1 files changed, 154 insertions, 102 deletions

diff --git a/block/bio.c b/block/bio.c
index 41173710430c..4db1008309ed 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -244,7 +244,7 @@ fallback:
 
 void bio_uninit(struct bio *bio)
 {
-	bio_disassociate_task(bio);
+	bio_disassociate_blkg(bio);
 }
 EXPORT_SYMBOL(bio_uninit);
 
@@ -571,14 +571,13 @@ void bio_put(struct bio *bio)
 }
 EXPORT_SYMBOL(bio_put);
 
-inline int bio_phys_segments(struct request_queue *q, struct bio *bio)
+int bio_phys_segments(struct request_queue *q, struct bio *bio)
 {
 	if (unlikely(!bio_flagged(bio, BIO_SEG_VALID)))
 		blk_recount_segments(q, bio);
 
 	return bio->bi_phys_segments;
 }
-EXPORT_SYMBOL(bio_phys_segments);
 
 /**
  * 	__bio_clone_fast - clone a bio that shares the original bio's biovec
@@ -605,11 +604,13 @@ void __bio_clone_fast(struct bio *bio, struct bio *bio_src)
 	if (bio_flagged(bio_src, BIO_THROTTLED))
 		bio_set_flag(bio, BIO_THROTTLED);
 	bio->bi_opf = bio_src->bi_opf;
+	bio->bi_ioprio = bio_src->bi_ioprio;
 	bio->bi_write_hint = bio_src->bi_write_hint;
 	bio->bi_iter = bio_src->bi_iter;
 	bio->bi_io_vec = bio_src->bi_io_vec;
 
-	bio_clone_blkcg_association(bio, bio_src);
+	bio_clone_blkg_association(bio, bio_src);
+	blkcg_bio_issue_init(bio);
 }
 EXPORT_SYMBOL(__bio_clone_fast);
 
@@ -729,7 +730,7 @@ int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page
 	}
 
 	/* If we may be able to merge these biovecs, force a recount */
-	if (bio->bi_vcnt > 1 && (BIOVEC_PHYS_MERGEABLE(bvec-1, bvec)))
+	if (bio->bi_vcnt > 1 && biovec_phys_mergeable(q, bvec - 1, bvec))
 		bio_clear_flag(bio, BIO_SEG_VALID);
 
  done:
@@ -827,6 +828,8 @@ int bio_add_page(struct bio *bio, struct page *page,
 }
 EXPORT_SYMBOL(bio_add_page);
 
+#define PAGE_PTRS_PER_BVEC     (sizeof(struct bio_vec) / sizeof(struct page *))
+
 /**
  * __bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio
  * @bio: bio to add pages to
@@ -839,38 +842,35 @@ EXPORT_SYMBOL(bio_add_page);
  */
 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, idx;
+	unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt;
+	unsigned short entries_left = bio->bi_max_vecs - bio->bi_vcnt;
 	struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt;
 	struct page **pages = (struct page **)bv;
+	ssize_t size, left;
+	unsigned len, i;
 	size_t offset;
-	ssize_t size;
+
+	/*
+	 * Move page array up in the allocated memory for the bio vecs as far as
+	 * possible so that we can start filling biovecs from the beginning
+	 * without overwriting the temporary page array.
+	*/
+	BUILD_BUG_ON(PAGE_PTRS_PER_BVEC < 2);
+	pages += entries_left * (PAGE_PTRS_PER_BVEC - 1);
 
 	size = iov_iter_get_pages(iter, pages, LONG_MAX, nr_pages, &offset);
 	if (unlikely(size <= 0))
 		return size ? size : -EFAULT;
-	idx = nr_pages = (size + offset + PAGE_SIZE - 1) / PAGE_SIZE;
 
-	/*
-	 * Deep magic below:  We need to walk the pinned pages backwards
-	 * because we are abusing the space allocated for the bio_vecs
-	 * for the page array.  Because the bio_vecs are larger than the
-	 * page pointers by definition this will always work.  But it also
-	 * means we can't use bio_add_page, so any changes to it's semantics
-	 * need to be reflected here as well.
-	 */
-	bio->bi_iter.bi_size += size;
-	bio->bi_vcnt += nr_pages;
+	for (left = size, i = 0; left > 0; left -= len, i++) {
+		struct page *page = pages[i];
 
-	while (idx--) {
-		bv[idx].bv_page = pages[idx];
-		bv[idx].bv_len = PAGE_SIZE;
-		bv[idx].bv_offset = 0;
+		len = min_t(size_t, PAGE_SIZE - offset, left);
+		if (WARN_ON_ONCE(bio_add_page(bio, page, len, offset) != len))
+			return -EINVAL;
+		offset = 0;
 	}
 
