Merge tag 'timers-v5.13-rc1' of https://git.linaro.org/people/daniel.lezcano/linux into timers/core

Pull clocksource/event updates from Daniel Lezcano:

 - Add dt bindings for the wpcm450 and the timer declaration (Jonathan
   Neuschäfer)

 - Add dt bindings for the JZ4760, the timer declaration for the
   ingenic ost and timer (Paul Cercueil)

 - Add dt bindings for the cmt r8a779a0 (Wolfram Sang)

 - Add dt bindings for the cmt r8a77961 (Niklas Söderlund)

 - Add missing dt bindings for the tmu r8a7795, r8a7796, r8a77961, r8a77965,
   r8a77990 and r8a77995 (Niklas Söderlund)

 - Check pending post before writing a new post in register for the
   timer TI dm and add the stopped callback ops to prevent any
   spurious interrupt (Tony Lindgren)

 - Fix return value check at init when calling device_node_to_regmap()
   for the Ingenic OST timer (Wei Yongjun)

 - Fix a trivial typo s/overflw/overflow/ for the pistachio timer (Drew Fustini)

 - Don't use CMTOUT_IE with R-Car Gen2/3 (Wolfram Sang)

 - Fix rollback when the initialization fails on the dw_apb timer (Dinh Nguyen)

 - Switch to timer TI dm on dra7 in order to prevent using the bogus
   architected timer which fails to wrap correctly after 388 days (Tony Lindgren)

 - Add function annotation to optimize memory for the ARM architected
   timer (Jisheng Zhang)

15 files changed, 229 insertions, 64 deletions

diff --git a/Documentation/devicetree/bindings/timer/ingenic,tcu.yaml b/Documentation/devicetree/bindings/timer/ingenic,tcu.yaml
index 024bcad75101..8165df4599cf 100644
--- a/Documentation/devicetree/bindings/timer/ingenic,tcu.yaml
+++ b/Documentation/devicetree/bindings/timer/ingenic,tcu.yaml
@@ -20,6 +20,8 @@ select:
         enum:
           - ingenic,jz4740-tcu
           - ingenic,jz4725b-tcu
+          - ingenic,jz4760-tcu
+          - ingenic,jz4760b-tcu
           - ingenic,jz4770-tcu
           - ingenic,jz4780-tcu
           - ingenic,x1000-tcu
@@ -52,12 +54,15 @@ properties:
           - enum:
               - ingenic,jz4740-tcu
               - ingenic,jz4725b-tcu
-              - ingenic,jz4770-tcu
+              - ingenic,jz4760-tcu
               - ingenic,x1000-tcu
           - const: simple-mfd
       - items:
-          - const: ingenic,jz4780-tcu
-          - const: ingenic,jz4770-tcu
+          - enum:
+              - ingenic,jz4780-tcu
+              - ingenic,jz4770-tcu
+              - ingenic,jz4760b-tcu
+          - const: ingenic,jz4760-tcu
           - const: simple-mfd
 
   reg:
@@ -118,6 +123,8 @@ patternProperties:
           - items:
               - enum:
                   - ingenic,jz4770-watchdog
+                  - ingenic,jz4760b-watchdog
+                  - ingenic,jz4760-watchdog
                   - ingenic,jz4725b-watchdog
               - const: ingenic,jz4740-watchdog
 
@@ -147,6 +154,8 @@ patternProperties:
               - ingenic,jz4725b-pwm
           - items:
               - enum:
+                  - ingenic,jz4760-pwm
+                  - ingenic,jz4760b-pwm
                   - ingenic,jz4770-pwm
                   - ingenic,jz4780-pwm
               - const: ingenic,jz4740-pwm
@@ -183,10 +192,15 @@ patternProperties:
         oneOf:
           - enum:
               - ingenic,jz4725b-ost
-              - ingenic,jz4770-ost
+              - ingenic,jz4760b-ost
           - items:
-              - const: ingenic,jz4780-ost
-              - const: ingenic,jz4770-ost
+              - const: ingenic,jz4760-ost
+              - const: ingenic,jz4725b-ost
+          - items:
+              - enum:
+                  - ingenic,jz4780-ost
+                  - ingenic,jz4770-ost
+              - const: ingenic,jz4760b-ost
 
