Commit 63f44d65 authored by Michael Ellerman's avatar Michael Ellerman
Browse files

powerpc/book3s: Print task info if we take a machine check in user mode 



For an MCE (Machine Check Exception) that hits while in user mode
MSR(PR=1), print the task info to the console MCE error log. This may
help to identify an application that triggered the MCE.

After this patch the MCE console looks like:

  Severe Machine check interrupt [Recovered]
    NIP: [0000000010039778] PID: 762 Comm: ebizzy
    Initiator: CPU
    Error type: SLB [Multihit]
      Effective address: 0000000010039778

  Severe Machine check interrupt [Not recovered]
    NIP: [0000000010039778] PID: 763 Comm: ebizzy
    Initiator: CPU
    Error type: UE [Page table walk ifetch]
      Effective address: 0000000010039778
  ebizzy[763]: unhandled signal 7 at 0000000010039778 nip 0000000010039778 lr 0000000010001b44 code 30004

Signed-off-by: default avatarMahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Signed-off-by: default avatarMichael Ellerman <mpe@ellerman.id.au>
parent 5b1d6fc2

arch/powerpc/include/asm/mce.h

+2 −1
Original line number Diff line number Diff line
@@ -207,7 +207,8 @@ extern void save_mce_event(struct pt_regs *regs, long handled, 
extern int get_mce_event(struct machine_check_event *mce, bool release);

extern void release_mce_event(void);

extern void machine_check_queue_event(void);

extern void machine_check_print_event_info(struct machine_check_event *evt);

extern void machine_check_print_event_info(struct machine_check_event *evt,

					   bool user_mode);

extern uint64_t get_mce_fault_addr(struct machine_check_event *evt);



#endif /* __ASM_PPC64_MCE_H__ */

arch/powerpc/kernel/mce.c

+12 −3
Original line number Diff line number Diff line
@@ -228,12 +228,13 @@ static void machine_check_process_queued_event(struct irq_work *work) 
	while (__this_cpu_read(mce_queue_count) > 0) {

		index = __this_cpu_read(mce_queue_count) - 1;

		machine_check_print_event_info(

				this_cpu_ptr(&mce_event_queue[index]));

				this_cpu_ptr(&mce_event_queue[index]), false);

		__this_cpu_dec(mce_queue_count);

	}

}



void machine_check_print_event_info(struct machine_check_event *evt)

void machine_check_print_event_info(struct machine_check_event *evt,

				    bool user_mode)

{

	const char *level, *sevstr, *subtype;

	static const char *mc_ue_types[] = {
@@ -311,7 +312,15 @@ void machine_check_print_event_info(struct machine_check_event *evt) 
	printk("%s%s Machine check interrupt [%s]\n", level, sevstr,

	       evt->disposition == MCE_DISPOSITION_RECOVERED ?

	       "Recovered" : "Not recovered");

	printk("%s  NIP [%016llx]: %pS\n", level, evt->srr0, (void *)evt->srr0);



	if (user_mode) {

		printk("%s  NIP: [%016llx] PID: %d Comm: %s\n", level,

			evt->srr0, current->pid, current->comm);

	} else {

		printk("%s  NIP [%016llx]: %pS\n", level, evt->srr0,

		       (void *)evt->srr0);

	}



	printk("%s  Initiator: %s\n", level,

	       evt->initiator == MCE_INITIATOR_CPU ? "CPU" : "Unknown");

	switch (evt->error_type) {

arch/powerpc/platforms/powernv/opal.c

+1 −1
Original line number Diff line number Diff line
@@ -435,7 +435,7 @@ int opal_machine_check(struct pt_regs *regs) 
		       evt.version);

		return 0;

	}

	machine_check_print_event_info(&evt);

	machine_check_print_event_info(&evt, user_mode(regs));



	if (opal_recover_mce(regs, &evt))

		return 1;

CRA Git | Maintained and supported by SUSTech CRA and CCSE