Merge branch 'ras-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull RAS updates from Borislav Petkov:

 - Support for varying MCA bank numbers per CPU: this is in preparation
   for future CPU enablement (Yazen Ghannam)

 - MCA banks read race fix (Tony Luck)

 - Facility to filter MCEs which should not be logged (Yazen Ghannam)

 - The usual round of cleanups and fixes

* 'ras-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/MCE/AMD: Don't report L1 BTB MCA errors on some family 17h models
  x86/MCE: Add an MCE-record filtering function
  RAS/CEC: Increment cec_entered under the mutex lock
  x86/mce: Fix debugfs_simple_attr.cocci warnings
  x86/mce: Remove mce_report_event()
  x86/mce: Handle varying MCA bank counts
  x86/mce: Fix machine_check_poll() tests for error types
  MAINTAINERS: Fix file pattern for X86 MCE INFRASTRUCTURE
  x86/MCE: Group AMD function prototypes in <asm/mce.h>

MAINTAINERS

@@ -16941,7 +16941,7 @@ M:	Tony Luck <tony.luck@intel.com>
 M:	Borislav Petkov <bp@alien8.de>
 L:	linux-edac@vger.kernel.org
 S:	Maintained
-F:	arch/x86/kernel/cpu/mcheck/*
+F:	arch/x86/kernel/cpu/mce/*
 
 X86 MICROCODE UPDATE SUPPORT
 M:	Borislav Petkov <bp@alien8.de>

arch/x86/include/asm/mce.h

@@ -210,16 +210,6 @@ static inline void cmci_rediscover(void) {}
 static inline void cmci_recheck(void) {}
 #endif
 
-#ifdef CONFIG_X86_MCE_AMD
-void mce_amd_feature_init(struct cpuinfo_x86 *c);
-int umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr);
-#else
-static inline void mce_amd_feature_init(struct cpuinfo_x86 *c) { }
-static inline int umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr) { return -EINVAL; };
-#endif
-
-static inline void mce_hygon_feature_init(struct cpuinfo_x86 *c) { return mce_amd_feature_init(c); }
-
 int mce_available(struct cpuinfo_x86 *c);
 bool mce_is_memory_error(struct mce *m);
 bool mce_is_correctable(struct mce *m);
@@ -345,12 +335,19 @@ extern bool amd_mce_is_memory_error(struct mce *m);
 extern int mce_threshold_create_device(unsigned int cpu);
 extern int mce_threshold_remove_device(unsigned int cpu);
 
-#else
+void mce_amd_feature_init(struct cpuinfo_x86 *c);
+int umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr);
 
-static inline int mce_threshold_create_device(unsigned int cpu) { return 0; };
-static inline int mce_threshold_remove_device(unsigned int cpu) { return 0; };
-static inline bool amd_mce_is_memory_error(struct mce *m) { return false; };
+#else
 
+static inline int mce_threshold_create_device(unsigned int cpu)		{ return 0; };
+static inline int mce_threshold_remove_device(unsigned int cpu)		{ return 0; };
+static inline bool amd_mce_is_memory_error(struct mce *m)		{ return false; };
+static inline void mce_amd_feature_init(struct cpuinfo_x86 *c)		{ }
+static inline int
+umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr)	{ return -EINVAL; };
 #endif
 
+static inline void mce_hygon_feature_init(struct cpuinfo_x86 *c)	{ return mce_amd_feature_init(c); }
+
 #endif /* _ASM_X86_MCE_H */

arch/x86/kernel/cpu/mce/amd.c

@@ -563,33 +563,59 @@ prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr,
 	return offset;
 }
 
