1 files changed, 426 insertions, 70 deletions

diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index cb70f1812a7..8695f70af1e 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -23,7 +23,9 @@
 #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"
 #include "ext4_jbd2.h"
 #include "xattr.h"
@@ -55,11 +57,11 @@ static int ext4_release_file(struct inode *inode, struct file *filp)
 	return 0;
 }
 
-static void ext4_aiodio_wait(struct inode *inode)
+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_aiodio_unwritten) == 0));
+	wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_unwritten) == 0));
 }
 
 /*
@@ -72,78 +74,128 @@ static void ext4_aiodio_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_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 inode *inode = iocb->ki_filp->f_path.dentry->d_inode;
-	int unaligned_aio = 0;
-	int ret;
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file_inode(iocb->ki_filp);
+	struct mutex *aio_mutex = NULL;
+	struct blk_plug plug;
+	int o_direct = file->f_flags & O_DIRECT;
+	int overwrite = 0;
+	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
+	 * 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);
+	}
+
+	mutex_lock(&inode->i_mutex);
+	if (file->f_flags & O_APPEND)
+		iocb->ki_pos = pos = i_size_read(inode);
 
 	/*
 	 * 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);
-		size_t length = iov_length(iov, nr_segs);
-
-		if ((pos > sbi->s_bitmap_maxbytes ||
-		    (pos == sbi->s_bitmap_maxbytes && length > 0)))
-			return -EFBIG;
 
-		if (pos + length > sbi->s_bitmap_maxbytes) {
-			nr_segs = iov_shorten((struct iovec *)iov, nr_segs,
-					      sbi->s_bitmap_maxbytes - pos);
+		if ((pos > sbi->s_bitmap_maxbytes) ||
+		    (pos == sbi->s_bitmap_maxbytes && length > 0)) {
+			mutex_unlock(&inode->i_mutex);
+			ret = -EFBIG;
+			goto errout;
 		}
-	} else if (unlikely((iocb->ki_filp->f_flags & O_DIRECT) &&
-		   !is_sync_kiocb(iocb))) {
-		unaligned_aio = ext4_unaligned_aio(inode, iov, nr_segs, pos);
+
+		if (pos + length > sbi->s_bitmap_maxbytes)
+			iov_iter_truncate(from, sbi->s_bitmap_maxbytes - pos);
 	}
 
-	/* Unaligned direct AIO must be serialized; see comment above */
-	if (unaligned_aio) {
-		static unsigned long unaligned_warn_time;
-
-		/* Warn about this once per day */
-		if (printk_timed_ratelimit(&unaligned_warn_time, 60*60*24*HZ))
-			ext4_msg(inode->i_sb, KERN_WARNING,
-				 "Unaligned AIO/DIO on inode %ld by %s; "
-				 "performance will be poor.",
-				 inode->i_ino, current->comm);
-		mutex_lock(ext4_aio_mutex(inode));
-		ext4_aiodio_wait(inode);
+	if (o_direct) {
+		blk_start_plug(&plug);
+
+		iocb->private = &overwrite;
+
+		/* 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;
+
+			map.m_lblk = pos >> blkbits;
+			map.m_len = (EXT4_BLOCK_ALIGN(pos + length, blkbits) >> blkbits)
+				- map.m_lblk;
+			len = map.m_len;
+
+			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;
+		}
 	}
 
-	ret = generic_file_aio_write(iocb, iov, nr_segs, pos);
+	ret = __generic_file_write_iter(iocb, from);
+	mutex_unlock(&inode->i_mutex);
 
-	if (unaligned_aio)
-		mutex_unlock(ext4_aio_mutex(inode));
+	if (ret > 0) {
+		ssize_t err;
 
+		err = generic_write_sync(file, iocb->ki_pos - ret, ret);
+		if (err < 0)
+			ret = err;
+	}
+	if (o_direct)
+		blk_finish_plug(&plug);
+
+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,
 };
 
 static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
@@ -154,7 +206,6 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
 		return -ENOEXEC;
 	file_accessed(file);
 	vma->vm_ops = &ext4_file_vm_ops;
-	vma->vm_flags |= VM_CAN_NONLINEAR;
 	return 0;
 }
 
