From 4a95a1b20da31db0c1ca5289a892fef21f691f27 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Thu, 11 Jun 2020 11:54:01 +0100
Subject: KVM: arm64: Enable Address Authentication at EL2 if available

While initializing EL2, enable Address Authentication if detected
from EL1. We still use the EL1-provided keys though.

Acked-by: Andrew Scull <ascull@google.com>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/hyp-init.S | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S
index 6e6ed5581eed..1587d146726a 100644
--- a/arch/arm64/kvm/hyp-init.S
+++ b/arch/arm64/kvm/hyp-init.S
@@ -104,6 +104,11 @@ alternative_else_nop_endif
 	 */
 	mov_q	x4, (SCTLR_EL2_RES1 | (SCTLR_ELx_FLAGS & ~SCTLR_ELx_A))
 CPU_BE(	orr	x4, x4, #SCTLR_ELx_EE)
+alternative_if ARM64_HAS_ADDRESS_AUTH
+	mov_q	x5, (SCTLR_ELx_ENIA | SCTLR_ELx_ENIB | \
+		     SCTLR_ELx_ENDA | SCTLR_ELx_ENDB)
+	orr	x4, x4, x5
+alternative_else_nop_endif
 	msr	sctlr_el2, x4
 	isb
 
-- 
cgit 


From dfb0589c8fff9dde809b9013335a6b8019b299b8 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Thu, 11 Jun 2020 12:18:58 +0100
Subject: KVM: arm64: Allow ARM64_PTR_AUTH when ARM64_VHE=n

We currently prevent PtrAuth from even being built if KVM is selected,
but VHE isn't. It is a bit of a pointless restriction, since we also
check this at run time (rejecting the enabling of PtrAuth for the
vcpu if we're not running with VHE).

Just drop this apparently useless restriction.

Acked-by: Andrew Scull <ascull@google.com>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/Kconfig | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 31380da53689..d719ea9c596d 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1516,7 +1516,6 @@ menu "ARMv8.3 architectural features"
 config ARM64_PTR_AUTH
 	bool "Enable support for pointer authentication"
 	default y
-	depends on !KVM || ARM64_VHE
 	depends on (CC_HAS_SIGN_RETURN_ADDRESS || CC_HAS_BRANCH_PROT_PAC_RET) && AS_HAS_PAC
 	# GCC 9.1 and later inserts a .note.gnu.property section note for PAC
 	# which is only understood by binutils starting with version 2.33.1.
@@ -1543,8 +1542,7 @@ config ARM64_PTR_AUTH
 
 	  The feature is detected at runtime. If the feature is not present in
 	  hardware it will not be advertised to userspace/KVM guest nor will it
-	  be enabled. However, KVM guest also require VHE mode and hence
-	  CONFIG_ARM64_VHE=y option to use this feature.
+	  be enabled.
 
 	  If the feature is present on the boot CPU but not on a late CPU, then
 	  the late CPU will be parked. Also, if the boot CPU does not have
-- 
cgit 


From aff7cce0d337f5468470d614ef83a507dcf4c93f Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Thu, 11 Jun 2020 13:20:28 +0100
Subject: KVM: arm64: Allow PtrAuth to be enabled from userspace on non-VHE
 systems

Now that the scene is set for enabling PtrAuth on non-VHE, drop
the restrictions preventing userspace from enabling it.

Acked-by: Andrew Scull <ascull@google.com>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/reset.c | 21 ++++++++++-----------
 1 file changed, 10 insertions(+), 11 deletions(-)

diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index d3b209023727..2a929789fe2e 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -42,6 +42,11 @@ static u32 kvm_ipa_limit;
 #define VCPU_RESET_PSTATE_SVC	(PSR_AA32_MODE_SVC | PSR_AA32_A_BIT | \
 				 PSR_AA32_I_BIT | PSR_AA32_F_BIT)
 
+static bool system_has_full_ptr_auth(void)
+{
+	return system_supports_address_auth() && system_supports_generic_auth();
+}
+
 /**
  * kvm_arch_vm_ioctl_check_extension
  *
@@ -80,8 +85,7 @@ int kvm_arch_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		break;
 	case KVM_CAP_ARM_PTRAUTH_ADDRESS:
 	case KVM_CAP_ARM_PTRAUTH_GENERIC:
-		r = has_vhe() && system_supports_address_auth() &&
-				 system_supports_generic_auth();
+		r = system_has_full_ptr_auth();
 		break;
 	default:
 		r = 0;
@@ -205,19 +209,14 @@ static void kvm_vcpu_reset_sve(struct kvm_vcpu *vcpu)
 
 static int kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu)
 {
-	/* Support ptrauth only if the system supports these capabilities. */
-	if (!has_vhe())
-		return -EINVAL;
-
-	if (!system_supports_address_auth() ||
-	    !system_supports_generic_auth())
-		return -EINVAL;
 	/*
 	 * For now make sure that both address/generic pointer authentication
-	 * features are requested by the userspace together.
+	 * features are requested by the userspace together and the system
+	 * supports these capabilities.
 	 */
 	if (!test_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, vcpu->arch.features) ||
-	    !test_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, vcpu->arch.features))
+	    !test_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, vcpu->arch.features) ||
+	    !system_has_full_ptr_auth())
 		return -EINVAL;
 
 	vcpu->arch.flags |= KVM_ARM64_GUEST_HAS_PTRAUTH;
-- 
cgit 


From 655169cec7bbf84f59faa9f824edb581eaecf78d Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Thu, 11 Jun 2020 11:26:09 +0100
Subject: KVM: arm64: Check HCR_EL2 instead of shadow copy to swap PtrAuth
 registers

When save/restoring PtrAuth registers between host and guest, it is
pretty useless to fetch the in-memory state, while we have the right
state in the HCR_EL2 system register. Use that instead.

Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_ptrauth.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_ptrauth.h b/arch/arm64/include/asm/kvm_ptrauth.h
index 6301813dcace..f1830173fa9e 100644
--- a/arch/arm64/include/asm/kvm_ptrauth.h
+++ b/arch/arm64/include/asm/kvm_ptrauth.h
@@ -74,7 +74,7 @@ alternative_if_not ARM64_HAS_ADDRESS_AUTH_IMP_DEF
 	b	1001f
 alternative_else_nop_endif
 1000:
-	ldr	\reg1, [\g_ctxt, #(VCPU_HCR_EL2 - VCPU_CONTEXT)]
+	mrs	\reg1, hcr_el2
 	and	\reg1, \reg1, #(HCR_API | HCR_APK)
 	cbz	\reg1, 1001f
 	add	\reg1, \g_ctxt, #CPU_APIAKEYLO_EL1
@@ -90,7 +90,7 @@ alternative_if_not ARM64_HAS_ADDRESS_AUTH_IMP_DEF
 	b	2001f
 alternative_else_nop_endif
 2000:
-	ldr	\reg1, [\g_ctxt, #(VCPU_HCR_EL2 - VCPU_CONTEXT)]
+	mrs	\reg1, hcr_el2
 	and	\reg1, \reg1, #(HCR_API | HCR_APK)
 	cbz	\reg1, 2001f
 	add	\reg1, \g_ctxt, #CPU_APIAKEYLO_EL1
-- 
cgit 


From 11ac16a4290b72efa8328cb144b727f3cbbdfa6a Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Mon, 15 Jun 2020 21:03:30 +0100
Subject: KVM: arm64: Simplify PtrAuth alternative patching

We currently decide to execute the PtrAuth save/restore code based
on a set of branches that evaluate as (ARM64_HAS_ADDRESS_AUTH_ARCH ||
ARM64_HAS_ADDRESS_AUTH_IMP_DEF). This can be easily replaced by
a much simpler test as the ARM64_HAS_ADDRESS_AUTH capability is
exactly this expression.

Suggested-by: Mark Rutland <mark.rutland@arm.com>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_ptrauth.h | 30 +++++++++++-------------------
 1 file changed, 11 insertions(+), 19 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_ptrauth.h b/arch/arm64/include/asm/kvm_ptrauth.h
index f1830173fa9e..0ddf98c3ba9f 100644
--- a/arch/arm64/include/asm/kvm_ptrauth.h
+++ b/arch/arm64/include/asm/kvm_ptrauth.h
@@ -61,44 +61,36 @@
 
 /*
  * Both ptrauth_switch_to_guest and ptrauth_switch_to_host macros will
- * check for the presence of one of the cpufeature flag
- * ARM64_HAS_ADDRESS_AUTH_ARCH or ARM64_HAS_ADDRESS_AUTH_IMP_DEF and
+ * check for the presence ARM64_HAS_ADDRESS_AUTH, which is defined as
+ * (ARM64_HAS_ADDRESS_AUTH_ARCH || ARM64_HAS_ADDRESS_AUTH_IMP_DEF) and
  * then proceed ahead with the save/restore of Pointer Authentication
- * key registers.
+ * key registers if enabled for the guest.
  */
 .macro ptrauth_switch_to_guest g_ctxt, reg1, reg2, reg3
-alternative_if ARM64_HAS_ADDRESS_AUTH_ARCH
-	b	1000f
+alternative_if_not ARM64_HAS_ADDRESS_AUTH
+	b	.L__skip_switch\@
 alternative_else_nop_endif
-alternative_if_not ARM64_HAS_ADDRESS_AUTH_IMP_DEF
-	b	1001f
-alternative_else_nop_endif
-1000:
 	mrs	\reg1, hcr_el2
 	and	\reg1, \reg1, #(HCR_API | HCR_APK)
-	cbz	\reg1, 1001f
+	cbz	\reg1, .L__skip_switch\@
 	add	\reg1, \g_ctxt, #CPU_APIAKEYLO_EL1
 	ptrauth_restore_state	\reg1, \reg2, \reg3
-1001:
+.L__skip_switch\@:
 .endm
 
 .macro ptrauth_switch_to_host g_ctxt, h_ctxt, reg1, reg2, reg3
-alternative_if ARM64_HAS_ADDRESS_AUTH_ARCH
-	b	2000f
-alternative_else_nop_endif
-alternative_if_not ARM64_HAS_ADDRESS_AUTH_IMP_DEF
-	b	2001f
+alternative_if_not ARM64_HAS_ADDRESS_AUTH
+	b	.L__skip_switch\@
 alternative_else_nop_endif
-2000:
 	mrs	\reg1, hcr_el2
 	and	\reg1, \reg1, #(HCR_API | HCR_APK)
-	cbz	\reg1, 2001f
+	cbz	\reg1, .L__skip_switch\@
 	add	\reg1, \g_ctxt, #CPU_APIAKEYLO_EL1
 	ptrauth_save_state	\reg1, \reg2, \reg3
 	add	\reg1, \h_ctxt, #CPU_APIAKEYLO_EL1
 	ptrauth_restore_state	\reg1, \reg2, \reg3
 	isb
-2001:
+.L__skip_switch\@:
 .endm
 
 #else /* !CONFIG_ARM64_PTR_AUTH */
-- 
cgit 


From a47dee5513cd7b6d1e20dfecd458363f24a19cdc Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Mon, 25 May 2020 09:45:21 +0100
Subject: KVM: arm64: Allow in-atomic injection of SPIs

On a system that uses SPIs to implement MSIs (as it would be
the case on a GICv2 system exposing a GICv2m to its guests),
we deny the possibility of injecting SPIs on the in-atomic
fast-path.

This results in a very large amount of context-switches
(roughly equivalent to twice the interrupt rate) on the host,
and suboptimal performance for the guest (as measured with
a test workload involving a virtio interface backed by vhost-net).
Given that GICv2 systems are usually on the low-end of the spectrum
performance wise, they could do without the aggravation.

We solved this for GICv3+ITS by having a translation cache. But
SPIs do not need any extra infrastructure, and can be immediately
injected in the virtual distributor as the locking is already
heavy enough that we don't need to worry about anything.

This halves the number of context switches for the same workload.

Reviewed-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/vgic/vgic-irqfd.c | 24 +++++++++++++++++++-----
 arch/arm64/kvm/vgic/vgic-its.c   |  3 +--
 2 files changed, 20 insertions(+), 7 deletions(-)

diff --git a/arch/arm64/kvm/vgic/vgic-irqfd.c b/arch/arm64/kvm/vgic/vgic-irqfd.c
index d8cdfea5cc96..79f8899b234c 100644
--- a/arch/arm64/kvm/vgic/vgic-irqfd.c
+++ b/arch/arm64/kvm/vgic/vgic-irqfd.c
@@ -100,19 +100,33 @@ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
 
 /**
  * kvm_arch_set_irq_inatomic: fast-path for irqfd injection
- *
- * Currently only direct MSI injection is supported.
  */
 int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e,
 			      struct kvm *kvm, int irq_source_id, int level,
 			      bool line_status)
 {
-	if (e->type == KVM_IRQ_ROUTING_MSI && vgic_has_its(kvm) && level) {
+	if (!level)
+		return -EWOULDBLOCK;
+
+	switch (e->type) {
+	case KVM_IRQ_ROUTING_MSI: {
 		struct kvm_msi msi;
 
+		if (!vgic_has_its(kvm))
+			break;
+
 		kvm_populate_msi(e, &msi);
-		if (!vgic_its_inject_cached_translation(kvm, &msi))
-			return 0;
+		return vgic_its_inject_cached_translation(kvm, &msi);
+	}
+
+	case KVM_IRQ_ROUTING_IRQCHIP:
+		/*
+		 * Injecting SPIs is always possible in atomic context
+		 * as long as the damn vgic is initialized.
+		 */
+		if (unlikely(!vgic_initialized(kvm)))
+			break;
+		return vgic_irqfd_set_irq(e, kvm, irq_source_id, 1, line_status);
 	}
 
 	return -EWOULDBLOCK;
diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c
index c012a52b19f5..40cbaca81333 100644
--- a/arch/arm64/kvm/vgic/vgic-its.c
+++ b/arch/arm64/kvm/vgic/vgic-its.c
@@ -757,9 +757,8 @@ int vgic_its_inject_cached_translation(struct kvm *kvm, struct kvm_msi *msi)
 
 	db = (u64)msi->address_hi << 32 | msi->address_lo;
 	irq = vgic_its_check_cache(kvm, db, msi->devid, msi->data);
-
 	if (!irq)
-		return -1;
+		return -EWOULDBLOCK;
 
 	raw_spin_lock_irqsave(&irq->irq_lock, flags);
 	irq->pending_latch = true;
-- 
cgit 


From 2da3ffa6e840b9f8fc65a71326c43b716992861d Mon Sep 17 00:00:00 2001
From: Andrew Scull <ascull@google.com>
Date: Thu, 18 Jun 2020 10:36:16 +0100
Subject: arm64: kvm: Remove kern_hyp_va from get_vcpu_ptr

get_vcpu_ptr is an assembly accessor for the percpu value
kvm_host_data->host_ctxt.__hyp_running_vcpu. kern_hyp_va only applies to
nVHE however __hyp_running_vcpu is always assigned a pointer that has
already had kern_hyp_va applied in __kvm_vcpu_run_nvhe.

kern_hyp_va is currently idempotent as it just masks and inserts the
tag, but this could change in future and the second application is
unnecessary.

Signed-off-by: Andrew Scull <ascull@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: James Morse <james.morse@arm.com>
Link: https://lore.kernel.org/r/20200618093616.164413-1-ascull@google.com
---
 arch/arm64/include/asm/kvm_asm.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 352aaebf4198..ac71d0939f2e 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -143,7 +143,6 @@ extern char __smccc_workaround_1_smc[__SMCCC_WORKAROUND_1_SMC_SZ];
 .macro get_vcpu_ptr vcpu, ctxt
 	get_host_ctxt \ctxt, \vcpu
 	ldr	\vcpu, [\ctxt, #HOST_CONTEXT_VCPU]
-	kern_hyp_va	\vcpu
 .endm
 
 #endif
-- 
cgit 


From 6b33e0d64f8501b51d32069e08d3ed68c58c25b4 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Mon, 22 Jun 2020 11:33:13 +0000
Subject: KVM: arm64: Drop the target_table[] indirection

KVM for 32bit arm had a get/set target mechanism to allow for
micro-architecture differences that are visible in system registers
to be described.

KVM's user-space can query the supported targets for a CPU, and
create vCPUs for that target. The target can override the handling
of system registers to provide different reset or RES0 behaviour.
On 32bit arm this was used to provide different ACTLR reset values
for A7 and A15.

On 64bit arm, the first few CPUs out of the gate used this mechanism,
before it was deemed redundant in commit bca556ac468a ("arm64/kvm:
Add generic v8 KVM target"). All future CPUs use the
KVM_ARM_TARGET_GENERIC_V8 target.

The 64bit target_table[] stuff exists to preserve the ABI to
user-space. As all targets registers genericv8_target_table, there
is no reason to look the target up.

Until we can merge genericv8_target_table with the main sys_regs
array, kvm_register_target_sys_reg_table() becomes
kvm_check_target_sys_reg_table(), which uses BUG_ON() in keeping
with the other callers in this file.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200622113317.20477-2-james.morse@arm.com
---
 arch/arm64/include/asm/kvm_coproc.h  |  3 +--
 arch/arm64/kvm/sys_regs.c            | 16 ++++------------
 arch/arm64/kvm/sys_regs.h            |  2 ++
 arch/arm64/kvm/sys_regs_generic_v8.c | 15 ++-------------
 4 files changed, 9 insertions(+), 27 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_coproc.h b/arch/arm64/include/asm/kvm_coproc.h
index 0185ee8b8b5e..4bf0d6d05e0f 100644
--- a/arch/arm64/include/asm/kvm_coproc.h
+++ b/arch/arm64/include/asm/kvm_coproc.h
@@ -24,8 +24,7 @@ struct kvm_sys_reg_target_table {
 	struct kvm_sys_reg_table table32;
 };
 
-void kvm_register_target_sys_reg_table(unsigned int target,
-				       struct kvm_sys_reg_target_table *table);
+void kvm_check_target_sys_reg_table(struct kvm_sys_reg_target_table *table);
 
 int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu, struct kvm_run *run);
 int kvm_handle_cp14_32(struct kvm_vcpu *vcpu, struct kvm_run *run);
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index baf5ce9225ce..6333a7cd92d3 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -2109,17 +2109,10 @@ static int check_sysreg_table(const struct sys_reg_desc *table, unsigned int n,
 	return 0;
 }
 
-/* Target specific emulation tables */
-static struct kvm_sys_reg_target_table *target_tables[KVM_ARM_NUM_TARGETS];
-
-void kvm_register_target_sys_reg_table(unsigned int target,
-				       struct kvm_sys_reg_target_table *table)
+void kvm_check_target_sys_reg_table(struct kvm_sys_reg_target_table *table)
 {
-	if (check_sysreg_table(table->table64.table, table->table64.num, false) ||
-	    check_sysreg_table(table->table32.table, table->table32.num, true))
-		return;
-
-	target_tables[target] = table;
+	BUG_ON(check_sysreg_table(table->table64.table, table->table64.num, false));
+	BUG_ON(check_sysreg_table(table->table32.table, table->table32.num, true));
 }
 
 /* Get specific register table for this target. */
@@ -2127,9 +2120,8 @@ static const struct sys_reg_desc *get_target_table(unsigned target,
 						   bool mode_is_64,
 						   size_t *num)
 {
-	struct kvm_sys_reg_target_table *table;
+	struct kvm_sys_reg_target_table *table = &genericv8_target_table;
 
-	table = target_tables[target];
 	if (mode_is_64) {
 		*num = table->table64.num;
 		return table->table64.table;
diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h
index 5a6fc30f5989..933609e883bf 100644
--- a/arch/arm64/kvm/sys_regs.h
+++ b/arch/arm64/kvm/sys_regs.h
@@ -165,4 +165,6 @@ const struct sys_reg_desc *find_reg_by_id(u64 id,
 	CRn(sys_reg_CRn(reg)), CRm(sys_reg_CRm(reg)),	\
 	Op2(sys_reg_Op2(reg))
 
+extern struct kvm_sys_reg_target_table genericv8_target_table;
+
 #endif /* __ARM64_KVM_SYS_REGS_LOCAL_H__ */
diff --git a/arch/arm64/kvm/sys_regs_generic_v8.c b/arch/arm64/kvm/sys_regs_generic_v8.c
index aa9d356451eb..a82cc2ccfd44 100644
--- a/arch/arm64/kvm/sys_regs_generic_v8.c
+++ b/arch/arm64/kvm/sys_regs_generic_v8.c
@@ -59,7 +59,7 @@ static const struct sys_reg_desc genericv8_cp15_regs[] = {
 	  access_actlr },
 };
 
-static struct kvm_sys_reg_target_table genericv8_target_table = {
+struct kvm_sys_reg_target_table genericv8_target_table = {
 	.table64 = {
 		.table = genericv8_sys_regs,
 		.num = ARRAY_SIZE(genericv8_sys_regs),
@@ -78,18 +78,7 @@ static int __init sys_reg_genericv8_init(void)
 		BUG_ON(cmp_sys_reg(&genericv8_sys_regs[i-1],
 			       &genericv8_sys_regs[i]) >= 0);
 
-	kvm_register_target_sys_reg_table(KVM_ARM_TARGET_AEM_V8,
-					  &genericv8_target_table);
-	kvm_register_target_sys_reg_table(KVM_ARM_TARGET_FOUNDATION_V8,
-					  &genericv8_target_table);
-	kvm_register_target_sys_reg_table(KVM_ARM_TARGET_CORTEX_A53,
-					  &genericv8_target_table);
-	kvm_register_target_sys_reg_table(KVM_ARM_TARGET_CORTEX_A57,
-					  &genericv8_target_table);
-	kvm_register_target_sys_reg_table(KVM_ARM_TARGET_XGENE_POTENZA,
-					  &genericv8_target_table);
-	kvm_register_target_sys_reg_table(KVM_ARM_TARGET_GENERIC_V8,
-					  &genericv8_target_table);
+	kvm_check_target_sys_reg_table(&genericv8_target_table);
 
 	return 0;
 }
-- 
cgit 


From 04343ae312ef0d80d601ea1b784b6b039ae9c82a Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Mon, 22 Jun 2020 11:33:14 +0000
Subject: KVM: arm64: Tolerate an empty target_table list

Before emptying the target_table lists, and then removing their
infrastructure, add some tolerance to an empty list.

Instead of bugging-out on an empty list, pretend we already
reached the end in the two-list-walk.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200622113317.20477-3-james.morse@arm.com
---
 arch/arm64/kvm/sys_regs.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 6333a7cd92d3..fb448bfc83ec 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -2809,7 +2809,10 @@ static int walk_sys_regs(struct kvm_vcpu *vcpu, u64 __user *uind)
 	i2 = sys_reg_descs;
 	end2 = sys_reg_descs + ARRAY_SIZE(sys_reg_descs);
 
-	BUG_ON(i1 == end1 || i2 == end2);
+	if (i1 == end1)
+		i1 = NULL;
+
+	BUG_ON(i2 == end2);
 
 	/* Walk carefully, as both tables may refer to the same register. */
 	while (i1 || i2) {
-- 
cgit 


From af4738290d9dfe3787f60e40f709a4f78a115943 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Mon, 22 Jun 2020 11:33:15 +0000
Subject: KVM: arm64: Move ACTLR_EL1 emulation to the sys_reg_descs array

The only entry in the genericv8_sys_regs arrays is for emulation of
ACTLR_EL1. As all targets emulate this in the same way, move it to
sys_reg_descs[].

