/* Content Code Description for PCI Function Error */ struct zpci_ccdf_err {
u32 reserved1;
u32 fh; /* function handle */
u32 fid; /* function id */
u32 ett : 4; /* expected table type */
u32 mvn : 12; /* MSI vector number */
u32 dmaas : 8; /* DMA address space */
u32 : 6;
u32 q : 1; /* event qualifier */
u32 rw : 1; /* read/write */
u64 faddr; /* failing address */
u32 reserved3;
u16 reserved4;
u16 pec; /* PCI event code */
} __packed;
/* Content Code Description for PCI Function Availability */ struct zpci_ccdf_avail {
u32 reserved1;
u32 fh; /* function handle */
u32 fid; /* function id */
u32 reserved2;
u32 reserved3;
u32 reserved4;
u32 reserved5;
u16 reserved6;
u16 pec; /* PCI event code */
} __packed;
staticinlinebool ers_result_indicates_abort(pci_ers_result_t ers_res)
{ switch (ers_res) { case PCI_ERS_RESULT_CAN_RECOVER: case PCI_ERS_RESULT_RECOVERED: case PCI_ERS_RESULT_NEED_RESET: case PCI_ERS_RESULT_NONE: returnfalse; default: returntrue;
}
}
pr_info("%s: Initiating reset\n", pci_name(pdev)); if (zpci_hot_reset_device(to_zpci(pdev))) {
pr_err("%s: The reset request failed\n", pci_name(pdev)); return ers_res;
}
pdev->error_state = pci_channel_io_normal;
if (driver->err_handler->slot_reset)
ers_res = driver->err_handler->slot_reset(pdev); else
ers_res = PCI_ERS_RESULT_NONE;
if (ers_result_indicates_abort(ers_res)) {
pr_info("%s: Automatic recovery failed after slot reset\n", pci_name(pdev)); return ers_res;
}
return ers_res;
}
/* zpci_event_attempt_error_recovery - Try to recover the given PCI function * @pdev: PCI function to recover currently in the error state * * We follow the scheme outlined in Documentation/PCI/pci-error-recovery.rst. * With the simplification that recovery always happens per function * and the platform determines which functions are affected for * multi-function devices.
*/ static pci_ers_result_t zpci_event_attempt_error_recovery(struct pci_dev *pdev)
{
pci_ers_result_t ers_res = PCI_ERS_RESULT_DISCONNECT; struct zpci_dev *zdev = to_zpci(pdev); char *status_str = "success"; struct pci_driver *driver;
/* * Ensure that the PCI function is not removed concurrently, no driver * is unbound or probed and that userspace can't access its * configuration space while we perform recovery.
*/
device_lock(&pdev->dev); if (pdev->error_state == pci_channel_io_perm_failure) {
ers_res = PCI_ERS_RESULT_DISCONNECT; goto out_unlock;
}
pdev->error_state = pci_channel_io_frozen;
if (is_passed_through(pdev)) {
pr_info("%s: Cannot be recovered in the host because it is a pass-through device\n",
pci_name(pdev));
status_str = "failed (pass-through)"; goto out_unlock;
}
driver = to_pci_driver(pdev->dev.driver); if (!is_driver_supported(driver)) { if (!driver) {
pr_info("%s: Cannot be recovered because no driver is bound to the device\n",
pci_name(pdev));
status_str = "failed (no driver)";
} else {
pr_info("%s: The %s driver bound to the device does not support error recovery\n",
pci_name(pdev),
driver->name);
status_str = "failed (no driver support)";
} goto out_unlock;
}
ers_res = zpci_event_notify_error_detected(pdev, driver); if (ers_result_indicates_abort(ers_res)) {
status_str = "failed (abort on detection)"; goto out_unlock;
}
if (ers_res != PCI_ERS_RESULT_NEED_RESET) {
ers_res = zpci_event_do_error_state_clear(pdev, driver); if (ers_result_indicates_abort(ers_res)) {
status_str = "failed (abort on MMIO enable)"; goto out_unlock;
}
}
if (ers_res == PCI_ERS_RESULT_NEED_RESET)
ers_res = zpci_event_do_reset(pdev, driver);
/* * ers_res can be PCI_ERS_RESULT_NONE either because the driver * decided to return it, indicating that it abstains from voting * on how to recover, or because it didn't implement the callback. * Both cases assume, that if there is nothing else causing a * disconnect, we recovered successfully.
*/ if (ers_res == PCI_ERS_RESULT_NONE)
ers_res = PCI_ERS_RESULT_RECOVERED;
pr_info("%s: The device is ready to resume operations\n", pci_name(pdev)); if (driver->err_handler->resume)
driver->err_handler->resume(pdev);
pci_uevent_ers(pdev, PCI_ERS_RESULT_RECOVERED);
out_unlock:
device_unlock(&pdev->dev);
zpci_report_status(zdev, "recovery", status_str);
return ers_res;
}
/* zpci_event_io_failure - Report PCI channel failure state to driver * @pdev: PCI function for which to report * @es: PCI channel failure state to report
*/ staticvoid zpci_event_io_failure(struct pci_dev *pdev, pci_channel_state_t es)
{ struct pci_driver *driver;
pci_dev_lock(pdev);
pdev->error_state = es; /** * While vfio-pci's error_detected callback notifies user-space QEMU * reacts to this by freezing the guest. In an s390 environment PCI * errors are rarely fatal so this is overkill. Instead in the future * we will inject the error event and let the guest recover the device * itself.
