From: Jiri Olsa <jolsa@redhat.com>
To: acme@redhat.com, a.p.zijlstra@chello.nl, mingo@elte.hu,
paulus@samba.org, cjashfor@linux.vnet.ibm.com,
fweisbec@gmail.com
Cc: eranian@google.com, gorcunov@openvz.org, tzanussi@gmail.com,
mhiramat@redhat.com, robert.richter@amd.com, fche@redhat.com,
linux-kernel@vger.kernel.org, masami.hiramatsu.pt@hitachi.com,
drepper@gmail.com, asharma@fb.com,
benjamin.redelings@nescent.org, Jiri Olsa <jolsa@redhat.com>
Subject: [PATCH 06/17] perf: Add ability to attach user stack dump to sample
Date: Sun, 22 Jul 2012 14:14:29 +0200 [thread overview]
Message-ID: <1342959280-5361-7-git-send-email-jolsa@redhat.com> (raw)
In-Reply-To: <1342959280-5361-1-git-send-email-jolsa@redhat.com>
Introducing PERF_SAMPLE_STACK_USER sample type bit to trigger
the dump of the user level stack on sample. The size of the
dump is specified by sample_stack_user value.
Being able to dump parts of the user stack, starting from the
stack pointer, will be useful to make a post mortem dwarf CFI
based stack unwinding.
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
---
include/linux/perf_event.h | 18 ++++++-
kernel/events/core.c | 121 +++++++++++++++++++++++++++++++++++++++++++-
2 files changed, 137 insertions(+), 2 deletions(-)
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index a4c53da..b4663b3 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -131,8 +131,9 @@ enum perf_event_sample_format {
PERF_SAMPLE_RAW = 1U << 10,
PERF_SAMPLE_BRANCH_STACK = 1U << 11,
PERF_SAMPLE_REGS_USER = 1U << 12,
+ PERF_SAMPLE_STACK_USER = 1U << 13,
- PERF_SAMPLE_MAX = 1U << 13, /* non-ABI */
+ PERF_SAMPLE_MAX = 1U << 14, /* non-ABI */
};
/*
@@ -196,6 +197,7 @@ enum perf_event_read_format {
#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 */
+#define PERF_ATTR_SIZE_VER4 96 /* add: sample_stack_user */
/*
* Hardware event_id to monitor via a performance monitoring event:
@@ -280,6 +282,14 @@ struct perf_event_attr {
* See asm/perf_regs.h for details.
*/
__u64 sample_regs_user;
+
+ /*
+ * Defines size of the user stack to dump on samples.
+ */
+ __u32 sample_stack_user;
+
+ /* Align to u64. */
+ __u32 __reserved_2;
};
/*
@@ -559,6 +569,10 @@ enum perf_event_type {
*
* { u64 available;
* u64 regs[weight(mask)]; } && PERF_SAMPLE_REGS_USER
+ *
+ * { u64 size;
+ * char data[size];
+ * u64 dyn_size; } && PERF_SAMPLE_STACK_USER
* };
*/
PERF_RECORD_SAMPLE = 9,
@@ -1146,6 +1160,7 @@ struct perf_sample_data {
struct perf_raw_record *raw;
struct perf_branch_stack *br_stack;
struct pt_regs *regs_user;
+ u64 stack_user_size;
};
static inline void perf_sample_data_init(struct perf_sample_data *data,
@@ -1157,6 +1172,7 @@ static inline void perf_sample_data_init(struct perf_sample_data *data,
data->br_stack = NULL;
data->period = period;
data->regs_user = NULL;
+ data->stack_user_size = 0;
}
extern void perf_output_sample(struct perf_output_handle *handle,
diff --git a/kernel/events/core.c b/kernel/events/core.c
index e817e32..8a9cf80 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3771,6 +3771,45 @@ perf_output_sample_regs(struct perf_output_handle *handle,
}
}
+static void
+perf_output_sample_ustack(struct perf_output_handle *handle, u64 dump_size,
+ struct pt_regs *regs)
+{
+ /* Case of a kernel thread, nothing to dump */
+ if (!regs) {
+ u64 size = 0;
+ perf_output_put(handle, size);
+ } else {
+ unsigned long sp;
+ unsigned int rem;
+ u64 dyn_size;
+
+ /*
+ * We dump:
+ * static size
+ * - the size requested by user or the best one we can fit
+ * in to the sample max size
+ * data
+ * - user stack dump data
+ * dynamic size
+ * - the actual dumped size
+ */
+
+ /* Static size. */
+ perf_output_put(handle, dump_size);
+
+ /* Data. */
+ sp = user_stack_pointer(regs);
+ rem = __output_copy_user(handle, (void *) sp, dump_size);
+ dyn_size = dump_size - rem;
+
+ perf_output_skip(handle, rem);
+
+ /* Dynamic size. */
+ perf_output_put(handle, dyn_size);
+ }
+}
+
static struct pt_regs *perf_sample_regs_user(struct pt_regs *regs)
{
if (!user_mode(regs)) {
@@ -4060,6 +4099,11 @@ void perf_output_sample(struct perf_output_handle *handle,
mask);
}
}
+
+ if (sample_type & PERF_SAMPLE_STACK_USER)
+ perf_output_sample_ustack(handle,
+ data->stack_user_size,
+ data->regs_user);
}
void perf_prepare_sample(struct perf_event_header *header,
@@ -4124,6 +4168,66 @@ void perf_prepare_sample(struct perf_event_header *header,
header->size += size;
}
+
+ if (sample_type & PERF_SAMPLE_STACK_USER) {
+ /*
+ * A first field that tells the _static_ size of the
+ * dump. 0 if there is nothing to dump (ie: we are in
+ * a kernel thread) otherwise the requested size.
