Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Paolo Bonzini:
 "x86:

   - Support for userspace to emulate Xen hypercalls

   - Raise the maximum number of user memslots

   - Scalability improvements for the new MMU.

     Instead of the complex "fast page fault" logic that is used in
     mmu.c, tdp_mmu.c uses an rwlock so that page faults are concurrent,
     but the code that can run against page faults is limited. Right now
     only page faults take the lock for reading; in the future this will
     be extended to some cases of page table destruction. I hope to
     switch the default MMU around 5.12-rc3 (some testing was delayed
     due to Chinese New Year).

   - Cleanups for MAXPHYADDR checks

   - Use static calls for vendor-specific callbacks

   - On AMD, use VMLOAD/VMSAVE to save and restore host state

   - Stop using deprecated jump label APIs

   - Workaround for AMD erratum that made nested virtualization
     unreliable

   - Support for LBR emulation in the guest

   - Support for communicating bus lock vmexits to userspace

   - Add support for SEV attestation command

   - Miscellaneous cleanups

  PPC:

   - Support for second data watchpoint on POWER10

   - Remove some complex workarounds for buggy early versions of POWER9

   - Guest entry/exit fixes

  ARM64:

   - Make the nVHE EL2 object relocatable

   - Cleanups for concurrent translation faults hitting the same page

   - Support for the standard TRNG hypervisor call

   - A bunch of small PMU/Debug fixes

   - Simplification of the early init hypercall handling

  Non-KVM changes (with acks):

   - Detection of contended rwlocks (implemented only for qrwlocks,
     because KVM only needs it for x86)

   - Allow __DISABLE_EXPORTS from assembly code

   - Provide a saner follow_pfn replacements for modules"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (192 commits)
  KVM: x86/xen: Explicitly pad struct compat_vcpu_info to 64 bytes
  KVM: selftests: Don't bother mapping GVA for Xen shinfo test
  KVM: selftests: Fix hex vs. decimal snafu in Xen test
  KVM: selftests: Fix size of memslots created by Xen tests
  KVM: selftests: Ignore recently added Xen tests' build output
  KVM: selftests: Add missing header file needed by xAPIC IPI tests
  KVM: selftests: Add operand to vmsave/vmload/vmrun in svm.c
  KVM: SVM: Make symbol 'svm_gp_erratum_intercept' static
  locking/arch: Move qrwlock.h include after qspinlock.h
  KVM: PPC: Book3S HV: Fix host radix SLB optimisation with hash guests
  KVM: PPC: Book3S HV: Ensure radix guest has no SLB entries
  KVM: PPC: Don't always report hash MMU capability for P9 < DD2.2
  KVM: PPC: Book3S HV: Save and restore FSCR in the P9 path
  KVM: PPC: remove unneeded semicolon
  KVM: PPC: Book3S HV: Use POWER9 SLBIA IH=6 variant to clear SLB
  KVM: PPC: Book3S HV: No need to clear radix host SLB before loading HPT guest
  KVM: PPC: Book3S HV: Fix radix guest SLB side channel
  KVM: PPC: Book3S HV: Remove support for running HPT guest on RPT host without mixed mode support
  KVM: PPC: Book3S HV: Introduce new capability for 2nd DAWR
  KVM: PPC: Book3S HV: Add infrastructure to support 2nd DAWR
  ...

31 files changed, 829 insertions, 224 deletions

diff --git a/arch/arm64/include/asm/hyp_image.h b/arch/arm64/include/asm/hyp_image.h
index daa1a1da539e..737ded6b6d0d 100644
--- a/arch/arm64/include/asm/hyp_image.h
+++ b/arch/arm64/include/asm/hyp_image.h
@@ -7,6 +7,9 @@
 #ifndef __ARM64_HYP_IMAGE_H__
 #define __ARM64_HYP_IMAGE_H__
 
+#define __HYP_CONCAT(a, b)	a ## b
+#define HYP_CONCAT(a, b)	__HYP_CONCAT(a, b)
+
 /*
  * KVM nVHE code has its own symbol namespace prefixed with __kvm_nvhe_,
  * to separate it from the kernel proper.
@@ -21,9 +24,31 @@
  */
 #define HYP_SECTION_NAME(NAME)	.hyp##NAME
 
+/* Symbol defined at the beginning of each hyp section. */
+#define HYP_SECTION_SYMBOL_NAME(NAME) \
+	HYP_CONCAT(__hyp_section_, HYP_SECTION_NAME(NAME))
+
+/*
+ * Helper to generate linker script statements starting a hyp section.
+ *
+ * A symbol with a well-known name is defined at the first byte. This
+ * is used as a base for hyp relocations (see gen-hyprel.c). It must
+ * be defined inside the section so the linker of `vmlinux` cannot
+ * separate it from the section data.
+ */
+#define BEGIN_HYP_SECTION(NAME)				\
+	HYP_SECTION_NAME(NAME) : {			\
+		HYP_SECTION_SYMBOL_NAME(NAME) = .;
+
+/* Helper to generate linker script statements ending a hyp section. */
+#define END_HYP_SECTION					\
+	}
+
 /* Defines an ELF hyp section from input section @NAME and its subsections. */
-#define HYP_SECTION(NAME) \
-	HYP_SECTION_NAME(NAME) : { *(NAME NAME##.*) }
+#define HYP_SECTION(NAME)			\
+	BEGIN_HYP_SECTION(NAME)			\
+		*(NAME NAME##.*)		\
+	END_HYP_SECTION
 
 /*
  * Defines a linker script alias of a kernel-proper symbol referenced by
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 7ccf770c53d9..22d933e9b59e 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -199,26 +199,6 @@ extern void __vgic_v3_init_lrs(void);
 
 extern u32 __kvm_get_mdcr_el2(void);
 
-/*
- * Obtain the PC-relative address of a kernel symbol
- * s: symbol
- *
- * The goal of this macro is to return a symbol's address based on a
- * PC-relative computation, as opposed to a loading the VA from a
- * constant pool or something similar. This works well for HYP, as an
- * absolute VA is guaranteed to be wrong. Only use this if trying to
- * obtain the address of a symbol (i.e. not something you obtained by
- * following a pointer).
- */
-#define hyp_symbol_addr(s)						\
-	({								\
-		typeof(s) *addr;					\
-		asm("adrp	%0, %1\n"				\
-		    "add	%0, %0, :lo12:%1\n"			\
-		    : "=r" (addr) : "S" (&s));				\
-		addr;							\
-	})
-
 #define __KVM_EXTABLE(from, to)						\
 	"	.pushsection	__kvm_ex_table, \"a\"\n"		\
 	"	.align		3\n"					\
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 8fcfab0c2567..3d10e6527f7d 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -30,7 +30,6 @@
 
 #define __KVM_HAVE_ARCH_INTC_INITIALIZED
 
-#define KVM_USER_MEM_SLOTS 512
 #define KVM_HALT_POLL_NS_DEFAULT 500000
 
 #include <kvm/arm_vgic.h>
@@ -771,4 +770,6 @@ bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu);
 #define kvm_vcpu_has_pmu(vcpu)					\
 	(test_bit(KVM_ARM_VCPU_PMU_V3, (vcpu)->arch.features))
 
+int kvm_trng_call(struct kvm_vcpu *vcpu);
+
 #endif /* __ARM64_KVM_HOST_H__ */
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index e52d82aeadca..90873851f677 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -73,49 +73,39 @@ alternative_cb_end
 .endm
 
 /*
- * Convert a kernel image address to a PA
- * reg: kernel address to be converted in place
+ * Convert a hypervisor VA to a PA
+ * reg: hypervisor address to be converted in place
  * tmp: temporary register
- *
- * The actual code generation takes place in kvm_get_kimage_voffset, and
- * the instructions below are only there to reserve the space and
- * perform the register allocation (kvm_get_kimage_voffset uses the
- * specific registers encoded in the instructions).
  */
-.macro kimg_pa reg, tmp
-alternative_cb kvm_get_kimage_voffset
-	movz	\tmp, #0
-	movk	\tmp, #0, lsl #16
-	movk	\tmp, #0, lsl #32
-	movk	\tmp, #0, lsl #48
-alternative_cb_end
-
-	/* reg = __pa(reg) */
-	sub	\reg, \reg, \tmp
+.macro hyp_pa reg, tmp
+	ldr_l	\tmp, hyp_physvirt_offset
+	add	\reg, \reg, \tmp
 .endm
 
 /*
- * Convert a kernel image address to a hyp VA
- * reg: kernel address to be converted in place
+ * Convert a hypervisor VA to a kernel image address
+ * reg: hypervisor address to be converted in place
  * tmp: temporary register
  *
  * The actual code generation takes place in kvm_get_kimage_voffset, and
  * the instructions below are only there to reserve the space and
- * perform the register allocation (kvm_update_kimg_phys_offset uses the
+ * perform the register allocation (kvm_get_kimage_voffset uses the
  * specific registers encoded in the instructions).
  */
-.macro kimg_hyp_va reg, tmp
-alternative_cb kvm_update_kimg_phys_offset
+.macro hyp_kimg_va reg, tmp
+	/* Convert hyp VA -> PA. */
+	hyp_pa	\reg, \tmp
+
+	/* Load kimage_voffset. */
+alternative_cb kvm_get_kimage_voffset
 	movz	\tmp, #0
 	movk	\tmp, #0, lsl #16
 	movk	\tmp, #0, lsl #32
 	movk	\tmp, #0, lsl #48
 alternative_cb_end
 
-	sub	\reg, \reg, \tmp
-	mov_q	\tmp, PAGE_OFFSET
-	orr	\reg, \reg, \tmp
-	kern_hyp_va \reg
+	/* Convert PA -> kimg VA. */
+	add	\reg, \reg, \tmp
 .endm
 
 #else
@@ -129,6 +119,7 @@ alternative_cb_end
 void kvm_update_va_mask(struct alt_instr *alt,
 			__le32 *origptr, __le32 *updptr, int nr_inst);
 void kvm_compute_layout(void);
+void kvm_apply_hyp_relocations(void);
 
 static __always_inline unsigned long __kern_hyp_va(unsigned long v)
 {
@@ -144,24 +135,6 @@ static __always_inline unsigned long __kern_hyp_va(unsigned long v)
 
