[PATCH v4 0/5] Handle MCA banks in a per_cpu way

[PATCH v4 0/5] Handle MCA banks in a per_cpu way

[Ghannam, Yazen]

From: Yazen Ghannam <yazen.ghannam@amd.com>

The focus of this patchset is define and use the MCA bank structures
and bank count per logical CPU.

With the exception of patch 4, this set applies to systems in production
today.

Patch 1:
Moves the declaration of struct mce_banks[] to the only file it's used.

Patch 2:
Splits struct mce_bank into a structure for fields common to MCA banks
on all CPUs and another structure that can be used per_cpu.

Patch 3:
Brings full circle the saga of the threshold block addresses on SMCA
systems. After taking a step back and reviewing the AMD documentation, I
think that this implimentation is the simplest and more robust way to
follow the spec.

Patch 4:
Saves and uses the MCA bank count as a per_cpu variable. This is to
support systems that have MCA bank counts that are different between
logical CPUs.

Patch 5:
Checks if an MCA banks is enabled after initialization.

Link:
https://lkml.kernel.org/r/20190430203206.104163-1-Yazen.Ghannam@amd.com

Thanks,
Yazen

Yazen Ghannam (5):
  x86/MCE: Make struct mce_banks[] static
  x86/MCE: Make mce_banks a per-CPU array
  x86/MCE/AMD: Don't cache block addresses on SMCA systems
  x86/MCE: Make the number of MCA banks a per-CPU variable
  x86/MCE: Determine MCA banks' init state properly

 arch/x86/kernel/cpu/mce/amd.c      |  92 +++++++++--------
 arch/x86/kernel/cpu/mce/core.c     | 161 +++++++++++++++++++++--------
 arch/x86/kernel/cpu/mce/internal.h |  12 +--
 3 files changed, 165 insertions(+), 100 deletions(-)

-- 
2.17.1

[PATCH v4 1/5] x86/MCE: Make struct mce_banks[] static

[Ghannam, Yazen]

From: Yazen Ghannam <yazen.ghannam@amd.com>

The struct mce_banks[] array is only used in mce/core.c so move its
definition there and make it static. Also, change the "init" field to
bool type.

Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com>
---
Link:
https://lkml.kernel.org/r/20190430203206.104163-2-Yazen.Ghannam@amd.com

v3->v4:
* No changes

v2->v3:
* No changes

v1->v2:
* No changes

 arch/x86/kernel/cpu/mce/core.c     | 11 ++++++++++-
 arch/x86/kernel/cpu/mce/internal.h | 10 ----------
 2 files changed, 10 insertions(+), 11 deletions(-)

diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 282916f3b8d8..55bdbedde0b8 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -65,7 +65,16 @@ static DEFINE_MUTEX(mce_sysfs_mutex);
 
 DEFINE_PER_CPU(unsigned, mce_exception_count);
 
-struct mce_bank *mce_banks __read_mostly;
+#define ATTR_LEN               16
+/* One object for each MCE bank, shared by all CPUs */
+struct mce_bank {
+	u64			ctl;			/* subevents to enable */
+	bool			init;			/* initialise bank? */
+	struct device_attribute	attr;			/* device attribute */
+	char			attrname[ATTR_LEN];	/* attribute name */
+};
+
+static struct mce_bank *mce_banks __read_mostly;
 struct mce_vendor_flags mce_flags __read_mostly;
 
 struct mca_config mca_cfg __read_mostly = {
diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h
index a34b55baa7aa..35b3e5c02c1c 100644
--- a/arch/x86/kernel/cpu/mce/internal.h
+++ b/arch/x86/kernel/cpu/mce/internal.h
@@ -22,17 +22,8 @@ enum severity_level {
 
 extern struct blocking_notifier_head x86_mce_decoder_chain;
 
-#define ATTR_LEN		16
 #define INITIAL_CHECK_INTERVAL	5 * 60 /* 5 minutes */
 
-/* One object for each MCE bank, shared by all CPUs */
-struct mce_bank {
-	u64			ctl;			/* subevents to enable */
-	unsigned char init;				/* initialise bank? */
-	struct device_attribute attr;			/* device attribute */
-	char			attrname[ATTR_LEN];	/* attribute name */
-};
-
 struct mce_evt_llist {
 	struct llist_node llnode;
 	struct mce mce;
@@ -47,7 +38,6 @@ struct llist_node *mce_gen_pool_prepare_records(void);
 extern int (*mce_severity)(struct mce *a, int tolerant, char **msg, bool is_excp);
 struct dentry *mce_get_debugfs_dir(void);
 
-extern struct mce_bank *mce_banks;
 extern mce_banks_t mce_banks_ce_disabled;
 
 #ifdef CONFIG_X86_MCE_INTEL
-- 
2.17.1

[PATCH v4 2/5] x86/MCE: Make mce_banks a per-CPU array

[Ghannam, Yazen]

From: Yazen Ghannam <yazen.ghannam@amd.com>

Current AMD systems have unique MCA banks per logical CPU even though
the type of the banks may all align to the same bank number. Each CPU
will have control of a set of MCA banks in the hardware and these are
not shared with other CPUs.

For example, bank 0 may be the Load-Store Unit on every logical CPU, but
each bank 0 is a unique structure in the hardware. In other words, there
isn't a *single* Load-Store Unit at MCA bank 0 that all logical CPUs
share.

This idea extends even to non-core MCA banks. For example, CPU0 and CPU4
may see a Unified Memory Controller at bank 15, but each CPU is actually
seeing a unique hardware structure that is not shared with other CPUs.

Because the MCA banks are all unique hardware structures, it would be
good to control them in a more granular way. For example, if there is a
known issue with the Floating Point Unit on CPU5 and a user wishes to
disable an error type on the Floating Point Unit, then it would be good
to do this only for CPU5 rather than all CPUs.

Also, future AMD systems may have heterogeneous MCA banks. Meaning
the bank numbers may not necessarily represent the same types between
CPUs. For example, bank 20 visible to CPU0 may be a Unified Memory
Controller and bank 20 visible to CPU4 may be a Coherent Slave. So
granular control will be even more necessary should the user wish to
control specific MCA banks.

Split the device attributes from struct mce_bank leaving only the MCA
bank control fields.

Make struct mce_banks[] per_cpu in order to have more granular control
over individual MCA banks in the hardware.

Allocate the device attributes statically based on the maximum number of
MCA banks supported. The sysfs interface will use as many as needed per
CPU. Currently, this is set to mca_cfg.banks, but will be changed to a
per_cpu bank count in a future patch.

Allocate the MCA control bits statically. This is in order to avoid
locking warnings when memory is allocated during secondary CPUs' init
sequences.

Also, remove the now unnecessary return values from
__mcheck_cpu_mce_banks_init() and __mcheck_cpu_cap_init().

Redo the sysfs store/show functions to handle the per_cpu mce_banks[].

 [ bp: s/mce_banks_percpu/mce_banks_array/g ]

[ Locking issue reported by ]
Reported-by: kernel test robot <rong.a.chen@intel.com>
[ Locking issue fix suggested by ]
Suggested-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com>
---
Link:
https://lkml.kernel.org/r/20190430203206.104163-3-Yazen.Ghannam@amd.com

v3->v4:
* Statically allocate all structures to avoid locking issues with
  secondary CPUs.

v2->v3:
* Keep old member alignment in struct mce_bank.
* Change "cpu" to "CPU" in modified comment.
* Use a local array pointer when doing multiple per_cpu accesses.

v1->v2:
* Change "struct mce_bank*" to "struct mce_bank *" in definition.

 arch/x86/kernel/cpu/mce/core.c | 76 +++++++++++++++++++++-------------
 1 file changed, 48 insertions(+), 28 deletions(-)

diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 55bdbedde0b8..c505b10f912a 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -65,16 +65,21 @@ static DEFINE_MUTEX(mce_sysfs_mutex);
 
 DEFINE_PER_CPU(unsigned, mce_exception_count);
 
-#define ATTR_LEN               16
-/* One object for each MCE bank, shared by all CPUs */
 struct mce_bank {
 	u64			ctl;			/* subevents to enable */
 	bool			init;			/* initialise bank? */
+};
+static DEFINE_PER_CPU_READ_MOSTLY(struct mce_bank [MAX_NR_BANKS], mce_banks_array);
+
+#define ATTR_LEN               16
+/* One object for each MCE bank, shared by all CPUs */
+struct mce_bank_dev {
 	struct device_attribute	attr;			/* device attribute */
 	char			attrname[ATTR_LEN];	/* attribute name */
+	u8			bank;			/* bank number */
 };
+static struct mce_bank_dev mce_bank_devs[MAX_NR_BANKS];
 
-static struct mce_bank *mce_banks __read_mostly;
 struct mce_vendor_flags mce_flags __read_mostly;
 
 struct mca_config mca_cfg __read_mostly = {
@@ -684,6 +689,7 @@ DEFINE_PER_CPU(unsigned, mce_poll_count);
  */
 bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
 {
+	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
 	bool error_seen = false;
 	struct mce m;
 	int i;
@@ -1131,6 +1137,7 @@ static void __mc_scan_banks(struct mce *m, struct mce *final,
 			    unsigned long *toclear, unsigned long *valid_banks,
 			    int no_way_out, int *worst)
 {
+	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
 	struct mca_config *cfg = &mca_cfg;
 	int severity, i;
 
@@ -1472,27 +1479,23 @@ int mce_notify_irq(void)
 }
 EXPORT_SYMBOL_GPL(mce_notify_irq);
 
-static int __mcheck_cpu_mce_banks_init(void)
+static void __mcheck_cpu_mce_banks_init(void)
 {
+	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
 	int i;
 
-	mce_banks = kcalloc(MAX_NR_BANKS, sizeof(struct mce_bank), GFP_KERNEL);
-	if (!mce_banks)
-		return -ENOMEM;
-
 	for (i = 0; i < MAX_NR_BANKS; i++) {
 		struct mce_bank *b = &mce_banks[i];
 
 		b->ctl = -1ULL;
 		b->init = 1;
 	}
-	return 0;
 }
 
 /*
  * Initialize Machine Checks for a CPU.
  */
-static int __mcheck_cpu_cap_init(void)
+static void __mcheck_cpu_cap_init(void)
 {
 	u64 cap;
 	u8 b;
@@ -1505,11 +1508,7 @@ static int __mcheck_cpu_cap_init(void)
 
 	mca_cfg.banks = max(mca_cfg.banks, b);
 
