Merge tag 'v4.13-rc4' into v4.14/dt64

Linux 4.13-rc4

25 files changed, 165 insertions, 76 deletions

diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi
index 9d00622ce845..bd0f33b77f57 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi
@@ -452,7 +452,7 @@
 		emac: ethernet@1c30000 {
 			compatible = "allwinner,sun50i-a64-emac";
 			syscon = <&syscon>;
-			reg = <0x01c30000 0x100>;
+			reg = <0x01c30000 0x10000>;
 			interrupts = <GIC_SPI 82 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-names = "macirq";
 			resets = <&ccu RST_BUS_EMAC>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
index f49831ea428c..f175db846286 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
@@ -414,7 +414,7 @@
 			};
 
 			pwm_AO_ab: pwm@550 {
-				compatible = "amlogic,meson-gx-pwm", "amlogic,meson-gxbb-pwm";
+				compatible = "amlogic,meson-gx-ao-pwm", "amlogic,meson-gxbb-ao-pwm";
 				reg = <0x0 0x00550 0x0 0x10>;
 				#pwm-cells = <3>;
 				status = "disabled";
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-khadas-vim.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-khadas-vim.dts
index a7cf54da4806..edc512ad0bac 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-khadas-vim.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-khadas-vim.dts
@@ -172,8 +172,8 @@
 	status = "okay";
 	pinctrl-0 = <&pwm_ao_a_3_pins>, <&pwm_ao_b_pins>;
 	pinctrl-names = "default";
-	clocks = <&clkc CLKID_FCLK_DIV4>;
-	clock-names = "clkin0";
+	clocks = <&xtal> , <&xtal>;
+	clock-names = "clkin0", "clkin1" ;
 };
 
 &pwm_ef {
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts
index d537d7c2e8a5..f5ed386e6591 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts
@@ -10,12 +10,20 @@
 
 #include <dt-bindings/input/input.h>
 
-#include "meson-gxl-s905x-p212.dtsi"
+#include "meson-gxl-s905x.dtsi"
 
 / {
 	compatible = "libretech,cc", "amlogic,s905x", "amlogic,meson-gxl";
 	model = "Libre Technology CC";
 
+	aliases {
+		serial0 = &uart_AO;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
 	cvbs-connector {
 		compatible = "composite-video-connector";
 
@@ -26,6 +34,11 @@
 		};
 	};
 
+	emmc_pwrseq: emmc-pwrseq {
+		compatible = "mmc-pwrseq-emmc";
+		reset-gpios = <&gpio BOOT_9 GPIO_ACTIVE_LOW>;
+	};
+
 	hdmi-connector {
 		compatible = "hdmi-connector";
 		type = "a";
@@ -53,6 +66,39 @@
 			linux,default-trigger = "heartbeat";
 		};
 	};
+
+	memory@0 {
+		device_type = "memory";
+		reg = <0x0 0x0 0x0 0x80000000>;
+	};
+
+	vcc_3v3: regulator-vcc_3v3 {
+		compatible = "regulator-fixed";
+		regulator-name = "VCC_3V3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+	};
+
+	vcc_card: regulator-vcc-card {
+		compatible = "regulator-gpio";
+
+		regulator-name = "VCC_CARD";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <3300000>;
+
+		gpios = <&gpio_ao GPIOAO_3 GPIO_ACTIVE_HIGH>;
+		gpios-states = <0>;
+
+		states = <3300000 0>,
+			 <1800000 1>;
+	};
+
+	vddio_boot: regulator-vddio_boot {
+		compatible = "regulator-fixed";
+		regulator-name = "VDDIO_BOOT";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+	};
 };
 
 &cec_AO {
@@ -68,6 +114,16 @@
 	};
 };
 
+&ethmac {
+	status = "okay";
+};
+
+&ir {
+	status = "okay";
+	pinctrl-0 = <&remote_input_ao_pins>;
+	pinctrl-names = "default";
+};
+
 &hdmi_tx {
 	status = "okay";
 	pinctrl-0 = <&hdmi_hpd_pins>, <&hdmi_i2c_pins>;
@@ -80,20 +136,43 @@
 	};
 };
 