       reg:
         maxItems: 1
@@ -226,7 +240,7 @@ examples:
     #include <dt-bindings/clock/jz4770-cgu.h>
     #include <dt-bindings/clock/ingenic,tcu.h>
     tcu: timer@10002000 {
-      compatible = "ingenic,jz4770-tcu", "simple-mfd";
+      compatible = "ingenic,jz4770-tcu", "ingenic,jz4760-tcu", "simple-mfd";
       reg = <0x10002000 0x1000>;
       #address-cells = <1>;
       #size-cells = <1>;
@@ -272,7 +286,7 @@ examples:
       };
 
       ost: timer@e0 {
-        compatible = "ingenic,jz4770-ost";
+        compatible = "ingenic,jz4770-ost", "ingenic,jz4760b-ost";
         reg = <0xe0 0x20>;
 
         clocks = <&tcu TCU_CLK_OST>;
diff --git a/Documentation/devicetree/bindings/timer/nuvoton,npcm7xx-timer.txt b/Documentation/devicetree/bindings/timer/nuvoton,npcm7xx-timer.txt
index 97258f1a1505..ac3a5e887455 100644
--- a/Documentation/devicetree/bindings/timer/nuvoton,npcm7xx-timer.txt
+++ b/Documentation/devicetree/bindings/timer/nuvoton,npcm7xx-timer.txt
@@ -4,7 +4,8 @@ Nuvoton NPCM7xx have three timer modules, each timer module provides five 24-bit
 timer counters.
 
 Required properties:
-- compatible      : "nuvoton,npcm750-timer" for Poleg NPCM750.
+- compatible      : "nuvoton,npcm750-timer" for Poleg NPCM750, or
+                    "nuvoton,wpcm450-timer" for Hermon WPCM450.
 - reg             : Offset and length of the register set for the device.
 - interrupts      : Contain the timer interrupt of timer 0.
 - clocks          : phandle of timer reference clock (usually a 25 MHz clock).
diff --git a/Documentation/devicetree/bindings/timer/renesas,cmt.yaml b/Documentation/devicetree/bindings/timer/renesas,cmt.yaml
index 428db3a21bb9..53dd6d9f518f 100644
--- a/Documentation/devicetree/bindings/timer/renesas,cmt.yaml
+++ b/Documentation/devicetree/bindings/timer/renesas,cmt.yaml
@@ -74,11 +74,13 @@ properties:
               - renesas,r8a774e1-cmt0     # 32-bit CMT0 on RZ/G2H
               - renesas,r8a7795-cmt0      # 32-bit CMT0 on R-Car H3
               - renesas,r8a7796-cmt0      # 32-bit CMT0 on R-Car M3-W
+              - renesas,r8a77961-cmt0     # 32-bit CMT0 on R-Car M3-W+
               - renesas,r8a77965-cmt0     # 32-bit CMT0 on R-Car M3-N
               - renesas,r8a77970-cmt0     # 32-bit CMT0 on R-Car V3M
               - renesas,r8a77980-cmt0     # 32-bit CMT0 on R-Car V3H
               - renesas,r8a77990-cmt0     # 32-bit CMT0 on R-Car E3
               - renesas,r8a77995-cmt0     # 32-bit CMT0 on R-Car D3
+              - renesas,r8a779a0-cmt0     # 32-bit CMT0 on R-Car V3U
           - const: renesas,rcar-gen3-cmt0 # 32-bit CMT0 on R-Car Gen3 and RZ/G2
 
       - items:
@@ -89,11 +91,13 @@ properties:
               - renesas,r8a774e1-cmt1     # 48-bit CMT on RZ/G2H
               - renesas,r8a7795-cmt1      # 48-bit CMT on R-Car H3
               - renesas,r8a7796-cmt1      # 48-bit CMT on R-Car M3-W
+              - renesas,r8a77961-cmt1     # 48-bit CMT on R-Car M3-W+
               - renesas,r8a77965-cmt1     # 48-bit CMT on R-Car M3-N
               - renesas,r8a77970-cmt1     # 48-bit CMT on R-Car V3M
               - renesas,r8a77980-cmt1     # 48-bit CMT on R-Car V3H
               - renesas,r8a77990-cmt1     # 48-bit CMT on R-Car E3
               - renesas,r8a77995-cmt1     # 48-bit CMT on R-Car D3
+              - renesas,r8a779a0-cmt1     # 48-bit CMT on R-Car V3U
           - const: renesas,rcar-gen3-cmt1 # 48-bit CMT on R-Car Gen3 and RZ/G2
 
