Merge tag 'v4.4-rc6' into devel

Linux 4.4-rc6

30 files changed, 398 insertions, 275 deletions

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 9ac16a4..871f217 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -49,7 +49,7 @@ config ARM64
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ARCH_BITREVERSE
 	select HAVE_ARCH_JUMP_LABEL
-	select HAVE_ARCH_KASAN if SPARSEMEM_VMEMMAP
+	select HAVE_ARCH_KASAN if SPARSEMEM_VMEMMAP && !(ARM64_16K_PAGES && ARM64_VA_BITS_48)
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_TRACEHOOK
@@ -316,6 +316,27 @@ config ARM64_ERRATUM_832075
 
 	  If unsure, say Y.
 
+config ARM64_ERRATUM_834220
+	bool "Cortex-A57: 834220: Stage 2 translation fault might be incorrectly reported in presence of a Stage 1 fault"
+	depends on KVM
+	default y
+	help
+	  This option adds an alternative code sequence to work around ARM
+	  erratum 834220 on Cortex-A57 parts up to r1p2.
+
+	  Affected Cortex-A57 parts might report a Stage 2 translation
+	  fault as the result of a Stage 1 fault for load crossing a
+	  page boundary when there is a permission or device memory
+	  alignment fault at Stage 1 and a translation fault at Stage 2.
+
+	  The workaround is to verify that the Stage 1 translation
+	  doesn't generate a fault before handling the Stage 2 fault.
+	  Please note that this does not necessarily enable the workaround,
+	  as it depends on the alternative framework, which will only patch
+	  the kernel if an affected CPU is detected.
+
+	  If unsure, say Y.
+
 config ARM64_ERRATUM_845719
 	bool "Cortex-A53: 845719: a load might read incorrect data"
 	depends on COMPAT
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi
index e81cd48..925552e 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi
@@ -269,6 +269,7 @@
 			clock-frequency = <0>;	/* Updated by bootloader */
 			voltage-ranges = <1800 1800 3300 3300>;
 			sdhci,auto-cmd12;
+			little-endian;
 			bus-width = <4>;
 		};
 
@@ -277,6 +278,7 @@
 			reg = <0x0 0x2300000 0x0 0x10000>;
 			interrupts = <0 36 0x4>; /* Level high type */
 			gpio-controller;
+			little-endian;
 			#gpio-cells = <2>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
@@ -287,6 +289,7 @@
 			reg = <0x0 0x2310000 0x0 0x10000>;
 			interrupts = <0 36 0x4>; /* Level high type */
 			gpio-controller;
+			little-endian;
 			#gpio-cells = <2>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
@@ -297,6 +300,7 @@
 			reg = <0x0 0x2320000 0x0 0x10000>;
 			interrupts = <0 37 0x4>; /* Level high type */
 			gpio-controller;
+			little-endian;
 			#gpio-cells = <2>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
@@ -307,6 +311,7 @@
 			reg = <0x0 0x2330000 0x0 0x10000>;
 			interrupts = <0 37 0x4>; /* Level high type */
 			gpio-controller;
+			little-endian;
 			#gpio-cells = <2>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
diff --git a/arch/arm64/crypto/aes-ce-cipher.c b/arch/arm64/crypto/aes-ce-cipher.c
index ce47792..f7bd9bf 100644
--- a/arch/arm64/crypto/aes-ce-cipher.c
+++ b/arch/arm64/crypto/aes-ce-cipher.c
@@ -237,7 +237,7 @@ EXPORT_SYMBOL(ce_aes_setkey);
 static struct crypto_alg aes_alg = {
 	.cra_name		= "aes",
 	.cra_driver_name	= "aes-ce",
-	.cra_priority		= 300,
+	.cra_priority		= 250,
 	.cra_flags		= CRYPTO_ALG_TYPE_CIPHER,
 	.cra_blocksize		= AES_BLOCK_SIZE,
 	.cra_ctxsize		= sizeof(struct crypto_aes_ctx),
diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h
index 030cdcb..2731d3b 100644
--- a/arch/arm64/include/asm/arch_gicv3.h
+++ b/arch/arm64/include/asm/arch_gicv3.h
@@ -77,6 +77,7 @@
 #ifndef __ASSEMBLY__
 
 #include <linux/stringify.h>
+#include <asm/barrier.h>
 
 /*
  * Low-level accessors
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index 624f967..9622eb4 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -64,27 +64,31 @@ do {									\
 
 #define smp_load_acquire(p)						\
 ({									\
-	typeof(*p) ___p1;						\
+	union { typeof(*p) __val; char __c[1]; } __u;			\
 	compiletime_assert_atomic_type(*p);				\
 	switch (sizeof(*p)) {						\
 	case 1:								\
 		asm volatile ("ldarb %w0, %1"				\
-			: "=r" (___p1) : "Q" (*p) : "memory");		\
+			: "=r" (*(__u8 *)__u.__c)			\
+			: "Q" (*p) : "memory");				\
 		break;							\
 	case 2:								\
 		asm volatile ("ldarh %w0, %1"				\
-			: "=r" (___p1) : "Q" (*p) : "memory");		\
+			: "=r" (*(__u16 *)__u.__c)			\
+			: "Q" (*p) : "memory");				\
 		break;							\
 	case 4:								\
 		asm volatile ("ldar %w0, %1"				\
-			: "=r" (___p1) : "Q" (*p) : "memory");		\
+			: "=r" (*(__u32 *)__u.__c)			\
+			: "Q" (*p) : "memory");				\
 		break;							\
 	case 8:								\
 		asm volatile ("ldar %0, %1"				\
-			: "=r" (___p1) : "Q" (*p) : "memory");		\
+			: "=r" (*(__u64 *)__u.__c)			\
+			: "Q" (*p) : "memory");				\
 		break;							\
 	}								\
-	___p1;								\
+	__u.__val;							\
 })
 
 #define read_barrier_depends()		do { } while(0)
diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h
index 7fbed69..eb8432b 100644
--- a/arch/arm64/include/asm/compat.h
+++ b/arch/arm64/include/asm/compat.h
@@ -23,7 +23,6 @@
  */
 #include <linux/types.h>
 #include <linux/sched.h>
-#include <linux/ptrace.h>
 
 #define COMPAT_USER_HZ		100
 #ifdef __AARCH64EB__
@@ -234,7 +233,7 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr)
 	return (u32)(unsigned long)uptr;
 }
 
-#define compat_user_stack_pointer() (user_stack_pointer(current_pt_regs()))
+#define compat_user_stack_pointer() (user_stack_pointer(task_pt_regs(current)))
 
 static inline void __user *arch_compat_alloc_user_space(long len)
 {
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 11d5bb0f..8f271b8 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -29,8 +29,9 @@
 #define ARM64_HAS_PAN				4
 #define ARM64_HAS_LSE_ATOMICS			5
 #define ARM64_WORKAROUND_CAVIUM_23154		6
+#define ARM64_WORKAROUND_834220			7
 
-#define ARM64_NCAPS				7
+#define ARM64_NCAPS				8
 
 #ifndef __ASSEMBLY__
 
@@ -46,8 +47,12 @@ enum ftr_type {
 #define FTR_STRICT	true	/* SANITY check strict matching required */
 #define FTR_NONSTRICT	false	/* SANITY check ignored */
 
+#define FTR_SIGNED	true	/* Value should be treated as signed */
+#define FTR_UNSIGNED	false	/* Value should be treated as unsigned */
+
 struct arm64_ftr_bits {
-	bool		strict;	  /* CPU Sanity check: strict matching required ? */
+	bool		sign;	/* Value is signed ? */
+	bool		strict;	/* CPU Sanity check: strict matching required ? */
 	enum ftr_type	type;
 	u8		shift;
 	u8		width;
@@ -123,6 +128,18 @@ cpuid_feature_extract_field(u64 features, int field)
 	return cpuid_feature_extract_field_width(features, field, 4);
 }
 
+static inline unsigned int __attribute_const__
+cpuid_feature_extract_unsigned_field_width(u64 features, int field, int width)
+{
+	return (u64)(features << (64 - width - field)) >> (64 - width);
+}
+
+static inline unsigned int __attribute_const__
+cpuid_feature_extract_unsigned_field(u64 features, int field)
+{
+	return cpuid_feature_extract_unsigned_field_width(features, field, 4);
+}
+
 static inline u64 arm64_ftr_mask(struct arm64_ftr_bits *ftrp)
 {
 	return (u64)GENMASK(ftrp->shift + ftrp->width - 1, ftrp->shift);
@@ -130,7 +147,9 @@ static inline u64 arm64_ftr_mask(struct arm64_ftr_bits *ftrp)
 
 static inline s64 arm64_ftr_value(struct arm64_ftr_bits *ftrp, u64 val)
 {
-	return cpuid_feature_extract_field_width(val, ftrp->shift, ftrp->width);
+	return ftrp->sign ?
+		cpuid_feature_extract_field_width(val, ftrp->shift, ftrp->width) :
+		cpuid_feature_extract_unsigned_field_width(val, ftrp->shift, ftrp->width);
 }
 
 static inline bool id_aa64mmfr0_mixed_endian_el0(u64 mmfr0)
diff --git a/arch/arm64/include/asm/dma-mapping.h b/arch/arm64/include/asm/dma-mapping.h
index 54d0ead..61e08f3 100644
--- a/arch/arm64/include/asm/dma-mapping.h
+++ b/arch/arm64/include/asm/dma-mapping.h
@@ -18,7 +18,6 @@
 
