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
  ..

1 files changed, 168 insertions, 91 deletions

diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 35ad5e8a31ab..0dc95e102e69 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -418,6 +418,46 @@ provisioning_mode_store(struct device *dev, struct device_attribute *attr,
 }
 static DEVICE_ATTR_RW(provisioning_mode);
 
+static const char *zeroing_mode[] = {
+	[SD_ZERO_WRITE]		= "write",
+	[SD_ZERO_WS]		= "writesame",
+	[SD_ZERO_WS16_UNMAP]	= "writesame_16_unmap",
+	[SD_ZERO_WS10_UNMAP]	= "writesame_10_unmap",
+};
+
+static ssize_t
+zeroing_mode_show(struct device *dev, struct device_attribute *attr,
+		  char *buf)
+{
+	struct scsi_disk *sdkp = to_scsi_disk(dev);
+
+	return snprintf(buf, 20, "%s\n", zeroing_mode[sdkp->zeroing_mode]);
+}
+
+static ssize_t
+zeroing_mode_store(struct device *dev, struct device_attribute *attr,
+		   const char *buf, size_t count)
+{
+	struct scsi_disk *sdkp = to_scsi_disk(dev);
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	if (!strncmp(buf, zeroing_mode[SD_ZERO_WRITE], 20))
+		sdkp->zeroing_mode = SD_ZERO_WRITE;
+	else if (!strncmp(buf, zeroing_mode[SD_ZERO_WS], 20))
+		sdkp->zeroing_mode = SD_ZERO_WS;
+	else if (!strncmp(buf, zeroing_mode[SD_ZERO_WS16_UNMAP], 20))
+		sdkp->zeroing_mode = SD_ZERO_WS16_UNMAP;
+	else if (!strncmp(buf, zeroing_mode[SD_ZERO_WS10_UNMAP], 20))
+		sdkp->zeroing_mode = SD_ZERO_WS10_UNMAP;
+	else
+		return -EINVAL;
+
+	return count;
+}
+static DEVICE_ATTR_RW(zeroing_mode);
+
 static ssize_t
 max_medium_access_timeouts_show(struct device *dev,
 				struct device_attribute *attr, char *buf)
@@ -496,6 +536,7 @@ static struct attribute *sd_disk_attrs[] = {
 	&dev_attr_app_tag_own.attr,
 	&dev_attr_thin_provisioning.attr,
 	&dev_attr_provisioning_mode.attr,
+	&dev_attr_zeroing_mode.attr,
 	&dev_attr_max_write_same_blocks.attr,
 	&dev_attr_max_medium_access_timeouts.attr,
 	NULL,
@@ -644,26 +685,11 @@ static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode)
 	unsigned int logical_block_size = sdkp->device->sector_size;
 	unsigned int max_blocks = 0;
 
-	q->limits.discard_zeroes_data = 0;
-
-	/*
-	 * When LBPRZ is reported, discard alignment and granularity
-	 * must be fixed to the logical block size. Otherwise the block
-	 * layer will drop misaligned portions of the request which can
-	 * lead to data corruption. If LBPRZ is not set, we honor the
-	 * device preference.
-	 */
-	if (sdkp->lbprz) {
-		q->limits.discard_alignment = 0;
-		q->limits.discard_granularity = logical_block_size;
-	} else {
-		q->limits.discard_alignment = sdkp->unmap_alignment *
-			logical_block_size;
-		q->limits.discard_granularity =
-			max(sdkp->physical_block_size,
-			    sdkp->unmap_granularity * logical_block_size);
-	}
-
+	q->limits.discard_alignment =
+		sdkp->unmap_alignment * logical_block_size;
+	q->limits.discard_granularity =
+		max(sdkp->physical_block_size,
+		    sdkp->unmap_granularity * logical_block_size);
 	sdkp->provisioning_mode = mode;
 
 	switch (mode) {
@@ -681,19 +707,16 @@ static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode)
 	case SD_LBP_WS16:
 		max_blocks = min_not_zero(sdkp->max_ws_blocks,
 					  (u32)SD_MAX_WS16_BLOCKS);
-		q->limits.discard_zeroes_data = sdkp->lbprz;
 		break;
 
 	case SD_LBP_WS10:
 		max_blocks = min_not_zero(sdkp->max_ws_blocks,
 					  (u32)SD_MAX_WS10_BLOCKS);
-		q->limits.discard_zeroes_data = sdkp->lbprz;
 		break;
 
 	case SD_LBP_ZERO:
 		max_blocks = min_not_zero(sdkp->max_ws_blocks,
 					  (u32)SD_MAX_WS10_BLOCKS);
-		q->limits.discard_zeroes_data = 1;
 		break;
 	}
 
