summaryrefslogtreecommitdiffstats
path: root/arch/powerpc/kernel/eeh_driver.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/powerpc/kernel/eeh_driver.c')
-rw-r--r--arch/powerpc/kernel/eeh_driver.c153
1 files changed, 121 insertions, 32 deletions
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 301be3126ae3..fb6207d2c604 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -34,6 +34,11 @@
#include <asm/prom.h>
#include <asm/rtas.h>
+struct eeh_rmv_data {
+ struct list_head edev_list;
+ int removed;
+};
+
/**
* eeh_pcid_name - Retrieve name of PCI device driver
* @pdev: PCI device
@@ -190,7 +195,7 @@ static void *eeh_report_error(void *data, void *userdata)
enum pci_ers_result rc, *res = userdata;
struct pci_driver *driver;
- if (!dev || eeh_dev_removed(edev))
+ if (!dev || eeh_dev_removed(edev) || eeh_pe_passed(edev->pe))
return NULL;
dev->error_state = pci_channel_io_frozen;
@@ -211,6 +216,7 @@ static void *eeh_report_error(void *data, void *userdata)
if (rc == PCI_ERS_RESULT_NEED_RESET) *res = rc;
if (*res == PCI_ERS_RESULT_NONE) *res = rc;
+ edev->in_error = true;
eeh_pcid_put(dev);
return NULL;
}
@@ -231,7 +237,7 @@ static void *eeh_report_mmio_enabled(void *data, void *userdata)
enum pci_ers_result rc, *res = userdata;
struct pci_driver *driver;
- if (!dev || eeh_dev_removed(edev))
+ if (!dev || eeh_dev_removed(edev) || eeh_pe_passed(edev->pe))
return NULL;
driver = eeh_pcid_get(dev);
@@ -271,7 +277,7 @@ static void *eeh_report_reset(void *data, void *userdata)
enum pci_ers_result rc, *res = userdata;
struct pci_driver *driver;
- if (!dev || eeh_dev_removed(edev))
+ if (!dev || eeh_dev_removed(edev) || eeh_pe_passed(edev->pe))
return NULL;
dev->error_state = pci_channel_io_normal;
@@ -282,7 +288,8 @@ static void *eeh_report_reset(void *data, void *userdata)
if (!driver->err_handler ||
!driver->err_handler->slot_reset ||
- (edev->mode & EEH_DEV_NO_HANDLER)) {
+ (edev->mode & EEH_DEV_NO_HANDLER) ||
+ (!edev->in_error)) {
eeh_pcid_put(dev);
return NULL;
}
@@ -326,20 +333,23 @@ static void *eeh_report_resume(void *data, void *userdata)
{
struct eeh_dev *edev = (struct eeh_dev *)data;
struct pci_dev *dev = eeh_dev_to_pci_dev(edev);
+ bool was_in_error;
struct pci_driver *driver;
- if (!dev || eeh_dev_removed(edev))
+ if (!dev || eeh_dev_removed(edev) || eeh_pe_passed(edev->pe))
return NULL;
dev->error_state = pci_channel_io_normal;
driver = eeh_pcid_get(dev);
if (!driver) return NULL;
+ was_in_error = edev->in_error;
+ edev->in_error = false;
eeh_enable_irq(dev);
if (!driver->err_handler ||
!driver->err_handler->resume ||
- (edev->mode & EEH_DEV_NO_HANDLER)) {
+ (edev->mode & EEH_DEV_NO_HANDLER) || !was_in_error) {
edev->mode &= ~EEH_DEV_NO_HANDLER;
eeh_pcid_put(dev);
return NULL;
@@ -365,7 +375,7 @@ static void *eeh_report_failure(void *data, void *userdata)
struct pci_dev *dev = eeh_dev_to_pci_dev(edev);
struct pci_driver *driver;
- if (!dev || eeh_dev_removed(edev))
+ if (!dev || eeh_dev_removed(edev) || eeh_pe_passed(edev->pe))
return NULL;
dev->error_state = pci_channel_io_perm_failure;
@@ -386,12 +396,40 @@ static void *eeh_report_failure(void *data, void *userdata)
return NULL;
}
+static void *eeh_add_virt_device(void *data, void *userdata)
+{
+ struct pci_driver *driver;
+ struct eeh_dev *edev = (struct eeh_dev *)data;
+ struct pci_dev *dev = eeh_dev_to_pci_dev(edev);
+ struct pci_dn *pdn = eeh_dev_to_pdn(edev);
+
+ if (!(edev->physfn)) {
+ pr_warn("%s: EEH dev %04x:%02x:%02x.%01x not for VF\n",
+ __func__, edev->phb->global_number, pdn->busno,
+ PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn));
+ return NULL;
+ }
+
+ driver = eeh_pcid_get(dev);
+ if (driver) {
+ eeh_pcid_put(dev);
+ if (driver->err_handler)
+ return NULL;
+ }
+
+#ifdef CONFIG_PPC_POWERNV
+ pci_iov_add_virtfn(edev->physfn, pdn->vf_index, 0);
+#endif
+ return NULL;
+}
+
static void *eeh_rmv_device(void *data, void *userdata)
{
struct pci_driver *driver;
struct eeh_dev *edev = (struct eeh_dev *)data;
struct pci_dev *dev = eeh_dev_to_pci_dev(edev);
- int *removed = (int *)userdata;
+ struct eeh_rmv_data *rmv_data = (struct eeh_rmv_data *)userdata;
+ int *removed = rmv_data ? &rmv_data->removed : NULL;
/*
* Actually, we should remove the PCI bridges as well.
