#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/mm.h>
+#include <linux/kthread.h>
+#include <linux/freezer.h>
#include <linux/writeback.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/buffer_head.h>
#include "internal.h"
+#define inode_to_bdi(inode) ((inode)->i_mapping->backing_dev_info)
-/**
- * writeback_acquire - attempt to get exclusive writeback access to a device
- * @bdi: the device's backing_dev_info structure
- *
- * It is a waste of resources to have more than one pdflush thread blocked on
- * a single request queue. Exclusion at the request_queue level is obtained
- * via a flag in the request_queue's backing_dev_info.state.
- *
- * Non-request_queue-backed address_spaces will share default_backing_dev_info,
- * unless they implement their own. Which is somewhat inefficient, as this
- * may prevent concurrent writeback against multiple devices.
+/*
+ * We don't actually have pdflush, but this one is exported though /proc...
+ */
+int nr_pdflush_threads;
+
+/*
+ * Passed into wb_writeback(), essentially a subset of writeback_control
+ */
+struct wb_writeback_args {
+ long nr_pages;
+ struct super_block *sb;
+ enum writeback_sync_modes sync_mode;
+ int for_kupdate:1;
+ int range_cyclic:1;
+ int for_background:1;
+};
+
+/*
+ * Work items for the bdi_writeback threads
*/
-static int writeback_acquire(struct backing_dev_info *bdi)
+struct bdi_work {
+ struct list_head list; /* pending work list */
+ struct rcu_head rcu_head; /* for RCU free/clear of work */
+
+ unsigned long seen; /* threads that have seen this work */
+ atomic_t pending; /* number of threads still to do work */
+
+ struct wb_writeback_args args; /* writeback arguments */
+
+ unsigned long state; /* flag bits, see WS_* */
+};
+
+enum {
+ WS_USED_B = 0,
+ WS_ONSTACK_B,
+};
+
+#define WS_USED (1 << WS_USED_B)
+#define WS_ONSTACK (1 << WS_ONSTACK_B)
+
+static inline bool bdi_work_on_stack(struct bdi_work *work)
+{
+ return test_bit(WS_ONSTACK_B, &work->state);
+}
+
+static inline void bdi_work_init(struct bdi_work *work,
+ struct wb_writeback_args *args)
{
- return !test_and_set_bit(BDI_pdflush, &bdi->state);
+ INIT_RCU_HEAD(&work->rcu_head);
+ work->args = *args;
+ work->state = WS_USED;
}
/**
* writeback_in_progress - determine whether there is writeback in progress
* @bdi: the device's backing_dev_info structure.
*
- * Determine whether there is writeback in progress against a backing device.
+ * Determine whether there is writeback waiting to be handled against a
+ * backing device.
*/
int writeback_in_progress(struct backing_dev_info *bdi)
{
- return test_bit(BDI_pdflush, &bdi->state);
+ return !list_empty(&bdi->work_list);
}
-/**
- * writeback_release - relinquish exclusive writeback access against a device.
- * @bdi: the device's backing_dev_info structure
- */
-static void writeback_release(struct backing_dev_info *bdi)
+static void bdi_work_clear(struct bdi_work *work)
{
- BUG_ON(!writeback_in_progress(bdi));
- clear_bit(BDI_pdflush, &bdi->state);
+ clear_bit(WS_USED_B, &work->state);
+ smp_mb__after_clear_bit();
+ /*
+ * work can have disappeared at this point. bit waitq functions
+ * should be able to tolerate this, provided bdi_sched_wait does
+ * not dereference it's pointer argument.
+ */
+ wake_up_bit(&work->state, WS_USED_B);
}
-/**
- * __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 bdi_work_free(struct rcu_head *head)
{
- struct super_block *sb = inode->i_sb;
+ struct bdi_work *work = container_of(head, struct bdi_work, rcu_head);
+
+ if (!bdi_work_on_stack(work))
+ kfree(work);
+ else
+ bdi_work_clear(work);
+}
+
+static void wb_work_complete(struct bdi_work *work)
+{
+ const enum writeback_sync_modes sync_mode = work->args.sync_mode;
+ int onstack = bdi_work_on_stack(work);
/*
- * Don't do this for I_DIRTY_PAGES - that doesn't actually
- * dirty the inode itself
+ * For allocated work, we can clear the done/seen bit right here.
+ * For on-stack work, we need to postpone both the clear and free
+ * to after the RCU grace period, since the stack could be invalidated
+ * as soon as bdi_work_clear() has done the wakeup.
