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

Pull scheduler updates from Ingo Molnar:
"The main changes in this cycle were:

- Add the SYSTEM_SCHEDULING bootup state to move various scheduler
debug checks earlier into the bootup. This turns silent and
sporadically deadly bugs into nice, deterministic splats. Fix some
of the splats that triggered. (Thomas Gleixner)

- A round of restructuring and refactoring of the load-balancing and
topology code (Peter Zijlstra)

- Another round of consolidating ~20 of incremental scheduler code
history: this time in terms of wait-queue nomenclature. (I didn't
get much feedback on these renaming patches, and we can still
easily change any names I might have misplaced, so if anyone hates
a new name, please holler and I'll fix it.) (Ingo Molnar)

- sched/numa improvements, fixes and updates (Rik van Riel)

- Another round of x86/tsc scheduler clock code improvements, in hope
of making it more robust (Peter Zijlstra)

- Improve NOHZ behavior (Frederic Weisbecker)

- Deadline scheduler improvements and fixes (Luca Abeni, Daniel
Bristot de Oliveira)

- Simplify and optimize the topology setup code (Lauro Ramos
Venancio)

- Debloat and decouple scheduler code some more (Nicolas Pitre)

- Simplify code by making better use of llist primitives (Byungchul
Park)

- ... plus other fixes and improvements"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (103 commits)
sched/cputime: Refactor the cputime_adjust() code
sched/debug: Expose the number of RT/DL tasks that can migrate
sched/numa: Hide numa_wake_affine() from UP build
sched/fair: Remove effective_load()
sched/numa: Implement NUMA node level wake_affine()
sched/fair: Simplify wake_affine() for the single socket case
sched/numa: Override part of migrate_degrades_locality() when idle balancing
sched/rt: Move RT related code from sched/core.c to sched/rt.c
sched/deadline: Move DL related code from sched/core.c to sched/deadline.c
sched/cpuset: Only offer CONFIG_CPUSETS if SMP is enabled
sched/fair: Spare idle load balancing on nohz_full CPUs
nohz: Move idle balancer registration to the idle path
sched/loadavg: Generalize "_idle" naming to "_nohz"
sched/core: Drop the unused try_get_task_struct() helper function
sched/fair: WARN() and refuse to set buddy when !se->on_rq
sched/debug: Fix SCHED_WARN_ON() to return a value on !CONFIG_SCHED_DEBUG as well
sched/wait: Disambiguate wq_entry->task_list and wq_head->task_list naming
sched/wait: Move bit_wait_table[] and related functionality from sched/core.c to sched/wait_bit.c
sched/wait: Split out the wait_bit*() APIs from <linux/wait.h> into <linux/wait_bit.h>
sched/wait: Re-adjust macro line continuation backslashes in <linux/wait.h>
...

Documentation/DocBook/kernel-hacking.tmpl

···
    certain condition is true.  They must be used carefully to ensure
    there is no race condition.  You declare a
    <type>wait_queue_head_t</type>, and then processes which want to
-   wait for that condition declare a <type>wait_queue_t</type>
+   wait for that condition declare a <type>wait_queue_entry_t</type>
    referring to themselves, and place that in the queue.
   </para>
 

Documentation/filesystems/autofs4.txt

···
         struct autofs_v5_packet {
                 int proto_version;                /* Protocol version */
                 int type;                        /* Type of packet */
-                autofs_wqt_t wait_queue_token;
+                autofs_wqt_t wait_queue_entry_token;
                 __u32 dev;
                 __u64 ino;
                 __u32 uid;
···
 `O_DIRECT`) to _pipe2(2)_ so that a read from the pipe will return at
 most one packet, and any unread portion of a packet will be discarded.
 
-The `wait_queue_token` is a unique number which can identify a
+The `wait_queue_entry_token` is a unique number which can identify a
 particular request to be acknowledged.  When a message is sent over
 the pipe the affected dentry is marked as either "active" or
 "expiring" and other accesses to it block until the message is
 acknowledged using one of the ioctls below and the relevant
-`wait_queue_token`.
+`wait_queue_entry_token`.
 
 Communicating with autofs: root directory ioctls
 ------------------------------------------------
···
 The available ioctl commands are:
 
 - **AUTOFS_IOC_READY**: a notification has been handled.  The argument
-    to the ioctl command is the "wait_queue_token" number
+    to the ioctl command is the "wait_queue_entry_token" number
     corresponding to the notification being acknowledged.
 - **AUTOFS_IOC_FAIL**: similar to above, but indicates failure with
     the error code `ENOENT`.
···
         struct autofs_packet_expire_multi {
                 int proto_version;              /* Protocol version */
                 int type;                       /* Type of packet */
-                autofs_wqt_t wait_queue_token;
+                autofs_wqt_t wait_queue_entry_token;
                 int len;
                 char name[NAME_MAX+1];
         };
 
      is required.  This is filled in with the name of something
      that can be unmounted or removed.  If nothing can be expired,
-     `errno` is set to `EAGAIN`.  Even though a `wait_queue_token`
+     `errno` is set to `EAGAIN`.  Even though a `wait_queue_entry_token`
      is present in the structure, no "wait queue" is established
      and no acknowledgment is needed.
 - **AUTOFS_IOC_EXPIRE_MULTI**:  This is similar to

Documentation/scheduler/sched-deadline.txt

···
  0. WARNING
  1. Overview
  2. Scheduling algorithm
+   2.1 Main algorithm
+   2.2 Bandwidth reclaiming
  3. Scheduling Real-Time Tasks
    3.1 Definitions
    3.2 Schedulability Analysis for Uniprocessor Systems
···
 
 2. Scheduling algorithm
 ==================
+
+2.1 Main algorithm
+------------------
 
  SCHED_DEADLINE uses three parameters, named "runtime", "period", and
  "deadline", to schedule tasks. A SCHED_DEADLINE task should receive
···
 
          scheduling deadline = scheduling deadline + period
          remaining runtime = remaining runtime + runtime
+
+
+2.2 Bandwidth reclaiming
+------------------------
+
+ Bandwidth reclaiming for deadline tasks is based on the GRUB (Greedy
+ Reclamation of Unused Bandwidth) algorithm [15, 16, 17] and it is enabled
+ when flag SCHED_FLAG_RECLAIM is set.
+
+ The following diagram illustrates the state names for tasks handled by GRUB:
+
+                             ------------
+                 (d)        |   Active   |
+              ------------->|            |
+              |             | Contending |
+              |              ------------
+              |                A      |
+          ----------           |      |
+         |          |          |      |
+         | Inactive |          |(b)   | (a)
+         |          |          |      |
+          ----------           |      |
+              A                |      V
+              |              ------------
+              |             |   Active   |
+              --------------|     Non    |
+                 (c)        | Contending |
+                             ------------
+
+ A task can be in one of the following states:
+
+  - ActiveContending: if it is ready for execution (or executing);
+
+  - ActiveNonContending: if it just blocked and has not yet surpassed the 0-lag
+    time;
+
+  - Inactive: if it is blocked and has surpassed the 0-lag time.
+
+ State transitions:
+
+  (a) When a task blocks, it does not become immediately inactive since its
+      bandwidth cannot be immediately reclaimed without breaking the
+      real-time guarantees. It therefore enters a transitional state called
+      ActiveNonContending. The scheduler arms the "inactive timer" to fire at
+      the 0-lag time, when the task's bandwidth can be reclaimed without
+      breaking the real-time guarantees.
+
+      The 0-lag time for a task entering the ActiveNonContending state is
+      computed as
+
+                        (runtime * dl_period)
+             deadline - ---------------------
+                             dl_runtime
+
+      where runtime is the remaining runtime, while dl_runtime and dl_period
+      are the reservation parameters.
+
+  (b) If the task wakes up before the inactive timer fires, the task re-enters
+      the ActiveContending state and the "inactive timer" is canceled.
+      In addition, if the task wakes up on a different runqueue, then
+      the task's utilization must be removed from the previous runqueue's active
+      utilization and must be added to the new runqueue's active utilization.
+      In order to avoid races between a task waking up on a runqueue while the
+       "inactive timer" is running on a different CPU, the "dl_non_contending"
+      flag is used to indicate that a task is not on a runqueue but is active
+      (so, the flag is set when the task blocks and is cleared when the
+      "inactive timer" fires or when the task  wakes up).
+
+  (c) When the "inactive timer" fires, the task enters the Inactive state and
+      its utilization is removed from the runqueue's active utilization.
+
+  (d) When an inactive task wakes up, it enters the ActiveContending state and
+      its utilization is added to the active utilization of the runqueue where
+      it has been enqueued.
+
+ For each runqueue, the algorithm GRUB keeps track of two different bandwidths:
+
+  - Active bandwidth (running_bw): this is the sum of the bandwidths of all
+    tasks in active state (i.e., ActiveContending or ActiveNonContending);
+
+  - Total bandwidth (this_bw): this is the sum of all tasks "belonging" to the
+    runqueue, including the tasks in Inactive state.
+
+
+ The algorithm reclaims the bandwidth of the tasks in Inactive state.
+ It does so by decrementing the runtime of the executing task Ti at a pace equal
+ to
+
+           dq = -max{ Ui, (1 - Uinact) } dt
+
+ where Uinact is the inactive utilization, computed as (this_bq - running_bw),
+ and Ui is the bandwidth of task Ti.
+
+
+ Let's now see a trivial example of two deadline tasks with runtime equal
+ to 4 and period equal to 8 (i.e., bandwidth equal to 0.5):
+
+     A            Task T1
+     |
+     |                               |
+     |                               |
+     |--------                       |----
+     |       |                       V
+     |---|---|---|---|---|---|---|---|--------->t
+     0   1   2   3   4   5   6   7   8
+
+
+     A            Task T2
+     |
+     |                               |
+     |                               |
+     |       ------------------------|
+     |       |                       V
+     |---|---|---|---|---|---|---|---|--------->t
+     0   1   2   3   4   5   6   7   8
+
+
+     A            running_bw
+     |
+   1 -----------------               ------
+     |               |               |
+  0.5-               -----------------
+     |                               |
+     |---|---|---|---|---|---|---|---|--------->t
+     0   1   2   3   4   5   6   7   8
+
+
+  - Time t = 0:
+
+    Both tasks are ready for execution and therefore in ActiveContending state.
+    Suppose Task T1 is the first task to start execution.
+    Since there are no inactive tasks, its runtime is decreased as dq = -1 dt.
+
+  - Time t = 2:
+
+    Suppose that task T1 blocks
+    Task T1 therefore enters the ActiveNonContending state. Since its remaining
+    runtime is equal to 2, its 0-lag time is equal to t = 4.
+    Task T2 start execution, with runtime still decreased as dq = -1 dt since
+    there are no inactive tasks.
+
+  - Time t = 4:
+
+    This is the 0-lag time for Task T1. Since it didn't woken up in the
+    meantime, it enters the Inactive state. Its bandwidth is removed from
+    running_bw.
+    Task T2 continues its execution. However, its runtime is now decreased as
+    dq = - 0.5 dt because Uinact = 0.5.
+    Task T2 therefore reclaims the bandwidth unused by Task T1.
+
+  - Time t = 8:
+
+    Task T1 wakes up. It enters the ActiveContending state again, and the
+    running_bw is incremented.
 
 
 3. Scheduling Real-Time Tasks
···
   14 - J. Erickson, U. Devi and S. Baruah. Improved tardiness bounds for
        Global EDF. Proceedings of the 22nd Euromicro Conference on
        Real-Time Systems, 2010.
+  15 - G. Lipari, S. Baruah, Greedy reclamation of unused bandwidth in
+       constant-bandwidth servers, 12th IEEE Euromicro Conference on Real-Time
+       Systems, 2000.
+  16 - L. Abeni, J. Lelli, C. Scordino, L. Palopoli, Greedy CPU reclaiming for
+       SCHED DEADLINE. In Proceedings of the Real-Time Linux Workshop (RTLWS),
+       Dusseldorf, Germany, 2014.
+  17 - L. Abeni, G. Lipari, A. Parri, Y. Sun, Multicore CPU reclaiming: parallel
+       or sequential?. In Proceedings of the 31st Annual ACM Symposium on Applied
+       Computing, 2016.
 
 
 4. Bandwidth management

Documentation/trace/ftrace.txt

···
   <idle>-0       3dN.2   14us : sched_avg_update <-__cpu_load_update
   <idle>-0       3dN.2   14us : _raw_spin_unlock <-cpu_load_update_nohz
   <idle>-0       3dN.2   14us : sub_preempt_count <-_raw_spin_unlock
-  <idle>-0       3dN.1   15us : calc_load_exit_idle <-tick_nohz_idle_exit
+  <idle>-0       3dN.1   15us : calc_load_nohz_stop <-tick_nohz_idle_exit
   <idle>-0       3dN.1   15us : touch_softlockup_watchdog <-tick_nohz_idle_exit
   <idle>-0       3dN.1   15us : hrtimer_cancel <-tick_nohz_idle_exit
   <idle>-0       3dN.1   15us : hrtimer_try_to_cancel <-hrtimer_cancel

arch/arm/kernel/smp.c

···
  */
 static void ipi_cpu_stop(unsigned int cpu)
 {
-	if (system_state == SYSTEM_BOOTING ||
-	    system_state == SYSTEM_RUNNING) {
+	if (system_state <= SYSTEM_RUNNING) {
 		raw_spin_lock(&stop_lock);
 		pr_crit("CPU%u: stopping\n", cpu);
 		dump_stack();

arch/arm64/kernel/smp.c

···
 		cpumask_copy(&mask, cpu_online_mask);
 		cpumask_clear_cpu(smp_processor_id(), &mask);
 
-		if (system_state == SYSTEM_BOOTING ||
-		    system_state == SYSTEM_RUNNING)
+		if (system_state <= SYSTEM_RUNNING)
 			pr_crit("SMP: stopping secondary CPUs\n");
 		smp_cross_call(&mask, IPI_CPU_STOP);
 	}

arch/metag/kernel/smp.c

···
 {
 	unsigned int cpu = smp_processor_id();
 
-	if (system_state == SYSTEM_BOOTING ||
-	    system_state == SYSTEM_RUNNING) {
+	if (system_state <= SYSTEM_RUNNING) {
 		spin_lock(&stop_lock);
 		pr_crit("CPU%u: stopping\n", cpu);
 		dump_stack();

arch/powerpc/kernel/smp.c

···
 	/* Special case - we inhibit secondary thread startup
 	 * during boot if the user requests it.
 	 */
-	if (system_state == SYSTEM_BOOTING && cpu_has_feature(CPU_FTR_SMT)) {
+	if (system_state < SYSTEM_RUNNING && cpu_has_feature(CPU_FTR_SMT)) {
 		if (!smt_enabled_at_boot && cpu_thread_in_core(nr) != 0)
 			return 0;
 		if (smt_enabled_at_boot

arch/x86/events/core.c

···
 void arch_perf_update_userpage(struct perf_event *event,
 			       struct perf_event_mmap_page *userpg, u64 now)
 {
-	struct cyc2ns_data *data;
+	struct cyc2ns_data data;
 	u64 offset;
 
 	userpg->cap_user_time = 0;
···
 	if (!using_native_sched_clock() || !sched_clock_stable())
 		return;
 
-	data = cyc2ns_read_begin();
+	cyc2ns_read_begin(&data);
 
-	offset = data->cyc2ns_offset + __sched_clock_offset;
+	offset = data.cyc2ns_offset + __sched_clock_offset;
 
 	/*
 	 * Internal timekeeping for enabled/running/stopped times
 	 * is always in the local_clock domain.
 	 */
 	userpg->cap_user_time = 1;
-	userpg->time_mult = data->cyc2ns_mul;
-	userpg->time_shift = data->cyc2ns_shift;
+	userpg->time_mult = data.cyc2ns_mul;
+	userpg->time_shift = data.cyc2ns_shift;
 	userpg->time_offset = offset - now;
 
 	/*
···
 		userpg->time_zero = offset;
 	}
 
-	cyc2ns_read_end(data);
+	cyc2ns_read_end();
 }
 
 void

arch/x86/include/asm/timer.h

···
 	u32 cyc2ns_mul;
 	u32 cyc2ns_shift;
 	u64 cyc2ns_offset;
-	u32 __count;
-	/* u32 hole */
-}; /* 24 bytes -- do not grow */
+}; /* 16 bytes */
 
-extern struct cyc2ns_data *cyc2ns_read_begin(void);
-extern void cyc2ns_read_end(struct cyc2ns_data *);
+extern void cyc2ns_read_begin(struct cyc2ns_data *);
+extern void cyc2ns_read_end(void);
 
 #endif /* _ASM_X86_TIMER_H */

arch/x86/kernel/smpboot.c

···
 	if (cpu == 1)
 		printk(KERN_INFO "x86: Booting SMP configuration:\n");
 
-	if (system_state == SYSTEM_BOOTING) {
+	if (system_state < SYSTEM_RUNNING) {
 		if (node != current_node) {
 			if (current_node > (-1))
 				pr_cont("\n");

arch/x86/kernel/tsc.c

···
 static u64 art_to_tsc_offset;
 struct clocksource *art_related_clocksource;
 
-/*
- * Use a ring-buffer like data structure, where a writer advances the head by
- * writing a new data entry and a reader advances the tail when it observes a
- * new entry.
- *
- * Writers are made to wait on readers until there's space to write a new
- * entry.
- *
- * This means that we can always use an {offset, mul} pair to compute a ns
- * value that is 'roughly' in the right direction, even if we're writing a new
- * {offset, mul} pair during the clock read.
- *
- * The down-side is that we can no longer guarantee strict monotonicity anymore
- * (assuming the TSC was that to begin with), because while we compute the
- * intersection point of the two clock slopes and make sure the time is
- * continuous at the point of switching; we can no longer guarantee a reader is
- * strictly before or after the switch point.
- *
- * It does mean a reader no longer needs to disable IRQs in order to avoid
- * CPU-Freq updates messing with his times, and similarly an NMI reader will
- * no longer run the risk of hitting half-written state.
- */
-
 struct cyc2ns {
-	struct cyc2ns_data data[2];	/*  0 + 2*24 = 48 */
-	struct cyc2ns_data *head;	/* 48 + 8    = 56 */
-	struct cyc2ns_data *tail;	/* 56 + 8    = 64 */
-}; /* exactly fits one cacheline */
+	struct cyc2ns_data data[2];	/*  0 + 2*16 = 32 */
+	seqcount_t	   seq;		/* 32 + 4    = 36 */
+
+}; /* fits one cacheline */
 
 static DEFINE_PER_CPU_ALIGNED(struct cyc2ns, cyc2ns);
 
-struct cyc2ns_data *cyc2ns_read_begin(void)
+void cyc2ns_read_begin(struct cyc2ns_data *data)
 {
-	struct cyc2ns_data *head;
+	int seq, idx;
 
-	preempt_disable();
+	preempt_disable_notrace();
 
-	head = this_cpu_read(cyc2ns.head);
-	/*
-	 * Ensure we observe the entry when we observe the pointer to it.
-	 * matches the wmb from cyc2ns_write_end().
-	 */
-	smp_read_barrier_depends();
-	head->__count++;
-	barrier();
+	do {
+		seq = this_cpu_read(cyc2ns.seq.sequence);
+		idx = seq & 1;
 
-	return head;
+		data->cyc2ns_offset = this_cpu_read(cyc2ns.data[idx].cyc2ns_offset);
+		data->cyc2ns_mul    = this_cpu_read(cyc2ns.data[idx].cyc2ns_mul);
+		data->cyc2ns_shift  = this_cpu_read(cyc2ns.data[idx].cyc2ns_shift);
+
+	} while (unlikely(seq != this_cpu_read(cyc2ns.seq.sequence)));
 }
 
-void cyc2ns_read_end(struct cyc2ns_data *head)
+void cyc2ns_read_end(void)
 {
-	barrier();
-	/*
-	 * If we're the outer most nested read; update the tail pointer
-	 * when we're done. This notifies possible pending writers
-	 * that we've observed the head pointer and that the other
-	 * entry is now free.
-	 */
-	if (!--head->__count) {
-		/*
-		 * x86-TSO does not reorder writes with older reads;
-		 * therefore once this write becomes visible to another
-		 * cpu, we must be finished reading the cyc2ns_data.
-		 *
-		 * matches with cyc2ns_write_begin().
-		 */
-		this_cpu_write(cyc2ns.tail, head);
-	}
-	preempt_enable();
-}
-
-/*
- * Begin writing a new @data entry for @cpu.
- *
- * Assumes some sort of write side lock; currently 'provided' by the assumption
- * that cpufreq will call its notifiers sequentially.
- */
-static struct cyc2ns_data *cyc2ns_write_begin(int cpu)
-{
-	struct cyc2ns *c2n = &per_cpu(cyc2ns, cpu);
-	struct cyc2ns_data *data = c2n->data;
-
-	if (data == c2n->head)
-		data++;
-
-	/* XXX send an IPI to @cpu in order to guarantee a read? */
-
-	/*
-	 * When we observe the tail write from cyc2ns_read_end(),
-	 * the cpu must be done with that entry and its safe
-	 * to start writing to it.
-	 */
-	while (c2n->tail == data)
-		cpu_relax();
-
-	return data;
-}
-
-static void cyc2ns_write_end(int cpu, struct cyc2ns_data *data)
-{
-	struct cyc2ns *c2n = &per_cpu(cyc2ns, cpu);
-
-	/*
-	 * Ensure the @data writes are visible before we publish the
-	 * entry. Matches the data-depencency in cyc2ns_read_begin().
-	 */
-	smp_wmb();
-
-	ACCESS_ONCE(c2n->head) = data;
+	preempt_enable_notrace();
 }
 
 /*
···
 	data->cyc2ns_mul = 0;
 	data->cyc2ns_shift = 0;
 	data->cyc2ns_offset = 0;
-	data->__count = 0;
 }
 
 static void cyc2ns_init(int cpu)
···
 	cyc2ns_data_init(&c2n->data[0]);
 	cyc2ns_data_init(&c2n->data[1]);
 
-	c2n->head = c2n->data;
-	c2n->tail = c2n->data;
+	seqcount_init(&c2n->seq);
 }
 
 static inline unsigned long long cycles_2_ns(unsigned long long cyc)
 {
-	struct cyc2ns_data *data, *tail;
+	struct cyc2ns_data data;
 	unsigned long long ns;
 
-	/*
-	 * See cyc2ns_read_*() for details; replicated in order to avoid
-	 * an extra few instructions that came with the abstraction.
-	 * Notable, it allows us to only do the __count and tail update
-	 * dance when its actually needed.
-	 */
+	cyc2ns_read_begin(&data);
 
-	preempt_disable_notrace();
-	data = this_cpu_read(cyc2ns.head);
-	tail = this_cpu_read(cyc2ns.tail);
+	ns = data.cyc2ns_offset;
+	ns += mul_u64_u32_shr(cyc, data.cyc2ns_mul, data.cyc2ns_shift);
 
-	if (likely(data == tail)) {
-		ns = data->cyc2ns_offset;
-		ns += mul_u64_u32_shr(cyc, data->cyc2ns_mul, data->cyc2ns_shift);
-	} else {
-		data->__count++;
-
-		barrier();
-
-		ns = data->cyc2ns_offset;
-		ns += mul_u64_u32_shr(cyc, data->cyc2ns_mul, data->cyc2ns_shift);
-
-		barrier();
-
-		if (!--data->__count)
-			this_cpu_write(cyc2ns.tail, data);
-	}
-	preempt_enable_notrace();
+	cyc2ns_read_end();
 
 	return ns;
 }
 
-static void set_cyc2ns_scale(unsigned long khz, int cpu)
+static void set_cyc2ns_scale(unsigned long khz, int cpu, unsigned long long tsc_now)
 {
-	unsigned long long tsc_now, ns_now;
-	struct cyc2ns_data *data;
+	unsigned long long ns_now;
+	struct cyc2ns_data data;
+	struct cyc2ns *c2n;
 	unsigned long flags;
 
 	local_irq_save(flags);
···
 	if (!khz)
 		goto done;
 
-	data = cyc2ns_write_begin(cpu);
-
-	tsc_now = rdtsc();
 	ns_now = cycles_2_ns(tsc_now);
 
 	/*
···
 	 * time function is continuous; see the comment near struct
 	 * cyc2ns_data.
 	 */
-	clocks_calc_mult_shift(&data->cyc2ns_mul, &data->cyc2ns_shift, khz,
+	clocks_calc_mult_shift(&data.cyc2ns_mul, &data.cyc2ns_shift, khz,
 			       NSEC_PER_MSEC, 0);
 
 	/*
···
 	 * conversion algorithm shifting a 32-bit value (now specifies a 64-bit
 	 * value) - refer perf_event_mmap_page documentation in perf_event.h.
 	 */
-	if (data->cyc2ns_shift == 32) {
-		data->cyc2ns_shift = 31;
-		data->cyc2ns_mul >>= 1;
+	if (data.cyc2ns_shift == 32) {
+		data.cyc2ns_shift = 31;
+		data.cyc2ns_mul >>= 1;
 	}
 
-	data->cyc2ns_offset = ns_now -
-		mul_u64_u32_shr(tsc_now, data->cyc2ns_mul, data->cyc2ns_shift);
+	data.cyc2ns_offset = ns_now -
+		mul_u64_u32_shr(tsc_now, data.cyc2ns_mul, data.cyc2ns_shift);
 
-	cyc2ns_write_end(cpu, data);
+	c2n = per_cpu_ptr(&cyc2ns, cpu);
+
+	raw_write_seqcount_latch(&c2n->seq);
+	c2n->data[0] = data;
+	raw_write_seqcount_latch(&c2n->seq);
+	c2n->data[1] = data;
 
 done:
-	sched_clock_idle_wakeup_event(0);
+	sched_clock_idle_wakeup_event();
 	local_irq_restore(flags);
 }
+
 /*
  * Scheduler clock - returns current time in nanosec units.
  */
···
 		tsc_clocksource_reliable = 1;
 	if (!strncmp(str, "noirqtime", 9))
 		no_sched_irq_time = 1;
+	if (!strcmp(str, "unstable"))
+		mark_tsc_unstable("boot parameter");
 	return 1;
 }
 
···
 }
 
 #ifdef CONFIG_CPU_FREQ
-
 /* Frequency scaling support. Adjust the TSC based timer when the cpu frequency
  * changes.
  *
···
 		if (!(freq->flags & CPUFREQ_CONST_LOOPS))
 			mark_tsc_unstable("cpufreq changes");
 
-		set_cyc2ns_scale(tsc_khz, freq->cpu);
+		set_cyc2ns_scale(tsc_khz, freq->cpu, rdtsc());
 	}
 
 	return 0;
···
 	pr_info("Marking TSC unstable due to clocksource watchdog\n");
 }
 
+static void tsc_cs_tick_stable(struct clocksource *cs)
+{
+	if (tsc_unstable)
+		return;
+
+	if (using_native_sched_clock())
+		sched_clock_tick_stable();
+}
+
 /*
  * .mask MUST be CLOCKSOURCE_MASK(64). See comment above read_tsc()
  */
···
 	.archdata               = { .vclock_mode = VCLOCK_TSC },
 	.resume			= tsc_resume,
 	.mark_unstable		= tsc_cs_mark_unstable,
+	.tick_stable		= tsc_cs_tick_stable,
 };
 
 void mark_tsc_unstable(char *reason)
···
 	static int hpet;
 	u64 tsc_stop, ref_stop, delta;
 	unsigned long freq;
+	int cpu;
 
 	/* Don't bother refining TSC on unstable systems */
 	if (check_tsc_unstable())
···
 	/* Inform the TSC deadline clockevent devices about the recalibration */
 	lapic_update_tsc_freq();
 
+	/* Update the sched_clock() rate to match the clocksource one */
+	for_each_possible_cpu(cpu)
+		set_cyc2ns_scale(tsc_khz, cpu, tsc_stop);
+
 out:
 	if (boot_cpu_has(X86_FEATURE_ART))
 		art_related_clocksource = &clocksource_tsc;
···
 
 void __init tsc_init(void)
 {
-	u64 lpj;
+	u64 lpj, cyc;
 	int cpu;
 
 	if (!boot_cpu_has(X86_FEATURE_TSC)) {
···
 	 * speed as the bootup CPU. (cpufreq notifiers will fix this
 	 * up if their speed diverges)
 	 */
+	cyc = rdtsc();
 	for_each_possible_cpu(cpu) {
 		cyc2ns_init(cpu);
-		set_cyc2ns_scale(tsc_khz, cpu);
+		set_cyc2ns_scale(tsc_khz, cpu, cyc);
 	}
 
 	if (tsc_disabled > 0)

arch/x86/platform/uv/tlb_uv.c

···
  */
 static inline unsigned long long cycles_2_ns(unsigned long long cyc)
 {
-	struct cyc2ns_data *data = cyc2ns_read_begin();
+	struct cyc2ns_data data;
 	unsigned long long ns;
 
-	ns = mul_u64_u32_shr(cyc, data->cyc2ns_mul, data->cyc2ns_shift);
+	cyc2ns_read_begin(&data);
+	ns = mul_u64_u32_shr(cyc, data.cyc2ns_mul, data.cyc2ns_shift);
+	cyc2ns_read_end();
 
-	cyc2ns_read_end(data);
 	return ns;
 }
 
···
  */
 static inline unsigned long long ns_2_cycles(unsigned long long ns)
 {
-	struct cyc2ns_data *data = cyc2ns_read_begin();
+	struct cyc2ns_data data;
 	unsigned long long cyc;
 
-	cyc = (ns << data->cyc2ns_shift) / data->cyc2ns_mul;
+	cyc2ns_read_begin(&data);
+	cyc = (ns << data.cyc2ns_shift) / data.cyc2ns_mul;
+	cyc2ns_read_end();
 
-	cyc2ns_read_end(data);
 	return cyc;
 }
 

block/blk-mq.c

···
 	return first != NULL;
 }
 
-static int blk_mq_dispatch_wake(wait_queue_t *wait, unsigned mode, int flags,
+static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode, int flags,
 				void *key)
 {
 	struct blk_mq_hw_ctx *hctx;
 
 	hctx = container_of(wait, struct blk_mq_hw_ctx, dispatch_wait);
 
-	list_del(&wait->task_list);
+	list_del(&wait->entry);
 	clear_bit_unlock(BLK_MQ_S_TAG_WAITING, &hctx->state);
 	blk_mq_run_hw_queue(hctx, true);
 	return 1;

block/blk-wbt.c

···
 }
 
 static inline bool may_queue(struct rq_wb *rwb, struct rq_wait *rqw,
-			     wait_queue_t *wait, unsigned long rw)
+			     wait_queue_entry_t *wait, unsigned long rw)
 {
 	/*
 	 * inc it here even if disabled, since we'll dec it at completion.
···
 	 * in line to be woken up, wait for our turn.
 	 */
 	if (waitqueue_active(&rqw->wait) &&
-	    rqw->wait.task_list.next != &wait->task_list)
+	    rqw->wait.head.next != &wait->entry)
 		return false;
 
 	return atomic_inc_below(&rqw->inflight, get_limit(rwb, rw));

block/kyber-iosched.c

···
 	struct list_head rqs[KYBER_NUM_DOMAINS];
 	unsigned int cur_domain;
 	unsigned int batching;
-	wait_queue_t domain_wait[KYBER_NUM_DOMAINS];
+	wait_queue_entry_t domain_wait[KYBER_NUM_DOMAINS];
 	atomic_t wait_index[KYBER_NUM_DOMAINS];
 };
 
···
 
 	for (i = 0; i < KYBER_NUM_DOMAINS; i++) {
 		INIT_LIST_HEAD(&khd->rqs[i]);
-		INIT_LIST_HEAD(&khd->domain_wait[i].task_list);
+		INIT_LIST_HEAD(&khd->domain_wait[i].entry);
 		atomic_set(&khd->wait_index[i], 0);
 	}
 
···
 	}
 }
 
-static int kyber_domain_wake(wait_queue_t *wait, unsigned mode, int flags,
+static int kyber_domain_wake(wait_queue_entry_t *wait, unsigned mode, int flags,
 			     void *key)
 {
 	struct blk_mq_hw_ctx *hctx = READ_ONCE(wait->private);
 
-	list_del_init(&wait->task_list);
+	list_del_init(&wait->entry);
 	blk_mq_run_hw_queue(hctx, true);
 	return 1;
 }
···
 {
 	unsigned int sched_domain = khd->cur_domain;
 	struct sbitmap_queue *domain_tokens = &kqd->domain_tokens[sched_domain];
-	wait_queue_t *wait = &khd->domain_wait[sched_domain];
+	wait_queue_entry_t *wait = &khd->domain_wait[sched_domain];
 	struct sbq_wait_state *ws;
 	int nr;
 
···
 	 * run when one becomes available. Note that this is serialized on
 	 * khd->lock, but we still need to be careful about the waker.
 	 */
-	if (list_empty_careful(&wait->task_list)) {
+	if (list_empty_careful(&wait->entry)) {
 		init_waitqueue_func_entry(wait, kyber_domain_wake);
 		wait->private = hctx;
 		ws = sbq_wait_ptr(domain_tokens,
···
 {									\
 	struct blk_mq_hw_ctx *hctx = data;				\
 	struct kyber_hctx_data *khd = hctx->sched_data;			\
-	wait_queue_t *wait = &khd->domain_wait[domain];			\
+	wait_queue_entry_t *wait = &khd->domain_wait[domain];		\
 									\
-	seq_printf(m, "%d\n", !list_empty_careful(&wait->task_list));	\
+	seq_printf(m, "%d\n", !list_empty_careful(&wait->entry));	\
 	return 0;							\
 }
 KYBER_DEBUGFS_DOMAIN_ATTRS(KYBER_READ, read)

drivers/acpi/pci_root.c

···
 	struct acpi_pci_root *root;
 	acpi_handle handle = device->handle;
 	int no_aspm = 0;
-	bool hotadd = system_state != SYSTEM_BOOTING;
+	bool hotadd = system_state == SYSTEM_RUNNING;
 
 	root = kzalloc(sizeof(struct acpi_pci_root), GFP_KERNEL);
 	if (!root)

drivers/base/node.c

···
 	if (!pfn_valid_within(pfn))
 		return -1;
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
-	if (system_state == SYSTEM_BOOTING)
+	if (system_state < SYSTEM_RUNNING)
 		return early_pfn_to_nid(pfn);
 #endif
 	page = pfn_to_page(pfn);

drivers/bluetooth/btmrvl_main.c

···
 	struct btmrvl_thread *thread = data;
 	struct btmrvl_private *priv = thread->priv;
 	struct btmrvl_adapter *adapter = priv->adapter;
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 	struct sk_buff *skb;
 	ulong flags;
 

drivers/char/ipmi/ipmi_watchdog.c

···
 			 loff_t      *ppos)
 {
 	int          rv = 0;
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 
 	if (count <= 0)
 		return 0;

drivers/cpufreq/pasemi-cpufreq.c

···
 	 * We don't support CPU hotplug. Don't unmap after the system
 	 * has already made it to a running state.
 	 */
-	if (system_state != SYSTEM_BOOTING)
+	if (system_state >= SYSTEM_RUNNING)
 		return 0;
 
 	if (sdcasr_mapbase)

drivers/cpuidle/cpuidle.c

···
 	entered_state = target_state->enter(dev, drv, index);
 	start_critical_timings();
 
+	sched_clock_idle_wakeup_event();
 	time_end = ns_to_ktime(local_clock());
 	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu);
 

drivers/gpu/drm/i915/i915_gem_request.h

···
 	 * It is used by the driver to then queue the request for execution.
 	 */
 	struct i915_sw_fence submit;
-	wait_queue_t submitq;
+	wait_queue_entry_t submitq;
 	wait_queue_head_t execute;
 
 	/* A list of everyone we wait upon, and everyone who waits upon us.

drivers/gpu/drm/i915/i915_sw_fence.c

···
 					struct list_head *continuation)
 {
 	wait_queue_head_t *x = &fence->wait;
-	wait_queue_t *pos, *next;
+	wait_queue_entry_t *pos, *next;
 	unsigned long flags;
 
 	debug_fence_deactivate(fence);
···
 
 	/*
 	 * To prevent unbounded recursion as we traverse the graph of
-	 * i915_sw_fences, we move the task_list from this, the next ready
-	 * fence, to the tail of the original fence's task_list
+	 * i915_sw_fences, we move the entry list from this, the next ready
+	 * fence, to the tail of the original fence's entry list
 	 * (and so added to the list to be woken).
 	 */
 
 	spin_lock_irqsave_nested(&x->lock, flags, 1 + !!continuation);
 	if (continuation) {
-		list_for_each_entry_safe(pos, next, &x->task_list, task_list) {
+		list_for_each_entry_safe(pos, next, &x->head, entry) {
 			if (pos->func == autoremove_wake_function)
 				pos->func(pos, TASK_NORMAL, 0, continuation);
 			else
-				list_move_tail(&pos->task_list, continuation);
+				list_move_tail(&pos->entry, continuation);
 		}
 	} else {
 		LIST_HEAD(extra);
 
 		do {
-			list_for_each_entry_safe(pos, next,
-						 &x->task_list, task_list)
+			list_for_each_entry_safe(pos, next, &x->head, entry)
 				pos->func(pos, TASK_NORMAL, 0, &extra);
 
 			if (list_empty(&extra))
 				break;
 
-			list_splice_tail_init(&extra, &x->task_list);
+			list_splice_tail_init(&extra, &x->head);
 		} while (1);
 	}
 	spin_unlock_irqrestore(&x->lock, flags);
···
 	__i915_sw_fence_commit(fence);
 }
 
-static int i915_sw_fence_wake(wait_queue_t *wq, unsigned mode, int flags, void *key)
+static int i915_sw_fence_wake(wait_queue_entry_t *wq, unsigned mode, int flags, void *key)
 {
-	list_del(&wq->task_list);
+	list_del(&wq->entry);
 	__i915_sw_fence_complete(wq->private, key);
 	i915_sw_fence_put(wq->private);
 	if (wq->flags & I915_SW_FENCE_FLAG_ALLOC)
···
 static bool __i915_sw_fence_check_if_after(struct i915_sw_fence *fence,
 				    const struct i915_sw_fence * const signaler)
 {
-	wait_queue_t *wq;
+	wait_queue_entry_t *wq;
 
 	if (__test_and_set_bit(I915_SW_FENCE_CHECKED_BIT, &fence->flags))
 		return false;
···
 	if (fence == signaler)
 		return true;
 
-	list_for_each_entry(wq, &fence->wait.task_list, task_list) {
+	list_for_each_entry(wq, &fence->wait.head, entry) {
 		if (wq->func != i915_sw_fence_wake)
 			continue;
 
···
 
 static void __i915_sw_fence_clear_checked_bit(struct i915_sw_fence *fence)
 {
-	wait_queue_t *wq;
+	wait_queue_entry_t *wq;
 
 	if (!__test_and_clear_bit(I915_SW_FENCE_CHECKED_BIT, &fence->flags))
 		return;
 
-	list_for_each_entry(wq, &fence->wait.task_list, task_list) {
+	list_for_each_entry(wq, &fence->wait.head, entry) {
 		if (wq->func != i915_sw_fence_wake)
 			continue;
 
···
 
 static int __i915_sw_fence_await_sw_fence(struct i915_sw_fence *fence,
 					  struct i915_sw_fence *signaler,
-					  wait_queue_t *wq, gfp_t gfp)
+					  wait_queue_entry_t *wq, gfp_t gfp)
 {
 	unsigned long flags;
 	int pending;
···
 		pending |= I915_SW_FENCE_FLAG_ALLOC;
 	}
 
-	INIT_LIST_HEAD(&wq->task_list);
+	INIT_LIST_HEAD(&wq->entry);
 	wq->flags = pending;
 	wq->func = i915_sw_fence_wake;
 	wq->private = i915_sw_fence_get(fence);
···
 
 	spin_lock_irqsave(&signaler->wait.lock, flags);
 	if (likely(!i915_sw_fence_done(signaler))) {
-		__add_wait_queue_tail(&signaler->wait, wq);
+		__add_wait_queue_entry_tail(&signaler->wait, wq);
 		pending = 1;
 	} else {
 		i915_sw_fence_wake(wq, 0, 0, NULL);
···
 
 int i915_sw_fence_await_sw_fence(struct i915_sw_fence *fence,
 				 struct i915_sw_fence *signaler,
-				 wait_queue_t *wq)
+				 wait_queue_entry_t *wq)
 {
 	return __i915_sw_fence_await_sw_fence(fence, signaler, wq, 0);
 }

drivers/gpu/drm/i915/i915_sw_fence.h

···
 
 int i915_sw_fence_await_sw_fence(struct i915_sw_fence *fence,
 				 struct i915_sw_fence *after,
-				 wait_queue_t *wq);
+				 wait_queue_entry_t *wq);
 int i915_sw_fence_await_sw_fence_gfp(struct i915_sw_fence *fence,
 				     struct i915_sw_fence *after,
 				     gfp_t gfp);

drivers/gpu/drm/radeon/radeon.h

···
 	unsigned		ring;
 	bool			is_vm_update;
 
-	wait_queue_t		fence_wake;
+	wait_queue_entry_t		fence_wake;
 };
 
 int radeon_fence_driver_start_ring(struct radeon_device *rdev, int ring);

drivers/gpu/drm/radeon/radeon_fence.c

···
  * for the fence locking itself, so unlocked variants are used for
  * fence_signal, and remove_wait_queue.
  */
-static int radeon_fence_check_signaled(wait_queue_t *wait, unsigned mode, int flags, void *key)
+static int radeon_fence_check_signaled(wait_queue_entry_t *wait, unsigned mode, int flags, void *key)
 {
 	struct radeon_fence *fence;
 	u64 seq;

drivers/gpu/vga/vgaarb.c

···
 {
 	struct vga_device *vgadev, *conflict;
 	unsigned long flags;
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 	int rc = 0;
 
 	vga_check_first_use();

drivers/infiniband/hw/i40iw/i40iw_main.c

···
 bool i40iw_vf_clear_to_send(struct i40iw_sc_dev *dev)
 {
 	struct i40iw_device *iwdev;
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 
 	iwdev = dev->back_dev;
 

drivers/iommu/intel-iommu.c

···
 	struct acpi_dmar_atsr *atsr;
 	struct dmar_atsr_unit *atsru;
 
-	if (system_state != SYSTEM_BOOTING && !intel_iommu_enabled)
+	if (system_state >= SYSTEM_RUNNING && !intel_iommu_enabled)
 		return 0;
 
 	atsr = container_of(hdr, struct acpi_dmar_atsr, header);
···
 	struct acpi_dmar_atsr *atsr;
 	struct acpi_dmar_reserved_memory *rmrr;
 
-	if (!intel_iommu_enabled && system_state != SYSTEM_BOOTING)
+	if (!intel_iommu_enabled && system_state >= SYSTEM_RUNNING)
 		return 0;
 
 	list_for_each_entry(rmrru, &dmar_rmrr_units, list) {

drivers/iommu/of_iommu.c

···
 	 * it never will be. We don't want to defer indefinitely, nor attempt
 	 * to dereference __iommu_of_table after it's been freed.
 	 */
-	if (system_state > SYSTEM_BOOTING)
+	if (system_state >= SYSTEM_RUNNING)
 		return false;
 
 	return of_match_node(&__iommu_of_table, np);

drivers/md/bcache/btree.h

···
 
 struct btree_op {
 	/* for waiting on btree reserve in btree_split() */
-	wait_queue_t		wait;
+	wait_queue_entry_t		wait;
 
 	/* Btree level at which we start taking write locks */
 	short			lock;

drivers/net/ethernet/cavium/liquidio/octeon_main.h

···
 sleep_cond(wait_queue_head_t *wait_queue, int *condition)
 {
 	int errno = 0;
-	wait_queue_t we;
+	wait_queue_entry_t we;
 
 	init_waitqueue_entry(&we, current);
 	add_wait_queue(wait_queue, &we);
···
 		   int *condition,
 		   int timeout)
 {
-	wait_queue_t we;
+	wait_queue_entry_t we;
 
 	init_waitqueue_entry(&we, current);
 	add_wait_queue(wait_queue, &we);

drivers/net/wireless/cisco/airo.c

···
 		if (ai->jobs) {
 			locked = down_interruptible(&ai->sem);
 		} else {
-			wait_queue_t wait;
+			wait_queue_entry_t wait;
 
 			init_waitqueue_entry(&wait, current);
 			add_wait_queue(&ai->thr_wait, &wait);

drivers/net/wireless/intersil/hostap/hostap_ioctl.c

···
 			ret = -EINVAL;
 		}
 		if (local->iw_mode == IW_MODE_MASTER) {
-			wait_queue_t __wait;
+			wait_queue_entry_t __wait;
 			init_waitqueue_entry(&__wait, current);
 			add_wait_queue(&local->hostscan_wq, &__wait);
 			set_current_state(TASK_INTERRUPTIBLE);

drivers/net/wireless/marvell/libertas/main.c

···
 {
 	struct net_device *dev = data;
 	struct lbs_private *priv = dev->ml_priv;
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 
 	lbs_deb_enter(LBS_DEB_THREAD);
 

drivers/rtc/rtc-imxdi.c

···
 		/*If the write wait queue is empty then there is no pending
 		  operations. It means the interrupt is for DryIce -Security.
 		  IRQ must be returned as none.*/
-		if (list_empty_careful(&imxdi->write_wait.task_list))
+		if (list_empty_careful(&imxdi->write_wait.head))
 			return rc;
 
 		/* DSR_WCF clears itself on DSR read */

drivers/scsi/dpt/dpti_i2o.h

···
 #include <linux/wait.h>
 typedef wait_queue_head_t adpt_wait_queue_head_t;
 #define ADPT_DECLARE_WAIT_QUEUE_HEAD(wait) DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wait)
-typedef wait_queue_t adpt_wait_queue_t;
+typedef wait_queue_entry_t adpt_wait_queue_entry_t;
 
