From: AKASHI Takahiro <takahiro.akashi@linaro.org>
To: catalin.marinas@arm.com, will.deacon@arm.com, rostedt@goodmis.org
Cc: jungseoklee85@gmail.com, olof@lixom.net, broonie@kernel.org,
david.griego@linaro.org, linux-arm-kernel@lists.infradead.org,
linux-kernel@vger.kernel.org,
AKASHI Takahiro <takahiro.akashi@linaro.org>
Subject: [RFC 3/3] arm64: ftrace: mcount() should not create a stack frame
Date: Mon, 13 Jul 2015 14:29:35 +0900 [thread overview]
Message-ID: <1436765375-7119-4-git-send-email-takahiro.akashi@linaro.org> (raw)
In-Reply-To: <1436765375-7119-1-git-send-email-takahiro.akashi@linaro.org>
Ftrace's stack tracer on arm64 returns wrong information about call stacks:
Depth Size Location (50 entries)
----- ---- --------
0) 5256 0 notifier_call_chain+0x30/0x94
1) 5256 0 ftrace_call+0x0/0x4
2) 5256 0 notifier_call_chain+0x2c/0x94
3) 5256 0 raw_notifier_call_chain+0x34/0x44
4) 5256 0 timekeeping_update.constprop.9+0xb8/0x114
5) 5256 0 update_wall_time+0x408/0x6dc
The instrumented function, notifier_call_chain(), appears twice.
On x86 (and other arch's), mcount (or ftrace_call) does not create a new
stack frame. This will eventually result in not listing the instrumented
function in save_stack_call() because the function's returned address does
not appear as saved lr in the stack. Stack tracer, instead, explicitly adds
this skipped function at the top of the list later in check_stack().
That is why it is listed twice on arm64 as shown above.
This patch modifies arm64 function tracer not to create a stack frame at
mcount() in order to fix this issue.
Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org>
---
arch/arm64/kernel/entry-ftrace.S | 15 ++++++++-------
1 file changed, 8 insertions(+), 7 deletions(-)
diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S
index 08cafc5..c74fa12 100644
--- a/arch/arm64/kernel/entry-ftrace.S
+++ b/arch/arm64/kernel/entry-ftrace.S
@@ -26,9 +26,11 @@
* as long as the kernel is compiled without -fomit-frame-pointer.
* (or CONFIG_FRAME_POINTER, this is forced on arm64)
*
+ * We don't update a frame pointer here as ftrace, in special stack tracer,
+ * assumes not. If we did, the instrumented function would be listed twice.
* stack layout after mcount_enter in _mcount():
*
- * current sp/fp => 0:+-----+
+ * current sp => 0:+-----+
* in _mcount() | x29 | -> instrumented function's fp
* +-----+
* | x30 | -> _mcount()'s lr (= instrumented function's pc)
@@ -47,7 +49,6 @@
.macro mcount_enter
stp x29, x30, [sp, #-16]!
- mov x29, sp
.endm
.macro mcount_exit
@@ -61,7 +62,7 @@
/* for instrumented function's parent */
.macro mcount_get_parent_fp reg
- ldr \reg, [x29]
+ ldr \reg, [sp]
ldr \reg, [\reg]
.endm
@@ -71,18 +72,18 @@
.endm
.macro mcount_get_pc reg
- ldr \reg, [x29, #8]
+ ldr \reg, [sp, #8]
mcount_adjust_addr \reg, \reg
.endm
.macro mcount_get_lr reg
- ldr \reg, [x29]
+ ldr \reg, [sp]
ldr \reg, [\reg, #8]
mcount_adjust_addr \reg, \reg
.endm
.macro mcount_get_lr_addr reg
- ldr \reg, [x29]
+ ldr \reg, [sp]
add \reg, \reg, #8
.endm
@@ -205,7 +206,7 @@ ENDPROC(ftrace_graph_caller)
*/
ENTRY(return_to_handler)
str x0, [sp, #-16]!
- mov x0, x29 // parent's fp
+ mov x0, sp // parent's fp
bl ftrace_return_to_handler// addr = ftrace_return_to_hander(fp);
mov x30, x0 // restore the original return address
ldr x0, [sp], #16
--
1.7.9.5
WARNING: multiple messages have this Message-ID (diff)
From: takahiro.akashi@linaro.org (AKASHI Takahiro)
To: linux-arm-kernel@lists.infradead.org
Subject: [RFC 3/3] arm64: ftrace: mcount() should not create a stack frame
Date: Mon, 13 Jul 2015 14:29:35 +0900 [thread overview]
Message-ID: <1436765375-7119-4-git-send-email-takahiro.akashi@linaro.org> (raw)
In-Reply-To: <1436765375-7119-1-git-send-email-takahiro.akashi@linaro.org>
Ftrace's stack tracer on arm64 returns wrong information about call stacks:
Depth Size Location (50 entries)
----- ---- --------
0) 5256 0 notifier_call_chain+0x30/0x94
1) 5256 0 ftrace_call+0x0/0x4
2) 5256 0 notifier_call_chain+0x2c/0x94
3) 5256 0 raw_notifier_call_chain+0x34/0x44
4) 5256 0 timekeeping_update.constprop.9+0xb8/0x114
5) 5256 0 update_wall_time+0x408/0x6dc
The instrumented function, notifier_call_chain(), appears twice.
