Merge f6f5ec0ee3 into baeb9a7d8b

After twenty years of development we finally reached the point to enable
   PREEMPT_RT support in the mainline kernel.
 
   All prerequisites are merged, so enable it on the supported architectures
   ARM64, RISCV and X86(32/64-bit).
 -----BEGIN PGP SIGNATURE-----
 
 iQJHBAABCgAxFiEEQp8+kY+LLUocC4bMphj1TA10mKEFAmbpR28THHRnbHhAbGlu
 dXRyb25peC5kZQAKCRCmGPVMDXSYoZXyD/972yR+oUuGNu8mb02H4kEcOCrsMOuM
 gMAneOjJY7+m4P2ois1gPoK6aPCT6AUlQj6DxOwjOhlmpWV6TaznymiVkKVZMhiT
 hRm5mWGxjXFtak/cnNixzAy/FsVGzBkQ/urPRfjb8MOGN9+9AOwmenXWsKUziaq9
 b/XrovT1nkr5DA7fTbKa8Mw4+9PpZC5HacAfZwtbtPhKX7CbbCQugjMcrzN3h17/
 g2EOPBLORfaEdWtnce6ZW+LZJ7y9dLdodoE6S2vZg/PfobsHqKhw7Kkw/Wr/iB1/
 dHWps2b55X+3Oo410vm7Q4sEHY2Z4n0a51mHR7N2pqsEZLke+70SQuQ9MU7JRAKv
 ospsscPKCnbG4T4XYk8k3g56bbuu1xHnfGYFA6vhE48IrHMB/601lkH5Z5Xl2a3W
 x7wrXRuAwkPuLxiTRSp3MH3asq8cwBZKXMVelC7ctr6QqQbF3DSJFbyWezIvP+kz
 IyI7L3CcRYtExW8wY5ocXvMmwCDzz7XaQL9cqegLtkyxPd3CifzcDc9T8vWd6Zec
 PLMHBOFEaBWy+AsiOevvpSmy1kE8Ncm29xqafP06MyECAPQRzaexwVVBA5zalXIG
 zHyd0KdrVE1vix82JKGPn7ngDxdZPR6AEXc1NE1135fBCzSYM15T3JYrGXTzhFR1
 c+Qo+hqOoKztbQ==
 =+vJ6
 -----END PGP SIGNATURE-----

Merge tag 'sched-rt-2024-09-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull RT enablement from Thomas Gleixner:
 "Enable PREEMPT_RT on supported architectures:

  After twenty years of development we finally reached the point to
  enable PREEMPT_RT support in the mainline kernel.

  All prerequisites are merged, so enable it on the supported
  architectures ARM64, RISCV and X86(32/64-bit)"

* tag 'sched-rt-2024-09-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  riscv: Allow to enable PREEMPT_RT.
  arm64: Allow to enable PREEMPT_RT.
  x86: Allow to enable PREEMPT_RT.

Documentation/scheduler/sched-deadline.rst

@@ -749,21 +749,19 @@ Appendix A. Test suite
  of the command line options. Please refer to rt-app documentation for more
  details (`<rt-app-sources>/doc/*.json`).
 
- The second testing application is a modification of schedtool, called
- schedtool-dl, which can be used to setup SCHED_DEADLINE parameters for a
- certain pid/application. schedtool-dl is available at:
- https://github.com/scheduler-tools/schedtool-dl.git.
+ The second testing application is done using chrt which has support
+ for SCHED_DEADLINE.
 
  The usage is straightforward::
 
-  # schedtool -E -t 10000000:100000000 -e ./my_cpuhog_app
+  # chrt -d -T 10000000 -D 100000000 0 ./my_cpuhog_app
 
  With this, my_cpuhog_app is put to run inside a SCHED_DEADLINE reservation
- of 10ms every 100ms (note that parameters are expressed in microseconds).
- You can also use schedtool to create a reservation for an already running
+ of 10ms every 100ms (note that parameters are expressed in nanoseconds).
+ You can also use chrt to create a reservation for an already running
  application, given that you know its pid::
 
-  # schedtool -E -t 10000000:100000000 my_app_pid
+  # chrt -d -T 10000000 -D 100000000 -p 0 my_app_pid
 
 Appendix B. Minimal main()
 ==========================

arch/arm64/Kconfig

@@ -101,6 +101,7 @@ config ARM64
 	select ARCH_SUPPORTS_NUMA_BALANCING
 	select ARCH_SUPPORTS_PAGE_TABLE_CHECK
 	select ARCH_SUPPORTS_PER_VMA_LOCK
+	select ARCH_SUPPORTS_RT
 	select ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
 	select ARCH_WANT_COMPAT_IPC_PARSE_VERSION if COMPAT
 	select ARCH_WANT_DEFAULT_BPF_JIT

arch/riscv/Kconfig

@@ -65,6 +65,7 @@ config RISCV
 	select ARCH_SUPPORTS_LTO_CLANG_THIN if LLD_VERSION >= 140000
 	select ARCH_SUPPORTS_PAGE_TABLE_CHECK if MMU
 	select ARCH_SUPPORTS_PER_VMA_LOCK if MMU
+	select ARCH_SUPPORTS_RT
 	select ARCH_SUPPORTS_SHADOW_CALL_STACK if HAVE_SHADOW_CALL_STACK
 	select ARCH_USE_CMPXCHG_LOCKREF if 64BIT
 	select ARCH_USE_MEMTEST

arch/x86/Kconfig

@@ -124,6 +124,7 @@ config X86
 	select ARCH_USES_CFI_TRAPS		if X86_64 && CFI_CLANG
 	select ARCH_SUPPORTS_LTO_CLANG
 	select ARCH_SUPPORTS_LTO_CLANG_THIN
+	select ARCH_SUPPORTS_RT
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_CMPXCHG_LOCKREF		if X86_CMPXCHG64
 	select ARCH_USE_MEMTEST

drivers/cpufreq/cppc_cpufreq.c

@@ -224,9 +224,9 @@ static void __init cppc_freq_invariance_init(void)
 		 * Fake (unused) bandwidth; workaround to "fix"
 		 * priority inheritance.
 		 */
-		.sched_runtime	= 1000000,
-		.sched_deadline = 10000000,
-		.sched_period	= 10000000,
+		.sched_runtime	= NSEC_PER_MSEC,
+		.sched_deadline = 10 * NSEC_PER_MSEC,
+		.sched_period	= 10 * NSEC_PER_MSEC,
 	};
 	int ret;
 

drivers/i2c/busses/i2c-aspeed.c

@@ -170,6 +170,13 @@ struct aspeed_i2c_bus {
 
 static int aspeed_i2c_reset(struct aspeed_i2c_bus *bus);
 
+/* precondition: bus.lock has been acquired. */
+static void aspeed_i2c_do_stop(struct aspeed_i2c_bus *bus)
+{
+	bus->master_state = ASPEED_I2C_MASTER_STOP;
+	writel(ASPEED_I2CD_M_STOP_CMD, bus->base + ASPEED_I2C_CMD_REG);
+}
+
 static int aspeed_i2c_recover_bus(struct aspeed_i2c_bus *bus)
 {
 	unsigned long time_left, flags;
@@ -187,7 +194,7 @@ static int aspeed_i2c_recover_bus(struct aspeed_i2c_bus *bus)
 			command);
 
 		reinit_completion(&bus->cmd_complete);
-		writel(ASPEED_I2CD_M_STOP_CMD, bus->base + ASPEED_I2C_CMD_REG);
+		aspeed_i2c_do_stop(bus);
 		spin_unlock_irqrestore(&bus->lock, flags);
 
 		time_left = wait_for_completion_timeout(
@@ -390,13 +397,6 @@ static void aspeed_i2c_do_start(struct aspeed_i2c_bus *bus)
 	writel(command, bus->base + ASPEED_I2C_CMD_REG);
 }
 
-/* precondition: bus.lock has been acquired. */
-static void aspeed_i2c_do_stop(struct aspeed_i2c_bus *bus)
-{
-	bus->master_state = ASPEED_I2C_MASTER_STOP;
-	writel(ASPEED_I2CD_M_STOP_CMD, bus->base + ASPEED_I2C_CMD_REG);
-}
-
 /* precondition: bus.lock has been acquired. */
 static void aspeed_i2c_next_msg_or_stop(struct aspeed_i2c_bus *bus)
 {

drivers/i2c/busses/i2c-isch.c

@@ -99,8 +99,7 @@ static int sch_transaction(void)
 	if (retries > MAX_RETRIES) {
 		dev_err(&sch_adapter.dev, "SMBus Timeout!\n");
 		result = -ETIMEDOUT;
-	}
-	if (temp & 0x04) {
+	} else if (temp & 0x04) {
 		result = -EIO;
 		dev_dbg(&sch_adapter.dev, "Bus collision! SMBus may be "
 			"locked until next hard reset. (sorry!)\n");

drivers/i2c/busses/i2c-qcom-geni.c

@@ -818,15 +818,13 @@ static int geni_i2c_probe(struct platform_device *pdev)
 	init_completion(&gi2c->done);
 	spin_lock_init(&gi2c->lock);
 	platform_set_drvdata(pdev, gi2c);
-	ret = devm_request_irq(dev, gi2c->irq, geni_i2c_irq, 0,
+	ret = devm_request_irq(dev, gi2c->irq, geni_i2c_irq, IRQF_NO_AUTOEN,
 			       dev_name(dev), gi2c);
 	if (ret) {
 		dev_err(dev, "Request_irq failed:%d: err:%d\n",
 			gi2c->irq, ret);
 		return ret;
 	}
-	/* Disable the interrupt so that the system can enter low-power mode */
-	disable_irq(gi2c->irq);
 	i2c_set_adapdata(&gi2c->adap, gi2c);
 	gi2c->adap.dev.parent = dev;
 	gi2c->adap.dev.of_node = dev->of_node;

drivers/i2c/busses/i2c-xiic.c

@@ -772,14 +772,17 @@ static irqreturn_t xiic_process(int irq, void *dev_id)
 			goto out;
 		}
 
-		xiic_fill_tx_fifo(i2c);
-
-		/* current message sent and there is space in the fifo */
-		if (!xiic_tx_space(i2c) && xiic_tx_fifo_space(i2c) >= 2) {
+		if (xiic_tx_space(i2c)) {
+			xiic_fill_tx_fifo(i2c);
+		} else {
+			/* current message fully written */
 			dev_dbg(i2c->adap.dev.parent,
 				"%s end of message sent, nmsgs: %d\n",
 				__func__, i2c->nmsgs);
-			if (i2c->nmsgs > 1) {
+			/* Don't move onto the next message until the TX FIFO empties,
+			 * to ensure that a NAK is not missed.
+			 */
+			if (i2c->nmsgs > 1 && (pend & XIIC_INTR_TX_EMPTY_MASK)) {
 				i2c->nmsgs--;
 				i2c->tx_msg++;
 				xfer_more = 1;
@@ -790,11 +793,7 @@ static irqreturn_t xiic_process(int irq, void *dev_id)
 					"%s Got TX IRQ but no more to do...\n",
 					__func__);
 			}
-		} else if (!xiic_tx_space(i2c) && (i2c->nmsgs == 1))
-			/* current frame is sent and is last,
-			 * make sure to disable tx half
-			 */
-			xiic_irq_dis(i2c, XIIC_INTR_TX_HALF_MASK);
+		}
 	}
 
 	if (pend & XIIC_INTR_BNB_MASK) {
@@ -844,23 +843,11 @@ static int xiic_bus_busy(struct xiic_i2c *i2c)
 	return (sr & XIIC_SR_BUS_BUSY_MASK) ? -EBUSY : 0;
 }
 
-static int xiic_busy(struct xiic_i2c *i2c)
+static int xiic_wait_not_busy(struct xiic_i2c *i2c)
 {
 	int tries = 3;
 	int err;
 
-	if (i2c->tx_msg || i2c->rx_msg)
-		return -EBUSY;
-
-	/* In single master mode bus can only be busy, when in use by this
-	 * driver. If the register indicates bus being busy for some reason we
-	 * should ignore it, since bus will never be released and i2c will be
-	 * stuck forever.
-	 */
-	if (i2c->singlemaster) {
-		return 0;
-	}
-
 	/* for instance if previous transfer was terminated due to TX error
 	 * it might be that the bus is on it's way to become available
 	 * give it at most 3 ms to wake
@@ -1104,13 +1091,36 @@ static int xiic_start_xfer(struct xiic_i2c *i2c, struct i2c_msg *msgs, int num)
 
 	mutex_lock(&i2c->lock);
 
-	ret = xiic_busy(i2c);
-	if (ret) {
+	if (i2c->tx_msg || i2c->rx_msg) {
 		dev_err(i2c->adap.dev.parent,
 			"cannot start a transfer while busy\n");
+		ret = -EBUSY;
 		goto out;
 	}
 
+	/* In single master mode bus can only be busy, when in use by this
+	 * driver. If the register indicates bus being busy for some reason we
+	 * should ignore it, since bus will never be released and i2c will be
+	 * stuck forever.
+	 */
+	if (!i2c->singlemaster) {
+		ret = xiic_wait_not_busy(i2c);
+		if (ret) {
+			/* If the bus is stuck in a busy state, such as due to spurious low
+			 * pulses on the bus causing a false start condition to be detected,
+			 * then try to recover by re-initializing the controller and check
+			 * again if the bus is still busy.
+			 */
+			dev_warn(i2c->adap.dev.parent, "I2C bus busy timeout, reinitializing\n");
+			ret = xiic_reinit(i2c);
+			if (ret)
+				goto out;
+			ret = xiic_wait_not_busy(i2c);
+			if (ret)
+				goto out;
+		}
+	}
+
 	i2c->tx_msg = msgs;
 	i2c->rx_msg = NULL;
 	i2c->nmsgs = num;

fs/bcachefs/six.c

@@ -335,7 +335,7 @@ static inline bool six_owner_running(struct six_lock *lock)
 	 */
 	rcu_read_lock();
 	struct task_struct *owner = READ_ONCE(lock->owner);
-	bool ret = owner ? owner_on_cpu(owner) : !rt_task(current);
+	bool ret = owner ? owner_on_cpu(owner) : !rt_or_dl_task(current);
 	rcu_read_unlock();
 
 	return ret;

fs/proc/base.c

@@ -2626,7 +2626,7 @@ static ssize_t timerslack_ns_write(struct file *file, const char __user *buf,
 	}
 
 	task_lock(p);
-	if (task_is_realtime(p))
+	if (rt_or_dl_task_policy(p))
 		slack_ns = 0;
 	else if (slack_ns == 0)
 		slack_ns = p->default_timer_slack_ns;

include/linux/ioprio.h

@@ -40,7 +40,7 @@ static inline int task_nice_ioclass(struct task_struct *task)
 {
 	if (task->policy == SCHED_IDLE)
 		return IOPRIO_CLASS_IDLE;
-	else if (task_is_realtime(task))
+	else if (rt_or_dl_task_policy(task))
 		return IOPRIO_CLASS_RT;
 	else
 		return IOPRIO_CLASS_BE;

include/linux/sched.h

@@ -149,8 +149,9 @@ struct user_event_mm;
  * Special states are those that do not use the normal wait-loop pattern. See
  * the comment with set_special_state().
  */
-#define is_special_task_state(state)				\
-	((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_PARKED | TASK_DEAD))
+#define is_special_task_state(state)					\
+	((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_PARKED |	\
+		    TASK_DEAD | TASK_FROZEN))
 
