1 files changed, 235 insertions, 48 deletions

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index a85c23dfcddb..56f00a25c003 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -32,7 +32,6 @@
 #include <linux/writeback.h>
 #include <linux/statfs.h>
 #include <linux/compat.h>
-#include <linux/aio.h>
 #include <linux/bit_spinlock.h>
 #include <linux/xattr.h>
 #include <linux/posix_acl.h>
@@ -43,6 +42,7 @@
 #include <linux/btrfs.h>
 #include <linux/blkdev.h>
 #include <linux/posix_acl_xattr.h>
+#include <linux/uio.h>
 #include "ctree.h"
 #include "disk-io.h"
 #include "transaction.h"
@@ -59,6 +59,7 @@
 #include "backref.h"
 #include "hash.h"
 #include "props.h"
+#include "qgroup.h"
 
 struct btrfs_iget_args {
 	struct btrfs_key *location;
@@ -108,6 +109,13 @@ static struct extent_map *create_pinned_em(struct inode *inode, u64 start,
 
 static int btrfs_dirty_inode(struct inode *inode);
 
+#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+void btrfs_test_inode_set_ops(struct inode *inode)
+{
+	BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
+}
+#endif
+
 static int btrfs_init_inode_security(struct btrfs_trans_handle *trans,
 				     struct inode *inode,  struct inode *dir,
 				     const struct qstr *qstr)
@@ -463,7 +471,7 @@ again:
 	 */
 	if (inode_need_compress(inode)) {
 		WARN_ON(pages);
-		pages = kzalloc(sizeof(struct page *) * nr_pages, GFP_NOFS);
+		pages = kcalloc(nr_pages, sizeof(struct page *), GFP_NOFS);
 		if (!pages) {
 			/* just bail out to the uncompressed code */
 			goto cont;
@@ -745,7 +753,6 @@ retry:
 			}
 			goto out_free;
 		}
-
 		/*
 		 * here we're doing allocation and writeback of the
 		 * compressed pages
@@ -1542,30 +1549,17 @@ static void btrfs_split_extent_hook(struct inode *inode,
 		u64 new_size;
 
 		/*
-		 * We need the largest size of the remaining extent to see if we
-		 * need to add a new outstanding extent.  Think of the following
-		 * case
-		 *
-		 * [MEAX_EXTENT_SIZEx2 - 4k][4k]
-		 *
-		 * The new_size would just be 4k and we'd think we had enough
-		 * outstanding extents for this if we only took one side of the
-		 * split, same goes for the other direction.  We need to see if
-		 * the larger size still is the same amount of extents as the
-		 * original size, because if it is we need to add a new
-		 * outstanding extent.  But if we split up and the larger size
-		 * is less than the original then we are good to go since we've
-		 * already accounted for the extra extent in our original
-		 * accounting.
+		 * See the explanation in btrfs_merge_extent_hook, the same
+		 * applies here, just in reverse.
 		 */
 		new_size = orig->end - split + 1;
-		if ((split - orig->start) > new_size)
-			new_size = split - orig->start;
-
-		num_extents = div64_u64(size + BTRFS_MAX_EXTENT_SIZE - 1,
+		num_extents = div64_u64(new_size + BTRFS_MAX_EXTENT_SIZE - 1,
+					BTRFS_MAX_EXTENT_SIZE);
+		new_size = split - orig->start;
+		num_extents += div64_u64(new_size + BTRFS_MAX_EXTENT_SIZE - 1,
 					BTRFS_MAX_EXTENT_SIZE);
-		if (div64_u64(new_size + BTRFS_MAX_EXTENT_SIZE - 1,
-			      BTRFS_MAX_EXTENT_SIZE) < num_extents)
+		if (div64_u64(size + BTRFS_MAX_EXTENT_SIZE - 1,
+			      BTRFS_MAX_EXTENT_SIZE) >= num_extents)
 			return;
 	}
 
@@ -1591,8 +1585,10 @@ static void btrfs_merge_extent_hook(struct inode *inode,
 	if (!(other->state & EXTENT_DELALLOC))
 		return;
 
-	old_size = other->end - other->start + 1;
-	new_size = old_size + (new->end - new->start + 1);
+	if (new->start > other->start)
+		new_size = new->end - other->start + 1;
+	else
+		new_size = other->end - new->start + 1;
 