+bool amd_filter_mce(struct mce *m)
+{
+	enum smca_bank_types bank_type = smca_get_bank_type(m->bank);
+	struct cpuinfo_x86 *c = &boot_cpu_data;
+	u8 xec = (m->status >> 16) & 0x3F;
+
+	/* See Family 17h Models 10h-2Fh Erratum #1114. */
+	if (c->x86 == 0x17 &&
+	    c->x86_model >= 0x10 && c->x86_model <= 0x2F &&
+	    bank_type == SMCA_IF && xec == 10)
+		return true;
+
+	return false;
+}
+
 /*
- * Turn off MC4_MISC thresholding banks on all family 0x15 models since
- * they're not supported there.
+ * Turn off thresholding banks for the following conditions:
+ * - MC4_MISC thresholding is not supported on Family 0x15.
+ * - Prevent possible spurious interrupts from the IF bank on Family 0x17
+ *   Models 0x10-0x2F due to Erratum #1114.
  */
-void disable_err_thresholding(struct cpuinfo_x86 *c)
+void disable_err_thresholding(struct cpuinfo_x86 *c, unsigned int bank)
 {
-	int i;
+	int i, num_msrs;
 	u64 hwcr;
 	bool need_toggle;
-	u32 msrs[] = {
-		0x00000413, /* MC4_MISC0 */
-		0xc0000408, /* MC4_MISC1 */
-	};
+	u32 msrs[NR_BLOCKS];
+
+	if (c->x86 == 0x15 && bank == 4) {
+		msrs[0] = 0x00000413; /* MC4_MISC0 */
+		msrs[1] = 0xc0000408; /* MC4_MISC1 */
+		num_msrs = 2;
+	} else if (c->x86 == 0x17 &&
+		   (c->x86_model >= 0x10 && c->x86_model <= 0x2F)) {
 
-	if (c->x86 != 0x15)
+		if (smca_get_bank_type(bank) != SMCA_IF)
+			return;
+
+		msrs[0] = MSR_AMD64_SMCA_MCx_MISC(bank);
+		num_msrs = 1;
+	} else {
 		return;
+	}
 
 	rdmsrl(MSR_K7_HWCR, hwcr);
 
 	/* McStatusWrEn has to be set */
 	need_toggle = !(hwcr & BIT(18));
-
 	if (need_toggle)
 		wrmsrl(MSR_K7_HWCR, hwcr | BIT(18));
 
 	/* Clear CntP bit safely */
-	for (i = 0; i < ARRAY_SIZE(msrs); i++)
+	for (i = 0; i < num_msrs; i++)
 		msr_clear_bit(msrs[i], 62);
 
 	/* restore old settings */
@@ -604,12 +630,12 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
 	unsigned int bank, block, cpu = smp_processor_id();
 	int offset = -1;
 
-	disable_err_thresholding(c);
-
 	for (bank = 0; bank < mca_cfg.banks; ++bank) {
 		if (mce_flags.smca)
 			smca_configure(bank, cpu);
 
+		disable_err_thresholding(c, bank);
+
 		for (block = 0; block < NR_BLOCKS; ++block) {
 			address = get_block_address(address, low, high, bank, block);
 			if (!address)

arch/x86/kernel/cpu/mce/core.c

@@ -460,23 +460,6 @@ static void mce_irq_work_cb(struct irq_work *entry)
 	mce_schedule_work();
 }
 
-static void mce_report_event(struct pt_regs *regs)
-{
-	if (regs->flags & (X86_VM_MASK|X86_EFLAGS_IF)) {
-		mce_notify_irq();
-		/*
-		 * Triggering the work queue here is just an insurance
-		 * policy in case the syscall exit notify handler
-		 * doesn't run soon enough or ends up running on the
-		 * wrong CPU (can happen when audit sleeps)
-		 */
-		mce_schedule_work();
-		return;
-	}
-
-	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
@@ -712,19 +695,49 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
 
 		barrier();
 		m.status = mce_rdmsrl(msr_ops.status(i));
+
+		/* If this entry is not valid, ignore it */
 		if (!(m.status & MCI_STATUS_VAL))
 			continue;
 
 		/*
-		 * Uncorrected or signalled events are handled by the exception
-		 * handler when it is enabled, so don't process those here.
-		 *
-		 * TBD do the same check for MCI_STATUS_EN here?
+		 * If we are logging everything (at CPU online) or this
+		 * is a corrected error, then we must log it.
 		 */
-		if (!(flags & MCP_UC) &&
-		    (m.status & (mca_cfg.ser ? MCI_STATUS_S : MCI_STATUS_UC)))
-			continue;
+		if ((flags & MCP_UC) || !(m.status & MCI_STATUS_UC))
+			goto log_it;
+
+		/*
+		 * Newer Intel systems that support software error
+		 * recovery need to make additional checks. Other
+		 * CPUs should skip over uncorrected errors, but log
+		 * everything else.
+		 */
+		if (!mca_cfg.ser) {
+			if (m.status & MCI_STATUS_UC)
+				continue;
+			goto log_it;
+		}
 