   reg:
diff --git a/Documentation/devicetree/bindings/timer/renesas,tmu.yaml b/Documentation/devicetree/bindings/timer/renesas,tmu.yaml
index c54188731a1b..f0f0f121c355 100644
--- a/Documentation/devicetree/bindings/timer/renesas,tmu.yaml
+++ b/Documentation/devicetree/bindings/timer/renesas,tmu.yaml
@@ -28,8 +28,14 @@ properties:
           - renesas,tmu-r8a774e1 # RZ/G2H
           - renesas,tmu-r8a7778  # R-Car M1A
           - renesas,tmu-r8a7779  # R-Car H1
+          - renesas,tmu-r8a7795  # R-Car H3
+          - renesas,tmu-r8a7796  # R-Car M3-W
+          - renesas,tmu-r8a77961 # R-Car M3-W+
+          - renesas,tmu-r8a77965 # R-Car M3-N
           - renesas,tmu-r8a77970 # R-Car V3M
           - renesas,tmu-r8a77980 # R-Car V3H
+          - renesas,tmu-r8a77990 # R-Car E3
+          - renesas,tmu-r8a77995 # R-Car D3
       - const: renesas,tmu
 
   reg:
diff --git a/arch/arm/boot/dts/dra7-l4.dtsi b/arch/arm/boot/dts/dra7-l4.dtsi
index 3bf90d9e3335..a294a02f2d23 100644
--- a/arch/arm/boot/dts/dra7-l4.dtsi
+++ b/arch/arm/boot/dts/dra7-l4.dtsi
@@ -1168,7 +1168,7 @@
 			};
 		};
 
-		target-module@34000 {			/* 0x48034000, ap 7 46.0 */
+		timer3_target: target-module@34000 {	/* 0x48034000, ap 7 46.0 */
 			compatible = "ti,sysc-omap4-timer", "ti,sysc";
 			reg = <0x34000 0x4>,
 			      <0x34010 0x4>;
@@ -1195,7 +1195,7 @@
 			};
 		};
 
-		target-module@36000 {			/* 0x48036000, ap 9 4e.0 */
+		timer4_target: target-module@36000 {	/* 0x48036000, ap 9 4e.0 */
 			compatible = "ti,sysc-omap4-timer", "ti,sysc";
 			reg = <0x36000 0x4>,
 			      <0x36010 0x4>;
diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
index ce1194744f84..53d68786a61f 100644
--- a/arch/arm/boot/dts/dra7.dtsi
+++ b/arch/arm/boot/dts/dra7.dtsi
@@ -46,6 +46,7 @@
 
 	timer {
 		compatible = "arm,armv7-timer";
+		status = "disabled";	/* See ARM architected timer wrap erratum i940 */
 		interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>,
 			     <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>,
 			     <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>,
@@ -1241,3 +1242,22 @@
 		assigned-clock-parents = <&sys_32k_ck>;
 	};
 };
+
+/* Local timers, see ARM architected timer wrap erratum i940 */
+&timer3_target {
+	ti,no-reset-on-init;
+	ti,no-idle;
+	timer@0 {
+		assigned-clocks = <&l4per_clkctrl DRA7_L4PER_TIMER3_CLKCTRL 24>;
+		assigned-clock-parents = <&timer_sys_clk_div>;
+	};
+};
+
+&timer4_target {
+	ti,no-reset-on-init;
+	ti,no-idle;
+	timer@0 {
+		assigned-clocks = <&l4per_clkctrl DRA7_L4PER_TIMER4_CLKCTRL 24>;
+		assigned-clock-parents = <&timer_sys_clk_div>;
+	};
+};
diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index d0177824c518..1b885964fb34 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -51,7 +51,7 @@
 
 static unsigned arch_timers_present __initdata;
 
-static void __iomem *arch_counter_base;
+static void __iomem *arch_counter_base __ro_after_init;
 
 struct arch_timer {
 	void __iomem *base;
@@ -60,15 +60,16 @@ struct arch_timer {
 
 #define to_arch_timer(e) container_of(e, struct arch_timer, evt)
 
-static u32 arch_timer_rate;
-static int arch_timer_ppi[ARCH_TIMER_MAX_TIMER_PPI];
+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 struct clock_event_device __percpu *arch_timer_evt;
 
