1 files changed, 302 insertions, 0 deletions

diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 05efcc7061a7..7f972e59cc04 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -28,6 +28,11 @@
 #define BITS_PER_BITMAP         (PAGE_CACHE_SIZE * 8)
 #define MAX_CACHE_BYTES_PER_GIG (32 * 1024)
 
+static void recalculate_thresholds(struct btrfs_block_group_cache
+                                   *block_group);
+static int link_free_space(struct btrfs_block_group_cache *block_group,
+                           struct btrfs_free_space *info);
+
 struct inode *lookup_free_space_inode(struct btrfs_root *root,
                                       struct btrfs_block_group_cache
                                       *block_group, struct btrfs_path *path)
@@ -182,6 +187,303 @@ int btrfs_truncate_free_space_cache(struct btrfs_root *root,
         return btrfs_update_inode(trans, root, inode);
 }
 
+int btrfs_write_out_cache(struct btrfs_root *root,
+                          struct btrfs_trans_handle *trans,
+                          struct btrfs_block_group_cache *block_group,
+                          struct btrfs_path *path)
+{
+        struct btrfs_free_space_header *header;
+        struct extent_buffer *leaf;
+        struct inode *inode;
+        struct rb_node *node;
+        struct list_head *pos, *n;
+        struct page *page;
+        struct extent_state *cached_state = NULL;
+        struct list_head bitmap_list;
+        struct btrfs_key key;
+        u64 bytes = 0;
+        u32 *crc, *checksums;
+        pgoff_t index = 0, last_index = 0;
+        unsigned long first_page_offset;
+        int num_checksums;
+        int entries = 0;
+        int bitmaps = 0;
+        int ret = 0;
+
+        root = root->fs_info->tree_root;
+
+        INIT_LIST_HEAD(&bitmap_list);
+
+        spin_lock(&block_group->lock);
+        if (block_group->disk_cache_state < BTRFS_DC_SETUP) {
+                spin_unlock(&block_group->lock);
+                return 0;
+        }
+        spin_unlock(&block_group->lock);
+
+        inode = lookup_free_space_inode(root, block_group, path);
+        if (IS_ERR(inode))
+                return 0;
+
+        if (!i_size_read(inode)) {
+                iput(inode);
+                return 0;
+        }
+
+        last_index = (i_size_read(inode) - 1) >> PAGE_CACHE_SHIFT;
+        filemap_write_and_wait(inode->i_mapping);
+        btrfs_wait_ordered_range(inode, inode->i_size &
+                                 ~(root->sectorsize - 1), (u64)-1);
+
+        /* We need a checksum per page. */
+        num_checksums = i_size_read(inode) / PAGE_CACHE_SIZE;
+        crc = checksums  = kzalloc(sizeof(u32) * num_checksums, GFP_NOFS);
+        if (!crc) {
+                iput(inode);
+                return 0;
+        }
+
+        /* Since the first page has all of our checksums and our generation we
+         * need to calculate the offset into the page that we can start writing
+         * our entries.
+         */
+        first_page_offset = (sizeof(u32) * num_checksums) + sizeof(u64);
+
+        node = rb_first(&block_group->free_space_offset);
+        if (!node)
+                goto out_free;
+
+        /*
+         * Lock all pages first so we can lock the extent safely.
+         *
+         * NOTE: Because we hold the ref the entire time we're going to write to
+         * the page find_get_page should never fail, so we don't do a check
+         * after find_get_page at this point.  Just putting this here so people
+         * know and don't freak out.
+         */
+        while (index <= last_index) {
+                page = grab_cache_page(inode->i_mapping, index);
+                if (!page) {
+                        pgoff_t i = 0;
+
+                        while (i < index) {
+                                page = find_get_page(inode->i_mapping, i);
+                                unlock_page(page);
+                                page_cache_release(page);
+                                page_cache_release(page);
+                                i++;
+                        }
+                        goto out_free;
+                }
+                index++;
+        }
+
+        index = 0;
+        lock_extent_bits(&BTRFS_I(inode)->io_tree, 0, i_size_read(inode) - 1,
+                         0, &cached_state, GFP_NOFS);
+
+        /* Write out the extent entries */
+        do {
+                struct btrfs_free_space_entry *entry;
+                void *addr;
+                unsigned long offset = 0;
+                unsigned long start_offset = 0;
+
+                if (index == 0) {
+                        start_offset = first_page_offset;
+                        offset = start_offset;
+                }
+
+                page = find_get_page(inode->i_mapping, index);
+
+                addr = kmap(page);
+                entry = addr + start_offset;
+
+                memset(addr, 0, PAGE_CACHE_SIZE);
+                while (1) {
+                        struct btrfs_free_space *e;
+
+                        e = rb_entry(node, struct btrfs_free_space, offset_index);
+                        entries++;
+
+                        entry->offset = cpu_to_le64(e->offset);
+                        entry->bytes = cpu_to_le64(e->bytes);
+                        if (e->bitmap) {
+                                entry->type = BTRFS_FREE_SPACE_BITMAP;
+                                list_add_tail(&e->list, &bitmap_list);
+                                bitmaps++;
+                        } else {
+                                entry->type = BTRFS_FREE_SPACE_EXTENT;
+                        }
+                        node = rb_next(node);
+                        if (!node)
+                                break;
+                        offset += sizeof(struct btrfs_free_space_entry);
+                        if (offset + sizeof(struct btrfs_free_space_entry) >=
+                            PAGE_CACHE_SIZE)
+                                break;
+                        entry++;
+                }
+                *crc = ~(u32)0;