 #ifdef __KERNEL__
 
-#include <linux/acpi.h>
 #include <linux/types.h>
 #include <linux/vmalloc.h>
 
@@ -26,22 +25,16 @@
 #include <asm/xen/hypervisor.h>
 
 #define DMA_ERROR_CODE	(~(dma_addr_t)0)
-extern struct dma_map_ops *dma_ops;
 extern struct dma_map_ops dummy_dma_ops;
 
 static inline struct dma_map_ops *__generic_dma_ops(struct device *dev)
 {
-	if (unlikely(!dev))
-		return dma_ops;
-	else if (dev->archdata.dma_ops)
+	if (dev && dev->archdata.dma_ops)
 		return dev->archdata.dma_ops;
-	else if (acpi_disabled)
-		return dma_ops;
 
 	/*
-	 * When ACPI is enabled, if arch_set_dma_ops is not called,
-	 * we will disable device DMA capability by setting it
-	 * to dummy_dma_ops.
+	 * We expect no ISA devices, and all other DMA masters are expected to
+	 * have someone call arch_setup_dma_ops at device creation time.
 	 */
 	return &dummy_dma_ops;
 }
diff --git a/arch/arm64/include/asm/hw_breakpoint.h b/arch/arm64/include/asm/hw_breakpoint.h
index e54415e..9732908 100644
--- a/arch/arm64/include/asm/hw_breakpoint.h
+++ b/arch/arm64/include/asm/hw_breakpoint.h
@@ -138,16 +138,18 @@ extern struct pmu perf_ops_bp;
 /* Determine number of BRP registers available. */
 static inline int get_num_brps(void)
 {
+	u64 dfr0 = read_system_reg(SYS_ID_AA64DFR0_EL1);
 	return 1 +
-		cpuid_feature_extract_field(read_system_reg(SYS_ID_AA64DFR0_EL1),
+		cpuid_feature_extract_unsigned_field(dfr0,
 						ID_AA64DFR0_BRPS_SHIFT);
 }
 
 /* Determine number of WRP registers available. */
 static inline int get_num_wrps(void)
 {
+	u64 dfr0 = read_system_reg(SYS_ID_AA64DFR0_EL1);
 	return 1 +
-		cpuid_feature_extract_field(read_system_reg(SYS_ID_AA64DFR0_EL1),
+		cpuid_feature_extract_unsigned_field(dfr0,
 						ID_AA64DFR0_WRPS_SHIFT);
 }
 
diff --git a/arch/arm64/include/asm/irq.h b/arch/arm64/include/asm/irq.h
index 23eb450..8e8d306 100644
--- a/arch/arm64/include/asm/irq.h
+++ b/arch/arm64/include/asm/irq.h
@@ -7,4 +7,9 @@ struct pt_regs;
 
 extern void set_handle_irq(void (*handle_irq)(struct pt_regs *));
 
+static inline int nr_legacy_irqs(void)
+{
+	return 0;
+}
+
 #endif
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 17e92f0..25a4021 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -99,12 +99,22 @@ static inline void vcpu_set_thumb(struct kvm_vcpu *vcpu)
 	*vcpu_cpsr(vcpu) |= COMPAT_PSR_T_BIT;
 }
 
-static inline unsigned long *vcpu_reg(const struct kvm_vcpu *vcpu, u8 reg_num)
+/*
+ * vcpu_get_reg and vcpu_set_reg should always be passed a register number
+ * coming from a read of ESR_EL2. Otherwise, it may give the wrong result on
+ * AArch32 with banked registers.
+ */
+static inline unsigned long vcpu_get_reg(const struct kvm_vcpu *vcpu,
+					 u8 reg_num)
 {
-	if (vcpu_mode_is_32bit(vcpu))
-		return vcpu_reg32(vcpu, reg_num);
+	return (reg_num == 31) ? 0 : vcpu_gp_regs(vcpu)->regs.regs[reg_num];
+}
 
-	return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.regs[reg_num];
+static inline void vcpu_set_reg(struct kvm_vcpu *vcpu, u8 reg_num,
+				unsigned long val)
+{
+	if (reg_num != 31)
+		vcpu_gp_regs(vcpu)->regs.regs[reg_num] = val;
 }
 
 /* Get vcpu SPSR for current mode */
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index c0e8789..2416578 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -101,7 +101,7 @@ static inline void cpu_set_default_tcr_t0sz(void)
 #define destroy_context(mm)		do { } while(0)
 void check_and_switch_context(struct mm_struct *mm, unsigned int cpu);
 
-#define init_new_context(tsk,mm)	({ atomic64_set(&mm->context.id, 0); 0; })
+#define init_new_context(tsk,mm)	({ atomic64_set(&(mm)->context.id, 0); 0; })
 
 /*
  * This is called when "tsk" is about to enter lazy TLB mode.
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 9819a94..63f52b5 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -81,6 +81,7 @@ extern void __pgd_error(const char *file, int line, unsigned long val);
 
 #define PAGE_KERNEL		__pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE)
 #define PAGE_KERNEL_RO		__pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_RDONLY)
+#define PAGE_KERNEL_ROX	__pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_RDONLY)
 #define PAGE_KERNEL_EXEC	__pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE)
 #define PAGE_KERNEL_EXEC_CONT	__pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_CONT)
 
@@ -275,10 +276,14 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 	 * hardware updates of the pte (ptep_set_access_flags safely changes
 	 * valid ptes without going through an invalid entry).
 	 */
-	if (IS_ENABLED(CONFIG_DEBUG_VM) && IS_ENABLED(CONFIG_ARM64_HW_AFDBM) &&
-	    pte_valid(*ptep)) {
-		BUG_ON(!pte_young(pte));
-		BUG_ON(pte_write(*ptep) && !pte_dirty(pte));
+	if (IS_ENABLED(CONFIG_ARM64_HW_AFDBM) &&
+	    pte_valid(*ptep) && pte_valid(pte)) {
+		VM_WARN_ONCE(!pte_young(pte),
+			     "%s: racy access flag clearing: 0x%016llx -> 0x%016llx",
+			     __func__, pte_val(*ptep), pte_val(pte));
+		VM_WARN_ONCE(pte_write(*ptep) && !pte_dirty(pte),
+			     "%s: racy dirty state clearing: 0x%016llx -> 0x%016llx",
+			     __func__, pte_val(*ptep), pte_val(pte));
 	}
 
 	set_pte(ptep, pte);
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 24926f2..feb6b4e 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -75,6 +75,15 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 			   (1 << MIDR_VARIANT_SHIFT) | 2),
 	},
 #endif
+#ifdef CONFIG_ARM64_ERRATUM_834220
+	{
+	/* Cortex-A57 r0p0 - r1p2 */
+		.desc = "ARM erratum 834220",
+		.capability = ARM64_WORKAROUND_834220,
+		MIDR_RANGE(MIDR_CORTEX_A57, 0x00,
+			   (1 << MIDR_VARIANT_SHIFT) | 2),
+	},
+#endif
 #ifdef CONFIG_ARM64_ERRATUM_845719
 	{
 	/* Cortex-A53 r0p[01234] */
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index c8cf892..0669c63 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -44,8 +44,9 @@ unsigned int compat_elf_hwcap2 __read_mostly;
 
 DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS);
 
-#define ARM64_FTR_BITS(STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) \
+#define __ARM64_FTR_BITS(SIGNED, STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) \
 	{						\
+		.sign = SIGNED,				\
 		.strict = STRICT,			\
 		.type = TYPE,				\
 		.shift = SHIFT,				\
@@ -53,6 +54,14 @@ DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS);
 		.safe_val = SAFE_VAL,			\
 	}
 
+/* Define a feature with signed values */
+#define ARM64_FTR_BITS(STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) \
+	__ARM64_FTR_BITS(FTR_SIGNED, STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL)
+
+/* Define a feature with unsigned value */
+#define U_ARM64_FTR_BITS(STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) \
+	__ARM64_FTR_BITS(FTR_UNSIGNED, STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL)
+
 #define ARM64_FTR_END					\
 	{						\
 		.width = 0,				\
@@ -99,7 +108,7 @@ static struct arm64_ftr_bits ftr_id_aa64mmfr0[] = {
 	 * Differing PARange is fine as long as all peripherals and memory are mapped
 	 * within the minimum PARange of all CPUs
 	 */
-	ARM64_FTR_BITS(FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_PARANGE_SHIFT, 4, 0),
+	U_ARM64_FTR_BITS(FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_PARANGE_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
@@ -115,18 +124,18 @@ static struct arm64_ftr_bits ftr_id_aa64mmfr1[] = {
 };
 
 static struct arm64_ftr_bits ftr_ctr[] = {
-	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 31, 1, 1),	/* RAO */
+	U_ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 31, 1, 1),	/* RAO */
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 28, 3, 0),
-	ARM64_FTR_BITS(FTR_STRICT, FTR_HIGHER_SAFE, 24, 4, 0),	/* CWG */
-	ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0),	/* ERG */
-	ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 1),	/* DminLine */
+	U_ARM64_FTR_BITS(FTR_STRICT, FTR_HIGHER_SAFE, 24, 4, 0),	/* CWG */
+	U_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0),	/* ERG */
+	U_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 1),	/* DminLine */
 	/*
 	 * Linux can handle differing I-cache policies. Userspace JITs will
 	 * make use of *minLine
 	 */
-	ARM64_FTR_BITS(FTR_NONSTRICT, FTR_EXACT, 14, 2, 0),	/* L1Ip */
+	U_ARM64_FTR_BITS(FTR_NONSTRICT, FTR_EXACT, 14, 2, 0),	/* L1Ip */
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 4, 10, 0),	/* RAZ */
-	ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0),	/* IminLine */
+	U_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0),	/* IminLine */
 	ARM64_FTR_END,
 };
 