-	if (!mce_banks) {
-		int err = __mcheck_cpu_mce_banks_init();
-		if (err)
-			return err;
-	}
+	__mcheck_cpu_mce_banks_init();
 
 	/* Use accurate RIP reporting if available. */
 	if ((cap & MCG_EXT_P) && MCG_EXT_CNT(cap) >= 9)
@@ -1517,8 +1516,6 @@ static int __mcheck_cpu_cap_init(void)
 
 	if (cap & MCG_SER_P)
 		mca_cfg.ser = 1;
-
-	return 0;
 }
 
 static void __mcheck_cpu_init_generic(void)
@@ -1545,6 +1542,7 @@ static void __mcheck_cpu_init_generic(void)
 
 static void __mcheck_cpu_init_clear_banks(void)
 {
+	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
 	int i;
 
 	for (i = 0; i < mca_cfg.banks; i++) {
@@ -1588,6 +1586,7 @@ static void quirk_sandybridge_ifu(int bank, struct mce *m, struct pt_regs *regs)
 /* Add per CPU specific workarounds here */
 static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
 {
+	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
 	struct mca_config *cfg = &mca_cfg;
 
 	if (c->x86_vendor == X86_VENDOR_UNKNOWN) {
@@ -1824,7 +1823,9 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c)
 	if (!mce_available(c))
 		return;
 
-	if (__mcheck_cpu_cap_init() < 0 || __mcheck_cpu_apply_quirks(c) < 0) {
+	__mcheck_cpu_cap_init();
+
+	if (__mcheck_cpu_apply_quirks(c) < 0) {
 		mca_cfg.disabled = 1;
 		return;
 	}
@@ -1958,6 +1959,7 @@ int __init mcheck_init(void)
  */
 static void mce_disable_error_reporting(void)
 {
+	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
 	int i;
 
 	for (i = 0; i < mca_cfg.banks; i++) {
@@ -2060,26 +2062,41 @@ static struct bus_type mce_subsys = {
 
 DEFINE_PER_CPU(struct device *, mce_device);
 
-static inline struct mce_bank *attr_to_bank(struct device_attribute *attr)
+static inline struct mce_bank_dev *attr_to_bank(struct device_attribute *attr)
 {
-	return container_of(attr, struct mce_bank, attr);
+	return container_of(attr, struct mce_bank_dev, attr);
 }
 
 static ssize_t show_bank(struct device *s, struct device_attribute *attr,
 			 char *buf)
 {
-	return sprintf(buf, "%llx\n", attr_to_bank(attr)->ctl);
+	u8 bank = attr_to_bank(attr)->bank;
+	struct mce_bank *b;
+
+	if (bank >= mca_cfg.banks)
+		return -EINVAL;
+
+	b = &per_cpu(mce_banks_array, s->id)[bank];
+
+	return sprintf(buf, "%llx\n", b->ctl);
 }
 
 static ssize_t set_bank(struct device *s, struct device_attribute *attr,
 			const char *buf, size_t size)
 {
+	u8 bank = attr_to_bank(attr)->bank;
+	struct mce_bank *b;
 	u64 new;
 
 	if (kstrtou64(buf, 0, &new) < 0)
 		return -EINVAL;
 
-	attr_to_bank(attr)->ctl = new;
+	if (bank >= mca_cfg.banks)
+		return -EINVAL;
+
+	b = &per_cpu(mce_banks_array, s->id)[bank];
+
+	b->ctl = new;
 	mce_restart();
 
 	return size;
@@ -2194,7 +2211,7 @@ static void mce_device_release(struct device *dev)
 	kfree(dev);
 }
 
-/* Per cpu device init. All of the cpus still share the same ctrl bank: */
+/* Per CPU device init. All of the CPUs still share the same bank device: */
 static int mce_device_create(unsigned int cpu)
 {
 	struct device *dev;
@@ -2227,7 +2244,7 @@ static int mce_device_create(unsigned int cpu)
 			goto error;
 	}
 	for (j = 0; j < mca_cfg.banks; j++) {
-		err = device_create_file(dev, &mce_banks[j].attr);
+		err = device_create_file(dev, &mce_bank_devs[j].attr);
 		if (err)
 			goto error2;
 	}
@@ -2237,7 +2254,7 @@ static int mce_device_create(unsigned int cpu)
 	return 0;
 error2:
 	while (--j >= 0)
-		device_remove_file(dev, &mce_banks[j].attr);
+		device_remove_file(dev, &mce_bank_devs[j].attr);
 error:
 	while (--i >= 0)
 		device_remove_file(dev, mce_device_attrs[i]);
@@ -2259,7 +2276,7 @@ static void mce_device_remove(unsigned int cpu)
 		device_remove_file(dev, mce_device_attrs[i]);
 
 	for (i = 0; i < mca_cfg.banks; i++)
-		device_remove_file(dev, &mce_banks[i].attr);
+		device_remove_file(dev, &mce_bank_devs[i].attr);
 
 	device_unregister(dev);
 	cpumask_clear_cpu(cpu, mce_device_initialized);
@@ -2280,6 +2297,7 @@ static void mce_disable_cpu(void)
 
 static void mce_reenable_cpu(void)
 {
+	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
 	int i;
 
 	if (!mce_available(raw_cpu_ptr(&cpu_info)))
@@ -2337,10 +2355,12 @@ static __init void mce_init_banks(void)
 {
 	int i;
 
-	for (i = 0; i < mca_cfg.banks; i++) {
-		struct mce_bank *b = &mce_banks[i];
+	for (i = 0; i < MAX_NR_BANKS; i++) {
+		struct mce_bank_dev *b = &mce_bank_devs[i];
 		struct device_attribute *a = &b->attr;
 
+		b->bank = i;
+
 		sysfs_attr_init(&a->attr);
 		a->attr.name	= b->attrname;
 		snprintf(b->attrname, ATTR_LEN, "bank%d", i);
-- 
2.17.1

[PATCH v4 3/5] x86/MCE/AMD: Don't cache block addresses on SMCA systems

[Ghannam, Yazen]

From: Yazen Ghannam <yazen.ghannam@amd.com>

On legacy systems, the addresses of the MCA_MISC* registers need to be
recursively discovered based on a Block Pointer field in the registers.

On Scalable MCA systems, the register space is fixed, and particular
addresses can be derived by regular offsets for bank and register type.
This fixed address space includes the MCA_MISC* registers.

MCA_MISC0 is always available for each MCA bank. MCA_MISC1 through
MCA_MISC4 are considered available if MCA_MISC0[BlkPtr]=1.

Cache the value of MCA_MISC0[BlkPtr] for each bank and per CPU. This
needs to be done only during init. The values should be saved per CPU
to accommodate heterogeneous SMCA systems.

Redo smca_get_block_address() to directly return the block addresses.

Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com>
---
Link:
https://lkml.kernel.org/r/20190430203206.104163-4-Yazen.Ghannam@amd.com

v3->v4:
* No change.

v2->v3:
* Change name of new map variable to "smca_misc_banks_map".
* Use "BIT()" where appropriate.

v1->v2:
* No change.

 arch/x86/kernel/cpu/mce/amd.c | 73 ++++++++++++++++++-----------------
 1 file changed, 37 insertions(+), 36 deletions(-)

diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index d904aafe6409..d4d6e4b7f9dc 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -101,11 +101,6 @@ static struct smca_bank_name smca_names[] = {
 	[SMCA_PCIE]	= { "pcie",		"PCI Express Unit" },
 };
 
-static u32 smca_bank_addrs[MAX_NR_BANKS][NR_BLOCKS] __ro_after_init =
-{
-	[0 ... MAX_NR_BANKS - 1] = { [0 ... NR_BLOCKS - 1] = -1 }
-};
-
 static const char *smca_get_name(enum smca_bank_types t)
 {
 	if (t >= N_SMCA_BANK_TYPES)
@@ -199,6 +194,9 @@ static char buf_mcatype[MAX_MCATYPE_NAME_LEN];
 static DEFINE_PER_CPU(struct threshold_bank **, threshold_banks);
 static DEFINE_PER_CPU(unsigned int, bank_map);	/* see which banks are on */
 
+/* Map of banks that have more than MCA_MISC0 available. */
+static DEFINE_PER_CPU(u32, smca_misc_banks_map);
+
 static void amd_threshold_interrupt(void);
 static void amd_deferred_error_interrupt(void);
 
@@ -208,6 +206,28 @@ static void default_deferred_error_interrupt(void)
 }
 void (*deferred_error_int_vector)(void) = default_deferred_error_interrupt;
 
+static void smca_set_misc_banks_map(unsigned int bank, unsigned int cpu)
+{
+	u32 low, high;
+
+	/*
+	 * For SMCA enabled processors, BLKPTR field of the first MISC register
+	 * (MCx_MISC0) indicates presence of additional MISC regs set (MISC1-4).
+	 */
+	if (rdmsr_safe(MSR_AMD64_SMCA_MCx_CONFIG(bank), &low, &high))
+		return;
+
+	if (!(low & MCI_CONFIG_MCAX))
+		return;
+
+	if (rdmsr_safe(MSR_AMD64_SMCA_MCx_MISC(bank), &low, &high))
+		return;
+
+	if (low & MASK_BLKPTR_LO)
+		per_cpu(smca_misc_banks_map, cpu) |= BIT(bank);
+
+}
+
 static void smca_configure(unsigned int bank, unsigned int cpu)
 {
 	unsigned int i, hwid_mcatype;
@@ -245,6 +265,8 @@ static void smca_configure(unsigned int bank, unsigned int cpu)
 		wrmsr(smca_config, low, high);
 	}
 
+	smca_set_misc_banks_map(bank, cpu);
+
 	/* Return early if this bank was already initialized. */
 	if (smca_banks[bank].hwid)
 		return;
@@ -455,42 +477,21 @@ static void deferred_error_interrupt_enable(struct cpuinfo_x86 *c)
 	wrmsr(MSR_CU_DEF_ERR, low, high);
 }
 
