Skip to contentSkip to conversation

New attempt at adding an disassembler to perf v2

PATCH In review Andi Kleen 4 participants 16 messages Jan 10, 2017 – Jan 18, 2017 perf events

lore
Share & tools
lore

Andi Kleen

author
#0 lore raw

A native disassembler in perf is very useful, in particular with perf script to trace instruction streams, but also for other analysis. Previously I attempted to do this using the udis86 library, but that was rejected because:
- udis86 was not maintained anymore and lacking recent instructions
- udis86 is dynamically linked and gives a runtime dependency.
Doing this needs a full disassembler, not just a decoder, so the existing instruction decoder cannot be used without major changes.

This patchkit addresses these issues. Intel recently released an open source version of the XED disassembler library, which is used in many other Intel software. It is very well maintained, uptodate, and supports static linking, so there is no runtime dependency. This version adds XED support to perf, and uses it to implement assembler output in perf script. It also fixes a range of issues in the previous version, see the individual change logs.

Available in
git://git.kernel.org/pub/scm/linux/kernel/git/ak/linux-misc.git perf/xed-4

v1: First post of XED version
v2: Change probing to not be default and support XED_DIR. Other cleanups based on review.

-Andi

author
#1 lore raw

PATCH 1/5 perf, tools: Add probing for xed

From: Andi Kleen <[email protected]>

Add autoprobing for the xed disassembler library.

Can be downloaded from https://github.com/intelxed/xed

v2: Hide. Require XED=1 to enable. Add XED_DIR

Signed-off-by Andi Kleen <[email protected]>
---
 tools/build/Makefile.feature   |  8 +++++---
 tools/build/feature/Makefile   |  8 ++++++--
 tools/build/feature/test-all.c |  5 +++++
 tools/build/feature/test-xed.c |  9 +++++++++
 tools/perf/Makefile.config     | 16 ++++++++++++++++
 tools/perf/Makefile.perf       |  3 +++
 6 files changed, 44 insertions(+), 5 deletions(-)
 create mode 100644 tools/build/feature/test-xed.c
tools/build/Makefile.feature +5 -3
index e3fb5ecbdcb6..971a9ef87ca6 100644
@@ -63,7 +63,7 @@ FEATURE_TESTS_BASIC :=                  \
         lzma                            \
         get_cpuid                       \
         bpf                             \
-        sdt
+	sdt				\
 
 # FEATURE_TESTS_BASIC + FEATURE_TESTS_EXTRA is the complete list
 # of all feature tests

@@ -74,11 +74,12 @@ FEATURE_TESTS_EXTRA :=                  \
          cplus-demangle                 \
          hello                          \
          libbabeltrace                  \
+	 xed				\
          liberty                        \
          liberty-z                      \
          libunwind-debug-frame          \
          libunwind-debug-frame-arm      \
-         libunwind-debug-frame-aarch64
+	 libunwind-debug-frame-aarch64
 
 FEATURE_TESTS ?= $(FEATURE_TESTS_BASIC)
 

@@ -105,7 +106,7 @@ FEATURE_DISPLAY ?=              \
          zlib                   \
          lzma                   \
          get_cpuid              \
-         bpf
+	 bpf
 
 # Set FEATURE_CHECK_(C|LD)FLAGS-all for all FEATURE_TESTS features.
 # If in the future we need per-feature checks/flags for features not

@@ -140,6 +141,7 @@ ifeq ($(feature-all), 1)
   $(call feature_check,compile-x32)
   $(call feature_check,bionic)
   $(call feature_check,libbabeltrace)
+  $(call feature_check,xed)
 else
   $(foreach feat,$(FEATURE_TESTS),$(call feature_check,$(feat)))
 endif
tools/build/feature/Makefile +6 -2
index b564a2eea039..a1275965c67d 100644
@@ -48,7 +48,8 @@ FILES=                                          \
          test-get_cpuid.bin                     \
          test-sdt.bin                           \
          test-cxx.bin                           \
-         test-jvmti.bin
+         test-jvmti.bin				\
+         test-xed.bin
 
 FILES := $(addprefix $(OUTPUT),$(FILES))
 

@@ -68,7 +69,7 @@ __BUILDXX = $(CXX) $(CXXFLAGS) -Wall -Werror -o $@ $(patsubst %.bin,%.cpp,$(@F))
 ###############################
 
