Merge branch 'for-3.20/core' of git://git.kernel.dk/linux-block

Pull core block IO changes from Jens Axboe:
"This contains:

- A series from Christoph that cleans up and refactors various parts
of the REQ_BLOCK_PC handling. Contributions in that series from
Dongsu Park and Kent Overstreet as well.

- CFQ:
- A bug fix for cfq for realtime IO scheduling from Jeff Moyer.
- A stable patch fixing a potential crash in CFQ in OOM
situations. From Konstantin Khlebnikov.

- blk-mq:
- Add support for tag allocation policies, from Shaohua. This is
a prep patch enabling libata (and other SCSI parts) to use the
blk-mq tagging, instead of rolling their own.
- Various little tweaks from Keith and Mike, in preparation for
DM blk-mq support.
- Minor little fixes or tweaks from me.
- A double free error fix from Tony Battersby.

- The partition 4k issue fixes from Matthew and Boaz.

- Add support for zero+unprovision for blkdev_issue_zeroout() from
Martin"

* 'for-3.20/core' of git://git.kernel.dk/linux-block: (27 commits)
block: remove unused function blk_bio_map_sg
block: handle the null_mapped flag correctly in blk_rq_map_user_iov
blk-mq: fix double-free in error path
block: prevent request-to-request merging with gaps if not allowed
blk-mq: make blk_mq_run_queues() static
dm: fix multipath regression due to initializing wrong request
cfq-iosched: handle failure of cfq group allocation
block: Quiesce zeroout wrapper
block: rewrite and split __bio_copy_iov()
block: merge __bio_map_user_iov into bio_map_user_iov
block: merge __bio_map_kern into bio_map_kern
block: pass iov_iter to the BLOCK_PC mapping functions
block: add a helper to free bio bounce buffer pages
block: use blk_rq_map_user_iov to implement blk_rq_map_user
block: simplify bio_map_kern
block: mark blk-mq devices as stackable
block: keep established cmd_flags when cloning into a blk-mq request
block: add blk-mq support to blk_insert_cloned_request()
block: require blk_rq_prep_clone() be given an initialized clone request
blk-mq: add tag allocation policy
...

Documentation/filesystems/xip.txt

···
 Execute-in-place is implemented in three steps: block device operation,
 address space operation, and file operations.
 
-A block device operation named direct_access is used to retrieve a
-reference (pointer) to a block on-disk. The reference is supposed to be
-cpu-addressable, physical address and remain valid until the release operation
-is performed. A struct block_device reference is used to address the device,
-and a sector_t argument is used to identify the individual block. As an
-alternative, memory technology devices can be used for this.
+A block device operation named direct_access is used to translate the
+block device sector number to a page frame number (pfn) that identifies
+the physical page for the memory.  It also returns a kernel virtual
+address that can be used to access the memory.
+
+The direct_access method takes a 'size' parameter that indicates the
+number of bytes being requested.  The function should return the number
+of bytes that can be contiguously accessed at that offset.  It may also
+return a negative errno if an error occurs.
 
 The block device operation is optional, these block devices support it as of
 today:

arch/powerpc/sysdev/axonram.c

···
  * axon_ram_direct_access - direct_access() method for block device
  * @device, @sector, @data: see block_device_operations method
  */
-static int
+static long
 axon_ram_direct_access(struct block_device *device, sector_t sector,
-		       void **kaddr, unsigned long *pfn)
+		       void **kaddr, unsigned long *pfn, long size)
 {
 	struct axon_ram_bank *bank = device->bd_disk->private_data;
-	loff_t offset;
-
-	offset = sector;
-	if (device->bd_part != NULL)
-		offset += device->bd_part->start_sect;
-	offset <<= AXON_RAM_SECTOR_SHIFT;
-	if (offset >= bank->size) {
-		dev_err(&bank->device->dev, "Access outside of address space\n");
-		return -ERANGE;
-	}
+	loff_t offset = (loff_t)sector << AXON_RAM_SECTOR_SHIFT;
 
 	*kaddr = (void *)(bank->ph_addr + offset);
 	*pfn = virt_to_phys(kaddr) >> PAGE_SHIFT;
 
-	return 0;
+	return bank->size - offset;
 }
 
 static const struct block_device_operations axon_ram_devops = {

block/bio.c

···
 #include <linux/mempool.h>
 #include <linux/workqueue.h>
 #include <linux/cgroup.h>
-#include <scsi/sg.h>		/* for struct sg_iovec */
 
 #include <trace/events/block.h>
 
···
 EXPORT_SYMBOL(bio_copy_data);
 
 struct bio_map_data {
-	int nr_sgvecs;
 	int is_our_pages;
-	struct sg_iovec sgvecs[];
+	struct iov_iter iter;
+	struct iovec iov[];
 };
-
-static void bio_set_map_data(struct bio_map_data *bmd, struct bio *bio,
-			     const struct sg_iovec *iov, int iov_count,
-			     int is_our_pages)
-{
-	memcpy(bmd->sgvecs, iov, sizeof(struct sg_iovec) * iov_count);
-	bmd->nr_sgvecs = iov_count;
-	bmd->is_our_pages = is_our_pages;
-	bio->bi_private = bmd;
-}
 
 static struct bio_map_data *bio_alloc_map_data(unsigned int iov_count,
 					       gfp_t gfp_mask)
···
 		return NULL;
 
 	return kmalloc(sizeof(struct bio_map_data) +
-		       sizeof(struct sg_iovec) * iov_count, gfp_mask);
+		       sizeof(struct iovec) * iov_count, gfp_mask);
 }
 
-static int __bio_copy_iov(struct bio *bio, const struct sg_iovec *iov, int iov_count,
-			  int to_user, int from_user, int do_free_page)
+/**
+ * bio_copy_from_iter - copy all pages from iov_iter to bio
+ * @bio: The &struct bio which describes the I/O as destination
+ * @iter: iov_iter as source
+ *
+ * Copy all pages from iov_iter to bio.
+ * Returns 0 on success, or error on failure.
+ */
+static int bio_copy_from_iter(struct bio *bio, struct iov_iter iter)
 {
-	int ret = 0, i;
+	int i;
 	struct bio_vec *bvec;
-	int iov_idx = 0;
-	unsigned int iov_off = 0;
 
 	bio_for_each_segment_all(bvec, bio, i) {
-		char *bv_addr = page_address(bvec->bv_page);
-		unsigned int bv_len = bvec->bv_len;
+		ssize_t ret;
 
-		while (bv_len && iov_idx < iov_count) {
-			unsigned int bytes;
-			char __user *iov_addr;
+		ret = copy_page_from_iter(bvec->bv_page,
+					  bvec->bv_offset,
+					  bvec->bv_len,
+					  &iter);
 
-			bytes = min_t(unsigned int,
-				      iov[iov_idx].iov_len - iov_off, bv_len);
-			iov_addr = iov[iov_idx].iov_base + iov_off;
+		if (!iov_iter_count(&iter))
+			break;
 
-			if (!ret) {
-				if (to_user)
-					ret = copy_to_user(iov_addr, bv_addr,
-							   bytes);
-
-				if (from_user)
-					ret = copy_from_user(bv_addr, iov_addr,
-							     bytes);
-
-				if (ret)
-					ret = -EFAULT;
-			}
-
-			bv_len -= bytes;
-			bv_addr += bytes;
-			iov_addr += bytes;
-			iov_off += bytes;
-
-			if (iov[iov_idx].iov_len == iov_off) {
-				iov_idx++;
-				iov_off = 0;
-			}
-		}
-
-		if (do_free_page)
-			__free_page(bvec->bv_page);
+		if (ret < bvec->bv_len)
+			return -EFAULT;
 	}
 
-	return ret;
+	return 0;
+}
+
+/**
+ * bio_copy_to_iter - copy all pages from bio to iov_iter
+ * @bio: The &struct bio which describes the I/O as source
+ * @iter: iov_iter as destination
+ *
+ * Copy all pages from bio to iov_iter.
+ * Returns 0 on success, or error on failure.
+ */
+static int bio_copy_to_iter(struct bio *bio, struct iov_iter iter)
+{
+	int i;
+	struct bio_vec *bvec;
+
+	bio_for_each_segment_all(bvec, bio, i) {
+		ssize_t ret;
+
+		ret = copy_page_to_iter(bvec->bv_page,
+					bvec->bv_offset,
+					bvec->bv_len,
+					&iter);
+
+		if (!iov_iter_count(&iter))
+			break;
+
+		if (ret < bvec->bv_len)
+			return -EFAULT;
+	}
+
+	return 0;
+}
+
+static void bio_free_pages(struct bio *bio)
+{
+	struct bio_vec *bvec;
+	int i;
+
+	bio_for_each_segment_all(bvec, bio, i)
+		__free_page(bvec->bv_page);
 }
 
