From ada018b15ccecbdb95df46db7121516edb906bf6 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 14 Feb 2020 18:32:43 +0100
Subject: x86/mce/amd: Do proper cleanup on error paths

Drop kobject reference counts properly on error in the banks and blocks
allocation functions.

 [ bp: Write commit message. ]

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200403161943.1458-2-bp@alien8.de
---
 arch/x86/kernel/cpu/mce/amd.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index 52de616a8065..477cf773cf1c 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -1267,13 +1267,12 @@ 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;
 }
@@ -1339,6 +1338,7 @@ 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;
@@ -1357,16 +1357,17 @@ 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;
+		goto out_kobj;
 
 	per_cpu(threshold_banks, cpu)[bank] = b;
 
 	return 0;
 
- out_free:
+out_kobj:
+	kobject_put(b->kobj);
+out_free:
 	kfree(b);
-
- out:
+out:
 	return err;
 }
 
-- 
cgit v1.2.3


From c9bf318f77b3a78483e656e609d005c52aadc86d Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 12 Feb 2020 00:34:01 +0100
Subject: x86/mce/amd: Init thresholding machinery only on relevant vendors

... and not unconditionally.

 [ bp: Add a new vendor_flags bit for that. ]

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200403161943.1458-3-bp@alien8.de
---
 arch/x86/kernel/cpu/mce/amd.c      | 12 ++++++++++--
 arch/x86/kernel/cpu/mce/core.c     |  1 +
 arch/x86/kernel/cpu/mce/internal.h |  9 ++++++---
 3 files changed, 17 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index 477cf773cf1c..c3b3326ad4ac 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -1442,15 +1442,20 @@ free_out:
 
 int mce_threshold_remove_device(unsigned int cpu)
 {
+	struct threshold_bank **bp = this_cpu_read(threshold_banks);
 	unsigned int bank;
 
+	if (!bp)
+		return 0;
+
 	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);
 	}
-	kfree(per_cpu(threshold_banks, cpu));
-	per_cpu(threshold_banks, cpu) = NULL;
+	/* Clear the pointer before freeing the memory */
+	this_cpu_write(threshold_banks, NULL);
+	kfree(bp);
 	return 0;
 }
 
@@ -1461,6 +1466,9 @@ int mce_threshold_create_device(unsigned int cpu)
 	struct threshold_bank **bp;
 	int err = 0;
 
+	if (!mce_flags.amd_threshold)
+		return 0;
+
 	bp = per_cpu(threshold_banks, cpu);
 	if (bp)
 		return 0;
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 54165f3569e8..43ca91e14a77 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -1756,6 +1756,7 @@ 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;
diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h
index 3b008172ad73..74a01829c4f4 100644
--- a/arch/x86/kernel/cpu/mce/internal.h
+++ b/arch/x86/kernel/cpu/mce/internal.h
@@ -148,7 +148,7 @@ 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 +156,12 @@ 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;
-- 
cgit v1.2.3


From cca9cc05fe98f3eb0cfb58ec6739cfc9d0b4ccbf Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 12 Mar 2020 20:05:43 +0100
Subject: x86/mce/amd: Protect a not-fully initialized bank from the
 thresholding interrupt

Make sure the thresholding bank descriptor is fully initialized when the
thresholding interrupt fires after a hotplug event.

 [ bp: Write commit message and document long-forgotten bank_map. ]

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200403161943.1458-4-bp@alien8.de
---
 arch/x86/kernel/cpu/mce/amd.c | 19 +++++++++++++++++--
 1 file changed, 17 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index c3b3326ad4ac..563942157758 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);
@@ -1016,13 +1021,22 @@ 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;
 
@@ -1247,6 +1261,7 @@ 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
-- 
cgit v1.2.3


From 6e7a41c63abcfee28734c4c8872dae8d642329b6 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 30 Mar 2020 16:21:54 +0200
Subject: x86/mce/amd: Sanitize thresholding device creation hotplug path

Drop the stupid threshold_init_device() initcall iterating over all
online CPUs in favor of properly setting up everything on the CPU
hotplug path, when each CPU's callback is invoked.

 [ bp: Write commit message. ]

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200403161943.1458-5-bp@alien8.de
---
 arch/x86/kernel/cpu/mce/amd.c  | 57 ++++++++++++------------------------------
 arch/x86/kernel/cpu/mce/core.c | 11 ++++++++
 2 files changed, 27 insertions(+), 41 deletions(-)

diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index 563942157758..d3c416b6052a 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -1474,12 +1474,22 @@ int mce_threshold_remove_device(unsigned int cpu)
 	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;
 	struct threshold_bank **bp;
-	int err = 0;
+	int err;
 
 	if (!mce_flags.amd_threshold)
 		return 0;
@@ -1500,49 +1510,14 @@ int mce_threshold_create_device(unsigned int cpu)
 			continue;
 		err = threshold_create_bank(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;
 	}
 
 	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 43ca91e14a77..a6009efdfe2b 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -2481,6 +2481,13 @@ 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;
@@ -2512,6 +2519,10 @@ 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)
-- 
cgit v1.2.3


From 6458de97fc15530b54477c4e2b70af653e8ac3d9 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 30 Mar 2020 20:30:45 +0200
Subject: x86/mce/amd: Straighten CPU hotplug path

mce_threshold_create_device() hotplug callback runs on the plugged in
CPU so:

 - use this_cpu_read() which is faster
 - pass in struct threshold_bank **bp to threshold_create_bank() and
   instead of doing per-CPU accesses
 - Use rdmsr_safe() instead of rdmsr_safe_on_cpu() which avoids an IPI.

No functional changes.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200403161943.1458-6-bp@alien8.de
---
 arch/x86/kernel/cpu/mce/amd.c | 32 +++++++++++++++-----------------
 1 file changed, 15 insertions(+), 17 deletions(-)

diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index d3c416b6052a..a33d9a1caf36 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -1223,10 +1223,10 @@ 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)) {
@@ -1316,9 +1316,10 @@ 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);
@@ -1338,7 +1339,7 @@ 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);
@@ -1374,8 +1375,7 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank)
 	if (err)
 		goto out_kobj;
 
-	per_cpu(threshold_banks, cpu)[bank] = b;
-
+	bp[bank] = b;
 	return 0;
 
 out_kobj:
@@ -1487,35 +1487,33 @@ int mce_threshold_remove_device(unsigned int cpu)
  */
 int mce_threshold_create_device(unsigned int cpu)
 {
-	unsigned int bank;
+	unsigned int numbanks, bank;
 	struct threshold_bank **bp;
 	int err;
 
 	if (!mce_flags.amd_threshold)
 		return 0;
 
-	bp = per_cpu(threshold_banks, cpu);
+	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 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);
-- 
cgit v1.2.3


From f26d2580a7ddc84aa9e51e47fdbb5ad63dbee5a7 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 31 Mar 2020 10:53:18 +0200
Subject: x86/mce/amd: Cleanup threshold device remove path

Pass in the bank pointer directly to the cleaning up functions,
obviating the need for per-CPU accesses. Make the clean up path
interrupt-safe by cleaning the bank pointer first so that the rest of
the teardown happens safe from the thresholding interrupt.

No functional changes.

