diff options
| -rw-r--r-- | Documentation/acpi/apei/einj.txt | 196 | ||||
| -rw-r--r-- | arch/x86/include/asm/mce.h | 16 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mcheck/mce-internal.h | 11 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mcheck/mce-severity.c | 66 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mcheck/mce.c | 154 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mcheck/mce_amd.c | 11 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mcheck/mce_intel.c | 63 |
7 files changed, 336 insertions, 181 deletions
diff --git a/Documentation/acpi/apei/einj.txt b/Documentation/acpi/apei/einj.txt index f51861b..e550c8b 100644 --- a/Documentation/acpi/apei/einj.txt +++ b/Documentation/acpi/apei/einj.txt @@ -1,129 +1,177 @@ APEI Error INJection ~~~~~~~~~~~~~~~~~~~~ -EINJ provides a hardware error injection mechanism -It is very useful for debugging and testing of other APEI and RAS features. +EINJ provides a hardware error injection mechanism. It is very useful +for debugging and testing APEI and RAS features in general. -To use EINJ, make sure the following are enabled in your kernel +You need to check whether your BIOS supports EINJ first. For that, look +for early boot messages similar to this one: + +ACPI: EINJ 0x000000007370A000 000150 (v01 INTEL 00000001 INTL 00000001) + +which shows that the BIOS is exposing an EINJ table - it is the +mechanism through which the injection is done. + +Alternatively, look in /sys/firmware/acpi/tables for an "EINJ" file, +which is a different representation of the same thing. + +It doesn't necessarily mean that EINJ is not supported if those above +don't exist: before you give up, go into BIOS setup to see if the BIOS +has an option to enable error injection. Look for something called WHEA +or similar. Often, you need to enable an ACPI5 support option prior, in +order to see the APEI,EINJ,... functionality supported and exposed by +the BIOS menu. + +To use EINJ, make sure the following are options enabled in your kernel configuration: CONFIG_DEBUG_FS CONFIG_ACPI_APEI CONFIG_ACPI_APEI_EINJ -The user interface of EINJ is debug file system, under the -directory apei/einj. The following files are provided. +The EINJ user interface is in <debugfs mount point>/apei/einj. + +The following files belong to it: - available_error_type - Reading this file returns the error injection capability of the - platform, that is, which error types are supported. The error type - definition is as follow, the left field is the error type value, the - right field is error description. - - 0x00000001 Processor Correctable - 0x00000002 Processor Uncorrectable non-fatal - 0x00000004 Processor Uncorrectable fatal - 0x00000008 Memory Correctable - 0x00000010 Memory Uncorrectable non-fatal - 0x00000020 Memory Uncorrectable fatal - 0x00000040 PCI Express Correctable - 0x00000080 PCI Express Uncorrectable fatal - 0x00000100 PCI Express Uncorrectable non-fatal - 0x00000200 Platform Correctable - 0x00000400 Platform Uncorrectable non-fatal - 0x00000800 Platform Uncorrectable fatal - - The format of file contents are as above, except there are only the - available error type lines. + + This file shows which error types are supported: + + Error Type Value Error Description + ================ ================= + 0x00000001 Processor Correctable + 0x00000002 Processor Uncorrectable non-fatal + 0x00000004 Processor Uncorrectable fatal + 0x00000008 Memory Correctable + 0x00000010 Memory Uncorrectable non-fatal + 0x00000020 Memory Uncorrectable fatal + 0x00000040 PCI Express Correctable + 0x00000080 PCI Express Uncorrectable fatal + 0x00000100 PCI Express Uncorrectable non-fatal + 0x00000200 Platform Correctable + 0x00000400 Platform Uncorrectable non-fatal + 0x00000800 Platform Uncorrectable fatal + + The format of the file contents are as above, except