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

Pull RAS updates from Ingo Molnar:
 "Boris is on vacation so I'm sending the RAS bits this time. The main
  changes were:

   - Various RAS/CEC improvements and fixes by Borislav Petkov:
       - error insertion fixes
       - offlining latency fix
       - memory leak fix
       - additional sanity checks
       - cleanups
       - debug output improvements

   - More SMCA enhancements by Yazen Ghannam:
       - make banks truly per-CPU which they are in the hardware
       - don't over-cache certain registers
       - make the number of MCA banks per-CPU variable

     The long term goal with these changes is to support future
     heterogenous SMCA extensions.

   - Misc fixes and improvements"

* 'ras-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/mce: Do not check return value of debugfs_create functions
  x86/MCE: Determine MCA banks' init state properly
  x86/MCE: Make the number of MCA banks a per-CPU variable
  x86/MCE/AMD: Don't cache block addresses on SMCA systems
  x86/MCE: Make mce_banks a per-CPU array
  x86/MCE: Make struct mce_banks[] static
  RAS/CEC: Add copyright
  RAS/CEC: Add CONFIG_RAS_CEC_DEBUG and move CEC debug features there
  RAS/CEC: Dump the different array element sections
  RAS/CEC: Rename count_threshold to action_threshold
  RAS/CEC: Sanity-check array on every insertion
  RAS/CEC: Fix potential memory leak
  RAS/CEC: Do not set decay value on error
  RAS/CEC: Check count_threshold unconditionally
  RAS/CEC: Fix pfn insertion

7 files changed, 269 insertions, 205 deletions

diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index 785050af85e5..6ea7fdc82f3c 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -99,11 +99,6 @@ static struct smca_bank_name smca_names[] = {
 	[SMCA_PCIE]	= { "pcie",		"PCI Express Unit" },
 };
 
-static u32 smca_bank_addrs[MAX_NR_BANKS][NR_BLOCKS] __ro_after_init =
-{
-	[0 ... MAX_NR_BANKS - 1] = { [0 ... NR_BLOCKS - 1] = -1 }
-};
-
 static const char *smca_get_name(enum smca_bank_types t)
 {
 	if (t >= N_SMCA_BANK_TYPES)
@@ -197,6 +192,9 @@ static char buf_mcatype[MAX_MCATYPE_NAME_LEN];
 static DEFINE_PER_CPU(struct threshold_bank **, threshold_banks);
 static DEFINE_PER_CPU(unsigned int, bank_map);	/* see which banks are on */
 
+/* Map of banks that have more than MCA_MISC0 available. */
+static DEFINE_PER_CPU(u32, smca_misc_banks_map);
+
 static void amd_threshold_interrupt(void);
 static void amd_deferred_error_interrupt(void);
 
@@ -206,6 +204,28 @@ static void default_deferred_error_interrupt(void)
 }
 void (*deferred_error_int_vector)(void) = default_deferred_error_interrupt;
 
+static void smca_set_misc_banks_map(unsigned int bank, unsigned int cpu)
+{
+	u32 low, high;
+
+	/*
+	 * For SMCA enabled processors, BLKPTR field of the first MISC register
+	 * (MCx_MISC0) indicates presence of additional MISC regs set (MISC1-4).
+	 */
+	if (rdmsr_safe(MSR_AMD64_SMCA_MCx_CONFIG(bank), &low, &high))
+		return;
+
+	if (!(low & MCI_CONFIG_MCAX))
+		return;
+
+	if (rdmsr_safe(MSR_AMD64_SMCA_MCx_MISC(bank), &low, &high))
+		return;
+
+	if (low & MASK_BLKPTR_LO)
+		per_cpu(smca_misc_banks_map, cpu) |= BIT(bank);
+
+}
+
 static void smca_configure(unsigned int bank, unsigned int cpu)
 {
 	unsigned int i, hwid_mcatype;
@@ -243,6 +263,8 @@ static void smca_configure(unsigned int bank, unsigned int cpu)
 		wrmsr(smca_config, low, high);
 	}
 
+	smca_set_misc_banks_map(bank, cpu);
+
 	/* Return early if this bank was already initialized. */
 	if (smca_banks[bank].hwid)
 		return;
@@ -453,50 +475,29 @@ static void deferred_error_interrupt_enable(struct cpuinfo_x86 *c)
 	wrmsr(MSR_CU_DEF_ERR, low, high);
 }
 
-static u32 smca_get_block_address(unsigned int bank, unsigned int block)
+static u32 smca_get_block_address(unsigned int bank, unsigned int block,
+				  unsigned int cpu)
 {
-	u32 low, high;
-	u32 addr = 0;
-
-	if (smca_get_bank_type(bank) == SMCA_RESERVED)
-		return addr;
-
 	if (!block)
 		return MSR_AMD64_SMCA_MCx_MISC(bank);
 
