Tags Tags

[RFCv5 00/23] perf: Add backtrace post dwarf unwind

June 19th, 2012 - 11:50 am ET by Jiri Olsa | Report spam
Help Create a new topic
hi,

patches available also as tarball in here:
http://people.redhat.com/~jolsa/perf_post_unwind_v6.tar.bz2

v6 changes:
patch 01/23 - unrelated - ftrace stuff
patch 03/23 - added PERF_SAMPLE_REGS_USER bit
- added regs_user initialization
patch 07/23 - added PERF_SAMPLE_STACK_USER bit
- sample_stack_user changed to u32 and
added size check
new patches 1,9,10,20

v5 changes:
patch 1/19 - having just one enum set of the perf registers
patch 2/19 - using for_each_set_bit for scanning the mask
- single regs enum for both 32 and 64 bits versions
- using regs mask != 0 trigger to trigger the regs dump
patch 5/19 - adding perf_output_skip so we can skip undumped part of the stack in RB
patch 6/19 - using stack size != 0 trigger to trigger the stack dump
- do not zero the memory for non retrieved part of the stack dump
patch 7/19 - adding exclude_callchain_kernel attribute
patch 8/19 - this could be taken without the rest of the series

v4 changes:
- no real change from v3, just rebase
- v3 patch 06/17 got already merged

v3 changes:
patch 01/17
- added HAVE_PERF_REGS config option
patch 02/17, 04/17
- regs and stack perf interface is more general now
patch 06/17
- unrelated online fix for i386 compilation
patch 16/17
- few namespace fixies


Adding the post unwinding user stack backtrace using dwarf unwind
via libunwind. The original work was done by Frederic. I mostly took
his patches and make them compile in current kernel code plus I added
some stuff here and there.

The main idea is to store user registers and portion of user
stack when the sample data during the record phase. Then during
the report, when the data is presented, perform the actual dwarf
dwarf unwind.

attached patches:
01/23 tracing/filter: Add missing initialization
02/23 perf: Unified API to record selective sets of arch registers
03/23 perf: Add ability to attach user level registers dump to sample
04/23 perf, x86: Add copy_from_user_nmi_nochk for best effort copy
05/23 perf: Factor __output_copy to be usable with specific copy function
06/23 perf: Add perf_output_skip function to skip bytes in sample
07/23 perf: Add ability to attach user stack dump to sample
08/23 perf: Add attribute to filter out callchains
09/23 x86_64: Store userspace rsp in system_call fastpath
10/23 perf, tool: Adding PERF_ATTR_SIZE_VER2 to the header swap check
11/23 perf, tool: Remove unsused evsel parameter from machine__resolve_callchain
12/23 perf, tool: Factor DSO symtab types to generic binary types
13/23 perf, tool: Add interface to read DSO image data
14/23 perf, tool: Add '.note' check into search for NOTE section
15/23 perf, tool: Back [vdso] DSO with real data
16/23 perf, tool: Add interface to arch registers sets
17/23 perf, tool: Add libunwind dependency for dwarf cfi unwinding
18/23 perf, tool: Support user regs and stack in sample parsing
19/23 perf, tool: Support for dwarf cfi unwinding on post processing
20/23 perf, tool: Adding round_up/round_down macros
21/23 perf, tool: Support for dwarf mode callchain on perf
22/23 perf, tool: Add dso data caching
23/23 perf, tool: Add dso data caching tests


I tested on Fedora. There was not much gain on i386, because the
binaries are compiled with frame pointers. Thought the dwarf
backtrace is more accurade and unwraps calls in more details
(functions that do not set the frame pointers).

I could see some improvement on x86_64, where I got full backtrace
where current code could got just the first address out of the
instruction pointer.

Example on x86_64:
[dwarf]
perf record -g -e syscalls:sys_enter_write date

100.00% date libc-2.14.90.so [.] __GI___libc_write
|
__GI___libc_write
_IO_file_write@@GLIBC_2.2.5
new_do_write
_IO_do_write@@GLIBC_2.2.5
_IO_file_overflow@@GLIBC_2.2.5
0x4022cd
0x401ee6
__libc_start_main
0x4020b9


[frame pointer]
perf record -g fp -e syscalls:sys_enter_write date

100.00% date libc-2.14.90.so [.] __GI___libc_write
|
__GI___libc_write

Also I tested on coreutils binaries mainly, but I could see
getting wider backtraces with dwarf unwind for more complex
application like firefox.

The unwind should go throught [vdso] object. I haven't studied
the [vsyscall] yet, so not sure there.

Attached patches should work on both x86 and x86_64. I did
some initial testing so far.