present are only + the available error types. - error_type - This file is used to set the error type value. The error type value - is defined in "available_error_type" description. + + Set the value of the error type being injected. Possible error types + are defined in the file available_error_type above. - error_inject - Write any integer to this file to trigger the error - injection. Before this, please specify all necessary error - parameters. + + Write any integer to this file to trigger the error injection. Make + sure you have specified all necessary error parameters, i.e. this + write should be the last step when injecting errors. - flags - Present for kernel version 3.13 and above. Used to specify which - of param{1..4} are valid and should be used by BIOS during injection. - Value is a bitmask as specified in ACPI5.0 spec for the + + Present for kernel versions 3.13 and above. Used to specify which + of param{1..4} are valid and should be used by the firmware during + injection. Value is a bitmask as specified in ACPI5.0 spec for the SET_ERROR_TYPE_WITH_ADDRESS data structure: - Bit 0 - Processor APIC field valid (see param3 below) - Bit 1 - Memory address and mask valid (param1 and param2) - Bit 2 - PCIe (seg,bus,dev,fn) valid (param4 below) - If set to zero, legacy behaviour is used where the type of injection - specifies just one bit set, and param1 is multiplexed. + + Bit 0 - Processor APIC field valid (see param3 below). + Bit 1 - Memory address and mask valid (param1 and param2). + Bit 2 - PCIe (seg,bus,dev,fn) valid (see param4 below). + + If set to zero, legacy behavior is mimicked where the type of + injection specifies just one bit set, and param1 is multiplexed. - param1 - This file is used to set the first error parameter value. Effect of - parameter depends on error_type specified. For example, if error - type is memory related type, the param1 should be a valid physical - memory address. [Unless "flag" is set - see above] + + This file is used to set the first error parameter value. Its effect + depends on the error type specified in error_type. For example, if + error type is memory related type, the param1 should be a valid + physical memory address. [Unless "flag" is set - see above] - param2 - This file is used to set the second error parameter value. Effect of - parameter depends on error_type specified. For example, if error - type is memory related type, the param2 should be a physical memory - address mask. Linux requires page or narrower granularity, say, - 0xfffffffffffff000. + + Same use as param1 above. For example, if error type is of memory + related type, then param2 should be a physical memory address mask. + Linux requires page or narrower granularity, say, 0xfffffffffffff000. - param3 - Used when the 0x1 bit is set in "flag" to specify the APIC id + + Used when the 0x1 bit is set in "flags" to specify the APIC id - param4 - Used when the 0x4 bit is set in "flag" to specify target PCIe device + Used when the 0x4 bit is set in "flags" to specify target PCIe device - notrigger - The EINJ mechanism is a two step process. First inject the error, then - perform some actions to trigger it. Setting "notrigger" to 1 skips the - trigger phase, which *may* allow the user to cause the error in some other - context by a simple access to the cpu, memory location, or device that is - the target of the error injection. Whether this actually works depends - on what operations the BIOS actually includes in the trigger phase. - -BIOS versions based in the ACPI 4.0 specification have limited options -to control where the errors are injected. Your BIOS may support an -extension (enabled with the param_extension=1 module parameter, or -boot command line einj.param_extension=1). This allows the address -and mask for memory injections to be specified by the param1 and -param2 files in apei/einj. - -BIOS versions using the ACPI 5.0 specification have more control over -the target of the injection. For processor related errors (type 0x1, -0x2 and 0x4) the APICID of the target should be provided using the -param1 file in apei/einj. For memory errors (type 0x8, 0x10 and 0x20) -the address is set using param1 with a mask in param2 (0x0 is equivalent -to all ones). For PCI express errors (type 0x40, 0x80 and 0x100) the -segment, bus, device and function are specified using param1: + + The error injection mechanism is a two-step process. First inject the + error, then perform some actions to trigger it. Setting "notrigger" + to 1 skips the trigger phase, which *may* allow the user to cause the + error in some other context by a simple access to the CPU, memory + location, or device that is the target of the error injection. Whether + this actually works depends on what operations the BIOS actually + includes in the trigger phase. + +BIOS versions based on the ACPI 4.0 specification have limited options +in controlling where the errors are injected. Your BIOS may support an +extension (enabled with the param_extension=1 module parameter, or boot +command line einj.param_extension=1). This allows the address and mask +for memory injections to be specified by the param1 and param2 files in +apei/einj. + +BIOS versions based on the ACPI 5.0 specification have more control over +the target of the injection. For processor-related errors (type 0x1, 0x2 +and 0x4), you can set flags to 0x3 (param3 for bit 0, and param1 and +param2 for bit 1) so that you have more information added to the error +signature being injected. The actual data passed is this: + + memory_address = param1; + memory_address_range = param2; + apicid = param3; + pcie_sbdf = param4; + +For memory errors (type 0x8, 0x10 and 0x20) the address is set using +param1 with a mask in param2 (0x0 is equivalent to all ones). For PCI +express errors (type 0x40, 0x80 and 0x100) the segment, bus, device and +function are specified using param1: 31 24 23 16 15 11 10 8 7 0 +-------------------------------------------------+ | segment | bus | device | function | reserved | +-------------------------------------------------+ -An ACPI 5.0 BIOS may also allow vendor specific errors to be injected. +Anyway, you get the idea, if there's doubt just take a look at the code +in drivers/acpi/apei/einj.c. + +An ACPI 5.0 BIOS may also allow vendor-specific errors to be injected. In this case a file named vendor will contain identifying information from the BIOS that hopefully will allow an application wishing to use -the vendor specific extension to tell that they are running on a BIOS +the vendor-specific extension to tell that they are running on a BIOS that supports it. All vendor extensions have the 0x80000000 bit set in error_type. A file vendor_flags controls the interpretation of param1 and param2 (1 = PROCESSOR, 2 = MEMORY, 4 = PCI). See your BIOS vendor documentation for details (and expect changes to this API if vendors creativity in using this feature expands beyond our expectations). -Example: + +An error injection example: + # cd /sys/kernel/debug/apei/einj # cat available_error_type # See which errors can be injected 0x00000002 Processor Uncorrectable non-fatal 0x00000008 Memory Correctable 0x00000010 Memory Uncorrectable non-fatal # echo 0x12345000 > param1 # Set memory address for injection -# echo 0xfffffffffffff000 > param2 # Mask - anywhere in this page +# echo $((-1 << 12)) > param2 # Mask 0xfffffffffffff000 - anywhere in this page # echo 0x8 > error_type # Choose correctable memory error # echo 1 > error_inject # Inject now +You should see something like this in dmesg: + +[22715.830801] EDAC sbridge MC3: HANDLING MCE MEMORY ERROR +[22715.834759] EDAC sbridge MC3: CPU 0: Machine Check Event: 0 Bank 