SysRq-L and RCU stall detector call arch_trigger_cpumask_backtrace() to trigger other CPU's backtrace, but its behavior is totally broken. The root cause is arch_trigger_cpumask_backtrace() use call-function IPI in irq context, which trigger deadlocks in smp_call_function_single() and smp_call_function_many().

This patch fix arch_trigger_cpumask_backtrace() by: 1, Use a dedecated IPI (SMP_CPU_BACKTRACE) to trigger backtraces; 2, If myself is in target cpumask, do backtrace and clear myself; 3, Use a spinlock to avoid parallel backtrace output; 4, Handle SMP_CPU_BACKTRACE IPI for Loongson-3.

I have attempted to implement SMP_CPU_BACKTRACE for all MIPS CPUs, but I failed because some of their IPIs are not extensible. :(

Cc: stable@vger.kernel.org Signed-off-by: Huacai Chen chenhc@lemote.com --- arch/mips/include/asm/smp.h | 3 +++ arch/mips/kernel/process.c | 23 ++++++++++++++++++----- arch/mips/loongson64/loongson-3/smp.c | 6 ++++++ 3 files changed, 27 insertions(+), 5 deletions(-)

diff --git a/arch/mips/include/asm/smp.h b/arch/mips/include/asm/smp.h index 88ebd83..b0521f4 100644 --- a/arch/mips/include/asm/smp.h +++ b/arch/mips/include/asm/smp.h @@ -43,6 +43,7 @@ extern int __cpu_logical_map[NR_CPUS]; /* Octeon - Tell another core to flush its icache */ #define SMP_ICACHE_FLUSH 0x4 #define SMP_ASK_C0COUNT 0x8 +#define SMP_CPU_BACKTRACE 0x10

/* Mask of CPUs which are currently definitely operating coherently */ extern cpumask_t cpu_coherent_mask; @@ -81,6 +82,8 @@ static inline void __cpu_die(unsigned int cpu) extern void play_dead(void); #endif

+void arch_dump_stack(void); + /* * This function will set up the necessary IPIs for Linux to communicate * with the CPUs in mask. diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index 57028d4..647e15d 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -655,26 +655,39 @@ unsigned long arch_align_stack(unsigned long sp) return sp & ALMASK; }

-static void arch_dump_stack(void *info) +void arch_dump_stack(void) { struct pt_regs *regs; + static arch_spinlock_t lock = __ARCH_SPIN_LOCK_UNLOCKED;

+ arch_spin_lock(&lock); regs = get_irq_regs();

if (regs) show_regs(regs);

dump_stack(); + arch_spin_unlock(&lock); }

void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self) { long this_cpu = get_cpu(); + struct cpumask backtrace_mask; + extern const struct plat_smp_ops *mp_ops; + + cpumask_copy(&backtrace_mask, mask); + if (cpumask_test_cpu(this_cpu, mask)) { + if (!exclude_self) { + struct pt_regs *regs = get_irq_regs(); + if (regs) + show_regs(regs); + dump_stack(); + } + cpumask_clear_cpu(this_cpu, &backtrace_mask); + }

- if (cpumask_test_cpu(this_cpu, mask) && !exclude_self) - dump_stack(); - - smp_call_function_many(mask, arch_dump_stack, NULL, 1); + mp_ops->send_ipi_mask(&backtrace_mask, SMP_CPU_BACKTRACE);

put_cpu(); } diff --git a/arch/mips/loongson64/loongson-3/smp.c b/arch/mips/loongson64/loongson-3/smp.c index 8501109..0655114 100644 --- a/arch/mips/loongson64/loongson-3/smp.c +++ b/arch/mips/loongson64/loongson-3/smp.c @@ -291,6 +291,12 @@ void loongson3_ipi_interrupt(struct pt_regs *regs) __wbflush(); /* Let others see the result ASAP */ }

+ if (action & SMP_CPU_BACKTRACE) { + irq_enter(); + arch_dump_stack(); + irq_exit(); + } + if (irqs) { int irq; while ((irq = ffs(irqs))) {