1 files changed, 118 insertions, 41 deletions

diff --git a/fs/iomap.c b/fs/iomap.c
index ec15cf2ec696..97cb9d486a7d 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -30,7 +30,6 @@
 #include <linux/task_io_accounting_ops.h>
 #include <linux/dax.h>
 #include <linux/sched/signal.h>
-#include <linux/swap.h>
 
 #include "internal.h"
 
@@ -117,6 +116,12 @@ iomap_page_create(struct inode *inode, struct page *page)
 	atomic_set(&iop->read_count, 0);
 	atomic_set(&iop->write_count, 0);
 	bitmap_zero(iop->uptodate, PAGE_SIZE / SECTOR_SIZE);
+
+	/*
+	 * migrate_page_move_mapping() assumes that pages with private data have
+	 * their count elevated by 1.
+	 */
+	get_page(page);
 	set_page_private(page, (unsigned long)iop);
 	SetPagePrivate(page);
 	return iop;
@@ -133,6 +138,7 @@ iomap_page_release(struct page *page)
 	WARN_ON_ONCE(atomic_read(&iop->write_count));
 	ClearPagePrivate(page);
 	set_page_private(page, 0);
+	put_page(page);
 	kfree(iop);
 }
 
@@ -143,13 +149,14 @@ static void
 iomap_adjust_read_range(struct inode *inode, struct iomap_page *iop,
 		loff_t *pos, loff_t length, unsigned *offp, unsigned *lenp)
 {
+	loff_t orig_pos = *pos;
+	loff_t isize = i_size_read(inode);
 	unsigned block_bits = inode->i_blkbits;
 	unsigned block_size = (1 << block_bits);
 	unsigned poff = offset_in_page(*pos);
 	unsigned plen = min_t(loff_t, PAGE_SIZE - poff, length);
 	unsigned first = poff >> block_bits;
 	unsigned last = (poff + plen - 1) >> block_bits;
-	unsigned end = offset_in_page(i_size_read(inode)) >> block_bits;
 
 	/*
 	 * If the block size is smaller than the page size we need to check the
@@ -184,8 +191,12 @@ iomap_adjust_read_range(struct inode *inode, struct iomap_page *iop,
 	 * handle both halves separately so that we properly zero data in the
 	 * page cache for blocks that are entirely outside of i_size.
 	 */
-	if (first <= end && last > end)
-		plen -= (last - end) * block_size;
+	if (orig_pos <= isize && orig_pos + length > isize) {
+		unsigned end = offset_in_page(isize - 1) >> block_bits;
+
+		if (first <= end && last > end)
+			plen -= (last - end) * block_size;
+	}
 
 	*offp = poff;
 	*lenp = plen;
@@ -263,8 +274,9 @@ iomap_read_end_io(struct bio *bio)
 	int error = blk_status_to_errno(bio->bi_status);
 	struct bio_vec *bvec;
 	int i;
+	struct bvec_iter_all iter_all;
 
-	bio_for_each_segment_all(bvec, bio, i)
+	bio_for_each_segment_all(bvec, bio, i, iter_all)
 		iomap_read_page_end_io(bvec, error);
 	bio_put(bio);
 }
@@ -313,7 +325,7 @@ iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 	 */
 	sector = iomap_sector(iomap, pos);
 	if (ctx->bio && bio_end_sector(ctx->bio) == sector) {
-		if (__bio_try_merge_page(ctx->bio, page, plen, poff))
+		if (__bio_try_merge_page(ctx->bio, page, plen, poff, true))
 			goto done;
 		is_contig = true;
 	}
@@ -344,7 +356,7 @@ iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 		ctx->bio->bi_end_io = iomap_read_end_io;
 	}
 
-	__bio_add_page(ctx->bio, page, plen, poff);
+	bio_add_page(ctx->bio, page, plen, poff);
 done:
 	/*
 	 * Move the caller beyond our range so that it keeps making progress.
@@ -488,16 +500,29 @@ done:
 }
 EXPORT_SYMBOL_GPL(iomap_readpages);
 