@@ -144,12 +153,12 @@ static struct arm64_ftr_bits ftr_id_mmfr0[] = {
 
 static struct arm64_ftr_bits ftr_id_aa64dfr0[] = {
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 32, 32, 0),
-	ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_CTX_CMPS_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_WRPS_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_BRPS_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64DFR0_PMUVER_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64DFR0_TRACEVER_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64DFR0_DEBUGVER_SHIFT, 4, 0x6),
+	U_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_CTX_CMPS_SHIFT, 4, 0),
+	U_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_WRPS_SHIFT, 4, 0),
+	U_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_BRPS_SHIFT, 4, 0),
+	U_ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64DFR0_PMUVER_SHIFT, 4, 0),
+	U_ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64DFR0_TRACEVER_SHIFT, 4, 0),
+	U_ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64DFR0_DEBUGVER_SHIFT, 4, 0x6),
 	ARM64_FTR_END,
 };
 
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 706679d..212ae63 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -30,6 +30,7 @@
 #include <linux/seq_file.h>
 #include <linux/sched.h>
 #include <linux/smp.h>
+#include <linux/delay.h>
 
 /*
  * In case the boot CPU is hotpluggable, we record its initial state and
@@ -112,6 +113,10 @@ static int c_show(struct seq_file *m, void *v)
 		 */
 		seq_printf(m, "processor\t: %d\n", i);
 
+		seq_printf(m, "BogoMIPS\t: %lu.%02lu\n",
+			   loops_per_jiffy / (500000UL/HZ),
+			   loops_per_jiffy / (5000UL/HZ) % 100);
+
 		/*
 		 * Dump out the common processor features in a single line.
 		 * Userspace should read the hwcaps with getauxval(AT_HWCAP)
diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c
index de46b50..4eeb171 100644
--- a/arch/arm64/kernel/efi.c
+++ b/arch/arm64/kernel/efi.c
@@ -127,7 +127,11 @@ static int __init uefi_init(void)
 	table_size = sizeof(efi_config_table_64_t) * efi.systab->nr_tables;
 	config_tables = early_memremap(efi_to_phys(efi.systab->tables),
 				       table_size);
-
+	if (config_tables == NULL) {
+		pr_warn("Unable to map EFI config table array.\n");
+		retval = -ENOMEM;
+		goto out;
+	}
 	retval = efi_config_parse_tables(config_tables, efi.systab->nr_tables,
 					 sizeof(efi_config_table_64_t), NULL);
 
@@ -209,6 +213,14 @@ void __init efi_init(void)
 			 PAGE_ALIGN(params.mmap_size + (params.mmap & ~PAGE_MASK)));
 	memmap.phys_map = params.mmap;
 	memmap.map = early_memremap(params.mmap, params.mmap_size);
+	if (memmap.map == NULL) {
+		/*
+		* If we are booting via UEFI, the UEFI memory map is the only
+		* description of memory we have, so there is little point in
+		* proceeding if we cannot access it.
+		*/
+		panic("Unable to map EFI memory map.\n");
+	}
 	memmap.map_end = memmap.map + params.mmap_size;
 	memmap.desc_size = params.desc_size;
 	memmap.desc_version = params.desc_ver;
@@ -224,8 +236,9 @@ static bool __init efi_virtmap_init(void)
 {
 	efi_memory_desc_t *md;
 
+	init_new_context(NULL, &efi_mm);
+
 	for_each_efi_memory_desc(&memmap, md) {
-		u64 paddr, npages, size;
 		pgprot_t prot;
 
 		if (!(md->attribute & EFI_MEMORY_RUNTIME))
@@ -233,11 +246,6 @@ static bool __init efi_virtmap_init(void)
 		if (md->virt_addr == 0)
 			return false;
 
-		paddr = md->phys_addr;
-		npages = md->num_pages;
-		memrange_efi_to_native(&paddr, &npages);
-		size = npages << PAGE_SHIFT;
-
 		pr_info("  EFI remap 0x%016llx => %p\n",
 			md->phys_addr, (void *)md->virt_addr);
 
@@ -254,7 +262,9 @@ static bool __init efi_virtmap_init(void)
 		else
 			prot = PAGE_KERNEL;
 
-		create_pgd_mapping(&efi_mm, paddr, md->virt_addr, size, prot);
+		create_pgd_mapping(&efi_mm, md->phys_addr, md->virt_addr,
+				   md->num_pages << EFI_PAGE_SHIFT, 
+				   __pgprot(pgprot_val(prot) | PTE_NG));
 	}
 	return true;
 }
@@ -270,12 +280,12 @@ static int __init arm64_enable_runtime_services(void)
 
 	if (!efi_enabled(EFI_BOOT)) {
 		pr_info("EFI services will not be available.\n");
-		return -1;
+		return 0;
 	}
 
 	if (efi_runtime_disabled()) {
 		pr_info("EFI runtime services will be disabled.\n");
-		return -1;
+		return 0;
 	}
 
 	pr_info("Remapping and enabling EFI services.\n");
@@ -285,7 +295,7 @@ static int __init arm64_enable_runtime_services(void)
 						   mapsize);
 	if (!memmap.map) {
 		pr_err("Failed to remap EFI memory map\n");
-		return -1;
+		return -ENOMEM;
 	}
 	memmap.map_end = memmap.map + mapsize;
 	efi.memmap = &memmap;
@@ -294,13 +304,13 @@ static int __init arm64_enable_runtime_services(void)
 						   sizeof(efi_system_table_t));
 	if (!efi.systab) {
 		pr_err("Failed to remap EFI System Table\n");
-		return -1;
+		return -ENOMEM;
 	}
 	set_bit(EFI_SYSTEM_TABLES, &efi.flags);
 
 	if (!efi_virtmap_init()) {
 		pr_err("No UEFI virtual mapping was installed -- runtime services will not be available\n");
-		return -1;
+		return -ENOMEM;
 	}
 
 	/* Set up runtime services function pointers */
@@ -329,14 +339,7 @@ core_initcall(arm64_dmi_init);
 
 static void efi_set_pgd(struct mm_struct *mm)
 {
-	if (mm == &init_mm)
-		cpu_set_reserved_ttbr0();
-	else
-		cpu_switch_mm(mm->pgd, mm);
-
-	local_flush_tlb_all();
-	if (icache_is_aivivt())
-		__local_flush_icache_all();
+	switch_mm(NULL, mm, NULL);
 }
 
 void efi_virtmap_load(void)
diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c
index fce95e1..1095aa4 100644
--- a/arch/arm64/kernel/suspend.c
+++ b/arch/arm64/kernel/suspend.c
@@ -1,3 +1,4 @@
+#include <linux/ftrace.h>
 #include <linux/percpu.h>
 #include <linux/slab.h>
 #include <asm/cacheflush.h>
@@ -71,6 +72,13 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 	local_dbg_save(flags);
 
 	/*
+	 * Function graph tracer state gets incosistent when the kernel
+	 * calls functions that never return (aka suspend finishers) hence
+	 * disable graph tracing during their execution.
+	 */
+	pause_graph_tracing();
+
+	/*
 	 * mm context saved on the stack, it will be restored when
 	 * the cpu comes out of reset through the identity mapped
 	 * page tables, so that the thread address space is properly
@@ -111,6 +119,8 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 			hw_breakpoint_restore(NULL);
 	}
 
+	unpause_graph_tracing();
+
 	/*
 	 * Restore pstate flags. OS lock and mdscr have been already
 	 * restored, so from this point onwards, debugging is fully
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 1ee2c39..71426a7 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -5,6 +5,7 @@
  */
 
 #include <asm-generic/vmlinux.lds.h>
+#include <asm/cache.h>
 #include <asm/kernel-pgtable.h>
 #include <asm/thread_info.h>
 #include <asm/memory.h>
@@ -140,7 +141,7 @@ SECTIONS
 		ARM_EXIT_KEEP(EXIT_DATA)
 	}
 
-	PERCPU_SECTION(64)
+	PERCPU_SECTION(L1_CACHE_BYTES)
 
 	. = ALIGN(PAGE_SIZE);
 	__init_end = .;
@@ -158,7 +159,7 @@ SECTIONS
 	. = ALIGN(PAGE_SIZE);
 	_data = .;
 	_sdata = .;
-	RW_DATA_SECTION(64, PAGE_SIZE, THREAD_SIZE)
+	RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
 	PECOFF_EDATA_PADDING
 	_edata = .;
 
