Commit 733e4a4c authored by Balbir Singh's avatar Balbir Singh Committed by Michael Ellerman
Browse files

powerpc/mce: hookup memory_failure for UE errors 



If we are in user space and hit a UE error, we now have the
basic infrastructure to walk the page tables and find out
the effective address that was accessed, since the DAR
is not valid.

We use a work_queue content to hookup the bad pfn, any
other context causes problems, since memory_failure itself
can call into schedule() via lru_drain_ bits.

We could probably poison the struct page to avoid a race
between detection and taking corrective action.

Signed-off-by: default avatarBalbir Singh <bsingharora@gmail.com>
Reviewed-by: default avatarNicholas Piggin <npiggin@gmail.com>
Signed-off-by: default avatarMichael Ellerman <mpe@ellerman.id.au>
parent 01eaac2b

arch/powerpc/kernel/mce.c

+67 −3
Original line number Original line Diff line number Diff line
@@ -39,11 +39,21 @@ static DEFINE_PER_CPU(struct machine_check_event[MAX_MC_EVT], mce_event); 
static DEFINE_PER_CPU(int, mce_queue_count);

static DEFINE_PER_CPU(int, mce_queue_count);

static DEFINE_PER_CPU(struct machine_check_event[MAX_MC_EVT], mce_event_queue);

static DEFINE_PER_CPU(struct machine_check_event[MAX_MC_EVT], mce_event_queue);





/* Queue for delayed MCE UE events. */

static DEFINE_PER_CPU(int, mce_ue_count);

static DEFINE_PER_CPU(struct machine_check_event[MAX_MC_EVT],

					mce_ue_event_queue);



static void machine_check_process_queued_event(struct irq_work *work);

static void machine_check_process_queued_event(struct irq_work *work);

void machine_check_ue_event(struct machine_check_event *evt);

static void machine_process_ue_event(struct work_struct *work);



static struct irq_work mce_event_process_work = {

static struct irq_work mce_event_process_work = {

        .func = machine_check_process_queued_event,

        .func = machine_check_process_queued_event,

};

};





DECLARE_WORK(mce_ue_event_work, machine_process_ue_event);



static void mce_set_error_info(struct machine_check_event *mce,

static void mce_set_error_info(struct machine_check_event *mce,

			       struct mce_error_info *mce_err)

			       struct mce_error_info *mce_err)

{

{
@@ -143,6 +153,7 @@ void save_mce_event(struct pt_regs *regs, long handled, 
		if (phys_addr != ULONG_MAX) {

		if (phys_addr != ULONG_MAX) {

			mce->u.ue_error.physical_address_provided = true;

			mce->u.ue_error.physical_address_provided = true;

			mce->u.ue_error.physical_address = phys_addr;

			mce->u.ue_error.physical_address = phys_addr;

			machine_check_ue_event(mce);

		}

		}

	}

	}

	return;

	return;
@@ -197,6 +208,26 @@ void release_mce_event(void) 
	get_mce_event(NULL, true);

	get_mce_event(NULL, true);

}

}







/*

 * Queue up the MCE event which then can be handled later.

 */

void machine_check_ue_event(struct machine_check_event *evt)

{

	int index;



	index = __this_cpu_inc_return(mce_ue_count) - 1;

	/* If queue is full, just return for now. */

	if (index >= MAX_MC_EVT) {

		__this_cpu_dec(mce_ue_count);

		return;

	}

	memcpy(this_cpu_ptr(&mce_ue_event_queue[index]), evt, sizeof(*evt));



	/* Queue work to process this event later. */

	schedule_work(&mce_ue_event_work);

}



/*

/*

 * Queue up the MCE event which then can be handled later.

 * Queue up the MCE event which then can be handled later.

 */

 */
@@ -219,7 +250,39 @@ void machine_check_queue_event(void) 
	/* Queue irq work to process this event later. */

	/* Queue irq work to process this event later. */

	irq_work_queue(&mce_event_process_work);

	irq_work_queue(&mce_event_process_work);

}

}

/*

 * process pending MCE event from the mce event queue. This function will be

 * called during syscall exit.

 */

static void machine_process_ue_event(struct work_struct *work)

{

	int index;

	struct machine_check_event *evt;





	while (__this_cpu_read(mce_ue_count) > 0) {

		index = __this_cpu_read(mce_ue_count) - 1;

		evt = this_cpu_ptr(&mce_ue_event_queue[index]);

#ifdef CONFIG_MEMORY_FAILURE

		/*

		 * This should probably queued elsewhere, but

		 * oh! well

		 */

		if (evt->error_type == MCE_ERROR_TYPE_UE) {

			if (evt->u.ue_error.physical_address_provided) {

				unsigned long pfn;



				pfn = evt->u.ue_error.physical_address >>

					PAGE_SHIFT;

				memory_failure(pfn, SIGBUS, 0);

			} else

				pr_warn("Failed to identify bad address from "

					"where the uncorrectable error (UE) "

					"was generated\n");

		}

#endif

		__this_cpu_dec(mce_ue_count);

	}

}

/*

/*

 * process pending MCE event from the mce event queue. This function will be

 * process pending MCE event from the mce event queue. This function will be

 * called during syscall exit.

 * called during syscall exit.
@@ -227,6 +290,7 @@ void machine_check_queue_event(void) 
static void machine_check_process_queued_event(struct irq_work *work)

static void machine_check_process_queued_event(struct irq_work *work)

{

{

	int index;

	int index;

	struct machine_check_event *evt;





	add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);

	add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
@@ -236,8 +300,8 @@ static void machine_check_process_queued_event(struct irq_work *work) 
	 */

	 */

	while (__this_cpu_read(mce_queue_count) > 0) {

	while (__this_cpu_read(mce_queue_count) > 0) {

		index = __this_cpu_read(mce_queue_count) - 1;

		index = __this_cpu_read(mce_queue_count) - 1;

		machine_check_print_event_info(

		evt = this_cpu_ptr(&mce_event_queue[index]);

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

		machine_check_print_event_info(evt, false);

		__this_cpu_dec(mce_queue_count);

		__this_cpu_dec(mce_queue_count);

	}

	}

}

}

CRA Git | Maintained and supported by SUSTech CRA and CCSE