From 83a4d54840c88a4a45c49670f044b8c7ddeaa8c7 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Mon, 27 Dec 2010 16:19:53 +0800 Subject: Btrfs: Fix memory leak at umount fs_info, which is allocated in open_ctree(), should be freed in close_ctree(). Signed-off-by: Li Zefan --- fs/btrfs/disk-io.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index a5d2249e6da..089871e5cd5 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2513,6 +2513,8 @@ int close_ctree(struct btrfs_root *root) kfree(fs_info->chunk_root); kfree(fs_info->dev_root); kfree(fs_info->csum_root); + kfree(fs_info); + return 0; } -- cgit v1.2.3-70-g09d2 From 3612b49598c303cfb22a4b609427f829828e2427 Mon Sep 17 00:00:00 2001 From: Tsutomu Itoh Date: Tue, 25 Jan 2011 02:51:38 +0000 Subject: btrfs: fix return value check of btrfs_join_transaction() The error check of btrfs_join_transaction()/btrfs_join_transaction_nolock() is added, and the mistake of the error check in several places is corrected. For more stable Btrfs, I think that we should reduce BUG_ON(). But, I think that long time is necessary for this. So, I propose this patch as a short-term solution. With this patch: - To more stable Btrfs, the part that should be corrected is clarified. - The panic isn't done by the NULL pointer reference etc. (even if BUG_ON() is increased temporarily) - The error code is returned in the place where the error can be easily returned. As a long-term plan: - BUG_ON() is reduced by using the forced-readonly framework, etc. Signed-off-by: Tsutomu Itoh Signed-off-by: Chris Mason --- fs/btrfs/disk-io.c | 5 +++++ fs/btrfs/extent-tree.c | 2 +- fs/btrfs/inode.c | 24 ++++++++++++++++-------- fs/btrfs/ioctl.c | 2 +- fs/btrfs/relocation.c | 26 +++++++++++++++++++++++--- fs/btrfs/transaction.c | 5 +++++ 6 files changed, 51 insertions(+), 13 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 2887b8be6fd..b36eeef1919 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1550,6 +1550,7 @@ static int transaction_kthread(void *arg) spin_unlock(&root->fs_info->new_trans_lock); trans = btrfs_join_transaction(root, 1); + BUG_ON(IS_ERR(trans)); if (transid == trans->transid) { ret = btrfs_commit_transaction(trans, root); BUG_ON(ret); @@ -2464,10 +2465,14 @@ int btrfs_commit_super(struct btrfs_root *root) up_write(&root->fs_info->cleanup_work_sem); trans = btrfs_join_transaction(root, 1); + if (IS_ERR(trans)) + return PTR_ERR(trans); ret = btrfs_commit_transaction(trans, root); BUG_ON(ret); /* run commit again to drop the original snapshot */ trans = btrfs_join_transaction(root, 1); + if (IS_ERR(trans)) + return PTR_ERR(trans); btrfs_commit_transaction(trans, root); ret = btrfs_write_and_wait_transaction(NULL, root); BUG_ON(ret); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index bcf303204f7..98ee139885c 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -7478,7 +7478,7 @@ int btrfs_drop_dead_reloc_roots(struct btrfs_root *root) BUG_ON(reloc_root->commit_root != NULL); while (1) { trans = btrfs_join_transaction(root, 1); - BUG_ON(!trans); + BUG_ON(IS_ERR(trans)); mutex_lock(&root->fs_info->drop_mutex); ret = btrfs_drop_snapshot(trans, reloc_root); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 2b7d251d6ad..40fee137dd1 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -416,7 +416,7 @@ again: } if (start == 0) { trans = btrfs_join_transaction(root, 1); - BUG_ON(!trans); + BUG_ON(IS_ERR(trans)); btrfs_set_trans_block_group(trans, inode); trans->block_rsv = &root->fs_info->delalloc_block_rsv; @@ -612,6 +612,7 @@ retry: GFP_NOFS); trans = btrfs_join_transaction(root, 1); + BUG_ON(IS_ERR(trans)); ret = btrfs_reserve_extent(trans, root, async_extent->compressed_size, async_extent->compressed_size, @@ -771,7 +772,7 @@ static noinline int cow_file_range(struct inode *inode, BUG_ON(root == root->fs_info->tree_root); trans = btrfs_join_transaction(root, 1); - BUG_ON(!trans); + BUG_ON(IS_ERR(trans)); btrfs_set_trans_block_group(trans, inode); trans->block_rsv = &root->fs_info->delalloc_block_rsv; @@ -1049,7 +1050,7 @@ static noinline int run_delalloc_nocow(struct inode *inode, } else { trans = btrfs_join_transaction(root, 1); } - BUG_ON(!trans); + BUG_ON(IS_ERR(trans)); cow_start = (u64)-1; cur_offset = start; @@ -1704,7 +1705,7 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end) trans = btrfs_join_transaction_nolock(root, 1); else trans = btrfs_join_transaction(root, 1); - BUG_ON(!trans); + BUG_ON(IS_ERR(trans)); btrfs_set_trans_block_group(trans, inode); trans->block_rsv = &root->fs_info->delalloc_block_rsv; ret = btrfs_update_inode(trans, root, inode); @@ -1721,6 +1722,7 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end) trans = btrfs_join_transaction_nolock(root, 1); else trans = btrfs_join_transaction(root, 1); + BUG_ON(IS_ERR(trans)); btrfs_set_trans_block_group(trans, inode); trans->block_rsv = &root->fs_info->delalloc_block_rsv; @@ -2382,6 +2384,7 @@ void btrfs_orphan_cleanup(struct btrfs_root *root) if (root->orphan_block_rsv || root->orphan_item_inserted) { trans = btrfs_join_transaction(root, 1); + BUG_ON(IS_ERR(trans)); btrfs_end_transaction(trans, root); } @@ -4350,6 +4353,8 @@ int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc) trans = btrfs_join_transaction_nolock(root, 1); else trans = btrfs_join_transaction(root, 1); + if (IS_ERR(trans)) + return PTR_ERR(trans); btrfs_set_trans_block_group(trans, inode); if (nolock) ret = btrfs_end_transaction_nolock(trans, root); @@ -4375,6 +4380,7 @@ void btrfs_dirty_inode(struct inode *inode) return; trans = btrfs_join_transaction(root, 1); + BUG_ON(IS_ERR(trans)); btrfs_set_trans_block_group(trans, inode); ret = btrfs_update_inode(trans, root, inode); @@ -5179,6 +5185,8 @@ again: em = NULL; btrfs_release_path(root, path); trans = btrfs_join_transaction(root, 1); + if (IS_ERR(trans)) + return ERR_CAST(trans); goto again; } map = kmap(page); @@ -5283,8 +5291,8 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode, btrfs_drop_extent_cache(inode, start, start + len - 1, 0); trans = btrfs_join_transaction(root, 0); - if (!trans) - return ERR_PTR(-ENOMEM); + if (IS_ERR(trans)) + return ERR_CAST(trans); trans->block_rsv = &root->fs_info->delalloc_block_rsv; @@ -5508,7 +5516,7 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, * while we look for nocow cross refs */ trans = btrfs_join_transaction(root, 0); - if (!trans) + if (IS_ERR(trans)) goto must_cow; if (can_nocow_odirect(trans, inode, start, len) == 1) { @@ -5643,7 +5651,7 @@ again: BUG_ON(!ordered); trans = btrfs_join_transaction(root, 1); - if (!trans) { + if (IS_ERR(trans)) { err = -ENOMEM; goto out; } diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index edd82becbb9..04b4fb9144a 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -203,7 +203,7 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) trans = btrfs_join_transaction(root, 1); - BUG_ON(!trans); + BUG_ON(IS_ERR(trans)); ret = btrfs_update_inode(trans, root, inode); BUG_ON(ret); diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 045c9c2b2d7..ea996543024 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -2147,6 +2147,12 @@ again: } trans = btrfs_join_transaction(rc->extent_root, 1); + if (IS_ERR(trans)) { + if (!err) + btrfs_block_rsv_release(rc->extent_root, + rc->block_rsv, num_bytes); + return PTR_ERR(trans); + } if (!err) { if (num_bytes != rc->merging_rsv_size) { @@ -3222,6 +3228,7 @@ truncate: trans = btrfs_join_transaction(root, 0); if (IS_ERR(trans)) { btrfs_free_path(path); + ret = PTR_ERR(trans); goto out; } @@ -3628,6 +3635,7 @@ int prepare_to_relocate(struct reloc_control *rc) set_reloc_control(rc); trans = btrfs_join_transaction(rc->extent_root, 1); + BUG_ON(IS_ERR(trans)); btrfs_commit_transaction(trans, rc->extent_root); return 0; } @@ -3804,7 +3812,10 @@ static noinline_for_stack int relocate_block_group(struct reloc_control *rc) /* get rid of pinned extents */ trans = btrfs_join_transaction(rc->extent_root, 1); - btrfs_commit_transaction(trans, rc->extent_root); + if (IS_ERR(trans)) + err = PTR_ERR(trans); + else + btrfs_commit_transaction(trans, rc->extent_root); out_free: btrfs_free_block_rsv(rc->extent_root, rc->block_rsv); btrfs_free_path(path); @@ -4125,6 +4136,11 @@ int btrfs_recover_relocation(struct btrfs_root *root) set_reloc_control(rc); trans = btrfs_join_transaction(rc->extent_root, 1); + if (IS_ERR(trans)) { + unset_reloc_control(rc); + err = PTR_ERR(trans); + goto out_free; + } rc->merge_reloc_tree = 1; @@ -4154,9 +4170,13 @@ int btrfs_recover_relocation(struct btrfs_root *root) unset_reloc_control(rc); trans = btrfs_join_transaction(rc->extent_root, 1); - btrfs_commit_transaction(trans, rc->extent_root); -out: + if (IS_ERR(trans)) + err = PTR_ERR(trans); + else + btrfs_commit_transaction(trans, rc->extent_root); +out_free: kfree(rc); +out: while (!list_empty(&reloc_roots)) { reloc_root = list_entry(reloc_roots.next, struct btrfs_root, root_list); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index bae5c7b8bbe..3d73c8d93bb 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1161,6 +1161,11 @@ int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans, INIT_DELAYED_WORK(&ac->work, do_async_commit); ac->root = root; ac->newtrans = btrfs_join_transaction(root, 0); + if (IS_ERR(ac->newtrans)) { + int err = PTR_ERR(ac->newtrans); + kfree(ac); + return err; + } /* take transaction reference */ mutex_lock(&root->fs_info->trans_mutex); -- cgit v1.2.3-70-g09d2 From eb14ab8ed24a0405fd056068b28c33a1cd846024 Mon Sep 17 00:00:00 2001 From: Chris Mason Date: Thu, 10 Feb 2011 12:35:00 -0500 Subject: Btrfs: fix page->private races There is a race where btrfs_releasepage can drop the page->private contents just as alloc_extent_buffer is setting up pages for metadata. Because of how the Btrfs page flags work, this results in us skipping the crc on the page during IO. This patch sovles the race by waiting until after the extent buffer is inserted into the radix tree before it sets page private. Signed-off-by: Chris Mason --- fs/btrfs/disk-io.c | 8 ++++++-- fs/btrfs/extent_io.c | 38 +++++++++++++++++++++++++++++++++++--- 2 files changed, 41 insertions(+), 5 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index b36eeef1919..3e1ea3e0477 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -359,10 +359,14 @@ static int csum_dirty_buffer(struct btrfs_root *root, struct page *page) tree = &BTRFS_I(page->mapping->host)->io_tree; - if (page->private == EXTENT_PAGE_PRIVATE) + if (page->private == EXTENT_PAGE_PRIVATE) { + WARN_ON(1); goto out; - if (!page->private) + } + if (!page->private) { + WARN_ON(1); goto out; + } len = page->private >> 2; WARN_ON(len == 0); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 8862dda46ff..0418bf2c975 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -1946,6 +1946,7 @@ void set_page_extent_mapped(struct page *page) static void set_page_extent_head(struct page *page, unsigned long len) { + WARN_ON(!PagePrivate(page)); set_page_private(page, EXTENT_PAGE_PRIVATE_FIRST_PAGE | len << 2); } @@ -3195,7 +3196,13 @@ struct extent_buffer *alloc_extent_buffer(struct extent_io_tree *tree, } if (!PageUptodate(p)) uptodate = 0; - unlock_page(p); + + /* + * see below about how we avoid a nasty race with release page + * and why we unlock later + */ + if (i != 0) + unlock_page(p); } if (uptodate) set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags); @@ -3219,9 +3226,26 @@ struct extent_buffer *alloc_extent_buffer(struct extent_io_tree *tree, atomic_inc(&eb->refs); spin_unlock(&tree->buffer_lock); radix_tree_preload_end(); + + /* + * there is a race where release page may have + * tried to find this extent buffer in the radix + * but failed. It will tell the VM it is safe to + * reclaim the, and it will clear the page private bit. + * We must make sure to set the page private bit properly + * after the extent buffer is in the radix tree so + * it doesn't get lost + */ + set_page_extent_mapped(eb->first_page); + set_page_extent_head(eb->first_page, eb->len); + if (!page0) + unlock_page(eb->first_page); return eb; free_eb: + if (eb->first_page && !page0) + unlock_page(eb->first_page); + if (!atomic_dec_and_test(&eb->refs)) return exists; btrfs_release_extent_buffer(eb); @@ -3272,10 +3296,11 @@ int clear_extent_buffer_dirty(struct extent_io_tree *tree, continue; lock_page(page); + WARN_ON(!PagePrivate(page)); + + set_page_extent_mapped(page); if (i == 0) set_page_extent_head(page, eb->len); - else - set_page_private(page, EXTENT_PAGE_PRIVATE); clear_page_dirty_for_io(page); spin_lock_irq(&page->mapping->tree_lock); @@ -3465,6 +3490,13 @@ int read_extent_buffer_pages(struct extent_io_tree *tree, for (i = start_i; i < num_pages; i++) { page = extent_buffer_page(eb, i); + + WARN_ON(!PagePrivate(page)); + + set_page_extent_mapped(page); + if (i == 0) + set_page_extent_head(page, eb->len); + if (inc_all_pages) page_cache_get(page); if (!PageUptodate(page)) { -- cgit v1.2.3-70-g09d2 From ae0e47f02aaedbfdd5e4bec73f79b714d758223d Mon Sep 17 00:00:00 2001 From: "Justin P. Mattock" Date: Tue, 1 Mar 2011 15:06:02 +0100 Subject: Remove one to many n's in a word Signed-off-by: Justin P. Mattock Signed-off-by: Jiri Kosina --- drivers/dma/timb_dma.c | 2 +- drivers/usb/core/hub.c | 2 +- drivers/usb/host/uhci-hcd.c | 2 +- drivers/watchdog/sbc_epx_c3.c | 2 +- fs/btrfs/disk-io.c | 2 +- fs/notify/fanotify/fanotify_user.c | 2 +- fs/notify/inotify/inotify_user.c | 2 +- mm/mempolicy.c | 2 +- mm/shmem.c | 2 +- 9 files changed, 9 insertions(+), 9 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/drivers/dma/timb_dma.c b/drivers/dma/timb_dma.c index 3b88a4e7c98..f69f90a6187 100644 --- a/drivers/dma/timb_dma.c +++ b/drivers/dma/timb_dma.c @@ -629,7 +629,7 @@ static int td_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd, desc_node) list_move(&td_desc->desc_node, &td_chan->free_list); - /* now tear down the runnning */ + /* now tear down the running */ __td_finish(td_chan); spin_unlock_bh(&td_chan->lock); diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index d041c6826e4..bb9a25dbd2c 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -616,7 +616,7 @@ static int hub_port_disable(struct usb_hub *hub, int port1, int set_state) } /* - * Disable a port and mark a logical connnect-change event, so that some + * Disable a port and mark a logical connect-change event, so that some * time later khubd will disconnect() any existing usb_device on the port * and will re-enumerate if there actually is a device attached. */ diff --git a/drivers/usb/host/uhci-hcd.c b/drivers/usb/host/uhci-hcd.c index cee867829ec..4f65b14e5e0 100644 --- a/drivers/usb/host/uhci-hcd.c +++ b/drivers/usb/host/uhci-hcd.c @@ -471,7 +471,7 @@ static irqreturn_t uhci_irq(struct usb_hcd *hcd) /* * Store the current frame number in uhci->frame_number if the controller - * is runnning. Expand from 11 bits (of which we use only 10) to a + * is running. Expand from 11 bits (of which we use only 10) to a * full-sized integer. * * Like many other parts of the driver, this code relies on being polled diff --git a/drivers/watchdog/sbc_epx_c3.c b/drivers/watchdog/sbc_epx_c3.c index 28f1214457b..3066a5127ca 100644 --- a/drivers/watchdog/sbc_epx_c3.c +++ b/drivers/watchdog/sbc_epx_c3.c @@ -220,7 +220,7 @@ module_exit(watchdog_exit); MODULE_AUTHOR("Calin A. Culianu "); MODULE_DESCRIPTION("Hardware Watchdog Device for Winsystems EPX-C3 SBC. " "Note that there is no way to probe for this device -- " - "so only use it if you are *sure* you are runnning on this specific " + "so only use it if you are *sure* you are running on this specific " "SBC system from Winsystems! It writes to IO ports 0x1ee and 0x1ef!"); MODULE_LICENSE("GPL"); MODULE_ALIAS_MISCDEV(WATCHDOG_MINOR); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index fdce8799b98..7b658d2107b 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2489,7 +2489,7 @@ int close_ctree(struct btrfs_root *root) * ERROR state on disk. * * 2. when btrfs flips readonly just in btrfs_commit_super, - * and in such case, btrfs cannnot write sb via btrfs_commit_super, + * and in such case, btrfs cannot write sb via btrfs_commit_super, * and since fs_state has been set BTRFS_SUPER_FLAG_ERROR flag, * btrfs will cleanup all FS resources first and write sb then. */ diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 8b61220cffc..6b1305dc26c 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -876,7 +876,7 @@ SYSCALL_ALIAS(sys_fanotify_mark, SyS_fanotify_mark); #endif /* - * fanotify_user_setup - Our initialization function. Note that we cannnot return + * fanotify_user_setup - Our initialization function. Note that we cannot return * error because we have compiled-in VFS hooks. So an (unlikely) failure here * must result in panic(). */ diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index 4cd5d5d78f9..bd46e7c8a0e 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -841,7 +841,7 @@ out: } /* - * inotify_user_setup - Our initialization function. Note that we cannnot return + * inotify_user_setup - Our initialization function. Note that we cannot return * error because we have compiled-in VFS hooks. So an (unlikely) failure here * must result in panic(). */ diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 368fc9d2361..a5d79958492 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -993,7 +993,7 @@ int do_migrate_pages(struct mm_struct *mm, * most recent pair that moved (s != d). If we find a pair * that not only moved, but what's better, moved to an empty slot * (d is not set in tmp), then we break out then, with that pair. - * Otherwise when we finish scannng from_tmp, we at least have the + * Otherwise when we finish scanning from_tmp, we at least have the * most recent pair that moved. If we get all the way through * the scan of tmp without finding any node that moved, much less * moved to an empty node, then there is nothing left worth migrating. diff --git a/mm/shmem.c b/mm/shmem.c index 5ee67c99060..3cdb243256f 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -779,7 +779,7 @@ static int shmem_notify_change(struct dentry *dentry, struct iattr *attr) * If truncating down to a partial page, then * if that page is already allocated, hold it * in memory until the truncation is over, so - * truncate_partial_page cannnot miss it were + * truncate_partial_page cannot miss it were * it assigned to swap. */ if (newsize & (PAGE_CACHE_SIZE-1)) { -- cgit v1.2.3-70-g09d2 From 7eaceaccab5f40bbfda044629a6298616aeaed50 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 10 Mar 2011 08:52:07 +0100 Subject: block: remove per-queue plugging Code has been converted over to the new explicit on-stack plugging, and delay users have been converted to use the new API for that. So lets kill off the old plugging along with aops->sync_page(). Signed-off-by: Jens Axboe --- Documentation/block/biodoc.txt | 5 -- block/blk-core.c | 173 +++++------------------------------- block/blk-exec.c | 4 +- block/blk-flush.c | 3 +- block/blk-settings.c | 8 -- block/blk-throttle.c | 1 - block/blk.h | 2 - block/cfq-iosched.c | 8 -- block/deadline-iosched.c | 9 -- block/elevator.c | 43 +-------- block/noop-iosched.c | 8 -- drivers/block/cciss.c | 6 -- drivers/block/cpqarray.c | 3 - drivers/block/drbd/drbd_actlog.c | 2 - drivers/block/drbd/drbd_bitmap.c | 1 - drivers/block/drbd/drbd_int.h | 14 --- drivers/block/drbd/drbd_main.c | 33 +------ drivers/block/drbd/drbd_receiver.c | 20 +---- drivers/block/drbd/drbd_req.c | 4 - drivers/block/drbd/drbd_worker.c | 1 - drivers/block/drbd/drbd_wrappers.h | 18 ---- drivers/block/floppy.c | 1 - drivers/block/loop.c | 13 --- drivers/block/pktcdvd.c | 2 - drivers/block/umem.c | 16 +--- drivers/ide/ide-atapi.c | 3 +- drivers/ide/ide-io.c | 4 - drivers/ide/ide-park.c | 2 +- drivers/md/bitmap.c | 3 +- drivers/md/dm-crypt.c | 9 +- drivers/md/dm-kcopyd.c | 52 ++--------- drivers/md/dm-raid.c | 2 +- drivers/md/dm-raid1.c | 2 - drivers/md/dm-table.c | 24 ----- drivers/md/dm.c | 33 ++----- drivers/md/linear.c | 17 ---- drivers/md/md.c | 7 -- drivers/md/multipath.c | 31 ------- drivers/md/raid0.c | 16 ---- drivers/md/raid1.c | 83 ++++------------- drivers/md/raid10.c | 87 ++++-------------- drivers/md/raid5.c | 62 ++----------- drivers/md/raid5.h | 2 +- drivers/message/i2o/i2o_block.c | 6 +- drivers/mmc/card/queue.c | 3 +- drivers/s390/block/dasd.c | 2 +- drivers/s390/char/tape_block.c | 1 - drivers/scsi/scsi_transport_fc.c | 2 +- drivers/scsi/scsi_transport_sas.c | 6 +- drivers/target/target_core_iblock.c | 7 +- fs/adfs/inode.c | 1 - fs/affs/file.c | 2 - fs/aio.c | 4 +- fs/befs/linuxvfs.c | 1 - fs/bfs/file.c | 1 - fs/block_dev.c | 1 - fs/btrfs/disk-io.c | 79 ---------------- fs/btrfs/inode.c | 1 - fs/btrfs/volumes.c | 91 +++---------------- fs/buffer.c | 31 +------ fs/cifs/file.c | 30 ------- fs/direct-io.c | 5 +- fs/efs/inode.c | 1 - fs/exofs/inode.c | 1 - fs/ext2/inode.c | 2 - fs/ext3/inode.c | 3 - fs/ext4/inode.c | 4 - fs/fat/inode.c | 1 - fs/freevxfs/vxfs_subr.c | 1 - fs/fuse/inode.c | 1 - fs/gfs2/aops.c | 3 - fs/gfs2/meta_io.c | 1 - fs/hfs/inode.c | 2 - fs/hfsplus/inode.c | 2 - fs/hpfs/file.c | 1 - fs/isofs/inode.c | 1 - fs/jfs/inode.c | 1 - fs/jfs/jfs_metapage.c | 1 - fs/logfs/dev_bdev.c | 2 - fs/minix/inode.c | 1 - fs/nilfs2/btnode.c | 6 +- fs/nilfs2/gcinode.c | 1 - fs/nilfs2/inode.c | 1 - fs/nilfs2/mdt.c | 9 +- fs/nilfs2/page.c | 5 +- fs/nilfs2/page.h | 3 +- fs/ntfs/aops.c | 4 - fs/ntfs/compress.c | 3 +- fs/ocfs2/aops.c | 1 - fs/ocfs2/cluster/heartbeat.c | 4 - fs/omfs/file.c | 1 - fs/qnx4/inode.c | 1 - fs/reiserfs/inode.c | 1 - fs/sysv/itree.c | 1 - fs/ubifs/super.c | 1 - fs/udf/file.c | 1 - fs/udf/inode.c | 1 - fs/ufs/inode.c | 1 - fs/ufs/truncate.c | 2 +- fs/xfs/linux-2.6/xfs_aops.c | 1 - fs/xfs/linux-2.6/xfs_buf.c | 13 ++- include/linux/backing-dev.h | 16 ---- include/linux/blkdev.h | 31 ++----- include/linux/buffer_head.h | 1 - include/linux/device-mapper.h | 5 -- include/linux/elevator.h | 7 +- include/linux/fs.h | 1 - include/linux/pagemap.h | 12 --- include/linux/swap.h | 2 - mm/backing-dev.c | 6 -- mm/filemap.c | 67 ++------------ mm/memory-failure.c | 8 +- mm/nommu.c | 4 - mm/page-writeback.c | 2 +- mm/readahead.c | 12 --- mm/shmem.c | 1 - mm/swap_state.c | 5 +- mm/swapfile.c | 37 -------- mm/vmscan.c | 2 +- 119 files changed, 151 insertions(+), 1269 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/Documentation/block/biodoc.txt b/Documentation/block/biodoc.txt index b9a83dd2473..2a7b38c832c 100644 --- a/Documentation/block/biodoc.txt +++ b/Documentation/block/biodoc.txt @@ -963,11 +963,6 @@ elevator_dispatch_fn* fills the dispatch queue with ready requests. elevator_add_req_fn* called to add a new request into the scheduler -elevator_queue_empty_fn returns true if the merge queue is empty. - Drivers shouldn't use this, but rather check - if elv_next_request is NULL (without losing the - request if one exists!) - elevator_former_req_fn elevator_latter_req_fn These return the request before or after the one specified in disk sort order. Used by the diff --git a/block/blk-core.c b/block/blk-core.c index 6efb55cc5af..82a45898ba7 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -198,6 +198,19 @@ void blk_dump_rq_flags(struct request *rq, char *msg) } EXPORT_SYMBOL(blk_dump_rq_flags); +/* + * Make sure that plugs that were pending when this function was entered, + * are now complete and requests pushed to the queue. +*/ +static inline void queue_sync_plugs(struct request_queue *q) +{ + /* + * If the current process is plugged and has barriers submitted, + * we will livelock if we don't unplug first. + */ + blk_flush_plug(current); +} + static void blk_delay_work(struct work_struct *work) { struct request_queue *q; @@ -224,137 +237,6 @@ void blk_delay_queue(struct request_queue *q, unsigned long msecs) } EXPORT_SYMBOL(blk_delay_queue); -/* - * "plug" the device if there are no outstanding requests: this will - * force the transfer to start only after we have put all the requests - * on the list. - * - * This is called with interrupts off and no requests on the queue and - * with the queue lock held. - */ -void blk_plug_device(struct request_queue *q) -{ - WARN_ON(!irqs_disabled()); - - /* - * don't plug a stopped queue, it must be paired with blk_start_queue() - * which will restart the queueing - */ - if (blk_queue_stopped(q)) - return; - - if (!queue_flag_test_and_set(QUEUE_FLAG_PLUGGED, q)) { - mod_timer(&q->unplug_timer, jiffies + q->unplug_delay); - trace_block_plug(q); - } -} -EXPORT_SYMBOL(blk_plug_device); - -/** - * blk_plug_device_unlocked - plug a