diff options
author | Artem Bityutskiy <Artem.Bityutskiy@nokia.com> | 2009-09-21 12:09:22 +0300 |
---|---|---|
committer | Artem Bityutskiy <Artem.Bityutskiy@nokia.com> | 2009-09-21 12:09:22 +0300 |
commit | 7cce2f4cb7f5f641f78c8e3eea4e7b1b96cb71c0 (patch) | |
tree | b064d077928cf224660ab1e1841cdab2c9fd8b08 /fs/fs-writeback.c | |
parent | e055f7e873d900925c222cf2d1ec955af4a9ca90 (diff) | |
parent | ebc79c4f8da0f92efa968e0328f32334a2ce80cf (diff) |
Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6 into linux-next
Conflicts:
fs/ubifs/super.c
Merge the upstream tree in order to resolve a conflict with the
per-bdi writeback changes from the linux-2.6-block tree.
Diffstat (limited to 'fs/fs-writeback.c')
-rw-r--r-- | fs/fs-writeback.c | 1104 |
1 files changed, 763 insertions, 341 deletions
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index c54226be529..8e1e5e19d21 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -19,171 +19,245 @@ #include <linux/sched.h> #include <linux/fs.h> #include <linux/mm.h> +#include <linux/kthread.h> +#include <linux/freezer.h> #include <linux/writeback.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/buffer_head.h> #include "internal.h" +#define inode_to_bdi(inode) ((inode)->i_mapping->backing_dev_info) -/** - * writeback_acquire - attempt to get exclusive writeback access to a device - * @bdi: the device's backing_dev_info structure - * - * It is a waste of resources to have more than one pdflush thread blocked on - * a single request queue. Exclusion at the request_queue level is obtained - * via a flag in the request_queue's backing_dev_info.state. - * - * Non-request_queue-backed address_spaces will share default_backing_dev_info, - * unless they implement their own. Which is somewhat inefficient, as this - * may prevent concurrent writeback against multiple devices. +/* + * We don't actually have pdflush, but this one is exported though /proc... + */ +int nr_pdflush_threads; + +/* + * Passed into wb_writeback(), essentially a subset of writeback_control + */ +struct wb_writeback_args { + long nr_pages; + struct super_block *sb; + enum writeback_sync_modes sync_mode; + int for_kupdate; + int range_cyclic; +}; + +/* + * Work items for the bdi_writeback threads */ -static int writeback_acquire(struct backing_dev_info *bdi) +struct bdi_work { + struct list_head list; /* pending work list */ + struct rcu_head rcu_head; /* for RCU free/clear of work */ + + unsigned long seen; /* threads that have seen this work */ + atomic_t pending; /* number of threads still to do work */ + + struct wb_writeback_args args; /* writeback arguments */ + + unsigned long state; /* flag bits, see WS_* */ +}; + +enum { + WS_USED_B = 0, + WS_ONSTACK_B, +}; + +#define WS_USED (1 << WS_USED_B) +#define WS_ONSTACK (1 << WS_ONSTACK_B) + +static inline bool bdi_work_on_stack(struct bdi_work *work) +{ + return test_bit(WS_ONSTACK_B, &work->state); +} + +static inline void bdi_work_init(struct bdi_work *work, + struct wb_writeback_args *args) { - return !test_and_set_bit(BDI_pdflush, &bdi->state); + INIT_RCU_HEAD(&work->rcu_head); + work->args = *args; + work->state = WS_USED; } /** * writeback_in_progress - determine whether there is writeback in progress * @bdi: the device's backing_dev_info structure. * - * Determine whether there is writeback in progress against a backing device. + * Determine whether there is writeback waiting to be handled against a + * backing device. */ int writeback_in_progress(struct backing_dev_info *bdi) { - return test_bit(BDI_pdflush, &bdi->state); + return !list_empty(&bdi->work_list); } -/** - * writeback_release - relinquish exclusive writeback access against a device. - * @bdi: the device's backing_dev_info structure - */ -static void writeback_release(struct backing_dev_info *bdi) +static void bdi_work_clear(struct bdi_work *work) { - BUG_ON(!writeback_in_progress(bdi)); - clear_bit(BDI_pdflush, &bdi->state); + clear_bit(WS_USED_B, &work->state); + smp_mb__after_clear_bit(); + /* + * work can have disappeared at this point. bit waitq functions + * should be able to tolerate this, provided bdi_sched_wait does + * not dereference it's pointer argument. + */ + wake_up_bit(&work->state, WS_USED_B); } -static noinline void block_dump___mark_inode_dirty(struct inode *inode) +static void bdi_work_free(struct rcu_head *head) { - if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev")) { - struct dentry *dentry; - const char *name = "?"; + struct bdi_work *work = container_of(head, struct bdi_work, rcu_head); - dentry = d_find_alias(inode); - if (dentry) { - spin_lock(&dentry->d_lock); - name = (const char *) dentry->d_name.name; - } - printk(KERN_DEBUG - "%s(%d): dirtied inode %lu (%s) on %s\n", - current->comm, task_pid_nr(current), inode->i_ino, - name, inode->i_sb->s_id); - if (dentry) { - spin_unlock(&dentry->d_lock); - dput(dentry); - } - } + if (!bdi_work_on_stack(work)) + kfree(work); + else + bdi_work_clear(work); } -/** - * __mark_inode_dirty - internal function - * @inode: inode to mark - * @flags: what kind