 $(OUTPUT)test-all.bin:
-	$(BUILD) -fstack-protector-all -O2 -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -laudit -I/usr/include/slang -lslang $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null) $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl -lz -llzma
+	$(BUILD) -fstack-protector-all -O2 -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -laudit -I/usr/include/slang -lslang $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null) $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl -lz -llzma -lxed
 
 $(OUTPUT)test-hello.bin:
 	$(BUILD)

@@ -123,6 +124,9 @@ $(OUTPUT)test-numa_num_possible_cpus.bin:
 $(OUTPUT)test-libunwind.bin:
 	$(BUILD) -lelf
 
+$(OUTPUT)test-xed.bin:
+	$(BUILD) -lxed
+
 $(OUTPUT)test-libunwind-debug-frame.bin:
 	$(BUILD) -lelf
 $(OUTPUT)test-libunwind-x86.bin:
tools/build/feature/test-all.c +5 -0
index 699e43627397..4a6dd1d1ff49 100644
@@ -149,6 +149,10 @@
 # include "test-sdt.c"
 #undef main
 
+#define main main_test_xed
+#  include "test-xed.c"
+#endif
+
 int main(int argc, char *argv[])
 {
 	main_test_libpython();

@@ -183,6 +187,7 @@ int main(int argc, char *argv[])
 	main_test_bpf();
 	main_test_libcrypto();
 	main_test_sdt();
+	main_test_xed();
 
 	return 0;
 }
tools/build/feature/test-xed.c new file +9 -0
new file mode 100644
index 000000000000..ef9aebf1559d
@@ -0,0 +1,9 @@
+#include <xed/xed-interface.h>
+#include <xed/xed-decode.h>
+#include <xed/xed-decoded-inst-api.h>
+
+int main(void)
+{
+	xed_tables_init();
+	return 0;
+}
tools/perf/Makefile.config +16 -0
index 76c84f0eec52..05dfa31506b6 100644
@@ -682,6 +682,22 @@ ifndef NO_ZLIB
   endif
 endif
 
+ifdef XED
+  ifdef XED_DIR
+    FEATURE_CHECK_CFLAGS-xed := -I $(XED_DIR)/include
+    # override for lib64?
+    FEATURE_CHECK_LDFLAGS-xed := -L $(XED_DIR)/lib -lxed
+  else
+    FEATURE_CHECK_CFLAGS-xed :=
+    FEATURE_CHECK_LDFLAGS-xed := -lxed
+  endif
+  $(call feature_check,xed)
+  ifeq ($(feature-xed), 1)
+    EXTLIBS += -lxed
+    $(call detected,CONFIG_XED)
+  endif
+endif
+
 ifndef NO_LZMA
   ifeq ($(feature-lzma), 1)
     CFLAGS += -DHAVE_LZMA_SUPPORT
tools/perf/Makefile.perf +3 -0
index 8f1c258b151a..5f3413050b39 100644
@@ -84,6 +84,9 @@ include ../scripts/utilities.mak
 # Define NO_SDT if you do not want to define SDT event in perf tools,
 # note that it doesn't disable SDT scanning support.
 #
+# Define XED=1 to build WITH the XED disassembler for perf script
+# Can also set XED_DIR=/path to set XED directory.
+#
 # Define FEATURES_DUMP to provide features detection dump file
 # and bypass the feature detection
 #
Signature · 1 line
2.9.3
#2 lore raw

Re: [PATCH 1/5] perf, tools: Add probing for xed

Hi Andi,

just a very minor cosmetic detail, but your editor seems to use tabs while there were 8 spaces around, causing visual alignment defects below :

tools/build/Makefile.feature FEATURE_TESTS_BASIC := \ · line 66

Quoted 10 lines · Andi Kleen
tools/build/Makefile.feature +1 -1
index e3fb5ecbdcb6..971a9ef87ca6 100644
@@ -63,7 +63,7 @@ FEATURE_TESTS_BASIC :=                  \
         lzma                            \
         get_cpuid                       \
         bpf                             \
-        sdt
+	sdt				\

here

tools/build/Makefile.feature FEATURE_TESTS_EXTRA := \ · line 77

Quoted 7 lines
tools/build/Makefile.feature +1 -0
 # FEATURE_TESTS_BASIC + FEATURE_TESTS_EXTRA is the complete list
 # of all feature tests