 	/* we're not bigger than the max, unreserve the space and go */
 	if (new_size <= BTRFS_MAX_EXTENT_SIZE) {
@@ -1603,13 +1599,32 @@ static void btrfs_merge_extent_hook(struct inode *inode,
 	}
 
 	/*
-	 * If we grew by another max_extent, just return, we want to keep that
-	 * reserved amount.
+	 * We have to add up either side to figure out how many extents were
+	 * accounted for before we merged into one big extent.  If the number of
+	 * extents we accounted for is <= the amount we need for the new range
+	 * then we can return, otherwise drop.  Think of it like this
+	 *
+	 * [ 4k][MAX_SIZE]
+	 *
+	 * So we've grown the extent by a MAX_SIZE extent, this would mean we
+	 * need 2 outstanding extents, on one side we have 1 and the other side
+	 * we have 1 so they are == and we can return.  But in this case
+	 *
+	 * [MAX_SIZE+4k][MAX_SIZE+4k]
+	 *
+	 * Each range on their own accounts for 2 extents, but merged together
+	 * they are only 3 extents worth of accounting, so we need to drop in
+	 * this case.
 	 */
+	old_size = other->end - other->start + 1;
 	num_extents = div64_u64(old_size + BTRFS_MAX_EXTENT_SIZE - 1,
 				BTRFS_MAX_EXTENT_SIZE);
+	old_size = new->end - new->start + 1;
+	num_extents += div64_u64(old_size + BTRFS_MAX_EXTENT_SIZE - 1,
+				 BTRFS_MAX_EXTENT_SIZE);
+
 	if (div64_u64(new_size + BTRFS_MAX_EXTENT_SIZE - 1,
-		      BTRFS_MAX_EXTENT_SIZE) > num_extents)
+		      BTRFS_MAX_EXTENT_SIZE) >= num_extents)
 		return;
 
 	spin_lock(&BTRFS_I(inode)->lock);
@@ -1686,6 +1701,10 @@ static void btrfs_set_bit_hook(struct inode *inode,
 			spin_unlock(&BTRFS_I(inode)->lock);
 		}
 
+		/* For sanity tests */
+		if (btrfs_test_is_dummy_root(root))
+			return;
+
 		__percpu_counter_add(&root->fs_info->delalloc_bytes, len,
 				     root->fs_info->delalloc_batch);
 		spin_lock(&BTRFS_I(inode)->lock);
@@ -1741,6 +1760,10 @@ static void btrfs_clear_bit_hook(struct inode *inode,
 		    root != root->fs_info->tree_root)
 			btrfs_delalloc_release_metadata(inode, len);
 
+		/* For sanity tests. */
+		if (btrfs_test_is_dummy_root(root))
+			return;
+
 		if (root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID
 		    && do_list && !(state->state & EXTENT_NORESERVE))
 			btrfs_free_reserved_data_space(inode, len);
@@ -3087,6 +3110,8 @@ void btrfs_run_delayed_iputs(struct btrfs_root *root)
 	if (empty)
 		return;
 
+	down_read(&fs_info->delayed_iput_sem);
+
 	spin_lock(&fs_info->delayed_iput_lock);
 	list_splice_init(&fs_info->delayed_iputs, &list);
 	spin_unlock(&fs_info->delayed_iput_lock);
@@ -3097,6 +3122,8 @@ void btrfs_run_delayed_iputs(struct btrfs_root *root)
 		iput(delayed->inode);
 		kfree(delayed);
 	}
+
+	up_read(&root->fs_info->delayed_iput_sem);
 }
 
 /*
@@ -4139,6 +4166,21 @@ out:
 	return err;
 }
 
+static int truncate_space_check(struct btrfs_trans_handle *trans,
+				struct btrfs_root *root,
+				u64 bytes_deleted)
+{
+	int ret;
+
+	bytes_deleted = btrfs_csum_bytes_to_leaves(root, bytes_deleted);
+	ret = btrfs_block_rsv_add(root, &root->fs_info->trans_block_rsv,
+				  bytes_deleted, BTRFS_RESERVE_NO_FLUSH);
+	if (!ret)
+		trans->bytes_reserved += bytes_deleted;
+	return ret;
+
+}
+
 /*
  * this can truncate away extent items, csum items and directory items.
  * It starts at a high offset and removes keys until it can't find
@@ -4174,9 +4216,21 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
 	int ret;
 	int err = 0;
 	u64 ino = btrfs_ino(inode);
+	u64 bytes_deleted = 0;
+	bool be_nice = 0;
+	bool should_throttle = 0;
+	bool should_end = 0;
 
