From: kan.liang@intel.com
To: a.p.zijlstra@chello.nl, eranian@google.com
Cc: linux-kernel@vger.kernel.org, mingo@redhat.com, paulus@samba.org,
acme@kernel.org, ak@linux.intel.com, kan.liang@intel.com, "Yan,
Zheng" <zheng.z.yan@intel.com>
Subject: [PATCH V5 11/16] perf, core: Pass perf_sample_data to perf_callchain()
Date: Wed, 10 Sep 2014 10:09:08 -0400 [thread overview]
Message-ID: <1410358153-421-12-git-send-email-kan.liang@intel.com> (raw)
In-Reply-To: <1410358153-421-1-git-send-email-kan.liang@intel.com>
From: Kan Liang <kan.liang@intel.com>
Haswell has a new feature that utilizes the existing Last Branch Record
facility to record call chains. When the feature is enabled, function
call will be collected as normal, but as return instructions are
executed the last captured branch record is popped from the on-chip LBR
registers.
The LBR call stack facility can help perf to get call chains of progam
without frame pointer.
This patch modifies various architectures' perf_callchain() to accept
perf sample data. Later patch will add code that use the sample data to
get call chains.
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
---
arch/arm/kernel/perf_event.c | 4 ++--
arch/powerpc/perf/callchain.c | 4 ++--
arch/sparc/kernel/perf_event.c | 4 ++--
arch/x86/kernel/cpu/perf_event.c | 4 ++--
include/linux/perf_event.h | 4 +++-
kernel/events/callchain.c | 8 +++++---
kernel/events/core.c | 2 +-
kernel/events/internal.h | 3 ++-
8 files changed, 19 insertions(+), 14 deletions(-)
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 266cba4..9532bd0 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -584,8 +584,8 @@ user_backtrace(struct frame_tail __user *tail,
return buftail.fp - 1;
}
-void
-perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
+void perf_callchain_user(struct perf_callchain_entry *entry,
+ struct pt_regs *regs, struct perf_sample_data *data)
{
struct frame_tail __user *tail;
diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c
index 74d1e78..b379ebc 100644
--- a/arch/powerpc/perf/callchain.c
+++ b/arch/powerpc/perf/callchain.c
@@ -482,8 +482,8 @@ static void perf_callchain_user_32(struct perf_callchain_entry *entry,
}
}
-void
-perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
+void perf_callchain_user(struct perf_callchain_entry *entry,
+ struct pt_regs *regs, struct perf_sample_data *data)
{
if (current_is_64bit())
perf_callchain_user_64(entry, regs);
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index d35c490..9078fe2 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -1791,8 +1791,8 @@ static void perf_callchain_user_32(struct perf_callchain_entry *entry,
} while (entry->nr < PERF_MAX_STACK_DEPTH);
}
-void
-perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
+void perf_callchain_user(struct perf_callchain_entry *entry,
+ struct pt_regs *regs, struct perf_sample_data *data)
{
perf_callchain_store(entry, regs->tpc);
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index a18fd78..71e293a 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -2049,8 +2049,8 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
}
#endif
-void
-perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
+void perf_callchain_user(struct perf_callchain_entry *entry,
+ struct pt_regs *regs, struct perf_sample_data *data)
{
struct stack_frame frame;
const void __user *fp;
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index a190e91..8db3520 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -735,7 +735,9 @@ extern void perf_event_fork(struct task_struct *tsk);
/* Callchains */
DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry);
-extern void perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs);
+extern void perf_callchain_user(struct perf_callchain_entry *entry,
+ struct pt_regs *regs,
+ struct perf_sample_data *data);
extern void perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs);
static inline void perf_callchain_store(struct perf_callchain_entry *entry, u64 ip)
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index f2a88de..4a18e1e 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -30,7 +30,8 @@ __weak void perf_callchain_kernel(struct perf_callchain_entry *entry,
}
__weak void perf_callchain_user(struct perf_callchain_entry *entry,
- struct pt_regs *regs)
+ struct pt_regs *regs,
+ struct perf_sample_data *data)
{
}
@@ -157,7 +158,8 @@ put_callchain_entry(int rctx)
}
struct perf_callchain_entry *
-perf_callchain(struct perf_event *event, struct pt_regs *regs)
