Revisit MCE handling for UE Errors
v3 cover Revisit MCE handling for UE Errors
This patch series is designed to hook up memory_failure on UE errors, this is specially helpful for user_mode UE errors.
The first two patches cleanup bits, remove dead code. I could not find any users of get_mce_fault_addr(). The second one improves printing of physical address
The third patch walks kernel/user mode page tables in real mode to extract the effective address of the instruction that caused the UE error and the effective address it was trying to access (for load/store). The fourth patch hooks up the pfn for instruction UE errors (ierror).
The fifth patch hooks up memory_failure to the MCE patch.
TODO:
Log the address in NVRAM, so that we can recover from bad pages at boot and keep the blacklist persistent.
Changelog v3:
- Check for recursive MCE invocations (suggested by Nick)
Changelog v2:
- Remove pr_warn from real mode to a more delayed context, where its OK to warn.
- Add a trivial patch to align prints of physical and effective address
Changelog v1:
- Address review comments from Nick and Mahesh (initialization of pfn and more comments on failure when addr_to_pfn() or anaylse_instr() fail)
- Hookup ierrors to the framework as well (comments from Mahesh)
Balbir Singh (5):
powerpc/mce.c: Remove unused function get_mce_fault_addr() powerpc/mce: align the print of physical address better powerpc/mce: Hookup derror (load/store) UE errors powerpc/mce: Hookup ierror (instruction) UE errors powerpc/mce: hookup memory_failure for UE errors
arch/powerpc/include/asm/mce.h | 4 +- arch/powerpc/kernel/mce.c | 114 ++++++++++++++++++++++++---------------- arch/powerpc/kernel/mce_power.c | 109 +++++++++++++++++++++++++++++++++++--- 3 files changed, 172 insertions(+), 55 deletions(-)
Signature · 1 line
2.9.5
PATCH v3 1/5 powerpc/mce.c: Remove unused function get_mce_fault_addr()
There are no users of get_mce_fault_addr()
--- arch/powerpc/include/asm/mce.h | 2 -- arch/powerpc/kernel/mce.c | 39 --------------------------------------- 2 files changed, 41 deletions(-)
arch/powerpc/include/asm/mce.h +0 -2
@@ -210,6 +210,4 @@ 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,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 +0 -39
@@ -411,45 +411,6 @@ void machine_check_print_event_info(struct machine_check_event *evt, }EXPORT_SYMBOL_GPL (machine_check_print_event_info); -uint64_t get_mce_fault_addr (struct machine_check_event *evt) -{ -switch (evt->error_type) { -case MCE_ERROR_TYPE_UE : -if (evt->u.ue_error.effective_address_provided) -return evt->u.ue_error.effective_address; -break ; -case MCE_ERROR_TYPE_SLB : -if (evt->u.slb_error.effective_address_provided) -return evt->u.slb_error.effective_address; -break ; -case MCE_ERROR_TYPE_ERAT : -if (evt->u.erat_error.effective_address_provided) -return evt->u.erat_error.effective_address; -break ; -case MCE_ERROR_TYPE_TLB : -if (evt->u.tlb_error.effective_address_provided) -return evt->u.tlb_error.effective_address; -break ; -case MCE_ERROR_TYPE_USER : -if (evt->u.user_error.effective_address_provided) -return evt->u.user_error.effective_address; -break ; -case MCE_ERROR_TYPE_RA : -if (evt->u.ra_error.effective_address_provided) -return evt->u.ra_error.effective_address; -break ; -case MCE_ERROR_TYPE_LINK : -if (evt->u.link_error.effective_address_provided) -return evt->u.link_error.effective_address; -break ; -default : -case MCE_ERROR_TYPE_UNKNOWN : -break ; - } -return 0 ; -} -EXPORT_SYMBOL (get_mce_fault_addr); -/* * This function is called in real mode. Strictly no printk's please. *
Signature · 1 line
2.9.5
PATCH v3 2/5 powerpc/mce: align the print of physical address better
In reply to Balbir SinghUse the same alignment as Effective address and rename phyiscal address to Page Frame Number
--- arch/powerpc/kernel/mce.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
arch/powerpc/kernel/mce.c +1 -1
@@ -340,7 +340,7 @@ void machine_check_print_event_info(struct machine_check_event *evt,printk ("%s Effective address: %016llx\n" , level, evt->u.ue_error.effective_address);if (evt->u.ue_error.physical_address_provided) -printk ("%s Physical address: %016llx\n" , +printk ("%s Page Frame Number: %016llx\n" , level, evt->u.ue_error.physical_address);break ;case MCE_ERROR_TYPE_SLB :
Signature · 1 line
2.9.5
PATCH v3 3/5 powerpc/mce: Hookup derror (load/store) UE errors
In reply to Balbir SinghExtract physical_address for UE errors by walking the page tables for the mm and address at the NIP, to extract the instruction. Then use the instruction to find the effective address via analyse_instr().
