diff options
Diffstat (limited to 'fs/fs-writeback.c')
| -rw-r--r-- | fs/fs-writeback.c | 1761 |
1 files changed, 1216 insertions, 545 deletions
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 06557679ca4..be568b7311d 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -8,136 +8,187 @@ * pages against inodes. ie: data writeback. Writeout of the * inode itself is not handled here. * - * 10Apr2002 akpm@zip.com.au + * 10Apr2002 Andrew Morton * Split out of fs/inode.c * Additions for address_space-based writeback */ #include <linux/kernel.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/spinlock.h> +#include <linux/slab.h> #include <linux/sched.h> #include <linux/fs.h> #include <linux/mm.h> +#include <linux/pagemap.h> +#include <linux/kthread.h> #include <linux/writeback.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> -#include <linux/buffer_head.h> +#include <linux/tracepoint.h> +#include <linux/device.h> #include "internal.h" +/* + * 4MB minimal write chunk size + */ +#define MIN_WRITEBACK_PAGES (4096UL >> (PAGE_CACHE_SHIFT - 10)) + +/* + * Passed into wb_writeback(), essentially a subset of writeback_control + */ +struct wb_writeback_work { + long nr_pages; + struct super_block *sb; + unsigned long *older_than_this; + enum writeback_sync_modes sync_mode; + unsigned int tagged_writepages:1; + unsigned int for_kupdate:1; + unsigned int range_cyclic:1; + unsigned int for_background:1; + unsigned int for_sync:1; /* sync(2) WB_SYNC_ALL writeback */ + enum wb_reason reason; /* why was writeback initiated? */ + + struct list_head list; /* pending work list */ + struct completion *done; /* set if the caller waits */ +}; + /** - * __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. + * writeback_in_progress - determine whether there is writeback in progress + * @bdi: the device's backing_dev_info structure. * - * 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. + * Determine whether there is writeback waiting to be handled against a + * backing device. */ -void __mark_inode_dirty(struct inode *inode, int flags) +int writeback_in_progress(struct backing_dev_info *bdi) +{ + return test_bit(BDI_writeback_running, &bdi->state); +} +EXPORT_SYMBOL(writeback_in_progress); + +static inline struct backing_dev_info *inode_to_bdi(struct inode *inode) { struct super_block *sb = inode->i_sb; - /* - * 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); - } + if (sb_is_blkdev_sb(sb)) + return inode->i_mapping->backing_dev_info; - /* - * make sure that changes are seen by all cpus before we test i_state - * -- mikulas - */ - smp_mb(); + return sb->s_bdi; +} - /* avoid the locking if we can */ - if ((inode->i_state & flags) == flags) - return; +static inline struct inode *wb_inode(struct list_head *head) +{ + return list_entry(head, struct inode, i_wb_list); +} - if (unlikely(block_dump)) { - struct dentry *dentry = NULL; - const char *name = "?"; +/* + * Include the creation of the trace points after defining the + * wb_writeback_work structure and inline functions so that the definition + * remains local to this file. + */ +#define CREATE_TRACE_POINTS +#include <trace/events/writeback.h> - if (!list_empty(&inode->i_dentry)) { - dentry = list_entry(inode->i_dentry.next, - struct dentry, d_alias); - if (dentry && dentry->d_name.name) - name = (const char *) dentry->d_name.name; - } +EXPORT_TRACEPOINT_SYMBOL_GPL(wbc_writepage); + +static void bdi_wakeup_thread(struct backing_dev_info *bdi) +{ + spin_lock_bh(&bdi->wb_lock); + if (test_bit(BDI_registered, &bdi->state)) + mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0); + spin_unlock_bh(&bdi->wb_lock); +} - if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev")) - 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); +static void bdi_queue_work(struct backing_dev_info *bdi, + struct wb_writeback_work *work) +{ + trace_writeback_queue(bdi, work); + + spin_lock_bh(&bdi->wb_lock); + if (!test_bit(BDI_registered, &bdi->state)) { + if (work->done) + complete(work->done); + goto out_unlock; } + list_add_tail(&work->list, &bdi->work_list); + mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0); +out_unlock: + spin_unlock_bh(&bdi->wb_lock); +} - spin_lock(&inode_lock); - if ((inode->i_state & flags) != flags) { - const int was_dirty = inode->i_state & I_DIRTY; +static void +__bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages, + bool range_cyclic, enum wb_reason reason) +{ + struct wb_writeback_work *work; - inode->i_state |= flags; + /* + * This is WB_SYNC_NONE writeback, so if allocation fails just + * wakeup the thread for old dirty data writeback + */ + work = kzalloc(sizeof(*work), GFP_ATOMIC); + if (!work) { + trace_writeback_nowork(bdi); + bdi_wakeup_thread(bdi); + return; + } - /* - * 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; + work->sync_mode = WB_SYNC_NONE; + work->nr_pages = nr_pages; + work->range_cyclic = range_cyclic; + work->reason = reason; - /* - * 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; + bdi_queue_work(bdi, work); +} - /* - * 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); - } - } -out: - spin_unlock(&inode_lock); +/** + * bdi_start_writeback - start writeback + * @bdi: the backing device to write from + * @nr_pages: the number of pages to write + * @reason: reason why some writeback work was initiated + * + * Description: + * This does WB_SYNC_NONE opportunistic writeback. The IO is only + * started when this function returns, we make no guarantees on + * completion. Caller need not hold sb s_umount semaphore. + * + */ +void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages, + enum wb_reason reason) +{ + __bdi_start_writeback(bdi, nr_pages, true, reason); } -EXPORT_SYMBOL(__mark_inode_dirty); +/** + * bdi_start_background_writeback - start background writeback + * @bdi: the backing device to write from + * + * Description: + * This makes sure WB_SYNC_NONE background writeback happens. When + * this function returns, it is only guaranteed that for given BDI + * some IO is happening if we are over background dirty threshold. + * Caller need not hold sb s_umount