The unwind backtrace can be interrupted by following reasons:
- bug in unwind information of processed shared library
- bug in unwind processing code (most likely ;) )
- insufficient dump stack size
- wrong register value - x86_64 does not store whole
set of registers when in exception, but so far
it looks like RIP and RSP should be enough

thanks for comments,
jirka

arch/Kconfig | 6 +
arch/x86/Kconfig | 1 +
arch/x86/include/asm/perf_event.h | 2 +
arch/x86/include/asm/perf_regs.h | 34 ++
arch/x86/include/asm/uaccess.h | 2 +
arch/x86/kernel/Makefile | 2 +
arch/x86/kernel/entry_64.S | 5 +
arch/x86/kernel/perf_regs.c | 90 +++
arch/x86/lib/usercopy.c | 15 +-
include/linux/perf_event.h | 45 ++-
include/linux/perf_regs.h | 19 +
kernel/events/callchain.c | 25 +-
kernel/events/core.c | 184 +++++++-
kernel/events/internal.h | 69 ++-
kernel/events/ring_buffer.c | 10 +-
kernel/trace/trace_events_filter.c | 2 +-
tools/perf/Makefile | 45 ++-
tools/perf/arch/x86/Makefile | 3 +
tools/perf/arch/x86/include/perf_regs.h | 80 +++
tools/perf/arch/x86/util/unwind.c | 111 ++++
tools/perf/builtin-record.c | 106 ++++-
tools/perf/builtin-report.c | 24 +-
tools/perf/builtin-script.c | 56 ++-
tools/perf/builtin-test.c | 8 +-
tools/perf/builtin-top.c | 7 +-
tools/perf/config/feature-tests.mak | 25 +
tools/perf/perf.h | 9 +-
tools/perf/util/annotate.c | 2 +-
tools/perf/util/dso-test-data.c | 154 ++++++
tools/perf/util/event.h | 16 +-
tools/perf/util/evlist.c | 8 +
tools/perf/util/evlist.h | 1 +
tools/perf/util/evsel.c | 41 ++-
tools/perf/util/header.c | 3 +
tools/perf/util/include/linux/compiler.h | 1 +
tools/perf/util/include/linux/kernel.h | 10 +
tools/perf/util/map.c | 23 +-
tools/perf/util/map.h | 9 +-
tools/perf/util/perf_regs.h | 14 +
tools/perf/util/python.c | 3 +-
.../perf/util/scripting-engines/trace-event-perl.c | 3 +-
.../util/scripting-engines/trace-event-python.c | 3 +-
tools/perf/util/session.c | 111 ++++-
tools/perf/util/session.h | 15 +-
tools/perf/util/symbol.c | 435 ++++++++++++
tools/perf/util/symbol.h | 52 ++-
tools/perf/util/trace-event-scripting.c | 3 +-
tools/perf/util/trace-event.h | 5 +-
tools/perf/util/unwind.c | 567 ++++++++++++++++++++
tools/perf/util/unwind.h | 34 ++
tools/perf/util/vdso.c | 90 +++
tools/perf/util/vdso.h | 8 +
52 files changed, 2385 insertions(+), 211 deletions(-)
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
email Follow the discussionReplies 40 repliesReplies Make a reply

Replies

#1 Jiri Olsa
June 19th, 2012 - 11:50 am ET | Report spam
Introducing PERF_SAMPLE_REGS_USER sample type bit to trigger
the dump of user level registers on sample. Registers we want
to dump are specified by sample_regs_user bitmask.

Only user level registers are dump at the moment. Meaning the
register values of the user space context as it was before the
user entered the kernel for whatever reason (syscall, irq,
exception, or a PMI happening in userspace).

The layout of the sample_regs_user bitmap is described in
asm/perf_regs.h for archs that support register dump.

This is going to be useful to bring Dwarf CFI based stack
unwinding on top of samples.

Signed-off-by: Frederic Weisbecker
Signed-off-by: Jiri Olsa

include/linux/perf_event.h | 20 ++++++++++++--
kernel/events/core.c | 61 ++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 78 insertions(+), 3 deletions(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 1ce887a..969ee0b 100644
a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -130,8 +130,9 @@ enum perf_event_sample_format {
PERF_SAMPLE_STREAM_ID = 1U << 9,
PERF_SAMPLE_RAW = 1U << 10,
PERF_SAMPLE_BRANCH_STACK = 1U << 11,
+ PERF_SAMPLE_REGS_USER = 1U << 12,

- PERF_SAMPLE_MAX = 1U << 12, /* non-ABI */
+ PERF_SAMPLE_MAX = 1U << 13, /* non-ABI */
};

/*
@@ -194,6 +195,7 @@ enum perf_event_read_format {
#define PERF_ATTR_SIZE_VER0 64 /* sizeof first published struct */
#define PERF_ATTR_SIZE_VER1 72 /* add: config2 */
#define PERF_ATTR_SIZE_VER2 80 /* add: branch_sample_type */
+#define PERF_ATTR_SIZE_VER3 88 /* add: sample_regs_user */

