Merge branch 'for-3.10/core' of git://git.kernel.dk/linux-block

Pull block core updates from Jens Axboe:

 - Major bit is Kents prep work for immutable bio vecs.

 - Stable candidate fix for a scheduling-while-atomic in the queue
   bypass operation.

 - Fix for the hang on exceeded rq->datalen 32-bit unsigned when merging
   discard bios.

 - Tejuns changes to convert the writeback thread pool to the generic
   workqueue mechanism.

 - Runtime PM framework, SCSI patches exists on top of these in James'
   tree.

 - A few random fixes.

* 'for-3.10/core' of git://git.kernel.dk/linux-block: (40 commits)
  relay: move remove_buf_file inside relay_close_buf
  partitions/efi.c: replace useless kzalloc's by kmalloc's
  fs/block_dev.c: fix iov_shorten() criteria in blkdev_aio_read()
  block: fix max discard sectors limit
  blkcg: fix "scheduling while atomic" in blk_queue_bypass_start
  Documentation: cfq-iosched: update documentation help for cfq tunables
  writeback: expose the bdi_wq workqueue
  writeback: replace custom worker pool implementation with unbound workqueue
  writeback: remove unused bdi_pending_list
  aoe: Fix unitialized var usage
  bio-integrity: Add explicit field for owner of bip_buf
  block: Add an explicit bio flag for bios that own their bvec
  block: Add bio_alloc_pages()
  block: Convert some code to bio_for_each_segment_all()
  block: Add bio_for_each_segment_all()
  bounce: Refactor __blk_queue_bounce to not use bi_io_vec
  raid1: use bio_copy_data()
  pktcdvd: Use bio_reset() in disabled code to kill bi_idx usage
  pktcdvd: use bio_copy_data()
  block: Add bio_copy_data()
  ...

1 files changed, 32 insertions, 70 deletions

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 798d4458a4d3..3be57189efd5 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -22,7 +22,6 @@
 #include <linux/mm.h>
 #include <linux/pagemap.h>
 #include <linux/kthread.h>
-#include <linux/freezer.h>
 #include <linux/writeback.h>
 #include <linux/blkdev.h>
 #include <linux/backing-dev.h>
@@ -88,20 +87,6 @@ static inline struct inode *wb_inode(struct list_head *head)
 #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)
-{
-        if (bdi->wb.task) {
-                wake_up_process(bdi->wb.task);
-        } else {
-                /*
-                 * The bdi thread isn't there, wake up the forker thread which
-                 * will create and run it.
-                 */
-                wake_up_process(default_backing_dev_info.wb.task);
-        }
-}
-
 static void bdi_queue_work(struct backing_dev_info *bdi,
                            struct wb_writeback_work *work)
 {
@@ -109,10 +94,9 @@ static void bdi_queue_work(struct backing_dev_info *bdi,
 
         spin_lock_bh(&bdi->wb_lock);
         list_add_tail(&work->list, &bdi->work_list);
-        if (!bdi->wb.task)
-                trace_writeback_nothread(bdi, work);
-        bdi_wakeup_flusher(bdi);
         spin_unlock_bh(&bdi->wb_lock);
+
+        mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
 }
 
 static void
@@ -127,10 +111,8 @@ __bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
          */
         work = kzalloc(sizeof(*work), GFP_ATOMIC);
         if (!work) {
-                if (bdi->wb.task) {
-                        trace_writeback_nowork(bdi);
-                        wake_up_process(bdi->wb.task);
-                }
+                trace_writeback_nowork(bdi);
+                mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
                 return;
         }
 
@@ -177,9 +159,7 @@ void bdi_start_background_writeback(struct backing_dev_info *bdi)
          * writeback as soon as there is no other work to do.
          */
         trace_writeback_wake_background(bdi);
-        spin_lock_bh(&bdi->wb_lock);
-        bdi_wakeup_flusher(bdi);
-        spin_unlock_bh(&bdi->wb_lock);
+        mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
 }
 
 /*
@@ -1020,67 +1000,49 @@ long wb_do_writeback(struct bdi_writeback *wb, int force_wait)
 
 /*
  * Handle writeback of dirty data for the device backed by this bdi. Also
- * wakes up periodically and does kupdated style flushing.
+ * reschedules periodically and does kupdated style flushing.
  */
-int bdi_writeback_thread(void *data)
+void bdi_writeback_workfn(struct work_struct *work)
 {
-        struct bdi_writeback *wb = data;
+        struct bdi_writeback *wb = container_of(to_delayed_work(work),
+                                                struct bdi_writeback, dwork);
         struct backing_dev_info *bdi = wb->bdi;
         long pages_written;
 
         set_worker_desc("flush-%s", dev_name(bdi->dev));
         current->flags |= PF_SWAPWRITE;
-        set_freezable();
-        wb->last_active = jiffies;
-
-        /*
-         * Our parent may run at a different priority, just set us to normal
-         */
-        set_user_nice(current, 0);
-
-        trace_writeback_thread_start(bdi);
 
-        while (!kthread_freezable_should_stop(NULL)) {
+        if (likely(!current_is_workqueue_rescuer() ||
+                   list_empty(&bdi->bdi_list))) {
                 /*
-                 * Remove own delayed wake-up timer, since we are already awake
-                 * and we'll take care of the periodic write-back.
+                 * The normal path.  Keep writing back @bdi until its
+                 * work_list is empty.  Note that this path is also taken
+                 * if @bdi is shutting down even when we're running off the
+                 * rescuer as work_list needs to be drained.
                  */
-                del_timer(&wb->wakeup_timer);
-
-                pages_written = wb_do_writeback(wb, 0);
-
+                do {
+                        pages_written = wb_do_writeback(wb, 0);
+                        trace_writeback_pages_written(pages_written);
+                } while (!list_empty(&bdi->work_list));
+        } else {
+                /*
+                 * bdi_wq can't get enough workers and we're running off
+                 * the emergency worker.  Don't hog it.  Hopefully, 1024 is
+                 * enough for efficient IO.
+                 */
+                pages_written = writeback_inodes_wb(&bdi->wb, 1024,
+                                                    WB_REASON_FORKER_THREAD);
                 trace_writeback_pages_written(pages_written);
-
-                if (pages_written)
-                        wb->last_active = jiffies;
-
-                set_current_state(TASK_INTERRUPTIBLE);
-                if (!list_empty(&bdi->work_list) || kthread_should_stop()) {
-                        __set_current_state(TASK_RUNNING);
-                        continue;
-                }
-
-                if (wb_has_dirty_io(wb) && dirty_writeback_interval)
-                        schedule_timeout(msecs_to_jiffies(dirty_writeback_interval * 10));
-                else {
-                        /*
-                         * We have nothing to do, so can go sleep without any
-                         * timeout and save power. When a work is queued or
-                         * something is made dirty - we will be woken up.
-                         */
-                        schedule();
-                }
         }
 
-        /* Flush any work that raced with us exiting */
-        if (!list_empty(&bdi->work_list))
-                wb_do_writeback(wb, 1);
+        if (!list_empty(&bdi->work_list) ||
+            (wb_has_dirty_io(wb) && dirty_writeback_interval))
+                queue_delayed_work(bdi_wq, &wb->dwork,
+                        msecs_to_jiffies(dirty_writeback_interval * 10));
 
-        trace_writeback_thread_stop(bdi);
-        return 0;
+        current->flags &= ~PF_SWAPWRITE;
 }
 
-
 /*
  * Start writeback of `nr_pages' pages.  If `nr_pages' is zero, write back
  * the whole world.