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
  ...

6 files changed, 16 insertions, 41 deletions

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 749f5984425d..f00b569a9f89 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -203,13 +203,12 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter,
 {
 	struct file *file = iocb->ki_filp;
 	struct block_device *bdev = I_BDEV(bdev_file_inode(file));
-	struct bio_vec inline_vecs[DIO_INLINE_BIO_VECS], *vecs, *bvec;
+	struct bio_vec inline_vecs[DIO_INLINE_BIO_VECS], *vecs;
 	loff_t pos = iocb->ki_pos;
 	bool should_dirty = false;
 	struct bio bio;
 	ssize_t ret;
 	blk_qc_t qc;
-	struct bvec_iter_all iter_all;
 
 	if ((pos | iov_iter_alignment(iter)) &
 	    (bdev_logical_block_size(bdev) - 1))
@@ -259,13 +258,7 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter,
 	}
 	__set_current_state(TASK_RUNNING);
 
-	bio_for_each_segment_all(bvec, &bio, iter_all) {
-		if (should_dirty && !PageCompound(bvec->bv_page))
-			set_page_dirty_lock(bvec->bv_page);
-		if (!bio_flagged(&bio, BIO_NO_PAGE_REF))
-			put_page(bvec->bv_page);
-	}
-
+	bio_release_pages(&bio, should_dirty);
 	if (unlikely(bio.bi_status))
 		ret = blk_status_to_errno(bio.bi_status);
 
@@ -335,13 +328,7 @@ static void blkdev_bio_end_io(struct bio *bio)
 	if (should_dirty) {
 		bio_check_pages_dirty(bio);
 	} else {
-		if (!bio_flagged(bio, BIO_NO_PAGE_REF)) {
-			struct bvec_iter_all iter_all;
-			struct bio_vec *bvec;
-
-			bio_for_each_segment_all(bvec, bio, iter_all)
-				put_page(bvec->bv_page);
-		}
+		bio_release_pages(bio, false);
 		bio_put(bio);
 	}
 }
diff --git a/fs/direct-io.c b/fs/direct-io.c
index ac7fb19b6ade..ae196784f487 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -538,8 +538,8 @@ static struct bio *dio_await_one(struct dio *dio)
  */
 static blk_status_t dio_bio_complete(struct dio *dio, struct bio *bio)
 {
-	struct bio_vec *bvec;
 	blk_status_t err = bio->bi_status;
+	bool should_dirty = dio->op == REQ_OP_READ && dio->should_dirty;
 
 	if (err) {
 		if (err == BLK_STS_AGAIN && (bio->bi_opf & REQ_NOWAIT))
@@ -548,19 +548,10 @@ static blk_status_t dio_bio_complete(struct dio *dio, struct bio *bio)
 			dio->io_error = -EIO;
 	}
 
-	if (dio->is_async && dio->op == REQ_OP_READ && dio->should_dirty) {
+	if (dio->is_async && should_dirty) {
 		bio_check_pages_dirty(bio);	/* transfers ownership */
 	} else {
-		struct bvec_iter_all iter_all;
-
-		bio_for_each_segment_all(bvec, bio, iter_all) {
-			struct page *page = bvec->bv_page;
-
-			if (dio->op == REQ_OP_READ && !PageCompound(page) &&
-					dio->should_dirty)
-				set_page_dirty_lock(page);
-			put_page(page);
-		}
+		bio_release_pages(bio, should_dirty);
 		bio_put(bio);
 	}
 	return err;
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index e41cbe8e81b9..9ebfb1b28430 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -715,6 +715,7 @@ void wbc_detach_inode(struct writeback_control *wbc)
 void wbc_account_io(struct writeback_control *wbc, struct page *page,
 		    size_t bytes)
 {
+	struct cgroup_subsys_state *css;
 	int id;
 
 	/*
@@ -726,7 +727,12 @@ void wbc_account_io(struct writeback_control *wbc, struct page *page,
 	if (!wbc->wb)
 		return;
 
-	id = mem_cgroup_css_from_page(page)->id;
+	css = mem_cgroup_css_from_page(page);
+	/* dead cgroups shouldn't contribute to inode ownership arbitration */
+	if (!(css->flags & CSS_ONLINE))
+		return;
+
+	id = css->id;
 
 	if (id == wbc->wb_id) {
 		wbc->wb_bytes += bytes;
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 4ef62a45045d..4ed4b110a154 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -998,9 +998,6 @@ static int io_import_fixed(struct io_ring_ctx *ctx, int rw,
 	iov_iter_bvec(iter, rw, imu->bvec, imu->nr_bvecs, offset + len);
 	if (offset)
 		iov_iter_advance(iter, offset);
-
-	/* don't drop a reference to these pages */
-	iter->type |= ITER_BVEC_FLAG_NO_REF;
 	return 0;
 }
 
diff --git a/fs/iomap.c b/fs/iomap.c
index 12654c2e78f8..7a147aa0c4d9 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -333,7 +333,7 @@ iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 	if (iop)
 		atomic_inc(&iop->read_count);
 
-	if (!ctx->bio || !is_contig || bio_full(ctx->bio)) {
+	if (!ctx->bio || !is_contig || bio_full(ctx->bio, plen)) {
 		gfp_t gfp = mapping_gfp_constraint(page->mapping, GFP_KERNEL);
 		int nr_vecs = (length + PAGE_SIZE - 1) >> PAGE_SHIFT;
 
@@ -1599,13 +1599,7 @@ static void iomap_dio_bio_end_io(struct bio *bio)
 	if (should_dirty) {
 		bio_check_pages_dirty(bio);
 	} else {
-		if (!bio_flagged(bio, BIO_NO_PAGE_REF)) {
-			struct bvec_iter_all iter_all;
-			struct bio_vec *bvec;
-
-			bio_for_each_segment_all(bvec, bio, iter_all)
-				put_page(bvec->bv_page);
-		}
+		bio_release_pages(bio, false);
 		bio_put(bio);
 	}
 }
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 8da5e6637771..11f703d4a605 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -782,7 +782,7 @@ xfs_add_to_ioend(
 		atomic_inc(&iop->write_count);
 
 	if (!merged) {
-		if (bio_full(wpc->ioend->io_bio))
+		if (bio_full(wpc->ioend->io_bio, len))
 			xfs_chain_bio(wpc->ioend, wbc, bdev, sector);
 		bio_add_page(wpc->ioend->io_bio, page, len, poff);
 	}