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200622113317.20477-4-james.morse@arm.com
---
 arch/arm64/kvm/sys_regs.c            | 28 ++++++++++++++++++++++++++++
 arch/arm64/kvm/sys_regs_generic_v8.c | 30 ------------------------------
 2 files changed, 28 insertions(+), 30 deletions(-)

diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index fb448bfc83ec..f8407cfa9032 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -242,6 +242,25 @@ static bool access_vm_reg(struct kvm_vcpu *vcpu,
 	return true;
 }
 
+static bool access_actlr(struct kvm_vcpu *vcpu,
+			 struct sys_reg_params *p,
+			 const struct sys_reg_desc *r)
+{
+	if (p->is_write)
+		return ignore_write(vcpu, p);
+
+	p->regval = vcpu_read_sys_reg(vcpu, ACTLR_EL1);
+
+	if (p->is_aarch32) {
+		if (r->Op2 & 2)
+			p->regval = upper_32_bits(p->regval);
+		else
+			p->regval = lower_32_bits(p->regval);
+	}
+
+	return true;
+}
+
 /*
  * Trap handler for the GICv3 SGI generation system register.
  * Forward the request to the VGIC emulation.
@@ -615,6 +634,12 @@ static void reset_amair_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 	vcpu_write_sys_reg(vcpu, amair, AMAIR_EL1);
 }
 
+static void reset_actlr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
+{
+	u64 actlr = read_sysreg(actlr_el1);
+	vcpu_write_sys_reg(vcpu, actlr, ACTLR_EL1);
+}
+
 static void reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 {
 	u64 mpidr;
@@ -1518,6 +1543,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	ID_UNALLOCATED(7,7),
 
 	{ SYS_DESC(SYS_SCTLR_EL1), access_vm_reg, reset_val, SCTLR_EL1, 0x00C50078 },
+	{ SYS_DESC(SYS_ACTLR_EL1), access_actlr, reset_actlr, ACTLR_EL1 },
 	{ SYS_DESC(SYS_CPACR_EL1), NULL, reset_val, CPACR_EL1, 0 },
 	{ SYS_DESC(SYS_ZCR_EL1), NULL, reset_val, ZCR_EL1, 0, .visibility = sve_visibility },
 	{ SYS_DESC(SYS_TTBR0_EL1), access_vm_reg, reset_unknown, TTBR0_EL1 },
@@ -1957,6 +1983,8 @@ static const struct sys_reg_desc cp14_64_regs[] = {
 static const struct sys_reg_desc cp15_regs[] = {
 	{ Op1( 0), CRn( 0), CRm( 0), Op2( 1), access_ctr },
 	{ Op1( 0), CRn( 1), CRm( 0), Op2( 0), access_vm_reg, NULL, c1_SCTLR },
+	{ Op1( 0), CRn( 1), CRm( 0), Op2( 1), access_actlr },
+	{ Op1( 0), CRn( 1), CRm( 0), Op2( 3), access_actlr },
 	{ Op1( 0), CRn( 2), CRm( 0), Op2( 0), access_vm_reg, NULL, c2_TTBR0 },
 	{ Op1( 0), CRn( 2), CRm( 0), Op2( 1), access_vm_reg, NULL, c2_TTBR1 },
 	{ Op1( 0), CRn( 2), CRm( 0), Op2( 2), access_vm_reg, NULL, c2_TTBCR },
diff --git a/arch/arm64/kvm/sys_regs_generic_v8.c b/arch/arm64/kvm/sys_regs_generic_v8.c
index a82cc2ccfd44..a7e21e61beea 100644
--- a/arch/arm64/kvm/sys_regs_generic_v8.c
+++ b/arch/arm64/kvm/sys_regs_generic_v8.c
@@ -19,44 +19,14 @@
 
 #include "sys_regs.h"
 
-static bool access_actlr(struct kvm_vcpu *vcpu,
-			 struct sys_reg_params *p,
-			 const struct sys_reg_desc *r)
-{
-	if (p->is_write)
-		return ignore_write(vcpu, p);
-
-	p->regval = vcpu_read_sys_reg(vcpu, ACTLR_EL1);
-
-	if (p->is_aarch32) {
-		if (r->Op2 & 2)
-			p->regval = upper_32_bits(p->regval);
-		else
-			p->regval = lower_32_bits(p->regval);
-	}
-
-	return true;
-}
-
-static void reset_actlr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
-{
-	__vcpu_sys_reg(vcpu, ACTLR_EL1) = read_sysreg(actlr_el1);
-}
-
 /*
  * Implementation specific sys-reg registers.
  * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2
  */
 static const struct sys_reg_desc genericv8_sys_regs[] = {
-	{ SYS_DESC(SYS_ACTLR_EL1), access_actlr, reset_actlr, ACTLR_EL1 },
 };
 
 static const struct sys_reg_desc genericv8_cp15_regs[] = {
-	/* ACTLR */
-	{ Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b001),
-	  access_actlr },
-	{ Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b011),
-	  access_actlr },
 };
 
 struct kvm_sys_reg_target_table genericv8_target_table = {
-- 
cgit 


From dcaffa7bf911578a6d69165d712501996c587fbe Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Mon, 22 Jun 2020 11:33:16 +0000
Subject: KVM: arm64: Remove target_table from exit handlers

Whenever KVM searches for a register (e.g. due to a guest exit), it
works with two tables, as the target table overrides the sys_regs array.

Now that everything is in the sys_regs array, and the target table is
empty, stop doing that.

Remove the second table and its size from all the functions that take
it.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200622113317.20477-5-james.morse@arm.com
---
 arch/arm64/kvm/sys_regs.c | 87 +++++++++--------------------------------------
 1 file changed, 16 insertions(+), 71 deletions(-)

diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index f8407cfa9032..14333005b476 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -2269,9 +2269,7 @@ static void unhandled_cp_access(struct kvm_vcpu *vcpu,
  */
 static int kvm_handle_cp_64(struct kvm_vcpu *vcpu,
 			    const struct sys_reg_desc *global,
-			    size_t nr_global,
-			    const struct sys_reg_desc *target_specific,
-			    size_t nr_specific)
+			    size_t nr_global)
 {
 	struct sys_reg_params params;
 	u32 hsr = kvm_vcpu_get_hsr(vcpu);
@@ -2298,14 +2296,11 @@ static int kvm_handle_cp_64(struct kvm_vcpu *vcpu,
 	}
 
 	/*
-	 * Try to emulate the coprocessor access using the target
-	 * specific table first, and using the global table afterwards.
-	 * If either of the tables contains a handler, handle the
+	 * If the table contains a handler, handle the
 	 * potential register operation in the case of a read and return
 	 * with success.
 	 */
-	if (!emulate_cp(vcpu, &params, target_specific, nr_specific) ||
-	    !emulate_cp(vcpu, &params, global, nr_global)) {
+	if (!emulate_cp(vcpu, &params, global, nr_global)) {
 		/* Split up the value between registers for the read side */
 		if (!params.is_write) {
 			vcpu_set_reg(vcpu, Rt, lower_32_bits(params.regval));
@@ -2326,9 +2321,7 @@ static int kvm_handle_cp_64(struct kvm_vcpu *vcpu,
  */
 static int kvm_handle_cp_32(struct kvm_vcpu *vcpu,
 			    const struct sys_reg_desc *global,
-			    size_t nr_global,
-			    const struct sys_reg_desc *target_specific,
-			    size_t nr_specific)
+			    size_t nr_global)
 {
 	struct sys_reg_params params;
 	u32 hsr = kvm_vcpu_get_hsr(vcpu);
@@ -2344,8 +2337,7 @@ static int kvm_handle_cp_32(struct kvm_vcpu *vcpu,
 	params.Op1 = (hsr >> 14) & 0x7;
 	params.Op2 = (hsr >> 17) & 0x7;
 
-	if (!emulate_cp(vcpu, &params, target_specific, nr_specific) ||
-	    !emulate_cp(vcpu, &params, global, nr_global)) {
+	if (!emulate_cp(vcpu, &params, global, nr_global)) {
 		if (!params.is_write)
 			vcpu_set_reg(vcpu, Rt, params.regval);
 		return 1;
@@ -2357,38 +2349,22 @@ static int kvm_handle_cp_32(struct kvm_vcpu *vcpu,
 
 int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
-	const struct sys_reg_desc *target_specific;
-	size_t num;
-
-	target_specific = get_target_table(vcpu->arch.target, false, &num);
-	return kvm_handle_cp_64(vcpu,
-				cp15_64_regs, ARRAY_SIZE(cp15_64_regs),
-				target_specific, num);
+	return kvm_handle_cp_64(vcpu, cp15_64_regs, ARRAY_SIZE(cp15_64_regs));
 }
 
 int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
-	const struct sys_reg_desc *target_specific;
-	size_t num;
-
-	target_specific = get_target_table(vcpu->arch.target, false, &num);
-	return kvm_handle_cp_32(vcpu,
-				cp15_regs, ARRAY_SIZE(cp15_regs),
-				target_specific, num);
+	return kvm_handle_cp_32(vcpu, cp15_regs, ARRAY_SIZE(cp15_regs));
 }
 
 int kvm_handle_cp14_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
-	return kvm_handle_cp_64(vcpu,
-				cp14_64_regs, ARRAY_SIZE(cp14_64_regs),
-				NULL, 0);
+	return kvm_handle_cp_64(vcpu, cp14_64_regs, ARRAY_SIZE(cp14_64_regs));
 }
 
 int kvm_handle_cp14_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
-	return kvm_handle_cp_32(vcpu,
-				cp14_regs, ARRAY_SIZE(cp14_regs),
-				NULL, 0);
+	return kvm_handle_cp_32(vcpu, cp14_regs, ARRAY_SIZE(cp14_regs));
 }
 
 static bool is_imp_def_sys_reg(struct sys_reg_params *params)
@@ -2400,15 +2376,9 @@ static bool is_imp_def_sys_reg(struct sys_reg_params *params)
 static int emulate_sys_reg(struct kvm_vcpu *vcpu,
 			   struct sys_reg_params *params)
 {
-	size_t num;
-	const struct sys_reg_desc *table, *r;
-
-	table = get_target_table(vcpu->arch.target, true, &num);
+	const struct sys_reg_desc *r;
 
-	/* Search target-specific then generic table. */
-	r = find_reg(params, table, num);
-	if (!r)
-		r = find_reg(params, sys_reg_descs, ARRAY_SIZE(sys_reg_descs));
+	r = find_reg(params, sys_reg_descs, ARRAY_SIZE(sys_reg_descs));
 
 	if (likely(r)) {
 		perform_access(vcpu, params, r);
@@ -2512,8 +2482,7 @@ const struct sys_reg_desc *find_reg_by_id(u64 id,
 static const struct sys_reg_desc *index_to_sys_reg_desc(struct kvm_vcpu *vcpu,
 						    u64 id)
 {
-	size_t num;
-	const struct sys_reg_desc *table, *r;
+	const struct sys_reg_desc *r;
 	struct sys_reg_params params;
 
 	/* We only do sys_reg for now. */
@@ -2523,10 +2492,7 @@ static const struct sys_reg_desc *index_to_sys_reg_desc(struct kvm_vcpu *vcpu,
 	if (!index_to_params(id, &params))
 		return NULL;
 
-	table = get_target_table(vcpu->arch.target, true, &num);
-	r = find_reg(&params, table, num);
-	if (!r)
-		r = find_reg(&params, sys_reg_descs, ARRAY_SIZE(sys_reg_descs));
+	r = find_reg(&params, sys_reg_descs, ARRAY_SIZE(sys_reg_descs));
 
 	/* Not saved in the sys_reg array and not otherwise accessible? */
 	if (r && !(r->reg || r->get_user))
@@ -2826,38 +2792,17 @@ static int walk_one_sys_reg(const struct kvm_vcpu *vcpu,
 /* Assumed ordered tables, see kvm_sys_reg_table_init. */
 static int walk_sys_regs(struct kvm_vcpu *vcpu, u64 __user *uind)
 {
-	const struct sys_reg_desc *i1, *i2, *end1, *end2;
+	const struct sys_reg_desc *i2, *end2;
 	unsigned int total = 0;
-	size_t num;
 	int err;
 
-	/* We check for duplicates here, to allow arch-specific overrides. */
-	i1 = get_target_table(vcpu->arch.target, true, &num);
-	end1 = i1 + num;
 	i2 = sys_reg_descs;
 	end2 = sys_reg_descs + ARRAY_SIZE(sys_reg_descs);
 
-	if (i1 == end1)
-		i1 = NULL;
-
-	BUG_ON(i2 == end2);
-
-	/* Walk carefully, as both tables may refer to the same register. */
-	while (i1 || i2) {
-		int cmp = cmp_sys_reg(i1, i2);
-		/* target-specific overrides generic entry. */
-		if (cmp <= 0)
-			err = walk_one_sys_reg(vcpu, i1, &uind, &total);
-		else
-			err = walk_one_sys_reg(vcpu, i2, &uind, &total);
-
+	while (i2 != end2) {
+		err = walk_one_sys_reg(vcpu, i2++, &uind, &total);
 		if (err)
 			return err;
-
-		if (cmp <= 0 && ++i1 == end1)
-			i1 = NULL;
-		if (cmp >= 0 && ++i2 == end2)
-			i2 = NULL;
 	}
 	return total;
 }
-- 
cgit 


From 750ed56693803e992ed09ac9c46e07226dd4d350 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Mon, 22 Jun 2020 11:33:17 +0000
Subject: KVM: arm64: Remove the target table

Finally, remove the target table. Merge the code that checks the
tables into kvm_reset_sys_regs() as there is now only one table.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200622113317.20477-6-james.morse@arm.com
---
 arch/arm64/include/asm/kvm_coproc.h  |  7 -----
 arch/arm64/kvm/Makefile              |  2 +-
 arch/arm64/kvm/sys_regs.c            | 57 +++++++-----------------------------
 arch/arm64/kvm/sys_regs.h            |  2 --
 arch/arm64/kvm/sys_regs_generic_v8.c | 55 ----------------------------------
 5 files changed, 12 insertions(+), 111 deletions(-)
 delete mode 100644 arch/arm64/kvm/sys_regs_generic_v8.c

diff --git a/arch/arm64/include/asm/kvm_coproc.h b/arch/arm64/include/asm/kvm_coproc.h
index 4bf0d6d05e0f..147f3a77e6a5 100644
--- a/arch/arm64/include/asm/kvm_coproc.h
+++ b/arch/arm64/include/asm/kvm_coproc.h
@@ -19,13 +19,6 @@ struct kvm_sys_reg_table {
 	size_t num;
 };
 
-struct kvm_sys_reg_target_table {
-	struct kvm_sys_reg_table table64;
-	struct kvm_sys_reg_table table32;
-};
-
-void kvm_check_target_sys_reg_table(struct kvm_sys_reg_target_table *table);
-
 int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu, struct kvm_run *run);
 int kvm_handle_cp14_32(struct kvm_vcpu *vcpu, struct kvm_run *run);
 int kvm_handle_cp14_64(struct kvm_vcpu *vcpu, struct kvm_run *run);
diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile
index 8d3d9513cbfe..48cda50aa225 100644
--- a/arch/arm64/kvm/Makefile
+++ b/arch/arm64/kvm/Makefile
@@ -14,7 +14,7 @@ kvm-y := $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o \
 	 $(KVM)/vfio.o $(KVM)/irqchip.o \
 	 arm.o mmu.o mmio.o psci.o perf.o hypercalls.o pvtime.o \
 	 inject_fault.o regmap.o va_layout.o hyp.o hyp-init.o handle_exit.o \
-	 guest.o debug.o reset.o sys_regs.o sys_regs_generic_v8.o \
+	 guest.o debug.o reset.o sys_regs.o \
 	 vgic-sys-reg-v3.o fpsimd.o pmu.o \
 	 aarch32.o arch_timer.o \
 	 vgic/vgic.o vgic/vgic-init.o \
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 14333005b476..41a4d3d2a312 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -2137,28 +2137,6 @@ static int check_sysreg_table(const struct sys_reg_desc *table, unsigned int n,
 	return 0;
 }
 
-void kvm_check_target_sys_reg_table(struct kvm_sys_reg_target_table *table)
-{
-	BUG_ON(check_sysreg_table(table->table64.table, table->table64.num, false));
-	BUG_ON(check_sysreg_table(table->table32.table, table->table32.num, true));
-}
-
-/* Get specific register table for this target. */
-static const struct sys_reg_desc *get_target_table(unsigned target,
-						   bool mode_is_64,
-						   size_t *num)
-{
-	struct kvm_sys_reg_target_table *table = &genericv8_target_table;
-
-	if (mode_is_64) {
-		*num = table->table64.num;
-		return table->table64.table;
-	} else {
-		*num = table->table32.num;
-		return table->table32.table;
-	}
-}
-
 static int match_sys_reg(const void *key, const void *elt)
 {
 	const unsigned long pval = (unsigned long)key;
@@ -2393,14 +2371,20 @@ static int emulate_sys_reg(struct kvm_vcpu *vcpu,
 	return 1;
 }
 
-static void reset_sys_reg_descs(struct kvm_vcpu *vcpu,
-				const struct sys_reg_desc *table, size_t num)
+/**
+ * kvm_reset_sys_regs - sets system registers to reset value
+ * @vcpu: The VCPU pointer
+ *
+ * This function finds the right table above and sets the registers on the
+ * virtual CPU struct to their architecturally defined reset values.
+ */
+void kvm_reset_sys_regs(struct kvm_vcpu *vcpu)
 {
 	unsigned long i;
 
-	for (i = 0; i < num; i++)
-		if (table[i].reset)
-			table[i].reset(vcpu, &table[i]);
+	for (i = 0; i < ARRAY_SIZE(sys_reg_descs); i++)
+		if (sys_reg_descs[i].reset)
+			sys_reg_descs[i].reset(vcpu, &sys_reg_descs[i]);
 }
 
 /**
@@ -2869,22 +2853,3 @@ void kvm_sys_reg_table_init(void)
 	/* Clear all higher bits. */
 	cache_levels &= (1 << (i*3))-1;
 }
-
-/**
- * kvm_reset_sys_regs - sets system registers to reset value
- * @vcpu: The VCPU pointer
- *
- * This function finds the right table above and sets the registers on the
- * virtual CPU struct to their architecturally defined reset values.
- */
-void kvm_reset_sys_regs(struct kvm_vcpu *vcpu)
-{
-	size_t num;
-	const struct sys_reg_desc *table;
-
-	/* Generic chip reset first (so target could override). */
-	reset_sys_reg_descs(vcpu, sys_reg_descs, ARRAY_SIZE(sys_reg_descs));
-
-	table = get_target_table(vcpu->arch.target, true, &num);
-	reset_sys_reg_descs(vcpu, table, num);
-}
diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h
index 933609e883bf..5a6fc30f5989 100644
--- a/arch/arm64/kvm/sys_regs.h
+++ b/arch/arm64/kvm/sys_regs.h
@@ -165,6 +165,4 @@ const struct sys_reg_desc *find_reg_by_id(u64 id,
 	CRn(sys_reg_CRn(reg)), CRm(sys_reg_CRm(reg)),	\
 	Op2(sys_reg_Op2(reg))
 
-extern struct kvm_sys_reg_target_table genericv8_target_table;
-
 #endif /* __ARM64_KVM_SYS_REGS_LOCAL_H__ */
diff --git a/arch/arm64/kvm/sys_regs_generic_v8.c b/arch/arm64/kvm/sys_regs_generic_v8.c
deleted file mode 100644
index a7e21e61beea..000000000000
--- a/arch/arm64/kvm/sys_regs_generic_v8.c
+++ /dev/null
@@ -1,55 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Copyright (C) 2012,2013 - ARM Ltd
- * Author: Marc Zyngier <marc.zyngier@arm.com>
- *
- * Based on arch/arm/kvm/coproc_a15.c:
- * Copyright (C) 2012 - Virtual Open Systems and Columbia University
- * Authors: Rusty Russell <rusty@rustcorp.au>
- *          Christoffer Dall <c.dall@virtualopensystems.com>
- */
-#include <linux/kvm_host.h>
-#include <asm/cputype.h>
-#include <asm/kvm_arm.h>
-#include <asm/kvm_asm.h>
-#include <asm/kvm_emulate.h>
-#include <asm/kvm_coproc.h>
-#include <asm/sysreg.h>
-#include <linux/init.h>
-
-#include "sys_regs.h"
-
-/*
- * Implementation specific sys-reg registers.
- * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2
- */
-static const struct sys_reg_desc genericv8_sys_regs[] = {
-};
-
-static const struct sys_reg_desc genericv8_cp15_regs[] = {
-};
-
-struct kvm_sys_reg_target_table genericv8_target_table = {
-	.table64 = {
-		.table = genericv8_sys_regs,
-		.num = ARRAY_SIZE(genericv8_sys_regs),
-	},
-	.table32 = {
-		.table = genericv8_cp15_regs,
-		.num = ARRAY_SIZE(genericv8_cp15_regs),
-	},
-};
-
-static int __init sys_reg_genericv8_init(void)
-{
-	unsigned int i;
-
-	for (i = 1; i < ARRAY_SIZE(genericv8_sys_regs); i++)
-		BUG_ON(cmp_sys_reg(&genericv8_sys_regs[i-1],
-			       &genericv8_sys_regs[i]) >= 0);
-
-	kvm_check_target_sys_reg_table(&genericv8_target_table);
-
-	return 0;
-}
-late_initcall(sys_reg_genericv8_init);
-- 
cgit 


From b38b298aa4397e2dc74a89b4dd3eac9e59b64c96 Mon Sep 17 00:00:00 2001
From: David Brazdil <dbrazdil@google.com>
Date: Thu, 25 Jun 2020 14:14:06 +0100
Subject: KVM: arm64: Fix symbol dependency in __hyp_call_panic_nvhe

__hyp_call_panic_nvhe contains inline assembly which did not declare
its dependency on the __hyp_panic_string symbol.

The static-declared string has previously been kept alive because of a use in
__hyp_call_panic_vhe. Fix this in preparation for separating the source files
between VHE and nVHE when the two users land in two different compilation
units. The static variable otherwise gets dropped when compiling the nVHE
source file, causing an undefined symbol linker error later.

Signed-off-by: David Brazdil <dbrazdil@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200625131420.71444-2-dbrazdil@google.com
---
 arch/arm64/kvm/hyp/switch.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index db1c4487d95d..9270b14157b5 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -897,7 +897,7 @@ static void __hyp_text __hyp_call_panic_nvhe(u64 spsr, u64 elr, u64 par,
 	 * making sure it is a kernel address and not a PC-relative
 	 * reference.
 	 */
-	asm volatile("ldr %0, =__hyp_panic_string" : "=r" (str_va));
+	asm volatile("ldr %0, =%1" : "=r" (str_va) : "S" (__hyp_panic_string));
 
 	__hyp_do_panic(str_va,
 		       spsr, elr,
-- 
cgit 


From 7b2399ea5640b2e5f576af08b91091a26f240ea4 Mon Sep 17 00:00:00 2001
From: David Brazdil <dbrazdil@google.com>
Date: Thu, 25 Jun 2020 14:14:07 +0100
Subject: KVM: arm64: Move __smccc_workaround_1_smc to .rodata

This snippet of assembly is used by cpu_errata.c to overwrite parts of KVM hyp
vector. Move it to its own source file and change its ELF section to .rodata.

Signed-off-by: David Brazdil <dbrazdil@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200625131420.71444-3-dbrazdil@google.com
---
 arch/arm64/kvm/hyp/Makefile    |  1 +
 arch/arm64/kvm/hyp/hyp-entry.S | 16 ----------------
 arch/arm64/kvm/hyp/smccc_wa.S  | 32 ++++++++++++++++++++++++++++++++
 3 files changed, 33 insertions(+), 16 deletions(-)
 create mode 100644 arch/arm64/kvm/hyp/smccc_wa.S

diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile
index 8c9880783839..5d8357ddc234 100644
--- a/arch/arm64/kvm/hyp/Makefile
+++ b/arch/arm64/kvm/hyp/Makefile
@@ -7,6 +7,7 @@ ccflags-y += -fno-stack-protector -DDISABLE_BRANCH_PROFILING \
 		$(DISABLE_STACKLEAK_PLUGIN)
 
 obj-$(CONFIG_KVM) += hyp.o
+obj-$(CONFIG_KVM_INDIRECT_VECTORS) += smccc_wa.o
 
 hyp-y := vgic-v3-sr.o timer-sr.o aarch32.o vgic-v2-cpuif-proxy.o sysreg-sr.o \
 	 debug-sr.o entry.o switch.o fpsimd.o tlb.o hyp-entry.o
diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S
index 9c5cfb04170e..d362fad97cc8 100644
--- a/arch/arm64/kvm/hyp/hyp-entry.S
+++ b/arch/arm64/kvm/hyp/hyp-entry.S
@@ -318,20 +318,4 @@ SYM_CODE_START(__bp_harden_hyp_vecs)
 1:	.org __bp_harden_hyp_vecs + __BP_HARDEN_HYP_VECS_SZ
 	.org 1b
 SYM_CODE_END(__bp_harden_hyp_vecs)
-
-	.popsection
-
-SYM_CODE_START(__smccc_workaround_1_smc)
-	esb
-	sub	sp, sp, #(8 * 4)
-	stp	x2, x3, [sp, #(8 * 0)]
-	stp	x0, x1, [sp, #(8 * 2)]
-	mov	w0, #ARM_SMCCC_ARCH_WORKAROUND_1
-	smc	#0
-	ldp	x2, x3, [sp, #(8 * 0)]
-	ldp	x0, x1, [sp, #(8 * 2)]
-	add	sp, sp, #(8 * 4)
-1:	.org __smccc_workaround_1_smc + __SMCCC_WORKAROUND_1_SMC_SZ
-	.org 1b
-SYM_CODE_END(__smccc_workaround_1_smc)
 #endif
diff --git a/arch/arm64/kvm/hyp/smccc_wa.S b/arch/arm64/kvm/hyp/smccc_wa.S
new file mode 100644
index 000000000000..b0441dbdf68b
--- /dev/null
+++ b/arch/arm64/kvm/hyp/smccc_wa.S
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2015-2018 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#include <linux/arm-smccc.h>
+#include <linux/linkage.h>
+
+#include <asm/kvm_asm.h>
+#include <asm/kvm_mmu.h>
+
+	/*
+	 * This is not executed directly and is instead copied into the vectors
+	 * by install_bp_hardening_cb().
+	 */
+	.data
+	.pushsection	.rodata
+	.global		__smccc_workaround_1_smc
+SYM_DATA_START(__smccc_workaround_1_smc)
+	esb
+	sub	sp, sp, #(8 * 4)
+	stp	x2, x3, [sp, #(8 * 0)]
+	stp	x0, x1, [sp, #(8 * 2)]
+	mov	w0, #ARM_SMCCC_ARCH_WORKAROUND_1
+	smc	#0
+	ldp	x2, x3, [sp, #(8 * 0)]
+	ldp	x0, x1, [sp, #(8 * 2)]
+	add	sp, sp, #(8 * 4)
+1:	.org __smccc_workaround_1_smc + __SMCCC_WORKAROUND_1_SMC_SZ
+	.org 1b
+SYM_DATA_END(__smccc_workaround_1_smc)
-- 
cgit 


From 7621712918ad4f5e6356193d9058debf657a6254 Mon Sep 17 00:00:00 2001
From: David Brazdil <dbrazdil@google.com>
Date: Thu, 25 Jun 2020 14:14:08 +0100
Subject: KVM: arm64: Add build rules for separate VHE/nVHE object files

Add new folders arch/arm64/kvm/hyp/{vhe,nvhe} and Makefiles for building code
that runs in EL2 under VHE/nVHE KVM, repsectivelly. Add an include folder for
hyp-specific header files which will include code common to VHE/nVHE.

