Merge tag 'timers-core-2021-08-30' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull timer updates from Thomas Gleixner:
 "Updates for timekeeping, timers and related drivers:

  Core code:

   - Cure a couple of correctness issues in the posix CPU timer code to
     prevent that the tick dependency for NOHZ full is kept alive for no
     reason.

   - Avoid expensive double reprogramming of the clockevent device in
     hrtimer_start_range_ns().

   - Avoid pointless SMP function calls when the clock was set to avoid
     disturbing CPUs which do not have any affected timers queued.

   - Make the clocksource watchdog test work correctly when CONFIG_HZ is
     less than 100.

  Drivers:

   - Prefer the ARM architected timer over the Exynos timer which is way
     more expensive to access.

   - Add device tree bindings for new Ingenic SoCs

   - The usual improvements and cleanups all over the place"

* tag 'timers-core-2021-08-30' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (29 commits)
  clocksource: Make clocksource watchdog test safe for slow-HZ systems
  dt-bindings: timer: Add ABIs for new Ingenic SoCs
  clocksource/drivers/fttmr010: Pass around less pointers
  clocksource/drivers/mediatek: Optimize systimer irq clear flow on shutdown
  clocksource/drivers/ingenic: Use bitfield macro helpers
  clocksource/drivers/sh_cmt: Fix wrong setting if don't request IRQ for clock source channel
  dt-bindings: timer: convert rockchip,rk-timer.txt to YAML
  clocksource/drivers/exynos_mct: Mark MCT device as CLOCK_EVT_FEAT_PERCPU
  clocksource/drivers/exynos_mct: Prioritise Arm arch timer on arm64
  hrtimer: Unbreak hrtimer_force_reprogram()
  hrtimer: Use raw_cpu_ptr() in clock_was_set()
  hrtimer: Avoid more SMP function calls in clock_was_set()
  hrtimer: Avoid unnecessary SMP function calls in clock_was_set()
  hrtimer: Add bases argument to clock_was_set()
  time/timekeeping: Avoid invoking clock_was_set() twice
  timekeeping: Distangle resume and clock-was-set events
  timerfd: Provide timerfd_resume()
  hrtimer: Force clock_was_set() handling for the HIGHRES=n, NOHZ=y case
  hrtimer: Ensure timerfd notification for HIGHRES=n
  hrtimer: Consolidate reprogramming code
  ...

