tip/ras/core: Second pile

index 6b7039c166b8..43f8b49ef570 100644
@@ -1495,7 +1495,7 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
 			 */
 			clear_bit(10, (unsigned long *)&mce_banks[4].ctl);
 		}
-		if (c->x86 <= 17 && cfg->bootlog < 0) {
+		if (c->x86 < 17 && cfg->bootlog < 0) {
 			/*
 			 * Lots of broken BIOS around that don't clear them
 			 * by default and leave crap in there. Don't log:

index 5119766d9889..631356c8cca4 100644
@@ -204,6 +204,33 @@ static int error_context(struct mce *m)
 	return IN_KERNEL;
 }
 
+static int mce_severity_amd_smca(struct mce *m, int err_ctx)
+{
+	u32 addr = MSR_AMD64_SMCA_MCx_CONFIG(m->bank);
+	u32 low, high;
+
+	/*
+	 * We need to look at the following bits:
+	 * - "succor" bit (data poisoning support), and
+	 * - TCC bit (Task Context Corrupt)
+	 * in MCi_STATUS to determine error severity.
+	 */
+	if (!mce_flags.succor)
+		return MCE_PANIC_SEVERITY;
+
+	if (rdmsr_safe(addr, &low, &high))
+		return MCE_PANIC_SEVERITY;
+
+	/* TCC (Task context corrupt). If set and if IN_KERNEL, panic. */
+	if ((low & MCI_CONFIG_MCAX) &&
+	    (m->status & MCI_STATUS_TCC) &&
+	    (err_ctx == IN_KERNEL))
+		return MCE_PANIC_SEVERITY;
+
+	 /* ...otherwise invoke hwpoison handler. */
+	return MCE_AR_SEVERITY;
+}
+
 /*
  * See AMD Error Scope Hierarchy table in a newer BKDG. For example
  * 49125_15h_Models_30h-3Fh_BKDG.pdf, section "RAS Features"

@@ -225,6 +252,9 @@ static int mce_severity_amd(struct mce *m, int tolerant, char **msg, bool is_exc
 		 * to at least kill process to prolong system operation.
 		 */
 		if (mce_flags.overflow_recov) {
+			if (mce_flags.smca)
+				return mce_severity_amd_smca(m, ctx);
+
 			/* software can try to contain */
 			if (!(m->mcgstatus & MCG_STATUS_RIPV) && (ctx == IN_KERNEL))
 				return MCE_PANIC_SEVERITY;

index 43f8b49ef570..6bffb26e05e0 100644
@@ -1420,7 +1420,6 @@ static void __mcheck_cpu_init_generic(void)
 	enum mcp_flags m_fl = 0;
 	mce_banks_t all_banks;
 	u64 cap;
-	int i;
 
 	if (!mca_cfg.bootlog)
 		m_fl = MCP_DONTLOG;

@@ -1436,6 +1435,11 @@ static void __mcheck_cpu_init_generic(void)
 	rdmsrl(MSR_IA32_MCG_CAP, cap);
 	if (cap & MCG_CTL_P)
 		wrmsr(MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff);
+}
+
+static void __mcheck_cpu_init_clear_banks(void)
+{
+	int i;
 
 	for (i = 0; i < mca_cfg.banks; i++) {
 		struct mce_bank *b = &mce_banks[i];

@@ -1717,6 +1721,7 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c)
 
 	__mcheck_cpu_init_generic();
 	__mcheck_cpu_init_vendor(c);
+	__mcheck_cpu_init_clear_banks();
 	__mcheck_cpu_init_timer();
 }
 

@@ -2121,6 +2126,7 @@ static void mce_syscore_resume(void)
 {
 	__mcheck_cpu_init_generic();
 	__mcheck_cpu_init_vendor(raw_cpu_ptr(&cpu_info));
+	__mcheck_cpu_init_clear_banks();
 }
 
 static struct syscore_ops mce_syscore_ops = {

@@ -2138,6 +2144,7 @@ static void mce_cpu_restart(void *data)
 	if (!mce_available(raw_cpu_ptr(&cpu_info)))
 		return;
 	__mcheck_cpu_init_generic();
+	__mcheck_cpu_init_clear_banks();
 	__mcheck_cpu_init_timer();
 }
 

index 92b6f651fa4f..53ab69704771 100644
@@ -104,10 +104,16 @@
 #define MCE_LOG_SIGNATURE	"MACHINECHECK"
 