 [ bp: Write commit message and reverse bank->shared test to save an
   indentation level in threshold_remove_bank(). ]

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200403161943.1458-7-bp@alien8.de
---
 arch/x86/include/asm/amd_nb.h |  1 +
 arch/x86/kernel/cpu/mce/amd.c | 79 ++++++++++++++++++++-----------------------
 2 files changed, 38 insertions(+), 42 deletions(-)

diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h
index c7df20e78b09..455066a06f60 100644
--- a/arch/x86/include/asm/amd_nb.h
+++ b/arch/x86/include/asm/amd_nb.h
@@ -57,6 +57,7 @@ struct threshold_bank {
 
 	/* initialized to the number of CPUs on the node sharing this bank */
 	refcount_t		cpus;
+	unsigned int		shared;
 };
 
 struct amd_northbridge {
diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index a33d9a1caf36..16e7aea86ab1 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -1362,6 +1362,7 @@ static int threshold_create_bank(struct threshold_bank **bp, unsigned int cpu,
 	}
 
 	if (is_shared_bank(bank)) {
+		b->shared = 1;
 		refcount_set(&b->cpus, 1);
 
 		/* nb is already initialized, see above */
@@ -1391,21 +1392,16 @@ 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];
-
-	if (!head)
-		return;
+	struct threshold_block *pos, *tmp;
 
-	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)
@@ -1419,57 +1415,56 @@ 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)
 {
 	struct threshold_bank **bp = this_cpu_read(threshold_banks);
-	unsigned int bank;
+	unsigned int bank, numbanks = this_cpu_read(mce_num_banks);
 
 	if (!bp)
 		return 0;
 
-	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);
-	}
-	/* Clear the pointer before freeing the memory */
+	/*
+	 * 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(bp);
 	return 0;
 }
-- 
cgit v1.2.3


From a037f3ca0ea0a660e3f961431095a88674b8f3c4 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 31 Mar 2020 13:16:44 +0200
Subject: x86/mce/amd: Make threshold bank setting hotplug robust

Handle the cases when the CPU goes offline before the bank
setting/reading happens.

 [ bp: Write commit message. ]

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200403161943.1458-8-bp@alien8.de
---
 arch/x86/kernel/cpu/mce/amd.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index 16e7aea86ab1..15c87b87b901 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -386,6 +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))
@@ -1085,7 +1089,8 @@ 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;
 }
@@ -1109,7 +1114,8 @@ 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;
 }
@@ -1118,7 +1124,9 @@ 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)));
-- 
cgit v1.2.3


From 3e0fdec858d82c829774f271e88b5ceb17051551 Mon Sep 17 00:00:00 2001
From: Borislav Petkov <bp@suse.de>
Date: Tue, 7 Apr 2020 09:55:10 +0200
Subject: x86/mce/amd, edac: Remove report_gart_errors

... because no one should be interested in spurious MCEs anyway. Make
the filtering unconditional and move it to amd_filter_mce().

Signed-off-by: Borislav Petkov <bp@suse.de>
Tested-by: Tony Luck <tony.luck@intel.com>
Link: https://lkml.kernel.org/r/20200407163414.18058-2-bp@alien8.de
---
 arch/x86/include/asm/mce.h    |  3 ++-
 arch/x86/kernel/cpu/mce/amd.c |  9 +++++++--
 drivers/edac/amd64_edac.c     |  8 --------
 drivers/edac/mce_amd.c        | 24 ------------------------
 drivers/edac/mce_amd.h        |  2 --
 5 files changed, 9 insertions(+), 37 deletions(-)

diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index f9cea081c05b..83b6ddafa032 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -127,6 +127,8 @@
 #define MSR_AMD64_SMCA_MCx_DEADDR(x)	(MSR_AMD64_SMCA_MC0_DEADDR + 0x10*(x))
 #define MSR_AMD64_SMCA_MCx_MISCy(x, y)	((MSR_AMD64_SMCA_MC0_MISC1 + y) + (0x10*(x)))
 
+#define XEC(x, mask)			(((x) >> 16) & mask)
+
 /*
  * This structure contains all data related to the MCE log.  Also
  * carries a signature to make it easier to find from external
@@ -347,5 +349,4 @@ umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr)	{ return
 #endif
 
 static inline void mce_hygon_feature_init(struct cpuinfo_x86 *c)	{ return mce_amd_feature_init(c); }
-
 #endif /* _ASM_X86_MCE_H */
diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index 15c87b87b901..ea3cf714b7ad 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -577,14 +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;
 }
 
diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index f91f3bc1e0b2..6bdc5bb8c8bc 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -4,9 +4,6 @@
 
 static struct edac_pci_ctl_info *pci_ctl;
 
-static int report_gart_errors;
-module_param(report_gart_errors, int, 0644);
-
 /*
  * Set by command line parameter. If BIOS has enabled the ECC, this override is
  * cleared to prevent re-enabling the hardware by this driver.
@@ -3681,9 +3678,6 @@ static int __init amd64_edac_init(void)
 	}
 
 	/* register stuff with EDAC MCE */
-	if (report_gart_errors)
-		amd_report_gart_errors(true);
-
 	if (boot_cpu_data.x86 >= 0x17)
 		amd_register_ecc_decoder(decode_umc_error);
 	else
@@ -3718,8 +3712,6 @@ static void __exit amd64_edac_exit(void)
 		edac_pci_release_generic_ctl(pci_ctl);
 
 	/* unregister from EDAC MCE */
-	amd_report_gart_errors(false);
-
 	if (boot_cpu_data.x86 >= 0x17)
 		amd_unregister_ecc_decoder(decode_umc_error);
 	else
diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c
index 8874b7722b2f..e58644d9c92b 100644
--- a/drivers/edac/mce_amd.c
+++ b/drivers/edac/mce_amd.c
@@ -10,15 +10,8 @@ static struct amd_decoder_ops fam_ops;
 
 static u8 xec_mask	 = 0xf;
 
-static bool report_gart_errors;
 static void (*decode_dram_ecc)(int node_id, struct mce *m);
 
-void amd_report_gart_errors(bool v)
-{
-	report_gart_errors = v;
-}
-EXPORT_SYMBOL_GPL(amd_report_gart_errors);
-
 void amd_register_ecc_decoder(void (*f)(int, struct mce *))
 {
 	decode_dram_ecc = f;
@@ -1030,20 +1023,6 @@ static inline void amd_decode_err_code(u16 ec)
 	pr_cont("\n");
 }
 
-/*
- * Filter out unwanted MCE signatures here.
- */
-static bool ignore_mce(struct mce *m)
-{
-	/*
-	 * NB GART TLB error reporting is disabled by default.
-	 */
-	if (m->bank == 4 && XEC(m->status, 0x1f) == 0x5 && !report_gart_errors)
-		return true;
-
-	return false;
-}
-
 static const char *decode_error_status(struct mce *m)
 {
 	if (m->status & MCI_STATUS_UC) {
@@ -1067,9 +1046,6 @@ amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data)
 	unsigned int fam = x86_family(m->cpuid);
 	int ecc;
 
-	if (ignore_mce(m))
-		return NOTIFY_STOP;
-
 	pr_emerg(HW_ERR "%s\n", decode_error_status(m));
 
 	pr_emerg(HW_ERR "CPU:%d (%x:%x:%x) MC%d_STATUS[%s|%s|%s|%s|%s",
diff --git a/drivers/edac/mce_amd.h b/drivers/edac/mce_amd.h
index 4e9c5e596c6c..4811b18d9606 100644
--- a/drivers/edac/mce_amd.h
+++ b/drivers/edac/mce_amd.h
@@ -7,7 +7,6 @@
 #include <asm/mce.h>
 
 #define EC(x)				((x) & 0xffff)
-#define XEC(x, mask)			(((x) >> 16) & mask)
 
 #define LOW_SYNDROME(x)			(((x) >> 15) & 0xff)
 #define HIGH_SYNDROME(x)		(((x) >> 24) & 0xff)
@@ -77,7 +76,6 @@ struct amd_decoder_ops {
 	bool (*mc2_mce)(u16, u8);
 };
 
-void amd_report_gart_errors(bool);
 void amd_register_ecc_decoder(void (*f)(int, struct mce *));
 void amd_unregister_ecc_decoder(void (*f)(int, struct mce *));
 
-- 
cgit v1.2.3


From c9c6d216ed28be6e2c91e3651af169eca284813a Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Fri, 14 Feb 2020 14:27:14 -0800
Subject: x86/mce: Rename "first" function as "early"

It isn't going to be first on the notifier chain when the CEC is moved
to be a normal user of the notifier chain.

Fix the enum for the MCE_PRIO symbols to list them in reverse order so
that the compiler can give them numbers from low to high priority. Add
an entry for MCE_PRIO_CEC as the highest priority.