22 files changed, 574 insertions, 230 deletions

diff --git a/Documentation/devicetree/bindings/timer/rockchip,rk-timer.txt b/Documentation/devicetree/bindings/timer/rockchip,rk-timer.txt
deleted file mode 100644
index d65fdce7c7f0..000000000000
--- a/Documentation/devicetree/bindings/timer/rockchip,rk-timer.txt
+++ /dev/null
@@ -1,27 +0,0 @@
-Rockchip rk timer
-
-Required properties:
-- compatible: should be:
-  "rockchip,rv1108-timer", "rockchip,rk3288-timer": for Rockchip RV1108
-  "rockchip,rk3036-timer", "rockchip,rk3288-timer": for Rockchip RK3036
-  "rockchip,rk3066-timer", "rockchip,rk3288-timer": for Rockchip RK3066
-  "rockchip,rk3188-timer", "rockchip,rk3288-timer": for Rockchip RK3188
-  "rockchip,rk3228-timer", "rockchip,rk3288-timer": for Rockchip RK3228
-  "rockchip,rk3229-timer", "rockchip,rk3288-timer": for Rockchip RK3229
-  "rockchip,rk3288-timer": for Rockchip RK3288
-  "rockchip,rk3368-timer", "rockchip,rk3288-timer": for Rockchip RK3368
-  "rockchip,rk3399-timer": for Rockchip RK3399
-- reg: base address of the timer register starting with TIMERS CONTROL register
-- interrupts: should contain the interrupts for Timer0
-- clocks : must contain an entry for each entry in clock-names
-- clock-names : must include the following entries:
-  "timer", "pclk"
-
-Example:
-	timer: timer@ff810000 {
-		compatible = "rockchip,rk3288-timer";
-		reg = <0xff810000 0x20>;
-		interrupts = <GIC_SPI 72 IRQ_TYPE_LEVEL_HIGH>;
-		clocks = <&xin24m>, <&cru PCLK_TIMER>;
-		clock-names = "timer", "pclk";
-	};
diff --git a/Documentation/devicetree/bindings/timer/rockchip,rk-timer.yaml b/Documentation/devicetree/bindings/timer/rockchip,rk-timer.yaml
new file mode 100644
index 000000000000..e26ecb5893ae
--- /dev/null
+++ b/Documentation/devicetree/bindings/timer/rockchip,rk-timer.yaml
@@ -0,0 +1,64 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/timer/rockchip,rk-timer.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Rockchip Timer Device Tree Bindings
+
+maintainers:
+  - Daniel Lezcano <daniel.lezcano@linaro.org>
+
+properties:
+  compatible:
+    oneOf:
+      - const: rockchip,rk3288-timer
+      - const: rockchip,rk3399-timer
+      - items:
+          - enum:
+              - rockchip,rv1108-timer
+              - rockchip,rk3036-timer
+              - rockchip,rk3066-timer
+              - rockchip,rk3188-timer
+              - rockchip,rk3228-timer
+              - rockchip,rk3229-timer
+              - rockchip,rk3288-timer
+              - rockchip,rk3368-timer
+              - rockchip,px30-timer
+          - const: rockchip,rk3288-timer
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    minItems: 2
+    maxItems: 2
+
+  clock-names:
+    items:
+      - const: pclk
+      - const: timer
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - clock-names
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/clock/rk3288-cru.h>
+
+    timer: timer@ff810000 {
+        compatible = "rockchip,rk3288-timer";
+        reg = <0xff810000 0x20>;
+        interrupts = <GIC_SPI 72 IRQ_TYPE_LEVEL_HIGH>;
+        clocks = <&cru PCLK_TIMER>, <&xin24m>;
+        clock-names = "pclk", "timer";
+    };
diff --git a/drivers/clocksource/exynos_mct.c b/drivers/clocksource/exynos_mct.c
index fabad79baafc..5e3e96d3d1b9 100644
--- a/drivers/clocksource/exynos_mct.c
+++ b/drivers/clocksource/exynos_mct.c
@@ -51,6 +51,15 @@
 
 #define TICK_BASE_CNT	1
 
+#ifdef CONFIG_ARM
+/* Use values higher than ARM arch timer. See 6282edb72bed. */
+#define MCT_CLKSOURCE_RATING		450
+#define MCT_CLKEVENTS_RATING		500
+#else
+#define MCT_CLKSOURCE_RATING		350
+#define MCT_CLKEVENTS_RATING		350
+#endif
+
 enum {
 	MCT_INT_SPI,
 	MCT_INT_PPI
@@ -206,7 +215,7 @@ static void exynos4_frc_resume(struct clocksource *cs)
 
 static struct clocksource mct_frc = {
 	.name		= "mct-frc",
-	.rating		= 450,	/* use value higher than ARM arch timer */
+	.rating		= MCT_CLKSOURCE_RATING,
 	.read		= exynos4_frc_read,
 	.mask		= CLOCKSOURCE_MASK(32),
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
@@ -456,8 +465,9 @@ static int exynos4_mct_starting_cpu(unsigned int cpu)
 	evt->set_state_oneshot = set_state_shutdown;
 	evt->set_state_oneshot_stopped = set_state_shutdown;
 	evt->tick_resume = set_state_shutdown;
-	evt->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
-	evt->rating = 500;	/* use value higher than ARM arch timer */
+	evt->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT |
+			CLOCK_EVT_FEAT_PERCPU;
+	evt->rating = MCT_CLKEVENTS_RATING,
 
 	exynos4_mct_write(TICK_BASE_CNT, mevt->base + MCT_L_TCNTB_OFFSET);
 
diff --git a/drivers/clocksource/ingenic-sysost.c b/drivers/clocksource/ingenic-sysost.c
index a129840f14f9..cb6fc2f152d4 100644
--- a/drivers/clocksource/ingenic-sysost.c
+++ b/drivers/clocksource/ingenic-sysost.c
@@ -4,6 +4,7 @@
  * Copyright (c) 2020 周琰杰 (Zhou Yanjie) <zhouyanjie@wanyeetech.com>
  */
 
+#include <linux/bitfield.h>
 #include <linux/bitops.h>
 #include <linux/clk.h>
 #include <linux/clk-provider.h>
@@ -34,8 +35,6 @@
 /* bits within the OSTCCR register */
 #define OSTCCR_PRESCALE1_MASK	0x3
 #define OSTCCR_PRESCALE2_MASK	0xc
-#define OSTCCR_PRESCALE1_LSB	0
-#define OSTCCR_PRESCALE2_LSB	2
 