*/
- if (flags & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) {
- if (sb->s_op->dirty_inode)
- sb->s_op->dirty_inode(inode);
- }
+ if (!onstack)
+ bdi_work_clear(work);
+ if (sync_mode == WB_SYNC_NONE || onstack)
+ call_rcu(&work->rcu_head, bdi_work_free);
+}
+static void wb_clear_pending(struct bdi_writeback *wb, struct bdi_work *work)
+{
/*
- * make sure that changes are seen by all cpus before we test i_state
- * -- mikulas
+ * The caller has retrieved the work arguments from this work,
+ * drop our reference. If this is the last ref, delete and free it
*/
- smp_mb();
+ if (atomic_dec_and_test(&work->pending)) {
+ struct backing_dev_info *bdi = wb->bdi;
- /* avoid the locking if we can */
- if ((inode->i_state & flags) == flags)
- return;
+ spin_lock(&bdi->wb_lock);
+ list_del_rcu(&work->list);
+ spin_unlock(&bdi->wb_lock);
- if (unlikely(block_dump)) {
- struct dentry *dentry = NULL;
- const char *name = "?";
+ wb_work_complete(work);
+ }
+}
- 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;
- }
+static void bdi_queue_work(struct backing_dev_info *bdi, struct bdi_work *work)
+{
+ work->seen = bdi->wb_mask;
+ BUG_ON(!work->seen);
+ atomic_set(&work->pending, bdi->wb_cnt);
+ BUG_ON(!bdi->wb_cnt);
- 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);
- }
+ /*
+ * list_add_tail_rcu() contains the necessary barriers to
+ * make sure the above stores are seen before the item is
+ * noticed on the list
+ */
+ spin_lock(&bdi->wb_lock);
+ list_add_tail_rcu(&work->list, &bdi->work_list);
+ spin_unlock(&bdi->wb_lock);
- spin_lock(&inode_lock);
- if ((inode->i_state & flags) != flags) {
- const int was_dirty = inode->i_state & I_DIRTY;
+ /*
+ * 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;
- inode->i_state |= flags;
+ if (wb->task)
+ wake_up_process(wb->task);
+ }
+}
- /*
- * 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;
+/*
+ * 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);
+}
- /*
- * 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;
+static void bdi_alloc_queue_work(struct backing_dev_info *bdi,
+ struct wb_writeback_args *args)
+{
+ struct bdi_work *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);
- }
+ /*
+ * This is WB_SYNC_NONE writeback, so if allocation fails just
+ * wakeup the thread for old dirty data writeback
+ */
+ work = kmalloc(sizeof(*work), GFP_ATOMIC);
+ if (work) {
+ bdi_work_init(work, args);
+ bdi_queue_work(bdi, work);
+ } else {
+ struct bdi_writeback *wb = &bdi->wb;
+
+ if (wb->task)
+ wake_up_process(wb->task);
}
-out:
- spin_unlock(&inode_lock);
}
-EXPORT_SYMBOL(__mark_inode_dirty);
+/**
+ * bdi_sync_writeback - start and wait for writeback
+ * @bdi: the backing device to write from
+ * @sb: write inodes from this super_block
+ *
+ * Description:
+ * This does WB_SYNC_ALL data integrity writeback and waits for the
+ * IO to complete. Callers must hold the sb s_umount semaphore for
+ * reading, to avoid having the super disappear before we are done.
+ */
+static void bdi_sync_writeback(struct backing_dev_info *bdi,
+ struct super_block *sb)
+{
+ struct wb_writeback_args args = {
+ .sb = sb,
+ .sync_mode = WB_SYNC_ALL,
+ .nr_pages = LONG_MAX,
+ .range_cyclic = 0,
+ };
+ struct bdi_work work;
-static int write_inode(struct inode *inode, int sync)
+ bdi_work_init(&work, &args);
+ work.state |= WS_ONSTACK;
+
+ bdi_queue_work(bdi, &work);
+ bdi_wait_on_work_clear(&work);
+}
+
+/**
+ * bdi_start_writeback - start writeback
+ * @bdi: the backing device to write from
+ * @sb: write inodes from this super_block
+ * @nr_pages: the number of pages to write
+ *
+ * Description:
+ * This does WB_SYNC_NONE opportunistic writeback. The IO is only
+ * started when this function returns, we make no guarentees on
+ * completion. Caller need not hold sb s_umount semaphore.
+ *
+ */
+void bdi_start_writeback(struct backing_dev_info *bdi, struct super_block *sb,
+ long nr_pages)
{
- if (inode->i_sb->s_op->write_inode && !is_bad_inode(inode))
- return inode->i_sb->s_op->write_inode(inode, sync);
- return 0;
+ struct wb_writeback_args args = {
+ .sb = sb,
+ .sync_mode = WB_SYNC_NONE,
+ .nr_pages = nr_pages,
+ .range_cyclic = 1,
+ };
+
+ /*
+ * We treat @nr_pages=0 as the special case to do background writeback,
+ * ie. to sync pages until the background dirty threshold is reached.
+ */
+ if (!nr_pages) {
+ args.nr_pages = LONG_MAX;
+ args.for_background = 1;
+ }
+
+ bdi_alloc_queue_work(bdi, &args);
}
/*
* furthest end of its superblock's dirty-inode list.
*
* Before stamping the inode's ->dirtied_when, we check to see whether it is
- * already the most-recently-dirtied inode on the s_dirty list. If that is
+ * already the most-recently-dirtied inode on the b_dirty list. If that is
* the case then the inode must have been redirtied while it was being written
* out and we don't reset its dirtied_when.
*/
static void redirty_tail(struct inode *inode)
{
- struct super_block *sb = inode->i_sb;
+ struct bdi_writeback *wb = &inode_to_bdi(inode)->wb;
- if (!list_empty(&sb->s_dirty)) {
- struct inode *tail_inode;
+ if (!list_empty(&wb->b_dirty)) {
+ struct inode *tail;
- tail_inode = list_entry(sb->s_dirty.next, struct inode, i_list);
- if (!time_after_eq(inode->dirtied_when,
- tail_inode->dirtied_when))
+ tail = list_entry(wb->b_dirty.next, struct inode, i_list);
+ if (time_before(inode->dirtied_when, tail->dirtied_when))
inode->dirtied_when = jiffies;
}
- list_move(&inode->i_list, &sb->s_dirty);
+ list_move(&inode->i_list, &wb->b_dirty);
}
/*
- * requeue inode for re-scanning after sb->s_io list is exhausted.