-static u32 smca_get_block_address(unsigned int bank, unsigned int block)
+static u32 smca_get_block_address(unsigned int bank, unsigned int block,
+				  unsigned int cpu)
 {
-	u32 low, high;
-	u32 addr = 0;
-
-	if (smca_get_bank_type(bank) == SMCA_RESERVED)
-		return addr;
-
 	if (!block)
 		return MSR_AMD64_SMCA_MCx_MISC(bank);
 
-	/* Check our cache first: */
-	if (smca_bank_addrs[bank][block] != -1)
-		return smca_bank_addrs[bank][block];
-
-	/*
-	 * For SMCA enabled processors, BLKPTR field of the first MISC register
-	 * (MCx_MISC0) indicates presence of additional MISC regs set (MISC1-4).
-	 */
-	if (rdmsr_safe(MSR_AMD64_SMCA_MCx_CONFIG(bank), &low, &high))
-		goto out;
-
-	if (!(low & MCI_CONFIG_MCAX))
-		goto out;
-
-	if (!rdmsr_safe(MSR_AMD64_SMCA_MCx_MISC(bank), &low, &high) &&
-	    (low & MASK_BLKPTR_LO))
-		addr = MSR_AMD64_SMCA_MCx_MISCy(bank, block - 1);
+	if (!(per_cpu(smca_misc_banks_map, cpu) & BIT(bank)))
+		return 0;
 
-out:
-	smca_bank_addrs[bank][block] = addr;
-	return addr;
+	return MSR_AMD64_SMCA_MCx_MISCy(bank, block - 1);
 }
 
 static u32 get_block_address(u32 current_addr, u32 low, u32 high,
-			     unsigned int bank, unsigned int block)
+			     unsigned int bank, unsigned int block,
+			     unsigned int cpu)
 {
 	u32 addr = 0, offset = 0;
 
@@ -498,7 +499,7 @@ static u32 get_block_address(u32 current_addr, u32 low, u32 high,
 		return addr;
 
 	if (mce_flags.smca)
-		return smca_get_block_address(bank, block);
+		return smca_get_block_address(bank, block, cpu);
 
 	/* Fall back to method we used for older processors: */
 	switch (block) {
@@ -637,7 +638,7 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
 		disable_err_thresholding(c, bank);
 
 		for (block = 0; block < NR_BLOCKS; ++block) {
-			address = get_block_address(address, low, high, bank, block);
+			address = get_block_address(address, low, high, bank, block, cpu);
 			if (!address)
 				break;
 
@@ -1254,7 +1255,7 @@ static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank,
 	if (err)
 		goto out_free;
 recurse:
-	address = get_block_address(address, low, high, bank, ++block);
+	address = get_block_address(address, low, high, bank, ++block, cpu);
 	if (!address)
 		return 0;
 
-- 
2.17.1

[PATCH v4 4/5] x86/MCE: Make the number of MCA banks a per-CPU variable

[Ghannam, Yazen]

From: Yazen Ghannam <yazen.ghannam@amd.com>

The number of MCA banks is provided per logical CPU. Historically, this
number has been the same across all CPUs, but this is not an
architectural guarantee. Future AMD systems may have MCA bank counts
that vary between logical CPUs in a system.

This issue was partially addressed in

  006c077041dc ("x86/mce: Handle varying MCA bank counts")

by allocating structures using the maximum number of MCA banks and by
saving the maximum MCA bank count in a system as the global count. This
means that some extra structures are allocated. Also, this means that
CPUs will spend more time in the #MC and other handlers checking extra
MCA banks.

Thus, define the number of MCA banks as a per-CPU variable.

 [ bp: Make mce_num_banks an unsigned int. ]

Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com>
---
Link:
https://lkml.kernel.org/r/20190430203206.104163-5-Yazen.Ghannam@amd.com

v3->v4:
* Include Boris' change.

v2->v3:
* Drop pr_debug() message.
* Change commit reference format.

v1->v2:
* Drop export of new variable and leave injector code as-is.
* Add "mce_" prefix to new "num_banks" variable.

 arch/x86/kernel/cpu/mce/amd.c      | 19 +++++++------
 arch/x86/kernel/cpu/mce/core.c     | 45 +++++++++++++++++-------------
 arch/x86/kernel/cpu/mce/internal.h |  2 +-
 3 files changed, 36 insertions(+), 30 deletions(-)

diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index d4d6e4b7f9dc..fb5c935af2c5 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -495,7 +495,7 @@ static u32 get_block_address(u32 current_addr, u32 low, u32 high,
 {
 	u32 addr = 0, offset = 0;
 
-	if ((bank >= mca_cfg.banks) || (block >= NR_BLOCKS))
+	if ((bank >= per_cpu(mce_num_banks, cpu)) || (block >= NR_BLOCKS))
 		return addr;
 
 	if (mce_flags.smca)
@@ -627,11 +627,12 @@ void disable_err_thresholding(struct cpuinfo_x86 *c, unsigned int bank)
 /* cpu init entry point, called from mce.c with preempt off */
 void mce_amd_feature_init(struct cpuinfo_x86 *c)
 {
-	u32 low = 0, high = 0, address = 0;
 	unsigned int bank, block, cpu = smp_processor_id();
+	u32 low = 0, high = 0, address = 0;
 	int offset = -1;
 
-	for (bank = 0; bank < mca_cfg.banks; ++bank) {
+
+	for (bank = 0; bank < this_cpu_read(mce_num_banks); ++bank) {
 		if (mce_flags.smca)
 			smca_configure(bank, cpu);
 
@@ -976,7 +977,7 @@ static void amd_deferred_error_interrupt(void)
 {
 	unsigned int bank;
 
-	for (bank = 0; bank < mca_cfg.banks; ++bank)
+	for (bank = 0; bank < this_cpu_read(mce_num_banks); ++bank)
 		log_error_deferred(bank);
 }
 
@@ -1017,7 +1018,7 @@ static void amd_threshold_interrupt(void)
 	struct threshold_block *first_block = NULL, *block = NULL, *tmp = NULL;
 	unsigned int bank, cpu = smp_processor_id();
 
-	for (bank = 0; bank < mca_cfg.banks; ++bank) {
+	for (bank = 0; bank < this_cpu_read(mce_num_banks); ++bank) {
 		if (!(per_cpu(bank_map, cpu) & (1 << bank)))
 			continue;
 
@@ -1204,7 +1205,7 @@ static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank,
 	u32 low, high;
 	int err;
 
-	if ((bank >= mca_cfg.banks) || (block >= NR_BLOCKS))
+	if ((bank >= per_cpu(mce_num_banks, cpu)) || (block >= NR_BLOCKS))
 		return 0;
 
 	if (rdmsr_safe_on_cpu(cpu, address, &low, &high))
@@ -1438,7 +1439,7 @@ int mce_threshold_remove_device(unsigned int cpu)
 {
 	unsigned int bank;
 
-	for (bank = 0; bank < mca_cfg.banks; ++bank) {
+	for (bank = 0; bank < per_cpu(mce_num_banks, cpu); ++bank) {
 		if (!(per_cpu(bank_map, cpu) & (1 << bank)))
 			continue;
 		threshold_remove_bank(cpu, bank);
@@ -1459,14 +1460,14 @@ int mce_threshold_create_device(unsigned int cpu)
 	if (bp)
 		return 0;
 
-	bp = kcalloc(mca_cfg.banks, sizeof(struct threshold_bank *),
+	bp = kcalloc(per_cpu(mce_num_banks, cpu), sizeof(struct threshold_bank *),
 		     GFP_KERNEL);
 	if (!bp)
 		return -ENOMEM;
 
 	per_cpu(threshold_banks, cpu) = bp;
 
-	for (bank = 0; bank < mca_cfg.banks; ++bank) {
+	for (bank = 0; bank < per_cpu(mce_num_banks, cpu); ++bank) {
 		if (!(per_cpu(bank_map, cpu) & (1 << bank)))
 			continue;
 		err = threshold_create_bank(cpu, bank);
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index c505b10f912a..6813712d8648 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -65,6 +65,8 @@ static DEFINE_MUTEX(mce_sysfs_mutex);
 
 DEFINE_PER_CPU(unsigned, mce_exception_count);
 
+DEFINE_PER_CPU_READ_MOSTLY(unsigned int, mce_num_banks);
+
 struct mce_bank {
 	u64			ctl;			/* subevents to enable */
 	bool			init;			/* initialise bank? */
@@ -701,7 +703,7 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
 	if (flags & MCP_TIMESTAMP)
 		m.tsc = rdtsc();
 
-	for (i = 0; i < mca_cfg.banks; i++) {
+	for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
 		if (!mce_banks[i].ctl || !test_bit(i, *b))
 			continue;
 
@@ -803,7 +805,7 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp,
 	char *tmp;
 	int i;
 
-	for (i = 0; i < mca_cfg.banks; i++) {
+	for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
 		m->status = mce_rdmsrl(msr_ops.status(i));
 		if (!(m->status & MCI_STATUS_VAL))
 			continue;
@@ -1083,7 +1085,7 @@ static void mce_clear_state(unsigned long *toclear)
 {
 	int i;
 
-	for (i = 0; i < mca_cfg.banks; i++) {
+	for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
 		if (test_bit(i, toclear))
 			mce_wrmsrl(msr_ops.status(i), 0);
 	}
@@ -1141,7 +1143,7 @@ static void __mc_scan_banks(struct mce *m, struct mce *final,
 	struct mca_config *cfg = &mca_cfg;
 	int severity, i;
 
-	for (i = 0; i < cfg->banks; i++) {
+	for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
 		__clear_bit(i, toclear);
 		if (!test_bit(i, valid_banks))
 			continue;
@@ -1482,9 +1484,10 @@ EXPORT_SYMBOL_GPL(mce_notify_irq);
 static void __mcheck_cpu_mce_banks_init(void)
 {
 	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
+	u8 n_banks = this_cpu_read(mce_num_banks);
 	int i;
 
