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
  ...

Author: torvalds

Documentation/devicetree/bindings/timer/rockchip,rk-timer.txt

@@ -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";
+    };

Documentation/devicetree/bindings/timer/rockchip,rk-timer.yaml

@@ -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);
 

drivers/clocksource/exynos_mct.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;

drivers/clocksource/ingenic-sysost.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",

drivers/clocksource/sh_cmt.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;
@@ -374,17 +372,25 @@ 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.
 	 */
 	writel(0, fttmr010->base + TIMER1_COUNT);
 	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 @@ static int __init fttmr010_common_init(struct device_node *np,
 
 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);

drivers/clocksource/timer-fttmr010.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)));
 

drivers/clocksource/timer-mediatek.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) {

fs/timerfd.c

@@ -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__ */