 #define kern_hyp_va(v) 	((typeof(v))(__kern_hyp_va((unsigned long)(v))))
 
-static __always_inline unsigned long __kimg_hyp_va(unsigned long v)
-{
-	unsigned long offset;
-
-	asm volatile(ALTERNATIVE_CB("movz %0, #0\n"
-				    "movk %0, #0, lsl #16\n"
-				    "movk %0, #0, lsl #32\n"
-				    "movk %0, #0, lsl #48\n",
-				    kvm_update_kimg_phys_offset)
-		     : "=r" (offset));
-
-	return __kern_hyp_va((v - offset) | PAGE_OFFSET);
-}
-
-#define kimg_fn_hyp_va(v) 	((typeof(*v))(__kimg_hyp_va((unsigned long)(v))))
-
-#define kimg_fn_ptr(x)	(typeof(x) **)(x)
-
 /*
  * We currently support using a VM-specified IPA size. For backward
  * compatibility, the default IPA size is fixed to 40bits.
diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
index 52ab38db04c7..8886d43cfb11 100644
--- a/arch/arm64/include/asm/kvm_pgtable.h
+++ b/arch/arm64/include/asm/kvm_pgtable.h
@@ -157,6 +157,11 @@ void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt);
  * If device attributes are not explicitly requested in @prot, then the
  * mapping will be normal, cacheable.
  *
+ * Note that the update of a valid leaf PTE in this function will be aborted,
+ * if it's trying to recreate the exact same mapping or only change the access
+ * permissions. Instead, the vCPU will exit one more time from guest if still
+ * needed and then go through the path of relaxing permissions.
+ *
  * Note that this function will both coalesce existing table entries and split
  * existing block mappings, relying on page-faults to fault back areas outside
  * of the new mapping lazily.
diff --git a/arch/arm64/include/asm/sections.h b/arch/arm64/include/asm/sections.h
index 8ff579361731..2f36b16a5b5d 100644
--- a/arch/arm64/include/asm/sections.h
+++ b/arch/arm64/include/asm/sections.h
@@ -11,7 +11,8 @@ extern char __alt_instructions[], __alt_instructions_end[];
 extern char __hibernate_exit_text_start[], __hibernate_exit_text_end[];
 extern char __hyp_idmap_text_start[], __hyp_idmap_text_end[];
 extern char __hyp_text_start[], __hyp_text_end[];
-extern char __hyp_data_ro_after_init_start[], __hyp_data_ro_after_init_end[];
+extern char __hyp_rodata_start[], __hyp_rodata_end[];
+extern char __hyp_reloc_begin[], __hyp_reloc_end[];
 extern char __idmap_text_start[], __idmap_text_end[];
 extern char __initdata_begin[], __initdata_end[];
 extern char __inittext_begin[], __inittext_end[];
diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h
index 9083d6992603..0525c0b089ed 100644
--- a/arch/arm64/include/asm/spinlock.h
+++ b/arch/arm64/include/asm/spinlock.h
@@ -5,8 +5,8 @@
 #ifndef __ASM_SPINLOCK_H
 #define __ASM_SPINLOCK_H
 
-#include <asm/qrwlock.h>
 #include <asm/qspinlock.h>
+#include <asm/qrwlock.h>
 
 /* See include/linux/spinlock.h */
 #define smp_mb__after_spinlock()	smp_mb()
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 767bb2d47be9..f9fbbb4734e8 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -853,7 +853,10 @@
 
 #define ID_DFR0_PERFMON_SHIFT		24
 
+#define ID_DFR0_PERFMON_8_0		0x3
 #define ID_DFR0_PERFMON_8_1		0x4
+#define ID_DFR0_PERFMON_8_4		0x5
+#define ID_DFR0_PERFMON_8_5		0x6
 
 #define ID_ISAR4_SWP_FRAC_SHIFT		28
 #define ID_ISAR4_PSR_M_SHIFT		24
diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index f676243abac6..23f1a557bd9f 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -64,7 +64,6 @@ __efistub__ctype		= _ctype;
 /* Alternative callbacks for init-time patching of nVHE hyp code. */
 KVM_NVHE_ALIAS(kvm_patch_vector_branch);
 KVM_NVHE_ALIAS(kvm_update_va_mask);
-KVM_NVHE_ALIAS(kvm_update_kimg_phys_offset);
 KVM_NVHE_ALIAS(kvm_get_kimage_voffset);
 
 /* Global kernel state accessed by nVHE hyp code. */
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index ad00f99ee9b0..357590beaabb 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -434,8 +434,10 @@ static void __init hyp_mode_check(void)
 			   "CPU: CPUs started in inconsistent modes");
 	else
 		pr_info("CPU: All CPU(s) started at EL1\n");
-	if (IS_ENABLED(CONFIG_KVM) && !is_kernel_in_hyp_mode())
+	if (IS_ENABLED(CONFIG_KVM) && !is_kernel_in_hyp_mode()) {
 		kvm_compute_layout();
+		kvm_apply_hyp_relocations();
+	}
 }
 
 void __init smp_cpus_done(unsigned int max_cpus)
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 68f76a96c60b..7eea7888bb02 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -31,10 +31,11 @@ jiffies = jiffies_64;
 	__stop___kvm_ex_table = .;
 
 #define HYPERVISOR_DATA_SECTIONS				\
-	HYP_SECTION_NAME(.data..ro_after_init) : {		\
-		__hyp_data_ro_after_init_start = .;		\
+	HYP_SECTION_NAME(.rodata) : {				\
+		__hyp_rodata_start = .;				\
 		*(HYP_SECTION_NAME(.data..ro_after_init))	\
-		__hyp_data_ro_after_init_end = .;		\
+		*(HYP_SECTION_NAME(.rodata))			\
+		__hyp_rodata_end = .;				\
 	}
 
 #define HYPERVISOR_PERCPU_SECTION				\
@@ -42,10 +43,19 @@ jiffies = jiffies_64;
 	HYP_SECTION_NAME(.data..percpu) : {			\
 		*(HYP_SECTION_NAME(.data..percpu))		\
 	}
+
+#define HYPERVISOR_RELOC_SECTION				\
+	.hyp.reloc : ALIGN(4) {					\
+		__hyp_reloc_begin = .;				\
+		*(.hyp.reloc)					\
+		__hyp_reloc_end = .;				\
+	}
+
 #else /* CONFIG_KVM */
 #define HYPERVISOR_EXTABLE
 #define HYPERVISOR_DATA_SECTIONS
 #define HYPERVISOR_PERCPU_SECTION
+#define HYPERVISOR_RELOC_SECTION
 #endif
 
 #define HYPERVISOR_TEXT					\
@@ -216,6 +226,8 @@ SECTIONS
 	PERCPU_SECTION(L1_CACHE_BYTES)
 	HYPERVISOR_PERCPU_SECTION
 
+	HYPERVISOR_RELOC_SECTION
+
 	.rela.dyn : ALIGN(8) {
 		*(.rela .rela*)
 	}
diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile
index 13b017284bf9..589921392cb1 100644
--- a/arch/arm64/kvm/Makefile
+++ b/arch/arm64/kvm/Makefile
@@ -16,7 +16,7 @@ kvm-y := $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o \
 	 inject_fault.o va_layout.o handle_exit.o \
 	 guest.o debug.o reset.o sys_regs.o \
 	 vgic-sys-reg-v3.o fpsimd.o pmu.o \
-	 arch_timer.o \
+	 arch_timer.o trng.o\
 	 vgic/vgic.o vgic/vgic-init.o \
 	 vgic/vgic-irqfd.o vgic/vgic-v2.o \
 	 vgic/vgic-v3.o vgic/vgic-v4.o \
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 6804c5673312..fc4c95dd2d26 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -1750,11 +1750,10 @@ static int init_hyp_mode(void)
 		goto out_err;
 	}
 
-	err = create_hyp_mappings(kvm_ksym_ref(__hyp_data_ro_after_init_start),
-				  kvm_ksym_ref(__hyp_data_ro_after_init_end),
-				  PAGE_HYP_RO);
+	err = create_hyp_mappings(kvm_ksym_ref(__hyp_rodata_start),
+				  kvm_ksym_ref(__hyp_rodata_end), PAGE_HYP_RO);
 	if (err) {
-		kvm_err("Cannot map .hyp.data..ro_after_init section\n");
+		kvm_err("Cannot map .hyp.rodata section\n");
 		goto out_err;
 	}
 
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 84473574c2e7..54f4860cd87c 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -505,8 +505,8 @@ static inline void __kvm_unexpected_el2_exception(void)
 	struct exception_table_entry *entry, *end;
 	unsigned long elr_el2 = read_sysreg(elr_el2);
 
-	entry = hyp_symbol_addr(__start___kvm_ex_table);
-	end = hyp_symbol_addr(__stop___kvm_ex_table);
+	entry = &__start___kvm_ex_table;
+	end = &__stop___kvm_ex_table;
 
 	while (entry < end) {
 		addr = (unsigned long)&entry->insn + entry->insn;
diff --git a/arch/arm64/kvm/hyp/nvhe/.gitignore b/arch/arm64/kvm/hyp/nvhe/.gitignore
index 695d73d0249e..5b6c43cc96f8 100644
--- a/arch/arm64/kvm/hyp/nvhe/.gitignore
+++ b/arch/arm64/kvm/hyp/nvhe/.gitignore
@@ -1,2 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
+gen-hyprel
 hyp.lds
+hyp-reloc.S
diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile
index 1f1e351c5fe2..a6707df4f6c0 100644
--- a/arch/arm64/kvm/hyp/nvhe/Makefile
+++ b/arch/arm64/kvm/hyp/nvhe/Makefile
@@ -3,8 +3,11 @@
 # Makefile for Kernel-based Virtual Machine module, HYP/nVHE part
 #
 
