Merge tag 'timers-core-2021-06-29' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull timer updates from Thomas Gleixner:
 "Time and clocksource/clockevent related updates:

  Core changes:

   - Infrastructure to support per CPU "broadcast" devices for per CPU
     clockevent devices which stop in deep idle states. This allows us
     to utilize the more efficient architected timer on certain ARM SoCs
     for normal operation instead of permanentely using the slow to
     access SoC specific clockevent device.

   - Print the name of the broadcast/wakeup device in /proc/timer_list

   - Make the clocksource watchdog more robust against delays between
     reading the current active clocksource and the watchdog
     clocksource. Such delays can be caused by NMIs, SMIs and vCPU
     preemption.

     Handle this by reading the watchdog clocksource twice, i.e. before
     and after reading the current active clocksource. In case that the
     two watchdog reads shows an excessive time delta, the read sequence
     is repeated up to 3 times.

   - Improve the debug output and add a test module for the watchdog
     mechanism.

   - Reimplementation of the venerable time64_to_tm() function with a
     faster and significantly smaller version. Straight from the source,
     i.e. the author of the related research paper contributed this!

  Driver changes:

   - No new drivers, not even new device tree bindings!

   - Fixes, improvements and cleanups and all over the place"

* tag 'timers-core-2021-06-29' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (30 commits)
  time/kunit: Add missing MODULE_LICENSE()
  time: Improve performance of time64_to_tm()
  clockevents: Use list_move() instead of list_del()/list_add()
  clocksource: Print deviation in nanoseconds when a clocksource becomes unstable
  clocksource: Provide kernel module to test clocksource watchdog
  clocksource: Reduce clocksource-skew threshold
  clocksource: Limit number of CPUs checked for clock synchronization
  clocksource: Check per-CPU clock synchronization when marked unstable
  clocksource: Retry clock read if long delays detected
  clockevents: Add missing parameter documentation
  clocksource/drivers/timer-ti-dm: Drop unnecessary restore
  clocksource/arm_arch_timer: Improve Allwinner A64 timer workaround
  clocksource/drivers/arm_global_timer: Remove duplicated argument in arm_global_timer
  clocksource/drivers/arm_global_timer: Make symbol 'gt_clk_rate_change_nb' static
  arm: zynq: don't disable CONFIG_ARM_GLOBAL_TIMER due to CONFIG_CPU_FREQ anymore
  clocksource/drivers/arm_global_timer: Implement rate compensation whenever source clock changes
  clocksource/drivers/ingenic: Rename unreasonable array names
  clocksource/drivers/timer-ti-dm: Save and restore timer TIOCP_CFG
  clocksource/drivers/mediatek: Ack and disable interrupts on suspend
  clocksource/drivers/samsung_pwm: Constify source IO memory
  ...

Author: torvalds

Documentation/admin-guide/kernel-parameters.txt

@@ -581,6 +581,28 @@
 			loops can be debugged more effectively on production
 			systems.
 
+	clocksource.max_cswd_read_retries= [KNL]
+			Number of clocksource_watchdog() retries due to
+			external delays before the clock will be marked
+			unstable.  Defaults to three retries, that is,
+			four attempts to read the clock under test.
+
+	clocksource.verify_n_cpus= [KNL]
+			Limit the number of CPUs checked for clocksources
+			marked with CLOCK_SOURCE_VERIFY_PERCPU that
+			are marked unstable due to excessive skew.
+			A negative value says to check all CPUs, while
+			zero says not to check any.  Values larger than
+			nr_cpu_ids are silently truncated to nr_cpu_ids.
+			The actual CPUs are chosen randomly, with
+			no replacement if the same CPU is chosen twice.
+
+	clocksource-wdtest.holdoff= [KNL]
+			Set the time in seconds that the clocksource
+			watchdog test waits before commencing its tests.
+			Defaults to zero when built as a module and to
+			10 seconds when built into the kernel.
+
 	clearcpuid=BITNUM[,BITNUM...] [X86]
 			Disable CPUID feature X for the kernel. See
 			arch/x86/include/asm/cpufeatures.h for the valid bit

arch/arm/mach-zynq/Kconfig

@@ -6,7 +6,7 @@ config ARCH_ZYNQ
 	select ARCH_SUPPORTS_BIG_ENDIAN
 	select ARM_AMBA
 	select ARM_GIC
-	select ARM_GLOBAL_TIMER if !CPU_FREQ
+	select ARM_GLOBAL_TIMER
 	select CADENCE_TTC_TIMER
 	select HAVE_ARM_SCU if SMP
 	select HAVE_ARM_TWD if SMP

