1 files changed, 446 insertions, 86 deletions

diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 8d2bbcc2d813..0d624250a62b 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -29,10 +29,58 @@
 #include <linux/pagevec.h>
 #include <linux/uio.h>
 #include <linux/mman.h>
+#include <linux/backing-dev.h>
 #include "ext4.h"
 #include "ext4_jbd2.h"
 #include "xattr.h"
 #include "acl.h"
+#include "truncate.h"
+
+static bool ext4_dio_supported(struct inode *inode)
+{
+	if (IS_ENABLED(CONFIG_FS_ENCRYPTION) && IS_ENCRYPTED(inode))
+		return false;
+	if (fsverity_active(inode))
+		return false;
+	if (ext4_should_journal_data(inode))
+		return false;
+	if (ext4_has_inline_data(inode))
+		return false;
+	return true;
+}
+
+static ssize_t ext4_dio_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+	ssize_t ret;
+	struct inode *inode = file_inode(iocb->ki_filp);
+
+	if (iocb->ki_flags & IOCB_NOWAIT) {
+		if (!inode_trylock_shared(inode))
+			return -EAGAIN;
+	} else {
+		inode_lock_shared(inode);
+	}
+
+	if (!ext4_dio_supported(inode)) {
+		inode_unlock_shared(inode);
+		/*
+		 * Fallback to buffered I/O if the operation being performed on
+		 * the inode is not supported by direct I/O. The IOCB_DIRECT
+		 * flag needs to be cleared here in order to ensure that the
+		 * direct I/O path within generic_file_read_iter() is not
+		 * taken.
+		 */
+		iocb->ki_flags &= ~IOCB_DIRECT;
+		return generic_file_read_iter(iocb, to);
+	}
+
+	ret = iomap_dio_rw(iocb, to, &ext4_iomap_ops, NULL,
+			   is_sync_kiocb(iocb));
+	inode_unlock_shared(inode);
+
+	file_accessed(iocb->ki_filp);
+	return ret;
+}
 
 #ifdef CONFIG_FS_DAX
 static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
@@ -40,9 +88,10 @@ static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
 	struct inode *inode = file_inode(iocb->ki_filp);
 	ssize_t ret;
 
-	if (!inode_trylock_shared(inode)) {
-		if (iocb->ki_flags & IOCB_NOWAIT)
+	if (iocb->ki_flags & IOCB_NOWAIT) {
+		if (!inode_trylock_shared(inode))
 			return -EAGAIN;
+	} else {
 		inode_lock_shared(inode);
 	}
 	/*
@@ -64,16 +113,21 @@ static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
 
 static ssize_t ext4_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
-	if (unlikely(ext4_forced_shutdown(EXT4_SB(file_inode(iocb->ki_filp)->i_sb))))
+	struct inode *inode = file_inode(iocb->ki_filp);
+
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
 		return -EIO;
 
 	if (!iov_iter_count(to))
 		return 0; /* skip atime */
 
 #ifdef CONFIG_FS_DAX
-	if (IS_DAX(file_inode(iocb->ki_filp)))
+	if (IS_DAX(inode))
 		return ext4_dax_read_iter(iocb, to);
 #endif
+	if (iocb->ki_flags & IOCB_DIRECT)
+		return ext4_dio_read_iter(iocb, to);
+
 	return generic_file_read_iter(iocb, to);
 }
 
@@ -103,13 +157,6 @@ static int ext4_release_file(struct inode *inode, struct file *filp)
 	return 0;
 }
 
-static void ext4_unwritten_wait(struct inode *inode)
-{
-	wait_queue_head_t *wq = ext4_ioend_wq(inode);
-
-	wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_unwritten) == 0));
-}
-
 /*
  * This tests whether the IO in question is block-aligned or not.
  * Ext4 utilizes unwritten extents when hole-filling during direct IO, and they
@@ -119,19 +166,25 @@ static void ext4_unwritten_wait(struct inode *inode)
  * threads are at work on the same unwritten block, they must be synchronized
  * or one thread will zero the other's data, causing corruption.
  */
-static int
-ext4_unaligned_aio(struct inode *inode, struct iov_iter *from, loff_t pos)
+static bool
+ext4_unaligned_io(struct inode *inode, struct iov_iter *from, loff_t pos)
 {
 	struct super_block *sb = inode->i_sb;
-	int blockmask = sb->s_blocksize - 1;
-
-	if (pos >= ALIGN(i_size_read(inode), sb->s_blocksize))
-		return 0;
+	unsigned long blockmask = sb->s_blocksize - 1;
 
 	if ((pos | iov_iter_alignment(from)) & blockmask)
-		return 1;
+		return true;
 
