Merge tag 'kvm-arm-for-v4.16' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm

KVM/ARM Changes for v4.16

The changes for this version include icache invalidation optimizations
(improving VM startup time), support for forwarded level-triggered
interrupts (improved performance for timers and passthrough platform
devices), a small fix for power-management notifiers, and some cosmetic
changes.

24 files changed, 197 insertions, 51 deletions

diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h
index 3d22eb87f919..9003bd19cb70 100644
--- a/arch/arm/include/asm/kvm_emulate.h
+++ b/arch/arm/include/asm/kvm_emulate.h
@@ -131,7 +131,7 @@ static inline bool mode_has_spsr(struct kvm_vcpu *vcpu)
 static inline bool vcpu_mode_priv(struct kvm_vcpu *vcpu)
 {
 	unsigned long cpsr_mode = vcpu->arch.ctxt.gp_regs.usr_regs.ARM_cpsr & MODE_MASK;
-	return cpsr_mode > USR_MODE;;
+	return cpsr_mode > USR_MODE;
 }
 
 static inline u32 kvm_vcpu_get_hsr(const struct kvm_vcpu *vcpu)
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index a9f7d3f47134..6394fb99da7f 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -48,6 +48,8 @@
 	KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
 #define KVM_REQ_IRQ_PENDING	KVM_ARCH_REQ(1)
 
+DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
+
 u32 *kvm_vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num, u32 mode);
 int __attribute_const__ kvm_target_cpu(void);
 int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
diff --git a/arch/arm/include/asm/kvm_hyp.h b/arch/arm/include/asm/kvm_hyp.h
index ab20ffa8b9e7..1ab8329e9ff7 100644
--- a/arch/arm/include/asm/kvm_hyp.h
+++ b/arch/arm/include/asm/kvm_hyp.h
@@ -21,7 +21,6 @@
 #include <linux/compiler.h>
 #include <linux/kvm_host.h>
 #include <asm/cp15.h>
-#include <asm/kvm_mmu.h>
 #include <asm/vfp.h>
 
 #define __hyp_text __section(.hyp.text) notrace
@@ -69,6 +68,8 @@
 #define HIFAR		__ACCESS_CP15(c6, 4, c0, 2)
 #define HPFAR		__ACCESS_CP15(c6, 4, c0, 4)
 #define ICIALLUIS	__ACCESS_CP15(c7, 0, c1, 0)
+#define BPIALLIS	__ACCESS_CP15(c7, 0, c1, 6)
+#define ICIMVAU		__ACCESS_CP15(c7, 0, c5, 1)
 #define ATS1CPR		__ACCESS_CP15(c7, 0, c8, 0)
 #define TLBIALLIS	__ACCESS_CP15(c8, 0, c3, 0)
 #define TLBIALL		__ACCESS_CP15(c8, 0, c7, 0)
diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index fa6f2174276b..bc70a1f0f42d 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -37,6 +37,8 @@
 
 #include <linux/highmem.h>
 #include <asm/cacheflush.h>
+#include <asm/cputype.h>
+#include <asm/kvm_hyp.h>
 #include <asm/pgalloc.h>
 #include <asm/stage2_pgtable.h>
 
@@ -83,6 +85,18 @@ static inline pmd_t kvm_s2pmd_mkwrite(pmd_t pmd)
 	return pmd;
 }
 
+static inline pte_t kvm_s2pte_mkexec(pte_t pte)
+{
+	pte_val(pte) &= ~L_PTE_XN;
+	return pte;
+}
+
+static inline pmd_t kvm_s2pmd_mkexec(pmd_t pmd)
+{
+	pmd_val(pmd) &= ~PMD_SECT_XN;
+	return pmd;
+}
+
 static inline void kvm_set_s2pte_readonly(pte_t *pte)
 {
 	pte_val(*pte) = (pte_val(*pte) & ~L_PTE_S2_RDWR) | L_PTE_S2_RDONLY;
@@ -93,6 +107,11 @@ static inline bool kvm_s2pte_readonly(pte_t *pte)
 	return (pte_val(*pte) & L_PTE_S2_RDWR) == L_PTE_S2_RDONLY;
 }
 