 /* bits within the OSTCR register */
 #define OSTCR_OST1CLR			BIT(0)
@@ -98,7 +97,7 @@ static unsigned long ingenic_ost_percpu_timer_recalc_rate(struct clk_hw *hw,
 
 	prescale = readl(ost_clk->ost->base + info->ostccr_reg);
 
-	prescale = (prescale & OSTCCR_PRESCALE1_MASK) >> OSTCCR_PRESCALE1_LSB;
+	prescale = FIELD_GET(OSTCCR_PRESCALE1_MASK, prescale);
 
 	return parent_rate >> (prescale * 2);
 }
@@ -112,7 +111,7 @@ static unsigned long ingenic_ost_global_timer_recalc_rate(struct clk_hw *hw,
 
 	prescale = readl(ost_clk->ost->base + info->ostccr_reg);
 
-	prescale = (prescale & OSTCCR_PRESCALE2_MASK) >> OSTCCR_PRESCALE2_LSB;
+	prescale = FIELD_GET(OSTCCR_PRESCALE2_MASK, prescale);
 
 	return parent_rate >> (prescale * 2);
 }
@@ -151,7 +150,8 @@ static int ingenic_ost_percpu_timer_set_rate(struct clk_hw *hw, unsigned long re
 	int val;
 
 	val = readl(ost_clk->ost->base + info->ostccr_reg);
-	val = (val & ~OSTCCR_PRESCALE1_MASK) | (prescale << OSTCCR_PRESCALE1_LSB);
+	val &= ~OSTCCR_PRESCALE1_MASK;
+	val |= FIELD_PREP(OSTCCR_PRESCALE1_MASK, prescale);
 	writel(val, ost_clk->ost->base + info->ostccr_reg);
 
 	return 0;
@@ -166,7 +166,8 @@ static int ingenic_ost_global_timer_set_rate(struct clk_hw *hw, unsigned long re
 	int val;
 
 	val = readl(ost_clk->ost->base + info->ostccr_reg);
-	val = (val & ~OSTCCR_PRESCALE2_MASK) | (prescale << OSTCCR_PRESCALE2_LSB);
+	val &= ~OSTCCR_PRESCALE2_MASK;
+	val |= FIELD_PREP(OSTCCR_PRESCALE2_MASK, prescale);
 	writel(val, ost_clk->ost->base + info->ostccr_reg);
 
 	return 0;
diff --git a/drivers/clocksource/sh_cmt.c b/drivers/clocksource/sh_cmt.c
index d7ed99f0001f..dd0956ad969c 100644
--- a/drivers/clocksource/sh_cmt.c
+++ b/drivers/clocksource/sh_cmt.c
@@ -579,7 +579,8 @@ static int sh_cmt_start(struct sh_cmt_channel *ch, unsigned long flag)
 	ch->flags |= flag;
 
 	/* setup timeout if no clockevent */
-	if ((flag == FLAG_CLOCKSOURCE) && (!(ch->flags & FLAG_CLOCKEVENT)))
+	if (ch->cmt->num_channels == 1 &&
+	    flag == FLAG_CLOCKSOURCE && (!(ch->flags & FLAG_CLOCKEVENT)))
 		__sh_cmt_set_next(ch, ch->max_match_value);
  out:
 	raw_spin_unlock_irqrestore(&ch->lock, flags);
@@ -621,20 +622,25 @@ static struct sh_cmt_channel *cs_to_sh_cmt(struct clocksource *cs)
 static u64 sh_cmt_clocksource_read(struct clocksource *cs)
 {
 	struct sh_cmt_channel *ch = cs_to_sh_cmt(cs);
-	unsigned long flags;
 	u32 has_wrapped;
-	u64 value;
-	u32 raw;
 
-	raw_spin_lock_irqsave(&ch->lock, flags);
-	value = ch->total_cycles;
-	raw = sh_cmt_get_counter(ch, &has_wrapped);
+	if (ch->cmt->num_channels == 1) {
+		unsigned long flags;
+		u64 value;
+		u32 raw;
 