-/*
- * The following devices exists but are exposed on the general
- * purpose GPIO header. End user may well decide to use those pins
- * for another purpose
- */
+/* SD card */
+&sd_emmc_b {
+	status = "okay";
+	pinctrl-0 = <&sdcard_pins>;
+	pinctrl-names = "default";
+
+	bus-width = <4>;
+	cap-sd-highspeed;
+	max-frequency = <100000000>;
+	disable-wp;
+
+	cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>;
+	cd-inverted;
 
-&sd_emmc_a {
-	status = "disabled";
+	vmmc-supply = <&vcc_3v3>;
+	vqmmc-supply = <&vcc_card>;
 };
 
-&uart_A {
-	status = "disabled";
+/* eMMC */
+&sd_emmc_c {
+	status = "okay";
+	pinctrl-0 = <&emmc_pins>;
+	pinctrl-names = "default";
+
+	bus-width = <8>;
+	cap-mmc-highspeed;
+	max-frequency = <50000000>;
+	non-removable;
+	disable-wp;
+
+	mmc-pwrseq = <&emmc_pwrseq>;
+	vmmc-supply = <&vcc_3v3>;
+	vqmmc-supply = <&vddio_boot>;
 };
 
-&wifi32k {
-	status = "disabled";
+&uart_AO {
+	status = "okay";
+	pinctrl-0 = <&uart_ao_a_pins>;
+	pinctrl-names = "default";
 };
diff --git a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi
index dbcc3d4e2ed5..51763d674050 100644
--- a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi
@@ -219,7 +219,7 @@
 				reg = <0x18800 0x100>, <0x18C00 0x20>;
 				gpiosb: gpio {
 					#gpio-cells = <2>;
-					gpio-ranges = <&pinctrl_sb 0 0 29>;
+					gpio-ranges = <&pinctrl_sb 0 0 30>;
 					gpio-controller;
 					interrupts =
 					<GIC_SPI 160 IRQ_TYPE_LEVEL_HIGH>,
diff --git a/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi
index 726528ce54e9..4c68605675a8 100644
--- a/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi
@@ -270,6 +270,7 @@
 				interrupt-names = "mem", "ring0", "ring1",
 				"ring2", "ring3", "eip";
 				clocks = <&cpm_clk 1 26>;
+				dma-coherent;
 			};
 		};
 
diff --git a/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi
index 95f8e5f607f6..923f354b02f0 100644
--- a/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi
@@ -64,7 +64,7 @@
 				compatible = "marvell,armada-8k-rtc";
 				reg = <0x284000 0x20>, <0x284080 0x24>;
 				reg-names = "rtc", "rtc-soc";
-				interrupts = <GIC_SPI 71 IRQ_TYPE_LEVEL_HIGH>;
+				interrupts = <ICU_GRP_NSR 77 IRQ_TYPE_LEVEL_HIGH>;
 			};
 
 			cps_ethernet: ethernet@0 {
@@ -261,6 +261,7 @@
 				interrupt-names = "mem", "ring0", "ring1",
 						  "ring2", "ring3", "eip";
 				clocks = <&cps_clk 1 26>;
+				dma-coherent;
 				/*
 				 * The cryptographic engine found on the cp110
 				 * master is enabled by default at the SoC
diff --git a/arch/arm64/boot/dts/renesas/salvator-common.dtsi b/arch/arm64/boot/dts/renesas/salvator-common.dtsi
index aef35e0b685a..a451996f590a 100644
--- a/arch/arm64/boot/dts/renesas/salvator-common.dtsi
+++ b/arch/arm64/boot/dts/renesas/salvator-common.dtsi
@@ -508,7 +508,7 @@
 