-	/* Check our cache first: */
-	if (smca_bank_addrs[bank][block] != -1)
-		return smca_bank_addrs[bank][block];
-
-	/*
-	 * For SMCA enabled processors, BLKPTR field of the first MISC register
-	 * (MCx_MISC0) indicates presence of additional MISC regs set (MISC1-4).
-	 */
-	if (rdmsr_safe(MSR_AMD64_SMCA_MCx_CONFIG(bank), &low, &high))
-		goto out;
-
-	if (!(low & MCI_CONFIG_MCAX))
-		goto out;
-
-	if (!rdmsr_safe(MSR_AMD64_SMCA_MCx_MISC(bank), &low, &high) &&
-	    (low & MASK_BLKPTR_LO))
-		addr = MSR_AMD64_SMCA_MCx_MISCy(bank, block - 1);
+	if (!(per_cpu(smca_misc_banks_map, cpu) & BIT(bank)))
+		return 0;
 
-out:
-	smca_bank_addrs[bank][block] = addr;
-	return addr;
+	return MSR_AMD64_SMCA_MCx_MISCy(bank, block - 1);
 }
 
 static u32 get_block_address(u32 current_addr, u32 low, u32 high,
-			     unsigned int bank, unsigned int block)
+			     unsigned int bank, unsigned int block,
+			     unsigned int cpu)
 {
 	u32 addr = 0, offset = 0;
 
-	if ((bank >= mca_cfg.banks) || (block >= NR_BLOCKS))
+	if ((bank >= per_cpu(mce_num_banks, cpu)) || (block >= NR_BLOCKS))
 		return addr;
 
 	if (mce_flags.smca)
-		return smca_get_block_address(bank, block);
+		return smca_get_block_address(bank, block, cpu);
 
 	/* Fall back to method we used for older processors: */
 	switch (block) {
@@ -624,18 +625,19 @@ void disable_err_thresholding(struct cpuinfo_x86 *c, unsigned int bank)
 /* cpu init entry point, called from mce.c with preempt off */
 void mce_amd_feature_init(struct cpuinfo_x86 *c)
 {
-	u32 low = 0, high = 0, address = 0;
 	unsigned int bank, block, cpu = smp_processor_id();
+	u32 low = 0, high = 0, address = 0;
 	int offset = -1;
 
-	for (bank = 0; bank < mca_cfg.banks; ++bank) {
+
+	for (bank = 0; bank < this_cpu_read(mce_num_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);
+			address = get_block_address(address, low, high, bank, block, cpu);
 			if (!address)
 				break;
 
@@ -973,7 +975,7 @@ static void amd_deferred_error_interrupt(void)
 {
 	unsigned int bank;
 
-	for (bank = 0; bank < mca_cfg.banks; ++bank)
+	for (bank = 0; bank < this_cpu_read(mce_num_banks); ++bank)
 		log_error_deferred(bank);
 }
 
@@ -1014,7 +1016,7 @@ static void amd_threshold_interrupt(void)
 	struct threshold_block *first_block = NULL, *block = NULL, *tmp = NULL;
 	unsigned int bank, cpu = smp_processor_id();
 
-	for (bank = 0; bank < mca_cfg.banks; ++bank) {
+	for (bank = 0; bank < this_cpu_read(mce_num_banks); ++bank) {
 		if (!(per_cpu(bank_map, cpu) & (1 << bank)))
 			continue;
 
@@ -1201,7 +1203,7 @@ static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank,
 	u32 low, high;
 	int err;
 
-	if ((bank >= mca_cfg.banks) || (block >= NR_BLOCKS))
+	if ((bank >= per_cpu(mce_num_banks, cpu)) || (block >= NR_BLOCKS))
 		return 0;
 
 	if (rdmsr_safe_on_cpu(cpu, address, &low, &high))
@@ -1252,7 +1254,7 @@ static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank,
 	if (err)
 		goto out_free;
 recurse:
-	address = get_block_address(address, low, high, bank, ++block);
+	address = get_block_address(address, low, high, bank, ++block, cpu);
 	if (!address)
 		return 0;
 
@@ -1435,7 +1437,7 @@ int mce_threshold_remove_device(unsigned int cpu)
 {
 	unsigned int bank;
 
-	for (bank = 0; bank < mca_cfg.banks; ++bank) {
+	for (bank = 0; bank < per_cpu(mce_num_banks, cpu); ++bank) {
 		if (!(per_cpu(bank_map, cpu) & (1 << bank)))
 			continue;
 		threshold_remove_bank(cpu, bank);
@@ -1456,14 +1458,14 @@ int mce_threshold_create_device(unsigned int cpu)
 	if (bp)
 		return 0;
 
-	bp = kcalloc(mca_cfg.banks, sizeof(struct threshold_bank *),
+	bp = kcalloc(per_cpu(mce_num_banks, cpu), sizeof(struct threshold_bank *),
 		     GFP_KERNEL);
 	if (!bp)
 		return -ENOMEM;
 
 	per_cpu(threshold_banks, cpu) = bp;
 
-	for (bank = 0; bank < mca_cfg.banks; ++bank) {
+	for (bank = 0; bank < per_cpu(mce_num_banks, cpu); ++bank) {
 		if (!(per_cpu(bank_map, cpu) & (1 << bank)))
 			continue;
 		err = threshold_create_bank(cpu, bank);
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 282916f3b8d8..066562a1ea20 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -65,7 +65,23 @@ static DEFINE_MUTEX(mce_sysfs_mutex);
 
 DEFINE_PER_CPU(unsigned, mce_exception_count);
 