 /* AMD Scalable MCA */
+#define MSR_AMD64_SMCA_MC0_CTL		0xc0002000
+#define MSR_AMD64_SMCA_MC0_STATUS	0xc0002001
+#define MSR_AMD64_SMCA_MC0_ADDR		0xc0002002
 #define MSR_AMD64_SMCA_MC0_MISC0	0xc0002003
 #define MSR_AMD64_SMCA_MC0_CONFIG	0xc0002004
 #define MSR_AMD64_SMCA_MC0_IPID		0xc0002005
 #define MSR_AMD64_SMCA_MC0_MISC1	0xc000200a
+#define MSR_AMD64_SMCA_MCx_CTL(x)	(MSR_AMD64_SMCA_MC0_CTL + 0x10*(x))
+#define MSR_AMD64_SMCA_MCx_STATUS(x)	(MSR_AMD64_SMCA_MC0_STATUS + 0x10*(x))
+#define MSR_AMD64_SMCA_MCx_ADDR(x)	(MSR_AMD64_SMCA_MC0_ADDR + 0x10*(x))
 #define MSR_AMD64_SMCA_MCx_MISC(x)	(MSR_AMD64_SMCA_MC0_MISC0 + 0x10*(x))
 #define MSR_AMD64_SMCA_MCx_CONFIG(x)	(MSR_AMD64_SMCA_MC0_CONFIG + 0x10*(x))
 #define MSR_AMD64_SMCA_MCx_IPID(x)	(MSR_AMD64_SMCA_MC0_IPID + 0x10*(x))

@@ -168,9 +174,18 @@ struct mce_vendor_flags {
 
 	      __reserved_0	: 61;
 };
+
+struct mca_msr_regs {
+	u32 (*ctl)	(int bank);
+	u32 (*status)	(int bank);
+	u32 (*addr)	(int bank);
+	u32 (*misc)	(int bank);
+};
+
 extern struct mce_vendor_flags mce_flags;
 
 extern struct mca_config mca_cfg;
+extern struct mca_msr_regs msr_ops;
 extern void mce_register_decode_chain(struct notifier_block *nb);
 extern void mce_unregister_decode_chain(struct notifier_block *nb);
 

53 lines not on this page · raw message

index 54a4881b9475..d77f3b04b277 100644
@@ -403,11 +403,11 @@ static int msr_to_offset(u32 msr)
 
 	if (msr == mca_cfg.rip_msr)
 		return offsetof(struct mce, ip);
-	if (msr == MSR_IA32_MCx_STATUS(bank))
+	if (msr == msr_ops.status(bank))
 		return offsetof(struct mce, status);
-	if (msr == MSR_IA32_MCx_ADDR(bank))
+	if (msr == msr_ops.addr(bank))
 		return offsetof(struct mce, addr);
-	if (msr == MSR_IA32_MCx_MISC(bank))
+	if (msr == msr_ops.misc(bank))
 		return offsetof(struct mce, misc);
 	if (msr == MSR_IA32_MCG_STATUS)
 		return offsetof(struct mce, mcgstatus);

@@ -570,9 +570,9 @@ static struct notifier_block mce_srao_nb = {
 static void mce_read_aux(struct mce *m, int i)
 {
 	if (m->status & MCI_STATUS_MISCV)
-		m->misc = mce_rdmsrl(MSR_IA32_MCx_MISC(i));
+		m->misc = mce_rdmsrl(msr_ops.misc(i));
 	if (m->status & MCI_STATUS_ADDRV) {
-		m->addr = mce_rdmsrl(MSR_IA32_MCx_ADDR(i));
+		m->addr = mce_rdmsrl(msr_ops.addr(i));
 
 		/*
 		 * Mask the reported address by the reported granularity.