-asflags-y := -D__KVM_NVHE_HYPERVISOR__
-ccflags-y := -D__KVM_NVHE_HYPERVISOR__
+asflags-y := -D__KVM_NVHE_HYPERVISOR__ -D__DISABLE_EXPORTS
+ccflags-y := -D__KVM_NVHE_HYPERVISOR__ -D__DISABLE_EXPORTS
+
+hostprogs := gen-hyprel
+HOST_EXTRACFLAGS += -I$(objtree)/include
 
 obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o hyp-init.o host.o \
 	 hyp-main.o hyp-smp.o psci-relay.o
@@ -19,7 +22,7 @@ obj-y += ../vgic-v3-sr.o ../aarch32.o ../vgic-v2-cpuif-proxy.o ../entry.o \
 
 hyp-obj := $(patsubst %.o,%.nvhe.o,$(obj-y))
 obj-y := kvm_nvhe.o
-extra-y := $(hyp-obj) kvm_nvhe.tmp.o hyp.lds
+extra-y := $(hyp-obj) kvm_nvhe.tmp.o kvm_nvhe.rel.o hyp.lds hyp-reloc.S hyp-reloc.o
 
 # 1) Compile all source files to `.nvhe.o` object files. The file extension
 #    avoids file name clashes for files shared with VHE.
@@ -42,11 +45,31 @@ LDFLAGS_kvm_nvhe.tmp.o := -r -T
 $(obj)/kvm_nvhe.tmp.o: $(obj)/hyp.lds $(addprefix $(obj)/,$(hyp-obj)) FORCE
 	$(call if_changed,ld)
 
-# 4) Produce the final 'kvm_nvhe.o', ready to be linked into 'vmlinux'.
+# 4) Generate list of hyp code/data positions that need to be relocated at
+#    runtime. Because the hypervisor is part of the kernel binary, relocations
+#    produce a kernel VA. We enumerate relocations targeting hyp at build time
+#    and convert the kernel VAs at those positions to hyp VAs.
+$(obj)/hyp-reloc.S: $(obj)/kvm_nvhe.tmp.o $(obj)/gen-hyprel
+	$(call if_changed,hyprel)
+
+# 5) Compile hyp-reloc.S and link it into the existing partially linked object.
+#    The object file now contains a section with pointers to hyp positions that
+#    will contain kernel VAs at runtime. These pointers have relocations on them
+#    so that they get updated as the hyp object is linked into `vmlinux`.
+LDFLAGS_kvm_nvhe.rel.o := -r
+$(obj)/kvm_nvhe.rel.o: $(obj)/kvm_nvhe.tmp.o $(obj)/hyp-reloc.o FORCE
+	$(call if_changed,ld)
+
+# 6) Produce the final 'kvm_nvhe.o', ready to be linked into 'vmlinux'.
 #    Prefixes names of ELF symbols with '__kvm_nvhe_'.
-$(obj)/kvm_nvhe.o: $(obj)/kvm_nvhe.tmp.o FORCE
+$(obj)/kvm_nvhe.o: $(obj)/kvm_nvhe.rel.o FORCE
 	$(call if_changed,hypcopy)
 
