1 files changed, 105 insertions, 39 deletions

diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 5f225881176b..a7a597c727e6 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -36,17 +36,34 @@
 #include "acl.h"
 #include "truncate.h"
 
-static bool ext4_dio_supported(struct inode *inode)
+/*
+ * Returns %true if the given DIO request should be attempted with DIO, or
+ * %false if it should fall back to buffered I/O.
+ *
+ * DIO isn't well specified; when it's unsupported (either due to the request
+ * being misaligned, or due to the file not supporting DIO at all), filesystems
+ * either fall back to buffered I/O or return EINVAL.  For files that don't use
+ * any special features like encryption or verity, ext4 has traditionally
+ * returned EINVAL for misaligned DIO.  iomap_dio_rw() uses this convention too.
+ * In this case, we should attempt the DIO, *not* fall back to buffered I/O.
+ *
+ * In contrast, in cases where DIO is unsupported due to ext4 features, ext4
+ * traditionally falls back to buffered I/O.
+ *
+ * This function implements the traditional ext4 behavior in all these cases.
+ */
+static bool ext4_should_use_dio(struct kiocb *iocb, struct iov_iter *iter)
 {
-	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))
+	struct inode *inode = file_inode(iocb->ki_filp);
+	u32 dio_align = ext4_dio_alignment(inode);
+
+	if (dio_align == 0)
 		return false;
-	return true;
+
+	if (dio_align == 1)
+		return true;
+
+	return IS_ALIGNED(iocb->ki_pos | iov_iter_alignment(iter), dio_align);
 }
 
 static ssize_t ext4_dio_read_iter(struct kiocb *iocb, struct iov_iter *to)
@@ -61,7 +78,7 @@ static ssize_t ext4_dio_read_iter(struct kiocb *iocb, struct iov_iter *to)
 		inode_lock_shared(inode);
 	}
 
-	if (!ext4_dio_supported(inode)) {
+	if (!ext4_should_use_dio(iocb, to)) {
 		inode_unlock_shared(inode);
 		/*
 		 * Fallback to buffered I/O if the operation being performed on
@@ -74,8 +91,7 @@ static ssize_t ext4_dio_read_iter(struct kiocb *iocb, struct iov_iter *to)
 		return generic_file_read_iter(iocb, to);
 	}
 
-	ret = iomap_dio_rw(iocb, to, &ext4_iomap_ops, NULL,
-			   is_sync_kiocb(iocb));
+	ret = iomap_dio_rw(iocb, to, &ext4_iomap_ops, NULL, 0, NULL, 0);
 	inode_unlock_shared(inode);
 
 	file_accessed(iocb->ki_filp);
@@ -145,10 +161,9 @@ static int ext4_release_file(struct inode *inode, struct file *filp)
 	/* if we are the last writer on the inode, drop the block reservation */
 	if ((filp->f_mode & FMODE_WRITE) &&
 			(atomic_read(&inode->i_writecount) == 1) &&
-		        !EXT4_I(inode)->i_reserved_data_blocks)
-	{
+			!EXT4_I(inode)->i_reserved_data_blocks) {
 		down_write(&EXT4_I(inode)->i_data_sem);
-		ext4_discard_preallocations(inode);
+		ext4_discard_preallocations(inode, 0);
 		up_write(&EXT4_I(inode)->i_data_sem);
 	}
 	if (is_dx(inode) && filp->private_data)
@@ -267,7 +282,7 @@ static ssize_t ext4_buffered_write_iter(struct kiocb *iocb,
 		goto out;
 
 	current->backing_dev_info = inode_to_bdi(inode);
-	ret = generic_perform_write(iocb->ki_filp, from, iocb->ki_pos);
+	ret = generic_perform_write(iocb, from);
 	current->backing_dev_info = NULL;
 
 out:
@@ -287,6 +302,7 @@ static ssize_t ext4_handle_inode_extension(struct inode *inode, loff_t offset,
 	bool truncate = false;
 	u8 blkbits = inode->i_blkbits;
 	ext4_lblk_t written_blk, end_blk;
+	int ret;
 
 	/*
 	 * Note that EXT4_I(inode)->i_disksize can get extended up to
@@ -327,8 +343,14 @@ static ssize_t ext4_handle_inode_extension(struct inode *inode, loff_t offset,
 		goto truncate;
 	}
 
