Merge tag 'timers-core-2024-09-16' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull timer updates from Thomas Gleixner:
"Core:

- Overhaul of posix-timers in preparation of removing the workaround
for periodic timers which have signal delivery ignored.

- Remove the historical extra jiffie in msleep()

msleep() adds an extra jiffie to the timeout value to ensure
minimal sleep time. The timer wheel ensures minimal sleep time
since the large rewrite to a non-cascading wheel, but the extra
jiffie in msleep() remained unnoticed. Remove it.

- Make the timer slack handling correct for realtime tasks.

The procfs interface is inconsistent and does neither reflect
reality nor conforms to the man page. Show the correct 0 slack for
real time tasks and enforce it at the core level instead of having
inconsistent individual checks in various timer setup functions.

- The usual set of updates and enhancements all over the place.

Drivers:

- Allow the ACPI PM timer to be turned off during suspend

- No new drivers

- The usual updates and enhancements in various drivers"

* tag 'timers-core-2024-09-16' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (43 commits)
ntp: Make sure RTC is synchronized when time goes backwards
treewide: Fix wrong singular form of jiffies in comments
cpu: Use already existing usleep_range()
timers: Rename next_expiry_recalc() to be unique
platform/x86:intel/pmc: Fix comment for the pmc_core_acpi_pm_timer_suspend_resume function
clocksource/drivers/jcore: Use request_percpu_irq()
clocksource/drivers/cadence-ttc: Add missing clk_disable_unprepare in ttc_setup_clockevent
clocksource/drivers/asm9260: Add missing clk_disable_unprepare in asm9260_timer_init
clocksource/drivers/qcom: Add missing iounmap() on errors in msm_dt_timer_init()
clocksource/drivers/ingenic: Use devm_clk_get_enabled() helpers
platform/x86:intel/pmc: Enable the ACPI PM Timer to be turned off when suspended
clocksource: acpi_pm: Add external callback for suspend/resume
clocksource/drivers/arm_arch_timer: Using for_each_available_child_of_node_scoped()
dt-bindings: timer: rockchip: Add rk3576 compatible
timers: Annotate possible non critical data race of next_expiry
timers: Remove historical extra jiffie for timeout in msleep()
hrtimer: Use and report correct timerslack values for realtime tasks
hrtimer: Annotate hrtimer_cpu_base_.*_expiry() for sparse.
timers: Add sparse annotation for timer_sync_wait_running().
signal: Replace BUG_ON()s
...

Documentation/admin-guide/media/vivid.rst

···
 detail below.
 
 Special attention has been given to the rate at which new frames become
-available. The jitter will be around 1 jiffie (that depends on the HZ
+available. The jitter will be around 1 jiffy (that depends on the HZ
 configuration of your kernel, so usually 1/100, 1/250 or 1/1000 of a second),
 but the long-term behavior is exactly following the framerate. So a
 framerate of 59.94 Hz is really different from 60 Hz. If the framerate

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

···
               - rockchip,rk3228-timer
               - rockchip,rk3229-timer
               - rockchip,rk3368-timer
+              - rockchip,rk3576-timer
               - rockchip,rk3588-timer
               - rockchip,px30-timer
           - const: rockchip,rk3288-timer

Documentation/timers/timers-howto.rst

···
 
 ATOMIC CONTEXT:
 	You must use the `*delay` family of functions. These
-	functions use the jiffie estimation of clock speed
+	functions use the jiffy estimation of clock speed
 	and will busy wait for enough loop cycles to achieve
 	the desired delay:
 

Documentation/translations/sp_SP/scheduler/sched-design-CFS.rst

···
 ==================================
 
 CFS usa una granularidad de nanosegundos y no depende de ningún
-jiffie o detalles como HZ. De este modo, el gestor de tareas CFS no tiene
+jiffy o detalles como HZ. De este modo, el gestor de tareas CFS no tiene
 noción de "ventanas de tiempo" de la forma en que tenía el gestor de
 tareas previo, y tampoco tiene heurísticos. Únicamente hay un parámetro
 central ajustable (se ha de cambiar en CONFIG_SCHED_DEBUG):

arch/arm/mach-versatile/spc.c

···
 
 /*
  * Even though the SPC takes max 3-5 ms to complete any OPP/COMMS
- * operation, the operation could start just before jiffie is about
+ * operation, the operation could start just before jiffy is about
  * to be incremented. So setting timeout value of 20ms = 2jiffies@100Hz
  */
 #define TIMEOUT_US	20000

arch/m68k/q40/q40ints.c

···
  * this stuff doesn't really belong here..
  */
 
-int ql_ticks;              /* 200Hz ticks since last jiffie */
+int ql_ticks;              /* 200Hz ticks since last jiffy */
 static int sound_ticks;
 
 #define SVOL 45

arch/x86/kernel/cpu/mce/dev-mcelog.c

···
 
 	/*
 	 * Need to give user space some time to set everything up,
-	 * so do it a jiffie or two later everywhere.
+	 * so do it a jiffy or two later everywhere.
 	 */
 	schedule_timeout(2);
 

drivers/char/ipmi/ipmi_ssif.c

···
 			ipmi_ssif_unlock_cond(ssif_info, flags);
 			start_get(ssif_info);
 		} else {
-			/* Wait a jiffie then request the next message */
+			/* Wait a jiffy then request the next message */
 			ssif_info->waiting_alert = true;
 			ssif_info->retries_left = SSIF_RECV_RETRIES;
 			if (!ssif_info->stopping)

drivers/clocksource/acpi_pm.c

···
 #include <asm/io.h>
 #include <asm/time.h>
 
+static void *suspend_resume_cb_data;
+
+static void (*suspend_resume_callback)(void *data, bool suspend);
+
 /*
  * The I/O port the PMTMR resides at.
  * The location is detected during setup_arch(),
···
 	return v2;
 }
 
+void acpi_pmtmr_register_suspend_resume_callback(void (*cb)(void *data, bool suspend), void *data)
+{
+	suspend_resume_callback = cb;
+	suspend_resume_cb_data = data;
+}
+EXPORT_SYMBOL_GPL(acpi_pmtmr_register_suspend_resume_callback);
+
+void acpi_pmtmr_unregister_suspend_resume_callback(void)
+{
+	suspend_resume_callback = NULL;
+	suspend_resume_cb_data = NULL;
+}
+EXPORT_SYMBOL_GPL(acpi_pmtmr_unregister_suspend_resume_callback);
+
+static void acpi_pm_suspend(struct clocksource *cs)
+{
+	if (suspend_resume_callback)
+		suspend_resume_callback(suspend_resume_cb_data, true);
+}
+
+static void acpi_pm_resume(struct clocksource *cs)
+{
+	if (suspend_resume_callback)
+		suspend_resume_callback(suspend_resume_cb_data, false);
+}
+
 static u64 acpi_pm_read(struct clocksource *cs)
 {
 	return (u64)read_pmtmr();
···
 	.read		= acpi_pm_read,
 	.mask		= (u64)ACPI_PM_MASK,
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
+	.suspend	= acpi_pm_suspend,
+	.resume		= acpi_pm_resume,
 };
 
 

drivers/clocksource/arm_arch_timer.c

···
 {
 	struct arch_timer_mem *timer_mem;
 	struct arch_timer_mem_frame *frame;
-	struct device_node *frame_node;
 	struct resource res;
 	int ret = -EINVAL;
 	u32 rate;
···
 	timer_mem->cntctlbase = res.start;
 	timer_mem->size = resource_size(&res);
 
-	for_each_available_child_of_node(np, frame_node) {
+	for_each_available_child_of_node_scoped(np, frame_node) {
 		u32 n;
 		struct arch_timer_mem_frame *frame;
 
 		if (of_property_read_u32(frame_node, "frame-number", &n)) {
 			pr_err(FW_BUG "Missing frame-number.\n");
-			of_node_put(frame_node);
 			goto out;
 		}
 		if (n >= ARCH_TIMER_MEM_MAX_FRAMES) {
 			pr_err(FW_BUG "Wrong frame-number, only 0-%u are permitted.\n",
 			       ARCH_TIMER_MEM_MAX_FRAMES - 1);
-			of_node_put(frame_node);
 			goto out;
 		}
 		frame = &timer_mem->frame[n];
 
 		if (frame->valid) {
 			pr_err(FW_BUG "Duplicated frame-number.\n");
-			of_node_put(frame_node);
 			goto out;
 		}
 
-		if (of_address_to_resource(frame_node, 0, &res)) {
-			of_node_put(frame_node);
+		if (of_address_to_resource(frame_node, 0, &res))
 			goto out;
-		}
+
 		frame->cntbase = res.start;
 		frame->size = resource_size(&res);
 

drivers/clocksource/asm9260_timer.c

···
 			DRIVER_NAME, &event_dev);
 	if (ret) {
 		pr_err("Failed to setup irq!\n");
+		clk_disable_unprepare(clk);
 		return ret;
 	}
 

drivers/clocksource/ingenic-ost.c

···
 		return PTR_ERR(map);
 	}
 
-	ost->clk = devm_clk_get(dev, "ost");
+	ost->clk = devm_clk_get_enabled(dev, "ost");
 	if (IS_ERR(ost->clk))
 		return PTR_ERR(ost->clk);
-
-	err = clk_prepare_enable(ost->clk);
-	if (err)
-		return err;
 
 	/* Clear counter high/low registers */
 	if (soc_info->is64bit)
···
 	err = clocksource_register_hz(cs, rate);
 	if (err) {
 		dev_err(dev, "clocksource registration failed");
-		clk_disable_unprepare(ost->clk);
 		return err;
 	}
 

drivers/clocksource/jcore-pit.c

···
 
 static irqreturn_t jcore_timer_interrupt(int irq, void *dev_id)
 {
-	struct jcore_pit *pit = this_cpu_ptr(dev_id);
+	struct jcore_pit *pit = dev_id;
 
 	if (clockevent_state_oneshot(&pit->ced))
 		jcore_pit_disable(pit);
···
 		return -ENOMEM;
 	}
 
-	err = request_irq(pit_irq, jcore_timer_interrupt,
-			  IRQF_TIMER | IRQF_PERCPU,
-			  "jcore_pit", jcore_pit_percpu);
+	err = request_percpu_irq(pit_irq, jcore_timer_interrupt,
+				 "jcore_pit", jcore_pit_percpu);
 	if (err) {
 		pr_err("pit irq request failed: %d\n", err);
 		free_percpu(jcore_pit_percpu);

drivers/clocksource/timer-cadence-ttc.c

···
 				    &ttcce->ttc.clk_rate_change_nb);
 	if (err) {
 		pr_warn("Unable to register clock notifier.\n");
-		goto out_kfree;
+		goto out_clk_unprepare;
 	}
 
 	ttcce->ttc.freq = clk_get_rate(ttcce->ttc.clk);
···
 	err = request_irq(irq, ttc_clock_event_interrupt,
 			  IRQF_TIMER, ttcce->ce.name, ttcce);
 	if (err)
-		goto out_kfree;
+		goto out_clk_unprepare;
 
 	clockevents_config_and_register(&ttcce->ce,
 			ttcce->ttc.freq / PRESCALE, 1, 0xfffe);
 
 	return 0;
 
