Merge tag 'ras-core-2020-06-12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 RAS updates from Thomas Gleixner:
 "RAS updates from Borislav Petkov:

   - Unmap a whole guest page if an MCE is encountered in it to avoid
     follow-on MCEs leading to the guest crashing, by Tony Luck.

     This change collided with the entry changes and the merge
     resolution would have been rather unpleasant. To avoid that the
     entry branch was merged in before applying this. The resulting code
     did not change over the rebase.

   - AMD MCE error thresholding machinery cleanup and hotplug
     sanitization, by Thomas Gleixner.

   - Change the MCE notifiers to denote whether they have handled the
     error and not break the chain early by returning NOTIFY_STOP, thus
     giving the opportunity for the later handlers in the chain to see
     it. By Tony Luck.

   - Add AMD family 0x17, models 0x60-6f support, by Alexander Monakov.

   - Last but not least, the usual round of fixes and improvements"

* tag 'ras-core-2020-06-12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (23 commits)
  x86/mce/dev-mcelog: Fix -Wstringop-truncation warning about strncpy()
  x86/{mce,mm}: Unmap the entire page if the whole page is affected and poisoned
  EDAC/amd64: Add AMD family 17h model 60h PCI IDs
  hwmon: (k10temp) Add AMD family 17h model 60h PCI match
  x86/amd_nb: Add AMD family 17h model 60h PCI IDs
  x86/mcelog: Add compat_ioctl for 32-bit mcelog support
  x86/mce: Drop bogus comment about mce.kflags
  x86/mce: Fixup exception only for the correct MCEs
  EDAC: Drop the EDAC report status checks
  x86/mce: Add mce=print_all option
  x86/mce: Change default MCE logger to check mce->kflags
  x86/mce: Fix all mce notifiers to update the mce->kflags bitmask
  x86/mce: Add a struct mce.kflags field
  x86/mce: Convert the CEC to use the MCE notifier
  x86/mce: Rename "first" function as "early"
  x86/mce/amd, edac: Remove report_gart_errors
  x86/mce/amd: Make threshold bank setting hotplug robust
  x86/mce/amd: Cleanup threshold device remove path
  x86/mce/amd: Straighten CPU hotplug path
  x86/mce/amd: Sanitize thresholding device creation hotplug path
  ...

6 files changed, 198 insertions, 166 deletions

diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index b6b3297851f3..18f6b7c4bd79 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -18,9 +18,11 @@
 #define PCI_DEVICE_ID_AMD_17H_ROOT	0x1450
 #define PCI_DEVICE_ID_AMD_17H_M10H_ROOT	0x15d0
 #define PCI_DEVICE_ID_AMD_17H_M30H_ROOT	0x1480
+#define PCI_DEVICE_ID_AMD_17H_M60H_ROOT	0x1630
 #define PCI_DEVICE_ID_AMD_17H_DF_F4	0x1464
 #define PCI_DEVICE_ID_AMD_17H_M10H_DF_F4 0x15ec
 #define PCI_DEVICE_ID_AMD_17H_M30H_DF_F4 0x1494
+#define PCI_DEVICE_ID_AMD_17H_M60H_DF_F4 0x144c
 #define PCI_DEVICE_ID_AMD_17H_M70H_DF_F4 0x1444
 #define PCI_DEVICE_ID_AMD_19H_DF_F4	0x1654
 
@@ -33,6 +35,7 @@ static const struct pci_device_id amd_root_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_ROOT) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_ROOT) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_ROOT) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M60H_ROOT) },
 	{}
 };
 
@@ -50,6 +53,7 @@ static const struct pci_device_id amd_nb_misc_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F3) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F3) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_DF_F3) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M60H_DF_F3) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F3) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_DF_F3) },
@@ -65,6 +69,7 @@ static const struct pci_device_id amd_nb_link_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F4) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F4) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_DF_F4) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M60H_DF_F4) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F4) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_DF_F4) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) },
diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index a906d68a18a2..99be063fcb1b 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -192,7 +192,12 @@ EXPORT_SYMBOL_GPL(smca_banks);
 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 */
+
+/*
+ * A list of the banks enabled on each logical CPU. Controls which respective
+ * descriptors to initialize later in mce_threshold_create_device().
+ */
+static DEFINE_PER_CPU(unsigned int, bank_map);
 
