Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Fix error output of boot instance creation failure

   Currently if a boot instance creation fails, instead of printing out
   the name of the instance that failed, it prints "(null)". That is
   because it prints "cur_str" that had already been processed by
   strsep(). Print the saved name instead.

   While at it, print the error code of the failure.

 - Fix use-after-free for same named historgrams

   Histograms can be named so that they can be used in multiple events.
   But if the named histogram has a variable attached, the second event
   that uses the named histogram which duplicates it and needs to free
   the original after duplication leaves the old variable in place and
   still visible. If another histogram uses than variable, it will use
   the stale one which will try to reference the freed duplicate
   histogram and crash the kernel.

   Free the duplicate variables along with the duplicated histogram
   data.

 - Check return value of kthread_run() in event self test

   The events self tests uses a kthread for testing but does not check
   if it succeeded in creating a kthread. If the kthread creation were
   to fail, the code will still try to call kthread_stop() on the error
   returned.

 - Fix race between reading trace_pipe and updating subbuffer size

   If a user is reading the trace_pipe file at the same time they update
   the ring buffer sub-buffer size, can cause the trace_pipe read to
   read stale data. Add trace_access_lock() around updating the ring
   buffer sub-buffer size.

 - Fix eventfs_inode on failure path in creation of the events directory

   In the creation of the "events" directory, if after allocating the
   eventfs_inode a failure is detected, it calls cleanup_ei() which
   calls free_ei(). The free_ei() will test if eventfs_inode being freed
   has no children. It is a bug if it does. But on the failure case of
   the creation of the "events" directory, the children lists have not
   yet been initialized and the free will trigger a warning because
   list_empty() on an uninitialized list returns false.

   Move the initialization into init_ei() where it makes more sense and
   makes sure that a created eventfs_inode has its lists initialized
   upon creation.

 - Check return value of kthread_run() in ftrace direct sample code

   The sample code that shows how to use the ftrace direct calls does
   not test the return of kthread_run() to see if it succeeds. Return a
   failure if the kthread_run() doesn't succeed.

 - Clear user events state on fork in case of alloc failure

   On fork, the child gets a pointer to the parent's user events state.
   It makes a copy of it then updates the child's pointer to it. But if
   the allocation fails, the duplication function leaves the child with
   a pointer to its parent's descriptor. When the child cleans up its
   data, it will free the parent's descriptor while the parent is still
   using it.

   In the duplication function, set the child's user_event_mm to NULL
   before testing if the allocation succeeded, and when it exits it will
   not free the parent's descriptor.

 - Fix retry exhaustion in simple ring buffer reader swap

   simple_ring_buffer_swap_reader_page() starts with retry set to 8 and
   post-decrements it only after a failed link replacement. On the final
   attempt, a successful replacement leaves retry at zero, while a
   failed replacement leaves it at -1.

   But the check for success expects the retry value to be non-zero and
   exits with an error on zero. This is the opposite result. Fix it.

 - Fail nicely when the remote swap_reader_page() returns an error

   Currently, if the swap_reader_page() of a remote buffer fails, it
   triggers a WARN_ON_ONCE() and continues normally. Instead, have it
   exit with an error and a pr_warn() print instead of a full WARNING.

* tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Stop remote reader update when page swap fails
  tracing: Fix retry exhaustion in simple ring buffer reader swap
  tracing/user_events: Clear copied tracing state before fork duplication
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify
  eventfs: Initialize ei->children and ei->list in init_ei()
  tracing: Fix use-after-free in trace_pipe read on sub-buffer order change
  tracing: Fix crash passing ERR_PTR to kthread_stop()
  tracing: Fix use-after-free with same-name named triggers
  tracing: Fix logged instance name on creation failure

