diff options
Diffstat (limited to 'arch/powerpc/kernel/mce.c')
-rw-r--r-- | arch/powerpc/kernel/mce.c | 189 |
1 files changed, 130 insertions, 59 deletions
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c index 34c1001e9e8b..219f28637a3e 100644 --- a/arch/powerpc/kernel/mce.c +++ b/arch/powerpc/kernel/mce.c @@ -15,37 +15,36 @@ #include <linux/percpu.h> #include <linux/export.h> #include <linux/irq_work.h> +#include <linux/extable.h> +#include <linux/ftrace.h> +#include <linux/memblock.h> +#include <linux/of.h> +#include <asm/interrupt.h> #include <asm/machdep.h> #include <asm/mce.h> #include <asm/nmi.h> -static DEFINE_PER_CPU(int, mce_nest_count); -static DEFINE_PER_CPU(struct machine_check_event[MAX_MC_EVT], mce_event); +#include "setup.h" -/* Queue for delayed MCE events. */ -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); -static void machine_check_ue_irq_work(struct irq_work *work); static 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, -}; +static DECLARE_WORK(mce_ue_event_work, machine_process_ue_event); -static struct irq_work mce_ue_event_irq_work = { - .func = machine_check_ue_irq_work, -}; +static BLOCKING_NOTIFIER_HEAD(mce_notifier_list); -DECLARE_WORK(mce_ue_event_work, machine_process_ue_event); +int mce_register_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_register(&mce_notifier_list, nb); +} +EXPORT_SYMBOL_GPL(mce_register_notifier); + +int mce_unregister_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_unregister(&mce_notifier_list, nb); +} +EXPORT_SYMBOL_GPL(mce_unregister_notifier); static void mce_set_error_info(struct machine_check_event *mce, struct mce_error_info *mce_err) @@ -79,6 +78,13 @@ static void mce_set_error_info(struct machine_check_event *mce, } } +void mce_irq_work_queue(void) +{ + /* Raise decrementer interrupt */ + arch_irq_work_raise(); + set_mce_pending_irq_work(); +} + /* * Decode and save high level MCE information into per cpu buffer which * is an array of machine_check_event structure. @@ -87,9 +93,10 @@ void save_mce_event(struct pt_regs *regs, long handled, struct mce_error_info *mce_err, 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]); + int index = local_paca->mce_info->mce_nest_count++; + struct machine_check_event *mce; + mce = &local_paca->mce_info->mce_event[index]; /* * Return if we don't have enough space to log mce event. * mce_nest_count may go beyond MAX_MC_EVT but that's ok, @@ -121,6 +128,15 @@ void save_mce_event(struct pt_regs *regs, long handled, * Populate the mce error_type and type-specific error_type. */ mce_set_error_info(mce, mce_err); + if (mce->error_type == MCE_ERROR_TYPE_UE) + mce->u.ue_error.ignore_event = mce_err->ignore_event; + + /* + * Raise irq work, So that we don't miss to log the error for + * unrecoverable errors. + */ + if (mce->disposition == MCE_DISPOSITION_NOT_RECOVERED) + mce_irq_work_queue(); if (!addr) return; @@ -149,7 +165,6 @@ 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; - mce->u.ue_error.ignore_event = mce_err->ignore_event; machine_check_ue_event(mce); } } @@ -175,7 +190,7 @@ void save_mce_event(struct pt_regs *regs, long handled, */ int get_mce_event(struct machine_check_event *mce, bool release) { - int index = __this_cpu_read(mce_nest_count) - 1; + int index = local_paca->mce_info->mce_nest_count - 1; struct machine_check_event *mc_evt; int ret = 0; @@ -185,7 +200,7 @@ int get_mce_event(struct machine_check_event *mce, bool release) /* Check if we have MCE info to process. */ if (index < MAX_MC_EVT) { - mc_evt = this_cpu_ptr(&mce_event[index]); + mc_evt = &local_paca->mce_info->mce_event[index]; /* Copy the event structure and release the original */ if (mce) *mce = *mc_evt; @@ -195,7 +210,7 @@ int get_mce_event(struct machine_check_event *mce, bool release) } /* Decrement the count to free the slot. */ if (release) - __this_cpu_dec(mce_nest_count); + local_paca->mce_info->mce_nest_count--; return ret; } @@ -205,7 +220,7 @@ void release_mce_event(void) get_mce_event(NULL, true); } -static void machine_check_ue_irq_work(struct irq_work *work) +static void machine_check_ue_work(void) { schedule_work(&mce_ue_event_work); } @@ -217,16 +232,14 @@ static void machine_check_ue_event(struct machine_check_event *evt) { int index; - index = __this_cpu_inc_return(mce_ue_count) - 1; + index = local_paca->mce_info->mce_ue_count++; /* If queue is full, just return for now. */ if (index >= MAX_MC_EVT) { - __this_cpu_dec(mce_ue_count); + local_paca->mce_info->mce_ue_count--; return; } - memcpy(this_cpu_ptr(&mce_ue_event_queue[index]), evt, sizeof(*evt)); - - /* Queue work to process this event later. */ - irq_work_queue(&mce_ue_event_irq_work); + memcpy(&local_paca->mce_info->mce_ue_event_queue[index], + evt, sizeof(*evt)); } /* @@ -240,17 +253,30 @@ void machine_check_queue_event(void) if (!get_mce_event(&evt, MCE_EVENT_RELEASE)) return; - index = __this_cpu_inc_return(mce_queue_count) - 1; + index = local_paca->mce_info->mce_queue_count++; /* If queue is full, just return for now. */ if (index >= MAX_MC_EVT) { - __this_cpu_dec(mce_queue_count); + local_paca->mce_info->mce_queue_count--; return; } - memcpy(this_cpu_ptr(&mce_event_queue[index]), &evt, sizeof(evt)); + memcpy(&local_paca->mce_info->mce_event_queue[index], + &evt, sizeof(evt)); + + mce_irq_work_queue(); +} + +void mce_common_process_ue(struct pt_regs *regs, + struct mce_error_info *mce_err) +{ + const struct exception_table_entry *entry; - /* Queue irq work to process this event later. */ - irq_work_queue(&mce_event_process_work); + entry = search_kernel_exception_table(regs->nip); + if (entry) { + mce_err->ignore_event = true; + regs_set_return_ip(regs, extable_fixup(entry)); + } } + /* * process pending MCE event from the mce event queue. This function will be * called during syscall exit. @@ -260,9 +286,10 @@ 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]); + while (local_paca->mce_info->mce_ue_count > 0) { + index = local_paca->mce_info->mce_ue_count - 1; + evt = &local_paca->mce_info->mce_ue_event_queue[index]; + blocking_notifier_call_chain(&mce_notifier_list, 0, evt); #ifdef CONFIG_MEMORY_FAILURE /* * This should probably queued elsewhere, but @@ -274,7 +301,7 @@ static void machine_process_ue_event(struct work_struct *work) */ if (evt->error_type == MCE_ERROR_TYPE_UE) { if (evt->u.ue_error.ignore_event) { - __this_cpu_dec(mce_ue_count); + local_paca->mce_info->mce_ue_count--; continue; } @@ -290,14 +317,14 @@ static void machine_process_ue_event(struct work_struct *work) "was generated\n"); } #endif - __this_cpu_dec(mce_ue_count); + local_paca->mce_info->mce_ue_count--; } } /* * process pending MCE event from the mce event queue. This function will be * called during syscall exit. */ -static void machine_check_process_queued_event(struct irq_work *work) +static void machine_check_process_queued_event(void) { int index; struct machine_check_event *evt; @@ -308,17 +335,38 @@ static void machine_check_process_queued_event(struct irq_work *work) * For now just print it to console. * TODO: log this error event to FSP or nvram. */ - while (__this_cpu_read(mce_queue_count) > 0) { - index = __this_cpu_read(mce_queue_count) - 1; - evt = this_cpu_ptr(&mce_event_queue[index]); + while (local_paca->mce_info->mce_queue_count > 0) { + index = local_paca->mce_info->mce_queue_count - 