-	if (unlikely(has_wrapped))
-		raw += ch->match_value + 1;
-	raw_spin_unlock_irqrestore(&ch->lock, flags);
+		raw_spin_lock_irqsave(&ch->lock, flags);
+		value = ch->total_cycles;
+		raw = sh_cmt_get_counter(ch, &has_wrapped);
+
+		if (unlikely(has_wrapped))
+			raw += ch->match_value + 1;
+		raw_spin_unlock_irqrestore(&ch->lock, flags);
+
+		return value + raw;
+	}
 
-	return value + raw;
+	return sh_cmt_get_counter(ch, &has_wrapped);
 }
 
 static int sh_cmt_clocksource_enable(struct clocksource *cs)
@@ -697,7 +703,7 @@ static int sh_cmt_register_clocksource(struct sh_cmt_channel *ch,
 	cs->disable = sh_cmt_clocksource_disable;
 	cs->suspend = sh_cmt_clocksource_suspend;
 	cs->resume = sh_cmt_clocksource_resume;
-	cs->mask = CLOCKSOURCE_MASK(sizeof(u64) * 8);
+	cs->mask = CLOCKSOURCE_MASK(ch->cmt->info->width);
 	cs->flags = CLOCK_SOURCE_IS_CONTINUOUS;
 
 	dev_info(&ch->cmt->pdev->dev, "ch%u: used as clock source\n",
diff --git a/drivers/clocksource/timer-fttmr010.c b/drivers/clocksource/timer-fttmr010.c
index edb1d5f193f5..126fb1f259b2 100644
--- a/drivers/clocksource/timer-fttmr010.c
+++ b/drivers/clocksource/timer-fttmr010.c
@@ -271,9 +271,7 @@ static irqreturn_t ast2600_timer_interrupt(int irq, void *dev_id)
 }
 
 static int __init fttmr010_common_init(struct device_node *np,
-		bool is_aspeed,
-		int (*timer_shutdown)(struct clock_event_device *),
-		irq_handler_t irq_handler)
+				       bool is_aspeed, bool is_ast2600)
 {
 	struct fttmr010 *fttmr010;
 	int irq;
@@ -374,8 +372,6 @@ static int __init fttmr010_common_init(struct device_node *np,
 				     fttmr010->tick_rate);
 	}
 
-	fttmr010->timer_shutdown = timer_shutdown;
-
 	/*
 	 * Setup clockevent timer (interrupt-driven) on timer 1.
 	 */
@@ -383,8 +379,18 @@ static int __init fttmr010_common_init(struct device_node *np,
 	writel(0, fttmr010->base + TIMER1_LOAD);
 	writel(0, fttmr010->base + TIMER1_MATCH1);
 	writel(0, fttmr010->base + TIMER1_MATCH2);
-	ret = request_irq(irq, irq_handler, IRQF_TIMER,
-			  "FTTMR010-TIMER1", &fttmr010->clkevt);
+
+	if (is_ast2600) {
+		fttmr010->timer_shutdown = ast2600_timer_shutdown;
+		ret = request_irq(irq, ast2600_timer_interrupt,
+				  IRQF_TIMER, "FTTMR010-TIMER1",
+				  &fttmr010->clkevt);
+	} else {
+		fttmr010->timer_shutdown = fttmr010_timer_shutdown;
+		ret = request_irq(irq, fttmr010_timer_interrupt,
+				  IRQF_TIMER, "FTTMR010-TIMER1",
+				  &fttmr010->clkevt);
+	}
 	if (ret) {
 		pr_err("FTTMR010-TIMER1 no IRQ\n");
 		goto out_unmap;
@@ -432,23 +438,17 @@ out_disable_clock:
 
 static __init int ast2600_timer_init(struct device_node *np)
 {
-	return fttmr010_common_init(np, true,
-			ast2600_timer_shutdown,
-			ast2600_timer_interrupt);
+	return fttmr010_common_init(np, true, true);
 }
 
 static __init int aspeed_timer_init(struct device_node *np)
 {
-	return fttmr010_common_init(np, true,
-			fttmr010_timer_shutdown,
-			fttmr010_timer_interrupt);
+	return fttmr010_common_init(np, true, false);
 }
 
 static __init int fttmr010_timer_init(struct device_node *np)
 {
-	return fttmr010_common_init(np, false,
-			fttmr010_timer_shutdown,
-			fttmr010_timer_interrupt);
+	return fttmr010_common_init(np, false, false);
 }
 
