Merge branch 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull core timer updates from Thomas Gleixner:
 "Timers and timekeeping updates:

   - A large overhaul of the posix CPU timer code which is a preparation
     for moving the CPU timer expiry out into task work so it can be
     properly accounted on the task/process.

     An update to the bogus permission checks will come later during the
     merge window as feedback was not complete before heading of for
     travel.

   - Switch the timerqueue code to use cached rbtrees and get rid of the
     homebrewn caching of the leftmost node.

   - Consolidate hrtimer_init() + hrtimer_init_sleeper() calls into a
     single function

   - Implement the separation of hrtimers to be forced to expire in hard
     interrupt context even when PREEMPT_RT is enabled and mark the
     affected timers accordingly.

   - Implement a mechanism for hrtimers and the timer wheel to protect
     RT against priority inversion and live lock issues when a (hr)timer
     which should be canceled is currently executing the callback.
     Instead of infinitely spinning, the task which tries to cancel the
     timer blocks on a per cpu base expiry lock which is held and
     released by the (hr)timer expiry code.

   - Enable the Hyper-V TSC page based sched_clock for Hyper-V guests
     resulting in faster access to timekeeping functions.

   - Updates to various clocksource/clockevent drivers and their device
     tree bindings.

   - The usual small improvements all over the place"

* 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (101 commits)
  posix-cpu-timers: Fix permission check regression
  posix-cpu-timers: Always clear head pointer on dequeue
  hrtimer: Add a missing bracket and hide `migration_base' on !SMP
  posix-cpu-timers: Make expiry_active check actually work correctly
  posix-timers: Unbreak CONFIG_POSIX_TIMERS=n build
  tick: Mark sched_timer to expire in hard interrupt context
  hrtimer: Add kernel doc annotation for HRTIMER_MODE_HARD
  x86/hyperv: Hide pv_ops access for CONFIG_PARAVIRT=n
  posix-cpu-timers: Utilize timerqueue for storage
  posix-cpu-timers: Move state tracking to struct posix_cputimers
  posix-cpu-timers: Deduplicate rlimit handling
  posix-cpu-timers: Remove pointless comparisons
  posix-cpu-timers: Get rid of 64bit divisions
  posix-cpu-timers: Consolidate timer expiry further
  posix-cpu-timers: Get rid of zero checks
  rlimit: Rewrite non-sensical RLIMIT_CPU comment
  posix-cpu-timers: Respect INFINITY for hard RTTIME limit
  posix-cpu-timers: Switch thread group sampling to array
  posix-cpu-timers: Restructure expiry array
  posix-cpu-timers: Remove cputime_expires
  ...

12 files changed, 71 insertions, 52 deletions

diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index 5e9317dc3d39..a642c23b2fba 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -429,7 +429,7 @@ config ATMEL_ST
 
 config ATMEL_TCB_CLKSRC
 	bool "Atmel TC Block timer driver" if COMPILE_TEST
-	depends on HAS_IOMEM
+	depends on ARM && HAS_IOMEM
 	select TIMER_OF if OF
 	help
 	  Support for Timer Counter Blocks on Atmel SoCs.
diff --git a/drivers/clocksource/em_sti.c b/drivers/clocksource/em_sti.c
index 8e12b11e81b0..9039df4f90e2 100644
--- a/drivers/clocksource/em_sti.c
+++ b/drivers/clocksource/em_sti.c
@@ -291,10 +291,8 @@ static int em_sti_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, p);
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		dev_err(&pdev->dev, "failed to get irq\n");
+	if (irq < 0)
 		return irq;
-	}
 
 	/* map memory, let base point to the STI instance */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c
index ba2c79e6a0ee..2317d4e3daaf 100644
--- a/drivers/clocksource/hyperv_timer.c
+++ b/drivers/clocksource/hyperv_timer.c
@@ -22,6 +22,7 @@
 #include <asm/mshyperv.h>
 
 static struct clock_event_device __percpu *hv_clock_event;
+static u64 hv_sched_clock_offset __ro_after_init;
 