On x86 (and other arch's), mcount (or ftrace_call) does not create a new
stack frame. This will eventually result in not listing the instrumented
function in save_stack_call() because the function's returned address does
not appear as saved lr in the stack. Stack tracer, instead, explicitly adds
this skipped function at the top of the list later in check_stack().
That is why it is listed twice on arm64 as shown above.
This patch modifies arm64 function tracer not to create a stack frame at
mcount() in order to fix this issue.
Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org>
---
arch/arm64/kernel/entry-ftrace.S | 15 ++++++++-------
1 file changed, 8 insertions(+), 7 deletions(-)
diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S
index 08cafc5..c74fa12 100644
--- a/arch/arm64/kernel/entry-ftrace.S
+++ b/arch/arm64/kernel/entry-ftrace.S
@@ -26,9 +26,11 @@
* as long as the kernel is compiled without -fomit-frame-pointer.
* (or CONFIG_FRAME_POINTER, this is forced on arm64)
*
+ * We don't update a frame pointer here as ftrace, in special stack tracer,
+ * assumes not. If we did, the instrumented function would be listed twice.
* stack layout after mcount_enter in _mcount():
*
- * current sp/fp => 0:+-----+
+ * current sp => 0:+-----+
* in _mcount() | x29 | -> instrumented function's fp
* +-----+
* | x30 | -> _mcount()'s lr (= instrumented function's pc)
@@ -47,7 +49,6 @@
.macro mcount_enter
stp x29, x30, [sp, #-16]!
- mov x29, sp
.endm
.macro mcount_exit
@@ -61,7 +62,7 @@
/* for instrumented function's parent */
.macro mcount_get_parent_fp reg
- ldr \reg, [x29]
+ ldr \reg, [sp]
ldr \reg, [\reg]
.endm
@@ -71,18 +72,18 @@
.endm
.macro mcount_get_pc reg
- ldr \reg, [x29, #8]
+ ldr \reg, [sp, #8]
mcount_adjust_addr \reg, \reg
.endm
.macro mcount_get_lr reg
- ldr \reg, [x29]
+ ldr \reg, [sp]
ldr \reg, [\reg, #8]
mcount_adjust_addr \reg, \reg
.endm
.macro mcount_get_lr_addr reg
- ldr \reg, [x29]
+ ldr \reg, [sp]
add \reg, \reg, #8
.endm
@@ -205,7 +206,7 @@ ENDPROC(ftrace_graph_caller)
*/
ENTRY(return_to_handler)
str x0, [sp, #-16]!
- mov x0, x29 // parent's fp
+ mov x0, sp // parent's fp
bl ftrace_return_to_handler// addr = ftrace_return_to_hander(fp);
mov x30, x0 // restore the original return address
ldr x0, [sp], #16
--
1.7.9.5
next prev parent reply other threads:[~2015-07-13 5:31 UTC|newest]
Thread overview: 106+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-07-13 5:29 [RFC 0/3] arm64: ftrace: fix incorrect output from stack tracer AKASHI Takahiro
2015-07-13 5:29 ` AKASHI Takahiro
2015-07-13 5:29 ` [RFC 1/3] ftrace: adjust a function's pc to search for in check_stack() for arm64 AKASHI Takahiro
2015-07-13 5:29 ` AKASHI Takahiro
2015-07-13 15:24 ` Steven Rostedt
2015-07-13 15:24 ` Steven Rostedt
2015-07-15 0:22 ` AKASHI Takahiro
2015-07-15 0:22 ` AKASHI Takahiro
2015-07-13 5:29 ` [RFC 2/3] arm64: refactor save_stack_trace() AKASHI Takahiro
2015-07-13 5:29 ` AKASHI Takahiro
2015-07-14 12:47 ` Jungseok Lee
2015-07-14 12:47 ` Jungseok Lee
2015-07-14 13:31 ` Steven Rostedt
2015-07-14 13:31 ` Steven Rostedt
2015-07-15 0:20 ` AKASHI Takahiro
2015-07-15 0:20 ` AKASHI Takahiro
2015-07-15 2:51 ` Steven Rostedt
2015-07-15 2:51 ` Steven Rostedt
2015-07-15 11:41 ` AKASHI Takahiro
2015-07-15 11:41 ` AKASHI Takahiro
2015-07-15 14:55 ` Steven Rostedt
2015-07-15 14:55 ` Steven Rostedt