-	for (i = 0; i < MAX_NR_BANKS; i++) {
+	for (i = 0; i < n_banks; i++) {
 		struct mce_bank *b = &mce_banks[i];
 
 		b->ctl = -1ULL;
@@ -1503,10 +1506,14 @@ static void __mcheck_cpu_cap_init(void)
 	rdmsrl(MSR_IA32_MCG_CAP, cap);
 
 	b = cap & MCG_BANKCNT_MASK;
-	if (WARN_ON_ONCE(b > MAX_NR_BANKS))
+
+	if (b > MAX_NR_BANKS) {
+		pr_warn("CPU%d: Using only %u machine check banks out of %u\n",
+			smp_processor_id(), MAX_NR_BANKS, b);
 		b = MAX_NR_BANKS;
+	}
 
-	mca_cfg.banks = max(mca_cfg.banks, b);
+	this_cpu_write(mce_num_banks, b);
 
 	__mcheck_cpu_mce_banks_init();
 
@@ -1545,7 +1552,7 @@ static void __mcheck_cpu_init_clear_banks(void)
 	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
 	int i;
 
-	for (i = 0; i < mca_cfg.banks; i++) {
+	for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
 		struct mce_bank *b = &mce_banks[i];
 
 		if (!b->init)
@@ -1596,7 +1603,7 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
 
 	/* This should be disabled by the BIOS, but isn't always */
 	if (c->x86_vendor == X86_VENDOR_AMD) {
-		if (c->x86 == 15 && cfg->banks > 4) {
+		if (c->x86 == 15 && this_cpu_read(mce_num_banks) > 4) {
 			/*
 			 * disable GART TBL walk error reporting, which
 			 * trips off incorrectly with the IOMMU & 3ware
@@ -1615,7 +1622,7 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
 		 * Various K7s with broken bank 0 around. Always disable
 		 * by default.
 		 */
-		if (c->x86 == 6 && cfg->banks > 0)
+		if (c->x86 == 6 && this_cpu_read(mce_num_banks) > 0)
 			mce_banks[0].ctl = 0;
 
 		/*
@@ -1637,7 +1644,7 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
 		 * valid event later, merely don't write CTL0.
 		 */
 
-		if (c->x86 == 6 && c->x86_model < 0x1A && cfg->banks > 0)
+		if (c->x86 == 6 && c->x86_model < 0x1A && this_cpu_read(mce_num_banks) > 0)
 			mce_banks[0].init = 0;
 
 		/*
@@ -1873,7 +1880,7 @@ static void __mce_disable_bank(void *arg)
 
 void mce_disable_bank(int bank)
 {
-	if (bank >= mca_cfg.banks) {
+	if (bank >= this_cpu_read(mce_num_banks)) {
 		pr_warn(FW_BUG
 			"Ignoring request to disable invalid MCA bank %d.\n",
 			bank);
@@ -1962,7 +1969,7 @@ static void mce_disable_error_reporting(void)
 	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
 	int i;
 
-	for (i = 0; i < mca_cfg.banks; i++) {
+	for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
 		struct mce_bank *b = &mce_banks[i];
 
 		if (b->init)
@@ -2073,7 +2080,7 @@ static ssize_t show_bank(struct device *s, struct device_attribute *attr,
 	u8 bank = attr_to_bank(attr)->bank;
 	struct mce_bank *b;
 
-	if (bank >= mca_cfg.banks)
+	if (bank >= per_cpu(mce_num_banks, s->id))
 		return -EINVAL;
 
 	b = &per_cpu(mce_banks_array, s->id)[bank];
@@ -2091,7 +2098,7 @@ static ssize_t set_bank(struct device *s, struct device_attribute *attr,
 	if (kstrtou64(buf, 0, &new) < 0)
 		return -EINVAL;
 
-	if (bank >= mca_cfg.banks)
+	if (bank >= per_cpu(mce_num_banks, s->id))
 		return -EINVAL;
 
 	b = &per_cpu(mce_banks_array, s->id)[bank];
@@ -2243,7 +2250,7 @@ static int mce_device_create(unsigned int cpu)
 		if (err)
 			goto error;
 	}
-	for (j = 0; j < mca_cfg.banks; j++) {
+	for (j = 0; j < per_cpu(mce_num_banks, cpu); j++) {
 		err = device_create_file(dev, &mce_bank_devs[j].attr);
 		if (err)
 			goto error2;
@@ -2275,7 +2282,7 @@ static void mce_device_remove(unsigned int cpu)
 	for (i = 0; mce_device_attrs[i]; i++)
 		device_remove_file(dev, mce_device_attrs[i]);
 
-	for (i = 0; i < mca_cfg.banks; i++)
+	for (i = 0; i < per_cpu(mce_num_banks, cpu); i++)
 		device_remove_file(dev, &mce_bank_devs[i].attr);
 
 	device_unregister(dev);
@@ -2305,7 +2312,7 @@ static void mce_reenable_cpu(void)
 
 	if (!cpuhp_tasks_frozen)
 		cmci_reenable();
-	for (i = 0; i < mca_cfg.banks; i++) {
+	for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
 		struct mce_bank *b = &mce_banks[i];
 
 		if (b->init)
@@ -2493,8 +2500,6 @@ EXPORT_SYMBOL_GPL(mcsafe_key);
 
 static int __init mcheck_late_init(void)
 {
-	pr_info("Using %d MCE banks\n", mca_cfg.banks);
-
 	if (mca_cfg.recovery)
 		static_branch_inc(&mcsafe_key);
 
diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h
index 35b3e5c02c1c..43031db429d2 100644
--- a/arch/x86/kernel/cpu/mce/internal.h
+++ b/arch/x86/kernel/cpu/mce/internal.h
@@ -118,7 +118,6 @@ struct mca_config {
 	      bios_cmci_threshold	: 1,
 	      __reserved		: 59;
 
-	u8 banks;
 	s8 bootlog;
 	int tolerant;
 	int monarch_timeout;
@@ -127,6 +126,7 @@ struct mca_config {
 };
 
 extern struct mca_config mca_cfg;
+DECLARE_PER_CPU_READ_MOSTLY(unsigned int, mce_num_banks);
 
 struct mce_vendor_flags {
 	/*
-- 
2.17.1

[PATCH v4 5/5] x86/MCE: Determine MCA banks' init state properly

[Ghannam, Yazen]

From: Yazen Ghannam <yazen.ghannam@amd.com>

The OS is expected to write all bits to MCA_CTL for each bank,
thus enabling error reporting in all banks. However, some banks
may be unused in which case the registers for such banks are
Read-as-Zero/Writes-Ignored. Also, the OS may avoid setting some control
bits because of quirks, etc.

A bank can be considered uninitialized if the MCA_CTL register returns
zero. This is because either the OS did not write anything or because
the hardware is enforcing RAZ/WI for the bank.

Set a bank's init value based on if the control bits are set or not in
hardware. Return an error code in the sysfs interface for uninitialized
banks.

Do a final bank init check in a separate function which is not part of
any user-controlled code flows. This is so a user may enable/disable a
bank during runtime without having to restart their system.

 [ bp: Massage a bit. Discover bank init state at boot. ]

Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com>
---
Link:
https://lkml.kernel.org/r/20190430203206.104163-6-Yazen.Ghannam@amd.com

v3->v4:
* Patch 5 version 3 was zapped.
* This is based on new patch from Boris which was based on Patch 6 version 3.
* Reworked new patch to fix sysfs issue with disabled banks.

v2->v3:
* No change.

v1->v2:
* No change.

 arch/x86/kernel/cpu/mce/core.c | 39 ++++++++++++++++++++++++++++++++++
 1 file changed, 39 insertions(+)

diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 6813712d8648..ae7723a942f6 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -1490,6 +1490,11 @@ static void __mcheck_cpu_mce_banks_init(void)
 	for (i = 0; i < n_banks; i++) {
 		struct mce_bank *b = &mce_banks[i];
 
+		/*
+		 * Init them all, __mcheck_cpu_apply_quirks() is going to apply
+		 * the required vendor quirks before
+		 * __mcheck_cpu_init_clear_banks() does the final bank setup.
+		 */
 		b->ctl = -1ULL;
 		b->init = 1;
 	}
@@ -1562,6 +1567,33 @@ static void __mcheck_cpu_init_clear_banks(void)
 	}
 }
 
+/*
+ * Do a final check to see if there are any unused/RAZ banks.
+ *
+ * This must be done after the banks have been initialized and any quirks have
+ * been applied.
+ *
+ * Do not call this from any user-initialed flows, e.g. CPU hotplug or sysfs.
+ * Otherwise, a user who disables a bank will not be able to re-enable it
+ * without a system reboot.
+ */
+static void __mcheck_cpu_check_banks(void)
+{
+	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
+	u64 msrval;
+	int i;
+
+	for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
+		struct mce_bank *b = &mce_banks[i];
+
+		if (!b->init)
+			continue;
+
+		rdmsrl(msr_ops.ctl(i), msrval);
+		b->init = !!msrval;
+	}
+}
+
 /*
  * During IFU recovery Sandy Bridge -EP4S processors set the RIPV and
  * EIPV bits in MCG_STATUS to zero on the affected logical processor (SDM
@@ -1849,6 +1881,7 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c)
 	__mcheck_cpu_init_generic();
 	__mcheck_cpu_init_vendor(c);
 	__mcheck_cpu_init_clear_banks();
+	__mcheck_cpu_check_banks();
 	__mcheck_cpu_setup_timer();
 }
 
@@ -2085,6 +2118,9 @@ static ssize_t show_bank(struct device *s, struct device_attribute *attr,
 
 	b = &per_cpu(mce_banks_array, s->id)[bank];
 
+	if (!b->init)
+		return -ENODEV;
+
 	return sprintf(buf, "%llx\n", b->ctl);
 }
 
@@ -2103,6 +2139,9 @@ static ssize_t set_bank(struct device *s, struct device_attribute *attr,
 
 	b = &per_cpu(mce_banks_array, s->id)[bank];
 
+	if (!b->init)
+		return -ENODEV;
+
 	b->ctl = new;
 	mce_restart();
 
-- 
2.17.1

[tip:ras/core] x86/MCE: Make struct mce_banks[] static

[tip-bot for Yazen Ghannam]

Commit-ID:  95fdce6b24f3526c2bd1aad15978d238b79da6bd
Gitweb:     https://git.kernel.org/tip/95fdce6b24f3526c2bd1aad15978d238b79da6bd
Author:     Yazen Ghannam <yazen.ghannam@amd.com>
AuthorDate: Fri, 7 Jun 2019 20:18:03 +0000
Committer:  Borislav Petkov <bp@suse.de>
CommitDate: Tue, 11 Jun 2019 15:13:51 +0200

x86/MCE: Make struct mce_banks[] static

The struct mce_banks[] array is only used in mce/core.c so move its
definition there and make it static. Also, change the "init" field to
bool type.

Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: linux-edac <linux-edac@vger.kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tony Luck <tony.luck@intel.com>
Cc: "x86@kernel.org" <x86@kernel.org>
Link: https://lkml.kernel.org/r/20190607201752.221446-2-Yazen.Ghannam@amd.com
---
 arch/x86/kernel/cpu/mce/core.c     | 11 ++++++++++-
 arch/x86/kernel/cpu/mce/internal.h | 10 ----------
 2 files changed, 10 insertions(+), 11 deletions(-)

diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 282916f3b8d8..55bdbedde0b8 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -65,7 +65,16 @@ static DEFINE_MUTEX(mce_sysfs_mutex);
 
 DEFINE_PER_CPU(unsigned, mce_exception_count);
 
-struct mce_bank *mce_banks __read_mostly;
+#define ATTR_LEN               16
+/* One object for each MCE bank, shared by all CPUs */
+struct mce_bank {
+	u64			ctl;			/* subevents to enable */
+	bool			init;			/* initialise bank? */
+	struct device_attribute	attr;			/* device attribute */
+	char			attrname[ATTR_LEN];	/* attribute name */
+};
+
+static struct mce_bank *mce_banks __read_mostly;
 struct mce_vendor_flags mce_flags __read_mostly;
 
 struct mca_config mca_cfg __read_mostly = {
diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h
index a34b55baa7aa..35b3e5c02c1c 100644
--- a/arch/x86/kernel/cpu/mce/internal.h
+++ b/arch/x86/kernel/cpu/mce/internal.h
@@ -22,17 +22,8 @@ enum severity_level {
 
 extern struct blocking_notifier_head x86_mce_decoder_chain;
 
-#define ATTR_LEN		16
 #define INITIAL_CHECK_INTERVAL	5 * 60 /* 5 minutes */
 
-/* One object for each MCE bank, shared by all CPUs */
-struct mce_bank {
-	u64			ctl;			/* subevents to enable */
-	unsigned char init;				/* initialise bank? */
-	struct device_attribute attr;			/* device attribute */
-	char			attrname[ATTR_LEN];	/* attribute name */
-};
-
 struct mce_evt_llist {
 	struct llist_node llnode;
 	struct mce mce;
@@ -47,7 +38,6 @@ struct llist_node *mce_gen_pool_prepare_records(void);
 extern int (*mce_severity)(struct mce *a, int tolerant, char **msg, bool is_excp);
 struct dentry *mce_get_debugfs_dir(void);
 
-extern struct mce_bank *mce_banks;
 extern mce_banks_t mce_banks_ce_disabled;
 
 #ifdef CONFIG_X86_MCE_INTEL

[tip:ras/core] x86/MCE: Make mce_banks a per-CPU array

[tip-bot for Yazen Ghannam]

Commit-ID:  b4914508f1fe0eca1cd011b6026ff762a1aa62d5
Gitweb:     https://git.kernel.org/tip/b4914508f1fe0eca1cd011b6026ff762a1aa62d5
Author:     Yazen Ghannam <yazen.ghannam@amd.com>
AuthorDate: Fri, 7 Jun 2019 20:18:04 +0000
Committer:  Borislav Petkov <bp@suse.de>
CommitDate: Tue, 11 Jun 2019 15:22:13 +0200

x86/MCE: Make mce_banks a per-CPU array

Current AMD systems have unique MCA banks per logical CPU even though
the type of the banks may all align to the same bank number. Each CPU
will have control of a set of MCA banks in the hardware and these are
not shared with other CPUs.

For example, bank 0 may be the Load-Store Unit on every logical CPU, but
each bank 0 is a unique structure in the hardware. In other words, there
isn't a *single* Load-Store Unit at MCA bank 0 that all logical CPUs
share.

This idea extends even to non-core MCA banks. For example, CPU0 and CPU4
may see a Unified Memory Controller at bank 15, but each CPU is actually
seeing a unique hardware structure that is not shared with other CPUs.

Because the MCA banks are all unique hardware structures, it would be
good to control them in a more granular way. For example, if there is a
known issue with the Floating Point Unit on CPU5 and a user wishes to
disable an error type on the Floating Point Unit, then it would be good
to do this only for CPU5 rather than all CPUs.

Also, future AMD systems may have heterogeneous MCA banks. Meaning
the bank numbers may not necessarily represent the same types between
CPUs. For example, bank 20 visible to CPU0 may be a Unified Memory
Controller and bank 20 visible to CPU4 may be a Coherent Slave. So
granular control will be even more necessary should the user wish to
control specific MCA banks.

Split the device attributes from struct mce_bank leaving only the MCA
bank control fields.

Make struct mce_banks[] per_cpu in order to have more granular control
over individual MCA banks in the hardware.

Allocate the device attributes statically based on the maximum number of
MCA banks supported. The sysfs interface will use as many as needed per
CPU. Currently, this is set to mca_cfg.banks, but will be changed to a
per_cpu bank count in a future patch.

Allocate the MCA control bits statically. This is in order to avoid
locking warnings when memory is allocated during secondary CPUs' init
sequences.

Also, remove the now unnecessary return values from
__mcheck_cpu_mce_banks_init() and __mcheck_cpu_cap_init().

Redo the sysfs store/show functions to handle the per_cpu mce_banks[].

 [ bp: s/mce_banks_percpu/mce_banks_array/g ]

[ Locking issue reported by ]
Reported-by: kernel test robot <rong.a.chen@intel.com>
Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "linux-edac@vger.kernel.org" <linux-edac@vger.kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tony Luck <tony.luck@intel.com>
Cc: "x86@kernel.org" <x86@kernel.org>
Link: https://lkml.kernel.org/r/20190607201752.221446-3-Yazen.Ghannam@amd.com
---
 arch/x86/kernel/cpu/mce/core.c | 76 ++++++++++++++++++++++++++----------------
 1 file changed, 48 insertions(+), 28 deletions(-)

diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 55bdbedde0b8..49fac95d036b 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -65,16 +65,21 @@ static DEFINE_MUTEX(mce_sysfs_mutex);
 
 DEFINE_PER_CPU(unsigned, mce_exception_count);
 
-#define ATTR_LEN               16
-/* One object for each MCE bank, shared by all CPUs */
 struct mce_bank {
 	u64			ctl;			/* subevents to enable */
 	bool			init;			/* initialise bank? */
+};
+static DEFINE_PER_CPU_READ_MOSTLY(struct mce_bank[MAX_NR_BANKS], mce_banks_array);
+
+#define ATTR_LEN               16
+/* One object for each MCE bank, shared by all CPUs */
+struct mce_bank_dev {
 	struct device_attribute	attr;			/* device attribute */
 	char			attrname[ATTR_LEN];	/* attribute name */
+	u8			bank;			/* bank number */
 };
+static struct mce_bank_dev mce_bank_devs[MAX_NR_BANKS];
 
-static struct mce_bank *mce_banks __read_mostly;
 struct mce_vendor_flags mce_flags __read_mostly;
 
 struct mca_config mca_cfg __read_mostly = {
@@ -684,6 +689,7 @@ DEFINE_PER_CPU(unsigned, mce_poll_count);
  */
 bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
 {
+	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
 	bool error_seen = false;
 	struct mce m;
 	int i;
@@ -1131,6 +1137,7 @@ static void __mc_scan_banks(struct mce *m, struct mce *final,
 			    unsigned long *toclear, unsigned long *valid_banks,
 			    int no_way_out, int *worst)
 {
+	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
 	struct mca_config *cfg = &mca_cfg;
 	int severity, i;
 
@@ -1472,27 +1479,23 @@ int mce_notify_irq(void)
 }
 EXPORT_SYMBOL_GPL(mce_notify_irq);
 
-static int __mcheck_cpu_mce_banks_init(void)
+static void __mcheck_cpu_mce_banks_init(void)
 {
+	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
 	int i;
 
-	mce_banks = kcalloc(MAX_NR_BANKS, sizeof(struct mce_bank), GFP_KERNEL);
-	if (!mce_banks)
-		return -ENOMEM;
-
 	for (i = 0; i < MAX_NR_BANKS; i++) {
 		struct mce_bank *b = &mce_banks[i];
 
 		b->ctl = -1ULL;
 		b->init = 1;
 	}
-	return 0;
 }
 
 /*
  * Initialize Machine Checks for a CPU.
  */
-static int __mcheck_cpu_cap_init(void)
+static void __mcheck_cpu_cap_init(void)
 {
 	u64 cap;
 	u8 b;
@@ -1505,11 +1508,7 @@ static int __mcheck_cpu_cap_init(void)
 
 	mca_cfg.banks = max(mca_cfg.banks, b);
 
-	if (!mce_banks) {
-		int err = __mcheck_cpu_mce_banks_init();
-		if (err)
-			return err;
-	}
+	__mcheck_cpu_mce_banks_init();
 
 	/* Use accurate RIP reporting if available. */
 	if ((cap & MCG_EXT_P) && MCG_EXT_CNT(cap) >= 9)
@@ -1517,8 +1516,6 @@ static int __mcheck_cpu_cap_init(void)
 
 	if (cap & MCG_SER_P)
 		mca_cfg.ser = 1;
-
-	return 0;
 }
 
 static void __mcheck_cpu_init_generic(void)
@@ -1545,6 +1542,7 @@ static void __mcheck_cpu_init_generic(void)
 
 static void __mcheck_cpu_init_clear_banks(void)
 {
+	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
 	int i;
 
 	for (i = 0; i < mca_cfg.banks; i++) {
@@ -1588,6 +1586,7 @@ static void quirk_sandybridge_ifu(int bank, struct mce *m, struct pt_regs *regs)
 /* Add per CPU specific workarounds here */
 static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
 {
+	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
 	struct mca_config *cfg = &mca_cfg;
 
 	if (c->x86_vendor == X86_VENDOR_UNKNOWN) {
@@ -1824,7 +1823,9 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c)
 	if (!mce_available(c))
 		return;
 