+static inline bool kvm_s2pte_exec(pte_t *pte)
+{
+	return !(pte_val(*pte) & L_PTE_XN);
+}
+
 static inline void kvm_set_s2pmd_readonly(pmd_t *pmd)
 {
 	pmd_val(*pmd) = (pmd_val(*pmd) & ~L_PMD_S2_RDWR) | L_PMD_S2_RDONLY;
@@ -103,6 +122,11 @@ static inline bool kvm_s2pmd_readonly(pmd_t *pmd)
 	return (pmd_val(*pmd) & L_PMD_S2_RDWR) == L_PMD_S2_RDONLY;
 }
 
+static inline bool kvm_s2pmd_exec(pmd_t *pmd)
+{
+	return !(pmd_val(*pmd) & PMD_SECT_XN);
+}
+
 static inline bool kvm_page_empty(void *ptr)
 {
 	struct page *ptr_page = virt_to_page(ptr);
@@ -126,10 +150,36 @@ static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu)
 	return (vcpu_cp15(vcpu, c1_SCTLR) & 0b101) == 0b101;
 }
 
-static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu,
-					       kvm_pfn_t pfn,
-					       unsigned long size)
+static inline void __clean_dcache_guest_page(kvm_pfn_t pfn, unsigned long size)
+{
+	/*
+	 * Clean the dcache to the Point of Coherency.
+	 *
+	 * We need to do this through a kernel mapping (using the
+	 * user-space mapping has proved to be the wrong
+	 * solution). For that, we need to kmap one page at a time,
+	 * and iterate over the range.
+	 */
+
+	VM_BUG_ON(size & ~PAGE_MASK);
+
+	while (size) {
+		void *va = kmap_atomic_pfn(pfn);
+
+		kvm_flush_dcache_to_poc(va, PAGE_SIZE);
+
+		size -= PAGE_SIZE;
+		pfn++;
+
+		kunmap_atomic(va);
+	}
+}
+
+static inline void __invalidate_icache_guest_page(kvm_pfn_t pfn,
+						  unsigned long size)
 {
+	u32 iclsz;
+
 	/*
 	 * If we are going to insert an instruction page and the icache is
 	 * either VIPT or PIPT, there is a potential problem where the host
@@ -141,23 +191,40 @@ static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu,
 	 *
 	 * VIVT caches are tagged using both the ASID and the VMID and doesn't
 	 * need any kind of flushing (DDI 0406C.b - Page B3-1392).
-	 *
-	 * We need to do this through a kernel mapping (using the
-	 * user-space mapping has proved to be the wrong
-	 * solution). For that, we need to kmap one page at a time,
-	 * and iterate over the range.
 	 */
 
 	VM_BUG_ON(size & ~PAGE_MASK);
 
+	if (icache_is_vivt_asid_tagged())
+		return;
+
+	if (!icache_is_pipt()) {
+		/* any kind of VIPT cache */
+		__flush_icache_all();
+		return;
+	}
+
+	/*
+	 * CTR IminLine contains Log2 of the number of words in the
+	 * cache line, so we can get the number of words as
+	 * 2 << (IminLine - 1).  To get the number of bytes, we
+	 * multiply by 4 (the number of bytes in a 32-bit word), and
+	 * get 4 << (IminLine).
+	 */
+	iclsz = 4 << (read_cpuid(CPUID_CACHETYPE) & 0xf);
+
 	while (size) {
 		void *va = kmap_atomic_pfn(pfn);
+		void *end = va + PAGE_SIZE;
+		void *addr = va;
 
-		kvm_flush_dcache_to_poc(va, PAGE_SIZE);
+		do {
+			write_sysreg(addr, ICIMVAU);
+			addr += iclsz;
+		} while (addr < end);
 
