From: Namhyung Kim <namhyung@kernel.org>
To: Arnaldo Carvalho de Melo <acme@kernel.org>,
Ian Rogers <irogers@google.com>,
Kan Liang <kan.liang@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>,
Adrian Hunter <adrian.hunter@intel.com>,
Peter Zijlstra <peterz@infradead.org>,
Ingo Molnar <mingo@kernel.org>,
LKML <linux-kernel@vger.kernel.org>,
linux-perf-users@vger.kernel.org
Subject: [PATCH 3/6] perf annotate-data: Handle direct global variable access
Date: Wed, 1 May 2024 23:00:08 -0700 [thread overview]
Message-ID: <20240502060011.1838090-4-namhyung@kernel.org> (raw)
In-Reply-To: <20240502060011.1838090-1-namhyung@kernel.org>
Like per-cpu base offset array, sometimes it accesses the global
variable directly using the offset. Allow this type of instructions as
long as it finds a global variable for the address.
movslq %edi, %rcx
mov -0x7dc94ae0(,%rcx,8), %rcx <<<--- here
As %rcx has a valid type (i.e. array index) from the first instruction,
it will be checked by the first case in check_matching_type(). But as
it's not a pointer type, the match will fail. But in this case, it
should check if it accesses the kernel global array variable.
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
tools/perf/util/annotate-data.c | 27 +++++++++++++++------------
1 file changed, 15 insertions(+), 12 deletions(-)
diff --git a/tools/perf/util/annotate-data.c b/tools/perf/util/annotate-data.c
index 4dd0911904f2..f1e52a531563 100644
--- a/tools/perf/util/annotate-data.c
+++ b/tools/perf/util/annotate-data.c
@@ -1256,14 +1256,19 @@ static int check_matching_type(struct type_state *state,
if (state->regs[reg].ok && state->regs[reg].kind == TSR_KIND_TYPE) {
int tag = dwarf_tag(&state->regs[reg].type);
- pr_debug_dtp("\n");
-
/*
* Normal registers should hold a pointer (or array) to
* dereference a memory location.
*/
- if (tag != DW_TAG_pointer_type && tag != DW_TAG_array_type)
+ if (tag != DW_TAG_pointer_type && tag != DW_TAG_array_type) {
+ if (dloc->op->offset < 0 && reg != state->stack_reg)
+ goto check_kernel;
+
+ pr_debug_dtp("\n");
return -1;
+ }
+
+ pr_debug_dtp("\n");
/* Remove the pointer and get the target type */
if (die_get_real_type(&state->regs[reg].type, type_die) == NULL)
@@ -1376,12 +1381,14 @@ static int check_matching_type(struct type_state *state,
return -1;
}
- if (map__dso(dloc->ms->map)->kernel && arch__is(dloc->arch, "x86")) {
+check_kernel:
+ if (map__dso(dloc->ms->map)->kernel) {
u64 addr;
int offset;
/* Direct this-cpu access like "%gs:0x34740" */
- if (dloc->op->segment == INSN_SEG_X86_GS && dloc->op->imm) {
+ if (dloc->op->segment == INSN_SEG_X86_GS && dloc->op->imm &&
+ arch__is(dloc->arch, "x86")) {
pr_debug_dtp(" this-cpu var\n");
addr = dloc->op->offset;
@@ -1394,17 +1401,13 @@ static int check_matching_type(struct type_state *state,
return -1;
}
- /* Access to per-cpu base like "-0x7dcf0500(,%rdx,8)" */
+ /* Access to global variable like "-0x7dcf0500(,%rdx,8)" */
if (dloc->op->offset < 0 && reg != state->stack_reg) {
- const char *var_name = NULL;
-
addr = (s64) dloc->op->offset;
- if (get_global_var_info(dloc, addr, &var_name, &offset) &&
- !strcmp(var_name, "__per_cpu_offset") && offset == 0 &&
- get_global_var_type(cu_die, dloc, dloc->ip, addr,
+ if (get_global_var_type(cu_die, dloc, dloc->ip, addr,
&offset, type_die)) {
- pr_debug_dtp(" percpu base\n");
+ pr_debug_dtp(" global var\n");
dloc->type_offset = offset;
return 1;
--
2.45.0.rc1.225.g2a3ae87e7f-goog
next prev parent reply other threads:[~2024-05-02 6:00 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-05-02 6:00 [PATCHSET 0/6] perf annotate-data: Small updates in the data type profiling (v1) Namhyung Kim
2024-05-02 6:00 ` [PATCH 1/6] perf dwarf-aux: Add die_collect_global_vars() Namhyung Kim
2024-05-02 6:00 ` [PATCH 2/6] perf annotate-data: Collect global variables in advance Namhyung Kim
2024-05-02 13:50 ` Arnaldo Carvalho de Melo
2024-05-02 18:23 ` Namhyung Kim
2024-05-02 23:28 ` Namhyung Kim
2024-05-02 6:00 ` Namhyung Kim [this message]
2024-05-02 6:00 ` [PATCH 4/6] perf annotate-data: Check memory access with two registers Namhyung Kim
2024-05-02 14:05 ` Arnaldo Carvalho de Melo
2024-05-02 18:14 ` Namhyung Kim
2024-05-04 18:26 ` Arnaldo Carvalho de Melo
2024-05-02 6:00 ` [PATCH 5/6] perf annotate-data: Handle multi regs in find_data_type_block() Namhyung Kim
2024-05-02 6:00 ` [PATCH 6/6] perf annotate-data: Check kind of stack variables Namhyung Kim
2024-05-02 14:25 ` [PATCHSET 0/6] perf annotate-data: Small updates in the data type profiling (v1) Arnaldo Carvalho de Melo
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20240502060011.1838090-4-namhyung@kernel.org \
--to=namhyung@kernel.org \
--cc=acme@kernel.org \
--cc=adrian.hunter@intel.com \
--cc=irogers@google.com \
--cc=jolsa@kernel.org \
--cc=kan.liang@linux.intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-perf-users@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=peterz@infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®