+# The HYPREL command calls `gen-hyprel` to generate an assembly file with
+# a list of relocations targeting hyp code/data.
+quiet_cmd_hyprel = HYPREL  $@
+      cmd_hyprel = $(obj)/gen-hyprel $< > $@
+
 # The HYPCOPY command uses `objcopy` to prefix all ELF symbol names
 # to avoid clashes with VHE code/data.
 quiet_cmd_hypcopy = HYPCOPY $@
diff --git a/arch/arm64/kvm/hyp/nvhe/gen-hyprel.c b/arch/arm64/kvm/hyp/nvhe/gen-hyprel.c
new file mode 100644
index 000000000000..ead02c6a7628
--- /dev/null
+++ b/arch/arm64/kvm/hyp/nvhe/gen-hyprel.c
@@ -0,0 +1,438 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020 - Google LLC
+ * Author: David Brazdil <dbrazdil@google.com>
+ *
+ * Generates relocation information used by the kernel to convert
+ * absolute addresses in hyp data from kernel VAs to hyp VAs.
+ *
+ * This is necessary because hyp code is linked into the same binary
+ * as the kernel but executes under different memory mappings.
+ * If the compiler used absolute addressing, those addresses need to
+ * be converted before they are used by hyp code.
+ *
+ * The input of this program is the relocatable ELF object containing
+ * all hyp code/data, not yet linked into vmlinux. Hyp section names
+ * should have been prefixed with `.hyp` at this point.
+ *
+ * The output (printed to stdout) is an assembly file containing
+ * an array of 32-bit integers and static relocations that instruct
+ * the linker of `vmlinux` to populate the array entries with offsets
+ * to positions in the kernel binary containing VAs used by hyp code.
+ *
+ * Note that dynamic relocations could be used for the same purpose.
+ * However, those are only generated if CONFIG_RELOCATABLE=y.
+ */
+
+#include <elf.h>
+#include <endian.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/mman.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+
+#include <generated/autoconf.h>
+
+#define HYP_SECTION_PREFIX		".hyp"
+#define HYP_RELOC_SECTION		".hyp.reloc"
+#define HYP_SECTION_SYMBOL_PREFIX	"__hyp_section_"
+
+/*
+ * AArch64 relocation type constants.
+ * Included in case these are not defined in the host toolchain.
+ */
+#ifndef R_AARCH64_ABS64
+#define R_AARCH64_ABS64			257
+#endif
+#ifndef R_AARCH64_LD_PREL_LO19
+#define R_AARCH64_LD_PREL_LO19		273
+#endif
+#ifndef R_AARCH64_ADR_PREL_LO21
+#define R_AARCH64_ADR_PREL_LO21		274
+#endif
+#ifndef R_AARCH64_ADR_PREL_PG_HI21
+#define R_AARCH64_ADR_PREL_PG_HI21	275
+#endif
+#ifndef R_AARCH64_ADR_PREL_PG_HI21_NC
+#define R_AARCH64_ADR_PREL_PG_HI21_NC	276
+#endif
+#ifndef R_AARCH64_ADD_ABS_LO12_NC
+#define R_AARCH64_ADD_ABS_LO12_NC	277
+#endif
+#ifndef R_AARCH64_LDST8_ABS_LO12_NC
+#define R_AARCH64_LDST8_ABS_LO12_NC	278
+#endif
+#ifndef R_AARCH64_TSTBR14
+#define R_AARCH64_TSTBR14		279
+#endif
+#ifndef R_AARCH64_CONDBR19
+#define R_AARCH64_CONDBR19		280
+#endif
+#ifndef R_AARCH64_JUMP26
+#define R_AARCH64_JUMP26		282
+#endif
+#ifndef R_AARCH64_CALL26
+#define R_AARCH64_CALL26		283
+#endif
+#ifndef R_AARCH64_LDST16_ABS_LO12_NC
+#define R_AARCH64_LDST16_ABS_LO12_NC	284
+#endif
+#ifndef R_AARCH64_LDST32_ABS_LO12_NC
+#define R_AARCH64_LDST32_ABS_LO12_NC	285
+#endif
+#ifndef R_AARCH64_LDST64_ABS_LO12_NC
+#define R_AARCH64_LDST64_ABS_LO12_NC	286
+#endif
+#ifndef R_AARCH64_MOVW_PREL_G0
+#define R_AARCH64_MOVW_PREL_G0		287
+#endif
+#ifndef R_AARCH64_MOVW_PREL_G0_NC
+#define R_AARCH64_MOVW_PREL_G0_NC	288
+#endif
+#ifndef R_AARCH64_MOVW_PREL_G1
+#define R_AARCH64_MOVW_PREL_G1		289
+#endif
+#ifndef R_AARCH64_MOVW_PREL_G1_NC
+#define R_AARCH64_MOVW_PREL_G1_NC	290
+#endif
+#ifndef R_AARCH64_MOVW_PREL_G2
+#define R_AARCH64_MOVW_PREL_G2		291
+#endif
+#ifndef R_AARCH64_MOVW_PREL_G2_NC
+#define R_AARCH64_MOVW_PREL_G2_NC	292
+#endif
+#ifndef R_AARCH64_MOVW_PREL_G3
+#define R_AARCH64_MOVW_PREL_G3		293
+#endif
+#ifndef R_AARCH64_LDST128_ABS_LO12_NC
+#define R_AARCH64_LDST128_ABS_LO12_NC	299
+#endif
+
+/* Global state of the processed ELF. */
+static struct {
+	const char	*path;
+	char		*begin;
+	size_t		size;
+	Elf64_Ehdr	*ehdr;
+	Elf64_Shdr	*sh_table;
+	const char	*sh_string;
+} elf;
+
+#if defined(CONFIG_CPU_LITTLE_ENDIAN)
+
+#define elf16toh(x)	le16toh(x)
+#define elf32toh(x)	le32toh(x)
+#define elf64toh(x)	le64toh(x)
+
+#define ELFENDIAN	ELFDATA2LSB
+
+#elif defined(CONFIG_CPU_BIG_ENDIAN)
+
+#define elf16toh(x)	be16toh(x)
+#define elf32toh(x)	be32toh(x)
+#define elf64toh(x)	be64toh(x)
+
+#define ELFENDIAN	ELFDATA2MSB
+
+#else
+
+#error PDP-endian sadly unsupported...
+
+#endif
+
+#define fatal_error(fmt, ...)						\
+	({								\
+		fprintf(stderr, "error: %s: " fmt "\n",			\
+			elf.path, ## __VA_ARGS__);			\
+		exit(EXIT_FAILURE);					\
+		__builtin_unreachable();				\
+	})
+
+#define fatal_perror(msg)						\
+	({								\
+		fprintf(stderr, "error: %s: " msg ": %s\n",		\
+			elf.path, strerror(errno));			\
+		exit(EXIT_FAILURE);					\
+		__builtin_unreachable();				\
+	})
+
+#define assert_op(lhs, rhs, fmt, op)					\
+	({								\
+		typeof(lhs) _lhs = (lhs);				\
+		typeof(rhs) _rhs = (rhs);				\
+									\
+		if (!(_lhs op _rhs)) {					\
+			fatal_error("assertion " #lhs " " #op " " #rhs	\
+				" failed (lhs=" fmt ", rhs=" fmt	\
+				", line=%d)", _lhs, _rhs, __LINE__);	\
+		}							\
+	})
+
+#define assert_eq(lhs, rhs, fmt)	assert_op(lhs, rhs, fmt, ==)
+#define assert_ne(lhs, rhs, fmt)	assert_op(lhs, rhs, fmt, !=)
+#define assert_lt(lhs, rhs, fmt)	assert_op(lhs, rhs, fmt, <)
+#define assert_ge(lhs, rhs, fmt)	assert_op(lhs, rhs, fmt, >=)
+
+/*
+ * Return a pointer of a given type at a given offset from
+ * the beginning of the ELF file.
+ */
+#define elf_ptr(type, off) ((type *)(elf.begin + (off)))
+
+/* Iterate over all sections in the ELF. */
+#define for_each_section(var) \
+	for (var = elf.sh_table; var < elf.sh_table + elf16toh(elf.ehdr->e_shnum); ++var)
+
+/* Iterate over all Elf64_Rela relocations in a given section. */
+#define for_each_rela(shdr, var)					\
+	for (var = elf_ptr(Elf64_Rela, elf64toh(shdr->sh_offset));	\
+	     var < elf_ptr(Elf64_Rela, elf64toh(shdr->sh_offset) + elf64toh(shdr->sh_size)); var++)
+
+/* True if a string starts with a given prefix. */
+static inline bool starts_with(const char *str, const char *prefix)
+{
+	return memcmp(str, prefix, strlen(prefix)) == 0;
+}
+
+/* Returns a string containing the name of a given section. */
+static inline const char *section_name(Elf64_Shdr *shdr)
+{
+	return elf.sh_string + elf32toh(shdr->sh_name);
+}
+
+/* Returns a pointer to the first byte of section data. */
+static inline const char *section_begin(Elf64_Shdr *shdr)
+{
+	return elf_ptr(char, elf64toh(shdr->sh_offset));
+}
+
+/* Find a section by its offset from the beginning of the file. */
+static inline Elf64_Shdr *section_by_off(Elf64_Off off)
+{
+	assert_ne(off, 0UL, "%lu");
+	return elf_ptr(Elf64_Shdr, off);
+}
+
+/* Find a section by its index. */
+static inline Elf64_Shdr *section_by_idx(uint16_t idx)
+{
+	assert_ne(idx, SHN_UNDEF, "%u");
+	return &elf.sh_table[idx];
+}
+
+/*
+ * Memory-map the given ELF file, perform sanity checks, and
+ * populate global state.
+ */
+static void init_elf(const char *path)
+{
+	int fd, ret;
+	struct stat stat;
+
+	/* Store path in the global struct for error printing. */
+	elf.path = path;
+
+	/* Open the ELF file. */
+	fd = open(path, O_RDONLY);
+	if (fd < 0)
+		fatal_perror("Could not open ELF file");
+
+	/* Get status of ELF file to obtain its size. */
+	ret = fstat(fd, &stat);
+	if (ret < 0) {
+		close(fd);
+		fatal_perror("Could not get status of ELF file");
+	}
+
+	/* mmap() the entire ELF file read-only at an arbitrary address. */
+	elf.begin = mmap(0, stat.st_size, PROT_READ, MAP_PRIVATE, fd, 0);
+	if (elf.begin == MAP_FAILED) {
+		close(fd);
+		fatal_perror("Could not mmap ELF file");
+	}
+
+	/* mmap() was successful, close the FD. */
+	close(fd);
+
+	/* Get pointer to the ELF header. */
+	assert_ge(stat.st_size, sizeof(*elf.ehdr), "%lu");
+	elf.ehdr = elf_ptr(Elf64_Ehdr, 0);
+
+	/* Check the ELF magic. */
+	assert_eq(elf.ehdr->e_ident[EI_MAG0], ELFMAG0, "0x%x");
+	assert_eq(elf.ehdr->e_ident[EI_MAG1], ELFMAG1, "0x%x");
+	assert_eq(elf.ehdr->e_ident[EI_MAG2], ELFMAG2, "0x%x");
+	assert_eq(elf.ehdr->e_ident[EI_MAG3], ELFMAG3, "0x%x");
+
+	/* Sanity check that this is an ELF64 relocatable object for AArch64. */
+	assert_eq(elf.ehdr->e_ident[EI_CLASS], ELFCLASS64, "%u");
+	assert_eq(elf.ehdr->e_ident[EI_DATA], ELFENDIAN, "%u");
+	assert_eq(elf16toh(elf.ehdr->e_type), ET_REL, "%u");
+	assert_eq(elf16toh(elf.ehdr->e_machine), EM_AARCH64, "%u");
+
+	/* Populate fields of the global struct. */
+	elf.sh_table = section_by_off(elf64toh(elf.ehdr->e_shoff));
+	elf.sh_string = section_begin(section_by_idx(elf16toh(elf.ehdr->e_shstrndx)));
+}
+
+/* Print the prologue of the output ASM file. */
+static void emit_prologue(void)
+{
+	printf(".data\n"
+	       ".pushsection " HYP_RELOC_SECTION ", \"a\"\n");
+}
+
+/* Print ASM statements needed as a prologue to a processed hyp section. */
+static void emit_section_prologue(const char *sh_orig_name)
+{
+	/* Declare the hyp section symbol. */
+	printf(".global %s%s\n", HYP_SECTION_SYMBOL_PREFIX, sh_orig_name);
+}
+
+/*
+ * Print ASM statements to create a hyp relocation entry for a given
+ * R_AARCH64_ABS64 relocation.
+ *
+ * The linker of vmlinux will populate the position given by `rela` with
+ * an absolute 64-bit kernel VA. If the kernel is relocatable, it will
+ * also generate a dynamic relocation entry so that the kernel can shift
+ * the address at runtime for KASLR.
+ *
+ * Emit a 32-bit offset from the current address to the position given
+ * by `rela`. This way the kernel can iterate over all kernel VAs used
+ * by hyp at runtime and convert them to hyp VAs. However, that offset
+ * will not be known until linking of `vmlinux`, so emit a PREL32
+ * relocation referencing a symbol that the hyp linker script put at
+ * the beginning of the relocated section + the offset from `rela`.
+ */
+static void emit_rela_abs64(Elf64_Rela *rela, const char *sh_orig_name)
+{
+	/* Offset of this reloc from the beginning of HYP_RELOC_SECTION. */
+	static size_t reloc_offset;
+
+	/* Create storage for the 32-bit offset. */
+	printf(".word 0\n");
+
+	/*
+	 * Create a PREL32 relocation which instructs the linker of `vmlinux`
+	 * to insert offset to position <base> + <offset>, where <base> is
+	 * a symbol at the beginning of the relocated section, and <offset>
+	 * is `rela->r_offset`.
+	 */
+	printf(".reloc %lu, R_AARCH64_PREL32, %s%s + 0x%lx\n",
+	       reloc_offset, HYP_SECTION_SYMBOL_PREFIX, sh_orig_name,
+	       elf64toh(rela->r_offset));
+
+	reloc_offset += 4;
+}
+
+/* Print the epilogue of the output ASM file. */
+static void emit_epilogue(void)
+{
+	printf(".popsection\n");
+}
+
+/*
+ * Iterate over all RELA relocations in a given section and emit
+ * hyp relocation data for all absolute addresses in hyp code/data.
+ *
+ * Static relocations that generate PC-relative-addressing are ignored.
+ * Failure is reported for unexpected relocation types.
+ */
+static void emit_rela_section(Elf64_Shdr *sh_rela)
+{
+	Elf64_Shdr *sh_orig = &elf.sh_table[elf32toh(sh_rela->sh_info)];
+	const char *sh_orig_name = section_name(sh_orig);
+	Elf64_Rela *rela;
+
+	/* Skip all non-hyp sections. */
+	if (!starts_with(sh_orig_name, HYP_SECTION_PREFIX))
+		return;
+
+	emit_section_prologue(sh_orig_name);
+
+	for_each_rela(sh_rela, rela) {
+		uint32_t type = (uint32_t)elf64toh(rela->r_info);
+
+		/* Check that rela points inside the relocated section. */
+		assert_lt(elf64toh(rela->r_offset), elf64toh(sh_orig->sh_size), "0x%lx");
+
+		switch (type) {
+		/*
+		 * Data relocations to generate absolute addressing.
+		 * Emit a hyp relocation.
+		 */
+		case R_AARCH64_ABS64:
+			emit_rela_abs64(rela, sh_orig_name);
+			break;
+		/* Allow relocations to generate PC-relative addressing. */
+		case R_AARCH64_LD_PREL_LO19:
+		case R_AARCH64_ADR_PREL_LO21:
+		case R_AARCH64_ADR_PREL_PG_HI21:
+		case R_AARCH64_ADR_PREL_PG_HI21_NC:
+		case R_AARCH64_ADD_ABS_LO12_NC:
+		case R_AARCH64_LDST8_ABS_LO12_NC:
+		case R_AARCH64_LDST16_ABS_LO12_NC:
+		case R_AARCH64_LDST32_ABS_LO12_NC:
+		case R_AARCH64_LDST64_ABS_LO12_NC:
+		case R_AARCH64_LDST128_ABS_LO12_NC:
+			break;
+		/* Allow relative relocations for control-flow instructions. */
+		case R_AARCH64_TSTBR14:
+		case R_AARCH64_CONDBR19:
+		case R_AARCH64_JUMP26:
+		case R_AARCH64_CALL26:
+			break;
+		/* Allow group relocations to create PC-relative offset inline. */
+		case R_AARCH64_MOVW_PREL_G0:
+		case R_AARCH64_MOVW_PREL_G0_NC:
+		case R_AARCH64_MOVW_PREL_G1:
+		case R_AARCH64_MOVW_PREL_G1_NC:
+		case R_AARCH64_MOVW_PREL_G2:
+		case R_AARCH64_MOVW_PREL_G2_NC:
+		case R_AARCH64_MOVW_PREL_G3:
+			break;
+		default:
+			fatal_error("Unexpected RELA type %u", type);
+		}
+	}
+}
+
+/* Iterate over all sections and emit hyp relocation data for RELA sections. */
+static void emit_all_relocs(void)
+{
+	Elf64_Shdr *shdr;
+
+	for_each_section(shdr) {
+		switch (elf32toh(shdr->sh_type)) {
+		case SHT_REL:
+			fatal_error("Unexpected SHT_REL section \"%s\"",
+				section_name(shdr));
+		case SHT_RELA:
+			emit_rela_section(shdr);
+			break;
+		}
+	}
+}
+
+int main(int argc, const char **argv)
+{
+	if (argc != 2) {
+		fprintf(stderr, "Usage: %s <elf_input>\n", argv[0]);
+		return EXIT_FAILURE;
+	}
+
+	init_elf(argv[1]);
+
+	emit_prologue();
+	emit_all_relocs();
+	emit_epilogue();
+
+	return EXIT_SUCCESS;
+}
diff --git a/arch/arm64/kvm/hyp/nvhe/host.S b/arch/arm64/kvm/hyp/nvhe/host.S
index a820dfdc9c25..6585a7cbbc56 100644
--- a/arch/arm64/kvm/hyp/nvhe/host.S
+++ b/arch/arm64/kvm/hyp/nvhe/host.S
@@ -74,27 +74,28 @@ SYM_FUNC_END(__host_enter)
  * void __noreturn __hyp_do_panic(bool restore_host, u64 spsr, u64 elr, u64 par);
  */
 SYM_FUNC_START(__hyp_do_panic)
-	/* Load the format arguments into x1-7 */
-	mov	x6, x3
-	get_vcpu_ptr x7, x3
-
-	mrs	x3, esr_el2
-	mrs	x4, far_el2
-	mrs	x5, hpfar_el2
-
 	/* Prepare and exit to the host's panic funciton. */
 	mov	lr, #(PSR_F_BIT | PSR_I_BIT | PSR_A_BIT | PSR_D_BIT |\
 		      PSR_MODE_EL1h)
 	msr	spsr_el2, lr
 	ldr	lr, =panic
+	hyp_kimg_va lr, x6
 	msr	elr_el2, lr
 