-struct mce_bank *mce_banks __read_mostly;
+DEFINE_PER_CPU_READ_MOSTLY(unsigned int, mce_num_banks);
+
+struct mce_bank {
+	u64			ctl;			/* subevents to enable */
+	bool			init;			/* initialise bank? */
+};
+static DEFINE_PER_CPU_READ_MOSTLY(struct mce_bank[MAX_NR_BANKS], mce_banks_array);
+
+#define ATTR_LEN               16
+/* One object for each MCE bank, shared by all CPUs */
+struct mce_bank_dev {
+	struct device_attribute	attr;			/* device attribute */
+	char			attrname[ATTR_LEN];	/* attribute name */
+	u8			bank;			/* bank number */
+};
+static struct mce_bank_dev mce_bank_devs[MAX_NR_BANKS];
+
 struct mce_vendor_flags mce_flags __read_mostly;
 
 struct mca_config mca_cfg __read_mostly = {
@@ -675,6 +691,7 @@ DEFINE_PER_CPU(unsigned, mce_poll_count);
  */
 bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
 {
+	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
 	bool error_seen = false;
 	struct mce m;
 	int i;
@@ -686,7 +703,7 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
 	if (flags & MCP_TIMESTAMP)
 		m.tsc = rdtsc();
 
-	for (i = 0; i < mca_cfg.banks; i++) {
+	for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
 		if (!mce_banks[i].ctl || !test_bit(i, *b))
 			continue;
 
@@ -788,7 +805,7 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp,
 	char *tmp;
 	int i;
 
-	for (i = 0; i < mca_cfg.banks; i++) {
+	for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
 		m->status = mce_rdmsrl(msr_ops.status(i));
 		if (!(m->status & MCI_STATUS_VAL))
 			continue;
@@ -1068,7 +1085,7 @@ static void mce_clear_state(unsigned long *toclear)
 {
 	int i;
 
-	for (i = 0; i < mca_cfg.banks; i++) {
+	for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
 		if (test_bit(i, toclear))
 			mce_wrmsrl(msr_ops.status(i), 0);
 	}
@@ -1122,10 +1139,11 @@ static void __mc_scan_banks(struct mce *m, struct mce *final,
 			    unsigned long *toclear, unsigned long *valid_banks,
 			    int no_way_out, int *worst)
 {
+	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
 	struct mca_config *cfg = &mca_cfg;
 	int severity, i;
 
-	for (i = 0; i < cfg->banks; i++) {
+	for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
 		__clear_bit(i, toclear);
 		if (!test_bit(i, valid_banks))
 			continue;
@@ -1463,27 +1481,29 @@ int mce_notify_irq(void)
 }
 EXPORT_SYMBOL_GPL(mce_notify_irq);
 
-static int __mcheck_cpu_mce_banks_init(void)
+static void __mcheck_cpu_mce_banks_init(void)
 {
+	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
+	u8 n_banks = this_cpu_read(mce_num_banks);
 	int i;
 
-	mce_banks = kcalloc(MAX_NR_BANKS, sizeof(struct mce_bank), GFP_KERNEL);
-	if (!mce_banks)
-		return -ENOMEM;
-
-	for (i = 0; i < MAX_NR_BANKS; i++) {
+	for (i = 0; i < n_banks; i++) {
 		struct mce_bank *b = &mce_banks[i];
 
+		/*
+		 * Init them all, __mcheck_cpu_apply_quirks() is going to apply
+		 * the required vendor quirks before
+		 * __mcheck_cpu_init_clear_banks() does the final bank setup.
+		 */
 		b->ctl = -1ULL;
 		b->init = 1;
 	}
-	return 0;
 }
 
 /*
  * Initialize Machine Checks for a CPU.
  */
-static int __mcheck_cpu_cap_init(void)
+static void __mcheck_cpu_cap_init(void)
 {
 	u64 cap;
 	u8 b;
@@ -1491,16 +1511,16 @@ static int __mcheck_cpu_cap_init(void)
 	rdmsrl(MSR_IA32_MCG_CAP, cap);
 
 	b = cap & MCG_BANKCNT_MASK;
-	if (WARN_ON_ONCE(b > MAX_NR_BANKS))
+
+	if (b > MAX_NR_BANKS) {
+		pr_warn("CPU%d: Using only %u machine check banks out of %u\n",
+			smp_processor_id(), MAX_NR_BANKS, b);
 		b = MAX_NR_BANKS;
+	}
 
-	mca_cfg.banks = max(mca_cfg.banks, b);
+	this_cpu_write(mce_num_banks, b);
 
-	if (!mce_banks) {
-		int err = __mcheck_cpu_mce_banks_init();
-		if (err)
-			return err;
-	}
+	__mcheck_cpu_mce_banks_init();
 
 	/* Use accurate RIP reporting if available. */
 	if ((cap & MCG_EXT_P) && MCG_EXT_CNT(cap) >= 9)
@@ -1508,8 +1528,6 @@ static int __mcheck_cpu_cap_init(void)
 
 	if (cap & MCG_SER_P)
 		mca_cfg.ser = 1;
-
-	return 0;
 }
 
 static void __mcheck_cpu_init_generic(void)
@@ -1536,9 +1554,10 @@ static void __mcheck_cpu_init_generic(void)
 
 static void __mcheck_cpu_init_clear_banks(void)
 {
+	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
 	int i;
 
