Merge branch 'timers/drivers/armv8.6_arch_timer' into timers/drivers/next

The branch is a stable branch shared with ARM maintainers for the
first 13th patches of the series:

It is based on v5.14-rc3.

As stated by the changelog:

" [... ] enabling ARMv8.6 support for timer subsystem, and was prompted by a
discussion with Oliver around the fact that an ARMv8.6 implementation
must have a 1GHz counter, which leads to a number of things to break
in the timer code:

- the counter rollover can come pretty quickly as we only advertise a
  56bit counter,
- the maximum timer delta can be remarkably small, as we use the
  countdown interface which is limited to 32bit...

Thankfully, there is a way out: we can compute the minimal width of
the counter based on the guarantees that the architecture gives us,
and we can use the 64bit comparator interface instead of the countdown
to program the timer.

Finally, we start making use of the ARMv8.6 ECV features by switching
accesses to the counters to a self-synchronising register, removing
the need for an ISB. Hopefully, implementations will *not* just stick
an invisible ISB there...

A side effect of the switch to CVAL is that XGene-1 breaks. I have
added a workaround to keep it alive.

I have added Oliver's original patch[0] to the series and tweaked a
couple of things. Blame me if I broke anything.

The whole things has been tested on Juno (sysreg + MMIO timers),
XGene-1 (broken sysreg timers), FVP (FEAT_ECV, CNT*CTSS_EL0).
"

Link: https://lore.kernel.org/r/20211017124225.3018098-1-maz@kernel.org
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>

4 files changed, 193 insertions, 141 deletions

diff --git a/arch/arm/include/asm/arch_timer.h b/arch/arm/include/asm/arch_timer.h
index 99175812d903..bb129b6d2366 100644
--- a/arch/arm/include/asm/arch_timer.h
+++ b/arch/arm/include/asm/arch_timer.h
@@ -7,6 +7,7 @@
 #include <asm/hwcap.h>
 #include <linux/clocksource.h>
 #include <linux/init.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
 #include <linux/types.h>
 
 #include <clocksource/arm_arch_timer.h>
@@ -24,29 +25,35 @@ int arch_timer_arch_init(void);
  * the code. At least it does so with a recent GCC (4.6.3).
  */
 static __always_inline
-void arch_timer_reg_write_cp15(int access, enum arch_timer_reg reg, u32 val)
+void arch_timer_reg_write_cp15(int access, enum arch_timer_reg reg, u64 val)
 {
 	if (access == ARCH_TIMER_PHYS_ACCESS) {
 		switch (reg) {
 		case ARCH_TIMER_REG_CTRL:
-			asm volatile("mcr p15, 0, %0, c14, c2, 1" : : "r" (val));
+			asm volatile("mcr p15, 0, %0, c14, c2, 1" : : "r" ((u32)val));
+			isb();
 			break;
-		case ARCH_TIMER_REG_TVAL:
-			asm volatile("mcr p15, 0, %0, c14, c2, 0" : : "r" (val));
+		case ARCH_TIMER_REG_CVAL:
+			asm volatile("mcrr p15, 2, %Q0, %R0, c14" : : "r" (val));
 			break;
+		default:
+			BUILD_BUG();
 		}
 	} else if (access == ARCH_TIMER_VIRT_ACCESS) {
 		switch (reg) {
 		case ARCH_TIMER_REG_CTRL:
-			asm volatile("mcr p15, 0, %0, c14, c3, 1" : : "r" (val));
+			asm volatile("mcr p15, 0, %0, c14, c3, 1" : : "r" ((u32)val));
+			isb();
 			break;
-		case ARCH_TIMER_REG_TVAL:
-			asm volatile("mcr p15, 0, %0, c14, c3, 0" : : "r" (val));
+		case ARCH_TIMER_REG_CVAL:
+			asm volatile("mcrr p15, 3, %Q0, %R0, c14" : : "r" (val));
 			break;
+		default:
+			BUILD_BUG();
 		}
+	} else {
+		BUILD_BUG();
 	}
-
-	isb();
 }
 
