1 files changed, 195 insertions, 156 deletions

diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 23cb8da3ff6..225302b39af 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -1,8 +1,8 @@
 #include <linux/err.h>
 #include <linux/slab.h>
-#include <linux/module.h>
 #include <linux/spinlock.h>
 #include <linux/hardirq.h>
+#include "ctree.h"
 #include "extent_map.h"
 
 
@@ -10,7 +10,7 @@ static struct kmem_cache *extent_map_cache;
 
 int __init extent_map_init(void)
 {
-	extent_map_cache = kmem_cache_create("extent_map",
+	extent_map_cache = kmem_cache_create("btrfs_extent_map",
 			sizeof(struct extent_map), 0,
 			SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, NULL);
 	if (!extent_map_cache)
@@ -27,34 +27,36 @@ void extent_map_exit(void)
 /**
  * extent_map_tree_init - initialize extent map tree
  * @tree:		tree to initialize
- * @mask:		flags for memory allocations during tree operations
  *
  * Initialize the extent tree @tree.  Should be called for each new inode
  * or other user of the extent_map interface.
  */
-void extent_map_tree_init(struct extent_map_tree *tree, gfp_t mask)
+void extent_map_tree_init(struct extent_map_tree *tree)
 {
 	tree->map = RB_ROOT;
+	INIT_LIST_HEAD(&tree->modified_extents);
 	rwlock_init(&tree->lock);
 }
 
 /**
  * alloc_extent_map - allocate new extent map structure
- * @mask:	memory allocation flags
  *
  * Allocate a new extent_map structure.  The new structure is
  * returned with a reference count of one and needs to be
  * freed using free_extent_map()
  */
-struct extent_map *alloc_extent_map(gfp_t mask)
+struct extent_map *alloc_extent_map(void)
 {
 	struct extent_map *em;
-	em = kmem_cache_alloc(extent_map_cache, mask);
-	if (!em || IS_ERR(em))
-		return em;
-	em->in_tree = 0;
+	em = kmem_cache_zalloc(extent_map_cache, GFP_NOFS);
+	if (!em)
+		return NULL;
+	RB_CLEAR_NODE(&em->rb_node);
 	em->flags = 0;
+	em->compress_type = BTRFS_COMPRESS_NONE;
+	em->generation = 0;
 	atomic_set(&em->refs, 1);
+	INIT_LIST_HEAD(&em->list);
 	return em;
 }
 
@@ -71,37 +73,64 @@ void free_extent_map(struct extent_map *em)
 		return;
 	WARN_ON(atomic_read(&em->refs) == 0);
 	if (atomic_dec_and_test(&em->refs)) {
-		WARN_ON(em->in_tree);
+		WARN_ON(extent_map_in_tree(em));
+		WARN_ON(!list_empty(&em->list));
+		if (test_bit(EXTENT_FLAG_FS_MAPPING, &em->flags))
+			kfree(em->bdev);
 		kmem_cache_free(extent_map_cache, em);
 	}
 }
 
-static struct rb_node *tree_insert(struct rb_root *root, u64 offset,
-				   struct rb_node *node)
+/* simple helper to do math around the end of an extent, handling wrap */
+static u64 range_end(u64 start, u64 len)
+{
+	if (start + len < start)
+		return (u64)-1;
+	return start + len;
+}
+
+static int tree_insert(struct rb_root *root, struct extent_map *em)
 {
 	struct rb_node **p = &root->rb_node;
 	struct rb_node *parent = NULL;
-	struct extent_map *entry;
+	struct extent_map *entry = NULL;
+	struct rb_node *orig_parent = NULL;
+	u64 end = range_end(em->start, em->len);
 
 	while (*p) {
 		parent = *p;
 		entry = rb_entry(parent, struct extent_map, rb_node);
 
-		WARN_ON(!entry->in_tree);
-
-		if (offset < entry->start)
+		if (em->start < entry->start)
 			p = &(*p)->rb_left;
-		else if (offset >= extent_map_end(entry))
+		else if (em->start >= extent_map_end(entry))
 			p = &(*p)->rb_right;
 		else
-			return parent;
+			return -EEXIST;
 	}
 