 /*
  * message structures

drivers/scsi/ips.c

···
 static uint32_t ips_statupd_morpheus(ips_ha_t *);
 static ips_scb_t *ips_getscb(ips_ha_t *);
 static void ips_putq_scb_head(ips_scb_queue_t *, ips_scb_t *);
-static void ips_putq_wait_tail(ips_wait_queue_t *, struct scsi_cmnd *);
+static void ips_putq_wait_tail(ips_wait_queue_entry_t *, struct scsi_cmnd *);
 static void ips_putq_copp_tail(ips_copp_queue_t *,
 				      ips_copp_wait_item_t *);
 static ips_scb_t *ips_removeq_scb_head(ips_scb_queue_t *);
 static ips_scb_t *ips_removeq_scb(ips_scb_queue_t *, ips_scb_t *);
-static struct scsi_cmnd *ips_removeq_wait_head(ips_wait_queue_t *);
-static struct scsi_cmnd *ips_removeq_wait(ips_wait_queue_t *,
+static struct scsi_cmnd *ips_removeq_wait_head(ips_wait_queue_entry_t *);
+static struct scsi_cmnd *ips_removeq_wait(ips_wait_queue_entry_t *,
 					  struct scsi_cmnd *);
 static ips_copp_wait_item_t *ips_removeq_copp(ips_copp_queue_t *,
 						     ips_copp_wait_item_t *);
···
 /* ASSUMED to be called from within the HA lock                             */
 /*                                                                          */
 /****************************************************************************/
-static void ips_putq_wait_tail(ips_wait_queue_t *queue, struct scsi_cmnd *item)
+static void ips_putq_wait_tail(ips_wait_queue_entry_t *queue, struct scsi_cmnd *item)
 {
 	METHOD_TRACE("ips_putq_wait_tail", 1);
 
···
 /* ASSUMED to be called from within the HA lock                             */
 /*                                                                          */
 /****************************************************************************/
-static struct scsi_cmnd *ips_removeq_wait_head(ips_wait_queue_t *queue)
+static struct scsi_cmnd *ips_removeq_wait_head(ips_wait_queue_entry_t *queue)
 {
 	struct scsi_cmnd *item;
 
···
 /* ASSUMED to be called from within the HA lock                             */
 /*                                                                          */
 /****************************************************************************/
-static struct scsi_cmnd *ips_removeq_wait(ips_wait_queue_t *queue,
+static struct scsi_cmnd *ips_removeq_wait(ips_wait_queue_entry_t *queue,
 					  struct scsi_cmnd *item)
 {
 	struct scsi_cmnd *p;

drivers/scsi/ips.h

···
 	struct scsi_cmnd *head;
 	struct scsi_cmnd *tail;
 	int count;
-} ips_wait_queue_t;
+} ips_wait_queue_entry_t;
 
 typedef struct ips_copp_wait_item {
 	struct scsi_cmnd *scsi_cmd;
···
    ips_stat_t         sp;                 /* Status packer pointer      */
    struct ips_scb    *scbs;               /* Array of all CCBS          */
    struct ips_scb    *scb_freelist;       /* SCB free list              */
-   ips_wait_queue_t   scb_waitlist;       /* Pending SCB list           */
+   ips_wait_queue_entry_t   scb_waitlist;       /* Pending SCB list           */
    ips_copp_queue_t   copp_waitlist;      /* Pending PT list            */
    ips_scb_queue_t    scb_activelist;     /* Active SCB list            */
    IPS_IO_CMD        *dummy;              /* dummy command              */

drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c

···
 kiblnd_connd(void *arg)
 {
 	spinlock_t *lock = &kiblnd_data.kib_connd_lock;
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 	unsigned long flags;
 	struct kib_conn *conn;
 	int timeout;
···
 	long id = (long)arg;
 	struct kib_sched_info *sched;
 	struct kib_conn *conn;
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 	unsigned long flags;
 	struct ib_wc wc;
 	int did_something;
···
 {
 	rwlock_t *glock = &kiblnd_data.kib_global_lock;
 	struct kib_dev *dev;
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 	unsigned long flags;
 	int rc;
 

drivers/staging/lustre/lnet/klnds/socklnd/socklnd_cb.c

···
 {
 	spinlock_t *connd_lock = &ksocknal_data.ksnd_connd_lock;
 	struct ksock_connreq *cr;
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 	int nloops = 0;
 	int cons_retry = 0;
 
···
 int
 ksocknal_reaper(void *arg)
 {
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 	struct ksock_conn *conn;
 	struct ksock_sched *sched;
 	struct list_head enomem_conns;

drivers/staging/lustre/lnet/libcfs/debug.c

···
 
 void libcfs_debug_dumplog(void)
 {
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 	struct task_struct *dumper;
 
 	/* we're being careful to ensure that the kernel thread is

drivers/staging/lustre/lnet/libcfs/tracefile.c

···
 	complete(&tctl->tctl_start);
 
 	while (1) {
-		wait_queue_t __wait;
+		wait_queue_entry_t __wait;
 
 		pc.pc_want_daemon_pages = 0;
 		collect_pages(&pc);

drivers/staging/lustre/lnet/lnet/lib-eq.c

···
 {
 	int tms = *timeout_ms;
 	int wait;
-	wait_queue_t wl;
+	wait_queue_entry_t wl;
 	unsigned long now;
 
 	if (!tms)

drivers/staging/lustre/lnet/lnet/lib-socket.c

···
 int
 lnet_sock_accept(struct socket **newsockp, struct socket *sock)
 {
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 	struct socket *newsock;
 	int rc;
 

drivers/staging/lustre/lustre/fid/fid_request.c

···
 }
 
 static int seq_fid_alloc_prep(struct lu_client_seq *seq,
-			      wait_queue_t *link)
+			      wait_queue_entry_t *link)
 {
 	if (seq->lcs_update) {
 		add_wait_queue(&seq->lcs_waitq, link);
···
 int seq_client_alloc_fid(const struct lu_env *env,
 			 struct lu_client_seq *seq, struct lu_fid *fid)
 {
-	wait_queue_t link;
+	wait_queue_entry_t link;
 	int rc;
 
 	LASSERT(seq);
···
  */
 void seq_client_flush(struct lu_client_seq *seq)
 {
-	wait_queue_t link;
+	wait_queue_entry_t link;
 
 	LASSERT(seq);
 	init_waitqueue_entry(&link, current);

drivers/staging/lustre/lustre/include/lustre_lib.h

···
 			   sigmask(SIGALRM))
 
 /**
- * wait_queue_t of Linux (version < 2.6.34) is a FIFO list for exclusively
+ * wait_queue_entry_t of Linux (version < 2.6.34) is a FIFO list for exclusively
  * waiting threads, which is not always desirable because all threads will
  * be waken up again and again, even user only needs a few of them to be
  * active most time. This is not good for performance because cache can
···
  */
 #define __l_wait_event(wq, condition, info, ret, l_add_wait)		   \
 do {									   \
-	wait_queue_t __wait;						 \
+	wait_queue_entry_t __wait;						 \
 	long __timeout = info->lwi_timeout;			  \
 	sigset_t   __blocked;					      \
 	int   __allow_intr = info->lwi_allow_intr;			     \

drivers/staging/lustre/lustre/llite/lcommon_cl.c

···
 static void cl_object_put_last(struct lu_env *env, struct cl_object *obj)
 {
 	struct lu_object_header *header = obj->co_lu.lo_header;
-	wait_queue_t	   waiter;
+	wait_queue_entry_t	   waiter;
 
 	if (unlikely(atomic_read(&header->loh_ref) != 1)) {
 		struct lu_site *site = obj->co_lu.lo_dev->ld_site;

drivers/staging/lustre/lustre/lov/lov_cl_internal.h

···
 	struct ost_lvb	  lti_lvb;
 	struct cl_2queue	lti_cl2q;
 	struct cl_page_list     lti_plist;
-	wait_queue_t	  lti_waiter;
+	wait_queue_entry_t	  lti_waiter;
 	struct cl_attr          lti_attr;
 };
 

drivers/staging/lustre/lustre/lov/lov_object.c

···
 	struct lov_layout_raid0 *r0;
 	struct lu_site	  *site;
 	struct lu_site_bkt_data *bkt;
-	wait_queue_t	  *waiter;
+	wait_queue_entry_t	  *waiter;
 
 	r0  = &lov->u.raid0;
 	LASSERT(r0->lo_sub[idx] == los);

drivers/staging/lustre/lustre/obdclass/lu_object.c

···
 static struct lu_object *htable_lookup(struct lu_site *s,
 				       struct cfs_hash_bd *bd,
 				       const struct lu_fid *f,
-				       wait_queue_t *waiter,
+				       wait_queue_entry_t *waiter,
 				       __u64 *version)
 {
 	struct lu_site_bkt_data *bkt;
···
 					    struct lu_device *dev,
 					    const struct lu_fid *f,
 					    const struct lu_object_conf *conf,
-					    wait_queue_t *waiter)
+					    wait_queue_entry_t *waiter)
 {
 	struct lu_object      *o;
 	struct lu_object      *shadow;
···
 {
 	struct lu_site_bkt_data *bkt;
 	struct lu_object	*obj;
-	wait_queue_t	   wait;
+	wait_queue_entry_t	   wait;
 
 	while (1) {
 		obj = lu_object_find_try(env, dev, f, conf, &wait);

drivers/tty/synclink_gt.c

···
 struct cond_wait {
 	struct cond_wait *next;
 	wait_queue_head_t q;
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 	unsigned int data;
 };
 static void init_cond_wait(struct cond_wait *w, unsigned int data);

drivers/vfio/virqfd.c

···
 	queue_work(vfio_irqfd_cleanup_wq, &virqfd->shutdown);
 }
 
-static int virqfd_wakeup(wait_queue_t *wait, unsigned mode, int sync, void *key)
+static int virqfd_wakeup(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
 {
 	struct virqfd *virqfd = container_of(wait, struct virqfd, wait);
 	unsigned long flags = (unsigned long)key;

drivers/vhost/vhost.c

···
 	add_wait_queue(wqh, &poll->wait);
 }
 
-static int vhost_poll_wakeup(wait_queue_t *wait, unsigned mode, int sync,
+static int vhost_poll_wakeup(wait_queue_entry_t *wait, unsigned mode, int sync,
 			     void *key)
 {
 	struct vhost_poll *poll = container_of(wait, struct vhost_poll, wait);

drivers/vhost/vhost.h

···
 struct vhost_poll {
 	poll_table                table;
 	wait_queue_head_t        *wqh;
-	wait_queue_t              wait;
+	wait_queue_entry_t              wait;
 	struct vhost_work	  work;
 	unsigned long		  mask;
 	struct vhost_dev	 *dev;

drivers/xen/manage.c

···
 {
 	switch (system_state) {
 	case SYSTEM_BOOTING:
+	case SYSTEM_SCHEDULING:
 		orderly_poweroff(true);
 		break;
 	case SYSTEM_RUNNING:

fs/autofs4/autofs_i.h

···
 struct autofs_wait_queue {
 	wait_queue_head_t queue;
 	struct autofs_wait_queue *next;
-	autofs_wqt_t wait_queue_token;
+	autofs_wqt_t wait_queue_entry_token;
 	/* We use the following to see what we are waiting for */
 	struct qstr name;
 	u32 dev;

fs/autofs4/waitq.c

···
 	size_t pktsz;
 
 	pr_debug("wait id = 0x%08lx, name = %.*s, type=%d\n",
-		 (unsigned long) wq->wait_queue_token,
+		 (unsigned long) wq->wait_queue_entry_token,
 		 wq->name.len, wq->name.name, type);
 
 	memset(&pkt, 0, sizeof(pkt)); /* For security reasons */
···
 
 		pktsz = sizeof(*mp);
 
-		mp->wait_queue_token = wq->wait_queue_token;
+		mp->wait_queue_entry_token = wq->wait_queue_entry_token;
 		mp->len = wq->name.len;
 		memcpy(mp->name, wq->name.name, wq->name.len);
 		mp->name[wq->name.len] = '\0';
···
 
 		pktsz = sizeof(*ep);
 
-		ep->wait_queue_token = wq->wait_queue_token;
+		ep->wait_queue_entry_token = wq->wait_queue_entry_token;
 		ep->len = wq->name.len;
 		memcpy(ep->name, wq->name.name, wq->name.len);
 		ep->name[wq->name.len] = '\0';
···
 
 		pktsz = sizeof(*packet);
 
-		packet->wait_queue_token = wq->wait_queue_token;
+		packet->wait_queue_entry_token = wq->wait_queue_entry_token;
 		packet->len = wq->name.len;
 		memcpy(packet->name, wq->name.name, wq->name.len);
 		packet->name[wq->name.len] = '\0';
···
 			return -ENOMEM;
 		}
 
-		wq->wait_queue_token = autofs4_next_wait_queue;
+		wq->wait_queue_entry_token = autofs4_next_wait_queue;
 		if (++autofs4_next_wait_queue == 0)
 			autofs4_next_wait_queue = 1;
 		wq->next = sbi->queues;
···
 		}
 
 		pr_debug("new wait id = 0x%08lx, name = %.*s, nfy=%d\n",
-			 (unsigned long) wq->wait_queue_token, wq->name.len,
+			 (unsigned long) wq->wait_queue_entry_token, wq->name.len,
 			 wq->name.name, notify);
 
 		/*
···
 	} else {
 		wq->wait_ctr++;
 		pr_debug("existing wait id = 0x%08lx, name = %.*s, nfy=%d\n",
-			 (unsigned long) wq->wait_queue_token, wq->name.len,
+			 (unsigned long) wq->wait_queue_entry_token, wq->name.len,
 			 wq->name.name, notify);
 		mutex_unlock(&sbi->wq_mutex);
 		kfree(qstr.name);
···
 }
 
 
-int autofs4_wait_release(struct autofs_sb_info *sbi, autofs_wqt_t wait_queue_token, int status)
+int autofs4_wait_release(struct autofs_sb_info *sbi, autofs_wqt_t wait_queue_entry_token, int status)
 {
 	struct autofs_wait_queue *wq, **wql;
 
 	mutex_lock(&sbi->wq_mutex);
 	for (wql = &sbi->queues; (wq = *wql) != NULL; wql = &wq->next) {
-		if (wq->wait_queue_token == wait_queue_token)
+		if (wq->wait_queue_entry_token == wait_queue_entry_token)
 			break;
 	}
 

fs/cachefiles/internal.h

···
 
 #include <linux/fscache-cache.h>
 #include <linux/timer.h>
-#include <linux/wait.h>
+#include <linux/wait_bit.h>
 #include <linux/cred.h>
 #include <linux/workqueue.h>
 #include <linux/security.h>
···
  * backing file read tracking
  */
 struct cachefiles_one_read {
-	wait_queue_t			monitor;	/* link into monitored waitqueue */
+	wait_queue_entry_t			monitor;	/* link into monitored waitqueue */
 	struct page			*back_page;	/* backing file page we're waiting for */
 	struct page			*netfs_page;	/* netfs page we're going to fill */
 	struct fscache_retrieval	*op;		/* retrieval op covering this */

fs/cachefiles/namei.c

···
 		wait_queue_head_t *wq;
 
 		signed long timeout = 60 * HZ;
-		wait_queue_t wait;
+		wait_queue_entry_t wait;
 		bool requeue;
 
 		/* if the object we're waiting for is queued for processing,

fs/cachefiles/rdwr.c

···
  * - we use this to detect read completion of backing pages
  * - the caller holds the waitqueue lock
  */
-static int cachefiles_read_waiter(wait_queue_t *wait, unsigned mode,
+static int cachefiles_read_waiter(wait_queue_entry_t *wait, unsigned mode,
 				  int sync, void *_key)
 {
 	struct cachefiles_one_read *monitor =
···
 	}
 
 	/* remove from the waitqueue */
-	list_del(&wait->task_list);
+	list_del(&wait->entry);
 
 	/* move onto the action list and queue for FS-Cache thread pool */
 	ASSERT(monitor->op);

fs/cifs/inode.c

···
 #include <linux/pagemap.h>
 #include <linux/freezer.h>
 #include <linux/sched/signal.h>
+#include <linux/wait_bit.h>
 
 #include <asm/div64.h>
 #include "cifsfs.h"

fs/dax.c

···
 };
 
 struct wait_exceptional_entry_queue {
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 	struct exceptional_entry_key key;
 };
 
···
 	return wait_table + hash;
 }
 
-static int wake_exceptional_entry_func(wait_queue_t *wait, unsigned int mode,
+static int wake_exceptional_entry_func(wait_queue_entry_t *wait, unsigned int mode,
 				       int sync, void *keyp)
 {
 	struct exceptional_entry_key *key = keyp;

fs/eventfd.c

···
  * This is used to atomically remove a wait queue entry from the eventfd wait
  * queue head, and read/reset the counter value.
  */
-int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_t *wait,
+int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *wait,
 				  __u64 *cnt)
 {
 	unsigned long flags;

fs/eventpoll.c

···
 	 * Wait queue item that will be linked to the target file wait
 	 * queue head.
 	 */
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 
 	/* The wait queue head that linked the "wait" wait queue item */
 	wait_queue_head_t *whead;
···
 	return !list_empty(p);
 }
 
-static inline struct eppoll_entry *ep_pwq_from_wait(wait_queue_t *p)
+static inline struct eppoll_entry *ep_pwq_from_wait(wait_queue_entry_t *p)
 {
 	return container_of(p, struct eppoll_entry, wait);
 }
 
 /* Get the "struct epitem" from a wait queue pointer */
-static inline struct epitem *ep_item_from_wait(wait_queue_t *p)
+static inline struct epitem *ep_item_from_wait(wait_queue_entry_t *p)
 {
 	return container_of(p, struct eppoll_entry, wait)->base;
 }
···
  * mechanism. It is called by the stored file descriptors when they
  * have events to report.
  */
-static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *key)
+static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
 {
 	int pwake = 0;
 	unsigned long flags;
···
 		 * can't use __remove_wait_queue(). whead->lock is held by
 		 * the caller.
 		 */
-		list_del_init(&wait->task_list);
+		list_del_init(&wait->entry);
 	}
 
 	spin_lock_irqsave(&ep->lock, flags);
···
 	int res = 0, eavail, timed_out = 0;
 	unsigned long flags;
 	u64 slack = 0;
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 	ktime_t expires, *to = NULL;
 
 	if (timeout > 0) {

fs/fs_pin.c

···
 
 void pin_kill(struct fs_pin *p)
 {
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 
 	if (!p) {
 		rcu_read_unlock();
···
 		rcu_read_unlock();
 		schedule();
 		rcu_read_lock();
-		if (likely(list_empty(&wait.task_list)))
+		if (likely(list_empty(&wait.entry)))
 			break;
 		/* OK, we know p couldn't have been freed yet */
 		spin_lock_irq(&p->wait.lock);

fs/inode.c

···
 	wait_queue_head_t *wq;
 	DEFINE_WAIT_BIT(wait, &inode->i_state, __I_NEW);
 	wq = bit_waitqueue(&inode->i_state, __I_NEW);
-	prepare_to_wait(wq, &wait.wait, TASK_UNINTERRUPTIBLE);
+	prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE);
 	spin_unlock(&inode->i_lock);
 	spin_unlock(&inode_hash_lock);
 	schedule();
-	finish_wait(wq, &wait.wait);
+	finish_wait(wq, &wait.wq_entry);
 	spin_lock(&inode_hash_lock);
 }
 
···
 	DEFINE_WAIT_BIT(q, &inode->i_state, __I_DIO_WAKEUP);
 
 	do {
-		prepare_to_wait(wq, &q.wait, TASK_UNINTERRUPTIBLE);
+		prepare_to_wait(wq, &q.wq_entry, TASK_UNINTERRUPTIBLE);
 		if (atomic_read(&inode->i_dio_count))
 			schedule();
 	} while (atomic_read(&inode->i_dio_count));
-	finish_wait(wq, &q.wait);
+	finish_wait(wq, &q.wq_entry);
 }
 
 /**

fs/jbd2/journal.c

···
 		wait_queue_head_t *wq;
 		DEFINE_WAIT_BIT(wait, &jinode->i_flags, __JI_COMMIT_RUNNING);
 		wq = bit_waitqueue(&jinode->i_flags, __JI_COMMIT_RUNNING);
-		prepare_to_wait(wq, &wait.wait, TASK_UNINTERRUPTIBLE);
+		prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE);
 		spin_unlock(&journal->j_list_lock);
 		schedule();
-		finish_wait(wq, &wait.wait);
+		finish_wait(wq, &wait.wq_entry);
 		goto restart;
 	}
 

fs/nfs/internal.h

···
 #include <linux/security.h>
 #include <linux/crc32.h>
 #include <linux/nfs_page.h>
+#include <linux/wait_bit.h>
 
 #define NFS_MS_MASK (MS_RDONLY|MS_NOSUID|MS_NODEV|MS_NOEXEC|MS_SYNCHRONOUS)
 

fs/nfs/nfs4proc.c

···
 };
 
 static int
-nfs4_wake_lock_waiter(wait_queue_t *wait, unsigned int mode, int flags, void *key)
+nfs4_wake_lock_waiter(wait_queue_entry_t *wait, unsigned int mode, int flags, void *key)
 {
 	int ret;
 	struct cb_notify_lock_args *cbnl = key;
···
 					   .inode = state->inode,
 					   .owner = &owner,
 					   .notified = false };
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 
 	/* Don't bother with waitqueue if we don't expect a callback */
 	if (!test_bit(NFS_STATE_MAY_NOTIFY_LOCK, &state->flags))

fs/nilfs2/segment.c

···
 }
 
 struct nilfs_segctor_wait_request {
-	wait_queue_t	wq;
+	wait_queue_entry_t	wq;
 	__u32		seq;
 	int		err;
 	atomic_t	done;
···
 	unsigned long flags;
 
 	spin_lock_irqsave(&sci->sc_wait_request.lock, flags);
-	list_for_each_entry_safe(wrq, n, &sci->sc_wait_request.task_list,
-				 wq.task_list) {
+	list_for_each_entry_safe(wrq, n, &sci->sc_wait_request.head, wq.entry) {
 		if (!atomic_read(&wrq->done) &&
 		    nilfs_cnt32_ge(sci->sc_seq_done, wrq->seq)) {
 			wrq->err = err;

fs/orangefs/orangefs-bufmap.c

···
 	spin_lock(&m->q.lock);
 	if (m->c != -1) {
 		for (;;) {
-			if (likely(list_empty(&wait.task_list)))
-				__add_wait_queue_tail(&m->q, &wait);
+			if (likely(list_empty(&wait.entry)))
+				__add_wait_queue_entry_tail(&m->q, &wait);
 			set_current_state(TASK_UNINTERRUPTIBLE);
 
 			if (m->c == -1)
···
 
 	do {
 		long n = left, t;
-		if (likely(list_empty(&wait.task_list)))
-			__add_wait_queue_tail_exclusive(&m->q, &wait);
+		if (likely(list_empty(&wait.entry)))
+			__add_wait_queue_entry_tail_exclusive(&m->q, &wait);
 		set_current_state(TASK_INTERRUPTIBLE);
 
 		if (m->c > 0)
···
 			left = -EINTR;
 	} while (left > 0);
 
-	if (!list_empty(&wait.task_list))
-		list_del(&wait.task_list);
+	if (!list_empty(&wait.entry))
+		list_del(&wait.entry);
 	else if (left <= 0 && waitqueue_active(&m->q))
 		__wake_up_locked_key(&m->q, TASK_INTERRUPTIBLE, NULL);
 	__set_current_state(TASK_RUNNING);

fs/reiserfs/journal.c

···
 
 static void queue_log_writer(struct super_block *s)
 {
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 	struct reiserfs_journal *journal = SB_JOURNAL(s);
 	set_bit(J_WRITERS_QUEUED, &journal->j_state);
 

fs/select.c

···
 	return table->entry++;
 }
 
-static int __pollwake(wait_queue_t *wait, unsigned mode, int sync, void *key)
+static int __pollwake(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
 {
 	struct poll_wqueues *pwq = wait->private;
 	DECLARE_WAITQUEUE(dummy_wait, pwq->polling_task);
···
 	return default_wake_function(&dummy_wait, mode, sync, key);
 }
 
-static int pollwake(wait_queue_t *wait, unsigned mode, int sync, void *key)
+static int pollwake(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
 {
 	struct poll_table_entry *entry;
 

fs/signalfd.c

···
 	if (likely(!waitqueue_active(wqh)))
 		return;
 
-	/* wait_queue_t->func(POLLFREE) should do remove_wait_queue() */
+	/* wait_queue_entry_t->func(POLLFREE) should do remove_wait_queue() */
 	wake_up_poll(wqh, POLLHUP | POLLFREE);
 }
 

fs/userfaultfd.c

···
 
 struct userfaultfd_wait_queue {
 	struct uffd_msg msg;
-	wait_queue_t wq;
+	wait_queue_entry_t wq;
 	struct userfaultfd_ctx *ctx;
 	bool waken;
 };
···
 	unsigned long len;
 };
 
-static int userfaultfd_wake_function(wait_queue_t *wq, unsigned mode,
+static int userfaultfd_wake_function(wait_queue_entry_t *wq, unsigned mode,
 				     int wake_flags, void *key)
 {
 	struct userfaultfd_wake_range *range = key;
···
 		 * wouldn't be enough, the smp_mb__before_spinlock is
 		 * enough to avoid an explicit smp_mb() here.
 		 */
-		list_del_init(&wq->task_list);
+		list_del_init(&wq->entry);
 out:
 	return ret;
 }
···
 	 * and it's fine not to block on the spinlock. The uwq on this
 	 * kernel stack can be released after the list_del_init.
 	 */
-	if (!list_empty_careful(&uwq.wq.task_list)) {
+	if (!list_empty_careful(&uwq.wq.entry)) {
 		spin_lock(&ctx->fault_pending_wqh.lock);
 		/*
 		 * No need of list_del_init(), the uwq on the stack
 		 * will be freed shortly anyway.
 		 */
-		list_del(&uwq.wq.task_list);
+		list_del(&uwq.wq.entry);
 		spin_unlock(&ctx->fault_pending_wqh.lock);
 	}
 
···
 static inline struct userfaultfd_wait_queue *find_userfault_in(
 		wait_queue_head_t *wqh)
 {
-	wait_queue_t *wq;
+	wait_queue_entry_t *wq;
 	struct userfaultfd_wait_queue *uwq;
 
 	VM_BUG_ON(!spin_is_locked(&wqh->lock));
···
 	if (!waitqueue_active(wqh))
 		goto out;
 	/* walk in reverse to provide FIFO behavior to read userfaults */
-	wq = list_last_entry(&wqh->task_list, typeof(*wq), task_list);
+	wq = list_last_entry(&wqh->head, typeof(*wq), entry);
 	uwq = container_of(wq, struct userfaultfd_wait_queue, wq);
 out:
 	return uwq;
···
 			 * changes __remove_wait_queue() to use
 			 * list_del_init() in turn breaking the
 			 * !list_empty_careful() check in
-			 * handle_userfault(). The uwq->wq.task_list
+			 * handle_userfault(). The uwq->wq.head list
 			 * must never be empty at any time during the
 			 * refile, or the waitqueue could disappear
 			 * from under us. The "wait_queue_head_t"
 			 * parameter of __remove_wait_queue() is unused
 			 * anyway.
 			 */
-			list_del(&uwq->wq.task_list);
+			list_del(&uwq->wq.entry);
 			__add_wait_queue(&ctx->fault_wqh, &uwq->wq);
 
 			write_seqcount_end(&ctx->refile_seq);
···
 				fork_nctx = (struct userfaultfd_ctx *)
 					(unsigned long)
 					uwq->msg.arg.reserved.reserved1;
-				list_move(&uwq->wq.task_list, &fork_event);
+				list_move(&uwq->wq.entry, &fork_event);
 				spin_unlock(&ctx->event_wqh.lock);
 				ret = 0;
 				break;
···
 			if (!list_empty(&fork_event)) {
 				uwq = list_first_entry(&fork_event,
 						       typeof(*uwq),
-						       wq.task_list);
-				list_del(&uwq->wq.task_list);
+						       wq.entry);
+				list_del(&uwq->wq.entry);
 				__add_wait_queue(&ctx->event_wqh, &uwq->wq);
 				userfaultfd_event_complete(ctx, uwq);
 			}
···
 static void userfaultfd_show_fdinfo(struct seq_file *m, struct file *f)
 {
 	struct userfaultfd_ctx *ctx = f->private_data;
-	wait_queue_t *wq;
+	wait_queue_entry_t *wq;
 	struct userfaultfd_wait_queue *uwq;
 	unsigned long pending = 0, total = 0;
 
 	spin_lock(&ctx->fault_pending_wqh.lock);
-	list_for_each_entry(wq, &ctx->fault_pending_wqh.task_list, task_list) {
+	list_for_each_entry(wq, &ctx->fault_pending_wqh.head, entry) {
 		uwq = container_of(wq, struct userfaultfd_wait_queue, wq);
 		pending++;
 		total++;
 	}
-	list_for_each_entry(wq, &ctx->fault_wqh.task_list, task_list) {
+	list_for_each_entry(wq, &ctx->fault_wqh.head, entry) {
 		uwq = container_of(wq, struct userfaultfd_wait_queue, wq);
 		total++;
 	}

fs/xfs/xfs_icache.c

···
 	DEFINE_WAIT_BIT(wait, &ip->i_flags, __XFS_INEW_BIT);
 
 	do {
-		prepare_to_wait(wq, &wait.wait, TASK_UNINTERRUPTIBLE);
+		prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE);
 		if (!xfs_iflags_test(ip, XFS_INEW))
 			break;
 		schedule();
 	} while (true);
-	finish_wait(wq, &wait.wait);
+	finish_wait(wq, &wait.wq_entry);
 }
 
 /*

fs/xfs/xfs_inode.c

···
 	DEFINE_WAIT_BIT(wait, &ip->i_flags, __XFS_IFLOCK_BIT);
 
 	do {
-		prepare_to_wait_exclusive(wq, &wait.wait, TASK_UNINTERRUPTIBLE);
+		prepare_to_wait_exclusive(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE);
 		if (xfs_isiflocked(ip))
 			io_schedule();
 	} while (!xfs_iflock_nowait(ip));
 
-	finish_wait(wq, &wait.wait);
+	finish_wait(wq, &wait.wq_entry);
 }
 
 STATIC uint
···
 	xfs_iunpin(ip);
 
 	do {
-		prepare_to_wait(wq, &wait.wait, TASK_UNINTERRUPTIBLE);
+		prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE);
 		if (xfs_ipincount(ip))
 			io_schedule();
 	} while (xfs_ipincount(ip));
-	finish_wait(wq, &wait.wait);
+	finish_wait(wq, &wait.wq_entry);
 }
 
 void

include/linux/blk-mq.h

···
 	struct blk_mq_ctx	**ctxs;
 	unsigned int		nr_ctx;
 
-	wait_queue_t		dispatch_wait;
+	wait_queue_entry_t		dispatch_wait;
 	atomic_t		wait_index;
 
 	struct blk_mq_tags	*tags;

include/linux/clocksource.h

···
 	void (*suspend)(struct clocksource *cs);
 	void (*resume)(struct clocksource *cs);
 	void (*mark_unstable)(struct clocksource *cs);
+	void (*tick_stable)(struct clocksource *cs);
 
 	/* private: */
 #ifdef CONFIG_CLOCKSOURCE_WATCHDOG

include/linux/cpumask.h

···
 		(cpu) = cpumask_next_zero((cpu), (mask)),	\
 		(cpu) < nr_cpu_ids;)
 
+extern int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap);
+
+/**
+ * for_each_cpu_wrap - iterate over every cpu in a mask, starting at a specified location
+ * @cpu: the (optionally unsigned) integer iterator
+ * @mask: the cpumask poiter
+ * @start: the start location
+ *
+ * The implementation does not assume any bit in @mask is set (including @start).
+ *
+ * After the loop, cpu is >= nr_cpu_ids.
+ */
+#define for_each_cpu_wrap(cpu, mask, start)					\
+	for ((cpu) = cpumask_next_wrap((start)-1, (mask), (start), false);	\
+	     (cpu) < nr_cpumask_bits;						\
+	     (cpu) = cpumask_next_wrap((cpu), (mask), (start), true))
+
 /**
  * for_each_cpu_and - iterate over every cpu in both masks
  * @cpu: the (optionally unsigned) integer iterator
···
 	set_bit(cpumask_check(cpu), cpumask_bits(dstp));
 }
 
+static inline void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp)
+{
+	__set_bit(cpumask_check(cpu), cpumask_bits(dstp));
+}
+
+
 /**
  * cpumask_clear_cpu - clear a cpu in a cpumask
  * @cpu: cpu number (< nr_cpu_ids)
···
 static inline void cpumask_clear_cpu(int cpu, struct cpumask *dstp)
 {
 	clear_bit(cpumask_check(cpu), cpumask_bits(dstp));
+}
+
+static inline void __cpumask_clear_cpu(int cpu, struct cpumask *dstp)
+{
+	__clear_bit(cpumask_check(cpu), cpumask_bits(dstp));
 }
 
 /**

include/linux/eventfd.h

···
 struct eventfd_ctx *eventfd_ctx_fileget(struct file *file);
 __u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n);
 ssize_t eventfd_ctx_read(struct eventfd_ctx *ctx, int no_wait, __u64 *cnt);
-int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_t *wait,
+int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *wait,
 				  __u64 *cnt);
 
 #else /* CONFIG_EVENTFD */
···
 }
 
 static inline int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx,
-						wait_queue_t *wait, __u64 *cnt)
+						wait_queue_entry_t *wait, __u64 *cnt)
 {
 	return -ENOSYS;
 }

include/linux/fs.h

···
 #define _LINUX_FS_H
 
 #include <linux/linkage.h>
-#include <linux/wait.h>
+#include <linux/wait_bit.h>
 #include <linux/kdev_t.h>
 #include <linux/dcache.h>
 #include <linux/path.h>

include/linux/kernel.h

···
 
 extern bool early_boot_irqs_disabled;
 
-/* Values used for system_state */
+/*
+ * Values used for system_state. Ordering of the states must not be changed
+ * as code checks for <, <=, >, >= STATE.
+ */
 extern enum system_states {
 	SYSTEM_BOOTING,
+	SYSTEM_SCHEDULING,
 	SYSTEM_RUNNING,
 	SYSTEM_HALT,
 	SYSTEM_POWER_OFF,

include/linux/kvm_irqfd.h

···
 struct kvm_kernel_irqfd {
 	/* Used for MSI fast-path */
 	struct kvm *kvm;
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 	/* Update side is protected by irqfds.lock */
 	struct kvm_kernel_irq_routing_entry irq_entry;
 	seqcount_t irq_entry_sc;

include/linux/llist.h

···
 	for ((pos) = (node); pos; (pos) = (pos)->next)
 
 /**
+ * llist_for_each_safe - iterate over some deleted entries of a lock-less list
+ *			 safe against removal of list entry
+ * @pos:	the &struct llist_node to use as a loop cursor
+ * @n:		another &struct llist_node to use as temporary storage
+ * @node:	the first entry of deleted list entries
+ *
+ * In general, some entries of the lock-less list can be traversed
+ * safely only after being deleted from list, so start with an entry
+ * instead of list head.
+ *
+ * If being used on entries deleted from lock-less list directly, the
+ * traverse order is from the newest to the oldest added entry.  If
+ * you want to traverse from the oldest to the newest, you must
+ * reverse the order by yourself before traversing.
+ */
+#define llist_for_each_safe(pos, n, node)			\
+	for ((pos) = (node); (pos) && ((n) = (pos)->next, true); (pos) = (n))
+
+/**
  * llist_for_each_entry - iterate over some deleted entries of lock-less list of given type
  * @pos:	the type * to use as a loop cursor.
  * @node:	the fist entry of deleted list entries.

include/linux/pagemap.h

···
 /*
  * Add an arbitrary waiter to a page's wait queue
  */
-extern void add_page_wait_queue(struct page *page, wait_queue_t *waiter);
+extern void add_page_wait_queue(struct page *page, wait_queue_entry_t *waiter);
 
 /*
  * Fault everything in given userspace address range in.

include/linux/poll.h

···
 struct poll_table_entry {
 	struct file *filp;
 	unsigned long key;
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 	wait_queue_head_t *wait_address;
 };
 

include/linux/sched.h

···
 	u64				dl_runtime;	/* Maximum runtime for each instance	*/
 	u64				dl_deadline;	/* Relative deadline of each instance	*/
 	u64				dl_period;	/* Separation of two instances (period) */
-	u64				dl_bw;		/* dl_runtime / dl_deadline		*/
+	u64				dl_bw;		/* dl_runtime / dl_period		*/
+	u64				dl_density;	/* dl_runtime / dl_deadline		*/
 
 	/*
 	 * Actual scheduling parameters. Initialized with the values above,
···
 	 *
 	 * @dl_yielded tells if task gave up the CPU before consuming
 	 * all its available runtime during the last job.
+	 *
+	 * @dl_non_contending tells if the task is inactive while still
+	 * contributing to the active utilization. In other words, it
+	 * indicates if the inactive timer has been armed and its handler
+	 * has not been executed yet. This flag is useful to avoid race
+	 * conditions between the inactive timer handler and the wakeup
+	 * code.
 	 */
 	int				dl_throttled;
 	int				dl_boosted;
 	int				dl_yielded;
+	int				dl_non_contending;
 
 	/*
 	 * Bandwidth enforcement timer. Each -deadline task has its
 	 * own bandwidth to be enforced, thus we need one timer per task.
 	 */
 	struct hrtimer			dl_timer;
+
+	/*
+	 * Inactive timer, responsible for decreasing the active utilization
+	 * at the "0-lag time". When a -deadline task blocks, it contributes
+	 * to GRUB's active utilization until the "0-lag time", hence a
+	 * timer is needed to decrease the active utilization at the correct
+	 * time.
+	 */
+	struct hrtimer inactive_timer;
 };
 
 union rcu_special {
···
  * task_xid_vnr()    : virtual id, i.e. the id seen from the pid namespace of
  *                     current.
  * task_xid_nr_ns()  : id seen from the ns specified;
- *
- * set_task_vxid()   : assigns a virtual id to a task;
  *
  * see also pid_nr() etc in include/linux/pid.h
  */

include/linux/sched/clock.h

···
 extern void sched_clock_init(void);
 
 #ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
-static inline void sched_clock_init_late(void)
-{
-}
-
 static inline void sched_clock_tick(void)
 {
 }
···
 {
 }
 
-static inline void sched_clock_idle_wakeup_event(u64 delta_ns)
+static inline void sched_clock_idle_wakeup_event(void)
 {
 }
 
···
 	return sched_clock();
 }
 #else
-extern void sched_clock_init_late(void);
 extern int sched_clock_stable(void);
 extern void clear_sched_clock_stable(void);
 
···
  */
 extern u64 __sched_clock_offset;
 
-
 extern void sched_clock_tick(void);
+extern void sched_clock_tick_stable(void);
 extern void sched_clock_idle_sleep_event(void);
-extern void sched_clock_idle_wakeup_event(u64 delta_ns);
+extern void sched_clock_idle_wakeup_event(void);
 
 /*
  * As outlined in clock.c, provides a fast, high resolution, nanosecond

include/linux/sched/nohz.h

···
 #endif
 
 #ifdef CONFIG_NO_HZ_COMMON
-void calc_load_enter_idle(void);
-void calc_load_exit_idle(void);
+void calc_load_nohz_start(void);
+void calc_load_nohz_stop(void);
 #else
-static inline void calc_load_enter_idle(void) { }
-static inline void calc_load_exit_idle(void) { }
+static inline void calc_load_nohz_start(void) { }
+static inline void calc_load_nohz_stop(void) { }
 #endif /* CONFIG_NO_HZ_COMMON */
 
 #if defined(CONFIG_NO_HZ_COMMON) && defined(CONFIG_SMP)

include/linux/sched/task.h

···
 }
 
 struct task_struct *task_rcu_dereference(struct task_struct **ptask);
-struct task_struct *try_get_task_struct(struct task_struct **ptask);
-
 
 #ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT
 extern int arch_task_struct_size __read_mostly;

include/linux/sunrpc/sched.h

···
 #include <linux/ktime.h>
 #include <linux/sunrpc/types.h>
 #include <linux/spinlock.h>
-#include <linux/wait.h>
+#include <linux/wait_bit.h>
 #include <linux/workqueue.h>
 #include <linux/sunrpc/xdr.h>
 

include/linux/vfio.h

···
 	void			(*thread)(void *, void *);
 	void			*data;
 	struct work_struct	inject;
-	wait_queue_t		wait;
+	wait_queue_entry_t		wait;
 	poll_table		pt;
 	struct work_struct	shutdown;
 	struct virqfd		**pvirqfd;

include/linux/wait.h

···
 #include <asm/current.h>
 #include <uapi/linux/wait.h>
 
-typedef struct __wait_queue wait_queue_t;
-typedef int (*wait_queue_func_t)(wait_queue_t *wait, unsigned mode, int flags, void *key);
-int default_wake_function(wait_queue_t *wait, unsigned mode, int flags, void *key);
+typedef struct wait_queue_entry wait_queue_entry_t;
 
-/* __wait_queue::flags */
+typedef int (*wait_queue_func_t)(struct wait_queue_entry *wq_entry, unsigned mode, int flags, void *key);
+int default_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int flags, void *key);
+
+/* wait_queue_entry::flags */
 #define WQ_FLAG_EXCLUSIVE	0x01
 #define WQ_FLAG_WOKEN		0x02
 
-struct __wait_queue {
+/*
+ * A single wait-queue entry structure:
+ */
+struct wait_queue_entry {
 	unsigned int		flags;
 	void			*private;
 	wait_queue_func_t	func;
-	struct list_head	task_list;
+	struct list_head	entry;
 };
 
-struct wait_bit_key {
-	void			*flags;
-	int			bit_nr;
-#define WAIT_ATOMIC_T_BIT_NR	-1
-	unsigned long		timeout;
-};
-
-struct wait_bit_queue {
-	struct wait_bit_key	key;
-	wait_queue_t		wait;
-};
-
-struct __wait_queue_head {
+struct wait_queue_head {
 	spinlock_t		lock;
-	struct list_head	task_list;
+	struct list_head	head;
 };
-typedef struct __wait_queue_head wait_queue_head_t;
+typedef struct wait_queue_head wait_queue_head_t;
 
 struct task_struct;
 
···
  * Macros for declaration and initialisaton of the datatypes
  */
 
-#define __WAITQUEUE_INITIALIZER(name, tsk) {				\
-	.private	= tsk,						\
-	.func		= default_wake_function,			\
-	.task_list	= { NULL, NULL } }
+#define __WAITQUEUE_INITIALIZER(name, tsk) {					\
+	.private	= tsk,							\
+	.func		= default_wake_function,				\
+	.entry		= { NULL, NULL } }
 
-#define DECLARE_WAITQUEUE(name, tsk)					\
-	wait_queue_t name = __WAITQUEUE_INITIALIZER(name, tsk)
+#define DECLARE_WAITQUEUE(name, tsk)						\
+	struct wait_queue_entry name = __WAITQUEUE_INITIALIZER(name, tsk)
 
-#define __WAIT_QUEUE_HEAD_INITIALIZER(name) {				\
-	.lock		= __SPIN_LOCK_UNLOCKED(name.lock),		\
-	.task_list	= { &(name).task_list, &(name).task_list } }
+#define __WAIT_QUEUE_HEAD_INITIALIZER(name) {					\
+	.lock		= __SPIN_LOCK_UNLOCKED(name.lock),			\
+	.head		= { &(name).head, &(name).head } }
 
 #define DECLARE_WAIT_QUEUE_HEAD(name) \
-	wait_queue_head_t name = __WAIT_QUEUE_HEAD_INITIALIZER(name)
+	struct wait_queue_head name = __WAIT_QUEUE_HEAD_INITIALIZER(name)
 
-#define __WAIT_BIT_KEY_INITIALIZER(word, bit)				\
-	{ .flags = word, .bit_nr = bit, }
+extern void __init_waitqueue_head(struct wait_queue_head *wq_head, const char *name, struct lock_class_key *);
 
-#define __WAIT_ATOMIC_T_KEY_INITIALIZER(p)				\
-	{ .flags = p, .bit_nr = WAIT_ATOMIC_T_BIT_NR, }
-
-extern void __init_waitqueue_head(wait_queue_head_t *q, const char *name, struct lock_class_key *);
-
-#define init_waitqueue_head(q)				\
-	do {						\
-		static struct lock_class_key __key;	\
-							\
-		__init_waitqueue_head((q), #q, &__key);	\
+#define init_waitqueue_head(wq_head)						\
+	do {									\
+		static struct lock_class_key __key;				\
+										\
+		__init_waitqueue_head((wq_head), #wq_head, &__key);		\
 	} while (0)
 
 #ifdef CONFIG_LOCKDEP
 # define __WAIT_QUEUE_HEAD_INIT_ONSTACK(name) \
 	({ init_waitqueue_head(&name); name; })
 # define DECLARE_WAIT_QUEUE_HEAD_ONSTACK(name) \
-	wait_queue_head_t name = __WAIT_QUEUE_HEAD_INIT_ONSTACK(name)
+	struct wait_queue_head name = __WAIT_QUEUE_HEAD_INIT_ONSTACK(name)
 #else
 # define DECLARE_WAIT_QUEUE_HEAD_ONSTACK(name) DECLARE_WAIT_QUEUE_HEAD(name)
 #endif
 