-	/*
-	 * Set the panic format string and enter the host, conditionally
-	 * restoring the host context.
-	 */
+	/* Set the panic format string. Use the, now free, LR as scratch. */
+	ldr	lr, =__hyp_panic_string
+	hyp_kimg_va lr, x6
+
+	/* Load the format arguments into x1-7. */
+	mov	x6, x3
+	get_vcpu_ptr x7, x3
+	mrs	x3, esr_el2
+	mrs	x4, far_el2
+	mrs	x5, hpfar_el2
+
+	/* Enter the host, conditionally restoring the host context. */
 	cmp	x0, xzr
-	ldr	x0, =__hyp_panic_string
+	mov	x0, lr
 	b.eq	__host_enter_without_restoring
 	b	__host_enter_for_panic
 SYM_FUNC_END(__hyp_do_panic)
@@ -124,7 +125,7 @@ SYM_FUNC_END(__hyp_do_panic)
 	 * Preserve x0-x4, which may contain stub parameters.
 	 */
 	ldr	x5, =__kvm_handle_stub_hvc
-	kimg_pa x5, x6
+	hyp_pa	x5, x6
 	br	x5
 .L__vect_end\@:
 .if ((.L__vect_end\@ - .L__vect_start\@) > 0x80)
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-init.S b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
index 882fd40d068e..c631e29fb001 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-init.S
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
@@ -18,7 +18,7 @@
 #include <asm/virt.h>
 
 	.text
-	.pushsection	.hyp.idmap.text, "ax"
+	.pushsection	.idmap.text, "ax"
 
 	.align	11
 
@@ -57,17 +57,10 @@ __do_hyp_init:
 	cmp	x0, #HVC_STUB_HCALL_NR
 	b.lo	__kvm_handle_stub_hvc
 
-	// We only actively check bits [24:31], and everything
-	// else has to be zero, which we check at build time.
-#if (KVM_HOST_SMCCC_FUNC(__kvm_hyp_init) & 0xFFFFFFFF00FFFFFF)
-#error Unexpected __KVM_HOST_SMCCC_FUNC___kvm_hyp_init value
-#endif
-
-	ror	x0, x0, #24
-	eor	x0, x0, #((KVM_HOST_SMCCC_FUNC(__kvm_hyp_init) >> 24) & 0xF)
-	ror	x0, x0, #4
-	eor	x0, x0, #((KVM_HOST_SMCCC_FUNC(__kvm_hyp_init) >> 28) & 0xF)
-	cbz	x0, 1f
+	mov	x3, #KVM_HOST_SMCCC_FUNC(__kvm_hyp_init)
+	cmp	x0, x3
+	b.eq	1f
+
 	mov	x0, #SMCCC_RET_NOT_SUPPORTED
 	eret
 
@@ -141,7 +134,6 @@ alternative_else_nop_endif
 
 	/* Set the host vector */
 	ldr	x0, =__kvm_hyp_host_vector
-	kimg_hyp_va x0, x1
 	msr	vbar_el2, x0
 
 	ret
@@ -200,7 +192,6 @@ SYM_CODE_START_LOCAL(__kvm_hyp_init_cpu)
 	/* Leave idmap. */
 	mov	x0, x29
 	ldr	x1, =kvm_host_psci_cpu_entry
-	kimg_hyp_va x1, x2
 	br	x1
 SYM_CODE_END(__kvm_hyp_init_cpu)
 
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index a906f9e2ff34..f012f8665ecc 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -108,9 +108,9 @@ static void handle___vgic_v3_restore_aprs(struct kvm_cpu_context *host_ctxt)
 
 typedef void (*hcall_t)(struct kvm_cpu_context *);
 
-#define HANDLE_FUNC(x)	[__KVM_HOST_SMCCC_FUNC_##x] = kimg_fn_ptr(handle_##x)
+#define HANDLE_FUNC(x)	[__KVM_HOST_SMCCC_FUNC_##x] = (hcall_t)handle_##x
 
-static const hcall_t *host_hcall[] = {
+static const hcall_t host_hcall[] = {
 	HANDLE_FUNC(__kvm_vcpu_run),
 	HANDLE_FUNC(__kvm_flush_vm_context),
 	HANDLE_FUNC(__kvm_tlb_flush_vmid_ipa),
@@ -130,7 +130,6 @@ static const hcall_t *host_hcall[] = {
 static void handle_host_hcall(struct kvm_cpu_context *host_ctxt)
 {
 	DECLARE_REG(unsigned long, id, host_ctxt, 0);
-	const hcall_t *kfn;
 	hcall_t hfn;
 
 	id -= KVM_HOST_SMCCC_ID(0);
@@ -138,13 +137,11 @@ static void handle_host_hcall(struct kvm_cpu_context *host_ctxt)
 	if (unlikely(id >= ARRAY_SIZE(host_hcall)))
 		goto inval;
 
-	kfn = host_hcall[id];
-	if (unlikely(!kfn))
+	hfn = host_hcall[id];
+	if (unlikely(!hfn))
 		goto inval;
 
 	cpu_reg(host_ctxt, 0) = SMCCC_RET_SUCCESS;
-
-	hfn = kimg_fn_hyp_va(kfn);
 	hfn(host_ctxt);
 
 	return;
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-smp.c b/arch/arm64/kvm/hyp/nvhe/hyp-smp.c
index 2997aa156d8e..879559057dee 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-smp.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-smp.c
@@ -33,8 +33,8 @@ unsigned long __hyp_per_cpu_offset(unsigned int cpu)
 	if (cpu >= ARRAY_SIZE(kvm_arm_hyp_percpu_base))
 		hyp_panic();
 
-	cpu_base_array = (unsigned long *)hyp_symbol_addr(kvm_arm_hyp_percpu_base);
+	cpu_base_array = (unsigned long *)&kvm_arm_hyp_percpu_base;
 	this_cpu_base = kern_hyp_va(cpu_base_array[cpu]);
-	elf_base = (unsigned long)hyp_symbol_addr(__per_cpu_start);
+	elf_base = (unsigned long)&__per_cpu_start;
 	return this_cpu_base - elf_base;
 }
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp.lds.S b/arch/arm64/kvm/hyp/nvhe/hyp.lds.S
index 1206d0d754d5..cd119d82d8e3 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp.lds.S
+++ b/arch/arm64/kvm/hyp/nvhe/hyp.lds.S
@@ -12,14 +12,17 @@
 #include <asm/memory.h>
 
 SECTIONS {
+	HYP_SECTION(.idmap.text)
 	HYP_SECTION(.text)
+	HYP_SECTION(.data..ro_after_init)
+	HYP_SECTION(.rodata)
+
 	/*
 	 * .hyp..data..percpu needs to be page aligned to maintain the same
 	 * alignment for when linking into vmlinux.
 	 */
 	. = ALIGN(PAGE_SIZE);
-	HYP_SECTION_NAME(.data..percpu) : {
+	BEGIN_HYP_SECTION(.data..percpu)
 		PERCPU_INPUT(L1_CACHE_BYTES)
-	}
-	HYP_SECTION(.data..ro_after_init)
+	END_HYP_SECTION
 }
diff --git a/arch/arm64/kvm/hyp/nvhe/psci-relay.c b/arch/arm64/kvm/hyp/nvhe/psci-relay.c
index 8e7128cb7667..63de71c0481e 100644
--- a/arch/arm64/kvm/hyp/nvhe/psci-relay.c
+++ b/arch/arm64/kvm/hyp/nvhe/psci-relay.c
@@ -128,8 +128,8 @@ static int psci_cpu_on(u64 func_id, struct kvm_cpu_context *host_ctxt)
 	if (cpu_id == INVALID_CPU_ID)
 		return PSCI_RET_INVALID_PARAMS;
 
-	boot_args = per_cpu_ptr(hyp_symbol_addr(cpu_on_args), cpu_id);
-	init_params = per_cpu_ptr(hyp_symbol_addr(kvm_init_params), cpu_id);
+	boot_args = per_cpu_ptr(&cpu_on_args, cpu_id);
+	init_params = per_cpu_ptr(&kvm_init_params, cpu_id);
 