-	entry = rb_entry(node, struct extent_map, rb_node);
-	entry->in_tree = 1;
-	rb_link_node(node, parent, p);
-	rb_insert_color(node, root);
-	return NULL;
+	orig_parent = parent;
+	while (parent && em->start >= extent_map_end(entry)) {
+		parent = rb_next(parent);
+		entry = rb_entry(parent, struct extent_map, rb_node);
+	}
+	if (parent)
+		if (end > entry->start && em->start < extent_map_end(entry))
+			return -EEXIST;
+
+	parent = orig_parent;
+	entry = rb_entry(parent, struct extent_map, rb_node);
+	while (parent && em->start < entry->start) {
+		parent = rb_prev(parent);
+		entry = rb_entry(parent, struct extent_map, rb_node);
+	}
+	if (parent)
+		if (end > entry->start && em->start < extent_map_end(entry))
+			return -EEXIST;
+
+	rb_link_node(&em->rb_node, orig_parent, p);
+	rb_insert_color(&em->rb_node, root);
+	return 0;
 }
 
 /*
@@ -123,8 +152,6 @@ static struct rb_node *__tree_search(struct rb_root *root, u64 offset,
 		prev = n;
 		prev_entry = entry;
 
-		WARN_ON(!entry->in_tree);
-
 		if (offset < entry->start)
 			n = n->rb_left;
 		else if (offset >= extent_map_end(entry))
@@ -167,6 +194,18 @@ static int mergable_maps(struct extent_map *prev, struct extent_map *next)
 	if (test_bit(EXTENT_FLAG_COMPRESSED, &prev->flags))
 		return 0;
 
+	if (test_bit(EXTENT_FLAG_LOGGING, &prev->flags) ||
+	    test_bit(EXTENT_FLAG_LOGGING, &next->flags))
+		return 0;
+
+	/*
+	 * We don't want to merge stuff that hasn't been written to the log yet
+	 * since it may not reflect exactly what is on disk, and that would be
+	 * bad.
+	 */
+	if (!list_empty(&prev->list) || !list_empty(&next->list))
+		return 0;
+
 	if (extent_map_end(prev) == next->start &&
 	    prev->flags == next->flags &&
 	    prev->bdev == next->bdev &&
@@ -183,22 +222,10 @@ static int mergable_maps(struct extent_map *prev, struct extent_map *next)
 	return 0;
 }
 
-int unpin_extent_cache(struct extent_map_tree *tree, u64 start, u64 len)
+static void try_merge_map(struct extent_map_tree *tree, struct extent_map *em)
 {
-	int ret = 0;
 	struct extent_map *merge = NULL;
 	struct rb_node *rb;
-	struct extent_map *em;
-
-	write_lock(&tree->lock);
-	em = lookup_extent_mapping(tree, start, len);
-
-	WARN_ON(!em || em->start != start);
-
-	if (!em)
-		goto out;
-
-	clear_bit(EXTENT_FLAG_PINNED, &em->flags);
 
 	if (em->start != 0) {
 		rb = rb_prev(&em->rb_node);
@@ -206,11 +233,16 @@ int unpin_extent_cache(struct extent_map_tree *tree, u64 start, u64 len)
 			merge = rb_entry(rb, struct extent_map, rb_node);
 		if (rb && mergable_maps(merge, em)) {
 			em->start = merge->start;
+			em->orig_start = merge->orig_start;
 			em->len += merge->len;
 			em->block_len += merge->block_len;
 			em->block_start = merge->block_start;
-			merge->in_tree = 0;
+			em->mod_len = (em->mod_len + em->mod_start) - merge->mod_start;
+			em->mod_start = merge->mod_start;
+			em->generation = max(em->generation, merge->generation);
+
 			rb_erase(&merge->rb_node, &tree->map);
+			RB_CLEAR_NODE(&merge->rb_node);
 			free_extent_map(merge);
 		}
 	}
@@ -220,11 +252,59 @@ int unpin_extent_cache(struct extent_map_tree *tree, u64 start, u64 len)
 		merge = rb_entry(rb, struct extent_map, rb_node);
 	if (rb && mergable_maps(em, merge)) {
 		em->len += merge->len;
-		em->block_len += merge->len;
+		em->block_len += merge->block_len;
 		rb_erase(&merge->rb_node, &tree->map);
-		merge->in_tree = 0;
+		RB_CLEAR_NODE(&merge->rb_node);
+		em->mod_len = (merge->mod_start + merge->mod_len) - em->mod_start;
+		em->generation = max(em->generation, merge->generation);
 		free_extent_map(merge);
 	}
+}
+
+/**
+ * unpin_extent_cache - unpin an extent from the cache
+ * @tree:	tree to unpin the extent in
+ * @start:	logical offset in the file
+ * @len:	length of the extent
+ * @gen:	generation that this extent has been modified in
+ *
+ * Called after an extent has been written to disk properly.  Set the generation
+ * to the generation that actually added the file item to the inode so we know
+ * we need to sync this extent when we call fsync().
+ */
+int unpin_extent_cache(struct extent_map_tree *tree, u64 start, u64 len,
+		       u64 gen)
+{
+	int ret = 0;
+	struct extent_map *em;
+	bool prealloc = false;
+
+	write_lock(&tree->lock);
+	em = lookup_extent_mapping(tree, start, len);
+
+	WARN_ON(!em || em->start != start);
+
+	if (!em)
+		goto out;
+
+	if (!test_bit(EXTENT_FLAG_LOGGING, &em->flags))
+		list_move(&em->list, &tree->modified_extents);
+	em->generation = gen;
+	clear_bit(EXTENT_FLAG_PINNED, &em->flags);
+	em->mod_start = em->start;
+	em->mod_len = em->len;
+
+	if (test_bit(EXTENT_FLAG_FILLING, &em->flags)) {
+		prealloc = true;
+		clear_bit(EXTENT_FLAG_FILLING, &em->flags);
+	}
+
+	try_merge_map(tree, em);
+
+	if (prealloc) {
+		em->mod_start = em->start;
+		em->mod_len = em->len;
+	}
 