+ * requeue inode for re-scanning after bdi->b_io list is exhausted.
*/
static void requeue_io(struct inode *inode)
{
- list_move(&inode->i_list, &inode->i_sb->s_more_io);
+ struct bdi_writeback *wb = &inode_to_bdi(inode)->wb;
+
+ list_move(&inode->i_list, &wb->b_more_io);
}
static void inode_sync_complete(struct inode *inode)
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.
*/
struct list_head *dispatch_queue,
unsigned long *older_than_this)
{
+ LIST_HEAD(tmp);
+ struct list_head *pos, *node;
+ struct super_block *sb = NULL;
+ struct inode *inode;
+ int do_sb_sort = 0;
+
while (!list_empty(delaying_queue)) {
- struct inode *inode = list_entry(delaying_queue->prev,
- struct inode, i_list);
+ inode = list_entry(delaying_queue->prev, struct inode, i_list);
if (older_than_this &&
- time_after(inode->dirtied_when, *older_than_this))
+ inode_dirtied_after(inode, *older_than_this))
break;
- list_move(&inode->i_list, dispatch_queue);
+ if (sb && sb != inode->i_sb)
+ do_sb_sort = 1;
+ sb = inode->i_sb;
+ list_move(&inode->i_list, &tmp);
+ }
+
+ /* just one sb in list, splice to dispatch_queue and we're done */
+ if (!do_sb_sort) {
+ list_splice(&tmp, dispatch_queue);
+ return;
+ }
+
+ /* Move inodes from one superblock together */
+ while (!list_empty(&tmp)) {
+ inode = list_entry(tmp.prev, struct inode, i_list);
+ sb = inode->i_sb;
+ list_for_each_prev_safe(pos, node, &tmp) {
+ inode = list_entry(pos, struct inode, i_list);
+ if (inode->i_sb == sb)
+ list_move(&inode->i_list, dispatch_queue);
+ }
}
}
/*
* Queue all expired dirty inodes for io, eldest first.
*/
-static void queue_io(struct super_block *sb,
- unsigned long *older_than_this)
+static void queue_io(struct bdi_writeback *wb, unsigned long *older_than_this)
{
- list_splice_init(&sb->s_more_io, sb->s_io.prev);
- move_expired_inodes(&sb->s_dirty, &sb->s_io, older_than_this);
+ list_splice_init(&wb->b_more_io, wb->b_io.prev);
+ move_expired_inodes(&wb->b_dirty, &wb->b_io, older_than_this);
+}
+
+static int write_inode(struct inode *inode, 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, wbc);
+ return 0;
}
-int sb_has_dirty_inodes(struct super_block *sb)
+/*
+ * Wait for writeback on an inode to complete.
+ */
+static void inode_wait_for_writeback(struct inode *inode)
{
- return !list_empty(&sb->s_dirty) ||
- !list_empty(&sb->s_io) ||
- !list_empty(&sb->s_more_io);
+ DEFINE_WAIT_BIT(wq, &inode->i_state, __I_SYNC);
+ wait_queue_head_t *wqh;
+
+ 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);
}
-EXPORT_SYMBOL(sb_has_dirty_inodes);
/*
- * Write a single inode's dirty pages and inode data out to disk.
+ * 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)
+ *
* If `wait' is set, wait on the writeout.
*
* The whole writeout design is quite complex and fragile. We want to avoid
* Called under inode_lock.
*/
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;
+ unsigned dirty;
int ret;
+ 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 (inode->i_state & I_SYNC) {
+ /*
+ * 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.
+ */
+ if (wbc->sync_mode != WB_SYNC_ALL) {
+ requeue_io(inode);
+ return 0;
+ }
+
+ /*
+ * It's a data-integrity sync. We must wait.
+ */
+ inode_wait_for_writeback(inode);
+ }
+
BUG_ON(inode->i_state & I_SYNC);
- WARN_ON(inode->i_state & I_NEW);
/* Set I_SYNC, reset I_DIRTY */
dirty = inode->i_state & I_DIRTY;
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.
+ */
+ if (wbc->sync_mode == WB_SYNC_ALL) {
+ int err = filemap_fdatawait(mapping);
if (ret == 0)
ret = err;
}
- if (wait) {
- int err = filemap_fdatawait(mapping);
+ /* 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);
- WARN_ON(inode->i_state & I_NEW);
inode->i_state &= ~I_SYNC;
- if (!(inode->i_state & I_FREEING)) {
- if (!(inode->i_state & I_DIRTY) &&
- mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
+ if (!(inode->i_state & (I_FREEING | I_CLEAR))) {
+ if ((inode->i_state & I_DIRTY_PAGES) && wbc->for_kupdate) {
+ /*
+ * More pages get dirtied by a fast dirtier.
+ */
+ goto select_queue;
+ } else if (inode->i_state & I_DIRTY) {
+ /*
+ * At least XFS will redirty the inode during the
+ * writeback (delalloc) and on io completion (isize).
+ */
+ redirty_tail(inode);
+ } else if (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.