 	BUG_ON(new_size > 0 && min_type != BTRFS_EXTENT_DATA_KEY);
 
+	/*
+	 * for non-free space inodes and ref cows, we want to back off from
+	 * time to time
+	 */
+	if (!btrfs_is_free_space_inode(inode) &&
+	    test_bit(BTRFS_ROOT_REF_COWS, &root->state))
+		be_nice = 1;
+
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
@@ -4206,6 +4260,19 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
 	key.type = (u8)-1;
 
 search_again:
+	/*
+	 * with a 16K leaf size and 128MB extents, you can actually queue
+	 * up a huge file in a single leaf.  Most of the time that
+	 * bytes_deleted is > 0, it will be huge by the time we get here
+	 */
+	if (be_nice && bytes_deleted > 32 * 1024 * 1024) {
+		if (btrfs_should_end_transaction(trans, root)) {
+			err = -EAGAIN;
+			goto error;
+		}
+	}
+
+
 	path->leave_spinning = 1;
 	ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
 	if (ret < 0) {
@@ -4348,22 +4415,39 @@ delete:
 		} else {
 			break;
 		}
+		should_throttle = 0;
+
 		if (found_extent &&
 		    (test_bit(BTRFS_ROOT_REF_COWS, &root->state) ||
 		     root == root->fs_info->tree_root)) {
 			btrfs_set_path_blocking(path);
+			bytes_deleted += extent_num_bytes;
 			ret = btrfs_free_extent(trans, root, extent_start,
 						extent_num_bytes, 0,
 						btrfs_header_owner(leaf),
 						ino, extent_offset, 0);
 			BUG_ON(ret);
+			if (btrfs_should_throttle_delayed_refs(trans, root))
+				btrfs_async_run_delayed_refs(root,
+					trans->delayed_ref_updates * 2, 0);
+			if (be_nice) {
+				if (truncate_space_check(trans, root,
+							 extent_num_bytes)) {
+					should_end = 1;
+				}
+				if (btrfs_should_throttle_delayed_refs(trans,
+								       root)) {
+					should_throttle = 1;
+				}
+			}
 		}
 
 		if (found_type == BTRFS_INODE_ITEM_KEY)
 			break;
 
 		if (path->slots[0] == 0 ||
-		    path->slots[0] != pending_del_slot) {
+		    path->slots[0] != pending_del_slot ||
+		    should_throttle || should_end) {
 			if (pending_del_nr) {
 				ret = btrfs_del_items(trans, root, path,
 						pending_del_slot,
@@ -4376,6 +4460,23 @@ delete:
 				pending_del_nr = 0;
 			}
 			btrfs_release_path(path);
+			if (should_throttle) {
+				unsigned long updates = trans->delayed_ref_updates;
+				if (updates) {
+					trans->delayed_ref_updates = 0;
+					ret = btrfs_run_delayed_refs(trans, root, updates * 2);
+					if (ret && !err)
+						err = ret;
+				}
+			}
+			/*
+			 * if we failed to refill our space rsv, bail out
+			 * and let the transaction restart
+			 */
+			if (should_end) {
+				err = -EAGAIN;
+				goto error;
+			}
 			goto search_again;
 		} else {
 			path->slots[0]--;
@@ -4392,7 +4493,18 @@ error:
 	if (last_size != (u64)-1 &&
 	    root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID)
 		btrfs_ordered_update_i_size(inode, last_size, NULL);
+
 	btrfs_free_path(path);
+
+	if (be_nice && bytes_deleted > 32 * 1024 * 1024) {
+		unsigned long updates = trans->delayed_ref_updates;
+		if (updates) {
+			trans->delayed_ref_updates = 0;
+			ret = btrfs_run_delayed_refs(trans, root, updates * 2);
+			if (ret && !err)
+				err = ret;
+		}
+	}
 	return err;
 }
 
@@ -4901,6 +5013,7 @@ void btrfs_evict_inode(struct inode *inode)
 	struct btrfs_trans_handle *trans;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_block_rsv *rsv, *global_rsv;
+	int steal_from_global = 0;
 	u64 min_size = btrfs_calc_trunc_metadata_size(root, 1);
 	int ret;
 
