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

…linux/kernel/git/tip/tip

Pull timer updates from Thomas Gleixner:
 "The timer department delivers this time:

   - Support for cross clock domain timestamps in the core code plus a
     first user.  That allows more precise timestamping for PTP and
     later for audio and other peripherals.

     The ptp/e1000e patches have been acked by the relevant maintainers
     and are carried in the timer tree to avoid merge ordering issues.

   - Support for unregistering the current clocksource watchdog.  That
     lifts a limitation for switching clocksources which has been there
     from day 1

   - The usual pile of fixes and updates to the core and the drivers.
     Nothing outstanding and exciting"

* 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (26 commits)
  time/timekeeping: Work around false positive GCC warning
  e1000e: Adds hardware supported cross timestamp on e1000e nic
  ptp: Add PTP_SYS_OFFSET_PRECISE for driver crosstimestamping
  x86/tsc: Always Running Timer (ART) correlated clocksource
  hrtimer: Revert CLOCK_MONOTONIC_RAW support
  time: Add history to cross timestamp interface supporting slower devices
  time: Add driver cross timestamp interface for higher precision time synchronization
  time: Remove duplicated code in ktime_get_raw_and_real()
  time: Add timekeeping snapshot code capturing system time and counter
  time: Add cycles to nanoseconds translation
  jiffies: Use CLOCKSOURCE_MASK instead of constant
  clocksource: Introduce clocksource_freq2mult()
  clockevents/drivers/exynos_mct: Implement ->set_state_oneshot_stopped()
  clockevents/drivers/arm_global_timer: Implement ->set_state_oneshot_stopped()
  clockevents/drivers/arm_arch_timer: Implement ->set_state_oneshot_stopped()
  clocksource/drivers/arm_global_timer: Register delay timer
  clocksource/drivers/lpc32xx: Support timer-based ARM delay
  clocksource/drivers/lpc32xx: Support periodic mode
  clocksource/drivers/lpc32xx: Don't use the prescaler counter for clockevents
  clocksource/drivers/rockchip: Add err handle for rk_timer_init
  ...

Documentation/ptp/testptp.c

@@ -277,13 +277,15 @@ int main(int argc, char *argv[])
 			       "  %d external time stamp channels\n"
 			       "  %d programmable periodic signals\n"
 			       "  %d pulse per second\n"
-			       "  %d programmable pins\n",
+			       "  %d programmable pins\n"
+			       "  %d cross timestamping\n",
 			       caps.max_adj,
 			       caps.n_alarm,
 			       caps.n_ext_ts,
 			       caps.n_per_out,
 			       caps.pps,
-			       caps.n_pins);
+			       caps.n_pins,
+			       caps.cross_timestamping);
 		}
 	}
 

arch/x86/include/asm/cpufeatures.h

@@ -85,7 +85,7 @@
 #define X86_FEATURE_P4		( 3*32+ 7) /* "" P4 */
 #define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* TSC ticks at a constant rate */
 #define X86_FEATURE_UP		( 3*32+ 9) /* smp kernel running on up */
-/* free, was #define X86_FEATURE_FXSAVE_LEAK ( 3*32+10) * "" FXSAVE leaks FOP/FIP/FOP */
+#define X86_FEATURE_ART		( 3*32+10) /* Platform has always running timer (ART) */
 #define X86_FEATURE_ARCH_PERFMON ( 3*32+11) /* Intel Architectural PerfMon */
 #define X86_FEATURE_PEBS	( 3*32+12) /* Precise-Event Based Sampling */
 #define X86_FEATURE_BTS		( 3*32+13) /* Branch Trace Store */

arch/x86/include/asm/tsc.h

@@ -29,6 +29,8 @@ static inline cycles_t get_cycles(void)
 	return rdtsc();
 }
 
+extern struct system_counterval_t convert_art_to_tsc(cycle_t art);
+
 extern void tsc_init(void);
 extern void mark_tsc_unstable(char *reason);
 extern int unsynchronized_tsc(void);

arch/x86/kernel/tsc.c

@@ -43,6 +43,11 @@ static DEFINE_STATIC_KEY_FALSE(__use_tsc);
 
 int tsc_clocksource_reliable;
 
+static u32 art_to_tsc_numerator;
+static u32 art_to_tsc_denominator;
+static u64 art_to_tsc_offset;
+struct clocksource *art_related_clocksource;
+
 /*
  * Use a ring-buffer like data structure, where a writer advances the head by
  * writing a new data entry and a reader advances the tail when it observes a
@@ -964,6 +969,37 @@ core_initcall(cpufreq_tsc);
 
