All of lore.kernel.org
 help / color / mirror / Atom feed
From: Andi Kleen <andi@firstfloor.org>
To: acme@kernel.org
Cc: jolsa@kernel.org, linux-kernel@vger.kernel.org,
	Andi Kleen <ak@linux.intel.com>,
	adrian.hunter@intel.com
Subject: [PATCH 4/5] perf, tools, script: Add support for printing assembler
Date: Wed, 18 Jan 2017 17:41:49 -0800	[thread overview]
Message-ID: <20170119014150.19218-5-andi@firstfloor.org> (raw)
In-Reply-To: <20170119014150.19218-1-andi@firstfloor.org>

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

When dumping PT traces with perf script it is very useful to see the
assembler for each sample, so that it is easily possible to follow
the control flow.

As using objdump is difficult and inefficient from perf script this
patch uses the Intel xed library to implement assembler output.
The library can be downloaded from http://github.com/intelxed/xed

The previous version of this patch used udis86, but was
rejected because udis86 was unmaintained and a runtime dependency.
Using the recently released xed avoids both of these problems:
- XED is well maintained and used by many Intel tools
- XED is linked statically so there is no runtime dependency.

The library is probed as an external dependency in the usual way. Then perf
script calls into it when needed, and handles callbacks to resolve
symbols.

% perf record -e intel_pt//u true
% perf script -F sym,symoff,ip,asm --itrace=i0ns | head
     7fc7188b4190 _start+0x0	mov %rsp, %rdi
     7fc7188b4193 _start+0x3	call _dl_start
     7fc7188b7710 _dl_start+0x0	push %rbp
     7fc7188b7711 _dl_start+0x1	mov %rsp, %rbp
     7fc7188b7714 _dl_start+0x4	push %r15
     7fc7188b7716 _dl_start+0x6	push %r14
     7fc7188b7718 _dl_start+0x8	push %r13
     7fc7188b771a _dl_start+0xa	push %r12
     7fc7188b771c _dl_start+0xc	mov %rdi, %r12
     7fc7188b771f _dl_start+0xf	push %rbx

v2:
Converted to use XED instead of udis86.
Separate disassembler interface into separate arch specific file.
Lots of cleanups and improvements.

Cc: adrian.hunter@intel.com
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/Documentation/perf-script.txt |  4 +-
 tools/perf/builtin-script.c              | 72 +++++++++++++++++++++++++++-----
 2 files changed, 64 insertions(+), 12 deletions(-)

diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 4ed5f239ba7d..497989ea9768 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -116,7 +116,7 @@ OPTIONS
 --fields::
         Comma separated list of fields to print. Options are:
         comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff,
-        srcline, period, iregs, brstack, brstacksym, flags, bpf-output,
+        srcline, period, iregs, brstack, brstacksym, flags, bpf-output, asm.
         callindent, insn, insnlen. Field list can be prepended with the type, trace, sw or hw,
         to indicate to which event type the field list applies.
         e.g., -F sw:comm,tid,time,ip,sym  and -F trace:time,cpu,trace
@@ -198,6 +198,8 @@ OPTIONS
 
 	The brstacksym is identical to brstack, except that the FROM and TO addresses are printed in a symbolic form if possible.
 
+	When asm is specified the assembler instruction of each sample is printed in disassembled form.
+
 -k::
 --vmlinux=<file>::
         vmlinux pathname
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index c0783b4f7b6c..7a09c4f7df3f 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -28,6 +28,7 @@
 #include <linux/time64.h>
 #include "asm/bug.h"
 #include "util/mem-events.h"
+#include "util/dis.h"
 
 static char const		*script_name;
 static char const		*generate_script_lang;
@@ -69,6 +70,7 @@ enum perf_output_field {
 	PERF_OUTPUT_CALLINDENT	    = 1U << 20,
 	PERF_OUTPUT_INSN	    = 1U << 21,
 	PERF_OUTPUT_INSNLEN	    = 1U << 22,
+	PERF_OUTPUT_ASM		    = 1U << 23,
 };
 
 struct output_option {
@@ -98,6 +100,7 @@ struct output_option {
 	{.str = "callindent", .field = PERF_OUTPUT_CALLINDENT},
 	{.str = "insn", .field = PERF_OUTPUT_INSN},
 	{.str = "insnlen", .field = PERF_OUTPUT_INSNLEN},
+	{.str = "asm", .field = PERF_OUTPUT_ASM},
 };
 
