diff mbox

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

Message ID 1399391733-11927-4-git-send-email-jean.pihet@linaro.org (mailing list archive)
State New, archived
Headers show

Commit Message

Jean Pihet May 6, 2014, 3:55 p.m. UTC 
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

Comments

Will Deacon May 6, 2014, 5 p.m. UTC | #1 
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
Jean Pihet May 6, 2014, 5:41 p.m. UTC | #2 
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
Will Deacon May 6, 2014, 5:52 p.m. UTC | #3 
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
Jean Pihet May 7, 2014, 7:40 a.m. UTC | #4 
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@lists.infradead.org
> http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
diff mbox

Patch

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);
+}