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
 # define debug_normal_state_change(state_value)				\
@@ -541,9 +542,14 @@ struct sched_entity {
 	struct rb_node			run_node;
 	u64				deadline;
 	u64				min_vruntime;
+	u64				min_slice;
 
 	struct list_head		group_node;
-	unsigned int			on_rq;
+	unsigned char			on_rq;
+	unsigned char			sched_delayed;
+	unsigned char			rel_deadline;
+	unsigned char			custom_slice;
+					/* hole */
 
 	u64				exec_start;
 	u64				sum_exec_runtime;
@@ -639,12 +645,26 @@ struct sched_dl_entity {
 	 *
 	 * @dl_overrun tells if the task asked to be informed about runtime
 	 * overruns.
+	 *
+	 * @dl_server tells if this is a server entity.
+	 *
+	 * @dl_defer tells if this is a deferred or regular server. For
+	 * now only defer server exists.
+	 *
+	 * @dl_defer_armed tells if the deferrable server is waiting
+	 * for the replenishment timer to activate it.
+	 *
+	 * @dl_defer_running tells if the deferrable server is actually
+	 * running, skipping the defer phase.
 	 */
 	unsigned int			dl_throttled      : 1;
 	unsigned int			dl_yielded        : 1;
 	unsigned int			dl_non_contending : 1;
 	unsigned int			dl_overrun	  : 1;
 	unsigned int			dl_server         : 1;
+	unsigned int			dl_defer	  : 1;
+	unsigned int			dl_defer_armed	  : 1;
+	unsigned int			dl_defer_running  : 1;
 
 	/*
 	 * Bandwidth enforcement timer. Each -deadline task has its
@@ -672,7 +692,7 @@ struct sched_dl_entity {
 	 */
 	struct rq			*rq;
 	dl_server_has_tasks_f		server_has_tasks;
-	dl_server_pick_f		server_pick;
+	dl_server_pick_f		server_pick_task;
 
 #ifdef CONFIG_RT_MUTEXES
 	/*

include/linux/sched/deadline.h

@@ -10,16 +10,16 @@
 
 #include <linux/sched.h>
 
-#define MAX_DL_PRIO		0
-
-static inline int dl_prio(int prio)
+static inline bool dl_prio(int prio)
 {
-	if (unlikely(prio < MAX_DL_PRIO))
-		return 1;
-	return 0;
+	return unlikely(prio < MAX_DL_PRIO);
 }
 
-static inline int dl_task(struct task_struct *p)
+/*
+ * Returns true if a task has a priority that belongs to DL class. PI-boosted
+ * tasks will return true. Use dl_policy() to ignore PI-boosted tasks.
+ */
+static inline bool dl_task(struct task_struct *p)
 {
 	return dl_prio(p->prio);
 }

include/linux/sched/prio.h

@@ -14,6 +14,7 @@
  */
 
 #define MAX_RT_PRIO		100
+#define MAX_DL_PRIO		0
 
 #define MAX_PRIO		(MAX_RT_PRIO + NICE_WIDTH)
 #define DEFAULT_PRIO		(MAX_RT_PRIO + NICE_WIDTH / 2)

include/linux/sched/rt.h

@@ -6,19 +6,40 @@
 
 struct task_struct;
 
-static inline int rt_prio(int prio)
+static inline bool rt_prio(int prio)
 {
-	if (unlikely(prio < MAX_RT_PRIO))
-		return 1;
-	return 0;
+	return unlikely(prio < MAX_RT_PRIO && prio >= MAX_DL_PRIO);
 }
 
-static inline int rt_task(struct task_struct *p)
+static inline bool rt_or_dl_prio(int prio)
+{
+	return unlikely(prio < MAX_RT_PRIO);
+}
+
+/*
+ * Returns true if a task has a priority that belongs to RT class. PI-boosted
+ * tasks will return true. Use rt_policy() to ignore PI-boosted tasks.
+ */
+static inline bool rt_task(struct task_struct *p)
 {
 	return rt_prio(p->prio);
 }
 
-static inline bool task_is_realtime(struct task_struct *tsk)
+/*
+ * Returns true if a task has a priority that belongs to RT or DL classes.
+ * PI-boosted tasks will return true. Use rt_or_dl_task_policy() to ignore
+ * PI-boosted tasks.
+ */
+static inline bool rt_or_dl_task(struct task_struct *p)
+{
+	return rt_or_dl_prio(p->prio);
+}
+
+/*
+ * Returns true if a task has a policy that belongs to RT or DL classes.
+ * PI-boosted tasks will return false.
+ */
+static inline bool rt_or_dl_task_policy(struct task_struct *tsk)
 {
 	int policy = tsk->policy;
 

include/uapi/linux/netfilter/nfnetlink_conntrack.h

@@ -3,7 +3,7 @@
 #define _IPCONNTRACK_NETLINK_H
 #include <linux/netfilter/nfnetlink.h>
 
-enum cntl_msg_types {
+enum ctnl_msg_types {
 	IPCTNL_MSG_CT_NEW,
 	IPCTNL_MSG_CT_GET,
 	IPCTNL_MSG_CT_DELETE,

include/uapi/linux/sched/types.h

@@ -58,9 +58,9 @@
  *
  * This is reflected by the following fields of the sched_attr structure:
  *
- *  @sched_deadline	representative of the task's deadline
- *  @sched_runtime	representative of the task's runtime
- *  @sched_period	representative of the task's period
+ *  @sched_deadline	representative of the task's deadline in nanoseconds
+ *  @sched_runtime	representative of the task's runtime in nanoseconds
+ *  @sched_period	representative of the task's period in nanoseconds
  *
  * Given this task model, there are a multiplicity of scheduling algorithms
  * and policies, that can be used to ensure all the tasks will make their

kernel/freezer.c

@@ -72,7 +72,7 @@ bool __refrigerator(bool check_kthr_stop)
 		bool freeze;
 
 		raw_spin_lock_irq(&current->pi_lock);
-		set_current_state(TASK_FROZEN);
+		WRITE_ONCE(current->__state, TASK_FROZEN);
 		/* unstale saved_state so that __thaw_task() will wake us up */
 		current->saved_state = TASK_RUNNING;
 		raw_spin_unlock_irq(&current->pi_lock);

kernel/kthread.c

@@ -845,8 +845,16 @@ repeat:
 		 * event only cares about the address.
 		 */
 		trace_sched_kthread_work_execute_end(work, func);
-	} else if (!freezing(current))
+	} else if (!freezing(current)) {
 		schedule();
+	} else {
+		/*
+		 * Handle the case where the current remains
+		 * TASK_INTERRUPTIBLE. try_to_freeze() expects
+		 * the current to be TASK_RUNNING.
+		 */
+		__set_current_state(TASK_RUNNING);
+	}
 
 	try_to_freeze();
 	cond_resched();

kernel/locking/rtmutex.c

@@ -347,7 +347,7 @@ static __always_inline int __waiter_prio(struct task_struct *task)
 {
 	int prio = task->prio;
 
-	if (!rt_prio(prio))
+	if (!rt_or_dl_prio(prio))
 		return DEFAULT_PRIO;
 
 	return prio;
@@ -435,7 +435,7 @@ static inline bool rt_mutex_steal(struct rt_mutex_waiter *waiter,
 	 * Note that RT tasks are excluded from same priority (lateral)
 	 * steals to prevent the introduction of an unbounded latency.
 	 */
-	if (rt_prio(waiter->tree.prio) || dl_prio(waiter->tree.prio))
+	if (rt_or_dl_prio(waiter->tree.prio))
 		return false;
 
 	return rt_waiter_node_equal(&waiter->tree, &top_waiter->tree);

kernel/locking/rwsem.c

@@ -631,7 +631,7 @@ static inline bool rwsem_try_write_lock(struct rw_semaphore *sem,
 			 * if it is an RT task or wait in the wait queue
 			 * for too long.
 			 */
-			if (has_handoff || (!rt_task(waiter->task) &&
+			if (has_handoff || (!rt_or_dl_task(waiter->task) &&
 					    !time_after(jiffies, waiter->timeout)))
 				return false;
 
@@ -914,7 +914,7 @@ static bool rwsem_optimistic_spin(struct rw_semaphore *sem)
 		if (owner_state != OWNER_WRITER) {
 			if (need_resched())
 				break;
-			if (rt_task(current) &&
+			if (rt_or_dl_task(current) &&
 			   (prev_owner_state != OWNER_WRITER))
 				break;
 		}

kernel/locking/ww_mutex.h

@@ -237,7 +237,7 @@ __ww_ctx_less(struct ww_acquire_ctx *a, struct ww_acquire_ctx *b)
 	int a_prio = a->task->prio;
 	int b_prio = b->task->prio;
 
-	if (rt_prio(a_prio) || rt_prio(b_prio)) {
+	if (rt_or_dl_prio(a_prio) || rt_or_dl_prio(b_prio)) {
 
 		if (a_prio > b_prio)
 			return true;

kernel/sched/core.c

@@ -163,7 +163,10 @@ static inline int __task_prio(const struct task_struct *p)
 	if (p->sched_class == &stop_sched_class) /* trumps deadline */
 		return -2;
 
-	if (rt_prio(p->prio)) /* includes deadline */
+	if (p->dl_server)
+		return -1; /* deadline */
+
+	if (rt_or_dl_prio(p->prio))
 		return p->prio; /* [-1, 99] */
 
 	if (p->sched_class == &idle_sched_class)
@@ -192,8 +195,24 @@ static inline bool prio_less(const struct task_struct *a,
 	if (-pb < -pa)
 		return false;
 
-	if (pa == -1) /* dl_prio() doesn't work because of stop_class above */
-		return !dl_time_before(a->dl.deadline, b->dl.deadline);
+	if (pa == -1) { /* dl_prio() doesn't work because of stop_class above */
+		const struct sched_dl_entity *a_dl, *b_dl;
+
+		a_dl = &a->dl;
+		/*
+		 * Since,'a' and 'b' can be CFS tasks served by DL server,
+		 * __task_prio() can return -1 (for DL) even for those. In that
+		 * case, get to the dl_server's DL entity.
+		 */
+		if (a->dl_server)
+			a_dl = a->dl_server;
+
+		b_dl = &b->dl;
+		if (b->dl_server)
+			b_dl = b->dl_server;
+
+		return !dl_time_before(a_dl->deadline, b_dl->deadline);
+	}
 
 	if (pa == MAX_RT_PRIO + MAX_NICE)	/* fair */
 		return cfs_prio_less(a, b, in_fi);
@@ -240,6 +259,9 @@ static inline int rb_sched_core_cmp(const void *key, const struct rb_node *node)
 
 void sched_core_enqueue(struct rq *rq, struct task_struct *p)
 {
+	if (p->se.sched_delayed)
+		return;
+
 	rq->core->core_task_seq++;
 
 	if (!p->core_cookie)
@@ -250,6 +272,9 @@ void sched_core_enqueue(struct rq *rq, struct task_struct *p)
 
 void sched_core_dequeue(struct rq *rq, struct task_struct *p, int flags)
 {
+	if (p->se.sched_delayed)
+		return;
+
 	rq->core->core_task_seq++;
 
 	if (sched_core_enqueued(p)) {
@@ -1269,7 +1294,7 @@ bool sched_can_stop_tick(struct rq *rq)
 	 * dequeued by migrating while the constrained task continues to run.
 	 * E.g. going from 2->1 without going through pick_next_task().
 	 */
-	if (sched_feat(HZ_BW) && __need_bw_check(rq, rq->curr)) {
+	if (__need_bw_check(rq, rq->curr)) {
 		if (cfs_task_bw_constrained(rq->curr))
 			return false;
 	}
@@ -1672,6 +1697,9 @@ static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p)
 	if (unlikely(!p->sched_class->uclamp_enabled))
 		return;
 
+	if (p->se.sched_delayed)
+		return;
+
 	for_each_clamp_id(clamp_id)
 		uclamp_rq_inc_id(rq, p, clamp_id);
 
@@ -1696,6 +1724,9 @@ static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p)
 	if (unlikely(!p->sched_class->uclamp_enabled))
 		return;
 
+	if (p->se.sched_delayed)
+		return;
+
 	for_each_clamp_id(clamp_id)
 		uclamp_rq_dec_id(rq, p, clamp_id);
 }
@@ -1975,14 +2006,21 @@ void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
 		psi_enqueue(p, (flags & ENQUEUE_WAKEUP) && !(flags & ENQUEUE_MIGRATED));
 	}
 
-	uclamp_rq_inc(rq, p);
 	p->sched_class->enqueue_task(rq, p, flags);
+	/*
+	 * Must be after ->enqueue_task() because ENQUEUE_DELAYED can clear
+	 * ->sched_delayed.
+	 */
+	uclamp_rq_inc(rq, p);
 
 	if (sched_core_enabled(rq))
 		sched_core_enqueue(rq, p);
 }
 
-void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
+/*
+ * Must only return false when DEQUEUE_SLEEP.
+ */
+inline bool dequeue_task(struct rq *rq, struct task_struct *p, int flags)
 {
 	if (sched_core_enabled(rq))
 		sched_core_dequeue(rq, p, flags);
@@ -1995,8 +2033,12 @@ void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
 		psi_dequeue(p, flags & DEQUEUE_SLEEP);
 	}
 
+	/*
+	 * Must be before ->dequeue_task() because ->dequeue_task() can 'fail'
+	 * and mark the task ->sched_delayed.
+	 */
 	uclamp_rq_dec(rq, p);
-	p->sched_class->dequeue_task(rq, p, flags);
+	return p->sched_class->dequeue_task(rq, p, flags);
 }
 
 void activate_task(struct rq *rq, struct task_struct *p, int flags)
@@ -2014,12 +2056,25 @@ void activate_task(struct rq *rq, struct task_struct *p, int flags)
 
 void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
 {
-	WRITE_ONCE(p->on_rq, (flags & DEQUEUE_SLEEP) ? 0 : TASK_ON_RQ_MIGRATING);
+	SCHED_WARN_ON(flags & DEQUEUE_SLEEP);
+
+	WRITE_ONCE(p->on_rq, TASK_ON_RQ_MIGRATING);
 	ASSERT_EXCLUSIVE_WRITER(p->on_rq);
 
+	/*
+	 * Code explicitly relies on TASK_ON_RQ_MIGRATING begin set *before*
+	 * dequeue_task() and cleared *after* enqueue_task().
+	 */
+
 	dequeue_task(rq, p, flags);
 }
 
+static void block_task(struct rq *rq, struct task_struct *p, int flags)
+{
+	if (dequeue_task(rq, p, DEQUEUE_SLEEP | flags))
+		__block_task(rq, p);
+}
+
 /**
  * task_curr - is this task currently executing on a CPU?
  * @p: the task in question.
@@ -2233,6 +2288,12 @@ void migrate_disable(void)
 	struct task_struct *p = current;
 
 	if (p->migration_disabled) {
+#ifdef CONFIG_DEBUG_PREEMPT
+		/*
+		 *Warn about overflow half-way through the range.
+		 */
+		WARN_ON_ONCE((s16)p->migration_disabled < 0);
+#endif
 		p->migration_disabled++;
 		return;
 	}
@@ -2251,14 +2312,20 @@ void migrate_enable(void)
 		.flags     = SCA_MIGRATE_ENABLE,
 	};
 
+#ifdef CONFIG_DEBUG_PREEMPT
+	/*
+	 * Check both overflow from migrate_disable() and superfluous
+	 * migrate_enable().
+	 */
+	if (WARN_ON_ONCE((s16)p->migration_disabled <= 0))
+		return;
+#endif
+
 	if (p->migration_disabled > 1) {
 		p->migration_disabled--;
 		return;
 	}
 
-	if (WARN_ON_ONCE(!p->migration_disabled))
-		return;
-
 	/*
 	 * Ensure stop_task runs either before or after this, and that
 	 * __set_cpus_allowed_ptr(SCA_MIGRATE_ENABLE) doesn't schedule().
@@ -3607,8 +3674,6 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
 		rq->idle_stamp = 0;
 	}
 #endif
-
-	p->dl_server = NULL;
 }
 