1 files changed, 955 insertions, 0 deletions

diff --git a/block/fops.c b/block/fops.c
new file mode 100644
index 000000000..2ce7c6c47
--- /dev/null
+++ b/block/fops.c
@@ -0,0 +1,955 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 1991, 1992  Linus Torvalds
+ * Copyright (C) 2001  Andrea Arcangeli <andrea@suse.de> SuSE
+ * Copyright (C) 2016 - 2020 Christoph Hellwig
+ */
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/blkdev.h>
+#include <linux/blk-integrity.h>
+#include <linux/buffer_head.h>
+#include <linux/mpage.h>
+#include <linux/uio.h>
+#include <linux/namei.h>
+#include <linux/task_io_accounting_ops.h>
+#include <linux/falloc.h>
+#include <linux/suspend.h>
+#include <linux/fs.h>
+#include <linux/iomap.h>
+#include <linux/module.h>
+#include <linux/io_uring/cmd.h>
+#include "blk.h"
+
+static inline struct inode *bdev_file_inode(struct file *file)
+{
+	return file->f_mapping->host;
+}
+
+static blk_opf_t dio_bio_write_op(struct kiocb *iocb)
+{
+	blk_opf_t opf = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE;
+
+	/* avoid the need for a I/O completion work item */
+	if (iocb_is_dsync(iocb))
+		opf |= REQ_FUA;
+	return opf;
+}
+
+static bool blkdev_dio_invalid(struct block_device *bdev, struct kiocb *iocb,
+				struct iov_iter *iter)
+{
+	return (iocb->ki_pos | iov_iter_count(iter)) &
+			(bdev_logical_block_size(bdev) - 1);
+}
+
+static inline int blkdev_iov_iter_get_pages(struct bio *bio,
+		struct iov_iter *iter, struct block_device *bdev)
+{
+	return bio_iov_iter_get_pages(bio, iter, bdev_dma_alignment(bdev),
+			bdev_logical_block_size(bdev) - 1);
+}
+
+#define DIO_INLINE_BIO_VECS 4
+
+static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb,
+		struct iov_iter *iter, struct block_device *bdev,
+		unsigned int nr_pages)
+{
+	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;
+
+	if (nr_pages <= DIO_INLINE_BIO_VECS)
+		vecs = inline_vecs;
+	else {
+		vecs = kmalloc_objs(struct bio_vec, nr_pages);
+		if (!vecs)
+			return -ENOMEM;
+	}
+
+	if (iov_iter_rw(iter) == READ) {
+		bio_init(&bio, bdev, vecs, nr_pages, REQ_OP_READ);
+		if (user_backed_iter(iter))
+			should_dirty = true;
+	} else {
+		bio_init(&bio, bdev, vecs, nr_pages, dio_bio_write_op(iocb));
+	}
+	bio.bi_iter.bi_sector = pos >> SECTOR_SHIFT;
+	bio.bi_write_hint = file_inode(iocb->ki_filp)->i_write_hint;
+	bio.bi_write_stream = iocb->ki_write_stream;
+	bio.bi_ioprio = iocb->ki_ioprio;
+	if (iocb->ki_flags & IOCB_ATOMIC)
+		bio.bi_opf |= REQ_ATOMIC;
+
+	ret = blkdev_iov_iter_get_pages(&bio, iter, bdev);
+	if (unlikely(ret))
+		goto out;
+	ret = bio.bi_iter.bi_size;
+
+	if (iov_iter_rw(iter) == WRITE)
+		task_io_account_write(ret);
+
+	if (iocb->ki_flags & IOCB_NOWAIT)
+		bio.bi_opf |= REQ_NOWAIT;
+
+	submit_bio_wait(&bio);
+
+	bio_release_pages(&bio, should_dirty);
+	if (unlikely(bio.bi_status))
+		ret = blk_status_to_errno(bio.bi_status);
+
+out:
+	if (vecs != inline_vecs)
+		kfree(vecs);
+
+	bio_uninit(&bio);
+
+	return ret;
+}
+
+enum {
+	DIO_SHOULD_DIRTY	= 1,
+	DIO_IS_SYNC		= 2,
+};
+
+struct blkdev_dio {
+	union {
+		struct kiocb		*iocb;
+		struct task_struct	*waiter;
+	};
+	size_t			size;
+	atomic_t		ref;
+	unsigned int		flags;
+	struct bio		bio ____cacheline_aligned_in_smp;
+};
+
+static struct bio_set blkdev_dio_pool;
+
+static void blkdev_bio_end_io(struct bio *bio)
+{
+	struct blkdev_dio *dio = bio->bi_private;
+	bool should_dirty = dio->flags & DIO_SHOULD_DIRTY;
+	bool is_sync = dio->flags & DIO_IS_SYNC;
+
+	if (bio->bi_status && !dio->bio.bi_status)
+		dio->bio.bi_status = bio->bi_status;
+
+	if (bio_integrity(bio))