@@ -654,7 +654,7 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
 		m.tsc = 0;
 
 		barrier();
-		m.status = mce_rdmsrl(MSR_IA32_MCx_STATUS(i));
+		m.status = mce_rdmsrl(msr_ops.status(i));
 		if (!(m.status & MCI_STATUS_VAL))
 			continue;
 

@@ -701,7 +701,7 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
 		/*
 		 * Clear state for this bank.
 		 */
-		mce_wrmsrl(MSR_IA32_MCx_STATUS(i), 0);
+		mce_wrmsrl(msr_ops.status(i), 0);
 	}
 
 	/*

@@ -726,7 +726,7 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp,
 	char *tmp;
 
 	for (i = 0; i < mca_cfg.banks; i++) {
-		m->status = mce_rdmsrl(MSR_IA32_MCx_STATUS(i));
+		m->status = mce_rdmsrl(msr_ops.status(i));
 		if (m->status & MCI_STATUS_VAL) {
 			__set_bit(i, validp);
 			if (quirk_no_way_out)

@@ -1004,7 +1004,7 @@ static void mce_clear_state(unsigned long *toclear)
 
 	for (i = 0; i < mca_cfg.banks; i++) {
 		if (test_bit(i, toclear))
-			mce_wrmsrl(MSR_IA32_MCx_STATUS(i), 0);
+			mce_wrmsrl(msr_ops.status(i), 0);
 	}
 }
 

@@ -1123,7 +1123,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 		m.addr = 0;
 		m.bank = i;
 
-		m.status = mce_rdmsrl(MSR_IA32_MCx_STATUS(i));
+		m.status = mce_rdmsrl(msr_ops.status(i));
 		if ((m.status & MCI_STATUS_VAL) == 0)
 			continue;
 

@@ -1493,8 +1493,8 @@ static void __mcheck_cpu_init_clear_banks(void)
 
 		if (!b->init)
 			continue;
-		wrmsrl(MSR_IA32_MCx_CTL(i), b->ctl);
-		wrmsrl(MSR_IA32_MCx_STATUS(i), 0);
+		wrmsrl(msr_ops.ctl(i), b->ctl);
+		wrmsrl(msr_ops.status(i), 0);
 	}
 }
 

@@ -1684,6 +1684,16 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
 		mce_flags.overflow_recov = !!(ebx & BIT(0));
 		mce_flags.succor	 = !!(ebx & BIT(1));
 		mce_flags.smca		 = !!(ebx & BIT(3));
+
+		/*
+		 * Install proper ops for Scalable MCA enabled processors
+		 */
+		if (mce_flags.smca) {
+			msr_ops.ctl	= smca_ctl_reg;
+			msr_ops.status	= smca_status_reg;
+			msr_ops.addr	= smca_addr_reg;
+			msr_ops.misc	= smca_misc_reg;
+		}
 		mce_amd_feature_init(c);
 
 		break;

@@ -2134,7 +2144,7 @@ static void mce_disable_error_reporting(void)
 		struct mce_bank *b = &mce_banks[i];
 
 		if (b->init)
-			wrmsrl(MSR_IA32_MCx_CTL(i), 0);
+			wrmsrl(msr_ops.ctl(i), 0);
 	}
 	return;
 }

@@ -2467,7 +2477,7 @@ static void mce_reenable_cpu(void *h)
 		struct mce_bank *b = &mce_banks[i];
 
 		if (b->init)
-			wrmsrl(MSR_IA32_MCx_CTL(i), b->ctl);
+			wrmsrl(msr_ops.ctl(i), b->ctl);
 	}
 }
 

index 9d656fd436ef..c594680c36f2 100644
@@ -333,7 +333,7 @@ static u32 get_block_address(u32 current_addr, u32 low, u32 high,
 	/* Fall back to method we used for older processors: */
 	switch (block) {
 	case 0:
-		addr = MSR_IA32_MCx_MISC(bank);
+		addr = msr_ops.misc(bank);
 		break;
 	case 1:
 		offset = ((low & MASK_BLKPTR_LO) >> 21);

@@ -435,7 +435,7 @@ static void __log_error(unsigned int bank, bool threshold_err, u64 misc)
 	struct mce m;
 	u64 status;
 
-	rdmsrl(MSR_IA32_MCx_STATUS(bank), status);
+	rdmsrl(msr_ops.status(bank), status);
 	if (!(status & MCI_STATUS_VAL))
 		return;
 