+ * the inode; Move it from b_io onto b_more_io/b_dirty.
*/
/*
* akpm: if the caller was the kupdate function we put
- * this inode at the head of s_dirty so it gets first
+ * this inode at the head of b_dirty so it gets first
* consideration. Otherwise, move it to the tail, for
* the reasons described there. I'm not really sure
* how much sense this makes. Presumably I had a good
if (wbc->for_kupdate) {
/*
* For the kupdate function we move the inode
- * to s_more_io so it will get more writeout as
+ * to b_more_io so it will get more writeout as
* soon as the queue becomes uncongested.
*/
inode->i_state |= I_DIRTY_PAGES;
+select_queue:
if (wbc->nr_to_write <= 0) {
/*
* slice used up: queue for next turn
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
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)
- */
-static int
-__writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
+static void unpin_sb_for_writeback(struct super_block **psb)
{
- wait_queue_head_t *wqh;
-
- 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)) {
- /*
- * 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.
- */
- requeue_io(inode);
- return 0;
- }
+ struct super_block *sb = *psb;
- /*
- * It's a data-integrity sync. We must wait.
- */
- if (inode->i_state & I_SYNC) {
- DEFINE_WAIT_BIT(wq, &inode->i_state, __I_SYNC);
-
- 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);
+ if (sb) {
+ up_read(&sb->s_umount);
+ put_super(sb);
+ *psb = NULL;
}
- return __sync_single_inode(inode, 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.
- *
- * 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.
+ * 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.
*
- * FIXME: this linear search could get expensive with many fileystems. But
- * how to fix? We need to go from an address_space to all inodes which share
- * a queue with that address_space. (Easy: have a global "dirty superblocks"
- * list).
- *
- * The inodes to be written are parked on sb->s_io. They are moved back onto
- * sb->s_dirty as they are selected for writing. This way, none can be missed
- * on the writer throttling path, and we get decent balancing between many
- * throttled threads: we don't want them all piling up on inode_sync_wait.
+ * Returns 0 if the super was successfully pinned (or pinning wasn't needed),
+ * 1 if we failed.
*/
-void generic_sync_sb_inodes(struct super_block *sb,
- struct writeback_control *wbc)
+static int pin_sb_for_writeback(struct writeback_control *wbc,
+ struct inode *inode, struct super_block **psb)
{
- const unsigned long start = jiffies; /* livelock avoidance */
- int sync = wbc->sync_mode == WB_SYNC_ALL;
+ struct super_block *sb = inode->i_sb;
- spin_lock(&inode_lock);
- if (!wbc->for_kupdate || list_empty(&sb->s_io))
- queue_io(sb, wbc->older_than_this);
+ /*
+ * If this sb is already pinned, nothing more to do. If not and
+ * *psb is non-NULL, unpin the old one first
+ */
+ if (sb == *psb)
+ return 0;
+ else if (*psb)
+ unpin_sb_for_writeback(psb);
- 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;
+ /*
+ * 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;
+ }
- if (!bdi_cap_writeback_dirty(bdi)) {
- redirty_tail(inode);
- if (sb_is_blkdev_sb(sb)) {
- /*
- * Dirty memory-backed blockdev: the ramdisk
- * driver does this. Skip just this inode
- */
- continue;
- }
- /*
- * Dirty memory-backed inode against a filesystem other
- * than the kernel-internal bdev filesystem. Skip the
- * entire superblock.
- */
- break;
+ spin_lock(&sb_lock);
+ sb->s_count++;
+ if (down_read_trylock(&sb->s_umount)) {
+ if (sb->s_root) {
+ spin_unlock(&sb_lock);
+ goto pinned;
}
+ /*
+ * umounted, drop rwsem again and fall through to failure
+ */
+ up_read(&sb->s_umount);
+ }
- if (inode->i_state & I_NEW) {
- requeue_io(inode);
- continue;
- }
+ sb->s_count--;
+ spin_unlock(&sb_lock);
+ return 1;
+pinned:
+ *psb = sb;
+ return 0;
+}
- 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 */
+static void writeback_inodes_wb(struct bdi_writeback *wb,
+ struct writeback_control *wbc)
+{
+ struct super_block *sb = wbc->sb, *pin_sb = NULL;
+ const unsigned long start = jiffies; /* livelock avoidance */
+
+ spin_lock(&inode_lock);
+
+ if (!wbc->for_kupdate || list_empty(&wb->b_io))
+ queue_io(wb, wbc->older_than_this);
+
+ while (!list_empty(&wb->b_io)) {
+ struct inode *inode = list_entry(wb->b_io.prev,
+ struct inode, i_list);
+ long pages_skipped;
+
+ /*
+ * super block given and doesn't match, skip this inode
+ */
+ if (sb && sb != inode->i_sb) {
+ redirty_tail(inode);
+ continue;
}
- if (wbc->bdi && bdi != wbc->bdi) {
- if (!sb_is_blkdev_sb(sb))
- break; /* fs has the wrong queue */
+ if (inode->i_state & (I_NEW | I_WILL_FREE)) {
requeue_io(inode);
- continue; /* blockdev has wrong queue */
+ continue;
}
- /* Was this inode dirtied after sync_sb_inodes was called? */
- if (time_after(inode->dirtied_when, start))
+ /*
+ * Was this inode dirtied after sync_sb_inodes was called?
+ * This keeps sync from extra jobs and livelock.