 	/* Check if the target CPU is already being booted. */
 	if (!try_acquire_boot_args(boot_args))
@@ -140,7 +140,7 @@ static int psci_cpu_on(u64 func_id, struct kvm_cpu_context *host_ctxt)
 	wmb();
 
 	ret = psci_call(func_id, mpidr,
-			__hyp_pa(hyp_symbol_addr(kvm_hyp_cpu_entry)),
+			__hyp_pa(&kvm_hyp_cpu_entry),
 			__hyp_pa(init_params));
 
 	/* If successful, the lock will be released by the target CPU. */
@@ -159,8 +159,8 @@ static int psci_cpu_suspend(u64 func_id, struct kvm_cpu_context *host_ctxt)
 	struct psci_boot_args *boot_args;
 	struct kvm_nvhe_init_params *init_params;
 
-	boot_args = this_cpu_ptr(hyp_symbol_addr(suspend_args));
-	init_params = this_cpu_ptr(hyp_symbol_addr(kvm_init_params));
+	boot_args = this_cpu_ptr(&suspend_args);
+	init_params = this_cpu_ptr(&kvm_init_params);
 
 	/*
 	 * No need to acquire a lock before writing to boot_args because a core
@@ -174,7 +174,7 @@ static int psci_cpu_suspend(u64 func_id, struct kvm_cpu_context *host_ctxt)
 	 * point if it is a deep sleep state.
 	 */
 	return psci_call(func_id, power_state,
-			 __hyp_pa(hyp_symbol_addr(kvm_hyp_cpu_resume)),
+			 __hyp_pa(&kvm_hyp_cpu_resume),
 			 __hyp_pa(init_params));
 }
 
@@ -186,8 +186,8 @@ static int psci_system_suspend(u64 func_id, struct kvm_cpu_context *host_ctxt)
 	struct psci_boot_args *boot_args;
 	struct kvm_nvhe_init_params *init_params;
 
-	boot_args = this_cpu_ptr(hyp_symbol_addr(suspend_args));
-	init_params = this_cpu_ptr(hyp_symbol_addr(kvm_init_params));
+	boot_args = this_cpu_ptr(&suspend_args);
+	init_params = this_cpu_ptr(&kvm_init_params);
 
 	/*
 	 * No need to acquire a lock before writing to boot_args because a core
@@ -198,7 +198,7 @@ static int psci_system_suspend(u64 func_id, struct kvm_cpu_context *host_ctxt)
 
 	/* Will only return on error. */
 	return psci_call(func_id,
-			 __hyp_pa(hyp_symbol_addr(kvm_hyp_cpu_resume)),
+			 __hyp_pa(&kvm_hyp_cpu_resume),
 			 __hyp_pa(init_params), 0);
 }
 
@@ -207,12 +207,12 @@ asmlinkage void __noreturn kvm_host_psci_cpu_entry(bool is_cpu_on)
 	struct psci_boot_args *boot_args;
 	struct kvm_cpu_context *host_ctxt;
 
-	host_ctxt = &this_cpu_ptr(hyp_symbol_addr(kvm_host_data))->host_ctxt;
+	host_ctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt;
 
 	if (is_cpu_on)
-		boot_args = this_cpu_ptr(hyp_symbol_addr(cpu_on_args));
+		boot_args = this_cpu_ptr(&cpu_on_args);
 	else
-		boot_args = this_cpu_ptr(hyp_symbol_addr(suspend_args));
+		boot_args = this_cpu_ptr(&suspend_args);
 
 	cpu_reg(host_ctxt, 0) = boot_args->r0;
 	write_sysreg_el2(boot_args->pc, SYS_ELR);
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index bdf8e55ed308..4d177ce1d536 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -45,6 +45,10 @@
 
 #define KVM_PTE_LEAF_ATTR_HI_S2_XN	BIT(54)
 
+#define KVM_PTE_LEAF_ATTR_S2_PERMS	(KVM_PTE_LEAF_ATTR_LO_S2_S2AP_R | \
+					 KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W | \
+					 KVM_PTE_LEAF_ATTR_HI_S2_XN)
+
 struct kvm_pgtable_walk_data {
 	struct kvm_pgtable		*pgt;
 	struct kvm_pgtable_walker	*walker;
@@ -170,10 +174,9 @@ static void kvm_set_table_pte(kvm_pte_t *ptep, kvm_pte_t *childp)
 	smp_store_release(ptep, pte);
 }
 
-static bool kvm_set_valid_leaf_pte(kvm_pte_t *ptep, u64 pa, kvm_pte_t attr,
-				   u32 level)
+static kvm_pte_t kvm_init_valid_leaf_pte(u64 pa, kvm_pte_t attr, u32 level)
 {
-	kvm_pte_t old = *ptep, pte = kvm_phys_to_pte(pa);
+	kvm_pte_t pte = kvm_phys_to_pte(pa);
 	u64 type = (level == KVM_PGTABLE_MAX_LEVELS - 1) ? KVM_PTE_TYPE_PAGE :
 							   KVM_PTE_TYPE_BLOCK;
 
@@ -181,12 +184,7 @@ static bool kvm_set_valid_leaf_pte(kvm_pte_t *ptep, u64 pa, kvm_pte_t attr,
 	pte |= FIELD_PREP(KVM_PTE_TYPE, type);
 	pte |= KVM_PTE_VALID;
 
-	/* Tolerate KVM recreating the exact same mapping. */
-	if (kvm_pte_valid(old))
-		return old == pte;
-
-	smp_store_release(ptep, pte);
-	return true;
+	return pte;
 }
 
 static int kvm_pgtable_visitor_cb(struct kvm_pgtable_walk_data *data, u64 addr,
@@ -341,12 +339,17 @@ static int hyp_map_set_prot_attr(enum kvm_pgtable_prot prot,
 static bool hyp_map_walker_try_leaf(u64 addr, u64 end, u32 level,
 				    kvm_pte_t *ptep, struct hyp_map_data *data)
 {
+	kvm_pte_t new, old = *ptep;
 	u64 granule = kvm_granule_size(level), phys = data->phys;
 
 	if (!kvm_block_mapping_supported(addr, end, phys, level))
 		return false;
 
-	WARN_ON(!kvm_set_valid_leaf_pte(ptep, phys, data->attr, level));
+	/* Tolerate KVM recreating the exact same mapping */
+	new = kvm_init_valid_leaf_pte(phys, data->attr, level);
+	if (old != new && !WARN_ON(kvm_pte_valid(old)))
+		smp_store_release(ptep, new);
+
 	data->phys += granule;
 	return true;
 }
@@ -461,34 +464,41 @@ static int stage2_map_set_prot_attr(enum kvm_pgtable_prot prot,
 	return 0;
 }
 
-static bool stage2_map_walker_try_leaf(u64 addr, u64 end, u32 level,
-				       kvm_pte_t *ptep,
-				       struct stage2_map_data *data)
+static int stage2_map_walker_try_leaf(u64 addr, u64 end, u32 level,
+				      kvm_pte_t *ptep,
+				      struct stage2_map_data *data)
 {
+	kvm_pte_t new, old = *ptep;
 	u64 granule = kvm_granule_size(level), phys = data->phys;
+	struct page *page = virt_to_page(ptep);
 
 	if (!kvm_block_mapping_supported(addr, end, phys, level))
-		return false;
-
-	/*
-	 * If the PTE was already valid, drop the refcount on the table
-	 * early, as it will be bumped-up again in stage2_map_walk_leaf().
-	 * This ensures that the refcount stays constant across a valid to
-	 * valid PTE update.
-	 */
-	if (kvm_pte_valid(*ptep))
-		put_page(virt_to_page(ptep));
-
-	if (kvm_set_valid_leaf_pte(ptep, phys, data->attr, level))
-		goto out;
+		return -E2BIG;
+
+	new = kvm_init_valid_leaf_pte(phys, data->attr, level);
+	if (kvm_pte_valid(old)) {
+		/*
+		 * Skip updating the PTE if we are trying to recreate the exact
+		 * same mapping or only change the access permissions. Instead,
+		 * the vCPU will exit one more time from guest if still needed
+		 * and then go through the path of relaxing permissions.
+		 */
+		if (!((old ^ new) & (~KVM_PTE_LEAF_ATTR_S2_PERMS)))
+			return -EAGAIN;
+
+		/*
+		 * There's an existing different valid leaf entry, so perform
+		 * break-before-make.
+		 */
+		kvm_set_invalid_pte(ptep);
+		kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, data->mmu, addr, level);
+		put_page(page);
+	}
 
-	/* There's an existing valid leaf entry, so perform break-before-make */
-	kvm_set_invalid_pte(ptep);
-	kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, data->mmu, addr, level);
-	kvm_set_valid_leaf_pte(ptep, phys, data->attr, level);
-out:
+	smp_store_release(ptep, new);
+	get_page(page);
 	data->phys += granule;
-	return true;
+	return 0;
 }
 
 static int stage2_map_walk_table_pre(u64 addr, u64 end, u32 level,
@@ -516,6 +526,7 @@ static int stage2_map_walk_table_pre(u64 addr, u64 end, u32 level,
 static int stage2_map_walk_leaf(u64 addr, u64 end, u32 level, kvm_pte_t *ptep,
 				struct stage2_map_data *data)
 {
+	int ret;
 	kvm_pte_t *childp, pte = *ptep;
 	struct page *page = virt_to_page(ptep);
 
@@ -526,8 +537,9 @@ static int stage2_map_walk_leaf(u64 addr, u64 end, u32 level, kvm_pte_t *ptep,
 		return 0;
 	}
 