 /**
  *	bio_uncopy_user	-	finish previously mapped bio
  *	@bio: bio being terminated
  *
- *	Free pages allocated from bio_copy_user() and write back data
+ *	Free pages allocated from bio_copy_user_iov() and write back data
  *	to user space in case of a read.
  */
 int bio_uncopy_user(struct bio *bio)
 {
 	struct bio_map_data *bmd = bio->bi_private;
-	struct bio_vec *bvec;
-	int ret = 0, i;
+	int ret = 0;
 
 	if (!bio_flagged(bio, BIO_NULL_MAPPED)) {
 		/*
 		 * if we're in a workqueue, the request is orphaned, so
 		 * don't copy into a random user address space, just free.
 		 */
-		if (current->mm)
-			ret = __bio_copy_iov(bio, bmd->sgvecs, bmd->nr_sgvecs,
-					     bio_data_dir(bio) == READ,
-					     0, bmd->is_our_pages);
-		else if (bmd->is_our_pages)
-			bio_for_each_segment_all(bvec, bio, i)
-				__free_page(bvec->bv_page);
+		if (current->mm && bio_data_dir(bio) == READ)
+			ret = bio_copy_to_iter(bio, bmd->iter);
+		if (bmd->is_our_pages)
+			bio_free_pages(bio);
 	}
 	kfree(bmd);
 	bio_put(bio);
···
 
 /**
  *	bio_copy_user_iov	-	copy user data to bio
- *	@q: destination block queue
- *	@map_data: pointer to the rq_map_data holding pages (if necessary)
- *	@iov:	the iovec.
- *	@iov_count: number of elements in the iovec
- *	@write_to_vm: bool indicating writing to pages or not
- *	@gfp_mask: memory allocation flags
+ *	@q:		destination block queue
+ *	@map_data:	pointer to the rq_map_data holding pages (if necessary)
+ *	@iter:		iovec iterator
+ *	@gfp_mask:	memory allocation flags
  *
  *	Prepares and returns a bio for indirect user io, bouncing data
  *	to/from kernel pages as necessary. Must be paired with
···
  */
 struct bio *bio_copy_user_iov(struct request_queue *q,
 			      struct rq_map_data *map_data,
-			      const struct sg_iovec *iov, int iov_count,
-			      int write_to_vm, gfp_t gfp_mask)
+			      const struct iov_iter *iter,
+			      gfp_t gfp_mask)
 {
 	struct bio_map_data *bmd;
-	struct bio_vec *bvec;
 	struct page *page;
 	struct bio *bio;
 	int i, ret;
 	int nr_pages = 0;
-	unsigned int len = 0;
+	unsigned int len = iter->count;
 	unsigned int offset = map_data ? map_data->offset & ~PAGE_MASK : 0;
 
-	for (i = 0; i < iov_count; i++) {
+	for (i = 0; i < iter->nr_segs; i++) {
 		unsigned long uaddr;
 		unsigned long end;
 		unsigned long start;
 
-		uaddr = (unsigned long)iov[i].iov_base;
-		end = (uaddr + iov[i].iov_len + PAGE_SIZE - 1) >> PAGE_SHIFT;
+		uaddr = (unsigned long) iter->iov[i].iov_base;
+		end = (uaddr + iter->iov[i].iov_len + PAGE_SIZE - 1)
+			>> PAGE_SHIFT;
 		start = uaddr >> PAGE_SHIFT;
 
 		/*
···
 			return ERR_PTR(-EINVAL);
 
 		nr_pages += end - start;
-		len += iov[i].iov_len;
 	}
 
 	if (offset)
 		nr_pages++;
 
-	bmd = bio_alloc_map_data(iov_count, gfp_mask);
+	bmd = bio_alloc_map_data(iter->nr_segs, gfp_mask);
 	if (!bmd)
 		return ERR_PTR(-ENOMEM);
+
+	/*
+	 * We need to do a deep copy of the iov_iter including the iovecs.
+	 * The caller provided iov might point to an on-stack or otherwise
+	 * shortlived one.
+	 */
+	bmd->is_our_pages = map_data ? 0 : 1;
+	memcpy(bmd->iov, iter->iov, sizeof(struct iovec) * iter->nr_segs);
+	iov_iter_init(&bmd->iter, iter->type, bmd->iov,
+			iter->nr_segs, iter->count);
 
 	ret = -ENOMEM;
 	bio = bio_kmalloc(gfp_mask, nr_pages);
 	if (!bio)
 		goto out_bmd;
 
-	if (!write_to_vm)
+	if (iter->type & WRITE)
 		bio->bi_rw |= REQ_WRITE;
 
 	ret = 0;
···
 	/*
 	 * success
 	 */
-	if ((!write_to_vm && (!map_data || !map_data->null_mapped)) ||
+	if (((iter->type & WRITE) && (!map_data || !map_data->null_mapped)) ||
 	    (map_data && map_data->from_user)) {
-		ret = __bio_copy_iov(bio, iov, iov_count, 0, 1, 0);
+		ret = bio_copy_from_iter(bio, *iter);
 		if (ret)
 			goto cleanup;
 	}
 
-	bio_set_map_data(bmd, bio, iov, iov_count, map_data ? 0 : 1);
+	bio->bi_private = bmd;
 	return bio;
 cleanup:
 	if (!map_data)
-		bio_for_each_segment_all(bvec, bio, i)
-			__free_page(bvec->bv_page);
-
+		bio_free_pages(bio);
 	bio_put(bio);
 out_bmd:
 	kfree(bmd);
···
 }
 
 /**
- *	bio_copy_user	-	copy user data to bio
- *	@q: destination block queue
- *	@map_data: pointer to the rq_map_data holding pages (if necessary)
- *	@uaddr: start of user address
- *	@len: length in bytes
- *	@write_to_vm: bool indicating writing to pages or not
- *	@gfp_mask: memory allocation flags
+ *	bio_map_user_iov - map user iovec into bio
+ *	@q:		the struct request_queue for the bio
+ *	@iter:		iovec iterator
+ *	@gfp_mask:	memory allocation flags
  *
- *	Prepares and returns a bio for indirect user io, bouncing data
- *	to/from kernel pages as necessary. Must be paired with
- *	call bio_uncopy_user() on io completion.
+ *	Map the user space address into a bio suitable for io to a block
+ *	device. Returns an error pointer in case of error.
  */
-struct bio *bio_copy_user(struct request_queue *q, struct rq_map_data *map_data,
-			  unsigned long uaddr, unsigned int len,
-			  int write_to_vm, gfp_t gfp_mask)
+struct bio *bio_map_user_iov(struct request_queue *q,
+			     const struct iov_iter *iter,
+			     gfp_t gfp_mask)
 {
-	struct sg_iovec iov;
-
-	iov.iov_base = (void __user *)uaddr;
-	iov.iov_len = len;
-
-	return bio_copy_user_iov(q, map_data, &iov, 1, write_to_vm, gfp_mask);
-}
-EXPORT_SYMBOL(bio_copy_user);
-
-static struct bio *__bio_map_user_iov(struct request_queue *q,
-				      struct block_device *bdev,
-				      const struct sg_iovec *iov, int iov_count,
-				      int write_to_vm, gfp_t gfp_mask)
-{
-	int i, j;
+	int j;
 	int nr_pages = 0;
 	struct page **pages;
 	struct bio *bio;
 	int cur_page = 0;
 	int ret, offset;
+	struct iov_iter i;
+	struct iovec iov;
 
-	for (i = 0; i < iov_count; i++) {
-		unsigned long uaddr = (unsigned long)iov[i].iov_base;
-		unsigned long len = iov[i].iov_len;
+	iov_for_each(iov, i, *iter) {
+		unsigned long uaddr = (unsigned long) iov.iov_base;
+		unsigned long len = iov.iov_len;
 		unsigned long end = (uaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
 		unsigned long start = uaddr >> PAGE_SHIFT;
 
···
 	if (!pages)
 		goto out;
 
-	for (i = 0; i < iov_count; i++) {
-		unsigned long uaddr = (unsigned long)iov[i].iov_base;
-		unsigned long len = iov[i].iov_len;
+	iov_for_each(iov, i, *iter) {
+		unsigned long uaddr = (unsigned long) iov.iov_base;
+		unsigned long len = iov.iov_len;
 		unsigned long end = (uaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
 		unsigned long start = uaddr >> PAGE_SHIFT;
 		const int local_nr_pages = end - start;
 		const int page_limit = cur_page + local_nr_pages;
 
 		ret = get_user_pages_fast(uaddr, local_nr_pages,
-				write_to_vm, &pages[cur_page]);
+				(iter->type & WRITE) != WRITE,
+				&pages[cur_page]);
 		if (ret < local_nr_pages) {
 			ret = -EFAULT;
 			goto out_unmap;
···
 	/*
 	 * set data direction, and check if mapped pages need bouncing
 	 */
-	if (!write_to_vm)
+	if (iter->type & WRITE)
 		bio->bi_rw |= REQ_WRITE;
 
