1 files changed, 125 insertions, 137 deletions

diff --git a/block/bio.c b/block/bio.c
index 67eff5eddc49..b12966e415d3 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -28,9 +28,11 @@
 #include <linux/mempool.h>
 #include <linux/workqueue.h>
 #include <linux/cgroup.h>
+#include <linux/blk-cgroup.h>
 
 #include <trace/events/block.h>
 #include "blk.h"
+#include "blk-rq-qos.h"
 
 /*
  * Test patch to inline a certain number of bi_io_vec's inside the bio
@@ -156,7 +158,7 @@ out:
 
 unsigned int bvec_nr_vecs(unsigned short idx)
 {
-	return bvec_slabs[idx].nr_vecs;
+	return bvec_slabs[--idx].nr_vecs;
 }
 
 void bvec_free(mempool_t *pool, struct bio_vec *bv, unsigned int idx)
@@ -645,83 +647,6 @@ struct bio *bio_clone_fast(struct bio *bio, gfp_t gfp_mask, struct bio_set *bs)
 EXPORT_SYMBOL(bio_clone_fast);
 
 /**
- * 	bio_clone_bioset - clone a bio
- * 	@bio_src: bio to clone
- *	@gfp_mask: allocation priority
- *	@bs: bio_set to allocate from
- *
- *	Clone bio. Caller will own the returned bio, but not the actual data it
- *	points to. Reference count of returned bio will be one.
- */
-struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask,
-			     struct bio_set *bs)
-{
-	struct bvec_iter iter;
-	struct bio_vec bv;
-	struct bio *bio;
-
-	/*
-	 * Pre immutable biovecs, __bio_clone() used to just do a memcpy from
-	 * bio_src->bi_io_vec to bio->bi_io_vec.
-	 *
-	 * We can't do that anymore, because:
-	 *
-	 *  - The point of cloning the biovec is to produce a bio with a biovec
-	 *    the caller can modify: bi_idx and bi_bvec_done should be 0.
-	 *
-	 *  - The original bio could've had more than BIO_MAX_PAGES biovecs; if
-	 *    we tried to clone the whole thing bio_alloc_bioset() would fail.
-	 *    But the clone should succeed as long as the number of biovecs we
-	 *    actually need to allocate is fewer than BIO_MAX_PAGES.
-	 *
-	 *  - Lastly, bi_vcnt should not be looked at or relied upon by code
-	 *    that does not own the bio - reason being drivers don't use it for
-	 *    iterating over the biovec anymore, so expecting it to be kept up
-	 *    to date (i.e. for clones that share the parent biovec) is just
-	 *    asking for trouble and would force extra work on
-	 *    __bio_clone_fast() anyways.
-	 */
-
-	bio = bio_alloc_bioset(gfp_mask, bio_segments(bio_src), bs);
-	if (!bio)
-		return NULL;
-	bio->bi_disk		= bio_src->bi_disk;
-	bio->bi_opf		= bio_src->bi_opf;
-	bio->bi_write_hint	= bio_src->bi_write_hint;
-	bio->bi_iter.bi_sector	= bio_src->bi_iter.bi_sector;
-	bio->bi_iter.bi_size	= bio_src->bi_iter.bi_size;
-
-	switch (bio_op(bio)) {
-	case REQ_OP_DISCARD:
-	case REQ_OP_SECURE_ERASE:
-	case REQ_OP_WRITE_ZEROES:
-		break;
-	case REQ_OP_WRITE_SAME:
-		bio->bi_io_vec[bio->bi_vcnt++] = bio_src->bi_io_vec[0];
-		break;
-	default:
-		bio_for_each_segment(bv, bio_src, iter)
-			bio->bi_io_vec[bio->bi_vcnt++] = bv;
-		break;
-	}
-
-	if (bio_integrity(bio_src)) {
-		int ret;
-
-		ret = bio_integrity_clone(bio, bio_src, gfp_mask);
-		if (ret < 0) {
-			bio_put(bio);
-			return NULL;
-		}
-	}
-
-	bio_clone_blkcg_association(bio, bio_src);
-
-	return bio;
-}
-EXPORT_SYMBOL(bio_clone_bioset);
-
-/**
  *	bio_add_pc_page	-	attempt to add page to bio
  *	@q: the target queue
  *	@bio: destination bio
@@ -903,25 +828,27 @@ int bio_add_page(struct bio *bio, struct page *page,
 EXPORT_SYMBOL(bio_add_page);
 