 [ bp: Use passive voice, add comments. ]

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Tested-by: Tony Luck <tony.luck@intel.com>
Link: https://lkml.kernel.org/r/20200214222720.13168-2-tony.luck@intel.com
---
 arch/x86/include/asm/mce.h     | 16 +++++++++-------
 arch/x86/kernel/cpu/mce/core.c | 10 +++++-----
 2 files changed, 14 insertions(+), 12 deletions(-)

diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 83b6ddafa032..689ac6e9c65f 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -144,14 +144,16 @@ struct mce_log_buffer {
 	struct mce entry[];
 };
 
+/* Highest last */
 enum mce_notifier_prios {
-	MCE_PRIO_FIRST		= INT_MAX,
-	MCE_PRIO_UC		= INT_MAX - 1,
-	MCE_PRIO_EXTLOG		= INT_MAX - 2,
-	MCE_PRIO_NFIT		= INT_MAX - 3,
-	MCE_PRIO_EDAC		= INT_MAX - 4,
-	MCE_PRIO_MCELOG		= 1,
-	MCE_PRIO_LOWEST		= 0,
+	MCE_PRIO_LOWEST,
+	MCE_PRIO_MCELOG,
+	MCE_PRIO_EDAC,
+	MCE_PRIO_NFIT,
+	MCE_PRIO_EXTLOG,
+	MCE_PRIO_UC,
+	MCE_PRIO_EARLY,
+	MCE_PRIO_CEC
 };
 
 struct notifier_block;
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index a6009efdfe2b..43b1519ad4e5 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -559,7 +559,7 @@ static bool cec_add_mce(struct mce *m)
 	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;
@@ -580,9 +580,9 @@ 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,
@@ -2041,7 +2041,7 @@ __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();
-- 
cgit v1.2.3


From 9554bfe403bdfc084823df8695a01f28c680af61 Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Fri, 14 Feb 2020 14:27:15 -0800
Subject: x86/mce: Convert the CEC to use the MCE notifier

The CEC code has its claws in a couple of routines in mce/core.c.
Convert it to just register itself on the normal MCE notifier chain.

 [ bp: Make cec_add_elem() and cec_init() static. ]

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Tested-by: Tony Luck <tony.luck@intel.com>
Link: https://lkml.kernel.org/r/20200214222720.13168-3-tony.luck@intel.com
---
 arch/x86/kernel/cpu/mce/core.c | 19 -------------------
 drivers/ras/cec.c              | 30 ++++++++++++++++++++++++++++--
 include/linux/ras.h            |  5 -----
 3 files changed, 28 insertions(+), 26 deletions(-)

diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 43b1519ad4e5..b033b3589630 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -544,21 +544,6 @@ 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_early_notifier(struct notifier_block *nb, unsigned long val,
 			      void *data)
 {
@@ -567,9 +552,6 @@ static int mce_early_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);
 
@@ -2612,7 +2594,6 @@ 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/drivers/ras/cec.c b/drivers/ras/cec.c
index c09cf55e2d20..6b42040bf956 100644
--- a/drivers/ras/cec.c
+++ b/drivers/ras/cec.c
@@ -309,7 +309,7 @@ static bool sanity_check(struct ce_array *ca)
 	return ret;
 }
 
-int cec_add_elem(u64 pfn)
+static int cec_add_elem(u64 pfn)
 {
 	struct ce_array *ca = &ce_arr;
 	unsigned int to = 0;
@@ -527,7 +527,30 @@ err:
 	return 1;
 }
 
-void __init cec_init(void)
+static int cec_notifier(struct notifier_block *nb, unsigned long val,
+			void *data)
+{
+	struct mce *m = (struct mce *)data;
+
+	if (!m)
+		return NOTIFY_DONE;
+
+	/* 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 NOTIFY_STOP;
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block cec_nb = {
+	.notifier_call	= cec_notifier,
+	.priority	= MCE_PRIO_CEC,
+};
+
+static void __init cec_init(void)
 {
 	if (ce_arr.disabled)
 		return;
@@ -546,8 +569,11 @@ void __init cec_init(void)
 	INIT_DELAYED_WORK(&cec_work, cec_work_fn);
 	schedule_delayed_work(&cec_work, CEC_DECAY_DEFAULT_INTERVAL);
 
+	mce_register_decode_chain(&cec_nb);
+
 	pr_info("Correctable Errors collector initialized.\n");
 }
+late_initcall(cec_init);
 
 int __init parse_cec_param(char *str)
 {
diff --git a/include/linux/ras.h b/include/linux/ras.h
index 7c3debb47c87..1f4048bf2674 100644
--- a/include/linux/ras.h
+++ b/include/linux/ras.h
@@ -17,12 +17,7 @@ static inline int ras_add_daemon_trace(void) { return 0; }
 #endif
 
 #ifdef CONFIG_RAS_CEC
-void __init cec_init(void);
 int __init parse_cec_param(char *str);
-int cec_add_elem(u64 pfn);
-#else
-static inline void __init cec_init(void)	{ }
-static inline int cec_add_elem(u64 pfn)		{ return -ENODEV; }
 #endif
 
 #ifdef CONFIG_RAS
-- 
cgit v1.2.3


From 1de08dccd383482a3e88845d3554094d338f5ff9 Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Fri, 14 Feb 2020 14:27:16 -0800
Subject: x86/mce: Add a struct mce.kflags field

There can be many different subsystems register on the mce handler
chain. Add a new bitmask field and define values so that handlers can
indicate whether they took any action to log or otherwise handle an
error.

The default handler at the end of the chain can use this information to
decide whether to print to the console log.

Boris suggested a generic name and leaving plenty of spare bits for
possible future use.

 [ bp: Move flag bits to the internal mce.h header and use BIT_ULL(). ]

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Tested-by: Tony Luck <tony.luck@intel.com>
Link: https://lkml.kernel.org/r/20200214222720.13168-4-tony.luck@intel.com
---
 arch/x86/include/asm/mce.h      | 8 ++++++++
 arch/x86/include/uapi/asm/mce.h | 1 +
 2 files changed, 9 insertions(+)

diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 689ac6e9c65f..5f04a24f30ea 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -129,6 +129,14 @@
 
 #define XEC(x, mask)			(((x) >> 16) & mask)
 
+/* mce.kflags flag bits for logging etc. */
+#define	MCE_HANDLED_CEC		BIT_ULL(0)
+#define	MCE_HANDLED_UC		BIT_ULL(1)
+#define	MCE_HANDLED_EXTLOG	BIT_ULL(2)
+#define	MCE_HANDLED_NFIT	BIT_ULL(3)
+#define	MCE_HANDLED_EDAC	BIT_ULL(4)
+#define	MCE_HANDLED_MCELOG	BIT_ULL(5)
+
 /*
  * This structure contains all data related to the MCE log.  Also
  * carries a signature to make it easier to find from external
diff --git a/arch/x86/include/uapi/asm/mce.h b/arch/x86/include/uapi/asm/mce.h
index 955c2a2e1cf9..5b59d80f1d4e 100644
--- a/arch/x86/include/uapi/asm/mce.h
+++ b/arch/x86/include/uapi/asm/mce.h
@@ -35,6 +35,7 @@ struct mce {
 	__u64 ipid;		/* MCA_IPID MSR: only valid on SMCA systems */
 	__u64 ppin;		/* Protected Processor Inventory Number */
 	__u32 microcode;	/* Microcode revision */
+	__u64 kflags;		/* Internal kernel use. See below */
 };
 
 #define MCE_GET_RECORD_LEN   _IOR('M', 1, int)
-- 
cgit v1.2.3


From 23ba710a0864108910c7531dc4c73ef65eca5568 Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Fri, 14 Feb 2020 14:27:17 -0800
Subject: x86/mce: Fix all mce notifiers to update the mce->kflags bitmask

If the handler took any action to log or deal with the error, set a bit
in mce->kflags so that the default handler on the end of the machine
check chain can see what has been done.