+out_clk_unprepare:
+	clk_disable_unprepare(ttcce->ttc.clk);
 out_kfree:
 	kfree(ttcce);
 	return err;

drivers/clocksource/timer-qcom.c

···
 	}
 
 	if (of_property_read_u32(np, "clock-frequency", &freq)) {
+		iounmap(cpu0_base);
 		pr_err("Unknown frequency\n");
 		return -EINVAL;
 	}
···
 	freq /= 4;
 	writel_relaxed(DGT_CLK_CTL_DIV_4, source_base + DGT_CLK_CTL);
 
-	return msm_timer_init(freq, 32, irq, !!percpu_offset);
+	ret = msm_timer_init(freq, 32, irq, !!percpu_offset);
+	if (ret)
+		iounmap(cpu0_base);
+
+	return ret;
 }
 TIMER_OF_DECLARE(kpss_timer, "qcom,kpss-timer", msm_dt_timer_init);
 TIMER_OF_DECLARE(scss_timer, "qcom,scss-timer", msm_dt_timer_init);

drivers/dma-buf/st-dma-fence.c

···
 
 	if (dma_fence_wait_timeout(wt.f, false, 2) == -ETIME) {
 		if (timer_pending(&wt.timer)) {
-			pr_notice("Timer did not fire within the jiffie!\n");
+			pr_notice("Timer did not fire within the jiffy!\n");
 			err = 0; /* not our fault! */
 		} else {
 			pr_err("Wait reported incomplete after timeout\n");

drivers/gpu/drm/i915/gem/i915_gem_wait.c

···
 		if (ret == -ETIME && !nsecs_to_jiffies(args->timeout_ns))
 			args->timeout_ns = 0;
 
-		/* Asked to wait beyond the jiffie/scheduler precision? */
+		/* Asked to wait beyond the jiffy/scheduler precision? */
 		if (ret == -ETIME && args->timeout_ns)
 			ret = -EAGAIN;
 	}

drivers/gpu/drm/i915/gt/selftest_execlists.c

···
 		return -EINVAL;
 	}
 
-	/* Give the request a jiffie to complete after flushing the worker */
+	/* Give the request a jiffy to complete after flushing the worker */
 	if (i915_request_wait(rq, 0,
 			      max(0l, (long)(timeout - jiffies)) + 1) < 0) {
 		pr_err("%s: hanging request %llx:%lld did not complete\n",
···
 			cpu_relax();
 
 		saved_timeout = engine->props.preempt_timeout_ms;
-		engine->props.preempt_timeout_ms = 1; /* in ms, -> 1 jiffie */
+		engine->props.preempt_timeout_ms = 1; /* in ms, -> 1 jiffy */
 
 		i915_request_get(rq);
 		i915_request_add(rq);

drivers/gpu/drm/i915/i915_utils.c

···
 	 * Paranoia to make sure the compiler computes the timeout before
 	 * loading 'jiffies' as jiffies is volatile and may be updated in
 	 * the background by a timer tick. All to reduce the complexity
-	 * of the addition and reduce the risk of losing a jiffie.
+	 * of the addition and reduce the risk of losing a jiffy.
 	 */
 	barrier();
 

drivers/gpu/drm/v3d/v3d_bo.c

···
 	else
 		args->timeout_ns = 0;
 
-	/* Asked to wait beyond the jiffie/scheduler precision? */
+	/* Asked to wait beyond the jiffy/scheduler precision? */
 	if (ret == -ETIME && args->timeout_ns)
 		ret = -EAGAIN;
 

drivers/isdn/mISDN/dsp_cmx.c

···
  *  - has multiple clocks.
  *  - has no usable clock due to jitter or packet loss (VoIP).
  * In this case the system's clock is used. The clock resolution depends on
- * the jiffie resolution.
+ * the jiffy resolution.
  *
  * If a member joins a conference:
  *

drivers/net/ethernet/marvell/mvmdio.c

···
 			return 0;
 	} else {
 		/* wait_event_timeout does not guarantee a delay of at
-		 * least one whole jiffie, so timeout must be no less
+		 * least one whole jiffy, so timeout must be no less
 		 * than two.
 		 */
 		timeout = max(usecs_to_jiffies(MVMDIO_SMI_TIMEOUT), 2);

drivers/platform/x86/intel/pmc/adl.c

···
 	.ppfear_buckets = CNP_PPFEAR_NUM_ENTRIES,
 	.pm_cfg_offset = CNP_PMC_PM_CFG_OFFSET,
 	.pm_read_disable_bit = CNP_PMC_READ_DISABLE_BIT,
+	.acpi_pm_tmr_ctl_offset = SPT_PMC_ACPI_PM_TMR_CTL_OFFSET,
+	.acpi_pm_tmr_disable_bit = SPT_PMC_BIT_ACPI_PM_TMR_DISABLE,
 	.ltr_ignore_max = ADL_NUM_IP_IGN_ALLOWED,
 	.lpm_num_modes = ADL_LPM_NUM_MODES,
 	.lpm_num_maps = ADL_LPM_NUM_MAPS,

drivers/platform/x86/intel/pmc/cnp.c

···
 	.ppfear_buckets = CNP_PPFEAR_NUM_ENTRIES,
 	.pm_cfg_offset = CNP_PMC_PM_CFG_OFFSET,
 	.pm_read_disable_bit = CNP_PMC_READ_DISABLE_BIT,
+	.acpi_pm_tmr_ctl_offset = SPT_PMC_ACPI_PM_TMR_CTL_OFFSET,
+	.acpi_pm_tmr_disable_bit = SPT_PMC_BIT_ACPI_PM_TMR_DISABLE,
 	.ltr_ignore_max = CNP_NUM_IP_IGN_ALLOWED,
 	.etr3_offset = ETR3_OFFSET,
 };

drivers/platform/x86/intel/pmc/core.c

···
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/acpi_pmtmr.h>
 #include <linux/bitfield.h>
 #include <linux/debugfs.h>
 #include <linux/delay.h>
···
 	return val == 1;
 }
 
+/*
+ * Enable or disable ACPI PM Timer
+ *
+ * This function is intended to be a callback for ACPI PM suspend/resume event.
+ * The ACPI PM Timer is enabled on resume only if it was enabled during suspend.
+ */
+static void pmc_core_acpi_pm_timer_suspend_resume(void *data, bool suspend)
+{
+	struct pmc_dev *pmcdev = data;
+	struct pmc *pmc = pmcdev->pmcs[PMC_IDX_MAIN];
+	const struct pmc_reg_map *map = pmc->map;
+	bool enabled;
+	u32 reg;
+
+	if (!map->acpi_pm_tmr_ctl_offset)
+		return;
+
+	guard(mutex)(&pmcdev->lock);
+
+	if (!suspend && !pmcdev->enable_acpi_pm_timer_on_resume)
+		return;
+
+	reg = pmc_core_reg_read(pmc, map->acpi_pm_tmr_ctl_offset);
+	enabled = !(reg & map->acpi_pm_tmr_disable_bit);
+	if (suspend)
+		reg |= map->acpi_pm_tmr_disable_bit;
+	else
+		reg &= ~map->acpi_pm_tmr_disable_bit;
+	pmc_core_reg_write(pmc, map->acpi_pm_tmr_ctl_offset, reg);
+
+	pmcdev->enable_acpi_pm_timer_on_resume = suspend && enabled;
+}
 
 static void pmc_core_dbgfs_unregister(struct pmc_dev *pmcdev)
 {
···
 	struct pmc_dev *pmcdev;
 	const struct x86_cpu_id *cpu_id;
 	int (*core_init)(struct pmc_dev *pmcdev);
+	const struct pmc_reg_map *map;
 	struct pmc *primary_pmc;
 	int ret;
 
···
 	pm_report_max_hw_sleep(FIELD_MAX(SLP_S0_RES_COUNTER_MASK) *
 			       pmc_core_adjust_slp_s0_step(primary_pmc, 1));
 
+	map = primary_pmc->map;
+	if (map->acpi_pm_tmr_ctl_offset)
+		acpi_pmtmr_register_suspend_resume_callback(pmc_core_acpi_pm_timer_suspend_resume,
+							 pmcdev);
+
 	device_initialized = true;
 	dev_info(&pdev->dev, " initialized\n");
 
···
 static void pmc_core_remove(struct platform_device *pdev)
 {
 	struct pmc_dev *pmcdev = platform_get_drvdata(pdev);
+	const struct pmc *pmc = pmcdev->pmcs[PMC_IDX_MAIN];
+	const struct pmc_reg_map *map = pmc->map;
+
+	if (map->acpi_pm_tmr_ctl_offset)
+		acpi_pmtmr_unregister_suspend_resume_callback();
+
 	pmc_core_dbgfs_unregister(pmcdev);
 	pmc_core_clean_structure(pdev);
 }

drivers/platform/x86/intel/pmc/core.h

···
 #define SPT_PMC_LTR_SCC				0x3A0
 #define SPT_PMC_LTR_ISH				0x3A4
 
+#define SPT_PMC_ACPI_PM_TMR_CTL_OFFSET		0x18FC
+
 /* Sunrise Point: PGD PFET Enable Ack Status Registers */
 enum ppfear_regs {
 	SPT_PMC_XRAM_PPFEAR0A = 0x590,
···
 
 #define SPT_PMC_VRIC1_SLPS0LVEN			BIT(13)
 #define SPT_PMC_VRIC1_XTALSDQDIS		BIT(22)
+
+#define SPT_PMC_BIT_ACPI_PM_TMR_DISABLE		BIT(1)
 
 /* Cannonlake Power Management Controller register offsets */
 #define CNP_PMC_SLPS0_DBG_OFFSET		0x10B4
···
 	const u8  *lpm_reg_index;
 	const u32 pson_residency_offset;
 	const u32 pson_residency_counter_step;
+	const u32 acpi_pm_tmr_ctl_offset;
+	const u32 acpi_pm_tmr_disable_bit;
 };
 
