Merge branch 'linux-4.14.y_for_4.14-2.0.x-imx' into 4.14-2.0.x-imx

25 files changed, 204 insertions, 108 deletions

diff --git a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts
index 3aee6123d161..6887cc1a743d 100644
--- a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts
+++ b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts
@@ -118,6 +118,7 @@
 		reset-gpios = <&gpio0 5 GPIO_ACTIVE_LOW>;
 		clocks = <&pmic>;
 		clock-names = "ext_clock";
+		post-power-on-delay-ms = <10>;
 		power-off-delay-us = <10>;
 	};
 
diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi
index ab00be277c6f..6f372ec055dd 100644
--- a/arch/arm64/boot/dts/qcom/msm8996.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi
@@ -359,7 +359,7 @@
 		};
 
 		intc: interrupt-controller@9bc0000 {
-			compatible = "arm,gic-v3";
+			compatible = "qcom,msm8996-gic-v3", "arm,gic-v3";
 			#interrupt-cells = <3>;
 			interrupt-controller;
 			#redistributor-regions = <1>;
diff --git a/arch/arm64/boot/dts/renesas/r8a7796.dtsi b/arch/arm64/boot/dts/renesas/r8a7796.dtsi
index 369092e17e34..016b84552a62 100644
--- a/arch/arm64/boot/dts/renesas/r8a7796.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a7796.dtsi
@@ -937,6 +937,9 @@
 				 <&cpg CPG_CORE R8A7796_CLK_S3D1>,
 				 <&scif_clk>;
 			clock-names = "fck", "brg_int", "scif_clk";
+			dmas = <&dmac1 0x13>, <&dmac1 0x12>,
+			       <&dmac2 0x13>, <&dmac2 0x12>;
+			dma-names = "tx", "rx", "tx", "rx";
 			power-domains = <&sysc R8A7796_PD_ALWAYS_ON>;
 			resets = <&cpg 310>;
 			status = "disabled";
diff --git a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts
index 28257724a56e..e720f40bbd5d 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts
@@ -82,8 +82,7 @@
 
 	vcc_host1_5v: vcc_otg_5v: vcc-host1-5v-regulator {
 		compatible = "regulator-fixed";
-		enable-active-high;
-		gpio = <&gpio0 RK_PD3 GPIO_ACTIVE_HIGH>;
+		gpio = <&gpio0 RK_PA2 GPIO_ACTIVE_LOW>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&usb20_host_drv>;
 		regulator-name = "vcc_host1_5v";
@@ -275,7 +274,7 @@
 
 	usb2 {
 		usb20_host_drv: usb20-host-drv {
-			rockchip,pins = <0 RK_PD3 RK_FUNC_GPIO &pcfg_pull_none>;
+			rockchip,pins = <0 RK_PA2 RK_FUNC_GPIO &pcfg_pull_none>;
 		};
 	};
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi
index efac2202b16e..f6b4b8f0260f 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi
@@ -1333,11 +1333,11 @@
 
 		sdmmc0 {
 			sdmmc0_clk: sdmmc0-clk {
-				rockchip,pins = <1 RK_PA6 1 &pcfg_pull_none_4ma>;
+				rockchip,pins = <1 RK_PA6 1 &pcfg_pull_none_8ma>;
 			};
 
 			sdmmc0_cmd: sdmmc0-cmd {
-				rockchip,pins = <1 RK_PA4 1 &pcfg_pull_up_4ma>;
+				rockchip,pins = <1 RK_PA4 1 &pcfg_pull_up_8ma>;
 			};
 
 			sdmmc0_dectn: sdmmc0-dectn {
@@ -1349,14 +1349,14 @@
 			};
 
 			sdmmc0_bus1: sdmmc0-bus1 {
-				rockchip,pins = <1 RK_PA0 1 &pcfg_pull_up_4ma>;
+				rockchip,pins = <1 RK_PA0 1 &pcfg_pull_up_8ma>;
 			};
 
 			sdmmc0_bus4: sdmmc0-bus4 {
-				rockchip,pins = <1 RK_PA0 1 &pcfg_pull_up_4ma>,
-						<1 RK_PA1 1 &pcfg_pull_up_4ma>,
-						<1 RK_PA2 1 &pcfg_pull_up_4ma>,
-						<1 RK_PA3 1 &pcfg_pull_up_4ma>;
+				rockchip,pins = <1 RK_PA0 1 &pcfg_pull_up_8ma>,
+						<1 RK_PA1 1 &pcfg_pull_up_8ma>,
+						<1 RK_PA2 1 &pcfg_pull_up_8ma>,
+						<1 RK_PA3 1 &pcfg_pull_up_8ma>;
 			};
 