 /**
- * bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio
+ * __bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio
  * @bio: bio to add pages to
  * @iter: iov iterator describing the region to be mapped
  *
- * Pins as many pages from *iter and appends them to @bio's bvec array. The
+ * Pins pages from *iter and appends them to @bio's bvec array. The
  * pages will have to be released using put_page() when done.
+ * For multi-segment *iter, this function only adds pages from the
+ * the next non-empty segment of the iov iterator.
  */
-int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
+static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 {
-	unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt;
+	unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt, idx;
 	struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt;
 	struct page **pages = (struct page **)bv;
-	size_t offset, diff;
+	size_t offset;
 	ssize_t size;
 
 	size = iov_iter_get_pages(iter, pages, LONG_MAX, nr_pages, &offset);
 	if (unlikely(size <= 0))
 		return size ? size : -EFAULT;
-	nr_pages = (size + offset + PAGE_SIZE - 1) / PAGE_SIZE;
+	idx = nr_pages = (size + offset + PAGE_SIZE - 1) / PAGE_SIZE;
 
 	/*
 	 * Deep magic below:  We need to walk the pinned pages backwards
@@ -934,21 +861,46 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 	bio->bi_iter.bi_size += size;
 	bio->bi_vcnt += nr_pages;
 
-	diff = (nr_pages * PAGE_SIZE - offset) - size;
-	while (nr_pages--) {
-		bv[nr_pages].bv_page = pages[nr_pages];
-		bv[nr_pages].bv_len = PAGE_SIZE;
-		bv[nr_pages].bv_offset = 0;
+	while (idx--) {
+		bv[idx].bv_page = pages[idx];
+		bv[idx].bv_len = PAGE_SIZE;
+		bv[idx].bv_offset = 0;
 	}
 
 	bv[0].bv_offset += offset;
 	bv[0].bv_len -= offset;
-	if (diff)
-		bv[bio->bi_vcnt - 1].bv_len -= diff;
+	bv[nr_pages - 1].bv_len -= nr_pages * PAGE_SIZE - offset - size;
 
 	iov_iter_advance(iter, size);
 	return 0;
 }
+
+/**
+ * bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio
+ * @bio: bio to add pages to
+ * @iter: iov iterator describing the region to be mapped
+ *
+ * Pins pages from *iter and appends them to @bio's bvec array. The
+ * pages will have to be released using put_page() when done.
+ * The function tries, but does not guarantee, to pin as many pages as
+ * fit into the bio, or are requested in *iter, whatever is smaller.
+ * If MM encounters an error pinning the requested pages, it stops.
+ * Error is returned only if 0 pages could be pinned.
+ */
+int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
+{
+	unsigned short orig_vcnt = bio->bi_vcnt;
+
+	do {
+		int ret = __bio_iov_iter_get_pages(bio, iter);
+
+		if (unlikely(ret))
+			return bio->bi_vcnt > orig_vcnt ? 0 : ret;
+
+	} while (iov_iter_count(iter) && !bio_full(bio));
+
+	return 0;
+}
 EXPORT_SYMBOL_GPL(bio_iov_iter_get_pages);
 
 static void submit_bio_wait_endio(struct bio *bio)
@@ -1634,10 +1586,8 @@ void bio_set_pages_dirty(struct bio *bio)
 	int i;
 
 	bio_for_each_segment_all(bvec, bio, i) {
-		struct page *page = bvec->bv_page;
-
-		if (page && !PageCompound(page))
-			set_page_dirty_lock(page);
+		if (!PageCompound(bvec->bv_page))
+			set_page_dirty_lock(bvec->bv_page);
 	}
 }
 EXPORT_SYMBOL_GPL(bio_set_pages_dirty);
@@ -1647,19 +1597,15 @@ static void bio_release_pages(struct bio *bio)
 	struct bio_vec *bvec;
 	int i;
 
