static int eeh_error_buf_size;
/* System monitoring statistics */
+static DEFINE_PER_CPU(unsigned long, no_device);
+static DEFINE_PER_CPU(unsigned long, no_dn);
+static DEFINE_PER_CPU(unsigned long, no_cfg_addr);
+static DEFINE_PER_CPU(unsigned long, ignored_check);
static DEFINE_PER_CPU(unsigned long, total_mmio_ffs);
static DEFINE_PER_CPU(unsigned long, false_positives);
static DEFINE_PER_CPU(unsigned long, ignored_failures);
/* --------------------------------------------------------------- */
/* Above lies the PCI Address Cache. Below lies the EEH event infrastructure */
+void eeh_slot_error_detail (struct pci_dn *pdn, int severity)
+{
+ unsigned long flags;
+ int rc;
+
+ /* Log the error with the rtas logger */
+ spin_lock_irqsave(&slot_errbuf_lock, flags);
+ memset(slot_errbuf, 0, eeh_error_buf_size);
+
+ rc = rtas_call(ibm_slot_error_detail,
+ 8, 1, NULL, pdn->eeh_config_addr,
+ BUID_HI(pdn->phb->buid),
+ BUID_LO(pdn->phb->buid), NULL, 0,
+ virt_to_phys(slot_errbuf),
+ eeh_error_buf_size,
+ severity);
+
+ if (rc == 0)
+ log_error(slot_errbuf, ERR_TYPE_RTAS_LOG, 0);
+ spin_unlock_irqrestore(&slot_errbuf_lock, flags);
+}
+
/**
* eeh_register_notifier - Register to find out about EEH events.
* @nb: notifier block to callback on events
* Since the panic_on_oops sysctl is used to halt the system
* in light of potential corruption, we can use it here.
*/
- if (panic_on_oops)
+ if (panic_on_oops) {
+ struct device_node *dn = pci_device_to_OF_node(dev);
+ eeh_slot_error_detail (PCI_DN(dn), 2 /* Permanent Error */);
panic("EEH: MMIO failure (%d) on device:%s\n", reset_state,
pci_name(dev));
+ }
else {
__get_cpu_var(ignored_failures)++;
printk(KERN_INFO "EEH: Ignored MMIO failure (%d) on device:%s\n",
notifier_call_chain (&eeh_notifier_chain,
EEH_NOTIFY_FREEZE, event);
- __get_cpu_var(slot_resets)++;
-
pci_dev_put(event->dev);
kfree(event);
}
int ret;
int rets[3];
unsigned long flags;
- int rc, reset_state;
+ int reset_state;
struct eeh_event *event;
struct pci_dn *pdn;
if (!eeh_subsystem_enabled)
return 0;
- if (!dn)
+ if (!dn) {
+ __get_cpu_var(no_dn)++;
return 0;
+ }
pdn = PCI_DN(dn);
/* Access to IO BARs might get this far and still not want checking. */
if (!pdn->eeh_capable || !(pdn->eeh_mode & EEH_MODE_SUPPORTED) ||
pdn->eeh_mode & EEH_MODE_NOCHECK) {
+ __get_cpu_var(ignored_check)++;
+#ifdef DEBUG
+ printk ("EEH:ignored check for %s %s\n", pci_name (dev), dn->full_name);
+#endif
return 0;
}
if (!pdn->eeh_config_addr) {
+ __get_cpu_var(no_cfg_addr)++;
return 0;
}
* In any case they must share a common PHB.