 /*
@@ -3644,12 +3709,14 @@ static int ttwu_runnable(struct task_struct *p, int wake_flags)
 
 	rq = __task_rq_lock(p, &rf);
 	if (task_on_rq_queued(p)) {
+		update_rq_clock(rq);
+		if (p->se.sched_delayed)
+			enqueue_task(rq, p, ENQUEUE_NOCLOCK | ENQUEUE_DELAYED);
 		if (!task_on_cpu(rq, p)) {
 			/*
 			 * When on_rq && !on_cpu the task is preempted, see if
 			 * it should preempt the task that is current now.
 			 */
-			update_rq_clock(rq);
 			wakeup_preempt(rq, p, wake_flags);
 		}
 		ttwu_do_wakeup(p);
@@ -4029,11 +4096,16 @@ int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 		 * case the whole 'p->on_rq && ttwu_runnable()' case below
 		 * without taking any locks.
 		 *
+		 * Specifically, given current runs ttwu() we must be before
+		 * schedule()'s block_task(), as such this must not observe
+		 * sched_delayed.
+		 *
 		 * In particular:
 		 *  - we rely on Program-Order guarantees for all the ordering,
 		 *  - we're serialized against set_special_state() by virtue of
 		 *    it disabling IRQs (this allows not taking ->pi_lock).
 		 */
+		SCHED_WARN_ON(p->se.sched_delayed);
 		if (!ttwu_state_match(p, state, &success))
 			goto out;
 
@@ -4322,9 +4394,11 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 	p->se.nr_migrations		= 0;
 	p->se.vruntime			= 0;
 	p->se.vlag			= 0;
-	p->se.slice			= sysctl_sched_base_slice;
 	INIT_LIST_HEAD(&p->se.group_node);
 
+	/* A delayed task cannot be in clone(). */
+	SCHED_WARN_ON(p->se.sched_delayed);
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	p->se.cfs_rq			= NULL;
 #endif
@@ -4572,6 +4646,8 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 
 		p->prio = p->normal_prio = p->static_prio;
 		set_load_weight(p, false);
+		p->se.custom_slice = 0;
+		p->se.slice = sysctl_sched_base_slice;
 
 		/*
 		 * We don't need the reset flag anymore after the fork. It has
@@ -4686,7 +4762,7 @@ void wake_up_new_task(struct task_struct *p)
 	update_rq_clock(rq);
 	post_init_entity_util_avg(p);
 
-	activate_task(rq, p, ENQUEUE_NOCLOCK);
+	activate_task(rq, p, ENQUEUE_NOCLOCK | ENQUEUE_INITIAL);
 	trace_sched_wakeup_new(p);
 	wakeup_preempt(rq, p, WF_FORK);
 #ifdef CONFIG_SMP
@@ -5769,8 +5845,8 @@ static inline void schedule_debug(struct task_struct *prev, bool preempt)
 	schedstat_inc(this_rq()->sched_count);
 }
 
-static void put_prev_task_balance(struct rq *rq, struct task_struct *prev,
-				  struct rq_flags *rf)
+static void prev_balance(struct rq *rq, struct task_struct *prev,
+			 struct rq_flags *rf)
 {
 #ifdef CONFIG_SMP
 	const struct sched_class *class;
@@ -5787,8 +5863,6 @@ static void put_prev_task_balance(struct rq *rq, struct task_struct *prev,
 			break;
 	}
 #endif
-
-	put_prev_task(rq, prev);
 }
 
 /*
@@ -5800,6 +5874,8 @@ __pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 	const struct sched_class *class;
 	struct task_struct *p;
 
+	rq->dl_server = NULL;
+
 	/*
 	 * Optimization: we know that if all tasks are in the fair class we can
 	 * call that function directly, but only if the @prev task wasn't of a
@@ -5815,35 +5891,28 @@ __pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 
 		/* Assume the next prioritized class is idle_sched_class */
 		if (!p) {
-			put_prev_task(rq, prev);
-			p = pick_next_task_idle(rq);
+			p = pick_task_idle(rq);
+			put_prev_set_next_task(rq, prev, p);
 		}
 
-		/*
-		 * This is the fast path; it cannot be a DL server pick;
-		 * therefore even if @p == @prev, ->dl_server must be NULL.
-		 */
-		if (p->dl_server)
-			p->dl_server = NULL;
-
 		return p;
 	}
 
 restart:
-	put_prev_task_balance(rq, prev, rf);
-
-	/*
-	 * We've updated @prev and no longer need the server link, clear it.
-	 * Must be done before ->pick_next_task() because that can (re)set
-	 * ->dl_server.
-	 */
-	if (prev->dl_server)
-		prev->dl_server = NULL;
+	prev_balance(rq, prev, rf);
 
 	for_each_class(class) {
-		p = class->pick_next_task(rq);
-		if (p)
-			return p;
+		if (class->pick_next_task) {
+			p = class->pick_next_task(rq, prev);
+			if (p)
+				return p;
+		} else {
+			p = class->pick_task(rq);
+			if (p) {
+				put_prev_set_next_task(rq, prev, p);
+				return p;
+			}
+		}
 	}
 
 	BUG(); /* The idle class should always have a runnable task. */
@@ -5873,6 +5942,8 @@ static inline struct task_struct *pick_task(struct rq *rq)
 	const struct sched_class *class;
 	struct task_struct *p;
 
+	rq->dl_server = NULL;
+
 	for_each_class(class) {
 		p = class->pick_task(rq);
 		if (p)
@@ -5911,6 +5982,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 		 * another cpu during offline.
 		 */
 		rq->core_pick = NULL;
+		rq->core_dl_server = NULL;
 		return __pick_next_task(rq, prev, rf);
 	}
 
@@ -5929,16 +6001,13 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 		WRITE_ONCE(rq->core_sched_seq, rq->core->core_pick_seq);
 
 		next = rq->core_pick;
-		if (next != prev) {
-			put_prev_task(rq, prev);
-			set_next_task(rq, next);
-		}
-
+		rq->dl_server = rq->core_dl_server;
 		rq->core_pick = NULL;
-		goto out;
+		rq->core_dl_server = NULL;
+		goto out_set_next;
 	}
 
-	put_prev_task_balance(rq, prev, rf);
+	prev_balance(rq, prev, rf);
 
 	smt_mask = cpu_smt_mask(cpu);
 	need_sync = !!rq->core->core_cookie;
@@ -5979,6 +6048,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 		next = pick_task(rq);
 		if (!next->core_cookie) {
 			rq->core_pick = NULL;
+			rq->core_dl_server = NULL;
 			/*
 			 * For robustness, update the min_vruntime_fi for
 			 * unconstrained picks as well.
@@ -6006,7 +6076,9 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 		if (i != cpu && (rq_i != rq->core || !core_clock_updated))
 			update_rq_clock(rq_i);
 
-		p = rq_i->core_pick = pick_task(rq_i);
+		rq_i->core_pick = p = pick_task(rq_i);
+		rq_i->core_dl_server = rq_i->dl_server;
+
 		if (!max || prio_less(max, p, fi_before))
 			max = p;
 	}
@@ -6030,6 +6102,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 		}
 
 		rq_i->core_pick = p;
+		rq_i->core_dl_server = NULL;
 
 		if (p == rq_i->idle) {
 			if (rq_i->nr_running) {
@@ -6090,6 +6163,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 
 		if (i == cpu) {
 			rq_i->core_pick = NULL;
+			rq_i->core_dl_server = NULL;
 			continue;
 		}
 
@@ -6098,6 +6172,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 
 		if (rq_i->curr == rq_i->core_pick) {
 			rq_i->core_pick = NULL;
+			rq_i->core_dl_server = NULL;
 			continue;
 		}
 
@@ -6105,8 +6180,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 	}
 
 out_set_next:
-	set_next_task(rq, next);
-out:
+	put_prev_set_next_task(rq, prev, next);
 	if (rq->core->core_forceidle_count && next == rq->idle)
 		queue_core_balance(rq);
 
@@ -6342,19 +6416,12 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
  * Constants for the sched_mode argument of __schedule().
  *
  * The mode argument allows RT enabled kernels to differentiate a
- * preemption from blocking on an 'sleeping' spin/rwlock. Note that
- * SM_MASK_PREEMPT for !RT has all bits set, which allows the compiler to
- * optimize the AND operation out and just check for zero.
+ * preemption from blocking on an 'sleeping' spin/rwlock.
  */
-#define SM_NONE			0x0
-#define SM_PREEMPT		0x1
-#define SM_RTLOCK_WAIT		0x2
-
-#ifndef CONFIG_PREEMPT_RT
-# define SM_MASK_PREEMPT	(~0U)
-#else
-# define SM_MASK_PREEMPT	SM_PREEMPT
-#endif
+#define SM_IDLE			(-1)
+#define SM_NONE			0
+#define SM_PREEMPT		1
+#define SM_RTLOCK_WAIT		2
 
 /*
  * __schedule() is the main scheduler function.
@@ -6395,9 +6462,14 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
  *
  * WARNING: must be called with preemption disabled!
  */
-static void __sched notrace __schedule(unsigned int sched_mode)
+static void __sched notrace __schedule(int sched_mode)
 {
 	struct task_struct *prev, *next;
+	/*
+	 * On PREEMPT_RT kernel, SM_RTLOCK_WAIT is noted
+	 * as a preemption by schedule_debug() and RCU.
+	 */
+	bool preempt = sched_mode > SM_NONE;
 	unsigned long *switch_count;
 	unsigned long prev_state;
 	struct rq_flags rf;
@@ -6408,13 +6480,13 @@ static void __sched notrace __schedule(unsigned int sched_mode)
 	rq = cpu_rq(cpu);
 	prev = rq->curr;
 
-	schedule_debug(prev, !!sched_mode);
+	schedule_debug(prev, preempt);
 
 	if (sched_feat(HRTICK) || sched_feat(HRTICK_DL))
 		hrtick_clear(rq);
 
 	local_irq_disable();
-	rcu_note_context_switch(!!sched_mode);
+	rcu_note_context_switch(preempt);
 
 	/*
 	 * Make sure that signal_pending_state()->signal_pending() below
@@ -6443,22 +6515,32 @@ static void __sched notrace __schedule(unsigned int sched_mode)
 
 	switch_count = &prev->nivcsw;
 
+	/* Task state changes only considers SM_PREEMPT as preemption */
+	preempt = sched_mode == SM_PREEMPT;
+
 	/*
 	 * We must load prev->state once (task_struct::state is volatile), such
 	 * that we form a control dependency vs deactivate_task() below.
 	 */
 	prev_state = READ_ONCE(prev->__state);
-	if (!(sched_mode & SM_MASK_PREEMPT) && prev_state) {
+	if (sched_mode == SM_IDLE) {
+		if (!rq->nr_running) {
+			next = prev;
+			goto picked;
+		}
+	} else if (!preempt && prev_state) {
 		if (signal_pending_state(prev_state, prev)) {
 			WRITE_ONCE(prev->__state, TASK_RUNNING);
 		} else {
+			int flags = DEQUEUE_NOCLOCK;
+
 			prev->sched_contributes_to_load =
 				(prev_state & TASK_UNINTERRUPTIBLE) &&
 				!(prev_state & TASK_NOLOAD) &&
 				!(prev_state & TASK_FROZEN);
 
-			if (prev->sched_contributes_to_load)
-				rq->nr_uninterruptible++;
+			if (unlikely(is_special_task_state(prev_state)))
+				flags |= DEQUEUE_SPECIAL;
 
 			/*
 			 * __schedule()			ttwu()
@@ -6471,17 +6553,13 @@ static void __sched notrace __schedule(unsigned int sched_mode)
 			 *
 			 * After this, schedule() must not care about p->state any more.
 			 */
-			deactivate_task(rq, prev, DEQUEUE_SLEEP | DEQUEUE_NOCLOCK);
-
-			if (prev->in_iowait) {
-				atomic_inc(&rq->nr_iowait);
-				delayacct_blkio_start();
-			}
+			block_task(rq, prev, flags);
 		}
 		switch_count = &prev->nvcsw;
 	}
 
 	next = pick_next_task(rq, prev, &rf);
+picked:
 	clear_tsk_need_resched(prev);
 	clear_preempt_need_resched();
 #ifdef CONFIG_SCHED_DEBUG
@@ -6523,7 +6601,7 @@ static void __sched notrace __schedule(unsigned int sched_mode)
 		psi_account_irqtime(rq, prev, next);
 		psi_sched_switch(prev, next, !task_on_rq_queued(prev));
 
-		trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev, next, prev_state);
+		trace_sched_switch(preempt, prev, next, prev_state);
 
 		/* Also unlocks the rq: */
 		rq = context_switch(rq, prev, next, &rf);
@@ -6599,7 +6677,7 @@ static void sched_update_worker(struct task_struct *tsk)
 	}
 }
 
-static __always_inline void __schedule_loop(unsigned int sched_mode)
+static __always_inline void __schedule_loop(int sched_mode)
 {
 	do {
 		preempt_disable();
@@ -6644,7 +6722,7 @@ void __sched schedule_idle(void)
 	 */
 	WARN_ON_ONCE(current->__state);
 	do {
-		__schedule(SM_NONE);
+		__schedule(SM_IDLE);
 	} while (need_resched());
 }
 
@@ -8228,8 +8306,6 @@ void __init sched_init(void)
 #endif /* CONFIG_RT_GROUP_SCHED */
 	}
 
-	init_rt_bandwidth(&def_rt_bandwidth, global_rt_period(), global_rt_runtime());
-
 #ifdef CONFIG_SMP
 	init_defrootdomain();
 #endif
@@ -8284,8 +8360,13 @@ void __init sched_init(void)
 		init_tg_cfs_entry(&root_task_group, &rq->cfs, NULL, i, NULL);
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
-		rq->rt.rt_runtime = def_rt_bandwidth.rt_runtime;
 #ifdef CONFIG_RT_GROUP_SCHED
+		/*
+		 * This is required for init cpu because rt.c:__enable_runtime()
+		 * starts working after scheduler_running, which is not the case
+		 * yet.
+		 */
+		rq->rt.rt_runtime = global_rt_runtime();
 		init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, NULL);
 #endif
 #ifdef CONFIG_SMP
@@ -8317,10 +8398,12 @@ void __init sched_init(void)
 #endif /* CONFIG_SMP */
 		hrtick_rq_init(rq);
 		atomic_set(&rq->nr_iowait, 0);
+		fair_server_init(rq);
 
 #ifdef CONFIG_SCHED_CORE
 		rq->core = rq;
 		rq->core_pick = NULL;
+		rq->core_dl_server = NULL;
 		rq->core_enabled = 0;
 		rq->core_tree = RB_ROOT;
 		rq->core_forceidle_count = 0;
@@ -8333,6 +8416,7 @@ void __init sched_init(void)
 	}
 
 	set_load_weight(&init_task, false);
+	init_task.se.slice = sysctl_sched_base_slice,
 
 	/*
 	 * The boot idle thread does lazy MMU switching as well:
@@ -8548,7 +8632,7 @@ void normalize_rt_tasks(void)
 		schedstat_set(p->stats.sleep_start, 0);
 		schedstat_set(p->stats.block_start, 0);
 