arch/x86/kernel/tsc.c

@@ -1128,6 +1128,7 @@ static int tsc_cs_enable(struct clocksource *cs)
 static struct clocksource clocksource_tsc_early = {
 	.name			= "tsc-early",
 	.rating			= 299,
+	.uncertainty_margin	= 32 * NSEC_PER_MSEC,
 	.read			= read_tsc,
 	.mask			= CLOCKSOURCE_MASK(64),
 	.flags			= CLOCK_SOURCE_IS_CONTINUOUS |
@@ -1152,7 +1153,8 @@ static struct clocksource clocksource_tsc = {
 	.mask			= CLOCKSOURCE_MASK(64),
 	.flags			= CLOCK_SOURCE_IS_CONTINUOUS |
 				  CLOCK_SOURCE_VALID_FOR_HRES |
-				  CLOCK_SOURCE_MUST_VERIFY,
+				  CLOCK_SOURCE_MUST_VERIFY |
+				  CLOCK_SOURCE_VERIFY_PERCPU,
 	.vdso_clock_mode	= VDSO_CLOCKMODE_TSC,
 	.enable			= tsc_cs_enable,
 	.resume			= tsc_resume,

drivers/clocksource/Kconfig

@@ -358,6 +358,20 @@ config ARM_GLOBAL_TIMER
 	help
 	  This option enables support for the ARM global timer unit.
 
+config ARM_GT_INITIAL_PRESCALER_VAL
+	int "ARM global timer initial prescaler value"
+	default 2 if ARCH_ZYNQ
+	default 1
+	depends on ARM_GLOBAL_TIMER
+	help
+	  When the ARM global timer initializes, its current rate is declared
+	  to the kernel and maintained forever. Should it's parent clock
+	  change, the driver tries to fix the timer's internal prescaler.
+	  On some machs (i.e. Zynq) the initial prescaler value thus poses
+	  bounds about how much the parent clock is allowed to decrease or
+	  increase wrt the initial clock value.
+	  This affects CPU_FREQ max delta from the initial frequency.
+
 config ARM_TIMER_SP804
 	bool "Support for Dual Timer SP804 module" if COMPILE_TEST
 	depends on GENERIC_SCHED_CLOCK && CLKDEV_LOOKUP

drivers/clocksource/arm_arch_timer.c

@@ -64,7 +64,6 @@ struct arch_timer {
 #define to_arch_timer(e) container_of(e, struct arch_timer, evt)
 
 static u32 arch_timer_rate __ro_after_init;
-u32 arch_timer_rate1 __ro_after_init;
 static int arch_timer_ppi[ARCH_TIMER_MAX_TIMER_PPI] __ro_after_init;
 
 static const char *arch_timer_ppi_names[ARCH_TIMER_MAX_TIMER_PPI] = {
@@ -365,7 +364,7 @@ static u64 notrace arm64_858921_read_cntvct_el0(void)
 	do {								\
 		_val = read_sysreg(reg);				\
 		_retries--;						\
-	} while (((_val + 1) & GENMASK(9, 0)) <= 1 && _retries);	\
+	} while (((_val + 1) & GENMASK(8, 0)) <= 1 && _retries);	\
 									\
 	WARN_ON_ONCE(!_retries);					\
 	_val;								\

drivers/clocksource/arm_global_timer.c

@@ -31,6 +31,10 @@
 #define GT_CONTROL_COMP_ENABLE		BIT(1)	/* banked */
 #define GT_CONTROL_IRQ_ENABLE		BIT(2)	/* banked */
 #define GT_CONTROL_AUTO_INC		BIT(3)	/* banked */
+#define GT_CONTROL_PRESCALER_SHIFT      8
+#define GT_CONTROL_PRESCALER_MAX        0xF
+#define GT_CONTROL_PRESCALER_MASK       (GT_CONTROL_PRESCALER_MAX << \
+					 GT_CONTROL_PRESCALER_SHIFT)
 
 #define GT_INT_STATUS	0x0c
 #define GT_INT_STATUS_EVENT_FLAG	BIT(0)
@@ -39,14 +43,16 @@
 #define GT_COMP1	0x14
 #define GT_AUTO_INC	0x18
 
+#define MAX_F_ERR 50
 /*
  * We are expecting to be clocked by the ARM peripheral clock.
  *
  * Note: it is assumed we are using a prescaler value of zero, so this is
  * the units for all operations.
  */
 static void __iomem *gt_base;
-static unsigned long gt_clk_rate;
+static struct notifier_block gt_clk_rate_change_nb;
+static u32 gt_psv_new, gt_psv_bck, gt_target_rate;
 static int gt_ppi;
 static struct clock_event_device __percpu *gt_evt;
 
