4.12.4-stable review

@@ -67,19 +67,12 @@ static inline void vtime_account_system(
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
 extern void arch_vtime_task_switch(struct task_struct *tsk);
-extern void vtime_account_user(struct task_struct *tsk);
 extern void vtime_user_enter(struct task_struct *tsk);
-
-static inline void vtime_user_exit(struct task_struct *tsk)
-{
-	vtime_account_user(tsk);
-}
-
+extern void vtime_user_exit(struct task_struct *tsk);
 extern void vtime_guest_enter(struct task_struct *tsk);
 extern void vtime_guest_exit(struct task_struct *tsk);
 extern void vtime_init_idle(struct task_struct *tsk, int cpu);
 #else /* !CONFIG_VIRT_CPU_ACCOUNTING_GEN  */
-static inline void vtime_account_user(struct task_struct *tsk) { }
 static inline void vtime_user_enter(struct task_struct *tsk) { }
 static inline void vtime_user_exit(struct task_struct *tsk) { }
 static inline void vtime_guest_enter(struct task_struct *tsk) { }

@@ -724,21 +724,21 @@ void vtime_account_system(struct task_st
 	write_seqcount_end(&tsk->vtime_seqcount);
 }
 
-void vtime_account_user(struct task_struct *tsk)
+void vtime_user_enter(struct task_struct *tsk)
 {
 	write_seqcount_begin(&tsk->vtime_seqcount);
-	tsk->vtime_snap_whence = VTIME_SYS;
 	if (vtime_delta(tsk))
-		account_user_time(tsk, get_vtime_delta(tsk));
+		__vtime_account_system(tsk);
+	tsk->vtime_snap_whence = VTIME_USER;
 	write_seqcount_end(&tsk->vtime_seqcount);
 }
 
-void vtime_user_enter(struct task_struct *tsk)
+void vtime_user_exit(struct task_struct *tsk)
 {
 	write_seqcount_begin(&tsk->vtime_seqcount);
+	tsk->vtime_snap_whence = VTIME_SYS;
 	if (vtime_delta(tsk))
-		__vtime_account_system(tsk);
-	tsk->vtime_snap_whence = VTIME_USER;
+		account_user_time(tsk, get_vtime_delta(tsk));
 	write_seqcount_end(&tsk->vtime_seqcount);
 }
 

@@ -736,9 +736,9 @@ void vtime_user_enter(struct task_struct
 void vtime_user_exit(struct task_struct *tsk)
 {
 	write_seqcount_begin(&tsk->vtime_seqcount);
-	tsk->vtime_snap_whence = VTIME_SYS;
 	if (vtime_delta(tsk))
 		account_user_time(tsk, get_vtime_delta(tsk));
+	tsk->vtime_snap_whence = VTIME_SYS;
 	write_seqcount_end(&tsk->vtime_seqcount);
 }
 

@@ -171,8 +171,8 @@ extern struct cred init_cred;
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
 # define INIT_VTIME(tsk)						\
 	.vtime_seqcount = SEQCNT_ZERO(tsk.vtime_seqcount),	\
-	.vtime_snap = 0,				\
-	.vtime_snap_whence = VTIME_SYS,
+	.vtime_starttime = 0,				\
+	.vtime_state = VTIME_SYS,
 #else
 # define INIT_VTIME(tsk)
 #endif

@@ -671,7 +671,7 @@ struct task_struct {
 	struct prev_cputime		prev_cputime;
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
 	seqcount_t			vtime_seqcount;
-	unsigned long long		vtime_snap;
+	unsigned long long		vtime_starttime;
 	enum {
 		/* Task is sleeping or running in a CPU with VTIME inactive: */
 		VTIME_INACTIVE = 0,

@@ -679,7 +679,7 @@ struct task_struct {
 		VTIME_USER,
 		/* Task runs in kernelspace in a CPU with VTIME active: */
 		VTIME_SYS,
-	} vtime_snap_whence;
+	} vtime_state;
 #endif
 
 #ifdef CONFIG_NO_HZ_FULL

@@ -1638,8 +1638,8 @@ static __latent_entropy struct task_stru
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
 	seqcount_init(&p->vtime_seqcount);
-	p->vtime_snap = 0;
-	p->vtime_snap_whence = VTIME_INACTIVE;
+	p->vtime_starttime = 0;
+	p->vtime_state = VTIME_INACTIVE;
 #endif
 
 #if defined(SPLIT_RSS_COUNTING)

@@ -683,10 +683,10 @@ static u64 vtime_delta(struct task_struc
 {
 	unsigned long now = READ_ONCE(jiffies);
 
-	if (time_before(now, (unsigned long)tsk->vtime_snap))
+	if (time_before(now, (unsigned long)tsk->vtime_starttime))
 		return 0;
 
-	return jiffies_to_nsecs(now - tsk->vtime_snap);
+	return jiffies_to_nsecs(now - tsk->vtime_starttime);
 }
 
 static u64 get_vtime_delta(struct task_struct *tsk)

@@ -701,10 +701,10 @@ static u64 get_vtime_delta(struct task_s
 	 * elapsed time. Limit account_other_time to prevent rounding
 	 * errors from causing elapsed vtime to go negative.
 	 */
-	delta = jiffies_to_nsecs(now - tsk->vtime_snap);
+	delta = jiffies_to_nsecs(now - tsk->vtime_starttime);
 	other = account_other_time(delta);
-	WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_INACTIVE);
-	tsk->vtime_snap = now;
+	WARN_ON_ONCE(tsk->vtime_state == VTIME_INACTIVE);
+	tsk->vtime_starttime = now;
 
 	return delta - other;
 }

@@ -746,7 +746,7 @@ void vtime_guest_enter(struct task_struc
 {
 	/*
 	 * The flags must be updated under the lock with
-	 * the vtime_snap flush and update.
+	 * the vtime_starttime flush and update.
 	 * That enforces a right ordering and update sequence
 	 * synchronization against the reader (task_gtime())
 	 * that can thus safely catch up with a tickless delta.

