* 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/buffer_head.h>
#include "internal.h"
+
+/**
+ * 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.
+ */
+static 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.
+ *
+ * Determine whether there is writeback in progress against a backing device.
+ */
+int writeback_in_progress(struct backing_dev_info *bdi)
+{
+ return test_bit(BDI_pdflush, &bdi->state);
+}
+
+/**
+ * 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)
+{
+ BUG_ON(!writeback_in_progress(bdi));
+ clear_bit(BDI_pdflush, &bdi->state);
+}
+
+static noinline void block_dump___mark_inode_dirty(struct inode *inode)
+{
+ if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev")) {
+ struct dentry *dentry;
+ const char *name = "?";
+
+ dentry = d_find_alias(inode);
+ if (dentry) {
+ spin_lock(&dentry->d_lock);
+ name = (const char *) dentry->d_name.name;
+ }
+ printk(KERN_DEBUG
+ "%s(%d): dirtied inode %lu (%s) on %s\n",
+ current->comm, task_pid_nr(current), inode->i_ino,
+ name, inode->i_sb->s_id);
+ if (dentry) {
+ spin_unlock(&dentry->d_lock);
+ dput(dentry);
+ }
+ }
+}
+
/**
* __mark_inode_dirty - internal function
* @inode: inode to mark
if ((inode->i_state & flags) == flags)
return;
- if (unlikely(block_dump)) {
- struct dentry *dentry = NULL;
- const char *name = "?";
-
- 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;
- }
-
- 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);
- }
+ if (unlikely(block_dump))
+ block_dump___mark_inode_dirty(inode);
spin_lock(&inode_lock);
if ((inode->i_state & flags) != flags) {
struct inode *tail_inode;
tail_inode = list_entry(sb->s_dirty.next, struct inode, i_list);
- if (!time_after_eq(inode->dirtied_when,
+ if (time_before(inode->dirtied_when,
tail_inode->dirtied_when))
inode->dirtied_when = jiffies;
}
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 pdflush writeback.
+ */
+ ret = ret && time_before_eq(inode->dirtied_when, jiffies);
+#endif
+ return ret;
+}
+
/*
* Move expired dirty inodes from @delaying_queue to @dispatch_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_dirtied_after(inode, *older_than_this))
break;
list_move(&inode->i_list, dispatch_queue);
}
EXPORT_SYMBOL(sb_has_dirty_inodes);
/*
- * Write a single inode's dirty pages and inode data out to disk.
+ * Wait for writeback on an inode to complete.
+ */
+static void inode_wait_for_writeback(struct inode *inode)
+{
+ 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);
+}
+
+/*
+ * 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 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.
+ */
+ if (!wait) {
+ 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);
/* Set I_SYNC, reset I_DIRTY */
spin_lock(&inode_lock);
inode->i_state &= ~I_SYNC;
- if (!(inode->i_state & I_FREEING)) {
+ if (!(inode->i_state & (I_FREEING | I_CLEAR))) {
if (!(inode->i_state & I_DIRTY) &&
mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
/*
* soon as the queue becomes uncongested.
*/
inode->i_state |= I_DIRTY_PAGES;
- requeue_io(inode);
+ 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
}
/*
- * 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)
-{
- 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)) {
- struct address_space *mapping = inode->i_mapping;
- int ret;
-
- /*
- * 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);
-
- /*
- * Even if we don't actually write the inode itself here,
- * we can at least start some of the data writeout..
- */
- spin_unlock(&inode_lock);
- ret = do_writepages(mapping, wbc);
- spin_lock(&inode_lock);
- return ret;
- }
-
- /*
- * 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);
- }
- 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
+ * If we're a pdflush 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().