/*
* Hardware event_id to monitor via a performance monitoring event:
@@ -271,7 +273,13 @@ struct perf_event_attr {
__u64 bp_len;
__u64 config2; /* extension of config1 */
};
- __u64 branch_sample_type; /* enum branch_sample_type */
+ __u64 branch_sample_type; /* enum perf_branch_sample_type */
+
+ /*
+ * Defines set of user regs to dump on samples.
+ * See asm/perf_regs.h for details.
+ */
+ __u64 sample_regs_user;
};

/*
@@ -548,6 +556,9 @@ enum perf_event_type {
* char data[size];}&& PERF_SAMPLE_RAW
*
* { u64 from, to, flags } lbr[nr];} && PERF_SAMPLE_BRANCH_STACK
+ *
+ * { u64 available;
+ * u64 regs[weight(mask)]; } && PERF_SAMPLE_REGS_USER
* };
*/
PERF_RECORD_SAMPLE = 9,
@@ -609,6 +620,7 @@ struct perf_guest_info_callbacks {
#include <linux/static_key.h>
#include <linux/atomic.h>
#include <linux/sysfs.h>
+#include <linux/perf_regs.h>
#include <asm/local.h>

struct perf_callchain_entry {
@@ -1131,6 +1143,7 @@ struct perf_sample_data {
struct perf_callchain_entry *callchain;
struct perf_raw_record *raw;
struct perf_branch_stack *br_stack;
+ struct pt_regs *regs_user;
};

static inline void perf_sample_data_init(struct perf_sample_data *data,
@@ -1140,7 +1153,8 @@ static inline void perf_sample_data_init(struct perf_sample_data *data,
data->addr = addr;
data->raw = NULL;
data->br_stack = NULL;
- data->period = period;
+ data->period = period;
+ data->regs_user = NULL;
}

extern void perf_output_sample(struct perf_output_handle *handle,
diff --git a/kernel/events/core.c b/kernel/events/core.c
index f85c015..7df37e0 100644
a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3750,6 +3750,33 @@ int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs)
}
EXPORT_SYMBOL_GPL(perf_unregister_guest_info_callbacks);

+static void
+perf_output_sample_regs(struct perf_output_handle *handle,
+ struct pt_regs *regs, u64 mask)
+{
+ int bit;
+
+ for_each_set_bit(bit, (const unsigned long *) &mask,
+ sizeof(mask) * BITS_PER_BYTE) {
+ u64 val;
+
+ val = perf_reg_value(regs, bit);
+ perf_output_put(handle, val);
+ }
+}
+
+static struct pt_regs *perf_sample_regs_user(struct pt_regs *regs)
+{
+ if (!user_mode(regs)) {
+ if (current->mm)
+ regs = task_pt_regs(current);
+ else
+ regs = NULL;
+ }
+
+ return regs;
+}
+
static void __perf_event_header__init_id(struct perf_event_header *header,
struct perf_sample_data *data,
struct perf_event *event)
@@ -4010,6 +4037,23 @@ void perf_output_sample(struct perf_output_handle *handle,
perf_output_put(handle, nr);
}
}
+
+ if (sample_type & PERF_SAMPLE_REGS_USER) {
+ u64 avail = (data->regs_user != NULL);
+
+ /*
+ * If there are no regs to dump, notice it through
+ * first u64 being zero.
+ */
+ perf_output_put(handle, avail);
+
+ if (avail) {
+ u64 mask = event->attr.sample_regs_user;
+ perf_output_sample_regs(handle,
+ data->regs_user,
+ mask);
+ }
+ }
}

void perf_prepare_sample(struct perf_event_header *header,
@@ -4061,6 +4105,19 @@ void perf_prepare_sample(struct perf_event_header *header,
}
header->size += size;
}
+
+ if (sample_type & PERF_SAMPLE_REGS_USER) {
+ /* regs dump available bool */
+ int size = sizeof(u64);
+
+ data->regs_user = perf_sample_regs_user(regs);
+ if (data->regs_user) {
+ u64 mask = event->attr.sample_regs_user;
+ size += hweight64(mask) * sizeof(u64);
+ }
+
+ header->size += size;
+ }
}

static void perf_event_output(struct perf_event *event,
@@ -6110,6 +6167,10 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
attr->branch_sample_type = mask;
}
}
+
+ if (attr->sample_type & PERF_SAMPLE_REGS_USER)
+ ret = perf_reg_validate(attr->sample_regs_user);
+
out:
return ret;

1.7.7.6

To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

Similar topics

Make your own search :