+/*
+ * iomap_is_partially_uptodate checks whether blocks within a page are
+ * uptodate or not.
+ *
+ * Returns true if all blocks which correspond to a file portion
+ * we want to read within the page are uptodate.
+ */
 int
 iomap_is_partially_uptodate(struct page *page, unsigned long from,
 		unsigned long count)
 {
 	struct iomap_page *iop = to_iomap_page(page);
 	struct inode *inode = page->mapping->host;
-	unsigned first = from >> inode->i_blkbits;
-	unsigned last = (from + count - 1) >> inode->i_blkbits;
+	unsigned len, first, last;
 	unsigned i;
 
+	/* Limit range to one page */
+	len = min_t(unsigned, PAGE_SIZE - from, count);
+
+	/* First and last blocks in range within page */
+	first = from >> inode->i_blkbits;
+	last = (from + len - 1) >> inode->i_blkbits;
+
 	if (iop) {
 		for (i = first; i <= last; i++)
 			if (!test_bit(i, iop->uptodate))
@@ -546,14 +571,16 @@ iomap_migrate_page(struct address_space *mapping, struct page *newpage,
 {
 	int ret;
 
-	ret = migrate_page_move_mapping(mapping, newpage, page, NULL, mode, 0);
+	ret = migrate_page_move_mapping(mapping, newpage, page, mode, 0);
 	if (ret != MIGRATEPAGE_SUCCESS)
 		return ret;
 
 	if (page_has_private(page)) {
 		ClearPagePrivate(page);
+		get_page(newpage);
 		set_page_private(newpage, page_private(page));
 		set_page_private(page, 0);
+		put_page(page);
 		SetPagePrivate(newpage);
 	}
 
@@ -1057,7 +1084,7 @@ iomap_page_mkwrite_actor(struct inode *inode, loff_t pos, loff_t length,
 	return length;
 }
 
-int iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops)
+vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops)
 {
 	struct page *page = vmf->page;
 	struct inode *inode = file_inode(vmf->vma->vm_file);
@@ -1437,6 +1464,28 @@ struct iomap_dio {
 	};
 };
 
+int iomap_dio_iopoll(struct kiocb *kiocb, bool spin)
+{
+	struct request_queue *q = READ_ONCE(kiocb->private);
+
+	if (!q)
+		return 0;
+	return blk_poll(q, READ_ONCE(kiocb->ki_cookie), spin);
+}
+EXPORT_SYMBOL_GPL(iomap_dio_iopoll);
+
+static void iomap_dio_submit_bio(struct iomap_dio *dio, struct iomap *iomap,
+		struct bio *bio)
+{
+	atomic_inc(&dio->ref);
+
+	if (dio->iocb->ki_flags & IOCB_HIPRI)
+		bio_set_polled(bio, dio->iocb);
+
+	dio->submit.last_queue = bdev_get_queue(iomap->bdev);
+	dio->submit.cookie = submit_bio(bio);
+}
+
 static ssize_t iomap_dio_complete(struct iomap_dio *dio)
 {
 	struct kiocb *iocb = dio->iocb;
@@ -1526,7 +1575,7 @@ static void iomap_dio_bio_end_io(struct bio *bio)
 		if (dio->wait_for_completion) {
 			struct task_struct *waiter = dio->submit.waiter;
 			WRITE_ONCE(dio->submit.waiter, NULL);
-			wake_up_process(waiter);
+			blk_wake_io_task(waiter);
 		} else if (dio->flags & IOMAP_DIO_WRITE) {
 			struct inode *inode = file_inode(dio->iocb->ki_filp);
 
@@ -1542,18 +1591,20 @@ static void iomap_dio_bio_end_io(struct bio *bio)
 	} else {
 		struct bio_vec *bvec;
 		int i;
+		struct bvec_iter_all iter_all;
 