 /**
···
 	u32 die_c6_offset;
 	struct telem_endpoint *punit_ep;
 	struct pmc_info *regmap_list;
+
+	bool enable_acpi_pm_timer_on_resume;
 };
 
 enum pmc_index {

drivers/platform/x86/intel/pmc/icl.c

···
 	.ppfear_buckets = ICL_PPFEAR_NUM_ENTRIES,
 	.pm_cfg_offset = CNP_PMC_PM_CFG_OFFSET,
 	.pm_read_disable_bit = CNP_PMC_READ_DISABLE_BIT,
+	.acpi_pm_tmr_ctl_offset = SPT_PMC_ACPI_PM_TMR_CTL_OFFSET,
+	.acpi_pm_tmr_disable_bit = SPT_PMC_BIT_ACPI_PM_TMR_DISABLE,
 	.ltr_ignore_max = ICL_NUM_IP_IGN_ALLOWED,
 	.etr3_offset = ETR3_OFFSET,
 };

drivers/platform/x86/intel/pmc/mtl.c

···
 	.ppfear_buckets = MTL_SOCM_PPFEAR_NUM_ENTRIES,
 	.pm_cfg_offset = CNP_PMC_PM_CFG_OFFSET,
 	.pm_read_disable_bit = CNP_PMC_READ_DISABLE_BIT,
+	.acpi_pm_tmr_ctl_offset = SPT_PMC_ACPI_PM_TMR_CTL_OFFSET,
+	.acpi_pm_tmr_disable_bit = SPT_PMC_BIT_ACPI_PM_TMR_DISABLE,
 	.lpm_num_maps = ADL_LPM_NUM_MAPS,
 	.ltr_ignore_max = MTL_SOCM_NUM_IP_IGN_ALLOWED,
 	.lpm_res_counter_step_x2 = TGL_PMC_LPM_RES_COUNTER_STEP_X2,

drivers/platform/x86/intel/pmc/spt.c

···
 	.ppfear_buckets = SPT_PPFEAR_NUM_ENTRIES,
 	.pm_cfg_offset = SPT_PMC_PM_CFG_OFFSET,
 	.pm_read_disable_bit = SPT_PMC_READ_DISABLE_BIT,
+	.acpi_pm_tmr_ctl_offset = SPT_PMC_ACPI_PM_TMR_CTL_OFFSET,
+	.acpi_pm_tmr_disable_bit = SPT_PMC_BIT_ACPI_PM_TMR_DISABLE,
 	.ltr_ignore_max = SPT_NUM_IP_IGN_ALLOWED,
 	.pm_vric1_offset = SPT_PMC_VRIC1_OFFSET,
 };

drivers/platform/x86/intel/pmc/tgl.c

···
 	.ppfear_buckets = ICL_PPFEAR_NUM_ENTRIES,
 	.pm_cfg_offset = CNP_PMC_PM_CFG_OFFSET,
 	.pm_read_disable_bit = CNP_PMC_READ_DISABLE_BIT,
+	.acpi_pm_tmr_ctl_offset = SPT_PMC_ACPI_PM_TMR_CTL_OFFSET,
+	.acpi_pm_tmr_disable_bit = SPT_PMC_BIT_ACPI_PM_TMR_DISABLE,
 	.ltr_ignore_max = TGL_NUM_IP_IGN_ALLOWED,
 	.lpm_num_maps = TGL_LPM_NUM_MAPS,
 	.lpm_res_counter_step_x2 = TGL_PMC_LPM_RES_COUNTER_STEP_X2,

fs/proc/base.c

···
 	if (!tp->sighand)
 		return ERR_PTR(-ESRCH);
 
-	return seq_list_start(&tp->task->signal->posix_timers, *pos);
+	return seq_hlist_start(&tp->task->signal->posix_timers, *pos);
 }
 
 static void *timers_next(struct seq_file *m, void *v, loff_t *pos)
 {
 	struct timers_private *tp = m->private;
-	return seq_list_next(v, &tp->task->signal->posix_timers, pos);
+	return seq_hlist_next(v, &tp->task->signal->posix_timers, pos);
 }
 
 static void timers_stop(struct seq_file *m, void *v)
···
 		[SIGEV_THREAD] = "thread",
 	};
 
-	timer = list_entry((struct list_head *)v, struct k_itimer, list);
+	timer = hlist_entry((struct hlist_node *)v, struct k_itimer, list);
 	notify = timer->it_sigev_notify;
 
 	seq_printf(m, "ID: %d\n", timer->it_id);
···
 	}
 
 	task_lock(p);
-	if (slack_ns == 0)
-		p->timer_slack_ns = p->default_timer_slack_ns;
-	else
-		p->timer_slack_ns = slack_ns;
+	if (task_is_realtime(p))
+		slack_ns = 0;
+	else if (slack_ns == 0)
+		slack_ns = p->default_timer_slack_ns;
+	p->timer_slack_ns = slack_ns;
 	task_unlock(p);
 
 out:

fs/select.c

···
 {
 	u64 ret;
 	struct timespec64 now;
+	u64 slack = current->timer_slack_ns;
 
-	/*
-	 * Realtime tasks get a slack of 0 for obvious reasons.
-	 */
-
-	if (rt_task(current))
+	if (slack == 0)
 		return 0;
 
 	ktime_get_ts64(&now);
 	now = timespec64_sub(*tv, now);
 	ret = __estimate_accuracy(&now);
-	if (ret < current->timer_slack_ns)
-		return current->timer_slack_ns;
+	if (ret < slack)
+		return slack;
 	return ret;
 }
 

fs/signalfd.c

···
 	DECLARE_WAITQUEUE(wait, current);
 
 	spin_lock_irq(&current->sighand->siglock);
-	ret = dequeue_signal(current, &ctx->sigmask, info, &type);
+	ret = dequeue_signal(&ctx->sigmask, info, &type);
 	switch (ret) {
 	case 0:
 		if (!nonblock)
···
 	add_wait_queue(&current->sighand->signalfd_wqh, &wait);
 	for (;;) {
 		set_current_state(TASK_INTERRUPTIBLE);
-		ret = dequeue_signal(current, &ctx->sigmask, info, &type);
+		ret = dequeue_signal(&ctx->sigmask, info, &type);
 		if (ret != 0)
 			break;
 		if (signal_pending(current)) {

fs/xfs/xfs_buf.h

···
 	 * success the write is considered to be failed permanently and the
 	 * iodone handler will take appropriate action.
 	 *
-	 * For retry timeouts, we record the jiffie of the first failure. This
+	 * For retry timeouts, we record the jiffy of the first failure. This
 	 * means that we can change the retry timeout for buffers already under
 	 * I/O and thus avoid getting stuck in a retry loop with a long timeout.
 	 *

include/linux/acpi_pmtmr.h

···
 	return acpi_pm_read_verified() & ACPI_PM_MASK;
 }
 
+/**
+ * Register callback for suspend and resume event
+ *
+ * @cb Callback triggered on suspend and resume
+ * @data Data passed with the callback
+ */
+void acpi_pmtmr_register_suspend_resume_callback(void (*cb)(void *data, bool suspend), void *data);
+
+/**
+ * Remove registered callback for suspend and resume event
+ */
+void acpi_pmtmr_unregister_suspend_resume_callback(void);
+
 #else
 
 static inline u32 acpi_pm_read_early(void)

include/linux/jiffies.h

···
 #define NSEC_CONVERSION ((unsigned long)((((u64)1 << NSEC_JIFFIE_SC) +\
                                         TICK_NSEC -1) / (u64)TICK_NSEC))
 /*
- * The maximum jiffie value is (MAX_INT >> 1).  Here we translate that
+ * The maximum jiffy value is (MAX_INT >> 1).  Here we translate that
  * into seconds.  The 64-bit case will overflow if we are not careful,
  * so use the messy SH_DIV macro to do it.  Still all constants.
  */

include/linux/posix-timers.h

···
  * @rcu:		RCU head for freeing the timer.
  */
 struct k_itimer {
-	struct list_head	list;
+	struct hlist_node	list;
 	struct hlist_node	t_hash;
 	spinlock_t		it_lock;
 	const struct k_clock	*kclock;

include/linux/sched/signal.h

···
 
 	/* POSIX.1b Interval Timers */
 	unsigned int		next_posix_timer_id;
-	struct list_head	posix_timers;
+	struct hlist_head	posix_timers;
 
 	/* ITIMER_REAL timer for the process */
 	struct hrtimer real_timer;
···
 extern void flush_signals(struct task_struct *);
 extern void ignore_signals(struct task_struct *);
 extern void flush_signal_handlers(struct task_struct *, int force_default);
-extern int dequeue_signal(struct task_struct *task, sigset_t *mask,
-			  kernel_siginfo_t *info, enum pid_type *type);
+extern int dequeue_signal(sigset_t *mask, kernel_siginfo_t *info, enum pid_type *type);
 
 static inline int kernel_dequeue_signal(void)
 {
···
 	int ret;
 
 	spin_lock_irq(&task->sighand->siglock);
-	ret = dequeue_signal(task, &task->blocked, &__info, &__type);
+	ret = dequeue_signal(&task->blocked, &__info, &__type);
 	spin_unlock_irq(&task->sighand->siglock);
 
 	return ret;

include/linux/timekeeper_internal.h

···
  * @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)
+ * we need to add to xtime (or xtime corrected for sub jiffy times)
  * to get to monotonic time.  Monotonic is pegged at zero at system
  * boot time, so wall_to_monotonic will be negative, however, we will
  * ALWAYS keep the tv_nsec part positive so we can use the usual

init/init_task.c

···
 	.cred_guard_mutex = __MUTEX_INITIALIZER(init_signals.cred_guard_mutex),
 	.exec_update_lock = __RWSEM_INITIALIZER(init_signals.exec_update_lock),
 #ifdef CONFIG_POSIX_TIMERS
-	.posix_timers = LIST_HEAD_INIT(init_signals.posix_timers),
+	.posix_timers	= HLIST_HEAD_INIT,
 	.cputimer	= {
 		.cputime_atomic	= INIT_CPUTIME_ATOMIC,
 	},

kernel/cpu.c

···
 			/* Poll for one millisecond */
 			arch_cpuhp_sync_state_poll();
 		} else {
-			usleep_range_state(USEC_PER_MSEC, 2 * USEC_PER_MSEC, TASK_UNINTERRUPTIBLE);
+			usleep_range(USEC_PER_MSEC, 2 * USEC_PER_MSEC);
 		}
 		sync = atomic_read(st);
 	}

kernel/fork.c

···
 	prev_cputime_init(&sig->prev_cputime);
 
 #ifdef CONFIG_POSIX_TIMERS
-	INIT_LIST_HEAD(&sig->posix_timers);
+	INIT_HLIST_HEAD(&sig->posix_timers);
 	hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	sig->real_timer.function = it_real_fn;
 #endif

kernel/sched/syscalls.c

···
 	else if (fair_policy(policy))
 		p->static_prio = NICE_TO_PRIO(attr->sched_nice);
 
+	/* rt-policy tasks do not have a timerslack */
+	if (task_is_realtime(p)) {
+		p->timer_slack_ns = 0;
+	} else if (p->timer_slack_ns == 0) {
+		/* when switching back to non-rt policy, restore timerslack */
+		p->timer_slack_ns = p->default_timer_slack_ns;
+	}
+
 	/*
 	 * __sched_setscheduler() ensures attr->sched_priority == 0 when
 	 * !rt_policy. Always setting this ensures that things like

kernel/signal.c

···
 }
 
 /*
- * Dequeue a signal and return the element to the caller, which is
- * expected to free it.
- *
- * All callers have to hold the siglock.
+ * Try to dequeue a signal. If a deliverable signal is found fill in the
+ * caller provided siginfo and return the signal number. Otherwise return
+ * 0.
  */
-int dequeue_signal(struct task_struct *tsk, sigset_t *mask,
-		   kernel_siginfo_t *info, enum pid_type *type)
+int dequeue_signal(sigset_t *mask, kernel_siginfo_t *info, enum pid_type *type)
 {
+	struct task_struct *tsk = current;
 	bool resched_timer = false;
 	int signr;
 
-	/* We only dequeue private signals from ourselves, we don't let
-	 * signalfd steal them
-	 */
+	lockdep_assert_held(&tsk->sighand->siglock);
+
 	*type = PIDTYPE_PID;
 	signr = __dequeue_signal(&tsk->pending, mask, info, &resched_timer);
 	if (!signr) {
···
 
 void sigqueue_free(struct sigqueue *q)
 {
-	unsigned long flags;
 	spinlock_t *lock = &current->sighand->siglock;
+	unsigned long flags;
 