-	bio->bi_bdev = bdev;
 	bio->bi_flags |= (1 << BIO_USER_MAPPED);
-	return bio;
-
- out_unmap:
-	for (i = 0; i < nr_pages; i++) {
-		if(!pages[i])
-			break;
-		page_cache_release(pages[i]);
-	}
- out:
-	kfree(pages);
-	bio_put(bio);
-	return ERR_PTR(ret);
-}
-
-/**
- *	bio_map_user	-	map user address into bio
- *	@q: the struct request_queue for the bio
- *	@bdev: destination block device
- *	@uaddr: start of user address
- *	@len: length in bytes
- *	@write_to_vm: bool indicating writing to pages or not
- *	@gfp_mask: memory allocation flags
- *
- *	Map the user space address into a bio suitable for io to a block
- *	device. Returns an error pointer in case of error.
- */
-struct bio *bio_map_user(struct request_queue *q, struct block_device *bdev,
-			 unsigned long uaddr, unsigned int len, int write_to_vm,
-			 gfp_t gfp_mask)
-{
-	struct sg_iovec iov;
-
-	iov.iov_base = (void __user *)uaddr;
-	iov.iov_len = len;
-
-	return bio_map_user_iov(q, bdev, &iov, 1, write_to_vm, gfp_mask);
-}
-EXPORT_SYMBOL(bio_map_user);
-
-/**
- *	bio_map_user_iov - map user sg_iovec table into bio
- *	@q: the struct request_queue for the bio
- *	@bdev: destination block device
- *	@iov:	the iovec.
- *	@iov_count: number of elements in the iovec
- *	@write_to_vm: bool indicating writing to pages or not
- *	@gfp_mask: memory allocation flags
- *
- *	Map the user space address into a bio suitable for io to a block
- *	device. Returns an error pointer in case of error.
- */
-struct bio *bio_map_user_iov(struct request_queue *q, struct block_device *bdev,
-			     const struct sg_iovec *iov, int iov_count,
-			     int write_to_vm, gfp_t gfp_mask)
-{
-	struct bio *bio;
-
-	bio = __bio_map_user_iov(q, bdev, iov, iov_count, write_to_vm,
-				 gfp_mask);
-	if (IS_ERR(bio))
-		return bio;
 
 	/*
 	 * subtle -- if __bio_map_user() ended up bouncing a bio,
···
 	 * reference to it
 	 */
 	bio_get(bio);
-
 	return bio;
+
+ out_unmap:
+	for (j = 0; j < nr_pages; j++) {
+		if (!pages[j])
+			break;
+		page_cache_release(pages[j]);
+	}
+ out:
+	kfree(pages);
+	bio_put(bio);
+	return ERR_PTR(ret);
 }
 
 static void __bio_unmap_user(struct bio *bio)
···
 	bio_put(bio);
 }
 
-static struct bio *__bio_map_kern(struct request_queue *q, void *data,
-				  unsigned int len, gfp_t gfp_mask)
+/**
+ *	bio_map_kern	-	map kernel address into bio
+ *	@q: the struct request_queue for the bio
+ *	@data: pointer to buffer to map
+ *	@len: length in bytes
+ *	@gfp_mask: allocation flags for bio allocation
+ *
+ *	Map the kernel address into a bio suitable for io to a block
+ *	device. Returns an error pointer in case of error.
+ */
+struct bio *bio_map_kern(struct request_queue *q, void *data, unsigned int len,
+			 gfp_t gfp_mask)
 {
 	unsigned long kaddr = (unsigned long)data;
 	unsigned long end = (kaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
···
 			bytes = len;
 
 		if (bio_add_pc_page(q, bio, virt_to_page(data), bytes,
-				    offset) < bytes)
-			break;
+				    offset) < bytes) {
+			/* we don't support partial mappings */
+			bio_put(bio);
+			return ERR_PTR(-EINVAL);
+		}
 
 		data += bytes;
 		len -= bytes;
···
 	bio->bi_end_io = bio_map_kern_endio;
 	return bio;
 }
-
-/**
- *	bio_map_kern	-	map kernel address into bio
- *	@q: the struct request_queue for the bio
- *	@data: pointer to buffer to map
- *	@len: length in bytes
- *	@gfp_mask: allocation flags for bio allocation
- *
- *	Map the kernel address into a bio suitable for io to a block
- *	device. Returns an error pointer in case of error.
- */
-struct bio *bio_map_kern(struct request_queue *q, void *data, unsigned int len,
-			 gfp_t gfp_mask)
-{
-	struct bio *bio;
-
-	bio = __bio_map_kern(q, data, len, gfp_mask);
-	if (IS_ERR(bio))
-		return bio;
-
-	if (bio->bi_iter.bi_size == len)
-		return bio;
-
-	/*
-	 * Don't support partial mappings.
-	 */
-	bio_put(bio);
-	return ERR_PTR(-EINVAL);
-}
 EXPORT_SYMBOL(bio_map_kern);
 
 static void bio_copy_kern_endio(struct bio *bio, int err)
 {
+	bio_free_pages(bio);
+	bio_put(bio);
+}
+
+static void bio_copy_kern_endio_read(struct bio *bio, int err)
+{
+	char *p = bio->bi_private;
 	struct bio_vec *bvec;
-	const int read = bio_data_dir(bio) == READ;
-	struct bio_map_data *bmd = bio->bi_private;
 	int i;
-	char *p = bmd->sgvecs[0].iov_base;
 
 	bio_for_each_segment_all(bvec, bio, i) {
-		char *addr = page_address(bvec->bv_page);
-
-		if (read)
-			memcpy(p, addr, bvec->bv_len);
-
-		__free_page(bvec->bv_page);
+		memcpy(p, page_address(bvec->bv_page), bvec->bv_len);
 		p += bvec->bv_len;
 	}
 
-	kfree(bmd);
-	bio_put(bio);
+	bio_copy_kern_endio(bio, err);
 }
 
 /**
···
 struct bio *bio_copy_kern(struct request_queue *q, void *data, unsigned int len,
 			  gfp_t gfp_mask, int reading)
 {
+	unsigned long kaddr = (unsigned long)data;
+	unsigned long end = (kaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	unsigned long start = kaddr >> PAGE_SHIFT;
 	struct bio *bio;
-	struct bio_vec *bvec;
-	int i;
+	void *p = data;
+	int nr_pages = 0;
 
-	bio = bio_copy_user(q, NULL, (unsigned long)data, len, 1, gfp_mask);
-	if (IS_ERR(bio))
-		return bio;
+	/*
+	 * Overflow, abort
+	 */
+	if (end < start)
+		return ERR_PTR(-EINVAL);
 
-	if (!reading) {
-		void *p = data;
+	nr_pages = end - start;
+	bio = bio_kmalloc(gfp_mask, nr_pages);
+	if (!bio)
+		return ERR_PTR(-ENOMEM);
 
-		bio_for_each_segment_all(bvec, bio, i) {
-			char *addr = page_address(bvec->bv_page);
+	while (len) {
+		struct page *page;
+		unsigned int bytes = PAGE_SIZE;
 
-			memcpy(addr, p, bvec->bv_len);
-			p += bvec->bv_len;
-		}
+		if (bytes > len)
+			bytes = len;
+
+		page = alloc_page(q->bounce_gfp | gfp_mask);
+		if (!page)
+			goto cleanup;
+
+		if (!reading)
+			memcpy(page_address(page), p, bytes);
+
+		if (bio_add_pc_page(q, bio, page, bytes, 0) < bytes)
+			break;
+
+		len -= bytes;
+		p += bytes;
 	}
 
-	bio->bi_end_io = bio_copy_kern_endio;
+	if (reading) {
+		bio->bi_end_io = bio_copy_kern_endio_read;
+		bio->bi_private = data;
+	} else {
+		bio->bi_end_io = bio_copy_kern_endio;
+		bio->bi_rw |= REQ_WRITE;
+	}
 
 	return bio;
+
+cleanup:
+	bio_free_pages(bio);
+	bio_put(bio);
+	return ERR_PTR(-ENOMEM);
 }
 EXPORT_SYMBOL(bio_copy_kern);
 

block/blk-core.c

···
 	    should_fail_request(&rq->rq_disk->part0, blk_rq_bytes(rq)))
 		return -EIO;
 
+	if (q->mq_ops) {
+		if (blk_queue_io_stat(q))
+			blk_account_io_start(rq, true);
+		blk_mq_insert_request(rq, false, true, true);
+		return 0;
+	}
+
 	spin_lock_irqsave(q->queue_lock, flags);
 	if (unlikely(blk_queue_dying(q))) {
 		spin_unlock_irqrestore(q->queue_lock, flags);
···
 static void __blk_rq_prep_clone(struct request *dst, struct request *src)
 {
 	dst->cpu = src->cpu;
-	dst->cmd_flags = (src->cmd_flags & REQ_CLONE_MASK) | REQ_NOMERGE;
+	dst->cmd_flags |= (src->cmd_flags & REQ_CLONE_MASK) | REQ_NOMERGE;
 	dst->cmd_type = src->cmd_type;
 	dst->__sector = blk_rq_pos(src);
 	dst->__data_len = blk_rq_bytes(src);
···
 
 	if (!bs)
 		bs = fs_bio_set;
-
-	blk_rq_init(NULL, rq);
 