We might have page table walking races, but we expect them to be rare, the physical address extraction is best effort. The idea is to then hook up this infrastructure to memory failure eventually.
--- arch/powerpc/include/asm/mce.h | 2 +- arch/powerpc/kernel/mce.c | 6 ++- arch/powerpc/kernel/mce_power.c | 86 ++++++++++++++++++++++++++++++++++++++--- 3 files changed, 87 insertions(+), 7 deletions(-)
arch/powerpc/include/asm/mce.h +1 -1
@@ -204,7 +204,7 @@ struct mce_error_info {extern void save_mce_event (struct pt_regs *regs,long handled,struct mce_error_info *mce_err,uint64_t nip, -uint64_t addr); +uint64_t addr,uint64_t phys_addr);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 );
arch/powerpc/kernel/mce.c +5 -1
@@ -82,7 +82,7 @@ static void mce_set_error_info(struct machine_check_event *mce,*/ void save_mce_event (struct pt_regs *regs,long handled,struct mce_error_info *mce_err, -uint64_t nip,uint64_t addr) +uint64_t nip,uint64_t addr,uint64_t phys_addr) {int index =__this_cpu_inc_return (mce_nest_count) -1 ;struct machine_check_event *mce =this_cpu_ptr (&mce_event[index]);
@@ -140,6 +140,10 @@ void save_mce_event(struct pt_regs *regs, long handled, }else if (mce->error_type ==MCE_ERROR_TYPE_UE ) { mce->u.ue_error.effective_address_provided = true; mce->u.ue_error.effective_address = addr; +if (phys_addr !=ULONG_MAX ) { + mce->u.ue_error.physical_address_provided = true; + mce->u.ue_error.physical_address = phys_addr; + } }return ; }
arch/powerpc/kernel/mce_power.c +81 -5
126 lines not on this page · raw message
Signature · 1 line
2.9.5
PATCH v3 4/5 powerpc/mce: Hookup ierror (instruction) UE errors
In reply to Balbir SinghHookup instruction errors (UE) for memory offling via memory_failure() in a manner similar to load/store errors (derror). Since we have access to the NIP, the conversion is a one step process in this case.
--- arch/powerpc/kernel/mce_power.c | 23 ++++++++++++++++++++--- 1 file changed, 20 insertions(+), 3 deletions(-)
arch/powerpc/kernel/mce_power.c +20 -3
@@ -488,7 +488,8 @@ static int mce_find_instr_ea_and_pfn(struct pt_regs *regs, uint64_t *addr,static int mce_handle_ierror (struct pt_regs *regs,const struct mce_ierror_table table[], -struct mce_error_info *mce_err,uint64_t *addr) +struct mce_error_info *mce_err,uint64_t *addr, +uint64_t *phys_addr) {uint64_t srr1 = regs->msr;int handled =0 ;
@@ -540,8 +541,23 @@ static int mce_handle_ierror(struct pt_regs *regs, } mce_err->severity = table[i].severity; mce_err->initiator = table[i].initiator; -if (table[i].nip_valid) +if (table[i].nip_valid) { *addr = regs->nip; +if (mce_err->severity ==MCE_SEV_ERROR_SYNC && + table[i].error_type ==MCE_ERROR_TYPE_UE ) { +unsigned long pfn; +struct mm_struct *mm; + +if (user_mode (regs)) + mm = current->mm; +else + mm = &init_mm; + + pfn =addr_to_pfn (mm, regs->nip); +if (pfn !=ULONG_MAX ) + *phys_addr = pfn; + } + }return handled; }
@@ -675,7 +691,8 @@ static long mce_handle_error(struct pt_regs *regs, handled =mce_handle_derror (regs, dtable, &mce_err, &addr, &phys_addr); else - handled =mce_handle_ierror (regs, itable, &mce_err, &addr); + handled =mce_handle_ierror (regs, itable, &mce_err, &addr, + &phys_addr);if (!handled && mce_err.error_type ==MCE_ERROR_TYPE_UE ) handled =mce_handle_ue_error (regs);
Signature · 1 line
2.9.5
PATCH v3 5/5 powerpc/mce: hookup memory_failure for UE errors
In reply to Balbir SinghIf 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.
--- arch/powerpc/kernel/mce.c | 67 ++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 64 insertions(+), 3 deletions(-)
arch/powerpc/kernel/mce.c +64 -3
@@ -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 +250,36 @@ 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) +memory_failure (evt->u.ue_error.physical_address, +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 +287,7 @@ 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 +297,8 @@ 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); } }
Signature · 1 line
2.9.5