-	return 0;
+	return false;
+}
+
+static bool
+ext4_extending_io(struct inode *inode, loff_t offset, size_t len)
+{
+	if (offset + len > i_size_read(inode) ||
+	    offset + len > EXT4_I(inode)->i_disksize)
+		return true;
+	return false;
 }
 
 /* Is IO overwriting allocated and initialized blocks? */
@@ -157,18 +210,19 @@ static bool ext4_overwrite_io(struct inode *inode, loff_t pos, loff_t len)
 	return err == blklen && (map.m_flags & EXT4_MAP_MAPPED);
 }
 
-static ssize_t ext4_write_checks(struct kiocb *iocb, struct iov_iter *from)
+static ssize_t ext4_generic_write_checks(struct kiocb *iocb,
+					 struct iov_iter *from)
 {
 	struct inode *inode = file_inode(iocb->ki_filp);
 	ssize_t ret;
 
+	if (unlikely(IS_IMMUTABLE(inode)))
+		return -EPERM;
+
 	ret = generic_write_checks(iocb, from);
 	if (ret <= 0)
 		return ret;
 
-	if (unlikely(IS_IMMUTABLE(inode)))
-		return -EPERM;
-
 	/*
 	 * If we have encountered a bitmap-format file, the size limit
 	 * is smaller than s_maxbytes, which is for extent-mapped files.
@@ -180,110 +234,413 @@ static ssize_t ext4_write_checks(struct kiocb *iocb, struct iov_iter *from)
 			return -EFBIG;
 		iov_iter_truncate(from, sbi->s_bitmap_maxbytes - iocb->ki_pos);
 	}
+
 	return iov_iter_count(from);
 }
 
-#ifdef CONFIG_FS_DAX
-static ssize_t
-ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
+static ssize_t ext4_write_checks(struct kiocb *iocb, struct iov_iter *from)
+{
+	ssize_t ret, count;
+
+	count = ext4_generic_write_checks(iocb, from);
+	if (count <= 0)
+		return count;
+
+	ret = file_modified(iocb->ki_filp);
+	if (ret)
+		return ret;
+	return count;
+}
+
+static ssize_t ext4_buffered_write_iter(struct kiocb *iocb,
+					struct iov_iter *from)
 {
-	struct inode *inode = file_inode(iocb->ki_filp);
 	ssize_t ret;
+	struct inode *inode = file_inode(iocb->ki_filp);
 
-	if (!inode_trylock(inode)) {
-		if (iocb->ki_flags & IOCB_NOWAIT)
-			return -EAGAIN;
-		inode_lock(inode);
-	}
+	if (iocb->ki_flags & IOCB_NOWAIT)
+		return -EOPNOTSUPP;
+
+	inode_lock(inode);
 	ret = ext4_write_checks(iocb, from);
 	if (ret <= 0)
 		goto out;
-	ret = file_remove_privs(iocb->ki_filp);
-	if (ret)
-		goto out;
-	ret = file_update_time(iocb->ki_filp);
-	if (ret)
-		goto out;
 
-	ret = dax_iomap_rw(iocb, from, &ext4_iomap_ops);
+	current->backing_dev_info = inode_to_bdi(inode);
+	ret = generic_perform_write(iocb->ki_filp, from, iocb->ki_pos);
+	current->backing_dev_info = NULL;
+
 out:
 	inode_unlock(inode);
-	if (ret > 0)
+	if (likely(ret > 0)) {
+		iocb->ki_pos += ret;
 		ret = generic_write_sync(iocb, ret);
+	}
+
 	return ret;
 }
-#endif
 
-static ssize_t
-ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
+static ssize_t ext4_handle_inode_extension(struct inode *inode, loff_t offset,
+					   ssize_t written, size_t count)
 {
-	struct inode *inode = file_inode(iocb->ki_filp);
-	int o_direct = iocb->ki_flags & IOCB_DIRECT;
-	int unaligned_aio = 0;
-	int overwrite = 0;
-	ssize_t ret;
+	handle_t *handle;
+	bool truncate = false;
+	u8 blkbits = inode->i_blkbits;
+	ext4_lblk_t written_blk, end_blk;
 
