[PATCH 0/3] perf tools: Add libdw DWARF post unwind support for ARM64

[PATCH 0/3] perf tools: Add libdw DWARF post unwind support for ARM64

[Jean Pihet]

Adding libdw DWARF post unwind support, which is part
of elfutils-devel/libdw-dev package from version 0.158.

Also includes the test suite for dwarf unwinding, by adding the
arch specific test code and the perf_regs_load function.

This series depends on the following kernel patches series:
- AARCH64 unwinding support [1]. Already mainlined.
- ARM libdw integration [2],
and on the changes from the branch for:
- libdw AARCH64 unwinding support [3].

[1] http://www.spinics.net/lists/arm-kernel/msg304483.html
[2] https://lkml.org/lkml/2014/5/6/366
[3] https://git.fedorahosted.org/cgit/elfutils.git/log/?h=mjw/aarch64-unwind

ToDo: investigate the libdw unwinding problem with compat binaries (i.e.
ARMv7 binaries running on ARMv8). Since this functionality works ok with
libunwind, the problem should be in libdw compat support [3].


Jean Pihet (3):
  perf tests: Introduce perf_regs_load function on ARM64
  perf tests: Add dwarf unwind test on ARM64
  perf tools: Add libdw DWARF post unwind support for ARM64

 tools/perf/Makefile.perf                   |  2 +-
 tools/perf/arch/arm64/Makefile             |  7 ++++
 tools/perf/arch/arm64/include/perf_regs.h  |  5 +++
 tools/perf/arch/arm64/tests/dwarf-unwind.c | 59 ++++++++++++++++++++++++++++++
 tools/perf/arch/arm64/tests/regs_load.S    | 39 ++++++++++++++++++++
 tools/perf/arch/arm64/util/unwind-libdw.c  | 53 +++++++++++++++++++++++++++
 tools/perf/tests/builtin-test.c            |  3 +-
 tools/perf/tests/tests.h                   |  3 +-
 8 files changed, 168 insertions(+), 3 deletions(-)
 create mode 100644 tools/perf/arch/arm64/tests/dwarf-unwind.c
 create mode 100644 tools/perf/arch/arm64/tests/regs_load.S
 create mode 100644 tools/perf/arch/arm64/util/unwind-libdw.c

---
Rebased on the latest jolsa/perf/core

-- 
1.7.11.7

[PATCH 1/3] perf tests: Introduce perf_regs_load function on ARM64

[Jean Pihet]

Introducing perf_regs_load function, which is going
to be used for dwarf unwind test in following patches.

It takes single argument as a pointer to the regs dump
buffer and populates it with current registers values, as
expected by the perf built-in unwinding test.

Signed-off-by: Jean Pihet <jean.pihet@linaro.org>
Cc: Steve Capper <steve.capper@linaro.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
---
 tools/perf/arch/arm64/Makefile            |  1 +
 tools/perf/arch/arm64/include/perf_regs.h |  2 ++
 tools/perf/arch/arm64/tests/regs_load.S   | 39 +++++++++++++++++++++++++++++++
 3 files changed, 42 insertions(+)
 create mode 100644 tools/perf/arch/arm64/tests/regs_load.S

diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile
index 67e9b3d..9b8f87e 100644
--- a/tools/perf/arch/arm64/Makefile
+++ b/tools/perf/arch/arm64/Makefile
@@ -4,4 +4,5 @@ LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
 endif
 ifndef NO_LIBUNWIND
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind-libunwind.o
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/tests/regs_load.o
 endif
diff --git a/tools/perf/arch/arm64/include/perf_regs.h b/tools/perf/arch/arm64/include/perf_regs.h
index 2359546..1e052f1 100644
--- a/tools/perf/arch/arm64/include/perf_regs.h
+++ b/tools/perf/arch/arm64/include/perf_regs.h
@@ -9,6 +9,8 @@
 #define PERF_REG_IP	PERF_REG_ARM64_PC
 #define PERF_REG_SP	PERF_REG_ARM64_SP
 