-	if (__mcheck_cpu_cap_init() < 0 || __mcheck_cpu_apply_quirks(c) < 0) {
+	__mcheck_cpu_cap_init();
+
+	if (__mcheck_cpu_apply_quirks(c) < 0) {
 		mca_cfg.disabled = 1;
 		return;
 	}
@@ -1958,6 +1959,7 @@ int __init mcheck_init(void)
  */
 static void mce_disable_error_reporting(void)
 {
+	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
 	int i;
 
 	for (i = 0; i < mca_cfg.banks; i++) {
@@ -2060,26 +2062,41 @@ static struct bus_type mce_subsys = {
 
 DEFINE_PER_CPU(struct device *, mce_device);
 
-static inline struct mce_bank *attr_to_bank(struct device_attribute *attr)
+static inline struct mce_bank_dev *attr_to_bank(struct device_attribute *attr)
 {
-	return container_of(attr, struct mce_bank, attr);
+	return container_of(attr, struct mce_bank_dev, attr);
 }
 
 static ssize_t show_bank(struct device *s, struct device_attribute *attr,
 			 char *buf)
 {
-	return sprintf(buf, "%llx\n", attr_to_bank(attr)->ctl);
+	u8 bank = attr_to_bank(attr)->bank;
+	struct mce_bank *b;
+
+	if (bank >= mca_cfg.banks)
+		return -EINVAL;
+
+	b = &per_cpu(mce_banks_array, s->id)[bank];
+
+	return sprintf(buf, "%llx\n", b->ctl);
 }
 
 static ssize_t set_bank(struct device *s, struct device_attribute *attr,
 			const char *buf, size_t size)
 {
+	u8 bank = attr_to_bank(attr)->bank;
+	struct mce_bank *b;
 	u64 new;
 
 	if (kstrtou64(buf, 0, &new) < 0)
 		return -EINVAL;
 
-	attr_to_bank(attr)->ctl = new;
+	if (bank >= mca_cfg.banks)
+		return -EINVAL;
+
+	b = &per_cpu(mce_banks_array, s->id)[bank];
+
+	b->ctl = new;
 	mce_restart();
 
 	return size;
@@ -2194,7 +2211,7 @@ static void mce_device_release(struct device *dev)
 	kfree(dev);
 }
 
-/* Per cpu device init. All of the cpus still share the same ctrl bank: */
+/* Per CPU device init. All of the CPUs still share the same bank device: */
 static int mce_device_create(unsigned int cpu)
 {
 	struct device *dev;
@@ -2227,7 +2244,7 @@ static int mce_device_create(unsigned int cpu)
 			goto error;
 	}
 	for (j = 0; j < mca_cfg.banks; j++) {
-		err = device_create_file(dev, &mce_banks[j].attr);
+		err = device_create_file(dev, &mce_bank_devs[j].attr);
 		if (err)
 			goto error2;
 	}
@@ -2237,7 +2254,7 @@ static int mce_device_create(unsigned int cpu)
 	return 0;
 error2:
 	while (--j >= 0)
-		device_remove_file(dev, &mce_banks[j].attr);
+		device_remove_file(dev, &mce_bank_devs[j].attr);
 error:
 	while (--i >= 0)
 		device_remove_file(dev, mce_device_attrs[i]);
@@ -2259,7 +2276,7 @@ static void mce_device_remove(unsigned int cpu)
 		device_remove_file(dev, mce_device_attrs[i]);
 
 	for (i = 0; i < mca_cfg.banks; i++)
-		device_remove_file(dev, &mce_banks[i].attr);
+		device_remove_file(dev, &mce_bank_devs[i].attr);
 
 	device_unregister(dev);
 	cpumask_clear_cpu(cpu, mce_device_initialized);
@@ -2280,6 +2297,7 @@ static void mce_disable_cpu(void)
 
 static void mce_reenable_cpu(void)
 {
+	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
 	int i;
 
 	if (!mce_available(raw_cpu_ptr(&cpu_info)))
@@ -2337,10 +2355,12 @@ static __init void mce_init_banks(void)
 {
 	int i;
 
-	for (i = 0; i < mca_cfg.banks; i++) {
-		struct mce_bank *b = &mce_banks[i];
+	for (i = 0; i < MAX_NR_BANKS; i++) {
+		struct mce_bank_dev *b = &mce_bank_devs[i];
 		struct device_attribute *a = &b->attr;
 
+		b->bank = i;
+
 		sysfs_attr_init(&a->attr);
 		a->attr.name	= b->attrname;
 		snprintf(b->attrname, ATTR_LEN, "bank%d", i);

[tip:ras/core] x86/MCE/AMD: Don't cache block addresses on SMCA systems

[tip-bot for Yazen Ghannam]

Commit-ID:  95d057f54664f3c6e8f650faf5690b82b30a9e52
Gitweb:     https://git.kernel.org/tip/95d057f54664f3c6e8f650faf5690b82b30a9e52
Author:     Yazen Ghannam <yazen.ghannam@amd.com>
AuthorDate: Fri, 7 Jun 2019 20:18:04 +0000
Committer:  Borislav Petkov <bp@suse.de>
CommitDate: Tue, 11 Jun 2019 15:22:41 +0200

x86/MCE/AMD: Don't cache block addresses on SMCA systems

On legacy systems, the addresses of the MCA_MISC* registers need to be
recursively discovered based on a Block Pointer field in the registers.

On Scalable MCA systems, the register space is fixed, and particular
addresses can be derived by regular offsets for bank and register type.
This fixed address space includes the MCA_MISC* registers.

MCA_MISC0 is always available for each MCA bank. MCA_MISC1 through
MCA_MISC4 are considered available if MCA_MISC0[BlkPtr]=1.

Cache the value of MCA_MISC0[BlkPtr] for each bank and per CPU. This
needs to be done only during init. The values should be saved per CPU
to accommodate heterogeneous SMCA systems.

Redo smca_get_block_address() to directly return the block addresses.

Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "linux-edac@vger.kernel.org" <linux-edac@vger.kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tony Luck <tony.luck@intel.com>
Cc: "x86@kernel.org" <x86@kernel.org>
Link: https://lkml.kernel.org/r/20190607201752.221446-4-Yazen.Ghannam@amd.com
---
 arch/x86/kernel/cpu/mce/amd.c | 73 ++++++++++++++++++++++---------------------
 1 file changed, 37 insertions(+), 36 deletions(-)

diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index d904aafe6409..d4d6e4b7f9dc 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -101,11 +101,6 @@ static struct smca_bank_name smca_names[] = {
 	[SMCA_PCIE]	= { "pcie",		"PCI Express Unit" },
 };
 
-static u32 smca_bank_addrs[MAX_NR_BANKS][NR_BLOCKS] __ro_after_init =
-{
-	[0 ... MAX_NR_BANKS - 1] = { [0 ... NR_BLOCKS - 1] = -1 }
-};
-
 static const char *smca_get_name(enum smca_bank_types t)
 {
 	if (t >= N_SMCA_BANK_TYPES)
@@ -199,6 +194,9 @@ static char buf_mcatype[MAX_MCATYPE_NAME_LEN];
 static DEFINE_PER_CPU(struct threshold_bank **, threshold_banks);
 static DEFINE_PER_CPU(unsigned int, bank_map);	/* see which banks are on */
 
+/* Map of banks that have more than MCA_MISC0 available. */
+static DEFINE_PER_CPU(u32, smca_misc_banks_map);
+
 static void amd_threshold_interrupt(void);
 static void amd_deferred_error_interrupt(void);
 
@@ -208,6 +206,28 @@ static void default_deferred_error_interrupt(void)
 }
 void (*deferred_error_int_vector)(void) = default_deferred_error_interrupt;
 
+static void smca_set_misc_banks_map(unsigned int bank, unsigned int cpu)
+{
+	u32 low, high;
+
+	/*
+	 * For SMCA enabled processors, BLKPTR field of the first MISC register
+	 * (MCx_MISC0) indicates presence of additional MISC regs set (MISC1-4).
+	 */
+	if (rdmsr_safe(MSR_AMD64_SMCA_MCx_CONFIG(bank), &low, &high))
+		return;
+
+	if (!(low & MCI_CONFIG_MCAX))
+		return;
+
+	if (rdmsr_safe(MSR_AMD64_SMCA_MCx_MISC(bank), &low, &high))
+		return;
+
+	if (low & MASK_BLKPTR_LO)
+		per_cpu(smca_misc_banks_map, cpu) |= BIT(bank);
+
+}
+
 static void smca_configure(unsigned int bank, unsigned int cpu)
 {
 	unsigned int i, hwid_mcatype;
@@ -245,6 +265,8 @@ static void smca_configure(unsigned int bank, unsigned int cpu)
 		wrmsr(smca_config, low, high);
 	}
 
+	smca_set_misc_banks_map(bank, cpu);
+
 	/* Return early if this bank was already initialized. */
 	if (smca_banks[bank].hwid)
 		return;
@@ -455,42 +477,21 @@ static void deferred_error_interrupt_enable(struct cpuinfo_x86 *c)
 	wrmsr(MSR_CU_DEF_ERR, low, high);
 }
 
-static u32 smca_get_block_address(unsigned int bank, unsigned int block)
+static u32 smca_get_block_address(unsigned int bank, unsigned int block,
+				  unsigned int cpu)
 {
-	u32 low, high;
-	u32 addr = 0;
-
-	if (smca_get_bank_type(bank) == SMCA_RESERVED)
-		return addr;
-
 	if (!block)
 		return MSR_AMD64_SMCA_MCx_MISC(bank);
 
