diff options
| -rw-r--r-- | fs/buffer.c | 2 | ||||
| -rw-r--r-- | fs/fs-writeback.c | 999 | ||||
| -rw-r--r-- | fs/super.c | 2 | ||||
| -rw-r--r-- | fs/sync.c | 2 | ||||
| -rw-r--r-- | include/linux/backing-dev.h | 55 | ||||
| -rw-r--r-- | include/linux/fs.h | 2 | ||||
| -rw-r--r-- | include/linux/writeback.h | 8 | ||||
| -rw-r--r-- | mm/backing-dev.c | 341 | ||||
| -rw-r--r-- | mm/page-writeback.c | 179 | ||||
| -rw-r--r-- | mm/vmscan.c | 2 |
10 files changed, 1120 insertions, 472 deletions
diff --git a/fs/buffer.c b/fs/buffer.c index 28f320f..90a9886 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -281,7 +281,7 @@ static void free_more_memory(void) struct zone *zone; int nid; - wakeup_pdflush(1024); + wakeup_flusher_threads(1024); yield(); for_each_online_node(nid) { diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 45ad4bb..7f6dae8 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -19,6 +19,8 @@ #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> @@ -27,165 +29,208 @@ #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. +/* + * Work items for the bdi_writeback threads */ -static int writeback_acquire(struct backing_dev_info *bdi) +struct bdi_work { + struct list_head list; + struct list_head wait_list; + struct rcu_head rcu_head; + + unsigned long seen; + atomic_t pending; + + struct super_block *sb; + unsigned long nr_pages; + enum writeback_sync_modes sync_mode; + + unsigned long state; +}; + +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 writeback_control *wbc) +{ + INIT_RCU_HEAD(&work->rcu_head); + work->sb = wbc->sb; + work->nr_pages = wbc->nr_to_write; + work->sync_mode = wbc->sync_mode; + work->state = WS_USED; +} + +static inline void bdi_work_init_on_stack(struct bdi_work *work, + struct writeback_control *wbc) { - return !test_and_set_bit(BDI_pdflush, &bdi->state); + bdi_work_init(work, wbc); + work->state |= WS_ONSTACK; } /** * 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(); + 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->sync_mode; /* - * 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 (!bdi_work_on_stack(work)) + bdi_work_clear(work); + if (sync_mode == WB_SYNC_NONE || bdi_work_on_stack(work)) + 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; - - if (unlikely(block_dump)) - block_dump___mark_inode_dirty(inode); + spin_lock(&bdi->wb_lock); + list_del_rcu(&work->list); + spin_unlock(&bdi->wb_lock); - spin_lock(&inode_lock); - if ((inode->i_state & flags) != flags) { - const int was_dirty = inode->i_state & I_DIRTY; + wb_work_complete(work); + } +} - inode->i_state |= flags; +static void bdi_queue_work(struct backing_dev_info *bdi, struct bdi_work *work) +{ + if (work) { + work->seen = bdi->wb_mask; + BUG_ON(!work->seen); + atomic_set(&work->pending, bdi->wb_cnt); + BUG_ON(!bdi->wb_cnt); /* - * 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. + * Make sure stores are seen before it appears on the list */ - if (inode->i_state & I_SYNC) - goto out; + smp_mb(); - /* - * 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; + spin_lock(&bdi->wb_lock); + list_add_tail_rcu(&work->list, &bdi->work_list); + spin_unlock(&bdi->wb_lock); + } + + /* + * 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; /* - * 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 we failed allocating the bdi work item, wake up the wb + * thread always. As a safety precaution, it'll flush out + * everything */ - if (!was_dirty) { - inode->dirtied_when = jiffies; - list_move(&inode->i_list, - &inode_to_bdi(inode)->b_dirty); - } + if (!wb_has_dirty_io(wb)) { + if (work) + wb_clear_pending(wb, work); + } else if (wb->task) + wake_up_process(wb->task); } -out: - spin_unlock(&inode_lock); } -EXPORT_SYMBOL(__mark_inode_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 int write_inode(struct inode *inode, int sync) +static struct bdi_work *bdi_alloc_work(struct writeback_control *wbc) { - 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 bdi_work *work; + + work = kmalloc(sizeof(*work), GFP_ATOMIC); + if (work) + bdi_work_init(work, wbc); + + return work; +} + +void bdi_start_writeback(struct writeback_control *wbc) +{ + const bool must_wait = wbc->sync_mode == WB_SYNC_ALL; + struct bdi_work work_stack, *work = NULL; + + if (!must_wait) + work = bdi_alloc_work(wbc); + + if (!work) { + work = &work_stack; + bdi_work_init_on_stack(work, wbc); + } + + bdi_queue_work(wbc->bdi, work); + + /* + * If the sync mode is WB_SYNC_ALL, block waiting for the work to + * complete. If not, we only need to wait for the work to be started, + * if we allocated it on-stack. We use the same mechanism, if the + * wait bit is set in the bdi_work struct, then threads will not + * clear pending until after they are done. + * + * Note that work == &work_stack if must_wait is true, so we don't + * need to do call_rcu() here ever, since the completion path will + * have done that for us. + */ + if (must_wait || work == &work_stack) { + bdi_wait_on_work_clear(work); + if (work != &work_stack) + call_rcu(&work->rcu_head, bdi_work_free); + } } /* @@ -199,16 +244,16 @@ static int write_inode(struct inode *inode, int sync) */ static void redirty_tail(struct inode *inode) { - struct backing_dev_info *bdi = inode_to_bdi(inode); + struct bdi_writeback *wb = &inode_to_bdi(inode)->wb; - if (!list_empty(&bdi->b_dirty)) { + if (!list_empty(&wb->b_dirty)) { struct inode *tail; - tail = list_entry(bdi->b_dirty.next, struct inode, i_list); + 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, &bdi->b_dirty); + list_move(&inode->i_list, &wb->b_dirty); } /* @@ -216,7 +261,9 @@ static void redirty_tail(struct inode *inode) */ static void requeue_io(struct inode *inode) { - list_move(&inode->i_list, &inode_to_bdi(inode)->b_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) @@ -263,52 +310,18 @@ static void move_expired_inodes(struct list_head *delaying_queue, /* * Queue all expired dirty inodes for io, eldest first. */ -static void queue_io(struct backing_dev_info *bdi, - unsigned long *older_than_this) +static void queue_io(struct bdi_writeback *wb, unsigned long *older_than_this) { - list_splice_init(&bdi->b_more_io, bdi->b_io.prev); - move_expired_inodes(&bdi->b_dirty, &bdi->b_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); } -static int sb_on_inode_list(struct super_block *sb, struct list_head *list) -{ - struct inode *inode; - int ret = 0; - - spin_lock(&inode_lock); - list_for_each_entry(inode, list, i_list) { - if (inode->i_sb == sb) { - ret = 1; - break; - } - } - spin_unlock(&inode_lock); - return ret; -} - -int sb_has_dirty_inodes(struct super_block *sb) +static int write_inode(struct inode *inode, int sync) { - struct backing_dev_info *bdi; - int ret = 0; - - /* - * This is REALLY expensive right now, but it'll go away - * when the bdi writeback is introduced - */ - mutex_lock(&bdi_lock); - list_for_each_entry(bdi, &bdi_list, bdi_list) { - if (sb_on_inode_list(sb, &bdi->b_dirty) || - sb_on_inode_list(sb, &bdi->b_io) || - sb_on_inode_list(sb, &bdi->b_more_io)) { - ret = 1; - break; - } - } - mutex_unlock(&bdi_lock); - - return ret; + 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. @@ -466,20 +479,71 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc) return ret; } -static void generic_sync_bdi_inodes(struct backing_dev_info *bdi, - struct writeback_control *wbc, - struct super_block *sb) +/* + * 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. + * + * Returns 0 if the super was successfully pinned (or pinning wasn't needed), + * 1 if we failed. + */ +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 */ spin_lock(&inode_lock); - if (!wbc->for_kupdate || list_empty(&bdi->b_io)) - queue_io(bdi, wbc->older_than_this); + if (!wbc->for_kupdate || list_empty(&wb->b_io)) + queue_io(wb, wbc->older_than_this); - while (!list_empty(&bdi->b_io)) { - struct inode *inode = list_entry(bdi->b_io.prev, + while (!list_empty(&wb->b_io)) { + struct inode *inode = list_entry(wb->b_io.prev, struct inode, i_list); long pages_skipped; @@ -491,7 +555,7 @@ static void generic_sync_bdi_inodes(struct backing_dev_info *bdi, continue; } - if (!bdi_cap_writeback_dirty(bdi)) { + if (!bdi_cap_writeback_dirty(wb->bdi)) { redirty_tail(inode); if (is_blkdev_sb) { /* @@ -513,7 +577,7 @@ static void generic_sync_bdi_inodes(struct backing_dev_info *bdi, continue; } - if (wbc->nonblocking && bdi_write_congested(bdi)) { + if (wbc->nonblocking && bdi_write_congested(wb->bdi)) { wbc->encountered_congestion = 1; if (!is_blkdev_sb) break; /* Skip a congested fs */ @@ -521,13 +585,6 @@ static void generic_sync_bdi_inodes(struct backing_dev_info *bdi, continue; /* Skip a congested blockdev */ } - if (wbc->bdi && bdi != wbc->bdi) { - if (!is_blkdev_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. @@ -535,16 +592,16 @@ static void generic_sync_bdi_inodes(struct backing_dev_info *bdi, 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 @@ -560,7 +617,7 @@ static void generic_sync_bdi_inodes(struct backing_dev_info *bdi, wbc->more_io = 1; break; } - if (!list_empty(&bdi->b_more_io)) + if (!list_empty(&wb->b_more_io)) wbc->more_io = 1; } @@ -568,139 +625,500 @@ static void generic_sync_bdi_inodes(struct backing_dev_info *bdi, /* 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); +} + /* - * 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. + * 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. * - * 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. + * 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. * - * 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). + * 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. * - * 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. + * 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 void generic_sync_sb_inodes(struct super_block *sb, - struct writeback_control *wbc) +static long wb_writeback(struct bdi_writeback *wb, long nr_pages, + struct super_block *sb, + enum writeback_sync_modes sync_mode, int for_kupdate) { - struct backing_dev_info *bdi; - - if (!wbc->bdi) { - mutex_lock(&bdi_lock); - list_for_each_entry(bdi, &bdi_list, bdi_list) - generic_sync_bdi_inodes(bdi, wbc, sb); - mutex_unlock(&bdi_lock); - } else - generic_sync_bdi_inodes(wbc->bdi, wbc, sb); + struct writeback_control wbc = { + .bdi = wb->bdi, + .sb = sb, + .sync_mode = sync_mode, + .older_than_this = NULL, + .for_kupdate = for_kupdate, + .range_cyclic = 1, + }; + unsigned