Merge git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-unstable

* git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-unstable:
  Btrfs: break out of shrink_delalloc earlier
  btrfs: fix not enough reserved space
  btrfs: fix dip leak
  Btrfs: make sure not to return overlapping extents to fiemap
  Btrfs: deal with short returns from copy_from_user
  Btrfs: fix regressions in copy_from_user handling

5 files changed, 135 insertions, 62 deletions

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 6f820fa..7f78cc7 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -729,6 +729,15 @@ struct btrfs_space_info {
 	u64 disk_total;		/* total bytes on disk, takes mirrors into
 				   account */
 
+	/*
+	 * we bump reservation progress every time we decrement
+	 * bytes_reserved.  This way people waiting for reservations
+	 * know something good has happened and they can check
+	 * for progress.  The number here isn't to be trusted, it
+	 * just shows reclaim activity
+	 */
+	unsigned long reservation_progress;
+
 	int full;		/* indicates that we cannot allocate any more
 				   chunks for this space */
 	int force_alloc;	/* set if we need to force a chunk alloc for
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 588ff98..7b3089b 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3342,15 +3342,16 @@ static int shrink_delalloc(struct btrfs_trans_handle *trans,
 	u64 max_reclaim;
 	u64 reclaimed = 0;
 	long time_left;
-	int pause = 1;
 	int nr_pages = (2 * 1024 * 1024) >> PAGE_CACHE_SHIFT;
 	int loops = 0;
+	unsigned long progress;
 
 	block_rsv = &root->fs_info->delalloc_block_rsv;
 	space_info = block_rsv->space_info;
 
 	smp_mb();
 	reserved = space_info->bytes_reserved;
+	progress = space_info->reservation_progress;
 
 	if (reserved == 0)
 		return 0;
@@ -3365,31 +3366,36 @@ static int shrink_delalloc(struct btrfs_trans_handle *trans,
 		writeback_inodes_sb_nr_if_idle(root->fs_info->sb, nr_pages);
 
 		spin_lock(&space_info->lock);
-		if (reserved > space_info->bytes_reserved) {
-			loops = 0;
+		if (reserved > space_info->bytes_reserved)
 			reclaimed += reserved - space_info->bytes_reserved;
-		} else {
-			loops++;
-		}
 		reserved = space_info->bytes_reserved;
 		spin_unlock(&space_info->lock);
 
+		loops++;
+
 		if (reserved == 0 || reclaimed >= max_reclaim)
 			break;
 
 		if (trans && trans->transaction->blocked)
 			return -EAGAIN;
 
-		__set_current_state(TASK_INTERRUPTIBLE);
-		time_left = schedule_timeout(pause);
+		time_left = schedule_timeout_interruptible(1);
 
 		/* We were interrupted, exit */
 		if (time_left)
 			break;
 
-		pause <<= 1;
-		if (pause > HZ / 10)
-			pause = HZ / 10;
+		/* we've kicked the IO a few times, if anything has been freed,
+		 * exit.  There is no sense in looping here for a long time
+		 * when we really need to commit the transaction, or there are
+		 * just too many writers without enough free space
+		 */
+
+		if (loops > 3) {
+			smp_mb();
+			if (progress != space_info->reservation_progress)
+				break;
+		}
 
 	}
 	return reclaimed >= to_reclaim;
@@ -3612,6 +3618,7 @@ void block_rsv_release_bytes(struct btrfs_block_rsv *block_rsv,
 		if (num_bytes) {
 			spin_lock(&space_info->lock);
 			space_info->bytes_reserved -= num_bytes;
+			space_info->reservation_progress++;
 			spin_unlock(&space_info->lock);
 		}
 	}
@@ -3844,6 +3851,7 @@ static void update_global_block_rsv(struct btrfs_fs_info *fs_info)
 	if (block_rsv->reserved >= block_rsv->size) {
 		num_bytes = block_rsv->reserved - block_rsv->size;
 		sinfo->bytes_reserved -= num_bytes;
+		sinfo->reservation_progress++;
 		block_rsv->reserved = block_rsv->size;
 		block_rsv->full = 1;
 	}
@@ -4005,7 +4013,6 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
 		to_reserve = 0;
 	}
 	spin_unlock(&BTRFS_I(inode)->accounting_lock);
-
 	to_reserve += calc_csum_metadata_size(inode, num_bytes);
 	ret = reserve_metadata_bytes(NULL, root, block_rsv, to_reserve, 1);
 	if (ret)
@@ -4133,6 +4140,7 @@ static int update_block_group(struct btrfs_trans_handle *trans,
 			btrfs_set_block_group_used(&cache->item, old_val);
 			cache->reserved -= num_bytes;
 			cache->space_info->bytes_reserved -= num_bytes;
+			cache->space_info->reservation_progress++;
 			cache->space_info->bytes_used += num_bytes;
 			cache->space_info->disk_used += num_bytes * factor;
 			spin_unlock(&cache->lock);
@@ -4184,6 +4192,7 @@ static int pin_down_extent(struct btrfs_root *root,
 	if (reserved) {
 		cache->reserved -= num_bytes;
 		cache->space_info->bytes_reserved -= num_bytes;
+		cache->space_info->reservation_progress++;
 	}
 	spin_unlock(&cache->lock);
 	spin_unlock(&cache->space_info->lock);
@@ -4234,6 +4243,7 @@ static int update_reserved_bytes(struct btrfs_block_group_cache *cache,
 				space_info->bytes_readonly += num_bytes;
 			cache->reserved -= num_bytes;
 			space_info->bytes_reserved -= num_bytes;
+			space_info->reservation_progress++;
 		}
 		spin_unlock(&cache->lock);
 		spin_unlock(&space_info->lock);
@@ -4712,6 +4722,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
 		if (ret) {
 			spin_lock(&cache->space_info->lock);
 			cache->space_info->bytes_reserved -= buf->len;
+			cache->space_info->reservation_progress++;
 			spin_unlock(&cache->space_info->lock);
 		}
 		goto out;
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index fd3f172..714adc4 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -3046,17 +3046,38 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	}
 
