Merge branch 'for-4.12/block' of git://git.kernel.dk/linux-block

Pull block layer updates from Jens Axboe:

 - Add BFQ IO scheduler under the new blk-mq scheduling framework. BFQ
   was initially a fork of CFQ, but subsequently changed to implement
   fairness based on B-WF2Q+, a modified variant of WF2Q. BFQ is meant
   to be used on desktop type single drives, providing good fairness.
   From Paolo.

 - Add Kyber IO scheduler. This is a full multiqueue aware scheduler,
   using a scalable token based algorithm that throttles IO based on
   live completion IO stats, similary to blk-wbt. From Omar.

 - A series from Jan, moving users to separately allocated backing
   devices. This continues the work of separating backing device life
   times, solving various problems with hot removal.

 - A series of updates for lightnvm, mostly from Javier. Includes a
   'pblk' target that exposes an open channel SSD as a physical block
   device.

 - A series of fixes and improvements for nbd from Josef.

 - A series from Omar, removing queue sharing between devices on mostly
   legacy drivers. This helps us clean up other bits, if we know that a
   queue only has a single device backing. This has been overdue for
   more than a decade.

 - Fixes for the blk-stats, and improvements to unify the stats and user
   windows. This both improves blk-wbt, and enables other users to
   register a need to receive IO stats for a device. From Omar.

 - blk-throttle improvements from Shaohua. This provides a scalable
   framework for implementing scalable priotization - particularly for
   blk-mq, but applicable to any type of block device. The interface is
   marked experimental for now.

 - Bucketized IO stats for IO polling from Stephen Bates. This improves
   efficiency of polled workloads in the presence of mixed block size
   IO.

 - A few fixes for opal, from Scott.

 - A few pulls for NVMe, including a lot of fixes for NVMe-over-fabrics.
   From a variety of folks, mostly Sagi and James Smart.

 - A series from Bart, improving our exposed info and capabilities from
   the blk-mq debugfs support.

 - A series from Christoph, cleaning up how handle WRITE_ZEROES.

 - A series from Christoph, cleaning up the block layer handling of how
   we track errors in a request. On top of being a nice cleanup, it also
   shrinks the size of struct request a bit.

 - Removal of mg_disk and hd (sorry Linus) by Christoph. The former was
   never used by platforms, and the latter has outlived it's usefulness.

 - Various little bug fixes and cleanups from a wide variety of folks.

* 'for-4.12/block' of git://git.kernel.dk/linux-block: (329 commits)
  block: hide badblocks attribute by default
  blk-mq: unify hctx delay_work and run_work
  block: add kblock_mod_delayed_work_on()
  blk-mq: unify hctx delayed_run_work and run_work
  nbd: fix use after free on module unload
  MAINTAINERS: bfq: Add Paolo as maintainer for the BFQ I/O scheduler
  blk-mq-sched: alloate reserved tags out of normal pool
  mtip32xx: use runtime tag to initialize command header
  scsi: Implement blk_mq_ops.show_rq()
  blk-mq: Add blk_mq_ops.show_rq()
  blk-mq: Show operation, cmd_flags and rq_flags names
  blk-mq: Make blk_flags_show() callers append a newline character
  blk-mq: Move the "state" debugfs attribute one level down
  blk-mq: Unregister debugfs attributes earlier
  blk-mq: Only unregister hctxs for which registration succeeded
  blk-mq-debugfs: Rename functions for registering and unregistering the mq directory
  blk-mq: Let blk_mq_debugfs_register() look up the queue name
  blk-mq: Register <dev>/queue/mq after having registered <dev>/queue
  ide-pm: always pass 0 error to ide_complete_rq in ide_do_devset
  ide-pm: always pass 0 error to __blk_end_request_all
  ..

2 files changed, 37 insertions, 22 deletions

diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index 1d1dc11aa5fa..02804cc79d82 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -169,6 +169,25 @@ static bool mtip_check_surprise_removal(struct pci_dev *pdev)
 	return false; /* device present */
 }
 
+/* we have to use runtime tag to setup command header */
+static void mtip_init_cmd_header(struct request *rq)
+{
+	struct driver_data *dd = rq->q->queuedata;
+	struct mtip_cmd *cmd = blk_mq_rq_to_pdu(rq);
+	u32 host_cap_64 = readl(dd->mmio + HOST_CAP) & HOST_CAP_64;
+
+	/* Point the command headers at the command tables. */
+	cmd->command_header = dd->port->command_list +
+				(sizeof(struct mtip_cmd_hdr) * rq->tag);
+	cmd->command_header_dma = dd->port->command_list_dma +
+				(sizeof(struct mtip_cmd_hdr) * rq->tag);
+
+	if (host_cap_64)
+		cmd->command_header->ctbau = __force_bit2int cpu_to_le32((cmd->command_dma >> 16) >> 16);
+
+	cmd->command_header->ctba = __force_bit2int cpu_to_le32(cmd->command_dma & 0xFFFFFFFF);
+}
+
 static struct mtip_cmd *mtip_get_int_command(struct driver_data *dd)
 {
 	struct request *rq;
@@ -180,6 +199,9 @@ static struct mtip_cmd *mtip_get_int_command(struct driver_data *dd)
 	if (IS_ERR(rq))
 		return NULL;
 
+	/* Internal cmd isn't submitted via .queue_rq */
+	mtip_init_cmd_header(rq);
+
 	return blk_mq_rq_to_pdu(rq);
 }
 
@@ -241,7 +263,8 @@ static void mtip_async_complete(struct mtip_port *port,
 
 	rq = mtip_rq_from_tag(dd, tag);
 
-	blk_mq_complete_request(rq, status);
+	cmd->status = status;
+	blk_mq_complete_request(rq);
 }
 
