytes, so the TSC Offset might differ 1276 only 7-bytes, so the TSC Offset might differ from the actual value in the 8th byte. That will
1374 have no effect i.e. the resulting timestamps 1277 have no effect i.e. the resulting timestamps will be correct anyway.
1375 1278
1376 $ perf inject -i perf.data.kvm --vm-time-cor 1279 $ perf inject -i perf.data.kvm --vm-time-correlation=dry-run
1377 ERROR: Unknown TSC Offset for VMCS 0x1bff6a 1280 ERROR: Unknown TSC Offset for VMCS 0x1bff6a
1378 VMCS: 0x1bff6a TSC Offset 0xffffe42722c64c4 1281 VMCS: 0x1bff6a TSC Offset 0xffffe42722c64c41
1379 ERROR: Unknown TSC Offset for VMCS 0x1cbc08 1282 ERROR: Unknown TSC Offset for VMCS 0x1cbc08
1380 VMCS: 0x1cbc08 TSC Offset 0xffffe42722c64c4 1283 VMCS: 0x1cbc08 TSC Offset 0xffffe42722c64c41
1381 ERROR: Unknown TSC Offset for VMCS 0x1c3ce8 1284 ERROR: Unknown TSC Offset for VMCS 0x1c3ce8
1382 VMCS: 0x1c3ce8 TSC Offset 0xffffe42722c64c4 1285 VMCS: 0x1c3ce8 TSC Offset 0xffffe42722c64c41
1383 ERROR: Unknown TSC Offset for VMCS 0x1cbce9 1286 ERROR: Unknown TSC Offset for VMCS 0x1cbce9
1384 VMCS: 0x1cbce9 TSC Offset 0xffffe42722c64c4 1287 VMCS: 0x1cbce9 TSC Offset 0xffffe42722c64c41
1385 1288
1386 Each virtual CPU has a different Virtual Mach 1289 Each virtual CPU has a different Virtual Machine Control Structure (VMCS)
1387 shown above with the calculated TSC Offset. F 1290 shown above with the calculated TSC Offset. For an unchanging TSC Offset
1388 they should all be the same for the same virt 1291 they should all be the same for the same virtual machine.
1389 1292
1390 Now that the TSC Offset is known, it can be p 1293 Now that the TSC Offset is known, it can be provided to 'perf inject'
1391 1294
1392 $ perf inject -i perf.data.kvm --vm-time-cor 1295 $ perf inject -i perf.data.kvm --vm-time-correlation="dry-run 0xffffe42722c64c41"
1393 1296
1394 Note the options for 'perf inject' --vm-time- 1297 Note the options for 'perf inject' --vm-time-correlation are:
1395 1298
1396 [ dry-run ] [ <TSC Offset> [ : <VMCS> [ , <V 1299 [ dry-run ] [ <TSC Offset> [ : <VMCS> [ , <VMCS> ]... ] ]...
1397 1300
1398 So it is possible to specify different TSC Of 1301 So it is possible to specify different TSC Offsets for different VMCS.
1399 The option "dry-run" will cause the file to b 1302 The option "dry-run" will cause the file to be processed but without updating it.
1400 Note it is also possible to get a intel_pt.lo 1303 Note it is also possible to get a intel_pt.log file by adding option --itrace=d
1401 1304
1402 There were no errors so, do it for real 1305 There were no errors so, do it for real
1403 1306
1404 $ perf inject -i perf.data.kvm --vm-time-cor 1307 $ perf inject -i perf.data.kvm --vm-time-correlation=0xffffe42722c64c41 --force
1405 1308
1406 'perf script' can be used to see if there are 1309 'perf script' can be used to see if there are any decoder errors
1407 1310
1408 $ perf script -i perf.data.kvm --guestkallsy 1311 $ perf script -i perf.data.kvm --guestkallsyms $KALLSYMS --itrace=e-o