 	/* audio_clkout0/1/2/3 */
 	#clock-cells = <1>;
-	clock-frequency = <11289600 12288000>;
+	clock-frequency = <12288000 11289600>;
 
 	status = "okay";
 
diff --git a/arch/arm64/boot/dts/renesas/ulcb.dtsi b/arch/arm64/boot/dts/renesas/ulcb.dtsi
index b5c6ee07d7f9..d1a3f3b7a0ab 100644
--- a/arch/arm64/boot/dts/renesas/ulcb.dtsi
+++ b/arch/arm64/boot/dts/renesas/ulcb.dtsi
@@ -281,7 +281,7 @@
 
 	/* audio_clkout0/1/2/3 */
 	#clock-cells = <1>;
-	clock-frequency = <11289600 12288000>;
+	clock-frequency = <12288000 11289600>;
 
 	status = "okay";
 
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 6c7d147eed54..b4ca115b3be1 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -476,6 +476,7 @@ CONFIG_QCOM_CLK_SMD_RPM=y
 CONFIG_MSM_GCC_8916=y
 CONFIG_MSM_GCC_8994=y
 CONFIG_MSM_MMCC_8996=y
+CONFIG_HWSPINLOCK=y
 CONFIG_HWSPINLOCK_QCOM=y
 CONFIG_ARM_MHU=y
 CONFIG_PLATFORM_MHU=y
diff --git a/arch/arm64/include/asm/atomic_lse.h b/arch/arm64/include/asm/atomic_lse.h
index 99fa69c9c3cf..9ef0797380cb 100644
--- a/arch/arm64/include/asm/atomic_lse.h
+++ b/arch/arm64/include/asm/atomic_lse.h
@@ -435,7 +435,7 @@ static inline long atomic64_dec_if_positive(atomic64_t *v)
 	"	sub	x30, x30, %[ret]\n"
 	"	cbnz	x30, 1b\n"
 	"2:")
-	: [ret] "+&r" (x0), [v] "+Q" (v->counter)
+	: [ret] "+r" (x0), [v] "+Q" (v->counter)
 	:
 	: __LL_SC_CLOBBERS, "cc", "memory");
 
diff --git a/arch/arm64/include/asm/bug.h b/arch/arm64/include/asm/bug.h
index 366448eb0fb7..a02a57186f56 100644
--- a/arch/arm64/include/asm/bug.h
+++ b/arch/arm64/include/asm/bug.h
@@ -36,7 +36,7 @@
 #ifdef CONFIG_GENERIC_BUG
 
 #define __BUG_ENTRY(flags) 				\
-		".pushsection __bug_table,\"a\"\n\t"	\
+		".pushsection __bug_table,\"aw\"\n\t"	\
 		".align 2\n\t"				\
 	"0:	.long 1f - 0b\n\t"			\
 _BUGVERBOSE_LOCATION(__FILE__, __LINE__)		\
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 32f82723338a..ef39dcb9ca6a 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -64,8 +64,10 @@
  * TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area.
  */
 #define VA_BITS			(CONFIG_ARM64_VA_BITS)
-#define VA_START		(UL(0xffffffffffffffff) << VA_BITS)
-#define PAGE_OFFSET		(UL(0xffffffffffffffff) << (VA_BITS - 1))
+#define VA_START		(UL(0xffffffffffffffff) - \
+	(UL(1) << VA_BITS) + 1)
+#define PAGE_OFFSET		(UL(0xffffffffffffffff) - \
+	(UL(1) << (VA_BITS - 1)) + 1)
 #define KIMAGE_VADDR		(MODULES_END)
 #define MODULES_END		(MODULES_VADDR + MODULES_VSIZE)
 #define MODULES_VADDR		(VA_START + KASAN_SHADOW_SIZE)
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 16e44fa9b3b6..248339e4aaf5 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -492,7 +492,7 @@ asm(
  * the "%x0" template means XZR.
  */
 #define write_sysreg(v, r) do {					\
-	u64 __val = (u64)v;					\
+	u64 __val = (u64)(v);					\
 	asm volatile("msr " __stringify(r) ", %x0"		\
 		     : : "rZ" (__val));				\
 } while (0)
@@ -508,7 +508,7 @@ asm(
 })
 
