summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--arch/x86/kernel/cpu/mce/amd.c19
-rw-r--r--arch/x86/kernel/cpu/mce/core.c45
-rw-r--r--arch/x86/kernel/cpu/mce/internal.h2
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 {
/*
generated by cgit v1.2.3 (git 2.39.1) at 2025-05-28 20:16:34 +0000