Merge tag 'for-5.3/block-20190708' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:
 "This is the main block updates for 5.3. Nothing earth shattering or
  major in here, just fixes, additions, and improvements all over the
  map. This contains:

   - Series of documentation fixes (Bart)

   - Optimization of the blk-mq ctx get/put (Bart)

   - null_blk removal race condition fix (Bob)

   - req/bio_op() cleanups (Chaitanya)

   - Series cleaning up the segment accounting, and request/bio mapping
     (Christoph)

   - Series cleaning up the page getting/putting for bios (Christoph)

   - block cgroup cleanups and moving it to where it is used (Christoph)

   - block cgroup fixes (Tejun)

   - Series of fixes and improvements to bcache, most notably a write
     deadlock fix (Coly)

   - blk-iolatency STS_AGAIN and accounting fixes (Dennis)

   - Series of improvements and fixes to BFQ (Douglas, Paolo)

   - debugfs_create() return value check removal for drbd (Greg)

   - Use struct_size(), where appropriate (Gustavo)

   - Two lighnvm fixes (Heiner, Geert)

   - MD fixes, including a read balance and corruption fix (Guoqing,
     Marcos, Xiao, Yufen)

   - block opal shadow mbr additions (Jonas, Revanth)

   - sbitmap compare-and-exhange improvemnts (Pavel)

   - Fix for potential bio->bi_size overflow (Ming)

   - NVMe pull requests:
       - improved PCIe suspent support (Keith Busch)
       - error injection support for the admin queue (Akinobu Mita)
       - Fibre Channel discovery improvements (James Smart)
       - tracing improvements including nvmetc tracing support (Minwoo Im)
       - misc fixes and cleanups (Anton Eidelman, Minwoo Im, Chaitanya
         Kulkarni)"

   - Various little fixes and improvements to drivers and core"

* tag 'for-5.3/block-20190708' of git://git.kernel.dk/linux-block: (153 commits)
  blk-iolatency: fix STS_AGAIN handling
  block: nr_phys_segments needs to be zero for REQ_OP_WRITE_ZEROES
  blk-mq: simplify blk_mq_make_request()
  blk-mq: remove blk_mq_put_ctx()
  sbitmap: Replace cmpxchg with xchg
  block: fix .bi_size overflow
  block: sed-opal: check size of shadow mbr
  block: sed-opal: ioctl for writing to shadow mbr
  block: sed-opal: add ioctl for done-mark of shadow mbr
  block: never take page references for ITER_BVEC
  direct-io: use bio_release_pages in dio_bio_complete
  block_dev: use bio_release_pages in bio_unmap_user
  block_dev: use bio_release_pages in blkdev_bio_end_io
  iomap: use bio_release_pages in iomap_dio_bio_end_io
  block: use bio_release_pages in bio_map_user_iov
  block: use bio_release_pages in bio_unmap_user
  block: optionally mark pages dirty in bio_release_pages
  block: move the BIO_NO_PAGE_REF check into bio_release_pages
  block: skd_main.c: Remove call to memset after dma_alloc_coherent
  block: mtip32xx: Remove call to memset after dma_alloc_coherent
  ...

1 files changed, 20 insertions, 76 deletions

diff --git a/block/bio.c b/block/bio.c
index ce797d73bb43..29cd6cf4da51 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -558,14 +558,6 @@ void bio_put(struct bio *bio)
 }
 EXPORT_SYMBOL(bio_put);
 
-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;
-}
-
 /**
  * 	__bio_clone_fast - clone a bio that shares the original bio's biovec
  * 	@bio: destination bio
@@ -731,10 +723,10 @@ static int __bio_add_pc_page(struct request_queue *q, struct bio *bio,
 		}
 	}
 
-	if (bio_full(bio))
+	if (bio_full(bio, len))
 		return 0;
 
-	if (bio->bi_phys_segments >= queue_max_segments(q))
+	if (bio->bi_vcnt >= queue_max_segments(q))
 		return 0;
 
 	bvec = &bio->bi_io_vec[bio->bi_vcnt];
@@ -744,8 +736,6 @@ static int __bio_add_pc_page(struct request_queue *q, struct bio *bio,
 	bio->bi_vcnt++;
  done:
 	bio->bi_iter.bi_size += len;
-	bio->bi_phys_segments = bio->bi_vcnt;
-	bio_set_flag(bio, BIO_SEG_VALID);
 	return len;
 }
 
@@ -807,7 +797,7 @@ void __bio_add_page(struct bio *bio, struct page *page,
 	struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt];
 
 	WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED));
-	WARN_ON_ONCE(bio_full(bio));
+	WARN_ON_ONCE(bio_full(bio, len));
 
 	bv->bv_page = page;
 	bv->bv_offset = off;
@@ -834,7 +824,7 @@ int bio_add_page(struct bio *bio, struct page *page,
 	bool same_page = false;
 
 	if (!__bio_try_merge_page(bio, page, len, offset, &same_page)) {
-		if (bio_full(bio))
+		if (bio_full(bio, len))
 			return 0;
 		__bio_add_page(bio, page, len, offset);
 	}
@@ -842,22 +832,19 @@ int bio_add_page(struct bio *bio, struct page *page,
 }
 EXPORT_SYMBOL(bio_add_page);
 
-static void bio_get_pages(struct bio *bio)
+void bio_release_pages(struct bio *bio, bool mark_dirty)
 {
 	struct bvec_iter_all iter_all;
 	struct bio_vec *bvec;
 