+		bio_integrity_unmap_user(bio);
+
+	if (atomic_dec_and_test(&dio->ref)) {
+		if (!is_sync) {
+			struct kiocb *iocb = dio->iocb;
+			ssize_t ret;
+
+			WRITE_ONCE(iocb->private, NULL);
+
+			if (likely(!dio->bio.bi_status)) {
+				ret = dio->size;
+				iocb->ki_pos += ret;
+			} else {
+				ret = blk_status_to_errno(dio->bio.bi_status);
+			}
+
+			dio->iocb->ki_complete(iocb, ret);
+			bio_put(&dio->bio);
+		} else {
+			struct task_struct *waiter = dio->waiter;
+
+			WRITE_ONCE(dio->waiter, NULL);
+			blk_wake_io_task(waiter);
+		}
+	}
+
+	if (should_dirty) {
+		bio_check_pages_dirty(bio);
+	} else {
+		bio_release_pages(bio, false);
+		bio_put(bio);
+	}
+}
+
+static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
+		struct block_device *bdev, unsigned int nr_pages)
+{
+	struct blk_plug plug;
+	struct blkdev_dio *dio;
+	struct bio *bio;
+	bool is_read = (iov_iter_rw(iter) == READ), is_sync;
+	blk_opf_t opf = is_read ? REQ_OP_READ : dio_bio_write_op(iocb);
+	loff_t pos = iocb->ki_pos;
+	int ret = 0;
+
+	bio = bio_alloc_bioset(bdev, nr_pages, opf, GFP_KERNEL,
+			       &blkdev_dio_pool);
+	dio = container_of(bio, struct blkdev_dio, bio);
+	atomic_set(&dio->ref, 1);
+	/*
+	 * Grab an extra reference to ensure the dio structure which is embedded
+	 * into the first bio stays around.
+	 */
+	bio_get(bio);
+
+	is_sync = is_sync_kiocb(iocb);
+	if (is_sync) {
+		dio->flags = DIO_IS_SYNC;
+		dio->waiter = current;
+	} else {
+		dio->flags = 0;
+		dio->iocb = iocb;
+	}
+
+	dio->size = 0;
+	if (is_read && user_backed_iter(iter))
+		dio->flags |= DIO_SHOULD_DIRTY;
+
+	blk_start_plug(&plug);
+
+	for (;;) {
+		bio->bi_iter.bi_sector = pos >> SECTOR_SHIFT;
+		bio->bi_write_hint = file_inode(iocb->ki_filp)->i_write_hint;
+		bio->bi_write_stream = iocb->ki_write_stream;
+		bio->bi_private = dio;
+		bio->bi_end_io = blkdev_bio_end_io;
+		bio->bi_ioprio = iocb->ki_ioprio;
+
+		ret = blkdev_iov_iter_get_pages(bio, iter, bdev);
+		if (unlikely(ret)) {
+			bio_endio_status(bio, errno_to_blk_status(ret));
+			break;
+		}
+		if (iocb->ki_flags & IOCB_NOWAIT) {
+			/*
+			 * This is nonblocking IO, and we need to allocate
+			 * another bio if we have data left to map. As we
+			 * cannot guarantee that one of the sub bios will not
+			 * fail getting issued FOR NOWAIT and as error results
+			 * are coalesced across all of them, be safe and ask for
+			 * a retry of this from blocking context.
+			 */
+			if (unlikely(iov_iter_count(iter))) {
+				ret = -EAGAIN;
+				goto fail;
+			}
+			bio->bi_opf |= REQ_NOWAIT;
+		}
+		if (iocb->ki_flags & IOCB_HAS_METADATA) {
+			ret = bio_integrity_map_iter(bio, iocb->private);
+			if (unlikely(ret)) {
+				bio_endio_status(bio, errno_to_blk_status(ret));
+				break;
+			}
+		}
+
+		if (is_read) {
+			if (dio->flags & DIO_SHOULD_DIRTY)
+				bio_set_pages_dirty(bio);
+		} else {
+			task_io_account_write(bio->bi_iter.bi_size);
+		}
+		dio->size += bio->bi_iter.bi_size;
+		pos += bio->bi_iter.bi_size;
+
+		nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS);
+		if (!nr_pages) {
+			submit_bio(bio);
+			break;
+		}
+		atomic_inc(&dio->ref);
+		submit_bio(bio);
+		bio = bio_alloc(bdev, nr_pages, opf, GFP_KERNEL);
+	}
+
+	blk_finish_plug(&plug);
+
+	if (!is_sync)
+		return -EIOCBQUEUED;
+
+	for (;;) {
+		set_current_state(TASK_UNINTERRUPTIBLE);
+		if (!READ_ONCE(dio->waiter))
+			break;
+		blk_io_schedule();
+	}
+	__set_current_state(TASK_RUNNING);
+
+	if (!ret)
+		ret = blk_status_to_errno(dio->bio.bi_status);
+	if (likely(!ret))
+		ret = dio->size;
+
+	bio_put(&dio->bio);
+	return ret;
+fail:
+	bio_release_pages(bio, false);
+	bio_clear_flag(bio, BIO_REFFED);
+	bio_put(bio);
+	blk_finish_plug(&plug);
+	return ret;
+}
+
+static void blkdev_bio_end_io_async(struct bio *bio)
+{
+	struct blkdev_dio *dio = container_of(bio, struct blkdev_dio, bio);
+	struct kiocb *iocb = dio->iocb;
+	ssize_t ret;
+
+	WRITE_ONCE(iocb->private, NULL);
+
+	if (likely(!bio->bi_status)) {
+		ret = dio->size;
+		iocb->ki_pos += ret;
+	} else {
+		ret = blk_status_to_errno(bio->bi_status);
+	}
+
+	if (bio_integrity(bio))
+		bio_integrity_unmap_user(bio);
+
+	iocb->ki_complete(iocb, ret);
+
+	if (dio->flags & DIO_SHOULD_DIRTY) {
+		bio_check_pages_dirty(bio);
+	} else {
+		bio_release_pages(bio, false);
+		bio_put(bio);
+	}
+}
+
+static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb,
+					struct iov_iter *iter,
+					struct block_device *bdev,
+					unsigned int nr_pages)
+{
+	bool is_read = iov_iter_rw(iter) == READ;
+	blk_opf_t opf = is_read ? REQ_OP_READ : dio_bio_write_op(iocb);
+	struct blkdev_dio *dio;
+	struct bio *bio;
+	loff_t pos = iocb->ki_pos;
+	int ret = 0;
+
+	bio = bio_alloc_bioset(bdev, nr_pages, opf, GFP_KERNEL,
+			       &blkdev_dio_pool);
+	dio = container_of(bio, struct blkdev_dio, bio);
+	dio->flags = 0;
+	dio->iocb = iocb;
+	bio->bi_iter.bi_sector = pos >> SECTOR_SHIFT;
+	bio->bi_write_hint = file_inode(iocb->ki_filp)->i_write_hint;
+	bio->bi_write_stream = iocb->ki_write_stream;
+	bio->bi_end_io = blkdev_bio_end_io_async;
+	bio->bi_ioprio = iocb->ki_ioprio;
+
+	/*
+	 * Users don't rely on the iterator being in any particular
+	 * state for async I/O returning -EIOCBQUEUED, hence we can
+	 * avoid expensive iov_iter_advance(). Bypass
+	 * bio_iov_iter_get_pages() and set the bvec directly.
+	 */
+	if (!bio_iov_iter_set(bio, iter)) {
+		ret = blkdev_iov_iter_get_pages(bio, iter, bdev);
+		if (unlikely(ret))
+			goto out_bio_put;
+	}
+	dio->size = bio->bi_iter.bi_size;
+
+	if (is_read) {
+		if (user_backed_iter(iter)) {
+			dio->flags |= DIO_SHOULD_DIRTY;
+			bio_set_pages_dirty(bio);
+		}
+	} else {
+		task_io_account_write(bio->bi_iter.bi_size);
+	}
+
+	if (iocb->ki_flags & IOCB_HAS_METADATA) {
+		ret = bio_integrity_map_iter(bio, iocb->private);
+		WRITE_ONCE(iocb->private, NULL);
+		if (unlikely(ret))
+			goto out_bio_put;
+	}
+
+	if (iocb->ki_flags & IOCB_ATOMIC)
+		bio->bi_opf |= REQ_ATOMIC;
+
+	if (iocb->ki_flags & IOCB_NOWAIT)
+		bio->bi_opf |= REQ_NOWAIT;
+
+	if (iocb->ki_flags & IOCB_HIPRI) {
+		bio->bi_opf |= REQ_POLLED;
+		submit_bio(bio);
+		WRITE_ONCE(iocb->private, bio);
+	} else {
+		submit_bio(bio);
+	}
+	return -EIOCBQUEUED;
+
+out_bio_put:
+	bio_put(bio);
+	return ret;
+}
+
+static ssize_t blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
+{
+	struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host);
+	unsigned int nr_pages;
+
+	if (!iov_iter_count(iter))
+		return 0;
+
+	if (blkdev_dio_invalid(bdev, iocb, iter))
+		return -EINVAL;
+
+	if (iov_iter_rw(iter) == WRITE) {
+		u16 max_write_streams = bdev_max_write_streams(bdev);
+
+		if (iocb->ki_write_stream) {
+			if (iocb->ki_write_stream > max_write_streams)
+				return -EINVAL;
+		} else if (max_write_streams) {
+			enum rw_hint write_hint =
+				file_inode(iocb->ki_filp)->i_write_hint;
+
+			/*
+			 * Just use the write hint as write stream for block
+			 * device writes.  This assumes no file system is
+			 * mounted that would use the streams differently.
+			 */
+			if (write_hint <= max_write_streams)
+				iocb->ki_write_stream = write_hint;
+		}
+	}
+
+	nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS + 1);
