linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Andi Kleen <andi@firstfloor.org>
To: acme@kernel.org
Cc: jolsa@kernel.org, linux-perf-users@vger.kernel.org,
	linux-kernel@vger.kernel.org, Andi Kleen <ak@linux.intel.com>
Subject: [PATCH v5 02/15] perf tools script: Support insn output for normal samples
Date: Fri,  8 Mar 2019 21:56:15 -0800	[thread overview]
Message-ID: <20190309055628.21617-3-andi@firstfloor.org> (raw)
In-Reply-To: <20190309055628.21617-1-andi@firstfloor.org>

From: Andi Kleen <ak@linux.intel.com>

perf script -F +insn was only working for PT traces because
the PT instruction decoder was filling in the insn/insn_len
sample attributes. Support it for non PT samples too on x86
using the existing x86 instruction decoder.

This adds some extra checking to ensure that we don't try
to decode instructions when using perf.data from a different
architecture.

% perf record -a sleep 1
% perf script -F ip,sym,insn --xed
 ffffffff811704c9 remote_function               movl  %eax, 0x18(%rbx)
 ffffffff8100bb50 intel_bts_enable_local                retq
 ffffffff81048612 native_apic_mem_write                 movl  %esi, -0xa04000(%rdi)
 ffffffff81048612 native_apic_mem_write                 movl  %esi, -0xa04000(%rdi)
 ffffffff81048612 native_apic_mem_write                 movl  %esi, -0xa04000(%rdi)
 ffffffff810f1f79 generic_exec_single           xor %eax, %eax
 ffffffff811704c9 remote_function               movl  %eax, 0x18(%rbx)
 ffffffff8100bb34 intel_bts_enable_local                movl  0x2000(%rax), %edx
 ffffffff81048610 native_apic_mem_write                 mov %edi, %edi
...

Signed-off-by: Andi Kleen <ak@linux.intel.com>

---
v2:
Avoid printing instruction when empty
Only decode when perf.data file was collected on same architecture
---
 tools/perf/arch/x86/util/Build      |  1 +
 tools/perf/arch/x86/util/archinsn.c | 28 ++++++++++++++++++++++++++++
 tools/perf/builtin-script.c         | 21 ++++++++++++++++++++-
 tools/perf/util/archinsn.h          | 12 ++++++++++++
 4 files changed, 61 insertions(+), 1 deletion(-)
 create mode 100644 tools/perf/arch/x86/util/archinsn.c
 create mode 100644 tools/perf/util/archinsn.h

diff --git a/tools/perf/arch/x86/util/Build b/tools/perf/arch/x86/util/Build
index 7aab0be5fc5f..7b8e69bbbdfe 100644
--- a/tools/perf/arch/x86/util/Build
+++ b/tools/perf/arch/x86/util/Build
@@ -6,6 +6,7 @@ perf-y += perf_regs.o
 perf-y += group.o
 perf-y += machine.o
 perf-y += event.o
+perf-y += archinsn.o
 
 perf-$(CONFIG_DWARF) += dwarf-regs.o
 perf-$(CONFIG_BPF_PROLOGUE) += dwarf-regs.o
diff --git a/tools/perf/arch/x86/util/archinsn.c b/tools/perf/arch/x86/util/archinsn.c
new file mode 100644
index 000000000000..10b3c2a08b8f
--- /dev/null
+++ b/tools/perf/arch/x86/util/archinsn.c
@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "perf.h"
+#include "archinsn.h"
+#include "fetch.h"
+#include "util/intel-pt-decoder/insn.h"
+#include "machine.h"
+#include "thread.h"
+#include "symbol.h"
+
+void arch_fetch_insn(struct perf_sample *sample,
+		     struct thread *thread,
+		     struct machine *machine)
+{
+	struct insn insn;
+	int len;
+	bool is64bit = false;
+
+	if (!sample->ip)
+		return;
+	len = fetch_exe(sample->ip, thread, machine, sample->insn,
+			sizeof(sample->insn), &is64bit);
+	if (len <= 0)
+		return;
+	insn_init(&insn, sample->insn, len, is64bit);
+	insn_get_length(&insn);
+	if (insn_complete(&insn) && insn.length <= len)
+		sample->insn_len = insn.length;
+}
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 2d8cb1d1682c..fbc440bdf880 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -29,10 +29,12 @@
 #include "util/time-utils.h"
 #include "util/path.h"
 #include "print_binary.h"
+#include "archinsn.h"
 #include <linux/bitmap.h>
 #include <linux/kernel.h>
 #include <linux/stringify.h>
 #include <linux/time64.h>
+#include <sys/utsname.h>
 #include "asm/bug.h"
 #include "util/mem-events.h"
 #include "util/dump-insn.h"
@@ -63,6 +65,7 @@ static const char		*cpu_list;
 static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 static struct perf_stat_config	stat_config;
 static int			max_blocks;
+static bool			native_arch;
 
 unsigned int scripting_max_stack = PERF_MAX_STACK_DEPTH;
 