-		bio_for_each_segment_all(bvec, bio, i)
+		bio_for_each_segment_all(bvec, bio, i, iter_all)
 			put_page(bvec->bv_page);
 		bio_put(bio);
 	}
 }
 
-static blk_qc_t
+static void
 iomap_dio_zero(struct iomap_dio *dio, struct iomap *iomap, loff_t pos,
 		unsigned len)
 {
 	struct page *page = ZERO_PAGE(0);
+	int flags = REQ_SYNC | REQ_IDLE;
 	struct bio *bio;
 
 	bio = bio_alloc(GFP_KERNEL, 1);
@@ -1564,10 +1615,8 @@ iomap_dio_zero(struct iomap_dio *dio, struct iomap *iomap, loff_t pos,
 
 	get_page(page);
 	__bio_add_page(bio, page, len, 0);
-	bio_set_op_attrs(bio, REQ_OP_WRITE, REQ_SYNC | REQ_IDLE);
-
-	atomic_inc(&dio->ref);
-	return submit_bio(bio);
+	bio_set_op_attrs(bio, REQ_OP_WRITE, flags);
+	iomap_dio_submit_bio(dio, iomap, bio);
 }
 
 static loff_t
@@ -1581,7 +1630,7 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
 	struct bio *bio;
 	bool need_zeroout = false;
 	bool use_fua = false;
-	int nr_pages, ret;
+	int nr_pages, ret = 0;
 	size_t copied = 0;
 
 	if ((pos | length | align) & ((1 << blkbits) - 1))
@@ -1597,12 +1646,13 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
 
 	if (iomap->flags & IOMAP_F_NEW) {
 		need_zeroout = true;
-	} else {
+	} else if (iomap->type == IOMAP_MAPPED) {
 		/*
-		 * Use a FUA write if we need datasync semantics, this
-		 * is a pure data IO that doesn't require any metadata
-		 * updates and the underlying device supports FUA. This
-		 * allows us to avoid cache flushes on IO completion.
+		 * Use a FUA write if we need datasync semantics, this is a pure
+		 * data IO that doesn't require any metadata updates (including
+		 * after IO completion such as unwritten extent conversion) and
+		 * the underlying device supports FUA. This allows us to avoid
+		 * cache flushes on IO completion.
 		 */
 		if (!(iomap->flags & (IOMAP_F_SHARED|IOMAP_F_DIRTY)) &&
 		    (dio->flags & IOMAP_DIO_WRITE_FUA) &&
@@ -1645,8 +1695,14 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
 
 		ret = bio_iov_iter_get_pages(bio, &iter);
 		if (unlikely(ret)) {
+			/*
+			 * We have to stop part way through an IO. We must fall
+			 * through to the sub-block tail zeroing here, otherwise
+			 * this short IO may expose stale data in the tail of
+			 * the block we haven't written data to.
+			 */
 			bio_put(bio);
-			return copied ? copied : ret;
+			goto zero_tail;
 		}
 
 		n = bio->bi_iter.bi_size;
@@ -1670,20 +1726,24 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
 		copied += n;
 
 		nr_pages = iov_iter_npages(&iter, BIO_MAX_PAGES);
-
-		atomic_inc(&dio->ref);
-
-		dio->submit.last_queue = bdev_get_queue(iomap->bdev);
-		dio->submit.cookie = submit_bio(bio);
+		iomap_dio_submit_bio(dio, iomap, bio);
 	} while (nr_pages);
 
