Merge branch 'timers/core' into sched/hrtimers

Merge sched/core and timers/core so we can apply the sched balancing
patch queue, which depends on both.

Documentation/devicetree/bindings/arm/armv7m_systick.txt

@@ -0,0 +1,26 @@
+* ARMv7M System Timer
+
+ARMv7-M includes a system timer, known as SysTick. Current driver only
+implements the clocksource feature.
+
+Required properties:
+- compatible	  : Should be "arm,armv7m-systick"
+- reg		  : The address range of the timer
+
+Required clocking property, have to be one of:
+- clocks	  : The input clock of the timer
+- clock-frequency : The rate in HZ in input of the ARM SysTick
+
+Examples:
+
+systick: timer@e000e010 {
+	compatible = "arm,armv7m-systick";
+	reg = <0xe000e010 0x10>;
+	clocks = <&clk_systick>;
+};
+
+systick: timer@e000e010 {
+	compatible = "arm,armv7m-systick";
+	reg = <0xe000e010 0x10>;
+	clock-frequency = <90000000>;
+};

Documentation/devicetree/bindings/timer/nxp,lpc3220-timer.txt

@@ -0,0 +1,26 @@
+* NXP LPC3220 timer
+
+The NXP LPC3220 timer is used on a wide range of NXP SoCs. This
+includes LPC32xx, LPC178x, LPC18xx and LPC43xx parts.
+
+Required properties:
+- compatible:
+	Should be "nxp,lpc3220-timer".
+- reg:
+	Address and length of the register set.
+- interrupts:
+	Reference to the timer interrupt
+- clocks:
+	Should contain a reference to timer clock.
+- clock-names:
+	Should contain "timerclk".
+
+Example:
+
+timer1: timer@40085000 {
+	compatible = "nxp,lpc3220-timer";
+	reg = <0x40085000 0x1000>;
+	interrupts = <13>;
+	clocks = <&ccu1 CLK_CPU_TIMER1>;
+	clock-names = "timerclk";
+};

Documentation/devicetree/bindings/timer/st,stm32-timer.txt

@@ -0,0 +1,22 @@
+. STMicroelectronics STM32 timer
+
+The STM32 MCUs family has several general-purpose 16 and 32 bits timers.
+
+Required properties:
+- compatible : Should be "st,stm32-timer"
+- reg : Address and length of the register set
+- clocks : Reference on the timer input clock
+- interrupts : Reference to the timer interrupt
+
+Optional properties:
+- resets: Reference to a reset controller asserting the timer
+
+Example:
+
+timer5: timer@40000c00 {
+	compatible = "st,stm32-timer";
+	reg = <0x40000c00 0x400>;
+	interrupts = <50>;
+	resets = <&rrc 259>;
+	clocks = <&clk_pmtr1>;
+};

Kbuild

@@ -2,8 +2,9 @@
 # Kbuild for top-level directory of the kernel
 # This file takes care of the following:
 # 1) Generate bounds.h
-# 2) Generate asm-offsets.h (may need bounds.h)
-# 3) Check for missing system calls
+# 2) Generate timeconst.h
+# 3) Generate asm-offsets.h (may need bounds.h and timeconst.h)
+# 4) Check for missing system calls
 
 # Default sed regexp - multiline due to syntax constraints
 define sed-y
@@ -47,7 +48,26 @@ $(obj)/$(bounds-file): kernel/bounds.s FORCE
 	$(call filechk,offsets,__LINUX_BOUNDS_H__)
 
 #####
-# 2) Generate asm-offsets.h
+# 2) Generate timeconst.h
+
+timeconst-file := include/generated/timeconst.h
+
+#always  += $(timeconst-file)
+targets += $(timeconst-file)
+
+quiet_cmd_gentimeconst = GEN     $@
+define cmd_gentimeconst
+	(echo $(CONFIG_HZ) | bc -q $< ) > $@
+endef
+define filechk_gentimeconst
+	(echo $(CONFIG_HZ) | bc -q $< )
+endef
+
+$(obj)/$(timeconst-file): kernel/time/timeconst.bc FORCE
+	$(call filechk,gentimeconst)
+
+#####
+# 3) Generate asm-offsets.h
 #
 
 offsets-file := include/generated/asm-offsets.h
@@ -57,7 +77,7 @@ targets += arch/$(SRCARCH)/kernel/asm-offsets.s
 
 # We use internal kbuild rules to avoid the "is up to date" message from make
 arch/$(SRCARCH)/kernel/asm-offsets.s: arch/$(SRCARCH)/kernel/asm-offsets.c \
-                                      $(obj)/$(bounds-file) FORCE
+                                      $(obj)/$(timeconst-file) $(obj)/$(bounds-file) FORCE
 	$(Q)mkdir -p $(dir $@)
 	$(call if_changed_dep,cc_s_c)
 
@@ -65,7 +85,7 @@ $(obj)/$(offsets-file): arch/$(SRCARCH)/kernel/asm-offsets.s FORCE
 	$(call filechk,offsets,__ASM_OFFSETS_H__)
 
 #####
-# 3) Check for missing system calls
+# 4) Check for missing system calls
 #
 
 always += missing-syscalls
@@ -77,5 +97,5 @@ quiet_cmd_syscalls = CALL    $<
 missing-syscalls: scripts/checksyscalls.sh $(offsets-file) FORCE
 	$(call cmd,syscalls)
 
-# Keep these two files during make clean
-no-clean-files := $(bounds-file) $(offsets-file)
+# Keep these three files during make clean
+no-clean-files := $(bounds-file) $(offsets-file) $(timeconst-file)

arch/s390/include/asm/timex.h

@@ -10,6 +10,7 @@
 #define _ASM_S390_TIMEX_H
 
 #include <asm/lowcore.h>
+#include <linux/time64.h>
 
 /* The value of the TOD clock for 1.1.1970. */
 #define TOD_UNIX_EPOCH 0x7d91048bca000000ULL
@@ -108,10 +109,10 @@ int get_sync_clock(unsigned long long *clock);
 void init_cpu_timer(void);
 unsigned long long monotonic_clock(void);
 
-void tod_to_timeval(__u64, struct timespec *);
+void tod_to_timeval(__u64 todval, struct timespec64 *xt);
 
 static inline
-void stck_to_timespec(unsigned long long stck, struct timespec *ts)
+void stck_to_timespec64(unsigned long long stck, struct timespec64 *ts)
 {
 	tod_to_timeval(stck - TOD_UNIX_EPOCH, ts);
 }

arch/s390/kernel/debug.c

@@ -1457,23 +1457,24 @@ int
 debug_dflt_header_fn(debug_info_t * id, struct debug_view *view,
 			 int area, debug_entry_t * entry, char *out_buf)
 {
-	struct timespec time_spec;
+	struct timespec64 time_spec;
 	char *except_str;
 	unsigned long caller;
 	int rc = 0;
 	unsigned int level;
 
 	level = entry->id.fields.level;
-	stck_to_timespec(entry->id.stck, &time_spec);
+	stck_to_timespec64(entry->id.stck, &time_spec);
 
 	if (entry->id.fields.exception)
 		except_str = "*";
 	else
 		except_str = "-";
 	caller = ((unsigned long) entry->caller) & PSW_ADDR_INSN;
-	rc += sprintf(out_buf, "%02i %011lu:%06lu %1u %1s %02i %p  ",
-		      area, time_spec.tv_sec, time_spec.tv_nsec / 1000, level,
-		      except_str, entry->id.fields.cpuid, (void *) caller);
+	rc += sprintf(out_buf, "%02i %011lld:%06lu %1u %1s %02i %p  ",
+		      area, (long long)time_spec.tv_sec,
+		      time_spec.tv_nsec / 1000, level, except_str,
+		      entry->id.fields.cpuid, (void *)caller);
 	return rc;
 }
 EXPORT_SYMBOL(debug_dflt_header_fn);

arch/s390/kernel/time.c

@@ -76,7 +76,7 @@ unsigned long long monotonic_clock(void)
 }
 EXPORT_SYMBOL(monotonic_clock);
 
-void tod_to_timeval(__u64 todval, struct timespec *xt)
+void tod_to_timeval(__u64 todval, struct timespec64 *xt)
 {
 	unsigned long long sec;
 
@@ -181,12 +181,12 @@ static void timing_alert_interrupt(struct ext_code ext_code,
 static void etr_reset(void);
 static void stp_reset(void);
 
-void read_persistent_clock(struct timespec *ts)
+void read_persistent_clock64(struct timespec64 *ts)
 {
 	tod_to_timeval(get_tod_clock() - TOD_UNIX_EPOCH, ts);
 }
 
-void read_boot_clock(struct timespec *ts)
+void read_boot_clock64(struct timespec64 *ts)
 {
 	tod_to_timeval(sched_clock_base_cc - TOD_UNIX_EPOCH, ts);
 }

arch/x86/kernel/cpu/perf_event_intel_rapl.c

@@ -204,9 +204,8 @@ again:
 
 static void rapl_start_hrtimer(struct rapl_pmu *pmu)
 {
-	__hrtimer_start_range_ns(&pmu->hrtimer,
-			pmu->timer_interval, 0,
-			HRTIMER_MODE_REL_PINNED, 0);
+       hrtimer_start(&pmu->hrtimer, pmu->timer_interval,
+		     HRTIMER_MODE_REL_PINNED);
 }
 
 static void rapl_stop_hrtimer(struct rapl_pmu *pmu)

arch/x86/kernel/cpu/perf_event_intel_uncore.c

@@ -233,9 +233,8 @@ static enum hrtimer_restart uncore_pmu_hrtimer(struct hrtimer *hrtimer)
 
 void uncore_pmu_start_hrtimer(struct intel_uncore_box *box)
 {
-	__hrtimer_start_range_ns(&box->hrtimer,
-			ns_to_ktime(box->hrtimer_duration), 0,
-			HRTIMER_MODE_REL_PINNED, 0);
+	hrtimer_start(&box->hrtimer, ns_to_ktime(box->hrtimer_duration),
+		      HRTIMER_MODE_REL_PINNED);
 }
 
 void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box)

drivers/clocksource/Kconfig

@@ -106,6 +106,16 @@ config CLKSRC_EFM32
 	  Support to use the timers of EFM32 SoCs as clock source and clock
 	  event device.
 
+config CLKSRC_LPC32XX
+	bool
+	select CLKSRC_MMIO
+	select CLKSRC_OF
+
+config CLKSRC_STM32
+	bool "Clocksource for STM32 SoCs" if COMPILE_TEST
+	depends on OF
+	select CLKSRC_MMIO
+
 config ARM_ARCH_TIMER
 	bool
 	select CLKSRC_OF if OF
@@ -139,6 +149,13 @@ config CLKSRC_ARM_GLOBAL_TIMER_SCHED_CLOCK
 	help
 	 Use ARM global timer clock source as sched_clock
 
+config ARMV7M_SYSTICK
+	bool
+	select CLKSRC_OF if OF
+	select CLKSRC_MMIO
+	help
+	  This options enables support for the ARMv7M system timer unit
+
 config ATMEL_PIT
 	select CLKSRC_OF if OF
 	def_bool SOC_AT91SAM9 || SOC_SAMA5

drivers/clocksource/Makefile

@@ -36,7 +36,9 @@ obj-$(CONFIG_ARCH_NSPIRE)	+= zevio-timer.o
 obj-$(CONFIG_ARCH_BCM_MOBILE)	+= bcm_kona_timer.o
 obj-$(CONFIG_CADENCE_TTC_TIMER)	+= cadence_ttc_timer.o
 obj-$(CONFIG_CLKSRC_EFM32)	+= time-efm32.o
+obj-$(CONFIG_CLKSRC_STM32)	+= timer-stm32.o
 obj-$(CONFIG_CLKSRC_EXYNOS_MCT)	+= exynos_mct.o
+obj-$(CONFIG_CLKSRC_LPC32XX)	+= time-lpc32xx.o
 obj-$(CONFIG_CLKSRC_SAMSUNG_PWM)	+= samsung_pwm_timer.o
 obj-$(CONFIG_FSL_FTM_TIMER)	+= fsl_ftm_timer.o
 obj-$(CONFIG_VF_PIT_TIMER)	+= vf_pit_timer.o
@@ -45,6 +47,7 @@ obj-$(CONFIG_MTK_TIMER)		+= mtk_timer.o
 
 obj-$(CONFIG_ARM_ARCH_TIMER)		+= arm_arch_timer.o
 obj-$(CONFIG_ARM_GLOBAL_TIMER)		+= arm_global_timer.o
+obj-$(CONFIG_ARMV7M_SYSTICK)		+= armv7m_systick.o
 obj-$(CONFIG_CLKSRC_METAG_GENERIC)	+= metag_generic.o
 obj-$(CONFIG_ARCH_HAS_TICK_BROADCAST)	+= dummy_timer.o
 obj-$(CONFIG_ARCH_KEYSTONE)		+= timer-keystone.o

drivers/clocksource/armv7m_systick.c

@@ -0,0 +1,79 @@
+/*
+ * Copyright (C) Maxime Coquelin 2015
+ * Author:  Maxime Coquelin <mcoquelin.stm32@gmail.com>
+ * License terms:  GNU General Public License (GPL), version 2
+ */
+
+#include <linux/kernel.h>
+#include <linux/clocksource.h>
+#include <linux/clockchips.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/clk.h>
+#include <linux/bitops.h>
+
+#define SYST_CSR	0x00
+#define SYST_RVR	0x04
+#define SYST_CVR	0x08
+#define SYST_CALIB	0x0c
+
+#define SYST_CSR_ENABLE BIT(0)
+
+#define SYSTICK_LOAD_RELOAD_MASK 0x00FFFFFF
+
+static void __init system_timer_of_register(struct device_node *np)
+{
+	struct clk *clk = NULL;
+	void __iomem *base;
+	u32 rate;
+	int ret;
+
+	base = of_iomap(np, 0);
+	if (!base) {
+		pr_warn("system-timer: invalid base address\n");
+		return;
+	}
+
+	ret = of_property_read_u32(np, "clock-frequency", &rate);
+	if (ret) {
+		clk = of_clk_get(np, 0);
+		if (IS_ERR(clk))
+			goto out_unmap;
+
+		ret = clk_prepare_enable(clk);
+		if (ret)
+			goto out_clk_put;
+
+		rate = clk_get_rate(clk);
+		if (!rate)
+			goto out_clk_disable;
+	}
+
+	writel_relaxed(SYSTICK_LOAD_RELOAD_MASK, base + SYST_RVR);
+	writel_relaxed(SYST_CSR_ENABLE, base + SYST_CSR);
+
+	ret = clocksource_mmio_init(base + SYST_CVR, "arm_system_timer", rate,
+			200, 24, clocksource_mmio_readl_down);
+	if (ret) {
+		pr_err("failed to init clocksource (%d)\n", ret);
+		if (clk)
+			goto out_clk_disable;
+		else
+			goto out_unmap;
+	}
+
+	pr_info("ARM System timer initialized as clocksource\n");
+
+	return;
+
+out_clk_disable:
+	clk_disable_unprepare(clk);
+out_clk_put:
+	clk_put(clk);
+out_unmap:
+	iounmap(base);
+	pr_warn("ARM System timer register failed (%d)\n", ret);
+}
+
+CLOCKSOURCE_OF_DECLARE(arm_systick, "arm,armv7m-systick",
+			system_timer_of_register);

drivers/clocksource/asm9260_timer.c

@@ -178,7 +178,7 @@ static void __init asm9260_timer_init(struct device_node *np)
 	unsigned long rate;
 
 	priv.base = of_io_request_and_map(np, 0, np->name);
-	if (!priv.base)
+	if (IS_ERR(priv.base))
 		panic("%s: unable to map resource", np->name);
 
 	clk = of_clk_get(np, 0);

drivers/clocksource/exynos_mct.c

@@ -209,7 +209,7 @@ static void exynos4_frc_resume(struct clocksource *cs)
 	exynos4_mct_frc_start();
 }
 
-struct clocksource mct_frc = {
+static struct clocksource mct_frc = {
 	.name		= "mct-frc",
 	.rating		= 400,
 	.read		= exynos4_frc_read,
@@ -413,7 +413,7 @@ static inline void exynos4_tick_set_mode(enum clock_event_mode mode,
 	}
 }
 
-static int exynos4_mct_tick_clear(struct mct_clock_event_device *mevt)
+static void exynos4_mct_tick_clear(struct mct_clock_event_device *mevt)
 {
 	struct clock_event_device *evt = &mevt->evt;
 
@@ -426,12 +426,8 @@ static int exynos4_mct_tick_clear(struct mct_clock_event_device *mevt)
 		exynos4_mct_tick_stop(mevt);
 
 	/* Clear the MCT tick interrupt */
-	if (readl_relaxed(reg_base + mevt->base + MCT_L_INT_CSTAT_OFFSET) & 1) {
+	if (readl_relaxed(reg_base + mevt->base + MCT_L_INT_CSTAT_OFFSET) & 1)
 		exynos4_mct_write(0x1, mevt->base + MCT_L_INT_CSTAT_OFFSET);
-		return 1;
-	} else {
-		return 0;
-	}
 }
 
 static irqreturn_t exynos4_mct_tick_isr(int irq, void *dev_id)
@@ -564,18 +560,6 @@ out_irq:
 	free_percpu_irq(mct_irqs[MCT_L0_IRQ], &percpu_mct_tick);
 }
 
-void __init mct_init(void __iomem *base, int irq_g0, int irq_l0, int irq_l1)
-{
-	mct_irqs[MCT_G0_IRQ] = irq_g0;
-	mct_irqs[MCT_L0_IRQ] = irq_l0;
-	mct_irqs[MCT_L1_IRQ] = irq_l1;
-	mct_int_type = MCT_INT_SPI;
-
-	exynos4_timer_resources(NULL, base);
-	exynos4_clocksource_init();
-	exynos4_clockevent_init();
-}
-
 static void __init mct_init_dt(struct device_node *np, unsigned int int_type)
 {
 	u32 nr_irqs, i;

drivers/clocksource/qcom-timer.c

@@ -40,8 +40,6 @@
 
 #define GPT_HZ 32768
 
-#define MSM_DGT_SHIFT 5
-
 static void __iomem *event_base;
 static void __iomem *sts_base;
 
@@ -232,7 +230,6 @@ err:
 	register_current_timer_delay(&msm_delay_timer);
 }
 
-#ifdef CONFIG_ARCH_QCOM
 static void __init msm_dt_timer_init(struct device_node *np)
 {
 	u32 freq;
@@ -285,59 +282,3 @@ static void __init msm_dt_timer_init(struct device_node *np)
 }
 CLOCKSOURCE_OF_DECLARE(kpss_timer, "qcom,kpss-timer", msm_dt_timer_init);
 CLOCKSOURCE_OF_DECLARE(scss_timer, "qcom,scss-timer", msm_dt_timer_init);
-#else
-
-static int __init msm_timer_map(phys_addr_t addr, u32 event, u32 source,
-				u32 sts)
-{
-	void __iomem *base;
-
-	base = ioremap(addr, SZ_256);
-	if (!base) {
-		pr_err("Failed to map timer base\n");
-		return -ENOMEM;
-	}
-	event_base = base + event;
-	source_base = base + source;
-	if (sts)
-		sts_base = base + sts;
-
-	return 0;
-}
-
-static notrace cycle_t msm_read_timer_count_shift(struct clocksource *cs)
-{
-	/*
-	 * Shift timer count down by a constant due to unreliable lower bits
-	 * on some targets.
-	 */
-	return msm_read_timer_count(cs) >> MSM_DGT_SHIFT;
-}
-
-void __init msm7x01_timer_init(void)
-{
-	struct clocksource *cs = &msm_clocksource;
-
-	if (msm_timer_map(0xc0100000, 0x0, 0x10, 0x0))
-		return;
-	cs->read = msm_read_timer_count_shift;
-	cs->mask = CLOCKSOURCE_MASK((32 - MSM_DGT_SHIFT));
-	/* 600 KHz */
-	msm_timer_init(19200000 >> MSM_DGT_SHIFT, 32 - MSM_DGT_SHIFT, 7,
-			false);
-}
-
-void __init msm7x30_timer_init(void)
-{
-	if (msm_timer_map(0xc0100000, 0x4, 0x24, 0x80))
-		return;
-	msm_timer_init(24576000 / 4, 32, 1, false);
-}
-
-void __init qsd8x50_timer_init(void)
-{
-	if (msm_timer_map(0xAC100000, 0x0, 0x10, 0x34))
-		return;
-	msm_timer_init(19200000 / 4, 32, 7, false);
-}
-#endif

drivers/clocksource/time-lpc32xx.c

@@ -0,0 +1,272 @@
+/*
+ * Clocksource driver for NXP LPC32xx/18xx/43xx timer
+ *
+ * Copyright (C) 2015 Joachim Eastwood <manabian@gmail.com>
+ *
+ * Based on:
+ * time-efm32 Copyright (C) 2013 Pengutronix
+ * mach-lpc32xx/timer.c Copyright (C) 2009 - 2010 NXP Semiconductors
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ *
+ */
+
+#define pr_fmt(fmt) "%s: " fmt, __func__
+
+#include <linux/clk.h>
+#include <linux/clockchips.h>
+#include <linux/clocksource.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/kernel.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/sched_clock.h>
+
+#define LPC32XX_TIMER_IR		0x000
+#define  LPC32XX_TIMER_IR_MR0INT	BIT(0)
+#define LPC32XX_TIMER_TCR		0x004
+#define  LPC32XX_TIMER_TCR_CEN		BIT(0)
+#define  LPC32XX_TIMER_TCR_CRST		BIT(1)
+#define LPC32XX_TIMER_TC		0x008
+#define LPC32XX_TIMER_PR		0x00c
+#define LPC32XX_TIMER_MCR		0x014
+#define  LPC32XX_TIMER_MCR_MR0I		BIT(0)
+#define  LPC32XX_TIMER_MCR_MR0R		BIT(1)
+#define  LPC32XX_TIMER_MCR_MR0S		BIT(2)
+#define LPC32XX_TIMER_MR0		0x018
+#define LPC32XX_TIMER_CTCR		0x070
+
+struct lpc32xx_clock_event_ddata {
+	struct clock_event_device evtdev;
+	void __iomem *base;
+};
+
+/* Needed for the sched clock */
+static void __iomem *clocksource_timer_counter;
+
+static u64 notrace lpc32xx_read_sched_clock(void)
+{
+	return readl(clocksource_timer_counter);
+}
+
+static int lpc32xx_clkevt_next_event(unsigned long delta,
+				     struct clock_event_device *evtdev)
+{
+	struct lpc32xx_clock_event_ddata *ddata =
+		container_of(evtdev, struct lpc32xx_clock_event_ddata, evtdev);
+
+	/*
+	 * Place timer in reset and program the delta in the prescale
+	 * register (PR). When the prescale counter matches the value
+	 * in PR the counter register is incremented and the compare
+	 * match will trigger. After setup the timer is released from
+	 * reset and enabled.
+	 */
+	writel_relaxed(LPC32XX_TIMER_TCR_CRST, ddata->base + LPC32XX_TIMER_TCR);
+	writel_relaxed(delta, ddata->base + LPC32XX_TIMER_PR);
+	writel_relaxed(LPC32XX_TIMER_TCR_CEN, ddata->base + LPC32XX_TIMER_TCR);
+
+	return 0;
+}
+
+static int lpc32xx_clkevt_shutdown(struct clock_event_device *evtdev)
+{
+	struct lpc32xx_clock_event_ddata *ddata =
+		container_of(evtdev, struct lpc32xx_clock_event_ddata, evtdev);
+
+	/* Disable the timer */
+	writel_relaxed(0, ddata->base + LPC32XX_TIMER_TCR);
+
+	return 0;
+}
+
+static int lpc32xx_clkevt_oneshot(struct clock_event_device *evtdev)
+{
+	/*
+	 * When using oneshot, we must also disable the timer
+	 * to wait for the first call to set_next_event().
+	 */
+	return lpc32xx_clkevt_shutdown(evtdev);
+}
+
+static irqreturn_t lpc32xx_clock_event_handler(int irq, void *dev_id)
+{
+	struct lpc32xx_clock_event_ddata *ddata = dev_id;
+
+	/* Clear match on channel 0 */
+	writel_relaxed(LPC32XX_TIMER_IR_MR0INT, ddata->base + LPC32XX_TIMER_IR);
+
+	ddata->evtdev.event_handler(&ddata->evtdev);
+
+	return IRQ_HANDLED;
+}
+
+static struct lpc32xx_clock_event_ddata lpc32xx_clk_event_ddata = {
+	.evtdev = {
+		.name			= "lpc3220 clockevent",
+		.features		= CLOCK_EVT_FEAT_ONESHOT,
+		.rating			= 300,
+		.set_next_event		= lpc32xx_clkevt_next_event,
+		.set_state_shutdown	= lpc32xx_clkevt_shutdown,
+		.set_state_oneshot	= lpc32xx_clkevt_oneshot,
+	},
+};
+
+static int __init lpc32xx_clocksource_init(struct device_node *np)
+{
+	void __iomem *base;
+	unsigned long rate;
+	struct clk *clk;
+	int ret;
+
+	clk = of_clk_get_by_name(np, "timerclk");
+	if (IS_ERR(clk)) {
+		pr_err("clock get failed (%lu)\n", PTR_ERR(clk));
+		return PTR_ERR(clk);
+	}
+
+	ret = clk_prepare_enable(clk);
+	if (ret) {
+		pr_err("clock enable failed (%d)\n", ret);
+		goto err_clk_enable;
+	}
+
+	base = of_iomap(np, 0);
+	if (!base) {
+		pr_err("unable to map registers\n");
+		ret = -EADDRNOTAVAIL;
+		goto err_iomap;
+	}
+
+	/*
+	 * Disable and reset timer then set it to free running timer
+	 * mode (CTCR) with no prescaler (PR) or match operations (MCR).
+	 * After setup the timer is released from reset and enabled.
+	 */
+	writel_relaxed(LPC32XX_TIMER_TCR_CRST, base + LPC32XX_TIMER_TCR);
+	writel_relaxed(0, base + LPC32XX_TIMER_PR);
+	writel_relaxed(0, base + LPC32XX_TIMER_MCR);
+	writel_relaxed(0, base + LPC32XX_TIMER_CTCR);
+	writel_relaxed(LPC32XX_TIMER_TCR_CEN, base + LPC32XX_TIMER_TCR);
+
+	rate = clk_get_rate(clk);
+	ret = clocksource_mmio_init(base + LPC32XX_TIMER_TC, "lpc3220 timer",
+				    rate, 300, 32, clocksource_mmio_readl_up);
+	if (ret) {
+		pr_err("failed to init clocksource (%d)\n", ret);
+		goto err_clocksource_init;
+	}
+
+	clocksource_timer_counter = base + LPC32XX_TIMER_TC;
+	sched_clock_register(lpc32xx_read_sched_clock, 32, rate);
+
+	return 0;
+
+err_clocksource_init:
+	iounmap(base);
+err_iomap:
+	clk_disable_unprepare(clk);
+err_clk_enable:
+	clk_put(clk);
+	return ret;
+}
+
+static int __init lpc32xx_clockevent_init(struct device_node *np)
+{
+	void __iomem *base;
+	unsigned long rate;
+	struct clk *clk;
+	int ret, irq;
+
+	clk = of_clk_get_by_name(np, "timerclk");
+	if (IS_ERR(clk)) {
+		pr_err("clock get failed (%lu)\n", PTR_ERR(clk));
+		return PTR_ERR(clk);
+	}
+
+	ret = clk_prepare_enable(clk);
+	if (ret) {
+		pr_err("clock enable failed (%d)\n", ret);
+		goto err_clk_enable;
+	}
+
+	base = of_iomap(np, 0);
+	if (!base) {
+		pr_err("unable to map registers\n");
+		ret = -EADDRNOTAVAIL;
+		goto err_iomap;
+	}
+
+	irq = irq_of_parse_and_map(np, 0);
+	if (!irq) {
+		pr_err("get irq failed\n");
+		ret = -ENOENT;
+		goto err_irq;
+	}
+
+	/*
+	 * Disable timer and clear any pending interrupt (IR) on match
+	 * channel 0 (MR0). Configure a compare match value of 1 on MR0
+	 * and enable interrupt, reset on match and stop on match (MCR).
+	 */
+	writel_relaxed(0, base + LPC32XX_TIMER_TCR);
+	writel_relaxed(0, base + LPC32XX_TIMER_CTCR);
+	writel_relaxed(LPC32XX_TIMER_IR_MR0INT, base + LPC32XX_TIMER_IR);
+	writel_relaxed(1, base + LPC32XX_TIMER_MR0);
+	writel_relaxed(LPC32XX_TIMER_MCR_MR0I | LPC32XX_TIMER_MCR_MR0R |
+		       LPC32XX_TIMER_MCR_MR0S, base + LPC32XX_TIMER_MCR);
+
+	rate = clk_get_rate(clk);
+	lpc32xx_clk_event_ddata.base = base;
+	clockevents_config_and_register(&lpc32xx_clk_event_ddata.evtdev,
+					rate, 1, -1);
+
+	ret = request_irq(irq, lpc32xx_clock_event_handler,
+			  IRQF_TIMER | IRQF_IRQPOLL, "lpc3220 clockevent",
+			  &lpc32xx_clk_event_ddata);
+	if (ret) {
+		pr_err("request irq failed\n");
+		goto err_irq;
+	}
+
+	return 0;
+
+err_irq:
+	iounmap(base);
+err_iomap:
+	clk_disable_unprepare(clk);
+err_clk_enable:
+	clk_put(clk);
+	return ret;
+}
+
+/*
+ * This function asserts that we have exactly one clocksource and one
+ * clock_event_device in the end.
+ */
+static void __init lpc32xx_timer_init(struct device_node *np)
+{
+	static int has_clocksource, has_clockevent;
+	int ret;
+
+	if (!has_clocksource) {
+		ret = lpc32xx_clocksource_init(np);
+		if (!ret) {
+			has_clocksource = 1;
+			return;
+		}
+	}
+
+	if (!has_clockevent) {
+		ret = lpc32xx_clockevent_init(np);
+		if (!ret) {
+			has_clockevent = 1;
+			return;
+		}
+	}
+}
+CLOCKSOURCE_OF_DECLARE(lpc32xx_timer, "nxp,lpc3220-timer", lpc32xx_timer_init);