+void perf_regs_load(u64 *regs);
+
 static inline const char *perf_reg_name(int id)
 {
 	switch (id) {
diff --git a/tools/perf/arch/arm64/tests/regs_load.S b/tools/perf/arch/arm64/tests/regs_load.S
new file mode 100644
index 0000000..92ab968
--- /dev/null
+++ b/tools/perf/arch/arm64/tests/regs_load.S
@@ -0,0 +1,39 @@
+#include <linux/linkage.h>
+
+/*
+ * Implementation of void perf_regs_load(u64 *regs);
+ *
+ * This functions fills in the 'regs' buffer from the actual registers values,
+ * in the way the perf built-in unwinding test expects them:
+ * - the PC at the time at the call to this function. Since this function
+ *   is called using a bl instruction, the PC value is taken from LR,
+ * - the current SP (not touched by this function),
+ * - the current value of LR is merely retrieved and stored because the
+ *   value before the call to this function is unknown at this time; it will
+ *   be unwound from the dwarf information in unwind__get_entries.
+ */
+
+.text
+.type perf_regs_load,%function
+ENTRY(perf_regs_load)
+	stp x0,  x1,  [x0], #16	// store x0..x29
+	stp x2,  x3,  [x0], #16
+	stp x4,  x5,  [x0], #16
+	stp x6,  x7,  [x0], #16
+	stp x8,  x9,  [x0], #16
+	stp x10, x11, [x0], #16
+	stp x12, x13, [x0], #16
+	stp x14, x15, [x0], #16
+	stp x16, x17, [x0], #16
+	stp x18, x19, [x0], #16
+	stp x20, x21, [x0], #16
+	stp x22, x23, [x0], #16
+	stp x24, x25, [x0], #16
+	stp x26, x27, [x0], #16
+	stp x28, x29, [x0], #16
+	mov x1,  sp
+	stp x30, x1,  [x0], #16	// store lr and sp
+	str x30, [x0]		// store pc as lr in order to skip the call
+				//  to this function
+	ret
+ENDPROC(perf_regs_load)
-- 
1.7.11.7

[PATCH 2/3] perf tests: Add dwarf unwind test on ARM64

[Jean Pihet]

Adding dwarf unwind test, that setups live machine data over
the perf test thread and does the remote unwind.

Need to use -fno-optimize-sibling-calls for test compilation,
otherwise 'krava_*' function calls are optimized into jumps
and ommited from the stack unwind.

Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: David Ahern <dsahern@gmail.com>
Signed-off-by: Jean Pihet <jean.pihet@linaro.org>
---
 tools/perf/Makefile.perf                   |  2 +-
 tools/perf/arch/arm64/Makefile             |  1 +
 tools/perf/arch/arm64/include/perf_regs.h  |  3 ++
 tools/perf/arch/arm64/tests/dwarf-unwind.c | 59 ++++++++++++++++++++++++++++++
 tools/perf/tests/builtin-test.c            |  3 +-
 tools/perf/tests/tests.h                   |  3 +-
 6 files changed, 68 insertions(+), 3 deletions(-)
 create mode 100644 tools/perf/arch/arm64/tests/dwarf-unwind.c

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index dea2d633..6cde50f 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -411,7 +411,7 @@ LIB_OBJS += $(OUTPUT)tests/code-reading.o
 LIB_OBJS += $(OUTPUT)tests/sample-parsing.o
 LIB_OBJS += $(OUTPUT)tests/parse-no-sample-id-all.o
 ifndef NO_DWARF_UNWIND
-ifeq ($(ARCH),$(filter $(ARCH),x86 arm))
+ifeq ($(ARCH),$(filter $(ARCH),x86 arm arm64))
 LIB_OBJS += $(OUTPUT)tests/dwarf-unwind.o
 endif
 endif
diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile
index 9b8f87e..221f21d 100644
--- a/tools/perf/arch/arm64/Makefile
+++ b/tools/perf/arch/arm64/Makefile
@@ -5,4 +5,5 @@ endif
 ifndef NO_LIBUNWIND
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind-libunwind.o
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/tests/regs_load.o
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/tests/dwarf-unwind.o
 endif
diff --git a/tools/perf/arch/arm64/include/perf_regs.h b/tools/perf/arch/arm64/include/perf_regs.h
index 1e052f1..e74df99 100644
--- a/tools/perf/arch/arm64/include/perf_regs.h
+++ b/tools/perf/arch/arm64/include/perf_regs.h
@@ -9,6 +9,9 @@
 #define PERF_REG_IP	PERF_REG_ARM64_PC
 #define PERF_REG_SP	PERF_REG_ARM64_SP
 
