mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-25 09:01:47 +07:00
2566349648
Enable '-j stack' applicability together with '--call-graph dwarf' option so thread stack data and LBR call stack could be captured jointly: $ perf record -g --call-graph dwarf,1024 -j stack,u -- stack_test Collected LBR call stack can be used to augment DWARF call stack calculated from the raw thread stack data and to provide more comprehensive call stack information for cases when collected SIZE is not enough to cover complete thread stack. Such cases are typical for workloads that allocate large arrays of data on its threads stacks or the possible SIZE to collect can't be large enough due to workload nature or system configuration and this is where hardware captured LBR call stacks can provide missing stack frames. Possible DWARF plus LBR call stacks consolidation algorithm description follows. With this patch set perf report command UI currently ignores collected LBR call stack data and still provides DWARF based call stacks information. =========================================================================== Overview: Legend: THS - thread stack CTX - thread register context SWS - software stack SSF - skipped stack frames PSS - Perf sample stack ip,sp,bp - HW registers values d - allocated stack regions kip - ip address in the kernel space K - captured thread stack size THS ----- | |<-stack bottom ... |---| |ip4| |---| PSS = SWS(THS(K)) | | --> | | | |d3 | user/ | |---| user PSS kernel PSS | |ip3| ------ ------ | |---| |SSF | |SSF | | | | .... .... | | | ------ ------ | |d2 | | -1 | | -1 | |---| user ------ ------ K |ip2| CTX |ip3 | |ip3 | |---| |----| |----| | |d1 | ... |ip2 | , |ip2 | | |---| |---| |----| |----| | |ip1| |bp0| |ip1 | |ip1 | | |---| |---| |----| |----| | | | |ip0|->|ip0 | |ip0 |<-user stack top | | | |---| ------ ------ | | |<-|sp0|<-stack |kip0|<-kernel stack bottom --> ----- ----- top |----| |kip1| |----| |kip2| |----| .... | |<-kernel stack top ------ Algorithm details: Legend: HWS - hardware stack K-SWS - kernel software stack BRANCH TABLE HWS ip ip from to ------ ----------- |ip7`| |ip7`| | |----| |----|----| |ip6`| |ip6`| | user PSS |----| |----|----| |ip5`| |ip5`| | ------ |----| |----|----| | -1 | |ip4`| |ip4`| | ------ |----| |----|----| |ip3 |~~~|ip3`| |ip3`| | |----| |----| |----|----| |ip2 |~~~|ip2`| |ip2`| | |----| |----| |----|----| |ip1 |~~~|ip1`| |ip1`|ip0`| |----| |----| ----------- |ip0 |~~~|ip0`|<---------' ------ ------ 1. if (sym(ipj) == sym(ipj`)), j=0-3 ===> user PSS 2. ipj` , j=4-7 ===> user PSS Augmented PSS = A_SWS(SWS(THS(K)), HWS): user/ user PSS kernel PSS ------ ------ |ip7`| |ip7`|<-user PSS bottom |----| |----| |ip6`| |ip6`| |----| |----| HWS |ip5`| |ip5`| |----| |----| |ip4`| |ip4`| ------ ------ |ip3 | |ip3 | |----| |----| SWS |ip2 | |ip2 | |----| |----| |ip1 | |ip1 | |----| |----| |ip0 | |ip0 |<-user PSS top ------ ------ |kip0|<-kernel PSS bottom |----| |kip1| K-SWS |----| |kip2| |----| |kip3|<-kernel PSS top ------ APSS Committer testing: Before: # perf record -g --call-graph dwarf,1024 -j stack,u ls > /dev/null unknown branch filter stack, check man page Usage: perf record [<options>] [<command>] or: perf record [<options>] -- <command> [<options>] -j, --branch-filter <branch filter mask> branch stack filter modes # perf record -g --call-graph dwarf,1024 -j u ls > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.054 MB perf.data (12 samples) ] # perf evlist -v cycles: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|ADDR|CALLCHAIN|PERIOD|BRANCH_STACK|REGS_USER|STACK_USER|DATA_SRC, read_format: ID, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, enable_on_exec: 