1 files changed, 104 insertions, 140 deletions

diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 64848b595b2..8695f70af1e 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -23,6 +23,7 @@
 #include <linux/jbd2.h>
 #include <linux/mount.h>
 #include <linux/path.h>
+#include <linux/aio.h>
 #include <linux/quotaops.h>
 #include <linux/pagevec.h>
 #include "ext4.h"
@@ -56,7 +57,7 @@ static int ext4_release_file(struct inode *inode, struct file *filp)
 	return 0;
 }
 
-void ext4_unwritten_wait(struct inode *inode)
+static void ext4_unwritten_wait(struct inode *inode)
 {
 	wait_queue_head_t *wq = ext4_ioend_wq(inode);
 
@@ -73,132 +74,126 @@ void ext4_unwritten_wait(struct inode *inode)
  * or one thread will zero the other's data, causing corruption.
  */
 static int
-ext4_unaligned_aio(struct inode *inode, const struct iovec *iov,
-		   unsigned long nr_segs, loff_t pos)
+ext4_unaligned_aio(struct inode *inode, struct iov_iter *from, loff_t pos)
 {
 	struct super_block *sb = inode->i_sb;
 	int blockmask = sb->s_blocksize - 1;
-	size_t count = iov_length(iov, nr_segs);
-	loff_t final_size = pos + count;
 
-	if (pos >= inode->i_size)
+	if (pos >= i_size_read(inode))
 		return 0;
 
-	if ((pos & blockmask) || (final_size & blockmask))
+	if ((pos | iov_iter_alignment(from)) & blockmask)
 		return 1;
 
 	return 0;
 }
 
 static ssize_t
-ext4_file_dio_write(struct kiocb *iocb, const struct iovec *iov,
-		    unsigned long nr_segs, loff_t pos)
+ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
-	struct inode *inode = file->f_mapping->host;
+	struct inode *inode = file_inode(iocb->ki_filp);
+	struct mutex *aio_mutex = NULL;
 	struct blk_plug plug;
-	int unaligned_aio = 0;
-	ssize_t ret;
+	int o_direct = file->f_flags & O_DIRECT;
 	int overwrite = 0;
-	size_t length = iov_length(iov, nr_segs);
-
-	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) &&
-	    !is_sync_kiocb(iocb))
-		unaligned_aio = ext4_unaligned_aio(inode, iov, nr_segs, pos);
+	size_t length = iov_iter_count(from);
+	ssize_t ret;
+	loff_t pos = iocb->ki_pos;
 
-	/* Unaligned direct AIO must be serialized; see comment above */
-	if (unaligned_aio) {
-		mutex_lock(ext4_aio_mutex(inode));
+	/*
+	 * Unaligned direct AIO must be serialized; see comment above
+	 * In the case of O_APPEND, assume that we must always serialize
+	 */
+	if (o_direct &&
+	    ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) &&
+	    !is_sync_kiocb(iocb) &&
+	    (file->f_flags & O_APPEND ||
+	     ext4_unaligned_aio(inode, from, pos))) {
+		aio_mutex = ext4_aio_mutex(inode);
+		mutex_lock(aio_mutex);
 		ext4_unwritten_wait(inode);
 	}
 
-	BUG_ON(iocb->ki_pos != pos);
-
 	mutex_lock(&inode->i_mutex);
-	blk_start_plug(&plug);
-
-	iocb->private = &overwrite;
+	if (file->f_flags & O_APPEND)
+		iocb->ki_pos = pos = i_size_read(inode);
 
-	/* check whether we do a DIO overwrite or not */
-	if (ext4_should_dioread_nolock(inode) && !unaligned_aio &&
-	    !file->f_mapping->nrpages && pos + length <= i_size_read(inode)) {
-		struct ext4_map_blocks map;
-		unsigned int blkbits = inode->i_blkbits;
-		int err, len;
+	/*
+	 * If we have encountered a bitmap-format file, the size limit
+	 * is smaller than s_maxbytes, which is for extent-mapped files.
+	 */
+	if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
+		struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 
-		map.m_lblk = pos >> blkbits;
-		map.m_len = (EXT4_BLOCK_ALIGN(pos + length, blkbits) >> blkbits)
-			- map.m_lblk;
-		len = map.m_len;
+		if ((pos > sbi->s_bitmap_maxbytes) ||
+		    (pos == sbi->s_bitmap_maxbytes && length > 0)) {
+			mutex_unlock(&inode->i_mutex);
+			ret = -EFBIG;
+			goto errout;
+		}
 