 /* Map of banks that have more than MCA_MISC0 available. */
 static DEFINE_PER_CPU(u32, smca_misc_banks_map);
@@ -381,6 +386,10 @@ static void threshold_restart_bank(void *_tr)
 	struct thresh_restart *tr = _tr;
 	u32 hi, lo;
 
+	/* sysfs write might race against an offline operation */
+	if (this_cpu_read(threshold_banks))
+		return;
+
 	rdmsr(tr->b->address, lo, hi);
 
 	if (tr->b->threshold_limit < (hi & THRESHOLD_MAX))
@@ -568,14 +577,19 @@ 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)
+	    bank_type == SMCA_IF && XEC(m->status, 0x3f) == 10)
 		return true;
 
+	/* NB GART TLB error reporting is disabled by default. */
+	if (c->x86 < 0x17) {
+		if (m->bank == 4 && XEC(m->status, 0x1f) == 0x5)
+			return true;
+	}
+
 	return false;
 }
 
@@ -1015,13 +1029,22 @@ static void log_and_reset_block(struct threshold_block *block)
 static void amd_threshold_interrupt(void)
 {
 	struct threshold_block *first_block = NULL, *block = NULL, *tmp = NULL;
+	struct threshold_bank **bp = this_cpu_read(threshold_banks);
 	unsigned int bank, cpu = smp_processor_id();
 
+	/*
+	 * Validate that the threshold bank has been initialized already. The
+	 * handler is installed at boot time, but on a hotplug event the
+	 * interrupt might fire before the data has been initialized.
+	 */
+	if (!bp)
+		return;
+
 	for (bank = 0; bank < this_cpu_read(mce_num_banks); ++bank) {
 		if (!(per_cpu(bank_map, cpu) & (1 << bank)))
 			continue;
 
-		first_block = per_cpu(threshold_banks, cpu)[bank]->blocks;
+		first_block = bp[bank]->blocks;
 		if (!first_block)
 			continue;
 
@@ -1070,7 +1093,8 @@ store_interrupt_enable(struct threshold_block *b, const char *buf, size_t size)
 	memset(&tr, 0, sizeof(tr));
 	tr.b		= b;
 
-	smp_call_function_single(b->cpu, threshold_restart_bank, &tr, 1);
+	if (smp_call_function_single(b->cpu, threshold_restart_bank, &tr, 1))
+		return -ENODEV;
 
 	return size;
 }
@@ -1094,7 +1118,8 @@ store_threshold_limit(struct threshold_block *b, const char *buf, size_t size)
 	b->threshold_limit = new;
 	tr.b = b;
 
-	smp_call_function_single(b->cpu, threshold_restart_bank, &tr, 1);
+	if (smp_call_function_single(b->cpu, threshold_restart_bank, &tr, 1))
+		return -ENODEV;
 
 	return size;
 }
@@ -1103,7 +1128,9 @@ static ssize_t show_error_count(struct threshold_block *b, char *buf)
 {
 	u32 lo, hi;
 
-	rdmsr_on_cpu(b->cpu, b->address, &lo, &hi);
+	/* CPU might be offline by now */
+	if (rdmsr_on_cpu(b->cpu, b->address, &lo, &hi))
+		return -ENODEV;
 
 	return sprintf(buf, "%u\n", ((hi & THRESHOLD_MAX) -
 				     (THRESHOLD_MAX - b->threshold_limit)));
@@ -1208,10 +1235,10 @@ static int allocate_threshold_blocks(unsigned int cpu, struct threshold_bank *tb
 	u32 low, high;
 	int err;
 
-	if ((bank >= per_cpu(mce_num_banks, cpu)) || (block >= NR_BLOCKS))
+	if ((bank >= this_cpu_read(mce_num_banks)) || (block >= NR_BLOCKS))
 		return 0;
 
-	if (rdmsr_safe_on_cpu(cpu, address, &low, &high))
+	if (rdmsr_safe(address, &low, &high))
 		return 0;
 
 	if (!(high & MASK_VALID_HI)) {
@@ -1246,6 +1273,7 @@ static int allocate_threshold_blocks(unsigned int cpu, struct threshold_bank *tb
 
 	INIT_LIST_HEAD(&b->miscj);
 