 #define write_sysreg_s(v, r) do {					\
-	u64 __val = (u64)v;						\
+	u64 __val = (u64)(v);						\
 	asm volatile("msr_s " __stringify(r) ", %x0" : : "rZ" (__val));	\
 } while (0)
 
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 8f0a1de11e4a..fab46a0ea223 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -69,7 +69,7 @@ static inline void set_fs(mm_segment_t fs)
  */
 #define __range_ok(addr, size)						\
 ({									\
-	unsigned long __addr = (unsigned long __force)(addr);		\
+	unsigned long __addr = (unsigned long)(addr);			\
 	unsigned long flag, roksum;					\
 	__chk_user_ptr(addr);						\
 	asm("adds %1, %1, %3; ccmp %1, %4, #2, cc; cset %0, ls"		\
diff --git a/arch/arm64/kernel/cpu_ops.c b/arch/arm64/kernel/cpu_ops.c
index e137ceaf5016..d16978213c5b 100644
--- a/arch/arm64/kernel/cpu_ops.c
+++ b/arch/arm64/kernel/cpu_ops.c
@@ -82,8 +82,8 @@ static const char *__init cpu_read_enable_method(int cpu)
 			 * Don't warn spuriously.
 			 */
 			if (cpu != 0)
-				pr_err("%s: missing enable-method property\n",
-					dn->full_name);
+				pr_err("%pOF: missing enable-method property\n",
+					dn);
 		}
 	} else {
 		enable_method = acpi_get_enable_method(cpu);
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 321119881abf..dc66e6ec3a99 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -469,7 +469,7 @@ static u64 __init of_get_cpu_mpidr(struct device_node *dn)
 	 */
 	cell = of_get_property(dn, "reg", NULL);
 	if (!cell) {
-		pr_err("%s: missing reg property\n", dn->full_name);
+		pr_err("%pOF: missing reg property\n", dn);
 		return INVALID_HWID;
 	}
 
@@ -478,7 +478,7 @@ static u64 __init of_get_cpu_mpidr(struct device_node *dn)
 	 * Non affinity bits must be set to 0 in the DT
 	 */
 	if (hwid & ~MPIDR_HWID_BITMASK) {
-		pr_err("%s: invalid reg property\n", dn->full_name);
+		pr_err("%pOF: invalid reg property\n", dn);
 		return INVALID_HWID;
 	}
 	return hwid;
@@ -627,8 +627,8 @@ static void __init of_parse_and_init_cpus(void)
 			goto next;
 
 		if (is_mpidr_duplicate(cpu_count, hwid)) {
-			pr_err("%s: duplicate cpu reg properties in the DT\n",
-				dn->full_name);
+			pr_err("%pOF: duplicate cpu reg properties in the DT\n",
+				dn);
 			goto next;
 		}
 
@@ -640,8 +640,8 @@ static void __init of_parse_and_init_cpus(void)
 		 */
 		if (hwid == cpu_logical_map(0)) {
 			if (bootcpu_valid) {
-				pr_err("%s: duplicate boot cpu reg property in DT\n",
-					dn->full_name);
+				pr_err("%pOF: duplicate boot cpu reg property in DT\n",
+					dn);
 				goto next;
 			}
 
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 79244c75eaec..8d48b233e6ce 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -45,7 +45,7 @@ static int __init get_cpu_for_node(struct device_node *node)
 		}
 	}
 
