From: Andy Lutomirski <luto@amacapital.net>
To: "Jiri Olsa" <jolsa@redhat.com>, "Ingo Molnar" <mingo@redhat.com>,
"Peter Zijlstra" <peterz@infradead.org>,
"秦承刚(承刚)" <chenggang.qcg@alibaba-inc.com>
Cc: "Andy Lutomirski" <luto@amacapital.net>,
"Stephane Eranian" <eranian@google.com>,
root <chenggang.qin@gmail.com>,
"Andrew Morton" <akpm@linux-foundation.org>,
"秦承刚(承刚)" <chenggang.qcg@taobao.com>,
"Wu Fengguang" <fengguang.wu@intel.com>,
"Namhyung Kim" <namhyung@gmail.com>,
"Mike Galbraith" <efault@gmx.de>,
"Arjan van de Ven" <arjan@linux.intel.com>,
linux-kernel <linux-kernel@vger.kernel.org>,
"David Ahern" <dsahern@gmail.com>,
"Paul Mackerras" <paulus@samba.org>,
"Yanmin Zhang" <yanmin.zhang@intel.com>
Subject: [PATCH 1/2] perf: Move task_pt_regs sampling into arch code
Date: Sun, 4 Jan 2015 10:36:19 -0800
Message-ID: <e431cd4c18c2e1c44c774f10758527fb2d1025c4.1420396372.git.luto@amacapital.net> (raw)
In-Reply-To: <cover.1420396372.git.luto@amacapital.net>
In-Reply-To: <cover.1420396372.git.luto@amacapital.net>
On x86_64, at least, task_pt_regs may be only partially initialized
in many contexts, so x86_64 should not use it without extra care
from interrupt context, let alone NMI context.
This will allow x86_64 to override the logic and will supply some
scratch space to use to make a cleaner copy of user regs.
Signed-off-by: Andy Lutomirski <luto@amacapital.net>
---
arch/arm/kernel/perf_regs.c | 8 ++++++++
arch/arm64/kernel/perf_regs.c | 8 ++++++++
arch/x86/kernel/perf_regs.c | 16 ++++++++++++++++
include/linux/perf_event.h | 12 +++++++-----
include/linux/perf_regs.h | 16 ++++++++++++++++
kernel/events/core.c | 19 ++++++++-----------
6 files changed, 63 insertions(+), 16 deletions(-)
diff --git a/arch/arm/kernel/perf_regs.c b/arch/arm/kernel/perf_regs.c
index 6e4379c67cbc..592dda3f21ff 100644
--- a/arch/arm/kernel/perf_regs.c
+++ b/arch/arm/kernel/perf_regs.c
@@ -28,3 +28,11 @@ u64 perf_reg_abi(struct task_struct *task)
{
return PERF_SAMPLE_REGS_ABI_32;
}
+
+void perf_get_regs_user(struct perf_regs *regs_user,
+ struct pt_regs *regs,
+ struct pt_regs *regs_user_copy)
+{
+ regs_user->regs = task_pt_regs(current);
+ regs_user->abi = perf_reg_abi(current);
+}
diff --git a/arch/arm64/kernel/perf_regs.c b/arch/arm64/kernel/perf_regs.c
index 6762ad705587..3f62b35fb6f1 100644
--- a/arch/arm64/kernel/perf_regs.c
+++ b/arch/arm64/kernel/perf_regs.c
@@ -50,3 +50,11 @@ u64 perf_reg_abi(struct task_struct *task)
else
return PERF_SAMPLE_REGS_ABI_64;
}
+
+void perf_get_regs_user(struct perf_regs *regs_user,
+ struct pt_regs *regs,
+ struct pt_regs *regs_user_copy)
+{
+ regs_user->regs = task_pt_regs(current);
+ regs_user->abi = perf_reg_abi(current);
+}
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
index e309cc5c276e..3bbbb1a4fb52 100644
--- a/arch/x86/kernel/perf_regs.c
+++ b/arch/x86/kernel/perf_regs.c
@@ -78,6 +78,14 @@ u64 perf_reg_abi(struct task_struct *task)
{
return PERF_SAMPLE_REGS_ABI_32;
}
+
+void perf_get_regs_user(struct perf_regs *regs_user,
+ struct pt_regs *regs,
+ struct pt_regs *regs_user_copy)