 /*
  * If false, we're using the old mechanism for stimer0 interrupts
@@ -212,19 +213,17 @@ EXPORT_SYMBOL_GPL(hv_stimer_global_cleanup);
 struct clocksource *hyperv_cs;
 EXPORT_SYMBOL_GPL(hyperv_cs);
 
-#ifdef CONFIG_HYPERV_TSCPAGE
-
-static struct ms_hyperv_tsc_page *tsc_pg;
+static struct ms_hyperv_tsc_page tsc_pg __aligned(PAGE_SIZE);
 
 struct ms_hyperv_tsc_page *hv_get_tsc_page(void)
 {
-	return tsc_pg;
+	return &tsc_pg;
 }
 EXPORT_SYMBOL_GPL(hv_get_tsc_page);
 
-static u64 notrace read_hv_sched_clock_tsc(void)
+static u64 notrace read_hv_clock_tsc(struct clocksource *arg)
 {
-	u64 current_tick = hv_read_tsc_page(tsc_pg);
+	u64 current_tick = hv_read_tsc_page(&tsc_pg);
 
 	if (current_tick == U64_MAX)
 		hv_get_time_ref_count(current_tick);
@@ -232,9 +231,9 @@ static u64 notrace read_hv_sched_clock_tsc(void)
 	return current_tick;
 }
 
-static u64 read_hv_clock_tsc(struct clocksource *arg)
+static u64 read_hv_sched_clock_tsc(void)
 {
-	return read_hv_sched_clock_tsc();
+	return read_hv_clock_tsc(NULL) - hv_sched_clock_offset;
 }
 
 static struct clocksource hyperv_cs_tsc = {
@@ -244,9 +243,8 @@ static struct clocksource hyperv_cs_tsc = {
 	.mask	= CLOCKSOURCE_MASK(64),
 	.flags	= CLOCK_SOURCE_IS_CONTINUOUS,
 };
-#endif
 
-static u64 notrace read_hv_sched_clock_msr(void)
+static u64 notrace read_hv_clock_msr(struct clocksource *arg)
 {
 	u64 current_tick;
 	/*
@@ -258,9 +256,9 @@ static u64 notrace read_hv_sched_clock_msr(void)
 	return current_tick;
 }
 
-static u64 read_hv_clock_msr(struct clocksource *arg)
+static u64 read_hv_sched_clock_msr(void)
 {
-	return read_hv_sched_clock_msr();
+	return read_hv_clock_msr(NULL) - hv_sched_clock_offset;
 }
 
 static struct clocksource hyperv_cs_msr = {
@@ -271,7 +269,6 @@ static struct clocksource hyperv_cs_msr = {
 	.flags	= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
-#ifdef CONFIG_HYPERV_TSCPAGE
 static bool __init hv_init_tsc_clocksource(void)
 {
 	u64		tsc_msr;
@@ -280,12 +277,8 @@ static bool __init hv_init_tsc_clocksource(void)
 	if (!(ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE))
 		return false;
 
-	tsc_pg = vmalloc(PAGE_SIZE);
-	if (!tsc_pg)
-		return false;
-
 	hyperv_cs = &hyperv_cs_tsc;
-	phys_addr = page_to_phys(vmalloc_to_page(tsc_pg));
+	phys_addr = virt_to_phys(&tsc_pg);
 
 	/*
 	 * The Hyper-V TLFS specifies to preserve the value of reserved
@@ -302,17 +295,11 @@ static bool __init hv_init_tsc_clocksource(void)
 	hv_set_clocksource_vdso(hyperv_cs_tsc);
 	clocksource_register_hz(&hyperv_cs_tsc, NSEC_PER_SEC/100);
 
-	/* sched_clock_register is needed on ARM64 but is a no-op on x86 */
-	sched_clock_register(read_hv_sched_clock_tsc, 64, HV_CLOCK_HZ);
+	hv_sched_clock_offset = hyperv_cs->read(hyperv_cs);
+	hv_setup_sched_clock(read_hv_sched_clock_tsc);
+
 	return true;
 }
-#else
-static bool __init hv_init_tsc_clocksource(void)
-{
-	return false;
-}
-#endif
-
 
 void __init hv_init_clocksource(void)
 {
@@ -333,7 +320,7 @@ void __init hv_init_clocksource(void)
 	hyperv_cs = &hyperv_cs_msr;
 	clocksource_register_hz(&hyperv_cs_msr, NSEC_PER_SEC/100);
 