-		if (icache_is_pipt())
-			__cpuc_coherent_user_range((unsigned long)va,
-						   (unsigned long)va + PAGE_SIZE);
+		dsb(ishst);
+		isb();
 
 		size -= PAGE_SIZE;
 		pfn++;
@@ -165,9 +232,11 @@ static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu,
 		kunmap_atomic(va);
 	}
 
-	if (!icache_is_pipt() && !icache_is_vivt_asid_tagged()) {
-		/* any kind of VIPT cache */
-		__flush_icache_all();
+	/* Check if we need to invalidate the BTB */
+	if ((read_cpuid_ext(CPUID_EXT_MMFR1) >> 28) != 4) {
+		write_sysreg(0, BPIALLIS);
+		dsb(ishst);
+		isb();
 	}
 }
 
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index 150ece66ddf3..a757401129f9 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -102,8 +102,8 @@ extern pgprot_t		pgprot_s2_device;
 #define PAGE_HYP_EXEC		_MOD_PROT(pgprot_kernel, L_PTE_HYP | L_PTE_RDONLY)
 #define PAGE_HYP_RO		_MOD_PROT(pgprot_kernel, L_PTE_HYP | L_PTE_RDONLY | L_PTE_XN)
 #define PAGE_HYP_DEVICE		_MOD_PROT(pgprot_hyp_device, L_PTE_HYP)
-#define PAGE_S2			_MOD_PROT(pgprot_s2, L_PTE_S2_RDONLY)
-#define PAGE_S2_DEVICE		_MOD_PROT(pgprot_s2_device, L_PTE_S2_RDONLY)
+#define PAGE_S2			_MOD_PROT(pgprot_s2, L_PTE_S2_RDONLY | L_PTE_XN)
+#define PAGE_S2_DEVICE		_MOD_PROT(pgprot_s2_device, L_PTE_S2_RDONLY | L_PTE_XN)
 
 #define __PAGE_NONE		__pgprot(_L_PTE_DEFAULT | L_PTE_RDONLY | L_PTE_XN | L_PTE_NONE)
 #define __PAGE_SHARED		__pgprot(_L_PTE_DEFAULT | L_PTE_USER | L_PTE_XN)
diff --git a/arch/arm/kvm/hyp/switch.c b/arch/arm/kvm/hyp/switch.c
index 330c9ce34ba5..ae45ae96aac2 100644
--- a/arch/arm/kvm/hyp/switch.c
+++ b/arch/arm/kvm/hyp/switch.c
@@ -18,6 +18,7 @@
 
 #include <asm/kvm_asm.h>
 #include <asm/kvm_hyp.h>
+#include <asm/kvm_mmu.h>
 
 __asm__(".arch_extension     virt");
 
diff --git a/arch/arm/kvm/hyp/tlb.c b/arch/arm/kvm/hyp/tlb.c
index 6d810af2d9fd..c0edd450e104 100644
--- a/arch/arm/kvm/hyp/tlb.c
+++ b/arch/arm/kvm/hyp/tlb.c
@@ -19,6 +19,7 @@
  */
 
 #include <asm/kvm_hyp.h>
+#include <asm/kvm_mmu.h>
 
 /**
  * Flush per-VMID TLBs
diff --git a/arch/arm64/include/asm/asm-uaccess.h b/arch/arm64/include/asm/asm-uaccess.h
index b3da6c886835..03064261ee0b 100644
--- a/arch/arm64/include/asm/asm-uaccess.h
+++ b/arch/arm64/include/asm/asm-uaccess.h
@@ -25,13 +25,13 @@
 	isb
 	.endm
 
-	.macro	uaccess_ttbr0_disable, tmp1
+	.macro	uaccess_ttbr0_disable, tmp1, tmp2
 alternative_if_not ARM64_HAS_PAN
 	__uaccess_ttbr0_disable \tmp1
 alternative_else_nop_endif
 	.endm
 