-	if (stage2_map_walker_try_leaf(addr, end, level, ptep, data))
-		goto out_get_page;
+	ret = stage2_map_walker_try_leaf(addr, end, level, ptep, data);
+	if (ret != -E2BIG)
+		return ret;
 
 	if (WARN_ON(level == KVM_PGTABLE_MAX_LEVELS - 1))
 		return -EINVAL;
@@ -551,9 +563,8 @@ static int stage2_map_walk_leaf(u64 addr, u64 end, u32 level, kvm_pte_t *ptep,
 	}
 
 	kvm_set_table_pte(ptep, childp);
-
-out_get_page:
 	get_page(page);
+
 	return 0;
 }
 
diff --git a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
index 8f0585640241..87a54375bd6e 100644
--- a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
+++ b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
@@ -64,7 +64,7 @@ int __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu)
 	}
 
 	rd = kvm_vcpu_dabt_get_rd(vcpu);
-	addr  = hyp_symbol_addr(kvm_vgic_global_state)->vcpu_hyp_va;
+	addr  = kvm_vgic_global_state.vcpu_hyp_va;
 	addr += fault_ipa - vgic->vgic_cpu_base;
 
 	if (kvm_vcpu_dabt_iswrite(vcpu)) {
diff --git a/arch/arm64/kvm/hypercalls.c b/arch/arm64/kvm/hypercalls.c
index 25ea4ecb6449..ead21b98b620 100644
--- a/arch/arm64/kvm/hypercalls.c
+++ b/arch/arm64/kvm/hypercalls.c
@@ -71,6 +71,12 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu)
 		if (gpa != GPA_INVALID)
 			val = gpa;
 		break;
+	case ARM_SMCCC_TRNG_VERSION:
+	case ARM_SMCCC_TRNG_FEATURES:
+	case ARM_SMCCC_TRNG_GET_UUID:
+	case ARM_SMCCC_TRNG_RND32:
+	case ARM_SMCCC_TRNG_RND64:
+		return kvm_trng_call(vcpu);
 	default:
 		return kvm_psci_call(vcpu);
 	}
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 7d2257cc5438..77cb2d28f2a4 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -879,11 +879,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	if (vma_pagesize == PAGE_SIZE && !force_pte)
 		vma_pagesize = transparent_hugepage_adjust(memslot, hva,
 							   &pfn, &fault_ipa);
-	if (writable) {
+	if (writable)
 		prot |= KVM_PGTABLE_PROT_W;
-		kvm_set_pfn_dirty(pfn);
-		mark_page_dirty(kvm, gfn);
-	}
 
 	if (fault_status != FSC_PERM && !device)
 		clean_dcache_guest_page(pfn, vma_pagesize);
@@ -911,11 +908,17 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 					     memcache);
 	}
 
+	/* Mark the page dirty only if the fault is handled successfully */
+	if (writable && !ret) {
+		kvm_set_pfn_dirty(pfn);
+		mark_page_dirty(kvm, gfn);
+	}
+
 out_unlock:
 	spin_unlock(&kvm->mmu_lock);
 	kvm_set_pfn_accessed(pfn);
 	kvm_release_pfn_clean(pfn);
-	return ret;
+	return ret != -EAGAIN ? ret : 0;
 }
 
 /* Resolve the access fault by making the page young again. */
diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index 247422ac78a9..e9ec08b0b070 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -23,11 +23,11 @@ static void kvm_pmu_stop_counter(struct kvm_vcpu *vcpu, struct kvm_pmc *pmc);
 static u32 kvm_pmu_event_mask(struct kvm *kvm)
 {
 	switch (kvm->arch.pmuver) {
-	case 1:			/* ARMv8.0 */
+	case ID_AA64DFR0_PMUVER_8_0:
 		return GENMASK(9, 0);
-	case 4:			/* ARMv8.1 */
-	case 5:			/* ARMv8.4 */
-	case 6:			/* ARMv8.5 */
+	case ID_AA64DFR0_PMUVER_8_1:
+	case ID_AA64DFR0_PMUVER_8_4:
+	case ID_AA64DFR0_PMUVER_8_5:
 		return GENMASK(15, 0);
 	default:		/* Shouldn't be here, just for sanity */
 		WARN_ONCE(1, "Unknown PMU version %d\n", kvm->arch.pmuver);
@@ -795,6 +795,12 @@ u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1)
 		base = 0;
 	} else {
 		val = read_sysreg(pmceid1_el0);
+		/*
+		 * Don't advertise STALL_SLOT, as PMMIR_EL0 is handled
+		 * as RAZ
+		 */
+		if (vcpu->kvm->arch.pmuver >= ID_AA64DFR0_PMUVER_8_4)
+			val &= ~BIT_ULL(ARMV8_PMUV3_PERFCTR_STALL_SLOT - 32);
 		base = 32;
 	}
 
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 7c4f79532406..4f2f1e3145de 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -9,6 +9,7 @@
  *          Christoffer Dall <c.dall@virtualopensystems.com>
  */
 
+#include <linux/bitfield.h>
 #include <linux/bsearch.h>
 #include <linux/kvm_host.h>
 #include <linux/mm.h>
@@ -700,14 +701,18 @@ static bool access_pmselr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 static bool access_pmceid(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 			  const struct sys_reg_desc *r)
 {
-	u64 pmceid;
+	u64 pmceid, mask, shift;
 
 	BUG_ON(p->is_write);
 
 	if (pmu_access_el0_disabled(vcpu))
 		return false;
 
+	get_access_mask(r, &mask, &shift);
+
 	pmceid = kvm_pmu_get_pmceid(vcpu, (p->Op2 & 1));
+	pmceid &= mask;
+	pmceid >>= shift;
 
 	p->regval = pmceid;
 
@@ -1021,6 +1026,8 @@ static bool access_arch_timer(struct kvm_vcpu *vcpu,
 	return true;
 }
 
+#define FEATURE(x)	(GENMASK_ULL(x##_SHIFT + 3, x##_SHIFT))
+
 /* Read a sanitised cpufeature ID register by sys_reg_desc */
 static u64 read_id_reg(const struct kvm_vcpu *vcpu,
 		struct sys_reg_desc const *r, bool raz)
@@ -1028,36 +1035,41 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu,
 	u32 id = reg_to_encoding(r);
 	u64 val = raz ? 0 : read_sanitised_ftr_reg(id);
 
-	if (id == SYS_ID_AA64PFR0_EL1) {
+	switch (id) {
+	case SYS_ID_AA64PFR0_EL1:
 		if (!vcpu_has_sve(vcpu))
-			val &= ~(0xfUL << ID_AA64PFR0_SVE_SHIFT);
-		val &= ~(0xfUL << ID_AA64PFR0_AMU_SHIFT);
-		val &= ~(0xfUL << ID_AA64PFR0_CSV2_SHIFT);
-		val |= ((u64)vcpu->kvm->arch.pfr0_csv2 << ID_AA64PFR0_CSV2_SHIFT);
-		val &= ~(0xfUL << ID_AA64PFR0_CSV3_SHIFT);
-		val |= ((u64)vcpu->kvm->arch.pfr0_csv3 << ID_AA64PFR0_CSV3_SHIFT);
-	} else if (id == SYS_ID_AA64PFR1_EL1) {
-		val &= ~(0xfUL << ID_AA64PFR1_MTE_SHIFT);
-	} else if (id == SYS_ID_AA64ISAR1_EL1 && !vcpu_has_ptrauth(vcpu)) {
-		val &= ~((0xfUL << ID_AA64ISAR1_APA_SHIFT) |
-			 (0xfUL << ID_AA64ISAR1_API_SHIFT) |
-			 (0xfUL << ID_AA64ISAR1_GPA_SHIFT) |
-			 (0xfUL << ID_AA64ISAR1_GPI_SHIFT));
-	} else if (id == SYS_ID_AA64DFR0_EL1) {
-		u64 cap = 0;
-
-		/* Limit guests to PMUv3 for ARMv8.1 */
-		if (kvm_vcpu_has_pmu(vcpu))
-			cap = ID_AA64DFR0_PMUVER_8_1;
-
+			val &= ~FEATURE(ID_AA64PFR0_SVE);
+		val &= ~FEATURE(ID_AA64PFR0_AMU);
+		val &= ~FEATURE(ID_AA64PFR0_CSV2);
+		val |= FIELD_PREP(FEATURE(ID_AA64PFR0_CSV2), (u64)vcpu->kvm->arch.pfr0_csv2);
+		val &= ~FEATURE(ID_AA64PFR0_CSV3);
+		val |= FIELD_PREP(FEATURE(ID_AA64PFR0_CSV3), (u64)vcpu->kvm->arch.pfr0_csv3);
+		break;
+	case SYS_ID_AA64PFR1_EL1:
+		val &= ~FEATURE(ID_AA64PFR1_MTE);
+		break;
+	case SYS_ID_AA64ISAR1_EL1:
+		if (!vcpu_has_ptrauth(vcpu))
+			val &= ~(FEATURE(ID_AA64ISAR1_APA) |
+				 FEATURE(ID_AA64ISAR1_API) |
+				 FEATURE(ID_AA64ISAR1_GPA) |
+				 FEATURE(ID_AA64ISAR1_GPI));
+		break;
+	case SYS_ID_AA64DFR0_EL1:
+		/* Limit debug to ARMv8.0 */
+		val &= ~FEATURE(ID_AA64DFR0_DEBUGVER);
+		val |= FIELD_PREP(FEATURE(ID_AA64DFR0_DEBUGVER), 6);
+		/* Limit guests to PMUv3 for ARMv8.4 */
 		val = cpuid_feature_cap_perfmon_field(val,
-						ID_AA64DFR0_PMUVER_SHIFT,
-						cap);
-	} else if (id == SYS_ID_DFR0_EL1) {
-		/* Limit guests to PMUv3 for ARMv8.1 */
+						      ID_AA64DFR0_PMUVER_SHIFT,
+						      kvm_vcpu_has_pmu(vcpu) ? ID_AA64DFR0_PMUVER_8_4 : 0);
+		break;
+	case SYS_ID_DFR0_EL1:
+		/* Limit guests to PMUv3 for ARMv8.4 */
 		val = cpuid_feature_cap_perfmon_field(val,
-						ID_DFR0_PERFMON_SHIFT,
-						ID_DFR0_PERFMON_8_1);
+						      ID_DFR0_PERFMON_SHIFT,
+						      kvm_vcpu_has_pmu(vcpu) ? ID_DFR0_PERFMON_8_4 : 0);
+		break;
 	}
 
 	return val;
@@ -1493,6 +1505,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	  .access = access_pminten, .reg = PMINTENSET_EL1 },
 	{ PMU_SYS_REG(SYS_PMINTENCLR_EL1),
 	  .access = access_pminten, .reg = PMINTENSET_EL1 },
+	{ SYS_DESC(SYS_PMMIR_EL1), trap_raz_wi },
 
