From patchwork Wed Mar 12 14:20:31 2014 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Chandan Rajendra X-Patchwork-Id: 3818101 Return-Path: X-Original-To: patchwork-linux-btrfs@patchwork.kernel.org Delivered-To: patchwork-parsemail@patchwork1.web.kernel.org Received: from mail.kernel.org (mail.kernel.org [198.145.19.201]) by patchwork1.web.kernel.org (Postfix) with ESMTP id ECCA29F1CD for ; Wed, 12 Mar 2014 14:21:46 +0000 (UTC) Received: from mail.kernel.org (localhost [127.0.0.1]) by mail.kernel.org (Postfix) with ESMTP id 4C2B52027D for ; Wed, 12 Mar 2014 14:21:44 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id 5E45620270 for ; Wed, 12 Mar 2014 14:21:41 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754441AbaCLOVh (ORCPT ); Wed, 12 Mar 2014 10:21:37 -0400 Received: from e28smtp03.in.ibm.com ([122.248.162.3]:49272 "EHLO e28smtp03.in.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754404AbaCLOVf (ORCPT ); Wed, 12 Mar 2014 10:21:35 -0400 Received: from /spool/local by e28smtp03.in.ibm.com with IBM ESMTP SMTP Gateway: Authorized Use Only! Violators will be prosecuted for from ; Wed, 12 Mar 2014 19:51:32 +0530 Received: from d28dlp01.in.ibm.com (9.184.220.126) by e28smtp03.in.ibm.com (192.168.1.133) with IBM ESMTP SMTP Gateway: Authorized Use Only! Violators will be prosecuted; Wed, 12 Mar 2014 19:51:31 +0530 Received: from d28relay01.in.ibm.com (d28relay01.in.ibm.com [9.184.220.58]) by d28dlp01.in.ibm.com (Postfix) with ESMTP id B9243E0044 for ; Wed, 12 Mar 2014 19:55:17 +0530 (IST) Received: from d28av03.in.ibm.com (d28av03.in.ibm.com [9.184.220.65]) by d28relay01.in.ibm.com (8.13.8/8.13.8/NCO v10.0) with ESMTP id s2CELO4c55050450 for ; Wed, 12 Mar 2014 19:51:24 +0530 Received: from d28av03.in.ibm.com (localhost [127.0.0.1]) by d28av03.in.ibm.com (8.14.4/8.14.4/NCO v10.0 AVout) with ESMTP id s2CELULB010471 for ; Wed, 12 Mar 2014 19:51:30 +0530 Received: from localhost.in.ibm.com ([9.77.126.47]) by d28av03.in.ibm.com (8.14.4/8.14.4/NCO v10.0 AVin) with ESMTP id s2CEKw7M008421; Wed, 12 Mar 2014 19:51:30 +0530 From: Chandan Rajendra To: linux-btrfs@vger.kernel.org Cc: Chandra Seetharaman , aneesh.kumar@linux.vnet.ibm.com, Chandan Rajendra Subject: [PATCH 4/6] Btrfs: subpagesize-blocksize: Define extent_buffer_head Date: Wed, 12 Mar 2014 19:50:31 +0530 Message-Id: <1394634033-2528-5-git-send-email-chandan@linux.vnet.ibm.com> X-Mailer: git-send-email 1.8.3.1 In-Reply-To: <1394634033-2528-1-git-send-email-chandan@linux.vnet.ibm.com> References: <1394634033-2528-1-git-send-email-chandan@linux.vnet.ibm.com> X-TM-AS-MML: disable X-Content-Scanned: Fidelis XPS MAILER x-cbid: 14031214-3864-0000-0000-00000CED33B8 Sender: linux-btrfs-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-btrfs@vger.kernel.org X-Spam-Status: No, score=-6.9 required=5.0 tests=BAYES_00, RCVD_IN_DNSWL_HI, T_RP_MATCHES_RCVD, UNPARSEABLE_RELAY autolearn=unavailable version=3.3.1 X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on mail.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP From: Chandra Seetharaman In order to handle multiple extent buffers per page, first we need to create a way to handle all the extent buffers that are attached to a page. This patch creates a new data structure eb_head, and moves fields that are common to all extent buffers in a page from extent buffer to eb_head. This also adds changes that are needed to handle multiple extent buffers per page case. Signed-off-by: Chandra Seetharaman Signed-off-by: Chandan Rajendra --- fs/btrfs/backref.c | 2 +- fs/btrfs/ctree.c | 2 +- fs/btrfs/ctree.h | 6 +- fs/btrfs/disk-io.c | 111 +++++++---- fs/btrfs/extent-tree.c | 6 +- fs/btrfs/extent_io.c | 427 ++++++++++++++++++++++++++----------------- fs/btrfs/extent_io.h | 55 ++++-- fs/btrfs/volumes.c | 2 +- include/trace/events/btrfs.h | 2 +- 9 files changed, 388 insertions(+), 225 deletions(-) diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index a88da72..603ae44 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -1272,7 +1272,7 @@ char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path, eb = path->nodes[0]; /* make sure we can use eb after releasing the path */ if (eb != eb_in) { - atomic_inc(&eb->refs); + atomic_inc(&eb_head(eb)->refs); btrfs_tree_read_lock(eb); btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK); } diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index cbd3a7d..0d4ad91 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -169,7 +169,7 @@ struct extent_buffer *btrfs_root_node(struct btrfs_root *root) * the inc_not_zero dance and if it doesn't work then * synchronize_rcu and try again. */ - if (atomic_inc_not_zero(&eb->refs)) { + if (atomic_inc_not_zero(&eb_head(eb)->refs)) { rcu_read_unlock(); break; } diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index dac6653..901ada2 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2138,14 +2138,16 @@ static inline void btrfs_set_token_##name(struct extent_buffer *eb, \ #define BTRFS_SETGET_HEADER_FUNCS(name, type, member, bits) \ static inline u##bits btrfs_##name(struct extent_buffer *eb) \ { \ - type *p = page_address(eb->pages[0]); \ + type *p = page_address(eb_head(eb)->pages[0]) + \ + (eb->start & (PAGE_CACHE_SIZE -1)); \ u##bits res = le##bits##_to_cpu(p->member); \ return res; \ } \ static inline void btrfs_set_##name(struct extent_buffer *eb, \ u##bits val) \ { \ - type *p = page_address(eb->pages[0]); \ + type *p = page_address(eb_head(eb)->pages[0]) + \ + (eb->start & (PAGE_CACHE_SIZE -1)); \ p->member = cpu_to_le##bits(val); \ } diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index cc1b423..796d889 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -413,7 +413,7 @@ static int btree_read_extent_buffer_pages(struct btrfs_root *root, int mirror_num = 0; int failed_mirror = 0; - clear_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags); + clear_bit(EXTENT_BUFFER_CORRUPT, &eb_head(eb)->bflags); io_tree = &BTRFS_I(root->fs_info->btree_inode)->io_tree; while (1) { ret = read_extent_buffer_pages(io_tree, eb, start, @@ -432,7 +432,7 @@ static int btree_read_extent_buffer_pages(struct btrfs_root *root, * there is no reason to read the other copies, they won't be * any less wrong. */ - if (test_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags)) + if (test_bit(EXTENT_BUFFER_CORRUPT, &eb_head(eb)->bflags)) break; num_copies = btrfs_num_copies(root->fs_info, @@ -442,7 +442,7 @@ static int btree_read_extent_buffer_pages(struct btrfs_root *root, if (!failed_mirror) { failed = 1; - failed_mirror = eb->read_mirror; + failed_mirror = eb_head(eb)->read_mirror; } mirror_num++; @@ -466,17 +466,20 @@ static int btree_read_extent_buffer_pages(struct btrfs_root *root, static int csum_dirty_buffer(struct btrfs_root *root, struct page *page) { - u64 start = page_offset(page); u64 found_start; struct extent_buffer *eb; + struct extent_buffer_head *eb_head; - eb = (struct extent_buffer *)page->private; - if (page != eb->pages[0]) + eb_head = (struct extent_buffer_head *)page->private; + if (page != eb_head->pages[0]) return 0; - found_start = btrfs_header_bytenr(eb); - if (WARN_ON(found_start != start || !PageUptodate(page))) + if (WARN_ON(!PageUptodate(page))) return 0; - csum_tree_block(root, eb, 0); + for (eb = &eb_head->extent_buf[0]; eb->start; eb++) { + found_start = btrfs_header_bytenr(eb); + if (found_start == eb->start) + csum_tree_block(root, eb, 0); + } return 0; } @@ -573,24 +576,35 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio, struct extent_buffer *eb; struct btrfs_root *root = BTRFS_I(page->mapping->host)->root; int ret = 0; - int reads_done; + int reads_done = 0; + struct extent_buffer_head *eb_head; if (!page->private) goto out; - eb = (struct extent_buffer *)page->private; + + eb_head = (struct extent_buffer_head *)page->private; + + /* Get the eb corresponding to this IO */ + eb = eb_head->io_eb; + if (!eb) { + ret = -EIO; + goto err; + } /* the pending IO might have been the only thing that kept this buffer * in memory. Make sure we have a ref for all this other checks */ extent_buffer_get(eb); - reads_done = atomic_dec_and_test(&eb->io_pages); + reads_done = atomic_dec_and_test(&eb_head->io_pages); if (!reads_done) goto err; - eb->read_mirror = mirror; - if (test_bit(EXTENT_BUFFER_IOERR, &eb->bflags)) { + eb_head->io_eb = NULL; + + eb_head->read_mirror = mirror; + if (test_bit(EXTENT_BUFFER_IOERR, &eb_head->bflags)) { ret = -EIO; goto err; } @@ -632,7 +646,7 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio, * return -EIO. */ if (found_level == 0 && check_leaf(root, eb)) { - set_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags); + set_bit(EXTENT_BUFFER_CORRUPT, &eb_head->bflags); ret = -EIO; } @@ -640,7 +654,7 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio, set_extent_buffer_uptodate(eb); err: if (reads_done && - test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags)) + test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb_head->bflags)) btree_readahead_hook(root, eb, eb->start, ret); if (ret) { @@ -649,7 +663,7 @@ err: * again, we have to make sure it has something * to decrement */ - atomic_inc(&eb->io_pages); + atomic_inc(&eb_head->io_pages); clear_extent_buffer_uptodate(eb); } free_extent_buffer(eb); @@ -659,15 +673,22 @@ out: static int btree_io_failed_hook(struct page *page, int failed_mirror) { + struct extent_buffer_head *eb_head + = (struct extent_buffer_head *)page->private; struct extent_buffer *eb; struct btrfs_root *root = BTRFS_I(page->mapping->host)->root; - eb = (struct extent_buffer *)page->private; - set_bit(EXTENT_BUFFER_IOERR, &eb->bflags); - eb->read_mirror = failed_mirror; - atomic_dec(&eb->io_pages); - if (test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags)) + set_bit(EXTENT_BUFFER_IOERR, &eb_head->bflags); + eb_head->read_mirror = failed_mirror; + atomic_dec(&eb_head->io_pages); + /* Get the eb corresponding to this IO */ + eb = eb_head->io_eb; + if (!eb) + goto out; + eb_head->io_eb = NULL; + if (test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb_head->bflags)) btree_readahead_hook(root, eb, eb->start, -EIO); +out: return -EIO; /* we fixed nothing */ } @@ -1017,14 +1038,20 @@ static void btree_invalidatepage(struct page *page, unsigned int offset, static int btree_set_page_dirty(struct page *page) { #ifdef DEBUG + struct extent_buffer_head *ebh; struct extent_buffer *eb; + int i, dirty = 0; BUG_ON(!PagePrivate(page)); - eb = (struct extent_buffer *)page->private; - BUG_ON(!eb); - BUG_ON(!test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)); - BUG_ON(!atomic_read(&eb->refs)); - btrfs_assert_tree_locked(eb); + ebh = (struct extent_buffer_head *)page->private; + BUG_ON(!ebh); + for (i = 0; i < MAX_EXTENT_BUFFERS_PER_PAGE && !dirty; i++) { + eb = &ebh->extent_buf[i]; + dirty = test_and_clear_bit(EXTENT_BUFFER_DIRTY, &eb->ebflags); + } + BUG_ON(dirty); + BUG_ON(!atomic_read(&ebh->refs)); + btrfs_assert_tree_locked(&ebh->extent_buf[0]); #endif return __set_page_dirty_nobuffers(page); } @@ -1068,7 +1095,7 @@ int reada_tree_block_flagged(struct btrfs_root *root, u64 bytenr, u32 blocksize, if (!buf) return 0; - set_bit(EXTENT_BUFFER_READAHEAD, &buf->bflags); + set_bit(EXTENT_BUFFER_READAHEAD, &eb_head(buf)->bflags); ret = read_extent_buffer_pages(io_tree, buf, 0, WAIT_PAGE_LOCK, btree_get_extent, mirror_num); @@ -1077,7 +1104,7 @@ int reada_tree_block_flagged(struct btrfs_root *root, u64 bytenr, u32 blocksize, return ret; } - if (test_bit(EXTENT_BUFFER_CORRUPT, &buf->bflags)) { + if (test_bit(EXTENT_BUFFER_CORRUPT, &eb_head(buf)->bflags)) { free_extent_buffer(buf); return -EIO; } else if (extent_buffer_uptodate(buf)) { @@ -1103,14 +1130,16 @@ struct extent_buffer *btrfs_find_create_tree_block(struct btrfs_root *root, int btrfs_write_tree_block(struct