drivers/clocksource/timer-integrator-ap.c

@@ -166,7 +166,7 @@ static void __init integrator_ap_timer_init_of(struct device_node *node)
 	struct device_node *sec_node;
 
 	base = of_io_request_and_map(node, 0, "integrator-timer");
-	if (!base)
+	if (IS_ERR(base))
 		return;
 
 	clk = of_clk_get(node, 0);

drivers/clocksource/timer-stm32.c

@@ -0,0 +1,184 @@
+/*
+ * Copyright (C) Maxime Coquelin 2015
+ * Author:  Maxime Coquelin <mcoquelin.stm32@gmail.com>
+ * License terms:  GNU General Public License (GPL), version 2
+ *
+ * Inspired by time-efm32.c from Uwe Kleine-Koenig
+ */
+
+#include <linux/kernel.h>
+#include <linux/clocksource.h>
+#include <linux/clockchips.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/clk.h>
+#include <linux/reset.h>
+
+#define TIM_CR1		0x00
+#define TIM_DIER	0x0c
+#define TIM_SR		0x10
+#define TIM_EGR		0x14
+#define TIM_PSC		0x28
+#define TIM_ARR		0x2c
+
+#define TIM_CR1_CEN	BIT(0)
+#define TIM_CR1_OPM	BIT(3)
+#define TIM_CR1_ARPE	BIT(7)
+
+#define TIM_DIER_UIE	BIT(0)
+
+#define TIM_SR_UIF	BIT(0)
+
+#define TIM_EGR_UG	BIT(0)
+
+struct stm32_clock_event_ddata {
+	struct clock_event_device evtdev;
+	unsigned periodic_top;
+	void __iomem *base;
+};
+
+static void stm32_clock_event_set_mode(enum clock_event_mode mode,
+				       struct clock_event_device *evtdev)
+{
+	struct stm32_clock_event_ddata *data =
+		container_of(evtdev, struct stm32_clock_event_ddata, evtdev);
+	void *base = data->base;
+
+	switch (mode) {
+	case CLOCK_EVT_MODE_PERIODIC:
+		writel_relaxed(data->periodic_top, base + TIM_ARR);
+		writel_relaxed(TIM_CR1_ARPE | TIM_CR1_CEN, base + TIM_CR1);
+		break;
+
+	case CLOCK_EVT_MODE_ONESHOT:
+	default:
+		writel_relaxed(0, base + TIM_CR1);
+		break;
+	}
+}
+
+static int stm32_clock_event_set_next_event(unsigned long evt,
+					    struct clock_event_device *evtdev)
+{
+	struct stm32_clock_event_ddata *data =
+		container_of(evtdev, struct stm32_clock_event_ddata, evtdev);
+
+	writel_relaxed(evt, data->base + TIM_ARR);
+	writel_relaxed(TIM_CR1_ARPE | TIM_CR1_OPM | TIM_CR1_CEN,
+		       data->base + TIM_CR1);
+
+	return 0;
+}
+
+static irqreturn_t stm32_clock_event_handler(int irq, void *dev_id)
+{
+	struct stm32_clock_event_ddata *data = dev_id;
+
+	writel_relaxed(0, data->base + TIM_SR);
+
+	data->evtdev.event_handler(&data->evtdev);
+
+	return IRQ_HANDLED;
+}
+
+static struct stm32_clock_event_ddata clock_event_ddata = {
+	.evtdev = {
+		.name = "stm32 clockevent",
+		.features = CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_PERIODIC,
+		.set_mode = stm32_clock_event_set_mode,
+		.set_next_event = stm32_clock_event_set_next_event,
+		.rating = 200,
+	},
+};
+
+static void __init stm32_clockevent_init(struct device_node *np)
+{
+	struct stm32_clock_event_ddata *data = &clock_event_ddata;
+	struct clk *clk;
+	struct reset_control *rstc;
+	unsigned long rate, max_delta;
+	int irq, ret, bits, prescaler = 1;
+
+	clk = of_clk_get(np, 0);
+	if (IS_ERR(clk)) {
+		ret = PTR_ERR(clk);
+		pr_err("failed to get clock for clockevent (%d)\n", ret);
+		goto err_clk_get;
+	}
+
+	ret = clk_prepare_enable(clk);
+	if (ret) {
+		pr_err("failed to enable timer clock for clockevent (%d)\n",
+		       ret);
+		goto err_clk_enable;
+	}
+
+	rate = clk_get_rate(clk);
+
+	rstc = of_reset_control_get(np, NULL);
+	if (!IS_ERR(rstc)) {
+		reset_control_assert(rstc);
+		reset_control_deassert(rstc);
+	}
+
+	data->base = of_iomap(np, 0);
+	if (!data->base) {
+		pr_err("failed to map registers for clockevent\n");
+		goto err_iomap;
+	}
+
+	irq = irq_of_parse_and_map(np, 0);
+	if (!irq) {
+		pr_err("%s: failed to get irq.\n", np->full_name);
+		goto err_get_irq;
+	}
+
+	/* Detect whether the timer is 16 or 32 bits */
+	writel_relaxed(~0U, data->base + TIM_ARR);
+	max_delta = readl_relaxed(data->base + TIM_ARR);
+	if (max_delta == ~0U) {
+		prescaler = 1;
+		bits = 32;
+	} else {
+		prescaler = 1024;
+		bits = 16;
+	}
+	writel_relaxed(0, data->base + TIM_ARR);
+
+	writel_relaxed(prescaler - 1, data->base + TIM_PSC);
+	writel_relaxed(TIM_EGR_UG, data->base + TIM_EGR);
+	writel_relaxed(TIM_DIER_UIE, data->base + TIM_DIER);
+	writel_relaxed(0, data->base + TIM_SR);
+
+	data->periodic_top = DIV_ROUND_CLOSEST(rate, prescaler * HZ);
+
+	clockevents_config_and_register(&data->evtdev,
+					DIV_ROUND_CLOSEST(rate, prescaler),
+					0x1, max_delta);
+
+	ret = request_irq(irq, stm32_clock_event_handler, IRQF_TIMER,
+			"stm32 clockevent", data);
+	if (ret) {
+		pr_err("%s: failed to request irq.\n", np->full_name);
+		goto err_get_irq;
+	}
+
+	pr_info("%s: STM32 clockevent driver initialized (%d bits)\n",
+			np->full_name, bits);
+
+	return;
+
+err_get_irq:
+	iounmap(data->base);
+err_iomap:
+	clk_disable_unprepare(clk);
+err_clk_enable:
+	clk_put(clk);
+err_clk_get:
+	return;
+}
+
+CLOCKSOURCE_OF_DECLARE(stm32, "st,stm32-timer", stm32_clockevent_init);

drivers/clocksource/timer-sun5i.c

@@ -324,7 +324,7 @@ static void __init sun5i_timer_init(struct device_node *node)
 	int irq;
 
 	timer_base = of_io_request_and_map(node, 0, of_node_full_name(node));
-	if (!timer_base)
+	if (IS_ERR(timer_base))
 		panic("Can't map registers");
 
 	irq = irq_of_parse_and_map(node, 0);

drivers/power/reset/ltc2952-poweroff.c

@@ -158,7 +158,6 @@ static irqreturn_t ltc2952_poweroff_handler(int irq, void *dev_id)
 			      HRTIMER_MODE_REL);
 	} else {
 		hrtimer_cancel(&data->timer_trigger);
-		/* omitting return value check, timer should have been valid */
 	}
 	return IRQ_HANDLED;
 }

fs/dcache.c

@@ -322,17 +322,17 @@ static void dentry_free(struct dentry *dentry)
 }
 
 /**
- * dentry_rcuwalk_barrier - invalidate in-progress rcu-walk lookups
+ * dentry_rcuwalk_invalidate - invalidate in-progress rcu-walk lookups
  * @dentry: the target dentry
  * After this call, in-progress rcu-walk path lookup will fail. This
  * should be called after unhashing, and after changing d_inode (if
  * the dentry has not already been unhashed).
  */
-static inline void dentry_rcuwalk_barrier(struct dentry *dentry)
+static inline void dentry_rcuwalk_invalidate(struct dentry *dentry)
 {
-	assert_spin_locked(&dentry->d_lock);
-	/* Go through a barrier */
-	write_seqcount_barrier(&dentry->d_seq);
+	lockdep_assert_held(&dentry->d_lock);
+	/* Go through am invalidation barrier */
+	write_seqcount_invalidate(&dentry->d_seq);
 }
 
 /*
@@ -372,7 +372,7 @@ static void dentry_unlink_inode(struct dentry * dentry)
 	struct inode *inode = dentry->d_inode;
 	__d_clear_type_and_inode(dentry);
 	hlist_del_init(&dentry->d_u.d_alias);
-	dentry_rcuwalk_barrier(dentry);
+	dentry_rcuwalk_invalidate(dentry);
 	spin_unlock(&dentry->d_lock);
 	spin_unlock(&inode->i_lock);
 	if (!inode->i_nlink)
@@ -494,7 +494,7 @@ void __d_drop(struct dentry *dentry)
 		__hlist_bl_del(&dentry->d_hash);
 		dentry->d_hash.pprev = NULL;
 		hlist_bl_unlock(b);
-		dentry_rcuwalk_barrier(dentry);
+		dentry_rcuwalk_invalidate(dentry);
 	}
 }
 EXPORT_SYMBOL(__d_drop);
@@ -1752,7 +1752,7 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode)
 	if (inode)
 		hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry);
 	__d_set_inode_and_type(dentry, inode, add_flags);
-	dentry_rcuwalk_barrier(dentry);
+	dentry_rcuwalk_invalidate(dentry);
 	spin_unlock(&dentry->d_lock);
 	fsnotify_d_instantiate(dentry, inode);
 }

include/linux/alarmtimer.h

@@ -43,8 +43,8 @@ struct alarm {
 
 void alarm_init(struct alarm *alarm, enum alarmtimer_type type,
 		enum alarmtimer_restart (*function)(struct alarm *, ktime_t));
-int alarm_start(struct alarm *alarm, ktime_t start);
-int alarm_start_relative(struct alarm *alarm, ktime_t start);
+void alarm_start(struct alarm *alarm, ktime_t start);
+void alarm_start_relative(struct alarm *alarm, ktime_t start);
 void alarm_restart(struct alarm *alarm);
 int alarm_try_to_cancel(struct alarm *alarm);
 int alarm_cancel(struct alarm *alarm);

include/linux/clockchips.h

@@ -37,12 +37,15 @@ enum clock_event_mode {
  *		reached from DETACHED or SHUTDOWN.
  * ONESHOT:	Device is programmed to generate event only once. Can be reached
  *		from DETACHED or SHUTDOWN.
+ * ONESHOT_STOPPED: Device was programmed in ONESHOT mode and is temporarily
+ *		    stopped.
  */
 enum clock_event_state {
 	CLOCK_EVT_STATE_DETACHED,
 	CLOCK_EVT_STATE_SHUTDOWN,
 	CLOCK_EVT_STATE_PERIODIC,
 	CLOCK_EVT_STATE_ONESHOT,
+	CLOCK_EVT_STATE_ONESHOT_STOPPED,
 };
 
 /*
@@ -84,12 +87,13 @@ enum clock_event_state {
  * @mult:		nanosecond to cycles multiplier
  * @shift:		nanoseconds to cycles divisor (power of two)
  * @mode:		operating mode, relevant only to ->set_mode(), OBSOLETE
- * @state:		current state of the device, assigned by the core code
+ * @state_use_accessors:current state of the device, assigned by the core code
  * @features:		features
  * @retries:		number of forced programming retries
  * @set_mode:		legacy set mode function, only for modes <= CLOCK_EVT_MODE_RESUME.
  * @set_state_periodic:	switch state to periodic, if !set_mode
  * @set_state_oneshot:	switch state to oneshot, if !set_mode
+ * @set_state_oneshot_stopped: switch state to oneshot_stopped, if !set_mode
  * @set_state_shutdown:	switch state to shutdown, if !set_mode
  * @tick_resume:	resume clkevt device, if !set_mode
  * @broadcast:		function to broadcast events
@@ -113,7 +117,7 @@ struct clock_event_device {
 	u32			mult;
 	u32			shift;
 	enum clock_event_mode	mode;
-	enum clock_event_state	state;
+	enum clock_event_state	state_use_accessors;
 	unsigned int		features;
 	unsigned long		retries;
 
@@ -121,11 +125,12 @@ struct clock_event_device {
 	 * State transition callback(s): Only one of the two groups should be
 	 * defined:
 	 * - set_mode(), only for modes <= CLOCK_EVT_MODE_RESUME.
-	 * - set_state_{shutdown|periodic|oneshot}(), tick_resume().
+	 * - set_state_{shutdown|periodic|oneshot|oneshot_stopped}(), tick_resume().
 	 */
 	void			(*set_mode)(enum clock_event_mode mode, struct clock_event_device *);
 	int			(*set_state_periodic)(struct clock_event_device *);
 	int			(*set_state_oneshot)(struct clock_event_device *);
+	int			(*set_state_oneshot_stopped)(struct clock_event_device *);
 	int			(*set_state_shutdown)(struct clock_event_device *);
 	int			(*tick_resume)(struct clock_event_device *);
 
@@ -144,6 +149,32 @@ struct clock_event_device {
 	struct module		*owner;
 } ____cacheline_aligned;
 
+/* Helpers to verify state of a clockevent device */
+static inline bool clockevent_state_detached(struct clock_event_device *dev)
+{
+	return dev->state_use_accessors == CLOCK_EVT_STATE_DETACHED;
+}
+
+static inline bool clockevent_state_shutdown(struct clock_event_device *dev)
+{
+	return dev->state_use_accessors == CLOCK_EVT_STATE_SHUTDOWN;
+}
+
+static inline bool clockevent_state_periodic(struct clock_event_device *dev)
+{
+	return dev->state_use_accessors == CLOCK_EVT_STATE_PERIODIC;
+}
+
+static inline bool clockevent_state_oneshot(struct clock_event_device *dev)
+{
+	return dev->state_use_accessors == CLOCK_EVT_STATE_ONESHOT;
+}
+
+static inline bool clockevent_state_oneshot_stopped(struct clock_event_device *dev)
+{
+	return dev->state_use_accessors == CLOCK_EVT_STATE_ONESHOT_STOPPED;
+}
+
 /*
  * Calculate a multiplication factor for scaled math, which is used to convert
  * nanoseconds based values to clock ticks:

include/linux/clocksource.h

@@ -181,7 +181,6 @@ static inline s64 clocksource_cyc2ns(cycle_t cycles, u32 mult, u32 shift)
 
 extern int clocksource_unregister(struct clocksource*);
 extern void clocksource_touch_watchdog(void);
-extern struct clocksource* clocksource_get_next(void);
 extern void clocksource_change_rating(struct clocksource *cs, int rating);
 extern void clocksource_suspend(void);
 extern void clocksource_resume(void);

include/linux/hrtimer.h

@@ -53,34 +53,25 @@ enum hrtimer_restart {
  *
  * 0x00		inactive
  * 0x01		enqueued into rbtree
- * 0x02		callback function running
- * 0x04		timer is migrated to another cpu
  *
- * Special cases:
- * 0x03		callback function running and enqueued
- *		(was requeued on another CPU)
- * 0x05		timer was migrated on CPU hotunplug
+ * The callback state is not part of the timer->state because clearing it would
+ * mean touching the timer after the callback, this makes it impossible to free
+ * the timer from the callback function.
  *
- * The "callback function running and enqueued" status is only possible on
- * SMP. It happens for example when a posix timer expired and the callback
+ * Therefore we track the callback state in:
+ *
+ *	timer->base->cpu_base->running == timer
+ *
+ * On SMP it is possible to have a "callback function running and enqueued"
+ * status. It happens for example when a posix timer expired and the callback
  * queued a signal. Between dropping the lock which protects the posix timer
  * and reacquiring the base lock of the hrtimer, another CPU can deliver the
- * signal and rearm the timer. We have to preserve the callback running state,
- * as otherwise the timer could be removed before the softirq code finishes the
- * the handling of the timer.
- *
- * The HRTIMER_STATE_ENQUEUED bit is always or'ed to the current state
- * to preserve the HRTIMER_STATE_CALLBACK in the above scenario. This
- * also affects HRTIMER_STATE_MIGRATE where the preservation is not
- * necessary. HRTIMER_STATE_MIGRATE is cleared after the timer is
- * enqueued on the new cpu.
+ * signal and rearm the timer.
  *
  * All state transitions are protected by cpu_base->lock.
  */
 #define HRTIMER_STATE_INACTIVE	0x00
 #define HRTIMER_STATE_ENQUEUED	0x01
-#define HRTIMER_STATE_CALLBACK	0x02
-#define HRTIMER_STATE_MIGRATE	0x04
 
 /**
  * struct hrtimer - the basic hrtimer structure
@@ -130,6 +121,12 @@ struct hrtimer_sleeper {
 	struct task_struct *task;
 };
 
+#ifdef CONFIG_64BIT
+# define HRTIMER_CLOCK_BASE_ALIGN	64
+#else
+# define HRTIMER_CLOCK_BASE_ALIGN	32
+#endif
+
 /**
  * struct hrtimer_clock_base - the timer base for a specific clock
  * @cpu_base:		per cpu clock base
@@ -137,9 +134,7 @@ struct hrtimer_sleeper {
  *			timer to a base on another cpu.
  * @clockid:		clock id for per_cpu support
  * @active:		red black tree root node for the active timers
- * @resolution:		the resolution of the clock, in nanoseconds
  * @get_time:		function to retrieve the current time of the clock
- * @softirq_time:	the time when running the hrtimer queue in the softirq
  * @offset:		offset of this clock to the monotonic base
  */
 struct hrtimer_clock_base {
@@ -147,11 +142,9 @@ struct hrtimer_clock_base {
 	int			index;
 	clockid_t		clockid;
 	struct timerqueue_head	active;
-	ktime_t			resolution;
 	ktime_t			(*get_time)(void);
-	ktime_t			softirq_time;
 	ktime_t			offset;
-};
+} __attribute__((__aligned__(HRTIMER_CLOCK_BASE_ALIGN)));
 
 enum  hrtimer_base_type {
 	HRTIMER_BASE_MONOTONIC,
@@ -165,11 +158,14 @@ enum  hrtimer_base_type {
  * struct hrtimer_cpu_base - the per cpu clock bases
  * @lock:		lock protecting the base and associated clock bases
  *			and timers
+ * @seq:		seqcount around __run_hrtimer
+ * @running:		pointer to the currently running hrtimer
  * @cpu:		cpu number
  * @active_bases:	Bitfield to mark bases with active timers
- * @clock_was_set:	Indicates that clock was set from irq context.
+ * @clock_was_set_seq:	Sequence counter of clock was set events
  * @expires_next:	absolute time of the next event which was scheduled
  *			via clock_set_next_event()
+ * @next_timer:		Pointer to the first expiring timer
  * @in_hrtirq:		hrtimer_interrupt() is currently executing
  * @hres_active:	State of high resolution mode
  * @hang_detected:	The last hrtimer interrupt detected a hang
@@ -178,27 +174,36 @@ enum  hrtimer_base_type {
  * @nr_hangs:		Total number of hrtimer interrupt hangs
  * @max_hang_time:	Maximum time spent in hrtimer_interrupt
  * @clock_base:		array of clock bases for this cpu
+ *
+ * Note: next_timer is just an optimization for __remove_hrtimer().
+ *	 Do not dereference the pointer because it is not reliable on
+ *	 cross cpu removals.
  */
 struct hrtimer_cpu_base {
 	raw_spinlock_t			lock;
+	seqcount_t			seq;
+	struct hrtimer			*running;
 	unsigned int			cpu;
 	unsigned int			active_bases;
-	unsigned int			clock_was_set;
+	unsigned int			clock_was_set_seq;
 #ifdef CONFIG_HIGH_RES_TIMERS
+	unsigned int			in_hrtirq	: 1,
+					hres_active	: 1,
+					hang_detected	: 1;
 	ktime_t				expires_next;
-	int				in_hrtirq;
-	int				hres_active;
-	int				hang_detected;
-	unsigned long			nr_events;
-	unsigned long			nr_retries;
-	unsigned long			nr_hangs;
-	ktime_t				max_hang_time;
+	struct hrtimer			*next_timer;
+	unsigned int			nr_events;
+	unsigned int			nr_retries;
+	unsigned int			nr_hangs;
+	unsigned int			max_hang_time;
 #endif
 	struct hrtimer_clock_base	clock_base[HRTIMER_MAX_CLOCK_BASES];
-};
+} ____cacheline_aligned;
 
 static inline void hrtimer_set_expires(struct hrtimer *timer, ktime_t time)
 {
+	BUILD_BUG_ON(sizeof(struct hrtimer_clock_base) > HRTIMER_CLOCK_BASE_ALIGN);
+
 	timer->node.expires = time;
 	timer->_softexpires = time;
 }
@@ -262,19 +267,16 @@ static inline ktime_t hrtimer_expires_remaining(const struct hrtimer *timer)
 	return ktime_sub(timer->node.expires, timer->base->get_time());
 }
 
-#ifdef CONFIG_HIGH_RES_TIMERS
-struct clock_event_device;
-
-extern void hrtimer_interrupt(struct clock_event_device *dev);
-
-/*
- * In high resolution mode the time reference must be read accurate
- */
 static inline ktime_t hrtimer_cb_get_time(struct hrtimer *timer)
 {
 	return timer->base->get_time();
 }
 
+#ifdef CONFIG_HIGH_RES_TIMERS
+struct clock_event_device;
+
+extern void hrtimer_interrupt(struct clock_event_device *dev);
+
 static inline int hrtimer_is_hres_active(struct hrtimer *timer)
 {
 	return timer->base->cpu_base->hres_active;
@@ -295,21 +297,16 @@ extern void hrtimer_peek_ahead_timers(void);
 
 extern void clock_was_set_delayed(void);
 
+extern unsigned int hrtimer_resolution;
+
 #else
 
 # define MONOTONIC_RES_NSEC	LOW_RES_NSEC
 # define KTIME_MONOTONIC_RES	KTIME_LOW_RES
 
-static inline void hrtimer_peek_ahead_timers(void) { }
+#define hrtimer_resolution	(unsigned int)LOW_RES_NSEC
 
-/*
- * In non high resolution mode the time reference is taken from
- * the base softirq time variable.
- */
-static inline ktime_t hrtimer_cb_get_time(struct hrtimer *timer)
-{
-	return timer->base->softirq_time;
-}
+static inline void hrtimer_peek_ahead_timers(void) { }
 
 static inline int hrtimer_is_hres_active(struct hrtimer *timer)
 {
@@ -353,49 +350,47 @@ static inline void destroy_hrtimer_on_stack(struct hrtimer *timer) { }
 #endif
 
 /* Basic timer operations: */
-extern int hrtimer_start(struct hrtimer *timer, ktime_t tim,
-			 const enum hrtimer_mode mode);
-extern int hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
+extern void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 			unsigned long range_ns, const enum hrtimer_mode mode);
-extern int
-__hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
-			 unsigned long delta_ns,
-			 const enum hrtimer_mode mode, int wakeup);
+
+/**
+ * hrtimer_start - (re)start an hrtimer on the current CPU
+ * @timer:	the timer to be added
+ * @tim:	expiry time
+ * @mode:	expiry mode: absolute (HRTIMER_MODE_ABS) or
+ *		relative (HRTIMER_MODE_REL)
+ */
+static inline void hrtimer_start(struct hrtimer *timer, ktime_t tim,
+				 const enum hrtimer_mode mode)
+{
+	hrtimer_start_range_ns(timer, tim, 0, mode);
+}
 
 extern int hrtimer_cancel(struct hrtimer *timer);
 extern int hrtimer_try_to_cancel(struct hrtimer *timer);
 
-static inline int hrtimer_start_expires(struct hrtimer *timer,
-						enum hrtimer_mode mode)
+static inline void hrtimer_start_expires(struct hrtimer *timer,
+					 enum hrtimer_mode mode)
 {
 	unsigned long delta;
 	ktime_t soft, hard;
 	soft = hrtimer_get_softexpires(timer);
 	hard = hrtimer_get_expires(timer);
 	delta = ktime_to_ns(ktime_sub(hard, soft));
-	return hrtimer_start_range_ns(timer, soft, delta, mode);
+	hrtimer_start_range_ns(timer, soft, delta, mode);
 }
 
-static inline int hrtimer_restart(struct hrtimer *timer)
+static inline void hrtimer_restart(struct hrtimer *timer)
 {
-	return hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
+	hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
 }
 
 /* Query timers: */
 extern ktime_t hrtimer_get_remaining(const struct hrtimer *timer);
-extern int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp);
 
-extern ktime_t hrtimer_get_next_event(void);
+extern u64 hrtimer_get_next_event(void);
 
-/*
- * A timer is active, when it is enqueued into the rbtree or the
- * callback function is running or it's in the state of being migrated
- * to another cpu.
- */
-static inline int hrtimer_active(const struct hrtimer *timer)
-{
-	return timer->state != HRTIMER_STATE_INACTIVE;
-}
+extern bool hrtimer_active(const struct hrtimer *timer);
 
 /*
  * Helper function to check, whether the timer is on one of the queues
@@ -411,14 +406,29 @@ static inline int hrtimer_is_queued(struct hrtimer *timer)
  */
 static inline int hrtimer_callback_running(struct hrtimer *timer)
 {
-	return timer->state & HRTIMER_STATE_CALLBACK;
+	return timer->base->cpu_base->running == timer;
 }
 
 /* Forward a hrtimer so it expires after now: */
 extern u64
 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval);
 
-/* Forward a hrtimer so it expires after the hrtimer's current now */
+/**
+ * hrtimer_forward_now - forward the timer expiry so it expires after now
+ * @timer:	hrtimer to forward
+ * @interval:	the interval to forward
+ *
+ * Forward the timer expiry so it will expire after the current time
+ * of the hrtimer clock base. Returns the number of overruns.
+ *
+ * Can be safely called from the callback function of @timer. If
+ * called from other contexts @timer must neither be enqueued nor
+ * running the callback and the caller needs to take care of
+ * serialization.
+ *
+ * Note: This only updates the timer expiry value and does not requeue
+ * the timer.
+ */
 static inline u64 hrtimer_forward_now(struct hrtimer *timer,
 				      ktime_t interval)
 {
@@ -443,7 +453,6 @@ extern int schedule_hrtimeout(ktime_t *expires, const enum hrtimer_mode mode);
 
 /* Soft interrupt function to run the hrtimer queues: */
 extern void hrtimer_run_queues(void);
-extern void hrtimer_run_pending(void);
 
 /* Bootup initialization: */
 extern void __init hrtimers_init(void);

include/linux/interrupt.h

@@ -413,7 +413,8 @@ enum
 	BLOCK_IOPOLL_SOFTIRQ,
 	TASKLET_SOFTIRQ,
 	SCHED_SOFTIRQ,
-	HRTIMER_SOFTIRQ,
+	HRTIMER_SOFTIRQ, /* Unused, but kept as tools rely on the
+			    numbering. Sigh! */
 	RCU_SOFTIRQ,    /* Preferable RCU should always be the last softirq */
 
