1 files changed, 78 insertions, 38 deletions

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index b231ae13b269..07b3ac662e19 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -100,38 +100,83 @@ struct async_submit_bio {
         struct btrfs_work work;
 };
 
-/* These are used to set the lockdep class on the extent buffer locks.
- * The class is set by the readpage_end_io_hook after the buffer has
- * passed csum validation but before the pages are unlocked.
+/*
+ * Lockdep class keys for extent_buffer->lock's in this root.  For a given
+ * eb, the lockdep key is determined by the btrfs_root it belongs to and
+ * the level the eb occupies in the tree.
+ *
+ * Different roots are used for different purposes and may nest inside each
+ * other and they require separate keysets.  As lockdep keys should be
+ * static, assign keysets according to the purpose of the root as indicated
+ * by btrfs_root->objectid.  This ensures that all special purpose roots
+ * have separate keysets.
  *
- * The lockdep class is also set by btrfs_init_new_buffer on freshly
- * allocated blocks.
+ * Lock-nesting across peer nodes is always done with the immediate parent
+ * node locked thus preventing deadlock.  As lockdep doesn't know this, use
+ * subclass to avoid triggering lockdep warning in such cases.
  *
- * The class is based on the level in the tree block, which allows lockdep
- * to know that lower nodes nest inside the locks of higher nodes.
+ * The key is set by the readpage_end_io_hook after the buffer has passed
+ * csum validation but before the pages are unlocked.  It is also set by
+ * btrfs_init_new_buffer on freshly allocated blocks.
  *
- * We also add a check to make sure the highest level of the tree is
- * the same as our lockdep setup here.  If BTRFS_MAX_LEVEL changes, this
- * code needs update as well.
+ * We also add a check to make sure the highest level of the tree is the
+ * same as our lockdep setup here.  If BTRFS_MAX_LEVEL changes, this code
+ * needs update as well.
  */
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 # if BTRFS_MAX_LEVEL != 8
 #  error
 # endif
-static struct lock_class_key btrfs_eb_class[BTRFS_MAX_LEVEL + 1];
-static const char *btrfs_eb_name[BTRFS_MAX_LEVEL + 1] = {
-        /* leaf */
-        "btrfs-extent-00",
-        "btrfs-extent-01",
-        "btrfs-extent-02",
-        "btrfs-extent-03",
-        "btrfs-extent-04",
-        "btrfs-extent-05",
-        "btrfs-extent-06",
-        "btrfs-extent-07",
-        /* highest possible level */
-        "btrfs-extent-08",
+
+static struct btrfs_lockdep_keyset {
+        u64                     id;             /* root objectid */
+        const char              *name_stem;     /* lock name stem */
+        char                    names[BTRFS_MAX_LEVEL + 1][20];
+        struct lock_class_key   keys[BTRFS_MAX_LEVEL + 1];
+} btrfs_lockdep_keysets[] = {
+        { .id = BTRFS_ROOT_TREE_OBJECTID,       .name_stem = "root"     },
+        { .id = BTRFS_EXTENT_TREE_OBJECTID,     .name_stem = "extent"   },
+        { .id = BTRFS_CHUNK_TREE_OBJECTID,      .name_stem = "chunk"    },
+        { .id = BTRFS_DEV_TREE_OBJECTID,        .name_stem = "dev"      },
+        { .id = BTRFS_FS_TREE_OBJECTID,         .name_stem = "fs"       },
+        { .id = BTRFS_CSUM_TREE_OBJECTID,       .name_stem = "csum"     },
+        { .id = BTRFS_ORPHAN_OBJECTID,          .name_stem = "orphan"   },
+        { .id = BTRFS_TREE_LOG_OBJECTID,        .name_stem = "log"      },
+        { .id = BTRFS_TREE_RELOC_OBJECTID,      .name_stem = "treloc"   },
+        { .id = BTRFS_DATA_RELOC_TREE_OBJECTID, .name_stem = "dreloc"   },
+        { .id = 0,                              .name_stem = "tree"     },
 };
+
+void __init btrfs_init_lockdep(void)
+{
+        int i, j;
+
+        /* initialize lockdep class names */
+        for (i = 0; i < ARRAY_SIZE(btrfs_lockdep_keysets); i++) {
+                struct btrfs_lockdep_keyset *ks = &btrfs_lockdep_keysets[i];
+
+                for (j = 0; j < ARRAY_SIZE(ks->names); j++)
+                        snprintf(ks->names[j], sizeof(ks->names[j]),
+                                 "btrfs-%s-%02d", ks->name_stem, j);
+        }
+}
+
+void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb,
+                                    int level)
+{
+        struct btrfs_lockdep_keyset *ks;
+
+        BUG_ON(level >= ARRAY_SIZE(ks->keys));
+
+        /* find the matching keyset, id 0 is the default entry */
+        for (ks = btrfs_lockdep_keysets; ks->id; ks++)
+                if (ks->id == objectid)
+                        break;
+
+        lockdep_set_class_and_name(&eb->lock,
+                                   &ks->keys[level], ks->names[level]);
+}
+
 #endif
 