-static enum arch_timer_ppi_nr arch_timer_uses_ppi = ARCH_TIMER_VIRT_PPI;
-static bool arch_timer_c3stop;
-static bool arch_timer_mem_use_virtual;
-static bool arch_counter_suspend_stop;
+static enum arch_timer_ppi_nr arch_timer_uses_ppi __ro_after_init = ARCH_TIMER_VIRT_PPI;
+static bool arch_timer_c3stop __ro_after_init;
+static bool arch_timer_mem_use_virtual __ro_after_init;
+static bool arch_counter_suspend_stop __ro_after_init;
 #ifdef CONFIG_GENERIC_GETTIMEOFDAY
 static enum vdso_clock_mode vdso_default = VDSO_CLOCKMODE_ARCHTIMER;
 #else
@@ -76,7 +77,7 @@ static enum vdso_clock_mode vdso_default = VDSO_CLOCKMODE_NONE;
 #endif /* CONFIG_GENERIC_GETTIMEOFDAY */
 
 static cpumask_t evtstrm_available = CPU_MASK_NONE;
-static bool evtstrm_enable = IS_ENABLED(CONFIG_ARM_ARCH_TIMER_EVTSTREAM);
+static bool evtstrm_enable __ro_after_init = IS_ENABLED(CONFIG_ARM_ARCH_TIMER_EVTSTREAM);
 
 static int __init early_evtstrm_cfg(char *buf)
 {
@@ -176,7 +177,7 @@ static notrace u64 arch_counter_get_cntvct(void)
  * to exist on arm64. arm doesn't use this before DT is probed so even
  * if we don't have the cp15 accessors we won't have a problem.
  */
-u64 (*arch_timer_read_counter)(void) = arch_counter_get_cntvct;
+u64 (*arch_timer_read_counter)(void) __ro_after_init = arch_counter_get_cntvct;
 EXPORT_SYMBOL_GPL(arch_timer_read_counter);
 
 static u64 arch_counter_read(struct clocksource *cs)
@@ -925,7 +926,7 @@ static int validate_timer_rate(void)
  * rate was probed first, and don't verify that others match. If the first node
  * probed has a clock-frequency property, this overrides the HW register.
  */
-static void arch_timer_of_configure_rate(u32 rate, struct device_node *np)
+static void __init arch_timer_of_configure_rate(u32 rate, struct device_node *np)
 {
 	/* Who has more than one independent system counter? */
 	if (arch_timer_rate)
@@ -939,7 +940,7 @@ static void arch_timer_of_configure_rate(u32 rate, struct device_node *np)
 		pr_warn("frequency not available\n");
 }
 
-static void arch_timer_banner(unsigned type)
+static void __init arch_timer_banner(unsigned type)
 {
 	pr_info("%s%s%s timer(s) running at %lu.%02luMHz (%s%s%s).\n",
 		type & ARCH_TIMER_TYPE_CP15 ? "cp15" : "",
diff --git a/drivers/clocksource/dw_apb_timer_of.c b/drivers/clocksource/dw_apb_timer_of.c
index 2b2c3b586987..3819ef5b7098 100644
--- a/drivers/clocksource/dw_apb_timer_of.c
+++ b/drivers/clocksource/dw_apb_timer_of.c
@@ -52,18 +52,34 @@ static int __init timer_get_base_and_rate(struct device_node *np,
 		return 0;
 
 	timer_clk = of_clk_get_by_name(np, "timer");
-	if (IS_ERR(timer_clk))
-		return PTR_ERR(timer_clk);
+	if (IS_ERR(timer_clk)) {
+		ret = PTR_ERR(timer_clk);
+		goto out_pclk_disable;
+	}
 
 	ret = clk_prepare_enable(timer_clk);
 	if (ret)
-		return ret;
+		goto out_timer_clk_put;
 
 	*rate = clk_get_rate(timer_clk);
-	if (!(*rate))
-		return -EINVAL;
+	if (!(*rate)) {
+		ret = -EINVAL;
+		goto out_timer_clk_disable;
+	}
 
 	return 0;
+
+out_timer_clk_disable:
+	clk_disable_unprepare(timer_clk);
+out_timer_clk_put:
+	clk_put(timer_clk);
+out_pclk_disable:
+	if (!IS_ERR(pclk)) {
+		clk_disable_unprepare(pclk);
+		clk_put(pclk);
+	}
+	iounmap(*base);
+	return ret;
 }
 