long oldest_jif; + long wrote = 0; - if (wbc->sync_mode == WB_SYNC_ALL) { - struct inode *inode, *old_inode = NULL; + if (wbc.for_kupdate) { + wbc.older_than_this = &oldest_jif; + oldest_jif = jiffies - + msecs_to_jiffies(dirty_expire_interval * 10); + } - spin_lock(&inode_lock); + for (;;) { + /* + * Don't flush anything for non-integrity writeback where + * no nr_pages was given + */ + if (!for_kupdate && nr_pages <= 0 && sync_mode == WB_SYNC_NONE) + break; /* - * 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. + * 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 */ - list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { - struct address_space *mapping; + if (for_kupdate && nr_pages <= 0 && !over_bground_thresh()) + break; - if (inode->i_state & - (I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW)) - continue; - mapping = inode->i_mapping; - if (mapping->nrpages == 0) + wbc.more_io = 0; + wbc.encountered_congestion = 0; + wbc.nr_to_write = MAX_WRITEBACK_PAGES; + wbc.pages_skipped = 0; + writeback_inodes_wb(wb, &wbc); + 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); + break; + } + } + + return wrote; +} + +/* + * Return the next bdi_work struct that hasn't been processed by this + * wb thread yet + */ +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_and_clear_bit(wb->nr, &work->seen)) + continue; + + 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) + return wb_writeback(wb, nr_pages, NULL, WB_SYNC_NONE, 1); + + 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 nr_pages, wrote = 0; + + while ((work = get_next_work_item(bdi, wb)) != NULL) { + enum writeback_sync_modes sync_mode; + + nr_pages = work->nr_pages; + + /* + * Override sync mode, in case we must wait for completion + */ + if (force_wait) + work->sync_mode = sync_mode = WB_SYNC_ALL; + else + sync_mode = work->sync_mode; + + /* + * If this isn't a data integrity operation, just notify + * that we have seen this work and we are now starting it. + */ + if (sync_mode == WB_SYNC_NONE) + wb_clear_pending(wb, work); + + wrote += wb_writeback(wb, nr_pages, work->sb, sync_mode, 0); + + /* + * This is a data integrity writeback, so only do the + * notification when we have completed the work. + */ + if (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; + /* - * 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. + * Longest period of inactivity that we tolerate. If we + * see dirty data again later, the task will get + * recreated automatically. */ - iput(old_inode); - old_inode = inode; + max_idle = max(5UL * 60 * HZ, wait_jiffies); + if (time_after(jiffies, max_idle + last_active)) + break; + } + + wait_jiffies = msecs_to_jiffies(dirty_writeback_interval * 10); + set_current_state(TASK_INTERRUPTIBLE); + schedule_timeout(wait_jiffies); + try_to_freeze(); + } + + return 0; +} + +/* + * Schedule writeback for all backing devices. Expensive! If this is a data + * integrity operation, writeback will be complete when this returns. If + * we are simply called for WB_SYNC_NONE, then writeback will merely be + * scheduled to run. + */ +static void bdi_writeback_all(struct writeback_control *wbc) +{ + const bool must_wait = wbc->sync_mode == WB_SYNC_ALL; + struct backing_dev_info *bdi; + struct bdi_work *work; + LIST_HEAD(list); + +restart: + spin_lock(&bdi_lock); + + list_for_each_entry(bdi, &bdi_list, bdi_list) { + struct bdi_work *work; + + if (!bdi_has_dirty_io(bdi)) + continue; - filemap_fdatawait(mapping); + /* + * If work allocation fails, do the writes inline. We drop + * the lock and restart the list writeout. This should be OK, + * since this happens rarely and because the writeout should + * eventually make more free memory available. + */ + work = bdi_alloc_work(wbc); + if (!work) { + struct writeback_control __wbc; - cond_resched(); + /* + * Not a data integrity writeout, just continue + */ + if (!must_wait) + continue; - spin_lock(&inode_lock); + spin_unlock(&bdi_lock); + __wbc = *wbc; + __wbc.bdi = bdi; + writeback_inodes_wbc(&__wbc); + goto restart; } - spin_unlock(&inode_lock); - iput(old_inode); + if (must_wait) + list_add_tail(&work->wait_list, &list); + + bdi_queue_work(bdi, work); + } + + spin_unlock(&bdi_lock); + + /* + * If this is for WB_SYNC_ALL, wait for pending work to complete + * before returning. + */ + while (!list_empty(&list)) { + work = list_entry(list.next, struct bdi_work, wait_list); + list_del(&work->wait_list); + bdi_wait_on_work_clear(work); + call_rcu(&work->rcu_head, bdi_work_free); } } /* - * 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) +{ + struct writeback_control wbc = { + .sync_mode = WB_SYNC_NONE, + .older_than_this = NULL, + .range_cyclic = 1, + }; + + if (nr_pages == 0) + nr_pages = global_page_state(NR_FILE_DIRTY) + + global_page_state(NR_UNSTABLE_NFS); + wbc.nr_to_write = nr_pages; + bdi_writeback_all(&wbc); +} + +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. * - * Note: - * We don't need to grab a reference to superblock here. If it has non-empty - * ->b_dirty it's hadn't been killed yet and kill_super() won't proceed - * past sync_inodes_sb() until the ->b_dirty/b_io/b_more_io lists are all - * empty. Since __sync_single_inode() regains inode_lock