-	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
-		return -EIO;
+	/*
+	 * Note that EXT4_I(inode)->i_disksize can get extended up to
+	 * inode->i_size while the I/O was running due to writeback of delalloc
+	 * blocks. But, the code in ext4_iomap_alloc() is careful to use
+	 * zeroed/unwritten extents if this is possible; thus we won't leave
+	 * uninitialized blocks in a file even if we didn't succeed in writing
+	 * as much as we intended.
+	 */
+	WARN_ON_ONCE(i_size_read(inode) < EXT4_I(inode)->i_disksize);
+	if (offset + count <= EXT4_I(inode)->i_disksize) {
+		/*
+		 * We need to ensure that the inode is removed from the orphan
+		 * list if it has been added prematurely, due to writeback of
+		 * delalloc blocks.
+		 */
+		if (!list_empty(&EXT4_I(inode)->i_orphan) && inode->i_nlink) {
+			handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
+
+			if (IS_ERR(handle)) {
+				ext4_orphan_del(NULL, inode);
+				return PTR_ERR(handle);
+			}
+
+			ext4_orphan_del(handle, inode);
+			ext4_journal_stop(handle);
+		}
 
-#ifdef CONFIG_FS_DAX
-	if (IS_DAX(inode))
-		return ext4_dax_write_iter(iocb, from);
-#endif
+		return written;
+	}
 
-	if (!inode_trylock(inode)) {
-		if (iocb->ki_flags & IOCB_NOWAIT)
-			return -EAGAIN;
-		inode_lock(inode);
+	if (written < 0)
+		goto truncate;
+
+	handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
+	if (IS_ERR(handle)) {
+		written = PTR_ERR(handle);
+		goto truncate;
 	}
 
-	ret = ext4_write_checks(iocb, from);
+	if (ext4_update_inode_size(inode, offset + written))
+		ext4_mark_inode_dirty(handle, inode);
+
+	/*
+	 * We may need to truncate allocated but not written blocks beyond EOF.
+	 */
+	written_blk = ALIGN(offset + written, 1 << blkbits);
+	end_blk = ALIGN(offset + count, 1 << blkbits);
+	if (written_blk < end_blk && ext4_can_truncate(inode))
+		truncate = true;
+
+	/*
+	 * Remove the inode from the orphan list if it has been extended and
+	 * everything went OK.
+	 */
+	if (!truncate && inode->i_nlink)
+		ext4_orphan_del(handle, inode);
+	ext4_journal_stop(handle);
+
+	if (truncate) {
+truncate:
+		ext4_truncate_failed_write(inode);
+		/*
+		 * If the truncate operation failed early, then the inode may
+		 * still be on the orphan list. In that case, we need to try
+		 * remove the inode from the in-memory linked list.
+		 */
+		if (inode->i_nlink)
+			ext4_orphan_del(NULL, inode);
+	}
+
+	return written;
+}
+
+static int ext4_dio_write_end_io(struct kiocb *iocb, ssize_t size,
+				 int error, unsigned int flags)
+{
+	loff_t offset = iocb->ki_pos;
+	struct inode *inode = file_inode(iocb->ki_filp);
+
+	if (error)
+		return error;
+
+	if (size && flags & IOMAP_DIO_UNWRITTEN)
+		return ext4_convert_unwritten_extents(NULL, inode,
+						      offset, size);
+
+	return 0;
+}
+
+static const struct iomap_dio_ops ext4_dio_write_ops = {
+	.end_io = ext4_dio_write_end_io,
+};
+
+/*
+ * The intention here is to start with shared lock acquired then see if any
+ * condition requires an exclusive inode lock. If yes, then we restart the
+ * whole operation by releasing the shared lock and acquiring exclusive lock.
+ *
+ * - For unaligned_io we never take shared lock as it may cause data corruption
+ *   when two unaligned IO tries to modify the same block e.g. while zeroing.
+ *
+ * - For extending writes case we don't take the shared lock, since it requires
+ *   updating inode i_disksize and/or orphan handling with exclusive lock.
+ *
+ * - shared locking will only be true mostly with overwrites. Otherwise we will
+ *   switch to exclusive i_rwsem lock.
+ */
+static ssize_t ext4_dio_write_checks(struct kiocb *iocb, struct iov_iter *from,
+				     bool *ilock_shared, bool *extend)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file_inode(file);
+	loff_t offset;
+	size_t count;
+	ssize_t ret;
+
+restart:
+	ret = ext4_generic_write_checks(iocb, from);
 	if (ret <= 0)
 		goto out;
 