@@ -701,93 +724,122 @@ static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode)
 	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
 }
 
-/**
- * sd_setup_discard_cmnd - unmap blocks on thinly provisioned device
- * @sdp: scsi device to operate on
- * @rq: Request to prepare
- *
- * Will issue either UNMAP or WRITE SAME(16) depending on preference
- * indicated by target device.
- **/
-static int sd_setup_discard_cmnd(struct scsi_cmnd *cmd)
+static int sd_setup_unmap_cmnd(struct scsi_cmnd *cmd)
 {
-	struct request *rq = cmd->request;
 	struct scsi_device *sdp = cmd->device;
-	struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
-	sector_t sector = blk_rq_pos(rq);
-	unsigned int nr_sectors = blk_rq_sectors(rq);
-	unsigned int len;
-	int ret;
+	struct request *rq = cmd->request;
+	u64 sector = blk_rq_pos(rq) >> (ilog2(sdp->sector_size) - 9);
+	u32 nr_sectors = blk_rq_sectors(rq) >> (ilog2(sdp->sector_size) - 9);
+	unsigned int data_len = 24;
 	char *buf;
-	struct page *page;
-
-	sector >>= ilog2(sdp->sector_size) - 9;
-	nr_sectors >>= ilog2(sdp->sector_size) - 9;
 
-	page = alloc_page(GFP_ATOMIC | __GFP_ZERO);
-	if (!page)
+	rq->special_vec.bv_page = alloc_page(GFP_ATOMIC | __GFP_ZERO);
+	if (!rq->special_vec.bv_page)
 		return BLKPREP_DEFER;
+	rq->special_vec.bv_offset = 0;
+	rq->special_vec.bv_len = data_len;
+	rq->rq_flags |= RQF_SPECIAL_PAYLOAD;
 
-	switch (sdkp->provisioning_mode) {
-	case SD_LBP_UNMAP:
-		buf = page_address(page);
+	cmd->cmd_len = 10;
+	cmd->cmnd[0] = UNMAP;
+	cmd->cmnd[8] = 24;
 
-		cmd->cmd_len = 10;
-		cmd->cmnd[0] = UNMAP;
-		cmd->cmnd[8] = 24;
+	buf = page_address(rq->special_vec.bv_page);
+	put_unaligned_be16(6 + 16, &buf[0]);
+	put_unaligned_be16(16, &buf[2]);
+	put_unaligned_be64(sector, &buf[8]);
+	put_unaligned_be32(nr_sectors, &buf[16]);
 
-		put_unaligned_be16(6 + 16, &buf[0]);
-		put_unaligned_be16(16, &buf[2]);
-		put_unaligned_be64(sector, &buf[8]);
-		put_unaligned_be32(nr_sectors, &buf[16]);
+	cmd->allowed = SD_MAX_RETRIES;
+	cmd->transfersize = data_len;
+	rq->timeout = SD_TIMEOUT;
+	scsi_req(rq)->resid_len = data_len;
 