+{
+ regs_user->regs = task_pt_regs(current);
+ regs_user->abi = perf_reg_abi(current);
+}
#else /* CONFIG_X86_64 */
#define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \
(1ULL << PERF_REG_X86_ES) | \
@@ -102,4 +110,12 @@ u64 perf_reg_abi(struct task_struct *task)
else
return PERF_SAMPLE_REGS_ABI_64;
}
+
+void perf_get_regs_user(struct perf_regs *regs_user,
+ struct pt_regs *regs,
+ struct pt_regs *regs_user_copy)
+{
+ regs_user->regs = task_pt_regs(current);
+ regs_user->abi = perf_reg_abi(current);
+}
#endif /* CONFIG_X86_32 */
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 486e84ccb1f9..4f7a61ca4b39 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -79,11 +79,6 @@ struct perf_branch_stack {
struct perf_branch_entry entries[0];
};
-struct perf_regs {
- __u64 abi;
- struct pt_regs *regs;
-};
-
struct task_struct;
/*
@@ -610,7 +605,14 @@ struct perf_sample_data {
u32 reserved;
} cpu_entry;
struct perf_callchain_entry *callchain;
+
+ /*
+ * regs_user may point to task_pt_regs or to regs_user_copy, depending
+ * on arch details.
+ */
struct perf_regs regs_user;
+ struct pt_regs regs_user_copy;
+
struct perf_regs regs_intr;
u64 stack_user_size;
} ____cacheline_aligned;
diff --git a/include/linux/perf_regs.h b/include/linux/perf_regs.h
index 3c73d5fe18be..a5f98d53d732 100644
--- a/include/linux/perf_regs.h
+++ b/include/linux/perf_regs.h
@@ -1,11 +1,19 @@
#ifndef _LINUX_PERF_REGS_H
#define _LINUX_PERF_REGS_H
+struct perf_regs {
+ __u64 abi;
+ struct pt_regs *regs;
+};
+
#ifdef CONFIG_HAVE_PERF_REGS
#include <asm/perf_regs.h>
u64 perf_reg_value(struct pt_regs *regs, int idx);
int perf_reg_validate(u64 mask);
u64 perf_reg_abi(struct task_struct *task);
+void perf_get_regs_user(struct perf_regs *regs_user,
+ struct pt_regs *regs,
+ struct pt_regs *regs_user_copy);
#else
static inline u64 perf_reg_value(struct pt_regs *regs, int idx)
{
@@ -21,5 +29,13 @@ static inline u64 perf_reg_abi(struct task_struct *task)
{
return PERF_SAMPLE_REGS_ABI_NONE;
}
+
+static inline void perf_get_regs_user(struct perf_regs *regs_user,
+ struct pt_regs *regs,
+ struct pt_regs *regs_user_copy)
+{
+ regs_user->regs = task_pt_regs(current);
+ regs_user->abi = perf_reg_abi(current);
+}
#endif /* CONFIG_HAVE_PERF_REGS */
#endif /* _LINUX_PERF_REGS_H */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 4c1ee7f2bebc..882f835a0d85 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4461,18 +4461,14 @@ perf_output_sample_regs(struct perf_output_handle *handle,
}
static void perf_sample_regs_user(struct perf_regs *regs_user,
- struct pt_regs *regs)
+ struct pt_regs *regs,
+ struct pt_regs *regs_user_copy)
{
- if (!user_mode(regs)) {
- if (current->mm)
- regs = task_pt_regs(current);
- else
- regs = NULL;
- }
-
- if (regs) {
- regs_user->abi = perf_reg_abi(current);
+ if (user_mode(regs)) {
+ regs_user->abi = perf_reg_abi(current);
regs_user->regs = regs;
+ } else if (current->mm) {
+ perf_get_regs_user(regs_user, regs, regs_user_copy);
} else {
regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE;
regs_user->regs = NULL;