@@ -448,10 +448,10 @@ static void __log_error(unsigned int bank, bool threshold_err, u64 misc)
 		m.misc = misc;
 
 	if (m.status & MCI_STATUS_ADDRV)
-		rdmsrl(MSR_IA32_MCx_ADDR(bank), m.addr);
+		rdmsrl(msr_ops.addr(bank), m.addr);
 
 	mce_log(&m);
-	wrmsrl(MSR_IA32_MCx_STATUS(bank), 0);
+	wrmsrl(msr_ops.status(bank), 0);
 }
 
 static inline void __smp_deferred_error_interrupt(void)

@@ -483,7 +483,7 @@ static void amd_deferred_error_interrupt(void)
 	unsigned int bank;
 
 	for (bank = 0; bank < mca_cfg.banks; ++bank) {
-		rdmsrl(MSR_IA32_MCx_STATUS(bank), status);
+		rdmsrl(msr_ops.status(bank), status);
 
 		if (!(status & MCI_STATUS_VAL) ||
 		    !(status & MCI_STATUS_DEFERRED))

index 2658e2af74ec..6e68a464659a 100644
@@ -26,6 +26,52 @@ static struct gen_pool *mce_evt_pool;
 static LLIST_HEAD(mce_event_llist);
 static char gen_pool_buf[MCE_POOLSZ];
 
+/*
+ * Compare the record "t" with each of the records on list "l" to see if
+ * an equivalent one is present in the list.
+ */
+static bool is_duplicate_mce_record(struct mce_evt_llist *t, struct mce_evt_llist *l)
+{
+	struct mce_evt_llist *node;
+	struct mce *m1, *m2;
+
+	m1 = &t->mce;
+
+	llist_for_each_entry(node, &l->llnode, llnode) {
+		m2 = &node->mce;
+
+		if (!mce_cmp(m1, m2))
+			return true;
+	}
+	return false;
+}
+
+/*
+ * The system has panicked - we'd like to peruse the list of mce records
+ * that have been queued, but not seen by anyone yet.  The list is in
+ * reverse time order, so we need to reverse it. While doing that we can
+ * also drop duplicate records (these were logged because some banks are
+ * shared between cores or by all threads on a socket).
+ */
+struct llist_node *mce_gen_pool_prepare_records(void)
+{
+	struct llist_node *head;
+	LLIST_HEAD(new_head);
+	struct mce_evt_llist *node, *t;
+
+	head = llist_del_all(&mce_event_llist);
+	if (!head)
+		return NULL;
+
+	/* squeeze out duplicates while reversing order */
+	llist_for_each_entry_safe(node, t, head, llnode) {
+		if (!is_duplicate_mce_record(node, t))
+			llist_add(&node->llnode, &new_head);
+	}
+
+	return new_head.first;
+}
+
 void mce_gen_pool_process(void)
 {
 	struct llist_node *head;

index 547720efd923..cd74a3f00aea 100644
@@ -35,6 +35,7 @@ void mce_gen_pool_process(void);
 bool mce_gen_pool_empty(void);
 int mce_gen_pool_add(struct mce *mce);
 int mce_gen_pool_init(void);
+struct llist_node *mce_gen_pool_prepare_records(void);
 
 extern int (*mce_severity)(struct mce *a, int tolerant, char **msg, bool is_excp);
 struct dentry *mce_get_debugfs_dir(void);

@@ -81,3 +82,17 @@ static inline int apei_clear_mce(u64 record_id)
 #endif
 
 void mce_inject_log(struct mce *m);
+
+/*
+ * We consider records to be equivalent if bank+status+addr+misc all match.
+ * This is only used when the system is going down because of a fatal error
+ * to avoid cluttering the console log with essentially repeated information.
+ * In normal processing all errors seen are logged.
+ */
+static inline bool mce_cmp(struct mce *m1, struct mce *m2)
+{
+	return m1->bank != m2->bank ||
+		m1->status != m2->status ||
+		m1->addr != m2->addr ||
+		m1->misc != m2->misc;
+}

index d77f3b04b277..c356f47894c9 100644
@@ -161,7 +161,6 @@ void mce_log(struct mce *mce)
 	if (!mce_gen_pool_add(mce))
 		irq_work_queue(&mce_irq_work);
 
-	mce->finished = 0;
 	wmb();
 	for (;;) {
 		entry = mce_log_get_idx_check(mcelog.next);

