linux-kernel - [PATCH 15/52] perf annotate: Check if operand has multiple regs

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20231110000012.3538610-16-namhyung@kernel.org>
Date:   Thu,  9 Nov 2023 15:59:34 -0800
From:   Namhyung Kim <namhyung@...nel.org>
To:     Arnaldo Carvalho de Melo <acme@...nel.org>,
        Jiri Olsa <jolsa@...nel.org>,
        Peter Zijlstra <peterz@...radead.org>
Cc:     Ian Rogers <irogers@...gle.com>,
        Adrian Hunter <adrian.hunter@...el.com>,
        Ingo Molnar <mingo@...nel.org>,
        LKML <linux-kernel@...r.kernel.org>,
        linux-perf-users@...r.kernel.org,
        Linus Torvalds <torvalds@...ux-foundation.org>,
        Stephane Eranian <eranian@...gle.com>,
        Masami Hiramatsu <mhiramat@...nel.org>,
        Andi Kleen <ak@...ux.intel.com>,
        linux-trace-devel@...r.kernel.org, linux-toolchains@...r.kernel.org
Subject: [PATCH 15/52] perf annotate: Check if operand has multiple regs

It needs to check all possible information in an instruction.  Let's add
a field indicating if the operand has multiple registers.  I'll be used
to search type information like in an array access on x86 like:

  mov    0x10(%rax,%rbx,8), %rcx
             -------------
                 here

Signed-off-by: Namhyung Kim <namhyung@...nel.org>
---
 tools/perf/util/annotate.c | 36 ++++++++++++++++++++++++++++++++++++
 tools/perf/util/annotate.h |  2 ++
 2 files changed, 38 insertions(+)

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 83e0996992af..9e297adc8c59 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -85,6 +85,8 @@ struct arch {
 	struct		{
 		char comment_char;
 		char skip_functions_char;
+		char register_char;
+		char memory_ref_char;
 	} objdump;
 };
 
@@ -188,6 +190,8 @@ static struct arch architectures[] = {
 		.insn_suffix = "bwlq",
 		.objdump =  {
 			.comment_char = '#',
+			.register_char = '%',
+			.memory_ref_char = '(',
 		},
 	},
 	{
@@ -566,6 +570,34 @@ static struct ins_ops lock_ops = {
 	.scnprintf = lock__scnprintf,
 };
 
+/*
+ * Check if the operand has more than one registers like x86 SIB addressing:
+ *   0x1234(%rax, %rbx, 8)
+ *
+ * But it doesn't care segment selectors like %gs:0x5678(%rcx), so just check
+ * the input string after 'memory_ref_char' if exists.
+ */
+static bool check_multi_regs(struct arch *arch, const char *op)
+{
+	int count = 0;
+
+	if (arch->objdump.register_char == 0)
+		return false;
+
+	if (arch->objdump.memory_ref_char) {
+		op = strchr(op, arch->objdump.memory_ref_char);
+		if (op == NULL)
+			return false;
+	}
+
+	while ((op = strchr(op, arch->objdump.register_char)) != NULL) {
+		count++;
+		op++;
+	}
+
+	return count > 1;
+}
+
 static int mov__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms __maybe_unused)
 {
 	char *s = strchr(ops->raw, ','), *target, *comment, prev;
@@ -593,6 +625,8 @@ static int mov__parse(struct arch *arch, struct ins_operands *ops, struct map_sy
 	if (ops->source.raw == NULL)
 		return -1;
 
+	ops->source.multi_regs = check_multi_regs(arch, ops->source.raw);
+
 	target = skip_spaces(++s);
 	comment = strchr(s, arch->objdump.comment_char);
 
@@ -613,6 +647,8 @@ static int mov__parse(struct arch *arch, struct ins_operands *ops, struct map_sy
 	if (ops->target.raw == NULL)
 		goto out_free_source;
 
+	ops->target.multi_regs = check_multi_regs(arch, ops->target.raw);
+
 	if (comment == NULL)
 		return 0;
 
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index e8b0173f5f00..4ebc6407c68a 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -39,12 +39,14 @@ struct ins_operands {
 		s64	offset;
 		bool	offset_avail;
 		bool	outside;
+		bool	multi_regs;
 	} target;
 	union {
 		struct {
 			char	*raw;
 			char	*name;
 			u64	addr;
+			bool	multi_regs;
 		} source;
 		struct {
 			struct ins	    ins;
-- 
2.42.0.869.gea05f2083d-goog