[PATCH for-next 12/13] IB/{hfi1, qib}: Add handling of kernel restart

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



From: Alex Estrin <alex.estrin@xxxxxxxxx>

A warm restart will fail to unload the driver, leaving link state
potentially flapping up to the point the BIOS resets the adapter.
Correct the issue by hooking the shutdown pci method,
which will bring link down and remove the driver.

Cc: <stable@xxxxxxxxxxxxxxx> # 4.9.x
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@xxxxxxxxx>
Signed-off-by: Alex Estrin <alex.estrin@xxxxxxxxx>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@xxxxxxxxx>
---
 drivers/infiniband/hw/hfi1/hfi.h     |    1 +
 drivers/infiniband/hw/hfi1/init.c    |    5 +++++
 drivers/infiniband/hw/qib/qib.h      |    1 +
 drivers/infiniband/hw/qib/qib_init.c |    5 +++++
 4 files changed, 12 insertions(+), 0 deletions(-)

diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h
index 4305000..777abb8 100644
--- a/drivers/infiniband/hw/hfi1/hfi.h
+++ b/drivers/infiniband/hw/hfi1/hfi.h
@@ -1857,6 +1857,7 @@ struct cc_state *get_cc_state_protected(struct hfi1_pportdata *ppd)
 #define HFI1_HAS_SDMA_TIMEOUT  0x8
 #define HFI1_HAS_SEND_DMA      0x10   /* Supports Send DMA */
 #define HFI1_FORCED_FREEZE     0x80   /* driver forced freeze mode */
+#define HFI1_REMOVE           0x100   /* unloading device */
 
 /* IB dword length mask in PBC (lower 11 bits); same for all chips */
 #define HFI1_PBC_LENGTH_MASK                     ((1 << 11) - 1)
diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c
index c45cca5..20fa898 100644
--- a/drivers/infiniband/hw/hfi1/init.c
+++ b/drivers/infiniband/hw/hfi1/init.c
@@ -1388,6 +1388,7 @@ void hfi1_disable_after_error(struct hfi1_devdata *dd)
 	.name = DRIVER_NAME,
 	.probe = init_one,
 	.remove = remove_one,
+	.shutdown = remove_one,
 	.id_table = hfi1_pci_tbl,
 	.err_handler = &hfi1_pci_err_handler,
 };
@@ -1768,6 +1769,10 @@ static void remove_one(struct pci_dev *pdev)
 {
 	struct hfi1_devdata *dd = pci_get_drvdata(pdev);
 
+	if (dd->flags & HFI1_REMOVE)
+		return;
+	dd->flags |= HFI1_REMOVE;
+
 	/* close debugfs files before ib unregister */
 	hfi1_dbg_ibdev_exit(&dd->verbs_dev);
 
diff --git a/drivers/infiniband/hw/qib/qib.h b/drivers/infiniband/hw/qib/qib.h
index 4607245..677b757 100644
--- a/drivers/infiniband/hw/qib/qib.h
+++ b/drivers/infiniband/hw/qib/qib.h
@@ -1228,6 +1228,7 @@ int qib_cdev_init(int minor, const char *name,
 #define QIB_BADINTR           0x8000 /* severe interrupt problems */
 #define QIB_DCA_ENABLED       0x10000 /* Direct Cache Access enabled */
 #define QIB_HAS_QSFP          0x20000 /* device (card instance) has QSFP */
+#define QIB_REMOVE            0x40000 /* unloading device */
 
 /*
  * values for ppd->lflags (_ib_port_ related flags)
diff --git a/drivers/infiniband/hw/qib/qib_init.c b/drivers/infiniband/hw/qib/qib_init.c
index 3990f38..796dea4 100644
--- a/drivers/infiniband/hw/qib/qib_init.c
+++ b/drivers/infiniband/hw/qib/qib_init.c
@@ -1201,6 +1201,7 @@ void qib_disable_after_error(struct qib_devdata *dd)
 	.name = QIB_DRV_NAME,
 	.probe = qib_init_one,
 	.remove = qib_remove_one,
+	.shutdown = qib_remove_one,
 	.id_table = qib_pci_tbl,
 	.err_handler = &qib_pci_err_handler,
 };
@@ -1526,6 +1527,10 @@ static void qib_remove_one(struct pci_dev *pdev)
 	struct qib_devdata *dd = pci_get_drvdata(pdev);
 	int ret;
 
+	if (dd->flags & QIB_REMOVE)
+		return;
+	dd->flags |= QIB_REMOVE;
+
 	/* unregister from IB core */
 	qib_unregister_ib_device(dd);
 

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html



[Index of Archives]     [Linux USB Devel]     [Video for Linux]     [Linux Audio Users]     [Photo]     [Yosemite News]     [Yosemite Photos]     [Linux Kernel]     [Linux SCSI]     [XFree86]

  Powered by Linux