qla2xxx: Prevent removal and board_disable race

Introduce mutual exclusion between the qla2xxx_remove_one PCI driver
callback and qla2x00_disable_board_on_pci_error, which is scheduled as
board_disable work by qla2x00_check_reg{32,16}_for_disconnect:

* Leave the driver-specific data attached to the underlying PCI device
intact in qla2x00_disable_board_on_pci_error, so that qla2x00_remove_one
has enough breadcrumbs to determine that any board_disable work has been
completed.

* In qla2xxx_remove_one, set a bit to prevent any subsequent
board_disable work from scheduling, then cancel and wait until pending
work has completed.

* Reuse the PCI device enable count check in qla2x00_remove_one to
determine if board_disable has occured. The original purpose of this
check was unnecessary since the driver remove function wasn't called
when the probe fails.

Signed-off-by: Joe Lawrence <joe.lawrence@stratus.com>
Acked-by: Chad Dupuis <chad.dupuis@qlogic.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

3 files changed, 22 insertions, 13 deletions

diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 4267ec6..1398818 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -3404,6 +3404,7 @@ typedef struct scsi_qla_host {
 
 	unsigned long	pci_flags;
 #define PFLG_DISCONNECTED	0	/* PCI device removed */
+#define PFLG_DRIVER_REMOVING	1	/* PCI driver .remove */
 
 	uint32_t	device_flags;
 #define SWITCH_FOUND		BIT_0
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index fd75b91..341c64d 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -117,7 +117,8 @@ qla2x00_check_reg32_for_disconnect(scsi_qla_host_t *vha, uint32_t reg)
 {
 	/* Check for PCI disconnection */
 	if (reg == 0xffffffff) {
-		if (!test_and_set_bit(PFLG_DISCONNECTED, &vha->pci_flags)) {
+		if (!test_and_set_bit(PFLG_DISCONNECTED, &vha->pci_flags) &&
+		    !test_bit(PFLG_DRIVER_REMOVING, &vha->pci_flags)) {
 			/*
 			 * Schedule this (only once) on the default system
 			 * workqueue so that all the adapter workqueues and the
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 3bfa89d..84d4df6 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -3131,15 +3131,25 @@ qla2x00_remove_one(struct pci_dev *pdev)
 	scsi_qla_host_t *base_vha;
 	struct qla_hw_data  *ha;
 
+	base_vha = pci_get_drvdata(pdev);
+	ha = base_vha->hw;
+
+	/* Indicate device removal to prevent future board_disable and wait
+	 * until any pending board_disable has completed. */
+	set_bit(PFLG_DRIVER_REMOVING, &base_vha->pci_flags);
+	cancel_work_sync(&ha->board_disable);
+
 	/*
-	 * If the PCI device is disabled that means that probe failed and any
-	 * resources should be have cleaned up on probe exit.
+	 * If the PCI device is disabled then there was a PCI-disconnect and
+	 * qla2x00_disable_board_on_pci_error has taken care of most of the
+	 * resources.
 	 */
-	if (!atomic_read(&pdev->enable_cnt))
+	if (!atomic_read(&pdev->enable_cnt)) {
+		scsi_host_put(base_vha->host);
+		kfree(ha);
+		pci_set_drvdata(pdev, NULL);
 		return;
-
-	base_vha = pci_get_drvdata(pdev);
-	ha = base_vha->hw;
+	}
 
 	qla2x00_wait_for_hba_ready(base_vha);
 
@@ -4799,18 +4809,15 @@ qla2x00_disable_board_on_pci_error(struct work_struct *work)
 	qla82xx_md_free(base_vha);
 	qla2x00_free_queues(ha);
 
-	scsi_host_put(base_vha->host);
-
 	qla2x00_unmap_iobases(ha);
 
 	pci_release_selected_regions(ha->pdev, ha->bars);
-	kfree(ha);
-	ha = NULL;
-
 	pci_disable_pcie_error_reporting(pdev);
 	pci_disable_device(pdev);
-	pci_set_drvdata(pdev, NULL);
 
+	/*
+	 * Let qla2x00_remove_one cleanup qla_hw_data on device removal.
+	 */
 }
 
 /**************************************************************************