-	bv[0].bv_offset += offset;
-	bv[0].bv_len -= offset;
-	bv[nr_pages - 1].bv_len -= nr_pages * PAGE_SIZE - offset - size;
-
 	iov_iter_advance(iter, size);
 	return 0;
 }
@@ -901,7 +901,6 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(bio_iov_iter_get_pages);
 
 static void submit_bio_wait_endio(struct bio *bio)
 {
@@ -1255,13 +1254,14 @@ struct bio *bio_copy_user_iov(struct request_queue *q,
 	/*
 	 * success
 	 */
-	if (((iter->type & WRITE) && (!map_data || !map_data->null_mapped)) ||
+	if ((iov_iter_rw(iter) == WRITE && (!map_data || !map_data->null_mapped)) ||
 	    (map_data && map_data->from_user)) {
 		ret = bio_copy_from_iter(bio, iter);
 		if (ret)
 			goto cleanup;
 	} else {
-		zero_fill_bio(bio);
+		if (bmd->is_our_pages)
+			zero_fill_bio(bio);
 		iov_iter_advance(iter, bio->bi_iter.bi_size);
 	}
 
@@ -1591,7 +1591,6 @@ void bio_set_pages_dirty(struct bio *bio)
 			set_page_dirty_lock(bvec->bv_page);
 	}
 }
-EXPORT_SYMBOL_GPL(bio_set_pages_dirty);
 
 static void bio_release_pages(struct bio *bio)
 {
@@ -1661,17 +1660,33 @@ defer:
 	spin_unlock_irqrestore(&bio_dirty_lock, flags);
 	schedule_work(&bio_dirty_work);
 }
-EXPORT_SYMBOL_GPL(bio_check_pages_dirty);
+
+void update_io_ticks(struct hd_struct *part, unsigned long now)
+{
+	unsigned long stamp;
+again:
+	stamp = READ_ONCE(part->stamp);
+	if (unlikely(stamp != now)) {
+		if (likely(cmpxchg(&part->stamp, stamp, now) == stamp)) {
+			__part_stat_add(part, io_ticks, 1);
+		}
+	}
+	if (part->partno) {
+		part = &part_to_disk(part)->part0;
+		goto again;
+	}
+}
 
 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[sgrp]);
-	part_stat_add(cpu, part, sectors[sgrp], sectors);
+	part_stat_lock();
+
+	update_io_ticks(part, jiffies);
+	part_stat_inc(part, ios[sgrp]);
+	part_stat_add(part, sectors[sgrp], sectors);
 	part_inc_in_flight(q, part, op_is_write(op));
 
 	part_stat_unlock();
@@ -1681,12 +1696,15 @@ EXPORT_SYMBOL(generic_start_io_acct);
 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;
+	unsigned long now = jiffies;
+	unsigned long duration = now - start_time;
 	const int sgrp = op_stat_group(req_op);
-	int cpu = part_stat_lock();
 
-	part_stat_add(cpu, part, nsecs[sgrp], jiffies_to_nsecs(duration));
-	part_round_stats(q, cpu, part);
+	part_stat_lock();
+
+	update_io_ticks(part, now);
+	part_stat_add(part, nsecs[sgrp], jiffies_to_nsecs(duration));
+	part_stat_add(part, time_in_queue, duration);
 	part_dec_in_flight(q, part, op_is_write(req_op));
 
 	part_stat_unlock();
@@ -1808,7 +1826,6 @@ 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);
@@ -1957,102 +1974,137 @@ 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_disassociate_blkg - puts back the blkg reference if associated
  * @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.
+ * Helper to disassociate the blkg from @bio if a blkg is associated.
  */
-int bio_associate_blkcg_from_page(struct bio *bio, struct page *page)
+void bio_disassociate_blkg(struct bio *bio)
 {
-	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;
+	if (bio->bi_blkg) {
+		blkg_put(bio->bi_blkg);
+		bio->bi_blkg = NULL;
+	}
 }
-#endif /* CONFIG_MEMCG */
+EXPORT_SYMBOL_GPL(bio_disassociate_blkg);
 
 /**
- * bio_associate_blkcg - associate a bio with the specified blkcg
+ * __bio_associate_blkg - associate a bio with the a blkg
  * @bio: target bio
- * @blkcg_css: css of the blkcg to associate
+ * @blkg: the blkg to associate
  *
- * Associate @bio with the blkcg specified by @blkcg_css.  Block layer will
- * treat @bio as if it were issued by a task which belongs to the blkcg.
+ * This tries to associate @bio with the specified @blkg.  Association failure
+ * is handled by walking up the blkg tree.  Therefore, the blkg associated can
+ * be anything between @blkg and the root_blkg.  This situation only happens
+ * when a cgroup is dying and then the remaining bios will spill to the closest
+ * alive blkg.
  *
- * This function takes an extra reference of @blkcg_css which will be put
- * when @bio is released.  The caller must own @bio and is responsible for
- * synchronizing calls to this function.
+ * A reference will be taken on the @blkg and will be released when @bio is
+ * freed.
  */
-int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css)
+static void __bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg)
 {
-	if (unlikely(bio->bi_css))
-		return -EBUSY;
-	css_get(blkcg_css);
-	bio->bi_css = blkcg_css;
-	return 0;
+	bio_disassociate_blkg(bio);
+
+	bio->bi_blkg = blkg_tryget_closest(blkg);
 }
-EXPORT_SYMBOL_GPL(bio_associate_blkcg);
 
