All of lore.kernel.org
 help / color / mirror / Atom feed
From: Namhyung Kim <namhyung@kernel.org>
To: Arnaldo Carvalho de Melo <acme@kernel.org>,
	Jiri Olsa <jolsa@kernel.org>,
	Peter Zijlstra <peterz@infradead.org>
Cc: Ian Rogers <irogers@google.com>,
	Adrian Hunter <adrian.hunter@intel.com>,
	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>,
	Andi Kleen <ak@linux.intel.com>,
	linux-trace-devel@vger.kernel.org,
	linux-toolchains@vger.kernel.org
Subject: [PATCH 37/52] perf dwarf-aux: Check allowed DWARF Ops
Date: Thu,  9 Nov 2023 15:59:56 -0800	[thread overview]
Message-ID: <20231110000012.3538610-38-namhyung@kernel.org> (raw)
In-Reply-To: <20231110000012.3538610-1-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;
-- 
2.42.0.869.gea05f2083d-goog


  parent reply	other threads:[~2023-11-10  0:03 UTC|newest]

Thread overview: 69+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-11-09 23:59 [RFC 00/52] perf tools: Introduce data type profiling (v2) Namhyung Kim
2023-11-09 23:59 ` [PATCH 01/52] perf annotate: Pass "-l" option to objdump conditionally Namhyung Kim
2023-11-09 23:59 ` [PATCH 02/52] perf annotate: Move raw_comment and raw_func_start Namhyung Kim
2023-11-09 23:59 ` [PATCH 03/52] perf tools: Add util/debuginfo.[ch] files Namhyung Kim
2023-11-09 23:59 ` [PATCH 04/52] perf dwarf-aux: Fix die_get_typename() for void * Namhyung Kim
2023-11-09 23:59 ` [PATCH 05/52] perf dwarf-aux: Move #ifdef code to the header file Namhyung Kim
2023-11-09 23:59 ` [PATCH 06/52] perf dwarf-aux: Add die_get_scopes() helper Namhyung Kim
2023-11-09 23:59 ` [PATCH 07/52] perf dwarf-aux: Add die_find_variable_by_reg() helper Namhyung Kim
2023-11-09 23:59 ` [PATCH 08/52] perf build: Add feature check for dwarf_getcfi() Namhyung Kim
2023-11-10 10:26   ` Masami Hiramatsu
2023-11-09 23:59 ` [PATCH 09/52] perf probe: Convert to check dwarf_getcfi feature Namhyung Kim
2023-11-10 10:25   ` Masami Hiramatsu
2023-11-09 23:59 ` [PATCH 10/52] perf dwarf-aux: Factor out die_get_typename_from_type() Namhyung Kim
2023-11-09 23:59 ` [PATCH 11/52] perf dwarf-regs: Add get_dwarf_regnum() Namhyung Kim
2023-11-09 23:59 ` [PATCH 12/52] perf annotate-data: Add find_data_type() Namhyung Kim
     [not found]   ` <CA+JHD90fkWNrQWO5DrHeV8mCmFyKKqJ8fV=KwztRi7TSw+8yDg@mail.gmail.com>
2023-11-20 20:43     ` Namhyung Kim
2023-11-09 23:59 ` [PATCH 13/52] perf annotate-data: Add dso->data_types tree Namhyung Kim
2023-12-21 20:10   ` Arnaldo Carvalho de Melo
2023-12-21 20:13     ` Arnaldo Carvalho de Melo
2023-12-21 20:32       ` Arnaldo Carvalho de Melo
2023-11-09 23:59 ` [PATCH 14/52] perf annotate: Factor out evsel__get_arch() Namhyung Kim
2023-12-23 14:14   ` Arnaldo Carvalho de Melo
2023-11-09 23:59 ` [PATCH 15/52] perf annotate: Check if operand has multiple regs Namhyung Kim
2023-11-09 23:59 ` [PATCH 16/52] perf annotate: Add annotate_get_insn_location() Namhyung Kim
2023-11-09 23:59 ` [PATCH 17/52] perf annotate: Implement hist_entry__get_data_type() Namhyung Kim
2023-11-09 23:59 ` [PATCH 18/52] perf report: Add 'type' sort key Namhyung Kim
2023-11-21 17:55   ` Arnaldo Carvalho de Melo
2023-11-22 18:49     ` Namhyung Kim
2023-11-22 19:54       ` Arnaldo Carvalho de Melo
2023-11-22 21:13         ` Namhyung Kim
2023-11-23 13:40           ` Arnaldo Carvalho de Melo
2023-11-09 23:59 ` [PATCH 19/52] perf report: Support data type profiling Namhyung Kim