 	__rq_for_each_bio(bio_src, rq_src) {
 		bio = bio_clone_fast(bio_src, gfp_mask, bs);

block/blk-lib.c

···
  * @sector:	start sector
  * @nr_sects:	number of sectors to write
  * @gfp_mask:	memory allocation flags (for bio_alloc)
+ * @discard:	whether to discard the block range
  *
  * Description:
- *  Generate and issue number of bios with zerofiled pages.
+ *  Zero-fill a block range.  If the discard flag is set and the block
+ *  device guarantees that subsequent READ operations to the block range
+ *  in question will return zeroes, the blocks will be discarded. Should
+ *  the discard request fail, if the discard flag is not set, or if
+ *  discard_zeroes_data is not supported, this function will resort to
+ *  zeroing the blocks manually, thus provisioning (allocating,
+ *  anchoring) them. If the block device supports the WRITE SAME command
+ *  blkdev_issue_zeroout() will use it to optimize the process of
+ *  clearing the block range. Otherwise the zeroing will be performed
+ *  using regular WRITE calls.
  */
 
 int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
-			 sector_t nr_sects, gfp_t gfp_mask)
+			 sector_t nr_sects, gfp_t gfp_mask, bool discard)
 {
-	if (bdev_write_same(bdev)) {
-		unsigned char bdn[BDEVNAME_SIZE];
+	struct request_queue *q = bdev_get_queue(bdev);
 
-		if (!blkdev_issue_write_same(bdev, sector, nr_sects, gfp_mask,
-					     ZERO_PAGE(0)))
-			return 0;
+	if (discard && blk_queue_discard(q) && q->limits.discard_zeroes_data &&
+	    blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask, 0) == 0)
+		return 0;
 
-		bdevname(bdev, bdn);
-		pr_err("%s: WRITE SAME failed. Manually zeroing.\n", bdn);
-	}
+	if (bdev_write_same(bdev) &&
+	    blkdev_issue_write_same(bdev, sector, nr_sects, gfp_mask,
+				    ZERO_PAGE(0)) == 0)
+		return 0;
 
 	return __blkdev_issue_zeroout(bdev, sector, nr_sects, gfp_mask);
 }

block/blk-map.c

···
 #include <linux/module.h>
 #include <linux/bio.h>
 #include <linux/blkdev.h>
-#include <scsi/sg.h>		/* for struct sg_iovec */
+#include <linux/uio.h>
 
 #include "blk.h"
 
···
 	return ret;
 }
 
-static int __blk_rq_map_user(struct request_queue *q, struct request *rq,
-			     struct rq_map_data *map_data, void __user *ubuf,
-			     unsigned int len, gfp_t gfp_mask)
-{
-	unsigned long uaddr;
-	struct bio *bio, *orig_bio;
-	int reading, ret;
-
-	reading = rq_data_dir(rq) == READ;
-
-	/*
-	 * if alignment requirement is satisfied, map in user pages for
-	 * direct dma. else, set up kernel bounce buffers
-	 */
-	uaddr = (unsigned long) ubuf;
-	if (blk_rq_aligned(q, uaddr, len) && !map_data)
-		bio = bio_map_user(q, NULL, uaddr, len, reading, gfp_mask);
-	else
-		bio = bio_copy_user(q, map_data, uaddr, len, reading, gfp_mask);
-
-	if (IS_ERR(bio))
-		return PTR_ERR(bio);
-
-	if (map_data && map_data->null_mapped)
-		bio->bi_flags |= (1 << BIO_NULL_MAPPED);
-
-	orig_bio = bio;
-	blk_queue_bounce(q, &bio);
-
-	/*
-	 * We link the bounce buffer in and could have to traverse it
-	 * later so we have to get a ref to prevent it from being freed
-	 */
-	bio_get(bio);
-
-	ret = blk_rq_append_bio(q, rq, bio);
-	if (!ret)
-		return bio->bi_iter.bi_size;
-
-	/* if it was boucned we must call the end io function */
-	bio_endio(bio, 0);
-	__blk_rq_unmap_user(orig_bio);
-	bio_put(bio);
-	return ret;
-}
-
-/**
- * blk_rq_map_user - map user data to a request, for REQ_TYPE_BLOCK_PC usage
- * @q:		request queue where request should be inserted
- * @rq:		request structure to fill
- * @map_data:   pointer to the rq_map_data holding pages (if necessary)
- * @ubuf:	the user buffer
- * @len:	length of user data
- * @gfp_mask:	memory allocation flags
- *
- * Description:
- *    Data will be mapped directly for zero copy I/O, if possible. Otherwise
- *    a kernel bounce buffer is used.
- *
- *    A matching blk_rq_unmap_user() must be issued at the end of I/O, while
- *    still in process context.
- *
- *    Note: The mapped bio may need to be bounced through blk_queue_bounce()
- *    before being submitted to the device, as pages mapped may be out of
- *    reach. It's the callers responsibility to make sure this happens. The
- *    original bio must be passed back in to blk_rq_unmap_user() for proper
- *    unmapping.
- */
-int blk_rq_map_user(struct request_queue *q, struct request *rq,
-		    struct rq_map_data *map_data, void __user *ubuf,
-		    unsigned long len, gfp_t gfp_mask)
-{
-	unsigned long bytes_read = 0;
-	struct bio *bio = NULL;
-	int ret;
-
-	if (len > (queue_max_hw_sectors(q) << 9))
-		return -EINVAL;
-	if (!len)
-		return -EINVAL;
-
-	if (!ubuf && (!map_data || !map_data->null_mapped))
-		return -EINVAL;
-
-	while (bytes_read != len) {
-		unsigned long map_len, end, start;
-
-		map_len = min_t(unsigned long, len - bytes_read, BIO_MAX_SIZE);
-		end = ((unsigned long)ubuf + map_len + PAGE_SIZE - 1)
-								>> PAGE_SHIFT;
-		start = (unsigned long)ubuf >> PAGE_SHIFT;
-
-		/*
-		 * A bad offset could cause us to require BIO_MAX_PAGES + 1
-		 * pages. If this happens we just lower the requested
-		 * mapping len by a page so that we can fit
-		 */
-		if (end - start > BIO_MAX_PAGES)
-			map_len -= PAGE_SIZE;
-
-		ret = __blk_rq_map_user(q, rq, map_data, ubuf, map_len,
-					gfp_mask);
-		if (ret < 0)
-			goto unmap_rq;
-		if (!bio)
-			bio = rq->bio;
-		bytes_read += ret;
-		ubuf += ret;
-
-		if (map_data)
-			map_data->offset += ret;
-	}
-
-	if (!bio_flagged(bio, BIO_USER_MAPPED))
-		rq->cmd_flags |= REQ_COPY_USER;
-
-	return 0;
-unmap_rq:
-	blk_rq_unmap_user(bio);
-	rq->bio = NULL;
-	return ret;
-}
-EXPORT_SYMBOL(blk_rq_map_user);
-
 /**
  * blk_rq_map_user_iov - map user data to a request, for REQ_TYPE_BLOCK_PC usage
  * @q:		request queue where request should be inserted
  * @rq:		request to map data to
  * @map_data:   pointer to the rq_map_data holding pages (if necessary)
- * @iov:	pointer to the iovec
- * @iov_count:	number of elements in the iovec
- * @len:	I/O byte count
+ * @iter:	iovec iterator
  * @gfp_mask:	memory allocation flags
  *
  * Description:
···
  *    unmapping.
  */
 int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
-			struct rq_map_data *map_data, const struct sg_iovec *iov,
-			int iov_count, unsigned int len, gfp_t gfp_mask)
+			struct rq_map_data *map_data,
+			const struct iov_iter *iter, gfp_t gfp_mask)
 {
 	struct bio *bio;
-	int i, read = rq_data_dir(rq) == READ;
 	int unaligned = 0;
+	struct iov_iter i;
+	struct iovec iov;
 
-	if (!iov || iov_count <= 0)
+	if (!iter || !iter->count)
 		return -EINVAL;
 
-	for (i = 0; i < iov_count; i++) {
-		unsigned long uaddr = (unsigned long)iov[i].iov_base;
+	iov_for_each(iov, i, *iter) {
+		unsigned long uaddr = (unsigned long) iov.iov_base;
 
-		if (!iov[i].iov_len)
+		if (!iov.iov_len)
 			return -EINVAL;
 
 		/*
···
 			unaligned = 1;
 	}
 
-	if (unaligned || (q->dma_pad_mask & len) || map_data)
-		bio = bio_copy_user_iov(q, map_data, iov, iov_count, read,
-					gfp_mask);
+	if (unaligned || (q->dma_pad_mask & iter->count) || map_data)
+		bio = bio_copy_user_iov(q, map_data, iter, gfp_mask);
 	else
-		bio = bio_map_user_iov(q, NULL, iov, iov_count, read, gfp_mask);
+		bio = bio_map_user_iov(q, iter, gfp_mask);
 
 	if (IS_ERR(bio))
 		return PTR_ERR(bio);
 
-	if (bio->bi_iter.bi_size != len) {
+	if (map_data && map_data->null_mapped)
+		bio->bi_flags |= (1 << BIO_NULL_MAPPED);
+
+	if (bio->bi_iter.bi_size != iter->count) {
 		/*
 		 * Grab an extra reference to this bio, as bio_unmap_user()
 		 * expects to be able to drop it twice as it happens on the
···
 	return 0;
 }
 EXPORT_SYMBOL(blk_rq_map_user_iov);
+
+int blk_rq_map_user(struct request_queue *q, struct request *rq,
+		    struct rq_map_data *map_data, void __user *ubuf,
+		    unsigned long len, gfp_t gfp_mask)
+{
+	struct iovec iov;
+	struct iov_iter i;
+
+	iov.iov_base = ubuf;
+	iov.iov_len = len;
+	iov_iter_init(&i, rq_data_dir(rq), &iov, 1, len);
+
+	return blk_rq_map_user_iov(q, rq, map_data, &i, gfp_mask);
+}
+EXPORT_SYMBOL(blk_rq_map_user);
 
