diff --git a/arch/arm/mach-imx/cpuidle-imx6q.c b/arch/arm/mach-imx/cpuidle-imx6q.c
index 326e870d712394fad445033defd8e3ff5975ebdd..d9ac80aa1eb0a17dae81a0aa4e883f7386b86886 100644
--- a/arch/arm/mach-imx/cpuidle-imx6q.c
+++ b/arch/arm/mach-imx/cpuidle-imx6q.c
@@ -17,22 +17,22 @@
 #include "hardware.h"
 
 static int num_idle_cpus = 0;
-static DEFINE_SPINLOCK(cpuidle_lock);
+static DEFINE_RAW_SPINLOCK(cpuidle_lock);
 
 static int imx6q_enter_wait(struct cpuidle_device *dev,
 			    struct cpuidle_driver *drv, int index)
 {
-	spin_lock(&cpuidle_lock);
+	raw_spin_lock(&cpuidle_lock);
 	if (++num_idle_cpus == num_online_cpus())
 		imx6_set_lpm(WAIT_UNCLOCKED);
-	spin_unlock(&cpuidle_lock);
+	raw_spin_unlock(&cpuidle_lock);
 
 	cpu_do_idle();
 
-	spin_lock(&cpuidle_lock);
+	raw_spin_lock(&cpuidle_lock);
 	if (num_idle_cpus-- == num_online_cpus())
 		imx6_set_lpm(WAIT_CLOCKED);
-	spin_unlock(&cpuidle_lock);
+	raw_spin_unlock(&cpuidle_lock);
 
 	return index;
 }
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 3e4dd4b2771d13a3cf05567565d2bf03aa33094e..5840d9033b5b7c3e36a5aad95df016f88f59099c 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -2261,7 +2261,7 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu)
 	apic->vcpu = vcpu;
 
 	hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC,
-		     HRTIMER_MODE_ABS_PINNED);
+		     HRTIMER_MODE_ABS_PINNED_HARD);
 	apic->lapic_timer.timer.function = apic_timer_fn;
 
 	/*
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 4542fb0217773acbe99dd0c4214a1d5c079c5ba4..7ac3221b57698013ddf18a906941d76548f653d5 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -3416,10 +3416,9 @@ static bool blk_mq_poll_hybrid_sleep(struct request_queue *q,
 	kt = nsecs;
 
 	mode = HRTIMER_MODE_REL;
-	hrtimer_init_on_stack(&hs.timer, CLOCK_MONOTONIC, mode);
+	hrtimer_init_sleeper_on_stack(&hs, CLOCK_MONOTONIC, mode, current);
 	hrtimer_set_expires(&hs.timer, kt);
 
-	hrtimer_init_sleeper(&hs, current);
 	do {
 		if (blk_mq_rq_state(rq) == MQ_RQ_COMPLETE)
 			break;
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 1a71e49fcda41615753e4b563585814192cbf374..01b7bb2a97c0f58562e32086baa0133b4e3f4ae9 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -70,7 +70,7 @@
 #include <linux/writeback.h>
 #include <linux/completion.h>
 #include <linux/highmem.h>
-#include <linux/kthread.h>
+#include <linux/kthread-cgroup.h>
 #include <linux/splice.h>
 #include <linux/sysfs.h>
 #include <linux/miscdevice.h>
diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c
index 77d4fb86d05beecab63e35c2edbde61771f3ab36..ea70bc0b06e9f91a94fb3bcc3b17c2c2c57f5bc1 100644
--- a/drivers/pci/switch/switchtec.c
+++ b/drivers/pci/switch/switchtec.c
@@ -360,7 +360,7 @@ static int switchtec_dev_open(struct inode *inode, struct file *filp)
 		return PTR_ERR(stuser);
 
 	filp->private_data = stuser;
-	nonseekable_open(inode, filp);
+	stream_open(inode, filp);
 
 	dev_dbg(&stdev->dev, "%s: %p\n", __func__, stuser);
 
diff --git a/drivers/spi/spi-rockchip.c b/drivers/spi/spi-rockchip.c
index e05426079b4df27562d9ddcf9925ed729ad5a78e..7998278221a4cf63eed5c3e1cc9d823482ecca0b 100644
--- a/drivers/spi/spi-rockchip.c
+++ b/drivers/spi/spi-rockchip.c
@@ -23,6 +23,7 @@
 #include <linux/spi/spi.h>
 #include <linux/pm_runtime.h>
 #include <linux/scatterlist.h>
+#include <linux/interrupt.h>
 
 #define DRIVER_NAME "rockchip-spi"
 
diff --git a/drivers/staging/android/vsoc.c b/drivers/staging/android/vsoc.c
index 22571abcaa4e88c0a141adf42f2a899c5669303e..78a529d363f3b5299bf2b588366ade7a9fe7df8d 100644
--- a/drivers/staging/android/vsoc.c
+++ b/drivers/staging/android/vsoc.c
@@ -437,12 +437,10 @@ static int handle_vsoc_cond_wait(struct file *filp, struct vsoc_cond_wait *arg)
 			return -EINVAL;
 		wake_time = ktime_set(arg->wake_time_sec, arg->wake_time_nsec);
 
-		hrtimer_init_on_stack(&to->timer, CLOCK_MONOTONIC,
-				      HRTIMER_MODE_ABS);
+		hrtimer_init_sleeper_on_stack(to, CLOCK_MONOTONIC,
+					      HRTIMER_MODE_ABS, current);
 		hrtimer_set_expires_range_ns(&to->timer, wake_time,
 					     current->timer_slack_ns);
-
-		hrtimer_init_sleeper(to, current);
 	}
 
 	while (1) {
diff --git a/fs/timerfd.c b/fs/timerfd.c
index d69ad801eb8039af7f19054d32791d48b40589aa..f845093466be1fd3c6a5afae135c8bd7586c41a6 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -471,7 +471,11 @@ static int do_timerfd_settime(int ufd, int flags,
 				break;
 		}
 		spin_unlock_irq(&ctx->wqh.lock);
-		cpu_relax();
+
+		if (isalarm(ctx))
+			hrtimer_grab_expiry_lock(&ctx->t.alarm.timer);
+		else
+			hrtimer_grab_expiry_lock(&ctx->t.tmr);
 	}
 
 	/*
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index 670f0019a67c32e230f5bce852c3e2139ba49f7f..d7476470957e71305be75310b8408c9ba2b6f43a 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -14,7 +14,7 @@
  * 	              Nauman Rafique <nauman@google.com>
  */
 
-#include <linux/cgroup.h>
+#include <linux/kthread-cgroup.h>
 #include <linux/percpu_counter.h>
 #include <linux/seq_file.h>
 #include <linux/radix-tree.h>
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 3892e9c8b2deb7993c11c1ac171375c7ba6e9e09..6c4c38186c99526c1697b47103ec0c9927d7a0d2 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -41,6 +41,7 @@ enum hrtimer_mode {
 	HRTIMER_MODE_REL	= 0x01,
 	HRTIMER_MODE_PINNED	= 0x02,
 	HRTIMER_MODE_SOFT	= 0x04,
+	HRTIMER_MODE_HARD	= 0x08,
 
 	HRTIMER_MODE_ABS_PINNED = HRTIMER_MODE_ABS | HRTIMER_MODE_PINNED,
 	HRTIMER_MODE_REL_PINNED = HRTIMER_MODE_REL | HRTIMER_MODE_PINNED,
@@ -51,6 +52,11 @@ enum hrtimer_mode {
 	HRTIMER_MODE_ABS_PINNED_SOFT = HRTIMER_MODE_ABS_PINNED | HRTIMER_MODE_SOFT,
 	HRTIMER_MODE_REL_PINNED_SOFT = HRTIMER_MODE_REL_PINNED | HRTIMER_MODE_SOFT,
 