 static __always_inline
@@ -59,19 +66,19 @@ u32 arch_timer_reg_read_cp15(int access, enum arch_timer_reg reg)
 		case ARCH_TIMER_REG_CTRL:
 			asm volatile("mrc p15, 0, %0, c14, c2, 1" : "=r" (val));
 			break;
-		case ARCH_TIMER_REG_TVAL:
-			asm volatile("mrc p15, 0, %0, c14, c2, 0" : "=r" (val));
-			break;
+		default:
+			BUILD_BUG();
 		}
 	} else if (access == ARCH_TIMER_VIRT_ACCESS) {
 		switch (reg) {
 		case ARCH_TIMER_REG_CTRL:
 			asm volatile("mrc p15, 0, %0, c14, c3, 1" : "=r" (val));
 			break;
-		case ARCH_TIMER_REG_TVAL:
-			asm volatile("mrc p15, 0, %0, c14, c3, 0" : "=r" (val));
-			break;
+		default:
+			BUILD_BUG();
 		}
+	} else {
+		BUILD_BUG();
 	}
 
 	return val;
diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h
index 88d20f04c64a..519ac1f7f859 100644
--- a/arch/arm64/include/asm/arch_timer.h
+++ b/arch/arm64/include/asm/arch_timer.h
@@ -32,7 +32,7 @@
 	({								\
 		const struct arch_timer_erratum_workaround *__wa;	\
 		__wa = __this_cpu_read(timer_unstable_counter_workaround); \
-		(__wa && __wa->h) ? __wa->h : arch_timer_##h;		\
+		(__wa && __wa->h) ? ({ isb(); __wa->h;}) : arch_timer_##h; \
 	})
 
 #else
@@ -52,8 +52,6 @@ struct arch_timer_erratum_workaround {
 	enum arch_timer_erratum_match_type match_type;
 	const void *id;
 	const char *desc;
-	u32 (*read_cntp_tval_el0)(void);
-	u32 (*read_cntv_tval_el0)(void);
 	u64 (*read_cntpct_el0)(void);
 	u64 (*read_cntvct_el0)(void);
 	int (*set_next_event_phys)(unsigned long, struct clock_event_device *);
@@ -64,24 +62,15 @@ struct arch_timer_erratum_workaround {
 DECLARE_PER_CPU(const struct arch_timer_erratum_workaround *,
 		timer_unstable_counter_workaround);
 
-/* inline sysreg accessors that make erratum_handler() work */
-static inline notrace u32 arch_timer_read_cntp_tval_el0(void)
-{
-	return read_sysreg(cntp_tval_el0);
-}
-
-static inline notrace u32 arch_timer_read_cntv_tval_el0(void)
-{
-	return read_sysreg(cntv_tval_el0);
-}
-
 static inline notrace u64 arch_timer_read_cntpct_el0(void)
 {
+	isb();
 	return read_sysreg(cntpct_el0);
 }
 
 static inline notrace u64 arch_timer_read_cntvct_el0(void)
 {
+	isb();
 	return read_sysreg(cntvct_el0);
 }
 
@@ -102,51 +91,58 @@ static inline notrace u64 arch_timer_read_cntvct_el0(void)
  * the code.
  */
 static __always_inline
-void arch_timer_reg_write_cp15(int access, enum arch_timer_reg reg, u32 val)
+void arch_timer_reg_write_cp15(int access, enum arch_timer_reg reg, u64 val)
 {
 	if (access == ARCH_TIMER_PHYS_ACCESS) {
 		switch (reg) {
 		case ARCH_TIMER_REG_CTRL:
 			write_sysreg(val, cntp_ctl_el0);
+			isb();
 			break;
-		case ARCH_TIMER_REG_TVAL:
-			write_sysreg(val, cntp_tval_el0);
+		case ARCH_TIMER_REG_CVAL:
+			write_sysreg(val, cntp_cval_el0);
 			break;
+		default:
+			BUILD_BUG();
 		}
 	} else if (access == ARCH_TIMER_VIRT_ACCESS) {
 		switch (reg) {
 		case ARCH_TIMER_REG_CTRL:
 			write_sysreg(val, cntv_ctl_el0);
+			isb();
 			break;
-		case ARCH_TIMER_REG_TVAL:
-			write_sysreg(val, cntv_tval_el0);
+		case ARCH_TIMER_REG_CVAL:
+			write_sysreg(val, cntv_cval_el0);
 			break;
+		default:
+			BUILD_BUG();
 		}
+	} else {
+		BUILD_BUG();
 	}
-
-	isb();
 }
 