device without queue lock held - * @q: The &struct request_queue to plug - * - * Description: - * Like @blk_plug_device(), but grabs the queue lock and disables - * interrupts. - **/ -void blk_plug_device_unlocked(struct request_queue *q) -{ - unsigned long flags; - - spin_lock_irqsave(q->queue_lock, flags); - blk_plug_device(q); - spin_unlock_irqrestore(q->queue_lock, flags); -} -EXPORT_SYMBOL(blk_plug_device_unlocked); - -/* - * remove the queue from the plugged list, if present. called with - * queue lock held and interrupts disabled. - */ -int blk_remove_plug(struct request_queue *q) -{ - WARN_ON(!irqs_disabled()); - - if (!queue_flag_test_and_clear(QUEUE_FLAG_PLUGGED, q)) - return 0; - - del_timer(&q->unplug_timer); - return 1; -} -EXPORT_SYMBOL(blk_remove_plug); - -/* - * remove the plug and let it rip.. - */ -void __generic_unplug_device(struct request_queue *q) -{ - if (unlikely(blk_queue_stopped(q))) - return; - if (!blk_remove_plug(q) && !blk_queue_nonrot(q)) - return; - - q->request_fn(q); -} - -/** - * generic_unplug_device - fire a request queue - * @q: The &struct request_queue in question - * - * Description: - * Linux uses plugging to build bigger requests queues before letting - * the device have at them. If a queue is plugged, the I/O scheduler - * is still adding and merging requests on the queue. Once the queue - * gets unplugged, the request_fn defined for the queue is invoked and - * transfers started. - **/ -void generic_unplug_device(struct request_queue *q) -{ - if (blk_queue_plugged(q)) { - spin_lock_irq(q->queue_lock); - __generic_unplug_device(q); - spin_unlock_irq(q->queue_lock); - } -} -EXPORT_SYMBOL(generic_unplug_device); - -static void blk_backing_dev_unplug(struct backing_dev_info *bdi, - struct page *page) -{ - struct request_queue *q = bdi->unplug_io_data; - - blk_unplug(q); -} - -void blk_unplug_work(struct work_struct *work) -{ - struct request_queue *q = - container_of(work, struct request_queue, unplug_work); - - trace_block_unplug_io(q); - q->unplug_fn(q); -} - -void blk_unplug_timeout(unsigned long data) -{ - struct request_queue *q = (struct request_queue *)data; - - trace_block_unplug_timer(q); - kblockd_schedule_work(q, &q->unplug_work); -} - -void blk_unplug(struct request_queue *q) -{ - /* - * devices don't necessarily have an ->unplug_fn defined - */ - if (q->unplug_fn) { - trace_block_unplug_io(q); - q->unplug_fn(q); - } -} -EXPORT_SYMBOL(blk_unplug); - /** * blk_start_queue - restart a previously stopped queue * @q: The &struct request_queue in question @@ -389,7 +271,6 @@ EXPORT_SYMBOL(blk_start_queue); **/ void blk_stop_queue(struct request_queue *q) { - blk_remove_plug(q); cancel_delayed_work(&q->delay_work); queue_flag_set(QUEUE_FLAG_STOPPED, q); } @@ -411,11 +292,10 @@ EXPORT_SYMBOL(blk_stop_queue); */ void blk_sync_queue(struct request_queue *q) { - del_timer_sync(&q->unplug_timer); del_timer_sync(&q->timeout); - cancel_work_sync(&q->unplug_work); throtl_shutdown_timer_wq(q); cancel_delayed_work_sync(&q->delay_work); + queue_sync_plugs(q); } EXPORT_SYMBOL(blk_sync_queue); @@ -430,14 +310,9 @@ EXPORT_SYMBOL(blk_sync_queue); */ void __blk_run_queue(struct request_queue *q) { - blk_remove_plug(q); - if (unlikely(blk_queue_stopped(q))) return; - if (elv_queue_empty(q)) - return; - /* * Only recurse once to avoid overrunning the stack, let the unplug * handling reinvoke the handler shortly if we already got there. @@ -445,10 +320,8 @@ void __blk_run_queue(struct request_queue *q) if (!queue_flag_test_and_set(QUEUE_FLAG_REENTER, q)) { q->request_fn(q); queue_flag_clear(QUEUE_FLAG_REENTER, q); - } else { - queue_flag_set(QUEUE_FLAG_PLUGGED, q); - kblockd_schedule_work(q, &q->unplug_work); - } + } else + queue_delayed_work(kblockd_workqueue, &q->delay_work, 0); } EXPORT_SYMBOL(__blk_run_queue); @@ -535,8 +408,6 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) if (!q) return NULL; - q->backing_dev_info.unplug_io_fn = blk_backing_dev_unplug; - q->backing_dev_info.unplug_io_data = q; q->backing_dev_info.ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE; q->backing_dev_info.state = 0; @@ -556,13 +427,11 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) setup_timer(&q->backing_dev_info.laptop_mode_wb_timer, laptop_mode_timer_fn, (unsigned long) q); - init_timer(&q->unplug_timer); setup_timer(&q->timeout, blk_rq_timed_out_timer, (unsigned long) q); INIT_LIST_HEAD(&q->timeout_list); INIT_LIST_HEAD(&q->flush_queue[0]); INIT_LIST_HEAD(&q->flush_queue[1]); INIT_LIST_HEAD(&q->flush_data_in_flight); - INIT_WORK(&q->unplug_work, blk_unplug_work); INIT_DELAYED_WORK(&q->delay_work, blk_delay_work); kobject_init(&q->kobj, &blk_queue_ktype); @@ -652,7 +521,6 @@ blk_init_allocated_queue_node(struct request_queue *q, request_fn_proc *rfn, q->request_fn = rfn; q->prep_rq_fn = NULL; q->unprep_rq_fn = NULL; - q->unplug_fn = generic_unplug_device; q->queue_flags = QUEUE_FLAG_DEFAULT; q->queue_lock = lock; @@ -910,8 +778,8 @@ out: } /* - * No available requests for this queue, unplug the device and wait for some - * requests to become available. + * No available requests for this queue, wait for some requests to become + * available. * * Called with q->queue_lock held, and returns with it unlocked. */ @@ -932,7 +800,6 @@ static struct request *get_request_wait(struct request_queue *q, int rw_flags, trace_block_sleeprq(q, bio, rw_flags & 1); - __generic_unplug_device(q); spin_unlock_irq(q->queue_lock); io_schedule(); @@ -1058,7 +925,7 @@ static void add_acct_request(struct request_queue *q, struct request *rq, int where) { drive_stat_acct(rq, 1); - __elv_add_request(q, rq, where, 0); + __elv_add_request(q, rq, where); } /** @@ -2798,7 +2665,7 @@ static void flush_plug_list(struct blk_plug *plug) /* * rq is already accounted, so use raw insert */ - __elv_add_request(q, rq, ELEVATOR_INSERT_SORT, 0); + __elv_add_request(q, rq, ELEVATOR_INSERT_SORT); } if (q) { diff --git a/block/blk-exec.c b/block/blk-exec.c index cf1456a02ac..81e31819a59 100644 --- a/block/blk-exec.c +++ b/block/blk-exec.c @@ -54,8 +54,8 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk, rq->end_io = done; WARN_ON(irqs_disabled()); spin_lock_irq(q->queue_lock); - __elv_add_request(q, rq, where, 1); - __generic_unplug_device(q); + __elv_add_request(q, rq, where); + __blk_run_queue(q); /* the queue is stopped so it won't be plugged+unplugged */ if (rq->cmd_type == REQ_TYPE_PM_RESUME) q->request_fn(q); diff --git a/block/blk-flush.c b/block/blk-flush.c index 1e2aa8a8908..671fa9da756 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -194,7 +194,6 @@ static void flush_end_io(struct request *flush_rq, int error) { struct request_queue *q = flush_rq->q; struct list_head *running = &q->flush_queue[q->flush_running_idx]; - bool was_empty = elv_queue_empty(q); bool queued = false; struct request *rq, *n; @@ -213,7 +212,7 @@ static void flush_end_io(struct request *flush_rq, int error) } /* after populating an empty queue, kick it to avoid stall */ - if (queued && was_empty) + if (queued) __blk_run_queue(q); } diff --git a/block/blk-settings.c b/block/blk-settings.c index 36c8c1f2af1..c8d68921ddd 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -164,14 +164,6 @@ void blk_queue_make_request(struct request_queue *q, make_request_fn *mfn) blk_queue_congestion_threshold(q); q->nr_batching = BLK_BATCH_REQ; - q->unplug_thresh = 4; /* hmm */ - q->unplug_delay = msecs_to_jiffies(3); /* 3 milliseconds */ - if (q->unplug_delay == 0) - q->unplug_delay = 1; - - q->unplug_timer.function = blk_unplug_timeout; - q->unplug_timer.data = (unsigned long)q; - blk_set_default_limits(&q->limits); blk_queue_max_hw_sectors(q, BLK_SAFE_MAX_SECTORS); diff --git a/block/blk-throttle.c b/block/blk-throttle.c index a89043a3caa..b8dcdc2663a 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -800,7 +800,6 @@ out: if (nr_disp) { while((bio = bio_list_pop(&bio_list_on_stack))) generic_make_request(bio); - blk_unplug(q); } return nr_disp; } diff --git a/block/blk.h b/block/blk.h index 284b500852b..49d21af81d0 100644 --- a/block/blk.h +++ b/block/blk.h @@ -18,8 +18,6 @@ int blk_rq_append_bio(struct request_queue *q, struct request *rq, void blk_dequeue_request(struct request *rq); void __blk_queue_free_tags(struct request_queue *q); -void blk_unplug_work(struct work_struct *work); -void blk_unplug_timeout(unsigned long data); void blk_rq_timed_out_timer(unsigned long data); void blk_delete_timer(struct request *); void blk_add_timer(struct request *); diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 3202c7e87fb..ef631539dd2 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -499,13 +499,6 @@ static inline void cfq_schedule_dispatch(struct cfq_data *cfqd) } } -static int cfq_queue_empty(struct request_queue *q) -{ - struct cfq_data *cfqd = q->elevator->elevator_data; - - return !cfqd->rq_queued; -} - /* * Scale schedule slice based on io priority. Use the sync time slice only * if a queue is marked sync and has sync io queued. A sync queue with async @@ -4061,7 +4054,6 @@ static struct elevator_type iosched_cfq = { .elevator_add_req_fn = cfq_insert_request, .elevator_activate_req_fn = cfq_activate_request, .elevator_deactivate_req_fn = cfq_deactivate_request, - .elevator_queue_empty_fn = cfq_queue_empty, .elevator_completed_req_fn = cfq_completed_request, .elevator_former_req_fn = elv_rb_former_request, .elevator_latter_req_fn = elv_rb_latter_request, diff --git a/block/deadline-iosched.c b/block/deadline-iosched.c index b547cbca7b2..5139c0ea186 100644 --- a/block/deadline-iosched.c +++ b/block/deadline-iosched.c @@ -326,14 +326,6 @@ dispatch_request: return 1; } -static int deadline_queue_empty(struct request_queue *q) -{ - struct deadline_data *dd = q->elevator->elevator_data; - - return list_empty(&dd->fifo_list[WRITE]) - && list_empty(&dd->fifo_list[READ]); -} - static void deadline_exit_queue(struct elevator_queue *e) { struct deadline_data *dd = e->elevator_data; @@ -445,7 +437,6 @@ static struct elevator_type iosched_deadline = { .elevator_merge_req_fn = deadline_merged_requests, .elevator_dispatch_fn = deadline_dispatch_requests, .elevator_add_req_fn = deadline_add_request, - .elevator_queue_empty_fn = deadline_queue_empty, .elevator_former_req_fn = elv_rb_former_request, .elevator_latter_req_fn = elv_rb_latter_request, .elevator_init_fn = deadline_init_queue, diff --git a/block/elevator.c b/block/elevator.c index 25713927c0d..3ea208256e7 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -619,21 +619,12 @@ void elv_quiesce_end(struct request_queue *q) void elv_insert(struct request_queue *q, struct request *rq, int where) { - int unplug_it = 1; - trace_block_rq_insert(q, rq); rq->q = q; switch (where) { case ELEVATOR_INSERT_REQUEUE: - /* - * Most requeues happen because of a busy condition, - * don't force unplug of the queue for that case. - * Clear unplug_it and fall through. - */ - unplug_it = 0; - case ELEVATOR_INSERT_FRONT: rq->cmd_flags |= REQ_SOFTBARRIER; list_add(&rq->queuelist, &q->queue_head); @@ -679,24 +670,14 @@ void elv_insert(struct request_queue *q, struct request *rq, int where) rq->cmd_flags |= REQ_SOFTBARRIER; blk_insert_flush(rq); break; - default: printk(KERN_ERR "%s: bad insertion point %d\n", __func__, where); BUG(); } - - if (unplug_it && blk_queue_plugged(q)) { - int nrq = q->rq.count[BLK_RW_SYNC] + q->rq.count[BLK_RW_ASYNC] - - queue_in_flight(q); - - if (nrq >= q->unplug_thresh) - __generic_unplug_device(q); - } } -void __elv_add_request(struct request_queue *q, struct request *rq, int where, - int plug) +void __elv_add_request(struct request_queue *q, struct request *rq, int where) { BUG_ON(rq->cmd_flags & REQ_ON_PLUG); @@ -711,38 +692,20 @@ void __elv_add_request(struct request_queue *q, struct request *rq, int where, where == ELEVATOR_INSERT_SORT) where = ELEVATOR_INSERT_BACK; - if (plug) - blk_plug_device(q); - elv_insert(q, rq, where); } EXPORT_SYMBOL(__elv_add_request); -void elv_add_request(struct request_queue *q, struct request *rq, int where, - int plug) +void elv_add_request(struct request_queue *q, struct request *rq, int where) { unsigned long flags; spin_lock_irqsave(q->queue_lock, flags); - __elv_add_request(q, rq, where, plug); + __elv_add_request(q, rq, where); spin_unlock_irqrestore(q->queue_lock, flags); } EXPORT_SYMBOL(elv_add_request); -int elv_queue_empty(struct request_queue *q) -{ - struct elevator_queue *e = q->elevator; - - if (!list_empty(&q->queue_head)) - return 0; - - if (e->ops->elevator_queue_empty_fn) - return e->ops->elevator_queue_empty_fn(q); - - return 1; -} -EXPORT_SYMBOL(elv_queue_empty); - struct request *elv_latter_request(struct request_queue *q, struct request *rq) { struct elevator_queue *e = q->elevator; diff --git a/block/noop-iosched.c b/block/noop-iosched.c index 232c4b38cd3..06389e9ef96 100644 --- a/block/noop-iosched.c +++ b/block/noop-iosched.c @@ -39,13 +39,6 @@ static void noop_add_request(struct request_queue *q, struct request *rq) list_add_tail(&rq->queuelist, &nd->queue); } -static int noop_queue_empty(struct request_queue *q) -{ - struct noop_data *nd = q->elevator->elevator_data; - - return list_empty(&nd->queue); -} - static struct request * noop_former_request(struct request_queue *q, struct request *rq) { @@ -90,7 +83,6 @@ static struct elevator_type elevator_noop = { .elevator_merge_req_fn = noop_merged_requests, .elevator_dispatch_fn = noop_dispatch, .elevator_add_req_fn = noop_add_request, - .elevator_queue_empty_fn = noop_queue_empty, .elevator_former_req_fn = noop_former_request, .elevator_latter_req_fn = noop_latter_request, .elevator_init_fn = noop_init_queue, diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c index 9279272b373..35658f445fc 100644 --- a/drivers/block/cciss.c +++ b/drivers/block/cciss.c @@ -3170,12 +3170,6 @@ static void do_cciss_request(struct request_queue *q) int sg_index = 0; int chained = 0; - /* We call start_io here in case there is a command waiting on the - * queue that has not been sent. - */ - if (blk_queue_plugged(q)) - goto startio; - queue: creq = blk_peek_request(q); if (!creq) diff --git a/drivers/block/cpqarray.c b/drivers/block/cpqarray.c index 946dad4caef..b2fceb53e80 100644 --- a/drivers/block/cpqarray.c +++ b/drivers/block/cpqarray.c @@ -911,9 +911,6 @@ static void do_ida_request(struct request_queue *q) struct scatterlist tmp_sg[SG_MAX]; int i, dir, seg; - if (blk_queue_plugged(q)) - goto startio; - queue_next: creq = blk_peek_request(q); if (!creq) diff --git a/drivers/block/drbd/drbd_actlog.c b/drivers/block/drbd/drbd_actlog.c index ba95cba192b..2096628d6e6 100644 --- a/drivers/block/drbd/drbd_actlog.c +++ b/drivers/block/drbd/drbd_actlog.c @@ -689,8 +689,6 @@ void drbd_al_to_on_disk_bm(struct drbd_conf *mdev) } } - drbd_blk_run_queue(bdev_get_queue(mdev->ldev->md_bdev)); - /* always (try to) flush bitmap to stable storage */ drbd_md_flush(mdev); diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c index fd42832f785..0645ca829a9 100644 --- a/drivers/block/drbd/drbd_bitmap.c +++ b/drivers/block/drbd/drbd_bitmap.c @@ -840,7 +840,6 @@ static int bm_rw(struct drbd_conf *mdev, int rw) __must_hold(local) for (i = 0; i < num_pages; i++) bm_page_io_async(mdev, b, i, rw); - drbd_blk_run_queue(bdev_get_queue(mdev->ldev->md_bdev)); wait_event(b->bm_io_wait, atomic_read(&b->bm_async_io) == 0); if (test_bit(BM_MD_IO_ERROR, &b->bm_flags)) { diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h index 3803a034893..0b5718e1958 100644 --- a/drivers/block/drbd/drbd_int.h +++ b/drivers/block/drbd/drbd_int.h @@ -2382,20 +2382,6 @@ static inline int drbd_queue_order_type(struct drbd_conf *mdev) return QUEUE_ORDERED_NONE; } -static inline void drbd_blk_run_queue(struct request_queue *q) -{ - if (q && q->unplug_fn) - q->unplug_fn(q); -} - -static inline void drbd_kick_lo(struct drbd_conf *mdev) -{ - if (get_ldev(mdev)) { - drbd_blk_run_queue(bdev_get_queue(mdev->ldev->backing_bdev)); - put_ldev(mdev); - } -} - static inline void drbd_md_flush(struct drbd_conf *mdev) { int r; diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 29cd0dc9fe4..6049cb85310 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -2719,35 +2719,6 @@ static int drbd_release(struct gendisk *gd, fmode_t mode) return 0; } -static void drbd_unplug_fn(struct request_queue *q) -{ - struct drbd_conf *mdev = q->queuedata; - - /* unplug FIRST */ - spin_lock_irq(q->queue_lock); - blk_remove_plug(q); - spin_unlock_irq(q->queue_lock); - - /* only if connected */ - spin_lock_irq(&mdev->req_lock); - if (mdev->state.pdsk >= D_INCONSISTENT && mdev->state.conn >= C_CONNECTED) { - D_ASSERT(mdev->state.role == R_PRIMARY); - if (test_and_clear_bit(UNPLUG_REMOTE, &mdev->flags)) { - /* add to the data.work queue, - * unless already queued. - * XXX this might be a good addition to drbd_queue_work - * anyways, to detect "double queuing" ... */ - if (list_empty(&mdev->unplug_work.list)) - drbd_queue_work(&mdev->data.work, - &mdev->unplug_work); - } - } - spin_unlock_irq(&mdev->req_lock); - - if (mdev->state.disk >= D_INCONSISTENT) - drbd_kick_lo(mdev); -} - static void drbd_set_defaults(struct drbd_conf *mdev) { /* This way we get a compile error when sync_conf grows, @@ -3222,9 +3193,7 @@ struct drbd_conf *drbd_new_device(unsigned int minor) blk_queue_max_segment_size(q, DRBD_MAX_SEGMENT_SIZE); blk_queue_bounce_limit(q, BLK_BOUNCE_ANY); blk_queue_merge_bvec(q, drbd_merge_bvec); - q->queue_lock = &mdev->req_lock; /* needed since we use */ - /* plugging on a queue, that actually has no requests! */ - q->unplug_fn = drbd_unplug_fn; + q->queue_lock = &mdev->req_lock; mdev->md_io_page = alloc_page(GFP_KERNEL); if (!mdev->md_io_page) diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index 24487d4fb20..84132f8bf8a 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -187,15 +187,6 @@ static struct page *drbd_pp_first_pages_or_try_alloc(struct drbd_conf *mdev, int return NULL; } -/* kick lower level device, if we have more than (arbitrary number) - * reference counts on it, which typically are locally submitted io - * requests. don't use unacked_cnt, so we speed up proto A and B, too. */ -static void maybe_kick_lo(struct drbd_conf *mdev) -{ - if (atomic_read(&mdev->local_cnt) >= mdev->net_conf->unplug_watermark) - drbd_kick_lo(mdev); -} - static void reclaim_net_ee(struct drbd_conf *mdev, struct list_head *to_be_freed) { struct drbd_epoch_entry *e; @@ -219,7 +210,6 @@ static void drbd_kick_lo_and_reclaim_net(struct drbd_conf *mdev) LIST_HEAD(reclaimed); struct drbd_epoch_entry *e, *t; - maybe_kick_lo(mdev); spin_lock_irq(&mdev->req_lock); reclaim_net_ee(mdev, &reclaimed); spin_unlock_irq(&mdev->req_lock); @@ -436,8 +426,7 @@ void _drbd_wait_ee_list_empty(struct drbd_conf *mdev, struct list_head *head) while (!list_empty(head)) { prepare_to_wait(&mdev->ee_wait, &wait, TASK_UNINTERRUPTIBLE); spin_unlock_irq(&mdev->req_lock); - drbd_kick_lo(mdev); - schedule(); + io_schedule(); finish_wait(&mdev->ee_wait, &wait); spin_lock_irq(&mdev->req_lock); } @@ -1147,7 +1136,6 @@ next_bio: drbd_generic_make_request(mdev, fault_type, bio); } while (bios); - maybe_kick_lo(mdev); return 0; fail: @@ -1167,9 +1155,6 @@ static int receive_Barrier(struct drbd_conf *mdev, enum drbd_packets cmd, unsign inc_unacked(mdev); - if (mdev->net_conf->wire_protocol != DRBD_PROT_C) - drbd_kick_lo(mdev); - mdev->current_epoch->barrier_nr = p->barrier; rv = drbd_may_finish_epoch(mdev, mdev->current_epoch, EV_GOT_BARRIER_NR); @@ -3556,9 +3541,6 @@ static int receive_skip(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned static int receive_UnplugRemote(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned int data_size) { - if (mdev->state.disk >= D_INCONSISTENT) - drbd_kick_lo(mdev); - /* Make sure we've acked all the TCP data associated * with the data requests being unplugged */ drbd_tcp_quickack(mdev->data.socket); diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c index 11a75d32a2e..ad3fc6228f2 100644 --- a/drivers/block/drbd/drbd_req.c +++ b/drivers/block/drbd/drbd_req.c @@ -960,10 +960,6 @@ allocate_barrier: bio_endio(req->private_bio, -EIO); } - /* we need to plug ALWAYS since we possibly need to kick lo_dev. - * we plug after submit, so we won't miss an unplug event */ - drbd_plug_device(mdev); - return 0; fail_conflicting: diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c index 34f224b018b..e027446590d 100644 --- a/drivers/block/drbd/drbd_worker.c +++ b/drivers/block/drbd/drbd_worker.c @@ -792,7 +792,6 @@ int drbd_resync_finished(struct drbd_conf *mdev) * queue (or even the read operations for those packets * is not finished by now). Retry in 100ms. */ - drbd_kick_lo(mdev); __set_current_state(TASK_INTERRUPTIBLE); schedule_timeout(HZ / 10); w = kmalloc(sizeof(struct drbd_work), GFP_ATOMIC); diff --git a/drivers/block/drbd/drbd_wrappers.h b/drivers/block/drbd/drbd_wrappers.h index defdb5013ea..53586fa5ae1 100644 --- a/drivers/block/drbd/drbd_wrappers.h +++ b/drivers/block/drbd/drbd_wrappers.h @@ -45,24 +45,6 @@ static inline void drbd_generic_make_request(struct drbd_conf *mdev, generic_make_request(bio); } -static inline void drbd_plug_device(struct drbd_conf *mdev) -{ - struct request_queue *q; - q = bdev_get_queue(mdev->this_bdev); - - spin_lock_irq(q->queue_lock); - -/* XXX the check on !blk_queue_plugged is redundant, - * implicitly checked in blk_plug_device */ - - if (!blk_queue_plugged(q)) { - blk_plug_device(q); - del_timer(&q->unplug_timer); - /* unplugging should not happen automatically... */ - } - spin_unlock_irq(q->queue_lock); -} - static inline int drbd_crypto_is_hash(struct crypto_tfm *tfm) { return (crypto_tfm_alg_type(tfm) & CRYPTO_ALG_TYPE_HASH_MASK) diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index b9ba04fc2b3..271142b9e2c 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -3837,7 +3837,6 @@ static int __floppy_read_block_0(struct block_device *bdev) bio.bi_end_io = floppy_rb0_complete; submit_bio(READ, &bio); - generic_unplug_device(bdev_get_queue(bdev)); process_fd_request(); wait_for_completion(&complete); diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 49e6a545eb6..01b8e4a87c9 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -541,17 +541,6 @@ out: return 0; } -/* - * kick off io on the underlying address space - */ -static void loop_unplug(struct request_queue *q) -{ - struct loop_device *lo = q->queuedata; - - queue_flag_clear_unlocked(QUEUE_FLAG_PLUGGED, q); - blk_run_address_space(lo->lo_backing_file->f_mapping); -} - struct switch_request { struct file *file; struct completion wait; @@ -918,7 +907,6 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, */ blk_queue_make_request(lo->lo_queue, loop_make_request); lo->lo_queue->queuedata = lo; - lo->lo_queue->unplug_fn = loop_unplug; if (!(lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync) blk_queue_flush(lo->lo_queue, REQ_FLUSH); @@ -1020,7 +1008,6 @@ static int loop_clr_fd(struct loop_device *lo, struct block_device *bdev) kthread_stop(lo->lo_thread); - lo->lo_queue->unplug_fn = NULL; lo->lo_backing_file = NULL; loop_release_xfer(lo); diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 77d70eebb6b..d20e13f8000 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -1606,8 +1606,6 @@ static int kcdrwd(void *foobar) min_sleep_time = pkt->sleep_time; } - generic_unplug_device(bdev_get_queue(pd->bdev)); - VPRINTK("kcdrwd: sleeping\n"); residue = schedule_timeout(min_sleep_time); VPRINTK("kcdrwd: wake up\n"); diff --git a/drivers/block/umem.c b/drivers/block/umem.c index 8be57151f5d..653439faa72 100644 --- a/drivers/block/umem.c +++ b/drivers/block/umem.c @@ -241,8 +241,7 @@ static void dump_dmastat(struct cardinfo *card, unsigned int dmastat) * * Whenever IO on the active page completes, the Ready page is activated * and the ex-Active page is clean out and made Ready. - * Otherwise the Ready page is only activated when it becomes full, or - * when mm_unplug_device is called via the unplug_io_fn. + * Otherwise the Ready page is only activated when it becomes full. * * If a request arrives while both pages a full, it is queued, and b_rdev is * overloaded to record whether it was a read or a write. @@ -333,17 +332,6 @@ static inline void reset_page(struct mm_page *page) page->biotail = &page->bio; } -static void mm_unplug_device(struct request_queue *q) -{ - struct cardinfo *card = q->queuedata; - unsigned long flags; - - spin_lock_irqsave(&card->lock, flags); - if (blk_remove_plug(q)) - activate(card); - spin_unlock_irqrestore(&card->lock, flags); -} - /* * If there is room on Ready page, take * one bh off list and add it. @@ -535,7 +523,6 @@ static int mm_make_request(struct request_queue *q, struct bio *bio) *card->biotail = bio; bio->bi_next = NULL; card->biotail = &bio->bi_next; - blk_plug_device(q); spin_unlock_irq(&card->lock); return 0; @@ -907,7 +894,6 @@ static int __devinit mm_pci_probe(struct pci_dev *dev, blk_queue_make_request(card->queue, mm_make_request); card->queue->queue_lock = &card->lock; card->queue->queuedata = card; - card->queue->unplug_fn = mm_unplug_device; tasklet_init(&card->tasklet, process_page, (unsigned long)card); diff --git a/drivers/ide/ide-atapi.c b/drivers/ide/ide-atapi.c index e88a2cf1771..6f218e014e9 100644 --- a/drivers/ide/ide-atapi.c +++ b/drivers/ide/ide-atapi.c @@ -233,8 +233,7 @@ int ide_queue_sense_rq(ide_drive_t *drive, void *special) drive->hwif->rq = NULL; - elv_add_request(drive->queue, &drive->sense_rq, - ELEVATOR_INSERT_FRONT, 0); + elv_add_request(drive->queue, &drive->sense_rq, ELEVATOR_INSERT_FRONT); return 0; } EXPORT_SYMBOL_GPL(ide_queue_sense_rq); diff --git a/drivers/ide/ide-io.c b/drivers/ide/ide-io.c index 999dac054bc..f4077840d3a 100644 --- a/drivers/ide/ide-io.c +++ b/drivers/ide/ide-io.c @@ -549,8 +549,6 @@ plug_device_2: if (rq) blk_requeue_request(q, rq); - if (!elv_queue_empty(q)) - blk_plug_device(q); } void ide_requeue_and_plug(ide_drive_t *drive, struct request *rq) @@ -562,8 +560,6 @@ void ide_requeue_and_plug(ide_drive_t *drive, struct request *rq) if (rq) blk_requeue_request(q, rq); - if (!elv_queue_empty(q)) - blk_plug_device(q); spin_unlock_irqrestore(q->queue_lock, flags); } diff --git a/drivers/ide/ide-park.c b/drivers/ide/ide-park.c index 88a380c5a47..6ab9ab2a508 100644 --- a/drivers/ide/ide-park.c +++ b/drivers/ide/ide-park.c @@ -52,7 +52,7 @@ static void issue_park_cmd(ide_drive_t *drive, unsigned long timeout) rq->cmd[0] = REQ_UNPARK_HEADS; rq->cmd_len = 1; rq->cmd_type = REQ_TYPE_SPECIAL; - elv_add_request(q, rq, ELEVATOR_INSERT_FRONT, 1); + elv_add_request(q, rq, ELEVATOR_INSERT_FRONT); out: return; diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c index 9a35320fb59..54bfc274b39 100644 --- a/drivers/md/bitmap.c +++ b/drivers/md/bitmap.c @@ -1339,8 +1339,7 @@ int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sect prepare_to_wait(&bitmap->overflow_wait, &__wait, TASK_UNINTERRUPTIBLE); spin_unlock_irq(&bitmap->lock); - md_unplug(bitmap->mddev); - schedule(); + io_schedule(); finish_wait(&bitmap->overflow_wait, &__wait); continue; } diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 4e054bd9166..2c62c1169f7 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -991,11 +991,6 @@ static void clone_init(struct dm_crypt_io *io, struct bio *clone) clone->bi_destructor = dm_crypt_bio_destructor; } -static void kcryptd_unplug(struct crypt_config *cc) -{ - blk_unplug(bdev_get_queue(cc->dev->bdev)); -} - static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp) { struct crypt_config *cc = io->target->private; @@ -1008,10 +1003,8 @@ static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp) * one in order to decrypt the whole bio data *afterwards*. */ clone = bio_alloc_bioset(gfp, bio_segments(base_bio), cc->bs); - if (!clone) { - kcryptd_unplug(cc); + if (!clone) return 1; - } crypt_inc_pending(io); diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c index 924f5f0084c..400cf35094a 100644 --- a/drivers/md/dm-kcopyd.c +++ b/drivers/md/dm-kcopyd.c @@ -37,13 +37,6 @@ struct dm_kcopyd_client { unsigned int nr_pages; unsigned int nr_free_pages; - /* - * Block devices to unplug. - * Non-NULL pointer means that a block device has some pending requests - * and needs to be unplugged. - */ - struct block_device *unplug[2]; - struct dm_io_client *io_client; wait_queue_head_t destroyq; @@ -315,31 +308,6 @@ static int run_complete_job(struct kcopyd_job *job) return 0; } -/* - * Unplug the block device at the specified index. - */ -static void unplug(struct dm_kcopyd_client *kc, int rw) -{ - if (kc->unplug[rw] != NULL) { - blk_unplug(bdev_get_queue(kc->unplug[rw])); - kc->unplug[rw] = NULL; - } -} - -/* - * Prepare block device unplug. If there's another device - * to be unplugged at the same array index, we unplug that - * device first. - */ -static void prepare_unplug(struct dm_kcopyd_client *kc, int rw, - struct block_device *bdev) -{ - if (likely(kc->unplug[rw] == bdev)) - return; - unplug(kc, rw); - kc->unplug[rw] = bdev; -} - static void complete_io(unsigned long error, void *context) { struct kcopyd_job *job = (struct kcopyd_job *) context; @@ -386,15 +354,12 @@ static int run_io_job(struct kcopyd_job *job) .client = job->kc->io_client, }; - if (job->rw == READ) { + if (job->rw == READ) r = dm_io(&io_req, 1, &job->source, NULL); - prepare_unplug(job->kc, READ, job->source.bdev); - } else { + else { if (job->num_dests > 1) io_req.bi_rw |= REQ_UNPLUG; r = dm_io(&io_req, job->num_dests, job->dests, NULL); - if (!(io_req.bi_rw & REQ_UNPLUG)) - prepare_unplug(job->kc, WRITE, job->dests[0].bdev); } return r; @@ -466,6 +431,7 @@ static void do_work(struct work_struct *work) { struct dm_kcopyd_client *kc = container_of(work, struct dm_kcopyd_client, kcopyd_work); + struct blk_plug plug; /* * The order that these are called is *very* important. @@ -473,18 +439,12 @@ static void do_work(struct work_struct *work) * Pages jobs when successful will jump onto the io jobs * list. io jobs call wake when they complete and it all * starts again. - * - * Note that io_jobs add block devices to the unplug array, - * this array is cleared with "unplug" calls. It is thus - * forbidden to run complete_jobs after io_jobs and before - * unplug because the block device could be destroyed in - * job completion callback. */ + blk_start_plug(&plug); process_jobs(&kc->complete_jobs, kc, run_complete_job); process_jobs(&kc->pages_jobs, kc, run_pages_job); process_jobs(&kc->io_jobs, kc, run_io_job); - unplug(kc, READ); - unplug(kc, WRITE); + blk_finish_plug(&plug); } /* @@ -665,8 +625,6 @@ int dm_kcopyd_client_create(unsigned int nr_pages, INIT_LIST_HEAD(&kc->io_jobs); INIT_LIST_HEAD(&kc->pages_jobs); - memset(kc->unplug, 0, sizeof(kc->unplug)); - kc->job_pool = mempool_create_slab_pool(MIN_JOBS, _job_cache); if (!kc->job_pool) goto bad_slab; diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index b9e1e15ef11..5ef136cdba9 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -394,7 +394,7 @@ static void raid_unplug(struct dm_target_callbacks *cb) { struct raid_set *rs = container_of(cb, struct raid_set, callbacks); - md_raid5_unplug_device(rs->md.private); + md_raid5_kick_device(rs->md.private); } /* diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c index dee326775c6..976ad4688af 100644 --- a/drivers/md/dm-raid1.c +++ b/drivers/md/dm-raid1.c @@ -842,8 +842,6 @@ static void do_mirror(struct work_struct *work) do_reads(ms, &reads); do_writes(ms, &writes); do_failures(ms, &failures); - - dm_table_unplug_all(ms->ti->table); } /*----------------------------------------------------------------- diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 38e4eb1bb96..f50a7b95225 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -1275,29 +1275,6 @@ int dm_table_any_busy_target(struct dm_table *t) return 0; } -void dm_table_unplug_all(struct dm_table *t) -{ - struct dm_dev_internal *dd; - struct list_head *devices = dm_table_get_devices(t); - struct dm_target_callbacks *cb; - - list_for_each_entry(dd, devices, list) { - struct request_queue *q = bdev_get_queue(dd->dm_dev.bdev); - char b[BDEVNAME_SIZE]; - - if (likely(q)) - blk_unplug(q); - else - DMWARN_LIMIT("%s: Cannot unplug nonexistent device %s", - dm_device_name(t->md), - bdevname(dd->dm_dev.bdev, b)); - } - - list_for_each_entry(cb, &t->target_callbacks, list) - if (cb->unplug_fn) - cb->unplug_fn(cb); -} - struct mapped_device *dm_table_get_md(struct dm_table *t) { return t->md; @@ -1345,4 +1322,3 @@ EXPORT_SYMBOL(dm_table_get_mode); EXPORT_SYMBOL(dm_table_get_md); EXPORT_SYMBOL(dm_table_put); EXPORT_SYMBOL(dm_table_get); -EXPORT_SYMBOL(dm_table_unplug_all); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index eaa3af0e063..d22b9905c16 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -807,8 +807,6 @@ void dm_requeue_unmapped_request(struct request *clone) dm_unprep_request(rq); spin_lock_irqsave(q->queue_lock, flags); - if (elv_queue_empty(q)) - blk_plug_device(q); blk_requeue_request(q, rq); spin_unlock_irqrestore(q->queue_lock, flags); @@ -1613,10 +1611,10 @@ static void dm_request_fn(struct request_queue *q) * number of in-flight I/Os after the queue is stopped in * dm_suspend(). */ - while (!blk_queue_plugged(q) && !blk_queue_stopped(q)) { + while (!blk_queue_stopped(q)) { rq = blk_peek_request(q); if (!rq) - goto plug_and_out; + goto delay_and_out; /* always use block 0 to find the target for flushes for now */ pos = 0; @@ -1627,7 +1625,7 @@ static void dm_request_fn(struct request_queue *q) BUG_ON(!dm_target_is_valid(ti)); if (ti->type->busy && ti->type->busy(ti)) - goto plug_and_out; + goto delay_and_out; blk_start_request(rq); clone = rq->special; @@ -1647,11 +1645,8 @@ requeued: BUG_ON(!irqs_disabled()); spin_lock(q->queue_lock); -plug_and_out: - if (!elv_queue_empty(q)) - /* Some requests still remain, retry later */ - blk_plug_device(q); - +delay_and_out: + blk_delay_queue(q, HZ / 10); out: dm_table_put(map); @@ -1680,20 +1675,6 @@ static int dm_lld_busy(struct request_queue *q) return r; } -static void dm_unplug_all(struct request_queue *q) -{ - struct mapped_device *md = q->queuedata; - struct dm_table *map = dm_get_live_table(md); - - if (map) { - if (dm_request_based(md)) - generic_unplug_device(q); - - dm_table_unplug_all(map); - dm_table_put(map); - } -} - static int dm_any_congested(void *congested_data, int bdi_bits) { int r = bdi_bits; @@ -1817,7 +1798,6 @@ static void dm_init_md_queue(struct mapped_device *md) md->queue->backing_dev_info.congested_data = md; blk_queue_make_request(md->queue, dm_request); blk_queue_bounce_limit(md->queue, BLK_BOUNCE_ANY); - md->queue->unplug_fn = dm_unplug_all; blk_queue_merge_bvec(md->queue, dm_merge_bvec); blk_queue_flush(md->queue, REQ_FLUSH | REQ_FUA); } @@ -2263,8 +2243,6 @@ static int dm_wait_for_completion(struct mapped_device *md, int interruptible) int r = 0; DECLARE_WAITQUEUE(wait, current); - dm_unplug_all(md->queue); - add_wait_queue(&md->wait, &wait); while (1) { @@ -2539,7 +2517,6 @@ int dm_resume(struct mapped_device *md) clear_bit(DMF_SUSPENDED, &md->flags); - dm_table_unplug_all(map); r = 0; out: dm_table_put(map); diff --git a/drivers/md/linear.c b/drivers/md/linear.c index 8a2f767f26d..38861b5b9d9 100644 --- a/drivers/md/linear.c +++ b/drivers/md/linear.c @@ -87,22 +87,6 @@ static int linear_mergeable_bvec(struct request_queue *q, return maxsectors << 9; } -static void linear_unplug(struct request_queue *q) -{ - mddev_t *mddev = q->queuedata; - linear_conf_t *conf; - int i; - - rcu_read_lock(); - conf = rcu_dereference(mddev->private); - - for (i=0; i < mddev->raid_disks; i++) { - struct request_queue *r_queue = bdev_get_queue(conf->disks[i].rdev->bdev); - blk_unplug(r_queue); - } - rcu_read_unlock(); -} - static int linear_congested(void *data, int bits) { mddev_t *mddev = data; @@ -225,7 +209,6 @@ static int linear_run (mddev_t *mddev) md_set_array_sectors(mddev, linear_size(mddev, 0, 0)); blk_queue_merge_bvec(mddev->queue, linear_mergeable_bvec); - mddev->queue->unplug_fn = linear_unplug; mddev->queue->backing_dev_info.congested_fn = linear_congested; mddev->queue->backing_dev_info.congested_data = mddev; md_integrity_register(mddev); diff --git a/drivers/md/md.c b/drivers/md/md.c index 0cc30ecda4c..ca0d79c264b 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -4812,7 +4812,6 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open) __md_stop_writes(mddev); md_stop(mddev); mddev->queue->merge_bvec_fn = NULL; - mddev->queue->unplug_fn = NULL; mddev->queue->backing_dev_info.congested_fn = NULL; /* tell userspace to handle 'inactive' */ @@ -6669,8 +6668,6 @@ EXPORT_SYMBOL_GPL(md_allow_write); void md_unplug(mddev_t *mddev) { - if (mddev->queue) - blk_unplug(mddev->queue); if (mddev->plug) mddev->plug->unplug_fn(mddev->plug); } @@ -6853,7 +6850,6 @@ void md_do_sync(mddev_t *mddev) >= mddev->resync_max - mddev->curr_resync_completed )) { /* time to update curr_resync_completed */ - md_unplug(mddev); wait_event(mddev->recovery_wait, atomic_read(&mddev->recovery_active) == 0); mddev->curr_resync_completed = j; @@ -6929,7 +6925,6 @@ void md_do_sync(mddev_t *mddev) * about not overloading the IO subsystem. (things like an * e2fsck being done on the RAID array should execute fast) */ - md_unplug(mddev); cond_resched(); currspeed = ((unsigned long)(io_sectors-mddev->resync_mark_cnt))/2 @@ -6948,8 +6943,6 @@ void md_do_sync(mddev_t *mddev) * this also signals 'finished resyncing' to md_stop */ out: - md_unplug(mddev); - wait_event(mddev->recovery_wait, !atomic_read(&mddev->recovery_active)); /* tell personality that we are finished */ diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c index 6d7ddf32ef2..1cc8ed44e4a 100644 --- a/drivers/md/multipath.c +++ b/drivers/md/multipath.c @@ -106,36 +106,6 @@ static void multipath_end_request(struct bio *bio, int error) rdev_dec_pending(rdev, conf->mddev); } -static void unplug_slaves(mddev_t *mddev) -{ - multipath_conf_t *conf = mddev->private; - int i; - - rcu_read_lock(); - for (i=0; iraid_disks; i++) { - mdk_rdev_t *rdev = rcu_dereference(conf->multipaths[i].rdev); - if (rdev && !test_bit(Faulty, &rdev->flags) - && atomic_read(&rdev->nr_pending)) { - struct request_queue *r_queue = bdev_get_queue(rdev->bdev); - - atomic_inc(&rdev->nr_pending); - rcu_read_unlock(); - - blk_unplug(r_queue); - - rdev_dec_pending(rdev, mddev); - rcu_read_lock(); - } - } - rcu_read_unlock(); -} - -static void multipath_unplug(struct request_queue *q) -{ - unplug_slaves(q->queuedata); -} - - static int multipath_make_request(mddev_t *mddev, struct bio * bio) { multipath_conf_t *conf = mddev->private; @@ -518,7 +488,6 @@ static int multipath_run (mddev_t *mddev) */ md_set_array_sectors(mddev, multipath_size(mddev, 0, 0)); - mddev->queue->unplug_fn = multipath_unplug; mddev->queue->backing_dev_info.congested_fn = multipath_congested; mddev->queue->backing_dev_info.congested_data = mddev; md_integrity_register(mddev); diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index 637a96855ed..6338c0fe620 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -25,21 +25,6 @@ #include "raid0.h" #include "raid5.h" -static void raid0_unplug(struct request_queue *q) -{ - mddev_t *mddev = q->queuedata; - raid0_conf_t *conf = mddev->private; - mdk_rdev_t **devlist = conf->devlist; - int raid_disks = conf->strip_zone[0].nb_dev; - int i; - - for (i=0; i < raid_disks; i++) { - struct request_queue *r_queue = bdev_get_queue(devlist[i]->bdev); - - blk_unplug(r_queue); - } -} - static int raid0_congested(void *data, int bits) { mddev_t *mddev = data; @@ -272,7 +257,6 @@ static int create_strip_zones(mddev_t *mddev, raid0_conf_t **private_conf) mdname(mddev), (unsigned long long)smallest->sectors); } - mddev->queue->unplug_fn = raid0_unplug; mddev->queue->backing_dev_info.congested_fn = raid0_congested; mddev->queue->backing_dev_info.congested_data = mddev; diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index a23ffa397ba..b67d822d57a 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -52,23 +52,16 @@ #define NR_RAID1_BIOS 256 -static void unplug_slaves(mddev_t *mddev); - static void allow_barrier(conf_t *conf); static void lower_barrier(conf_t *conf); static void * r1bio_pool_alloc(gfp_t gfp_flags, void *data) { struct pool_info *pi = data; - r1bio_t *r1_bio; int size = offsetof(r1bio_t, bios[pi->raid_disks]); /* allocate a r1bio with room for raid_disks entries in the bios array */ - r1_bio = kzalloc(size, gfp_flags); - if (!r1_bio && pi->mddev) - unplug_slaves(pi->mddev); - - return r1_bio; + return kzalloc(size, gfp_flags); } static void r1bio_pool_free(void *r1_bio, void *data) @@ -91,10 +84,8 @@ static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data) int i, j; r1_bio = r1bio_pool_alloc(gfp_flags, pi); - if (!r1_bio) { - unplug_slaves(pi->mddev); + if (!r1_bio) return NULL; - } /* * Allocate bios : 1 for reading, n-1 for writing @@ -520,37 +511,6 @@ static int read_balance(conf_t *conf, r1bio_t *r1_bio) return new_disk; } -static void unplug_slaves(mddev_t *mddev) -{ - conf_t *conf = mddev->private; - int i; - - rcu_read_lock(); - for (i=0; iraid_disks; i++) { - mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev); - if (rdev && !test_bit(Faulty, &rdev->flags) && atomic_read(&rdev->nr_pending)) { - struct request_queue *r_queue = bdev_get_queue(rdev->bdev); - - atomic_inc(&rdev->nr_pending); - rcu_read_unlock(); - - blk_unplug(r_queue); - - rdev_dec_pending(rdev, mddev); - rcu_read_lock(); - } - } - rcu_read_unlock(); -} - -static void raid1_unplug(struct request_queue *q) -{ - mddev_t *mddev = q->queuedata; - - unplug_slaves(mddev); - md_wakeup_thread(mddev->thread); -} - static int raid1_congested(void *data, int bits) { mddev_t *mddev = data; @@ -580,20 +540,16 @@ static int raid1_congested(void *data, int bits) } -static int flush_pending_writes(conf_t *conf) +static void flush_pending_writes(conf_t *conf) { /* Any writes that have been queued but are awaiting * bitmap updates get flushed here. - * We return 1 if any requests were actually submitted. */ - int rv = 0; - spin_lock_irq(&conf->device_lock); if (conf->pending_bio_list.head) { struct bio *bio; bio = bio_list_get(&conf->pending_bio_list); - blk_remove_plug(conf->mddev->queue); spin_unlock_irq(&conf->device_lock); /* flush any pending bitmap writes to * disk before proceeding w/ I/O */ @@ -605,10 +561,14 @@ static int flush_pending_writes(conf_t *conf) generic_make_request(bio); bio = next; } - rv = 1; } else spin_unlock_irq(&conf->device_lock); - return rv; +} + +static void md_kick_device(mddev_t *mddev) +{ + blk_flush_plug(current); + md_wakeup_thread(mddev->thread); } /* Barriers.... @@ -640,8 +600,7 @@ static void raise_barrier(conf_t *conf) /* Wait until no block IO is waiting */ wait_event_lock_irq(conf->wait_barrier, !conf->nr_waiting, - conf->resync_lock, - raid1_unplug(conf->mddev->queue)); + conf->resync_lock, md_kick_device(conf->mddev)); /* block any new IO from starting */ conf->barrier++; @@ -649,8 +608,7 @@ static void raise_barrier(conf_t *conf) /* Now wait for all pending IO to complete */ wait_event_lock_irq(conf->wait_barrier, !conf->nr_pending && conf->barrier < RESYNC_DEPTH, - conf->resync_lock, - raid1_unplug(conf->mddev->queue)); + conf->resync_lock, md_kick_device(conf->mddev)); spin_unlock_irq(&conf->resync_lock); } @@ -672,7 +630,7 @@ static void wait_barrier(conf_t *conf) conf->nr_waiting++; wait_event_lock_irq(conf->wait_barrier, !conf->barrier, conf->resync_lock, - raid1_unplug(conf->mddev->queue)); + md_kick_device(conf->mddev)); conf->nr_waiting--; } conf->nr_pending++; @@ -709,7 +667,7 @@ static void freeze_array(conf_t *conf) conf->nr_pending == conf->nr_queued+1, conf->resync_lock, ({ flush_pending_writes(conf); - raid1_unplug(conf->mddev->queue); })); + md_kick_device(conf->mddev); })); spin_unlock_irq(&conf->resync_lock); } static void unfreeze_array(conf_t *conf) @@ -959,7 +917,6 @@ static int make_request(mddev_t *mddev, struct bio * bio) atomic_inc(&r1_bio->remaining); spin_lock_irqsave(&conf->device_lock, flags); bio_list_add(&conf->pending_bio_list, mbio); - blk_plug_device(mddev->queue); spin_unlock_irqrestore(&conf->device_lock, flags); } r1_bio_write_done(r1_bio, bio->bi_vcnt, behind_pages, behind_pages != NULL); @@ -968,7 +925,7 @@ static int make_request(mddev_t *mddev, struct bio * bio) /* In case raid1d snuck in to freeze_array */ wake_up(&conf->wait_barrier); - if (do_sync) + if (do_sync || !bitmap) md_wakeup_thread(mddev->thread); return 0; @@ -1558,7 +1515,6 @@ static void raid1d(mddev_t *mddev) unsigned long flags; conf_t *conf = mddev->private; struct list_head *head = &conf->retry_list; - int unplug=0; mdk_rdev_t *rdev; md_check_recovery(mddev); @@ -1566,7 +1522,7 @@ static void raid1d(mddev_t *mddev) for (;;) { char b[BDEVNAME_SIZE]; - unplug += flush_pending_writes(conf); + flush_pending_writes(conf); spin_lock_irqsave(&conf->device_lock, flags); if (list_empty(head)) { @@ -1580,10 +1536,9 @@ static void raid1d(mddev_t *mddev) mddev = r1_bio->mddev; conf = mddev->private; - if (test_bit(R1BIO_IsSync, &r1_bio->state)) { + if (test_bit(R1BIO_IsSync, &r1_bio->state)) sync_request_write(mddev, r1_bio); - unplug = 1; - } else { + else { int disk; /* we got a read error. Maybe the drive is bad. Maybe just @@ -1633,14 +1588,11 @@ static void raid1d(mddev_t *mddev) bio->bi_end_io = raid1_end_read_request; bio->bi_rw = READ | do_sync; bio->bi_private = r1_bio; - unplug = 1; generic_make_request(bio); } } cond_resched(); } - if (unplug) - unplug_slaves(mddev); } @@ -2064,7 +2016,6 @@ static int run(mddev_t *mddev) md_set_array_sectors(mddev, raid1_size(mddev, 0, 0)); - mddev->queue->unplug_fn = raid1_unplug; mddev->queue->backing_dev_info.congested_fn = raid1_congested; mddev->queue->backing_dev_info.congested_data = mddev; md_integrity_register(mddev); diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 3b607b28741..e79f1c5bf71 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -57,23 +57,16 @@ */ #define NR_RAID10_BIOS 256 -static void unplug_slaves(mddev_t *mddev); - static void allow_barrier(conf_t *conf); static void lower_barrier(conf_t *conf); static void * r10bio_pool_alloc(gfp_t gfp_flags, void *data) { conf_t *conf = data; - r10bio_t *r10_bio; int size = offsetof(struct r10bio_s, devs[conf->copies]); /* allocate a r10bio with room for raid_disks entries in the bios array */ - r10_bio = kzalloc(size, gfp_flags); - if (!r10_bio && conf->mddev) - unplug_slaves(conf->mddev); - - return r10_bio; + return kzalloc(size, gfp_flags); } static void r10bio_pool_free(void *r10_bio, void *data) @@ -106,10 +99,8 @@ static void * r10buf_pool_alloc(gfp_t gfp_flags, void *data) int nalloc; r10_bio = r10bio_pool_alloc(gfp_flags, conf); - if (!r10_bio) { - unplug_slaves(conf->mddev); + if (!r10_bio) return NULL; - } if (test_bit(MD_RECOVERY_SYNC, &conf->mddev->recovery)) nalloc = conf->copies; /* resync */ @@ -597,37 +588,6 @@ rb_out: return disk; } -static void unplug_slaves(mddev_t *mddev) -{ - conf_t *conf = mddev->private; - int i; - - rcu_read_lock(); - for (i=0; i < conf->raid_disks; i++) { - mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev); - if (rdev && !test_bit(Faulty, &rdev->flags) && atomic_read(&rdev->nr_pending)) { - struct request_queue *r_queue = bdev_get_queue(rdev->bdev); - - atomic_inc(&rdev->nr_pending); - rcu_read_unlock(); - - blk_unplug(r_queue); - - rdev_dec_pending(rdev, mddev); - rcu_read_lock(); - } - } - rcu_read_unlock(); -} - -static void raid10_unplug(struct request_queue *q) -{ - mddev_t *mddev = q->queuedata; - - unplug_slaves(q->queuedata); - md_wakeup_thread(mddev->thread); -} - static int raid10_congested(void *data, int bits) { mddev_t *mddev = data; @@ -649,20 +609,16 @@ static int raid10_congested(void *data, int bits) return ret; } -static int flush_pending_writes(conf_t *conf) +static void flush_pending_writes(conf_t *conf) { /* Any writes that have been queued but are awaiting * bitmap updates get flushed here. - * We return 1 if any requests were actually submitted. */ - int rv = 0; - spin_lock_irq(&conf->device_lock); if (conf->pending_bio_list.head) { struct bio *bio; bio = bio_list_get(&conf->pending_bio_list); - blk_remove_plug(conf->mddev->queue); spin_unlock_irq(&conf->device_lock); /* flush any pending bitmap writes to disk * before proceeding w/ I/O */ @@ -674,11 +630,16 @@ static int flush_pending_writes(conf_t *conf) generic_make_request(bio); bio = next; } - rv = 1; } else spin_unlock_irq(&conf->device_lock); - return rv; } + +static void md_kick_device(mddev_t *mddev) +{ + blk_flush_plug(current); + md_wakeup_thread(mddev->thread); +} + /* Barriers.... * Sometimes we need to suspend IO while we do something else, * either some resync/recovery, or reconfigure the array. @@ -708,8 +669,7 @@ static void raise_barrier(conf_t *conf, int force) /* Wait until no block IO is waiting (unless 'force') */ wait_event_lock_irq(conf->wait_barrier, force || !conf->nr_waiting, - conf->resync_lock, - raid10_unplug(conf->mddev->queue)); + conf->resync_lock, md_kick_device(conf->mddev)); /* block any new IO from starting */ conf->barrier++; @@ -717,8 +677,7 @@ static void