+	HRTIMER_MODE_ABS_HARD	= HRTIMER_MODE_ABS | HRTIMER_MODE_HARD,
+	HRTIMER_MODE_REL_HARD	= HRTIMER_MODE_REL | HRTIMER_MODE_HARD,
+
+	HRTIMER_MODE_ABS_PINNED_HARD = HRTIMER_MODE_ABS_PINNED | HRTIMER_MODE_HARD,
+	HRTIMER_MODE_REL_PINNED_HARD = HRTIMER_MODE_REL_PINNED | HRTIMER_MODE_HARD,
 };
 
 /*
@@ -186,6 +192,8 @@ enum  hrtimer_base_type {
  * @nr_retries:		Total number of hrtimer interrupt retries
  * @nr_hangs:		Total number of hrtimer interrupt hangs
  * @max_hang_time:	Maximum time spent in hrtimer_interrupt
+ * @softirq_expiry_lock: Lock which is taken while softirq based hrtimer are
+ *			 expired
  * @expires_next:	absolute time of the next event, is required for remote
  *			hrtimer enqueue; it is the total first expiry time (hard
  *			and soft hrtimer are taken into account)
@@ -213,6 +221,7 @@ struct hrtimer_cpu_base {
 	unsigned short			nr_hangs;
 	unsigned int			max_hang_time;
 #endif
+	spinlock_t			softirq_expiry_lock;
 	ktime_t				expires_next;
 	struct hrtimer			*next_timer;
 	ktime_t				softirq_expires_next;
@@ -364,10 +373,17 @@ DECLARE_PER_CPU(struct tick_device, tick_cpu_device);
 /* Initialize timers: */
 extern void hrtimer_init(struct hrtimer *timer, clockid_t which_clock,
 			 enum hrtimer_mode mode);
+extern void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, clockid_t clock_id,
+				 enum hrtimer_mode mode,
+				 struct task_struct *task);
 
 #ifdef CONFIG_DEBUG_OBJECTS_TIMERS
 extern void hrtimer_init_on_stack(struct hrtimer *timer, clockid_t which_clock,
 				  enum hrtimer_mode mode);
+extern void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl,
+					  clockid_t clock_id,
+					  enum hrtimer_mode mode,
+					  struct task_struct *task);
 
 extern void destroy_hrtimer_on_stack(struct hrtimer *timer);
 #else
@@ -377,6 +393,15 @@ static inline void hrtimer_init_on_stack(struct hrtimer *timer,
 {
 	hrtimer_init(timer, which_clock, mode);
 }
+
+static inline void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl,
+					    clockid_t clock_id,
+					    enum hrtimer_mode mode,
+					    struct task_struct *task)
+{
+	hrtimer_init_sleeper(sl, clock_id, mode, task);
+}
+
 static inline void destroy_hrtimer_on_stack(struct hrtimer *timer) { }
 #endif
 
@@ -400,6 +425,7 @@ static inline void hrtimer_start(struct hrtimer *timer, ktime_t tim,
 
 extern int hrtimer_cancel(struct hrtimer *timer);
 extern int hrtimer_try_to_cancel(struct hrtimer *timer);
+extern void hrtimer_grab_expiry_lock(const struct hrtimer *timer);
 
 static inline void hrtimer_start_expires(struct hrtimer *timer,
 					 enum hrtimer_mode mode)
@@ -480,9 +506,6 @@ extern long hrtimer_nanosleep(const struct timespec64 *rqtp,
 			      const enum hrtimer_mode mode,
 			      const clockid_t clockid);
 
-extern void hrtimer_init_sleeper(struct hrtimer_sleeper *sl,
-				 struct task_struct *tsk);
-
 extern int schedule_hrtimeout_range(ktime_t *expires, u64 delta,
 						const enum hrtimer_mode mode);
 extern int schedule_hrtimeout_range_clock(ktime_t *expires,
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 6936d921aa53a00d67f65725a8af09e89876d7c4..26579b8233a7f97f3f5fc4859a204a3f022d0888 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -13,7 +13,7 @@
 #include <linux/hrtimer.h>
 #include <linux/kref.h>
 #include <linux/workqueue.h>
-#include <linux/swork.h>
+#include <linux/kthread.h>
 
 #include <linux/atomic.h>
 #include <asm/ptrace.h>
@@ -248,7 +248,6 @@ extern void resume_device_irqs(void);
  * struct irq_affinity_notify - context for notification of IRQ affinity changes
  * @irq:		Interrupt to which notification applies
  * @kref:		Reference count, for internal use
- * @swork:		Swork item, for internal use
  * @work:		Work item, for internal use
  * @notify:		Function to be called on change.  This will be
  *			called in process context.
@@ -261,7 +260,7 @@ struct irq_affinity_notify {
 	unsigned int irq;
 	struct kref kref;
 #ifdef CONFIG_PREEMPT_RT_BASE
-	struct swork_event swork;
+	struct kthread_work work;
 #else
 	struct work_struct work;
 #endif
diff --git a/include/linux/kthread-cgroup.h b/include/linux/kthread-cgroup.h
new file mode 100644
index 0000000000000000000000000000000000000000..53d34bca9d7249be700abcaa43c67019d463f36d
--- /dev/null
+++ b/include/linux/kthread-cgroup.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_KTHREAD_CGROUP_H
+#define _LINUX_KTHREAD_CGROUP_H
+#include <linux/kthread.h>
+#include <linux/cgroup.h>
+
+#ifdef CONFIG_BLK_CGROUP
+void kthread_associate_blkcg(struct cgroup_subsys_state *css);
+struct cgroup_subsys_state *kthread_blkcg(void);
+#else
+static inline void kthread_associate_blkcg(struct cgroup_subsys_state *css) { }
+static inline struct cgroup_subsys_state *kthread_blkcg(void)
+{
+	return NULL;
+}
+#endif
+#endif
diff --git a/include/linux/kthread.h b/include/linux/kthread.h
index fd6403945fc3c725d5ab3a4f6f7bca42514cb930..4571e251123788f5fb373129aee848812ab02467 100644
--- a/include/linux/kthread.h
+++ b/include/linux/kthread.h
@@ -105,7 +105,7 @@ struct kthread_delayed_work {
 };
 
 #define KTHREAD_WORKER_INIT(worker)	{				\
-	.lock = __SPIN_LOCK_UNLOCKED((worker).lock),			\
+	.lock = __RAW_SPIN_LOCK_UNLOCKED((worker).lock),			\
 	.work_list = LIST_HEAD_INIT((worker).work_list),		\
 	.delayed_work_list = LIST_HEAD_INIT((worker).delayed_work_list),\
 	}
@@ -199,14 +199,12 @@ void kthread_destroy_worker(struct kthread_worker *worker);
 
 struct cgroup_subsys_state;
 
-#ifdef CONFIG_BLK_CGROUP
-void kthread_associate_blkcg(struct cgroup_subsys_state *css);
-struct cgroup_subsys_state *kthread_blkcg(void);
-#else
-static inline void kthread_associate_blkcg(struct cgroup_subsys_state *css) { }
-static inline struct cgroup_subsys_state *kthread_blkcg(void)
+extern struct kthread_worker kthread_global_worker;
+void kthread_init_global_worker(void);
+
+static inline bool kthread_schedule_work(struct kthread_work *work)
 {
-	return NULL;
+	return kthread_queue_work(&kthread_global_worker, work);
 }
-#endif
+
 #endif /* _LINUX_KTHREAD_H */
diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index ee7e987ea1b4354ef93a149c997caf75b6269c1b..3e6c91bdf2ef8678f3319fe7b81c9f20359a4448 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -15,6 +15,7 @@ struct cpu_timer_list {
 	u64 expires, incr;
 	struct task_struct *task;
 	int firing;
+	int firing_cpu;
 };
 
