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returned by __get_SP() is no longer valid.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>

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

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);

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

arch/powerpc/kernel/ppc_ksyms.c

@@ -41,3 +41,5 @@ EXPORT_SYMBOL(giveup_spe);
 #ifdef CONFIG_EPAPR_PARAVIRT
 EXPORT_SYMBOL(epapr_hypercall_start);
 #endif
+
+EXPORT_SYMBOL(__get_SP);

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;
 	}

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);
 }