extent_buffer *buf) { - return filemap_fdatawrite_range(buf->pages[0]->mapping, buf->start, + return filemap_fdatawrite_range(eb_head(buf)->pages[0]->mapping, + buf->start, buf->start + buf->len - 1); } int btrfs_wait_tree_block_writeback(struct extent_buffer *buf) { - return filemap_fdatawait_range(buf->pages[0]->mapping, - buf->start, buf->start + buf->len - 1); + return filemap_fdatawait_range(eb_head(buf)->pages[0]->mapping, + buf->start, + buf->start + buf->len - 1); } struct extent_buffer *read_tree_block(struct btrfs_root *root, u64 bytenr, @@ -1141,7 +1170,8 @@ void clean_tree_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, fs_info->running_transaction->transid) { btrfs_assert_tree_locked(buf); - if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &buf->bflags)) { + if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, + &buf->ebflags)) { __percpu_counter_add(&fs_info->dirty_metadata_bytes, -buf->len, fs_info->dirty_metadata_batch); @@ -2613,7 +2643,8 @@ int open_ctree(struct super_block *sb, btrfs_super_chunk_root(disk_super), blocksize, generation); if (!chunk_root->node || - !test_bit(EXTENT_BUFFER_UPTODATE, &chunk_root->node->bflags)) { + !test_bit(EXTENT_BUFFER_UPTODATE, + &eb_head(chunk_root->node)->bflags)) { printk(KERN_WARNING "BTRFS: failed to read chunk root on %s\n", sb->s_id); goto fail_tree_roots; @@ -2652,7 +2683,8 @@ retry_root_backup: btrfs_super_root(disk_super), blocksize, generation); if (!tree_root->node || - !test_bit(EXTENT_BUFFER_UPTODATE, &tree_root->node->bflags)) { + !test_bit(EXTENT_BUFFER_UPTODATE, + &eb_head(tree_root->node)->bflags)) { printk(KERN_WARNING "BTRFS: failed to read tree root on %s\n", sb->s_id); @@ -3642,7 +3674,7 @@ int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid, int atomic) { int ret; - struct inode *btree_inode = buf->pages[0]->mapping->host; + struct inode *btree_inode = eb_head(buf)->pages[0]->mapping->host; ret = extent_buffer_uptodate(buf); if (!ret) @@ -3675,7 +3707,7 @@ void btrfs_mark_buffer_dirty(struct extent_buffer *buf) if (unlikely(test_bit(EXTENT_BUFFER_DUMMY, &buf->bflags))) return; #endif - root = BTRFS_I(buf->pages[0]->mapping->host)->root; + root = BTRFS_I(eb_head(buf)->pages[0]->mapping->host)->root; btrfs_assert_tree_locked(buf); if (transid != root->fs_info->generation) WARN(1, KERN_CRIT "btrfs transid mismatch buffer %llu, " @@ -3724,7 +3756,8 @@ void btrfs_btree_balance_dirty_nodelay(struct btrfs_root *root) int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid) { - struct btrfs_root *root = BTRFS_I(buf->pages[0]->mapping->host)->root; + struct btrfs_root *root = + BTRFS_I(eb_head(buf)->pages[0]->mapping->host)->root; return btree_read_extent_buffer_pages(root, buf, 0, parent_transid); } @@ -3962,7 +3995,7 @@ static int btrfs_destroy_marked_extents(struct btrfs_root *root, wait_on_extent_buffer_writeback(eb); if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, - &eb->bflags)) + &eb->ebflags)) clear_extent_buffer_dirty(eb); free_extent_buffer_stale(eb); } diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 32312e0..0f677de 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -5984,7 +5984,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, goto out; } - WARN_ON(test_bit(EXTENT_BUFFER_DIRTY, &buf->bflags)); + WARN_ON(test_bit(EXTENT_BUFFER_DIRTY, &buf->ebflags)); btrfs_add_free_space(cache, buf->start, buf->len); btrfs_update_reserved_bytes(cache, buf->len, RESERVE_FREE); @@ -6001,7 +6001,7 @@ out: * Deleting the buffer, clear the corrupt flag since it doesn't matter * anymore. */ - clear_bit(EXTENT_BUFFER_CORRUPT, &buf->bflags); + clear_bit(EXTENT_BUFFER_CORRUPT, &eb_head(buf)->bflags); btrfs_put_block_group(cache); } @@ -6887,7 +6887,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root, btrfs_set_buffer_lockdep_class(root->root_key.objectid, buf, level); btrfs_tree_lock(buf); clean_tree_block(trans, root, buf); - clear_bit(EXTENT_BUFFER_STALE, &buf->bflags); + clear_bit(EXTENT_BUFFER_STALE, &eb_head(buf)->bflags); btrfs_set_lock_blocking(buf); btrfs_set_buffer_uptodate(buf); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 9e77645..25d34b0 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -54,8 +54,10 @@ void btrfs_leak_debug_del(struct list_head *entry) static inline void btrfs_leak_debug_check(void) { + int i; struct extent_state *state; struct extent_buffer *eb; + struct extent_buffer_head *ebh; while (!list_empty(&states)) { state = list_entry(states.next, struct extent_state, leak_list); @@ -68,12 +70,17 @@ void btrfs_leak_debug_check(void) } 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", - eb->start, eb->len, atomic_read(&eb->refs)); - list_del(&eb->leak_list); - kmem_cache_free(extent_buffer_cache, eb); + ebh = list_entry(buffers.next, struct extent_buffer_head, leak_list); + printk(KERN_ERR "btrfs buffer leak "); + for (i = 0; i < MAX_EXTENT_BUFFERS_PER_PAGE; i++) { + eb = &ebh->extent_buf[i]; + if (!eb->start) + break; + printk(KERN_ERR "eb %p %llu:%lu ", eb, eb->start, eb->len); + } + printk(KERN_ERR "refs %d\n", atomic_read(&ebh->refs)); + list_del(&ebh->leak_list); + kmem_cache_free(extent_buffer_cache, ebh); } } @@ -144,7 +151,7 @@ int __init extent_io_init(void) return -ENOMEM; extent_buffer_cache = kmem_cache_create("btrfs_extent_buffer", - sizeof(struct extent_buffer), 0, + sizeof(struct extent_buffer_head), 0, SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, NULL); if (!extent_buffer_cache) goto free_state_cache; @@ -2105,7 +2112,7 @@ int repair_io_failure(struct btrfs_fs_info *fs_info, u64 start, int repair_eb_io_failure(struct btrfs_root *root, struct extent_buffer *eb, int mirror_num) { - u64 start = eb->start; + u64 start = eb_head(eb)->extent_buf[0].start; unsigned long i, num_pages = num_extent_pages(eb->start, eb->len); int ret = 0; @@ -2822,15 +2829,15 @@ static int submit_extent_page(int rw, struct extent_io_tree *tree, return ret; } -static void attach_extent_buffer_page(struct extent_buffer *eb, +static void attach_extent_buffer_page(struct extent_buffer_head *ebh, struct page *page) { if (!PagePrivate(page)) { SetPagePrivate(page); page_cache_get(page); - set_page_private(page, (unsigned long)eb); + set_page_private(page, (unsigned long)ebh); } else { - WARN_ON(page->private != (unsigned long)eb); + WARN_ON(page->private != (unsigned long)ebh); } } @@ -3484,17 +3491,19 @@ static int eb_wait(void *word) void wait_on_extent_buffer_writeback(struct extent_buffer *eb) { - wait_on_bit(&eb->bflags, EXTENT_BUFFER_WRITEBACK, eb_wait, + wait_on_bit(&eb_head(eb)->bflags, EXTENT_BUFFER_WRITEBACK, eb_wait, TASK_UNINTERRUPTIBLE); } -static int lock_extent_buffer_for_io(struct extent_buffer *eb, +static int lock_extent_buffer_for_io(struct extent_buffer_head *ebh, struct btrfs_fs_info *fs_info, struct extent_page_data *epd) { unsigned long i, num_pages; int flush = 0; + bool dirty = false, dirty_arr[MAX_EXTENT_BUFFERS_PER_PAGE] = { 0 }; int ret = 0; + struct extent_buffer *eb = &ebh->extent_buf[0], *ebtemp; if (!btrfs_try_tree_write_lock(eb)) { flush = 1; @@ -3502,7 +3511,7 @@ static int lock_extent_buffer_for_io(struct extent_buffer *eb, btrfs_tree_lock(eb); } - if (test_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags)) { + if (test_bit(EXTENT_BUFFER_WRITEBACK, &ebh->bflags)) { btrfs_tree_unlock(eb); if (!epd->sync_io) return 0; @@ -3513,7 +3522,7 @@ static int lock_extent_buffer_for_io(struct extent_buffer *eb, while (1) { wait_on_extent_buffer_writeback(eb); btrfs_tree_lock(eb); - if (!test_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags)) + if (!test_bit(EXTENT_BUFFER_WRITEBACK, &ebh->bflags)) break; btrfs_tree_unlock(eb); } @@ -3524,17 +3533,27 @@ static int lock_extent_buffer_for_io(struct extent_buffer *eb, * under IO since we can end up having no IO bits set for a short period * of time. */ - spin_lock(&eb->refs_lock); - if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)) { - set_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags); - spin_unlock(&eb->refs_lock); - btrfs_set_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN); - __percpu_counter_add(&fs_info->dirty_metadata_bytes, - -eb->len, + spin_lock(&ebh->refs_lock); + for (i = 0; i < MAX_EXTENT_BUFFERS_PER_PAGE; i++) { + ebtemp = &ebh->extent_buf[i]; + dirty_arr[i] |= test_and_clear_bit(EXTENT_BUFFER_DIRTY, &ebtemp->ebflags); + dirty = dirty || dirty_arr[i]; + } + if (dirty) { + set_bit(EXTENT_BUFFER_WRITEBACK, &ebh->bflags); + spin_unlock(&ebh->refs_lock); + for (i = 0; i < MAX_EXTENT_BUFFERS_PER_PAGE; i++) { + if (dirty_arr[i] == false) + continue; + ebtemp = &ebh->extent_buf[i]; + btrfs_set_header_flag(ebtemp, BTRFS_HEADER_FLAG_WRITTEN); + __percpu_counter_add(&fs_info->dirty_metadata_bytes, + -ebtemp->len, fs_info->dirty_metadata_batch); + } ret = 1; } else { - spin_unlock(&eb->refs_lock); + spin_unlock(&ebh->refs_lock); } btrfs_tree_unlock(eb); @@ -3558,30 +3577,30 @@ static int lock_extent_buffer_for_io(struct extent_buffer *eb, return ret; } -static void end_extent_buffer_writeback(struct extent_buffer *eb) +static void end_extent_buffer_writeback(struct extent_buffer_head *ebh) { - clear_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags); + clear_bit(EXTENT_BUFFER_WRITEBACK, &ebh->bflags); smp_mb__after_clear_bit(); - wake_up_bit(&eb->bflags, EXTENT_BUFFER_WRITEBACK); + wake_up_bit(&ebh->bflags, EXTENT_BUFFER_WRITEBACK); } static void end_bio_extent_buffer_writepage(struct bio *bio, int err) { int uptodate = err == 0; struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1; - struct extent_buffer *eb; + struct extent_buffer_head *ebh; int done; do { struct page *page = bvec->bv_page; bvec--; - eb = (struct extent_buffer *)page->private; - BUG_ON(!eb); - done = atomic_dec_and_test(&eb->io_pages); + ebh = (struct extent_buffer_head *)page->private; + BUG_ON(!ebh); + done = atomic_dec_and_test(&ebh->io_pages); - if (!uptodate || test_bit(EXTENT_BUFFER_IOERR, &eb->bflags)) { - set_bit(EXTENT_BUFFER_IOERR, &eb->bflags); + if (!uptodate || test_bit(EXTENT_BUFFER_IOERR, &ebh->bflags)) { + set_bit(EXTENT_BUFFER_IOERR, &ebh->bflags); ClearPageUptodate(page); SetPageError(page); } @@ -3591,7 +3610,7 @@ static void end_bio_extent_buffer_writepage(struct bio *bio, int err) if (!done) continue; - end_extent_buffer_writeback(eb); + end_extent_buffer_writeback(ebh); } while (bvec >= bio->bi_io_vec); bio_put(bio); @@ -3605,15 +3624,15 @@ static int write_one_eb(struct extent_buffer *eb, { struct block_device *bdev = fs_info->fs_devices->latest_bdev; struct extent_io_tree *tree = &BTRFS_I(fs_info->btree_inode)->io_tree; - u64 offset = eb->start; + u64 offset = eb->start & ~(PAGE_CACHE_SIZE - 1); unsigned long i, num_pages; unsigned long bio_flags = 0; int rw = (epd->sync_io ? WRITE_SYNC : WRITE) | REQ_META; int ret = 0; - clear_bit(EXTENT_BUFFER_IOERR, &eb->bflags); + clear_bit(EXTENT_BUFFER_IOERR, &eb_head(eb)->bflags); num_pages = num_extent_pages(eb->start, eb->len); - atomic_set(&eb->io_pages, num_pages); + atomic_set(&eb_head(eb)->io_pages, num_pages); if (btrfs_header_owner(eb) == BTRFS_TREE_LOG_OBJECTID) bio_flags = EXTENT_BIO_TREE_LOG; @@ -3628,10 +3647,11 @@ static int write_one_eb(struct extent_buffer *eb, 0, epd->bio_flags, bio_flags); epd->bio_flags = bio_flags; if (ret) { - set_bit(EXTENT_BUFFER_IOERR, &eb->bflags); + set_bit(EXTENT_BUFFER_IOERR, &eb_head(eb)->bflags); SetPageError(p); - if (atomic_sub_and_test(num_pages - i, &eb->io_pages)) - end_extent_buffer_writeback(eb); + if (atomic_sub_and_test(num_pages - i, + &eb_head(eb)->io_pages)) + end_extent_buffer_writeback(eb_head(eb)); ret = -EIO; break; } @@ -3655,7 +3675,8 @@ int btree_write_cache_pages(struct address_space *mapping, { struct extent_io_tree *tree = &BTRFS_I(mapping->host)->io_tree; struct btrfs_fs_info *fs_info = BTRFS_I(mapping->host)->root->fs_info; - struct extent_buffer *eb, *prev_eb = NULL; + struct extent_buffer *eb; + struct extent_buffer_head *ebh, *prev_ebh = NULL; struct extent_page_data epd = { .bio = NULL, .tree = tree, @@ -3712,30 +3733,31 @@ retry: continue; } - eb = (struct extent_buffer *)page->private; + ebh = (struct extent_buffer_head *)page->private; /* * Shouldn't happen and normally this would be a BUG_ON * but no sense in crashing the users box for something * we can survive anyway. */ - if (WARN_ON(!eb)) { + if (WARN_ON(!ebh)) { spin_unlock(&mapping->private_lock); continue; } - if (eb == prev_eb) { + if (ebh == prev_ebh) { spin_unlock(&mapping->private_lock); continue; } - ret = atomic_inc_not_zero(&eb->refs); + ret = atomic_inc_not_zero(&ebh->refs); spin_unlock(&mapping->private_lock); if (!ret) continue; - prev_eb = eb; - ret = lock_extent_buffer_for_io(eb, fs_info, &epd); + eb = &ebh->extent_buf[0]; + prev_ebh = ebh; + ret = lock_extent_buffer_for_io(ebh, fs_info, &epd); if (!ret) { free_extent_buffer(eb); continue; @@ -4410,17 +4432,23 @@ out: return ret; } -static void __free_extent_buffer(struct extent_buffer *eb) +static void __free_extent_buffer(struct extent_buffer_head *ebh) { - btrfs_leak_debug_del(&eb->leak_list); - kmem_cache_free(extent_buffer_cache, eb); + btrfs_leak_debug_del(&ebh->leak_list); + kmem_cache_free(extent_buffer_cache, ebh); } -static int extent_buffer_under_io(struct extent_buffer *eb) +static int extent_buffer_under_io(struct extent_buffer_head *ebh) { - return (atomic_read(&eb->io_pages) || - test_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags) || - test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)); + int i, dirty = 0; + struct extent_buffer *eb; + + for (i = 0; i < MAX_EXTENT_BUFFERS_PER_PAGE && !dirty; i++) { + eb = &ebh->extent_buf[i]; + dirty = test_bit(EXTENT_BUFFER_DIRTY, &eb->ebflags); + } + return (dirty || atomic_read(&ebh->io_pages) || + test_bit(EXTENT_BUFFER_WRITEBACK, &ebh->bflags)); } /* @@ -4432,9 +4460,10 @@ static void btrfs_release_extent_buffer_page(struct extent_buffer *eb, unsigned long index; unsigned long num_pages; struct page *page; - int mapped = !test_bit(EXTENT_BUFFER_DUMMY, &eb->bflags); + struct extent_buffer_head *ebh = eb_head(eb); + int mapped = !test_bit(EXTENT_BUFFER_DUMMY, &ebh->bflags); - BUG_ON(extent_buffer_under_io(eb)); + BUG_ON(extent_buffer_under_io(ebh)); num_pages = num_extent_pages(eb->start, eb->len); index = start_idx + num_pages; @@ -4454,8 +4483,8 @@ static void btrfs_release_extent_buffer_page(struct extent_buffer *eb, * this eb. */ if (PagePrivate(page) && - page->private == (unsigned long)eb) { - BUG_ON(test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)); + page->private == (unsigned long)ebh) { + BUG_ON(test_bit(EXTENT_BUFFER_DIRTY, &eb->ebflags)); BUG_ON(PageDirty(page)); BUG_ON(PageWriteback(page)); /* @@ -4483,22 +4512,14 @@ static void btrfs_release_extent_buffer_page(struct extent_buffer *eb, static inline void btrfs_release_extent_buffer(struct extent_buffer *eb) { btrfs_release_extent_buffer_page(eb, 0); - __free_extent_buffer(eb); + __free_extent_buffer(eb_head(eb)); } -static struct extent_buffer * -__alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64 start, - unsigned long len, gfp_t mask) +static void __init_extent_buffer(struct extent_buffer *eb, u64 start, + unsigned long len) { - struct extent_buffer *eb = NULL; - - eb = kmem_cache_zalloc(extent_buffer_cache, mask); - if (eb == NULL) - return NULL; eb->start = start; eb->len = len; - eb->fs_info = fs_info; - eb->bflags = 0; rwlock_init(&eb->lock); atomic_set(&eb->write_locks, 0); atomic_set(&eb->read_locks, 0); @@ -4509,12 +4530,26 @@ __alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64 start, eb->lock_nested = 0; init_waitqueue_head(&eb->write_lock_wq); init_waitqueue_head(&eb->read_lock_wq); +} - btrfs_leak_debug_add(&eb->leak_list, &buffers); +static struct extent_buffer *__alloc_extent_buffer(struct btrfs_fs_info *fs_info, + u64 start, unsigned long len, + gfp_t mask) +{ + struct extent_buffer_head *ebh = NULL; + struct extent_buffer *eb = NULL; + int i, index = -1; + + ebh = kmem_cache_zalloc(extent_buffer_cache, mask); + if (ebh == NULL) + return NULL; + ebh->fs_info = fs_info; + ebh->bflags = 0; + btrfs_leak_debug_add(&ebh->leak_list, &buffers); - spin_lock_init(&eb->refs_lock); - atomic_set(&eb->refs, 1); - atomic_set(&eb->io_pages, 0); + spin_lock_init(&ebh->refs_lock); + atomic_set(&ebh->refs, 1); + atomic_set(&ebh->io_pages, 0); /* * Sanity checks, currently the maximum is 64k covered by 16x 4k pages @@ -4523,6 +4558,34 @@ __alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64 start, > MAX_INLINE_EXTENT_BUFFER_SIZE); BUG_ON(len > MAX_INLINE_EXTENT_BUFFER_SIZE); + if (len < PAGE_CACHE_SIZE) { + u64 st = start & ~(PAGE_CACHE_SIZE - 1); + unsigned long totlen = 0; + /* + * Make sure we have enough room to fit extent buffers + * that belong a single page in a single extent_buffer_head. + * If this BUG_ON is tripped, then it means either the + * blocksize, i.e len, is too small or we need to increase + * MAX_EXTENT_BUFFERS_PER_PAGE. + */ + BUG_ON(len * MAX_EXTENT_BUFFERS_PER_PAGE < PAGE_CACHE_SIZE); + + for (i = 0; i < MAX_EXTENT_BUFFERS_PER_PAGE + && totlen < PAGE_CACHE_SIZE ; + i++, st += len, totlen += len) { + __init_extent_buffer(&ebh->extent_buf[i], st, len); + if (st == start) { + index = i; + eb = &ebh->extent_buf[i]; + } + + } + BUG_ON(!eb); + } else { + eb = &ebh->extent_buf[0]; + __init_extent_buffer(eb, start, len); + } + return eb; } @@ -4543,15 +4606,15 @@ struct extent_buffer *btrfs_clone_extent_buffer(struct extent_buffer *src) btrfs_release_extent_buffer(new); return NULL; } - attach_extent_buffer_page(new, p); + attach_extent_buffer_page(eb_head(new), p); WARN_ON(PageDirty(p)); SetPageUptodate(p); - new->pages[i] = p; + eb_head(new)->pages[i] = p; } copy_extent_buffer(new, src, 