diff options
Diffstat (limited to 'fs/btrfs/extent_io.c')
| -rw-r--r-- | fs/btrfs/extent_io.c | 3717 |
1 files changed, 3717 insertions, 0 deletions
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c new file mode 100644 index 00000000000..e086d407f1f --- /dev/null +++ b/fs/btrfs/extent_io.c @@ -0,0 +1,3717 @@ +#include <linux/bitops.h> +#include <linux/slab.h> +#include <linux/bio.h> +#include <linux/mm.h> +#include <linux/gfp.h> +#include <linux/pagemap.h> +#include <linux/page-flags.h> +#include <linux/module.h> +#include <linux/spinlock.h> +#include <linux/blkdev.h> +#include <linux/swap.h> +#include <linux/version.h> +#include <linux/writeback.h> +#include <linux/pagevec.h> +#include "extent_io.h" +#include "extent_map.h" +#include "compat.h" +#include "ctree.h" +#include "btrfs_inode.h" + +/* temporary define until extent_map moves out of btrfs */ +struct kmem_cache *btrfs_cache_create(const char *name, size_t size, + unsigned long extra_flags, + void (*ctor)(void *, struct kmem_cache *, + unsigned long)); + +static struct kmem_cache *extent_state_cache; +static struct kmem_cache *extent_buffer_cache; + +static LIST_HEAD(buffers); +static LIST_HEAD(states); + +#define LEAK_DEBUG 0 +#ifdef LEAK_DEBUG +static DEFINE_SPINLOCK(leak_lock); +#endif + +#define BUFFER_LRU_MAX 64 + +struct tree_entry { + u64 start; + u64 end; + struct rb_node rb_node; +}; + +struct extent_page_data { + struct bio *bio; + struct extent_io_tree *tree; + get_extent_t *get_extent; + + /* tells writepage not to lock the state bits for this range + * it still does the unlocking + */ + int extent_locked; +}; + +int __init extent_io_init(void) +{ + extent_state_cache = btrfs_cache_create("extent_state", + sizeof(struct extent_state), 0, + NULL); + if (!extent_state_cache) + return -ENOMEM; + + extent_buffer_cache = btrfs_cache_create("extent_buffers", + sizeof(struct extent_buffer), 0, + NULL); + if (!extent_buffer_cache) + goto free_state_cache; + return 0; + +free_state_cache: + kmem_cache_destroy(extent_state_cache); + return -ENOMEM; +} + +void extent_io_exit(void) +{ + struct extent_state *state; + struct extent_buffer *eb; + + while (!list_empty(&states)) { + state = list_entry(states.next, struct extent_state, leak_list); + printk(KERN_ERR "btrfs state leak: start %llu end %llu " + "state %lu in tree %p refs %d\n", + (unsigned long long)state->start, + (unsigned long long)state->end, + state->state, state->tree, atomic_read(&state->refs)); + list_del(&state->leak_list); + kmem_cache_free(extent_state_cache, state); + + } + + while (!list_empty(&buffers)) { + eb = list_entry(buffers.next, struct extent_buffer, leak_list); + printk(KERN_ERR "btrfs buffer leak start %llu len %lu " + "refs %d\n", (unsigned long long)eb->start, + eb->len, atomic_read(&eb->refs)); + list_del(&eb->leak_list); + kmem_cache_free(extent_buffer_cache, eb); + } + if (extent_state_cache) + kmem_cache_destroy(extent_state_cache); + if (extent_buffer_cache) + kmem_cache_destroy(extent_buffer_cache); +} + +void extent_io_tree_init(struct extent_io_tree *tree, + struct address_space *mapping, gfp_t mask) +{ + tree->state.rb_node = NULL; + tree->buffer.rb_node = NULL; + tree->ops = NULL; + tree->dirty_bytes = 0; + spin_lock_init(&tree->lock); + spin_lock_init(&tree->buffer_lock); + tree->mapping = mapping; +} + +static struct extent_state *alloc_extent_state(gfp_t mask) +{ + struct extent_state *state; +#ifdef LEAK_DEBUG + unsigned long flags; +#endif + + state = kmem_cache_alloc(extent_state_cache, mask); + if (!state) + return state; + state->state = 0; + state->private = 0; + state->tree = NULL; +#ifdef LEAK_DEBUG + spin_lock_irqsave(&leak_lock, flags); + list_add(&state->leak_list, &states); + spin_unlock_irqrestore(&leak_lock, flags); +#endif + atomic_set(&state->refs, 1); + init_waitqueue_head(&state->wq); + return