 static __always_inline
-u32 arch_timer_reg_read_cp15(int access, enum arch_timer_reg reg)
+u64 arch_timer_reg_read_cp15(int access, enum arch_timer_reg reg)
 {
 	if (access == ARCH_TIMER_PHYS_ACCESS) {
 		switch (reg) {
 		case ARCH_TIMER_REG_CTRL:
 			return read_sysreg(cntp_ctl_el0);
-		case ARCH_TIMER_REG_TVAL:
-			return arch_timer_reg_read_stable(cntp_tval_el0);
+		default:
+			BUILD_BUG();
 		}
 	} else if (access == ARCH_TIMER_VIRT_ACCESS) {
 		switch (reg) {
 		case ARCH_TIMER_REG_CTRL:
 			return read_sysreg(cntv_ctl_el0);
-		case ARCH_TIMER_REG_TVAL:
-			return arch_timer_reg_read_stable(cntv_tval_el0);
+		default:
+			BUILD_BUG();
 		}
 	}
 
-	BUG();
+	BUILD_BUG();
+	unreachable();
 }
 
 static inline u32 arch_timer_get_cntfrq(void)
@@ -169,7 +165,6 @@ static __always_inline u64 __arch_counter_get_cntpct_stable(void)
 {
 	u64 cnt;
 
-	isb();
 	cnt = arch_timer_reg_read_stable(cntpct_el0);
 	arch_counter_enforce_ordering(cnt);
 	return cnt;
@@ -189,7 +184,6 @@ static __always_inline u64 __arch_counter_get_cntvct_stable(void)
 {
 	u64 cnt;
 
-	isb();
 	cnt = arch_timer_reg_read_stable(cntvct_el0);
 	arch_counter_enforce_ordering(cnt);
 	return cnt;
diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index be6d741d404c..9a04eacc4412 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -44,23 +44,29 @@
 #define CNTACR_RWVT	BIT(4)
 #define CNTACR_RWPT	BIT(5)
 
-#define CNTVCT_LO	0x08
-#define CNTVCT_HI	0x0c
+#define CNTVCT_LO	0x00
+#define CNTPCT_LO	0x08
 #define CNTFRQ		0x10
-#define CNTP_TVAL	0x28
+#define CNTP_CVAL_LO	0x20
 #define CNTP_CTL	0x2c
-#define CNTV_TVAL	0x38
+#define CNTV_CVAL_LO	0x30
 #define CNTV_CTL	0x3c
 
-static unsigned arch_timers_present __initdata;
+/*
+ * The minimum amount of time a generic counter is guaranteed to not roll over
+ * (40 years)
+ */
+#define MIN_ROLLOVER_SECS	(40ULL * 365 * 24 * 3600)
 
-static void __iomem *arch_counter_base __ro_after_init;
+static unsigned arch_timers_present __initdata;
 
 struct arch_timer {
 	void __iomem *base;
 	struct clock_event_device evt;
 };
 
+static struct arch_timer *arch_timer_mem __ro_after_init;
+
 #define to_arch_timer(e) container_of(e, struct arch_timer, evt)
 
 static u32 arch_timer_rate __ro_after_init;
@@ -96,32 +102,57 @@ static int __init early_evtstrm_cfg(char *buf)
 early_param("clocksource.arm_arch_timer.evtstrm", early_evtstrm_cfg);
 