@@ -96,7 +102,10 @@ static void gt_compare_set(unsigned long delta, int periodic)
 	unsigned long ctrl;
 
 	counter += delta;
-	ctrl = GT_CONTROL_TIMER_ENABLE;
+	ctrl = readl(gt_base + GT_CONTROL);
+	ctrl &= ~(GT_CONTROL_COMP_ENABLE | GT_CONTROL_IRQ_ENABLE |
+		  GT_CONTROL_AUTO_INC);
+	ctrl |= GT_CONTROL_TIMER_ENABLE;
 	writel_relaxed(ctrl, gt_base + GT_CONTROL);
 	writel_relaxed(lower_32_bits(counter), gt_base + GT_COMP0);
 	writel_relaxed(upper_32_bits(counter), gt_base + GT_COMP1);
@@ -123,7 +132,7 @@ static int gt_clockevent_shutdown(struct clock_event_device *evt)
 
 static int gt_clockevent_set_periodic(struct clock_event_device *evt)
 {
-	gt_compare_set(DIV_ROUND_CLOSEST(gt_clk_rate, HZ), 1);
+	gt_compare_set(DIV_ROUND_CLOSEST(gt_target_rate, HZ), 1);
 	return 0;
 }
 
@@ -177,7 +186,7 @@ static int gt_starting_cpu(unsigned int cpu)
 	clk->cpumask = cpumask_of(cpu);
 	clk->rating = 300;
 	clk->irq = gt_ppi;
-	clockevents_config_and_register(clk, gt_clk_rate,
+	clockevents_config_and_register(clk, gt_target_rate,
 					1, 0xffffffff);
 	enable_percpu_irq(clk->irq, IRQ_TYPE_NONE);
 	return 0;
@@ -232,9 +241,28 @@ static struct delay_timer gt_delay_timer = {
 	.read_current_timer = gt_read_long,
 };
 
+static void gt_write_presc(u32 psv)
+{
+	u32 reg;
+
+	reg = readl(gt_base + GT_CONTROL);
+	reg &= ~GT_CONTROL_PRESCALER_MASK;
+	reg |= psv << GT_CONTROL_PRESCALER_SHIFT;
+	writel(reg, gt_base + GT_CONTROL);
+}
+
+static u32 gt_read_presc(void)
+{
+	u32 reg;
+
+	reg = readl(gt_base + GT_CONTROL);
+	reg &= GT_CONTROL_PRESCALER_MASK;
+	return reg >> GT_CONTROL_PRESCALER_SHIFT;
+}
+
 static void __init gt_delay_timer_init(void)
 {
-	gt_delay_timer.freq = gt_clk_rate;
+	gt_delay_timer.freq = gt_target_rate;
 	register_current_timer_delay(&gt_delay_timer);
 }
 
@@ -243,18 +271,81 @@ static int __init gt_clocksource_init(void)
 	writel(0, gt_base + GT_CONTROL);
 	writel(0, gt_base + GT_COUNTER0);
 	writel(0, gt_base + GT_COUNTER1);
-	/* enables timer on all the cores */
-	writel(GT_CONTROL_TIMER_ENABLE, gt_base + GT_CONTROL);
+	/* set prescaler and enable timer on all the cores */
+	writel(((CONFIG_ARM_GT_INITIAL_PRESCALER_VAL - 1) <<
+		GT_CONTROL_PRESCALER_SHIFT)
+	       | GT_CONTROL_TIMER_ENABLE, gt_base + GT_CONTROL);
 
 #ifdef CONFIG_CLKSRC_ARM_GLOBAL_TIMER_SCHED_CLOCK
-	sched_clock_register(gt_sched_clock_read, 64, gt_clk_rate);
+	sched_clock_register(gt_sched_clock_read, 64, gt_target_rate);
 #endif
-	return clocksource_register_hz(&gt_clocksource, gt_clk_rate);
+	return clocksource_register_hz(&gt_clocksource, gt_target_rate);
+}
+
+static int gt_clk_rate_change_cb(struct notifier_block *nb,
+				 unsigned long event, void *data)
+{
+	struct clk_notifier_data *ndata = data;
+
+	switch (event) {
+	case PRE_RATE_CHANGE:
+	{
+		int psv;
+
+		psv = DIV_ROUND_CLOSEST(ndata->new_rate,
+					gt_target_rate);
+
+		if (abs(gt_target_rate - (ndata->new_rate / psv)) > MAX_F_ERR)
+			return NOTIFY_BAD;
+
+		psv--;
+
+		/* prescaler within legal range? */
+		if (psv < 0 || psv > GT_CONTROL_PRESCALER_MAX)
+			return NOTIFY_BAD;
+
+		/*
+		 * store timer clock ctrl register so we can restore it in case
+		 * of an abort.
+		 */
+		gt_psv_bck = gt_read_presc();
+		gt_psv_new = psv;
+		/* scale down: adjust divider in post-change notification */
+		if (ndata->new_rate < ndata->old_rate)
+			return NOTIFY_DONE;
+
+		/* scale up: adjust divider now - before frequency change */
+		gt_write_presc(psv);
+		break;
+	}
+	case POST_RATE_CHANGE:
+		/* scale up: pre-change notification did the adjustment */
+		if (ndata->new_rate > ndata->old_rate)
+			return NOTIFY_OK;
+
+		/* scale down: adjust divider now - after frequency change */
+		gt_write_presc(gt_psv_new);
+		break;
+
+	case ABORT_RATE_CHANGE:
+		/* we have to undo the adjustment in case we scale up */
+		if (ndata->new_rate < ndata->old_rate)
+			return NOTIFY_OK;
+
+		/* restore original register value */
+		gt_write_presc(gt_psv_bck);
+		break;
+	default:
+		return NOTIFY_DONE;
+	}
+
+	return NOTIFY_DONE;
 }
 