 static int __init add_clockevent(struct device_node *event_timer)
diff --git a/drivers/clocksource/ingenic-ost.c b/drivers/clocksource/ingenic-ost.c
index 029efc2731b4..06d25754e606 100644
--- a/drivers/clocksource/ingenic-ost.c
+++ b/drivers/clocksource/ingenic-ost.c
@@ -88,9 +88,9 @@ static int __init ingenic_ost_probe(struct platform_device *pdev)
 		return PTR_ERR(ost->regs);
 
 	map = device_node_to_regmap(dev->parent->of_node);
-	if (!map) {
+	if (IS_ERR(map)) {
 		dev_err(dev, "regmap not found");
-		return -EINVAL;
+		return PTR_ERR(map);
 	}
 
 	ost->clk = devm_clk_get(dev, "ost");
@@ -167,13 +167,14 @@ static const struct ingenic_ost_soc_info jz4725b_ost_soc_info = {
 	.is64bit = false,
 };
 
-static const struct ingenic_ost_soc_info jz4770_ost_soc_info = {
+static const struct ingenic_ost_soc_info jz4760b_ost_soc_info = {
 	.is64bit = true,
 };
 
 static const struct of_device_id ingenic_ost_of_match[] = {
 	{ .compatible = "ingenic,jz4725b-ost", .data = &jz4725b_ost_soc_info, },
-	{ .compatible = "ingenic,jz4770-ost", .data = &jz4770_ost_soc_info, },
+	{ .compatible = "ingenic,jz4760b-ost", .data = &jz4760b_ost_soc_info, },
+	{ .compatible = "ingenic,jz4770-ost", .data = &jz4760b_ost_soc_info, },
 	{ }
 };
 
diff --git a/drivers/clocksource/ingenic-timer.c b/drivers/clocksource/ingenic-timer.c
index 905fd6b163a8..24ed0f1f089b 100644
--- a/drivers/clocksource/ingenic-timer.c
+++ b/drivers/clocksource/ingenic-timer.c
@@ -264,6 +264,7 @@ static const struct ingenic_soc_info jz4725b_soc_info = {
 static const struct of_device_id ingenic_tcu_of_match[] = {
 	{ .compatible = "ingenic,jz4740-tcu", .data = &jz4740_soc_info, },
 	{ .compatible = "ingenic,jz4725b-tcu", .data = &jz4725b_soc_info, },
+	{ .compatible = "ingenic,jz4760-tcu", .data = &jz4740_soc_info, },
 	{ .compatible = "ingenic,jz4770-tcu", .data = &jz4740_soc_info, },
 	{ .compatible = "ingenic,x1000-tcu", .data = &jz4740_soc_info, },
 	{ /* sentinel */ }
@@ -358,6 +359,7 @@ err_free_ingenic_tcu:
 
 TIMER_OF_DECLARE(jz4740_tcu_intc,  "ingenic,jz4740-tcu",  ingenic_tcu_init);
 TIMER_OF_DECLARE(jz4725b_tcu_intc, "ingenic,jz4725b-tcu", ingenic_tcu_init);
+TIMER_OF_DECLARE(jz4760_tcu_intc,  "ingenic,jz4760-tcu",  ingenic_tcu_init);
 TIMER_OF_DECLARE(jz4770_tcu_intc,  "ingenic,jz4770-tcu",  ingenic_tcu_init);
 TIMER_OF_DECLARE(x1000_tcu_intc,  "ingenic,x1000-tcu",  ingenic_tcu_init);
 
diff --git a/drivers/clocksource/sh_cmt.c b/drivers/clocksource/sh_cmt.c
index c98f8851fd68..d7ed99f0001f 100644
--- a/drivers/clocksource/sh_cmt.c
+++ b/drivers/clocksource/sh_cmt.c
@@ -339,8 +339,9 @@ static int sh_cmt_enable(struct sh_cmt_channel *ch)
 		sh_cmt_write_cmcsr(ch, SH_CMT16_CMCSR_CMIE |
 				   SH_CMT16_CMCSR_CKS512);
 	} else {
-		sh_cmt_write_cmcsr(ch, SH_CMT32_CMCSR_CMM |
-				   SH_CMT32_CMCSR_CMTOUT_IE |
+		u32 cmtout = ch->cmt->info->model <= SH_CMT_48BIT ?
+			      SH_CMT32_CMCSR_CMTOUT_IE : 0;
+		sh_cmt_write_cmcsr(ch, cmtout | SH_CMT32_CMCSR_CMM |
 				   SH_CMT32_CMCSR_CMR_IRQ |
 				   SH_CMT32_CMCSR_CKS_RCLK8);
 	}
diff --git a/drivers/clocksource/timer-npcm7xx.c b/drivers/clocksource/timer-npcm7xx.c
index 9780ffd8010e..a00520cbb660 100644
--- a/drivers/clocksource/timer-npcm7xx.c
+++ b/drivers/clocksource/timer-npcm7xx.c
@@ -208,5 +208,6 @@ static int __init npcm7xx_timer_init(struct device_node *np)
 	return 0;
 }
 