+	/* This is safe as @tb is not visible yet */
 	if (tb->blocks)
 		list_add(&b->miscj, &tb->blocks->miscj);
 	else
@@ -1266,13 +1294,12 @@ recurse:
 	if (b)
 		kobject_uevent(&b->kobj, KOBJ_ADD);
 
-	return err;
+	return 0;
 
 out_free:
 	if (b) {
-		kobject_put(&b->kobj);
 		list_del(&b->miscj);
-		kfree(b);
+		kobject_put(&b->kobj);
 	}
 	return err;
 }
@@ -1301,9 +1328,10 @@ static int __threshold_add_blocks(struct threshold_bank *b)
 	return err;
 }
 
-static int threshold_create_bank(unsigned int cpu, unsigned int bank)
+static int threshold_create_bank(struct threshold_bank **bp, unsigned int cpu,
+				 unsigned int bank)
 {
-	struct device *dev = per_cpu(mce_device, cpu);
+	struct device *dev = this_cpu_read(mce_device);
 	struct amd_northbridge *nb = NULL;
 	struct threshold_bank *b = NULL;
 	const char *name = get_name(bank, NULL);
@@ -1323,7 +1351,7 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank)
 			if (err)
 				goto out;
 
-			per_cpu(threshold_banks, cpu)[bank] = b;
+			bp[bank] = b;
 			refcount_inc(&b->cpus);
 
 			err = __threshold_add_blocks(b);
@@ -1338,6 +1366,7 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank)
 		goto out;
 	}
 
+	/* Associate the bank with the per-CPU MCE device */
 	b->kobj = kobject_create_and_add(name, &dev->kobj);
 	if (!b->kobj) {
 		err = -EINVAL;
@@ -1345,6 +1374,7 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank)
 	}
 
 	if (is_shared_bank(bank)) {
+		b->shared = 1;
 		refcount_set(&b->cpus, 1);
 
 		/* nb is already initialized, see above */
@@ -1356,16 +1386,16 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank)
 
 	err = allocate_threshold_blocks(cpu, b, bank, 0, msr_ops.misc(bank));
 	if (err)
-		goto out_free;
-
-	per_cpu(threshold_banks, cpu)[bank] = b;
+		goto out_kobj;
 
+	bp[bank] = b;
 	return 0;
 
- out_free:
+out_kobj:
+	kobject_put(b->kobj);
+out_free:
 	kfree(b);
-
- out:
+out:
 	return err;
 }
 
@@ -1374,21 +1404,16 @@ static void threshold_block_release(struct kobject *kobj)
 	kfree(to_block(kobj));
 }
 
-static void deallocate_threshold_block(unsigned int cpu, unsigned int bank)
+static void deallocate_threshold_blocks(struct threshold_bank *bank)
 {
-	struct threshold_block *pos = NULL;
-	struct threshold_block *tmp = NULL;
-	struct threshold_bank *head = per_cpu(threshold_banks, cpu)[bank];
+	struct threshold_block *pos, *tmp;
 
-	if (!head)
-		return;
-
-	list_for_each_entry_safe(pos, tmp, &head->blocks->miscj, miscj) {
+	list_for_each_entry_safe(pos, tmp, &bank->blocks->miscj, miscj) {
 		list_del(&pos->miscj);
 		kobject_put(&pos->kobj);
 	}
 
-	kobject_put(&head->blocks->kobj);
+	kobject_put(&bank->blocks->kobj);
 }
 
 static void __threshold_remove_blocks(struct threshold_bank *b)
@@ -1402,122 +1427,102 @@ static void __threshold_remove_blocks(struct threshold_bank *b)
 		kobject_del(&pos->kobj);
 }
 
-static void threshold_remove_bank(unsigned int cpu, int bank)
+static void threshold_remove_bank(struct threshold_bank *bank)
 {
 	struct amd_northbridge *nb;
-	struct threshold_bank *b;
 
-	b = per_cpu(threshold_banks, cpu)[bank];
-	if (!b)
-		return;
+	if (!bank->blocks)
+		goto out_free;
 
-	if (!b->blocks)
-		goto free_out;
+	if (!bank->shared)
+		goto out_dealloc;
 