+#define PERF_REGS_MAX	PERF_REG_ARM64_MAX
+#define PERF_SAMPLE_REGS_ABI	PERF_SAMPLE_REGS_ABI_64
+
 void perf_regs_load(u64 *regs);
 
 static inline const char *perf_reg_name(int id)
diff --git a/tools/perf/arch/arm64/tests/dwarf-unwind.c b/tools/perf/arch/arm64/tests/dwarf-unwind.c
new file mode 100644
index 0000000..0aa64f3
--- /dev/null
+++ b/tools/perf/arch/arm64/tests/dwarf-unwind.c
@@ -0,0 +1,59 @@
+#include <string.h>
+#include "perf_regs.h"
+#include "thread.h"
+#include "map.h"
+#include "event.h"
+#include "tests/tests.h"
+
+#define STACK_SIZE 8192
+
+static int sample_ustack(struct perf_sample *sample,
+			 struct thread *thread, u64 *regs)
+{
+	struct stack_dump *stack = &sample->user_stack;
+	struct map *map;
+	unsigned long sp;
+	u64 stack_size, *buf;
+
+	buf = malloc(STACK_SIZE);
+	if (!buf) {
+		pr_debug("failed to allocate sample uregs data\n");
+		return -1;
+	}
+
+	sp = (unsigned long) regs[PERF_REG_ARM64_SP];
+
+	map = map_groups__find(&thread->mg, MAP__FUNCTION, (u64) sp);
+	if (!map) {
+		pr_debug("failed to get stack map\n");
+		return -1;
+	}
+
+	stack_size = map->end - sp;
+	stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size;
+
+	memcpy(buf, (void *) sp, stack_size);
+	stack->data = (char *) buf;
+	stack->size = stack_size;
+	return 0;
+}
+
+int test__arch_unwind_sample(struct perf_sample *sample,
+			     struct thread *thread)
+{
+	struct regs_dump *regs = &sample->user_regs;
+	u64 *buf;
+
+	buf = malloc(sizeof(u64) * PERF_REGS_MAX);
+	if (!buf) {
+		pr_debug("failed to allocate sample uregs data\n");
+		return -1;
+	}
+
+	perf_regs_load(buf);
+	regs->abi  = PERF_SAMPLE_REGS_ABI;
+	regs->regs = buf;
+	regs->mask = PERF_REGS_MASK;
+
+	return sample_ustack(sample, thread, buf);
+}
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 5e0764b..7921aa0 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -115,7 +115,8 @@ static struct test {
 		.desc = "Test parsing with no sample_id_all bit set",
 		.func = test__parse_no_sample_id_all,
 	},
-#if defined(__x86_64__) || defined(__i386__) || defined(__arm__)
+#if defined(__x86_64__) || defined(__i386__) || \
+    defined(__arm__) || defined(__aarch64__)
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
 	{
 		.desc = "Test dwarf unwind",
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 8f91fb0..426680e 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -45,7 +45,8 @@ int test__hists_filter(void);
 int test__mmap_thread_lookup(void);
 int test__thread_mg_share(void);
 
-#if defined(__x86_64__) || defined(__i386__) || defined(__arm__)
+#if defined(__x86_64__) || defined(__i386__) || \
+    defined(__arm__) || defined(__aarch64__)
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
 struct thread;
 struct perf_sample;
-- 
1.7.11.7

[PATCH 2/3] perf tests: Add dwarf unwind test on ARM64

[Jiri Olsa]