+perf_callchain(struct perf_event *event, struct pt_regs *regs,
+ struct perf_sample_data *data)
{
int rctx;
struct perf_callchain_entry *entry;
@@ -198,7 +200,7 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs)
goto exit_put;
perf_callchain_store(entry, PERF_CONTEXT_USER);
- perf_callchain_user(entry, regs);
+ perf_callchain_user(entry, regs, data);
}
}
diff --git a/kernel/events/core.c b/kernel/events/core.c
index b37f2f3..eed0424 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4885,7 +4885,7 @@ void perf_prepare_sample(struct perf_event_header *header,
if (sample_type & PERF_SAMPLE_CALLCHAIN) {
int size = 1;
- data->callchain = perf_callchain(event, regs);
+ data->callchain = perf_callchain(event, regs, data);
if (data->callchain)
size += data->callchain->nr;
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index 569b2187..cd18b64 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -147,7 +147,8 @@ DEFINE_OUTPUT_COPY(__output_copy_user, arch_perf_out_copy_user)
/* Callchain handling */
extern struct perf_callchain_entry *
-perf_callchain(struct perf_event *event, struct pt_regs *regs);
+perf_callchain(struct perf_event *event, struct pt_regs *regs,
+ struct perf_sample_data *data);
extern int get_callchain_buffers(void);
extern void put_callchain_buffers(void);
--
1.8.3.2
next prev parent reply other threads:[~2014-09-10 14:10 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-09-10 14:08 [PATCH V5 00/16] perf, x86: Haswell LBR call stack support kan.liang
2014-09-10 14:08 ` [PATCH V5 01/16] perf, x86: Reduce lbr_sel_map size kan.liang
2014-09-24 10:50 ` Peter Zijlstra
2014-09-10 14:08 ` [PATCH V5 02/16] perf, core: introduce pmu context switch callback kan.liang
2014-09-24 11:23 ` Peter Zijlstra
2014-09-24 13:13 ` Peter Zijlstra
2014-09-10 14:09 ` [PATCH V5 03/16] perf, x86: use context switch callback to flush LBR stack kan.liang
2014-09-10 14:09 ` [PATCH V5 04/16] perf, x86: Basic Haswell LBR call stack support kan.liang
2014-09-10 14:09 ` [PATCH V5 05/16] perf, core: pmu specific data for perf task context kan.liang
2014-09-10 14:09 ` [PATCH V5 06/16] perf, core: always switch pmu specific data during context switch kan.liang
2014-09-10 14:09 ` [PATCH V5 07/16] perf, x86: allocate space for storing LBR stack kan.liang
2014-09-10 14:09 ` [PATCH V5 08/16] perf, x86: track number of events that use LBR callstack kan.liang
2014-09-24 12:53 ` Peter Zijlstra
2014-10-07 2:59 ` Liang, Kan
2014-10-07 15:19 ` Peter Zijlstra
2014-09-10 14:09 ` [PATCH V5 09/16] perf, x86: Save/resotre LBR stack during context switch kan.liang
2014-09-24 13:33 ` Peter Zijlstra
2014-09-10 14:09 ` [PATCH V5 10/16] perf, core: simplify need branch stack check kan.liang
2014-09-24 13:55 ` Peter Zijlstra
2014-09-10 14:09 ` kan.liang [this message]
2014-09-24 14:15 ` [PATCH V5 11/16] perf, core: Pass perf_sample_data to perf_callchain() Peter Zijlstra
2014-10-07 3:00 ` Liang, Kan
2014-10-07 15:24 ` Peter Zijlstra
2014-10-07 15:50 ` Liang, Kan
2014-10-07 16:29 ` Peter Zijlstra
2014-09-10 14:09 ` [PATCH V5 12/16] perf, x86: use LBR call stack to get user callchain kan.liang
2014-09-10 14:09 ` [PATCH V5 13/16] perf, x86: re-organize code that implicitly enables LBR/PEBS kan.liang
2014-09-10 14:09 ` [PATCH V5 14/16] perf, x86: enable LBR callstack when recording callchain kan.liang
2014-09-24 14:21 ` Peter Zijlstra
2014-10-07 3:00 ` Liang, Kan
2014-10-07 15:25 ` Peter Zijlstra
2014-10-07 16:04 ` Liang, Kan
2014-09-10 14:09 ` [PATCH V5 15/16] perf, x86: disable FREEZE_LBRS_ON_PMI when LBR operates in callstack mode kan.liang
2014-09-10 14:09 ` [PATCH V5 16/16] perf, x86: Discard zero length call entries in LBR call stack kan.liang
-- strict thread matches above, loose matches on Subject: below --
2014-07-07 6:28 [PATCH v5 00/16] perf, x86: Haswell LBR call stack support Yan, Zheng
2014-07-07 6:28 ` [PATCH v5 11/16] perf, core: Pass perf_sample_data to perf_callchain() Yan, Zheng
2001-01-08 2:31 [PATCH V5 10/16] perf, core: simplify need branch stack check kan.liang
2001-01-08 2:31 ` [PATCH V5 11/16] perf, core: Pass perf_sample_data to perf_callchain() kan.liang
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=1410358153-421-12-git-send-email-kan.liang@intel.com \
--to=kan.liang@intel.com \
--cc=a.p.zijlstra@chello.nl \
--cc=acme@kernel.org \
--cc=ak@linux.intel.com \
--cc=eranian@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=paulus@samba.org \
--cc=zheng.z.yan@intel.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