+TIMER_OF_DECLARE(wpcm450, "nuvoton,wpcm450-timer", npcm7xx_timer_init);
 TIMER_OF_DECLARE(npcm7xx, "nuvoton,npcm750-timer", npcm7xx_timer_init);
 
diff --git a/drivers/clocksource/timer-pistachio.c b/drivers/clocksource/timer-pistachio.c
index a2dd85d0c1d7..6f37181a8c63 100644
--- a/drivers/clocksource/timer-pistachio.c
+++ b/drivers/clocksource/timer-pistachio.c
@@ -71,7 +71,7 @@ static u64 notrace
 pistachio_clocksource_read_cycles(struct clocksource *cs)
 {
 	struct pistachio_clocksource *pcs = to_pistachio_clocksource(cs);
-	u32 counter, overflw;
+	u32 counter, overflow;
 	unsigned long flags;
 
 	/*
@@ -80,7 +80,7 @@ pistachio_clocksource_read_cycles(struct clocksource *cs)
 	 */
 
 	raw_spin_lock_irqsave(&pcs->lock, flags);
-	overflw = gpt_readl(pcs->base, TIMER_CURRENT_OVERFLOW_VALUE, 0);
+	overflow = gpt_readl(pcs->base, TIMER_CURRENT_OVERFLOW_VALUE, 0);
 	counter = gpt_readl(pcs->base, TIMER_CURRENT_VALUE, 0);
 	raw_spin_unlock_irqrestore(&pcs->lock, flags);
 
diff --git a/drivers/clocksource/timer-ti-dm-systimer.c b/drivers/clocksource/timer-ti-dm-systimer.c
index 614c8380f3e9..b6f97960d8ee 100644
--- a/drivers/clocksource/timer-ti-dm-systimer.c
+++ b/drivers/clocksource/timer-ti-dm-systimer.c
@@ -2,6 +2,7 @@
 #include <linux/clk.h>
 #include <linux/clocksource.h>
 #include <linux/clockchips.h>
+#include <linux/cpuhotplug.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/iopoll.h>
@@ -449,13 +450,13 @@ static int dmtimer_set_next_event(unsigned long cycles,
 	struct dmtimer_systimer *t = &clkevt->t;
 	void __iomem *pend = t->base + t->pend;
 
-	writel_relaxed(0xffffffff - cycles, t->base + t->counter);
 	while (readl_relaxed(pend) & WP_TCRR)
 		cpu_relax();
+	writel_relaxed(0xffffffff - cycles, t->base + t->counter);
 
-	writel_relaxed(OMAP_TIMER_CTRL_ST, t->base + t->ctrl);
 	while (readl_relaxed(pend) & WP_TCLR)
 		cpu_relax();
+	writel_relaxed(OMAP_TIMER_CTRL_ST, t->base + t->ctrl);
 
 	return 0;
 }
@@ -490,18 +491,18 @@ static int dmtimer_set_periodic(struct clock_event_device *evt)
 	dmtimer_clockevent_shutdown(evt);
 
 	/* Looks like we need to first set the load value separately */
-	writel_relaxed(clkevt->period, t->base + t->load);
 	while (readl_relaxed(pend) & WP_TLDR)
 		cpu_relax();
+	writel_relaxed(clkevt->period, t->base + t->load);
 
-	writel_relaxed(clkevt->period, t->base + t->counter);
 	while (readl_relaxed(pend) & WP_TCRR)
 		cpu_relax();
+	writel_relaxed(clkevt->period, t->base + t->counter);
 
-	writel_relaxed(OMAP_TIMER_CTRL_AR | OMAP_TIMER_CTRL_ST,
-		       t->base + t->ctrl);
 	while (readl_relaxed(pend) & WP_TCLR)
 		cpu_relax();
+	writel_relaxed(OMAP_TIMER_CTRL_AR | OMAP_TIMER_CTRL_ST,
+		       t->base + t->ctrl);
 
 	return 0;
 }
@@ -530,17 +531,17 @@ static void omap_clockevent_unidle(struct clock_event_device *evt)
 	writel_relaxed(OMAP_TIMER_INT_OVERFLOW, t->base + t->wakeup);
 }
 