1, task: 1, precise_ip: 3, mmap_data: 1, sample_id_all: 1, exclude_guest: 1, exclude_callchain_user: 1, mmap2: 1, comm_exec: 1, ksymbol: 1, bpf_event: 1, branch_sample_type: ANY, sample_regs_user: 0xff0fff, sample_stack_user: 1024 # After: # perf record -g --call-graph dwarf,1024 -j stack,u ls > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.044 MB perf.data (11 samples) ] [root@quaco ~]# perf evlist -v cycles: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|ADDR|CALLCHAIN|PERIOD|BRANCH_STACK|REGS_USER|STACK_USER|DATA_SRC, read_format: ID, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, enable_on_exec: 1, task: 1, precise_ip: 3, mmap_data: 1, sample_id_all: 1, exclude_guest: 1, exclude_callchain_user: 1, mmap2: 1, comm_exec: 1, ksymbol: 1, bpf_event: 1, branch_sample_type: USER|CALL_STACK, sample_regs_user: 0xff0fff, sample_stack_user: 1024 # Signed-off-by: Alexey Budankov <alexey.budankov@linux.intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/e9e00090-66fb-d2a4-c90f-1d12344f7788@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
108 lines
2.2 KiB
C
108 lines
2.2 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
#include "perf.h"
|
|
#include "util/debug.h"
|
|
#include <subcmd/parse-options.h>
|
|
#include "util/parse-branch-options.h"
|
|
#include <stdlib.h>
|
|
|
|
#define BRANCH_OPT(n, m) \
|
|
{ .name = n, .mode = (m) }
|
|
|
|
#define BRANCH_END { .name = NULL }
|
|
|
|
struct branch_mode {
|
|
const char *name;
|
|
int mode;
|
|
};
|
|
|
|
static const struct branch_mode branch_modes[] = {
|
|
BRANCH_OPT("u", PERF_SAMPLE_BRANCH_USER),
|
|
BRANCH_OPT("k", PERF_SAMPLE_BRANCH_KERNEL),
|
|
BRANCH_OPT("hv", PERF_SAMPLE_BRANCH_HV),
|
|
BRANCH_OPT("any", PERF_SAMPLE_BRANCH_ANY),
|
|
BRANCH_OPT("any_call", PERF_SAMPLE_BRANCH_ANY_CALL),
|
|
BRANCH_OPT("any_ret", PERF_SAMPLE_BRANCH_ANY_RETURN),
|
|
BRANCH_OPT("ind_call", PERF_SAMPLE_BRANCH_IND_CALL),
|
|
BRANCH_OPT("abort_tx", PERF_SAMPLE_BRANCH_ABORT_TX),
|
|
BRANCH_OPT("in_tx", PERF_SAMPLE_BRANCH_IN_TX),
|
|
BRANCH_OPT("no_tx", PERF_SAMPLE_BRANCH_NO_TX),
|
|
BRANCH_OPT("cond", PERF_SAMPLE_BRANCH_COND),
|
|
BRANCH_OPT("ind_jmp", PERF_SAMPLE_BRANCH_IND_JUMP),
|
|
BRANCH_OPT("call", PERF_SAMPLE_BRANCH_CALL),
|
|
BRANCH_OPT("save_type", PERF_SAMPLE_BRANCH_TYPE_SAVE),
|
|
BRANCH_OPT("stack", PERF_SAMPLE_BRANCH_CALL_STACK),
|
|
BRANCH_END
|
|
};
|
|
|
|
int parse_branch_str(const char *str, __u64 *mode)
|
|
{
|
|
#define ONLY_PLM \
|
|
(PERF_SAMPLE_BRANCH_USER |\
|
|
PERF_SAMPLE_BRANCH_KERNEL |\
|
|
PERF_SAMPLE_BRANCH_HV)
|
|
|
|
int ret = 0;
|
|
char *p, *s;
|
|
char *os = NULL;
|
|
const struct branch_mode *br;
|
|
|
|
if (str == NULL) {
|
|
*mode = PERF_SAMPLE_BRANCH_ANY;
|
|
return 0;
|
|
}
|
|
|
|
/* because str is read-only */
|
|
s = os = strdup(str);
|
|
if (!s)
|
|
return -1;
|
|
|
|
for (;;) {
|
|
p = strchr(s, ',');
|
|
if (p)
|
|
*p = '\0';
|
|
|
|
for (br = branch_modes; br->name; br++) {
|
|
if (!strcasecmp(s, br->name))
|
|
break;
|
|
}
|
|
if (!br->name) {
|
|
ret = -1;
|
|
pr_warning("unknown branch filter %s,"
|
|
" check man page\n", s);
|
|
goto error;
|
|
}
|
|
|
|
*mode |= br->mode;
|
|
|
|
if (!p)
|
|
break;
|
|
|
|
s = p + 1;
|
|
}
|
|
|
|
/* default to any branch */
|
|
if ((*mode & ~ONLY_PLM) == 0) {
|
|
*mode = PERF_SAMPLE_BRANCH_ANY;
|
|
}
|
|
error:
|
|
free(os);
|
|
return ret;
|
|
}
|
|
|
|
int
|
|
parse_branch_stack(const struct option *opt, const char *str, int unset)
|
|
{
|
|
__u64 *mode = (__u64 *)opt->value;
|
|
|
|
if (unset)
|
|
return 0;
|
|
|
|
/*
|
|
* cannot set it twice, -b + --branch-filter for instance
|
|
*/
|
|
if (*mode)
|
|
return -1;
|
|
|
|
return parse_branch_str(str, mode);
|
|
}
|