+                *crc = btrfs_csum_data(root, addr + start_offset, *crc,
+                                       PAGE_CACHE_SIZE - start_offset);
+                kunmap(page);
+
+                btrfs_csum_final(*crc, (char *)crc);
+                crc++;
+
+                bytes += PAGE_CACHE_SIZE;
+
+                ClearPageChecked(page);
+                set_page_extent_mapped(page);
+                SetPageUptodate(page);
+                set_page_dirty(page);
+
+                /*
+                 * We need to release our reference we got for grab_cache_page,
+                 * except for the first page which will hold our checksums, we
+                 * do that below.
+                 */
+                if (index != 0) {
+                        unlock_page(page);
+                        page_cache_release(page);
+                }
+
+                page_cache_release(page);
+
+                index++;
+        } while (node);
+
+        /* Write out the bitmaps */
+        list_for_each_safe(pos, n, &bitmap_list) {
+                void *addr;
+                struct btrfs_free_space *entry =
+                        list_entry(pos, struct btrfs_free_space, list);
+
+                page = find_get_page(inode->i_mapping, index);
+
+                addr = kmap(page);
+                memcpy(addr, entry->bitmap, PAGE_CACHE_SIZE);
+                *crc = ~(u32)0;
+                *crc = btrfs_csum_data(root, addr, *crc, PAGE_CACHE_SIZE);
+                kunmap(page);
+                btrfs_csum_final(*crc, (char *)crc);
+                crc++;
+                bytes += PAGE_CACHE_SIZE;
+
+                ClearPageChecked(page);
+                set_page_extent_mapped(page);
+                SetPageUptodate(page);
+                set_page_dirty(page);
+                unlock_page(page);
+                page_cache_release(page);
+                page_cache_release(page);
+                list_del_init(&entry->list);
+                index++;
+        }
+
+        /* Zero out the rest of the pages just to make sure */
+        while (index <= last_index) {
+                void *addr;
+
+                page = find_get_page(inode->i_mapping, index);
+
+                addr = kmap(page);
+                memset(addr, 0, PAGE_CACHE_SIZE);
+                kunmap(page);
+                ClearPageChecked(page);
+                set_page_extent_mapped(page);
+                SetPageUptodate(page);
+                set_page_dirty(page);
+                unlock_page(page);
+                page_cache_release(page);
+                page_cache_release(page);
+                bytes += PAGE_CACHE_SIZE;
+                index++;
+        }
+
+        btrfs_set_extent_delalloc(inode, 0, bytes - 1, &cached_state);
+
+        /* Write the checksums and trans id to the first page */
+        {
+                void *addr;
+                u64 *gen;
+
+                page = find_get_page(inode->i_mapping, 0);
+
+                addr = kmap(page);
+                memcpy(addr, checksums, sizeof(u32) * num_checksums);
+                gen = addr + (sizeof(u32) * num_checksums);
+                *gen = trans->transid;
+                kunmap(page);
+                ClearPageChecked(page);
+                set_page_extent_mapped(page);
+                SetPageUptodate(page);
+                set_page_dirty(page);
+                unlock_page(page);
+                page_cache_release(page);
+                page_cache_release(page);
+        }
+        BTRFS_I(inode)->generation = trans->transid;
+
+        unlock_extent_cached(&BTRFS_I(inode)->io_tree, 0,
+                             i_size_read(inode) - 1, &cached_state, GFP_NOFS);
+
+        filemap_write_and_wait(inode->i_mapping);
+
+        key.objectid = BTRFS_FREE_SPACE_OBJECTID;
+        key.offset = block_group->key.objectid;
+        key.type = 0;
+
+        ret = btrfs_search_slot(trans, root, &key, path, 1, 1);
+        if (ret < 0) {
+                ret = 0;
+                clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, bytes - 1,
+                                 EXTENT_DIRTY | EXTENT_DELALLOC |
+                                 EXTENT_DO_ACCOUNTING, 0, 0, NULL, GFP_NOFS);
+                goto out_free;
+        }
+        leaf = path->nodes[0];
+        if (ret > 0) {
+                struct btrfs_key found_key;
+                BUG_ON(!path->slots[0]);
+                path->slots[0]--;
+                btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
+                if (found_key.objectid != BTRFS_FREE_SPACE_OBJECTID ||
+                    found_key.offset != block_group->key.objectid) {
+                        ret = 0;
+                        clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, bytes - 1,
+                                         EXTENT_DIRTY | EXTENT_DELALLOC |
+                                         EXTENT_DO_ACCOUNTING, 0, 0, NULL,
+                                         GFP_NOFS);
+                        btrfs_release_path(root, path);
+                        goto out_free;
+                }
+        }
+        header = btrfs_item_ptr(leaf, path->slots[0],
+                                struct btrfs_free_space_header);
+        btrfs_set_free_space_entries(leaf, header, entries);
+        btrfs_set_free_space_bitmaps(leaf, header, bitmaps);
+        btrfs_set_free_space_generation(leaf, header, trans->transid);
+        btrfs_mark_buffer_dirty(leaf);
+        btrfs_release_path(root, path);
+
+        ret = 1;
+
+out_free:
+        if (ret == 0) {
+                invalidate_inode_pages2_range(inode->i_mapping, 0, index);
+                spin_lock(&block_group->lock);
+                block_group->disk_cache_state = BTRFS_DC_ERROR;
+                spin_unlock(&block_group->lock);
+                BTRFS_I(inode)->generation = 0;
+        }
+        kfree(checksums);
+        btrfs_update_inode(trans, root, inode);
+        iput(inode);
+        return ret;
+}
+
 static inline unsigned long offset_to_bit(u64 bitmap_start, u64 sectorsize,
                                           u64 offset)
 {