@@ -776,12 +776,12 @@ void vtime_account_idle(struct task_stru
 void arch_vtime_task_switch(struct task_struct *prev)
 {
 	write_seqcount_begin(&prev->vtime_seqcount);
-	prev->vtime_snap_whence = VTIME_INACTIVE;
+	prev->vtime_state = VTIME_INACTIVE;
 	write_seqcount_end(&prev->vtime_seqcount);
 
 	write_seqcount_begin(&current->vtime_seqcount);
-	current->vtime_snap_whence = VTIME_SYS;
-	current->vtime_snap = jiffies;
+	current->vtime_state = VTIME_SYS;
+	current->vtime_starttime = jiffies;
 	write_seqcount_end(&current->vtime_seqcount);
 }
 

@@ -791,8 +791,8 @@ void vtime_init_idle(struct task_struct
 
 	local_irq_save(flags);
 	write_seqcount_begin(&t->vtime_seqcount);
-	t->vtime_snap_whence = VTIME_SYS;
-	t->vtime_snap = jiffies;
+	t->vtime_state = VTIME_SYS;
+	t->vtime_starttime = jiffies;
 	write_seqcount_end(&t->vtime_seqcount);
 	local_irq_restore(flags);
 }

@@ -809,7 +809,7 @@ u64 task_gtime(struct task_struct *t)
 		seq = read_seqcount_begin(&t->vtime_seqcount);
 
 		gtime = t->gtime;
-		if (t->vtime_snap_whence == VTIME_SYS && t->flags & PF_VCPU)
+		if (t->vtime_state == VTIME_SYS && t->flags & PF_VCPU)
 			gtime += vtime_delta(t);
 
 	} while (read_seqcount_retry(&t->vtime_seqcount, seq));

@@ -840,7 +840,7 @@ void task_cputime(struct task_struct *t,
 		*stime = t->stime;
 
 		/* Task is sleeping, nothing to add */
-		if (t->vtime_snap_whence == VTIME_INACTIVE || is_idle_task(t))
+		if (t->vtime_state == VTIME_INACTIVE || is_idle_task(t))
 			continue;
 
 		delta = vtime_delta(t);

@@ -849,9 +849,9 @@ void task_cputime(struct task_struct *t,
 		 * Task runs either in user or kernel space, add pending nohz time to
 		 * the right place.
 		 */
-		if (t->vtime_snap_whence == VTIME_USER || t->flags & PF_VCPU)
+		if (t->vtime_state == VTIME_USER || t->flags & PF_VCPU)
 			*utime += delta;
-		else if (t->vtime_snap_whence == VTIME_SYS)
+		else if (t->vtime_state == VTIME_SYS)
 			*stime += delta;
 	} while (read_seqcount_retry(&t->vtime_seqcount, seq));
 }

@@ -170,9 +170,9 @@ extern struct cred init_cred;
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
 # define INIT_VTIME(tsk)						\
-	.vtime_seqcount = SEQCNT_ZERO(tsk.vtime_seqcount),	\
-	.vtime_starttime = 0,				\
-	.vtime_state = VTIME_SYS,
+	.vtime.seqcount = SEQCNT_ZERO(tsk.vtime.seqcount),		\
+	.vtime.starttime = 0,						\
+	.vtime.state = VTIME_SYS,
 #else
 # define INIT_VTIME(tsk)
 #endif

@@ -223,6 +223,21 @@ struct task_cputime {
 #define prof_exp			stime
 #define sched_exp			sum_exec_runtime
 
+enum vtime_state {
+	/* Task is sleeping or running in a CPU with VTIME inactive: */
+	VTIME_INACTIVE = 0,
+	/* Task runs in userspace in a CPU with VTIME active: */
+	VTIME_USER,
+	/* Task runs in kernelspace in a CPU with VTIME active: */
+	VTIME_SYS,
+};
+
+struct vtime {
+	seqcount_t		seqcount;
+	unsigned long long	starttime;
+	enum vtime_state	state;
+};
+
 struct sched_info {
 #ifdef CONFIG_SCHED_INFO
 	/* Cumulative counters: */

@@ -670,16 +685,7 @@ struct task_struct {
 	u64				gtime;
 	struct prev_cputime		prev_cputime;
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
-	seqcount_t			vtime_seqcount;
-	unsigned long long		vtime_starttime;
-	enum {
-		/* Task is sleeping or running in a CPU with VTIME inactive: */
-		VTIME_INACTIVE = 0,
-		/* Task runs in userspace in a CPU with VTIME active: */
-		VTIME_USER,
-		/* Task runs in kernelspace in a CPU with VTIME active: */
-		VTIME_SYS,
-	} vtime_state;
+	struct vtime			vtime;
 #endif
 
 #ifdef CONFIG_NO_HZ_FULL

@@ -1637,9 +1637,9 @@ static __latent_entropy struct task_stru
 	prev_cputime_init(&p->prev_cputime);
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
-	seqcount_init(&p->vtime_seqcount);
-	p->vtime_starttime = 0;
-	p->vtime_state = VTIME_INACTIVE;
+	seqcount_init(&p->vtime.seqcount);
+	p->vtime.starttime = 0;
+	p->vtime.state = VTIME_INACTIVE;
 #endif
 
 #if defined(SPLIT_RSS_COUNTING)

231 lines not on this page · raw message

@@ -236,6 +236,9 @@ struct vtime {
 	seqcount_t		seqcount;
 	unsigned long long	starttime;
 	enum vtime_state	state;
+	u64			utime;
+	u64			stime;
+	u64			gtime;
 };
 
 struct sched_info {

145 lines not on this page · raw message

index 3dafea579263..ad275b25e3f9 100644
@@ -683,7 +683,7 @@ static u64 vtime_delta(struct vtime *vtime)
 {
 	unsigned long long clock;
 
-	clock = sched_clock_cpu(smp_processor_id());
+	clock = sched_clock();
 	if (clock < vtime->starttime)
 		return 0;
 

@@ -814,7 +814,7 @@ void arch_vtime_task_switch(struct task_struct *prev)
 
 	write_seqcount_begin(&vtime->seqcount);
 	vtime->state = VTIME_SYS;
-	vtime->starttime = sched_clock_cpu(smp_processor_id());
+	vtime->starttime = sched_clock();
 	write_seqcount_end(&vtime->seqcount);
 }
 

@@ -826,7 +826,7 @@ void vtime_init_idle(struct task_struct *t, int cpu)
 	local_irq_save(flags);
 	write_seqcount_begin(&vtime->seqcount);
 	vtime->state = VTIME_SYS;
-	vtime->starttime = sched_clock_cpu(cpu);
+	vtime->starttime = sched_clock();
 	write_seqcount_end(&vtime->seqcount);
 	local_irq_restore(flags);
 }