 /* default set to maintain compatibility with current format */
@@ -292,7 +295,11 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 		       "selected. Hence, no address to lookup the source line number.\n");
 		return -EINVAL;
 	}
-
+	if (PRINT_FIELD(ASM) && !PRINT_FIELD(IP)) {
+		pr_err("Display of assembler requested but sample IP is not\n"
+		       "selected.\n");
+		return -EINVAL;
+	}
 	if ((PRINT_FIELD(PID) || PRINT_FIELD(TID)) &&
 		perf_evsel__check_stype(evsel, PERF_SAMPLE_TID, "TID",
 					PERF_OUTPUT_TID|PERF_OUTPUT_PID))
@@ -436,6 +443,39 @@ static void print_sample_iregs(struct perf_sample *sample,
 	}
 }
 
+static void print_sample_asm(union perf_event *event,
+			     struct perf_sample *sample,
+			     struct thread *thread,
+			     struct addr_location *al,
+			     struct machine *machine)
+{
+	struct perf_dis x;
+	u8 buffer[32];
+	int len;
+	u64 offset;
+
+	x.thread = thread;
+	x.cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+	x.cpu = sample->cpu;
+
+	if (!al->map || !al->map->dso)
+		return;
+	if (al->map->dso->data.status == DSO_DATA_STATUS_ERROR)
+		return;
+
+	/* Load maps to ensure dso->is_64_bit has been updated */
+	map__load(al->map);
+	x.is64bit = al->map->dso->is_64_bit;
+
+	offset = al->map->map_ip(al->map, sample->ip);
+	len = dso__data_read_offset(al->map->dso, machine,
+				    offset, buffer, MAXINSN);
+	if (len <= 0)
+		return;
+
+	printf("\t%s", disas_inst(&x, sample->ip, buffer, len, NULL));
+}
+
 static void print_sample_start(struct perf_sample *sample,
 			       struct thread *thread,
 			       struct perf_evsel *evsel)
@@ -631,8 +671,12 @@ static void print_sample_callindent(struct perf_sample *sample,
 		printf("%*s", spacing - len, "");
 }
 
-static void print_insn(struct perf_sample *sample,
-		       struct perf_event_attr *attr)
+static void print_insn(union perf_event *event,
+		       struct perf_sample *sample,
+		       struct perf_event_attr *attr,
+		       struct thread *thread,
+		       struct addr_location *al,
+		       struct machine *machine)
 {
 	if (PRINT_FIELD(INSNLEN))
 		printf(" ilen: %d", sample->insn_len);
@@ -643,12 +687,16 @@ static void print_insn(struct perf_sample *sample,
 		for (i = 0; i < sample->insn_len; i++)
 			printf(" %02x", (unsigned char)sample->insn[i]);
 	}
+	if (PRINT_FIELD(ASM))
+		print_sample_asm(event, sample, thread, al, machine);
 }
 
-static void print_sample_bts(struct perf_sample *sample,
+static void print_sample_bts(union perf_event *event,
+			     struct perf_sample *sample,
 			     struct perf_evsel *evsel,
 			     struct thread *thread,
-			     struct addr_location *al)
+			     struct addr_location *al,
+			     struct machine *machine)
 {
 	struct perf_event_attr *attr = &evsel->attr;
 	bool print_srcline_last = false;
@@ -689,7 +737,7 @@ static void print_sample_bts(struct perf_sample *sample,
 	if (print_srcline_last)
 		map__fprintf_srcline(al->map, al->addr, "\n  ", stdout);
 