-	.macro	uaccess_ttbr0_enable, tmp1, tmp2
+	.macro	uaccess_ttbr0_enable, tmp1, tmp2, tmp3
 alternative_if_not ARM64_HAS_PAN
 	save_and_disable_irq \tmp2		// avoid preemption
 	__uaccess_ttbr0_enable \tmp1
@@ -39,18 +39,18 @@ alternative_if_not ARM64_HAS_PAN
 alternative_else_nop_endif
 	.endm
 #else
-	.macro	uaccess_ttbr0_disable, tmp1
+	.macro	uaccess_ttbr0_disable, tmp1, tmp2
 	.endm
 
-	.macro	uaccess_ttbr0_enable, tmp1, tmp2
+	.macro	uaccess_ttbr0_enable, tmp1, tmp2, tmp3
 	.endm
 #endif
 
 /*
  * These macros are no-ops when UAO is present.
  */
-	.macro	uaccess_disable_not_uao, tmp1
-	uaccess_ttbr0_disable \tmp1
+	.macro	uaccess_disable_not_uao, tmp1, tmp2
+	uaccess_ttbr0_disable \tmp1, \tmp2
 alternative_if ARM64_ALT_PAN_NOT_UAO
 	SET_PSTATE_PAN(1)
 alternative_else_nop_endif
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index aef72d886677..0884e1fdfd30 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -388,6 +388,27 @@ alternative_endif
 	.endm
 
 /*
+ * Macro to perform an instruction cache maintenance for the interval
+ * [start, end)
+ *
+ * 	start, end:	virtual addresses describing the region
+ *	label:		A label to branch to on user fault.
+ * 	Corrupts:	tmp1, tmp2
+ */
+	.macro invalidate_icache_by_line start, end, tmp1, tmp2, label
+	icache_line_size \tmp1, \tmp2
+	sub	\tmp2, \tmp1, #1
+	bic	\tmp2, \start, \tmp2
+9997:
+USER(\label, ic	ivau, \tmp2)			// invalidate I line PoU
+	add	\tmp2, \tmp2, \tmp1
+	cmp	\tmp2, \end
+	b.lo	9997b
+	dsb	ish
+	isb
+	.endm
+
+/*
  * reset_pmuserenr_el0 - reset PMUSERENR_EL0 if PMUv3 present
  */
 	.macro	reset_pmuserenr_el0, tmpreg
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index 955130762a3c..bef9f418f089 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -52,6 +52,12 @@
  *		- start  - virtual start address
  *		- end    - virtual end address
  *
+ *	invalidate_icache_range(start, end)
+ *
+ *		Invalidate the I-cache in the region described by start, end.
+ *		- start  - virtual start address
+ *		- end    - virtual end address
+ *
  *	__flush_cache_user_range(start, end)
  *
  *		Ensure coherency between the I-cache and the D-cache in the
@@ -66,6 +72,7 @@
  *		- size   - region size
  */
 extern void flush_icache_range(unsigned long start, unsigned long end);
+extern int  invalidate_icache_range(unsigned long start, unsigned long end);
 extern void __flush_dcache_area(void *addr, size_t len);
 extern void __inval_dcache_area(void *addr, size_t len);
 extern void __clean_dcache_area_poc(void *addr, size_t len);
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index ea6cb5b24258..e7218cf7df2a 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -47,6 +47,8 @@
 	KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
 #define KVM_REQ_IRQ_PENDING	KVM_ARCH_REQ(1)
 
+DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
+
 int __attribute_const__ kvm_target_cpu(void);
 int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
 int kvm_arch_dev_ioctl_check_extension(struct kvm *kvm, long ext);
diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index 08d3bb66c8b7..f26f9cd70c72 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -20,7 +20,6 @@
 
 #include <linux/compiler.h>
 #include <linux/kvm_host.h>
-#include <asm/kvm_mmu.h>
 #include <asm/sysreg.h>
 