raise_barrier(conf_t *conf, int force) /* No wait for all pending IO to complete */ wait_event_lock_irq(conf->wait_barrier, !conf->nr_pending && conf->barrier < RESYNC_DEPTH, - conf->resync_lock, - raid10_unplug(conf->mddev->queue)); + conf->resync_lock, md_kick_device(conf->mddev)); spin_unlock_irq(&conf->resync_lock); } @@ -739,7 +698,7 @@ static void wait_barrier(conf_t *conf) conf->nr_waiting++; wait_event_lock_irq(conf->wait_barrier, !conf->barrier, conf->resync_lock, - raid10_unplug(conf->mddev->queue)); + md_kick_device(conf->mddev)); conf->nr_waiting--; } conf->nr_pending++; @@ -776,7 +735,7 @@ static void freeze_array(conf_t *conf) conf->nr_pending == conf->nr_queued+1, conf->resync_lock, ({ flush_pending_writes(conf); - raid10_unplug(conf->mddev->queue); })); + md_kick_device(conf->mddev); })); spin_unlock_irq(&conf->resync_lock); } @@ -971,7 +930,6 @@ static int make_request(mddev_t *mddev, struct bio * bio) atomic_inc(&r10_bio->remaining); spin_lock_irqsave(&conf->device_lock, flags); bio_list_add(&conf->pending_bio_list, mbio); - blk_plug_device(mddev->queue); spin_unlock_irqrestore(&conf->device_lock, flags); } @@ -988,7 +946,7 @@ static int make_request(mddev_t *mddev, struct bio * bio) /* In case raid10d snuck in to freeze_array */ wake_up(&conf->wait_barrier); - if (do_sync) + if (do_sync || !mddev->bitmap) md_wakeup_thread(mddev->thread); return 0; @@ -1681,7 +1639,6 @@ static void raid10d(mddev_t *mddev) unsigned long flags; conf_t *conf = mddev->private; struct list_head *head = &conf->retry_list; - int unplug=0; mdk_rdev_t *rdev; md_check_recovery(mddev); @@ -1689,7 +1646,7 @@ static void raid10d(mddev_t *mddev) for (;;) { char b[BDEVNAME_SIZE]; - unplug += flush_pending_writes(conf); + flush_pending_writes(conf); spin_lock_irqsave(&conf->device_lock, flags); if (list_empty(head)) { @@ -1703,13 +1660,11 @@ static void raid10d(mddev_t *mddev) mddev = r10_bio->mddev; conf = mddev->private; - if (test_bit(R10BIO_IsSync, &r10_bio->state)) { + if (test_bit(R10BIO_IsSync, &r10_bio->state)) sync_request_write(mddev, r10_bio); - unplug = 1; - } else if (test_bit(R10BIO_IsRecover, &r10_bio->state)) { + else if (test_bit(R10BIO_IsRecover, &r10_bio->state)) recovery_request_write(mddev, r10_bio); - unplug = 1; - } else { + else { int mirror; /* we got a read error. Maybe the drive is bad. Maybe just * the block and we can fix it. @@ -1756,14 +1711,11 @@ static void raid10d(mddev_t *mddev) bio->bi_rw = READ | do_sync; bio->bi_private = r10_bio; bio->bi_end_io = raid10_end_read_request; - unplug = 1; generic_make_request(bio); } } cond_resched(); } - if (unplug) - unplug_slaves(mddev); } @@ -2376,7 +2328,6 @@ static int run(mddev_t *mddev) md_set_array_sectors(mddev, size); mddev->resync_max_sectors = size; - mddev->queue->unplug_fn = raid10_unplug; mddev->queue->backing_dev_info.congested_fn = raid10_congested; mddev->queue->backing_dev_info.congested_data = mddev; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 70281282419..e867ee42b15 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -433,8 +433,6 @@ static int has_failed(raid5_conf_t *conf) return 0; } -static void unplug_slaves(mddev_t *mddev); - static struct stripe_head * get_active_stripe(raid5_conf_t *conf, sector_t sector, int previous, int noblock, int noquiesce) @@ -463,8 +461,7 @@ get_active_stripe(raid5_conf_t *conf, sector_t sector, < (conf->max_nr_stripes *3/4) || !conf->inactive_blocked), conf->device_lock, - md_raid5_unplug_device(conf) - ); + md_raid5_kick_device(conf)); conf->inactive_blocked = 0; } else init_stripe(sh, sector, previous); @@ -1473,8 +1470,7 @@ static int resize_stripes(raid5_conf_t *conf, int newsize) wait_event_lock_irq(conf->wait_for_stripe, !list_empty(&conf->inactive_list), conf->device_lock, - unplug_slaves(conf->mddev) - ); + blk_flush_plug(current)); osh = get_free_stripe(conf); spin_unlock_irq(&conf->device_lock); atomic_set(&nsh->count, 1); @@ -3645,58 +3641,19 @@ static void activate_bit_delay(raid5_conf_t *conf) } } -static void unplug_slaves(mddev_t *mddev) +void md_raid5_kick_device(raid5_conf_t *conf) { - raid5_conf_t *conf = mddev->private; - int i; - int devs = max(conf->raid_disks, conf->previous_raid_disks); - - rcu_read_lock(); - for (i = 0; i < devs; i++) { - mdk_rdev_t *rdev = rcu_dereference(conf->disks[i].rdev); - if (rdev && !test_bit(Faulty, &rdev->flags) && atomic_read(&rdev->nr_pending)) { - struct request_queue *r_queue = bdev_get_queue(rdev->bdev); - - atomic_inc(&rdev->nr_pending); - rcu_read_unlock(); - - blk_unplug(r_queue); - - rdev_dec_pending(rdev, mddev); - rcu_read_lock(); - } - } - rcu_read_unlock(); -} - -void md_raid5_unplug_device(raid5_conf_t *conf) -{ - unsigned long flags; - - spin_lock_irqsave(&conf->device_lock, flags); - - if (plugger_remove_plug(&conf->plug)) { - conf->seq_flush++; - raid5_activate_delayed(conf); - } + blk_flush_plug(current); + raid5_activate_delayed(conf); md_wakeup_thread(conf->mddev->thread); - - spin_unlock_irqrestore(&conf->device_lock, flags); - - unplug_slaves(conf->mddev); } -EXPORT_SYMBOL_GPL(md_raid5_unplug_device); +EXPORT_SYMBOL_GPL(md_raid5_kick_device); static void raid5_unplug(struct plug_handle *plug) { raid5_conf_t *conf = container_of(plug, raid5_conf_t, plug); - md_raid5_unplug_device(conf); -} -static void raid5_unplug_queue(struct request_queue *q) -{ - mddev_t *mddev = q->queuedata; - md_raid5_unplug_device(mddev->private); + md_raid5_kick_device(conf); } int md_raid5_congested(mddev_t *mddev, int bits) @@ -4100,7 +4057,7 @@ static int make_request(mddev_t *mddev, struct bio * bi) * add failed due to overlap. Flush everything * and wait a while */ - md_raid5_unplug_device(conf); + md_raid5_kick_device(conf); release_stripe(sh); schedule(); goto retry; @@ -4365,7 +4322,6 @@ static inline sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *ski if (sector_nr >= max_sector) { /* just being told to finish up .. nothing much to do */ - unplug_slaves(mddev); if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery)) { end_reshape(conf); @@ -4569,7 +4525,6 @@ static void raid5d(mddev_t *mddev) spin_unlock_irq(&conf->device_lock); async_tx_issue_pending_all(); - unplug_slaves(mddev); pr_debug("--- raid5d inactive\n"); } @@ -5205,7 +5160,6 @@ static int run(mddev_t *mddev) mddev->queue->backing_dev_info.congested_data = mddev; mddev->queue->backing_dev_info.congested_fn = raid5_congested; mddev->queue->queue_lock = &conf->device_lock; - mddev->queue->unplug_fn = raid5_unplug_queue; chunk_size = mddev->chunk_sectors << 9; blk_queue_io_min(mddev->queue, chunk_size); diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h index 2ace0582b40..8d563a4f022 100644 --- a/drivers/md/raid5.h +++ b/drivers/md/raid5.h @@ -503,6 +503,6 @@ static inline int algorithm_is_DDF(int layout) } extern int md_raid5_congested(mddev_t *mddev, int bits); -extern void md_raid5_unplug_device(raid5_conf_t *conf); +extern void md_raid5_kick_device(raid5_conf_t *conf); extern int raid5_set_cache_size(mddev_t *mddev, int size); #endif diff --git a/drivers/message/i2o/i2o_block.c b/drivers/message/i2o/i2o_block.c index ae7cad18589..b29eb4eaa86 100644 --- a/drivers/message/i2o/i2o_block.c +++ b/drivers/message/i2o/i2o_block.c @@ -895,11 +895,7 @@ static void i2o_block_request_fn(struct request_queue *q) { struct request *req; - while (!blk_queue_plugged(q)) { - req = blk_peek_request(q); - if (!req) - break; - + while ((req = blk_peek_request(q)) != NULL) { if (req->cmd_type == REQ_TYPE_FS) { struct i2o_block_delayed_request *dreq; struct i2o_block_request *ireq = req->special; diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c index 4e42d030e09..2ae727568df 100644 --- a/drivers/mmc/card/queue.c +++ b/drivers/mmc/card/queue.c @@ -55,8 +55,7 @@ static int mmc_queue_thread(void *d) spin_lock_irq(q->queue_lock); set_current_state(TASK_INTERRUPTIBLE); - if (!blk_queue_plugged(q)) - req = blk_fetch_request(q); + req = blk_fetch_request(q); mq->req = req; spin_unlock_irq(q->queue_lock); diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index 794bfd96226..4d2df2f76ea 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -1917,7 +1917,7 @@ static void __dasd_process_request_queue(struct dasd_block *block) return; } /* Now we try to fetch requests from the request queue */ - while (!blk_queue_plugged(queue) && (req = blk_peek_request(queue))) { + while ((req = blk_peek_request(queue))) { if (basedev->features & DASD_FEATURE_READONLY && rq_data_dir(req) == WRITE) { DBF_DEV_EVENT(DBF_ERR, basedev, diff --git a/drivers/s390/char/tape_block.c b/drivers/s390/char/tape_block.c index 55d2d0f4eab..f061b2527b4 100644 --- a/drivers/s390/char/tape_block.c +++ b/drivers/s390/char/tape_block.c @@ -161,7 +161,6 @@ tapeblock_requeue(struct work_struct *work) { spin_lock_irq(&device->blk_data.request_queue_lock); while ( - !blk_queue_plugged(queue) && blk_peek_request(queue) && nr_queued < TAPEBLOCK_MIN_REQUEUE ) { diff --git a/drivers/scsi/scsi_transport_fc.c b/drivers/scsi/scsi_transport_fc.c index 998c01be323..2cefabd5bdb 100644 --- a/drivers/scsi/scsi_transport_fc.c +++ b/drivers/scsi/scsi_transport_fc.c @@ -3913,7 +3913,7 @@ fc_bsg_request_handler(struct request_queue *q, struct Scsi_Host *shost, if (!get_device(dev)) return; - while (!blk_queue_plugged(q)) { + while (1) { if (rport && (rport->port_state == FC_PORTSTATE_BLOCKED) && !(rport->flags & FC_RPORT_FAST_FAIL_TIMEDOUT)) break; diff --git a/drivers/scsi/scsi_transport_sas.c b/drivers/scsi/scsi_transport_sas.c index 927e99cb722..c6fcf76cade 100644 --- a/drivers/scsi/scsi_transport_sas.c +++ b/drivers/scsi/scsi_transport_sas.c @@ -173,11 +173,7 @@ static void sas_smp_request(struct request_queue *q, struct Scsi_Host *shost, int ret; int (*handler)(struct Scsi_Host *, struct sas_rphy *, struct request *); - while (!blk_queue_plugged(q)) { - req = blk_fetch_request(q); - if (!req) - break; - + while ((req = blk_fetch_request(q)) != NULL) { spin_unlock_irq(q->queue_lock); handler = to_sas_internal(shost->transportt)->f->smp_handler; diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c index 67f0c09983c..c1b539d7b0d 100644 --- a/drivers/target/target_core_iblock.c +++ b/drivers/target/target_core_iblock.c @@ -392,9 +392,8 @@ static int iblock_do_task(struct se_task *task) { struct se_device *dev = task->task_se_cmd->se_dev; struct iblock_req *req = IBLOCK_REQ(task); - struct iblock_dev *ibd = (struct iblock_dev *)req->ib_dev; - struct request_queue *q = bdev_get_queue(ibd->ibd_bd); struct bio *bio = req->ib_bio, *nbio = NULL; + struct blk_plug plug; int rw; if (task->task_data_direction == DMA_TO_DEVICE) { @@ -412,6 +411,7 @@ static int iblock_do_task(struct se_task *task) rw = READ; } + blk_start_plug(&plug); while (bio) { nbio = bio->bi_next; bio->bi_next = NULL; @@ -421,9 +421,8 @@ static int iblock_do_task(struct se_task *task) submit_bio(rw, bio); bio = nbio; } + blk_finish_plug(&plug); - if (q->unplug_fn) - q->unplug_fn(q); return PYX_TRANSPORT_SENT_TO_TRANSPORT; } diff --git a/fs/adfs/inode.c b/fs/adfs/inode.c index 65794b8fe79..1cc84b27613 100644 --- a/fs/adfs/inode.c +++ b/fs/adfs/inode.c @@ -73,7 +73,6 @@ static sector_t _adfs_bmap(struct address_space *mapping, sector_t block) static const struct address_space_operations adfs_aops = { .readpage = adfs_readpage, .writepage = adfs_writepage, - .sync_page = block_sync_page, .write_begin = adfs_write_begin, .write_end = generic_write_end, .bmap = _adfs_bmap diff --git a/fs/affs/file.c b/fs/affs/file.c index 0a90dcd46de..acf321b70fc 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -429,7 +429,6 @@ static sector_t _affs_bmap(struct address_space *mapping, sector_t block) const struct address_space_operations affs_aops = { .readpage = affs_readpage, .writepage = affs_writepage, - .sync_page = block_sync_page, .write_begin = affs_write_begin, .write_end = generic_write_end, .bmap = _affs_bmap @@ -786,7 +785,6 @@ out: const struct address_space_operations affs_aops_ofs = { .readpage = affs_readpage_ofs, //.writepage = affs_writepage_ofs, - //.sync_page = affs_sync_page_ofs, .write_begin = affs_write_begin_ofs, .write_end = affs_write_end_ofs }; diff --git a/fs/aio.c b/fs/aio.c index fc557a3be0a..c5ea494ea9e 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -1550,9 +1550,11 @@ static void aio_batch_free(struct hlist_head *batch_hash) struct hlist_node *pos, *n; int i; + /* + * TODO: kill this + */ for (i = 0; i < AIO_BATCH_HASH_SIZE; i++) { hlist_for_each_entry_safe(abe, pos, n, &batch_hash[i], list) { - blk_run_address_space(abe->mapping); iput(abe->mapping->host); hlist_del(&abe->list); mempool_free(abe, abe_pool); diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c index b1d0c794747..06457ed8f3e 100644 --- a/fs/befs/linuxvfs.c +++ b/fs/befs/linuxvfs.c @@ -75,7 +75,6 @@ static const struct inode_operations befs_dir_inode_operations = { static const struct address_space_operations befs_aops = { .readpage = befs_readpage, - .sync_page = block_sync_page, .bmap = befs_bmap, }; diff --git a/fs/bfs/file.c b/fs/bfs/file.c index eb67edd0f8e..f20e8a71062 100644 --- a/fs/bfs/file.c +++ b/fs/bfs/file.c @@ -186,7 +186,6 @@ static sector_t bfs_bmap(struct address_space *mapping, sector_t block) const struct address_space_operations bfs_aops = { .readpage = bfs_readpage, .writepage = bfs_writepage, - .sync_page = block_sync_page, .write_begin = bfs_write_begin, .write_end = generic_write_end, .bmap = bfs_bmap, diff --git a/fs/block_dev.c b/fs/block_dev.c index 4fb8a343153..fffc2c67239 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1520,7 +1520,6 @@ static int blkdev_releasepage(struct page *page, gfp_t wait) static const struct address_space_operations def_blk_aops = { .readpage = blkdev_readpage, .writepage = blkdev_writepage, - .sync_page = block_sync_page, .write_begin = blkdev_write_begin, .write_end = blkdev_write_end, .writepages = generic_writepages, diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index e1aa8d607bc..ada1f6bd0a5 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -847,7 +847,6 @@ static const struct address_space_operations btree_aops = { .writepages = btree_writepages, .releasepage = btree_releasepage, .invalidatepage = btree_invalidatepage, - .sync_page = block_sync_page, #ifdef CONFIG_MIGRATION .migratepage = btree_migratepage, #endif @@ -1330,82 +1329,6 @@ static int btrfs_congested_fn(void *congested_data, int bdi_bits) return ret; } -/* - * this unplugs every device on the box, and it is only used when page - * is null - */ -static void __unplug_io_fn(struct backing_dev_info *bdi, struct page *page) -{ - struct btrfs_device *device; - struct btrfs_fs_info *info; - - info = (struct btrfs_fs_info *)bdi->unplug_io_data; - list_for_each_entry(device, &info->fs_devices->devices, dev_list) { - if (!device->bdev) - continue; - - bdi = blk_get_backing_dev_info(device->bdev); - if (bdi->unplug_io_fn) - bdi->unplug_io_fn(bdi, page); - } -} - -static void btrfs_unplug_io_fn(struct backing_dev_info *bdi, struct page *page) -{ - struct inode *inode; - struct extent_map_tree *em_tree; - struct extent_map *em; - struct address_space *mapping; - u64 offset; - - /* the generic O_DIRECT read code does this */ - if (1 || !page) { - __unplug_io_fn(bdi, page); - return; - } - - /* - * page->mapping may change at any time. Get a consistent copy - * and use that for everything below - */ - smp_mb(); - mapping = page->mapping; - if (!mapping) - return; - - inode = mapping->host; - - /* - * don't do the expensive searching for a small number of - * devices - */ - if (BTRFS_I(inode)->root->fs_info->fs_devices->open_devices <= 2) { - __unplug_io_fn(bdi, page); - return; - } - - offset = page_offset(page); - - em_tree = &BTRFS_I(inode)->extent_tree; - read_lock(&em_tree->lock); - em = lookup_extent_mapping(em_tree, offset, PAGE_CACHE_SIZE); - read_unlock(&em_tree->lock); - if (!em) { - __unplug_io_fn(bdi, page); - return; - } - - if (em->block_start >= EXTENT_MAP_LAST_BYTE) { - free_extent_map(em); - __unplug_io_fn(bdi, page); - return; - } - offset = offset - em->start; - btrfs_unplug_page(&BTRFS_I(inode)->root->fs_info->mapping_tree, - em->block_start + offset, page); - free_extent_map(em); -} - /* * If this fails, caller must call bdi_destroy() to get rid of the * bdi again. @@ -1420,8 +1343,6 @@ static int setup_bdi(struct btrfs_fs_info *info, struct backing_dev_info *bdi) return err; bdi->ra_pages = default_backing_dev_info.ra_pages; - bdi->unplug_io_fn = btrfs_unplug_io_fn; - bdi->unplug_io_data = info; bdi->congested_fn = btrfs_congested_fn; bdi->congested_data = info; return 0; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index fb9bd7832b6..462e08e724b 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -7218,7 +7218,6 @@ static const struct address_space_operations btrfs_aops = { .writepage = btrfs_writepage, .writepages = btrfs_writepages, .readpages = btrfs_readpages, - .sync_page = block_sync_page, .direct_IO = btrfs_direct_IO, .invalidatepage = btrfs_invalidatepage, .releasepage = btrfs_releasepage, diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index af7dbca1527..6e0e82a1b18 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -162,7 +162,6 @@ static noinline int run_scheduled_bios(struct btrfs_device *device) struct bio *cur; int again = 0; unsigned long num_run; - unsigned long num_sync_run; unsigned long batch_run = 0; unsigned long limit; unsigned long last_waited = 0; @@ -173,11 +172,6 @@ static noinline int run_scheduled_bios(struct btrfs_device *device) limit = btrfs_async_submit_limit(fs_info); limit = limit * 2 / 3; - /* we want to make sure that every time we switch from the sync - * list to the normal list, we unplug - */ - num_sync_run = 0; - loop: spin_lock(&device->io_lock); @@ -223,15 +217,6 @@ loop_lock: spin_unlock(&device->io_lock); - /* - * if we're doing the regular priority list, make sure we unplug - * for any high prio bios we've sent down - */ - if (pending_bios == &device->pending_bios && num_sync_run > 0) { - num_sync_run = 0; - blk_run_backing_dev(bdi, NULL); - } - while (pending) { rmb(); @@ -259,19 +244,11 @@ loop_lock: BUG_ON(atomic_read(&cur->bi_cnt) == 0); - if (cur->bi_rw & REQ_SYNC) - num_sync_run++; - submit_bio(cur->bi_rw, cur); num_run++; batch_run++; - if (need_resched()) { - if (num_sync_run) { - blk_run_backing_dev(bdi, NULL); - num_sync_run = 0; - } + if (need_resched()) cond_resched(); - } /* * we made progress, there is more work to do and the bdi @@ -304,13 +281,8 @@ loop_lock: * against it before looping */ last_waited = ioc->last_waited; - if (need_resched()) { - if (num_sync_run) { - blk_run_backing_dev(bdi, NULL); - num_sync_run = 0; - } + if (need_resched()) cond_resched(); - } continue; } spin_lock(&device->io_lock); @@ -323,22 +295,6 @@ loop_lock: } } - if (num_sync_run) { - num_sync_run = 0; - blk_run_backing_dev(bdi, NULL); - } - /* - * IO has already been through a long path to get here. Checksumming, - * async helper threads, perhaps compression. We've done a pretty - * good job of collecting a batch of IO and should just unplug - * the device right away. - * - * This will help anyone who is waiting on the IO, they might have - * already unplugged, but managed to do so before the bio they - * cared about found its way down here. - */ - blk_run_backing_dev(bdi, NULL); - cond_resched(); if (again) goto loop; @@ -2948,7 +2904,7 @@ static int find_live_mirror(struct map_lookup *map, int first, int num, static int __btrfs_map_block(struct btrfs_mapping_tree *map_tree, int rw, u64 logical, u64 *length, struct btrfs_multi_bio **multi_ret, - int mirror_num, struct page *unplug_page) + int mirror_num) { struct extent_map *em; struct map_lookup *map; @@ -2980,11 +2936,6 @@ again: em = lookup_extent_mapping(em_tree, logical, *length); read_unlock(&em_tree->lock); - if (!em && unplug_page) { - kfree(multi); - return 0; - } - if (!em) { printk(KERN_CRIT "unable to find logical %llu len %llu\n", (unsigned long long)logical, @@ -3040,13 +2991,13 @@ again: *length = em->len - offset; } - if (!multi_ret && !unplug_page) + if (!multi_ret) goto out; num_stripes = 1; stripe_index = 0; if (map->type & BTRFS_BLOCK_GROUP_RAID1) { - if (unplug_page || (rw & REQ_WRITE)) + if (rw & REQ_WRITE) num_stripes = map->num_stripes; else if (mirror_num) stripe_index = mirror_num - 1; @@ -3068,7 +3019,7 @@ again: stripe_index = do_div(stripe_nr, factor); stripe_index *= map->sub_stripes; - if (unplug_page || (rw & REQ_WRITE)) + if (rw & REQ_WRITE) num_stripes = map->sub_stripes; else if (mirror_num) stripe_index += mirror_num - 1; @@ -3088,22 +3039,10 @@ again: BUG_ON(stripe_index >= map->num_stripes); for (i = 0; i < num_stripes; i++) { - if (unplug_page) { - struct btrfs_device *device; - struct backing_dev_info *bdi; - - device = map->stripes[stripe_index].dev; - if (device->bdev) { - bdi = blk_get_backing_dev_info(device->bdev); - if (bdi->unplug_io_fn) - bdi->unplug_io_fn(bdi, unplug_page); - } - } else { - multi->stripes[i].physical = - map->stripes[stripe_index].physical + - stripe_offset + stripe_nr * map->stripe_len; - multi->stripes[i].dev = map->stripes[stripe_index].dev; - } + multi->stripes[i].physical = + map->stripes[stripe_index].physical + + stripe_offset + stripe_nr * map->stripe_len; + multi->stripes[i].dev = map->stripes[stripe_index].dev; stripe_index++; } if (multi_ret) { @@ -3121,7 +3060,7 @@ int btrfs_map_block(struct btrfs_mapping_tree *map_tree, int rw, struct btrfs_multi_bio **multi_ret, int mirror_num) { return __btrfs_map_block(map_tree, rw, logical, length, multi_ret, - mirror_num, NULL); + mirror_num); } int btrfs_rmap_block(struct btrfs_mapping_tree *map_tree, @@ -3189,14 +3128,6 @@ int btrfs_rmap_block(struct btrfs_mapping_tree *map_tree, return 0; } -int btrfs_unplug_page(struct btrfs_mapping_tree *map_tree, - u64 logical, struct page *page) -{ - u64 length = PAGE_CACHE_SIZE; - return __btrfs_map_block(map_tree, READ, logical, &length, - NULL, 0, page); -} - static void end_bio_multi_stripe(struct bio *bio, int err) { struct btrfs_multi_bio *multi = bio->bi_private; diff --git a/fs/buffer.c b/fs/buffer.c index 2219a76e2ca..f903f2e5b4f 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -54,23 +54,15 @@ init_buffer(struct buffer_head *bh, bh_end_io_t *handler, void *private) } EXPORT_SYMBOL(init_buffer); -static int sync_buffer(void *word) +static int sleep_on_buffer(void *word) { - struct block_device *bd; - struct buffer_head *bh - = container_of(word, struct buffer_head, b_state); - - smp_mb(); - bd = bh->b_bdev; - if (bd) - blk_run_address_space(bd->bd_inode->i_mapping); io_schedule(); return 0; } void __lock_buffer(struct buffer_head *bh) { - wait_on_bit_lock(&bh->b_state, BH_Lock, sync_buffer, + wait_on_bit_lock(&bh->b_state, BH_Lock, sleep_on_buffer, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(__lock_buffer); @@ -90,7 +82,7 @@ EXPORT_SYMBOL(unlock_buffer); */ void __wait_on_buffer(struct buffer_head * bh) { - wait_on_bit(&bh->b_state, BH_Lock, sync_buffer, TASK_UNINTERRUPTIBLE); + wait_on_bit(&bh->b_state, BH_Lock, sleep_on_buffer, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(__wait_on_buffer); @@ -749,7 +741,7 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list) { struct buffer_head *bh; struct list_head tmp; - struct address_space *mapping, *prev_mapping = NULL; + struct address_space *mapping; int err = 0, err2; INIT_LIST_HEAD(&tmp); @@ -783,10 +775,6 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list) * wait_on_buffer() will do that for us * through sync_buffer(). */ - if (prev_mapping && prev_mapping != mapping) - blk_run_address_space(prev_mapping); - prev_mapping = mapping; - brelse(bh); spin_lock(lock); } @@ -3138,17 +3126,6 @@ out: } EXPORT_SYMBOL(try_to_free_buffers); -void block_sync_page(struct page *page) -{ - struct address_space *mapping; - - smp_mb(); - mapping = page_mapping(page); - if (mapping) - blk_run_backing_dev(mapping->backing_dev_info, page); -} -EXPORT_SYMBOL(block_sync_page); - /* * There are no bdflush tunables left. But distributions are * still running obsolete flush daemons, so we terminate them here. diff --git a/fs/cifs/file.c b/fs/cifs/file.c index e964b1cd5dd..c27d236738f 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -1569,34 +1569,6 @@ int cifs_fsync(struct file *file, int datasync) return rc; } -/* static void cifs_sync_page(struct page *page) -{ - struct address_space *mapping; - struct inode *inode; - unsigned long index = page->index; - unsigned int rpages = 0; - int rc = 0; - - cFYI(1, "sync page %p", page); - mapping = page->mapping; - if (!mapping) - return 0; - inode = mapping->host; - if (!inode) - return; */ - -/* fill in rpages then - result = cifs_pagein_inode(inode, index, rpages); */ /* BB finish */ - -/* cFYI(1, "rpages is %d for sync page of Index %ld", rpages, index); - -#if 0 - if (rc < 0) - return rc; - return 0; -#endif -} */ - /* * As file closes, flush all cached write data for this inode checking * for write behind errors. @@ -2510,7 +2482,6 @@ const struct address_space_operations cifs_addr_ops = { .set_page_dirty = __set_page_dirty_nobuffers, .releasepage = cifs_release_page, .invalidatepage = cifs_invalidate_page, - /* .sync_page = cifs_sync_page, */ /* .direct_IO = */ }; @@ -2528,6 +2499,5 @@ const struct address_space_operations cifs_addr_ops_smallbuf = { .set_page_dirty = __set_page_dirty_nobuffers, .releasepage = cifs_release_page, .invalidatepage = cifs_invalidate_page, - /* .sync_page = cifs_sync_page, */ /* .direct_IO = */ }; diff --git a/fs/direct-io.c b/fs/direct-io.c index b044705eedd..df709b3b860 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -1110,11 +1110,8 @@ direct_io_worker(int rw, struct kiocb *iocb, struct inode *inode, ((rw & READ) || (dio->result == dio->size))) ret = -EIOCBQUEUED; - if (ret != -EIOCBQUEUED) { - /* All IO is now issued, send it on its way */ - blk_run_address_space(inode->i_mapping); + if (ret != -EIOCBQUEUED) dio_await_completion(dio); - } /* * Sync will always be dropping the final ref and completing the diff --git a/fs/efs/inode.c b/fs/efs/inode.c index a8e7797b947..9c13412e6c9 100644 --- a/fs/efs/inode.c +++ b/fs/efs/inode.c @@ -23,7 +23,6 @@ static sector_t _efs_bmap(struct address_space *mapping, sector_t block) } static const struct address_space_operations efs_aops = { .readpage = efs_readpage, - .sync_page = block_sync_page, .bmap = _efs_bmap }; diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c index a7555238c41..82b94c8f5d2 100644 --- a/fs/exofs/inode.c +++ b/fs/exofs/inode.c @@ -795,7 +795,6 @@ const struct address_space_operations exofs_aops = { .direct_IO = NULL, /* TODO: Should be trivial to do */ /* With these NULL has special meaning or default is not exported */ - .sync_page = NULL, .get_xip_mem = NULL, .migratepage = NULL, .launder_page = NULL, diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 40ad210a504..c47f706878b 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -860,7 +860,6 @@ const struct address_space_operations ext2_aops = { .readpage = ext2_readpage, .readpages = ext2_readpages, .writepage = ext2_writepage, - .sync_page = block_sync_page, .write_begin = ext2_write_begin, .write_end = ext2_write_end, .bmap = ext2_bmap, @@ -880,7 +879,6 @@ const struct address_space_operations ext2_nobh_aops = { .readpage = ext2_readpage, .readpages = ext2_readpages, .writepage = ext2_nobh_writepage, - .sync_page = block_sync_page, .write_begin = ext2_nobh_write_begin, .write_end = nobh_write_end, .bmap = ext2_bmap, diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index ae94f6d949f..fe2541d250e 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -1894,7 +1894,6 @@ static const struct address_space_operations ext3_ordered_aops = { .readpage = ext3_readpage, .readpages = ext3_readpages, .writepage = ext3_ordered_writepage, - .sync_page = block_sync_page, .write_begin = ext3_write_begin, .write_end = ext3_ordered_write_end, .bmap = ext3_bmap, @@ -1910,7 +1909,6 @@ static const struct address_space_operations ext3_writeback_aops = { .readpage = ext3_readpage, .readpages = ext3_readpages, .writepage = ext3_writeback_writepage, - .sync_page = block_sync_page, .write_begin = ext3_write_begin, .write_end = ext3_writeback_write_end, .bmap = ext3_bmap, @@ -1926,7 +1924,6 @@ static const struct address_space_operations ext3_journalled_aops = { .readpage = ext3_readpage, .readpages = ext3_readpages, .writepage = ext3_journalled_writepage, - .sync_page = block_sync_page, .write_begin = ext3_write_begin, .write_end = ext3_journalled_write_end, .set_page_dirty = ext3_journalled_set_page_dirty, diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 9f7f9e49914..9297ad46c46 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3903,7 +3903,6 @@ static const struct address_space_operations ext4_ordered_aops = { .readpage = ext4_readpage, .readpages = ext4_readpages, .writepage = ext4_writepage, - .sync_page = block_sync_page, .write_begin = ext4_write_begin, .write_end = ext4_ordered_write_end, .bmap = ext4_bmap, @@ -3919,7 +3918,6 @@ static const struct address_space_operations ext4_writeback_aops = { .readpage = ext4_readpage, .readpages = ext4_readpages, .writepage = ext4_writepage, - .sync_page = block_sync_page, .write_begin = ext4_write_begin, .write_end = ext4_writeback_write_end, .bmap = ext4_bmap, @@ -3935,7 +3933,6 @@ static const struct address_space_operations ext4_journalled_aops = { .readpage = ext4_readpage, .readpages = ext4_readpages, .writepage = ext4_writepage, - .sync_page = block_sync_page, .write_begin = ext4_write_begin, .write_end = ext4_journalled_write_end, .set_page_dirty = ext4_journalled_set_page_dirty, @@ -3951,7 +3948,6 @@ static const struct address_space_operations ext4_da_aops = { .readpages = ext4_readpages, .writepage = ext4_writepage, .writepages = ext4_da_writepages, - .sync_page = block_sync_page, .write_begin = ext4_da_write_begin, .write_end = ext4_da_write_end, .bmap = ext4_bmap, diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 86753fe10bd..f4ff09fb79b 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -236,7 +236,6 @@ static const struct address_space_operations fat_aops = { .readpages = fat_readpages, .writepage = fat_writepage, .writepages = fat_writepages, - .sync_page = block_sync_page, .write_begin = fat_write_begin, .write_end = fat_write_end, .direct_IO = fat_direct_IO, diff --git a/fs/freevxfs/vxfs_subr.c b/fs/freevxfs/vxfs_subr.c index 1429f3ae1e8..5d318c44f85 100644 --- a/fs/freevxfs/vxfs_subr.c +++ b/fs/freevxfs/vxfs_subr.c @@ -44,7 +44,6 @@ static sector_t vxfs_bmap(struct address_space *, sector_t); const struct address_space_operations vxfs_aops = { .readpage = vxfs_readpage, .bmap = vxfs_bmap, - .sync_page = block_sync_page, }; inline void diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 9e3f68cc1bd..09e8d51eeb6 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -868,7 +868,6 @@ static int fuse_bdi_init(struct fuse_conn *fc, struct super_block *sb) fc->bdi.name = "fuse"; fc->bdi.ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE; - fc->bdi.unplug_io_fn = default_unplug_io_fn; /* fuse does it's own writeback accounting */ fc->bdi.capabilities = BDI_CAP_NO_ACCT_WB; diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 4f36f8832b9..2f87ad27efd 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -1116,7 +1116,6 @@ static const struct address_space_operations gfs2_writeback_aops = { .writepages = gfs2_writeback_writepages, .readpage = gfs2_readpage, .readpages = gfs2_readpages, - .sync_page = block_sync_page, .write_begin = gfs2_write_begin, .write_end = gfs2_write_end, .bmap = gfs2_bmap, @@ -1132,7 +1131,6 @@ static const struct address_space_operations gfs2_ordered_aops = { .writepage = gfs2_ordered_writepage, .readpage = gfs2_readpage, .readpages = gfs2_readpages, - .sync_page = block_sync_page, .write_begin = gfs2_write_begin, .write_end = gfs2_write_end, .set_page_dirty = gfs2_set_page_dirty, @@ -1150,7 +1148,6 @@ static const struct address_space_operations gfs2_jdata_aops = { .writepages = gfs2_jdata_writepages, .readpage = gfs2_readpage, .readpages = gfs2_readpages, - .sync_page = block_sync_page, .write_begin = gfs2_write_begin, .write_end = gfs2_write_end, .set_page_dirty = gfs2_set_page_dirty, diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index 939739c7b3f..a566331db4e 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -94,7 +94,6 @@ static int gfs2_aspace_writepage(struct page *page, struct writeback_control *wb const struct address_space_operations gfs2_meta_aops = { .writepage = gfs2_aspace_writepage, .releasepage = gfs2_releasepage, - .sync_page = block_sync_page, }; /** diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index dffb4e99664..fff16c968e6 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -150,7 +150,6 @@ static int hfs_writepages(struct address_space *mapping, const struct address_space_operations hfs_btree_aops = { .readpage = hfs_readpage, .writepage = hfs_writepage, - .sync_page = block_sync_page, .write_begin = hfs_write_begin, .write_end = generic_write_end, .bmap = hfs_bmap, @@ -160,7 +159,6 @@ const struct address_space_operations hfs_btree_aops = { const struct address_space_operations hfs_aops = { .readpage = hfs_readpage, .writepage = hfs_writepage, - .sync_page = block_sync_page, .write_begin = hfs_write_begin, .write_end = generic_write_end, .bmap = hfs_bmap, diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index a8df651747f..b248a6cfcad 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -146,7 +146,6 @@ static int hfsplus_writepages(struct address_space *mapping, const struct address_space_operations hfsplus_btree_aops = { .readpage = hfsplus_readpage, .writepage = hfsplus_writepage, - .sync_page = block_sync_page, .write_begin = hfsplus_write_begin, .write_end = generic_write_end, .bmap = hfsplus_bmap, @@ -156,7 +155,6 @@ const struct address_space_operations hfsplus_btree_aops = { const struct address_space_operations hfsplus_aops = { .readpage = hfsplus_readpage, .writepage = hfsplus_writepage, - .sync_page = block_sync_page, .write_begin = hfsplus_write_begin, .write_end = generic_write_end, .bmap = hfsplus_bmap, diff --git a/fs/hpfs/file.c b/fs/hpfs/file.c index c0340887c7e..9e84257b3ad 100644 --- a/fs/hpfs/file.c +++ b/fs/hpfs/file.c @@ -120,7 +120,6 @@ static sector_t _hpfs_bmap(struct address_space *mapping, sector_t block) const struct address_space_operations hpfs_aops = { .readpage = hpfs_readpage, .writepage = hpfs_writepage, - .sync_page = block_sync_page, .write_begin = hpfs_write_begin, .write_end = generic_write_end, .bmap = _hpfs_bmap diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index a0f3833c0db..3db5ba4568f 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -1158,7 +1158,6 @@ static sector_t _isofs_bmap(struct address_space *mapping, sector_t block) static const struct address_space_operations isofs_aops = { .readpage = isofs_readpage, - .sync_page = block_sync_page, .bmap = _isofs_bmap }; diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c index 9978803ceed..eddbb373209 100644 --- a/fs/jfs/inode.c +++ b/fs/jfs/inode.c @@ -352,7 +352,6 @@ const struct address_space_operations jfs_aops = { .readpages = jfs_readpages, .writepage = jfs_writepage, .writepages = jfs_writepages, - .sync_page = block_sync_page, .write_begin = jfs_write_begin, .write_end = nobh_write_end, .bmap = jfs_bmap, diff --git a/fs/jfs/jfs_metapage.c b/fs/jfs/jfs_metapage.c index 48b44bd8267..6740d34cd82 100644 --- a/fs/jfs/jfs_metapage.c +++ b/fs/jfs/jfs_metapage.c @@ -583,7 +583,6 @@ static void metapage_invalidatepage(struct page *page, unsigned long offset) const struct address_space_operations jfs_metapage_aops = { .readpage = metapage_readpage, .writepage = metapage_writepage, - .sync_page = block_sync_page, .releasepage = metapage_releasepage, .invalidatepage = metapage_invalidatepage, .set_page_dirty = __set_page_dirty_nobuffers, diff --git a/fs/logfs/dev_bdev.c b/fs/logfs/dev_bdev.c index 723bc5bca09..1adc8d455f0 100644 --- a/fs/logfs/dev_bdev.c +++ b/fs/logfs/dev_bdev.c @@ -39,7 +39,6 @@ static int sync_request(struct page *page, struct block_device *bdev, int rw) bio.bi_end_io = request_complete; submit_bio(rw, &bio); - generic_unplug_device(bdev_get_queue(bdev)); wait_for_completion(&complete); return test_bit(BIO_UPTODATE, &bio.bi_flags) ? 0 : -EIO; } @@ -168,7 +167,6 @@ static void bdev_writeseg(struct super_block *sb, u64 ofs, size_t len) } len = PAGE_ALIGN(len); __bdev_writeseg(sb, ofs, ofs >> PAGE_SHIFT, len >> PAGE_SHIFT); - generic_unplug_device(bdev_get_queue(logfs_super(sb)->s_bdev)); } diff --git a/fs/minix/inode.c b/fs/minix/inode.c index ae0b83f476a..adcdc0a4e18 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -399,7 +399,6 @@ static sector_t minix_bmap(struct address_space *mapping, sector_t block) static const struct address_space_operations minix_aops = { .readpage = minix_readpage, .writepage = minix_writepage, - .sync_page = block_sync_page, .write_begin = minix_write_begin, .write_end = generic_write_end, .bmap = minix_bmap diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c index 388e9e8f528..f4f1c08807e 100644 --- a/fs/nilfs2/btnode.c +++ b/fs/nilfs2/btnode.c @@ -40,14 +40,10 @@ void nilfs_btnode_cache_init_once(struct address_space *btnc) nilfs_mapping_init_once(btnc); } -static const struct address_space_operations def_btnode_aops = { - .sync_page = block_sync_page, -}; - void nilfs_btnode_cache_init(struct address_space *btnc, struct backing_dev_info *bdi) { - nilfs_mapping_init(btnc, bdi, &def_btnode_aops); + nilfs_mapping_init(btnc, bdi); } void nilfs_btnode_cache_clear(struct address_space *btnc) diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c index caf9a6a3fb5..1c2a3e23f8b 100644 --- a/fs/nilfs2/gcinode.c +++ b/fs/nilfs2/gcinode.c @@ -49,7 +49,6 @@ #include "ifile.h" static const struct address_space_operations def_gcinode_aops = { - .sync_page = block_sync_page, }; /* diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 2fd440d8d6b..c89d5d1ea7c 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -262,7 +262,6 @@ nilfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, const struct address_space_operations nilfs_aops = { .writepage = nilfs_writepage, .readpage = nilfs_readpage, - .sync_page = block_sync_page, .writepages = nilfs_writepages, .set_page_dirty = nilfs_set_page_dirty, .readpages = nilfs_readpages, diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c index 6a0e2a189f6..3fdb61d79c9 100644 --- a/fs/nilfs2/mdt.c +++ b/fs/nilfs2/mdt.c @@ -399,7 +399,6 @@ nilfs_mdt_write_page(struct page *page, struct writeback_control *wbc) static const struct address_space_operations def_mdt_aops = { .writepage = nilfs_mdt_write_page, - .sync_page = block_sync_page, }; static const struct inode_operations def_mdt_iops; @@ -438,10 +437,6 @@ void nilfs_mdt_set_entry_size(struct inode *inode, unsigned entry_size, mi->mi_first_entry_offset = DIV_ROUND_UP(header_size, entry_size); } -static const struct address_space_operations shadow_map_aops = { - .sync_page = block_sync_page, -}; - /** * nilfs_mdt_setup_shadow_map - setup shadow map and bind it to metadata file * @inode: inode of the metadata file @@ -455,9 +450,9 @@ int nilfs_mdt_setup_shadow_map(struct inode *inode, INIT_LIST_HEAD(&shadow->frozen_buffers); nilfs_mapping_init_once(&shadow->frozen_data); - nilfs_mapping_init(&shadow->frozen_data, bdi, &shadow_map_aops); + nilfs_mapping_init(&shadow->frozen_data, bdi); nilfs_mapping_init_once(&shadow->frozen_btnodes); - nilfs_mapping_init(&shadow->frozen_btnodes, bdi, &shadow_map_aops); + nilfs_mapping_init(&shadow->frozen_btnodes, bdi); mi->mi_shadow = shadow; return 0; } diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c index 0c432416cfe..3da37cc5de3 100644 --- a/fs/nilfs2/page.c +++ b/fs/nilfs2/page.c @@ -506,15 +506,14 @@ void nilfs_mapping_init_once(struct address_space *mapping) } void nilfs_mapping_init(struct address_space *mapping, - struct backing_dev_info *bdi, - const struct address_space_operations *aops) + struct backing_dev_info *bdi) { mapping->host = NULL; mapping->flags = 0; mapping_set_gfp_mask(mapping, GFP_NOFS); mapping->assoc_mapping = NULL; mapping->backing_dev_info = bdi; - mapping->a_ops = aops; + mapping->a_ops = NULL; } /* diff --git a/fs/nilfs2/page.h b/fs/nilfs2/page.h index 622df27cd89..ba4d6fd40b0 100644 --- a/fs/nilfs2/page.h +++ b/fs/nilfs2/page.h @@ -63,8 +63,7 @@ void nilfs_copy_back_pages(struct address_space *, struct address_space *); void nilfs_clear_dirty_pages(struct address_space *); void nilfs_mapping_init_once(struct address_space *mapping); void nilfs_mapping_init(struct address_space *mapping, - struct backing_dev_info *bdi, - const struct address_space_operations *aops); + struct backing_dev_info *bdi); unsigned nilfs_page_count_clean_buffers(struct page *, unsigned, unsigned); unsigned long nilfs_find_uncommitted_extent(struct inode *inode, sector_t start_blk, diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c index c3c2c7ac902..0b1e885b8cf 100644 --- a/fs/ntfs/aops.c +++ b/fs/ntfs/aops.c @@ -1543,8 +1543,6 @@ err_out: */ const struct address_space_operations ntfs_aops = { .readpage = ntfs_readpage, /* Fill page with data. */ - .sync_page = block_sync_page, /* Currently, just unplugs the - disk request queue. */ #ifdef NTFS_RW .writepage = ntfs_writepage, /* Write dirty page to disk. */ #endif /* NTFS_RW */ @@ -1560,8 +1558,6 @@ const struct address_space_operations ntfs_aops = { */ const struct address_space_operations ntfs_mst_aops = { .readpage = ntfs_readpage, /* Fill page with data. */ - .sync_page = block_sync_page, /* Currently, just unplugs the - disk request queue. */ #ifdef NTFS_RW .writepage = ntfs_writepage, /* Write dirty page to disk. */ .set_page_dirty = __set_page_dirty_nobuffers, /* Set the page dirty diff --git a/fs/ntfs/compress.c b/fs/ntfs/compress.c index 6551c7cbad9..ef9ed854255 100644 --- a/fs/ntfs/compress.c +++ b/fs/ntfs/compress.c @@ -698,8 +698,7 @@ lock_retry_remap: "uptodate! Unplugging the disk queue " "and rescheduling."); get_bh(tbh); - blk_run_address_space(mapping); - schedule(); + io_schedule(); put_bh(tbh); if (unlikely(!buffer_uptodate(tbh))) goto read_err; diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 1fbb0e20131..daea0359e97 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -2043,7 +2043,6 @@ const struct address_space_operations ocfs2_aops = { .write_begin = ocfs2_write_begin, .write_end = ocfs2_write_end, .bmap = ocfs2_bmap, - .sync_page = block_sync_page, .direct_IO = ocfs2_direct_IO, .invalidatepage = ocfs2_invalidatepage, .releasepage = ocfs2_releasepage, diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index b108e863d8f..1adab287bd2 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -367,11 +367,7 @@ static inline void o2hb_bio_wait_dec(struct o2hb_bio_wait_ctxt *wc, static void o2hb_wait_on_io(struct o2hb_region *reg, struct o2hb_bio_wait_ctxt *wc) { - struct address_space *mapping = reg->hr_bdev->bd_inode->i_mapping; - - blk_run_address_space(mapping); o2hb_bio_wait_dec(wc, 1); - wait_for_completion(&wc->wc_io_complete); } diff --git a/fs/omfs/file.c b/fs/omfs/file.c index 8a6d34fa668..d738a7e493d 100644 --- a/fs/omfs/file.c +++ b/fs/omfs/file.c @@ -372,7 +372,6 @@ const struct address_space_operations omfs_aops = { .readpages = omfs_readpages, .writepage = omfs_writepage, .writepages = omfs_writepages, - .sync_page = block_sync_page, .write_begin = omfs_write_begin, .write_end = generic_write_end, .bmap = omfs_bmap, diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c index e63b4171d58..2b0646613f5 100644 --- a/fs/qnx4/inode.c +++ b/fs/qnx4/inode.c @@ -335,7 +335,6 @@ static sector_t qnx4_bmap(struct address_space *mapping, sector_t block) static const struct address_space_operations qnx4_aops = { .readpage = qnx4_readpage, .writepage = qnx4_writepage, - .sync_page = block_sync_page, .write_begin = qnx4_write_begin, .write_end = generic_write_end, .bmap = qnx4_bmap diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index 0bae036831e..03674675f88 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -3212,7 +3212,6 @@ const struct address_space_operations reiserfs_address_space_operations = { .readpages = reiserfs_readpages, .releasepage = reiserfs_releasepage, .invalidatepage = reiserfs_invalidatepage, - .sync_page = block_sync_page, .write_begin = reiserfs_write_begin, .write_end = reiserfs_write_end, .bmap = reiserfs_aop_bmap, diff --git a/fs/sysv/itree.c b/fs/sysv/itree.c index 9ca66276315..fa8d43c92bb 100644 --- a/fs/sysv/itree.c +++ b/fs/sysv/itree.c @@ -488,7 +488,6 @@ static sector_t sysv_bmap(struct address_space *mapping, sector_t block) const struct address_space_operations sysv_aops = { .readpage = sysv_readpage, .writepage = sysv_writepage, - .sync_page = block_sync_page, .write_begin = sysv_write_begin, .write_end = generic_write_end, .bmap = sysv_bmap diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 6e11c2975dc..81368d4d4a2 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -1979,7 +1979,6 @@ static int ubifs_fill_super(struct super_block *sb, void *data, int silent) */ c->bdi.name = "ubifs", c->bdi.capabilities = BDI_CAP_MAP_COPY; - c->bdi.unplug_io_fn = default_unplug_io_fn; err = bdi_init(&c->bdi); if (err) goto out_close; diff --git a/fs/udf/file.c b/fs/udf/file.c index 89c78486cbb..94e4553491c 100644 --- a/fs/udf/file.c +++ b/fs/udf/file.c @@ -98,7 +98,6 @@ static int udf_adinicb_write_end(struct file *file, const struct address_space_operations udf_adinicb_aops = { .readpage = udf_adinicb_readpage, .writepage = udf_adinicb_writepage, - .sync_page = block_sync_page, .write_begin = simple_write_begin, .write_end = udf_adinicb_write_end, }; diff --git a/fs/udf/inode.c b/fs/udf/inode.c index c6a2e782b97..fa96fc0fe12 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -133,7 +133,6 @@ static sector_t udf_bmap(struct address_space *mapping, sector_t block) const struct address_space_operations udf_aops = { .readpage = udf_readpage, .writepage = udf_writepage, - .sync_page = block_sync_page, .write_begin = udf_write_begin, .write_end = generic_write_end, .bmap = udf_bmap, diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c index 2b251f2093a..83b28444eb1 100644 --- a/fs/ufs/inode.c +++ b/fs/ufs/inode.c @@ -588,7 +588,6 @@ static sector_t ufs_bmap(struct address_space *mapping, sector_t block) const struct address_space_operations ufs_aops = { .readpage = ufs_readpage, .writepage = ufs_writepage, - .sync_page = block_sync_page, .write_begin = ufs_write_begin, .write_end = generic_write_end, .bmap = ufs_bmap diff --git a/fs/ufs/truncate.c b/fs/ufs/truncate.c index a58f9155fc9..ff0e79276f2 100644 --- a/fs/ufs/truncate.c +++ b/fs/ufs/truncate.c @@ -481,7 +481,7 @@ int ufs_truncate(struct inode *inode, loff_t old_i_size) break; if (IS_SYNC(inode) && (inode->i_state & I_DIRTY)) ufs_sync_inode (inode); - blk_run_address_space(inode->i_mapping); + blk_flush_plug(current); yield(); } diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c index ec7bbb5645b..83c1c20d145 100644 --- a/fs/xfs/linux-2.6/xfs_aops.c +++ b/fs/xfs/linux-2.6/xfs_aops.c @@ -1495,7 +1495,6 @@ const struct address_space_operations xfs_address_space_operations = { .readpages = xfs_vm_readpages, .writepage = xfs_vm_writepage, .writepages = xfs_vm_writepages, - .sync_page = block_sync_page, .releasepage = xfs_vm_releasepage, .invalidatepage = xfs_vm_invalidatepage, .write_begin = xfs_vm_write_begin, diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c index ac1c7e8378d..4f8f53c4d42 100644 --- a/fs/xfs/linux-2.6/xfs_buf.c +++ b/fs/xfs/linux-2.6/xfs_buf.c @@ -991,7 +991,7 @@ xfs_buf_lock( if (atomic_read(&bp->b_pin_count) && (bp->b_flags & XBF_STALE)) xfs_log_force(bp->b_target->bt_mount, 0); if (atomic_read(&bp->b_io_remaining)) - blk_run_address_space(bp->b_target->bt_mapping); + blk_flush_plug(current); down(&bp->b_sema); XB_SET_OWNER(bp); @@ -1035,9 +1035,7 @@ xfs_buf_wait_unpin( set_current_state(TASK_UNINTERRUPTIBLE); if (atomic_read(&bp->b_pin_count) == 0) break; - if (atomic_read(&bp->b_io_remaining)) - blk_run_address_space(bp->b_target->bt_mapping); - schedule(); + io_schedule(); } remove_wait_queue(&bp->b_waiters, &wait); set_current_state(TASK_RUNNING); @@ -1443,7 +1441,7 @@ xfs_buf_iowait( trace_xfs_buf_iowait(bp, _RET_IP_); if (atomic_read(&bp->b_io_remaining)) - blk_run_address_space(bp->b_target->bt_mapping); + blk_flush_plug(current); wait_for_completion(&bp->b_iowait); trace_xfs_buf_iowait_done(bp, _RET_IP_); @@ -1667,7 +1665,6 @@ xfs_mapping_buftarg( struct inode *inode; struct address_space *mapping; static const struct address_space_operations mapping_aops = { - .sync_page = block_sync_page, .migratepage = fail_migrate_page, }; @@ -1948,7 +1945,7 @@ xfsbufd( count++; } if (count) - blk_run_address_space(target->bt_mapping); + blk_flush_plug(current); } while (!kthread_should_stop()); @@ -1996,7 +1993,7 @@ xfs_flush_buftarg( if (wait) { /* Expedite and wait for IO to complete. */ - blk_run_address_space(target->bt_mapping); + blk_flush_plug(current); while (!list_empty(&wait_list)) { bp = list_first_entry(&wait_list, struct xfs_buf, b_list); diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 4ce34fa937d..96f4094b706 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -66,8 +66,6 @@ struct backing_dev_info { unsigned int capabilities; /* Device capabilities */ congested_fn *congested_fn; /* Function pointer if device is md/dm */ void *congested_data; /* Pointer to aux data for congested func */ - void (*unplug_io_fn)(struct backing_dev_info *, struct page *); - void *unplug_io_data; char *name; @@ -251,7 +249,6 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio); extern struct backing_dev_info default_backing_dev_info; extern struct backing_dev_info noop_backing_dev_info; -void default_unplug_io_fn(struct backing_dev_info *bdi, struct page *page); int writeback_in_progress(struct backing_dev_info *bdi); @@ -336,17 +333,4 @@ static inline int bdi_sched_wait(void *word) return 0; } -static inline void blk_run_backing_dev(struct backing_dev_info *bdi, - struct page *page) -{ - if (bdi && bdi->unplug_io_fn) - bdi->unplug_io_fn(bdi, page); -} - -static inline void blk_run_address_space(struct address_space *mapping) -{ - if (mapping) - blk_run_backing_dev(mapping->backing_dev_info, NULL); -} - #endif /* _LINUX_BACKING_DEV_H */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 5873037eeb9..64ab2a1bb16 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -196,7 +196,6 @@ typedef void (request_fn_proc) (struct request_queue *q); typedef int (make_request_fn) (struct request_queue *q, struct bio *bio); typedef int (prep_rq_fn) (struct request_queue *, struct request *); typedef void (unprep_rq_fn) (struct request_queue *, struct request *); -typedef void (unplug_fn) (struct request_queue *); struct bio_vec; struct bvec_merge_data { @@ -279,7 +278,6 @@ struct request_queue make_request_fn *make_request_fn; prep_rq_fn *prep_rq_fn; unprep_rq_fn *unprep_rq_fn; - unplug_fn *unplug_fn; merge_bvec_fn *merge_bvec_fn; softirq_done_fn *softirq_done_fn; rq_timed_out_fn *rq_timed_out_fn; @@ -292,14 +290,6 @@ struct request_queue sector_t end_sector; struct request *boundary_rq; - /* - * Auto-unplugging state - */ - struct timer_list unplug_timer; - int unplug_thresh; /* After this many requests */ - unsigned long unplug_delay; /* After this many jiffies */ - struct work_struct unplug_work; - /* * Delayed queue handling */ @@ -399,14 +389,13 @@ struct request_queue #define QUEUE_FLAG_ASYNCFULL 4 /* write queue has been filled */ #define QUEUE_FLAG_DEAD 5 /* queue being torn down */ #define QUEUE_FLAG_REENTER 6 /* Re-entrancy avoidance */ -#define QUEUE_FLAG_PLUGGED 7 /* queue is plugged */ -#define QUEUE_FLAG_ELVSWITCH 8 /* don't use elevator, just do FIFO */ -#define QUEUE_FLAG_BIDI 9 /* queue supports bidi requests */ -#define QUEUE_FLAG_NOMERGES 10 /* disable merge attempts */ -#define QUEUE_FLAG_SAME_COMP 11 /* force complete on same CPU */ -#define QUEUE_FLAG_FAIL_IO 12 /* fake timeout */ -#define QUEUE_FLAG_STACKABLE 13 /* supports request stacking */ -#define QUEUE_FLAG_NONROT 14 /* non-rotational device (SSD) */ +#define QUEUE_FLAG_ELVSWITCH 7 /* don't use elevator, just do FIFO */ +#define QUEUE_FLAG_BIDI 8 /* queue supports bidi requests */ +#define QUEUE_FLAG_NOMERGES 9 /* disable merge attempts */ +#define QUEUE_FLAG_SAME_COMP 10 /* force complete on same CPU */ +#define QUEUE_FLAG_FAIL_IO 11 /* fake timeout */ +#define QUEUE_FLAG_STACKABLE 12 /* supports request stacking */ +#define QUEUE_FLAG_NONROT 13 /* non-rotational device (SSD) */ #define QUEUE_FLAG_VIRT QUEUE_FLAG_NONROT /* paravirt device */ #define QUEUE_FLAG_IO_STAT 15 /* do IO stats */ #define QUEUE_FLAG_DISCARD 16 /* supports DISCARD */ @@ -484,7 +473,6 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q) __clear_bit(flag, &q->queue_flags); } -#define blk_queue_plugged(q) test_bit(QUEUE_FLAG_PLUGGED, &(q)->queue_flags) #define blk_queue_tagged(q) test_bit(QUEUE_FLAG_QUEUED, &(q)->queue_flags) #define blk_queue_stopped(q) test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags) #define blk_queue_nomerges(q) test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags) @@ -679,9 +667,6 @@ extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src, extern void blk_rq_unprep_clone(struct request *rq); extern int blk_insert_cloned_request(struct request_queue *q, struct request *rq); -extern void blk_plug_device(struct request_queue *); -extern void blk_plug_device_unlocked(struct request_queue *); -extern int blk_remove_plug(struct request_queue *); extern void blk_delay_queue(struct request_queue *, unsigned long); extern void blk_recount_segments(struct request_queue *, struct bio *); extern int scsi_cmd_ioctl(struct request_queue *, struct gendisk *, fmode_t, @@ -726,7 +711,6 @@ extern int blk_execute_rq(struct request_queue *, struct gendisk *, struct request *, int); extern void blk_execute_rq_nowait(struct request_queue *, struct gendisk *, struct request *, int, rq_end_io_fn *); -extern void blk_unplug(struct request_queue *q); static inline struct request_queue *bdev_get_queue(struct block_device *bdev) { @@ -863,7 +847,6 @@ extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bd extern int blk_rq_map_sg(struct request_queue *, struct request *, struct scatterlist *); extern void blk_dump_rq_flags(struct request *, char *); -extern void generic_unplug_device(struct request_queue *); extern long nr_blockdev_pages(void); int blk_get_queue(struct request_queue *); diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 68d1fe7b877..f5df23561b9 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -219,7 +219,6 @@ int generic_cont_expand_simple(struct inode *inode, loff_t size); int block_commit_write(struct page *page, unsigned from, unsigned to); int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, get_block_t get_block); -void block_sync_page(struct page *); sector_t generic_block_bmap(struct address_space *, sector_t, get_block_t *); int block_truncate_page(struct address_space *, loff_t, get_block_t *); int nobh_write_begin(struct address_space *, loff_t, unsigned, unsigned, diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 272496d1fae..e2768834f39 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -285,11 +285,6 @@ void dm_table_add_target_callbacks(struct dm_table *t, struct dm_target_callback */ int dm_table_complete(struct dm_table *t); -/* - * Unplug all devices in a table. - */ -void dm_table_unplug_all(struct dm_table *t); - /* * Table reference counting. */ diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 8857cf9adbb..ec6f72b8447 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -20,7 +20,6 @@ typedef void (elevator_bio_merged_fn) (struct request_queue *, typedef int (elevator_dispatch_fn) (struct request_queue *, int); typedef void (elevator_add_req_fn) (struct request_queue *, struct request *); -typedef int (elevator_queue_empty_fn) (struct request_queue *); typedef struct request *(elevator_request_list_fn) (struct request_queue *, struct request *); typedef void (elevator_completed_req_fn) (struct request_queue *, struct request *); typedef int (elevator_may_queue_fn) (struct request_queue *, int); @@ -46,7 +45,6 @@ struct elevator_ops elevator_activate_req_fn *elevator_activate_req_fn; elevator_deactivate_req_fn *elevator_deactivate_req_fn; - elevator_queue_empty_fn *elevator_queue_empty_fn; elevator_completed_req_fn *elevator_completed_req_fn; elevator_request_list_fn *elevator_former_req_fn; @@ -101,8 +99,8 @@ struct elevator_queue */ extern void elv_dispatch_sort(struct request_queue *, struct request *); extern void elv_dispatch_add_tail(struct request_queue *, struct request *); -extern void elv_add_request(struct request_queue *, struct request *, int, int); -extern void __elv_add_request(struct request_queue *, struct request *, int, int); +extern void elv_add_request(struct request_queue *, struct request *, int); +extern void __elv_add_request(struct request_queue *, struct request *, int); extern void elv_insert(struct request_queue *, struct request *, int); extern int elv_merge(struct request_queue *, struct request **, struct bio *); extern int elv_try_merge(struct request *, struct bio *); @@ -112,7 +110,6 @@ extern void elv_merged_request(struct request_queue *, struct request *, int); extern void elv_bio_merged(struct request_queue *q, struct request *, struct bio *); extern void elv_requeue_request(struct request_queue *, struct request *); -extern int elv_queue_empty(struct request_queue *); extern struct request *elv_former_request(struct request_queue *, struct request *); extern struct request *elv_latter_request(struct request_queue *, struct request *); extern int elv_register_queue(struct request_queue *q); diff --git a/include/linux/fs.h b/include/linux/fs.h index bd3215940c3..9f2cf69911b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -583,7 +583,6 @@ typedef int (*read_actor_t)(read_descriptor_t *, struct page *, struct address_space_operations { int (*writepage)(struct page *page, struct writeback_control *wbc); int (*readpage)(struct file *, struct page *); - void (*sync_page)(struct page *); /* Write back some dirty pages from this mapping. */ int (*writepages)(struct address_space *, struct writeback_control *); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 9c66e994540..e112b8db2f3 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -298,7 +298,6 @@ static inline pgoff_t linear_page_index(struct vm_area_struct *vma, extern void __lock_page(struct page *page); extern int __lock_page_killable(struct page *page); -extern void __lock_page_nosync(struct page *page); extern int __lock_page_or_retry(struct page *page, struct mm_struct *mm, unsigned int flags); extern void unlock_page(struct page *page); @@ -341,17 +340,6 @@ static inline int lock_page_killable(struct page *page) return 0; } -/* - * lock_page_nosync should only be used if we can't pin the page's inode. - * Doesn't play quite so well with block device plugging. - */ -static inline void lock_page_nosync(struct page *page) -{ - might_sleep(); - if (!trylock_page(page)) - __lock_page_nosync(page); -} - /* * lock_page_or_retry - Lock the page, unless this would block and the * caller indicated that it can handle a retry. diff --git a/include/linux/swap.h b/include/linux/swap.h index 4d559325d91..9ee321833b2 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -299,8 +299,6 @@ extern void mem_cgroup_get_shmem_target(struct inode *inode, pgoff_t pgoff, struct page **pagep, swp_entry_t *ent); #endif -extern void swap_unplug_io_fn(struct backing_dev_info *, struct page *); - #ifdef CONFIG_SWAP /* linux/mm/page_io.c */ extern int swap_readpage(struct page *); diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 027100d3022..c91e139a652 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -14,17 +14,11 @@ static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0); -void default_unplug_io_fn(struct backing_dev_info *bdi, struct page *page) -{ -} -EXPORT_SYMBOL(default_unplug_io_fn); - struct backing_dev_info default_backing_dev_info = { .name = "default", .ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE, .state = 0, .capabilities = BDI_CAP_MAP_COPY, - .unplug_io_fn = default_unplug_io_fn, }; EXPORT_SYMBOL_GPL(default_backing_dev_info); diff --git a/mm/filemap.c b/mm/filemap.c index 83a45d35468..380776c2a9a 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -155,45 +155,15 @@ void remove_from_page_cache(struct page *page) } EXPORT_SYMBOL(remove_from_page_cache); -static int sync_page(void *word) +static int sleep_on_page(void *word) { - struct address_space *mapping; - struct page *page; - - page = container_of((unsigned long *)word, struct page, flags); - - /* - * page_mapping() is being called without PG_locked held. - * Some knowledge of the state and use of the page is used to - * reduce the requirements down to a memory barrier. - * The danger here is of a stale page_mapping() return value - * indicating a struct address_space different from the one it's - * associated with when it is associated with one. - * After smp_mb(), it's either the correct page_mapping() for - * the page, or an old page_mapping() and the page's own - * page_mapping() has gone NULL. - * The ->sync_page() address_space operation must tolerate - * page_mapping() going NULL. By an amazing coincidence, - * this comes about because none of the users of the page - * in the ->sync_page() methods make essential use of the - * page_mapping(), merely passing the page down to the backing - * device's unplug functions when it's non-NULL, which in turn - * ignore it for all cases but swap, where only page_private(page) is - * of interest. When page_mapping() does go NULL, the entire - * call stack gracefully ignores the page and returns. - * -- wli - */ - smp_mb(); - mapping = page_mapping(page); - if (mapping && mapping->a_ops && mapping->a_ops->sync_page) - mapping->a_ops->sync_page(page); io_schedule(); return 0; } -static int sync_page_killable(void *word) +static int sleep_on_page_killable(void *word) { - sync_page(word); + sleep_on_page(word); return fatal_signal_pending(current) ? -EINTR : 0; } @@ -479,12 +449,6 @@ struct page *__page_cache_alloc(gfp_t gfp) EXPORT_SYMBOL(__page_cache_alloc); #endif -static int __sleep_on_page_lock(void *word) -{ - io_schedule(); - return 0; -} - /* * In order to wait for pages to become available there must be * waitqueues associated with pages. By using a hash table of @@ -512,7 +476,7 @@ void wait_on_page_bit(struct page *page, int bit_nr) DEFINE_WAIT_BIT(wait, &page->flags, bit_nr); if (test_bit(bit_nr, &page->flags)) - __wait_on_bit(page_waitqueue(page), &wait, sync_page, + __wait_on_bit(page_waitqueue(page), &wait, sleep_on_page, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(wait_on_page_bit); @@ -576,17 +540,12 @@ EXPORT_SYMBOL(end_page_writeback); /** * __lock_page - get a lock on the page, assuming we need to sleep to get it * @page: the page to lock - * - * Ugly. Running sync_page() in state TASK_UNINTERRUPTIBLE is scary. If some - * random driver's requestfn sets TASK_RUNNING, we could busywait. However - * chances are that on the second loop, the block layer's plug list is empty, - * so sync_page() will then return in state TASK_UNINTERRUPTIBLE. */ void __lock_page(struct page *page) { DEFINE_WAIT_BIT(wait, &page->flags, PG_locked); - __wait_on_bit_lock(page_waitqueue(page), &wait, sync_page, + __wait_on_bit_lock(page_waitqueue(page), &wait, sleep_on_page, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(__lock_page); @@ -596,24 +555,10 @@ int __lock_page_killable(struct page *page) DEFINE_WAIT_BIT(wait, &page->flags, PG_locked); return __wait_on_bit_lock(page_waitqueue(page), &wait, - sync_page_killable, TASK_KILLABLE); + sleep_on_page_killable, TASK_KILLABLE); } EXPORT_SYMBOL_GPL(__lock_page_killable); -/** - * __lock_page_nosync - get a lock on the page, without calling sync_page() - * @page: the page to lock - * - * Variant of lock_page that does not require the caller to hold a reference - * on the page's mapping. - */ -void __lock_page_nosync(struct page *page) -{ - DEFINE_WAIT_BIT(wait, &page->flags, PG_locked); - __wait_on_bit_lock(page_waitqueue(page), &wait, __sleep_on_page_lock, - TASK_UNINTERRUPTIBLE); -} - int __lock_page_or_retry(struct page *page, struct mm_struct *mm, unsigned int flags) { diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 0207c2f6f8b..bfba796d374 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -945,7 +945,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, collect_procs(ppage, &tokill); if (hpage != ppage) - lock_page_nosync(ppage); + lock_page(ppage); ret = try_to_unmap(ppage, ttu); if (ret != SWAP_SUCCESS) @@ -1038,7 +1038,7 @@ int __memory_failure(unsigned long pfn, int trapno, int flags) * Check "just unpoisoned", "filter hit", and * "race with other subpage." */ - lock_page_nosync(hpage); + lock_page(hpage); if (!PageHWPoison(hpage) || (hwpoison_filter(p) && TestClearPageHWPoison(p)) || (p != hpage && TestSetPageHWPoison(hpage))) { @@ -1088,7 +1088,7 @@ int __memory_failure(unsigned long pfn, int trapno, int flags) * It's very difficult to mess with pages currently under IO * and in many cases impossible, so we just avoid it here. */ - lock_page_nosync(hpage); + lock_page(hpage); /* * unpoison always clear PG_hwpoison inside page lock @@ -1231,7 +1231,7 @@ int unpoison_memory(unsigned long pfn) return 0; } - lock_page_nosync(page); + lock_page(page); /* * This test is racy because PG_hwpoison is set outside of page lock. * That's acceptable because that won't trigger kernel panic. Instead, diff --git a/mm/nommu.c b/mm/nommu.c index f59e1424d3d..fb6cbd6abe1 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -1842,10 +1842,6 @@ int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, } EXPORT_SYMBOL(remap_vmalloc_range); -void swap_unplug_io_fn(struct backing_dev_info *bdi, struct page *page) -{ -} - unsigned long arch_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 2cb01f6ec5d..cc0ede169e4 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1239,7 +1239,7 @@ int set_page_dirty_lock(struct page *page) { int ret; - lock_page_nosync(page); + lock_page(page); ret = set_page_dirty(page); unlock_page(page); return ret; diff --git a/mm/readahead.c b/mm/readahead.c index 77506a291a2..cbddc3e1724 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -554,17 +554,5 @@ page_cache_async_readahead(struct address_space *mapping, /* do read-ahead */ ondemand_readahead(mapping, ra, filp, true, offset, req_size); - -#ifdef CONFIG_BLOCK - /* - * Normally the current page is !uptodate and lock_page() will be - * immediately called to implicitly unplug the device. However this - * is not always true for RAID conifgurations, where data arrives - * not strictly in their submission order. In this case we need to - * explicitly kick off the IO. - */ - if (PageUptodate(page)) - blk_run_backing_dev(mapping->backing_dev_info, NULL); -#endif } EXPORT_SYMBOL_GPL(page_cache_async_readahead); diff --git a/mm/shmem.c b/mm/shmem.c index 5ee67c99060..24d23f5bedf 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -224,7 +224,6 @@ static const struct vm_operations_struct shmem_vm_ops; static struct backing_dev_info shmem_backing_dev_info __read_mostly = { .ra_pages = 0, /* No readahead */ .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_SWAP_BACKED, - .unplug_io_fn = default_unplug_io_fn, }; static LIST_HEAD(shmem_swaplist); diff --git a/mm/swap_state.c b/mm/swap_state.c index 5c8cfabbc9b..46680461785 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -24,12 +24,10 @@ /* * swapper_space is a fiction, retained to simplify the path through - * vmscan's shrink_page_list, to make sync_page look nicer, and to allow - * future use of radix_tree tags in the swap cache. + * vmscan's shrink_page_list. */ static const struct address_space_operations swap_aops = { .writepage = swap_writepage, - .sync_page = block_sync_page, .set_page_dirty = __set_page_dirty_nobuffers, .migratepage = migrate_page, }; @@ -37,7 +35,6 @@ static const struct address_space_operations swap_aops = { static struct backing_dev_info swap_backing_dev_info = { .name = "swap", .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_SWAP_BACKED, - .unplug_io_fn = swap_unplug_io_fn, }; struct address_space swapper_space = { diff --git a/mm/swapfile.c b/mm/swapfile.c index 07a458d72fa..7ceea78ceb2 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -94,39 +94,6 @@ __try_to_reclaim_swap(struct swap_info_struct *si, unsigned long offset) return ret; } -/* - * We need this because the bdev->unplug_fn can sleep and we cannot - * hold swap_lock while calling the unplug_fn. And swap_lock - * cannot be turned into a mutex. - */ -static DECLARE_RWSEM(swap_unplug_sem); - -void swap_unplug_io_fn(struct backing_dev_info *unused_bdi, struct page *page) -{ - swp_entry_t entry; - - down_read(&swap_unplug_sem); - entry.val = page_private(page); - if (PageSwapCache(page)) { - struct block_device *bdev = swap_info[swp_type(entry)]->bdev; - struct backing_dev_info *bdi; - - /* - * If the page is removed from swapcache from under us (with a - * racy try_to_unuse/swapoff) we need an additional reference - * count to avoid reading garbage from page_private(page) above. - * If the WARN_ON triggers during a swapoff it maybe the race - * condition and it's harmless. However if it triggers without - * swapoff it signals a problem. - */ - WARN_ON(page_count(page) <= 1); - - bdi = bdev->bd_inode->i_mapping->backing_dev_info; - blk_run_backing_dev(bdi, page); - } - up_read(&swap_unplug_sem); -} - /* * swapon tell device that all the old swap contents can be discarded, * to allow the swap device to optimize its wear-levelling. @@ -1643,10 +1610,6 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) goto out_dput; } - /* wait for any unplug function to finish */ - down_write(&swap_unplug_sem); - up_write(&swap_unplug_sem); - destroy_swap_extents(p); if (p->flags & SWP_CONTINUED) free_swap_count_continuations(p); diff --git a/mm/vmscan.c b/mm/vmscan.c index 17497d0cd8b..251bed73ac0 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -358,7 +358,7 @@ static int may_write_to_queue(struct backing_dev_info *bdi, static void handle_write_error(struct address_space *mapping, struct page *page, int error) { - lock_page_nosync(page); + lock_page(page); if (page_mapping(page) == mapping) mapping_set_error(mapping, error); unlock_page(page); -- cgit v1.2.3-70-g09d2 From 66b4ffd110f9b48b8d8c1319ee446b53b8d073bf Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Mon, 31 Jan 2011 16:22:42 -0500 Subject: Btrfs: handle errors in btrfs_orphan_cleanup If we cannot truncate an inode for some reason we will never delete the orphan item associated with that inode, which means that we will loop forever in btrfs_orphan_cleanup. Instead of doing this just return error so we fail to mount. It sucks, but hey it's better than hanging. Thanks, Signed-off-by: Josef Bacik --- fs/btrfs/ctree.h | 2 +- fs/btrfs/disk-io.c | 15 ++++++++++++--- fs/btrfs/extent-tree.c | 3 ++- fs/btrfs/inode.c | 47 +++++++++++++++++++++++++++++++---------------- fs/btrfs/ioctl.c | 4 +++- fs/btrfs/relocation.c | 2 +- 6 files changed, 50 insertions(+), 23 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 34142d5647d..841330f3d68 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2529,7 +2529,7 @@ int btrfs_update_inode(struct btrfs_trans_handle *trans, struct inode *inode); int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode); int btrfs_orphan_del(struct btrfs_trans_handle *trans, struct inode *inode); -void btrfs_orphan_cleanup(struct btrfs_root *root); +int btrfs_orphan_cleanup(struct btrfs_root *root); void btrfs_orphan_pre_snapshot(struct btrfs_trans_handle *trans, struct btrfs_pending_snapshot *pending, u64 *bytes_to_reserve); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index e1aa8d607bc..495b1ac45f8 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2058,9 +2058,14 @@ struct btrfs_root *open_ctree(struct super_block *sb, if (!