[PATCH 1/5] PCI/switchtec: Error out MRPC execution when no GAS access

[kelvin.cao]

From: Kelvin Cao <kelvin.cao@xxxxxxxxxxxxx>

After a firmware hard reset, MRPC command executions, which are based
on the PCI BAR (which Microchip refers to as GAS) read/write, will hang
indefinitely. This is because after a reset, the host will fail all GAS
reads (get all 1s), in which case the driver won't get a valid MRPC
status.

Add a read check to GAS access when a MRPC command execution doesn't
response timely, error out if the check fails.

Signed-off-by: Kelvin Cao <kelvin.cao@xxxxxxxxxxxxx>
---
 drivers/pci/switch/switchtec.c | 59 ++++++++++++++++++++++++++++++----
 1 file changed, 52 insertions(+), 7 deletions(-)

diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c
index 0b301f8be9ed..092653487021 100644
--- a/drivers/pci/switch/switchtec.c
+++ b/drivers/pci/switch/switchtec.c
@@ -45,6 +45,7 @@ enum mrpc_state {
 	MRPC_QUEUED,
 	MRPC_RUNNING,
 	MRPC_DONE,
+	MRPC_IO_ERROR,
 };
 
 struct switchtec_user {
@@ -66,6 +67,13 @@ struct switchtec_user {
 	int event_cnt;
 };
 
+static int check_access(struct switchtec_dev *stdev)
+{
+	u32 device = ioread32(&stdev->mmio_sys_info->device_id);
+
+	return stdev->pdev->device == device;
+}
+
 static struct switchtec_user *stuser_create(struct switchtec_dev *stdev)
 {
 	struct switchtec_user *stuser;
@@ -113,6 +121,7 @@ static void stuser_set_state(struct switchtec_user *stuser,
 		[MRPC_QUEUED] = "QUEUED",
 		[MRPC_RUNNING] = "RUNNING",
 		[MRPC_DONE] = "DONE",
+		[MRPC_IO_ERROR] = "IO_ERROR",
 	};
 
 	stuser->state = state;
@@ -184,6 +193,21 @@ static int mrpc_queue_cmd(struct switchtec_user *stuser)
 	return 0;
 }
 
+static void mrpc_cleanup_cmd(struct switchtec_dev *stdev)
+{
+	/* requires the mrpc_mutex to already be held when called */
+	struct switchtec_user *stuser = list_entry(stdev->mrpc_queue.next,
+						   struct switchtec_user, list);
+
+	stuser->cmd_done = true;
+	wake_up_interruptible(&stuser->cmd_comp);
+	list_del_init(&stuser->list);
+	stuser_put(stuser);
+	stdev->mrpc_busy = 0;
+
+	mrpc_cmd_submit(stdev);
+}
+
 static void mrpc_complete_cmd(struct switchtec_dev *stdev)
 {
 	/* requires the mrpc_mutex to already be held when called */
@@ -223,13 +247,7 @@ static void mrpc_complete_cmd(struct switchtec_dev *stdev)
 		memcpy_fromio(stuser->data, &stdev->mmio_mrpc->output_data,
 			      stuser->read_len);
 out:
-	stuser->cmd_done = true;
-	wake_up_interruptible(&stuser->cmd_comp);
-	list_del_init(&stuser->list);
-	stuser_put(stuser);
-	stdev->mrpc_busy = 0;
-
-	mrpc_cmd_submit(stdev);
+	mrpc_cleanup_cmd(stdev);
 }
 
 static void mrpc_event_work(struct work_struct *work)
@@ -246,6 +264,23 @@ static void mrpc_event_work(struct work_struct *work)
 	mutex_unlock(&stdev->mrpc_mutex);
 }
 
+static void mrpc_error_complete_cmd(struct switchtec_dev *stdev)
+{
+	/* requires the mrpc_mutex to already be held when called */
+
+	struct switchtec_user *stuser;
+
+	if (list_empty(&stdev->mrpc_queue))
+		return;
+
+	stuser = list_entry(stdev->mrpc_queue.next,
+			    struct switchtec_user, list);
+
+	stuser_set_state(stuser, MRPC_IO_ERROR);
+
+	mrpc_cleanup_cmd(stdev);
+}
+
 static void mrpc_timeout_work(struct work_struct *work)
 {
 	struct switchtec_dev *stdev;
@@ -257,6 +292,11 @@ static void mrpc_timeout_work(struct work_struct *work)
 
 	mutex_lock(&stdev->mrpc_mutex);
 
+	if (!check_access(stdev)) {
+		mrpc_error_complete_cmd(stdev);
+		goto out;
+	}
+
 	if (stdev->dma_mrpc)
 		status = stdev->dma_mrpc->status;
 	else
@@ -544,6 +584,11 @@ static ssize_t switchtec_dev_read(struct file *filp, char __user *data,
 	if (rc)
 		return rc;
 
+	if (stuser->state == MRPC_IO_ERROR) {
+		mutex_unlock(&stdev->mrpc_mutex);
+		return -EIO;
+	}
+
 	if (stuser->state != MRPC_DONE) {
 		mutex_unlock(&stdev->mrpc_mutex);
 		return -EBADE;
-- 
2.25.1