mirror of
https://github.com/torvalds/linux
synced 2024-11-05 18:23:50 +00:00
291dcb98d7
Perf records IBS (Instruction Based Sampling) extra sample data when 'perf record --raw-samples' is used with an IBS-compatible event, on a machine that supports IBS. IBS support is indicated in CPUID_Fn80000001_ECX bit #10. Up until now, users have been able to see the extra sample data solely in raw hex format using 'perf report --dump-raw-trace'. From there, users could decode the data either manually, or by using an external script. Enable the built-in 'perf report --dump-raw-trace' to do the decoding of the extra sample data bits, so manual or external script decoding isn't necessary. Example usage: $ sudo perf record -c 10000001 -a --raw-samples -e ibs_fetch/rand_en=1/,ibs_op/cnt_ctl=1/ -C 0,1 taskset -c 0,1 7za b -mmt2 | perf report --dump-raw-trace Stdout contains IBS Fetch samples, e.g.: ibs_fetch_ctl: 02170007ffffffff MaxCnt 1048560 Cnt 1048560 Lat 7 En 1 Val 1 Comp 1 IcMiss 0 PhyAddrValid 1 L1TlbPgSz 4KB L1TlbMiss 0 L2TlbMiss 0 RandEn 1 L2Miss 0 IbsFetchLinAd: 000056016b2ead40 IbsFetchPhysAd: 000000115cedfd40 c_ibs_ext_ctl: 0000000000000000 IbsItlbRefillLat 0 ..and IBS Op samples, e.g.: ibs_op_ctl: 0000009e009e8968 MaxCnt 10000000 En 1 Val 1 CntCtl 1=uOps CurCnt 158 IbsOpRip: 000056016b2ea73d ibs_op_data: 00000000000b0002 CompToRetCtr 2 TagToRetCtr 11 BrnRet 0 RipInvalid 0 BrnFuse 0 Microcode 0 ibs_op_data2: 0000000000000002 CacheHitSt 0=M-state RmtNode 0 DataSrc 2=Local node cache ibs_op_data3: 0000000000c60002 LdOp 0 StOp 1 DcL1TlbMiss 0 DcL2TlbMiss 0 DcL1TlbHit2M 0 DcL1TlbHit1G 0 DcL2TlbHit2M 0 DcMiss 0 DcMisAcc 0 DcWcMemAcc 0 DcUcMemAcc 0 DcLockedOp 0 DcMissNoMabAlloc 0 DcLinAddrValid 1 DcPhyAddrValid 1 DcL2TlbHit1G 0 L2Miss 0 SwPf 0 OpMemWidth 4 bytes OpDcMissOpenMemReqs 0 DcMissLat 0 TlbRefillLat 0 IbsDCLinAd: 00007f133c319ce0 IbsDCPhysAd: 0000000270485ce0 Committer notes: Fixed up this: util/amd-sample-raw.c: In function ‘evlist__amd_sample_raw’: util/amd-sample-raw.c:125:42: error: ‘ bytes’ directive output may be truncated writing 6 bytes into a region of size between 4 and 7 [-Werror=format-truncation=] 125 | " OpMemWidth %2d bytes", 1 << (reg.op_mem_width - 1)); | ^~~~~~ In file included from /usr/include/stdio.h:866, from util/amd-sample-raw.c:7: /usr/include/bits/stdio2.h:71:10: note: ‘__builtin___snprintf_chk’ output between 21 and 24 bytes into a destination of size 21 71 | return __builtin___snprintf_chk (__s, __n, __USE_FORTIFY_LEVEL - 1, | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 72 | __glibc_objsize (__s), __fmt, | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 73 | __va_arg_pack ()); | ~~~~~~~~~~~~~~~~~ cc1: all warnings being treated as errors As that %2d won't limit the number of chars to 2, just state that 2 is the minimal width: $ cat printf.c #include <stdio.h> #include <stdlib.h> int main(int argc, char *argv[]) { char bf[64]; int len = snprintf(bf, sizeof(bf), "%2d", atoi(argv[1])); printf("strlen(%s): %u\n", bf, len); return 0; } $ ./printf 1 strlen( 1): 2 $ ./printf 12 strlen(12): 2 $ ./printf 123 strlen(123): 3 $ ./printf 1234 strlen(1234): 4 $ ./printf 12345 strlen(12345): 5 $ ./printf 123456 strlen(123456): 6 $ And since we probably don't want that output to be truncated, just assume the worst case, as the compiler did, and add a few more chars to that buffer. Also use sizeof(var) instead of sizeof(dup-of-wanted-format-string) to avoid bugs when changing one but not the other. I also had to change this: -#include <asm/amd-ibs.h> +#include "../../arch/x86/include/asm/amd-ibs.h" To make it build on other architectures, just like intel-pt does. Signed-off-by: Kim Phillips <kim.phillips@amd.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joao Martins <joao.m.martins@oracle.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> Cc: Stephane Eranian <eranian@google.com> Link: https //lore.kernel.org/r/20210817221509.88391-4-kim.phillips@amd.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
26 lines
742 B
C
26 lines
742 B
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
|
|
#include <string.h>
|
|
#include <linux/string.h>
|
|
#include "evlist.h"
|
|
#include "env.h"
|
|
#include "header.h"
|
|
#include "sample-raw.h"
|
|
|
|
/*
|
|
* Check platform the perf data file was created on and perform platform
|
|
* specific interpretation.
|
|
*/
|
|
void evlist__init_trace_event_sample_raw(struct evlist *evlist)
|
|
{
|
|
const char *arch_pf = perf_env__arch(evlist->env);
|
|
const char *cpuid = perf_env__cpuid(evlist->env);
|
|
|
|
if (arch_pf && !strcmp("s390", arch_pf))
|
|
evlist->trace_event_sample_raw = evlist__s390_sample_raw;
|
|
else if (arch_pf && !strcmp("x86", arch_pf) &&
|
|
cpuid && strstarts(cpuid, "AuthenticAMD") &&
|
|
evlist__has_amd_ibs(evlist)) {
|
|
evlist->trace_event_sample_raw = evlist__amd_sample_raw;
|
|
}
|
|
}
|