 	NR_SOFTIRQS
@@ -592,10 +593,10 @@ tasklet_hrtimer_init(struct tasklet_hrtimer *ttimer,
 		     clockid_t which_clock, enum hrtimer_mode mode);
 
 static inline
-int tasklet_hrtimer_start(struct tasklet_hrtimer *ttimer, ktime_t time,
-			  const enum hrtimer_mode mode)
+void tasklet_hrtimer_start(struct tasklet_hrtimer *ttimer, ktime_t time,
+			   const enum hrtimer_mode mode)
 {
-	return hrtimer_start(&ttimer->timer, time, mode);
+	hrtimer_start(&ttimer->timer, time, mode);
 }
 
 static inline

include/linux/jiffies.h

@@ -7,6 +7,7 @@
 #include <linux/time.h>
 #include <linux/timex.h>
 #include <asm/param.h>			/* for HZ */
+#include <generated/timeconst.h>
 
 /*
  * The following defines establish the engineering parameters of the PLL
@@ -288,8 +289,133 @@ static inline u64 jiffies_to_nsecs(const unsigned long j)
 	return (u64)jiffies_to_usecs(j) * NSEC_PER_USEC;
 }
 
-extern unsigned long msecs_to_jiffies(const unsigned int m);
-extern unsigned long usecs_to_jiffies(const unsigned int u);
+extern unsigned long __msecs_to_jiffies(const unsigned int m);
+#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ)
+/*
+ * HZ is equal to or smaller than 1000, and 1000 is a nice round
+ * multiple of HZ, divide with the factor between them, but round
+ * upwards:
+ */
+static inline unsigned long _msecs_to_jiffies(const unsigned int m)
+{
+	return (m + (MSEC_PER_SEC / HZ) - 1) / (MSEC_PER_SEC / HZ);
+}
+#elif HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC)
+/*
+ * HZ is larger than 1000, and HZ is a nice round multiple of 1000 -
+ * simply multiply with the factor between them.
+ *
+ * But first make sure the multiplication result cannot overflow:
+ */
+static inline unsigned long _msecs_to_jiffies(const unsigned int m)
+{
+	if (m > jiffies_to_msecs(MAX_JIFFY_OFFSET))
+		return MAX_JIFFY_OFFSET;
+	return m * (HZ / MSEC_PER_SEC);
+}
+#else
+/*
+ * Generic case - multiply, round and divide. But first check that if
+ * we are doing a net multiplication, that we wouldn't overflow:
+ */
+static inline unsigned long _msecs_to_jiffies(const unsigned int m)
+{
+	if (HZ > MSEC_PER_SEC && m > jiffies_to_msecs(MAX_JIFFY_OFFSET))
+		return MAX_JIFFY_OFFSET;
+
+	return (MSEC_TO_HZ_MUL32 * m + MSEC_TO_HZ_ADJ32) >> MSEC_TO_HZ_SHR32;
+}
+#endif
+/**
+ * msecs_to_jiffies: - convert milliseconds to jiffies
+ * @m:	time in milliseconds
+ *
+ * conversion is done as follows:
+ *
+ * - negative values mean 'infinite timeout' (MAX_JIFFY_OFFSET)
+ *
+ * - 'too large' values [that would result in larger than
+ *   MAX_JIFFY_OFFSET values] mean 'infinite timeout' too.
+ *
+ * - all other values are converted to jiffies by either multiplying
+ *   the input value by a factor or dividing it with a factor and
+ *   handling any 32-bit overflows.
+ *   for the details see __msecs_to_jiffies()
+ *
+ * msecs_to_jiffies() checks for the passed in value being a constant
+ * via __builtin_constant_p() allowing gcc to eliminate most of the
+ * code, __msecs_to_jiffies() is called if the value passed does not
+ * allow constant folding and the actual conversion must be done at
+ * runtime.
+ * the HZ range specific helpers _msecs_to_jiffies() are called both
+ * directly here and from __msecs_to_jiffies() in the case where
+ * constant folding is not possible.
+ */
+static inline unsigned long msecs_to_jiffies(const unsigned int m)
+{
+	if (__builtin_constant_p(m)) {
+		if ((int)m < 0)
+			return MAX_JIFFY_OFFSET;
+		return _msecs_to_jiffies(m);
+	} else {
+		return __msecs_to_jiffies(m);
+	}
+}
+
+extern unsigned long __usecs_to_jiffies(const unsigned int u);
+#if HZ <= USEC_PER_SEC && !(USEC_PER_SEC % HZ)
+static inline unsigned long _usecs_to_jiffies(const unsigned int u)
+{
+	return (u + (USEC_PER_SEC / HZ) - 1) / (USEC_PER_SEC / HZ);
+}
+#elif HZ > USEC_PER_SEC && !(HZ % USEC_PER_SEC)
+static inline unsigned long _usecs_to_jiffies(const unsigned int u)
+{
+	return u * (HZ / USEC_PER_SEC);
+}
+static inline unsigned long _usecs_to_jiffies(const unsigned int u)
+{
+#else
+static inline unsigned long _usecs_to_jiffies(const unsigned int u)
+{
+	return (USEC_TO_HZ_MUL32 * u + USEC_TO_HZ_ADJ32)
+		>> USEC_TO_HZ_SHR32;
+}
+#endif
+
+/**
+ * usecs_to_jiffies: - convert microseconds to jiffies
+ * @u:	time in microseconds
+ *
+ * conversion is done as follows:
+ *
+ * - 'too large' values [that would result in larger than
+ *   MAX_JIFFY_OFFSET values] mean 'infinite timeout' too.
+ *
+ * - all other values are converted to jiffies by either multiplying
+ *   the input value by a factor or dividing it with a factor and
+ *   handling any 32-bit overflows as for msecs_to_jiffies.
+ *
+ * usecs_to_jiffies() checks for the passed in value being a constant
+ * via __builtin_constant_p() allowing gcc to eliminate most of the
+ * code, __usecs_to_jiffies() is called if the value passed does not
+ * allow constant folding and the actual conversion must be done at
+ * runtime.
+ * the HZ range specific helpers _usecs_to_jiffies() are called both
+ * directly here and from __msecs_to_jiffies() in the case where
+ * constant folding is not possible.
+ */
+static inline unsigned long usecs_to_jiffies(const unsigned int u)
+{
+	if (__builtin_constant_p(u)) {
+		if (u > jiffies_to_usecs(MAX_JIFFY_OFFSET))
+			return MAX_JIFFY_OFFSET;
+		return _usecs_to_jiffies(u);
+	} else {
+		return __usecs_to_jiffies(u);
+	}
+}
+
 extern unsigned long timespec_to_jiffies(const struct timespec *value);
 extern void jiffies_to_timespec(const unsigned long jiffies,
 				struct timespec *value);

include/linux/perf_event.h

@@ -566,8 +566,12 @@ struct perf_cpu_context {
 	struct perf_event_context	*task_ctx;
 	int				active_oncpu;
 	int				exclusive;
+
+	raw_spinlock_t			hrtimer_lock;
 	struct hrtimer			hrtimer;
 	ktime_t				hrtimer_interval;
+	unsigned int			hrtimer_active;
+
 	struct pmu			*unique_pmu;
 	struct perf_cgroup		*cgrp;
 };

include/linux/rcupdate.h

@@ -44,6 +44,8 @@
 #include <linux/debugobjects.h>
 #include <linux/bug.h>
 #include <linux/compiler.h>
+#include <linux/ktime.h>
+
 #include <asm/barrier.h>
 
 extern int rcu_expedited; /* for sysctl */
@@ -1154,9 +1156,9 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
 	__kfree_rcu(&((ptr)->rcu_head), offsetof(typeof(*(ptr)), rcu_head))
 
 #if defined(CONFIG_TINY_RCU) || defined(CONFIG_RCU_NOCB_CPU_ALL)
-static inline int rcu_needs_cpu(unsigned long *delta_jiffies)
+static inline int rcu_needs_cpu(u64 basemono, u64 *nextevt)
 {
-	*delta_jiffies = ULONG_MAX;
+	*nextevt = KTIME_MAX;
 	return 0;
 }
 #endif /* #if defined(CONFIG_TINY_RCU) || defined(CONFIG_RCU_NOCB_CPU_ALL) */

include/linux/rcutree.h

@@ -32,7 +32,7 @@
 
 void rcu_note_context_switch(void);
 #ifndef CONFIG_RCU_NOCB_CPU_ALL
-int rcu_needs_cpu(unsigned long *delta_jiffies);
+int rcu_needs_cpu(u64 basem, u64 *nextevt);
 #endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
 void rcu_cpu_stall_reset(void);
 

include/linux/seqlock.h

@@ -233,6 +233,47 @@ static inline void raw_write_seqcount_end(seqcount_t *s)
 	s->sequence++;
 }
 
+/**
+ * raw_write_seqcount_barrier - do a seq write barrier
+ * @s: pointer to seqcount_t
+ *
+ * This can be used to provide an ordering guarantee instead of the
+ * usual consistency guarantee. It is one wmb cheaper, because we can
+ * collapse the two back-to-back wmb()s.
+ *
+ *      seqcount_t seq;
+ *      bool X = true, Y = false;
+ *
+ *      void read(void)
+ *      {
+ *              bool x, y;
+ *
+ *              do {
+ *                      int s = read_seqcount_begin(&seq);
+ *
+ *                      x = X; y = Y;
+ *
+ *              } while (read_seqcount_retry(&seq, s));
+ *
+ *              BUG_ON(!x && !y);
+ *      }
+ *
+ *      void write(void)
+ *      {
+ *              Y = true;
+ *
+ *              raw_write_seqcount_barrier(seq);
+ *
+ *              X = false;
+ *      }
+ */
+static inline void raw_write_seqcount_barrier(seqcount_t *s)
+{
+	s->sequence++;
+	smp_wmb();
+	s->sequence++;
+}
+
 /*
  * raw_write_seqcount_latch - redirect readers to even/odd copy
  * @s: pointer to seqcount_t
@@ -266,13 +307,13 @@ static inline void write_seqcount_end(seqcount_t *s)
 }
 
 /**
- * write_seqcount_barrier - invalidate in-progress read-side seq operations
+ * write_seqcount_invalidate - invalidate in-progress read-side seq operations
  * @s: pointer to seqcount_t
  *
- * After write_seqcount_barrier, no read-side seq operations will complete
+ * After write_seqcount_invalidate, no read-side seq operations will complete
  * successfully and see data older than this.
  */
-static inline void write_seqcount_barrier(seqcount_t *s)
+static inline void write_seqcount_invalidate(seqcount_t *s)
 {
 	smp_wmb();
 	s->sequence+=2;

include/linux/time64.h

@@ -2,6 +2,7 @@
 #define _LINUX_TIME64_H
 
 #include <uapi/linux/time.h>
+#include <linux/math64.h>
 
 typedef __s64 time64_t;
 
@@ -28,6 +29,7 @@ struct timespec64 {
 #define FSEC_PER_SEC	1000000000000000LL
 
 /* Located here for timespec[64]_valid_strict */
+#define TIME64_MAX			((s64)~((u64)1 << 63))
 #define KTIME_MAX			((s64)~((u64)1 << 63))
 #define KTIME_SEC_MAX			(KTIME_MAX / NSEC_PER_SEC)
 

include/linux/timekeeper_internal.h

@@ -49,6 +49,8 @@ struct tk_read_base {
  * @offs_boot:		Offset clock monotonic -> clock boottime
  * @offs_tai:		Offset clock monotonic -> clock tai
  * @tai_offset:		The current UTC to TAI offset in seconds
+ * @clock_was_set_seq:	The sequence number of clock was set events
+ * @next_leap_ktime:	CLOCK_MONOTONIC time value of a pending leap-second
  * @raw_time:		Monotonic raw base time in timespec64 format
  * @cycle_interval:	Number of clock cycles in one NTP interval
  * @xtime_interval:	Number of clock shifted nano seconds in one NTP
@@ -60,6 +62,9 @@ struct tk_read_base {
  *			shifted nano seconds.
  * @ntp_error_shift:	Shift conversion between clock shifted nano seconds and
  *			ntp shifted nano seconds.
+ * @last_warning:	Warning ratelimiter (DEBUG_TIMEKEEPING)
+ * @underflow_seen:	Underflow warning flag (DEBUG_TIMEKEEPING)
+ * @overflow_seen:	Overflow warning flag (DEBUG_TIMEKEEPING)
  *
  * Note: For timespec(64) based interfaces wall_to_monotonic is what
  * we need to add to xtime (or xtime corrected for sub jiffie times)
@@ -85,6 +90,8 @@ struct timekeeper {
 	ktime_t			offs_boot;
 	ktime_t			offs_tai;
 	s32			tai_offset;
+	unsigned int		clock_was_set_seq;
+	ktime_t			next_leap_ktime;
 	struct timespec64	raw_time;
 
 	/* The following members are for timekeeping internal use */
@@ -104,6 +111,18 @@ struct timekeeper {
 	s64			ntp_error;
 	u32			ntp_error_shift;
 	u32			ntp_err_mult;
+#ifdef CONFIG_DEBUG_TIMEKEEPING
+	long			last_warning;
+	/*
+	 * These simple flag variables are managed
+	 * without locks, which is racy, but they are
+	 * ok since we don't really care about being
+	 * super precise about how many events were
+	 * seen, just that a problem was observed.
+	 */
+	int			underflow_seen;
+	int			overflow_seen;
+#endif
 };
 
 #ifdef CONFIG_GENERIC_TIME_VSYSCALL

include/linux/timekeeping.h

@@ -163,6 +163,7 @@ extern ktime_t ktime_get(void);
 extern ktime_t ktime_get_with_offset(enum tk_offsets offs);
 extern ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs);
 extern ktime_t ktime_get_raw(void);
+extern u32 ktime_get_resolution_ns(void);
 
 /**
  * ktime_get_real - get the real (wall-) time in ktime_t format
@@ -266,7 +267,6 @@ extern int persistent_clock_is_local;
 
 extern void read_persistent_clock(struct timespec *ts);
 extern void read_persistent_clock64(struct timespec64 *ts);
-extern void read_boot_clock(struct timespec *ts);
 extern void read_boot_clock64(struct timespec64 *ts);
 extern int update_persistent_clock(struct timespec now);
 extern int update_persistent_clock64(struct timespec64 now);

include/linux/timer.h

@@ -187,13 +187,6 @@ extern void set_timer_slack(struct timer_list *time, int slack_hz);
  */
 #define NEXT_TIMER_MAX_DELTA	((1UL << 30) - 1)
 
-/*
- * Return when the next timer-wheel timeout occurs (in absolute jiffies),
- * locks the timer base and does the comparison against the given
- * jiffie.
- */
-extern unsigned long get_next_timer_interrupt(unsigned long now);
-
 /*
  * Timer-statistics info:
  */

include/linux/timerqueue.h

@@ -16,10 +16,10 @@ struct timerqueue_head {
 };
 
 
-extern void timerqueue_add(struct timerqueue_head *head,
-				struct timerqueue_node *node);
-extern void timerqueue_del(struct timerqueue_head *head,
-				struct timerqueue_node *node);
+extern bool timerqueue_add(struct timerqueue_head *head,
+			   struct timerqueue_node *node);
+extern bool timerqueue_del(struct timerqueue_head *head,
+			   struct timerqueue_node *node);
 extern struct timerqueue_node *timerqueue_iterate_next(
 						struct timerqueue_node *node);
 

include/trace/events/timer.h

@@ -43,15 +43,18 @@ DEFINE_EVENT(timer_class, timer_init,
  */
 TRACE_EVENT(timer_start,
 
-	TP_PROTO(struct timer_list *timer, unsigned long expires),
+	TP_PROTO(struct timer_list *timer,
+		unsigned long expires,
+		unsigned int deferrable),
 
-	TP_ARGS(timer, expires),
+	TP_ARGS(timer, expires, deferrable),
 
 	TP_STRUCT__entry(
 		__field( void *,	timer		)
 		__field( void *,	function	)
 		__field( unsigned long,	expires		)
 		__field( unsigned long,	now		)
+		__field( unsigned int,	deferrable	)
 	),
 
 	TP_fast_assign(
@@ -59,11 +62,13 @@ TRACE_EVENT(timer_start,
 		__entry->function	= timer->function;
 		__entry->expires	= expires;
 		__entry->now		= jiffies;
+		__entry->deferrable     = deferrable;
 	),
 
-	TP_printk("timer=%p function=%pf expires=%lu [timeout=%ld]",
+	TP_printk("timer=%p function=%pf expires=%lu [timeout=%ld] defer=%c",
 		  __entry->timer, __entry->function, __entry->expires,
-		  (long)__entry->expires - __entry->now)
+		  (long)__entry->expires - __entry->now,
+		  __entry->deferrable > 0 ? 'y':'n')
 );
 
 /**

kernel/events/core.c

@@ -51,9 +51,11 @@
 
 static struct workqueue_struct *perf_wq;
 
+typedef int (*remote_function_f)(void *);
+
 struct remote_function_call {
 	struct task_struct	*p;
-	int			(*func)(void *info);
+	remote_function_f	func;
 	void			*info;
 	int			ret;
 };
@@ -86,7 +88,7 @@ static void remote_function(void *data)
  *	    -EAGAIN - when the process moved away
  */
 static int
-task_function_call(struct task_struct *p, int (*func) (void *info), void *info)
+task_function_call(struct task_struct *p, remote_function_f func, void *info)
 {
 	struct remote_function_call data = {
 		.p	= p,
@@ -110,7 +112,7 @@ task_function_call(struct task_struct *p, int (*func) (void *info), void *info)
  *
  * returns: @func return value or -ENXIO when the cpu is offline
  */
-static int cpu_function_call(int cpu, int (*func) (void *info), void *info)
+static int cpu_function_call(int cpu, remote_function_f func, void *info)
 {
 	struct remote_function_call data = {
 		.p	= NULL,
@@ -747,62 +749,31 @@ perf_cgroup_mark_enabled(struct perf_event *event,
 /*
  * function must be called with interrupts disbled
  */
-static enum hrtimer_restart perf_cpu_hrtimer_handler(struct hrtimer *hr)
+static enum hrtimer_restart perf_mux_hrtimer_handler(struct hrtimer *hr)
 {
 	struct perf_cpu_context *cpuctx;
-	enum hrtimer_restart ret = HRTIMER_NORESTART;
 	int rotations = 0;
 
 	WARN_ON(!irqs_disabled());
 
 	cpuctx = container_of(hr, struct perf_cpu_context, hrtimer);
-
 	rotations = perf_rotate_context(cpuctx);
 
-	/*
-	 * arm timer if needed
-	 */
-	if (rotations) {
+	raw_spin_lock(&cpuctx->hrtimer_lock);
+	if (rotations)
 		hrtimer_forward_now(hr, cpuctx->hrtimer_interval);
-		ret = HRTIMER_RESTART;
-	}
-
-	return ret;
-}
-
-/* CPU is going down */
-void perf_cpu_hrtimer_cancel(int cpu)
-{
-	struct perf_cpu_context *cpuctx;
-	struct pmu *pmu;
-	unsigned long flags;
-
-	if (WARN_ON(cpu != smp_processor_id()))
-		return;
-
-	local_irq_save(flags);
-
-	rcu_read_lock();
-
-	list_for_each_entry_rcu(pmu, &pmus, entry) {
-		cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
-
-		if (pmu->task_ctx_nr == perf_sw_context)
-			continue;
-
-		hrtimer_cancel(&cpuctx->hrtimer);
-	}
-
-	rcu_read_unlock();
+	else
+		cpuctx->hrtimer_active = 0;
+	raw_spin_unlock(&cpuctx->hrtimer_lock);
 
-	local_irq_restore(flags);
+	return rotations ? HRTIMER_RESTART : HRTIMER_NORESTART;
 }
 
-static void __perf_cpu_hrtimer_init(struct perf_cpu_context *cpuctx, int cpu)
+static void __perf_mux_hrtimer_init(struct perf_cpu_context *cpuctx, int cpu)
 {
-	struct hrtimer *hr = &cpuctx->hrtimer;
+	struct hrtimer *timer = &cpuctx->hrtimer;
 	struct pmu *pmu = cpuctx->ctx.pmu;
-	int timer;
+	u64 interval;
 
 	/* no multiplexing needed for SW PMU */
 	if (pmu->task_ctx_nr == perf_sw_context)
@@ -812,31 +783,36 @@ static void __perf_cpu_hrtimer_init(struct perf_cpu_context *cpuctx, int cpu)
 	 * check default is sane, if not set then force to
 	 * default interval (1/tick)
 	 */
-	timer = pmu->hrtimer_interval_ms;
-	if (timer < 1)
-		timer = pmu->hrtimer_interval_ms = PERF_CPU_HRTIMER;
+	interval = pmu->hrtimer_interval_ms;
+	if (interval < 1)
+		interval = pmu->hrtimer_interval_ms = PERF_CPU_HRTIMER;
 
-	cpuctx->hrtimer_interval = ns_to_ktime(NSEC_PER_MSEC * timer);
+	cpuctx->hrtimer_interval = ns_to_ktime(NSEC_PER_MSEC * interval);
 
-	hrtimer_init(hr, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
-	hr->function = perf_cpu_hrtimer_handler;
+	raw_spin_lock_init(&cpuctx->hrtimer_lock);
+	hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
+	timer->function = perf_mux_hrtimer_handler;
 }
 
-static void perf_cpu_hrtimer_restart(struct perf_cpu_context *cpuctx)
+static int perf_mux_hrtimer_restart(struct perf_cpu_context *cpuctx)
 {
-	struct hrtimer *hr = &cpuctx->hrtimer;
+	struct hrtimer *timer = &cpuctx->hrtimer;
 	struct pmu *pmu = cpuctx->ctx.pmu;
+	unsigned long flags;
 
 	/* not for SW PMU */
 	if (pmu->task_ctx_nr == perf_sw_context)
-		return;
+		return 0;
 
-	if (hrtimer_active(hr))
-		return;
+	raw_spin_lock_irqsave(&cpuctx->hrtimer_lock, flags);
+	if (!cpuctx->hrtimer_active) {
+		cpuctx->hrtimer_active = 1;
+		hrtimer_forward_now(timer, cpuctx->hrtimer_interval);
+		hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED);
+	}
+	raw_spin_unlock_irqrestore(&cpuctx->hrtimer_lock, flags);
 
-	if (!hrtimer_callback_running(hr))
-		__hrtimer_start_range_ns(hr, cpuctx->hrtimer_interval,
-					 0, HRTIMER_MODE_REL_PINNED, 0);
+	return 0;
 }
 
 void perf_pmu_disable(struct pmu *pmu)
@@ -1935,7 +1911,7 @@ group_sched_in(struct perf_event *group_event,
 
 	if (event_sched_in(group_event, cpuctx, ctx)) {
 		pmu->cancel_txn(pmu);
-		perf_cpu_hrtimer_restart(cpuctx);
+		perf_mux_hrtimer_restart(cpuctx);
 		return -EAGAIN;
 	}
 
@@ -1982,7 +1958,7 @@ group_error:
 
 	pmu->cancel_txn(pmu);
 
-	perf_cpu_hrtimer_restart(cpuctx);
+	perf_mux_hrtimer_restart(cpuctx);
 
 	return -EAGAIN;
 }
@@ -2255,7 +2231,7 @@ static int __perf_event_enable(void *info)
 		 */
 		if (leader != event) {
 			group_sched_out(leader, cpuctx, ctx);
-			perf_cpu_hrtimer_restart(cpuctx);
+			perf_mux_hrtimer_restart(cpuctx);
 		}
 		if (leader->attr.pinned) {
 			update_group_times(leader);
@@ -6863,9 +6839,8 @@ static void perf_swevent_start_hrtimer(struct perf_event *event)
 	} else {
 		period = max_t(u64, 10000, hwc->sample_period);
 	}
-	__hrtimer_start_range_ns(&hwc->hrtimer,
-				ns_to_ktime(period), 0,
-				HRTIMER_MODE_REL_PINNED, 0);
+	hrtimer_start(&hwc->hrtimer, ns_to_ktime(period),
+		      HRTIMER_MODE_REL_PINNED);
 }
 
 static void perf_swevent_cancel_hrtimer(struct perf_event *event)
@@ -7166,6 +7141,8 @@ perf_event_mux_interval_ms_show(struct device *dev,
 	return snprintf(page, PAGE_SIZE-1, "%d\n", pmu->hrtimer_interval_ms);
 }
 
+static DEFINE_MUTEX(mux_interval_mutex);
+
 static ssize_t
 perf_event_mux_interval_ms_store(struct device *dev,
 				 struct device_attribute *attr,
@@ -7185,17 +7162,21 @@ perf_event_mux_interval_ms_store(struct device *dev,
 	if (timer == pmu->hrtimer_interval_ms)
 		return count;
 
+	mutex_lock(&mux_interval_mutex);
 	pmu->hrtimer_interval_ms = timer;
 
 	/* update all cpuctx for this PMU */
-	for_each_possible_cpu(cpu) {
+	get_online_cpus();
+	for_each_online_cpu(cpu) {
 		struct perf_cpu_context *cpuctx;
 		cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
 		cpuctx->hrtimer_interval = ns_to_ktime(NSEC_PER_MSEC * timer);
 
-		if (hrtimer_active(&cpuctx->hrtimer))
-			hrtimer_forward_now(&cpuctx->hrtimer, cpuctx->hrtimer_interval);
+		cpu_function_call(cpu,
+			(remote_function_f)perf_mux_hrtimer_restart, cpuctx);
 	}
+	put_online_cpus();
+	mutex_unlock(&mux_interval_mutex);
 
 	return count;
 }
@@ -7300,7 +7281,7 @@ skip_type:
 		lockdep_set_class(&cpuctx->ctx.lock, &cpuctx_lock);
 		cpuctx->ctx.pmu = pmu;
 
-		__perf_cpu_hrtimer_init(cpuctx, cpu);
+		__perf_mux_hrtimer_init(cpuctx, cpu);
 
 		cpuctx->unique_pmu = pmu;
 	}

kernel/futex.c

@@ -2064,11 +2064,8 @@ static void futex_wait_queue_me(struct futex_hash_bucket *hb, struct futex_q *q,
 	queue_me(q, hb);
 
 	/* Arm the timer */
-	if (timeout) {
+	if (timeout)
 		hrtimer_start_expires(&timeout->timer, HRTIMER_MODE_ABS);
-		if (!hrtimer_active(&timeout->timer))
-			timeout->task = NULL;
-	}
 
 	/*
 	 * If we have been removed from the hash list, then another task

kernel/locking/rtmutex.c

@@ -1182,11 +1182,8 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 	set_current_state(state);
 
 	/* Setup the timer, when timeout != NULL */
-	if (unlikely(timeout)) {
+	if (unlikely(timeout))
 		hrtimer_start_expires(&timeout->timer, HRTIMER_MODE_ABS);
-		if (!hrtimer_active(&timeout->timer))
-			timeout->task = NULL;
-	}
 
 	ret = task_blocks_on_rt_mutex(lock, &waiter, current, chwalk);
 

kernel/rcu/tree_plugin.h

@@ -1368,9 +1368,9 @@ static void rcu_prepare_kthreads(int cpu)
  * any flavor of RCU.
  */
 #ifndef CONFIG_RCU_NOCB_CPU_ALL
-int rcu_needs_cpu(unsigned long *delta_jiffies)
+int rcu_needs_cpu(u64 basemono, u64 *nextevt)
 {
-	*delta_jiffies = ULONG_MAX;
+	*nextevt = KTIME_MAX;
 	return rcu_cpu_has_callbacks(NULL);
 }
 #endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
@@ -1481,16 +1481,17 @@ static bool __maybe_unused rcu_try_advance_all_cbs(void)
  * The caller must have disabled interrupts.
  */
 #ifndef CONFIG_RCU_NOCB_CPU_ALL
-int rcu_needs_cpu(unsigned long *dj)
+int rcu_needs_cpu(u64 basemono, u64 *nextevt)
 {
 	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
+	unsigned long dj;
 
 	/* Snapshot to detect later posting of non-lazy callback. */
 	rdtp->nonlazy_posted_snap = rdtp->nonlazy_posted;
 
 	/* If no callbacks, RCU doesn't need the CPU. */
 	if (!rcu_cpu_has_callbacks(&rdtp->all_lazy)) {
-		*dj = ULONG_MAX;
+		*nextevt = KTIME_MAX;
 		return 0;
 	}
 
@@ -1504,11 +1505,12 @@ int rcu_needs_cpu(unsigned long *dj)
 