 /**
  * blk_rq_unmap_user - unmap a request with user data

block/blk-merge.c

···
 }
 EXPORT_SYMBOL(blk_rq_map_sg);
 
-/**
- * blk_bio_map_sg - map a bio to a scatterlist
- * @q: request_queue in question
- * @bio: bio being mapped
- * @sglist: scatterlist being mapped
- *
- * Note:
- *    Caller must make sure sg can hold bio->bi_phys_segments entries
- *
- * Will return the number of sg entries setup
- */
-int blk_bio_map_sg(struct request_queue *q, struct bio *bio,
-		   struct scatterlist *sglist)
-{
-	struct scatterlist *sg = NULL;
-	int nsegs;
-	struct bio *next = bio->bi_next;
-	bio->bi_next = NULL;
-
-	nsegs = __blk_bios_map_sg(q, bio, sglist, &sg);
-	bio->bi_next = next;
-	if (sg)
-		sg_mark_end(sg);
-
-	BUG_ON(bio->bi_phys_segments && nsegs > bio->bi_phys_segments);
-	return nsegs;
-}
-EXPORT_SYMBOL(blk_bio_map_sg);
-
 static inline int ll_new_hw_segment(struct request_queue *q,
 				    struct request *req,
 				    struct bio *bio)
···
 	return !q->mq_ops && req->special;
 }
 
+static int req_gap_to_prev(struct request *req, struct request *next)
+{
+	struct bio *prev = req->biotail;
+
+	return bvec_gap_to_prev(&prev->bi_io_vec[prev->bi_vcnt - 1],
+				next->bio->bi_io_vec[0].bv_offset);
+}
+
 static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
 				struct request *next)
 {
···
 	 * requests.  Can't merge them if they are.
 	 */
 	if (req_no_special_merge(req) || req_no_special_merge(next))
+		return 0;
+
+	if (test_bit(QUEUE_FLAG_SG_GAPS, &q->queue_flags) &&
+	    req_gap_to_prev(req, next))
 		return 0;
 
 	/*

block/blk-mq-tag.c

···
 	return atomic_read(&hctx->nr_active) < depth;
 }
 
-static int __bt_get_word(struct blk_align_bitmap *bm, unsigned int last_tag)
+static int __bt_get_word(struct blk_align_bitmap *bm, unsigned int last_tag,
+			 bool nowrap)
 {
-	int tag, org_last_tag, end;
-	bool wrap = last_tag != 0;
+	int tag, org_last_tag = last_tag;
 
-	org_last_tag = last_tag;
-	end = bm->depth;
-	do {
-restart:
-		tag = find_next_zero_bit(&bm->word, end, last_tag);
-		if (unlikely(tag >= end)) {
+	while (1) {
+		tag = find_next_zero_bit(&bm->word, bm->depth, last_tag);
+		if (unlikely(tag >= bm->depth)) {
 			/*
-			 * We started with an offset, start from 0 to
+			 * We started with an offset, and we didn't reset the
+			 * offset to 0 in a failure case, so start from 0 to
 			 * exhaust the map.
 			 */
-			if (wrap) {
-				wrap = false;
-				end = org_last_tag;
-				last_tag = 0;
-				goto restart;
+			if (org_last_tag && last_tag && !nowrap) {
+				last_tag = org_last_tag = 0;
+				continue;
 			}
 			return -1;
 		}
+
+		if (!test_and_set_bit(tag, &bm->word))
+			break;
+
 		last_tag = tag + 1;
-	} while (test_and_set_bit(tag, &bm->word));
+		if (last_tag >= bm->depth - 1)
+			last_tag = 0;
+	}
 
 	return tag;
 }
+
+#define BT_ALLOC_RR(tags) (tags->alloc_policy == BLK_TAG_ALLOC_RR)
 
 /*
  * Straight forward bitmap tag implementation, where each bit is a tag
···
  * until the map is exhausted.
  */
 static int __bt_get(struct blk_mq_hw_ctx *hctx, struct blk_mq_bitmap_tags *bt,
-		    unsigned int *tag_cache)
+		    unsigned int *tag_cache, struct blk_mq_tags *tags)
 {
 	unsigned int last_tag, org_last_tag;
 	int index, i, tag;
···
 	index = TAG_TO_INDEX(bt, last_tag);
 
 	for (i = 0; i < bt->map_nr; i++) {
-		tag = __bt_get_word(&bt->map[index], TAG_TO_BIT(bt, last_tag));
+		tag = __bt_get_word(&bt->map[index], TAG_TO_BIT(bt, last_tag),
+				    BT_ALLOC_RR(tags));
 		if (tag != -1) {
 			tag += (index << bt->bits_per_word);
 			goto done;
 		}
 
-		last_tag = 0;
-		if (++index >= bt->map_nr)
+		/*
+		 * Jump to next index, and reset the last tag to be the
+		 * first tag of that index
+		 */
+		index++;
+		last_tag = (index << bt->bits_per_word);
+
+		if (index >= bt->map_nr) {
 			index = 0;
+			last_tag = 0;
+		}
 	}
 
 	*tag_cache = 0;
···
 	 * up using the specific cached tag.
 	 */
 done:
-	if (tag == org_last_tag) {
+	if (tag == org_last_tag || unlikely(BT_ALLOC_RR(tags))) {
 		last_tag = tag + 1;
 		if (last_tag >= bt->depth - 1)
 			last_tag = 0;
···
 static int bt_get(struct blk_mq_alloc_data *data,
 		struct blk_mq_bitmap_tags *bt,
 		struct blk_mq_hw_ctx *hctx,
-		unsigned int *last_tag)
+		unsigned int *last_tag, struct blk_mq_tags *tags)
 {
 	struct bt_wait_state *bs;
 	DEFINE_WAIT(wait);
 	int tag;
 
-	tag = __bt_get(hctx, bt, last_tag);
+	tag = __bt_get(hctx, bt, last_tag, tags);
 	if (tag != -1)
 		return tag;
 
···
 	do {
 		prepare_to_wait(&bs->wait, &wait, TASK_UNINTERRUPTIBLE);
 
-		tag = __bt_get(hctx, bt, last_tag);
+		tag = __bt_get(hctx, bt, last_tag, tags);
 		if (tag != -1)
 			break;
 
···
 		 * Retry tag allocation after running the hardware queue,
 		 * as running the queue may also have found completions.
 		 */
-		tag = __bt_get(hctx, bt, last_tag);
+		tag = __bt_get(hctx, bt, last_tag, tags);
 		if (tag != -1)
 			break;
 
···
 	int tag;
 
 	tag = bt_get(data, &data->hctx->tags->bitmap_tags, data->hctx,
-			&data->ctx->last_tag);
+			&data->ctx->last_tag, data->hctx->tags);
 	if (tag >= 0)
 		return tag + data->hctx->tags->nr_reserved_tags;
 
···
 		return BLK_MQ_TAG_FAIL;
 	}
 
-	tag = bt_get(data, &data->hctx->tags->breserved_tags, NULL, &zero);
+	tag = bt_get(data, &data->hctx->tags->breserved_tags, NULL, &zero,
+		data->hctx->tags);
 	if (tag < 0)
 		return BLK_MQ_TAG_FAIL;
 
···
 
 		BUG_ON(real_tag >= tags->nr_tags);
 		bt_clear_tag(&tags->bitmap_tags, real_tag);
-		*last_tag = real_tag;
+		if (likely(tags->alloc_policy == BLK_TAG_ALLOC_FIFO))
+			*last_tag = real_tag;
 	} else {
 		BUG_ON(tag >= tags->nr_reserved_tags);
 		bt_clear_tag(&tags->breserved_tags, tag);
···
 	bt->bs = kzalloc(BT_WAIT_QUEUES * sizeof(*bt->bs), GFP_KERNEL);
 	if (!bt->bs) {
 		kfree(bt->map);
+		bt->map = NULL;
 		return -ENOMEM;
 	}
 
···
 }
 
 static struct blk_mq_tags *blk_mq_init_bitmap_tags(struct blk_mq_tags *tags,
-						   int node)
+						   int node, int alloc_policy)
 {
 	unsigned int depth = tags->nr_tags - tags->nr_reserved_tags;
+
+	tags->alloc_policy = alloc_policy;
 
 	if (bt_alloc(&tags->bitmap_tags, depth, node, false))
 		goto enomem;
···
 }
 
 struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags,
-				     unsigned int reserved_tags, int node)
+				     unsigned int reserved_tags,
+				     int node, int alloc_policy)
 {
 	struct blk_mq_tags *tags;
 
···
 	tags->nr_tags = total_tags;
 	tags->nr_reserved_tags = reserved_tags;
 
-	return blk_mq_init_bitmap_tags(tags, node);
+	return blk_mq_init_bitmap_tags(tags, node, alloc_policy);
 }
 
 void blk_mq_free_tags(struct blk_mq_tags *tags)

block/blk-mq-tag.h

···
 
 	struct request **rqs;
 	struct list_head page_list;
+
+	int alloc_policy;
 };
 