 /*
@@ -114,8 +115,8 @@ struct k_itimer {
 		struct {
 			struct alarm	alarmtimer;
 		} alarm;
-		struct rcu_head		rcu;
 	} it;
+	struct rcu_head		rcu;
 };
 
 void run_posix_cpu_timers(struct task_struct *task);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 68fa3d093a97559aefdb5814c17ce00227190098..5425ccb2d689154b8a778516e76c013040069af3 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -938,6 +938,9 @@ struct task_struct {
 #ifdef CONFIG_POSIX_TIMERS
 	struct task_cputime		cputime_expires;
 	struct list_head		cpu_timers[3];
+#ifdef CONFIG_PREEMPT_RT_BASE
+	struct task_struct		*posix_timer_list;
+#endif
 #endif
 
 	/* Process credentials: */
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 2b5ef8e94d19268a383a53adaaa82d14a57be71c..94bd2e841de646ed52e6f5331682aa6133a38f0b 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -489,8 +489,8 @@ do {										\
 	int __ret = 0;								\
 	struct hrtimer_sleeper __t;						\
 										\
-	hrtimer_init_on_stack(&__t.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);	\
-	hrtimer_init_sleeper(&__t, current);					\
+	hrtimer_init_sleeper_on_stack(&__t, CLOCK_MONOTONIC, HRTIMER_MODE_REL,	\
+				      current);					\
 	if ((timeout) != KTIME_MAX)						\
 		hrtimer_start_range_ns(&__t.timer, timeout,			\
 				       current->timer_slack_ns,			\
diff --git a/init/init_task.c b/init/init_task.c
index 0b49b9cf55714000700f4120ef04ff90db43a3b8..9e33627482147ed06bf11f74e64463def98371c2 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -50,6 +50,12 @@ static struct sighand_struct init_sighand = {
 	.signalfd_wqh	= __WAIT_QUEUE_HEAD_INITIALIZER(init_sighand.signalfd_wqh),
 };
 
+#if defined(CONFIG_POSIX_TIMERS) && defined(CONFIG_PREEMPT_RT_BASE)
+# define INIT_TIMER_LIST		.posix_timer_list = NULL,
+#else
+# define INIT_TIMER_LIST
+#endif
+
 /*
  * Set up the first task table, touch at your own risk!. Base=0,
  * limit=0x1fffff (=2MB)
@@ -119,6 +125,7 @@ struct task_struct init_task
 	INIT_CPU_TIMERS(init_task)
 	.pi_lock	= __RAW_SPIN_LOCK_UNLOCKED(init_task.pi_lock),
 	.timer_slack_ns = 50000, /* 50 usec default slack */
+	INIT_TIMER_LIST
 	.thread_pid	= &init_struct_pid,
 	.thread_group	= LIST_HEAD_INIT(init_task.thread_group),
 	.thread_node	= LIST_HEAD_INIT(init_signals.thread_head),
diff --git a/init/main.c b/init/main.c
index c11aed805ef58cbcadf07ec643b7d80623e28679..e244ed4045c0a4fb1dfe23422a59503e75cad274 100644
--- a/init/main.c
+++ b/init/main.c
@@ -1136,6 +1136,7 @@ static noinline void __init kernel_init_freeable(void)
 	smp_prepare_cpus(setup_max_cpus);
 
 	workqueue_init();
+	kthread_init_global_worker();
 
 	init_mm_internals();
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 64c8205704451ff29b7a62a08e0489ff6b0aaa33..ce1ebde1a0ec0dd71cbb383238d412c8d89883e5 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1102,7 +1102,7 @@ static void __perf_mux_hrtimer_init(struct perf_cpu_context *cpuctx, int cpu)
 	cpuctx->hrtimer_interval = ns_to_ktime(NSEC_PER_MSEC * interval);
 
 	raw_spin_lock_init(&cpuctx->hrtimer_lock);
-	hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
+	hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED_HARD);
 	timer->function = perf_mux_hrtimer_handler;
 }
 
@@ -9326,7 +9326,7 @@ static void perf_swevent_init_hrtimer(struct perf_event *event)
 	if (!is_sampling_event(event))
 		return;
 
-	hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
 	hwc->hrtimer.function = perf_swevent_hrtimer;
 
 	/*
diff --git a/kernel/fork.c b/kernel/fork.c
index e43babb1af4f0616582e43c75d4f6c345c065702..6aef8c531a9064f40d68cadfa3545deff43bef3d 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1631,6 +1631,9 @@ static void rt_mutex_init_task(struct task_struct *p)
  */
 static void posix_cpu_timers_init(struct task_struct *tsk)
 {
+#ifdef CONFIG_PREEMPT_RT_BASE
+	tsk->posix_timer_list = NULL;
+#endif
 	tsk->cputime_expires.prof_exp = 0;
 	tsk->cputime_expires.virt_exp = 0;
 	tsk->cputime_expires.sched_exp = 0;
diff --git a/kernel/futex.c b/kernel/futex.c
index 0e5b78290df648759aded198fd8406504ee8ae5d..0ef8ec8a583eca2a0617c8844a95c49395c55183 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -2708,10 +2708,9 @@ static int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val,
 	if (abs_time) {
 		to = &timeout;
 
-		hrtimer_init_on_stack(&to->timer, (flags & FLAGS_CLOCKRT) ?
-				      CLOCK_REALTIME : CLOCK_MONOTONIC,
-				      HRTIMER_MODE_ABS);
-		hrtimer_init_sleeper(to, current);
+		hrtimer_init_sleeper_on_stack(to, (flags & FLAGS_CLOCKRT) ?
+					      CLOCK_REALTIME : CLOCK_MONOTONIC,
+					      HRTIMER_MODE_ABS, current);
 		hrtimer_set_expires_range_ns(&to->timer, *abs_time,
 					     current->timer_slack_ns);
 	}
@@ -2810,9 +2809,8 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags,
 
 	if (time) {
 		to = &timeout;
-		hrtimer_init_on_stack(&to->timer, CLOCK_REALTIME,
-				      HRTIMER_MODE_ABS);
-		hrtimer_init_sleeper(to, current);
+		hrtimer_init_sleeper_on_stack(to, CLOCK_REALTIME,
+					      HRTIMER_MODE_ABS, current);
 		hrtimer_set_expires(&to->timer, *time);
 	}
 
@@ -3249,10 +3247,9 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 
 	if (abs_time) {
 		to = &timeout;
-		hrtimer_init_on_stack(&to->timer, (flags & FLAGS_CLOCKRT) ?
-				      CLOCK_REALTIME : CLOCK_MONOTONIC,
-				      HRTIMER_MODE_ABS);
-		hrtimer_init_sleeper(to, current);
+		hrtimer_init_sleeper_on_stack(to, (flags & FLAGS_CLOCKRT) ?
+					      CLOCK_REALTIME : CLOCK_MONOTONIC,
+					      HRTIMER_MODE_ABS, current);
 		hrtimer_set_expires_range_ns(&to->timer, *abs_time,
 					     current->timer_slack_ns);
 	}
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 7e51e1d9f437359a372eec31838eb00349151320..c7440dd83e230290788f1352ad2c262871612cb8 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -324,7 +324,7 @@ int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask,
 		kref_get(&desc->affinity_notify->kref);
 
 #ifdef CONFIG_PREEMPT_RT_BASE
-		swork_queue(&desc->affinity_notify->swork);
+		kthread_schedule_work(&desc->affinity_notify->work);
 #else
 		schedule_work(&desc->affinity_notify->work);
 #endif
@@ -389,21 +389,11 @@ static void _irq_affinity_notify(struct irq_affinity_notify *notify)
 }
 
 #ifdef CONFIG_PREEMPT_RT_BASE
-static void init_helper_thread(void)
-{
-	static int init_sworker_once;
-
-	if (init_sworker_once)
-		return;
-	if (WARN_ON(swork_get()))
-		return;
-	init_sworker_once = 1;
-}
 