 			sdmmc0_gpio: sdmmc0-gpio {
@@ -1530,50 +1530,50 @@
 			rgmiim1_pins: rgmiim1-pins {
 				rockchip,pins =
 					/* mac_txclk */
-					<1 RK_PB4 2 &pcfg_pull_none_12ma>,
+					<1 RK_PB4 2 &pcfg_pull_none_8ma>,
 					/* mac_rxclk */
-					<1 RK_PB5 2 &pcfg_pull_none_2ma>,
+					<1 RK_PB5 2 &pcfg_pull_none_4ma>,
 					/* mac_mdio */
-					<1 RK_PC3 2 &pcfg_pull_none_2ma>,
+					<1 RK_PC3 2 &pcfg_pull_none_4ma>,
 					/* mac_txen */
-					<1 RK_PD1 2 &pcfg_pull_none_12ma>,
+					<1 RK_PD1 2 &pcfg_pull_none_8ma>,
 					/* mac_clk */
-					<1 RK_PC5 2 &pcfg_pull_none_2ma>,
+					<1 RK_PC5 2 &pcfg_pull_none_4ma>,
 					/* mac_rxdv */
-					<1 RK_PC6 2 &pcfg_pull_none_2ma>,
+					<1 RK_PC6 2 &pcfg_pull_none_4ma>,
 					/* mac_mdc */
-					<1 RK_PC7 2 &pcfg_pull_none_2ma>,
+					<1 RK_PC7 2 &pcfg_pull_none_4ma>,
 					/* mac_rxd1 */
-					<1 RK_PB2 2 &pcfg_pull_none_2ma>,
+					<1 RK_PB2 2 &pcfg_pull_none_4ma>,
 					/* mac_rxd0 */
-					<1 RK_PB3 2 &pcfg_pull_none_2ma>,
+					<1 RK_PB3 2 &pcfg_pull_none_4ma>,
 					/* mac_txd1 */
-					<1 RK_PB0 2 &pcfg_pull_none_12ma>,
+					<1 RK_PB0 2 &pcfg_pull_none_8ma>,
 					/* mac_txd0 */
-					<1 RK_PB1 2 &pcfg_pull_none_12ma>,
+					<1 RK_PB1 2 &pcfg_pull_none_8ma>,
 					/* mac_rxd3 */
-					<1 RK_PB6 2 &pcfg_pull_none_2ma>,
+					<1 RK_PB6 2 &pcfg_pull_none_4ma>,
 					/* mac_rxd2 */
-					<1 RK_PB7 2 &pcfg_pull_none_2ma>,
+					<1 RK_PB7 2 &pcfg_pull_none_4ma>,
 					/* mac_txd3 */
-					<1 RK_PC0 2 &pcfg_pull_none_12ma>,
+					<1 RK_PC0 2 &pcfg_pull_none_8ma>,
 					/* mac_txd2 */
-					<1 RK_PC1 2 &pcfg_pull_none_12ma>,
+					<1 RK_PC1 2 &pcfg_pull_none_8ma>,
 
 					/* mac_txclk */
-					<0 RK_PB0 1 &pcfg_pull_none>,
+					<0 RK_PB0 1 &pcfg_pull_none_8ma>,
 					/* mac_txen */
-					<0 RK_PB4 1 &pcfg_pull_none>,
+					<0 RK_PB4 1 &pcfg_pull_none_8ma>,
 					/* mac_clk */
-					<0 RK_PD0 1 &pcfg_pull_none>,
+					<0 RK_PD0 1 &pcfg_pull_none_4ma>,
 					/* mac_txd1 */
-					<0 RK_PC0 1 &pcfg_pull_none>,
+					<0 RK_PC0 1 &pcfg_pull_none_8ma>,
 					/* mac_txd0 */
-					<0 RK_PC1 1 &pcfg_pull_none>,
+					<0 RK_PC1 1 &pcfg_pull_none_8ma>,
 					/* mac_txd3 */
-					<0 RK_PC7 1 &pcfg_pull_none>,
+					<0 RK_PC7 1 &pcfg_pull_none_8ma>,
 					/* mac_txd2 */
-					<0 RK_PC6 1 &pcfg_pull_none>;
+					<0 RK_PC6 1 &pcfg_pull_none_8ma>;
 			};
 