@@ -416,10 +454,13 @@ static void *eeh_rmv_device(void *data, void *userdata)
driver = eeh_pcid_get(dev);
if (driver) {
eeh_pcid_put(dev);
- if (driver->err_handler &&
+ if (removed &&
+ eeh_pe_passed(edev->pe))
+ return NULL;
+ if (removed &&
+ driver->err_handler &&
driver->err_handler->error_detected &&
- driver->err_handler->slot_reset &&
- driver->err_handler->resume)
+ driver->err_handler->slot_reset)
return NULL;
}
@@ -428,11 +469,29 @@ static void *eeh_rmv_device(void *data, void *userdata)
pci_name(dev));
edev->bus = dev->bus;
edev->mode |= EEH_DEV_DISCONNECTED;
- (*removed)++;
+ if (removed)
+ (*removed)++;
- pci_lock_rescan_remove();
- pci_stop_and_remove_bus_device(dev);
- pci_unlock_rescan_remove();
+ if (edev->physfn) {
+#ifdef CONFIG_PPC_POWERNV
+ struct pci_dn *pdn = eeh_dev_to_pdn(edev);
+
+ pci_iov_remove_virtfn(edev->physfn, pdn->vf_index, 0);
+ edev->pdev = NULL;
+
+ /*
+ * We have to set the VF PE number to invalid one, which is
+ * required to plug the VF successfully.
+ */
+ pdn->pe_number = IODA_INVALID_PE;
+#endif
+ if (rmv_data)
+ list_add(&edev->rmv_list, &rmv_data->edev_list);
+ } else {
+ pci_lock_rescan_remove();
+ pci_stop_and_remove_bus_device(dev);
+ pci_unlock_rescan_remove();
+ }
return NULL;
}
@@ -546,11 +605,13 @@ int eeh_pe_reset_and_recover(struct eeh_pe *pe)
* During the reset, udev might be invoked because those affected
* PCI devices will be removed and then added.
*/
-static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
+static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
+ struct eeh_rmv_data *rmv_data)
{
struct pci_bus *frozen_bus = eeh_pe_bus_get(pe);
struct timeval tstamp;
- int cnt, rc, removed = 0;
+ int cnt, rc;
+ struct eeh_dev *edev;
/* pcibios will clear the counter; save the value */
cnt = pe->freeze_count;
@@ -564,12 +625,16 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
*/
eeh_pe_state_mark(pe, EEH_PE_KEEP);
if (bus) {
- eeh_pe_state_clear(pe, EEH_PE_PRI_BUS);
- pci_lock_rescan_remove();
- pcibios_remove_pci_devices(bus);
- pci_unlock_rescan_remove();
+ if (pe->type & EEH_PE_VF) {
+ eeh_pe_dev_traverse(pe, eeh_rmv_device, NULL);
+ } else {
+ eeh_pe_state_clear(pe, EEH_PE_PRI_BUS);
+ pci_lock_rescan_remove();
+ pcibios_remove_pci_devices(bus);
+ pci_unlock_rescan_remove();
+ }
} else if (frozen_bus) {
- eeh_pe_dev_traverse(pe, eeh_rmv_device, &removed);
+ eeh_pe_dev_traverse(pe, eeh_rmv_device, &rmv_data);
}
/*
@@ -611,14 +676,22 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
* PE. We should disconnect it so the binding can be
* rebuilt when adding PCI devices.