+	offset = iocb->ki_pos;
+	count = ret;
+	if (ext4_extending_io(inode, offset, count))
+		*extend = true;
 	/*
-	 * Unaligned direct AIO must be serialized among each other as zeroing
-	 * of partial blocks of two competing unaligned AIOs can result in data
-	 * corruption.
+	 * Determine whether the IO operation will overwrite allocated
+	 * and initialized blocks.
+	 * We need exclusive i_rwsem for changing security info
+	 * in file_modified().
 	 */
-	if (o_direct && ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) &&
-	    !is_sync_kiocb(iocb) &&
-	    ext4_unaligned_aio(inode, from, iocb->ki_pos)) {
-		unaligned_aio = 1;
-		ext4_unwritten_wait(inode);
+	if (*ilock_shared && (!IS_NOSEC(inode) || *extend ||
+	     !ext4_overwrite_io(inode, offset, count))) {
+		inode_unlock_shared(inode);
+		*ilock_shared = false;
+		inode_lock(inode);
+		goto restart;
 	}
 
-	iocb->private = &overwrite;
-	/* Check whether we do a DIO overwrite or not */
-	if (o_direct && !unaligned_aio) {
-		if (ext4_overwrite_io(inode, iocb->ki_pos, iov_iter_count(from))) {
-			if (ext4_should_dioread_nolock(inode))
-				overwrite = 1;
-		} else if (iocb->ki_flags & IOCB_NOWAIT) {
-			ret = -EAGAIN;
-			goto out;
+	ret = file_modified(file);
+	if (ret < 0)
+		goto out;
+
+	return count;
+out:
+	if (*ilock_shared)
+		inode_unlock_shared(inode);
+	else
+		inode_unlock(inode);
+	return ret;
+}
+
+static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+	ssize_t ret;
+	handle_t *handle;
+	struct inode *inode = file_inode(iocb->ki_filp);
+	loff_t offset = iocb->ki_pos;
+	size_t count = iov_iter_count(from);
+	const struct iomap_ops *iomap_ops = &ext4_iomap_ops;
+	bool extend = false, unaligned_io = false;
+	bool ilock_shared = true;
+
+	/*
+	 * We initially start with shared inode lock unless it is
+	 * unaligned IO which needs exclusive lock anyways.
+	 */
+	if (ext4_unaligned_io(inode, from, offset)) {
+		unaligned_io = true;
+		ilock_shared = false;
+	}
+	/*
+	 * Quick check here without any i_rwsem lock to see if it is extending
+	 * IO. A more reliable check is done in ext4_dio_write_checks() with
+	 * proper locking in place.
+	 */
+	if (offset + count > i_size_read(inode))
+		ilock_shared = false;
+
+	if (iocb->ki_flags & IOCB_NOWAIT) {
+		if (ilock_shared) {
+			if (!inode_trylock_shared(inode))
+				return -EAGAIN;
+		} else {
+			if (!inode_trylock(inode))
+				return -EAGAIN;
 		}
+	} else {
+		if (ilock_shared)
+			inode_lock_shared(inode);
+		else
+			inode_lock(inode);
+	}
+
+	/* Fallback to buffered I/O if the inode does not support direct I/O. */
+	if (!ext4_dio_supported(inode)) {
+		if (ilock_shared)
+			inode_unlock_shared(inode);
+		else
+			inode_unlock(inode);
+		return ext4_buffered_write_iter(iocb, from);
 	}
 
-	ret = __generic_file_write_iter(iocb, from);
+	ret = ext4_dio_write_checks(iocb, from, &ilock_shared, &extend);
+	if (ret <= 0)
+		return ret;
+
+	offset = iocb->ki_pos;
+	count = ret;
+
 	/*
-	 * Unaligned direct AIO must be the only IO in flight. Otherwise
-	 * overlapping aligned IO after unaligned might result in data
+	 * Unaligned direct IO must be serialized among each other as zeroing
+	 * of partial blocks of two competing unaligned IOs can result in data
 	 * corruption.
+	 *
+	 * So we make sure we don't allow any unaligned IO in flight.
+	 * For IOs where we need not wait (like unaligned non-AIO DIO),
+	 * below inode_dio_wait() may anyway become a no-op, since we start
+	 * with exclusive lock.
 	 */
-	if (ret == -EIOCBQUEUED && unaligned_aio)
-		ext4_unwritten_wait(inode);
-	inode_unlock(inode);
+	if (unaligned_io)
+		inode_dio_wait(inode);
 