@@ -6619,10 +6619,10 @@ int can_migrate_task(struct task_struct
 		 * our sched_group. We may want to revisit it if we couldn't
 		 * meet load balance goals by pulling other tasks on src_cpu.
 		 *
-		 * Also avoid computing new_dst_cpu if we have already computed
-		 * one in current iteration.
+		 * Avoid computing new_dst_cpu for NEWLY_IDLE or if we have
+		 * already computed one in current iteration.
 		 */
-		if (!env->dst_grpmask || (env->flags & LBF_DST_PINNED))
+		if (env->idle == CPU_NEWLY_IDLE || (env->flags & LBF_DST_PINNED))
 			return 0;
 
 		/* Prevent to re-select dst_cpu via env's cpus */

@@ -7973,14 +7973,7 @@ static int load_balance(int this_cpu, st
 		.tasks		= LIST_HEAD_INIT(env.tasks),
 	};
 
-	/*
-	 * For NEWLY_IDLE load_balancing, we don't need to consider
-	 * other cpus in our group
-	 */
-	if (idle == CPU_NEWLY_IDLE)
-		env.dst_grpmask = NULL;
-
-	cpumask_copy(cpus, cpu_active_mask);
+	cpumask_and(cpus, sched_domain_span(sd), cpu_active_mask);
 
 	schedstat_inc(sd->lb_count[idle]);
 

@@ -8102,7 +8095,15 @@ more_balance:
 		/* All tasks on this runqueue were pinned by CPU affinity */
 		if (unlikely(env.flags & LBF_ALL_PINNED)) {
 			cpumask_clear_cpu(cpu_of(busiest), cpus);
-			if (!cpumask_empty(cpus)) {
+			/*
+			 * Attempting to continue load balancing at the current
+			 * sched_domain level only makes sense if there are
+			 * active CPUs remaining as possible busiest CPUs to
+			 * pull load from which are not contained within the
+			 * destination group that is receiving any migrated
+			 * load.
+			 */
+			if (!cpumask_subset(cpus, env.dst_grpmask)) {
 				env.loop = 0;
 				env.loop_break = sched_nr_migrate_break;
 				goto redo;

@@ -8398,6 +8399,13 @@ static int active_load_balance_cpu_stop(
 			.src_cpu	= busiest_rq->cpu,
 			.src_rq		= busiest_rq,
 			.idle		= CPU_IDLE,
+			/*
+			 * can_migrate_task() doesn't need to compute new_dst_cpu
+			 * for active balancing. Since we have CPU_IDLE, but no
+			 * @dst_grpmask we need to make that test go away with lying
+			 * about DST_PINNED.
+			 */
+			.flags		= LBF_DST_PINNED,
 		};
 
 		schedstat_inc(sd->alb_count);

@@ -1255,9 +1255,9 @@ void clean_tree_block(struct btrfs_fs_in
 		btrfs_assert_tree_locked(buf);
 
 		if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &buf->bflags)) {
-			__percpu_counter_add(&fs_info->dirty_metadata_bytes,
-					     -buf->len,
-					     fs_info->dirty_metadata_batch);
+			percpu_counter_add_batch(&fs_info->dirty_metadata_bytes,
+						 -buf->len,
+						 fs_info->dirty_metadata_batch);
 			/* ugh, clear_extent_buffer_dirty needs to lock the page */
 			btrfs_set_lock_blocking(buf);
 			clear_extent_buffer_dirty(buf);

@@ -4049,9 +4049,9 @@ void btrfs_mark_buffer_dirty(struct exte
 			buf->start, transid, fs_info->generation);
 	was_dirty = set_extent_buffer_dirty(buf);
 	if (!was_dirty)
-		__percpu_counter_add(&fs_info->dirty_metadata_bytes,
-				     buf->len,
-				     fs_info->dirty_metadata_batch);
+		percpu_counter_add_batch(&fs_info->dirty_metadata_bytes,
+					 buf->len,
+					 fs_info->dirty_metadata_batch);
 #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
 	if (btrfs_header_level(buf) == 0 && check_leaf(root, buf)) {
 		btrfs_print_leaf(fs_info, buf);

@@ -3597,9 +3597,9 @@ lock_extent_buffer_for_io(struct extent_
 		set_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags);
 		spin_unlock(&eb->refs_lock);
 		btrfs_set_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN);
-		__percpu_counter_add(&fs_info->dirty_metadata_bytes,
-				     -eb->len,
-				     fs_info->dirty_metadata_batch);
+		percpu_counter_add_batch(&fs_info->dirty_metadata_bytes,
+					 -eb->len,
+					 fs_info->dirty_metadata_batch);
 		ret = 1;
 	} else {
 		spin_unlock(&eb->refs_lock);

@@ -1766,8 +1766,8 @@ static void btrfs_set_bit_hook(struct in
 		if (btrfs_is_testing(fs_info))
 			return;
 
-		__percpu_counter_add(&fs_info->delalloc_bytes, len,
-				     fs_info->delalloc_batch);
+		percpu_counter_add_batch(&fs_info->delalloc_bytes, len,
+					 fs_info->delalloc_batch);
 		spin_lock(&BTRFS_I(inode)->lock);
 		BTRFS_I(inode)->delalloc_bytes += len;
 		if (*bits & EXTENT_DEFRAG)

@@ -1840,8 +1840,8 @@ static void btrfs_clear_bit_hook(struct
 					&inode->vfs_inode,
 					state->start, len);
 
-		__percpu_counter_add(&fs_info->delalloc_bytes, -len,
-				     fs_info->delalloc_batch);
+		percpu_counter_add_batch(&fs_info->delalloc_bytes, -len,
+					 fs_info->delalloc_batch);
 		spin_lock(&inode->lock);
 		inode->delalloc_bytes -= len;
 		if (do_list && inode->delalloc_bytes == 0 &&

@@ -1209,7 +1209,7 @@ xfs_mod_icount(
 	struct xfs_mount	*mp,
 	int64_t			delta)
 {
-	__percpu_counter_add(&mp->m_icount, delta, XFS_ICOUNT_BATCH);
+	percpu_counter_add_batch(&mp->m_icount, delta, XFS_ICOUNT_BATCH);
 	if (__percpu_counter_compare(&mp->m_icount, 0, XFS_ICOUNT_BATCH) < 0) {
 		ASSERT(0);
 		percpu_counter_add(&mp->m_icount, -delta);