 	/* Request timer delay depending on laziness, and round. */
 	if (!rdtp->all_lazy) {
-		*dj = round_up(rcu_idle_gp_delay + jiffies,
+		dj = round_up(rcu_idle_gp_delay + jiffies,
 			       rcu_idle_gp_delay) - jiffies;
 	} else {
-		*dj = round_jiffies(rcu_idle_lazy_gp_delay + jiffies) - jiffies;
+		dj = round_jiffies(rcu_idle_lazy_gp_delay + jiffies) - jiffies;
 	}
+	*nextevt = basemono + dj * TICK_NSEC;
 	return 0;
 }
 #endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */

kernel/sched/core.c

@@ -90,26 +90,6 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/sched.h>
 
-void start_bandwidth_timer(struct hrtimer *period_timer, ktime_t period)
-{
-	unsigned long delta;
-	ktime_t soft, hard, now;
-
-	for (;;) {
-		if (hrtimer_active(period_timer))
-			break;
-
-		now = hrtimer_cb_get_time(period_timer);
-		hrtimer_forward(period_timer, now, period);
-
-		soft = hrtimer_get_softexpires(period_timer);
-		hard = hrtimer_get_expires(period_timer);
-		delta = ktime_to_ns(ktime_sub(hard, soft));
-		__hrtimer_start_range_ns(period_timer, soft, delta,
-					 HRTIMER_MODE_ABS_PINNED, 0);
-	}
-}
-
 DEFINE_MUTEX(sched_domains_mutex);
 DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 
@@ -355,12 +335,11 @@ static enum hrtimer_restart hrtick(struct hrtimer *timer)
 
 #ifdef CONFIG_SMP
 
-static int __hrtick_restart(struct rq *rq)
+static void __hrtick_restart(struct rq *rq)
 {
 	struct hrtimer *timer = &rq->hrtick_timer;
-	ktime_t time = hrtimer_get_softexpires(timer);
 
-	return __hrtimer_start_range_ns(timer, time, 0, HRTIMER_MODE_ABS_PINNED, 0);
+	hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED);
 }
 
 /*
@@ -440,8 +419,8 @@ void hrtick_start(struct rq *rq, u64 delay)
 	 * doesn't make sense. Rely on vruntime for fairness.
 	 */
 	delay = max_t(u64, delay, 10000LL);
-	__hrtimer_start_range_ns(&rq->hrtick_timer, ns_to_ktime(delay), 0,
-			HRTIMER_MODE_REL_PINNED, 0);
+	hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay),
+		      HRTIMER_MODE_REL_PINNED);
 }
 
 static inline void init_hrtick(void)
@@ -8146,10 +8125,8 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
 
 	__refill_cfs_bandwidth_runtime(cfs_b);
 	/* restart the period timer (if active) to handle new period expiry */
-	if (runtime_enabled && cfs_b->timer_active) {
-		/* force a reprogram */
-		__start_cfs_bandwidth(cfs_b, true);
-	}
+	if (runtime_enabled)
+		start_cfs_bandwidth(cfs_b);
 	raw_spin_unlock_irq(&cfs_b->lock);
 
 	for_each_online_cpu(i) {

kernel/sched/deadline.c

@@ -503,8 +503,6 @@ static int start_dl_timer(struct sched_dl_entity *dl_se, bool boosted)
 	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
 	struct rq *rq = rq_of_dl_rq(dl_rq);
 	ktime_t now, act;
-	ktime_t soft, hard;
-	unsigned long range;
 	s64 delta;
 
 	if (boosted)
@@ -527,15 +525,9 @@ static int start_dl_timer(struct sched_dl_entity *dl_se, bool boosted)
 	if (ktime_us_delta(act, now) < 0)
 		return 0;
 
-	hrtimer_set_expires(&dl_se->dl_timer, act);
+	hrtimer_start(&dl_se->dl_timer, act, HRTIMER_MODE_ABS);
 
-	soft = hrtimer_get_softexpires(&dl_se->dl_timer);
-	hard = hrtimer_get_expires(&dl_se->dl_timer);
-	range = ktime_to_ns(ktime_sub(hard, soft));
-	__hrtimer_start_range_ns(&dl_se->dl_timer, soft,
-				 range, HRTIMER_MODE_ABS, 0);
-
-	return hrtimer_active(&dl_se->dl_timer);
+	return 1;
 }
 
 /*

kernel/sched/debug.c

@@ -230,8 +230,6 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 #endif
 #endif
 #ifdef CONFIG_CFS_BANDWIDTH
-	SEQ_printf(m, "  .%-30s: %d\n", "tg->cfs_bandwidth.timer_active",
-			cfs_rq->tg->cfs_bandwidth.timer_active);
 	SEQ_printf(m, "  .%-30s: %d\n", "throttled",
 			cfs_rq->throttled);
 	SEQ_printf(m, "  .%-30s: %d\n", "throttle_count",

kernel/sched/fair.c

@@ -3504,16 +3504,7 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 	if (cfs_b->quota == RUNTIME_INF)
 		amount = min_amount;
 	else {
-		/*
-		 * If the bandwidth pool has become inactive, then at least one
-		 * period must have elapsed since the last consumption.
-		 * Refresh the global state and ensure bandwidth timer becomes
-		 * active.
-		 */
-		if (!cfs_b->timer_active) {
-			__refill_cfs_bandwidth_runtime(cfs_b);
-			__start_cfs_bandwidth(cfs_b, false);
-		}
+		start_cfs_bandwidth(cfs_b);
 
 		if (cfs_b->runtime > 0) {
 			amount = min(cfs_b->runtime, min_amount);
@@ -3662,6 +3653,7 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
 	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
 	struct sched_entity *se;
 	long task_delta, dequeue = 1;
+	bool empty;
 
 	se = cfs_rq->tg->se[cpu_of(rq_of(cfs_rq))];
 
@@ -3691,13 +3683,21 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
 	cfs_rq->throttled = 1;
 	cfs_rq->throttled_clock = rq_clock(rq);
 	raw_spin_lock(&cfs_b->lock);
+	empty = list_empty(&cfs_rq->throttled_list);
+
 	/*
 	 * Add to the _head_ of the list, so that an already-started
 	 * distribute_cfs_runtime will not see us
 	 */
 	list_add_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
-	if (!cfs_b->timer_active)
-		__start_cfs_bandwidth(cfs_b, false);
+
+	/*
+	 * If we're the first throttled task, make sure the bandwidth
+	 * timer is running.
+	 */
+	if (empty)
+		start_cfs_bandwidth(cfs_b);
+
 	raw_spin_unlock(&cfs_b->lock);
 }
 
@@ -3812,13 +3812,6 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun)
 	if (cfs_b->idle && !throttled)
 		goto out_deactivate;
 
-	/*
-	 * if we have relooped after returning idle once, we need to update our
-	 * status as actually running, so that other cpus doing
-	 * __start_cfs_bandwidth will stop trying to cancel us.
-	 */
-	cfs_b->timer_active = 1;
-
 	__refill_cfs_bandwidth_runtime(cfs_b);
 
 	if (!throttled) {
@@ -3863,7 +3856,6 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun)
 	return 0;
 
 out_deactivate:
-	cfs_b->timer_active = 0;
 	return 1;
 }
 
@@ -3878,7 +3870,7 @@ static const u64 cfs_bandwidth_slack_period = 5 * NSEC_PER_MSEC;
  * Are we near the end of the current quota period?
  *
  * Requires cfs_b->lock for hrtimer_expires_remaining to be safe against the
- * hrtimer base being cleared by __hrtimer_start_range_ns. In the case of
+ * hrtimer base being cleared by hrtimer_start. In the case of
  * migrate_hrtimers, base is never cleared, so we are fine.
  */
 static int runtime_refresh_within(struct cfs_bandwidth *cfs_b, u64 min_expire)
@@ -3906,8 +3898,9 @@ static void start_cfs_slack_bandwidth(struct cfs_bandwidth *cfs_b)
 	if (runtime_refresh_within(cfs_b, min_left))
 		return;
 
-	start_bandwidth_timer(&cfs_b->slack_timer,
-				ns_to_ktime(cfs_bandwidth_slack_period));
+	hrtimer_start(&cfs_b->slack_timer,
+			ns_to_ktime(cfs_bandwidth_slack_period),
+			HRTIMER_MODE_REL);
 }
 
 /* we know any runtime found here is valid as update_curr() precedes return */
@@ -4027,6 +4020,7 @@ static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer)
 {
 	struct cfs_bandwidth *cfs_b =
 		container_of(timer, struct cfs_bandwidth, slack_timer);
+
 	do_sched_cfs_slack_timer(cfs_b);
 
 	return HRTIMER_NORESTART;
@@ -4036,20 +4030,19 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
 {
 	struct cfs_bandwidth *cfs_b =
 		container_of(timer, struct cfs_bandwidth, period_timer);
-	ktime_t now;
 	int overrun;
 	int idle = 0;
 
 	raw_spin_lock(&cfs_b->lock);
 	for (;;) {
-		now = hrtimer_cb_get_time(timer);
-		overrun = hrtimer_forward(timer, now, cfs_b->period);
-
+		overrun = hrtimer_forward_now(timer, cfs_b->period);
 		if (!overrun)
 			break;
 
 		idle = do_sched_cfs_period_timer(cfs_b, overrun);
 	}
+	if (idle)
+		cfs_b->period_active = 0;
 	raw_spin_unlock(&cfs_b->lock);
 
 	return idle ? HRTIMER_NORESTART : HRTIMER_RESTART;
@@ -4063,7 +4056,7 @@ void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
 	cfs_b->period = ns_to_ktime(default_cfs_period());
 
 	INIT_LIST_HEAD(&cfs_b->throttled_cfs_rq);
-	hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
 	cfs_b->period_timer.function = sched_cfs_period_timer;
 	hrtimer_init(&cfs_b->slack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	cfs_b->slack_timer.function = sched_cfs_slack_timer;
@@ -4075,28 +4068,15 @@ static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 	INIT_LIST_HEAD(&cfs_rq->throttled_list);
 }
 
-/* requires cfs_b->lock, may release to reprogram timer */
-void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b, bool force)
+void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
 {
-	/*
-	 * The timer may be active because we're trying to set a new bandwidth
-	 * period or because we're racing with the tear-down path
-	 * (timer_active==0 becomes visible before the hrtimer call-back
-	 * terminates).  In either case we ensure that it's re-programmed
-	 */
-	while (unlikely(hrtimer_active(&cfs_b->period_timer)) &&
-	       hrtimer_try_to_cancel(&cfs_b->period_timer) < 0) {
-		/* bounce the lock to allow do_sched_cfs_period_timer to run */
-		raw_spin_unlock(&cfs_b->lock);
-		cpu_relax();
-		raw_spin_lock(&cfs_b->lock);
-		/* if someone else restarted the timer then we're done */
-		if (!force && cfs_b->timer_active)
-			return;
-	}
+	lockdep_assert_held(&cfs_b->lock);
 
-	cfs_b->timer_active = 1;
-	start_bandwidth_timer(&cfs_b->period_timer, cfs_b->period);
+	if (!cfs_b->period_active) {
+		cfs_b->period_active = 1;
+		hrtimer_forward_now(&cfs_b->period_timer, cfs_b->period);
+		hrtimer_start_expires(&cfs_b->period_timer, HRTIMER_MODE_ABS_PINNED);
+	}
 }
 
 static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b)

kernel/sched/rt.c

@@ -18,19 +18,22 @@ static enum hrtimer_restart sched_rt_period_timer(struct hrtimer *timer)
 {
 	struct rt_bandwidth *rt_b =
 		container_of(timer, struct rt_bandwidth, rt_period_timer);
-	ktime_t now;
-	int overrun;
 	int idle = 0;
+	int overrun;
 
+	raw_spin_lock(&rt_b->rt_runtime_lock);
 	for (;;) {
-		now = hrtimer_cb_get_time(timer);
-		overrun = hrtimer_forward(timer, now, rt_b->rt_period);
-
+		overrun = hrtimer_forward_now(timer, rt_b->rt_period);
 		if (!overrun)
 			break;
 
+		raw_spin_unlock(&rt_b->rt_runtime_lock);
 		idle = do_sched_rt_period_timer(rt_b, overrun);
+		raw_spin_lock(&rt_b->rt_runtime_lock);
 	}
+	if (idle)
+		rt_b->rt_period_active = 0;
+	raw_spin_unlock(&rt_b->rt_runtime_lock);
 
 	return idle ? HRTIMER_NORESTART : HRTIMER_RESTART;
 }
@@ -52,11 +55,12 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
 	if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF)
 		return;
 
-	if (hrtimer_active(&rt_b->rt_period_timer))
-		return;
-
 	raw_spin_lock(&rt_b->rt_runtime_lock);
-	start_bandwidth_timer(&rt_b->rt_period_timer, rt_b->rt_period);
+	if (!rt_b->rt_period_active) {
+		rt_b->rt_period_active = 1;
+		hrtimer_forward_now(&rt_b->rt_period_timer, rt_b->rt_period);
+		hrtimer_start_expires(&rt_b->rt_period_timer, HRTIMER_MODE_ABS_PINNED);
+	}
 	raw_spin_unlock(&rt_b->rt_runtime_lock);
 }
 

kernel/sched/sched.h

@@ -137,6 +137,7 @@ struct rt_bandwidth {
 	ktime_t			rt_period;
 	u64			rt_runtime;
 	struct hrtimer		rt_period_timer;
+	unsigned int		rt_period_active;
 };
 
 void __dl_clear_params(struct task_struct *p);
@@ -221,7 +222,7 @@ struct cfs_bandwidth {
 	s64 hierarchical_quota;
 	u64 runtime_expires;
 
-	int idle, timer_active;
+	int idle, period_active;
 	struct hrtimer period_timer, slack_timer;
 	struct list_head throttled_cfs_rq;
 
@@ -312,7 +313,7 @@ extern void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
 extern int sched_group_set_shares(struct task_group *tg, unsigned long shares);
 
 extern void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b);
-extern void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b, bool force);
+extern void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
 extern void unthrottle_cfs_rq(struct cfs_rq *cfs_rq);
 
 extern void free_rt_sched_group(struct task_group *tg);
@@ -1410,8 +1411,6 @@ static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta) { }
 static inline void sched_avg_update(struct rq *rq) { }
 #endif
 
-extern void start_bandwidth_timer(struct hrtimer *period_timer, ktime_t period);
-
 /*
  * __task_rq_lock - lock the rq @p resides on.
  */

kernel/time/Makefile

@@ -13,19 +13,4 @@ obj-$(CONFIG_TIMER_STATS)			+= timer_stats.o
 obj-$(CONFIG_DEBUG_FS)				+= timekeeping_debug.o
 obj-$(CONFIG_TEST_UDELAY)			+= test_udelay.o
 
-$(obj)/time.o: $(obj)/timeconst.h
-
-quiet_cmd_hzfile = HZFILE  $@
-      cmd_hzfile = echo "hz=$(CONFIG_HZ)" > $@
-
-targets += hz.bc
-$(obj)/hz.bc: $(objtree)/include/config/hz.h FORCE
-	$(call if_changed,hzfile)
-
-quiet_cmd_bc  = BC      $@
-      cmd_bc  = bc -q $(filter-out FORCE,$^) > $@
-
-targets += timeconst.h
-$(obj)/timeconst.h: $(obj)/hz.bc $(src)/timeconst.bc FORCE
-	$(call if_changed,bc)
-
+$(obj)/time.o: $(objtree)/include/config/

kernel/time/alarmtimer.c

@@ -317,19 +317,16 @@ EXPORT_SYMBOL_GPL(alarm_init);
  * @alarm: ptr to alarm to set
  * @start: time to run the alarm
  */
-int alarm_start(struct alarm *alarm, ktime_t start)
+void alarm_start(struct alarm *alarm, ktime_t start)
 {
 	struct alarm_base *base = &alarm_bases[alarm->type];
 	unsigned long flags;
-	int ret;
 
 	spin_lock_irqsave(&base->lock, flags);
 	alarm->node.expires = start;
 	alarmtimer_enqueue(base, alarm);
-	ret = hrtimer_start(&alarm->timer, alarm->node.expires,
-				HRTIMER_MODE_ABS);
+	hrtimer_start(&alarm->timer, alarm->node.expires, HRTIMER_MODE_ABS);
 	spin_unlock_irqrestore(&base->lock, flags);
-	return ret;
 }
 EXPORT_SYMBOL_GPL(alarm_start);
 
@@ -338,12 +335,12 @@ EXPORT_SYMBOL_GPL(alarm_start);
  * @alarm: ptr to alarm to set
  * @start: time relative to now to run the alarm
  */
-int alarm_start_relative(struct alarm *alarm, ktime_t start)
+void alarm_start_relative(struct alarm *alarm, ktime_t start)
 {
 	struct alarm_base *base = &alarm_bases[alarm->type];
 
 	start = ktime_add(start, base->gettime());
-	return alarm_start(alarm, start);
+	alarm_start(alarm, start);
 }
 EXPORT_SYMBOL_GPL(alarm_start_relative);
 
@@ -495,12 +492,12 @@ static enum alarmtimer_restart alarm_handle_timer(struct alarm *alarm,
  */
 static int alarm_clock_getres(const clockid_t which_clock, struct timespec *tp)
 {
-	clockid_t baseid = alarm_bases[clock2alarm(which_clock)].base_clockid;
-
 	if (!alarmtimer_get_rtcdev())
 		return -EINVAL;
 
-	return hrtimer_get_res(baseid, tp);
+	tp->tv_sec = 0;
+	tp->tv_nsec = hrtimer_resolution;
+	return 0;
 }
 
 /**

kernel/time/clockevents.c

@@ -94,8 +94,8 @@ u64 clockevent_delta2ns(unsigned long latch, struct clock_event_device *evt)
 }
 EXPORT_SYMBOL_GPL(clockevent_delta2ns);
 
-static int __clockevents_set_state(struct clock_event_device *dev,
-				   enum clock_event_state state)
+static int __clockevents_switch_state(struct clock_event_device *dev,
+				      enum clock_event_state state)
 {
 	/* Transition with legacy set_mode() callback */
 	if (dev->set_mode) {
@@ -134,32 +134,44 @@ static int __clockevents_set_state(struct clock_event_device *dev,
 			return -ENOSYS;
 		return dev->set_state_oneshot(dev);
 
+	case CLOCK_EVT_STATE_ONESHOT_STOPPED:
+		/* Core internal bug */
+		if (WARN_ONCE(!clockevent_state_oneshot(dev),
+			      "Current state: %d\n",
+			      clockevent_get_state(dev)))
+			return -EINVAL;
+
+		if (dev->set_state_oneshot_stopped)
+			return dev->set_state_oneshot_stopped(dev);
+		else
+			return -ENOSYS;
+
 	default:
 		return -ENOSYS;
 	}
 }
 
 /**
- * clockevents_set_state - set the operating state of a clock event device
+ * clockevents_switch_state - set the operating state of a clock event device
  * @dev:	device to modify
  * @state:	new state
  *
  * Must be called with interrupts disabled !
  */
-void clockevents_set_state(struct clock_event_device *dev,
-			   enum clock_event_state state)
+void clockevents_switch_state(struct clock_event_device *dev,
+			      enum clock_event_state state)
 {
-	if (dev->state != state) {
-		if (__clockevents_set_state(dev, state))
+	if (clockevent_get_state(dev) != state) {
+		if (__clockevents_switch_state(dev, state))
 			return;
 
-		dev->state = state;
+		clockevent_set_state(dev, state);
 
 		/*
 		 * A nsec2cyc multiplicator of 0 is invalid and we'd crash
 		 * on it, so fix it up and emit a warning:
 		 */
-		if (state == CLOCK_EVT_STATE_ONESHOT) {
+		if (clockevent_state_oneshot(dev)) {
 			if (unlikely(!dev->mult)) {
 				dev->mult = 1;
 				WARN_ON(1);
@@ -174,7 +186,7 @@ void clockevents_set_state(struct clock_event_device *dev,
  */
 void clockevents_shutdown(struct clock_event_device *dev)
 {
-	clockevents_set_state(dev, CLOCK_EVT_STATE_SHUTDOWN);
+	clockevents_switch_state(dev, CLOCK_EVT_STATE_SHUTDOWN);
 	dev->next_event.tv64 = KTIME_MAX;
 }
 
@@ -248,7 +260,7 @@ static int clockevents_program_min_delta(struct clock_event_device *dev)
 		delta = dev->min_delta_ns;
 		dev->next_event = ktime_add_ns(ktime_get(), delta);
 
-		if (dev->state == CLOCK_EVT_STATE_SHUTDOWN)
+		if (clockevent_state_shutdown(dev))
 			return 0;
 
 		dev->retries++;
@@ -285,7 +297,7 @@ static int clockevents_program_min_delta(struct clock_event_device *dev)
 	delta = dev->min_delta_ns;
 	dev->next_event = ktime_add_ns(ktime_get(), delta);
 
-	if (dev->state == CLOCK_EVT_STATE_SHUTDOWN)
+	if (clockevent_state_shutdown(dev))
 		return 0;
 
 	dev->retries++;
@@ -317,9 +329,13 @@ int clockevents_program_event(struct clock_event_device *dev, ktime_t expires,
 
 	dev->next_event = expires;
 
-	if (dev->state == CLOCK_EVT_STATE_SHUTDOWN)
+	if (clockevent_state_shutdown(dev))
 		return 0;
 
+	/* We must be in ONESHOT state here */
+	WARN_ONCE(!clockevent_state_oneshot(dev), "Current state: %d\n",
+		  clockevent_get_state(dev));
+
 	/* Shortcut for clockevent devices that can deal with ktime. */
 	if (dev->features & CLOCK_EVT_FEAT_KTIME)
 		return dev->set_next_ktime(expires, dev);
@@ -362,7 +378,7 @@ static int clockevents_replace(struct clock_event_device *ced)
 	struct clock_event_device *dev, *newdev = NULL;
 
 	list_for_each_entry(dev, &clockevent_devices, list) {
-		if (dev == ced || dev->state != CLOCK_EVT_STATE_DETACHED)
+		if (dev == ced || !clockevent_state_detached(dev))
 			continue;
 
 		if (!tick_check_replacement(newdev, dev))
@@ -388,7 +404,7 @@ static int clockevents_replace(struct clock_event_device *ced)
 static int __clockevents_try_unbind(struct clock_event_device *ced, int cpu)
 {
 	/* Fast track. Device is unused */
-	if (ced->state == CLOCK_EVT_STATE_DETACHED) {
+	if (clockevent_state_detached(ced)) {
 		list_del_init(&ced->list);
 		return 0;
 	}
@@ -445,7 +461,8 @@ static int clockevents_sanity_check(struct clock_event_device *dev)
 	if (dev->set_mode) {
 		/* We shouldn't be supporting new modes now */
 		WARN_ON(dev->set_state_periodic || dev->set_state_oneshot ||
-			dev->set_state_shutdown || dev->tick_resume);
+			dev->set_state_shutdown || dev->tick_resume ||
+			dev->set_state_oneshot_stopped);
 
 		BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED);
 		return 0;
@@ -480,7 +497,7 @@ void clockevents_register_device(struct clock_event_device *dev)
 	BUG_ON(clockevents_sanity_check(dev));
 
 	/* Initialize state to DETACHED */
-	dev->state = CLOCK_EVT_STATE_DETACHED;
+	clockevent_set_state(dev, CLOCK_EVT_STATE_DETACHED);
 
 	if (!dev->cpumask) {
 		WARN_ON(num_possible_cpus() > 1);
@@ -545,11 +562,11 @@ int __clockevents_update_freq(struct clock_event_device *dev, u32 freq)
 {
 	clockevents_config(dev, freq);
 
-	if (dev->state == CLOCK_EVT_STATE_ONESHOT)
+	if (clockevent_state_oneshot(dev))
 		return clockevents_program_event(dev, dev->next_event, false);
 
-	if (dev->state == CLOCK_EVT_STATE_PERIODIC)
-		return __clockevents_set_state(dev, CLOCK_EVT_STATE_PERIODIC);
+	if (clockevent_state_periodic(dev))
+		return __clockevents_switch_state(dev, CLOCK_EVT_STATE_PERIODIC);
 
 	return 0;
 }
@@ -603,13 +620,13 @@ void clockevents_exchange_device(struct clock_event_device *old,
 	 */
 	if (old) {
 		module_put(old->owner);
-		clockevents_set_state(old, CLOCK_EVT_STATE_DETACHED);
+		clockevents_switch_state(old, CLOCK_EVT_STATE_DETACHED);
 		list_del(&old->list);
 		list_add(&old->list, &clockevents_released);
 	}
 
 	if (new) {
-		BUG_ON(new->state != CLOCK_EVT_STATE_DETACHED);
+		BUG_ON(!clockevent_state_detached(new));
 		clockevents_shutdown(new);
 	}
 }
@@ -622,7 +639,7 @@ void clockevents_suspend(void)
 	struct clock_event_device *dev;
 
 	list_for_each_entry_reverse(dev, &clockevent_devices, list)
-		if (dev->suspend)
+		if (dev->suspend && !clockevent_state_detached(dev))
 			dev->suspend(dev);
 }
 
@@ -634,7 +651,7 @@ void clockevents_resume(void)
 	struct clock_event_device *dev;
 
 	list_for_each_entry(dev, &clockevent_devices, list)
-		if (dev->resume)
+		if (dev->resume && !clockevent_state_detached(dev))
 			dev->resume(dev);
 }
 
@@ -665,7 +682,7 @@ void tick_cleanup_dead_cpu(int cpu)
 		if (cpumask_test_cpu(cpu, dev->cpumask) &&
 		    cpumask_weight(dev->cpumask) == 1 &&
 		    !tick_is_broadcast_device(dev)) {
-			BUG_ON(dev->state != CLOCK_EVT_STATE_DETACHED);
+			BUG_ON(!clockevent_state_detached(dev));
 			list_del(&dev->list);
 		}
 	}

kernel/time/clocksource.c

@@ -23,6 +23,8 @@
  *   o Allow clocksource drivers to be unregistered
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/device.h>
 #include <linux/clocksource.h>
 #include <linux/init.h>
@@ -216,10 +218,11 @@ static void clocksource_watchdog(unsigned long data)
 
 		/* Check the deviation from the watchdog clocksource. */
 		if ((abs(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD)) {
-			pr_warn("timekeeping watchdog: Marking clocksource '%s' as unstable, because the skew is too large:\n", cs->name);
-			pr_warn("	'%s' wd_now: %llx wd_last: %llx mask: %llx\n",
+			pr_warn("timekeeping watchdog: Marking clocksource '%s' as unstable because the skew is too large:\n",
+				cs->name);
+			pr_warn("                      '%s' wd_now: %llx wd_last: %llx mask: %llx\n",
 				watchdog->name, wdnow, wdlast, watchdog->mask);
-			pr_warn("	'%s' cs_now: %llx cs_last: %llx mask: %llx\n",
+			pr_warn("                      '%s' cs_now: %llx cs_last: %llx mask: %llx\n",
 				cs->name, csnow, cslast, cs->mask);
 			__clocksource_unstable(cs);
 			continue;
@@ -567,9 +570,8 @@ static void __clocksource_select(bool skipcur)
 		 */
 		if (!(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES) && oneshot) {
 			/* Override clocksource cannot be used. */
-			printk(KERN_WARNING "Override clocksource %s is not "
-			       "HRT compatible. Cannot switch while in "
-			       "HRT/NOHZ mode\n", cs->name);
+			pr_warn("Override clocksource %s is not HRT compatible - cannot switch while in HRT/NOHZ mode\n",
+				cs->name);
 			override_name[0] = 0;
 		} else
 			/* Override clocksource can be used. */
@@ -708,8 +710,8 @@ void __clocksource_update_freq_scale(struct clocksource *cs, u32 scale, u32 freq
 
 	clocksource_update_max_deferment(cs);
 
-	pr_info("clocksource %s: mask: 0x%llx max_cycles: 0x%llx, max_idle_ns: %lld ns\n",
-			cs->name, cs->mask, cs->max_cycles, cs->max_idle_ns);
+	pr_info("%s: mask: 0x%llx max_cycles: 0x%llx, max_idle_ns: %lld ns\n",
+		cs->name, cs->mask, cs->max_cycles, cs->max_idle_ns);
 }
 EXPORT_SYMBOL_GPL(__clocksource_update_freq_scale);
 
@@ -1008,12 +1010,10 @@ __setup("clocksource=", boot_override_clocksource);
 static int __init boot_override_clock(char* str)
 {
 	if (!strcmp(str, "pmtmr")) {
-		printk("Warning: clock=pmtmr is deprecated. "
-			"Use clocksource=acpi_pm.\n");
+		pr_warn("clock=pmtmr is deprecated - use clocksource=acpi_pm\n");
 		return boot_override_clocksource("acpi_pm");
 	}
-	printk("Warning! clock= boot option is deprecated. "
-		"Use clocksource=xyz\n");
+	pr_warn("clock= boot option is deprecated - use clocksource=xyz\n");
 	return boot_override_clocksource(str);
 }
 

kernel/time/hrtimer.c

@@ -66,33 +66,29 @@
  */
 DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
 {
-
 	.lock = __RAW_SPIN_LOCK_UNLOCKED(hrtimer_bases.lock),
+	.seq = SEQCNT_ZERO(hrtimer_bases.seq),
 	.clock_base =
 	{
 		{
 			.index = HRTIMER_BASE_MONOTONIC,
 			.clockid = CLOCK_MONOTONIC,
 			.get_time = &ktime_get,
-			.resolution = KTIME_LOW_RES,
 		},
 		{
 			.index = HRTIMER_BASE_REALTIME,
 			.clockid = CLOCK_REALTIME,
 			.get_time = &ktime_get_real,
-			.resolution = KTIME_LOW_RES,
 		},
 		{
 			.index = HRTIMER_BASE_BOOTTIME,
 			.clockid = CLOCK_BOOTTIME,
 			.get_time = &ktime_get_boottime,
-			.resolution = KTIME_LOW_RES,
 		},
 		{
 			.index = HRTIMER_BASE_TAI,
 			.clockid = CLOCK_TAI,
 			.get_time = &ktime_get_clocktai,
-			.resolution = KTIME_LOW_RES,
 		},
 	}
 };
@@ -109,33 +105,24 @@ static inline int hrtimer_clockid_to_base(clockid_t clock_id)
 	return hrtimer_clock_to_base_table[clock_id];
 }
 