-	if (is_shared_bank(bank)) {
-		if (!refcount_dec_and_test(&b->cpus)) {
-			__threshold_remove_blocks(b);
-			per_cpu(threshold_banks, cpu)[bank] = NULL;
-			return;
-		} else {
-			/*
-			 * the last CPU on this node using the shared bank is
-			 * going away, remove that bank now.
-			 */
-			nb = node_to_amd_nb(amd_get_nb_id(cpu));
-			nb->bank4 = NULL;
-		}
+	if (!refcount_dec_and_test(&bank->cpus)) {
+		__threshold_remove_blocks(bank);
+		return;
+	} else {
+		/*
+		 * The last CPU on this node using the shared bank is going
+		 * away, remove that bank now.
+		 */
+		nb = node_to_amd_nb(amd_get_nb_id(smp_processor_id()));
+		nb->bank4 = NULL;
 	}
 
-	deallocate_threshold_block(cpu, bank);
+out_dealloc:
+	deallocate_threshold_blocks(bank);
 
-free_out:
-	kobject_del(b->kobj);
-	kobject_put(b->kobj);
-	kfree(b);
-	per_cpu(threshold_banks, cpu)[bank] = NULL;
+out_free:
+	kobject_put(bank->kobj);
+	kfree(bank);
 }
 
 int mce_threshold_remove_device(unsigned int cpu)
 {
-	unsigned int bank;
+	struct threshold_bank **bp = this_cpu_read(threshold_banks);
+	unsigned int bank, numbanks = this_cpu_read(mce_num_banks);
 
-	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);
+	if (!bp)
+		return 0;
+
+	/*
+	 * Clear the pointer before cleaning up, so that the interrupt won't
+	 * touch anything of this.
+	 */
+	this_cpu_write(threshold_banks, NULL);
+
+	for (bank = 0; bank < numbanks; bank++) {
+		if (bp[bank]) {
+			threshold_remove_bank(bp[bank]);
+			bp[bank] = NULL;
+		}
 	}
-	kfree(per_cpu(threshold_banks, cpu));
-	per_cpu(threshold_banks, cpu) = NULL;
+	kfree(bp);
 	return 0;
 }
 
-/* create dir/files for all valid threshold banks */
+/**
+ * mce_threshold_create_device - Create the per-CPU MCE threshold device
+ * @cpu:	The plugged in CPU
+ *
+ * Create directories and files for all valid threshold banks.
+ *
+ * This is invoked from the CPU hotplug callback which was installed in
+ * mcheck_init_device(). The invocation happens in context of the hotplug
+ * thread running on @cpu.  The callback is invoked on all CPUs which are
+ * online when the callback is installed or during a real hotplug event.
+ */
 int mce_threshold_create_device(unsigned int cpu)
 {
-	unsigned int bank;
+	unsigned int numbanks, bank;
 	struct threshold_bank **bp;
-	int err = 0;
+	int err;
 
-	bp = per_cpu(threshold_banks, cpu);
+	if (!mce_flags.amd_threshold)
+		return 0;
+
+	bp = this_cpu_read(threshold_banks);
 	if (bp)
 		return 0;
 
-	bp = kcalloc(per_cpu(mce_num_banks, cpu), sizeof(struct threshold_bank *),
-		     GFP_KERNEL);
+	numbanks = this_cpu_read(mce_num_banks);
+	bp = kcalloc(numbanks, sizeof(*bp), GFP_KERNEL);
 	if (!bp)
 		return -ENOMEM;
 
-	per_cpu(threshold_banks, cpu) = bp;
-
-	for (bank = 0; bank < per_cpu(mce_num_banks, cpu); ++bank) {
-		if (!(per_cpu(bank_map, cpu) & (1 << bank)))
+	for (bank = 0; bank < numbanks; ++bank) {
+		if (!(this_cpu_read(bank_map) & (1 << bank)))
 			continue;
-		err = threshold_create_bank(cpu, bank);
+		err = threshold_create_bank(bp, cpu, bank);
 		if (err)
-			goto err;
-	}
-	return err;
-err:
-	mce_threshold_remove_device(cpu);
-	return err;
-}
-
-static __init int threshold_init_device(void)
-{
-	unsigned lcpu = 0;
-
-	/* to hit CPUs online before the notifier is up */
-	for_each_online_cpu(lcpu) {
-		int err = mce_threshold_create_device(lcpu);
-
-		if (err)
-			return err;
+			goto out_err;
 	}
+	this_cpu_write(threshold_banks, bp);
 