@@ -1288,7 +1288,7 @@ xfs_mod_fdblocks(
 	else
 		batch = XFS_FDBLOCKS_BATCH;
 
-	__percpu_counter_add(&mp->m_fdblocks, delta, batch);
+	percpu_counter_add_batch(&mp->m_fdblocks, delta, batch);
 	if (__percpu_counter_compare(&mp->m_fdblocks, mp->m_alloc_set_aside,
 				     XFS_FDBLOCKS_BATCH) >= 0) {
 		/* we had space! */

@@ -66,7 +66,7 @@ static inline bool bdi_has_dirty_io(stru
 static inline void __add_wb_stat(struct bdi_writeback *wb,
 				 enum wb_stat_item item, s64 amount)
 {
-	__percpu_counter_add(&wb->stat[item], amount, WB_STAT_BATCH);
+	percpu_counter_add_batch(&wb->stat[item], amount, WB_STAT_BATCH);
 }
 
 static inline void __inc_wb_stat(struct bdi_writeback *wb,

@@ -518,7 +518,7 @@ static inline void blkg_stat_exit(struct
  */
 static inline void blkg_stat_add(struct blkg_stat *stat, uint64_t val)
 {
-	__percpu_counter_add(&stat->cpu_cnt, val, BLKG_STAT_CPU_BATCH);
+	percpu_counter_add_batch(&stat->cpu_cnt, val, BLKG_STAT_CPU_BATCH);
 }
 
 /**

@@ -597,14 +597,14 @@ static inline void blkg_rwstat_add(struc
 	else
 		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_READ];
 
-	__percpu_counter_add(cnt, val, BLKG_STAT_CPU_BATCH);
+	percpu_counter_add_batch(cnt, val, BLKG_STAT_CPU_BATCH);
 
 	if (op_is_sync(op))
 		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_SYNC];
 	else
 		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_ASYNC];
 
-	__percpu_counter_add(cnt, val, BLKG_STAT_CPU_BATCH);
+	percpu_counter_add_batch(cnt, val, BLKG_STAT_CPU_BATCH);
 }
 
 /**

@@ -22,7 +22,7 @@ unsigned long vm_memory_committed(void);
 
 static inline void vm_acct_memory(long pages)
 {
-	__percpu_counter_add(&vm_committed_as, pages, vm_committed_as_batch);
+	percpu_counter_add_batch(&vm_committed_as, pages, vm_committed_as_batch);
 }
 
 static inline void vm_unacct_memory(long pages)

@@ -39,7 +39,8 @@ int __percpu_counter_init(struct percpu_
 
 void percpu_counter_destroy(struct percpu_counter *fbc);
 void percpu_counter_set(struct percpu_counter *fbc, s64 amount);
-void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch);
+void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount,
+			      s32 batch);
 s64 __percpu_counter_sum(struct percpu_counter *fbc);
 int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch);
 

@@ -50,7 +51,7 @@ static inline int percpu_counter_compare
 
 static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount)
 {
-	__percpu_counter_add(fbc, amount, percpu_counter_batch);
+	percpu_counter_add_batch(fbc, amount, percpu_counter_batch);
 }
 
 static inline s64 percpu_counter_sum_positive(struct percpu_counter *fbc)

@@ -136,7 +137,7 @@ percpu_counter_add(struct percpu_counter
 }
 
 static inline void
-__percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch)
+percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch)
 {
 	percpu_counter_add(fbc, amount);
 }

@@ -154,12 +154,12 @@ static inline int frag_mem_limit(struct
 
 static inline void sub_frag_mem_limit(struct netns_frags *nf, int i)
 {
-	__percpu_counter_add(&nf->mem, -i, frag_percpu_counter_batch);
+	percpu_counter_add_batch(&nf->mem, -i, frag_percpu_counter_batch);
 }
 
 static inline void add_frag_mem_limit(struct netns_frags *nf, int i)
 {
-	__percpu_counter_add(&nf->mem, i, frag_percpu_counter_batch);
+	percpu_counter_add_batch(&nf->mem, i, frag_percpu_counter_batch);
 }
 
 static inline unsigned int sum_frag_mem_limit(struct netns_frags *nf)

@@ -207,7 +207,7 @@ static void fprop_reflect_period_percpu(
 		if (val < (nr_cpu_ids * PROP_BATCH))
 			val = percpu_counter_sum(&pl->events);
 
-		__percpu_counter_add(&pl->events,
+		percpu_counter_add_batch(&pl->events,
 			-val + (val >> (period-pl->period)), PROP_BATCH);
 	} else
 		percpu_counter_set(&pl->events, 0);

@@ -219,7 +219,7 @@ static void fprop_reflect_period_percpu(
 void __fprop_inc_percpu(struct fprop_global *p, struct fprop_local_percpu *pl)
 {
 	fprop_reflect_period_percpu(p, pl);
-	__percpu_counter_add(&pl->events, 1, PROP_BATCH);
+	percpu_counter_add_batch(&pl->events, 1, PROP_BATCH);
 	percpu_counter_add(&p->events, 1);
 }
 

@@ -267,6 +267,6 @@ void __fprop_inc_percpu_max(struct fprop
 			return;
 	} else
 		fprop_reflect_period_percpu(p, pl);
-	__percpu_counter_add(&pl->events, 1, PROP_BATCH);
+	percpu_counter_add_batch(&pl->events, 1, PROP_BATCH);
 	percpu_counter_add(&p->events, 1);
 }

@@ -72,7 +72,7 @@ void percpu_counter_set(struct percpu_co
 }
 EXPORT_SYMBOL(percpu_counter_set);
 
-void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch)
+void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch)
 {
 	s64 count;
 

@@ -89,7 +89,7 @@ void __percpu_counter_add(struct percpu_
 	}
 	preempt_enable();
 }
-EXPORT_SYMBOL(__percpu_counter_add);
+EXPORT_SYMBOL(percpu_counter_add_batch);
 
 /*
  * Add up all the per-cpu counts, return the result.  This is a more accurate

@@ -380,8 +380,8 @@ static void inode_switch_wbs_work_fn(str
 		struct page *page = radix_tree_deref_slot_protected(slot,
 							&mapping->tree_lock);
 		if (likely(page) && PageDirty(page)) {
-			__dec_wb_stat(old_wb, WB_RECLAIMABLE);
-			__inc_wb_stat(new_wb, WB_RECLAIMABLE);
+			dec_wb_stat(old_wb, WB_RECLAIMABLE);
+			inc_wb_stat(new_wb, WB_RECLAIMABLE);
 		}
 	}
 