 			rmiim1_pins: rmiim1-pins {
diff --git a/arch/arm64/crypto/aes-ce-ccm-core.S b/arch/arm64/crypto/aes-ce-ccm-core.S
index e3a375c4cb83..1b151442dac1 100644
--- a/arch/arm64/crypto/aes-ce-ccm-core.S
+++ b/arch/arm64/crypto/aes-ce-ccm-core.S
@@ -74,12 +74,13 @@ ENTRY(ce_aes_ccm_auth_data)
 	beq	10f
 	ext	v0.16b, v0.16b, v0.16b, #1	/* rotate out the mac bytes */
 	b	7b
-8:	mov	w7, w8
+8:	cbz	w8, 91f
+	mov	w7, w8
 	add	w8, w8, #16
 9:	ext	v1.16b, v1.16b, v1.16b, #1
 	adds	w7, w7, #1
 	bne	9b
-	eor	v0.16b, v0.16b, v1.16b
+91:	eor	v0.16b, v0.16b, v1.16b
 	st1	{v0.16b}, [x0]
 10:	str	w8, [x3]
 	ret
diff --git a/arch/arm64/crypto/aes-ce-ccm-glue.c b/arch/arm64/crypto/aes-ce-ccm-glue.c
index a1254036f2b1..ae0d26705851 100644
--- a/arch/arm64/crypto/aes-ce-ccm-glue.c
+++ b/arch/arm64/crypto/aes-ce-ccm-glue.c
@@ -123,7 +123,7 @@ static void ccm_update_mac(struct crypto_aes_ctx *key, u8 mac[], u8 const in[],
 			abytes -= added;
 		}
 
-		while (abytes > AES_BLOCK_SIZE) {
+		while (abytes >= AES_BLOCK_SIZE) {
 			__aes_arm64_encrypt(key->key_enc, mac, mac,
 					    num_rounds(key));
 			crypto_xor(mac, in, AES_BLOCK_SIZE);
@@ -137,8 +137,6 @@ static void ccm_update_mac(struct crypto_aes_ctx *key, u8 mac[], u8 const in[],
 					    num_rounds(key));
 			crypto_xor(mac, in, abytes);
 			*macp = abytes;
-		} else {
-			*macp = 0;
 		}
 	}
 }
diff --git a/arch/arm64/crypto/aes-neonbs-core.S b/arch/arm64/crypto/aes-neonbs-core.S
index ca0472500433..3b18e3e79531 100644
--- a/arch/arm64/crypto/aes-neonbs-core.S
+++ b/arch/arm64/crypto/aes-neonbs-core.S
@@ -940,7 +940,7 @@ CPU_LE(	rev		x8, x8		)
 8:	next_ctr	v0
 	cbnz		x4, 99b
 
-0:	st1		{v0.16b}, [x5]
+	st1		{v0.16b}, [x5]
 	ldp		x29, x30, [sp], #16
 	ret
 
@@ -948,6 +948,9 @@ CPU_LE(	rev		x8, x8		)
 	 * If we are handling the tail of the input (x6 != NULL), return the
 	 * final keystream block back to the caller.
 	 */
+0:	cbz		x6, 8b
+	st1		{v0.16b}, [x6]
+	b		8b
 1:	cbz		x6, 8b
 	st1		{v1.16b}, [x6]
 	b		8b
diff --git a/arch/arm64/crypto/crct10dif-ce-glue.c b/arch/arm64/crypto/crct10dif-ce-glue.c
index 96f0cae4a022..617bcfc1b080 100644
--- a/arch/arm64/crypto/crct10dif-ce-glue.c
+++ b/arch/arm64/crypto/crct10dif-ce-glue.c
@@ -36,26 +36,13 @@ static int crct10dif_update(struct shash_desc *desc, const u8 *data,
 			    unsigned int length)
 {
 	u16 *crc = shash_desc_ctx(desc);
-	unsigned int l;
 
-	if (unlikely((u64)data % CRC_T10DIF_PMULL_CHUNK_SIZE)) {
-		l = min_t(u32, length, CRC_T10DIF_PMULL_CHUNK_SIZE -
-			  ((u64)data % CRC_T10DIF_PMULL_CHUNK_SIZE));
-
-		*crc = crc_t10dif_generic(*crc, data, l);
-
-		length -= l;
-		data += l;
-	}
-
-	if (length > 0) {
-		if (may_use_simd()) {
-			kernel_neon_begin();
-			*crc = crc_t10dif_pmull(*crc, data, length);
-			kernel_neon_end();
-		} else {
-			*crc = crc_t10dif_generic(*crc, data, length);
-		}
+	if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE && may_use_simd()) {
+		kernel_neon_begin();
+		*crc = crc_t10dif_pmull(*crc, data, length);
+		kernel_neon_end();
+	} else {
+		*crc = crc_t10dif_generic(*crc, data, length);
 	}
 