-		err = ext4_map_blocks(NULL, inode, &map, 0);
-		/*
-		 * 'err==len' means that all of blocks has been preallocated no
-		 * matter they are initialized or not.  For excluding
-		 * uninitialized extents, we need to check m_flags.  There are
-		 * two conditions that indicate for initialized extents.
-		 * 1) If we hit extent cache, EXT4_MAP_MAPPED flag is returned;
-		 * 2) If we do a real lookup, non-flags are returned.
-		 * So we should check these two conditions.
-		 */
-		if (err == len && (map.m_flags & EXT4_MAP_MAPPED))
-			overwrite = 1;
+		if (pos + length > sbi->s_bitmap_maxbytes)
+			iov_iter_truncate(from, sbi->s_bitmap_maxbytes - pos);
 	}
 
-	ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
-	mutex_unlock(&inode->i_mutex);
+	if (o_direct) {
+		blk_start_plug(&plug);
 
-	if (ret > 0 || ret == -EIOCBQUEUED) {
-		ssize_t err;
+		iocb->private = &overwrite;
 
-		err = generic_write_sync(file, pos, ret);
-		if (err < 0 && ret > 0)
-			ret = err;
-	}
-	blk_finish_plug(&plug);
-
-	if (unaligned_aio)
-		mutex_unlock(ext4_aio_mutex(inode));
-
-	return ret;
-}
+		/* check whether we do a DIO overwrite or not */
+		if (ext4_should_dioread_nolock(inode) && !aio_mutex &&
+		    !file->f_mapping->nrpages && pos + length <= i_size_read(inode)) {
+			struct ext4_map_blocks map;
+			unsigned int blkbits = inode->i_blkbits;
+			int err, len;
 
-static ssize_t
-ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
-		unsigned long nr_segs, loff_t pos)
-{
-	struct inode *inode = file_inode(iocb->ki_filp);
-	ssize_t ret;
+			map.m_lblk = pos >> blkbits;
+			map.m_len = (EXT4_BLOCK_ALIGN(pos + length, blkbits) >> blkbits)
+				- map.m_lblk;
+			len = map.m_len;
 
-	/*
-	 * If we have encountered a bitmap-format file, the size limit
-	 * is smaller than s_maxbytes, which is for extent-mapped files.
-	 */
+			err = ext4_map_blocks(NULL, inode, &map, 0);
+			/*
+			 * 'err==len' means that all of blocks has
+			 * been preallocated no matter they are
+			 * initialized or not.  For excluding
+			 * unwritten extents, we need to check
+			 * m_flags.  There are two conditions that
+			 * indicate for initialized extents.  1) If we
+			 * hit extent cache, EXT4_MAP_MAPPED flag is
+			 * returned; 2) If we do a real lookup,
+			 * non-flags are returned.  So we should check
+			 * these two conditions.
+			 */
+			if (err == len && (map.m_flags & EXT4_MAP_MAPPED))
+				overwrite = 1;
+		}
+	}
 
-	if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
-		struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
-		size_t length = iov_length(iov, nr_segs);
+	ret = __generic_file_write_iter(iocb, from);
+	mutex_unlock(&inode->i_mutex);
 
-		if ((pos > sbi->s_bitmap_maxbytes ||
-		    (pos == sbi->s_bitmap_maxbytes && length > 0)))
-			return -EFBIG;
+	if (ret > 0) {
+		ssize_t err;
 
-		if (pos + length > sbi->s_bitmap_maxbytes) {
-			nr_segs = iov_shorten((struct iovec *)iov, nr_segs,
-					      sbi->s_bitmap_maxbytes - pos);
-		}
+		err = generic_write_sync(file, iocb->ki_pos - ret, ret);
+		if (err < 0)
+			ret = err;
 	}
+	if (o_direct)
+		blk_finish_plug(&plug);
 
