unsigned int for_kupdate:1;
unsigned int range_cyclic:1;
unsigned int for_background:1;
+ enum wb_reason reason; /* why was writeback initiated? */
struct list_head list; /* pending work list */
struct completion *done; /* set if the caller waits */
};
-/*
- * Include the creation of the trace points after defining the
- * wb_writeback_work structure so that the definition remains local to this
- * file.
- */
-#define CREATE_TRACE_POINTS
-#include <trace/events/writeback.h>
-
/*
* We don't actually have pdflush, but this one is exported though /proc...
*/
{
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)
{
return list_entry(head, struct inode, i_wb_list);
}
+/*
+ * 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>
+
/* Wakeup flusher thread or forker thread to fork it. Requires bdi->wb_lock. */
static void bdi_wakeup_flusher(struct backing_dev_info *bdi)
{
static void
__bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
- bool range_cyclic)
+ bool range_cyclic, enum wb_reason reason)
{
struct wb_writeback_work *work;
work->sync_mode = WB_SYNC_NONE;
work->nr_pages = nr_pages;
work->range_cyclic = range_cyclic;
+ work->reason = reason;
bdi_queue_work(bdi, work);
}
* 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
* completion. Caller need not hold sb s_umount semaphore.
*
*/
-void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages)
+void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
+ enum wb_reason reason)
{
- __bdi_start_writeback(bdi, nr_pages, true);
+ __bdi_start_writeback(bdi, nr_pages, true, reason);
}
/**
*/
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;
while (!list_empty(delaying_queue)) {
inode = wb_inode(delaying_queue->prev);
- if (older_than_this &&
- inode_dirtied_after(inode, *older_than_this))
+ if (work->older_than_this &&
+ inode_dirtied_after(inode, *work->older_than_this))
break;
if (sb && sb != inode->i_sb)
do_sb_sort = 1;
* |
* +--> dequeue for IO
*/
-static void queue_io(struct bdi_writeback *wb, unsigned long *older_than_this)
+static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work)
{
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, older_than_this);
- trace_writeback_queue_io(wb, older_than_this, moved);
+ moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, work);
+ trace_writeback_queue_io(wb, work, moved);
}
static int write_inode(struct inode *inode, struct writeback_control *wbc)
/* Set I_SYNC, reset I_DIRTY_PAGES */
inode->i_state |= I_SYNC;
- inode->i_state &= ~I_DIRTY_PAGES;
spin_unlock(&inode->i_lock);
spin_unlock(&wb->list_lock);
* write_inode()
*/
spin_lock(&inode->i_lock);
+
dirty = inode->i_state & I_DIRTY;
- inode->i_state &= ~(I_DIRTY_SYNC | I_DIRTY_DATASYNC);
+ inode->i_state &= ~I_DIRTY;
+
+ /*
+ * Paired with smp_mb() in __mark_inode_dirty(). This allows
+ * __mark_inode_dirty() to test i_state without grabbing i_lock -
+ * either they see the I_DIRTY bits cleared or we see the dirtied
+ * inode.
+ *
+ * I_DIRTY_PAGES is always cleared together above even if @mapping
+ * still has dirty pages. The flag is reinstated after smp_mb() if
+ * necessary. This guarantees that either __mark_inode_dirty()
+ * sees clear I_DIRTY_PAGES or we see PAGECACHE_TAG_DIRTY.
+ */
+ smp_mb();
+
+ if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
+ inode->i_state |= I_DIRTY_PAGES;
+
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);
* We didn't write back all the pages. nfs_writepages()
* sometimes bales out without doing anything.