 	return 0;
diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h
index 07fe2479d310..fd1e722f3821 100644
--- a/arch/arm64/include/asm/futex.h
+++ b/arch/arm64/include/asm/futex.h
@@ -30,8 +30,8 @@ do {									\
 "	prfm	pstl1strm, %2\n"					\
 "1:	ldxr	%w1, %2\n"						\
 	insn "\n"							\
-"2:	stlxr	%w3, %w0, %2\n"						\
-"	cbnz	%w3, 1b\n"						\
+"2:	stlxr	%w0, %w3, %2\n"						\
+"	cbnz	%w0, 1b\n"						\
 "	dmb	ish\n"							\
 "3:\n"									\
 "	.pushsection .fixup,\"ax\"\n"					\
@@ -57,23 +57,23 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *_uaddr)
 
 	switch (op) {
 	case FUTEX_OP_SET:
-		__futex_atomic_op("mov	%w0, %w4",
+		__futex_atomic_op("mov	%w3, %w4",
 				  ret, oldval, uaddr, tmp, oparg);
 		break;
 	case FUTEX_OP_ADD:
-		__futex_atomic_op("add	%w0, %w1, %w4",
+		__futex_atomic_op("add	%w3, %w1, %w4",
 				  ret, oldval, uaddr, tmp, oparg);
 		break;
 	case FUTEX_OP_OR:
-		__futex_atomic_op("orr	%w0, %w1, %w4",
+		__futex_atomic_op("orr	%w3, %w1, %w4",
 				  ret, oldval, uaddr, tmp, oparg);
 		break;
 	case FUTEX_OP_ANDN:
-		__futex_atomic_op("and	%w0, %w1, %w4",
+		__futex_atomic_op("and	%w3, %w1, %w4",
 				  ret, oldval, uaddr, tmp, ~oparg);
 		break;
 	case FUTEX_OP_XOR:
-		__futex_atomic_op("eor	%w0, %w1, %w4",
+		__futex_atomic_op("eor	%w3, %w1, %w4",
 				  ret, oldval, uaddr, tmp, oparg);
 		break;
 	default:
diff --git a/arch/arm64/include/asm/hardirq.h b/arch/arm64/include/asm/hardirq.h
index 1473fc2f7ab7..89691c86640a 100644
--- a/arch/arm64/include/asm/hardirq.h
+++ b/arch/arm64/include/asm/hardirq.h
@@ -17,8 +17,12 @@
 #define __ASM_HARDIRQ_H
 
 #include <linux/cache.h>
+#include <linux/percpu.h>
 #include <linux/threads.h>
+#include <asm/barrier.h>
 #include <asm/irq.h>
+#include <asm/kvm_arm.h>
+#include <asm/sysreg.h>
 
 #define NR_IPI	7
 
@@ -37,6 +41,33 @@ u64 smp_irq_stat_cpu(unsigned int cpu);
 
 #define __ARCH_IRQ_EXIT_IRQS_DISABLED	1
 
+struct nmi_ctx {
+	u64 hcr;
+};
+
+DECLARE_PER_CPU(struct nmi_ctx, nmi_contexts);
+
+#define arch_nmi_enter()							\
+	do {									\
+		if (is_kernel_in_hyp_mode()) {					\
+			struct nmi_ctx *nmi_ctx = this_cpu_ptr(&nmi_contexts);	\
+			nmi_ctx->hcr = read_sysreg(hcr_el2);			\
+			if (!(nmi_ctx->hcr & HCR_TGE)) {			\
+				write_sysreg(nmi_ctx->hcr | HCR_TGE, hcr_el2);	\
+				isb();						\
+			}							\
+		}								\
+	} while (0)
+
+#define arch_nmi_exit()								\
+	do {									\
+		if (is_kernel_in_hyp_mode()) {					\
+			struct nmi_ctx *nmi_ctx = this_cpu_ptr(&nmi_contexts);	\
+			if (!(nmi_ctx->hcr & HCR_TGE))				\
+				write_sysreg(nmi_ctx->hcr, hcr_el2);		\
+		}								\
+	} while (0)
+
 static inline void ack_bad_irq(unsigned int irq)
 {
 	extern unsigned long irq_err_count;
diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index 35b2e50f17fb..49bb9a020a09 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -106,7 +106,23 @@ static inline u64 __raw_readq(const volatile void __iomem *addr)
 }
 
 /* IO barriers */
-#define __iormb()		rmb()
+#define __iormb(v)							\
+({									\
+	unsigned long tmp;						\
+									\
+	rmb();								\
+									\
+	/*								\
+	 * Create a dummy control dependency from the IO read to any	\
+	 * later instructions. This ensures that a subsequent call to	\
+	 * udelay() will be ordered due to the ISB in get_cycles().	\
+	 */								\
+	asm volatile("eor	%0, %1, %1\n"				\
+		     "cbnz	%0, ."					\
+		     : "=r" (tmp) : "r" ((unsigned long)(v))		\
+		     : "memory");					\
+})
+
 #define __iowmb()		wmb()
 