 TIMER_OF_DECLARE(fttmr010, "faraday,fttmr010", fttmr010_timer_init);
diff --git a/drivers/clocksource/timer-mediatek.c b/drivers/clocksource/timer-mediatek.c
index ab63b95e414f..7bcb4a3f26fb 100644
--- a/drivers/clocksource/timer-mediatek.c
+++ b/drivers/clocksource/timer-mediatek.c
@@ -60,9 +60,9 @@
  * SYST_CON_EN: Clock enable. Shall be set to
  *   - Start timer countdown.
  *   - Allow timeout ticks being updated.
- *   - Allow changing interrupt functions.
+ *   - Allow changing interrupt status,like clear irq pending.
  *
- * SYST_CON_IRQ_EN: Set to allow interrupt.
+ * SYST_CON_IRQ_EN: Set to enable interrupt.
  *
  * SYST_CON_IRQ_CLR: Set to clear interrupt.
  */
@@ -75,6 +75,7 @@ static void __iomem *gpt_sched_reg __read_mostly;
 static void mtk_syst_ack_irq(struct timer_of *to)
 {
 	/* Clear and disable interrupt */
+	writel(SYST_CON_EN, SYST_CON_REG(to));
 	writel(SYST_CON_IRQ_CLR | SYST_CON_EN, SYST_CON_REG(to));
 }
 
@@ -111,6 +112,9 @@ static int mtk_syst_clkevt_next_event(unsigned long ticks,
 
 static int mtk_syst_clkevt_shutdown(struct clock_event_device *clkevt)
 {
+	/* Clear any irq */
+	mtk_syst_ack_irq(to_timer_of(clkevt));
+
 	/* Disable timer */
 	writel(0, SYST_CON_REG(to_timer_of(clkevt)));
 
diff --git a/fs/timerfd.c b/fs/timerfd.c
index c5509d2448e3..e9c96a0c79f1 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -115,6 +115,22 @@ void timerfd_clock_was_set(void)
 	rcu_read_unlock();
 }
 
+static void timerfd_resume_work(struct work_struct *work)
+{
+	timerfd_clock_was_set();
+}
+
+static DECLARE_WORK(timerfd_work, timerfd_resume_work);
+
+/*
+ * Invoked from timekeeping_resume(). Defer the actual update to work so
+ * timerfd_clock_was_set() runs in task context.
+ */
+void timerfd_resume(void)
+{
+	schedule_work(&timerfd_work);
+}
+
 static void __timerfd_remove_cancel(struct timerfd_ctx *ctx)
 {
 	if (ctx->might_cancel) {
diff --git a/include/dt-bindings/clock/ingenic,sysost.h b/include/dt-bindings/clock/ingenic,sysost.h
index 063791b01ab3..d7aa42c08ded 100644
--- a/include/dt-bindings/clock/ingenic,sysost.h
+++ b/include/dt-bindings/clock/ingenic,sysost.h
@@ -13,4 +13,23 @@
 #define OST_CLK_PERCPU_TIMER2	3
 #define OST_CLK_PERCPU_TIMER3	4
 
+#define OST_CLK_EVENT_TIMER		1
+
+#define OST_CLK_EVENT_TIMER0	0
+#define OST_CLK_EVENT_TIMER1	1
+#define OST_CLK_EVENT_TIMER2	2
+#define OST_CLK_EVENT_TIMER3	3
+#define OST_CLK_EVENT_TIMER4	4
+#define OST_CLK_EVENT_TIMER5	5
+#define OST_CLK_EVENT_TIMER6	6
+#define OST_CLK_EVENT_TIMER7	7
+#define OST_CLK_EVENT_TIMER8	8
+#define OST_CLK_EVENT_TIMER9	9
+#define OST_CLK_EVENT_TIMER10	10
+#define OST_CLK_EVENT_TIMER11	11
+#define OST_CLK_EVENT_TIMER12	12
+#define OST_CLK_EVENT_TIMER13	13
+#define OST_CLK_EVENT_TIMER14	14
+#define OST_CLK_EVENT_TIMER15	15
+
 #endif /* __DT_BINDINGS_CLOCK_INGENIC_OST_H__ */
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index bb5e7b0a4274..0ee140176f10 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -318,16 +318,12 @@ struct clock_event_device;
 
 extern void hrtimer_interrupt(struct clock_event_device *dev);
 