Get rid of NOTIFY_STOP returns. Make the EDAC and dev-mcelog handlers
skip over errors already processed by CEC.

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Tested-by: Tony Luck <tony.luck@intel.com>
Link: https://lkml.kernel.org/r/20200214222720.13168-5-tony.luck@intel.com
---
 arch/x86/kernel/cpu/mce/core.c       | 4 +++-
 arch/x86/kernel/cpu/mce/dev-mcelog.c | 5 +++++
 drivers/acpi/acpi_extlog.c           | 5 +++--
 drivers/acpi/nfit/mce.c              | 1 +
 drivers/edac/i7core_edac.c           | 5 +++--
 drivers/edac/mce_amd.c               | 6 +++++-
 drivers/edac/pnd2_edac.c             | 5 +++--
 drivers/edac/sb_edac.c               | 5 ++++-
 drivers/edac/skx_common.c            | 4 ++++
 drivers/ras/cec.c                    | 9 ++++++---
 10 files changed, 37 insertions(+), 12 deletions(-)

diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index b033b3589630..5666a48a4bc9 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -581,8 +581,10 @@ 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))
+	if (!memory_failure(pfn, 0)) {
 		set_mce_nospec(pfn);
+		mce->kflags |= MCE_HANDLED_UC;
+	}
 
 	return NOTIFY_OK;
 }
diff --git a/arch/x86/kernel/cpu/mce/dev-mcelog.c b/arch/x86/kernel/cpu/mce/dev-mcelog.c
index d089567a9ce8..c033e7ea9e3c 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;
 }
 
diff --git a/drivers/acpi/acpi_extlog.c b/drivers/acpi/acpi_extlog.c
index 8596a106a933..9cc3c1f92db5 100644
--- a/drivers/acpi/acpi_extlog.c
+++ b/drivers/acpi/acpi_extlog.c
@@ -146,7 +146,7 @@ static int extlog_print(struct notifier_block *nb, unsigned long val,
 	static u32 err_seq;
 
 	estatus = extlog_elog_entry_check(cpu, bank);
-	if (estatus == NULL)
+	if (estatus == NULL || (mce->kflags & MCE_HANDLED_CEC))
 		return NOTIFY_DONE;
 
 	memcpy(elog_buf, (void *)estatus, ELOG_ENTRY_LEN);
@@ -176,7 +176,8 @@ static int extlog_print(struct notifier_block *nb, unsigned long val,
 	}
 
 out:
-	return NOTIFY_STOP;
+	mce->kflags |= MCE_HANDLED_EXTLOG;
+	return NOTIFY_OK;
 }
 
 static bool __init extlog_get_l1addr(void)
diff --git a/drivers/acpi/nfit/mce.c b/drivers/acpi/nfit/mce.c
index f0ae48515b48..ee8d9973f60b 100644
--- a/drivers/acpi/nfit/mce.c
+++ b/drivers/acpi/nfit/mce.c
@@ -76,6 +76,7 @@ static int nfit_handle_mce(struct notifier_block *nb, unsigned long val,
 			 */
 			acpi_nfit_ars_rescan(acpi_desc, 0);
 		}
+		mce->kflags |= MCE_HANDLED_NFIT;
 		break;
 	}
 
diff --git a/drivers/edac/i7core_edac.c b/drivers/edac/i7core_edac.c
index b3135b208f9a..5860ca41185c 100644
--- a/drivers/edac/i7core_edac.c
+++ b/drivers/edac/i7core_edac.c
@@ -1815,7 +1815,7 @@ static int i7core_mce_check_error(struct notifier_block *nb, unsigned long val,
 	struct mem_ctl_info *mci;
 
 	i7_dev = get_i7core_dev(mce->socketid);
-	if (!i7_dev)
+	if (!i7_dev || (mce->kflags & MCE_HANDLED_CEC))
 		return NOTIFY_DONE;
 
 	mci = i7_dev->mci;
@@ -1834,7 +1834,8 @@ static int i7core_mce_check_error(struct notifier_block *nb, unsigned long val,
 	i7core_check_error(mci, mce);
 
 	/* Advise mcelog that the errors were handled */
-	return NOTIFY_STOP;
+	mce->kflags |= MCE_HANDLED_EDAC;
+	return NOTIFY_OK;
 }
 
 static struct notifier_block i7_mce_dec = {
diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c
index e58644d9c92b..2b5401db56ad 100644
--- a/drivers/edac/mce_amd.c
+++ b/drivers/edac/mce_amd.c
@@ -1046,6 +1046,9 @@ amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data)
 	unsigned int fam = x86_family(m->cpuid);
 	int ecc;
 
+	if (m->kflags & MCE_HANDLED_CEC)
+		return NOTIFY_DONE;
+
 	pr_emerg(HW_ERR "%s\n", decode_error_status(m));
 
 	pr_emerg(HW_ERR "CPU:%d (%x:%x:%x) MC%d_STATUS[%s|%s|%s|%s|%s",
@@ -1146,7 +1149,8 @@ amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data)
  err_code:
 	amd_decode_err_code(m->status & 0xffff);
 
-	return NOTIFY_STOP;
+	m->kflags |= MCE_HANDLED_EDAC;
+	return NOTIFY_OK;
 }
 
 static struct notifier_block amd_mce_dec_nb = {
diff --git a/drivers/edac/pnd2_edac.c b/drivers/edac/pnd2_edac.c
index bc47328eb485..1929a5dc8f94 100644
--- a/drivers/edac/pnd2_edac.c
+++ b/drivers/edac/pnd2_edac.c
@@ -1400,7 +1400,7 @@ static int pnd2_mce_check_error(struct notifier_block *nb, unsigned long val, vo
 		return NOTIFY_DONE;
 
 	mci = pnd2_mci;
-	if (!mci)
+	if (!mci || (mce->kflags & MCE_HANDLED_CEC))
 		return NOTIFY_DONE;
 
 	/*
@@ -1429,7 +1429,8 @@ static int pnd2_mce_check_error(struct notifier_block *nb, unsigned long val, vo
 	pnd2_mce_output_error(mci, mce, &daddr);
 
 	/* Advice mcelog that the error were handled */
-	return NOTIFY_STOP;
+	mce->kflags |= MCE_HANDLED_EDAC;
+	return NOTIFY_OK;
 }
 
 static struct notifier_block pnd2_mce_dec = {
diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c
index 7d51c82be62b..f790f7d08688 100644
--- a/drivers/edac/sb_edac.c
+++ b/drivers/edac/sb_edac.c
@@ -3136,6 +3136,8 @@ static int sbridge_mce_check_error(struct notifier_block *nb, unsigned long val,
 
 	if (edac_get_report_status() == EDAC_REPORTING_DISABLED)
 		return NOTIFY_DONE;
+	if (mce->kflags & MCE_HANDLED_CEC)
+		return NOTIFY_DONE;
 
 	/*
 	 * Just let mcelog handle it if the error is
@@ -3183,7 +3185,8 @@ static int sbridge_mce_check_error(struct notifier_block *nb, unsigned long val,
 	sbridge_mce_output_error(mci, mce);
 
 	/* Advice mcelog that the error were handled */
-	return NOTIFY_STOP;
+	mce->kflags |= MCE_HANDLED_EDAC;
+	return NOTIFY_OK;
 }
 
 static struct notifier_block sbridge_mce_dec = {
diff --git a/drivers/edac/skx_common.c b/drivers/edac/skx_common.c
index 99bbaf629b8d..6f08a12f6b11 100644
--- a/drivers/edac/skx_common.c
+++ b/drivers/edac/skx_common.c
@@ -577,6 +577,9 @@ int skx_mce_check_error(struct notifier_block *nb, unsigned long val,
 	if (edac_get_report_status() == EDAC_REPORTING_DISABLED)
 		return NOTIFY_DONE;
 