-	for (i = 0; i < mca_cfg.banks; i++) {
+	for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
 		struct mce_bank *b = &mce_banks[i];
 
 		if (!b->init)
@@ -1549,6 +1568,33 @@ static void __mcheck_cpu_init_clear_banks(void)
 }
 
 /*
+ * Do a final check to see if there are any unused/RAZ banks.
+ *
+ * This must be done after the banks have been initialized and any quirks have
+ * been applied.
+ *
+ * Do not call this from any user-initiated flows, e.g. CPU hotplug or sysfs.
+ * Otherwise, a user who disables a bank will not be able to re-enable it
+ * without a system reboot.
+ */
+static void __mcheck_cpu_check_banks(void)
+{
+	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
+	u64 msrval;
+	int i;
+
+	for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
+		struct mce_bank *b = &mce_banks[i];
+
+		if (!b->init)
+			continue;
+
+		rdmsrl(msr_ops.ctl(i), msrval);
+		b->init = !!msrval;
+	}
+}
+
+/*
  * During IFU recovery Sandy Bridge -EP4S processors set the RIPV and
  * EIPV bits in MCG_STATUS to zero on the affected logical processor (SDM
  * Vol 3B Table 15-20). But this confuses both the code that determines
@@ -1579,6 +1625,7 @@ static void quirk_sandybridge_ifu(int bank, struct mce *m, struct pt_regs *regs)
 /* Add per CPU specific workarounds here */
 static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
 {
+	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
 	struct mca_config *cfg = &mca_cfg;
 
 	if (c->x86_vendor == X86_VENDOR_UNKNOWN) {
@@ -1588,7 +1635,7 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
 
 	/* This should be disabled by the BIOS, but isn't always */
 	if (c->x86_vendor == X86_VENDOR_AMD) {
-		if (c->x86 == 15 && cfg->banks > 4) {
+		if (c->x86 == 15 && this_cpu_read(mce_num_banks) > 4) {
 			/*
 			 * disable GART TBL walk error reporting, which
 			 * trips off incorrectly with the IOMMU & 3ware
@@ -1607,7 +1654,7 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
 		 * Various K7s with broken bank 0 around. Always disable
 		 * by default.
 		 */
-		if (c->x86 == 6 && cfg->banks > 0)
+		if (c->x86 == 6 && this_cpu_read(mce_num_banks) > 0)
 			mce_banks[0].ctl = 0;
 
 		/*
@@ -1629,7 +1676,7 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
 		 * valid event later, merely don't write CTL0.
 		 */
 
-		if (c->x86 == 6 && c->x86_model < 0x1A && cfg->banks > 0)
+		if (c->x86 == 6 && c->x86_model < 0x1A && this_cpu_read(mce_num_banks) > 0)
 			mce_banks[0].init = 0;
 
 		/*
@@ -1815,7 +1862,9 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c)
 	if (!mce_available(c))
 		return;
 
-	if (__mcheck_cpu_cap_init() < 0 || __mcheck_cpu_apply_quirks(c) < 0) {
+	__mcheck_cpu_cap_init();
+
+	if (__mcheck_cpu_apply_quirks(c) < 0) {
 		mca_cfg.disabled = 1;
 		return;
 	}
@@ -1832,6 +1881,7 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c)
 	__mcheck_cpu_init_generic();
 	__mcheck_cpu_init_vendor(c);
 	__mcheck_cpu_init_clear_banks();
+	__mcheck_cpu_check_banks();
 	__mcheck_cpu_setup_timer();
 }
 
@@ -1863,7 +1913,7 @@ static void __mce_disable_bank(void *arg)
 
 void mce_disable_bank(int bank)
 {
-	if (bank >= mca_cfg.banks) {
+	if (bank >= this_cpu_read(mce_num_banks)) {
 		pr_warn(FW_BUG
 			"Ignoring request to disable invalid MCA bank %d.\n",
 			bank);
@@ -1949,9 +1999,10 @@ int __init mcheck_init(void)
  */
 static void mce_disable_error_reporting(void)
 {
+	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
 	int i;
 
-	for (i = 0; i < mca_cfg.banks; i++) {
+	for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
 		struct mce_bank *b = &mce_banks[i];
 
 		if (b->init)
@@ -2051,26 +2102,47 @@ static struct bus_type mce_subsys = {
 
 DEFINE_PER_CPU(struct device *, mce_device);
 
-static inline struct mce_bank *attr_to_bank(struct device_attribute *attr)
+static inline struct mce_bank_dev *attr_to_bank(struct device_attribute *attr)
 {
-	return container_of(attr, struct mce_bank, attr);
+	return container_of(attr, struct mce_bank_dev, attr);
 }
 
 static ssize_t show_bank(struct device *s, struct device_attribute *attr,
 			 char *buf)
 {
-	return sprintf(buf, "%llx\n", attr_to_bank(attr)->ctl);
+	u8 bank = attr_to_bank(attr)->bank;
+	struct mce_bank *b;
+
+	if (bank >= per_cpu(mce_num_banks, s->id))
+		return -EINVAL;
+
+	b = &per_cpu(mce_banks_array, s->id)[bank];
+
+	if (!b->init)
+		return -ENODEV;
+
+	return sprintf(buf, "%llx\n", b->ctl);
 }
 
 static ssize_t set_bank(struct device *s, struct device_attribute *attr,
 			const char *buf, size_t size)
 {
+	u8 bank = attr_to_bank(attr)->bank;
+	struct mce_bank *b;
 	u64 new;
 
 	if (kstrtou64(buf, 0, &new) < 0)
 		return -EINVAL;
 
