From: Zecheng Li <zecheng@google.com>
To: Peter Zijlstra <peterz@infradead.org>,
Ingo Molnar <mingo@redhat.com>,
Arnaldo Carvalho de Melo <acme@kernel.org>,
Namhyung Kim <namhyung@kernel.org>,
Mark Rutland <mark.rutland@arm.com>,
Alexander Shishkin <alexander.shishkin@linux.intel.com>,
Jiri Olsa <jolsa@kernel.org>, Ian Rogers <irogers@google.com>,
Adrian Hunter <adrian.hunter@intel.com>,
"Liang, Kan" <kan.liang@linux.intel.com>,
Masami Hiramatsu <mhiramat@kernel.org>
Cc: Zecheng Li <zli94@ncsu.edu>, Xu Liu <xliuprof@google.com>,
linux-perf-users@vger.kernel.org, linux-kernel@vger.kernel.org,
Zecheng Li <zecheng@google.com>
Subject: [PATCH v1 2/6] perf dwarf-aux: More accurate variable type match for breg
Date: Fri, 25 Jul 2025 20:28:05 +0000 [thread overview]
Message-ID: <20250725202809.1230085-3-zecheng@google.com> (raw)
In-Reply-To: <20250725202809.1230085-1-zecheng@google.com>
Introduces the function is_breg_access_indirect to determine whether a
memory access involving a DW_OP_breg* operation refers to the variable's
value directly or requires dereferencing the variable's type as a
pointer based on the DWARF expression. Previously, all breg based
accesses were assumed to directly access the variable's value
(is_pointer = false).
The is_breg_access_indirect function handles three main cases:
1. Base register + offset only: (e.g., DW_OP_breg7 RSP+88) The
calculated address is the location of the variable. The access is
direct, so no type dereference is needed. Returns false.
2. Base register + offset, followed by other operations ending in
DW_OP_stack_value, including DW_OP_deref: (e.g., DW_OP_breg7 RSP+96,
DW_OP_deref, DW_OP_plus_uconst 0x64, DW_OP_stack_value) The DWARF
expression computes the variable's value, but that value requires a
dereference. The memory access is fetching that value, so no type
dereference is needed. Returns false.
3. Base register + offset, followed only by DW_OP_stack_value: (e.g.,
DW_OP_breg7 RSP+176, DW_OP_stack_value) This indicates the value at
the base + offset is the variable's value. Since this value is being
used as an address in the memory access, the variable's type is
treated as a pointer and requires a type dereference. Returns true.
The is_pointer argument passed to match_var_offset is now set by
is_breg_access_indirect for breg accesses.
Signed-off-by: Zecheng Li <zecheng@google.com>
---
tools/perf/util/dwarf-aux.c | 42 ++++++++++++++++++++++++++++++++-----
1 file changed, 37 insertions(+), 5 deletions(-)
diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index bf906dff9ef0..814c96ea509f 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -1424,6 +1424,38 @@ static bool match_var_offset(Dwarf_Die *die_mem, struct find_var_data *data,
return true;
}
+/**
+ * is_breg_access_indirect - Check if breg based access implies type dereference
+ * @ops: DWARF operations array
+ * @nops: Number of operations in @ops
+ *
+ * Returns true if the DWARF expression indicates the variable's value is
+ * a pointer that the memory access dereferences.
+ * Returns false if the expression evaluates to the variable's value directly.
+ * This is called after check_allowed_ops.