 	while (!end) {
-		off = extent_map_end(em);
-		if (off >= max)
-			end = 1;
+		u64 offset_in_extent;
+
+		/* break if the extent we found is outside the range */
+		if (em->start >= max || extent_map_end(em) < off)
+			break;
+
+		/*
+		 * get_extent may return an extent that starts before our
+		 * requested range.  We have to make sure the ranges
+		 * we return to fiemap always move forward and don't
+		 * overlap, so adjust the offsets here
+		 */
+		em_start = max(em->start, off);
 
-		em_start = em->start;
-		em_len = em->len;
+		/*
+		 * record the offset from the start of the extent
+		 * for adjusting the disk offset below
+		 */
+		offset_in_extent = em_start - em->start;
 		em_end = extent_map_end(em);
+		em_len = em_end - em_start;
 		emflags = em->flags;
 		disko = 0;
 		flags = 0;
 
+		/*
+		 * bump off for our next call to get_extent
+		 */
+		off = extent_map_end(em);
+		if (off >= max)
+			end = 1;
+
 		if (em->block_start == EXTENT_MAP_LAST_BYTE) {
 			end = 1;
 			flags |= FIEMAP_EXTENT_LAST;
@@ -3067,7 +3088,7 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 			flags |= (FIEMAP_EXTENT_DELALLOC |
 				  FIEMAP_EXTENT_UNKNOWN);
 		} else {
-			disko = em->block_start;
+			disko = em->block_start + offset_in_extent;
 		}
 		if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags))
 			flags |= FIEMAP_EXTENT_ENCODED;
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 7084140..f447b78 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -70,6 +70,19 @@ static noinline int btrfs_copy_from_user(loff_t pos, int num_pages,
 
 		/* Flush processor's dcache for this page */
 		flush_dcache_page(page);
+
+		/*
+		 * if we get a partial write, we can end up with
+		 * partially up to date pages.  These add
+		 * a lot of complexity, so make sure they don't
+		 * happen by forcing this copy to be retried.
+		 *
+		 * The rest of the btrfs_file_write code will fall
+		 * back to page at a time copies after we return 0.
+		 */
+		if (!PageUptodate(page) && copied < count)
+			copied = 0;
+
 		iov_iter_advance(i, copied);
 		write_bytes -= copied;
 		total_copied += copied;
@@ -763,6 +776,27 @@ out:
 }
 
 /*
+ * on error we return an unlocked page and the error value
+ * on success we return a locked page and 0
+ */
+static int prepare_uptodate_page(struct page *page, u64 pos)
+{
+	int ret = 0;
+
+	if ((pos & (PAGE_CACHE_SIZE - 1)) && !PageUptodate(page)) {
+		ret = btrfs_readpage(NULL, page);
+		if (ret)
+			return ret;
+		lock_page(page);
+		if (!PageUptodate(page)) {
+			unlock_page(page);
+			return -EIO;
+		}
+	}
+	return 0;
+}
+
+/*
  * this gets pages into the page cache and locks them down, it also properly
  * waits for data=ordered extents to finish before allowing the pages to be
  * modified.
@@ -777,6 +811,7 @@ static noinline int prepare_pages(struct btrfs_root *root, struct file *file,
 	unsigned long index = pos >> PAGE_CACHE_SHIFT;
 	struct inode *inode = fdentry(file)->d_inode;
 	int err = 0;
+	int faili = 0;
 	u64 start_pos;
 	u64 last_pos;
 