-static int __init dmtimer_clockevent_init(struct device_node *np)
+static int __init dmtimer_clkevt_init_common(struct dmtimer_clockevent *clkevt,
+					     struct device_node *np,
+					     unsigned int features,
+					     const struct cpumask *cpumask,
+					     const char *name,
+					     int rating)
 {
-	struct dmtimer_clockevent *clkevt;
 	struct clock_event_device *dev;
 	struct dmtimer_systimer *t;
 	int error;
 
-	clkevt = kzalloc(sizeof(*clkevt), GFP_KERNEL);
-	if (!clkevt)
-		return -ENOMEM;
-
 	t = &clkevt->t;
 	dev = &clkevt->dev;
 
@@ -548,24 +549,23 @@ static int __init dmtimer_clockevent_init(struct device_node *np)
 	 * We mostly use cpuidle_coupled with ARM local timers for runtime,
 	 * so there's probably no use for CLOCK_EVT_FEAT_DYNIRQ here.
 	 */
-	dev->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
-	dev->rating = 300;
+	dev->features = features;
+	dev->rating = rating;
 	dev->set_next_event = dmtimer_set_next_event;
 	dev->set_state_shutdown = dmtimer_clockevent_shutdown;
 	dev->set_state_periodic = dmtimer_set_periodic;
 	dev->set_state_oneshot = dmtimer_clockevent_shutdown;
+	dev->set_state_oneshot_stopped = dmtimer_clockevent_shutdown;
 	dev->tick_resume = dmtimer_clockevent_shutdown;
-	dev->cpumask = cpu_possible_mask;
+	dev->cpumask = cpumask;
 
 	dev->irq = irq_of_parse_and_map(np, 0);
-	if (!dev->irq) {
-		error = -ENXIO;
-		goto err_out_free;
-	}
+	if (!dev->irq)
+		return -ENXIO;
 
 	error = dmtimer_systimer_setup(np, &clkevt->t);
 	if (error)
-		goto err_out_free;
+		return error;
 
 	clkevt->period = 0xffffffff - DIV_ROUND_CLOSEST(t->rate, HZ);
 
@@ -577,38 +577,132 @@ static int __init dmtimer_clockevent_init(struct device_node *np)
 	writel_relaxed(OMAP_TIMER_CTRL_POSTED, t->base + t->ifctrl);
 
 	error = request_irq(dev->irq, dmtimer_clockevent_interrupt,
-			    IRQF_TIMER, "clockevent", clkevt);
+			    IRQF_TIMER, name, clkevt);
 	if (error)
 		goto err_out_unmap;
 
 	writel_relaxed(OMAP_TIMER_INT_OVERFLOW, t->base + t->irq_ena);
 	writel_relaxed(OMAP_TIMER_INT_OVERFLOW, t->base + t->wakeup);
 
-	pr_info("TI gptimer clockevent: %s%lu Hz at %pOF\n",
-		of_find_property(np, "ti,timer-alwon", NULL) ?
+	pr_info("TI gptimer %s: %s%lu Hz at %pOF\n",
+		name, of_find_property(np, "ti,timer-alwon", NULL) ?
 		"always-on " : "", t->rate, np->parent);
 
-	clockevents_config_and_register(dev, t->rate,
+	return 0;
+
+err_out_unmap:
+	iounmap(t->base);
+
+	return error;
+}
+
+static int __init dmtimer_clockevent_init(struct device_node *np)
+{
+	struct dmtimer_clockevent *clkevt;
+	int error;
+
+	clkevt = kzalloc(sizeof(*clkevt), GFP_KERNEL);
+	if (!clkevt)
+		return -ENOMEM;
+
+	error = dmtimer_clkevt_init_common(clkevt, np,
+					   CLOCK_EVT_FEAT_PERIODIC |
+					   CLOCK_EVT_FEAT_ONESHOT,
+					   cpu_possible_mask, "clockevent",
+					   300);
+	if (error)
+		goto err_out_free;
+
+	clockevents_config_and_register(&clkevt->dev, clkevt->t.rate,
 					3, /* Timer internal resync latency */
 					0xffffffff);
 
 	if (of_machine_is_compatible("ti,am33xx") ||
 	    of_machine_is_compatible("ti,am43")) {
-		dev->suspend = omap_clockevent_idle;
-		dev->resume = omap_clockevent_unidle;
+		clkevt->dev.suspend = omap_clockevent_idle;
+		clkevt->dev.resume = omap_clockevent_unidle;
 	}
 
 	return 0;
 