-static inline void init_waitqueue_entry(wait_queue_t *q, struct task_struct *p)
+static inline void init_waitqueue_entry(struct wait_queue_entry *wq_entry, struct task_struct *p)
 {
-	q->flags	= 0;
-	q->private	= p;
-	q->func		= default_wake_function;
+	wq_entry->flags		= 0;
+	wq_entry->private	= p;
+	wq_entry->func		= default_wake_function;
 }
 
 static inline void
-init_waitqueue_func_entry(wait_queue_t *q, wait_queue_func_t func)
+init_waitqueue_func_entry(struct wait_queue_entry *wq_entry, wait_queue_func_t func)
 {
-	q->flags	= 0;
-	q->private	= NULL;
-	q->func		= func;
+	wq_entry->flags		= 0;
+	wq_entry->private	= NULL;
+	wq_entry->func		= func;
 }
 
 /**
  * waitqueue_active -- locklessly test for waiters on the queue
- * @q: the waitqueue to test for waiters
+ * @wq_head: the waitqueue to test for waiters
  *
  * returns true if the wait list is not empty
  *
  * NOTE: this function is lockless and requires care, incorrect usage _will_
  * lead to sporadic and non-obvious failure.
  *
- * Use either while holding wait_queue_head_t::lock or when used for wakeups
+ * Use either while holding wait_queue_head::lock or when used for wakeups
  * with an extra smp_mb() like:
  *
  *      CPU0 - waker                    CPU1 - waiter
  *
  *                                      for (;;) {
- *      @cond = true;                     prepare_to_wait(&wq, &wait, state);
+ *      @cond = true;                     prepare_to_wait(&wq_head, &wait, state);
  *      smp_mb();                         // smp_mb() from set_current_state()
- *      if (waitqueue_active(wq))         if (@cond)
- *        wake_up(wq);                      break;
+ *      if (waitqueue_active(wq_head))         if (@cond)
+ *        wake_up(wq_head);                      break;
  *                                        schedule();
  *                                      }
- *                                      finish_wait(&wq, &wait);
+ *                                      finish_wait(&wq_head, &wait);
  *
  * Because without the explicit smp_mb() it's possible for the
  * waitqueue_active() load to get hoisted over the @cond store such that we'll
···
  * Also note that this 'optimization' trades a spin_lock() for an smp_mb(),
  * which (when the lock is uncontended) are of roughly equal cost.
  */
-static inline int waitqueue_active(wait_queue_head_t *q)
+static inline int waitqueue_active(struct wait_queue_head *wq_head)
 {
-	return !list_empty(&q->task_list);
+	return !list_empty(&wq_head->head);
 }
 
 /**
  * wq_has_sleeper - check if there are any waiting processes
- * @wq: wait queue head
+ * @wq_head: wait queue head
  *
- * Returns true if wq has waiting processes
+ * Returns true if wq_head has waiting processes
  *
  * Please refer to the comment for waitqueue_active.
  */
-static inline bool wq_has_sleeper(wait_queue_head_t *wq)
+static inline bool wq_has_sleeper(struct wait_queue_head *wq_head)
 {
 	/*
 	 * We need to be sure we are in sync with the
···
 	 * waiting side.
 	 */
 	smp_mb();
-	return waitqueue_active(wq);
+	return waitqueue_active(wq_head);
 }
 
-extern void add_wait_queue(wait_queue_head_t *q, wait_queue_t *wait);
-extern void add_wait_queue_exclusive(wait_queue_head_t *q, wait_queue_t *wait);
-extern void remove_wait_queue(wait_queue_head_t *q, wait_queue_t *wait);
+extern void add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry);
+extern void add_wait_queue_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry);
+extern void remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry);
 
-static inline void __add_wait_queue(wait_queue_head_t *head, wait_queue_t *new)
+static inline void __add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
 {
-	list_add(&new->task_list, &head->task_list);
+	list_add(&wq_entry->entry, &wq_head->head);
 }
 
 /*
  * Used for wake-one threads:
  */
 static inline void
-__add_wait_queue_exclusive(wait_queue_head_t *q, wait_queue_t *wait)
+__add_wait_queue_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
 {
-	wait->flags |= WQ_FLAG_EXCLUSIVE;
-	__add_wait_queue(q, wait);
+	wq_entry->flags |= WQ_FLAG_EXCLUSIVE;
+	__add_wait_queue(wq_head, wq_entry);
 }
 
-static inline void __add_wait_queue_tail(wait_queue_head_t *head,
-					 wait_queue_t *new)
+static inline void __add_wait_queue_entry_tail(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
 {
-	list_add_tail(&new->task_list, &head->task_list);
-}
-
-static inline void
-__add_wait_queue_tail_exclusive(wait_queue_head_t *q, wait_queue_t *wait)
-{
-	wait->flags |= WQ_FLAG_EXCLUSIVE;
-	__add_wait_queue_tail(q, wait);
+	list_add_tail(&wq_entry->entry, &wq_head->head);
 }
 
 static inline void
-__remove_wait_queue(wait_queue_head_t *head, wait_queue_t *old)
+__add_wait_queue_entry_tail_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
 {
-	list_del(&old->task_list);
+	wq_entry->flags |= WQ_FLAG_EXCLUSIVE;
+	__add_wait_queue_entry_tail(wq_head, wq_entry);
 }
 
-typedef int wait_bit_action_f(struct wait_bit_key *, int mode);
-void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key);
-void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key);
-void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr, void *key);
-void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr);
-void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr);
-void __wake_up_bit(wait_queue_head_t *, void *, int);
-int __wait_on_bit(wait_queue_head_t *, struct wait_bit_queue *, wait_bit_action_f *, unsigned);
-int __wait_on_bit_lock(wait_queue_head_t *, struct wait_bit_queue *, wait_bit_action_f *, unsigned);
-void wake_up_bit(void *, int);
-void wake_up_atomic_t(atomic_t *);
-int out_of_line_wait_on_bit(void *, int, wait_bit_action_f *, unsigned);
-int out_of_line_wait_on_bit_timeout(void *, int, wait_bit_action_f *, unsigned, unsigned long);
-int out_of_line_wait_on_bit_lock(void *, int, wait_bit_action_f *, unsigned);
-int out_of_line_wait_on_atomic_t(atomic_t *, int (*)(atomic_t *), unsigned);
-wait_queue_head_t *bit_waitqueue(void *, int);
+static inline void
+__remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
+{
+	list_del(&wq_entry->entry);
+}
+
+void __wake_up(struct wait_queue_head *wq_head, unsigned int mode, int nr, void *key);
+void __wake_up_locked_key(struct wait_queue_head *wq_head, unsigned int mode, void *key);
+void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode, int nr, void *key);
+void __wake_up_locked(struct wait_queue_head *wq_head, unsigned int mode, int nr);
+void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode, int nr);
 
 #define wake_up(x)			__wake_up(x, TASK_NORMAL, 1, NULL)
 #define wake_up_nr(x, nr)		__wake_up(x, TASK_NORMAL, nr, NULL)
···
 /*
  * Wakeup macros to be used to report events to the targets.
  */
-#define wake_up_poll(x, m)						\
+#define wake_up_poll(x, m)							\
 	__wake_up(x, TASK_NORMAL, 1, (void *) (m))
-#define wake_up_locked_poll(x, m)					\
+#define wake_up_locked_poll(x, m)						\
 	__wake_up_locked_key((x), TASK_NORMAL, (void *) (m))
-#define wake_up_interruptible_poll(x, m)				\
+#define wake_up_interruptible_poll(x, m)					\
 	__wake_up(x, TASK_INTERRUPTIBLE, 1, (void *) (m))
-#define wake_up_interruptible_sync_poll(x, m)				\
+#define wake_up_interruptible_sync_poll(x, m)					\
 	__wake_up_sync_key((x), TASK_INTERRUPTIBLE, 1, (void *) (m))
 
-#define ___wait_cond_timeout(condition)					\
-({									\
-	bool __cond = (condition);					\
-	if (__cond && !__ret)						\
-		__ret = 1;						\
-	__cond || !__ret;						\
+#define ___wait_cond_timeout(condition)						\
+({										\
+	bool __cond = (condition);						\
+	if (__cond && !__ret)							\
+		__ret = 1;							\
+	__cond || !__ret;							\
 })
 
-#define ___wait_is_interruptible(state)					\
-	(!__builtin_constant_p(state) ||				\
-		state == TASK_INTERRUPTIBLE || state == TASK_KILLABLE)	\
+#define ___wait_is_interruptible(state)						\
+	(!__builtin_constant_p(state) ||					\
+		state == TASK_INTERRUPTIBLE || state == TASK_KILLABLE)		\
 
-extern void init_wait_entry(wait_queue_t *__wait, int flags);
+extern void init_wait_entry(struct wait_queue_entry *wq_entry, int flags);
 
 /*
  * The below macro ___wait_event() has an explicit shadow of the __ret
···
  * otherwise.
  */
 
-#define ___wait_event(wq, condition, state, exclusive, ret, cmd)	\
-({									\
-	__label__ __out;						\
-	wait_queue_t __wait;						\
-	long __ret = ret;	/* explicit shadow */			\
-									\
-	init_wait_entry(&__wait, exclusive ? WQ_FLAG_EXCLUSIVE : 0);	\
-	for (;;) {							\
-		long __int = prepare_to_wait_event(&wq, &__wait, state);\
-									\
-		if (condition)						\
-			break;						\
-									\
-		if (___wait_is_interruptible(state) && __int) {		\
-			__ret = __int;					\
-			goto __out;					\
-		}							\
-									\
-		cmd;							\
-	}								\
-	finish_wait(&wq, &__wait);					\
-__out:	__ret;								\
+#define ___wait_event(wq_head, condition, state, exclusive, ret, cmd)		\
+({										\
+	__label__ __out;							\
+	struct wait_queue_entry __wq_entry;					\
+	long __ret = ret;	/* explicit shadow */				\
+										\
+	init_wait_entry(&__wq_entry, exclusive ? WQ_FLAG_EXCLUSIVE : 0);	\
+	for (;;) {								\
+		long __int = prepare_to_wait_event(&wq_head, &__wq_entry, state);\
+										\
+		if (condition)							\
+			break;							\
+										\
+		if (___wait_is_interruptible(state) && __int) {			\
+			__ret = __int;						\
+			goto __out;						\
+		}								\
+										\
+		cmd;								\
+	}									\
+	finish_wait(&wq_head, &__wq_entry);					\
+__out:	__ret;									\
 })
 
-#define __wait_event(wq, condition)					\
-	(void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, 0,	\
+#define __wait_event(wq_head, condition)					\
+	(void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0,	\
 			    schedule())
 
 /**
  * wait_event - sleep until a condition gets true
- * @wq: the waitqueue to wait on
+ * @wq_head: the waitqueue to wait on
  * @condition: a C expression for the event to wait for
  *
  * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the
  * @condition evaluates to true. The @condition is checked each time
- * the waitqueue @wq is woken up.
+ * the waitqueue @wq_head is woken up.
  *
  * wake_up() has to be called after changing any variable that could
  * change the result of the wait condition.
  */
-#define wait_event(wq, condition)					\
-do {									\
-	might_sleep();							\
-	if (condition)							\
-		break;							\
-	__wait_event(wq, condition);					\
+#define wait_event(wq_head, condition)						\
+do {										\
+	might_sleep();								\
+	if (condition)								\
+		break;								\
+	__wait_event(wq_head, condition);					\
 } while (0)
 
-#define __io_wait_event(wq, condition)					\
-	(void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, 0,	\
+#define __io_wait_event(wq_head, condition)					\
+	(void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0,	\
 			    io_schedule())
 
 /*
  * io_wait_event() -- like wait_event() but with io_schedule()
  */
-#define io_wait_event(wq, condition)					\
-do {									\
-	might_sleep();							\
-	if (condition)							\
-		break;							\
-	__io_wait_event(wq, condition);					\
+#define io_wait_event(wq_head, condition)					\
+do {										\
+	might_sleep();								\
+	if (condition)								\
+		break;								\
+	__io_wait_event(wq_head, condition);					\
 } while (0)
 
-#define __wait_event_freezable(wq, condition)				\
-	___wait_event(wq, condition, TASK_INTERRUPTIBLE, 0, 0,		\
+#define __wait_event_freezable(wq_head, condition)				\
+	___wait_event(wq_head, condition, TASK_INTERRUPTIBLE, 0, 0,		\
 			    schedule(); try_to_freeze())
 
 /**
  * wait_event_freezable - sleep (or freeze) until a condition gets true
- * @wq: the waitqueue to wait on
+ * @wq_head: the waitqueue to wait on
  * @condition: a C expression for the event to wait for
  *
  * The process is put to sleep (TASK_INTERRUPTIBLE -- so as not to contribute
  * to system load) until the @condition evaluates to true. The
- * @condition is checked each time the waitqueue @wq is woken up.
+ * @condition is checked each time the waitqueue @wq_head is woken up.
  *
  * wake_up() has to be called after changing any variable that could
  * change the result of the wait condition.
  */
-#define wait_event_freezable(wq, condition)				\
-({									\
-	int __ret = 0;							\
-	might_sleep();							\
-	if (!(condition))						\
-		__ret = __wait_event_freezable(wq, condition);		\
-	__ret;								\
+#define wait_event_freezable(wq_head, condition)				\
+({										\
+	int __ret = 0;								\
+	might_sleep();								\
+	if (!(condition))							\
+		__ret = __wait_event_freezable(wq_head, condition);		\
+	__ret;									\
 })
 
-#define __wait_event_timeout(wq, condition, timeout)			\
-	___wait_event(wq, ___wait_cond_timeout(condition),		\
-		      TASK_UNINTERRUPTIBLE, 0, timeout,			\
+#define __wait_event_timeout(wq_head, condition, timeout)			\
+	___wait_event(wq_head, ___wait_cond_timeout(condition),			\
+		      TASK_UNINTERRUPTIBLE, 0, timeout,				\
 		      __ret = schedule_timeout(__ret))
 
 /**
  * wait_event_timeout - sleep until a condition gets true or a timeout elapses
- * @wq: the waitqueue to wait on
+ * @wq_head: the waitqueue to wait on
  * @condition: a C expression for the event to wait for
  * @timeout: timeout, in jiffies
  *
  * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the
  * @condition evaluates to true. The @condition is checked each time
- * the waitqueue @wq is woken up.
+ * the waitqueue @wq_head is woken up.
  *
  * wake_up() has to be called after changing any variable that could
  * change the result of the wait condition.
···
  * or the remaining jiffies (at least 1) if the @condition evaluated
  * to %true before the @timeout elapsed.
  */
-#define wait_event_timeout(wq, condition, timeout)			\
-({									\
-	long __ret = timeout;						\
-	might_sleep();							\
-	if (!___wait_cond_timeout(condition))				\
-		__ret = __wait_event_timeout(wq, condition, timeout);	\
-	__ret;								\
+#define wait_event_timeout(wq_head, condition, timeout)				\
+({										\
+	long __ret = timeout;							\
+	might_sleep();								\
+	if (!___wait_cond_timeout(condition))					\
+		__ret = __wait_event_timeout(wq_head, condition, timeout);	\
+	__ret;									\
 })
 
-#define __wait_event_freezable_timeout(wq, condition, timeout)		\
-	___wait_event(wq, ___wait_cond_timeout(condition),		\
-		      TASK_INTERRUPTIBLE, 0, timeout,			\
+#define __wait_event_freezable_timeout(wq_head, condition, timeout)		\
+	___wait_event(wq_head, ___wait_cond_timeout(condition),			\
+		      TASK_INTERRUPTIBLE, 0, timeout,				\
 		      __ret = schedule_timeout(__ret); try_to_freeze())
 
 /*
  * like wait_event_timeout() -- except it uses TASK_INTERRUPTIBLE to avoid
  * increasing load and is freezable.
  */
-#define wait_event_freezable_timeout(wq, condition, timeout)		\
-({									\
-	long __ret = timeout;						\
-	might_sleep();							\
-	if (!___wait_cond_timeout(condition))				\
-		__ret = __wait_event_freezable_timeout(wq, condition, timeout);	\
-	__ret;								\
+#define wait_event_freezable_timeout(wq_head, condition, timeout)		\
+({										\
+	long __ret = timeout;							\
+	might_sleep();								\
+	if (!___wait_cond_timeout(condition))					\
+		__ret = __wait_event_freezable_timeout(wq_head, condition, timeout); \
+	__ret;									\
 })
 
-#define __wait_event_exclusive_cmd(wq, condition, cmd1, cmd2)		\
-	(void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 1, 0,	\
+#define __wait_event_exclusive_cmd(wq_head, condition, cmd1, cmd2)		\
+	(void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 1, 0,	\
 			    cmd1; schedule(); cmd2)
 /*
  * Just like wait_event_cmd(), except it sets exclusive flag
  */
-#define wait_event_exclusive_cmd(wq, condition, cmd1, cmd2)		\
-do {									\
-	if (condition)							\
-		break;							\
-	__wait_event_exclusive_cmd(wq, condition, cmd1, cmd2);		\
+#define wait_event_exclusive_cmd(wq_head, condition, cmd1, cmd2)		\
+do {										\
+	if (condition)								\
+		break;								\
+	__wait_event_exclusive_cmd(wq_head, condition, cmd1, cmd2);		\
 } while (0)
 
-#define __wait_event_cmd(wq, condition, cmd1, cmd2)			\
-	(void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, 0,	\
+#define __wait_event_cmd(wq_head, condition, cmd1, cmd2)			\
+	(void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0,	\
 			    cmd1; schedule(); cmd2)
 
 /**
  * wait_event_cmd - sleep until a condition gets true
- * @wq: the waitqueue to wait on
+ * @wq_head: the waitqueue to wait on
  * @condition: a C expression for the event to wait for
  * @cmd1: the command will be executed before sleep
  * @cmd2: the command will be executed after sleep
  *
  * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the
  * @condition evaluates to true. The @condition is checked each time
- * the waitqueue @wq is woken up.
+ * the waitqueue @wq_head is woken up.
  *
  * wake_up() has to be called after changing any variable that could
  * change the result of the wait condition.
  */
-#define wait_event_cmd(wq, condition, cmd1, cmd2)			\
-do {									\
-	if (condition)							\
-		break;							\
-	__wait_event_cmd(wq, condition, cmd1, cmd2);			\
+#define wait_event_cmd(wq_head, condition, cmd1, cmd2)				\
+do {										\
+	if (condition)								\
+		break;								\
+	__wait_event_cmd(wq_head, condition, cmd1, cmd2);			\
 } while (0)
 
-#define __wait_event_interruptible(wq, condition)			\
-	___wait_event(wq, condition, TASK_INTERRUPTIBLE, 0, 0,		\
+#define __wait_event_interruptible(wq_head, condition)				\
+	___wait_event(wq_head, condition, TASK_INTERRUPTIBLE, 0, 0,		\
 		      schedule())
 
 /**
  * wait_event_interruptible - sleep until a condition gets true
- * @wq: the waitqueue to wait on
+ * @wq_head: the waitqueue to wait on
  * @condition: a C expression for the event to wait for
  *
  * The process is put to sleep (TASK_INTERRUPTIBLE) until the
  * @condition evaluates to true or a signal is received.
- * The @condition is checked each time the waitqueue @wq is woken up.
+ * The @condition is checked each time the waitqueue @wq_head is woken up.
  *
  * wake_up() has to be called after changing any variable that could
  * change the result of the wait condition.
···
  * The function will return -ERESTARTSYS if it was interrupted by a
  * signal and 0 if @condition evaluated to true.
  */
-#define wait_event_interruptible(wq, condition)				\
-({									\
-	int __ret = 0;							\
-	might_sleep();							\
-	if (!(condition))						\
-		__ret = __wait_event_interruptible(wq, condition);	\
-	__ret;								\
+#define wait_event_interruptible(wq_head, condition)				\
+({										\
+	int __ret = 0;								\
+	might_sleep();								\
+	if (!(condition))							\
+		__ret = __wait_event_interruptible(wq_head, condition);		\
+	__ret;									\
 })
 
-#define __wait_event_interruptible_timeout(wq, condition, timeout)	\
-	___wait_event(wq, ___wait_cond_timeout(condition),		\
-		      TASK_INTERRUPTIBLE, 0, timeout,			\
+#define __wait_event_interruptible_timeout(wq_head, condition, timeout)		\
+	___wait_event(wq_head, ___wait_cond_timeout(condition),			\
+		      TASK_INTERRUPTIBLE, 0, timeout,				\
 		      __ret = schedule_timeout(__ret))
 
 /**
  * wait_event_interruptible_timeout - sleep until a condition gets true or a timeout elapses
- * @wq: the waitqueue to wait on
+ * @wq_head: the waitqueue to wait on
  * @condition: a C expression for the event to wait for
  * @timeout: timeout, in jiffies
  *
  * The process is put to sleep (TASK_INTERRUPTIBLE) until the
  * @condition evaluates to true or a signal is received.
- * The @condition is checked each time the waitqueue @wq is woken up.
+ * The @condition is checked each time the waitqueue @wq_head is woken up.
  *
  * wake_up() has to be called after changing any variable that could
  * change the result of the wait condition.
···
  * to %true before the @timeout elapsed, or -%ERESTARTSYS if it was
  * interrupted by a signal.
  */
-#define wait_event_interruptible_timeout(wq, condition, timeout)	\
-({									\
-	long __ret = timeout;						\
-	might_sleep();							\
-	if (!___wait_cond_timeout(condition))				\
-		__ret = __wait_event_interruptible_timeout(wq,		\
-						condition, timeout);	\
-	__ret;								\
+#define wait_event_interruptible_timeout(wq_head, condition, timeout)		\
+({										\
+	long __ret = timeout;							\
+	might_sleep();								\
+	if (!___wait_cond_timeout(condition))					\
+		__ret = __wait_event_interruptible_timeout(wq_head,		\
+						condition, timeout);		\
+	__ret;									\
 })
 
-#define __wait_event_hrtimeout(wq, condition, timeout, state)		\
-({									\
-	int __ret = 0;							\
-	struct hrtimer_sleeper __t;					\
-									\
-	hrtimer_init_on_stack(&__t.timer, CLOCK_MONOTONIC,		\
-			      HRTIMER_MODE_REL);			\
-	hrtimer_init_sleeper(&__t, current);				\
-	if ((timeout) != KTIME_MAX)				\
-		hrtimer_start_range_ns(&__t.timer, timeout,		\
-				       current->timer_slack_ns,		\
-				       HRTIMER_MODE_REL);		\
-									\
-	__ret = ___wait_event(wq, condition, state, 0, 0,		\
-		if (!__t.task) {					\
-			__ret = -ETIME;					\
-			break;						\
-		}							\
-		schedule());						\
-									\
-	hrtimer_cancel(&__t.timer);					\
-	destroy_hrtimer_on_stack(&__t.timer);				\
-	__ret;								\
+#define __wait_event_hrtimeout(wq_head, condition, timeout, state)		\
+({										\
+	int __ret = 0;								\
+	struct hrtimer_sleeper __t;						\
+										\
+	hrtimer_init_on_stack(&__t.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);	\
+	hrtimer_init_sleeper(&__t, current);					\
+	if ((timeout) != KTIME_MAX)						\
+		hrtimer_start_range_ns(&__t.timer, timeout,			\
+				       current->timer_slack_ns,			\
+				       HRTIMER_MODE_REL);			\
+										\
+	__ret = ___wait_event(wq_head, condition, state, 0, 0,			\
+		if (!__t.task) {						\
+			__ret = -ETIME;						\
+			break;							\
+		}								\
+		schedule());							\
+										\
+	hrtimer_cancel(&__t.timer);						\
+	destroy_hrtimer_on_stack(&__t.timer);					\
+	__ret;									\
 })
 
 /**
  * wait_event_hrtimeout - sleep until a condition gets true or a timeout elapses
- * @wq: the waitqueue to wait on
+ * @wq_head: the waitqueue to wait on
  * @condition: a C expression for the event to wait for
  * @timeout: timeout, as a ktime_t
  *
  * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the
  * @condition evaluates to true or a signal is received.
- * The @condition is checked each time the waitqueue @wq is woken up.
+ * The @condition is checked each time the waitqueue @wq_head is woken up.
  *
  * wake_up() has to be called after changing any variable that could
  * change the result of the wait condition.
···
  * The function returns 0 if @condition became true, or -ETIME if the timeout
  * elapsed.
  */
-#define wait_event_hrtimeout(wq, condition, timeout)			\
-({									\
-	int __ret = 0;							\
-	might_sleep();							\
-	if (!(condition))						\
-		__ret = __wait_event_hrtimeout(wq, condition, timeout,	\
-					       TASK_UNINTERRUPTIBLE);	\
-	__ret;								\
+#define wait_event_hrtimeout(wq_head, condition, timeout)			\
+({										\
+	int __ret = 0;								\
+	might_sleep();								\
+	if (!(condition))							\
+		__ret = __wait_event_hrtimeout(wq_head, condition, timeout,	\
+					       TASK_UNINTERRUPTIBLE);		\
+	__ret;									\
 })
 
 /**
  * wait_event_interruptible_hrtimeout - sleep until a condition gets true or a timeout elapses
- * @wq: the waitqueue to wait on
+ * @wq_head: the waitqueue to wait on
  * @condition: a C expression for the event to wait for
  * @timeout: timeout, as a ktime_t
  *
  * The process is put to sleep (TASK_INTERRUPTIBLE) until the
  * @condition evaluates to true or a signal is received.
- * The @condition is checked each time the waitqueue @wq is woken up.
+ * The @condition is checked each time the waitqueue @wq_head is woken up.
  *
  * wake_up() has to be called after changing any variable that could
  * change the result of the wait condition.
···
  * The function returns 0 if @condition became true, -ERESTARTSYS if it was
  * interrupted by a signal, or -ETIME if the timeout elapsed.
  */
-#define wait_event_interruptible_hrtimeout(wq, condition, timeout)	\
-({									\
-	long __ret = 0;							\
-	might_sleep();							\
-	if (!(condition))						\
-		__ret = __wait_event_hrtimeout(wq, condition, timeout,	\
-					       TASK_INTERRUPTIBLE);	\
-	__ret;								\
+#define wait_event_interruptible_hrtimeout(wq, condition, timeout)		\
+({										\
+	long __ret = 0;								\
+	might_sleep();								\
+	if (!(condition))							\
+		__ret = __wait_event_hrtimeout(wq, condition, timeout,		\
+					       TASK_INTERRUPTIBLE);		\
+	__ret;									\
 })
 
-#define __wait_event_interruptible_exclusive(wq, condition)		\
-	___wait_event(wq, condition, TASK_INTERRUPTIBLE, 1, 0,		\
+#define __wait_event_interruptible_exclusive(wq, condition)			\
+	___wait_event(wq, condition, TASK_INTERRUPTIBLE, 1, 0,			\
 		      schedule())
 
-#define wait_event_interruptible_exclusive(wq, condition)		\
-({									\
-	int __ret = 0;							\
-	might_sleep();							\
-	if (!(condition))						\
-		__ret = __wait_event_interruptible_exclusive(wq, condition);\
-	__ret;								\
+#define wait_event_interruptible_exclusive(wq, condition)			\
+({										\
+	int __ret = 0;								\
+	might_sleep();								\
+	if (!(condition))							\
+		__ret = __wait_event_interruptible_exclusive(wq, condition);	\
+	__ret;									\
 })
 
-#define __wait_event_killable_exclusive(wq, condition)			\
-	___wait_event(wq, condition, TASK_KILLABLE, 1, 0,		\
+#define __wait_event_killable_exclusive(wq, condition)				\
+	___wait_event(wq, condition, TASK_KILLABLE, 1, 0,			\
 		      schedule())
 
-#define wait_event_killable_exclusive(wq, condition)			\
-({									\
-	int __ret = 0;							\
-	might_sleep();							\
-	if (!(condition))						\
-		__ret = __wait_event_killable_exclusive(wq, condition);	\
-	__ret;								\
+#define wait_event_killable_exclusive(wq, condition)				\
+({										\
+	int __ret = 0;								\
+	might_sleep();								\
+	if (!(condition))							\
+		__ret = __wait_event_killable_exclusive(wq, condition);		\
+	__ret;									\
 })
 
 
-#define __wait_event_freezable_exclusive(wq, condition)			\
-	___wait_event(wq, condition, TASK_INTERRUPTIBLE, 1, 0,		\
+#define __wait_event_freezable_exclusive(wq, condition)				\
+	___wait_event(wq, condition, TASK_INTERRUPTIBLE, 1, 0,			\
 			schedule(); try_to_freeze())
 
-#define wait_event_freezable_exclusive(wq, condition)			\
-({									\
-	int __ret = 0;							\
-	might_sleep();							\
-	if (!(condition))						\
-		__ret = __wait_event_freezable_exclusive(wq, condition);\
-	__ret;								\
+#define wait_event_freezable_exclusive(wq, condition)				\
+({										\
+	int __ret = 0;								\
+	might_sleep();								\
+	if (!(condition))							\
+		__ret = __wait_event_freezable_exclusive(wq, condition);	\
+	__ret;									\
 })
 
-extern int do_wait_intr(wait_queue_head_t *, wait_queue_t *);
-extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_t *);
+extern int do_wait_intr(wait_queue_head_t *, wait_queue_entry_t *);
+extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_entry_t *);
 
-#define __wait_event_interruptible_locked(wq, condition, exclusive, fn) \
-({									\
-	int __ret;							\
-	DEFINE_WAIT(__wait);						\
-	if (exclusive)							\
-		__wait.flags |= WQ_FLAG_EXCLUSIVE;			\
-	do {								\
-		__ret = fn(&(wq), &__wait);				\
-		if (__ret)						\
-			break;						\
-	} while (!(condition));						\
-	__remove_wait_queue(&(wq), &__wait);				\
-	__set_current_state(TASK_RUNNING);				\
-	__ret;								\
+#define __wait_event_interruptible_locked(wq, condition, exclusive, fn)		\
+({										\
+	int __ret;								\
+	DEFINE_WAIT(__wait);							\
+	if (exclusive)								\
+		__wait.flags |= WQ_FLAG_EXCLUSIVE;				\
+	do {									\
+		__ret = fn(&(wq), &__wait);					\
+		if (__ret)							\
+			break;							\
+	} while (!(condition));							\
+	__remove_wait_queue(&(wq), &__wait);					\
+	__set_current_state(TASK_RUNNING);					\
+	__ret;									\
 })
 
 
···
  * The function will return -ERESTARTSYS if it was interrupted by a
  * signal and 0 if @condition evaluated to true.
  */
-#define wait_event_interruptible_locked(wq, condition)			\
-	((condition)							\
+#define wait_event_interruptible_locked(wq, condition)				\
+	((condition)								\
 	 ? 0 : __wait_event_interruptible_locked(wq, condition, 0, do_wait_intr))
 
 /**
···
  * The function will return -ERESTARTSYS if it was interrupted by a
  * signal and 0 if @condition evaluated to true.
  */
-#define wait_event_interruptible_locked_irq(wq, condition)		\
-	((condition)							\
+#define wait_event_interruptible_locked_irq(wq, condition)			\
+	((condition)								\
 	 ? 0 : __wait_event_interruptible_locked(wq, condition, 0, do_wait_intr_irq))
 
 /**
···
  * The function will return -ERESTARTSYS if it was interrupted by a
  * signal and 0 if @condition evaluated to true.
  */
-#define wait_event_interruptible_exclusive_locked(wq, condition)	\
-	((condition)							\
+#define wait_event_interruptible_exclusive_locked(wq, condition)		\
+	((condition)								\
 	 ? 0 : __wait_event_interruptible_locked(wq, condition, 1, do_wait_intr))
 
 /**
···
  * The function will return -ERESTARTSYS if it was interrupted by a
  * signal and 0 if @condition evaluated to true.
  */
-#define wait_event_interruptible_exclusive_locked_irq(wq, condition)	\
-	((condition)							\
+#define wait_event_interruptible_exclusive_locked_irq(wq, condition)		\
+	((condition)								\
 	 ? 0 : __wait_event_interruptible_locked(wq, condition, 1, do_wait_intr_irq))
 
 
-#define __wait_event_killable(wq, condition)				\
+#define __wait_event_killable(wq, condition)					\
 	___wait_event(wq, condition, TASK_KILLABLE, 0, 0, schedule())
 
 /**
···
  * The function will return -ERESTARTSYS if it was interrupted by a
  * signal and 0 if @condition evaluated to true.
  */
-#define wait_event_killable(wq, condition)				\
-({									\
-	int __ret = 0;							\
-	might_sleep();							\
-	if (!(condition))						\
-		__ret = __wait_event_killable(wq, condition);		\
-	__ret;								\
+#define wait_event_killable(wq_head, condition)					\
+({										\
+	int __ret = 0;								\
+	might_sleep();								\
+	if (!(condition))							\
+		__ret = __wait_event_killable(wq_head, condition);		\
+	__ret;									\
 })
 
 
-#define __wait_event_lock_irq(wq, condition, lock, cmd)			\
-	(void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, 0,	\
-			    spin_unlock_irq(&lock);			\
-			    cmd;					\
-			    schedule();					\
+#define __wait_event_lock_irq(wq_head, condition, lock, cmd)			\
+	(void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0,	\
+			    spin_unlock_irq(&lock);				\
+			    cmd;						\
+			    schedule();						\
 			    spin_lock_irq(&lock))
 
 /**
···
  *			     condition is checked under the lock. This
  *			     is expected to be called with the lock
  *			     taken.
- * @wq: the waitqueue to wait on
+ * @wq_head: the waitqueue to wait on
  * @condition: a C expression for the event to wait for
  * @lock: a locked spinlock_t, which will be released before cmd
  *	  and schedule() and reacquired afterwards.
···
  *
  * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the
  * @condition evaluates to true. The @condition is checked each time
- * the waitqueue @wq is woken up.
+ * the waitqueue @wq_head is woken up.
  *
  * wake_up() has to be called after changing any variable that could
  * change the result of the wait condition.
···
  * dropped before invoking the cmd and going to sleep and is reacquired
  * afterwards.
  */
-#define wait_event_lock_irq_cmd(wq, condition, lock, cmd)		\
-do {									\
-	if (condition)							\
-		break;							\
-	__wait_event_lock_irq(wq, condition, lock, cmd);		\
+#define wait_event_lock_irq_cmd(wq_head, condition, lock, cmd)			\
+do {										\
+	if (condition)								\
+		break;								\
+	__wait_event_lock_irq(wq_head, condition, lock, cmd);			\
 } while (0)
 
 /**
···
  *			 condition is checked under the lock. This
  *			 is expected to be called with the lock
  *			 taken.
- * @wq: the waitqueue to wait on
+ * @wq_head: the waitqueue to wait on
  * @condition: a C expression for the event to wait for
  * @lock: a locked spinlock_t, which will be released before schedule()
  *	  and reacquired afterwards.
  *
  * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the
  * @condition evaluates to true. The @condition is checked each time
- * the waitqueue @wq is woken up.
+ * the waitqueue @wq_head is woken up.
  *
  * wake_up() has to be called after changing any variable that could
  * change the result of the wait condition.
···
  * This is supposed to be called while holding the lock. The lock is
  * dropped before going to sleep and is reacquired afterwards.
  */
-#define wait_event_lock_irq(wq, condition, lock)			\
-do {									\
-	if (condition)							\
-		break;							\
-	__wait_event_lock_irq(wq, condition, lock, );			\
+#define wait_event_lock_irq(wq_head, condition, lock)				\
+do {										\
+	if (condition)								\
+		break;								\
+	__wait_event_lock_irq(wq_head, condition, lock, );			\
 } while (0)
 
 
-#define __wait_event_interruptible_lock_irq(wq, condition, lock, cmd)	\
-	___wait_event(wq, condition, TASK_INTERRUPTIBLE, 0, 0,		\
-		      spin_unlock_irq(&lock);				\
-		      cmd;						\
-		      schedule();					\
+#define __wait_event_interruptible_lock_irq(wq_head, condition, lock, cmd)	\
+	___wait_event(wq_head, condition, TASK_INTERRUPTIBLE, 0, 0,		\
+		      spin_unlock_irq(&lock);					\
+		      cmd;							\
+		      schedule();						\
 		      spin_lock_irq(&lock))
 
 /**
  * wait_event_interruptible_lock_irq_cmd - sleep until a condition gets true.
  *		The condition is checked under the lock. This is expected to
  *		be called with the lock taken.
- * @wq: the waitqueue to wait on
+ * @wq_head: the waitqueue to wait on
  * @condition: a C expression for the event to wait for
  * @lock: a locked spinlock_t, which will be released before cmd and
  *	  schedule() and reacquired afterwards.
···
  *
  * The process is put to sleep (TASK_INTERRUPTIBLE) until the
  * @condition evaluates to true or a signal is received. The @condition is
- * checked each time the waitqueue @wq is woken up.
+ * checked each time the waitqueue @wq_head is woken up.
  *
  * wake_up() has to be called after changing any variable that could
  * change the result of the wait condition.
···
  * The macro will return -ERESTARTSYS if it was interrupted by a signal
  * and 0 if @condition evaluated to true.
  */
-#define wait_event_interruptible_lock_irq_cmd(wq, condition, lock, cmd)	\
-({									\
-	int __ret = 0;							\
-	if (!(condition))						\
-		__ret = __wait_event_interruptible_lock_irq(wq,		\
-						condition, lock, cmd);	\
-	__ret;								\
+#define wait_event_interruptible_lock_irq_cmd(wq_head, condition, lock, cmd)	\
+({										\
+	int __ret = 0;								\
+	if (!(condition))							\
+		__ret = __wait_event_interruptible_lock_irq(wq_head,		\
+						condition, lock, cmd);		\
+	__ret;									\
 })
 
 /**
  * wait_event_interruptible_lock_irq - sleep until a condition gets true.
  *		The condition is checked under the lock. This is expected
  *		to be called with the lock taken.
- * @wq: the waitqueue to wait on
+ * @wq_head: the waitqueue to wait on
  * @condition: a C expression for the event to wait for
  * @lock: a locked spinlock_t, which will be released before schedule()
  *	  and reacquired afterwards.
  *
  * The process is put to sleep (TASK_INTERRUPTIBLE) until the
  * @condition evaluates to true or signal is received. The @condition is
- * checked each time the waitqueue @wq is woken up.
+ * checked each time the waitqueue @wq_head is woken up.
  *
  * wake_up() has to be called after changing any variable that could
  * change the result of the wait condition.
···
  * The macro will return -ERESTARTSYS if it was interrupted by a signal
  * and 0 if @condition evaluated to true.
  */
-#define wait_event_interruptible_lock_irq(wq, condition, lock)		\
-({									\
-	int __ret = 0;							\
-	if (!(condition))						\
-		__ret = __wait_event_interruptible_lock_irq(wq,		\
-						condition, lock,);	\
-	__ret;								\
+#define wait_event_interruptible_lock_irq(wq_head, condition, lock)		\
+({										\
+	int __ret = 0;								\
+	if (!(condition))							\
+		__ret = __wait_event_interruptible_lock_irq(wq_head,		\
+						condition, lock,);		\
+	__ret;									\
 })
 
-#define __wait_event_interruptible_lock_irq_timeout(wq, condition,	\
-						    lock, timeout)	\
-	___wait_event(wq, ___wait_cond_timeout(condition),		\
-		      TASK_INTERRUPTIBLE, 0, timeout,			\
-		      spin_unlock_irq(&lock);				\
-		      __ret = schedule_timeout(__ret);			\
+#define __wait_event_interruptible_lock_irq_timeout(wq_head, condition,		\
+						    lock, timeout)		\
+	___wait_event(wq_head, ___wait_cond_timeout(condition),			\
+		      TASK_INTERRUPTIBLE, 0, timeout,				\
+		      spin_unlock_irq(&lock);					\
+		      __ret = schedule_timeout(__ret);				\
 		      spin_lock_irq(&lock));
 
 /**
  * wait_event_interruptible_lock_irq_timeout - sleep until a condition gets
  *		true or a timeout elapses. The condition is checked under
  *		the lock. This is expected to be called with the lock taken.
- * @wq: the waitqueue to wait on
+ * @wq_head: the waitqueue to wait on
  * @condition: a C expression for the event to wait for
  * @lock: a locked spinlock_t, which will be released before schedule()
  *	  and reacquired afterwards.
···
  *
  * The process is put to sleep (TASK_INTERRUPTIBLE) until the
  * @condition evaluates to true or signal is received. The @condition is
- * checked each time the waitqueue @wq is woken up.
+ * checked each time the waitqueue @wq_head is woken up.
  *
  * wake_up() has to be called after changing any variable that could
  * change the result of the wait condition.
···
  * was interrupted by a signal, and the remaining jiffies otherwise
  * if the condition evaluated to true before the timeout elapsed.
  */
-#define wait_event_interruptible_lock_irq_timeout(wq, condition, lock,	\
-						  timeout)		\
-({									\
-	long __ret = timeout;						\
-	if (!___wait_cond_timeout(condition))				\
-		__ret = __wait_event_interruptible_lock_irq_timeout(	\
-					wq, condition, lock, timeout);	\
-	__ret;								\
+#define wait_event_interruptible_lock_irq_timeout(wq_head, condition, lock,	\
+						  timeout)			\
+({										\
+	long __ret = timeout;							\
+	if (!___wait_cond_timeout(condition))					\
+		__ret = __wait_event_interruptible_lock_irq_timeout(		\
+					wq_head, condition, lock, timeout);	\
+	__ret;									\
 })
 
 /*
  * Waitqueues which are removed from the waitqueue_head at wakeup time
  */
-void prepare_to_wait(wait_queue_head_t *q, wait_queue_t *wait, int state);
-void prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int state);
-long prepare_to_wait_event(wait_queue_head_t *q, wait_queue_t *wait, int state);
-void finish_wait(wait_queue_head_t *q, wait_queue_t *wait);
-long wait_woken(wait_queue_t *wait, unsigned mode, long timeout);
-int woken_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
-int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
-int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
+void prepare_to_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state);
+void prepare_to_wait_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state);
+long prepare_to_wait_event(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state);
+void finish_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry);
+long wait_woken(struct wait_queue_entry *wq_entry, unsigned mode, long timeout);
+int woken_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key);
+int autoremove_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key);
 
-#define DEFINE_WAIT_FUNC(name, function)				\
-	wait_queue_t name = {						\
-		.private	= current,				\
-		.func		= function,				\
-		.task_list	= LIST_HEAD_INIT((name).task_list),	\
+#define DEFINE_WAIT_FUNC(name, function)					\
+	struct wait_queue_entry name = {					\
+		.private	= current,					\
+		.func		= function,					\
+		.entry		= LIST_HEAD_INIT((name).entry),			\
 	}
 
 #define DEFINE_WAIT(name) DEFINE_WAIT_FUNC(name, autoremove_wake_function)
 