 /*
+ * Makes an educated guess at a valid counter width based on the Generic Timer
+ * specification. Of note:
+ *   1) the system counter is at least 56 bits wide
+ *   2) a roll-over time of not less than 40 years
+ *
+ * See 'ARM DDI 0487G.a D11.1.2 ("The system counter")' for more details.
+ */
+static int arch_counter_get_width(void)
+{
+	u64 min_cycles = MIN_ROLLOVER_SECS * arch_timer_rate;
+
+	/* guarantee the returned width is within the valid range */
+	return clamp_val(ilog2(min_cycles - 1) + 1, 56, 64);
+}
+
+/*
  * Architected system timer support.
  */
 
 static __always_inline
-void arch_timer_reg_write(int access, enum arch_timer_reg reg, u32 val,
+void arch_timer_reg_write(int access, enum arch_timer_reg reg, u64 val,
 			  struct clock_event_device *clk)
 {
 	if (access == ARCH_TIMER_MEM_PHYS_ACCESS) {
 		struct arch_timer *timer = to_arch_timer(clk);
 		switch (reg) {
 		case ARCH_TIMER_REG_CTRL:
-			writel_relaxed(val, timer->base + CNTP_CTL);
+			writel_relaxed((u32)val, timer->base + CNTP_CTL);
 			break;
-		case ARCH_TIMER_REG_TVAL:
-			writel_relaxed(val, timer->base + CNTP_TVAL);
+		case ARCH_TIMER_REG_CVAL:
+			/*
+			 * Not guaranteed to be atomic, so the timer
+			 * must be disabled at this point.
+			 */
+			writeq_relaxed(val, timer->base + CNTP_CVAL_LO);
 			break;
+		default:
+			BUILD_BUG();
 		}
 	} else if (access == ARCH_TIMER_MEM_VIRT_ACCESS) {
 		struct arch_timer *timer = to_arch_timer(clk);
 		switch (reg) {
 		case ARCH_TIMER_REG_CTRL:
-			writel_relaxed(val, timer->base + CNTV_CTL);
+			writel_relaxed((u32)val, timer->base + CNTV_CTL);
 			break;
-		case ARCH_TIMER_REG_TVAL:
-			writel_relaxed(val, timer->base + CNTV_TVAL);
+		case ARCH_TIMER_REG_CVAL:
+			/* Same restriction as above */
+			writeq_relaxed(val, timer->base + CNTV_CVAL_LO);
 			break;
+		default:
+			BUILD_BUG();
 		}
 	} else {
 		arch_timer_reg_write_cp15(access, reg, val);
@@ -140,9 +171,8 @@ u32 arch_timer_reg_read(int access, enum arch_timer_reg reg,
 		case ARCH_TIMER_REG_CTRL:
 			val = readl_relaxed(timer->base + CNTP_CTL);
 			break;
-		case ARCH_TIMER_REG_TVAL:
-			val = readl_relaxed(timer->base + CNTP_TVAL);
-			break;
+		default:
+			BUILD_BUG();
 		}
 	} else if (access == ARCH_TIMER_MEM_VIRT_ACCESS) {
 		struct arch_timer *timer = to_arch_timer(clk);
@@ -150,9 +180,8 @@ u32 arch_timer_reg_read(int access, enum arch_timer_reg reg,
 		case ARCH_TIMER_REG_CTRL:
 			val = readl_relaxed(timer->base + CNTV_CTL);
 			break;
-		case ARCH_TIMER_REG_TVAL:
-			val = readl_relaxed(timer->base + CNTV_TVAL);
-			break;
+		default:
+			BUILD_BUG();
 		}
 	} else {
 		val = arch_timer_reg_read_cp15(access, reg);
@@ -205,13 +234,11 @@ static struct clocksource clocksource_counter = {
 	.id	= CSID_ARM_ARCH_COUNTER,
 	.rating	= 400,
 	.read	= arch_counter_read,
-	.mask	= CLOCKSOURCE_MASK(56),
 	.flags	= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
 static struct cyclecounter cyclecounter __ro_after_init = {
 	.read	= arch_counter_read_cc,
-	.mask	= CLOCKSOURCE_MASK(56),
 };
 
 struct ate_acpi_oem_info {
@@ -239,16 +266,6 @@ struct ate_acpi_oem_info {
 	_new;						\
 })
 