1409 1312
1410 There were none. 1313 There were none.
1411 1314
1412 'perf script' can be used to provide an instr 1315 'perf script' can be used to provide an instruction trace showing timestamps
1413 1316
1414 $ perf script -i perf.data.kvm --guestkallsy !! 1317 $ perf script -i perf.data.kvm --guestkallsyms $KALLSYMS --insn-trace --xed -F+ipc | grep -C10 vmresume | head -21
1415 CPU 1/KVM 17006 [001] 11500.262865593: 1318 CPU 1/KVM 17006 [001] 11500.262865593: ffffffff82133cdd __vmx_vcpu_run+0x3d ([kernel.kallsyms]) movq 0x48(%rax), %r9
1416 CPU 1/KVM 17006 [001] 11500.262865593: 1319 CPU 1/KVM 17006 [001] 11500.262865593: ffffffff82133ce1 __vmx_vcpu_run+0x41 ([kernel.kallsyms]) movq 0x50(%rax), %r10
1417 CPU 1/KVM 17006 [001] 11500.262865593: 1320 CPU 1/KVM 17006 [001] 11500.262865593: ffffffff82133ce5 __vmx_vcpu_run+0x45 ([kernel.kallsyms]) movq 0x58(%rax), %r11
1418 CPU 1/KVM 17006 [001] 11500.262865593: 1321 CPU 1/KVM 17006 [001] 11500.262865593: ffffffff82133ce9 __vmx_vcpu_run+0x49 ([kernel.kallsyms]) movq 0x60(%rax), %r12
1419 CPU 1/KVM 17006 [001] 11500.262865593: 1322 CPU 1/KVM 17006 [001] 11500.262865593: ffffffff82133ced __vmx_vcpu_run+0x4d ([kernel.kallsyms]) movq 0x68(%rax), %r13
1420 CPU 1/KVM 17006 [001] 11500.262865593: 1323 CPU 1/KVM 17006 [001] 11500.262865593: ffffffff82133cf1 __vmx_vcpu_run+0x51 ([kernel.kallsyms]) movq 0x70(%rax), %r14
1421 CPU 1/KVM 17006 [001] 11500.262865593: 1324 CPU 1/KVM 17006 [001] 11500.262865593: ffffffff82133cf5 __vmx_vcpu_run+0x55 ([kernel.kallsyms]) movq 0x78(%rax), %r15
1422 CPU 1/KVM 17006 [001] 11500.262865593: 1325 CPU 1/KVM 17006 [001] 11500.262865593: ffffffff82133cf9 __vmx_vcpu_run+0x59 ([kernel.kallsyms]) movq (%rax), %rax
1423 CPU 1/KVM 17006 [001] 11500.262865593: 1326 CPU 1/KVM 17006 [001] 11500.262865593: ffffffff82133cfc __vmx_vcpu_run+0x5c ([kernel.kallsyms]) callq 0xffffffff82133c40
1424 CPU 1/KVM 17006 [001] 11500.262865593: 1327 CPU 1/KVM 17006 [001] 11500.262865593: ffffffff82133c40 vmx_vmenter+0x0 ([kernel.kallsyms]) jz 0xffffffff82133c46
1425 CPU 1/KVM 17006 [001] 11500.262866075: 1328 CPU 1/KVM 17006 [001] 11500.262866075: ffffffff82133c42 vmx_vmenter+0x2 ([kernel.kallsyms]) vmresume IPC: 0.05 (40/769)
1426 :17006 17006 [001] 11500.262869216: 1329 :17006 17006 [001] 11500.262869216: ffffffff82200cb0 asm_sysvec_apic_timer_interrupt+0x0 ([guest.kernel.kallsyms]) clac
1427 :17006 17006 [001] 11500.262869216: 1330 :17006 17006 [001] 11500.262869216: ffffffff82200cb3 asm_sysvec_apic_timer_interrupt+0x3 ([guest.kernel.kallsyms]) pushq $0xffffffffffffffff
1428 :17006 17006 [001] 11500.262869216: 1331 :17006 17006 [001] 11500.262869216: ffffffff82200cb5 asm_sysvec_apic_timer_interrupt+0x5 ([guest.kernel.kallsyms]) callq 0xffffffff82201160
1429 :17006 17006 [001] 11500.262869216: 1332 :17006 17006 [001] 11500.262869216: ffffffff82201160 error_entry+0x0 ([guest.kernel.kallsyms]) cld
1430 :17006 17006 [001] 11500.262869216: 1333 :17006 17006 [001] 11500.262869216: ffffffff82201161 error_entry+0x1 ([guest.kernel.kallsyms]) pushq %rsi
1431 :17006 17006 [001] 11500.262869216: 1334 :17006 17006 [001] 11500.262869216: ffffffff82201162 error_entry+0x2 ([guest.kernel.kallsyms]) movq 0x8(%rsp), %rsi
1432 :17006 17006 [001] 11500.262869216: 1335 :17006 17006 [001] 11500.262869216: ffffffff82201167 error_entry+0x7 ([guest.kernel.kallsyms]) movq %rdi, 0x8(%rsp)
1433 :17006 17006 [001] 11500.262869216: 1336 :17006 17006 [001] 11500.262869216: ffffffff8220116c error_entry+0xc ([guest.kernel.kallsyms]) pushq %rdx
1434 :17006 17006 [001] 11500.262869216: 1337 :17006 17006 [001] 11500.262869216: ffffffff8220116d error_entry+0xd ([guest.kernel.kallsyms]) pushq %rcx
1435 :17006 17006 [001] 11500.262869216: 1338 :17006 17006 [001] 11500.262869216: ffffffff8220116e error_entry+0xe ([guest.kernel.kallsyms]) pushq %rax
1436 1339
1437 <<
1438 Tracing Virtual Machines (including user spac <<
