Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/l…

…inux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:

 - Move the nohz kick code out of the scheduler tick to a dedicated IPI,
   from Frederic Weisbecker.

  This necessiated quite some background infrastructure rework,
  including:

   * Clean up some irq-work internals
   * Implement remote irq-work
   * Implement nohz kick on top of remote irq-work
   * Move full dynticks timer enqueue notification to new kick
   * Move multi-task notification to new kick
   * Remove unecessary barriers on multi-task notification

 - Remove proliferation of wait_on_bit() action functions and allow
   wait_on_bit_action() functions to support a timeout.  (Neil Brown)

 - Another round of sched/numa improvements, cleanups and fixes.  (Rik
   van Riel)

 - Implement fast idling of CPUs when the system is partially loaded,
   for better scalability.  (Tim Chen)

 - Restructure and fix the CPU hotplug handling code that may leave
   cfs_rq and rt_rq's throttled when tasks are migrated away from a dead
   cpu.  (Kirill Tkhai)

 - Robustify the sched topology setup code.  (Peterz Zijlstra)

 - Improve sched_feat() handling wrt.  static_keys (Jason Baron)

 - Misc fixes.

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (37 commits)
  sched/fair: Fix 'make xmldocs' warning caused by missing description
  sched: Use macro for magic number of -1 for setparam
  sched: Robustify topology setup
  sched: Fix sched_setparam() policy == -1 logic
  sched: Allow wait_on_bit_action() functions to support a timeout
  sched: Remove proliferation of wait_on_bit() action functions
  sched/numa: Revert "Use effective_load() to balance NUMA loads"
  sched: Fix static_key race with sched_feat()
  sched: Remove extra static_key*() function indirection
  sched/rt: Fix replenish_dl_entity() comments to match the current upstream code
  sched: Transform resched_task() into resched_curr()
  sched/deadline: Kill task_struct->pi_top_task
  sched: Rework check_for_tasks()
  sched/rt: Enqueue just unthrottled rt_rq back on the stack in __disable_runtime()
  sched/fair: Disable runtime_enabled on dying rq
  sched/numa: Change scan period code to match intent
  sched/numa: Rework best node setting in task_numa_migrate()
  sched/numa: Examine a task move when examining a task swap
  sched/numa: Simplify task_numa_compare()
  sched/numa: Use effective_load() to balance NUMA loads
  ...

Documentation/filesystems/caching/operations.txt

@@ -90,7 +90,7 @@ operations:
      to be cleared before proceeding:
 
 		wait_on_bit(&op->flags, FSCACHE_OP_WAITING,
-			    fscache_wait_bit, TASK_UNINTERRUPTIBLE);
+			    TASK_UNINTERRUPTIBLE);
 
 
  (2) The operation may be fast asynchronous (FSCACHE_OP_FAST), in which case it

Documentation/trace/ftrace.txt

@@ -1515,7 +1515,7 @@ Doing the same with chrt -r 5 and function-trace set.
   <idle>-0       3d.h4    1us+:      0:120:R   + [003]  2448: 94:R sleep
   <idle>-0       3d.h4    2us : ttwu_do_activate.constprop.87 <-try_to_wake_up
   <idle>-0       3d.h3    3us : check_preempt_curr <-ttwu_do_wakeup
-  <idle>-0       3d.h3    3us : resched_task <-check_preempt_curr
+  <idle>-0       3d.h3    3us : resched_curr <-check_preempt_curr
   <idle>-0       3dNh3    4us : task_woken_rt <-ttwu_do_wakeup
   <idle>-0       3dNh3    4us : _raw_spin_unlock <-try_to_wake_up
   <idle>-0       3dNh3    4us : sub_preempt_count <-_raw_spin_unlock

drivers/md/dm-bufio.c

@@ -614,16 +614,6 @@ static void write_endio(struct bio *bio, int error)
 	wake_up_bit(&b->state, B_WRITING);
 }
 
