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 06/19] perf: Add ability to attach user stack dump to sample
Date: Mon, 11 Jun 2012 15:20:01 +0200 [thread overview]
Message-ID: <1339420814-7379-7-git-send-email-jolsa@redhat.com> (raw)
In-Reply-To: <1339420814-7379-1-git-send-email-jolsa@redhat.com>
Introducing sample_stack_user value into the perf_event_attr
struct to define the size of the user stack dump to be attached
to the sample. The dump itself is triggered once the
sample_stack_user is not zero.
Beeing 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: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
---
include/linux/perf_event.h | 5 +++
kernel/events/core.c | 66 ++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 71 insertions(+), 0 deletions(-)
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 8960968..8db1655 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -278,6 +278,11 @@ 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.
+ */
+ __u64 sample_stack_user;
};
/*
diff --git a/kernel/events/core.c b/kernel/events/core.c
index e4df59d..c1062a1 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3765,6 +3765,38 @@ 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;
+
+ /*
+ * Static size: we always dump the size
+ * requested by the user because most of the
+ * time, the top of the user stack is not
+ * paged out.
+ */
+ perf_output_put(handle, dump_size);
+
+ 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: whole dump - padding. */
+ perf_output_put(handle, dyn_size);
+ }
+}
+
static struct pt_regs *perf_sample_regs_user(struct pt_regs *regs)
{
if (!user_mode(regs)) {
@@ -4054,6 +4086,11 @@ void perf_output_sample(struct perf_output_handle *handle,
mask);
}
}
+
+ if (event->attr.sample_stack_user)
+ perf_output_sample_ustack(handle,
+ event->attr.sample_stack_user,
+ data->regs_user);
}
void perf_prepare_sample(struct perf_event_header *header,
@@ -4118,6 +4155,31 @@ void perf_prepare_sample(struct perf_event_header *header,
header->size += size;
}
+
+ if (event->attr.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.
+ */
+ int size = sizeof(u64);
+
+ 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) {
+ size += event->attr.sample_stack_user;
+ size += sizeof(u64);
+ }
+
+ header->size += size;
+ }
}
static void perf_event_output(struct perf_event *event,
@@ -6171,6 +6233,10 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
if (attr->sample_regs_user)
ret = perf_reg_validate(attr->sample_regs_user);
+ if (attr->sample_stack_user)
+ attr->sample_stack_user = round_up(attr->sample_stack_user,
+ sizeof(u64));
+
out:
return ret;
--
1.7.7.6
next prev parent reply other threads:[~2012-06-11 13:21 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-06-11 13:19 [RFCv5 00/19] perf: Add backtrace post dwarf unwind Jiri Olsa
2012-06-11 13:19 ` [PATCH 01/19] perf: Unified API to record selective sets of arch registers Jiri Olsa
2012-06-11 13:19 ` [PATCH 02/19] perf: Add ability to attach user level registers dump to sample Jiri Olsa
2012-06-13 11:16 ` Stephane Eranian
2012-06-13 13:12 ` Jiri Olsa
2012-06-13 13:18 ` Stephane Eranian
2012-06-13 13:23 ` Jiri Olsa
2012-06-13 13:25 ` Stephane Eranian
2012-06-13 13:40 ` Peter Zijlstra
2012-06-13 13:41 ` Stephane Eranian
2012-06-13 13:51 ` Stephane Eranian
2012-06-14 8:36 ` Peter Zijlstra
2012-06-14 10:45 ` Stephane Eranian
2012-06-14 10:50 ` Peter Zijlstra
2012-06-14 10:56 ` Peter Zijlstra
2012-06-13 13:37 ` Peter Zijlstra
2012-06-13 13:29 ` Stephane Eranian
2012-06-11 13:19 ` [PATCH 03/19] perf, x86: Add copy_from_user_nmi_nochk for best effort copy Jiri Olsa
2012-06-11 13:19 ` [PATCH 04/19] perf: Factor __output_copy to be usable with specific copy function Jiri Olsa
2012-06-11 13:20 ` [PATCH 05/19] perf: Add perf_output_skip function to skip bytes in sample Jiri Olsa
2012-06-11 13:20 ` Jiri Olsa [this message]
2012-06-11 13:20 ` [PATCH 07/19] perf: Add attribute to filter out callchains Jiri Olsa
2012-06-11 13:20 ` [PATCH 08/19] perf, tool: Remove unsused evsel parameter from machine__resolve_callchain Jiri Olsa
2012-06-20 16:59 ` [tip:perf/core] perf tools: Remove unused " tip-bot for Jiri Olsa
2012-06-11 13:20 ` [PATCH 09/19] perf, tool: Factor DSO symtab types to generic binary types Jiri Olsa
2012-06-11 13:20 ` [PATCH 10/19] perf, tool: Add interface to read DSO image data Jiri Olsa
2012-06-11 13:20 ` [PATCH 11/19] perf, tool: Add '.note' check into search for NOTE section Jiri Olsa
2012-06-11 13:20 ` [PATCH 12/19] perf, tool: Back [vdso] DSO with real data Jiri Olsa
2012-06-29 18:49 ` Arnaldo Carvalho de Melo
2012-06-11 13:20 ` [PATCH 13/19] perf, tool: Add interface to arch registers sets Jiri Olsa
2012-06-11 13:20 ` [PATCH 14/19] perf, tool: Add libunwind dependency for dwarf cfi unwinding Jiri Olsa
2012-06-11 13:20 ` [PATCH 15/19] perf, tool: Support user regs and stack in sample parsing Jiri Olsa
2012-06-11 13:20 ` [PATCH 16/19] perf, tool: Support for dwarf cfi unwinding on post processing Jiri Olsa
2012-06-11 13:20 ` [PATCH 17/19] perf, tool: Support for dwarf mode callchain on perf record Jiri Olsa
2012-06-11 13:20 ` [PATCH 18/19] perf, tool: Add dso data caching Jiri Olsa
2012-06-11 13:20 ` [PATCH 19/19] perf, tool: Add dso data caching tests Jiri Olsa
2012-06-11 21:44 ` [RFCv5 00/19] perf: Add backtrace post dwarf unwind Benjamin Redelings
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=1339420814-7379-7-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®