*/
- inode->i_state |= I_DIRTY_PAGES;
if (wbc->nr_to_write <= 0) {
/*
* slice used up: queue for next turn
return wrote;
}
-long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages)
+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, NULL);
+ queue_io(wb, &work);
__writeback_inodes_wb(wb, &work);
spin_unlock(&wb->list_lock);
return nr_pages - work.nr_pages;
}
-static inline bool over_bground_thresh(void)
+static bool over_bground_thresh(struct backing_dev_info *bdi)
{
unsigned long background_thresh, dirty_thresh;
global_dirty_limits(&background_thresh, &dirty_thresh);
- return (global_page_state(NR_FILE_DIRTY) +
- global_page_state(NR_UNSTABLE_NFS) > background_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;
}
/*
static void wb_update_bandwidth(struct bdi_writeback *wb,
unsigned long start_time)
{
- __bdi_update_bandwidth(wb->bdi, 0, 0, 0, 0, start_time);
+ __bdi_update_bandwidth(wb->bdi, 0, 0, 0, 0, 0, start_time);
}
/*
* For background writeout, stop when we are below the
* background dirty threshold
*/
- if (work->for_background && !over_bground_thresh())
+ if (work->for_background && !over_bground_thresh(wb->bdi))
break;
if (work->for_kupdate) {
trace_writeback_start(wb->bdi, work);
if (list_empty(&wb->b_io))
- queue_io(wb, work->older_than_this);
+ queue_io(wb, work);
if (work->sb)
progress = writeback_sb_inodes(work->sb, wb, work);
else
static long wb_check_background_flush(struct bdi_writeback *wb)
{
- if (over_bground_thresh()) {
+ 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);
.sync_mode = WB_SYNC_NONE,
.for_kupdate = 1,
.range_cyclic = 1,
+ .reason = WB_REASON_PERIODIC,
};
return wb_writeback(wb, &work);
* Start writeback of `nr_pages' pages. If `nr_pages' is zero, write back
* the whole world.
*/
-void wakeup_flusher_threads(long nr_pages)
+void wakeup_flusher_threads(long nr_pages, enum wb_reason reason)
{
struct backing_dev_info *bdi;
list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) {
if (!bdi_has_dirty_io(bdi))
continue;
- __bdi_start_writeback(bdi, nr_pages, false);
+ __bdi_start_writeback(bdi, nr_pages, false, reason);
}
rcu_read_unlock();
}
}
/*
- * make sure that changes are seen by all cpus before we test i_state
- * -- mikulas
+ * Paired with smp_mb() in __writeback_single_inode() for the
+ * following lockless i_state test. See there for details.
*/
smp_mb();
- /* avoid the locking if we can */
if ((inode->i_state & flags) == flags)
return;
* 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)
+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 = {
.tagged_writepages = 1,
.done = &done,
.nr_pages = nr,
+ .reason = reason,
};
WARN_ON(!rwsem_is_locked(&sb->s_umount));
/**
* 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)
+void writeback_inodes_sb(struct super_block *sb, enum wb_reason reason)
{
- return writeback_inodes_sb_nr(sb, get_nr_dirty_pages());
+ return writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason);
}
EXPORT_SYMBOL(writeback_inodes_sb);
/**
* writeback_inodes_sb_if_idle - start writeback if none underway
* @sb: the superblock
+ * @reason: reason why some writeback work was initiated
*
* 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)
+int writeback_inodes_sb_if_idle(struct super_block *sb, enum wb_reason reason)
{
if (!writeback_in_progress(sb->s_bdi)) {
down_read(&sb->s_umount);
- writeback_inodes_sb(sb);
+ writeback_inodes_sb(sb, reason);
up_read(&sb->s_umount);
return 1;
} else
* writeback_inodes_sb_if_idle - start writeback if none underway
* @sb: the superblock
* @nr: the number of pages to write
+ * @reason: reason why some writeback work was initiated
*
* Invoke writeback_inodes_sb if no writeback is currently underway.
* Returns 1 if writeback was started, 0 if not.
*/
int writeback_inodes_sb_nr_if_idle(struct super_block *sb,
- unsigned long nr)
+ unsigned long nr,
+ enum wb_reason reason)
{
if (!writeback_in_progress(sb->s_bdi)) {
down_read(&sb->s_umount);
- writeback_inodes_sb_nr(sb, nr);
+ writeback_inodes_sb_nr(sb, nr, reason);
up_read(&sb->s_umount);
return 1;
} else
.nr_pages = LONG_MAX,
.range_cyclic = 0,
.done = &done,
+ .reason = WB_REASON_SYNC,
};
WARN_ON(!rwsem_is_locked(&sb->s_umount));