@@ -194,7 +193,6 @@ void mce_log(struct mce *mce)
 	mcelog.entry[entry].finished = 1;
 	wmb();
 
-	mce->finished = 1;
 	set_bit(0, &mce_need_notify);
 }
 

@@ -337,7 +335,9 @@ static void wait_for_panic(void)
 
 static void mce_panic(const char *msg, struct mce *final, char *exp)
 {
-	int i, apei_err = 0;
+	int apei_err = 0;
+	struct llist_node *pending;
+	struct mce_evt_llist *l;
 
 	if (!fake_panic) {
 		/*

@@ -354,11 +354,10 @@ static void mce_panic(const char *msg, struct mce *final, char *exp)
 		if (atomic_inc_return(&mce_fake_panicked) > 1)
 			return;
 	}
+	pending = mce_gen_pool_prepare_records();
 	/* First print corrected ones that are still unlogged */
-	for (i = 0; i < MCE_LOG_LEN; i++) {
-		struct mce *m = &mcelog.entry[i];
-		if (!(m->status & MCI_STATUS_VAL))
-			continue;
+	llist_for_each_entry(l, pending, llnode) {
+		struct mce *m = &l->mce;
 		if (!(m->status & MCI_STATUS_UC)) {
 			print_mce(m);
 			if (!apei_err)

@@ -366,13 +365,11 @@ static void mce_panic(const char *msg, struct mce *final, char *exp)
 		}
 	}
 	/* Now print uncorrected but with the final one last */
-	for (i = 0; i < MCE_LOG_LEN; i++) {
-		struct mce *m = &mcelog.entry[i];
-		if (!(m->status & MCI_STATUS_VAL))
-			continue;
+	llist_for_each_entry(l, pending, llnode) {
+		struct mce *m = &l->mce;
 		if (!(m->status & MCI_STATUS_UC))
 			continue;
-		if (!final || memcmp(m, final, sizeof(struct mce))) {
+		if (!final || mce_cmp(m, final)) {
 			print_mce(m);
 			if (!apei_err)
 				apei_err = apei_write_mce(m);

index c356f47894c9..aeda44684758 100644
@@ -1038,11 +1038,12 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 	int i;
 	int worst = 0;
 	int severity;
+
 	/*
 	 * Establish sequential order between the CPUs entering the machine
 	 * check handler.
 	 */
-	int order;
+	int order = -1;
 	/*
 	 * If no_way_out gets set, there is no safe way to recover from this
 	 * MCE.  If mca_cfg.tolerant is cranked up, we'll try anyway.

@@ -1056,7 +1057,12 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 	DECLARE_BITMAP(toclear, MAX_NR_BANKS);
 	DECLARE_BITMAP(valid_banks, MAX_NR_BANKS);
 	char *msg = "Unknown";
-	int lmce = 0;
+
+	/*
+	 * MCEs are always local on AMD. Same is determined by MCG_STATUS_LMCES
+	 * on Intel.
+	 */
+	int lmce = 1;
 
 	/* If this CPU is offline, just bail out. */
 	if (cpu_is_offline(smp_processor_id())) {

@@ -1095,19 +1101,20 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 		kill_it = 1;
 
 	/*
-	 * Check if this MCE is signaled to only this logical processor
+	 * Check if this MCE is signaled to only this logical processor,
+	 * on Intel only.
 	 */
-	if (m.mcgstatus & MCG_STATUS_LMCES)
-		lmce = 1;
-	else {
-		/*
-		 * Go through all the banks in exclusion of the other CPUs.
-		 * This way we don't report duplicated events on shared banks
-		 * because the first one to see it will clear it.
-		 * If this is a Local MCE, then no need to perform rendezvous.
-		 */
+	if (m.cpuvendor == X86_VENDOR_INTEL)
+		lmce = m.mcgstatus & MCG_STATUS_LMCES;
+
+	/*
+	 * Go through all banks in exclusion of the other CPUs. This way we
+	 * don't report duplicated events on shared banks because the first one
+	 * to see it will clear it. If this is a Local MCE, then no need to
+	 * perform rendezvous.
+	 */
+	if (!lmce)
 		order = mce_start(&no_way_out);
-	}
 
 	for (i = 0; i < cfg->banks; i++) {
 		__clear_bit(i, toclear);