 #endif /* CONFIG_CPU_FREQ */
 
+#define ART_CPUID_LEAF (0x15)
+#define ART_MIN_DENOMINATOR (1)
+
+
+/*
+ * If ART is present detect the numerator:denominator to convert to TSC
+ */
+static void detect_art(void)
+{
+	unsigned int unused[2];
+
+	if (boot_cpu_data.cpuid_level < ART_CPUID_LEAF)
+		return;
+
+	cpuid(ART_CPUID_LEAF, &art_to_tsc_denominator,
+	      &art_to_tsc_numerator, unused, unused+1);
+
+	/* Don't enable ART in a VM, non-stop TSC required */
+	if (boot_cpu_has(X86_FEATURE_HYPERVISOR) ||
+	    !boot_cpu_has(X86_FEATURE_NONSTOP_TSC) ||
+	    art_to_tsc_denominator < ART_MIN_DENOMINATOR)
+		return;
+
+	if (rdmsrl_safe(MSR_IA32_TSC_ADJUST, &art_to_tsc_offset))
+		return;
+
+	/* Make this sticky over multiple CPU init calls */
+	setup_force_cpu_cap(X86_FEATURE_ART);
+}
+
+
 /* clocksource code */
 
 static struct clocksource clocksource_tsc;
@@ -1071,6 +1107,25 @@ int unsynchronized_tsc(void)
 	return 0;
 }
 
+/*
+ * Convert ART to TSC given numerator/denominator found in detect_art()
+ */
+struct system_counterval_t convert_art_to_tsc(cycle_t art)
+{
+	u64 tmp, res, rem;
+
+	rem = do_div(art, art_to_tsc_denominator);
+
+	res = art * art_to_tsc_numerator;
+	tmp = rem * art_to_tsc_numerator;
+
+	do_div(tmp, art_to_tsc_denominator);
+	res += tmp + art_to_tsc_offset;
+
+	return (struct system_counterval_t) {.cs = art_related_clocksource,
+			.cycles = res};
+}
+EXPORT_SYMBOL(convert_art_to_tsc);
 
 static void tsc_refine_calibration_work(struct work_struct *work);
 static DECLARE_DELAYED_WORK(tsc_irqwork, tsc_refine_calibration_work);
@@ -1142,6 +1197,8 @@ static void tsc_refine_calibration_work(struct work_struct *work)
 		(unsigned long)tsc_khz % 1000);
 
 out:
+	if (boot_cpu_has(X86_FEATURE_ART))
+		art_related_clocksource = &clocksource_tsc;
 	clocksource_register_khz(&clocksource_tsc, tsc_khz);
 }
 
@@ -1235,6 +1292,8 @@ void __init tsc_init(void)
 		mark_tsc_unstable("TSCs unsynchronized");
 
 	check_system_tsc_reliable();
+
+	detect_art();
 }
 
 #ifdef CONFIG_SMP

drivers/clocksource/Kconfig

@@ -160,6 +160,7 @@ config CLKSRC_EFM32
 config CLKSRC_LPC32XX
 	bool "Clocksource for LPC32XX" if COMPILE_TEST
 	depends on GENERIC_CLOCKEVENTS && HAS_IOMEM
+	depends on ARM
 	select CLKSRC_MMIO
 	select CLKSRC_OF
 	help

drivers/clocksource/arm_arch_timer.c

@@ -32,6 +32,14 @@
 #define CNTTIDR		0x08
 #define CNTTIDR_VIRT(n)	(BIT(1) << ((n) * 4))
 