-		if (!dl_task(p) && !rt_task(p)) {
+		if (!rt_or_dl_task(p)) {
 			/*
 			 * Renice negative nice level userspace
 			 * tasks back to 0:

kernel/sched/cpufreq_schedutil.c

@@ -654,9 +654,9 @@ static int sugov_kthread_create(struct sugov_policy *sg_policy)
 		 * Fake (unused) bandwidth; workaround to "fix"
 		 * priority inheritance.
 		 */
-		.sched_runtime	=  1000000,
-		.sched_deadline = 10000000,
-		.sched_period	= 10000000,
+		.sched_runtime	= NSEC_PER_MSEC,
+		.sched_deadline = 10 * NSEC_PER_MSEC,
+		.sched_period	= 10 * NSEC_PER_MSEC,
 	};
 	struct cpufreq_policy *policy = sg_policy->policy;
 	int ret;

kernel/sched/deadline.c

@@ -320,19 +320,12 @@ void sub_running_bw(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 		__sub_running_bw(dl_se->dl_bw, dl_rq);
 }
 
-static void dl_change_utilization(struct task_struct *p, u64 new_bw)
+static void dl_rq_change_utilization(struct rq *rq, struct sched_dl_entity *dl_se, u64 new_bw)
 {
-	struct rq *rq;
+	if (dl_se->dl_non_contending) {
+		sub_running_bw(dl_se, &rq->dl);
+		dl_se->dl_non_contending = 0;
 
-	WARN_ON_ONCE(p->dl.flags & SCHED_FLAG_SUGOV);
-
-	if (task_on_rq_queued(p))
-		return;
-
-	rq = task_rq(p);
-	if (p->dl.dl_non_contending) {
-		sub_running_bw(&p->dl, &rq->dl);
-		p->dl.dl_non_contending = 0;
 		/*
 		 * If the timer handler is currently running and the
 		 * timer cannot be canceled, inactive_task_timer()
@@ -340,13 +333,25 @@ static void dl_change_utilization(struct task_struct *p, u64 new_bw)
 		 * 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);
+		if (hrtimer_try_to_cancel(&dl_se->inactive_timer) == 1) {
+			if (!dl_server(dl_se))
+				put_task_struct(dl_task_of(dl_se));
+		}
 	}
-	__sub_rq_bw(p->dl.dl_bw, &rq->dl);
+	__sub_rq_bw(dl_se->dl_bw, &rq->dl);
 	__add_rq_bw(new_bw, &rq->dl);
 }
 
+static void dl_change_utilization(struct task_struct *p, u64 new_bw)
+{
+	WARN_ON_ONCE(p->dl.flags & SCHED_FLAG_SUGOV);
+
+	if (task_on_rq_queued(p))
+		return;
+
+	dl_rq_change_utilization(task_rq(p), &p->dl, new_bw);
+}
+
 static void __dl_clear_params(struct sched_dl_entity *dl_se);
 
 /*
@@ -771,6 +776,15 @@ static inline void replenish_dl_new_period(struct sched_dl_entity *dl_se,
 	/* for non-boosted task, pi_of(dl_se) == dl_se */
 	dl_se->deadline = rq_clock(rq) + pi_of(dl_se)->dl_deadline;
 	dl_se->runtime = pi_of(dl_se)->dl_runtime;
+
+	/*
+	 * If it is a deferred reservation, and the server
+	 * is not handling an starvation case, defer it.
+	 */
+	if (dl_se->dl_defer & !dl_se->dl_defer_running) {
+		dl_se->dl_throttled = 1;
+		dl_se->dl_defer_armed = 1;
+	}
 }
 
 /*
@@ -809,6 +823,9 @@ static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se)
 	replenish_dl_new_period(dl_se, rq);
 }
 
+static int start_dl_timer(struct sched_dl_entity *dl_se);
+static bool dl_entity_overflow(struct sched_dl_entity *dl_se, u64 t);
+
 /*
  * Pure Earliest Deadline First (EDF) scheduling does not deal with the
  * possibility of a entity lasting more than what it declared, and thus
@@ -837,9 +854,18 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se)
 	/*
 	 * This could be the case for a !-dl task that is boosted.
 	 * Just go with full inherited parameters.
+	 *
+	 * Or, it could be the case of a deferred reservation that
+	 * was not able to consume its runtime in background and
+	 * reached this point with current u > U.
+	 *
+	 * In both cases, set a new period.
 	 */
-	if (dl_se->dl_deadline == 0)
-		replenish_dl_new_period(dl_se, rq);
+	if (dl_se->dl_deadline == 0 ||
+	    (dl_se->dl_defer_armed && dl_entity_overflow(dl_se, rq_clock(rq)))) {
+		dl_se->deadline = rq_clock(rq) + pi_of(dl_se)->dl_deadline;
+		dl_se->runtime = pi_of(dl_se)->dl_runtime;
+	}
 
 	if (dl_se->dl_yielded && dl_se->runtime > 0)
 		dl_se->runtime = 0;
@@ -873,6 +899,44 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se)
 		dl_se->dl_yielded = 0;
 	if (dl_se->dl_throttled)
 		dl_se->dl_throttled = 0;
+
+	/*
+	 * If this is the replenishment of a deferred reservation,
+	 * clear the flag and return.
+	 */
+	if (dl_se->dl_defer_armed) {
+		dl_se->dl_defer_armed = 0;
+		return;
+	}
+
+	/*
+	 * A this point, if the deferred server is not armed, and the deadline
+	 * is in the future, if it is not running already, throttle the server
+	 * and arm the defer timer.
+	 */
+	if (dl_se->dl_defer && !dl_se->dl_defer_running &&
+	    dl_time_before(rq_clock(dl_se->rq), dl_se->deadline - dl_se->runtime)) {
+		if (!is_dl_boosted(dl_se) && dl_se->server_has_tasks(dl_se)) {
+
+			/*
+			 * Set dl_se->dl_defer_armed and dl_throttled variables to
+			 * inform the start_dl_timer() that this is a deferred
+			 * activation.
+			 */
+			dl_se->dl_defer_armed = 1;
+			dl_se->dl_throttled = 1;
+			if (!start_dl_timer(dl_se)) {
+				/*
+				 * If for whatever reason (delays), a previous timer was
+				 * queued but not serviced, cancel it and clean the
+				 * deferrable server variables intended for start_dl_timer().
+				 */
+				hrtimer_try_to_cancel(&dl_se->dl_timer);
+				dl_se->dl_defer_armed = 0;
+				dl_se->dl_throttled = 0;
+			}
+		}
+	}
 }
 
 /*
@@ -1023,6 +1087,15 @@ static void update_dl_entity(struct sched_dl_entity *dl_se)
 		}
 
 		replenish_dl_new_period(dl_se, rq);
+	} else if (dl_server(dl_se) && dl_se->dl_defer) {
+		/*
+		 * The server can still use its previous deadline, so check if
+		 * it left the dl_defer_running state.
+		 */
+		if (!dl_se->dl_defer_running) {
+			dl_se->dl_defer_armed = 1;
+			dl_se->dl_throttled = 1;
+		}
 	}
 }
 
@@ -1055,8 +1128,21 @@ static int start_dl_timer(struct sched_dl_entity *dl_se)
 	 * We want the timer to fire at the deadline, but considering
 	 * that it is actually coming from rq->clock and not from
 	 * hrtimer's time base reading.
+	 *
+	 * The deferred reservation will have its timer set to
+	 * (deadline - runtime). At that point, the CBS rule will decide
+	 * if the current deadline can be used, or if a replenishment is
+	 * required to avoid add too much pressure on the system
+	 * (current u > U).
 	 */
-	act = ns_to_ktime(dl_next_period(dl_se));
+	if (dl_se->dl_defer_armed) {
+		WARN_ON_ONCE(!dl_se->dl_throttled);
+		act = ns_to_ktime(dl_se->deadline - dl_se->runtime);
+	} else {
+		/* act = deadline - rel-deadline + period */
+		act = ns_to_ktime(dl_next_period(dl_se));
+	}
+
 	now = hrtimer_cb_get_time(timer);
 	delta = ktime_to_ns(now) - rq_clock(rq);
 	act = ktime_add_ns(act, delta);
@@ -1106,6 +1192,62 @@ static void __push_dl_task(struct rq *rq, struct rq_flags *rf)
 #endif
 }
 
+/* a defer timer will not be reset if the runtime consumed was < dl_server_min_res */
+static const u64 dl_server_min_res = 1 * NSEC_PER_MSEC;
+
+static enum hrtimer_restart dl_server_timer(struct hrtimer *timer, struct sched_dl_entity *dl_se)
+{
+	struct rq *rq = rq_of_dl_se(dl_se);
+	u64 fw;
+
+	scoped_guard (rq_lock, rq) {
+		struct rq_flags *rf = &scope.rf;
+
+		if (!dl_se->dl_throttled || !dl_se->dl_runtime)
+			return HRTIMER_NORESTART;
+
+		sched_clock_tick();
+		update_rq_clock(rq);
+
+		if (!dl_se->dl_runtime)
+			return HRTIMER_NORESTART;
+
+		if (!dl_se->server_has_tasks(dl_se)) {
+			replenish_dl_entity(dl_se);
+			return HRTIMER_NORESTART;
+		}
+
+		if (dl_se->dl_defer_armed) {
+			/*
+			 * First check if the server could consume runtime in background.
+			 * If so, it is possible to push the defer timer for this amount
+			 * of time. The dl_server_min_res serves as a limit to avoid
+			 * forwarding the timer for a too small amount of time.
+			 */
+			if (dl_time_before(rq_clock(dl_se->rq),
+					   (dl_se->deadline - dl_se->runtime - dl_server_min_res))) {
+
+				/* reset the defer timer */
+				fw = dl_se->deadline - rq_clock(dl_se->rq) - dl_se->runtime;
+
+				hrtimer_forward_now(timer, ns_to_ktime(fw));
+				return HRTIMER_RESTART;
+			}
+
+			dl_se->dl_defer_running = 1;
+		}
+
+		enqueue_dl_entity(dl_se, ENQUEUE_REPLENISH);
+
+		if (!dl_task(dl_se->rq->curr) || dl_entity_preempt(dl_se, &dl_se->rq->curr->dl))
+			resched_curr(rq);
+
+		__push_dl_task(rq, rf);
+	}
+
+	return HRTIMER_NORESTART;
+}
+
 /*
  * This is the bandwidth enforcement timer callback. If here, we know
  * a task is not on its dl_rq, since the fact that the timer was running
@@ -1128,28 +1270,8 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
 	struct rq_flags rf;
 	struct rq *rq;
 
-	if (dl_server(dl_se)) {
-		struct rq *rq = rq_of_dl_se(dl_se);
-		struct rq_flags rf;
-
-		rq_lock(rq, &rf);
-		if (dl_se->dl_throttled) {
-			sched_clock_tick();
-			update_rq_clock(rq);
-
-			if (dl_se->server_has_tasks(dl_se)) {
-				enqueue_dl_entity(dl_se, ENQUEUE_REPLENISH);
-				resched_curr(rq);
-				__push_dl_task(rq, &rf);
-			} else {
-				replenish_dl_entity(dl_se);
-			}
-
-		}
-		rq_unlock(rq, &rf);
-
-		return HRTIMER_NORESTART;
-	}
+	if (dl_server(dl_se))
+		return dl_server_timer(timer, dl_se);
 
 	p = dl_task_of(dl_se);
 	rq = task_rq_lock(p, &rf);
@@ -1319,22 +1441,10 @@ static u64 grub_reclaim(u64 delta, struct rq *rq, struct sched_dl_entity *dl_se)
 	return (delta * u_act) >> BW_SHIFT;
 }
 
-static inline void
-update_stats_dequeue_dl(struct dl_rq *dl_rq, struct sched_dl_entity *dl_se,
-                        int flags);
-static void update_curr_dl_se(struct rq *rq, struct sched_dl_entity *dl_se, s64 delta_exec)
+s64 dl_scaled_delta_exec(struct rq *rq, struct sched_dl_entity *dl_se, s64 delta_exec)
 {
 	s64 scaled_delta_exec;
 
-	if (unlikely(delta_exec <= 0)) {
-		if (unlikely(dl_se->dl_yielded))
-			goto throttle;
-		return;
-	}
-
-	if (dl_entity_is_special(dl_se))
-		return;
-
 	/*
 	 * For tasks that participate in GRUB, we implement GRUB-PA: the
 	 * spare reclaimed bandwidth is used to clock down frequency.
@@ -1353,8 +1463,64 @@ static void update_curr_dl_se(struct rq *rq, struct sched_dl_entity *dl_se, s64
 		scaled_delta_exec = cap_scale(scaled_delta_exec, scale_cpu);
 	}
 
+	return scaled_delta_exec;
+}
+
+static inline void
+update_stats_dequeue_dl(struct dl_rq *dl_rq, struct sched_dl_entity *dl_se,
+			int flags);
+static void update_curr_dl_se(struct rq *rq, struct sched_dl_entity *dl_se, s64 delta_exec)
+{
+	s64 scaled_delta_exec;
+
+	if (unlikely(delta_exec <= 0)) {
+		if (unlikely(dl_se->dl_yielded))
+			goto throttle;
+		return;
+	}
+
+	if (dl_server(dl_se) && dl_se->dl_throttled && !dl_se->dl_defer)
+		return;
+
+	if (dl_entity_is_special(dl_se))
+		return;
+
+	scaled_delta_exec = dl_scaled_delta_exec(rq, dl_se, delta_exec);
+
 	dl_se->runtime -= scaled_delta_exec;
 
+	/*
+	 * The fair server can consume its runtime while throttled (not queued/
+	 * running as regular CFS).
+	 *
+	 * If the server consumes its entire runtime in this state. The server
+	 * is not required for the current period. Thus, reset the server by
+	 * starting a new period, pushing the activation.
+	 */
+	if (dl_se->dl_defer && dl_se->dl_throttled && dl_runtime_exceeded(dl_se)) {
+		/*
+		 * If the server was previously activated - the starving condition
+		 * took place, it this point it went away because the fair scheduler
+		 * was able to get runtime in background. So return to the initial
+		 * state.
+		 */
+		dl_se->dl_defer_running = 0;
+
+		hrtimer_try_to_cancel(&dl_se->dl_timer);
+
+		replenish_dl_new_period(dl_se, dl_se->rq);
+
+		/*
+		 * Not being able to start the timer seems problematic. If it could not
+		 * be started for whatever reason, we need to "unthrottle" the DL server
+		 * and queue right away. Otherwise nothing might queue it. That's similar
+		 * to what enqueue_dl_entity() does on start_dl_timer==0. For now, just warn.
+		 */
+		WARN_ON_ONCE(!start_dl_timer(dl_se));
+
+		return;
+	}
+
 throttle:
 	if (dl_runtime_exceeded(dl_se) || dl_se->dl_yielded) {
 		dl_se->dl_throttled = 1;
@@ -1381,6 +1547,14 @@ throttle:
 			resched_curr(rq);
 	}
 