-#define DEFINE_WAIT_BIT(name, word, bit)				\
-	struct wait_bit_queue name = {					\
-		.key = __WAIT_BIT_KEY_INITIALIZER(word, bit),		\
-		.wait	= {						\
-			.private	= current,			\
-			.func		= wake_bit_function,		\
-			.task_list	=				\
-				LIST_HEAD_INIT((name).wait.task_list),	\
-		},							\
-	}
-
-#define init_wait(wait)							\
-	do {								\
-		(wait)->private = current;				\
-		(wait)->func = autoremove_wake_function;		\
-		INIT_LIST_HEAD(&(wait)->task_list);			\
-		(wait)->flags = 0;					\
+#define init_wait(wait)								\
+	do {									\
+		(wait)->private = current;					\
+		(wait)->func = autoremove_wake_function;			\
+		INIT_LIST_HEAD(&(wait)->entry);					\
+		(wait)->flags = 0;						\
 	} while (0)
-
-
-extern int bit_wait(struct wait_bit_key *, int);
-extern int bit_wait_io(struct wait_bit_key *, int);
-extern int bit_wait_timeout(struct wait_bit_key *, int);
-extern int bit_wait_io_timeout(struct wait_bit_key *, int);
-
-/**
- * wait_on_bit - wait for a bit to be cleared
- * @word: the word being waited on, a kernel virtual address
- * @bit: the bit of the word being waited on
- * @mode: the task state to sleep in
- *
- * There is a standard hashed waitqueue table for generic use. This
- * is the part of the hashtable's accessor API that waits on a bit.
- * For instance, if one were to have waiters on a bitflag, one would
- * call wait_on_bit() in threads waiting for the bit to clear.
- * One uses wait_on_bit() where one is waiting for the bit to clear,
- * but has no intention of setting it.
- * Returned value will be zero if the bit was cleared, or non-zero
- * if the process received a signal and the mode permitted wakeup
- * on that signal.
- */
-static inline int
-wait_on_bit(unsigned long *word, int bit, unsigned mode)
-{
-	might_sleep();
-	if (!test_bit(bit, word))
-		return 0;
-	return out_of_line_wait_on_bit(word, bit,
-				       bit_wait,
-				       mode);
-}
-
-/**
- * wait_on_bit_io - wait for a bit to be cleared
- * @word: the word being waited on, a kernel virtual address
- * @bit: the bit of the word being waited on
- * @mode: the task state to sleep in
- *
- * Use the standard hashed waitqueue table to wait for a bit
- * to be cleared.  This is similar to wait_on_bit(), but calls
- * io_schedule() instead of schedule() for the actual waiting.
- *
- * Returned value will be zero if the bit was cleared, or non-zero
- * if the process received a signal and the mode permitted wakeup
- * on that signal.
- */
-static inline int
-wait_on_bit_io(unsigned long *word, int bit, unsigned mode)
-{
-	might_sleep();
-	if (!test_bit(bit, word))
-		return 0;
-	return out_of_line_wait_on_bit(word, bit,
-				       bit_wait_io,
-				       mode);
-}
-
-/**
- * wait_on_bit_timeout - wait for a bit to be cleared or a timeout elapses
- * @word: the word being waited on, a kernel virtual address
- * @bit: the bit of the word being waited on
- * @mode: the task state to sleep in
- * @timeout: timeout, in jiffies
- *
- * Use the standard hashed waitqueue table to wait for a bit
- * to be cleared. This is similar to wait_on_bit(), except also takes a
- * timeout parameter.
- *
- * Returned value will be zero if the bit was cleared before the
- * @timeout elapsed, or non-zero if the @timeout elapsed or process
- * received a signal and the mode permitted wakeup on that signal.
- */
-static inline int
-wait_on_bit_timeout(unsigned long *word, int bit, unsigned mode,
-		    unsigned long timeout)
-{
-	might_sleep();
-	if (!test_bit(bit, word))
-		return 0;
-	return out_of_line_wait_on_bit_timeout(word, bit,
-					       bit_wait_timeout,
-					       mode, timeout);
-}
-
-/**
- * wait_on_bit_action - wait for a bit to be cleared
- * @word: the word being waited on, a kernel virtual address
- * @bit: the bit of the word being waited on
- * @action: the function used to sleep, which may take special actions
- * @mode: the task state to sleep in
- *
- * Use the standard hashed waitqueue table to wait for a bit
- * to be cleared, and allow the waiting action to be specified.
- * This is like wait_on_bit() but allows fine control of how the waiting
- * is done.
- *
- * Returned value will be zero if the bit was cleared, or non-zero
- * if the process received a signal and the mode permitted wakeup
- * on that signal.
- */
-static inline int
-wait_on_bit_action(unsigned long *word, int bit, wait_bit_action_f *action,
-		   unsigned mode)
-{
-	might_sleep();
-	if (!test_bit(bit, word))
-		return 0;
-	return out_of_line_wait_on_bit(word, bit, action, mode);
-}
-
-/**
- * wait_on_bit_lock - wait for a bit to be cleared, when wanting to set it
- * @word: the word being waited on, a kernel virtual address
- * @bit: the bit of the word being waited on
- * @mode: the task state to sleep in
- *
- * There is a standard hashed waitqueue table for generic use. This
- * is the part of the hashtable's accessor API that waits on a bit
- * when one intends to set it, for instance, trying to lock bitflags.
- * For instance, if one were to have waiters trying to set bitflag
- * and waiting for it to clear before setting it, one would call
- * wait_on_bit() in threads waiting to be able to set the bit.
- * One uses wait_on_bit_lock() where one is waiting for the bit to
- * clear with the intention of setting it, and when done, clearing it.
- *
- * Returns zero if the bit was (eventually) found to be clear and was
- * set.  Returns non-zero if a signal was delivered to the process and
- * the @mode allows that signal to wake the process.
- */
-static inline int
-wait_on_bit_lock(unsigned long *word, int bit, unsigned mode)
-{
-	might_sleep();
-	if (!test_and_set_bit(bit, word))
-		return 0;
-	return out_of_line_wait_on_bit_lock(word, bit, bit_wait, mode);
-}
-
-/**
- * wait_on_bit_lock_io - wait for a bit to be cleared, when wanting to set it
- * @word: the word being waited on, a kernel virtual address
- * @bit: the bit of the word being waited on
- * @mode: the task state to sleep in
- *
- * Use the standard hashed waitqueue table to wait for a bit
- * to be cleared and then to atomically set it.  This is similar
- * to wait_on_bit(), but calls io_schedule() instead of schedule()
- * for the actual waiting.
- *
- * Returns zero if the bit was (eventually) found to be clear and was
- * set.  Returns non-zero if a signal was delivered to the process and
- * the @mode allows that signal to wake the process.
- */
-static inline int
-wait_on_bit_lock_io(unsigned long *word, int bit, unsigned mode)
-{
-	might_sleep();
-	if (!test_and_set_bit(bit, word))
-		return 0;
-	return out_of_line_wait_on_bit_lock(word, bit, bit_wait_io, mode);
-}
-
-/**
- * wait_on_bit_lock_action - wait for a bit to be cleared, when wanting to set it
- * @word: the word being waited on, a kernel virtual address
- * @bit: the bit of the word being waited on
- * @action: the function used to sleep, which may take special actions
- * @mode: the task state to sleep in
- *
- * Use the standard hashed waitqueue table to wait for a bit
- * to be cleared and then to set it, and allow the waiting action
- * to be specified.
- * This is like wait_on_bit() but allows fine control of how the waiting
- * is done.
- *
- * Returns zero if the bit was (eventually) found to be clear and was
- * set.  Returns non-zero if a signal was delivered to the process and
- * the @mode allows that signal to wake the process.
- */
-static inline int
-wait_on_bit_lock_action(unsigned long *word, int bit, wait_bit_action_f *action,
-			unsigned mode)
-{
-	might_sleep();
-	if (!test_and_set_bit(bit, word))
-		return 0;
-	return out_of_line_wait_on_bit_lock(word, bit, action, mode);
-}
-
-/**
- * wait_on_atomic_t - Wait for an atomic_t to become 0
- * @val: The atomic value being waited on, a kernel virtual address
- * @action: the function used to sleep, which may take special actions
- * @mode: the task state to sleep in
- *
- * Wait for an atomic_t to become 0.  We abuse the bit-wait waitqueue table for
- * the purpose of getting a waitqueue, but we set the key to a bit number
- * outside of the target 'word'.
- */
-static inline
-int wait_on_atomic_t(atomic_t *val, int (*action)(atomic_t *), unsigned mode)
-{
-	might_sleep();
-	if (atomic_read(val) == 0)
-		return 0;
-	return out_of_line_wait_on_atomic_t(val, action, mode);
-}
 
 #endif /* _LINUX_WAIT_H */

include/linux/wait_bit.h

···
+#ifndef _LINUX_WAIT_BIT_H
+#define _LINUX_WAIT_BIT_H
+
+/*
+ * Linux wait-bit related types and methods:
+ */
+#include <linux/wait.h>
+
+struct wait_bit_key {
+	void			*flags;
+	int			bit_nr;
+#define WAIT_ATOMIC_T_BIT_NR	-1
+	unsigned long		timeout;
+};
+
+struct wait_bit_queue_entry {
+	struct wait_bit_key	key;
+	struct wait_queue_entry	wq_entry;
+};
+
+#define __WAIT_BIT_KEY_INITIALIZER(word, bit)					\
+	{ .flags = word, .bit_nr = bit, }
+
+#define __WAIT_ATOMIC_T_KEY_INITIALIZER(p)					\
+	{ .flags = p, .bit_nr = WAIT_ATOMIC_T_BIT_NR, }
+
+typedef int wait_bit_action_f(struct wait_bit_key *key, int mode);
+void __wake_up_bit(struct wait_queue_head *wq_head, void *word, int bit);
+int __wait_on_bit(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry, wait_bit_action_f *action, unsigned int mode);
+int __wait_on_bit_lock(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry, wait_bit_action_f *action, unsigned int mode);
+void wake_up_bit(void *word, int bit);
+void wake_up_atomic_t(atomic_t *p);
+int out_of_line_wait_on_bit(void *word, int, wait_bit_action_f *action, unsigned int mode);
+int out_of_line_wait_on_bit_timeout(void *word, int, wait_bit_action_f *action, unsigned int mode, unsigned long timeout);
+int out_of_line_wait_on_bit_lock(void *word, int, wait_bit_action_f *action, unsigned int mode);
+int out_of_line_wait_on_atomic_t(atomic_t *p, int (*)(atomic_t *), unsigned int mode);
+struct wait_queue_head *bit_waitqueue(void *word, int bit);
+extern void __init wait_bit_init(void);
+
+int wake_bit_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key);
+
+#define DEFINE_WAIT_BIT(name, word, bit)					\
+	struct wait_bit_queue_entry name = {					\
+		.key = __WAIT_BIT_KEY_INITIALIZER(word, bit),			\
+		.wq_entry = {							\
+			.private	= current,				\
+			.func		= wake_bit_function,			\
+			.entry		=					\
+				LIST_HEAD_INIT((name).wq_entry.entry),		\
+		},								\
+	}
+
+extern int bit_wait(struct wait_bit_key *key, int bit);
+extern int bit_wait_io(struct wait_bit_key *key, int bit);
+extern int bit_wait_timeout(struct wait_bit_key *key, int bit);
+extern int bit_wait_io_timeout(struct wait_bit_key *key, int bit);
+
+/**
+ * wait_on_bit - wait for a bit to be cleared
+ * @word: the word being waited on, a kernel virtual address
+ * @bit: the bit of the word being waited on
+ * @mode: the task state to sleep in
+ *
+ * There is a standard hashed waitqueue table for generic use. This
+ * is the part of the hashtable's accessor API that waits on a bit.
+ * For instance, if one were to have waiters on a bitflag, one would
+ * call wait_on_bit() in threads waiting for the bit to clear.
+ * One uses wait_on_bit() where one is waiting for the bit to clear,
+ * but has no intention of setting it.
+ * Returned value will be zero if the bit was cleared, or non-zero
+ * if the process received a signal and the mode permitted wakeup
+ * on that signal.
+ */
+static inline int
+wait_on_bit(unsigned long *word, int bit, unsigned mode)
+{
+	might_sleep();
+	if (!test_bit(bit, word))
+		return 0;
+	return out_of_line_wait_on_bit(word, bit,
+				       bit_wait,
+				       mode);
+}
+
+/**
+ * wait_on_bit_io - wait for a bit to be cleared
+ * @word: the word being waited on, a kernel virtual address
+ * @bit: the bit of the word being waited on
+ * @mode: the task state to sleep in
+ *
+ * Use the standard hashed waitqueue table to wait for a bit
+ * to be cleared.  This is similar to wait_on_bit(), but calls
+ * io_schedule() instead of schedule() for the actual waiting.
+ *
+ * Returned value will be zero if the bit was cleared, or non-zero
+ * if the process received a signal and the mode permitted wakeup
+ * on that signal.
+ */
+static inline int
+wait_on_bit_io(unsigned long *word, int bit, unsigned mode)
+{
+	might_sleep();
+	if (!test_bit(bit, word))
+		return 0;
+	return out_of_line_wait_on_bit(word, bit,
+				       bit_wait_io,
+				       mode);
+}
+
+/**
+ * wait_on_bit_timeout - wait for a bit to be cleared or a timeout elapses
+ * @word: the word being waited on, a kernel virtual address
+ * @bit: the bit of the word being waited on
+ * @mode: the task state to sleep in
+ * @timeout: timeout, in jiffies
+ *
+ * Use the standard hashed waitqueue table to wait for a bit
+ * to be cleared. This is similar to wait_on_bit(), except also takes a
+ * timeout parameter.
+ *
+ * Returned value will be zero if the bit was cleared before the
+ * @timeout elapsed, or non-zero if the @timeout elapsed or process
+ * received a signal and the mode permitted wakeup on that signal.
+ */
+static inline int
+wait_on_bit_timeout(unsigned long *word, int bit, unsigned mode,
+		    unsigned long timeout)
+{
+	might_sleep();
+	if (!test_bit(bit, word))
+		return 0;
+	return out_of_line_wait_on_bit_timeout(word, bit,
+					       bit_wait_timeout,
+					       mode, timeout);
+}
+
+/**
+ * wait_on_bit_action - wait for a bit to be cleared
+ * @word: the word being waited on, a kernel virtual address
+ * @bit: the bit of the word being waited on
+ * @action: the function used to sleep, which may take special actions
+ * @mode: the task state to sleep in
+ *
+ * Use the standard hashed waitqueue table to wait for a bit
+ * to be cleared, and allow the waiting action to be specified.
+ * This is like wait_on_bit() but allows fine control of how the waiting
+ * is done.
+ *
+ * Returned value will be zero if the bit was cleared, or non-zero
+ * if the process received a signal and the mode permitted wakeup
+ * on that signal.
+ */
+static inline int
+wait_on_bit_action(unsigned long *word, int bit, wait_bit_action_f *action,
+		   unsigned mode)
+{
+	might_sleep();
+	if (!test_bit(bit, word))
+		return 0;
+	return out_of_line_wait_on_bit(word, bit, action, mode);
+}
+
+/**
+ * wait_on_bit_lock - wait for a bit to be cleared, when wanting to set it
+ * @word: the word being waited on, a kernel virtual address
+ * @bit: the bit of the word being waited on
+ * @mode: the task state to sleep in
+ *
+ * There is a standard hashed waitqueue table for generic use. This
+ * is the part of the hashtable's accessor API that waits on a bit
+ * when one intends to set it, for instance, trying to lock bitflags.
+ * For instance, if one were to have waiters trying to set bitflag
+ * and waiting for it to clear before setting it, one would call
+ * wait_on_bit() in threads waiting to be able to set the bit.
+ * One uses wait_on_bit_lock() where one is waiting for the bit to
+ * clear with the intention of setting it, and when done, clearing it.
+ *
+ * Returns zero if the bit was (eventually) found to be clear and was
+ * set.  Returns non-zero if a signal was delivered to the process and
+ * the @mode allows that signal to wake the process.
+ */
+static inline int
+wait_on_bit_lock(unsigned long *word, int bit, unsigned mode)
+{
+	might_sleep();
+	if (!test_and_set_bit(bit, word))
+		return 0;
+	return out_of_line_wait_on_bit_lock(word, bit, bit_wait, mode);
+}
+
+/**
+ * wait_on_bit_lock_io - wait for a bit to be cleared, when wanting to set it
+ * @word: the word being waited on, a kernel virtual address
+ * @bit: the bit of the word being waited on
+ * @mode: the task state to sleep in
+ *
+ * Use the standard hashed waitqueue table to wait for a bit
+ * to be cleared and then to atomically set it.  This is similar
+ * to wait_on_bit(), but calls io_schedule() instead of schedule()
+ * for the actual waiting.
+ *
+ * Returns zero if the bit was (eventually) found to be clear and was
+ * set.  Returns non-zero if a signal was delivered to the process and
+ * the @mode allows that signal to wake the process.
+ */
+static inline int
+wait_on_bit_lock_io(unsigned long *word, int bit, unsigned mode)
+{
+	might_sleep();
+	if (!test_and_set_bit(bit, word))
+		return 0;
+	return out_of_line_wait_on_bit_lock(word, bit, bit_wait_io, mode);
+}
+
+/**
+ * wait_on_bit_lock_action - wait for a bit to be cleared, when wanting to set it
+ * @word: the word being waited on, a kernel virtual address
+ * @bit: the bit of the word being waited on
+ * @action: the function used to sleep, which may take special actions
+ * @mode: the task state to sleep in
+ *
+ * Use the standard hashed waitqueue table to wait for a bit
+ * to be cleared and then to set it, and allow the waiting action
+ * to be specified.
+ * This is like wait_on_bit() but allows fine control of how the waiting
+ * is done.
+ *
+ * Returns zero if the bit was (eventually) found to be clear and was
+ * set.  Returns non-zero if a signal was delivered to the process and
+ * the @mode allows that signal to wake the process.
+ */
+static inline int
+wait_on_bit_lock_action(unsigned long *word, int bit, wait_bit_action_f *action,
+			unsigned mode)
+{
+	might_sleep();
+	if (!test_and_set_bit(bit, word))
+		return 0;
+	return out_of_line_wait_on_bit_lock(word, bit, action, mode);
+}
+
+/**
+ * wait_on_atomic_t - Wait for an atomic_t to become 0
+ * @val: The atomic value being waited on, a kernel virtual address
+ * @action: the function used to sleep, which may take special actions
+ * @mode: the task state to sleep in
+ *
+ * Wait for an atomic_t to become 0.  We abuse the bit-wait waitqueue table for
+ * the purpose of getting a waitqueue, but we set the key to a bit number
+ * outside of the target 'word'.
+ */
+static inline
+int wait_on_atomic_t(atomic_t *val, int (*action)(atomic_t *), unsigned mode)
+{
+	might_sleep();
+	if (atomic_read(val) == 0)
+		return 0;
+	return out_of_line_wait_on_atomic_t(val, action, mode);
+}
+
+#endif /* _LINUX_WAIT_BIT_H */

include/net/af_unix.h

···
 #define UNIX_GC_CANDIDATE	0
 #define UNIX_GC_MAYBE_CYCLE	1
 	struct socket_wq	peer_wq;
-	wait_queue_t		peer_wake;
+	wait_queue_entry_t		peer_wake;
 };
 
 static inline struct unix_sock *unix_sk(const struct sock *sk)

include/uapi/linux/auto_fs.h

···
 #define AUTOFS_MIN_PROTO_VERSION	AUTOFS_PROTO_VERSION
 
 /*
- * The wait_queue_token (autofs_wqt_t) is part of a structure which is passed
+ * The wait_queue_entry_token (autofs_wqt_t) is part of a structure which is passed
  * back to the kernel via ioctl from userspace. On architectures where 32- and
  * 64-bit userspace binaries can be executed it's important that the size of
  * autofs_wqt_t stays constant between 32- and 64-bit Linux kernels so that we
···
 
 struct autofs_packet_missing {
 	struct autofs_packet_hdr hdr;
-	autofs_wqt_t wait_queue_token;
+	autofs_wqt_t wait_queue_entry_token;
 	int len;
 	char name[NAME_MAX+1];
 };	

include/uapi/linux/auto_fs4.h

···
 /* v4 multi expire (via pipe) */
 struct autofs_packet_expire_multi {
 	struct autofs_packet_hdr hdr;
-	autofs_wqt_t wait_queue_token;
+	autofs_wqt_t wait_queue_entry_token;
 	int len;
 	char name[NAME_MAX+1];
 };
···
 /* autofs v5 common packet struct */
 struct autofs_v5_packet {
 	struct autofs_packet_hdr hdr;
-	autofs_wqt_t wait_queue_token;
+	autofs_wqt_t wait_queue_entry_token;
 	__u32 dev;
 	__u64 ino;
 	__u32 uid;

include/uapi/linux/sched.h

···
  * For the sched_{set,get}attr() calls
  */
 #define SCHED_FLAG_RESET_ON_FORK	0x01
+#define SCHED_FLAG_RECLAIM		0x02
 
 #endif /* _UAPI_LINUX_SCHED_H */

init/Kconfig

···
 
 config CPUSETS
 	bool "Cpuset controller"
+	depends on SMP
 	help
 	  This option will let you create and manage CPUSETs which
 	  allow dynamically partitioning a system into sets of CPUs and

init/main.c

···
 
 static noinline void __ref rest_init(void)
 {
+	struct task_struct *tsk;
 	int pid;
 
 	rcu_scheduler_starting();
···
 	 * the init task will end up wanting to create kthreads, which, if
 	 * we schedule it before we create kthreadd, will OOPS.
 	 */
-	kernel_thread(kernel_init, NULL, CLONE_FS);
+	pid = kernel_thread(kernel_init, NULL, CLONE_FS);
+	/*
+	 * Pin init on the boot CPU. Task migration is not properly working
+	 * until sched_init_smp() has been run. It will set the allowed
+	 * CPUs for init to the non isolated CPUs.
+	 */
+	rcu_read_lock();
+	tsk = find_task_by_pid_ns(pid, &init_pid_ns);
+	set_cpus_allowed_ptr(tsk, cpumask_of(smp_processor_id()));
+	rcu_read_unlock();
+
 	numa_default_policy();
 	pid = kernel_thread(kthreadd, NULL, CLONE_FS | CLONE_FILES);
 	rcu_read_lock();
 	kthreadd_task = find_task_by_pid_ns(pid, &init_pid_ns);
 	rcu_read_unlock();
+
+	/*
+	 * Enable might_sleep() and smp_processor_id() checks.
+	 * They cannot be enabled earlier because with CONFIG_PRREMPT=y
+	 * kernel_thread() would trigger might_sleep() splats. With
+	 * CONFIG_PREEMPT_VOLUNTARY=y the init task might have scheduled
+	 * already, but it's stuck on the kthreadd_done completion.
+	 */
+	system_state = SYSTEM_SCHEDULING;
+
 	complete(&kthreadd_done);
 
 	/*
···
 	 * init can allocate pages on any node
 	 */
 	set_mems_allowed(node_states[N_MEMORY]);
-	/*
-	 * init can run on any cpu.
-	 */
-	set_cpus_allowed_ptr(current, cpu_all_mask);
 
 	cad_pid = task_pid(current);
 

kernel/async.c

···
 	ktime_t uninitialized_var(calltime), delta, rettime;
 
 	/* 1) run (and print duration) */
-	if (initcall_debug && system_state == SYSTEM_BOOTING) {
+	if (initcall_debug && system_state < SYSTEM_RUNNING) {
 		pr_debug("calling  %lli_%pF @ %i\n",
 			(long long)entry->cookie,
 			entry->func, task_pid_nr(current));
 		calltime = ktime_get();
 	}
 	entry->func(entry->data, entry->cookie);
-	if (initcall_debug && system_state == SYSTEM_BOOTING) {
+	if (initcall_debug && system_state < SYSTEM_RUNNING) {
 		rettime = ktime_get();
 		delta = ktime_sub(rettime, calltime);
 		pr_debug("initcall %lli_%pF returned 0 after %lld usecs\n",
···
 {
 	ktime_t uninitialized_var(starttime), delta, endtime;
 
-	if (initcall_debug && system_state == SYSTEM_BOOTING) {
+	if (initcall_debug && system_state < SYSTEM_RUNNING) {
 		pr_debug("async_waiting @ %i\n", task_pid_nr(current));
 		starttime = ktime_get();
 	}
 
 	wait_event(async_done, lowest_in_progress(domain) >= cookie);
 
-	if (initcall_debug && system_state == SYSTEM_BOOTING) {
+	if (initcall_debug && system_state < SYSTEM_RUNNING) {
 		endtime = ktime_get();
 		delta = ktime_sub(endtime, starttime);
 

kernel/exit.c

···
 	rcu_read_unlock();
 }
 
-struct task_struct *try_get_task_struct(struct task_struct **ptask)
-{
-	struct task_struct *task;
-
-	rcu_read_lock();
-	task = task_rcu_dereference(ptask);
-	if (task)
-		get_task_struct(task);
-	rcu_read_unlock();
-
-	return task;
-}
-
 /*
  * Determine if a process group is "orphaned", according to the POSIX
  * definition in 2.2.2.52.  Orphaned process groups are not to be affected
···
 	int __user		*wo_stat;
 	struct rusage __user	*wo_rusage;
 
-	wait_queue_t		child_wait;
+	wait_queue_entry_t		child_wait;
 	int			notask_error;
 };
 
···
 	return 0;
 }
 
-static int child_wait_callback(wait_queue_t *wait, unsigned mode,
+static int child_wait_callback(wait_queue_entry_t *wait, unsigned mode,
 				int sync, void *key)
 {
 	struct wait_opts *wo = container_of(wait, struct wait_opts,

kernel/extable.c

···
 	    addr < (unsigned long)_etext)
 		return 1;
 
-	if (system_state == SYSTEM_BOOTING &&
+	if (system_state < SYSTEM_RUNNING &&
 	    init_kernel_text(addr))
 		return 1;
 	return 0;

kernel/futex.c

···
  * @requeue_pi_key:	the requeue_pi target futex key
  * @bitset:		bitset for the optional bitmasked wakeup
  *
- * We use this hashed waitqueue, instead of a normal wait_queue_t, so
+ * We use this hashed waitqueue, instead of a normal wait_queue_entry_t, so
  * we can wake only the relevant ones (hashed queues may be shared).
  *
  * A futex_q has a woken state, just like tasks have TASK_RUNNING.

kernel/printk/printk.c

···
 	unsigned long long k;
 	unsigned long timeout;
 
-	if ((boot_delay == 0 || system_state != SYSTEM_BOOTING)
+	if ((boot_delay == 0 || system_state >= SYSTEM_RUNNING)
 		|| suppress_message_printing(level)) {
 		return;
 	}

kernel/sched/Makefile

···
 endif
 
 obj-y += core.o loadavg.o clock.o cputime.o
-obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o
-obj-y += wait.o swait.o completion.o idle.o
-obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o
+obj-y += idle_task.o fair.o rt.o deadline.o
+obj-y += wait.o wait_bit.o swait.o completion.o idle.o
+obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o stop_task.o
 obj-$(CONFIG_SCHED_AUTOGROUP) += autogroup.o
 obj-$(CONFIG_SCHEDSTATS) += stats.o
 obj-$(CONFIG_SCHED_DEBUG) += debug.o

kernel/sched/clock.c

···
 #include <linux/workqueue.h>
 #include <linux/compiler.h>
 #include <linux/tick.h>
+#include <linux/init.h>
 
 /*
  * Scheduler clock - returns current time in nanosec units.
···
 	return static_branch_likely(&__sched_clock_stable);
 }
 
+static void __scd_stamp(struct sched_clock_data *scd)
+{
+	scd->tick_gtod = ktime_get_ns();
+	scd->tick_raw = sched_clock();
+}
+
 static void __set_sched_clock_stable(void)
 {
-	struct sched_clock_data *scd = this_scd();
+	struct sched_clock_data *scd;
 
+	/*
+	 * Since we're still unstable and the tick is already running, we have
+	 * to disable IRQs in order to get a consistent scd->tick* reading.
+	 */
+	local_irq_disable();
+	scd = this_scd();
 	/*
 	 * Attempt to make the (initial) unstable->stable transition continuous.
 	 */
 	__sched_clock_offset = (scd->tick_gtod + __gtod_offset) - (scd->tick_raw);
+	local_irq_enable();
 
 	printk(KERN_INFO "sched_clock: Marking stable (%lld, %lld)->(%lld, %lld)\n",
 			scd->tick_gtod, __gtod_offset,
···
 	tick_dep_clear(TICK_DEP_BIT_CLOCK_UNSTABLE);
 }
 
+/*
+ * If we ever get here, we're screwed, because we found out -- typically after
+ * the fact -- that TSC wasn't good. This means all our clocksources (including
+ * ktime) could have reported wrong values.
+ *
+ * What we do here is an attempt to fix up and continue sort of where we left
+ * off in a coherent manner.
+ *
+ * The only way to fully avoid random clock jumps is to boot with:
+ * "tsc=unstable".
+ */
 static void __sched_clock_work(struct work_struct *work)
 {
+	struct sched_clock_data *scd;
+	int cpu;
+
+	/* take a current timestamp and set 'now' */
+	preempt_disable();
+	scd = this_scd();
+	__scd_stamp(scd);
+	scd->clock = scd->tick_gtod + __gtod_offset;
+	preempt_enable();
+
+	/* clone to all CPUs */
+	for_each_possible_cpu(cpu)
+		per_cpu(sched_clock_data, cpu) = *scd;
+
+	printk(KERN_WARNING "TSC found unstable after boot, most likely due to broken BIOS. Use 'tsc=unstable'.\n");
+	printk(KERN_INFO "sched_clock: Marking unstable (%lld, %lld)<-(%lld, %lld)\n",
+			scd->tick_gtod, __gtod_offset,
+			scd->tick_raw,  __sched_clock_offset);
+
 	static_branch_disable(&__sched_clock_stable);
 }
 
···
 
 static void __clear_sched_clock_stable(void)
 {
-	struct sched_clock_data *scd = this_scd();
-
-	/*
-	 * Attempt to make the stable->unstable transition continuous.
-	 *
-	 * Trouble is, this is typically called from the TSC watchdog
-	 * timer, which is late per definition. This means the tick
-	 * values can already be screwy.
-	 *
-	 * Still do what we can.
-	 */
-	__gtod_offset = (scd->tick_raw + __sched_clock_offset) - (scd->tick_gtod);
-
-	printk(KERN_INFO "sched_clock: Marking unstable (%lld, %lld)<-(%lld, %lld)\n",
-			scd->tick_gtod, __gtod_offset,
-			scd->tick_raw,  __sched_clock_offset);
+	if (!sched_clock_stable())
+		return;
 
 	tick_dep_set(TICK_DEP_BIT_CLOCK_UNSTABLE);
-
-	if (sched_clock_stable())
-		schedule_work(&sched_clock_work);
+	schedule_work(&sched_clock_work);
 }
 
 void clear_sched_clock_stable(void)
···
 		__clear_sched_clock_stable();
 }
 
-void sched_clock_init_late(void)
+/*
+ * We run this as late_initcall() such that it runs after all built-in drivers,
+ * notably: acpi_processor and intel_idle, which can mark the TSC as unstable.
+ */
+static int __init sched_clock_init_late(void)
 {
 	sched_clock_running = 2;
 	/*
···
 
 	if (__sched_clock_stable_early)
 		__set_sched_clock_stable();
+
+	return 0;
 }
+late_initcall(sched_clock_init_late);
 
 /*
  * min, max except they take wrapping into account
···
 {
 	struct sched_clock_data *scd;
 
+	if (sched_clock_stable())
+		return;
+
+	if (unlikely(!sched_clock_running))
+		return;
+
 	WARN_ON_ONCE(!irqs_disabled());
 
-	/*
-	 * Update these values even if sched_clock_stable(), because it can
-	 * become unstable at any point in time at which point we need some
-	 * values to fall back on.
-	 *
-	 * XXX arguably we can skip this if we expose tsc_clocksource_reliable
-	 */
 	scd = this_scd();
-	scd->tick_raw  = sched_clock();
-	scd->tick_gtod = ktime_get_ns();
+	__scd_stamp(scd);
+	sched_clock_local(scd);
+}
 
-	if (!sched_clock_stable() && likely(sched_clock_running))
-		sched_clock_local(scd);
+void sched_clock_tick_stable(void)
+{
+	u64 gtod, clock;
+
+	if (!sched_clock_stable())
+		return;
+
+	/*
+	 * Called under watchdog_lock.
+	 *
+	 * The watchdog just found this TSC to (still) be stable, so now is a
+	 * good moment to update our __gtod_offset. Because once we find the
+	 * TSC to be unstable, any computation will be computing crap.
+	 */
+	local_irq_disable();
+	gtod = ktime_get_ns();
+	clock = sched_clock();
+	__gtod_offset = (clock + __sched_clock_offset) - gtod;
+	local_irq_enable();
 }
 
 /*
···
 EXPORT_SYMBOL_GPL(sched_clock_idle_sleep_event);
 
 /*
- * We just idled delta nanoseconds (called with irqs disabled):
+ * We just idled; resync with ktime.
  */
-void sched_clock_idle_wakeup_event(u64 delta_ns)
+void sched_clock_idle_wakeup_event(void)
 {
-	if (timekeeping_suspended)
+	unsigned long flags;
+
+	if (sched_clock_stable())
 		return;
 
+	if (unlikely(timekeeping_suspended))
+		return;
+
+	local_irq_save(flags);
 	sched_clock_tick();
-	touch_softlockup_watchdog_sched();
+	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);
 

kernel/sched/completion.c

···
 	if (!x->done) {
 		DECLARE_WAITQUEUE(wait, current);
 
-		__add_wait_queue_tail_exclusive(&x->wait, &wait);
+		__add_wait_queue_entry_tail_exclusive(&x->wait, &wait);
 		do {
 			if (signal_pending_state(state, current)) {
 				timeout = -ERESTARTSYS;

kernel/sched/core.c

···
 #include <uapi/linux/sched/types.h>
 #include <linux/sched/loadavg.h>
 #include <linux/sched/hotplug.h>
+#include <linux/wait_bit.h>
 #include <linux/cpuset.h>
 #include <linux/delayacct.h>
 #include <linux/init_task.h>
···
 	dequeue_task(rq, p, flags);
 }
 
-void sched_set_stop_task(int cpu, struct task_struct *stop)
-{
-	struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 };
-	struct task_struct *old_stop = cpu_rq(cpu)->stop;
-
-	if (stop) {
-		/*
-		 * Make it appear like a SCHED_FIFO task, its something
-		 * userspace knows about and won't get confused about.
-		 *
-		 * Also, it will make PI more or less work without too
-		 * much confusion -- but then, stop work should not
-		 * rely on PI working anyway.
-		 */
-		sched_setscheduler_nocheck(stop, SCHED_FIFO, &param);
-
-		stop->sched_class = &stop_sched_class;
-	}
-
-	cpu_rq(cpu)->stop = stop;
-
-	if (old_stop) {
-		/*
-		 * Reset it back to a normal scheduling class so that
-		 * it can die in pieces.
-		 */
-		old_stop->sched_class = &rt_sched_class;
-	}
-}
-
 /*
  * __normal_prio - return the priority that is based on the static prio
  */
···
 	*avg += diff >> 3;
 }
 
+void sched_set_stop_task(int cpu, struct task_struct *stop)
+{
+	struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 };
+	struct task_struct *old_stop = cpu_rq(cpu)->stop;
+
+	if (stop) {
+		/*
+		 * Make it appear like a SCHED_FIFO task, its something
+		 * userspace knows about and won't get confused about.
+		 *
+		 * Also, it will make PI more or less work without too
+		 * much confusion -- but then, stop work should not
+		 * rely on PI working anyway.
+		 */
+		sched_setscheduler_nocheck(stop, SCHED_FIFO, &param);
+
+		stop->sched_class = &stop_sched_class;
+	}
+
+	cpu_rq(cpu)->stop = stop;
+
+	if (old_stop) {
+		/*
+		 * Reset it back to a normal scheduling class so that
+		 * it can die in pieces.
+		 */
+		old_stop->sched_class = &rt_sched_class;
+	}
+}
+
 #else
 
 static inline int __set_cpus_allowed_ptr(struct task_struct *p,
···
 {
 	struct rq *rq = this_rq();
 	struct llist_node *llist = llist_del_all(&rq->wake_list);
-	struct task_struct *p;
+	struct task_struct *p, *t;
 	struct rq_flags rf;
 
 	if (!llist)
···
 	rq_lock_irqsave(rq, &rf);
 	update_rq_clock(rq);
 
-	while (llist) {
-		int wake_flags = 0;
-
-		p = llist_entry(llist, struct task_struct, wake_entry);
-		llist = llist_next(llist);
-
-		if (p->sched_remote_wakeup)
-			wake_flags = WF_MIGRATED;
-
-		ttwu_do_activate(rq, p, wake_flags, &rf);
-	}
+	llist_for_each_entry_safe(p, t, llist, wake_entry)
+		ttwu_do_activate(rq, p, p->sched_remote_wakeup ? WF_MIGRATED : 0, &rf);
 
 	rq_unlock_irqrestore(rq, &rf);
 }
···
 }
 
 /*
- * This function clears the sched_dl_entity static params.
- */
-void __dl_clear_params(struct task_struct *p)
-{
-	struct sched_dl_entity *dl_se = &p->dl;
-
-	dl_se->dl_runtime = 0;
-	dl_se->dl_deadline = 0;
-	dl_se->dl_period = 0;
-	dl_se->flags = 0;
-	dl_se->dl_bw = 0;
-
-	dl_se->dl_throttled = 0;
-	dl_se->dl_yielded = 0;
-}
-
-/*
  * Perform scheduler related setup for a newly forked process p.
  * p is forked by current.
  *
···
 
 	RB_CLEAR_NODE(&p->dl.rb_node);
 	init_dl_task_timer(&p->dl);
+	init_dl_inactive_task_timer(&p->dl);
 	__dl_clear_params(p);
 
 	INIT_LIST_HEAD(&p->rt.run_list);
···
 unsigned long to_ratio(u64 period, u64 runtime)
 {
 	if (runtime == RUNTIME_INF)
-		return 1ULL << 20;
+		return BW_UNIT;
 
 	/*
 	 * Doing this here saves a lot of checks in all
···
 	if (period == 0)
 		return 0;
 
-	return div64_u64(runtime << 20, period);
+	return div64_u64(runtime << BW_SHIFT, period);
 }
-
-#ifdef CONFIG_SMP
-inline struct dl_bw *dl_bw_of(int i)
-{
-	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
-			 "sched RCU must be held");
-	return &cpu_rq(i)->rd->dl_bw;
-}
-
-static inline int dl_bw_cpus(int i)
-{
-	struct root_domain *rd = cpu_rq(i)->rd;
-	int cpus = 0;
-
-	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
-			 "sched RCU must be held");
-	for_each_cpu_and(i, rd->span, cpu_active_mask)
-		cpus++;
-
-	return cpus;
-}
-#else
-inline struct dl_bw *dl_bw_of(int i)
-{
-	return &cpu_rq(i)->dl.dl_bw;
-}
-
-static inline int dl_bw_cpus(int i)
-{
-	return 1;
-}
-#endif
-
-/*
- * We must be sure that accepting a new task (or allowing changing the
- * parameters of an existing one) is consistent with the bandwidth
- * constraints. If yes, this function also accordingly updates the currently
- * allocated bandwidth to reflect the new situation.
- *
- * This function is called while holding p's rq->lock.
- *
- * XXX we should delay bw change until the task's 0-lag point, see
- * __setparam_dl().
- */
-static int dl_overflow(struct task_struct *p, int policy,
-		       const struct sched_attr *attr)
-{
-
-	struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
-	u64 period = attr->sched_period ?: attr->sched_deadline;
-	u64 runtime = attr->sched_runtime;
-	u64 new_bw = dl_policy(policy) ? to_ratio(period, runtime) : 0;
-	int cpus, err = -1;
-
-	/* !deadline task may carry old deadline bandwidth */
-	if (new_bw == p->dl.dl_bw && task_has_dl_policy(p))
-		return 0;
-
-	/*
-	 * Either if a task, enters, leave, or stays -deadline but changes
-	 * its parameters, we may need to update accordingly the total
-	 * allocated bandwidth of the container.
-	 */
-	raw_spin_lock(&dl_b->lock);
-	cpus = dl_bw_cpus(task_cpu(p));
-	if (dl_policy(policy) && !task_has_dl_policy(p) &&
-	    !__dl_overflow(dl_b, cpus, 0, new_bw)) {
-		__dl_add(dl_b, new_bw);
-		err = 0;
-	} else if (dl_policy(policy) && task_has_dl_policy(p) &&
-		   !__dl_overflow(dl_b, cpus, p->dl.dl_bw, new_bw)) {
-		__dl_clear(dl_b, p->dl.dl_bw);
-		__dl_add(dl_b, new_bw);
-		err = 0;
-	} else if (!dl_policy(policy) && task_has_dl_policy(p)) {
-		__dl_clear(dl_b, p->dl.dl_bw);
-		err = 0;
-	}
-	raw_spin_unlock(&dl_b->lock);
-
-	return err;
-}
-
-extern void init_dl_bw(struct dl_bw *dl_b);
 
 /*
  * wake_up_new_task - wake up a newly created task for the first time.
···
 	exception_exit(prev_state);
 }
 
-int default_wake_function(wait_queue_t *curr, unsigned mode, int wake_flags,
+int default_wake_function(wait_queue_entry_t *curr, unsigned mode, int wake_flags,
 			  void *key)
 {
 	return try_to_wake_up(curr->private, mode, wake_flags);
···
 }
 
 /*
- * This function initializes the sched_dl_entity of a newly becoming
- * SCHED_DEADLINE task.
- *
- * Only the static values are considered here, the actual runtime and the
- * absolute deadline will be properly calculated when the task is enqueued
- * for the first time with its new policy.
- */
-static void
-__setparam_dl(struct task_struct *p, const struct sched_attr *attr)
-{
-	struct sched_dl_entity *dl_se = &p->dl;
-
-	dl_se->dl_runtime = attr->sched_runtime;
-	dl_se->dl_deadline = attr->sched_deadline;
-	dl_se->dl_period = attr->sched_period ?: dl_se->dl_deadline;
-	dl_se->flags = attr->sched_flags;
-	dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime);
-
-	/*
-	 * Changing the parameters of a task is 'tricky' and we're not doing
-	 * the correct thing -- also see task_dead_dl() and switched_from_dl().
-	 *
-	 * What we SHOULD do is delay the bandwidth release until the 0-lag
-	 * point. This would include retaining the task_struct until that time
-	 * and change dl_overflow() to not immediately decrement the current
-	 * amount.
-	 *
-	 * Instead we retain the current runtime/deadline and let the new
-	 * parameters take effect after the current reservation period lapses.
-	 * This is safe (albeit pessimistic) because the 0-lag point is always
-	 * before the current scheduling deadline.
-	 *
-	 * We can still have temporary overloads because we do not delay the
-	 * change in bandwidth until that time; so admission control is
-	 * not on the safe side. It does however guarantee tasks will never
-	 * consume more than promised.
-	 */
-}
-
-/*
  * sched_setparam() passes in -1 for its policy, to let the functions
  * it calls know not to change it.
  */
···
 		p->sched_class = &fair_sched_class;
 }
 
-static void
-__getparam_dl(struct task_struct *p, struct sched_attr *attr)
-{
-	struct sched_dl_entity *dl_se = &p->dl;
-
-	attr->sched_priority = p->rt_priority;
-	attr->sched_runtime = dl_se->dl_runtime;
-	attr->sched_deadline = dl_se->dl_deadline;
-	attr->sched_period = dl_se->dl_period;
-	attr->sched_flags = dl_se->flags;
-}
-
-/*
- * This function validates the new parameters of a -deadline task.
- * We ask for the deadline not being zero, and greater or equal
- * than the runtime, as well as the period of being zero or
- * greater than deadline. Furthermore, we have to be sure that
- * user parameters are above the internal resolution of 1us (we
- * check sched_runtime only since it is always the smaller one) and
- * below 2^63 ns (we have to check both sched_deadline and
- * sched_period, as the latter can be zero).
- */
-static bool
-__checkparam_dl(const struct sched_attr *attr)
-{
-	/* deadline != 0 */
-	if (attr->sched_deadline == 0)
-		return false;
-
-	/*
-	 * Since we truncate DL_SCALE bits, make sure we're at least
-	 * that big.
-	 */
-	if (attr->sched_runtime < (1ULL << DL_SCALE))
-		return false;
-
-	/*
-	 * Since we use the MSB for wrap-around and sign issues, make
-	 * sure it's not set (mind that period can be equal to zero).
-	 */
-	if (attr->sched_deadline & (1ULL << 63) ||
-	    attr->sched_period & (1ULL << 63))
-		return false;
-
-	/* runtime <= deadline <= period (if period != 0) */
-	if ((attr->sched_period != 0 &&
-	     attr->sched_period < attr->sched_deadline) ||
-	    attr->sched_deadline < attr->sched_runtime)
-		return false;
-
-	return true;
-}
-
 /*
  * Check the target process has a UID that matches the current process's:
  */
···
 	return match;
 }
 
-static bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr)
-{
-	struct sched_dl_entity *dl_se = &p->dl;
-
-	if (dl_se->dl_runtime != attr->sched_runtime ||
-		dl_se->dl_deadline != attr->sched_deadline ||
-		dl_se->dl_period != attr->sched_period ||
-		dl_se->flags != attr->sched_flags)
-		return true;
-
-	return false;
-}
-
 static int __sched_setscheduler(struct task_struct *p,
 				const struct sched_attr *attr,
 				bool user, bool pi)
···
 	int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
 	struct rq *rq;
 
-	/* May grab non-irq protected spin_locks: */
-	BUG_ON(in_interrupt());
+	/* The pi code expects interrupts enabled */
+	BUG_ON(pi && in_interrupt());
 recheck:
 	/* Double check policy once rq lock held: */
 	if (policy < 0) {
···
 			return -EINVAL;
 	}
 
-	if (attr->sched_flags & ~(SCHED_FLAG_RESET_ON_FORK))
+	if (attr->sched_flags &
+		~(SCHED_FLAG_RESET_ON_FORK | SCHED_FLAG_RECLAIM))
 		return -EINVAL;
 
 	/*
···
 	 * of a SCHED_DEADLINE task) we need to check if enough bandwidth
 	 * is available.
 	 */
-	if ((dl_policy(policy) || dl_task(p)) && dl_overflow(p, policy, attr)) {
+	if ((dl_policy(policy) || dl_task(p)) && sched_dl_overflow(p, policy, attr)) {
 		task_rq_unlock(rq, p, &rf);
 		return -EBUSY;
 	}
···
 #endif
 }
 
+#ifdef CONFIG_SMP
+
 int cpuset_cpumask_can_shrink(const struct cpumask *cur,
 			      const struct cpumask *trial)
 {
-	int ret = 1, trial_cpus;
-	struct dl_bw *cur_dl_b;
-	unsigned long flags;
+	int ret = 1;
 
 	if (!cpumask_weight(cur))
 		return ret;
 
-	rcu_read_lock_sched();
-	cur_dl_b = dl_bw_of(cpumask_any(cur));
-	trial_cpus = cpumask_weight(trial);
-
-	raw_spin_lock_irqsave(&cur_dl_b->lock, flags);
-	if (cur_dl_b->bw != -1 &&
-	    cur_dl_b->bw * trial_cpus < cur_dl_b->total_bw)
-		ret = 0;
-	raw_spin_unlock_irqrestore(&cur_dl_b->lock, flags);
-	rcu_read_unlock_sched();
+	ret = dl_cpuset_cpumask_can_shrink(cur, trial);
 
 	return ret;
 }
···
 		goto out;
 	}
 
-#ifdef CONFIG_SMP
 	if (dl_task(p) && !cpumask_intersects(task_rq(p)->rd->span,
-					      cs_cpus_allowed)) {
-		unsigned int dest_cpu = cpumask_any_and(cpu_active_mask,
-							cs_cpus_allowed);
-		struct dl_bw *dl_b;
-		bool overflow;
-		int cpus;
-		unsigned long flags;
+					      cs_cpus_allowed))
+		ret = dl_task_can_attach(p, cs_cpus_allowed);
 
-		rcu_read_lock_sched();
-		dl_b = dl_bw_of(dest_cpu);
-		raw_spin_lock_irqsave(&dl_b->lock, flags);
-		cpus = dl_bw_cpus(dest_cpu);
-		overflow = __dl_overflow(dl_b, cpus, 0, p->dl.dl_bw);
-		if (overflow)
-			ret = -EBUSY;
-		else {
-			/*
-			 * We reserve space for this task in the destination
-			 * root_domain, as we can't fail after this point.
-			 * We will free resources in the source root_domain
-			 * later on (see set_cpus_allowed_dl()).
-			 */
-			__dl_add(dl_b, p->dl.dl_bw);
-		}
-		raw_spin_unlock_irqrestore(&dl_b->lock, flags);
-		rcu_read_unlock_sched();
-
-	}
-#endif
 out:
 	return ret;
 }
-
-#ifdef CONFIG_SMP
 
 bool sched_smp_initialized __read_mostly;
 