 #define __hyp_text __section(.hyp.text) notrace
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 672c8684d5c2..06f1f9794679 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -173,6 +173,18 @@ static inline pmd_t kvm_s2pmd_mkwrite(pmd_t pmd)
 	return pmd;
 }
 
+static inline pte_t kvm_s2pte_mkexec(pte_t pte)
+{
+	pte_val(pte) &= ~PTE_S2_XN;
+	return pte;
+}
+
+static inline pmd_t kvm_s2pmd_mkexec(pmd_t pmd)
+{
+	pmd_val(pmd) &= ~PMD_S2_XN;
+	return pmd;
+}
+
 static inline void kvm_set_s2pte_readonly(pte_t *pte)
 {
 	pteval_t old_pteval, pteval;
@@ -191,6 +203,11 @@ static inline bool kvm_s2pte_readonly(pte_t *pte)
 	return (pte_val(*pte) & PTE_S2_RDWR) == PTE_S2_RDONLY;
 }
 
+static inline bool kvm_s2pte_exec(pte_t *pte)
+{
+	return !(pte_val(*pte) & PTE_S2_XN);
+}
+
 static inline void kvm_set_s2pmd_readonly(pmd_t *pmd)
 {
 	kvm_set_s2pte_readonly((pte_t *)pmd);
@@ -201,6 +218,11 @@ static inline bool kvm_s2pmd_readonly(pmd_t *pmd)
 	return kvm_s2pte_readonly((pte_t *)pmd);
 }
 
+static inline bool kvm_s2pmd_exec(pmd_t *pmd)
+{
+	return !(pmd_val(*pmd) & PMD_S2_XN);
+}
+
 static inline bool kvm_page_empty(void *ptr)
 {
 	struct page *ptr_page = virt_to_page(ptr);
@@ -230,21 +252,25 @@ static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu)
 	return (vcpu_sys_reg(vcpu, SCTLR_EL1) & 0b101) == 0b101;
 }
 
-static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu,
-					       kvm_pfn_t pfn,
-					       unsigned long size)
+static inline void __clean_dcache_guest_page(kvm_pfn_t pfn, unsigned long size)
 {
 	void *va = page_address(pfn_to_page(pfn));
 
 	kvm_flush_dcache_to_poc(va, size);
+}
 
+static inline void __invalidate_icache_guest_page(kvm_pfn_t pfn,
+						  unsigned long size)
+{
 	if (icache_is_aliasing()) {
 		/* any kind of VIPT cache */
 		__flush_icache_all();
 	} else if (is_kernel_in_hyp_mode() || !icache_is_vpipt()) {
 		/* PIPT or VPIPT at EL2 (see comment in __kvm_tlb_flush_vmid_ipa) */
-		flush_icache_range((unsigned long)va,
-				   (unsigned long)va + size);
+		void *va = page_address(pfn_to_page(pfn));
+
+		invalidate_icache_range((unsigned long)va,
+					(unsigned long)va + size);
 	}
 }
 
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index eb0c2bd90de9..af035331fb09 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -177,9 +177,11 @@
  */
 #define PTE_S2_RDONLY		(_AT(pteval_t, 1) << 6)   /* HAP[2:1] */
 #define PTE_S2_RDWR		(_AT(pteval_t, 3) << 6)   /* HAP[2:1] */
+#define PTE_S2_XN		(_AT(pteval_t, 2) << 53)  /* XN[1:0] */
 
 #define PMD_S2_RDONLY		(_AT(pmdval_t, 1) << 6)   /* HAP[2:1] */
 #define PMD_S2_RDWR		(_AT(pmdval_t, 3) << 6)   /* HAP[2:1] */
+#define PMD_S2_XN		(_AT(pmdval_t, 2) << 53)  /* XN[1:0] */
 
 /*
  * Memory Attribute override for Stage-2 (MemAttr[3:0])
diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index 0a5635fb0ef9..4e12dabd342b 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -60,8 +60,8 @@
 #define PAGE_HYP_RO		__pgprot(_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY | PTE_HYP_XN)
 #define PAGE_HYP_DEVICE		__pgprot(PROT_DEVICE_nGnRE | PTE_HYP)
 