-
-/*
- * Get the coarse grained time at the softirq based on xtime and
- * wall_to_monotonic.
- */
-static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base)
-{
-	ktime_t xtim, mono, boot, tai;
-	ktime_t off_real, off_boot, off_tai;
-
-	mono = ktime_get_update_offsets_tick(&off_real, &off_boot, &off_tai);
-	boot = ktime_add(mono, off_boot);
-	xtim = ktime_add(mono, off_real);
-	tai = ktime_add(mono, off_tai);
-
-	base->clock_base[HRTIMER_BASE_REALTIME].softirq_time = xtim;
-	base->clock_base[HRTIMER_BASE_MONOTONIC].softirq_time = mono;
-	base->clock_base[HRTIMER_BASE_BOOTTIME].softirq_time = boot;
-	base->clock_base[HRTIMER_BASE_TAI].softirq_time = tai;
-}
-
 /*
  * Functions and macros which are different for UP/SMP systems are kept in a
  * single place
  */
 #ifdef CONFIG_SMP
 
+/*
+ * We require the migration_base for lock_hrtimer_base()/switch_hrtimer_base()
+ * such that hrtimer_callback_running() can unconditionally dereference
+ * timer->base->cpu_base
+ */
+static struct hrtimer_cpu_base migration_cpu_base = {
+	.seq = SEQCNT_ZERO(migration_cpu_base),
+	.clock_base = { { .cpu_base = &migration_cpu_base, }, },
+};
+
+#define migration_base	migration_cpu_base.clock_base[0]
+
 /*
  * We are using hashed locking: holding per_cpu(hrtimer_bases)[n].lock
  * means that all timers which are tied to this base via timer->base are
@@ -145,8 +132,8 @@ static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base)
  * be found on the lists/queues.
  *
  * When the timer's base is locked, and the timer removed from list, it is
- * possible to set timer->base = NULL and drop the lock: the timer remains
- * locked.
+ * possible to set timer->base = &migration_base and drop the lock: the timer
+ * remains locked.
  */
 static
 struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer,
@@ -156,7 +143,7 @@ struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer,
 
 	for (;;) {
 		base = timer->base;
-		if (likely(base != NULL)) {
+		if (likely(base != &migration_base)) {
 			raw_spin_lock_irqsave(&base->cpu_base->lock, *flags);
 			if (likely(base == timer->base))
 				return base;
@@ -220,8 +207,8 @@ again:
 		if (unlikely(hrtimer_callback_running(timer)))
 			return base;
 
-		/* See the comment in lock_timer_base() */
-		timer->base = NULL;
+		/* See the comment in lock_hrtimer_base() */
+		timer->base = &migration_base;
 		raw_spin_unlock(&base->cpu_base->lock);
 		raw_spin_lock(&new_base->cpu_base->lock);
 
@@ -443,24 +430,35 @@ static inline void debug_deactivate(struct hrtimer *timer)
 }
 
 #if defined(CONFIG_NO_HZ_COMMON) || defined(CONFIG_HIGH_RES_TIMERS)
+static inline void hrtimer_update_next_timer(struct hrtimer_cpu_base *cpu_base,
+					     struct hrtimer *timer)
+{
+#ifdef CONFIG_HIGH_RES_TIMERS
+	cpu_base->next_timer = timer;
+#endif
+}
+
 static ktime_t __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base)
 {
 	struct hrtimer_clock_base *base = cpu_base->clock_base;
 	ktime_t expires, expires_next = { .tv64 = KTIME_MAX };
-	int i;
+	unsigned int active = cpu_base->active_bases;
 
-	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) {
+	hrtimer_update_next_timer(cpu_base, NULL);
+	for (; active; base++, active >>= 1) {
 		struct timerqueue_node *next;
 		struct hrtimer *timer;
 
-		next = timerqueue_getnext(&base->active);
-		if (!next)
+		if (!(active & 0x01))
 			continue;
 
+		next = timerqueue_getnext(&base->active);
 		timer = container_of(next, struct hrtimer, node);
 		expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
-		if (expires.tv64 < expires_next.tv64)
+		if (expires.tv64 < expires_next.tv64) {
 			expires_next = expires;
+			hrtimer_update_next_timer(cpu_base, timer);
+		}
 	}
 	/*
 	 * clock_was_set() might have changed base->offset of any of
@@ -473,6 +471,16 @@ static ktime_t __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base)
 }
 #endif
 
+static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base)
+{
+	ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset;
+	ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset;
+	ktime_t *offs_tai = &base->clock_base[HRTIMER_BASE_TAI].offset;
+
+	return ktime_get_update_offsets_now(&base->clock_was_set_seq,
+					    offs_real, offs_boot, offs_tai);
+}
+
 /* High resolution timer related functions */
 #ifdef CONFIG_HIGH_RES_TIMERS
 
@@ -480,6 +488,8 @@ static ktime_t __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base)
  * High resolution timer enabled ?
  */
 static int hrtimer_hres_enabled __read_mostly  = 1;
+unsigned int hrtimer_resolution __read_mostly = LOW_RES_NSEC;
+EXPORT_SYMBOL_GPL(hrtimer_resolution);
 
 /*
  * Enable / Disable high resolution mode
@@ -508,9 +518,14 @@ static inline int hrtimer_is_hres_enabled(void)
 /*
  * Is the high resolution mode active ?
  */
+static inline int __hrtimer_hres_active(struct hrtimer_cpu_base *cpu_base)
+{
+	return cpu_base->hres_active;
+}
+
 static inline int hrtimer_hres_active(void)
 {
-	return __this_cpu_read(hrtimer_bases.hres_active);
+	return __hrtimer_hres_active(this_cpu_ptr(&hrtimer_bases));
 }
 
 /*
@@ -521,7 +536,12 @@ static inline int hrtimer_hres_active(void)
 static void
 hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
 {
-	ktime_t expires_next = __hrtimer_get_next_event(cpu_base);
+	ktime_t expires_next;
+
+	if (!cpu_base->hres_active)
+		return;
+
+	expires_next = __hrtimer_get_next_event(cpu_base);
 
 	if (skip_equal && expires_next.tv64 == cpu_base->expires_next.tv64)
 		return;
@@ -545,63 +565,53 @@ hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
 	if (cpu_base->hang_detected)
 		return;
 
-	if (cpu_base->expires_next.tv64 != KTIME_MAX)
-		tick_program_event(cpu_base->expires_next, 1);
+	tick_program_event(cpu_base->expires_next, 1);
 }
 
 /*
- * Shared reprogramming for clock_realtime and clock_monotonic
- *
  * When a timer is enqueued and expires earlier than the already enqueued
  * timers, we have to check, whether it expires earlier than the timer for
  * which the clock event device was armed.
  *
- * Note, that in case the state has HRTIMER_STATE_CALLBACK set, no reprogramming
- * and no expiry check happens. The timer gets enqueued into the rbtree. The
- * reprogramming and expiry check is done in the hrtimer_interrupt or in the
- * softirq.
- *
  * Called with interrupts disabled and base->cpu_base.lock held
  */
-static int hrtimer_reprogram(struct hrtimer *timer,
-			     struct hrtimer_clock_base *base)
+static void hrtimer_reprogram(struct hrtimer *timer,
+			      struct hrtimer_clock_base *base)
 {
 	struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
 	ktime_t expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
-	int res;
 
 	WARN_ON_ONCE(hrtimer_get_expires_tv64(timer) < 0);
 
 	/*
-	 * When the callback is running, we do not reprogram the clock event
-	 * device. The timer callback is either running on a different CPU or
-	 * the callback is executed in the hrtimer_interrupt context. The
-	 * reprogramming is handled either by the softirq, which called the
-	 * callback or at the end of the hrtimer_interrupt.
+	 * If the timer is not on the current cpu, we cannot reprogram
+	 * the other cpus clock event device.
 	 */
-	if (hrtimer_callback_running(timer))
-		return 0;
+	if (base->cpu_base != cpu_base)
+		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 (cpu_base->in_hrtirq)
+		return;
 
 	/*
 	 * CLOCK_REALTIME timer might be requested with an absolute
-	 * expiry time which is less than base->offset. Nothing wrong
-	 * about that, just avoid to call into the tick code, which
-	 * has now objections against negative expiry values.
+	 * expiry time which is less than base->offset. Set it to 0.
 	 */
 	if (expires.tv64 < 0)
-		return -ETIME;
+		expires.tv64 = 0;
 
 	if (expires.tv64 >= cpu_base->expires_next.tv64)
-		return 0;
+		return;
 
-	/*
-	 * When the target cpu of the timer is currently executing
-	 * hrtimer_interrupt(), then we do not touch the clock event
-	 * device. hrtimer_interrupt() will reevaluate all clock bases
-	 * before reprogramming the device.
-	 */
-	if (cpu_base->in_hrtirq)
-		return 0;
+	/* Update the pointer to the next expiring timer */
+	cpu_base->next_timer = timer;
 
 	/*
 	 * If a hang was detected in the last timer interrupt then we
@@ -610,15 +620,14 @@ static int hrtimer_reprogram(struct hrtimer *timer,
 	 * to make progress.
 	 */
 	if (cpu_base->hang_detected)
-		return 0;
+		return;
 
 	/*
-	 * Clockevents returns -ETIME, when the event was in the past.
+	 * Program the timer hardware. We enforce the expiry for
+	 * events which are already in the past.
 	 */
-	res = tick_program_event(expires, 0);
-	if (!IS_ERR_VALUE(res))
-		cpu_base->expires_next = expires;
-	return res;
+	cpu_base->expires_next = expires;
+	tick_program_event(expires, 1);
 }
 
 /*
@@ -630,15 +639,6 @@ static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base)
 	base->hres_active = 0;
 }
 
-static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base)
-{
-	ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset;
-	ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset;
-	ktime_t *offs_tai = &base->clock_base[HRTIMER_BASE_TAI].offset;
-
-	return ktime_get_update_offsets_now(offs_real, offs_boot, offs_tai);
-}
-
 /*
  * Retrigger next event is called after clock was set
  *
@@ -648,7 +648,7 @@ static void retrigger_next_event(void *arg)
 {
 	struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases);
 
-	if (!hrtimer_hres_active())
+	if (!base->hres_active)
 		return;
 
 	raw_spin_lock(&base->lock);
@@ -662,29 +662,19 @@ static void retrigger_next_event(void *arg)
  */
 static int hrtimer_switch_to_hres(void)
 {
-	int i, cpu = smp_processor_id();
-	struct hrtimer_cpu_base *base = &per_cpu(hrtimer_bases, cpu);
-	unsigned long flags;
-
-	if (base->hres_active)
-		return 1;
-
-	local_irq_save(flags);
+	struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases);
 
 	if (tick_init_highres()) {
-		local_irq_restore(flags);
 		printk(KERN_WARNING "Could not switch to high resolution "
-				    "mode on CPU %d\n", cpu);
+				    "mode on CPU %d\n", base->cpu);
 		return 0;
 	}
 	base->hres_active = 1;
-	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++)
-		base->clock_base[i].resolution = KTIME_HIGH_RES;
+	hrtimer_resolution = HIGH_RES_NSEC;
 
 	tick_setup_sched_timer();
 	/* "Retrigger" the interrupt to get things going */
 	retrigger_next_event(NULL);
-	local_irq_restore(flags);
 	return 1;
 }
 
@@ -706,6 +696,7 @@ void clock_was_set_delayed(void)
 
 #else
 
+static inline int __hrtimer_hres_active(struct hrtimer_cpu_base *b) { return 0; }
 static inline int hrtimer_hres_active(void) { return 0; }
 static inline int hrtimer_is_hres_enabled(void) { return 0; }
 static inline int hrtimer_switch_to_hres(void) { return 0; }
@@ -803,6 +794,14 @@ void unlock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags)
  *
  * Forward the timer expiry so it will expire in the future.
  * Returns the number of overruns.
+ *
+ * Can be safely called from the callback function of @timer. If
+ * called from other contexts @timer must neither be enqueued nor
+ * running the callback and the caller needs to take care of
+ * serialization.
+ *
+ * Note: This only updates the timer expiry value and does not requeue
+ * the timer.
  */
 u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval)
 {
@@ -814,8 +813,11 @@ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval)
 	if (delta.tv64 < 0)
 		return 0;
 
-	if (interval.tv64 < timer->base->resolution.tv64)
-		interval.tv64 = timer->base->resolution.tv64;
+	if (WARN_ON(timer->state & HRTIMER_STATE_ENQUEUED))
+		return 0;
+
+	if (interval.tv64 < hrtimer_resolution)
+		interval.tv64 = hrtimer_resolution;
 
 	if (unlikely(delta.tv64 >= interval.tv64)) {
 		s64 incr = ktime_to_ns(interval);
@@ -849,16 +851,11 @@ static int enqueue_hrtimer(struct hrtimer *timer,
 {
 	debug_activate(timer);
 
-	timerqueue_add(&base->active, &timer->node);
 	base->cpu_base->active_bases |= 1 << base->index;
 
-	/*
-	 * HRTIMER_STATE_ENQUEUED is or'ed to the current state to preserve the
-	 * state of a possibly running callback.
-	 */
-	timer->state |= HRTIMER_STATE_ENQUEUED;
+	timer->state = HRTIMER_STATE_ENQUEUED;
 
-	return (&timer->node == base->active.next);
+	return timerqueue_add(&base->active, &timer->node);
 }
 
 /*
@@ -875,39 +872,38 @@ static void __remove_hrtimer(struct hrtimer *timer,
 			     struct hrtimer_clock_base *base,
 			     unsigned long newstate, int reprogram)
 {
-	struct timerqueue_node *next_timer;
-	if (!(timer->state & HRTIMER_STATE_ENQUEUED))
-		goto out;
+	struct hrtimer_cpu_base *cpu_base = base->cpu_base;
+	unsigned int state = timer->state;
+
+	timer->state = newstate;
+	if (!(state & HRTIMER_STATE_ENQUEUED))
+		return;
+
+	if (!timerqueue_del(&base->active, &timer->node))
+		cpu_base->active_bases &= ~(1 << base->index);
 
-	next_timer = timerqueue_getnext(&base->active);
-	timerqueue_del(&base->active, &timer->node);
-	if (&timer->node == next_timer) {
 #ifdef CONFIG_HIGH_RES_TIMERS
-		/* Reprogram the clock event device. if enabled */
-		if (reprogram && hrtimer_hres_active()) {
-			ktime_t expires;
-
-			expires = ktime_sub(hrtimer_get_expires(timer),
-					    base->offset);
-			if (base->cpu_base->expires_next.tv64 == expires.tv64)
-				hrtimer_force_reprogram(base->cpu_base, 1);
-		}
+	/*
+	 * Note: If reprogram is false we do not update
+	 * cpu_base->next_timer. This happens when we remove the first
+	 * timer on a remote cpu. No harm as we never dereference
+	 * cpu_base->next_timer. So the worst thing what can happen is
+	 * an superflous call to hrtimer_force_reprogram() on the
+	 * remote cpu later on if the same timer gets enqueued again.
+	 */
+	if (reprogram && timer == cpu_base->next_timer)
+		hrtimer_force_reprogram(cpu_base, 1);
 #endif
-	}
-	if (!timerqueue_getnext(&base->active))
-		base->cpu_base->active_bases &= ~(1 << base->index);
-out:
-	timer->state = newstate;
 }
 
 /*
  * remove hrtimer, called with base lock held
  */
 static inline int
-remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
+remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, bool restart)
 {
 	if (hrtimer_is_queued(timer)) {
-		unsigned long state;
+		unsigned long state = timer->state;
 		int reprogram;
 
 		/*
@@ -921,30 +917,35 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
 		debug_deactivate(timer);
 		timer_stats_hrtimer_clear_start_info(timer);
 		reprogram = base->cpu_base == this_cpu_ptr(&hrtimer_bases);
-		/*
-		 * We must preserve the CALLBACK state flag here,
-		 * otherwise we could move the timer base in
-		 * switch_hrtimer_base.
-		 */
-		state = timer->state & HRTIMER_STATE_CALLBACK;
+
+		if (!restart)
+			state = HRTIMER_STATE_INACTIVE;
+
 		__remove_hrtimer(timer, base, state, reprogram);
 		return 1;
 	}
 	return 0;
 }
 
-int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
-		unsigned long delta_ns, const enum hrtimer_mode mode,
-		int wakeup)
+/**
+ * hrtimer_start_range_ns - (re)start an hrtimer on the current CPU
+ * @timer:	the timer to be added
+ * @tim:	expiry time
+ * @delta_ns:	"slack" range for the timer
+ * @mode:	expiry mode: absolute (HRTIMER_MODE_ABS) or
+ *		relative (HRTIMER_MODE_REL)
+ */
+void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
+			    unsigned long delta_ns, const enum hrtimer_mode mode)
 {
 	struct hrtimer_clock_base *base, *new_base;
 	unsigned long flags;
-	int ret, leftmost;
+	int leftmost;
 
 	base = lock_hrtimer_base(timer, &flags);
 
 	/* Remove an active timer from the queue: */
-	ret = remove_hrtimer(timer, base);
+	remove_hrtimer(timer, base, true);
 
 	if (mode & HRTIMER_MODE_REL) {
 		tim = ktime_add_safe(tim, base->get_time());
@@ -956,7 +957,7 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 		 * timeouts. This will go away with the GTOD framework.
 		 */
 #ifdef CONFIG_TIME_LOW_RES
-		tim = ktime_add_safe(tim, base->resolution);
+		tim = ktime_add_safe(tim, ktime_set(0, hrtimer_resolution));
 #endif
 	}
 
@@ -968,11 +969,8 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 	timer_stats_hrtimer_set_start_info(timer);
 
 	leftmost = enqueue_hrtimer(timer, new_base);
-
-	if (!leftmost) {
-		unlock_hrtimer_base(timer, &flags);
-		return ret;
-	}
+	if (!leftmost)
+		goto unlock;
 
 	if (!hrtimer_is_hres_active(timer)) {
 		/*
@@ -980,72 +978,14 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 		 * on dynticks target.
 		 */
 		wake_up_nohz_cpu(new_base->cpu_base->cpu);
-	} else if (new_base->cpu_base == this_cpu_ptr(&hrtimer_bases) &&
-			hrtimer_reprogram(timer, new_base)) {
-		/*
-		 * Only allow reprogramming if the new base is on this CPU.
-		 * (it might still be on another CPU if the timer was pending)
-		 *
-		 * XXX send_remote_softirq() ?
-		 */
-		if (wakeup) {
-			/*
-			 * We need to drop cpu_base->lock to avoid a
-			 * lock ordering issue vs. rq->lock.
-			 */
-			raw_spin_unlock(&new_base->cpu_base->lock);
-			raise_softirq_irqoff(HRTIMER_SOFTIRQ);
-			local_irq_restore(flags);
-			return ret;
-		} else {
-			__raise_softirq_irqoff(HRTIMER_SOFTIRQ);
-		}
+	} else {
+		hrtimer_reprogram(timer, new_base);
 	}
-
+unlock:
 	unlock_hrtimer_base(timer, &flags);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(__hrtimer_start_range_ns);
-
-/**
- * hrtimer_start_range_ns - (re)start an hrtimer on the current CPU
- * @timer:	the timer to be added
- * @tim:	expiry time
- * @delta_ns:	"slack" range for the timer
- * @mode:	expiry mode: absolute (HRTIMER_MODE_ABS) or
- *		relative (HRTIMER_MODE_REL)
- *
- * Returns:
- *  0 on success
- *  1 when the timer was active
- */
-int hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
-		unsigned long delta_ns, const enum hrtimer_mode mode)
-{
-	return __hrtimer_start_range_ns(timer, tim, delta_ns, mode, 1);
 }
 EXPORT_SYMBOL_GPL(hrtimer_start_range_ns);
 
-/**
- * hrtimer_start - (re)start an hrtimer on the current CPU
- * @timer:	the timer to be added
- * @tim:	expiry time
- * @mode:	expiry mode: absolute (HRTIMER_MODE_ABS) or
- *		relative (HRTIMER_MODE_REL)
- *
- * Returns:
- *  0 on success
- *  1 when the timer was active
- */
-int
-hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
-{
-	return __hrtimer_start_range_ns(timer, tim, 0, mode, 1);
-}
-EXPORT_SYMBOL_GPL(hrtimer_start);
-
-
 /**
  * hrtimer_try_to_cancel - try to deactivate a timer
  * @timer:	hrtimer to stop
@@ -1062,10 +1002,19 @@ int hrtimer_try_to_cancel(struct hrtimer *timer)
 	unsigned long flags;
 	int ret = -1;
 
+	/*
+	 * Check lockless first. If the timer is not active (neither
+	 * enqueued nor running the callback, nothing to do here.  The
+	 * base lock does not serialize against a concurrent enqueue,
+	 * so we can avoid taking it.
+	 */
+	if (!hrtimer_active(timer))
+		return 0;
+
 	base = lock_hrtimer_base(timer, &flags);
 
 	if (!hrtimer_callback_running(timer))
-		ret = remove_hrtimer(timer, base);
+		ret = remove_hrtimer(timer, base, false);
 
 	unlock_hrtimer_base(timer, &flags);
 
@@ -1115,26 +1064,22 @@ EXPORT_SYMBOL_GPL(hrtimer_get_remaining);
 /**
  * hrtimer_get_next_event - get the time until next expiry event
  *
- * Returns the delta to the next expiry event or KTIME_MAX if no timer
- * is pending.
+ * Returns the next expiry time or KTIME_MAX if no timer is pending.
  */
-ktime_t hrtimer_get_next_event(void)
+u64 hrtimer_get_next_event(void)
 {
 	struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
-	ktime_t mindelta = { .tv64 = KTIME_MAX };
+	u64 expires = KTIME_MAX;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&cpu_base->lock, flags);
 
-	if (!hrtimer_hres_active())
-		mindelta = ktime_sub(__hrtimer_get_next_event(cpu_base),
-				     ktime_get());
+	if (!__hrtimer_hres_active(cpu_base))
+		expires = __hrtimer_get_next_event(cpu_base).tv64;
 
 	raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
 
-	if (mindelta.tv64 < 0)
-		mindelta.tv64 = 0;
-	return mindelta;
+	return expires;
 }
 #endif
 
@@ -1176,37 +1121,73 @@ void hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
 }
 EXPORT_SYMBOL_GPL(hrtimer_init);
 
-/**
- * hrtimer_get_res - get the timer resolution for a clock
- * @which_clock: which clock to query
- * @tp:		 pointer to timespec variable to store the resolution
+/*
+ * A timer is active, when it is enqueued into the rbtree or the
+ * callback function is running or it's in the state of being migrated
+ * to another cpu.
  *
- * Store the resolution of the clock selected by @which_clock in the
- * variable pointed to by @tp.
+ * It is important for this function to not return a false negative.
  */
-int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp)
+bool hrtimer_active(const struct hrtimer *timer)
 {
 	struct hrtimer_cpu_base *cpu_base;
-	int base = hrtimer_clockid_to_base(which_clock);
+	unsigned int seq;
 
-	cpu_base = raw_cpu_ptr(&hrtimer_bases);
-	*tp = ktime_to_timespec(cpu_base->clock_base[base].resolution);
+	do {
+		cpu_base = READ_ONCE(timer->base->cpu_base);
+		seq = raw_read_seqcount_begin(&cpu_base->seq);
 
-	return 0;
+		if (timer->state != HRTIMER_STATE_INACTIVE ||
+		    cpu_base->running == timer)
+			return true;
+
+	} while (read_seqcount_retry(&cpu_base->seq, seq) ||
+		 cpu_base != READ_ONCE(timer->base->cpu_base));
+
+	return false;
 }
-EXPORT_SYMBOL_GPL(hrtimer_get_res);
+EXPORT_SYMBOL_GPL(hrtimer_active);
 
-static void __run_hrtimer(struct hrtimer *timer, ktime_t *now)
+/*
+ * The write_seqcount_barrier()s in __run_hrtimer() split the thing into 3
+ * distinct sections:
+ *
+ *  - queued:	the timer is queued
+ *  - callback:	the timer is being ran
+ *  - post:	the timer is inactive or (re)queued
+ *
+ * On the read side we ensure we observe timer->state and cpu_base->running
+ * from the same section, if anything changed while we looked at it, we retry.
+ * This includes timer->base changing because sequence numbers alone are
+ * insufficient for that.
+ *
+ * The sequence numbers are required because otherwise we could still observe
+ * a false negative if the read side got smeared over multiple consequtive
+ * __run_hrtimer() invocations.
+ */
+
+static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base,
+			  struct hrtimer_clock_base *base,
+			  struct hrtimer *timer, ktime_t *now)
 {
-	struct hrtimer_clock_base *base = timer->base;
-	struct hrtimer_cpu_base *cpu_base = base->cpu_base;
 	enum hrtimer_restart (*fn)(struct hrtimer *);
 	int restart;
 
-	WARN_ON(!irqs_disabled());
+	lockdep_assert_held(&cpu_base->lock);
 
 	debug_deactivate(timer);
-	__remove_hrtimer(timer, base, HRTIMER_STATE_CALLBACK, 0);
+	cpu_base->running = timer;
+
+	/*
+	 * Separate the ->running assignment from the ->state assignment.
+	 *
+	 * As with a regular write barrier, this ensures the read side in
+	 * hrtimer_active() cannot observe cpu_base->running == NULL &&
+	 * timer->state == INACTIVE.
+	 */
+	raw_write_seqcount_barrier(&cpu_base->seq);
+
+	__remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE, 0);
 	timer_stats_account_hrtimer(timer);
 	fn = timer->function;
 
@@ -1222,58 +1203,43 @@ static void __run_hrtimer(struct hrtimer *timer, ktime_t *now)
 	raw_spin_lock(&cpu_base->lock);
 
 	/*
-	 * Note: We clear the CALLBACK bit after enqueue_hrtimer and
+	 * Note: We clear the running state after enqueue_hrtimer and
 	 * we do not reprogramm the event hardware. Happens either in
 	 * hrtimer_start_range_ns() or in hrtimer_interrupt()
+	 *
+	 * Note: Because we dropped the cpu_base->lock above,
+	 * hrtimer_start_range_ns() can have popped in and enqueued the timer
+	 * for us already.
 	 */
-	if (restart != HRTIMER_NORESTART) {
-		BUG_ON(timer->state != HRTIMER_STATE_CALLBACK);
+	if (restart != HRTIMER_NORESTART &&
+	    !(timer->state & HRTIMER_STATE_ENQUEUED))
 		enqueue_hrtimer(timer, base);
-	}
 
-	WARN_ON_ONCE(!(timer->state & HRTIMER_STATE_CALLBACK));
+	/*
+	 * Separate the ->running assignment from the ->state assignment.
+	 *
+	 * As with a regular write barrier, this ensures the read side in
+	 * hrtimer_active() cannot observe cpu_base->running == NULL &&
+	 * timer->state == INACTIVE.
+	 */
+	raw_write_seqcount_barrier(&cpu_base->seq);
 
-	timer->state &= ~HRTIMER_STATE_CALLBACK;
+	WARN_ON_ONCE(cpu_base->running != timer);
+	cpu_base->running = NULL;
 }
 
-#ifdef CONFIG_HIGH_RES_TIMERS
-
-/*
- * High resolution timer interrupt
- * Called with interrupts disabled
- */
-void hrtimer_interrupt(struct clock_event_device *dev)
+static void __hrtimer_run_queues(struct hrtimer_cpu_base *cpu_base, ktime_t now)
 {
-	struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
-	ktime_t expires_next, now, entry_time, delta;
-	int i, retries = 0;
-
-	BUG_ON(!cpu_base->hres_active);
-	cpu_base->nr_events++;
-	dev->next_event.tv64 = KTIME_MAX;
-
-	raw_spin_lock(&cpu_base->lock);
-	entry_time = now = hrtimer_update_base(cpu_base);
-retry:
-	cpu_base->in_hrtirq = 1;
-	/*
-	 * We set expires_next to KTIME_MAX here with cpu_base->lock
-	 * held to prevent that a timer is enqueued in our queue via
-	 * the migration code. This does not affect enqueueing of
-	 * timers which run their callback and need to be requeued on
-	 * this CPU.
-	 */
-	cpu_base->expires_next.tv64 = KTIME_MAX;
+	struct hrtimer_clock_base *base = cpu_base->clock_base;
+	unsigned int active = cpu_base->active_bases;
 
