From 8b38937b7ab55e93065a14c88753b1fe83e93c60 Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Tue, 24 Nov 2015 08:41:17 +0100 Subject: x86/mce: Do not enter deferred errors into the generic pool twice We used to have a special ring buffer for deferred errors that was used to mark problem pages. We replaced that with a generic pool. Then later converted mce_log() to also use the same pool. As a result, we end up adding all deferred errors to the pool twice. Rearrange this code. Make sure to set the m.severity and m.usable_addr fields for deferred errors. Then if flags and mca_cfg.dont_log_ce mean we call mce_log() we are done, because that will add this entry to the generic pool. If we skipped mce_log(), then we still want to take action for the deferred error, so add to the pool. Change the name of the boolean "error_logged" to "error_seen", we should set it whether of not we logged an error because the return value from machine_check_poll() is used to decide whether storms have subsided or not. Reported-by: Gong Chen Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-edac Link: http://lkml.kernel.org/r/1448350880-5573-2-git-send-email-bp@alien8.de Signed-off-by: Ingo Molnar diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index c5b0d56..6531cb4 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -567,7 +567,7 @@ DEFINE_PER_CPU(unsigned, mce_poll_count); */ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) { - bool error_logged = false; + bool error_seen = false; struct mce m; int severity; int i; @@ -601,6 +601,8 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) (m.status & (mca_cfg.ser ? MCI_STATUS_S : MCI_STATUS_UC))) continue; + error_seen = true; + mce_read_aux(&m, i); if (!(flags & MCP_TIMESTAMP)) @@ -608,17 +610,10 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) severity = mce_severity(&m, mca_cfg.tolerant, NULL, false); - /* - * In the cases where we don't have a valid address after all, - * do not add it into the ring buffer. - */ if (severity == MCE_DEFERRED_SEVERITY && memory_error(&m)) { if (m.status & MCI_STATUS_ADDRV) { m.severity = severity; m.usable_addr = mce_usable_address(&m); - - if (!mce_gen_pool_add(&m)) - mce_schedule_work(); } } @@ -626,9 +621,16 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) * Don't get the IP here because it's unlikely to * have anything to do with the actual error location. */ - if (!(flags & MCP_DONTLOG) && !mca_cfg.dont_log_ce) { - error_logged = true; + if (!(flags & MCP_DONTLOG) && !mca_cfg.dont_log_ce) mce_log(&m); + else if (m.usable_addr) { + /* + * Although we skipped logging this, we still want + * to take action. Add to the pool so the registered + * notifiers will see it. + */ + if (!mce_gen_pool_add(&m)) + mce_schedule_work(); } /* @@ -644,7 +646,7 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) sync_core(); - return error_logged; + return error_seen; } EXPORT_SYMBOL_GPL(machine_check_poll); -- cgit v0.10.2 From c0ec382e1928402031e754ad0391ecbdabb18c43 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Tue, 24 Nov 2015 08:41:18 +0100 Subject: x86/RAS: Remove mce.usable_addr It is useless and we can use the function instead. Besides, mcelog(8) hasn't managed to make use of it yet. So kill it. Signed-off-by: Borislav Petkov Acked-by: Tony Luck Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1448350880-5573-3-git-send-email-bp@alien8.de Signed-off-by: Ingo Molnar diff --git a/arch/x86/include/uapi/asm/mce.h b/arch/x86/include/uapi/asm/mce.h index 03429da..2184943 100644 --- a/arch/x86/include/uapi/asm/mce.h +++ b/arch/x86/include/uapi/asm/mce.h @@ -16,7 +16,7 @@ struct mce { __u8 cpuvendor; /* cpu vendor as encoded in system.h */ __u8 inject_flags; /* software inject flags */ __u8 severity; - __u8 usable_addr; + __u8 pad; __u32 cpuid; /* CPUID 1 EAX */ __u8 cs; /* code segment */ __u8 bank; /* machine check bank */ diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 6531cb4..fb8b1db 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -484,7 +484,7 @@ static int srao_decode_notifier(struct notifier_block *nb, unsigned long val, if (!mce) return NOTIFY_DONE; - if (mce->usable_addr && (mce->severity == MCE_AO_SEVERITY)) { + if (mce_usable_address(mce) && (mce->severity == MCE_AO_SEVERITY)) { pfn = mce->addr >> PAGE_SHIFT; memory_failure(pfn, MCE_VECTOR, 0); } @@ -610,12 +610,9 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) severity = mce_severity(&m, mca_cfg.tolerant, NULL, false); - if (severity == MCE_DEFERRED_SEVERITY && memory_error(&m)) { - if (m.status & MCI_STATUS_ADDRV) { + if (severity == MCE_DEFERRED_SEVERITY && memory_error(&m)) + if (m.status & MCI_STATUS_ADDRV) m.severity = severity; - m.usable_addr = mce_usable_address(&m); - } - } /* * Don't get the IP here because it's unlikely to @@ -623,7 +620,7 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) */ if (!