···
 
 static int cpuset_cpu_inactive(unsigned int cpu)
 {
-	unsigned long flags;
-	struct dl_bw *dl_b;
-	bool overflow;
-	int cpus;
-
 	if (!cpuhp_tasks_frozen) {
-		rcu_read_lock_sched();
-		dl_b = dl_bw_of(cpu);
-
-		raw_spin_lock_irqsave(&dl_b->lock, flags);
-		cpus = dl_bw_cpus(cpu);
-		overflow = __dl_overflow(dl_b, cpus, 0, 0);
-		raw_spin_unlock_irqrestore(&dl_b->lock, flags);
-
-		rcu_read_unlock_sched();
-
-		if (overflow)
+		if (dl_cpu_busy(cpu))
 			return -EBUSY;
 		cpuset_update_active_cpus();
 	} else {
···
 	cpumask_var_t non_isolated_cpus;
 
 	alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL);
-	alloc_cpumask_var(&fallback_doms, GFP_KERNEL);
 
 	sched_init_numa();
 
···
 	 * happen.
 	 */
 	mutex_lock(&sched_domains_mutex);
-	init_sched_domains(cpu_active_mask);
+	sched_init_domains(cpu_active_mask);
 	cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map);
 	if (cpumask_empty(non_isolated_cpus))
 		cpumask_set_cpu(smp_processor_id(), non_isolated_cpus);
···
 	init_sched_dl_class();
 
 	sched_init_smt();
-	sched_clock_init_late();
 
 	sched_smp_initialized = true;
 }
···
 void __init sched_init_smp(void)
 {
 	sched_init_granularity();
-	sched_clock_init_late();
 }
 #endif /* CONFIG_SMP */
 
···
 DECLARE_PER_CPU(cpumask_var_t, load_balance_mask);
 DECLARE_PER_CPU(cpumask_var_t, select_idle_mask);
 
-#define WAIT_TABLE_BITS 8
-#define WAIT_TABLE_SIZE (1 << WAIT_TABLE_BITS)
-static wait_queue_head_t bit_wait_table[WAIT_TABLE_SIZE] __cacheline_aligned;
-
-wait_queue_head_t *bit_waitqueue(void *word, int bit)
-{
-	const int shift = BITS_PER_LONG == 32 ? 5 : 6;
-	unsigned long val = (unsigned long)word << shift | bit;
-
-	return bit_wait_table + hash_long(val, WAIT_TABLE_BITS);
-}
-EXPORT_SYMBOL(bit_waitqueue);
-
 void __init sched_init(void)
 {
 	int i, j;
 	unsigned long alloc_size = 0, ptr;
 
 	sched_clock_init();
-
-	for (i = 0; i < WAIT_TABLE_SIZE; i++)
-		init_waitqueue_head(bit_wait_table + i);
+	wait_bit_init();
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	alloc_size += 2 * nr_cpu_ids * sizeof(void **);
···
 	calc_load_update = jiffies + LOAD_FREQ;
 
 #ifdef CONFIG_SMP
-	zalloc_cpumask_var(&sched_domains_tmpmask, GFP_NOWAIT);
 	/* May be allocated at isolcpus cmdline parse time */
 	if (cpu_isolated_map == NULL)
 		zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
···
 
 	if ((preempt_count_equals(preempt_offset) && !irqs_disabled() &&
 	     !is_idle_task(current)) ||
-	    system_state != SYSTEM_RUNNING || oops_in_progress)
+	    system_state == SYSTEM_BOOTING || system_state > SYSTEM_RUNNING ||
+	    oops_in_progress)
 		return;
+
 	if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
 		return;
 	prev_jiffy = jiffies;
···
 
 	task_rq_unlock(rq, tsk, &rf);
 }
-#endif /* CONFIG_CGROUP_SCHED */
-
-#ifdef CONFIG_RT_GROUP_SCHED
-/*
- * Ensure that the real time constraints are schedulable.
- */
-static DEFINE_MUTEX(rt_constraints_mutex);
-
-/* Must be called with tasklist_lock held */
-static inline int tg_has_rt_tasks(struct task_group *tg)
-{
-	struct task_struct *g, *p;
-
-	/*
-	 * Autogroups do not have RT tasks; see autogroup_create().
-	 */
-	if (task_group_is_autogroup(tg))
-		return 0;
-
-	for_each_process_thread(g, p) {
-		if (rt_task(p) && task_group(p) == tg)
-			return 1;
-	}
-
-	return 0;
-}
-
-struct rt_schedulable_data {
-	struct task_group *tg;
-	u64 rt_period;
-	u64 rt_runtime;
-};
-
-static int tg_rt_schedulable(struct task_group *tg, void *data)
-{
-	struct rt_schedulable_data *d = data;
-	struct task_group *child;
-	unsigned long total, sum = 0;
-	u64 period, runtime;
-
-	period = ktime_to_ns(tg->rt_bandwidth.rt_period);
-	runtime = tg->rt_bandwidth.rt_runtime;
-
-	if (tg == d->tg) {
-		period = d->rt_period;
-		runtime = d->rt_runtime;
-	}
-
-	/*
-	 * Cannot have more runtime than the period.
-	 */
-	if (runtime > period && runtime != RUNTIME_INF)
-		return -EINVAL;
-
-	/*
-	 * Ensure we don't starve existing RT tasks.
-	 */
-	if (rt_bandwidth_enabled() && !runtime && tg_has_rt_tasks(tg))
-		return -EBUSY;
-
-	total = to_ratio(period, runtime);
-
-	/*
-	 * Nobody can have more than the global setting allows.
-	 */
-	if (total > to_ratio(global_rt_period(), global_rt_runtime()))
-		return -EINVAL;
-
-	/*
-	 * The sum of our children's runtime should not exceed our own.
-	 */
-	list_for_each_entry_rcu(child, &tg->children, siblings) {
-		period = ktime_to_ns(child->rt_bandwidth.rt_period);
-		runtime = child->rt_bandwidth.rt_runtime;
-
-		if (child == d->tg) {
-			period = d->rt_period;
-			runtime = d->rt_runtime;
-		}
-
-		sum += to_ratio(period, runtime);
-	}
-
-	if (sum > total)
-		return -EINVAL;
-
-	return 0;
-}
-
-static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime)
-{
-	int ret;
-
-	struct rt_schedulable_data data = {
-		.tg = tg,
-		.rt_period = period,
-		.rt_runtime = runtime,
-	};
-
-	rcu_read_lock();
-	ret = walk_tg_tree(tg_rt_schedulable, tg_nop, &data);
-	rcu_read_unlock();
-
-	return ret;
-}
-
-static int tg_set_rt_bandwidth(struct task_group *tg,
-		u64 rt_period, u64 rt_runtime)
-{
-	int i, err = 0;
-
-	/*
-	 * Disallowing the root group RT runtime is BAD, it would disallow the
-	 * kernel creating (and or operating) RT threads.
-	 */
-	if (tg == &root_task_group && rt_runtime == 0)
-		return -EINVAL;
-
-	/* No period doesn't make any sense. */
-	if (rt_period == 0)
-		return -EINVAL;
-
-	mutex_lock(&rt_constraints_mutex);
-	read_lock(&tasklist_lock);
-	err = __rt_schedulable(tg, rt_period, rt_runtime);
-	if (err)
-		goto unlock;
-
-	raw_spin_lock_irq(&tg->rt_bandwidth.rt_runtime_lock);
-	tg->rt_bandwidth.rt_period = ns_to_ktime(rt_period);
-	tg->rt_bandwidth.rt_runtime = rt_runtime;
-
-	for_each_possible_cpu(i) {
-		struct rt_rq *rt_rq = tg->rt_rq[i];
-
-		raw_spin_lock(&rt_rq->rt_runtime_lock);
-		rt_rq->rt_runtime = rt_runtime;
-		raw_spin_unlock(&rt_rq->rt_runtime_lock);
-	}
-	raw_spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock);
-unlock:
-	read_unlock(&tasklist_lock);
-	mutex_unlock(&rt_constraints_mutex);
-
-	return err;
-}
-
-static int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us)
-{
-	u64 rt_runtime, rt_period;
-
-	rt_period = ktime_to_ns(tg->rt_bandwidth.rt_period);
-	rt_runtime = (u64)rt_runtime_us * NSEC_PER_USEC;
-	if (rt_runtime_us < 0)
-		rt_runtime = RUNTIME_INF;
-
-	return tg_set_rt_bandwidth(tg, rt_period, rt_runtime);
-}
-
-static long sched_group_rt_runtime(struct task_group *tg)
-{
-	u64 rt_runtime_us;
-
-	if (tg->rt_bandwidth.rt_runtime == RUNTIME_INF)
-		return -1;
-
-	rt_runtime_us = tg->rt_bandwidth.rt_runtime;
-	do_div(rt_runtime_us, NSEC_PER_USEC);
-	return rt_runtime_us;
-}
-
-static int sched_group_set_rt_period(struct task_group *tg, u64 rt_period_us)
-{
-	u64 rt_runtime, rt_period;
-
-	rt_period = rt_period_us * NSEC_PER_USEC;
-	rt_runtime = tg->rt_bandwidth.rt_runtime;
-
-	return tg_set_rt_bandwidth(tg, rt_period, rt_runtime);
-}
-
-static long sched_group_rt_period(struct task_group *tg)
-{
-	u64 rt_period_us;
-
-	rt_period_us = ktime_to_ns(tg->rt_bandwidth.rt_period);
-	do_div(rt_period_us, NSEC_PER_USEC);
-	return rt_period_us;
-}
-#endif /* CONFIG_RT_GROUP_SCHED */
-
-#ifdef CONFIG_RT_GROUP_SCHED
-static int sched_rt_global_constraints(void)
-{
-	int ret = 0;
-
-	mutex_lock(&rt_constraints_mutex);
-	read_lock(&tasklist_lock);
-	ret = __rt_schedulable(NULL, 0, 0);
-	read_unlock(&tasklist_lock);
-	mutex_unlock(&rt_constraints_mutex);
-
-	return ret;
-}
-
-static int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk)
-{
-	/* Don't accept realtime tasks when there is no way for them to run */
-	if (rt_task(tsk) && tg->rt_bandwidth.rt_runtime == 0)
-		return 0;
-
-	return 1;
-}
-
-#else /* !CONFIG_RT_GROUP_SCHED */
-static int sched_rt_global_constraints(void)
-{
-	unsigned long flags;
-	int i;
-
-	raw_spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags);
-	for_each_possible_cpu(i) {
-		struct rt_rq *rt_rq = &cpu_rq(i)->rt;
-
-		raw_spin_lock(&rt_rq->rt_runtime_lock);
-		rt_rq->rt_runtime = global_rt_runtime();
-		raw_spin_unlock(&rt_rq->rt_runtime_lock);
-	}
-	raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags);
-
-	return 0;
-}
-#endif /* CONFIG_RT_GROUP_SCHED */
-
-static int sched_dl_global_validate(void)
-{
-	u64 runtime = global_rt_runtime();
-	u64 period = global_rt_period();
-	u64 new_bw = to_ratio(period, runtime);
-	struct dl_bw *dl_b;
-	int cpu, ret = 0;
-	unsigned long flags;
-
-	/*
-	 * Here we want to check the bandwidth not being set to some
-	 * value smaller than the currently allocated bandwidth in
-	 * any of the root_domains.
-	 *
-	 * FIXME: Cycling on all the CPUs is overdoing, but simpler than
-	 * cycling on root_domains... Discussion on different/better
-	 * solutions is welcome!
-	 */
-	for_each_possible_cpu(cpu) {
-		rcu_read_lock_sched();
-		dl_b = dl_bw_of(cpu);
-
-		raw_spin_lock_irqsave(&dl_b->lock, flags);
-		if (new_bw < dl_b->total_bw)
-			ret = -EBUSY;
-		raw_spin_unlock_irqrestore(&dl_b->lock, flags);
-
-		rcu_read_unlock_sched();
-
-		if (ret)
-			break;
-	}
-
-	return ret;
-}
-
-static void sched_dl_do_global(void)
-{
-	u64 new_bw = -1;
-	struct dl_bw *dl_b;
-	int cpu;
-	unsigned long flags;
-
-	def_dl_bandwidth.dl_period = global_rt_period();
-	def_dl_bandwidth.dl_runtime = global_rt_runtime();
-
-	if (global_rt_runtime() != RUNTIME_INF)
-		new_bw = to_ratio(global_rt_period(), global_rt_runtime());
-
-	/*
-	 * FIXME: As above...
-	 */
-	for_each_possible_cpu(cpu) {
-		rcu_read_lock_sched();
-		dl_b = dl_bw_of(cpu);
-
-		raw_spin_lock_irqsave(&dl_b->lock, flags);
-		dl_b->bw = new_bw;
-		raw_spin_unlock_irqrestore(&dl_b->lock, flags);
-
-		rcu_read_unlock_sched();
-	}
-}
-
-static int sched_rt_global_validate(void)
-{
-	if (sysctl_sched_rt_period <= 0)
-		return -EINVAL;
-
-	if ((sysctl_sched_rt_runtime != RUNTIME_INF) &&
-		(sysctl_sched_rt_runtime > sysctl_sched_rt_period))
-		return -EINVAL;
-
-	return 0;
-}
-
-static void sched_rt_do_global(void)
-{
-	def_rt_bandwidth.rt_runtime = global_rt_runtime();
-	def_rt_bandwidth.rt_period = ns_to_ktime(global_rt_period());
-}
-
-int sched_rt_handler(struct ctl_table *table, int write,
-		void __user *buffer, size_t *lenp,
-		loff_t *ppos)
-{
-	int old_period, old_runtime;
-	static DEFINE_MUTEX(mutex);
-	int ret;
-
-	mutex_lock(&mutex);
-	old_period = sysctl_sched_rt_period;
-	old_runtime = sysctl_sched_rt_runtime;
-
-	ret = proc_dointvec(table, write, buffer, lenp, ppos);
-
-	if (!ret && write) {
-		ret = sched_rt_global_validate();
-		if (ret)
-			goto undo;
-
-		ret = sched_dl_global_validate();
-		if (ret)
-			goto undo;
-
-		ret = sched_rt_global_constraints();
-		if (ret)
-			goto undo;
-
-		sched_rt_do_global();
-		sched_dl_do_global();
-	}
-	if (0) {
-undo:
-		sysctl_sched_rt_period = old_period;
-		sysctl_sched_rt_runtime = old_runtime;
-	}
-	mutex_unlock(&mutex);
-
-	return ret;
-}
-
-int sched_rr_handler(struct ctl_table *table, int write,
-		void __user *buffer, size_t *lenp,
-		loff_t *ppos)
-{
-	int ret;
-	static DEFINE_MUTEX(mutex);
-
-	mutex_lock(&mutex);
-	ret = proc_dointvec(table, write, buffer, lenp, ppos);
-	/*
-	 * Make sure that internally we keep jiffies.
-	 * Also, writing zero resets the timeslice to default:
-	 */
-	if (!ret && write) {
-		sched_rr_timeslice =
-			sysctl_sched_rr_timeslice <= 0 ? RR_TIMESLICE :
-			msecs_to_jiffies(sysctl_sched_rr_timeslice);
-	}
-	mutex_unlock(&mutex);
-	return ret;
-}
-
-#ifdef CONFIG_CGROUP_SCHED
 
 static inline struct task_group *css_tg(struct cgroup_subsys_state *css)
 {

kernel/sched/cputime.c

···
 	 * userspace. Once a task gets some ticks, the monotonicy code at
 	 * 'update' will ensure things converge to the observed ratio.
 	 */
-	if (stime == 0) {
-		utime = rtime;
-		goto update;
+	if (stime != 0) {
+		if (utime == 0)
+			stime = rtime;
+		else
+			stime = scale_stime(stime, rtime, stime + utime);
 	}
 
-	if (utime == 0) {
-		stime = rtime;
-		goto update;
-	}
-
-	stime = scale_stime(stime, rtime, stime + utime);
-
-update:
 	/*
 	 * Make sure stime doesn't go backwards; this preserves monotonicity
 	 * for utime because rtime is monotonic.

kernel/sched/deadline.c

···
 #include "sched.h"
 
 #include <linux/slab.h>
+#include <uapi/linux/sched/types.h>
 
 struct dl_bandwidth def_dl_bandwidth;
 
···
 static inline int on_dl_rq(struct sched_dl_entity *dl_se)
 {
 	return !RB_EMPTY_NODE(&dl_se->rb_node);
+}
+
+#ifdef CONFIG_SMP
+static inline struct dl_bw *dl_bw_of(int i)
+{
+	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
+			 "sched RCU must be held");
+	return &cpu_rq(i)->rd->dl_bw;
+}
+
+static inline int dl_bw_cpus(int i)
+{
+	struct root_domain *rd = cpu_rq(i)->rd;
+	int cpus = 0;
+
+	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
+			 "sched RCU must be held");
+	for_each_cpu_and(i, rd->span, cpu_active_mask)
+		cpus++;
+
+	return cpus;
+}
+#else
+static inline struct dl_bw *dl_bw_of(int i)
+{
+	return &cpu_rq(i)->dl.dl_bw;
+}
+
+static inline int dl_bw_cpus(int i)
+{
+	return 1;
+}
+#endif
+
+static inline
+void add_running_bw(u64 dl_bw, struct dl_rq *dl_rq)
+{
+	u64 old = dl_rq->running_bw;
+
+	lockdep_assert_held(&(rq_of_dl_rq(dl_rq))->lock);
+	dl_rq->running_bw += dl_bw;
+	SCHED_WARN_ON(dl_rq->running_bw < old); /* overflow */
+	SCHED_WARN_ON(dl_rq->running_bw > dl_rq->this_bw);
+}
+
+static inline
+void sub_running_bw(u64 dl_bw, struct dl_rq *dl_rq)
+{
+	u64 old = dl_rq->running_bw;
+
+	lockdep_assert_held(&(rq_of_dl_rq(dl_rq))->lock);
+	dl_rq->running_bw -= dl_bw;
+	SCHED_WARN_ON(dl_rq->running_bw > old); /* underflow */
+	if (dl_rq->running_bw > old)
+		dl_rq->running_bw = 0;
+}
+
+static inline
+void add_rq_bw(u64 dl_bw, struct dl_rq *dl_rq)
+{
+	u64 old = dl_rq->this_bw;
+
+	lockdep_assert_held(&(rq_of_dl_rq(dl_rq))->lock);
+	dl_rq->this_bw += dl_bw;
+	SCHED_WARN_ON(dl_rq->this_bw < old); /* overflow */
+}
+
+static inline
+void sub_rq_bw(u64 dl_bw, struct dl_rq *dl_rq)
+{
+	u64 old = dl_rq->this_bw;
+
+	lockdep_assert_held(&(rq_of_dl_rq(dl_rq))->lock);
+	dl_rq->this_bw -= dl_bw;
+	SCHED_WARN_ON(dl_rq->this_bw > old); /* underflow */
+	if (dl_rq->this_bw > old)
+		dl_rq->this_bw = 0;
+	SCHED_WARN_ON(dl_rq->running_bw > dl_rq->this_bw);
+}
+
+void dl_change_utilization(struct task_struct *p, u64 new_bw)
+{
+	struct rq *rq;
+
+	if (task_on_rq_queued(p))
+		return;
+
+	rq = task_rq(p);
+	if (p->dl.dl_non_contending) {
+		sub_running_bw(p->dl.dl_bw, &rq->dl);
+		p->dl.dl_non_contending = 0;
+		/*
+		 * If the timer handler is currently running and the
+		 * timer cannot be cancelled, inactive_task_timer()
+		 * will see that dl_not_contending is not set, and
+		 * will not touch the rq's active utilization,
+		 * so we are still safe.
+		 */
+		if (hrtimer_try_to_cancel(&p->dl.inactive_timer) == 1)
+			put_task_struct(p);
+	}
+	sub_rq_bw(p->dl.dl_bw, &rq->dl);
+	add_rq_bw(new_bw, &rq->dl);
+}
+
+/*
+ * The utilization of a task cannot be immediately removed from
+ * the rq active utilization (running_bw) when the task blocks.
+ * Instead, we have to wait for the so called "0-lag time".
+ *
+ * If a task blocks before the "0-lag time", a timer (the inactive
+ * timer) is armed, and running_bw is decreased when the timer
+ * fires.
+ *
+ * If the task wakes up again before the inactive timer fires,
+ * the timer is cancelled, whereas if the task wakes up after the
+ * inactive timer fired (and running_bw has been decreased) the
+ * task's utilization has to be added to running_bw again.
+ * A flag in the deadline scheduling entity (dl_non_contending)
+ * is used to avoid race conditions between the inactive timer handler
+ * and task wakeups.
+ *
+ * The following diagram shows how running_bw is updated. A task is
+ * "ACTIVE" when its utilization contributes to running_bw; an
+ * "ACTIVE contending" task is in the TASK_RUNNING state, while an
+ * "ACTIVE non contending" task is a blocked task for which the "0-lag time"
+ * has not passed yet. An "INACTIVE" task is a task for which the "0-lag"
+ * time already passed, which does not contribute to running_bw anymore.
+ *                              +------------------+
+ *             wakeup           |    ACTIVE        |
+ *          +------------------>+   contending     |
+ *          | add_running_bw    |                  |
+ *          |                   +----+------+------+
+ *          |                        |      ^
+ *          |                dequeue |      |
+ * +--------+-------+                |      |
+ * |                |   t >= 0-lag   |      | wakeup
+ * |    INACTIVE    |<---------------+      |
+ * |                | sub_running_bw |      |
+ * +--------+-------+                |      |
+ *          ^                        |      |
+ *          |              t < 0-lag |      |
+ *          |                        |      |
+ *          |                        V      |
+ *          |                   +----+------+------+
+ *          | sub_running_bw    |    ACTIVE        |
+ *          +-------------------+                  |
+ *            inactive timer    |  non contending  |
+ *            fired             +------------------+
+ *
+ * The task_non_contending() function is invoked when a task
+ * blocks, and checks if the 0-lag time already passed or
+ * not (in the first case, it directly updates running_bw;
+ * in the second case, it arms the inactive timer).
+ *
+ * The task_contending() function is invoked when a task wakes
+ * up, and checks if the task is still in the "ACTIVE non contending"
+ * state or not (in the second case, it updates running_bw).
+ */
+static void task_non_contending(struct task_struct *p)
+{
+	struct sched_dl_entity *dl_se = &p->dl;
+	struct hrtimer *timer = &dl_se->inactive_timer;
+	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
+	struct rq *rq = rq_of_dl_rq(dl_rq);
+	s64 zerolag_time;
+
+	/*
+	 * If this is a non-deadline task that has been boosted,
+	 * do nothing
+	 */
+	if (dl_se->dl_runtime == 0)
+		return;
+
+	WARN_ON(hrtimer_active(&dl_se->inactive_timer));
+	WARN_ON(dl_se->dl_non_contending);
+
+	zerolag_time = dl_se->deadline -
+		 div64_long((dl_se->runtime * dl_se->dl_period),
+			dl_se->dl_runtime);
+
+	/*
+	 * Using relative times instead of the absolute "0-lag time"
+	 * allows to simplify the code
+	 */
+	zerolag_time -= rq_clock(rq);
+
+	/*
+	 * If the "0-lag time" already passed, decrease the active
+	 * utilization now, instead of starting a timer
+	 */
+	if (zerolag_time < 0) {
+		if (dl_task(p))
+			sub_running_bw(dl_se->dl_bw, dl_rq);
+		if (!dl_task(p) || p->state == TASK_DEAD) {
+			struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
+
+			if (p->state == TASK_DEAD)
+				sub_rq_bw(p->dl.dl_bw, &rq->dl);
+			raw_spin_lock(&dl_b->lock);
+			__dl_clear(dl_b, p->dl.dl_bw, dl_bw_cpus(task_cpu(p)));
+			__dl_clear_params(p);
+			raw_spin_unlock(&dl_b->lock);
+		}
+
+		return;
+	}
+
+	dl_se->dl_non_contending = 1;
+	get_task_struct(p);
+	hrtimer_start(timer, ns_to_ktime(zerolag_time), HRTIMER_MODE_REL);
+}
+
+static void task_contending(struct sched_dl_entity *dl_se, int flags)
+{
+	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
+
+	/*
+	 * If this is a non-deadline task that has been boosted,
+	 * do nothing
+	 */
+	if (dl_se->dl_runtime == 0)
+		return;
+
+	if (flags & ENQUEUE_MIGRATED)
+		add_rq_bw(dl_se->dl_bw, dl_rq);
+
+	if (dl_se->dl_non_contending) {
+		dl_se->dl_non_contending = 0;
+		/*
+		 * If the timer handler is currently running and the
+		 * timer cannot be cancelled, inactive_task_timer()
+		 * will see that dl_not_contending is not set, and
+		 * will not touch the rq's active utilization,
+		 * so we are still safe.
+		 */
+		if (hrtimer_try_to_cancel(&dl_se->inactive_timer) == 1)
+			put_task_struct(dl_task_of(dl_se));
+	} else {
+		/*
+		 * Since "dl_non_contending" is not set, the
+		 * task's utilization has already been removed from
+		 * active utilization (either when the task blocked,
+		 * when the "inactive timer" fired).
+		 * So, add it back.
+		 */
+		add_running_bw(dl_se->dl_bw, dl_rq);
+	}
 }
 
 static inline int is_leftmost(struct task_struct *p, struct dl_rq *dl_rq)
···
 #else
 	init_dl_bw(&dl_rq->dl_bw);
 #endif
+
+	dl_rq->running_bw = 0;
+	dl_rq->this_bw = 0;
+	init_dl_rq_bw_ratio(dl_rq);
 }
 
 #ifdef CONFIG_SMP
···
 }
 
 /*
- * When a -deadline entity is queued back on the runqueue, its runtime and
- * deadline might need updating.
+ * Revised wakeup rule [1]: For self-suspending tasks, rather then
+ * re-initializing task's runtime and deadline, the revised wakeup
+ * rule adjusts the task's runtime to avoid the task to overrun its
+ * density.
  *
- * The policy here is that we update the deadline of the entity only if:
- *  - the current deadline is in the past,
- *  - using the remaining runtime with the current deadline would make
- *    the entity exceed its bandwidth.
+ * Reasoning: a task may overrun the density if:
+ *    runtime / (deadline - t) > dl_runtime / dl_deadline
+ *
+ * Therefore, runtime can be adjusted to:
+ *     runtime = (dl_runtime / dl_deadline) * (deadline - t)
+ *
+ * In such way that runtime will be equal to the maximum density
+ * the task can use without breaking any rule.
+ *
+ * [1] Luca Abeni, Giuseppe Lipari, and Juri Lelli. 2015. Constant
+ * bandwidth server revisited. SIGBED Rev. 11, 4 (January 2015), 19-24.
+ */
+static void
+update_dl_revised_wakeup(struct sched_dl_entity *dl_se, struct rq *rq)
+{
+	u64 laxity = dl_se->deadline - rq_clock(rq);
+
+	/*
+	 * If the task has deadline < period, and the deadline is in the past,
+	 * it should already be throttled before this check.
+	 *
+	 * See update_dl_entity() comments for further details.
+	 */
+	WARN_ON(dl_time_before(dl_se->deadline, rq_clock(rq)));
+
+	dl_se->runtime = (dl_se->dl_density * laxity) >> BW_SHIFT;
+}
+
+/*
+ * Regarding the deadline, a task with implicit deadline has a relative
+ * deadline == relative period. A task with constrained deadline has a
+ * relative deadline <= relative period.
+ *
+ * We support constrained deadline tasks. However, there are some restrictions
+ * applied only for tasks which do not have an implicit deadline. See
+ * update_dl_entity() to know more about such restrictions.
+ *
+ * The dl_is_implicit() returns true if the task has an implicit deadline.
+ */
+static inline bool dl_is_implicit(struct sched_dl_entity *dl_se)
+{
+	return dl_se->dl_deadline == dl_se->dl_period;
+}
+
+/*
+ * When a deadline entity is placed in the runqueue, its runtime and deadline
+ * might need to be updated. This is done by a CBS wake up rule. There are two
+ * different rules: 1) the original CBS; and 2) the Revisited CBS.
+ *
+ * When the task is starting a new period, the Original CBS is used. In this
+ * case, the runtime is replenished and a new absolute deadline is set.
+ *
+ * When a task is queued before the begin of the next period, using the
+ * remaining runtime and deadline could make the entity to overflow, see
+ * dl_entity_overflow() to find more about runtime overflow. When such case
+ * is detected, the runtime and deadline need to be updated.
+ *
+ * If the task has an implicit deadline, i.e., deadline == period, the Original
+ * CBS is applied. the runtime is replenished and a new absolute deadline is
+ * set, as in the previous cases.
+ *
+ * However, the Original CBS does not work properly for tasks with
+ * deadline < period, which are said to have a constrained deadline. By
+ * applying the Original CBS, a constrained deadline task would be able to run
+ * runtime/deadline in a period. With deadline < period, the task would
+ * overrun the runtime/period allowed bandwidth, breaking the admission test.
+ *
+ * In order to prevent this misbehave, the Revisited CBS is used for
+ * constrained deadline tasks when a runtime overflow is detected. In the
+ * Revisited CBS, rather than replenishing & setting a new absolute deadline,
+ * the remaining runtime of the task is reduced to avoid runtime overflow.
+ * Please refer to the comments update_dl_revised_wakeup() function to find
+ * more about the Revised CBS rule.
  */
 static void update_dl_entity(struct sched_dl_entity *dl_se,
 			     struct sched_dl_entity *pi_se)
···
 
 	if (dl_time_before(dl_se->deadline, rq_clock(rq)) ||
 	    dl_entity_overflow(dl_se, pi_se, rq_clock(rq))) {
+
+		if (unlikely(!dl_is_implicit(dl_se) &&
+			     !dl_time_before(dl_se->deadline, rq_clock(rq)) &&
+			     !dl_se->dl_boosted)){
+			update_dl_revised_wakeup(dl_se, rq);
+			return;
+		}
+
 		dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
 		dl_se->runtime = pi_se->dl_runtime;
 	}
···
 	 * The task might have changed its scheduling policy to something
 	 * different than SCHED_DEADLINE (through switched_from_dl()).
 	 */
-	if (!dl_task(p)) {
-		__dl_clear_params(p);
+	if (!dl_task(p))
 		goto unlock;
-	}
 
 	/*
 	 * The task might have been boosted by someone else and might be in the
···
 		if (unlikely(dl_se->dl_boosted || !start_dl_timer(p)))
 			return;
 		dl_se->dl_throttled = 1;
+		if (dl_se->runtime > 0)
+			dl_se->runtime = 0;
 	}
 }
 
···
 }
 
 extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq);
+
+/*
+ * This function implements the GRUB accounting rule:
+ * according to the GRUB reclaiming algorithm, the runtime is
+ * not decreased as "dq = -dt", but as
+ * "dq = -max{u / Umax, (1 - Uinact - Uextra)} dt",
+ * where u is the utilization of the task, Umax is the maximum reclaimable
+ * utilization, Uinact is the (per-runqueue) inactive utilization, computed
+ * as the difference between the "total runqueue utilization" and the
+ * runqueue active utilization, and Uextra is the (per runqueue) extra
+ * reclaimable utilization.
+ * Since rq->dl.running_bw and rq->dl.this_bw contain utilizations
+ * multiplied by 2^BW_SHIFT, the result has to be shifted right by
+ * BW_SHIFT.
+ * Since rq->dl.bw_ratio contains 1 / Umax multipled by 2^RATIO_SHIFT,
+ * dl_bw is multiped by rq->dl.bw_ratio and shifted right by RATIO_SHIFT.
+ * Since delta is a 64 bit variable, to have an overflow its value
+ * should be larger than 2^(64 - 20 - 8), which is more than 64 seconds.
+ * So, overflow is not an issue here.
+ */
+u64 grub_reclaim(u64 delta, struct rq *rq, struct sched_dl_entity *dl_se)
+{
+	u64 u_inact = rq->dl.this_bw - rq->dl.running_bw; /* Utot - Uact */
+	u64 u_act;
+	u64 u_act_min = (dl_se->dl_bw * rq->dl.bw_ratio) >> RATIO_SHIFT;
+
+	/*
+	 * Instead of computing max{u * bw_ratio, (1 - u_inact - u_extra)},
+	 * we compare u_inact + rq->dl.extra_bw with
+	 * 1 - (u * rq->dl.bw_ratio >> RATIO_SHIFT), because
+	 * u_inact + rq->dl.extra_bw can be larger than
+	 * 1 * (so, 1 - u_inact - rq->dl.extra_bw would be negative
+	 * leading to wrong results)
+	 */
+	if (u_inact + rq->dl.extra_bw > BW_UNIT - u_act_min)
+		u_act = u_act_min;
+	else
+		u_act = BW_UNIT - u_inact - rq->dl.extra_bw;
+
+	return (delta * u_act) >> BW_SHIFT;
+}
 
 /*
  * Update the current task's runtime statistics (provided it is still
···
 
 	sched_rt_avg_update(rq, delta_exec);
 
+	if (unlikely(dl_se->flags & SCHED_FLAG_RECLAIM))
+		delta_exec = grub_reclaim(delta_exec, rq, &curr->dl);
 	dl_se->runtime -= delta_exec;
 
 throttle:
···
 			rt_rq->rt_time += delta_exec;
 		raw_spin_unlock(&rt_rq->rt_runtime_lock);
 	}
+}
+
+static enum hrtimer_restart inactive_task_timer(struct hrtimer *timer)
+{
+	struct sched_dl_entity *dl_se = container_of(timer,
+						     struct sched_dl_entity,
+						     inactive_timer);
+	struct task_struct *p = dl_task_of(dl_se);
+	struct rq_flags rf;
+	struct rq *rq;
+
+	rq = task_rq_lock(p, &rf);
+
+	if (!dl_task(p) || p->state == TASK_DEAD) {
+		struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
+
+		if (p->state == TASK_DEAD && dl_se->dl_non_contending) {
+			sub_running_bw(p->dl.dl_bw, dl_rq_of_se(&p->dl));
+			sub_rq_bw(p->dl.dl_bw, dl_rq_of_se(&p->dl));
+			dl_se->dl_non_contending = 0;
+		}
+
+		raw_spin_lock(&dl_b->lock);
+		__dl_clear(dl_b, p->dl.dl_bw, dl_bw_cpus(task_cpu(p)));
+		raw_spin_unlock(&dl_b->lock);
+		__dl_clear_params(p);
+
+		goto unlock;
+	}
+	if (dl_se->dl_non_contending == 0)
+		goto unlock;
+
+	sched_clock_tick();
+	update_rq_clock(rq);
+
+	sub_running_bw(dl_se->dl_bw, &rq->dl);
+	dl_se->dl_non_contending = 0;
+unlock:
+	task_rq_unlock(rq, p, &rf);
+	put_task_struct(p);
+
+	return HRTIMER_NORESTART;
+}
+
+void init_dl_inactive_task_timer(struct sched_dl_entity *dl_se)
+{
+	struct hrtimer *timer = &dl_se->inactive_timer;
+
+	hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	timer->function = inactive_task_timer;
 }
 
 #ifdef CONFIG_SMP
···
 	 * parameters of the task might need updating. Otherwise,
 	 * we want a replenishment of its runtime.
 	 */
-	if (flags & ENQUEUE_WAKEUP)
+	if (flags & ENQUEUE_WAKEUP) {
+		task_contending(dl_se, flags);
 		update_dl_entity(dl_se, pi_se);
-	else if (flags & ENQUEUE_REPLENISH)
+	} else if (flags & ENQUEUE_REPLENISH) {
 		replenish_dl_entity(dl_se, pi_se);
+	}
 
 	__enqueue_dl_entity(dl_se);
 }
···
 static void dequeue_dl_entity(struct sched_dl_entity *dl_se)
 {
 	__dequeue_dl_entity(dl_se);
-}
-
-static inline bool dl_is_constrained(struct sched_dl_entity *dl_se)
-{
-	return dl_se->dl_deadline < dl_se->dl_period;
 }
 
 static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
···
 	 * If that is the case, the task will be throttled and
 	 * the replenishment timer will be set to the next period.
 	 */
-	if (!p->dl.dl_throttled && dl_is_constrained(&p->dl))
+	if (!p->dl.dl_throttled && !dl_is_implicit(&p->dl))
 		dl_check_constrained_dl(&p->dl);
 
+	if (p->on_rq == TASK_ON_RQ_MIGRATING || flags & ENQUEUE_RESTORE) {
+		add_rq_bw(p->dl.dl_bw, &rq->dl);
+		add_running_bw(p->dl.dl_bw, &rq->dl);
+	}
+
 	/*
-	 * If p is throttled, we do nothing. In fact, if it exhausted
+	 * If p is throttled, we do not enqueue it. In fact, if it exhausted
 	 * its budget it needs a replenishment and, since it now is on
 	 * its rq, the bandwidth timer callback (which clearly has not
 	 * run yet) will take care of this.
+	 * However, the active utilization does not depend on the fact
+	 * that the task is on the runqueue or not (but depends on the
+	 * task's state - in GRUB parlance, "inactive" vs "active contending").
+	 * In other words, even if a task is throttled its utilization must
+	 * be counted in the active utilization; hence, we need to call
+	 * add_running_bw().
 	 */
-	if (p->dl.dl_throttled && !(flags & ENQUEUE_REPLENISH))
+	if (p->dl.dl_throttled && !(flags & ENQUEUE_REPLENISH)) {
+		if (flags & ENQUEUE_WAKEUP)
+			task_contending(&p->dl, flags);
+
 		return;
+	}
 
 	enqueue_dl_entity(&p->dl, pi_se, flags);
 
···
 {
 	update_curr_dl(rq);
 	__dequeue_task_dl(rq, p, flags);
+
+	if (p->on_rq == TASK_ON_RQ_MIGRATING || flags & DEQUEUE_SAVE) {
+		sub_running_bw(p->dl.dl_bw, &rq->dl);
+		sub_rq_bw(p->dl.dl_bw, &rq->dl);
+	}
+
+	/*
+	 * This check allows to start the inactive timer (or to immediately
+	 * decrease the active utilization, if needed) in two cases:
+	 * when the task blocks and when it is terminating
+	 * (p->state == TASK_DEAD). We can handle the two cases in the same
+	 * way, because from GRUB's point of view the same thing is happening
+	 * (the task moves from "active contending" to "active non contending"
+	 * or "inactive")
+	 */
+	if (flags & DEQUEUE_SLEEP)
+		task_non_contending(p);
 }
 
 /*
···
 
 out:
 	return cpu;
+}
+
+static void migrate_task_rq_dl(struct task_struct *p)
+{
+	struct rq *rq;
+
+	if (p->state != TASK_WAKING)
+		return;
+
+	rq = task_rq(p);
+	/*
+	 * Since p->state == TASK_WAKING, set_task_cpu() has been called
+	 * from try_to_wake_up(). Hence, p->pi_lock is locked, but
+	 * rq->lock is not... So, lock it
+	 */
+	raw_spin_lock(&rq->lock);
+	if (p->dl.dl_non_contending) {
+		sub_running_bw(p->dl.dl_bw, &rq->dl);
+		p->dl.dl_non_contending = 0;
+		/*
+		 * If the timer handler is currently running and the
+		 * timer cannot be cancelled, inactive_task_timer()
+		 * will see that dl_not_contending is not set, and
+		 * will not touch the rq's active utilization,
+		 * so we are still safe.
+		 */
+		if (hrtimer_try_to_cancel(&p->dl.inactive_timer) == 1)
+			put_task_struct(p);
+	}
+	sub_rq_bw(p->dl.dl_bw, &rq->dl);
+	raw_spin_unlock(&rq->lock);
 }
 
 static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p)
···
 	 * SCHED_DEADLINE tasks cannot fork and this is achieved through
 	 * sched_fork()
 	 */
-}
-
-static void task_dead_dl(struct task_struct *p)
-{
-	struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
-
-	/*
-	 * Since we are TASK_DEAD we won't slip out of the domain!
-	 */
-	raw_spin_lock_irq(&dl_b->lock);
-	/* XXX we should retain the bw until 0-lag */
-	dl_b->total_bw -= p->dl.dl_bw;
-	raw_spin_unlock_irq(&dl_b->lock);
 }
 
 static void set_curr_task_dl(struct rq *rq)
···
 		 * then possible that next_task has migrated.
 		 */
 		task = pick_next_pushable_dl_task(rq);
-		if (task_cpu(next_task) == rq->cpu && task == next_task) {
+		if (task == next_task) {
 			/*
 			 * The task is still there. We don't try
 			 * again, some other cpu will pull it when ready.
···
 	}
 
 	deactivate_task(rq, next_task, 0);
+	sub_running_bw(next_task->dl.dl_bw, &rq->dl);
+	sub_rq_bw(next_task->dl.dl_bw, &rq->dl);
 	set_task_cpu(next_task, later_rq->cpu);
+	add_rq_bw(next_task->dl.dl_bw, &later_rq->dl);
+	add_running_bw(next_task->dl.dl_bw, &later_rq->dl);
 	activate_task(later_rq, next_task, 0);
 	ret = 1;
 
···
 			resched = true;
 
 			deactivate_task(src_rq, p, 0);
+			sub_running_bw(p->dl.dl_bw, &src_rq->dl);
+			sub_rq_bw(p->dl.dl_bw, &src_rq->dl);
 			set_task_cpu(p, this_cpu);
+			add_rq_bw(p->dl.dl_bw, &this_rq->dl);
+			add_running_bw(p->dl.dl_bw, &this_rq->dl);
 			activate_task(this_rq, p, 0);
 			dmin = p->dl.deadline;
 
···
 		 * until we complete the update.
 		 */
 		raw_spin_lock(&src_dl_b->lock);
-		__dl_clear(src_dl_b, p->dl.dl_bw);
+		__dl_clear(src_dl_b, p->dl.dl_bw, dl_bw_cpus(task_cpu(p)));
 		raw_spin_unlock(&src_dl_b->lock);
 	}
 
···
 static void switched_from_dl(struct rq *rq, struct task_struct *p)
 {
 	/*
-	 * Start the deadline timer; if we switch back to dl before this we'll
-	 * continue consuming our current CBS slice. If we stay outside of
-	 * SCHED_DEADLINE until the deadline passes, the timer will reset the
-	 * task.
+	 * task_non_contending() can start the "inactive timer" (if the 0-lag
+	 * time is in the future). If the task switches back to dl before
+	 * the "inactive timer" fires, it can continue to consume its current
+	 * runtime using its current deadline. If it stays outside of
+	 * SCHED_DEADLINE until the 0-lag time passes, inactive_task_timer()
+	 * will reset the task parameters.
 	 */
-	if (!start_dl_timer(p))
-		__dl_clear_params(p);
+	if (task_on_rq_queued(p) && p->dl.dl_runtime)
+		task_non_contending(p);
+
+	if (!task_on_rq_queued(p))
+		sub_rq_bw(p->dl.dl_bw, &rq->dl);
+
+	/*
+	 * We cannot use inactive_task_timer() to invoke sub_running_bw()
+	 * at the 0-lag time, because the task could have been migrated
+	 * while SCHED_OTHER in the meanwhile.
+	 */
+	if (p->dl.dl_non_contending)
+		p->dl.dl_non_contending = 0;
 
 	/*
 	 * Since this might be the only -deadline task on the rq,
···
  */
 static void switched_to_dl(struct rq *rq, struct task_struct *p)
 {
+	if (hrtimer_try_to_cancel(&p->dl.inactive_timer) == 1)
+		put_task_struct(p);
 
 	/* If p is not queued we will update its parameters at next wakeup. */
-	if (!task_on_rq_queued(p))
-		return;
+	if (!task_on_rq_queued(p)) {
+		add_rq_bw(p->dl.dl_bw, &rq->dl);
 
+		return;
+	}
 	/*
 	 * If p is boosted we already updated its params in
 	 * rt_mutex_setprio()->enqueue_task(..., ENQUEUE_REPLENISH),
···
 
 #ifdef CONFIG_SMP
 	.select_task_rq		= select_task_rq_dl,
+	.migrate_task_rq	= migrate_task_rq_dl,
 	.set_cpus_allowed       = set_cpus_allowed_dl,
 	.rq_online              = rq_online_dl,
 	.rq_offline             = rq_offline_dl,
···
 	.set_curr_task		= set_curr_task_dl,
 	.task_tick		= task_tick_dl,
 	.task_fork              = task_fork_dl,
-	.task_dead		= task_dead_dl,
 
 	.prio_changed           = prio_changed_dl,
 	.switched_from		= switched_from_dl,
···
 