*/ if (is_passed_through(pdev)) goto out;
driver = to_pci_driver(pdev->dev.driver); if (driver && driver->err_handler && driver->err_handler->error_detected)
driver->err_handler->error_detected(pdev, pdev->error_state);
out:
pci_dev_unlock(pdev);
}
if (zdev) {
mutex_lock(&zdev->state_lock);
rc = clp_refresh_fh(zdev->fid, &fh); if (rc) goto no_pdev; if (!fh || ccdf->fh != fh) { /* Ignore events with stale handles */
zpci_dbg(3, "err fid:%x, fh:%x (stale %x)\n",
ccdf->fid, fh, ccdf->fh); goto no_pdev;
}
zpci_update_fh(zdev, ccdf->fh); if (zdev->zbus->bus)
pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn);
}
pr_err("%s: Event 0x%x reports an error for PCI function 0x%x\n",
pdev ? pci_name(pdev) : "n/a", ccdf->pec, ccdf->fid);
if (!pdev) goto no_pdev;
switch (ccdf->pec) { case 0x002a: /* Error event concerns FMB */ case 0x002b: case 0x002c: break; case 0x0040: /* Service Action or Error Recovery Failed */ case 0x003b:
zpci_event_io_failure(pdev, pci_channel_io_perm_failure); break; default: /* PCI function left in the error state attempt to recover */
ers_res = zpci_event_attempt_error_recovery(pdev); if (ers_res != PCI_ERS_RESULT_RECOVERED)
zpci_event_io_failure(pdev, pci_channel_io_perm_failure); break;
}
pci_dev_put(pdev);
no_pdev: if (zdev)
mutex_unlock(&zdev->state_lock);
zpci_zdev_put(zdev);
}
void zpci_event_error(void *data)
{ if (zpci_is_enabled())
__zpci_event_error(data);
}
staticvoid zpci_event_hard_deconfigured(struct zpci_dev *zdev, u32 fh)
{
zpci_update_fh(zdev, fh); /* Give the driver a hint that the function is * already unusable.
*/
zpci_bus_remove_device(zdev, true); /* Even though the device is already gone we still * need to free zPCI resources as part of the disable.
*/ if (zdev_enabled(zdev))
zpci_disable_device(zdev);
zdev->state = ZPCI_FN_STATE_STANDBY;
}
staticvoid zpci_event_reappear(struct zpci_dev *zdev)
{
lockdep_assert_held(&zdev->state_lock); /* * The zdev is in the reserved state. This means that it was presumed to * go away but there are still undropped references. Now, the platform * announced its availability again. Bring back the lingering zdev * to standby. This is safe because we hold a temporary reference * now so that it won't go away. Account for the re-appearance of the * underlying device by incrementing the reference count.
*/
zdev->state = ZPCI_FN_STATE_STANDBY;
zpci_zdev_get(zdev);
zpci_dbg(1, "rea fid:%x, fh:%x\n", zdev->fid, zdev->fh);
}
switch (ccdf->pec) { case 0x0301: /* Reserved|Standby -> Configured */ if (!zdev) {
zdev = zpci_create_device(ccdf->fid, ccdf->fh, ZPCI_FN_STATE_CONFIGURED); if (IS_ERR(zdev)) break; if (zpci_add_device(zdev)) {
kfree(zdev); break;
}
} else { if (zdev->state == ZPCI_FN_STATE_RESERVED)
zpci_event_reappear(zdev); /* the configuration request may be stale */ elseif (zdev->state != ZPCI_FN_STATE_STANDBY) break;
zdev->state = ZPCI_FN_STATE_CONFIGURED;
}
zpci_scan_configured_device(zdev, ccdf->fh); break; case 0x0302: /* Reserved -> Standby */ if (!zdev) {
zdev = zpci_create_device(ccdf->fid, ccdf->fh, ZPCI_FN_STATE_STANDBY); if (IS_ERR(zdev)) break; if (zpci_add_device(zdev)) {
kfree(zdev); break;
}
} else { if (zdev->state == ZPCI_FN_STATE_RESERVED)
zpci_event_reappear(zdev);
zpci_update_fh(zdev, ccdf->fh);
} break; case 0x0303: /* Deconfiguration requested */ if (zdev) { /* The event may have been queued before we configured * the device.
*/ if (zdev->state != ZPCI_FN_STATE_CONFIGURED) break;
zpci_update_fh(zdev, ccdf->fh);
zpci_deconfigure_device(zdev);
} break; case 0x0304: /* Configured -> Standby|Reserved */ if (zdev) { /* The event may have been queued before we configured * the device.:
*/ if (zdev->state == ZPCI_FN_STATE_CONFIGURED)
zpci_event_hard_deconfigured(zdev, ccdf->fh); /* The 0x0304 event may immediately reserve the device */ if (!clp_get_state(zdev->fid, &state) &&
state == ZPCI_FN_STATE_RESERVED) {
zpci_device_reserved(zdev);
}
} break; case 0x0306: /* 0x308 or 0x302 for multiple devices */
zpci_remove_reserved_devices();
zpci_scan_devices(); break; case 0x0308: /* Standby -> Reserved */ if (!zdev) break;
zpci_device_reserved(zdev); break; default: break;
} if (existing_zdev) {
mutex_unlock(&zdev->state_lock);
zpci_zdev_put(zdev);
}
}
void zpci_event_availability(void *data)
{ if (zpci_is_enabled())
__zpci_event_availability(data);
}
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.