+ */
+ 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, &pin_sb)) {
+ requeue_io(inode);
+ continue;
+ }
- BUG_ON(inode->i_state & I_FREEING);
+ 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);
+ writeback_single_inode(inode, wbc);
if (wbc->pages_skipped != pages_skipped) {
/*
* writeback is not making progress due to locked
wbc->more_io = 1;
break;
}
- if (!list_empty(&sb->s_more_io))
+ if (!list_empty(&wb->b_more_io))
wbc->more_io = 1;
}
- if (sync) {
- struct inode *inode, *old_inode = NULL;
+ unpin_sb_for_writeback(&pin_sb);
+ spin_unlock(&inode_lock);
+ /* Leave any unwritten inodes on b_io */
+}
+
+void writeback_inodes_wbc(struct writeback_control *wbc)
+{
+ struct backing_dev_info *bdi = wbc->bdi;
+
+ writeback_inodes_wb(&bdi->wb, wbc);
+}
+
+/*
+ * The maximum number of pages to writeout in a single bdi flush/kupdate
+ * operation. We do this so we don't hold I_SYNC against an inode for
+ * enormous amounts of time, which would block a userspace task which has
+ * been forced to throttle against that inode. Also, the code reevaluates
+ * the dirty each time it has written this many pages.
+ */
+#define MAX_WRITEBACK_PAGES 1024
+
+static inline bool over_bground_thresh(void)
+{
+ unsigned long background_thresh, dirty_thresh;
+
+ get_dirty_limits(&background_thresh, &dirty_thresh, NULL, NULL);
+
+ return (global_page_state(NR_FILE_DIRTY) +
+ global_page_state(NR_UNSTABLE_NFS) >= background_thresh);
+}
+
+/*
+ * Explicit flushing or periodic writeback of "old" data.
+ *
+ * Define "old": the first time one of an inode's pages is dirtied, we mark the
+ * dirtying-time in the inode's address_space. So this periodic writeback code
+ * just walks the superblock inode list, writing back any inodes which are
+ * older than a specific point in time.
+ *
+ * Try to run once per dirty_writeback_interval. But if a writeback event
+ * takes longer than a dirty_writeback_interval interval, then leave a
+ * one-second gap.
+ *
+ * older_than_this takes precedence over nr_to_write. So we'll only write back
+ * all dirty pages if they are all attached to "old" mappings.
+ */
+static long wb_writeback(struct bdi_writeback *wb,
+ struct wb_writeback_args *args)
+{
+ struct writeback_control wbc = {
+ .bdi = wb->bdi,
+ .sb = args->sb,
+ .sync_mode = args->sync_mode,
+ .older_than_this = NULL,
+ .for_kupdate = args->for_kupdate,
+ .for_background = args->for_background,
+ .range_cyclic = args->range_cyclic,
+ };
+ unsigned long oldest_jif;
+ long wrote = 0;
+ struct inode *inode;
+
+ if (wbc.for_kupdate) {
+ wbc.older_than_this = &oldest_jif;
+ oldest_jif = jiffies -
+ msecs_to_jiffies(dirty_expire_interval * 10);
+ }
+ if (!wbc.range_cyclic) {
+ wbc.range_start = 0;
+ wbc.range_end = LLONG_MAX;
+ }
+
+ for (;;) {
/*
- * Data integrity sync. Must wait for all pages under writeback,
- * because there may have been pages dirtied before our sync
- * call, but which had writeout started before we write it out.
- * In which case, the inode may not be on the dirty list, but
- * we still have to wait for that writeout.
+ * Stop writeback when nr_pages has been consumed
*/
- list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
- struct address_space *mapping;
-
- if (inode->i_state &
- (I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW))
- continue;
- mapping = inode->i_mapping;
- if (mapping->nrpages == 0)
- continue;
- __iget(inode);
- spin_unlock(&inode_lock);
- /*
- * We hold a reference to 'inode' so it couldn't have
- * been removed from s_inodes list while we dropped the
- * inode_lock. We cannot iput the inode now as we can
- * be holding the last reference and we cannot iput it
- * under inode_lock. So we keep the reference and iput
- * it later.
- */
- iput(old_inode);
- old_inode = inode;
+ if (args->nr_pages <= 0)
+ break;
- filemap_fdatawait(mapping);
+ /*
+ * For background writeout, stop when we are below the
+ * background dirty threshold
+ */
+ if (args->for_background && !over_bground_thresh())
+ break;
- cond_resched();
+ wbc.more_io = 0;
+ wbc.nr_to_write = MAX_WRITEBACK_PAGES;
+ wbc.pages_skipped = 0;
+ writeback_inodes_wb(wb, &wbc);
+ args->nr_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
+ wrote += MAX_WRITEBACK_PAGES - wbc.nr_to_write;
- spin_lock(&inode_lock);
+ /*
+ * If we consumed everything, see if we have more
+ */
+ if (wbc.nr_to_write <= 0)
+ continue;
+ /*
+ * Didn't write everything and we don't have more IO, bail
+ */
+ if (!wbc.more_io)
+ break;
+ /*
+ * Did we write something? Try for more
+ */
+ if (wbc.nr_to_write < MAX_WRITEBACK_PAGES)
+ continue;
+ /*
+ * Nothing written. Wait for some inode to
+ * become available for writeback. Otherwise
+ * we'll just busyloop.