+		/* Log "not enabled" (speculative) errors */
+		if (!(m.status & MCI_STATUS_EN))
+			goto log_it;
+
+		/*
+		 * Log UCNA (SDM: 15.6.3 "UCR Error Classification")
+		 * UC == 1 && PCC == 0 && S == 0
+		 */
+		if (!(m.status & MCI_STATUS_PCC) && !(m.status & MCI_STATUS_S))
+			goto log_it;
+
+		/*
+		 * Skip anything else. Presumption is that our read of this
+		 * bank is racing with a machine check. Leave the log alone
+		 * for do_machine_check() to deal with it.
+		 */
+		continue;
+
+log_it:
 		error_seen = true;
 
 		mce_read_aux(&m, i);
@@ -1301,7 +1314,8 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 		mce_panic("Fatal machine check on current CPU", &m, msg);
 
 	if (worst > 0)
-		mce_report_event(regs);
+		irq_work_queue(&mce_irq_work);
+
 	mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
 
 	sync_core();
@@ -1451,13 +1465,12 @@ EXPORT_SYMBOL_GPL(mce_notify_irq);
 static int __mcheck_cpu_mce_banks_init(void)
 {
 	int i;
-	u8 num_banks = mca_cfg.banks;
 
-	mce_banks = kcalloc(num_banks, sizeof(struct mce_bank), GFP_KERNEL);
+	mce_banks = kcalloc(MAX_NR_BANKS, sizeof(struct mce_bank), GFP_KERNEL);
 	if (!mce_banks)
 		return -ENOMEM;
 
-	for (i = 0; i < num_banks; i++) {
+	for (i = 0; i < MAX_NR_BANKS; i++) {
 		struct mce_bank *b = &mce_banks[i];
 
 		b->ctl = -1ULL;
@@ -1471,28 +1484,19 @@ static int __mcheck_cpu_mce_banks_init(void)
  */
 static int __mcheck_cpu_cap_init(void)
 {
-	unsigned b;
 	u64 cap;
+	u8 b;
 
 	rdmsrl(MSR_IA32_MCG_CAP, cap);
 
 	b = cap & MCG_BANKCNT_MASK;
-	if (!mca_cfg.banks)
-		pr_info("CPU supports %d MCE banks\n", b);
-
-	if (b > MAX_NR_BANKS) {
-		pr_warn("Using only %u machine check banks out of %u\n",
-			MAX_NR_BANKS, b);
+	if (WARN_ON_ONCE(b > MAX_NR_BANKS))
 		b = MAX_NR_BANKS;
-	}
 
-	/* Don't support asymmetric configurations today */
-	WARN_ON(mca_cfg.banks != 0 && b != mca_cfg.banks);
-	mca_cfg.banks = b;
+	mca_cfg.banks = max(mca_cfg.banks, b);
 
 	if (!mce_banks) {
 		int err = __mcheck_cpu_mce_banks_init();
-
 		if (err)
 			return err;
 	}
@@ -1771,6 +1775,14 @@ static void __mcheck_cpu_init_timer(void)
 	mce_start_timer(t);
 }
 
+bool filter_mce(struct mce *m)
+{
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+		return amd_filter_mce(m);
+
+	return false;
+}
+
 /* Handle unconfigured int18 (should never happen) */
 static void unexpected_machine_check(struct pt_regs *regs, long error_code)
 {
@@ -2425,8 +2437,8 @@ static int fake_panic_set(void *data, u64 val)
 	return 0;
 }
 
-DEFINE_SIMPLE_ATTRIBUTE(fake_panic_fops, fake_panic_get,
-			fake_panic_set, "%llu\n");
+DEFINE_DEBUGFS_ATTRIBUTE(fake_panic_fops, fake_panic_get, fake_panic_set,
+			 "%llu\n");
 
 static int __init mcheck_debugfs_init(void)
 {
@@ -2435,8 +2447,8 @@ static int __init mcheck_debugfs_init(void)
 	dmce = mce_get_debugfs_dir();
 	if (!dmce)
 		return -ENOMEM;
-	ffake_panic = debugfs_create_file("fake_panic", 0444, dmce, NULL,
-					  &fake_panic_fops);
+	ffake_panic = debugfs_create_file_unsafe("fake_panic", 0444, dmce,
+						 NULL, &fake_panic_fops);
 	if (!ffake_panic)
 		return -ENOMEM;
 