-static void irq_affinity_notify(struct swork_event *swork)
+static void irq_affinity_notify(struct kthread_work *work)
 {
 	struct irq_affinity_notify *notify =
-		container_of(swork, struct irq_affinity_notify, swork);
+		container_of(work, struct irq_affinity_notify, work);
 	_irq_affinity_notify(notify);
 }
 
@@ -446,8 +436,7 @@ irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify)
 		notify->irq = irq;
 		kref_init(&notify->kref);
 #ifdef CONFIG_PREEMPT_RT_BASE
-		INIT_SWORK(&notify->swork, irq_affinity_notify);
-		init_helper_thread();
+		kthread_init_work(&notify->work, irq_affinity_notify);
 #else
 		INIT_WORK(&notify->work, irq_affinity_notify);
 #endif
@@ -459,8 +448,9 @@ irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify)
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 
 	if (old_notify) {
-#ifndef CONFIG_PREEMPT_RT_BASE
-		/* Need to address this for PREEMPT_RT */
+#ifdef CONFIG_PREEMPT_RT_BASE
+		kthread_cancel_work_sync(&notify->work);
+#else
 		cancel_work_sync(&old_notify->work);
 #endif
 		kref_put(&old_notify->kref, old_notify->release);
diff --git a/kernel/kthread.c b/kernel/kthread.c
index fcb3a1a6e14bc64fec6c97132fcc5d125a4050f4..20d01a4bf16d02c7486ba4ef697ed967ab0e529e 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -21,6 +21,7 @@
 #include <linux/freezer.h>
 #include <linux/ptrace.h>
 #include <linux/uaccess.h>
+#include <linux/cgroup.h>
 #include <trace/events/sched.h>
 
 static DEFINE_SPINLOCK(kthread_create_lock);
@@ -1181,6 +1182,19 @@ void kthread_destroy_worker(struct kthread_worker *worker)
 }
 EXPORT_SYMBOL(kthread_destroy_worker);
 
+DEFINE_KTHREAD_WORKER(kthread_global_worker);
+EXPORT_SYMBOL(kthread_global_worker);
+
+__init void kthread_init_global_worker(void)
+{
+	kthread_global_worker.task = kthread_create(kthread_worker_fn,
+						    &kthread_global_worker,
+						    "kswork");
+	if (WARN_ON(IS_ERR(kthread_global_worker.task)))
+		return;
+	wake_up_process(kthread_global_worker.task);
+}
+
 #ifdef CONFIG_BLK_CGROUP
 /**
  * kthread_associate_blkcg - associate blkcg to current kthread
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 16d8dba23329aa6bea256ac41d59aef83ed4a7cb..ed75addd3ccda42c4eaabafa91c4187863ba9033 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -69,7 +69,9 @@ module_param(rcu_expedited, int, 0);
 extern int rcu_normal; /* from sysctl */
 module_param(rcu_normal, int, 0);
 static int rcu_normal_after_boot = IS_ENABLED(CONFIG_PREEMPT_RT_FULL);
+#ifndef CONFIG_PREEMPT_RT_FULL
 module_param(rcu_normal_after_boot, int, 0);
+#endif
 #endif /* #ifndef CONFIG_TINY_RCU */
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c
index 755a58084978198b7b2438b9fad59943447aeb13..49c14137988ea5947e22c1229d2512075f2f8efa 100644
--- a/kernel/sched/completion.c
+++ b/kernel/sched/completion.c
@@ -72,12 +72,12 @@ do_wait_for_common(struct completion *x,
 	if (!x->done) {
 		DECLARE_SWAITQUEUE(wait);
 
-		__prepare_to_swait(&x->wait, &wait);
 		do {
 			if (signal_pending_state(state, current)) {
 				timeout = -ERESTARTSYS;
 				break;
 			}
+			__prepare_to_swait(&x->wait, &wait);
 			__set_current_state(state);
 			raw_spin_unlock_irq(&x->wait.lock);
 			timeout = action(timeout);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 60de304a7b097fccdd00e512441fd4f0b489bcd5..e37d8d0911b6144f65c91012b4a08c1d980a59c4 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -330,7 +330,7 @@ static void hrtick_rq_init(struct rq *rq)
 	rq->hrtick_csd.info = rq;
 #endif
 
-	hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
 	rq->hrtick_timer.function = hrtick;
 }
 #else	/* CONFIG_SCHED_HRTICK */
@@ -569,14 +569,11 @@ void resched_cpu(int cpu)
  */
 int get_nohz_timer_target(void)
 {
-	int i, cpu;
+	int i, cpu = smp_processor_id();
 	struct sched_domain *sd;
 
-	preempt_disable_rt();
-	cpu = smp_processor_id();
-
 	if (!idle_cpu(cpu) && housekeeping_cpu(cpu, HK_FLAG_TIMER))
-		goto preempt_en_rt;
+		return cpu;
 
 	rcu_read_lock();
 	for_each_domain(cpu, sd) {
@@ -595,8 +592,6 @@ int get_nohz_timer_target(void)
 		cpu = housekeeping_any_cpu(HK_FLAG_TIMER);
 unlock:
 	rcu_read_unlock();
-preempt_en_rt:
-	preempt_enable_rt();
 	return cpu;
 }
 
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 4b13df38c069e646997b12763e3f3b72506298ab..974a8f9b615a3555fffe3e4d09922bdac7fcbc22 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1086,7 +1086,7 @@ void init_dl_task_timer(struct sched_dl_entity *dl_se)
 {
 	struct hrtimer *timer = &dl_se->dl_timer;
 
-	hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
 	timer->function = dl_task_timer;
 }
 
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index e9a609cdd19b683f7fdb498f50e5b47db0ab2ea2..f5f522d5151a64613c16c15ddbd8be30ba0563bf 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -45,8 +45,8 @@ void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime)
 
 	raw_spin_lock_init(&rt_b->rt_runtime_lock);
 
-	hrtimer_init(&rt_b->rt_period_timer,
-			CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	hrtimer_init(&rt_b->rt_period_timer, CLOCK_MONOTONIC,
+		     HRTIMER_MODE_REL_HARD);
 	rt_b->rt_period_timer.function = sched_rt_period_timer;
 }
 
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index f4255a65c44b2347bd4559137e53c2bf7636cd0c..61ab2c923579d30ad1fd0396774a373c99d799d7 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -436,7 +436,7 @@ int alarm_cancel(struct alarm *alarm)
 		int ret = alarm_try_to_cancel(alarm);
 		if (ret >= 0)
 			return ret;
-		cpu_relax();
+		hrtimer_grab_expiry_lock(&alarm->timer);
 	}
 }
 EXPORT_SYMBOL_GPL(alarm_cancel);
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 49feba6f076252c17badf34a43d664c4b3fdbe58..4534e7871c8c169017b5cd1c9a2168c371968191 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -730,6 +730,29 @@ static void hrtimer_switch_to_hres(void)
 	retrigger_next_event(NULL);
 }
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+
+static struct swork_event clock_set_delay_work;
+
+static void run_clock_set_delay(struct swork_event *event)
+{
+	clock_was_set();
+}
+
+void clock_was_set_delayed(void)
+{
+	swork_queue(&clock_set_delay_work);
+}
+
+static __init int create_clock_set_delay_thread(void)
+{
+	WARN_ON(swork_get());
+	INIT_SWORK(&clock_set_delay_work, run_clock_set_delay);
+	return 0;
+}
+early_initcall(create_clock_set_delay_thread);
+#else /* PREEMPT_RT_FULL */
+
 static void clock_was_set_work(struct work_struct *work)
 {
 	clock_was_set();
@@ -745,6 +768,7 @@ void clock_was_set_delayed(void)
 {
 	schedule_work(&hrtimer_work);
 }
+#endif
 
 #else
 
@@ -939,6 +963,16 @@ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval)
 }
 EXPORT_SYMBOL_GPL(hrtimer_forward);
 