semaphore. + */ +void bdi_start_background_writeback(struct backing_dev_info *bdi) +{ + /* + * We just wake up the flusher thread. It will perform background + * writeback as soon as there is no other work to do. + */ + trace_writeback_wake_background(bdi); + bdi_wakeup_thread(bdi); +} -static int write_inode(struct inode *inode, int sync) +/* + * Remove the inode from the writeback list it is on. + */ +void inode_wb_list_del(struct inode *inode) { - 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 backing_dev_info *bdi = inode_to_bdi(inode); + + spin_lock(&bdi->wb.list_lock); + list_del_init(&inode->i_wb_list); + spin_unlock(&bdi->wb.list_lock); } /* @@ -145,500 +196,1203 @@ 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) +static void redirty_tail(struct inode *inode, struct bdi_writeback *wb) { - struct super_block *sb = inode->i_sb; - - if (!list_empty(&sb->s_dirty)) { - struct inode *tail_inode; + assert_spin_locked(&wb->list_lock); + if (!list_empty(&wb->b_dirty)) { + struct inode *tail; - tail_inode = list_entry(sb->s_dirty.next, struct inode, i_list); - if (!time_after_eq(inode->dirtied_when, - tail_inode->dirtied_when)) + tail = wb_inode(wb->b_dirty.next); + 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_wb_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) +static void requeue_io(struct inode *inode, struct bdi_writeback *wb) { - list_move(&inode->i_list, &inode->i_sb->s_more_io); + assert_spin_locked(&wb->list_lock); + list_move(&inode->i_wb_list, &wb->b_more_io); } static void inode_sync_complete(struct inode *inode) { - /* - * Prevent speculative execution through spin_unlock(&inode_lock); - */ + inode->i_state &= ~I_SYNC; + /* If inode is clean an unused, put it into LRU now... */ + inode_add_lru(inode); + /* Waiters must see I_SYNC cleared before being woken up */ smp_mb(); wake_up_bit(&inode->i_state, __I_SYNC); } +static bool inode_dirtied_after(struct inode *inode, unsigned long t) +{ + bool ret = time_after(inode->dirtied_when, t); +#ifndef CONFIG_64BIT + /* + * For inodes being constantly redirtied, dirtied_when can get stuck. + * It _appears_ to be in the future, but is actually in distant past. + * This test is necessary to prevent such wrapped-around relative times + * from permanently stopping the whole bdi writeback. + */ + ret = ret && time_before_eq(inode->dirtied_when, jiffies); +#endif + return ret; +} + /* - * Move expired dirty inodes from @delaying_queue to @dispatch_queue. + * Move expired (dirtied before work->older_than_this) dirty inodes from + * @delaying_queue to @dispatch_queue. */ -static void move_expired_inodes(struct list_head *delaying_queue, +static int move_expired_inodes(struct list_head *delaying_queue, struct list_head *dispatch_queue, - unsigned long *older_than_this) + struct wb_writeback_work *work) { + LIST_HEAD(tmp); + struct list_head *pos, *node; + struct super_block *sb = NULL; + struct inode *inode; + int do_sb_sort = 0; + int moved = 0; + while (!list_empty(delaying_queue)) { - struct inode *inode = list_entry(delaying_queue->prev, - struct inode, i_list); - if (older_than_this && - time_after(inode->dirtied_when, *older_than_this)) + inode = wb_inode(delaying_queue->prev); + if (work->older_than_this && + inode_dirtied_after(inode, *work->older_than_this)) break; - list_move(&inode->i_list, dispatch_queue); + list_move(&inode->i_wb_list, &tmp); + moved++; + if (sb_is_blkdev_sb(inode->i_sb)) + continue; + if (sb && sb != inode->i_sb) + do_sb_sort = 1; + sb = inode->i_sb; + } + + /* just one sb in list, splice to dispatch_queue and we're done */ + if (!do_sb_sort) { + list_splice(&tmp, dispatch_queue); + goto out; + } + + /* Move inodes from one superblock together */ + while (!list_empty(&tmp)) { + sb = wb_inode(tmp.prev)->i_sb; + list_for_each_prev_safe(pos, node, &tmp) { + inode = wb_inode(pos); + if (inode->i_sb == sb) + list_move(&inode->i_wb_list, dispatch_queue); + } } +out: + return moved; } /* * Queue all expired dirty inodes for io, eldest first. + * Before + * newly dirtied b_dirty b_io b_more_io + * =============> gf edc BA + * After + * newly dirtied b_dirty b_io b_more_io + * =============> g fBAedc + * | + * +--> dequeue for IO */ -static void queue_io(struct super_block *sb, - unsigned long *older_than_this) +static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work) { - list_splice_init(&sb->s_more_io, sb->s_io.prev); - move_expired_inodes(&sb->s_dirty, &sb->s_io, older_than_this); + int moved; + assert_spin_locked(&wb->list_lock); + list_splice_init(&wb->b_more_io, &wb->b_io); + moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, work); + trace_writeback_queue_io(wb, work, moved); } -int sb_has_dirty_inodes(struct super_block *sb) +static int write_inode(struct inode *inode, struct writeback_control *wbc) { - return !list_empty(&sb->s_dirty) || - !list_empty(&sb->s_io) || - !list_empty(&sb->s_more_io); + int ret; + + if (inode->i_sb->s_op->write_inode && !is_bad_inode(inode)) { + trace_writeback_write_inode_start(inode, wbc); + ret = inode->i_sb->s_op->write_inode(inode, wbc); + trace_writeback_write_inode(inode, wbc); + return ret; + } + return 0; } -EXPORT_SYMBOL(sb_has_dirty_inodes); /* - * Write a single inode's dirty pages and inode data out to disk. - * If `wait' is set, wait on the writeout. - * - * The whole writeout design is quite complex and fragile. We want to avoid - * starvation of particular inodes when others are being redirtied, prevent - * livelocks, etc. - * - * Called under inode_lock. + * Wait for writeback on an inode to complete. Called with i_lock held. + * Caller must make sure inode cannot go away when we drop i_lock. + */ +static void __inode_wait_for_writeback(struct inode *inode) + __releases(inode->i_lock) + __acquires(inode->i_lock) +{ + DEFINE_WAIT_BIT(wq, &inode->i_state, __I_SYNC); + wait_queue_head_t *wqh; + + wqh = bit_waitqueue(&inode->i_state, __I_SYNC); + while (inode->i_state & I_SYNC) { + spin_unlock(&inode->i_lock); + __wait_on_bit(wqh, &wq, inode_wait, TASK_UNINTERRUPTIBLE); + spin_lock(&inode->i_lock); + } +} + +/* + * Wait for writeback