-err_out_unmap:
-	iounmap(t->base);
-
 err_out_free:
 	kfree(clkevt);
 
 	return error;
 }
 
+/* Dmtimer as percpu timer. See dra7 ARM architected timer wrap erratum i940 */
+static DEFINE_PER_CPU(struct dmtimer_clockevent, dmtimer_percpu_timer);
+
+static int __init dmtimer_percpu_timer_init(struct device_node *np, int cpu)
+{
+	struct dmtimer_clockevent *clkevt;
+	int error;
+
+	if (!cpu_possible(cpu))
+		return -EINVAL;
+
+	if (!of_property_read_bool(np->parent, "ti,no-reset-on-init") ||
+	    !of_property_read_bool(np->parent, "ti,no-idle"))
+		pr_warn("Incomplete dtb for percpu dmtimer %pOF\n", np->parent);
+
+	clkevt = per_cpu_ptr(&dmtimer_percpu_timer, cpu);
+
+	error = dmtimer_clkevt_init_common(clkevt, np, CLOCK_EVT_FEAT_ONESHOT,
+					   cpumask_of(cpu), "percpu-dmtimer",
+					   500);
+	if (error)
+		return error;
+
+	return 0;
+}
+
+/* See TRM for timer internal resynch latency */
+static int omap_dmtimer_starting_cpu(unsigned int cpu)
+{
+	struct dmtimer_clockevent *clkevt = per_cpu_ptr(&dmtimer_percpu_timer, cpu);
+	struct clock_event_device *dev = &clkevt->dev;
+	struct dmtimer_systimer *t = &clkevt->t;
+
+	clockevents_config_and_register(dev, t->rate, 3, ULONG_MAX);
+	irq_force_affinity(dev->irq, cpumask_of(cpu));
+
+	return 0;
+}
+
+static int __init dmtimer_percpu_timer_startup(void)
+{
+	struct dmtimer_clockevent *clkevt = per_cpu_ptr(&dmtimer_percpu_timer, 0);
+	struct dmtimer_systimer *t = &clkevt->t;
+
+	if (t->sysc) {
+		cpuhp_setup_state(CPUHP_AP_TI_GP_TIMER_STARTING,
+				  "clockevents/omap/gptimer:starting",
+				  omap_dmtimer_starting_cpu, NULL);
+	}
+
+	return 0;
+}
+subsys_initcall(dmtimer_percpu_timer_startup);
+
+static int __init dmtimer_percpu_quirk_init(struct device_node *np, u32 pa)
+{
+	struct device_node *arm_timer;
+
+	arm_timer = of_find_compatible_node(NULL, NULL, "arm,armv7-timer");
+	if (of_device_is_available(arm_timer)) {
+		pr_warn_once("ARM architected timer wrap issue i940 detected\n");
+		return 0;
+	}
+
+	if (pa == 0x48034000)		/* dra7 dmtimer3 */
+		return dmtimer_percpu_timer_init(np, 0);
+	else if (pa == 0x48036000)	/* dra7 dmtimer4 */
+		return dmtimer_percpu_timer_init(np, 1);
+
+	return 0;
+}
+
 /* Clocksource */
 static struct dmtimer_clocksource *
 to_dmtimer_clocksource(struct clocksource *cs)
@@ -742,6 +836,9 @@ static int __init dmtimer_systimer_init(struct device_node *np)
 	if (clockevent == pa)
 		return dmtimer_clockevent_init(np);
 
+	if (of_machine_is_compatible("ti,dra7"))
+		return dmtimer_percpu_quirk_init(np, pa);
+
 	return 0;
 }
 
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index f14adb882338..cc7c3fda2aa6 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -135,6 +135,7 @@ enum cpuhp_state {
 	CPUHP_AP_RISCV_TIMER_STARTING,
 	CPUHP_AP_CLINT_TIMER_STARTING,
 	CPUHP_AP_CSKY_TIMER_STARTING,
+	CPUHP_AP_TI_GP_TIMER_STARTING,
 	CPUHP_AP_HYPERV_TIMER_STARTING,
 	CPUHP_AP_KVM_STARTING,
 	CPUHP_AP_KVM_ARM_VGIC_INIT_STARTING,