+	if (likely(nr_pages <= BIO_MAX_VECS &&
+		   !(iocb->ki_flags & IOCB_HAS_METADATA))) {
+		if (is_sync_kiocb(iocb))
+			return __blkdev_direct_IO_simple(iocb, iter, bdev,
+							nr_pages);
+		return __blkdev_direct_IO_async(iocb, iter, bdev, nr_pages);
+	} else if (iocb->ki_flags & IOCB_ATOMIC) {
+		return -EINVAL;
+	}
+	return __blkdev_direct_IO(iocb, iter, bdev, bio_max_segs(nr_pages));
+}
+
+static int blkdev_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
+		unsigned int flags, struct iomap *iomap, struct iomap *srcmap)
+{
+	struct block_device *bdev = I_BDEV(inode);
+	loff_t isize = i_size_read(inode);
+
+	if (offset >= isize)
+		return -EIO;
+
+	iomap->bdev = bdev;
+	iomap->offset = ALIGN_DOWN(offset, bdev_logical_block_size(bdev));
+	iomap->type = IOMAP_MAPPED;
+	iomap->addr = iomap->offset;
+	iomap->length = isize - iomap->offset;
+	iomap->flags |= IOMAP_F_BUFFER_HEAD; /* noop for !CONFIG_BUFFER_HEAD */
+	return 0;
+}
+
+static DEFINE_IOMAP_ITER_NEXT(blkdev_iomap_next, blkdev_iomap_begin);
+
+static const struct iomap_ops blkdev_iomap_ops = {
+	.iomap_next		= blkdev_iomap_next,
+};
+
+#ifdef CONFIG_BUFFER_HEAD
+static int blkdev_get_block(struct inode *inode, sector_t iblock,
+		struct buffer_head *bh, int create)
+{
+	bh->b_bdev = I_BDEV(inode);
+	bh->b_blocknr = iblock;
+	set_buffer_mapped(bh);
+	return 0;
+}
+
+/*
+ * We cannot call mpage_writepages() as it does not take the buffer lock.
+ * We must use block_write_full_folio() directly which holds the buffer
+ * lock.  The buffer lock provides the synchronisation with writeback
+ * that filesystems rely on when they use the blockdev's mapping.
+ */
+static int blkdev_writepages(struct address_space *mapping,
+		struct writeback_control *wbc)
+{
+	struct folio *folio = NULL;
+	struct blk_plug plug;
+	int err;
+
+	blk_start_plug(&plug);
+	while ((folio = writeback_iter(mapping, wbc, folio, &err)))
+		err = block_write_full_folio(folio, wbc, blkdev_get_block);
+	blk_finish_plug(&plug);
+
+	return err;
+}
+
+static int blkdev_read_folio(struct file *file, struct folio *folio)
+{
+	return block_read_full_folio(folio, blkdev_get_block);
+}
+
+static void blkdev_readahead(struct readahead_control *rac)
+{
+	mpage_readahead(rac, blkdev_get_block);
+}
+
+const struct address_space_operations def_blk_aops = {
+	.dirty_folio	= block_dirty_folio,
+	.invalidate_folio = block_invalidate_folio,
+	.read_folio	= blkdev_read_folio,
+	.readahead	= blkdev_readahead,
+	.writepages	= blkdev_writepages,
+	.migrate_folio	= buffer_migrate_folio_norefs,
+	.is_dirty_writeback = buffer_check_dirty_writeback,
+};
+#else /* CONFIG_BUFFER_HEAD */
+static int blkdev_read_folio(struct file *file, struct folio *folio)
+{
+	iomap_bio_read_folio(folio, &blkdev_iomap_ops);
+	return 0;
+}
+
+static void blkdev_readahead(struct readahead_control *rac)
+{
+	iomap_bio_readahead(rac, &blkdev_iomap_ops);
+}
+
+static ssize_t blkdev_writeback_range(struct iomap_writepage_ctx *wpc,
+		struct folio *folio, u64 offset, unsigned int len, u64 end_pos)
+{
+	loff_t isize = i_size_read(wpc->inode);
+
+	if (WARN_ON_ONCE(offset >= isize))
+		return -EIO;
+
+	if (offset < wpc->iomap.offset ||
+	    offset >= wpc->iomap.offset + wpc->iomap.length) {
+		int error;
+
+		error = blkdev_iomap_begin(wpc->inode, offset, isize - offset,
+				IOMAP_WRITE, &wpc->iomap, NULL);
+		if (error)
+			return error;
+	}
+
+	return iomap_add_to_ioend(wpc, folio, offset, end_pos, len);
+}
+
+static const struct iomap_writeback_ops blkdev_writeback_ops = {
+	.writeback_range	= blkdev_writeback_range,
+	.writeback_submit	= iomap_ioend_writeback_submit,