-/*
- * This function is called when wait_on_bit is actually waiting.
- */
-static int do_io_schedule(void *word)
-{
-	io_schedule();
-
-	return 0;
-}
-
 /*
  * Initiate a write on a dirty buffer, but don't wait for it.
  *
@@ -640,8 +630,7 @@ static void __write_dirty_buffer(struct dm_buffer *b,
 		return;
 
 	clear_bit(B_DIRTY, &b->state);
-	wait_on_bit_lock(&b->state, B_WRITING,
-			 do_io_schedule, TASK_UNINTERRUPTIBLE);
+	wait_on_bit_lock_io(&b->state, B_WRITING, TASK_UNINTERRUPTIBLE);
 
 	if (!write_list)
 		submit_io(b, WRITE, b->block, write_endio);
@@ -675,9 +664,9 @@ static void __make_buffer_clean(struct dm_buffer *b)
 	if (!b->state)	/* fast case */
 		return;
 
-	wait_on_bit(&b->state, B_READING, do_io_schedule, TASK_UNINTERRUPTIBLE);
+	wait_on_bit_io(&b->state, B_READING, TASK_UNINTERRUPTIBLE);
 	__write_dirty_buffer(b, NULL);
-	wait_on_bit(&b->state, B_WRITING, do_io_schedule, TASK_UNINTERRUPTIBLE);
+	wait_on_bit_io(&b->state, B_WRITING, TASK_UNINTERRUPTIBLE);
 }
 
 /*
@@ -1030,7 +1019,7 @@ static void *new_read(struct dm_bufio_client *c, sector_t block,
 	if (need_submit)
 		submit_io(b, READ, b->block, read_endio);
 
-	wait_on_bit(&b->state, B_READING, do_io_schedule, TASK_UNINTERRUPTIBLE);
+	wait_on_bit_io(&b->state, B_READING, TASK_UNINTERRUPTIBLE);
 
 	if (b->read_error) {
 		int error = b->read_error;
@@ -1209,15 +1198,13 @@ int dm_bufio_write_dirty_buffers(struct dm_bufio_client *c)
 				dropped_lock = 1;
 				b->hold_count++;
 				dm_bufio_unlock(c);
-				wait_on_bit(&b->state, B_WRITING,
-					    do_io_schedule,
-					    TASK_UNINTERRUPTIBLE);
+				wait_on_bit_io(&b->state, B_WRITING,
+					       TASK_UNINTERRUPTIBLE);
 				dm_bufio_lock(c);
 				b->hold_count--;
 			} else
-				wait_on_bit(&b->state, B_WRITING,
-					    do_io_schedule,
-					    TASK_UNINTERRUPTIBLE);
+				wait_on_bit_io(&b->state, B_WRITING,
+					       TASK_UNINTERRUPTIBLE);
 		}
 
 		if (!test_bit(B_DIRTY, &b->state) &&
@@ -1321,15 +1308,15 @@ void dm_bufio_release_move(struct dm_buffer *b, sector_t new_block)
 
 	__write_dirty_buffer(b, NULL);
 	if (b->hold_count == 1) {
-		wait_on_bit(&b->state, B_WRITING,
-			    do_io_schedule, TASK_UNINTERRUPTIBLE);
+		wait_on_bit_io(&b->state, B_WRITING,
+			       TASK_UNINTERRUPTIBLE);
 		set_bit(B_DIRTY, &b->state);
 		__unlink_buffer(b);
 		__link_buffer(b, new_block, LIST_DIRTY);
 	} else {
 		sector_t old_block;
-		wait_on_bit_lock(&b->state, B_WRITING,
-				 do_io_schedule, TASK_UNINTERRUPTIBLE);
+		wait_on_bit_lock_io(&b->state, B_WRITING,
+				    TASK_UNINTERRUPTIBLE);
 		/*
 		 * Relink buffer to "new_block" so that write_callback
 		 * sees "new_block" as a block number.
@@ -1341,8 +1328,8 @@ void dm_bufio_release_move(struct dm_buffer *b, sector_t new_block)
 		__unlink_buffer(b);
 		__link_buffer(b, new_block, b->list_mode);
 		submit_io(b, WRITE, new_block, write_endio);
-		wait_on_bit(&b->state, B_WRITING,
-			    do_io_schedule, TASK_UNINTERRUPTIBLE);
+		wait_on_bit_io(&b->state, B_WRITING,
+			       TASK_UNINTERRUPTIBLE);
 		__unlink_buffer(b);
 		__link_buffer(b, old_block, b->list_mode);
 	}