2023-11-09 23:59 ` [PATCH 20/52] perf annotate-data: Add member field in the data type Namhyung Kim
2023-11-09 23:59 ` [PATCH 21/52] perf annotate-data: Update sample histogram for type Namhyung Kim
2023-11-09 23:59 ` [PATCH 22/52] perf report: Add 'typeoff' sort key Namhyung Kim
2023-11-09 23:59 ` [PATCH 23/52] perf report: Add 'symoff' " Namhyung Kim
2023-12-23 14:29   ` Arnaldo Carvalho de Melo
2023-11-09 23:59 ` [PATCH 24/52] perf annotate: Add --data-type option Namhyung Kim
2023-11-09 23:59 ` [PATCH 25/52] perf annotate: Support event group display Namhyung Kim
2023-11-09 23:59 ` [PATCH 26/52] perf annotate: Add --type-stat option for debugging Namhyung Kim
2023-11-09 23:59 ` [PATCH 27/52] perf annotate: Add --insn-stat " Namhyung Kim
2023-11-09 23:59 ` [PATCH 28/52] perf annotate-data: Parse 'lock' prefix from llvm-objdump Namhyung Kim
2023-11-09 23:59 ` [PATCH 29/52] perf annotate-data: Handle macro fusion on x86 Namhyung Kim
2023-11-09 23:59 ` [PATCH 30/52] perf annotate-data: Handle array style accesses Namhyung Kim
2023-11-09 23:59 ` [PATCH 31/52] perf annotate-data: Add stack operation pseudo type Namhyung Kim
2023-11-09 23:59 ` [PATCH 32/52] perf dwarf-aux: Add die_find_variable_by_addr() Namhyung Kim
2023-11-27 22:07   ` Arnaldo Carvalho de Melo
2023-11-09 23:59 ` [PATCH 33/52] perf annotate-data: Handle PC-relative addressing Namhyung Kim
2023-11-09 23:59 ` [PATCH 34/52] perf annotate-data: Support global variables Namhyung Kim
2023-11-09 23:59 ` [PATCH 35/52] perf dwarf-aux: Add die_get_cfa() Namhyung Kim
2023-11-09 23:59 ` [PATCH 36/52] perf annotate-data: Support stack variables Namhyung Kim
2023-11-09 23:59 ` Namhyung Kim [this message]
2023-11-09 23:59 ` [PATCH 38/52] perf dwarf-aux: Add die_collect_vars() Namhyung Kim
2023-11-09 23:59 ` [PATCH 39/52] perf dwarf-aux: Handle type transfer for memory access Namhyung Kim
2023-11-09 23:59 ` [PATCH 40/52] perf annotate-data: Introduce struct data_loc_info Namhyung Kim
2023-11-10  0:00 ` [PATCH 41/52] perf map: Add map__objdump_2rip() Namhyung Kim
2023-11-10  0:00 ` [PATCH 42/52] perf annotate: Add annotate_get_basic_blocks() Namhyung Kim
2023-11-10  0:00 ` [PATCH 43/52] perf annotate-data: Maintain variable type info Namhyung Kim
2023-11-10  0:00 ` [PATCH 44/52] perf annotate-data: Add update_insn_state() Namhyung Kim
2023-11-10  0:00 ` [PATCH 45/52] perf annotate-data: Handle global variable access Namhyung Kim
2023-11-10  0:00 ` [PATCH 46/52] perf annotate-data: Handle call instructions Namhyung Kim
2023-11-10  0:00 ` [PATCH 47/52] perf annotate-data: Implement instruction tracking Namhyung Kim
2023-11-10  0:00 ` [PATCH 48/52] perf annotate: Parse x86 segment register location Namhyung Kim
2023-11-10  0:00 ` [PATCH 49/52] perf annotate-data: Handle this-cpu variables in kernel Namhyung Kim
2023-11-10  0:00 ` [PATCH 50/52] perf annotate-data: Track instructions with a this-cpu variable Namhyung Kim
2023-11-10  0:00 ` [PATCH 51/52] perf annotate-data: Add stack canary type Namhyung Kim
2023-11-10  0:00 ` [PATCH 52/52] perf annotate-data: Add debug message Namhyung Kim
2023-11-10 12:05 ` [RFC 00/52] perf tools: Introduce data type profiling (v2) Arnaldo Carvalho de Melo
2023-11-11  2:27   ` 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=20231110000012.3538610-38-namhyung@kernel.org \
    --to=namhyung@kernel.org \
    --cc=acme@kernel.org \
    --cc=adrian.hunter@intel.com \
    --cc=ak@linux.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.