summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2012-05-26 03:14:12 +0400
committerLinus Torvalds <torvalds@linux-foundation.org>2012-05-26 03:14:12 +0400
commit786f02b719f2285e2c0350b6a04dab4a1a0871a1 (patch)
tree0836083fa3bef945a46449c2d6badd5c29d7baad
parentfa2af6e4fe0c4d2f8875d42625b25675e8584010 (diff)
parent37c3459b67dd5a396a968e819cf4a86d24ac9ace (diff)
downloadlinux-786f02b719f2285e2c0350b6a04dab4a1a0871a1.tar.xz
Merge tag 'x86-mce-merge' of git://git.kernel.org/pub/scm/linux/kernel/git/ras/ras
Pull x86/mce merge window patches from Tony Luck: "Including two that make error_context() checks less sucky" * tag 'x86-mce-merge' of git://git.kernel.org/pub/scm/linux/kernel/git/ras/ras: x86/mce: Add instruction recovery signatures to mce-severity table x86/mce: Fix check for processor context when machine check was taken. MCE: Fix vm86 handling for 32bit mce handler x86/mce Add validation check before GHES error is recorded x86/mce: Avoid reading every machine check bank register twice.
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-apei.c3
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-severity.c26
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c24
3 files changed, 41 insertions, 12 deletions
diff --git a/arch/x86/kernel/cpu/mcheck/mce-apei.c b/arch/x86/kernel/cpu/mcheck/mce-apei.c
index 507ea58688e2..cd8b166a1735 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-apei.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-apei.c
@@ -42,7 +42,8 @@ void apei_mce_report_mem_error(int corrected, struct cper_sec_mem_err *mem_err)
struct mce m;
/* Only corrected MC is reported */
- if (!corrected)
+ if (!corrected || !(mem_err->validation_bits &
+ CPER_MEM_VALID_PHYSICAL_ADDRESS))
return;
mce_setup(&m);
diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c
index 0c82091b1652..413c2ced887c 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-severity.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c
@@ -126,6 +126,16 @@ static struct severity {
SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA),
USER
),
+ MCESEV(
+ KEEP, "HT thread notices Action required: instruction fetch error",
+ SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_INSTR),
+ MCGMASK(MCG_STATUS_EIPV, 0)
+ ),
+ MCESEV(
+ AR, "Action required: instruction fetch error",
+ SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_INSTR),
+ USER
+ ),
#endif
MCESEV(
PANIC, "Action required: unknown MCACOD",
@@ -165,15 +175,19 @@ static struct severity {
};
/*
- * If the EIPV bit is set, it means the saved IP is the
- * instruction which caused the MCE.
+ * If mcgstatus indicated that ip/cs on the stack were
+ * no good, then "m->cs" will be zero and we will have
+ * to assume the worst case (IN_KERNEL) as we actually
+ * have no idea what we were executing when the machine
+ * check hit.
+ * If we do have a good "m->cs" (or a faked one in the
+ * case we were executing in VM86 mode) we can use it to
+ * distinguish an exception taken in user from from one
+ * taken in the kernel.
*/
static int error_context(struct mce *m)
{
- if (m->mcgstatus & MCG_STATUS_EIPV)
- return (m->ip && (m->cs & 3) == 3) ? IN_USER : IN_KERNEL;
- /* Unknown, assume kernel */
- return IN_KERNEL;
+ return ((m->cs & 3) == 3) ? IN_USER : IN_KERNEL;
}
int mce_severity(struct mce *m, int tolerant, char **msg)
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 2afcbd253e1d..b772dd6ad450 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -437,6 +437,14 @@ static inline void mce_gather_info(struct mce *m, struct pt_regs *regs)
if (m->mcgstatus & (MCG_STATUS_RIPV|MCG_STATUS_EIPV)) {
m->ip = regs->ip;
m->cs = regs->cs;
+
+ /*
+ * When in VM86 mode make the cs look like ring 3
+ * always. This is a lie, but it's better than passing
+ * the additional vm86 bit around everywhere.
+ */
+ if (v8086_mode(regs))
+ m->cs |= 3;
}
/* Use accurate RIP reporting if available. */
if (rip_msr)
@@ -641,16 +649,18 @@ EXPORT_SYMBOL_GPL(machine_check_poll);
* Do a quick check if any of the events requires a panic.
* This decides if we keep the events around or clear them.
*/
-static int mce_no_way_out(struct mce *m, char **msg)
+static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp)
{
- int i;
+ int i, ret = 0;
for (i = 0; i < banks; i++) {
m->status = mce_rdmsrl(MSR_IA32_MCx_STATUS(i));
+ if (m->status & MCI_STATUS_VAL)
+ __set_bit(i, validp);
if (mce_severity(m, tolerant, msg) >= MCE_PANIC_SEVERITY)
- return 1;
+ ret = 1;
}
- return 0;
+ return ret;
}
/*
@@ -1013,6 +1023,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
*/
int kill_it = 0;
DECLARE_BITMAP(toclear, MAX_NR_BANKS);
+ DECLARE_BITMAP(valid_banks, MAX_NR_BANKS);
char *msg = "Unknown";
atomic_inc(&mce_entry);
@@ -1027,7 +1038,8 @@ void do_machine_check(struct pt_regs *regs, long error_code)
final = &__get_cpu_var(mces_seen);
*final = m;
- no_way_out = mce_no_way_out(&m, &msg);
+ memset(valid_banks, 0, sizeof(valid_banks));
+ no_way_out = mce_no_way_out(&m, &msg, valid_banks);
barrier();
@@ -1047,6 +1059,8 @@ void do_machine_check(struct pt_regs *regs, long error_code)
order = mce_start(&no_way_out);
for (i = 0; i < banks; i++) {
__clear_bit(i, toclear);
+ if (!test_bit(i, valid_banks))
+ continue;
if (!mce_banks[i].ctl)
continue;