-	if (ext4_update_inode_size(inode, offset + written))
-		ext4_mark_inode_dirty(handle, inode);
+	if (ext4_update_inode_size(inode, offset + written)) {
+		ret = ext4_mark_inode_dirty(handle, inode);
+		if (unlikely(ret)) {
+			written = ret;
+			ext4_journal_stop(handle);
+			goto truncate;
+		}
+	}
 
 	/*
 	 * We may need to truncate allocated but not written blocks beyond EOF.
@@ -364,15 +386,32 @@ truncate:
 static int ext4_dio_write_end_io(struct kiocb *iocb, ssize_t size,
 				 int error, unsigned int flags)
 {
-	loff_t offset = iocb->ki_pos;
+	loff_t pos = 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);
+	if (size && flags & IOMAP_DIO_UNWRITTEN) {
+		error = ext4_convert_unwritten_extents(NULL, inode, pos, size);
+		if (error < 0)
+			return error;
+	}
+	/*
+	 * If we are extending the file, we have to update i_size here before
+	 * page cache gets invalidated in iomap_dio_rw(). Otherwise racing
+	 * buffered reads could zero out too much from page cache pages. Update
+	 * of on-disk size will happen later in ext4_dio_write_iter() where
+	 * we have enough information to also perform orphan list handling etc.
+	 * Note that we perform all extending writes synchronously under
+	 * i_rwsem held exclusively so i_size update is safe here in that case.
+	 * If the write was not extending, we cannot see pos > i_size here
+	 * because operations reducing i_size like truncate wait for all
+	 * outstanding DIO before updating i_size.
+	 */
+	pos += size;
+	if (pos > i_size_read(inode))
+		i_size_write(inode, pos);
 
 	return 0;
 }
@@ -421,6 +460,10 @@ restart:
 	 */
 	if (*ilock_shared && (!IS_NOSEC(inode) || *extend ||
 	     !ext4_overwrite_io(inode, offset, count))) {
+		if (iocb->ki_flags & IOCB_NOWAIT) {
+			ret = -EAGAIN;
+			goto out;
+		}
 		inode_unlock_shared(inode);
 		*ilock_shared = false;
 		inode_lock(inode);
@@ -483,7 +526,7 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	}
 
 	/* Fallback to buffered I/O if the inode does not support direct I/O. */
-	if (!ext4_dio_supported(inode)) {
+	if (!ext4_should_use_dio(iocb, from)) {
 		if (ilock_shared)
 			inode_unlock_shared(inode);
 		else
@@ -495,6 +538,18 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (ret <= 0)
 		return ret;
 
+	/* if we're going to block and IOCB_NOWAIT is set, return -EAGAIN */
+	if ((iocb->ki_flags & IOCB_NOWAIT) && (unaligned_io || extend)) {
+		ret = -EAGAIN;
+		goto out;
+	}
+	/*
+	 * Make sure inline data cannot be created anymore since we are going
+	 * to allocate blocks for DIO. We know the inode does not have any
+	 * inline data now because ext4_dio_supported() checked for that.
+	 */
+	ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
+
 	offset = iocb->ki_pos;
 	count = ret;
 
@@ -530,7 +585,10 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	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);
+			   (unaligned_io || extend) ? IOMAP_DIO_FORCE_WAIT : 0,
+			   NULL, 0);
+	if (ret == -ENOTBLK)
+		ret = 0;
 
 	if (extend)
 		ret = ext4_handle_inode_extension(inode, offset, ret, count);
@@ -638,8 +696,8 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 #endif
 	if (iocb->ki_flags & IOCB_DIRECT)
 		return ext4_dio_write_iter(iocb, from);
-
-	return ext4_buffered_write_iter(iocb, from);
+	else
+		return ext4_buffered_write_iter(iocb, from);
 }
 
 #ifdef CONFIG_FS_DAX
@@ -666,22 +724,23 @@ static vm_fault_t ext4_dax_huge_fault(struct vm_fault *vmf,
 	 */
 	bool write = (vmf->flags & FAULT_FLAG_WRITE) &&
 		(vmf->vma->vm_flags & VM_SHARED);
+	struct address_space *mapping = vmf->vma->vm_file->f_mapping;
 	pfn_t pfn;
 