before it finally moves - * inode from superblock lists we are OK. + * 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. * - * If `older_than_this' is non-zero then only flush inodes which have a - * flushtime older than *older_than_this. + * This function *must* be atomic for the I_DIRTY_PAGES case - + * set_page_dirty() is called under spinlock in several places. * - * 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... + * 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) - generic_sync_sb_inodes(sb, wbc); - up_read(&sb->s_umount); - } - spin_lock(&sb_lock); - if (__put_super_and_need_restart(sb)) - goto restart; + /* + * 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; + + 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); + +/* + * 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. + * + * 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. + * + * 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. + */ +static void wait_sb_inodes(struct writeback_control *wbc) +{ + 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(&wbc->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, &wbc->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(); + + spin_lock(&inode_lock); + } + spin_unlock(&inode_lock); + iput(old_inode); } /** @@ -715,6 +1133,7 @@ restart: long writeback_inodes_sb(struct super_block *sb) { struct writeback_control wbc = { + .sb = sb, .sync_mode = WB_SYNC_NONE, .range_start = 0, .range_end = LLONG_MAX, @@ -727,7 +1146,7 @@ long writeback_inodes_sb(struct super_block *sb) (inodes_stat.nr_inodes - inodes_stat.nr_unused); wbc.nr_to_write = nr_to_write; - generic_sync_sb_inodes(sb, &wbc); + bdi_writeback_all(&wbc); return nr_to_write - wbc.nr_to_write; } EXPORT_SYMBOL(writeback_inodes_sb); @@ -742,6 +1161,7 @@ EXPORT_SYMBOL(writeback_inodes_sb); long sync_inodes_sb(struct super_block *sb) { struct writeback_control wbc = { + .sb = sb, .sync_mode = WB_SYNC_ALL, .range_start = 0, .range_end = LLONG_MAX, @@ -749,7 +1169,8 @@ long sync_inodes_sb(struct super_block *sb) long nr_to_write = LONG_MAX; /* doesn't actually matter */ wbc.nr_to_write = nr_to_write; - generic_sync_sb_inodes(sb, &wbc); + bdi_writeback_all(&wbc); + wait_sb_inodes(&wbc); return nr_to_write - wbc.nr_to_write; } EXPORT_SYMBOL(sync_inodes_sb); @@ -168,7 +168,7 @@ int __put_super_and_need_restart(struct super_block *sb) * Drops a temporary reference, frees superblock if there's no * references left. */ -static void put_super(struct super_block *sb) +void put_super(struct super_block *sb) { spin_lock(&sb_lock); __put_super(sb); @@ -120,7 +120,7 @@ restart: */ SYSCALL_DEFINE0(sync) { - wakeup_pdflush(0); + wakeup_flusher_threads(0); sync_filesystems(0); sync_filesystems(1); if (unlikely(laptop_mode)) diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 928cd54..d045f5f 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -13,6 +13,8 @@ #include <linux/proportions.h> #include <linux/kernel.h> #include <linux/fs.h> +#include <linux/sched.h> +#include <linux/writeback.h> #include <asm/atomic.h> struct page; @@ -23,7 +25,8 @@ struct dentry; * Bits in backing_dev_info.state */ enum bdi_state { - BDI_pdflush, /* A pdflush thread is working this device */ + BDI_pending, /* On its way to being activated */ + BDI_wb_alloc, /* Default embedded wb allocated */ BDI_async_congested, /* The async (write) queue is getting full */ BDI_sync_congested, /* The sync queue is getting full */ BDI_unused, /* Available bits start here */ @@ -39,9 +42,22 @@ enum bdi_stat_item { #define BDI_STAT_BATCH (8*(1+ilog2(nr_cpu_ids))) +struct bdi_writeback { + struct list_head list; /* hangs off the bdi */ + + struct backing_dev_info *bdi; /* our parent bdi */ + unsigned int nr; + + unsigned long last_old_flush; /* last old data flush */ + + struct task_struct *task; /* writeback task */ + struct list_head b_dirty; /* dirty inodes */ + struct list_head b_io; /* parked for writeback */ + struct list_head b_more_io; /* parked for more writeback */ +}; + struct backing_dev_info { struct list_head bdi_list; - unsigned long ra_pages; /* max readahead in PAGE_CACHE_SIZE units */ unsigned long state; /* Always use atomic bitops on this */ unsigned int capabilities; /* Device capabilities */ @@ -58,11 +74,15 @@ struct backing_dev_info { unsigned int min_ratio; unsigned int max_ratio, max_prop_frac; - struct device *dev; + struct bdi_writeback wb; /* default writeback info for this bdi */ + spinlock_t wb_lock; /* protects update side of wb_list */ + struct list_head wb_list; /* the flusher threads hanging off this bdi */ + unsigned long wb_mask; /* bitmask of registered tasks */ + unsigned int wb_cnt; /* number of registered tasks */ - struct list_head b_dirty; /* dirty inodes */ - struct list_head b_io; /* parked for writeback */ - struct list_head b_more_io; /* parked for more writeback */ + struct list_head work_list; + + struct device *dev; #ifdef CONFIG_DEBUG_FS struct dentry *debug_dir; @@ -77,10 +97,20 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent, const char *fmt, ...); int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev); void bdi_unregister(struct backing_dev_info *bdi); +void bdi_start_writeback(struct