 /*
@@ -217,7 +262,6 @@ static int csum_tree_block(struct btrfs_root *root, struct extent_buffer *buf,
         unsigned long len;
         unsigned long cur_len;
         unsigned long offset = BTRFS_CSUM_SIZE;
-        char *map_token = NULL;
         char *kaddr;
         unsigned long map_start;
         unsigned long map_len;
@@ -228,8 +272,7 @@ static int csum_tree_block(struct btrfs_root *root, struct extent_buffer *buf,
         len = buf->len - offset;
         while (len > 0) {
                 err = map_private_extent_buffer(buf, offset, 32,
-                                        &map_token, &kaddr,
-                                        &map_start, &map_len, KM_USER0);
+                                        &kaddr, &map_start, &map_len);
                 if (err)
                         return 1;
                 cur_len = min(len, map_len - (offset - map_start));
@@ -237,7 +280,6 @@ static int csum_tree_block(struct btrfs_root *root, struct extent_buffer *buf,
                                       crc, cur_len);
                 len -= cur_len;
                 offset += cur_len;
-                unmap_extent_buffer(buf, map_token, KM_USER0);
         }
         if (csum_size > sizeof(inline_result)) {
                 result = kzalloc(csum_size * sizeof(char), GFP_NOFS);
@@ -494,15 +536,6 @@ static noinline int check_leaf(struct btrfs_root *root,
         return 0;
 }
 
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-void btrfs_set_buffer_lockdep_class(struct extent_buffer *eb, int level)
-{
-        lockdep_set_class_and_name(&eb->lock,
-                           &btrfs_eb_class[level],
-                           btrfs_eb_name[level]);
-}
-#endif
-
 static int btree_readpage_end_io_hook(struct page *page, u64 start, u64 end,
                                struct extent_state *state)
 {
@@ -553,7 +586,8 @@ static int btree_readpage_end_io_hook(struct page *page, u64 start, u64 end,
         }
         found_level = btrfs_header_level(eb);
 
-        btrfs_set_buffer_lockdep_class(eb, found_level);
+        btrfs_set_buffer_lockdep_class(btrfs_header_owner(eb),
+                                       eb, found_level);
 
         ret = csum_tree_block(root, eb, 1);
         if (ret) {
@@ -1598,7 +1632,7 @@ struct btrfs_root *open_ctree(struct super_block *sb,
                 goto fail_bdi;
         }
 
-        fs_info->btree_inode->i_mapping->flags &= ~__GFP_FS;
+        mapping_set_gfp_mask(fs_info->btree_inode->i_mapping, GFP_NOFS);
 
         INIT_RADIX_TREE(&fs_info->fs_roots_radix, GFP_ATOMIC);
         INIT_LIST_HEAD(&fs_info->trans_list);
@@ -1802,6 +1836,9 @@ struct btrfs_root *open_ctree(struct super_block *sb,
                            fs_info->thread_pool_size),
                            &fs_info->generic_worker);
 
+        btrfs_init_workers(&fs_info->caching_workers, "cache",
+                           2, &fs_info->generic_worker);
+
         /* a higher idle thresh on the submit workers makes it much more
          * likely that bios will be send down in a sane order to the
          * devices
@@ -1855,6 +1892,7 @@ struct btrfs_root *open_ctree(struct super_block *sb,
         btrfs_start_workers(&fs_info->endio_write_workers, 1);
         btrfs_start_workers(&fs_info->endio_freespace_worker, 1);
         btrfs_start_workers(&fs_info->delayed_workers, 1);
+        btrfs_start_workers(&fs_info->caching_workers, 1);
 
         fs_info->bdi.ra_pages *= btrfs_super_num_devices(disk_super);
         fs_info->bdi.ra_pages = max(fs_info->bdi.ra_pages,
@@ -2112,6 +2150,7 @@ fail_sb_buffer:
         btrfs_stop_workers(&fs_info->endio_freespace_worker);
         btrfs_stop_workers(&fs_info->submit_workers);
         btrfs_stop_workers(&fs_info->delayed_workers);
+        btrfs_stop_workers(&fs_info->caching_workers);
 fail_alloc:
         kfree(fs_info->delayed_root);
 fail_iput:
@@ -2577,6 +2616,7 @@ int close_ctree(struct btrfs_root *root)
         btrfs_stop_workers(&fs_info->endio_freespace_worker);
         btrfs_stop_workers(&fs_info->submit_workers);
         btrfs_stop_workers(&fs_info->delayed_workers);
+        btrfs_stop_workers(&fs_info->caching_workers);
 
         btrfs_close_devices(fs_info->fs_devices);
         btrfs_mapping_tree_free(&fs_info->mapping_tree);