0, 0, src->len); - set_bit(EXTENT_BUFFER_UPTODATE, &new->bflags); - set_bit(EXTENT_BUFFER_DUMMY, &new->bflags); + set_bit(EXTENT_BUFFER_UPTODATE, &eb_head(new)->bflags); + set_bit(EXTENT_BUFFER_DUMMY, &eb_head(new)->bflags); return new; } @@ -4567,19 +4630,19 @@ struct extent_buffer *alloc_dummy_extent_buffer(u64 start, unsigned long len) return NULL; for (i = 0; i < num_pages; i++) { - eb->pages[i] = alloc_page(GFP_NOFS); - if (!eb->pages[i]) + eb_head(eb)->pages[i] = alloc_page(GFP_NOFS); + if (!eb_head(eb)->pages[i]) goto err; } set_extent_buffer_uptodate(eb); btrfs_set_header_nritems(eb, 0); - set_bit(EXTENT_BUFFER_DUMMY, &eb->bflags); + set_bit(EXTENT_BUFFER_DUMMY, &eb_head(eb)->bflags); return eb; err: for (; i > 0; i--) - __free_page(eb->pages[i - 1]); - __free_extent_buffer(eb); + __free_page(eb_head(eb)->pages[i - 1]); + __free_extent_buffer(eb_head(eb)); return NULL; } @@ -4606,14 +4669,15 @@ static void check_buffer_tree_ref(struct extent_buffer *eb) * So bump the ref count first, then set the bit. If someone * beat us to it, drop the ref we added. */ - refs = atomic_read(&eb->refs); - if (refs >= 2 && test_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags)) + refs = atomic_read(&eb_head(eb)->refs); + if (refs >= 2 && test_bit(EXTENT_BUFFER_TREE_REF, + &eb_head(eb)->bflags)) return; - spin_lock(&eb->refs_lock); - if (!test_and_set_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags)) - atomic_inc(&eb->refs); - spin_unlock(&eb->refs_lock); + spin_lock(&eb_head(eb)->refs_lock); + if (!test_and_set_bit(EXTENT_BUFFER_TREE_REF, &eb_head(eb)->bflags)) + atomic_inc(&eb_head(eb)->refs); + spin_unlock(&eb_head(eb)->refs_lock); } static void mark_extent_buffer_accessed(struct extent_buffer *eb) @@ -4633,14 +4697,22 @@ struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info, u64 start) { struct extent_buffer *eb; + struct extent_buffer_head *ebh; + int i = 0; rcu_read_lock(); - eb = radix_tree_lookup(&fs_info->buffer_radix, - start >> PAGE_CACHE_SHIFT); - if (eb && atomic_inc_not_zero(&eb->refs)) { + ebh = radix_tree_lookup(&fs_info->buffer_radix, + start >> PAGE_CACHE_SHIFT); + if (ebh && atomic_inc_not_zero(&ebh->refs)) { rcu_read_unlock(); - mark_extent_buffer_accessed(eb); - return eb; + do { + eb = &ebh->extent_buf[i++]; + if (eb->start == start) { + mark_extent_buffer_accessed(eb); + return eb; + } + } while (i < MAX_EXTENT_BUFFERS_PER_PAGE); + BUG(); } rcu_read_unlock(); @@ -4653,8 +4725,8 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, unsigned long num_pages = num_extent_pages(start, len); unsigned long i; unsigned long index = start >> PAGE_CACHE_SHIFT; - struct extent_buffer *eb; - struct extent_buffer *exists = NULL; + struct extent_buffer *eb, *old_eb = NULL; + struct extent_buffer_head *exists = NULL; struct page *p; struct address_space *mapping = fs_info->btree_inode->i_mapping; int uptodate = 1; @@ -4682,13 +4754,20 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, * we can just return that one, else we know we can just * overwrite page->private. */ - exists = (struct extent_buffer *)p->private; + exists = (struct extent_buffer_head *)p->private; if (atomic_inc_not_zero(&exists->refs)) { + int j = 0; spin_unlock(&mapping->private_lock); unlock_page(p); page_cache_release(p); - mark_extent_buffer_accessed(exists); - goto free_eb; + do { + old_eb = &exists->extent_buf[j++]; + if (old_eb->start == start) { + mark_extent_buffer_accessed(old_eb); + goto free_eb; + } + } while (j < MAX_EXTENT_BUFFERS_PER_PAGE); + BUG(); } /* @@ -4699,11 +4778,11 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, WARN_ON(PageDirty(p)); page_cache_release(p); } - attach_extent_buffer_page(eb, p); + attach_extent_buffer_page(eb_head(eb), p); spin_unlock(&mapping->private_lock); WARN_ON(PageDirty(p)); mark_page_accessed(p); - eb->pages[i] = p; + eb_head(eb)->pages[i] = p; if (!PageUptodate(p)) uptodate = 0; @@ -4713,7 +4792,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, */ } if (uptodate) - set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags); + set_bit(EXTENT_BUFFER_UPTODATE, &eb_head(eb)->bflags); again: ret = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM); if (ret) @@ -4721,19 +4800,19 @@ again: spin_lock(&fs_info->buffer_lock); ret = radix_tree_insert(&fs_info->buffer_radix, - start >> PAGE_CACHE_SHIFT, eb); + start >> PAGE_CACHE_SHIFT, eb_head(eb)); spin_unlock(&fs_info->buffer_lock); radix_tree_preload_end(); if (ret == -EEXIST) { - exists = find_extent_buffer(fs_info, start); - if (exists) + old_eb = find_extent_buffer(fs_info, start); + if (old_eb) goto free_eb; else goto again; } /* add one reference for the tree */ check_buffer_tree_ref(eb); - set_bit(EXTENT_BUFFER_IN_TREE, &eb->bflags); + set_bit(EXTENT_BUFFER_IN_TREE, &eb_head(eb)->bflags); /* * there is a race where release page may have @@ -4744,58 +4823,58 @@ again: * after the extent buffer is in the radix tree so * it doesn't get lost */ - SetPageChecked(eb->pages[0]); + SetPageChecked(eb_head(eb)->pages[0]); for (i = 1; i < num_pages; i++) { p = extent_buffer_page(eb, i); ClearPageChecked(p); unlock_page(p); } - unlock_page(eb->pages[0]); + unlock_page(eb_head(eb)->pages[0]); return eb; free_eb: for (i = 0; i < num_pages; i++) { - if (eb->pages[i]) - unlock_page(eb->pages[i]); + if (eb_head(eb)->pages[i]) + unlock_page(eb_head(eb)->pages[i]); } - WARN_ON(!atomic_dec_and_test(&eb->refs)); + WARN_ON(!atomic_dec_and_test(&eb_head(eb)->refs)); btrfs_release_extent_buffer(eb); - return exists; + return old_eb; } static inline void btrfs_release_extent_buffer_rcu(struct rcu_head *head) { - struct extent_buffer *eb = - container_of(head, struct extent_buffer, rcu_head); + struct extent_buffer_head *ebh = + container_of(head, struct extent_buffer_head, rcu_head); - __free_extent_buffer(eb); + __free_extent_buffer(ebh); } /* Expects to have eb->eb_lock