(flags & MCP_DONTLOG) && !mca_cfg.dont_log_ce) mce_log(&m); - else if (m.usable_addr) { + else if (mce_usable_address(&m)) { /* * Although we skipped logging this, we still want * to take action. Add to the pool so the registered @@ -1091,7 +1088,6 @@ void do_machine_check(struct pt_regs *regs, long error_code) /* assuming valid severity level != 0 */ m.severity = severity; - m.usable_addr = mce_usable_address(&m); mce_log(&m); -- cgit v0.10.2 From db548a28fcee0f38cf4c7c726becf24c8afacf02 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Tue, 24 Nov 2015 08:41:19 +0100 Subject: x86/mce: Add the missing memory error check on AMD We simply need to look at the extended error code when detecting whether the error is of type memory. Signed-off-by: Borislav Petkov Acked-by: Tony Luck Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1448350880-5573-4-git-send-email-bp@alien8.de Signed-off-by: Ingo Molnar diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index fb8b1db..e00e85a 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -522,10 +522,10 @@ static bool memory_error(struct mce *m) struct cpuinfo_x86 *c = &boot_cpu_data; if (c->x86_vendor == X86_VENDOR_AMD) { - /* - * coming soon - */ - return false; + /* ErrCodeExt[20:16] */ + u8 xec = (m->status >> 16) & 0x1f; + + return (xec == 0x0 || xec == 0x8); } else if (c->x86_vendor == X86_VENDOR_INTEL) { /* * Intel SDM Volume 3B - 15.9.2 Compound Error Codes -- cgit v0.10.2 From feab21f8356bde572663e29c9d9e48c964292e05 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Tue, 24 Nov 2015 08:41:20 +0100 Subject: x86/mce: Make usable address checks Intel-only The MCi_MISC bitfield definitions mce_usable_address() checks are Intel-only. Make them so. While at it, move mce_usable_address() up, before all its callers and get rid of the forward declaration. Signed-off-by: Borislav Petkov Acked-by: Tony Luck Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1448350880-5573-5-git-send-email-bp@alien8.de Signed-off-by: Ingo Molnar diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index e00e85a..3865e95 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -114,7 +114,6 @@ static struct work_struct mce_work; static struct irq_work mce_irq_work; static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs); -static int mce_usable_address(struct mce *m); /* * CPU/chipset specific EDAC code can register a notifier call here to print @@ -475,6 +474,28 @@ static void mce_report_event(struct pt_regs *regs) irq_work_queue(&mce_irq_work); } +/* + * Check if the address reported by the CPU is in a format we can parse. + * It would be possible to add code for most other cases, but all would + * be somewhat complicated (e.g. segment offset would require an instruction + * parser). So only support physical addresses up to page granuality for now. + */ +static int mce_usable_address(struct mce *m) +{ + if (!(m->status & MCI_STATUS_MISCV) || !(m->status & MCI_STATUS_ADDRV)) + return 0; + + /* Checks after this one are Intel-specific: */ + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + return 1; + + if (MCI_MISC_ADDR_LSB(m->misc) > PAGE_SHIFT) + return 0; + if (MCI_MISC_ADDR_MODE(m->misc) != MCI_MISC_ADDR_PHYS) + return 0; + return 1; +} + static int srao_decode_notifier(struct notifier_block *nb, unsigned long val, void *data) { @@ -930,23 +951,6 @@ reset: return ret; } -/* - * Check if the address reported by the CPU is in a format we can parse. - * It would be possible to add code for most other cases, but all would - * be somewhat complicated (e.g. segment offset would require an instruction - * parser). So only support physical addresses up to page granuality for now. - */ -static int mce_usable_address(struct mce *m) -{ - if (!(m->status & MCI_STATUS_MISCV) || !(m->status & MCI_STATUS_ADDRV)) - return 0; - if (MCI_MISC_ADDR_LSB(m->misc) > PAGE_SHIFT) - return 0; - if (MCI_MISC_ADDR_MODE(m->misc) != MCI_MISC_ADDR_PHYS) - return 0; - return 1; -} - static void mce_clear_state(unsigned long *toclear) { int i; -- cgit v0.10.2