on an inode to complete. Caller must have inode pinned. + */ +void inode_wait_for_writeback(struct inode *inode) +{ + spin_lock(&inode->i_lock); + __inode_wait_for_writeback(inode); + spin_unlock(&inode->i_lock); +} + +/* + * Sleep until I_SYNC is cleared. This function must be called with i_lock + * held and drops it. It is aimed for callers not holding any inode reference + * so once i_lock is dropped, inode can go away. + */ +static void inode_sleep_on_writeback(struct inode *inode) + __releases(inode->i_lock) +{ + DEFINE_WAIT(wait); + wait_queue_head_t *wqh = bit_waitqueue(&inode->i_state, __I_SYNC); + int sleep; + + prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE); + sleep = inode->i_state & I_SYNC; + spin_unlock(&inode->i_lock); + if (sleep) + schedule(); + finish_wait(wqh, &wait); +} + +/* + * Find proper writeback list for the inode depending on its current state and + * possibly also change of its state while we were doing writeback. Here we + * handle things such as livelock prevention or fairness of writeback among + * inodes. This function can be called only by flusher thread - noone else + * processes all inodes in writeback lists and requeueing inodes behind flusher + * thread's back can have unexpected consequences. + */ +static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, + struct writeback_control *wbc) +{ + if (inode->i_state & I_FREEING) + return; + + /* + * Sync livelock prevention. Each inode is tagged and synced in one + * shot. If still dirty, it will be redirty_tail()'ed below. Update + * the dirty time to prevent enqueue and sync it again. + */ + if ((inode->i_state & I_DIRTY) && + (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)) + inode->dirtied_when = jiffies; + + if (wbc->pages_skipped) { + /* + * writeback is not making progress due to locked + * buffers. Skip this inode for now. + */ + redirty_tail(inode, wb); + return; + } + + if (mapping_tagged(inode->i_mapping, PAGECACHE_TAG_DIRTY)) { + /* + * We didn't write back all the pages. nfs_writepages() + * sometimes bales out without doing anything. + */ + if (wbc->nr_to_write <= 0) { + /* Slice used up. Queue for next turn. */ + requeue_io(inode, wb); + } else { + /* + * Writeback blocked by something other than + * congestion. Delay the inode for some time to + * avoid spinning on the CPU (100% iowait) + * retrying writeback of the dirty page/inode + * that cannot be performed immediately. + */ + redirty_tail(inode, wb); + } + } else if (inode->i_state & I_DIRTY) { + /* + * Filesystems can dirty the inode during writeback operations, + * such as delayed allocation during submission or metadata + * updates after data IO completion. + */ + redirty_tail(inode, wb); + } else { + /* The inode is clean. Remove from writeback lists. */ + list_del_init(&inode->i_wb_list); + } +} + +/* + * Write out an inode and its dirty pages. Do not update the writeback list + * linkage. That is left to the caller. The caller is also responsible for + * setting I_SYNC flag and calling inode_sync_complete() to clear it. */ static int -__sync_single_inode(struct inode *inode, struct writeback_control *wbc) +__writeback_single_inode(struct inode *inode, struct writeback_control *wbc) { - unsigned dirty; struct address_space *mapping = inode->i_mapping; - int wait = wbc->sync_mode == WB_SYNC_ALL; + long nr_to_write = wbc->nr_to_write; + unsigned dirty; int ret; - BUG_ON(inode->i_state & I_SYNC); + WARN_ON(!(inode->i_state & I_SYNC)); - /* Set I_SYNC, reset I_DIRTY */ - dirty = inode->i_state & I_DIRTY; - inode->i_state |= I_SYNC; - inode->i_state &= ~I_DIRTY; - - spin_unlock(&inode_lock); + trace_writeback_single_inode_start(inode, wbc, nr_to_write); ret = do_writepages(mapping, wbc); - /* Don't write the inode if only I_DIRTY_PAGES was set */ - if (dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) { - int err = write_inode(inode, wait); + /* + * Make sure to wait on the data before writing out the metadata. + * This is important for filesystems that modify metadata on data + * I/O completion. We don't do it for sync(2) writeback because it has a + * separate, external IO completion path and ->sync_fs for guaranteeing + * inode metadata is written back correctly. + */ + if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync) { + int err = filemap_fdatawait(mapping); if (ret == 0) ret = err; } - if (wait) { - int err = filemap_fdatawait(mapping); + /* + * Some filesystems may redirty the inode during the writeback + * due to delalloc, clear dirty metadata flags right before + * write_inode() + */ + spin_lock(&inode->i_lock); + /* Clear I_DIRTY_PAGES if we've written out all dirty pages */ + if (!mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) + inode->i_state &= ~I_DIRTY_PAGES; + dirty = inode->i_state & I_DIRTY; + inode->i_state &= ~(I_DIRTY_SYNC | I_DIRTY_DATASYNC); + spin_unlock(&inode->i_lock); + /* Don't write the inode if only I_DIRTY_PAGES was set */ + if (dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) { + int err = write_inode(inode, wbc); if (ret == 0) ret = err; } - - spin_lock(&inode_lock); - inode->i_state &= ~I_SYNC; - if (!(inode->i_state & I_FREEING)) { - if (!(inode->i_state & I_DIRTY) && - mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) { - /* - * 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. - */ - /* - * akpm: if the caller was the kupdate function we put - * this inode at the head of s_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 - * reasons for doing it this way, and I'd rather not - * muck with it at present. - */ - if (wbc->for_kupdate) { - /* - * For the kupdate function we move the inode - * to s_more_io so it will get more writeout as - * soon as the queue becomes uncongested. - */ - inode->i_state |= I_DIRTY_PAGES; - if (wbc->nr_to_write <= 0) { - /* - * slice used up: queue for next turn - */ - requeue_io(inode); - } else { - /* - * somehow blocked: retry later - */ - redirty_tail(inode); - } - } else { - /* - * Otherwise fully redirty the inode so that - * other inodes on this superblock will get some - * writeout. Otherwise heavy