 	free_extent_map(em);
 out:
@@ -233,6 +313,27 @@ out:
 
 }
 
+void clear_em_logging(struct extent_map_tree *tree, struct extent_map *em)
+{
+	clear_bit(EXTENT_FLAG_LOGGING, &em->flags);
+	if (extent_map_in_tree(em))
+		try_merge_map(tree, em);
+}
+
+static inline void setup_extent_mapping(struct extent_map_tree *tree,
+					struct extent_map *em,
+					int modified)
+{
+	atomic_inc(&em->refs);
+	em->mod_start = em->start;
+	em->mod_len = em->len;
+
+	if (modified)
+		list_move(&em->list, &tree->modified_extents);
+	else
+		try_merge_map(tree, em);
+}
+
 /**
  * add_extent_mapping - add new extent map to the extent tree
  * @tree:	tree to insert new map in
@@ -241,62 +342,49 @@ out:
  * Insert @em into @tree or perform a simple forward/backward merge with
  * existing mappings.  The extent_map struct passed in will be inserted
  * into the tree directly, with an additional reference taken, or a
- * reference dropped if the merge attempt was successfull.
+ * reference dropped if the merge attempt was successful.
  */
 int add_extent_mapping(struct extent_map_tree *tree,
-		       struct extent_map *em)
+		       struct extent_map *em, int modified)
 {
 	int ret = 0;
-	struct extent_map *merge = NULL;
-	struct rb_node *rb;
-	struct extent_map *exist;
 
-	exist = lookup_extent_mapping(tree, em->start, em->len);
-	if (exist) {
-		free_extent_map(exist);
-		ret = -EEXIST;
+	ret = tree_insert(&tree->map, em);
+	if (ret)
 		goto out;
-	}
-	rb = tree_insert(&tree->map, em->start, &em->rb_node);
-	if (rb) {
-		ret = -EEXIST;
-		goto out;
-	}
-	atomic_inc(&em->refs);
-	if (em->start != 0) {
-		rb = rb_prev(&em->rb_node);
-		if (rb)
-			merge = rb_entry(rb, struct extent_map, rb_node);
-		if (rb && mergable_maps(merge, em)) {
-			em->start = merge->start;
-			em->len += merge->len;
-			em->block_len += merge->block_len;
-			em->block_start = merge->block_start;
-			merge->in_tree = 0;
-			rb_erase(&merge->rb_node, &tree->map);
-			free_extent_map(merge);
-		}
-	 }
-	rb = rb_next(&em->rb_node);
-	if (rb)
-		merge = rb_entry(rb, struct extent_map, rb_node);
-	if (rb && mergable_maps(em, merge)) {
-		em->len += merge->len;
-		em->block_len += merge->len;
-		rb_erase(&merge->rb_node, &tree->map);
-		merge->in_tree = 0;
-		free_extent_map(merge);
-	}
+
+	setup_extent_mapping(tree, em, modified);
 out:
 	return ret;
 }
 