7: 8c00004000010090 +[22715.834759] EDAC sbridge MC3: TSC 0 +[22715.834759] EDAC sbridge MC3: ADDR 12345000 EDAC sbridge MC3: MISC 144780c86 +[22715.834759] EDAC sbridge MC3: PROCESSOR 0:306e7 TIME 1422553404 SOCKET 0 APIC 0 +[22716.616173] EDAC MC3: 1 CE memory read error on CPU_SrcID#0_Channel#0_DIMM#0 (channel:0 slot:0 page:0x12345 offset:0x0 grain:32 syndrome:0x0 - area:DRAM err_code:0001:0090 socket:0 channel_mask:1 rank:0) For more information about EINJ, please refer to ACPI specification version 4.0, section 17.5 and ACPI 5.0, section 18.6. diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 9b3de99..1f5a86d 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -116,6 +116,12 @@ struct mca_config { u32 rip_msr; }; +struct mce_vendor_flags { + __u64 overflow_recov : 1, /* cpuid_ebx(80000007) */ + __reserved_0 : 63; +}; +extern struct mce_vendor_flags mce_flags; + extern struct mca_config mca_cfg; extern void mce_register_decode_chain(struct notifier_block *nb); extern void mce_unregister_decode_chain(struct notifier_block *nb); @@ -128,9 +134,11 @@ extern int mce_p5_enabled; #ifdef CONFIG_X86_MCE int mcheck_init(void); void mcheck_cpu_init(struct cpuinfo_x86 *c); +void mcheck_vendor_init_severity(void); #else static inline int mcheck_init(void) { return 0; } static inline void mcheck_cpu_init(struct cpuinfo_x86 *c) {} +static inline void mcheck_vendor_init_severity(void) {} #endif #ifdef CONFIG_X86_ANCIENT_MCE @@ -183,11 +191,11 @@ typedef DECLARE_BITMAP(mce_banks_t, MAX_NR_BANKS); DECLARE_PER_CPU(mce_banks_t, mce_poll_banks); enum mcp_flags { - MCP_TIMESTAMP = (1 << 0), /* log time stamp */ - MCP_UC = (1 << 1), /* log uncorrected errors */ - MCP_DONTLOG = (1 << 2), /* only clear, don't log */ + MCP_TIMESTAMP = BIT(0), /* log time stamp */ + MCP_UC = BIT(1), /* log uncorrected errors */ + MCP_DONTLOG = BIT(2), /* only clear, don't log */ }; -void machine_check_poll(enum mcp_flags flags, mce_banks_t *b); +bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b); int mce_notify_irq(void); diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h index 10b4690..fe32074 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -14,6 +14,7 @@ enum severity_level { }; #define ATTR_LEN 16 +#define INITIAL_CHECK_INTERVAL 5 * 60 /* 5 minutes */ /* One object for each MCE bank, shared by all CPUs */ struct mce_bank { @@ -23,20 +24,20 @@ struct mce_bank { char attrname[ATTR_LEN]; /* attribute name */ }; -int mce_severity(struct mce *a, int tolerant, char **msg, bool is_excp); +extern int (*mce_severity)(struct mce *a, int tolerant, char **msg, bool is_excp); struct dentry *mce_get_debugfs_dir(void); extern struct mce_bank *mce_banks; extern mce_banks_t mce_banks_ce_disabled; #ifdef CONFIG_X86_MCE_INTEL -unsigned long mce_intel_adjust_timer(unsigned long interval); -void mce_intel_cmci_poll(void); +unsigned long cmci_intel_adjust_timer(unsigned long interval); +bool mce_intel_cmci_poll(void); void mce_intel_hcpu_update(unsigned long cpu); void cmci_disable_bank(int bank); #else -# define mce_intel_adjust_timer mce_adjust_timer_default -static inline void mce_intel_cmci_poll(void) { } +# define cmci_intel_adjust_timer mce_adjust_timer_default +static inline bool mce_intel_cmci_poll(void) { return false; } static inline void mce_intel_hcpu_update(unsigned long cpu) { } static inline void cmci_disable_bank(int bank) { } #endif diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c index 8bb4330..9c682c2 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-severity.c +++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c @@ -186,7 +186,61 @@ static int error_context(struct mce *m) return ((m->cs & 3) == 3) ? IN_USER : IN_KERNEL; } -int mce_severity(struct mce *m, int tolerant, char **msg, bool is_excp) +/* + * See AMD Error Scope Hierarchy table in a newer BKDG. For example + * 