 
-extern struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags, unsigned int reserved_tags, int node);
+extern struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags, unsigned int reserved_tags, int node, int alloc_policy);
 extern void blk_mq_free_tags(struct blk_mq_tags *tags);
 
 extern unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data);

block/blk-mq.c

···
 static LIST_HEAD(all_q_list);
 
 static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx);
+static void blk_mq_run_queues(struct request_queue *q);
 
 /*
  * Check if any of the ctx's have pending work in this hardware queue
···
 
 	if (freeze) {
 		percpu_ref_kill(&q->mq_usage_counter);
-		blk_mq_run_queues(q, false);
+		blk_mq_run_queues(q);
 	}
 }
 EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_start);
···
 	blk_mq_freeze_queue_start(q);
 	blk_mq_freeze_queue_wait(q);
 }
+EXPORT_SYMBOL_GPL(blk_mq_freeze_queue);
 
 void blk_mq_unfreeze_queue(struct request_queue *q)
 {
···
 			&hctx->run_work, 0);
 }
 
-void blk_mq_run_queues(struct request_queue *q, bool async)
+static void blk_mq_run_queues(struct request_queue *q)
 {
 	struct blk_mq_hw_ctx *hctx;
 	int i;
···
 		    test_bit(BLK_MQ_S_STOPPED, &hctx->state))
 			continue;
 
-		blk_mq_run_hw_queue(hctx, async);
+		blk_mq_run_hw_queue(hctx, false);
 	}
 }
-EXPORT_SYMBOL(blk_mq_run_queues);
 
 void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx)
 {
···
 		blk_mq_start_hw_queue(hctx);
 }
 EXPORT_SYMBOL(blk_mq_start_hw_queues);
-
 
 void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async)
 {
···
 	size_t rq_size, left;
 
 	tags = blk_mq_init_tags(set->queue_depth, set->reserved_tags,
-				set->numa_node);
+				set->numa_node,
+				BLK_MQ_FLAG_TO_ALLOC_POLICY(set->flags));
 	if (!tags)
 		return NULL;
 

block/blk-tag.c

···
 }
 
 static struct blk_queue_tag *__blk_queue_init_tags(struct request_queue *q,
-						   int depth)
+						int depth, int alloc_policy)
 {
 	struct blk_queue_tag *tags;
 
···
 		goto fail;
 
 	atomic_set(&tags->refcnt, 1);
+	tags->alloc_policy = alloc_policy;
+	tags->next_tag = 0;
 	return tags;
 fail:
 	kfree(tags);
···
 /**
  * blk_init_tags - initialize the tag info for an external tag map
  * @depth:	the maximum queue depth supported
+ * @alloc_policy: tag allocation policy
  **/
-struct blk_queue_tag *blk_init_tags(int depth)
+struct blk_queue_tag *blk_init_tags(int depth, int alloc_policy)
 {
-	return __blk_queue_init_tags(NULL, depth);
+	return __blk_queue_init_tags(NULL, depth, alloc_policy);
 }
 EXPORT_SYMBOL(blk_init_tags);
 
···
  * @q:  the request queue for the device
  * @depth:  the maximum queue depth supported
  * @tags: the tag to use
+ * @alloc_policy: tag allocation policy
  *
  * Queue lock must be held here if the function is called to resize an
  * existing map.
  **/
 int blk_queue_init_tags(struct request_queue *q, int depth,
-			struct blk_queue_tag *tags)
+			struct blk_queue_tag *tags, int alloc_policy)
 {
 	int rc;
 
 	BUG_ON(tags && q->queue_tags && tags != q->queue_tags);
 
 	if (!tags && !q->queue_tags) {
-		tags = __blk_queue_init_tags(q, depth);
+		tags = __blk_queue_init_tags(q, depth, alloc_policy);
 
 		if (!tags)
 			return -ENOMEM;
···
 	}
 
 	do {
-		tag = find_first_zero_bit(bqt->tag_map, max_depth);
-		if (tag >= max_depth)
-			return 1;
+		if (bqt->alloc_policy == BLK_TAG_ALLOC_FIFO) {
+			tag = find_first_zero_bit(bqt->tag_map, max_depth);
+			if (tag >= max_depth)
+				return 1;
+		} else {
+			int start = bqt->next_tag;
+			int size = min_t(int, bqt->max_depth, max_depth + start);
+			tag = find_next_zero_bit(bqt->tag_map, size, start);
+			if (tag >= size && start + size > bqt->max_depth) {
+				size = start + size - bqt->max_depth;
+				tag = find_first_zero_bit(bqt->tag_map, size);
+			}
+			if (tag >= size)
+				return 1;
+		}
 
 	} while (test_and_set_bit_lock(tag, bqt->tag_map));
 	/*
···
 	 * See blk_queue_end_tag for details.
 	 */
 
+	bqt->next_tag = (tag + 1) % bqt->max_depth;
 	rq->cmd_flags |= REQ_QUEUED;
 	rq->tag = tag;
 	bqt->tag_index[tag] = rq;

block/cfq-iosched.c

···
 
 	blkcg = bio_blkcg(bio);
 	cfqg = cfq_lookup_create_cfqg(cfqd, blkcg);
+	if (!cfqg) {
+		cfqq = &cfqd->oom_cfqq;
+		goto out;
+	}
+
 	cfqq = cic_to_cfqq(cic, is_sync);
 
 	/*
···
 		} else
 			cfqq = &cfqd->oom_cfqq;
 	}
-
+out:
 	if (new_cfqq)
 		kmem_cache_free(cfq_pool, new_cfqq);
 
···
 cfq_get_queue(struct cfq_data *cfqd, bool is_sync, struct cfq_io_cq *cic,
 	      struct bio *bio, gfp_t gfp_mask)
 {
-	const int ioprio_class = IOPRIO_PRIO_CLASS(cic->ioprio);
-	const int ioprio = IOPRIO_PRIO_DATA(cic->ioprio);
+	int ioprio_class = IOPRIO_PRIO_CLASS(cic->ioprio);
+	int ioprio = IOPRIO_PRIO_DATA(cic->ioprio);
 	struct cfq_queue **async_cfqq = NULL;
 	struct cfq_queue *cfqq = NULL;
 
 	if (!is_sync) {
+		if (!ioprio_valid(cic->ioprio)) {
+			struct task_struct *tsk = current;
+			ioprio = task_nice_ioprio(tsk);
+			ioprio_class = task_nice_ioclass(tsk);
+		}
 		async_cfqq = cfq_async_queue_prio(cfqd, ioprio_class, ioprio);
 		cfqq = *async_cfqq;
 	}

block/ioctl.c

···
 	if (start + len > (i_size_read(bdev->bd_inode) >> 9))
 		return -EINVAL;
 
-	return blkdev_issue_zeroout(bdev, start, len, GFP_KERNEL);
+	return blkdev_issue_zeroout(bdev, start, len, GFP_KERNEL, false);
 }
 
 static int put_ushort(unsigned long arg, unsigned short val)

block/partitions/check.c

···
 	if (err)
 	/* The partition is unrecognized. So report I/O errors if there were any */
 		res = err;
-	if (!res)
-		strlcat(state->pp_buf, " unknown partition table\n", PAGE_SIZE);
-	else if (warn_no_part)
-		strlcat(state->pp_buf, " unable to read partition table\n", PAGE_SIZE);
-
-	printk(KERN_INFO "%s", state->pp_buf);
+	if (res) {
+		if (warn_no_part)
+			strlcat(state->pp_buf,
+				" unable to read partition table\n", PAGE_SIZE);
+		printk(KERN_INFO "%s", state->pp_buf);
+	}
 
 	free_page((unsigned long)state->pp_buf);
 	free_partitions(state);

block/scsi_ioctl.c

···
 
 	ret = 0;
 	if (hdr->iovec_count) {
-		size_t iov_data_len;
+		struct iov_iter i;
 		struct iovec *iov = NULL;
 
 		ret = rw_copy_check_uvector(-1, hdr->dxferp, hdr->iovec_count,
···
 			goto out_free_cdb;
 		}
 
-		iov_data_len = ret;
-		ret = 0;
-
 		/* SG_IO howto says that the shorter of the two wins */
-		if (hdr->dxfer_len < iov_data_len) {
-			hdr->iovec_count = iov_shorten(iov,
-						       hdr->iovec_count,
-						       hdr->dxfer_len);
-			iov_data_len = hdr->dxfer_len;
-		}
+		iov_iter_init(&i, rq_data_dir(rq), iov, hdr->iovec_count,
+			      min_t(unsigned, ret, hdr->dxfer_len));
 