-	/* sched_clock_register is needed on ARM64 but is a no-op on x86 */
-	sched_clock_register(read_hv_sched_clock_msr, 64, HV_CLOCK_HZ);
+	hv_sched_clock_offset = hyperv_cs->read(hyperv_cs);
+	hv_setup_sched_clock(read_hv_sched_clock_msr);
 }
 EXPORT_SYMBOL_GPL(hv_init_clocksource);
diff --git a/drivers/clocksource/renesas-ostm.c b/drivers/clocksource/renesas-ostm.c
index 61d5f3b539ce..37c39b901bb1 100644
--- a/drivers/clocksource/renesas-ostm.c
+++ b/drivers/clocksource/renesas-ostm.c
@@ -221,7 +221,7 @@ static int __init ostm_init(struct device_node *np)
 	}
 
 	rate = clk_get_rate(ostm_clk);
-	ostm->ticks_per_jiffy = (rate + HZ / 2) / HZ;
+	ostm->ticks_per_jiffy = DIV_ROUND_CLOSEST(rate, HZ);
 
 	/*
 	 * First probed device will be used as system clocksource. Any
diff --git a/drivers/clocksource/sh_cmt.c b/drivers/clocksource/sh_cmt.c
index 55d3e03f2cd4..ef773db080e9 100644
--- a/drivers/clocksource/sh_cmt.c
+++ b/drivers/clocksource/sh_cmt.c
@@ -776,11 +776,8 @@ static int sh_cmt_register_clockevent(struct sh_cmt_channel *ch,
 	int ret;
 
 	irq = platform_get_irq(ch->cmt->pdev, ch->index);
-	if (irq < 0) {
-		dev_err(&ch->cmt->pdev->dev, "ch%u: failed to get irq\n",
-			ch->index);
+	if (irq < 0)
 		return irq;
-	}
 
 	ret = request_irq(irq, sh_cmt_interrupt,
 			  IRQF_TIMER | IRQF_IRQPOLL | IRQF_NOBALANCING,
@@ -921,13 +918,25 @@ static const struct platform_device_id sh_cmt_id_table[] = {
 MODULE_DEVICE_TABLE(platform, sh_cmt_id_table);
 
 static const struct of_device_id sh_cmt_of_table[] __maybe_unused = {
-	{ .compatible = "renesas,cmt-48", .data = &sh_cmt_info[SH_CMT_48BIT] },
+	{
+		/* deprecated, preserved for backward compatibility */
+		.compatible = "renesas,cmt-48",
+		.data = &sh_cmt_info[SH_CMT_48BIT]
+	},
 	{
 		/* deprecated, preserved for backward compatibility */
 		.compatible = "renesas,cmt-48-gen2",
 		.data = &sh_cmt_info[SH_CMT0_RCAR_GEN2]
 	},
 	{
+		.compatible = "renesas,r8a7740-cmt1",
+		.data = &sh_cmt_info[SH_CMT_48BIT]
+	},
+	{
+		.compatible = "renesas,sh73a0-cmt1",
+		.data = &sh_cmt_info[SH_CMT_48BIT]
+	},
+	{
 		.compatible = "renesas,rcar-gen2-cmt0",
 		.data = &sh_cmt_info[SH_CMT0_RCAR_GEN2]
 	},
diff --git a/drivers/clocksource/sh_tmu.c b/drivers/clocksource/sh_tmu.c
index 49f1c805fc95..8c4f3753b36e 100644
--- a/drivers/clocksource/sh_tmu.c
+++ b/drivers/clocksource/sh_tmu.c
@@ -462,11 +462,8 @@ static int sh_tmu_channel_setup(struct sh_tmu_channel *ch, unsigned int index,
 		ch->base = tmu->mapbase + 8 + ch->index * 12;
 
 	ch->irq = platform_get_irq(tmu->pdev, index);
-	if (ch->irq < 0) {
-		dev_err(&tmu->pdev->dev, "ch%u: failed to get irq\n",
-			ch->index);
+	if (ch->irq < 0)
 		return ch->irq;
-	}
 
 	ch->cs_enabled = false;
 	ch->enable_count = 0;
diff --git a/drivers/clocksource/timer-atmel-tcb.c b/drivers/clocksource/timer-atmel-tcb.c
index 6ed31f9def7e..7427b07495a8 100644
--- a/drivers/clocksource/timer-atmel-tcb.c
+++ b/drivers/clocksource/timer-atmel-tcb.c
@@ -6,6 +6,7 @@
 #include <linux/irq.h>
 