 /*
@@ -2910,18 +2933,19 @@ static void mtip_softirq_done_fn(struct request *rq)
 	if (unlikely(cmd->unaligned))
 		up(&dd->port->cmd_slot_unal);
 
-	blk_mq_end_request(rq, rq->errors);
+	blk_mq_end_request(rq, cmd->status);
 }
 
 static void mtip_abort_cmd(struct request *req, void *data,
 							bool reserved)
 {
+	struct mtip_cmd *cmd = blk_mq_rq_to_pdu(req);
 	struct driver_data *dd = data;
 
 	dbg_printk(MTIP_DRV_NAME " Aborting request, tag = %d\n", req->tag);
 
 	clear_bit(req->tag, dd->port->cmds_to_issue);
-	req->errors = -EIO;
+	cmd->status = -EIO;
 	mtip_softirq_done_fn(req);
 }
 
@@ -3807,6 +3831,8 @@ static int mtip_queue_rq(struct blk_mq_hw_ctx *hctx,
 	struct request *rq = bd->rq;
 	int ret;
 
+	mtip_init_cmd_header(rq);
+
 	if (unlikely(mtip_check_unal_depth(hctx, rq)))
 		return BLK_MQ_RQ_QUEUE_BUSY;
 
@@ -3816,7 +3842,6 @@ static int mtip_queue_rq(struct blk_mq_hw_ctx *hctx,
 	if (likely(!ret))
 		return BLK_MQ_RQ_QUEUE_OK;
 
-	rq->errors = ret;
 	return BLK_MQ_RQ_QUEUE_ERROR;
 }
 
@@ -3838,7 +3863,6 @@ static int mtip_init_cmd(void *data, struct request *rq, unsigned int hctx_idx,
 {
 	struct driver_data *dd = data;
 	struct mtip_cmd *cmd = blk_mq_rq_to_pdu(rq);
-	u32 host_cap_64 = readl(dd->mmio + HOST_CAP) & HOST_CAP_64;
 
 	/*
 	 * For flush requests, request_idx starts at the end of the
@@ -3855,17 +3879,6 @@ static int mtip_init_cmd(void *data, struct request *rq, unsigned int hctx_idx,
 
 	memset(cmd->command, 0, CMD_DMA_ALLOC_SZ);
 
-	/* Point the command headers at the command tables. */
-	cmd->command_header = dd->port->command_list +
-				(sizeof(struct mtip_cmd_hdr) * request_idx);
-	cmd->command_header_dma = dd->port->command_list_dma +
-				(sizeof(struct mtip_cmd_hdr) * request_idx);
-
-	if (host_cap_64)
-		cmd->command_header->ctbau = __force_bit2int cpu_to_le32((cmd->command_dma >> 16) >> 16);
-
-	cmd->command_header->ctba = __force_bit2int cpu_to_le32(cmd->command_dma & 0xFFFFFFFF);
-
 	sg_init_table(cmd->sg, MTIP_MAX_SG);
 	return 0;
 }
@@ -3889,7 +3902,7 @@ exit_handler:
 	return BLK_EH_RESET_TIMER;
 }
 
-static struct blk_mq_ops mtip_mq_ops = {
+static const struct blk_mq_ops mtip_mq_ops = {
 	.queue_rq	= mtip_queue_rq,
 	.init_request	= mtip_init_cmd,
 	.exit_request	= mtip_free_cmd,
@@ -4025,7 +4038,6 @@ skip_create_disk:
 		dd->queue->limits.discard_granularity = 4096;
 		blk_queue_max_discard_sectors(dd->queue,
 			MTIP_MAX_TRIM_ENTRY_LEN * MTIP_MAX_TRIM_ENTRIES);
-		dd->queue->limits.discard_zeroes_data = 0;
 	}
 
 	/* Set the capacity of the device in 512 byte sectors. */
@@ -4107,9 +4119,11 @@ static void mtip_no_dev_cleanup(struct request *rq, void *data, bool reserv)
 	struct driver_data *dd = (struct driver_data *)data;
 	struct mtip_cmd *cmd;
 
-	if (likely(!reserv))
-		blk_mq_complete_request(rq, -ENODEV);
-	else if (test_bit(MTIP_PF_IC_ACTIVE_BIT, &dd->port->flags)) {
+	if (likely(!reserv)) {
+		cmd = blk_mq_rq_to_pdu(rq);
+		cmd->status = -ENODEV;
+		blk_mq_complete_request(rq);
+	} else if (test_bit(MTIP_PF_IC_ACTIVE_BIT, &dd->port->flags)) {
 
 		cmd = mtip_cmd_from_tag(dd, MTIP_TAG_INTERNAL);
 		if (cmd->comp_func)
@@ -4162,7 +4176,7 @@ static int mtip_block_remove(struct driver_data *dd)
 		dev_info(&dd->pdev->dev, "device %s surprise removal\n",
 						dd->disk->disk_name);
 
-	blk_mq_freeze_queue_start(dd->queue);
+	blk_freeze_queue_start(dd->queue);
 	blk_mq_stop_hw_queues(dd->queue);
 	blk_mq_tagset_busy_iter(&dd->tags, mtip_no_dev_cleanup, dd);
 
diff --git a/drivers/block/mtip32xx/mtip32xx.h b/drivers/block/mtip32xx/mtip32xx.h
index 7617888f7944..57b41528a824 100644
--- a/drivers/block/mtip32xx/mtip32xx.h
+++ b/drivers/block/mtip32xx/mtip32xx.h
@@ -352,6 +352,7 @@ struct mtip_cmd {
 	int retries; /* The number of retries left for this command. */
 
 	int direction; /* Data transfer direction */
+	int status;
 };
 
 /* Structure used to describe a port. */