 /**
- * bio_associate_blkg - associate a bio with the specified blkg
+ * bio_associate_blkg_from_css - associate a bio with a specified css
  * @bio: target bio
- * @blkg: the blkg to associate
+ * @css: target css
  *
- * 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.
+ * Associate @bio with the blkg found by combining the css's blkg and the
+ * request_queue of the @bio.  This falls back to the queue's root_blkg if
+ * the association fails with the css.
  */
-int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg)
+void bio_associate_blkg_from_css(struct bio *bio,
+				 struct cgroup_subsys_state *css)
 {
-	if (unlikely(bio->bi_blkg))
-		return -EBUSY;
-	if (!blkg_try_get(blkg))
-		return -ENODEV;
-	bio->bi_blkg = blkg;
-	return 0;
+	struct request_queue *q = bio->bi_disk->queue;
+	struct blkcg_gq *blkg;
+
+	rcu_read_lock();
+
+	if (!css || !css->parent)
+		blkg = q->root_blkg;
+	else
+		blkg = blkg_lookup_create(css_to_blkcg(css), q);
+
+	__bio_associate_blkg(bio, blkg);
+
+	rcu_read_unlock();
 }
+EXPORT_SYMBOL_GPL(bio_associate_blkg_from_css);
 
+#ifdef CONFIG_MEMCG
 /**
- * bio_disassociate_task - undo bio_associate_current()
+ * bio_associate_blkg_from_page - associate a bio with the page's blkg
  * @bio: target bio
+ * @page: the page to lookup the blkcg from
+ *
+ * Associate @bio with the blkg from @page's owning memcg and the respective
+ * request_queue.  If cgroup_e_css returns %NULL, fall back to the queue's
+ * root_blkg.
  */
-void bio_disassociate_task(struct bio *bio)
+void bio_associate_blkg_from_page(struct bio *bio, struct page *page)
 {
-	if (bio->bi_ioc) {
-		put_io_context(bio->bi_ioc);
-		bio->bi_ioc = NULL;
-	}
-	if (bio->bi_css) {
-		css_put(bio->bi_css);
-		bio->bi_css = NULL;
-	}
-	if (bio->bi_blkg) {
-		blkg_put(bio->bi_blkg);
-		bio->bi_blkg = NULL;
-	}
+	struct cgroup_subsys_state *css;
+
+	if (!page->mem_cgroup)
+		return;
+
+	rcu_read_lock();
+
+	css = cgroup_e_css(page->mem_cgroup->css.cgroup, &io_cgrp_subsys);
+	bio_associate_blkg_from_css(bio, css);
+
+	rcu_read_unlock();
+}
+#endif /* CONFIG_MEMCG */
+
+/**
+ * bio_associate_blkg - associate a bio with a blkg
+ * @bio: target bio
+ *
+ * Associate @bio with the blkg found from the bio's css and request_queue.
+ * If one is not found, bio_lookup_blkg() creates the blkg.  If a blkg is
+ * already associated, the css is reused and association redone as the
+ * request_queue may have changed.
+ */
+void bio_associate_blkg(struct bio *bio)
+{
+	struct cgroup_subsys_state *css;
+
+	rcu_read_lock();
+
+	if (bio->bi_blkg)
+		css = &bio_blkcg(bio)->css;
+	else
+		css = blkcg_css();
+
+	bio_associate_blkg_from_css(bio, css);
+
+	rcu_read_unlock();
 }
+EXPORT_SYMBOL_GPL(bio_associate_blkg);
 
 /**
- * bio_clone_blkcg_association - clone blkcg association from src to dst bio
+ * bio_clone_blkg_association - clone blkg association from src to dst bio
  * @dst: destination bio
  * @src: source bio
  */
-void bio_clone_blkcg_association(struct bio *dst, struct bio *src)
+void bio_clone_blkg_association(struct bio *dst, struct bio *src)
 {
-	if (src->bi_css)
-		WARN_ON(bio_associate_blkcg(dst, src->bi_css));
+	rcu_read_lock();
+
+	if (src->bi_blkg)
+		__bio_associate_blkg(dst, src->bi_blkg);
+
+	rcu_read_unlock();
 }
-EXPORT_SYMBOL_GPL(bio_clone_blkcg_association);
+EXPORT_SYMBOL_GPL(bio_clone_blkg_association);
 #endif /* CONFIG_BLK_CGROUP */
 
 static void __init biovec_init_slabs(void)