of dirty (i.e. I_DIRTY_SYNC) - * Mark an inode as dirty. Callers should use mark_inode_dirty or - * mark_inode_dirty_sync. - * - * Put the inode on the super block's dirty list. - * - * CAREFUL! We mark it dirty unconditionally, but move it onto the - * dirty list only if it is hashed or if it refers to a blockdev. - * If it was not hashed, it will never be added to the dirty list - * even if it is later hashed, as it will have been marked dirty already. - * - * In short, make sure you hash any inodes _before_ you start marking - * them dirty. - * - * This function *must* be atomic for the I_DIRTY_PAGES case - - * set_page_dirty() is called under spinlock in several places. - * - * Note that for blockdevs, inode->dirtied_when represents the dirtying time of - * the block-special inode (/dev/hda1) itself. And the ->dirtied_when field of - * the kernel-internal blockdev inode represents the dirtying time of the - * blockdev's pages. This is why for I_DIRTY_PAGES we always use - * page->mapping->host, so the page-dirtying time is recorded in the internal - * blockdev inode. - */ -void __mark_inode_dirty(struct inode *inode, int flags) +static void wb_work_complete(struct bdi_work *work) { - struct super_block *sb = inode->i_sb; + const enum writeback_sync_modes sync_mode = work->args.sync_mode; + int onstack = bdi_work_on_stack(work); /* - * Don't do this for I_DIRTY_PAGES - that doesn't actually - * dirty the inode itself + * For allocated work, we can clear the done/seen bit right here. + * For on-stack work, we need to postpone both the clear and free + * to after the RCU grace period, since the stack could be invalidated + * as soon as bdi_work_clear() has done the wakeup. */ - if (flags & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) { - if (sb->s_op->dirty_inode) - sb->s_op->dirty_inode(inode); - } + if (!onstack) + bdi_work_clear(work); + if (sync_mode == WB_SYNC_NONE || onstack) + call_rcu(&work->rcu_head, bdi_work_free); +} +static void wb_clear_pending(struct bdi_writeback *wb, struct bdi_work *work) +{ /* - * make sure that changes are seen by all cpus before we test i_state - * -- mikulas + * The caller has retrieved the work arguments from this work, + * drop our reference. If this is the last ref, delete and free it */ - smp_mb(); + if (atomic_dec_and_test(&work->pending)) { + struct backing_dev_info *bdi = wb->bdi; - /* avoid the locking if we can */ - if ((inode->i_state & flags) == flags) - return; + spin_lock(&bdi->wb_lock); + list_del_rcu(&work->list); + spin_unlock(&bdi->wb_lock); - if (unlikely(block_dump)) - block_dump___mark_inode_dirty(inode); + wb_work_complete(work); + } +} - spin_lock(&inode_lock); - if ((inode->i_state & flags) != flags) { - const int was_dirty = inode->i_state & I_DIRTY; +static void bdi_queue_work(struct backing_dev_info *bdi, struct bdi_work *work) +{ + work->seen = bdi->wb_mask; + BUG_ON(!work->seen); + atomic_set(&work->pending, bdi->wb_cnt); + BUG_ON(!bdi->wb_cnt); - inode->i_state |= flags; + /* + * list_add_tail_rcu() contains the necessary barriers to + * make sure the above stores are seen before the item is + * noticed on the list + */ + spin_lock(&bdi->wb_lock); + list_add_tail_rcu(&work->list, &bdi->work_list); + spin_unlock(&bdi->wb_lock); - /* - * If the inode is being synced, just update its dirty state. - * The unlocker will place the inode on the appropriate - * superblock list, based upon its state. - */ - if (inode->i_state & I_SYNC) - goto out; + /* + * If the default thread isn't there, make sure we add it. When + * it gets created and wakes up, we'll run this work. + */ + if (unlikely(list_empty_careful(&bdi->wb_list))) + wake_up_process(default_backing_dev_info.wb.task); + else { + struct bdi_writeback *wb = &bdi->wb; - /* - * Only add valid (hashed) inodes to the superblock's - * dirty list. Add blockdev inodes as well. - */ - if (!S_ISBLK(inode->i_mode)) { - if (hlist_unhashed(&inode->i_hash)) - goto out; - } - if (inode->i_state & (I_FREEING|I_CLEAR)) - goto out; + if (wb->task) + wake_up_process(wb->task); + } +} - /* - * If the inode was already on s_dirty/s_io/s_more_io, don't - * reposition it (that would break s_dirty time-ordering). - */ - if (!was_dirty) { - inode->dirtied_when = jiffies; - list_move(&inode->i_list, &sb->s_dirty); - } +/* + * Used for on-stack allocated work items. The caller needs to wait until + * the wb threads have acked the work before it's safe to continue. + */ +static void bdi_wait_on_work_clear(struct bdi_work *work) +{ + wait_on_bit(&work->state, WS_USED_B, bdi_sched_wait, + TASK_UNINTERRUPTIBLE); +} + +static void bdi_alloc_queue_work(struct backing_dev_info *bdi, + struct wb_writeback_args *args) +{ + struct bdi_work *work; + + /* + * This is WB_SYNC_NONE writeback, so if allocation fails just + * wakeup the thread for old dirty data writeback + */ + work = kmalloc(sizeof(*work), GFP_ATOMIC); + if (work) { + bdi_work_init(work, args); + bdi_queue_work(bdi, work); + } else { + struct bdi_writeback *wb = &bdi->wb; + + if (wb->task) + wake_up_process(wb->task); } -out: - spin_unlock(&inode_lock); } -EXPORT_SYMBOL(__mark_inode_dirty); +/** + * bdi_sync_writeback - start and wait for writeback + * @bdi: the backing device to write from + * @sb: write inodes from this super_block + * + * Description: + * This does WB_SYNC_ALL data integrity writeback and waits for the + * IO to complete. Callers must hold the sb s_umount semaphore for + * reading, to avoid having the super disappear before we are done. + */ +static void bdi_sync_writeback(struct backing_dev_info *bdi, + struct super_block *sb) +{ + struct wb_writeback_args args = { + .sb = sb, + .sync_mode = WB_SYNC_ALL, + .nr_pages = LONG_MAX, + .range_cyclic = 0, + }; + struct bdi_work work; -static int write_inode(struct inode *inode, int sync) + bdi_work_init(&work, &args); + work.state |= WS_ONSTACK; + + bdi_queue_work(bdi, &work); + bdi_wait_on_work_clear(&work); +} + +/** + * bdi_start_writeback - start writeback + * @bdi: the backing device to write from + * @nr_pages: the number of pages to write + * + * Description: + * This does WB_SYNC_NONE opportunistic writeback. The IO is only + * started when this function returns, we make no guarentees on + * completion. Caller need not hold sb s_umount semaphore. + * + */ +void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages) { - if (inode->i_sb->s_op->write_inode && !is_bad_inode(inode)) - return inode->i_sb->s_op->write_inode(inode, sync); - return 0; + struct wb_writeback_args args = { + .sync_mode = WB_SYNC_NONE, + .nr_pages = nr_pages, + .range_cyclic = 1, + }; + + bdi_alloc_queue_work(bdi, &args); } /* @@ -191,31 +265,32 @@ static int write_inode(struct inode *inode, int sync) * furthest end of its superblock's dirty-inode list. * * Before stamping the inode's ->dirtied_when, we check to see whether it is - * already the most-recently-dirtied inode on the s_dirty list. If that is + * already the most-recently-dirtied inode on the b_dirty list. If that is * the case then the inode must have been redirtied while it was being written * out and we don't reset its dirtied_when. */ static void redirty_tail(struct inode *inode) { - struct super_block *sb = inode->i_sb; + struct bdi_writeback *wb = &inode_to_bdi(inode)->wb; - if (!list_empty(&sb->s_dirty)) { - struct inode *tail_inode; + if (!list_empty(&wb->b_dirty)) { + struct inode *tail; - tail_inode = list_entry(sb->s_dirty.next, struct inode, i_list); - if (time_before(inode->dirtied_when, - tail_inode->dirtied_when)) + tail = list_entry(wb->b_dirty.next, struct inode, i_list); + if (time_before(inode->dirtied_when, tail->dirtied_when)) inode->dirtied_when = jiffies; } - list_move(&inode->i_list, &sb->s_dirty); + list_move(&inode->i_list, &wb->b_dirty); } /* - * requeue inode for re-scanning after sb->s_io list is exhausted. + * requeue inode for re-scanning after bdi->b_io list is exhausted. */ static void requeue_io(struct inode *inode) { - list_move(&inode->i_list, &inode->i_sb->s_more_io); + struct bdi_writeback *wb = &inode_to_bdi(inode)->wb; + + list_move(&inode->i_list, &wb->b_more_io); } static void inode_sync_complete(struct inode *inode) @@ -262,20 +337,18 @@ static void move_expired_inodes(struct list_head *delaying_queue, /* * Queue all expired dirty inodes for io, eldest first. */ -static void queue_io(struct super_block *sb, - unsigned long *older_than_this) +static void queue_io(struct bdi_writeback *wb, unsigned long *older_than_this) { - list_splice_init(&sb->s_more_io, sb->s_io.prev); - move_expired_inodes(&sb->s_dirty, &sb->s_io, older_than_this); + list_splice_init(&wb->b_more_io, wb->b_io.prev); + move_expired_inodes(&wb->b_dirty, &wb->b_io, older_than_this); } -int sb_has_dirty_inodes(struct super_block *sb) +static int write_inode(struct inode *inode, int sync) { - return !list_empty(&sb->s_dirty) || - !list_empty(&sb->s_io) || - !list_empty(&sb->s_more_io); + if (inode->i_sb->s_op->write_inode && !is_bad_inode(inode)) + return inode->i_sb->s_op->write_inode(inode, sync); + return 0; } -EXPORT_SYMBOL(sb_has_dirty_inodes); /* * Wait for writeback on an inode to complete. @@ -322,11 +395,11 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc) if (inode->i_state & I_SYNC) { /* * If this inode is locked for writeback and we are not doing - * writeback-for-data-integrity, move it to s_more_io so that + * writeback-for-data-integrity, move it to b_more_io so that * writeback can proceed with the other inodes on s_io. * * We'll have another go at writing back this inode when we - * completed a full scan of s_io. + * completed a full scan of b_io. */ if (!wait) { requeue_io(inode); @@ -371,11 +444,11 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc) /* * We didn't write back all the pages. nfs_writepages() * sometimes bales out without doing anything. Redirty - * the inode; Move it from s_io onto s_more_io/s_dirty. + * the inode; Move it from b_io onto b_more_io/b_dirty. */ /* * akpm: if the caller was the kupdate function we put - * this inode at the head of s_dirty so it gets first + * this inode at the head of b_dirty so