 	.update_curr		= update_curr_dl,
 };
+
+int sched_dl_global_validate(void)
+{
+	u64 runtime = global_rt_runtime();
+	u64 period = global_rt_period();
+	u64 new_bw = to_ratio(period, runtime);
+	struct dl_bw *dl_b;
+	int cpu, ret = 0;
+	unsigned long flags;
+
+	/*
+	 * Here we want to check the bandwidth not being set to some
+	 * value smaller than the currently allocated bandwidth in
+	 * any of the root_domains.
+	 *
+	 * FIXME: Cycling on all the CPUs is overdoing, but simpler than
+	 * cycling on root_domains... Discussion on different/better
+	 * solutions is welcome!
+	 */
+	for_each_possible_cpu(cpu) {
+		rcu_read_lock_sched();
+		dl_b = dl_bw_of(cpu);
+
+		raw_spin_lock_irqsave(&dl_b->lock, flags);
+		if (new_bw < dl_b->total_bw)
+			ret = -EBUSY;
+		raw_spin_unlock_irqrestore(&dl_b->lock, flags);
+
+		rcu_read_unlock_sched();
+
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
+void init_dl_rq_bw_ratio(struct dl_rq *dl_rq)
+{
+	if (global_rt_runtime() == RUNTIME_INF) {
+		dl_rq->bw_ratio = 1 << RATIO_SHIFT;
+		dl_rq->extra_bw = 1 << BW_SHIFT;
+	} else {
+		dl_rq->bw_ratio = to_ratio(global_rt_runtime(),
+			  global_rt_period()) >> (BW_SHIFT - RATIO_SHIFT);
+		dl_rq->extra_bw = to_ratio(global_rt_period(),
+						    global_rt_runtime());
+	}
+}
+
+void sched_dl_do_global(void)
+{
+	u64 new_bw = -1;
+	struct dl_bw *dl_b;
+	int cpu;
+	unsigned long flags;
+
+	def_dl_bandwidth.dl_period = global_rt_period();
+	def_dl_bandwidth.dl_runtime = global_rt_runtime();
+
+	if (global_rt_runtime() != RUNTIME_INF)
+		new_bw = to_ratio(global_rt_period(), global_rt_runtime());
+
+	/*
+	 * FIXME: As above...
+	 */
+	for_each_possible_cpu(cpu) {
+		rcu_read_lock_sched();
+		dl_b = dl_bw_of(cpu);
+
+		raw_spin_lock_irqsave(&dl_b->lock, flags);
+		dl_b->bw = new_bw;
+		raw_spin_unlock_irqrestore(&dl_b->lock, flags);
+
+		rcu_read_unlock_sched();
+		init_dl_rq_bw_ratio(&cpu_rq(cpu)->dl);
+	}
+}
+
+/*
+ * We must be sure that accepting a new task (or allowing changing the
+ * parameters of an existing one) is consistent with the bandwidth
+ * constraints. If yes, this function also accordingly updates the currently
+ * allocated bandwidth to reflect the new situation.
+ *
+ * This function is called while holding p's rq->lock.
+ */
+int sched_dl_overflow(struct task_struct *p, int policy,
+		      const struct sched_attr *attr)
+{
+	struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
+	u64 period = attr->sched_period ?: attr->sched_deadline;
+	u64 runtime = attr->sched_runtime;
+	u64 new_bw = dl_policy(policy) ? to_ratio(period, runtime) : 0;
+	int cpus, err = -1;
+
+	/* !deadline task may carry old deadline bandwidth */
+	if (new_bw == p->dl.dl_bw && task_has_dl_policy(p))
+		return 0;
+
+	/*
+	 * Either if a task, enters, leave, or stays -deadline but changes
+	 * its parameters, we may need to update accordingly the total
+	 * allocated bandwidth of the container.
+	 */
+	raw_spin_lock(&dl_b->lock);
+	cpus = dl_bw_cpus(task_cpu(p));
+	if (dl_policy(policy) && !task_has_dl_policy(p) &&
+	    !__dl_overflow(dl_b, cpus, 0, new_bw)) {
+		if (hrtimer_active(&p->dl.inactive_timer))
+			__dl_clear(dl_b, p->dl.dl_bw, cpus);
+		__dl_add(dl_b, new_bw, cpus);
+		err = 0;
+	} else if (dl_policy(policy) && task_has_dl_policy(p) &&
+		   !__dl_overflow(dl_b, cpus, p->dl.dl_bw, new_bw)) {
+		/*
+		 * XXX this is slightly incorrect: when the task
+		 * utilization decreases, we should delay the total
+		 * utilization change until the task's 0-lag point.
+		 * But this would require to set the task's "inactive
+		 * timer" when the task is not inactive.
+		 */
+		__dl_clear(dl_b, p->dl.dl_bw, cpus);
+		__dl_add(dl_b, new_bw, cpus);
+		dl_change_utilization(p, new_bw);
+		err = 0;
+	} else if (!dl_policy(policy) && task_has_dl_policy(p)) {
+		/*
+		 * Do not decrease the total deadline utilization here,
+		 * switched_from_dl() will take care to do it at the correct
+		 * (0-lag) time.
+		 */
+		err = 0;
+	}
+	raw_spin_unlock(&dl_b->lock);
+
+	return err;
+}
+
+/*
+ * This function initializes the sched_dl_entity of a newly becoming
+ * SCHED_DEADLINE task.
+ *
+ * Only the static values are considered here, the actual runtime and the
+ * absolute deadline will be properly calculated when the task is enqueued
+ * for the first time with its new policy.
+ */
+void __setparam_dl(struct task_struct *p, const struct sched_attr *attr)
+{
+	struct sched_dl_entity *dl_se = &p->dl;
+
+	dl_se->dl_runtime = attr->sched_runtime;
+	dl_se->dl_deadline = attr->sched_deadline;
+	dl_se->dl_period = attr->sched_period ?: dl_se->dl_deadline;
+	dl_se->flags = attr->sched_flags;
+	dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime);
+	dl_se->dl_density = to_ratio(dl_se->dl_deadline, dl_se->dl_runtime);
+}
+
+void __getparam_dl(struct task_struct *p, struct sched_attr *attr)
+{
+	struct sched_dl_entity *dl_se = &p->dl;
+
+	attr->sched_priority = p->rt_priority;
+	attr->sched_runtime = dl_se->dl_runtime;
+	attr->sched_deadline = dl_se->dl_deadline;
+	attr->sched_period = dl_se->dl_period;
+	attr->sched_flags = dl_se->flags;
+}
+
+/*
+ * This function validates the new parameters of a -deadline task.
+ * We ask for the deadline not being zero, and greater or equal
+ * than the runtime, as well as the period of being zero or
+ * greater than deadline. Furthermore, we have to be sure that
+ * user parameters are above the internal resolution of 1us (we
+ * check sched_runtime only since it is always the smaller one) and
+ * below 2^63 ns (we have to check both sched_deadline and
+ * sched_period, as the latter can be zero).
+ */
+bool __checkparam_dl(const struct sched_attr *attr)
+{
+	/* deadline != 0 */
+	if (attr->sched_deadline == 0)
+		return false;
+
+	/*
+	 * Since we truncate DL_SCALE bits, make sure we're at least
+	 * that big.
+	 */
+	if (attr->sched_runtime < (1ULL << DL_SCALE))
+		return false;
+
+	/*
+	 * Since we use the MSB for wrap-around and sign issues, make
+	 * sure it's not set (mind that period can be equal to zero).
+	 */
+	if (attr->sched_deadline & (1ULL << 63) ||
+	    attr->sched_period & (1ULL << 63))
+		return false;
+
+	/* runtime <= deadline <= period (if period != 0) */
+	if ((attr->sched_period != 0 &&
+	     attr->sched_period < attr->sched_deadline) ||
+	    attr->sched_deadline < attr->sched_runtime)
+		return false;
+
+	return true;
+}
+
+/*
+ * This function clears the sched_dl_entity static params.
+ */
+void __dl_clear_params(struct task_struct *p)
+{
+	struct sched_dl_entity *dl_se = &p->dl;
+
+	dl_se->dl_runtime = 0;
+	dl_se->dl_deadline = 0;
+	dl_se->dl_period = 0;
+	dl_se->flags = 0;
+	dl_se->dl_bw = 0;
+	dl_se->dl_density = 0;
+
+	dl_se->dl_throttled = 0;
+	dl_se->dl_yielded = 0;
+	dl_se->dl_non_contending = 0;
+}
+
+bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr)
+{
+	struct sched_dl_entity *dl_se = &p->dl;
+
+	if (dl_se->dl_runtime != attr->sched_runtime ||
+	    dl_se->dl_deadline != attr->sched_deadline ||
+	    dl_se->dl_period != attr->sched_period ||
+	    dl_se->flags != attr->sched_flags)
+		return true;
+
+	return false;
+}
+
+#ifdef CONFIG_SMP
+int dl_task_can_attach(struct task_struct *p, const struct cpumask *cs_cpus_allowed)
+{
+	unsigned int dest_cpu = cpumask_any_and(cpu_active_mask,
+							cs_cpus_allowed);
+	struct dl_bw *dl_b;
+	bool overflow;
+	int cpus, ret;
+	unsigned long flags;
+
+	rcu_read_lock_sched();
+	dl_b = dl_bw_of(dest_cpu);
+	raw_spin_lock_irqsave(&dl_b->lock, flags);
+	cpus = dl_bw_cpus(dest_cpu);
+	overflow = __dl_overflow(dl_b, cpus, 0, p->dl.dl_bw);
+	if (overflow)
+		ret = -EBUSY;
+	else {
+		/*
+		 * We reserve space for this task in the destination
+		 * root_domain, as we can't fail after this point.
+		 * We will free resources in the source root_domain
+		 * later on (see set_cpus_allowed_dl()).
+		 */
+		__dl_add(dl_b, p->dl.dl_bw, cpus);
+		ret = 0;
+	}
+	raw_spin_unlock_irqrestore(&dl_b->lock, flags);
+	rcu_read_unlock_sched();
+	return ret;
+}
+
+int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur,
+				 const struct cpumask *trial)
+{
+	int ret = 1, trial_cpus;
+	struct dl_bw *cur_dl_b;
+	unsigned long flags;
+
+	rcu_read_lock_sched();
+	cur_dl_b = dl_bw_of(cpumask_any(cur));
+	trial_cpus = cpumask_weight(trial);
+
+	raw_spin_lock_irqsave(&cur_dl_b->lock, flags);
+	if (cur_dl_b->bw != -1 &&
+	    cur_dl_b->bw * trial_cpus < cur_dl_b->total_bw)
+		ret = 0;
+	raw_spin_unlock_irqrestore(&cur_dl_b->lock, flags);
+	rcu_read_unlock_sched();
+	return ret;
+}
+
+bool dl_cpu_busy(unsigned int cpu)
+{
+	unsigned long flags;
+	struct dl_bw *dl_b;
+	bool overflow;
+	int cpus;
+
+	rcu_read_lock_sched();
+	dl_b = dl_bw_of(cpu);
+	raw_spin_lock_irqsave(&dl_b->lock, flags);
+	cpus = dl_bw_cpus(cpu);
+	overflow = __dl_overflow(dl_b, cpus, 0, 0);
+	raw_spin_unlock_irqrestore(&dl_b->lock, flags);
+	rcu_read_unlock_sched();
+	return overflow;
+}
+#endif
 
 #ifdef CONFIG_SCHED_DEBUG
 extern void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq);

kernel/sched/debug.c

···
 
 #define P(x) \
 	SEQ_printf(m, "  .%-30s: %Ld\n", #x, (long long)(rt_rq->x))
+#define PU(x) \
+	SEQ_printf(m, "  .%-30s: %lu\n", #x, (unsigned long)(rt_rq->x))
 #define PN(x) \
 	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", #x, SPLIT_NS(rt_rq->x))
 
-	P(rt_nr_running);
+	PU(rt_nr_running);
+#ifdef CONFIG_SMP
+	PU(rt_nr_migratory);
+#endif
 	P(rt_throttled);
 	PN(rt_time);
 	PN(rt_runtime);
 
 #undef PN
+#undef PU
 #undef P
 }
 
···
 	struct dl_bw *dl_bw;
 
 	SEQ_printf(m, "\ndl_rq[%d]:\n", cpu);
-	SEQ_printf(m, "  .%-30s: %ld\n", "dl_nr_running", dl_rq->dl_nr_running);
+
+#define PU(x) \
+	SEQ_printf(m, "  .%-30s: %lu\n", #x, (unsigned long)(dl_rq->x))
+
+	PU(dl_nr_running);
 #ifdef CONFIG_SMP
+	PU(dl_nr_migratory);
 	dl_bw = &cpu_rq(cpu)->rd->dl_bw;
 #else
 	dl_bw = &dl_rq->dl_bw;
 #endif
 	SEQ_printf(m, "  .%-30s: %lld\n", "dl_bw->bw", dl_bw->bw);
 	SEQ_printf(m, "  .%-30s: %lld\n", "dl_bw->total_bw", dl_bw->total_bw);
+
+#undef PU
 }
 
 extern __read_mostly int sched_clock_running;

kernel/sched/fair.c

···
 }
 
 /* Iterate thr' all leaf cfs_rq's on a runqueue */
-#define for_each_leaf_cfs_rq(rq, cfs_rq) \
-	list_for_each_entry_rcu(cfs_rq, &rq->leaf_cfs_rq_list, leaf_cfs_rq_list)
+#define for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos)			\
+	list_for_each_entry_safe(cfs_rq, pos, &rq->leaf_cfs_rq_list,	\
+				 leaf_cfs_rq_list)
 
 /* Do the two (enqueued) entities belong to the same group ? */
 static inline struct cfs_rq *
···
 {
 }
 
-#define for_each_leaf_cfs_rq(rq, cfs_rq) \
-		for (cfs_rq = &rq->cfs; cfs_rq; cfs_rq = NULL)
+#define for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos)	\
+		for (cfs_rq = &rq->cfs, pos = NULL; cfs_rq; cfs_rq = pos)
 
 static inline struct sched_entity *parent_entity(struct sched_entity *se)
 {
···
 static unsigned long source_load(int cpu, int type);
 static unsigned long target_load(int cpu, int type);
 static unsigned long capacity_of(int cpu);
-static long effective_load(struct task_group *tg, int cpu, long wl, long wg);
 
 /* Cached statistics for all CPUs within a node */
 struct numa_stats {
···
 		return;
 
 
-	down_read(&mm->mmap_sem);
+	if (!down_read_trylock(&mm->mmap_sem))
+		return;
 	vma = find_vma(mm, start);
 	if (!vma) {
 		reset_ptenuma_scan(p);
···
 		}
 	}
 }
+
+/*
+ * Can a task be moved from prev_cpu to this_cpu without causing a load
+ * imbalance that would trigger the load balancer?
+ */
+static inline bool numa_wake_affine(struct sched_domain *sd,
+				    struct task_struct *p, int this_cpu,
+				    int prev_cpu, int sync)
+{
+	struct numa_stats prev_load, this_load;
+	s64 this_eff_load, prev_eff_load;
+
+	update_numa_stats(&prev_load, cpu_to_node(prev_cpu));
+	update_numa_stats(&this_load, cpu_to_node(this_cpu));
+
+	/*
+	 * If sync wakeup then subtract the (maximum possible)
+	 * effect of the currently running task from the load
+	 * of the current CPU:
+	 */
+	if (sync) {
+		unsigned long current_load = task_h_load(current);
+
+		if (this_load.load > current_load)
+			this_load.load -= current_load;
+		else
+			this_load.load = 0;
+	}
+
+	/*
+	 * In low-load situations, where this_cpu's node is idle due to the
+	 * sync cause above having dropped this_load.load to 0, move the task.
+	 * Moving to an idle socket will not create a bad imbalance.
+	 *
+	 * Otherwise check if the nodes are near enough in load to allow this
+	 * task to be woken on this_cpu's node.
+	 */
+	if (this_load.load > 0) {
+		unsigned long task_load = task_h_load(p);
+
+		this_eff_load = 100;
+		this_eff_load *= prev_load.compute_capacity;
+
+		prev_eff_load = 100 + (sd->imbalance_pct - 100) / 2;
+		prev_eff_load *= this_load.compute_capacity;
+
+		this_eff_load *= this_load.load + task_load;
+		prev_eff_load *= prev_load.load - task_load;
+
+		return this_eff_load <= prev_eff_load;
+	}
+
+	return true;
+}
 #else
 static void task_tick_numa(struct rq *rq, struct task_struct *curr)
 {
···
 static inline void account_numa_dequeue(struct rq *rq, struct task_struct *p)
 {
 }
+
+#ifdef CONFIG_SMP
+static inline bool numa_wake_affine(struct sched_domain *sd,
+				    struct task_struct *p, int this_cpu,
+				    int prev_cpu, int sync)
+{
+	return true;
+}
+#endif /* !SMP */
 #endif /* CONFIG_NUMA_BALANCING */
 
 static void
···
 	/*
 	 * Step 2: update *_avg.
 	 */
-	sa->load_avg = div_u64(sa->load_sum, LOAD_AVG_MAX);
+	sa->load_avg = div_u64(sa->load_sum, LOAD_AVG_MAX - 1024 + sa->period_contrib);
 	if (cfs_rq) {
 		cfs_rq->runnable_load_avg =
-			div_u64(cfs_rq->runnable_load_sum, LOAD_AVG_MAX);
+			div_u64(cfs_rq->runnable_load_sum, LOAD_AVG_MAX - 1024 + sa->period_contrib);
 	}
-	sa->util_avg = sa->util_sum / LOAD_AVG_MAX;
+	sa->util_avg = sa->util_sum / (LOAD_AVG_MAX - 1024 + sa->period_contrib);
 
 	return 1;
 }
···
  * differential update where we store the last value we propagated. This in
  * turn allows skipping updates if the differential is 'small'.
  *
- * Updating tg's load_avg is necessary before update_cfs_share() (which is
- * done) and effective_load() (which is not done because it is too costly).
+ * Updating tg's load_avg is necessary before update_cfs_share().
  */
 static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force)
 {
···
 	hrtimer_cancel(&cfs_b->slack_timer);
 }
 
+/*
+ * Both these cpu hotplug callbacks race against unregister_fair_sched_group()
+ *
+ * The race is harmless, since modifying bandwidth settings of unhooked group
+ * bits doesn't do much.
+ */
+
+/* cpu online calback */
 static void __maybe_unused update_runtime_enabled(struct rq *rq)
 {
-	struct cfs_rq *cfs_rq;
+	struct task_group *tg;
 
-	for_each_leaf_cfs_rq(rq, cfs_rq) {
-		struct cfs_bandwidth *cfs_b = &cfs_rq->tg->cfs_bandwidth;
+	lockdep_assert_held(&rq->lock);
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(tg, &task_groups, list) {
+		struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth;
+		struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)];
 
 		raw_spin_lock(&cfs_b->lock);
 		cfs_rq->runtime_enabled = cfs_b->quota != RUNTIME_INF;
 		raw_spin_unlock(&cfs_b->lock);
 	}
+	rcu_read_unlock();
 }
 
+/* cpu offline callback */
 static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq)
 {
-	struct cfs_rq *cfs_rq;
+	struct task_group *tg;
 
-	for_each_leaf_cfs_rq(rq, cfs_rq) {
+	lockdep_assert_held(&rq->lock);
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(tg, &task_groups, list) {
+		struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)];
+
 		if (!cfs_rq->runtime_enabled)
 			continue;
 
···
 		if (cfs_rq_throttled(cfs_rq))
 			unthrottle_cfs_rq(cfs_rq);
 	}
+	rcu_read_unlock();
 }
 
 #else /* CONFIG_CFS_BANDWIDTH */
···
 	return 0;
 }
 
-#ifdef CONFIG_FAIR_GROUP_SCHED
-/*
- * effective_load() calculates the load change as seen from the root_task_group
- *
- * Adding load to a group doesn't make a group heavier, but can cause movement
- * of group shares between cpus. Assuming the shares were perfectly aligned one
- * can calculate the shift in shares.
- *
- * Calculate the effective load difference if @wl is added (subtracted) to @tg
- * on this @cpu and results in a total addition (subtraction) of @wg to the
- * total group weight.
- *
- * Given a runqueue weight distribution (rw_i) we can compute a shares
- * distribution (s_i) using:
- *
- *   s_i = rw_i / \Sum rw_j						(1)
- *
- * Suppose we have 4 CPUs and our @tg is a direct child of the root group and
- * has 7 equal weight tasks, distributed as below (rw_i), with the resulting
- * shares distribution (s_i):
- *
- *   rw_i = {   2,   4,   1,   0 }
- *   s_i  = { 2/7, 4/7, 1/7,   0 }
- *
- * As per wake_affine() we're interested in the load of two CPUs (the CPU the
- * task used to run on and the CPU the waker is running on), we need to
- * compute the effect of waking a task on either CPU and, in case of a sync
- * wakeup, compute the effect of the current task going to sleep.
- *
- * So for a change of @wl to the local @cpu with an overall group weight change
- * of @wl we can compute the new shares distribution (s'_i) using:
- *
- *   s'_i = (rw_i + @wl) / (@wg + \Sum rw_j)				(2)
- *
- * Suppose we're interested in CPUs 0 and 1, and want to compute the load
- * differences in waking a task to CPU 0. The additional task changes the
- * weight and shares distributions like:
- *
- *   rw'_i = {   3,   4,   1,   0 }
- *   s'_i  = { 3/8, 4/8, 1/8,   0 }
- *
- * We can then compute the difference in effective weight by using:
- *
- *   dw_i = S * (s'_i - s_i)						(3)
- *
- * Where 'S' is the group weight as seen by its parent.
- *
- * Therefore the effective change in loads on CPU 0 would be 5/56 (3/8 - 2/7)
- * times the weight of the group. The effect on CPU 1 would be -4/56 (4/8 -
- * 4/7) times the weight of the group.
- */
-static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
-{
-	struct sched_entity *se = tg->se[cpu];
-
-	if (!tg->parent)	/* the trivial, non-cgroup case */
-		return wl;
-
-	for_each_sched_entity(se) {
-		struct cfs_rq *cfs_rq = se->my_q;
-		long W, w = cfs_rq_load_avg(cfs_rq);
-
-		tg = cfs_rq->tg;
-
-		/*
-		 * W = @wg + \Sum rw_j
-		 */
-		W = wg + atomic_long_read(&tg->load_avg);
-
-		/* Ensure \Sum rw_j >= rw_i */
-		W -= cfs_rq->tg_load_avg_contrib;
-		W += w;
-
-		/*
-		 * w = rw_i + @wl
-		 */
-		w += wl;
-
-		/*
-		 * wl = S * s'_i; see (2)
-		 */
-		if (W > 0 && w < W)
-			wl = (w * (long)scale_load_down(tg->shares)) / W;
-		else
-			wl = scale_load_down(tg->shares);
-
-		/*
-		 * Per the above, wl is the new se->load.weight value; since
-		 * those are clipped to [MIN_SHARES, ...) do so now. See
-		 * calc_cfs_shares().
-		 */
-		if (wl < MIN_SHARES)
-			wl = MIN_SHARES;
-
-		/*
-		 * wl = dw_i = S * (s'_i - s_i); see (3)
-		 */
-		wl -= se->avg.load_avg;
-
-		/*
-		 * Recursively apply this logic to all parent groups to compute
-		 * the final effective load change on the root group. Since
-		 * only the @tg group gets extra weight, all parent groups can
-		 * only redistribute existing shares. @wl is the shift in shares
-		 * resulting from this level per the above.
-		 */
-		wg = 0;
-	}
-
-	return wl;
-}
-#else
-
-static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
-{
-	return wl;
-}
-
-#endif
-
 static void record_wakee(struct task_struct *p)
 {
 	/*
···
 static int wake_affine(struct sched_domain *sd, struct task_struct *p,
 		       int prev_cpu, int sync)
 {
-	s64 this_load, load;
-	s64 this_eff_load, prev_eff_load;
-	int idx, this_cpu;
-	struct task_group *tg;
-	unsigned long weight;
-	int balanced;
-
-	idx	  = sd->wake_idx;
-	this_cpu  = smp_processor_id();
-	load	  = source_load(prev_cpu, idx);
-	this_load = target_load(this_cpu, idx);
+	int this_cpu = smp_processor_id();
+	bool affine = false;
 
 	/*
-	 * If sync wakeup then subtract the (maximum possible)
-	 * effect of the currently running task from the load
-	 * of the current CPU:
+	 * Common case: CPUs are in the same socket, and select_idle_sibling()
+	 * will do its thing regardless of what we return:
 	 */
-	if (sync) {
-		tg = task_group(current);
-		weight = current->se.avg.load_avg;
-
-		this_load += effective_load(tg, this_cpu, -weight, -weight);
-		load += effective_load(tg, prev_cpu, 0, -weight);
-	}
-
-	tg = task_group(p);
-	weight = p->se.avg.load_avg;
-
-	/*
-	 * In low-load situations, where prev_cpu is idle and this_cpu is idle
-	 * due to the sync cause above having dropped this_load to 0, we'll
-	 * always have an imbalance, but there's really nothing you can do
-	 * about that, so that's good too.
-	 *
-	 * Otherwise check if either cpus are near enough in load to allow this
-	 * task to be woken on this_cpu.
-	 */
-	this_eff_load = 100;
-	this_eff_load *= capacity_of(prev_cpu);
-
-	prev_eff_load = 100 + (sd->imbalance_pct - 100) / 2;
-	prev_eff_load *= capacity_of(this_cpu);
-
-	if (this_load > 0) {
-		this_eff_load *= this_load +
-			effective_load(tg, this_cpu, weight, weight);
-
-		prev_eff_load *= load + effective_load(tg, prev_cpu, 0, weight);
-	}
-
-	balanced = this_eff_load <= prev_eff_load;
+	if (cpus_share_cache(prev_cpu, this_cpu))
+		affine = true;
+	else
+		affine = numa_wake_affine(sd, p, this_cpu, prev_cpu, sync);
 
 	schedstat_inc(p->se.statistics.nr_wakeups_affine_attempts);
+	if (affine) {
+		schedstat_inc(sd->ttwu_move_affine);
+		schedstat_inc(p->se.statistics.nr_wakeups_affine);
+	}
 
-	if (!balanced)
-		return 0;
-
-	schedstat_inc(sd->ttwu_move_affine);
-	schedstat_inc(p->se.statistics.nr_wakeups_affine);
-
-	return 1;
+	return affine;
 }
 
 static inline int task_util(struct task_struct *p);
···
 		int i;
 
 		/* Skip over this group if it has no CPUs allowed */
-		if (!cpumask_intersects(sched_group_cpus(group),
+		if (!cpumask_intersects(sched_group_span(group),
 					&p->cpus_allowed))
 			continue;
 
 		local_group = cpumask_test_cpu(this_cpu,
-					       sched_group_cpus(group));
+					       sched_group_span(group));
 
 		/*
 		 * Tally up the load of all CPUs in the group and find
···
 		runnable_load = 0;
 		max_spare_cap = 0;
 
-		for_each_cpu(i, sched_group_cpus(group)) {
+		for_each_cpu(i, sched_group_span(group)) {
 			/* Bias balancing toward cpus of our domain */
 			if (local_group)
 				load = source_load(i, load_idx);
···
 
 	/* Check if we have any choice: */
 	if (group->group_weight == 1)
-		return cpumask_first(sched_group_cpus(group));
+		return cpumask_first(sched_group_span(group));
 
 	/* Traverse only the allowed CPUs */
-	for_each_cpu_and(i, sched_group_cpus(group), &p->cpus_allowed) {
+	for_each_cpu_and(i, sched_group_span(group), &p->cpus_allowed) {
 		if (idle_cpu(i)) {
 			struct rq *rq = cpu_rq(i);
 			struct cpuidle_state *idle = idle_get_state(rq);
···
 
 	return shallowest_idle_cpu != -1 ? shallowest_idle_cpu : least_loaded_cpu;
 }
-
-/*
- * Implement a for_each_cpu() variant that starts the scan at a given cpu
- * (@start), and wraps around.
- *
- * This is used to scan for idle CPUs; such that not all CPUs looking for an
- * idle CPU find the same CPU. The down-side is that tasks tend to cycle
- * through the LLC domain.
- *
- * Especially tbench is found sensitive to this.
- */
-
-static int cpumask_next_wrap(int n, const struct cpumask *mask, int start, int *wrapped)
-{
-	int next;
-
-again:
-	next = find_next_bit(cpumask_bits(mask), nr_cpumask_bits, n+1);
-
-	if (*wrapped) {
-		if (next >= start)
-			return nr_cpumask_bits;
-	} else {
-		if (next >= nr_cpumask_bits) {
-			*wrapped = 1;
-			n = -1;
-			goto again;
-		}
-	}
-
-	return next;
-}
-
-#define for_each_cpu_wrap(cpu, mask, start, wrap)				\
-	for ((wrap) = 0, (cpu) = (start)-1;					\
-		(cpu) = cpumask_next_wrap((cpu), (mask), (start), &(wrap)),	\
-		(cpu) < nr_cpumask_bits; )
 
 #ifdef CONFIG_SCHED_SMT
 
···
 static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int target)
 {
 	struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_idle_mask);
-	int core, cpu, wrap;
+	int core, cpu;
 
 	if (!static_branch_likely(&sched_smt_present))
 		return -1;
···
 
 	cpumask_and(cpus, sched_domain_span(sd), &p->cpus_allowed);
 
-	for_each_cpu_wrap(core, cpus, target, wrap) {
+	for_each_cpu_wrap(core, cpus, target) {
 		bool idle = true;
 
 		for_each_cpu(cpu, cpu_smt_mask(core)) {
···
 static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int target)
 {
 	struct sched_domain *this_sd;
-	u64 avg_cost, avg_idle = this_rq()->avg_idle;
+	u64 avg_cost, avg_idle;
 	u64 time, cost;
 	s64 delta;
-	int cpu, wrap;
+	int cpu, nr = INT_MAX;
 
 	this_sd = rcu_dereference(*this_cpu_ptr(&sd_llc));
 	if (!this_sd)
 		return -1;
 
-	avg_cost = this_sd->avg_scan_cost;
-
 	/*
 	 * Due to large variance we need a large fuzz factor; hackbench in
 	 * particularly is sensitive here.
 	 */
-	if (sched_feat(SIS_AVG_CPU) && (avg_idle / 512) < avg_cost)
+	avg_idle = this_rq()->avg_idle / 512;
+	avg_cost = this_sd->avg_scan_cost + 1;
+
+	if (sched_feat(SIS_AVG_CPU) && avg_idle < avg_cost)
 		return -1;
+
+	if (sched_feat(SIS_PROP)) {
+		u64 span_avg = sd->span_weight * avg_idle;
+		if (span_avg > 4*avg_cost)
+			nr = div_u64(span_avg, avg_cost);
+		else
+			nr = 4;
+	}
 
 	time = local_clock();
 
-	for_each_cpu_wrap(cpu, sched_domain_span(sd), target, wrap) {
+	for_each_cpu_wrap(cpu, sched_domain_span(sd), target) {
+		if (!--nr)
+			return -1;
 		if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
 			continue;
 		if (idle_cpu(cpu))
···
 
 	if (affine_sd) {
 		sd = NULL; /* Prefer wake_affine over balance flags */
-		if (cpu != prev_cpu && wake_affine(affine_sd, p, prev_cpu, sync))
+		if (cpu == prev_cpu)
+			goto pick_cpu;
+
+		if (wake_affine(affine_sd, p, prev_cpu, sync))
 			new_cpu = cpu;
 	}
 
 	if (!sd) {
+ pick_cpu:
 		if (sd_flag & SD_BALANCE_WAKE) /* XXX always ? */
 			new_cpu = select_idle_sibling(p, prev_cpu, new_cpu);
 
···
 	if (entity_is_task(se) && unlikely(task_of(se)->policy == SCHED_IDLE))
 		return;
 
-	for_each_sched_entity(se)
+	for_each_sched_entity(se) {
+		if (SCHED_WARN_ON(!se->on_rq))
+			return;
 		cfs_rq_of(se)->last = se;
+	}
 }
 
 static void set_next_buddy(struct sched_entity *se)
···
 	if (entity_is_task(se) && unlikely(task_of(se)->policy == SCHED_IDLE))
 		return;
 
-	for_each_sched_entity(se)
+	for_each_sched_entity(se) {
+		if (SCHED_WARN_ON(!se->on_rq))
+			return;
 		cfs_rq_of(se)->next = se;
+	}
 }
 
 static void set_skip_buddy(struct sched_entity *se)
···
 	if (dst_nid == p->numa_preferred_nid)
 		return 0;
 
+	/* Leaving a core idle is often worse than degrading locality. */
+	if (env->idle != CPU_NOT_IDLE)
+		return -1;
+
 	if (numa_group) {
 		src_faults = group_faults(p, src_nid);
 		dst_faults = group_faults(p, dst_nid);
···
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
+
+static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
+{
+	if (cfs_rq->load.weight)
+		return false;
+
+	if (cfs_rq->avg.load_sum)
+		return false;
+
+	if (cfs_rq->avg.util_sum)
+		return false;
+
+	if (cfs_rq->runnable_load_sum)
+		return false;
+
+	return true;
+}
+
 static void update_blocked_averages(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
-	struct cfs_rq *cfs_rq;
+	struct cfs_rq *cfs_rq, *pos;
 	struct rq_flags rf;
 
 	rq_lock_irqsave(rq, &rf);
···
 	 * Iterates the task_group tree in a bottom up fashion, see
 	 * list_add_leaf_cfs_rq() for details.
 	 */
-	for_each_leaf_cfs_rq(rq, cfs_rq) {
+	for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos) {
 		struct sched_entity *se;
 
 		/* throttled entities do not contribute to load */
···
 		se = cfs_rq->tg->se[cpu];
 		if (se && !skip_blocked_update(se))
 			update_load_avg(se, 0);
+
+		/*
+		 * There can be a lot of idle CPU cgroups.  Don't let fully
+		 * decayed cfs_rqs linger on the list.
+		 */
+		if (cfs_rq_is_decayed(cfs_rq))
+			list_del_leaf_cfs_rq(cfs_rq);
 	}
 	rq_unlock_irqrestore(rq, &rf);
 }
···
 		 * span the current group.
 		 */
 
-		for_each_cpu(cpu, sched_group_cpus(sdg)) {
+		for_each_cpu(cpu, sched_group_span(sdg)) {
 			struct sched_group_capacity *sgc;
 			struct rq *rq = cpu_rq(cpu);
 
···
 
 	memset(sgs, 0, sizeof(*sgs));
 
-	for_each_cpu_and(i, sched_group_cpus(group), env->cpus) {
+	for_each_cpu_and(i, sched_group_span(group), env->cpus) {
 		struct rq *rq = cpu_rq(i);
 
 		/* Bias balancing toward cpus of our domain */
···
 		struct sg_lb_stats *sgs = &tmp_sgs;
 		int local_group;
 
-		local_group = cpumask_test_cpu(env->dst_cpu, sched_group_cpus(sg));
+		local_group = cpumask_test_cpu(env->dst_cpu, sched_group_span(sg));
 		if (local_group) {
 			sds->local = sg;
 			sgs = local;
···
 	unsigned long busiest_load = 0, busiest_capacity = 1;
 	int i;
 
-	for_each_cpu_and(i, sched_group_cpus(group), env->cpus) {
+	for_each_cpu_and(i, sched_group_span(group), env->cpus) {
 		unsigned long capacity, wl;
 		enum fbq_type rt;
 
···
 static int should_we_balance(struct lb_env *env)
 {
 	struct sched_group *sg = env->sd->groups;
-	struct cpumask *sg_cpus, *sg_mask;
 	int cpu, balance_cpu = -1;
 
 	/*
···
 	if (env->idle == CPU_NEWLY_IDLE)
 		return 1;
 
-	sg_cpus = sched_group_cpus(sg);
-	sg_mask = sched_group_mask(sg);
 	/* Try to find first idle cpu */
-	for_each_cpu_and(cpu, sg_cpus, env->cpus) {
-		if (!cpumask_test_cpu(cpu, sg_mask) || !idle_cpu(cpu))
+	for_each_cpu_and(cpu, group_balance_mask(sg), env->cpus) {
+		if (!idle_cpu(cpu))
 			continue;
 
 		balance_cpu = cpu;
···
 		.sd		= sd,
 		.dst_cpu	= this_cpu,
 		.dst_rq		= this_rq,
-		.dst_grpmask    = sched_group_cpus(sd->groups),
+		.dst_grpmask    = sched_group_span(sd->groups),
 		.idle		= idle,
 		.loop_break	= sched_nr_migrate_break,
 		.cpus		= cpus,
···
 	 * If this cpu is going down, then nothing needs to be done.
 	 */
 	if (!cpu_active(cpu))
+		return;
+
+	/* Spare idle load balancing on CPUs that don't want to be disturbed: */
+	if (!is_housekeeping_cpu(cpu))
 		return;
 
 	if (test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)))
···
 #ifdef CONFIG_SCHED_DEBUG
 void print_cfs_stats(struct seq_file *m, int cpu)
 {
-	struct cfs_rq *cfs_rq;
+	struct cfs_rq *cfs_rq, *pos;
 
 	rcu_read_lock();
-	for_each_leaf_cfs_rq(cpu_rq(cpu), cfs_rq)
+	for_each_leaf_cfs_rq_safe(cpu_rq(cpu), cfs_rq, pos)
 		print_cfs_rq(m, cpu, cfs_rq);
 	rcu_read_unlock();
 }

kernel/sched/features.h

···
  * When doing wakeups, attempt to limit superfluous scans of the LLC domain.
  */
 SCHED_FEAT(SIS_AVG_CPU, false)
+SCHED_FEAT(SIS_PROP, true)
 
 /*
  * Issue a WARN when we do multiple update_rq_clock() calls
···
 SCHED_FEAT(RT_PUSH_IPI, true)
 #endif
 
-SCHED_FEAT(FORCE_SD_OVERLAP, false)
 SCHED_FEAT(RT_RUNTIME_SHARE, true)
 SCHED_FEAT(LB_MIN, false)
 SCHED_FEAT(ATTACH_AGE_LOAD, true)

kernel/sched/idle.c

···
 	 */
 
 	__current_set_polling();
+	quiet_vmstat();
 	tick_nohz_idle_enter();
 
 	while (!need_resched()) {

kernel/sched/loadavg.c

···
  * load-average relies on per-cpu sampling from the tick, it is affected by
  * NO_HZ.
  *
- * The basic idea is to fold the nr_active delta into a global idle-delta upon
+ * The basic idea is to fold the nr_active delta into a global NO_HZ-delta upon
  * entering NO_HZ state such that we can include this as an 'extra' cpu delta
  * when we read the global state.
  *
···
  *  - When we go NO_HZ idle during the window, we can negate our sample
  *    contribution, causing under-accounting.
  *
- *    We avoid this by keeping two idle-delta counters and flipping them
+ *    We avoid this by keeping two NO_HZ-delta counters and flipping them
  *    when the window starts, thus separating old and new NO_HZ load.
  *
  *    The only trick is the slight shift in index flip for read vs write.
···
  *    r:0 0 1           1 0           0 1           1 0
  *    w:0 1 1           0 0           1 1           0 0
  *
- *    This ensures we'll fold the old idle contribution in this window while
+ *    This ensures we'll fold the old NO_HZ contribution in this window while
  *    accumlating the new one.
  *
- *  - When we wake up from NO_HZ idle during the window, we push up our
+ *  - When we wake up from NO_HZ during the window, we push up our
  *    contribution, since we effectively move our sample point to a known
  *    busy state.
  *
  *    This is solved by pushing the window forward, and thus skipping the
- *    sample, for this cpu (effectively using the idle-delta for this cpu which
+ *    sample, for this cpu (effectively using the NO_HZ-delta for this cpu which
  *    was in effect at the time the window opened). This also solves the issue
- *    of having to deal with a cpu having been in NOHZ idle for multiple
- *    LOAD_FREQ intervals.
+ *    of having to deal with a cpu having been in NO_HZ for multiple LOAD_FREQ
+ *    intervals.
  *
  * When making the ILB scale, we should try to pull this in as well.
  */
-static atomic_long_t calc_load_idle[2];
+static atomic_long_t calc_load_nohz[2];
 static int calc_load_idx;
 
 static inline int calc_load_write_idx(void)
···
 
 	/*
 	 * If the folding window started, make sure we start writing in the
-	 * next idle-delta.
+	 * next NO_HZ-delta.
 	 */
 	if (!time_before(jiffies, READ_ONCE(calc_load_update)))
 		idx++;
···
 	return calc_load_idx & 1;
 }
 
-void calc_load_enter_idle(void)
+void calc_load_nohz_start(void)
 {
 	struct rq *this_rq = this_rq();
 	long delta;
 
 	/*
-	 * We're going into NOHZ mode, if there's any pending delta, fold it
-	 * into the pending idle delta.
+	 * We're going into NO_HZ mode, if there's any pending delta, fold it
+	 * into the pending NO_HZ delta.
 	 */
 	delta = calc_load_fold_active(this_rq, 0);
 	if (delta) {
 		int idx = calc_load_write_idx();
 
-		atomic_long_add(delta, &calc_load_idle[idx]);
+		atomic_long_add(delta, &calc_load_nohz[idx]);
 	}
 }
 
-void calc_load_exit_idle(void)
+void calc_load_nohz_stop(void)
 {
 	struct rq *this_rq = this_rq();
 
···
 		this_rq->calc_load_update += LOAD_FREQ;
 }
 
-static long calc_load_fold_idle(void)
+static long calc_load_nohz_fold(void)
 {
 	int idx = calc_load_read_idx();
 	long delta = 0;
 
-	if (atomic_long_read(&calc_load_idle[idx]))
-		delta = atomic_long_xchg(&calc_load_idle[idx], 0);
+	if (atomic_long_read(&calc_load_nohz[idx]))
+		delta = atomic_long_xchg(&calc_load_nohz[idx], 0);
 
 	return delta;
 }
···
 
 /*
  * NO_HZ can leave us missing all per-cpu ticks calling
- * calc_load_account_active(), but since an idle CPU folds its delta into
- * calc_load_tasks_idle per calc_load_account_idle(), all we need to do is fold
- * in the pending idle delta if our idle period crossed a load cycle boundary.
+ * calc_load_fold_active(), but since a NO_HZ CPU folds its delta into
+ * calc_load_nohz per calc_load_nohz_start(), all we need to do is fold
+ * in the pending NO_HZ delta if our NO_HZ period crossed a load cycle boundary.
  *
  * Once we've updated the global active value, we need to apply the exponential
  * weights adjusted to the number of cycles missed.
···
 	}
 
 	/*
-	 * Flip the idle index...
+	 * Flip the NO_HZ index...
 	 *
 	 * Make sure we first write the new time then flip the index, so that
 	 * calc_load_write_idx() will see the new time when it reads the new
···
 }
 #else /* !CONFIG_NO_HZ_COMMON */
 
-static inline long calc_load_fold_idle(void) { return 0; }
+static inline long calc_load_nohz_fold(void) { return 0; }
 static inline void calc_global_nohz(void) { }
 
 #endif /* CONFIG_NO_HZ_COMMON */
···
 		return;
 
 	/*
-	 * Fold the 'old' idle-delta to include all NO_HZ cpus.
+	 * Fold the 'old' NO_HZ-delta to include all NO_HZ cpus.
 	 */
-	delta = calc_load_fold_idle();
+	delta = calc_load_nohz_fold();
 	if (delta)
 		atomic_long_add(delta, &calc_load_tasks);
 
···
 	WRITE_ONCE(calc_load_update, sample_window + LOAD_FREQ);
 
 	/*
-	 * In case we idled for multiple LOAD_FREQ intervals, catch up in bulk.
+	 * In case we went to NO_HZ for multiple LOAD_FREQ intervals
+	 * catch up in bulk.
 	 */
 	calc_global_nohz();
 }

kernel/sched/rt.c

···
 		int enqueue = 0;
 		struct rt_rq *rt_rq = sched_rt_period_rt_rq(rt_b, i);
 		struct rq *rq = rq_of_rt_rq(rt_rq);
+		int skip;
+
+		/*
+		 * When span == cpu_online_mask, taking each rq->lock
+		 * can be time-consuming. Try to avoid it when possible.
+		 */
+		raw_spin_lock(&rt_rq->rt_runtime_lock);
+		skip = !rt_rq->rt_time && !rt_rq->rt_nr_running;
+		raw_spin_unlock(&rt_rq->rt_runtime_lock);
+		if (skip)
+			continue;
 
 		raw_spin_lock(&rq->lock);
 		if (rt_rq->rt_time) {
···
 		 * pushing.
 		 */
 		task = pick_next_pushable_task(rq);
-		if (task_cpu(next_task) == rq->cpu && task == next_task) {
+		if (task == next_task) {
 			/*
 			 * The task hasn't migrated, and is still the next
 			 * eligible task, but we failed to find a run-queue
···
 