writeback_control *wbc); +int bdi_writeback_task(struct bdi_writeback *wb); +int bdi_has_dirty_io(struct backing_dev_info *bdi); -extern struct mutex bdi_lock; +extern spinlock_t bdi_lock; extern struct list_head bdi_list; +static inline int wb_has_dirty_io(struct bdi_writeback *wb) +{ + return !list_empty(&wb->b_dirty) || + !list_empty(&wb->b_io) || + !list_empty(&wb->b_more_io); +} + static inline void __add_bdi_stat(struct backing_dev_info *bdi, enum bdi_stat_item item, s64 amount) { @@ -270,6 +300,11 @@ static inline bool bdi_cap_swap_backed(struct backing_dev_info *bdi) return bdi->capabilities & BDI_CAP_SWAP_BACKED; } +static inline bool bdi_cap_flush_forker(struct backing_dev_info *bdi) +{ + return bdi == &default_backing_dev_info; +} + static inline bool mapping_cap_writeback_dirty(struct address_space *mapping) { return bdi_cap_writeback_dirty(mapping->backing_dev_info); @@ -285,4 +320,10 @@ static inline bool mapping_cap_swap_backed(struct address_space *mapping) return bdi_cap_swap_backed(mapping->backing_dev_info); } +static inline int bdi_sched_wait(void *word) +{ + schedule(); + return 0; +} + #endif /* _LINUX_BACKING_DEV_H */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 56371be..26da98f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1786,6 +1786,7 @@ extern int get_sb_pseudo(struct file_system_type *, char *, struct vfsmount *mnt); extern void simple_set_mnt(struct vfsmount *mnt, struct super_block *sb); int __put_super_and_need_restart(struct super_block *sb); +void put_super(struct super_block *sb); /* Alas, no aliases. Too much hassle with bringing module.h everywhere */ #define fops_get(fops) \ @@ -2182,7 +2183,6 @@ extern int bdev_read_only(struct block_device *); extern int set_blocksize(struct block_device *, int); extern int sb_set_blocksize(struct super_block *, int); extern int sb_min_blocksize(struct super_block *, int); -extern int sb_has_dirty_inodes(struct super_block *); extern int generic_file_mmap(struct file *, struct vm_area_struct *); extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 0703929..cef7552 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -40,6 +40,8 @@ enum writeback_sync_modes { struct writeback_control { struct backing_dev_info *bdi; /* If !NULL, only write back this queue */ + struct super_block *sb; /* if !NULL, only write inodes from + this super_block */ enum writeback_sync_modes sync_mode; unsigned long *older_than_this; /* If !NULL, only write back inodes older than this */ @@ -76,10 +78,13 @@ struct writeback_control { /* * fs/fs-writeback.c */ -void writeback_inodes(struct writeback_control *wbc); +struct bdi_writeback; int inode_wait(void *); long writeback_inodes_sb(struct super_block *); long sync_inodes_sb(struct super_block *); +void writeback_inodes_wbc(struct writeback_control *wbc); +long wb_do_writeback(struct bdi_writeback *wb, int force_wait); +void wakeup_flusher_threads(long nr_pages); /* writeback.h requires fs.h; it, too, is not included from here. */ static inline void wait_on_inode(struct inode *inode) @@ -99,7 +104,6 @@ static inline void inode_sync_wait(struct inode *inode) /* * mm/page-writeback.c */ -int wakeup_pdflush(long nr_pages); void laptop_io_completion(void); void laptop_sync_completion(void); void throttle_vm_writeout(gfp_t gfp_mask); diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 6f163e0..7f3fa79 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -1,8 +1,11 @@ #include <linux/wait.h> #include <linux/backing-dev.h> +#include <linux/kthread.h> +#include <linux/freezer.h> #include <linux/fs.h> #include <linux/pagemap.h> +#include <linux/mm.h> #include <linux/sched.h> #include <linux/module.h> #include <linux/writeback.h> @@ -22,8 +25,18 @@ struct backing_dev_info default_backing_dev_info = { EXPORT_SYMBOL_GPL(default_backing_dev_info); static struct class *bdi_class; -DEFINE_MUTEX(bdi_lock); +DEFINE_SPINLOCK(bdi_lock); LIST_HEAD(bdi_list); +LIST_HEAD(bdi_pending_list); + +static struct task_struct *sync_supers_tsk; +static struct timer_list sync_supers_timer; + +static int bdi_sync_supers(void *); +static void sync_supers_timer_fn(unsigned long); +static void arm_supers_timer(void); + +static void bdi_add_default_flusher_task(struct backing_dev_info *bdi); #ifdef CONFIG_DEBUG_FS #include <linux/debugfs.h> @@ -187,6 +200,13 @@ static int __init default_bdi_init(void) { int err; + sync_supers_tsk = kthread_run(bdi_sync_supers, NULL, "sync_supers"); + BUG_ON(IS_ERR(sync_supers_tsk)); + + init_timer(&sync_supers_timer); + setup_timer(&sync_supers_timer, sync_supers_timer_fn, 0); + arm_supers_timer(); + err = bdi_init(&default_backing_dev_info); if (!err) bdi_register(&default_backing_dev_info, NULL, "default"); @@ -195,6 +215,242 @@ static int __init default_bdi_init(void) } subsys_initcall(default_bdi_init); +static void bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi) +{ + memset(wb, 0, sizeof(*wb)); + + wb->bdi = bdi; + wb->last_old_flush = jiffies; + INIT_LIST_HEAD(&wb->b_dirty); + INIT_LIST_HEAD(&wb->b_io); + INIT_LIST_HEAD(&wb->b_more_io); +} + +static void bdi_task_init(struct backing_dev_info *bdi, + struct bdi_writeback *wb) +{ + struct task_struct *tsk = current; + + spin_lock(&bdi->wb_lock); + list_add_tail_rcu(&wb->list, &bdi->wb_list); + spin_unlock(&bdi->wb_lock); + + tsk->flags |= PF_FLUSHER | PF_SWAPWRITE; + set_freezable(); + + /* + * Our parent may run at a different priority, just set us to normal + */ + set_user_nice(tsk, 0); +} + +static int bdi_start_fn(void *ptr) +{ + struct bdi_writeback *wb = ptr; + struct backing_dev_info *bdi = wb->bdi; + int ret; + + /* + * Add us to the active bdi_list + */ + spin_lock(&bdi_lock); + list_add(&bdi->bdi_list, &bdi_list); + spin_unlock(&bdi_lock); + + bdi_task_init(bdi, wb); + + /* + * Clear pending bit and wakeup anybody waiting to tear us down + */ + clear_bit(BDI_pending, &bdi->state); + smp_mb__after_clear_bit(); + wake_up_bit(&bdi->state, BDI_pending); + + ret = bdi_writeback_task(wb); + + /* + * Remove us from the list + */ + spin_lock(&bdi->wb_lock); + list_del_rcu(&wb->list); + spin_unlock(&bdi->wb_lock); + + /* + * Flush any work that raced with us exiting. No new work + * will be added, since this bdi isn't discoverable anymore. + */ + if (!list_empty(&bdi->work_list)) + wb_do_writeback(wb, 1); + + wb->task = NULL; + return ret; +} + +int bdi_has_dirty_io(struct backing_dev_info *bdi) +{ + return wb_has_dirty_io(&bdi->wb); +} + +static void bdi_flush_io(struct backing_dev_info *bdi) +{ + struct writeback_control wbc = { + .bdi = bdi, + .sync_mode = WB_SYNC_NONE, + .older_than_this = NULL, + .range_cyclic = 1, + .nr_to_write = 1024, + }; + + writeback_inodes_wbc(&wbc); +} + +/* + * kupdated() used to do this. We cannot do it from the bdi_forker_task() + * or we risk deadlocking on ->s_umount. The longer term solution would be + * to implement sync_supers_bdi() or similar and simply do it from the + * bdi writeback tasks individually. + */ +static int bdi_sync_supers(void *unused) +{ + set_user_nice(current, 0); + + while (!kthread_should_stop()) { + set_current_state(TASK_INTERRUPTIBLE); + schedule(); + + /* + * Do this periodically, like kupdated() did before. + */ + sync_supers(); + } + + return 0; +} + +static void arm_supers_timer(void) +{ + unsigned long next; + + next = msecs_to_jiffies(dirty_writeback_interval * 10) + jiffies; + mod_timer(&sync_supers_timer, round_jiffies_up(next)); +} + +static void sync_supers_timer_fn(unsigned long unused) +{ + wake_up_process(sync_supers_tsk); + arm_supers_timer(); +} + +static int bdi_forker_task(void *ptr) +{ + struct bdi_writeback *me = ptr; + + bdi_task_init(me->bdi, me); + + for (;;) { + struct backing_dev_info *bdi, *tmp; + struct bdi_writeback *wb; + + /* + * Temporary measure, we want to make sure we don't see + * dirty data on the default backing_dev_info + */ + if (wb_has_dirty_io(me) || !list_empty(&me->bdi->work_list)) + wb_do_writeback(me, 0); + + spin_lock(&bdi_lock); + + /* + * Check if any existing bdi's have dirty data without + * a thread registered. If so, set that up. + */ + list_for_each_entry_safe(bdi, tmp, &bdi_list, bdi_list) { + if (bdi->wb.task) + continue; + if (list_empty(&bdi->work_list) && + !bdi_has_dirty_io(bdi)) + continue; + + bdi_add_default_flusher_task(bdi); + } + + set_current_state(TASK_INTERRUPTIBLE); + + if (list_empty(&bdi_pending_list)) { + unsigned long wait; + + spin_unlock(&bdi_lock); + wait = msecs_to_jiffies(dirty_writeback_interval * 10); + schedule_timeout(wait); + try_to_freeze(); + continue; + } + + __set_current_state(TASK_RUNNING); + + /* + * This is our real job - check for pending entries in + * bdi_pending_list, and create the tasks that got added + */ + bdi = list_entry(bdi_pending_list.next, struct backing_dev_info, + bdi_list); + list_del_init(&bdi->bdi_list); + spin_unlock(&bdi_lock); + + wb = &bdi->wb; + wb->task = kthread_run(bdi_start_fn, wb, "flush-%s", + dev_name(bdi->dev)); + /* + * If task creation fails, then readd the bdi to + * the pending list and force writeout of the bdi + * from this forker thread. That will free some memory + * and we can try again. + */ + if (IS_ERR(wb->task)) { + wb->task = NULL; + + /* + * Add this 'bdi' to the back, so we get + * a chance to flush other bdi's to free + * memory. + */ + spin_lock(&bdi_lock); + list_add_tail(&bdi->bdi_list, &bdi_pending_list); + spin_unlock(&bdi_lock); + + bdi_flush_io(bdi); + } + } + + return 0; +} + +/* + * Add the default flusher task that gets created for any bdi + * that has dirty data pending writeout + */ +void static bdi_add_default_flusher_task(struct backing_dev_info *bdi) +{ + if (!bdi_cap_writeback_dirty(bdi)) + return; + + /* + * Check with the helper whether to proceed adding a task. Will only + * abort if we two or more simultanous calls to + * bdi_add_default_flusher_task() occured, further additions will block + * waiting for previous additions to finish. + */ + if (!test_and_set_bit(BDI_pending, &bdi->state)) { + list_move_tail(&bdi->bdi_list, &bdi_pending_list); + + /* + * We are now on the pending list, wake up bdi_forker_task() + * to finish the job and add us back to the active bdi_list + */ + wake_up_process(default_backing_dev_info.wb.task); + } +} + int bdi_register(struct backing_dev_info *bdi, struct device *parent, const char *fmt, ...) { @@ -213,13 +469,34 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent, goto