 	if (thresholding_irq_en)
 		mce_threshold_vector = amd_threshold_interrupt;
-
 	return 0;
+out_err:
+	mce_threshold_remove_device(cpu);
+	return err;
 }
-/*
- * there are 3 funcs which need to be _initcalled in a logic sequence:
- * 1. xen_late_init_mcelog
- * 2. mcheck_init_device
- * 3. threshold_init_device
- *
- * xen_late_init_mcelog must register xen_mce_chrdev_device before
- * native mce_chrdev_device registration if running under xen platform;
- *
- * mcheck_init_device should be inited before threshold_init_device to
- * initialize mce_device, otherwise a NULL ptr dereference will cause panic.
- *
- * so we use following _initcalls
- * 1. device_initcall(xen_late_init_mcelog);
- * 2. device_initcall_sync(mcheck_init_device);
- * 3. late_initcall(threshold_init_device);
- *
- * when running under xen, the initcall order is 1,2,3;
- * on baremetal, we skip 1 and we do only 2 and 3.
- */
-late_initcall(threshold_init_device);
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index b9cb381b4019..ce9120c4f740 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -160,29 +160,17 @@ void mce_log(struct mce *m)
 }
 EXPORT_SYMBOL_GPL(mce_log);
 
-/*
- * We run the default notifier if we have only the UC, the first and the
- * default notifier registered. I.e., the mandatory NUM_DEFAULT_NOTIFIERS
- * notifiers registered on the chain.
- */
-#define NUM_DEFAULT_NOTIFIERS	3
-static atomic_t num_notifiers;
-
 void mce_register_decode_chain(struct notifier_block *nb)
 {
 	if (WARN_ON(nb->priority > MCE_PRIO_MCELOG && nb->priority < MCE_PRIO_EDAC))
 		return;
 
-	atomic_inc(&num_notifiers);
-
 	blocking_notifier_chain_register(&x86_mce_decoder_chain, nb);
 }
 EXPORT_SYMBOL_GPL(mce_register_decode_chain);
 
 void mce_unregister_decode_chain(struct notifier_block *nb)
 {
-	atomic_dec(&num_notifiers);
-
 	blocking_notifier_chain_unregister(&x86_mce_decoder_chain, nb);
 }
 EXPORT_SYMBOL_GPL(mce_unregister_decode_chain);
@@ -265,6 +253,7 @@ static void __print_mce(struct mce *m)
 	}
 
 	pr_cont("\n");
+
 	/*
 	 * Note this output is parsed by external tools and old fields
 	 * should not be changed.
@@ -531,6 +520,14 @@ bool mce_is_memory_error(struct mce *m)
 }
 EXPORT_SYMBOL_GPL(mce_is_memory_error);
 
+static bool whole_page(struct mce *m)
+{
+	if (!mca_cfg.ser || !(m->status & MCI_STATUS_MISCV))
+		return true;
+
+	return MCI_MISC_ADDR_LSB(m->misc) >= PAGE_SHIFT;
+}
+
 bool mce_is_correctable(struct mce *m)
 {
 	if (m->cpuvendor == X86_VENDOR_AMD && m->status & MCI_STATUS_DEFERRED)
@@ -546,22 +543,7 @@ bool mce_is_correctable(struct mce *m)
 }
 EXPORT_SYMBOL_GPL(mce_is_correctable);
 
-static bool cec_add_mce(struct mce *m)
-{
-	if (!m)
-		return false;
-
-	/* We eat only correctable DRAM errors with usable addresses. */
-	if (mce_is_memory_error(m) &&
-	    mce_is_correctable(m)  &&
-	    mce_usable_address(m))
-		if (!cec_add_elem(m->addr >> PAGE_SHIFT))
-			return true;
-
-	return false;
-}
-
-static int mce_first_notifier(struct notifier_block *nb, unsigned long val,
+static int mce_early_notifier(struct notifier_block *nb, unsigned long val,
 			      void *data)
 {
 	struct mce *m = (struct mce *)data;
@@ -569,9 +551,6 @@ static int mce_first_notifier(struct notifier_block *nb, unsigned long val,
 	if (!m)
 		return NOTIFY_DONE;
 