@@ -74,11 +74,12 @@ FEATURE_TESTS_EXTRA :=                  \
          cplus-demangle                 \
          hello                          \
          libbabeltrace                  \
+	 xed				\

here

tools/build/Makefile.feature FEATURE_TESTS_EXTRA := \ · line 82

Quoted 6 lines
tools/build/Makefile.feature +1 -1
          liberty                        \
          liberty-z                      \
          libunwind-debug-frame          \
          libunwind-debug-frame-arm      \
-         libunwind-debug-frame-aarch64
+	 libunwind-debug-frame-aarch64

here

tools/build/Makefile.feature FEATURE_DISPLAY ?= \ · line 109

Quoted 9 lines
tools/build/Makefile.feature +1 -1
 FEATURE_TESTS ?= $(FEATURE_TESTS_BASIC)
 

@@ -105,7 +106,7 @@ FEATURE_DISPLAY ?=              \
          zlib                   \
          lzma                   \
          get_cpuid              \
-         bpf
+	 bpf

and here.

I think it would be nice to fix them before merging.

Did I say it was very minor ? :-)

Regards,
Willy

#3 lore raw

Re: [PATCH 1/5] perf, tools: Add probing for xed

Quoted 50 lines · Willy Tarreau

Hi Andi,

just a very minor cosmetic detail, but your editor seems to use tabs while there were 8 spaces around, causing visual alignment defects below :

tools/build/Makefile.feature FEATURE_TESTS_BASIC := \ · line 66

Quoted 10 lines · Andi Kleen
tools/build/Makefile.feature +1 -1
index e3fb5ecbdcb6..971a9ef87ca6 100644
@@ -63,7 +63,7 @@ FEATURE_TESTS_BASIC :=                  \
         lzma                            \
         get_cpuid                       \
         bpf                             \
-        sdt
+	sdt				\

here

tools/build/Makefile.feature FEATURE_TESTS_EXTRA := \ · line 77

Quoted 7 lines
tools/build/Makefile.feature +1 -0
 # FEATURE_TESTS_BASIC + FEATURE_TESTS_EXTRA is the complete list
 # of all feature tests

@@ -74,11 +74,12 @@ FEATURE_TESTS_EXTRA :=                  \
          cplus-demangle                 \
          hello                          \
          libbabeltrace                  \
+	 xed				\

here

tools/build/Makefile.feature FEATURE_TESTS_EXTRA := \ · line 82

Quoted 6 lines
tools/build/Makefile.feature +1 -1
          liberty                        \
          liberty-z                      \
          libunwind-debug-frame          \
          libunwind-debug-frame-arm      \
-         libunwind-debug-frame-aarch64
+	 libunwind-debug-frame-aarch64

here

tools/build/Makefile.feature FEATURE_DISPLAY ?= \ · line 109

Quoted 9 lines
tools/build/Makefile.feature +1 -1
 FEATURE_TESTS ?= $(FEATURE_TESTS_BASIC)
 

@@ -105,7 +106,7 @@ FEATURE_DISPLAY ?=              \
          zlib                   \
          lzma                   \
          get_cpuid              \
-         bpf
+	 bpf

and here.

Quoted 3 lines

I think it would be nice to fix them before merging.

Did I say it was very minor ? :-)

yea, but still.. ;-)

jirka

author
#4 lore raw

PATCH 1/1 perf, tools: Add probing for xed

From: Andi Kleen <[email protected]>

Add autoprobing for the xed disassembler library.

Can be downloaded from https://github.com/intelxed/xed

v2: Hide. Require XED=1 to enable. Add XED_DIR
v3: Remove -lxed from probe all. Don't touch FEATURE_DISPLAY.

Signed-off-by Andi Kleen <[email protected]>
---
 tools/build/Makefile.feature   |  5 ++++-
 tools/build/feature/Makefile   |  6 +++++-
 tools/build/feature/test-all.c |  5 +++++
 tools/build/feature/test-xed.c |  9 +++++++++
 tools/perf/Makefile.config     | 16 ++++++++++++++++
 tools/perf/Makefile.perf       |  3 +++
 6 files changed, 42 insertions(+), 2 deletions(-)
 create mode 100644 tools/build/feature/test-xed.c
tools/build/Makefile.feature +4 -1
index e3fb5ecbdcb6..0806238fd385 100644
@@ -63,7 +63,8 @@ FEATURE_TESTS_BASIC :=                  \
         lzma                            \
         get_cpuid                       \
         bpf                             \
-        sdt
+	sdt                             \
+	xed
 