-	if (unlikely(iocb->ki_filp->f_flags & O_DIRECT))
-		ret = ext4_file_dio_write(iocb, iov, nr_segs, pos);
-	else
-		ret = generic_file_aio_write(iocb, iov, nr_segs, pos);
-
+errout:
+	if (aio_mutex)
+		mutex_unlock(aio_mutex);
 	return ret;
 }
 
 static const struct vm_operations_struct ext4_file_vm_ops = {
 	.fault		= filemap_fault,
+	.map_pages	= filemap_map_pages,
 	.page_mkwrite   = ext4_page_mkwrite,
 	.remap_pages	= generic_file_remap_pages,
 };
@@ -218,7 +213,6 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
 {
 	struct super_block *sb = inode->i_sb;
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
-	struct ext4_inode_info *ei = EXT4_I(inode);
 	struct vfsmount *mnt = filp->f_path.mnt;
 	struct path path;
 	char buf[64], *cp;
@@ -243,6 +237,7 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
 			handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 1);
 			if (IS_ERR(handle))
 				return PTR_ERR(handle);
+			BUFFER_TRACE(sbi->s_sbh, "get_write_access");
 			err = ext4_journal_get_write_access(handle, sbi->s_sbh);
 			if (err) {
 				ext4_journal_stop(handle);
@@ -258,22 +253,10 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
 	 * Set up the jbd2_inode if we are opening the inode for
 	 * writing and the journal is present
 	 */
-	if (sbi->s_journal && !ei->jinode && (filp->f_mode & FMODE_WRITE)) {
-		struct jbd2_inode *jinode = jbd2_alloc_inode(GFP_KERNEL);
-
-		spin_lock(&inode->i_lock);
-		if (!ei->jinode) {
-			if (!jinode) {
-				spin_unlock(&inode->i_lock);
-				return -ENOMEM;
-			}
-			ei->jinode = jinode;
-			jbd2_journal_init_jbd_inode(ei->jinode, inode);
-			jinode = NULL;
-		}
-		spin_unlock(&inode->i_lock);
-		if (unlikely(jinode != NULL))
-			jbd2_free_inode(jinode);
+	if (filp->f_mode & FMODE_WRITE) {
+		int ret = ext4_inode_attach_jinode(inode);
+		if (ret < 0)
+			return ret;
 	}
 	return dquot_file_open(inode, filp);
 }
@@ -311,7 +294,7 @@ static int ext4_find_unwritten_pgoff(struct inode *inode,
 	blkbits = inode->i_sb->s_blocksize_bits;
 	startoff = *offset;
 	lastoff = startoff;
-	endoff = (map->m_lblk + map->m_len) << blkbits;
+	endoff = (loff_t)(map->m_lblk + map->m_len) << blkbits;
 
 	index = startoff >> PAGE_CACHE_SHIFT;
 	end = endoff >> PAGE_CACHE_SHIFT;
@@ -456,7 +439,7 @@ static loff_t ext4_seek_data(struct file *file, loff_t offset, loff_t maxsize)
 		ret = ext4_map_blocks(NULL, inode, &map, 0);
 		if (ret > 0 && !(map.m_flags & EXT4_MAP_UNWRITTEN)) {
 			if (last != start)
-				dataoff = last << blkbits;
+				dataoff = (loff_t)last << blkbits;
 			break;
 		}
 
@@ -464,10 +447,10 @@ static loff_t ext4_seek_data(struct file *file, loff_t offset, loff_t maxsize)
 		 * If there is a delay extent at this offset,
 		 * it will be as a data.
 		 */
-		ext4_es_find_delayed_extent(inode, last, &es);
+		ext4_es_find_delayed_extent_range(inode, last, last, &es);
 		if (es.es_len != 0 && in_range(last, es.es_lblk, es.es_len)) {
 			if (last != start)
-				dataoff = last << blkbits;
+				dataoff = (loff_t)last << blkbits;
 			break;
 		}
 