49125_15h_Models_30h-3Fh_BKDG.pdf, section "RAS Features" + */ +static int mce_severity_amd(struct mce *m, int tolerant, char **msg, bool is_excp) +{ + enum context ctx = error_context(m); + + /* Processor Context Corrupt, no need to fumble too much, die! */ + if (m->status & MCI_STATUS_PCC) + return MCE_PANIC_SEVERITY; + + if (m->status & MCI_STATUS_UC) { + + /* + * On older systems where overflow_recov flag is not present, we + * should simply panic if an error overflow occurs. If + * overflow_recov flag is present and set, then software can try + * to at least kill process to prolong system operation. + */ + if (mce_flags.overflow_recov) { + /* software can try to contain */ + if (!(m->mcgstatus & MCG_STATUS_RIPV) && (ctx == IN_KERNEL)) + return MCE_PANIC_SEVERITY; + + /* kill current process */ + return MCE_AR_SEVERITY; + } else { + /* at least one error was not logged */ + if (m->status & MCI_STATUS_OVER) + return MCE_PANIC_SEVERITY; + } + + /* + * For any other case, return MCE_UC_SEVERITY so that we log the + * error and exit #MC handler. + */ + return MCE_UC_SEVERITY; + } + + /* + * deferred error: poll handler catches these and adds to mce_ring so + * memory-failure can take recovery actions. + */ + if (m->status & MCI_STATUS_DEFERRED) + return MCE_DEFERRED_SEVERITY; + + /* + * corrected error: poll handler catches these and passes responsibility + * of decoding the error to EDAC + */ + return MCE_KEEP_SEVERITY; +} + +static int mce_severity_intel(struct mce *m, int tolerant, char **msg, bool is_excp) { enum exception excp = (is_excp ? EXCP_CONTEXT : NO_EXCP); enum context ctx = error_context(m); @@ -216,6 +270,16 @@ int mce_severity(struct mce *m, int tolerant, char **msg, bool is_excp) } } +/* Default to mce_severity_intel */ +int (*mce_severity)(struct mce *m, int tolerant, char **msg, bool is_excp) = + mce_severity_intel; + +void __init mcheck_vendor_init_severity(void) +{ + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) + mce_severity = mce_severity_amd; +} + #ifdef CONFIG_DEBUG_FS static void *s_start(struct seq_file *f, loff_t *pos) { diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 3c036cb..e535533 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -60,11 +60,12 @@ static DEFINE_MUTEX(mce_chrdev_read_mutex); #define CREATE_TRACE_POINTS #include <trace/events/mce.h> -#define SPINUNIT 100 /* 100ns */ +#define SPINUNIT 100 /* 100ns */ DEFINE_PER_CPU(unsigned, mce_exception_count); struct mce_bank *mce_banks __read_mostly; +struct mce_vendor_flags mce_flags __read_mostly; struct mca_config mca_cfg __read_mostly = { .bootlog = -1, @@ -89,9 +90,6 @@ static DECLARE_WAIT_QUEUE_HEAD(mce_chrdev_wait); static DEFINE_PER_CPU(struct mce, mces_seen); static int cpu_missing; -/* CMCI storm detection filter */ -static DEFINE_PER_CPU(unsigned long, mce_polled_error); - /* * MCA banks polled by the period polling timer for corrected events. * With Intel CMCI, this only has MCA banks which do not support CMCI (if any). @@ -622,8 +620,9 @@ DEFINE_PER_CPU(unsigned, mce_poll_count); * is already totally * confused. In this case it's likely it will * not fully execute the machine check handler either. */ -void machine_check_poll(enum mcp_flags flags, mce_banks_t *b) +bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) { + bool error_logged = false; struct mce m; int severity; int i; @@ -646,7 +645,7 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b) if (!(m.status & MCI_STATUS_VAL)) continue; - this_cpu_write(mce_polled_error, 1); + /* * Uncorrected or signalled events are handled by the exception * handler when it is enabled, so don't process those here. @@ -679,8 +678,10 @@ void 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) + if (!