diff options
author | Balbir Singh <bsingharora@gmail.com> | 2017-09-29 14:26:55 +1000 |
---|---|---|
committer | Michael Ellerman <mpe@ellerman.id.au> | 2017-10-16 23:12:02 +1100 |
commit | 733e4a4c4467033918f4e64f797b03efe209d82c (patch) | |
tree | b710e2e735d8359e3d7b8a2e6cd82d4ab5647432 /arch/powerpc/kernel | |
parent | 01eaac2b0591f7114d9de5cc65c88352de0daca6 (diff) | |
download | op-kernel-dev-733e4a4c4467033918f4e64f797b03efe209d82c.zip op-kernel-dev-733e4a4c4467033918f4e64f797b03efe209d82c.tar.gz |
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: Balbir Singh <bsingharora@gmail.com>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Diffstat (limited to 'arch/powerpc/kernel')
-rw-r--r-- | arch/powerpc/kernel/mce.c | 70 |
1 files changed, 67 insertions, 3 deletions
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c index 1af7c55..742e465 100644 --- a/arch/powerpc/kernel/mce.c +++ b/arch/powerpc/kernel/mce.c @@ -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(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); +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 = { .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, 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) { mce->u.ue_error.physical_address_provided = true; mce->u.ue_error.physical_address = phys_addr; + machine_check_ue_event(mce); } } return; @@ -197,6 +208,26 @@ void release_mce_event(void) 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. */ @@ -219,7 +250,39 @@ void machine_check_queue_event(void) /* Queue irq work to process this event later. */ 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 * 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) { int index; + struct machine_check_event *evt; 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) { index = __this_cpu_read(mce_queue_count) - 1; - machine_check_print_event_info( - this_cpu_ptr(&mce_event_queue[index]), false); + evt = this_cpu_ptr(&mce_event_queue[index]); + machine_check_print_event_info(evt, false); __this_cpu_dec(mce_queue_count); } } |