*/
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;
+ int range_cyclic;
+};
+
/*
* Work items for the bdi_writeback threads
*/
unsigned long seen;
atomic_t pending;
- struct super_block *sb;
- unsigned long nr_pages;
- enum writeback_sync_modes sync_mode;
+ struct wb_writeback_args args;
unsigned long state;
};
struct writeback_control *wbc)
{
INIT_RCU_HEAD(&work->rcu_head);
- work->sb = wbc->sb;
- work->nr_pages = wbc->nr_to_write;
- work->sync_mode = wbc->sync_mode;
+ work->args.sb = wbc->sb;
+ work->args.nr_pages = wbc->nr_to_write;
+ work->args.sync_mode = wbc->sync_mode;
+ work->args.range_cyclic = wbc->range_cyclic;
+ work->args.for_kupdate = 0;
work->state = WS_USED;
}
-static inline void bdi_work_init_on_stack(struct bdi_work *work,
- struct writeback_control *wbc)
-{
- bdi_work_init(work, wbc);
- work->state |= WS_ONSTACK;
-}
-
/**
* writeback_in_progress - determine whether there is writeback in progress
* @bdi: the device's backing_dev_info structure.
static void wb_work_complete(struct bdi_work *work)
{
- const enum writeback_sync_modes sync_mode = work->sync_mode;
+ const enum writeback_sync_modes sync_mode = work->args.sync_mode;
/*
* For allocated work, we can clear the done/seen bit right here.
void bdi_start_writeback(struct writeback_control *wbc)
{
- const bool must_wait = wbc->sync_mode == WB_SYNC_ALL;
- struct bdi_work work_stack, *work = NULL;
-
- if (!must_wait)
- work = bdi_alloc_work(wbc);
+ /*
+ * WB_SYNC_NONE is opportunistic writeback. If this allocation fails,
+ * bdi_queue_work() will wake up the thread and flush old data. This
+ * should ensure some amount of progress in freeing memory.
+ */
+ if (wbc->sync_mode != WB_SYNC_ALL) {
+ struct bdi_work *w = bdi_alloc_work(wbc);
- if (!work) {
- work = &work_stack;
- bdi_work_init_on_stack(work, wbc);
- }
+ bdi_queue_work(wbc->bdi, w);
+ } else {
+ struct bdi_work work;
- bdi_queue_work(wbc->bdi, work);
+ bdi_work_init(&work, wbc);
+ work.state |= WS_ONSTACK;
- /*
- * If the sync mode is WB_SYNC_ALL, block waiting for the work to
- * complete. If not, we only need to wait for the work to be started,
- * if we allocated it on-stack. We use the same mechanism, if the
- * wait bit is set in the bdi_work struct, then threads will not
- * clear pending until after they are done.
- *
- * Note that work == &work_stack if must_wait is true, so we don't
- * need to do call_rcu() here ever, since the completion path will
- * have done that for us.
- */
- if (must_wait || work == &work_stack) {
- bdi_wait_on_work_clear(work);
- if (work != &work_stack)
- call_rcu(&work->rcu_head, bdi_work_free);
+ bdi_queue_work(wbc->bdi, &work);
+ bdi_wait_on_work_clear(&work);
}
}
* 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, long nr_pages,
- struct super_block *sb,
- enum writeback_sync_modes sync_mode, int for_kupdate)
+static long wb_writeback(struct bdi_writeback *wb,
+ struct wb_writeback_args *args)
{
struct writeback_control wbc = {
.bdi = wb->bdi,
- .sb = sb,
- .sync_mode = sync_mode,
+ .sb = args->sb,
+ .sync_mode = args->sync_mode,
.older_than_this = NULL,
- .for_kupdate = for_kupdate,
- .range_cyclic = 1,
+ .for_kupdate = args->for_kupdate,
+ .range_cyclic = args->range_cyclic,
};
unsigned long oldest_jif;
long wrote = 0;
oldest_jif = jiffies -
msecs_to_jiffies(dirty_expire_interval * 10);
}
+ if (!wbc.range_cyclic) {
+ wbc.range_start = 0;
+ wbc.range_end = LLONG_MAX;
+ }
for (;;) {
/*
* Don't flush anything for non-integrity writeback where
* no nr_pages was given
*/
- if (!for_kupdate && nr_pages <= 0 && sync_mode == WB_SYNC_NONE)
+ if (!args->for_kupdate && args->nr_pages <= 0 &&
+ args->sync_mode == WB_SYNC_NONE)
break;
/*
* periodic background writeout and we are below the
* background dirty threshold, don't do anything
*/
- if (for_kupdate && nr_pages <= 0 && !over_bground_thresh())
+ if (args->for_kupdate && args->nr_pages <= 0 &&
+ !over_bground_thresh())
break;
wbc.more_io = 0;
wbc.nr_to_write = MAX_WRITEBACK_PAGES;
wbc.pages_skipped = 0;
writeback_inodes_wb(wb, &wbc);
- nr_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
+ args->nr_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
wrote += MAX_WRITEBACK_PAGES - wbc.nr_to_write;
/*
global_page_state(NR_UNSTABLE_NFS) +
(inodes_stat.nr_inodes - inodes_stat.nr_unused);
- if (nr_pages)
- return wb_writeback(wb, nr_pages, NULL, WB_SYNC_NONE, 1);
+ 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;
}
{
struct backing_dev_info *bdi = wb->bdi;
struct bdi_work *work;
- long nr_pages, wrote = 0;
+ long wrote = 0;
while ((work = get_next_work_item(bdi, wb)) != NULL) {
- enum writeback_sync_modes sync_mode;
-
- nr_pages = work->nr_pages;
+ struct wb_writeback_args args = work->args;
/*
* Override sync mode, in case we must wait for completion
*/
if (force_wait)
- work->sync_mode = sync_mode = WB_SYNC_ALL;
- else
- sync_mode = work->sync_mode;
+ 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 (sync_mode == WB_SYNC_NONE)
+ if (args.sync_mode == WB_SYNC_NONE)
wb_clear_pending(wb, work);
- wrote += wb_writeback(wb, nr_pages, work->sb, sync_mode, 0);
+ wrote += wb_writeback(wb, &args);
/*
* This is a data integrity writeback, so only do the
* notification when we have completed the work.
*/
- if (sync_mode == WB_SYNC_ALL)
+ if (args.sync_mode == WB_SYNC_ALL)
wb_clear_pending(wb, work);
}
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);