-	/* Check our cache first: */
-	if (smca_bank_addrs[bank][block] != -1)
-		return smca_bank_addrs[bank][block];
-
-	/*
-	 * For SMCA enabled processors, BLKPTR field of the first MISC register
-	 * (MCx_MISC0) indicates presence of additional MISC regs set (MISC1-4).
-	 */
-	if (rdmsr_safe(MSR_AMD64_SMCA_MCx_CONFIG(bank), &low, &high))
-		goto out;
-
-	if (!(low & MCI_CONFIG_MCAX))
-		goto out;
-
-	if (!rdmsr_safe(MSR_AMD64_SMCA_MCx_MISC(bank), &low, &high) &&
-	    (low & MASK_BLKPTR_LO))
-		addr = MSR_AMD64_SMCA_MCx_MISCy(bank, block - 1);
+	if (!(per_cpu(smca_misc_banks_map, cpu) & BIT(bank)))
+		return 0;
 
-out:
-	smca_bank_addrs[bank][block] = addr;
-	return addr;
+	return MSR_AMD64_SMCA_MCx_MISCy(bank, block - 1);
 }
 
 static u32 get_block_address(u32 current_addr, u32 low, u32 high,
-			     unsigned int bank, unsigned int block)
+			     unsigned int bank, unsigned int block,
+			     unsigned int cpu)
 {
 	u32 addr = 0, offset = 0;
 
@@ -498,7 +499,7 @@ static u32 get_block_address(u32 current_addr, u32 low, u32 high,
 		return addr;
 
 	if (mce_flags.smca)
-		return smca_get_block_address(bank, block);
+		return smca_get_block_address(bank, block, cpu);
 
 	/* Fall back to method we used for older processors: */
 	switch (block) {
@@ -637,7 +638,7 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
 		disable_err_thresholding(c, bank);
 
 		for (block = 0; block < NR_BLOCKS; ++block) {
-			address = get_block_address(address, low, high, bank, block);
+			address = get_block_address(address, low, high, bank, block, cpu);
 			if (!address)
 				break;
 
@@ -1254,7 +1255,7 @@ static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank,
 	if (err)
 		goto out_free;
 recurse:
-	address = get_block_address(address, low, high, bank, ++block);
+	address = get_block_address(address, low, high, bank, ++block, cpu);
 	if (!address)
 		return 0;
 

[tip:ras/core] x86/MCE: Make the number of MCA banks a per-CPU variable

[tip-bot for Yazen Ghannam]

Commit-ID:  c7d314f386e987be8b51eeb7dd947756ae23f6b6
Gitweb:     https://git.kernel.org/tip/c7d314f386e987be8b51eeb7dd947756ae23f6b6
Author:     Yazen Ghannam <yazen.ghannam@amd.com>
AuthorDate: Fri, 7 Jun 2019 20:18:05 +0000
Committer:  Borislav Petkov <bp@suse.de>
CommitDate: Tue, 11 Jun 2019 15:23:09 +0200

x86/MCE: Make the number of MCA banks a per-CPU variable

The number of MCA banks is provided per logical CPU. Historically, this
number has been the same across all CPUs, but this is not an
architectural guarantee. Future AMD systems may have MCA bank counts
that vary between logical CPUs in a system.

This issue was partially addressed in

  006c077041dc ("x86/mce: Handle varying MCA bank counts")

by allocating structures using the maximum number of MCA banks and by
saving the maximum MCA bank count in a system as the global count. This
means that some extra structures are allocated. Also, this means that
CPUs will spend more time in the #MC and other handlers checking extra
MCA banks.

Thus, define the number of MCA banks as a per-CPU variable.

 [ bp: Make mce_num_banks an unsigned int. ]

Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "linux-edac@vger.kernel.org" <linux-edac@vger.kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tony Luck <tony.luck@intel.com>
Cc: "x86@kernel.org" <x86@kernel.org>
Link: https://lkml.kernel.org/r/20190607201752.221446-5-Yazen.Ghannam@amd.com
---
 arch/x86/kernel/cpu/mce/amd.c      | 19 ++++++++--------
 arch/x86/kernel/cpu/mce/core.c     | 45 +++++++++++++++++++++-----------------
 arch/x86/kernel/cpu/mce/internal.h |  2 +-
 3 files changed, 36 insertions(+), 30 deletions(-)

diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index d4d6e4b7f9dc..fb5c935af2c5 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -495,7 +495,7 @@ static u32 get_block_address(u32 current_addr, u32 low, u32 high,
 {
 	u32 addr = 0, offset = 0;
 
-	if ((bank >= mca_cfg.banks) || (block >= NR_BLOCKS))
+	if ((bank >= per_cpu(mce_num_banks, cpu)) || (block >= NR_BLOCKS))
 		return addr;
 
 	if (mce_flags.smca)
@@ -627,11 +627,12 @@ void disable_err_thresholding(struct cpuinfo_x86 *c, unsigned int bank)
 /* cpu init entry point, called from mce.c with preempt off */
 void mce_amd_feature_init(struct cpuinfo_x86 *c)
 {
-	u32 low = 0, high = 0, address = 0;
 	unsigned int bank, block, cpu = smp_processor_id();
+	u32 low = 0, high = 0, address = 0;
 	int offset = -1;
 
-	for (bank = 0; bank < mca_cfg.banks; ++bank) {
+
+	for (bank = 0; bank < this_cpu_read(mce_num_banks); ++bank) {
 		if (mce_flags.smca)
 			smca_configure(bank, cpu);
 
@@ -976,7 +977,7 @@ static void amd_deferred_error_interrupt(void)
 {
 	unsigned int bank;
 
-	for (bank = 0; bank < mca_cfg.banks; ++bank)
+	for (bank = 0; bank < this_cpu_read(mce_num_banks); ++bank)
 		log_error_deferred(bank);
 }
 
@@ -1017,7 +1018,7 @@ static void amd_threshold_interrupt(void)
 	struct threshold_block *first_block = NULL, *block = NULL, *tmp = NULL;
 	unsigned int bank, cpu = smp_processor_id();
 
-	for (bank = 0; bank < mca_cfg.banks; ++bank) {
+	for (bank = 0; bank < this_cpu_read(mce_num_banks); ++bank) {
 		if (!(per_cpu(bank_map, cpu) & (1 << bank)))
 			continue;
 
@@ -1204,7 +1205,7 @@ static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank,
 	u32 low, high;
 	int err;
 
-	if ((bank >= mca_cfg.banks) || (block >= NR_BLOCKS))
+	if ((bank >= per_cpu(mce_num_banks, cpu)) || (block >= NR_BLOCKS))
 		return 0;
 
 	if (rdmsr_safe_on_cpu(cpu, address, &low, &high))
@@ -1438,7 +1439,7 @@ int mce_threshold_remove_device(unsigned int cpu)
 {
 	unsigned int bank;
 
-	for (bank = 0; bank < mca_cfg.banks; ++bank) {
+	for (bank = 0; bank < per_cpu(mce_num_banks, cpu); ++bank) {
 		if (!(per_cpu(bank_map, cpu) & (1 << bank)))
 			continue;
 		threshold_remove_bank(cpu, bank);
@@ -1459,14 +1460,14 @@ int mce_threshold_create_device(unsigned int cpu)
 	if (bp)
 		return 0;
 
-	bp = kcalloc(mca_cfg.banks, sizeof(struct threshold_bank *),
+	bp = kcalloc(per_cpu(mce_num_banks, cpu), sizeof(struct threshold_bank *),
 		     GFP_KERNEL);
 	if (!bp)
 		return -ENOMEM;
 
 	per_cpu(threshold_banks, cpu) = bp;
 
-	for (bank = 0; bank < mca_cfg.banks; ++bank) {
+	for (bank = 0; bank < per_cpu(mce_num_banks, cpu); ++bank) {
 		if (!(per_cpu(bank_map, cpu) & (1 << bank)))
 			continue;
 		err = threshold_create_bank(cpu, bank);
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 49fac95d036b..10f9f140985e 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -65,6 +65,8 @@ static DEFINE_MUTEX(mce_sysfs_mutex);
 
 DEFINE_PER_CPU(unsigned, mce_exception_count);
 
+DEFINE_PER_CPU_READ_MOSTLY(unsigned int, mce_num_banks);
+
 struct mce_bank {
 	u64			ctl;			/* subevents to enable */
 	bool			init;			/* initialise bank? */
@@ -701,7 +703,7 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
 	if (flags & MCP_TIMESTAMP)
 		m.tsc = rdtsc();
 
-	for (i = 0; i < mca_cfg.banks; i++) {
+	for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
 		if (!mce_banks[i].ctl || !test_bit(i, *b))
 			continue;
 
@@ -803,7 +805,7 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp,
 	char *tmp;
 	int i;
 
-	for (i = 0; i < mca_cfg.banks; i++) {
+	for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
 		m->status = mce_rdmsrl(msr_ops.status(i));
 		if (!(m->status & MCI_STATUS_VAL))
 			continue;
@@ -1083,7 +1085,7 @@ static void mce_clear_state(unsigned long *toclear)
 {
 	int i;
 
-	for (i = 0; i < mca_cfg.banks; i++) {
+	for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
 		if (test_bit(i, toclear))
 			mce_wrmsrl(msr_ops.status(i), 0);
 	}
@@ -1141,7 +1143,7 @@ static void __mc_scan_banks(struct mce *m, struct mce *final,
 	struct mca_config *cfg = &mca_cfg;
 	int severity, i;
 
-	for (i = 0; i < cfg->banks; i++) {
+	for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
 		__clear_bit(i, toclear);
 		if (!test_bit(i, valid_banks))
 			continue;
@@ -1482,9 +1484,10 @@ EXPORT_SYMBOL_GPL(mce_notify_irq);
 static void __mcheck_cpu_mce_banks_init(void)
 {
 	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
+	u8 n_banks = this_cpu_read(mce_num_banks);
 	int i;
 