+	/*
+	 * The fair server (sole dl_server) does not account for real-time
+	 * workload because it is running fair work.
+	 */
+	if (dl_se == &rq->fair_server)
+		return;
+
+#ifdef CONFIG_RT_GROUP_SCHED
 	/*
 	 * Because -- for now -- we share the rt bandwidth, we need to
 	 * account our runtime there too, otherwise actual rt tasks
@@ -1405,34 +1579,155 @@ throttle:
 			rt_rq->rt_time += delta_exec;
 		raw_spin_unlock(&rt_rq->rt_runtime_lock);
 	}
+#endif
+}
+
+/*
+ * In the non-defer mode, the idle time is not accounted, as the
+ * server provides a guarantee.
+ *
+ * If the dl_server is in defer mode, the idle time is also considered
+ * as time available for the fair server, avoiding a penalty for the
+ * rt scheduler that did not consumed that time.
+ */
+void dl_server_update_idle_time(struct rq *rq, struct task_struct *p)
+{
+	s64 delta_exec, scaled_delta_exec;
+
+	if (!rq->fair_server.dl_defer)
+		return;
+
+	/* no need to discount more */
+	if (rq->fair_server.runtime < 0)
+		return;
+
+	delta_exec = rq_clock_task(rq) - p->se.exec_start;
+	if (delta_exec < 0)
+		return;
+
+	scaled_delta_exec = dl_scaled_delta_exec(rq, &rq->fair_server, delta_exec);
+
+	rq->fair_server.runtime -= scaled_delta_exec;
+
+	if (rq->fair_server.runtime < 0) {
+		rq->fair_server.dl_defer_running = 0;
+		rq->fair_server.runtime = 0;
+	}
+
+	p->se.exec_start = rq_clock_task(rq);
 }
 
 void dl_server_update(struct sched_dl_entity *dl_se, s64 delta_exec)
 {
-	update_curr_dl_se(dl_se->rq, dl_se, delta_exec);
+	/* 0 runtime = fair server disabled */
+	if (dl_se->dl_runtime)
+		update_curr_dl_se(dl_se->rq, dl_se, delta_exec);
 }
 
 void dl_server_start(struct sched_dl_entity *dl_se)
 {
+	struct rq *rq = dl_se->rq;
+
+	/*
+	 * XXX: the apply do not work fine at the init phase for the
+	 * fair server because things are not yet set. We need to improve
+	 * this before getting generic.
+	 */
 	if (!dl_server(dl_se)) {
+		u64 runtime =  50 * NSEC_PER_MSEC;
+		u64 period = 1000 * NSEC_PER_MSEC;
+
+		dl_server_apply_params(dl_se, runtime, period, 1);
+
 		dl_se->dl_server = 1;
+		dl_se->dl_defer = 1;
 		setup_new_dl_entity(dl_se);
 	}
+
+	if (!dl_se->dl_runtime)
+		return;
+
 	enqueue_dl_entity(dl_se, ENQUEUE_WAKEUP);
+	if (!dl_task(dl_se->rq->curr) || dl_entity_preempt(dl_se, &rq->curr->dl))
+		resched_curr(dl_se->rq);
 }
 
 void dl_server_stop(struct sched_dl_entity *dl_se)
 {
+	if (!dl_se->dl_runtime)
+		return;
+
 	dequeue_dl_entity(dl_se, DEQUEUE_SLEEP);
+	hrtimer_try_to_cancel(&dl_se->dl_timer);
+	dl_se->dl_defer_armed = 0;
+	dl_se->dl_throttled = 0;
 }
 
 void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq,
 		    dl_server_has_tasks_f has_tasks,
-		    dl_server_pick_f pick)
+		    dl_server_pick_f pick_task)
 {
 	dl_se->rq = rq;
 	dl_se->server_has_tasks = has_tasks;
-	dl_se->server_pick = pick;
+	dl_se->server_pick_task = pick_task;
+}
+
+void __dl_server_attach_root(struct sched_dl_entity *dl_se, struct rq *rq)
+{
+	u64 new_bw = dl_se->dl_bw;
+	int cpu = cpu_of(rq);
+	struct dl_bw *dl_b;
+
+	dl_b = dl_bw_of(cpu_of(rq));
+	guard(raw_spinlock)(&dl_b->lock);
+
+	if (!dl_bw_cpus(cpu))
+		return;
+
+	__dl_add(dl_b, new_bw, dl_bw_cpus(cpu));
+}
+
+int dl_server_apply_params(struct sched_dl_entity *dl_se, u64 runtime, u64 period, bool init)
+{
+	u64 old_bw = init ? 0 : to_ratio(dl_se->dl_period, dl_se->dl_runtime);
+	u64 new_bw = to_ratio(period, runtime);
+	struct rq *rq = dl_se->rq;
+	int cpu = cpu_of(rq);
+	struct dl_bw *dl_b;
+	unsigned long cap;
+	int retval = 0;
+	int cpus;
+
+	dl_b = dl_bw_of(cpu);
+	guard(raw_spinlock)(&dl_b->lock);
+
+	cpus = dl_bw_cpus(cpu);
+	cap = dl_bw_capacity(cpu);
+
+	if (__dl_overflow(dl_b, cap, old_bw, new_bw))
+		return -EBUSY;
+
+	if (init) {
+		__add_rq_bw(new_bw, &rq->dl);
+		__dl_add(dl_b, new_bw, cpus);
+	} else {
+		__dl_sub(dl_b, dl_se->dl_bw, cpus);
+		__dl_add(dl_b, new_bw, cpus);
+
+		dl_rq_change_utilization(rq, dl_se, new_bw);
+	}
+
+	dl_se->dl_runtime = runtime;
+	dl_se->dl_deadline = period;
+	dl_se->dl_period = period;
+
+	dl_se->runtime = 0;
+	dl_se->deadline = 0;
+
+	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);
+
+	return retval;
 }
 
 /*
@@ -1599,46 +1894,40 @@ static inline bool __dl_less(struct rb_node *a, const struct rb_node *b)
 	return dl_time_before(__node_2_dle(a)->deadline, __node_2_dle(b)->deadline);
 }
 
-static inline struct sched_statistics *
+static __always_inline struct sched_statistics *
 __schedstats_from_dl_se(struct sched_dl_entity *dl_se)
 {
+	if (!schedstat_enabled())
+		return NULL;
+
+	if (dl_server(dl_se))
+		return NULL;
+
 	return &dl_task_of(dl_se)->stats;
 }
 
 static inline void
 update_stats_wait_start_dl(struct dl_rq *dl_rq, struct sched_dl_entity *dl_se)
 {
-	struct sched_statistics *stats;
-
-	if (!schedstat_enabled())
-		return;
-
-	stats = __schedstats_from_dl_se(dl_se);
-	__update_stats_wait_start(rq_of_dl_rq(dl_rq), dl_task_of(dl_se), stats);
+	struct sched_statistics *stats = __schedstats_from_dl_se(dl_se);
+	if (stats)
+		__update_stats_wait_start(rq_of_dl_rq(dl_rq), dl_task_of(dl_se), stats);
 }
 
 static inline void
 update_stats_wait_end_dl(struct dl_rq *dl_rq, struct sched_dl_entity *dl_se)
 {
-	struct sched_statistics *stats;
-
-	if (!schedstat_enabled())
-		return;
-
-	stats = __schedstats_from_dl_se(dl_se);
-	__update_stats_wait_end(rq_of_dl_rq(dl_rq), dl_task_of(dl_se), stats);
+	struct sched_statistics *stats = __schedstats_from_dl_se(dl_se);
+	if (stats)
+		__update_stats_wait_end(rq_of_dl_rq(dl_rq), dl_task_of(dl_se), stats);
 }
 
 static inline void
 update_stats_enqueue_sleeper_dl(struct dl_rq *dl_rq, struct sched_dl_entity *dl_se)
 {
-	struct sched_statistics *stats;
-
-	if (!schedstat_enabled())
-		return;
-
-	stats = __schedstats_from_dl_se(dl_se);
-	__update_stats_enqueue_sleeper(rq_of_dl_rq(dl_rq), dl_task_of(dl_se), stats);
+	struct sched_statistics *stats = __schedstats_from_dl_se(dl_se);
+	if (stats)
+		__update_stats_enqueue_sleeper(rq_of_dl_rq(dl_rq), dl_task_of(dl_se), stats);
 }
 
 static inline void
@@ -1735,7 +2024,7 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags)
 	 * be counted in the active utilization; hence, we need to call
 	 * add_running_bw().
 	 */
-	if (dl_se->dl_throttled && !(flags & ENQUEUE_REPLENISH)) {
+	if (!dl_se->dl_defer && dl_se->dl_throttled && !(flags & ENQUEUE_REPLENISH)) {
 		if (flags & ENQUEUE_WAKEUP)
 			task_contending(dl_se, flags);
 
@@ -1757,6 +2046,25 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags)
 		setup_new_dl_entity(dl_se);
 	}
 
+	/*
+	 * If the reservation is still throttled, e.g., it got replenished but is a
+	 * deferred task and still got to wait, don't enqueue.
+	 */
+	if (dl_se->dl_throttled && start_dl_timer(dl_se))
+		return;
+
+	/*
+	 * We're about to enqueue, make sure we're not ->dl_throttled!
+	 * In case the timer was not started, say because the defer time
+	 * has passed, mark as not throttled and mark unarmed.
+	 * Also cancel earlier timers, since letting those run is pointless.
+	 */
+	if (dl_se->dl_throttled) {
+		hrtimer_try_to_cancel(&dl_se->dl_timer);
+		dl_se->dl_defer_armed = 0;
+		dl_se->dl_throttled = 0;
+	}
+
 	__enqueue_dl_entity(dl_se);
 }
 
@@ -1846,7 +2154,7 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 		enqueue_pushable_dl_task(rq, p);
 }
 
-static void dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
+static bool dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 {
 	update_curr_dl(rq);
 
@@ -1856,6 +2164,8 @@ static void dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 	dequeue_dl_entity(&p->dl, flags);
 	if (!p->dl.dl_throttled && !dl_server(&p->dl))
 		dequeue_pushable_dl_task(rq, p);
+
+	return true;
 }
 
 /*
@@ -2074,6 +2384,9 @@ static void set_next_task_dl(struct rq *rq, struct task_struct *p, bool first)
 		update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 0);
 
 	deadline_queue_push_tasks(rq);
+
+	if (hrtick_enabled(rq))
+		start_hrtick_dl(rq, &p->dl);
 }
 
 static struct sched_dl_entity *pick_next_dl_entity(struct dl_rq *dl_rq)
@@ -2086,7 +2399,11 @@ static struct sched_dl_entity *pick_next_dl_entity(struct dl_rq *dl_rq)
 	return __node_2_dle(left);
 }
 
-static struct task_struct *pick_task_dl(struct rq *rq)
+/*
+ * __pick_next_task_dl - Helper to pick the next -deadline task to run.
+ * @rq: The runqueue to pick the next task from.
+ */
+static struct task_struct *__pick_task_dl(struct rq *rq)
 {
 	struct sched_dl_entity *dl_se;
 	struct dl_rq *dl_rq = &rq->dl;
@@ -2100,14 +2417,13 @@ again:
 	WARN_ON_ONCE(!dl_se);
 
 	if (dl_server(dl_se)) {
-		p = dl_se->server_pick(dl_se);
+		p = dl_se->server_pick_task(dl_se);
 		if (!p) {
-			WARN_ON_ONCE(1);
 			dl_se->dl_yielded = 1;
 			update_curr_dl_se(rq, dl_se, 0);
 			goto again;
 		}
-		p->dl_server = dl_se;
+		rq->dl_server = dl_se;
 	} else {
 		p = dl_task_of(dl_se);
 	}
@@ -2115,24 +2431,12 @@ again:
 	return p;
 }
 
-static struct task_struct *pick_next_task_dl(struct rq *rq)
+static struct task_struct *pick_task_dl(struct rq *rq)
 {
-	struct task_struct *p;
-
-	p = pick_task_dl(rq);
-	if (!p)
-		return p;
-
-	if (!p->dl_server)
-		set_next_task_dl(rq, p, true);
-
-	if (hrtick_enabled(rq))
-		start_hrtick_dl(rq, &p->dl);
-
-	return p;
+	return __pick_task_dl(rq);
 }
 
-static void put_prev_task_dl(struct rq *rq, struct task_struct *p)
+static void put_prev_task_dl(struct rq *rq, struct task_struct *p, struct task_struct *next)
 {
 	struct sched_dl_entity *dl_se = &p->dl;
 	struct dl_rq *dl_rq = &rq->dl;
@@ -2824,13 +3128,12 @@ DEFINE_SCHED_CLASS(dl) = {
 
 	.wakeup_preempt		= wakeup_preempt_dl,
 
-	.pick_next_task		= pick_next_task_dl,
+	.pick_task		= pick_task_dl,
 	.put_prev_task		= put_prev_task_dl,
 	.set_next_task		= set_next_task_dl,
 
 #ifdef CONFIG_SMP
 	.balance		= balance_dl,
-	.pick_task		= pick_task_dl,
 	.select_task_rq		= select_task_rq_dl,
 	.migrate_task_rq	= migrate_task_rq_dl,
 	.set_cpus_allowed       = set_cpus_allowed_dl,

kernel/sched/debug.c

@@ -333,8 +333,165 @@ static const struct file_operations sched_debug_fops = {
 	.release	= seq_release,
 };
 
+enum dl_param {
+	DL_RUNTIME = 0,
+	DL_PERIOD,
+};
+
+static unsigned long fair_server_period_max = (1UL << 22) * NSEC_PER_USEC; /* ~4 seconds */
+static unsigned long fair_server_period_min = (100) * NSEC_PER_USEC;     /* 100 us */
+
+static ssize_t sched_fair_server_write(struct file *filp, const char __user *ubuf,
+				       size_t cnt, loff_t *ppos, enum dl_param param)
+{
+	long cpu = (long) ((struct seq_file *) filp->private_data)->private;
+	struct rq *rq = cpu_rq(cpu);
+	u64 runtime, period;
+	size_t err;
+	int retval;
+	u64 value;
+
+	err = kstrtoull_from_user(ubuf, cnt, 10, &value);
+	if (err)
+		return err;
+
+	scoped_guard (rq_lock_irqsave, rq) {
+		runtime  = rq->fair_server.dl_runtime;
+		period = rq->fair_server.dl_period;
+
+		switch (param) {
+		case DL_RUNTIME:
+			if (runtime == value)
+				break;
+			runtime = value;
+			break;
+		case DL_PERIOD:
+			if (value == period)
+				break;
+			period = value;
+			break;
+		}
+
+		if (runtime > period ||
+		    period > fair_server_period_max ||
+		    period < fair_server_period_min) {
+			return  -EINVAL;
+		}
+
+		if (rq->cfs.h_nr_running) {
+			update_rq_clock(rq);
+			dl_server_stop(&rq->fair_server);
+		}
+
+		retval = dl_server_apply_params(&rq->fair_server, runtime, period, 0);
+		if (retval)
+			cnt = retval;
+
+		if (!runtime)
+			printk_deferred("Fair server disabled in CPU %d, system may crash due to starvation.\n",
+					cpu_of(rq));
+
+		if (rq->cfs.h_nr_running)
+			dl_server_start(&rq->fair_server);
+	}
+
+	*ppos += cnt;
+	return cnt;
+}
+
+static size_t sched_fair_server_show(struct seq_file *m, void *v, enum dl_param param)
+{
+	unsigned long cpu = (unsigned long) m->private;
+	struct rq *rq = cpu_rq(cpu);
+	u64 value;
+
+	switch (param) {
+	case DL_RUNTIME:
+		value = rq->fair_server.dl_runtime;
+		break;
+	case DL_PERIOD:
+		value = rq->fair_server.dl_period;
+		break;
+	}
+
+	seq_printf(m, "%llu\n", value);
+	return 0;
+
+}
+
+static ssize_t
+sched_fair_server_runtime_write(struct file *filp, const char __user *ubuf,
+				size_t cnt, loff_t *ppos)
+{
+	return sched_fair_server_write(filp, ubuf, cnt, ppos, DL_RUNTIME);
+}
+
+static int sched_fair_server_runtime_show(struct seq_file *m, void *v)
+{
+	return sched_fair_server_show(m, v, DL_RUNTIME);
+}
+
+static int sched_fair_server_runtime_open(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, sched_fair_server_runtime_show, inode->i_private);
+}
+
+static const struct file_operations fair_server_runtime_fops = {
+	.open		= sched_fair_server_runtime_open,
+	.write		= sched_fair_server_runtime_write,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static ssize_t
+sched_fair_server_period_write(struct file *filp, const char __user *ubuf,
+			       size_t cnt, loff_t *ppos)
+{
+	return sched_fair_server_write(filp, ubuf, cnt, ppos, DL_PERIOD);
+}
+
+static int sched_fair_server_period_show(struct seq_file *m, void *v)
+{
+	return sched_fair_server_show(m, v, DL_PERIOD);
+}
+
+static int sched_fair_server_period_open(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, sched_fair_server_period_show, inode->i_private);
+}
+
+static const struct file_operations fair_server_period_fops = {
+	.open		= sched_fair_server_period_open,
+	.write		= sched_fair_server_period_write,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
 static struct dentry *debugfs_sched;
 