2015-07-15 16:13 ` Steven Rostedt
2015-07-15 16:13 ` Steven Rostedt
2015-07-16 0:27 ` AKASHI Takahiro
2015-07-16 0:27 ` AKASHI Takahiro
2015-07-16 1:08 ` AKASHI Takahiro
2015-07-16 1:08 ` AKASHI Takahiro
2015-07-16 1:38 ` Steven Rostedt
2015-07-16 1:38 ` Steven Rostedt
2015-07-17 10:46 ` Will Deacon
2015-07-17 10:46 ` Will Deacon
2015-07-16 13:29 ` Jungseok Lee
2015-07-16 13:29 ` Jungseok Lee
2015-07-16 13:54 ` Jungseok Lee
2015-07-16 13:54 ` Jungseok Lee
2015-07-16 14:24 ` Steven Rostedt
2015-07-16 14:24 ` Steven Rostedt
2015-07-16 15:01 ` Jungseok Lee
2015-07-16 15:01 ` Jungseok Lee
2015-07-16 15:31 ` Steven Rostedt
2015-07-16 15:31 ` Steven Rostedt
2015-07-16 15:52 ` Jungseok Lee
2015-07-16 15:52 ` Jungseok Lee
2015-07-16 20:22 ` Steven Rostedt
2015-07-16 20:22 ` Steven Rostedt
2015-07-17 2:49 ` AKASHI Takahiro
2015-07-17 2:49 ` AKASHI Takahiro
2015-07-17 3:21 ` Steven Rostedt
2015-07-17 3:21 ` Steven Rostedt
2015-07-16 16:16 ` Steven Rostedt
2015-07-16 16:16 ` Steven Rostedt
2015-07-17 12:40 ` Mark Rutland
2015-07-17 12:40 ` Mark Rutland
2015-07-17 12:51 ` Steven Rostedt
2015-07-17 12:51 ` Steven Rostedt
2015-07-17 13:00 ` Steven Rostedt
2015-07-17 13:00 ` Steven Rostedt
2015-07-17 14:28 ` Jungseok Lee
2015-07-17 14:28 ` Jungseok Lee
2015-07-17 14:41 ` Steven Rostedt
2015-07-17 14:41 ` Steven Rostedt
2015-07-17 14:59 ` Jungseok Lee
2015-07-17 14:59 ` Jungseok Lee
2015-07-17 15:34 ` Jungseok Lee
2015-07-17 15:34 ` Jungseok Lee
2015-07-17 16:01 ` Steven Rostedt
2015-07-17 16:01 ` Steven Rostedt
2015-07-20 16:20 ` Will Deacon
2015-07-20 16:20 ` Will Deacon
2015-07-20 23:53 ` AKASHI Takahiro
2015-07-20 23:53 ` AKASHI Takahiro
2015-07-21 10:26 ` AKASHI Takahiro
2015-07-21 10:26 ` AKASHI Takahiro
2015-07-21 14:34 ` Jungseok Lee
2015-07-21 14:34 ` Jungseok Lee
2015-08-03 9:09 ` Will Deacon
2015-08-03 9:09 ` Will Deacon
2015-08-03 14:01 ` Steven Rostedt
2015-08-03 14:01 ` Steven Rostedt
2015-08-03 14:04 ` Will Deacon
2015-08-03 14:04 ` Will Deacon
2015-08-03 16:30 ` Jungseok Lee
2015-08-03 16:30 ` Jungseok Lee
2015-08-03 16:57 ` Steven Rostedt
2015-08-03 16:57 ` Steven Rostedt
2015-08-03 17:22 ` Jungseok Lee
2015-08-03 17:22 ` Jungseok Lee
2015-08-03 17:32 ` Steven Rostedt
2015-08-03 17:32 ` Steven Rostedt
2015-08-04 7:41 ` AKASHI Takahiro
2015-08-04 7:41 ` AKASHI Takahiro
2015-07-17 2:04 ` AKASHI Takahiro
2015-07-17 2:04 ` AKASHI Takahiro
2015-07-17 14:38 ` Jungseok Lee
2015-07-17 14:38 ` Jungseok Lee
2015-07-16 14:28 ` Mark Rutland
2015-07-16 14:28 ` Mark Rutland
2015-07-16 14:34 ` Steven Rostedt
2015-07-16 14:34 ` Steven Rostedt
2015-07-17 2:09 ` AKASHI Takahiro
2015-07-17 2:09 ` AKASHI Takahiro
2015-07-13 5:29 ` AKASHI Takahiro [this message]
2015-07-13 5:29 ` [RFC 3/3] arm64: ftrace: mcount() should not create a stack frame AKASHI Takahiro
2015-07-13 15:01 ` [RFC 0/3] arm64: ftrace: fix incorrect output from stack tracer Jungseok Lee
2015-07-13 15:01 ` Jungseok Lee
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=1436765375-7119-4-git-send-email-takahiro.akashi@linaro.org \
--to=takahiro.akashi@linaro.org \
--cc=broonie@kernel.org \
--cc=catalin.marinas@arm.com \
--cc=david.griego@linaro.org \
--cc=jungseoklee85@gmail.com \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=olof@lixom.net \
--cc=rostedt@goodmis.org \
--cc=will.deacon@arm.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.