-	pr_crit("Unable to find CPU node for %s\n", cpu_node->full_name);
+	pr_crit("Unable to find CPU node for %pOF\n", cpu_node);
 
 	of_node_put(cpu_node);
 	return -1;
@@ -71,8 +71,8 @@ static int __init parse_core(struct device_node *core, int cluster_id,
 				cpu_topology[cpu].core_id = core_id;
 				cpu_topology[cpu].thread_id = i;
 			} else {
-				pr_err("%s: Can't get CPU for thread\n",
-				       t->full_name);
+				pr_err("%pOF: Can't get CPU for thread\n",
+				       t);
 				of_node_put(t);
 				return -EINVAL;
 			}
@@ -84,15 +84,15 @@ static int __init parse_core(struct device_node *core, int cluster_id,
 	cpu = get_cpu_for_node(core);
 	if (cpu >= 0) {
 		if (!leaf) {
-			pr_err("%s: Core has both threads and CPU\n",
-			       core->full_name);
+			pr_err("%pOF: Core has both threads and CPU\n",
+			       core);
 			return -EINVAL;
 		}
 
 		cpu_topology[cpu].cluster_id = cluster_id;
 		cpu_topology[cpu].core_id = core_id;
 	} else if (leaf) {
-		pr_err("%s: Can't get CPU for leaf core\n", core->full_name);
+		pr_err("%pOF: Can't get CPU for leaf core\n", core);
 		return -EINVAL;
 	}
 
@@ -137,8 +137,8 @@ static int __init parse_cluster(struct device_node *cluster, int depth)
 			has_cores = true;
 
 			if (depth == 0) {
-				pr_err("%s: cpu-map children should be clusters\n",
-				       c->full_name);
+				pr_err("%pOF: cpu-map children should be clusters\n",
+				       c);
 				of_node_put(c);
 				return -EINVAL;
 			}
@@ -146,8 +146,8 @@ static int __init parse_cluster(struct device_node *cluster, int depth)
 			if (leaf) {
 				ret = parse_core(c, cluster_id, core_id++);
 			} else {
-				pr_err("%s: Non-leaf cluster with core %s\n",
-				       cluster->full_name, name);
+				pr_err("%pOF: Non-leaf cluster with core %s\n",
+				       cluster, name);
 				ret = -EINVAL;
 			}
 
@@ -159,7 +159,7 @@ static int __init parse_cluster(struct device_node *cluster, int depth)
 	} while (c);
 
 	if (leaf && !has_cores)
-		pr_warn("%s: empty cluster\n", cluster->full_name);
+		pr_warn("%pOF: empty cluster\n", cluster);
 
 	if (leaf)
 		cluster_id++;
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index c7c7088097be..8a62648848e5 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -274,10 +274,12 @@ static DEFINE_RAW_SPINLOCK(die_lock);
 void die(const char *str, struct pt_regs *regs, int err)
 {
 	int ret;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&die_lock, flags);
 
 	oops_enter();
 
-	raw_spin_lock_irq(&die_lock);
 	console_verbose();
 	bust_spinlocks(1);
 	ret = __die(str, err, regs);
@@ -287,13 +289,15 @@ void die(const char *str, struct pt_regs *regs, int err)
 
 	bust_spinlocks(0);
 	add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE);
-	raw_spin_unlock_irq(&die_lock);
 	oops_exit();
 
 	if (in_interrupt())
 		panic("Fatal exception in interrupt");
 	if (panic_on_oops)
 		panic("Fatal exception");
+
+	raw_spin_unlock_irqrestore(&die_lock, flags);
+
 	if (ret != NOTIFY_STOP)
 		do_exit(SIGSEGV);
 }
@@ -519,7 +523,7 @@ static void cntfrq_read_handler(unsigned int esr, struct pt_regs *regs)
 {
 	int rt = (esr & ESR_ELx_SYS64_ISS_RT_MASK) >> ESR_ELx_SYS64_ISS_RT_SHIFT;
 
-	pt_regs_write_reg(regs, rt, read_sysreg(cntfrq_el0));
+	pt_regs_write_reg(regs, rt, arch_timer_get_rate());
 	regs->pc += 4;
 }
 