(flags & MCP_DONTLOG) && !mca_cfg.dont_log_ce) { + error_logged = true; mce_log(&m); + } /* * Clear state for this bank. @@ -694,6 +695,8 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b) */ sync_core(); + + return error_logged; } EXPORT_SYMBOL_GPL(machine_check_poll); @@ -813,7 +816,7 @@ static void mce_reign(void) * other CPUs. */ if (m && global_worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3) - mce_panic("Fatal Machine check", m, msg); + mce_panic("Fatal machine check", m, msg); /* * For UC somewhere we let the CPU who detects it handle it. @@ -826,7 +829,7 @@ static void mce_reign(void) * source or one CPU is hung. Panic. */ if (global_worst <= MCE_KEEP_SEVERITY && mca_cfg.tolerant < 3) - mce_panic("Machine check from unknown source", NULL, NULL); + mce_panic("Fatal machine check from unknown source", NULL, NULL); /* * Now clear all the mces_seen so that they don't reappear on @@ -1258,7 +1261,7 @@ void mce_log_therm_throt_event(__u64 status) * poller finds an MCE, poll 2x faster. When the poller finds no more * errors, poll 2x slower (up to check_interval seconds). */ -static unsigned long check_interval = 5 * 60; /* 5 minutes */ +static unsigned long check_interval = INITIAL_CHECK_INTERVAL; static DEFINE_PER_CPU(unsigned long, mce_next_interval); /* in jiffies */ static DEFINE_PER_CPU(struct timer_list, mce_timer); @@ -1268,49 +1271,57 @@ static unsigned long mce_adjust_timer_default(unsigned long interval) return interval; } -static unsigned long (*mce_adjust_timer)(unsigned long interval) = - mce_adjust_timer_default; +static unsigned long (*mce_adjust_timer)(unsigned long interval) = mce_adjust_timer_default; -static int cmc_error_seen(void) +static void __restart_timer(struct timer_list *t, unsigned long interval) { - unsigned long *v = this_cpu_ptr(&mce_polled_error); + unsigned long when = jiffies + interval; + unsigned long flags; + + local_irq_save(flags); - return test_and_clear_bit(0, v); + if (timer_pending(t)) { + if (time_before(when, t->expires)) + mod_timer_pinned(t, when); + } else { + t->expires = round_jiffies(when); + add_timer_on(t, smp_processor_id()); + } + + local_irq_restore(flags); } static void mce_timer_fn(unsigned long data) { struct timer_list *t = this_cpu_ptr(&mce_timer); + int cpu = smp_processor_id(); unsigned long iv; - int notify; - WARN_ON(smp_processor_id() != data); + WARN_ON(cpu != data); + + iv = __this_cpu_read(mce_next_interval); if (mce_available(this_cpu_ptr(&cpu_info))) { - machine_check_poll(MCP_TIMESTAMP, - this_cpu_ptr(&mce_poll_banks)); - mce_intel_cmci_poll(); + machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_poll_banks)); + + if (mce_intel_cmci_poll()) { + iv = mce_adjust_timer(iv); + goto done; + } } /* - * Alert userspace if needed. If we logged an MCE, reduce the - * polling interval, otherwise increase the polling interval. + * Alert userspace if needed. If we logged an MCE, reduce the polling + * interval, otherwise increase the polling interval. */ - iv = __this_cpu_read(mce_next_interval); - notify = mce_notify_irq(); - notify |= cmc_error_seen(); - if (notify) { + if (mce_notify_irq()) iv = max(iv / 2, (unsigned long) HZ/100); - } else { + else iv = min(iv * 2, round_jiffies_relative(check_interval * HZ)); - iv = mce_adjust_timer(iv); - } + +done: __this_cpu_write(mce_next_interval, iv); - /* Might have become 0 after CMCI storm subsided */ - if (iv) { - t->expires = jiffies + iv; - add_timer_on(t, smp_processor_id()); - } + __restart_timer(t, iv); } /* @@ -1319,16 +1330,10 @@ static void mce_timer_fn(unsigned long data) void mce_timer_kick(unsigned long interval) { struct timer_list *t = this_cpu_ptr(&mce_timer); - unsigned long when = jiffies + interval; unsigned long iv = __this_cpu_read(mce_next_interval); - if (timer_pending(t)) { - if (time_before(when, t->expires)) - mod_timer_pinned(t, when); - } else { - t->expires = round_jiffies(when); - add_timer_on(t, smp_processor_id()); - } + __restart_timer(t, interval); + if (interval < iv) __this_cpu_write(mce_next_interval, interval); } @@ -1525,45 +1530,46 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) * Various K7s with broken bank 0 around. Always disable * by default. */ - if (c->x86 == 6 && cfg->banks > 0) + if (c->x86 == 6 && cfg->banks > 0) mce_banks[0].ctl = 0; - /* - * Turn off MC4_MISC thresholding banks on those models since - * they're not supported there. - */ - if (c->x86 == 0x15 && - (c->x86_model >= 0x10 && c->x86_model <= 0x1f)) { - int i; - u64 val, hwcr; - bool need_toggle; - u32 msrs[] = { + /* + * overflow_recov is supported for F15h Models 00h-0fh + * even though we don't have a CPUID bit for it. + */ + if (c->x86 == 0x15 && c->x86_model <= 0xf) + mce_flags.overflow_recov = 1; + + /* + * Turn off MC4_MISC thresholding banks on those models since + * they're not supported there. + */ + if (c->x86 == 0x15 && + (c->x86_model >= 0x10 && c->x86_model <= 0x1f)) { + int i; + u64 hwcr; + bool need_toggle; + u32 msrs[] = { 0x00000413, /* MC4_MISC0 */ 0xc0000408, /* MC4_MISC1 */ - }; + }; - rdmsrl(MSR_K7_HWCR, hwcr); + rdmsrl(MSR_K7_HWCR, hwcr); - /* McStatusWrEn has to be set */ - need_toggle = !(hwcr & BIT(18)); + /* McStatusWrEn has to be set */ + need_toggle = !(hwcr & BIT(18)); - if (need_toggle) - wrmsrl(MSR_K7_HWCR, hwcr | BIT(18)); + if (need_toggle) + wrmsrl(MSR_K7_HWCR, hwcr | BIT(18)); - for (i = 0; i < ARRAY_SIZE(msrs); i++) { - rdmsrl(msrs[i], val); + /* Clear CntP bit safely */ + for (i = 0; i < ARRAY_SIZE(msrs); i++) + msr_clear_bit(msrs[i], 62); - /* CntP bit set? */ - if (val & BIT_64(62)) { - val &= ~BIT_64(62); - wrmsrl(msrs[i], val); - } - } - - /* restore old settings */ - if (need_toggle) - wrmsrl(MSR_K7_HWCR, hwcr); - } + /* restore old settings */ + if (need_toggle) + wrmsrl(MSR_K7_HWCR, hwcr); + } } if (c->x86_vendor == X86_VENDOR_INTEL) { @@ -1629,10 +1635,11 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) switch (c->x86_vendor) { case X86_VENDOR_INTEL: mce_intel_feature_init(c); - mce_adjust_timer = mce_intel_adjust_timer; + mce_adjust_timer = cmci_intel_adjust_timer; break; case X86_VENDOR_AMD: mce_amd_feature_init(c); + mce_flags.overflow_recov = cpuid_ebx(0x80000007) & 0x1; break; default: break; @@ -2017,6 +2024,7 @@ __setup("mce", mcheck_enable); int __init mcheck_init(void) { mcheck_intel_therm_init(); + mcheck_vendor_init_severity(); return 0; } diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index f1c3769..55ad9b3 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -79,7 +79,7 @@ static inline bool is_shared_bank(int bank) return (bank == 4); } -static const char * const bank4_names(struct threshold_block *b) +static const char *bank4_names(const struct threshold_block *b) { switch (b->address) { /* MSR4_MISC0 */ @@ -250,6 +250,7 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) if (!b.interrupt_capable) goto init; + b.interrupt_enable = 1; new = (high & MASK_LVTOFF_HI) >> 20; offset = setup_APIC_mce(offset, new); @@ -322,6 +323,8 @@ static void amd_threshold_interrupt(void) log: mce_setup(&m); rdmsrl(MSR_IA32_MCx_STATUS(bank), m.status); + if (!(m.status & MCI_STATUS_VAL)) + return; m.misc = ((u64)high << 32) | low; m.bank = bank; mce_log(&m); @@ -497,10 +500,12 @@ static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank, b->interrupt_capable = lvt_interrupt_supported(bank, high); b->threshold_limit = THRESHOLD_MAX; - if (b->interrupt_capable) + if (b->interrupt_capable) { threshold_ktype.default_attrs[2] = &interrupt_enable.attr; - else + b->interrupt_enable = 1; + } else { threshold_ktype.default_attrs[2] = NULL; + } INIT_LIST_HEAD(&b->miscj); diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c index b3c97ba..b4a41cf 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c @@ -39,6 +39,15 @@ static DEFINE_PER_CPU(mce_banks_t, mce_banks_owned); /* + * CMCI storm detection