Build nVHE code with -D__KVM_NVHE_HYPERVISOR__, VHE code with
-D__KVM_VHE_HYPERVISOR__.

Under nVHE compile each source file into a `.hyp.tmp.o` object first, then
prefix all its symbols with "__kvm_nvhe_" using `objcopy` and produce
a `.hyp.o`. Suffixes were chosen so that it would be possible for VHE and nVHE
to share some source files, but compiled with different CFLAGS.

The nVHE ELF symbol prefix is added to kallsyms.c as ignored. EL2-only symbols
will never appear in EL1 stack traces.

Due to symbol prefixing, add a section in image-vars.h for aliases of symbols
that are defined in nVHE EL2 and accessed by kernel in EL1 or vice versa.

Signed-off-by: David Brazdil <dbrazdil@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200625131420.71444-4-dbrazdil@google.com
---
 arch/arm64/kernel/image-vars.h   | 14 ++++++++++++++
 arch/arm64/kvm/hyp/Makefile      | 10 +++++++---
 arch/arm64/kvm/hyp/nvhe/Makefile | 34 ++++++++++++++++++++++++++++++++++
 arch/arm64/kvm/hyp/vhe/Makefile  | 17 +++++++++++++++++
 scripts/kallsyms.c               |  1 +
 5 files changed, 73 insertions(+), 3 deletions(-)
 create mode 100644 arch/arm64/kvm/hyp/nvhe/Makefile
 create mode 100644 arch/arm64/kvm/hyp/vhe/Makefile

diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index be0a63ffed23..3dc27da47712 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -51,4 +51,18 @@ __efistub__ctype		= _ctype;
 
 #endif
 
+#ifdef CONFIG_KVM
+
+/*
+ * KVM nVHE code has its own symbol namespace prefixed with __kvm_nvhe_, to
+ * separate it from the kernel proper. The following symbols are legally
+ * accessed by it, therefore provide aliases to make them linkable.
+ * Do not include symbols which may not be safely accessed under hypervisor
+ * memory mappings.
+ */
+
+#define KVM_NVHE_ALIAS(sym) __kvm_nvhe_##sym = sym;
+
+#endif /* CONFIG_KVM */
+
 #endif /* __ARM64_KERNEL_IMAGE_VARS_H */
diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile
index 5d8357ddc234..9c5dfe6ff80b 100644
--- a/arch/arm64/kvm/hyp/Makefile
+++ b/arch/arm64/kvm/hyp/Makefile
@@ -3,10 +3,14 @@
 # Makefile for Kernel-based Virtual Machine module, HYP part
 #
 
-ccflags-y += -fno-stack-protector -DDISABLE_BRANCH_PROFILING \
-		$(DISABLE_STACKLEAK_PLUGIN)
+incdir := $(srctree)/$(src)/include
+subdir-asflags-y := -I$(incdir)
+subdir-ccflags-y := -I$(incdir)				\
+		    -fno-stack-protector		\
+		    -DDISABLE_BRANCH_PROFILING		\
+		    $(DISABLE_STACKLEAK_PLUGIN)
 
-obj-$(CONFIG_KVM) += hyp.o
+obj-$(CONFIG_KVM) += hyp.o nvhe/
 obj-$(CONFIG_KVM_INDIRECT_VECTORS) += smccc_wa.o
 
 hyp-y := vgic-v3-sr.o timer-sr.o aarch32.o vgic-v2-cpuif-proxy.o sysreg-sr.o \
diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile
new file mode 100644
index 000000000000..955f4188e00f
--- /dev/null
+++ b/arch/arm64/kvm/hyp/nvhe/Makefile
@@ -0,0 +1,34 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for Kernel-based Virtual Machine module, HYP/nVHE part
+#
+
+asflags-y := -D__KVM_NVHE_HYPERVISOR__
+ccflags-y := -D__KVM_NVHE_HYPERVISOR__
+
+obj-y :=
+
+obj-y := $(patsubst %.o,%.hyp.o,$(obj-y))
+extra-y := $(patsubst %.hyp.o,%.hyp.tmp.o,$(obj-y))
+
+$(obj)/%.hyp.tmp.o: $(src)/%.c FORCE
+	$(call if_changed_rule,cc_o_c)
+$(obj)/%.hyp.tmp.o: $(src)/%.S FORCE
+	$(call if_changed_rule,as_o_S)
+$(obj)/%.hyp.o: $(obj)/%.hyp.tmp.o FORCE
+	$(call if_changed,hypcopy)
+
+quiet_cmd_hypcopy = HYPCOPY $@
+      cmd_hypcopy = $(OBJCOPY) --prefix-symbols=__kvm_nvhe_ $< $@
+
+# KVM nVHE code is run at a different exception code with a different map, so
+# compiler instrumentation that inserts callbacks or checks into the code may
+# cause crashes. Just disable it.
+GCOV_PROFILE	:= n
+KASAN_SANITIZE	:= n
+UBSAN_SANITIZE	:= n
+KCOV_INSTRUMENT	:= n
+
+# Skip objtool checking for this directory because nVHE code is compiled with
+# non-standard build rules.
+OBJECT_FILES_NON_STANDARD := y
diff --git a/arch/arm64/kvm/hyp/vhe/Makefile b/arch/arm64/kvm/hyp/vhe/Makefile
new file mode 100644
index 000000000000..e04375546081
--- /dev/null
+++ b/arch/arm64/kvm/hyp/vhe/Makefile
@@ -0,0 +1,17 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for Kernel-based Virtual Machine module, HYP/nVHE part
+#
+
+asflags-y := -D__KVM_VHE_HYPERVISOR__
+ccflags-y := -D__KVM_VHE_HYPERVISOR__
+
+obj-y :=
+
+# KVM code is run at a different exception code with a different map, so
+# compiler instrumentation that inserts callbacks or checks into the code may
+# cause crashes. Just disable it.
+GCOV_PROFILE	:= n
+KASAN_SANITIZE	:= n
+UBSAN_SANITIZE	:= n
+KCOV_INSTRUMENT	:= n
diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c
index 6dc3078649fa..0096cd965332 100644
--- a/scripts/kallsyms.c
+++ b/scripts/kallsyms.c
@@ -109,6 +109,7 @@ static bool is_ignored_symbol(const char *name, char type)
 		".LASANPC",		/* s390 kasan local symbols */
 		"__crc_",		/* modversions */
 		"__efistub_",		/* arm64 EFI stub namespace */
+		"__kvm_nvhe_",		/* arm64 non-VHE KVM namespace */
 		NULL
 	};
 
-- 
cgit 


From 53b671128bd7f9ea41ae1a06106d88eb4cf66623 Mon Sep 17 00:00:00 2001
From: David Brazdil <dbrazdil@google.com>
Date: Thu, 25 Jun 2020 14:14:09 +0100
Subject: KVM: arm64: Use build-time defines in has_vhe()

Build system compiles hyp code with macros specifying if the code belongs
to VHE or nVHE. Use these macros to evaluate has_vhe() at compile time.

Signed-off-by: David Brazdil <dbrazdil@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200625131420.71444-5-dbrazdil@google.com
---
 arch/arm64/include/asm/virt.h | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h
index 5051b388c654..09977acc007d 100644
--- a/arch/arm64/include/asm/virt.h
+++ b/arch/arm64/include/asm/virt.h
@@ -85,10 +85,17 @@ static inline bool is_kernel_in_hyp_mode(void)
 
 static __always_inline bool has_vhe(void)
 {
-	if (cpus_have_final_cap(ARM64_HAS_VIRT_HOST_EXTN))
+	/*
+	 * The following macros are defined for code specic to VHE/nVHE.
+	 * If has_vhe() is inlined into those compilation units, it can
+	 * be determined statically. Otherwise fall back to caps.
+	 */
+	if (__is_defined(__KVM_VHE_HYPERVISOR__))
 		return true;
-
-	return false;
+	else if (__is_defined(__KVM_NVHE_HYPERVISOR__))
+		return false;
+	else
+		return cpus_have_final_cap(ARM64_HAS_VIRT_HOST_EXTN);
 }
 
 #endif /* __ASSEMBLY__ */
-- 
cgit 


From f50b6f6ae131b6ee7d5dd738961eda0c00b7f027 Mon Sep 17 00:00:00 2001
From: Andrew Scull <ascull@google.com>
Date: Thu, 25 Jun 2020 14:14:10 +0100
Subject: KVM: arm64: Handle calls to prefixed hyp functions

Once hyp functions are moved to a hyp object, they will have prefixed symbols.
This change declares and gets the address of the prefixed version for calls to
the hyp functions.

To aid migration, the hyp functions that have not yet moved have their prefixed
versions aliased to their non-prefixed version. This begins with all the hyp
functions being listed and will reduce to none of them once the migration is
complete.

Signed-off-by: Andrew Scull <ascull@google.com>

[David: Extracted kvm_call_hyp nVHE branches into own helper macros, added
        comments around symbol aliases.]

Signed-off-by: David Brazdil <dbrazdil@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200625131420.71444-6-dbrazdil@google.com
---
 arch/arm64/include/asm/kvm_asm.h  | 19 +++++++++++++++++++
 arch/arm64/include/asm/kvm_host.h | 17 ++++++++++++++---
 arch/arm64/kernel/image-vars.h    | 26 ++++++++++++++++++++++++++
 3 files changed, 59 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 352aaebf4198..6a682d66a640 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -42,6 +42,24 @@
 
 #include <linux/mm.h>
 
+/*
+ * Translate name of a symbol defined in nVHE hyp to the name seen
+ * by kernel proper. All nVHE symbols are prefixed by the build system
+ * to avoid clashes with the VHE variants.
+ */
+#define kvm_nvhe_sym(sym)	__kvm_nvhe_##sym
+
+#define DECLARE_KVM_VHE_SYM(sym)	extern char sym[]
+#define DECLARE_KVM_NVHE_SYM(sym)	extern char kvm_nvhe_sym(sym)[]
+
+/*
+ * Define a pair of symbols sharing the same name but one defined in
+ * VHE and the other in nVHE hyp implementations.
+ */
+#define DECLARE_KVM_HYP_SYM(sym)		\
+	DECLARE_KVM_VHE_SYM(sym);		\
+	DECLARE_KVM_NVHE_SYM(sym)
+
 /* Translate a kernel address of @sym into its equivalent linear mapping */
 #define kvm_ksym_ref(sym)						\
 	({								\
@@ -50,6 +68,7 @@
 			val = lm_alias(&sym);				\
 		val;							\
 	 })
+#define kvm_ksym_ref_nvhe(sym)	kvm_ksym_ref(kvm_nvhe_sym(sym))
 
 struct kvm;
 struct kvm_vcpu;
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index c3e6fcc664b1..49d1a5cd8f8f 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -448,6 +448,18 @@ void kvm_arm_resume_guest(struct kvm *kvm);
 
 u64 __kvm_call_hyp(void *hypfn, ...);
 
+#define kvm_call_hyp_nvhe(f, ...)					\
+	do {								\
+		DECLARE_KVM_NVHE_SYM(f);				\
+		__kvm_call_hyp(kvm_ksym_ref_nvhe(f), ##__VA_ARGS__);	\
+	} while(0)
+
+#define kvm_call_hyp_nvhe_ret(f, ...)					\
+	({								\
+		DECLARE_KVM_NVHE_SYM(f);				\
+		__kvm_call_hyp(kvm_ksym_ref_nvhe(f), ##__VA_ARGS__);	\
+	})
+
 /*
  * The couple of isb() below are there to guarantee the same behaviour
  * on VHE as on !VHE, where the eret to EL1 acts as a context
@@ -459,7 +471,7 @@ u64 __kvm_call_hyp(void *hypfn, ...);
 			f(__VA_ARGS__);					\
 			isb();						\
 		} else {						\
-			__kvm_call_hyp(kvm_ksym_ref(f), ##__VA_ARGS__); \
+			kvm_call_hyp_nvhe(f, ##__VA_ARGS__);		\
 		}							\
 	} while(0)
 
@@ -471,8 +483,7 @@ u64 __kvm_call_hyp(void *hypfn, ...);
 			ret = f(__VA_ARGS__);				\
 			isb();						\
 		} else {						\
-			ret = __kvm_call_hyp(kvm_ksym_ref(f),		\
-					     ##__VA_ARGS__);		\
+			ret = kvm_call_hyp_nvhe_ret(f, ##__VA_ARGS__);	\
 		}							\
 									\
 		ret;							\
diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index 3dc27da47712..36444bac6a05 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -63,6 +63,32 @@ __efistub__ctype		= _ctype;
 
 #define KVM_NVHE_ALIAS(sym) __kvm_nvhe_##sym = sym;
 
+/* Symbols defined in debug-sr.c (not yet compiled with nVHE build rules). */
+KVM_NVHE_ALIAS(__kvm_get_mdcr_el2);
+
+/* Symbols defined in switch.c (not yet compiled with nVHE build rules). */
+KVM_NVHE_ALIAS(__kvm_vcpu_run_nvhe);
+
+/* Symbols defined in sysreg-sr.c (not yet compiled with nVHE build rules). */
+KVM_NVHE_ALIAS(__kvm_enable_ssbs);
+
+/* Symbols defined in timer-sr.c (not yet compiled with nVHE build rules). */
+KVM_NVHE_ALIAS(__kvm_timer_set_cntvoff);
+
+/* Symbols defined in tlb.c (not yet compiled with nVHE build rules). */
+KVM_NVHE_ALIAS(__kvm_flush_vm_context);
+KVM_NVHE_ALIAS(__kvm_tlb_flush_local_vmid);
+KVM_NVHE_ALIAS(__kvm_tlb_flush_vmid);
+KVM_NVHE_ALIAS(__kvm_tlb_flush_vmid_ipa);
+
+/* Symbols defined in vgic-v3-sr.c (not yet compiled with nVHE build rules). */
+KVM_NVHE_ALIAS(__vgic_v3_get_ich_vtr_el2);
+KVM_NVHE_ALIAS(__vgic_v3_init_lrs);
+KVM_NVHE_ALIAS(__vgic_v3_read_vmcr);
+KVM_NVHE_ALIAS(__vgic_v3_restore_aprs);
+KVM_NVHE_ALIAS(__vgic_v3_save_aprs);
+KVM_NVHE_ALIAS(__vgic_v3_write_vmcr);
+
 #endif /* CONFIG_KVM */
 
 #endif /* __ARM64_KERNEL_IMAGE_VARS_H */
-- 
cgit 


From b877e9849d41e7d2100d2933e0a3971d0ddec011 Mon Sep 17 00:00:00 2001
From: David Brazdil <dbrazdil@google.com>
Date: Thu, 25 Jun 2020 14:14:11 +0100
Subject: KVM: arm64: Build hyp-entry.S separately for VHE/nVHE

hyp-entry.S contains implementation of KVM hyp vectors. This code is mostly
shared between VHE/nVHE, therefore compile it under both VHE and nVHE build
rules. nVHE-specific host HVC handler is hidden behind __KVM_NVHE_HYPERVISOR__.

Adjust code which selects which KVM hyp vecs to install to choose the correct
VHE/nVHE symbol.

Signed-off-by: David Brazdil <dbrazdil@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200625131420.71444-7-dbrazdil@google.com
---
 arch/arm64/include/asm/kvm_asm.h | 22 +++++++++++++++++-----
 arch/arm64/include/asm/mmu.h     |  7 -------
 arch/arm64/kernel/image-vars.h   | 24 ++++++++++++++++++++++++
 arch/arm64/kvm/arm.c             |  2 +-
 arch/arm64/kvm/hyp/Makefile      |  4 ++--
 arch/arm64/kvm/hyp/hyp-entry.S   |  2 ++
 arch/arm64/kvm/hyp/nvhe/Makefile |  2 +-
 arch/arm64/kvm/hyp/vhe/Makefile  |  2 +-
 8 files changed, 48 insertions(+), 17 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 6a682d66a640..6026cbd204ae 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -60,12 +60,17 @@
 	DECLARE_KVM_VHE_SYM(sym);		\
 	DECLARE_KVM_NVHE_SYM(sym)
 
-/* Translate a kernel address of @sym into its equivalent linear mapping */
-#define kvm_ksym_ref(sym)						\
+#define CHOOSE_VHE_SYM(sym)	sym
+#define CHOOSE_NVHE_SYM(sym)	kvm_nvhe_sym(sym)
+#define CHOOSE_HYP_SYM(sym)	(has_vhe() ? CHOOSE_VHE_SYM(sym) \
+					   : CHOOSE_NVHE_SYM(sym))
+
+/* Translate a kernel address @ptr into its equivalent linear mapping */
+#define kvm_ksym_ref(ptr)						\
 	({								\
-		void *val = &sym;					\
+		void *val = (ptr);					\
 		if (!is_kernel_in_hyp_mode())				\
-			val = lm_alias(&sym);				\
+			val = lm_alias((ptr));				\
 		val;							\
 	 })
 #define kvm_ksym_ref_nvhe(sym)	kvm_ksym_ref(kvm_nvhe_sym(sym))
@@ -76,7 +81,14 @@ struct kvm_vcpu;
 extern char __kvm_hyp_init[];
 extern char __kvm_hyp_init_end[];
 
-extern char __kvm_hyp_vector[];
+DECLARE_KVM_HYP_SYM(__kvm_hyp_vector);
+#define __kvm_hyp_vector	CHOOSE_HYP_SYM(__kvm_hyp_vector)
+
+#ifdef CONFIG_KVM_INDIRECT_VECTORS
+extern atomic_t arm64_el2_vector_last_slot;
+DECLARE_KVM_HYP_SYM(__bp_harden_hyp_vecs);
+#define __bp_harden_hyp_vecs	CHOOSE_HYP_SYM(__bp_harden_hyp_vecs)
+#endif
 
 extern void __kvm_flush_vm_context(void);
 extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index 8444df000181..a7a5ecaa2e83 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -45,13 +45,6 @@ struct bp_hardening_data {
 	bp_hardening_cb_t	fn;
 };
 
-#if (defined(CONFIG_HARDEN_BRANCH_PREDICTOR) ||	\
-     defined(CONFIG_HARDEN_EL2_VECTORS))
-
-extern char __bp_harden_hyp_vecs[];
-extern atomic_t arm64_el2_vector_last_slot;
-#endif  /* CONFIG_HARDEN_BRANCH_PREDICTOR || CONFIG_HARDEN_EL2_VECTORS */
-
 #ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
 DECLARE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data);
 
diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index 36444bac6a05..f28da486b75a 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -66,8 +66,17 @@ __efistub__ctype		= _ctype;
 /* Symbols defined in debug-sr.c (not yet compiled with nVHE build rules). */
 KVM_NVHE_ALIAS(__kvm_get_mdcr_el2);
 
+/* Symbols defined in entry.S (not yet compiled with nVHE build rules). */
+KVM_NVHE_ALIAS(__guest_exit);
+KVM_NVHE_ALIAS(abort_guest_exit_end);
+KVM_NVHE_ALIAS(abort_guest_exit_start);
+
+/* Symbols defined in hyp-init.S (not yet compiled with nVHE build rules). */
+KVM_NVHE_ALIAS(__kvm_handle_stub_hvc);
+
 /* Symbols defined in switch.c (not yet compiled with nVHE build rules). */
 KVM_NVHE_ALIAS(__kvm_vcpu_run_nvhe);
+KVM_NVHE_ALIAS(hyp_panic);
 
 /* Symbols defined in sysreg-sr.c (not yet compiled with nVHE build rules). */
 KVM_NVHE_ALIAS(__kvm_enable_ssbs);
@@ -89,6 +98,21 @@ KVM_NVHE_ALIAS(__vgic_v3_restore_aprs);
 KVM_NVHE_ALIAS(__vgic_v3_save_aprs);
 KVM_NVHE_ALIAS(__vgic_v3_write_vmcr);
 
+/* Alternative callbacks for init-time patching of nVHE hyp code. */
+KVM_NVHE_ALIAS(arm64_enable_wa2_handling);
+KVM_NVHE_ALIAS(kvm_patch_vector_branch);
+KVM_NVHE_ALIAS(kvm_update_va_mask);
+
+/* Global kernel state accessed by nVHE hyp code. */
+KVM_NVHE_ALIAS(arm64_ssbd_callback_required);
+KVM_NVHE_ALIAS(kvm_host_data);
+
+/* Kernel constant needed to compute idmap addresses. */
+KVM_NVHE_ALIAS(kimage_voffset);
+
+/* Kernel symbols used to call panic() from nVHE hyp code (via ERET). */
+KVM_NVHE_ALIAS(panic);
+
 #endif /* CONFIG_KVM */
 
 #endif /* __ARM64_KERNEL_IMAGE_VARS_H */
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 90cb90561446..34b551385153 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -1285,7 +1285,7 @@ static void cpu_init_hyp_mode(void)
 	 * so that we can use adr_l to access per-cpu variables in EL2.
 	 */
 	tpidr_el2 = ((unsigned long)this_cpu_ptr(&kvm_host_data) -
-		     (unsigned long)kvm_ksym_ref(kvm_host_data));
+		     (unsigned long)kvm_ksym_ref(&kvm_host_data));
 
 	pgd_ptr = kvm_mmu_get_httbr();
 	hyp_stack_ptr = __this_cpu_read(kvm_arm_hyp_stack_page) + PAGE_SIZE;
diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile
index 9c5dfe6ff80b..8b0cf85080b5 100644
--- a/arch/arm64/kvm/hyp/Makefile
+++ b/arch/arm64/kvm/hyp/Makefile
@@ -10,11 +10,11 @@ subdir-ccflags-y := -I$(incdir)				\
 		    -DDISABLE_BRANCH_PROFILING		\
 		    $(DISABLE_STACKLEAK_PLUGIN)
 
-obj-$(CONFIG_KVM) += hyp.o nvhe/
+obj-$(CONFIG_KVM) += hyp.o vhe/ nvhe/
 obj-$(CONFIG_KVM_INDIRECT_VECTORS) += smccc_wa.o
 
 hyp-y := vgic-v3-sr.o timer-sr.o aarch32.o vgic-v2-cpuif-proxy.o sysreg-sr.o \
-	 debug-sr.o entry.o switch.o fpsimd.o tlb.o hyp-entry.o
+	 debug-sr.o entry.o switch.o fpsimd.o tlb.o
 
 # KVM code is run at a different exception code with a different map, so
 # compiler instrumentation that inserts callbacks or checks into the code may
diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S
index d362fad97cc8..7e3c72fa634f 100644
--- a/arch/arm64/kvm/hyp/hyp-entry.S
+++ b/arch/arm64/kvm/hyp/hyp-entry.S
@@ -40,6 +40,7 @@ el1_sync:				// Guest trapped into EL2
 	ccmp	x0, #ESR_ELx_EC_HVC32, #4, ne
 	b.ne	el1_trap
 
+#ifdef __KVM_NVHE_HYPERVISOR__
 	mrs	x1, vttbr_el2		// If vttbr is valid, the guest
 	cbnz	x1, el1_hvc_guest	// called HVC
 
@@ -74,6 +75,7 @@ el1_sync:				// Guest trapped into EL2
 
 	eret
 	sb
+#endif /* __KVM_NVHE_HYPERVISOR__ */
 
 el1_hvc_guest:
 	/*
diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile
index 955f4188e00f..79eb8eed96a1 100644
--- a/arch/arm64/kvm/hyp/nvhe/Makefile
+++ b/arch/arm64/kvm/hyp/nvhe/Makefile
@@ -6,7 +6,7 @@
 asflags-y := -D__KVM_NVHE_HYPERVISOR__
 ccflags-y := -D__KVM_NVHE_HYPERVISOR__
 
-obj-y :=
+obj-y := ../hyp-entry.o
 
 obj-y := $(patsubst %.o,%.hyp.o,$(obj-y))
 extra-y := $(patsubst %.hyp.o,%.hyp.tmp.o,$(obj-y))
diff --git a/arch/arm64/kvm/hyp/vhe/Makefile b/arch/arm64/kvm/hyp/vhe/Makefile
index e04375546081..323029e02b4e 100644
--- a/arch/arm64/kvm/hyp/vhe/Makefile
+++ b/arch/arm64/kvm/hyp/vhe/Makefile
@@ -6,7 +6,7 @@
 asflags-y := -D__KVM_VHE_HYPERVISOR__
 ccflags-y := -D__KVM_VHE_HYPERVISOR__
 
-obj-y :=
+obj-y := ../hyp-entry.o
 
 # KVM code is run at a different exception code with a different map, so
 # compiler instrumentation that inserts callbacks or checks into the code may
-- 
cgit 


From 208243c752a7eeef4236f7b7d67e806ee356e3f8 Mon Sep 17 00:00:00 2001
From: Andrew Scull <ascull@google.com>
Date: Thu, 25 Jun 2020 14:14:12 +0100
Subject: KVM: arm64: Move hyp-init.S to nVHE

hyp-init.S contains the identity mapped initialisation code for the
non-VHE code that runs at EL2. It is only used for non-VHE.

Adjust code that calls into this to use the prefixed symbol name.