@@ -2451,6 +2463,8 @@ EXPORT_SYMBOL_GPL(mcsafe_key);
 
 static int __init mcheck_late_init(void)
 {
+	pr_info("Using %d MCE banks\n", mca_cfg.banks);
+
 	if (mca_cfg.recovery)
 		static_branch_inc(&mcsafe_key);
 

arch/x86/kernel/cpu/mce/genpool.c

@@ -99,6 +99,9 @@ int mce_gen_pool_add(struct mce *mce)
 {
 	struct mce_evt_llist *node;
 
+	if (filter_mce(mce))
+		return -EINVAL;
+
 	if (!mce_evt_pool)
 		return -EINVAL;
 

arch/x86/kernel/cpu/mce/inject.c

@@ -46,8 +46,6 @@
 static struct mce i_mce;
 static struct dentry *dfs_inj;
 
-static u8 n_banks;
-
 #define MAX_FLAG_OPT_SIZE	4
 #define NBCFG			0x44
 
@@ -570,9 +568,15 @@ static void do_inject(void)
 static int inj_bank_set(void *data, u64 val)
 {
 	struct mce *m = (struct mce *)data;
+	u8 n_banks;
+	u64 cap;
+
+	/* Get bank count on target CPU so we can handle non-uniform values. */
+	rdmsrl_on_cpu(m->extcpu, MSR_IA32_MCG_CAP, &cap);
+	n_banks = cap & MCG_BANKCNT_MASK;
 
 	if (val >= n_banks) {
-		pr_err("Non-existent MCE bank: %llu\n", val);
+		pr_err("MCA bank %llu non-existent on CPU%d\n", val, m->extcpu);
 		return -EINVAL;
 	}
 
@@ -665,10 +669,6 @@ static struct dfs_node {
 static int __init debugfs_init(void)
 {
 	unsigned int i;
-	u64 cap;
-
-	rdmsrl(MSR_IA32_MCG_CAP, cap);
-	n_banks = cap & MCG_BANKCNT_MASK;
 
 	dfs_inj = debugfs_create_dir("mce-inject", NULL);
 	if (!dfs_inj)

arch/x86/kernel/cpu/mce/internal.h

@@ -173,4 +173,13 @@ struct mca_msr_regs {
 
 extern struct mca_msr_regs msr_ops;
 
+/* Decide whether to add MCE record to MCE event pool or filter it out. */
+extern bool filter_mce(struct mce *m);
+
+#ifdef CONFIG_X86_MCE_AMD
+extern bool amd_filter_mce(struct mce *m);
+#else
+static inline bool amd_filter_mce(struct mce *m)			{ return false; };
+#endif
+
 #endif /* __X86_MCE_INTERNAL_H__ */

drivers/edac/mce_amd.c

@@ -1004,7 +1004,7 @@ static inline void amd_decode_err_code(u16 ec)
 /*
  * Filter out unwanted MCE signatures here.
  */
-static bool amd_filter_mce(struct mce *m)
+static bool ignore_mce(struct mce *m)
 {
 	/*
 	 * NB GART TLB error reporting is disabled by default.
@@ -1038,7 +1038,7 @@ amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data)
 	unsigned int fam = x86_family(m->cpuid);
 	int ecc;
 
-	if (amd_filter_mce(m))
+	if (ignore_mce(m))
 		return NOTIFY_STOP;
 
 	pr_emerg(HW_ERR "%s\n", decode_error_status(m));

drivers/ras/cec.c

@@ -286,10 +286,10 @@ int cec_add_elem(u64 pfn)
 	if (!ce_arr.array || ce_arr.disabled)
 		return -ENODEV;
 
-	ca->ces_entered++;
-
 	mutex_lock(&ce_mutex);
 
+	ca->ces_entered++;
+
 	if (ca->n == MAX_ELEMS)
 		WARN_ON(!del_lru_elem_unlocked(ca));