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 68a0759..15f0477 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -37,7 +37,7 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
 	int ret;
 
-	trace_kvm_hvc_arm64(*vcpu_pc(vcpu), *vcpu_reg(vcpu, 0),
+	trace_kvm_hvc_arm64(*vcpu_pc(vcpu), vcpu_get_reg(vcpu, 0),
 			    kvm_vcpu_hvc_get_imm(vcpu));
 
 	ret = kvm_psci_call(vcpu);
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index 1599701..86c2898 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -864,6 +864,10 @@ ENTRY(__kvm_flush_vm_context)
 ENDPROC(__kvm_flush_vm_context)
 
 __kvm_hyp_panic:
+	// Stash PAR_EL1 before corrupting it in __restore_sysregs
+	mrs	x0, par_el1
+	push	x0, xzr
+
 	// Guess the context by looking at VTTBR:
 	// If zero, then we're already a host.
 	// Otherwise restore a minimal host context before panicing.
@@ -898,7 +902,7 @@ __kvm_hyp_panic:
 	mrs	x3, esr_el2
 	mrs	x4, far_el2
 	mrs	x5, hpfar_el2
-	mrs	x6, par_el1
+	pop	x6, xzr		// active context PAR_EL1
 	mrs	x7, tpidr_el2
 
 	mov	lr, #(PSR_F_BIT | PSR_I_BIT | PSR_A_BIT | PSR_D_BIT |\
@@ -914,7 +918,7 @@ __kvm_hyp_panic:
 ENDPROC(__kvm_hyp_panic)
 
 __hyp_panic_str:
-	.ascii	"HYP panic:\nPS:%08x PC:%p ESR:%p\nFAR:%p HPFAR:%p PAR:%p\nVCPU:%p\n\0"
+	.ascii	"HYP panic:\nPS:%08x PC:%016x ESR:%08x\nFAR:%016x HPFAR:%016x PAR:%016x\nVCPU:%p\n\0"
 
 	.align	2
 
@@ -1015,9 +1019,15 @@ el1_trap:
 	b.ne	1f		// Not an abort we care about
 
 	/* This is an abort. Check for permission fault */
+alternative_if_not ARM64_WORKAROUND_834220
 	and	x2, x1, #ESR_ELx_FSC_TYPE
 	cmp	x2, #FSC_PERM
 	b.ne	1f		// Not a permission fault
+alternative_else
+	nop			// Use the permission fault path to
+	nop			// check for a valid S1 translation,
+	nop			// regardless of the ESR value.
+alternative_endif
 
 	/*
 	 * Check for Stage-1 page table walk, which is guaranteed
diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c
index 85c5715..648112e 100644
--- a/arch/arm64/kvm/inject_fault.c
+++ b/arch/arm64/kvm/inject_fault.c
@@ -48,7 +48,7 @@ static void prepare_fault32(struct kvm_vcpu *vcpu, u32 mode, u32 vect_offset)
 
 	/* Note: These now point to the banked copies */
 	*vcpu_spsr(vcpu) = new_spsr_value;
-	*vcpu_reg(vcpu, 14) = *vcpu_pc(vcpu) + return_offset;
+	*vcpu_reg32(vcpu, 14) = *vcpu_pc(vcpu) + return_offset;
 
 	/* Branch to exception vector */
 	if (sctlr & (1 << 13))
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 87a64e8..d2650e8 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -78,7 +78,7 @@ static u32 get_ccsidr(u32 csselr)
  * See note at ARMv7 ARM B1.14.4 (TL;DR: S/W ops are not easily virtualized).
  */
 static bool access_dcsw(struct kvm_vcpu *vcpu,
-			const struct sys_reg_params *p,
+			struct sys_reg_params *p,
 			const struct sys_reg_desc *r)
 {
 	if (!p->is_write)
@@ -94,21 +94,19 @@ static bool access_dcsw(struct kvm_vcpu *vcpu,
  * sys_regs and leave it in complete control of the caches.
  */
 static bool access_vm_reg(struct kvm_vcpu *vcpu,
-			  const struct sys_reg_params *p,
+			  struct sys_reg_params *p,
 			  const struct sys_reg_desc *r)
 {
-	unsigned long val;
 	bool was_enabled = vcpu_has_cache_enabled(vcpu);
 
 	BUG_ON(!p->is_write);
 
-	val = *vcpu_reg(vcpu, p->Rt);
 	if (!p->is_aarch32) {
-		vcpu_sys_reg(vcpu, r->reg) = val;
+		vcpu_sys_reg(vcpu, r->reg) = p->regval;
 	} else {
 		if (!p->is_32bit)
-			vcpu_cp15_64_high(vcpu, r->reg) = val >> 32;
-		vcpu_cp15_64_low(vcpu, r->reg) = val & 0xffffffffUL;
+			vcpu_cp15_64_high(vcpu, r->reg) = upper_32_bits(p->regval);
+		vcpu_cp15_64_low(vcpu, r->reg) = lower_32_bits(p->regval);
 	}
 
 	kvm_toggle_cache(vcpu, was_enabled);
@@ -122,22 +120,19 @@ static bool access_vm_reg(struct kvm_vcpu *vcpu,
  * for both AArch64 and AArch32 accesses.
  */
 static bool access_gic_sgi(struct kvm_vcpu *vcpu,
-			   const struct sys_reg_params *p,
+			   struct sys_reg_params *p,
 			   const struct sys_reg_desc *r)
 {
-	u64 val;
-
 	if (!p->is_write)
 		return read_from_write_only(vcpu, p);
 
-	val = *vcpu_reg(vcpu, p->Rt);
-	vgic_v3_dispatch_sgi(vcpu, val);
+	vgic_v3_dispatch_sgi(vcpu, p->regval);
 
 	return true;
 }
 
 static bool trap_raz_wi(struct kvm_vcpu *vcpu,
-			const struct sys_reg_params *p,
+			struct sys_reg_params *p,
 			const struct sys_reg_desc *r)
 {
 	if (p->is_write)
@@ -147,19 +142,19 @@ static bool trap_raz_wi(struct kvm_vcpu *vcpu,
 }
 
 static bool trap_oslsr_el1(struct kvm_vcpu *vcpu,
-			   const struct sys_reg_params *p,
+			   struct sys_reg_params *p,
 			   const struct sys_reg_desc *r)
 {
 	if (p->is_write) {
 		return ignore_write(vcpu, p);
 	} else {
-		*vcpu_reg(vcpu, p->Rt) = (1 << 3);
+		p->regval = (1 << 3);
 		return true;
 	}
 }
 
 static bool trap_dbgauthstatus_el1(struct kvm_vcpu *vcpu,
-				   const struct sys_reg_params *p,
+				   struct sys_reg_params *p,
 				   const struct sys_reg_desc *r)
 {
 	if (p->is_write) {
@@ -167,7 +162,7 @@ static bool trap_dbgauthstatus_el1(struct kvm_vcpu *vcpu,
 	} else {
 		u32 val;
 		asm volatile("mrs %0, dbgauthstatus_el1" : "=r" (val));
-		*vcpu_reg(vcpu, p->Rt) = val;
+		p->regval = val;
 		return true;
 	}
 }
@@ -200,17 +195,17 @@ static bool trap_dbgauthstatus_el1(struct kvm_vcpu *vcpu,
  *   now use the debug registers.
  */
 static bool trap_debug_regs(struct kvm_vcpu *vcpu,
-			    const struct sys_reg_params *p,
+			    struct sys_reg_params *p,
 			    const struct sys_reg_desc *r)
 {
 	if (p->is_write) {
-		vcpu_sys_reg(vcpu, r->reg) = *vcpu_reg(vcpu, p->Rt);
+		vcpu_sys_reg(vcpu, r->reg) = p->regval;
 		vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY;
 	} else {
-		*vcpu_reg(vcpu, p->Rt) = vcpu_sys_reg(vcpu, r->reg);
+		p->regval = vcpu_sys_reg(vcpu, r->reg);
 	}
 