Signed-off-by: Andrew Scull <ascull@google.com>
Signed-off-by: David Brazdil <dbrazdil@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200625131420.71444-8-dbrazdil@google.com
---
 arch/arm64/include/asm/kvm_asm.h   |   5 +-
 arch/arm64/kernel/image-vars.h     |   9 +-
 arch/arm64/kvm/Makefile            |   2 +-
 arch/arm64/kvm/hyp-init.S          | 163 -------------------------------------
 arch/arm64/kvm/hyp/nvhe/Makefile   |   2 +-
 arch/arm64/kvm/hyp/nvhe/hyp-init.S | 163 +++++++++++++++++++++++++++++++++++++
 6 files changed, 173 insertions(+), 171 deletions(-)
 delete mode 100644 arch/arm64/kvm/hyp-init.S
 create mode 100644 arch/arm64/kvm/hyp/nvhe/hyp-init.S

diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 6026cbd204ae..3476abb046e3 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -78,10 +78,9 @@
 struct kvm;
 struct kvm_vcpu;
 
-extern char __kvm_hyp_init[];
-extern char __kvm_hyp_init_end[];
-
+DECLARE_KVM_NVHE_SYM(__kvm_hyp_init);
 DECLARE_KVM_HYP_SYM(__kvm_hyp_vector);
+#define __kvm_hyp_init		CHOOSE_NVHE_SYM(__kvm_hyp_init)
 #define __kvm_hyp_vector	CHOOSE_HYP_SYM(__kvm_hyp_vector)
 
 #ifdef CONFIG_KVM_INDIRECT_VECTORS
diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index f28da486b75a..63186c91b614 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -71,9 +71,6 @@ KVM_NVHE_ALIAS(__guest_exit);
 KVM_NVHE_ALIAS(abort_guest_exit_end);
 KVM_NVHE_ALIAS(abort_guest_exit_start);
 
-/* Symbols defined in hyp-init.S (not yet compiled with nVHE build rules). */
-KVM_NVHE_ALIAS(__kvm_handle_stub_hvc);
-
 /* Symbols defined in switch.c (not yet compiled with nVHE build rules). */
 KVM_NVHE_ALIAS(__kvm_vcpu_run_nvhe);
 KVM_NVHE_ALIAS(hyp_panic);
@@ -113,6 +110,12 @@ KVM_NVHE_ALIAS(kimage_voffset);
 /* Kernel symbols used to call panic() from nVHE hyp code (via ERET). */
 KVM_NVHE_ALIAS(panic);
 
+/* Vectors installed by hyp-init on reset HVC. */
+KVM_NVHE_ALIAS(__hyp_stub_vectors);
+
+/* IDMAP TCR_EL1.T0SZ as computed by the EL1 init code */
+KVM_NVHE_ALIAS(idmap_t0sz);
+
 #endif /* CONFIG_KVM */
 
 #endif /* __ARM64_KERNEL_IMAGE_VARS_H */
diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile
index 8d3d9513cbfe..152d8845a1a2 100644
--- a/arch/arm64/kvm/Makefile
+++ b/arch/arm64/kvm/Makefile
@@ -13,7 +13,7 @@ obj-$(CONFIG_KVM) += hyp/
 kvm-y := $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o \
 	 $(KVM)/vfio.o $(KVM)/irqchip.o \
 	 arm.o mmu.o mmio.o psci.o perf.o hypercalls.o pvtime.o \
-	 inject_fault.o regmap.o va_layout.o hyp.o hyp-init.o handle_exit.o \
+	 inject_fault.o regmap.o va_layout.o hyp.o handle_exit.o \
 	 guest.o debug.o reset.o sys_regs.o sys_regs_generic_v8.o \
 	 vgic-sys-reg-v3.o fpsimd.o pmu.o \
 	 aarch32.o arch_timer.o \
diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S
deleted file mode 100644
index 6e6ed5581eed..000000000000
--- a/arch/arm64/kvm/hyp-init.S
+++ /dev/null
@@ -1,163 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) 2012,2013 - ARM Ltd
- * Author: Marc Zyngier <marc.zyngier@arm.com>
- */
-
-#include <linux/linkage.h>
-
-#include <asm/assembler.h>
-#include <asm/kvm_arm.h>
-#include <asm/kvm_mmu.h>
-#include <asm/pgtable-hwdef.h>
-#include <asm/sysreg.h>
-#include <asm/virt.h>
-
-	.text
-	.pushsection	.hyp.idmap.text, "ax"
-
-	.align	11
-
-SYM_CODE_START(__kvm_hyp_init)
-	ventry	__invalid		// Synchronous EL2t
-	ventry	__invalid		// IRQ EL2t
-	ventry	__invalid		// FIQ EL2t
-	ventry	__invalid		// Error EL2t
-
-	ventry	__invalid		// Synchronous EL2h
-	ventry	__invalid		// IRQ EL2h
-	ventry	__invalid		// FIQ EL2h
-	ventry	__invalid		// Error EL2h
-
-	ventry	__do_hyp_init		// Synchronous 64-bit EL1
-	ventry	__invalid		// IRQ 64-bit EL1
-	ventry	__invalid		// FIQ 64-bit EL1
-	ventry	__invalid		// Error 64-bit EL1
-
-	ventry	__invalid		// Synchronous 32-bit EL1
-	ventry	__invalid		// IRQ 32-bit EL1
-	ventry	__invalid		// FIQ 32-bit EL1
-	ventry	__invalid		// Error 32-bit EL1
-
-__invalid:
-	b	.
-
-	/*
-	 * x0: HYP pgd
-	 * x1: HYP stack
-	 * x2: HYP vectors
-	 * x3: per-CPU offset
-	 */
-__do_hyp_init:
-	/* Check for a stub HVC call */
-	cmp	x0, #HVC_STUB_HCALL_NR
-	b.lo	__kvm_handle_stub_hvc
-
-	phys_to_ttbr x4, x0
-alternative_if ARM64_HAS_CNP
-	orr	x4, x4, #TTBR_CNP_BIT
-alternative_else_nop_endif
-	msr	ttbr0_el2, x4
-
-	mrs	x4, tcr_el1
-	mov_q	x5, TCR_EL2_MASK
-	and	x4, x4, x5
-	mov	x5, #TCR_EL2_RES1
-	orr	x4, x4, x5
-
-	/*
-	 * The ID map may be configured to use an extended virtual address
-	 * range. This is only the case if system RAM is out of range for the
-	 * currently configured page size and VA_BITS, in which case we will
-	 * also need the extended virtual range for the HYP ID map, or we won't
-	 * be able to enable the EL2 MMU.
-	 *
-	 * However, at EL2, there is only one TTBR register, and we can't switch
-	 * between translation tables *and* update TCR_EL2.T0SZ at the same
-	 * time. Bottom line: we need to use the extended range with *both* our
-	 * translation tables.
-	 *
-	 * So use the same T0SZ value we use for the ID map.
-	 */
-	ldr_l	x5, idmap_t0sz
-	bfi	x4, x5, TCR_T0SZ_OFFSET, TCR_TxSZ_WIDTH
-
-	/*
-	 * Set the PS bits in TCR_EL2.
-	 */
-	tcr_compute_pa_size x4, #TCR_EL2_PS_SHIFT, x5, x6
-
-	msr	tcr_el2, x4
-
-	mrs	x4, mair_el1
-	msr	mair_el2, x4
-	isb
-
-	/* Invalidate the stale TLBs from Bootloader */
-	tlbi	alle2
-	dsb	sy
-
-	/*
-	 * Preserve all the RES1 bits while setting the default flags,
-	 * as well as the EE bit on BE. Drop the A flag since the compiler
-	 * is allowed to generate unaligned accesses.
-	 */
-	mov_q	x4, (SCTLR_EL2_RES1 | (SCTLR_ELx_FLAGS & ~SCTLR_ELx_A))
-CPU_BE(	orr	x4, x4, #SCTLR_ELx_EE)
-	msr	sctlr_el2, x4
-	isb
-
-	/* Set the stack and new vectors */
-	kern_hyp_va	x1
-	mov	sp, x1
-	msr	vbar_el2, x2
-
-	/* Set tpidr_el2 for use by HYP */
-	msr	tpidr_el2, x3
-
-	/* Hello, World! */
-	eret
-SYM_CODE_END(__kvm_hyp_init)
-
-SYM_CODE_START(__kvm_handle_stub_hvc)
-	cmp	x0, #HVC_SOFT_RESTART
-	b.ne	1f
-
-	/* This is where we're about to jump, staying at EL2 */
-	msr	elr_el2, x1
-	mov	x0, #(PSR_F_BIT | PSR_I_BIT | PSR_A_BIT | PSR_D_BIT | PSR_MODE_EL2h)
-	msr	spsr_el2, x0
-
-	/* Shuffle the arguments, and don't come back */
-	mov	x0, x2
-	mov	x1, x3
-	mov	x2, x4
-	b	reset
-
-1:	cmp	x0, #HVC_RESET_VECTORS
-	b.ne	1f
-reset:
-	/*
-	 * Reset kvm back to the hyp stub. Do not clobber x0-x4 in
-	 * case we coming via HVC_SOFT_RESTART.
-	 */
-	mrs	x5, sctlr_el2
-	mov_q	x6, SCTLR_ELx_FLAGS
-	bic	x5, x5, x6		// Clear SCTL_M and etc
-	pre_disable_mmu_workaround
-	msr	sctlr_el2, x5
-	isb
-
-	/* Install stub vectors */
-	adr_l	x5, __hyp_stub_vectors
-	msr	vbar_el2, x5
-	mov	x0, xzr
-	eret
-
-1:	/* Bad stub call */
-	mov_q	x0, HVC_STUB_ERR
-	eret
-
-SYM_CODE_END(__kvm_handle_stub_hvc)
-
-	.popsection
diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile
index 79eb8eed96a1..bf2d8dea5400 100644
--- a/arch/arm64/kvm/hyp/nvhe/Makefile
+++ b/arch/arm64/kvm/hyp/nvhe/Makefile
@@ -6,7 +6,7 @@
 asflags-y := -D__KVM_NVHE_HYPERVISOR__
 ccflags-y := -D__KVM_NVHE_HYPERVISOR__
 
-obj-y := ../hyp-entry.o
+obj-y := hyp-init.o ../hyp-entry.o
 
 obj-y := $(patsubst %.o,%.hyp.o,$(obj-y))
 extra-y := $(patsubst %.hyp.o,%.hyp.tmp.o,$(obj-y))
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-init.S b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
new file mode 100644
index 000000000000..6e6ed5581eed
--- /dev/null
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
@@ -0,0 +1,163 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#include <linux/linkage.h>
+
+#include <asm/assembler.h>
+#include <asm/kvm_arm.h>
+#include <asm/kvm_mmu.h>
+#include <asm/pgtable-hwdef.h>
+#include <asm/sysreg.h>
+#include <asm/virt.h>
+
+	.text
+	.pushsection	.hyp.idmap.text, "ax"
+
+	.align	11
+
+SYM_CODE_START(__kvm_hyp_init)
+	ventry	__invalid		// Synchronous EL2t
+	ventry	__invalid		// IRQ EL2t
+	ventry	__invalid		// FIQ EL2t
+	ventry	__invalid		// Error EL2t
+
+	ventry	__invalid		// Synchronous EL2h
+	ventry	__invalid		// IRQ EL2h
+	ventry	__invalid		// FIQ EL2h
+	ventry	__invalid		// Error EL2h
+
+	ventry	__do_hyp_init		// Synchronous 64-bit EL1
+	ventry	__invalid		// IRQ 64-bit EL1
+	ventry	__invalid		// FIQ 64-bit EL1
+	ventry	__invalid		// Error 64-bit EL1
+
+	ventry	__invalid		// Synchronous 32-bit EL1
+	ventry	__invalid		// IRQ 32-bit EL1
+	ventry	__invalid		// FIQ 32-bit EL1
+	ventry	__invalid		// Error 32-bit EL1
+
+__invalid:
+	b	.
+
+	/*
+	 * x0: HYP pgd
+	 * x1: HYP stack
+	 * x2: HYP vectors
+	 * x3: per-CPU offset
+	 */
+__do_hyp_init:
+	/* Check for a stub HVC call */
+	cmp	x0, #HVC_STUB_HCALL_NR
+	b.lo	__kvm_handle_stub_hvc
+
+	phys_to_ttbr x4, x0
+alternative_if ARM64_HAS_CNP
+	orr	x4, x4, #TTBR_CNP_BIT
+alternative_else_nop_endif
+	msr	ttbr0_el2, x4
+
+	mrs	x4, tcr_el1
+	mov_q	x5, TCR_EL2_MASK
+	and	x4, x4, x5
+	mov	x5, #TCR_EL2_RES1
+	orr	x4, x4, x5
+
+	/*
+	 * The ID map may be configured to use an extended virtual address
+	 * range. This is only the case if system RAM is out of range for the
+	 * currently configured page size and VA_BITS, in which case we will
+	 * also need the extended virtual range for the HYP ID map, or we won't
+	 * be able to enable the EL2 MMU.
+	 *
+	 * However, at EL2, there is only one TTBR register, and we can't switch
+	 * between translation tables *and* update TCR_EL2.T0SZ at the same
+	 * time. Bottom line: we need to use the extended range with *both* our
+	 * translation tables.
+	 *
+	 * So use the same T0SZ value we use for the ID map.
+	 */
+	ldr_l	x5, idmap_t0sz
+	bfi	x4, x5, TCR_T0SZ_OFFSET, TCR_TxSZ_WIDTH
+
+	/*
+	 * Set the PS bits in TCR_EL2.
+	 */
+	tcr_compute_pa_size x4, #TCR_EL2_PS_SHIFT, x5, x6
+
+	msr	tcr_el2, x4
+
+	mrs	x4, mair_el1
+	msr	mair_el2, x4
+	isb
+
+	/* Invalidate the stale TLBs from Bootloader */
+	tlbi	alle2
+	dsb	sy
+
+	/*
+	 * Preserve all the RES1 bits while setting the default flags,
+	 * as well as the EE bit on BE. Drop the A flag since the compiler
+	 * is allowed to generate unaligned accesses.
+	 */
+	mov_q	x4, (SCTLR_EL2_RES1 | (SCTLR_ELx_FLAGS & ~SCTLR_ELx_A))
+CPU_BE(	orr	x4, x4, #SCTLR_ELx_EE)
+	msr	sctlr_el2, x4
+	isb
+
+	/* Set the stack and new vectors */
+	kern_hyp_va	x1
+	mov	sp, x1
+	msr	vbar_el2, x2
+
+	/* Set tpidr_el2 for use by HYP */
+	msr	tpidr_el2, x3
+
+	/* Hello, World! */
+	eret
+SYM_CODE_END(__kvm_hyp_init)
+
+SYM_CODE_START(__kvm_handle_stub_hvc)
+	cmp	x0, #HVC_SOFT_RESTART
+	b.ne	1f
+
+	/* This is where we're about to jump, staying at EL2 */
+	msr	elr_el2, x1
+	mov	x0, #(PSR_F_BIT | PSR_I_BIT | PSR_A_BIT | PSR_D_BIT | PSR_MODE_EL2h)
+	msr	spsr_el2, x0
+
+	/* Shuffle the arguments, and don't come back */
+	mov	x0, x2
+	mov	x1, x3
+	mov	x2, x4
+	b	reset
+
+1:	cmp	x0, #HVC_RESET_VECTORS
+	b.ne	1f
+reset:
+	/*
+	 * Reset kvm back to the hyp stub. Do not clobber x0-x4 in
+	 * case we coming via HVC_SOFT_RESTART.
+	 */
+	mrs	x5, sctlr_el2
+	mov_q	x6, SCTLR_ELx_FLAGS
+	bic	x5, x5, x6		// Clear SCTL_M and etc
+	pre_disable_mmu_workaround
+	msr	sctlr_el2, x5
+	isb
+
+	/* Install stub vectors */
+	adr_l	x5, __hyp_stub_vectors
+	msr	vbar_el2, x5
+	mov	x0, xzr
+	eret
+
+1:	/* Bad stub call */
+	mov_q	x0, HVC_STUB_ERR
+	eret
+
+SYM_CODE_END(__kvm_handle_stub_hvc)
+
+	.popsection
-- 
cgit 


From e03fa29164ec1db1a81dc0168d0017a9e0366c7c Mon Sep 17 00:00:00 2001
From: David Brazdil <dbrazdil@google.com>
Date: Thu, 25 Jun 2020 14:14:13 +0100
Subject: KVM: arm64: Duplicate hyp/tlb.c for VHE/nVHE

tlb.c contains code for flushing the TLB, with code shared between VHE/nVHE.
Because common code is small, duplicate tlb.c and specialize each copy for
VHE/nVHE.

Signed-off-by: David Brazdil <dbrazdil@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200625131420.71444-9-dbrazdil@google.com
---
 arch/arm64/kernel/image-vars.h   |  14 ++-
 arch/arm64/kvm/hyp/Makefile      |   2 +-
 arch/arm64/kvm/hyp/nvhe/Makefile |   2 +-
 arch/arm64/kvm/hyp/nvhe/tlb.c    | 156 +++++++++++++++++++++++++
 arch/arm64/kvm/hyp/tlb.c         | 242 ---------------------------------------
 arch/arm64/kvm/hyp/vhe/Makefile  |   2 +-
 arch/arm64/kvm/hyp/vhe/tlb.c     | 161 ++++++++++++++++++++++++++
 7 files changed, 328 insertions(+), 251 deletions(-)
 create mode 100644 arch/arm64/kvm/hyp/nvhe/tlb.c
 delete mode 100644 arch/arm64/kvm/hyp/tlb.c
 create mode 100644 arch/arm64/kvm/hyp/vhe/tlb.c

diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index 63186c91b614..f029f3ea7ffe 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -81,12 +81,6 @@ KVM_NVHE_ALIAS(__kvm_enable_ssbs);
 /* Symbols defined in timer-sr.c (not yet compiled with nVHE build rules). */
 KVM_NVHE_ALIAS(__kvm_timer_set_cntvoff);
 
-/* Symbols defined in tlb.c (not yet compiled with nVHE build rules). */
-KVM_NVHE_ALIAS(__kvm_flush_vm_context);
-KVM_NVHE_ALIAS(__kvm_tlb_flush_local_vmid);
-KVM_NVHE_ALIAS(__kvm_tlb_flush_vmid);
-KVM_NVHE_ALIAS(__kvm_tlb_flush_vmid_ipa);
-
 /* Symbols defined in vgic-v3-sr.c (not yet compiled with nVHE build rules). */
 KVM_NVHE_ALIAS(__vgic_v3_get_ich_vtr_el2);
 KVM_NVHE_ALIAS(__vgic_v3_init_lrs);
@@ -116,6 +110,14 @@ KVM_NVHE_ALIAS(__hyp_stub_vectors);
 /* IDMAP TCR_EL1.T0SZ as computed by the EL1 init code */
 KVM_NVHE_ALIAS(idmap_t0sz);
 
+/* Kernel symbol used by icache_is_vpipt(). */
+KVM_NVHE_ALIAS(__icache_flags);
+
+/* Kernel symbols needed for cpus_have_final/const_caps checks. */
+KVM_NVHE_ALIAS(arm64_const_caps_ready);
+KVM_NVHE_ALIAS(cpu_hwcap_keys);
+KVM_NVHE_ALIAS(cpu_hwcaps);
+
 #endif /* CONFIG_KVM */
 
 #endif /* __ARM64_KERNEL_IMAGE_VARS_H */
diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile
index 8b0cf85080b5..87d3cce2b26e 100644
--- a/arch/arm64/kvm/hyp/Makefile
+++ b/arch/arm64/kvm/hyp/Makefile
@@ -14,7 +14,7 @@ obj-$(CONFIG_KVM) += hyp.o vhe/ nvhe/
 obj-$(CONFIG_KVM_INDIRECT_VECTORS) += smccc_wa.o
 
 hyp-y := vgic-v3-sr.o timer-sr.o aarch32.o vgic-v2-cpuif-proxy.o sysreg-sr.o \
-	 debug-sr.o entry.o switch.o fpsimd.o tlb.o
+	 debug-sr.o entry.o switch.o fpsimd.o
 
 # KVM code is run at a different exception code with a different map, so
 # compiler instrumentation that inserts callbacks or checks into the code may
diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile
index bf2d8dea5400..a5316e97d373 100644
--- a/arch/arm64/kvm/hyp/nvhe/Makefile
+++ b/arch/arm64/kvm/hyp/nvhe/Makefile
@@ -6,7 +6,7 @@
 asflags-y := -D__KVM_NVHE_HYPERVISOR__
 ccflags-y := -D__KVM_NVHE_HYPERVISOR__
 