+ */
+ spin_lock(&inode_lock);
+ if (!list_empty(&wb->b_more_io)) {
+ inode = list_entry(wb->b_more_io.prev,
+ struct inode, i_list);
+ inode_wait_for_writeback(inode);
}
spin_unlock(&inode_lock);
- iput(old_inode);
- } else
- spin_unlock(&inode_lock);
+ }
- return; /* Leave any unwritten inodes on s_io */
+ return wrote;
}
-EXPORT_SYMBOL_GPL(generic_sync_sb_inodes);
-static void sync_sb_inodes(struct super_block *sb,
- struct writeback_control *wbc)
+/*
+ * Return the next bdi_work struct that hasn't been processed by this
+ * wb thread yet. ->seen is initially set for each thread that exists
+ * for this device, when a thread first notices a piece of work it
+ * clears its bit. Depending on writeback type, the thread will notify
+ * completion on either receiving the work (WB_SYNC_NONE) or after
+ * it is done (WB_SYNC_ALL).
+ */
+static struct bdi_work *get_next_work_item(struct backing_dev_info *bdi,
+ struct bdi_writeback *wb)
{
- generic_sync_sb_inodes(sb, wbc);
+ struct bdi_work *work, *ret = NULL;
+
+ rcu_read_lock();
+
+ list_for_each_entry_rcu(work, &bdi->work_list, list) {
+ if (!test_bit(wb->nr, &work->seen))
+ continue;
+ clear_bit(wb->nr, &work->seen);
+
+ ret = work;
+ break;
+ }
+
+ rcu_read_unlock();
+ return ret;
+}
+
+static long wb_check_old_data_flush(struct bdi_writeback *wb)
+{
+ unsigned long expired;
+ long nr_pages;
+
+ expired = wb->last_old_flush +
+ msecs_to_jiffies(dirty_writeback_interval * 10);
+ if (time_before(jiffies, expired))
+ return 0;
+
+ wb->last_old_flush = jiffies;
+ nr_pages = global_page_state(NR_FILE_DIRTY) +
+ global_page_state(NR_UNSTABLE_NFS) +
+ (inodes_stat.nr_inodes - inodes_stat.nr_unused);
+
+ if (nr_pages) {
+ struct wb_writeback_args args = {
+ .nr_pages = nr_pages,
+ .sync_mode = WB_SYNC_NONE,
+ .for_kupdate = 1,
+ .range_cyclic = 1,
+ };
+
+ return wb_writeback(wb, &args);
+ }
+
+ return 0;
}
/*
- * Start writeback of dirty pagecache data against all unlocked inodes.
- *
- * 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.
- *
- * If `older_than_this' is non-zero then only flush inodes which have a
- * flushtime older than *older_than_this.
- *
- * 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...
+ * Retrieve work items and do the writeback they describe
*/
-void
-writeback_inodes(struct writeback_control *wbc)
+long wb_do_writeback(struct bdi_writeback *wb, int force_wait)
{
- struct super_block *sb;
+ struct backing_dev_info *bdi = wb->bdi;
+ struct bdi_work *work;
+ long wrote = 0;
+
+ while ((work = get_next_work_item(bdi, wb)) != NULL) {
+ struct wb_writeback_args args = work->args;
+
+ /*
+ * Override sync mode, in case we must wait for completion
+ */
+ if (force_wait)
+ work->args.sync_mode = args.sync_mode = WB_SYNC_ALL;
+
+ /*
+ * If this isn't a data integrity operation, just notify
+ * that we have seen this work and we are now starting it.
+ */
+ if (args.sync_mode == WB_SYNC_NONE)
+ wb_clear_pending(wb, work);
+
+ wrote += wb_writeback(wb, &args);
+
+ /*
+ * This is a data integrity writeback, so only do the
+ * notification when we have completed the work.
+ */
+ if (args.sync_mode == WB_SYNC_ALL)
+ wb_clear_pending(wb, work);
+ }
+
+ /*
+ * Check for periodic writeback, kupdated() style
+ */
+ wrote += wb_check_old_data_flush(wb);
+
+ return wrote;
+}
+
+/*
+ * Handle writeback of dirty data for the device backed by this bdi. Also
+ * wakes up periodically and does kupdated style flushing.
+ */
+int bdi_writeback_task(struct bdi_writeback *wb)
+{
+ unsigned long last_active = jiffies;
+ unsigned long wait_jiffies = -1UL;
+ long pages_written;
+
+ while (!kthread_should_stop()) {
+ pages_written = wb_do_writeback(wb, 0);
+
+ if (pages_written)
+ last_active = jiffies;
+ else if (wait_jiffies != -1UL) {
+ unsigned long max_idle;
- 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.
+ * Longest period of inactivity that we tolerate. If we
+ * see dirty data again later, the task will get
+ * recreated automatically.
*/
- if (down_read_trylock(&sb->s_umount)) {
- if (sb->s_root)
- sync_sb_inodes(sb, wbc);
- up_read(&sb->s_umount);
- }
- spin_lock(&sb_lock);
- if (__put_super_and_need_restart(sb))
- goto restart;
+ max_idle = max(5UL * 60 * HZ, wait_jiffies);
+ if (time_after(jiffies, max_idle + last_active))
+ break;
}
- if (wbc->nr_to_write <= 0)
- break;
+
+ wait_jiffies = msecs_to_jiffies(dirty_writeback_interval * 10);
+ schedule_timeout_interruptible(wait_jiffies);
+ try_to_freeze();
}
- spin_unlock(&sb_lock);
+
+ return 0;
}
/*
- * writeback and wait upon the filesystem's dirty inodes. The caller will
- * do this in two passes - one to write, and one to wait.