@@ -1227,6 +1230,12 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample,
 	return len + dlen;
 }
 
+__weak void arch_fetch_insn(struct perf_sample *sample __maybe_unused,
+			    struct thread *thread __maybe_unused,
+			    struct machine *machine __maybe_unused)
+{
+}
+
 static int perf_sample__fprintf_insn(struct perf_sample *sample,
 				     struct perf_event_attr *attr,
 				     struct thread *thread,
@@ -1234,9 +1243,12 @@ static int perf_sample__fprintf_insn(struct perf_sample *sample,
 {
 	int printed = 0;
 
+	if (sample->insn_len == 0 && native_arch)
+		arch_fetch_insn(sample, thread, machine);
+
 	if (PRINT_FIELD(INSNLEN))
 		printed += fprintf(fp, " ilen: %d", sample->insn_len);
-	if (PRINT_FIELD(INSN)) {
+	if (PRINT_FIELD(INSN) && sample->insn_len) {
 		int i;
 
 		printed += fprintf(fp, " insn:");
@@ -3277,6 +3289,7 @@ int cmd_script(int argc, const char **argv)
 		.set = false,
 		.default_no_sample = true,
 	};
+	struct utsname uts;
 	char *script_path = NULL;
 	const char **__argv;
 	int i, j, err = 0;
@@ -3615,6 +3628,12 @@ int cmd_script(int argc, const char **argv)
 	if (symbol__init(&session->header.env) < 0)
 		goto out_delete;
 
+	uname(&uts);
+	if (!strcmp(uts.machine, session->header.env.arch) ||
+		(!strcmp(uts.machine, "x86_64") &&
+		 !strcmp(session->header.env.arch, "i386")))
+		native_arch = true;
+
 	script.session = session;
 	script__setup_sample_type(&script);
 
diff --git a/tools/perf/util/archinsn.h b/tools/perf/util/archinsn.h
new file mode 100644
index 000000000000..448cbb6b8d7e
--- /dev/null
+++ b/tools/perf/util/archinsn.h
@@ -0,0 +1,12 @@
+#ifndef INSN_H
+#define INSN_H 1
+
+struct perf_sample;
+struct machine;
+struct thread;
+
+void arch_fetch_insn(struct perf_sample *sample,
+		     struct thread *thread,
+		     struct machine *machine);
+
+#endif
-- 
2.20.1


  parent reply	other threads:[~2019-03-09  5:58 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-03-09  5:56 Support sample context in perf report Andi Kleen
2019-03-09  5:56 ` [PATCH v5 01/15] perf tools: Add utility function to fetch executable Andi Kleen
2019-03-11 12:32   ` Jiri Olsa
2019-03-09  5:56 ` Andi Kleen [this message]
2019-03-09  5:56 ` [PATCH v5 03/15] perf tools script: Filter COMM/FORK/.. events by CPU Andi Kleen
2019-03-11 12:32   ` Jiri Olsa
2019-03-09  5:56 ` [PATCH v5 04/15] perf tools report: Support nano seconds Andi Kleen
2019-03-09  5:56 ` [PATCH v5 05/15] perf tools report: Parse time quantum Andi Kleen
2019-03-09  5:56 ` [PATCH v5 06/15] perf tools report: Support time sort key Andi Kleen
2019-03-09  5:56 ` [PATCH v5 07/15] perf tools report: Use less for scripts output Andi Kleen
2019-03-22 22:07   ` [tip:perf/urgent] perf " tip-bot for Andi Kleen
2019-03-09  5:56 ` [PATCH v5 08/15] perf tools report: Support running scripts for current time range Andi Kleen
2019-03-09  5:56 ` [PATCH v5 09/15] perf tools report: Support builtin perf script in scripts menu Andi Kleen
2019-03-09  5:56 ` [PATCH v5 10/15] perf tools: Add utility function to print ns time stamps Andi Kleen
2019-03-09  5:56 ` [PATCH v5 11/15] perf tools report: Implement browsing of individual samples Andi Kleen
2019-03-11 12:32   ` Jiri Olsa
2019-03-09  5:56 ` [PATCH v5 12/15] perf tools: Add some new tips describing the new options Andi Kleen
2019-03-09  5:56 ` [PATCH v5 13/15] perf tools report: Add custom scripts to script menu Andi Kleen
2019-03-09  5:56 ` [PATCH v5 14/15] perf tools script: Add array bound checking to list_scripts Andi Kleen
2019-03-09  5:56 ` [PATCH v5 15/15] perf tools ui: Fix ui popup browser for many entries Andi Kleen

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=20190309055628.21617-3-andi@firstfloor.org \
    --to=andi@firstfloor.org \
    --cc=acme@kernel.org \
    --cc=ak@linux.intel.com \
    --cc=jolsa@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-perf-users@vger.kernel.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).