 	.update_curr		= update_curr_rt,
 };
+
+#ifdef CONFIG_RT_GROUP_SCHED
+/*
+ * Ensure that the real time constraints are schedulable.
+ */
+static DEFINE_MUTEX(rt_constraints_mutex);
+
+/* Must be called with tasklist_lock held */
+static inline int tg_has_rt_tasks(struct task_group *tg)
+{
+	struct task_struct *g, *p;
+
+	/*
+	 * Autogroups do not have RT tasks; see autogroup_create().
+	 */
+	if (task_group_is_autogroup(tg))
+		return 0;
+
+	for_each_process_thread(g, p) {
+		if (rt_task(p) && task_group(p) == tg)
+			return 1;
+	}
+
+	return 0;
+}
+
+struct rt_schedulable_data {
+	struct task_group *tg;
+	u64 rt_period;
+	u64 rt_runtime;
+};
+
+static int tg_rt_schedulable(struct task_group *tg, void *data)
+{
+	struct rt_schedulable_data *d = data;
+	struct task_group *child;
+	unsigned long total, sum = 0;
+	u64 period, runtime;
+
+	period = ktime_to_ns(tg->rt_bandwidth.rt_period);
+	runtime = tg->rt_bandwidth.rt_runtime;
+
+	if (tg == d->tg) {
+		period = d->rt_period;
+		runtime = d->rt_runtime;
+	}
+
+	/*
+	 * Cannot have more runtime than the period.
+	 */
+	if (runtime > period && runtime != RUNTIME_INF)
+		return -EINVAL;
+
+	/*
+	 * Ensure we don't starve existing RT tasks.
+	 */
+	if (rt_bandwidth_enabled() && !runtime && tg_has_rt_tasks(tg))
+		return -EBUSY;
+
+	total = to_ratio(period, runtime);
+
+	/*
+	 * Nobody can have more than the global setting allows.
+	 */
+	if (total > to_ratio(global_rt_period(), global_rt_runtime()))
+		return -EINVAL;
+
+	/*
+	 * The sum of our children's runtime should not exceed our own.
+	 */
+	list_for_each_entry_rcu(child, &tg->children, siblings) {
+		period = ktime_to_ns(child->rt_bandwidth.rt_period);
+		runtime = child->rt_bandwidth.rt_runtime;
+
+		if (child == d->tg) {
+			period = d->rt_period;
+			runtime = d->rt_runtime;
+		}
+
+		sum += to_ratio(period, runtime);
+	}
+
+	if (sum > total)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime)
+{
+	int ret;
+
+	struct rt_schedulable_data data = {
+		.tg = tg,
+		.rt_period = period,
+		.rt_runtime = runtime,
+	};
+
+	rcu_read_lock();
+	ret = walk_tg_tree(tg_rt_schedulable, tg_nop, &data);
+	rcu_read_unlock();
+
+	return ret;
+}
+
+static int tg_set_rt_bandwidth(struct task_group *tg,
+		u64 rt_period, u64 rt_runtime)
+{
+	int i, err = 0;
+
+	/*
+	 * Disallowing the root group RT runtime is BAD, it would disallow the
+	 * kernel creating (and or operating) RT threads.
+	 */
+	if (tg == &root_task_group && rt_runtime == 0)
+		return -EINVAL;
+
+	/* No period doesn't make any sense. */
+	if (rt_period == 0)
+		return -EINVAL;
+
+	mutex_lock(&rt_constraints_mutex);
+	read_lock(&tasklist_lock);
+	err = __rt_schedulable(tg, rt_period, rt_runtime);
+	if (err)
+		goto unlock;
+
+	raw_spin_lock_irq(&tg->rt_bandwidth.rt_runtime_lock);
+	tg->rt_bandwidth.rt_period = ns_to_ktime(rt_period);
+	tg->rt_bandwidth.rt_runtime = rt_runtime;
+
+	for_each_possible_cpu(i) {
+		struct rt_rq *rt_rq = tg->rt_rq[i];
+
+		raw_spin_lock(&rt_rq->rt_runtime_lock);
+		rt_rq->rt_runtime = rt_runtime;
+		raw_spin_unlock(&rt_rq->rt_runtime_lock);
+	}
+	raw_spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock);
+unlock:
+	read_unlock(&tasklist_lock);
+	mutex_unlock(&rt_constraints_mutex);
+
+	return err;
+}
+
+int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us)
+{
+	u64 rt_runtime, rt_period;
+
+	rt_period = ktime_to_ns(tg->rt_bandwidth.rt_period);
+	rt_runtime = (u64)rt_runtime_us * NSEC_PER_USEC;
+	if (rt_runtime_us < 0)
+		rt_runtime = RUNTIME_INF;
+
+	return tg_set_rt_bandwidth(tg, rt_period, rt_runtime);
+}
+
+long sched_group_rt_runtime(struct task_group *tg)
+{
+	u64 rt_runtime_us;
+
+	if (tg->rt_bandwidth.rt_runtime == RUNTIME_INF)
+		return -1;
+
+	rt_runtime_us = tg->rt_bandwidth.rt_runtime;
+	do_div(rt_runtime_us, NSEC_PER_USEC);
+	return rt_runtime_us;
+}
+
+int sched_group_set_rt_period(struct task_group *tg, u64 rt_period_us)
+{
+	u64 rt_runtime, rt_period;
+
+	rt_period = rt_period_us * NSEC_PER_USEC;
+	rt_runtime = tg->rt_bandwidth.rt_runtime;
+
+	return tg_set_rt_bandwidth(tg, rt_period, rt_runtime);
+}
+
+long sched_group_rt_period(struct task_group *tg)
+{
+	u64 rt_period_us;
+
+	rt_period_us = ktime_to_ns(tg->rt_bandwidth.rt_period);
+	do_div(rt_period_us, NSEC_PER_USEC);
+	return rt_period_us;
+}
+
+static int sched_rt_global_constraints(void)
+{
+	int ret = 0;
+
+	mutex_lock(&rt_constraints_mutex);
+	read_lock(&tasklist_lock);
+	ret = __rt_schedulable(NULL, 0, 0);
+	read_unlock(&tasklist_lock);
+	mutex_unlock(&rt_constraints_mutex);
+
+	return ret;
+}
+
+int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk)
+{
+	/* Don't accept realtime tasks when there is no way for them to run */
+	if (rt_task(tsk) && tg->rt_bandwidth.rt_runtime == 0)
+		return 0;
+
+	return 1;
+}
+
+#else /* !CONFIG_RT_GROUP_SCHED */
+static int sched_rt_global_constraints(void)
+{
+	unsigned long flags;
+	int i;
+
+	raw_spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags);
+	for_each_possible_cpu(i) {
+		struct rt_rq *rt_rq = &cpu_rq(i)->rt;
+
+		raw_spin_lock(&rt_rq->rt_runtime_lock);
+		rt_rq->rt_runtime = global_rt_runtime();
+		raw_spin_unlock(&rt_rq->rt_runtime_lock);
+	}
+	raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags);
+
+	return 0;
+}
+#endif /* CONFIG_RT_GROUP_SCHED */
+
+static int sched_rt_global_validate(void)
+{
+	if (sysctl_sched_rt_period <= 0)
+		return -EINVAL;
+
+	if ((sysctl_sched_rt_runtime != RUNTIME_INF) &&
+		(sysctl_sched_rt_runtime > sysctl_sched_rt_period))
+		return -EINVAL;
+
+	return 0;
+}
+
+static void sched_rt_do_global(void)
+{
+	def_rt_bandwidth.rt_runtime = global_rt_runtime();
+	def_rt_bandwidth.rt_period = ns_to_ktime(global_rt_period());
+}
+
+int sched_rt_handler(struct ctl_table *table, int write,
+		void __user *buffer, size_t *lenp,
+		loff_t *ppos)
+{
+	int old_period, old_runtime;
+	static DEFINE_MUTEX(mutex);
+	int ret;
+
+	mutex_lock(&mutex);
+	old_period = sysctl_sched_rt_period;
+	old_runtime = sysctl_sched_rt_runtime;
+
+	ret = proc_dointvec(table, write, buffer, lenp, ppos);
+
+	if (!ret && write) {
+		ret = sched_rt_global_validate();
+		if (ret)
+			goto undo;
+
+		ret = sched_dl_global_validate();
+		if (ret)
+			goto undo;
+
+		ret = sched_rt_global_constraints();
+		if (ret)
+			goto undo;
+
+		sched_rt_do_global();
+		sched_dl_do_global();
+	}
+	if (0) {
+undo:
+		sysctl_sched_rt_period = old_period;
+		sysctl_sched_rt_runtime = old_runtime;
+	}
+	mutex_unlock(&mutex);
+
+	return ret;
+}
+
+int sched_rr_handler(struct ctl_table *table, int write,
+		void __user *buffer, size_t *lenp,
+		loff_t *ppos)
+{
+	int ret;
+	static DEFINE_MUTEX(mutex);
+
+	mutex_lock(&mutex);
+	ret = proc_dointvec(table, write, buffer, lenp, ppos);
+	/*
+	 * Make sure that internally we keep jiffies.
+	 * Also, writing zero resets the timeslice to default:
+	 */
+	if (!ret && write) {
+		sched_rr_timeslice =
+			sysctl_sched_rr_timeslice <= 0 ? RR_TIMESLICE :
+			msecs_to_jiffies(sysctl_sched_rr_timeslice);
+	}
+	mutex_unlock(&mutex);
+	return ret;
+}
 
 #ifdef CONFIG_SCHED_DEBUG
 extern void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq);

kernel/sched/sched.h

···
 #include "cpuacct.h"
 
 #ifdef CONFIG_SCHED_DEBUG
-#define SCHED_WARN_ON(x)	WARN_ONCE(x, #x)
+# define SCHED_WARN_ON(x)	WARN_ONCE(x, #x)
 #else
-#define SCHED_WARN_ON(x)	((void)(x))
+# define SCHED_WARN_ON(x)	({ (void)(x), 0; })
 #endif
 
 struct rq;
···
 	return sysctl_sched_rt_runtime >= 0;
 }
 
-extern struct dl_bw *dl_bw_of(int i);
-
 struct dl_bw {
 	raw_spinlock_t lock;
 	u64 bw, total_bw;
 };
 
+static inline void __dl_update(struct dl_bw *dl_b, s64 bw);
+
 static inline
-void __dl_clear(struct dl_bw *dl_b, u64 tsk_bw)
+void __dl_clear(struct dl_bw *dl_b, u64 tsk_bw, int cpus)
 {
 	dl_b->total_bw -= tsk_bw;
+	__dl_update(dl_b, (s32)tsk_bw / cpus);
 }
 
 static inline
-void __dl_add(struct dl_bw *dl_b, u64 tsk_bw)
+void __dl_add(struct dl_bw *dl_b, u64 tsk_bw, int cpus)
 {
 	dl_b->total_bw += tsk_bw;
+	__dl_update(dl_b, -((s32)tsk_bw / cpus));
 }
 
 static inline
···
 	       dl_b->bw * cpus < dl_b->total_bw - old_bw + new_bw;
 }
 
+void dl_change_utilization(struct task_struct *p, u64 new_bw);
 extern void init_dl_bw(struct dl_bw *dl_b);
+extern int sched_dl_global_validate(void);
+extern void sched_dl_do_global(void);
+extern int sched_dl_overflow(struct task_struct *p, int policy,
+			     const struct sched_attr *attr);
+extern void __setparam_dl(struct task_struct *p, const struct sched_attr *attr);
+extern void __getparam_dl(struct task_struct *p, struct sched_attr *attr);
+extern bool __checkparam_dl(const struct sched_attr *attr);
+extern void __dl_clear_params(struct task_struct *p);
+extern bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr);
+extern int dl_task_can_attach(struct task_struct *p,
+			      const struct cpumask *cs_cpus_allowed);
+extern int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur,
+					const struct cpumask *trial);
+extern bool dl_cpu_busy(unsigned int cpu);
 
 #ifdef CONFIG_CGROUP_SCHED
 
···
 extern void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
 		struct sched_rt_entity *rt_se, int cpu,
 		struct sched_rt_entity *parent);
+extern int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us);
+extern int sched_group_set_rt_period(struct task_group *tg, u64 rt_period_us);
+extern long sched_group_rt_runtime(struct task_group *tg);
+extern long sched_group_rt_period(struct task_group *tg);
+extern int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk);
 
 extern struct task_group *sched_create_group(struct task_group *parent);
 extern void sched_online_group(struct task_group *tg,
···
 #else
 	struct dl_bw dl_bw;
 #endif
+	/*
+	 * "Active utilization" for this runqueue: increased when a
+	 * task wakes up (becomes TASK_RUNNING) and decreased when a
+	 * task blocks
+	 */
+	u64 running_bw;
+
+	/*
+	 * Utilization of the tasks "assigned" to this runqueue (including
+	 * the tasks that are in runqueue and the tasks that executed on this
+	 * CPU and blocked). Increased when a task moves to this runqueue, and
+	 * decreased when the task moves away (migrates, changes scheduling
+	 * policy, or terminates).
+	 * This is needed to compute the "inactive utilization" for the
+	 * runqueue (inactive utilization = this_bw - running_bw).
+	 */
+	u64 this_bw;
+	u64 extra_bw;
+
+	/*
+	 * Inverse of the fraction of CPU utilization that can be reclaimed
+	 * by the GRUB algorithm.
+	 */
+	u64 bw_ratio;
 };
 
 #ifdef CONFIG_SMP
···
 
 extern struct root_domain def_root_domain;
 extern struct mutex sched_domains_mutex;
-extern cpumask_var_t fallback_doms;
-extern cpumask_var_t sched_domains_tmpmask;
 
 extern void init_defrootdomain(void);
-extern int init_sched_domains(const struct cpumask *cpu_map);
+extern int sched_init_domains(const struct cpumask *cpu_map);
 extern void rq_attach_root(struct rq *rq, struct root_domain *rd);
 
 #endif /* CONFIG_SMP */
···
 	unsigned long next_update;
 	int imbalance; /* XXX unrelated to capacity but shared group state */
 
-	unsigned long cpumask[0]; /* iteration mask */
+#ifdef CONFIG_SCHED_DEBUG
+	int id;
+#endif
+
+	unsigned long cpumask[0]; /* balance mask */
 };
 
 struct sched_group {
···
 	unsigned long cpumask[0];
 };
 
-static inline struct cpumask *sched_group_cpus(struct sched_group *sg)
+static inline struct cpumask *sched_group_span(struct sched_group *sg)
 {
 	return to_cpumask(sg->cpumask);
 }
 
 /*
- * cpumask masking which cpus in the group are allowed to iterate up the domain
- * tree.
+ * See build_balance_mask().
  */
-static inline struct cpumask *sched_group_mask(struct sched_group *sg)
+static inline struct cpumask *group_balance_mask(struct sched_group *sg)
 {
 	return to_cpumask(sg->sgc->cpumask);
 }
···
  */
 static inline unsigned int group_first_cpu(struct sched_group *group)
 {
-	return cpumask_first(sched_group_cpus(group));
+	return cpumask_first(sched_group_span(group));
 }
 
 extern int group_balance_cpu(struct sched_group *sg);
···
 	curr->sched_class->set_curr_task(rq);
 }
 
+#ifdef CONFIG_SMP
 #define sched_class_highest (&stop_sched_class)
+#else
+#define sched_class_highest (&dl_sched_class)
+#endif
 #define for_each_class(class) \
    for (class = sched_class_highest; class; class = class->next)
 
···
 extern struct dl_bandwidth def_dl_bandwidth;
 extern void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime);
 extern void init_dl_task_timer(struct sched_dl_entity *dl_se);
+extern void init_dl_inactive_task_timer(struct sched_dl_entity *dl_se);
+extern void init_dl_rq_bw_ratio(struct dl_rq *dl_rq);
 
+#define BW_SHIFT	20
+#define BW_UNIT		(1 << BW_SHIFT)
+#define RATIO_SHIFT	8
 unsigned long to_ratio(u64 period, u64 runtime);
 
 extern void init_entity_runnable_average(struct sched_entity *se);
···
 #else
 static inline void nohz_balance_exit_idle(unsigned int cpu) { }
 #endif
+
+
+#ifdef CONFIG_SMP
+static inline
+void __dl_update(struct dl_bw *dl_b, s64 bw)
+{
+	struct root_domain *rd = container_of(dl_b, struct root_domain, dl_bw);
+	int i;
+
+	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
+			 "sched RCU must be held");
+	for_each_cpu_and(i, rd->span, cpu_active_mask) {
+		struct rq *rq = cpu_rq(i);
+
+		rq->dl.extra_bw += bw;
+	}
+}
+#else
+static inline
+void __dl_update(struct dl_bw *dl_b, s64 bw)
+{
+	struct dl_rq *dl = container_of(dl_b, struct dl_rq, dl_bw);
+
+	dl->extra_bw += bw;
+}
+#endif
+
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
 struct irqtime {

kernel/sched/topology.c

···
 
 /* Protected by sched_domains_mutex: */
 cpumask_var_t sched_domains_tmpmask;
+cpumask_var_t sched_domains_tmpmask2;
 
 #ifdef CONFIG_SCHED_DEBUG
 
···
 
 	cpumask_clear(groupmask);
 
-	printk(KERN_DEBUG "%*s domain %d: ", level, "", level);
+	printk(KERN_DEBUG "%*s domain-%d: ", level, "", level);
 
 	if (!(sd->flags & SD_LOAD_BALANCE)) {
 		printk("does not load-balance\n");
···
 		return -1;
 	}
 
-	printk(KERN_CONT "span %*pbl level %s\n",
+	printk(KERN_CONT "span=%*pbl level=%s\n",
 	       cpumask_pr_args(sched_domain_span(sd)), sd->name);
 
 	if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) {
 		printk(KERN_ERR "ERROR: domain->span does not contain "
 				"CPU%d\n", cpu);
 	}
-	if (!cpumask_test_cpu(cpu, sched_group_cpus(group))) {
+	if (!cpumask_test_cpu(cpu, sched_group_span(group))) {
 		printk(KERN_ERR "ERROR: domain->groups does not contain"
 				" CPU%d\n", cpu);
 	}
···
 			break;
 		}
 
-		if (!cpumask_weight(sched_group_cpus(group))) {
+		if (!cpumask_weight(sched_group_span(group))) {
 			printk(KERN_CONT "\n");
 			printk(KERN_ERR "ERROR: empty group\n");
 			break;
 		}
 
 		if (!(sd->flags & SD_OVERLAP) &&
-		    cpumask_intersects(groupmask, sched_group_cpus(group))) {
+		    cpumask_intersects(groupmask, sched_group_span(group))) {
 			printk(KERN_CONT "\n");
 			printk(KERN_ERR "ERROR: repeated CPUs\n");
 			break;
 		}
 
-		cpumask_or(groupmask, groupmask, sched_group_cpus(group));
+		cpumask_or(groupmask, groupmask, sched_group_span(group));
 
-		printk(KERN_CONT " %*pbl",
-		       cpumask_pr_args(sched_group_cpus(group)));
-		if (group->sgc->capacity != SCHED_CAPACITY_SCALE) {
-			printk(KERN_CONT " (cpu_capacity = %lu)",
-				group->sgc->capacity);
+		printk(KERN_CONT " %d:{ span=%*pbl",
+				group->sgc->id,
+				cpumask_pr_args(sched_group_span(group)));
+
+		if ((sd->flags & SD_OVERLAP) &&
+		    !cpumask_equal(group_balance_mask(group), sched_group_span(group))) {
+			printk(KERN_CONT " mask=%*pbl",
+				cpumask_pr_args(group_balance_mask(group)));
 		}
 
+		if (group->sgc->capacity != SCHED_CAPACITY_SCALE)
+			printk(KERN_CONT " cap=%lu", group->sgc->capacity);
+
+		if (group == sd->groups && sd->child &&
+		    !cpumask_equal(sched_domain_span(sd->child),
+				   sched_group_span(group))) {
+			printk(KERN_ERR "ERROR: domain->groups does not match domain->child\n");
+		}
+
+		printk(KERN_CONT " }");
+
 		group = group->next;
+
+		if (group != sd->groups)
+			printk(KERN_CONT ",");
+
 	} while (group != sd->groups);
 	printk(KERN_CONT "\n");
 
···
 		return;
 	}
 
-	printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu);
+	printk(KERN_DEBUG "CPU%d attaching sched-domain(s):\n", cpu);
 
 	for (;;) {
 		if (sched_domain_debug_one(sd, cpu, level, sched_domains_tmpmask))
···
 };
 
 /*
- * Build an iteration mask that can exclude certain CPUs from the upwards
- * domain traversal.
+ * Return the canonical balance CPU for this group, this is the first CPU
+ * of this group that's also in the balance mask.
  *
- * Asymmetric node setups can result in situations where the domain tree is of
- * unequal depth, make sure to skip domains that already cover the entire
- * range.
+ * The balance mask are all those CPUs that could actually end up at this
+ * group. See build_balance_mask().
  *
- * In that case build_sched_domains() will have terminated the iteration early
- * and our sibling sd spans will be empty. Domains should always include the
- * CPU they're built on, so check that.
+ * Also see should_we_balance().
  */
-static void build_group_mask(struct sched_domain *sd, struct sched_group *sg)
+int group_balance_cpu(struct sched_group *sg)
 {
-	const struct cpumask *span = sched_domain_span(sd);
+	return cpumask_first(group_balance_mask(sg));
+}
+
+
+/*
+ * NUMA topology (first read the regular topology blurb below)
+ *
+ * Given a node-distance table, for example:
+ *
+ *   node   0   1   2   3
+ *     0:  10  20  30  20
+ *     1:  20  10  20  30
+ *     2:  30  20  10  20
+ *     3:  20  30  20  10
+ *
+ * which represents a 4 node ring topology like:
+ *
+ *   0 ----- 1
+ *   |       |
+ *   |       |
+ *   |       |
+ *   3 ----- 2
+ *
+ * We want to construct domains and groups to represent this. The way we go
+ * about doing this is to build the domains on 'hops'. For each NUMA level we
+ * construct the mask of all nodes reachable in @level hops.
+ *
+ * For the above NUMA topology that gives 3 levels:
+ *
+ * NUMA-2	0-3		0-3		0-3		0-3
+ *  groups:	{0-1,3},{1-3}	{0-2},{0,2-3}	{1-3},{0-1,3}	{0,2-3},{0-2}
+ *
+ * NUMA-1	0-1,3		0-2		1-3		0,2-3
+ *  groups:	{0},{1},{3}	{0},{1},{2}	{1},{2},{3}	{0},{2},{3}
+ *
+ * NUMA-0	0		1		2		3
+ *
+ *
+ * As can be seen; things don't nicely line up as with the regular topology.
+ * When we iterate a domain in child domain chunks some nodes can be
+ * represented multiple times -- hence the "overlap" naming for this part of
+ * the topology.
+ *
+ * In order to minimize this overlap, we only build enough groups to cover the
+ * domain. For instance Node-0 NUMA-2 would only get groups: 0-1,3 and 1-3.
+ *
+ * Because:
+ *
+ *  - the first group of each domain is its child domain; this
+ *    gets us the first 0-1,3
+ *  - the only uncovered node is 2, who's child domain is 1-3.
+ *
+ * However, because of the overlap, computing a unique CPU for each group is
+ * more complicated. Consider for instance the groups of NODE-1 NUMA-2, both
+ * groups include the CPUs of Node-0, while those CPUs would not in fact ever
+ * end up at those groups (they would end up in group: 0-1,3).
+ *
+ * To correct this we have to introduce the group balance mask. This mask
+ * will contain those CPUs in the group that can reach this group given the
+ * (child) domain tree.
+ *
+ * With this we can once again compute balance_cpu and sched_group_capacity
+ * relations.
+ *
+ * XXX include words on how balance_cpu is unique and therefore can be
+ * used for sched_group_capacity links.
+ *
+ *
+ * Another 'interesting' topology is:
+ *
+ *   node   0   1   2   3
+ *     0:  10  20  20  30
+ *     1:  20  10  20  20
+ *     2:  20  20  10  20
+ *     3:  30  20  20  10
+ *
+ * Which looks a little like:
+ *
+ *   0 ----- 1
+ *   |     / |
+ *   |   /   |
+ *   | /     |
+ *   2 ----- 3
+ *
+ * This topology is asymmetric, nodes 1,2 are fully connected, but nodes 0,3
+ * are not.
+ *
+ * This leads to a few particularly weird cases where the sched_domain's are
+ * not of the same number for each cpu. Consider:
+ *
+ * NUMA-2	0-3						0-3
+ *  groups:	{0-2},{1-3}					{1-3},{0-2}
+ *
+ * NUMA-1	0-2		0-3		0-3		1-3
+ *
+ * NUMA-0	0		1		2		3
+ *
+ */
+
+
+/*
+ * Build the balance mask; it contains only those CPUs that can arrive at this
+ * group and should be considered to continue balancing.
+ *
+ * We do this during the group creation pass, therefore the group information
+ * isn't complete yet, however since each group represents a (child) domain we
+ * can fully construct this using the sched_domain bits (which are already
+ * complete).
+ */
+static void
+build_balance_mask(struct sched_domain *sd, struct sched_group *sg, struct cpumask *mask)
+{
+	const struct cpumask *sg_span = sched_group_span(sg);
 	struct sd_data *sdd = sd->private;
 	struct sched_domain *sibling;
 	int i;
 
-	for_each_cpu(i, span) {
+	cpumask_clear(mask);
+
+	for_each_cpu(i, sg_span) {
 		sibling = *per_cpu_ptr(sdd->sd, i);
-		if (!cpumask_test_cpu(i, sched_domain_span(sibling)))
+
+		/*
+		 * Can happen in the asymmetric case, where these siblings are
+		 * unused. The mask will not be empty because those CPUs that
+		 * do have the top domain _should_ span the domain.
+		 */
+		if (!sibling->child)
 			continue;
 
-		cpumask_set_cpu(i, sched_group_mask(sg));
+		/* If we would not end up here, we can't continue from here */
+		if (!cpumask_equal(sg_span, sched_domain_span(sibling->child)))
+			continue;
+
+		cpumask_set_cpu(i, mask);
 	}
+
+	/* We must not have empty masks here */
+	WARN_ON_ONCE(cpumask_empty(mask));
 }
 
 /*
- * Return the canonical balance CPU for this group, this is the first CPU
- * of this group that's also in the iteration mask.
+ * XXX: This creates per-node group entries; since the load-balancer will
+ * immediately access remote memory to construct this group's load-balance
+ * statistics having the groups node local is of dubious benefit.
  */
-int group_balance_cpu(struct sched_group *sg)
+static struct sched_group *
+build_group_from_child_sched_domain(struct sched_domain *sd, int cpu)
 {
-	return cpumask_first_and(sched_group_cpus(sg), sched_group_mask(sg));
+	struct sched_group *sg;
+	struct cpumask *sg_span;
+
+	sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(),
+			GFP_KERNEL, cpu_to_node(cpu));
+
+	if (!sg)
+		return NULL;
+
+	sg_span = sched_group_span(sg);
+	if (sd->child)
+		cpumask_copy(sg_span, sched_domain_span(sd->child));
+	else
+		cpumask_copy(sg_span, sched_domain_span(sd));
+
+	return sg;
+}
+
+static void init_overlap_sched_group(struct sched_domain *sd,
+				     struct sched_group *sg)
+{
+	struct cpumask *mask = sched_domains_tmpmask2;
+	struct sd_data *sdd = sd->private;
+	struct cpumask *sg_span;
+	int cpu;
+
+	build_balance_mask(sd, sg, mask);
+	cpu = cpumask_first_and(sched_group_span(sg), mask);
+
+	sg->sgc = *per_cpu_ptr(sdd->sgc, cpu);
+	if (atomic_inc_return(&sg->sgc->ref) == 1)
+		cpumask_copy(group_balance_mask(sg), mask);
+	else
+		WARN_ON_ONCE(!cpumask_equal(group_balance_mask(sg), mask));
+
+	/*
+	 * Initialize sgc->capacity such that even if we mess up the
+	 * domains and no possible iteration will get us here, we won't
+	 * die on a /0 trap.
+	 */
+	sg_span = sched_group_span(sg);
+	sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span);
+	sg->sgc->min_capacity = SCHED_CAPACITY_SCALE;
 }
 
 static int
 build_overlap_sched_groups(struct sched_domain *sd, int cpu)
 {
-	struct sched_group *first = NULL, *last = NULL, *groups = NULL, *sg;
+	struct sched_group *first = NULL, *last = NULL, *sg;
 	const struct cpumask *span = sched_domain_span(sd);
 	struct cpumask *covered = sched_domains_tmpmask;
 	struct sd_data *sdd = sd->private;
···
 
 	cpumask_clear(covered);
 
-	for_each_cpu(i, span) {
+	for_each_cpu_wrap(i, span, cpu) {
 		struct cpumask *sg_span;
 
 		if (cpumask_test_cpu(i, covered))
···
 
 		sibling = *per_cpu_ptr(sdd->sd, i);
 
-		/* See the comment near build_group_mask(). */
+		/*
+		 * Asymmetric node setups can result in situations where the
+		 * domain tree is of unequal depth, make sure to skip domains
+		 * that already cover the entire range.
+		 *
+		 * In that case build_sched_domains() will have terminated the
+		 * iteration early and our sibling sd spans will be empty.
+		 * Domains should always include the CPU they're built on, so
+		 * check that.
+		 */
 		if (!cpumask_test_cpu(i, sched_domain_span(sibling)))
 			continue;
 
-		sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(),
-				GFP_KERNEL, cpu_to_node(cpu));
-
+		sg = build_group_from_child_sched_domain(sibling, cpu);
 		if (!sg)
 			goto fail;
 
-		sg_span = sched_group_cpus(sg);
-		if (sibling->child)
-			cpumask_copy(sg_span, sched_domain_span(sibling->child));
-		else
-			cpumask_set_cpu(i, sg_span);
-
+		sg_span = sched_group_span(sg);
 		cpumask_or(covered, covered, sg_span);
 
-		sg->sgc = *per_cpu_ptr(sdd->sgc, i);
-		if (atomic_inc_return(&sg->sgc->ref) == 1)
-			build_group_mask(sd, sg);
-
-		/*
-		 * Initialize sgc->capacity such that even if we mess up the
-		 * domains and no possible iteration will get us here, we won't
-		 * die on a /0 trap.
-		 */
-		sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span);
-		sg->sgc->min_capacity = SCHED_CAPACITY_SCALE;
-
-		/*
-		 * Make sure the first group of this domain contains the
-		 * canonical balance CPU. Otherwise the sched_domain iteration
-		 * breaks. See update_sg_lb_stats().
-		 */
-		if ((!groups && cpumask_test_cpu(cpu, sg_span)) ||
-		    group_balance_cpu(sg) == cpu)
-			groups = sg;
+		init_overlap_sched_group(sd, sg);
 
 		if (!first)
 			first = sg;
···
 		last = sg;
 		last->next = first;
 	}
-	sd->groups = groups;
+	sd->groups = first;
 
 	return 0;
 
···
 	return -ENOMEM;
 }
 
-static int get_group(int cpu, struct sd_data *sdd, struct sched_group **sg)
+
+/*
+ * Package topology (also see the load-balance blurb in fair.c)
+ *
+ * The scheduler builds a tree structure to represent a number of important
+ * topology features. By default (default_topology[]) these include:
+ *
+ *  - Simultaneous multithreading (SMT)
+ *  - Multi-Core Cache (MC)
+ *  - Package (DIE)
+ *
+ * Where the last one more or less denotes everything up to a NUMA node.
+ *
+ * The tree consists of 3 primary data structures:
+ *
+ *	sched_domain -> sched_group -> sched_group_capacity
+ *	    ^ ^             ^ ^
+ *          `-'             `-'
+ *
+ * The sched_domains are per-cpu and have a two way link (parent & child) and
+ * denote the ever growing mask of CPUs belonging to that level of topology.
+ *
+ * Each sched_domain has a circular (double) linked list of sched_group's, each
+ * denoting the domains of the level below (or individual CPUs in case of the
+ * first domain level). The sched_group linked by a sched_domain includes the
+ * CPU of that sched_domain [*].
+ *
+ * Take for instance a 2 threaded, 2 core, 2 cache cluster part:
+ *
+ * CPU   0   1   2   3   4   5   6   7
+ *
+ * DIE  [                             ]
+ * MC   [             ] [             ]
+ * SMT  [     ] [     ] [     ] [     ]
+ *
+ *  - or -
+ *
+ * DIE  0-7 0-7 0-7 0-7 0-7 0-7 0-7 0-7
+ * MC	0-3 0-3 0-3 0-3 4-7 4-7 4-7 4-7
+ * SMT  0-1 0-1 2-3 2-3 4-5 4-5 6-7 6-7
+ *
+ * CPU   0   1   2   3   4   5   6   7
+ *
+ * One way to think about it is: sched_domain moves you up and down among these
+ * topology levels, while sched_group moves you sideways through it, at child
+ * domain granularity.
+ *
+ * sched_group_capacity ensures each unique sched_group has shared storage.
+ *
+ * There are two related construction problems, both require a CPU that
+ * uniquely identify each group (for a given domain):
+ *
+ *  - The first is the balance_cpu (see should_we_balance() and the
+ *    load-balance blub in fair.c); for each group we only want 1 CPU to
+ *    continue balancing at a higher domain.
+ *
+ *  - The second is the sched_group_capacity; we want all identical groups
+ *    to share a single sched_group_capacity.
+ *
+ * Since these topologies are exclusive by construction. That is, its
+ * impossible for an SMT thread to belong to multiple cores, and cores to
+ * be part of multiple caches. There is a very clear and unique location
+ * for each CPU in the hierarchy.
+ *
+ * Therefore computing a unique CPU for each group is trivial (the iteration
+ * mask is redundant and set all 1s; all CPUs in a group will end up at _that_
+ * group), we can simply pick the first CPU in each group.
+ *
+ *
+ * [*] in other words, the first group of each domain is its child domain.
+ */
+
+static struct sched_group *get_group(int cpu, struct sd_data *sdd)
 {
 	struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu);
 	struct sched_domain *child = sd->child;
+	struct sched_group *sg;
 
 	if (child)
 		cpu = cpumask_first(sched_domain_span(child));
 
-	if (sg) {
-		*sg = *per_cpu_ptr(sdd->sg, cpu);
-		(*sg)->sgc = *per_cpu_ptr(sdd->sgc, cpu);
+	sg = *per_cpu_ptr(sdd->sg, cpu);
+	sg->sgc = *per_cpu_ptr(sdd->sgc, cpu);
 
-		/* For claim_allocations: */
-		atomic_set(&(*sg)->sgc->ref, 1);
+	/* For claim_allocations: */
+	atomic_inc(&sg->ref);
+	atomic_inc(&sg->sgc->ref);
+
+	if (child) {
+		cpumask_copy(sched_group_span(sg), sched_domain_span(child));
+		cpumask_copy(group_balance_mask(sg), sched_group_span(sg));
+	} else {
+		cpumask_set_cpu(cpu, sched_group_span(sg));
+		cpumask_set_cpu(cpu, group_balance_mask(sg));
 	}
 
-	return cpu;
+	sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sched_group_span(sg));
+	sg->sgc->min_capacity = SCHED_CAPACITY_SCALE;
+
+	return sg;
 }
 
 /*
···
 	struct cpumask *covered;
 	int i;
 
-	get_group(cpu, sdd, &sd->groups);
-	atomic_inc(&sd->groups->ref);
-
-	if (cpu != cpumask_first(span))
-		return 0;
-
 	lockdep_assert_held(&sched_domains_mutex);
 	covered = sched_domains_tmpmask;
 
 	cpumask_clear(covered);
 
-	for_each_cpu(i, span) {
+	for_each_cpu_wrap(i, span, cpu) {
 		struct sched_group *sg;
-		int group, j;
 
 		if (cpumask_test_cpu(i, covered))
 			continue;
 
-		group = get_group(i, sdd, &sg);
-		cpumask_setall(sched_group_mask(sg));
+		sg = get_group(i, sdd);
 
-		for_each_cpu(j, span) {
-			if (get_group(j, sdd, NULL) != group)
-				continue;
-
-			cpumask_set_cpu(j, covered);
-			cpumask_set_cpu(j, sched_group_cpus(sg));
-		}
+		cpumask_or(covered, covered, sched_group_span(sg));
 
 		if (!first)
 			first = sg;
···
 		last = sg;
 	}
 	last->next = first;
+	sd->groups = first;
 
 	return 0;
 }
···
 	do {
 		int cpu, max_cpu = -1;
 
-		sg->group_weight = cpumask_weight(sched_group_cpus(sg));
+		sg->group_weight = cpumask_weight(sched_group_span(sg));
 
 		if (!(sd->flags & SD_ASYM_PACKING))
 			goto next;
 
-		for_each_cpu(cpu, sched_group_cpus(sg)) {
+		for_each_cpu(cpu, sched_group_span(sg)) {
 			if (max_cpu < 0)
 				max_cpu = cpu;
 			else if (sched_asym_prefer(cpu, max_cpu))
···
 			if (!sgc)
 				return -ENOMEM;
 
+#ifdef CONFIG_SCHED_DEBUG
+			sgc->id = j;
+#endif
+
 			*per_cpu_ptr(sdd->sgc, j) = sgc;
 		}
 	}
···
 			sd = build_sched_domain(tl, cpu_map, attr, sd, i);
 			if (tl == sched_domain_topology)
 				*per_cpu_ptr(d.sd, i) = sd;
-			if (tl->flags & SDTL_OVERLAP || sched_feat(FORCE_SD_OVERLAP))
+			if (tl->flags & SDTL_OVERLAP)
 				sd->flags |= SD_OVERLAP;
 			if (cpumask_equal(cpu_map, sched_domain_span(sd)))
 				break;
···
  * cpumask) fails, then fallback to a single sched domain,
  * as determined by the single cpumask fallback_doms.
  */
-cpumask_var_t				fallback_doms;
+static cpumask_var_t			fallback_doms;
 
 /*
  * arch_update_cpu_topology lets virtualized architectures update the
···
  * For now this just excludes isolated CPUs, but could be used to
  * exclude other special cases in the future.
  */
-int init_sched_domains(const struct cpumask *cpu_map)
+int sched_init_domains(const struct cpumask *cpu_map)
 {
 	int err;
+
+	zalloc_cpumask_var(&sched_domains_tmpmask, GFP_KERNEL);
+	zalloc_cpumask_var(&sched_domains_tmpmask2, GFP_KERNEL);
+	zalloc_cpumask_var(&fallback_doms, GFP_KERNEL);
 
 	arch_update_cpu_topology();
 	ndoms_cur = 1;

kernel/sched/wait.c

···
 #include <linux/hash.h>
 #include <linux/kthread.h>
 
-void __init_waitqueue_head(wait_queue_head_t *q, const char *name, struct lock_class_key *key)
+void __init_waitqueue_head(struct wait_queue_head *wq_head, const char *name, struct lock_class_key *key)
 {
-	spin_lock_init(&q->lock);
-	lockdep_set_class_and_name(&q->lock, key, name);
-	INIT_LIST_HEAD(&q->task_list);
+	spin_lock_init(&wq_head->lock);
+	lockdep_set_class_and_name(&wq_head->lock, key, name);
+	INIT_LIST_HEAD(&wq_head->head);
 }
 
 EXPORT_SYMBOL(__init_waitqueue_head);
 
-void add_wait_queue(wait_queue_head_t *q, wait_queue_t *wait)
+void add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
 {
 	unsigned long flags;
 
-	wait->flags &= ~WQ_FLAG_EXCLUSIVE;
-	spin_lock_irqsave(&q->lock, flags);
-	__add_wait_queue(q, wait);
-	spin_unlock_irqrestore(&q->lock, flags);
+	wq_entry->flags &= ~WQ_FLAG_EXCLUSIVE;
+	spin_lock_irqsave(&wq_head->lock, flags);
+	__add_wait_queue_entry_tail(wq_head, wq_entry);
+	spin_unlock_irqrestore(&wq_head->lock, flags);
 }
 EXPORT_SYMBOL(add_wait_queue);
 
-void add_wait_queue_exclusive(wait_queue_head_t *q, wait_queue_t *wait)
+void add_wait_queue_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
 {
 	unsigned long flags;
 
-	wait->flags |= WQ_FLAG_EXCLUSIVE;
-	spin_lock_irqsave(&q->lock, flags);
-	__add_wait_queue_tail(q, wait);
-	spin_unlock_irqrestore(&q->lock, flags);
+	wq_entry->flags |= WQ_FLAG_EXCLUSIVE;
+	spin_lock_irqsave(&wq_head->lock, flags);
+	__add_wait_queue_entry_tail(wq_head, wq_entry);
+	spin_unlock_irqrestore(&wq_head->lock, flags);
 }
 EXPORT_SYMBOL(add_wait_queue_exclusive);
 
-void remove_wait_queue(wait_queue_head_t *q, wait_queue_t *wait)
+void remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&q->lock, flags);
-	__remove_wait_queue(q, wait);
-	spin_unlock_irqrestore(&q->lock, flags);
+	spin_lock_irqsave(&wq_head->lock, flags);
+	__remove_wait_queue(wq_head, wq_entry);
+	spin_unlock_irqrestore(&wq_head->lock, flags);
 }
 EXPORT_SYMBOL(remove_wait_queue);
 
···
  * started to run but is not in state TASK_RUNNING. try_to_wake_up() returns
  * zero in this (rare) case, and we handle it by continuing to scan the queue.
  */
-static void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
+static void __wake_up_common(struct wait_queue_head *wq_head, unsigned int mode,
 			int nr_exclusive, int wake_flags, void *key)
 {
-	wait_queue_t *curr, *next;
+	wait_queue_entry_t *curr, *next;
 
-	list_for_each_entry_safe(curr, next, &q->task_list, task_list) {
+	list_for_each_entry_safe(curr, next, &wq_head->head, entry) {
 		unsigned flags = curr->flags;
 
 		if (curr->func(curr, mode, wake_flags, key) &&
···
 
 /**
  * __wake_up - wake up threads blocked on a waitqueue.
- * @q: the waitqueue
+ * @wq_head: the waitqueue
  * @mode: which threads
  * @nr_exclusive: how many wake-one or wake-many threads to wake up
  * @key: is directly passed to the wakeup function
···
  * It may be assumed that this function implies a write memory barrier before
  * changing the task state if and only if any tasks are woken up.
  */
-void __wake_up(wait_queue_head_t *q, unsigned int mode,
+void __wake_up(struct wait_queue_head *wq_head, unsigned int mode,
 			int nr_exclusive, void *key)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&q->lock, flags);
-	__wake_up_common(q, mode, nr_exclusive, 0, key);
-	spin_unlock_irqrestore(&q->lock, flags);
+	spin_lock_irqsave(&wq_head->lock, flags);
+	__wake_up_common(wq_head, mode, nr_exclusive, 0, key);
+	spin_unlock_irqrestore(&wq_head->lock, flags);
 }
 EXPORT_SYMBOL(__wake_up);
 
 /*
  * Same as __wake_up but called with the spinlock in wait_queue_head_t held.
  */
-void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr)
+void __wake_up_locked(struct wait_queue_head *wq_head, unsigned int mode, int nr)
 {
-	__wake_up_common(q, mode, nr, 0, NULL);
+	__wake_up_common(wq_head, mode, nr, 0, NULL);
 }
 EXPORT_SYMBOL_GPL(__wake_up_locked);
 
-void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key)
+void __wake_up_locked_key(struct wait_queue_head *wq_head, unsigned int mode, void *key)
 {
-	__wake_up_common(q, mode, 1, 0, key);
+	__wake_up_common(wq_head, mode, 1, 0, key);
 }
 EXPORT_SYMBOL_GPL(__wake_up_locked_key);
 
 /**
  * __wake_up_sync_key - wake up threads blocked on a waitqueue.
- * @q: the waitqueue
+ * @wq_head: the waitqueue
  * @mode: which threads
  * @nr_exclusive: how many wake-one or wake-many threads to wake up
  * @key: opaque value to be passed to wakeup targets
···
  * It may be assumed that this function implies a write memory barrier before
  * changing the task state if and only if any tasks are woken up.
  */
-void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode,
+void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode,
 			int nr_exclusive, void *key)
 {
 	unsigned long flags;
 	int wake_flags = 1; /* XXX WF_SYNC */
 
-	if (unlikely(!q))
+	if (unlikely(!wq_head))
 		return;
 
 	if (unlikely(nr_exclusive != 1))
 		wake_flags = 0;
 
-	spin_lock_irqsave(&q->lock, flags);
-	__wake_up_common(q, mode, nr_exclusive, wake_flags, key);
-	spin_unlock_irqrestore(&q->lock, flags);
+	spin_lock_irqsave(&wq_head->lock, flags);
+	__wake_up_common(wq_head, mode, nr_exclusive, wake_flags, key);
+	spin_unlock_irqrestore(&wq_head->lock, flags);
 }
 EXPORT_SYMBOL_GPL(__wake_up_sync_key);
 
 /*
  * __wake_up_sync - see __wake_up_sync_key()
  */
-void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive)
+void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode, int nr_exclusive)
 {
-	__wake_up_sync_key(q, mode, nr_exclusive, NULL);
+	__wake_up_sync_key(wq_head, mode, nr_exclusive, NULL);
 }
 EXPORT_SYMBOL_GPL(__wake_up_sync);	/* For internal use only */
 
···
  * loads to move into the critical region).
  */
 void
-prepare_to_wait(wait_queue_head_t *q, wait_queue_t *wait, int state)
+prepare_to_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state)
 {
 	unsigned long flags;
 
-	wait->flags &= ~WQ_FLAG_EXCLUSIVE;
-	spin_lock_irqsave(&q->lock, flags);
-	if (list_empty(&wait->task_list))
-		__add_wait_queue(q, wait);
+	wq_entry->flags &= ~WQ_FLAG_EXCLUSIVE;
+	spin_lock_irqsave(&wq_head->lock, flags);
+	if (list_empty(&wq_entry->entry))
+		__add_wait_queue(wq_head, wq_entry);
 	set_current_state(state);
-	spin_unlock_irqrestore(&q->lock, flags);
+	spin_unlock_irqrestore(&wq_head->lock, flags);
 }
 EXPORT_SYMBOL(prepare_to_wait);
 
 void
-prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int state)
+prepare_to_wait_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state)
 {
 	unsigned long flags;
 
-	wait->flags |= WQ_FLAG_EXCLUSIVE;
-	spin_lock_irqsave(&q->lock, flags);
-	if (list_empty(&wait->task_list))
-		__add_wait_queue_tail(q, wait);
+	wq_entry->flags |= WQ_FLAG_EXCLUSIVE;
+	spin_lock_irqsave(&wq_head->lock, flags);
+	if (list_empty(&wq_entry->entry))
+		__add_wait_queue_entry_tail(wq_head, wq_entry);
 	set_current_state(state);
-	spin_unlock_irqrestore(&q->lock, flags);
+	spin_unlock_irqrestore(&wq_head->lock, flags);
 }
 EXPORT_SYMBOL(prepare_to_wait_exclusive);
 
-void init_wait_entry(wait_queue_t *wait, int flags)
+void init_wait_entry(struct wait_queue_entry *wq_entry, int flags)
 {
-	wait->flags = flags;
-	wait->private = current;
-	wait->func = autoremove_wake_function;
-	INIT_LIST_HEAD(&wait->task_list);
+	wq_entry->flags = flags;
+	wq_entry->private = current;
+	wq_entry->func = autoremove_wake_function;
+	INIT_LIST_HEAD(&wq_entry->entry);
 }
 EXPORT_SYMBOL(init_wait_entry);
 