 	{ SYS_DESC(SYS_MAIR_EL1), access_vm_reg, reset_unknown, MAIR_EL1 },
 	{ SYS_DESC(SYS_AMAIR_EL1), access_vm_reg, reset_amair_el1, AMAIR_EL1 },
@@ -1720,7 +1733,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_FPEXC32_EL2), NULL, reset_val, FPEXC32_EL2, 0x700 },
 };
 
-static bool trap_dbgidr(struct kvm_vcpu *vcpu,
+static bool trap_dbgdidr(struct kvm_vcpu *vcpu,
 			struct sys_reg_params *p,
 			const struct sys_reg_desc *r)
 {
@@ -1734,7 +1747,7 @@ static bool trap_dbgidr(struct kvm_vcpu *vcpu,
 		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));
+			     | (6 << 16) | (1 << 15) | (el3 << 14) | (el3 << 12));
 		return true;
 	}
 }
@@ -1767,8 +1780,8 @@ static bool trap_dbgidr(struct kvm_vcpu *vcpu,
  * guest. Revisit this one day, would this principle change.
  */
 static const struct sys_reg_desc cp14_regs[] = {
-	/* DBGIDR */
-	{ Op1( 0), CRn( 0), CRm( 0), Op2( 0), trap_dbgidr },
+	/* DBGDIDR */
+	{ Op1( 0), CRn( 0), CRm( 0), Op2( 0), trap_dbgdidr },
 	/* DBGDTRRXext */
 	{ Op1( 0), CRn( 0), CRm( 0), Op2( 2), trap_raz_wi },
 
@@ -1918,8 +1931,8 @@ static const struct sys_reg_desc cp15_regs[] = {
 	{ Op1( 0), CRn( 9), CRm(12), Op2( 3), access_pmovs },
 	{ Op1( 0), CRn( 9), CRm(12), Op2( 4), access_pmswinc },
 	{ Op1( 0), CRn( 9), CRm(12), Op2( 5), access_pmselr },
-	{ Op1( 0), CRn( 9), CRm(12), Op2( 6), access_pmceid },
-	{ Op1( 0), CRn( 9), CRm(12), Op2( 7), access_pmceid },
+	{ AA32(LO), Op1( 0), CRn( 9), CRm(12), Op2( 6), access_pmceid },
+	{ AA32(LO), Op1( 0), CRn( 9), CRm(12), Op2( 7), access_pmceid },
 	{ Op1( 0), CRn( 9), CRm(13), Op2( 0), access_pmu_evcntr },
 	{ Op1( 0), CRn( 9), CRm(13), Op2( 1), access_pmu_evtyper },
 	{ Op1( 0), CRn( 9), CRm(13), Op2( 2), access_pmu_evcntr },
@@ -1927,6 +1940,10 @@ static const struct sys_reg_desc cp15_regs[] = {
 	{ Op1( 0), CRn( 9), CRm(14), Op2( 1), access_pminten },
 	{ Op1( 0), CRn( 9), CRm(14), Op2( 2), access_pminten },
 	{ Op1( 0), CRn( 9), CRm(14), Op2( 3), access_pmovs },
+	{ AA32(HI), Op1( 0), CRn( 9), CRm(14), Op2( 4), access_pmceid },
+	{ AA32(HI), Op1( 0), CRn( 9), CRm(14), Op2( 5), access_pmceid },
+	/* PMMIR */
+	{ Op1( 0), CRn( 9), CRm(14), Op2( 6), trap_raz_wi },
 
 	/* PRRR/MAIR0 */
 	{ AA32(LO), Op1( 0), CRn(10), CRm( 2), Op2( 0), access_vm_reg, NULL, MAIR_EL1 },
diff --git a/arch/arm64/kvm/trng.c b/arch/arm64/kvm/trng.c
new file mode 100644
index 000000000000..99bdd7103c9c
--- /dev/null
+++ b/arch/arm64/kvm/trng.c
@@ -0,0 +1,85 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2020 Arm Ltd.
+
+#include <linux/arm-smccc.h>
+#include <linux/kvm_host.h>
+
+#include <asm/kvm_emulate.h>
+
+#include <kvm/arm_hypercalls.h>
+
+#define ARM_SMCCC_TRNG_VERSION_1_0	0x10000UL
+
+/* Those values are deliberately separate from the generic SMCCC definitions. */
+#define TRNG_SUCCESS			0UL
+#define TRNG_NOT_SUPPORTED		((unsigned long)-1)
+#define TRNG_INVALID_PARAMETER		((unsigned long)-2)
+#define TRNG_NO_ENTROPY			((unsigned long)-3)
+
+#define TRNG_MAX_BITS64			192
+
+static const uuid_t arm_smc_trng_uuid __aligned(4) = UUID_INIT(
+	0x0d21e000, 0x4384, 0x11eb, 0x80, 0x70, 0x52, 0x44, 0x55, 0x4e, 0x5a, 0x4c);
+
+static int kvm_trng_do_rnd(struct kvm_vcpu *vcpu, int size)
+{
+	DECLARE_BITMAP(bits, TRNG_MAX_BITS64);
+	u32 num_bits = smccc_get_arg1(vcpu);
+	int i;
+
+	if (num_bits > 3 * size) {
+		smccc_set_retval(vcpu, TRNG_INVALID_PARAMETER, 0, 0, 0);
+		return 1;
+	}
+
+	/* get as many bits as we need to fulfil the request */
+	for (i = 0; i < DIV_ROUND_UP(num_bits, BITS_PER_LONG); i++)
+		bits[i] = get_random_long();
+
+	bitmap_clear(bits, num_bits, TRNG_MAX_BITS64 - num_bits);
+
+	if (size == 32)
+		smccc_set_retval(vcpu, TRNG_SUCCESS, lower_32_bits(bits[1]),
+				 upper_32_bits(bits[0]), lower_32_bits(bits[0]));
+	else
+		smccc_set_retval(vcpu, TRNG_SUCCESS, bits[2], bits[1], bits[0]);
+
+	memzero_explicit(bits, sizeof(bits));
+	return 1;
+}
+
+int kvm_trng_call(struct kvm_vcpu *vcpu)
+{
+	const __le32 *u = (__le32 *)arm_smc_trng_uuid.b;
+	u32 func_id = smccc_get_function(vcpu);
+	unsigned long val = TRNG_NOT_SUPPORTED;
+	int size = 64;
+
+	switch (func_id) {
+	case ARM_SMCCC_TRNG_VERSION:
+		val = ARM_SMCCC_TRNG_VERSION_1_0;
+		break;
+	case ARM_SMCCC_TRNG_FEATURES:
+		switch (smccc_get_arg1(vcpu)) {
+		case ARM_SMCCC_TRNG_VERSION:
+		case ARM_SMCCC_TRNG_FEATURES:
+		case ARM_SMCCC_TRNG_GET_UUID:
+		case ARM_SMCCC_TRNG_RND32:
+		case ARM_SMCCC_TRNG_RND64:
+			val = TRNG_SUCCESS;
+		}
+		break;
+	case ARM_SMCCC_TRNG_GET_UUID:
+		smccc_set_retval(vcpu, le32_to_cpu(u[0]), le32_to_cpu(u[1]),
+				 le32_to_cpu(u[2]), le32_to_cpu(u[3]));
+		return 1;
+	case ARM_SMCCC_TRNG_RND32:
+		size = 32;
+		fallthrough;
+	case ARM_SMCCC_TRNG_RND64:
+		return kvm_trng_do_rnd(vcpu, size);
+	}
+
+	smccc_set_retval(vcpu, val, 0, 0, 0);
+	return 1;
+}
diff --git a/arch/arm64/kvm/va_layout.c b/arch/arm64/kvm/va_layout.c
index 70fcd6a12fe1..978301392d67 100644
--- a/arch/arm64/kvm/va_layout.c
+++ b/arch/arm64/kvm/va_layout.c
@@ -81,6 +81,34 @@ __init void kvm_compute_layout(void)
 	init_hyp_physvirt_offset();
 }
 
+/*
+ * The .hyp.reloc ELF section contains a list of kimg positions that
+ * contains kimg VAs but will be accessed only in hyp execution context.
+ * Convert them to hyp VAs. See gen-hyprel.c for more details.
+ */
+__init void kvm_apply_hyp_relocations(void)
+{
+	int32_t *rel;
+	int32_t *begin = (int32_t *)__hyp_reloc_begin;
+	int32_t *end = (int32_t *)__hyp_reloc_end;
+
+	for (rel = begin; rel < end; ++rel) {
+		uintptr_t *ptr, kimg_va;
+
+		/*
+		 * Each entry contains a 32-bit relative offset from itself
+		 * to a kimg VA position.
+		 */
+		ptr = (uintptr_t *)lm_alias((char *)rel + *rel);
+
+		/* Read the kimg VA value at the relocation address. */
+		kimg_va = *ptr;
+
+		/* Convert to hyp VA and store back to the relocation address. */
+		*ptr = __early_kern_hyp_va((uintptr_t)lm_alias(kimg_va));
+	}
+}
+
 static u32 compute_instruction(int n, u32 rd, u32 rn)
 {
 	u32 insn = AARCH64_BREAK_FAULT;
@@ -255,12 +283,6 @@ static void generate_mov_q(u64 val, __le32 *origptr, __le32 *updptr, int nr_inst
 	*updptr++ = cpu_to_le32(insn);
 }
 
-void kvm_update_kimg_phys_offset(struct alt_instr *alt,
-				 __le32 *origptr, __le32 *updptr, int nr_inst)
-{
-	generate_mov_q(kimage_voffset + PHYS_OFFSET, origptr, updptr, nr_inst);
-}
-
 void kvm_get_kimage_voffset(struct alt_instr *alt,
 			    __le32 *origptr, __le32 *updptr, int nr_inst)
 {