+};
+
+static int blkdev_writepages(struct address_space *mapping,
+		struct writeback_control *wbc)
+{
+	struct iomap_writepage_ctx wpc = {
+		.inode		= mapping->host,
+		.wbc		= wbc,
+		.ops		= &blkdev_writeback_ops
+	};
+
+	return iomap_writepages(&wpc);
+}
+
+const struct address_space_operations def_blk_aops = {
+	.dirty_folio	= filemap_dirty_folio,
+	.release_folio		= iomap_release_folio,
+	.invalidate_folio	= iomap_invalidate_folio,
+	.read_folio		= blkdev_read_folio,
+	.readahead		= blkdev_readahead,
+	.writepages		= blkdev_writepages,
+	.is_partially_uptodate  = iomap_is_partially_uptodate,
+	.error_remove_folio	= generic_error_remove_folio,
+	.migrate_folio		= filemap_migrate_folio,
+};
+#endif /* CONFIG_BUFFER_HEAD */
+
+/*
+ * for a block special file file_inode(file)->i_size is zero
+ * so we compute the size by hand (just as in block_read/write above)
+ */
+static loff_t blkdev_llseek(struct file *file, loff_t offset, int whence)
+{
+	struct inode *bd_inode = bdev_file_inode(file);
+	loff_t retval;
+
+	inode_lock(bd_inode);
+	retval = fixed_size_llseek(file, offset, whence, i_size_read(bd_inode));
+	inode_unlock(bd_inode);
+	return retval;
+}
+
+static int blkdev_fsync(struct file *filp, loff_t start, loff_t end,
+		int datasync)
+{
+	struct block_device *bdev = I_BDEV(filp->f_mapping->host);
+	int error;
+
+	error = file_write_and_wait_range(filp, start, end);
+	if (error)
+		return error;
+
+	/*
+	 * There is no need to serialise calls to blkdev_issue_flush with
+	 * i_mutex and doing so causes performance issues with concurrent
+	 * O_SYNC writers to a block device.
+	 */
+	error = blkdev_issue_flush(bdev);
+	if (error == -EOPNOTSUPP)
+		error = 0;
+
+	return error;
+}
+
+/**
+ * file_to_blk_mode - get block open flags from file flags
+ * @file: file whose open flags should be converted
+ *
+ * Look at file open flags and generate corresponding block open flags from
+ * them. The function works both for file just being open (e.g. during ->open
+ * callback) and for file that is already open. This is actually non-trivial
+ * (see comment in the function).
+ */
+blk_mode_t file_to_blk_mode(struct file *file)
+{
+	blk_mode_t mode = 0;
+
+	if (file->f_mode & FMODE_READ)
+		mode |= BLK_OPEN_READ;
+	if (file->f_mode & FMODE_WRITE)
+		mode |= BLK_OPEN_WRITE;
+	/*
+	 * do_dentry_open() clears O_EXCL from f_flags, use file->private_data
+	 * to determine whether the open was exclusive for already open files.
+	 */
+	if (file->private_data)
+		mode |= BLK_OPEN_EXCL;
+	else if (file->f_flags & O_EXCL)
+		mode |= BLK_OPEN_EXCL;
+	if (file->f_flags & O_NDELAY)
+		mode |= BLK_OPEN_NDELAY;
+
+	/*
+	 * If all bits in O_ACCMODE set (aka O_RDWR | O_WRONLY), the floppy
+	 * driver has historically allowed ioctls as if the file was opened for
+	 * writing, but does not allow and actual reads or writes.
+	 */
+	if ((file->f_flags & O_ACCMODE) == (O_RDWR | O_WRONLY))
+		mode |= BLK_OPEN_WRITE_IOCTL;
+
+	return mode;
+}
+
+static int blkdev_open(struct inode *inode, struct file *filp)
+{
+	struct block_device *bdev;
+	blk_mode_t mode;
+	int ret;
+
+	mode = file_to_blk_mode(filp);
+	/* Use the file as the holder. */
+	if (mode & BLK_OPEN_EXCL)
+		filp->private_data = filp;
+	ret = bdev_permission(inode->i_rdev, mode, filp->private_data);
+	if (ret)
+		return ret;
+
+	bdev = blkdev_get_no_open(inode->i_rdev, true);
+	if (!bdev)
+		return -ENXIO;
+
+	if (bdev_can_atomic_write(bdev))
+		filp->f_mode |= FMODE_CAN_ATOMIC_WRITE;
+	if (blk_get_integrity(bdev->bd_disk))
+		filp->f_mode |= FMODE_HAS_METADATA;
+