- *
- * 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.
+ * Schedule writeback for all backing devices. This does WB_SYNC_NONE
+ * writeback, for integrity writeback see bdi_sync_writeback().
*/
-void sync_inodes_sb(struct super_block *sb, int wait)
+static void bdi_writeback_all(struct super_block *sb, long nr_pages)
{
- struct writeback_control wbc = {
- .sync_mode = wait ? WB_SYNC_ALL : WB_SYNC_NONE,
- .range_start = 0,
- .range_end = LLONG_MAX,
+ struct wb_writeback_args args = {
+ .sb = sb,
+ .nr_pages = nr_pages,
+ .sync_mode = WB_SYNC_NONE,
};
+ struct backing_dev_info *bdi;
- if (!wait) {
- unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY);
- unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS);
+ rcu_read_lock();
- wbc.nr_to_write = nr_dirty + nr_unstable +
- (inodes_stat.nr_inodes - inodes_stat.nr_unused);
- } else
- wbc.nr_to_write = LONG_MAX; /* doesn't actually matter */
+ list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) {
+ if (!bdi_has_dirty_io(bdi))
+ continue;
+
+ bdi_alloc_queue_work(bdi, &args);
+ }
+
+ rcu_read_unlock();
+}
+
+/*
+ * Start writeback of `nr_pages' pages. If `nr_pages' is zero, write back
+ * the whole world.
+ */
+void wakeup_flusher_threads(long nr_pages)
+{
+ if (nr_pages == 0)
+ nr_pages = global_page_state(NR_FILE_DIRTY) +
+ global_page_state(NR_UNSTABLE_NFS);
+ bdi_writeback_all(NULL, nr_pages);
+}
+
+static noinline void block_dump___mark_inode_dirty(struct inode *inode)
+{
+ if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev")) {
+ struct dentry *dentry;
+ const char *name = "?";
- sync_sb_inodes(sb, &wbc);
+ 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.
*
- * 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.
+ * Put the inode on the super block's dirty list.
*
- * 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.
+ * 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.
*/
-static void __sync_inodes(int wait)
+void __mark_inode_dirty(struct inode *inode, int flags)
{
- struct super_block *sb;
+ struct super_block *sb = inode->i_sb;
- spin_lock(&sb_lock);
-restart:
- list_for_each_entry(sb, &super_blocks, s_list) {
- 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)) {
+ if (sb->s_op->dirty_inode)
+ sb->s_op->dirty_inode(inode);
+ }
+
+ /*
+ * make sure that changes are seen by all cpus before we test i_state
+ * -- mikulas
+ */
+ smp_mb();
+
+ /* avoid the locking if we can */
+ if ((inode->i_state & flags) == flags)
+ return;
+
+ if (unlikely(block_dump))
+ block_dump___mark_inode_dirty(inode);
+
+ spin_lock(&inode_lock);
+ if ((inode->i_state & flags) != flags) {
+ const int was_dirty = inode->i_state & I_DIRTY;
+
+ inode->i_state |= flags;
+
+ /*
+ * If the inode is being synced, just update its dirty state.
+ * The unlocker will place the inode on the appropriate
+ * superblock list, based upon its state.
+ */
+ if (inode->i_state & I_SYNC)
+ goto out;
+
+ /*
+ * Only add valid (hashed) inodes to the superblock's
+ * dirty list. Add blockdev inodes as well.
+ */
+ if (!S_ISBLK(inode->i_mode)) {
+ if (hlist_unhashed(&inode->i_hash))
+ goto out;
+ }
+ if (inode->i_state & (I_FREEING|I_CLEAR))
+ goto out;
+
+ /*
+ * If the inode was already on b_dirty/b_io/b_more_io, don't
+ * reposition it (that would break b_dirty time-ordering).
+ */
+ if (!was_dirty) {
+ struct bdi_writeback *wb = &inode_to_bdi(inode)->wb;
+ struct backing_dev_info *bdi = wb->bdi;
+
+ if (bdi_cap_writeback_dirty(bdi) &&
+ !test_bit(BDI_registered, &bdi->state)) {
+ WARN_ON(1);
+ printk(KERN_ERR "bdi-%s not registered\n",
+ bdi->name);
+ }
+
+ inode->dirtied_when = jiffies;
+ list_move(&inode->i_list, &wb->b_dirty);
}
- up_read(&sb->s_umount);
- spin_lock(&sb_lock);
- if (__put_super_and_need_restart(sb))
- goto restart;
}
- spin_unlock(&sb_lock);
+out:
+ spin_unlock(&inode_lock);
}
+EXPORT_SYMBOL(__mark_inode_dirty);
-void sync_inodes(int wait)
+/*
+ * Write out a superblock's list of dirty inodes. A wait will be performed
+ * upon no inodes, all inodes or the final one, depending upon sync_mode.
+ *
+ * If older_than_this is non-NULL, then only write out inodes which
+ * had their first dirtying at a time earlier than *older_than_this.