 #define mmiowb()		do { } while (0)
@@ -131,10 +147,10 @@ static inline u64 __raw_readq(const volatile void __iomem *addr)
  * following Normal memory access. Writes are ordered relative to any prior
  * Normal memory access.
  */
-#define readb(c)		({ u8  __v = readb_relaxed(c); __iormb(); __v; })
-#define readw(c)		({ u16 __v = readw_relaxed(c); __iormb(); __v; })
-#define readl(c)		({ u32 __v = readl_relaxed(c); __iormb(); __v; })
-#define readq(c)		({ u64 __v = readq_relaxed(c); __iormb(); __v; })
+#define readb(c)		({ u8  __v = readb_relaxed(c); __iormb(__v); __v; })
+#define readw(c)		({ u16 __v = readw_relaxed(c); __iormb(__v); __v; })
+#define readl(c)		({ u32 __v = readl_relaxed(c); __iormb(__v); __v; })
+#define readq(c)		({ u64 __v = readq_relaxed(c); __iormb(__v); __v; })
 
 #define writeb(v,c)		({ __iowmb(); writeb_relaxed((v),(c)); })
 #define writew(v,c)		({ __iowmb(); writew_relaxed((v),(c)); })
@@ -185,9 +201,9 @@ extern void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size);
 /*
  * io{read,write}{16,32,64}be() macros
  */
-#define ioread16be(p)		({ __u16 __v = be16_to_cpu((__force __be16)__raw_readw(p)); __iormb(); __v; })
-#define ioread32be(p)		({ __u32 __v = be32_to_cpu((__force __be32)__raw_readl(p)); __iormb(); __v; })
-#define ioread64be(p)		({ __u64 __v = be64_to_cpu((__force __be64)__raw_readq(p)); __iormb(); __v; })
+#define ioread16be(p)		({ __u16 __v = be16_to_cpu((__force __be16)__raw_readw(p)); __iormb(__v); __v; })
+#define ioread32be(p)		({ __u32 __v = be32_to_cpu((__force __be32)__raw_readl(p)); __iormb(__v); __v; })
+#define ioread64be(p)		({ __u64 __v = be64_to_cpu((__force __be64)__raw_readq(p)); __iormb(__v); __v; })
 
 #define iowrite16be(v,p)	({ __iowmb(); __raw_writew((__force __u16)cpu_to_be16(v), p); })
 #define iowrite32be(v,p)	({ __iowmb(); __raw_writel((__force __u32)cpu_to_be32(v), p); })
diff --git a/arch/arm64/include/asm/traps.h b/arch/arm64/include/asm/traps.h
index d131501c6222..45e3da34bdc4 100644
--- a/arch/arm64/include/asm/traps.h
+++ b/arch/arm64/include/asm/traps.h
@@ -37,6 +37,12 @@ void unregister_undef_hook(struct undef_hook *hook);
 
 void arm64_notify_segfault(struct pt_regs *regs, unsigned long addr);
 
+/*
+ * Move regs->pc to next instruction and do necessary setup before it
+ * is executed.
+ */
+void arm64_skip_faulting_instruction(struct pt_regs *regs, unsigned long size);
+
 static inline int __in_irqentry_text(unsigned long ptr)
 {
 	return ptr >= (unsigned long)&__irqentry_text_start &&
diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c
index d06fbe4cd38d..a4dc115d7659 100644
--- a/arch/arm64/kernel/armv8_deprecated.c
+++ b/arch/arm64/kernel/armv8_deprecated.c
@@ -431,7 +431,7 @@ ret:
 	pr_warn_ratelimited("\"%s\" (%ld) uses obsolete SWP{B} instruction at 0x%llx\n",
 			current->comm, (unsigned long)current->pid, regs->pc);
 
-	regs->pc += 4;
+	arm64_skip_faulting_instruction(regs, 4);
 	return 0;
 
 fault:
@@ -512,7 +512,7 @@ ret:
 	pr_warn_ratelimited("\"%s\" (%ld) uses deprecated CP15 Barrier instruction at 0x%llx\n",
 			current->comm, (unsigned long)current->pid, regs->pc);
 
