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

8 files changed, 16 insertions, 24 deletions

diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 4042ff5..524dd80 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -361,8 +361,8 @@ start:
 	 * Prevent starvation issues if someone is doing a consistency
 	 * sync-to-disk
 	 */
-	ret = wait_on_bit(&NFS_I(mapping->host)->flags, NFS_INO_FLUSHING,
-			nfs_wait_bit_killable, TASK_KILLABLE);
+	ret = wait_on_bit_action(&NFS_I(mapping->host)->flags, NFS_INO_FLUSHING,
+				 nfs_wait_bit_killable, TASK_KILLABLE);
 	if (ret)
 		return ret;
 
diff --git a/fs/nfs/filelayout/filelayoutdev.c b/fs/nfs/filelayout/filelayoutdev.c
index 44bf014..e2a0361 100644
--- a/fs/nfs/filelayout/filelayoutdev.c
+++ b/fs/nfs/filelayout/filelayoutdev.c
@@ -783,8 +783,8 @@ nfs4_fl_select_ds_fh(struct pnfs_layout_segment *lseg, u32 j)
 static void nfs4_wait_ds_connect(struct nfs4_pnfs_ds *ds)
 {
 	might_sleep();
-	wait_on_bit(&ds->ds_state, NFS4DS_CONNECTING,
-			nfs_wait_bit_killable, TASK_KILLABLE);
+	wait_on_bit_action(&ds->ds_state, NFS4DS_CONNECTING,
+			   nfs_wait_bit_killable, TASK_KILLABLE);
 }
 
 static void nfs4_clear_ds_conn_bit(struct nfs4_pnfs_ds *ds)
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 9927913..abd37a3 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -75,7 +75,7 @@ nfs_fattr_to_ino_t(struct nfs_fattr *fattr)
  * nfs_wait_bit_killable - helper for functions that are sleeping on bit locks
  * @word: long word containing the bit lock
  */
-int nfs_wait_bit_killable(void *word)
+int nfs_wait_bit_killable(struct wait_bit_key *key)
 {
 	if (fatal_signal_pending(current))
 		return -ERESTARTSYS;
@@ -1074,8 +1074,8 @@ int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
 	 * the bit lock here if it looks like we're going to be doing that.
 	 */
 	for (;;) {
-		ret = wait_on_bit(bitlock, NFS_INO_INVALIDATING,
-				  nfs_wait_bit_killable, TASK_KILLABLE);
+		ret = wait_on_bit_action(bitlock, NFS_INO_INVALIDATING,
+					 nfs_wait_bit_killable, TASK_KILLABLE);
 		if (ret)
 			goto out;
 		spin_lock(&inode->i_lock);
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index f415cbf..617f366 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -348,7 +348,7 @@ extern int nfs_drop_inode(struct inode *);
 extern void nfs_clear_inode(struct inode *);
 extern void nfs_evict_inode(struct inode *);
 void nfs_zap_acl_cache(struct inode *inode);
-extern int nfs_wait_bit_killable(void *word);
+extern int nfs_wait_bit_killable(struct wait_bit_key *key);
 
 /* super.c */
 extern const struct super_operations nfs_sops;
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 848f685..42f1211 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1251,8 +1251,8 @@ int nfs4_wait_clnt_recover(struct nfs_client *clp)
 	might_sleep();
 
 	atomic_inc(&clp->cl_count);
-	res = wait_on_bit(&clp->cl_state, NFS4CLNT_MANAGER_RUNNING,
-			nfs_wait_bit_killable, TASK_KILLABLE);
+	res = wait_on_bit_action(&clp->cl_state, NFS4CLNT_MANAGER_RUNNING,
+				 nfs_wait_bit_killable, TASK_KILLABLE);
 	if (res)
 		goto out;
 	if (clp->cl_cons_state < 0)
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 17fab89..0be5050 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -115,7 +115,7 @@ __nfs_iocounter_wait(struct nfs_io_counter *c)
 		set_bit(NFS_IO_INPROGRESS, &c->flags);
 		if (atomic_read(&c->io_count) == 0)
 			break;
-		ret = nfs_wait_bit_killable(&c->flags);
+		ret = nfs_wait_bit_killable(&q.key);
 	} while (atomic_read(&c->io_count) != 0);
 	finish_wait(wq, &q.wait);
 	return ret;
@@ -136,12 +136,6 @@ nfs_iocounter_wait(struct nfs_io_counter *c)
 	return __nfs_iocounter_wait(c);
 }
 
-static int nfs_wait_bit_uninterruptible(void *word)
-{
-	io_schedule();
-	return 0;
-}
-
 /*
  * nfs_page_group_lock - lock the head of the page group
  * @req - request in group that is to be locked
@@ -156,7 +150,6 @@ nfs_page_group_lock(struct nfs_page *req)
 	WARN_ON_ONCE(head != head->wb_head);
 
 	wait_on_bit_lock(&head->wb_flags, PG_HEADLOCK,
-			nfs_wait_bit_uninterruptible,
 			TASK_UNINTERRUPTIBLE);
 }
 
@@ -435,9 +428,8 @@ void nfs_release_request(struct nfs_page *req)
 int
 nfs_wait_on_request(struct nfs_page *req)
 {
-	return wait_on_bit(&req->wb_flags, PG_BUSY,
-			nfs_wait_bit_uninterruptible,
-			TASK_UNINTERRUPTIBLE);
+	return wait_on_bit_io(&req->wb_flags, PG_BUSY,
+			      TASK_UNINTERRUPTIBLE);
 }
 
 /*
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 6fdcd23..a8914b3 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1885,7 +1885,7 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync)
 	if (test_and_set_bit(NFS_INO_LAYOUTCOMMITTING, &nfsi->flags)) {
 		if (!sync)
 			goto out;
-		status = wait_on_bit_lock(&nfsi->flags,
+		status = wait_on_bit_lock_action(&nfsi->flags,
 				NFS_INO_LAYOUTCOMMITTING,
 				nfs_wait_bit_killable,
 				TASK_KILLABLE);
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 5e2f1030..962c9ee 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -623,7 +623,7 @@ int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
 	int err;
 
 	/* Stop dirtying of new pages while we sync */
-	err = wait_on_bit_lock(bitlock, NFS_INO_FLUSHING,
+	err = wait_on_bit_lock_action(bitlock, NFS_INO_FLUSHING,
 			nfs_wait_bit_killable, TASK_KILLABLE);
 	if (err)
 		goto out_err;
@@ -1703,7 +1703,7 @@ int nfs_commit_inode(struct inode *inode, int how)
 			return error;
 		if (!may_wait)
 			goto out_mark_dirty;
-		error = wait_on_bit(&NFS_I(inode)->flags,
+		error = wait_on_bit_action(&NFS_I(inode)->flags,
 				NFS_INO_COMMIT,
 				nfs_wait_bit_killable,
 				TASK_KILLABLE);