 static int __init global_timer_of_register(struct device_node *np)
 {
 	struct clk *gt_clk;
+	static unsigned long gt_clk_rate;
 	int err = 0;
 
 	/*
@@ -292,11 +383,20 @@ static int __init global_timer_of_register(struct device_node *np)
 	}
 
 	gt_clk_rate = clk_get_rate(gt_clk);
+	gt_target_rate = gt_clk_rate / CONFIG_ARM_GT_INITIAL_PRESCALER_VAL;
+	gt_clk_rate_change_nb.notifier_call =
+		gt_clk_rate_change_cb;
+	err = clk_notifier_register(gt_clk, &gt_clk_rate_change_nb);
+	if (err) {
+		pr_warn("Unable to register clock notifier\n");
+		goto out_clk;
+	}
+
 	gt_evt = alloc_percpu(struct clock_event_device);
 	if (!gt_evt) {
 		pr_warn("global-timer: can't allocate memory\n");
 		err = -ENOMEM;
-		goto out_clk;
+		goto out_clk_nb;
 	}
 
 	err = request_percpu_irq(gt_ppi, gt_clockevent_interrupt,
@@ -326,6 +426,8 @@ static int __init global_timer_of_register(struct device_node *np)
 	free_percpu_irq(gt_ppi, gt_evt);
 out_free:
 	free_percpu(gt_evt);
+out_clk_nb:
+	clk_notifier_unregister(gt_clk, &gt_clk_rate_change_nb);
 out_clk:
 	clk_disable_unprepare(gt_clk);
 out_unmap:

drivers/clocksource/ingenic-sysost.c

@@ -186,7 +186,7 @@ static const struct clk_ops ingenic_ost_global_timer_ops = {
 
 static const char * const ingenic_ost_clk_parents[] = { "ext" };
 
-static const struct ingenic_ost_clk_info ingenic_ost_clk_info[] = {
+static const struct ingenic_ost_clk_info x1000_ost_clk_info[] = {
 	[OST_CLK_PERCPU_TIMER] = {
 		.init_data = {
 			.name = "percpu timer",
@@ -414,14 +414,14 @@ static const struct ingenic_soc_info x1000_soc_info = {
 	.num_channels = 2,
 };
 
-static const struct of_device_id __maybe_unused ingenic_ost_of_match[] __initconst = {
-	{ .compatible = "ingenic,x1000-ost", .data = &x1000_soc_info, },
+static const struct of_device_id __maybe_unused ingenic_ost_of_matches[] __initconst = {
+	{ .compatible = "ingenic,x1000-ost", .data = &x1000_soc_info },
 	{ /* sentinel */ }
 };
 
 static int __init ingenic_ost_probe(struct device_node *np)
 {
-	const struct of_device_id *id = of_match_node(ingenic_ost_of_match, np);
+	const struct of_device_id *id = of_match_node(ingenic_ost_of_matches, np);
 	struct ingenic_ost *ost;
 	unsigned int i;
 	int ret;
@@ -462,7 +462,7 @@ static int __init ingenic_ost_probe(struct device_node *np)
 	ost->clocks->num = ost->soc_info->num_channels;
 
 	for (i = 0; i < ost->clocks->num; i++) {
-		ret = ingenic_ost_register_clock(ost, i, &ingenic_ost_clk_info[i], ost->clocks);
+		ret = ingenic_ost_register_clock(ost, i, &x1000_ost_clk_info[i], ost->clocks);
 		if (ret) {
 			pr_crit("%s: Cannot register clock %d\n", __func__, i);
 			goto err_unregister_ost_clocks;