-obj-y := hyp-init.o ../hyp-entry.o
+obj-y := tlb.o hyp-init.o ../hyp-entry.o
 
 obj-y := $(patsubst %.o,%.hyp.o,$(obj-y))
 extra-y := $(patsubst %.hyp.o,%.hyp.tmp.o,$(obj-y))
diff --git a/arch/arm64/kvm/hyp/nvhe/tlb.c b/arch/arm64/kvm/hyp/nvhe/tlb.c
new file mode 100644
index 000000000000..deb48c8c00ee
--- /dev/null
+++ b/arch/arm64/kvm/hyp/nvhe/tlb.c
@@ -0,0 +1,156 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#include <asm/kvm_hyp.h>
+#include <asm/kvm_mmu.h>
+#include <asm/tlbflush.h>
+
+struct tlb_inv_context {
+	u64		tcr;
+};
+
+static void __hyp_text __tlb_switch_to_guest(struct kvm *kvm,
+					     struct tlb_inv_context *cxt)
+{
+	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
+		u64 val;
+
+		/*
+		 * For CPUs that are affected by ARM 1319367, we need to
+		 * avoid a host Stage-1 walk while we have the guest's
+		 * VMID set in the VTTBR in order to invalidate TLBs.
+		 * We're guaranteed that the S1 MMU is enabled, so we can
+		 * simply set the EPD bits to avoid any further TLB fill.
+		 */
+		val = cxt->tcr = read_sysreg_el1(SYS_TCR);
+		val |= TCR_EPD1_MASK | TCR_EPD0_MASK;
+		write_sysreg_el1(val, SYS_TCR);
+		isb();
+	}
+
+	/* __load_guest_stage2() includes an ISB for the workaround. */
+	__load_guest_stage2(kvm);
+	asm(ALTERNATIVE("isb", "nop", ARM64_WORKAROUND_SPECULATIVE_AT));
+}
+
+static void __hyp_text __tlb_switch_to_host(struct kvm *kvm,
+					    struct tlb_inv_context *cxt)
+{
+	write_sysreg(0, vttbr_el2);
+
+	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
+		/* Ensure write of the host VMID */
+		isb();
+		/* Restore the host's TCR_EL1 */
+		write_sysreg_el1(cxt->tcr, SYS_TCR);
+	}
+}
+
+void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
+{
+	struct tlb_inv_context cxt;
+
+	dsb(ishst);
+
+	/* Switch to requested VMID */
+	kvm = kern_hyp_va(kvm);
+	__tlb_switch_to_guest(kvm, &cxt);
+
+	/*
+	 * We could do so much better if we had the VA as well.
+	 * Instead, we invalidate Stage-2 for this IPA, and the
+	 * whole of Stage-1. Weep...
+	 */
+	ipa >>= 12;
+	__tlbi(ipas2e1is, ipa);
+
+	/*
+	 * We have to ensure completion of the invalidation at Stage-2,
+	 * since a table walk on another CPU could refill a TLB with a
+	 * complete (S1 + S2) walk based on the old Stage-2 mapping if
+	 * the Stage-1 invalidation happened first.
+	 */
+	dsb(ish);
+	__tlbi(vmalle1is);
+	dsb(ish);
+	isb();
+
+	/*
+	 * If the host is running at EL1 and we have a VPIPT I-cache,
+	 * then we must perform I-cache maintenance at EL2 in order for
+	 * it to have an effect on the guest. Since the guest cannot hit
+	 * I-cache lines allocated with a different VMID, we don't need
+	 * to worry about junk out of guest reset (we nuke the I-cache on
+	 * VMID rollover), but we do need to be careful when remapping
+	 * executable pages for the same guest. This can happen when KSM
+	 * takes a CoW fault on an executable page, copies the page into
+	 * a page that was previously mapped in the guest and then needs
+	 * to invalidate the guest view of the I-cache for that page
+	 * from EL1. To solve this, we invalidate the entire I-cache when
+	 * unmapping a page from a guest if we have a VPIPT I-cache but
+	 * the host is running at EL1. As above, we could do better if
+	 * we had the VA.
+	 *
+	 * The moral of this story is: if you have a VPIPT I-cache, then
+	 * you should be running with VHE enabled.
+	 */
+	if (icache_is_vpipt())
+		__flush_icache_all();
+
+	__tlb_switch_to_host(kvm, &cxt);
+}
+
+void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm)
+{
+	struct tlb_inv_context cxt;
+
+	dsb(ishst);
+
+	/* Switch to requested VMID */
+	kvm = kern_hyp_va(kvm);
+	__tlb_switch_to_guest(kvm, &cxt);
+
+	__tlbi(vmalls12e1is);
+	dsb(ish);
+	isb();
+
+	__tlb_switch_to_host(kvm, &cxt);
+}
+
+void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = kern_hyp_va(kern_hyp_va(vcpu)->kvm);
+	struct tlb_inv_context cxt;
+
+	/* Switch to requested VMID */
+	__tlb_switch_to_guest(kvm, &cxt);
+
+	__tlbi(vmalle1);
+	dsb(nsh);
+	isb();
+
+	__tlb_switch_to_host(kvm, &cxt);
+}
+
+void __hyp_text __kvm_flush_vm_context(void)
+{
+	dsb(ishst);
+	__tlbi(alle1is);
+
+	/*
+	 * VIPT and PIPT caches are not affected by VMID, so no maintenance
+	 * is necessary across a VMID rollover.
+	 *
+	 * VPIPT caches constrain lookup and maintenance to the active VMID,
+	 * so we need to invalidate lines with a stale VMID to avoid an ABA
+	 * race after multiple rollovers.
+	 *
+	 */
+	if (icache_is_vpipt())
+		asm volatile("ic ialluis");
+
+	dsb(ish);
+}
diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c
deleted file mode 100644
index d063a576d511..000000000000
--- a/arch/arm64/kvm/hyp/tlb.c
+++ /dev/null
@@ -1,242 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Copyright (C) 2015 - ARM Ltd
- * Author: Marc Zyngier <marc.zyngier@arm.com>
- */
-
-#include <linux/irqflags.h>
-
-#include <asm/kvm_hyp.h>
-#include <asm/kvm_mmu.h>
-#include <asm/tlbflush.h>
-
-struct tlb_inv_context {
-	unsigned long	flags;
-	u64		tcr;
-	u64		sctlr;
-};
-
-static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm,
-						 struct tlb_inv_context *cxt)
-{
-	u64 val;
-
-	local_irq_save(cxt->flags);
-
-	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
-		/*
-		 * For CPUs that are affected by ARM errata 1165522 or 1530923,
-		 * we cannot trust stage-1 to be in a correct state at that
-		 * point. Since we do not want to force a full load of the
-		 * vcpu state, we prevent the EL1 page-table walker to
-		 * allocate new TLBs. This is done by setting the EPD bits
-		 * in the TCR_EL1 register. We also need to prevent it to
-		 * allocate IPA->PA walks, so we enable the S1 MMU...
-		 */
-		val = cxt->tcr = read_sysreg_el1(SYS_TCR);
-		val |= TCR_EPD1_MASK | TCR_EPD0_MASK;
-		write_sysreg_el1(val, SYS_TCR);
-		val = cxt->sctlr = read_sysreg_el1(SYS_SCTLR);
-		val |= SCTLR_ELx_M;
-		write_sysreg_el1(val, SYS_SCTLR);
-	}
-
-	/*
-	 * With VHE enabled, we have HCR_EL2.{E2H,TGE} = {1,1}, and
-	 * most TLB operations target EL2/EL0. In order to affect the
-	 * guest TLBs (EL1/EL0), we need to change one of these two
-	 * bits. Changing E2H is impossible (goodbye TTBR1_EL2), so
-	 * let's flip TGE before executing the TLB operation.
-	 *
-	 * ARM erratum 1165522 requires some special handling (again),
-	 * as we need to make sure both stages of translation are in
-	 * place before clearing TGE. __load_guest_stage2() already
-	 * has an ISB in order to deal with this.
-	 */
-	__load_guest_stage2(kvm);
-	val = read_sysreg(hcr_el2);
-	val &= ~HCR_TGE;
-	write_sysreg(val, hcr_el2);
-	isb();
-}
-
-static void __hyp_text __tlb_switch_to_guest_nvhe(struct kvm *kvm,
-						  struct tlb_inv_context *cxt)
-{
-	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
-		u64 val;
-
-		/*
-		 * For CPUs that are affected by ARM 1319367, we need to
-		 * avoid a host Stage-1 walk while we have the guest's
-		 * VMID set in the VTTBR in order to invalidate TLBs.
-		 * We're guaranteed that the S1 MMU is enabled, so we can
-		 * simply set the EPD bits to avoid any further TLB fill.
-		 */
-		val = cxt->tcr = read_sysreg_el1(SYS_TCR);
-		val |= TCR_EPD1_MASK | TCR_EPD0_MASK;
-		write_sysreg_el1(val, SYS_TCR);
-		isb();
-	}
-
-	/* __load_guest_stage2() includes an ISB for the workaround. */
-	__load_guest_stage2(kvm);
-	asm(ALTERNATIVE("isb", "nop", ARM64_WORKAROUND_SPECULATIVE_AT));
-}
-
-static void __hyp_text __tlb_switch_to_guest(struct kvm *kvm,
-					     struct tlb_inv_context *cxt)
-{
-	if (has_vhe())
-		__tlb_switch_to_guest_vhe(kvm, cxt);
-	else
-		__tlb_switch_to_guest_nvhe(kvm, cxt);
-}
-
-static void __hyp_text __tlb_switch_to_host_vhe(struct kvm *kvm,
-						struct tlb_inv_context *cxt)
-{
-	/*
-	 * We're done with the TLB operation, let's restore the host's
-	 * view of HCR_EL2.
-	 */
-	write_sysreg(0, vttbr_el2);
-	write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2);
-	isb();
-
-	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
-		/* Restore the registers to what they were */
-		write_sysreg_el1(cxt->tcr, SYS_TCR);
-		write_sysreg_el1(cxt->sctlr, SYS_SCTLR);
-	}
-
-	local_irq_restore(cxt->flags);
-}
-
-static void __hyp_text __tlb_switch_to_host_nvhe(struct kvm *kvm,
-						 struct tlb_inv_context *cxt)
-{
-	write_sysreg(0, vttbr_el2);
-
-	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
-		/* Ensure write of the host VMID */
-		isb();
-		/* Restore the host's TCR_EL1 */
-		write_sysreg_el1(cxt->tcr, SYS_TCR);
-	}
-}
-
-static void __hyp_text __tlb_switch_to_host(struct kvm *kvm,
-					    struct tlb_inv_context *cxt)
-{
-	if (has_vhe())
-		__tlb_switch_to_host_vhe(kvm, cxt);
-	else
-		__tlb_switch_to_host_nvhe(kvm, cxt);
-}
-
-void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
-{
-	struct tlb_inv_context cxt;
-
-	dsb(ishst);
-
-	/* Switch to requested VMID */
-	kvm = kern_hyp_va(kvm);
-	__tlb_switch_to_guest(kvm, &cxt);
-
-	/*
-	 * We could do so much better if we had the VA as well.
-	 * Instead, we invalidate Stage-2 for this IPA, and the
-	 * whole of Stage-1. Weep...
-	 */
-	ipa >>= 12;
-	__tlbi(ipas2e1is, ipa);
-
-	/*
-	 * We have to ensure completion of the invalidation at Stage-2,
-	 * since a table walk on another CPU could refill a TLB with a
-	 * complete (S1 + S2) walk based on the old Stage-2 mapping if
-	 * the Stage-1 invalidation happened first.
-	 */
-	dsb(ish);
-	__tlbi(vmalle1is);
-	dsb(ish);
-	isb();
-
-	/*
-	 * If the host is running at EL1 and we have a VPIPT I-cache,
-	 * then we must perform I-cache maintenance at EL2 in order for
-	 * it to have an effect on the guest. Since the guest cannot hit
-	 * I-cache lines allocated with a different VMID, we don't need
-	 * to worry about junk out of guest reset (we nuke the I-cache on
-	 * VMID rollover), but we do need to be careful when remapping
-	 * executable pages for the same guest. This can happen when KSM
-	 * takes a CoW fault on an executable page, copies the page into
-	 * a page that was previously mapped in the guest and then needs
-	 * to invalidate the guest view of the I-cache for that page
-	 * from EL1. To solve this, we invalidate the entire I-cache when
-	 * unmapping a page from a guest if we have a VPIPT I-cache but
-	 * the host is running at EL1. As above, we could do better if
-	 * we had the VA.
-	 *
-	 * The moral of this story is: if you have a VPIPT I-cache, then
-	 * you should be running with VHE enabled.
-	 */
-	if (!has_vhe() && icache_is_vpipt())
-		__flush_icache_all();
-
-	__tlb_switch_to_host(kvm, &cxt);
-}
-
-void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm)
-{
-	struct tlb_inv_context cxt;
-
-	dsb(ishst);
-
-	/* Switch to requested VMID */
-	kvm = kern_hyp_va(kvm);
-	__tlb_switch_to_guest(kvm, &cxt);
-
-	__tlbi(vmalls12e1is);
-	dsb(ish);
-	isb();
-
-	__tlb_switch_to_host(kvm, &cxt);
-}
-
-void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
-{
-	struct kvm *kvm = kern_hyp_va(kern_hyp_va(vcpu)->kvm);
-	struct tlb_inv_context cxt;
-
-	/* Switch to requested VMID */
-	__tlb_switch_to_guest(kvm, &cxt);
-
-	__tlbi(vmalle1);
-	dsb(nsh);
-	isb();
-
-	__tlb_switch_to_host(kvm, &cxt);
-}
-
-void __hyp_text __kvm_flush_vm_context(void)
-{
-	dsb(ishst);
-	__tlbi(alle1is);
-
-	/*
-	 * VIPT and PIPT caches are not affected by VMID, so no maintenance
-	 * is necessary across a VMID rollover.
-	 *
-	 * VPIPT caches constrain lookup and maintenance to the active VMID,
-	 * so we need to invalidate lines with a stale VMID to avoid an ABA
-	 * race after multiple rollovers.
-	 *
-	 */
-	if (icache_is_vpipt())
-		asm volatile("ic ialluis");
-
-	dsb(ish);
-}
diff --git a/arch/arm64/kvm/hyp/vhe/Makefile b/arch/arm64/kvm/hyp/vhe/Makefile
index 323029e02b4e..704140fc5d66 100644
--- a/arch/arm64/kvm/hyp/vhe/Makefile
+++ b/arch/arm64/kvm/hyp/vhe/Makefile
@@ -6,7 +6,7 @@
 asflags-y := -D__KVM_VHE_HYPERVISOR__
 ccflags-y := -D__KVM_VHE_HYPERVISOR__
 
-obj-y := ../hyp-entry.o
+obj-y := tlb.o ../hyp-entry.o
 
 # KVM code is run at a different exception code with a different map, so
 # compiler instrumentation that inserts callbacks or checks into the code may
diff --git a/arch/arm64/kvm/hyp/vhe/tlb.c b/arch/arm64/kvm/hyp/vhe/tlb.c
new file mode 100644
index 000000000000..b275101e9c9c
--- /dev/null
+++ b/arch/arm64/kvm/hyp/vhe/tlb.c
@@ -0,0 +1,161 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#include <linux/irqflags.h>
+
+#include <asm/kvm_hyp.h>
+#include <asm/kvm_mmu.h>
+#include <asm/tlbflush.h>
+
+struct tlb_inv_context {
+	unsigned long	flags;
+	u64		tcr;
+	u64		sctlr;
+};
+
+static void __tlb_switch_to_guest(struct kvm *kvm, struct tlb_inv_context *cxt)
+{
+	u64 val;
+
+	local_irq_save(cxt->flags);
+
+	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
+		/*
+		 * For CPUs that are affected by ARM errata 1165522 or 1530923,
+		 * we cannot trust stage-1 to be in a correct state at that
+		 * point. Since we do not want to force a full load of the
+		 * vcpu state, we prevent the EL1 page-table walker to
+		 * allocate new TLBs. This is done by setting the EPD bits
+		 * in the TCR_EL1 register. We also need to prevent it to
+		 * allocate IPA->PA walks, so we enable the S1 MMU...
+		 */
+		val = cxt->tcr = read_sysreg_el1(SYS_TCR);
+		val |= TCR_EPD1_MASK | TCR_EPD0_MASK;
+		write_sysreg_el1(val, SYS_TCR);
+		val = cxt->sctlr = read_sysreg_el1(SYS_SCTLR);
+		val |= SCTLR_ELx_M;
+		write_sysreg_el1(val, SYS_SCTLR);
+	}
+
+	/*
+	 * With VHE enabled, we have HCR_EL2.{E2H,TGE} = {1,1}, and
+	 * most TLB operations target EL2/EL0. In order to affect the
+	 * guest TLBs (EL1/EL0), we need to change one of these two
+	 * bits. Changing E2H is impossible (goodbye TTBR1_EL2), so
+	 * let's flip TGE before executing the TLB operation.
+	 *
+	 * ARM erratum 1165522 requires some special handling (again),
+	 * as we need to make sure both stages of translation are in
+	 * place before clearing TGE. __load_guest_stage2() already
+	 * has an ISB in order to deal with this.
+	 */
+	__load_guest_stage2(kvm);
+	val = read_sysreg(hcr_el2);
+	val &= ~HCR_TGE;
+	write_sysreg(val, hcr_el2);
+	isb();
+}
+
+static void __tlb_switch_to_host(struct kvm *kvm, struct tlb_inv_context *cxt)
+{
+	/*
+	 * We're done with the TLB operation, let's restore the host's
+	 * view of HCR_EL2.
+	 */
+	write_sysreg(0, vttbr_el2);
+	write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2);
+	isb();
+
+	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
+		/* Restore the registers to what they were */
+		write_sysreg_el1(cxt->tcr, SYS_TCR);
+		write_sysreg_el1(cxt->sctlr, SYS_SCTLR);
+	}
+
+	local_irq_restore(cxt->flags);
+}
+
+void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
+{
+	struct tlb_inv_context cxt;
+
+	dsb(ishst);
+
+	/* Switch to requested VMID */
+	__tlb_switch_to_guest(kvm, &cxt);
+
+	/*
+	 * We could do so much better if we had the VA as well.
+	 * Instead, we invalidate Stage-2 for this IPA, and the
+	 * whole of Stage-1. Weep...
+	 */
+	ipa >>= 12;
+	__tlbi(ipas2e1is, ipa);
+
+	/*
+	 * We have to ensure completion of the invalidation at Stage-2,
+	 * since a table walk on another CPU could refill a TLB with a
+	 * complete (S1 + S2) walk based on the old Stage-2 mapping if
+	 * the Stage-1 invalidation happened first.
+	 */
+	dsb(ish);
+	__tlbi(vmalle1is);
+	dsb(ish);
+	isb();
+
+	__tlb_switch_to_host(kvm, &cxt);
+}
+
+void __kvm_tlb_flush_vmid(struct kvm *kvm)
+{
+	struct tlb_inv_context cxt;
+
+	dsb(ishst);
+
+	/* Switch to requested VMID */
+	__tlb_switch_to_guest(kvm, &cxt);
+
+	__tlbi(vmalls12e1is);
+	dsb(ish);
+	isb();
+
+	__tlb_switch_to_host(kvm, &cxt);
+}
+
+void __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct tlb_inv_context cxt;
+
+	/* Switch to requested VMID */
+	__tlb_switch_to_guest(kvm, &cxt);
+
+	__tlbi(vmalle1);
+	dsb(nsh);
+	isb();
+
+	__tlb_switch_to_host(kvm, &cxt);
+}
+
+void __kvm_flush_vm_context(void)
+{
+	dsb(ishst);
+	__tlbi(alle1is);
+
+	/*
+	 * VIPT and PIPT caches are not affected by VMID, so no maintenance
+	 * is necessary across a VMID rollover.
+	 *
+	 * VPIPT caches constrain lookup and maintenance to the active VMID,
+	 * so we need to invalidate lines with a stale VMID to avoid an ABA
+	 * race after multiple rollovers.
+	 *
+	 */
+	if (icache_is_vpipt())
+		asm volatile("ic ialluis");
+
+	dsb(ish);
+}
-- 
cgit 


From 09cf57eba304246141367b95c89801fd2047ac96 Mon Sep 17 00:00:00 2001
From: David Brazdil <dbrazdil@google.com>
Date: Thu, 25 Jun 2020 14:14:14 +0100
Subject: KVM: arm64: Split hyp/switch.c to VHE/nVHE

switch.c implements context-switching for KVM, with large parts shared between
VHE/nVHE. These common routines are moved to a header file, VHE-specific code
is moved to vhe/switch.c and nVHE-specific code is moved to nvhe/switch.c.

Previously __kvm_vcpu_run needed a different symbol name for VHE/nVHE. This
is cleaned up and the caller in arm.c simplified.

Signed-off-by: David Brazdil <dbrazdil@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200625131420.71444-10-dbrazdil@google.com
---
 arch/arm64/include/asm/kvm_asm.h        |   4 +-
 arch/arm64/include/asm/kvm_hyp.h        |   6 +
 arch/arm64/kernel/image-vars.h          |  37 +-
 arch/arm64/kvm/arm.c                    |   6 +-
 arch/arm64/kvm/hyp/Makefile             |   2 +-
 arch/arm64/kvm/hyp/hyp-entry.S          |   2 +
 arch/arm64/kvm/hyp/include/hyp/switch.h | 509 +++++++++++++++++
 arch/arm64/kvm/hyp/nvhe/Makefile        |   2 +-
 arch/arm64/kvm/hyp/nvhe/switch.c        | 271 +++++++++
 arch/arm64/kvm/hyp/switch.c             | 936 --------------------------------
 arch/arm64/kvm/hyp/sysreg-sr.c          |   4 +-
 arch/arm64/kvm/hyp/vhe/Makefile         |   2 +-
 arch/arm64/kvm/hyp/vhe/switch.c         | 219 ++++++++
 13 files changed, 1048 insertions(+), 952 deletions(-)
 create mode 100644 arch/arm64/kvm/hyp/include/hyp/switch.h
 create mode 100644 arch/arm64/kvm/hyp/nvhe/switch.c
 delete mode 100644 arch/arm64/kvm/hyp/switch.c
 create mode 100644 arch/arm64/kvm/hyp/vhe/switch.c

diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 3476abb046e3..5a91aaae78d2 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -96,9 +96,7 @@ extern void __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu);
 
 extern void __kvm_timer_set_cntvoff(u64 cntvoff);
 
-extern int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu);
-
-extern int __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu);
+extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
 
 extern void __kvm_enable_ssbs(void);
 
diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index ce3080834bfa..82fa05d15b8b 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -81,11 +81,17 @@ void __debug_switch_to_host(struct kvm_vcpu *vcpu);
 void __fpsimd_save_state(struct user_fpsimd_state *fp_regs);
 void __fpsimd_restore_state(struct user_fpsimd_state *fp_regs);
 
+#ifndef __KVM_NVHE_HYPERVISOR__
 void activate_traps_vhe_load(struct kvm_vcpu *vcpu);
 void deactivate_traps_vhe_put(void);
+#endif
 
 u64 __guest_enter(struct kvm_vcpu *vcpu, struct kvm_cpu_context *host_ctxt);
+
+void __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt);
+#ifdef __KVM_NVHE_HYPERVISOR__
 void __noreturn __hyp_do_panic(unsigned long, ...);
+#endif
 
 #endif /* __ARM64_KVM_HYP_H__ */
 
diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index f029f3ea7ffe..06fe9833104a 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -63,30 +63,50 @@ __efistub__ctype		= _ctype;
 
 #define KVM_NVHE_ALIAS(sym) __kvm_nvhe_##sym = sym;
 
+/* Symbols defined in aarch32.c (not yet compiled with nVHE build rules). */
+KVM_NVHE_ALIAS(kvm_skip_instr32);
+
 /* Symbols defined in debug-sr.c (not yet compiled with nVHE build rules). */
+KVM_NVHE_ALIAS(__debug_switch_to_guest);
+KVM_NVHE_ALIAS(__debug_switch_to_host);
 KVM_NVHE_ALIAS(__kvm_get_mdcr_el2);
 
 /* Symbols defined in entry.S (not yet compiled with nVHE build rules). */
+KVM_NVHE_ALIAS(__guest_enter);
 KVM_NVHE_ALIAS(__guest_exit);
 KVM_NVHE_ALIAS(abort_guest_exit_end);
 KVM_NVHE_ALIAS(abort_guest_exit_start);
 
-/* Symbols defined in switch.c (not yet compiled with nVHE build rules). */
-KVM_NVHE_ALIAS(__kvm_vcpu_run_nvhe);
-KVM_NVHE_ALIAS(hyp_panic);
+/* Symbols defined in fpsimd.S (not yet compiled with nVHE build rules). */
+KVM_NVHE_ALIAS(__fpsimd_restore_state);
+KVM_NVHE_ALIAS(__fpsimd_save_state);
 
 /* Symbols defined in sysreg-sr.c (not yet compiled with nVHE build rules). */
 KVM_NVHE_ALIAS(__kvm_enable_ssbs);
+KVM_NVHE_ALIAS(__sysreg32_restore_state);
+KVM_NVHE_ALIAS(__sysreg32_save_state);
+KVM_NVHE_ALIAS(__sysreg_restore_state_nvhe);
+KVM_NVHE_ALIAS(__sysreg_save_state_nvhe);
 
 /* Symbols defined in timer-sr.c (not yet compiled with nVHE build rules). */
 KVM_NVHE_ALIAS(__kvm_timer_set_cntvoff);
+KVM_NVHE_ALIAS(__timer_disable_traps);
+KVM_NVHE_ALIAS(__timer_enable_traps);
+
+/* Symbols defined in vgic-v2-cpuif-proxy.c (not yet compiled with nVHE build rules). */
+KVM_NVHE_ALIAS(__vgic_v2_perform_cpuif_access);
 
 /* Symbols defined in vgic-v3-sr.c (not yet compiled with nVHE build rules). */
+KVM_NVHE_ALIAS(__vgic_v3_activate_traps);
+KVM_NVHE_ALIAS(__vgic_v3_deactivate_traps);
 KVM_NVHE_ALIAS(__vgic_v3_get_ich_vtr_el2);
 KVM_NVHE_ALIAS(__vgic_v3_init_lrs);
+KVM_NVHE_ALIAS(__vgic_v3_perform_cpuif_access);
 KVM_NVHE_ALIAS(__vgic_v3_read_vmcr);
 KVM_NVHE_ALIAS(__vgic_v3_restore_aprs);
+KVM_NVHE_ALIAS(__vgic_v3_restore_state);
 KVM_NVHE_ALIAS(__vgic_v3_save_aprs);
+KVM_NVHE_ALIAS(__vgic_v3_save_state);
 KVM_NVHE_ALIAS(__vgic_v3_write_vmcr);
 
 /* Alternative callbacks for init-time patching of nVHE hyp code. */
@@ -97,11 +117,13 @@ KVM_NVHE_ALIAS(kvm_update_va_mask);
 /* Global kernel state accessed by nVHE hyp code. */
 KVM_NVHE_ALIAS(arm64_ssbd_callback_required);
 KVM_NVHE_ALIAS(kvm_host_data);
+KVM_NVHE_ALIAS(kvm_vgic_global_state);
 
 /* Kernel constant needed to compute idmap addresses. */
 KVM_NVHE_ALIAS(kimage_voffset);
 
 /* Kernel symbols used to call panic() from nVHE hyp code (via ERET). */
+KVM_NVHE_ALIAS(__hyp_panic_string);
 KVM_NVHE_ALIAS(panic);
 
 /* Vectors installed by hyp-init on reset HVC. */
@@ -118,6 +140,15 @@ KVM_NVHE_ALIAS(arm64_const_caps_ready);
 KVM_NVHE_ALIAS(cpu_hwcap_keys);
 KVM_NVHE_ALIAS(cpu_hwcaps);
 
+/* Static keys which are set if a vGIC trap should be handled in hyp. */
+KVM_NVHE_ALIAS(vgic_v2_cpuif_trap);
+KVM_NVHE_ALIAS(vgic_v3_cpuif_trap);
+
+/* Static key checked in pmr_sync(). */
+#ifdef CONFIG_ARM64_PSEUDO_NMI
+KVM_NVHE_ALIAS(gic_pmr_sync);
+#endif
+
 #endif /* CONFIG_KVM */
 
 #endif /* __ARM64_KERNEL_IMAGE_VARS_H */
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 34b551385153..26780b78a523 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -748,11 +748,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		trace_kvm_entry(*vcpu_pc(vcpu));
 		guest_enter_irqoff();
 
-		if (has_vhe()) {
-			ret = kvm_vcpu_run_vhe(vcpu);
-		} else {
-			ret = kvm_call_hyp_ret(__kvm_vcpu_run_nvhe, vcpu);
-		}
+		ret = kvm_call_hyp_ret(__kvm_vcpu_run, vcpu);
 
 		vcpu->mode = OUTSIDE_GUEST_MODE;
 		vcpu->stat.exits++;
diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile
index 87d3cce2b26e..7462d3a8a6f2 100644
--- a/arch/arm64/kvm/hyp/Makefile
+++ b/arch/arm64/kvm/hyp/Makefile
@@ -14,7 +14,7 @@ obj-$(CONFIG_KVM) += hyp.o vhe/ nvhe/
 obj-$(CONFIG_KVM_INDIRECT_VECTORS) += smccc_wa.o
 
 hyp-y := vgic-v3-sr.o timer-sr.o aarch32.o vgic-v2-cpuif-proxy.o sysreg-sr.o \
-	 debug-sr.o entry.o switch.o fpsimd.o
+	 debug-sr.o entry.o fpsimd.o
 
 # KVM code is run at a different exception code with a different map, so
 # compiler instrumentation that inserts callbacks or checks into the code may
diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S
index 7e3c72fa634f..8316ee67d6a0 100644
--- a/arch/arm64/kvm/hyp/hyp-entry.S
+++ b/arch/arm64/kvm/hyp/hyp-entry.S
@@ -182,6 +182,7 @@ el2_error:
 	eret
 	sb
 
+#ifdef __KVM_NVHE_HYPERVISOR__
 SYM_FUNC_START(__hyp_do_panic)
 	mov	lr, #(PSR_F_BIT | PSR_I_BIT | PSR_A_BIT | PSR_D_BIT |\
 		      PSR_MODE_EL1h)
@@ -191,6 +192,7 @@ SYM_FUNC_START(__hyp_do_panic)
 	eret
 	sb
 SYM_FUNC_END(__hyp_do_panic)
+#endif
 