-	attr_to_bank(attr)->ctl = new;
+	if (bank >= per_cpu(mce_num_banks, s->id))
+		return -EINVAL;
+
+	b = &per_cpu(mce_banks_array, s->id)[bank];
+
+	if (!b->init)
+		return -ENODEV;
+
+	b->ctl = new;
 	mce_restart();
 
 	return size;
@@ -2185,7 +2257,7 @@ static void mce_device_release(struct device *dev)
 	kfree(dev);
 }
 
-/* Per cpu device init. All of the cpus still share the same ctrl bank: */
+/* Per CPU device init. All of the CPUs still share the same bank device: */
 static int mce_device_create(unsigned int cpu)
 {
 	struct device *dev;
@@ -2217,8 +2289,8 @@ static int mce_device_create(unsigned int cpu)
 		if (err)
 			goto error;
 	}
-	for (j = 0; j < mca_cfg.banks; j++) {
-		err = device_create_file(dev, &mce_banks[j].attr);
+	for (j = 0; j < per_cpu(mce_num_banks, cpu); j++) {
+		err = device_create_file(dev, &mce_bank_devs[j].attr);
 		if (err)
 			goto error2;
 	}
@@ -2228,7 +2300,7 @@ static int mce_device_create(unsigned int cpu)
 	return 0;
 error2:
 	while (--j >= 0)
-		device_remove_file(dev, &mce_banks[j].attr);
+		device_remove_file(dev, &mce_bank_devs[j].attr);
 error:
 	while (--i >= 0)
 		device_remove_file(dev, mce_device_attrs[i]);
@@ -2249,8 +2321,8 @@ static void mce_device_remove(unsigned int cpu)
 	for (i = 0; mce_device_attrs[i]; i++)
 		device_remove_file(dev, mce_device_attrs[i]);
 
-	for (i = 0; i < mca_cfg.banks; i++)
-		device_remove_file(dev, &mce_banks[i].attr);
+	for (i = 0; i < per_cpu(mce_num_banks, cpu); i++)
+		device_remove_file(dev, &mce_bank_devs[i].attr);
 
 	device_unregister(dev);
 	cpumask_clear_cpu(cpu, mce_device_initialized);
@@ -2271,6 +2343,7 @@ static void mce_disable_cpu(void)
 
 static void mce_reenable_cpu(void)
 {
+	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
 	int i;
 
 	if (!mce_available(raw_cpu_ptr(&cpu_info)))
@@ -2278,7 +2351,7 @@ static void mce_reenable_cpu(void)
 
 	if (!cpuhp_tasks_frozen)
 		cmci_reenable();
-	for (i = 0; i < mca_cfg.banks; i++) {
+	for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
 		struct mce_bank *b = &mce_banks[i];
 
 		if (b->init)
@@ -2328,10 +2401,12 @@ static __init void mce_init_banks(void)
 {
 	int i;
 
-	for (i = 0; i < mca_cfg.banks; i++) {
-		struct mce_bank *b = &mce_banks[i];
+	for (i = 0; i < MAX_NR_BANKS; i++) {
+		struct mce_bank_dev *b = &mce_bank_devs[i];
 		struct device_attribute *a = &b->attr;
 
+		b->bank = i;
+
 		sysfs_attr_init(&a->attr);
 		a->attr.name	= b->attrname;
 		snprintf(b->attrname, ATTR_LEN, "bank%d", i);
@@ -2441,22 +2516,16 @@ static int fake_panic_set(void *data, u64 val)
 DEFINE_DEBUGFS_ATTRIBUTE(fake_panic_fops, fake_panic_get, fake_panic_set,
 			 "%llu\n");
 
-static int __init mcheck_debugfs_init(void)
+static void __init mcheck_debugfs_init(void)
 {
-	struct dentry *dmce, *ffake_panic;
+	struct dentry *dmce;
 
 	dmce = mce_get_debugfs_dir();
-	if (!dmce)
-		return -ENOMEM;
-	ffake_panic = debugfs_create_file_unsafe("fake_panic", 0444, dmce,
-						 NULL, &fake_panic_fops);
-	if (!ffake_panic)
-		return -ENOMEM;
-
-	return 0;
+	debugfs_create_file_unsafe("fake_panic", 0444, dmce, NULL,
+				   &fake_panic_fops);
 }
 #else
-static int __init mcheck_debugfs_init(void) { return -EINVAL; }
+static void __init mcheck_debugfs_init(void) { }
 #endif
 
 DEFINE_STATIC_KEY_FALSE(mcsafe_key);
@@ -2464,8 +2533,6 @@ 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);
 
diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c
index 5d108f70f315..1f30117b24ba 100644
--- a/arch/x86/kernel/cpu/mce/inject.c
+++ b/arch/x86/kernel/cpu/mce/inject.c
@@ -645,7 +645,6 @@ static const struct file_operations readme_fops = {
 
 static struct dfs_node {
 	char *name;
-	struct dentry *d;
 	const struct file_operations *fops;
 	umode_t perm;
 } dfs_fls[] = {
@@ -659,49 +658,23 @@ static struct dfs_node {
 	{ .name = "README",	.fops = &readme_fops, .perm = S_IRUSR | S_IRGRP | S_IROTH },
 };
 