+	if (mce->kflags & MCE_HANDLED_CEC)
+		return NOTIFY_DONE;
+
 	/* ignore unless this is memory related with an address */
 	if ((mce->status & 0xefff) >> 7 != 1 || !(mce->status & MCI_STATUS_ADDRV))
 		return NOTIFY_DONE;
@@ -616,6 +619,7 @@ int skx_mce_check_error(struct notifier_block *nb, unsigned long val,
 
 	skx_mce_output_error(mci, mce, &res);
 
+	mce->kflags |= MCE_HANDLED_EDAC;
 	return NOTIFY_DONE;
 }
 
diff --git a/drivers/ras/cec.c b/drivers/ras/cec.c
index 6b42040bf956..569d9ad2c594 100644
--- a/drivers/ras/cec.c
+++ b/drivers/ras/cec.c
@@ -538,9 +538,12 @@ static int cec_notifier(struct notifier_block *nb, unsigned long val,
 	/* 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 NOTIFY_STOP;
+	    mce_usable_address(m)) {
+		if (!cec_add_elem(m->addr >> PAGE_SHIFT)) {
+			m->kflags |= MCE_HANDLED_CEC;
+			return NOTIFY_OK;
+		}
+	}
 
 	return NOTIFY_DONE;
 }
-- 
cgit v1.2.3


From 925946cfa715a5a71639528f82b98e58f14dd4cb Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Fri, 14 Feb 2020 14:27:18 -0800
Subject: x86/mce: Change default MCE logger to check mce->kflags

Instead of keeping count of how many handlers are registered on the
MCE notifier chain and printing if below some magic value, look at
mce->kflags to see if anyone claims to have handled/logged this error.

 [ bp: Do not print ->kflags in __print_mce(). ]

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Tested-by: Tony Luck <tony.luck@intel.com>
Link: https://lkml.kernel.org/r/20200214222720.13168-6-tony.luck@intel.com
---
 arch/x86/kernel/cpu/mce/core.c | 19 +++----------------
 1 file changed, 3 insertions(+), 16 deletions(-)

diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 5666a48a4bc9..fc879b6669d5 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -158,29 +158,17 @@ 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);
@@ -263,6 +251,7 @@ 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.
@@ -602,10 +591,8 @@ 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 (!m->kflags)
+		__print_mce(m);
 
 	return NOTIFY_DONE;
 }
-- 
cgit v1.2.3


From 43505646941bee217b91d064756975aa1ab6ee3b Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Fri, 14 Feb 2020 14:27:19 -0800
Subject: x86/mce: Add mce=print_all option

Sometimes, when logs are getting lost, it's nice to just
have everything dumped to the serial console.

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Tested-by: Tony Luck <tony.luck@intel.com>
Link: https://lkml.kernel.org/r/20200214222720.13168-7-tony.luck@intel.com
---
 arch/x86/kernel/cpu/mce/core.c     | 7 ++++++-
 arch/x86/kernel/cpu/mce/internal.h | 1 +
 2 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index fc879b6669d5..4efe6c128887 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -591,7 +591,7 @@ static int mce_default_notifier(struct notifier_block *nb, unsigned long val,
 	if (!m)
 		return NOTIFY_DONE;
 
-	if (!m->kflags)
+	if (mca_cfg.print_all || !m->kflags)
 		__print_mce(m);
 
 	return NOTIFY_DONE;
@@ -1962,6 +1962,7 @@ 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
@@ -1990,6 +1991,8 @@ 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"))
@@ -2256,6 +2259,7 @@ 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),
@@ -2280,6 +2284,7 @@ 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
diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h
index 74a01829c4f4..55f5c7b755f2 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,
-- 
cgit v1.2.3


From 7fc0b9b995f222646ece8d5bca528060c098ee88 Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Fri, 14 Feb 2020 14:27:20 -0800
Subject: EDAC: Drop the EDAC report status checks

When acpi_extlog was added, we were worried that the same error would
be reported more than once by different subsystems. But in the ensuing
years I've seen complaints that people could not find an error log
(because this mechanism suppressed the log they were looking for).

Rip it all out. People are smart enough to notice the same address from
different reporting mechanisms.

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Tested-by: Tony Luck <tony.luck@intel.com>
Link: https://lkml.kernel.org/r/20200214222720.13168-8-tony.luck@intel.com
---
 drivers/acpi/acpi_extlog.c | 14 -----------
 drivers/edac/edac_mc.c     | 61 ----------------------------------------------
 drivers/edac/pnd2_edac.c   |  3 ---
 drivers/edac/sb_edac.c     |  4 ---
 drivers/edac/skx_common.c  |  3 ---
 include/linux/edac.h       |  8 ------
 6 files changed, 93 deletions(-)

diff --git a/drivers/acpi/acpi_extlog.c b/drivers/acpi/acpi_extlog.c
index 9cc3c1f92db5..f138e12b7b82 100644
--- a/drivers/acpi/acpi_extlog.c
+++ b/drivers/acpi/acpi_extlog.c
@@ -42,8 +42,6 @@ struct extlog_l1_head {
 	u8  rev1[12];
 };
 
-static int old_edac_report_status;
-
 static u8 extlog_dsm_uuid[] __initdata = "663E35AF-CC10-41A4-88EA-5470AF055295";
 
 /* L1 table related physical address */
@@ -229,11 +227,6 @@ static int __init extlog_init(void)
 	if (!(cap & MCG_ELOG_P) || !extlog_get_l1addr())
 		return -ENODEV;
 
-	if (edac_get_report_status() == EDAC_REPORTING_FORCE) {
-		pr_warn("Not loading eMCA, error reporting force-enabled through EDAC.\n");
-		return -EPERM;
-	}
-
 	rc = -EINVAL;
 	/* get L1 header to fetch necessary information */
 	l1_hdr_size = sizeof(struct extlog_l1_head);
@@ -281,12 +274,6 @@ static int __init extlog_init(void)
 	if (elog_buf == NULL)
 		goto err_release_elog;
 
-	/*
-	 * eMCA event report method has higher priority than EDAC method,
-	 * unless EDAC event report method is mandatory.
-	 */
-	old_edac_report_status = edac_get_report_status();
-	edac_set_report_status(EDAC_REPORTING_DISABLED);
 	mce_register_decode_chain(&extlog_mce_dec);
 	/* enable OS to be involved to take over management from BIOS */
 	((struct extlog_l1_head *)extlog_l1_addr)->flags |= FLAG_OS_OPTIN;
@@ -308,7 +295,6 @@ err:
 
 static void __exit extlog_exit(void)
 {
-	edac_set_report_status(old_edac_report_status);
 	mce_unregister_decode_chain(&extlog_mce_dec);
 	((struct extlog_l1_head *)extlog_l1_addr)->flags &= ~FLAG_OS_OPTIN;
 	if (extlog_l1_addr)
diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c
index 75ede27bdf6a..5813e931f2f0 100644
--- a/drivers/edac/edac_mc.c
+++ b/drivers/edac/edac_mc.c
@@ -43,8 +43,6 @@
 int edac_op_state = EDAC_OPSTATE_INVAL;
 EXPORT_SYMBOL_GPL(edac_op_state);
 
-static int edac_report = EDAC_REPORTING_ENABLED;
-
 /* lock to memory controller's control array */
 static DEFINE_MUTEX(mem_ctls_mutex);
 static LIST_HEAD(mc_devices);
@@ -60,65 +58,6 @@ static struct mem_ctl_info *error_desc_to_mci(struct edac_raw_error_desc *e)
 	return container_of(e, struct mem_ctl_info, error_desc);
 }
 