+void hrtimer_grab_expiry_lock(const struct hrtimer *timer)
+{
+	struct hrtimer_clock_base *base = timer->base;
+
+	if (base && base->cpu_base) {
+		spin_lock(&base->cpu_base->softirq_expiry_lock);
+		spin_unlock(&base->cpu_base->softirq_expiry_lock);
+	}
+}
+
 /*
  * enqueue_hrtimer - internal function to (re)start a timer
  *
@@ -1108,7 +1142,9 @@ void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 	 * Check whether the HRTIMER_MODE_SOFT bit and hrtimer.is_soft
 	 * match.
 	 */
+#ifndef CONFIG_PREEMPT_RT_BASE
 	WARN_ON_ONCE(!(mode & HRTIMER_MODE_SOFT) ^ !timer->is_soft);
+#endif
 
 	base = lock_hrtimer_base(timer, &flags);
 
@@ -1171,7 +1207,7 @@ int hrtimer_cancel(struct hrtimer *timer)
 
 		if (ret >= 0)
 			return ret;
-		cpu_relax();
+		hrtimer_grab_expiry_lock(timer);
 	}
 }
 EXPORT_SYMBOL_GPL(hrtimer_cancel);
@@ -1268,10 +1304,17 @@ static inline int hrtimer_clockid_to_base(clockid_t clock_id)
 static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
 			   enum hrtimer_mode mode)
 {
-	bool softtimer = !!(mode & HRTIMER_MODE_SOFT);
-	int base = softtimer ? HRTIMER_MAX_CLOCK_BASES / 2 : 0;
+	bool softtimer;
+	int base;
 	struct hrtimer_cpu_base *cpu_base;
 
+	softtimer = !!(mode & HRTIMER_MODE_SOFT);
+#ifdef CONFIG_PREEMPT_RT_FULL
+	if (!softtimer && !(mode & HRTIMER_MODE_HARD))
+		softtimer = true;
+#endif
+	base = softtimer ? HRTIMER_MAX_CLOCK_BASES / 2 : 0;
+
 	memset(timer, 0, sizeof(struct hrtimer));
 
 	cpu_base = raw_cpu_ptr(&hrtimer_bases);
@@ -1468,6 +1511,7 @@ static __latent_entropy void hrtimer_run_softirq(struct softirq_action *h)
 	unsigned long flags;
 	ktime_t now;
 
+	spin_lock(&cpu_base->softirq_expiry_lock);
 	raw_spin_lock_irqsave(&cpu_base->lock, flags);
 
 	now = hrtimer_update_base(cpu_base);
@@ -1477,6 +1521,7 @@ static __latent_entropy void hrtimer_run_softirq(struct softirq_action *h)
 	hrtimer_update_softirq_timer(cpu_base, true);
 
 	raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
+	spin_unlock(&cpu_base->softirq_expiry_lock);
 }
 
 #ifdef CONFIG_HIGH_RES_TIMERS
@@ -1648,13 +1693,52 @@ static enum hrtimer_restart hrtimer_wakeup(struct hrtimer *timer)
 	return HRTIMER_NORESTART;
 }
 
-void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *task)
+static void __hrtimer_init_sleeper(struct hrtimer_sleeper *sl,
+				   clockid_t clock_id,
+				   enum hrtimer_mode mode,
+				   struct task_struct *task)
 {
+#ifdef CONFIG_PREEMPT_RT_FULL
+	if (!(mode & (HRTIMER_MODE_SOFT | HRTIMER_MODE_HARD))) {
+		if (task_is_realtime(current) || system_state != SYSTEM_RUNNING)
+			mode |= HRTIMER_MODE_HARD;
+		else
+			mode |= HRTIMER_MODE_SOFT;
+	}
+#endif
+	__hrtimer_init(&sl->timer, clock_id, mode);
 	sl->timer.function = hrtimer_wakeup;
 	sl->task = task;
 }
+
+/**
+ * hrtimer_init_sleeper - initialize sleeper to the given clock
+ * @sl:		sleeper to be initialized
+ * @clock_id:	the clock to be used
+ * @mode:	timer mode abs/rel
+ * @task:	the task to wake up
+ */
+void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, clockid_t clock_id,
+			  enum hrtimer_mode mode, struct task_struct *task)
+{
+	debug_init(&sl->timer, clock_id, mode);
+	__hrtimer_init_sleeper(sl, clock_id, mode, task);
+
+}
 EXPORT_SYMBOL_GPL(hrtimer_init_sleeper);
 
+#ifdef CONFIG_DEBUG_OBJECTS_TIMERS
+void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl,
+				   clockid_t clock_id,
+				   enum hrtimer_mode mode,
+				   struct task_struct *task)
+{
+	debug_object_init_on_stack(&sl->timer, &hrtimer_debug_descr);
+	__hrtimer_init_sleeper(sl, clock_id, mode, task);
+}
+EXPORT_SYMBOL_GPL(hrtimer_init_sleeper_on_stack);
+#endif
+
 int nanosleep_copyout(struct restart_block *restart, struct timespec64 *ts)
 {
 	switch(restart->nanosleep.type) {
@@ -1678,8 +1762,6 @@ static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mod
 {
 	struct restart_block *restart;
 
-	hrtimer_init_sleeper(t, current);
-
 	do {
 		set_current_state(TASK_INTERRUPTIBLE);
 		hrtimer_start_expires(&t->timer, mode);
@@ -1687,12 +1769,12 @@ static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mod
 		if (likely(t->task))
 			freezable_schedule();
 
+		__set_current_state(TASK_RUNNING);
 		hrtimer_cancel(&t->timer);
 		mode = HRTIMER_MODE_ABS;
 
 	} while (t->task && !signal_pending(current));
 
-	__set_current_state(TASK_RUNNING);
 
 	if (!t->task)
 		return 0;
@@ -1716,10 +1798,9 @@ static long __sched hrtimer_nanosleep_restart(struct restart_block *restart)
 	struct hrtimer_sleeper t;
 	int ret;
 
-	hrtimer_init_on_stack(&t.timer, restart->nanosleep.clockid,
-				HRTIMER_MODE_ABS);
+	hrtimer_init_sleeper_on_stack(&t, restart->nanosleep.clockid,
+				      HRTIMER_MODE_ABS, current);
 	hrtimer_set_expires_tv64(&t.timer, restart->nanosleep.expires);
-
 	ret = do_nanosleep(&t, HRTIMER_MODE_ABS);
 	destroy_hrtimer_on_stack(&t.timer);
 	return ret;
@@ -1737,7 +1818,7 @@ long hrtimer_nanosleep(const struct timespec64 *rqtp,
 	if (dl_task(current) || rt_task(current))
 		slack = 0;
 
-	hrtimer_init_on_stack(&t.timer, clockid, mode);
+	hrtimer_init_sleeper_on_stack(&t, clockid, mode, current);
 	hrtimer_set_expires_range_ns(&t.timer, timespec64_to_ktime(*rqtp), slack);
 	ret = do_nanosleep(&t, mode);
 	if (ret != -ERESTART_RESTARTBLOCK)
@@ -1850,6 +1931,7 @@ int hrtimers_prepare_cpu(unsigned int cpu)
 	cpu_base->softirq_next_timer = NULL;
 	cpu_base->expires_next = KTIME_MAX;
 	cpu_base->softirq_expires_next = KTIME_MAX;
+	spin_lock_init(&cpu_base->softirq_expiry_lock);
 	return 0;
 }
 
@@ -1968,11 +2050,9 @@ schedule_hrtimeout_range_clock(ktime_t *expires, u64 delta,
 		return -EINTR;
 	}
 
-	hrtimer_init_on_stack(&t.timer, clock_id, mode);
+	hrtimer_init_sleeper_on_stack(&t, clock_id, mode, current);
 	hrtimer_set_expires_range_ns(&t.timer, *expires, delta);
 
