Merge branch 'x86-ras-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 RAS update from Ingo Molnar:
 "The changes in this cycle were:

   - allow mmcfg access to APEI error injection handlers

   - improve MCE error messages

   - smaller cleanups"

* 'x86-ras-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86, mce: Fix sparse errors
  x86, mce: Improve timeout error messages
  ACPI, EINJ: Enhance error injection tolerance level
This commit is contained in:
Linus Torvalds 2015-02-09 18:22:04 -08:00
commit e07e0d4cb0
3 changed files with 67 additions and 16 deletions

View file

@ -116,7 +116,7 @@ static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs);
* CPU/chipset specific EDAC code can register a notifier call here to print
* MCE errors in a human-readable form.
*/
ATOMIC_NOTIFIER_HEAD(x86_mce_decoder_chain);
static ATOMIC_NOTIFIER_HEAD(x86_mce_decoder_chain);
/* Do initial initialization of a struct mce */
void mce_setup(struct mce *m)
@ -312,7 +312,7 @@ static void wait_for_panic(void)
panic("Panicing machine check CPU died");
}
static void mce_panic(char *msg, struct mce *final, char *exp)
static void mce_panic(const char *msg, struct mce *final, char *exp)
{
int i, apei_err = 0;
@ -530,7 +530,7 @@ static void mce_schedule_work(void)
schedule_work(this_cpu_ptr(&mce_work));
}
DEFINE_PER_CPU(struct irq_work, mce_irq_work);
static DEFINE_PER_CPU(struct irq_work, mce_irq_work);
static void mce_irq_work_cb(struct irq_work *entry)
{
@ -736,7 +736,7 @@ static atomic_t mce_callin;
/*
* Check if a timeout waiting for other CPUs happened.
*/
static int mce_timed_out(u64 *t)
static int mce_timed_out(u64 *t, const char *msg)
{
/*
* The others already did panic for some reason.
@ -751,8 +751,7 @@ static int mce_timed_out(u64 *t)
goto out;
if ((s64)*t < SPINUNIT) {
if (mca_cfg.tolerant <= 1)
mce_panic("Timeout synchronizing machine check over CPUs",
NULL, NULL);
mce_panic(msg, NULL, NULL);
cpu_missing = 1;
return 1;
}
@ -868,7 +867,8 @@ static int mce_start(int *no_way_out)
* Wait for everyone.
*/
while (atomic_read(&mce_callin) != cpus) {
if (mce_timed_out(&timeout)) {
if (mce_timed_out(&timeout,
"Timeout: Not all CPUs entered broadcast exception handler")) {
atomic_set(&global_nwo, 0);
return -1;
}
@ -893,7 +893,8 @@ static int mce_start(int *no_way_out)
* only seen by one CPU before cleared, avoiding duplicates.
*/
while (atomic_read(&mce_executing) < order) {
if (mce_timed_out(&timeout)) {
if (mce_timed_out(&timeout,
"Timeout: Subject CPUs unable to finish machine check processing")) {
atomic_set(&global_nwo, 0);
return -1;
}
@ -937,7 +938,8 @@ static int mce_end(int order)
* loops.
*/
while (atomic_read(&mce_executing) <= cpus) {
if (mce_timed_out(&timeout))
if (mce_timed_out(&timeout,
"Timeout: Monarch CPU unable to finish machine check processing"))
goto reset;
ndelay(SPINUNIT);
}
@ -950,7 +952,8 @@ static int mce_end(int order)
* Subject: Wait for Monarch to finish.
*/
while (atomic_read(&mce_executing) != 0) {
if (mce_timed_out(&timeout))
if (mce_timed_out(&timeout,
"Timeout: Monarch CPU did not finish machine check processing"))
goto reset;
ndelay(SPINUNIT);
}

View file

@ -610,6 +610,32 @@ static int __init pci_parse_mcfg(struct acpi_table_header *header)
return 0;
}
#ifdef CONFIG_ACPI_APEI
extern int (*arch_apei_filter_addr)(int (*func)(__u64 start, __u64 size,
void *data), void *data);
static int pci_mmcfg_for_each_region(int (*func)(__u64 start, __u64 size,
void *data), void *data)
{
struct pci_mmcfg_region *cfg;
int rc;
if (list_empty(&pci_mmcfg_list))
return 0;
list_for_each_entry(cfg, &pci_mmcfg_list, list) {
rc = func(cfg->res.start, resource_size(&cfg->res), data);
if (rc)
return rc;
}
return 0;
}
#define set_apei_filter() (arch_apei_filter_addr = pci_mmcfg_for_each_region)
#else
#define set_apei_filter()
#endif
static void __init __pci_mmcfg_init(int early)
{
pci_mmcfg_reject_broken(early);
@ -644,6 +670,8 @@ void __init pci_mmcfg_early_init(void)
else
acpi_sfi_table_parse(ACPI_SIG_MCFG, pci_parse_mcfg);
__pci_mmcfg_init(1);
set_apei_filter();
}
}

View file

@ -449,7 +449,7 @@ int apei_resources_sub(struct apei_resources *resources1,
}
EXPORT_SYMBOL_GPL(apei_resources_sub);
static int apei_get_nvs_callback(__u64 start, __u64 size, void *data)
static int apei_get_res_callback(__u64 start, __u64 size, void *data)
{
struct apei_resources *resources = data;
return apei_res_add(&resources->iomem, start, size);
@ -457,7 +457,15 @@ static int apei_get_nvs_callback(__u64 start, __u64 size, void *data)
static int apei_get_nvs_resources(struct apei_resources *resources)
{
return acpi_nvs_for_each_region(apei_get_nvs_callback, resources);
return acpi_nvs_for_each_region(apei_get_res_callback, resources);
}
int (*arch_apei_filter_addr)(int (*func)(__u64 start, __u64 size,
void *data), void *data);
static int apei_get_arch_resources(struct apei_resources *resources)
{
return arch_apei_filter_addr(apei_get_res_callback, resources);
}
/*
@ -470,7 +478,7 @@ int apei_resources_request(struct apei_resources *resources,
{
struct apei_res *res, *res_bak = NULL;
struct resource *r;
struct apei_resources nvs_resources;
struct apei_resources nvs_resources, arch_res;
int rc;
rc = apei_resources_sub(resources, &apei_resources_all);
@ -485,10 +493,20 @@ int apei_resources_request(struct apei_resources *resources,
apei_resources_init(&nvs_resources);
rc = apei_get_nvs_resources(&nvs_resources);
if (rc)
goto res_fini;
goto nvs_res_fini;
rc = apei_resources_sub(resources, &nvs_resources);
if (rc)
goto res_fini;
goto nvs_res_fini;
if (arch_apei_filter_addr) {
apei_resources_init(&arch_res);
rc = apei_get_arch_resources(&arch_res);
if (rc)
goto arch_res_fini;
rc = apei_resources_sub(resources, &arch_res);
if (rc)
goto arch_res_fini;
}
rc = -EINVAL;
list_for_each_entry(res, &resources->iomem, list) {
@ -536,7 +554,9 @@ int apei_resources_request(struct apei_resources *resources,
break;
release_mem_region(res->start, res->end - res->start);
}
res_fini:
arch_res_fini:
apei_resources_fini(&arch_res);
nvs_res_fini:
apei_resources_fini(&nvs_resources);
return rc;
}