+#define CNTACR(n)	(0x40 + ((n) * 4))
+#define CNTACR_RPCT	BIT(0)
+#define CNTACR_RVCT	BIT(1)
+#define CNTACR_RFRQ	BIT(2)
+#define CNTACR_RVOFF	BIT(3)
+#define CNTACR_RWVT	BIT(4)
+#define CNTACR_RWPT	BIT(5)
+
 #define CNTVCT_LO	0x08
 #define CNTVCT_HI	0x0c
 #define CNTFRQ		0x10
@@ -266,10 +274,12 @@ static void __arch_timer_setup(unsigned type,
 		if (arch_timer_use_virtual) {
 			clk->irq = arch_timer_ppi[VIRT_PPI];
 			clk->set_state_shutdown = arch_timer_shutdown_virt;
+			clk->set_state_oneshot_stopped = arch_timer_shutdown_virt;
 			clk->set_next_event = arch_timer_set_next_event_virt;
 		} else {
 			clk->irq = arch_timer_ppi[PHYS_SECURE_PPI];
 			clk->set_state_shutdown = arch_timer_shutdown_phys;
+			clk->set_state_oneshot_stopped = arch_timer_shutdown_phys;
 			clk->set_next_event = arch_timer_set_next_event_phys;
 		}
 	} else {
@@ -279,10 +289,12 @@ static void __arch_timer_setup(unsigned type,
 		clk->cpumask = cpu_all_mask;
 		if (arch_timer_mem_use_virtual) {
 			clk->set_state_shutdown = arch_timer_shutdown_virt_mem;
+			clk->set_state_oneshot_stopped = arch_timer_shutdown_virt_mem;
 			clk->set_next_event =
 				arch_timer_set_next_event_virt_mem;
 		} else {
 			clk->set_state_shutdown = arch_timer_shutdown_phys_mem;
+			clk->set_state_oneshot_stopped = arch_timer_shutdown_phys_mem;
 			clk->set_next_event =
 				arch_timer_set_next_event_phys_mem;
 		}
@@ -757,53 +769,65 @@ static void __init arch_timer_mem_init(struct device_node *np)
 	}
 
 	cnttidr = readl_relaxed(cntctlbase + CNTTIDR);
-	iounmap(cntctlbase);
 
 	/*
 	 * Try to find a virtual capable frame. Otherwise fall back to a
 	 * physical capable frame.
 	 */
 	for_each_available_child_of_node(np, frame) {
 		int n;
+		u32 cntacr;
 
 		if (of_property_read_u32(frame, "frame-number", &n)) {
 			pr_err("arch_timer: Missing frame-number\n");
-			of_node_put(best_frame);
 			of_node_put(frame);
-			return;
+			goto out;
 		}
 
-		if (cnttidr & CNTTIDR_VIRT(n)) {
+		/* Try enabling everything, and see what sticks */
+		cntacr = CNTACR_RFRQ | CNTACR_RWPT | CNTACR_RPCT |
+			 CNTACR_RWVT | CNTACR_RVOFF | CNTACR_RVCT;
+		writel_relaxed(cntacr, cntctlbase + CNTACR(n));
+		cntacr = readl_relaxed(cntctlbase + CNTACR(n));
+
+		if ((cnttidr & CNTTIDR_VIRT(n)) &&
+		    !(~cntacr & (CNTACR_RWVT | CNTACR_RVCT))) {
 			of_node_put(best_frame);
 			best_frame = frame;
 			arch_timer_mem_use_virtual = true;
 			break;
 		}
+
+		if (~cntacr & (CNTACR_RWPT | CNTACR_RPCT))
+			continue;
+
 		of_node_put(best_frame);
 		best_frame = of_node_get(frame);
 	}
 
 	base = arch_counter_base = of_iomap(best_frame, 0);
 	if (!base) {
 		pr_err("arch_timer: Can't map frame's registers\n");
-		of_node_put(best_frame);
-		return;
+		goto out;
 	}
 
 	if (arch_timer_mem_use_virtual)
 		irq = irq_of_parse_and_map(best_frame, 1);
 	else
 		irq = irq_of_parse_and_map(best_frame, 0);
-	of_node_put(best_frame);
+
 	if (!irq) {
 		pr_err("arch_timer: Frame missing %s irq",
 		       arch_timer_mem_use_virtual ? "virt" : "phys");
-		return;
+		goto out;
 	}
 
 	arch_timer_detect_rate(base, np);
 	arch_timer_mem_register(base, irq);
 	arch_timer_common_init();
+out:
+	iounmap(cntctlbase);
+	of_node_put(best_frame);
 }
 CLOCKSOURCE_OF_DECLARE(armv7_arch_timer_mem, "arm,armv7-timer-mem",
 		       arch_timer_mem_init);

drivers/clocksource/arm_global_timer.c

@@ -16,6 +16,7 @@
 #include <linux/clockchips.h>
 #include <linux/cpu.h>
 #include <linux/clk.h>
+#include <linux/delay.h>
 #include <linux/err.h>
 #include <linux/io.h>
 #include <linux/of.h>
@@ -174,6 +175,7 @@ static int gt_clockevents_init(struct clock_event_device *clk)
 	clk->set_state_shutdown = gt_clockevent_shutdown;
 	clk->set_state_periodic = gt_clockevent_set_periodic;
 	clk->set_state_oneshot = gt_clockevent_shutdown;
+	clk->set_state_oneshot_stopped = gt_clockevent_shutdown;
 	clk->set_next_event = gt_clockevent_set_next_event;
 	clk->cpumask = cpumask_of(cpu);
 	clk->rating = 300;
@@ -221,6 +223,21 @@ static u64 notrace gt_sched_clock_read(void)
 }
 #endif
 