-	BUG_ON(!(q->flags & SIGQUEUE_PREALLOC));
+	if (WARN_ON_ONCE(!(q->flags & SIGQUEUE_PREALLOC)))
+		return;
 	/*
 	 * We must hold ->siglock while testing q->list
 	 * to serialize with collect_signal() or with
···
 	unsigned long flags;
 	int ret, result;
 
-	BUG_ON(!(q->flags & SIGQUEUE_PREALLOC));
+	if (WARN_ON_ONCE(!(q->flags & SIGQUEUE_PREALLOC)))
+		return 0;
+	if (WARN_ON_ONCE(q->info.si_code != SI_TIMER))
+		return 0;
 
 	ret = -1;
 	rcu_read_lock();
···
 		 * If an SI_TIMER entry is already queue just increment
 		 * the overrun count.
 		 */
-		BUG_ON(q->info.si_code != SI_TIMER);
 		q->info.si_overrun++;
 		result = TRACE_SIGNAL_ALREADY_PENDING;
 		goto out;
···
 		type = PIDTYPE_PID;
 		signr = dequeue_synchronous_signal(&ksig->info);
 		if (!signr)
-			signr = dequeue_signal(current, &current->blocked,
-					       &ksig->info, &type);
+			signr = dequeue_signal(&current->blocked, &ksig->info, &type);
 
 		if (!signr)
 			break; /* will return 0 */
···
 	signotset(&mask);
 
 	spin_lock_irq(&tsk->sighand->siglock);
-	sig = dequeue_signal(tsk, &mask, info, &type);
+	sig = dequeue_signal(&mask, info, &type);
 	if (!sig && timeout) {
 		/*
 		 * None ready, temporarily unblock those we're interested
···
 		spin_lock_irq(&tsk->sighand->siglock);
 		__set_task_blocked(tsk, &tsk->real_blocked);
 		sigemptyset(&tsk->real_blocked);
-		sig = dequeue_signal(tsk, &mask, info, &type);
+		sig = dequeue_signal(&mask, info, &type);
 	}
 	spin_unlock_irq(&tsk->sighand->siglock);
 

kernel/sys.c

···
 			error = current->timer_slack_ns;
 		break;
 	case PR_SET_TIMERSLACK:
+		if (task_is_realtime(current))
+			break;
 		if (arg2 <= 0)
 			current->timer_slack_ns =
 					current->default_timer_slack_ns;

kernel/time/alarmtimer.c

···
 		 * promised in the context of posix_timer_fn() never
 		 * materialized, but someone should really work on it.
 		 *
-		 * To prevent DOS fake @now to be 1 jiffie out which keeps
+		 * To prevent DOS fake @now to be 1 jiffy out which keeps
 		 * the overrun accounting correct but creates an
 		 * inconsistency vs. timer_gettime(2).
 		 */
···
 					    it.alarm.alarmtimer);
 	enum alarmtimer_restart result = ALARMTIMER_NORESTART;
 	unsigned long flags;
-	int si_private = 0;
 
 	spin_lock_irqsave(&ptr->it_lock, flags);
 
-	ptr->it_active = 0;
-	if (ptr->it_interval)
-		si_private = ++ptr->it_requeue_pending;
-
-	if (posix_timer_event(ptr, si_private) && ptr->it_interval) {
+	if (posix_timer_queue_signal(ptr) && ptr->it_interval) {
 		/*
 		 * Handle ignored signals and rearm the timer. This will go
 		 * away once we handle ignored signals proper. Ensure that

kernel/time/clockevents.c

···
 
 #ifdef CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST
 
-/* Limit min_delta to a jiffie */
+/* Limit min_delta to a jiffy */
 #define MIN_DELTA_LIMIT		(NSEC_PER_SEC / HZ)
 
 /**

kernel/time/hrtimer.c

···
 	/*
 	 * CONFIG_TIME_LOW_RES indicates that the system has no way to return
 	 * granular time values. For relative timers we add hrtimer_resolution
-	 * (i.e. one jiffie) to prevent short timeouts.
+	 * (i.e. one jiffy) to prevent short timeouts.
 	 */
 	timer->is_rel = mode & HRTIMER_MODE_REL;
 	if (timer->is_rel)
···
 }
 
 static void hrtimer_cpu_base_lock_expiry(struct hrtimer_cpu_base *base)
+	__acquires(&base->softirq_expiry_lock)
 {
 	spin_lock(&base->softirq_expiry_lock);
 }
 
 static void hrtimer_cpu_base_unlock_expiry(struct hrtimer_cpu_base *base)
+	__releases(&base->softirq_expiry_lock)
 {
 	spin_unlock(&base->softirq_expiry_lock);
 }
···
 	struct restart_block *restart;
 	struct hrtimer_sleeper t;
 	int ret = 0;
-	u64 slack;
-
-	slack = current->timer_slack_ns;
-	if (rt_task(current))
-		slack = 0;
 
 	hrtimer_init_sleeper_on_stack(&t, clockid, mode);
-	hrtimer_set_expires_range_ns(&t.timer, rqtp, slack);
+	hrtimer_set_expires_range_ns(&t.timer, rqtp, current->timer_slack_ns);
 	ret = do_nanosleep(&t, mode);
 	if (ret != -ERESTART_RESTARTBLOCK)
 		goto out;
···
 /**
  * schedule_hrtimeout_range_clock - sleep until timeout
  * @expires:	timeout value (ktime_t)
- * @delta:	slack in expires timeout (ktime_t) for SCHED_OTHER tasks
+ * @delta:	slack in expires timeout (ktime_t)
  * @mode:	timer mode
  * @clock_id:	timer clock to be used
  */
···
 		return -EINTR;
 	}
 
-	/*
-	 * Override any slack passed by the user if under
-	 * rt contraints.
-	 */
-	if (rt_task(current))
-		delta = 0;
-
 	hrtimer_init_sleeper_on_stack(&t, clock_id, mode);
 	hrtimer_set_expires_range_ns(&t.timer, *expires, delta);
 	hrtimer_sleeper_start_expires(&t, mode);
···
 /**
  * schedule_hrtimeout_range - sleep until timeout
  * @expires:	timeout value (ktime_t)
- * @delta:	slack in expires timeout (ktime_t) for SCHED_OTHER tasks
+ * @delta:	slack in expires timeout (ktime_t)
  * @mode:	timer mode
  *
  * Make the current task sleep until the given expiry time has

kernel/time/ntp.c

···
 	sched_sync_hw_clock(offset_nsec, res != 0);
 }
 
-void ntp_notify_cmos_timer(void)
+void ntp_notify_cmos_timer(bool offset_set)
 {
+	/*
+	 * If the time jumped (using ADJ_SETOFFSET) cancels sync timer,
+	 * which may have been running if the time was synchronized
+	 * prior to the ADJ_SETOFFSET call.
+	 */
+	if (offset_set)
+		hrtimer_cancel(&sync_hrtimer);
+
 	/*
 	 * When the work is currently executed but has not yet the timer
 	 * rearmed this queues the work immediately again. No big issue,

kernel/time/ntp_internal.h

···
 extern void __hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_ts);
 
 #if defined(CONFIG_GENERIC_CMOS_UPDATE) || defined(CONFIG_RTC_SYSTOHC)
-extern void ntp_notify_cmos_timer(void);
+extern void ntp_notify_cmos_timer(bool offset_set);
 #else
-static inline void ntp_notify_cmos_timer(void) { }
+static inline void ntp_notify_cmos_timer(bool offset_set) { }
 #endif
 
 #endif /* _LINUX_NTP_INTERNAL_H */

kernel/time/posix-cpu-timers.c

···
 	struct cpu_timer *ctmr = &timer->it.cpu;
 	struct posix_cputimer_base *base;
 
+	timer->it_active = 0;
 	if (!cpu_timer_dequeue(ctmr))
 		return;
 
···
 	struct cpu_timer *ctmr = &timer->it.cpu;
 	u64 newexp = cpu_timer_getexpires(ctmr);
 
+	timer->it_active = 1;
 	if (!cpu_timer_enqueue(&base->tqhead, ctmr))
 		return;
 
···
 {
 	struct cpu_timer *ctmr = &timer->it.cpu;
 
-	if ((timer->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE) {
-		/*
-		 * User don't want any signal.
-		 */
-		cpu_timer_setexpires(ctmr, 0);
-	} else if (unlikely(timer->sigq == NULL)) {
+	timer->it_active = 0;
+	if (unlikely(timer->sigq == NULL)) {
 		/*
 		 * This a special case for clock_nanosleep,
 		 * not a normal timer from sys_timer_create.
···
 		/*
 		 * One-shot timer.  Clear it as soon as it's fired.
 		 */
-		posix_timer_event(timer, 0);
+		posix_timer_queue_signal(timer);
 		cpu_timer_setexpires(ctmr, 0);
-	} else if (posix_timer_event(timer, ++timer->it_requeue_pending)) {
+	} else if (posix_timer_queue_signal(timer)) {
 		/*
 		 * The signal did not get queued because the signal
 		 * was ignored, so we won't get any callback to
···
 	}
 }
 
+static void __posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec64 *itp, u64 now);
+
 /*
  * Guts of sys_timer_settime for CPU timers.
  * This is called with the timer locked and interrupts disabled.
···
 static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
 			       struct itimerspec64 *new, struct itimerspec64 *old)
 {
+	bool sigev_none = timer->it_sigev_notify == SIGEV_NONE;
 	clockid_t clkid = CPUCLOCK_WHICH(timer->it_clock);
-	u64 old_expires, new_expires, old_incr, val;
 	struct cpu_timer *ctmr = &timer->it.cpu;
+	u64 old_expires, new_expires, now;
 	struct sighand_struct *sighand;
 	struct task_struct *p;
 	unsigned long flags;
···
 		return -ESRCH;
 	}
 
-	/*
-	 * Disarm any old timer after extracting its expiry time.
-	 */
-	old_incr = timer->it_interval;
+	/* Retrieve the current expiry time before disarming the timer */
 	old_expires = cpu_timer_getexpires(ctmr);
 
 	if (unlikely(timer->it.cpu.firing)) {
···
 		ret = TIMER_RETRY;
 	} else {
 		cpu_timer_dequeue(ctmr);
+		timer->it_active = 0;
 	}
 
 	/*
-	 * We need to sample the current value to convert the new
-	 * value from to relative and absolute, and to convert the
-	 * old value from absolute to relative.  To set a process
-	 * timer, we need a sample to balance the thread expiry
-	 * times (in arm_timer).  With an absolute time, we must
-	 * check if it's already passed.  In short, we need a sample.
+	 * Sample the current clock for saving the previous setting
+	 * and for rearming the timer.
 	 */
 	if (CPUCLOCK_PERTHREAD(timer->it_clock))
-		val = cpu_clock_sample(clkid, p);
+		now = cpu_clock_sample(clkid, p);
 	else
-		val = cpu_clock_sample_group(clkid, p, true);
+		now = cpu_clock_sample_group(clkid, p, !sigev_none);
 