+static void debugfs_fair_server_init(void)
+{
+	struct dentry *d_fair;
+	unsigned long cpu;
+
+	d_fair = debugfs_create_dir("fair_server", debugfs_sched);
+	if (!d_fair)
+		return;
+
+	for_each_possible_cpu(cpu) {
+		struct dentry *d_cpu;
+		char buf[32];
+
+		snprintf(buf, sizeof(buf), "cpu%lu", cpu);
+		d_cpu = debugfs_create_dir(buf, d_fair);
+
+		debugfs_create_file("runtime", 0644, d_cpu, (void *) cpu, &fair_server_runtime_fops);
+		debugfs_create_file("period", 0644, d_cpu, (void *) cpu, &fair_server_period_fops);
+	}
+}
+
 static __init int sched_init_debug(void)
 {
 	struct dentry __maybe_unused *numa;
@@ -374,6 +531,8 @@ static __init int sched_init_debug(void)
 
 	debugfs_create_file("debug", 0444, debugfs_sched, NULL, &sched_debug_fops);
 
+	debugfs_fair_server_init();
+
 	return 0;
 }
 late_initcall(sched_init_debug);
@@ -580,27 +739,27 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
 	else
 		SEQ_printf(m, " %c", task_state_to_char(p));
 
-	SEQ_printf(m, "%15s %5d %9Ld.%06ld %c %9Ld.%06ld %9Ld.%06ld %9Ld.%06ld %9Ld %5d ",
+	SEQ_printf(m, " %15s %5d %9Ld.%06ld   %c   %9Ld.%06ld %c %9Ld.%06ld %9Ld.%06ld %9Ld   %5d ",
 		p->comm, task_pid_nr(p),
 		SPLIT_NS(p->se.vruntime),
 		entity_eligible(cfs_rq_of(&p->se), &p->se) ? 'E' : 'N',
 		SPLIT_NS(p->se.deadline),
+		p->se.custom_slice ? 'S' : ' ',
 		SPLIT_NS(p->se.slice),
 		SPLIT_NS(p->se.sum_exec_runtime),
 		(long long)(p->nvcsw + p->nivcsw),
 		p->prio);
 
-	SEQ_printf(m, "%9lld.%06ld %9lld.%06ld %9lld.%06ld %9lld.%06ld",
+	SEQ_printf(m, "%9lld.%06ld %9lld.%06ld %9lld.%06ld",
 		SPLIT_NS(schedstat_val_or_zero(p->stats.wait_sum)),
-		SPLIT_NS(p->se.sum_exec_runtime),
 		SPLIT_NS(schedstat_val_or_zero(p->stats.sum_sleep_runtime)),
 		SPLIT_NS(schedstat_val_or_zero(p->stats.sum_block_runtime)));
 
 #ifdef CONFIG_NUMA_BALANCING
-	SEQ_printf(m, " %d %d", task_node(p), task_numa_group_id(p));
+	SEQ_printf(m, "   %d      %d", task_node(p), task_numa_group_id(p));
 #endif
 #ifdef CONFIG_CGROUP_SCHED
-	SEQ_printf_task_group_path(m, task_group(p), " %s")
+	SEQ_printf_task_group_path(m, task_group(p), "        %s")
 #endif
 
 	SEQ_printf(m, "\n");
@@ -612,10 +771,26 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu)
 
 	SEQ_printf(m, "\n");
 	SEQ_printf(m, "runnable tasks:\n");
-	SEQ_printf(m, " S            task   PID         tree-key  switches  prio"
-		   "     wait-time             sum-exec        sum-sleep\n");
+	SEQ_printf(m, " S            task   PID       vruntime   eligible    "
+		   "deadline             slice          sum-exec      switches  "
+		   "prio         wait-time        sum-sleep       sum-block"
+#ifdef CONFIG_NUMA_BALANCING
+		   "  node   group-id"
+#endif
+#ifdef CONFIG_CGROUP_SCHED
+		   "  group-path"
+#endif
+		   "\n");
 	SEQ_printf(m, "-------------------------------------------------------"
-		   "------------------------------------------------------\n");
+		   "------------------------------------------------------"
+		   "------------------------------------------------------"
+#ifdef CONFIG_NUMA_BALANCING
+		   "--------------"
+#endif
+#ifdef CONFIG_CGROUP_SCHED
+		   "--------------"
+#endif
+		   "\n");
 
 	rcu_read_lock();
 	for_each_process_thread(g, p) {
@@ -641,8 +816,6 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 	SEQ_printf(m, "\n");
 	SEQ_printf(m, "cfs_rq[%d]:\n", cpu);
 #endif
-	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "exec_clock",
-			SPLIT_NS(cfs_rq->exec_clock));
 
 	raw_spin_rq_lock_irqsave(rq, flags);
 	root = __pick_root_entity(cfs_rq);
@@ -669,8 +842,6 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 			SPLIT_NS(right_vruntime));
 	spread = right_vruntime - left_vruntime;
 	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "spread", SPLIT_NS(spread));
-	SEQ_printf(m, "  .%-30s: %d\n", "nr_spread_over",
-			cfs_rq->nr_spread_over);
 	SEQ_printf(m, "  .%-30s: %d\n", "nr_running", cfs_rq->nr_running);
 	SEQ_printf(m, "  .%-30s: %d\n", "h_nr_running", cfs_rq->h_nr_running);
 	SEQ_printf(m, "  .%-30s: %d\n", "idle_nr_running",
@@ -730,9 +901,12 @@ void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq)
 	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", #x, SPLIT_NS(rt_rq->x))
 
 	PU(rt_nr_running);
+
+#ifdef CONFIG_RT_GROUP_SCHED
 	P(rt_throttled);
 	PN(rt_time);
 	PN(rt_runtime);
+#endif
 
 #undef PN
 #undef PU

kernel/sched/features.h

@@ -5,8 +5,24 @@
  * sleep+wake cycles. EEVDF placement strategy #1, #2 if disabled.
  */
 SCHED_FEAT(PLACE_LAG, true)
+/*
+ * Give new tasks half a slice to ease into the competition.
+ */
 SCHED_FEAT(PLACE_DEADLINE_INITIAL, true)
+/*
+ * Preserve relative virtual deadline on 'migration'.
+ */
+SCHED_FEAT(PLACE_REL_DEADLINE, true)
+/*
+ * Inhibit (wakeup) preemption until the current task has either matched the
+ * 0-lag point or until is has exhausted it's slice.
+ */
 SCHED_FEAT(RUN_TO_PARITY, true)
+/*
+ * Allow wakeup of tasks with a shorter slice to cancel RESPECT_SLICE for
+ * current.
+ */
+SCHED_FEAT(PREEMPT_SHORT, true)
 
 /*
  * Prefer to schedule the task we woke last (assuming it failed
@@ -21,6 +37,18 @@ SCHED_FEAT(NEXT_BUDDY, false)
  */
 SCHED_FEAT(CACHE_HOT_BUDDY, true)
 
+/*
+ * Delay dequeueing tasks until they get selected or woken.
+ *
+ * By delaying the dequeue for non-eligible tasks, they remain in the
+ * competition and can burn off their negative lag. When they get selected
+ * they'll have positive lag by definition.
+ *
+ * DELAY_ZERO clips the lag on dequeue (or wakeup) to 0.
+ */
+SCHED_FEAT(DELAY_DEQUEUE, true)
+SCHED_FEAT(DELAY_ZERO, true)
+
 /*
  * Allow wakeup-time preemption of the current task:
  */
@@ -85,5 +113,3 @@ SCHED_FEAT(WA_BIAS, true)
 SCHED_FEAT(UTIL_EST, true)
 
 SCHED_FEAT(LATENCY_WARN, false)
-
-SCHED_FEAT(HZ_BW, true)

kernel/sched/idle.c

@@ -450,43 +450,35 @@ static void wakeup_preempt_idle(struct rq *rq, struct task_struct *p, int flags)
 	resched_curr(rq);
 }
 
-static void put_prev_task_idle(struct rq *rq, struct task_struct *prev)
+static void put_prev_task_idle(struct rq *rq, struct task_struct *prev, struct task_struct *next)
 {
+	dl_server_update_idle_time(rq, prev);
 }
 
 static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool first)
 {
 	update_idle_core(rq);
 	schedstat_inc(rq->sched_goidle);
+	next->se.exec_start = rq_clock_task(rq);
 }
 
-#ifdef CONFIG_SMP
-static struct task_struct *pick_task_idle(struct rq *rq)
+struct task_struct *pick_task_idle(struct rq *rq)
 {
 	return rq->idle;
 }
-#endif
-
-struct task_struct *pick_next_task_idle(struct rq *rq)
-{
-	struct task_struct *next = rq->idle;
-
-	set_next_task_idle(rq, next, true);
-
-	return next;
-}
 
 /*
  * It is not legal to sleep in the idle task - print a warning
  * message if some code attempts to do it:
  */
-static void
+static bool
 dequeue_task_idle(struct rq *rq, struct task_struct *p, int flags)
 {
 	raw_spin_rq_unlock_irq(rq);
 	printk(KERN_ERR "bad: scheduling from the idle thread!\n");
 	dump_stack();
 	raw_spin_rq_lock_irq(rq);
+	return true;
 }
 
 /*
@@ -528,13 +520,12 @@ DEFINE_SCHED_CLASS(idle) = {
 
 	.wakeup_preempt		= wakeup_preempt_idle,
 
-	.pick_next_task		= pick_next_task_idle,
+	.pick_task		= pick_task_idle,
 	.put_prev_task		= put_prev_task_idle,
 	.set_next_task          = set_next_task_idle,
 
 #ifdef CONFIG_SMP
 	.balance		= balance_idle,
-	.pick_task		= pick_task_idle,
 	.select_task_rq		= select_task_rq_idle,
 	.set_cpus_allowed	= set_cpus_allowed_common,
 #endif

kernel/sched/rt.c

@@ -8,10 +8,6 @@ int sched_rr_timeslice = RR_TIMESLICE;
 /* More than 4 hours if BW_SHIFT equals 20. */
 static const u64 max_rt_runtime = MAX_BW;
 
-static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun);
-
-struct rt_bandwidth def_rt_bandwidth;
-
 /*
  * period over which we measure -rt task CPU usage in us.
  * default: 1s
@@ -66,6 +62,40 @@ static int __init sched_rt_sysctl_init(void)
 late_initcall(sched_rt_sysctl_init);
 #endif
 
+void init_rt_rq(struct rt_rq *rt_rq)
+{
+	struct rt_prio_array *array;
+	int i;
+
+	array = &rt_rq->active;
+	for (i = 0; i < MAX_RT_PRIO; i++) {
+		INIT_LIST_HEAD(array->queue + i);
+		__clear_bit(i, array->bitmap);
+	}
+	/* delimiter for bitsearch: */
+	__set_bit(MAX_RT_PRIO, array->bitmap);
+
+#if defined CONFIG_SMP
+	rt_rq->highest_prio.curr = MAX_RT_PRIO-1;
+	rt_rq->highest_prio.next = MAX_RT_PRIO-1;
+	rt_rq->overloaded = 0;
+	plist_head_init(&rt_rq->pushable_tasks);
+#endif /* CONFIG_SMP */
+	/* We start is dequeued state, because no RT tasks are queued */
+	rt_rq->rt_queued = 0;
+
+#ifdef CONFIG_RT_GROUP_SCHED
+	rt_rq->rt_time = 0;
+	rt_rq->rt_throttled = 0;
+	rt_rq->rt_runtime = 0;
+	raw_spin_lock_init(&rt_rq->rt_runtime_lock);
+#endif
+}
+
+#ifdef CONFIG_RT_GROUP_SCHED
+
+static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun);
+
 static enum hrtimer_restart sched_rt_period_timer(struct hrtimer *timer)
 {
 	struct rt_bandwidth *rt_b =
@@ -130,35 +160,6 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
 	do_start_rt_bandwidth(rt_b);
 }
 
-void init_rt_rq(struct rt_rq *rt_rq)
-{
-	struct rt_prio_array *array;
-	int i;
-
-	array = &rt_rq->active;
-	for (i = 0; i < MAX_RT_PRIO; i++) {
-		INIT_LIST_HEAD(array->queue + i);
-		__clear_bit(i, array->bitmap);
-	}
-	/* delimiter for bit-search: */
-	__set_bit(MAX_RT_PRIO, array->bitmap);
-
-#if defined CONFIG_SMP
-	rt_rq->highest_prio.curr = MAX_RT_PRIO-1;
-	rt_rq->highest_prio.next = MAX_RT_PRIO-1;
-	rt_rq->overloaded = 0;
-	plist_head_init(&rt_rq->pushable_tasks);
-#endif /* CONFIG_SMP */
-	/* We start is dequeued state, because no RT tasks are queued */
-	rt_rq->rt_queued = 0;
-
-	rt_rq->rt_time = 0;
-	rt_rq->rt_throttled = 0;
-	rt_rq->rt_runtime = 0;
-	raw_spin_lock_init(&rt_rq->rt_runtime_lock);
-}
-
-#ifdef CONFIG_RT_GROUP_SCHED
 static void destroy_rt_bandwidth(struct rt_bandwidth *rt_b)
 {
 	hrtimer_cancel(&rt_b->rt_period_timer);
@@ -195,7 +196,6 @@ void unregister_rt_sched_group(struct task_group *tg)
 {
 	if (tg->rt_se)
 		destroy_rt_bandwidth(&tg->rt_bandwidth);
-
 }
 
 void free_rt_sched_group(struct task_group *tg)
@@ -253,8 +253,7 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
 	if (!tg->rt_se)
 		goto err;
 
-	init_rt_bandwidth(&tg->rt_bandwidth,
-			ktime_to_ns(def_rt_bandwidth.rt_period), 0);
+	init_rt_bandwidth(&tg->rt_bandwidth, ktime_to_ns(global_rt_period()), 0);
 
 	for_each_possible_cpu(i) {
 		rt_rq = kzalloc_node(sizeof(struct rt_rq),
@@ -604,70 +603,6 @@ static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq)
 	return &rt_rq->tg->rt_bandwidth;
 }
 