-static u32 notrace fsl_a008585_read_cntp_tval_el0(void)
-{
-	return __fsl_a008585_read_reg(cntp_tval_el0);
-}
-
-static u32 notrace fsl_a008585_read_cntv_tval_el0(void)
-{
-	return __fsl_a008585_read_reg(cntv_tval_el0);
-}
-
 static u64 notrace fsl_a008585_read_cntpct_el0(void)
 {
 	return __fsl_a008585_read_reg(cntpct_el0);
@@ -285,16 +302,6 @@ static u64 notrace fsl_a008585_read_cntvct_el0(void)
 	_new;							\
 })
 
-static u32 notrace hisi_161010101_read_cntp_tval_el0(void)
-{
-	return __hisi_161010101_read_reg(cntp_tval_el0);
-}
-
-static u32 notrace hisi_161010101_read_cntv_tval_el0(void)
-{
-	return __hisi_161010101_read_reg(cntv_tval_el0);
-}
-
 static u64 notrace hisi_161010101_read_cntpct_el0(void)
 {
 	return __hisi_161010101_read_reg(cntpct_el0);
@@ -379,16 +386,6 @@ static u64 notrace sun50i_a64_read_cntvct_el0(void)
 {
 	return __sun50i_a64_read_reg(cntvct_el0);
 }
-
-static u32 notrace sun50i_a64_read_cntp_tval_el0(void)
-{
-	return read_sysreg(cntp_cval_el0) - sun50i_a64_read_cntpct_el0();
-}
-
-static u32 notrace sun50i_a64_read_cntv_tval_el0(void)
-{
-	return read_sysreg(cntv_cval_el0) - sun50i_a64_read_cntvct_el0();
-}
 #endif
 
 #ifdef CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND
@@ -397,7 +394,7 @@ EXPORT_SYMBOL_GPL(timer_unstable_counter_workaround);
 
 static atomic_t timer_unstable_counter_workaround_in_use = ATOMIC_INIT(0);
 
-static void erratum_set_next_event_tval_generic(const int access, unsigned long evt,
+static void erratum_set_next_event_generic(const int access, unsigned long evt,
 						struct clock_event_device *clk)
 {
 	unsigned long ctrl;
@@ -418,17 +415,17 @@ static void erratum_set_next_event_tval_generic(const int access, unsigned long
 	arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, clk);
 }
 
-static __maybe_unused int erratum_set_next_event_tval_virt(unsigned long evt,
+static __maybe_unused int erratum_set_next_event_virt(unsigned long evt,
 					    struct clock_event_device *clk)
 {
-	erratum_set_next_event_tval_generic(ARCH_TIMER_VIRT_ACCESS, evt, clk);
+	erratum_set_next_event_generic(ARCH_TIMER_VIRT_ACCESS, evt, clk);
 	return 0;
 }
 
-static __maybe_unused int erratum_set_next_event_tval_phys(unsigned long evt,
+static __maybe_unused int erratum_set_next_event_phys(unsigned long evt,
 					    struct clock_event_device *clk)
 {
-	erratum_set_next_event_tval_generic(ARCH_TIMER_PHYS_ACCESS, evt, clk);
+	erratum_set_next_event_generic(ARCH_TIMER_PHYS_ACCESS, evt, clk);
 	return 0;
 }
 