@@ -162,7 +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;
@@ -181,41 +231,336 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
 		path.dentry = mnt->mnt_root;
 		cp = d_path(&path, buf, sizeof(buf));
 		if (!IS_ERR(cp)) {
+			handle_t *handle;
+			int err;
+
+			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);
+				return err;
+			}
 			strlcpy(sbi->s_es->s_last_mounted, cp,
 				sizeof(sbi->s_es->s_last_mounted));
-			ext4_mark_super_dirty(sb);
+			ext4_handle_dirty_super(handle, sb);
+			ext4_journal_stop(handle);
 		}
 	}
 	/*
 	 * 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;
+	if (filp->f_mode & FMODE_WRITE) {
+		int ret = ext4_inode_attach_jinode(inode);
+		if (ret < 0)
+			return ret;
+	}
+	return dquot_file_open(inode, filp);
+}
+
+/*
+ * Here we use ext4_map_blocks() to get a block mapping for a extent-based
+ * file rather than ext4_ext_walk_space() because we can introduce
+ * SEEK_DATA/SEEK_HOLE for block-mapped and extent-mapped file at the same
+ * function.  When extent status tree has been fully implemented, it will
+ * track all extent status for a file and we can directly use it to
+ * retrieve the offset for SEEK_DATA/SEEK_HOLE.
+ */
+
+/*
+ * When we retrieve the offset for SEEK_DATA/SEEK_HOLE, we would need to
+ * lookup page cache to check whether or not there has some data between
+ * [startoff, endoff] because, if this range contains an unwritten extent,
+ * we determine this extent as a data or a hole according to whether the
+ * page cache has data or not.
+ */
+static int ext4_find_unwritten_pgoff(struct inode *inode,
+				     int whence,
+				     struct ext4_map_blocks *map,
+				     loff_t *offset)
+{
+	struct pagevec pvec;
+	unsigned int blkbits;
+	pgoff_t index;
+	pgoff_t end;
+	loff_t endoff;
+	loff_t startoff;
+	loff_t lastoff;
+	int found = 0;
+
+	blkbits = inode->i_sb->s_blocksize_bits;
+	startoff = *offset;
+	lastoff = startoff;
+	endoff = (loff_t)(map->m_lblk + map->m_len) << blkbits;
+
+	index = startoff >> PAGE_CACHE_SHIFT;
+	end = endoff >> PAGE_CACHE_SHIFT;
+
+	pagevec_init(&pvec, 0);
+	do {
+		int i, num;
+		unsigned long nr_pages;
+
+		num = min_t(pgoff_t, end - index, PAGEVEC_SIZE);
+		nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index,
+					  (pgoff_t)num);
+		if (nr_pages == 0) {
+			if (whence == SEEK_DATA)
+				break;
+
+			BUG_ON(whence != SEEK_HOLE);
+			/*
+			 * If this is the first time to go into the loop and
+			 * offset is not beyond the end offset, it will be a
+			 * hole at this offset
+			 */
+			if (lastoff == startoff || lastoff < endoff)
+				found = 1;
+			break;
+		}
+
+		/*
+		 * If this is the first time to go into the loop and
+		 * offset is smaller than the first page offset, it will be a
+		 * hole at this offset.
+		 */
+		if (lastoff == startoff && whence == SEEK_HOLE &&
+		    lastoff < page_offset(pvec.pages[0])) {
+			found = 1;
+			break;
+		}
+
+		for (i = 0; i < nr_pages; i++) {
+			struct page *page = pvec.pages[i];
+			struct buffer_head *bh, *head;
+
+			/*
+			 * If the current offset is not beyond the end of given
+			 * range, it will be a hole.
+			 */
+			if (lastoff < endoff && whence == SEEK_HOLE &&
+			    page->index > end) {
+				found = 1;
+				*offset = lastoff;
+				goto out;
+			}
+
+			lock_page(page);
+
+			if (unlikely(page->mapping != inode->i_mapping)) {
+				unlock_page(page);
+				continue;
+			}
+
+			if (!page_has_buffers(page)) {
+				unlock_page(page);
+				continue;
 			}
-			ei->jinode = jinode;
-			jbd2_journal_init_jbd_inode(ei->jinode, inode);
-			jinode = NULL;
+
+			if (page_has_buffers(page)) {
+				lastoff = page_offset(page);
+				bh = head = page_buffers(page);
+				do {
+					if (buffer_uptodate(bh) ||
+					    buffer_unwritten(bh)) {
+						if (whence == SEEK_DATA)
+							found = 1;
+					} else {
+						if (whence == SEEK_HOLE)
+							found = 1;
+					}
+					if (found) {
+						*offset = max_t(loff_t,
+							startoff, lastoff);