-	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
-		struct hrtimer_clock_base *base;
+	for (; active; base++, active >>= 1) {
 		struct timerqueue_node *node;
 		ktime_t basenow;
 
-		if (!(cpu_base->active_bases & (1 << i)))
+		if (!(active & 0x01))
 			continue;
 
-		base = cpu_base->clock_base + i;
 		basenow = ktime_add(now, base->offset);
 
 		while ((node = timerqueue_getnext(&base->active))) {
@@ -1296,9 +1262,42 @@ retry:
 			if (basenow.tv64 < hrtimer_get_softexpires_tv64(timer))
 				break;
 
-			__run_hrtimer(timer, &basenow);
+			__run_hrtimer(cpu_base, base, timer, &basenow);
 		}
 	}
+}
+
+#ifdef CONFIG_HIGH_RES_TIMERS
+
+/*
+ * High resolution timer interrupt
+ * Called with interrupts disabled
+ */
+void hrtimer_interrupt(struct clock_event_device *dev)
+{
+	struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
+	ktime_t expires_next, now, entry_time, delta;
+	int retries = 0;
+
+	BUG_ON(!cpu_base->hres_active);
+	cpu_base->nr_events++;
+	dev->next_event.tv64 = KTIME_MAX;
+
+	raw_spin_lock(&cpu_base->lock);
+	entry_time = now = hrtimer_update_base(cpu_base);
+retry:
+	cpu_base->in_hrtirq = 1;
+	/*
+	 * We set expires_next to KTIME_MAX here with cpu_base->lock
+	 * held to prevent that a timer is enqueued in our queue via
+	 * the migration code. This does not affect enqueueing of
+	 * timers which run their callback and need to be requeued on
+	 * this CPU.
+	 */
+	cpu_base->expires_next.tv64 = KTIME_MAX;
+
+	__hrtimer_run_queues(cpu_base, now);
+
 	/* Reevaluate the clock bases for the next expiry */
 	expires_next = __hrtimer_get_next_event(cpu_base);
 	/*
@@ -1310,8 +1309,7 @@ retry:
 	raw_spin_unlock(&cpu_base->lock);
 
 	/* Reprogramming necessary ? */
-	if (expires_next.tv64 == KTIME_MAX ||
-	    !tick_program_event(expires_next, 0)) {
+	if (!tick_program_event(expires_next, 0)) {
 		cpu_base->hang_detected = 0;
 		return;
 	}
@@ -1344,8 +1342,8 @@ retry:
 	cpu_base->hang_detected = 1;
 	raw_spin_unlock(&cpu_base->lock);
 	delta = ktime_sub(now, entry_time);
-	if (delta.tv64 > cpu_base->max_hang_time.tv64)
-		cpu_base->max_hang_time = delta;
+	if ((unsigned int)delta.tv64 > cpu_base->max_hang_time)
+		cpu_base->max_hang_time = (unsigned int) delta.tv64;
 	/*
 	 * Limit it to a sensible value as we enforce a longer
 	 * delay. Give the CPU at least 100ms to catch up.
@@ -1363,7 +1361,7 @@ retry:
  * local version of hrtimer_peek_ahead_timers() called with interrupts
  * disabled.
  */
-static void __hrtimer_peek_ahead_timers(void)
+static inline void __hrtimer_peek_ahead_timers(void)
 {
 	struct tick_device *td;
 
@@ -1375,29 +1373,6 @@ static void __hrtimer_peek_ahead_timers(void)
 		hrtimer_interrupt(td->evtdev);
 }
 
-/**
- * hrtimer_peek_ahead_timers -- run soft-expired timers now
- *
- * hrtimer_peek_ahead_timers will peek at the timer queue of
- * the current cpu and check if there are any timers for which
- * the soft expires time has passed. If any such timers exist,
- * they are run immediately and then removed from the timer queue.
- *
- */
-void hrtimer_peek_ahead_timers(void)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	__hrtimer_peek_ahead_timers();
-	local_irq_restore(flags);
-}
-
-static void run_hrtimer_softirq(struct softirq_action *h)
-{
-	hrtimer_peek_ahead_timers();
-}
-
 #else /* CONFIG_HIGH_RES_TIMERS */
 
 static inline void __hrtimer_peek_ahead_timers(void) { }
@@ -1405,66 +1380,32 @@ static inline void __hrtimer_peek_ahead_timers(void) { }
 #endif	/* !CONFIG_HIGH_RES_TIMERS */
 
 /*
- * Called from timer softirq every jiffy, expire hrtimers:
- *
- * For HRT its the fall back code to run the softirq in the timer
- * softirq context in case the hrtimer initialization failed or has
- * not been done yet.
+ * Called from run_local_timers in hardirq context every jiffy
  */
-void hrtimer_run_pending(void)
+void hrtimer_run_queues(void)
 {
-	if (hrtimer_hres_active())
+	struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
+	ktime_t now;
+
+	if (__hrtimer_hres_active(cpu_base))
 		return;
 
 	/*
-	 * This _is_ ugly: We have to check in the softirq context,
-	 * whether we can switch to highres and / or nohz mode. The
-	 * clocksource switch happens in the timer interrupt with
-	 * xtime_lock held. Notification from there only sets the
-	 * check bit in the tick_oneshot code, otherwise we might
-	 * deadlock vs. xtime_lock.
+	 * This _is_ ugly: We have to check periodically, whether we
+	 * can switch to highres and / or nohz mode. The clocksource
+	 * switch happens with xtime_lock held. Notification from
+	 * there only sets the check bit in the tick_oneshot code,
+	 * otherwise we might deadlock vs. xtime_lock.
 	 */
-	if (tick_check_oneshot_change(!hrtimer_is_hres_enabled()))
+	if (tick_check_oneshot_change(!hrtimer_is_hres_enabled())) {
 		hrtimer_switch_to_hres();
-}
-
-/*
- * Called from hardirq context every jiffy
- */
-void hrtimer_run_queues(void)
-{
-	struct timerqueue_node *node;
-	struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
-	struct hrtimer_clock_base *base;
-	int index, gettime = 1;
-
-	if (hrtimer_hres_active())
 		return;
-
-	for (index = 0; index < HRTIMER_MAX_CLOCK_BASES; index++) {
-		base = &cpu_base->clock_base[index];
-		if (!timerqueue_getnext(&base->active))
-			continue;
-
-		if (gettime) {
-			hrtimer_get_softirq_time(cpu_base);
-			gettime = 0;
-		}
-
-		raw_spin_lock(&cpu_base->lock);
-
-		while ((node = timerqueue_getnext(&base->active))) {
-			struct hrtimer *timer;
-
-			timer = container_of(node, struct hrtimer, node);
-			if (base->softirq_time.tv64 <=
-					hrtimer_get_expires_tv64(timer))
-				break;
-
-			__run_hrtimer(timer, &base->softirq_time);
-		}
-		raw_spin_unlock(&cpu_base->lock);
 	}
+
+	raw_spin_lock(&cpu_base->lock);
+	now = hrtimer_update_base(cpu_base);
+	__hrtimer_run_queues(cpu_base, now);
+	raw_spin_unlock(&cpu_base->lock);
 }
 
 /*
@@ -1497,8 +1438,6 @@ static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mod
 	do {
 		set_current_state(TASK_INTERRUPTIBLE);
 		hrtimer_start_expires(&t->timer, mode);
-		if (!hrtimer_active(&t->timer))
-			t->task = NULL;
 
 		if (likely(t->task))
 			freezable_schedule();
@@ -1642,11 +1581,11 @@ static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
 		debug_deactivate(timer);
 
 		/*
-		 * Mark it as STATE_MIGRATE not INACTIVE otherwise the
+		 * Mark it as ENQUEUED not INACTIVE otherwise the
 		 * timer could be seen as !active and just vanish away
 		 * under us on another CPU
 		 */
-		__remove_hrtimer(timer, old_base, HRTIMER_STATE_MIGRATE, 0);
+		__remove_hrtimer(timer, old_base, HRTIMER_STATE_ENQUEUED, 0);
 		timer->base = new_base;
 		/*
 		 * Enqueue the timers on the new cpu. This does not
@@ -1657,9 +1596,6 @@ static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
 		 * event device.
 		 */
 		enqueue_hrtimer(timer, new_base);
-
-		/* Clear the migration state bit */
-		timer->state &= ~HRTIMER_STATE_MIGRATE;
 	}
 }
 
@@ -1731,9 +1667,6 @@ void __init hrtimers_init(void)
 	hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE,
 			  (void *)(long)smp_processor_id());
 	register_cpu_notifier(&hrtimers_nb);
-#ifdef CONFIG_HIGH_RES_TIMERS
-	open_softirq(HRTIMER_SOFTIRQ, run_hrtimer_softirq);
-#endif
 }
 
 /**
@@ -1772,8 +1705,6 @@ schedule_hrtimeout_range_clock(ktime_t *expires, unsigned long delta,
 	hrtimer_init_sleeper(&t, current);
 
 	hrtimer_start_expires(&t.timer, mode);
-	if (!hrtimer_active(&t.timer))
-		t.task = NULL;
 
 	if (likely(t.task))
 		schedule();

kernel/time/ntp.c

@@ -35,6 +35,7 @@ unsigned long			tick_nsec;
 static u64			tick_length;
 static u64			tick_length_base;
 
+#define SECS_PER_DAY		86400
 #define MAX_TICKADJ		500LL		/* usecs */
 #define MAX_TICKADJ_SCALED \
 	(((MAX_TICKADJ * NSEC_PER_USEC) << NTP_SCALE_SHIFT) / NTP_INTERVAL_FREQ)
@@ -76,6 +77,9 @@ static long			time_adjust;
 /* constant (boot-param configurable) NTP tick adjustment (upscaled)	*/
 static s64			ntp_tick_adj;
 
+/* second value of the next pending leapsecond, or TIME64_MAX if no leap */
+static time64_t			ntp_next_leap_sec = TIME64_MAX;
+
 #ifdef CONFIG_NTP_PPS
 
 /*
@@ -349,6 +353,7 @@ void ntp_clear(void)
 	tick_length	= tick_length_base;
 	time_offset	= 0;
 
+	ntp_next_leap_sec = TIME64_MAX;
 	/* Clear PPS state variables */
 	pps_clear();
 }
@@ -359,6 +364,21 @@ u64 ntp_tick_length(void)
 	return tick_length;
 }
 
+/**
+ * ntp_get_next_leap - Returns the next leapsecond in CLOCK_REALTIME ktime_t
+ *
+ * Provides the time of the next leapsecond against CLOCK_REALTIME in
+ * a ktime_t format. Returns KTIME_MAX if no leapsecond is pending.
+ */
+ktime_t ntp_get_next_leap(void)
+{
+	ktime_t ret;
+
+	if ((time_state == TIME_INS) && (time_status & STA_INS))
+		return ktime_set(ntp_next_leap_sec, 0);
+	ret.tv64 = KTIME_MAX;
+	return ret;
+}
 
 /*
  * this routine handles the overflow of the microsecond field
@@ -382,15 +402,21 @@ int second_overflow(unsigned long secs)
 	 */
 	switch (time_state) {
 	case TIME_OK:
-		if (time_status & STA_INS)
+		if (time_status & STA_INS) {
 			time_state = TIME_INS;
-		else if (time_status & STA_DEL)
+			ntp_next_leap_sec = secs + SECS_PER_DAY -
+						(secs % SECS_PER_DAY);
+		} else if (time_status & STA_DEL) {
 			time_state = TIME_DEL;
+			ntp_next_leap_sec = secs + SECS_PER_DAY -
+						 ((secs+1) % SECS_PER_DAY);
+		}
 		break;
 	case TIME_INS:
-		if (!(time_status & STA_INS))
+		if (!(time_status & STA_INS)) {
+			ntp_next_leap_sec = TIME64_MAX;
 			time_state = TIME_OK;
-		else if (secs % 86400 == 0) {
+		} else if (secs % SECS_PER_DAY == 0) {
 			leap = -1;
 			time_state = TIME_OOP;
 			printk(KERN_NOTICE
@@ -398,19 +424,21 @@ int second_overflow(unsigned long secs)
 		}
 		break;
 	case TIME_DEL:
-		if (!(time_status & STA_DEL))
+		if (!(time_status & STA_DEL)) {
+			ntp_next_leap_sec = TIME64_MAX;
 			time_state = TIME_OK;
-		else if ((secs + 1) % 86400 == 0) {
+		} else if ((secs + 1) % SECS_PER_DAY == 0) {
 			leap = 1;
+			ntp_next_leap_sec = TIME64_MAX;
 			time_state = TIME_WAIT;
 			printk(KERN_NOTICE
 				"Clock: deleting leap second 23:59:59 UTC\n");
 		}
 		break;
 	case TIME_OOP:
+		ntp_next_leap_sec = TIME64_MAX;
 		time_state = TIME_WAIT;
 		break;
-
 	case TIME_WAIT:
 		if (!(time_status & (STA_INS | STA_DEL)))
 			time_state = TIME_OK;
@@ -547,6 +575,7 @@ static inline void process_adj_status(struct timex *txc, struct timespec64 *ts)
 	if ((time_status & STA_PLL) && !(txc->status & STA_PLL)) {
 		time_state = TIME_OK;
 		time_status = STA_UNSYNC;
+		ntp_next_leap_sec = TIME64_MAX;
 		/* restart PPS frequency calibration */
 		pps_reset_freq_interval();
 	}
@@ -711,6 +740,24 @@ int __do_adjtimex(struct timex *txc, struct timespec64 *ts, s32 *time_tai)
 	if (!(time_status & STA_NANO))
 		txc->time.tv_usec /= NSEC_PER_USEC;
 
+	/* Handle leapsec adjustments */
+	if (unlikely(ts->tv_sec >= ntp_next_leap_sec)) {
+		if ((time_state == TIME_INS) && (time_status & STA_INS)) {
+			result = TIME_OOP;
+			txc->tai++;
+			txc->time.tv_sec--;
+		}
+		if ((time_state == TIME_DEL) && (time_status & STA_DEL)) {
+			result = TIME_WAIT;
+			txc->tai--;
+			txc->time.tv_sec++;
+		}
+		if ((time_state == TIME_OOP) &&
+					(ts->tv_sec == ntp_next_leap_sec)) {
+			result = TIME_WAIT;
+		}
+	}
+
 	return result;
 }
 

kernel/time/ntp_internal.h

@@ -5,6 +5,7 @@ extern void ntp_init(void);
 extern void ntp_clear(void);
 /* Returns how long ticks are at present, in ns / 2^NTP_SCALE_SHIFT. */
 extern u64 ntp_tick_length(void);
+extern ktime_t ntp_get_next_leap(void);
 extern int second_overflow(unsigned long secs);
 extern int ntp_validate_timex(struct timex *);
 extern int __do_adjtimex(struct timex *, struct timespec64 *, s32 *);

kernel/time/posix-timers.c

@@ -272,13 +272,20 @@ static int posix_get_tai(clockid_t which_clock, struct timespec *tp)
 	return 0;
 }
 
+static int posix_get_hrtimer_res(clockid_t which_clock, struct timespec *tp)
+{
+	tp->tv_sec = 0;
+	tp->tv_nsec = hrtimer_resolution;
+	return 0;
+}
+
 /*
  * Initialize everything, well, just everything in Posix clocks/timers ;)
  */
 static __init int init_posix_timers(void)
 {
 	struct k_clock clock_realtime = {
-		.clock_getres	= hrtimer_get_res,
+		.clock_getres	= posix_get_hrtimer_res,
 		.clock_get	= posix_clock_realtime_get,
 		.clock_set	= posix_clock_realtime_set,
 		.clock_adj	= posix_clock_realtime_adj,
@@ -290,7 +297,7 @@ static __init int init_posix_timers(void)
 		.timer_del	= common_timer_del,
 	};
 	struct k_clock clock_monotonic = {
-		.clock_getres	= hrtimer_get_res,
+		.clock_getres	= posix_get_hrtimer_res,
 		.clock_get	= posix_ktime_get_ts,
 		.nsleep		= common_nsleep,
 		.nsleep_restart	= hrtimer_nanosleep_restart,
@@ -300,7 +307,7 @@ static __init int init_posix_timers(void)
 		.timer_del	= common_timer_del,
 	};
 	struct k_clock clock_monotonic_raw = {
-		.clock_getres	= hrtimer_get_res,
+		.clock_getres	= posix_get_hrtimer_res,
 		.clock_get	= posix_get_monotonic_raw,
 	};
 	struct k_clock clock_realtime_coarse = {
@@ -312,7 +319,7 @@ static __init int init_posix_timers(void)
 		.clock_get	= posix_get_monotonic_coarse,
 	};
 	struct k_clock clock_tai = {
-		.clock_getres	= hrtimer_get_res,
+		.clock_getres	= posix_get_hrtimer_res,
 		.clock_get	= posix_get_tai,
 		.nsleep		= common_nsleep,
 		.nsleep_restart	= hrtimer_nanosleep_restart,
@@ -322,7 +329,7 @@ static __init int init_posix_timers(void)
 		.timer_del	= common_timer_del,
 	};
 	struct k_clock clock_boottime = {
-		.clock_getres	= hrtimer_get_res,
+		.clock_getres	= posix_get_hrtimer_res,
 		.clock_get	= posix_get_boottime,
 		.nsleep		= common_nsleep,
 		.nsleep_restart	= hrtimer_nanosleep_restart,

kernel/time/tick-broadcast-hrtimer.c

@@ -22,6 +22,7 @@ static void bc_set_mode(enum clock_event_mode mode,
 			struct clock_event_device *bc)
 {
 	switch (mode) {
+	case CLOCK_EVT_MODE_UNUSED:
 	case CLOCK_EVT_MODE_SHUTDOWN:
 		/*
 		 * Note, we cannot cancel the timer here as we might
@@ -66,9 +67,11 @@ static int bc_set_next(ktime_t expires, struct clock_event_device *bc)
 	 * hrtimer_{start/cancel} functions call into tracing,
 	 * calls to these functions must be bound within RCU_NONIDLE.
 	 */
-	RCU_NONIDLE(bc_moved = (hrtimer_try_to_cancel(&bctimer) >= 0) ?
-		!hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED) :
-			0);
+	RCU_NONIDLE({
+			bc_moved = hrtimer_try_to_cancel(&bctimer) >= 0;
+			if (bc_moved)
+				hrtimer_start(&bctimer, expires,
+					      HRTIMER_MODE_ABS_PINNED);});
 	if (bc_moved) {
 		/* Bind the "device" to the cpu */
 		bc->bound_on = smp_processor_id();
@@ -99,10 +102,13 @@ static enum hrtimer_restart bc_handler(struct hrtimer *t)
 {
 	ce_broadcast_hrtimer.event_handler(&ce_broadcast_hrtimer);
 
-	if (ce_broadcast_hrtimer.next_event.tv64 == KTIME_MAX)
+	switch (ce_broadcast_hrtimer.mode) {
+	case CLOCK_EVT_MODE_ONESHOT:
+		if (ce_broadcast_hrtimer.next_event.tv64 != KTIME_MAX)
+			return HRTIMER_RESTART;
+	default:
 		return HRTIMER_NORESTART;
-
-	return HRTIMER_RESTART;
+	}
 }
 
 void tick_setup_hrtimer_broadcast(void)

kernel/time/tick-broadcast.c

@@ -255,18 +255,18 @@ int tick_receive_broadcast(void)
 /*
  * Broadcast the event to the cpus, which are set in the mask (mangled).
  */
-static void tick_do_broadcast(struct cpumask *mask)
+static bool tick_do_broadcast(struct cpumask *mask)
 {
 	int cpu = smp_processor_id();
 	struct tick_device *td;
+	bool local = false;
 
 	/*
 	 * Check, if the current cpu is in the mask
 	 */
 	if (cpumask_test_cpu(cpu, mask)) {
 		cpumask_clear_cpu(cpu, mask);
-		td = &per_cpu(tick_cpu_device, cpu);
-		td->evtdev->event_handler(td->evtdev);
+		local = true;
 	}
 
 	if (!cpumask_empty(mask)) {
@@ -279,16 +279,17 @@ static void tick_do_broadcast(struct cpumask *mask)
 		td = &per_cpu(tick_cpu_device, cpumask_first(mask));
 		td->evtdev->broadcast(mask);
 	}
+	return local;
 }
 
 /*
  * Periodic broadcast:
  * - invoke the broadcast handlers
  */
-static void tick_do_periodic_broadcast(void)
+static bool tick_do_periodic_broadcast(void)
 {
 	cpumask_and(tmpmask, cpu_online_mask, tick_broadcast_mask);
-	tick_do_broadcast(tmpmask);
+	return tick_do_broadcast(tmpmask);
 }
 
 /*
@@ -296,34 +297,26 @@ static void tick_do_periodic_broadcast(void)
  */
 static void tick_handle_periodic_broadcast(struct clock_event_device *dev)
 {
-	ktime_t next;
+	struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
+	bool bc_local;
 
 	raw_spin_lock(&tick_broadcast_lock);
+	bc_local = tick_do_periodic_broadcast();
 
-	tick_do_periodic_broadcast();
+	if (clockevent_state_oneshot(dev)) {
+		ktime_t next = ktime_add(dev->next_event, tick_period);
 
-	/*
-	 * The device is in periodic mode. No reprogramming necessary:
-	 */
-	if (dev->state == CLOCK_EVT_STATE_PERIODIC)
-		goto unlock;
+		clockevents_program_event(dev, next, true);
+	}
+	raw_spin_unlock(&tick_broadcast_lock);
 
 	/*
-	 * Setup the next period for devices, which do not have
-	 * periodic mode. We read dev->next_event first and add to it
-	 * when the event already expired. clockevents_program_event()
-	 * sets dev->next_event only when the event is really
-	 * programmed to the device.
+	 * We run the handler of the local cpu after dropping
+	 * tick_broadcast_lock because the handler might deadlock when
+	 * trying to switch to oneshot mode.
 	 */
-	for (next = dev->next_event; ;) {
-		next = ktime_add(next, tick_period);
-
-		if (!clockevents_program_event(dev, next, false))
-			goto unlock;
-		tick_do_periodic_broadcast();
-	}
-unlock:
-	raw_spin_unlock(&tick_broadcast_lock);
+	if (bc_local)
+		td->evtdev->event_handler(td->evtdev);
 }
 
 /**
@@ -532,23 +525,19 @@ static void tick_broadcast_set_affinity(struct clock_event_device *bc,
 	irq_set_affinity(bc->irq, bc->cpumask);
 }
 
-static int tick_broadcast_set_event(struct clock_event_device *bc, int cpu,
-				    ktime_t expires, int force)
+static void tick_broadcast_set_event(struct clock_event_device *bc, int cpu,
+				     ktime_t expires)
 {
-	int ret;
-
-	if (bc->state != CLOCK_EVT_STATE_ONESHOT)
-		clockevents_set_state(bc, CLOCK_EVT_STATE_ONESHOT);
+	if (!clockevent_state_oneshot(bc))
+		clockevents_switch_state(bc, CLOCK_EVT_STATE_ONESHOT);
 
-	ret = clockevents_program_event(bc, expires, force);
-	if (!ret)
-		tick_broadcast_set_affinity(bc, cpumask_of(cpu));
-	return ret;
+	clockevents_program_event(bc, expires, 1);
+	tick_broadcast_set_affinity(bc, cpumask_of(cpu));
 }
 
 static void tick_resume_broadcast_oneshot(struct clock_event_device *bc)
 {
-	clockevents_set_state(bc, CLOCK_EVT_STATE_ONESHOT);
+	clockevents_switch_state(bc, CLOCK_EVT_STATE_ONESHOT);
 }
 
 /*
@@ -566,7 +555,7 @@ void tick_check_oneshot_broadcast_this_cpu(void)
 		 * switched over, leave the device alone.
 		 */
 		if (td->mode == TICKDEV_MODE_ONESHOT) {
-			clockevents_set_state(td->evtdev,
+			clockevents_switch_state(td->evtdev,
 					      CLOCK_EVT_STATE_ONESHOT);
 		}
 	}
@@ -580,9 +569,9 @@ static void tick_handle_oneshot_broadcast(struct clock_event_device *dev)
 	struct tick_device *td;
 	ktime_t now, next_event;
 	int cpu, next_cpu = 0;
+	bool bc_local;
 
 	raw_spin_lock(&tick_broadcast_lock);
-again:
 	dev->next_event.tv64 = KTIME_MAX;
 	next_event.tv64 = KTIME_MAX;
 	cpumask_clear(tmpmask);
@@ -624,7 +613,7 @@ again:
 	/*
 	 * Wakeup the cpus which have an expired event.
 	 */
-	tick_do_broadcast(tmpmask);
+	bc_local = tick_do_broadcast(tmpmask);
 
 	/*
 	 * Two reasons for reprogram:
@@ -636,15 +625,15 @@ again:
 	 * - There are pending events on sleeping CPUs which were not
 	 * in the event mask
 	 */
-	if (next_event.tv64 != KTIME_MAX) {
-		/*
-		 * Rearm the broadcast device. If event expired,
-		 * repeat the above
-		 */
-		if (tick_broadcast_set_event(dev, next_cpu, next_event, 0))
-			goto again;
-	}
+	if (next_event.tv64 != KTIME_MAX)
+		tick_broadcast_set_event(dev, next_cpu, next_event);
+
 	raw_spin_unlock(&tick_broadcast_lock);
+
+	if (bc_local) {
+		td = this_cpu_ptr(&tick_cpu_device);
+		td->evtdev->event_handler(td->evtdev);
+	}
 }
 
 static int broadcast_needs_cpu(struct clock_event_device *bc, int cpu)
@@ -670,7 +659,7 @@ static void broadcast_shutdown_local(struct clock_event_device *bc,
 		if (dev->next_event.tv64 < bc->next_event.tv64)
 			return;
 	}
-	clockevents_set_state(dev, CLOCK_EVT_STATE_SHUTDOWN);
+	clockevents_switch_state(dev, CLOCK_EVT_STATE_SHUTDOWN);
 }
 
 /**
@@ -726,7 +715,7 @@ int tick_broadcast_oneshot_control(enum tick_broadcast_state state)
 			 */
 			if (!cpumask_test_cpu(cpu, tick_broadcast_force_mask) &&
 			    dev->next_event.tv64 < bc->next_event.tv64)
-				tick_broadcast_set_event(bc, cpu, dev->next_event, 1);
+				tick_broadcast_set_event(bc, cpu, dev->next_event);
 		}
 		/*
 		 * If the current CPU owns the hrtimer broadcast
@@ -740,7 +729,7 @@ int tick_broadcast_oneshot_control(enum tick_broadcast_state state)
 			cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask);
 	} else {
 		if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_oneshot_mask)) {
-			clockevents_set_state(dev, CLOCK_EVT_STATE_ONESHOT);
+			clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT);
 			/*
 			 * The cpu which was handling the broadcast
 			 * timer marked this cpu in the broadcast
@@ -842,7 +831,7 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 
 	/* Set it up only once ! */
 	if (bc->event_handler != tick_handle_oneshot_broadcast) {
-		int was_periodic = bc->state == CLOCK_EVT_STATE_PERIODIC;
+		int was_periodic = clockevent_state_periodic(bc);
 
 		bc->event_handler = tick_handle_oneshot_broadcast;
 
@@ -858,10 +847,10 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 			   tick_broadcast_oneshot_mask, tmpmask);
 
 		if (was_periodic && !cpumask_empty(tmpmask)) {
-			clockevents_set_state(bc, CLOCK_EVT_STATE_ONESHOT);
+			clockevents_switch_state(bc, CLOCK_EVT_STATE_ONESHOT);
 			tick_broadcast_init_next_event(tmpmask,
 						       tick_next_period);
-			tick_broadcast_set_event(bc, cpu, tick_next_period, 1);
+			tick_broadcast_set_event(bc, cpu, tick_next_period);
 		} else
 			bc->next_event.tv64 = KTIME_MAX;
 	} else {

kernel/time/tick-common.c

@@ -102,7 +102,17 @@ void tick_handle_periodic(struct clock_event_device *dev)
 
 	tick_periodic(cpu);
 