1439 --------------------------------------------- <<
1440 <<
1441 It is possible to use perf record to record s <<
1442 Sideband events from the guest perf.data file <<
1443 <<
1444 Here is an example of the steps needed: <<
1445 <<
1446 On the guest machine: <<
1447 <<
1448 Check that no-kvmclock kernel command line op <<
1449 <<
1450 Note, this is essential to enable time correl <<
1451 <<
1452 $ cat /proc/cmdline <<
1453 BOOT_IMAGE=/boot/vmlinuz-5.10.0-16-amd64 roo <<
1454 <<
1455 There is no BPF support at present so, if pos <<
1456 <<
1457 $ echo 0 | sudo tee /proc/sys/net/core/bpf_j <<
1458 0 <<
1459 <<
1460 Start perf record to collect sideband events: <<
1461 <<
1462 $ sudo perf record -o guest-sideband-testing <<
1463 <<
1464 On the host machine: <<
1465 <<
1466 Start perf record to collect Intel PT trace: <<
1467 <<
1468 Note, the host trace will get very big, very <<
1469 <<
1470 $ sudo perf record -o guest-sideband-testing <<
1471 <<
1472 On the guest machine: <<
1473 <<
1474 Run a small test case, just 'uname' in this e <<
1475 <<
1476 $ uname <<
1477 Linux <<
1478 <<
1479 On the host machine: <<
1480 <<
1481 Stop the Intel PT trace: <<
1482 <<
1483 ^C <<
1484 [ perf record: Woken up 1 times to write dat <<
1485 [ perf record: Captured and wrote 76.122 MB <<
1486 <<
1487 On the guest machine: <<
1488 <<
1489 Stop the Intel PT trace: <<
1490 <<
1491 ^C <<
1492 [ perf record: Woken up 1 times to write dat <<
1493 [ perf record: Captured and wrote 1.247 MB g <<
1494 <<
1495 And then copy guest-sideband-testing-guest-pe <<
1496 <<
1497 On the host machine: <<
1498 <<
1499 With the 2 perf.data recordings, and with the <<
1500 <<
1501 Identify the TSC Offset: <<
1502 <<
1503 $ perf inject -i guest-sideband-testing-host <<
1504 VMCS: 0x103fc6 TSC Offset 0xfffffa6ae070cb2 <<
1505 VMCS: 0x103ff2 TSC Offset 0xfffffa6ae070cb2 <<
1506 VMCS: 0x10fdaa TSC Offset 0xfffffa6ae070cb2 <<
1507 VMCS: 0x24d57c TSC Offset 0xfffffa6ae070cb2 <<
1508 <<
1509 Correct Intel PT TSC timestamps for the guest <<
1510 <<
1511 $ perf inject -i guest-sideband-testing-host <<
1512 <<
1513 Identify the guest machine PID: <<
1514 <<
1515 $ perf script -i guest-sideband-testing-host <<
1516 CPU 0/KVM 0 [000] 0.000000: PE <<
1517 CPU 1/KVM 0 [000] 0.000000: PE <<
1518 CPU 2/KVM 0 [000] 0.000000: PE <<
1519 CPU 3/KVM 0 [000] 0.000000: PE <<
1520 <<
1521 Note, the QEMU option -name debug-threads=on <<
1522 can be used to determine which thread is runn <<
1523 <<
1524 Create a guestmount, assuming the guest machi <<
1525 <<
1526 $ mkdir -p ~/guestmount/13376 <<
1527 $ sshfs -o direct_io vm_to_test:/ ~/guestmou <<
1528 <<
1529 Inject the guest perf.data file into the host <<
1530 <<
1531 Note, due to the guestmount option, guest obj <<
1532 If needed, VDSO can be copied manually in a f <<
1533 <<
1534 $ perf inject -i guest-sideband-testing-host <<
1535 <<
1536 Show an excerpt from the result. In this cas <<
1537 <<
1538 Notes: <<
1539 <<
1540 - the CPU displayed, [002] in this ca <<
1541 - events happening in the virtual mac <<
1542 - only calls and errors are displayed <<
1543 - branches entering and exiting the v <<
1544 <<
1545 $ perf script -i inj --itrace=ce -F+machine_ <<
1546 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1547 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1548 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1549 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1550 VM:13376 VCPU:003 uname 3404/340 <<
1551 VM:13376 VCPU:003 uname 3404/340 <<
1552 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1553 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1554 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1555 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1556 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1557 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1558 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1559 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1560 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1561 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1562 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1563 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1564 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1565 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1566 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1567 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1568 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1569 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1570 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1571 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1572 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1573 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1574 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1575 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1576 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1577 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1578 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1579 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1580 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1581 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1582 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1583 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1584 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1585 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1586 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1587 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1588 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1589 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1590 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1591 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1592 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1593 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1594 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1595 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1596 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1597 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1598 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1599 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1600 CPU 3/KVM 13376/13384 [002] 7919.4088 <<
1601 VM:13376 VCPU:003 uname 3404/340 <<
1602 VM:13376 VCPU:003 uname 3404/340 <<
1603 VM:13376 VCPU:003 uname 3404/340 <<
1604 VM:13376 VCPU:003 uname 3404/340 <<
1605 VM:13376 VCPU:003 uname 3404/340 <<
1606 VM:13376 VCPU:003 uname 3404/340 <<
1607 VM:13376 VCPU:003 uname 3404/340 <<
1608 VM:13376 VCPU:003 uname 3404/340 <<
1609 <<
1610 <<
1611 Tracing Virtual Machines - Guest Code <<
1612 ------------------------------------- <<
1613 <<
1614 A common case for KVM test programs is that t <<
1615 hypervisor, creating, running and destroying <<
1616 providing the guest object code from its own <<
1617 the VM is not running an OS, but only the fun <<
1618 hypervisor test program, and conveniently, lo <<
1619 addresses. To support that, option "--guest-c <<
1620 and perf kvm report. <<
1621 <<
1622 Here is an example tracing a test program fro <<
1623 <<
1624 # perf record --kcore -e intel_pt/cyc/ -- to <<
1625 [ perf record: Woken up 1 times to write dat <<
1626 [ perf record: Captured and wrote 0.280 MB p <<
1627 # perf script --guest-code --itrace=bep --ns <<
1628 [SNIP] <<
1629 tsc_msrs_test 18436 [007] 10897.962087733: <<
1630 tsc_msrs_test 18436 [007] 10897.962087733: <<
1631 tsc_msrs_test 18436 [007] 10897.962087733: <<
1632 tsc_msrs_test 18436 [007] 10897.962087836: <<
1633 [guest/18436] 18436 [007] 10897.962087836: <<
1634 [guest/18436] 18436 [007] 10897.962087836: <<
1635 [guest/18436] 18436 [007] 10897.962088248: <<