 SYM_CODE_START(__hyp_panic)
 	get_host_ctxt x0, x1
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
new file mode 100644
index 000000000000..65d2a879b93b
--- /dev/null
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -0,0 +1,509 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#ifndef __ARM64_KVM_HYP_SWITCH_H__
+#define __ARM64_KVM_HYP_SWITCH_H__
+
+#include <linux/arm-smccc.h>
+#include <linux/kvm_host.h>
+#include <linux/types.h>
+#include <linux/jump_label.h>
+#include <uapi/linux/psci.h>
+
+#include <kvm/arm_psci.h>
+
+#include <asm/barrier.h>
+#include <asm/cpufeature.h>
+#include <asm/kprobes.h>
+#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>
+#include <asm/processor.h>
+#include <asm/thread_info.h>
+
+extern const char __hyp_panic_string[];
+
+/* Check whether the FP regs were dirtied while in the host-side run loop: */
+static inline bool __hyp_text update_fp_enabled(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * When the system doesn't support FP/SIMD, we cannot rely on
+	 * the _TIF_FOREIGN_FPSTATE flag. However, we always inject an
+	 * abort on the very first access to FP and thus we should never
+	 * see KVM_ARM64_FP_ENABLED. For added safety, make sure we always
+	 * trap the accesses.
+	 */
+	if (!system_supports_fpsimd() ||
+	    vcpu->arch.host_thread_info->flags & _TIF_FOREIGN_FPSTATE)
+		vcpu->arch.flags &= ~(KVM_ARM64_FP_ENABLED |
+				      KVM_ARM64_FP_HOST);
+
+	return !!(vcpu->arch.flags & KVM_ARM64_FP_ENABLED);
+}
+
+/* Save the 32-bit only FPSIMD system register state */
+static inline void __hyp_text __fpsimd_save_fpexc32(struct kvm_vcpu *vcpu)
+{
+	if (!vcpu_el1_is_32bit(vcpu))
+		return;
+
+	vcpu->arch.ctxt.sys_regs[FPEXC32_EL2] = read_sysreg(fpexc32_el2);
+}
+
+static inline void __hyp_text __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * We are about to set CPTR_EL2.TFP to trap all floating point
+	 * register accesses to EL2, however, the ARM ARM clearly states that
+	 * traps are only taken to EL2 if the operation would not otherwise
+	 * trap to EL1.  Therefore, always make sure that for 32-bit guests,
+	 * we set FPEXC.EN to prevent traps to EL1, when setting the TFP bit.
+	 * If FP/ASIMD is not implemented, FPEXC is UNDEFINED and any access to
+	 * it will cause an exception.
+	 */
+	if (vcpu_el1_is_32bit(vcpu) && system_supports_fpsimd()) {
+		write_sysreg(1 << 30, fpexc32_el2);
+		isb();
+	}
+}
+
+static inline void __hyp_text __activate_traps_common(struct kvm_vcpu *vcpu)
+{
+	/* Trap on AArch32 cp15 c15 (impdef sysregs) accesses (EL1 or EL0) */
+	write_sysreg(1 << 15, hstr_el2);
+
+	/*
+	 * Make sure we trap PMU access from EL0 to EL2. Also sanitize
+	 * PMSELR_EL0 to make sure it never contains the cycle
+	 * counter, which could make a PMXEVCNTR_EL0 access UNDEF at
+	 * EL1 instead of being trapped to EL2.
+	 */
+	write_sysreg(0, pmselr_el0);
+	write_sysreg(ARMV8_PMU_USERENR_MASK, pmuserenr_el0);
+	write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2);
+}
+
+static inline void __hyp_text __deactivate_traps_common(void)
+{
+	write_sysreg(0, hstr_el2);
+	write_sysreg(0, pmuserenr_el0);
+}
+
+static inline void __hyp_text ___activate_traps(struct kvm_vcpu *vcpu)
+{
+	u64 hcr = vcpu->arch.hcr_el2;
+
+	if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM))
+		hcr |= HCR_TVM;
+
+	write_sysreg(hcr, hcr_el2);
+
+	if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN) && (hcr & HCR_VSE))
+		write_sysreg_s(vcpu->arch.vsesr_el2, SYS_VSESR_EL2);
+}
+
+static inline void __hyp_text ___deactivate_traps(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * If we pended a virtual abort, preserve it until it gets
+	 * cleared. See D1.14.3 (Virtual Interrupts) for details, but
+	 * the crucial bit is "On taking a vSError interrupt,
+	 * HCR_EL2.VSE is cleared to 0."
+	 */
+	if (vcpu->arch.hcr_el2 & HCR_VSE) {
+		vcpu->arch.hcr_el2 &= ~HCR_VSE;
+		vcpu->arch.hcr_el2 |= read_sysreg(hcr_el2) & HCR_VSE;
+	}
+}
+
+static inline void __hyp_text __activate_vm(struct kvm *kvm)
+{
+	__load_guest_stage2(kvm);
+}
+
+static inline bool __hyp_text __translate_far_to_hpfar(u64 far, u64 *hpfar)
+{
+	u64 par, tmp;
+
+	/*
+	 * Resolve the IPA the hard way using the guest VA.
+	 *
+	 * Stage-1 translation already validated the memory access
+	 * rights. As such, we can use the EL1 translation regime, and
+	 * don't have to distinguish between EL0 and EL1 access.
+	 *
+	 * We do need to save/restore PAR_EL1 though, as we haven't
+	 * saved the guest context yet, and we may return early...
+	 */
+	par = read_sysreg(par_el1);
+	asm volatile("at s1e1r, %0" : : "r" (far));
+	isb();
+
+	tmp = read_sysreg(par_el1);
+	write_sysreg(par, par_el1);
+
+	if (unlikely(tmp & SYS_PAR_EL1_F))
+		return false; /* Translation failed, back to guest */
+
+	/* Convert PAR to HPFAR format */
+	*hpfar = PAR_TO_HPFAR(tmp);
+	return true;
+}
+
+static inline bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu)
+{
+	u8 ec;
+	u64 esr;
+	u64 hpfar, far;
+
+	esr = vcpu->arch.fault.esr_el2;
+	ec = ESR_ELx_EC(esr);
+
+	if (ec != ESR_ELx_EC_DABT_LOW && ec != ESR_ELx_EC_IABT_LOW)
+		return true;
+
+	far = read_sysreg_el2(SYS_FAR);
+
+	/*
+	 * The HPFAR can be invalid if the stage 2 fault did not
+	 * happen during a stage 1 page table walk (the ESR_EL2.S1PTW
+	 * bit is clear) and one of the two following cases are true:
+	 *   1. The fault was due to a permission fault
+	 *   2. The processor carries errata 834220
+	 *
+	 * Therefore, for all non S1PTW faults where we either have a
+	 * permission fault or the errata workaround is enabled, we
+	 * resolve the IPA using the AT instruction.
+	 */
+	if (!(esr & ESR_ELx_S1PTW) &&
+	    (cpus_have_final_cap(ARM64_WORKAROUND_834220) ||
+	     (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) {
+		if (!__translate_far_to_hpfar(far, &hpfar))
+			return false;
+	} else {
+		hpfar = read_sysreg(hpfar_el2);
+	}
+
+	vcpu->arch.fault.far_el2 = far;
+	vcpu->arch.fault.hpfar_el2 = hpfar;
+	return true;
+}
+
+/* Check for an FPSIMD/SVE trap and handle as appropriate */
+static inline bool __hyp_text __hyp_handle_fpsimd(struct kvm_vcpu *vcpu)
+{
+	bool vhe, sve_guest, sve_host;
+	u8 hsr_ec;
+
+	if (!system_supports_fpsimd())
+		return false;
+
+	/*
+	 * Currently system_supports_sve() currently implies has_vhe(),
+	 * so the check is redundant. However, has_vhe() can be determined
+	 * statically and helps the compiler remove dead code.
+	 */
+	if (has_vhe() && system_supports_sve()) {
+		sve_guest = vcpu_has_sve(vcpu);
+		sve_host = vcpu->arch.flags & KVM_ARM64_HOST_SVE_IN_USE;
+		vhe = true;
+	} else {
+		sve_guest = false;
+		sve_host = false;
+		vhe = has_vhe();
+	}
+
+	hsr_ec = kvm_vcpu_trap_get_class(vcpu);
+	if (hsr_ec != ESR_ELx_EC_FP_ASIMD &&
+	    hsr_ec != ESR_ELx_EC_SVE)
+		return false;
+
+	/* Don't handle SVE traps for non-SVE vcpus here: */
+	if (!sve_guest)
+		if (hsr_ec != ESR_ELx_EC_FP_ASIMD)
+			return false;
+
+	/* Valid trap.  Switch the context: */
+
+	if (vhe) {
+		u64 reg = read_sysreg(cpacr_el1) | CPACR_EL1_FPEN;
+
+		if (sve_guest)
+			reg |= CPACR_EL1_ZEN;
+
+		write_sysreg(reg, cpacr_el1);
+	} else {
+		write_sysreg(read_sysreg(cptr_el2) & ~(u64)CPTR_EL2_TFP,
+			     cptr_el2);
+	}
+
+	isb();
+
+	if (vcpu->arch.flags & KVM_ARM64_FP_HOST) {
+		/*
+		 * In the SVE case, VHE is assumed: it is enforced by
+		 * Kconfig and kvm_arch_init().
+		 */
+		if (sve_host) {
+			struct thread_struct *thread = container_of(
+				vcpu->arch.host_fpsimd_state,
+				struct thread_struct, uw.fpsimd_state);
+
+			sve_save_state(sve_pffr(thread),
+				       &vcpu->arch.host_fpsimd_state->fpsr);
+		} else {
+			__fpsimd_save_state(vcpu->arch.host_fpsimd_state);
+		}
+
+		vcpu->arch.flags &= ~KVM_ARM64_FP_HOST;
+	}
+
+	if (sve_guest) {
+		sve_load_state(vcpu_sve_pffr(vcpu),
+			       &vcpu->arch.ctxt.gp_regs.fp_regs.fpsr,
+			       sve_vq_from_vl(vcpu->arch.sve_max_vl) - 1);
+		write_sysreg_s(vcpu->arch.ctxt.sys_regs[ZCR_EL1], SYS_ZCR_EL12);
+	} else {
+		__fpsimd_restore_state(&vcpu->arch.ctxt.gp_regs.fp_regs);
+	}
+
+	/* Skip restoring fpexc32 for AArch64 guests */
+	if (!(read_sysreg(hcr_el2) & HCR_RW))
+		write_sysreg(vcpu->arch.ctxt.sys_regs[FPEXC32_EL2],
+			     fpexc32_el2);
+
+	vcpu->arch.flags |= KVM_ARM64_FP_ENABLED;
+
+	return true;
+}
+
+static inline bool __hyp_text handle_tx2_tvm(struct kvm_vcpu *vcpu)
+{
+	u32 sysreg = esr_sys64_to_sysreg(kvm_vcpu_get_hsr(vcpu));
+	int rt = kvm_vcpu_sys_get_rt(vcpu);
+	u64 val = vcpu_get_reg(vcpu, rt);
+
+	/*
+	 * The normal sysreg handling code expects to see the traps,
+	 * let's not do anything here.
+	 */
+	if (vcpu->arch.hcr_el2 & HCR_TVM)
+		return false;
+
+	switch (sysreg) {
+	case SYS_SCTLR_EL1:
+		write_sysreg_el1(val, SYS_SCTLR);
+		break;
+	case SYS_TTBR0_EL1:
+		write_sysreg_el1(val, SYS_TTBR0);
+		break;
+	case SYS_TTBR1_EL1:
+		write_sysreg_el1(val, SYS_TTBR1);
+		break;
+	case SYS_TCR_EL1:
+		write_sysreg_el1(val, SYS_TCR);
+		break;
+	case SYS_ESR_EL1:
+		write_sysreg_el1(val, SYS_ESR);
+		break;
+	case SYS_FAR_EL1:
+		write_sysreg_el1(val, SYS_FAR);
+		break;
+	case SYS_AFSR0_EL1:
+		write_sysreg_el1(val, SYS_AFSR0);
+		break;
+	case SYS_AFSR1_EL1:
+		write_sysreg_el1(val, SYS_AFSR1);
+		break;
+	case SYS_MAIR_EL1:
+		write_sysreg_el1(val, SYS_MAIR);
+		break;
+	case SYS_AMAIR_EL1:
+		write_sysreg_el1(val, SYS_AMAIR);
+		break;
+	case SYS_CONTEXTIDR_EL1:
+		write_sysreg_el1(val, SYS_CONTEXTIDR);
+		break;
+	default:
+		return false;
+	}
+
+	__kvm_skip_instr(vcpu);
+	return true;
+}
+
+static inline bool __hyp_text esr_is_ptrauth_trap(u32 esr)
+{
+	u32 ec = ESR_ELx_EC(esr);
+
+	if (ec == ESR_ELx_EC_PAC)
+		return true;
+
+	if (ec != ESR_ELx_EC_SYS64)
+		return false;
+
+	switch (esr_sys64_to_sysreg(esr)) {
+	case SYS_APIAKEYLO_EL1:
+	case SYS_APIAKEYHI_EL1:
+	case SYS_APIBKEYLO_EL1:
+	case SYS_APIBKEYHI_EL1:
+	case SYS_APDAKEYLO_EL1:
+	case SYS_APDAKEYHI_EL1:
+	case SYS_APDBKEYLO_EL1:
+	case SYS_APDBKEYHI_EL1:
+	case SYS_APGAKEYLO_EL1:
+	case SYS_APGAKEYHI_EL1:
+		return true;
+	}
+
+	return false;
+}
+
+#define __ptrauth_save_key(regs, key)						\
+({										\
+	regs[key ## KEYLO_EL1] = read_sysreg_s(SYS_ ## key ## KEYLO_EL1);	\
+	regs[key ## KEYHI_EL1] = read_sysreg_s(SYS_ ## key ## KEYHI_EL1);	\
+})
+
+static inline bool __hyp_text __hyp_handle_ptrauth(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpu_context *ctxt;
+	u64 val;
+
+	if (!vcpu_has_ptrauth(vcpu) ||
+	    !esr_is_ptrauth_trap(kvm_vcpu_get_hsr(vcpu)))
+		return false;
+
+	ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
+	__ptrauth_save_key(ctxt->sys_regs, APIA);
+	__ptrauth_save_key(ctxt->sys_regs, APIB);
+	__ptrauth_save_key(ctxt->sys_regs, APDA);
+	__ptrauth_save_key(ctxt->sys_regs, APDB);
+	__ptrauth_save_key(ctxt->sys_regs, APGA);
+
+	vcpu_ptrauth_enable(vcpu);
+
+	val = read_sysreg(hcr_el2);
+	val |= (HCR_API | HCR_APK);
+	write_sysreg(val, hcr_el2);
+
+	return true;
+}
+
+/*
+ * Return true when we were able to fixup the guest exit and should return to
+ * the guest, false when we should restore the host state and return to the
+ * main run loop.
+ */
+static inline bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	if (ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ)
+		vcpu->arch.fault.esr_el2 = read_sysreg_el2(SYS_ESR);
+
+	/*
+	 * We're using the raw exception code in order to only process
+	 * the trap if no SError is pending. We will come back to the
+	 * same PC once the SError has been injected, and replay the
+	 * trapping instruction.
+	 */
+	if (*exit_code != ARM_EXCEPTION_TRAP)
+		goto exit;
+
+	if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM) &&
+	    kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 &&
+	    handle_tx2_tvm(vcpu))
+		return true;
+
+	/*
+	 * We trap the first access to the FP/SIMD to save the host context
+	 * and restore the guest context lazily.
+	 * If FP/SIMD is not implemented, handle the trap and inject an
+	 * undefined instruction exception to the guest.
+	 * Similarly for trapped SVE accesses.
+	 */
+	if (__hyp_handle_fpsimd(vcpu))
+		return true;
+
+	if (__hyp_handle_ptrauth(vcpu))
+		return true;
+
+	if (!__populate_fault_info(vcpu))
+		return true;
+
+	if (static_branch_unlikely(&vgic_v2_cpuif_trap)) {
+		bool valid;
+
+		valid = kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_DABT_LOW &&
+			kvm_vcpu_trap_get_fault_type(vcpu) == FSC_FAULT &&
+			kvm_vcpu_dabt_isvalid(vcpu) &&
+			!kvm_vcpu_dabt_isextabt(vcpu) &&
+			!kvm_vcpu_dabt_iss1tw(vcpu);
+
+		if (valid) {
+			int ret = __vgic_v2_perform_cpuif_access(vcpu);
+
+			if (ret == 1)
+				return true;
+
+			/* Promote an illegal access to an SError.*/
+			if (ret == -1)
+				*exit_code = ARM_EXCEPTION_EL1_SERROR;
+
+			goto exit;
+		}
+	}
+
+	if (static_branch_unlikely(&vgic_v3_cpuif_trap) &&
+	    (kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 ||
+	     kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_CP15_32)) {
+		int ret = __vgic_v3_perform_cpuif_access(vcpu);
+
+		if (ret == 1)
+			return true;
+	}
+
+exit:
+	/* Return to the host kernel and handle the exit */
+	return false;
+}
+
+static inline bool __hyp_text __needs_ssbd_off(struct kvm_vcpu *vcpu)
+{
+	if (!cpus_have_final_cap(ARM64_SSBD))
+		return false;
+
+	return !(vcpu->arch.workaround_flags & VCPU_WORKAROUND_2_FLAG);
+}
+
+static inline void __hyp_text __set_guest_arch_workaround_state(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_ARM64_SSBD
+	/*
+	 * The host runs with the workaround always present. If the
+	 * guest wants it disabled, so be it...
+	 */
+	if (__needs_ssbd_off(vcpu) &&
+	    __hyp_this_cpu_read(arm64_ssbd_callback_required))
+		arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_2, 0, NULL);
+#endif
+}
+
+static inline void __hyp_text __set_host_arch_workaround_state(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_ARM64_SSBD
+	/*
+	 * If the guest has disabled the workaround, bring it back on.
+	 */
+	if (__needs_ssbd_off(vcpu) &&
+	    __hyp_this_cpu_read(arm64_ssbd_callback_required))
+		arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_2, 1, NULL);
+#endif
+}
+
+#endif /* __ARM64_KVM_HYP_SWITCH_H__ */
diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile
index a5316e97d373..8b3ac38eaa44 100644
--- a/arch/arm64/kvm/hyp/nvhe/Makefile
+++ b/arch/arm64/kvm/hyp/nvhe/Makefile
@@ -6,7 +6,7 @@
 asflags-y := -D__KVM_NVHE_HYPERVISOR__
 ccflags-y := -D__KVM_NVHE_HYPERVISOR__
 
-obj-y := tlb.o hyp-init.o ../hyp-entry.o
+obj-y := switch.o tlb.o hyp-init.o ../hyp-entry.o
 
