Btrfs: avoid sleeping in verify_parent_transid while atomic

verify_parent_transid needs to lock the extent range to make
sure no IO is underway, and so it can safely clear the
uptodate bits if our checks fail.

But, a few callers are using it with spinlocks held.  Most
of the time, the generation numbers are going to match, and
we don't want to switch to a blocking lock just for the error
case.  This adds an atomic flag to verify_parent_transid,
and changes it to return EAGAIN if it needs to block to
properly verifiy things.

Signed-off-by: Chris Mason <chris.mason@oracle.com>

5 files changed, 34 insertions, 17 deletions

diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 086303b9be64..4106264fbc65 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -725,7 +725,7 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans,
 
                 cur = btrfs_find_tree_block(root, blocknr, blocksize);
                 if (cur)
-                        uptodate = btrfs_buffer_uptodate(cur, gen);
+                        uptodate = btrfs_buffer_uptodate(cur, gen, 0);
                 else
                         uptodate = 0;
                 if (!cur || !uptodate) {
@@ -1360,7 +1360,12 @@ static noinline int reada_for_balance(struct btrfs_root *root,
                 block1 = btrfs_node_blockptr(parent, slot - 1);
                 gen = btrfs_node_ptr_generation(parent, slot - 1);
                 eb = btrfs_find_tree_block(root, block1, blocksize);
-                if (eb && btrfs_buffer_uptodate(eb, gen))
+                /*
+                 * if we get -eagain from btrfs_buffer_uptodate, we
+                 * don't want to return eagain here.  That will loop
+                 * forever
+                 */
+                if (eb && btrfs_buffer_uptodate(eb, gen, 1) != 0)
                         block1 = 0;
                 free_extent_buffer(eb);
         }
@@ -1368,7 +1373,7 @@ static noinline int reada_for_balance(struct btrfs_root *root,
                 block2 = btrfs_node_blockptr(parent, slot + 1);
                 gen = btrfs_node_ptr_generation(parent, slot + 1);
                 eb = btrfs_find_tree_block(root, block2, blocksize);
-                if (eb && btrfs_buffer_uptodate(eb, gen))
+                if (eb && btrfs_buffer_uptodate(eb, gen, 1) != 0)
                         block2 = 0;
                 free_extent_buffer(eb);
         }
@@ -1506,8 +1511,9 @@ read_block_for_search(struct btrfs_trans_handle *trans,
 
         tmp = btrfs_find_tree_block(root, blocknr, blocksize);
         if (tmp) {
-                if (btrfs_buffer_uptodate(tmp, 0)) {
-                        if (btrfs_buffer_uptodate(tmp, gen)) {
+                /* first we do an atomic uptodate check */
+                if (btrfs_buffer_uptodate(tmp, 0, 1) > 0) {
+                        if (btrfs_buffer_uptodate(tmp, gen, 1) > 0) {
                                 /*
                                  * we found an up to date block without
                                  * sleeping, return
@@ -1525,8 +1531,9 @@ read_block_for_search(struct btrfs_trans_handle *trans,
                         free_extent_buffer(tmp);
                         btrfs_set_path_blocking(p);
 
+                        /* now we're allowed to do a blocking uptodate check */
                         tmp = read_tree_block(root, blocknr, blocksize, gen);
-                        if (tmp && btrfs_buffer_uptodate(tmp, gen)) {
+                        if (tmp && btrfs_buffer_uptodate(tmp, gen, 0) > 0) {
                                 *eb_ret = tmp;
                                 return 0;
                         }
@@ -1561,7 +1568,7 @@ read_block_for_search(struct btrfs_trans_handle *trans,
                  * and give up so that our caller doesn't loop forever
                  * on our EAGAINs.
                  */
-                if (!btrfs_buffer_uptodate(tmp, 0))
+                if (!btrfs_buffer_uptodate(tmp, 0, 0))
                         ret = -EIO;
                 free_extent_buffer(tmp);
         }
@@ -4045,7 +4052,7 @@ again:
                         tmp = btrfs_find_tree_block(root, blockptr,
                                             btrfs_level_size(root, level - 1));
 