 #include <linux/clk.h>
+#include <linux/delay.h>
 #include <linux/err.h>
 #include <linux/ioport.h>
 #include <linux/io.h>
@@ -125,6 +126,18 @@ static u64 notrace tc_sched_clock_read32(void)
 	return tc_get_cycles32(&clksrc);
 }
 
+static struct delay_timer tc_delay_timer;
+
+static unsigned long tc_delay_timer_read(void)
+{
+	return tc_get_cycles(&clksrc);
+}
+
+static unsigned long notrace tc_delay_timer_read32(void)
+{
+	return tc_get_cycles32(&clksrc);
+}
+
 #ifdef CONFIG_GENERIC_CLOCKEVENTS
 
 struct tc_clkevt_device {
@@ -432,6 +445,7 @@ static int __init tcb_clksrc_init(struct device_node *node)
 		/* setup ony channel 0 */
 		tcb_setup_single_chan(&tc, best_divisor_idx);
 		tc_sched_clock = tc_sched_clock_read32;
+		tc_delay_timer.read_current_timer = tc_delay_timer_read32;
 	} else {
 		/* we have three clocks no matter what the
 		 * underlying platform supports.
@@ -444,6 +458,7 @@ static int __init tcb_clksrc_init(struct device_node *node)
 		/* setup both channel 0 & 1 */
 		tcb_setup_dual_chan(&tc, best_divisor_idx);
 		tc_sched_clock = tc_sched_clock_read;
+		tc_delay_timer.read_current_timer = tc_delay_timer_read;
 	}
 
 	/* and away we go! */
@@ -458,6 +473,9 @@ static int __init tcb_clksrc_init(struct device_node *node)
 
 	sched_clock_register(tc_sched_clock, 32, divided_rate);
 
+	tc_delay_timer.freq = divided_rate;
+	register_current_timer_delay(&tc_delay_timer);
+
 	return 0;
 
 err_unregister_clksrc:
diff --git a/drivers/clocksource/timer-imx-sysctr.c b/drivers/clocksource/timer-imx-sysctr.c
index fd7d68066efb..b7c80a368a1b 100644
--- a/drivers/clocksource/timer-imx-sysctr.c
+++ b/drivers/clocksource/timer-imx-sysctr.c
@@ -20,6 +20,8 @@
 #define SYS_CTR_EN		0x1
 #define SYS_CTR_IRQ_MASK	0x2
 
+#define SYS_CTR_CLK_DIV		0x3
+
 static void __iomem *sys_ctr_base;
 static u32 cmpcr;
 
@@ -134,6 +136,9 @@ static int __init sysctr_timer_init(struct device_node *np)
 	if (ret)
 		return ret;
 
+	/* system counter clock is divided by 3 internally */
+	to_sysctr.of_clk.rate /= SYS_CTR_CLK_DIV;
+
 	sys_ctr_base = timer_of_base(&to_sysctr);
 	cmpcr = readl(sys_ctr_base + CMPCR);
 	cmpcr &= ~SYS_CTR_EN;
diff --git a/drivers/clocksource/timer-npcm7xx.c b/drivers/clocksource/timer-npcm7xx.c
index 8a30da7f083b..9780ffd8010e 100644
--- a/drivers/clocksource/timer-npcm7xx.c
+++ b/drivers/clocksource/timer-npcm7xx.c
@@ -32,7 +32,7 @@
 #define NPCM7XX_Tx_INTEN		BIT(29)
 #define NPCM7XX_Tx_COUNTEN		BIT(30)
 #define NPCM7XX_Tx_ONESHOT		0x0
-#define NPCM7XX_Tx_OPER			GENMASK(27, 3)
+#define NPCM7XX_Tx_OPER			GENMASK(28, 27)
 #define NPCM7XX_Tx_MIN_PRESCALE		0x1
 #define NPCM7XX_Tx_TDR_MASK_BITS	24
 #define NPCM7XX_Tx_MAX_CNT		0xFFFFFF
@@ -84,8 +84,6 @@ static int npcm7xx_timer_oneshot(struct clock_event_device *evt)
 