+	/* Retrieve the previous expiry value if requested. */
 	if (old) {
-		if (old_expires == 0) {
-			old->it_value.tv_sec = 0;
-			old->it_value.tv_nsec = 0;
-		} else {
-			/*
-			 * Update the timer in case it has overrun already.
-			 * If it has, we'll report it as having overrun and
-			 * with the next reloaded timer already ticking,
-			 * though we are swallowing that pending
-			 * notification here to install the new setting.
-			 */
-			u64 exp = bump_cpu_timer(timer, val);
-
-			if (val < exp) {
-				old_expires = exp - val;
-				old->it_value = ns_to_timespec64(old_expires);
-			} else {
-				old->it_value.tv_nsec = 1;
-				old->it_value.tv_sec = 0;
-			}
-		}
+		old->it_value = (struct timespec64){ };
+		if (old_expires)
+			__posix_cpu_timer_get(timer, old, now);
 	}
 
+	/* Retry if the timer expiry is running concurrently */
 	if (unlikely(ret)) {
-		/*
-		 * We are colliding with the timer actually firing.
-		 * Punt after filling in the timer's old value, and
-		 * disable this firing since we are already reporting
-		 * it as an overrun (thanks to bump_cpu_timer above).
-		 */
 		unlock_task_sighand(p, &flags);
 		goto out;
 	}
 
-	if (new_expires != 0 && !(timer_flags & TIMER_ABSTIME)) {
-		new_expires += val;
-	}
+	/* Convert relative expiry time to absolute */
+	if (new_expires && !(timer_flags & TIMER_ABSTIME))
+		new_expires += now;
+
+	/* Set the new expiry time (might be 0) */
+	cpu_timer_setexpires(ctmr, new_expires);
 
 	/*
-	 * Install the new expiry time (or zero).
-	 * For a timer with no notification action, we don't actually
-	 * arm the timer (we'll just fake it for timer_gettime).
+	 * Arm the timer if it is not disabled, the new expiry value has
+	 * not yet expired and the timer requires signal delivery.
+	 * SIGEV_NONE timers are never armed. In case the timer is not
+	 * armed, enforce the reevaluation of the timer base so that the
+	 * process wide cputime counter can be disabled eventually.
 	 */
-	cpu_timer_setexpires(ctmr, new_expires);
-	if (new_expires != 0 && val < new_expires) {
-		arm_timer(timer, p);
+	if (likely(!sigev_none)) {
+		if (new_expires && now < new_expires)
+			arm_timer(timer, p);
+		else
+			trigger_base_recalc_expires(timer, p);
 	}
 
 	unlock_task_sighand(p, &flags);
-	/*
-	 * Install the new reload setting, and
-	 * set up the signal and overrun bookkeeping.
-	 */
-	timer->it_interval = timespec64_to_ktime(new->it_interval);
+
+	posix_timer_set_common(timer, new);
 
 	/*
-	 * This acts as a modification timestamp for the timer,
-	 * so any automatic reload attempt will punt on seeing
-	 * that we have reset the timer manually.
+	 * If the new expiry time was already in the past the timer was not
+	 * queued. Fire it immediately even if the thread never runs to
+	 * accumulate more time on this clock.
 	 */
-	timer->it_requeue_pending = (timer->it_requeue_pending + 2) &
-		~REQUEUE_PENDING;
-	timer->it_overrun_last = 0;
-	timer->it_overrun = -1;
-
-	if (val >= new_expires) {
-		if (new_expires != 0) {
-			/*
-			 * The designated time already passed, so we notify
-			 * immediately, even if the thread never runs to
-			 * accumulate more time on this clock.
-			 */
-			cpu_timer_fire(timer);
-		}
-
-		/*
-		 * Make sure we don't keep around the process wide cputime
-		 * counter or the tick dependency if they are not necessary.
-		 */
-		sighand = lock_task_sighand(p, &flags);
-		if (!sighand)
-			goto out;
-
-		if (!cpu_timer_queued(ctmr))
-			trigger_base_recalc_expires(timer, p);
-
-		unlock_task_sighand(p, &flags);
-	}
- out:
+	if (!sigev_none && new_expires && now >= new_expires)
+		cpu_timer_fire(timer);
+out:
 	rcu_read_unlock();
-	if (old)
-		old->it_interval = ns_to_timespec64(old_incr);
-
 	return ret;
+}
+
+static void __posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec64 *itp, u64 now)
+{
+	bool sigev_none = timer->it_sigev_notify == SIGEV_NONE;
+	u64 expires, iv = timer->it_interval;
+
+	/*
+	 * Make sure that interval timers are moved forward for the
+	 * following cases:
+	 *  - SIGEV_NONE timers which are never armed
+	 *  - Timers which expired, but the signal has not yet been
+	 *    delivered
+	 */
+	if (iv && ((timer->it_requeue_pending & REQUEUE_PENDING) || sigev_none))
+		expires = bump_cpu_timer(timer, now);
+	else
+		expires = cpu_timer_getexpires(&timer->it.cpu);
+
+	/*
+	 * Expired interval timers cannot have a remaining time <= 0.
+	 * The kernel has to move them forward so that the next
+	 * timer expiry is > @now.
+	 */
+	if (now < expires) {
+		itp->it_value = ns_to_timespec64(expires - now);
+	} else {
+		/*
+		 * A single shot SIGEV_NONE timer must return 0, when it is
+		 * expired! Timers which have a real signal delivery mode
+		 * must return a remaining time greater than 0 because the
+		 * signal has not yet been delivered.
+		 */
+		if (!sigev_none)
+			itp->it_value.tv_nsec = 1;
+	}
 }
 
 static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec64 *itp)
 {
 	clockid_t clkid = CPUCLOCK_WHICH(timer->it_clock);
-	struct cpu_timer *ctmr = &timer->it.cpu;
-	u64 now, expires = cpu_timer_getexpires(ctmr);
 	struct task_struct *p;
+	u64 now;
 
 	rcu_read_lock();
 	p = cpu_timer_task_rcu(timer);
-	if (!p)
-		goto out;
+	if (p && cpu_timer_getexpires(&timer->it.cpu)) {
+		itp->it_interval = ktime_to_timespec64(timer->it_interval);
 
-	/*
-	 * Easy part: convert the reload time.
-	 */
-	itp->it_interval = ktime_to_timespec64(timer->it_interval);
+		if (CPUCLOCK_PERTHREAD(timer->it_clock))
+			now = cpu_clock_sample(clkid, p);
+		else
+			now = cpu_clock_sample_group(clkid, p, false);
 
-	if (!expires)
-		goto out;
-
-	/*
-	 * Sample the clock to take the difference with the expiry time.
-	 */
-	if (CPUCLOCK_PERTHREAD(timer->it_clock))
-		now = cpu_clock_sample(clkid, p);
-	else
-		now = cpu_clock_sample_group(clkid, p, false);
-
-	if (now < expires) {
-		itp->it_value = ns_to_timespec64(expires - now);
-	} else {
-		/*
-		 * The timer should have expired already, but the firing
-		 * hasn't taken place yet.  Say it's just about to expire.
-		 */
-		itp->it_value.tv_nsec = 1;
-		itp->it_value.tv_sec = 0;
+		__posix_cpu_timer_get(timer, itp, now);
 	}
-out:
 	rcu_read_unlock();
 }
 

kernel/time/posix-timers.c

···
 	unlock_timer(timr, flags);
 }
 
-int posix_timer_event(struct k_itimer *timr, int si_private)
+int posix_timer_queue_signal(struct k_itimer *timr)
 {
+	int ret, si_private = 0;
 	enum pid_type type;
-	int ret;
+
+	lockdep_assert_held(&timr->it_lock);
+
+	timr->it_active = 0;
+	if (timr->it_interval)
+		si_private = ++timr->it_requeue_pending;
+
 	/*
 	 * FIXME: if ->sigq is queued we can race with
 	 * dequeue_signal()->posixtimer_rearm().
···
  */
 static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer)
 {
+	struct k_itimer *timr = container_of(timer, struct k_itimer, it.real.timer);
 	enum hrtimer_restart ret = HRTIMER_NORESTART;
-	struct k_itimer *timr;
 	unsigned long flags;
-	int si_private = 0;
 
-	timr = container_of(timer, struct k_itimer, it.real.timer);
 	spin_lock_irqsave(&timr->it_lock, flags);
 
-	timr->it_active = 0;
-	if (timr->it_interval != 0)
-		si_private = ++timr->it_requeue_pending;
-
-	if (posix_timer_event(timr, si_private)) {
+	if (posix_timer_queue_signal(timr)) {
 		/*
 		 * The signal was not queued due to SIG_IGN. As a
 		 * consequence the timer is not going to be rearmed from
···
 			 * change to the signal handling code.
 			 *
 			 * For now let timers with an interval less than a
-			 * jiffie expire every jiffie and recheck for a
+			 * jiffy expire every jiffy and recheck for a
 			 * valid signal handler.
 			 *
 			 * This avoids interrupt starvation in case of a
 			 * very small interval, which would expire the
 			 * timer immediately again.
 			 *
-			 * Moving now ahead of time by one jiffie tricks
+			 * Moving now ahead of time by one jiffy tricks
 			 * hrtimer_forward() to expire the timer later,
 			 * while it still maintains the overrun accuracy
 			 * for the price of a slight inconsistency in the
···
 	spin_lock_irq(&current->sighand->siglock);
 	/* This makes the timer valid in the hash table */
 	WRITE_ONCE(new_timer->it_signal, current->signal);
-	list_add(&new_timer->list, &current->signal->posix_timers);
+	hlist_add_head(&new_timer->list, &current->signal->posix_timers);
 	spin_unlock_irq(&current->sighand->siglock);
 	/*
 	 * After unlocking sighand::siglock @new_timer is subject to
···
 	return lock_timer(timer_id, flags);
 }
 
+/*
+ * Set up the new interval and reset the signal delivery data
+ */
+void posix_timer_set_common(struct k_itimer *timer, struct itimerspec64 *new_setting)
+{
+	if (new_setting->it_value.tv_sec || new_setting->it_value.tv_nsec)
+		timer->it_interval = timespec64_to_ktime(new_setting->it_interval);
+	else
+		timer->it_interval = 0;
+
+	/* Prevent reloading in case there is a signal pending */
+	timer->it_requeue_pending = (timer->it_requeue_pending + 2) & ~REQUEUE_PENDING;
+	/* Reset overrun accounting */
+	timer->it_overrun_last = 0;
+	timer->it_overrun = -1LL;
+}
+
 /* Set a POSIX.1b interval timer. */
 int common_timer_set(struct k_itimer *timr, int flags,
 		     struct itimerspec64 *new_setting,
···
 		return TIMER_RETRY;
 
 	timr->it_active = 0;
-	timr->it_requeue_pending = (timr->it_requeue_pending + 2) &
-		~REQUEUE_PENDING;
-	timr->it_overrun_last = 0;
+	posix_timer_set_common(timr, new_setting);
 
-	/* Switch off the timer when it_value is zero */
+	/* Keep timer disarmed when it_value is zero */
 	if (!new_setting->it_value.tv_sec && !new_setting->it_value.tv_nsec)
 		return 0;
 