-	trace_trap_reg(__func__, r->reg, p->is_write, *vcpu_reg(vcpu, p->Rt));
+	trace_trap_reg(__func__, r->reg, p->is_write, p->regval);
 
 	return true;
 }
@@ -225,10 +220,10 @@ static bool trap_debug_regs(struct kvm_vcpu *vcpu,
  * hyp.S code switches between host and guest values in future.
  */
 static inline void reg_to_dbg(struct kvm_vcpu *vcpu,
-			      const struct sys_reg_params *p,
+			      struct sys_reg_params *p,
 			      u64 *dbg_reg)
 {
-	u64 val = *vcpu_reg(vcpu, p->Rt);
+	u64 val = p->regval;
 
 	if (p->is_32bit) {
 		val &= 0xffffffffUL;
@@ -240,19 +235,16 @@ static inline void reg_to_dbg(struct kvm_vcpu *vcpu,
 }
 
 static inline void dbg_to_reg(struct kvm_vcpu *vcpu,
-			      const struct sys_reg_params *p,
+			      struct sys_reg_params *p,
 			      u64 *dbg_reg)
 {
-	u64 val = *dbg_reg;
-
+	p->regval = *dbg_reg;
 	if (p->is_32bit)
-		val &= 0xffffffffUL;
-
-	*vcpu_reg(vcpu, p->Rt) = val;
+		p->regval &= 0xffffffffUL;
 }
 
 static inline bool trap_bvr(struct kvm_vcpu *vcpu,
-			    const struct sys_reg_params *p,
+			    struct sys_reg_params *p,
 			    const struct sys_reg_desc *rd)
 {
 	u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg];
@@ -294,7 +286,7 @@ static inline void reset_bvr(struct kvm_vcpu *vcpu,
 }
 
 static inline bool trap_bcr(struct kvm_vcpu *vcpu,
-			    const struct sys_reg_params *p,
+			    struct sys_reg_params *p,
 			    const struct sys_reg_desc *rd)
 {
 	u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg];
@@ -337,7 +329,7 @@ static inline void reset_bcr(struct kvm_vcpu *vcpu,
 }
 
 static inline bool trap_wvr(struct kvm_vcpu *vcpu,
-			    const struct sys_reg_params *p,
+			    struct sys_reg_params *p,
 			    const struct sys_reg_desc *rd)
 {
 	u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg];
@@ -380,7 +372,7 @@ static inline void reset_wvr(struct kvm_vcpu *vcpu,
 }
 
 static inline bool trap_wcr(struct kvm_vcpu *vcpu,
-			    const struct sys_reg_params *p,
+			    struct sys_reg_params *p,
 			    const struct sys_reg_desc *rd)
 {
 	u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg];
@@ -687,7 +679,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 };
 
 static bool trap_dbgidr(struct kvm_vcpu *vcpu,
-			const struct sys_reg_params *p,
+			struct sys_reg_params *p,
 			const struct sys_reg_desc *r)
 {
 	if (p->is_write) {
@@ -697,23 +689,23 @@ static bool trap_dbgidr(struct kvm_vcpu *vcpu,
 		u64 pfr = read_system_reg(SYS_ID_AA64PFR0_EL1);
 		u32 el3 = !!cpuid_feature_extract_field(pfr, ID_AA64PFR0_EL3_SHIFT);
 
-		*vcpu_reg(vcpu, p->Rt) = ((((dfr >> ID_AA64DFR0_WRPS_SHIFT) & 0xf) << 28) |
-					  (((dfr >> ID_AA64DFR0_BRPS_SHIFT) & 0xf) << 24) |
-					  (((dfr >> ID_AA64DFR0_CTX_CMPS_SHIFT) & 0xf) << 20) |
-					  (6 << 16) | (el3 << 14) | (el3 << 12));
+		p->regval = ((((dfr >> ID_AA64DFR0_WRPS_SHIFT) & 0xf) << 28) |
+			     (((dfr >> ID_AA64DFR0_BRPS_SHIFT) & 0xf) << 24) |
+			     (((dfr >> ID_AA64DFR0_CTX_CMPS_SHIFT) & 0xf) << 20)
+			     | (6 << 16) | (el3 << 14) | (el3 << 12));
 		return true;
 	}
 }
 
 static bool trap_debug32(struct kvm_vcpu *vcpu,
-			 const struct sys_reg_params *p,
+			 struct sys_reg_params *p,
 			 const struct sys_reg_desc *r)
 {
 	if (p->is_write) {
-		vcpu_cp14(vcpu, r->reg) = *vcpu_reg(vcpu, p->Rt);
+		vcpu_cp14(vcpu, r->reg) = p->regval;
 		vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY;
 	} else {
-		*vcpu_reg(vcpu, p->Rt) = vcpu_cp14(vcpu, r->reg);
+		p->regval = vcpu_cp14(vcpu, r->reg);
 	}
 
 	return true;
@@ -731,7 +723,7 @@ static bool trap_debug32(struct kvm_vcpu *vcpu,
  */
 
 static inline bool trap_xvr(struct kvm_vcpu *vcpu,
-			    const struct sys_reg_params *p,
+			    struct sys_reg_params *p,
 			    const struct sys_reg_desc *rd)
 {
 	u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg];
@@ -740,12 +732,12 @@ static inline bool trap_xvr(struct kvm_vcpu *vcpu,
 		u64 val = *dbg_reg;
 
 		val &= 0xffffffffUL;
-		val |= *vcpu_reg(vcpu, p->Rt) << 32;
+		val |= p->regval << 32;
 		*dbg_reg = val;
 
 		vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY;
 	} else {
-		*vcpu_reg(vcpu, p->Rt) = *dbg_reg >> 32;
+		p->regval = *dbg_reg >> 32;
 	}
 
 	trace_trap_reg(__func__, rd->reg, p->is_write, *dbg_reg);
@@ -991,7 +983,7 @@ int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu, struct kvm_run *run)
  * Return 0 if the access has been handled, and -1 if not.
  */
 static int emulate_cp(struct kvm_vcpu *vcpu,
-		      const struct sys_reg_params *params,
+		      struct sys_reg_params *params,
 		      const struct sys_reg_desc *table,
 		      size_t num)
 {
@@ -1062,12 +1054,12 @@ static int kvm_handle_cp_64(struct kvm_vcpu *vcpu,
 {
 	struct sys_reg_params params;
 	u32 hsr = kvm_vcpu_get_hsr(vcpu);
+	int Rt = (hsr >> 5) & 0xf;
 	int Rt2 = (hsr >> 10) & 0xf;
 
 	params.is_aarch32 = true;
 	params.is_32bit = false;
 	params.CRm = (hsr >> 1) & 0xf;
-	params.Rt = (hsr >> 5) & 0xf;
 	params.is_write = ((hsr & 1) == 0);
 
 	params.Op0 = 0;
@@ -1076,15 +1068,12 @@ static int kvm_handle_cp_64(struct kvm_vcpu *vcpu,
 	params.CRn = 0;
 
 	/*
-	 * Massive hack here. Store Rt2 in the top 32bits so we only
-	 * have one register to deal with. As we use the same trap
+	 * Make a 64-bit value out of Rt and Rt2. As we use the same trap
 	 * backends between AArch32 and AArch64, we get away with it.
 	 */
 	if (params.is_write) {
-		u64 val = *vcpu_reg(vcpu, params.Rt);
-		val &= 0xffffffff;
-		val |= *vcpu_reg(vcpu, Rt2) << 32;
-		*vcpu_reg(vcpu, params.Rt) = val;
+		params.regval = vcpu_get_reg(vcpu, Rt) & 0xffffffff;
+		params.regval |= vcpu_get_reg(vcpu, Rt2) << 32;
 	}
 
 	if (!emulate_cp(vcpu, &params, target_specific, nr_specific))
@@ -1095,11 +1084,10 @@ static int kvm_handle_cp_64(struct kvm_vcpu *vcpu,
 	unhandled_cp_access(vcpu, &params);
 
 out:
-	/* Do the opposite hack for the read side */
+	/* Split up the value between registers for the read side */
 	if (!params.is_write) {
-		u64 val = *vcpu_reg(vcpu, params.Rt);
-		val >>= 32;
-		*vcpu_reg(vcpu, Rt2) = val;
+		vcpu_set_reg(vcpu, Rt, lower_32_bits(params.regval));
+		vcpu_set_reg(vcpu, Rt2, upper_32_bits(params.regval));
 	}
 
 	return 1;
@@ -1118,21 +1106,24 @@ static int kvm_handle_cp_32(struct kvm_vcpu *vcpu,
 {
 	struct sys_reg_params params;
 	u32 hsr = kvm_vcpu_get_hsr(vcpu);
+	int Rt  = (hsr >> 5) & 0xf;
 
 	params.is_aarch32 = true;
 	params.is_32bit = true;
 	params.CRm = (hsr >> 1) & 0xf;
-	params.Rt  = (hsr >> 5) & 0xf;
+	params.regval = vcpu_get_reg(vcpu, Rt);
 	params.is_write = ((hsr & 1) == 0);
 	params.CRn = (hsr >> 10) & 0xf;
 	params.Op0 = 0;
 	params.Op1 = (hsr >> 14) & 0x7;
 	params.Op2 = (hsr >> 17) & 0x7;
 
-	if (!emulate_cp(vcpu, &params, target_specific, nr_specific))
-		return 1;
-	if (!emulate_cp(vcpu, &params, global, nr_global))
+	if (!emulate_cp(vcpu, &params, target_specific, nr_specific) ||
+	    !emulate_cp(vcpu, &params, global, nr_global)) {
+		if (!params.is_write)
+			vcpu_set_reg(vcpu, Rt, params.regval);
 		return 1;
+	}
 
 	unhandled_cp_access(vcpu, &params);
 	return 1;
@@ -1175,7 +1166,7 @@ int kvm_handle_cp14_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
 }
 
 static int emulate_sys_reg(struct kvm_vcpu *vcpu,
-			   const struct sys_reg_params *params)
+			   struct sys_reg_params *params)
 {
 	size_t num;
 	const struct sys_reg_desc *table, *r;
@@ -1230,6 +1221,8 @@ int kvm_handle_sys_reg(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
 	struct sys_reg_params params;
 	unsigned long esr = kvm_vcpu_get_hsr(vcpu);
+	int Rt = (esr >> 5) & 0x1f;
+	int ret;
 
 	trace_kvm_handle_sys_reg(esr);
 