@@ -391,8 +391,8 @@ static void inode_switch_wbs_work_fn(str
 							&mapping->tree_lock);
 		if (likely(page)) {
 			WARN_ON_ONCE(!PageWriteback(page));
-			__dec_wb_stat(old_wb, WB_WRITEBACK);
-			__inc_wb_stat(new_wb, WB_WRITEBACK);
+			dec_wb_stat(old_wb, WB_WRITEBACK);
+			inc_wb_stat(new_wb, WB_WRITEBACK);
 		}
 	}
 

@@ -69,34 +69,14 @@ static inline void __add_wb_stat(struct
 	percpu_counter_add_batch(&wb->stat[item], amount, WB_STAT_BATCH);
 }
 
-static inline void __inc_wb_stat(struct bdi_writeback *wb,
-				 enum wb_stat_item item)
-{
-	__add_wb_stat(wb, item, 1);
-}
-
 static inline void inc_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item)
 {
-	unsigned long flags;
-
-	local_irq_save(flags);
-	__inc_wb_stat(wb, item);
-	local_irq_restore(flags);
-}
-
-static inline void __dec_wb_stat(struct bdi_writeback *wb,
-				 enum wb_stat_item item)
-{
-	__add_wb_stat(wb, item, -1);
+	__add_wb_stat(wb, item, 1);
 }
 
 static inline void dec_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item)
 {
-	unsigned long flags;
-
-	local_irq_save(flags);
-	__dec_wb_stat(wb, item);
-	local_irq_restore(flags);
+	__add_wb_stat(wb, item, -1);
 }
 
 static inline s64 wb_stat(struct bdi_writeback *wb, enum wb_stat_item item)

@@ -72,6 +72,13 @@ void percpu_counter_set(struct percpu_co
 }
 EXPORT_SYMBOL(percpu_counter_set);
 
+/**
+ * This function is both preempt and irq safe. The former is due to explicit
+ * preemption disable. The latter is guaranteed by the fact that the slow path
+ * is explicitly protected by an irq-safe spinlock whereas the fast patch uses
+ * this_cpu_add which is irq-safe by definition. Hence there is no need muck
+ * with irq state before calling this one
+ */
 void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch)
 {
 	s64 count;

@@ -601,7 +601,7 @@ static inline void __wb_writeout_inc(str
 {
 	struct wb_domain *cgdom;
 
-	__inc_wb_stat(wb, WB_WRITTEN);
+	inc_wb_stat(wb, WB_WRITTEN);
 	wb_domain_writeout_inc(&global_wb_domain, &wb->completions,
 			       wb->bdi->max_prop_frac);
 

@@ -2437,8 +2437,8 @@ void account_page_dirtied(struct page *p
 		__inc_node_page_state(page, NR_FILE_DIRTY);
 		__inc_zone_page_state(page, NR_ZONE_WRITE_PENDING);
 		__inc_node_page_state(page, NR_DIRTIED);
-		__inc_wb_stat(wb, WB_RECLAIMABLE);
-		__inc_wb_stat(wb, WB_DIRTIED);
+		inc_wb_stat(wb, WB_RECLAIMABLE);
+		inc_wb_stat(wb, WB_DIRTIED);
 		task_io_account_write(PAGE_SIZE);
 		current->nr_dirtied++;
 		this_cpu_inc(bdp_ratelimits);

@@ -2745,7 +2745,7 @@ int test_clear_page_writeback(struct pag
 			if (bdi_cap_account_writeback(bdi)) {
 				struct bdi_writeback *wb = inode_to_wb(inode);
 
-				__dec_wb_stat(wb, WB_WRITEBACK);
+				dec_wb_stat(wb, WB_WRITEBACK);
 				__wb_writeout_inc(wb);
 			}
 		}

@@ -2791,7 +2791,7 @@ int __test_set_page_writeback(struct pag
 						page_index(page),
 						PAGECACHE_TAG_WRITEBACK);
 			if (bdi_cap_account_writeback(bdi))
-				__inc_wb_stat(inode_to_wb(inode), WB_WRITEBACK);
+				inc_wb_stat(inode_to_wb(inode), WB_WRITEBACK);
 
 			/*
 			 * We can come through here when swapping anonymous

@@ -205,19 +205,17 @@ static unsigned long *alloc_thread_stack
 	void *stack;
 	int i;
 
-	local_irq_disable();
 	for (i = 0; i < NR_CACHED_STACKS; i++) {
-		struct vm_struct *s = this_cpu_read(cached_stacks[i]);
+		struct vm_struct *s;
+
+		s = this_cpu_xchg(cached_stacks[i], NULL);
 
 		if (!s)
 			continue;
-		this_cpu_write(cached_stacks[i], NULL);
 
 		tsk->stack_vm_area = s;
-		local_irq_enable();
 		return s->addr;
 	}
-	local_irq_enable();
 
 	stack = __vmalloc_node_range(THREAD_SIZE, THREAD_SIZE,
 				     VMALLOC_START, VMALLOC_END,

@@ -245,19 +243,15 @@ static inline void free_thread_stack(str
 {
 #ifdef CONFIG_VMAP_STACK
 	if (task_stack_vm_area(tsk)) {
-		unsigned long flags;
 		int i;
 
-		local_irq_save(flags);
 		for (i = 0; i < NR_CACHED_STACKS; i++) {
-			if (this_cpu_read(cached_stacks[i]))
+			if (this_cpu_cmpxchg(cached_stacks[i],
+					NULL, tsk->stack_vm_area) != NULL)
 				continue;
 
-			this_cpu_write(cached_stacks[i], tsk->stack_vm_area);
-			local_irq_restore(flags);
 			return;
 		}
-		local_irq_restore(flags);
 
 		vfree_atomic(tsk->stack);
 		return;

@@ -3043,6 +3043,8 @@ static struct acpi_driver acpi_nfit_driv
 
 static __init int nfit_init(void)
 {
+	int ret;
+
 	BUILD_BUG_ON(sizeof(struct acpi_table_nfit) != 40);
 	BUILD_BUG_ON(sizeof(struct acpi_nfit_system_address) != 56);
 	BUILD_BUG_ON(sizeof(struct acpi_nfit_memory_map) != 48);