-#else /* !CONFIG_RT_GROUP_SCHED */
-
-static inline u64 sched_rt_runtime(struct rt_rq *rt_rq)
-{
-	return rt_rq->rt_runtime;
-}
-
-static inline u64 sched_rt_period(struct rt_rq *rt_rq)
-{
-	return ktime_to_ns(def_rt_bandwidth.rt_period);
-}
-
-typedef struct rt_rq *rt_rq_iter_t;
-
-#define for_each_rt_rq(rt_rq, iter, rq) \
-	for ((void) iter, rt_rq = &rq->rt; rt_rq; rt_rq = NULL)
-
-#define for_each_sched_rt_entity(rt_se) \
-	for (; rt_se; rt_se = NULL)
-
-static inline struct rt_rq *group_rt_rq(struct sched_rt_entity *rt_se)
-{
-	return NULL;
-}
-
-static inline void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
-{
-	struct rq *rq = rq_of_rt_rq(rt_rq);
-
-	if (!rt_rq->rt_nr_running)
-		return;
-
-	enqueue_top_rt_rq(rt_rq);
-	resched_curr(rq);
-}
-
-static inline void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
-{
-	dequeue_top_rt_rq(rt_rq, rt_rq->rt_nr_running);
-}
-
-static inline int rt_rq_throttled(struct rt_rq *rt_rq)
-{
-	return rt_rq->rt_throttled;
-}
-
-static inline const struct cpumask *sched_rt_period_mask(void)
-{
-	return cpu_online_mask;
-}
-
-static inline
-struct rt_rq *sched_rt_period_rt_rq(struct rt_bandwidth *rt_b, int cpu)
-{
-	return &cpu_rq(cpu)->rt;
-}
-
-static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq)
-{
-	return &def_rt_bandwidth;
-}
-
-#endif /* CONFIG_RT_GROUP_SCHED */
-
 bool sched_rt_bandwidth_account(struct rt_rq *rt_rq)
 {
 	struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
@@ -859,7 +794,7 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
 	const struct cpumask *span;
 
 	span = sched_rt_period_mask();
-#ifdef CONFIG_RT_GROUP_SCHED
+
 	/*
 	 * FIXME: isolated CPUs should really leave the root task group,
 	 * whether they are isolcpus or were isolated via cpusets, lest
@@ -871,7 +806,7 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
 	 */
 	if (rt_b == &root_task_group.rt_bandwidth)
 		span = cpu_online_mask;
-#endif
+
 	for_each_cpu(i, span) {
 		int enqueue = 0;
 		struct rt_rq *rt_rq = sched_rt_period_rt_rq(rt_b, i);
@@ -938,18 +873,6 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
 	return idle;
 }
 
-static inline int rt_se_prio(struct sched_rt_entity *rt_se)
-{
-#ifdef CONFIG_RT_GROUP_SCHED
-	struct rt_rq *rt_rq = group_rt_rq(rt_se);
-
-	if (rt_rq)
-		return rt_rq->highest_prio.curr;
-#endif
-
-	return rt_task_of(rt_se)->prio;
-}
-
 static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq)
 {
 	u64 runtime = sched_rt_runtime(rt_rq);
@@ -993,6 +916,72 @@ static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq)
 	return 0;
 }
 
+#else /* !CONFIG_RT_GROUP_SCHED */
+
+typedef struct rt_rq *rt_rq_iter_t;
+
+#define for_each_rt_rq(rt_rq, iter, rq) \
+	for ((void) iter, rt_rq = &rq->rt; rt_rq; rt_rq = NULL)
+
+#define for_each_sched_rt_entity(rt_se) \
+	for (; rt_se; rt_se = NULL)
+
+static inline struct rt_rq *group_rt_rq(struct sched_rt_entity *rt_se)
+{
+	return NULL;
+}
+
+static inline void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
+{
+	struct rq *rq = rq_of_rt_rq(rt_rq);
+
+	if (!rt_rq->rt_nr_running)
+		return;
+
+	enqueue_top_rt_rq(rt_rq);
+	resched_curr(rq);
+}
+
+static inline void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
+{
+	dequeue_top_rt_rq(rt_rq, rt_rq->rt_nr_running);
+}
+
+static inline int rt_rq_throttled(struct rt_rq *rt_rq)
+{
+	return false;
+}
+
+static inline const struct cpumask *sched_rt_period_mask(void)
+{
+	return cpu_online_mask;
+}
+
+static inline
+struct rt_rq *sched_rt_period_rt_rq(struct rt_bandwidth *rt_b, int cpu)
+{
+	return &cpu_rq(cpu)->rt;
+}
+
+#ifdef CONFIG_SMP
+static void __enable_runtime(struct rq *rq) { }
+static void __disable_runtime(struct rq *rq) { }
+#endif
+
+#endif /* CONFIG_RT_GROUP_SCHED */
+
+static inline int rt_se_prio(struct sched_rt_entity *rt_se)
+{
+#ifdef CONFIG_RT_GROUP_SCHED
+	struct rt_rq *rt_rq = group_rt_rq(rt_se);
+
+	if (rt_rq)
+		return rt_rq->highest_prio.curr;
+#endif
+
+	return rt_task_of(rt_se)->prio;
+}
+
 /*
  * Update the current task's runtime statistics. Skip current tasks that
  * are not in our scheduling class.
@@ -1000,7 +989,6 @@ static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq)
 static void update_curr_rt(struct rq *rq)
 {
 	struct task_struct *curr = rq->curr;
-	struct sched_rt_entity *rt_se = &curr->rt;
 	s64 delta_exec;
 
 	if (curr->sched_class != &rt_sched_class)
@@ -1010,6 +998,9 @@ static void update_curr_rt(struct rq *rq)
 	if (unlikely(delta_exec <= 0))
 		return;
 
+#ifdef CONFIG_RT_GROUP_SCHED
+	struct sched_rt_entity *rt_se = &curr->rt;
+
 	if (!rt_bandwidth_enabled())
 		return;
 
@@ -1028,6 +1019,7 @@ static void update_curr_rt(struct rq *rq)
 				do_start_rt_bandwidth(sched_rt_bandwidth(rt_rq));
 		}
 	}
+#endif
 }
 
 static void
@@ -1184,7 +1176,6 @@ dec_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 static void
 inc_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 {
-	start_rt_bandwidth(&def_rt_bandwidth);
 }
 
 static inline
@@ -1492,7 +1483,7 @@ enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags)
 		enqueue_pushable_task(rq, p);
 }
 
-static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags)
+static bool dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags)
 {
 	struct sched_rt_entity *rt_se = &p->rt;
 
@@ -1500,6 +1491,8 @@ static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags)
 	dequeue_rt_entity(rt_se, flags);
 
 	dequeue_pushable_task(rq, p);
+
+	return true;
 }
 
 /*
@@ -1755,17 +1748,7 @@ static struct task_struct *pick_task_rt(struct rq *rq)
 	return p;
 }
 
-static struct task_struct *pick_next_task_rt(struct rq *rq)
-{
-	struct task_struct *p = pick_task_rt(rq);
-
-	if (p)
-		set_next_task_rt(rq, p, true);
-
-	return p;
-}
-
-static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
+static void put_prev_task_rt(struct rq *rq, struct task_struct *p, struct task_struct *next)
 {
 	struct sched_rt_entity *rt_se = &p->rt;
 	struct rt_rq *rt_rq = &rq->rt;
@@ -2652,13 +2635,12 @@ DEFINE_SCHED_CLASS(rt) = {
 
 	.wakeup_preempt		= wakeup_preempt_rt,
 
-	.pick_next_task		= pick_next_task_rt,
+	.pick_task		= pick_task_rt,
 	.put_prev_task		= put_prev_task_rt,
 	.set_next_task          = set_next_task_rt,
 
 #ifdef CONFIG_SMP
 	.balance		= balance_rt,
-	.pick_task		= pick_task_rt,
 	.select_task_rq		= select_task_rq_rt,
 	.set_cpus_allowed       = set_cpus_allowed_common,
 	.rq_online              = rq_online_rt,
@@ -2912,19 +2894,6 @@ int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk)
 #ifdef CONFIG_SYSCTL
 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_SYSCTL */
@@ -2944,12 +2913,6 @@ static int sched_rt_global_validate(void)
 
 static void sched_rt_do_global(void)
 {
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags);
-	def_rt_bandwidth.rt_runtime = global_rt_runtime();
-	def_rt_bandwidth.rt_period = ns_to_ktime(global_rt_period());
-	raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags);
 }
 
 static int sched_rt_handler(const struct ctl_table *table, int write, void *buffer,

kernel/sched/sched.h

@@ -68,6 +68,7 @@
 #include <linux/wait_api.h>
 #include <linux/wait_bit.h>
 #include <linux/workqueue_api.h>
+#include <linux/delayacct.h>
 
 #include <trace/events/power.h>
 #include <trace/events/sched.h>
@@ -335,7 +336,7 @@ extern bool __checkparam_dl(const struct sched_attr *attr);
 extern bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr);
 extern int  dl_cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial);
 extern int  dl_bw_check_overflow(int cpu);
-
+extern s64 dl_scaled_delta_exec(struct rq *rq, struct sched_dl_entity *dl_se, s64 delta_exec);
 /*
  * SCHED_DEADLINE supports servers (nested scheduling) with the following
  * interface:
@@ -361,7 +362,14 @@ extern void dl_server_start(struct sched_dl_entity *dl_se);
 extern void dl_server_stop(struct sched_dl_entity *dl_se);
 extern void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq,
 		    dl_server_has_tasks_f has_tasks,
-		    dl_server_pick_f pick);
+		    dl_server_pick_f pick_task);
+
+extern void dl_server_update_idle_time(struct rq *rq,
+		    struct task_struct *p);
+extern void fair_server_init(struct rq *rq);
+extern void __dl_server_attach_root(struct sched_dl_entity *dl_se, struct rq *rq);
+extern int dl_server_apply_params(struct sched_dl_entity *dl_se,
+		    u64 runtime, u64 period, bool init);
 
 #ifdef CONFIG_CGROUP_SCHED
 
@@ -599,17 +607,12 @@ struct cfs_rq {
 	s64			avg_vruntime;
 	u64			avg_load;
 
-	u64			exec_clock;
 	u64			min_vruntime;
 #ifdef CONFIG_SCHED_CORE
 	unsigned int		forceidle_seq;
 	u64			min_vruntime_fi;
 #endif
 
-#ifndef CONFIG_64BIT
-	u64			min_vruntime_copy;
-#endif
-
 	struct rb_root_cached	tasks_timeline;
 
 	/*
@@ -619,10 +622,6 @@ struct cfs_rq {
 	struct sched_entity	*curr;
 	struct sched_entity	*next;
 
-#ifdef	CONFIG_SCHED_DEBUG
-	unsigned int		nr_spread_over;
-#endif
-
 #ifdef CONFIG_SMP
 	/*
 	 * CFS load tracking
@@ -726,13 +725,13 @@ struct rt_rq {
 #endif /* CONFIG_SMP */
 	int			rt_queued;
 
+#ifdef CONFIG_RT_GROUP_SCHED
 	int			rt_throttled;
 	u64			rt_time;
 	u64			rt_runtime;
 	/* Nests inside the rq lock: */
 	raw_spinlock_t		rt_runtime_lock;
 
-#ifdef CONFIG_RT_GROUP_SCHED
 	unsigned int		rt_nr_boosted;
 
 	struct rq		*rq;
@@ -820,6 +819,9 @@ static inline void se_update_runnable(struct sched_entity *se)
 
 static inline long se_runnable(struct sched_entity *se)
 {
+	if (se->sched_delayed)
+		return false;
+
 	if (entity_is_task(se))
 		return !!se->on_rq;
 	else
@@ -834,6 +836,9 @@ static inline void se_update_runnable(struct sched_entity *se) { }
 
 static inline long se_runnable(struct sched_entity *se)
 {
+	if (se->sched_delayed)
+		return false;
+
 	return !!se->on_rq;
 }
 
@@ -1044,6 +1049,8 @@ struct rq {
 	struct rt_rq		rt;
 	struct dl_rq		dl;
 
+	struct sched_dl_entity	fair_server;
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	/* list of leaf cfs_rq on this CPU: */
 	struct list_head	leaf_cfs_rq_list;
@@ -1059,6 +1066,7 @@ struct rq {
 	unsigned int		nr_uninterruptible;
 
 	struct task_struct __rcu	*curr;
+	struct sched_dl_entity	*dl_server;
 	struct task_struct	*idle;
 	struct task_struct	*stop;
 	unsigned long		next_balance;
@@ -1158,7 +1166,6 @@ struct rq {
 	/* latency stats */
 	struct sched_info	rq_sched_info;
 	unsigned long long	rq_cpu_time;
-	/* could above be rq->cfs_rq.exec_clock + rq->rt_rq.rt_runtime ? */
 
 	/* sys_sched_yield() stats */
 	unsigned int		yld_count;
@@ -1187,6 +1194,7 @@ struct rq {
 	/* per rq */
 	struct rq		*core;
 	struct task_struct	*core_pick;
+	struct sched_dl_entity	*core_dl_server;
 	unsigned int		core_enabled;
 	unsigned int		core_sched_seq;
 	struct rb_root		core_tree;
@@ -2247,11 +2255,13 @@ extern const u32		sched_prio_to_wmult[40];
  *
  */
 
-#define DEQUEUE_SLEEP		0x01
+#define DEQUEUE_SLEEP		0x01 /* Matches ENQUEUE_WAKEUP */
 #define DEQUEUE_SAVE		0x02 /* Matches ENQUEUE_RESTORE */
 #define DEQUEUE_MOVE		0x04 /* Matches ENQUEUE_MOVE */
 #define DEQUEUE_NOCLOCK		0x08 /* Matches ENQUEUE_NOCLOCK */
+#define DEQUEUE_SPECIAL		0x10
 #define DEQUEUE_MIGRATING	0x100 /* Matches ENQUEUE_MIGRATING */
+#define DEQUEUE_DELAYED		0x200 /* Matches ENQUEUE_DELAYED */
 
 #define ENQUEUE_WAKEUP		0x01
 #define ENQUEUE_RESTORE		0x02
@@ -2267,6 +2277,7 @@ extern const u32		sched_prio_to_wmult[40];
 #endif
 #define ENQUEUE_INITIAL		0x80
 #define ENQUEUE_MIGRATING	0x100
+#define ENQUEUE_DELAYED		0x200
 
 #define RETRY_TASK		((void *)-1UL)
 
@@ -2285,23 +2296,31 @@ struct sched_class {
 #endif
 
 	void (*enqueue_task) (struct rq *rq, struct task_struct *p, int flags);
-	void (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags);
+	bool (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags);
 	void (*yield_task)   (struct rq *rq);
 	bool (*yield_to_task)(struct rq *rq, struct task_struct *p);
 
 	void (*wakeup_preempt)(struct rq *rq, struct task_struct *p, int flags);
 
-	struct task_struct *(*pick_next_task)(struct rq *rq);
+	struct task_struct *(*pick_task)(struct rq *rq);
+	/*
+	 * Optional! When implemented pick_next_task() should be equivalent to:
+	 *
+	 *   next = pick_task();
+	 *   if (next) {
+	 *       put_prev_task(prev);
+	 *       set_next_task_first(next);
+	 *   }
+	 */
+	struct task_struct *(*pick_next_task)(struct rq *rq, struct task_struct *prev);
 
-	void (*put_prev_task)(struct rq *rq, struct task_struct *p);
+	void (*put_prev_task)(struct rq *rq, struct task_struct *p, struct task_struct *next);
 	void (*set_next_task)(struct rq *rq, struct task_struct *p, bool first);
 
 #ifdef CONFIG_SMP
 	int (*balance)(struct rq *rq, struct task_struct *prev, struct rq_flags *rf);
 	int  (*select_task_rq)(struct task_struct *p, int task_cpu, int flags);
 
-	struct task_struct * (*pick_task)(struct rq *rq);
-
 	void (*migrate_task_rq)(struct task_struct *p, int new_cpu);
 
 	void (*task_woken)(struct rq *this_rq, struct task_struct *task);
@@ -2345,7 +2364,7 @@ struct sched_class {
 static inline void put_prev_task(struct rq *rq, struct task_struct *prev)
 {
 	WARN_ON_ONCE(rq->curr != prev);
-	prev->sched_class->put_prev_task(rq, prev);
+	prev->sched_class->put_prev_task(rq, prev, NULL);
 }
 
 static inline void set_next_task(struct rq *rq, struct task_struct *next)
@@ -2353,6 +2372,30 @@ static inline void set_next_task(struct rq *rq, struct task_struct *next)
 	next->sched_class->set_next_task(rq, next, false);
 }
 