it gets first * consideration. Otherwise, move it to the tail, for * the reasons described there. I'm not really sure * how much sense this makes. Presumably I had a good @@ -385,7 +458,7 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc) if (wbc->for_kupdate) { /* * For the kupdate function we move the inode - * to s_more_io so it will get more writeout as + * to b_more_io so it will get more writeout as * soon as the queue becomes uncongested. */ inode->i_state |= I_DIRTY_PAGES; @@ -434,50 +507,84 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc) } /* - * Write out a superblock's list of dirty inodes. A wait will be performed - * upon no inodes, all inodes or the final one, depending upon sync_mode. - * - * If older_than_this is non-NULL, then only write out inodes which - * had their first dirtying at a time earlier than *older_than_this. - * - * If we're a pdflush thread, then implement pdflush collision avoidance - * against the entire list. + * For WB_SYNC_NONE writeback, the caller does not have the sb pinned + * before calling writeback. So make sure that we do pin it, so it doesn't + * go away while we are writing inodes from it. * - * If `bdi' is non-zero then we're being asked to writeback a specific queue. - * This function assumes that the blockdev superblock's inodes are backed by - * a variety of queues, so all inodes are searched. For other superblocks, - * assume that all inodes are backed by the same queue. - * - * FIXME: this linear search could get expensive with many fileystems. But - * how to fix? We need to go from an address_space to all inodes which share - * a queue with that address_space. (Easy: have a global "dirty superblocks" - * list). - * - * The inodes to be written are parked on sb->s_io. They are moved back onto - * sb->s_dirty as they are selected for writing. This way, none can be missed - * on the writer throttling path, and we get decent balancing between many - * throttled threads: we don't want them all piling up on inode_sync_wait. + * Returns 0 if the super was successfully pinned (or pinning wasn't needed), + * 1 if we failed. */ -void generic_sync_sb_inodes(struct super_block *sb, +static int pin_sb_for_writeback(struct writeback_control *wbc, + struct inode *inode) +{ + struct super_block *sb = inode->i_sb; + + /* + * Caller must already hold the ref for this + */ + if (wbc->sync_mode == WB_SYNC_ALL) { + WARN_ON(!rwsem_is_locked(&sb->s_umount)); + return 0; + } + + spin_lock(&sb_lock); + sb->s_count++; + if (down_read_trylock(&sb->s_umount)) { + if (sb->s_root) { + spin_unlock(&sb_lock); + return 0; + } + /* + * umounted, drop rwsem again and fall through to failure + */ + up_read(&sb->s_umount); + } + + sb->s_count--; + spin_unlock(&sb_lock); + return 1; +} + +static void unpin_sb_for_writeback(struct writeback_control *wbc, + struct inode *inode) +{ + struct super_block *sb = inode->i_sb; + + if (wbc->sync_mode == WB_SYNC_ALL) + return; + + up_read(&sb->s_umount); + put_super(sb); +} + +static void writeback_inodes_wb(struct bdi_writeback *wb, struct writeback_control *wbc) { + struct super_block *sb = wbc->sb; + const int is_blkdev_sb = sb_is_blkdev_sb(sb); const unsigned long start = jiffies; /* livelock avoidance */ - int sync = wbc->sync_mode == WB_SYNC_ALL; spin_lock(&inode_lock); - if (!wbc->for_kupdate || list_empty(&sb->s_io)) - queue_io(sb, wbc->older_than_this); - while (!list_empty(&sb->s_io)) { - struct inode *inode = list_entry(sb->s_io.prev, + if (!wbc->for_kupdate || list_empty(&wb->b_io)) + queue_io(wb, wbc->older_than_this); + + while (!list_empty(&wb->b_io)) { + struct inode *inode = list_entry(wb->b_io.prev, struct inode, i_list); - struct address_space *mapping = inode->i_mapping; - struct backing_dev_info *bdi = mapping->backing_dev_info; long pages_skipped; - if (!bdi_cap_writeback_dirty(bdi)) { + /* + * super block given and doesn't match, skip this inode + */ + if (sb && sb != inode->i_sb) { + redirty_tail(inode); + continue; + } + + if (!bdi_cap_writeback_dirty(wb->bdi)) { redirty_tail(inode); - if (sb_is_blkdev_sb(sb)) { + if (is_blkdev_sb) { /* * Dirty memory-backed blockdev: the ramdisk * driver does this. Skip just this inode @@ -497,21 +604,14 @@ void generic_sync_sb_inodes(struct super_block *sb, continue; } - if (wbc->nonblocking && bdi_write_congested(bdi)) { + if (wbc->nonblocking && bdi_write_congested(wb->bdi)) { wbc->encountered_congestion = 1; - if (!sb_is_blkdev_sb(sb)) + if (!is_blkdev_sb) break; /* Skip a congested fs */ requeue_io(inode); continue; /* Skip a congested blockdev */ } - if (wbc->bdi && bdi != wbc->bdi) { - if (!sb_is_blkdev_sb(sb)) - break; /* fs has the wrong queue */ - requeue_io(inode); - continue; /* blockdev has wrong queue */ - } - /* * Was this inode dirtied after sync_sb_inodes was called? * This keeps sync from extra jobs and livelock. @@ -519,16 +619,16 @@ void generic_sync_sb_inodes(struct super_block *sb, if (inode_dirtied_after(inode, start)) break; - /* Is another pdflush already flushing this queue? */ - if (current_is_pdflush() && !writeback_acquire(bdi)) - break; + if (pin_sb_for_writeback(wbc, inode)) { + requeue_io(inode); + continue; + } BUG_ON(inode->i_state & (I_FREEING | I_CLEAR)); __iget(inode); pages_skipped = wbc->pages_skipped; writeback_single_inode(inode, wbc); - if (current_is_pdflush()) - writeback_release(bdi); + unpin_sb_for_writeback(wbc, inode); if (wbc->pages_skipped != pages_skipped) { /* * writeback is not making progress due to locked @@ -544,144 +644,520 @@ void generic_sync_sb_inodes(struct super_block *sb, wbc->more_io = 1; break; } - if (!list_empty(&sb->s_more_io)) + if (!list_empty(&wb->b_more_io)) wbc->more_io = 1; } - if (sync) { - struct inode *inode, *old_inode = NULL; + spin_unlock(&inode_lock); + /* Leave any unwritten inodes on b_io */ +} + +void writeback_inodes_wbc(struct writeback_control *wbc) +{ + struct backing_dev_info *bdi = wbc->bdi; + writeback_inodes_wb(&bdi->wb, wbc); +} + +/* + * The maximum number of pages to writeout in a single bdi flush/kupdate + * operation. We do this so we don't hold I_SYNC against an inode for + * enormous amounts of time, which would block a userspace task which has + * been forced to throttle against that inode. Also, the code reevaluates + * the dirty each time it has written this many pages. + */ +#define MAX_WRITEBACK_PAGES 1024 + +static inline bool over_bground_thresh(void) +{ + unsigned long background_thresh, dirty_thresh; + + get_dirty_limits(&background_thresh, &dirty_thresh, NULL, NULL); + + return (global_page_state(NR_FILE_DIRTY) + + global_page_state(NR_UNSTABLE_NFS) >= background_thresh); +} + +/* + * Explicit flushing or periodic writeback of "old" data. + * + * Define "old": the first time one of an inode's pages is dirtied, we mark the + * dirtying-time in the inode's address_space. So this periodic writeback code + * just walks the superblock inode list, writing back any inodes which are + * older than a specific point in time. + * + * Try to run once per dirty_writeback_interval. But if a writeback event + * takes longer than a dirty_writeback_interval interval, then leave a + * one-second gap. + * + * older_than_this takes precedence over nr_to_write. So we'll only write back + * all dirty pages if they are all attached to "old" mappings. + */ +static long wb_writeback(struct bdi_writeback *wb, + struct wb_writeback_args *args) +{ + struct writeback_control wbc = { + .bdi = wb->bdi, + .sb = args->sb, + .sync_mode = args->sync_mode, + .older_than_this = NULL, + .for_kupdate = args->for_kupdate, + .range_cyclic = args->range_cyclic, + }; + unsigned long oldest_jif; + long wrote = 0; + + if (wbc.for_kupdate) { + wbc.older_than_this = &oldest_jif; + oldest_jif = jiffies - + msecs_to_jiffies(dirty_expire_interval * 10); + } + if (!wbc.range_cyclic) { + wbc.range_start = 0; + wbc.range_end = LLONG_MAX; + } + + for (;;) { /* - * Data integrity sync. Must wait for all pages under writeback, - * because there may have been pages dirtied before our sync - * call, but which had writeout started before we write it out. - * In which case, the inode may not be on the dirty list, but - * we still have to wait for that writeout. + * Don't flush anything for non-integrity writeback where + * no nr_pages was given */ - list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { - struct address_space *mapping; + if (!args->for_kupdate && args->nr_pages <= 0 && + args->sync_mode == WB_SYNC_NONE) + break; - if (inode->i_state & - (I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW)) - continue; - mapping = inode->i_mapping; - if (mapping->nrpages == 0) + /* + * If no specific pages were given and this is just a + * periodic background writeout and we are below the + * background dirty threshold, don't do anything + */ + if (args->for_kupdate && args->nr_pages <= 0 && + !over_bground_thresh()) + break; + + wbc.more_io = 0; + wbc.encountered_congestion = 0; + wbc.nr_to_write = MAX_WRITEBACK_PAGES; + wbc.pages_skipped = 0; + writeback_inodes_wb(wb, &wbc); + args->nr_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write; + wrote += MAX_WRITEBACK_PAGES - wbc.nr_to_write; + + /* + * If we ran out of stuff to write, bail unless more_io got set + */ + if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) { + if (wbc.more_io && !wbc.for_kupdate) continue; - __iget(inode); - spin_unlock(&inode_lock); - /* - * We hold a reference to 'inode' so it couldn't have - * been removed from s_inodes list while we dropped the - * inode_lock. We cannot iput the inode now as we can - * be holding the last reference and we cannot iput it - * under inode_lock. So we keep the reference and iput - * it later. - */ - iput(old_inode); - old_inode = inode; + break; + } + } + + return wrote; +} + +/* + * Return the next bdi_work struct that hasn't been processed by this + * wb thread yet. ->seen is initially set for each thread that exists + * for this device, when a thread first notices a piece of work it + * clears its bit. Depending on writeback type, the thread will notify + * completion on either receiving the work (WB_SYNC_NONE) or