@@ -3070,8 +3072,14 @@ static __init int nfit_init(void)
 		return -ENOMEM;
 
 	nfit_mce_register();
+	ret = acpi_bus_register_driver(&acpi_nfit_driver);
+	if (ret) {
+		nfit_mce_unregister();
+		destroy_workqueue(nfit_wq);
+	}
+
+	return ret;
 
-	return acpi_bus_register_driver(&acpi_nfit_driver);
 }
 
 static __exit void nfit_exit(void)

@@ -606,6 +606,8 @@ static int vmbus_close_internal(struct v
 		get_order(channel->ringbuffer_pagecount * PAGE_SIZE));
 
 out:
+	/* re-enable tasklet for use on re-open */
+	tasklet_enable(&channel->callback_event);
 	return ret;
 }
 

@@ -225,6 +225,9 @@ struct global_params {
  * @vid:		Stores VID limits for this CPU
  * @pid:		Stores PID parameters for this CPU
  * @last_sample_time:	Last Sample time
+ * @aperf_mperf_shift:	Number of clock cycles after aperf, merf is incremented
+ *			This shift is a multiplier to mperf delta to
+ *			calculate CPU busy.
  * @prev_aperf:		Last APERF value read from APERF MSR
  * @prev_mperf:		Last MPERF value read from MPERF MSR
  * @prev_tsc:		Last timestamp counter (TSC) value

@@ -261,6 +264,7 @@ struct cpudata {
 
 	u64	last_update;
 	u64	last_sample_time;
+	u64	aperf_mperf_shift;
 	u64	prev_aperf;
 	u64	prev_mperf;
 	u64	prev_tsc;

@@ -323,6 +327,7 @@ struct pstate_funcs {
 	int (*get_min)(void);
 	int (*get_turbo)(void);
 	int (*get_scaling)(void);
+	int (*get_aperf_mperf_shift)(void);
 	u64 (*get_val)(struct cpudata*, int pstate);
 	void (*get_vid)(struct cpudata *);
 	void (*update_util)(struct update_util_data *data, u64 time,

@@ -1485,6 +1490,11 @@ static u64 core_get_val(struct cpudata *
 	return val;
 }
 
+static int knl_get_aperf_mperf_shift(void)
+{
+	return 10;
+}
+
 static int knl_get_turbo_pstate(void)
 {
 	u64 value;

@@ -1543,6 +1553,9 @@ static void intel_pstate_get_cpu_pstates
 	cpu->pstate.max_freq = cpu->pstate.max_pstate * cpu->pstate.scaling;
 	cpu->pstate.turbo_freq = cpu->pstate.turbo_pstate * cpu->pstate.scaling;
 
+	if (pstate_funcs.get_aperf_mperf_shift)
+		cpu->aperf_mperf_shift = pstate_funcs.get_aperf_mperf_shift();
+
 	if (pstate_funcs.get_vid)
 		pstate_funcs.get_vid(cpu);
 

@@ -1619,7 +1632,8 @@ static inline int32_t get_target_pstate_
 	if (cpu->policy == CPUFREQ_POLICY_PERFORMANCE)
 		return cpu->pstate.turbo_pstate;
 
-	busy_frac = div_fp(sample->mperf, sample->tsc);
+	busy_frac = div_fp(sample->mperf << cpu->aperf_mperf_shift,
+			   sample->tsc);
 
 	boost = cpu->iowait_boost;
 	cpu->iowait_boost >>= 1;

@@ -1681,7 +1695,8 @@ static inline int32_t get_target_pstate_
 		sample_ratio = div_fp(pid_params.sample_rate_ns, duration_ns);
 		perf_scaled = mul_fp(perf_scaled, sample_ratio);
 	} else {
-		sample_ratio = div_fp(100 * cpu->sample.mperf, cpu->sample.tsc);
+		sample_ratio = div_fp(100 * (cpu->sample.mperf << cpu->aperf_mperf_shift),
+				      cpu->sample.tsc);
 		if (sample_ratio < int_tofp(1))
 			perf_scaled = 0;
 	}

@@ -1824,6 +1839,7 @@ static const struct pstate_funcs knl_fun
 	.get_max_physical = core_get_max_pstate_physical,
 	.get_min = core_get_min_pstate,
 	.get_turbo = knl_get_turbo_pstate,
+	.get_aperf_mperf_shift = knl_get_aperf_mperf_shift,
 	.get_scaling = core_get_scaling,
 	.get_val = core_get_val,
 	.update_util = intel_pstate_update_util_pid,

@@ -2408,6 +2424,7 @@ static void __init copy_cpu_funcs(struct
 	pstate_funcs.get_val   = funcs->get_val;
 	pstate_funcs.get_vid   = funcs->get_vid;
 	pstate_funcs.update_util = funcs->update_util;
+	pstate_funcs.get_aperf_mperf_shift = funcs->get_aperf_mperf_shift;
 
 	intel_pstate_use_acpi_profile();
 }

@@ -365,11 +365,23 @@ static int spmi_drv_remove(struct device
 	return 0;
 }
 
+static int spmi_drv_uevent(struct device *dev, struct kobj_uevent_env *env)
+{
+	int ret;
+
+	ret = of_device_uevent_modalias(dev, env);
+	if (ret != -ENODEV)
+		return ret;
+
+	return 0;
+}
+
 static struct bus_type spmi_bus_type = {
 	.name		= "spmi",
 	.match		= spmi_device_match,
 	.probe		= spmi_drv_probe,
 	.remove		= spmi_drv_remove,
+	.uevent		= spmi_drv_uevent,
 };
 
 /**

@@ -37,7 +37,14 @@ reiserfs_set_acl(struct inode *inode, st
 	error = journal_begin(&th, inode->i_sb, jcreate_blocks);
 	reiserfs_write_unlock(inode->i_sb);
 	if (error == 0) {
+		if (type == ACL_TYPE_ACCESS && acl) {
+			error = posix_acl_update_mode(inode, &inode->i_mode,
+						      &acl);
+			if (error)
+				goto unlock;
+		}
 		error = __reiserfs_set_acl(&th, inode, type, acl);
+unlock:
 		reiserfs_write_lock(inode->i_sb);
 		error2 = journal_end(&th);
 		reiserfs_write_unlock(inode->i_sb);