backoff counter + * + * During storm, we reset this counter to INITIAL_CHECK_INTERVAL in case we've + * encountered an error. If not, we decrement it by one. We signal the end of + * the CMCI storm when it reaches 0. + */ +static DEFINE_PER_CPU(int, cmci_backoff_cnt); + +/* * cmci_discover_lock protects against parallel discovery attempts * which could race against each other. */ @@ -46,7 +55,7 @@ static DEFINE_RAW_SPINLOCK(cmci_discover_lock); #define CMCI_THRESHOLD 1 #define CMCI_POLL_INTERVAL (30 * HZ) -#define CMCI_STORM_INTERVAL (1 * HZ) +#define CMCI_STORM_INTERVAL (HZ) #define CMCI_STORM_THRESHOLD 15 static DEFINE_PER_CPU(unsigned long, cmci_time_stamp); @@ -82,11 +91,21 @@ static int cmci_supported(int *banks) return !!(cap & MCG_CMCI_P); } -void mce_intel_cmci_poll(void) +bool mce_intel_cmci_poll(void) { if (__this_cpu_read(cmci_storm_state) == CMCI_STORM_NONE) - return; - machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned)); + return false; + + /* + * Reset the counter if we've logged an error in the last poll + * during the storm. + */ + if (machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned))) + this_cpu_write(cmci_backoff_cnt, INITIAL_CHECK_INTERVAL); + else + this_cpu_dec(cmci_backoff_cnt); + + return true; } void mce_intel_hcpu_update(unsigned long cpu) @@ -97,31 +116,32 @@ void mce_intel_hcpu_update(unsigned long cpu) per_cpu(cmci_storm_state, cpu) = CMCI_STORM_NONE; } -unsigned long mce_intel_adjust_timer(unsigned long interval) +unsigned long cmci_intel_adjust_timer(unsigned long interval) { - int r; - - if (interval < CMCI_POLL_INTERVAL) - return interval; + if ((this_cpu_read(cmci_backoff_cnt) > 0) && + (__this_cpu_read(cmci_storm_state) == CMCI_STORM_ACTIVE)) { + mce_notify_irq(); + return CMCI_STORM_INTERVAL; + } switch (__this_cpu_read(cmci_storm_state)) { case CMCI_STORM_ACTIVE: + /* * We switch back to interrupt mode once the poll timer has - * silenced itself. That means no events recorded and the - * timer interval is back to our poll interval. + * silenced itself. That means no events recorded and the timer + * interval is back to our poll interval. */ __this_cpu_write(cmci_storm_state, CMCI_STORM_SUBSIDED); - r = atomic_sub_return(1, &cmci_storm_on_cpus); - if (r == 0) + if (!atomic_sub_return(1, &cmci_storm_on_cpus)) pr_notice("CMCI storm subsided: switching to interrupt mode\n"); + /* FALLTHROUGH */ case CMCI_STORM_SUBSIDED: /* - * We wait for all cpus to go back to SUBSIDED - * state. When that happens we switch back to - * interrupt mode. + * We wait for all CPUs to go back to SUBSIDED state. When that + * happens we switch back to interrupt mode. */ if (!atomic_read(&cmci_storm_on_cpus)) { __this_cpu_write(cmci_storm_state, CMCI_STORM_NONE); @@ -130,10 +150,8 @@ unsigned long mce_intel_adjust_timer(unsigned long interval) } return CMCI_POLL_INTERVAL; default: - /* - * We have shiny weather. Let the poll do whatever it - * thinks. - */ + + /* We have shiny weather. Let the poll do whatever it thinks. */ return interval; } } @@ -178,7 +196,8 @@ static bool cmci_storm_detect(void) cmci_storm_disable_banks(); __this_cpu_write(cmci_storm_state, CMCI_STORM_ACTIVE); r = atomic_add_return(1, &cmci_storm_on_cpus); - mce_timer_kick(CMCI_POLL_INTERVAL); + mce_timer_kick(CMCI_STORM_INTERVAL); + this_cpu_write(cmci_backoff_cnt, INITIAL_CHECK_INTERVAL); if (r == 1) pr_notice("CMCI storm detected: switching to poll mode\n"); @@ -195,6 +214,7 @@ static void intel_threshold_interrupt(void) { if (cmci_storm_detect()) return; + machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned)); mce_notify_irq(); } @@ -286,6 +306,7 @@ void cmci_recheck(void) if (!mce_available(raw_cpu_ptr(&cpu_info)) || !cmci_supported(&banks)) return; + local_irq_save(flags); machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned)); local_irq_restore(flags); |