PCI/switchtec: Error out MRPC execution when MMIO reads fail

A firmware hard reset may be initiated by various mechanisms including a
UART interface, TWI sideband interface from BMC, MRPC command from
userspace, etc. The switchtec management driver is unaware of these
resets.

The reset clears PCI state including the BARs and Memory Space Enable
bits, so the device no longer responds to the MMIO accesses the driver
uses to operate it.

MMIO reads to the device will fail with a PCIe error. When the root
complex handles that error, it typically fabricates ~0 data to complete
the CPU read.

Check for this sort of error by reading the device ID from MMIO space.
This ID can never be ~0, so if we see that value, it probably means the
PCIe Memory Read failed and we should return an error indication to the
application using the switchtec driver.

Link: https://lore.kernel.org/r/20211014141859.11444-2-kelvin.cao@microchip.comSigned-off-by: Kelvin Cao <kelvin.cao@microchip.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>

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 +67,19 @@ struct switchtec_user {
 	int event_cnt;
 };
 
+/*
+ * The MMIO reads to the device_id register should always return the device ID
+ * of the device, otherwise the firmware is probably stuck or unreachable
+ * due to a firmware reset which clears PCI state including the BARs and Memory
+ * Space Enable bits.
+ */
+static int is_firmware_running(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 +127,7 @@ 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;
@@ -184,9 +199,26 @@ 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 */
+
 	struct switchtec_user *stuser;
 
 	if (list_empty(&stdev->mrpc_queue))
@@ -223,13 +255,7 @@ 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 +272,23 @@ 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 +300,11 @@ static void mrpc_timeout_work(struct work_struct *work)
 
 	mutex_lock(&stdev->mrpc_mutex);
 
+	if (!is_firmware_running(stdev)) {
+		mrpc_error_complete_cmd(stdev);
+		goto out;
+	}
+
 	if (stdev->dma_mrpc)
 		status = stdev->dma_mrpc->status;
 	else
@@ -544,6 +592,11 @@ 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;