writing to one - * file would indefinitely suspend writeout of - * all the other files. - */ - inode->i_state |= I_DIRTY_PAGES; - redirty_tail(inode); - } - } else if (inode->i_state & I_DIRTY) { - /* - * Someone redirtied the inode while were writing back - * the pages. - */ - redirty_tail(inode); - } else if (atomic_read(&inode->i_count)) { - /* - * The inode is clean, inuse - */ - list_move(&inode->i_list, &inode_in_use); - } else { - /* - * The inode is clean, unused - */ - list_move(&inode->i_list, &inode_unused); - } - } - inode_sync_complete(inode); + trace_writeback_single_inode(inode, wbc, nr_to_write); return ret; } /* - * Write out an inode's dirty pages. Called under inode_lock. Either the - * caller has ref on the inode (either via __iget or via syscall against an fd) - * or the inode has I_WILL_FREE set (via generic_forget_inode) + * Write out an inode's dirty pages. Either the caller has an active reference + * on the inode or the inode has I_WILL_FREE set. + * + * This function is designed to be called for writing back one inode which + * we go e.g. from filesystem. Flusher thread uses __writeback_single_inode() + * and does more profound writeback list handling in writeback_sb_inodes(). */ static int -__writeback_single_inode(struct inode *inode, struct writeback_control *wbc) +writeback_single_inode(struct inode *inode, struct bdi_writeback *wb, + struct writeback_control *wbc) { - wait_queue_head_t *wqh; + int ret = 0; + spin_lock(&inode->i_lock); if (!atomic_read(&inode->i_count)) WARN_ON(!(inode->i_state & (I_WILL_FREE|I_FREEING))); else WARN_ON(inode->i_state & I_WILL_FREE); - if ((wbc->sync_mode != WB_SYNC_ALL) && (inode->i_state & I_SYNC)) { + if (inode->i_state & I_SYNC) { + if (wbc->sync_mode != WB_SYNC_ALL) + goto out; /* - * We're skipping this inode because it's locked, and we're not - * doing writeback-for-data-integrity. Move it to s_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. + * It's a data-integrity sync. We must wait. Since callers hold + * inode reference or inode has I_WILL_FREE set, it cannot go + * away under us. */ - requeue_io(inode); - return 0; + __inode_wait_for_writeback(inode); } + WARN_ON(inode->i_state & I_SYNC); + /* + * Skip inode if it is clean and we have no outstanding writeback in + * WB_SYNC_ALL mode. We don't want to mess with writeback lists in this + * function since flusher thread may be doing for example sync in + * parallel and if we move the inode, it could get skipped. So here we + * make sure inode is on some writeback list and leave it there unless + * we have completely cleaned the inode. + */ + if (!(inode->i_state & I_DIRTY) && + (wbc->sync_mode != WB_SYNC_ALL || + !mapping_tagged(inode->i_mapping, PAGECACHE_TAG_WRITEBACK))) + goto out; + inode->i_state |= I_SYNC; + spin_unlock(&inode->i_lock); + + ret = __writeback_single_inode(inode, wbc); + spin_lock(&wb->list_lock); + spin_lock(&inode->i_lock); /* - * It's a data-integrity sync. We must wait. + * If inode is clean, remove it from writeback lists. Otherwise don't + * touch it. See comment above for explanation. */ - if (inode->i_state & I_SYNC) { - DEFINE_WAIT_BIT(wq, &inode->i_state, __I_SYNC); + if (!(inode->i_state & I_DIRTY)) + list_del_init(&inode->i_wb_list); + spin_unlock(&wb->list_lock); + inode_sync_complete(inode); +out: + spin_unlock(&inode->i_lock); + return ret; +} - wqh = bit_waitqueue(&inode->i_state, __I_SYNC); - do { - spin_unlock(&inode_lock); - __wait_on_bit(wqh, &wq, inode_wait, - TASK_UNINTERRUPTIBLE); - spin_lock(&inode_lock); - } while (inode->i_state & I_SYNC); +static long writeback_chunk_size(struct backing_dev_info *bdi, + struct wb_writeback_work *work) +{ + long pages; + + /* + * WB_SYNC_ALL mode does livelock avoidance by syncing dirty + * inodes/pages in one big loop. Setting wbc.nr_to_write=LONG_MAX + * here avoids calling into writeback_inodes_wb() more than once. + * + * The intended call sequence for WB_SYNC_ALL writeback is: + * + * wb_writeback() + * writeback_sb_inodes() <== called only once + * write_cache_pages() <== called once for each inode + * (quickly) tag currently dirty pages + * (maybe slowly) sync all tagged pages + */ + if (work->sync_mode == WB_SYNC_ALL || work->tagged_writepages) + pages = LONG_MAX; + else { + pages = min(bdi->avg_write_bandwidth / 2, + global_dirty_limit / DIRTY_SCOPE); + pages = min(pages, work->nr_pages); + pages = round_down(pages + MIN_WRITEBACK_PAGES, + MIN_WRITEBACK_PAGES); } - return __sync_single_inode(inode, wbc); + + return pages; } /* - * 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. - * - * WB_SYNC_HOLD is a hack for sys_sync(): reattach the inode to sb->s_dirty so - * that it can be located for waiting on in __writeback_single_inode(). + * Write a portion of b_io inodes which belong to @sb. * - * Called under inode_lock. - * - * 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. + * Return the number of pages and/or inodes written. */ -static void -sync_sb_inodes(struct super_block *sb, struct writeback_control *wbc) +static long writeback_sb_inodes(struct super_block *sb, + struct bdi_writeback *wb, + struct wb_writeback_work *work) { - const unsigned long start = jiffies; /* livelock avoidance */ + struct writeback_control wbc = { + .sync_mode = work->sync_mode, + .tagged_writepages = work->tagged_writepages, + .for_kupdate = work->for_kupdate, + .for_background = work->for_background, + .for_sync = work->for_sync, + .range_cyclic = work->range_cyclic, + .range_start = 0, + .range_end = LLONG_MAX, + }; + unsigned long start_time = jiffies; + long write_chunk; + long wrote = 0; /* count both pages and inodes */ - if (!wbc->for_kupdate || list_empty(&sb->s_io)) - queue_io(sb, wbc->older_than_this); + while (!list_empty(&wb->b_io)) { + struct inode *inode = wb_inode(wb->b_io.prev); - while (!list_empty(&sb->s_io)) { - struct inode *inode = list_entry(sb->s_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)) { - redirty_tail(inode); - if (sb_is_blkdev_sb(sb)) { + if (inode->i_sb != sb) { + if (work->sb) { /* - * Dirty memory-backed blockdev: the ramdisk - * driver