On Tue, May 06, 2014 at 05:55:32PM +0200, Jean Pihet wrote:

SNIP

> +#include "tests/tests.h"
> +
> +#define STACK_SIZE 8192
> +
> +static int sample_ustack(struct perf_sample *sample,
> +			 struct thread *thread, u64 *regs)
> +{
> +	struct stack_dump *stack = &sample->user_stack;
> +	struct map *map;
> +	unsigned long sp;
> +	u64 stack_size, *buf;
> +
> +	buf = malloc(STACK_SIZE);
> +	if (!buf) {
> +		pr_debug("failed to allocate sample uregs data\n");
> +		return -1;
> +	}
> +
> +	sp = (unsigned long) regs[PERF_REG_ARM64_SP];
> +
> +	map = map_groups__find(&thread->mg, MAP__FUNCTION, (u64) sp);
> +	if (!map) {
> +		pr_debug("failed to get stack map\n");
> +		return -1;
> +	}

there's a memory leak of 'buf' already fixed fox x86:

  perf tests x86: Fix memory leak in sample_ustack()
  commit 763d7f5f2718f085bab5a9e63308349728f3ad12
  Author: Masanari Iida <standby24x7@gmail.com>
  Date:   Sun Apr 20 00:16:41 2014 +0900

jirka

[PATCH 3/3] perf tools: Add libdw DWARF post unwind support for ARM64

[Jean Pihet]

Adding libdw DWARF post unwind support, which is part
of elfutils-devel/libdw-dev package from version 0.158.

Note: the libdw code needs some support for dwarf unwinding
on ARM64, this code is submitted seperately on the elfutils
ML.

The new code is contained in unwin-libdw.c object, and
implements unwind__get_entries unwind interface function.

Signed-off-by: Jean Pihet <jean.pihet@linaro.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: David Ahern <dsahern@gmail.com>
---
 tools/perf/arch/arm64/Makefile            |  5 +++
 tools/perf/arch/arm64/util/unwind-libdw.c | 53 +++++++++++++++++++++++++++++++
 2 files changed, 58 insertions(+)
 create mode 100644 tools/perf/arch/arm64/util/unwind-libdw.c

diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile
index 221f21d..09d6215 100644
--- a/tools/perf/arch/arm64/Makefile
+++ b/tools/perf/arch/arm64/Makefile
@@ -4,6 +4,11 @@ LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
 endif
 ifndef NO_LIBUNWIND
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind-libunwind.o
+endif
+ifndef NO_LIBDW_DWARF_UNWIND
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind-libdw.o
+endif
+ifndef NO_DWARF_UNWIND
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/tests/regs_load.o
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/tests/dwarf-unwind.o
 endif
diff --git a/tools/perf/arch/arm64/util/unwind-libdw.c b/tools/perf/arch/arm64/util/unwind-libdw.c
new file mode 100644
index 0000000..8d24958
--- /dev/null
+++ b/tools/perf/arch/arm64/util/unwind-libdw.c
@@ -0,0 +1,53 @@
+#include <elfutils/libdwfl.h>
+#include "../../util/unwind-libdw.h"
+#include "../../util/perf_regs.h"
+
+bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg)
+{
+	struct unwind_info *ui = arg;
+	struct regs_dump *user_regs = &ui->sample->user_regs;
+	Dwarf_Word dwarf_regs[PERF_REG_ARM64_MAX];
+
+#define REG(r) ({						\
+	Dwarf_Word val = 0;					\
+	perf_reg_value(&val, user_regs, PERF_REG_ARM64_##r);	\
+	val;							\
+})
+
+	dwarf_regs[0]  = REG(X0);
+	dwarf_regs[1]  = REG(X1);
+	dwarf_regs[2]  = REG(X2);
+	dwarf_regs[3]  = REG(X3);
+	dwarf_regs[4]  = REG(X4);
+	dwarf_regs[5]  = REG(X5);
+	dwarf_regs[6]  = REG(X6);
+	dwarf_regs[7]  = REG(X7);
+	dwarf_regs[8]  = REG(X8);
+	dwarf_regs[9]  = REG(X9);
+	dwarf_regs[10] = REG(X10);
+	dwarf_regs[11] = REG(X11);
+	dwarf_regs[12] = REG(X12);
+	dwarf_regs[13] = REG(X13);
+	dwarf_regs[14] = REG(X14);
+	dwarf_regs[15] = REG(X15);
+	dwarf_regs[16] = REG(X16);
+	dwarf_regs[17] = REG(X17);
+	dwarf_regs[18] = REG(X18);
+	dwarf_regs[19] = REG(X19);
+	dwarf_regs[20] = REG(X20);
+	dwarf_regs[21] = REG(X21);
+	dwarf_regs[22] = REG(X22);
+	dwarf_regs[23] = REG(X23);
+	dwarf_regs[24] = REG(X24);
+	dwarf_regs[25] = REG(X25);
+	dwarf_regs[26] = REG(X26);
+	dwarf_regs[27] = REG(X27);
+	dwarf_regs[28] = REG(X28);
+	dwarf_regs[29] = REG(X29);
+	dwarf_regs[30] = REG(LR);
+	dwarf_regs[31] = REG(SP);
+	dwarf_regs[32] = REG(PC);
+
+	return dwfl_thread_state_registers(thread, 0, PERF_REG_ARM64_MAX,
+					   dwarf_regs);
+}
-- 
1.7.11.7