 # FEATURE_TESTS_BASIC + FEATURE_TESTS_EXTRA is the complete list
 # of all feature tests

@@ -74,6 +75,7 @@ FEATURE_TESTS_EXTRA :=                  \
          cplus-demangle                 \
          hello                          \
          libbabeltrace                  \
+	 xed				\
          liberty                        \
          liberty-z                      \
          libunwind-debug-frame          \

@@ -140,6 +142,7 @@ ifeq ($(feature-all), 1)
   $(call feature_check,compile-x32)
   $(call feature_check,bionic)
   $(call feature_check,libbabeltrace)
+  $(call feature_check,xed)
 else
   $(foreach feat,$(FEATURE_TESTS),$(call feature_check,$(feat)))
 endif
tools/build/feature/Makefile +5 -1
index b564a2eea039..4f1aa82b867a 100644
@@ -48,7 +48,8 @@ FILES=                                          \
          test-get_cpuid.bin                     \
          test-sdt.bin                           \
          test-cxx.bin                           \
-         test-jvmti.bin
+         test-jvmti.bin				\
+         test-xed.bin
 
 FILES := $(addprefix $(OUTPUT),$(FILES))
 

@@ -123,6 +124,9 @@ $(OUTPUT)test-numa_num_possible_cpus.bin:
 $(OUTPUT)test-libunwind.bin:
 	$(BUILD) -lelf
 
+$(OUTPUT)test-xed.bin:
+	$(BUILD) -lxed
+
 $(OUTPUT)test-libunwind-debug-frame.bin:
 	$(BUILD) -lelf
 $(OUTPUT)test-libunwind-x86.bin:
tools/build/feature/test-all.c +5 -0
index 699e43627397..4a6dd1d1ff49 100644
@@ -149,6 +149,10 @@
 # include "test-sdt.c"
 #undef main
 
+#define main main_test_xed
+#  include "test-xed.c"
+#endif
+
 int main(int argc, char *argv[])
 {
 	main_test_libpython();

@@ -183,6 +187,7 @@ int main(int argc, char *argv[])
 	main_test_bpf();
 	main_test_libcrypto();
 	main_test_sdt();
+	main_test_xed();
 
 	return 0;
 }
tools/build/feature/test-xed.c new file +9 -0
new file mode 100644
index 000000000000..ef9aebf1559d
@@ -0,0 +1,9 @@
+#include <xed/xed-interface.h>
+#include <xed/xed-decode.h>
+#include <xed/xed-decoded-inst-api.h>
+
+int main(void)
+{
+	xed_tables_init();
+	return 0;
+}
tools/perf/Makefile.config +16 -0
index 76c84f0eec52..05dfa31506b6 100644
@@ -682,6 +682,22 @@ ifndef NO_ZLIB
   endif
 endif
 
+ifdef XED
+  ifdef XED_DIR
+    FEATURE_CHECK_CFLAGS-xed := -I $(XED_DIR)/include
+    # override for lib64?
+    FEATURE_CHECK_LDFLAGS-xed := -L $(XED_DIR)/lib -lxed
+  else
+    FEATURE_CHECK_CFLAGS-xed :=
+    FEATURE_CHECK_LDFLAGS-xed := -lxed
+  endif
+  $(call feature_check,xed)
+  ifeq ($(feature-xed), 1)
+    EXTLIBS += -lxed
+    $(call detected,CONFIG_XED)
+  endif
+endif
+
 ifndef NO_LZMA
   ifeq ($(feature-lzma), 1)
     CFLAGS += -DHAVE_LZMA_SUPPORT
tools/perf/Makefile.perf +3 -0
index 8f1c258b151a..5f3413050b39 100644
@@ -84,6 +84,9 @@ include ../scripts/utilities.mak
 # Define NO_SDT if you do not want to define SDT event in perf tools,
 # note that it doesn't disable SDT scanning support.
 #
+# Define XED=1 to build WITH the XED disassembler for perf script
+# Can also set XED_DIR=/path to set XED directory.
+#
 # Define FEATURES_DUMP to provide features detection dump file
 # and bypass the feature detection
 #
Signature · 1 line
2.9.3
#5 lore raw

Re: [PATCH 1/5] perf, tools: Add probing for xed

In reply to Andi Kleen

On Mon, Jan 09, 2017 at 05:02:21PM -0800, Andi Kleen wrote:

SNIP

tools/build/feature/Makefile __BUILDXX = $(CXX) $(CXXFLAGS) -Wall -Werror -o $@ $(patsubst %.bin,%.cpp,$(@F)) · line 72

Quoted 3 lines

$(OUTPUT)test-all.bin:

tools/build/feature/Makefile +1 -1
-	$(BUILD) -fstack-protector-all -O2 -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -laudit -I/usr/include/slang -lslang $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null) $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl -lz -llzma
+	$(BUILD) -fstack-protector-all -O2 -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -laudit -I/usr/include/slang -lslang $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null) $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl -lz -llzma -lxed

I commented on this earlier:
http://marc.info/?l=linux-kernel&m=148388524322441&w=2

jirka

#6 lore raw

Re: [PATCH 1/5] perf, tools: Add probing for xed

In reply to Andi Kleen
Quoted 23 lines · Andi Kleen

From: Andi Kleen <[email protected]>

Add autoprobing for the xed disassembler library.

Can be downloaded from https://github.com/intelxed/xed

v2: Hide. Require XED=1 to enable. Add XED_DIR

Signed-off-by Andi Kleen <[email protected]>
---
 tools/build/Makefile.feature   |  8 +++++---
 tools/build/feature/Makefile   |  8 ++++++--
 tools/build/feature/test-all.c |  5 +++++
 tools/build/feature/test-xed.c |  9 +++++++++
 tools/perf/Makefile.config     | 16 ++++++++++++++++
 tools/perf/Makefile.perf       |  3 +++
 6 files changed, 44 insertions(+), 5 deletions(-)
 create mode 100644 tools/build/feature/test-xed.c
tools/build/Makefile.feature +0 -0
index e3fb5ecbdcb6..971a9ef87ca6 100644

tools/build/Makefile.feature FEATURE_TESTS_BASIC := \ · line 66

Quoted 5 lines
tools/build/Makefile.feature +1 -1
@@ -63,7 +63,7 @@ FEATURE_TESTS_BASIC :=                  \
         lzma                            \
         get_cpuid                       \
         bpf                             \
-        sdt
+	sdt				\

looks like you forgot to add xed in here? why the '\' ?

anyway, please add it in here so it's visible under make VF=1

jirka

#7 lore raw

Re: [PATCH 1/5] perf, tools: Add probing for xed

Quoted 4 lines
Quoted 4 lines
tools/build/Makefile.feature +0 -0
index e3fb5ecbdcb6..971a9ef87ca6 100644
Quoted 8 lines

tools/build/Makefile.feature FEATURE_TESTS_BASIC := \ · line 66

Quoted 6 lines
tools/build/Makefile.feature +1 -1
@@ -63,7 +63,7 @@ FEATURE_TESTS_BASIC :=                  \
         lzma                            \
         get_cpuid                       \
         bpf                             \
-        sdt
+	sdt				\

looks like you forgot to add xed in here? why the '\' ?

I removed it, but incompletely.

Quoted 1 line

anyway, please add it in here so it's visible under make VF=1

If I add it here then it is shown by default (even without VF=1). Arnaldo requested earlier that it shouldn't be shown.

-Andi

#8 lore raw

Re: [PATCH 1/5] perf, tools: Add probing for xed

Quoted 13 lines · Andi Kleen
Quoted 4 lines
Quoted 4 lines
tools/build/Makefile.feature +0 -0
index e3fb5ecbdcb6..971a9ef87ca6 100644
Quoted 8 lines

tools/build/Makefile.feature FEATURE_TESTS_BASIC := \ · line 66

Quoted 6 lines
tools/build/Makefile.feature +1 -1
@@ -63,7 +63,7 @@ FEATURE_TESTS_BASIC :=                  \
         lzma                            \
         get_cpuid                       \
         bpf                             \
-        sdt
+	sdt				\

looks like you forgot to add xed in here? why the '\' ?

Quoted 6 lines

I removed it, but incompletely.

Quoted 1 line

anyway, please add it in here so it's visible under make VF=1

If I add it here then it is shown by default (even without VF=1). Arnaldo requested earlier that it shouldn't be shown.

if you put it to FEATURE_TESTS_BASIC then it's displayed only for VF=1

FEATURE_DISPLAY is the one that's displayed by default

jirka

#9 lore raw

Re: [PATCH 1/5] perf, tools: Add probing for xed

Quoted 14 lines · Jiri Olsa
Quoted 13 lines · Andi Kleen
Quoted 12 lines

tools/build/Makefile.feature FEATURE_TESTS_BASIC := \ · line 66

Quoted 10 lines
tools/build/Makefile.feature +1 -1
index e3fb5ecbdcb6..971a9ef87ca6 100644
@@ -63,7 +63,7 @@ FEATURE_TESTS_BASIC :=                  \
         lzma                            \
         get_cpuid                       \
         bpf                             \
-        sdt
+	sdt				\

looks like you forgot to add xed in here? why the '\' ?