- *
- * 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,
* 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
-sync_sb_inodes(struct super_block *sb, struct writeback_control *wbc)
+void generic_sync_sb_inodes(struct super_block *sb,
+ struct writeback_control *wbc)
{
const unsigned long start = jiffies; /* livelock avoidance */
+ int sync = wbc->sync_mode == WB_SYNC_ALL;
+ spin_lock(&inode_lock);
if (!wbc->for_kupdate || list_empty(&sb->s_io))
queue_io(sb, wbc->older_than_this);
break;
}
+ if (inode->i_state & (I_NEW | I_WILL_FREE)) {
+ requeue_io(inode);
+ continue;
+ }
+
if (wbc->nonblocking && bdi_write_congested(bdi)) {
wbc->encountered_congestion = 1;
if (!sb_is_blkdev_sb(sb))
continue; /* blockdev has wrong queue */
}
- /* 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;
- 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 (wbc->sync_mode == WB_SYNC_HOLD) {
- inode->dirtied_when = jiffies;
- list_move(&inode->i_list, &sb->s_dirty);
- }
+ writeback_single_inode(inode, wbc);
if (current_is_pdflush())
writeback_release(bdi);
if (wbc->pages_skipped != pages_skipped) {
iput(inode);
cond_resched();
spin_lock(&inode_lock);
- if (wbc->nr_to_write <= 0)
+ if (wbc->nr_to_write <= 0) {
+ wbc->more_io = 1;
break;
+ }
+ if (!list_empty(&sb->s_more_io))
+ wbc->more_io = 1;
}
- if (!list_empty(&sb->s_more_io))
- wbc->more_io = 1;
+
+ if (sync) {
+ struct inode *inode, *old_inode = NULL;
+
+ /*
+ * 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);
+ } else
+ spin_unlock(&inode_lock);
+
return; /* Leave any unwritten inodes on s_io */
}
+EXPORT_SYMBOL_GPL(generic_sync_sb_inodes);
+
+static void sync_sb_inodes(struct super_block *sb,
+ struct writeback_control *wbc)
+{
+ generic_sync_sb_inodes(sb, wbc);
+}
/*
* Start writeback of dirty pagecache data against all unlocked inodes.
might_sleep();
spin_lock(&sb_lock);
restart:
- sb = sb_entry(super_blocks.prev);
- for (; sb != sb_entry(&super_blocks); sb = sb_entry(sb->s_list.prev)) {
+ 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++;
* be unmounted by the time it is released.
*/
if (down_read_trylock(&sb->s_umount)) {
- if (sb->s_root) {
- spin_lock(&inode_lock);
+ if (sb->s_root)
sync_sb_inodes(sb, wbc);
- spin_unlock(&inode_lock);
- }
up_read(&sb->s_umount);
}
spin_lock(&sb_lock);
/*
* 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.
+ * 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().
void sync_inodes_sb(struct super_block *sb, int wait)
{
struct writeback_control wbc = {
- .sync_mode = wait ? WB_SYNC_ALL : WB_SYNC_HOLD,
+ .sync_mode = wait ? WB_SYNC_ALL : WB_SYNC_NONE,
.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);
- 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);
-}
+ if (!wait) {
+ unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY);
+ unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS);
-/*
- * Rather lame livelock avoidance.
- */
-static void set_sb_syncing(int val)
-{
- struct super_block *sb;
- spin_lock(&sb_lock);
- sb = sb_entry(super_blocks.prev);
- for (; sb != sb_entry(&super_blocks); sb = sb_entry(sb->s_list.prev)) {
- sb->s_syncing = val;
- }
- spin_unlock(&sb_lock);
-}
-
-/**
- * sync_inodes - writes all inodes to disk
- * @wait: wait for completion
- *
- * 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.
- *
- * 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)
-{
- struct super_block *sb;
-
- 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);
- }
- up_read(&sb->s_umount);
- spin_lock(&sb_lock);
- if (__put_super_and_need_restart(sb))
- goto restart;
- }
- spin_unlock(&sb_lock);
-}
-
-void sync_inodes(int wait)
-{
- set_sb_syncing(0);
- __sync_inodes(0);
+ 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 */
- if (wait) {
- set_sb_syncing(0);
- __sync_inodes(1);
- }
+ sync_sb_inodes(sb, &wbc);
}
/**
int ret;
struct writeback_control wbc = {
.nr_to_write = LONG_MAX,
- .sync_mode = WB_SYNC_ALL,
+ .sync_mode = sync ? WB_SYNC_ALL : WB_SYNC_NONE,
.range_start = 0,
.range_end = LLONG_MAX,
};
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;
}
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.
- *
- * 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.
- *
- * Determine whether there is writeback in progress against a backing device.
- */
-int writeback_in_progress(struct backing_dev_info *bdi)
-{
- return test_bit(BDI_pdflush, &bdi->state);
-}
-
-/**
- * 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);
-}