-	bio_for_each_segment_all(bvec, bio, i) {
-		struct page *page = bvec->bv_page;
-
-		if (page)
-			put_page(page);
-	}
+	bio_for_each_segment_all(bvec, bio, i)
+		put_page(bvec->bv_page);
 }
 
 /*
  * bio_check_pages_dirty() will check that all the BIO's pages are still dirty.
  * If they are, then fine.  If, however, some pages are clean then they must
  * have been written out during the direct-IO read.  So we take another ref on
- * the BIO and the offending pages and re-dirty the pages in process context.
+ * the BIO and re-dirty the pages in process context.
  *
  * It is expected that bio_check_pages_dirty() will wholly own the BIO from
  * here on.  It will run one put_page() against each page and will run one
@@ -1677,78 +1623,70 @@ static struct bio *bio_dirty_list;
  */
 static void bio_dirty_fn(struct work_struct *work)
 {
-	unsigned long flags;
-	struct bio *bio;
+	struct bio *bio, *next;
 
-	spin_lock_irqsave(&bio_dirty_lock, flags);
-	bio = bio_dirty_list;
+	spin_lock_irq(&bio_dirty_lock);
+	next = bio_dirty_list;
 	bio_dirty_list = NULL;
-	spin_unlock_irqrestore(&bio_dirty_lock, flags);
+	spin_unlock_irq(&bio_dirty_lock);
 
-	while (bio) {
-		struct bio *next = bio->bi_private;
+	while ((bio = next) != NULL) {
+		next = bio->bi_private;
 
 		bio_set_pages_dirty(bio);
 		bio_release_pages(bio);
 		bio_put(bio);
-		bio = next;
 	}
 }
 
 void bio_check_pages_dirty(struct bio *bio)
 {
 	struct bio_vec *bvec;
-	int nr_clean_pages = 0;
+	unsigned long flags;
 	int i;
 
 	bio_for_each_segment_all(bvec, bio, i) {
-		struct page *page = bvec->bv_page;
-
-		if (PageDirty(page) || PageCompound(page)) {
-			put_page(page);
-			bvec->bv_page = NULL;
-		} else {
-			nr_clean_pages++;
-		}
+		if (!PageDirty(bvec->bv_page) && !PageCompound(bvec->bv_page))
+			goto defer;
 	}
 
-	if (nr_clean_pages) {
-		unsigned long flags;
-
-		spin_lock_irqsave(&bio_dirty_lock, flags);
-		bio->bi_private = bio_dirty_list;
-		bio_dirty_list = bio;
-		spin_unlock_irqrestore(&bio_dirty_lock, flags);
-		schedule_work(&bio_dirty_work);
-	} else {
-		bio_put(bio);
-	}
+	bio_release_pages(bio);
+	bio_put(bio);
+	return;
+defer:
+	spin_lock_irqsave(&bio_dirty_lock, flags);
+	bio->bi_private = bio_dirty_list;
+	bio_dirty_list = bio;
+	spin_unlock_irqrestore(&bio_dirty_lock, flags);
+	schedule_work(&bio_dirty_work);
 }
 EXPORT_SYMBOL_GPL(bio_check_pages_dirty);
 
-void generic_start_io_acct(struct request_queue *q, int rw,
+void generic_start_io_acct(struct request_queue *q, int op,
 			   unsigned long sectors, struct hd_struct *part)
 {
+	const int sgrp = op_stat_group(op);
 	int cpu = part_stat_lock();
 
 	part_round_stats(q, cpu, part);
-	part_stat_inc(cpu, part, ios[rw]);
-	part_stat_add(cpu, part, sectors[rw], sectors);
-	part_inc_in_flight(q, part, rw);
+	part_stat_inc(cpu, part, ios[sgrp]);
+	part_stat_add(cpu, part, sectors[sgrp], sectors);
+	part_inc_in_flight(q, part, op_is_write(op));
 
 	part_stat_unlock();
 }
 EXPORT_SYMBOL(generic_start_io_acct);
 