-static int __init debugfs_init(void)
+static void __init debugfs_init(void)
 {
 	unsigned int i;
 
 	dfs_inj = debugfs_create_dir("mce-inject", NULL);
-	if (!dfs_inj)
-		return -EINVAL;
-
-	for (i = 0; i < ARRAY_SIZE(dfs_fls); i++) {
-		dfs_fls[i].d = debugfs_create_file(dfs_fls[i].name,
-						    dfs_fls[i].perm,
-						    dfs_inj,
-						    &i_mce,
-						    dfs_fls[i].fops);
-
-		if (!dfs_fls[i].d)
-			goto err_dfs_add;
-	}
-
-	return 0;
-
-err_dfs_add:
-	while (i-- > 0)
-		debugfs_remove(dfs_fls[i].d);
 
-	debugfs_remove(dfs_inj);
-	dfs_inj = NULL;
-
-	return -ENODEV;
+	for (i = 0; i < ARRAY_SIZE(dfs_fls); i++)
+		debugfs_create_file(dfs_fls[i].name, dfs_fls[i].perm, dfs_inj,
+				    &i_mce, dfs_fls[i].fops);
 }
 
 static int __init inject_init(void)
 {
-	int err;
-
 	if (!alloc_cpumask_var(&mce_inject_cpumask, GFP_KERNEL))
 		return -ENOMEM;
 
-	err = debugfs_init();
-	if (err) {
-		free_cpumask_var(mce_inject_cpumask);
-		return err;
-	}
+	debugfs_init();
 
 	register_nmi_handler(NMI_LOCAL, mce_raise_notify, 0, "mce_notify");
 	mce_register_injector_chain(&inject_nb);
diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h
index a34b55baa7aa..43031db429d2 100644
--- a/arch/x86/kernel/cpu/mce/internal.h
+++ b/arch/x86/kernel/cpu/mce/internal.h
@@ -22,17 +22,8 @@ enum severity_level {
 
 extern struct blocking_notifier_head x86_mce_decoder_chain;
 
-#define ATTR_LEN		16
 #define INITIAL_CHECK_INTERVAL	5 * 60 /* 5 minutes */
 
-/* One object for each MCE bank, shared by all CPUs */
-struct mce_bank {
-	u64			ctl;			/* subevents to enable */
-	unsigned char init;				/* initialise bank? */
-	struct device_attribute attr;			/* device attribute */
-	char			attrname[ATTR_LEN];	/* attribute name */
-};
-
 struct mce_evt_llist {
 	struct llist_node llnode;
 	struct mce mce;
@@ -47,7 +38,6 @@ 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);
 
-extern struct mce_bank *mce_banks;
 extern mce_banks_t mce_banks_ce_disabled;
 
 #ifdef CONFIG_X86_MCE_INTEL
@@ -128,7 +118,6 @@ struct mca_config {
 	      bios_cmci_threshold	: 1,
 	      __reserved		: 59;
 
-	u8 banks;
 	s8 bootlog;
 	int tolerant;
 	int monarch_timeout;
@@ -137,6 +126,7 @@ struct mca_config {
 };
 
 extern struct mca_config mca_cfg;
+DECLARE_PER_CPU_READ_MOSTLY(unsigned int, mce_num_banks);
 
 struct mce_vendor_flags {
 	/*
diff --git a/arch/x86/kernel/cpu/mce/severity.c b/arch/x86/kernel/cpu/mce/severity.c
index 2d33a26d257e..210f1f5db5f7 100644
--- a/arch/x86/kernel/cpu/mce/severity.c
+++ b/arch/x86/kernel/cpu/mce/severity.c
@@ -400,21 +400,13 @@ static const struct file_operations severities_coverage_fops = {
 
 static int __init severities_debugfs_init(void)
 {
-	struct dentry *dmce, *fsev;
+	struct dentry *dmce;
 
 	dmce = mce_get_debugfs_dir();
-	if (!dmce)
-		goto err_out;
-
-	fsev = debugfs_create_file("severities-coverage", 0444, dmce, NULL,
-				   &severities_coverage_fops);
-	if (!fsev)
-		goto err_out;
 
+	debugfs_create_file("severities-coverage", 0444, dmce, NULL,
+			    &severities_coverage_fops);
 	return 0;
-
-err_out:
-	return -ENOMEM;
 }
 late_initcall(severities_debugfs_init);
 #endif /* CONFIG_DEBUG_FS */
diff --git a/arch/x86/ras/Kconfig b/arch/x86/ras/Kconfig
index a9c3db125222..9ad6842de4b4 100644
--- a/arch/x86/ras/Kconfig
+++ b/arch/x86/ras/Kconfig
@@ -11,3 +11,13 @@ config RAS_CEC
 
