linux-toolchains.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Namhyung Kim <namhyung@kernel.org>
To: Arnaldo Carvalho de Melo <acme@kernel.org>, Jiri Olsa <jolsa@kernel.org>
Cc: Ian Rogers <irogers@google.com>,
	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,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Stephane Eranian <eranian@google.com>,
	Masami Hiramatsu <mhiramat@kernel.org>,
	linux-toolchains@vger.kernel.org,
	linux-trace-devel@vger.kernel.org
Subject: [PATCH 9/9] perf dwarf-aux: Check allowed DWARF Ops
Date: Tue, 16 Jan 2024 22:26:57 -0800	[thread overview]
Message-ID: <20240117062657.985479-10-namhyung@kernel.org> (raw)
In-Reply-To: <20240117062657.985479-1-namhyung@kernel.org>

The DWARF location expression can be fairly complex and it'd be hard
to match it with the condition correctly.  So let's be conservative
and only allow simple expressions.  For now it just checks the first
operation in the list.  The following operations looks ok:

 * DW_OP_stack_value
 * DW_OP_deref_size
 * DW_OP_deref
 * DW_OP_piece

To refuse complex (and unsupported) location expressions, add
check_allowed_ops() to compare the rest of the list.  It seems earlier
result contained those unsupported expressions.  For example, I found
some local struct variable is placed like below.

 <2><43d1517>: Abbrev Number: 62 (DW_TAG_variable)
    <43d1518>   DW_AT_location    : 15 byte block: 91 50 93 8 91 78 93 4 93 84 8 91 68 93 4
        (DW_OP_fbreg: -48; DW_OP_piece: 8;
         DW_OP_fbreg: -8; DW_OP_piece: 4;
         DW_OP_piece: 1028;
         DW_OP_fbreg: -24; DW_OP_piece: 4)

Another example is something like this.

    0057c8be ffffffffffffffff ffffffff812109f0 (base address)
    0057c8ce ffffffff812112b5 ffffffff812112c8 (DW_OP_breg3 (rbx): 0;
                                                DW_OP_constu: 18446744073709551612;
                                                DW_OP_and;
                                                DW_OP_stack_value)

It should refuse them.  After the change, the stat shows:

  Annotate data type stats:
  total 294, ok 158 (53.7%), bad 136 (46.3%)
  -----------------------------------------------------------
          30 : no_sym
          32 : no_mem_ops
          53 : no_var
          14 : no_typeinfo
           7 : bad_offset

Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/dwarf-aux.c | 44 +++++++++++++++++++++++++++++++++----
 1 file changed, 40 insertions(+), 4 deletions(-)

diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index 7caf52fdc255..2791126069b4 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -1305,6 +1305,34 @@ static bool match_var_offset(Dwarf_Die *die_mem, struct find_var_data *data,
 	return true;
 }
 
+static bool check_allowed_ops(Dwarf_Op *ops, size_t nops)
+{
+	/* The first op is checked separately */
+	ops++;
+	nops--;
+
+	/*
+	 * It needs to make sure if the location expression matches to the given
+	 * register and offset exactly.  Thus it rejects any complex expressions
+	 * and only allows a few of selected operators that doesn't change the
+	 * location.
+	 */
+	while (nops) {
+		switch (ops->atom) {
+		case DW_OP_stack_value:
+		case DW_OP_deref_size:
+		case DW_OP_deref:
+		case DW_OP_piece:
+			break;
+		default:
+			return false;
+		}
+		ops++;
+		nops--;
+	}
+	return true;
+}
+
 /* Only checks direct child DIEs in the given scope. */
 static int __die_find_var_reg_cb(Dwarf_Die *die_mem, void *arg)
 {
@@ -1332,25 +1360,31 @@ static int __die_find_var_reg_cb(Dwarf_Die *die_mem, void *arg)
 		/* Local variables accessed using frame base register */
 		if (data->is_fbreg && ops->atom == DW_OP_fbreg &&
 		    data->offset >= (int)ops->number &&
+		    check_allowed_ops(ops, nops) &&
 		    match_var_offset(die_mem, data, data->offset, ops->number))
 			return DIE_FIND_CB_END;
 