does this. Skip just this inode + * We only want to write back data for this + * superblock, move all inodes not belonging + * to it back onto the dirty list. */ + redirty_tail(inode, wb); continue; } + /* - * Dirty memory-backed inode against a filesystem other - * than the kernel-internal bdev filesystem. Skip the - * entire superblock. + * The inode belongs to a different superblock. + * Bounce back to the caller to unpin this and + * pin the next superblock. */ break; } - if (wbc->nonblocking && bdi_write_congested(bdi)) { - wbc->encountered_congestion = 1; - if (!sb_is_blkdev_sb(sb)) - break; /* Skip a congested fs */ - requeue_io(inode); - continue; /* Skip a congested blockdev */ + /* + * Don't bother with new inodes or inodes being freed, first + * kind does not need periodic writeout yet, and for the latter + * kind writeout is handled by the freer. + */ + spin_lock(&inode->i_lock); + if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) { + spin_unlock(&inode->i_lock); + redirty_tail(inode, wb); + continue; } - - 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 */ + if ((inode->i_state & I_SYNC) && wbc.sync_mode != WB_SYNC_ALL) { + /* + * If this inode is locked for writeback and we are not + * doing 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 b_io. + */ + spin_unlock(&inode->i_lock); + requeue_io(inode, wb); + trace_writeback_sb_inodes_requeue(inode); + continue; } + spin_unlock(&wb->list_lock); - /* Was this inode dirtied after sync_sb_inodes was called? */ - if (time_after(inode->dirtied_when, start)) - break; + /* + * We already requeued the inode if it had I_SYNC set and we + * are doing WB_SYNC_NONE writeback. So this catches only the + * WB_SYNC_ALL case. + */ + if (inode->i_state & I_SYNC) { + /* Wait for I_SYNC. This function drops i_lock... */ + inode_sleep_on_writeback(inode); + /* Inode may be gone, start again */ + spin_lock(&wb->list_lock); + continue; + } + inode->i_state |= I_SYNC; + spin_unlock(&inode->i_lock); - /* Is another pdflush already flushing this queue? */ - if (current_is_pdflush() && !writeback_acquire(bdi)) - break; + write_chunk = writeback_chunk_size(wb->bdi, work); + wbc.nr_to_write = write_chunk; + wbc.pages_skipped = 0; - BUG_ON(inode->i_state & I_FREEING); - __iget(inode); - pages_skipped = wbc->pages_skipped; - __writeback_single_inode(inode, wbc); - if (wbc->sync_mode == WB_SYNC_HOLD) { - inode->dirtied_when = jiffies; - list_move(&inode->i_list, &sb->s_dirty); + /* + * We use I_SYNC to pin the inode in memory. While it is set + * evict_inode() will wait so the inode cannot be freed. + */ + __writeback_single_inode(inode, &wbc); + + work->nr_pages -= write_chunk - wbc.nr_to_write; + wrote += write_chunk - wbc.nr_to_write; + spin_lock(&wb->list_lock); + spin_lock(&inode->i_lock); + if (!(inode->i_state & I_DIRTY)) + wrote++; + requeue_inode(inode, wb, &wbc); + inode_sync_complete(inode); + spin_unlock(&inode->i_lock); + cond_resched_lock(&wb->list_lock); + /* + * bail out to wb_writeback() often enough to check + * background threshold and other termination conditions. + */ + if (wrote) { + if (time_is_before_jiffies(start_time + HZ / 10UL)) + break; + if (work->nr_pages <= 0) + break; } - if (current_is_pdflush()) - writeback_release(bdi); - if (wbc->pages_skipped != pages_skipped) { + } + return wrote; +} + +static long __writeback_inodes_wb(struct bdi_writeback *wb, + struct wb_writeback_work *work) +{ + unsigned long start_time = jiffies; + long wrote = 0; + + while (!list_empty(&wb->b_io)) { + struct inode *inode = wb_inode(wb->b_io.prev); + struct super_block *sb = inode->i_sb; + + if (!grab_super_passive(sb)) { /* - * writeback is not making progress due to locked - * buffers. Skip this inode for now. + * grab_super_passive() may fail consistently due to + * s_umount being grabbed by someone else. Don't use + * requeue_io() to avoid busy retrying the inode/sb. */ - redirty_tail(inode); + redirty_tail(inode, wb); + continue; } - spin_unlock(&inode_lock); - iput(inode); - cond_resched(); - spin_lock(&inode_lock); - if (wbc->nr_to_write <= 0) { - wbc->more_io = 1; - break; + wrote += writeback_sb_inodes(sb, wb, work); + drop_super(sb); + + /* refer to the same tests at the end of writeback_sb_inodes */ + if (wrote) { + if (time_is_before_jiffies(start_time + HZ / 10UL)) + break; + if (work->nr_pages <= 0) + break; } - if (!list_empty(&sb->s_more_io)) - wbc->more_io = 1; } - return; /* Leave any unwritten inodes on s_io */ + /* Leave any unwritten inodes on b_io */ + return wrote; +} + +static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages, + enum wb_reason reason) +{ + struct wb_writeback_work work = { + .nr_pages = nr_pages, + .sync_mode = WB_SYNC_NONE, + .range_cyclic = 1, + .reason = reason, + }; + + spin_lock(&wb->list_lock); + if (list_empty(&wb->b_io)) + queue_io(wb, &work); + __writeback_inodes_wb(wb, &work); + spin_unlock(&wb->list_lock); + + return nr_pages - work.nr_pages; +} + +static bool over_bground_thresh(struct backing_dev_info *bdi) +{ + unsigned long background_thresh, dirty_thresh; + + global_dirty_limits(&background_thresh, &dirty_thresh); + + if (global_page_state(NR_FILE_DIRTY) + + global_page_state(NR_UNSTABLE_NFS) > background_thresh) + return true; + + if (bdi_stat(bdi, BDI_RECLAIMABLE) > + bdi_dirty_limit(bdi, background_thresh)) + return true; + + return false; +} + +/* + * Called under wb->list_lock. If there are multiple wb per bdi, + * only the flusher working on the first wb should do it. + */ +static void wb_update_bandwidth(struct bdi_writeback *wb, + unsigned long start_time) +{ + __bdi_update_bandwidth(wb->bdi, 0, 0, 0, 0, 0, start_time); } /* - * Start writeback of dirty pagecache data against all unlocked inodes. + * Explicit flushing or periodic writeback of "old" data. * - * 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. + * 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. * - * If `older_than_this' is non-zero then only flush inodes which have a - * flushtime older than *older_than_this. + * 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. * - * 