@@ -4951,7 +4947,8 @@ void perf_prepare_sample(struct perf_event_header *header,
}
if (sample_type & (PERF_SAMPLE_REGS_USER | PERF_SAMPLE_STACK_USER))
- perf_sample_regs_user(&data->regs_user, regs);
+ perf_sample_regs_user(&data->regs_user, regs,
+ &data->regs_user_copy);
if (sample_type & PERF_SAMPLE_REGS_USER) {
/* regs dump ABI info */
--
2.1.0
next prev parent reply index
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-12-23 6:22 [PATCH] perf core: Use KSTK_ESP() instead of pt_regs->sp while output user regs root
2014-12-23 8:30 ` Andy Lutomirski
[not found] ` <c027bde0-5f4f-441f-8d45-3e7f6f702231@alibaba-inc.com>
2014-12-25 15:48 ` 答复:[PATCH] " Andy Lutomirski
2014-12-25 16:21 ` Andy Lutomirski
2014-12-30 19:03 ` Peter Zijlstra
2014-12-30 23:29 ` Andy Lutomirski
2014-12-31 2:00 ` Andy Lutomirski
2015-01-02 16:11 ` Jan Beulich
2015-01-02 18:03 ` Andy Lutomirski
2015-01-05 8:47 ` Jan Beulich
2015-01-04 16:10 ` Jiri Olsa
2015-01-04 17:18 ` Andy Lutomirski
2015-01-04 17:41 ` Jiri Olsa
2015-01-04 18:36 ` [PATCH 0/2] perf: Improve user regs sampling Andy Lutomirski
2015-01-04 18:36 ` Andy Lutomirski [this message]
2015-01-05 14:07 ` [PATCH 1/2] perf: Move task_pt_regs sampling into arch code Peter Zijlstra
2015-01-05 16:13 ` Andy Lutomirski
2015-01-05 16:44 ` Peter Zijlstra
2015-01-05 18:28 ` Andy Lutomirski
2015-01-09 12:32 ` [tip:perf/urgent] " tip-bot for Andy Lutomirski
2015-01-04 18:36 ` [PATCH 2/2] x86_64, perf: Improve user regs sampling Andy Lutomirski
2015-01-09 12:32 ` [tip:perf/urgent] perf/x86_64: " tip-bot for Andy Lutomirski
2015-01-05 10:46 ` [PATCH 0/2] perf: " Jiri Olsa
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=e431cd4c18c2e1c44c774f10758527fb2d1025c4.1420396372.git.luto@amacapital.net \
--to=luto@amacapital.net \
--cc=akpm@linux-foundation.org \
--cc=arjan@linux.intel.com \
--cc=chenggang.qcg@alibaba-inc.com \
--cc=chenggang.qcg@taobao.com \
--cc=chenggang.qin@gmail.com \
--cc=dsahern@gmail.com \
--cc=efault@gmx.de \
--cc=eranian@google.com \
--cc=fengguang.wu@intel.com \
--cc=jolsa@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=namhyung@gmail.com \
--cc=paulus@samba.org \
--cc=peterz@infradead.org \
--cc=yanmin.zhang@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
LKML Archive on lore.kernel.org
Archives are clonable:
git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git
git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git
git clone --mirror https://lore.kernel.org/lkml/7 lkml/git/7.git
git clone --mirror https://lore.kernel.org/lkml/8 lkml/git/8.git
git clone --mirror https://lore.kernel.org/lkml/9 lkml/git/9.git
# If you have public-inbox 1.1+ installed, you may
# initialize and index your mirror using the following commands:
public-inbox-init -V2 lkml lkml/ https://lore.kernel.org/lkml \
linux-kernel@vger.kernel.org
public-inbox-index lkml
Example config snippet for mirrors
Newsgroup available over NNTP:
nntp://nntp.lore.kernel.org/org.kernel.vger.linux-kernel
AGPL code for this site: git clone https://public-inbox.org/public-inbox.git