-	if (dev->state != CLOCK_EVT_STATE_ONESHOT)
+#if defined(CONFIG_HIGH_RES_TIMERS) || defined(CONFIG_NO_HZ_COMMON)
+	/*
+	 * The cpu might have transitioned to HIGHRES or NOHZ mode via
+	 * update_process_times() -> run_local_timers() ->
+	 * hrtimer_run_queues().
+	 */
+	if (dev->event_handler != tick_handle_periodic)
+		return;
+#endif
+
+	if (!clockevent_state_oneshot(dev))
 		return;
 	for (;;) {
 		/*
@@ -140,7 +150,7 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast)
 
 	if ((dev->features & CLOCK_EVT_FEAT_PERIODIC) &&
 	    !tick_broadcast_oneshot_active()) {
-		clockevents_set_state(dev, CLOCK_EVT_STATE_PERIODIC);
+		clockevents_switch_state(dev, CLOCK_EVT_STATE_PERIODIC);
 	} else {
 		unsigned long seq;
 		ktime_t next;
@@ -150,7 +160,7 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast)
 			next = tick_next_period;
 		} while (read_seqretry(&jiffies_lock, seq));
 
-		clockevents_set_state(dev, CLOCK_EVT_STATE_ONESHOT);
+		clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT);
 
 		for (;;) {
 			if (!clockevents_program_event(dev, next, false))
@@ -367,7 +377,7 @@ void tick_shutdown(unsigned int cpu)
 		 * Prevent that the clock events layer tries to call
 		 * the set mode function!
 		 */
-		dev->state = CLOCK_EVT_STATE_DETACHED;
+		clockevent_set_state(dev, CLOCK_EVT_STATE_DETACHED);
 		dev->mode = CLOCK_EVT_MODE_UNUSED;
 		clockevents_exchange_device(dev, NULL);
 		dev->event_handler = clockevents_handle_noop;

kernel/time/tick-internal.h

@@ -36,11 +36,22 @@ static inline int tick_device_is_functional(struct clock_event_device *dev)
 	return !(dev->features & CLOCK_EVT_FEAT_DUMMY);
 }
 
+static inline enum clock_event_state clockevent_get_state(struct clock_event_device *dev)
+{
+	return dev->state_use_accessors;
+}
+
+static inline void clockevent_set_state(struct clock_event_device *dev,
+					enum clock_event_state state)
+{
+	dev->state_use_accessors = state;
+}
+
 extern void clockevents_shutdown(struct clock_event_device *dev);
 extern void clockevents_exchange_device(struct clock_event_device *old,
 					struct clock_event_device *new);
-extern void clockevents_set_state(struct clock_event_device *dev,
-				 enum clock_event_state state);
+extern void clockevents_switch_state(struct clock_event_device *dev,
+				     enum clock_event_state state);
 extern int clockevents_program_event(struct clock_event_device *dev,
 				     ktime_t expires, bool force);
 extern void clockevents_handle_noop(struct clock_event_device *dev);
@@ -137,3 +148,5 @@ extern void tick_nohz_init(void);
 # else
 static inline void tick_nohz_init(void) { }
 #endif
+
+extern u64 get_next_timer_interrupt(unsigned long basej, u64 basem);

kernel/time/tick-oneshot.c

@@ -28,6 +28,22 @@ int tick_program_event(ktime_t expires, int force)
 {
 	struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
 
+	if (unlikely(expires.tv64 == KTIME_MAX)) {
+		/*
+		 * We don't need the clock event device any more, stop it.
+		 */
+		clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT_STOPPED);
+		return 0;
+	}
+
+	if (unlikely(clockevent_state_oneshot_stopped(dev))) {
+		/*
+		 * We need the clock event again, configure it in ONESHOT mode
+		 * before using it.
+		 */
+		clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT);
+	}
+
 	return clockevents_program_event(dev, expires, force);
 }
 
@@ -38,7 +54,7 @@ void tick_resume_oneshot(void)
 {
 	struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
 
-	clockevents_set_state(dev, CLOCK_EVT_STATE_ONESHOT);
+	clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT);
 	clockevents_program_event(dev, ktime_get(), true);
 }
 
@@ -50,7 +66,7 @@ void tick_setup_oneshot(struct clock_event_device *newdev,
 			ktime_t next_event)
 {
 	newdev->event_handler = handler;
-	clockevents_set_state(newdev, CLOCK_EVT_STATE_ONESHOT);
+	clockevents_switch_state(newdev, CLOCK_EVT_STATE_ONESHOT);
 	clockevents_program_event(newdev, next_event, true);
 }
 
@@ -81,7 +97,7 @@ int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *))
 
 	td->mode = TICKDEV_MODE_ONESHOT;
 	dev->event_handler = handler;
-	clockevents_set_state(dev, CLOCK_EVT_STATE_ONESHOT);
+	clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT);
 	tick_broadcast_switch_to_oneshot();
 	return 0;
 }

kernel/time/tick-sched.c

@@ -565,156 +565,144 @@ u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time)
 }
 EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us);
 
+static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
+{
+	hrtimer_cancel(&ts->sched_timer);
+	hrtimer_set_expires(&ts->sched_timer, ts->last_tick);
+
+	/* Forward the time to expire in the future */
+	hrtimer_forward(&ts->sched_timer, now, tick_period);
+
+	if (ts->nohz_mode == NOHZ_MODE_HIGHRES)
+		hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED);
+	else
+		tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1);
+}
+
 static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 					 ktime_t now, int cpu)
 {
-	unsigned long seq, last_jiffies, next_jiffies, delta_jiffies;
-	ktime_t last_update, expires, ret = { .tv64 = 0 };
-	unsigned long rcu_delta_jiffies;
 	struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
-	u64 time_delta;
-
-	time_delta = timekeeping_max_deferment();
+	u64 basemono, next_tick, next_tmr, next_rcu, delta, expires;
+	unsigned long seq, basejiff;
+	ktime_t	tick;
 
 	/* Read jiffies and the time when jiffies were updated last */
 	do {
 		seq = read_seqbegin(&jiffies_lock);
-		last_update = last_jiffies_update;
-		last_jiffies = jiffies;
+		basemono = last_jiffies_update.tv64;
+		basejiff = jiffies;
 	} while (read_seqretry(&jiffies_lock, seq));
+	ts->last_jiffies = basejiff;
 
-	if (rcu_needs_cpu(&rcu_delta_jiffies) ||
+	if (rcu_needs_cpu(basemono, &next_rcu) ||
 	    arch_needs_cpu() || irq_work_needs_cpu()) {
-		next_jiffies = last_jiffies + 1;
-		delta_jiffies = 1;
+		next_tick = basemono + TICK_NSEC;
 	} else {
-		/* Get the next timer wheel timer */
-		next_jiffies = get_next_timer_interrupt(last_jiffies);
-		delta_jiffies = next_jiffies - last_jiffies;
-		if (rcu_delta_jiffies < delta_jiffies) {
-			next_jiffies = last_jiffies + rcu_delta_jiffies;
-			delta_jiffies = rcu_delta_jiffies;
-		}
+		/*
+		 * Get the next pending timer. If high resolution
+		 * timers are enabled this only takes the timer wheel
+		 * timers into account. If high resolution timers are
+		 * disabled this also looks at the next expiring
+		 * hrtimer.
+		 */
+		next_tmr = get_next_timer_interrupt(basejiff, basemono);
+		ts->next_timer = next_tmr;
+		/* Take the next rcu event into account */
+		next_tick = next_rcu < next_tmr ? next_rcu : next_tmr;
 	}
 
 	/*
-	 * Do not stop the tick, if we are only one off (or less)
-	 * or if the cpu is required for RCU:
+	 * If the tick is due in the next period, keep it ticking or
+	 * restart it proper.
 	 */
-	if (!ts->tick_stopped && delta_jiffies <= 1)
-		goto out;
-
-	/* Schedule the tick, if we are at least one jiffie off */
-	if ((long)delta_jiffies >= 1) {
-
-		/*
-		 * If this cpu is the one which updates jiffies, then
-		 * give up the assignment and let it be taken by the
-		 * cpu which runs the tick timer next, which might be
-		 * this cpu as well. If we don't drop this here the
-		 * jiffies might be stale and do_timer() never
-		 * invoked. Keep track of the fact that it was the one
-		 * which had the do_timer() duty last. If this cpu is
-		 * the one which had the do_timer() duty last, we
-		 * limit the sleep time to the timekeeping
-		 * max_deferement value which we retrieved
-		 * above. Otherwise we can sleep as long as we want.
-		 */
-		if (cpu == tick_do_timer_cpu) {
-			tick_do_timer_cpu = TICK_DO_TIMER_NONE;
-			ts->do_timer_last = 1;
-		} else if (tick_do_timer_cpu != TICK_DO_TIMER_NONE) {
-			time_delta = KTIME_MAX;
-			ts->do_timer_last = 0;
-		} else if (!ts->do_timer_last) {
-			time_delta = KTIME_MAX;
+	delta = next_tick - basemono;
+	if (delta <= (u64)TICK_NSEC) {
+		tick.tv64 = 0;
+		if (!ts->tick_stopped)
+			goto out;
+		if (delta == 0) {
+			/* Tick is stopped, but required now. Enforce it */
+			tick_nohz_restart(ts, now);
+			goto out;
 		}
+	}
+
+	/*
+	 * If this cpu is the one which updates jiffies, then give up
+	 * the assignment and let it be taken by the cpu which runs
+	 * the tick timer next, which might be this cpu as well. If we
+	 * don't drop this here the jiffies might be stale and
+	 * do_timer() never invoked. Keep track of the fact that it
+	 * was the one which had the do_timer() duty last. If this cpu
+	 * is the one which had the do_timer() duty last, we limit the
+	 * sleep time to the timekeeping max_deferement value.
+	 * Otherwise we can sleep as long as we want.
+	 */
+	delta = timekeeping_max_deferment();
+	if (cpu == tick_do_timer_cpu) {
+		tick_do_timer_cpu = TICK_DO_TIMER_NONE;
+		ts->do_timer_last = 1;
+	} else if (tick_do_timer_cpu != TICK_DO_TIMER_NONE) {
+		delta = KTIME_MAX;
+		ts->do_timer_last = 0;
+	} else if (!ts->do_timer_last) {
+		delta = KTIME_MAX;
+	}
 
 #ifdef CONFIG_NO_HZ_FULL
-		if (!ts->inidle) {
-			time_delta = min(time_delta,
-					 scheduler_tick_max_deferment());
-		}
+	/* Limit the tick delta to the maximum scheduler deferment */
+	if (!ts->inidle)
+		delta = min(delta, scheduler_tick_max_deferment());
 #endif
 
-		/*
-		 * calculate the expiry time for the next timer wheel
-		 * timer. delta_jiffies >= NEXT_TIMER_MAX_DELTA signals
-		 * that there is no timer pending or at least extremely
-		 * far into the future (12 days for HZ=1000). In this
-		 * case we set the expiry to the end of time.
-		 */
-		if (likely(delta_jiffies < NEXT_TIMER_MAX_DELTA)) {
-			/*
-			 * Calculate the time delta for the next timer event.
-			 * If the time delta exceeds the maximum time delta
-			 * permitted by the current clocksource then adjust
-			 * the time delta accordingly to ensure the
-			 * clocksource does not wrap.
-			 */
-			time_delta = min_t(u64, time_delta,
-					   tick_period.tv64 * delta_jiffies);
-		}
-
-		if (time_delta < KTIME_MAX)
-			expires = ktime_add_ns(last_update, time_delta);
-		else
-			expires.tv64 = KTIME_MAX;
-
-		/* Skip reprogram of event if its not changed */
-		if (ts->tick_stopped && ktime_equal(expires, dev->next_event))
-			goto out;
+	/* Calculate the next expiry time */
+	if (delta < (KTIME_MAX - basemono))
+		expires = basemono + delta;
+	else
+		expires = KTIME_MAX;
 
-		ret = expires;
+	expires = min_t(u64, expires, next_tick);
+	tick.tv64 = expires;
 
-		/*
-		 * nohz_stop_sched_tick can be called several times before
-		 * the nohz_restart_sched_tick is called. This happens when
-		 * interrupts arrive which do not cause a reschedule. In the
-		 * first call we save the current tick time, so we can restart
-		 * the scheduler tick in nohz_restart_sched_tick.
-		 */
-		if (!ts->tick_stopped) {
-			nohz_balance_enter_idle(cpu);
-			calc_load_enter_idle();
+	/* Skip reprogram of event if its not changed */
+	if (ts->tick_stopped && (expires == dev->next_event.tv64))
+		goto out;
 
-			ts->last_tick = hrtimer_get_expires(&ts->sched_timer);
-			ts->tick_stopped = 1;
-			trace_tick_stop(1, " ");
-		}
+	/*
+	 * nohz_stop_sched_tick can be called several times before
+	 * the nohz_restart_sched_tick is called. This happens when
+	 * interrupts arrive which do not cause a reschedule. In the
+	 * first call we save the current tick time, so we can restart
+	 * the scheduler tick in nohz_restart_sched_tick.
+	 */
+	if (!ts->tick_stopped) {
+		nohz_balance_enter_idle(cpu);
+		calc_load_enter_idle();
 
-		/*
-		 * If the expiration time == KTIME_MAX, then
-		 * in this case we simply stop the tick timer.
-		 */
-		 if (unlikely(expires.tv64 == KTIME_MAX)) {
-			if (ts->nohz_mode == NOHZ_MODE_HIGHRES)
-				hrtimer_cancel(&ts->sched_timer);
-			goto out;
-		}
+		ts->last_tick = hrtimer_get_expires(&ts->sched_timer);
+		ts->tick_stopped = 1;
+		trace_tick_stop(1, " ");
+	}
 
-		if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
-			hrtimer_start(&ts->sched_timer, expires,
-				      HRTIMER_MODE_ABS_PINNED);
-			/* Check, if the timer was already in the past */
-			if (hrtimer_active(&ts->sched_timer))
-				goto out;
-		} else if (!tick_program_event(expires, 0))
-				goto out;
-		/*
-		 * We are past the event already. So we crossed a
-		 * jiffie boundary. Update jiffies and raise the
-		 * softirq.
-		 */
-		tick_do_update_jiffies64(ktime_get());
+	/*
+	 * If the expiration time == KTIME_MAX, then we simply stop
+	 * the tick timer.
+	 */
+	if (unlikely(expires == KTIME_MAX)) {
+		if (ts->nohz_mode == NOHZ_MODE_HIGHRES)
+			hrtimer_cancel(&ts->sched_timer);
+		goto out;
 	}
-	raise_softirq_irqoff(TIMER_SOFTIRQ);
+
+	if (ts->nohz_mode == NOHZ_MODE_HIGHRES)
+		hrtimer_start(&ts->sched_timer, tick, HRTIMER_MODE_ABS_PINNED);
+	else
+		tick_program_event(tick, 1);
 out:
-	ts->next_jiffies = next_jiffies;
-	ts->last_jiffies = last_jiffies;
+	/* Update the estimated sleep length */
 	ts->sleep_length = ktime_sub(dev->next_event, now);
-
-	return ret;
+	return tick;
 }
 
 static void tick_nohz_full_stop_tick(struct tick_sched *ts)
@@ -876,32 +864,6 @@ ktime_t tick_nohz_get_sleep_length(void)
 	return ts->sleep_length;
 }
 
-static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
-{
-	hrtimer_cancel(&ts->sched_timer);
-	hrtimer_set_expires(&ts->sched_timer, ts->last_tick);
-
-	while (1) {
-		/* Forward the time to expire in the future */
-		hrtimer_forward(&ts->sched_timer, now, tick_period);
-
-		if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
-			hrtimer_start_expires(&ts->sched_timer,
-					      HRTIMER_MODE_ABS_PINNED);
-			/* Check, if the timer was already in the past */
-			if (hrtimer_active(&ts->sched_timer))
-				break;
-		} else {
-			if (!tick_program_event(
-				hrtimer_get_expires(&ts->sched_timer), 0))
-				break;
-		}
-		/* Reread time and update jiffies */
-		now = ktime_get();
-		tick_do_update_jiffies64(now);
-	}
-}
-
 static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now)
 {
 	/* Update jiffies first */
@@ -972,12 +934,6 @@ void tick_nohz_idle_exit(void)
 	local_irq_enable();
 }
 
-static int tick_nohz_reprogram(struct tick_sched *ts, ktime_t now)
-{
-	hrtimer_forward(&ts->sched_timer, now, tick_period);
-	return tick_program_event(hrtimer_get_expires(&ts->sched_timer), 0);
-}
-
 /*
  * The nohz low res interrupt handler
  */
@@ -996,10 +952,8 @@ static void tick_nohz_handler(struct clock_event_device *dev)
 	if (unlikely(ts->tick_stopped))
 		return;
 
-	while (tick_nohz_reprogram(ts, now)) {
-		now = ktime_get();
-		tick_do_update_jiffies64(now);
-	}
+	hrtimer_forward(&ts->sched_timer, now, tick_period);
+	tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1);
 }
 
 /**
@@ -1013,11 +967,9 @@ static void tick_nohz_switch_to_nohz(void)
 	if (!tick_nohz_enabled)
 		return;
 
-	local_irq_disable();
-	if (tick_switch_to_oneshot(tick_nohz_handler)) {
-		local_irq_enable();
+	if (tick_switch_to_oneshot(tick_nohz_handler))
 		return;
-	}
+
 	tick_nohz_active = 1;
 	ts->nohz_mode = NOHZ_MODE_LOWRES;
 
@@ -1029,13 +981,9 @@ static void tick_nohz_switch_to_nohz(void)
 	/* Get the next period */
 	next = tick_init_jiffy_update();
 
-	for (;;) {
-		hrtimer_set_expires(&ts->sched_timer, next);
-		if (!tick_program_event(next, 0))
-			break;
-		next = ktime_add(next, tick_period);
-	}
-	local_irq_enable();
+	hrtimer_forward_now(&ts->sched_timer, tick_period);
+	hrtimer_set_expires(&ts->sched_timer, next);
+	tick_program_event(next, 1);
 }
 
 /*
@@ -1167,15 +1115,8 @@ void tick_setup_sched_timer(void)
 		hrtimer_add_expires_ns(&ts->sched_timer, offset);
 	}
 
-	for (;;) {
-		hrtimer_forward(&ts->sched_timer, now, tick_period);
-		hrtimer_start_expires(&ts->sched_timer,
-				      HRTIMER_MODE_ABS_PINNED);
-		/* Check, if the timer was already in the past */
-		if (hrtimer_active(&ts->sched_timer))
-			break;
-		now = ktime_get();
-	}
+	hrtimer_forward(&ts->sched_timer, now, tick_period);
+	hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED);
 
 #ifdef CONFIG_NO_HZ_COMMON
 	if (tick_nohz_enabled) {
@@ -1227,7 +1168,7 @@ void tick_oneshot_notify(void)
  * Called cyclic from the hrtimer softirq (driven by the timer
  * softirq) allow_nohz signals, that we can switch into low-res nohz
  * mode, because high resolution timers are disabled (either compile
- * or runtime).
+ * or runtime). Called with interrupts disabled.
  */
 int tick_check_oneshot_change(int allow_nohz)
 {

kernel/time/tick-sched.h

@@ -57,7 +57,7 @@ struct tick_sched {
 	ktime_t				iowait_sleeptime;
 	ktime_t				sleep_length;
 	unsigned long			last_jiffies;
-	unsigned long			next_jiffies;
+	u64				next_timer;
 	ktime_t				idle_expires;
 	int				do_timer_last;
 };

kernel/time/time.c

@@ -41,7 +41,7 @@
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
 
-#include "timeconst.h"
+#include <generated/timeconst.h>
 #include "timekeeping.h"
 
 /*
@@ -173,6 +173,10 @@ int do_sys_settimeofday(const struct timespec *tv, const struct timezone *tz)
 		return error;
 
 	if (tz) {
+		/* Verify we're witin the +-15 hrs range */
+		if (tz->tz_minuteswest > 15*60 || tz->tz_minuteswest < -15*60)
+			return -EINVAL;
+
 		sys_tz = *tz;
 		update_vsyscall_tz();
 		if (firsttime) {
@@ -483,9 +487,11 @@ struct timespec64 ns_to_timespec64(const s64 nsec)
 }
 EXPORT_SYMBOL(ns_to_timespec64);
 #endif
-/*
- * When we convert to jiffies then we interpret incoming values
- * the following way:
+/**
+ * msecs_to_jiffies: - convert milliseconds to jiffies
+ * @m:	time in milliseconds
+ *
+ * conversion is done as follows:
  *
  * - negative values mean 'infinite timeout' (MAX_JIFFY_OFFSET)
  *
@@ -493,66 +499,36 @@ EXPORT_SYMBOL(ns_to_timespec64);
  *   MAX_JIFFY_OFFSET values] mean 'infinite timeout' too.
  *
  * - all other values are converted to jiffies by either multiplying
- *   the input value by a factor or dividing it with a factor
- *
- * We must also be careful about 32-bit overflows.
+ *   the input value by a factor or dividing it with a factor and
+ *   handling any 32-bit overflows.
+ *   for the details see __msecs_to_jiffies()
+ *
+ * msecs_to_jiffies() checks for the passed in value being a constant
+ * via __builtin_constant_p() allowing gcc to eliminate most of the
+ * code, __msecs_to_jiffies() is called if the value passed does not
+ * allow constant folding and the actual conversion must be done at
+ * runtime.
+ * the _msecs_to_jiffies helpers are the HZ dependent conversion
+ * routines found in include/linux/jiffies.h
  */
-unsigned long msecs_to_jiffies(const unsigned int m)
+unsigned long __msecs_to_jiffies(const unsigned int m)
 {
 	/*
 	 * Negative value, means infinite timeout:
 	 */
 	if ((int)m < 0)
 		return MAX_JIFFY_OFFSET;
-
-#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ)
-	/*
-	 * HZ is equal to or smaller than 1000, and 1000 is a nice
-	 * round multiple of HZ, divide with the factor between them,
-	 * but round upwards:
-	 */
-	return (m + (MSEC_PER_SEC / HZ) - 1) / (MSEC_PER_SEC / HZ);
-#elif HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC)
-	/*
-	 * HZ is larger than 1000, and HZ is a nice round multiple of
-	 * 1000 - simply multiply with the factor between them.
-	 *
-	 * But first make sure the multiplication result cannot
-	 * overflow:
-	 */
-	if (m > jiffies_to_msecs(MAX_JIFFY_OFFSET))
-		return MAX_JIFFY_OFFSET;
-
-	return m * (HZ / MSEC_PER_SEC);
-#else
-	/*
-	 * Generic case - multiply, round and divide. But first
-	 * check that if we are doing a net multiplication, that
-	 * we wouldn't overflow:
-	 */
-	if (HZ > MSEC_PER_SEC && m > jiffies_to_msecs(MAX_JIFFY_OFFSET))
-		return MAX_JIFFY_OFFSET;
-
-	return (MSEC_TO_HZ_MUL32 * m + MSEC_TO_HZ_ADJ32)
-		>> MSEC_TO_HZ_SHR32;
-#endif
+	return _msecs_to_jiffies(m);
 }
-EXPORT_SYMBOL(msecs_to_jiffies);
+EXPORT_SYMBOL(__msecs_to_jiffies);
 
-unsigned long usecs_to_jiffies(const unsigned int u)
+unsigned long __usecs_to_jiffies(const unsigned int u)
 {
 	if (u > jiffies_to_usecs(MAX_JIFFY_OFFSET))
 		return MAX_JIFFY_OFFSET;
-#if HZ <= USEC_PER_SEC && !(USEC_PER_SEC % HZ)
-	return (u + (USEC_PER_SEC / HZ) - 1) / (USEC_PER_SEC / HZ);
-#elif HZ > USEC_PER_SEC && !(HZ % USEC_PER_SEC)
-	return u * (HZ / USEC_PER_SEC);
-#else
-	return (USEC_TO_HZ_MUL32 * u + USEC_TO_HZ_ADJ32)
-		>> USEC_TO_HZ_SHR32;
-#endif
+	return _usecs_to_jiffies(u);
 }
-EXPORT_SYMBOL(usecs_to_jiffies);
+EXPORT_SYMBOL(__usecs_to_jiffies);
 
 /*
  * The TICK_NSEC - 1 rounds up the value to the next resolution.  Note

kernel/time/timeconst.bc

@@ -50,7 +50,7 @@ define timeconst(hz) {
 	print "#include <linux/types.h>\n\n"
 
 	print "#if HZ != ", hz, "\n"
-	print "#error \qkernel/timeconst.h has the wrong HZ value!\q\n"
+	print "#error \qinclude/generated/timeconst.h has the wrong HZ value!\q\n"
 	print "#endif\n\n"
 
 	if (hz < 2) {
@@ -105,4 +105,5 @@ define timeconst(hz) {
 	halt
 }
 
+hz = read();
 timeconst(hz)

kernel/time/timekeeping.c

@@ -118,18 +118,6 @@ static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta)
 
 #ifdef CONFIG_DEBUG_TIMEKEEPING
 #define WARNING_FREQ (HZ*300) /* 5 minute rate-limiting */
-/*
- * These simple flag variables are managed
- * without locks, which is racy, but ok since
- * we don't really care about being super
- * precise about how many events were seen,
- * just that a problem was observed.
- */
-static int timekeeping_underflow_seen;
-static int timekeeping_overflow_seen;
-
-/* last_warning is only modified under the timekeeping lock */
-static long timekeeping_last_warning;
 
 static void timekeeping_check_update(struct timekeeper *tk, cycle_t offset)
 {
@@ -149,29 +137,30 @@ static void timekeeping_check_update(struct timekeeper *tk, cycle_t offset)
 		}
 	}
 
-	if (timekeeping_underflow_seen) {
-		if (jiffies - timekeeping_last_warning > WARNING_FREQ) {
+	if (tk->underflow_seen) {
+		if (jiffies - tk->last_warning > WARNING_FREQ) {
 			printk_deferred("WARNING: Underflow in clocksource '%s' observed, time update ignored.\n", name);
 			printk_deferred("         Please report this, consider using a different clocksource, if possible.\n");
 			printk_deferred("         Your kernel is probably still fine.\n");
-			timekeeping_last_warning = jiffies;
+			tk->last_warning = jiffies;
 		}
-		timekeeping_underflow_seen = 0;
+		tk->underflow_seen = 0;
 	}
 
-	if (timekeeping_overflow_seen) {
-		if (jiffies - timekeeping_last_warning > WARNING_FREQ) {
+	if (tk->overflow_seen) {
+		if (jiffies - tk->last_warning > WARNING_FREQ) {
 			printk_deferred("WARNING: Overflow in clocksource '%s' observed, time update capped.\n", name);
 			printk_deferred("         Please report this, consider using a different clocksource, if possible.\n");
 			printk_deferred("         Your kernel is probably still fine.\n");
-			timekeeping_last_warning = jiffies;
+			tk->last_warning = jiffies;
 		}
-		timekeeping_overflow_seen = 0;
+		tk->overflow_seen = 0;
 	}
 }
 
 static inline cycle_t timekeeping_get_delta(struct tk_read_base *tkr)
 {
+	struct timekeeper *tk = &tk_core.timekeeper;
 	cycle_t now, last, mask, max, delta;
 	unsigned int seq;
 
@@ -197,13 +186,13 @@ static inline cycle_t timekeeping_get_delta(struct tk_read_base *tkr)
 	 * mask-relative negative values.
 	 */
 	if (unlikely((~delta & mask) < (mask >> 3))) {
-		timekeeping_underflow_seen = 1;
+		tk->underflow_seen = 1;
 		delta = 0;
 	}
 
 	/* Cap delta value to the max_cycles values to avoid mult overflows */
 	if (unlikely(delta > max)) {
-		timekeeping_overflow_seen = 1;
+		tk->overflow_seen = 1;
 		delta = tkr->clock->max_cycles;
 	}
 
@@ -550,6 +539,17 @@ int pvclock_gtod_unregister_notifier(struct notifier_block *nb)
 }
 EXPORT_SYMBOL_GPL(pvclock_gtod_unregister_notifier);
 
+/*
+ * tk_update_leap_state - helper to update the next_leap_ktime
+ */
+static inline void tk_update_leap_state(struct timekeeper *tk)
+{
+	tk->next_leap_ktime = ntp_get_next_leap();
+	if (tk->next_leap_ktime.tv64 != KTIME_MAX)
+		/* Convert to monotonic time */
+		tk->next_leap_ktime = ktime_sub(tk->next_leap_ktime, tk->offs_real);
+}
+
 /*
  * Update the ktime_t based scalar nsec members of the timekeeper
  */
@@ -591,17 +591,25 @@ static void timekeeping_update(struct timekeeper *tk, unsigned int action)
 		ntp_clear();
 	}
 
+	tk_update_leap_state(tk);
 	tk_update_ktime_data(tk);
 
 	update_vsyscall(tk);
 	update_pvclock_gtod(tk, action & TK_CLOCK_WAS_SET);
 