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... + * 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. */ -void -writeback_inodes(struct writeback_control *wbc) +static long wb_writeback(struct bdi_writeback *wb, + struct wb_writeback_work *work) { - struct super_block *sb; + unsigned long wb_start = jiffies; + long nr_pages = work->nr_pages; + unsigned long oldest_jif; + struct inode *inode; + long progress; - 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) { - spin_lock(&inode_lock); - sync_sb_inodes(sb, wbc); - spin_unlock(&inode_lock); - } - up_read(&sb->s_umount); - } - spin_lock(&sb_lock); - if (__put_super_and_need_restart(sb)) - goto restart; - } - if (wbc->nr_to_write <= 0) + oldest_jif = jiffies; + work->older_than_this = &oldest_jif; + + spin_lock(&wb->list_lock); + for (;;) { + /* + * Stop writeback when nr_pages has been consumed + */ + if (work->nr_pages <= 0) break; + + /* + * Background writeout and kupdate-style writeback may + * run forever. Stop them if there is other work to do + * so that e.g. sync can proceed. They'll be restarted + * after the other works are all done. + */ + if ((work->for_background || work->for_kupdate) && + !list_empty(&wb->bdi->work_list)) + break; + + /* + * For background writeout, stop when we are below the + * background dirty threshold + */ + if (work->for_background && !over_bground_thresh(wb->bdi)) + break; + + /* + * Kupdate and background works are special and we want to + * include all inodes that need writing. Livelock avoidance is + * handled by these works yielding to any other work so we are + * safe. + */ + if (work->for_kupdate) { + oldest_jif = jiffies - + msecs_to_jiffies(dirty_expire_interval * 10); + } else if (work->for_background) + oldest_jif = jiffies; + + trace_writeback_start(wb->bdi, work); + if (list_empty(&wb->b_io)) + queue_io(wb, work); + if (work->sb) + progress = writeback_sb_inodes(work->sb, wb, work); + else + progress = __writeback_inodes_wb(wb, work); + trace_writeback_written(wb->bdi, work); + + wb_update_bandwidth(wb, wb_start); + + /* + * Did we write something? Try for more + * + * Dirty inodes are moved to b_io for writeback in batches. + * The completion of the current batch does not necessarily + * mean the overall work is done. So we keep looping as long + * as made some progress on cleaning pages or inodes. + */ + if (progress) + continue; + /* + * No more inodes for IO, bail + */ + if (list_empty(&wb->b_more_io)) + break; + /* + * Nothing written. Wait for some inode to + * become available for writeback. Otherwise + * we'll just busyloop. + */ + if (!list_empty(&wb->b_more_io)) { + trace_writeback_wait(wb->bdi, work); + inode = wb_inode(wb->b_more_io.prev); + spin_lock(&inode->i_lock); + spin_unlock(&wb->list_lock); + /* This function drops i_lock... */ + inode_sleep_on_writeback(inode); + spin_lock(&wb->list_lock); + } } - spin_unlock(&sb_lock); + spin_unlock(&wb->list_lock); + + return nr_pages - work->nr_pages; } /* - * writeback and wait upon the filesystem's dirty inodes. The caller will - * do this in two passes - one to write, and one to wait. WB_SYNC_HOLD is - * used to park the written inodes on sb->s_dirty for the wait pass. - * - * A finite limit is set on the number of pages which will be written. - * To prevent infinite livelock of sys_sync(). - * - * We add in the number of potentially dirty inodes, because each inode write - * can dirty pagecache in the underlying blockdev. + * Return the next wb_writeback_work struct that hasn't been processed yet. */ -void sync_inodes_sb(struct super_block *sb, int wait) +static struct wb_writeback_work * +get_next_work_item(struct backing_dev_info *bdi) { - struct writeback_control wbc = { - .sync_mode = wait ? WB_SYNC_ALL : WB_SYNC_HOLD, - .range_start = 0, - .range_end = LLONG_MAX, - }; - unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY); - unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS); + struct wb_writeback_work *work = NULL; - wbc.nr_to_write = nr_dirty + nr_unstable + - (inodes_stat.nr_inodes - inodes_stat.nr_unused) + - nr_dirty + nr_unstable; - wbc.nr_to_write += wbc.nr_to_write / 2; /* Bit more for luck */ - spin_lock(&inode_lock); - sync_sb_inodes(sb, &wbc); - spin_unlock(&inode_lock); + spin_lock_bh(&bdi->wb_lock); + if (!list_empty(&bdi->work_list)) { + work = list_entry(bdi->work_list.next, + struct wb_writeback_work, list); + list_del_init(&work->list); + } + spin_unlock_bh(&bdi->wb_lock); + return work; } /* - * Rather lame livelock avoidance. + * Add in the number of potentially dirty inodes, because each inode + * write can dirty pagecache in the underlying blockdev. */ -static void set_sb_syncing(int val) +static unsigned long get_nr_dirty_pages(void) { - struct super_block *sb; - spin_lock(&sb_lock); - list_for_each_entry_reverse(sb, &super_blocks, s_list) - sb->s_syncing = val; - spin_unlock(&sb_lock); + return global_page_state(NR_FILE_DIRTY) + + global_page_state(NR_UNSTABLE_NFS) + + get_nr_dirty_inodes(); +} + +static long wb_check_background_flush(struct bdi_writeback *wb) +{ + if (over_bground_thresh(wb->bdi)) { + + struct wb_writeback_work work = { + .nr_pages = LONG_MAX, + .sync_mode = WB_SYNC_NONE, + .for_background = 1, + .range_cyclic = 1, + .reason = WB_REASON_BACKGROUND, + }; + + return wb_writeback(wb, &work); + } + + return 0; +} + +static long wb_check_old_data_flush(struct bdi_writeback *wb) +{ + unsigned long expired; + long nr_pages; + + /* + * When set to zero, disable periodic writeback + */ + if (!dirty_writeback_interval) + return 0; + + 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 = get_nr_dirty_pages(); + + if (nr_pages) { + struct wb_writeback_work work = { + .nr_pages = nr_pages, + .sync_mode = WB_SYNC_NONE, + .for_kupdate = 1, + .range_cyclic = 1, + .reason = WB_REASON_PERIODIC, + }; + + return wb_writeback(wb, &work); + } + + return 0; +} + +/* + * Retrieve work items and do the writeback they describe + */ +static long wb_do_writeback(struct bdi_writeback *wb) +{ + struct backing_dev_info *bdi = wb->bdi; + struct wb_writeback_work *work; + long wrote = 