-		ret = blk_rq_map_user_iov(q, rq, NULL, (struct sg_iovec *) iov,
-					  hdr->iovec_count,
-					  iov_data_len, GFP_KERNEL);
+		ret = blk_rq_map_user_iov(q, rq, NULL, &i, GFP_KERNEL);
 		kfree(iov);
 	} else if (hdr->dxfer_len)
 		ret = blk_rq_map_user(q, rq, NULL, hdr->dxferp, hdr->dxfer_len,

drivers/block/brd.c

···
 }
 
 #ifdef CONFIG_BLK_DEV_XIP
-static int brd_direct_access(struct block_device *bdev, sector_t sector,
-			void **kaddr, unsigned long *pfn)
+static long brd_direct_access(struct block_device *bdev, sector_t sector,
+			void **kaddr, unsigned long *pfn, long size)
 {
 	struct brd_device *brd = bdev->bd_disk->private_data;
 	struct page *page;
 
 	if (!brd)
 		return -ENODEV;
-	if (sector & (PAGE_SECTORS-1))
-		return -EINVAL;
-	if (sector + PAGE_SECTORS > get_capacity(bdev->bd_disk))
-		return -ERANGE;
 	page = brd_insert_page(brd, sector);
 	if (!page)
 		return -ENOSPC;
 	*kaddr = page_address(page);
 	*pfn = page_to_pfn(page);
 
-	return 0;
+	/*
+	 * TODO: If size > PAGE_SIZE, we could look to see if the next page in
+	 * the file happens to be mapped to the next page of physical RAM.
+	 */
+	return PAGE_SIZE;
 }
 #endif
 

drivers/block/drbd/drbd_receiver.c

···
 		list_add_tail(&peer_req->w.list, &device->active_ee);
 		spin_unlock_irq(&device->resource->req_lock);
 		if (blkdev_issue_zeroout(device->ldev->backing_bdev,
-			sector, data_size >> 9, GFP_NOIO))
+			sector, data_size >> 9, GFP_NOIO, false))
 			peer_req->flags |= EE_WAS_ERROR;
 		drbd_endio_write_sec_final(peer_req);
 		return 0;

drivers/block/osdblk.c

···
 	}
 
 	/* switch queue to TCQ mode; allocate tag map */
-	rc = blk_queue_init_tags(q, OSDBLK_MAX_REQ, NULL);
+	rc = blk_queue_init_tags(q, OSDBLK_MAX_REQ, NULL, BLK_TAG_ALLOC_FIFO);
 	if (rc) {
 		blk_cleanup_queue(q);
 		put_disk(disk);

drivers/md/dm.c

···
 {
 	int r;
 
+	blk_rq_init(NULL, clone);
 	r = blk_rq_prep_clone(clone, rq, tio->md->bs, GFP_ATOMIC,
 			      dm_rq_bio_constructor, tio);
 	if (r)

drivers/s390/block/dcssblk.c

···
 static int dcssblk_open(struct block_device *bdev, fmode_t mode);
 static void dcssblk_release(struct gendisk *disk, fmode_t mode);
 static void dcssblk_make_request(struct request_queue *q, struct bio *bio);
-static int dcssblk_direct_access(struct block_device *bdev, sector_t secnum,
-				 void **kaddr, unsigned long *pfn);
+static long dcssblk_direct_access(struct block_device *bdev, sector_t secnum,
+				 void **kaddr, unsigned long *pfn, long size);
 
 static char dcssblk_segments[DCSSBLK_PARM_LEN] = "\0";
 
···
 	bio_io_error(bio);
 }
 
-static int
+static long
 dcssblk_direct_access (struct block_device *bdev, sector_t secnum,
-			void **kaddr, unsigned long *pfn)
+			void **kaddr, unsigned long *pfn, long size)
 {
 	struct dcssblk_dev_info *dev_info;
-	unsigned long pgoff;
+	unsigned long offset, dev_sz;
 
 	dev_info = bdev->bd_disk->private_data;
 	if (!dev_info)
 		return -ENODEV;
-	if (secnum % (PAGE_SIZE/512))
-		return -EINVAL;
-	pgoff = secnum / (PAGE_SIZE / 512);
-	if ((pgoff+1)*PAGE_SIZE-1 > dev_info->end - dev_info->start)
-		return -ERANGE;
-	*kaddr = (void *) (dev_info->start+pgoff*PAGE_SIZE);
+	dev_sz = dev_info->end - dev_info->start;
+	offset = secnum * 512;
+	*kaddr = (void *) (dev_info->start + offset);
 	*pfn = virt_to_phys(*kaddr) >> PAGE_SHIFT;
 
-	return 0;
+	return dev_sz - offset;
 }
 
 static void

drivers/scsi/scsi_lib.c

···
 	shost->tag_set.cmd_size = cmd_size;
 	shost->tag_set.numa_node = NUMA_NO_NODE;
 	shost->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE;
+	shost->tag_set.flags |=
+		BLK_ALLOC_POLICY_TO_MQ_FLAG(shost->hostt->tag_alloc_policy);
 	shost->tag_set.driver_data = shost;
 
 	return blk_mq_alloc_tag_set(&shost->tag_set);

drivers/scsi/scsi_scan.c

···
 	if (!shost_use_blk_mq(sdev->host) &&
 	    (shost->bqt || shost->hostt->use_blk_tags)) {
 		blk_queue_init_tags(sdev->request_queue,
-				    sdev->host->cmd_per_lun, shost->bqt);
+				    sdev->host->cmd_per_lun, shost->bqt,
+				    shost->hostt->tag_alloc_policy);
 	}
 	scsi_change_queue_depth(sdev, sdev->host->cmd_per_lun);
 

drivers/scsi/sg.c

···
 	}
 
 	if (iov_count) {
-		int len, size = sizeof(struct sg_iovec) * iov_count;
+		int size = sizeof(struct iovec) * iov_count;
 		struct iovec *iov;
+		struct iov_iter i;
 
 		iov = memdup_user(hp->dxferp, size);
 		if (IS_ERR(iov))
 			return PTR_ERR(iov);
 
-		len = iov_length(iov, iov_count);
-		if (hp->dxfer_len < len) {
-			iov_count = iov_shorten(iov, iov_count, hp->dxfer_len);
-			len = hp->dxfer_len;
-		}
+		iov_iter_init(&i, rw, iov, iov_count,
+			      min_t(size_t, hp->dxfer_len,
+				    iov_length(iov, iov_count)));
 
-		res = blk_rq_map_user_iov(q, rq, md, (struct sg_iovec *)iov,
-					  iov_count,
-					  len, GFP_ATOMIC);
+		res = blk_rq_map_user_iov(q, rq, md, &i, GFP_ATOMIC);
 		kfree(iov);
 	} else
 		res = blk_rq_map_user(q, rq, md, hp->dxferp,

fs/block_dev.c

···
 }
 EXPORT_SYMBOL_GPL(bdev_write_page);
 
+/**
+ * bdev_direct_access() - Get the address for directly-accessibly memory
+ * @bdev: The device containing the memory
+ * @sector: The offset within the device
+ * @addr: Where to put the address of the memory
+ * @pfn: The Page Frame Number for the memory
+ * @size: The number of bytes requested
+ *
+ * If a block device is made up of directly addressable memory, this function
+ * will tell the caller the PFN and the address of the memory.  The address
+ * may be directly dereferenced within the kernel without the need to call
+ * ioremap(), kmap() or similar.  The PFN is suitable for inserting into
+ * page tables.
+ *
+ * Return: negative errno if an error occurs, otherwise the number of bytes
+ * accessible at this address.
+ */
+long bdev_direct_access(struct block_device *bdev, sector_t sector,
+			void **addr, unsigned long *pfn, long size)
+{
+	long avail;
+	const struct block_device_operations *ops = bdev->bd_disk->fops;
+
+	if (size < 0)
+		return size;
+	if (!ops->direct_access)
+		return -EOPNOTSUPP;
+	if ((sector + DIV_ROUND_UP(size, 512)) >
+					part_nr_sects_read(bdev->bd_part))
+		return -ERANGE;
+	sector += get_start_sect(bdev);
+	if (sector % (PAGE_SIZE / 512))
+		return -EINVAL;
+	avail = ops->direct_access(bdev, sector, addr, pfn, size);
+	if (!avail)
+		return -ERANGE;
+	return min(avail, size);
+}
+EXPORT_SYMBOL_GPL(bdev_direct_access);
+
 /*
  * pseudo-fs
  */

fs/ext2/xip.c

···
 #include "ext2.h"
 #include "xip.h"
 
-static inline int
-__inode_direct_access(struct inode *inode, sector_t block,
-		      void **kaddr, unsigned long *pfn)
+static inline long __inode_direct_access(struct inode *inode, sector_t block,
+				void **kaddr, unsigned long *pfn, long size)
 {
 	struct block_device *bdev = inode->i_sb->s_bdev;
-	const struct block_device_operations *ops = bdev->bd_disk->fops;
-	sector_t sector;
-
-	sector = block * (PAGE_SIZE / 512); /* ext2 block to bdev sector */
-
-	BUG_ON(!ops->direct_access);
-	return ops->direct_access(bdev, sector, kaddr, pfn);
+	sector_t sector = block * (PAGE_SIZE / 512);
+	return bdev_direct_access(bdev, sector, kaddr, pfn, size);
 }
 
 static inline int
···
 {
 	void *kaddr;
 	unsigned long pfn;
-	int rc;
+	long size;
 