-extern void clock_was_set_delayed(void);
-
 extern unsigned int hrtimer_resolution;
 
 #else
 
 #define hrtimer_resolution	(unsigned int)LOW_RES_NSEC
 
-static inline void clock_was_set_delayed(void) { }
-
 #endif
 
 static inline ktime_t
@@ -351,13 +347,13 @@ hrtimer_expires_remaining_adjusted(const struct hrtimer *timer)
 						    timer->base->get_time());
 }
 
-extern void clock_was_set(void);
 #ifdef CONFIG_TIMERFD
 extern void timerfd_clock_was_set(void);
+extern void timerfd_resume(void);
 #else
 static inline void timerfd_clock_was_set(void) { }
+static inline void timerfd_resume(void) { }
 #endif
-extern void hrtimers_resume(void);
 
 DECLARE_PER_CPU(struct tick_device, tick_cpu_device);
 
diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index 896c16d2c5fb..00fef0064355 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -82,12 +82,19 @@ static inline bool cpu_timer_enqueue(struct timerqueue_head *head,
 	return timerqueue_add(head, &ctmr->node);
 }
 
-static inline void cpu_timer_dequeue(struct cpu_timer *ctmr)
+static inline bool cpu_timer_queued(struct cpu_timer *ctmr)
 {
-	if (ctmr->head) {
+	return !!ctmr->head;
+}
+
+static inline bool cpu_timer_dequeue(struct cpu_timer *ctmr)
+{
+	if (cpu_timer_queued(ctmr)) {
 		timerqueue_del(ctmr->head, &ctmr->node);
 		ctmr->head = NULL;
+		return true;
 	}
+	return false;
 }
 
 static inline u64 cpu_timer_getexpires(struct cpu_timer *ctmr)
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index b9126fe06c3f..0310a5add9ab 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -714,6 +714,12 @@ static inline void unlock_task_sighand(struct task_struct *task,
 	spin_unlock_irqrestore(&task->sighand->siglock, *flags);
 }
 
+#ifdef CONFIG_LOCKDEP
+extern void lockdep_assert_task_sighand_held(struct task_struct *task);
+#else
+static inline void lockdep_assert_task_sighand_held(struct task_struct *task) { }
+#endif
+
 static inline unsigned long task_rlimit(const struct task_struct *task,
 		unsigned int limit)
 {
diff --git a/kernel/signal.c b/kernel/signal.c
index a3229add4455..52b6abec0ff8 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1413,6 +1413,21 @@ struct sighand_struct *__lock_task_sighand(struct task_struct *tsk,
 	return sighand;
 }
 
+#ifdef CONFIG_LOCKDEP
+void lockdep_assert_task_sighand_held(struct task_struct *task)
+{
+	struct sighand_struct *sighand;
+
+	rcu_read_lock();
+	sighand = rcu_dereference(task->sighand);
+	if (sighand)
+		lockdep_assert_held(&sighand->siglock);
+	else
+		WARN_ON_ONCE(1);
+	rcu_read_unlock();
+}
+#endif
+
 /*
  * send signal info to all the members of a group
  */
diff --git a/kernel/time/clocksource-wdtest.c b/kernel/time/clocksource-wdtest.c
index 01df12395c0e..df922f49d171 100644
--- a/kernel/time/clocksource-wdtest.c
+++ b/kernel/time/clocksource-wdtest.c
@@ -19,6 +19,8 @@
 #include <linux/prandom.h>
 #include <linux/cpu.h>
 
+#include "tick-internal.h"
+
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Paul E. McKenney <paulmck@kernel.org>");
 
@@ -34,9 +36,6 @@ static u64 wdtest_jiffies_read(struct clocksource *cs)
 	return (u64)jiffies;
 }
 