+static inline void
+__put_prev_set_next_dl_server(struct rq *rq,
+			      struct task_struct *prev,
+			      struct task_struct *next)
+{
+	prev->dl_server = NULL;
+	next->dl_server = rq->dl_server;
+	rq->dl_server = NULL;
+}
+
+static inline void put_prev_set_next_task(struct rq *rq,
+					  struct task_struct *prev,
+					  struct task_struct *next)
+{
+	WARN_ON_ONCE(rq->curr != prev);
+
+	__put_prev_set_next_dl_server(rq, prev, next);
+
+	if (next == prev)
+		return;
+
+	prev->sched_class->put_prev_task(rq, prev, next);
+	next->sched_class->set_next_task(rq, next, true);
+}
 
 /*
  * Helper to define a sched_class instance; each one is placed in a separate
@@ -2408,7 +2451,7 @@ static inline bool sched_fair_runnable(struct rq *rq)
 }
 
 extern struct task_struct *pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf);
-extern struct task_struct *pick_next_task_idle(struct rq *rq);
+extern struct task_struct *pick_task_idle(struct rq *rq);
 
 #define SCA_CHECK		0x01
 #define SCA_MIGRATE_DISABLE	0x02
@@ -2515,7 +2558,6 @@ extern void reweight_task(struct task_struct *p, const struct load_weight *lw);
 extern void resched_curr(struct rq *rq);
 extern void resched_cpu(int cpu);
 
-extern struct rt_bandwidth def_rt_bandwidth;
 extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime);
 extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq);
 
@@ -2586,6 +2628,19 @@ static inline void sub_nr_running(struct rq *rq, unsigned count)
 	sched_update_tick_dependency(rq);
 }
 
+static inline void __block_task(struct rq *rq, struct task_struct *p)
+{
+	WRITE_ONCE(p->on_rq, 0);
+	ASSERT_EXCLUSIVE_WRITER(p->on_rq);
+	if (p->sched_contributes_to_load)
+		rq->nr_uninterruptible++;
+
+	if (p->in_iowait) {
+		atomic_inc(&rq->nr_iowait);
+		delayacct_blkio_start();
+	}
+}
+
 extern void activate_task(struct rq *rq, struct task_struct *p, int flags);
 extern void deactivate_task(struct rq *rq, struct task_struct *p, int flags);
 
@@ -3607,7 +3662,7 @@ extern int __sched_setaffinity(struct task_struct *p, struct affinity_context *c
 extern void __setscheduler_prio(struct task_struct *p, int prio);
 extern void set_load_weight(struct task_struct *p, bool update_load);
 extern void enqueue_task(struct rq *rq, struct task_struct *p, int flags);
-extern void dequeue_task(struct rq *rq, struct task_struct *p, int flags);
+extern bool dequeue_task(struct rq *rq, struct task_struct *p, int flags);
 
 extern void check_class_changed(struct rq *rq, struct task_struct *p,
 				const struct sched_class *prev_class,

kernel/sched/stop_task.c

@@ -41,26 +41,17 @@ static struct task_struct *pick_task_stop(struct rq *rq)
 	return rq->stop;
 }
 
-static struct task_struct *pick_next_task_stop(struct rq *rq)
-{
-	struct task_struct *p = pick_task_stop(rq);
-
-	if (p)
-		set_next_task_stop(rq, p, true);
-
-	return p;
-}
-
 static void
 enqueue_task_stop(struct rq *rq, struct task_struct *p, int flags)
 {
 	add_nr_running(rq, 1);
 }
 
-static void
+static bool
 dequeue_task_stop(struct rq *rq, struct task_struct *p, int flags)
 {
 	sub_nr_running(rq, 1);
+	return true;
 }
 
 static void yield_task_stop(struct rq *rq)
@@ -68,7 +59,7 @@ static void yield_task_stop(struct rq *rq)
 	BUG(); /* the stop task should never yield, its pointless. */
 }
 
-static void put_prev_task_stop(struct rq *rq, struct task_struct *prev)
+static void put_prev_task_stop(struct rq *rq, struct task_struct *prev, struct task_struct *next)
 {
 	update_curr_common(rq);
 }
@@ -111,13 +102,12 @@ DEFINE_SCHED_CLASS(stop) = {
 
 	.wakeup_preempt		= wakeup_preempt_stop,
 
-	.pick_next_task		= pick_next_task_stop,
+	.pick_task		= pick_task_stop,
 	.put_prev_task		= put_prev_task_stop,
 	.set_next_task          = set_next_task_stop,
 
 #ifdef CONFIG_SMP
 	.balance		= balance_stop,
-	.pick_task		= pick_task_stop,
 	.select_task_rq		= select_task_rq_stop,
 	.set_cpus_allowed	= set_cpus_allowed_common,
 #endif

kernel/sched/syscalls.c

@@ -57,7 +57,7 @@ static int effective_prio(struct task_struct *p)
 	 * keep the priority unchanged. Otherwise, update priority
 	 * to the normal priority:
 	 */
-	if (!rt_prio(p->prio))
+	if (!rt_or_dl_prio(p->prio))
 		return p->normal_prio;
 	return p->prio;
 }
@@ -258,107 +258,6 @@ int sched_core_idle_cpu(int cpu)
 
 #endif
 
-#ifdef CONFIG_SMP
-/*
- * This function computes an effective utilization for the given CPU, to be
- * used for frequency selection given the linear relation: f = u * f_max.
- *
- * The scheduler tracks the following metrics:
- *
- *   cpu_util_{cfs,rt,dl,irq}()
- *   cpu_bw_dl()
- *
- * Where the cfs,rt and dl util numbers are tracked with the same metric and
- * synchronized windows and are thus directly comparable.
- *
- * The cfs,rt,dl utilization are the running times measured with rq->clock_task
- * which excludes things like IRQ and steal-time. These latter are then accrued
- * in the IRQ utilization.
- *
- * The DL bandwidth number OTOH is not a measured metric but a value computed
- * based on the task model parameters and gives the minimal utilization
- * required to meet deadlines.
- */
-unsigned long effective_cpu_util(int cpu, unsigned long util_cfs,
-				 unsigned long *min,
-				 unsigned long *max)
-{
-	unsigned long util, irq, scale;
-	struct rq *rq = cpu_rq(cpu);
-
-	scale = arch_scale_cpu_capacity(cpu);
-
-	/*
-	 * Early check to see if IRQ/steal time saturates the CPU, can be
-	 * because of inaccuracies in how we track these -- see
-	 * update_irq_load_avg().
-	 */
-	irq = cpu_util_irq(rq);
-	if (unlikely(irq >= scale)) {
-		if (min)
-			*min = scale;
-		if (max)
-			*max = scale;
-		return scale;
-	}
-
-	if (min) {
-		/*
-		 * The minimum utilization returns the highest level between:
-		 * - the computed DL bandwidth needed with the IRQ pressure which
-		 *   steals time to the deadline task.
-		 * - The minimum performance requirement for CFS and/or RT.
-		 */
-		*min = max(irq + cpu_bw_dl(rq), uclamp_rq_get(rq, UCLAMP_MIN));
-
-		/*
-		 * When an RT task is runnable and uclamp is not used, we must
-		 * ensure that the task will run at maximum compute capacity.
-		 */
-		if (!uclamp_is_used() && rt_rq_is_runnable(&rq->rt))
-			*min = max(*min, scale);
-	}
-
-	/*
-	 * Because the time spend on RT/DL tasks is visible as 'lost' time to
-	 * CFS tasks and we use the same metric to track the effective
-	 * utilization (PELT windows are synchronized) we can directly add them
-	 * to obtain the CPU's actual utilization.
-	 */
-	util = util_cfs + cpu_util_rt(rq);
-	util += cpu_util_dl(rq);
-
-	/*
-	 * The maximum hint is a soft bandwidth requirement, which can be lower
-	 * than the actual utilization because of uclamp_max requirements.
-	 */
-	if (max)
-		*max = min(scale, uclamp_rq_get(rq, UCLAMP_MAX));
-
-	if (util >= scale)
-		return scale;
-
-	/*
-	 * There is still idle time; further improve the number by using the
-	 * IRQ metric. Because IRQ/steal time is hidden from the task clock we
-	 * need to scale the task numbers:
-	 *
-	 *              max - irq
-	 *   U' = irq + --------- * U
-	 *                 max
-	 */
-	util = scale_irq_capacity(util, irq, scale);
-	util += irq;
-
-	return min(scale, util);
-}
-
-unsigned long sched_cpu_util(int cpu)
-{
-	return effective_cpu_util(cpu, cpu_util_cfs(cpu), NULL, NULL);
-}
-#endif /* CONFIG_SMP */
-
 /**
  * find_process_by_pid - find a process with a matching PID value.
  * @pid: the pid in question.
@@ -401,13 +300,23 @@ static void __setscheduler_params(struct task_struct *p,
 
 	p->policy = policy;
 
-	if (dl_policy(policy))
+	if (dl_policy(policy)) {
 		__setparam_dl(p, attr);
-	else if (fair_policy(policy))
+	} else if (fair_policy(policy)) {
 		p->static_prio = NICE_TO_PRIO(attr->sched_nice);
+		if (attr->sched_runtime) {
+			p->se.custom_slice = 1;
+			p->se.slice = clamp_t(u64, attr->sched_runtime,
+					      NSEC_PER_MSEC/10,   /* HZ=1000 * 10 */
+					      NSEC_PER_MSEC*100); /* HZ=100  / 10 */
+		} else {
+			p->se.custom_slice = 0;
+			p->se.slice = sysctl_sched_base_slice;
+		}
+	}
 
 	/* rt-policy tasks do not have a timerslack */
-	if (task_is_realtime(p)) {
+	if (rt_or_dl_task_policy(p)) {
 		p->timer_slack_ns = 0;
 	} else if (p->timer_slack_ns == 0) {
 		/* when switching back to non-rt policy, restore timerslack */
@@ -708,7 +617,9 @@ recheck:
 	 * but store a possible modification of reset_on_fork.
 	 */
 	if (unlikely(policy == p->policy)) {
-		if (fair_policy(policy) && attr->sched_nice != task_nice(p))
+		if (fair_policy(policy) &&
+		    (attr->sched_nice != task_nice(p) ||
+		     (attr->sched_runtime != p->se.slice)))
 			goto change;
 		if (rt_policy(policy) && attr->sched_priority != p->rt_priority)
 			goto change;
@@ -854,6 +765,9 @@ static int _sched_setscheduler(struct task_struct *p, int policy,
 		.sched_nice	= PRIO_TO_NICE(p->static_prio),
 	};
 
+	if (p->se.custom_slice)
+		attr.sched_runtime = p->se.slice;
+
 	/* Fixup the legacy SCHED_RESET_ON_FORK hack. */
 	if ((policy != SETPARAM_POLICY) && (policy & SCHED_RESET_ON_FORK)) {
 		attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
@@ -1020,12 +934,14 @@ err_size:
 
 static void get_params(struct task_struct *p, struct sched_attr *attr)
 {
-	if (task_has_dl_policy(p))
+	if (task_has_dl_policy(p)) {
 		__getparam_dl(p, attr);
-	else if (task_has_rt_policy(p))
+	} else if (task_has_rt_policy(p)) {
 		attr->sched_priority = p->rt_priority;
-	else
+	} else {
 		attr->sched_nice = task_nice(p);
+		attr->sched_runtime = p->se.slice;
+	}
 }
 
 /**

kernel/sched/topology.c

@@ -516,6 +516,14 @@ void rq_attach_root(struct rq *rq, struct root_domain *rd)
 	if (cpumask_test_cpu(rq->cpu, cpu_active_mask))
 		set_rq_online(rq);
 
+	/*
+	 * Because the rq is not a task, dl_add_task_root_domain() did not
+	 * move the fair server bw to the rd if it already started.
+	 * Add it now.
+	 */
+	if (rq->fair_server.dl_server)
+		__dl_server_attach_root(&rq->fair_server, rq);
+
 	rq_unlock_irqrestore(rq, &rf);
 
 	if (old_rd)

kernel/sys.c

@@ -2557,7 +2557,7 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 			error = current->timer_slack_ns;
 		break;
 	case PR_SET_TIMERSLACK:
-		if (task_is_realtime(current))
+		if (rt_or_dl_task_policy(current))
 			break;
 		if (arg2 <= 0)
 			current->timer_slack_ns =

kernel/time/hrtimer.c

@@ -1977,7 +1977,7 @@ static void __hrtimer_init_sleeper(struct hrtimer_sleeper *sl,
 	 * expiry.
 	 */
 	if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
-		if (task_is_realtime(current) && !(mode & HRTIMER_MODE_SOFT))
+		if (rt_or_dl_task_policy(current) && !(mode & HRTIMER_MODE_SOFT))
 			mode |= HRTIMER_MODE_HARD;
 	}
 

kernel/trace/trace_sched_wakeup.c

@@ -547,7 +547,7 @@ probe_wakeup(void *ignore, struct task_struct *p)
 	 *  - wakeup_dl handles tasks belonging to sched_dl class only.
 	 */
 	if (tracing_dl || (wakeup_dl && !dl_task(p)) ||
-	    (wakeup_rt && !dl_task(p) && !rt_task(p)) ||
+	    (wakeup_rt && !rt_or_dl_task(p)) ||
 	    (!dl_task(p) && (p->prio >= wakeup_prio || p->prio >= current->prio)))
 		return;
 

mm/page-writeback.c

@@ -418,7 +418,7 @@ static void domain_dirty_limits(struct dirty_throttle_control *dtc)
 		bg_thresh = (bg_ratio * available_memory) / PAGE_SIZE;
 
 	tsk = current;
-	if (rt_task(tsk)) {
+	if (rt_or_dl_task(tsk)) {
 		bg_thresh += bg_thresh / 4 + global_wb_domain.dirty_limit / 32;
 		thresh += thresh / 4 + global_wb_domain.dirty_limit / 32;
 	}
@@ -477,7 +477,7 @@ static unsigned long node_dirty_limit(struct pglist_data *pgdat)
 	else
 		dirty = vm_dirty_ratio * node_memory / 100;
 
-	if (rt_task(tsk))
+	if (rt_or_dl_task(tsk))
 		dirty += dirty / 4;
 
 	/*

mm/page_alloc.c

@@ -4004,7 +4004,7 @@ gfp_to_alloc_flags(gfp_t gfp_mask, unsigned int order)
 		 */
 		if (alloc_flags & ALLOC_MIN_RESERVE)
 			alloc_flags &= ~ALLOC_CPUSET;
-	} else if (unlikely(rt_task(current)) && in_task())
+	} else if (unlikely(rt_or_dl_task(current)) && in_task())
 		alloc_flags |= ALLOC_MIN_RESERVE;
 
 	alloc_flags = gfp_to_alloc_flags_cma(gfp_mask, alloc_flags);

security/smack/smack_netfilter.c

@@ -19,8 +19,8 @@
 #include "smack.h"
 
 static unsigned int smack_ip_output(void *priv,
-					struct sk_buff *skb,
-					const struct nf_hook_state *state)
+				    struct sk_buff *skb,
+				    const struct nf_hook_state *state)
 {
 	struct sock *sk = skb_to_full_sk(skb);
 	struct socket_smack *ssp;

security/smack/smackfs.c

@@ -932,7 +932,7 @@ static ssize_t smk_set_cipso(struct file *file, const char __user *buf,
 	}
 	if (rc >= 0) {
 		old_cat = skp->smk_netlabel.attr.mls.cat;
-		skp->smk_netlabel.attr.mls.cat = ncats.attr.mls.cat;
+		rcu_assign_pointer(skp->smk_netlabel.attr.mls.cat, ncats.attr.mls.cat);
 		skp->smk_netlabel.attr.mls.lvl = ncats.attr.mls.lvl;
 		synchronize_rcu();
 		netlbl_catmap_free(old_cat);