+static unsigned long gt_read_long(void)
+{
+	return readl_relaxed(gt_base + GT_COUNTER0);
+}
+
+static struct delay_timer gt_delay_timer = {
+	.read_current_timer = gt_read_long,
+};
+
+static void __init gt_delay_timer_init(void)
+{
+	gt_delay_timer.freq = gt_clk_rate;
+	register_current_timer_delay(&gt_delay_timer);
+}
+
 static void __init gt_clocksource_init(void)
 {
 	writel(0, gt_base + GT_CONTROL);
@@ -317,6 +334,7 @@ static void __init global_timer_of_register(struct device_node *np)
 	/* Immediately configure the timer on the boot CPU */
 	gt_clocksource_init();
 	gt_clockevents_init(this_cpu_ptr(gt_evt));
+	gt_delay_timer_init();
 
 	return;
 

drivers/clocksource/exynos_mct.c

@@ -313,6 +313,7 @@ static struct clock_event_device mct_comp_device = {
 	.set_state_periodic	= mct_set_state_periodic,
 	.set_state_shutdown	= mct_set_state_shutdown,
 	.set_state_oneshot	= mct_set_state_shutdown,
+	.set_state_oneshot_stopped = mct_set_state_shutdown,
 	.tick_resume		= mct_set_state_shutdown,
 };
 
@@ -452,6 +453,7 @@ static int exynos4_local_timer_setup(struct mct_clock_event_device *mevt)
 	evt->set_state_periodic = set_state_periodic;
 	evt->set_state_shutdown = set_state_shutdown;
 	evt->set_state_oneshot = set_state_shutdown;
+	evt->set_state_oneshot_stopped = set_state_shutdown;
 	evt->tick_resume = set_state_shutdown;
 	evt->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
 	evt->rating = 450;

drivers/clocksource/rockchip_timer.c

@@ -122,31 +122,31 @@ static void __init rk_timer_init(struct device_node *np)
 	pclk = of_clk_get_by_name(np, "pclk");
 	if (IS_ERR(pclk)) {
 		pr_err("Failed to get pclk for '%s'\n", TIMER_NAME);
-		return;
+		goto out_unmap;
 	}
 
 	if (clk_prepare_enable(pclk)) {
 		pr_err("Failed to enable pclk for '%s'\n", TIMER_NAME);
-		return;
+		goto out_unmap;
 	}
 
 	timer_clk = of_clk_get_by_name(np, "timer");
 	if (IS_ERR(timer_clk)) {
 		pr_err("Failed to get timer clock for '%s'\n", TIMER_NAME);
-		return;
+		goto out_timer_clk;
 	}
 
 	if (clk_prepare_enable(timer_clk)) {
 		pr_err("Failed to enable timer clock\n");
-		return;
+		goto out_timer_clk;
 	}
 
 	bc_timer.freq = clk_get_rate(timer_clk);
 
 	irq = irq_of_parse_and_map(np, 0);
 	if (!irq) {
 		pr_err("Failed to map interrupts for '%s'\n", TIMER_NAME);
-		return;
+		goto out_irq;
 	}
 
 	ce->name = TIMER_NAME;
@@ -164,10 +164,19 @@ static void __init rk_timer_init(struct device_node *np)
 	ret = request_irq(irq, rk_timer_interrupt, IRQF_TIMER, TIMER_NAME, ce);
 	if (ret) {
 		pr_err("Failed to initialize '%s': %d\n", TIMER_NAME, ret);
-		return;
+		goto out_irq;
 	}
 
 	clockevents_config_and_register(ce, bc_timer.freq, 1, UINT_MAX);
+
+	return;
+
+out_irq:
+	clk_disable_unprepare(timer_clk);
+out_timer_clk:
+	clk_disable_unprepare(pclk);
+out_unmap:
+	iounmap(bc_timer.base);
 }
 
 CLOCKSOURCE_OF_DECLARE(rk_timer, "rockchip,rk3288-timer", rk_timer_init);