[PATCH 3/3] perf tools: Add libdw DWARF post unwind support for ARM64

[Will Deacon]

Hi Jean,

On Tue, May 06, 2014 at 04:55:33PM +0100, Jean Pihet wrote:
> Adding libdw DWARF post unwind support, which is part
> of elfutils-devel/libdw-dev package from version 0.158.
> 
> Note: the libdw code needs some support for dwarf unwinding
> on ARM64, this code is submitted seperately on the elfutils
> ML.
> 
> The new code is contained in unwin-libdw.c object, and
> implements unwind__get_entries unwind interface function.

Are you planning to implement support for 32-bit ARM too? If so, we'll need
compat handling here again (your favourite!).

> +bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg)
> +{
> +	struct unwind_info *ui = arg;
> +	struct regs_dump *user_regs = &ui->sample->user_regs;
> +	Dwarf_Word dwarf_regs[PERF_REG_ARM64_MAX];

Shouldn't this be PERF_REG_ARM64_MAX - 1?

Will

[PATCH 3/3] perf tools: Add libdw DWARF post unwind support for ARM64

[Jean Pihet]

Hi Will,

On 6 May 2014 19:00, Will Deacon <will.deacon@arm.com> wrote:
> Hi Jean,
>
> On Tue, May 06, 2014 at 04:55:33PM +0100, Jean Pihet wrote:
>> Adding libdw DWARF post unwind support, which is part
>> of elfutils-devel/libdw-dev package from version 0.158.
>>
>> Note: the libdw code needs some support for dwarf unwinding
>> on ARM64, this code is submitted seperately on the elfutils
>> ML.
>>
>> The new code is contained in unwin-libdw.c object, and
>> implements unwind__get_entries unwind interface function.
>
> Are you planning to implement support for 32-bit ARM too? If so, we'll need
> compat handling here again (your favourite!).
Yes! Another patch set (sent just before this one) targets ARM. There
is a nice ToDo in the cover letter: handle compat mode correctly. In
fact I sent a patch to libdw, so it supports it already but is
somewhat broken for compat mode. This is on my prefered ToDo list ;-)

>
>> +bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg)
>> +{
>> +     struct unwind_info *ui = arg;
>> +     struct regs_dump *user_regs = &ui->sample->user_regs;
>> +     Dwarf_Word dwarf_regs[PERF_REG_ARM64_MAX];
>
> Shouldn't this be PERF_REG_ARM64_MAX - 1?
Ah, well spotted! I will change although it shouldn't harm, right?