-	regs->pc += 4;
+	arm64_skip_faulting_instruction(regs, 4);
 	return 0;
 }
 
@@ -586,14 +586,14 @@ static int compat_setend_handler(struct pt_regs *regs, u32 big_endian)
 static int a32_setend_handler(struct pt_regs *regs, u32 instr)
 {
 	int rc = compat_setend_handler(regs, (instr >> 9) & 1);
-	regs->pc += 4;
+	arm64_skip_faulting_instruction(regs, 4);
 	return rc;
 }
 
 static int t16_setend_handler(struct pt_regs *regs, u32 instr)
 {
 	int rc = compat_setend_handler(regs, (instr >> 3) & 1);
-	regs->pc += 2;
+	arm64_skip_faulting_instruction(regs, 2);
 	return rc;
 }
 
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 003dd39225a0..29b5b72b7877 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -1398,7 +1398,7 @@ static int emulate_mrs(struct pt_regs *regs, u32 insn)
 	if (!rc) {
 		dst = aarch64_insn_decode_register(AARCH64_INSN_REGTYPE_RT, insn);
 		pt_regs_write_reg(regs, dst, val);
-		regs->pc += 4;
+		arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
 	}
 
 	return rc;
diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S
index e1be42e11ff5..5a10e3a3e843 100644
--- a/arch/arm64/kernel/entry-ftrace.S
+++ b/arch/arm64/kernel/entry-ftrace.S
@@ -79,7 +79,6 @@
 	.macro mcount_get_lr reg
 	ldr	\reg, [x29]
 	ldr	\reg, [\reg, #8]
-	mcount_adjust_addr	\reg, \reg
 	.endm
 
 	.macro mcount_get_lr_addr reg
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index ec393275ba04..1371542de0d3 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -442,8 +442,7 @@ set_hcr:
 	/* GICv3 system register access */
 	mrs	x0, id_aa64pfr0_el1
 	ubfx	x0, x0, #24, #4
-	cmp	x0, #1
-	b.ne	3f
+	cbz	x0, 3f
 
 	mrs_s	x0, SYS_ICC_SRE_EL2
 	orr	x0, x0, #ICC_SRE_EL2_SRE	// Set ICC_SRE_EL2.SRE==1
diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c
index 713561e5bcab..b91abb8f7cd4 100644
--- a/arch/arm64/kernel/irq.c
+++ b/arch/arm64/kernel/irq.c
@@ -32,6 +32,9 @@
 
 unsigned long irq_err_count;
 
+/* Only access this in an NMI enter/exit */
+DEFINE_PER_CPU(struct nmi_ctx, nmi_contexts);
+
 DEFINE_PER_CPU(unsigned long *, irq_stack_ptr);
 
 int arch_show_interrupts(struct seq_file *p, int prec)
diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c
index 2122cd187f19..470afb3a04ca 100644
--- a/arch/arm64/kernel/kgdb.c
+++ b/arch/arm64/kernel/kgdb.c
@@ -233,27 +233,33 @@ int kgdb_arch_handle_exception(int exception_vector, int signo,
 
 static int kgdb_brk_fn(struct pt_regs *regs, unsigned int esr)
 {
+	if (user_mode(regs))
+		return DBG_HOOK_ERROR;
+
 	kgdb_handle_exception(1, SIGTRAP, 0, regs);
-	return 0;
+	return DBG_HOOK_HANDLED;
 }
 NOKPROBE_SYMBOL(kgdb_brk_fn)
 
 static int kgdb_compiled_brk_fn(struct pt_regs *regs, unsigned int esr)
 {
+	if (user_mode(regs))
+		return DBG_HOOK_ERROR;
+
 	compiled_break = 1;
 	kgdb_handle_exception(1, SIGTRAP, 0, regs);
 
-	return 0;
+	return DBG_HOOK_HANDLED;
 }
 NOKPROBE_SYMBOL(kgdb_compiled_brk_fn);
 
 static int kgdb_step_brk_fn(struct pt_regs *regs, unsigned int esr)
 {
-	if (!kgdb_single_step)
+	if (user_mode(regs) || !kgdb_single_step)
 		return DBG_HOOK_ERROR;
 
 	kgdb_handle_exception(1, SIGTRAP, 0, regs);
-	return 0;
+	return DBG_HOOK_HANDLED;
 }
 NOKPROBE_SYMBOL(kgdb_step_brk_fn);
 
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index 0417c929d21a..6a6d661f38fb 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -458,6 +458,9 @@ kprobe_single_step_handler(struct pt_regs *regs, unsigned int esr)
 	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
 	int retval;
 
+	if (user_mode(regs))
+		return DBG_HOOK_ERROR;
+
 	/* return error if this is not our step */
 	retval = kprobe_ss_hit(kcb, instruction_pointer(regs));
 