Quoted 8 lines
Quoted 6 lines

I removed it, but incompletely.

Quoted 1 line

anyway, please add it in here so it's visible under make VF=1

If I add it here then it is shown by default (even without VF=1). Arnaldo requested earlier that it shouldn't be shown.

if you put it to FEATURE_TESTS_BASIC then it's displayed only for VF=1

It's already in FEATURE_TESTS_BASIC:

@ -63,7 +63,8 @@ FEATURE_TESTS_BASIC :=                  \
         lzma                            \
         get_cpuid                       \
         bpf                             \

- sdt
+ sdt \
+ xed

-ANdi

#10 lore raw

Re: [PATCH 1/5] perf, tools: Add probing for xed

Quoted 30 lines · Andi Kleen
Quoted 14 lines · Jiri Olsa
Quoted 13 lines · Andi Kleen
Quoted 12 lines

tools/build/Makefile.feature FEATURE_TESTS_BASIC := \ · line 66

Quoted 10 lines
tools/build/Makefile.feature +1 -1
index e3fb5ecbdcb6..971a9ef87ca6 100644
@@ -63,7 +63,7 @@ FEATURE_TESTS_BASIC :=                  \
         lzma                            \
         get_cpuid                       \
         bpf                             \
-        sdt
+	sdt				\

looks like you forgot to add xed in here? why the '\' ?

Quoted 8 lines
Quoted 6 lines

I removed it, but incompletely.

Quoted 1 line

anyway, please add it in here so it's visible under make VF=1

If I add it here then it is shown by default (even without VF=1). Arnaldo requested earlier that it shouldn't be shown.

if you put it to FEATURE_TESTS_BASIC then it's displayed only for VF=1

It's already in FEATURE_TESTS_BASIC:

@ -63,7 +63,8 @@ FEATURE_TESTS_BASIC :=                  \
         lzma                            \
         get_cpuid                       \
         bpf                             \

tools/build/Makefile.feature FEATURE_TESTS_BASIC := \

Quoted 3 lines
tools/build/Makefile.feature +2 -1
-        sdt
+       sdt                             \
+       xed

I see that on FEATURE_TESTS_EXTRA in your xed-4 branch, unless that's different to what you sent out

jirka

author
#11 lore raw

PATCH 2/5 perf, tools: Add one liner warning for disabled features

In reply to Andi Kleen

From: Andi Kleen <[email protected]>

Add a one liner warning for perf features that need to be enabled explicitly by the user, so that they know they are missing something. Currently enabled for XED and BABELTRACE.

Signed-off-by Andi Kleen <[email protected]>
---
 tools/perf/Makefile.config | 10 ++++++++++
 1 file changed, 10 insertions(+)
tools/perf/Makefile.config +10 -0
index 05dfa31506b6..e313739238a8 100644
@@ -65,6 +65,8 @@ ifneq ($(ARCH),$(filter $(ARCH),x86 arm))
   NO_LIBDW_DWARF_UNWIND := 1
 endif
 
+DISABLED_FEATURES =
+
 ifeq ($(LIBUNWIND_LIBS),)
   NO_LIBUNWIND := 1
 endif

@@ -696,6 +698,8 @@ ifdef XED
     EXTLIBS += -lxed
     $(call detected,CONFIG_XED)
   endif
+else
+  DISABLED_FEATURES += XED
 endif
 
 ifndef NO_LZMA

@@ -770,6 +774,8 @@ ifdef LIBBABELTRACE
   else
     msg := $(warning No libbabeltrace found, disables 'perf data' CTF format support, please install libbabeltrace-dev[el]/libbabeltrace-ctf-dev);
   endif
+else
+  DISABLED_FEATURES += LIBBABELTRACE
 endif
 
 ifndef NO_AUXTRACE

@@ -841,6 +847,10 @@ ifdef LIBCLANGLLVM
   endif
 endif
 
+ifneq ($(DISABLED_FEATURES),)
+  $(warning Disabled features, need explicit enabling by user: $(DISABLED_FEATURES))
+endif
+
 # Among the variables below, these:
 #   perfexecdir
 #   template_dir
Signature · 1 line
2.9.3
Acked-by on v1 2/5
#12 lore raw

Re: [PATCH 2/5] perf, tools: Add one liner warning for disabled features

Quoted 7 lines · Andi Kleen

From: Andi Kleen <[email protected]>

Add a one liner warning for perf features that need to be enabled explicitly by the user, so that they know they are missing something. Currently enabled for XED and BABELTRACE.