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 77862881ae86..2e070d3baf9f 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -764,7 +764,7 @@ static bool access_pmovs(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 	if (p->is_write) {
 		if (r->CRm & 0x2)
 			/* accessing PMOVSSET_EL0 */
-			kvm_pmu_overflow_set(vcpu, p->regval & mask);
+			vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= (p->regval & mask);
 		else
 			/* accessing PMOVSCLR_EL0 */
 			vcpu_sys_reg(vcpu, PMOVSSET_EL0) &= ~(p->regval & mask);
diff --git a/arch/arm64/lib/copy_page.S b/arch/arm64/lib/copy_page.S
index c3cd65e31814..076c43715e64 100644
--- a/arch/arm64/lib/copy_page.S
+++ b/arch/arm64/lib/copy_page.S
@@ -30,9 +30,10 @@
  */
 ENTRY(copy_page)
 alternative_if ARM64_HAS_NO_HW_PREFETCH
-	# Prefetch two cache lines ahead.
-	prfm    pldl1strm, [x1, #128]
-	prfm    pldl1strm, [x1, #256]
+	// Prefetch three cache lines ahead.
+	prfm	pldl1strm, [x1, #128]
+	prfm	pldl1strm, [x1, #256]
+	prfm	pldl1strm, [x1, #384]
 alternative_else_nop_endif
 
 	ldp	x2, x3, [x1]
@@ -50,7 +51,7 @@ alternative_else_nop_endif
 	subs	x18, x18, #128
 
 alternative_if ARM64_HAS_NO_HW_PREFETCH
-	prfm    pldl1strm, [x1, #384]
+	prfm	pldl1strm, [x1, #384]
 alternative_else_nop_endif
 
 	stnp	x2, x3, [x0]
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index e90cd1db42a8..f27d4dd04384 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -329,7 +329,7 @@ static int __swiotlb_mmap(struct device *dev,
 	vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot,
 					     is_device_dma_coherent(dev));
 
-	if (dma_mmap_from_coherent(dev, vma, cpu_addr, size, &ret))
+	if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
 		return ret;
 
 	return __swiotlb_mmap_pfn(vma, pfn, size);
@@ -706,7 +706,7 @@ static int __iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
 	vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot,
 					     is_device_dma_coherent(dev));
 
-	if (dma_mmap_from_coherent(dev, vma, cpu_addr, size, &ret))
+	if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
 		return ret;
 
 	if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) {
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index c7861c9864e6..2509e4fe6992 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -163,26 +163,27 @@ int ptep_set_access_flags(struct vm_area_struct *vma,
 	/* only preserve the access flags and write permission */
 	pte_val(entry) &= PTE_AF | PTE_WRITE | PTE_DIRTY;
 
-	/*
-	 * PTE_RDONLY is cleared by default in the asm below, so set it in
-	 * back if necessary (read-only or clean PTE).
-	 */
+	/* set PTE_RDONLY if actual read-only or clean PTE */
 	if (!pte_write(entry) || !pte_sw_dirty(entry))
 		pte_val(entry) |= PTE_RDONLY;
 
 	/*
 	 * Setting the flags must be done atomically to avoid racing with the
-	 * hardware update of the access/dirty state.
+	 * hardware update of the access/dirty state. The PTE_RDONLY bit must
+	 * be set to the most permissive (lowest value) of *ptep and entry
+	 * (calculated as: a & b == ~(~a | ~b)).
 	 */
+	pte_val(entry) ^= PTE_RDONLY;
 	asm volatile("//	ptep_set_access_flags\n"
 	"	prfm	pstl1strm, %2\n"
 	"1:	ldxr	%0, %2\n"
-	"	and	%0, %0, %3		// clear PTE_RDONLY\n"
+	"	eor	%0, %0, %3		// negate PTE_RDONLY in *ptep\n"
 	"	orr	%0, %0, %4		// set flags\n"
+	"	eor	%0, %0, %3		// negate final PTE_RDONLY\n"
 	"	stxr	%w1, %0, %2\n"
 	"	cbnz	%w1, 1b\n"
 	: "=&r" (old_pteval), "=&r" (tmp), "+Q" (pte_val(*ptep))
-	: "L" (~PTE_RDONLY), "r" (pte_val(entry)));
+	: "L" (PTE_RDONLY), "r" (pte_val(entry)));
 
