* [PATCH] powerpc: Reimplement __get_SP() as a function not a define
@ 2014-10-01 5:10 Anton Blanchard
2014-10-01 7:11 ` [PATCH] powerpc: Rename __get_SP() to current_stack_pointer() Anton Blanchard
2014-10-08 8:47 ` [PATCH] powerpc: Reimplement __get_SP() as a function not a define Li Zhong
0 siblings, 2 replies; 3+ messages in thread
From: Anton Blanchard @ 2014-10-01 5:10 UTC (permalink / raw)
To: zhong, benh, paulus, mpe; +Cc: linuxppc-dev
Li Zhong points out an issue with our current __get_SP()
implementation. If ftrace function tracing is enabled (ie -pg
profiling using _mcount) we spill a stack frame on 64bit all the
time.
If a function calls __get_SP() and later calls a function that is
tail call optimised, we will pop the stack frame and the value
returned by __get_SP() is no longer valid. An example from Li can
be found in save_stack_trace -> save_context_stack:
c0000000000432c0 <.save_stack_trace>:
c0000000000432c0: mflr r0
c0000000000432c4: std r0,16(r1)
c0000000000432c8: stdu r1,-128(r1) <-- stack frame for _mcount
c0000000000432cc: std r3,112(r1)
c0000000000432d0: bl <._mcount>
c0000000000432d4: nop
c0000000000432d8: mr r4,r1 <-- __get_SP()
c0000000000432dc: ld r5,632(r13)
c0000000000432e0: ld r3,112(r1)
c0000000000432e4: li r6,1
c0000000000432e8: addi r1,r1,128 <-- pop stack frame
c0000000000432ec: ld r0,16(r1)
c0000000000432f0: mtlr r0
c0000000000432f4: b <.save_context_stack> <-- tail call optimized
save_context_stack ends up with a stack pointer below the current
one, and it is likely to be scribbled over.
Fix this by making __get_SP() a function which returns the
callers stack frame. Also replace inline assembly which grabs
the stack pointer in save_stack_trace and show_stack with
__get_SP().
Reported-by: Li Zhong <zhong@linux.vnet.ibm.com>
Signed-off-by: Anton Blanchard <anton@samba.org>
---
arch/powerpc/include/asm/reg.h | 3 +--
arch/powerpc/kernel/misc.S | 4 ++++
arch/powerpc/kernel/process.c | 2 +-
arch/powerpc/kernel/stacktrace.c | 2 +-
4 files changed, 7 insertions(+), 4 deletions(-)
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 0c05059..0f973c0 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -1264,8 +1264,7 @@ static inline unsigned long mfvtb (void)
#define proc_trap() asm volatile("trap")
-#define __get_SP() ({unsigned long sp; \
- asm volatile("mr %0,1": "=r" (sp)); sp;})
+extern unsigned long __get_SP(void);
extern unsigned long scom970_read(unsigned int address);
extern void scom970_write(unsigned int address, unsigned long value);
diff --git a/arch/powerpc/kernel/misc.S b/arch/powerpc/kernel/misc.S
index 7ce26d4..120deb7 100644
--- a/arch/powerpc/kernel/misc.S
+++ b/arch/powerpc/kernel/misc.S
@@ -114,3 +114,7 @@ _GLOBAL(longjmp)
mtlr r0
mr r3,r4
blr
+
+_GLOBAL(__get_SP)
+ PPC_LL r3,0(r1)
+ blr
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index aa1df89..3cc6439 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1545,7 +1545,7 @@ void show_stack(struct task_struct *tsk, unsigned long *stack)
tsk = current;
if (sp == 0) {
if (tsk == current)
- asm("mr %0,1" : "=r" (sp));
+ sp = __get_SP();
else
sp = tsk->thread.ksp;
}
diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c
index 3d30ef1..7f65bae 100644
--- a/arch/powerpc/kernel/stacktrace.c
+++ b/arch/powerpc/kernel/stacktrace.c
@@ -50,7 +50,7 @@ void save_stack_trace(struct stack_trace *trace)
{
unsigned long sp;
- asm("mr %0,1" : "=r" (sp));
+ sp = __get_SP();
save_context_stack(trace, sp, current, 1);
}
--
1.9.1
^ permalink raw reply related [flat|nested] 3+ messages in thread
* [PATCH] powerpc: Rename __get_SP() to current_stack_pointer()
2014-10-01 5:10 [PATCH] powerpc: Reimplement __get_SP() as a function not a define Anton Blanchard
@ 2014-10-01 7:11 ` Anton Blanchard
2014-10-08 8:47 ` [PATCH] powerpc: Reimplement __get_SP() as a function not a define Li Zhong
1 sibling, 0 replies; 3+ messages in thread
From: Anton Blanchard @ 2014-10-01 7:11 UTC (permalink / raw)
To: zhong, benh, paulus, mpe; +Cc: linuxppc-dev
Michael points out that __get_SP() is a pretty horrible
function name. Let's give it a better name.