after + * it is done (WB_SYNC_ALL). + */ +static struct bdi_work *get_next_work_item(struct backing_dev_info *bdi, + struct bdi_writeback *wb) +{ + struct bdi_work *work, *ret = NULL; + + rcu_read_lock(); + + list_for_each_entry_rcu(work, &bdi->work_list, list) { + if (!test_bit(wb->nr, &work->seen)) + continue; + clear_bit(wb->nr, &work->seen); + + ret = work; + break; + } + + rcu_read_unlock(); + return ret; +} + +static long wb_check_old_data_flush(struct bdi_writeback *wb) +{ + unsigned long expired; + long nr_pages; + + expired = wb->last_old_flush + + msecs_to_jiffies(dirty_writeback_interval * 10); + if (time_before(jiffies, expired)) + return 0; + + wb->last_old_flush = jiffies; + nr_pages = global_page_state(NR_FILE_DIRTY) + + global_page_state(NR_UNSTABLE_NFS) + + (inodes_stat.nr_inodes - inodes_stat.nr_unused); + + if (nr_pages) { + struct wb_writeback_args args = { + .nr_pages = nr_pages, + .sync_mode = WB_SYNC_NONE, + .for_kupdate = 1, + .range_cyclic = 1, + }; + + return wb_writeback(wb, &args); + } + + return 0; +} + +/* + * Retrieve work items and do the writeback they describe + */ +long wb_do_writeback(struct bdi_writeback *wb, int force_wait) +{ + struct backing_dev_info *bdi = wb->bdi; + struct bdi_work *work; + long wrote = 0; - filemap_fdatawait(mapping); + while ((work = get_next_work_item(bdi, wb)) != NULL) { + struct wb_writeback_args args = work->args; - cond_resched(); + /* + * Override sync mode, in case we must wait for completion + */ + if (force_wait) + work->args.sync_mode = args.sync_mode = WB_SYNC_ALL; - spin_lock(&inode_lock); + /* + * If this isn't a data integrity operation, just notify + * that we have seen this work and we are now starting it. + */ + if (args.sync_mode == WB_SYNC_NONE) + wb_clear_pending(wb, work); + + wrote += wb_writeback(wb, &args); + + /* + * This is a data integrity writeback, so only do the + * notification when we have completed the work. + */ + if (args.sync_mode == WB_SYNC_ALL) + wb_clear_pending(wb, work); + } + + /* + * Check for periodic writeback, kupdated() style + */ + wrote += wb_check_old_data_flush(wb); + + return wrote; +} + +/* + * Handle writeback of dirty data for the device backed by this bdi. Also + * wakes up periodically and does kupdated style flushing. + */ +int bdi_writeback_task(struct bdi_writeback *wb) +{ + unsigned long last_active = jiffies; + unsigned long wait_jiffies = -1UL; + long pages_written; + + while (!kthread_should_stop()) { + pages_written = wb_do_writeback(wb, 0); + + if (pages_written) + last_active = jiffies; + else if (wait_jiffies != -1UL) { + unsigned long max_idle; + + /* + * Longest period of inactivity that we tolerate. If we + * see dirty data again later, the task will get + * recreated automatically. + */ + max_idle = max(5UL * 60 * HZ, wait_jiffies); + if (time_after(jiffies, max_idle + last_active)) + break; } - spin_unlock(&inode_lock); - iput(old_inode); - } else - spin_unlock(&inode_lock); - return; /* Leave any unwritten inodes on s_io */ + wait_jiffies = msecs_to_jiffies(dirty_writeback_interval * 10); + schedule_timeout_interruptible(wait_jiffies); + try_to_freeze(); + } + + return 0; } -EXPORT_SYMBOL_GPL(generic_sync_sb_inodes); -static void sync_sb_inodes(struct super_block *sb, - struct writeback_control *wbc) +/* + * Schedule writeback for all backing devices. This does WB_SYNC_NONE + * writeback, for integrity writeback see bdi_sync_writeback(). + */ +static void bdi_writeback_all(struct super_block *sb, long nr_pages) { - generic_sync_sb_inodes(sb, wbc); + struct wb_writeback_args args = { + .sb = sb, + .nr_pages = nr_pages, + .sync_mode = WB_SYNC_NONE, + }; + struct backing_dev_info *bdi; + + rcu_read_lock(); + + list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) { + if (!bdi_has_dirty_io(bdi)) + continue; + + bdi_alloc_queue_work(bdi, &args); + } + + rcu_read_unlock(); } /* - * Start writeback of dirty pagecache data against all unlocked inodes. + * Start writeback of `nr_pages' pages. If `nr_pages' is zero, write back + * the whole world. + */ +void wakeup_flusher_threads(long nr_pages) +{ + if (nr_pages == 0) + nr_pages = global_page_state(NR_FILE_DIRTY) + + global_page_state(NR_UNSTABLE_NFS); + bdi_writeback_all(NULL, nr_pages); +} + +static noinline void block_dump___mark_inode_dirty(struct inode *inode) +{ + if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev")) { + struct dentry *dentry; + const char *name = "?"; + + dentry = d_find_alias(inode); + if (dentry) { + spin_lock(&dentry->d_lock); + name = (const char *) dentry->d_name.name; + } + printk(KERN_DEBUG + "%s(%d): dirtied inode %lu (%s) on %s\n", + current->comm, task_pid_nr(current), inode->i_ino, + name, inode->i_sb->s_id); + if (dentry) { + spin_unlock(&dentry->d_lock); + dput(dentry); + } + } +} + +/** + * __mark_inode_dirty - internal function + * @inode: inode to mark + * @flags: what kind of dirty (i.e. I_DIRTY_SYNC) + * Mark an inode as dirty. Callers should use mark_inode_dirty or + * mark_inode_dirty_sync. + * + * Put the inode on the super