1; + evt = &local_paca->mce_info->mce_event_queue[index]; if (evt->error_type == MCE_ERROR_TYPE_UE && evt->u.ue_error.ignore_event) { - __this_cpu_dec(mce_queue_count); + local_paca->mce_info->mce_queue_count--; continue; } machine_check_print_event_info(evt, false, false); - __this_cpu_dec(mce_queue_count); + local_paca->mce_info->mce_queue_count--; + } +} + +void set_mce_pending_irq_work(void) +{ + local_paca->mce_pending_irq_work = 1; +} + +void clear_mce_pending_irq_work(void) +{ + local_paca->mce_pending_irq_work = 0; +} + +void mce_run_irq_context_handlers(void) +{ + if (unlikely(local_paca->mce_pending_irq_work)) { + if (ppc_md.machine_check_log_err) + ppc_md.machine_check_log_err(); + machine_check_process_queued_event(); + machine_check_ue_work(); + clear_mce_pending_irq_work(); } } @@ -355,18 +403,19 @@ void machine_check_print_event_info(struct machine_check_event *evt, static const char *mc_user_types[] = { "Indeterminate", "tlbie(l) invalid", + "scv invalid", }; static const char *mc_ra_types[] = { "Indeterminate", "Instruction fetch (bad)", - "Instruction fetch (foreign)", + "Instruction fetch (foreign/control memory)", "Page table walk ifetch (bad)", - "Page table walk ifetch (foreign)", + "Page table walk ifetch (foreign/control memory)", "Load (bad)", "Store (bad)", "Page table walk Load/Store (bad)", - "Page table walk Load/Store (foreign)", - "Load/Store (foreign)", + "Page table walk Load/Store (foreign/control memory)", + "Load/Store (foreign/control memory)", }; static const char *mc_link_types[] = { "Indeterminate", @@ -524,7 +573,7 @@ void machine_check_print_event_info(struct machine_check_event *evt, } printk("%sMCE: CPU%d: machine check (%s) %s %s %s %s[%s]\n", - level, evt->cpu, sevstr, in_guest ? "Guest" : "Host", + level, evt->cpu, sevstr, in_guest ? "Guest" : "", err_type, subtype, dar_str, evt->disposition == MCE_DISPOSITION_RECOVERED ? "Recovered" : "Not recovered"); @@ -544,9 +593,9 @@ void machine_check_print_event_info(struct machine_check_event *evt, mc_error_class[evt->error_class] : "Unknown"; printk("%sMCE: CPU%d: %s\n", level, evt->cpu, subtype); -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU /* Display faulty slb contents for SLB errors. */ - if (evt->error_type == MCE_ERROR_TYPE_SLB) + if (evt->error_type == MCE_ERROR_TYPE_SLB && !in_guest) slb_dump_contents(local_paca->mce_faulty_slbs); #endif } @@ -557,7 +606,7 @@ EXPORT_SYMBOL_GPL(machine_check_print_event_info); * * regs->nip and regs->msr contains srr0 and ssr1. */ -long machine_check_early(struct pt_regs *regs) +DEFINE_INTERRUPT_HANDLER_NMI(machine_check_early) { long handled = 0; @@ -568,6 +617,7 @@ long machine_check_early(struct pt_regs *regs) */ if (ppc_md.machine_check_early) handled = ppc_md.machine_check_early(regs); + return handled; } @@ -679,11 +729,11 @@ long hmi_handle_debugtrig(struct pt_regs *regs) /* * Return values: */ -long hmi_exception_realmode(struct pt_regs *regs) +DEFINE_INTERRUPT_HANDLER_NMI(hmi_exception_realmode) { int ret; - __this_cpu_inc(irq_stat.hmi_exceptions); + local_paca->hmi_irqs++; ret = hmi_handle_debugtrig(regs); if (ret >= 0) @@ -698,3 +748,24 @@ long hmi_exception_realmode(struct pt_regs *regs) return 1; } + +void __init mce_init(void) +{ + struct mce_info *mce_info; + u64 limit; + int i; + + limit = min(ppc64_bolted_size(), ppc64_rma_size); + for_each_possible_cpu(i) { + mce_info = memblock_alloc_try_nid(sizeof(*mce_info), + __alignof__(*mce_info), + MEMBLOCK_LOW_LIMIT, + limit, early_cpu_to_node(i)); + if (!mce_info) + goto err; + paca_ptrs[i]->mce_info = mce_info; + } + return; +err: + panic("Failed to allocate memory for MCE event data\n"); +} |