-/* simple helper to do math around the end of an extent, handling wrap */
-static u64 range_end(u64 start, u64 len)
+static struct extent_map *
+__lookup_extent_mapping(struct extent_map_tree *tree,
+			u64 start, u64 len, int strict)
 {
-	if (start + len < start)
-		return (u64)-1;
-	return start + len;
+	struct extent_map *em;
+	struct rb_node *rb_node;
+	struct rb_node *prev = NULL;
+	struct rb_node *next = NULL;
+	u64 end = range_end(start, len);
+
+	rb_node = __tree_search(&tree->map, start, &prev, &next);
+	if (!rb_node) {
+		if (prev)
+			rb_node = prev;
+		else if (next)
+			rb_node = next;
+		else
+			return NULL;
+	}
+
+	em = rb_entry(rb_node, struct extent_map, rb_node);
+
+	if (strict && !(end > em->start && start < extent_map_end(em)))
+		return NULL;
+
+	atomic_inc(&em->refs);
+	return em;
 }
 
 /**
@@ -313,42 +401,7 @@ static u64 range_end(u64 start, u64 len)
 struct extent_map *lookup_extent_mapping(struct extent_map_tree *tree,
 					 u64 start, u64 len)
 {
-	struct extent_map *em;
-	struct rb_node *rb_node;
-	struct rb_node *prev = NULL;
-	struct rb_node *next = NULL;
-	u64 end = range_end(start, len);
-
-	rb_node = __tree_search(&tree->map, start, &prev, &next);
-	if (!rb_node && prev) {
-		em = rb_entry(prev, struct extent_map, rb_node);
-		if (end > em->start && start < extent_map_end(em))
-			goto found;
-	}
-	if (!rb_node && next) {
-		em = rb_entry(next, struct extent_map, rb_node);
-		if (end > em->start && start < extent_map_end(em))
-			goto found;
-	}
-	if (!rb_node) {
-		em = NULL;
-		goto out;
-	}
-	if (IS_ERR(rb_node)) {
-		em = ERR_CAST(rb_node);
-		goto out;
-	}
-	em = rb_entry(rb_node, struct extent_map, rb_node);
-	if (end > em->start && start < extent_map_end(em))
-		goto found;
-
-	em = NULL;
-	goto out;
-
-found:
-	atomic_inc(&em->refs);
-out:
-	return em;
+	return __lookup_extent_mapping(tree, start, len, 1);
 }
 
 /**
@@ -365,38 +418,7 @@ out:
 struct extent_map *search_extent_mapping(struct extent_map_tree *tree,
 					 u64 start, u64 len)
 {
-	struct extent_map *em;
-	struct rb_node *rb_node;
-	struct rb_node *prev = NULL;
-	struct rb_node *next = NULL;
-
-	rb_node = __tree_search(&tree->map, start, &prev, &next);
-	if (!rb_node && prev) {
-		em = rb_entry(prev, struct extent_map, rb_node);
-		goto found;
-	}
-	if (!rb_node && next) {
-		em = rb_entry(next, struct extent_map, rb_node);
-		goto found;
-	}
-	if (!rb_node) {
-		em = NULL;
-		goto out;
-	}
-	if (IS_ERR(rb_node)) {
-		em = ERR_CAST(rb_node);
-		goto out;
-	}
-	em = rb_entry(rb_node, struct extent_map, rb_node);
-	goto found;
-
-	em = NULL;
-	goto out;
-
-found:
-	atomic_inc(&em->refs);
-out:
-	return em;
+	return __lookup_extent_mapping(tree, start, len, 0);
 }
 
 /**
@@ -413,6 +435,23 @@ int remove_extent_mapping(struct extent_map_tree *tree, struct extent_map *em)
 
 	WARN_ON(test_bit(EXTENT_FLAG_PINNED, &em->flags));
 	rb_erase(&em->rb_node, &tree->map);
-	em->in_tree = 0;
+	if (!test_bit(EXTENT_FLAG_LOGGING, &em->flags))
+		list_del_init(&em->list);
+	RB_CLEAR_NODE(&em->rb_node);
 	return ret;
 }
+
+void replace_extent_mapping(struct extent_map_tree *tree,
+			    struct extent_map *cur,
+			    struct extent_map *new,
+			    int modified)
+{
+	WARN_ON(test_bit(EXTENT_FLAG_PINNED, &cur->flags));
+	ASSERT(extent_map_in_tree(cur));
+	if (!test_bit(EXTENT_FLAG_LOGGING, &cur->flags))
+		list_del_init(&cur->list);
+	rb_replace_node(&cur->rb_node, &new->rb_node, &tree->map);
+	RB_CLEAR_NODE(&cur->rb_node);
+
+	setup_extent_mapping(tree, new, modified);
+}