-	hrtimer_init_sleeper(&t, current);
-
 	hrtimer_start_expires(&t.timer, mode);
 
 	if (likely(t.task))
diff --git a/kernel/time/itimer.c b/kernel/time/itimer.c
index 9a65713c83093f343466bd4ed0c5435d4077309c..a5ff222df4c706d813b90c794b2bb6e9d649a76c 100644
--- a/kernel/time/itimer.c
+++ b/kernel/time/itimer.c
@@ -215,6 +215,7 @@ int do_setitimer(int which, struct itimerval *value, struct itimerval *ovalue)
 		/* We are sharing ->siglock with it_real_fn() */
 		if (hrtimer_try_to_cancel(timer) < 0) {
 			spin_unlock_irq(&tsk->sighand->siglock);
+			hrtimer_grab_expiry_lock(timer);
 			goto again;
 		}
 		expires = timeval_to_ktime(value->it_value);
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index d62d7ae5201c5c5a525c48aa2a3197d3e4126041..765e700962ab6582756f4a208637c144068eb9cb 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -3,8 +3,10 @@
  * Implement CPU time clocks for the POSIX clock interface.
  */
 
+#include <uapi/linux/sched/types.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/cputime.h>
+#include <linux/sched/rt.h>
 #include <linux/posix-timers.h>
 #include <linux/errno.h>
 #include <linux/math64.h>
@@ -15,6 +17,7 @@
 #include <linux/workqueue.h>
 #include <linux/compat.h>
 #include <linux/sched/deadline.h>
+#include <linux/smpboot.h>
 
 #include "posix-timers.h"
 
@@ -789,6 +792,7 @@ check_timers_list(struct list_head *timers,
 			return t->expires;
 
 		t->firing = 1;
+		t->firing_cpu = smp_processor_id();
 		list_move_tail(&t->entry, firing);
 	}
 
@@ -1135,18 +1139,31 @@ static inline int fastpath_timer_check(struct task_struct *tsk)
 	return 0;
 }
 
+static DEFINE_PER_CPU(spinlock_t, cpu_timer_expiry_lock) = __SPIN_LOCK_UNLOCKED(cpu_timer_expiry_lock);
+
+void cpu_timers_grab_expiry_lock(struct k_itimer *timer)
+{
+	int cpu = timer->it.cpu.firing_cpu;
+
+	if (cpu >= 0) {
+		spinlock_t *expiry_lock = per_cpu_ptr(&cpu_timer_expiry_lock, cpu);
+
+		spin_lock_irq(expiry_lock);
+		spin_unlock_irq(expiry_lock);
+	}
+}
+
 /*
  * This is called from the timer interrupt handler.  The irq handler has
  * already updated our counts.  We need to check if any timers fire now.
  * Interrupts are disabled.
  */
-void run_posix_cpu_timers(struct task_struct *tsk)
+static void __run_posix_cpu_timers(struct task_struct *tsk)
 {
 	LIST_HEAD(firing);
 	struct k_itimer *timer, *next;
 	unsigned long flags;
-
-	lockdep_assert_irqs_disabled();
+	spinlock_t *expiry_lock;
 
 	/*
 	 * The fast path checks that there are no expired thread or thread
@@ -1155,6 +1172,9 @@ void run_posix_cpu_timers(struct task_struct *tsk)
 	if (!fastpath_timer_check(tsk))
 		return;
 
+	expiry_lock = this_cpu_ptr(&cpu_timer_expiry_lock);
+	spin_lock(expiry_lock);
+
 	if (!lock_task_sighand(tsk, &flags))
 		return;
 	/*
@@ -1189,6 +1209,7 @@ void run_posix_cpu_timers(struct task_struct *tsk)
 		list_del_init(&timer->it.cpu.entry);
 		cpu_firing = timer->it.cpu.firing;
 		timer->it.cpu.firing = 0;
+		timer->it.cpu.firing_cpu = -1;
 		/*
 		 * The firing flag is -1 if we collided with a reset
 		 * of the timer, which already reported this
@@ -1198,8 +1219,156 @@ void run_posix_cpu_timers(struct task_struct *tsk)
 			cpu_timer_fire(timer);
 		spin_unlock(&timer->it_lock);
 	}
+	spin_unlock(expiry_lock);
+}
+
+#ifdef CONFIG_PREEMPT_RT_BASE
+#include <linux/kthread.h>
+#include <linux/cpu.h>
+DEFINE_PER_CPU(struct task_struct *, posix_timer_task);
+DEFINE_PER_CPU(struct task_struct *, posix_timer_tasklist);
+DEFINE_PER_CPU(bool, posix_timer_th_active);
+
+static void posix_cpu_kthread_fn(unsigned int cpu)
+{
+	struct task_struct *tsk = NULL;
+	struct task_struct *next = NULL;
+
+	BUG_ON(per_cpu(posix_timer_task, cpu) != current);
+
+	/* grab task list */
+	raw_local_irq_disable();
+	tsk = per_cpu(posix_timer_tasklist, cpu);
+	per_cpu(posix_timer_tasklist, cpu) = NULL;
+	raw_local_irq_enable();
+
+	/* its possible the list is empty, just return */
+	if (!tsk)
+		return;
+
+	/* Process task list */
+	while (1) {
+		/* save next */
+		next = tsk->posix_timer_list;
+
+		/* run the task timers, clear its ptr and
+		 * unreference it
+		 */
+		__run_posix_cpu_timers(tsk);
+		tsk->posix_timer_list = NULL;
+		put_task_struct(tsk);
+
+		/* check if this is the last on the list */
+		if (next == tsk)
+			break;
+		tsk = next;
+	}
+}
+
+static inline int __fastpath_timer_check(struct task_struct *tsk)
+{
+	/* tsk == current, ensure it is safe to use ->signal/sighand */
+	if (unlikely(tsk->exit_state))
+		return 0;
+
+	if (!task_cputime_zero(&tsk->cputime_expires))
+			return 1;
+
+	if (!task_cputime_zero(&tsk->signal->cputime_expires))
+			return 1;
+
+	return 0;
+}
+
+void run_posix_cpu_timers(struct task_struct *tsk)
+{
+	unsigned int cpu = smp_processor_id();
+	struct task_struct *tasklist;
+
+	BUG_ON(!irqs_disabled());
+
+	if (per_cpu(posix_timer_th_active, cpu) != true)
+		return;
+
+	/* get per-cpu references */
+	tasklist = per_cpu(posix_timer_tasklist, cpu);
+
+	/* check to see if we're already queued */
+	if (!tsk->posix_timer_list && __fastpath_timer_check(tsk)) {
+		get_task_struct(tsk);
+		if (tasklist) {
+			tsk->posix_timer_list = tasklist;
+		} else {
+			/*
+			 * The list is terminated by a self-pointing
+			 * task_struct
+			 */
+			tsk->posix_timer_list = tsk;
+		}
+		per_cpu(posix_timer_tasklist, cpu) = tsk;
+
+		wake_up_process(per_cpu(posix_timer_task, cpu));
+	}
+}
+
+static int posix_cpu_kthread_should_run(unsigned int cpu)
+{
+	return __this_cpu_read(posix_timer_tasklist) != NULL;
+}
+
+static void posix_cpu_kthread_park(unsigned int cpu)
+{
+	this_cpu_write(posix_timer_th_active, false);
+}
+
+static void posix_cpu_kthread_unpark(unsigned int cpu)
+{
+	this_cpu_write(posix_timer_th_active, true);
 }
 