-int edac_get_report_status(void)
-{
-	return edac_report;
-}
-EXPORT_SYMBOL_GPL(edac_get_report_status);
-
-void edac_set_report_status(int new)
-{
-	if (new == EDAC_REPORTING_ENABLED ||
-	    new == EDAC_REPORTING_DISABLED ||
-	    new == EDAC_REPORTING_FORCE)
-		edac_report = new;
-}
-EXPORT_SYMBOL_GPL(edac_set_report_status);
-
-static int edac_report_set(const char *str, const struct kernel_param *kp)
-{
-	if (!str)
-		return -EINVAL;
-
-	if (!strncmp(str, "on", 2))
-		edac_report = EDAC_REPORTING_ENABLED;
-	else if (!strncmp(str, "off", 3))
-		edac_report = EDAC_REPORTING_DISABLED;
-	else if (!strncmp(str, "force", 5))
-		edac_report = EDAC_REPORTING_FORCE;
-
-	return 0;
-}
-
-static int edac_report_get(char *buffer, const struct kernel_param *kp)
-{
-	int ret = 0;
-
-	switch (edac_report) {
-	case EDAC_REPORTING_ENABLED:
-		ret = sprintf(buffer, "on");
-		break;
-	case EDAC_REPORTING_DISABLED:
-		ret = sprintf(buffer, "off");
-		break;
-	case EDAC_REPORTING_FORCE:
-		ret = sprintf(buffer, "force");
-		break;
-	default:
-		ret = -EINVAL;
-		break;
-	}
-
-	return ret;
-}
-
-static const struct kernel_param_ops edac_report_ops = {
-	.set = edac_report_set,
-	.get = edac_report_get,
-};
-
-module_param_cb(edac_report, &edac_report_ops, &edac_report, 0644);
-
 unsigned int edac_dimm_info_location(struct dimm_info *dimm, char *buf,
 				     unsigned int len)
 {
diff --git a/drivers/edac/pnd2_edac.c b/drivers/edac/pnd2_edac.c
index 1929a5dc8f94..c1f2e6deb021 100644
--- a/drivers/edac/pnd2_edac.c
+++ b/drivers/edac/pnd2_edac.c
@@ -1396,9 +1396,6 @@ static int pnd2_mce_check_error(struct notifier_block *nb, unsigned long val, vo
 	struct dram_addr daddr;
 	char *type;
 
-	if (edac_get_report_status() == EDAC_REPORTING_DISABLED)
-		return NOTIFY_DONE;
-
 	mci = pnd2_mci;
 	if (!mci || (mce->kflags & MCE_HANDLED_CEC))
 		return NOTIFY_DONE;
diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c
index f790f7d08688..d414698ca324 100644
--- a/drivers/edac/sb_edac.c
+++ b/drivers/edac/sb_edac.c
@@ -3134,8 +3134,6 @@ static int sbridge_mce_check_error(struct notifier_block *nb, unsigned long val,
 	struct mem_ctl_info *mci;
 	char *type;
 
-	if (edac_get_report_status() == EDAC_REPORTING_DISABLED)
-		return NOTIFY_DONE;
 	if (mce->kflags & MCE_HANDLED_CEC)
 		return NOTIFY_DONE;
 
@@ -3526,8 +3524,6 @@ static int __init sbridge_init(void)
 
 	if (rc >= 0) {
 		mce_register_decode_chain(&sbridge_mce_dec);
-		if (edac_get_report_status() == EDAC_REPORTING_DISABLED)
-			sbridge_printk(KERN_WARNING, "Loading driver, error reporting disabled.\n");
 		return 0;
 	}
 
diff --git a/drivers/edac/skx_common.c b/drivers/edac/skx_common.c
index 6f08a12f6b11..423d33aef54f 100644
--- a/drivers/edac/skx_common.c
+++ b/drivers/edac/skx_common.c
@@ -574,9 +574,6 @@ int skx_mce_check_error(struct notifier_block *nb, unsigned long val,
 	struct mem_ctl_info *mci;
 	char *type;
 
-	if (edac_get_report_status() == EDAC_REPORTING_DISABLED)
-		return NOTIFY_DONE;
-
 	if (mce->kflags & MCE_HANDLED_CEC)
 		return NOTIFY_DONE;
 
diff --git a/include/linux/edac.h b/include/linux/edac.h
index 0f20b986b0ab..6eb7d55d7c3d 100644
--- a/include/linux/edac.h
+++ b/include/linux/edac.h
@@ -31,14 +31,6 @@ struct device;
 extern int edac_op_state;
 
 struct bus_type *edac_get_sysfs_subsys(void);
-int edac_get_report_status(void);
-void edac_set_report_status(int new);
-
-enum {
-	EDAC_REPORTING_ENABLED,
-	EDAC_REPORTING_DISABLED,
-	EDAC_REPORTING_FORCE
-};
 
 static inline void opstate_init(void)
 {
-- 
cgit v1.2.3


From 1df73b2131e3b33d518609769636b41ce00212de Mon Sep 17 00:00:00 2001
From: Borislav Petkov <bp@suse.de>
Date: Tue, 7 Apr 2020 13:49:58 +0200
Subject: x86/mce: Fixup exception only for the correct MCEs

The severity grading code returns IN_KERNEL_RECOV error context for
errors which have happened in kernel space but from which the kernel can
recover. Whether the recovery can happen is determined by the exception
table entry having as handler ex_handler_fault() and which has been
declared at build time using _ASM_EXTABLE_FAULT().

IN_KERNEL_RECOV is used in mce_severity_intel() to lookup the
corresponding error severity in the severities table.

However, the mapping back from error severity to whether the error is
IN_KERNEL_RECOV is ambiguous and in the very paranoid case - which
might not be possible right now - but be better safe than sorry later,
an exception fixup could be attempted for another MCE whose address
is in the exception table and has the proper severity. Which would be
unfortunate, to say the least.

Therefore, mark such MCEs explicitly as MCE_IN_KERNEL_RECOV so that the
recovery attempt is done only for them.

Document the whole handling, while at it, as it is not trivial.

Reported-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Tested-by: Tony Luck <tony.luck@intel.com>
Link: https://lkml.kernel.org/r/20200407163414.18058-10-bp@alien8.de
---
 arch/x86/include/asm/mce.h         |  1 +
 arch/x86/kernel/cpu/mce/core.c     | 15 +++++++++++++--
 arch/x86/kernel/cpu/mce/severity.c |  6 +++++-
 3 files changed, 19 insertions(+), 3 deletions(-)

diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 5f04a24f30ea..c598aaab071b 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -136,6 +136,7 @@
 #define	MCE_HANDLED_NFIT	BIT_ULL(3)
 #define	MCE_HANDLED_EDAC	BIT_ULL(4)
 #define	MCE_HANDLED_MCELOG	BIT_ULL(5)
+#define MCE_IN_KERNEL_RECOV	BIT_ULL(6)
 
 /*
  * This structure contains all data related to the MCE log.  Also
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 4efe6c128887..02e1f165f148 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -1331,8 +1331,19 @@ void notrace do_machine_check(struct pt_regs *regs, long error_code)
 		local_irq_disable();
 		ist_end_non_atomic();
 	} else {
-		if (!fixup_exception(regs, X86_TRAP_MC, error_code, 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, error_code, 0))
+				mce_panic("Failed kernel mode recovery", &m, msg);
+		}
 	}
 
 out_ist:
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;
 }
 
-- 
cgit v1.2.3


From f82cdff1aa7f6dcf6625c7219342a6e5c977098d Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Wed, 15 Apr 2020 12:58:26 -0700
Subject: x86/mce: Drop bogus comment about mce.kflags

The bit definitions for kflags are for internal use only. A
late edit moved them from uapi/asm/mce.h to the internal
x86 <asm/mce.h>, but the comment saying "See below" was
accidentally left here.

Delete "See below". Just labelling this field as internal
kernel use is sufficient.