-	timr->it_interval = timespec64_to_ktime(new_setting->it_interval);
 	expires = timespec64_to_ktime(new_setting->it_value);
 	if (flags & TIMER_ABSTIME)
 		expires = timens_ktime_to_host(timr->it_clock, expires);
···
 	const struct k_clock *kc;
 	struct k_itimer *timr;
 	unsigned long flags;
-	int error = 0;
+	int error;
 
 	if (!timespec64_valid(&new_spec64->it_interval) ||
 	    !timespec64_valid(&new_spec64->it_value))
···
 retry:
 	if (!timr)
 		return -EINVAL;
+
+	if (old_spec64)
+		old_spec64->it_interval = ktime_to_timespec64(timr->it_interval);
 
 	kc = timr->kclock;
 	if (WARN_ON_ONCE(!kc || !kc->timer_set))
···
 	}
 
 	spin_lock(&current->sighand->siglock);
-	list_del(&timer->list);
+	hlist_del(&timer->list);
 	spin_unlock(&current->sighand->siglock);
 	/*
 	 * A concurrent lookup could check timer::it_signal lockless. It
···
 
 		goto retry_delete;
 	}
-	list_del(&timer->list);
+	hlist_del(&timer->list);
 
 	/*
 	 * Setting timer::it_signal to NULL is technically not required
···
  */
 void exit_itimers(struct task_struct *tsk)
 {
-	struct list_head timers;
-	struct k_itimer *tmr;
+	struct hlist_head timers;
 
-	if (list_empty(&tsk->signal->posix_timers))
+	if (hlist_empty(&tsk->signal->posix_timers))
 		return;
 
 	/* Protect against concurrent read via /proc/$PID/timers */
 	spin_lock_irq(&tsk->sighand->siglock);
-	list_replace_init(&tsk->signal->posix_timers, &timers);
+	hlist_move_list(&tsk->signal->posix_timers, &timers);
 	spin_unlock_irq(&tsk->sighand->siglock);
 
 	/* The timers are not longer accessible via tsk::signal */
-	while (!list_empty(&timers)) {
-		tmr = list_first_entry(&timers, struct k_itimer, list);
-		itimer_delete(tmr);
-	}
+	while (!hlist_empty(&timers))
+		itimer_delete(hlist_entry(timers.first, struct k_itimer, list));
 }
 
 SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock,

kernel/time/posix-timers.h

···
 extern const struct k_clock clock_thread;
 extern const struct k_clock alarm_clock;
 
-int posix_timer_event(struct k_itimer *timr, int si_private);
+int posix_timer_queue_signal(struct k_itimer *timr);
 
 void common_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting);
 int common_timer_set(struct k_itimer *timr, int flags,
 		     struct itimerspec64 *new_setting,
 		     struct itimerspec64 *old_setting);
+void posix_timer_set_common(struct k_itimer *timer, struct itimerspec64 *new_setting);
 int common_timer_del(struct k_itimer *timer);

kernel/time/timekeeping.c

···
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
 	struct audit_ntp_data ad;
+	bool offset_set = false;
 	bool clock_set = false;
 	struct timespec64 ts;
 	unsigned long flags;
···
 		if (ret)
 			return ret;
 
+		offset_set = delta.tv_sec != 0;
 		audit_tk_injoffset(delta);
 	}
 
···
 	if (clock_set)
 		clock_was_set(CLOCK_SET_WALL);
 
-	ntp_notify_cmos_timer();
+	ntp_notify_cmos_timer(offset_set);
 
 	return ret;
 }

kernel/time/timer.c

···
 	rem = j % HZ;
 
 	/*
-	 * If the target jiffie is just after a whole second (which can happen
+	 * If the target jiffy is just after a whole second (which can happen
 	 * due to delays of the timer irq, long irq off times etc etc) then
 	 * we should round down to the whole second, not up. Use 1/4th second
 	 * as cutoff for this rounding as an extreme upper bound for this.
···
 		 * Set the next expiry time and kick the CPU so it
 		 * can reevaluate the wheel:
 		 */
-		base->next_expiry = bucket_expiry;
+		WRITE_ONCE(base->next_expiry, bucket_expiry);
 		base->timers_pending = true;
 		base->next_expiry_recalc = false;
 		trigger_dyntick_cpu(base, timer);
···
  * the waiter to acquire the lock and make progress.
  */
 static void timer_sync_wait_running(struct timer_base *base)
+	__releases(&base->lock) __releases(&base->expiry_lock)
+	__acquires(&base->expiry_lock) __acquires(&base->lock)
 {
 	if (atomic_read(&base->timer_waiters)) {
 		raw_spin_unlock_irq(&base->lock);
···
  *
  * Store next expiry time in base->next_expiry.
  */
-static void next_expiry_recalc(struct timer_base *base)
+static void timer_recalc_next_expiry(struct timer_base *base)
 {
 	unsigned long clk, next, adj;
 	unsigned lvl, offset = 0;
···
 		 * bits are zero, we look at the next level as is. If not we
 		 * need to advance it by one because that's going to be the
 		 * next expiring bucket in that level. base->clk is the next
-		 * expiring jiffie. So in case of:
+		 * expiring jiffy. So in case of:
 		 *
 		 * LVL5 LVL4 LVL3 LVL2 LVL1 LVL0
 		 *  0    0    0    0    0    0
···
 		clk += adj;
 	}
 
-	base->next_expiry = next;
+	WRITE_ONCE(base->next_expiry, next);
 	base->next_expiry_recalc = false;
 	base->timers_pending = !(next == base->clk + NEXT_TIMER_MAX_DELTA);
 }
···
 		return basem;
 
 	/*
-	 * Round up to the next jiffie. High resolution timers are
+	 * Round up to the next jiffy. 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.
···
 					  unsigned long basej)
 {
 	if (base->next_expiry_recalc)
-		next_expiry_recalc(base);
+		timer_recalc_next_expiry(base);
 
 	/*
 	 * Move next_expiry for the empty base into the future to prevent an
···
 	 * easy comparable to find out which base holds the first pending timer.
 	 */
 	if (!base->timers_pending)
-		base->next_expiry = basej + NEXT_TIMER_MAX_DELTA;
+		WRITE_ONCE(base->next_expiry, basej + NEXT_TIMER_MAX_DELTA);
 
 	return base->next_expiry;
 }
···
 					     base_global, &tevt);
 
 	/*
-	 * If the next event is only one jiffie ahead there is no need to call
+	 * If the next event is only one jiffy ahead there is no need to call
 	 * timer migration hierarchy related functions. The value for the next
 	 * global timer in @tevt struct equals then KTIME_MAX. This is also
 	 * true, when the timer base is idle.
···
 		 * jiffies to avoid endless requeuing to current jiffies.
 		 */
 		base->clk++;
-		next_expiry_recalc(base);
+		timer_recalc_next_expiry(base);
 
 		while (levels--)
 			expire_timers(base, heads + levels);
···
 	hrtimer_run_queues();
 
 	for (int i = 0; i < NR_BASES; i++, base++) {
-		/* Raise the softirq only if required. */
-		if (time_after_eq(jiffies, base->next_expiry) ||
+		/*
+		 * Raise the softirq only if required.
+		 *
+		 * timer_base::next_expiry can be written by a remote CPU while
+		 * holding the lock. If this write happens at the same time than
+		 * the lockless local read, sanity checker could complain about
+		 * data corruption.
+		 *
+		 * There are two possible situations where
+		 * timer_base::next_expiry is written by a remote CPU:
+		 *
+		 * 1. Remote CPU expires global timers of this CPU and updates
+		 * timer_base::next_expiry of BASE_GLOBAL afterwards in
+		 * next_timer_interrupt() or timer_recalc_next_expiry(). The
+		 * worst outcome is a superfluous raise of the timer softirq
+		 * when the not yet updated value is read.
+		 *
+		 * 2. A new first pinned timer is enqueued by a remote CPU
+		 * and therefore timer_base::next_expiry of BASE_LOCAL is
+		 * updated. When this update is missed, this isn't a
+		 * problem, as an IPI is executed nevertheless when the CPU
+		 * was idle before. When the CPU wasn't idle but the update
+		 * is missed, then the timer would expire one jiffy late -
+		 * bad luck.
+		 *
+		 * Those unlikely corner cases where the worst outcome is only a
+		 * one jiffy delay or a superfluous raise of the softirq are
+		 * not that expensive as doing the check always while holding
+		 * the lock.
+		 *
+		 * Possible remote writers are using WRITE_ONCE(). Local reader
+		 * uses therefore READ_ONCE().
+		 */
+		if (time_after_eq(jiffies, READ_ONCE(base->next_expiry)) ||
 		    (i == BASE_DEF && tmigr_requires_handle_remote())) {
 			raise_softirq(TIMER_SOFTIRQ);
 			return;
···
  */
 void msleep(unsigned int msecs)
 {
-	unsigned long timeout = msecs_to_jiffies(msecs) + 1;
+	unsigned long timeout = msecs_to_jiffies(msecs);
 
 	while (timeout)
 		timeout = schedule_timeout_uninterruptible(timeout);
···
  */
 unsigned long msleep_interruptible(unsigned int msecs)
 {
-	unsigned long timeout = msecs_to_jiffies(msecs) + 1;
+	unsigned long timeout = msecs_to_jiffies(msecs);
 
 	while (timeout && !signal_pending(current))
 		timeout = schedule_timeout_interruptible(timeout);

lib/Kconfig.debug

···
 	  using "boot_delay=N".
 
 	  It is likely that you would also need to use "lpj=M" to preset
-	  the "loops per jiffie" value.
+	  the "loops per jiffy" value.
 	  See a previous boot log for the "lpj" value to use for your
 	  system, and then set "lpj=M" before setting "boot_delay=N".
 	  NOTE:  Using this option may adversely affect SMP systems.

net/batman-adv/types.h

···
 	/** @lock: lock to protect the list of fragments */
 	spinlock_t lock;
 
-	/** @timestamp: time (jiffie) of last received fragment */
+	/** @timestamp: time (jiffy) of last received fragment */
 	unsigned long timestamp;
 
 	/** @seqno: sequence number of the fragments in the list */

tools/testing/selftests/timers/posix_timers.c

···
  *
  * Kernel loop code stolen from Steven Rostedt <[e-mail]>
  */
-
+#define _GNU_SOURCE
 #include <sys/time.h>
+#include <sys/types.h>
 #include <stdio.h>
 #include <signal.h>
+#include <stdint.h>
+#include <string.h>
 #include <unistd.h>
 #include <time.h>
 #include <pthread.h>
···
 
 #define DELAY 2
 #define USECS_PER_SEC 1000000
+#define NSECS_PER_SEC 1000000000
+
+static void __fatal_error(const char *test, const char *name, const char *what)
+{
+	char buf[64];
+
+	strerror_r(errno, buf, sizeof(buf));
+
+	if (name && strlen(name))
+		ksft_exit_fail_msg("%s %s %s %s\n", test, name, what, buf);
+	else
+		ksft_exit_fail_msg("%s %s %s\n", test, what, buf);
+}
+
+#define fatal_error(name, what)	__fatal_error(__func__, name, what)
 
 static volatile int done;
 