-	if (cec_add_mce(m))
-		return NOTIFY_STOP;
-
 	/* Emit the trace record: */
 	trace_mce_record(m);
 
@@ -582,9 +561,9 @@ static int mce_first_notifier(struct notifier_block *nb, unsigned long val,
 	return NOTIFY_DONE;
 }
 
-static struct notifier_block first_nb = {
-	.notifier_call	= mce_first_notifier,
-	.priority	= MCE_PRIO_FIRST,
+static struct notifier_block early_nb = {
+	.notifier_call	= mce_early_notifier,
+	.priority	= MCE_PRIO_EARLY,
 };
 
 static int uc_decode_notifier(struct notifier_block *nb, unsigned long val,
@@ -601,8 +580,10 @@ static int uc_decode_notifier(struct notifier_block *nb, unsigned long val,
 		return NOTIFY_DONE;
 
 	pfn = mce->addr >> PAGE_SHIFT;
-	if (!memory_failure(pfn, 0))
-		set_mce_nospec(pfn);
+	if (!memory_failure(pfn, 0)) {
+		set_mce_nospec(pfn, whole_page(mce));
+		mce->kflags |= MCE_HANDLED_UC;
+	}
 
 	return NOTIFY_OK;
 }
@@ -620,10 +601,8 @@ static int mce_default_notifier(struct notifier_block *nb, unsigned long val,
 	if (!m)
 		return NOTIFY_DONE;
 
-	if (atomic_read(&num_notifiers) > NUM_DEFAULT_NOTIFIERS)
-		return NOTIFY_DONE;
-
-	__print_mce(m);
+	if (mca_cfg.print_all || !m->kflags)
+		__print_mce(m);
 
 	return NOTIFY_DONE;
 }
@@ -1202,11 +1181,12 @@ static void kill_me_maybe(struct callback_head *cb)
 	int flags = MF_ACTION_REQUIRED;
 
 	pr_err("Uncorrected hardware memory error in user-access at %llx", p->mce_addr);
-	if (!(p->mce_status & MCG_STATUS_RIPV))
+
+	if (!p->mce_ripv)
 		flags |= MF_MUST_KILL;
 
 	if (!memory_failure(p->mce_addr >> PAGE_SHIFT, flags)) {
-		set_mce_nospec(p->mce_addr >> PAGE_SHIFT);
+		set_mce_nospec(p->mce_addr >> PAGE_SHIFT, p->mce_whole_page);
 		return;
 	}
 
@@ -1360,14 +1340,26 @@ void noinstr do_machine_check(struct pt_regs *regs)
 		BUG_ON(!on_thread_stack() || !user_mode(regs));
 
 		current->mce_addr = m.addr;
-		current->mce_status = m.mcgstatus;
+		current->mce_ripv = !!(m.mcgstatus & MCG_STATUS_RIPV);
+		current->mce_whole_page = whole_page(&m);
 		current->mce_kill_me.func = kill_me_maybe;
 		if (kill_it)
 			current->mce_kill_me.func = kill_me_now;
 		task_work_add(current, &current->mce_kill_me, true);
 	} else {
-		if (!fixup_exception(regs, X86_TRAP_MC, 0, 0))
-			mce_panic("Failed kernel mode recovery", &m, msg);
+		/*
+		 * Handle an MCE which has happened in kernel space but from
+		 * which the kernel can recover: ex_has_fault_handler() has
+		 * already verified that the rIP at which the error happened is
+		 * a rIP from which the kernel can recover (by jumping to
+		 * recovery code specified in _ASM_EXTABLE_FAULT()) and the
+		 * corresponding exception handler which would do that is the
+		 * proper one.
+		 */
+		if (m.kflags & MCE_IN_KERNEL_RECOV) {
+			if (!fixup_exception(regs, X86_TRAP_MC, 0, 0))
+				mce_panic("Failed kernel mode recovery", &m, msg);
+		}
 	}
 }
 EXPORT_SYMBOL_GPL(do_machine_check);
@@ -1758,6 +1750,7 @@ static void __mcheck_cpu_init_early(struct cpuinfo_x86 *c)
 		mce_flags.overflow_recov = !!cpu_has(c, X86_FEATURE_OVERFLOW_RECOV);
 		mce_flags.succor	 = !!cpu_has(c, X86_FEATURE_SUCCOR);
 		mce_flags.smca		 = !!cpu_has(c, X86_FEATURE_SMCA);
+		mce_flags.amd_threshold	 = 1;
 