state; +} + +static void free_extent_state(struct extent_state *state) +{ + if (!state) + return; + if (atomic_dec_and_test(&state->refs)) { +#ifdef LEAK_DEBUG + unsigned long flags; +#endif + WARN_ON(state->tree); +#ifdef LEAK_DEBUG + spin_lock_irqsave(&leak_lock, flags); + list_del(&state->leak_list); + spin_unlock_irqrestore(&leak_lock, flags); +#endif + kmem_cache_free(extent_state_cache, state); + } +} + +static struct rb_node *tree_insert(struct rb_root *root, u64 offset, + struct rb_node *node) +{ + struct rb_node **p = &root->rb_node; + struct rb_node *parent = NULL; + struct tree_entry *entry; + + while (*p) { + parent = *p; + entry = rb_entry(parent, struct tree_entry, rb_node); + + if (offset < entry->start) + p = &(*p)->rb_left; + else if (offset > entry->end) + p = &(*p)->rb_right; + else + return parent; + } + + entry = rb_entry(node, struct tree_entry, rb_node); + rb_link_node(node, parent, p); + rb_insert_color(node, root); + return NULL; +} + +static struct rb_node *__etree_search(struct extent_io_tree *tree, u64 offset, + struct rb_node **prev_ret, + struct rb_node **next_ret) +{ + struct rb_root *root = &tree->state; + struct rb_node *n = root->rb_node; + struct rb_node *prev = NULL; + struct rb_node *orig_prev = NULL; + struct tree_entry *entry; + struct tree_entry *prev_entry = NULL; + + while (n) { + entry = rb_entry(n, struct tree_entry, rb_node); + prev = n; + prev_entry = entry; + + if (offset < entry->start) + n = n->rb_left; + else if (offset > entry->end) + n = n->rb_right; + else + return n; + } + + if (prev_ret) { + orig_prev = prev; + while (prev && offset > prev_entry->end) { + prev = rb_next(prev); + prev_entry = rb_entry(prev, struct tree_entry, rb_node); + } + *prev_ret = prev; + prev = orig_prev; + } + + if (next_ret) { + prev_entry = rb_entry(prev, struct tree_entry, rb_node); + while (prev && offset < prev_entry->start) { + prev = rb_prev(prev); + prev_entry = rb_entry(prev, struct tree_entry, rb_node); + } + *next_ret = prev; + } + return NULL; +} + +static inline struct rb_node *tree_search(struct extent_io_tree *tree, + u64 offset) +{ + struct rb_node *prev = NULL; + struct rb_node *ret; + + ret = __etree_search(tree, offset, &prev, NULL); + if (!ret) + return prev; + return ret; +} + +static struct extent_buffer *buffer_tree_insert(struct extent_io_tree *tree, + u64 offset, struct rb_node *node) +{ + struct rb_root *root = &tree->buffer; + struct rb_node **p = &root->rb_node; + struct rb_node *parent = NULL; + struct extent_buffer *eb; + + while (*p) { + parent = *p; + eb = rb_entry(parent, struct extent_buffer, rb_node); + + if (offset < eb->start) + p = &(*p)->rb_left; + else if (offset > eb->start) + p = &(*p)->rb_right; + else + return eb; + } + + rb_link_node(node, parent, p); + rb_insert_color(node, root); + return NULL; +} + +static struct extent_buffer *buffer_search(struct extent_io_tree *tree, + u64 offset) +{ + struct rb_root *root = &tree->buffer; + struct rb_node *n = root->rb_node; + struct extent_buffer *eb; + + while (n) { + eb = rb_entry(n, struct extent_buffer, rb_node); + if (offset < eb->start) + n = n->rb_left; + else if (offset > eb->start) + n = n->rb_right; + else + return eb; + } + return NULL; +} + +/* + * utility function to look for merge candidates inside a given range. + * Any extents with matching state are merged together into a single + * extent in the tree. Extents with EXTENT_IO in their state field + * are not merged because the end_io handlers need to be able to do + * operations on them without sleeping (or doing allocations/splits). + * + * This should be called with the tree lock held. + */ +static int merge_state(struct extent_io_tree *tree, + struct extent_state *state) +{ + struct extent_state *other; + struct rb_node *other_node; + + if (state->state & (EXTENT_IOBITS | EXTENT_BOUNDARY)) + return 0; + + other_node = rb_prev(&state->rb_node); + if (other_node) { + other = rb_entry(other_node, struct extent_state, rb_node); + if (other->end == state->start - 1 && + other->state == state->state) { + state->start = other->start; + other->tree = NULL; + rb_erase(&other->rb_node, &tree->state); + free_extent_state(other); + } + } + other_node = rb_next(&state->rb_node); + if (other_node) { + other = rb_entry(other_node, struct extent_state, rb_node); + if (other->start == state->end + 1 && + other->state == state->state) { + other->start = state->start; + state->tree = NULL; + rb_erase(&state->rb_node, &tree->state); + free_extent_state(state); + } + } + return 0; +} + +static void set_state_cb(struct extent_io_tree *tree, + struct extent_state *state, + unsigned long bits) +{ + if (tree->ops && tree->ops->set_bit_hook) { + tree->ops->set_bit_hook(tree->mapping->host, state->start, + state->end, state->state, bits); + } +} + +static void clear_state_cb(struct extent_io_tree *tree, + struct extent_state *state, + unsigned long bits) +{ + if (tree->ops && tree->ops->clear_bit_hook) { + tree->ops->clear_bit_hook(tree->mapping->host, state->start, + state->end, state->state, bits); + } +} + +/* + * insert an extent_state struct into the tree. 'bits' are set on the + * struct before it is inserted. + * + * This may return -EEXIST if the extent is already there, in which case the + * state struct is freed. + * + * The tree lock is not taken internally. This is a utility function and + * probably isn't what you want to call (see set/clear_extent_bit). + */ +static int insert_state(struct extent_io_tree *tree, + struct extent_state *state, u64 start, u64 end, + int bits) +{ + struct rb_node *node; + + if (end < start) { + printk(KERN_ERR "btrfs end < start %llu %llu\n", + (unsigned long long)end, + (unsigned long long)start); + WARN_ON(1); + } + if (bits & EXTENT_DIRTY) + tree->dirty_bytes += end - start + 1; + set_state_cb(tree, state, bits); + state->state |= bits; + state->start = start; + state->end = end; + node = tree_insert(&tree->state, end, &state->rb_node); + if (node) { + struct extent_state *found; + found = rb_entry(node, struct extent_state, rb_node); + printk(KERN_ERR "btrfs found node %llu %llu on insert of " + "%llu %llu\n", (unsigned long long)found->start, + (unsigned long long)found->end, + (unsigned long long)start, (unsigned long long)end); + free_extent_state(state); + return -EEXIST; + } + state->tree = tree; + merge_state(tree, state); + return 0; +} + +/* + * split a given extent state struct in two, inserting the preallocated + * struct 'prealloc' as the newly created second half. 'split' indicates an + * offset inside 'orig' where it should be split. + * + * Before calling, + * the tree has 'orig' at [orig->start, orig->end]. After calling, there + * are two extent state structs in the tree: + * prealloc: [orig->start, split - 1] + * orig: [ split, orig->end ] + * + * The tree locks are not taken by this function. They need to be held + * by the caller. + */ +static int split_state(struct extent_io_tree *tree, struct extent_state *orig, + struct extent_state *prealloc, u64 split) +{ + struct rb_node *node; + prealloc->start = orig->start; + prealloc->end = split - 1; + prealloc->state = orig->state; + orig->start = split; + + node = tree_insert(&tree->state, prealloc->end, &prealloc->rb_node); + if (node) { + struct extent_state *found; + found = rb_entry(node, struct extent_state, rb_node); + free_extent_state(prealloc); + return -EEXIST; + } + prealloc->tree = tree; + return 0; +} + +/* + * utility function to clear some bits in an extent state struct. + * it will optionally wake up any one waiting on this state (wake == 1), or + * forcibly remove the state from the tree (delete == 1). + * + * If no bits are set on the state struct after clearing things, the + * struct is freed and removed from the tree + */ +static int clear_state_bit(struct extent_io_tree *tree, + struct extent_state *state, int bits, int wake, + int delete) +{ + int ret = state->state & bits; + + if ((bits & EXTENT_DIRTY) && (state->state & EXTENT_DIRTY)) { + u64 range = state->end - state->start + 1; + WARN_ON(range > tree->dirty_bytes); + tree->dirty_bytes -= range; + } + clear_state_cb(tree, state, bits); + state->state &= ~bits; + if (wake) + wake_up(&state->wq); + if (delete || state->state == 0) { + if (state->tree) { + clear_state_cb(tree, state, state->state); + rb_erase(&state->rb_node, &tree->state); + state->tree = NULL; + free_extent_state(state); + } else { + WARN_ON(1); + } + } else { + merge_state(tree, state); + } + return ret; +} + +/* + * clear some bits on a range in the tree. This may require splitting + * or inserting elements in the tree, so the gfp mask is used to + * indicate which allocations or sleeping are allowed. + * + * pass 'wake' == 1 to kick any sleepers, and 'delete' == 1 to remove + * the given range from the tree regardless of state (ie for truncate). + * + * the range [start, end] is inclusive. + * + * This takes the tree lock, and returns < 0 on error, > 0 if any of the + * bits were already set, or zero if none of the bits were already set. + */ +int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, + int bits, int wake, int delete, gfp_t mask) +{ + struct extent_state *state; + struct extent_state *prealloc = NULL; + struct rb_node *node; + int err; + int set = 0; + +again: + if (!prealloc && (mask & __GFP_WAIT)) { + prealloc = alloc_extent_state(mask); + if (!prealloc) + return -ENOMEM; + } + + spin_lock(&tree->lock); + /* + * this search will find the extents that end after + * our range starts + */ + node = tree_search(tree, start); + if (!node) + goto out; + state = rb_entry(node, struct extent_state, rb_node); + if (state->start > end) + goto out; + WARN_ON(state->end < start); + + /* + * | ---- desired range ---- | + * | state | or + * | ------------- state -------------- | + * + * We need to split the extent we found, and may flip + * bits on second half. + * + * If the extent we found extends past our range, we + * just split and search again. It'll get split again + * the next time though. + * + * If the extent we found is inside our range, we clear + * the desired bit on it. + */ + + if (state->start < start) { + if (!prealloc) + prealloc = alloc_extent_state(GFP_ATOMIC); + err = split_state(tree, state, prealloc, start); + BUG_ON(err == -EEXIST); + prealloc = NULL; + if (err) + goto out; + if (state->end <= end) { + start = state->end + 1; + set |= clear_state_bit(tree, state, bits, + wake, delete); + } else { + start = state->start; + } + goto search_again; + } + /* + * | ---- desired range ---- | + * | state | + * We need to split the extent, and clear the bit + * on the first half + */ + if (state->start <= end && state->end > end) { + if (!prealloc) + prealloc = alloc_extent_state(GFP_ATOMIC); + err = split_state(tree, state, prealloc, end + 1); + BUG_ON(err == -EEXIST); + + if (wake) + wake_up(&state->wq); + set |= clear_state_bit(tree, prealloc, bits, + wake, delete); + prealloc = NULL; + goto out; + } + + start = state->end + 1; + set |= clear_state_bit(tree, state, bits, wake, delete); + goto search_again; + +out: + spin_unlock(&tree->lock); + if (prealloc) + free_extent_state(prealloc); + + return set; + +search_again: + if (start > end) + goto out; + spin_unlock(&tree->lock); + if (mask & __GFP_WAIT) + cond_resched(); + goto again; +} + +static int wait_on_state(struct extent_io_tree *tree, + struct extent_state *state) + __releases(tree->lock) + __acquires(tree->lock) +{ + DEFINE_WAIT(wait); + prepare_to_wait(&state->wq, &wait, TASK_UNINTERRUPTIBLE); + spin_unlock(&tree->lock); + schedule(); + spin_lock(&tree->lock); + finish_wait(&state->wq, &wait); + return 0; +} + +/* + * waits for one or more bits to clear on a range in the state tree. + * The range [start, end] is inclusive. + * The tree lock is taken by this function + */ +int wait_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, int bits) +{ + struct extent_state *state; + struct rb_node *node; + + spin_lock(&tree->lock); +again: + while (1) { + /* + * this search will find all the extents that end after + * our range starts + */ + node = tree_search(tree, start); + if (!node) + break; + + state = rb_entry(node, struct extent_state, rb_node); + + if (state->start > end) + goto out; + + if (state->state & bits) { + start = state->start; + atomic_inc(&state->refs); + wait_on_state(tree, state); + free_extent_state(state); + goto again; + } + start = state->end + 1; + + if (start > end) + break; + + if (need_resched()) { + spin_unlock(&tree->lock); + cond_resched(); + spin_lock(&tree->lock); + } + } +out: + spin_unlock(&tree->lock); + return 0; +} + +static void set_state_bits(struct extent_io_tree *tree, + struct extent_state *state, + int bits) +{ + if ((bits & EXTENT_DIRTY) && !(state->state & EXTENT_DIRTY)) { + u64 range = state->end - state->start + 1; + tree->dirty_bytes += range; + } + set_state_cb(tree, state, bits); + state->state |= bits; +} + +/* + * set some bits on a range in the tree. This may require allocations + * or sleeping, so the gfp mask is used to indicate what is allowed. + * + * If 'exclusive' == 1, this will fail with -EEXIST if some part of the + * range already has the desired bits set. The start of the existing + * range is returned in failed_start in this case. + * + * [start, end] is inclusive + * This takes the tree lock. + */ +static int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, + int bits, int exclusive, u64 *failed_start, + gfp_t mask) +{ + struct extent_state *state; + struct extent_state *prealloc = NULL; + struct rb_node *node; + int err = 0; + int set; + u64 last_start; + u64 last_end; +again: + if (!prealloc && (mask & __GFP_WAIT)) { + prealloc = alloc_extent_state(mask); + if (!prealloc) + return -ENOMEM; + } + + spin_lock(&tree->lock); + /* + * this search will find all the extents that end after + * our range starts. + */ + node = tree_search(tree, start); + if (!node) { + err = insert_state(tree, prealloc, start, end, bits); + prealloc = NULL; + BUG_ON(err == -EEXIST); + goto out; + } + + state = rb_entry(node, struct extent_state, rb_node); + last_start = state->start; + last_end = state->end; + + /* + * | ---- desired range ---- | + * | state | + * + * Just lock what we found and keep going + */ + if (state->start == start && state->end <= end) { + set = state->state & bits; + if (set && exclusive) { + *failed_start = state->start; + err = -EEXIST; + goto out; + } + set_state_bits(tree, state, bits); + start = state->end + 1; + merge_state(tree, state); + goto search_again; + } + + /* + * | ---- desired range ---- | + * | state | + * or + * | ------------- state -------------- | + * + * We need to split the extent we found, and may flip bits on + * second half. + * + * If the extent we found extends past our + * range, we just split and search again. It'll get split + * again the next time though. + * + * If the extent we found is inside our range, we set the + * desired bit on it. + */ + if (state->start < start) { + set = state->state & bits; + if (exclusive && set) { + *failed_start = start; + err = -EEXIST; + goto out; + } + err = split_state(tree, state, prealloc, start); + BUG_ON(err == -EEXIST); + prealloc = NULL; + if (err) + goto out; + if (state->end <= end) { + set_state_bits(tree, state, bits); + start = state->end + 1; + merge_state(tree, state); + } else { + start = state->start; + } + goto search_again; + } + /* + * | ---- desired range ---- | + * | state | or | state | + * + * There's a hole, we need to insert something in it and + * ignore the extent we found. + */ + if (state->start > start) { + u64 this_end; + if (end < last_start) + this_end = end; + else + this_end = last_start - 1; + err = insert_state(tree, prealloc, start, this_end, + bits); + prealloc = NULL; + BUG_ON(err == -EEXIST); + if (err) + goto out; + start = this_end + 1; + goto search_again; + } + /* + * | ---- desired range ---- | + * | state | + * We need to split the extent, and set the bit + * on the first half + */ + if (state->start <= end && state->end > end) { + set = state->state & bits; + if (exclusive && set) { + *failed_start = start; + err = -EEXIST; + goto out; + } + err = split_state(tree, state, prealloc, end + 1); + BUG_ON(err == -EEXIST); + + set_state_bits(tree, prealloc, bits); + merge_state(tree, prealloc); + prealloc = NULL; + goto out; + } + + goto search_again; + +out: + spin_unlock(&tree->lock); + if (prealloc) + free_extent_state(prealloc); + + return err; + +search_again: + if (start > end) + goto out; + spin_unlock(&tree->lock); + if (mask & __GFP_WAIT) + cond_resched(); + goto again; +} + +/* wrappers around set/clear extent bit */ +int set_extent_dirty(struct extent_io_tree *tree, u64 start, u64 end, + gfp_t mask) +{ + return set_extent_bit(tree, start, end, EXTENT_DIRTY, 0, NULL, + mask); +} + +int set_extent_ordered(struct extent_io_tree *tree, u64 start, u64 end, + gfp_t mask) +{ + return set_extent_bit(tree, start, end, EXTENT_ORDERED, 0, NULL, mask); +} + +int set_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, + int bits, gfp_t mask) +{ + return set_extent_bit(tree, start, end, bits, 0, NULL, + mask); +} + +int clear_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, + int bits, gfp_t mask) +{ + return clear_extent_bit(tree, start, end, bits, 0, 0, mask); +} + +int set_extent_delalloc(struct extent_io_tree *tree, u64 start, u64 end, + gfp_t mask) +{ + return set_extent_bit(tree, start, end, + EXTENT_DELALLOC | EXTENT_DIRTY, + 0, NULL, mask); +} + +int clear_extent_dirty(struct extent_io_tree *tree, u64 start, u64 end, + gfp_t mask) +{ + return clear_extent_bit(tree, start, end, + EXTENT_DIRTY | EXTENT_DELALLOC, 0, 0, mask); +} + +int clear_extent_ordered(struct extent_io_tree *tree, u64 start, u64 end, + gfp_t mask) +{ + return clear_extent_bit(tree, start, end, EXTENT_ORDERED, 1, 0, mask); +} + +int set_extent_new(struct extent_io_tree *tree, u64 start, u64 end, + gfp_t mask) +{ + return set_extent_bit(tree, start, end, EXTENT_NEW, 0, NULL, + mask); +} + +static int clear_extent_new(struct extent_io_tree *tree, u64 start, u64 end, + gfp_t mask) +{ + return clear_extent_bit(tree, start, end, EXTENT_NEW, 0, 0, mask); +} + +int set_extent_uptodate(struct extent_io_tree *tree, u64 start, u64 end, + gfp_t mask) +{ + return set_extent_bit(tree, start, end, EXTENT_UPTODATE, 0, NULL, + mask); +} + +static int clear_extent_uptodate(struct extent_io_tree *tree, u64 start, + u64 end, gfp_t mask) +{ + return clear_extent_bit(tree, start, end, EXTENT_UPTODATE, 0, 0, mask); +} + +static int set_extent_writeback(struct extent_io_tree *tree, u64 start, u64 end, + gfp_t mask) +{ + return set_extent_bit(tree, start, end, EXTENT_WRITEBACK, + 0, NULL, mask); +} + +static int clear_extent_writeback(struct extent_io_tree *tree, u64 start, + u64 end, gfp_t mask) +{ + return clear_extent_bit(tree, start, end, EXTENT_WRITEBACK, 1, 0, mask); +} + +int wait_on_extent_writeback(struct extent_io_tree *tree, u64 start, u64 end) +{ + return wait_extent_bit(tree, start, end, EXTENT_WRITEBACK); +} + +/* + * either insert or lock state struct between start