@@ -438,12 +435,10 @@ static const struct arch_timer_erratum_workaround ool_workarounds[] = {
 		.match_type = ate_match_dt,
 		.id = "fsl,erratum-a008585",
 		.desc = "Freescale erratum a005858",
-		.read_cntp_tval_el0 = fsl_a008585_read_cntp_tval_el0,
-		.read_cntv_tval_el0 = fsl_a008585_read_cntv_tval_el0,
 		.read_cntpct_el0 = fsl_a008585_read_cntpct_el0,
 		.read_cntvct_el0 = fsl_a008585_read_cntvct_el0,
-		.set_next_event_phys = erratum_set_next_event_tval_phys,
-		.set_next_event_virt = erratum_set_next_event_tval_virt,
+		.set_next_event_phys = erratum_set_next_event_phys,
+		.set_next_event_virt = erratum_set_next_event_virt,
 	},
 #endif
 #ifdef CONFIG_HISILICON_ERRATUM_161010101
@@ -451,23 +446,19 @@ static const struct arch_timer_erratum_workaround ool_workarounds[] = {
 		.match_type = ate_match_dt,
 		.id = "hisilicon,erratum-161010101",
 		.desc = "HiSilicon erratum 161010101",
-		.read_cntp_tval_el0 = hisi_161010101_read_cntp_tval_el0,
-		.read_cntv_tval_el0 = hisi_161010101_read_cntv_tval_el0,
 		.read_cntpct_el0 = hisi_161010101_read_cntpct_el0,
 		.read_cntvct_el0 = hisi_161010101_read_cntvct_el0,
-		.set_next_event_phys = erratum_set_next_event_tval_phys,
-		.set_next_event_virt = erratum_set_next_event_tval_virt,
+		.set_next_event_phys = erratum_set_next_event_phys,
+		.set_next_event_virt = erratum_set_next_event_virt,
 	},
 	{
 		.match_type = ate_match_acpi_oem_info,
 		.id = hisi_161010101_oem_info,
 		.desc = "HiSilicon erratum 161010101",
-		.read_cntp_tval_el0 = hisi_161010101_read_cntp_tval_el0,
-		.read_cntv_tval_el0 = hisi_161010101_read_cntv_tval_el0,
 		.read_cntpct_el0 = hisi_161010101_read_cntpct_el0,
 		.read_cntvct_el0 = hisi_161010101_read_cntvct_el0,
-		.set_next_event_phys = erratum_set_next_event_tval_phys,
-		.set_next_event_virt = erratum_set_next_event_tval_virt,
+		.set_next_event_phys = erratum_set_next_event_phys,
+		.set_next_event_virt = erratum_set_next_event_virt,
 	},
 #endif
 #ifdef CONFIG_ARM64_ERRATUM_858921
@@ -484,12 +475,10 @@ static const struct arch_timer_erratum_workaround ool_workarounds[] = {
 		.match_type = ate_match_dt,
 		.id = "allwinner,erratum-unknown1",
 		.desc = "Allwinner erratum UNKNOWN1",
-		.read_cntp_tval_el0 = sun50i_a64_read_cntp_tval_el0,
-		.read_cntv_tval_el0 = sun50i_a64_read_cntv_tval_el0,
 		.read_cntpct_el0 = sun50i_a64_read_cntpct_el0,
 		.read_cntvct_el0 = sun50i_a64_read_cntvct_el0,
-		.set_next_event_phys = erratum_set_next_event_tval_phys,
-		.set_next_event_virt = erratum_set_next_event_tval_virt,
+		.set_next_event_phys = erratum_set_next_event_phys,
+		.set_next_event_virt = erratum_set_next_event_virt,
 	},
 #endif
 #ifdef CONFIG_ARM64_ERRATUM_1418040
@@ -727,10 +716,18 @@ static __always_inline void set_next_event(const int access, unsigned long evt,
 					   struct clock_event_device *clk)
 {
 	unsigned long ctrl;
+	u64 cnt;
+
 	ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL, clk);
 	ctrl |= ARCH_TIMER_CTRL_ENABLE;
 	ctrl &= ~ARCH_TIMER_CTRL_IT_MASK;
-	arch_timer_reg_write(access, ARCH_TIMER_REG_TVAL, evt, clk);
+
+	if (access == ARCH_TIMER_PHYS_ACCESS)
+		cnt = __arch_counter_get_cntpct();
+	else
+		cnt = __arch_counter_get_cntvct();
+
+	arch_timer_reg_write(access, ARCH_TIMER_REG_CVAL, evt + cnt, clk);
 	arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, clk);
 }
 
@@ -748,23 +745,79 @@ static int arch_timer_set_next_event_phys(unsigned long evt,
 	return 0;
 }
 