 	val = readl(timer_of_base(to) + NPCM7XX_REG_TCSR0);
 	val &= ~NPCM7XX_Tx_OPER;
-
-	val = readl(timer_of_base(to) + NPCM7XX_REG_TCSR0);
 	val |= NPCM7XX_START_ONESHOT_Tx;
 	writel(val, timer_of_base(to) + NPCM7XX_REG_TCSR0);
 
@@ -97,12 +95,11 @@ static int npcm7xx_timer_periodic(struct clock_event_device *evt)
 	struct timer_of *to = to_timer_of(evt);
 	u32 val;
 
+	writel(timer_of_period(to), timer_of_base(to) + NPCM7XX_REG_TICR0);
+
 	val = readl(timer_of_base(to) + NPCM7XX_REG_TCSR0);
 	val &= ~NPCM7XX_Tx_OPER;
-
-	writel(timer_of_period(to), timer_of_base(to) + NPCM7XX_REG_TICR0);
 	val |= NPCM7XX_START_PERIODIC_Tx;
-
 	writel(val, timer_of_base(to) + NPCM7XX_REG_TCSR0);
 
 	return 0;
diff --git a/drivers/clocksource/timer-of.c b/drivers/clocksource/timer-of.c
index 80542289fae7..d8c2bd4391d0 100644
--- a/drivers/clocksource/timer-of.c
+++ b/drivers/clocksource/timer-of.c
@@ -113,8 +113,10 @@ static __init int timer_of_clk_init(struct device_node *np,
 	of_clk->clk = of_clk->name ? of_clk_get_by_name(np, of_clk->name) :
 		of_clk_get(np, of_clk->index);
 	if (IS_ERR(of_clk->clk)) {
-		pr_err("Failed to get clock for %pOF\n", np);
-		return PTR_ERR(of_clk->clk);
+		ret = PTR_ERR(of_clk->clk);
+		if (ret != -EPROBE_DEFER)
+			pr_err("Failed to get clock for %pOF\n", np);
+		goto out;
 	}
 
 	ret = clk_prepare_enable(of_clk->clk);
diff --git a/drivers/clocksource/timer-probe.c b/drivers/clocksource/timer-probe.c
index dda1946e84dd..ee9574da53c0 100644
--- a/drivers/clocksource/timer-probe.c
+++ b/drivers/clocksource/timer-probe.c
@@ -29,7 +29,9 @@ void __init timer_probe(void)
 
 		ret = init_func_ret(np);
 		if (ret) {
-			pr_err("Failed to initialize '%pOF': %d\n", np, ret);
+			if (ret != -EPROBE_DEFER)
+				pr_err("Failed to initialize '%pOF': %d\n", np,
+				       ret);
 			continue;
 		}
 
diff --git a/drivers/clocksource/timer-sun4i.c b/drivers/clocksource/timer-sun4i.c
index 65f38f6ca714..0ba8155b8287 100644
--- a/drivers/clocksource/timer-sun4i.c
+++ b/drivers/clocksource/timer-sun4i.c
@@ -219,5 +219,9 @@ static int __init sun4i_timer_init(struct device_node *node)
 }
 TIMER_OF_DECLARE(sun4i, "allwinner,sun4i-a10-timer",
 		       sun4i_timer_init);
+TIMER_OF_DECLARE(sun8i_a23, "allwinner,sun8i-a23-timer",
+		 sun4i_timer_init);
+TIMER_OF_DECLARE(sun8i_v3s, "allwinner,sun8i-v3s-timer",
+		 sun4i_timer_init);
 TIMER_OF_DECLARE(suniv, "allwinner,suniv-f1c100s-timer",
 		       sun4i_timer_init);