 	  Bear in mind that this is absolutely useless if your platform doesn't
 	  have ECC DIMMs and doesn't have DRAM ECC checking enabled in the BIOS.
+
+config RAS_CEC_DEBUG
+	bool "CEC debugging machinery"
+	default n
+	depends on RAS_CEC
+	help
+	  Add extra files to (debugfs)/ras/cec to test the correctable error
+	  collector feature. "pfn" is a writable file that allows user to
+	  simulate an error in a particular page frame. "array" is a read-only
+	  file that dumps out the current state of all pages logged so far.
diff --git a/drivers/ras/cec.c b/drivers/ras/cec.c
index 673f8a128397..5d545806d930 100644
--- a/drivers/ras/cec.c
+++ b/drivers/ras/cec.c
@@ -1,4 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2017-2019 Borislav Petkov, SUSE Labs.
+ */
 #include <linux/mm.h>
 #include <linux/gfp.h>
 #include <linux/kernel.h>
@@ -37,9 +40,9 @@
  * thus emulate an an LRU-like behavior when deleting elements to free up space
  * in the page.
  *
- * When an element reaches it's max count of count_threshold, we try to poison
- * it by assuming that errors triggered count_threshold times in a single page
- * are excessive and that page shouldn't be used anymore. count_threshold is
+ * When an element reaches it's max count of action_threshold, we try to poison
+ * it by assuming that errors triggered action_threshold times in a single page
+ * are excessive and that page shouldn't be used anymore. action_threshold is
  * initialized to COUNT_MASK which is the maximum.
  *
  * That error event entry causes cec_add_elem() to return !0 value and thus
@@ -122,7 +125,7 @@ static DEFINE_MUTEX(ce_mutex);
 static u64 dfs_pfn;
 
 /* Amount of errors after which we offline */
-static unsigned int count_threshold = COUNT_MASK;
+static u64 action_threshold = COUNT_MASK;
 
 /* Each element "decays" each decay_interval which is 24hrs by default. */
 #define CEC_DECAY_DEFAULT_INTERVAL	24 * 60 * 60	/* 24 hrs */
@@ -276,11 +279,39 @@ static u64 __maybe_unused del_lru_elem(void)
 	return pfn;
 }
 
+static bool sanity_check(struct ce_array *ca)
+{
+	bool ret = false;
+	u64 prev = 0;
+	int i;
+
+	for (i = 0; i < ca->n; i++) {
+		u64 this = PFN(ca->array[i]);
+
+		if (WARN(prev > this, "prev: 0x%016llx <-> this: 0x%016llx\n", prev, this))
+			ret = true;
+
+		prev = this;
+	}
+
+	if (!ret)
+		return ret;
+
+	pr_info("Sanity check dump:\n{ n: %d\n", ca->n);
+	for (i = 0; i < ca->n; i++) {
+		u64 this = PFN(ca->array[i]);
+
+		pr_info(" %03d: [%016llx|%03llx]\n", i, this, FULL_COUNT(ca->array[i]));
+	}
+	pr_info("}\n");
+
+	return ret;
+}
 
 int cec_add_elem(u64 pfn)
 {
 	struct ce_array *ca = &ce_arr;
-	unsigned int to;
+	unsigned int to = 0;
 	int count, ret = 0;
 
 	/*
@@ -294,6 +325,7 @@ int cec_add_elem(u64 pfn)
 
 	ca->ces_entered++;
 
+	/* Array full, free the LRU slot. */
 	if (ca->n == MAX_ELEMS)
 		WARN_ON(!del_lru_elem_unlocked(ca));
 
@@ -306,24 +338,17 @@ int cec_add_elem(u64 pfn)
 			(void *)&ca->array[to],
 			(ca->n - to) * sizeof(u64));
 
-		ca->array[to] = (pfn << PAGE_SHIFT) |
-				(DECAY_MASK << COUNT_BITS) | 1;
-
+		ca->array[to] = pfn << PAGE_SHIFT;
 		ca->n++;
-
-		ret = 0;
-
-		goto decay;
 	}
 
-	count = COUNT(ca->array[to]);
-
-	if (count < count_threshold) {
-		ca->array[to] |= (DECAY_MASK << COUNT_BITS);
-		ca->array[to]++;
+	/* Add/refresh element generation and increment count */
+	ca->array[to] |= DECAY_MASK << COUNT_BITS;
+	ca->array[to]++;
 
-		ret = 0;
-	} else {
+	/* Check action threshold and soft-offline, if reached. */
+	count = COUNT(ca->array[to]);
+	if (count >= action_threshold) {
 		u64 pfn = ca->array[to] >> PAGE_SHIFT;
 
 		if (!pfn_valid(pfn)) {
@@ -338,20 +363,21 @@ int cec_add_elem(u64 pfn)
 		del_elem(ca, to);
 
 		/*
-		 * Return a >0 value to denote that we've reached the offlining
-		 * threshold.
+		 * Return a >0 value to callers, to denote that we've reached
+		 * the offlining threshold.
 		 */
 		ret = 1;
 
 		goto unlock;
 	}
 
-decay:
 	ca->decay_count++;
 
 	if (ca->decay_count >= CLEAN_ELEMS)
 		do_spring_cleaning(ca);
 
+	WARN_ON_ONCE(sanity_check(ca));
+
 unlock:
 	mutex_unlock(&ce_mutex);
 
@@ -369,45 +395,48 @@ static int pfn_set(void *data, u64 val)
 {
 	*(u64 *)data = val;
 