+	ret = bdev_open(bdev, mode, filp->private_data, NULL, filp);
+	if (ret)
+		blkdev_put_no_open(bdev);
+	return ret;
+}
+
+static int blkdev_release(struct inode *inode, struct file *filp)
+{
+	bdev_release(filp);
+	return 0;
+}
+
+static ssize_t
+blkdev_direct_write(struct kiocb *iocb, struct iov_iter *from)
+{
+	size_t count = iov_iter_count(from);
+	ssize_t written;
+
+	written = kiocb_invalidate_pages(iocb, count);
+	if (written) {
+		if (written == -EBUSY)
+			return 0;
+		return written;
+	}
+
+	written = blkdev_direct_IO(iocb, from);
+	if (written > 0) {
+		kiocb_invalidate_post_direct_write(iocb, count);
+		iocb->ki_pos += written;
+		count -= written;
+	}
+	if (written != -EIOCBQUEUED)
+		iov_iter_revert(from, count - iov_iter_count(from));
+	return written;
+}
+
+static ssize_t blkdev_buffered_write(struct kiocb *iocb, struct iov_iter *from)
+{
+	return iomap_file_buffered_write(iocb, from, &blkdev_iomap_ops, NULL,
+			NULL);
+}
+
+/*
+ * Write data to the block device.  Only intended for the block device itself
+ * and the raw driver which basically is a fake block device.
+ *
+ * Does not take i_mutex for the write and thus is not for general purpose
+ * use.
+ */
+static ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *bd_inode = bdev_file_inode(file);
+	struct block_device *bdev = I_BDEV(bd_inode);
+	bool atomic = iocb->ki_flags & IOCB_ATOMIC;
+	loff_t size = bdev_nr_bytes(bdev);
+	size_t shorted = 0;
+	ssize_t ret;
+
+	if (bdev_read_only(bdev))
+		return -EPERM;
+
+	if (IS_SWAPFILE(bd_inode) && !is_hibernate_resume_dev(bd_inode->i_rdev))
+		return -ETXTBSY;
+
+	if (!iov_iter_count(from))
+		return 0;
+
+	if (iocb->ki_pos >= size)
+		return -ENOSPC;
+
+	if ((iocb->ki_flags & (IOCB_NOWAIT | IOCB_DIRECT)) == IOCB_NOWAIT)
+		return -EOPNOTSUPP;
+
+	if (atomic) {
+		ret = generic_atomic_write_valid(iocb, from);
+		if (ret)
+			return ret;
+	}
+
+	size -= iocb->ki_pos;
+	if (iov_iter_count(from) > size) {
+		if (atomic)
+			return -EINVAL;
+		shorted = iov_iter_count(from) - size;
+		iov_iter_truncate(from, size);
+	}
+
+	ret = file_update_time(file);
+	if (ret)
+		return ret;
+
+	if (iocb->ki_flags & IOCB_DIRECT) {
+		ret = blkdev_direct_write(iocb, from);
+		if (ret >= 0 && iov_iter_count(from))
+			ret = direct_write_fallback(iocb, from, ret,
+					blkdev_buffered_write(iocb, from));
+	} else {
+		/*
+		 * Take i_rwsem and invalidate_lock to avoid racing with
+		 * set_blocksize changing i_blkbits/folio order and punching
+		 * out the pagecache.
+		 */
+		inode_lock_shared(bd_inode);
+		ret = blkdev_buffered_write(iocb, from);
+		inode_unlock_shared(bd_inode);
+	}
+
+	if (ret > 0)
+		ret = generic_write_sync(iocb, ret);
+	iov_iter_reexpand(from, iov_iter_count(from) + shorted);
+	return ret;
+}
+
+static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+	struct inode *bd_inode = bdev_file_inode(iocb->ki_filp);
+	struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host);
+	loff_t size = bdev_nr_bytes(bdev);
+	loff_t pos = iocb->ki_pos;
+	size_t shorted = 0;
+	ssize_t ret = 0;
+	size_t count;
+
+	if (unlikely(pos + iov_iter_count(to) > size)) {
+		if (pos >= size)
+			return 0;
+		size -= pos;
+		shorted = iov_iter_count(to) - size;
+		iov_iter_truncate(to, size);
+	}
+
+	count = iov_iter_count(to);
+	if (!count)
+		goto reexpand; /* skip atime */
+
+	if (iocb->ki_flags & IOCB_DIRECT) {
+		ret = kiocb_write_and_wait(iocb, count);
+		if (ret < 0)
+			goto reexpand;
+		file_accessed(iocb->ki_filp);
+
+		ret = blkdev_direct_IO(iocb, to);
+		if (ret > 0) {
+			iocb->ki_pos += ret;
+			count -= ret;
+		}