@@ -485,7 +468,7 @@ static loff_t ext4_seek_data(struct file *file, loff_t offset, loff_t maxsize)
 		}
 
 		last++;
-		dataoff = last << blkbits;
+		dataoff = (loff_t)last << blkbits;
 	} while (last <= end);
 
 	mutex_unlock(&inode->i_mutex);
@@ -493,17 +476,7 @@ static loff_t ext4_seek_data(struct file *file, loff_t offset, loff_t maxsize)
 	if (dataoff > isize)
 		return -ENXIO;
 
-	if (dataoff < 0 && !(file->f_mode & FMODE_UNSIGNED_OFFSET))
-		return -EINVAL;
-	if (dataoff > maxsize)
-		return -EINVAL;
-
-	if (dataoff != file->f_pos) {
-		file->f_pos = dataoff;
-		file->f_version = 0;
-	}
-
-	return dataoff;
+	return vfs_setpos(file, dataoff, maxsize);
 }
 
 /*
@@ -539,7 +512,7 @@ static loff_t ext4_seek_hole(struct file *file, loff_t offset, loff_t maxsize)
 		ret = ext4_map_blocks(NULL, inode, &map, 0);
 		if (ret > 0 && !(map.m_flags & EXT4_MAP_UNWRITTEN)) {
 			last += ret;
-			holeoff = last << blkbits;
+			holeoff = (loff_t)last << blkbits;
 			continue;
 		}
 
@@ -547,10 +520,10 @@ static loff_t ext4_seek_hole(struct file *file, loff_t offset, loff_t maxsize)
 		 * If there is a delay extent at this offset,
 		 * we will skip this extent.
 		 */
-		ext4_es_find_delayed_extent(inode, last, &es);
+		ext4_es_find_delayed_extent_range(inode, last, last, &es);
 		if (es.es_len != 0 && in_range(last, es.es_lblk, es.es_len)) {
 			last = es.es_lblk + es.es_len;
-			holeoff = last << blkbits;
+			holeoff = (loff_t)last << blkbits;
 			continue;
 		}
 
@@ -565,7 +538,7 @@ static loff_t ext4_seek_hole(struct file *file, loff_t offset, loff_t maxsize)
 							      &map, &holeoff);
 			if (!unwritten) {
 				last += ret;
-				holeoff = last << blkbits;
+				holeoff = (loff_t)last << blkbits;
 				continue;
 			}
 		}
@@ -579,17 +552,7 @@ static loff_t ext4_seek_hole(struct file *file, loff_t offset, loff_t maxsize)
 	if (holeoff > isize)
 		holeoff = isize;
 
-	if (holeoff < 0 && !(file->f_mode & FMODE_UNSIGNED_OFFSET))
-		return -EINVAL;
-	if (holeoff > maxsize)
-		return -EINVAL;
-
-	if (holeoff != file->f_pos) {
-		file->f_pos = holeoff;
-		file->f_version = 0;
-	}
-
-	return holeoff;
+	return vfs_setpos(file, holeoff, maxsize);
 }
 
 /*
@@ -624,10 +587,10 @@ loff_t ext4_llseek(struct file *file, loff_t offset, int whence)
 
 const struct file_operations ext4_file_operations = {
 	.llseek		= ext4_llseek,
-	.read		= do_sync_read,
-	.write		= do_sync_write,
-	.aio_read	= generic_file_aio_read,
-	.aio_write	= ext4_file_write,
+	.read		= new_sync_read,
+	.write		= new_sync_write,
+	.read_iter	= generic_file_read_iter,
+	.write_iter	= ext4_file_write_iter,
 	.unlocked_ioctl = ext4_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= ext4_compat_ioctl,
@@ -637,7 +600,7 @@ const struct file_operations ext4_file_operations = {
 	.release	= ext4_release_file,
 	.fsync		= ext4_sync_file,
 	.splice_read	= generic_file_splice_read,
-	.splice_write	= generic_file_splice_write,
+	.splice_write	= iter_file_splice_write,
 	.fallocate	= ext4_fallocate,
 };
 
@@ -649,6 +612,7 @@ const struct inode_operations ext4_file_inode_operations = {
 	.listxattr	= ext4_listxattr,
 	.removexattr	= generic_removexattr,
 	.get_acl	= ext4_get_acl,
+	.set_acl	= ext4_set_acl,
 	.fiemap		= ext4_fiemap,
 };