-#define PAGE_S2			__pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY)
-#define PAGE_S2_DEVICE		__pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_UXN)
+#define PAGE_S2			__pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY | PTE_S2_XN)
+#define PAGE_S2_DEVICE		__pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_S2_XN)
 
 #define PAGE_NONE		__pgprot(((_PAGE_DEFAULT) & ~PTE_VALID) | PTE_PROT_NONE | PTE_RDONLY | PTE_PXN | PTE_UXN)
 #define PAGE_SHARED		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE)
diff --git a/arch/arm64/kvm/hyp/debug-sr.c b/arch/arm64/kvm/hyp/debug-sr.c
index 321c9c05dd9e..360455f86346 100644
--- a/arch/arm64/kvm/hyp/debug-sr.c
+++ b/arch/arm64/kvm/hyp/debug-sr.c
@@ -21,6 +21,7 @@
 #include <asm/debug-monitors.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_hyp.h>
+#include <asm/kvm_mmu.h>
 
 #define read_debug(r,n)		read_sysreg(r##n##_el1)
 #define write_debug(v,r,n)	write_sysreg(v, r##n##_el1)
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index f7c651f3a8c0..f3d8bed096f5 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -21,6 +21,7 @@
 #include <asm/kvm_asm.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_hyp.h>
+#include <asm/kvm_mmu.h>
 #include <asm/fpsimd.h>
 #include <asm/debug-monitors.h>
 
diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c
index 73464a96c365..131c7772703c 100644
--- a/arch/arm64/kvm/hyp/tlb.c
+++ b/arch/arm64/kvm/hyp/tlb.c
@@ -16,6 +16,7 @@
  */
 
 #include <asm/kvm_hyp.h>
+#include <asm/kvm_mmu.h>
 #include <asm/tlbflush.h>
 
 static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm)
diff --git a/arch/arm64/lib/clear_user.S b/arch/arm64/lib/clear_user.S
index e88fb99c1561..8932e5f7a6f3 100644
--- a/arch/arm64/lib/clear_user.S
+++ b/arch/arm64/lib/clear_user.S
@@ -50,7 +50,7 @@ uao_user_alternative 9f, strh, sttrh, wzr, x0, 2
 	b.mi	5f
 uao_user_alternative 9f, strb, sttrb, wzr, x0, 0
 5:	mov	x0, #0
-	uaccess_disable_not_uao x2
+	uaccess_disable_not_uao x2, x3
 	ret
 ENDPROC(__clear_user)
 