(sb->s_flags & MS_RDONLY)) { down_read(&fs_info->cleanup_work_sem); - btrfs_orphan_cleanup(fs_info->fs_root); - btrfs_orphan_cleanup(fs_info->tree_root); + err = btrfs_orphan_cleanup(fs_info->fs_root); + if (!err) + err = btrfs_orphan_cleanup(fs_info->tree_root); up_read(&fs_info->cleanup_work_sem); + if (err) { + close_ctree(tree_root); + return ERR_PTR(err); + } } return tree_root; @@ -2435,8 +2440,12 @@ int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info) root_objectid = gang[ret - 1]->root_key.objectid + 1; for (i = 0; i < ret; i++) { + int err; + root_objectid = gang[i]->root_key.objectid; - btrfs_orphan_cleanup(gang[i]); + err = btrfs_orphan_cleanup(gang[i]); + if (err) + return err; } root_objectid++; } diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 27376c97d85..a8f4e8d2ba6 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -7619,7 +7619,8 @@ int btrfs_cleanup_reloc_trees(struct btrfs_root *root) reloc_root = btrfs_read_fs_root_no_name(root->fs_info, &location); BUG_ON(!reloc_root); - btrfs_orphan_cleanup(reloc_root); + ret = btrfs_orphan_cleanup(reloc_root); + BUG_ON(ret); return 0; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index d83025063ee..0600265cb9b 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -2284,7 +2284,7 @@ int btrfs_orphan_del(struct btrfs_trans_handle *trans, struct inode *inode) * this cleans up any orphans that may be left on the list from the last use * of this root. */ -void btrfs_orphan_cleanup(struct btrfs_root *root) +int btrfs_orphan_cleanup(struct btrfs_root *root) { struct btrfs_path *path; struct extent_buffer *leaf; @@ -2294,10 +2294,13 @@ void btrfs_orphan_cleanup(struct btrfs_root *root) int ret = 0, nr_unlink = 0, nr_truncate = 0; if (cmpxchg(&root->orphan_cleanup_state, 0, ORPHAN_CLEANUP_STARTED)) - return; + return 0; path = btrfs_alloc_path(); - BUG_ON(!path); + if (!path) { + ret = -ENOMEM; + goto out; + } path->reada = -1; key.objectid = BTRFS_ORPHAN_OBJECTID; @@ -2306,11 +2309,8 @@ void btrfs_orphan_cleanup(struct btrfs_root *root) while (1) { ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); - if (ret < 0) { - printk(KERN_ERR "Error searching slot for orphan: %d" - "\n", ret); - break; - } + if (ret < 0) + goto out; /* * if ret == 0 means we found what we were searching for, which @@ -2318,6 +2318,7 @@ void btrfs_orphan_cleanup(struct btrfs_root *root) * find the key and see if we have stuff that matches */ if (ret > 0) { + ret = 0; if (path->slots[0] == 0) break; path->slots[0]--; @@ -2345,7 +2346,10 @@ void btrfs_orphan_cleanup(struct btrfs_root *root) found_key.type = BTRFS_INODE_ITEM_KEY; found_key.offset = 0; inode = btrfs_iget(root->fs_info->sb, &found_key, root, NULL); - BUG_ON(IS_ERR(inode)); + if (IS_ERR(inode)) { + ret = PTR_ERR(inode); + goto out; + } /* * add this inode to the orphan list so btrfs_orphan_del does @@ -2363,7 +2367,10 @@ void btrfs_orphan_cleanup(struct btrfs_root *root) */ if (is_bad_inode(inode)) { trans = btrfs_start_transaction(root, 0); - BUG_ON(IS_ERR(trans)); + if (IS_ERR(trans)) { + ret = PTR_ERR(trans); + goto out; + } btrfs_orphan_del(trans, inode); btrfs_end_transaction(trans, root); iput(inode); @@ -2378,16 +2385,16 @@ void btrfs_orphan_cleanup(struct btrfs_root *root) continue; } nr_truncate++; - btrfs_truncate(inode); + ret = btrfs_truncate(inode); } else { nr_unlink++; } /* this will do delete_inode and everything for us */ iput(inode); + if (ret) + goto out; } - btrfs_free_path(path); - root->orphan_cleanup_state = ORPHAN_CLEANUP_DONE; if (root->orphan_block_rsv) @@ -2396,14 +2403,20 @@ void btrfs_orphan_cleanup(struct btrfs_root *root) if (root->orphan_block_rsv || root->orphan_item_inserted) { trans = btrfs_join_transaction(root, 1); - BUG_ON(IS_ERR(trans)); - btrfs_end_transaction(trans, root); + if (!IS_ERR(trans)) + btrfs_end_transaction(trans, root); } if (nr_unlink) printk(KERN_INFO "btrfs: unlinked %d orphans\n", nr_unlink); if (nr_truncate) printk(KERN_INFO "btrfs: truncated %d orphans\n", nr_truncate); + +out: + if (ret) + printk(KERN_CRIT "btrfs: could not do orphan cleanup %d\n", ret); + btrfs_free_path(path); + return ret; } /* @@ -4156,8 +4169,10 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry) if (!IS_ERR(inode) && root != sub_root) { down_read(&root->fs_info->cleanup_work_sem); if (!(inode->i_sb->s_flags & MS_RDONLY)) - btrfs_orphan_cleanup(sub_root); + ret = btrfs_orphan_cleanup(sub_root); up_read(&root->fs_info->cleanup_work_sem); + if (ret) + inode = ERR_PTR(ret); } return inode; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 5fdb2abc4fa..ad9b8c0e930 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -409,7 +409,9 @@ static int create_snapshot(struct btrfs_root *root, struct dentry *dentry, if (ret) goto fail; - btrfs_orphan_cleanup(pending_snapshot->snap); + ret = btrfs_orphan_cleanup(pending_snapshot->snap); + if (ret) + goto fail; parent = dget_parent(dentry); inode = btrfs_lookup_dentry(parent->d_inode, dentry); diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 31ade5802ae..c863c844701 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -4209,7 +4209,7 @@ out: if (IS_ERR(fs_root)) err = PTR_ERR(fs_root); else - btrfs_orphan_cleanup(fs_root); + err = btrfs_orphan_cleanup(fs_root); } return err; } -- cgit v1.2.3-70-g09d2 From a826d6dcb32d811b4c81df57a5ef1367516586b0 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Wed, 16 Mar 2011 13:42:43 -0400 Subject: Btrfs: check items for correctness as we search Currently if we have corrupted items things will blow up in spectacular ways. So as we read in blocks and they are leaves, check the entire leaf to make sure all of the items are correct and point to valid parts in the leaf for the item data the are responsible for. If the item is corrupt we will kick back EIO and not read any of the copies since they are likely to not be correct either. This will catch generic corruptions, it will be up to the individual callers of btrfs_search_slot to make sure their items are right. Thanks, Signed-off-by: Josef Bacik --- fs/btrfs/ctree.c | 123 ------------------------------------------------- fs/btrfs/disk-io.c | 90 +++++++++++++++++++++++++++++++++++- fs/btrfs/extent-tree.c | 5 ++ fs/btrfs/extent_io.h | 1 + 4 files changed, 95 insertions(+), 124 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index b5baff0dccf..73e53009e12 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -732,122 +732,6 @@ static inline unsigned int leaf_data_end(struct btrfs_root *root, return btrfs_item_offset_nr(leaf, nr - 1); } -/* - * extra debugging checks to make sure all the items in a key are - * well formed and in the proper order - */ -static int check_node(struct btrfs_root *root, struct btrfs_path *path, - int level) -{ - struct extent_buffer *parent = NULL; - struct extent_buffer *node = path->nodes[level]; - struct btrfs_disk_key parent_key; - struct btrfs_disk_key node_key; - int parent_slot; - int slot; - struct btrfs_key cpukey; - u32 nritems = btrfs_header_nritems(node); - - if (path->nodes[level + 1]) - parent = path->nodes[level + 1]; - - slot = path->slots[level]; - BUG_ON(nritems == 0); - if (parent) { - parent_slot = path->slots[level + 1]; - btrfs_node_key(parent, &parent_key, parent_slot); - btrfs_node_key(node, &node_key, 0); - BUG_ON(memcmp(&parent_key, &node_key, - sizeof(struct btrfs_disk_key))); - BUG_ON(btrfs_node_blockptr(parent, parent_slot) != - btrfs_header_bytenr(node)); - } - BUG_ON(nritems > BTRFS_NODEPTRS_PER_BLOCK(root)); - if (slot != 0) { - btrfs_node_key_to_cpu(node, &cpukey, slot - 1); - btrfs_node_key(node, &node_key, slot); - BUG_ON(comp_keys(&node_key, &cpukey) <= 0); - } - if (slot < nritems - 1) { - btrfs_node_key_to_cpu(node, &cpukey, slot + 1); - btrfs_node_key(node, &node_key, slot); - BUG_ON(comp_keys(&node_key, &cpukey) >= 0); - } - return 0; -} - -/* - * extra checking to make sure all the items in a leaf are - * well formed and in the proper order - */ -static int check_leaf(struct btrfs_root *root, struct btrfs_path *path, - int level) -{ - struct extent_buffer *leaf = path->nodes[level]; - struct extent_buffer *parent = NULL; - int parent_slot; - struct btrfs_key cpukey; - struct btrfs_disk_key parent_key; - struct btrfs_disk_key leaf_key; - int slot = path->slots[0]; - - u32 nritems = btrfs_header_nritems(leaf); - - if (path->nodes[level + 1]) - parent = path->nodes[level + 1]; - - if (nritems == 0) - return 0; - - if (parent) { - parent_slot = path->slots[level + 1]; - btrfs_node_key(parent, &parent_key, parent_slot); - btrfs_item_key(leaf, &leaf_key, 0); - - BUG_ON(memcmp(&parent_key, &leaf_key, - sizeof(struct btrfs_disk_key))); - BUG_ON(btrfs_node_blockptr(parent, parent_slot) != - btrfs_header_bytenr(leaf)); - } - if (slot != 0 && slot < nritems - 1) { - btrfs_item_key(leaf, &leaf_key, slot); - btrfs_item_key_to_cpu(leaf, &cpukey, slot - 1); - if (comp_keys(&leaf_key, &cpukey) <= 0) { - btrfs_print_leaf(root, leaf); - printk(KERN_CRIT "slot %d offset bad key\n", slot); - BUG_ON(1); - } - if (btrfs_item_offset_nr(leaf, slot - 1) != - btrfs_item_end_nr(leaf, slot)) { - btrfs_print_leaf(root, leaf); - printk(KERN_CRIT "slot %d offset bad\n", slot); - BUG_ON(1); - } - } - if (slot < nritems - 1) { - btrfs_item_key(leaf, &leaf_key, slot); - btrfs_item_key_to_cpu(leaf, &cpukey, slot + 1); - BUG_ON(comp_keys(&leaf_key, &cpukey) >= 0); - if (btrfs_item_offset_nr(leaf, slot) != - btrfs_item_end_nr(leaf, slot + 1)) { - btrfs_print_leaf(root, leaf); - printk(KERN_CRIT "slot %d offset bad\n", slot); - BUG_ON(1); - } - } - BUG_ON(btrfs_item_offset_nr(leaf, 0) + - btrfs_item_size_nr(leaf, 0) != BTRFS_LEAF_DATA_SIZE(root)); - return 0; -} - -static noinline int check_block(struct btrfs_root *root, - struct btrfs_path *path, int level) -{ - return 0; - if (level == 0) - return check_leaf(root, path, level); - return check_node(root, path, level); -} /* * search for key in the extent_buffer. The items start at offset p, @@ -1188,7 +1072,6 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, } } /* double check we haven't messed things up */ - check_block(root, path, level); if (orig_ptr != btrfs_node_blockptr(path->nodes[level], path->slots[level])) BUG(); @@ -1798,12 +1681,6 @@ cow_done: if (!cow) btrfs_unlock_up_safe(p, level + 1); - ret = check_block(root, p, level); - if (ret) { - ret = -1; - goto done; - } - ret = bin_search(b, key, level, &slot); if (level != 0) { diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 495b1ac45f8..9f31e110b48 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -323,6 +323,7 @@ static int btree_read_extent_buffer_pages(struct btrfs_root *root, int num_copies = 0; int mirror_num = 0; + clear_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags); io_tree = &BTRFS_I(root->fs_info->btree_inode)->io_tree; while (1) { ret = read_extent_buffer_pages(io_tree, eb, start, 1, @@ -331,6 +332,14 @@ static int btree_read_extent_buffer_pages(struct btrfs_root *root, !verify_parent_transid(io_tree, eb, parent_transid)) return ret; + /* + * This buffer's crc is fine, but its contents are corrupted, so + * there is no reason to read the other copies, they won't be + * any less wrong. + */ + if (test_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags)) + return ret; + num_copies = btrfs_num_copies(&root->fs_info->mapping_tree, eb->start, eb->len); if (num_copies == 1) @@ -419,6 +428,73 @@ static int check_tree_block_fsid(struct btrfs_root *root, return ret; } +#define CORRUPT(reason, eb, root, slot) \ + printk(KERN_CRIT "btrfs: corrupt leaf, %s: block=%llu," \ + "root=%llu, slot=%d\n", reason, \ + (unsigned long long)btrfs_header_bytenr(eb), \ + (unsigned long long)root->objectid, slot) + +static noinline int check_leaf(struct btrfs_root *root, + struct extent_buffer *leaf) +{ + struct btrfs_key key; + struct btrfs_key leaf_key; + u32 nritems = btrfs_header_nritems(leaf); + int slot; + + if (nritems == 0) + return 0; + + /* Check the 0 item */ + if (btrfs_item_offset_nr(leaf, 0) + btrfs_item_size_nr(leaf, 0) != + BTRFS_LEAF_DATA_SIZE(root)) { + CORRUPT("invalid item offset size pair", leaf, root, 0); + return -EIO; + } + + /* + * Check to make sure each items keys are in the correct order and their + * offsets make sense. We only have to loop through nritems-1 because + * we check the current slot against the next slot, which verifies the + * next slot's offset+size makes sense and that the current's slot + * offset is correct. + */ + for (slot = 0; slot < nritems - 1; slot++) { + btrfs_item_key_to_cpu(leaf, &leaf_key, slot); + btrfs_item_key_to_cpu(leaf, &key, slot + 1); + + /* Make sure the keys are in the right order */ + if (btrfs_comp_cpu_keys(&leaf_key, &key) >= 0) { + CORRUPT("bad key order", leaf, root, slot); + return -EIO; + } + + /* + * Make sure the offset and ends are right, remember that the + * item data starts at the end of the leaf and grows towards the + * front. + */ + if (btrfs_item_offset_nr(leaf, slot) != + btrfs_item_end_nr(leaf, slot + 1)) { + CORRUPT("slot offset bad", leaf, root, slot); + return -EIO; + } + + /* + * Check to make sure that we don't point outside of the leaf, + * just incase all the items are consistent to eachother, but + * all point outside of the leaf. + */ + if (btrfs_item_end_nr(leaf, slot) > + BTRFS_LEAF_DATA_SIZE(root)) { + CORRUPT("slot end outside of leaf", leaf, root, slot); + return -EIO; + } + } + + return 0; +} + #ifdef CONFIG_DEBUG_LOCK_ALLOC void btrfs_set_buffer_lockdep_class(struct extent_buffer *eb, int level) { @@ -485,8 +561,20 @@ static int btree_readpage_end_io_hook(struct page *page, u64 start, u64 end, btrfs_set_buffer_lockdep_class(eb, found_level); ret = csum_tree_block(root, eb, 1); - if (ret) + if (ret) { ret = -EIO; + goto err; + } + + /* + * If this is a leaf block and it is corrupt, set the corrupt bit so + * that we don't try and read the other copies of this block, just + * return -EIO. + */ + if (found_level == 0 && check_leaf(root, eb)) { + set_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags); + ret = -EIO; + } end = min_t(u64, eb->len, PAGE_CACHE_SIZE); end = eb->start + end - 1; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index a8f4e8d2ba6..cd794c35a63 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -4754,6 +4754,11 @@ pin: } } out: + /* + * Deleting the buffer, clear the corrupt flag since it doesn't matter + * anymore. + */ + clear_bit(EXTENT_BUFFER_CORRUPT, &buf->bflags); btrfs_put_block_group(cache); } diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 9318dfefd59..f62c5442835 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -31,6 +31,7 @@ #define EXTENT_BUFFER_UPTODATE 0 #define EXTENT_BUFFER_BLOCKING 1 #define EXTENT_BUFFER_DIRTY 2 +#define EXTENT_BUFFER_CORRUPT 3 /* these are flags for extent_clear_unlock_delalloc */ #define EXTENT_CLEAR_UNLOCK_PAGE 0x1 -- cgit v1.2.3-70-g09d2 From db5b493ac78e46c7b6bad22cd25d8041564cd8ea Mon Sep 17 00:00:00 2001 From: Tsutomu Itoh Date: Wed, 23 Mar 2011 08:14:16 +0000 Subject: Btrfs: cleanup some BUG_ON() This patch changes some BUG_ON() to the error return. (but, most callers still use BUG_ON()) Signed-off-by: Tsutomu Itoh Signed-off-by: Chris Mason --- fs/btrfs/ctree.c | 3 ++- fs/btrfs/disk-io.c | 5 ++++- fs/btrfs/extent-tree.c | 25 ++++++++++++++++++------- fs/btrfs/file-item.c | 3 ++- fs/btrfs/inode-map.c | 3 ++- fs/btrfs/ioctl.c | 5 ++++- fs/btrfs/root-tree.c | 6 ++++-- fs/btrfs/transaction.c | 12 +++++++++--- fs/btrfs/tree-log.c | 15 +++++++++------ 9 files changed, 54 insertions(+), 23 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 465b5d7d6b4..4edcbe91573 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -3709,7 +3709,8 @@ int btrfs_insert_item(struct btrfs_trans_handle *trans, struct btrfs_root unsigned long ptr; path = btrfs_alloc_path(); - BUG_ON(!path); + if (!path) + return -ENOMEM; ret = btrfs_insert_empty_item(trans, root, path, cpu_key, data_size); if (!ret) { leaf = path->nodes[0]; diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 9f31e110b48..00cbb41af66 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1248,7 +1248,10 @@ struct btrfs_root *btrfs_read_fs_root_no_radix(struct btrfs_root *tree_root, root, fs_info, location->objectid); path = btrfs_alloc_path(); - BUG_ON(!path); + if (!path) { + kfree(root); + return ERR_PTR(-ENOMEM); + } ret = btrfs_search_slot(NULL, tree_root, location, path, 0, 0); if (ret == 0) { l = path->nodes[0]; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 86ea471d380..a6a8159c5d1 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -5463,7 +5463,8 @@ static int alloc_reserved_file_extent(struct btrfs_trans_handle *trans, size = sizeof(*extent_item) + btrfs_extent_inline_ref_size(type); path = btrfs_alloc_path(); - BUG_ON(!path); + if (!path) + return -ENOMEM; path->leave_spinning = 1; ret = btrfs_insert_empty_item(trans, fs_info->extent_root, path, @@ -6457,10 +6458,14 @@ int btrfs_drop_subtree(struct btrfs_trans_handle *trans, BUG_ON(root->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID); path = btrfs_alloc_path(); - BUG_ON(!path); + if (!path) + return -ENOMEM; wc = kzalloc(sizeof(*wc), GFP_NOFS); - BUG_ON(!wc); + if (!wc) { + btrfs_free_path(path); + return -ENOMEM; + } btrfs_assert_tree_locked(parent); parent_level = btrfs_header_level(parent); @@ -6918,7 +6923,11 @@ static noinline int get_new_locations(struct inode *reloc_inode, } path = btrfs_alloc_path(); - BUG_ON(!path); + if (!path) { + if (exts != *extents) + kfree(exts); + return -ENOMEM; + } cur_pos = extent_key->objectid - offset; last_byte = extent_key->objectid + extent_key->offset; @@ -7442,7 +7451,8 @@ static noinline int replace_extents_in_leaf(struct btrfs_trans_handle *trans, int ret; new_extent = kmalloc(sizeof(*new_extent), GFP_NOFS); - BUG_ON(!new_extent); + if (!new_extent) + return -ENOMEM; ref = btrfs_lookup_leaf_ref(root, leaf->start); BUG_ON(!ref); @@ -7647,7 +7657,8 @@ static noinline int init_reloc_tree(struct btrfs_trans_handle *trans, return 0; root_item = kmalloc(sizeof(*root_item), GFP_NOFS); - BUG_ON(!root_item); + if (!root_item) + return -ENOMEM; ret = btrfs_copy_root(trans, root, root->commit_root, &eb, BTRFS_TREE_RELOC_OBJECTID); @@ -7673,7 +7684,7 @@ static noinline int init_reloc_tree(struct btrfs_trans_handle *trans, reloc_root = btrfs_read_fs_root_no_radix(root->fs_info->tree_root, &root_key); - BUG_ON(!reloc_root); + BUG_ON(IS_ERR(reloc_root)); reloc_root->last_trans = trans->transid; reloc_root->commit_root = NULL; reloc_root->ref_tree = &root->fs_info->reloc_ref_tree; diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index 4f19a3e1bf3..a2134195a85 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -48,7 +48,8 @@ int btrfs_insert_file_extent(struct btrfs_trans_handle *trans, struct extent_buffer *leaf; path = btrfs_alloc_path(); - BUG_ON(!path); + if (!path) + return -ENOMEM; file_key.objectid = objectid; file_key.offset = pos; btrfs_set_key_type(&file_key, BTRFS_EXTENT_DATA_KEY); diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c index c56eb590917..c05a08f4c41 100644 --- a/fs/btrfs/inode-map.c +++ b/fs/btrfs/inode-map.c @@ -30,7 +30,8 @@ int btrfs_find_highest_inode(struct btrfs_root *root, u64 *objectid) int slot; path = btrfs_alloc_path(); - BUG_ON(!path); + if (!path) + return -ENOMEM; search_key.objectid = BTRFS_LAST_FREE_OBJECTID; search_key.type = -1; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index ad9b8c0e930..88d3cb2eaf7 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -2350,12 +2350,15 @@ static noinline long btrfs_ioctl_start_sync(struct file *file, void __user *argp struct btrfs_root *root = BTRFS_I(file->f_dentry->d_inode)->root; struct btrfs_trans_handle *trans; u64 transid; + int ret; trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) return PTR_ERR(trans); transid = trans->transid; - btrfs_commit_transaction_async(trans, root, 0); + ret = btrfs_commit_transaction_async(trans, root, 0); + if (ret) + return ret; if (argp) if (copy_to_user(argp, &transid, sizeof(transid))) diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index 6a1086e83ff..29b2d7c930e 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -88,7 +88,8 @@ int btrfs_find_last_root(struct btrfs_root *root, u64 objectid, search_key.offset = (u64)-1; path = btrfs_alloc_path(); - BUG_ON(!path); + if (!path) + return -ENOMEM; ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0); if (ret < 0) goto out; @@ -332,7 +333,8 @@ int btrfs_del_root(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *leaf; path = btrfs_alloc_path(); - BUG_ON(!path); + if (!path) + return -ENOMEM; ret = btrfs_search_slot(trans, root, key, path, -1, 1); if (ret < 0) goto out; diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 5b4bc685bb0..ce48eb59d61 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -57,7 +57,8 @@ static noinline int join_transaction(struct btrfs_root *root) if (!cur_trans) { cur_trans = kmem_cache_alloc(btrfs_transaction_cachep, GFP_NOFS); - BUG_ON(!cur_trans); + if (!cur_trans) + return -ENOMEM; root->fs_info->generation++; cur_trans->num_writers = 1; cur_trans->num_joined = 0; @@ -195,7 +196,11 @@ again: wait_current_trans(root); ret = join_transaction(root); - BUG_ON(ret); + if (ret < 0) { + if (type != TRANS_JOIN_NOLOCK) + mutex_unlock(&root->fs_info->trans_mutex); + return ERR_PTR(ret); + } cur_trans = root->fs_info->running_transaction; cur_trans->use_count++; @@ -1156,7 +1161,8 @@ int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans, struct btrfs_transaction *cur_trans; ac = kmalloc(sizeof(*ac), GFP_NOFS); - BUG_ON(!ac); + if (!ac) + return -ENOMEM; INIT_DELAYED_WORK(&ac->work, do_async_commit); ac->root = root; diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 429cfcfadf9..f9425e33e35 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -1828,7 +1828,8 @@ static int walk_log_tree(struct btrfs_trans_handle *trans, int orig_level; path = btrfs_alloc_path(); - BUG_ON(!path); + if (!path) + return -ENOMEM; level = btrfs_header_level(log->node); orig_level = level; @@ -3114,9 +3115,11 @@ int btrfs_recover_log_trees(struct btrfs_root *log_root_tree) .stage = 0, }; - fs_info->log_root_recovering = 1; path = btrfs_alloc_path(); - BUG_ON(!path); + if (!path) + return -ENOMEM; + + fs_info->log_root_recovering = 1; trans = btrfs_start_transaction(fs_info->tree_root, 0); BUG_ON(IS_ERR(trans)); @@ -3124,7 +3127,8 @@ int btrfs_recover_log_trees(struct btrfs_root *log_root_tree) wc.trans = trans; wc.pin = 1; - walk_log_tree(trans, log_root_tree, &wc); + ret = walk_log_tree(trans, log_root_tree, &wc); + BUG_ON(ret); again: key.objectid = BTRFS_TREE_LOG_OBJECTID; @@ -3148,8 +3152,7 @@ again: log = btrfs_read_fs_root_no_radix(log_root_tree, &found_key); - BUG_ON(!log); - + BUG_ON(IS_ERR(log)); tmp_key.objectid = found_key.offset; tmp_key.type = BTRFS_ROOT_ITEM_KEY; -- cgit v1.2.3-70-g09d2 From 7e75bf3ff3a716d7b21d8fb43bf823115801c1e9 Mon Sep 17 00:00:00 2001 From: David Sterba Date: Fri, 18 Mar 2011 22:56:43 +0000 Subject: btrfs: properly access unaligned checksum buffer On Fri, Mar 18, 2011 at 11:56:53AM -0400, Chris Mason wrote: > Thanks for fielding this one. Does put_unaligned_le32 optimize away on > platforms with efficient access? It would be great if we didn't need > the #ifdef. (quicktest: assembly output is same for put_unaligned_le32 and direct assignment on my x86_64) I was originally following examples in Documentation/unaligned-memory-access.txt. From other code it seems to me that the define CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS is intended for larger portions of code. Macros/wrappers for {put,get}_unaligned* are chosen via arch//include/asm/unaligned.h accordingly, therefore it's safe to use put_unaligned_le32 without the ifdef. dave Signed-off-by: Chris Mason --- fs/btrfs/disk-io.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 00cbb41af66..2bdb124333a 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -29,6 +29,7 @@ #include #include #include +#include #include "compat.h" #include "ctree.h" #include "disk-io.h" @@ -198,7 +199,7 @@ u32 btrfs_csum_data(struct btrfs_root *root, char *data, u32 seed, size_t len) void btrfs_csum_final(u32 crc, char *result) { - *(__le32 *)result = ~cpu_to_le32(crc); + put_unaligned_le32(~crc, result); } /* -- cgit v1.2.3-70-g09d2 From 75e7cb7fe0c391561bd3af36515be3f3c64a04c6 Mon Sep 17 00:00:00 2001 From: Liu Bo Date: Tue, 22 Mar 2011 10:12:20 +0000 Subject: Btrfs: Per file/directory controls for COW and compression Data compression and data cow are controlled across the entire FS by mount options right now. ioctls are needed to set this on a per file or per directory basis. This has been proposed previously, but VFS developers wanted us to use generic ioctls rather than btrfs-specific ones. According to Chris's comment, there should be just one true compression method(probably LZO) stored in the super. However, before this, we would wait for that one method is stable enough to be adopted into the super. So I list it as a long term goal, and just store it in ram today. After applying this patch, we can use the generic "FS_IOC_SETFLAGS" ioctl to control file and directory's datacow and compression attribute. NOTE: - The compression type is selected by such rules: If we mount btrfs with compress options, ie, zlib/lzo, the type is it. Otherwise, we'll use the default compress type (zlib today). v1->v2: - rebase to the latest btrfs. v2->v3: - fix a problem, i.e. when a file is set NOCOW via mount option, then this NOCOW will be screwed by inheritance from parent directory. Signed-off-by: Liu Bo Signed-off-by: Chris Mason --- fs/btrfs/ctree.h | 1 + fs/btrfs/disk-io.c | 6 ++++++ fs/btrfs/inode.c | 31 ++++++++++++++++++++++++++++--- fs/btrfs/ioctl.c | 41 +++++++++++++++++++++++++++++++++++++---- 4 files changed, 72 insertions(+), 7 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 9d0f59142af..8302ecd4197 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1282,6 +1282,7 @@ struct btrfs_root { #define BTRFS_INODE_NODUMP (1 << 8) #define BTRFS_INODE_NOATIME (1 << 9) #define BTRFS_INODE_DIRSYNC (1 << 10) +#define BTRFS_INODE_COMPRESS (1 << 11) /* some macros to generate set/get funcs for the struct fields. This * assumes there is a lefoo_to_cpu for every type, so lets make a simple diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 2bdb124333a..125639ddaff 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1854,6 +1854,12 @@ struct btrfs_root *open_ctree(struct super_block *sb, btrfs_check_super_valid(fs_info, sb->s_flags & MS_RDONLY); + /* + * In the long term, we'll store the compression type in the super + * block, and it'll be used for per file compression control. + */ + fs_info->compress_type = BTRFS_COMPRESS_ZLIB; + ret = btrfs_parse_options(tree_root, options); if (ret) { err = ret; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index eaa27148419..7a7a202b82a 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -384,7 +384,8 @@ again: */ if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NOCOMPRESS) && (btrfs_test_opt(root, COMPRESS) || - (BTRFS_I(inode)->force_compress))) { + (BTRFS_I(inode)->force_compress) || + (BTRFS_I(inode)->flags & BTRFS_INODE_COMPRESS))) { WARN_ON(pages); pages = kzalloc(sizeof(struct page *) * nr_pages, GFP_NOFS); @@ -1256,7 +1257,8 @@ static int run_delalloc_range(struct inode *inode, struct page *locked_page, ret = run_delalloc_nocow(inode, locked_page, start, end, page_started, 0, nr_written); else if (!btrfs_test_opt(root, COMPRESS) && - !