drivers/md/dm-snap.c

@@ -1032,21 +1032,13 @@ static void start_merge(struct dm_snapshot *s)
 		snapshot_merge_next_chunks(s);
 }
 
-static int wait_schedule(void *ptr)
-{
-	schedule();
-
-	return 0;
-}
-
 /*
  * Stop the merging process and wait until it finishes.
  */
 static void stop_merge(struct dm_snapshot *s)
 {
 	set_bit(SHUTDOWN_MERGE, &s->state_bits);
-	wait_on_bit(&s->state_bits, RUNNING_MERGE, wait_schedule,
-		    TASK_UNINTERRUPTIBLE);
+	wait_on_bit(&s->state_bits, RUNNING_MERGE, TASK_UNINTERRUPTIBLE);
 	clear_bit(SHUTDOWN_MERGE, &s->state_bits);
 }
 

drivers/media/usb/dvb-usb-v2/dvb_usb_core.c

@@ -253,13 +253,6 @@ static int dvb_usbv2_adapter_stream_exit(struct dvb_usb_adapter *adap)
 	return usb_urb_exitv2(&adap->stream);
 }
 
-static int wait_schedule(void *ptr)
-{
-	schedule();
-
-	return 0;
-}
-
 static int dvb_usb_start_feed(struct dvb_demux_feed *dvbdmxfeed)
 {
 	struct dvb_usb_adapter *adap = dvbdmxfeed->demux->priv;
@@ -273,8 +266,7 @@ static int dvb_usb_start_feed(struct dvb_demux_feed *dvbdmxfeed)
 			dvbdmxfeed->pid, dvbdmxfeed->index);
 
 	/* wait init is done */
-	wait_on_bit(&adap->state_bits, ADAP_INIT, wait_schedule,
-			TASK_UNINTERRUPTIBLE);
+	wait_on_bit(&adap->state_bits, ADAP_INIT, TASK_UNINTERRUPTIBLE);
 
 	if (adap->active_fe == -1)
 		return -EINVAL;
@@ -568,7 +560,7 @@ static int dvb_usb_fe_sleep(struct dvb_frontend *fe)
 
 	if (!adap->suspend_resume_active) {
 		set_bit(ADAP_SLEEP, &adap->state_bits);
-		wait_on_bit(&adap->state_bits, ADAP_STREAMING, wait_schedule,
+		wait_on_bit(&adap->state_bits, ADAP_STREAMING,
 				TASK_UNINTERRUPTIBLE);
 	}
 

fs/btrfs/extent_io.c

@@ -3437,16 +3437,10 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 	return 0;
 }
 
-static int eb_wait(void *word)
-{
-	io_schedule();
-	return 0;
-}
-
 void wait_on_extent_buffer_writeback(struct extent_buffer *eb)
 {
-	wait_on_bit(&eb->bflags, EXTENT_BUFFER_WRITEBACK, eb_wait,
-		    TASK_UNINTERRUPTIBLE);
+	wait_on_bit_io(&eb->bflags, EXTENT_BUFFER_WRITEBACK,
+		       TASK_UNINTERRUPTIBLE);
 }
 
 static noinline_for_stack int

fs/buffer.c

@@ -61,16 +61,9 @@ inline void touch_buffer(struct buffer_head *bh)
 }
 EXPORT_SYMBOL(touch_buffer);
 