@@ -1240,10 +1233,14 @@ int kvm_handle_sys_reg(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	params.CRn = (esr >> 10) & 0xf;
 	params.CRm = (esr >> 1) & 0xf;
 	params.Op2 = (esr >> 17) & 0x7;
-	params.Rt = (esr >> 5) & 0x1f;
+	params.regval = vcpu_get_reg(vcpu, Rt);
 	params.is_write = !(esr & 1);
 
-	return emulate_sys_reg(vcpu, &params);
+	ret = emulate_sys_reg(vcpu, &params);
+
+	if (!params.is_write)
+		vcpu_set_reg(vcpu, Rt, params.regval);
+	return ret;
 }
 
 /******************************************************************************
diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h
index eaa324e..dbbb01c 100644
--- a/arch/arm64/kvm/sys_regs.h
+++ b/arch/arm64/kvm/sys_regs.h
@@ -28,7 +28,7 @@ struct sys_reg_params {
 	u8	CRn;
 	u8	CRm;
 	u8	Op2;
-	u8	Rt;
+	u64	regval;
 	bool	is_write;
 	bool	is_aarch32;
 	bool	is_32bit;	/* Only valid if is_aarch32 is true */
@@ -44,7 +44,7 @@ struct sys_reg_desc {
 
 	/* Trapped access from guest, if non-NULL. */
 	bool (*access)(struct kvm_vcpu *,
-		       const struct sys_reg_params *,
+		       struct sys_reg_params *,
 		       const struct sys_reg_desc *);
 
 	/* Initialization for vcpu. */
@@ -77,9 +77,9 @@ static inline bool ignore_write(struct kvm_vcpu *vcpu,
 }
 
 static inline bool read_zero(struct kvm_vcpu *vcpu,
-			     const struct sys_reg_params *p)
+			     struct sys_reg_params *p)
 {
-	*vcpu_reg(vcpu, p->Rt) = 0;
+	p->regval = 0;
 	return true;
 }
 
diff --git a/arch/arm64/kvm/sys_regs_generic_v8.c b/arch/arm64/kvm/sys_regs_generic_v8.c
index 1e45768..ed90578 100644
--- a/arch/arm64/kvm/sys_regs_generic_v8.c
+++ b/arch/arm64/kvm/sys_regs_generic_v8.c
@@ -31,13 +31,13 @@
 #include "sys_regs.h"
 
 static bool access_actlr(struct kvm_vcpu *vcpu,
-			 const struct sys_reg_params *p,
+			 struct sys_reg_params *p,
 			 const struct sys_reg_desc *r)
 {
 	if (p->is_write)
 		return ignore_write(vcpu, p);
 
-	*vcpu_reg(vcpu, p->Rt) = vcpu_sys_reg(vcpu, ACTLR_EL1);
+	p->regval = vcpu_sys_reg(vcpu, ACTLR_EL1);
 	return true;
 }
 
diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c
index f636a26..e87f53f 100644
--- a/arch/arm64/mm/context.c
+++ b/arch/arm64/mm/context.c
@@ -76,13 +76,28 @@ static void flush_context(unsigned int cpu)
 		__flush_icache_all();
 }
 
-static int is_reserved_asid(u64 asid)
+static bool check_update_reserved_asid(u64 asid, u64 newasid)
 {
 	int cpu;
-	for_each_possible_cpu(cpu)
-		if (per_cpu(reserved_asids, cpu) == asid)
-			return 1;
-	return 0;
+	bool hit = false;
+
+	/*
+	 * Iterate over the set of reserved ASIDs looking for a match.
+	 * If we find one, then we can update our mm to use newasid
+	 * (i.e. the same ASID in the current generation) but we can't
+	 * exit the loop early, since we need to ensure that all copies
+	 * of the old ASID are updated to reflect the mm. Failure to do
+	 * so could result in us missing the reserved ASID in a future
+	 * generation.
+	 */
+	for_each_possible_cpu(cpu) {
+		if (per_cpu(reserved_asids, cpu) == asid) {
+			hit = true;
+			per_cpu(reserved_asids, cpu) = newasid;
+		}
+	}
+
+	return hit;
 }
 
 static u64 new_context(struct mm_struct *mm, unsigned int cpu)
@@ -92,12 +107,14 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu)
 	u64 generation = atomic64_read(&asid_generation);
 
 	if (asid != 0) {
+		u64 newasid = generation | (asid & ~ASID_MASK);
+
 		/*
 		 * If our current ASID was active during a rollover, we
 		 * can continue to use it and this was just a false alarm.
 		 */
-		if (is_reserved_asid(asid))
-			return generation | (asid & ~ASID_MASK);
+		if (check_update_reserved_asid(asid, newasid))
+			return newasid;
 
 		/*
 		 * We had a valid ASID in a previous life, so try to re-use
@@ -105,7 +122,7 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu)
 		 */
 		asid &= ~ASID_MASK;
 		if (!__test_and_set_bit(asid, asid_map))
-			goto bump_gen;
+			return newasid;
 	}
 
 	/*
@@ -129,10 +146,7 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu)
 set_asid:
 	__set_bit(asid, asid_map);
 	cur_idx = asid;
-
-bump_gen:
-	asid |= generation;
-	return asid;
+	return asid | generation;
 }
 
 void check_and_switch_context(struct mm_struct *mm, unsigned int cpu)
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 131a199..7963aa4 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -18,6 +18,7 @@
  */
 
 #include <linux/gfp.h>
+#include <linux/acpi.h>
 #include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/genalloc.h>
@@ -28,9 +29,6 @@
 
 #include <asm/cacheflush.h>
 
-struct dma_map_ops *dma_ops;
-EXPORT_SYMBOL(dma_ops);
-
 static pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot,
 				 bool coherent)
 {
@@ -515,13 +513,7 @@ EXPORT_SYMBOL(dummy_dma_ops);
 
 static int __init arm64_dma_init(void)
 {
-	int ret;
-
-	dma_ops = &swiotlb_dma_ops;
-
-	ret = atomic_pool_init();
-
-	return ret;
+	return atomic_pool_init();
 }
 arch_initcall(arm64_dma_init);
 
@@ -552,10 +544,14 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size,
 {
 	bool coherent = is_device_dma_coherent(dev);
 	int ioprot = dma_direction_to_prot(DMA_BIDIRECTIONAL, coherent);
+	size_t iosize = size;
 	void *addr;
 
 	if (WARN(!dev, "cannot create IOMMU mapping for unknown device\n"))
 		return NULL;
+
+	size = PAGE_ALIGN(size);
+
 	/*
 	 * Some drivers rely on this, and we probably don't want the
 	 * possibility of stale kernel data being read by devices anyway.
@@ -566,7 +562,7 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size,
 		struct page **pages;
 		pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL, coherent);
 
-		pages = iommu_dma_alloc(dev, size, gfp, ioprot,	handle,
+		pages = iommu_dma_alloc(dev, iosize, gfp, ioprot, handle,
 					flush_page);
 		if (!pages)
 			return NULL;
@@ -574,7 +570,7 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size,
 		addr = dma_common_pages_remap(pages, size, VM_USERMAP, prot,
 					      __builtin_return_address(0));
 		if (!addr)
-			iommu_dma_free(dev, pages, size, handle);
+			iommu_dma_free(dev, pages, iosize, handle);
 	} else {
 		struct page *page;
 		/*
@@ -591,7 +587,7 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size,
 		if (!addr)
 			return NULL;
 
-		*handle = iommu_dma_map_page(dev, page, 0, size, ioprot);
+		*handle = iommu_dma_map_page(dev, page, 0, iosize, ioprot);
 		if (iommu_dma_mapping_error(dev, *handle)) {
 			if (coherent)
 				__free_pages(page, get_order(size));
@@ -606,6 +602,9 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size,
 static void __iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
 			       dma_addr_t handle, struct dma_attrs *attrs)
 {
+	size_t iosize = size;
+
+	size = PAGE_ALIGN(size);
 	/*
 	 * @cpu_addr will be one of 3 things depending on how it was allocated:
 	 * - A remapped array of pages from iommu_dma_alloc(), for all
@@ -617,17 +616,17 @@ static void __iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
 	 * Hence how dodgy the below logic looks...
 	 */
 	if (__in_atomic_pool(cpu_addr, size)) {
-		iommu_dma_unmap_page(dev, handle, size, 0, NULL);
+		iommu_dma_unmap_page(dev, handle, iosize, 0, NULL);
 		__free_from_pool(cpu_addr, size);
 	} else if (is_vmalloc_addr(cpu_addr)){
 		struct vm_struct *area = find_vm_area(cpu_addr);
 