(BTRFS_I(inode)->force_compress)) + !(BTRFS_I(inode)->force_compress) && + !(BTRFS_I(inode)->flags & BTRFS_INODE_COMPRESS)) ret = cow_file_range(inode, locked_page, start, end, page_started, nr_written, 1); else @@ -4584,7 +4586,8 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans, if ((mode & S_IFREG)) { if (btrfs_test_opt(root, NODATASUM)) BTRFS_I(inode)->flags |= BTRFS_INODE_NODATASUM; - if (btrfs_test_opt(root, NODATACOW)) + if (btrfs_test_opt(root, NODATACOW) || + (BTRFS_I(dir)->flags & BTRFS_INODE_NODATACOW)) BTRFS_I(inode)->flags |= BTRFS_INODE_NODATACOW; } @@ -6866,6 +6869,26 @@ static int btrfs_getattr(struct vfsmount *mnt, return 0; } +/* + * If a file is moved, it will inherit the cow and compression flags of the new + * directory. + */ +static void fixup_inode_flags(struct inode *dir, struct inode *inode) +{ + struct btrfs_inode *b_dir = BTRFS_I(dir); + struct btrfs_inode *b_inode = BTRFS_I(inode); + + if (b_dir->flags & BTRFS_INODE_NODATACOW) + b_inode->flags |= BTRFS_INODE_NODATACOW; + else + b_inode->flags &= ~BTRFS_INODE_NODATACOW; + + if (b_dir->flags & BTRFS_INODE_COMPRESS) + b_inode->flags |= BTRFS_INODE_COMPRESS; + else + b_inode->flags &= ~BTRFS_INODE_COMPRESS; +} + static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry) { @@ -6999,6 +7022,8 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, } } + fixup_inode_flags(new_dir, old_inode); + ret = btrfs_add_link(trans, new_dir, old_inode, new_dentry->d_name.name, new_dentry->d_name.len, 0, index); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 88d3cb2eaf7..32c980ae0f1 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -138,6 +138,24 @@ static int btrfs_ioctl_getflags(struct file *file, void __user *arg) return 0; } +static int check_flags(unsigned int flags) +{ + if (flags & ~(FS_IMMUTABLE_FL | FS_APPEND_FL | \ + FS_NOATIME_FL | FS_NODUMP_FL | \ + FS_SYNC_FL | FS_DIRSYNC_FL | \ + FS_NOCOMP_FL | FS_COMPR_FL | \ + FS_NOCOW_FL | FS_COW_FL)) + return -EOPNOTSUPP; + + if ((flags & FS_NOCOMP_FL) && (flags & FS_COMPR_FL)) + return -EINVAL; + + if ((flags & FS_NOCOW_FL) && (flags & FS_COW_FL)) + return -EINVAL; + + return 0; +} + static int btrfs_ioctl_setflags(struct file *file, void __user *arg) { struct inode *inode = file->f_path.dentry->d_inode; @@ -153,10 +171,9 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) if (copy_from_user(&flags, arg, sizeof(flags))) return -EFAULT; - if (flags & ~(FS_IMMUTABLE_FL | FS_APPEND_FL | \ - FS_NOATIME_FL | FS_NODUMP_FL | \ - FS_SYNC_FL | FS_DIRSYNC_FL)) - return -EOPNOTSUPP; + ret = check_flags(flags); + if (ret) + return ret; if (!is_owner_or_cap(inode)) return -EACCES; @@ -201,6 +218,22 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) else ip->flags &= ~BTRFS_INODE_DIRSYNC; + /* + * The COMPRESS flag can only be changed by users, while the NOCOMPRESS + * flag may be changed automatically if compression code won't make + * things smaller. + */ + if (flags & FS_NOCOMP_FL) { + ip->flags &= ~BTRFS_INODE_COMPRESS; + ip->flags |= BTRFS_INODE_NOCOMPRESS; + } else if (flags & FS_COMPR_FL) { + ip->flags |= BTRFS_INODE_COMPRESS; + ip->flags &= ~BTRFS_INODE_NOCOMPRESS; + } + if (flags & FS_NOCOW_FL) + ip->flags |= BTRFS_INODE_NODATACOW; + else if (flags & FS_COW_FL) + ip->flags &= ~BTRFS_INODE_NODATACOW; trans = btrfs_join_transaction(root, 1); BUG_ON(IS_ERR(trans)); -- cgit v1.2.3-70-g09d2 From 5378e60734f5b7bfe1b43dc191aaf6131c1befe7 Mon Sep 17 00:00:00 2001 From: Li Dongyang Date: Thu, 24 Mar 2011 10:24:27 +0000 Subject: Btrfs: adjust btrfs_discard_extent() return errors and trimmed bytes Callers of btrfs_discard_extent() should check if we are mounted with -o discard, as we want to make fitrim to work even the fs is not mounted with -o discard. Also we should use REQ_DISCARD to map the free extent to get a full mapping, last we only return errors if 1. the error is not a EOPNOTSUPP 2. no device supports discard Signed-off-by: Li Dongyang Signed-off-by: Chris Mason --- fs/btrfs/ctree.h | 2 +- fs/btrfs/disk-io.c | 5 ++++- fs/btrfs/extent-tree.c | 43 ++++++++++++++++++++++++++----------------- 3 files changed, 31 insertions(+), 19 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 9e21176cdf5..a18b7bc2b22 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2229,7 +2229,7 @@ u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo); int btrfs_error_unpin_extent_range(struct btrfs_root *root, u64 start, u64 end); int btrfs_error_discard_extent(struct btrfs_root *root, u64 bytenr, - u64 num_bytes); + u64 num_bytes, u64 *actual_bytes); int btrfs_force_chunk_alloc(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 type); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 125639ddaff..8ecc5419d8b 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3054,7 +3054,10 @@ static int btrfs_destroy_pinned_extent(struct btrfs_root *root, break; /* opt_discard */ - ret = btrfs_error_discard_extent(root, start, end + 1 - start); + if (btrfs_test_opt(root, DISCARD)) + ret = btrfs_error_discard_extent(root, start, + end + 1 - start, + NULL); clear_extent_dirty(unpin, start, end, GFP_NOFS); btrfs_error_unpin_extent_range(root, start, end); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 0671f5b77eb..e990d2d1ba4 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -1738,39 +1738,45 @@ static int remove_extent_backref(struct btrfs_trans_handle *trans, return ret; } -static void btrfs_issue_discard(struct block_device *bdev, +static int btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len) { - blkdev_issue_discard(bdev, start >> 9, len >> 9, GFP_NOFS, 0); + return blkdev_issue_discard(bdev, start >> 9, len >> 9, GFP_NOFS, 0); } static int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr, - u64 num_bytes) + u64 num_bytes, u64 *actual_bytes) { int ret; - u64 map_length = num_bytes; + u64 discarded_bytes = 0; struct btrfs_multi_bio *multi = NULL; - if (!btrfs_test_opt(root, DISCARD)) - return 0; /* Tell the block device(s) that the sectors can be discarded */ - ret = btrfs_map_block(&root->fs_info->mapping_tree, READ, - bytenr, &map_length, &multi, 0); + ret = btrfs_map_block(&root->fs_info->mapping_tree, REQ_DISCARD, + bytenr, &num_bytes, &multi, 0); if (!ret) { struct btrfs_bio_stripe *stripe = multi->stripes; int i; - if (map_length > num_bytes) - map_length = num_bytes; for (i = 0; i < multi->num_stripes; i++, stripe++) { - btrfs_issue_discard(stripe->dev->bdev, - stripe->physical, - map_length); + ret = btrfs_issue_discard(stripe->dev->bdev, + stripe->physical, + stripe->length); + if (!ret) + discarded_bytes += stripe->length; + else if (ret != -EOPNOTSUPP) + break; } kfree(multi); } + if (discarded_bytes && ret == -EOPNOTSUPP) + ret = 0; + + if (actual_bytes) + *actual_bytes = discarded_bytes; + return ret; } @@ -4371,7 +4377,9 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans, if (ret) break; - ret = btrfs_discard_extent(root, start, end + 1 - start); + if (btrfs_test_opt(root, DISCARD)) + ret = btrfs_discard_extent(root, start, + end + 1 - start, NULL); clear_extent_dirty(unpin, start, end, GFP_NOFS); unpin_extent_range(root, start, end); @@ -5427,7 +5435,8 @@ int btrfs_free_reserved_extent(struct btrfs_root *root, u64 start, u64 len) return -ENOSPC; } - ret = btrfs_discard_extent(root, start, len); + if (btrfs_test_opt(root, DISCARD)) + ret = btrfs_discard_extent(root, start, len, NULL); btrfs_add_free_space(cache, start, len); btrfs_update_reserved_bytes(cache, len, 0, 1); @@ -8765,7 +8774,7 @@ int btrfs_error_unpin_extent_range(struct btrfs_root *root, u64 start, u64 end) } int btrfs_error_discard_extent(struct btrfs_root *root, u64 bytenr, - u64 num_bytes) + u64 num_bytes, u64 *actual_bytes) { - return btrfs_discard_extent(root, bytenr, num_bytes); + return btrfs_discard_extent(root, bytenr, num_bytes, actual_bytes); } -- cgit v1.2.3-70-g09d2 From c59021f846881a957ac5afe456d0f59d6a517b61 Mon Sep 17 00:00:00 2001 From: liubo Date: Mon, 7 Mar 2011 02:13:14 +0000 Subject: Btrfs: fix OOPS of empty filesystem after balance btrfs will remove unused block groups after balance. When a empty filesystem is balanced, the block group with tag "DATA" may be dropped, and after umount and mount again, it will not find "DATA" space_info and lead to OOPS. So we initial the necessary space_infos(DATA, SYSTEM, METADATA) to avoid OOPS. Reported-by: Daniel J Blueman Signed-off-by: Liu Bo Signed-off-by: Chris Mason --- fs/btrfs/ctree.h | 1 + fs/btrfs/disk-io.c | 6 ++++++ fs/btrfs/extent-tree.c | 23 +++++++++++++++++++++++ 3 files changed, 30 insertions(+) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 93a0191aded..d47ce830785 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2234,6 +2234,7 @@ int btrfs_force_chunk_alloc(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 type); int btrfs_trim_fs(struct btrfs_root *root, struct fstrim_range *range); +int btrfs_init_space_info(struct btrfs_fs_info *fs_info); /* ctree.c */ int btrfs_bin_search(struct extent_buffer *eb, struct btrfs_key *key, int level, int *slot); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 8ecc5419d8b..b3fc8475870 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2065,6 +2065,12 @@ struct btrfs_root *open_ctree(struct super_block *sb, fs_info->metadata_alloc_profile = (u64)-1; fs_info->system_alloc_profile = fs_info->metadata_alloc_profile; + ret = btrfs_init_space_info(fs_info); + if (ret) { + printk(KERN_ERR "Failed to initial space info: %d\n", ret); + goto fail_block_groups; + } + ret = btrfs_read_block_groups(extent_root); if (ret) { printk(KERN_ERR "Failed to read block groups: %d\n", ret); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index a561060f5ff..f619c3cb13b 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -8778,6 +8778,29 @@ out: return ret; } +int btrfs_init_space_info(struct btrfs_fs_info *fs_info) +{ + struct btrfs_space_info *space_info; + int ret; + + ret = update_space_info(fs_info, BTRFS_BLOCK_GROUP_SYSTEM, 0, 0, + &space_info); + if (ret) + return ret; + + ret = update_space_info(fs_info, BTRFS_BLOCK_GROUP_METADATA, 0, 0, + &space_info); + if (ret) + return ret; + + ret = update_space_info(fs_info, BTRFS_BLOCK_GROUP_DATA, 0, 0, + &space_info); + if (ret) + return ret; + + return ret; +} + int btrfs_error_unpin_extent_range(struct btrfs_root *root, u64 start, u64 end) { return unpin_extent_range(root, start, end); -- cgit v1.2.3-70-g09d2 From 1561deda687eef0e95065f1268d680ddc5976ee7 Mon Sep 17 00:00:00 2001 From: Miao Xie Date: Sun, 27 Mar 2011 16:07:36 +0800 Subject: btrfs: fix possible deadlock by clearing __GFP_FS flag Using the GFP_HIGHUSER_MOVABLE flag to allocate the metadata's page may cause deadlock. Task1 open() ... btrfs_search_slot() ... btrfs_cow_block() ... alloc_page() wait for reclaiming shrink_slab() ... shrink_icache_memory() ... btrfs_evict_inode() ... btrfs_search_slot() If the path is locked by task1, the deadlock happens. So the btree's page cache is different with the file's page cache, it can not allocate pages by GFP_HIGHUSER_MOVABLE flag, we must clear __GFP_FS flag in GFP_HIGHUSER_MOVABLE flag. Reported-by: Itaru Kitayama Signed-off-by: Miao Xie Signed-off-by: Chris Mason --- fs/btrfs/disk-io.c | 2 ++ fs/btrfs/inode.c | 3 ++- 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index b3fc8475870..5cf3aa7b125 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1724,6 +1724,8 @@ struct btrfs_root *open_ctree(struct super_block *sb, goto fail_bdi; } + fs_info->btree_inode->i_mapping->flags &= ~__GFP_FS; + INIT_RADIX_TREE(&fs_info->fs_roots_radix, GFP_ATOMIC); INIT_LIST_HEAD(&fs_info->trans_list); INIT_LIST_HEAD(&fs_info->dead_roots); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 04babaf31a3..06274186b29 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -2536,6 +2536,8 @@ static void btrfs_read_locked_inode(struct inode *inode) BTRFS_I(inode)->flags = btrfs_inode_flags(leaf, inode_item); alloc_group_block = btrfs_inode_block_group(leaf, inode_item); + if (location.objectid == BTRFS_FREE_SPACE_OBJECTID) + inode->i_mapping->flags &= ~__GFP_FS; /* * try to precache a NULL acl entry for files that don't have @@ -4084,7 +4086,6 @@ struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location, BTRFS_I(inode)->root = root; memcpy(&BTRFS_I(inode)->location, location, sizeof(*location)); btrfs_read_locked_inode(inode); - inode_tree_add(inode); unlock_new_inode(inode); if (new) -- cgit v1.2.3-70-g09d2 From 08fe4db170b4193603d9d31f40ebaf652d07ac9c Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Mon, 28 Mar 2011 02:01:25 +0000 Subject: Btrfs: Fix uninitialized root flags for subvolumes root_item->flags and root_item->byte_limit are not initialized when a subvolume is created. This bug is not revealed until we added readonly snapshot support - now you mount a btrfs filesystem and you may find the subvolumes in it are readonly. To work around this problem, we steal a bit from root_item->inode_item->flags, and use it to indicate if those fields have been properly initialized. When we read a tree root from disk, we check if the bit is set, and if not we'll set the flag and initialize the two fields of the root item. Reported-by: Andreas Philipp Signed-off-by: Li Zefan Tested-by: Andreas Philipp cc: stable@kernel.org Signed-off-by: Chris Mason --- fs/btrfs/ctree.h | 4 ++++ fs/btrfs/disk-io.c | 4 +++- fs/btrfs/ioctl.c | 4 ++++ fs/btrfs/root-tree.c | 18 ++++++++++++++++++ fs/btrfs/transaction.c | 1 + 5 files changed, 30 insertions(+), 1 deletion(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index d47ce830785..3458b572554 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1284,6 +1284,8 @@ struct btrfs_root { #define BTRFS_INODE_DIRSYNC (1 << 10) #define BTRFS_INODE_COMPRESS (1 << 11) +#define BTRFS_INODE_ROOT_ITEM_INIT (1 << 31) + /* some macros to generate set/get funcs for the struct fields. This * assumes there is a lefoo_to_cpu for every type, so lets make a simple * one for u8: @@ -2359,6 +2361,8 @@ int btrfs_find_dead_roots(struct btrfs_root *root, u64 objectid); int btrfs_find_orphan_roots(struct btrfs_root *tree_root); int btrfs_set_root_node(struct btrfs_root_item *item, struct extent_buffer *node); +void btrfs_check_and_init_root_item(struct btrfs_root_item *item); + /* dir-item.c */ int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, const char *name, diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 5cf3aa7b125..a272bfd74ea 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1276,8 +1276,10 @@ struct btrfs_root *btrfs_read_fs_root_no_radix(struct btrfs_root *tree_root, root->commit_root = btrfs_root_node(root); BUG_ON(!root->node); out: - if (location->objectid != BTRFS_TREE_LOG_OBJECTID) + if (location->objectid != BTRFS_TREE_LOG_OBJECTID) { root->ref_cows = 1; + btrfs_check_and_init_root_item(&root->root_item); + } return root; } diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 255c7c5279c..f9c93a9ed4a 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -373,6 +373,10 @@ static noinline int create_subvol(struct btrfs_root *root, inode_item->nbytes = cpu_to_le64(root->leafsize); inode_item->mode = cpu_to_le32(S_IFDIR | 0755); + root_item.flags = 0; + root_item.byte_limit = 0; + inode_item->flags = cpu_to_le64(BTRFS_INODE_ROOT_ITEM_INIT); + btrfs_set_root_bytenr(&root_item, leaf->start); btrfs_set_root_generation(&root_item, trans->transid); btrfs_set_root_level(&root_item, 0); diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index 29b2d7c930e..6928bff62da 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -473,3 +473,21 @@ again: btrfs_free_path(path); return 0; } + +/* + * Old btrfs forgets to init root_item->flags and root_item->byte_limit + * for subvolumes. To work around this problem, we steal a bit from + * root_item->inode_item->flags, and use it to indicate if those fields + * have been properly initialized. + */ +void btrfs_check_and_init_root_item(struct btrfs_root_item *root_item) +{ + u64 inode_flags = le64_to_cpu(root_item->inode.flags); + + if (!(inode_flags & BTRFS_INODE_ROOT_ITEM_INIT)) { + inode_flags |= BTRFS_INODE_ROOT_ITEM_INIT; + root_item->inode.flags = cpu_to_le64(inode_flags); + root_item->flags = 0; + root_item->byte_limit = 0; + } +} diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index d01cc249a8d..5b158da7e0b 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -976,6 +976,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, record_root_in_trans(trans, root); btrfs_set_root_last_snapshot(&root->root_item, trans->transid); memcpy(new_root_item, &root->root_item, sizeof(*new_root_item)); + btrfs_check_and_init_root_item(new_root_item); root_flags = btrfs_root_flags(new_root_item); if (pending->readonly) -- cgit v1.2.3-70-g09d2 From 13c5a93e7005d7dae0b6d070d25203593e692d13 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Mon, 11 Apr 2011 15:45:29 -0400 Subject: Btrfs: avoid taking the trans_mutex in btrfs_end_transaction I've been working on making our O_DIRECT latency not suck and I noticed we were taking the trans_mutex in btrfs_end_transaction. So to do this we convert num_writers and use_count to atomic_t's and just decrement them in btrfs_end_transaction. Instead of deleting the transaction from the trans list in put_transaction we do that in btrfs_commit_transaction() since that's the only time it actually needs to be removed from the list. Thanks, Signed-off-by: Josef Bacik --- fs/btrfs/disk-io.c | 2 +- fs/btrfs/transaction.c | 37 ++++++++++++++++--------------------- fs/btrfs/transaction.h | 4 ++-- 3 files changed, 19 insertions(+), 24 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index a272bfd74ea..ef6865c17cd 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3136,7 +3136,7 @@ static int btrfs_cleanup_transaction(struct btrfs_root *root) btrfs_destroy_pinned_extent(root, root->fs_info->pinned_extents); - t->use_count = 0; + atomic_set(&t->use_count, 0); list_del_init(&t->list); memset(t, 0, sizeof(*t)); kmem_cache_free(btrfs_transaction_cachep, t); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 4583008217e..c571734d5e5 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -32,10 +32,8 @@ static noinline void put_transaction(struct btrfs_transaction *transaction) { - WARN_ON(transaction->use_count == 0); - transaction->use_count--; - if (transaction->use_count == 0) { - list_del_init(&transaction->list); + WARN_ON(atomic_read(&transaction->use_count) == 0); + if (atomic_dec_and_test(&transaction->use_count)) { memset(transaction, 0, sizeof(*transaction)); kmem_cache_free(btrfs_transaction_cachep, transaction); } @@ -60,14 +58,14 @@ static noinline int join_transaction(struct btrfs_root *root) if (!cur_trans) return -ENOMEM; root->fs_info->generation++; - cur_trans->num_writers = 1; + atomic_set(&cur_trans->num_writers, 1); cur_trans->num_joined = 0; cur_trans->transid = root->fs_info->generation; init_waitqueue_head(&cur_trans->writer_wait); init_waitqueue_head(&cur_trans->commit_wait); cur_trans->in_commit = 0; cur_trans->blocked = 0; - cur_trans->use_count = 1; + atomic_set(&cur_trans->use_count, 1); cur_trans->commit_done = 0; cur_trans->start_time = get_seconds(); @@ -88,7 +86,7 @@ static noinline int join_transaction(struct btrfs_root *root) root->fs_info->running_transaction = cur_trans; spin_unlock(&root->fs_info->new_trans_lock); } else { - cur_trans->num_writers++; + atomic_inc(&cur_trans->num_writers); cur_trans->num_joined++; } @@ -145,7 +143,7 @@ static void wait_current_trans(struct btrfs_root *root) cur_trans = root->fs_info->running_transaction; if (cur_trans && cur_trans->blocked) { DEFINE_WAIT(wait); - cur_trans->use_count++; + atomic_inc(&cur_trans->use_count); while (1) { prepare_to_wait(&root->fs_info->transaction_wait, &wait, TASK_UNINTERRUPTIBLE); @@ -205,7 +203,7 @@ again: } cur_trans = root->fs_info->running_transaction; - cur_trans->use_count++; + atomic_inc(&cur_trans->use_count); if (type != TRANS_JOIN_NOLOCK) mutex_unlock(&root->fs_info->trans_mutex); @@ -336,7 +334,7 @@ int btrfs_wait_for_commit(struct btrfs_root *root, u64 transid) goto out_unlock; /* nothing committing|committed */ } - cur_trans->use_count++; + atomic_inc(&cur_trans->use_count); mutex_unlock(&root->fs_info->trans_mutex); wait_for_commit(root, cur_trans); @@ -466,18 +464,14 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans, wake_up_process(info->transaction_kthread); } - if (lock) - mutex_lock(&info->trans_mutex); WARN_ON(cur_trans != info->running_transaction); - WARN_ON(cur_trans->num_writers < 1); - cur_trans->num_writers--; + WARN_ON(atomic_read(&cur_trans->num_writers) < 1); + atomic_dec(&cur_trans->num_writers); smp_mb(); if (waitqueue_active(&cur_trans->writer_wait)) wake_up(&cur_trans->writer_wait); put_transaction(cur_trans); - if (lock) - mutex_unlock(&info->trans_mutex); if (current->journal_info == trans) current->journal_info = NULL; @@ -1187,7 +1181,7 @@ int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans, /* take transaction reference */ mutex_lock(&root->fs_info->trans_mutex); cur_trans = trans->transaction; - cur_trans->use_count++; + atomic_inc(&cur_trans->use_count); mutex_unlock(&root->fs_info->trans_mutex); btrfs_end_transaction(trans, root); @@ -1246,7 +1240,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, mutex_lock(&root->fs_info->trans_mutex); if (cur_trans->in_commit) { - cur_trans->use_count++; + atomic_inc(&cur_trans->use_count); mutex_unlock(&root->fs_info->trans_mutex); btrfs_end_transaction(trans, root); @@ -1268,7 +1262,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, prev_trans = list_entry(cur_trans->list.prev, struct btrfs_transaction, list); if (!prev_trans->commit_done) { - prev_trans->use_count++; + atomic_inc(&prev_trans->use_count); mutex_unlock(&root->fs_info->trans_mutex); wait_for_commit(root, prev_trans); @@ -1309,14 +1303,14 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, TASK_UNINTERRUPTIBLE); smp_mb(); - if (cur_trans->num_writers > 1) + if (atomic_read(&cur_trans->num_writers) > 1) schedule_timeout(MAX_SCHEDULE_TIMEOUT); else if (should_grow) schedule_timeout(1); mutex_lock(&root->fs_info->trans_mutex); finish_wait(&cur_trans->writer_wait, &wait); - } while (cur_trans->num_writers > 1 || + } while (atomic_read(&cur_trans->num_writers) > 1 || (should_grow && cur_trans->num_joined != joined)); ret = create_pending_snapshots(trans, root->fs_info); @@ -1403,6 +1397,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, wake_up(&cur_trans->commit_wait); + list_del_init(&cur_trans->list); put_transaction(cur_trans); put_transaction(cur_trans); diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 229a594cacd..e441acc6c58 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -27,11 +27,11 @@ struct btrfs_transaction { * total writers in this transaction, it must be zero before the * transaction can end */ - unsigned long num_writers; + atomic_t num_writers; unsigned long num_joined; int in_commit; - int use_count; + atomic_t use_count; int commit_done; int blocked; struct list_head list; -- cgit v1.2.3-70-g09d2