+static void posix_cpu_kthread_setup(unsigned int cpu)
+{
+	struct sched_param sp;
+
+	sp.sched_priority = MAX_RT_PRIO - 1;
+	sched_setscheduler_nocheck(current, SCHED_FIFO, &sp);
+	posix_cpu_kthread_unpark(cpu);
+}
+
+static struct smp_hotplug_thread posix_cpu_thread = {
+	.store			= &posix_timer_task,
+	.thread_should_run	= posix_cpu_kthread_should_run,
+	.thread_fn		= posix_cpu_kthread_fn,
+	.thread_comm		= "posixcputmr/%u",
+	.setup			= posix_cpu_kthread_setup,
+	.park			= posix_cpu_kthread_park,
+	.unpark			= posix_cpu_kthread_unpark,
+};
+
+static int __init posix_cpu_thread_init(void)
+{
+	/* Start one for boot CPU. */
+	unsigned long cpu;
+	int ret;
+
+	/* init the per-cpu posix_timer_tasklets */
+	for_each_possible_cpu(cpu)
+		per_cpu(posix_timer_tasklist, cpu) = NULL;
+
+	ret = smpboot_register_percpu_thread(&posix_cpu_thread);
+	WARN_ON(ret);
+
+	return 0;
+}
+early_initcall(posix_cpu_thread_init);
+#else /* CONFIG_PREEMPT_RT_BASE */
+void run_posix_cpu_timers(struct task_struct *tsk)
+{
+	lockdep_assert_irqs_disabled();
+	__run_posix_cpu_timers(tsk);
+}
+#endif /* CONFIG_PREEMPT_RT_BASE */
+
 /*
  * Set one of the process-wide special case CPU timers or RLIMIT_CPU.
  * The tsk->sighand->siglock must be held by the caller.
@@ -1318,6 +1487,8 @@ static int do_cpu_nanosleep(const clockid_t which_clock, int flags,
 		spin_unlock_irq(&timer.it_lock);
 
 		while (error == TIMER_RETRY) {
+
+			cpu_timers_grab_expiry_lock(&timer);
 			/*
 			 * We need to handle case when timer was or is in the
 			 * middle of firing. In other cases we already freed
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index 5a01c4fdbfef40337a5a06b9944391820df8d5cd..c7e97d421590e09301226321a135623980d47f44 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -463,7 +463,7 @@ static struct k_itimer * alloc_posix_timer(void)
 
 static void k_itimer_rcu_free(struct rcu_head *head)
 {
-	struct k_itimer *tmr = container_of(head, struct k_itimer, it.rcu);
+	struct k_itimer *tmr = container_of(head, struct k_itimer, rcu);
 
 	kmem_cache_free(posix_timers_cache, tmr);
 }
@@ -480,7 +480,7 @@ static void release_posix_timer(struct k_itimer *tmr, int it_id_set)
 	}
 	put_pid(tmr->it_pid);
 	sigqueue_free(tmr->sigq);
-	call_rcu(&tmr->it.rcu, k_itimer_rcu_free);
+	call_rcu(&tmr->rcu, k_itimer_rcu_free);
 }
 
 static int common_timer_create(struct k_itimer *new_timer)
@@ -826,6 +826,17 @@ static int common_hrtimer_try_to_cancel(struct k_itimer *timr)
 	return hrtimer_try_to_cancel(&timr->it.real.timer);
 }
 
+static void timer_wait_for_callback(const struct k_clock *kc, struct k_itimer *timer)
+{
+	if (kc->timer_arm == common_hrtimer_arm)
+		hrtimer_grab_expiry_lock(&timer->it.real.timer);
+	else if (kc == &alarm_clock)
+		hrtimer_grab_expiry_lock(&timer->it.alarm.alarmtimer.timer);
+	else
+		/* posix-cpu-timers */
+		cpu_timers_grab_expiry_lock(timer);
+}
+
 /* Set a POSIX.1b interval timer. */
 int common_timer_set(struct k_itimer *timr, int flags,
 		     struct itimerspec64 *new_setting,
@@ -891,11 +902,15 @@ static int do_timer_settime(timer_t timer_id, int flags,
 	else
 		error = kc->timer_set(timr, flags, new_spec64, old_spec64);
 
-	unlock_timer(timr, flag);
 	if (error == TIMER_RETRY) {
+		rcu_read_lock();
+		unlock_timer(timr, flag);
+		timer_wait_for_callback(kc, timr);
+		rcu_read_unlock();
 		old_spec64 = NULL;	// We already got the old time...
 		goto retry;
 	}
+	unlock_timer(timr, flag);
 
 	return error;
 }
@@ -957,13 +972,21 @@ int common_timer_del(struct k_itimer *timer)
 	return 0;
 }
 
-static inline int timer_delete_hook(struct k_itimer *timer)
+static int timer_delete_hook(struct k_itimer *timer)
 {
 	const struct k_clock *kc = timer->kclock;
+	int ret;
 
 	if (WARN_ON_ONCE(!kc || !kc->timer_del))
 		return -EINVAL;
-	return kc->timer_del(timer);
+	ret = kc->timer_del(timer);
+	if (ret == TIMER_RETRY) {
+		rcu_read_lock();
+		spin_unlock_irq(&timer->it_lock);
+		timer_wait_for_callback(kc, timer);
+		rcu_read_unlock();
+	}
+	return ret;
 }
 
 /* Delete a POSIX.1b interval timer. */
@@ -977,10 +1000,8 @@ SYSCALL_DEFINE1(timer_delete, timer_t, timer_id)
 	if (!timer)
 		return -EINVAL;
 
-	if (timer_delete_hook(timer) == TIMER_RETRY) {
-		unlock_timer(timer, flags);
+	if (timer_delete_hook(timer) == TIMER_RETRY)
 		goto retry_delete;
-	}
 
 	spin_lock(&current->sighand->siglock);
 	list_del(&timer->list);
@@ -1006,10 +1027,9 @@ static void itimer_delete(struct k_itimer *timer)
 retry_delete:
 	spin_lock_irqsave(&timer->it_lock, flags);
 
-	if (timer_delete_hook(timer) == TIMER_RETRY) {
-		unlock_timer(timer, flags);
+	if (timer_delete_hook(timer) == TIMER_RETRY)
 		goto retry_delete;
-	}
+
 	list_del(&timer->list);
 	/*
 	 * This keeps any tasks waiting on the spin lock from thinking
diff --git a/kernel/time/posix-timers.h b/kernel/time/posix-timers.h
index ddb21145211a0280f9b20667a33b9503ce62d776..725bd230a8db425ad209eef2be931c0637cb5e9c 100644
--- a/kernel/time/posix-timers.h
+++ b/kernel/time/posix-timers.h
@@ -32,6 +32,8 @@ extern const struct k_clock clock_process;
 extern const struct k_clock clock_thread;
 extern const struct k_clock alarm_clock;
 
+extern void cpu_timers_grab_expiry_lock(struct k_itimer *timer);
+
 int posix_timer_event(struct k_itimer *timr, int si_private);
 
 void common_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting);
diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c
index a836efd34589595f12087f11c9798e9ebb23293b..c50e8f3262deae65aeb03da6a50a2aadf505d833 100644
--- a/kernel/time/tick-broadcast-hrtimer.c
+++ b/kernel/time/tick-broadcast-hrtimer.c
@@ -107,7 +107,7 @@ static enum hrtimer_restart bc_handler(struct hrtimer *t)
 
 void tick_setup_hrtimer_broadcast(void)
 {
-	hrtimer_init(&bctimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+	hrtimer_init(&bctimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
 	bctimer.function = bc_handler;
 	clockevents_register_device(&ce_broadcast_hrtimer);
 }
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 2778d02bb71caa706a9815ec9607bc45d9cccbfb..0e9e5ebdf8ff1e8bdb2754f9b15d3e697fbc8150 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -1302,7 +1302,7 @@ void tick_setup_sched_timer(void)
 	/*
 	 * Emulate tick processing via per-CPU hrtimers:
 	 */
-	hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+	hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
 	ts->sched_timer.function = tick_sched_timer;
 
 	/* Get the next period (per-CPU) */
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index bdbfd52b1cfda1937126805ed82e328b41293400..716364bbe5becd4eceaca692d5715ccaeb68351e 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -45,7 +45,6 @@
 #include <linux/slab.h>
 #include <linux/compat.h>
 #include <linux/random.h>
-#include <linux/swait.h>
 