block's dirty list. * - * Note: - * We don't need to grab a reference to superblock here. If it has non-empty - * ->s_dirty it's hadn't been killed yet and kill_super() won't proceed - * past sync_inodes_sb() until the ->s_dirty/s_io/s_more_io lists are all - * empty. Since __sync_single_inode() regains inode_lock before it finally moves - * inode from superblock lists we are OK. + * CAREFUL! We mark it dirty unconditionally, but move it onto the + * dirty list only if it is hashed or if it refers to a blockdev. + * If it was not hashed, it will never be added to the dirty list + * even if it is later hashed, as it will have been marked dirty already. * - * If `older_than_this' is non-zero then only flush inodes which have a - * flushtime older than *older_than_this. + * In short, make sure you hash any inodes _before_ you start marking + * them dirty. * - * If `bdi' is non-zero then we will scan the first inode against each - * superblock until we find the matching ones. One group will be the dirty - * inodes against a filesystem. Then when we hit the dummy blockdev superblock, - * sync_sb_inodes will seekout the blockdev which matches `bdi'. Maybe not - * super-efficient but we're about to do a ton of I/O... + * This function *must* be atomic for the I_DIRTY_PAGES case - + * set_page_dirty() is called under spinlock in several places. + * + * Note that for blockdevs, inode->dirtied_when represents the dirtying time of + * the block-special inode (/dev/hda1) itself. And the ->dirtied_when field of + * the kernel-internal blockdev inode represents the dirtying time of the + * blockdev's pages. This is why for I_DIRTY_PAGES we always use + * page->mapping->host, so the page-dirtying time is recorded in the internal + * blockdev inode. */ -void -writeback_inodes(struct writeback_control *wbc) +void __mark_inode_dirty(struct inode *inode, int flags) { - struct super_block *sb; + struct super_block *sb = inode->i_sb; - might_sleep(); - spin_lock(&sb_lock); -restart: - list_for_each_entry_reverse(sb, &super_blocks, s_list) { - if (sb_has_dirty_inodes(sb)) { - /* we're making our own get_super here */ - sb->s_count++; - spin_unlock(&sb_lock); - /* - * If we can't get the readlock, there's no sense in - * waiting around, most of the time the FS is going to - * be unmounted by the time it is released. - */ - if (down_read_trylock(&sb->s_umount)) { - if (sb->s_root) - sync_sb_inodes(sb, wbc); - up_read(&sb->s_umount); + /* + * Don't do this for I_DIRTY_PAGES - that doesn't actually + * dirty the inode itself + */ + if (flags & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) { + if (sb->s_op->dirty_inode) + sb->s_op->dirty_inode(inode); + } + + /* + * make sure that changes are seen by all cpus before we test i_state + * -- mikulas + */ + smp_mb(); + + /* avoid the locking if we can */ + if ((inode->i_state & flags) == flags) + return; + + if (unlikely(block_dump)) + block_dump___mark_inode_dirty(inode); + + spin_lock(&inode_lock); + if ((inode->i_state & flags) != flags) { + const int was_dirty = inode->i_state & I_DIRTY; + + inode->i_state |= flags; + + /* + * If the inode is being synced, just update its dirty state. + * The unlocker will place the inode on the appropriate + * superblock list, based upon its state. + */ + if (inode->i_state & I_SYNC) + goto out; + + /* + * Only add valid (hashed) inodes to the superblock's + * dirty list. Add blockdev inodes as well. + */ + if (!S_ISBLK(inode->i_mode)) { + if (hlist_unhashed(&inode->i_hash)) + goto out; + } + if (inode->i_state & (I_FREEING|I_CLEAR)) + goto out; + + /* + * If the inode was already on b_dirty/b_io/b_more_io, don't + * reposition it (that would break b_dirty time-ordering). + */ + if (!was_dirty) { + struct bdi_writeback *wb = &inode_to_bdi(inode)->wb; + struct backing_dev_info *bdi = wb->bdi; + + if (bdi_cap_writeback_dirty(bdi) && + !test_bit(BDI_registered, &bdi->state)) { + WARN_ON(1); + printk(KERN_ERR "bdi-%s not registered\n", + bdi->name); } - spin_lock(&sb_lock); - if (__put_super_and_need_restart(sb)) - goto restart; + + inode->dirtied_when = jiffies; + list_move(&inode->i_list, &wb->b_dirty); } - if (wbc->nr_to_write <= 0) - break; } - spin_unlock(&sb_lock); +out: + spin_unlock(&inode_lock); } +EXPORT_SYMBOL(__mark_inode_dirty); /* - * writeback and wait upon the filesystem's dirty inodes. The caller will - * do this in two passes - one to write, and one to wait. + * Write out a superblock's list of dirty inodes. A wait will be performed + * upon no inodes, all inodes or the final one, depending upon sync_mode. + * + * If older_than_this is non-NULL, then only write out inodes which + * had their first dirtying at a time earlier than *older_than_this. + * + * If we're a pdlfush thread, then implement pdflush collision avoidance + * against the entire list. * - * A finite limit is set on the number of pages which will be written. - * To prevent infinite livelock of sys_sync(). + * If `bdi' is non-zero then we're being asked to writeback a specific queue. + * This function assumes that the