exit; } - mutex_lock(&bdi_lock); + spin_lock(&bdi_lock); list_add_tail(&bdi->bdi_list, &bdi_list); - mutex_unlock(&bdi_lock); + spin_unlock(&bdi_lock); bdi->dev = dev; - bdi_debug_register(bdi, dev_name(dev)); + /* + * Just start the forker thread for our default backing_dev_info, + * and add other bdi's to the list. They will get a thread created + * on-demand when they need it. + */ + if (bdi_cap_flush_forker(bdi)) { + struct bdi_writeback *wb = &bdi->wb; + + wb->task = kthread_run(bdi_forker_task, wb, "bdi-%s", + dev_name(dev)); + if (IS_ERR(wb->task)) { + wb->task = NULL; + ret = -ENOMEM; + + spin_lock(&bdi_lock); + list_del(&bdi->bdi_list); + spin_unlock(&bdi_lock); + goto exit; + } + } + + bdi_debug_register(bdi, dev_name(dev)); exit: return ret; } @@ -231,17 +508,42 @@ int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev) } EXPORT_SYMBOL(bdi_register_dev); -static void bdi_remove_from_list(struct backing_dev_info *bdi) +/* + * Remove bdi from the global list and shutdown any threads we have running + */ +static void bdi_wb_shutdown(struct backing_dev_info *bdi) { - mutex_lock(&bdi_lock); + struct bdi_writeback *wb; + + if (!bdi_cap_writeback_dirty(bdi)) + return; + + /* + * If setup is pending, wait for that to complete first + */ + wait_on_bit(&bdi->state, BDI_pending, bdi_sched_wait, + TASK_UNINTERRUPTIBLE); + + /* + * Make sure nobody finds us on the bdi_list anymore + */ + spin_lock(&bdi_lock); list_del(&bdi->bdi_list); - mutex_unlock(&bdi_lock); + spin_unlock(&bdi_lock); + + /* + * Finally, kill the kernel threads. We don't need to be RCU + * safe anymore, since the bdi is gone from visibility. + */ + list_for_each_entry(wb, &bdi->wb_list, list) + kthread_stop(wb->task); } void bdi_unregister(struct backing_dev_info *bdi) { if (bdi->dev) { - bdi_remove_from_list(bdi); + if (!bdi_cap_flush_forker(bdi)) + bdi_wb_shutdown(bdi); bdi_debug_unregister(bdi); device_unregister(bdi->dev); bdi->dev = NULL; @@ -251,18 +553,25 @@ EXPORT_SYMBOL(bdi_unregister); int bdi_init(struct backing_dev_info *bdi) { - int i; - int err; + int i, err; bdi->dev = NULL; bdi->min_ratio = 0; bdi->max_ratio = 100; bdi->max_prop_frac = PROP_FRAC_BASE; + spin_lock_init(&bdi->wb_lock); INIT_LIST_HEAD(&bdi->bdi_list); - INIT_LIST_HEAD(&bdi->b_io); - INIT_LIST_HEAD(&bdi->b_dirty); - INIT_LIST_HEAD(&bdi->b_more_io); + INIT_LIST_HEAD(&bdi->wb_list); + INIT_LIST_HEAD(&bdi->work_list); + + bdi_wb_init(&bdi->wb, bdi); + + /* + * Just one thread support for now, hard code mask and count + */ + bdi->wb_mask = 1; + bdi->wb_cnt = 1; for (i = 0; i < NR_BDI_STAT_ITEMS; i++) { err = percpu_counter_init(&bdi->bdi_stat[i], 0); @@ -277,8 +586,6 @@ int bdi_init(struct backing_dev_info *bdi) err: while (i--) percpu_counter_destroy(&bdi->bdi_stat[i]); - - bdi_remove_from_list(bdi); } return err; @@ -289,9 +596,7 @@ void bdi_destroy(struct backing_dev_info *bdi) { int i; - WARN_ON(!list_empty(&bdi->b_dirty)); - WARN_ON(!list_empty(&bdi->b_io)); - WARN_ON(!list_empty(&bdi->b_more_io)); + WARN_ON(bdi_has_dirty_io(bdi)); bdi_unregister(bdi); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index f8341b6..25e7770 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -36,15 +36,6 @@ #include <linux/pagevec.h> /* - * The maximum number of pages to writeout in a single bdflush/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 - -/* * After a CPU has dirtied this many pages, balance_dirty_pages_ratelimited * will look to see if it needs to force writeback or throttling. */ @@ -117,8 +108,6 @@ EXPORT_SYMBOL(laptop_mode); /* End of sysctl-exported parameters */ -static void background_writeout(unsigned long _min_pages); - /* * Scale the writeback cache size proportional to the relative writeout speeds. * @@ -326,7 +315,7 @@ int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio) { int ret = 0; - mutex_lock(&bdi_lock); + spin_lock(&bdi_lock); if (min_ratio > bdi->max_ratio) { ret = -EINVAL; } else { @@ -338,7 +327,7 @@ int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio) ret = -EINVAL; } } - mutex_unlock(&bdi_lock); + spin_unlock(&bdi_lock); return ret; } @@ -350,14 +339,14 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned max_ratio) if (max_ratio > 100) return -EINVAL; - mutex_lock(&bdi_lock); + spin_lock(&bdi_lock); if (bdi->min_ratio > max_ratio) { ret = -EINVAL; } else { bdi->max_ratio = max_ratio; bdi->max_prop_frac = (PROP_FRAC_BASE * max_ratio) / 100; } - mutex_unlock(&bdi_lock); + spin_unlock(&bdi_lock); return ret; } @@ -543,7 +532,7 @@ static void balance_dirty_pages(struct address_space *mapping) * up. */ if (bdi_nr_reclaimable > bdi_thresh) { - writeback_inodes(&wbc); + writeback_inodes_wbc(&wbc); pages_written += write_chunk - wbc.nr_to_write; get_dirty_limits(&background_thresh, &dirty_thresh, &bdi_thresh, bdi); @@ -572,7 +561,7 @@ static void balance_dirty_pages(struct address_space *mapping) if (pages_written >= write_chunk) break; /* We've done our duty */ - congestion_wait(BLK_RW_ASYNC, HZ/10); + schedule_timeout(1); } if (bdi_nr_reclaimable + bdi_nr_writeback < bdi_thresh && @@ -591,10 +580,18 @@ static void balance_dirty_pages(struct address_space *mapping) * background_thresh, to keep the amount of dirty memory low. */ if ((laptop_mode && pages_written) || - (!laptop_mode && (global_page_state(NR_FILE_DIRTY) - + global_page_state(NR_UNSTABLE_NFS) - > background_thresh))) - pdflush_operation(background_writeout, 0); + (!laptop_mode && ((nr_writeback = global_page_state(NR_FILE_DIRTY) + + global_page_state(NR_UNSTABLE_NFS)) + > background_thresh))) { + struct writeback_control wbc = { + .bdi = bdi, + .sync_mode = WB_SYNC_NONE, + .nr_to_write = nr_writeback, + }; + + + bdi_start_writeback(&wbc); + } } void set_page_dirty_balance(struct page *page, int page_mkwrite) @@ -678,153 +675,35 @@ void throttle_vm_writeout(gfp_t gfp_mask) } } -/* - * writeback at least _min_pages, and keep writing until the amount of dirty - * memory is less than the background threshold, or until we're all clean. - */ -static void background_writeout(unsigned long _min_pages) -{ - long min_pages = _min_pages; - struct writeback_control wbc = { - .bdi = NULL, - .sync_mode = WB_SYNC_NONE, - .older_than_this = NULL, - .nr_to_write = 0, - .nonblocking = 1, - .range_cyclic = 1, - }; - - for ( ; ; ) { - unsigned long background_thresh; - unsigned long dirty_thresh; - - get_dirty_limits(&background_thresh, &dirty_thresh, NULL, NULL); - if (global_page_state(NR_FILE_DIRTY) + - global_page_state(NR_UNSTABLE_NFS) < background_thresh - && min_pages <= 0) - break; - wbc.more_io = 0; - wbc.encountered_congestion = 0; - wbc.nr_to_write = MAX_WRITEBACK_PAGES; - wbc.pages_skipped = 0; - writeback_inodes(&wbc); - min_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write; - if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) { - /* Wrote less than expected */ - if (wbc.encountered_congestion || wbc.more_io) - congestion_wait(BLK_RW_ASYNC, HZ/10); - else - break; - } - } -} - -/* - * Start writeback of `nr_pages' pages. If `nr_pages' is zero, write back - * the whole world. Returns 0 if a pdflush thread was dispatched. Returns - * -1 if all pdflush threads were busy. - */ -int wakeup_pdflush(long nr_pages) -{ - if (nr_pages == 0) - nr_pages = global_page_state(NR_FILE_DIRTY) + - global_page_state(NR_UNSTABLE_NFS); - return pdflush_operation(background_writeout, nr_pages); -} - -static void wb_timer_fn(unsigned long unused); static void laptop_timer_fn(unsigned long unused); -static DEFINE_TIMER(wb_timer, wb_timer_fn, 0, 0); static DEFINE_TIMER(laptop_mode_wb_timer, laptop_timer_fn, 0, 0); /* - * 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 void wb_kupdate(unsigned long arg) -{ - unsigned long oldest_jif; - unsigned long start_jif; - unsigned long next_jif; - long nr_to_write; - struct writeback_control wbc = { - .bdi = NULL, - .sync_mode = WB_SYNC_NONE, - .older_than_this = &oldest_jif, - .nr_to_write = 0, - .nonblocking = 1, - .for_kupdate = 1, - .range_cyclic = 1, - }; - - sync_supers(); - - oldest_jif = jiffies - msecs_to_jiffies(dirty_expire_interval * 10); - start_jif = jiffies; - next_jif = start_jif + msecs_to_jiffies(dirty_writeback_interval * 10); - nr_to_write = global_page_state(NR_FILE_DIRTY) + - global_page_state(NR_UNSTABLE_NFS) + - (inodes_stat.nr_inodes - inodes_stat.nr_unused); - while (nr_to_write > 0) { - wbc.more_io = 0; - wbc.encountered_congestion = 0; - wbc.nr_to_write = MAX_WRITEBACK_PAGES; - writeback_inodes(&wbc); - if (wbc.nr_to_write > 0) { - if (wbc.encountered_congestion || wbc.more_io) - congestion_wait(BLK_RW_ASYNC, HZ/10); - else - break; /* All the old data is written */ - } - nr_to_write -= MAX_WRITEBACK_PAGES - wbc.nr_to_write; - } - if (time_before(next_jif, jiffies + HZ)) - next_jif = jiffies + HZ; - if (dirty_writeback_interval) - mod_timer(&wb_timer, next_jif); -} - -/* * sysctl handler for /proc/sys/vm/dirty_writeback_centisecs */ int dirty_writeback_centisecs_handler(ctl_table *table, int write, struct file *file, void __user *buffer, size_t *length, loff_t *ppos) { proc_dointvec(table, write, file, buffer, length, ppos); - if (dirty_writeback_interval) - mod_timer(&wb_timer, jiffies + - msecs_to_jiffies(dirty_writeback_interval * 10)); - else - del_timer(&wb_timer); return 0; } -static void wb_timer_fn(unsigned long unused) -{ - if (pdflush_operation(wb_kupdate, 0) < 0) - mod_timer(&wb_timer, jiffies + HZ); /* delay 1 second */ -} - -static void laptop_flush(unsigned long unused) +static void do_laptop_sync(struct work_struct *work) { - sys_sync(); + wakeup_flusher_threads(0); + kfree(work); } static void laptop_timer_fn(unsigned long unused) { - pdflush_operation(laptop_flush, 0); + struct work_struct *work; + + work = kmalloc(sizeof(*work), GFP_ATOMIC); + if (work) { + INIT_WORK(work, do_laptop_sync); + schedule_work(work); + } } /* @@ -907,8 +786,6 @@ void __init page_writeback_init(void) { int shift; - mod_timer(&wb_timer, - jiffies + msecs_to_jiffies(dirty_writeback_interval * 10)); writeback_set_ratelimit(); register_cpu_notifier(&ratelimit_nb); diff --git a/mm/vmscan.c b/mm/vmscan.c index 94e86dd..ba8228e 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1720,7 +1720,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, */ if (total_scanned > sc->swap_cluster_max + sc->swap_cluster_max / 2) { - wakeup_pdflush(laptop_mode ? 0 : total_scanned); + wakeup_flusher_threads(laptop_mode ? 0 : total_scanned); sc->may_writepage = 1; } |
