summaryrefslogtreecommitdiff
path: root/arch/x86/kernel/cpu/mcheck/mce.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel/cpu/mcheck/mce.c')
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c72
1 files changed, 60 insertions, 12 deletions
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 61a9668cebfd..d2c611699cd9 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -292,10 +292,10 @@ static void print_mce(struct mce *m)
#define PANIC_TIMEOUT 5 /* 5 seconds */
-static atomic_t mce_paniced;
+static atomic_t mce_panicked;
static int fake_panic;
-static atomic_t mce_fake_paniced;
+static atomic_t mce_fake_panicked;
/* Panic in progress. Enable interrupts and wait for final IPI */
static void wait_for_panic(void)
@@ -319,7 +319,7 @@ static void mce_panic(char *msg, struct mce *final, char *exp)
/*
* Make sure only one CPU runs in machine check panic
*/
- if (atomic_inc_return(&mce_paniced) > 1)
+ if (atomic_inc_return(&mce_panicked) > 1)
wait_for_panic();
barrier();
@@ -327,7 +327,7 @@ static void mce_panic(char *msg, struct mce *final, char *exp)
console_verbose();
} else {
/* Don't log too much for fake panic */
- if (atomic_inc_return(&mce_fake_paniced) > 1)
+ if (atomic_inc_return(&mce_fake_panicked) > 1)
return;
}
/* First print corrected ones that are still unlogged */
@@ -575,6 +575,37 @@ static void mce_read_aux(struct mce *m, int i)
}
}
+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;
+ } else if (c->x86_vendor == X86_VENDOR_INTEL) {
+ /*
+ * Intel SDM Volume 3B - 15.9.2 Compound Error Codes
+ *
+ * Bit 7 of the MCACOD field of IA32_MCi_STATUS is used for
+ * indicating a memory error. Bit 8 is used for indicating a
+ * cache hierarchy error. The combination of bit 2 and bit 3
+ * is used for indicating a `generic' cache hierarchy error
+ * But we can't just blindly check the above bits, because if
+ * bit 11 is set, then it is a bus/interconnect error - and
+ * either way the above bits just gives more detail on what
+ * bus/interconnect error happened. Note that bit 12 can be
+ * ignored, as it's the "filter" bit.
+ */
+ return (m->status & 0xef80) == BIT(7) ||
+ (m->status & 0xef00) == BIT(8) ||
+ (m->status & 0xeffc) == 0xc;
+ }
+
+ return false;
+}
+
DEFINE_PER_CPU(unsigned, mce_poll_count);
/*
@@ -595,6 +626,7 @@ DEFINE_PER_CPU(unsigned, mce_poll_count);
void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
{
struct mce m;
+ int severity;
int i;
this_cpu_inc(mce_poll_count);
@@ -630,6 +662,20 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
if (!(flags & MCP_TIMESTAMP))
m.tsc = 0;
+
+ 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) {
+ mce_ring_add(m.addr >> PAGE_SHIFT);
+ mce_schedule_work();
+ }
+ }
+
/*
* Don't get the IP here because it's unlikely to
* have anything to do with the actual error location.
@@ -668,7 +714,8 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp,
if (quirk_no_way_out)
quirk_no_way_out(i, m, regs);
}
- if (mce_severity(m, mca_cfg.tolerant, msg) >= MCE_PANIC_SEVERITY)
+ if (mce_severity(m, mca_cfg.tolerant, msg, true) >=
+ MCE_PANIC_SEVERITY)
ret = 1;
}
return ret;
@@ -697,7 +744,7 @@ static int mce_timed_out(u64 *t)
* might have been modified by someone else.
*/
rmb();
- if (atomic_read(&mce_paniced))
+ if (atomic_read(&mce_panicked))
wait_for_panic();
if (!mca_cfg.monarch_timeout)
goto out;
@@ -754,7 +801,7 @@ static void mce_reign(void)
for_each_possible_cpu(cpu) {
int severity = mce_severity(&per_cpu(mces_seen, cpu),
mca_cfg.tolerant,
- &nmsg);
+ &nmsg, true);
if (severity > global_worst) {
msg = nmsg;
global_worst = severity;
@@ -1095,13 +1142,14 @@ void do_machine_check(struct pt_regs *regs, long error_code)
*/
add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
- severity = mce_severity(&m, cfg->tolerant, NULL);
+ severity = mce_severity(&m, cfg->tolerant, NULL, true);
/*
- * When machine check was for corrected handler don't touch,
- * unless we're panicing.
+ * When machine check was for corrected/deferred handler don't
+ * touch, unless we're panicing.
*/
- if (severity == MCE_KEEP_SEVERITY && !no_way_out)
+ if ((severity == MCE_KEEP_SEVERITY ||
+ severity == MCE_UCNA_SEVERITY) && !no_way_out)
continue;
__set_bit(i, toclear);
if (severity == MCE_NO_SEVERITY) {
@@ -2520,7 +2568,7 @@ struct dentry *mce_get_debugfs_dir(void)
static void mce_reset(void)
{
cpu_missing = 0;
- atomic_set(&mce_fake_paniced, 0);
+ atomic_set(&mce_fake_panicked, 0);
atomic_set(&mce_executing, 0);
atomic_set(&mce_callin, 0);
atomic_set(&global_nwo, 0);