 	if (write) {
 		sb_start_pagefault(sb);
 		file_update_time(vmf->vma->vm_file);
-		down_read(&EXT4_I(inode)->i_mmap_sem);
+		filemap_invalidate_lock_shared(mapping);
 retry:
 		handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
 					       EXT4_DATA_TRANS_BLOCKS(sb));
 		if (IS_ERR(handle)) {
-			up_read(&EXT4_I(inode)->i_mmap_sem);
+			filemap_invalidate_unlock_shared(mapping);
 			sb_end_pagefault(sb);
 			return VM_FAULT_SIGBUS;
 		}
 	} else {
-		down_read(&EXT4_I(inode)->i_mmap_sem);
+		filemap_invalidate_lock_shared(mapping);
 	}
 	result = dax_iomap_fault(vmf, pe_size, &pfn, &error, &ext4_iomap_ops);
 	if (write) {
@@ -693,10 +752,10 @@ retry:
 		/* Handling synchronous page fault? */
 		if (result & VM_FAULT_NEEDDSYNC)
 			result = dax_finish_sync_fault(vmf, pe_size, pfn);
-		up_read(&EXT4_I(inode)->i_mmap_sem);
+		filemap_invalidate_unlock_shared(mapping);
 		sb_end_pagefault(sb);
 	} else {
-		up_read(&EXT4_I(inode)->i_mmap_sem);
+		filemap_invalidate_unlock_shared(mapping);
 	}
 
 	return result;
@@ -718,7 +777,7 @@ static const struct vm_operations_struct ext4_dax_vm_ops = {
 #endif
 
 static const struct vm_operations_struct ext4_file_vm_ops = {
-	.fault		= ext4_filemap_fault,
+	.fault		= filemap_fault,
 	.map_pages	= filemap_map_pages,
 	.page_mkwrite   = ext4_page_mkwrite,
 };
@@ -758,13 +817,13 @@ static int ext4_sample_last_mounted(struct super_block *sb,
 	handle_t *handle;
 	int err;
 
-	if (likely(sbi->s_mount_flags & EXT4_MF_MNTDIR_SAMPLED))
+	if (likely(ext4_test_mount_flag(sb, EXT4_MF_MNTDIR_SAMPLED)))
 		return 0;
 
 	if (sb_rdonly(sb) || !sb_start_intwrite_trylock(sb))
 		return 0;
 
-	sbi->s_mount_flags |= EXT4_MF_MNTDIR_SAMPLED;
+	ext4_set_mount_flag(sb, EXT4_MF_MNTDIR_SAMPLED);
 	/*
 	 * Sample where the filesystem has been mounted and
 	 * store it in the superblock for sysadmin convenience
@@ -784,12 +843,16 @@ static int ext4_sample_last_mounted(struct super_block *sb,
 	if (IS_ERR(handle))
 		goto out;
 	BUFFER_TRACE(sbi->s_sbh, "get_write_access");
-	err = ext4_journal_get_write_access(handle, sbi->s_sbh);
+	err = ext4_journal_get_write_access(handle, sb, sbi->s_sbh,
+					    EXT4_JTR_NONE);
 	if (err)
 		goto out_journal;
-	strlcpy(sbi->s_es->s_last_mounted, cp,
+	lock_buffer(sbi->s_sbh);
+	strncpy(sbi->s_es->s_last_mounted, cp,
 		sizeof(sbi->s_es->s_last_mounted));
-	ext4_handle_dirty_super(handle, sb);
+	ext4_superblock_csum_set(sb);
+	unlock_buffer(sbi->s_sbh);
+	ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh);
 out_journal:
 	ext4_journal_stop(handle);
 out:
@@ -797,7 +860,7 @@ out:
 	return err;
 }
 
-static int ext4_file_open(struct inode * inode, struct file * filp)
+static int ext4_file_open(struct inode *inode, struct file *filp)
 {
 	int ret;
 
@@ -826,7 +889,7 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
 			return ret;
 	}
 
-	filp->f_mode |= FMODE_NOWAIT;
+	filp->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC;
 	return dquot_file_open(inode, filp);
 }
 
@@ -872,6 +935,7 @@ const struct file_operations ext4_file_operations = {
 	.llseek		= ext4_llseek,
 	.read_iter	= ext4_file_read_iter,
 	.write_iter	= ext4_file_write_iter,
+	.iopoll		= iocb_bio_iopoll,
 	.unlocked_ioctl = ext4_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= ext4_compat_ioctl,
@@ -894,5 +958,7 @@ const struct inode_operations ext4_file_inode_operations = {
 	.get_acl	= ext4_get_acl,
 	.set_acl	= ext4_set_acl,
 	.fiemap		= ext4_fiemap,
+	.fileattr_get	= ext4_fileattr_get,
+	.fileattr_set	= ext4_fileattr_set,
 };