Signed-off-by Andi Kleen <[email protected]>

thanks for doing this

Acked-by Jiri Olsa <[email protected]>

jirka

author
#13 lore raw

PATCH 3/5 perf, tools: Add disassembler for x86 using the XED library

In reply to Andi Kleen

From: Andi Kleen <[email protected]>

Add a generic disassembler function for x86 using the XED library, and a fallback function for architectures that don't implement one. Other architectures can implement their own disassembler functions.

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, uptodate, and used by many Intel tools
- XED is linked statically so there is no runtime dependency.

The XED library can be downloaded from http://github.com/intelxed/xed

v2: Clean up includes.

Signed-off-by Andi Kleen <[email protected]>
---
 tools/perf/arch/x86/util/Build |  1 +
 tools/perf/arch/x86/util/dis.c | 86 ++++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/Build          |  1 +
 tools/perf/util/dis.c          | 15 ++++++++
 tools/perf/util/dis.h          | 20 ++++++++++
 5 files changed, 123 insertions(+)
 create mode 100644 tools/perf/arch/x86/util/dis.c
 create mode 100644 tools/perf/util/dis.c
 create mode 100644 tools/perf/util/dis.h
tools/perf/arch/x86/util/Build +1 -0
index f95e6f46ef0d..93490009ea6a 100644
@@ -14,3 +14,4 @@ libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
 libperf-$(CONFIG_AUXTRACE) += auxtrace.o
 libperf-$(CONFIG_AUXTRACE) += intel-pt.o
 libperf-$(CONFIG_AUXTRACE) += intel-bts.o
+libperf-$(CONFIG_XED) += dis.o
tools/perf/arch/x86/util/dis.c new file +86 -0

86 lines not on this page · raw message

tools/perf/util/Build +1 -0
index 3840e3a87057..393000501579 100644
@@ -88,6 +88,7 @@ libperf-y += mem-events.o
 libperf-y += vsprintf.o
 libperf-y += drv_configs.o
 libperf-y += time-utils.o
+libperf-y += dis.o
 
 libperf-$(CONFIG_LIBBPF) += bpf-loader.o
 libperf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o
tools/perf/util/dis.c new file +15 -0
new file mode 100644
index 000000000000..89c9b84051b8
@@ -0,0 +1,15 @@
+#include "perf.h"
+#include "dis.h"
+#include "util.h"
+
+/* Fallback for architectures with no disassembler */
+
+__weak char *disas_inst(struct perf_dis *x, uint64_t ip __maybe_unused,
+		u8 *inbuf __maybe_unused, int inlen __maybe_unused,
+		int *lenp)
+{
+	if (lenp)
+		*lenp = 0;
+	strcpy(x->out, "?");
+	return x->out;
+}
tools/perf/util/dis.h new file +20 -0
new file mode 100644
index 000000000000..ffda324cbc1a
@@ -0,0 +1,20 @@
+#ifndef DIS_H
+#define DIS_H 1
+
+#define MAXINSN 15
+
+struct perf_dis {
+	/* Initialized by callers: */
+	struct thread *thread;
+	u8 cpumode;
+	int cpu;
+	bool is64bit;
+	/* Temporary */
+	char out[256];
+};
+
+char *disas_inst(struct perf_dis *x, uint64_t ip, u8 *inbuf, int inlen,
+		 int *lenp);
+
+
+#endif
Signature · 1 line
2.9.3
author
#14 lore raw

PATCH 4/5 perf, tools, script: Add support for printing assembler

In reply to Andi Kleen

From: Andi Kleen <[email protected]>

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 [email protected]
Signed-off-by Andi Kleen <[email protected]>
---
 tools/perf/Documentation/perf-script.txt |  4 +-
 tools/perf/builtin-script.c              | 72 +++++++++++++++++++++++++++-----
 2 files changed, 64 insertions(+), 12 deletions(-)
tools/perf/Documentation/perf-script.txt +3 -1
index 5dc5c6a09ac4..863579b4d2e2 100644
@@ -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
tools/perf/builtin-script.c +61 -11