-void generic_end_io_acct(struct request_queue *q, int rw,
+void generic_end_io_acct(struct request_queue *q, int req_op,
 			 struct hd_struct *part, unsigned long start_time)
 {
 	unsigned long duration = jiffies - start_time;
+	const int sgrp = op_stat_group(req_op);
 	int cpu = part_stat_lock();
 
-	part_stat_add(cpu, part, ticks[rw], duration);
+	part_stat_add(cpu, part, ticks[sgrp], duration);
 	part_round_stats(q, cpu, part);
-	part_dec_in_flight(q, part, rw);
+	part_dec_in_flight(q, part, op_is_write(req_op));
 
 	part_stat_unlock();
 }
@@ -1807,6 +1745,9 @@ again:
 	if (!bio_integrity_endio(bio))
 		return;
 
+	if (bio->bi_disk)
+		rq_qos_done_bio(bio->bi_disk->queue, bio);
+
 	/*
 	 * Need to have a real endio function for chained bios, otherwise
 	 * various corner cases will break (like stacking block devices that
@@ -1866,6 +1807,7 @@ struct bio *bio_split(struct bio *bio, int sectors,
 		bio_integrity_trim(split);
 
 	bio_advance(bio, split->bi_iter.bi_size);
+	bio->bi_iter.bi_done = 0;
 
 	if (bio_flagged(bio, BIO_TRACE_COMPLETION))
 		bio_set_flag(split, BIO_TRACE_COMPLETION);
@@ -2014,6 +1956,30 @@ EXPORT_SYMBOL(bioset_init_from_src);
 
 #ifdef CONFIG_BLK_CGROUP
 
+#ifdef CONFIG_MEMCG
+/**
+ * bio_associate_blkcg_from_page - associate a bio with the page's blkcg
+ * @bio: target bio
+ * @page: the page to lookup the blkcg from
+ *
+ * Associate @bio with the blkcg from @page's owning memcg.  This works like
+ * every other associate function wrt references.
+ */
+int bio_associate_blkcg_from_page(struct bio *bio, struct page *page)
+{
+	struct cgroup_subsys_state *blkcg_css;
+
+	if (unlikely(bio->bi_css))
+		return -EBUSY;
+	if (!page->mem_cgroup)
+		return 0;
+	blkcg_css = cgroup_get_e_css(page->mem_cgroup->css.cgroup,
+				     &io_cgrp_subsys);
+	bio->bi_css = blkcg_css;
+	return 0;
+}
+#endif /* CONFIG_MEMCG */
+
 /**
  * bio_associate_blkcg - associate a bio with the specified blkcg
  * @bio: target bio
@@ -2037,6 +2003,24 @@ int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css)
 EXPORT_SYMBOL_GPL(bio_associate_blkcg);
 
 /**
+ * bio_associate_blkg - associate a bio with the specified blkg
+ * @bio: target bio
+ * @blkg: the blkg to associate
+ *
+ * Associate @bio with the blkg specified by @blkg.  This is the queue specific
+ * blkcg information associated with the @bio, a reference will be taken on the
+ * @blkg and will be freed when the bio is freed.
+ */
+int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg)
+{
+	if (unlikely(bio->bi_blkg))
+		return -EBUSY;
+	blkg_get(blkg);
+	bio->bi_blkg = blkg;
+	return 0;
+}
+
+/**
  * bio_disassociate_task - undo bio_associate_current()
  * @bio: target bio
  */
@@ -2050,6 +2034,10 @@ void bio_disassociate_task(struct bio *bio)
 		css_put(bio->bi_css);
 		bio->bi_css = NULL;
 	}
+	if (bio->bi_blkg) {
+		blkg_put(bio->bi_blkg);
+		bio->bi_blkg = NULL;
+	}
 }
 
 /**