 		if (mce_flags.smca) {
 			msr_ops.ctl	= smca_ctl_reg;
@@ -2055,6 +2048,7 @@ void mce_disable_bank(int bank)
  * mce=no_cmci Disables CMCI
  * mce=no_lmce Disables LMCE
  * mce=dont_log_ce Clears corrected events silently, no log created for CEs.
+ * mce=print_all Print all machine check logs to console
  * mce=ignore_ce Disables polling and CMCI, corrected events are not cleared.
  * mce=TOLERANCELEVEL[,monarchtimeout] (number, see above)
  *	monarchtimeout is how long to wait for other CPUs on machine
@@ -2083,6 +2077,8 @@ static int __init mcheck_enable(char *str)
 		cfg->lmce_disabled = 1;
 	else if (!strcmp(str, "dont_log_ce"))
 		cfg->dont_log_ce = true;
+	else if (!strcmp(str, "print_all"))
+		cfg->print_all = true;
 	else if (!strcmp(str, "ignore_ce"))
 		cfg->ignore_ce = true;
 	else if (!strcmp(str, "bootlog") || !strcmp(str, "nobootlog"))
@@ -2105,7 +2101,7 @@ __setup("mce", mcheck_enable);
 int __init mcheck_init(void)
 {
 	mcheck_intel_therm_init();
-	mce_register_decode_chain(&first_nb);
+	mce_register_decode_chain(&early_nb);
 	mce_register_decode_chain(&mce_uc_nb);
 	mce_register_decode_chain(&mce_default_nb);
 	mcheck_vendor_init_severity();
@@ -2349,6 +2345,7 @@ static ssize_t store_int_with_restart(struct device *s,
 static DEVICE_INT_ATTR(tolerant, 0644, mca_cfg.tolerant);
 static DEVICE_INT_ATTR(monarch_timeout, 0644, mca_cfg.monarch_timeout);
 static DEVICE_BOOL_ATTR(dont_log_ce, 0644, mca_cfg.dont_log_ce);
+static DEVICE_BOOL_ATTR(print_all, 0644, mca_cfg.print_all);
 
 static struct dev_ext_attribute dev_attr_check_interval = {
 	__ATTR(check_interval, 0644, device_show_int, store_int_with_restart),
@@ -2373,6 +2370,7 @@ static struct device_attribute *mce_device_attrs[] = {
 #endif
 	&dev_attr_monarch_timeout.attr,
 	&dev_attr_dont_log_ce.attr,
+	&dev_attr_print_all.attr,
 	&dev_attr_ignore_ce.attr,
 	&dev_attr_cmci_disabled.attr,
 	NULL
@@ -2545,6 +2543,13 @@ static __init void mce_init_banks(void)
 	}
 }
 
+/*
+ * When running on XEN, this initcall is ordered against the XEN mcelog
+ * initcall:
+ *
+ *   device_initcall(xen_late_init_mcelog);
+ *   device_initcall_sync(mcheck_init_device);
+ */
 static __init int mcheck_init_device(void)
 {
 	int err;
@@ -2576,6 +2581,10 @@ static __init int mcheck_init_device(void)
 	if (err)
 		goto err_out_mem;
 
+	/*
+	 * Invokes mce_cpu_online() on all CPUs which are online when
+	 * the state is installed.
+	 */
 	err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/mce:online",
 				mce_cpu_online, mce_cpu_pre_down);
 	if (err < 0)
@@ -2665,7 +2674,6 @@ static int __init mcheck_late_init(void)
 		static_branch_inc(&mcsafe_key);
 
 	mcheck_debugfs_init();
-	cec_init();
 