Signed-off-by: Anton Blanchard <anton@samba.org>
---
arch/powerpc/include/asm/perf_event.h | 2 +-
arch/powerpc/include/asm/reg.h | 2 +-
arch/powerpc/kernel/irq.c | 2 +-
arch/powerpc/kernel/misc.S | 2 +-
arch/powerpc/kernel/process.c | 2 +-
arch/powerpc/kernel/stacktrace.c | 2 +-
6 files changed, 6 insertions(+), 6 deletions(-)
diff --git a/arch/powerpc/include/asm/perf_event.h b/arch/powerpc/include/asm/perf_event.h
index 0bb2372..fc53598 100644
--- a/arch/powerpc/include/asm/perf_event.h
+++ b/arch/powerpc/include/asm/perf_event.h
@@ -34,7 +34,7 @@
do { \
(regs)->result = 0; \
(regs)->nip = __ip; \
- (regs)->gpr[1] = *(unsigned long *)__get_SP(); \
+ (regs)->gpr[1] = *(unsigned long *)current_stack_pointer(); \
asm volatile("mfmsr %0" : "=r" ((regs)->msr)); \
} while (0)
#endif
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 0f973c0..d8974b5 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -1264,7 +1264,7 @@ static inline unsigned long mfvtb (void)
#define proc_trap() asm volatile("trap")
-extern unsigned long __get_SP(void);
+extern unsigned long current_stack_pointer(void);
extern unsigned long scom970_read(unsigned int address);
extern void scom970_write(unsigned int address, unsigned long value);
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 8eb857f..c143835 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -466,7 +466,7 @@ static inline void check_stack_overflow(void)
#ifdef CONFIG_DEBUG_STACKOVERFLOW
long sp;
- sp = __get_SP() & (THREAD_SIZE-1);
+ sp = current_stack_pointer() & (THREAD_SIZE-1);
/* check for stack overflow: is there less than 2KB free? */
if (unlikely(sp < (sizeof(struct thread_info) + 2048))) {
diff --git a/arch/powerpc/kernel/misc.S b/arch/powerpc/kernel/misc.S
index 120deb7..0d43219 100644
--- a/arch/powerpc/kernel/misc.S
+++ b/arch/powerpc/kernel/misc.S
@@ -115,6 +115,6 @@ _GLOBAL(longjmp)
mr r3,r4
blr
-_GLOBAL(__get_SP)
+_GLOBAL(current_stack_pointer)
PPC_LL r3,0(r1)
blr
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 3cc6439..923cd2d 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1545,7 +1545,7 @@ void show_stack(struct task_struct *tsk, unsigned long *stack)
tsk = current;
if (sp == 0) {
if (tsk == current)
- sp = __get_SP();
+ sp = current_stack_pointer();
else
sp = tsk->thread.ksp;
}
diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c
index 7f65bae..ea43a34 100644
--- a/arch/powerpc/kernel/stacktrace.c
+++ b/arch/powerpc/kernel/stacktrace.c
@@ -50,7 +50,7 @@ void save_stack_trace(struct stack_trace *trace)
{
unsigned long sp;
- sp = __get_SP();
+ sp = current_stack_pointer();
save_context_stack(trace, sp, current, 1);
}
--
1.9.1
^ permalink raw reply related [flat|nested] 3+ messages in thread
* Re: [PATCH] powerpc: Reimplement __get_SP() as a function not a define
2014-10-01 5:10 [PATCH] powerpc: Reimplement __get_SP() as a function not a define Anton Blanchard
2014-10-01 7:11 ` [PATCH] powerpc: Rename __get_SP() to current_stack_pointer() Anton Blanchard
@ 2014-10-08 8:47 ` Li Zhong
1 sibling, 0 replies; 3+ messages in thread
From: Li Zhong @ 2014-10-08 8:47 UTC (permalink / raw)
To: Anton Blanchard; +Cc: paulus, linuxppc-dev
On 三, 2014-10-01 at 15:10 +1000, Anton Blanchard wrote:
> Li Zhong points out an issue with our current __get_SP()
> implementation. If ftrace function tracing is enabled (ie -pg
> profiling using _mcount) we spill a stack frame on 64bit all the
> time.