 		if (WARN_ON(!area || !area->pages))
 			return;
-		iommu_dma_free(dev, area->pages, size, &handle);
+		iommu_dma_free(dev, area->pages, iosize, &handle);
 		dma_common_free_remap(cpu_addr, size, VM_USERMAP);
 	} else {
-		iommu_dma_unmap_page(dev, handle, size, 0, NULL);
+		iommu_dma_unmap_page(dev, handle, iosize, 0, NULL);
 		__free_pages(virt_to_page(cpu_addr), get_order(size));
 	}
 }
@@ -984,8 +983,8 @@ static void __iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 			struct iommu_ops *iommu, bool coherent)
 {
-	if (!acpi_disabled && !dev->archdata.dma_ops)
-		dev->archdata.dma_ops = dma_ops;
+	if (!dev->archdata.dma_ops)
+		dev->archdata.dma_ops = &swiotlb_dma_ops;
 
 	dev->archdata.dma_coherent = coherent;
 	__iommu_setup_dma_ops(dev, dma_base, size, iommu);
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 19211c4..92ddac1 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -393,16 +393,16 @@ static struct fault_info {
 	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"level 1 translation fault"	},
 	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"level 2 translation fault"	},
 	{ do_page_fault,	SIGSEGV, SEGV_MAPERR,	"level 3 translation fault"	},
-	{ do_bad,		SIGBUS,  0,		"reserved access flag fault"	},
+	{ do_bad,		SIGBUS,  0,		"unknown 8"			},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 1 access flag fault"	},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 2 access flag fault"	},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 3 access flag fault"	},
-	{ do_bad,		SIGBUS,  0,		"reserved permission fault"	},
+	{ do_bad,		SIGBUS,  0,		"unknown 12"			},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 1 permission fault"	},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 2 permission fault"	},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 3 permission fault"	},
 	{ do_bad,		SIGBUS,  0,		"synchronous external abort"	},
-	{ do_bad,		SIGBUS,  0,		"asynchronous external abort"	},
+	{ do_bad,		SIGBUS,  0,		"unknown 17"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 18"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 19"			},
 	{ do_bad,		SIGBUS,  0,		"synchronous abort (translation table walk)" },
@@ -410,16 +410,16 @@ static struct fault_info {
 	{ do_bad,		SIGBUS,  0,		"synchronous abort (translation table walk)" },
 	{ do_bad,		SIGBUS,  0,		"synchronous abort (translation table walk)" },
 	{ do_bad,		SIGBUS,  0,		"synchronous parity error"	},
-	{ do_bad,		SIGBUS,  0,		"asynchronous parity error"	},
+	{ do_bad,		SIGBUS,  0,		"unknown 25"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 26"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 27"			},
-	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk" },
-	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk" },
-	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk" },
-	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk" },
+	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk)" },
+	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk)" },
+	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk)" },
+	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk)" },
 	{ do_bad,		SIGBUS,  0,		"unknown 32"			},
 	{ do_bad,		SIGBUS,  BUS_ADRALN,	"alignment fault"		},
-	{ do_bad,		SIGBUS,  0,		"debug event"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 34"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 35"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 36"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 37"			},
@@ -433,21 +433,21 @@ static struct fault_info {
 	{ do_bad,		SIGBUS,  0,		"unknown 45"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 46"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 47"			},
-	{ do_bad,		SIGBUS,  0,		"unknown 48"			},
+	{ do_bad,		SIGBUS,  0,		"TLB conflict abort"		},
 	{ do_bad,		SIGBUS,  0,		"unknown 49"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 50"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 51"			},
 	{ do_bad,		SIGBUS,  0,		"implementation fault (lockdown abort)" },
-	{ do_bad,		SIGBUS,  0,		"unknown 53"			},
+	{ do_bad,		SIGBUS,  0,		"implementation fault (unsupported exclusive)" },
 	{ do_bad,		SIGBUS,  0,		"unknown 54"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 55"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 56"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 57"			},
-	{ do_bad,		SIGBUS,  0,		"implementation fault (coprocessor abort)" },
+	{ do_bad,		SIGBUS,  0,		"unknown 58" 			},
 	{ do_bad,		SIGBUS,  0,		"unknown 59"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 60"			},
-	{ do_bad,		SIGBUS,  0,		"unknown 61"			},
-	{ do_bad,		SIGBUS,  0,		"unknown 62"			},
+	{ do_bad,		SIGBUS,  0,		"section domain fault"		},
+	{ do_bad,		SIGBUS,  0,		"page domain fault"		},
 	{ do_bad,		SIGBUS,  0,		"unknown 63"			},
 };
 
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index e3f563c..873e363 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -64,8 +64,12 @@ EXPORT_SYMBOL(phys_mem_access_prot);
 
 static void __init *early_alloc(unsigned long sz)
 {
-	void *ptr = __va(memblock_alloc(sz, sz));
-	BUG_ON(!ptr);
+	phys_addr_t phys;
+	void *ptr;
+
+	phys = memblock_alloc(sz, sz);
+	BUG_ON(!phys);
+	ptr = __va(phys);
 	memset(ptr, 0, sz);
 	return ptr;
 }
@@ -81,55 +85,19 @@ static void split_pmd(pmd_t *pmd, pte_t *pte)
 	do {
 		/*
 		 * Need to have the least restrictive permissions available
-		 * permissions will be fixed up later. Default the new page
-		 * range as contiguous ptes.
+		 * permissions will be fixed up later
 		 */
-		set_pte(pte, pfn_pte(pfn, PAGE_KERNEL_EXEC_CONT));
+		set_pte(pte, pfn_pte(pfn, PAGE_KERNEL_EXEC));
 		pfn++;
 	} while (pte++, i++, i < PTRS_PER_PTE);
 }
 
-/*
- * Given a PTE with the CONT bit set, determine where the CONT range
- * starts, and clear the entire range of PTE CONT bits.
- */
-static void clear_cont_pte_range(pte_t *pte, unsigned long addr)
-{
-	int i;
-
-	pte -= CONT_RANGE_OFFSET(addr);
-	for (i = 0; i < CONT_PTES; i++) {
-		set_pte(pte, pte_mknoncont(*pte));
-		pte++;
-	}
-	flush_tlb_all();
-}
-
-/*
- * Given a range of PTEs set the pfn and provided page protection flags
- */
-static void __populate_init_pte(pte_t *pte, unsigned long addr,
-				unsigned long end, phys_addr_t phys,
-				pgprot_t prot)
-{
-	unsigned long pfn = __phys_to_pfn(phys);
-
-	do {
-		/* clear all the bits except the pfn, then apply the prot */
-		set_pte(pte, pfn_pte(pfn, prot));
-		pte++;
-		pfn++;
-		addr += PAGE_SIZE;
-	} while (addr != end);
-}
-
 static void alloc_init_pte(pmd_t *pmd, unsigned long addr,
-				  unsigned long end, phys_addr_t phys,
+				  unsigned long end, unsigned long pfn,
 				  pgprot_t prot,
 				  void *(*alloc)(unsigned long size))
 {
 	pte_t *pte;
-	unsigned long next;
 
 	if (pmd_none(*pmd) || pmd_sect(*pmd)) {
 		pte = alloc(PTRS_PER_PTE * sizeof(pte_t));
@@ -142,27 +110,9 @@ static void alloc_init_pte(pmd_t *pmd, unsigned long addr,
 
 	pte = pte_offset_kernel(pmd, addr);
 	do {
-		next = min(end, (addr + CONT_SIZE) & CONT_MASK);
-		if (((addr | next | phys) & ~CONT_MASK) == 0) {
-			/* a block of CONT_PTES  */
-			__populate_init_pte(pte, addr, next, phys,
-					    __pgprot(pgprot_val(prot) | PTE_CONT));
-		} else {
-			/*
-			 * If the range being split is already inside of a
-			 * contiguous range but this PTE isn't going to be
-			 * contiguous, then we want to unmark the adjacent
-			 * ranges, then update the portion of the range we
-			 * are interrested in.
-			 */
-			 clear_cont_pte_range(pte, addr);
-			 __populate_init_pte(pte, addr, next, phys, prot);
-		}
-
-		pte += (next - addr) >> PAGE_SHIFT;
-		phys += next - addr;
-		addr = next;
-	} while (addr != end);
+		set_pte(pte, pfn_pte(pfn, prot));
+		pfn++;
+	} while (pte++, addr += PAGE_SIZE, addr != end);
 }
 
 static void split_pud(pud_t *old_pud, pmd_t *pmd)
@@ -223,7 +173,8 @@ static void alloc_init_pmd(struct mm_struct *mm, pud_t *pud,
 				}
 			}
 		} else {
-			alloc_init_pte(pmd, addr, next, phys, prot, alloc);
+			alloc_init_pte(pmd, addr, next, __phys_to_pfn(phys),
+				       prot, alloc);
 		}
 		phys += next - addr;
 	} while (pmd++, addr = next, addr != end);
@@ -362,8 +313,8 @@ static void __init __map_memblock(phys_addr_t start, phys_addr_t end)
 	 * for now. This will get more fine grained later once all memory
 	 * is mapped
 	 */
-	unsigned long kernel_x_start = round_down(__pa(_stext), SECTION_SIZE);
-	unsigned long kernel_x_end = round_up(__pa(__init_end), SECTION_SIZE);
+	unsigned long kernel_x_start = round_down(__pa(_stext), SWAPPER_BLOCK_SIZE);
+	unsigned long kernel_x_end = round_up(__pa(__init_end), SWAPPER_BLOCK_SIZE);
 
 	if (end < kernel_x_start) {
 		create_mapping(start, __phys_to_virt(start),
@@ -451,18 +402,18 @@ static void __init fixup_executable(void)
 {
 #ifdef CONFIG_DEBUG_RODATA
 	/* now that we are actually fully mapped, make the start/end more fine grained */
-	if (!IS_ALIGNED((unsigned long)_stext, SECTION_SIZE)) {
+	if (!IS_ALIGNED((unsigned long)_stext, SWAPPER_BLOCK_SIZE)) {
 		unsigned long aligned_start = round_down(__pa(_stext),
-							SECTION_SIZE);
+							 SWAPPER_BLOCK_SIZE);
 
 		create_mapping(aligned_start, __phys_to_virt(aligned_start),
 				__pa(_stext) - aligned_start,
 				PAGE_KERNEL);
 	}
 