@@ -794,15 +829,24 @@ again:
 	for (i = 0; i < num_pages; i++) {
 		pages[i] = grab_cache_page(inode->i_mapping, index + i);
 		if (!pages[i]) {
-			int c;
-			for (c = i - 1; c >= 0; c--) {
-				unlock_page(pages[c]);
-				page_cache_release(pages[c]);
-			}
-			return -ENOMEM;
+			faili = i - 1;
+			err = -ENOMEM;
+			goto fail;
+		}
+
+		if (i == 0)
+			err = prepare_uptodate_page(pages[i], pos);
+		if (i == num_pages - 1)
+			err = prepare_uptodate_page(pages[i],
+						    pos + write_bytes);
+		if (err) {
+			page_cache_release(pages[i]);
+			faili = i - 1;
+			goto fail;
 		}
 		wait_on_page_writeback(pages[i]);
 	}
+	err = 0;
 	if (start_pos < inode->i_size) {
 		struct btrfs_ordered_extent *ordered;
 		lock_extent_bits(&BTRFS_I(inode)->io_tree,
@@ -842,6 +886,14 @@ again:
 		WARN_ON(!PageLocked(pages[i]));
 	}
 	return 0;
+fail:
+	while (faili >= 0) {
+		unlock_page(pages[faili]);
+		page_cache_release(pages[faili]);
+		faili--;
+	}
+	return err;
+
 }
 
 static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
@@ -851,7 +903,6 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = fdentry(file)->d_inode;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
-	struct page *pinned[2];
 	struct page **pages = NULL;
 	struct iov_iter i;
 	loff_t *ppos = &iocb->ki_pos;
@@ -872,9 +923,6 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
 	will_write = ((file->f_flags & O_DSYNC) || IS_SYNC(inode) ||
 		      (file->f_flags & O_DIRECT));
 
-	pinned[0] = NULL;
-	pinned[1] = NULL;
-
 	start_pos = pos;
 
 	vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);
@@ -962,32 +1010,6 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
 	first_index = pos >> PAGE_CACHE_SHIFT;
 	last_index = (pos + iov_iter_count(&i)) >> PAGE_CACHE_SHIFT;
 
-	/*
-	 * there are lots of better ways to do this, but this code
-	 * makes sure the first and last page in the file range are
-	 * up to date and ready for cow
-	 */
-	if ((pos & (PAGE_CACHE_SIZE - 1))) {
-		pinned[0] = grab_cache_page(inode->i_mapping, first_index);
-		if (!PageUptodate(pinned[0])) {
-			ret = btrfs_readpage(NULL, pinned[0]);
-			BUG_ON(ret);
-			wait_on_page_locked(pinned[0]);
-		} else {
-			unlock_page(pinned[0]);
-		}
-	}
-	if ((pos + iov_iter_count(&i)) & (PAGE_CACHE_SIZE - 1)) {
-		pinned[1] = grab_cache_page(inode->i_mapping, last_index);
-		if (!PageUptodate(pinned[1])) {
-			ret = btrfs_readpage(NULL, pinned[1]);
-			BUG_ON(ret);
-			wait_on_page_locked(pinned[1]);
-		} else {
-			unlock_page(pinned[1]);
-		}
-	}
-
 	while (iov_iter_count(&i) > 0) {
 		size_t offset = pos & (PAGE_CACHE_SIZE - 1);
 		size_t write_bytes = min(iov_iter_count(&i),
@@ -1024,8 +1046,20 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
 
 		copied = btrfs_copy_from_user(pos, num_pages,
 					   write_bytes, pages, &i);
-		dirty_pages = (copied + offset + PAGE_CACHE_SIZE - 1) >>
-				PAGE_CACHE_SHIFT;
+
+		/*
+		 * if we have trouble faulting in the pages, fall
+		 * back to one page at a time
+		 */
+		if (copied < write_bytes)
+			nrptrs = 1;
+
+		if (copied == 0)
+			dirty_pages = 0;
+		else
+			dirty_pages = (copied + offset +
+				       PAGE_CACHE_SIZE - 1) >>
+				       PAGE_CACHE_SHIFT;
 
 		if (num_pages > dirty_pages) {
 			if (copied > 0)
@@ -1069,10 +1103,6 @@ out:
 		err = ret;
 
 	kfree(pages);
-	if (pinned[0])
-		page_cache_release(pinned[0]);
-	if (pinned[1])
-		page_cache_release(pinned[1]);
 	*ppos = pos;
 
 	/*
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 0efdb65..9007bbd 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4821,10 +4821,11 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 		goto fail;
 
 	/*
-	 * 1 item for inode ref
+	 * 2 items for inode and inode ref
 	 * 2 items for dir items
+	 * 1 item for parent inode
 	 */
-	trans = btrfs_start_transaction(root, 3);
+	trans = btrfs_start_transaction(root, 5);
 	if (IS_ERR(trans)) {
 		err = PTR_ERR(trans);
 		goto fail;
@@ -6056,6 +6057,7 @@ static void btrfs_submit_direct(int rw, struct bio *bio, struct inode *inode,
 	if (!skip_sum) {
 		dip->csums = kmalloc(sizeof(u32) * bio->bi_vcnt, GFP_NOFS);
 		if (!dip->csums) {
+			kfree(dip);
 			ret = -ENOMEM;
 			goto free_ordered;
 		}