+static u64 arch_counter_get_cnt_mem(struct arch_timer *t, int offset_lo)
+{
+	u32 cnt_lo, cnt_hi, tmp_hi;
+
+	do {
+		cnt_hi = readl_relaxed(t->base + offset_lo + 4);
+		cnt_lo = readl_relaxed(t->base + offset_lo);
+		tmp_hi = readl_relaxed(t->base + offset_lo + 4);
+	} while (cnt_hi != tmp_hi);
+
+	return ((u64) cnt_hi << 32) | cnt_lo;
+}
+
+static __always_inline void set_next_event_mem(const int access, unsigned long evt,
+					   struct clock_event_device *clk)
+{
+	struct arch_timer *timer = to_arch_timer(clk);
+	unsigned long ctrl;
+	u64 cnt;
+
+	ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL, clk);
+	ctrl |= ARCH_TIMER_CTRL_ENABLE;
+	ctrl &= ~ARCH_TIMER_CTRL_IT_MASK;
+
+	if (access ==  ARCH_TIMER_MEM_VIRT_ACCESS)
+		cnt = arch_counter_get_cnt_mem(timer, CNTVCT_LO);
+	else
+		cnt = arch_counter_get_cnt_mem(timer, CNTPCT_LO);
+
+	arch_timer_reg_write(access, ARCH_TIMER_REG_CVAL, evt + cnt, clk);
+	arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, clk);
+}
+
 static int arch_timer_set_next_event_virt_mem(unsigned long evt,
 					      struct clock_event_device *clk)
 {
-	set_next_event(ARCH_TIMER_MEM_VIRT_ACCESS, evt, clk);
+	set_next_event_mem(ARCH_TIMER_MEM_VIRT_ACCESS, evt, clk);
 	return 0;
 }
 
 static int arch_timer_set_next_event_phys_mem(unsigned long evt,
 					      struct clock_event_device *clk)
 {
-	set_next_event(ARCH_TIMER_MEM_PHYS_ACCESS, evt, clk);
+	set_next_event_mem(ARCH_TIMER_MEM_PHYS_ACCESS, evt, clk);
 	return 0;
 }
 
+static u64 __arch_timer_check_delta(void)
+{
+#ifdef CONFIG_ARM64
+	const struct midr_range broken_cval_midrs[] = {
+		/*
+		 * XGene-1 implements CVAL in terms of TVAL, meaning
+		 * that the maximum timer range is 32bit. Shame on them.
+		 */
+		MIDR_ALL_VERSIONS(MIDR_CPU_MODEL(ARM_CPU_IMP_APM,
+						 APM_CPU_PART_POTENZA)),
+		{},
+	};
+
+	if (is_midr_in_range_list(read_cpuid_id(), broken_cval_midrs)) {
+		pr_warn_once("Broken CNTx_CVAL_EL1, limiting width to 32bits");
+		return CLOCKSOURCE_MASK(32);
+	}
+#endif
+	return CLOCKSOURCE_MASK(arch_counter_get_width());
+}
+
 static void __arch_timer_setup(unsigned type,
 			       struct clock_event_device *clk)
 {
+	u64 max_delta;
+
 	clk->features = CLOCK_EVT_FEAT_ONESHOT;
 
 	if (type == ARCH_TIMER_TYPE_CP15) {
@@ -796,6 +849,7 @@ static void __arch_timer_setup(unsigned type,
 		}
 
 		clk->set_next_event = sne;
+		max_delta = __arch_timer_check_delta();
 	} else {
 		clk->features |= CLOCK_EVT_FEAT_DYNIRQ;
 		clk->name = "arch_mem_timer";
@@ -812,11 +866,13 @@ static void __arch_timer_setup(unsigned type,
 			clk->set_next_event =
 				arch_timer_set_next_event_phys_mem;
 		}
+
+		max_delta = CLOCKSOURCE_MASK(56);
 	}
 
 	clk->set_state_shutdown(clk);
 
-	clockevents_config_and_register(clk, arch_timer_rate, 0xf, 0x7fffffff);
+	clockevents_config_and_register(clk, arch_timer_rate, 0xf, max_delta);
 }
 
 static void arch_timer_evtstrm_enable(int divider)
@@ -986,15 +1042,7 @@ bool arch_timer_evtstrm_available(void)
 
 static u64 arch_counter_get_cntvct_mem(void)
 {
-	u32 vct_lo, vct_hi, tmp_hi;
-
-	do {
-		vct_hi = readl_relaxed(arch_counter_base + CNTVCT_HI);
-		vct_lo = readl_relaxed(arch_counter_base + CNTVCT_LO);
-		tmp_hi = readl_relaxed(arch_counter_base + CNTVCT_HI);
-	} while (vct_hi != tmp_hi);
-
-	return ((u64) vct_hi << 32) | vct_lo;
+	return arch_counter_get_cnt_mem(arch_timer_mem, CNTVCT_LO);
 }
 
 static struct arch_timer_kvm_info arch_timer_kvm_info;
@@ -1007,6 +1055,7 @@ struct arch_timer_kvm_info *arch_timer_get_kvm_info(void)
 static void __init arch_counter_register(unsigned type)
 {
 	u64 start_count;
+	int width;
 