>
> If a function calls __get_SP() and later calls a function that is
> tail call optimised, we will pop the stack frame and the value
> returned by __get_SP() is no longer valid. An example from Li can
> be found in save_stack_trace -> save_context_stack:
>
> c0000000000432c0 <.save_stack_trace>:
> c0000000000432c0: mflr r0
> c0000000000432c4: std r0,16(r1)
> c0000000000432c8: stdu r1,-128(r1) <-- stack frame for _mcount
> c0000000000432cc: std r3,112(r1)
> c0000000000432d0: bl <._mcount>
> c0000000000432d4: nop
>
> c0000000000432d8: mr r4,r1 <-- __get_SP()
>
> c0000000000432dc: ld r5,632(r13)
> c0000000000432e0: ld r3,112(r1)
> c0000000000432e4: li r6,1
>
> c0000000000432e8: addi r1,r1,128 <-- pop stack frame
>
> c0000000000432ec: ld r0,16(r1)
> c0000000000432f0: mtlr r0
> c0000000000432f4: b <.save_context_stack> <-- tail call optimized
>
> save_context_stack ends up with a stack pointer below the current
> one, and it is likely to be scribbled over.
>
> Fix this by making __get_SP() a function which returns the
> callers stack frame. Also replace inline assembly which grabs
> the stack pointer in save_stack_trace and show_stack with
> __get_SP().
>
> Reported-by: Li Zhong <zhong@linux.vnet.ibm.com>
> Signed-off-by: Anton Blanchard <anton@samba.org>
> ---
> arch/powerpc/include/asm/reg.h | 3 +--
> arch/powerpc/kernel/misc.S | 4 ++++
> arch/powerpc/kernel/process.c | 2 +-
> arch/powerpc/kernel/stacktrace.c | 2 +-
> 4 files changed, 7 insertions(+), 4 deletions(-)
>
> diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
> index 0c05059..0f973c0 100644
> --- a/arch/powerpc/include/asm/reg.h
> +++ b/arch/powerpc/include/asm/reg.h
> @@ -1264,8 +1264,7 @@ static inline unsigned long mfvtb (void)
>
> #define proc_trap() asm volatile("trap")
>
> -#define __get_SP() ({unsigned long sp; \
> - asm volatile("mr %0,1": "=r" (sp)); sp;})
> +extern unsigned long __get_SP(void);
It seems that some module code is using __get_SP, e.g. xfs in the
example below:
ERROR: ".__get_SP" [fs/xfs/xfs.ko] undefined!
Maybe we need export this symbol in arch/powerpc/kernel/ppc_ksyms.c?
diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c
index 48d17d6f..eebd4e4 100644
--- a/arch/powerpc/kernel/ppc_ksyms.c
+++ b/arch/powerpc/kernel/ppc_ksyms.c
@@ -207,3 +207,5 @@ EXPORT_SYMBOL_GPL(mmu_psize_defs);
#ifdef CONFIG_EPAPR_PARAVIRT
EXPORT_SYMBOL(epapr_hypercall_start);
#endif
+
+EXPORT_SYMBOL(__get_SP);
With the above compiling error fixed, this patch solved the SP issue I saw, so
Tested-by: Li Zhong <zhong@linux.vnet.ibm.com>
>
> extern unsigned long scom970_read(unsigned int address);
> extern void scom970_write(unsigned int address, unsigned long value);
> diff --git a/arch/powerpc/kernel/misc.S b/arch/powerpc/kernel/misc.S
> index 7ce26d4..120deb7 100644
> --- a/arch/powerpc/kernel/misc.S
> +++ b/arch/powerpc/kernel/misc.S
> @@ -114,3 +114,7 @@ _GLOBAL(longjmp)
> mtlr r0
> mr r3,r4
> blr
> +
> +_GLOBAL(__get_SP)
> + PPC_LL r3,0(r1)
> + blr
> diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
> index aa1df89..3cc6439 100644
> --- a/arch/powerpc/kernel/process.c
> +++ b/arch/powerpc/kernel/process.c
> @@ -1545,7 +1545,7 @@ void show_stack(struct task_struct *tsk, unsigned long *stack)
> tsk = current;
> if (sp == 0) {
> if (tsk == current)
> - asm("mr %0,1" : "=r" (sp));
> + sp = __get_SP();
> else
> sp = tsk->thread.ksp;
> }
> diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c
> index 3d30ef1..7f65bae 100644
> --- a/arch/powerpc/kernel/stacktrace.c
> +++ b/arch/powerpc/kernel/stacktrace.c
> @@ -50,7 +50,7 @@ void save_stack_trace(struct stack_trace *trace)
> {
> unsigned long sp;
>
> - asm("mr %0,1" : "=r" (sp));
> + sp = __get_SP();
>
> save_context_stack(trace, sp, current, 1);
> }
^ permalink raw reply related [flat|nested] 3+ messages in thread
end of thread, other threads:[~2014-10-08 8:48 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2014-10-01 5:10 [PATCH] powerpc: Reimplement __get_SP() as a function not a define Anton Blanchard
2014-10-01 7:11 ` [PATCH] powerpc: Rename __get_SP() to current_stack_pointer() Anton Blanchard
2014-10-08 8:47 ` [PATCH] powerpc: Reimplement __get_SP() as a function not a define Li Zhong
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).