 		/* Only match with a simple case */
 		if (data->reg < DWARF_OP_DIRECT_REGS) {
-			if (ops->atom == (DW_OP_reg0 + data->reg) && nops == 1)
+			/* pointer variables saved in a register 0 to 31 */
+			if (ops->atom == (DW_OP_reg0 + data->reg) &&
+			    check_allowed_ops(ops, nops))
 				return DIE_FIND_CB_END;
 
 			/* Local 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))
 				return DIE_FIND_CB_END;
 		} else {
+			/* pointer variables saved in a register 32 or above */
 			if (ops->atom == DW_OP_regx && ops->number == data->reg &&
-			    nops == 1)
+			    check_allowed_ops(ops, nops))
 				return DIE_FIND_CB_END;
 
 			/* Local 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))
 				return DIE_FIND_CB_END;
 		}
@@ -1412,7 +1446,8 @@ static int __die_find_var_addr_cb(Dwarf_Die *die_mem, void *arg)
 		if (data->addr < ops->number)
 			continue;
 
-		if (match_var_offset(die_mem, data, data->addr, ops->number))
+		if (check_allowed_ops(ops, nops) &&
+		    match_var_offset(die_mem, data, data->addr, ops->number))
 			return DIE_FIND_CB_END;
 	}
 	return DIE_FIND_CB_SIBLING;
@@ -1503,7 +1538,8 @@ int die_get_cfa(Dwarf *dwarf, u64 pc, int *preg, int *poffset)
 		return -1;
 
 	if (!dwarf_cfi_addrframe(cfi, pc, &frame) &&
-	    !dwarf_frame_cfa(frame, &ops, &nops) && nops == 1) {
+	    !dwarf_frame_cfa(frame, &ops, &nops) &&
+	    check_allowed_ops(ops, nops)) {
 		*preg = reg_from_dwarf_op(ops);
 		*poffset = offset_from_dwarf_op(ops);
 		return 0;
-- 
2.43.0.381.gb435a96ce8-goog


  parent reply	other threads:[~2024-01-17  6:27 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-01-17  6:26 [PATCHSET 0/9] perf tools: More updates on data type profiling (v4) Namhyung Kim
2024-01-17  6:26 ` [PATCH 1/9] perf annotate-data: Parse 'lock' prefix from llvm-objdump Namhyung Kim
2024-01-17  6:26 ` [PATCH 2/9] perf annotate-data: Handle macro fusion on x86 Namhyung Kim
2024-01-17  6:26 ` [PATCH 3/9] perf annotate-data: Handle array style accesses Namhyung Kim
2024-01-17  6:26 ` [PATCH 4/9] perf annotate-data: Add stack operation pseudo type Namhyung Kim
2024-01-17  6:26 ` [PATCH 5/9] perf annotate-data: Handle PC-relative addressing Namhyung Kim
2024-01-17  6:26 ` [PATCH 6/9] perf annotate-data: Support global variables Namhyung Kim
2024-01-17  6:26 ` [PATCH 7/9] perf dwarf-aux: Add die_get_cfa() Namhyung Kim
2024-01-17  6:26 ` [PATCH 8/9] perf annotate-data: Support stack variables Namhyung Kim
2024-01-17  6:26 ` Namhyung Kim [this message]
2024-01-18 16:36 ` [PATCHSET 0/9] perf tools: More updates on data type profiling (v4) Ian Rogers
2024-01-22 20:37 ` 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=20240117062657.985479-10-namhyung@kernel.org \
    --to=namhyung@kernel.org \
    --cc=acme@kernel.org \
    --cc=adrian.hunter@intel.com \
    --cc=eranian@google.com \
    --cc=irogers@google.com \
    --cc=jolsa@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-perf-users@vger.kernel.org \
    --cc=linux-toolchains@vger.kernel.org \
    --cc=linux-trace-devel@vger.kernel.org \
    --cc=mhiramat@kernel.org \
    --cc=mingo@kernel.org \
    --cc=peterz@infradead.org \
    --cc=torvalds@linux-foundation.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;
as well as URLs for NNTP newsgroup(s).