mtip32xx: mtip_async_complete() bug fixes

commit 5eb9291c upstream.

This patch fixes 2 issues in the fast completion path:
1) Possible double completions / double dma_unmap_sg() calls due to lack
of atomicity in the check and subsequent dereference of the upper layer
callback function. Fixed with cmpxchg before unmap and callback.
2) Regression in unaligned IO constraining workaround for p420m devices.
Fixed by checking if IO is unaligned and using proper semaphore if so.
Signed-off-by: Sam Bradshaw <sbradshaw@micron.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
[ kamal: backport to 3.13 (omitted the change to MTIP_DRV_VERSION string) ]
Signed-off-by: Kamal Mostafa <kamal@canonical.com>

drivers/block/mtip32xx/mtip32xx.c

@@ -231,38 +231,45 @@ static void mtip_async_complete(struct mtip_port *port,
 				void *data,
 				int status)
 {
-	struct mtip_cmd *command;
+	struct mtip_cmd *cmd;
 	struct driver_data *dd = data;
-	int cb_status = status ? -EIO : 0;
+	int unaligned, cb_status = status ? -EIO : 0;
+	void (*func)(void *, int);
 
 	if (unlikely(!dd) || unlikely(!port))
 		return;
 
-	command = &port->commands[tag];
+	cmd = &port->commands[tag];
 
 	if (unlikely(status == PORT_IRQ_TF_ERR)) {
 		dev_warn(&port->dd->pdev->dev,
 			"Command tag %d failed due to TFE\n", tag);
 	}
 
-	/* Unmap the DMA scatter list entries */
-	dma_unmap_sg(&dd->pdev->dev,
-		command->sg,
-		command->scatter_ents,
-		command->direction);
+	/* Clear the active flag */
+	atomic_set(&port->commands[tag].active, 0);
 
 	/* Upper layer callback */
-	if (likely(command->async_callback))
-		command->async_callback(command->async_data, cb_status);
+	func = cmd->async_callback;
+	if (likely(func && cmpxchg(&cmd->async_callback, func, 0) == func)) {
 
-	command->async_callback = NULL;
-	command->comp_func = NULL;
+		/* Unmap the DMA scatter list entries */
+		dma_unmap_sg(&dd->pdev->dev,
+			cmd->sg,
+			cmd->scatter_ents,
+			cmd->direction);
 
-	/* Clear the allocated and active bits for the command */
-	atomic_set(&port->commands[tag].active, 0);
-	release_slot(port, tag);
+		func(cmd->async_data, cb_status);
+		unaligned = cmd->unaligned;
 
-	up(&port->cmd_slot);
+		/* Clear the allocated bit for the command */
+		release_slot(port, tag);
+
+		if (unlikely(unaligned))
+			up(&port->cmd_slot_unal);
+		else
+			up(&port->cmd_slot);
+	}
 }
 
 /*
@@ -639,11 +646,12 @@ static void mtip_timeout_function(unsigned long int data)
 {
 	struct mtip_port *port = (struct mtip_port *) data;
 	struct host_to_dev_fis *fis;
-	struct mtip_cmd *command;
-	int tag, cmdto_cnt = 0;
+	struct mtip_cmd *cmd;
+	int unaligned, tag, cmdto_cnt = 0;
 	unsigned int bit, group;
 	unsigned int num_command_slots;
 	unsigned long to, tagaccum[SLOTBITS_IN_LONGS];
+	void (*func)(void *, int);
 
 	if (unlikely(!port))
 		return;
@@ -673,8 +681,8 @@ static void mtip_timeout_function(unsigned long int data)
 			group = tag >> 5;
 			bit = tag & 0x1F;
 
-			command = &port->commands[tag];
-			fis = (struct host_to_dev_fis *) command->command;
+			cmd = &port->commands[tag];
+			fis = (struct host_to_dev_fis *) cmd->command;
 
 			set_bit(tag, tagaccum);
 			cmdto_cnt++;
@@ -688,27 +696,30 @@ static void mtip_timeout_function(unsigned long int data)
 			 */
 			writel(1 << bit, port->completed[group]);
 
-			/* Unmap the DMA scatter list entries */
-			dma_unmap_sg(&port->dd->pdev->dev,
-					command->sg,
-					command->scatter_ents,
-					command->direction);
+			/* Clear the active flag for the command */
+			atomic_set(&port->commands[tag].active, 0);
 
-			/* Call the async completion callback. */
-			if (likely(command->async_callback))
-				command->async_callback(command->async_data,
-							 -EIO);
-			command->async_callback = NULL;
-			command->comp_func = NULL;
+			func = cmd->async_callback;
+			if (func &&
+			    cmpxchg(&cmd->async_callback, func, 0) == func) {
 
-			/*
-			 * Clear the allocated bit and active tag for the
-			 * command.
-			 */
-			atomic_set(&port->commands[tag].active, 0);
-			release_slot(port, tag);
+				/* Unmap the DMA scatter list entries */
+				dma_unmap_sg(&port->dd->pdev->dev,
+						cmd->sg,
+						cmd->scatter_ents,
+						cmd->direction);
 
-			up(&port->cmd_slot);
+				func(cmd->async_data, -EIO);
+				unaligned = cmd->unaligned;
+
+				/* Clear the allocated bit for the command. */
+				release_slot(port, tag);
+
+				if (unaligned)
+					up(&port->cmd_slot_unal);
+				else
+					up(&port->cmd_slot);
+			}
 		}
 	}