summaryrefslogtreecommitdiff
path: root/arch/powerpc/include
diff options
context:
space:
mode:
authorAnton Blanchard <anton@samba.org>2014-10-13 12:41:38 +0400
committerMichael Ellerman <mpe@ellerman.id.au>2014-10-15 04:23:19 +0400
commitbfe9a2cfe91a1c920f152ce5fd0a9ad74b3daf12 (patch)
treeff5f5b9cd9db51252e08ae41f8f5d751117a8fdf /arch/powerpc/include
parent2d73bae12b26db6eba074b70406c707961b6cda9 (diff)
downloadlinux-bfe9a2cfe91a1c920f152ce5fd0a9ad74b3daf12.tar.xz
powerpc: Reimplement __get_SP() as a function not a define
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later calls a function that is tail call optimised, we will pop the stack frame and the value returned by __get_SP() is no longer valid.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(). This also fixes an issue with perf_arch_fetch_caller_regs(). It currently unwinds the stack once, which will skip a valid stack frame on a leaf function. With the __get_SP() fixes in this patch, we never need to unwind the stack frame to get to the first interesting frame. We have to export __get_SP() because perf_arch_fetch_caller_regs() (which is used in modules) calls it from a header file. Reported-by: Li Zhong <zhong@linux.vnet.ibm.com> Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Diffstat (limited to 'arch/powerpc/include')
-rw-r--r--arch/powerpc/include/asm/perf_event.h2
-rw-r--r--arch/powerpc/include/asm/reg.h3
2 files changed, 2 insertions, 3 deletions
diff --git a/arch/powerpc/include/asm/perf_event.h b/arch/powerpc/include/asm/perf_event.h
index 0bb23725b1e7..b058568a850d 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] = __get_SP(); \
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 fe3f9488f321..e539d7e71451 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -1265,8 +1265,7 @@ 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);