>
> Will

Thx for reviewing,
Jean

[PATCH 3/3] perf tools: Add libdw DWARF post unwind support for ARM64

[Will Deacon]

On Tue, May 06, 2014 at 06:41:55PM +0100, Jean Pihet wrote:
> Hi Will,
> 
> On 6 May 2014 19:00, Will Deacon <will.deacon@arm.com> wrote:
> > Hi Jean,
> >
> > On Tue, May 06, 2014 at 04:55:33PM +0100, Jean Pihet wrote:
> >> Adding libdw DWARF post unwind support, which is part
> >> of elfutils-devel/libdw-dev package from version 0.158.
> >>
> >> Note: the libdw code needs some support for dwarf unwinding
> >> on ARM64, this code is submitted seperately on the elfutils
> >> ML.
> >>
> >> The new code is contained in unwin-libdw.c object, and
> >> implements unwind__get_entries unwind interface function.
> >
> > Are you planning to implement support for 32-bit ARM too? If so, we'll need
> > compat handling here again (your favourite!).
> Yes! Another patch set (sent just before this one) targets ARM. There
> is a nice ToDo in the cover letter: handle compat mode correctly. In
> fact I sent a patch to libdw, so it supports it already but is
> somewhat broken for compat mode. This is on my prefered ToDo list ;-)
> 
> >
> >> +bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg)
> >> +{
> >> +     struct unwind_info *ui = arg;
> >> +     struct regs_dump *user_regs = &ui->sample->user_regs;
> >> +     Dwarf_Word dwarf_regs[PERF_REG_ARM64_MAX];
> >
> > Shouldn't this be PERF_REG_ARM64_MAX - 1?
> Ah, well spotted! I will change although it shouldn't harm, right?

Actually, looking again, I think I'm wrong and your code was right first
time! It looks like dwfl_thread_state_registers takes the limit too, so I
don't think you need to change anything (except for adding compat support).

Sorry about that,

Will

[PATCH 3/3] perf tools: Add libdw DWARF post unwind support for ARM64

[Jean Pihet]

Hi Will,

On Tue, May 6, 2014 at 7:52 PM, Will Deacon <will.deacon@arm.com> wrote:
> On Tue, May 06, 2014 at 06:41:55PM +0100, Jean Pihet wrote:
>> Hi Will,
>>
>> On 6 May 2014 19:00, Will Deacon <will.deacon@arm.com> wrote:
>> > Hi Jean,
>> >
>> > On Tue, May 06, 2014 at 04:55:33PM +0100, Jean Pihet wrote:
>> >> Adding libdw DWARF post unwind support, which is part
>> >> of elfutils-devel/libdw-dev package from version 0.158.
>> >>
>> >> Note: the libdw code needs some support for dwarf unwinding
>> >> on ARM64, this code is submitted seperately on the elfutils
>> >> ML.
>> >>
>> >> The new code is contained in unwin-libdw.c object, and
>> >> implements unwind__get_entries unwind interface function.
>> >
>> > Are you planning to implement support for 32-bit ARM too? If so, we'll need
>> > compat handling here again (your favourite!).
>> Yes! Another patch set (sent just before this one) targets ARM. There
>> is a nice ToDo in the cover letter: handle compat mode correctly. In
>> fact I sent a patch to libdw, so it supports it already but is
>> somewhat broken for compat mode. This is on my prefered ToDo list ;-)
>>
>> >
>> >> +bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg)
>> >> +{
>> >> +     struct unwind_info *ui = arg;
>> >> +     struct regs_dump *user_regs = &ui->sample->user_regs;
>> >> +     Dwarf_Word dwarf_regs[PERF_REG_ARM64_MAX];
>> >
>> > Shouldn't this be PERF_REG_ARM64_MAX - 1?
>> Ah, well spotted! I will change although it shouldn't harm, right?
>
> Actually, looking again, I think I'm wrong and your code was right first
> time! It looks like dwfl_thread_state_registers takes the limit too, so I
> don't think you need to change anything (except for adding compat support).
>
> Sorry about that,
My bad, I haven't checked carefully enough before replying.