-	if (ret > 0)
-		ret = generic_write_sync(iocb, ret);
+	if (extend) {
+		handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
+		if (IS_ERR(handle)) {
+			ret = PTR_ERR(handle);
+			goto out;
+		}
+
+		ret = ext4_orphan_add(handle, inode);
+		if (ret) {
+			ext4_journal_stop(handle);
+			goto out;
+		}
+
+		ext4_journal_stop(handle);
+	}
+
+	if (ilock_shared)
+		iomap_ops = &ext4_iomap_overwrite_ops;
+	ret = iomap_dio_rw(iocb, from, iomap_ops, &ext4_dio_write_ops,
+			   is_sync_kiocb(iocb) || unaligned_io || extend);
+
+	if (extend)
+		ret = ext4_handle_inode_extension(inode, offset, ret, count);
+
+out:
+	if (ilock_shared)
+		inode_unlock_shared(inode);
+	else
+		inode_unlock(inode);
+
+	if (ret >= 0 && iov_iter_count(from)) {
+		ssize_t err;
+		loff_t endbyte;
+
+		offset = iocb->ki_pos;
+		err = ext4_buffered_write_iter(iocb, from);
+		if (err < 0)
+			return err;
+
+		/*
+		 * We need to ensure that the pages within the page cache for
+		 * the range covered by this I/O are written to disk and
+		 * invalidated. This is in attempt to preserve the expected
+		 * direct I/O semantics in the case we fallback to buffered I/O
+		 * to complete off the I/O request.
+		 */
+		ret += err;
+		endbyte = offset + err - 1;
+		err = filemap_write_and_wait_range(iocb->ki_filp->f_mapping,
+						   offset, endbyte);
+		if (!err)
+			invalidate_mapping_pages(iocb->ki_filp->f_mapping,
+						 offset >> PAGE_SHIFT,
+						 endbyte >> PAGE_SHIFT);
+	}
 
 	return ret;
+}
+
+#ifdef CONFIG_FS_DAX
+static ssize_t
+ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+	ssize_t ret;
+	size_t count;
+	loff_t offset;
+	handle_t *handle;
+	bool extend = false;
+	struct inode *inode = file_inode(iocb->ki_filp);
+
+	if (iocb->ki_flags & IOCB_NOWAIT) {
+		if (!inode_trylock(inode))
+			return -EAGAIN;
+	} else {
+		inode_lock(inode);
+	}
+
+	ret = ext4_write_checks(iocb, from);
+	if (ret <= 0)
+		goto out;
+
+	offset = iocb->ki_pos;
+	count = iov_iter_count(from);
+
+	if (offset + count > EXT4_I(inode)->i_disksize) {
+		handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
+		if (IS_ERR(handle)) {
+			ret = PTR_ERR(handle);
+			goto out;
+		}
+
+		ret = ext4_orphan_add(handle, inode);
+		if (ret) {
+			ext4_journal_stop(handle);
+			goto out;
+		}
+
+		extend = true;
+		ext4_journal_stop(handle);
+	}
+
+	ret = dax_iomap_rw(iocb, from, &ext4_iomap_ops);
 
+	if (extend)
+		ret = ext4_handle_inode_extension(inode, offset, ret, count);
 out:
 	inode_unlock(inode);
+	if (ret > 0)
+		ret = generic_write_sync(iocb, ret);
 	return ret;
 }
+#endif
+
+static ssize_t
+ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return -EIO;
+
+#ifdef CONFIG_FS_DAX
+	if (IS_DAX(inode))
+		return ext4_dax_write_iter(iocb, from);
+#endif
+	if (iocb->ki_flags & IOCB_DIRECT)
+		return ext4_dio_write_iter(iocb, from);
+
+	return ext4_buffered_write_iter(iocb, from);
+}
 
 #ifdef CONFIG_FS_DAX
 static vm_fault_t ext4_dax_huge_fault(struct vm_fault *vmf,
@@ -494,12 +851,14 @@ loff_t ext4_llseek(struct file *file, loff_t offset, int whence)
 						maxbytes, i_size_read(inode));
 	case SEEK_HOLE:
 		inode_lock_shared(inode);
-		offset = iomap_seek_hole(inode, offset, &ext4_iomap_ops);
+		offset = iomap_seek_hole(inode, offset,
+					 &ext4_iomap_report_ops);
 		inode_unlock_shared(inode);
 		break;
 	case SEEK_DATA:
 		inode_lock_shared(inode);
-		offset = iomap_seek_data(inode, offset, &ext4_iomap_ops);
+		offset = iomap_seek_data(inode, offset,
+					 &ext4_iomap_report_ops);
 		inode_unlock_shared(inode);
 		break;
 	}
@@ -513,6 +872,7 @@ const struct file_operations ext4_file_operations = {
 	.llseek		= ext4_llseek,
 	.read_iter	= ext4_file_read_iter,
 	.write_iter	= ext4_file_write_iter,
+	.iopoll		= iomap_dio_iopoll,
 	.unlocked_ioctl = ext4_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= ext4_compat_ioctl,