-static int sleep_on_buffer(void *word)
-{
-	io_schedule();
-	return 0;
-}
-
 void __lock_buffer(struct buffer_head *bh)
 {
-	wait_on_bit_lock(&bh->b_state, BH_Lock, sleep_on_buffer,
-							TASK_UNINTERRUPTIBLE);
+	wait_on_bit_lock_io(&bh->b_state, BH_Lock, TASK_UNINTERRUPTIBLE);
 }
 EXPORT_SYMBOL(__lock_buffer);
 
@@ -123,7 +116,7 @@ EXPORT_SYMBOL(buffer_check_dirty_writeback);
  */
 void __wait_on_buffer(struct buffer_head * bh)
 {
-	wait_on_bit(&bh->b_state, BH_Lock, sleep_on_buffer, TASK_UNINTERRUPTIBLE);
+	wait_on_bit_io(&bh->b_state, BH_Lock, TASK_UNINTERRUPTIBLE);
 }
 EXPORT_SYMBOL(__wait_on_buffer);
 

fs/cifs/connect.c

@@ -3934,13 +3934,6 @@ cifs_sb_master_tcon(struct cifs_sb_info *cifs_sb)
 	return tlink_tcon(cifs_sb_master_tlink(cifs_sb));
 }
 
-static int
-cifs_sb_tcon_pending_wait(void *unused)
-{
-	schedule();
-	return signal_pending(current) ? -ERESTARTSYS : 0;
-}
-
 /* find and return a tlink with given uid */
 static struct tcon_link *
 tlink_rb_search(struct rb_root *root, kuid_t uid)
@@ -4039,11 +4032,10 @@ cifs_sb_tlink(struct cifs_sb_info *cifs_sb)
 	} else {
 wait_for_construction:
 		ret = wait_on_bit(&tlink->tl_flags, TCON_LINK_PENDING,
-				  cifs_sb_tcon_pending_wait,
 				  TASK_INTERRUPTIBLE);
 		if (ret) {
 			cifs_put_tlink(tlink);
-			return ERR_PTR(ret);
+			return ERR_PTR(-ERESTARTSYS);
 		}
 
 		/* if it's good, return it */

fs/cifs/file.c

@@ -3618,13 +3618,6 @@ static int cifs_launder_page(struct page *page)
 	return rc;
 }
 
-static int
-cifs_pending_writers_wait(void *unused)
-{
-	schedule();
-	return 0;
-}
-
 void cifs_oplock_break(struct work_struct *work)
 {
 	struct cifsFileInfo *cfile = container_of(work, struct cifsFileInfo,
@@ -3636,7 +3629,7 @@ void cifs_oplock_break(struct work_struct *work)
 	int rc = 0;
 
 	wait_on_bit(&cinode->flags, CIFS_INODE_PENDING_WRITERS,
-			cifs_pending_writers_wait, TASK_UNINTERRUPTIBLE);
+			TASK_UNINTERRUPTIBLE);
 
 	server->ops->downgrade_oplock(server, cinode,
 		test_bit(CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, &cinode->flags));

fs/cifs/inode.c

@@ -1780,7 +1780,7 @@ cifs_invalidate_mapping(struct inode *inode)
  * @word: long word containing the bit lock
  */
 static int
-cifs_wait_bit_killable(void *word)
+cifs_wait_bit_killable(struct wait_bit_key *key)
 {
 	if (fatal_signal_pending(current))
 		return -ERESTARTSYS;
@@ -1794,8 +1794,8 @@ cifs_revalidate_mapping(struct inode *inode)
 	int rc;
 	unsigned long *flags = &CIFS_I(inode)->flags;
 