+						unlock_page(page);
+						goto out;
+					}
+					lastoff += bh->b_size;
+					bh = bh->b_this_page;
+				} while (bh != head);
+			}
+
+			lastoff = page_offset(page) + PAGE_SIZE;
+			unlock_page(page);
 		}
-		spin_unlock(&inode->i_lock);
-		if (unlikely(jinode != NULL))
-			jbd2_free_inode(jinode);
+
+		/*
+		 * The no. of pages is less than our desired, that would be a
+		 * hole in there.
+		 */
+		if (nr_pages < num && whence == SEEK_HOLE) {
+			found = 1;
+			*offset = lastoff;
+			break;
+		}
+
+		index = pvec.pages[i - 1]->index + 1;
+		pagevec_release(&pvec);
+	} while (index <= end);
+
+out:
+	pagevec_release(&pvec);
+	return found;
+}
+
+/*
+ * ext4_seek_data() retrieves the offset for SEEK_DATA.
+ */
+static loff_t ext4_seek_data(struct file *file, loff_t offset, loff_t maxsize)
+{
+	struct inode *inode = file->f_mapping->host;
+	struct ext4_map_blocks map;
+	struct extent_status es;
+	ext4_lblk_t start, last, end;
+	loff_t dataoff, isize;
+	int blkbits;
+	int ret = 0;
+
+	mutex_lock(&inode->i_mutex);
+
+	isize = i_size_read(inode);
+	if (offset >= isize) {
+		mutex_unlock(&inode->i_mutex);
+		return -ENXIO;
 	}
-	return dquot_file_open(inode, filp);
+
+	blkbits = inode->i_sb->s_blocksize_bits;
+	start = offset >> blkbits;
+	last = start;
+	end = isize >> blkbits;
+	dataoff = offset;
+
+	do {
+		map.m_lblk = last;
+		map.m_len = end - last + 1;
+		ret = ext4_map_blocks(NULL, inode, &map, 0);
+		if (ret > 0 && !(map.m_flags & EXT4_MAP_UNWRITTEN)) {
+			if (last != start)
+				dataoff = (loff_t)last << blkbits;
+			break;
+		}
+
+		/*
+		 * If there is a delay extent at this offset,
+		 * it will be as a data.
+		 */
+		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 = (loff_t)last << blkbits;
+			break;
+		}
+
+		/*
+		 * If there is a unwritten extent at this offset,
+		 * it will be as a data or a hole according to page
+		 * cache that has data or not.
+		 */
+		if (map.m_flags & EXT4_MAP_UNWRITTEN) {
+			int unwritten;
+			unwritten = ext4_find_unwritten_pgoff(inode, SEEK_DATA,
+							      &map, &dataoff);
+			if (unwritten)
+				break;
+		}
+
+		last++;
+		dataoff = (loff_t)last << blkbits;
+	} while (last <= end);
+
+	mutex_unlock(&inode->i_mutex);
+
+	if (dataoff > isize)
+		return -ENXIO;
+
+	return vfs_setpos(file, dataoff, maxsize);
+}
+
+/*
+ * ext4_seek_hole() retrieves the offset for SEEK_HOLE.
+ */
+static loff_t ext4_seek_hole(struct file *file, loff_t offset, loff_t maxsize)
+{
+	struct inode *inode = file->f_mapping->host;
+	struct ext4_map_blocks map;
+	struct extent_status es;
+	ext4_lblk_t start, last, end;
+	loff_t holeoff, isize;
+	int blkbits;
+	int ret = 0;
+
+	mutex_lock(&inode->i_mutex);
+
+	isize = i_size_read(inode);
+	if (offset >= isize) {
+		mutex_unlock(&inode->i_mutex);
+		return -ENXIO;
+	}
+
+	blkbits = inode->i_sb->s_blocksize_bits;
+	start = offset >> blkbits;
+	last = start;
+	end = isize >> blkbits;
+	holeoff = offset;
+
+	do {
+		map.m_lblk = last;
+		map.m_len = end - last + 1;
+		ret = ext4_map_blocks(NULL, inode, &map, 0);
+		if (ret > 0 && !(map.m_flags & EXT4_MAP_UNWRITTEN)) {
+			last += ret;
+			holeoff = (loff_t)last << blkbits;
+			continue;
+		}
+
+		/*
+		 * If there is a delay extent at this offset,
+		 * we will skip this extent.
+		 */
+		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 = (loff_t)last << blkbits;
+			continue;
+		}
+
+		/*
+		 * If there is a unwritten extent at this offset,
+		 * it will be as a data or a hole according to page
+		 * cache that has data or not.
+		 */
+		if (map.m_flags & EXT4_MAP_UNWRITTEN) {
+			int unwritten;
+			unwritten = ext4_find_unwritten_pgoff(inode, SEEK_HOLE,
+							      &map, &holeoff);
+			if (!unwritten) {
+				last += ret;
+				holeoff = (loff_t)last << blkbits;
+				continue;
+			}
+		}
+
+		/* find a hole */
+		break;
+	} while (last <= end);
+
+	mutex_unlock(&inode->i_mutex);
+
+	if (holeoff > isize)
+		holeoff = isize;
+
+	return vfs_setpos(file, holeoff, maxsize);
 }
 
