* 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);
+}
+
+/**
+ * enable_pwb - enable periodic write-back after an inode was marked as dirty.
+ * @inode: the inode which was marked as dirty
+ *
+ * This is a helper function for '__mark_inode_dirty()' which enables the
+ * periodic write-back, unless:
+ * * the backing device @inode belongs to does not support write-back;
+ * * periodic write-back is already enabled.
+ */
+static void enable_pwb(struct inode *inode)
+{
+ struct backing_dev_info *bdi = inode->i_mapping->backing_dev_info;
+
+ if (bdi_cap_writeback_dirty(bdi) &&
+ atomic_add_unless(&periodic_wb_enabled, 1, 1))
+ enable_periodic_wb();
+}
+
/**
* __mark_inode_dirty - internal function
* @inode: inode to mark
if (!was_dirty) {
inode->dirtied_when = jiffies;
list_move(&inode->i_list, &sb->s_dirty);
+ enable_pwb(inode);
}
}
out:
EXPORT_SYMBOL(__mark_inode_dirty);
+/**
+ * mark_sb_dirty - mark super block as dirty.
+ * @sb: the super block to mark as dirty
+ *
+ * This function marks super block @sb as dirty and enables the periodic
+ * write-back, unless it is already enabled. Note, VFS does not serialize the
+ * super block clean/dirty (@sb->s_dirt) state changes, and each FS is
+ * responsible for doing its own serialization.
+ */
+void mark_sb_dirty(struct super_block *sb)
+{
+ sb->s_dirt = 1;
+ /*
+ * If 'periodic_wb_enabled' is 0, set it to 1 and enable the periodic
+ * write-back.
+ */
+ if (atomic_add_unless(&periodic_wb_enabled, 1, 1))
+ enable_periodic_wb();
+}
+
+EXPORT_SYMBOL(mark_sb_dirty);
+
static int write_inode(struct inode *inode, int sync)
{
if (inode->i_sb->s_op->write_inode && !is_bad_inode(inode))
* 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
* 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 */
+ spin_lock(&inode_lock);
if (!wbc->for_kupdate || list_empty(&sb->s_io))
queue_io(sb, wbc->older_than_this);
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;
}
+ 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);
(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);
}
/*
{
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)) {
+ list_for_each_entry_reverse(sb, &super_blocks, s_list)
sb->s_syncing = val;
- }
spin_unlock(&sb_lock);
}
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,
};
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);
-}
projects / h-e-n / blobdiff