@@ -4968,9 +5081,20 @@ void btrfs_evict_inode(struct inode *inode)
 		 * hard as possible to get this to work.
 		 */
 		if (ret)
-			ret = btrfs_block_rsv_migrate(global_rsv, rsv, min_size);
+			steal_from_global++;
+		else
+			steal_from_global = 0;
+		ret = 0;
 
-		if (ret) {
+		/*
+		 * steal_from_global == 0: we reserved stuff, hooray!
+		 * steal_from_global == 1: we didn't reserve stuff, boo!
+		 * steal_from_global == 2: we've committed, still not a lot of
+		 * room but maybe we'll have room in the global reserve this
+		 * time.
+		 * steal_from_global == 3: abandon all hope!
+		 */
+		if (steal_from_global > 2) {
 			btrfs_warn(root->fs_info,
 				"Could not get space for a delete, will truncate on mount %d",
 				ret);
@@ -4986,10 +5110,40 @@ void btrfs_evict_inode(struct inode *inode)
 			goto no_delete;
 		}
 
+		/*
+		 * We can't just steal from the global reserve, we need tomake
+		 * sure there is room to do it, if not we need to commit and try
+		 * again.
+		 */
+		if (steal_from_global) {
+			if (!btrfs_check_space_for_delayed_refs(trans, root))
+				ret = btrfs_block_rsv_migrate(global_rsv, rsv,
+							      min_size);
+			else
+				ret = -ENOSPC;
+		}
+
+		/*
+		 * Couldn't steal from the global reserve, we have too much
+		 * pending stuff built up, commit the transaction and try it
+		 * again.
+		 */
+		if (ret) {
+			ret = btrfs_commit_transaction(trans, root);
+			if (ret) {
+				btrfs_orphan_del(NULL, inode);
+				btrfs_free_block_rsv(root, rsv);
+				goto no_delete;
+			}
+			continue;
+		} else {
+			steal_from_global = 0;
+		}
+
 		trans->block_rsv = rsv;
 
 		ret = btrfs_truncate_inode_items(trans, root, inode, 0, 0);
-		if (ret != -ENOSPC)
+		if (ret != -ENOSPC && ret != -EAGAIN)
 			break;
 
 		trans->block_rsv = &root->fs_info->trans_block_rsv;
@@ -7213,7 +7367,7 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
 	u64 start = iblock << inode->i_blkbits;
 	u64 lockstart, lockend;
 	u64 len = bh_result->b_size;
-	u64 orig_len = len;
+	u64 *outstanding_extents = NULL;
 	int unlock_bits = EXTENT_LOCKED;
 	int ret = 0;
 
@@ -7225,6 +7379,16 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
 	lockstart = start;
 	lockend = start + len - 1;
 
+	if (current->journal_info) {
+		/*
+		 * Need to pull our outstanding extents and set journal_info to NULL so
+		 * that anything that needs to check if there's a transction doesn't get
+		 * confused.
+		 */
+		outstanding_extents = current->journal_info;
+		current->journal_info = NULL;
+	}
+
 	/*
 	 * If this errors out it's because we couldn't invalidate pagecache for
 	 * this range and we need to fallback to buffered.
@@ -7285,7 +7449,6 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
 	    ((BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW) &&
 	     em->block_start != EXTENT_MAP_HOLE)) {
 		int type;
-		int ret;
 		u64 block_start, orig_start, orig_block_len, ram_bytes;
 
 		if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
@@ -7349,11 +7512,20 @@ unlock:
 		if (start + len > i_size_read(inode))
 			i_size_write(inode, start + len);
 
-		if (len < orig_len) {
+		/*
+		 * If we have an outstanding_extents count still set then we're
+		 * within our reservation, otherwise we need to adjust our inode
+		 * counter appropriately.
+		 */
+		if (*outstanding_extents) {
+			(*outstanding_extents)--;
+		} else {
 			spin_lock(&BTRFS_I(inode)->lock);
 			BTRFS_I(inode)->outstanding_extents++;
 			spin_unlock(&BTRFS_I(inode)->lock);
 		}
+
+		current->journal_info = outstanding_extents;
 		btrfs_free_reserved_data_space(inode, len);
 	}
 