diff --git a/arch/arm64/lib/copy_from_user.S b/arch/arm64/lib/copy_from_user.S
index 4b5d826895ff..bc108634992c 100644
--- a/arch/arm64/lib/copy_from_user.S
+++ b/arch/arm64/lib/copy_from_user.S
@@ -67,7 +67,7 @@ ENTRY(__arch_copy_from_user)
 	uaccess_enable_not_uao x3, x4
 	add	end, x0, x2
 #include "copy_template.S"
-	uaccess_disable_not_uao x3
+	uaccess_disable_not_uao x3, x4
 	mov	x0, #0				// Nothing to copy
 	ret
 ENDPROC(__arch_copy_from_user)
diff --git a/arch/arm64/lib/copy_in_user.S b/arch/arm64/lib/copy_in_user.S
index b24a830419ad..e6dd59dd4053 100644
--- a/arch/arm64/lib/copy_in_user.S
+++ b/arch/arm64/lib/copy_in_user.S
@@ -68,7 +68,7 @@ ENTRY(raw_copy_in_user)
 	uaccess_enable_not_uao x3, x4
 	add	end, x0, x2
 #include "copy_template.S"
-	uaccess_disable_not_uao x3
+	uaccess_disable_not_uao x3, x4
 	mov	x0, #0
 	ret
 ENDPROC(raw_copy_in_user)
diff --git a/arch/arm64/lib/copy_to_user.S b/arch/arm64/lib/copy_to_user.S
index 351f0766f7a6..bd20f9f7dd84 100644
--- a/arch/arm64/lib/copy_to_user.S
+++ b/arch/arm64/lib/copy_to_user.S
@@ -66,7 +66,7 @@ ENTRY(__arch_copy_to_user)
 	uaccess_enable_not_uao x3, x4
 	add	end, x0, x2
 #include "copy_template.S"
-	uaccess_disable_not_uao x3
+	uaccess_disable_not_uao x3, x4
 	mov	x0, #0
 	ret
 ENDPROC(__arch_copy_to_user)
diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S
index 7f1dbe962cf5..758bde7e2fa6 100644
--- a/arch/arm64/mm/cache.S
+++ b/arch/arm64/mm/cache.S
@@ -49,7 +49,7 @@ ENTRY(flush_icache_range)
  *	- end     - virtual end address of region
  */
 ENTRY(__flush_cache_user_range)
-	uaccess_ttbr0_enable x2, x3
+	uaccess_ttbr0_enable x2, x3, x4
 	dcache_line_size x2, x3
 	sub	x3, x2, #1
 	bic	x4, x0, x3
@@ -60,19 +60,10 @@ user_alt 9f, "dc cvau, x4",  "dc civac, x4",  ARM64_WORKAROUND_CLEAN_CACHE
 	b.lo	1b
 	dsb	ish
 
-	icache_line_size x2, x3
-	sub	x3, x2, #1
-	bic	x4, x0, x3
-1:
-USER(9f, ic	ivau, x4	)		// invalidate I line PoU
-	add	x4, x4, x2
-	cmp	x4, x1
-	b.lo	1b
-	dsb	ish
-	isb
+	invalidate_icache_by_line x0, x1, x2, x3, 9f
 	mov	x0, #0
 1:
-	uaccess_ttbr0_disable x1
+	uaccess_ttbr0_disable x1, x2
 	ret
 9:
 	mov	x0, #-EFAULT
@@ -81,6 +72,27 @@ ENDPROC(flush_icache_range)
 ENDPROC(__flush_cache_user_range)
 
 /*
+ *	invalidate_icache_range(start,end)
+ *
+ *	Ensure that the I cache is invalid within specified region.
+ *
+ *	- start   - virtual start address of region
+ *	- end     - virtual end address of region
+ */
+ENTRY(invalidate_icache_range)
+	uaccess_ttbr0_enable x2, x3, x4
+
+	invalidate_icache_by_line x0, x1, x2, x3, 2f
+	mov	x0, xzr
+1:
+	uaccess_ttbr0_disable x1, x2
+	ret
+2:
+	mov	x0, #-EFAULT
+	b	1b
+ENDPROC(invalidate_icache_range)
+
+/*
  *	__flush_dcache_area(kaddr, size)
  *
  *	Ensure that any D-cache lines for the interval [kaddr, kaddr+size)
diff --git a/arch/arm64/xen/hypercall.S b/arch/arm64/xen/hypercall.S
index 401ceb71540c..c5f05c4a4d00 100644
--- a/arch/arm64/xen/hypercall.S
+++ b/arch/arm64/xen/hypercall.S
@@ -101,12 +101,12 @@ ENTRY(privcmd_call)
 	 * need the explicit uaccess_enable/disable if the TTBR0 PAN emulation
 	 * is enabled (it implies that hardware UAO and PAN disabled).
 	 */
-	uaccess_ttbr0_enable x6, x7
+	uaccess_ttbr0_enable x6, x7, x8
 	hvc XEN_IMM
 
 	/*
 	 * Disable userspace access from kernel once the hyp call completed.
 	 */
-	uaccess_ttbr0_disable x6
+	uaccess_ttbr0_disable x6, x7
 	ret
 ENDPROC(privcmd_call);