-	if (need_zeroout) {
+	/*
+	 * We need to zeroout the tail of a sub-block write if the extent type
+	 * requires zeroing or the write extends beyond EOF. If we don't zero
+	 * the block tail in the latter case, we can expose stale data via mmap
+	 * reads of the EOF block.
+	 */
+zero_tail:
+	if (need_zeroout ||
+	    ((dio->flags & IOMAP_DIO_WRITE) && pos >= i_size_read(inode))) {
 		/* zero out from the end of the write to the end of the block */
 		pad = pos & (fs_block_size - 1);
 		if (pad)
 			iomap_dio_zero(dio, iomap, pos, fs_block_size - pad);
 	}
-	return copied;
+	return copied ? copied : ret;
 }
 
 static loff_t
@@ -1765,6 +1825,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	loff_t pos = iocb->ki_pos, start = pos;
 	loff_t end = iocb->ki_pos + count - 1, ret = 0;
 	unsigned int flags = IOMAP_DIRECT;
+	bool wait_for_completion = is_sync_kiocb(iocb);
 	struct blk_plug plug;
 	struct iomap_dio *dio;
 
@@ -1784,7 +1845,6 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	dio->end_io = end_io;
 	dio->error = 0;
 	dio->flags = 0;
-	dio->wait_for_completion = is_sync_kiocb(iocb);
 
 	dio->submit.iter = iter;
 	dio->submit.waiter = current;
@@ -1795,7 +1855,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		if (pos >= dio->i_size)
 			goto out_free_dio;
 
-		if (iter->type == ITER_IOVEC)
+		if (iter_is_iovec(iter) && iov_iter_rw(iter) == READ)
 			dio->flags |= IOMAP_DIO_DIRTY;
 	} else {
 		flags |= IOMAP_WRITE;
@@ -1839,7 +1899,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		dio_warn_stale_pagecache(iocb->ki_filp);
 	ret = 0;
 
-	if (iov_iter_rw(iter) == WRITE && !dio->wait_for_completion &&
+	if (iov_iter_rw(iter) == WRITE && !wait_for_completion &&
 	    !inode->i_sb->s_dio_done_wq) {
 		ret = sb_init_dio_done_wq(inode->i_sb);
 		if (ret < 0)
@@ -1855,7 +1915,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		if (ret <= 0) {
 			/* magic error code to fall back to buffered I/O */
 			if (ret == -ENOTBLK) {
-				dio->wait_for_completion = true;
+				wait_for_completion = true;
 				ret = 0;
 			}
 			break;
@@ -1877,8 +1937,27 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	if (dio->flags & IOMAP_DIO_WRITE_FUA)
 		dio->flags &= ~IOMAP_DIO_NEED_SYNC;
 
+	WRITE_ONCE(iocb->ki_cookie, dio->submit.cookie);
+	WRITE_ONCE(iocb->private, dio->submit.last_queue);
+
+	/*
+	 * We are about to drop our additional submission reference, which
+	 * might be the last reference to the dio.  There are three three
+	 * different ways we can progress here:
+	 *
+	 *  (a) If this is the last reference we will always complete and free
+	 *	the dio ourselves.
+	 *  (b) If this is not the last reference, and we serve an asynchronous
+	 *	iocb, we must never touch the dio after the decrement, the
+	 *	I/O completion handler will complete and free it.
+	 *  (c) If this is not the last reference, but we serve a synchronous
+	 *	iocb, the I/O completion handler will wake us up on the drop
+	 *	of the final reference, and we will complete and free it here
+	 *	after we got woken by the I/O completion handler.
+	 */
+	dio->wait_for_completion = wait_for_completion;
 	if (!atomic_dec_and_test(&dio->ref)) {
-		if (!dio->wait_for_completion)
+		if (!wait_for_completion)
 			return -EIOCBQUEUED;
 
 		for (;;) {
@@ -1889,15 +1968,13 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 			if (!(iocb->ki_flags & IOCB_HIPRI) ||
 			    !dio->submit.last_queue ||
 			    !blk_poll(dio->submit.last_queue,
-					 dio->submit.cookie))
+					 dio->submit.cookie, true))
 				io_schedule();
 		}
 		__set_current_state(TASK_RUNNING);
 	}
 
-	ret = iomap_dio_complete(dio);
-
-	return ret;
+	return iomap_dio_complete(dio);
 
 out_free_dio:
 	kfree(dio);