*/
ret = read_slot_reset_state(pdn, rets);
- if (!(ret == 0 && rets[1] == 1 && (rets[0] == 2 || rets[0] == 4))) {
+
+ /* If the call to firmware failed, punt */
+ if (ret != 0) {
+ printk(KERN_WARNING "EEH: read_slot_reset_state() failed; rc=%d dn=%s\n",
+ ret, dn->full_name);
+ __get_cpu_var(false_positives)++;
+ return 0;
+ }
+
+ /* If EEH is not supported on this device, punt. */
+ if (rets[1] != 1) {
+ printk(KERN_WARNING "EEH: event on unsupported device, rc=%d dn=%s\n",
+ ret, dn->full_name);
+ __get_cpu_var(false_positives)++;
+ return 0;
+ }
+
+ /* If not the kind of error we know about, punt. */
+ if (rets[0] != 2 && rets[0] != 4 && rets[0] != 5) {
+ __get_cpu_var(false_positives)++;
+ return 0;
+ }
+
+ /* Note that config-io to empty slots may fail;
+ * we recognize empty because they don't have children. */
+ if ((rets[0] == 5) && (dn->child == NULL)) {
__get_cpu_var(false_positives)++;
return 0;
}
/* prevent repeated reports of this failure */
pdn->eeh_mode |= EEH_MODE_ISOLATED;
+ __get_cpu_var(slot_resets)++;
reset_state = rets[0];
- spin_lock_irqsave(&slot_errbuf_lock, flags);
- memset(slot_errbuf, 0, eeh_error_buf_size);
-
- rc = rtas_call(ibm_slot_error_detail,
- 8, 1, NULL, pdn->eeh_config_addr,
- BUID_HI(pdn->phb->buid),
- BUID_LO(pdn->phb->buid), NULL, 0,
- virt_to_phys(slot_errbuf),
- eeh_error_buf_size,
- 1 /* Temporary Error */);
-
- if (rc == 0)
- log_error(slot_errbuf, ERR_TYPE_RTAS_LOG, 0);
- spin_unlock_irqrestore(&slot_errbuf_lock, flags);
+ eeh_slot_error_detail (pdn, 1 /* Temporary Error */);
printk(KERN_INFO "EEH: MMIO failure (%d) on device: %s %s\n",
rets[0], dn->name, dn->full_name);
/* Most EEH events are due to device driver bugs. Having
* a stack trace will help the device-driver authors figure
* out what happened. So print that out. */
- dump_stack();
+ if (rets[0] != 5) dump_stack();
schedule_work(&eeh_event_wq);
return 0;
/* Finding the phys addr + pci device; this is pretty quick. */
addr = eeh_token_to_phys((unsigned long __force) token);
dev = pci_get_device_by_addr(addr);
- if (!dev)
+ if (!dev) {
+ __get_cpu_var(no_device)++;
return val;
+ }
dn = pci_device_to_OF_node(dev);
eeh_dn_check_failure (dn, dev);
struct device_node *phb, *np;
struct eeh_early_enable_info info;
+ spin_lock_init(&slot_errbuf_lock);
+
np = of_find_node_by_path("/rtas");
if (np == NULL)
return;
unsigned int cpu;
unsigned long ffs = 0, positives = 0, failures = 0;
unsigned long resets = 0;
+ unsigned long no_dev = 0, no_dn = 0, no_cfg = 0, no_check = 0;
for_each_cpu(cpu) {
ffs += per_cpu(total_mmio_ffs, cpu);
positives += per_cpu(false_positives, cpu);
failures += per_cpu(ignored_failures, cpu);
resets += per_cpu(slot_resets, cpu);
+ no_dev += per_cpu(no_device, cpu);
+ no_dn += per_cpu(no_dn, cpu);
+ no_cfg += per_cpu(no_cfg_addr, cpu);
+ no_check += per_cpu(ignored_check, cpu);
}
if (0 == eeh_subsystem_enabled) {
seq_printf(m, "eeh_total_mmio_ffs=%ld\n", ffs);
} else {
seq_printf(m, "EEH Subsystem is enabled\n");
- seq_printf(m, "eeh_total_mmio_ffs=%ld\n"
- "eeh_false_positives=%ld\n"
- "eeh_ignored_failures=%ld\n"
- "eeh_slot_resets=%ld\n"
- "eeh_fail_count=%d\n",
- ffs, positives, failures, resets,
- eeh_fail_count.counter);
+ seq_printf(m,
+ "no device=%ld\n"
+ "no device node=%ld\n"
+ "no config address=%ld\n"
+ "check not wanted=%ld\n"
+ "eeh_total_mmio_ffs=%ld\n"
+ "eeh_false_positives=%ld\n"
+ "eeh_ignored_failures=%ld\n"
+ "eeh_slot_resets=%ld\n",
+ no_dev, no_dn, no_cfg, no_check,
+ ffs, positives, failures, resets);
}
return 0;
projects / mirror_ubuntu-bionic-kernel.git / blobdiff