 	flush_tlb_fix_spurious_fault(vma, address);
 	return 1;
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 23c2d89a362e..f1eb15e0e864 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -496,7 +496,7 @@ void mark_rodata_ro(void)
 
 static void __init map_kernel_segment(pgd_t *pgd, void *va_start, void *va_end,
 				      pgprot_t prot, struct vm_struct *vma,
-				      int flags)
+				      int flags, unsigned long vm_flags)
 {
 	phys_addr_t pa_start = __pa_symbol(va_start);
 	unsigned long size = va_end - va_start;
@@ -507,10 +507,13 @@ static void __init map_kernel_segment(pgd_t *pgd, void *va_start, void *va_end,
 	__create_pgd_mapping(pgd, pa_start, (unsigned long)va_start, size, prot,
 			     early_pgtable_alloc, flags);
 
+	if (!(vm_flags & VM_NO_GUARD))
+		size += PAGE_SIZE;
+
 	vma->addr	= va_start;
 	vma->phys_addr	= pa_start;
 	vma->size	= size;
-	vma->flags	= VM_MAP;
+	vma->flags	= VM_MAP | vm_flags;
 	vma->caller	= __builtin_return_address(0);
 
 	vm_area_add_early(vma);
@@ -541,14 +544,15 @@ static void __init map_kernel(pgd_t *pgd)
 	 * Only rodata will be remapped with different permissions later on,
 	 * all other segments are allowed to use contiguous mappings.
 	 */
-	map_kernel_segment(pgd, _text, _etext, text_prot, &vmlinux_text, 0);
+	map_kernel_segment(pgd, _text, _etext, text_prot, &vmlinux_text, 0,
+			   VM_NO_GUARD);
 	map_kernel_segment(pgd, __start_rodata, __inittext_begin, PAGE_KERNEL,
-			   &vmlinux_rodata, NO_CONT_MAPPINGS);
+			   &vmlinux_rodata, NO_CONT_MAPPINGS, VM_NO_GUARD);
 	map_kernel_segment(pgd, __inittext_begin, __inittext_end, text_prot,
-			   &vmlinux_inittext, 0);
+			   &vmlinux_inittext, 0, VM_NO_GUARD);
 	map_kernel_segment(pgd, __initdata_begin, __initdata_end, PAGE_KERNEL,
-			   &vmlinux_initdata, 0);
-	map_kernel_segment(pgd, _data, _end, PAGE_KERNEL, &vmlinux_data, 0);
+			   &vmlinux_initdata, 0, VM_NO_GUARD);
+	map_kernel_segment(pgd, _data, _end, PAGE_KERNEL, &vmlinux_data, 0, 0);
 
 	if (!pgd_val(*pgd_offset_raw(pgd, FIXADDR_START))) {
 		/*
diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c
index b388a99fea7b..dad128ba98bf 100644
--- a/arch/arm64/mm/numa.c
+++ b/arch/arm64/mm/numa.c
@@ -208,8 +208,6 @@ int __init numa_add_memblk(int nid, u64 start, u64 end)
 	}
 
 	node_set(nid, numa_nodes_parsed);
-	pr_info("Adding memblock [0x%llx - 0x%llx] on node %d\n",
-			start, (end - 1), nid);
 	return ret;
 }
 
@@ -223,10 +221,7 @@ static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn)
 	void *nd;
 	int tnid;
 
-	if (start_pfn < end_pfn)
-		pr_info("Initmem setup node %d [mem %#010Lx-%#010Lx]\n", nid,
-			start_pfn << PAGE_SHIFT, (end_pfn << PAGE_SHIFT) - 1);
-	else
+	if (start_pfn >= end_pfn)
 		pr_info("Initmem setup node %d [<memory-less node>]\n", nid);
 
 	nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid);