From: Adrian Hunter <adrian.hunter@xxxxxxxxx> [ Upstream commit 24e3599c5a88e0e2995e3f5c9305f80195942dc9 ] Add documentation for Event Trace and TNT disable to the perf Intel PT man page. Signed-off-by: Adrian Hunter <adrian.hunter@xxxxxxxxx> Cc: Alexander Shishkin <alexander.shishkin@xxxxxxxxxxxxxxx> Cc: Andi Kleen <ak@xxxxxxxxxxxxxxx> Cc: Jiri Olsa <jolsa@xxxxxxxxxx> Link: https://lore.kernel.org/r/20220124084201.2699795-26-adrian.hunter@xxxxxxxxx Signed-off-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx> Stable-dep-of: aeb802f872a7 ("perf intel-pt: Do not try to queue auxtrace data on pipe") Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx> --- tools/perf/Documentation/perf-intel-pt.txt | 104 ++++++++++++++++++++- 1 file changed, 102 insertions(+), 2 deletions(-) diff --git a/tools/perf/Documentation/perf-intel-pt.txt b/tools/perf/Documentation/perf-intel-pt.txt index db465fa7ee918..48460923a0e4e 100644 --- a/tools/perf/Documentation/perf-intel-pt.txt +++ b/tools/perf/Documentation/perf-intel-pt.txt @@ -108,9 +108,10 @@ displayed as follows: perf script --itrace=ibxwpe -F+flags -The flags are "bcrosyiABExgh" which stand for branch, call, return, conditional, +The flags are "bcrosyiABExghDt" which stand for branch, call, return, conditional, system, asynchronous, interrupt, transaction abort, trace begin, trace end, -in transaction, VM-entry, and VM-exit respectively. +in transaction, VM-entry, VM-exit, interrupt disabled, and interrupt disable +toggle respectively. perf script also supports higher level ways to dump instruction traces: @@ -472,6 +473,30 @@ pwr_evt Enable power events. The power events provide information about which contains "1" if the feature is supported and "0" otherwise. +event Enable Event Trace. The events provide information about asynchronous + events. + + Support for this feature is indicated by: + + /sys/bus/event_source/devices/intel_pt/caps/event_trace + + which contains "1" if the feature is supported and + "0" otherwise. + +notnt Disable TNT packets. Without TNT packets, it is not possible to walk + executable code to reconstruct control flow, however FUP, TIP, TIP.PGE + and TIP.PGD packets still indicate asynchronous control flow, and (if + return compression is disabled - see noretcomp) return statements. + The advantage of eliminating TNT packets is reducing the size of the + trace and corresponding tracing overhead. + + Support for this feature is indicated by: + + /sys/bus/event_source/devices/intel_pt/caps/tnt_disable + + which contains "1" if the feature is supported and + "0" otherwise. + AUX area sampling option ~~~~~~~~~~~~~~~~~~~~~~~~ @@ -865,6 +890,8 @@ The letters are: p synthesize "power" events (incl. PSB events) c synthesize branches events (calls only) r synthesize branches events (returns only) + o synthesize PEBS-via-PT events + I synthesize Event Trace events e synthesize tracing error events d create a debug log g synthesize a call chain (use with i or x) @@ -1338,6 +1365,79 @@ There were none. :17006 17006 [001] 11500.262869216: ffffffff8220116e error_entry+0xe ([guest.kernel.kallsyms]) pushq %rax +Event Trace +----------- + +Event Trace records information about asynchronous events, for example interrupts, +faults, VM exits and entries. The information is recorded in CFE and EVD packets, +and also the Interrupt Flag is recorded on the MODE.Exec packet. The CFE packet +contains a type field to identify one of the following: + + 1 INTR interrupt, fault, exception, NMI + 2 IRET interrupt return + 3 SMI system management interrupt + 4 RSM resume from system management mode + 5 SIPI startup interprocessor interrupt + 6 INIT INIT signal + 7 VMENTRY VM-Entry + 8 VMEXIT VM-Entry + 9 VMEXIT_INTR VM-Exit due to interrupt + 10 SHUTDOWN Shutdown + +For more details, refer to the Intel 64 and IA-32 Architectures Software +Developer Manuals (version 076 or later). + +The capability to do Event Trace is indicated by the +/sys/bus/event_source/devices/intel_pt/caps/event_trace file. + +Event trace is selected for recording using the "event" config term. e.g. + + perf record -e intel_pt/event/u uname + +Event trace events are output using the --itrace I option. e.g. + + perf script --itrace=Ie + +perf script displays events containing CFE type, vector and event data, +in the form: + + evt: hw int (t) cfe: INTR IP: 1 vector: 3 PFA: 0x8877665544332211 + +The IP flag indicates if the event binds to an IP, which includes any case where +flow control packet generation is enabled, as well as when CFE packet IP bit is +set. + +perf script displays events containing changes to the Interrupt Flag in the form: + + iflag: t IFLAG: 1->0 via branch + +where "via branch" indicates a branch (interrupt or return from interrupt) and +"non branch" indicates an instruction such as CFI, STI or POPF). + +In addition, the current state of the interrupt flag is indicated by the presence +or absence of the "D" (interrupt disabled) perf script flag. If the interrupt +flag is changed, then the "t" flag is also included i.e. + + no flag, interrupts enabled IF=1 + t interrupts become disabled IF=1 -> IF=0 + D interrupts are disabled IF=0 + Dt interrupts become enabled IF=0 -> IF=1 + +The intel-pt-events.py script illustrates how to access Event Trace information +using a Python script. + + +TNT Disable +----------- + +TNT packets are disabled using the "notnt" config term. e.g. + + perf record -e intel_pt/notnt/u uname + +In that case the --itrace q option is forced because walking executable code +to reconstruct the control flow is not possible. + + SEE ALSO -------- -- 2.39.2