-	print_insn(sample, attr);
+	print_insn(event, sample, attr, thread, al, machine);
 
 	printf("\n");
 }
@@ -871,7 +919,9 @@ static size_t data_src__printf(u64 data_src)
 
 static void process_event(struct perf_script *script,
 			  struct perf_sample *sample, struct perf_evsel *evsel,
-			  struct addr_location *al)
+			  struct addr_location *al,
+			  struct machine *machine,
+			  union perf_event *event)
 {
 	struct thread *thread = al->thread;
 	struct perf_event_attr *attr = &evsel->attr;
@@ -898,7 +948,7 @@ static void process_event(struct perf_script *script,
 		print_sample_flags(sample->flags);
 
 	if (is_bts_event(attr)) {
-		print_sample_bts(sample, evsel, thread, al);
+		print_sample_bts(event, sample, evsel, thread, al, machine);
 		return;
 	}
 
@@ -936,7 +986,7 @@ static void process_event(struct perf_script *script,
 
 	if (perf_evsel__is_bpf_output(evsel) && PRINT_FIELD(BPF_OUTPUT))
 		print_sample_bpf_output(sample);
-	print_insn(sample, attr);
+	print_insn(event, sample, attr, thread, al, machine);
 	printf("\n");
 }
 
@@ -1046,7 +1096,7 @@ static int process_sample_event(struct perf_tool *tool,
 	if (scripting_ops)
 		scripting_ops->process_event(event, sample, evsel, &al);
 	else
-		process_event(scr, sample, evsel, &al);
+		process_event(scr, sample, evsel, &al, machine, event);
 
 out_put:
 	addr_location__put(&al);
@@ -2152,7 +2202,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 		     "Valid types: hw,sw,trace,raw. "
 		     "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
 		     "addr,symoff,period,iregs,brstack,brstacksym,flags,"
-		     "bpf-output,callindent,insn,insnlen", parse_output_fields),
+		     "bpf-output,callindent,insn,insnlen,asm", parse_output_fields),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,
 		    "system-wide collection from all CPUs"),
 	OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
-- 
2.9.3

  parent reply	other threads:[~2017-01-19  1:43 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-01-19  1:41 New attempt at adding an disassembler to perf Andi Kleen
2017-01-19  1:41 ` [PATCH 1/5] perf, tools: Add probing for xed Andi Kleen
2017-01-19  1:41 ` [PATCH 2/5] perf, tools: Add one liner warning for disabled features Andi Kleen
2017-01-19  1:41 ` [PATCH 3/5] perf, tools: Add disassembler for x86 using the XED library Andi Kleen
2017-01-19  1:41 ` Andi Kleen [this message]
2017-01-23 19:49   ` [PATCH 4/5] perf, tools, script: Add support for printing assembler Arnaldo Carvalho de Melo
2017-01-23 19:55     ` Andi Kleen
2017-01-23 20:06       ` Arnaldo Carvalho de Melo
2017-01-19  1:41 ` [PATCH 5/5] perf, tools, script: Add brstackasm output for branch stacks Andi Kleen
2017-01-24 18:54   ` Arnaldo Carvalho de Melo
2017-01-19 15:36 ` New attempt at adding an disassembler to perf Jiri Olsa
2017-01-19 16:54   ` Andi Kleen
2017-01-20 13:22 ` Jiri Olsa
  -- strict thread matches above, loose matches on Subject: below --
2017-01-10  1:02 New attempt at adding an disassembler to perf v2 Andi Kleen
2017-01-10  1:02 ` [PATCH 4/5] perf, tools, script: Add support for printing assembler 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=20170119014150.19218-5-andi@firstfloor.org \
    --to=andi@firstfloor.org \
    --cc=acme@kernel.org \
    --cc=adrian.hunter@intel.com \
    --cc=ak@linux.intel.com \
    --cc=jolsa@kernel.org \
    --cc=linux-kernel@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 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.