-		len = 24;
-		break;
+	return scsi_init_io(cmd);
+}
 
-	case SD_LBP_WS16:
-		cmd->cmd_len = 16;
-		cmd->cmnd[0] = WRITE_SAME_16;
+static int sd_setup_write_same16_cmnd(struct scsi_cmnd *cmd, bool unmap)
+{
+	struct scsi_device *sdp = cmd->device;
+	struct request *rq = cmd->request;
+	u64 sector = blk_rq_pos(rq) >> (ilog2(sdp->sector_size) - 9);
+	u32 nr_sectors = blk_rq_sectors(rq) >> (ilog2(sdp->sector_size) - 9);
+	u32 data_len = sdp->sector_size;
+
+	rq->special_vec.bv_page = alloc_page(GFP_ATOMIC | __GFP_ZERO);
+	if (!rq->special_vec.bv_page)
+		return BLKPREP_DEFER;
+	rq->special_vec.bv_offset = 0;
+	rq->special_vec.bv_len = data_len;
+	rq->rq_flags |= RQF_SPECIAL_PAYLOAD;
+
+	cmd->cmd_len = 16;
+	cmd->cmnd[0] = WRITE_SAME_16;
+	if (unmap)
 		cmd->cmnd[1] = 0x8; /* UNMAP */
-		put_unaligned_be64(sector, &cmd->cmnd[2]);
-		put_unaligned_be32(nr_sectors, &cmd->cmnd[10]);
+	put_unaligned_be64(sector, &cmd->cmnd[2]);
+	put_unaligned_be32(nr_sectors, &cmd->cmnd[10]);
 
-		len = sdkp->device->sector_size;
-		break;
+	cmd->allowed = SD_MAX_RETRIES;
+	cmd->transfersize = data_len;
+	rq->timeout = unmap ? SD_TIMEOUT : SD_WRITE_SAME_TIMEOUT;
+	scsi_req(rq)->resid_len = data_len;
 
-	case SD_LBP_WS10:
-	case SD_LBP_ZERO:
-		cmd->cmd_len = 10;
-		cmd->cmnd[0] = WRITE_SAME;
-		if (sdkp->provisioning_mode == SD_LBP_WS10)
-			cmd->cmnd[1] = 0x8; /* UNMAP */
-		put_unaligned_be32(sector, &cmd->cmnd[2]);
-		put_unaligned_be16(nr_sectors, &cmd->cmnd[7]);
+	return scsi_init_io(cmd);
+}
 
-		len = sdkp->device->sector_size;
-		break;
+static int sd_setup_write_same10_cmnd(struct scsi_cmnd *cmd, bool unmap)
+{
+	struct scsi_device *sdp = cmd->device;
+	struct request *rq = cmd->request;
+	u64 sector = blk_rq_pos(rq) >> (ilog2(sdp->sector_size) - 9);
+	u32 nr_sectors = blk_rq_sectors(rq) >> (ilog2(sdp->sector_size) - 9);
+	u32 data_len = sdp->sector_size;
 
-	default:
-		ret = BLKPREP_INVALID;
-		goto out;
-	}
+	rq->special_vec.bv_page = alloc_page(GFP_ATOMIC | __GFP_ZERO);
+	if (!rq->special_vec.bv_page)
+		return BLKPREP_DEFER;
+	rq->special_vec.bv_offset = 0;
+	rq->special_vec.bv_len = data_len;
+	rq->rq_flags |= RQF_SPECIAL_PAYLOAD;
 
-	rq->timeout = SD_TIMEOUT;
+	cmd->cmd_len = 10;
+	cmd->cmnd[0] = WRITE_SAME;
+	if (unmap)
+		cmd->cmnd[1] = 0x8; /* UNMAP */
+	put_unaligned_be32(sector, &cmd->cmnd[2]);
+	put_unaligned_be16(nr_sectors, &cmd->cmnd[7]);
 
-	cmd->transfersize = len;
 	cmd->allowed = SD_MAX_RETRIES;
+	cmd->transfersize = data_len;
+	rq->timeout = unmap ? SD_TIMEOUT : SD_WRITE_SAME_TIMEOUT;
+	scsi_req(rq)->resid_len = data_len;
 
-	rq->special_vec.bv_page = page;
-	rq->special_vec.bv_offset = 0;
-	rq->special_vec.bv_len = len;
+	return scsi_init_io(cmd);
+}
 