+ */
+ u16 size = sizeof(u64);
+ u16 stack_size = 0;
+
+ if (!data->regs_user)
+ data->regs_user = perf_sample_regs_user(regs);
+
+ /*
+ * If there is something to dump, add space for the
+ * dump itself and for the field that tells the
+ * dynamic size, which is how many have been actually
+ * dumped.
+ */
+ if (data->regs_user) {
+ /*
+ * XXX We need to check if we fit in with the
+ * requested stack size into the sample. If we
+ * don't, we customize the stack size to fit in.
+ *
+ * Either we need PERF_SAMPLE_STACK_USER bit to
+ * be allways processed as the last one or have
+ * additional check added in case new sample type
+ * is added, because we could eat up the rest of
+ * the sample size.
+ */
+
+ u16 header_size = header->size;
+
+ stack_size = (u16) event->attr.sample_stack_user;
+
+ /*
+ * Current header size plus static size and
+ * dynamic size.
+ */
+ header_size += 2 * sizeof(u64);
+
+ /* Do we fit in with the current stack dump size? */
+ if ((u16) (header_size + stack_size) < header_size) {
+ /*
+ * If we overflow the maximum size for the
+ * sample, we customize the stack dump size
+ * to fit in.
+ */
+ stack_size = USHRT_MAX - header_size
+ - sizeof(u64);
+ stack_size = round_up(stack_size, sizeof(u64));
+ }
+
+ size += sizeof(u64) + stack_size;
+ }
+
+ data->stack_user_size = stack_size;
+ header->size += size;
+ }
}
static void perf_event_output(struct perf_event *event,
@@ -6174,8 +6278,23 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
}
}
- if (attr->sample_type & PERF_SAMPLE_REGS_USER)
+ if (attr->sample_type & PERF_SAMPLE_REGS_USER) {
ret = perf_reg_validate(attr->sample_regs_user);
+ if (ret)
+ return ret;
+ }
+
+ if (attr->sample_type & PERF_SAMPLE_STACK_USER) {
+ /*
+ * We have __u32 type for the size, but so far
+ * we can only use __u16 as maximum due to the
+ * __u16 sample size limit.