-	rc = wait_on_bit_lock(flags, CIFS_INO_LOCK, cifs_wait_bit_killable,
-				TASK_KILLABLE);
+	rc = wait_on_bit_lock_action(flags, CIFS_INO_LOCK, cifs_wait_bit_killable,
+				     TASK_KILLABLE);
 	if (rc)
 		return rc;
 

fs/cifs/misc.c

@@ -582,7 +582,7 @@ int cifs_get_writer(struct cifsInodeInfo *cinode)
 
 start:
 	rc = wait_on_bit(&cinode->flags, CIFS_INODE_PENDING_OPLOCK_BREAK,
-				   cifs_oplock_break_wait, TASK_KILLABLE);
+			 TASK_KILLABLE);
 	if (rc)
 		return rc;
 

fs/fs-writeback.c

@@ -342,7 +342,8 @@ static void __inode_wait_for_writeback(struct inode *inode)
 	wqh = bit_waitqueue(&inode->i_state, __I_SYNC);
 	while (inode->i_state & I_SYNC) {
 		spin_unlock(&inode->i_lock);
-		__wait_on_bit(wqh, &wq, inode_wait, TASK_UNINTERRUPTIBLE);
+		__wait_on_bit(wqh, &wq, bit_wait,
+			      TASK_UNINTERRUPTIBLE);
 		spin_lock(&inode->i_lock);
 	}
 }

fs/fscache/cookie.c

@@ -160,7 +160,7 @@ void __fscache_enable_cookie(struct fscache_cookie *cookie,
 	_enter("%p", cookie);
 
 	wait_on_bit_lock(&cookie->flags, FSCACHE_COOKIE_ENABLEMENT_LOCK,
-			 fscache_wait_bit, TASK_UNINTERRUPTIBLE);
+			 TASK_UNINTERRUPTIBLE);
 
 	if (test_bit(FSCACHE_COOKIE_ENABLED, &cookie->flags))
 		goto out_unlock;
@@ -255,7 +255,7 @@ static int fscache_acquire_non_index_cookie(struct fscache_cookie *cookie)
 	if (!fscache_defer_lookup) {
 		_debug("non-deferred lookup %p", &cookie->flags);
 		wait_on_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP,
-			    fscache_wait_bit, TASK_UNINTERRUPTIBLE);
+			    TASK_UNINTERRUPTIBLE);
 		_debug("complete");
 		if (test_bit(FSCACHE_COOKIE_UNAVAILABLE, &cookie->flags))
 			goto unavailable;
@@ -463,7 +463,6 @@ void __fscache_wait_on_invalidate(struct fscache_cookie *cookie)
 	_enter("%p", cookie);
 
 	wait_on_bit(&cookie->flags, FSCACHE_COOKIE_INVALIDATING,
-		    fscache_wait_bit_interruptible,
 		    TASK_UNINTERRUPTIBLE);
 
 	_leave("");
@@ -525,7 +524,7 @@ void __fscache_disable_cookie(struct fscache_cookie *cookie, bool invalidate)
 	}
 
 	wait_on_bit_lock(&cookie->flags, FSCACHE_COOKIE_ENABLEMENT_LOCK,
-			 fscache_wait_bit, TASK_UNINTERRUPTIBLE);
+			 TASK_UNINTERRUPTIBLE);
 	if (!test_and_clear_bit(FSCACHE_COOKIE_ENABLED, &cookie->flags))
 		goto out_unlock_enable;
 

fs/fscache/internal.h

@@ -97,8 +97,6 @@ static inline bool fscache_object_congested(void)
 	return workqueue_congested(WORK_CPU_UNBOUND, fscache_object_wq);
 }
 
-extern int fscache_wait_bit(void *);
-extern int fscache_wait_bit_interruptible(void *);
 extern int fscache_wait_atomic_t(atomic_t *);
 
 /*

fs/fscache/main.c

@@ -196,24 +196,6 @@ static void __exit fscache_exit(void)
 
 module_exit(fscache_exit);
 
-/*
- * wait_on_bit() sleep function for uninterruptible waiting
- */
-int fscache_wait_bit(void *flags)
-{
-	schedule();
-	return 0;
-}
-
-/*
- * wait_on_bit() sleep function for interruptible waiting
- */
-int fscache_wait_bit_interruptible(void *flags)
-{
-	schedule();
-	return signal_pending(current);
-}
-
 /*
  * wait_on_atomic_t() sleep function for uninterruptible waiting
  */