Thx!
Jean
>
> Will
>
> _______________________________________________
> linux-arm-kernel mailing list
> linux-arm-kernel at lists.infradead.org
> http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH 0/3] perf tools: Add libdw DWARF post unwind support for ARM64

[Jean Pihet]

Adding libdw DWARF post unwind support, which is part
of elfutils-devel/libdw-dev package from version 0.158.

Also includes the test suite for dwarf unwinding, by adding the
arch specific test code and the perf_regs_load function.

This series depends on the following kernel patches series:
- AARCH64 unwinding support [1],
- ARM libdw integration [2],
and on the changes from the branch for:
- libdw AARCH64 unwinding support [3].

[1] http://www.spinics.net/lists/arm-kernel/msg304483.html
[2] http://www.spinics.net/lists/arm-kernel/msg312423.html
[3] https://git.fedorahosted.org/cgit/elfutils.git/log/?h=mjw/aarch64-unwind


Jean Pihet (3):
  perf tests: Introduce perf_regs_load function on ARM64
  perf tests: Add dwarf unwind test on ARM64
  perf tools: Add libdw DWARF post unwind support for ARM64

 tools/perf/Makefile.perf                   |  2 +-
 tools/perf/arch/arm64/Makefile             |  7 ++++
 tools/perf/arch/arm64/include/perf_regs.h  |  5 +++
 tools/perf/arch/arm64/tests/dwarf-unwind.c | 59 ++++++++++++++++++++++++++++++
 tools/perf/arch/arm64/tests/regs_load.S    | 39 ++++++++++++++++++++
 tools/perf/arch/arm64/util/unwind-libdw.c  | 53 +++++++++++++++++++++++++++
 tools/perf/tests/builtin-test.c            |  3 +-
 tools/perf/tests/tests.h                   |  3 +-
 8 files changed, 168 insertions(+), 3 deletions(-)
 create mode 100644 tools/perf/arch/arm64/tests/dwarf-unwind.c
 create mode 100644 tools/perf/arch/arm64/tests/regs_load.S
 create mode 100644 tools/perf/arch/arm64/util/unwind-libdw.c

---

- Rebased on latest acme/perf/core git tree,
- Tested on the ARMv8 Foundation emulator.

-- 
1.7.11.7

[PATCH 2/3] perf tests: Add dwarf unwind test on ARM64

[Jean Pihet]

Adding dwarf unwind test, that setups live machine data over
the perf test thread and does the remote unwind.

Need to use -fno-optimize-sibling-calls for test compilation,
otherwise 'krava_*' function calls are optimized into jumps
and ommited from the stack unwind.

Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Cc: David Ahern <dsahern@gmail.com>
Signed-off-by: Jean Pihet <jean.pihet@linaro.org>
---
 tools/perf/Makefile.perf                   |  2 +-
 tools/perf/arch/arm64/Makefile             |  1 +
 tools/perf/arch/arm64/include/perf_regs.h  |  3 ++
 tools/perf/arch/arm64/tests/dwarf-unwind.c | 59 ++++++++++++++++++++++++++++++
 tools/perf/tests/builtin-test.c            |  3 +-
 tools/perf/tests/tests.h                   |  3 +-
 6 files changed, 68 insertions(+), 3 deletions(-)
 create mode 100644 tools/perf/arch/arm64/tests/dwarf-unwind.c

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index f281c4f..f9c8808 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -410,7 +410,7 @@ LIB_OBJS += $(OUTPUT)tests/code-reading.o
 LIB_OBJS += $(OUTPUT)tests/sample-parsing.o
 LIB_OBJS += $(OUTPUT)tests/parse-no-sample-id-all.o
 ifndef NO_DWARF_UNWIND
-ifeq ($(ARCH),$(filter $(ARCH),x86 arm))
+ifeq ($(ARCH),$(filter $(ARCH),x86 arm arm64))
 LIB_OBJS += $(OUTPUT)tests/dwarf-unwind.o
 endif
 endif
diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile
index 9b8f87e..221f21d 100644
--- a/tools/perf/arch/arm64/Makefile
+++ b/tools/perf/arch/arm64/Makefile
@@ -5,4 +5,5 @@ endif
 ifndef NO_LIBUNWIND
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind-libunwind.o
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/tests/regs_load.o
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/tests/dwarf-unwind.o
 endif
diff --git a/tools/perf/arch/arm64/include/perf_regs.h b/tools/perf/arch/arm64/include/perf_regs.h
index 1e052f1..e74df99 100644
--- a/tools/perf/arch/arm64/include/perf_regs.h
+++ b/tools/perf/arch/arm64/include/perf_regs.h
@@ -9,6 +9,9 @@
 #define PERF_REG_IP	PERF_REG_ARM64_PC
 #define PERF_REG_SP	PERF_REG_ARM64_SP
 