1636 tsc_msrs_test 18436 [007] 10897.962088248: <<
1637 tsc_msrs_test 18436 [007] 10897.962088248: <<
1638 tsc_msrs_test 18436 [007] 10897.962088256: <<
1639 tsc_msrs_test 18436 [007] 10897.962088270: <<
1640 [SNIP] <<
1641 tsc_msrs_test 18436 [007] 10897.962089321: <<
1642 tsc_msrs_test 18436 [007] 10897.962089321: <<
1643 tsc_msrs_test 18436 [007] 10897.962089321: <<
1644 tsc_msrs_test 18436 [007] 10897.962089424: <<
1645 [guest/18436] 18436 [007] 10897.962089424: <<
1646 [guest/18436] 18436 [007] 10897.962089701: <<
1647 [guest/18436] 18436 [007] 10897.962089701: <<
1648 [guest/18436] 18436 [007] 10897.962089701: <<
1649 [guest/18436] 18436 [007] 10897.962089701: <<
1650 [guest/18436] 18436 [007] 10897.962089878: <<
1651 tsc_msrs_test 18436 [007] 10897.962089878: <<
1652 tsc_msrs_test 18436 [007] 10897.962089878: <<
1653 tsc_msrs_test 18436 [007] 10897.962089887: <<
1654 tsc_msrs_test 18436 [007] 10897.962089901: <<
1655 [SNIP] <<
1656 <<
1657 # perf kvm --guest-code --guest --host repor <<
1658 <<
1659 # To display the perf.data header info, plea <<
1660 # <<
1661 # <<
1662 # Total Lost Samples: 0 <<
1663 # <<
1664 # Samples: 12 of event 'instructions' <<
1665 # Event count (approx.): 2274583 <<
1666 # <<
1667 # Children Self Command Shared <<
1668 # ........ ........ ............. ....... <<
1669 # <<
1670 54.70% 0.00% tsc_msrs_test [kernel. <<
1671 | <<
1672 ---entry_SYSCALL_64_after_hwframe <<
1673 do_syscall_64 <<
1674 | <<
1675 |--29.44%--syscall_exit_to_use <<
1676 | exit_to_user_mode_p <<
1677 | task_work_run <<
1678 | __fput <<
1679 <<
1680 <<
1681 Event Trace <<
1682 ----------- <<
1683 <<
1684 Event Trace records information about asynchr <<
1685 faults, VM exits and entries. The informatio <<
1686 and also the Interrupt Flag is recorded on th <<
1687 contains a type field to identify one of the <<
1688 <<
1689 1 INTR interrupt, fa <<
1690 2 IRET interrupt ret <<
1691 3 SMI system manage <<
1692 4 RSM resume from s <<
1693 5 SIPI startup inter <<
1694 6 INIT INIT signal <<
1695 7 VMENTRY VM-Entry <<
1696 8 VMEXIT VM-Entry <<
1697 9 VMEXIT_INTR VM-Exit due t <<
1698 10 SHUTDOWN Shutdown <<
1699 <<
1700 For more details, refer to the Intel 64 and I <<
1701 Developer Manuals (version 076 or later). <<
1702 <<
1703 The capability to do Event Trace is indicated <<
1704 /sys/bus/event_source/devices/intel_pt/caps/e <<
1705 <<
1706 Event trace is selected for recording using t <<
1707 <<
1708 perf record -e intel_pt/event/u uname <<
1709 <<
1710 Event trace events are output using the --itr <<
1711 <<
1712 perf script --itrace=Ie <<
1713 <<
1714 perf script displays events containing CFE ty <<
1715 in the form: <<
1716 <<
1717 evt: hw int (t) cfe: <<
1718 <<
1719 The IP flag indicates if the event binds to a <<
1720 flow control packet generation is enabled, as <<
1721 set. <<
1722 <<
1723 perf script displays events containing change <<
1724 <<
1725 iflag: t IFLAG <<
1726 <<
1727 where "via branch" indicates a branch (interr <<
1728 "non branch" indicates an instruction such as <<
1729 <<
1730 In addition, the current state of the interru <<
1731 or absence of the "D" (interrupt disabled) pe <<
1732 flag is changed, then the "t" flag is also in <<
1733 <<
1734 no flag, interrupts enabled I <<
1735 t interrupts become disabled IF <<
1736 D interrupts are disabled IF=0 <<
1737 Dt interrupts become enabled IF <<
1738 <<
1739 The intel-pt-events.py script illustrates how <<
1740 using a Python script. <<
1741 <<
1742 <<
1743 TNT Disable <<
1744 ----------- <<
1745 <<
1746 TNT packets are disabled using the "notnt" co <<
1747 <<
1748 perf record -e intel_pt/notnt/u uname <<
1749 <<
1750 In that case the --itrace q option is forced <<
1751 to reconstruct the control flow is not possib <<
1752 <<
1753 <<
1754 Emulated PTWRITE <<
1755 ---------------- <<
1756 <<
1757 Later perf tools support a method to emulate <<