@@ -241,11 +248,6 @@ __reiserfs_set_acl(struct reiserfs_trans
 	switch (type) {
 	case ACL_TYPE_ACCESS:
 		name = XATTR_NAME_POSIX_ACL_ACCESS;
-		if (acl) {
-			error = posix_acl_update_mode(inode, &inode->i_mode, &acl);
-			if (error)
-				return error;
-		}
 		break;
 	case ACL_TYPE_DEFAULT:
 		name = XATTR_NAME_POSIX_ACL_DEFAULT;

@@ -21,5 +21,5 @@ struct dax_region *alloc_dax_region(stru
 		int region_id, struct resource *res, unsigned int align,
 		void *addr, unsigned long flags);
 struct dev_dax *devm_create_dev_dax(struct dax_region *dax_region,
-		struct resource *res, int count);
+		int id, struct resource *res, int count);
 #endif /* __DEVICE_DAX_H__ */

@@ -528,7 +528,8 @@ static void dev_dax_release(struct devic
 	struct dax_region *dax_region = dev_dax->region;
 	struct dax_device *dax_dev = dev_dax->dax_dev;
 
-	ida_simple_remove(&dax_region->ida, dev_dax->id);
+	if (dev_dax->id >= 0)
+		ida_simple_remove(&dax_region->ida, dev_dax->id);
 	dax_region_put(dax_region);
 	put_dax(dax_dev);
 	kfree(dev_dax);

@@ -558,7 +559,7 @@ static void unregister_dev_dax(void *dev
 }
 
 struct dev_dax *devm_create_dev_dax(struct dax_region *dax_region,
-		struct resource *res, int count)
+		int id, struct resource *res, int count)
 {
 	struct device *parent = dax_region->dev;
 	struct dax_device *dax_dev;

@@ -586,10 +587,16 @@ struct dev_dax *devm_create_dev_dax(stru
 	if (i < count)
 		goto err_id;
 
-	dev_dax->id = ida_simple_get(&dax_region->ida, 0, 0, GFP_KERNEL);
-	if (dev_dax->id < 0) {
-		rc = dev_dax->id;
-		goto err_id;
+	if (id < 0) {
+		id = ida_simple_get(&dax_region->ida, 0, 0, GFP_KERNEL);
+		dev_dax->id = id;
+		if (id < 0) {
+			rc = id;
+			goto err_id;
+		}
+	} else {
+		/* region provider owns @id lifetime */
+		dev_dax->id = -1;
 	}
 
 	/*

@@ -619,7 +626,7 @@ struct dev_dax *devm_create_dev_dax(stru
 	dev->parent = parent;
 	dev->groups = dax_attribute_groups;
 	dev->release = dev_dax_release;
-	dev_set_name(dev, "dax%d.%d", dax_region->id, dev_dax->id);
+	dev_set_name(dev, "dax%d.%d", dax_region->id, id);
 
 	rc = cdev_device_add(cdev, dev);
 	if (rc) {

@@ -635,7 +642,8 @@ struct dev_dax *devm_create_dev_dax(stru
 	return dev_dax;
 
  err_dax:
-	ida_simple_remove(&dax_region->ida, dev_dax->id);
+	if (dev_dax->id >= 0)
+		ida_simple_remove(&dax_region->ida, dev_dax->id);
  err_id:
 	kfree(dev_dax);
 

@@ -58,13 +58,12 @@ static void dax_pmem_percpu_kill(void *d
 
 static int dax_pmem_probe(struct device *dev)
 {
-	int rc;
 	void *addr;
 	struct resource res;
+	int rc, id, region_id;
 	struct nd_pfn_sb *pfn_sb;
 	struct dev_dax *dev_dax;
 	struct dax_pmem *dax_pmem;
-	struct nd_region *nd_region;
 	struct nd_namespace_io *nsio;
 	struct dax_region *dax_region;
 	struct nd_namespace_common *ndns;

@@ -123,14 +122,17 @@ static int dax_pmem_probe(struct device
 	/* adjust the dax_region resource to the start of data */
 	res.start += le64_to_cpu(pfn_sb->dataoff);
 
-	nd_region = to_nd_region(dev->parent);
-	dax_region = alloc_dax_region(dev, nd_region->id, &res,
+	rc = sscanf(dev_name(&ndns->dev), "namespace%d.%d", &region_id, &id);
+	if (rc != 2)
+		return -EINVAL;
+
+	dax_region = alloc_dax_region(dev, region_id, &res,
 			le32_to_cpu(pfn_sb->align), addr, PFN_DEV|PFN_MAP);
 	if (!dax_region)
 		return -ENOMEM;
 
 	/* TODO: support for subdividing a dax region... */
-	dev_dax = devm_create_dev_dax(dax_region, &res, 1);
+	dev_dax = devm_create_dev_dax(dax_region, id, &res, 1);
 
 	/* child dev_dax instances now own the lifetime of the dax_region */
 	dax_region_put(dax_region);

@@ -237,7 +237,7 @@ static int imx_pd_bind(struct device *de
 
 	/* port@1 is the output port */
 	ret = drm_of_find_panel_or_bridge(np, 1, 0, &imxpd->panel, &imxpd->bridge);
-	if (ret)
+	if (ret && ret != -ENODEV)
 		return ret;
 
 	imxpd->dev = dev;

@@ -1168,8 +1168,6 @@ static struct generic_pm_domain_data *ge
 
 	spin_unlock_irq(&dev->power.lock);
 
-	dev_pm_domain_set(dev, &genpd->domain);
-
 	return gpd_data;
 
  err_free:

@@ -1183,8 +1181,6 @@ static struct generic_pm_domain_data *ge
 static void genpd_free_dev_data(struct device *dev,
 				struct generic_pm_domain_data *gpd_data)
 {
-	dev_pm_domain_set(dev, NULL);
-
 	spin_lock_irq(&dev->power.lock);
 
 	dev->power.subsys_data->domain_data = NULL;

@@ -1221,6 +1217,8 @@ static int genpd_add_device(struct gener
 	if (ret)
 		goto out;
 
+	dev_pm_domain_set(dev, &genpd->domain);
+
 	genpd->device_count++;
 	genpd->max_off_time_changed = true;
 

@@ -1282,6 +1280,8 @@ static int genpd_remove_device(struct ge
 	if (genpd->detach_dev)
 		genpd->detach_dev(genpd, dev);
 
+	dev_pm_domain_set(dev, NULL);
+
 	list_del_init(&pdd->list_node);
 
 	genpd_unlock(genpd);