@@ -474,6 +477,9 @@ kprobe_single_step_handler(struct pt_regs *regs, unsigned int esr)
 int __kprobes
 kprobe_breakpoint_handler(struct pt_regs *regs, unsigned int esr)
 {
+	if (user_mode(regs))
+		return DBG_HOOK_ERROR;
+
 	kprobe_handler(regs);
 	return DBG_HOOK_HANDLED;
 }
@@ -554,13 +560,13 @@ bool arch_within_kprobe_blacklist(unsigned long addr)
 	    addr < (unsigned long)__entry_text_end) ||
 	    (addr >= (unsigned long)__idmap_text_start &&
 	    addr < (unsigned long)__idmap_text_end) ||
+	    (addr >= (unsigned long)__hyp_text_start &&
+	    addr < (unsigned long)__hyp_text_end) ||
 	    !!search_exception_tables(addr))
 		return true;
 
 	if (!is_kernel_in_hyp_mode()) {
-		if ((addr >= (unsigned long)__hyp_text_start &&
-		    addr < (unsigned long)__hyp_text_end) ||
-		    (addr >= (unsigned long)__hyp_idmap_text_start &&
+		if ((addr >= (unsigned long)__hyp_idmap_text_start &&
 		    addr < (unsigned long)__hyp_idmap_text_end))
 			return true;
 	}
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 4fc0e958770b..74259ae9c7f2 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -145,10 +145,16 @@ static void dump_instr(const char *lvl, struct pt_regs *regs)
 void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
 {
 	struct stackframe frame;
-	int skip;
+	int skip = 0;
 
 	pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk);
 
+	if (regs) {
+		if (user_mode(regs))
+			return;
+		skip = 1;
+	}
+
 	if (!tsk)
 		tsk = current;
 
@@ -169,7 +175,6 @@ void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
 	frame.graph = tsk->curr_ret_stack;
 #endif
 
-	skip = !!regs;
 	printk("Call trace:\n");
 	while (1) {
 		unsigned long stack;
@@ -232,15 +237,13 @@ static int __die(const char *str, int err, struct pt_regs *regs)
 		return ret;
 
 	print_modules();
-	__show_regs(regs);
 	pr_emerg("Process %.*s (pid: %d, stack limit = 0x%p)\n",
 		 TASK_COMM_LEN, tsk->comm, task_pid_nr(tsk),
 		 end_of_stack(tsk));
+	show_regs(regs);
 
-	if (!user_mode(regs)) {
-		dump_backtrace(regs, tsk);
+	if (!user_mode(regs))
 		dump_instr(KERN_EMERG, regs);
-	}
 
 	return ret;
 }
@@ -293,6 +296,18 @@ void arm64_notify_die(const char *str, struct pt_regs *regs,
 	}
 }
 
+void arm64_skip_faulting_instruction(struct pt_regs *regs, unsigned long size)
+{
+	regs->pc += size;
+
+	/*
+	 * If we were single stepping, we want to get the step exception after
+	 * we return from the trap.
+	 */
+	if (user_mode(regs))
+		user_fastforward_single_step(current);
+}
+
 static LIST_HEAD(undef_hook);
 static DEFINE_RAW_SPINLOCK(undef_lock);
 
@@ -480,7 +495,7 @@ static void user_cache_maint_handler(unsigned int esr, struct pt_regs *regs)
 	if (ret)
 		arm64_notify_segfault(regs, address);
 	else
-		regs->pc += 4;
+		arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
 }
 
 static void ctr_read_handler(unsigned int esr, struct pt_regs *regs)
@@ -490,7 +505,7 @@ static void ctr_read_handler(unsigned int esr, struct pt_regs *regs)
 
 	pt_regs_write_reg(regs, rt, val);
 
-	regs->pc += 4;
+	arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
 }
 
 static void cntvct_read_handler(unsigned int esr, struct pt_regs *regs)
@@ -498,7 +513,7 @@ static void cntvct_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, arch_counter_get_cntvct());
-	regs->pc += 4;
+	arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
 }
 
 static void cntfrq_read_handler(unsigned int esr, struct pt_regs *regs)
@@ -506,7 +521,7 @@ 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, arch_timer_get_rate());
-	regs->pc += 4;
+	arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
 }
 
 struct sys64_hook {
@@ -753,7 +768,7 @@ static int bug_handler(struct pt_regs *regs, unsigned int esr)
 	}
 
 	/* If thread survives, skip over the BUG instruction and continue: */
-	regs->pc += AARCH64_INSN_SIZE;	/* skip BRK and resume */
+	arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
 	return DBG_HOOK_HANDLED;
 }
 
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index a74311beda35..c1c5a57249d2 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -95,16 +95,33 @@ int kvm_arch_dev_ioctl_check_extension(struct kvm *kvm, long ext)
  * This function finds the right table above and sets the registers on
  * the virtual CPU struct to their architecturally defined reset
  * values.
+ *
+ * Note: This function can be called from two paths: The KVM_ARM_VCPU_INIT
+ * ioctl or as part of handling a request issued by another VCPU in the PSCI
+ * handling code.  In the first case, the VCPU will not be loaded, and in the
+ * second case the VCPU will be loaded.  Because this function operates purely
+ * on the memory-backed valus of system registers, we want to do a full put if
+ * we were loaded (handling a request) and load the values back at the end of
+ * the function.  Otherwise we leave the state alone.  In both cases, we
+ * disable preemption around the vcpu reset as we would otherwise race with
+ * preempt notifiers which also call put/load.
  */
 int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 {
 	const struct kvm_regs *cpu_reset;
+	int ret = -EINVAL;
+	bool loaded;
+
+	preempt_disable();
+	loaded = (vcpu->cpu != -1);
+	if (loaded)
+		kvm_arch_vcpu_put(vcpu);
 
 	switch (vcpu->arch.target) {
 	default:
 		if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) {
 			if (!cpu_has_32bit_el1())
-				return -EINVAL;
+				goto out;
 			cpu_reset = &default_regs_reset32;
 		} else {
 			cpu_reset = &default_regs_reset;
@@ -127,5 +144,10 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 		vcpu->arch.workaround_flags |= VCPU_WORKAROUND_2_FLAG;
 
 	/* Reset timer */
-	return kvm_timer_vcpu_reset(vcpu);
+	ret = kvm_timer_vcpu_reset(vcpu);
+out:
+	if (loaded)
+		kvm_arch_vcpu_load(vcpu, smp_processor_id());
+	preempt_enable();
+	return ret;
 }
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 2e070d3baf9f..cfbf7bd0dfba 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1079,7 +1079,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 
 	{ SYS_DESC(SYS_DACR32_EL2), NULL, reset_unknown, DACR32_EL2 },
 	{ SYS_DESC(SYS_IFSR32_EL2), NULL, reset_unknown, IFSR32_EL2 },
-	{ SYS_DESC(SYS_FPEXC32_EL2), NULL, reset_val, FPEXC32_EL2, 0x70 },
+	{ SYS_DESC(SYS_FPEXC32_EL2), NULL, reset_val, FPEXC32_EL2, 0x700 },
 };
 
 static bool trap_dbgidr(struct kvm_vcpu *vcpu,
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 5edb706aacb0..465b90d7abf2 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -834,11 +834,12 @@ void __init hook_debug_fault_code(int nr,
 	debug_fault_info[nr].name	= name;
 }
 
-asmlinkage int __exception do_debug_exception(unsigned long addr,
+asmlinkage int __exception do_debug_exception(unsigned long addr_if_watchpoint,
 					      unsigned int esr,
 					      struct pt_regs *regs)
 {
 	const struct fault_info *inf = debug_fault_info + DBG_ESR_EVT(esr);
+	unsigned long pc = instruction_pointer(regs);
 	struct siginfo info;
 	int rv;
 
@@ -849,19 +850,19 @@ asmlinkage int __exception do_debug_exception(unsigned long addr,
 	if (interrupts_enabled(regs))
 		trace_hardirqs_off();
 
-	if (user_mode(regs) && instruction_pointer(regs) > TASK_SIZE)
+	if (user_mode(regs) && pc > TASK_SIZE)
 		arm64_apply_bp_hardening();
 
-	if (!inf->fn(addr, esr, regs)) {
+	if (!inf->fn(addr_if_watchpoint, esr, regs)) {
 		rv = 1;
 	} else {
 		pr_alert("Unhandled debug exception: %s (0x%08x) at 0x%016lx\n",
-			 inf->name, esr, addr);
+			 inf->name, esr, pc);
 
 		info.si_signo = inf->sig;
 		info.si_errno = 0;
 		info.si_code  = inf->code;
-		info.si_addr  = (void __user *)addr;
+		info.si_addr  = (void __user *)pc;
 		arm64_notify_die("", regs, &info, 0);
 		rv = 0;
 	}
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index caa295cd5d09..9e6c822d458d 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -447,7 +447,7 @@ void __init arm64_memblock_init(void)
 		 * memory spans, randomize the linear region as well.
 		 */
 		if (memstart_offset_seed > 0 && range >= ARM64_MEMSTART_ALIGN) {
-			range = range / ARM64_MEMSTART_ALIGN + 1;
+			range /= ARM64_MEMSTART_ALIGN;
 			memstart_addr -= ARM64_MEMSTART_ALIGN *
 					 ((range * memstart_offset_seed) >> 16);
 		}