-	rc = __inode_direct_access(inode, block, &kaddr, &pfn);
-	if (!rc)
-		clear_page(kaddr);
-	return rc;
+	size = __inode_direct_access(inode, block, &kaddr, &pfn, PAGE_SIZE);
+	if (size < 0)
+		return size;
+	clear_page(kaddr);
+	return 0;
 }
 
 void ext2_xip_verify_sb(struct super_block *sb)
···
 int ext2_get_xip_mem(struct address_space *mapping, pgoff_t pgoff, int create,
 				void **kmem, unsigned long *pfn)
 {
-	int rc;
+	long rc;
 	sector_t block;
 
 	/* first, retrieve the sector number */
···
 		return rc;
 
 	/* retrieve address of the target data */
-	rc = __inode_direct_access(mapping->host, block, kmem, pfn);
-	return rc;
+	rc = __inode_direct_access(mapping->host, block, kmem, pfn, PAGE_SIZE);
+	return (rc < 0) ? rc : 0;
 }

include/linux/bio.h

···
 extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *,
 			   unsigned int, unsigned int);
 extern int bio_get_nr_vecs(struct block_device *);
-extern struct bio *bio_map_user(struct request_queue *, struct block_device *,
-				unsigned long, unsigned int, int, gfp_t);
-struct sg_iovec;
 struct rq_map_data;
 extern struct bio *bio_map_user_iov(struct request_queue *,
-				    struct block_device *,
-				    const struct sg_iovec *, int, int, gfp_t);
+				    const struct iov_iter *, gfp_t);
 extern void bio_unmap_user(struct bio *);
 extern struct bio *bio_map_kern(struct request_queue *, void *, unsigned int,
 				gfp_t);
···
 extern void bio_copy_data(struct bio *dst, struct bio *src);
 extern int bio_alloc_pages(struct bio *bio, gfp_t gfp);
 
-extern struct bio *bio_copy_user(struct request_queue *, struct rq_map_data *,
-				 unsigned long, unsigned int, int, gfp_t);
 extern struct bio *bio_copy_user_iov(struct request_queue *,
 				     struct rq_map_data *,
-				     const struct sg_iovec *,
-				     int, int, gfp_t);
+				     const struct iov_iter *,
+				     gfp_t);
 extern int bio_uncopy_user(struct bio *);
 void zero_fill_bio(struct bio *bio);
 extern struct bio_vec *bvec_alloc(gfp_t, int, unsigned long *, mempool_t *);

include/linux/blk-mq.h

···
 	BLK_MQ_F_SG_MERGE	= 1 << 2,
 	BLK_MQ_F_SYSFS_UP	= 1 << 3,
 	BLK_MQ_F_DEFER_ISSUE	= 1 << 4,
+	BLK_MQ_F_ALLOC_POLICY_START_BIT = 8,
+	BLK_MQ_F_ALLOC_POLICY_BITS = 1,
 
 	BLK_MQ_S_STOPPED	= 0,
 	BLK_MQ_S_TAG_ACTIVE	= 1,
···
 
 	BLK_MQ_CPU_WORK_BATCH	= 8,
 };
+#define BLK_MQ_FLAG_TO_ALLOC_POLICY(flags) \
+	((flags >> BLK_MQ_F_ALLOC_POLICY_START_BIT) & \
+		((1 << BLK_MQ_F_ALLOC_POLICY_BITS) - 1))
+#define BLK_ALLOC_POLICY_TO_MQ_FLAG(policy) \
+	((policy & ((1 << BLK_MQ_F_ALLOC_POLICY_BITS) - 1)) \
+		<< BLK_MQ_F_ALLOC_POLICY_START_BIT)
 
 struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *);
 void blk_mq_finish_init(struct request_queue *q);
···
 void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule);
 
 void blk_mq_insert_request(struct request *, bool, bool, bool);
-void blk_mq_run_queues(struct request_queue *q, bool async);
 void blk_mq_free_request(struct request *rq);
 void blk_mq_free_hctx_request(struct blk_mq_hw_ctx *, struct request *rq);
 bool blk_mq_can_queue(struct blk_mq_hw_ctx *);
···
 void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs);
 void blk_mq_tag_busy_iter(struct blk_mq_hw_ctx *hctx, busy_iter_fn *fn,
 		void *priv);
+void blk_mq_freeze_queue(struct request_queue *q);
 void blk_mq_unfreeze_queue(struct request_queue *q);
 void blk_mq_freeze_queue_start(struct request_queue *q);
 

include/linux/blkdev.h

···
 	int max_depth;			/* what we will send to device */
 	int real_max_depth;		/* what the array can hold */
 	atomic_t refcnt;		/* map can be shared */
+	int alloc_policy;		/* tag allocation policy */
+	int next_tag;			/* next tag */
 };
+#define BLK_TAG_ALLOC_FIFO 0 /* allocate starting from 0 */
+#define BLK_TAG_ALLOC_RR 1 /* allocate starting from last allocated tag */
 
 #define BLK_SCSI_MAX_CMDS	(256)
 #define BLK_SCSI_CMD_PER_LONG	(BLK_SCSI_MAX_CMDS / (sizeof(long) * 8))
···
 				 (1 << QUEUE_FLAG_ADD_RANDOM))
 
 #define QUEUE_FLAG_MQ_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
+				 (1 << QUEUE_FLAG_STACKABLE)	|	\
 				 (1 << QUEUE_FLAG_SAME_COMP))
 
 static inline void queue_lockdep_assert_held(struct request_queue *q)
···
 extern int blk_rq_unmap_user(struct bio *);
 extern int blk_rq_map_kern(struct request_queue *, struct request *, void *, unsigned int, gfp_t);
 extern int blk_rq_map_user_iov(struct request_queue *, struct request *,
-			       struct rq_map_data *, const struct sg_iovec *,
-			       int, unsigned int, gfp_t);
+			       struct rq_map_data *, const struct iov_iter *,
+			       gfp_t);
 extern int blk_execute_rq(struct request_queue *, struct gendisk *,
 			  struct request *, int);
 extern void blk_execute_rq_nowait(struct request_queue *, struct gendisk *,
···
 extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev);
 
 extern int blk_rq_map_sg(struct request_queue *, struct request *, struct scatterlist *);
-extern int blk_bio_map_sg(struct request_queue *q, struct bio *bio,
-			  struct scatterlist *sglist);
 extern void blk_dump_rq_flags(struct request *, char *);
 extern long nr_blockdev_pages(void);
 
···
 extern int blk_queue_start_tag(struct request_queue *, struct request *);
 extern struct request *blk_queue_find_tag(struct request_queue *, int);
 extern void blk_queue_end_tag(struct request_queue *, struct request *);
-extern int blk_queue_init_tags(struct request_queue *, int, struct blk_queue_tag *);
+extern int blk_queue_init_tags(struct request_queue *, int, struct blk_queue_tag *, int);
 extern void blk_queue_free_tags(struct request_queue *);
 extern int blk_queue_resize_tags(struct request_queue *, int);
 extern void blk_queue_invalidate_tags(struct request_queue *);
-extern struct blk_queue_tag *blk_init_tags(int);
+extern struct blk_queue_tag *blk_init_tags(int, int);
 extern void blk_free_tags(struct blk_queue_tag *);
 
 static inline struct request *blk_map_queue_find_tag(struct blk_queue_tag *bqt,
···
 extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp_mask, struct page *page);
 extern int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
-			sector_t nr_sects, gfp_t gfp_mask);
+		sector_t nr_sects, gfp_t gfp_mask, bool discard);
 static inline int sb_issue_discard(struct super_block *sb, sector_t block,
 		sector_t nr_blocks, gfp_t gfp_mask, unsigned long flags)
 {
···
 	return blkdev_issue_zeroout(sb->s_bdev,
 				    block << (sb->s_blocksize_bits - 9),
 				    nr_blocks << (sb->s_blocksize_bits - 9),
-				    gfp_mask);
+				    gfp_mask, true);
 }
 
 extern int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm);
···
 	int (*rw_page)(struct block_device *, sector_t, struct page *, int rw);
 	int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 	int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
-	int (*direct_access) (struct block_device *, sector_t,
-						void **, unsigned long *);
+	long (*direct_access)(struct block_device *, sector_t,
+					void **, unsigned long *pfn, long size);
 	unsigned int (*check_events) (struct gendisk *disk,
 				      unsigned int clearing);
 	/* ->media_changed() is DEPRECATED, use ->check_events() instead */
···
 extern int bdev_read_page(struct block_device *, sector_t, struct page *);
 extern int bdev_write_page(struct block_device *, sector_t, struct page *,
 						struct writeback_control *);
+extern long bdev_direct_access(struct block_device *, sector_t, void **addr,
+						unsigned long *pfn, long size);
 #else /* CONFIG_BLOCK */
 
 struct block_device;

include/scsi/scsi_host.h

···
 	 */
 	unsigned char present;
 
+	/* If use block layer to manage tags, this is tag allocation policy */
+	int tag_alloc_policy;
+
 	/*
 	 * Let the block layer assigns tags to all commands.
 	 */

include/scsi/scsi_tcq.h

···
 	 * devices on the shared host (for libata)
 	 */
 	if (!shost->bqt) {
-		shost->bqt = blk_init_tags(depth);
+		shost->bqt = blk_init_tags(depth,
+			shost->hostt->tag_alloc_policy);
 		if (!shost->bqt)
 			return -ENOMEM;
 	}