···
 	return 0;
 }
 
-static int check_itimer(int which)
+static void check_itimer(int which, const char *name)
 {
-	const char *name;
-	int err;
 	struct timeval start, end;
 	struct itimerval val = {
 		.it_value.tv_sec = DELAY,
 	};
-
-	if (which == ITIMER_VIRTUAL)
-		name = "ITIMER_VIRTUAL";
-	else if (which == ITIMER_PROF)
-		name = "ITIMER_PROF";
-	else if (which == ITIMER_REAL)
-		name = "ITIMER_REAL";
-	else
-		return -1;
 
 	done = 0;
 
···
 	else if (which == ITIMER_REAL)
 		signal(SIGALRM, sig_handler);
 
-	err = gettimeofday(&start, NULL);
-	if (err < 0) {
-		ksft_perror("Can't call gettimeofday()");
-		return -1;
-	}
+	if (gettimeofday(&start, NULL) < 0)
+		fatal_error(name, "gettimeofday()");
 
-	err = setitimer(which, &val, NULL);
-	if (err < 0) {
-		ksft_perror("Can't set timer");
-		return -1;
-	}
+	if (setitimer(which, &val, NULL) < 0)
+		fatal_error(name, "setitimer()");
 
 	if (which == ITIMER_VIRTUAL)
 		user_loop();
···
 	else if (which == ITIMER_REAL)
 		idle_loop();
 
-	err = gettimeofday(&end, NULL);
-	if (err < 0) {
-		ksft_perror("Can't call gettimeofday()");
-		return -1;
-	}
+	if (gettimeofday(&end, NULL) < 0)
+		fatal_error(name, "gettimeofday()");
 
 	ksft_test_result(check_diff(start, end) == 0, "%s\n", name);
-
-	return 0;
 }
 
-static int check_timer_create(int which)
+static void check_timer_create(int which, const char *name)
 {
-	const char *type;
-	int err;
-	timer_t id;
 	struct timeval start, end;
 	struct itimerspec val = {
 		.it_value.tv_sec = DELAY,
 	};
-
-	if (which == CLOCK_THREAD_CPUTIME_ID) {
-		type = "thread";
-	} else if (which == CLOCK_PROCESS_CPUTIME_ID) {
-		type = "process";
-	} else {
-		ksft_print_msg("Unknown timer_create() type %d\n", which);
-		return -1;
-	}
+	timer_t id;
 
 	done = 0;
-	err = timer_create(which, NULL, &id);
-	if (err < 0) {
-		ksft_perror("Can't create timer");
-		return -1;
-	}
-	signal(SIGALRM, sig_handler);
 
-	err = gettimeofday(&start, NULL);
-	if (err < 0) {
-		ksft_perror("Can't call gettimeofday()");
-		return -1;
-	}
+	if (timer_create(which, NULL, &id) < 0)
+		fatal_error(name, "timer_create()");
 
-	err = timer_settime(id, 0, &val, NULL);
-	if (err < 0) {
-		ksft_perror("Can't set timer");
-		return -1;
-	}
+	if (signal(SIGALRM, sig_handler) == SIG_ERR)
+		fatal_error(name, "signal()");
+
+	if (gettimeofday(&start, NULL) < 0)
+		fatal_error(name, "gettimeofday()");
+
+	if (timer_settime(id, 0, &val, NULL) < 0)
+		fatal_error(name, "timer_settime()");
 
 	user_loop();
 
-	err = gettimeofday(&end, NULL);
-	if (err < 0) {
-		ksft_perror("Can't call gettimeofday()");
-		return -1;
-	}
+	if (gettimeofday(&end, NULL) < 0)
+		fatal_error(name, "gettimeofday()");
 
 	ksft_test_result(check_diff(start, end) == 0,
-			 "timer_create() per %s\n", type);
-
-	return 0;
+			 "timer_create() per %s\n", name);
 }
 
 static pthread_t ctd_thread;
···
 
 	ctd_count = 100;
 	if (timer_create(CLOCK_PROCESS_CPUTIME_ID, NULL, &id))
-		return "Can't create timer\n";
+		fatal_error(NULL, "timer_create()");
 	if (timer_settime(id, 0, &val, NULL))
-		return "Can't set timer\n";
-
+		fatal_error(NULL, "timer_settime()");
 	while (ctd_count > 0 && !ctd_failed)
 		;
 
 	if (timer_delete(id))
-		return "Can't delete timer\n";
+		fatal_error(NULL, "timer_delete()");
 
 	return NULL;
 }
···
 /*
  * Test that only the running thread receives the timer signal.
  */
-static int check_timer_distribution(void)
+static void check_timer_distribution(void)
 {
-	const char *errmsg;
+	if (signal(SIGALRM, ctd_sighandler) == SIG_ERR)
+		fatal_error(NULL, "signal()");
 
-	signal(SIGALRM, ctd_sighandler);
-
-	errmsg = "Can't create thread\n";
 	if (pthread_create(&ctd_thread, NULL, ctd_thread_func, NULL))
-		goto err;
+		fatal_error(NULL, "pthread_create()");
 
-	errmsg = "Can't join thread\n";
-	if (pthread_join(ctd_thread, (void **)&errmsg) || errmsg)
-		goto err;
+	if (pthread_join(ctd_thread, NULL))
+		fatal_error(NULL, "pthread_join()");
 