-	if (!IS_ALIGNED((unsigned long)__init_end, SECTION_SIZE)) {
+	if (!IS_ALIGNED((unsigned long)__init_end, SWAPPER_BLOCK_SIZE)) {
 		unsigned long aligned_end = round_up(__pa(__init_end),
-							SECTION_SIZE);
+							  SWAPPER_BLOCK_SIZE);
 		create_mapping(__pa(__init_end), (unsigned long)__init_end,
 				aligned_end - __pa(__init_end),
 				PAGE_KERNEL);
@@ -475,7 +426,7 @@ void mark_rodata_ro(void)
 {
 	create_mapping_late(__pa(_stext), (unsigned long)_stext,
 				(unsigned long)_etext - (unsigned long)_stext,
-				PAGE_KERNEL_EXEC | PTE_RDONLY);
+				PAGE_KERNEL_ROX);
 
 }
 #endif
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index cf3c7d4..b162ad7 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -50,7 +50,7 @@ static const int bpf2a64[] = {
 	[BPF_REG_8] = A64_R(21),
 	[BPF_REG_9] = A64_R(22),
 	/* read-only frame pointer to access stack */
-	[BPF_REG_FP] = A64_FP,
+	[BPF_REG_FP] = A64_R(25),
 	/* temporary register for internal BPF JIT */
 	[TMP_REG_1] = A64_R(23),
 	[TMP_REG_2] = A64_R(24),
@@ -139,6 +139,12 @@ static inline int epilogue_offset(const struct jit_ctx *ctx)
 /* Stack must be multiples of 16B */
 #define STACK_ALIGN(sz) (((sz) + 15) & ~15)
 
+#define _STACK_SIZE \
+	(MAX_BPF_STACK \
+	 + 4 /* extra for skb_copy_bits buffer */)
+
+#define STACK_SIZE STACK_ALIGN(_STACK_SIZE)
+
 static void build_prologue(struct jit_ctx *ctx)
 {
 	const u8 r6 = bpf2a64[BPF_REG_6];
@@ -150,10 +156,35 @@ static void build_prologue(struct jit_ctx *ctx)
 	const u8 rx = bpf2a64[BPF_REG_X];
 	const u8 tmp1 = bpf2a64[TMP_REG_1];
 	const u8 tmp2 = bpf2a64[TMP_REG_2];
-	int stack_size = MAX_BPF_STACK;
 
-	stack_size += 4; /* extra for skb_copy_bits buffer */
-	stack_size = STACK_ALIGN(stack_size);
+	/*
+	 * BPF prog stack layout
+	 *
+	 *                         high
+	 * original A64_SP =>   0:+-----+ BPF prologue
+	 *                        |FP/LR|
+	 * current A64_FP =>  -16:+-----+
+	 *                        | ... | callee saved registers
+	 *                        +-----+
+	 *                        |     | x25/x26
+	 * BPF fp register => -80:+-----+ <= (BPF_FP)
+	 *                        |     |
+	 *                        | ... | BPF prog stack
+	 *                        |     |
+	 *                        +-----+ <= (BPF_FP - MAX_BPF_STACK)
+	 *                        |RSVD | JIT scratchpad
+	 * current A64_SP =>      +-----+ <= (BPF_FP - STACK_SIZE)
+	 *                        |     |
+	 *                        | ... | Function call stack
+	 *                        |     |
+	 *                        +-----+
+	 *                          low
+	 *
+	 */
+
+	/* Save FP and LR registers to stay align with ARM64 AAPCS */
+	emit(A64_PUSH(A64_FP, A64_LR, A64_SP), ctx);
+	emit(A64_MOV(1, A64_FP, A64_SP), ctx);
 
 	/* Save callee-saved register */
 	emit(A64_PUSH(r6, r7, A64_SP), ctx);
@@ -161,12 +192,15 @@ static void build_prologue(struct jit_ctx *ctx)
 	if (ctx->tmp_used)
 		emit(A64_PUSH(tmp1, tmp2, A64_SP), ctx);
 
-	/* Set up BPF stack */
-	emit(A64_SUB_I(1, A64_SP, A64_SP, stack_size), ctx);
+	/* Save fp (x25) and x26. SP requires 16 bytes alignment */
+	emit(A64_PUSH(fp, A64_R(26), A64_SP), ctx);
 
-	/* Set up frame pointer */
+	/* Set up BPF prog stack base register (x25) */
 	emit(A64_MOV(1, fp, A64_SP), ctx);
 
+	/* Set up function call stack */
+	emit(A64_SUB_I(1, A64_SP, A64_SP, STACK_SIZE), ctx);
+
 	/* Clear registers A and X */
 	emit_a64_mov_i64(ra, 0, ctx);
 	emit_a64_mov_i64(rx, 0, ctx);
@@ -182,13 +216,12 @@ static void build_epilogue(struct jit_ctx *ctx)
 	const u8 fp = bpf2a64[BPF_REG_FP];
 	const u8 tmp1 = bpf2a64[TMP_REG_1];
 	const u8 tmp2 = bpf2a64[TMP_REG_2];
-	int stack_size = MAX_BPF_STACK;
-
-	stack_size += 4; /* extra for skb_copy_bits buffer */
-	stack_size = STACK_ALIGN(stack_size);
 
 	/* We're done with BPF stack */
-	emit(A64_ADD_I(1, A64_SP, A64_SP, stack_size), ctx);
+	emit(A64_ADD_I(1, A64_SP, A64_SP, STACK_SIZE), ctx);
+
+	/* Restore fs (x25) and x26 */
+	emit(A64_POP(fp, A64_R(26), A64_SP), ctx);
 
 	/* Restore callee-saved register */
 	if (ctx->tmp_used)
@@ -196,8 +229,8 @@ static void build_epilogue(struct jit_ctx *ctx)
 	emit(A64_POP(r8, r9, A64_SP), ctx);
 	emit(A64_POP(r6, r7, A64_SP), ctx);
 
-	/* Restore frame pointer */
-	emit(A64_MOV(1, fp, A64_SP), ctx);
+	/* Restore FP/LR registers */
+	emit(A64_POP(A64_FP, A64_LR, A64_SP), ctx);
 
 	/* Set return value */
 	emit(A64_MOV(1, A64_R(0), r0), ctx);
@@ -557,7 +590,25 @@ emit_cond_jmp:
 	case BPF_ST | BPF_MEM | BPF_H:
 	case BPF_ST | BPF_MEM | BPF_B:
 	case BPF_ST | BPF_MEM | BPF_DW:
-		goto notyet;
+		/* Load imm to a register then store it */
+		ctx->tmp_used = 1;
+		emit_a64_mov_i(1, tmp2, off, ctx);
+		emit_a64_mov_i(1, tmp, imm, ctx);
+		switch (BPF_SIZE(code)) {
+		case BPF_W:
+			emit(A64_STR32(tmp, dst, tmp2), ctx);
+			break;
+		case BPF_H:
+			emit(A64_STRH(tmp, dst, tmp2), ctx);
+			break;
+		case BPF_B:
+			emit(A64_STRB(tmp, dst, tmp2), ctx);
+			break;
+		case BPF_DW:
+			emit(A64_STR64(tmp, dst, tmp2), ctx);
+			break;
+		}
+		break;
 
 	/* STX: *(size *)(dst + off) = src */
 	case BPF_STX | BPF_MEM | BPF_W:
@@ -624,7 +675,7 @@ emit_cond_jmp:
 			return -EINVAL;
 		}
 		emit_a64_mov_i64(r3, size, ctx);
-		emit(A64_ADD_I(1, r4, fp, MAX_BPF_STACK), ctx);
+		emit(A64_SUB_I(1, r4, fp, STACK_SIZE), ctx);
 		emit_a64_mov_i64(r5, (unsigned long)bpf_load_pointer, ctx);
 		emit(A64_PUSH(A64_FP, A64_LR, A64_SP), ctx);
 		emit(A64_MOV(1, A64_FP, A64_SP), ctx);
@@ -758,7 +809,7 @@ void bpf_int_jit_compile(struct bpf_prog *prog)
 	if (bpf_jit_enable > 1)
 		bpf_jit_dump(prog->len, image_size, 2, ctx.image);
 
-	bpf_flush_icache(ctx.image, ctx.image + ctx.idx);
+	bpf_flush_icache(header, ctx.image + ctx.idx);
 
 	set_memory_ro((unsigned long)header, header->pages);
 	prog->bpf_func = (void *)ctx.image;