already held */ -static int release_extent_buffer(struct extent_buffer *eb) +static int release_extent_buffer(struct extent_buffer_head *ebh) { - WARN_ON(atomic_read(&eb->refs) == 0); - if (atomic_dec_and_test(&eb->refs)) { - if (test_and_clear_bit(EXTENT_BUFFER_IN_TREE, &eb->bflags)) { - struct btrfs_fs_info *fs_info = eb->fs_info; + WARN_ON(atomic_read(&ebh->refs) == 0); + if (atomic_dec_and_test(&ebh->refs)) { + if (test_and_clear_bit(EXTENT_BUFFER_IN_TREE, &ebh->bflags)) { + struct btrfs_fs_info *fs_info = ebh->fs_info; - spin_unlock(&eb->refs_lock); + spin_unlock(&ebh->refs_lock); spin_lock(&fs_info->buffer_lock); radix_tree_delete(&fs_info->buffer_radix, - eb->start >> PAGE_CACHE_SHIFT); + ebh->extent_buf[0].start >> PAGE_CACHE_SHIFT); spin_unlock(&fs_info->buffer_lock); } else { - spin_unlock(&eb->refs_lock); + spin_unlock(&ebh->refs_lock); } /* Should be safe to release our pages at this point */ - btrfs_release_extent_buffer_page(eb, 0); - call_rcu(&eb->rcu_head, btrfs_release_extent_buffer_rcu); + btrfs_release_extent_buffer_page(&ebh->extent_buf[0], 0); + call_rcu(&ebh->rcu_head, btrfs_release_extent_buffer_rcu); return 1; } - spin_unlock(&eb->refs_lock); + spin_unlock(&ebh->refs_lock); return 0; } @@ -4804,48 +4883,52 @@ void free_extent_buffer(struct extent_buffer *eb) { int refs; int old; + struct extent_buffer_head *ebh; if (!eb) return; + ebh = eb_head(eb); while (1) { - refs = atomic_read(&eb->refs); + refs = atomic_read(&ebh->refs); if (refs <= 3) break; - old = atomic_cmpxchg(&eb->refs, refs, refs - 1); + old = atomic_cmpxchg(&ebh->refs, refs, refs - 1); if (old == refs) return; } - spin_lock(&eb->refs_lock); - if (atomic_read(&eb->refs) == 2 && - test_bit(EXTENT_BUFFER_DUMMY, &eb->bflags)) - atomic_dec(&eb->refs); + spin_lock(&ebh->refs_lock); + if (atomic_read(&ebh->refs) == 2 && + test_bit(EXTENT_BUFFER_DUMMY, &ebh->bflags)) + atomic_dec(&ebh->refs); - if (atomic_read(&eb->refs) == 2 && - test_bit(EXTENT_BUFFER_STALE, &eb->bflags) && - !extent_buffer_under_io(eb) && - test_and_clear_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags)) - atomic_dec(&eb->refs); + if (atomic_read(&ebh->refs) == 2 && + test_bit(EXTENT_BUFFER_STALE, &ebh->bflags) && + !extent_buffer_under_io(ebh) && + test_and_clear_bit(EXTENT_BUFFER_TREE_REF, &ebh->bflags)) + atomic_dec(&ebh->refs); /* * I know this is terrible, but it's temporary until we stop tracking * the uptodate bits and such for the extent buffers. */ - release_extent_buffer(eb); + release_extent_buffer(ebh); } void free_extent_buffer_stale(struct extent_buffer *eb) { + struct extent_buffer_head *ebh; if (!eb) return; - spin_lock(&eb->refs_lock); - set_bit(EXTENT_BUFFER_STALE, &eb->bflags); + ebh = eb_head(eb); + spin_lock(&ebh->refs_lock); + set_bit(EXTENT_BUFFER_STALE, &ebh->bflags); - if (atomic_read(&eb->refs) == 2 && !extent_buffer_under_io(eb) && - test_and_clear_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags)) - atomic_dec(&eb->refs); - release_extent_buffer(eb); + if (atomic_read(&ebh->refs) == 2 && !extent_buffer_under_io(ebh) && + test_and_clear_bit(EXTENT_BUFFER_TREE_REF, &ebh->bflags)) + atomic_dec(&ebh->refs); + release_extent_buffer(ebh); } void clear_extent_buffer_dirty(struct extent_buffer *eb) @@ -4875,7 +4958,7 @@ void clear_extent_buffer_dirty(struct extent_buffer *eb) ClearPageError(page); unlock_page(page); } - WARN_ON(atomic_read(&eb->refs) == 0); + WARN_ON(atomic_read(&eb_head(eb)->refs) == 0); } int set_extent_buffer_dirty(struct extent_buffer *eb) @@ -4886,11 +4969,11 @@ int set_extent_buffer_dirty(struct extent_buffer *eb) check_buffer_tree_ref(eb); - was_dirty = test_and_set_bit(EXTENT_BUFFER_DIRTY, &eb->bflags); + was_dirty = test_and_set_bit(EXTENT_BUFFER_DIRTY, &eb->ebflags); num_pages = num_extent_pages(eb->start, eb->len); - WARN_ON(atomic_read(&eb->refs) == 0); - WARN_ON(!test_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags)); + WARN_ON(atomic_read(&eb_head(eb)->refs) == 0); + WARN_ON(!test_bit(EXTENT_BUFFER_TREE_REF, &eb_head(eb)->bflags)); for (i = 0; i < num_pages; i++) set_page_dirty(extent_buffer_page(eb, i)); @@ -4903,7 +4986,9 @@ int clear_extent_buffer_uptodate(struct extent_buffer *eb) struct page *page; unsigned long num_pages; - clear_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags); + if (!eb || !eb_head(eb)) + return 0; + clear_bit(EXTENT_BUFFER_UPTODATE, &eb_head(eb)->bflags); num_pages = num_extent_pages(eb->start, eb->len); for (i = 0; i < num_pages; i++) { page = extent_buffer_page(eb, i); @@ -4919,7 +5004,7 @@ int set_extent_buffer_uptodate(struct extent_buffer *eb) struct page *page; unsigned long num_pages; - set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags); + set_bit(EXTENT_BUFFER_UPTODATE, &eb_head(eb)->bflags); num_pages = num_extent_pages(eb->start, eb->len); for (i = 0; i < num_pages; i++) { page = extent_buffer_page(eb, i); @@ -4930,7 +5015,7 @@ int set_extent_buffer_uptodate(struct extent_buffer *eb) int extent_buffer_uptodate(struct extent_buffer *eb) { - return test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags); + return test_bit(EXTENT_BUFFER_UPTODATE, &eb_head(eb)->bflags); } int read_extent_buffer_pages(struct extent_io_tree *tree, @@ -4948,8 +5033,9 @@ int read_extent_buffer_pages(struct extent_io_tree *tree, unsigned long num_reads = 0; struct bio *bio = NULL; unsigned long bio_flags = 0; + struct extent_buffer_head *ebh = eb_head(eb); - if (test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags)) + if (test_bit(EXTENT_BUFFER_UPTODATE, &ebh->bflags)) return 0; if (start) { @@ -4960,6 +5046,7 @@ int read_extent_buffer_pages(struct extent_io_tree *tree, start_i = 0; } +recheck: num_pages = num_extent_pages(eb->start, eb->len); for (i = start_i; i < num_pages; i++) { page = extent_buffer_page(eb, i); @@ -4977,13 +5064,26 @@ int read_extent_buffer_pages(struct extent_io_tree *tree, } if (all_uptodate) { if (start_i == 0) - set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags); + set_bit(EXTENT_BUFFER_UPTODATE, &ebh->bflags); goto unlock_exit; } - clear_bit(EXTENT_BUFFER_IOERR, &eb->bflags); - eb->read_mirror = 0; - atomic_set(&eb->io_pages, num_reads); + if (eb_head(eb)->io_eb) { + all_uptodate = 1; + i = start_i; + while (locked_pages > 0) { + page = extent_buffer_page(eb, i); + i++; + unlock_page(page); + locked_pages--; + } + goto recheck; + } + BUG_ON(eb_head(eb)->io_eb); + eb_head(eb)->io_eb = eb; + clear_bit(EXTENT_BUFFER_IOERR, &ebh->bflags); + ebh->read_mirror = 0; + atomic_set(&ebh->io_pages, num_reads); for (i = start_i; i < num_pages; i++) { page = extent_buffer_page(eb, i); if (!PageUptodate(page)) { @@ -5350,7 +5450,7 @@ void memmove_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset, int try_release_extent_buffer(struct page *page) { - struct extent_buffer *eb; + struct extent_buffer_head *ebh; /* * We need to make sure noboody is attaching this page to an eb right @@ -5362,17 +5462,17 @@ int try_release_extent_buffer(struct page *page) return 1; } - eb = (struct extent_buffer *)page->private; - BUG_ON(!eb); + ebh = (struct extent_buffer_head *)page->private; + BUG_ON(!ebh); /* * This is a little awful but should be ok, we need to make sure that * the eb doesn't disappear out from under us while we're looking at * this page. */ - spin_lock(&eb->refs_lock); - if (atomic_read(&eb->refs) != 1 || extent_buffer_under_io(eb)) { - spin_unlock(&eb->refs_lock); + spin_lock(&ebh->refs_lock); + if (atomic_read(&ebh->refs) != 1 || extent_buffer_under_io(ebh)) { + spin_unlock(&ebh->refs_lock); spin_unlock(&page->mapping->private_lock); return 0; } @@ -5382,10 +5482,11 @@ int try_release_extent_buffer(struct page *page) * If tree ref isn't set then we know the ref on this eb is a real ref, * so just return, this page will likely be freed soon anyway. */ - if (!test_and_clear_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags)) { - spin_unlock(&eb->refs_lock); + if (!test_and_clear_bit(EXTENT_BUFFER_TREE_REF, &ebh->bflags)) { + spin_unlock(&ebh->refs_lock); return 0; } - return release_extent_buffer(eb); + return release_extent_buffer(ebh); } + diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 58b27e5..71100ad 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -123,19 +123,12 @@ struct extent_state { #define INLINE_EXTENT_BUFFER_PAGES 16 #define MAX_INLINE_EXTENT_BUFFER_SIZE (INLINE_EXTENT_BUFFER_PAGES * PAGE_CACHE_SIZE) +#define MAX_EXTENT_BUFFERS_PER_PAGE 16 + struct extent_buffer { u64 start; unsigned long len; - unsigned long map_start; - unsigned long map_len; - unsigned long bflags; - struct btrfs_fs_info *fs_info; - spinlock_t refs_lock; - atomic_t refs; - atomic_t io_pages; - int read_mirror; - struct rcu_head rcu_head; - pid_t lock_owner; + unsigned long ebflags; /* count of read lock holders on the extent buffer */ atomic_t write_locks; @@ -146,6 +139,8 @@ struct extent_buffer { atomic_t spinning_writers; int lock_nested; + pid_t lock_owner; + /* protects write locks */ rwlock_t lock; @@ -159,7 +154,21 @@ struct extent_buffer { */ wait_queue_head_t read_lock_wq; wait_queue_head_t lock_wq; +}; + +struct extent_buffer_head { + unsigned long bflags; + struct btrfs_fs_info *fs_info; + spinlock_t refs_lock; + atomic_t refs; + atomic_t io_pages; + int read_mirror; + struct rcu_head rcu_head; + struct page *pages[INLINE_EXTENT_BUFFER_PAGES]; + + struct extent_buffer extent_buf[MAX_EXTENT_BUFFERS_PER_PAGE]; + struct extent_buffer *io_eb; /* eb that submitted the current I/O */ #ifdef CONFIG_BTRFS_DEBUG struct list_head leak_list; #endif @@ -176,6 +185,24 @@ static inline int extent_compress_type(unsigned long bio_flags) return bio_flags >> EXTENT_BIO_FLAG_SHIFT; } +/* + * return the extent_buffer_head that contains the extent buffer provided. + */ +static inline struct extent_buffer_head *eb_head(struct extent_buffer *eb) +{ + int start, index; + struct extent_buffer_head *ebh; + struct extent_buffer *eb_base; + + BUG_ON(!eb); + start = eb->start & (PAGE_CACHE_SIZE - 1); + index = start >> (ffs(eb->len) - 1); + eb_base = eb - index; + ebh = (struct extent_buffer_head *) + ((char *) eb_base - offsetof(struct extent_buffer_head, extent_buf)); + return ebh; + +} struct extent_map_tree; typedef struct extent_map *(get_extent_t)(struct inode *inode, @@ -287,15 +314,15 @@ static inline unsigned long num_extent_pages(u64 start, u64 len) (start >> PAGE_CACHE_SHIFT); } -static inline struct page *extent_buffer_page(struct extent_buffer *eb, - unsigned long i) +static inline struct page *extent_buffer_page( + struct extent_buffer *eb, unsigned long i) { - return eb->pages[i]; + return eb_head(eb)->pages[i]; } static inline void extent_buffer_get(struct extent_buffer *eb) { - atomic_inc(&eb->refs); + atomic_inc(&eb_head(eb)->refs); } int memcmp_extent_buffer(struct extent_buffer *eb, const void *ptrv, diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 07629e9..1ec359b 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -5936,7 +5936,7 @@ int btrfs_read_sys_array(struct btrfs_root *root) * to silence the warning eg. on PowerPC 64. */ if (PAGE_CACHE_SIZE > BTRFS_SUPER_INFO_SIZE) - SetPageUptodate(sb->pages[0]); + SetPageUptodate(eb_head(sb)->pages[0]); write_extent_buffer(sb, super_copy, 0, BTRFS_SUPER_INFO_SIZE); array_size = btrfs_super_sys_array_size(super_copy); diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index 3176cdc..5b79ac2 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -695,7 +695,7 @@ TRACE_EVENT(btrfs_cow_block, TP_fast_assign( __entry->root_objectid = root->root_key.objectid; __entry->buf_start = buf->start; - __entry->refs = atomic_read(&buf->refs); + __entry->refs = atomic_read(&eb_head(buf)->refs); __entry->cow_start = cow->start; __entry->buf_level = btrfs_header_level(buf); __entry->cow_level = btrfs_header_level(cow);