-	for (i = 0; i < MAX_NR_BANKS; i++) {
+	for (i = 0; i < n_banks; i++) {
 		struct mce_bank *b = &mce_banks[i];
 
 		b->ctl = -1ULL;
@@ -1503,10 +1506,14 @@ static void __mcheck_cpu_cap_init(void)
 	rdmsrl(MSR_IA32_MCG_CAP, cap);
 
 	b = cap & MCG_BANKCNT_MASK;
-	if (WARN_ON_ONCE(b > MAX_NR_BANKS))
+
+	if (b > MAX_NR_BANKS) {
+		pr_warn("CPU%d: Using only %u machine check banks out of %u\n",
+			smp_processor_id(), MAX_NR_BANKS, b);
 		b = MAX_NR_BANKS;
+	}
 
-	mca_cfg.banks = max(mca_cfg.banks, b);
+	this_cpu_write(mce_num_banks, b);
 
 	__mcheck_cpu_mce_banks_init();
 
@@ -1545,7 +1552,7 @@ static void __mcheck_cpu_init_clear_banks(void)
 	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
 	int i;
 
-	for (i = 0; i < mca_cfg.banks; i++) {
+	for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
 		struct mce_bank *b = &mce_banks[i];
 
 		if (!b->init)
@@ -1596,7 +1603,7 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
 
 	/* This should be disabled by the BIOS, but isn't always */
 	if (c->x86_vendor == X86_VENDOR_AMD) {
-		if (c->x86 == 15 && cfg->banks > 4) {
+		if (c->x86 == 15 && this_cpu_read(mce_num_banks) > 4) {
 			/*
 			 * disable GART TBL walk error reporting, which
 			 * trips off incorrectly with the IOMMU & 3ware
@@ -1615,7 +1622,7 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
 		 * Various K7s with broken bank 0 around. Always disable
 		 * by default.
 		 */
-		if (c->x86 == 6 && cfg->banks > 0)
+		if (c->x86 == 6 && this_cpu_read(mce_num_banks) > 0)
 			mce_banks[0].ctl = 0;
 
 		/*
@@ -1637,7 +1644,7 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
 		 * valid event later, merely don't write CTL0.
 		 */
 
-		if (c->x86 == 6 && c->x86_model < 0x1A && cfg->banks > 0)
+		if (c->x86 == 6 && c->x86_model < 0x1A && this_cpu_read(mce_num_banks) > 0)
 			mce_banks[0].init = 0;
 
 		/*
@@ -1873,7 +1880,7 @@ static void __mce_disable_bank(void *arg)
 
 void mce_disable_bank(int bank)
 {
-	if (bank >= mca_cfg.banks) {
+	if (bank >= this_cpu_read(mce_num_banks)) {
 		pr_warn(FW_BUG
 			"Ignoring request to disable invalid MCA bank %d.\n",
 			bank);
@@ -1962,7 +1969,7 @@ static void mce_disable_error_reporting(void)
 	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
 	int i;
 
-	for (i = 0; i < mca_cfg.banks; i++) {
+	for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
 		struct mce_bank *b = &mce_banks[i];
 
 		if (b->init)
@@ -2073,7 +2080,7 @@ static ssize_t show_bank(struct device *s, struct device_attribute *attr,
 	u8 bank = attr_to_bank(attr)->bank;
 	struct mce_bank *b;
 
-	if (bank >= mca_cfg.banks)
+	if (bank >= per_cpu(mce_num_banks, s->id))
 		return -EINVAL;
 
 	b = &per_cpu(mce_banks_array, s->id)[bank];
@@ -2091,7 +2098,7 @@ static ssize_t set_bank(struct device *s, struct device_attribute *attr,
 	if (kstrtou64(buf, 0, &new) < 0)
 		return -EINVAL;
 
-	if (bank >= mca_cfg.banks)
+	if (bank >= per_cpu(mce_num_banks, s->id))
 		return -EINVAL;
 
 	b = &per_cpu(mce_banks_array, s->id)[bank];
@@ -2243,7 +2250,7 @@ static int mce_device_create(unsigned int cpu)
 		if (err)
 			goto error;
 	}
-	for (j = 0; j < mca_cfg.banks; j++) {
+	for (j = 0; j < per_cpu(mce_num_banks, cpu); j++) {
 		err = device_create_file(dev, &mce_bank_devs[j].attr);
 		if (err)
 			goto error2;
@@ -2275,7 +2282,7 @@ static void mce_device_remove(unsigned int cpu)
 	for (i = 0; mce_device_attrs[i]; i++)
 		device_remove_file(dev, mce_device_attrs[i]);
 
-	for (i = 0; i < mca_cfg.banks; i++)
+	for (i = 0; i < per_cpu(mce_num_banks, cpu); i++)
 		device_remove_file(dev, &mce_bank_devs[i].attr);
 
 	device_unregister(dev);
@@ -2305,7 +2312,7 @@ static void mce_reenable_cpu(void)
 
 	if (!cpuhp_tasks_frozen)
 		cmci_reenable();
-	for (i = 0; i < mca_cfg.banks; i++) {
+	for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
 		struct mce_bank *b = &mce_banks[i];
 
 		if (b->init)
@@ -2493,8 +2500,6 @@ EXPORT_SYMBOL_GPL(mcsafe_key);
 
 static int __init mcheck_late_init(void)
 {
-	pr_info("Using %d MCE banks\n", mca_cfg.banks);
-
 	if (mca_cfg.recovery)
 		static_branch_inc(&mcsafe_key);
 
diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h
index 35b3e5c02c1c..43031db429d2 100644
--- a/arch/x86/kernel/cpu/mce/internal.h
+++ b/arch/x86/kernel/cpu/mce/internal.h
@@ -118,7 +118,6 @@ struct mca_config {
 	      bios_cmci_threshold	: 1,
 	      __reserved		: 59;
 
-	u8 banks;
 	s8 bootlog;
 	int tolerant;
 	int monarch_timeout;
@@ -127,6 +126,7 @@ struct mca_config {
 };
 
 extern struct mca_config mca_cfg;
+DECLARE_PER_CPU_READ_MOSTLY(unsigned int, mce_num_banks);
 
 struct mce_vendor_flags {
 	/*

[tip:ras/core] x86/MCE: Determine MCA banks' init state properly

[tip-bot for Yazen Ghannam]

Commit-ID:  068b053dca0e2ab40b3d953b102a178654eec282
Gitweb:     https://git.kernel.org/tip/068b053dca0e2ab40b3d953b102a178654eec282
Author:     Yazen Ghannam <yazen.ghannam@amd.com>
AuthorDate: Fri, 7 Jun 2019 20:18:06 +0000
Committer:  Borislav Petkov <bp@suse.de>
CommitDate: Tue, 11 Jun 2019 15:23:34 +0200

x86/MCE: Determine MCA banks' init state properly

The OS is expected to write all bits to MCA_CTL for each bank,
thus enabling error reporting in all banks. However, some banks
may be unused in which case the registers for such banks are
Read-as-Zero/Writes-Ignored. Also, the OS may avoid setting some control
bits because of quirks, etc.

A bank can be considered uninitialized if the MCA_CTL register returns
zero. This is because either the OS did not write anything or because
the hardware is enforcing RAZ/WI for the bank.

Set a bank's init value based on if the control bits are set or not in
hardware. Return an error code in the sysfs interface for uninitialized
banks.

Do a final bank init check in a separate function which is not part of
any user-controlled code flows. This is so a user may enable/disable a
bank during runtime without having to restart their system.

 [ bp: Massage a bit. Discover bank init state at boot. ]

Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "linux-edac@vger.kernel.org" <linux-edac@vger.kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tony Luck <tony.luck@intel.com>
Cc: "x86@kernel.org" <x86@kernel.org>
Link: https://lkml.kernel.org/r/20190607201752.221446-6-Yazen.Ghannam@amd.com
---
 arch/x86/kernel/cpu/mce/core.c | 39 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 39 insertions(+)

diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 10f9f140985e..c2c93e9195ed 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -1490,6 +1490,11 @@ static void __mcheck_cpu_mce_banks_init(void)
 	for (i = 0; i < n_banks; i++) {
 		struct mce_bank *b = &mce_banks[i];
 
+		/*
+		 * Init them all, __mcheck_cpu_apply_quirks() is going to apply
+		 * the required vendor quirks before
+		 * __mcheck_cpu_init_clear_banks() does the final bank setup.
+		 */
 		b->ctl = -1ULL;
 		b->init = 1;
 	}
@@ -1562,6 +1567,33 @@ static void __mcheck_cpu_init_clear_banks(void)
 	}
 }
 
+/*
+ * Do a final check to see if there are any unused/RAZ banks.
+ *
+ * This must be done after the banks have been initialized and any quirks have
+ * been applied.
+ *
+ * Do not call this from any user-initiated flows, e.g. CPU hotplug or sysfs.
+ * Otherwise, a user who disables a bank will not be able to re-enable it
+ * without a system reboot.
+ */
+static void __mcheck_cpu_check_banks(void)
+{
+	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
+	u64 msrval;
+	int i;
+
+	for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
+		struct mce_bank *b = &mce_banks[i];
+
+		if (!b->init)
+			continue;
+
+		rdmsrl(msr_ops.ctl(i), msrval);
+		b->init = !!msrval;
+	}
+}
+
 /*
  * During IFU recovery Sandy Bridge -EP4S processors set the RIPV and
  * EIPV bits in MCG_STATUS to zero on the affected logical processor (SDM
@@ -1849,6 +1881,7 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c)
 	__mcheck_cpu_init_generic();
 	__mcheck_cpu_init_vendor(c);
 	__mcheck_cpu_init_clear_banks();
+	__mcheck_cpu_check_banks();
 	__mcheck_cpu_setup_timer();
 }
 
@@ -2085,6 +2118,9 @@ static ssize_t show_bank(struct device *s, struct device_attribute *attr,
 
 	b = &per_cpu(mce_banks_array, s->id)[bank];
 
+	if (!b->init)
+		return -ENODEV;
+
 	return sprintf(buf, "%llx\n", b->ctl);
 }
 
@@ -2103,6 +2139,9 @@ static ssize_t set_bank(struct device *s, struct device_attribute *attr,
 
 	b = &per_cpu(mce_banks_array, s->id)[bank];
 
+	if (!b->init)
+		return -ENODEV;
+
 	b->ctl = new;
 	mce_restart();