+#define PERF_REGS_MAX	PERF_REG_ARM64_MAX
+#define PERF_SAMPLE_REGS_ABI	PERF_SAMPLE_REGS_ABI_64
+
 void perf_regs_load(u64 *regs);
 
 static inline const char *perf_reg_name(int id)
diff --git a/tools/perf/arch/arm64/tests/dwarf-unwind.c b/tools/perf/arch/arm64/tests/dwarf-unwind.c
new file mode 100644
index 0000000..0aa64f3
--- /dev/null
+++ b/tools/perf/arch/arm64/tests/dwarf-unwind.c
@@ -0,0 +1,59 @@
+#include <string.h>
+#include "perf_regs.h"
+#include "thread.h"
+#include "map.h"
+#include "event.h"
+#include "tests/tests.h"
+
+#define STACK_SIZE 8192
+
+static int sample_ustack(struct perf_sample *sample,
+			 struct thread *thread, u64 *regs)
+{
+	struct stack_dump *stack = &sample->user_stack;
+	struct map *map;
+	unsigned long sp;
+	u64 stack_size, *buf;
+
+	buf = malloc(STACK_SIZE);
+	if (!buf) {
+		pr_debug("failed to allocate sample uregs data\n");
+		return -1;
+	}
+
+	sp = (unsigned long) regs[PERF_REG_ARM64_SP];
+
+	map = map_groups__find(&thread->mg, MAP__FUNCTION, (u64) sp);
+	if (!map) {
+		pr_debug("failed to get stack map\n");
+		return -1;
+	}
+
+	stack_size = map->end - sp;
+	stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size;
+
+	memcpy(buf, (void *) sp, stack_size);
+	stack->data = (char *) buf;
+	stack->size = stack_size;
+	return 0;
+}
+
+int test__arch_unwind_sample(struct perf_sample *sample,
+			     struct thread *thread)
+{
+	struct regs_dump *regs = &sample->user_regs;
+	u64 *buf;
+
+	buf = malloc(sizeof(u64) * PERF_REGS_MAX);
+	if (!buf) {
+		pr_debug("failed to allocate sample uregs data\n");
+		return -1;
+	}
+
+	perf_regs_load(buf);
+	regs->abi  = PERF_SAMPLE_REGS_ABI;
+	regs->regs = buf;
+	regs->mask = PERF_REGS_MASK;
+
+	return sample_ustack(sample, thread, buf);
+}
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 167d527..d802215 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -115,7 +115,8 @@ static struct test {
 		.desc = "Test parsing with no sample_id_all bit set",
 		.func = test__parse_no_sample_id_all,
 	},
-#if defined(__x86_64__) || defined(__i386__) || defined(__arm__)
+#if defined(__x86_64__) || defined(__i386__) || \
+    defined(__arm__) || defined(__aarch64__)
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
 	{
 		.desc = "Test dwarf unwind",
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 0c89cfe..e7bfddb 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -42,7 +42,8 @@ int test__keep_tracking(void);
 int test__parse_no_sample_id_all(void);
 int test__dwarf_unwind(void);
 
-#if defined(__x86_64__) || defined(__i386__) || defined(__arm__)
+#if defined(__x86_64__) || defined(__i386__) || \
+    defined(__arm__) || defined(__aarch64__)
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
 struct thread;
 struct perf_sample;
-- 
1.7.11.7