-/* Assume HZ > 100. */
-#define JIFFIES_SHIFT	8
-
 static struct clocksource clocksource_wdtest_jiffies = {
 	.name			= "wdtest-jiffies",
 	.rating			= 1, /* lowest valid rating*/
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index b89c76e1c02c..b8a14d2fb5ba 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -306,12 +306,12 @@ void clocksource_verify_percpu(struct clocksource *cs)
 		return;
 	cpumask_clear(&cpus_ahead);
 	cpumask_clear(&cpus_behind);
-	get_online_cpus();
+	cpus_read_lock();
 	preempt_disable();
 	clocksource_verify_choose_cpus();
 	if (cpumask_weight(&cpus_chosen) == 0) {
 		preempt_enable();
-		put_online_cpus();
+		cpus_read_unlock();
 		pr_warn("Not enough CPUs to check clocksource '%s'.\n", cs->name);
 		return;
 	}
@@ -337,7 +337,7 @@ void clocksource_verify_percpu(struct clocksource *cs)
 			cs_nsec_min = cs_nsec;
 	}
 	preempt_enable();
-	put_online_cpus();
+	cpus_read_unlock();
 	if (!cpumask_empty(&cpus_ahead))
 		pr_warn("        CPUs %*pbl ahead of CPU %d for clocksource %s.\n",
 			cpumask_pr_args(&cpus_ahead), testcpu, cs->name);
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 4a66725b1d4a..0ea8702eb516 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -652,21 +652,10 @@ static inline int hrtimer_hres_active(void)
 	return __hrtimer_hres_active(this_cpu_ptr(&hrtimer_bases));
 }
 
-/*
- * Reprogram the event source with checking both queues for the
- * next event
- * Called with interrupts disabled and base->lock held
- */
-static void
-hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
+static void __hrtimer_reprogram(struct hrtimer_cpu_base *cpu_base,
+				struct hrtimer *next_timer,
+				ktime_t expires_next)
 {
-	ktime_t expires_next;
-
-	expires_next = hrtimer_update_next_event(cpu_base);
-
-	if (skip_equal && expires_next == cpu_base->expires_next)
-		return;
-
 	cpu_base->expires_next = expires_next;
 
 	/*
@@ -689,7 +678,25 @@ hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
 	if (!__hrtimer_hres_active(cpu_base) || cpu_base->hang_detected)
 		return;
 
-	tick_program_event(cpu_base->expires_next, 1);
+	tick_program_event(expires_next, 1);
+}
+
+/*
+ * Reprogram the event source with checking both queues for the
+ * next event
+ * Called with interrupts disabled and base->lock held
+ */
+static void
+hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
+{
+	ktime_t expires_next;
+
+	expires_next = hrtimer_update_next_event(cpu_base);
+
+	if (skip_equal && expires_next == cpu_base->expires_next)
+		return;
+
+	__hrtimer_reprogram(cpu_base, cpu_base->next_timer, expires_next);
 }
 
 /* High resolution timer related functions */
@@ -720,23 +727,7 @@ static inline int hrtimer_is_hres_enabled(void)
 	return hrtimer_hres_enabled;
 }
 
-/*
- * Retrigger next event is called after clock was set
- *
- * Called with interrupts disabled via on_each_cpu()
- */
-static void retrigger_next_event(void *arg)
-{
-	struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases);
-
-	if (!__hrtimer_hres_active(base))
-		return;
-
-	raw_spin_lock(&base->lock);
-	hrtimer_update_base(base);
-	hrtimer_force_reprogram(base, 0);
-	raw_spin_unlock(&base->lock);
-}
+static void retrigger_next_event(void *arg);
 
 /*
  * Switch to high resolution mode
@@ -758,29 +749,54 @@ static void hrtimer_switch_to_hres(void)
 	retrigger_next_event(NULL);
 }
 
-static void clock_was_set_work(struct work_struct *work)
-{
-	clock_was_set();
-}
+#else
 
-static DECLARE_WORK(hrtimer_work, clock_was_set_work);
+static inline int hrtimer_is_hres_enabled(void) { return 0; }
+static inline void hrtimer_switch_to_hres(void) { }
 
+#endif /* CONFIG_HIGH_RES_TIMERS */
 /*
- * Called from timekeeping and resume code to reprogram the hrtimer
- * interrupt device on all cpus.
+ * Retrigger next event is called after clock was set with interrupts
+ * disabled through an SMP function call or directly from low level
+ * resume code.
+ *
+ * This is only invoked when:
+ *	- CONFIG_HIGH_RES_TIMERS is enabled.
+ *	- CONFIG_NOHZ_COMMON is enabled
+ *
+ * For the other cases this function is empty and because the call sites
+ * are optimized out it vanishes as well, i.e. no need for lots of
+ * #ifdeffery.
  */
-void clock_was_set_delayed(void)
+static void retrigger_next_event(void *arg)
 {
-	schedule_work(&hrtimer_work);
-}
-
-#else
+	struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases);
 
