Merge patch series "smartpqi updates"

Don Brace <don.brace@microchip.com> says:

These patches are based on Martin Petersen's 6.19/scsi-queue tree
  https://git.kernel.org/pub/scm/linux/kernel/git/mkp/scsi.git
  6.19/scsi-queue

This patch series includes four patches, with two main functional changes:

1. smartpqi-Add-timeout-value-to-RAID-path-requests-to-physical-devices

   Sets a timeout value for requests sent to physical devices via the
   RAID path. This prevents the controller firmware from waiting
   indefinitely and allows it to time out requests a few seconds before
   the OS issues Target Management Function (TMF) commands.

   The timeout value sent to the firmware is set to 3 seconds less than
   the OS timeout, which significantly reduces TMF invocations.

2. smartpqi-fix-Device-resources-accessed-after-device-removal
   Fixes a race condition during device removal by:
     * Checking for device removal in the reset handler and canceling any
       pending reset work if the device is no longer present.
     * Canceling outstanding TMF work items in the .sdev_destroy handler.

   Together, these changes eliminate races between reset operations
   and device removal.

The other two patches:
3. smartpqi-add-new-Hurray-Data-pci-device
   Adds support for new Hurray Data PCI device.
   No functional changes.
4. smartpqi-update-driver-version-to-2.1.36-026
   Updates the driver version string.
   No functional changes.

Link: https://patch.msgid.link/20251106163823.786828-1-don.brace@microchip.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

Author: martinkpetersen

drivers/scsi/smartpqi/smartpqi_init.c

@@ -34,11 +34,11 @@
 #define BUILD_TIMESTAMP
 #endif
 
-#define DRIVER_VERSION		"2.1.34-035"
+#define DRIVER_VERSION		"2.1.36-026"
 #define DRIVER_MAJOR		2
 #define DRIVER_MINOR		1
-#define DRIVER_RELEASE		34
-#define DRIVER_REVISION		35
+#define DRIVER_RELEASE		36
+#define DRIVER_REVISION		26
 
 #define DRIVER_NAME		"Microchip SmartPQI Driver (v" \
 				DRIVER_VERSION BUILD_TIMESTAMP ")"
@@ -5555,14 +5555,25 @@ static void pqi_raid_io_complete(struct pqi_io_request *io_request,
 	pqi_scsi_done(scmd);
 }
 
+/*
+ * Adjust the timeout value for physical devices sent to the firmware
+ * by subtracting 3 seconds for timeouts greater than or equal to 8 seconds.
+ *
+ * This provides the firmware with additional time to attempt early recovery
+ * before the OS-level timeout occurs.
+ */
+#define ADJUST_SECS_TIMEOUT_VALUE(tv)   (((tv) >= 8) ? ((tv) - 3) : (tv))
+
 static int pqi_raid_submit_io(struct pqi_ctrl_info *ctrl_info,
 	struct pqi_scsi_dev *device, struct scsi_cmnd *scmd,
 	struct pqi_queue_group *queue_group, bool io_high_prio)
 {
 	int rc;
+	u32 timeout;
 	size_t cdb_length;
 	struct pqi_io_request *io_request;
 	struct pqi_raid_path_request *request;
+	struct request *rq;
 
 	io_request = pqi_alloc_io_request(ctrl_info, scmd);
 	if (!io_request)
@@ -5634,6 +5645,12 @@ static int pqi_raid_submit_io(struct pqi_ctrl_info *ctrl_info,
 		return SCSI_MLQUEUE_HOST_BUSY;
 	}
 
+	if (device->is_physical_device) {
+		rq = scsi_cmd_to_rq(scmd);
+		timeout = rq->timeout / HZ;
+		put_unaligned_le32(ADJUST_SECS_TIMEOUT_VALUE(timeout), &request->timeout);
+	}
+
 	pqi_start_io(ctrl_info, queue_group, RAID_PATH, io_request);
 
 	return 0;
@@ -6410,10 +6427,22 @@ static int pqi_device_reset(struct pqi_ctrl_info *ctrl_info, struct pqi_scsi_dev
 
 static int pqi_device_reset_handler(struct pqi_ctrl_info *ctrl_info, struct pqi_scsi_dev *device, u8 lun, struct scsi_cmnd *scmd, u8 scsi_opcode)
 {
+	unsigned long flags;
 	int rc;
 
 	mutex_lock(&ctrl_info->lun_reset_mutex);
 
+	spin_lock_irqsave(&ctrl_info->scsi_device_list_lock, flags);
+	if (pqi_find_scsi_dev(ctrl_info, device->bus, device->target, device->lun) == NULL) {
+		dev_warn(&ctrl_info->pci_dev->dev,
+			"skipping reset of scsi %d:%d:%d:%u, device has been removed\n",
+			ctrl_info->scsi_host->host_no, device->bus, device->target, device->lun);
+		spin_unlock_irqrestore(&ctrl_info->scsi_device_list_lock, flags);
+		mutex_unlock(&ctrl_info->lun_reset_mutex);
+		return 0;
+	}
+	spin_unlock_irqrestore(&ctrl_info->scsi_device_list_lock, flags);
+
 	dev_err(&ctrl_info->pci_dev->dev,
 		"resetting scsi %d:%d:%d:%u SCSI cmd at %p due to cmd opcode 0x%02x\n",
 		ctrl_info->scsi_host->host_no, device->bus, device->target, lun, scmd, scsi_opcode);
@@ -6594,7 +6623,9 @@ static void pqi_sdev_destroy(struct scsi_device *sdev)
 {
 	struct pqi_ctrl_info *ctrl_info;
 	struct pqi_scsi_dev *device;
+	struct pqi_tmf_work *tmf_work;
 	int mutex_acquired;
+	unsigned int lun;
 	unsigned long flags;
 
 	ctrl_info = shost_to_hba(sdev->host);
@@ -6621,8 +6652,13 @@ static void pqi_sdev_destroy(struct scsi_device *sdev)
 
 	mutex_unlock(&ctrl_info->scan_mutex);
 
+	for (lun = 0, tmf_work = device->tmf_work; lun < PQI_MAX_LUNS_PER_DEVICE; lun++, tmf_work++)
+		cancel_work_sync(&tmf_work->work_struct);
+
+	mutex_lock(&ctrl_info->lun_reset_mutex);
 	pqi_dev_info(ctrl_info, "removed", device);
 	pqi_free_device(device);
+	mutex_unlock(&ctrl_info->lun_reset_mutex);
 }
 
 static int pqi_getpciinfo_ioctl(struct pqi_ctrl_info *ctrl_info, void __user *arg)
@@ -10109,6 +10145,10 @@ static const struct pci_device_id pqi_pci_id_table[] = {
 		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
 			       0x207d, 0x4240)
 	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       0x207d, 0x4840)
+	},
 	{
 		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
 			       PCI_VENDOR_ID_ADVANTECH, 0x8312)