+ */
+ if (attr->sample_stack_user >= USHRT_MAX)
+ ret = -EINVAL;
+ else if (!IS_ALIGNED(attr->sample_stack_user, sizeof(u64)))
+ ret = -EINVAL;
+ }
out:
return ret;
--
1.7.7.6
next prev parent reply other threads:[~2012-07-22 12:15 UTC|newest]
Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-07-22 12:14 [PATCHv7 00/17] perf: Add backtrace post dwarf unwind Jiri Olsa
2012-07-22 12:14 ` [PATCH 01/17] perf: Unified API to record selective sets of arch registers Jiri Olsa
2012-07-25 16:12 ` Frederic Weisbecker
2012-07-26 17:51 ` Arnaldo Carvalho de Melo
2012-07-29 22:45 ` Paul Mackerras
2012-07-22 12:14 ` [PATCH 02/17] perf: Add ability to attach user level registers dump to sample Jiri Olsa
2012-07-25 16:13 ` Frederic Weisbecker
2012-07-25 17:00 ` Arnaldo Carvalho de Melo
2012-07-25 17:39 ` Stephane Eranian
2012-07-25 18:27 ` Jiri Olsa
2012-07-26 17:42 ` Stephane Eranian
2012-07-26 17:58 ` Jiri Olsa
2012-07-22 12:14 ` [PATCH 03/17] perf, x86: Add copy_from_user_nmi_nochk for best effort copy Jiri Olsa
2012-07-25 16:11 ` Frederic Weisbecker
2012-07-25 17:16 ` Jiri Olsa
2012-07-25 17:25 ` Frederic Weisbecker
2012-07-25 17:30 ` Jiri Olsa
2012-07-25 17:35 ` Frederic Weisbecker
2012-08-02 18:47 ` Andy Lutomirski
2012-08-03 11:12 ` Jiri Olsa
2012-07-22 12:14 ` [PATCH 04/17] perf: Factor __output_copy to be usable with specific copy function Jiri Olsa
2012-07-22 12:14 ` [PATCH 05/17] perf: Add perf_output_skip function to skip bytes in sample Jiri Olsa
2012-07-22 12:14 ` Jiri Olsa [this message]
2012-07-25 16:36 ` [PATCH 06/17] perf: Add ability to attach user stack dump to sample Frederic Weisbecker
2012-07-25 17:03 ` Jiri Olsa
2012-07-22 12:14 ` [PATCH 07/17] perf: Add attribute to filter out callchains Jiri Olsa
2012-07-22 12:14 ` [PATCH 08/17] perf, tool: Adding PERF_ATTR_SIZE_VER2 to the header swap check Jiri Olsa
2012-07-22 12:14 ` [PATCH 09/17] perf, tool: Factor DSO symtab types to generic binary types Jiri Olsa
2012-07-25 19:24 ` [tip:perf/core] perf symbols: " tip-bot for Jiri Olsa
2012-07-22 12:14 ` [PATCH 10/17] perf, tool: Add interface to read DSO image data Jiri Olsa
2012-07-25 19:25 ` [tip:perf/core] perf symbols: " tip-bot for Jiri Olsa
2012-07-22 12:14 ` [PATCH 11/17] perf, tool: Add interface to arch registers sets Jiri Olsa
2012-07-22 12:14 ` [PATCH 12/17] perf, tool: Add libunwind dependency for dwarf cfi unwinding Jiri Olsa
2012-07-22 12:14 ` [PATCH 13/17] perf, tool: Support user regs and stack in sample parsing Jiri Olsa
2012-07-22 12:14 ` [PATCH 14/17] perf, tool: Support for dwarf cfi unwinding on post processing Jiri Olsa
2012-07-25 17:05 ` Frederic Weisbecker
2012-07-25 17:16 ` Arnaldo Carvalho de Melo
2012-07-25 17:21 ` Frederic Weisbecker
2012-07-22 12:14 ` [PATCH 15/17] perf, tool: Support for dwarf mode callchain on perf record Jiri Olsa
2012-07-22 12:14 ` [PATCH 16/17] perf, tool: Add dso data caching Jiri Olsa
2012-07-25 17:11 ` Frederic Weisbecker
2012-07-25 19:26 ` [tip:perf/core] perf symbols: " tip-bot for Jiri Olsa
2012-07-22 12:14 ` [PATCH 17/17] perf, tool: Add dso data caching tests Jiri Olsa
2012-07-25 19:28 ` [tip:perf/core] perf test: " tip-bot for Jiri Olsa
2012-07-25 17:15 ` [PATCHv7 00/17] perf: Add backtrace post dwarf unwind Frederic Weisbecker
2012-07-25 17:19 ` Ingo Molnar
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=1342959280-5361-7-git-send-email-jolsa@redhat.com \
--to=jolsa@redhat.com \
--cc=a.p.zijlstra@chello.nl \
--cc=acme@redhat.com \
--cc=asharma@fb.com \
--cc=benjamin.redelings@nescent.org \
--cc=cjashfor@linux.vnet.ibm.com \
--cc=drepper@gmail.com \
--cc=eranian@google.com \
--cc=fche@redhat.com \
--cc=fweisbec@gmail.com \
--cc=gorcunov@openvz.org \
--cc=linux-kernel@vger.kernel.org \
--cc=masami.hiramatsu.pt@hitachi.com \
--cc=mhiramat@redhat.com \
--cc=mingo@elte.hu \
--cc=paulus@samba.org \
--cc=robert.richter@amd.com \
--cc=tzanussi@gmail.com \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®