-	bio_for_each_segment_all(bvec, bio, iter_all)
-		get_page(bvec->bv_page);
-}
-
-static void bio_release_pages(struct bio *bio)
-{
-	struct bvec_iter_all iter_all;
-	struct bio_vec *bvec;
+	if (bio_flagged(bio, BIO_NO_PAGE_REF))
+		return;
 
-	bio_for_each_segment_all(bvec, bio, iter_all)
+	bio_for_each_segment_all(bvec, bio, iter_all) {
+		if (mark_dirty && !PageCompound(bvec->bv_page))
+			set_page_dirty_lock(bvec->bv_page);
 		put_page(bvec->bv_page);
+	}
 }
 
 static int __bio_iov_bvec_add_pages(struct bio *bio, struct iov_iter *iter)
@@ -922,7 +909,7 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 			if (same_page)
 				put_page(page);
 		} else {
-			if (WARN_ON_ONCE(bio_full(bio)))
+			if (WARN_ON_ONCE(bio_full(bio, len)))
                                 return -EINVAL;
 			__bio_add_page(bio, page, len, offset);
 		}
@@ -966,13 +953,10 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 			ret = __bio_iov_bvec_add_pages(bio, iter);
 		else
 			ret = __bio_iov_iter_get_pages(bio, iter);
-	} while (!ret && iov_iter_count(iter) && !bio_full(bio));
+	} while (!ret && iov_iter_count(iter) && !bio_full(bio, 0));
 
-	if (iov_iter_bvec_no_ref(iter))
+	if (is_bvec)
 		bio_set_flag(bio, BIO_NO_PAGE_REF);
-	else if (is_bvec)
-		bio_get_pages(bio);
-
 	return bio->bi_vcnt ? 0 : ret;
 }
 
@@ -1124,8 +1108,7 @@ static struct bio_map_data *bio_alloc_map_data(struct iov_iter *data,
 	if (data->nr_segs > UIO_MAXIOV)
 		return NULL;
 
-	bmd = kmalloc(sizeof(struct bio_map_data) +
-		       sizeof(struct iovec) * data->nr_segs, gfp_mask);
+	bmd = kmalloc(struct_size(bmd, iov, data->nr_segs), gfp_mask);
 	if (!bmd)
 		return NULL;
 	memcpy(bmd->iov, data->iov, sizeof(struct iovec) * data->nr_segs);
@@ -1371,8 +1354,6 @@ struct bio *bio_map_user_iov(struct request_queue *q,
 	int j;
 	struct bio *bio;
 	int ret;
-	struct bio_vec *bvec;
-	struct bvec_iter_all iter_all;
 
 	if (!iov_iter_count(iter))
 		return ERR_PTR(-EINVAL);
@@ -1439,31 +1420,11 @@ struct bio *bio_map_user_iov(struct request_queue *q,
 	return bio;
 
  out_unmap:
-	bio_for_each_segment_all(bvec, bio, iter_all) {
-		put_page(bvec->bv_page);
-	}
+	bio_release_pages(bio, false);
 	bio_put(bio);
 	return ERR_PTR(ret);
 }
 
-static void __bio_unmap_user(struct bio *bio)
-{
-	struct bio_vec *bvec;
-	struct bvec_iter_all iter_all;
-
-	/*
-	 * make sure we dirty pages we wrote to
-	 */
-	bio_for_each_segment_all(bvec, bio, iter_all) {
-		if (bio_data_dir(bio) == READ)
-			set_page_dirty_lock(bvec->bv_page);
-
-		put_page(bvec->bv_page);
-	}
-
-	bio_put(bio);
-}
-
 /**
  *	bio_unmap_user	-	unmap a bio
  *	@bio:		the bio being unmapped
@@ -1475,7 +1436,8 @@ static void __bio_unmap_user(struct bio *bio)
  */
 void bio_unmap_user(struct bio *bio)
 {
-	__bio_unmap_user(bio);
+	bio_release_pages(bio, bio_data_dir(bio) == READ);
+	bio_put(bio);
 	bio_put(bio);
 }
 
@@ -1695,9 +1657,7 @@ static void bio_dirty_fn(struct work_struct *work)
 	while ((bio = next) != NULL) {
 		next = bio->bi_private;
 
-		bio_set_pages_dirty(bio);
-		if (!bio_flagged(bio, BIO_NO_PAGE_REF))
-			bio_release_pages(bio);
+		bio_release_pages(bio, true);
 		bio_put(bio);
 	}
 }
@@ -1713,8 +1673,7 @@ void bio_check_pages_dirty(struct bio *bio)
 			goto defer;
 	}
 
-	if (!bio_flagged(bio, BIO_NO_PAGE_REF))
-		bio_release_pages(bio);
+	bio_release_pages(bio, false);
 	bio_put(bio);
 	return;
 defer:
@@ -1775,18 +1734,6 @@ void generic_end_io_acct(struct request_queue *q, int req_op,
 }
 EXPORT_SYMBOL(generic_end_io_acct);
 
-#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
-void bio_flush_dcache_pages(struct bio *bi)
-{
-	struct bio_vec bvec;
-	struct bvec_iter iter;
-
-	bio_for_each_segment(bvec, bi, iter)
-		flush_dcache_page(bvec.bv_page);
-}
-EXPORT_SYMBOL(bio_flush_dcache_pages);
-#endif
-
 static inline bool bio_remaining_done(struct bio *bio)
 {
 	/*
@@ -1914,10 +1861,7 @@ void bio_trim(struct bio *bio, int offset, int size)
 	if (offset == 0 && size == bio->bi_iter.bi_size)
 		return;
 
-	bio_clear_flag(bio, BIO_SEG_VALID);
-
 	bio_advance(bio, offset << 9);
-
 	bio->bi_iter.bi_size = size;
 
 	if (bio_integrity(bio))