-static inline int hrtimer_is_hres_enabled(void) { return 0; }
-static inline void hrtimer_switch_to_hres(void) { }
-static inline void retrigger_next_event(void *arg) { }
+	/*
+	 * When high resolution mode or nohz is active, then the offsets of
+	 * CLOCK_REALTIME/TAI/BOOTTIME have to be updated. Otherwise the
+	 * next tick will take care of that.
+	 *
+	 * If high resolution mode is active then the next expiring timer
+	 * must be reevaluated and the clock event device reprogrammed if
+	 * necessary.
+	 *
+	 * In the NOHZ case the update of the offset and the reevaluation
+	 * of the next expiring timer is enough. The return from the SMP
+	 * function call will take care of the reprogramming in case the
+	 * CPU was in a NOHZ idle sleep.
+	 */
+	if (!__hrtimer_hres_active(base) && !tick_nohz_active)
+		return;
 
-#endif /* CONFIG_HIGH_RES_TIMERS */
+	raw_spin_lock(&base->lock);
+	hrtimer_update_base(base);
+	if (__hrtimer_hres_active(base))
+		hrtimer_force_reprogram(base, 0);
+	else
+		hrtimer_update_next_event(base);
+	raw_spin_unlock(&base->lock);
+}
 
 /*
  * When a timer is enqueued and expires earlier than the already enqueued
@@ -835,75 +851,161 @@ static void hrtimer_reprogram(struct hrtimer *timer, bool reprogram)
 	if (base->cpu_base != cpu_base)
 		return;
 
+	if (expires >= cpu_base->expires_next)
+		return;
+
 	/*
-	 * If the hrtimer interrupt is running, then it will
-	 * reevaluate the clock bases and reprogram the clock event
-	 * device. The callbacks are always executed in hard interrupt
-	 * context so we don't need an extra check for a running
-	 * callback.
+	 * If the hrtimer interrupt is running, then it will reevaluate the
+	 * clock bases and reprogram the clock event device.
 	 */
 	if (cpu_base->in_hrtirq)
 		return;
 
-	if (expires >= cpu_base->expires_next)
-		return;
-
-	/* Update the pointer to the next expiring timer */
 	cpu_base->next_timer = timer;
-	cpu_base->expires_next = expires;
+
+	__hrtimer_reprogram(cpu_base, timer, expires);
+}
+
+static bool update_needs_ipi(struct hrtimer_cpu_base *cpu_base,
+			     unsigned int active)
+{
+	struct hrtimer_clock_base *base;
+	unsigned int seq;
+	ktime_t expires;
 
 	/*
-	 * If hres is not active, hardware does not have to be
-	 * programmed yet.
+	 * Update the base offsets unconditionally so the following
+	 * checks whether the SMP function call is required works.
 	 *
-	 * If a hang was detected in the last timer interrupt then we
-	 * do not schedule a timer which is earlier than the expiry
-	 * which we enforced in the hang detection. We want the system
-	 * to make progress.
+	 * The update is safe even when the remote CPU is in the hrtimer
+	 * interrupt or the hrtimer soft interrupt and expiring affected
+	 * bases. Either it will see the update before handling a base or
+	 * it will see it when it finishes the processing and reevaluates
+	 * the next expiring timer.
 	 */
-	if (!__hrtimer_hres_active(cpu_base) || cpu_base->hang_detected)
-		return;
+	seq = cpu_base->clock_was_set_seq;
+	hrtimer_update_base(cpu_base);
+
+	/*
+	 * If the sequence did not change over the update then the
+	 * remote CPU already handled it.
+	 */
+	if (seq == cpu_base->clock_was_set_seq)
+		return false;
+
+	/*
+	 * If the remote CPU is currently handling an hrtimer interrupt, it
+	 * will reevaluate the first expiring timer of all clock bases
+	 * before reprogramming. Nothing to do here.
+	 */
+	if (cpu_base->in_hrtirq)
+		return false;
 
 	/*
-	 * Program the timer hardware. We enforce the expiry for
-	 * events which are already in the past.
+	 * Walk the affected clock bases and check whether the first expiring
+	 * timer in a clock base is moving ahead of the first expiring timer of
+	 * @cpu_base. If so, the IPI must be invoked because per CPU clock
+	 * event devices cannot be remotely reprogrammed.