-	rq->rq_flags |= RQF_SPECIAL_PAYLOAD;
-	scsi_req(rq)->resid_len = len;
+static int sd_setup_write_zeroes_cmnd(struct scsi_cmnd *cmd)
+{
+	struct request *rq = cmd->request;
+	struct scsi_device *sdp = cmd->device;
+	struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
+	u64 sector = blk_rq_pos(rq) >> (ilog2(sdp->sector_size) - 9);
+	u32 nr_sectors = blk_rq_sectors(rq) >> (ilog2(sdp->sector_size) - 9);
+
+	if (!(rq->cmd_flags & REQ_NOUNMAP)) {
+		switch (sdkp->zeroing_mode) {
+		case SD_ZERO_WS16_UNMAP:
+			return sd_setup_write_same16_cmnd(cmd, true);
+		case SD_ZERO_WS10_UNMAP:
+			return sd_setup_write_same10_cmnd(cmd, true);
+		}
+	}
 
-	ret = scsi_init_io(cmd);
-out:
-	if (ret != BLKPREP_OK)
-		__free_page(page);
-	return ret;
+	if (sdp->no_write_same)
+		return BLKPREP_INVALID;
+	if (sdkp->ws16 || sector > 0xffffffff || nr_sectors > 0xffff)
+		return sd_setup_write_same16_cmnd(cmd, false);
+	return sd_setup_write_same10_cmnd(cmd, false);
 }
 
 static void sd_config_write_same(struct scsi_disk *sdkp)
@@ -816,9 +868,20 @@ static void sd_config_write_same(struct scsi_disk *sdkp)
 		sdkp->max_ws_blocks = 0;
 	}
 
+	if (sdkp->lbprz && sdkp->lbpws)
+		sdkp->zeroing_mode = SD_ZERO_WS16_UNMAP;
+	else if (sdkp->lbprz && sdkp->lbpws10)
+		sdkp->zeroing_mode = SD_ZERO_WS10_UNMAP;
+	else if (sdkp->max_ws_blocks)
+		sdkp->zeroing_mode = SD_ZERO_WS;
+	else
+		sdkp->zeroing_mode = SD_ZERO_WRITE;
+
 out:
 	blk_queue_max_write_same_sectors(q, sdkp->max_ws_blocks *
 					 (logical_block_size >> 9));
+	blk_queue_max_write_zeroes_sectors(q, sdkp->max_ws_blocks *
+					 (logical_block_size >> 9));
 }
 
 /**
@@ -1155,7 +1218,20 @@ static int sd_init_command(struct scsi_cmnd *cmd)
 
 	switch (req_op(rq)) {
 	case REQ_OP_DISCARD:
-		return sd_setup_discard_cmnd(cmd);
+		switch (scsi_disk(rq->rq_disk)->provisioning_mode) {
+		case SD_LBP_UNMAP:
+			return sd_setup_unmap_cmnd(cmd);
+		case SD_LBP_WS16:
+			return sd_setup_write_same16_cmnd(cmd, true);
+		case SD_LBP_WS10:
+			return sd_setup_write_same10_cmnd(cmd, true);
+		case SD_LBP_ZERO:
+			return sd_setup_write_same10_cmnd(cmd, false);
+		default:
+			return BLKPREP_INVALID;
+		}
+	case REQ_OP_WRITE_ZEROES:
+		return sd_setup_write_zeroes_cmnd(cmd);
 	case REQ_OP_WRITE_SAME:
 		return sd_setup_write_same_cmnd(cmd);
 	case REQ_OP_FLUSH:
@@ -1795,6 +1871,7 @@ static int sd_done(struct scsi_cmnd *SCpnt)
 
 	switch (req_op(req)) {
 	case REQ_OP_DISCARD:
+	case REQ_OP_WRITE_ZEROES:
 	case REQ_OP_WRITE_SAME:
 	case REQ_OP_ZONE_RESET:
 		if (!result) {
@@ -2768,7 +2845,7 @@ static void sd_read_block_limits(struct scsi_disk *sdkp)
 				sd_config_discard(sdkp, SD_LBP_WS16);
 
 		} else {	/* LBP VPD page tells us what to use */
-			if (sdkp->lbpu && sdkp->max_unmap_blocks && !sdkp->lbprz)
+			if (sdkp->lbpu && sdkp->max_unmap_blocks)
 				sd_config_discard(sdkp, SD_LBP_UNMAP);
 			else if (sdkp->lbpws)
 				sd_config_discard(sdkp, SD_LBP_WS16);