+		if (ret != -EIOCBQUEUED)
+			iov_iter_revert(to, count - iov_iter_count(to));
+		if (ret < 0 || !count)
+			goto reexpand;
+	}
+
+	/*
+	 * Take i_rwsem and invalidate_lock to avoid racing with set_blocksize
+	 * changing i_blkbits/folio order and punching out the pagecache.
+	 */
+	inode_lock_shared(bd_inode);
+	ret = filemap_read(iocb, to, ret);
+	inode_unlock_shared(bd_inode);
+
+reexpand:
+	if (unlikely(shorted))
+		iov_iter_reexpand(to, iov_iter_count(to) + shorted);
+	return ret;
+}
+
+#define	BLKDEV_FALLOC_FL_SUPPORTED					\
+		(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |		\
+		 FALLOC_FL_ZERO_RANGE | FALLOC_FL_WRITE_ZEROES)
+
+static long blkdev_fallocate(struct file *file, int mode, loff_t start,
+			     loff_t len)
+{
+	struct inode *inode = bdev_file_inode(file);
+	struct block_device *bdev = I_BDEV(inode);
+	loff_t end = start + len - 1;
+	loff_t isize;
+	unsigned int flags;
+	int error;
+
+	/* Fail if we don't recognize the flags. */
+	if (mode & ~BLKDEV_FALLOC_FL_SUPPORTED)
+		return -EOPNOTSUPP;
+	/*
+	 * Don't allow writing zeroes if the device does not enable the
+	 * unmap write zeroes operation.
+	 */
+	if ((mode & FALLOC_FL_WRITE_ZEROES) &&
+	    !bdev_write_zeroes_unmap_sectors(bdev))
+		return -EOPNOTSUPP;
+
+	/* Don't go off the end of the device. */
+	isize = bdev_nr_bytes(bdev);
+	if (start >= isize)
+		return -EINVAL;
+	if (end >= isize) {
+		if (mode & FALLOC_FL_KEEP_SIZE) {
+			len = isize - start;
+			end = start + len - 1;
+		} else
+			return -EINVAL;
+	}
+
+	/*
+	 * Don't allow IO that isn't aligned to logical block size.
+	 */
+	if ((start | len) & (bdev_logical_block_size(bdev) - 1))
+		return -EINVAL;
+
+	inode_lock(inode);
+	filemap_invalidate_lock(inode->i_mapping);
+
+	switch (mode) {
+	case FALLOC_FL_ZERO_RANGE:
+	case FALLOC_FL_ZERO_RANGE | FALLOC_FL_KEEP_SIZE:
+		flags = BLKDEV_ZERO_NOUNMAP;
+		break;
+	case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE:
+		flags = BLKDEV_ZERO_NOFALLBACK;
+		break;
+	case FALLOC_FL_WRITE_ZEROES:
+		flags = 0;
+		break;
+	default:
+		error = -EOPNOTSUPP;
+		goto fail;
+	}
+
+	/*
+	 * Invalidate the page cache, including dirty pages, for valid
+	 * de-allocate mode calls to fallocate().
+	 */
+	error = truncate_bdev_range(bdev, file_to_blk_mode(file), start, end);
+	if (error)
+		goto fail;
+
+	error = blkdev_issue_zeroout(bdev, start >> SECTOR_SHIFT,
+				     len >> SECTOR_SHIFT, GFP_KERNEL, flags);
+ fail:
+	filemap_invalidate_unlock(inode->i_mapping);
+	inode_unlock(inode);
+	return error;
+}
+
+static int blkdev_mmap_prepare(struct vm_area_desc *desc)
+{
+	struct file *file = desc->file;
+
+	if (bdev_read_only(I_BDEV(bdev_file_inode(file))))
+		return generic_file_readonly_mmap_prepare(desc);
+
+	return generic_file_mmap_prepare(desc);
+}
+
+const struct file_operations def_blk_fops = {
+	.open		= blkdev_open,
+	.release	= blkdev_release,
+	.llseek		= blkdev_llseek,
+	.read_iter	= blkdev_read_iter,
+	.write_iter	= blkdev_write_iter,
+	.iopoll		= iocb_bio_iopoll,
+	.mmap_prepare	= blkdev_mmap_prepare,
+	.fsync		= blkdev_fsync,
+	.unlocked_ioctl	= blkdev_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= compat_blkdev_ioctl,
+#endif
+	.splice_read	= filemap_splice_read,
+	.splice_write	= iter_file_splice_write,
+	.fallocate	= blkdev_fallocate,
+	.uring_cmd	= blkdev_uring_cmd,
+	.fop_flags	= FOP_BUFFER_RASYNC | FOP_DONTCACHE,
+};
+
+static __init int blkdev_init(void)
+{
+	return bioset_init(&blkdev_dio_pool, 4,
+				offsetof(struct blkdev_dio, bio),
+				BIOSET_NEED_BVECS|BIOSET_PERCPU_CACHE);
+}
+module_init(blkdev_init);