@@ -7594,6 +7594,7 @@ static int instance_rmdir(const char *na
 	}
 	kfree(tr->topts);
 
+	free_cpumask_var(tr->tracing_cpumask);
 	kfree(tr->name);
 	kfree(tr);
 

@@ -535,13 +535,14 @@ static void intel_fbdev_destroy(struct i
 
 	drm_fb_helper_fini(&ifbdev->helper);
 
-	if (ifbdev->fb) {
+	if (ifbdev->vma) {
 		mutex_lock(&ifbdev->helper.dev->struct_mutex);
 		intel_unpin_fb_vma(ifbdev->vma);
 		mutex_unlock(&ifbdev->helper.dev->struct_mutex);
+	}
 
+	if (ifbdev->fb)
 		drm_framebuffer_remove(&ifbdev->fb->base);
-	}
 
 	kfree(ifbdev);
 }

@@ -765,7 +766,7 @@ void intel_fbdev_set_suspend(struct drm_
 	struct intel_fbdev *ifbdev = dev_priv->fbdev;
 	struct fb_info *info;
 
-	if (!ifbdev || !ifbdev->fb)
+	if (!ifbdev || !ifbdev->vma)
 		return;
 
 	info = ifbdev->helper.fbdev;

@@ -812,7 +813,7 @@ void intel_fbdev_output_poll_changed(str
 {
 	struct intel_fbdev *ifbdev = to_i915(dev)->fbdev;
 
-	if (ifbdev && ifbdev->fb)
+	if (ifbdev && ifbdev->vma)
 		drm_fb_helper_hotplug_event(&ifbdev->helper);
 }
 

@@ -824,7 +825,7 @@ void intel_fbdev_restore_mode(struct drm
 		return;
 
 	intel_fbdev_sync(ifbdev);
-	if (!ifbdev->fb)
+	if (!ifbdev->vma)
 		return;
 
 	if (drm_fb_helper_restore_fbdev_mode_unlocked(&ifbdev->helper) == 0)

@@ -1210,10 +1210,6 @@ static int i915_oa_stream_init(struct i9
 			return ret;
 	}
 
-	ret = alloc_oa_buffer(dev_priv);
-	if (ret)
-		goto err_oa_buf_alloc;
-
 	/* PRM - observability performance counters:
 	 *
 	 *   OACONTROL, performance counter enable, note:

@@ -1229,6 +1225,10 @@ static int i915_oa_stream_init(struct i9
 	intel_runtime_pm_get(dev_priv);
 	intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
 
+	ret = alloc_oa_buffer(dev_priv);
+	if (ret)
+		goto err_oa_buf_alloc;
+
 	ret = dev_priv->perf.oa.ops.enable_metric_set(dev_priv);
 	if (ret)
 		goto err_enable;

@@ -1240,11 +1240,11 @@ static int i915_oa_stream_init(struct i9
 	return 0;
 
 err_enable:
-	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
-	intel_runtime_pm_put(dev_priv);
 	free_oa_buffer(dev_priv);
 
 err_oa_buf_alloc:
+	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
+	intel_runtime_pm_put(dev_priv);
 	if (stream->ctx)
 		oa_put_render_ctx_id(stream);
 

@@ -346,11 +346,25 @@ EXPORT_SYMBOL_GPL(cpu_hotplug_enable);
 
 /* Notifier wrappers for transitioning to state machine */
 
+static void __cpuhp_kick_ap_work(struct cpuhp_cpu_state *st);
+
 static int bringup_wait_for_ap(unsigned int cpu)
 {
 	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
 
+	/* Wait for the CPU to reach CPUHP_AP_ONLINE_IDLE */
 	wait_for_completion(&st->done);
+	BUG_ON(!cpu_online(cpu));
+
+	/* Unpark the stopper thread and the hotplug thread of the target cpu */
+	stop_machine_unpark(cpu);
+	kthread_unpark(st->thread);
+
+	/* Should we go further up ? */
+	if (st->target > CPUHP_AP_ONLINE_IDLE) {
+		__cpuhp_kick_ap_work(st);
+		wait_for_completion(&st->done);
+	}
 	return st->result;
 }
 

@@ -371,9 +385,7 @@ static int bringup_cpu(unsigned int cpu)
 	irq_unlock_sparse();
 	if (ret)
 		return ret;
-	ret = bringup_wait_for_ap(cpu);
-	BUG_ON(!cpu_online(cpu));
-	return ret;
+	return bringup_wait_for_ap(cpu);
 }
 
 /*

@@ -859,31 +871,20 @@ void notify_cpu_starting(unsigned int cp
 }
 
 /*
- * Called from the idle task. We need to set active here, so we can kick off
- * the stopper thread and unpark the smpboot threads. If the target state is
- * beyond CPUHP_AP_ONLINE_IDLE we kick cpuhp thread and let it bring up the
- * cpu further.
+ * Called from the idle task. Wake up the controlling task which brings the
+ * stopper and the hotplug thread of the upcoming CPU up and then delegates
+ * the rest of the online bringup to the hotplug thread.
  */
 void cpuhp_online_idle(enum cpuhp_state state)
 {
 	struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);
-	unsigned int cpu = smp_processor_id();
 
 	/* Happens for the boot cpu */
 	if (state != CPUHP_AP_ONLINE_IDLE)
 		return;
 
 	st->state = CPUHP_AP_ONLINE_IDLE;
-
-	/* Unpark the stopper thread and the hotplug thread of this cpu */
-	stop_machine_unpark(cpu);
-	kthread_unpark(st->thread);
-
-	/* Should we go further up ? */
-	if (st->target > CPUHP_AP_ONLINE_IDLE)
-		__cpuhp_kick_ap_work(st);
-	else
-		complete(&st->done);
+	complete(&st->done);
 }
 
 /* Requires cpu_add_remove_lock to be held */

@@ -354,7 +354,8 @@ static int bringup_wait_for_ap(unsigned
 
 	/* Wait for the CPU to reach CPUHP_AP_ONLINE_IDLE */
 	wait_for_completion(&st->done);
-	BUG_ON(!cpu_online(cpu));
+	if (WARN_ON_ONCE((!cpu_online(cpu))))
+		return -ECANCELED;
 
 	/* Unpark the stopper thread and the hotplug thread of the target cpu */
 	stop_machine_unpark(cpu);