blockdev superblock's inodes are backed by + * a variety of queues, so all inodes are searched. For other superblocks, + * assume that all inodes are backed by the same queue. * - * We add in the number of potentially dirty inodes, because each inode write - * can dirty pagecache in the underlying blockdev. + * The inodes to be written are parked on bdi->b_io. They are moved back onto + * bdi->b_dirty as they are selected for writing. This way, none can be missed + * on the writer throttling path, and we get decent balancing between many + * throttled threads: we don't want them all piling up on inode_sync_wait. */ -void sync_inodes_sb(struct super_block *sb, int wait) +static void wait_sb_inodes(struct super_block *sb) { - struct writeback_control wbc = { - .sync_mode = wait ? WB_SYNC_ALL : WB_SYNC_NONE, - .range_start = 0, - .range_end = LLONG_MAX, - }; + struct inode *inode, *old_inode = NULL; + + /* + * We need to be protected against the filesystem going from + * r/o to r/w or vice versa. + */ + WARN_ON(!rwsem_is_locked(&sb->s_umount)); + + spin_lock(&inode_lock); + + /* + * Data integrity sync. Must wait for all pages under writeback, + * because there may have been pages dirtied before our sync + * call, but which had writeout started before we write it out. + * In which case, the inode may not be on the dirty list, but + * we still have to wait for that writeout. + */ + list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { + struct address_space *mapping; + + if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW)) + continue; + mapping = inode->i_mapping; + if (mapping->nrpages == 0) + continue; + __iget(inode); + spin_unlock(&inode_lock); + /* + * We hold a reference to 'inode' so it couldn't have + * been removed from s_inodes list while we dropped the + * inode_lock. We cannot iput the inode now as we can + * be holding the last reference and we cannot iput it + * under inode_lock. So we keep the reference and iput + * it later. + */ + iput(old_inode); + old_inode = inode; + + filemap_fdatawait(mapping); + + cond_resched(); - if (!wait) { - unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY); - unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS); + spin_lock(&inode_lock); + } + spin_unlock(&inode_lock); + iput(old_inode); +} - wbc.nr_to_write = nr_dirty + nr_unstable + +/** + * writeback_inodes_sb - writeback dirty inodes from given super_block + * @sb: the superblock + * + * Start writeback on some inodes on this super_block. No guarantees are made + * on how many (if any) will be written, and this function does not wait + * for IO completion of submitted IO. The number of pages submitted is + * returned. + */ +void writeback_inodes_sb(struct super_block *sb) +{ + unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY); + unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS); + long nr_to_write; + + nr_to_write = nr_dirty + nr_unstable + (inodes_stat.nr_inodes - inodes_stat.nr_unused); - } else - wbc.nr_to_write = LONG_MAX; /* doesn't actually matter */ - sync_sb_inodes(sb, &wbc); + bdi_writeback_all(sb, nr_to_write); +} +EXPORT_SYMBOL(writeback_inodes_sb); + +/** + * sync_inodes_sb - sync sb inode pages + * @sb: the superblock + * + * This function writes and waits on any dirty inode belonging to this + * super_block. The number of pages synced is returned. + */ +void sync_inodes_sb(struct super_block *sb) +{ + bdi_sync_writeback(sb->s_bdi, sb); + wait_sb_inodes(sb); } +EXPORT_SYMBOL(sync_inodes_sb); /** * write_inode_now - write an inode to disk @@ -737,57 +1213,3 @@ int sync_inode(struct inode *inode, struct writeback_control *wbc) return ret; } EXPORT_SYMBOL(sync_inode); - -/** - * generic_osync_inode - flush all dirty data for a given inode to disk - * @inode: inode to write - * @mapping: the address_space that should be flushed - * @what: what to write and wait upon - * - * This can be called by file_write functions for files which have the - * O_SYNC flag set, to flush dirty writes to disk. - * - * @what is a bitmask, specifying which part of the inode's data should be - * written and waited upon. - * - * OSYNC_DATA: i_mapping's dirty data - * OSYNC_METADATA: the buffers at i_mapping->private_list - * OSYNC_INODE: the inode itself - */ - -int generic_osync_inode(struct inode *inode, struct address_space *mapping, int what) -{ - int err = 0; - int need_write_inode_now = 0; - int err2; - - if (what & OSYNC_DATA) - err = filemap_fdatawrite(mapping); - if (what & (OSYNC_METADATA|OSYNC_DATA)) { - err2 = sync_mapping_buffers(mapping); - if (!err) - err = err2; - } - if (what & OSYNC_DATA) { - err2 = filemap_fdatawait(mapping); - if (!err) - err = err2; - } - - spin_lock(&inode_lock); - if ((inode->i_state & I_DIRTY) && - ((what & OSYNC_INODE) || (inode->i_state & I_DIRTY_DATASYNC))) - need_write_inode_now = 1; - spin_unlock(&inode_lock); - - if (need_write_inode_now) { - err2 = write_inode_now(inode, 1); - if (!err) - err = err2; - } - else - inode_sync_wait(inode); - - return err; -} -EXPORT_SYMBOL(generic_osync_inode); |