+	update_fast_timekeeper(&tk->tkr_mono, &tk_fast_mono);
+	update_fast_timekeeper(&tk->tkr_raw,  &tk_fast_raw);
+
+	if (action & TK_CLOCK_WAS_SET)
+		tk->clock_was_set_seq++;
+	/*
+	 * The mirroring of the data to the shadow-timekeeper needs
+	 * to happen last here to ensure we don't over-write the
+	 * timekeeper structure on the next update with stale data
+	 */
 	if (action & TK_MIRROR)
 		memcpy(&shadow_timekeeper, &tk_core.timekeeper,
 		       sizeof(tk_core.timekeeper));
-
-	update_fast_timekeeper(&tk->tkr_mono, &tk_fast_mono);
-	update_fast_timekeeper(&tk->tkr_raw,  &tk_fast_raw);
 }
 
 /**
@@ -699,6 +707,23 @@ ktime_t ktime_get(void)
 }
 EXPORT_SYMBOL_GPL(ktime_get);
 
+u32 ktime_get_resolution_ns(void)
+{
+	struct timekeeper *tk = &tk_core.timekeeper;
+	unsigned int seq;
+	u32 nsecs;
+
+	WARN_ON(timekeeping_suspended);
+
+	do {
+		seq = read_seqcount_begin(&tk_core.seq);
+		nsecs = tk->tkr_mono.mult >> tk->tkr_mono.shift;
+	} while (read_seqcount_retry(&tk_core.seq, seq));
+
+	return nsecs;
+}
+EXPORT_SYMBOL_GPL(ktime_get_resolution_ns);
+
 static ktime_t *offsets[TK_OFFS_MAX] = {
 	[TK_OFFS_REAL]	= &tk_core.timekeeper.offs_real,
 	[TK_OFFS_BOOT]	= &tk_core.timekeeper.offs_boot,
@@ -1179,28 +1204,20 @@ void __weak read_persistent_clock64(struct timespec64 *ts64)
 }
 
 /**
- * read_boot_clock -  Return time of the system start.
+ * read_boot_clock64 -  Return time of the system start.
  *
  * Weak dummy function for arches that do not yet support it.
  * Function to read the exact time the system has been started.
- * Returns a timespec with tv_sec=0 and tv_nsec=0 if unsupported.
+ * Returns a timespec64 with tv_sec=0 and tv_nsec=0 if unsupported.
  *
  *  XXX - Do be sure to remove it once all arches implement it.
  */
-void __weak read_boot_clock(struct timespec *ts)
+void __weak read_boot_clock64(struct timespec64 *ts)
 {
 	ts->tv_sec = 0;
 	ts->tv_nsec = 0;
 }
 
-void __weak read_boot_clock64(struct timespec64 *ts64)
-{
-	struct timespec ts;
-
-	read_boot_clock(&ts);
-	*ts64 = timespec_to_timespec64(ts);
-}
-
 /* Flag for if timekeeping_resume() has injected sleeptime */
 static bool sleeptime_injected;
 
@@ -1836,8 +1853,9 @@ void update_wall_time(void)
 	 * memcpy under the tk_core.seq against one before we start
 	 * updating.
 	 */
+	timekeeping_update(tk, clock_set);
 	memcpy(real_tk, tk, sizeof(*tk));
-	timekeeping_update(real_tk, clock_set);
+	/* The memcpy must come last. Do not put anything here! */
 	write_seqcount_end(&tk_core.seq);
 out:
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
@@ -1925,48 +1943,21 @@ void do_timer(unsigned long ticks)
 	calc_global_load(ticks);
 }
 
-/**
- * ktime_get_update_offsets_tick - hrtimer helper
- * @offs_real:	pointer to storage for monotonic -> realtime offset
- * @offs_boot:	pointer to storage for monotonic -> boottime offset
- * @offs_tai:	pointer to storage for monotonic -> clock tai offset
- *
- * Returns monotonic time at last tick and various offsets
- */
-ktime_t ktime_get_update_offsets_tick(ktime_t *offs_real, ktime_t *offs_boot,
-							ktime_t *offs_tai)
-{
-	struct timekeeper *tk = &tk_core.timekeeper;
-	unsigned int seq;
-	ktime_t base;
-	u64 nsecs;
-
-	do {
-		seq = read_seqcount_begin(&tk_core.seq);
-
-		base = tk->tkr_mono.base;
-		nsecs = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
-
-		*offs_real = tk->offs_real;
-		*offs_boot = tk->offs_boot;
-		*offs_tai = tk->offs_tai;
-	} while (read_seqcount_retry(&tk_core.seq, seq));
-
-	return ktime_add_ns(base, nsecs);
-}
-
-#ifdef CONFIG_HIGH_RES_TIMERS
 /**
  * ktime_get_update_offsets_now - hrtimer helper
+ * @cwsseq:	pointer to check and store the clock was set sequence number
  * @offs_real:	pointer to storage for monotonic -> realtime offset
  * @offs_boot:	pointer to storage for monotonic -> boottime offset
  * @offs_tai:	pointer to storage for monotonic -> clock tai offset
  *
- * Returns current monotonic time and updates the offsets
+ * Returns current monotonic time and updates the offsets if the
+ * sequence number in @cwsseq and timekeeper.clock_was_set_seq are
+ * different.
+ *
  * Called from hrtimer_interrupt() or retrigger_next_event()
  */
-ktime_t ktime_get_update_offsets_now(ktime_t *offs_real, ktime_t *offs_boot,
-							ktime_t *offs_tai)
+ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real,
+				     ktime_t *offs_boot, ktime_t *offs_tai)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
 	unsigned int seq;
@@ -1978,15 +1969,23 @@ ktime_t ktime_get_update_offsets_now(ktime_t *offs_real, ktime_t *offs_boot,
 
 		base = tk->tkr_mono.base;
 		nsecs = timekeeping_get_ns(&tk->tkr_mono);
+		base = ktime_add_ns(base, nsecs);
+
+		if (*cwsseq != tk->clock_was_set_seq) {
+			*cwsseq = tk->clock_was_set_seq;
+			*offs_real = tk->offs_real;
+			*offs_boot = tk->offs_boot;
+			*offs_tai = tk->offs_tai;
+		}
+
+		/* Handle leapsecond insertion adjustments */
+		if (unlikely(base.tv64 >= tk->next_leap_ktime.tv64))
+			*offs_real = ktime_sub(tk->offs_real, ktime_set(1, 0));
 
-		*offs_real = tk->offs_real;
-		*offs_boot = tk->offs_boot;
-		*offs_tai = tk->offs_tai;
 	} while (read_seqcount_retry(&tk_core.seq, seq));
 
-	return ktime_add_ns(base, nsecs);
+	return base;
 }
-#endif
 
 /**
  * do_adjtimex() - Accessor function to NTP __do_adjtimex function
@@ -2027,6 +2026,8 @@ int do_adjtimex(struct timex *txc)
 		__timekeeping_set_tai_offset(tk, tai);
 		timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET);
 	}
+	tk_update_leap_state(tk);
+
 	write_seqcount_end(&tk_core.seq);
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
 

kernel/time/timekeeping.h

@@ -3,19 +3,16 @@
 /*
  * Internal interfaces for kernel/time/
  */
-extern ktime_t ktime_get_update_offsets_tick(ktime_t *offs_real,
-						ktime_t *offs_boot,
-						ktime_t *offs_tai);
-extern ktime_t ktime_get_update_offsets_now(ktime_t *offs_real,
-						ktime_t *offs_boot,
-						ktime_t *offs_tai);
+extern ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq,
+					    ktime_t *offs_real,
+					    ktime_t *offs_boot,
+					    ktime_t *offs_tai);
 
 extern int timekeeping_valid_for_hres(void);
 extern u64 timekeeping_max_deferment(void);
 extern int timekeeping_inject_offset(struct timespec *ts);
 extern s32 timekeeping_get_tai_offset(void);
 extern void timekeeping_set_tai_offset(s32 tai_offset);
-extern void timekeeping_clocktai(struct timespec *ts);
 extern int timekeeping_suspend(void);
 extern void timekeeping_resume(void);
 

kernel/time/timer.c

@@ -49,6 +49,8 @@
 #include <asm/timex.h>
 #include <asm/io.h>
 
+#include "tick-internal.h"
+
 #define CREATE_TRACE_POINTS
 #include <trace/events/timer.h>
 
@@ -434,7 +436,7 @@ static void internal_add_timer(struct tvec_base *base, struct timer_list *timer)
 	 * require special care against races with idle_cpu(), lets deal
 	 * with that later.
 	 */
-	if (!tbase_get_deferrable(base) || tick_nohz_full_cpu(base->cpu))
+	if (!tbase_get_deferrable(timer->base) || tick_nohz_full_cpu(base->cpu))
 		wake_up_nohz_cpu(base->cpu);
 }
 
@@ -648,7 +650,7 @@ static inline void
 debug_activate(struct timer_list *timer, unsigned long expires)
 {
 	debug_timer_activate(timer);
-	trace_timer_start(timer, expires);
+	trace_timer_start(timer, expires, tbase_get_deferrable(timer->base));
 }
 
 static inline void debug_deactivate(struct timer_list *timer)
@@ -1311,54 +1313,48 @@ cascade:
  * Check, if the next hrtimer event is before the next timer wheel
  * event:
  */
-static unsigned long cmp_next_hrtimer_event(unsigned long now,
-					    unsigned long expires)
+static u64 cmp_next_hrtimer_event(u64 basem, u64 expires)
 {
-	ktime_t hr_delta = hrtimer_get_next_event();
-	struct timespec tsdelta;
-	unsigned long delta;
-
-	if (hr_delta.tv64 == KTIME_MAX)
-		return expires;
+	u64 nextevt = hrtimer_get_next_event();
 
 	/*
-	 * Expired timer available, let it expire in the next tick
+	 * If high resolution timers are enabled
+	 * hrtimer_get_next_event() returns KTIME_MAX.
 	 */
-	if (hr_delta.tv64 <= 0)
-		return now + 1;
-
-	tsdelta = ktime_to_timespec(hr_delta);
-	delta = timespec_to_jiffies(&tsdelta);
+	if (expires <= nextevt)
+		return expires;
 
 	/*
-	 * Limit the delta to the max value, which is checked in
-	 * tick_nohz_stop_sched_tick():
+	 * If the next timer is already expired, return the tick base
+	 * time so the tick is fired immediately.
 	 */
-	if (delta > NEXT_TIMER_MAX_DELTA)
-		delta = NEXT_TIMER_MAX_DELTA;
+	if (nextevt <= basem)
+		return basem;
 
 	/*
-	 * Take rounding errors in to account and make sure, that it
-	 * expires in the next tick. Otherwise we go into an endless
-	 * ping pong due to tick_nohz_stop_sched_tick() retriggering
-	 * the timer softirq
+	 * Round up to the next jiffie. High resolution timers are
+	 * off, so the hrtimers are expired in the tick and we need to
+	 * make sure that this tick really expires the timer to avoid
+	 * a ping pong of the nohz stop code.
+	 *
+	 * Use DIV_ROUND_UP_ULL to prevent gcc calling __divdi3
 	 */
-	if (delta < 1)
-		delta = 1;
-	now += delta;
-	if (time_before(now, expires))
-		return now;
-	return expires;
+	return DIV_ROUND_UP_ULL(nextevt, TICK_NSEC) * TICK_NSEC;
 }
 
 /**
- * get_next_timer_interrupt - return the jiffy of the next pending timer
- * @now: current time (in jiffies)
+ * get_next_timer_interrupt - return the time (clock mono) of the next timer
+ * @basej:	base time jiffies
+ * @basem:	base time clock monotonic
+ *
+ * Returns the tick aligned clock monotonic time of the next pending
+ * timer or KTIME_MAX if no timer is pending.
  */
-unsigned long get_next_timer_interrupt(unsigned long now)
+u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
 {
 	struct tvec_base *base = __this_cpu_read(tvec_bases);
-	unsigned long expires = now + NEXT_TIMER_MAX_DELTA;
+	u64 expires = KTIME_MAX;
+	unsigned long nextevt;
 
 	/*
 	 * Pretend that there is no timer pending if the cpu is offline.
@@ -1371,14 +1367,15 @@ unsigned long get_next_timer_interrupt(unsigned long now)
 	if (base->active_timers) {
 		if (time_before_eq(base->next_timer, base->timer_jiffies))
 			base->next_timer = __next_timer_interrupt(base);
-		expires = base->next_timer;
+		nextevt = base->next_timer;
+		if (time_before_eq(nextevt, basej))
+			expires = basem;
+		else
+			expires = basem + (nextevt - basej) * TICK_NSEC;
 	}
 	spin_unlock(&base->lock);
 
-	if (time_before_eq(expires, now))
-		return now;
-
-	return cmp_next_hrtimer_event(now, expires);
+	return cmp_next_hrtimer_event(basem, expires);
 }
 #endif
 
@@ -1409,8 +1406,6 @@ static void run_timer_softirq(struct softirq_action *h)
 {
 	struct tvec_base *base = __this_cpu_read(tvec_bases);
 
-	hrtimer_run_pending();
-
 	if (time_after_eq(jiffies, base->timer_jiffies))
 		__run_timers(base);
 }
@@ -1697,14 +1692,14 @@ unsigned long msleep_interruptible(unsigned int msecs)
 
 EXPORT_SYMBOL(msleep_interruptible);
 
-static int __sched do_usleep_range(unsigned long min, unsigned long max)
+static void __sched do_usleep_range(unsigned long min, unsigned long max)
 {
 	ktime_t kmin;
 	unsigned long delta;
 
 	kmin = ktime_set(0, min * NSEC_PER_USEC);
 	delta = (max - min) * NSEC_PER_USEC;
-	return schedule_hrtimeout_range(&kmin, delta, HRTIMER_MODE_REL);
+	schedule_hrtimeout_range(&kmin, delta, HRTIMER_MODE_REL);
 }
 
 /**
@@ -1712,7 +1707,7 @@ static int __sched do_usleep_range(unsigned long min, unsigned long max)
  * @min: Minimum time in usecs to sleep
  * @max: Maximum time in usecs to sleep
  */
-void usleep_range(unsigned long min, unsigned long max)
+void __sched usleep_range(unsigned long min, unsigned long max)
 {
 	__set_current_state(TASK_UNINTERRUPTIBLE);
 	do_usleep_range(min, max);

kernel/time/timer_list.c

@@ -35,13 +35,20 @@ DECLARE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases);
  * This allows printing both to /proc/timer_list and
  * to the console (on SysRq-Q):
  */
-#define SEQ_printf(m, x...)			\
- do {						\
-	if (m)					\
-		seq_printf(m, x);		\
-	else					\
-		printk(x);			\
- } while (0)
+__printf(2, 3)
+static void SEQ_printf(struct seq_file *m, const char *fmt, ...)
+{
+	va_list args;
+
+	va_start(args, fmt);
+
+	if (m)
+		seq_vprintf(m, fmt, args);
+	else
+		vprintk(fmt, args);
+
+	va_end(args);
+}
 
 static void print_name_offset(struct seq_file *m, void *sym)
 {
@@ -120,10 +127,10 @@ static void
 print_base(struct seq_file *m, struct hrtimer_clock_base *base, u64 now)
 {
 	SEQ_printf(m, "  .base:       %pK\n", base);
-	SEQ_printf(m, "  .index:      %d\n",
-			base->index);
-	SEQ_printf(m, "  .resolution: %Lu nsecs\n",
-			(unsigned long long)ktime_to_ns(base->resolution));
+	SEQ_printf(m, "  .index:      %d\n", base->index);
+
+	SEQ_printf(m, "  .resolution: %u nsecs\n", (unsigned) hrtimer_resolution);
+
 	SEQ_printf(m,   "  .get_time:   ");
 	print_name_offset(m, base->get_time);
 	SEQ_printf(m,   "\n");
@@ -158,7 +165,7 @@ static void print_cpu(struct seq_file *m, int cpu, u64 now)
 	P(nr_events);
 	P(nr_retries);
 	P(nr_hangs);
-	P_ns(max_hang_time);
+	P(max_hang_time);
 #endif
 #undef P
 #undef P_ns
@@ -184,7 +191,7 @@ static void print_cpu(struct seq_file *m, int cpu, u64 now)
 		P_ns(idle_sleeptime);
 		P_ns(iowait_sleeptime);
 		P(last_jiffies);
-		P(next_jiffies);
+		P(next_timer);
 		P_ns(idle_expires);
 		SEQ_printf(m, "jiffies: %Lu\n",
 			   (unsigned long long)jiffies);
@@ -251,6 +258,12 @@ print_tickdevice(struct seq_file *m, struct tick_device *td, int cpu)
 			SEQ_printf(m, "\n");
 		}
 
+		if (dev->set_state_oneshot_stopped) {
+			SEQ_printf(m, " oneshot stopped: ");
+			print_name_offset(m, dev->set_state_oneshot_stopped);
+			SEQ_printf(m, "\n");
+		}
+
 		if (dev->tick_resume) {
 			SEQ_printf(m, " resume:   ");
 			print_name_offset(m, dev->tick_resume);
@@ -269,11 +282,11 @@ static void timer_list_show_tickdevices_header(struct seq_file *m)
 {
 #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
 	print_tickdevice(m, tick_get_broadcast_device(), -1);
-	SEQ_printf(m, "tick_broadcast_mask: %08lx\n",
-		   cpumask_bits(tick_get_broadcast_mask())[0]);
+	SEQ_printf(m, "tick_broadcast_mask: %*pb\n",
+		   cpumask_pr_args(tick_get_broadcast_mask()));
 #ifdef CONFIG_TICK_ONESHOT
-	SEQ_printf(m, "tick_broadcast_oneshot_mask: %08lx\n",
-		   cpumask_bits(tick_get_broadcast_oneshot_mask())[0]);
+	SEQ_printf(m, "tick_broadcast_oneshot_mask: %*pb\n",
+		   cpumask_pr_args(tick_get_broadcast_oneshot_mask()));
 #endif
 	SEQ_printf(m, "\n");
 #endif
@@ -282,7 +295,7 @@ static void timer_list_show_tickdevices_header(struct seq_file *m)
 
 static inline void timer_list_header(struct seq_file *m, u64 now)
 {
-	SEQ_printf(m, "Timer List Version: v0.7\n");
+	SEQ_printf(m, "Timer List Version: v0.8\n");
 	SEQ_printf(m, "HRTIMER_MAX_CLOCK_BASES: %d\n", HRTIMER_MAX_CLOCK_BASES);
 	SEQ_printf(m, "now at %Ld nsecs\n", (unsigned long long)now);
 	SEQ_printf(m, "\n");

lib/timerqueue.c

@@ -36,7 +36,7 @@
  * Adds the timer node to the timerqueue, sorted by the
  * node's expires value.
  */
-void timerqueue_add(struct timerqueue_head *head, struct timerqueue_node *node)
+bool timerqueue_add(struct timerqueue_head *head, struct timerqueue_node *node)
 {
 	struct rb_node **p = &head->head.rb_node;
 	struct rb_node *parent = NULL;
@@ -56,8 +56,11 @@ void timerqueue_add(struct timerqueue_head *head, struct timerqueue_node *node)
 	rb_link_node(&node->node, parent, p);
 	rb_insert_color(&node->node, &head->head);
 
-	if (!head->next || node->expires.tv64 < head->next->expires.tv64)
+	if (!head->next || node->expires.tv64 < head->next->expires.tv64) {
 		head->next = node;
+		return true;
+	}
+	return false;
 }
 EXPORT_SYMBOL_GPL(timerqueue_add);
 
@@ -69,7 +72,7 @@ EXPORT_SYMBOL_GPL(timerqueue_add);
  *
  * Removes the timer node from the timerqueue.
  */
-void timerqueue_del(struct timerqueue_head *head, struct timerqueue_node *node)
+bool timerqueue_del(struct timerqueue_head *head, struct timerqueue_node *node)
 {
 	WARN_ON_ONCE(RB_EMPTY_NODE(&node->node));
 
@@ -82,6 +85,7 @@ void timerqueue_del(struct timerqueue_head *head, struct timerqueue_node *node)
 	}
 	rb_erase(&node->node, &head->head);
 	RB_CLEAR_NODE(&node->node);
+	return head->next != NULL;
 }
 EXPORT_SYMBOL_GPL(timerqueue_del);
 

net/core/pktgen.c

@@ -2212,8 +2212,6 @@ static void spin(struct pktgen_dev *pkt_dev, ktime_t spin_until)
 		do {
 			set_current_state(TASK_INTERRUPTIBLE);
 			hrtimer_start_expires(&t.timer, HRTIMER_MODE_ABS);
-			if (!hrtimer_active(&t.timer))
-				t.task = NULL;
 
 			if (likely(t.task))
 				schedule();

net/sched/sch_api.c

@@ -1885,13 +1885,10 @@ EXPORT_SYMBOL(tcf_destroy_chain);
 #ifdef CONFIG_PROC_FS
 static int psched_show(struct seq_file *seq, void *v)
 {
-	struct timespec ts;
-
-	hrtimer_get_res(CLOCK_MONOTONIC, &ts);
 	seq_printf(seq, "%08x %08x %08x %08x\n",
 		   (u32)NSEC_PER_USEC, (u32)PSCHED_TICKS2NS(1),
 		   1000000,
-		   (u32)NSEC_PER_SEC/(u32)ktime_to_ns(timespec_to_ktime(ts)));
+		   (u32)NSEC_PER_SEC / hrtimer_resolution);
 
 	return 0;
 }

sound/core/hrtimer.c

@@ -121,16 +121,9 @@ static struct snd_timer *mytimer;
 static int __init snd_hrtimer_init(void)
 {
 	struct snd_timer *timer;
-	struct timespec tp;
 	int err;
 
-	hrtimer_get_res(CLOCK_MONOTONIC, &tp);
-	if (tp.tv_sec > 0 || !tp.tv_nsec) {
-		pr_err("snd-hrtimer: Invalid resolution %u.%09u",
-			   (unsigned)tp.tv_sec, (unsigned)tp.tv_nsec);
-		return -EINVAL;
-	}
-	resolution = tp.tv_nsec;
+	resolution = hrtimer_resolution;
 
 	/* Create a new timer and set up the fields */
 	err = snd_timer_global_new("hrtimer", SNDRV_TIMER_GLOBAL_HRTIMER,

sound/drivers/pcsp/pcsp.c

@@ -42,16 +42,13 @@ struct snd_pcsp pcsp_chip;
 static int snd_pcsp_create(struct snd_card *card)
 {
 	static struct snd_device_ops ops = { };
-	struct timespec tp;
-	int err;
-	int div, min_div, order;
-
-	hrtimer_get_res(CLOCK_MONOTONIC, &tp);
+	unsigned int resolution = hrtimer_resolution;
+	int err, div, min_div, order;
 
 	if (!nopcm) {
-		if (tp.tv_sec || tp.tv_nsec > PCSP_MAX_PERIOD_NS) {
+		if (resolution > PCSP_MAX_PERIOD_NS) {
 			printk(KERN_ERR "PCSP: Timer resolution is not sufficient "
-				"(%linS)\n", tp.tv_nsec);
+				"(%unS)\n", resolution);
 			printk(KERN_ERR "PCSP: Make sure you have HPET and ACPI "
 				"enabled.\n");
 			printk(KERN_ERR "PCSP: Turned into nopcm mode.\n");
@@ -59,13 +56,13 @@ static int snd_pcsp_create(struct snd_card *card)
 		}
 	}
 
-	if (loops_per_jiffy >= PCSP_MIN_LPJ && tp.tv_nsec <= PCSP_MIN_PERIOD_NS)
+	if (loops_per_jiffy >= PCSP_MIN_LPJ && resolution <= PCSP_MIN_PERIOD_NS)
 		min_div = MIN_DIV;
 	else
 		min_div = MAX_DIV;
 #if PCSP_DEBUG
-	printk(KERN_DEBUG "PCSP: lpj=%li, min_div=%i, res=%li\n",
-	       loops_per_jiffy, min_div, tp.tv_nsec);
+	printk(KERN_DEBUG "PCSP: lpj=%li, min_div=%i, res=%u\n",
+	       loops_per_jiffy, min_div, resolution);
 #endif
 
 	div = MAX_DIV / min_div;

tools/testing/selftests/timers/leap-a-day.c

@@ -44,6 +44,7 @@
 #include <time.h>
 #include <sys/time.h>
 #include <sys/timex.h>
+#include <sys/errno.h>
 #include <string.h>
 #include <signal.h>
 #include <unistd.h>
@@ -63,6 +64,9 @@ static inline int ksft_exit_fail(void)
 #define NSEC_PER_SEC 1000000000ULL
 #define CLOCK_TAI 11
 
+time_t next_leap;
+int error_found;
+
 /* returns 1 if a <= b, 0 otherwise */
 static inline int in_order(struct timespec a, struct timespec b)
 {
@@ -134,6 +138,35 @@ void handler(int unused)
 	exit(0);
 }
 
+void sigalarm(int signo)
+{
+	struct timex tx;
+	int ret;
+
+	tx.modes = 0;
+	ret = adjtimex(&tx);
+
+	if (tx.time.tv_sec < next_leap) {
+		printf("Error: Early timer expiration! (Should be %ld)\n", next_leap);
+		error_found = 1;
+		printf("adjtimex: %10ld sec + %6ld us (%i)\t%s\n",
+					tx.time.tv_sec,
+					tx.time.tv_usec,
+					tx.tai,
+					time_state_str(ret));
+	}
+	if (ret != TIME_WAIT) {
+		printf("Error: Timer seeing incorrect NTP state? (Should be TIME_WAIT)\n");
+		error_found = 1;
+		printf("adjtimex: %10ld sec + %6ld us (%i)\t%s\n",
+					tx.time.tv_sec,
+					tx.time.tv_usec,
+					tx.tai,
+					time_state_str(ret));
+	}
+}
+
+
 /* Test for known hrtimer failure */
 void test_hrtimer_failure(void)
 {
@@ -144,12 +177,19 @@ void test_hrtimer_failure(void)
 	clock_nanosleep(CLOCK_REALTIME, TIMER_ABSTIME, &target, NULL);
 	clock_gettime(CLOCK_REALTIME, &now);
 
-	if (!in_order(target, now))
+	if (!in_order(target, now)) {
 		printf("ERROR: hrtimer early expiration failure observed.\n");
+		error_found = 1;
+	}
 }
 
 int main(int argc, char **argv)
 {
+	timer_t tm1;
+	struct itimerspec its1;
+	struct sigevent se;
+	struct sigaction act;
+	int signum = SIGRTMAX;
 	int settime = 0;
 	int tai_time = 0;
 	int insert = 1;
@@ -191,6 +231,12 @@ int main(int argc, char **argv)
 	signal(SIGINT, handler);
 	signal(SIGKILL, handler);
 
+	/* Set up timer signal handler: */
+	sigfillset(&act.sa_mask);
+	act.sa_flags = 0;
+	act.sa_handler = sigalarm;
+	sigaction(signum, &act, NULL);
+
 	if (iterations < 0)
 		printf("This runs continuously. Press ctrl-c to stop\n");
 	else
@@ -201,7 +247,7 @@ int main(int argc, char **argv)
 		int ret;
 		struct timespec ts;
 		struct timex tx;
-		time_t now, next_leap;
+		time_t now;
 
 		/* Get the current time */
 		clock_gettime(CLOCK_REALTIME, &ts);
@@ -251,10 +297,27 @@ int main(int argc, char **argv)
 
 		printf("Scheduling leap second for %s", ctime(&next_leap));
 
+		/* Set up timer */
+		printf("Setting timer for %ld -  %s", next_leap, ctime(&next_leap));
+		memset(&se, 0, sizeof(se));
+		se.sigev_notify = SIGEV_SIGNAL;
+		se.sigev_signo = signum;
+		se.sigev_value.sival_int = 0;
+		if (timer_create(CLOCK_REALTIME, &se, &tm1) == -1) {
+			printf("Error: timer_create failed\n");
+			return ksft_exit_fail();
+		}
+		its1.it_value.tv_sec = next_leap;
+		its1.it_value.tv_nsec = 0;
+		its1.it_interval.tv_sec = 0;
+		its1.it_interval.tv_nsec = 0;
+		timer_settime(tm1, TIMER_ABSTIME, &its1, NULL);
+
 		/* Wake up 3 seconds before leap */
 		ts.tv_sec = next_leap - 3;
 		ts.tv_nsec = 0;
 
+
 		while (clock_nanosleep(CLOCK_REALTIME, TIMER_ABSTIME, &ts, NULL))
 			printf("Something woke us up, returning to sleep\n");
 
@@ -276,6 +339,7 @@ int main(int argc, char **argv)
 		while (now < next_leap + 2) {
 			char buf[26];
 			struct timespec tai;
+			int ret;
 
 			tx.modes = 0;
 			ret = adjtimex(&tx);
@@ -308,8 +372,13 @@ int main(int argc, char **argv)
 		/* Note if kernel has known hrtimer failure */
 		test_hrtimer_failure();
 
-		printf("Leap complete\n\n");
-
+		printf("Leap complete\n");
+		if (error_found) {
+			printf("Errors observed\n");
+			clear_time_state();
+			return ksft_exit_fail();
+		}
+		printf("\n");
 		if ((iterations != -1) && !(--iterations))
 			break;
 	}