[SCSI] lpfc: add PCI error recovery support

This patch adds PCI Error recovery support to the
Emulex Lightpulse Fibrechannel (lpfc) SCSI device driver.
Lightly tested at this point, works.

Signed-off-by: Linas Vepstas <linas@austin.ibm.com>
Acked-by: Bino.Sebastian@Emulex.Com
Acked-by: James Smart <james.smart@emulex.com>
Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
This commit is contained in:
Linas Vepstas 2007-02-14 14:28:36 -06:00 committed by James Bottomley
parent 4520b0089b
commit 8d63f37505
2 changed files with 109 additions and 0 deletions

View File

@ -518,6 +518,10 @@ lpfc_handle_eratt(struct lpfc_hba * phba)
struct lpfc_sli *psli = &phba->sli;
struct lpfc_sli_ring *pring;
uint32_t event_data;
/* If the pci channel is offline, ignore possible errors,
* since we cannot communicate with the pci card anyway. */
if (pci_channel_offline(phba->pcidev))
return;
if (phba->work_hs & HS_FFER6 ||
phba->work_hs & HS_FFER5) {
@ -1797,6 +1801,92 @@ lpfc_pci_remove_one(struct pci_dev *pdev)
pci_set_drvdata(pdev, NULL);
}
/**
* lpfc_io_error_detected - called when PCI error is detected
* @pdev: Pointer to PCI device
* @state: The current pci conneection state
*
* This function is called after a PCI bus error affecting
* this device has been detected.
*/
static pci_ers_result_t lpfc_io_error_detected(struct pci_dev *pdev,
pci_channel_state_t state)
{
struct Scsi_Host *host = pci_get_drvdata(pdev);
struct lpfc_hba *phba = (struct lpfc_hba *)host->hostdata;
struct lpfc_sli *psli = &phba->sli;
struct lpfc_sli_ring *pring;
if (state == pci_channel_io_perm_failure) {
lpfc_pci_remove_one(pdev);
return PCI_ERS_RESULT_DISCONNECT;
}
pci_disable_device(pdev);
/*
* There may be I/Os dropped by the firmware.
* Error iocb (I/O) on txcmplq and let the SCSI layer
* retry it after re-establishing link.
*/
pring = &psli->ring[psli->fcp_ring];
lpfc_sli_abort_iocb_ring(phba, pring);
/* Request a slot reset. */
return PCI_ERS_RESULT_NEED_RESET;
}
/**
* lpfc_io_slot_reset - called after the pci bus has been reset.
* @pdev: Pointer to PCI device
*
* Restart the card from scratch, as if from a cold-boot.
*/
static pci_ers_result_t lpfc_io_slot_reset(struct pci_dev *pdev)
{
struct Scsi_Host *host = pci_get_drvdata(pdev);
struct lpfc_hba *phba = (struct lpfc_hba *)host->hostdata;
struct lpfc_sli *psli = &phba->sli;
int bars = pci_select_bars(pdev, IORESOURCE_MEM);
dev_printk(KERN_INFO, &pdev->dev, "recovering from a slot reset.\n");
if (pci_enable_device_bars(pdev, bars)) {
printk(KERN_ERR "lpfc: Cannot re-enable "
"PCI device after reset.\n");
return PCI_ERS_RESULT_DISCONNECT;
}
pci_set_master(pdev);
/* Re-establishing Link */
spin_lock_irq(phba->host->host_lock);
phba->fc_flag |= FC_ESTABLISH_LINK;
psli->sli_flag &= ~LPFC_SLI2_ACTIVE;
spin_unlock_irq(phba->host->host_lock);
/* Take device offline; this will perform cleanup */
lpfc_offline(phba);
lpfc_sli_brdrestart(phba);
return PCI_ERS_RESULT_RECOVERED;
}
/**
* lpfc_io_resume - called when traffic can start flowing again.
* @pdev: Pointer to PCI device
*
* This callback is called when the error recovery driver tells us that
* its OK to resume normal operation.
*/
static void lpfc_io_resume(struct pci_dev *pdev)
{
struct Scsi_Host *host = pci_get_drvdata(pdev);
struct lpfc_hba *phba = (struct lpfc_hba *)host->hostdata;
if (lpfc_online(phba) == 0) {
mod_timer(&phba->fc_estabtmo, jiffies + HZ * 60);
}
}
static struct pci_device_id lpfc_id_table[] = {
{PCI_VENDOR_ID_EMULEX, PCI_DEVICE_ID_VIPER,
PCI_ANY_ID, PCI_ANY_ID, },
@ -1857,11 +1947,18 @@ static struct pci_device_id lpfc_id_table[] = {
MODULE_DEVICE_TABLE(pci, lpfc_id_table);
static struct pci_error_handlers lpfc_err_handler = {
.error_detected = lpfc_io_error_detected,
.slot_reset = lpfc_io_slot_reset,
.resume = lpfc_io_resume,
};
static struct pci_driver lpfc_driver = {
.name = LPFC_DRIVER_NAME,
.id_table = lpfc_id_table,
.probe = lpfc_pci_probe_one,
.remove = __devexit_p(lpfc_pci_remove_one),
.err_handler = &lpfc_err_handler,
};
static int __init

View File

@ -2104,6 +2104,10 @@ lpfc_sli_issue_mbox(struct lpfc_hba * phba, LPFC_MBOXQ_t * pmbox, uint32_t flag)
volatile uint32_t word0, ldata;
void __iomem *to_slim;
/* If the PCI channel is in offline state, do not post mbox. */
if (unlikely(pci_channel_offline(phba->pcidev)))
return MBX_NOT_FINISHED;
psli = &phba->sli;
spin_lock_irqsave(phba->host->host_lock, drvr_flag);
@ -2407,6 +2411,10 @@ lpfc_sli_issue_iocb(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
struct lpfc_iocbq *nextiocb;
IOCB_t *iocb;
/* If the PCI channel is in offline state, do not post iocbs. */
if (unlikely(pci_channel_offline(phba->pcidev)))
return IOCB_ERROR;
/*
* We should never get an IOCB if we are in a < LINK_DOWN state
*/
@ -3154,6 +3162,10 @@ lpfc_intr_handler(int irq, void *dev_id)
if (unlikely(!phba))
return IRQ_NONE;
/* If the pci channel is offline, ignore all the interrupts. */
if (unlikely(pci_channel_offline(phba->pcidev)))
return IRQ_NONE;
phba->sli.slistat.sli_intr++;
/*