 /*
- * ext4_llseek() copied from generic_file_llseek() to handle both
- * block-mapped and extent-mapped maxbytes values. This should
- * otherwise be identical with generic_file_llseek().
+ * ext4_llseek() handles both block-mapped and extent-mapped maxbytes values
+ * by calling generic_file_llseek_size() with the appropriate maxbytes
+ * value for each.
  */
-loff_t ext4_llseek(struct file *file, loff_t offset, int origin)
+loff_t ext4_llseek(struct file *file, loff_t offset, int whence)
 {
 	struct inode *inode = file->f_mapping->host;
 	loff_t maxbytes;
@@ -225,15 +570,27 @@ loff_t ext4_llseek(struct file *file, loff_t offset, int origin)
 	else
 		maxbytes = inode->i_sb->s_maxbytes;
 
-	return generic_file_llseek_size(file, offset, origin, maxbytes);
+	switch (whence) {
+	case SEEK_SET:
+	case SEEK_CUR:
+	case SEEK_END:
+		return generic_file_llseek_size(file, offset, whence,
+						maxbytes, i_size_read(inode));
+	case SEEK_DATA:
+		return ext4_seek_data(file, offset, maxbytes);
+	case SEEK_HOLE:
+		return ext4_seek_hole(file, offset, maxbytes);
+	}
+
+	return -EINVAL;
 }
 
 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,
@@ -243,20 +600,19 @@ 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,
 };
 
 const struct inode_operations ext4_file_inode_operations = {
 	.setattr	= ext4_setattr,
 	.getattr	= ext4_getattr,
-#ifdef CONFIG_EXT4_FS_XATTR
 	.setxattr	= generic_setxattr,
 	.getxattr	= generic_getxattr,
 	.listxattr	= ext4_listxattr,
 	.removexattr	= generic_removexattr,
-#endif
 	.get_acl	= ext4_get_acl,
+	.set_acl	= ext4_set_acl,
 	.fiemap		= ext4_fiemap,
 };