summaryrefslogtreecommitdiffstats
path: root/drivers/misc
diff options
context:
space:
mode:
authorKleber Sacilotto de Souza <klebers@linux.vnet.ibm.com>2014-06-04 10:57:52 -0300
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>2014-07-09 14:14:27 -0700
commit93b772b25fa905c9158ee73c11c87b48668eabd0 (patch)
tree12816bd16086ade26b3a44794353fa31f966f3d6 /drivers/misc
parentfb145456fa4f4311f90703aeee058bab3b274bf8 (diff)
downloadop-kernel-dev-93b772b25fa905c9158ee73c11c87b48668eabd0.zip
op-kernel-dev-93b772b25fa905c9158ee73c11c87b48668eabd0.tar.gz
GenWQE: Improve hardware error recovery
Currently, in the event of a fatal hardware error, the driver tries a recovery procedure that calls pci_reset_function() to reset the card. This is not sufficient in some cases, needing a fundamental reset to bring the card back. This patch implements a call to the platform fundamental reset procedure on the error recovery path if GENWQE_PLATFORM_ERROR_RECOVERY is enabled. This is implemented by default only on PPC64, since this can cause problems on other archs, e.g. zSeries, where the platform has its own recovery procedures, leading to a potencial race conditition. For these cases, the recovery is kept as it was before. Signed-off-by: Kleber Sacilotto de Souza <klebers@linux.vnet.ibm.com> Acked-by: Frank Haverkamp <haver@linux.vnet.ibm.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Diffstat (limited to 'drivers/misc')
-rw-r--r--drivers/misc/genwqe/card_base.c45
1 files changed, 45 insertions, 0 deletions
diff --git a/drivers/misc/genwqe/card_base.c b/drivers/misc/genwqe/card_base.c
index 87ebaba..abb7961 100644
--- a/drivers/misc/genwqe/card_base.c
+++ b/drivers/misc/genwqe/card_base.c
@@ -797,6 +797,41 @@ static int genwqe_pci_fundamental_reset(struct pci_dev *pci_dev)
return rc;
}
+
+static int genwqe_platform_recovery(struct genwqe_dev *cd)
+{
+ struct pci_dev *pci_dev = cd->pci_dev;
+ int rc;
+
+ dev_info(&pci_dev->dev,
+ "[%s] resetting card for error recovery\n", __func__);
+
+ /* Clear out error injection flags */
+ cd->err_inject &= ~(GENWQE_INJECT_HARDWARE_FAILURE |
+ GENWQE_INJECT_GFIR_FATAL |
+ GENWQE_INJECT_GFIR_INFO);
+
+ genwqe_stop(cd);
+
+ /* Try recoverying the card with fundamental reset */
+ rc = genwqe_pci_fundamental_reset(pci_dev);
+ if (!rc) {
+ rc = genwqe_start(cd);
+ if (!rc)
+ dev_info(&pci_dev->dev,
+ "[%s] card recovered\n", __func__);
+ else
+ dev_err(&pci_dev->dev,
+ "[%s] err: cannot start card services! (err=%d)\n",
+ __func__, rc);
+ } else {
+ dev_err(&pci_dev->dev,
+ "[%s] card reset failed\n", __func__);
+ }
+
+ return rc;
+}
+
/*
* genwqe_reload_bistream() - reload card bitstream
*
@@ -875,6 +910,7 @@ static int genwqe_health_thread(void *data)
struct pci_dev *pci_dev = cd->pci_dev;
u64 gfir, gfir_masked, slu_unitcfg, app_unitcfg;
+ health_thread_begin:
while (!kthread_should_stop()) {
rc = wait_event_interruptible_timeout(cd->health_waitq,
(genwqe_health_check_cond(cd, &gfir) ||
@@ -960,6 +996,15 @@ static int genwqe_health_thread(void *data)
/* We do nothing if the card is going over PCI recovery */
if (pci_channel_offline(pci_dev))
return -EIO;
+
+ /*
+ * If it's supported by the platform, we try a fundamental reset
+ * to recover from a fatal error. Otherwise, we continue to wait
+ * for an external recovery procedure to take care of it.
+ */
+ rc = genwqe_platform_recovery(cd);
+ if (!rc)
+ goto health_thread_begin;
}
dev_err(&pci_dev->dev,
OpenPOWER on IntegriCloud