-	return cec_add_elem(val);
+	cec_add_elem(val);
+
+	return 0;
 }
 
 DEFINE_DEBUGFS_ATTRIBUTE(pfn_ops, u64_get, pfn_set, "0x%llx\n");
 
 static int decay_interval_set(void *data, u64 val)
 {
-	*(u64 *)data = val;
-
 	if (val < CEC_DECAY_MIN_INTERVAL)
 		return -EINVAL;
 
 	if (val > CEC_DECAY_MAX_INTERVAL)
 		return -EINVAL;
 
+	*(u64 *)data   = val;
 	decay_interval = val;
 
 	cec_mod_work(decay_interval);
+
 	return 0;
 }
 DEFINE_DEBUGFS_ATTRIBUTE(decay_interval_ops, u64_get, decay_interval_set, "%lld\n");
 
-static int count_threshold_set(void *data, u64 val)
+static int action_threshold_set(void *data, u64 val)
 {
 	*(u64 *)data = val;
 
 	if (val > COUNT_MASK)
 		val = COUNT_MASK;
 
-	count_threshold = val;
+	action_threshold = val;
 
 	return 0;
 }
-DEFINE_DEBUGFS_ATTRIBUTE(count_threshold_ops, u64_get, count_threshold_set, "%lld\n");
+DEFINE_DEBUGFS_ATTRIBUTE(action_threshold_ops, u64_get, action_threshold_set, "%lld\n");
+
+static const char * const bins[] = { "00", "01", "10", "11" };
 
 static int array_dump(struct seq_file *m, void *v)
 {
 	struct ce_array *ca = &ce_arr;
-	u64 prev = 0;
 	int i;
 
 	mutex_lock(&ce_mutex);
@@ -416,11 +445,8 @@ static int array_dump(struct seq_file *m, void *v)
 	for (i = 0; i < ca->n; i++) {
 		u64 this = PFN(ca->array[i]);
 
-		seq_printf(m, " %03d: [%016llx|%03llx]\n", i, this, FULL_COUNT(ca->array[i]));
-
-		WARN_ON(prev > this);
-
-		prev = this;
+		seq_printf(m, " %3d: [%016llx|%s|%03llx]\n",
+			   i, this, bins[DECAY(ca->array[i])], COUNT(ca->array[i]));
 	}
 
 	seq_printf(m, "}\n");
@@ -433,7 +459,7 @@ static int array_dump(struct seq_file *m, void *v)
 	seq_printf(m, "Decay interval: %lld seconds\n", decay_interval);
 	seq_printf(m, "Decays: %lld\n", ca->decays_done);
 
-	seq_printf(m, "Action threshold: %d\n", count_threshold);
+	seq_printf(m, "Action threshold: %lld\n", action_threshold);
 
 	mutex_unlock(&ce_mutex);
 
@@ -463,18 +489,6 @@ static int __init create_debugfs_nodes(void)
 		return -1;
 	}
 
-	pfn = debugfs_create_file("pfn", S_IRUSR | S_IWUSR, d, &dfs_pfn, &pfn_ops);
-	if (!pfn) {
-		pr_warn("Error creating pfn debugfs node!\n");
-		goto err;
-	}
-
-	array = debugfs_create_file("array", S_IRUSR, d, NULL, &array_ops);
-	if (!array) {
-		pr_warn("Error creating array debugfs node!\n");
-		goto err;
-	}
-
 	decay = debugfs_create_file("decay_interval", S_IRUSR | S_IWUSR, d,
 				    &decay_interval, &decay_interval_ops);
 	if (!decay) {
@@ -482,13 +496,27 @@ static int __init create_debugfs_nodes(void)
 		goto err;
 	}
 
-	count = debugfs_create_file("count_threshold", S_IRUSR | S_IWUSR, d,
-				    &count_threshold, &count_threshold_ops);
+	count = debugfs_create_file("action_threshold", S_IRUSR | S_IWUSR, d,
+				    &action_threshold, &action_threshold_ops);
 	if (!count) {
-		pr_warn("Error creating count_threshold debugfs node!\n");
+		pr_warn("Error creating action_threshold debugfs node!\n");
+		goto err;
+	}
+
+	if (!IS_ENABLED(CONFIG_RAS_CEC_DEBUG))
+		return 0;
+
+	pfn = debugfs_create_file("pfn", S_IRUSR | S_IWUSR, d, &dfs_pfn, &pfn_ops);
+	if (!pfn) {
+		pr_warn("Error creating pfn debugfs node!\n");
 		goto err;
 	}
 
+	array = debugfs_create_file("array", S_IRUSR, d, NULL, &array_ops);
+	if (!array) {
+		pr_warn("Error creating array debugfs node!\n");
+		goto err;
+	}
 
 	return 0;
 
@@ -509,8 +537,10 @@ void __init cec_init(void)
 		return;
 	}
 
-	if (create_debugfs_nodes())
+	if (create_debugfs_nodes()) {
+		free_page((unsigned long)ce_arr.array);
 		return;
+	}
 
 	INIT_DELAYED_WORK(&cec_work, cec_work_fn);
 	schedule_delayed_work(&cec_work, CEC_DECAY_DEFAULT_INTERVAL);