0; + + set_bit(BDI_writeback_running, &wb->bdi->state); + while ((work = get_next_work_item(bdi)) != NULL) { + + trace_writeback_exec(bdi, work); + + wrote += wb_writeback(wb, work); + + /* + * Notify the caller of completion if this is a synchronous + * work item, otherwise just free it. + */ + if (work->done) + complete(work->done); + else + kfree(work); + } + + /* + * Check for periodic writeback, kupdated() style + */ + wrote += wb_check_old_data_flush(wb); + wrote += wb_check_background_flush(wb); + clear_bit(BDI_writeback_running, &wb->bdi->state); + + return wrote; +} + +/* + * Handle writeback of dirty data for the device backed by this bdi. Also + * reschedules periodically and does kupdated style flushing. + */ +void bdi_writeback_workfn(struct work_struct *work) +{ + struct bdi_writeback *wb = container_of(to_delayed_work(work), + struct bdi_writeback, dwork); + struct backing_dev_info *bdi = wb->bdi; + long pages_written; + + set_worker_desc("flush-%s", dev_name(bdi->dev)); + current->flags |= PF_SWAPWRITE; + + if (likely(!current_is_workqueue_rescuer() || + !test_bit(BDI_registered, &bdi->state))) { + /* + * The normal path. Keep writing back @bdi until its + * work_list is empty. Note that this path is also taken + * if @bdi is shutting down even when we're running off the + * rescuer as work_list needs to be drained. + */ + do { + pages_written = wb_do_writeback(wb); + trace_writeback_pages_written(pages_written); + } while (!list_empty(&bdi->work_list)); + } else { + /* + * bdi_wq can't get enough workers and we're running off + * the emergency worker. Don't hog it. Hopefully, 1024 is + * enough for efficient IO. + */ + pages_written = writeback_inodes_wb(&bdi->wb, 1024, + WB_REASON_FORKER_THREAD); + trace_writeback_pages_written(pages_written); + } + + if (!list_empty(&bdi->work_list)) + mod_delayed_work(bdi_wq, &wb->dwork, 0); + else if (wb_has_dirty_io(wb) && dirty_writeback_interval) + bdi_wakeup_thread_delayed(bdi); + + current->flags &= ~PF_SWAPWRITE; +} + +/* + * Start writeback of `nr_pages' pages. If `nr_pages' is zero, write back + * the whole world. + */ +void wakeup_flusher_threads(long nr_pages, enum wb_reason reason) +{ + struct backing_dev_info *bdi; + + if (!nr_pages) + nr_pages = get_nr_dirty_pages(); + + rcu_read_lock(); + list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) { + if (!bdi_has_dirty_io(bdi)) + continue; + __bdi_start_writeback(bdi, nr_pages, false, reason); + } + rcu_read_unlock(); +} + +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); + } + } } /** - * sync_inodes - writes all inodes to disk - * @wait: wait for completion + * __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. * - * sync_inodes() goes through each super block's dirty inode list, writes the - * inodes out, waits on the writeout and puts the inodes back on the normal - * 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 is for sys_sync(). fsync_dev() uses the same algorithm. The subtle - * part of the sync functions is that the blockdev "superblock" is processed - * last. This is because the write_inode() function of a typical fs will - * perform no I/O, but will mark buffers in the blockdev mapping as dirty. - * What we want to do is to perform all that dirtying first, and then write - * back all those inode blocks via the blockdev mapping in one sweep. So the - * additional (somewhat redundant) sync_blockdev() calls here are to make - * sure that really happens. Because if we call sync_inodes_sb(wait=1) with - * outstanding dirty inodes, the writeback goes block-at-a-time within the - * filesystem's write_inode(). This is extremely slow. - */ -static void __sync_inodes(int wait) + * 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) { - struct super_block *sb; + struct super_block *sb = inode->i_sb; + struct backing_dev_info *bdi = NULL; - spin_lock(&sb_lock); -restart: - list_for_each_entry(sb, &super_blocks, s_list) { - if (sb->s_syncing) - continue; - sb->s_syncing = 1; - sb->s_count++; - spin_unlock(&sb_lock); - down_read(&sb->s_umount); - if (sb->s_root) { - sync_inodes_sb(sb, wait); - sync_blockdev(sb->s_bdev); + /* + * Don't do this for I_DIRTY_PAGES - that doesn't actually + * dirty the inode itself + */ + if (flags & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) { + trace_writeback_dirty_inode_start(inode, flags); + + if (sb->s_op->dirty_inode) + sb->s_op->dirty_inode(inode, flags); + + trace_writeback_dirty_inode(inode, flags); + } + + /* + * 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->i_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_unlock_inode; + + /* + * Only add valid (hashed) inodes to the superblock's + * dirty list. Add blockdev inodes as well. + */ + if (!S_ISBLK(inode->i_mode)) { + if (inode_unhashed(inode)) + goto out_unlock_inode; + } + if (inode->i_state & I_FREEING) + goto out_unlock_inode; + + /* + * 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) { + bool wakeup_bdi = false; + bdi = inode_to_bdi(inode); + + spin_unlock(&inode->i_lock); + spin_lock(&bdi->wb.list_lock); + if (bdi_cap_writeback_dirty(bdi)) { + WARN(!test_bit(BDI_registered, &bdi->state), + "bdi-%s not registered\n", bdi->name); + + /* + * If this is the first dirty inode for this + * bdi, we have to wake-up the corresponding + * bdi thread to make sure background + * write-back happens later. + */ + if (!wb_has_dirty_io(&bdi->wb)) + wakeup_bdi = true; + } + + inode->dirtied_when = jiffies; + list_move(&inode->i_wb_list, &bdi->wb.b_dirty); + spin_unlock(&bdi->wb.list_lock); + + if (wakeup_bdi) + bdi_wakeup_thread_delayed(bdi); + return; } - up_read(&sb->s_umount); - spin_lock(&sb_lock); - if (__put_super_and_need_restart(sb)) - goto restart; } - spin_unlock(&sb_lock); +out_unlock_inode: + spin_unlock(&inode->i_lock); + } +EXPORT_SYMBOL(__mark_inode_dirty); -void sync_inodes(int wait) +static void wait_sb_inodes(struct super_block *sb) { - set_sb_syncing(0); - __sync_inodes(0); + 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_sb_list_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 = inode->i_mapping; - if (wait) { - set_sb_syncing(0); - __sync_inodes(1); + spin_lock(&inode->i_lock); + if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) || + (mapping->nrpages == 0)) { + spin_unlock(&inode->i_lock); + continue; + } + __iget(inode); + spin_unlock(&inode->i_lock); + spin_unlock(&inode_sb_list_lock); + + /* + * We hold a reference to 'inode' so it couldn't have been + * removed from s_inodes list while we dropped the + * inode_sb_list_lock. We cannot iput the inode now as we can + * be holding the last reference and we cannot iput it under + * inode_sb_list_lock. So we keep the reference and iput it + * later. + */ + iput(old_inode); + old_inode = inode; + + filemap_fdatawait(mapping); + + cond_resched(); + + spin_lock(&inode_sb_list_lock); } + spin_unlock(&inode_sb_list_lock); + iput(old_inode); +} + +/** + * writeback_inodes_sb_nr - writeback dirty inodes from given super_block + * @sb: the superblock + * @nr: the number of pages to write + * @reason: reason why some writeback work initiated + * + * 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. + */ +void writeback_inodes_sb_nr(struct super_block *sb, + unsigned long nr, + enum wb_reason reason) +{ + DECLARE_COMPLETION_ONSTACK(done); + struct wb_writeback_work work = { + .sb = sb, + .sync_mode = WB_SYNC_NONE, + .tagged_writepages = 1, + .done = &done, + .nr_pages = nr, + .reason = reason, + }; + + if (sb->s_bdi == &noop_backing_dev_info) + return; + WARN_ON(!rwsem_is_locked(&sb->s_umount)); + bdi_queue_work(sb->s_bdi, &work); + wait_for_completion(&done); +} +EXPORT_SYMBOL(writeback_inodes_sb_nr); + +/** + * writeback_inodes_sb - writeback dirty inodes from given super_block + * @sb: the superblock + * @reason: reason why some writeback work was initiated + * + * 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. + */ +void writeback_inodes_sb(struct super_block *sb, enum wb_reason reason) +{ + return writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason); } +EXPORT_SYMBOL(writeback_inodes_sb); + +/** + * try_to_writeback_inodes_sb_nr - try to start writeback if none underway + * @sb: the superblock + * @nr: the number of pages to write + * @reason: the reason of writeback + * + * Invoke writeback_inodes_sb_nr if no writeback is currently underway. + * Returns 1 if writeback was started, 0 if not. + */ +int try_to_writeback_inodes_sb_nr(struct super_block *sb, + unsigned long nr, + enum wb_reason reason) +{ + if (writeback_in_progress(sb->s_bdi)) + return 1; + + if (!down_read_trylock(&sb->s_umount)) + return 0; + + writeback_inodes_sb_nr(sb, nr, reason); + up_read(&sb->s_umount); + return 1; +} +EXPORT_SYMBOL(try_to_writeback_inodes_sb_nr); + +/** + * try_to_writeback_inodes_sb - try to start writeback if none underway + * @sb: the superblock + * @reason: reason why some writeback work was initiated + * + * Implement by try_to_writeback_inodes_sb_nr() + * Returns 1 if writeback was started, 0 if not. + */ +int try_to_writeback_inodes_sb(struct super_block *sb, enum wb_reason reason) +{ + return try_to_writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason); +} +EXPORT_SYMBOL(try_to_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. + */ +void sync_inodes_sb(struct super_block *sb) +{ + DECLARE_COMPLETION_ONSTACK(done); + struct wb_writeback_work work = { + .sb = sb, + .sync_mode = WB_SYNC_ALL, + .nr_pages = LONG_MAX, + .range_cyclic = 0, + .done = &done, + .reason = WB_REASON_SYNC, + .for_sync = 1, + }; + + /* Nothing to do? */ + if (sb->s_bdi == &noop_backing_dev_info) + return; + WARN_ON(!rwsem_is_locked(&sb->s_umount)); + + bdi_queue_work(sb->s_bdi, &work); + wait_for_completion(&done); + + wait_sb_inodes(sb); +} +EXPORT_SYMBOL(sync_inodes_sb); /** * write_inode_now - write an inode to disk @@ -652,7 +1406,7 @@ void sync_inodes(int wait) */ int write_inode_now(struct inode *inode, int sync) { - int ret; + struct bdi_writeback *wb = &inode_to_bdi(inode)->wb; struct writeback_control wbc = { .nr_to_write = LONG_MAX, .sync_mode = sync ? WB_SYNC_ALL : WB_SYNC_NONE, @@ -664,12 +1418,7 @@ int write_inode_now(struct inode *inode, int sync) wbc.nr_to_write = 0; might_sleep(); - spin_lock(&inode_lock); - ret = __writeback_single_inode(inode, &wbc); - spin_unlock(&inode_lock); - if (sync) - inode_sync_wait(inode); - return ret; + return writeback_single_inode(inode, wb, &wbc); } EXPORT_SYMBOL(write_inode_now); @@ -686,104 +1435,26 @@ EXPORT_SYMBOL(write_inode_now); */ int sync_inode(struct inode *inode, struct writeback_control *wbc) { - int ret; - - spin_lock(&inode_lock); - ret = __writeback_single_inode(inode, wbc); - spin_unlock(&inode_lock); - return ret; + return writeback_single_inode(inode, &inode_to_bdi(inode)->wb, wbc); } 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); - -/** - * 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. + * sync_inode_metadata - write an inode to disk + * @inode: the inode to sync + * @wait: wait for I/O to complete. * - * 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. - */ -int writeback_acquire(struct backing_dev_info *bdi) -{ - return !test_and_set_bit(BDI_pdflush, &bdi->state); -} - -/** - * writeback_in_progress - determine whether there is writeback in progress - * @bdi: the device's backing_dev_info structure. + * Write an inode to disk and adjust its dirty state after completion. * - * Determine whether there is writeback in progress against a backing device. + * Note: only writes the actual inode, no associated data or other metadata. */ -int writeback_in_progress(struct backing_dev_info *bdi) +int sync_inode_metadata(struct inode *inode, int wait) { - return test_bit(BDI_pdflush, &bdi->state); -} + struct writeback_control wbc = { + .sync_mode = wait ? WB_SYNC_ALL : WB_SYNC_NONE, + .nr_to_write = 0, /* metadata-only */ + }; -/** - * writeback_release - relinquish exclusive writeback access against a device. - * @bdi: the device's backing_dev_info structure - */ -void writeback_release(struct backing_dev_info *bdi) -{ - BUG_ON(!writeback_in_progress(bdi)); - clear_bit(BDI_pdflush, &bdi->state); + return sync_inode(inode, &wbc); } +EXPORT_SYMBOL(sync_inode_metadata); |