1758 can be useful if hardware does not support th <<
1759 <<
1760 Instead of using the ptwrite instruction, a f <<
1761 a trace that encodes the payload data into TN <<
1762 of the function: <<
1763 <<
1764 #include <stdint.h> <<
1765 <<
1766 void perf_emulate_ptwrite(uint64_t x) <<
1767 __attribute__((externally_visible, noipa, no <<
1768 <<
1769 #define PERF_EMULATE_PTWRITE_8_BITS \ <<
1770 "1: shl %rax\n" \ <<
1771 " jc 1f\n" \ <<
1772 "1: shl %rax\n" \ <<
1773 " jc 1f\n" \ <<
1774 "1: shl %rax\n" \ <<
1775 " jc 1f\n" \ <<
1776 "1: shl %rax\n" \ <<
1777 " jc 1f\n" \ <<
1778 "1: shl %rax\n" \ <<
1779 " jc 1f\n" \ <<
1780 "1: shl %rax\n" \ <<
1781 " jc 1f\n" \ <<
1782 "1: shl %rax\n" \ <<
1783 " jc 1f\n" \ <<
1784 "1: shl %rax\n" \ <<
1785 " jc 1f\n" <<
1786 <<
1787 /* Undefined instruction */ <<
1788 #define PERF_EMULATE_PTWRITE_UD2 ".by <<
1789 <<
1790 #define PERF_EMULATE_PTWRITE_MAGIC PE <<
1791 <<
1792 void perf_emulate_ptwrite(uint64_t x __attri <<
1793 { <<
1794 /* Assumes SysV ABI : x passed in r <<
1795 __asm__ volatile ( <<
1796 "jmp 1f\n" <<
1797 PERF_EMULATE_PTWRITE_MAGIC <<
1798 "1: mov %rdi, %rax\n" <<
1799 PERF_EMULATE_PTWRITE_8_BITS <<
1800 PERF_EMULATE_PTWRITE_8_BITS <<
1801 PERF_EMULATE_PTWRITE_8_BITS <<
1802 PERF_EMULATE_PTWRITE_8_BITS <<
1803 PERF_EMULATE_PTWRITE_8_BITS <<
1804 PERF_EMULATE_PTWRITE_8_BITS <<
1805 PERF_EMULATE_PTWRITE_8_BITS <<
1806 PERF_EMULATE_PTWRITE_8_BITS <<
1807 "1: ret\n" <<
1808 ); <<
1809 } <<
1810 <<
1811 For example, a test program with the function <<
1812 <<
1813 #include <stdio.h> <<
1814 #include <stdint.h> <<
1815 #include <stdlib.h> <<
1816 <<
1817 #include "perf_emulate_ptwrite.h" <<
1818 <<
1819 int main(int argc, char *argv[]) <<
1820 { <<
1821 uint64_t x = 0; <<
1822 <<
1823 if (argc > 1) <<
1824 x = strtoull(argv[1], NULL, <<
1825 perf_emulate_ptwrite(x); <<
1826 return 0; <<
1827 } <<
1828 <<
1829 Can be compiled and traced: <<
1830 <<
1831 $ gcc -Wall -Wextra -O3 -g -o eg_ptw eg_ptw. <<
1832 $ perf record -e intel_pt//u ./eg_ptw 0x1234 <<
1833 [ perf record: Woken up 1 times to write dat <<
1834 [ perf record: Captured and wrote 0.017 MB p <<
1835 $ perf script --itrace=ew <<
1836 eg_ptw 19875 [007] 8061.235912: <<
1837 $ <<
1838 <<
1839 <<
1840 Pipe mode <<
1841 --------- <<
1842 Pipe mode is a problem for Intel PT and possi <<
1843 It's not recommended to use a pipe as data ou <<
1844 of the following reason. <<
1845 <<
1846 Essentially the auxtrace buffers do not behav <<
1847 event buffers. That is because the head and <<
1848 software, but in the auxtrace case the data i <<
1849 So the head and tail do not get updated as da <<
1850 <<
1851 In the Intel PT case, the head and tail are u <<
1852 is disabled by software, for example: <<
1853 - full-trace, system wide : when buffer p <<
1854 - full-trace, not system-wide : when buff <<
1855 context s <<
1856 - snapshot mode : as above but also when <<
1857 - sample mode : as above but also when a <<
1858 <<
1859 That means finished-round ordering doesn't wo <<
1860 can turn up that has data that extends back i <<
1861 very beginning of tracing. <<
1862 <<
1863 For a perf.data file, that problem is solved <<
1864 and queuing up the auxtrace buffers in advanc <<
1865 <<
1866 For pipe mode, the order of events and timest <<
1867 be messed up. <<
1868 <<
1869 <<
1870 EXAMPLE <<
1871 ------- <<
1872 <<
1873 Examples can be found on perf wiki page "Perf <<
1874 <<
1875 https://perf.wiki.kernel.org/index.php/Perf_t <<
1876 1340
1877 1341
1878 SEE ALSO 1342 SEE ALSO
1879 -------- 1343 --------
1880 1344
1881 linkperf:perf-record[1], linkperf:perf-script 1345 linkperf:perf-record[1], linkperf:perf-script[1], linkperf:perf-report[1],
1882 linkperf:perf-inject[1] 1346 linkperf:perf-inject[1]
Linux® is a registered trademark of Linus Torvalds in the United States and other countries.
TOMOYO® is a registered trademark of NTT DATA CORPORATION.