+ */
+static bool is_breg_access_indirect(Dwarf_Op *ops, size_t nops)
+{
+ ops++;
+ nops--;
+
+ /* only the base register */
+ if (nops == 0)
+ return false;
+
+ switch (ops->atom) {
+ case DW_OP_stack_value:
+ return true;
+ case DW_OP_deref_size:
+ case DW_OP_deref:
+ case DW_OP_piece:
+ return false;
+ default:
+ /* unreachable, OP not supported */
+ return false;
+ }
+}
+
/* Only checks direct child DIEs in the given scope. */
static int __die_find_var_reg_cb(Dwarf_Die *die_mem, void *arg)
{
@@ -1452,7 +1484,7 @@ static int __die_find_var_reg_cb(Dwarf_Die *die_mem, void *arg)
if (data->is_fbreg && ops->atom == DW_OP_fbreg &&
check_allowed_ops(ops, nops) &&
match_var_offset(die_mem, data, data->offset, ops->number,
- /*is_pointer=*/false))
+ /*is_pointer=*/is_breg_access_indirect(ops, nops)))
return DIE_FIND_CB_END;
/* Only match with a simple case */
@@ -1464,11 +1496,11 @@ static int __die_find_var_reg_cb(Dwarf_Die *die_mem, void *arg)
/*is_pointer=*/true))
return DIE_FIND_CB_END;
- /* Local variables accessed by a register + offset */
+ /* variables accessed by a register + offset */
if (ops->atom == (DW_OP_breg0 + data->reg) &&
check_allowed_ops(ops, nops) &&
match_var_offset(die_mem, data, data->offset, ops->number,
- /*is_pointer=*/false))
+ /*is_pointer=*/is_breg_access_indirect(ops, nops)))
return DIE_FIND_CB_END;
} else {
/* pointer variables saved in a register 32 or above */
@@ -1478,11 +1510,11 @@ static int __die_find_var_reg_cb(Dwarf_Die *die_mem, void *arg)
/*is_pointer=*/true))
return DIE_FIND_CB_END;
- /* Local variables accessed by a register + offset */
+ /* variables accessed by a register + offset */
if (ops->atom == DW_OP_bregx && data->reg == ops->number &&
check_allowed_ops(ops, nops) &&
match_var_offset(die_mem, data, data->offset, ops->number2,
- /*is_poitner=*/false))
+ /*is_pointer=*/is_breg_access_indirect(ops, nops)))
return DIE_FIND_CB_END;
}
}
--
2.50.1.470.g6ba607880d-goog
next prev parent reply other threads:[~2025-07-25 20:28 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-07-25 20:28 [PATCH v1 0/6] perf tools: Some improvements on data type profiler Zecheng Li
2025-07-25 20:28 ` [PATCH v1 1/6] perf dwarf-aux: Use signed comparison in match_var_offset Zecheng Li
2025-07-26 0:58 ` Ian Rogers
2025-07-26 23:56 ` Namhyung Kim
2025-07-25 20:28 ` Zecheng Li [this message]
2025-07-27 0:14 ` [PATCH v1 2/6] perf dwarf-aux: More accurate variable type match for breg Namhyung Kim
2025-07-25 20:28 ` [PATCH v1 3/6] perf dwarf-aux: Better type matching for stack variables Zecheng Li
2025-07-26 1:17 ` Ian Rogers
2025-07-27 0:22 ` Namhyung Kim
2025-07-25 20:28 ` [PATCH v1 4/6] perf annotate: Skip annotating data types to lea instructions Zecheng Li
2025-07-26 1:19 ` Ian Rogers
2025-07-25 20:28 ` [PATCH v1 5/6] perf dwarf-aux: Find pointer type to a type Zecheng Li
2025-07-27 0:24 ` Namhyung Kim
2025-07-25 20:28 ` [PATCH v1 6/6] perf annotate: Track arithmetic instructions on pointers Zecheng Li
2025-07-27 0:32 ` Namhyung Kim
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=20250725202809.1230085-3-zecheng@google.com \
--to=zecheng@google.com \
--cc=acme@kernel.org \
--cc=adrian.hunter@intel.com \
--cc=alexander.shishkin@linux.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=mark.rutland@arm.com \
--cc=mhiramat@kernel.org \
--cc=mingo@redhat.com \
--cc=namhyung@kernel.org \
--cc=peterz@infradead.org \
--cc=xliuprof@google.com \
--cc=zli94@ncsu.edu \
/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;
as well as URLs for NNTP newsgroup(s).