 	if (!ctd_failed)
 		ksft_test_result_pass("check signal distribution\n");
···
 		ksft_test_result_fail("check signal distribution\n");
 	else
 		ksft_test_result_skip("check signal distribution (old kernel)\n");
-	return 0;
-err:
-	ksft_print_msg("%s", errmsg);
-	return -1;
+}
+
+struct tmrsig {
+	int	signals;
+	int	overruns;
+};
+
+static void siginfo_handler(int sig, siginfo_t *si, void *uc)
+{
+	struct tmrsig *tsig = si ? si->si_ptr : NULL;
+
+	if (tsig) {
+		tsig->signals++;
+		tsig->overruns += si->si_overrun;
+	}
+}
+
+static void *ignore_thread(void *arg)
+{
+	unsigned int *tid = arg;
+	sigset_t set;
+
+	sigemptyset(&set);
+	sigaddset(&set, SIGUSR1);
+	if (sigprocmask(SIG_BLOCK, &set, NULL))
+		fatal_error(NULL, "sigprocmask(SIG_BLOCK)");
+
+	*tid = gettid();
+	sleep(100);
+
+	if (sigprocmask(SIG_UNBLOCK, &set, NULL))
+		fatal_error(NULL, "sigprocmask(SIG_UNBLOCK)");
+	return NULL;
+}
+
+static void check_sig_ign(int thread)
+{
+	struct tmrsig tsig = { };
+	struct itimerspec its;
+	unsigned int tid = 0;
+	struct sigaction sa;
+	struct sigevent sev;
+	pthread_t pthread;
+	timer_t timerid;
+	sigset_t set;
+
+	if (thread) {
+		if (pthread_create(&pthread, NULL, ignore_thread, &tid))
+			fatal_error(NULL, "pthread_create()");
+		sleep(1);
+	}
+
+	sa.sa_flags = SA_SIGINFO;
+	sa.sa_sigaction = siginfo_handler;
+	sigemptyset(&sa.sa_mask);
+	if (sigaction(SIGUSR1, &sa, NULL))
+		fatal_error(NULL, "sigaction()");
+
+	/* Block the signal */
+	sigemptyset(&set);
+	sigaddset(&set, SIGUSR1);
+	if (sigprocmask(SIG_BLOCK, &set, NULL))
+		fatal_error(NULL, "sigprocmask(SIG_BLOCK)");
+
+	memset(&sev, 0, sizeof(sev));
+	sev.sigev_notify = SIGEV_SIGNAL;
+	sev.sigev_signo = SIGUSR1;
+	sev.sigev_value.sival_ptr = &tsig;
+	if (thread) {
+		sev.sigev_notify = SIGEV_THREAD_ID;
+		sev._sigev_un._tid = tid;
+	}
+
+	if (timer_create(CLOCK_MONOTONIC, &sev, &timerid))
+		fatal_error(NULL, "timer_create()");
+
+	/* Start the timer to expire in 100ms and 100ms intervals */
+	its.it_value.tv_sec = 0;
+	its.it_value.tv_nsec = 100000000;
+	its.it_interval.tv_sec = 0;
+	its.it_interval.tv_nsec = 100000000;
+	timer_settime(timerid, 0, &its, NULL);
+
+	sleep(1);
+
+	/* Set the signal to be ignored */
+	if (signal(SIGUSR1, SIG_IGN) == SIG_ERR)
+		fatal_error(NULL, "signal(SIG_IGN)");
+
+	sleep(1);
+
+	if (thread) {
+		/* Stop the thread first. No signal should be delivered to it */
+		if (pthread_cancel(pthread))
+			fatal_error(NULL, "pthread_cancel()");
+		if (pthread_join(pthread, NULL))
+			fatal_error(NULL, "pthread_join()");
+	}
+
+	/* Restore the handler */
+	if (sigaction(SIGUSR1, &sa, NULL))
+		fatal_error(NULL, "sigaction()");
+
+	sleep(1);
+
+	/* Unblock it, which should deliver the signal in the !thread case*/
+	if (sigprocmask(SIG_UNBLOCK, &set, NULL))
+		fatal_error(NULL, "sigprocmask(SIG_UNBLOCK)");
+
+	if (timer_delete(timerid))
+		fatal_error(NULL, "timer_delete()");
+
+	if (!thread) {
+		ksft_test_result(tsig.signals == 1 && tsig.overruns == 29,
+				 "check_sig_ign SIGEV_SIGNAL\n");
+	} else {
+		ksft_test_result(tsig.signals == 0 && tsig.overruns == 0,
+				 "check_sig_ign SIGEV_THREAD_ID\n");
+	}
+}
+
+static void check_rearm(void)
+{
+	struct tmrsig tsig = { };
+	struct itimerspec its;
+	struct sigaction sa;
+	struct sigevent sev;
+	timer_t timerid;
+	sigset_t set;
+
+	sa.sa_flags = SA_SIGINFO;
+	sa.sa_sigaction = siginfo_handler;
+	sigemptyset(&sa.sa_mask);
+	if (sigaction(SIGUSR1, &sa, NULL))
+		fatal_error(NULL, "sigaction()");
+
+	/* Block the signal */
+	sigemptyset(&set);
+	sigaddset(&set, SIGUSR1);
+	if (sigprocmask(SIG_BLOCK, &set, NULL))
+		fatal_error(NULL, "sigprocmask(SIG_BLOCK)");
+
+	memset(&sev, 0, sizeof(sev));
+	sev.sigev_notify = SIGEV_SIGNAL;
+	sev.sigev_signo = SIGUSR1;
+	sev.sigev_value.sival_ptr = &tsig;
+	if (timer_create(CLOCK_MONOTONIC, &sev, &timerid))
+		fatal_error(NULL, "timer_create()");
+
+	/* Start the timer to expire in 100ms and 100ms intervals */
+	its.it_value.tv_sec = 0;
+	its.it_value.tv_nsec = 100000000;
+	its.it_interval.tv_sec = 0;
+	its.it_interval.tv_nsec = 100000000;
+	if (timer_settime(timerid, 0, &its, NULL))
+		fatal_error(NULL, "timer_settime()");
+
+	sleep(1);
+
+	/* Reprogram the timer to single shot */
+	its.it_value.tv_sec = 10;
+	its.it_value.tv_nsec = 0;
+	its.it_interval.tv_sec = 0;
+	its.it_interval.tv_nsec = 0;
+	if (timer_settime(timerid, 0, &its, NULL))
+		fatal_error(NULL, "timer_settime()");
+
+	/* Unblock it, which should not deliver a signal */
+	if (sigprocmask(SIG_UNBLOCK, &set, NULL))
+		fatal_error(NULL, "sigprocmask(SIG_UNBLOCK)");
+
+	if (timer_delete(timerid))
+		fatal_error(NULL, "timer_delete()");
+
+	ksft_test_result(!tsig.signals, "check_rearm\n");
+}
+
+static void check_delete(void)
+{
+	struct tmrsig tsig = { };
+	struct itimerspec its;
+	struct sigaction sa;
+	struct sigevent sev;
+	timer_t timerid;
+	sigset_t set;
+
+	sa.sa_flags = SA_SIGINFO;
+	sa.sa_sigaction = siginfo_handler;
+	sigemptyset(&sa.sa_mask);
+	if (sigaction(SIGUSR1, &sa, NULL))
+		fatal_error(NULL, "sigaction()");
+
+	/* Block the signal */
+	sigemptyset(&set);
+	sigaddset(&set, SIGUSR1);
+	if (sigprocmask(SIG_BLOCK, &set, NULL))
+		fatal_error(NULL, "sigprocmask(SIG_BLOCK)");
+
+	memset(&sev, 0, sizeof(sev));
+	sev.sigev_notify = SIGEV_SIGNAL;
+	sev.sigev_signo = SIGUSR1;
+	sev.sigev_value.sival_ptr = &tsig;
+	if (timer_create(CLOCK_MONOTONIC, &sev, &timerid))
+		fatal_error(NULL, "timer_create()");
+
+	/* Start the timer to expire in 100ms and 100ms intervals */
+	its.it_value.tv_sec = 0;
+	its.it_value.tv_nsec = 100000000;
+	its.it_interval.tv_sec = 0;
+	its.it_interval.tv_nsec = 100000000;
+	if (timer_settime(timerid, 0, &its, NULL))
+		fatal_error(NULL, "timer_settime()");
+
+	sleep(1);
+
+	if (timer_delete(timerid))
+		fatal_error(NULL, "timer_delete()");
+
+	/* Unblock it, which should not deliver a signal */
+	if (sigprocmask(SIG_UNBLOCK, &set, NULL))
+		fatal_error(NULL, "sigprocmask(SIG_UNBLOCK)");
+
+	ksft_test_result(!tsig.signals, "check_delete\n");
+}
+
+static inline int64_t calcdiff_ns(struct timespec t1, struct timespec t2)
+{
+	int64_t diff;
+
+	diff = NSECS_PER_SEC * (int64_t)((int) t1.tv_sec - (int) t2.tv_sec);
+	diff += ((int) t1.tv_nsec - (int) t2.tv_nsec);
+	return diff;
+}
+
+static void check_sigev_none(int which, const char *name)
+{
+	struct timespec start, now;
+	struct itimerspec its;
+	struct sigevent sev;
+	timer_t timerid;
+
+	memset(&sev, 0, sizeof(sev));
+	sev.sigev_notify = SIGEV_NONE;
+
+	if (timer_create(which, &sev, &timerid))
+		fatal_error(name, "timer_create()");
+
+	/* Start the timer to expire in 100ms and 100ms intervals */
+	its.it_value.tv_sec = 0;
+	its.it_value.tv_nsec = 100000000;
+	its.it_interval.tv_sec = 0;
+	its.it_interval.tv_nsec = 100000000;
+	timer_settime(timerid, 0, &its, NULL);
+
+	if (clock_gettime(which, &start))
+		fatal_error(name, "clock_gettime()");
+
+	do {
+		if (clock_gettime(which, &now))
+			fatal_error(name, "clock_gettime()");
+	} while (calcdiff_ns(now, start) < NSECS_PER_SEC);
+
+	if (timer_gettime(timerid, &its))
+		fatal_error(name, "timer_gettime()");
+
+	if (timer_delete(timerid))
+		fatal_error(name, "timer_delete()");
+
+	ksft_test_result(its.it_value.tv_sec || its.it_value.tv_nsec,
+			 "check_sigev_none %s\n", name);
+}
+
+static void check_gettime(int which, const char *name)
+{
+	struct itimerspec its, prev;
+	struct timespec start, now;
+	struct sigevent sev;
+	timer_t timerid;
+	int wraps = 0;
+	sigset_t set;
+
+	/* Block the signal */
+	sigemptyset(&set);
+	sigaddset(&set, SIGUSR1);
+	if (sigprocmask(SIG_BLOCK, &set, NULL))
+		fatal_error(name, "sigprocmask(SIG_BLOCK)");
+
+	memset(&sev, 0, sizeof(sev));
+	sev.sigev_notify = SIGEV_SIGNAL;
+	sev.sigev_signo = SIGUSR1;
+
+	if (timer_create(which, &sev, &timerid))
+		fatal_error(name, "timer_create()");
+
+	/* Start the timer to expire in 100ms and 100ms intervals */
+	its.it_value.tv_sec = 0;
+	its.it_value.tv_nsec = 100000000;
+	its.it_interval.tv_sec = 0;
+	its.it_interval.tv_nsec = 100000000;
+	if (timer_settime(timerid, 0, &its, NULL))
+		fatal_error(name, "timer_settime()");
+
+	if (timer_gettime(timerid, &prev))
+		fatal_error(name, "timer_gettime()");
+
+	if (clock_gettime(which, &start))
+		fatal_error(name, "clock_gettime()");
+
+	do {
+		if (clock_gettime(which, &now))
+			fatal_error(name, "clock_gettime()");
+		if (timer_gettime(timerid, &its))
+			fatal_error(name, "timer_gettime()");
+		if (its.it_value.tv_nsec > prev.it_value.tv_nsec)
+			wraps++;
+		prev = its;
+
+	} while (calcdiff_ns(now, start) < NSECS_PER_SEC);
+
+	if (timer_delete(timerid))
+		fatal_error(name, "timer_delete()");
+
+	ksft_test_result(wraps > 1, "check_gettime %s\n", name);
+}
+
+static void check_overrun(int which, const char *name)
+{
+	struct timespec start, now;
+	struct tmrsig tsig = { };
+	struct itimerspec its;
+	struct sigaction sa;
+	struct sigevent sev;
+	timer_t timerid;
+	sigset_t set;
+
+	sa.sa_flags = SA_SIGINFO;
+	sa.sa_sigaction = siginfo_handler;
+	sigemptyset(&sa.sa_mask);
+	if (sigaction(SIGUSR1, &sa, NULL))
+		fatal_error(name, "sigaction()");
+
+	/* Block the signal */
+	sigemptyset(&set);
+	sigaddset(&set, SIGUSR1);
+	if (sigprocmask(SIG_BLOCK, &set, NULL))
+		fatal_error(name, "sigprocmask(SIG_BLOCK)");
+
+	memset(&sev, 0, sizeof(sev));
+	sev.sigev_notify = SIGEV_SIGNAL;
+	sev.sigev_signo = SIGUSR1;
+	sev.sigev_value.sival_ptr = &tsig;
+	if (timer_create(which, &sev, &timerid))
+		fatal_error(name, "timer_create()");
+
+	/* Start the timer to expire in 100ms and 100ms intervals */
+	its.it_value.tv_sec = 0;
+	its.it_value.tv_nsec = 100000000;
+	its.it_interval.tv_sec = 0;
+	its.it_interval.tv_nsec = 100000000;
+	if (timer_settime(timerid, 0, &its, NULL))
+		fatal_error(name, "timer_settime()");
+
+	if (clock_gettime(which, &start))
+		fatal_error(name, "clock_gettime()");
+
+	do {
+		if (clock_gettime(which, &now))
+			fatal_error(name, "clock_gettime()");
+	} while (calcdiff_ns(now, start) < NSECS_PER_SEC);
+
+	/* Unblock it, which should deliver a signal */
+	if (sigprocmask(SIG_UNBLOCK, &set, NULL))
+		fatal_error(name, "sigprocmask(SIG_UNBLOCK)");
+
+	if (timer_delete(timerid))
+		fatal_error(name, "timer_delete()");
+
+	ksft_test_result(tsig.signals == 1 && tsig.overruns == 9,
+			 "check_overrun %s\n", name);
 }
 
 int main(int argc, char **argv)
 {
 	ksft_print_header();
-	ksft_set_plan(6);
+	ksft_set_plan(18);
 
 	ksft_print_msg("Testing posix timers. False negative may happen on CPU execution \n");
 	ksft_print_msg("based timers if other threads run on the CPU...\n");
 
-	if (check_itimer(ITIMER_VIRTUAL) < 0)
-		ksft_exit_fail();
-
-	if (check_itimer(ITIMER_PROF) < 0)
-		ksft_exit_fail();
-
-	if (check_itimer(ITIMER_REAL) < 0)
-		ksft_exit_fail();
-
-	if (check_timer_create(CLOCK_THREAD_CPUTIME_ID) < 0)
-		ksft_exit_fail();
+	check_itimer(ITIMER_VIRTUAL, "ITIMER_VIRTUAL");
+	check_itimer(ITIMER_PROF, "ITIMER_PROF");
+	check_itimer(ITIMER_REAL, "ITIMER_REAL");
+	check_timer_create(CLOCK_THREAD_CPUTIME_ID, "CLOCK_THREAD_CPUTIME_ID");
 
 	/*
 	 * It's unfortunately hard to reliably test a timer expiration
···
 	 * to ensure true parallelism. So test only one thread until we
 	 * find a better solution.
 	 */
-	if (check_timer_create(CLOCK_PROCESS_CPUTIME_ID) < 0)
-		ksft_exit_fail();
+	check_timer_create(CLOCK_PROCESS_CPUTIME_ID, "CLOCK_PROCESS_CPUTIME_ID");
+	check_timer_distribution();
 
-	if (check_timer_distribution() < 0)
-		ksft_exit_fail();
+	check_sig_ign(0);
+	check_sig_ign(1);
+	check_rearm();
+	check_delete();
+	check_sigev_none(CLOCK_MONOTONIC, "CLOCK_MONOTONIC");
+	check_sigev_none(CLOCK_PROCESS_CPUTIME_ID, "CLOCK_PROCESS_CPUTIME_ID");
+	check_gettime(CLOCK_MONOTONIC, "CLOCK_MONOTONIC");
+	check_gettime(CLOCK_PROCESS_CPUTIME_ID, "CLOCK_PROCESS_CPUTIME_ID");
+	check_gettime(CLOCK_THREAD_CPUTIME_ID, "CLOCK_THREAD_CPUTIME_ID");
+	check_overrun(CLOCK_MONOTONIC, "CLOCK_MONOTONIC");
+	check_overrun(CLOCK_PROCESS_CPUTIME_ID, "CLOCK_PROCESS_CPUTIME_ID");
+	check_overrun(CLOCK_THREAD_CPUTIME_ID, "CLOCK_THREAD_CPUTIME_ID");
 
 	ksft_finished();
 }