Fixes: 1de08dccd383 ("x86/mce: Add a struct mce.kflags field")
Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200415195826.GA13681@agluck-desk2.amr.corp.intel.com
---
 arch/x86/include/uapi/asm/mce.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/include/uapi/asm/mce.h b/arch/x86/include/uapi/asm/mce.h
index 5b59d80f1d4e..db9adc081c5a 100644
--- a/arch/x86/include/uapi/asm/mce.h
+++ b/arch/x86/include/uapi/asm/mce.h
@@ -35,7 +35,7 @@ struct mce {
 	__u64 ipid;		/* MCA_IPID MSR: only valid on SMCA systems */
 	__u64 ppin;		/* Protected Processor Inventory Number */
 	__u32 microcode;	/* Microcode revision */
-	__u64 kflags;		/* Internal kernel use. See below */
+	__u64 kflags;		/* Internal kernel use */
 };
 
 #define MCE_GET_RECORD_LEN   _IOR('M', 1, int)
-- 
cgit v1.2.3


From 3b4ff4eb904fef04c36b39052ca8eb31fa41fad0 Mon Sep 17 00:00:00 2001
From: He Zhe <zhe.he@windriver.com>
Date: Wed, 4 Mar 2020 14:39:07 +0800
Subject: x86/mcelog: Add compat_ioctl for 32-bit mcelog support

A 32-bit version of mcelog issuing ioctls on /dev/mcelog causes errors
like the following:

  MCE_GET_RECORD_LEN: Inappropriate ioctl for device

This is due to a missing compat_ioctl callback.

Assign to it compat_ptr_ioctl() as a generic implementation of the
.compat_ioctl file operation to ioctl functions that either ignore the
argument or pass a pointer to a compatible data type.

 [ bp: Massage commit message. ]

Signed-off-by: He Zhe <zhe.he@windriver.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Tony Luck <tony.luck@intel.com>
Link: https://lkml.kernel.org/r/1583303947-49858-1-git-send-email-zhe.he@windriver.com
---
 arch/x86/kernel/cpu/mce/dev-mcelog.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/kernel/cpu/mce/dev-mcelog.c b/arch/x86/kernel/cpu/mce/dev-mcelog.c
index c033e7ea9e3c..a4fd5287f02f 100644
--- a/arch/x86/kernel/cpu/mce/dev-mcelog.c
+++ b/arch/x86/kernel/cpu/mce/dev-mcelog.c
@@ -329,6 +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,
 };
 
-- 
cgit v1.2.3


From a4e91825d7e1252f7cba005f1451e5464b23c15d Mon Sep 17 00:00:00 2001
From: Alexander Monakov <amonakov@ispras.ru>
Date: Sun, 10 May 2020 20:48:40 +0000
Subject: x86/amd_nb: Add AMD family 17h model 60h PCI IDs

Add PCI IDs for AMD Renoir (4000-series Ryzen CPUs). This is necessary
to enable support for temperature sensors via the k10temp module.

Signed-off-by: Alexander Monakov <amonakov@ispras.ru>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Yazen Ghannam <yazen.ghannam@amd.com>
Acked-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lkml.kernel.org/r/20200510204842.2603-2-amonakov@ispras.ru
---
 arch/x86/kernel/amd_nb.c | 5 +++++
 include/linux/pci_ids.h  | 1 +
 2 files changed, 6 insertions(+)

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/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 1dfc4e1dcb94..3155f5ada02e 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -550,6 +550,7 @@
 #define PCI_DEVICE_ID_AMD_17H_DF_F3	0x1463
 #define PCI_DEVICE_ID_AMD_17H_M10H_DF_F3 0x15eb
 #define PCI_DEVICE_ID_AMD_17H_M30H_DF_F3 0x1493
+#define PCI_DEVICE_ID_AMD_17H_M60H_DF_F3 0x144b
 #define PCI_DEVICE_ID_AMD_17H_M70H_DF_F3 0x1443
 #define PCI_DEVICE_ID_AMD_19H_DF_F3	0x1653
 #define PCI_DEVICE_ID_AMD_CNB17H_F3	0x1703
-- 
cgit v1.2.3


From 279f0b3a4b80660fba6faadc2ca2fa426bf3f7e9 Mon Sep 17 00:00:00 2001
From: Alexander Monakov <amonakov@ispras.ru>
Date: Sun, 10 May 2020 20:48:41 +0000
Subject: hwmon: (k10temp) Add AMD family 17h model 60h PCI match

Add support for retrieving Tdie and Tctl on AMD Renoir (4000-series
Ryzen CPUs).

It appears SMU offsets for reading current/voltage and CCD temperature
have changed for this generation (reads from currently used offsets
yield zeros), so those features cannot be enabled so trivially.

Signed-off-by: Alexander Monakov <amonakov@ispras.ru>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lkml.kernel.org/r/20200510204842.2603-3-amonakov@ispras.ru
---
 drivers/hwmon/k10temp.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/hwmon/k10temp.c b/drivers/hwmon/k10temp.c
index 3f37d5d81fe4..7ba82e0efbeb 100644
--- a/drivers/hwmon/k10temp.c
+++ b/drivers/hwmon/k10temp.c
@@ -632,6 +632,7 @@ static const struct pci_device_id k10temp_id_table[] = {
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_17H_DF_F3) },
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F3) },
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_17H_M30H_DF_F3) },
+	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_17H_M60H_DF_F3) },
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F3) },
 	{ PCI_VDEVICE(HYGON, PCI_DEVICE_ID_AMD_17H_DF_F3) },
 	{}
-- 
cgit v1.2.3


From b6bea24d41519e8c31e4798f1c1a3f67e540c5d0 Mon Sep 17 00:00:00 2001
From: Alexander Monakov <amonakov@ispras.ru>
Date: Sun, 10 May 2020 20:48:42 +0000
Subject: EDAC/amd64: Add AMD family 17h model 60h PCI IDs

Add support for AMD Renoir (4000-series Ryzen CPUs).

Signed-off-by: Alexander Monakov <amonakov@ispras.ru>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Yazen Ghannam <yazen.ghannam@amd.com>
Link: https://lkml.kernel.org/r/20200510204842.2603-4-amonakov@ispras.ru
---
 drivers/edac/amd64_edac.c | 14 ++++++++++++++
 drivers/edac/amd64_edac.h |  3 +++
 2 files changed, 17 insertions(+)

diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index 6bdc5bb8c8bc..42024a8d6a58 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -2316,6 +2316,16 @@ static struct amd64_family_type family_types[] = {
 			.dbam_to_cs		= f17_addr_mask_to_cs_size,
 		}
 	},
+	[F17_M60H_CPUS] = {
+		.ctl_name = "F17h_M60h",
+		.f0_id = PCI_DEVICE_ID_AMD_17H_M60H_DF_F0,
+		.f6_id = PCI_DEVICE_ID_AMD_17H_M60H_DF_F6,
+		.max_mcs = 2,
+		.ops = {
+			.early_channel_count	= f17_early_channel_count,
+			.dbam_to_cs		= f17_addr_mask_to_cs_size,
+		}
+	},
 	[F17_M70H_CPUS] = {
 		.ctl_name = "F17h_M70h",
 		.f0_id = PCI_DEVICE_ID_AMD_17H_M70H_DF_F0,
@@ -3354,6 +3364,10 @@ static struct amd64_family_type *per_family_init(struct amd64_pvt *pvt)
 			fam_type = &family_types[F17_M30H_CPUS];
 			pvt->ops = &family_types[F17_M30H_CPUS].ops;
 			break;
+		} else if (pvt->model >= 0x60 && pvt->model <= 0x6f) {
+			fam_type = &family_types[F17_M60H_CPUS];
+			pvt->ops = &family_types[F17_M60H_CPUS].ops;
+			break;
 		} else if (pvt->model >= 0x70 && pvt->model <= 0x7f) {
 			fam_type = &family_types[F17_M70H_CPUS];
 			pvt->ops = &family_types[F17_M70H_CPUS].ops;
diff --git a/drivers/edac/amd64_edac.h b/drivers/edac/amd64_edac.h
index abbf3c274d74..52b5d03eeba0 100644
--- a/drivers/edac/amd64_edac.h
+++ b/drivers/edac/amd64_edac.h
@@ -120,6 +120,8 @@
 #define PCI_DEVICE_ID_AMD_17H_M10H_DF_F6 0x15ee
 #define PCI_DEVICE_ID_AMD_17H_M30H_DF_F0 0x1490
 #define PCI_DEVICE_ID_AMD_17H_M30H_DF_F6 0x1496
+#define PCI_DEVICE_ID_AMD_17H_M60H_DF_F0 0x1448
+#define PCI_DEVICE_ID_AMD_17H_M60H_DF_F6 0x144e
 #define PCI_DEVICE_ID_AMD_17H_M70H_DF_F0 0x1440
 #define PCI_DEVICE_ID_AMD_17H_M70H_DF_F6 0x1446
 #define PCI_DEVICE_ID_AMD_19H_DF_F0	0x1650
@@ -293,6 +295,7 @@ enum amd_families {
 	F17_CPUS,
 	F17_M10H_CPUS,
 	F17_M30H_CPUS,
+	F17_M60H_CPUS,
 	F17_M70H_CPUS,
 	F19_CPUS,
 	NUM_FAMILIES,
-- 
cgit v1.2.3