 	/*
 	 * Flush out everything that has been logged during early boot, now that
diff --git a/arch/x86/kernel/cpu/mce/dev-mcelog.c b/arch/x86/kernel/cpu/mce/dev-mcelog.c
index d089567a9ce8..43c466020ed5 100644
--- a/arch/x86/kernel/cpu/mce/dev-mcelog.c
+++ b/arch/x86/kernel/cpu/mce/dev-mcelog.c
@@ -39,6 +39,9 @@ static int dev_mce_log(struct notifier_block *nb, unsigned long val,
 	struct mce *mce = (struct mce *)data;
 	unsigned int entry;
 
+	if (mce->kflags & MCE_HANDLED_CEC)
+		return NOTIFY_DONE;
+
 	mutex_lock(&mce_chrdev_read_mutex);
 
 	entry = mcelog->next;
@@ -56,6 +59,7 @@ static int dev_mce_log(struct notifier_block *nb, unsigned long val,
 
 	memcpy(mcelog->entry + entry, mce, sizeof(struct mce));
 	mcelog->entry[entry].finished = 1;
+	mcelog->entry[entry].kflags = 0;
 
 	/* wake processes polling /dev/mcelog */
 	wake_up_interruptible(&mce_chrdev_wait);
@@ -63,6 +67,7 @@ static int dev_mce_log(struct notifier_block *nb, unsigned long val,
 unlock:
 	mutex_unlock(&mce_chrdev_read_mutex);
 
+	mce->kflags |= MCE_HANDLED_MCELOG;
 	return NOTIFY_OK;
 }
 
@@ -324,6 +329,7 @@ static const struct file_operations mce_chrdev_ops = {
 	.write			= mce_chrdev_write,
 	.poll			= mce_chrdev_poll,
 	.unlocked_ioctl		= mce_chrdev_ioctl,
+	.compat_ioctl		= compat_ptr_ioctl,
 	.llseek			= no_llseek,
 };
 
@@ -343,7 +349,7 @@ static __init int dev_mcelog_init_device(void)
 	if (!mcelog)
 		return -ENOMEM;
 
-	strncpy(mcelog->signature, MCE_LOG_SIGNATURE, sizeof(mcelog->signature));
+	memcpy(mcelog->signature, MCE_LOG_SIGNATURE, sizeof(mcelog->signature));
 	mcelog->len = mce_log_len;
 	mcelog->recordlen = sizeof(struct mce);
 
diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h
index b74ca4a28c66..6473070b5da4 100644
--- a/arch/x86/kernel/cpu/mce/internal.h
+++ b/arch/x86/kernel/cpu/mce/internal.h
@@ -119,6 +119,7 @@ struct mca_config {
 	bool dont_log_ce;
 	bool cmci_disabled;
 	bool ignore_ce;
+	bool print_all;
 
 	__u64 lmce_disabled		: 1,
 	      disabled			: 1,
@@ -148,7 +149,7 @@ struct mce_vendor_flags {
 	 * Recovery. It indicates support for data poisoning in HW and deferred
 	 * error interrupts.
 	 */
-	      succor		: 1,
+	succor			: 1,
 
 	/*
 	 * (AMD) SMCA: This bit indicates support for Scalable MCA which expands
@@ -156,9 +157,12 @@ struct mce_vendor_flags {
 	 * banks. Also, to accommodate the new banks and registers, the MCA
 	 * register space is moved to a new MSR range.
 	 */
-	      smca		: 1,
+	smca			: 1,
 
-	      __reserved_0	: 61;
+	/* AMD-style error thresholding banks present. */
+	amd_threshold		: 1,
+
+	__reserved_0		: 60;
 };
 
 extern struct mce_vendor_flags mce_flags;
diff --git a/arch/x86/kernel/cpu/mce/severity.c b/arch/x86/kernel/cpu/mce/severity.c
index 87bcdc6dc2f0..e1da619add19 100644
--- a/arch/x86/kernel/cpu/mce/severity.c
+++ b/arch/x86/kernel/cpu/mce/severity.c
@@ -213,8 +213,12 @@ static int error_context(struct mce *m)
 {
 	if ((m->cs & 3) == 3)
 		return IN_USER;
-	if (mc_recoverable(m->mcgstatus) && ex_has_fault_handler(m->ip))
+
+	if (mc_recoverable(m->mcgstatus) && ex_has_fault_handler(m->ip)) {
+		m->kflags |= MCE_IN_KERNEL_RECOV;
 		return IN_KERNEL_RECOV;
+	}
+
 	return IN_KERNEL;
 }