[GIT PULL] RAS changes for v4.5

From: Ingo Molnar
Date: Mon Jan 11 2016 - 07:59:33 EST


Linus,

Please pull the latest ras-core-for-linus git tree from:

git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git ras-core-for-linus

# HEAD: feab21f8356bde572663e29c9d9e48c964292e05 x86/mce: Make usable address checks Intel-only

Various x86 MCE fixes and small enhancements.

Thanks,

Ingo

------------------>
Borislav Petkov (3):
x86/RAS: Remove mce.usable_addr
x86/mce: Add the missing memory error check on AMD
x86/mce: Make usable address checks Intel-only

Tony Luck (1):
x86/mce: Do not enter deferred errors into the generic pool twice


arch/x86/include/uapi/asm/mce.h | 2 +-
arch/x86/kernel/cpu/mcheck/mce.c | 82 ++++++++++++++++++++--------------------
2 files changed, 43 insertions(+), 41 deletions(-)

diff --git a/arch/x86/include/uapi/asm/mce.h b/arch/x86/include/uapi/asm/mce.h
index 03429da2fa80..2184943341bf 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 c5b0d562dbf5..3865e95cc5ec 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)
{
@@ -484,7 +505,7 @@ 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);
}
@@ -522,10 +543,10 @@ 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
@@ -567,7 +588,7 @@ 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 +622,8 @@ 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))
@@ -608,27 +631,24 @@ 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) {
+ 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();
- }
- }

/*
* 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 (mce_usable_address(&m)) {
+ /*
+ * 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 +664,7 @@ 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);

@@ -931,23 +951,6 @@ static int mce_end(int order)
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;
@@ -1089,7 +1092,6 @@ 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);