powerpc/64: Save stack pointer when we hard disable interrupts

A CPU that gets stuck with interrupts hard disable can be difficult to
debug, as on some platforms we have no way to interrupt the CPU to
find out what it's doing.

A stop-gap is to have the CPU save it's stack pointer (r1) in its paca
when it hard disables interrupts. That way if we can't interrupt it,
we can at least trace the stack based on where it last disabled
interrupts.

In some cases that will be total junk, but the stack trace code should
handle that. In the simple case of a CPU that disable interrupts and
then gets stuck in a loop, the stack trace should be informative.

We could clear the saved stack pointer when we enable interrupts, but
that loses information which could be useful if we have nothing else
to go on.

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>

diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index 9aec723..e151774 100644 (file)
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -238,8 +238,12 @@ static inline bool arch_irqs_disabled(void)
        __hard_irq_disable();                                           \
        flags = irq_soft_mask_set_return(IRQS_ALL_DISABLED);            \
        local_paca->irq_happened |= PACA_IRQ_HARD_DIS;                  \
-       if (!arch_irqs_disabled_flags(flags))                           \
+       if (!arch_irqs_disabled_flags(flags)) {                         \
+               asm ("stdx %%r1, 0, %1 ;"                               \
+                    : "=m" (local_paca->saved_r1)                      \
+                    : "b" (&local_paca->saved_r1));                    \
                trace_hardirqs_off();                                   \
+       }                                                               \
 } while(0)
 
 static inline bool lazy_irq_pending(void)

diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index 81471bd..6d34bd7 100644 (file)
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -161,7 +161,7 @@ struct paca_struct {
        struct task_struct *__current;  /* Pointer to current */
        u64 kstack;                     /* Saved Kernel stack addr */
        u64 stab_rr;                    /* stab/slb round-robin counter */
-       u64 saved_r1;                   /* r1 save for RTAS calls or PM */
+       u64 saved_r1;                   /* r1 save for RTAS calls or PM or EE=0 */
        u64 saved_msr;                  /* MSR saved here by enter_rtas */
        u16 trap_save;                  /* Used when bad stack is encountered */
        u8 irq_soft_mask;               /* mask for irq soft masking */

diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index ae6a849..bb26fe9 100644 (file)
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1499,6 +1499,7 @@ masked_##_H##interrupt:                                   \
        xori    r10,r10,MSR_EE; /* clear MSR_EE */      \
        mtspr   SPRN_##_H##SRR1,r10;                    \
 2:     mtcrf   0x80,r9;                                \
+       std     r1,PACAR1(r13);                         \
        ld      r9,PACA_EXGEN+EX_R9(r13);               \
        ld      r10,PACA_EXGEN+EX_R10(r13);             \
        ld      r11,PACA_EXGEN+EX_R11(r13);             \

diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 0561c14..47166ad 100644 (file)
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -1172,6 +1172,10 @@ static int cpu_cmd(void)
        /* try to switch to cpu specified */
        if (!cpumask_test_cpu(cpu, &cpus_in_xmon)) {
                printf("cpu 0x%lx isn't in xmon\n", cpu);
+#ifdef CONFIG_PPC64
+               printf("backtrace of paca[0x%lx].saved_r1 (possibly stale):\n", cpu);
+               xmon_show_stack(paca_ptrs[cpu]->saved_r1, 0, 0);
+#endif
                return 0;
        }
        xmon_taken = 0;