 obj-y := $(patsubst %.o,%.hyp.o,$(obj-y))
 extra-y := $(patsubst %.hyp.o,%.hyp.tmp.o,$(obj-y))
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
new file mode 100644
index 000000000000..7f6b8d3dc637
--- /dev/null
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -0,0 +1,271 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#include <hyp/switch.h>
+
+#include <linux/arm-smccc.h>
+#include <linux/kvm_host.h>
+#include <linux/types.h>
+#include <linux/jump_label.h>
+#include <uapi/linux/psci.h>
+
+#include <kvm/arm_psci.h>
+
+#include <asm/barrier.h>
+#include <asm/cpufeature.h>
+#include <asm/kprobes.h>
+#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>
+#include <asm/processor.h>
+#include <asm/thread_info.h>
+
+static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu)
+{
+	u64 val;
+
+	___activate_traps(vcpu);
+	__activate_traps_common(vcpu);
+
+	val = CPTR_EL2_DEFAULT;
+	val |= CPTR_EL2_TTA | CPTR_EL2_TZ | CPTR_EL2_TAM;
+	if (!update_fp_enabled(vcpu)) {
+		val |= CPTR_EL2_TFP;
+		__activate_traps_fpsimd32(vcpu);
+	}
+
+	write_sysreg(val, cptr_el2);
+
+	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
+		struct kvm_cpu_context *ctxt = &vcpu->arch.ctxt;
+
+		isb();
+		/*
+		 * At this stage, and thanks to the above isb(), S2 is
+		 * configured and enabled. We can now restore the guest's S1
+		 * configuration: SCTLR, and only then TCR.
+		 */
+		write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1],	SYS_SCTLR);
+		isb();
+		write_sysreg_el1(ctxt->sys_regs[TCR_EL1],	SYS_TCR);
+	}
+}
+
+static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu)
+{
+	u64 mdcr_el2;
+
+	___deactivate_traps(vcpu);
+
+	mdcr_el2 = read_sysreg(mdcr_el2);
+
+	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
+		u64 val;
+
+		/*
+		 * Set the TCR and SCTLR registers in the exact opposite
+		 * sequence as __activate_traps (first prevent walks,
+		 * then force the MMU on). A generous sprinkling of isb()
+		 * ensure that things happen in this exact order.
+		 */
+		val = read_sysreg_el1(SYS_TCR);
+		write_sysreg_el1(val | TCR_EPD1_MASK | TCR_EPD0_MASK, SYS_TCR);
+		isb();
+		val = read_sysreg_el1(SYS_SCTLR);
+		write_sysreg_el1(val | SCTLR_ELx_M, SYS_SCTLR);
+		isb();
+	}
+
+	__deactivate_traps_common();
+
+	mdcr_el2 &= MDCR_EL2_HPMN_MASK;
+	mdcr_el2 |= MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT;
+
+	write_sysreg(mdcr_el2, mdcr_el2);
+	write_sysreg(HCR_HOST_NVHE_FLAGS, hcr_el2);
+	write_sysreg(CPTR_EL2_DEFAULT, cptr_el2);
+}
+
+static void __hyp_text __deactivate_vm(struct kvm_vcpu *vcpu)
+{
+	write_sysreg(0, vttbr_el2);
+}
+
+/* Save VGICv3 state on non-VHE systems */
+static void __hyp_text __hyp_vgic_save_state(struct kvm_vcpu *vcpu)
+{
+	if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) {
+		__vgic_v3_save_state(&vcpu->arch.vgic_cpu.vgic_v3);
+		__vgic_v3_deactivate_traps(&vcpu->arch.vgic_cpu.vgic_v3);
+	}
+}
+
+/* Restore VGICv3 state on non_VEH systems */
+static void __hyp_text __hyp_vgic_restore_state(struct kvm_vcpu *vcpu)
+{
+	if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) {
+		__vgic_v3_activate_traps(&vcpu->arch.vgic_cpu.vgic_v3);
+		__vgic_v3_restore_state(&vcpu->arch.vgic_cpu.vgic_v3);
+	}
+}
+
+/**
+ * Disable host events, enable guest events
+ */
+static bool __hyp_text __pmu_switch_to_guest(struct kvm_cpu_context *host_ctxt)
+{
+	struct kvm_host_data *host;
+	struct kvm_pmu_events *pmu;
+
+	host = container_of(host_ctxt, struct kvm_host_data, host_ctxt);
+	pmu = &host->pmu_events;
+
+	if (pmu->events_host)
+		write_sysreg(pmu->events_host, pmcntenclr_el0);
+
+	if (pmu->events_guest)
+		write_sysreg(pmu->events_guest, pmcntenset_el0);
+
+	return (pmu->events_host || pmu->events_guest);
+}
+
+/**
+ * Disable guest events, enable host events
+ */
+static void __hyp_text __pmu_switch_to_host(struct kvm_cpu_context *host_ctxt)
+{
+	struct kvm_host_data *host;
+	struct kvm_pmu_events *pmu;
+
+	host = container_of(host_ctxt, struct kvm_host_data, host_ctxt);
+	pmu = &host->pmu_events;
+
+	if (pmu->events_guest)
+		write_sysreg(pmu->events_guest, pmcntenclr_el0);
+
+	if (pmu->events_host)
+		write_sysreg(pmu->events_host, pmcntenset_el0);
+}
+
+/* Switch to the guest for legacy non-VHE systems */
+int __hyp_text __kvm_vcpu_run(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpu_context *host_ctxt;
+	struct kvm_cpu_context *guest_ctxt;
+	bool pmu_switch_needed;
+	u64 exit_code;
+
+	/*
+	 * Having IRQs masked via PMR when entering the guest means the GIC
+	 * will not signal the CPU of interrupts of lower priority, and the
+	 * only way to get out will be via guest exceptions.
+	 * Naturally, we want to avoid this.
+	 */
+	if (system_uses_irq_prio_masking()) {
+		gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
+		pmr_sync();
+	}
+
+	vcpu = kern_hyp_va(vcpu);
+
+	host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
+	host_ctxt->__hyp_running_vcpu = vcpu;
+	guest_ctxt = &vcpu->arch.ctxt;
+
+	pmu_switch_needed = __pmu_switch_to_guest(host_ctxt);
+
+	__sysreg_save_state_nvhe(host_ctxt);
+
+	/*
+	 * We must restore the 32-bit state before the sysregs, thanks
+	 * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72).
+	 *
+	 * Also, and in order to be able to deal with erratum #1319537 (A57)
+	 * and #1319367 (A72), we must ensure that all VM-related sysreg are
+	 * restored before we enable S2 translation.
+	 */
+	__sysreg32_restore_state(vcpu);
+	__sysreg_restore_state_nvhe(guest_ctxt);
+
+	__activate_vm(kern_hyp_va(vcpu->kvm));
+	__activate_traps(vcpu);
+
+	__hyp_vgic_restore_state(vcpu);
+	__timer_enable_traps(vcpu);
+
+	__debug_switch_to_guest(vcpu);
+
+	__set_guest_arch_workaround_state(vcpu);
+
+	do {
+		/* Jump in the fire! */
+		exit_code = __guest_enter(vcpu, host_ctxt);
+
+		/* And we're baaack! */
+	} while (fixup_guest_exit(vcpu, &exit_code));
+
+	__set_host_arch_workaround_state(vcpu);
+
+	__sysreg_save_state_nvhe(guest_ctxt);
+	__sysreg32_save_state(vcpu);
+	__timer_disable_traps(vcpu);
+	__hyp_vgic_save_state(vcpu);
+
+	__deactivate_traps(vcpu);
+	__deactivate_vm(vcpu);
+
+	__sysreg_restore_state_nvhe(host_ctxt);
+
+	if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED)
+		__fpsimd_save_fpexc32(vcpu);
+
+	/*
+	 * This must come after restoring the host sysregs, since a non-VHE
+	 * system may enable SPE here and make use of the TTBRs.
+	 */
+	__debug_switch_to_host(vcpu);
+
+	if (pmu_switch_needed)
+		__pmu_switch_to_host(host_ctxt);
+
+	/* Returning to host will clear PSR.I, remask PMR if needed */
+	if (system_uses_irq_prio_masking())
+		gic_write_pmr(GIC_PRIO_IRQOFF);
+
+	return exit_code;
+}
+
+void __hyp_text __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt)
+{
+	u64 spsr = read_sysreg_el2(SYS_SPSR);
+	u64 elr = read_sysreg_el2(SYS_ELR);
+	u64 par = read_sysreg(par_el1);
+	struct kvm_vcpu *vcpu = host_ctxt->__hyp_running_vcpu;
+	unsigned long str_va;
+
+	if (read_sysreg(vttbr_el2)) {
+		__timer_disable_traps(vcpu);
+		__deactivate_traps(vcpu);
+		__deactivate_vm(vcpu);
+		__sysreg_restore_state_nvhe(host_ctxt);
+	}
+
+	/*
+	 * Force the panic string to be loaded from the literal pool,
+	 * making sure it is a kernel address and not a PC-relative
+	 * reference.
+	 */
+	asm volatile("ldr %0, =%1" : "=r" (str_va) : "S" (__hyp_panic_string));
+
+	__hyp_do_panic(str_va,
+		       spsr, elr,
+		       read_sysreg(esr_el2), read_sysreg_el2(SYS_FAR),
+		       read_sysreg(hpfar_el2), par, vcpu);
+	unreachable();
+}
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
deleted file mode 100644
index 9270b14157b5..000000000000
--- a/arch/arm64/kvm/hyp/switch.c
+++ /dev/null
@@ -1,936 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Copyright (C) 2015 - ARM Ltd
- * Author: Marc Zyngier <marc.zyngier@arm.com>
- */
-
-#include <linux/arm-smccc.h>
-#include <linux/kvm_host.h>
-#include <linux/types.h>
-#include <linux/jump_label.h>
-#include <uapi/linux/psci.h>
-
-#include <kvm/arm_psci.h>
-
-#include <asm/barrier.h>
-#include <asm/cpufeature.h>
-#include <asm/kprobes.h>
-#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>
-#include <asm/processor.h>
-#include <asm/thread_info.h>
-
-/* Check whether the FP regs were dirtied while in the host-side run loop: */
-static bool __hyp_text update_fp_enabled(struct kvm_vcpu *vcpu)
-{
-	/*
-	 * When the system doesn't support FP/SIMD, we cannot rely on
-	 * the _TIF_FOREIGN_FPSTATE flag. However, we always inject an
-	 * abort on the very first access to FP and thus we should never
-	 * see KVM_ARM64_FP_ENABLED. For added safety, make sure we always
-	 * trap the accesses.
-	 */
-	if (!system_supports_fpsimd() ||
-	    vcpu->arch.host_thread_info->flags & _TIF_FOREIGN_FPSTATE)
-		vcpu->arch.flags &= ~(KVM_ARM64_FP_ENABLED |
-				      KVM_ARM64_FP_HOST);
-
-	return !!(vcpu->arch.flags & KVM_ARM64_FP_ENABLED);
-}
-
-/* Save the 32-bit only FPSIMD system register state */
-static void __hyp_text __fpsimd_save_fpexc32(struct kvm_vcpu *vcpu)
-{
-	if (!vcpu_el1_is_32bit(vcpu))
-		return;
-
-	vcpu->arch.ctxt.sys_regs[FPEXC32_EL2] = read_sysreg(fpexc32_el2);
-}
-
-static void __hyp_text __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
-{
-	/*
-	 * We are about to set CPTR_EL2.TFP to trap all floating point
-	 * register accesses to EL2, however, the ARM ARM clearly states that
-	 * traps are only taken to EL2 if the operation would not otherwise
-	 * trap to EL1.  Therefore, always make sure that for 32-bit guests,
-	 * we set FPEXC.EN to prevent traps to EL1, when setting the TFP bit.
-	 * If FP/ASIMD is not implemented, FPEXC is UNDEFINED and any access to
-	 * it will cause an exception.
-	 */
-	if (vcpu_el1_is_32bit(vcpu) && system_supports_fpsimd()) {
-		write_sysreg(1 << 30, fpexc32_el2);
-		isb();
-	}
-}
-
-static void __hyp_text __activate_traps_common(struct kvm_vcpu *vcpu)
-{
-	/* Trap on AArch32 cp15 c15 (impdef sysregs) accesses (EL1 or EL0) */
-	write_sysreg(1 << 15, hstr_el2);
-
-	/*
-	 * Make sure we trap PMU access from EL0 to EL2. Also sanitize
-	 * PMSELR_EL0 to make sure it never contains the cycle
-	 * counter, which could make a PMXEVCNTR_EL0 access UNDEF at
-	 * EL1 instead of being trapped to EL2.
-	 */
-	write_sysreg(0, pmselr_el0);
-	write_sysreg(ARMV8_PMU_USERENR_MASK, pmuserenr_el0);
-	write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2);
-}
-
-static void __hyp_text __deactivate_traps_common(void)
-{
-	write_sysreg(0, hstr_el2);
-	write_sysreg(0, pmuserenr_el0);
-}
-
-static void activate_traps_vhe(struct kvm_vcpu *vcpu)
-{
-	u64 val;
-
-	val = read_sysreg(cpacr_el1);
-	val |= CPACR_EL1_TTA;
-	val &= ~CPACR_EL1_ZEN;
-
-	/*
-	 * With VHE (HCR.E2H == 1), accesses to CPACR_EL1 are routed to
-	 * CPTR_EL2. In general, CPACR_EL1 has the same layout as CPTR_EL2,
-	 * except for some missing controls, such as TAM.
-	 * In this case, CPTR_EL2.TAM has the same position with or without
-	 * VHE (HCR.E2H == 1) which allows us to use here the CPTR_EL2.TAM
-	 * shift value for trapping the AMU accesses.
-	 */
-
-	val |= CPTR_EL2_TAM;
-
-	if (update_fp_enabled(vcpu)) {
-		if (vcpu_has_sve(vcpu))
-			val |= CPACR_EL1_ZEN;
-	} else {
-		val &= ~CPACR_EL1_FPEN;
-		__activate_traps_fpsimd32(vcpu);
-	}
-
-	write_sysreg(val, cpacr_el1);
-
-	write_sysreg(kvm_get_hyp_vector(), vbar_el1);
-}
-NOKPROBE_SYMBOL(activate_traps_vhe);
-
-static void __hyp_text __activate_traps_nvhe(struct kvm_vcpu *vcpu)
-{
-	u64 val;
-
-	__activate_traps_common(vcpu);
-
-	val = CPTR_EL2_DEFAULT;
-	val |= CPTR_EL2_TTA | CPTR_EL2_TZ | CPTR_EL2_TAM;
-	if (!update_fp_enabled(vcpu)) {
-		val |= CPTR_EL2_TFP;
-		__activate_traps_fpsimd32(vcpu);
-	}
-
-	write_sysreg(val, cptr_el2);
-
-	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
-		struct kvm_cpu_context *ctxt = &vcpu->arch.ctxt;
-
-		isb();
-		/*
-		 * At this stage, and thanks to the above isb(), S2 is
-		 * configured and enabled. We can now restore the guest's S1
-		 * configuration: SCTLR, and only then TCR.
-		 */
-		write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1],	SYS_SCTLR);
-		isb();
-		write_sysreg_el1(ctxt->sys_regs[TCR_EL1],	SYS_TCR);
-	}
-}
-
-static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu)
-{
-	u64 hcr = vcpu->arch.hcr_el2;
-
-	if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM))
-		hcr |= HCR_TVM;
-
-	write_sysreg(hcr, hcr_el2);
-
-	if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN) && (hcr & HCR_VSE))
-		write_sysreg_s(vcpu->arch.vsesr_el2, SYS_VSESR_EL2);
-
-	if (has_vhe())
-		activate_traps_vhe(vcpu);
-	else
-		__activate_traps_nvhe(vcpu);
-}
-
-static void deactivate_traps_vhe(void)
-{
-	extern char vectors[];	/* kernel exception vectors */
-	write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2);
-
-	/*
-	 * ARM errata 1165522 and 1530923 require the actual execution of the
-	 * above before we can switch to the EL2/EL0 translation regime used by
-	 * the host.
-	 */
-	asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT));
-
-	write_sysreg(CPACR_EL1_DEFAULT, cpacr_el1);
-	write_sysreg(vectors, vbar_el1);
-}
-NOKPROBE_SYMBOL(deactivate_traps_vhe);
-
-static void __hyp_text __deactivate_traps_nvhe(void)
-{
-	u64 mdcr_el2 = read_sysreg(mdcr_el2);
-
-	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
-		u64 val;
-
-		/*
-		 * Set the TCR and SCTLR registers in the exact opposite
-		 * sequence as __activate_traps_nvhe (first prevent walks,
-		 * then force the MMU on). A generous sprinkling of isb()
-		 * ensure that things happen in this exact order.
-		 */
-		val = read_sysreg_el1(SYS_TCR);
-		write_sysreg_el1(val | TCR_EPD1_MASK | TCR_EPD0_MASK, SYS_TCR);
-		isb();
-		val = read_sysreg_el1(SYS_SCTLR);
-		write_sysreg_el1(val | SCTLR_ELx_M, SYS_SCTLR);
-		isb();
-	}
-
-	__deactivate_traps_common();
-
-	mdcr_el2 &= MDCR_EL2_HPMN_MASK;
-	mdcr_el2 |= MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT;
-
-	write_sysreg(mdcr_el2, mdcr_el2);
-	write_sysreg(HCR_HOST_NVHE_FLAGS, hcr_el2);
-	write_sysreg(CPTR_EL2_DEFAULT, cptr_el2);
-}
-
-static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu)
-{
-	/*
-	 * If we pended a virtual abort, preserve it until it gets
-	 * cleared. See D1.14.3 (Virtual Interrupts) for details, but
-	 * the crucial bit is "On taking a vSError interrupt,
-	 * HCR_EL2.VSE is cleared to 0."
-	 */
-	if (vcpu->arch.hcr_el2 & HCR_VSE) {
-		vcpu->arch.hcr_el2 &= ~HCR_VSE;
-		vcpu->arch.hcr_el2 |= read_sysreg(hcr_el2) & HCR_VSE;
-	}
-
-	if (has_vhe())
-		deactivate_traps_vhe();
-	else
-		__deactivate_traps_nvhe();
-}
-
-void activate_traps_vhe_load(struct kvm_vcpu *vcpu)
-{
-	__activate_traps_common(vcpu);
-}
-
-void deactivate_traps_vhe_put(void)
-{
-	u64 mdcr_el2 = read_sysreg(mdcr_el2);
-
-	mdcr_el2 &= MDCR_EL2_HPMN_MASK |
-		    MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT |
-		    MDCR_EL2_TPMS;
-
-	write_sysreg(mdcr_el2, mdcr_el2);
-
-	__deactivate_traps_common();
-}
-
-static void __hyp_text __activate_vm(struct kvm *kvm)
-{
-	__load_guest_stage2(kvm);
-}
-
-static void __hyp_text __deactivate_vm(struct kvm_vcpu *vcpu)
-{
-	write_sysreg(0, vttbr_el2);
-}
-
-/* Save VGICv3 state on non-VHE systems */
-static void __hyp_text __hyp_vgic_save_state(struct kvm_vcpu *vcpu)
-{
-	if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) {
-		__vgic_v3_save_state(&vcpu->arch.vgic_cpu.vgic_v3);
-		__vgic_v3_deactivate_traps(&vcpu->arch.vgic_cpu.vgic_v3);
-	}
-}
-
-/* Restore VGICv3 state on non_VEH systems */
-static void __hyp_text __hyp_vgic_restore_state(struct kvm_vcpu *vcpu)
-{
-	if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) {
-		__vgic_v3_activate_traps(&vcpu->arch.vgic_cpu.vgic_v3);
-		__vgic_v3_restore_state(&vcpu->arch.vgic_cpu.vgic_v3);
-	}
-}
-
-static bool __hyp_text __translate_far_to_hpfar(u64 far, u64 *hpfar)
-{
-	u64 par, tmp;
-
-	/*
-	 * Resolve the IPA the hard way using the guest VA.
-	 *
-	 * Stage-1 translation already validated the memory access
-	 * rights. As such, we can use the EL1 translation regime, and
-	 * don't have to distinguish between EL0 and EL1 access.
-	 *
-	 * We do need to save/restore PAR_EL1 though, as we haven't
-	 * saved the guest context yet, and we may return early...
-	 */
-	par = read_sysreg(par_el1);
-	asm volatile("at s1e1r, %0" : : "r" (far));
-	isb();
-
-	tmp = read_sysreg(par_el1);
-	write_sysreg(par, par_el1);
-
-	if (unlikely(tmp & SYS_PAR_EL1_F))
-		return false; /* Translation failed, back to guest */
-
-	/* Convert PAR to HPFAR format */
-	*hpfar = PAR_TO_HPFAR(tmp);
-	return true;
-}
-
-static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu)
-{
-	u8 ec;
-	u64 esr;
-	u64 hpfar, far;
-
-	esr = vcpu->arch.fault.esr_el2;
-	ec = ESR_ELx_EC(esr);
-
-	if (ec != ESR_ELx_EC_DABT_LOW && ec != ESR_ELx_EC_IABT_LOW)
-		return true;
-
-	far = read_sysreg_el2(SYS_FAR);
-
-	/*
-	 * The HPFAR can be invalid if the stage 2 fault did not
-	 * happen during a stage 1 page table walk (the ESR_EL2.S1PTW
-	 * bit is clear) and one of the two following cases are true:
-	 *   1. The fault was due to a permission fault
-	 *   2. The processor carries errata 834220
-	 *
-	 * Therefore, for all non S1PTW faults where we either have a
-	 * permission fault or the errata workaround is enabled, we
-	 * resolve the IPA using the AT instruction.
-	 */
-	if (!(esr & ESR_ELx_S1PTW) &&
-	    (cpus_have_final_cap(ARM64_WORKAROUND_834220) ||
-	     (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) {
-		if (!__translate_far_to_hpfar(far, &hpfar))
-			return false;
-	} else {
-		hpfar = read_sysreg(hpfar_el2);
-	}
-
-	vcpu->arch.fault.far_el2 = far;
-	vcpu->arch.fault.hpfar_el2 = hpfar;
-	return true;
-}
-
-/* Check for an FPSIMD/SVE trap and handle as appropriate */
-static bool __hyp_text __hyp_handle_fpsimd(struct kvm_vcpu *vcpu)
-{
-	bool vhe, sve_guest, sve_host;
-	u8 hsr_ec;
-
-	if (!system_supports_fpsimd())
-		return false;
-
-	if (system_supports_sve()) {
-		sve_guest = vcpu_has_sve(vcpu);
-		sve_host = vcpu->arch.flags & KVM_ARM64_HOST_SVE_IN_USE;
-		vhe = true;
-	} else {
-		sve_guest = false;
-		sve_host = false;
-		vhe = has_vhe();
-	}
-
-	hsr_ec = kvm_vcpu_trap_get_class(vcpu);
-	if (hsr_ec != ESR_ELx_EC_FP_ASIMD &&
-	    hsr_ec != ESR_ELx_EC_SVE)
-		return false;
-
-	/* Don't handle SVE traps for non-SVE vcpus here: */
-	if (!sve_guest)
-		if (hsr_ec != ESR_ELx_EC_FP_ASIMD)
-			return false;
-
-	/* Valid trap.  Switch the context: */
-
-	if (vhe) {
-		u64 reg = read_sysreg(cpacr_el1) | CPACR_EL1_FPEN;
-
-		if (sve_guest)
-			reg |= CPACR_EL1_ZEN;
-
-		write_sysreg(reg, cpacr_el1);
-	} else {
-		write_sysreg(read_sysreg(cptr_el2) & ~(u64)CPTR_EL2_TFP,
-			     cptr_el2);
-	}
-
-	isb();
-
-	if (vcpu->arch.flags & KVM_ARM64_FP_HOST) {
-		/*
-		 * In the SVE case, VHE is assumed: it is enforced by
-		 * Kconfig and kvm_arch_init().
-		 */
-		if (sve_host) {
-			struct thread_struct *thread = container_of(
-				vcpu->arch.host_fpsimd_state,
-				struct thread_struct, uw.fpsimd_state);
-
-			sve_save_state(sve_pffr(thread),
-				       &vcpu->arch.host_fpsimd_state->fpsr);
-		} else {
-			__fpsimd_save_state(vcpu->arch.host_fpsimd_state);
-		}
-
-		vcpu->arch.flags &= ~KVM_ARM64_FP_HOST;
-	}
-
-	if (sve_guest) {
-		sve_load_state(vcpu_sve_pffr(vcpu),
-			       &vcpu->arch.ctxt.gp_regs.fp_regs.fpsr,
-			       sve_vq_from_vl(vcpu->arch.sve_max_vl) - 1);
-		write_sysreg_s(vcpu->arch.ctxt.sys_regs[ZCR_EL1], SYS_ZCR_EL12);
-	} else {
-		__fpsimd_restore_state(&vcpu->arch.ctxt.gp_regs.fp_regs);
-	}
-
-	/* Skip restoring fpexc32 for AArch64 guests */
-	if (!(read_sysreg(hcr_el2) & HCR_RW))
-		write_sysreg(vcpu->arch.ctxt.sys_regs[FPEXC32_EL2],
-			     fpexc32_el2);
-
-	vcpu->arch.flags |= KVM_ARM64_FP_ENABLED;
-
-	return true;
-}
-
-static bool __hyp_text handle_tx2_tvm(struct kvm_vcpu *vcpu)
-{
-	u32 sysreg = esr_sys64_to_sysreg(kvm_vcpu_get_hsr(vcpu));
-	int rt = kvm_vcpu_sys_get_rt(vcpu);
-	u64 val = vcpu_get_reg(vcpu, rt);
-
-	/*
-	 * The normal sysreg handling code expects to see the traps,
-	 * let's not do anything here.
-	 */
-	if (vcpu->arch.hcr_el2 & HCR_TVM)
-		return false;
-
-	switch (sysreg) {
-	case SYS_SCTLR_EL1:
-		write_sysreg_el1(val, SYS_SCTLR);
-		break;
-	case SYS_TTBR0_EL1:
-		write_sysreg_el1(val, SYS_TTBR0);
-		break;
-	case SYS_TTBR1_EL1:
-		write_sysreg_el1(val, SYS_TTBR1);
-		break;
-	case SYS_TCR_EL1:
-		write_sysreg_el1(val, SYS_TCR);
-		break;
-	case SYS_ESR_EL1:
-		write_sysreg_el1(val, SYS_ESR);
-		break;
-	case SYS_FAR_EL1:
-		write_sysreg_el1(val, SYS_FAR);
-		break;
-	case SYS_AFSR0_EL1:
-		write_sysreg_el1(val, SYS_AFSR0);
-		break;
-	case SYS_AFSR1_EL1:
-		write_sysreg_el1(val, SYS_AFSR1);
-		break;
-	case SYS_MAIR_EL1:
-		write_sysreg_el1(val, SYS_MAIR);
-		break;
-	case SYS_AMAIR_EL1:
-		write_sysreg_el1(val, SYS_AMAIR);
-		break;
-	case SYS_CONTEXTIDR_EL1:
-		write_sysreg_el1(val, SYS_CONTEXTIDR);
-		break;
-	default:
-		return false;
-	}
-
-	__kvm_skip_instr(vcpu);
-	return true;
-}
-
-static bool __hyp_text esr_is_ptrauth_trap(u32 esr)
-{
-	u32 ec = ESR_ELx_EC(esr);
-
-	if (ec == ESR_ELx_EC_PAC)
-		return true;
-
-	if (ec != ESR_ELx_EC_SYS64)
-		return false;
-
-	switch (esr_sys64_to_sysreg(esr)) {
-	case SYS_APIAKEYLO_EL1:
-	case SYS_APIAKEYHI_EL1:
-	case SYS_APIBKEYLO_EL1:
-	case SYS_APIBKEYHI_EL1:
-	case SYS_APDAKEYLO_EL1:
-	case SYS_APDAKEYHI_EL1:
-	case SYS_APDBKEYLO_EL1:
-	case SYS_APDBKEYHI_EL1:
-	case SYS_APGAKEYLO_EL1:
-	case SYS_APGAKEYHI_EL1:
-		return true;
-	}
-
-	return false;
-}
-
-#define __ptrauth_save_key(regs, key)						\
-({										\
-	regs[key ## KEYLO_EL1] = read_sysreg_s(SYS_ ## key ## KEYLO_EL1);	\
-	regs[key ## KEYHI_EL1] = read_sysreg_s(SYS_ ## key ## KEYHI_EL1);	\
-})
-
-static bool __hyp_text __hyp_handle_ptrauth(struct kvm_vcpu *vcpu)
-{
-	struct kvm_cpu_context *ctxt;
-	u64 val;
-
-	if (!vcpu_has_ptrauth(vcpu) ||
-	    !esr_is_ptrauth_trap(kvm_vcpu_get_hsr(vcpu)))
-		return false;
-
-	ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
-	__ptrauth_save_key(ctxt->sys_regs, APIA);
-	__ptrauth_save_key(ctxt->sys_regs, APIB);
-	__ptrauth_save_key(ctxt->sys_regs, APDA);
-	__ptrauth_save_key(ctxt->sys_regs, APDB);
-	__ptrauth_save_key(ctxt->sys_regs, APGA);
-
-	vcpu_ptrauth_enable(vcpu);
-
-	val = read_sysreg(hcr_el2);
-	val |= (HCR_API | HCR_APK);
-	write_sysreg(val, hcr_el2);
-
-	return true;
-}
-
-/*
- * Return true when we were able to fixup the guest exit and should return to
- * the guest, false when we should restore the host state and return to the
- * main run loop.
- */
-static bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
-{
-	if (ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ)
-		vcpu->arch.fault.esr_el2 = read_sysreg_el2(SYS_ESR);
-
-	/*
-	 * We're using the raw exception code in order to only process
-	 * the trap if no SError is pending. We will come back to the
-	 * same PC once the SError has been injected, and replay the
-	 * trapping instruction.
-	 */
-	if (*exit_code != ARM_EXCEPTION_TRAP)
-		goto exit;
-
-	if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM) &&
-	    kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 &&
-	    handle_tx2_tvm(vcpu))
-		return true;
-
-	/*
-	 * We trap the first access to the FP/SIMD to save the host context
-	 * and restore the guest context lazily.
-	 * If FP/SIMD is not implemented, handle the trap and inject an
-	 * undefined instruction exception to the guest.
-	 * Similarly for trapped SVE accesses.
-	 */
-	if (__hyp_handle_fpsimd(vcpu))
-		return true;
-
-	if (__hyp_handle_ptrauth(vcpu))
-		return true;
-
-	if (!__populate_fault_info(vcpu))
-		return true;
-
-	if (static_branch_unlikely(&vgic_v2_cpuif_trap)) {
-		bool valid;
-
-		valid = kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_DABT_LOW &&
-			kvm_vcpu_trap_get_fault_type(vcpu) == FSC_FAULT &&
-			kvm_vcpu_dabt_isvalid(vcpu) &&
-			!kvm_vcpu_dabt_isextabt(vcpu) &&
-			!kvm_vcpu_dabt_iss1tw(vcpu);
-
-		if (valid) {
-			int ret = __vgic_v2_perform_cpuif_access(vcpu);
-
-			if (ret == 1)
-				return true;
-
-			/* Promote an illegal access to an SError.*/
-			if (ret == -1)
-				*exit_code = ARM_EXCEPTION_EL1_SERROR;
-
-			goto exit;
-		}
-	}
-
-	if (static_branch_unlikely(&vgic_v3_cpuif_trap) &&
-	    (kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 ||
-	     kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_CP15_32)) {
-		int ret = __vgic_v3_perform_cpuif_access(vcpu);
-
-		if (ret == 1)
-			return true;
-	}
-
-exit:
-	/* Return to the host kernel and handle the exit */
-	return false;
-}
-
-static inline bool __hyp_text __needs_ssbd_off(struct kvm_vcpu *vcpu)
-{
-	if (!cpus_have_final_cap(ARM64_SSBD))
-		return false;
-
-	return !(vcpu->arch.workaround_flags & VCPU_WORKAROUND_2_FLAG);
-}
-
-static void __hyp_text __set_guest_arch_workaround_state(struct kvm_vcpu *vcpu)
-{
-#ifdef CONFIG_ARM64_SSBD
-	/*
-	 * The host runs with the workaround always present. If the
-	 * guest wants it disabled, so be it...
-	 */
-	if (__needs_ssbd_off(vcpu) &&
-	    __hyp_this_cpu_read(arm64_ssbd_callback_required))
-		arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_2, 0, NULL);
-#endif
-}
-
-static void __hyp_text __set_host_arch_workaround_state(struct kvm_vcpu *vcpu)
-{
-#ifdef CONFIG_ARM64_SSBD
-	/*
-	 * If the guest has disabled the workaround, bring it back on.
-	 */
-	if (__needs_ssbd_off(vcpu) &&
-	    __hyp_this_cpu_read(arm64_ssbd_callback_required))
-		arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_2, 1, NULL);
-#endif
-}
-
-/**
- * Disable host events, enable guest events
- */
-static bool __hyp_text __pmu_switch_to_guest(struct kvm_cpu_context *host_ctxt)
-{
-	struct kvm_host_data *host;
-	struct kvm_pmu_events *pmu;
-
-	host = container_of(host_ctxt, struct kvm_host_data, host_ctxt);
-	pmu = &host->pmu_events;
-
-	if (pmu->events_host)
-		write_sysreg(pmu->events_host, pmcntenclr_el0);
-
-	if (pmu->events_guest)
-		write_sysreg(pmu->events_guest, pmcntenset_el0);
-
-	return (pmu->events_host || pmu->events_guest);
-}
-
-/**
- * Disable guest events, enable host events
- */
-static void __hyp_text __pmu_switch_to_host(struct kvm_cpu_context *host_ctxt)
-{
-	struct kvm_host_data *host;
-	struct kvm_pmu_events *pmu;
-
-	host = container_of(host_ctxt, struct kvm_host_data, host_ctxt);
-	pmu = &host->pmu_events;
-
-	if (pmu->events_guest)
-		write_sysreg(pmu->events_guest, pmcntenclr_el0);
-
-	if (pmu->events_host)
-		write_sysreg(pmu->events_host, pmcntenset_el0);
-}
-
-/* Switch to the guest for VHE systems running in EL2 */
-static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
-{
-	struct kvm_cpu_context *host_ctxt;
-	struct kvm_cpu_context *guest_ctxt;
-	u64 exit_code;
-
-	host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
-	host_ctxt->__hyp_running_vcpu = vcpu;
-	guest_ctxt = &vcpu->arch.ctxt;
-
-	sysreg_save_host_state_vhe(host_ctxt);
-
-	/*
-	 * ARM erratum 1165522 requires us to configure both stage 1 and
-	 * stage 2 translation for the guest context before we clear
-	 * HCR_EL2.TGE.
-	 *
-	 * We have already configured the guest's stage 1 translation in
-	 * kvm_vcpu_load_sysregs above.  We must now call __activate_vm
-	 * before __activate_traps, because __activate_vm configures
-	 * stage 2 translation, and __activate_traps clear HCR_EL2.TGE
-	 * (among other things).
-	 */
-	__activate_vm(vcpu->kvm);
-	__activate_traps(vcpu);
-
-	sysreg_restore_guest_state_vhe(guest_ctxt);
-	__debug_switch_to_guest(vcpu);
-
-	__set_guest_arch_workaround_state(vcpu);
-
-	do {
-		/* Jump in the fire! */
-		exit_code = __guest_enter(vcpu, host_ctxt);
-
-		/* And we're baaack! */
-	} while (fixup_guest_exit(vcpu, &exit_code));
-
-	__set_host_arch_workaround_state(vcpu);
-
-	sysreg_save_guest_state_vhe(guest_ctxt);
-
-	__deactivate_traps(vcpu);
-
-	sysreg_restore_host_state_vhe(host_ctxt);
-
-	if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED)
-		__fpsimd_save_fpexc32(vcpu);
-
-	__debug_switch_to_host(vcpu);
-
-	return exit_code;
-}
-NOKPROBE_SYMBOL(__kvm_vcpu_run_vhe);
-
-int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
-{
-	int ret;
-
-	local_daif_mask();
-
-	/*
-	 * Having IRQs masked via PMR when entering the guest means the GIC
-	 * will not signal the CPU of interrupts of lower priority, and the
-	 * only way to get out will be via guest exceptions.
-	 * Naturally, we want to avoid this.
-	 *
-	 * local_daif_mask() already sets GIC_PRIO_PSR_I_SET, we just need a
-	 * dsb to ensure the redistributor is forwards EL2 IRQs to the CPU.
-	 */
-	pmr_sync();
-
-	ret = __kvm_vcpu_run_vhe(vcpu);
-
-	/*
-	 * local_daif_restore() takes care to properly restore PSTATE.DAIF
-	 * and the GIC PMR if the host is using IRQ priorities.
-	 */
-	local_daif_restore(DAIF_PROCCTX_NOIRQ);
-
-	/*
-	 * When we exit from the guest we change a number of CPU configuration
-	 * parameters, such as traps.  Make sure these changes take effect
-	 * before running the host or additional guests.
-	 */
-	isb();
-
-	return ret;
-}
-
-/* Switch to the guest for legacy non-VHE systems */
-int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu)
-{
-	struct kvm_cpu_context *host_ctxt;
-	struct kvm_cpu_context *guest_ctxt;
-	bool pmu_switch_needed;
-	u64 exit_code;
-
-	/*
-	 * Having IRQs masked via PMR when entering the guest means the GIC
-	 * will not signal the CPU of interrupts of lower priority, and the
-	 * only way to get out will be via guest exceptions.
-	 * Naturally, we want to avoid this.
-	 */
-	if (system_uses_irq_prio_masking()) {
-		gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
-		pmr_sync();
-	}
-
-	vcpu = kern_hyp_va(vcpu);
-
-	host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
-	host_ctxt->__hyp_running_vcpu = vcpu;
-	guest_ctxt = &vcpu->arch.ctxt;
-
-	pmu_switch_needed = __pmu_switch_to_guest(host_ctxt);
-
-	__sysreg_save_state_nvhe(host_ctxt);
-
-	/*
-	 * We must restore the 32-bit state before the sysregs, thanks
-	 * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72).
-	 *
-	 * Also, and in order to be able to deal with erratum #1319537 (A57)
-	 * and #1319367 (A72), we must ensure that all VM-related sysreg are
-	 * restored before we enable S2 translation.
-	 */
-	__sysreg32_restore_state(vcpu);
-	__sysreg_restore_state_nvhe(guest_ctxt);
-
-	__activate_vm(kern_hyp_va(vcpu->kvm));
-	__activate_traps(vcpu);
-
-	__hyp_vgic_restore_state(vcpu);
-	__timer_enable_traps(vcpu);
-
-	__debug_switch_to_guest(vcpu);
-
-	__set_guest_arch_workaround_state(vcpu);
-
-	do {
-		/* Jump in the fire! */
-		exit_code = __guest_enter(vcpu, host_ctxt);
-
-		/* And we're baaack! */
-	} while (fixup_guest_exit(vcpu, &exit_code));
-
-	__set_host_arch_workaround_state(vcpu);
-
-	__sysreg_save_state_nvhe(guest_ctxt);
-	__sysreg32_save_state(vcpu);
-	__timer_disable_traps(vcpu);
-	__hyp_vgic_save_state(vcpu);
-
-	__deactivate_traps(vcpu);
-	__deactivate_vm(vcpu);
-
-	__sysreg_restore_state_nvhe(host_ctxt);
-
-	if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED)
-		__fpsimd_save_fpexc32(vcpu);
-
-	/*
-	 * This must come after restoring the host sysregs, since a non-VHE
-	 * system may enable SPE here and make use of the TTBRs.
-	 */
-	__debug_switch_to_host(vcpu);
-
-	if (pmu_switch_needed)
-		__pmu_switch_to_host(host_ctxt);
-
-	/* Returning to host will clear PSR.I, remask PMR if needed */
-	if (system_uses_irq_prio_masking())
-		gic_write_pmr(GIC_PRIO_IRQOFF);
-
-	return exit_code;
-}
-
-static const char __hyp_panic_string[] = "HYP panic:\nPS:%08llx PC:%016llx ESR:%08llx\nFAR:%016llx HPFAR:%016llx PAR:%016llx\nVCPU:%p\n";
-
-static void __hyp_text __hyp_call_panic_nvhe(u64 spsr, u64 elr, u64 par,
-					     struct kvm_cpu_context *__host_ctxt)
-{
-	struct kvm_vcpu *vcpu;
-	unsigned long str_va;
-
-	vcpu = __host_ctxt->__hyp_running_vcpu;
-
-	if (read_sysreg(vttbr_el2)) {
-		__timer_disable_traps(vcpu);
-		__deactivate_traps(vcpu);
-		__deactivate_vm(vcpu);
-		__sysreg_restore_state_nvhe(__host_ctxt);
-	}
-
-	/*
-	 * Force the panic string to be loaded from the literal pool,
-	 * making sure it is a kernel address and not a PC-relative
-	 * reference.
-	 */
-	asm volatile("ldr %0, =%1" : "=r" (str_va) : "S" (__hyp_panic_string));
-
-	__hyp_do_panic(str_va,
-		       spsr, elr,
-		       read_sysreg(esr_el2), read_sysreg_el2(SYS_FAR),
-		       read_sysreg(hpfar_el2), par, vcpu);
-}
-
-static void __hyp_call_panic_vhe(u64 spsr, u64 elr, u64 par,
-				 struct kvm_cpu_context *host_ctxt)
-{
-	struct kvm_vcpu *vcpu;
-	vcpu = host_ctxt->__hyp_running_vcpu;
-
-	__deactivate_traps(vcpu);
-	sysreg_restore_host_state_vhe(host_ctxt);
-
-	panic(__hyp_panic_string,
-	      spsr,  elr,
-	      read_sysreg_el2(SYS_ESR),   read_sysreg_el2(SYS_FAR),
-	      read_sysreg(hpfar_el2), par, vcpu);
-}
-NOKPROBE_SYMBOL(__hyp_call_panic_vhe);
-
-void __hyp_text __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt)
-{
-	u64 spsr = read_sysreg_el2(SYS_SPSR);
-	u64 elr = read_sysreg_el2(SYS_ELR);
-	u64 par = read_sysreg(par_el1);
-
-	if (!has_vhe())
-		__hyp_call_panic_nvhe(spsr, elr, par, host_ctxt);
-	else
-		__hyp_call_panic_vhe(spsr, elr, par, host_ctxt);
-
-	unreachable();
-}
diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c
index cc7e957f5b2c..2493439a5c54 100644
--- a/arch/arm64/kvm/hyp/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/sysreg-sr.c
@@ -114,7 +114,7 @@ static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
 		/*
 		 * Must only be done for guest registers, hence the context
 		 * test. We're coming from the host, so SCTLR.M is already
-		 * set. Pairs with __activate_traps_nvhe().
+		 * set. Pairs with nVHE's __activate_traps().
 		 */
 		write_sysreg_el1((ctxt->sys_regs[TCR_EL1] |
 				  TCR_EPD1_MASK | TCR_EPD0_MASK),
@@ -142,7 +142,7 @@ static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
 	    ctxt->__hyp_running_vcpu) {
 		/*
 		 * Must only be done for host registers, hence the context
-		 * test. Pairs with __deactivate_traps_nvhe().
+		 * test. Pairs with nVHE's __deactivate_traps().
 		 */
 		isb();
 		/*
diff --git a/arch/arm64/kvm/hyp/vhe/Makefile b/arch/arm64/kvm/hyp/vhe/Makefile
index 704140fc5d66..9f71cd3ba50d 100644
--- a/arch/arm64/kvm/hyp/vhe/Makefile
+++ b/arch/arm64/kvm/hyp/vhe/Makefile
@@ -6,7 +6,7 @@
 asflags-y := -D__KVM_VHE_HYPERVISOR__
 ccflags-y := -D__KVM_VHE_HYPERVISOR__
 