 #include <linux/uaccess.h>
 #include <asm/unistd.h>
@@ -199,9 +198,7 @@ EXPORT_SYMBOL(jiffies_64);
 struct timer_base {
 	raw_spinlock_t		lock;
 	struct timer_list	*running_timer;
-#ifdef CONFIG_PREEMPT_RT_FULL
-	struct swait_queue_head	wait_for_running_timer;
-#endif
+	spinlock_t		expiry_lock;
 	unsigned long		clk;
 	unsigned long		next_expiry;
 	unsigned int		cpu;
@@ -1201,33 +1198,6 @@ void add_timer_on(struct timer_list *timer, int cpu)
 }
 EXPORT_SYMBOL_GPL(add_timer_on);
 
-#ifdef CONFIG_PREEMPT_RT_FULL
-/*
- * Wait for a running timer
- */
-static void wait_for_running_timer(struct timer_list *timer)
-{
-	struct timer_base *base;
-	u32 tf = timer->flags;
-
-	if (tf & TIMER_MIGRATING)
-		return;
-
-	base = get_timer_base(tf);
-	swait_event_exclusive(base->wait_for_running_timer,
-			      base->running_timer != timer);
-}
-
-# define wakeup_timer_waiters(b)	swake_up_all(&(b)->wait_for_running_timer)
-#else
-static inline void wait_for_running_timer(struct timer_list *timer)
-{
-	cpu_relax();
-}
-
-# define wakeup_timer_waiters(b)	do { } while (0)
-#endif
-
 /**
  * del_timer - deactivate a timer.
  * @timer: the timer to be deactivated
@@ -1257,14 +1227,8 @@ int del_timer(struct timer_list *timer)
 }
 EXPORT_SYMBOL(del_timer);
 
-/**
- * try_to_del_timer_sync - Try to deactivate a timer
- * @timer: timer to delete
- *
- * This function tries to deactivate a timer. Upon successful (ret >= 0)
- * exit the timer is not queued and the handler is not running on any CPU.
- */
-int try_to_del_timer_sync(struct timer_list *timer)
+static int __try_to_del_timer_sync(struct timer_list *timer,
+				   struct timer_base **basep)
 {
 	struct timer_base *base;
 	unsigned long flags;
@@ -1272,7 +1236,7 @@ int try_to_del_timer_sync(struct timer_list *timer)
 
 	debug_assert_init(timer);
 
-	base = lock_timer_base(timer, &flags);
+	*basep = base = lock_timer_base(timer, &flags);
 
 	if (base->running_timer != timer)
 		ret = detach_if_pending(timer, base, true);
@@ -1281,9 +1245,42 @@ int try_to_del_timer_sync(struct timer_list *timer)
 
 	return ret;
 }
+
+/**
+ * try_to_del_timer_sync - Try to deactivate a timer
+ * @timer: timer to delete
+ *
+ * This function tries to deactivate a timer. Upon successful (ret >= 0)
+ * exit the timer is not queued and the handler is not running on any CPU.
+ */
+int try_to_del_timer_sync(struct timer_list *timer)
+{
+	struct timer_base *base;
+
+	return __try_to_del_timer_sync(timer, &base);
+}
 EXPORT_SYMBOL(try_to_del_timer_sync);
 
 #if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL)
+static int __del_timer_sync(struct timer_list *timer)
+{
+	struct timer_base *base;
+	int ret;
+
+	for (;;) {
+		ret = __try_to_del_timer_sync(timer, &base);
+		if (ret >= 0)
+			return ret;
+
+		/*
+		 * When accessing the lock, timers of base are no longer expired
+		 * and so timer is no longer running.
+		 */
+		spin_lock(&base->expiry_lock);
+		spin_unlock(&base->expiry_lock);
+	}
+}
+
 /**
  * del_timer_sync - deactivate a timer and wait for the handler to finish.
  * @timer: the timer to be deactivated
@@ -1339,12 +1336,8 @@ int del_timer_sync(struct timer_list *timer)
 	 * could lead to deadlock.
 	 */
 	WARN_ON(in_irq() && !(timer->flags & TIMER_IRQSAFE));
-	for (;;) {
-		int ret = try_to_del_timer_sync(timer);
-		if (ret >= 0)
-			return ret;
-		wait_for_running_timer(timer);
-	}
+
+	return __del_timer_sync(timer);
 }
 EXPORT_SYMBOL(del_timer_sync);
 #endif
@@ -1409,11 +1402,15 @@ static void expire_timers(struct timer_base *base, struct hlist_head *head)
 			raw_spin_unlock(&base->lock);
 			call_timer_fn(timer, fn);
 			base->running_timer = NULL;
+			spin_unlock(&base->expiry_lock);
+			spin_lock(&base->expiry_lock);
 			raw_spin_lock(&base->lock);
 		} else {
 			raw_spin_unlock_irq(&base->lock);
 			call_timer_fn(timer, fn);
 			base->running_timer = NULL;
+			spin_unlock(&base->expiry_lock);
+			spin_lock(&base->expiry_lock);
 			raw_spin_lock_irq(&base->lock);
 		}
 	}
@@ -1717,6 +1714,7 @@ static inline void __run_timers(struct timer_base *base)
 	if (!time_after_eq(jiffies, base->clk))
 		return;
 
+	spin_lock(&base->expiry_lock);
 	raw_spin_lock_irq(&base->lock);
 
 	/*
@@ -1744,7 +1742,7 @@ static inline void __run_timers(struct timer_base *base)
 			expire_timers(base, heads + levels);
 	}
 	raw_spin_unlock_irq(&base->lock);
-	wakeup_timer_waiters(base);
+	spin_unlock(&base->expiry_lock);
 }
 
 /*
@@ -1991,9 +1989,7 @@ static void __init init_timer_cpu(int cpu)
 		base->cpu = cpu;
 		raw_spin_lock_init(&base->lock);
 		base->clk = jiffies;
-#ifdef CONFIG_PREEMPT_RT_FULL
-		init_swait_queue_head(&base->wait_for_running_timer);
-#endif
+		spin_lock_init(&base->expiry_lock);
 	}
 }
 
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 72f18b6822245b1b19ac548f848f8e1af5bc287a..1c6c542e5f36b532952ae976d01c807209766d6b 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -558,7 +558,7 @@ static void watchdog_enable(unsigned int cpu)
 	 * Start the timer first to prevent the NMI watchdog triggering
 	 * before the timer has a chance to fire.
 	 */
-	hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
 	hrtimer->function = watchdog_timer_fn;
 	hrtimer_start(hrtimer, ns_to_ktime(sample_period),
 		      HRTIMER_MODE_REL_PINNED);
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 092fa3d75b32a8cef12ee6112343cd44f098618a..9d472d626aaac643141341052758ab5b847e5b6e 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -2160,7 +2160,8 @@ static void spin(struct pktgen_dev *pkt_dev, ktime_t spin_until)
 	s64 remaining;
 	struct hrtimer_sleeper t;
 
-	hrtimer_init_on_stack(&t.timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+	hrtimer_init_sleeper_on_stack(&t, CLOCK_MONOTONIC, HRTIMER_MODE_ABS,
+				      current);
 	hrtimer_set_expires(&t.timer, spin_until);
 
 	remaining = ktime_to_ns(hrtimer_expires_remaining(&t.timer));
@@ -2175,7 +2176,6 @@ static void spin(struct pktgen_dev *pkt_dev, ktime_t spin_until)
 		} while (ktime_compare(end_time, spin_until) < 0);
 	} else {
 		/* see do_nanosleep */
-		hrtimer_init_sleeper(&t, current);
 		do {
 			set_current_state(TASK_INTERRUPTIBLE);
 			hrtimer_start_expires(&t.timer, HRTIMER_MODE_ABS);