and end use mask to tell + * us if waiting is desired. + */ +int lock_extent(struct extent_io_tree *tree, u64 start, u64 end, gfp_t mask) +{ + int err; + u64 failed_start; + while (1) { + err = set_extent_bit(tree, start, end, EXTENT_LOCKED, 1, + &failed_start, mask); + if (err == -EEXIST && (mask & __GFP_WAIT)) { + wait_extent_bit(tree, failed_start, end, EXTENT_LOCKED); + start = failed_start; + } else { + break; + } + WARN_ON(start > end); + } + return err; +} + +int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end, + gfp_t mask) +{ + int err; + u64 failed_start; + + err = set_extent_bit(tree, start, end, EXTENT_LOCKED, 1, + &failed_start, mask); + if (err == -EEXIST) { + if (failed_start > start) + clear_extent_bit(tree, start, failed_start - 1, + EXTENT_LOCKED, 1, 0, mask); + return 0; + } + return 1; +} + +int unlock_extent(struct extent_io_tree *tree, u64 start, u64 end, + gfp_t mask) +{ + return clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, mask); +} + +/* + * helper function to set pages and extents in the tree dirty + */ +int set_range_dirty(struct extent_io_tree *tree, u64 start, u64 end) +{ + unsigned long index = start >> PAGE_CACHE_SHIFT; + unsigned long end_index = end >> PAGE_CACHE_SHIFT; + struct page *page; + + while (index <= end_index) { + page = find_get_page(tree->mapping, index); + BUG_ON(!page); + __set_page_dirty_nobuffers(page); + page_cache_release(page); + index++; + } + set_extent_dirty(tree, start, end, GFP_NOFS); + return 0; +} + +/* + * helper function to set both pages and extents in the tree writeback + */ +static int set_range_writeback(struct extent_io_tree *tree, u64 start, u64 end) +{ + unsigned long index = start >> PAGE_CACHE_SHIFT; + unsigned long end_index = end >> PAGE_CACHE_SHIFT; + struct page *page; + + while (index <= end_index) { + page = find_get_page(tree->mapping, index); + BUG_ON(!page); + set_page_writeback(page); + page_cache_release(page); + index++; + } + set_extent_writeback(tree, start, end, GFP_NOFS); + return 0; +} + +/* + * find the first offset in the io tree with 'bits' set. zero is + * returned if we find something, and *start_ret and *end_ret are + * set to reflect the state struct that was found. + * + * If nothing was found, 1 is returned, < 0 on error + */ +int find_first_extent_bit(struct extent_io_tree *tree, u64 start, + u64 *start_ret, u64 *end_ret, int bits) +{ + struct rb_node *node; + struct extent_state *state; + int ret = 1; + + spin_lock(&tree->lock); + /* + * this search will find all the extents that end after + * our range starts. + */ + node = tree_search(tree, start); + if (!node) + goto out; + + while (1) { + state = rb_entry(node, struct extent_state, rb_node); + if (state->end >= start && (state->state & bits)) { + *start_ret = state->start; + *end_ret = state->end; + ret = 0; + break; + } + node = rb_next(node); + if (!node) + break; + } +out: + spin_unlock(&tree->lock); + return ret; +} + +/* find the first state struct with 'bits' set after 'start', and + * return it. tree->lock must be held. NULL will returned if + * nothing was found after 'start' + */ +struct extent_state *find_first_extent_bit_state(struct extent_io_tree *tree, + u64 start, int bits) +{ + struct rb_node *node; + struct extent_state *state; + + /* + * this search will find all the extents that end after + * our range starts. + */ + node = tree_search(tree, start); + if (!node) + goto out; + + while (1) { + state = rb_entry(node, struct extent_state, rb_node); + if (state->end >= start && (state->state & bits)) + return state; + + node = rb_next(node); + if (!node) + break; + } +out: + return NULL; +} + +/* + * find a contiguous range of bytes in the file marked as delalloc, not + * more than 'max_bytes'. start and end are used to return the range, + * + * 1 is returned if we