+ *
+ * If `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 super_block *sb)
{
- __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));
- if (wait)
- __sync_inodes(1);
+ spin_lock(&inode_lock);
+
+ /*
+ * Data integrity sync. Must wait for all pages under writeback,
+ * because there may have been pages dirtied before our sync
+ * call, but which had writeout started before we write it out.
+ * In which case, the inode may not be on the dirty list, but
+ * we still have to wait for that writeout.
+ */
+ list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
+ struct address_space *mapping;
+
+ if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW))
+ continue;
+ mapping = inode->i_mapping;
+ if (mapping->nrpages == 0)
+ continue;
+ __iget(inode);
+ spin_unlock(&inode_lock);
+ /*
+ * We hold a reference to 'inode' so it couldn't have
+ * been removed from s_inodes list while we dropped the
+ * inode_lock. We cannot iput the inode now as we can
+ * be holding the last reference and we cannot iput it
+ * under inode_lock. So we keep the reference and iput
+ * it later.
+ */
+ iput(old_inode);
+ old_inode = inode;
+
+ filemap_fdatawait(mapping);
+
+ cond_resched();
+
+ spin_lock(&inode_lock);
+ }
+ spin_unlock(&inode_lock);
+ iput(old_inode);
}
+/**
+ * writeback_inodes_sb - writeback dirty inodes from given super_block
+ * @sb: the superblock
+ *
+ * Start writeback on some inodes on this super_block. No guarantees are made
+ * on how many (if any) will be written, and this function does not wait
+ * for IO completion of submitted IO. The number of pages submitted is
+ * returned.
+ */
+void writeback_inodes_sb(struct super_block *sb)
+{
+ unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY);
+ unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS);
+ long nr_to_write;
+
+ nr_to_write = nr_dirty + nr_unstable +
+ (inodes_stat.nr_inodes - inodes_stat.nr_unused);
+
+ bdi_start_writeback(sb->s_bdi, sb, nr_to_write);
+}
+EXPORT_SYMBOL(writeback_inodes_sb);
+
+/**
+ * writeback_inodes_sb_if_idle - start writeback if none underway
+ * @sb: the superblock
+ *
+ * Invoke writeback_inodes_sb if no writeback is currently underway.
+ * Returns 1 if writeback was started, 0 if not.
+ */
+int writeback_inodes_sb_if_idle(struct super_block *sb)
+{
+ if (!writeback_in_progress(sb->s_bdi)) {
+ writeback_inodes_sb(sb);
+ return 1;
+ } else
+ return 0;
+}
+EXPORT_SYMBOL(writeback_inodes_sb_if_idle);
+
+/**
+ * sync_inodes_sb - sync sb inode pages
+ * @sb: the superblock
+ *
+ * This function writes and waits on any dirty inode belonging to this
+ * super_block. The number of pages synced is returned.
+ */
+void sync_inodes_sb(struct super_block *sb)
+{
+ bdi_sync_writeback(sb->s_bdi, sb);
+ wait_sb_inodes(sb);
+}
+EXPORT_SYMBOL(sync_inodes_sb);
+
/**
* write_inode_now - write an inode to disk
* @inode: inode to write to disk
might_sleep();
spin_lock(&inode_lock);
- ret = __writeback_single_inode(inode, &wbc);
+ ret = writeback_single_inode(inode, &wbc);
spin_unlock(&inode_lock);
if (sync)
inode_sync_wait(inode);
int ret;
spin_lock(&inode_lock);
- ret = __writeback_single_inode(inode, wbc);
+ ret = writeback_single_inode(inode, wbc);
spin_unlock(&inode_lock);
return ret;
}
EXPORT_SYMBOL(sync_inode);
-
-/**
- * generic_osync_inode - flush all dirty data for a given inode to disk
- * @inode: inode to write
- * @mapping: the address_space that should be flushed
- * @what: what to write and wait upon
- *
- * This can be called by file_write functions for files which have the
- * O_SYNC flag set, to flush dirty writes to disk.
- *
- * @what is a bitmask, specifying which part of the inode's data should be
- * written and waited upon.
- *
- * OSYNC_DATA: i_mapping's dirty data
- * OSYNC_METADATA: the buffers at i_mapping->private_list
- * OSYNC_INODE: the inode itself
- */
-
-int generic_osync_inode(struct inode *inode, struct address_space *mapping, int what)
-{
- int err = 0;
- int need_write_inode_now = 0;
- int err2;
-
- if (what & OSYNC_DATA)
- err = filemap_fdatawrite(mapping);
- if (what & (OSYNC_METADATA|OSYNC_DATA)) {
- err2 = sync_mapping_buffers(mapping);
- if (!err)
- err = err2;
- }
- if (what & OSYNC_DATA) {
- err2 = filemap_fdatawait(mapping);
- if (!err)
- err = err2;
- }
-
- spin_lock(&inode_lock);
- if ((inode->i_state & I_DIRTY) &&
- ((what & OSYNC_INODE) || (inode->i_state & I_DIRTY_DATASYNC)))
- need_write_inode_now = 1;
- spin_unlock(&inode_lock);
-
- if (need_write_inode_now) {
- err2 = write_inode_now(inode, 1);
- if (!err)
- err = err2;
- }
- else
- inode_sync_wait(inode);
-
- return err;
-}
-EXPORT_SYMBOL(generic_osync_inode);
Code Review / linux-2.6.git / blobdiff