-                        if (tmp && btrfs_buffer_uptodate(tmp, gen)) {
+                        if (tmp && btrfs_buffer_uptodate(tmp, gen, 1) > 0) {
                                 free_extent_buffer(tmp);
                                 break;
                         }
@@ -4168,7 +4175,8 @@ next:
                                 struct extent_buffer *cur;
                                 cur = btrfs_find_tree_block(root, blockptr,
                                             btrfs_level_size(root, level - 1));
-                                if (!cur || !btrfs_buffer_uptodate(cur, gen)) {
+                                if (!cur ||
+                                    btrfs_buffer_uptodate(cur, gen, 1) <= 0) {
                                         slot++;
                                         if (cur)
                                                 free_extent_buffer(cur);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index d0c969beaad4..a7ffc88a7dbe 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -323,7 +323,8 @@ static int csum_tree_block(struct btrfs_root *root, struct extent_buffer *buf,
  * in the wrong place.
  */
 static int verify_parent_transid(struct extent_io_tree *io_tree,
-                                 struct extent_buffer *eb, u64 parent_transid)
+                                 struct extent_buffer *eb, u64 parent_transid,
+                                 int atomic)
 {
         struct extent_state *cached_state = NULL;
         int ret;
@@ -331,6 +332,9 @@ static int verify_parent_transid(struct extent_io_tree *io_tree,
         if (!parent_transid || btrfs_header_generation(eb) == parent_transid)
                 return 0;
 
+        if (atomic)
+                return -EAGAIN;
+
         lock_extent_bits(io_tree, eb->start, eb->start + eb->len - 1,
                          0, &cached_state);
         if (extent_buffer_uptodate(eb) &&
@@ -372,7 +376,8 @@ static int btree_read_extent_buffer_pages(struct btrfs_root *root,
                 ret = read_extent_buffer_pages(io_tree, eb, start,
                                                WAIT_COMPLETE,
                                                btree_get_extent, mirror_num);
-                if (!ret && !verify_parent_transid(io_tree, eb, parent_transid))
+                if (!ret && !verify_parent_transid(io_tree, eb,
+                                                   parent_transid, 0))
                         break;
 
                 /*
@@ -1202,7 +1207,7 @@ static int __must_check find_and_setup_root(struct btrfs_root *tree_root,
         root->commit_root = NULL;
         root->node = read_tree_block(root, btrfs_root_bytenr(&root->root_item),
                                      blocksize, generation);
-        if (!root->node || !btrfs_buffer_uptodate(root->node, generation)) {
+        if (!root->node || !btrfs_buffer_uptodate(root->node, generation, 0)) {
                 free_extent_buffer(root->node);
                 root->node = NULL;
                 return -EIO;
@@ -3143,7 +3148,8 @@ int close_ctree(struct btrfs_root *root)
         return 0;
 }
 
-int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid)
+int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid,
+                          int atomic)
 {
         int ret;
         struct inode *btree_inode = buf->pages[0]->mapping->host;
@@ -3153,7 +3159,9 @@ int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid)
                 return ret;
 
         ret = verify_parent_transid(&BTRFS_I(btree_inode)->io_tree, buf,
-                                    parent_transid);
+                                    parent_transid, atomic);
+        if (ret == -EAGAIN)
+                return ret;
         return !ret;
 }
 
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index a7ace1a2dd12..ab1830aaf0ed 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -66,7 +66,8 @@ void btrfs_btree_balance_dirty(struct btrfs_root *root, unsigned long nr);
 void __btrfs_btree_balance_dirty(struct btrfs_root *root, unsigned long nr);
 void btrfs_free_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root);
 void btrfs_mark_buffer_dirty(struct extent_buffer *buf);
-int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid);
+int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid,
+                          int atomic);
 int btrfs_set_buffer_uptodate(struct extent_buffer *buf);
 int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid);
 u32 btrfs_csum_data(struct btrfs_root *root, char *data, u32 seed, size_t len);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 6fc2e6f5aab8..49fd7b66d57b 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -6568,7 +6568,7 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
                         goto skip;
         }
 
-        if (!btrfs_buffer_uptodate(next, generation)) {
+        if (!btrfs_buffer_uptodate(next, generation, 0)) {
                 btrfs_tree_unlock(next);
                 free_extent_buffer(next);
                 next = NULL;
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index d017283ae6f5..eb1ae908582c 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -279,7 +279,7 @@ static int process_one_buffer(struct btrfs_root *log,
                                                 log->fs_info->extent_root,
                                                 eb->start, eb->len);
 
-        if (btrfs_buffer_uptodate(eb, gen)) {
+        if (btrfs_buffer_uptodate(eb, gen, 0)) {
                 if (wc->write)
                         btrfs_write_tree_block(eb);
                 if (wc->wait)