diff options
author | Ingo Molnar <mingo@elte.hu> | 2009-10-01 16:14:32 +0200 |
---|---|---|
committer | Ingo Molnar <mingo@elte.hu> | 2009-10-02 15:42:18 +0200 |
commit | f436f8bb73138bc74eb1c6527723e00988ad8a8a (patch) | |
tree | 834bd21c6d8daff79328582e429146417c262270 /arch/x86/kernel/cpu/mcheck/mce.c | |
parent | 24e35800cdc4350fc34e2bed37b608a9e13ab3b6 (diff) |
x86: EDAC: MCE: Fix MCE decoding callback logic
Make decoding of MCEs happen only on AMD hardware by registering a
non-default callback only on CPU families which support it.
While looking at the interaction of decode_mce() with the other MCE
code i also noticed a few other things and made the following
cleanups/fixes:
- Fixed the mce_decode() weak alias - a weak alias is really not
good here, it should be a proper callback. A weak alias will be
overriden if a piece of code is built into the kernel - not
good, obviously.
- The patch initializes the callback on AMD family 10h and 11h.
- Added the more correct fallback printk of:
No support for human readable MCE decoding on this CPU type.
Transcribe the message and run it through 'mcelog --ascii' to decode.
On CPUs that dont have a decoder.
- Made the surrounding code more readable.
Note that the callback allows us to have a default fallback -
without having to check the CPU versions during the printout
itself. When an EDAC module registers itself, it can install the
decode-print function.
(there's no unregister needed as this is core code.)
version -v2 by Borislav Petkov:
- add K8 to the set of supported CPUs
- always build in edac_mce_amd since we use an early_initcall now
- fix checkpatch warnings
Signed-off-by: Borislav Petkov <borislav.petkov@amd.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andi Kleen <andi@firstfloor.org>
LKML-Reference: <20091001141432.GA11410@aftab>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Diffstat (limited to 'arch/x86/kernel/cpu/mcheck/mce.c')
-rw-r--r-- | arch/x86/kernel/cpu/mcheck/mce.c | 58 |
1 files changed, 36 insertions, 22 deletions
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 183c3457d2f..b1598a9436d 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -85,6 +85,18 @@ static DECLARE_WAIT_QUEUE_HEAD(mce_wait); static DEFINE_PER_CPU(struct mce, mces_seen); static int cpu_missing; +static void default_decode_mce(struct mce *m) +{ + pr_emerg("No human readable MCE decoding support on this CPU type.\n"); + pr_emerg("Run the message through 'mcelog --ascii' to decode.\n"); +} + +/* + * CPU/chipset specific EDAC code can register a callback here to print + * MCE errors in a human-readable form: + */ +void (*x86_mce_decode_callback)(struct mce *m) = default_decode_mce; +EXPORT_SYMBOL(x86_mce_decode_callback); /* MCA banks polled by the period polling timer for corrected events */ DEFINE_PER_CPU(mce_banks_t, mce_poll_banks) = { @@ -165,46 +177,46 @@ void mce_log(struct mce *mce) set_bit(0, &mce_need_notify); } -void __weak decode_mce(struct mce *m) -{ - return; -} - static void print_mce(struct mce *m) { - printk(KERN_EMERG - "CPU %d: Machine Check Exception: %16Lx Bank %d: %016Lx\n", + pr_emerg("CPU %d: Machine Check Exception: %16Lx Bank %d: %016Lx\n", m->extcpu, m->mcgstatus, m->bank, m->status); + if (m->ip) { - printk(KERN_EMERG "RIP%s %02x:<%016Lx> ", - !(m->mcgstatus & MCG_STATUS_EIPV) ? " !INEXACT!" : "", - m->cs, m->ip); + pr_emerg("RIP%s %02x:<%016Lx> ", + !(m->mcgstatus & MCG_STATUS_EIPV) ? " !INEXACT!" : "", + m->cs, m->ip); + if (m->cs == __KERNEL_CS) print_symbol("{%s}", m->ip); - printk(KERN_CONT "\n"); + pr_cont("\n"); } - printk(KERN_EMERG "TSC %llx ", m->tsc); + + pr_emerg("TSC %llx ", m->tsc); if (m->addr) - printk(KERN_CONT "ADDR %llx ", m->addr); + pr_cont("ADDR %llx ", m->addr); if (m->misc) - printk(KERN_CONT "MISC %llx ", m->misc); - printk(KERN_CONT "\n"); - printk(KERN_EMERG "PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x\n", - m->cpuvendor, m->cpuid, m->time, m->socketid, - m->apicid); + pr_cont("MISC %llx ", m->misc); + + pr_cont("\n"); + pr_emerg("PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x\n", + m->cpuvendor, m->cpuid, m->time, m->socketid, m->apicid); - decode_mce(m); + /* + * Print out human-readable details about the MCE error, + * (if the CPU has an implementation for that): + */ + x86_mce_decode_callback(m); } static void print_mce_head(void) { - printk(KERN_EMERG "\nHARDWARE ERROR\n"); + pr_emerg("\nHARDWARE ERROR\n"); } static void print_mce_tail(void) { - printk(KERN_EMERG "This is not a software problem!\n" - "Run through mcelog --ascii to decode and contact your hardware vendor\n"); + pr_emerg("This is not a software problem!\n"); } #define PANIC_TIMEOUT 5 /* 5 seconds */ @@ -218,6 +230,7 @@ static atomic_t mce_fake_paniced; static void wait_for_panic(void) { long timeout = PANIC_TIMEOUT*USEC_PER_SEC; + preempt_disable(); local_irq_enable(); while (timeout-- > 0) @@ -285,6 +298,7 @@ static void mce_panic(char *msg, struct mce *final, char *exp) static int msr_to_offset(u32 msr) { unsigned bank = __get_cpu_var(injectm.bank); + if (msr == rip_msr) return offsetof(struct mce, ip); if (msr == MSR_IA32_MCx_STATUS(bank)) |