find something, 0 if nothing was in the tree + */ +static noinline u64 find_delalloc_range(struct extent_io_tree *tree, + u64 *start, u64 *end, u64 max_bytes) +{ + struct rb_node *node; + struct extent_state *state; + u64 cur_start = *start; + u64 found = 0; + u64 total_bytes = 0; + + spin_lock(&tree->lock); + + /* + * this search will find all the extents that end after + * our range starts. + */ + node = tree_search(tree, cur_start); + if (!node) { + if (!found) + *end = (u64)-1; + goto out; + } + + while (1) { + state = rb_entry(node, struct extent_state, rb_node); + if (found && (state->start != cur_start || + (state->state & EXTENT_BOUNDARY))) { + goto out; + } + if (!(state->state & EXTENT_DELALLOC)) { + if (!found) + *end = state->end; + goto out; + } + if (!found) + *start = state->start; + found++; + *end = state->end; + cur_start = state->end + 1; + node = rb_next(node); + if (!node) + break; + total_bytes += state->end - state->start + 1; + if (total_bytes >= max_bytes) + break; + } +out: + spin_unlock(&tree->lock); + return found; +} + +static noinline int __unlock_for_delalloc(struct inode *inode, + struct page *locked_page, + u64 start, u64 end) +{ + int ret; + struct page *pages[16]; + unsigned long index = start >> PAGE_CACHE_SHIFT; + unsigned long end_index = end >> PAGE_CACHE_SHIFT; + unsigned long nr_pages = end_index - index + 1; + int i; + + if (index == locked_page->index && end_index == index) + return 0; + + while (nr_pages > 0) { + ret = find_get_pages_contig(inode->i_mapping, index, + min_t(unsigned long, nr_pages, + ARRAY_SIZE(pages)), pages); + for (i = 0; i < ret; i++) { + if (pages[i] != locked_page) + unlock_page(pages[i]); + page_cache_release(pages[i]); + } + nr_pages -= ret; + index += ret; + cond_resched(); + } + return 0; +} + +static noinline int lock_delalloc_pages(struct inode *inode, + struct page *locked_page, + u64 delalloc_start, + u64 delalloc_end) +{ + unsigned long index = delalloc_start >> PAGE_CACHE_SHIFT; + unsigned long start_index = index; + unsigned long end_index = delalloc_end >> PAGE_CACHE_SHIFT; + unsigned long pages_locked = 0; + struct page *pages[16]; + unsigned long nrpages; + int ret; + int i; + + /* the caller is responsible for locking the start index */ + if (index == locked_page->index && index == end_index) + return 0; + + /* skip the page at the start index */ + nrpages = end_index - index + 1; + while (nrpages > 0) { + ret = find_get_pages_contig(inode->i_mapping, index, + min_t(unsigned long, + nrpages, ARRAY_SIZE(pages)), pages); + if (ret == 0) { + ret = -EAGAIN; + goto done; + } + /* now we have an array of pages, lock them all */ + for (i = 0; i < ret; i++) { + /* + * the caller is taking responsibility for + * locked_page + */ + if (pages[i] != locked_page) { + lock_page(pages[i]); + if (!PageDirty(pages[i]) || + pages[i]->mapping != inode->i_mapping) { + ret = -EAGAIN; + unlock_page(pages[i]); + page_cache_release(pages[i]); + goto done; + } + } + page_cache_release(pages[i]); + pages_locked++; + } + nrpages -= ret; + index += ret; + cond_resched(); + } + ret = 0; +done: + if (ret && pages_locked) { + __unlock_for_delalloc(inode, locked_page, + delalloc_start, + ((u64)(start_index + pages_locked - 1)) << + PAGE_CACHE_SHIFT); + } + return ret; +} + +/* + * find a contiguous range of bytes in the file marked as delalloc, not + * more than 'max_bytes'. start and end are used to return the range, + * + * 1 is returned if we find something, 0 if nothing was in the tree + */ +static noinline u64 find_lock_delalloc_range(struct inode *inode, + struct extent_io_tree *tree, + struct page *locked_page, + u64 *start, u64 *end, + u64 max_bytes) +{ + u64 delalloc_start; + u64 delalloc_end; + u64 found; + int ret; + int loops = 0; + +again: + /* step one, find a bunch of delalloc bytes sta |