From 17fae1294ad9d711b2c3dd0edef479d40c76a5e8 Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Wed, 20 May 2020 09:35:46 -0700
Subject: x86/{mce,mm}: Unmap the entire page if the whole page is affected and
 poisoned

An interesting thing happened when a guest Linux instance took a machine
check. The VMM unmapped the bad page from guest physical space and
passed the machine check to the guest.

Linux took all the normal actions to offline the page from the process
that was using it. But then guest Linux crashed because it said there
was a second machine check inside the kernel with this stack trace:

do_memory_failure
    set_mce_nospec
         set_memory_uc
              _set_memory_uc
                   change_page_attr_set_clr
                        cpa_flush
                             clflush_cache_range_opt

This was odd, because a CLFLUSH instruction shouldn't raise a machine
check (it isn't consuming the data). Further investigation showed that
the VMM had passed in another machine check because is appeared that the
guest was accessing the bad page.

Fix is to check the scope of the poison by checking the MCi_MISC register.
If the entire page is affected, then unmap the page. If only part of the
page is affected, then mark the page as uncacheable.

This assumes that VMMs will do the logical thing and pass in the "whole
page scope" via the MCi_MISC register (since they unmapped the entire
page).

  [ bp: Adjust to x86/entry changes. ]

Fixes: 284ce4011ba6 ("x86/memory_failure: Introduce {set, clear}_mce_nospec()")
Reported-by: Jue Wang <juew@google.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Jue Wang <juew@google.com>
Cc: <stable@vger.kernel.org>
Link: https://lkml.kernel.org/r/20200520163546.GA7977@agluck-desk2.amr.corp.intel.com
---
 arch/x86/include/asm/set_memory.h | 19 +++++++++++++------
 arch/x86/kernel/cpu/mce/core.c    | 18 ++++++++++++++----
 include/linux/sched.h             |  4 +++-
 include/linux/set_memory.h        |  2 +-
 4 files changed, 31 insertions(+), 12 deletions(-)

diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h
index ec2c0a094b5d..5948218f35c5 100644
--- a/arch/x86/include/asm/set_memory.h
+++ b/arch/x86/include/asm/set_memory.h
@@ -86,28 +86,35 @@ int set_direct_map_default_noflush(struct page *page);
 extern int kernel_set_to_readonly;
 
 #ifdef CONFIG_X86_64
-static inline int set_mce_nospec(unsigned long pfn)
+/*
+ * Prevent speculative access to the page by either unmapping
+ * it (if we do not require access to any part of the page) or
+ * marking it uncacheable (if we want to try to retrieve data
+ * from non-poisoned lines in the page).
+ */
+static inline int set_mce_nospec(unsigned long pfn, bool unmap)
 {
 	unsigned long decoy_addr;
 	int rc;
 
 	/*
-	 * Mark the linear address as UC to make sure we don't log more
-	 * errors because of speculative access to the page.
 	 * We would like to just call:
-	 *      set_memory_uc((unsigned long)pfn_to_kaddr(pfn), 1);
+	 *      set_memory_XX((unsigned long)pfn_to_kaddr(pfn), 1);
 	 * but doing that would radically increase the odds of a
 	 * speculative access to the poison page because we'd have
 	 * the virtual address of the kernel 1:1 mapping sitting
 	 * around in registers.
 	 * Instead we get tricky.  We create a non-canonical address
 	 * that looks just like the one we want, but has bit 63 flipped.
-	 * This relies on set_memory_uc() properly sanitizing any __pa()
+	 * This relies on set_memory_XX() properly sanitizing any __pa()
 	 * results with __PHYSICAL_MASK or PTE_PFN_MASK.
 	 */
 	decoy_addr = (pfn << PAGE_SHIFT) + (PAGE_OFFSET ^ BIT(63));
 
-	rc = set_memory_uc(decoy_addr, 1);
+	if (unmap)
+		rc = set_memory_np(decoy_addr, 1);
+	else
+		rc = set_memory_uc(decoy_addr, 1);
 	if (rc)
 		pr_warn("Could not invalidate pfn=0x%lx from 1:1 map\n", pfn);
 	return rc;
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 30413325de22..ce9120c4f740 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -520,6 +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)
@@ -573,7 +581,7 @@ static int uc_decode_notifier(struct notifier_block *nb, unsigned long val,
 
 	pfn = mce->addr >> PAGE_SHIFT;
 	if (!memory_failure(pfn, 0)) {
-		set_mce_nospec(pfn);
+		set_mce_nospec(pfn, whole_page(mce));
 		mce->kflags |= MCE_HANDLED_UC;
 	}
 
@@ -1173,11 +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;
 	}
 
@@ -1331,7 +1340,8 @@ 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;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index c5d96e3e7fff..62c1de522fc5 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1304,7 +1304,9 @@ struct task_struct {
 
 #ifdef CONFIG_X86_MCE
 	u64				mce_addr;
-	u64				mce_status;
+	__u64				mce_ripv : 1,
+					mce_whole_page : 1,
+					__mce_reserved : 62;
 	struct callback_head		mce_kill_me;
 #endif
 
diff --git a/include/linux/set_memory.h b/include/linux/set_memory.h
index 86281ac7c305..860e0f843c12 100644
--- a/include/linux/set_memory.h
+++ b/include/linux/set_memory.h
@@ -26,7 +26,7 @@ static inline int set_direct_map_default_noflush(struct page *page)
 #endif
 
 #ifndef set_mce_nospec
-static inline int set_mce_nospec(unsigned long pfn)
+static inline int set_mce_nospec(unsigned long pfn, bool unmap)
 {
 	return 0;
 }
-- 
cgit v1.2.3


From 7ccddc4613db446dc3cbb69a3763ba60ec651d13 Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Wed, 27 May 2020 11:28:08 -0700
Subject: x86/mce/dev-mcelog: Fix -Wstringop-truncation warning about strncpy()

The kbuild test robot reported this warning:

  arch/x86/kernel/cpu/mce/dev-mcelog.c: In function 'dev_mcelog_init_device':
  arch/x86/kernel/cpu/mce/dev-mcelog.c:346:2: warning: 'strncpy' output \
    truncated before terminating nul copying 12 bytes from a string of the \
    same length [-Wstringop-truncation]

This is accurate, but I don't care that the trailing NUL character isn't
copied. The string being copied is just a magic number signature so that
crash dump tools can be sure they are decoding the right blob of memory.

Use memcpy() instead of strncpy().

Fixes: d8ecca4043f2 ("x86/mce/dev-mcelog: Dynamically allocate space for machine check records")
Reported-by: kbuild test robot <lkp@intel.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/20200527182808.27737-1-tony.luck@intel.com
---
 arch/x86/kernel/cpu/mce/dev-mcelog.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/mce/dev-mcelog.c b/arch/x86/kernel/cpu/mce/dev-mcelog.c
index a4fd5287f02f..43c466020ed5 100644
--- a/arch/x86/kernel/cpu/mce/dev-mcelog.c
+++ b/arch/x86/kernel/cpu/mce/dev-mcelog.c
@@ -349,7 +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);
 
-- 
cgit v1.2.3