@@ -7377,6 +7549,8 @@ unlock:
 unlock_err:
 	clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockend,
 			 unlock_bits, 1, 0, &cached_state, GFP_NOFS);
+	if (outstanding_extents)
+		current->journal_info = outstanding_extents;
 	return ret;
 }
 
@@ -8038,7 +8212,7 @@ free_ordered:
 	bio_endio(dio_bio, ret);
 }
 
-static ssize_t check_direct_IO(struct btrfs_root *root, int rw, struct kiocb *iocb,
+static ssize_t check_direct_IO(struct btrfs_root *root, struct kiocb *iocb,
 			const struct iov_iter *iter, loff_t offset)
 {
 	int seg;
@@ -8053,7 +8227,7 @@ static ssize_t check_direct_IO(struct btrfs_root *root, int rw, struct kiocb *io
 		goto out;
 
 	/* If this is a write we don't need to check anymore */
-	if (rw & WRITE)
+	if (iov_iter_rw(iter) == WRITE)
 		return 0;
 	/*
 	 * Check to make sure we don't have duplicate iov_base's in this
@@ -8071,18 +8245,19 @@ out:
 	return retval;
 }
 
-static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,
-			struct iov_iter *iter, loff_t offset)
+static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
+			       loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
+	u64 outstanding_extents = 0;
 	size_t count = 0;
 	int flags = 0;
 	bool wakeup = true;
 	bool relock = false;
 	ssize_t ret;
 
-	if (check_direct_IO(BTRFS_I(inode)->root, rw, iocb, iter, offset))
+	if (check_direct_IO(BTRFS_I(inode)->root, iocb, iter, offset))
 		return 0;
 
 	atomic_inc(&inode->i_dio_count);
@@ -8100,7 +8275,7 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,
 		filemap_fdatawrite_range(inode->i_mapping, offset,
 					 offset + count - 1);
 
-	if (rw & WRITE) {
+	if (iov_iter_rw(iter) == WRITE) {
 		/*
 		 * If the write DIO is beyond the EOF, we need update
 		 * the isize, but it is protected by i_mutex. So we can
@@ -8113,6 +8288,16 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,
 		ret = btrfs_delalloc_reserve_space(inode, count);
 		if (ret)
 			goto out;
+		outstanding_extents = div64_u64(count +
+						BTRFS_MAX_EXTENT_SIZE - 1,
+						BTRFS_MAX_EXTENT_SIZE);
+
+		/*
+		 * We need to know how many extents we reserved so that we can
+		 * do the accounting properly if we go over the number we
+		 * originally calculated.  Abuse current->journal_info for this.
+		 */
+		current->journal_info = &outstanding_extents;
 	} else if (test_bit(BTRFS_INODE_READDIO_NEED_LOCK,
 				     &BTRFS_I(inode)->runtime_flags)) {
 		inode_dio_done(inode);
@@ -8120,11 +8305,12 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,
 		wakeup = false;
 	}
 
-	ret = __blockdev_direct_IO(rw, iocb, inode,
-			BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev,
-			iter, offset, btrfs_get_blocks_direct, NULL,
-			btrfs_submit_direct, flags);
-	if (rw & WRITE) {
+	ret = __blockdev_direct_IO(iocb, inode,
+				   BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev,
+				   iter, offset, btrfs_get_blocks_direct, NULL,
+				   btrfs_submit_direct, flags);
+	if (iov_iter_rw(iter) == WRITE) {
+		current->journal_info = NULL;
 		if (ret < 0 && ret != -EIOCBQUEUED)
 			btrfs_delalloc_release_space(inode, count);
 		else if (ret >= 0 && (size_t)ret < count)
@@ -8526,7 +8712,7 @@ static int btrfs_truncate(struct inode *inode)
 		ret = btrfs_truncate_inode_items(trans, root, inode,
 						 inode->i_size,
 						 BTRFS_EXTENT_DATA_KEY);
-		if (ret != -ENOSPC) {
+		if (ret != -ENOSPC && ret != -EAGAIN) {
 			err = ret;
 			break;
 		}
@@ -9396,6 +9582,7 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
 				btrfs_end_transaction(trans, root);
 			break;
 		}
+
 		btrfs_drop_extent_cache(inode, cur_offset,
 					cur_offset + ins.offset -1, 0);