154 lines not on this page · raw message

Signature · 1 line
2.9.3
author
#15 lore raw

PATCH 5/5 perf, tools, script: Add brstackasm output for branch stacks

In reply to Andi Kleen

From: Andi Kleen <[email protected]>

Implement printing full disassembled sequences for branch stacks in perf script. This allows to directly print hot paths for individual samples, together with branch misprediction and cycle count / IPC information if available (on Skylake systems). This only works when no special branch filters are specified.

% perf record -b ...
% perf script -F brstackasm
...

        000055b55d1147d0        pushq  %rbp
        000055b55d1147d1        pushq  %r15
        000055b55d1147d3        pushq  %r14
        000055b55d1147d5        pushq  %r13
        000055b55d1147d7        pushq  %r12
        000055b55d1147d9        pushq  %rbx
        000055b55d1147da        sub $0x18, %rsp
        000055b55d1147de        mov %r8, %r13
        000055b55d1147e1        mov %rcx, %rbp
        000055b55d1147e4        mov %rdx, %r14
        000055b55d1147e7        mov %rsi, %r15
        000055b55d1147ea        mov %rdi, %rbx
        000055b55d1147ed        movl  $0x0, 0xc(%rsp)
        000055b55d1147f5        movq  (%rbp), %rax
        000055b55d1147f9        test $0x1, %al
        000055b55d1147fb        jnz 0x55b55d114890              # PRED 4 cycles 3.75 IPC
        000055b55d114890        mov %eax, %ecx
        000055b55d114892        and $0x3, %ecx
        000055b55d114895        cmp $0x1, %rcx
        000055b55d114899        jnz 0x55b55d1148f8
        000055b55d11489b        movq  -0x1(%rax), %rcx
        000055b55d11489f        cmpb  $0x81, 0xb(%rcx)
        000055b55d1148a3        jnz 0x55b55d1148fe              # PRED 1 cycles 6.00 IPC

...

Occasionally the path does not reach up to the sample IP, as the LBRs may be frozen before executing a final jump. In this case we print a special message.

v2:
Use low level abstracted disassembler interface.
Print symbols and source lines as labels.
Print first jump in LBR too.
Patch up blocks with filtered ring transfers.
Show IPC
Lots of cleanups and improvements.
v3:
Print special message for branches frozen early.

Signed-off-by Andi Kleen <[email protected]>
---
 tools/perf/Documentation/perf-script.txt |  13 +-
 tools/perf/builtin-script.c              | 267 +++++++++++++++++++++++++++++++
 2 files changed, 278 insertions(+), 2 deletions(-)
tools/perf/Documentation/perf-script.txt +11 -2
index 863579b4d2e2..5df7e1f55c55 100644
@@ -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, asm.
+        srcline, period, iregs, brstack, brstacksym, flags, bpf-output, asm, brstackasm,
         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

@@ -189,17 +189,22 @@ OPTIONS
 	i.e., -F "" is not allowed.
 
 	The brstack output includes branch related information with raw addresses using the
-	/v/v/v/v/ syntax in the following order:
+	/v/v/v/v/cycles syntax in the following order:
 	FROM: branch source instruction
 	TO  : branch target instruction
         M/P/-: M=branch target mispredicted or branch direction was mispredicted, P=target predicted or direction predicted, -=not supported
 	X/- : X=branch inside a transactional region, -=not in transaction region or not supported
 	A/- : A=TSX abort entry, -=not aborted region or not supported
+	cycles
 
 	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.
 
+	When brstackasm is specified the full assembler sequences of branch sequences for each sample
+	is printed. This is the full execution path leading to the sample. This is only supported when the
+	sample was recorded with perf record -b or -j any.
+
 -k::
 --vmlinux=<file>::
         vmlinux pathname

@@ -301,6 +306,10 @@ include::itrace.txt[]
 	stop time is not given (i.e, time string is 'x.y,') then analysis goes
 	to end of file.
 
+--max-blocks::
+	Set the maximum number of program blocks to print with brstackasm for
+	each sample.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script-perl[1],
tools/perf/builtin-script.c +267 -0

309 lines not on this page · raw message

Signature · 1 line
2.9.3