 	/* Register the CP15 based counter if we have one */
 	if (type & ARCH_TIMER_TYPE_CP15) {
@@ -1031,6 +1080,10 @@ static void __init arch_counter_register(unsigned type)
 		arch_timer_read_counter = arch_counter_get_cntvct_mem;
 	}
 
+	width = arch_counter_get_width();
+	clocksource_counter.mask = CLOCKSOURCE_MASK(width);
+	cyclecounter.mask = CLOCKSOURCE_MASK(width);
+
 	if (!arch_counter_suspend_stop)
 		clocksource_counter.flags |= CLOCK_SOURCE_SUSPEND_NONSTOP;
 	start_count = arch_timer_read_counter();
@@ -1040,8 +1093,7 @@ static void __init arch_counter_register(unsigned type)
 	timecounter_init(&arch_timer_kvm_info.timecounter,
 			 &cyclecounter, start_count);
 
-	/* 56 bits minimum, so we assume worst case rollover */
-	sched_clock_register(arch_timer_read_counter, 56, arch_timer_rate);
+	sched_clock_register(arch_timer_read_counter, width, arch_timer_rate);
 }
 
 static void arch_timer_stop(struct clock_event_device *clk)
@@ -1182,25 +1234,25 @@ static int __init arch_timer_mem_register(void __iomem *base, unsigned int irq)
 {
 	int ret;
 	irq_handler_t func;
-	struct arch_timer *t;
 
-	t = kzalloc(sizeof(*t), GFP_KERNEL);
-	if (!t)
+	arch_timer_mem = kzalloc(sizeof(*arch_timer_mem), GFP_KERNEL);
+	if (!arch_timer_mem)
 		return -ENOMEM;
 
-	t->base = base;
-	t->evt.irq = irq;
-	__arch_timer_setup(ARCH_TIMER_TYPE_MEM, &t->evt);
+	arch_timer_mem->base = base;
+	arch_timer_mem->evt.irq = irq;
+	__arch_timer_setup(ARCH_TIMER_TYPE_MEM, &arch_timer_mem->evt);
 
 	if (arch_timer_mem_use_virtual)
 		func = arch_timer_handler_virt_mem;
 	else
 		func = arch_timer_handler_phys_mem;
 
-	ret = request_irq(irq, func, IRQF_TIMER, "arch_mem_timer", &t->evt);
+	ret = request_irq(irq, func, IRQF_TIMER, "arch_mem_timer", &arch_timer_mem->evt);
 	if (ret) {
 		pr_err("Failed to request mem timer irq\n");
-		kfree(t);
+		kfree(arch_timer_mem);
+		arch_timer_mem = NULL;
 	}
 
 	return ret;
@@ -1458,7 +1510,6 @@ arch_timer_mem_frame_register(struct arch_timer_mem_frame *frame)
 		return ret;
 	}
 
-	arch_counter_base = base;
 	arch_timers_present |= ARCH_TIMER_TYPE_MEM;
 
 	return 0;
diff --git a/include/clocksource/arm_arch_timer.h b/include/clocksource/arm_arch_timer.h
index 73c7139c866f..e715bdb720d5 100644
--- a/include/clocksource/arm_arch_timer.h
+++ b/include/clocksource/arm_arch_timer.h
@@ -24,7 +24,7 @@
 
 enum arch_timer_reg {
 	ARCH_TIMER_REG_CTRL,
-	ARCH_TIMER_REG_TVAL,
+	ARCH_TIMER_REG_CVAL,
 };
 
 enum arch_timer_ppi_nr {