*/
+ edev = list_first_entry(&pe->edevs, struct eeh_dev, list);
eeh_pe_traverse(pe, eeh_pe_detach_dev, NULL);
- pcibios_add_pci_devices(bus);
- } else if (frozen_bus && removed) {
+ if (pe->type & EEH_PE_VF)
+ eeh_add_virt_device(edev, NULL);
+ else
+ pcibios_add_pci_devices(bus);
+ } else if (frozen_bus && rmv_data->removed) {
pr_info("EEH: Sleep 5s ahead of partial hotplug\n");
ssleep(5);
+ edev = list_first_entry(&pe->edevs, struct eeh_dev, list);
eeh_pe_traverse(pe, eeh_pe_detach_dev, NULL);
- pcibios_add_pci_devices(frozen_bus);
+ if (pe->type & EEH_PE_VF)
+ eeh_add_virt_device(edev, NULL);
+ else
+ pcibios_add_pci_devices(frozen_bus);
}
eeh_pe_state_clear(pe, EEH_PE_KEEP);
@@ -637,8 +710,10 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
static void eeh_handle_normal_event(struct eeh_pe *pe)
{
struct pci_bus *frozen_bus;
+ struct eeh_dev *edev, *tmp;
int rc = 0;
enum pci_ers_result result = PCI_ERS_RESULT_NONE;
+ struct eeh_rmv_data rmv_data = {LIST_HEAD_INIT(rmv_data.edev_list), 0};
frozen_bus = eeh_pe_bus_get(pe);
if (!frozen_bus) {
@@ -693,7 +768,7 @@ static void eeh_handle_normal_event(struct eeh_pe *pe)
*/
if (result == PCI_ERS_RESULT_NONE) {
pr_info("EEH: Reset with hotplug activity\n");
- rc = eeh_reset_device(pe, frozen_bus);
+ rc = eeh_reset_device(pe, frozen_bus, NULL);
if (rc) {
pr_warn("%s: Unable to reset, err=%d\n",
__func__, rc);
@@ -745,7 +820,7 @@ static void eeh_handle_normal_event(struct eeh_pe *pe)
/* If any device called out for a reset, then reset the slot */
if (result == PCI_ERS_RESULT_NEED_RESET) {
pr_info("EEH: Reset without hotplug activity\n");
- rc = eeh_reset_device(pe, NULL);
+ rc = eeh_reset_device(pe, NULL, &rmv_data);
if (rc) {
pr_warn("%s: Cannot reset, err=%d\n",
__func__, rc);
@@ -765,6 +840,15 @@ static void eeh_handle_normal_event(struct eeh_pe *pe)
goto hard_fail;
}
+ /*
+ * For those hot removed VFs, we should add back them after PF get
+ * recovered properly.
+ */
+ list_for_each_entry_safe(edev, tmp, &rmv_data.edev_list, rmv_list) {
+ eeh_add_virt_device(edev, NULL);
+ list_del(&edev->rmv_list);
+ }
+
/* Tell all device drivers that they can resume operations */
pr_info("EEH: Notify device driver to resume\n");
eeh_pe_dev_traverse(pe, eeh_report_resume, NULL);
@@ -804,12 +888,17 @@ perm_error:
* the their PCI config any more.
*/
if (frozen_bus) {
- eeh_pe_state_clear(pe, EEH_PE_PRI_BUS);
- eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED);
+ if (pe->type & EEH_PE_VF) {
+ eeh_pe_dev_traverse(pe, eeh_rmv_device, NULL);
+ eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED);
+ } else {
+ eeh_pe_state_clear(pe, EEH_PE_PRI_BUS);
+ eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED);
- pci_lock_rescan_remove();
- pcibios_remove_pci_devices(frozen_bus);
- pci_unlock_rescan_remove();
+ pci_lock_rescan_remove();
+ pcibios_remove_pci_devices(frozen_bus);
+ pci_unlock_rescan_remove();
+ }
}
}
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-24 07:43:05 +0100