-long prepare_to_wait_event(wait_queue_head_t *q, wait_queue_t *wait, int state)
+long prepare_to_wait_event(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state)
 {
 	unsigned long flags;
 	long ret = 0;
 
-	spin_lock_irqsave(&q->lock, flags);
+	spin_lock_irqsave(&wq_head->lock, flags);
 	if (unlikely(signal_pending_state(state, current))) {
 		/*
 		 * Exclusive waiter must not fail if it was selected by wakeup,
···
 		 *
 		 * The caller will recheck the condition and return success if
 		 * we were already woken up, we can not miss the event because
-		 * wakeup locks/unlocks the same q->lock.
+		 * wakeup locks/unlocks the same wq_head->lock.
 		 *
 		 * But we need to ensure that set-condition + wakeup after that
 		 * can't see us, it should wake up another exclusive waiter if
 		 * we fail.
 		 */
-		list_del_init(&wait->task_list);
+		list_del_init(&wq_entry->entry);
 		ret = -ERESTARTSYS;
 	} else {
-		if (list_empty(&wait->task_list)) {
-			if (wait->flags & WQ_FLAG_EXCLUSIVE)
-				__add_wait_queue_tail(q, wait);
+		if (list_empty(&wq_entry->entry)) {
+			if (wq_entry->flags & WQ_FLAG_EXCLUSIVE)
+				__add_wait_queue_entry_tail(wq_head, wq_entry);
 			else
-				__add_wait_queue(q, wait);
+				__add_wait_queue(wq_head, wq_entry);
 		}
 		set_current_state(state);
 	}
-	spin_unlock_irqrestore(&q->lock, flags);
+	spin_unlock_irqrestore(&wq_head->lock, flags);
 
 	return ret;
 }
···
  * condition in the caller before they add the wait
  * entry to the wake queue.
  */
-int do_wait_intr(wait_queue_head_t *wq, wait_queue_t *wait)
+int do_wait_intr(wait_queue_head_t *wq, wait_queue_entry_t *wait)
 {
-	if (likely(list_empty(&wait->task_list)))
-		__add_wait_queue_tail(wq, wait);
+	if (likely(list_empty(&wait->entry)))
+		__add_wait_queue_entry_tail(wq, wait);
 
 	set_current_state(TASK_INTERRUPTIBLE);
 	if (signal_pending(current))
···
 }
 EXPORT_SYMBOL(do_wait_intr);
 
-int do_wait_intr_irq(wait_queue_head_t *wq, wait_queue_t *wait)
+int do_wait_intr_irq(wait_queue_head_t *wq, wait_queue_entry_t *wait)
 {
-	if (likely(list_empty(&wait->task_list)))
-		__add_wait_queue_tail(wq, wait);
+	if (likely(list_empty(&wait->entry)))
+		__add_wait_queue_entry_tail(wq, wait);
 
 	set_current_state(TASK_INTERRUPTIBLE);
 	if (signal_pending(current))
···
 
 /**
  * finish_wait - clean up after waiting in a queue
- * @q: waitqueue waited on
- * @wait: wait descriptor
+ * @wq_head: waitqueue waited on
+ * @wq_entry: wait descriptor
  *
  * Sets current thread back to running state and removes
  * the wait descriptor from the given waitqueue if still
  * queued.
  */
-void finish_wait(wait_queue_head_t *q, wait_queue_t *wait)
+void finish_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
 {
 	unsigned long flags;
 
···
 	 *    have _one_ other CPU that looks at or modifies
 	 *    the list).
 	 */
-	if (!list_empty_careful(&wait->task_list)) {
-		spin_lock_irqsave(&q->lock, flags);
-		list_del_init(&wait->task_list);
-		spin_unlock_irqrestore(&q->lock, flags);
+	if (!list_empty_careful(&wq_entry->entry)) {
+		spin_lock_irqsave(&wq_head->lock, flags);
+		list_del_init(&wq_entry->entry);
+		spin_unlock_irqrestore(&wq_head->lock, flags);
 	}
 }
 EXPORT_SYMBOL(finish_wait);
 
-int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key)
+int autoremove_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key)
 {
-	int ret = default_wake_function(wait, mode, sync, key);
+	int ret = default_wake_function(wq_entry, mode, sync, key);
 
 	if (ret)
-		list_del_init(&wait->task_list);
+		list_del_init(&wq_entry->entry);
 	return ret;
 }
 EXPORT_SYMBOL(autoremove_wake_function);
···
 /*
  * DEFINE_WAIT_FUNC(wait, woken_wake_func);
  *
- * add_wait_queue(&wq, &wait);
+ * add_wait_queue(&wq_head, &wait);
  * for (;;) {
  *     if (condition)
  *         break;
  *
  *     p->state = mode;				condition = true;
  *     smp_mb(); // A				smp_wmb(); // C
- *     if (!wait->flags & WQ_FLAG_WOKEN)	wait->flags |= WQ_FLAG_WOKEN;
+ *     if (!wq_entry->flags & WQ_FLAG_WOKEN)	wq_entry->flags |= WQ_FLAG_WOKEN;
  *         schedule()				try_to_wake_up();
  *     p->state = TASK_RUNNING;		    ~~~~~~~~~~~~~~~~~~
- *     wait->flags &= ~WQ_FLAG_WOKEN;		condition = true;
+ *     wq_entry->flags &= ~WQ_FLAG_WOKEN;		condition = true;
  *     smp_mb() // B				smp_wmb(); // C
- *						wait->flags |= WQ_FLAG_WOKEN;
+ *						wq_entry->flags |= WQ_FLAG_WOKEN;
  * }
- * remove_wait_queue(&wq, &wait);
+ * remove_wait_queue(&wq_head, &wait);
  *
  */
-long wait_woken(wait_queue_t *wait, unsigned mode, long timeout)
+long wait_woken(struct wait_queue_entry *wq_entry, unsigned mode, long timeout)
 {
 	set_current_state(mode); /* A */
 	/*
···
 	 * woken_wake_function() such that if we observe WQ_FLAG_WOKEN we must
 	 * also observe all state before the wakeup.
 	 */
-	if (!(wait->flags & WQ_FLAG_WOKEN) && !is_kthread_should_stop())
+	if (!(wq_entry->flags & WQ_FLAG_WOKEN) && !is_kthread_should_stop())
 		timeout = schedule_timeout(timeout);
 	__set_current_state(TASK_RUNNING);
 
···
 	 * condition being true _OR_ WQ_FLAG_WOKEN such that we will not miss
 	 * an event.
 	 */
-	smp_store_mb(wait->flags, wait->flags & ~WQ_FLAG_WOKEN); /* B */
+	smp_store_mb(wq_entry->flags, wq_entry->flags & ~WQ_FLAG_WOKEN); /* B */
 
 	return timeout;
 }
 EXPORT_SYMBOL(wait_woken);
 
-int woken_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key)
+int woken_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key)
 {
 	/*
 	 * Although this function is called under waitqueue lock, LOCK
···
 	 * and is paired with smp_store_mb() in wait_woken().
 	 */
 	smp_wmb(); /* C */
-	wait->flags |= WQ_FLAG_WOKEN;
+	wq_entry->flags |= WQ_FLAG_WOKEN;
 
-	return default_wake_function(wait, mode, sync, key);
+	return default_wake_function(wq_entry, mode, sync, key);
 }
 EXPORT_SYMBOL(woken_wake_function);
-
-int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *arg)
-{
-	struct wait_bit_key *key = arg;
-	struct wait_bit_queue *wait_bit
-		= container_of(wait, struct wait_bit_queue, wait);
-
-	if (wait_bit->key.flags != key->flags ||
-			wait_bit->key.bit_nr != key->bit_nr ||
-			test_bit(key->bit_nr, key->flags))
-		return 0;
-	else
-		return autoremove_wake_function(wait, mode, sync, key);
-}
-EXPORT_SYMBOL(wake_bit_function);
-
-/*
- * To allow interruptible waiting and asynchronous (i.e. nonblocking)
- * waiting, the actions of __wait_on_bit() and __wait_on_bit_lock() are
- * permitted return codes. Nonzero return codes halt waiting and return.
- */
-int __sched
-__wait_on_bit(wait_queue_head_t *wq, struct wait_bit_queue *q,
-	      wait_bit_action_f *action, unsigned mode)
-{
-	int ret = 0;
-
-	do {
-		prepare_to_wait(wq, &q->wait, mode);
-		if (test_bit(q->key.bit_nr, q->key.flags))
-			ret = (*action)(&q->key, mode);
-	} while (test_bit(q->key.bit_nr, q->key.flags) && !ret);
-	finish_wait(wq, &q->wait);
-	return ret;
-}
-EXPORT_SYMBOL(__wait_on_bit);
-
-int __sched out_of_line_wait_on_bit(void *word, int bit,
-				    wait_bit_action_f *action, unsigned mode)
-{
-	wait_queue_head_t *wq = bit_waitqueue(word, bit);
-	DEFINE_WAIT_BIT(wait, word, bit);
-
-	return __wait_on_bit(wq, &wait, action, mode);
-}
-EXPORT_SYMBOL(out_of_line_wait_on_bit);
-
-int __sched out_of_line_wait_on_bit_timeout(
-	void *word, int bit, wait_bit_action_f *action,
-	unsigned mode, unsigned long timeout)
-{
-	wait_queue_head_t *wq = bit_waitqueue(word, bit);
-	DEFINE_WAIT_BIT(wait, word, bit);
-
-	wait.key.timeout = jiffies + timeout;
-	return __wait_on_bit(wq, &wait, action, mode);
-}
-EXPORT_SYMBOL_GPL(out_of_line_wait_on_bit_timeout);
-
-int __sched
-__wait_on_bit_lock(wait_queue_head_t *wq, struct wait_bit_queue *q,
-			wait_bit_action_f *action, unsigned mode)
-{
-	int ret = 0;
-
-	for (;;) {
-		prepare_to_wait_exclusive(wq, &q->wait, mode);
-		if (test_bit(q->key.bit_nr, q->key.flags)) {
-			ret = action(&q->key, mode);
-			/*
-			 * See the comment in prepare_to_wait_event().
-			 * finish_wait() does not necessarily takes wq->lock,
-			 * but test_and_set_bit() implies mb() which pairs with
-			 * smp_mb__after_atomic() before wake_up_page().
-			 */
-			if (ret)
-				finish_wait(wq, &q->wait);
-		}
-		if (!test_and_set_bit(q->key.bit_nr, q->key.flags)) {
-			if (!ret)
-				finish_wait(wq, &q->wait);
-			return 0;
-		} else if (ret) {
-			return ret;
-		}
-	}
-}
-EXPORT_SYMBOL(__wait_on_bit_lock);
-
-int __sched out_of_line_wait_on_bit_lock(void *word, int bit,
-					 wait_bit_action_f *action, unsigned mode)
-{
-	wait_queue_head_t *wq = bit_waitqueue(word, bit);
-	DEFINE_WAIT_BIT(wait, word, bit);
-
-	return __wait_on_bit_lock(wq, &wait, action, mode);
-}
-EXPORT_SYMBOL(out_of_line_wait_on_bit_lock);
-
-void __wake_up_bit(wait_queue_head_t *wq, void *word, int bit)
-{
-	struct wait_bit_key key = __WAIT_BIT_KEY_INITIALIZER(word, bit);
-	if (waitqueue_active(wq))
-		__wake_up(wq, TASK_NORMAL, 1, &key);
-}
-EXPORT_SYMBOL(__wake_up_bit);
-
-/**
- * wake_up_bit - wake up a waiter on a bit
- * @word: the word being waited on, a kernel virtual address
- * @bit: the bit of the word being waited on
- *
- * There is a standard hashed waitqueue table for generic use. This
- * is the part of the hashtable's accessor API that wakes up waiters
- * on a bit. For instance, if one were to have waiters on a bitflag,
- * one would call wake_up_bit() after clearing the bit.
- *
- * In order for this to function properly, as it uses waitqueue_active()
- * internally, some kind of memory barrier must be done prior to calling
- * this. Typically, this will be smp_mb__after_atomic(), but in some
- * cases where bitflags are manipulated non-atomically under a lock, one
- * may need to use a less regular barrier, such fs/inode.c's smp_mb(),
- * because spin_unlock() does not guarantee a memory barrier.
- */
-void wake_up_bit(void *word, int bit)
-{
-	__wake_up_bit(bit_waitqueue(word, bit), word, bit);
-}
-EXPORT_SYMBOL(wake_up_bit);
-
-/*
- * Manipulate the atomic_t address to produce a better bit waitqueue table hash
- * index (we're keying off bit -1, but that would produce a horrible hash
- * value).
- */
-static inline wait_queue_head_t *atomic_t_waitqueue(atomic_t *p)
-{
-	if (BITS_PER_LONG == 64) {
-		unsigned long q = (unsigned long)p;
-		return bit_waitqueue((void *)(q & ~1), q & 1);
-	}
-	return bit_waitqueue(p, 0);
-}
-
-static int wake_atomic_t_function(wait_queue_t *wait, unsigned mode, int sync,
-				  void *arg)
-{
-	struct wait_bit_key *key = arg;
-	struct wait_bit_queue *wait_bit
-		= container_of(wait, struct wait_bit_queue, wait);
-	atomic_t *val = key->flags;
-
-	if (wait_bit->key.flags != key->flags ||
-	    wait_bit->key.bit_nr != key->bit_nr ||
-	    atomic_read(val) != 0)
-		return 0;
-	return autoremove_wake_function(wait, mode, sync, key);
-}
-
-/*
- * To allow interruptible waiting and asynchronous (i.e. nonblocking) waiting,
- * the actions of __wait_on_atomic_t() are permitted return codes.  Nonzero
- * return codes halt waiting and return.
- */
-static __sched
-int __wait_on_atomic_t(wait_queue_head_t *wq, struct wait_bit_queue *q,
-		       int (*action)(atomic_t *), unsigned mode)
-{
-	atomic_t *val;
-	int ret = 0;
-
-	do {
-		prepare_to_wait(wq, &q->wait, mode);
-		val = q->key.flags;
-		if (atomic_read(val) == 0)
-			break;
-		ret = (*action)(val);
-	} while (!ret && atomic_read(val) != 0);
-	finish_wait(wq, &q->wait);
-	return ret;
-}
-
-#define DEFINE_WAIT_ATOMIC_T(name, p)					\
-	struct wait_bit_queue name = {					\
-		.key = __WAIT_ATOMIC_T_KEY_INITIALIZER(p),		\
-		.wait	= {						\
-			.private	= current,			\
-			.func		= wake_atomic_t_function,	\
-			.task_list	=				\
-				LIST_HEAD_INIT((name).wait.task_list),	\
-		},							\
-	}
-
-__sched int out_of_line_wait_on_atomic_t(atomic_t *p, int (*action)(atomic_t *),
-					 unsigned mode)
-{
-	wait_queue_head_t *wq = atomic_t_waitqueue(p);
-	DEFINE_WAIT_ATOMIC_T(wait, p);
-
-	return __wait_on_atomic_t(wq, &wait, action, mode);
-}
-EXPORT_SYMBOL(out_of_line_wait_on_atomic_t);
-
-/**
- * wake_up_atomic_t - Wake up a waiter on a atomic_t
- * @p: The atomic_t being waited on, a kernel virtual address
- *
- * Wake up anyone waiting for the atomic_t to go to zero.
- *
- * Abuse the bit-waker function and its waitqueue hash table set (the atomic_t
- * check is done by the waiter's wake function, not the by the waker itself).
- */
-void wake_up_atomic_t(atomic_t *p)
-{
-	__wake_up_bit(atomic_t_waitqueue(p), p, WAIT_ATOMIC_T_BIT_NR);
-}
-EXPORT_SYMBOL(wake_up_atomic_t);
-
-__sched int bit_wait(struct wait_bit_key *word, int mode)
-{
-	schedule();
-	if (signal_pending_state(mode, current))
-		return -EINTR;
-	return 0;
-}
-EXPORT_SYMBOL(bit_wait);
-
-__sched int bit_wait_io(struct wait_bit_key *word, int mode)
-{
-	io_schedule();
-	if (signal_pending_state(mode, current))
-		return -EINTR;
-	return 0;
-}
-EXPORT_SYMBOL(bit_wait_io);
-
-__sched int bit_wait_timeout(struct wait_bit_key *word, int mode)
-{
-	unsigned long now = READ_ONCE(jiffies);
-	if (time_after_eq(now, word->timeout))
-		return -EAGAIN;
-	schedule_timeout(word->timeout - now);
-	if (signal_pending_state(mode, current))
-		return -EINTR;
-	return 0;
-}
-EXPORT_SYMBOL_GPL(bit_wait_timeout);
-
-__sched int bit_wait_io_timeout(struct wait_bit_key *word, int mode)
-{
-	unsigned long now = READ_ONCE(jiffies);
-	if (time_after_eq(now, word->timeout))
-		return -EAGAIN;
-	io_schedule_timeout(word->timeout - now);
-	if (signal_pending_state(mode, current))
-		return -EINTR;
-	return 0;
-}
-EXPORT_SYMBOL_GPL(bit_wait_io_timeout);

kernel/sched/wait_bit.c

···
+/*
+ * The implementation of the wait_bit*() and related waiting APIs:
+ */
+#include <linux/wait_bit.h>
+#include <linux/sched/signal.h>
+#include <linux/sched/debug.h>
+#include <linux/hash.h>
+
+#define WAIT_TABLE_BITS 8
+#define WAIT_TABLE_SIZE (1 << WAIT_TABLE_BITS)
+
+static wait_queue_head_t bit_wait_table[WAIT_TABLE_SIZE] __cacheline_aligned;
+
+wait_queue_head_t *bit_waitqueue(void *word, int bit)
+{
+	const int shift = BITS_PER_LONG == 32 ? 5 : 6;
+	unsigned long val = (unsigned long)word << shift | bit;
+
+	return bit_wait_table + hash_long(val, WAIT_TABLE_BITS);
+}
+EXPORT_SYMBOL(bit_waitqueue);
+
+int wake_bit_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *arg)
+{
+	struct wait_bit_key *key = arg;
+	struct wait_bit_queue_entry *wait_bit = container_of(wq_entry, struct wait_bit_queue_entry, wq_entry);
+
+	if (wait_bit->key.flags != key->flags ||
+			wait_bit->key.bit_nr != key->bit_nr ||
+			test_bit(key->bit_nr, key->flags))
+		return 0;
+	else
+		return autoremove_wake_function(wq_entry, mode, sync, key);
+}
+EXPORT_SYMBOL(wake_bit_function);
+
+/*
+ * To allow interruptible waiting and asynchronous (i.e. nonblocking)
+ * waiting, the actions of __wait_on_bit() and __wait_on_bit_lock() are
+ * permitted return codes. Nonzero return codes halt waiting and return.
+ */
+int __sched
+__wait_on_bit(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry,
+	      wait_bit_action_f *action, unsigned mode)
+{
+	int ret = 0;
+
+	do {
+		prepare_to_wait(wq_head, &wbq_entry->wq_entry, mode);
+		if (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags))
+			ret = (*action)(&wbq_entry->key, mode);
+	} while (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret);
+	finish_wait(wq_head, &wbq_entry->wq_entry);
+	return ret;
+}
+EXPORT_SYMBOL(__wait_on_bit);
+
+int __sched out_of_line_wait_on_bit(void *word, int bit,
+				    wait_bit_action_f *action, unsigned mode)
+{
+	struct wait_queue_head *wq_head = bit_waitqueue(word, bit);
+	DEFINE_WAIT_BIT(wq_entry, word, bit);
+
+	return __wait_on_bit(wq_head, &wq_entry, action, mode);
+}
+EXPORT_SYMBOL(out_of_line_wait_on_bit);
+
+int __sched out_of_line_wait_on_bit_timeout(
+	void *word, int bit, wait_bit_action_f *action,
+	unsigned mode, unsigned long timeout)
+{
+	struct wait_queue_head *wq_head = bit_waitqueue(word, bit);
+	DEFINE_WAIT_BIT(wq_entry, word, bit);
+
+	wq_entry.key.timeout = jiffies + timeout;
+	return __wait_on_bit(wq_head, &wq_entry, action, mode);
+}
+EXPORT_SYMBOL_GPL(out_of_line_wait_on_bit_timeout);
+
+int __sched
+__wait_on_bit_lock(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry,
+			wait_bit_action_f *action, unsigned mode)
+{
+	int ret = 0;
+
+	for (;;) {
+		prepare_to_wait_exclusive(wq_head, &wbq_entry->wq_entry, mode);
+		if (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags)) {
+			ret = action(&wbq_entry->key, mode);
+			/*
+			 * See the comment in prepare_to_wait_event().
+			 * finish_wait() does not necessarily takes wwq_head->lock,
+			 * but test_and_set_bit() implies mb() which pairs with
+			 * smp_mb__after_atomic() before wake_up_page().
+			 */
+			if (ret)
+				finish_wait(wq_head, &wbq_entry->wq_entry);
+		}
+		if (!test_and_set_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags)) {
+			if (!ret)
+				finish_wait(wq_head, &wbq_entry->wq_entry);
+			return 0;
+		} else if (ret) {
+			return ret;
+		}
+	}
+}
+EXPORT_SYMBOL(__wait_on_bit_lock);
+
+int __sched out_of_line_wait_on_bit_lock(void *word, int bit,
+					 wait_bit_action_f *action, unsigned mode)
+{
+	struct wait_queue_head *wq_head = bit_waitqueue(word, bit);
+	DEFINE_WAIT_BIT(wq_entry, word, bit);
+
+	return __wait_on_bit_lock(wq_head, &wq_entry, action, mode);
+}
+EXPORT_SYMBOL(out_of_line_wait_on_bit_lock);
+
+void __wake_up_bit(struct wait_queue_head *wq_head, void *word, int bit)
+{
+	struct wait_bit_key key = __WAIT_BIT_KEY_INITIALIZER(word, bit);
+	if (waitqueue_active(wq_head))
+		__wake_up(wq_head, TASK_NORMAL, 1, &key);
+}
+EXPORT_SYMBOL(__wake_up_bit);
+
+/**
+ * wake_up_bit - wake up a waiter on a bit
+ * @word: the word being waited on, a kernel virtual address
+ * @bit: the bit of the word being waited on
+ *
+ * There is a standard hashed waitqueue table for generic use. This
+ * is the part of the hashtable's accessor API that wakes up waiters
+ * on a bit. For instance, if one were to have waiters on a bitflag,
+ * one would call wake_up_bit() after clearing the bit.
+ *
+ * In order for this to function properly, as it uses waitqueue_active()
+ * internally, some kind of memory barrier must be done prior to calling
+ * this. Typically, this will be smp_mb__after_atomic(), but in some
+ * cases where bitflags are manipulated non-atomically under a lock, one
+ * may need to use a less regular barrier, such fs/inode.c's smp_mb(),
+ * because spin_unlock() does not guarantee a memory barrier.
+ */
+void wake_up_bit(void *word, int bit)
+{
+	__wake_up_bit(bit_waitqueue(word, bit), word, bit);
+}
+EXPORT_SYMBOL(wake_up_bit);
+
+/*
+ * Manipulate the atomic_t address to produce a better bit waitqueue table hash
+ * index (we're keying off bit -1, but that would produce a horrible hash
+ * value).
+ */
+static inline wait_queue_head_t *atomic_t_waitqueue(atomic_t *p)
+{
+	if (BITS_PER_LONG == 64) {
+		unsigned long q = (unsigned long)p;
+		return bit_waitqueue((void *)(q & ~1), q & 1);
+	}
+	return bit_waitqueue(p, 0);
+}
+
+static int wake_atomic_t_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync,
+				  void *arg)
+{
+	struct wait_bit_key *key = arg;
+	struct wait_bit_queue_entry *wait_bit = container_of(wq_entry, struct wait_bit_queue_entry, wq_entry);
+	atomic_t *val = key->flags;
+
+	if (wait_bit->key.flags != key->flags ||
+	    wait_bit->key.bit_nr != key->bit_nr ||
+	    atomic_read(val) != 0)
+		return 0;
+	return autoremove_wake_function(wq_entry, mode, sync, key);
+}
+
+/*
+ * To allow interruptible waiting and asynchronous (i.e. nonblocking) waiting,
+ * the actions of __wait_on_atomic_t() are permitted return codes.  Nonzero
+ * return codes halt waiting and return.
+ */
+static __sched
+int __wait_on_atomic_t(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry,
+		       int (*action)(atomic_t *), unsigned mode)
+{
+	atomic_t *val;
+	int ret = 0;
+
+	do {
+		prepare_to_wait(wq_head, &wbq_entry->wq_entry, mode);
+		val = wbq_entry->key.flags;
+		if (atomic_read(val) == 0)
+			break;
+		ret = (*action)(val);
+	} while (!ret && atomic_read(val) != 0);
+	finish_wait(wq_head, &wbq_entry->wq_entry);
+	return ret;
+}
+
+#define DEFINE_WAIT_ATOMIC_T(name, p)					\
+	struct wait_bit_queue_entry name = {				\
+		.key = __WAIT_ATOMIC_T_KEY_INITIALIZER(p),		\
+		.wq_entry = {						\
+			.private	= current,			\
+			.func		= wake_atomic_t_function,	\
+			.entry		=				\
+				LIST_HEAD_INIT((name).wq_entry.entry),	\
+		},							\
+	}
+
+__sched int out_of_line_wait_on_atomic_t(atomic_t *p, int (*action)(atomic_t *),
+					 unsigned mode)
+{
+	struct wait_queue_head *wq_head = atomic_t_waitqueue(p);
+	DEFINE_WAIT_ATOMIC_T(wq_entry, p);
+
+	return __wait_on_atomic_t(wq_head, &wq_entry, action, mode);
+}
+EXPORT_SYMBOL(out_of_line_wait_on_atomic_t);
+
+/**
+ * wake_up_atomic_t - Wake up a waiter on a atomic_t
+ * @p: The atomic_t being waited on, a kernel virtual address
+ *
+ * Wake up anyone waiting for the atomic_t to go to zero.
+ *
+ * Abuse the bit-waker function and its waitqueue hash table set (the atomic_t
+ * check is done by the waiter's wake function, not the by the waker itself).
+ */
+void wake_up_atomic_t(atomic_t *p)
+{
+	__wake_up_bit(atomic_t_waitqueue(p), p, WAIT_ATOMIC_T_BIT_NR);
+}
+EXPORT_SYMBOL(wake_up_atomic_t);
+
+__sched int bit_wait(struct wait_bit_key *word, int mode)
+{
+	schedule();
+	if (signal_pending_state(mode, current))
+		return -EINTR;
+	return 0;
+}
+EXPORT_SYMBOL(bit_wait);
+
+__sched int bit_wait_io(struct wait_bit_key *word, int mode)
+{
+	io_schedule();
+	if (signal_pending_state(mode, current))
+		return -EINTR;
+	return 0;
+}
+EXPORT_SYMBOL(bit_wait_io);
+
+__sched int bit_wait_timeout(struct wait_bit_key *word, int mode)
+{
+	unsigned long now = READ_ONCE(jiffies);
+	if (time_after_eq(now, word->timeout))
+		return -EAGAIN;
+	schedule_timeout(word->timeout - now);
+	if (signal_pending_state(mode, current))
+		return -EINTR;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(bit_wait_timeout);
+
+__sched int bit_wait_io_timeout(struct wait_bit_key *word, int mode)
+{
+	unsigned long now = READ_ONCE(jiffies);
+	if (time_after_eq(now, word->timeout))
+		return -EAGAIN;
+	io_schedule_timeout(word->timeout - now);
+	if (signal_pending_state(mode, current))
+		return -EINTR;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(bit_wait_io_timeout);
+
+void __init wait_bit_init(void)
+{
+	int i;
+
+	for (i = 0; i < WAIT_TABLE_SIZE; i++)
+		init_waitqueue_head(bit_wait_table + i);
+}

kernel/smp.c

···
 struct call_function_data {
 	struct call_single_data	__percpu *csd;
 	cpumask_var_t		cpumask;
+	cpumask_var_t		cpumask_ipi;
 };
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_function_data, cfd_data);
···
 	if (!zalloc_cpumask_var_node(&cfd->cpumask, GFP_KERNEL,
 				     cpu_to_node(cpu)))
 		return -ENOMEM;
+	if (!zalloc_cpumask_var_node(&cfd->cpumask_ipi, GFP_KERNEL,
+				     cpu_to_node(cpu))) {
+		free_cpumask_var(cfd->cpumask);
+		return -ENOMEM;
+	}
 	cfd->csd = alloc_percpu(struct call_single_data);
 	if (!cfd->csd) {
 		free_cpumask_var(cfd->cpumask);
+		free_cpumask_var(cfd->cpumask_ipi);
 		return -ENOMEM;
 	}
 
···
 	struct call_function_data *cfd = &per_cpu(cfd_data, cpu);
 
 	free_cpumask_var(cfd->cpumask);
+	free_cpumask_var(cfd->cpumask_ipi);
 	free_percpu(cfd->csd);
 	return 0;
 }
···
 	cfd = this_cpu_ptr(&cfd_data);
 
 	cpumask_and(cfd->cpumask, mask, cpu_online_mask);
-	cpumask_clear_cpu(this_cpu, cfd->cpumask);
+	__cpumask_clear_cpu(this_cpu, cfd->cpumask);
 
 	/* Some callers race with other cpus changing the passed mask */
 	if (unlikely(!cpumask_weight(cfd->cpumask)))
 		return;
 
+	cpumask_clear(cfd->cpumask_ipi);
 	for_each_cpu(cpu, cfd->cpumask) {
 		struct call_single_data *csd = per_cpu_ptr(cfd->csd, cpu);
 
···
 			csd->flags |= CSD_FLAG_SYNCHRONOUS;
 		csd->func = func;
 		csd->info = info;
-		llist_add(&csd->llist, &per_cpu(call_single_queue, cpu));
+		if (llist_add(&csd->llist, &per_cpu(call_single_queue, cpu)))
+			__cpumask_set_cpu(cpu, cfd->cpumask_ipi);
 	}
 
 	/* Send a message to all CPUs in the map */
-	arch_send_call_function_ipi_mask(cfd->cpumask);
+	arch_send_call_function_ipi_mask(cfd->cpumask_ipi);
 
 	if (wait) {
 		for_each_cpu(cpu, cfd->cpumask) {

kernel/time/clocksource.c

···
 			continue;
 		}
 
+		if (cs == curr_clocksource && cs->tick_stable)
+			cs->tick_stable(cs);
+
 		if (!(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES) &&
 		    (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS) &&
 		    (watchdog->flags & CLOCK_SOURCE_IS_CONTINUOUS)) {

kernel/time/tick-sched.c

···
 	update_ts_time_stats(smp_processor_id(), ts, now, NULL);
 	ts->idle_active = 0;
 
-	sched_clock_idle_wakeup_event(0);
+	sched_clock_idle_wakeup_event();
 }
 
 static ktime_t tick_nohz_start_idle(struct tick_sched *ts)
···
 	 * the scheduler tick in nohz_restart_sched_tick.
 	 */
 	if (!ts->tick_stopped) {
-		nohz_balance_enter_idle(cpu);
-		calc_load_enter_idle();
+		calc_load_nohz_start();
 		cpu_load_update_nohz_start();
 
 		ts->last_tick = hrtimer_get_expires(&ts->sched_timer);
···
 	 */
 	timer_clear_idle();
 
-	calc_load_exit_idle();
+	calc_load_nohz_stop();
 	touch_softlockup_watchdog_sched();
 	/*
 	 * Cancel the scheduled timer and restore the tick
···
 			ts->idle_expires = expires;
 		}
 
-		if (!was_stopped && ts->tick_stopped)
+		if (!was_stopped && ts->tick_stopped) {
 			ts->idle_jiffies = ts->last_jiffies;
+			nohz_balance_enter_idle(cpu);
+		}
 	}
 }
 

kernel/workqueue.c

···
 EXPORT_SYMBOL_GPL(flush_work);
 
 struct cwt_wait {
-	wait_queue_t		wait;
+	wait_queue_entry_t		wait;
 	struct work_struct	*work;
 };
 
-static int cwt_wakefn(wait_queue_t *wait, unsigned mode, int sync, void *key)
+static int cwt_wakefn(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
 {
 	struct cwt_wait *cwait = container_of(wait, struct cwt_wait, wait);
 

lib/cpumask.c

···
 }
 EXPORT_SYMBOL(cpumask_any_but);
 
+/**
+ * cpumask_next_wrap - helper to implement for_each_cpu_wrap
+ * @n: the cpu prior to the place to search
+ * @mask: the cpumask pointer
+ * @start: the start point of the iteration
+ * @wrap: assume @n crossing @start terminates the iteration
+ *
+ * Returns >= nr_cpu_ids on completion
+ *
+ * Note: the @wrap argument is required for the start condition when
+ * we cannot assume @start is set in @mask.
+ */
+int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap)
+{
+	int next;
+
+again:
+	next = cpumask_next(n, mask);
+
+	if (wrap && n < start && next >= start) {
+		return nr_cpumask_bits;
+
+	} else if (next >= nr_cpumask_bits) {
+		wrap = true;
+		n = -1;
+		goto again;
+	}
+
+	return next;
+}
+EXPORT_SYMBOL(cpumask_next_wrap);
+
 /* These are not inline because of header tangles. */
 #ifdef CONFIG_CPUMASK_OFFSTACK
 /**

lib/smp_processor_id.c

···
 	/*
 	 * It is valid to assume CPU-locality during early bootup:
 	 */
-	if (system_state != SYSTEM_RUNNING)
+	if (system_state < SYSTEM_SCHEDULING)
 		goto out;
 
 	/*

mm/filemap.c

···
 struct wait_page_queue {
 	struct page *page;
 	int bit_nr;
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 };
 
-static int wake_page_function(wait_queue_t *wait, unsigned mode, int sync, void *arg)
+static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, void *arg)
 {
 	struct wait_page_key *key = arg;
 	struct wait_page_queue *wait_page
···
 		struct page *page, int bit_nr, int state, bool lock)
 {
 	struct wait_page_queue wait_page;
-	wait_queue_t *wait = &wait_page.wait;
+	wait_queue_entry_t *wait = &wait_page.wait;
 	int ret = 0;
 
 	init_wait(wait);
···
 	for (;;) {
 		spin_lock_irq(&q->lock);
 
-		if (likely(list_empty(&wait->task_list))) {
+		if (likely(list_empty(&wait->entry))) {
 			if (lock)
-				__add_wait_queue_tail_exclusive(q, wait);
+				__add_wait_queue_entry_tail_exclusive(q, wait);
 			else
 				__add_wait_queue(q, wait);
 			SetPageWaiters(page);
···
  *
  * Add an arbitrary @waiter to the wait queue for the nominated @page.
  */
-void add_page_wait_queue(struct page *page, wait_queue_t *waiter)
+void add_page_wait_queue(struct page *page, wait_queue_entry_t *waiter)
 {
 	wait_queue_head_t *q = page_waitqueue(page);
 	unsigned long flags;

mm/memcontrol.c

···
 	 */
 	poll_table pt;
 	wait_queue_head_t *wqh;
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 	struct work_struct remove;
 };
 
···
 
 struct oom_wait_info {
 	struct mem_cgroup *memcg;
-	wait_queue_t	wait;
+	wait_queue_entry_t	wait;
 };
 
-static int memcg_oom_wake_function(wait_queue_t *wait,
+static int memcg_oom_wake_function(wait_queue_entry_t *wait,
 	unsigned mode, int sync, void *arg)
 {
 	struct mem_cgroup *wake_memcg = (struct mem_cgroup *)arg;
···
 	owait.wait.flags = 0;
 	owait.wait.func = memcg_oom_wake_function;
 	owait.wait.private = current;
-	INIT_LIST_HEAD(&owait.wait.task_list);
+	INIT_LIST_HEAD(&owait.wait.entry);
 
 	prepare_to_wait(&memcg_oom_waitq, &owait.wait, TASK_KILLABLE);
 	mem_cgroup_mark_under_oom(memcg);
···
  *
  * Called with wqh->lock held and interrupts disabled.
  */
-static int memcg_event_wake(wait_queue_t *wait, unsigned mode,
+static int memcg_event_wake(wait_queue_entry_t *wait, unsigned mode,
 			    int sync, void *key)
 {
 	struct mem_cgroup_event *event =

mm/mempool.c

···
 {
 	void *element;
 	unsigned long flags;
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 	gfp_t gfp_temp;
 
 	VM_WARN_ON_ONCE(gfp_mask & __GFP_ZERO);

mm/shmem.c

···
  * entry unconditionally - even if something else had already woken the
  * target.
  */
-static int synchronous_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key)
+static int synchronous_wake_function(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
 {
 	int ret = default_wake_function(wait, mode, sync, key);
-	list_del_init(&wait->task_list);
+	list_del_init(&wait->entry);
 	return ret;
 }
 
···
 		spin_lock(&inode->i_lock);
 		inode->i_private = NULL;
 		wake_up_all(&shmem_falloc_waitq);
-		WARN_ON_ONCE(!list_empty(&shmem_falloc_waitq.task_list));
+		WARN_ON_ONCE(!list_empty(&shmem_falloc_waitq.head));
 		spin_unlock(&inode->i_lock);
 		error = 0;
 		goto out;

mm/vmscan.c

···
 	pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid);
 	if (IS_ERR(pgdat->kswapd)) {
 		/* failure at boot is fatal */
-		BUG_ON(system_state == SYSTEM_BOOTING);
+		BUG_ON(system_state < SYSTEM_RUNNING);
 		pr_err("Failed to start kswapd on node %d\n", nid);
 		ret = PTR_ERR(pgdat->kswapd);
 		pgdat->kswapd = NULL;

net/9p/trans_fd.c

···
 
 struct p9_poll_wait {
 	struct p9_conn *conn;
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 	wait_queue_head_t *wait_addr;
 };
 
···
 	clear_bit(Wworksched, &m->wsched);
 }
 
-static int p9_pollwake(wait_queue_t *wait, unsigned int mode, int sync, void *key)
+static int p9_pollwake(wait_queue_entry_t *wait, unsigned int mode, int sync, void *key)
 {
 	struct p9_poll_wait *pwait =
 		container_of(wait, struct p9_poll_wait, wait);

net/bluetooth/bnep/core.c

···
 	struct net_device *dev = s->dev;
 	struct sock *sk = s->sock->sk;
 	struct sk_buff *skb;
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 
 	BT_DBG("");
 

net/bluetooth/cmtp/core.c

···
 	struct cmtp_session *session = arg;
 	struct sock *sk = session->sock->sk;
 	struct sk_buff *skb;
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 
 	BT_DBG("session %p", session);
 

net/bluetooth/hidp/core.c

···
 static int hidp_session_thread(void *arg)
 {
 	struct hidp_session *session = arg;
-	wait_queue_t ctrl_wait, intr_wait;
+	wait_queue_entry_t ctrl_wait, intr_wait;
 
 	BT_DBG("session %p", session);
 

net/core/datagram.c

···
 	return sk->sk_type == SOCK_SEQPACKET || sk->sk_type == SOCK_STREAM;
 }
 
-static int receiver_wake_function(wait_queue_t *wait, unsigned int mode, int sync,
+static int receiver_wake_function(wait_queue_entry_t *wait, unsigned int mode, int sync,
 				  void *key)
 {
 	unsigned long bits = (unsigned long)key;

net/unix/af_unix.c

···
  * are still connected to it and there's no way to inform "a polling
  * implementation" that it should let go of a certain wait queue
  *
- * In order to propagate a wake up, a wait_queue_t of the client
+ * In order to propagate a wake up, a wait_queue_entry_t of the client
  * socket is enqueued on the peer_wait queue of the server socket
  * whose wake function does a wake_up on the ordinary client socket
  * wait queue. This connection is established whenever a write (or
···
  * was relayed.
  */
 
-static int unix_dgram_peer_wake_relay(wait_queue_t *q, unsigned mode, int flags,
+static int unix_dgram_peer_wake_relay(wait_queue_entry_t *q, unsigned mode, int flags,
 				      void *key)
 {
 	struct unix_sock *u;

security/keys/internal.h

···
 #define _INTERNAL_H
 
 #include <linux/sched.h>
+#include <linux/wait_bit.h>
 #include <linux/cred.h>
 #include <linux/key-type.h>
 #include <linux/task_work.h>

sound/core/control.c

···
 		struct snd_ctl_event ev;
 		struct snd_kctl_event *kev;
 		while (list_empty(&ctl->events)) {
-			wait_queue_t wait;
+			wait_queue_entry_t wait;
 			if ((file->f_flags & O_NONBLOCK) != 0 || result > 0) {
 				err = -EAGAIN;
 				goto __end_lock;

sound/core/hwdep.c

···
 	int major = imajor(inode);
 	struct snd_hwdep *hw;
 	int err;
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 
 	if (major == snd_major) {
 		hw = snd_lookup_minor_data(iminor(inode),

sound/core/init.c

···
  */
 int snd_power_wait(struct snd_card *card, unsigned int power_state)
 {
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 	int result = 0;
 
 	/* fastpath */

sound/core/oss/pcm_oss.c

···
 	ssize_t result = 0;
 	snd_pcm_state_t state;
 	long res;
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 
 	runtime = substream->runtime;
 	init_waitqueue_entry(&wait, current);
···
 	struct snd_pcm_oss_file *pcm_oss_file;
 	struct snd_pcm_oss_setup setup[2];
 	int nonblock;
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 
 	err = nonseekable_open(inode, file);
 	if (err < 0)

sound/core/pcm_lib.c

···
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	int is_playback = substream->stream == SNDRV_PCM_STREAM_PLAYBACK;
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 	int err = 0;
 	snd_pcm_uframes_t avail = 0;
 	long wait_time, tout;

sound/core/pcm_native.c

···
 	struct snd_card *card;
 	struct snd_pcm_runtime *runtime;
 	struct snd_pcm_substream *s;
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 	int result = 0;
 	int nonblock = 0;
 
···
 static int snd_pcm_open(struct file *file, struct snd_pcm *pcm, int stream)
 {
 	int err;
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 
 	if (pcm == NULL) {
 		err = -ENODEV;

sound/core/rawmidi.c

···
 	int err;
 	struct snd_rawmidi *rmidi;
 	struct snd_rawmidi_file *rawmidi_file = NULL;
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 
 	if ((file->f_flags & O_APPEND) && !(file->f_flags & O_NONBLOCK)) 
 		return -EINVAL;		/* invalid combination */
···
 	while (count > 0) {
 		spin_lock_irq(&runtime->lock);
 		while (!snd_rawmidi_ready(substream)) {
-			wait_queue_t wait;
+			wait_queue_entry_t wait;
 			if ((file->f_flags & O_NONBLOCK) != 0 || result > 0) {
 				spin_unlock_irq(&runtime->lock);
 				return result > 0 ? result : -EAGAIN;
···
 	while (count > 0) {
 		spin_lock_irq(&runtime->lock);
 		while (!snd_rawmidi_ready_append(substream, count)) {
-			wait_queue_t wait;
+			wait_queue_entry_t wait;
 			if (file->f_flags & O_NONBLOCK) {
 				spin_unlock_irq(&runtime->lock);
 				return result > 0 ? result : -EAGAIN;
···
 	if (file->f_flags & O_DSYNC) {
 		spin_lock_irq(&runtime->lock);
 		while (runtime->avail != runtime->buffer_size) {
-			wait_queue_t wait;
+			wait_queue_entry_t wait;
 			unsigned int last_avail = runtime->avail;
 			init_waitqueue_entry(&wait, current);
 			add_wait_queue(&runtime->sleep, &wait);

sound/core/seq/seq_fifo.c

···
 {
 	struct snd_seq_event_cell *cell;
 	unsigned long flags;
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 
 	if (snd_BUG_ON(!f))
 		return -EINVAL;

sound/core/seq/seq_memory.c

···
 	struct snd_seq_event_cell *cell;
 	unsigned long flags;
 	int err = -EAGAIN;
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 
 	if (pool == NULL)
 		return -EINVAL;

sound/core/timer.c

···
 	spin_lock_irq(&tu->qlock);
 	while ((long)count - result >= unit) {
 		while (!tu->qused) {
-			wait_queue_t wait;
+			wait_queue_entry_t wait;
 
 			if ((file->f_flags & O_NONBLOCK) != 0 || result > 0) {
 				err = -EAGAIN;

sound/isa/wavefront/wavefront_synth.c

···
 				  int val, int port, unsigned long timeout)
 
 {
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 
 	init_waitqueue_entry(&wait, current);
 	spin_lock_irq(&dev->irq_lock);

sound/pci/mixart/mixart_core.c

···
 	struct mixart_msg resp;
 	u32 msg_frame = 0; /* set to 0, so it's no notification to wait for, but the answer */
 	int err;
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 	long timeout;
 
 	init_waitqueue_entry(&wait, current);
···
 				   struct mixart_msg *request, u32 notif_event)
 {
 	int err;
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 	long timeout;
 
 	if (snd_BUG_ON(!notif_event))

sound/pci/ymfpci/ymfpci_main.c

···
 
 static void snd_ymfpci_irq_wait(struct snd_ymfpci *chip)
 {
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 	int loops = 4;
 
 	while (loops-- > 0) {

virt/kvm/eventfd.c

···
  * Called with wqh->lock held and interrupts disabled
  */
 static int
-irqfd_wakeup(wait_queue_t *wait, unsigned mode, int sync, void *key)
+irqfd_wakeup(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
 {
 	struct kvm_kernel_irqfd *irqfd =
 		container_of(wait, struct kvm_kernel_irqfd, wait);