-obj-y := tlb.o ../hyp-entry.o
+obj-y := switch.o tlb.o ../hyp-entry.o
 
 # KVM code is run at a different exception code with a different map, so
 # compiler instrumentation that inserts callbacks or checks into the code may
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
new file mode 100644
index 000000000000..e8d76cab44e4
--- /dev/null
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -0,0 +1,219 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#include <hyp/switch.h>
+
+#include <linux/arm-smccc.h>
+#include <linux/kvm_host.h>
+#include <linux/types.h>
+#include <linux/jump_label.h>
+#include <uapi/linux/psci.h>
+
+#include <kvm/arm_psci.h>
+
+#include <asm/barrier.h>
+#include <asm/cpufeature.h>
+#include <asm/kprobes.h>
+#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>
+#include <asm/processor.h>
+#include <asm/thread_info.h>
+
+const char __hyp_panic_string[] = "HYP panic:\nPS:%08llx PC:%016llx ESR:%08llx\nFAR:%016llx HPFAR:%016llx PAR:%016llx\nVCPU:%p\n";
+
+static void __activate_traps(struct kvm_vcpu *vcpu)
+{
+	u64 val;
+
+	___activate_traps(vcpu);
+
+	val = read_sysreg(cpacr_el1);
+	val |= CPACR_EL1_TTA;
+	val &= ~CPACR_EL1_ZEN;
+
+	/*
+	 * With VHE (HCR.E2H == 1), accesses to CPACR_EL1 are routed to
+	 * CPTR_EL2. In general, CPACR_EL1 has the same layout as CPTR_EL2,
+	 * except for some missing controls, such as TAM.
+	 * In this case, CPTR_EL2.TAM has the same position with or without
+	 * VHE (HCR.E2H == 1) which allows us to use here the CPTR_EL2.TAM
+	 * shift value for trapping the AMU accesses.
+	 */
+
+	val |= CPTR_EL2_TAM;
+
+	if (update_fp_enabled(vcpu)) {
+		if (vcpu_has_sve(vcpu))
+			val |= CPACR_EL1_ZEN;
+	} else {
+		val &= ~CPACR_EL1_FPEN;
+		__activate_traps_fpsimd32(vcpu);
+	}
+
+	write_sysreg(val, cpacr_el1);
+
+	write_sysreg(kvm_get_hyp_vector(), vbar_el1);
+}
+NOKPROBE_SYMBOL(__activate_traps);
+
+static void __deactivate_traps(struct kvm_vcpu *vcpu)
+{
+	extern char vectors[];	/* kernel exception vectors */
+
+	___deactivate_traps(vcpu);
+
+	write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2);
+
+	/*
+	 * ARM errata 1165522 and 1530923 require the actual execution of the
+	 * above before we can switch to the EL2/EL0 translation regime used by
+	 * the host.
+	 */
+	asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT));
+
+	write_sysreg(CPACR_EL1_DEFAULT, cpacr_el1);
+	write_sysreg(vectors, vbar_el1);
+}
+NOKPROBE_SYMBOL(__deactivate_traps);
+
+void activate_traps_vhe_load(struct kvm_vcpu *vcpu)
+{
+	__activate_traps_common(vcpu);
+}
+
+void deactivate_traps_vhe_put(void)
+{
+	u64 mdcr_el2 = read_sysreg(mdcr_el2);
+
+	mdcr_el2 &= MDCR_EL2_HPMN_MASK |
+		    MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT |
+		    MDCR_EL2_TPMS;
+
+	write_sysreg(mdcr_el2, mdcr_el2);
+
+	__deactivate_traps_common();
+}
+
+/* Switch to the guest for VHE systems running in EL2 */
+static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpu_context *host_ctxt;
+	struct kvm_cpu_context *guest_ctxt;
+	u64 exit_code;
+
+	host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
+	host_ctxt->__hyp_running_vcpu = vcpu;
+	guest_ctxt = &vcpu->arch.ctxt;
+
+	sysreg_save_host_state_vhe(host_ctxt);
+
+	/*
+	 * ARM erratum 1165522 requires us to configure both stage 1 and
+	 * stage 2 translation for the guest context before we clear
+	 * HCR_EL2.TGE.
+	 *
+	 * We have already configured the guest's stage 1 translation in
+	 * kvm_vcpu_load_sysregs above.  We must now call __activate_vm
+	 * before __activate_traps, because __activate_vm configures
+	 * stage 2 translation, and __activate_traps clear HCR_EL2.TGE
+	 * (among other things).
+	 */
+	__activate_vm(vcpu->kvm);
+	__activate_traps(vcpu);
+
+	sysreg_restore_guest_state_vhe(guest_ctxt);
+	__debug_switch_to_guest(vcpu);
+
+	__set_guest_arch_workaround_state(vcpu);
+
+	do {
+		/* Jump in the fire! */
+		exit_code = __guest_enter(vcpu, host_ctxt);
+
+		/* And we're baaack! */
+	} while (fixup_guest_exit(vcpu, &exit_code));
+
+	__set_host_arch_workaround_state(vcpu);
+
+	sysreg_save_guest_state_vhe(guest_ctxt);
+
+	__deactivate_traps(vcpu);
+
+	sysreg_restore_host_state_vhe(host_ctxt);
+
+	if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED)
+		__fpsimd_save_fpexc32(vcpu);
+
+	__debug_switch_to_host(vcpu);
+
+	return exit_code;
+}
+NOKPROBE_SYMBOL(__kvm_vcpu_run_vhe);
+
+int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
+{
+	int ret;
+
+	local_daif_mask();
+
+	/*
+	 * Having IRQs masked via PMR when entering the guest means the GIC
+	 * will not signal the CPU of interrupts of lower priority, and the
+	 * only way to get out will be via guest exceptions.
+	 * Naturally, we want to avoid this.
+	 *
+	 * local_daif_mask() already sets GIC_PRIO_PSR_I_SET, we just need a
+	 * dsb to ensure the redistributor is forwards EL2 IRQs to the CPU.
+	 */
+	pmr_sync();
+
+	ret = __kvm_vcpu_run_vhe(vcpu);
+
+	/*
+	 * local_daif_restore() takes care to properly restore PSTATE.DAIF
+	 * and the GIC PMR if the host is using IRQ priorities.
+	 */
+	local_daif_restore(DAIF_PROCCTX_NOIRQ);
+
+	/*
+	 * When we exit from the guest we change a number of CPU configuration
+	 * parameters, such as traps.  Make sure these changes take effect
+	 * before running the host or additional guests.
+	 */
+	isb();
+
+	return ret;
+}
+
+static void __hyp_call_panic(u64 spsr, u64 elr, u64 par,
+			     struct kvm_cpu_context *host_ctxt)
+{
+	struct kvm_vcpu *vcpu;
+	vcpu = host_ctxt->__hyp_running_vcpu;
+
+	__deactivate_traps(vcpu);
+	sysreg_restore_host_state_vhe(host_ctxt);
+
+	panic(__hyp_panic_string,
+	      spsr, elr,
+	      read_sysreg_el2(SYS_ESR), read_sysreg_el2(SYS_FAR),
+	      read_sysreg(hpfar_el2), par, vcpu);
+}
+NOKPROBE_SYMBOL(__hyp_call_panic);
+
+void __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt)
+{
+	u64 spsr = read_sysreg_el2(SYS_SPSR);
+	u64 elr = read_sysreg_el2(SYS_ELR);
+	u64 par = read_sysreg(par_el1);
+
+	__hyp_call_panic(spsr, elr, par, host_ctxt);
+	unreachable();
+}
-- 
cgit 


From d400c5b2025c9aeca76213d6bd4138ec39da5cef Mon Sep 17 00:00:00 2001
From: David Brazdil <dbrazdil@google.com>
Date: Thu, 25 Jun 2020 14:14:15 +0100
Subject: KVM: arm64: Split hyp/debug-sr.c to VHE/nVHE

debug-sr.c contains KVM's code for context-switching debug registers, with some
code shared between VHE/nVHE. These common routines are moved to a header file,
VHE-specific code is moved to vhe/debug-sr.c and nVHE-specific code to
nvhe/debug-sr.c.

Functions are slightly refactored to move code hidden behind `has_vhe()` checks
to the corresponding .c files.

Signed-off-by: David Brazdil <dbrazdil@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200625131420.71444-11-dbrazdil@google.com
---
 arch/arm64/kernel/image-vars.h            |   5 -
 arch/arm64/kvm/hyp/Makefile               |   2 +-
 arch/arm64/kvm/hyp/debug-sr.c             | 224 ------------------------------
 arch/arm64/kvm/hyp/include/hyp/debug-sr.h | 170 +++++++++++++++++++++++
 arch/arm64/kvm/hyp/nvhe/Makefile          |   2 +-
 arch/arm64/kvm/hyp/nvhe/debug-sr.c        |  77 ++++++++++
 arch/arm64/kvm/hyp/vhe/Makefile           |   2 +-
 arch/arm64/kvm/hyp/vhe/debug-sr.c         |  26 ++++
 8 files changed, 276 insertions(+), 232 deletions(-)
 delete mode 100644 arch/arm64/kvm/hyp/debug-sr.c
 create mode 100644 arch/arm64/kvm/hyp/include/hyp/debug-sr.h
 create mode 100644 arch/arm64/kvm/hyp/nvhe/debug-sr.c
 create mode 100644 arch/arm64/kvm/hyp/vhe/debug-sr.c

diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index 06fe9833104a..c44ca4e7dd66 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -66,11 +66,6 @@ __efistub__ctype		= _ctype;
 /* Symbols defined in aarch32.c (not yet compiled with nVHE build rules). */
 KVM_NVHE_ALIAS(kvm_skip_instr32);
 
-/* Symbols defined in debug-sr.c (not yet compiled with nVHE build rules). */
-KVM_NVHE_ALIAS(__debug_switch_to_guest);
-KVM_NVHE_ALIAS(__debug_switch_to_host);
-KVM_NVHE_ALIAS(__kvm_get_mdcr_el2);
-
 /* Symbols defined in entry.S (not yet compiled with nVHE build rules). */
 KVM_NVHE_ALIAS(__guest_enter);
 KVM_NVHE_ALIAS(__guest_exit);
diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile
index 7462d3a8a6f2..fc09025d2e97 100644
--- a/arch/arm64/kvm/hyp/Makefile
+++ b/arch/arm64/kvm/hyp/Makefile
@@ -14,7 +14,7 @@ obj-$(CONFIG_KVM) += hyp.o vhe/ nvhe/
 obj-$(CONFIG_KVM_INDIRECT_VECTORS) += smccc_wa.o
 
 hyp-y := vgic-v3-sr.o timer-sr.o aarch32.o vgic-v2-cpuif-proxy.o sysreg-sr.o \
-	 debug-sr.o entry.o fpsimd.o
+	 entry.o fpsimd.o
 
 # KVM code is run at a different exception code with a different map, so
 # compiler instrumentation that inserts callbacks or checks into the code may
diff --git a/arch/arm64/kvm/hyp/debug-sr.c b/arch/arm64/kvm/hyp/debug-sr.c
deleted file mode 100644
index e95af204fec7..000000000000
--- a/arch/arm64/kvm/hyp/debug-sr.c
+++ /dev/null
@@ -1,224 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Copyright (C) 2015 - ARM Ltd
- * Author: Marc Zyngier <marc.zyngier@arm.com>
- */
-
-#include <linux/compiler.h>
-#include <linux/kvm_host.h>
-
-#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)
-
-#define save_debug(ptr,reg,nr)						\
-	switch (nr) {							\
-	case 15:	ptr[15] = read_debug(reg, 15);			\
-			/* Fall through */				\
-	case 14:	ptr[14] = read_debug(reg, 14);			\
-			/* Fall through */				\
-	case 13:	ptr[13] = read_debug(reg, 13);			\
-			/* Fall through */				\
-	case 12:	ptr[12] = read_debug(reg, 12);			\
-			/* Fall through */				\
-	case 11:	ptr[11] = read_debug(reg, 11);			\
-			/* Fall through */				\
-	case 10:	ptr[10] = read_debug(reg, 10);			\
-			/* Fall through */				\
-	case 9:		ptr[9] = read_debug(reg, 9);			\
-			/* Fall through */				\
-	case 8:		ptr[8] = read_debug(reg, 8);			\
-			/* Fall through */				\
-	case 7:		ptr[7] = read_debug(reg, 7);			\
-			/* Fall through */				\
-	case 6:		ptr[6] = read_debug(reg, 6);			\
-			/* Fall through */				\
-	case 5:		ptr[5] = read_debug(reg, 5);			\
-			/* Fall through */				\
-	case 4:		ptr[4] = read_debug(reg, 4);			\
-			/* Fall through */				\
-	case 3:		ptr[3] = read_debug(reg, 3);			\
-			/* Fall through */				\
-	case 2:		ptr[2] = read_debug(reg, 2);			\
-			/* Fall through */				\
-	case 1:		ptr[1] = read_debug(reg, 1);			\
-			/* Fall through */				\
-	default:	ptr[0] = read_debug(reg, 0);			\
-	}
-
-#define restore_debug(ptr,reg,nr)					\
-	switch (nr) {							\
-	case 15:	write_debug(ptr[15], reg, 15);			\
-			/* Fall through */				\
-	case 14:	write_debug(ptr[14], reg, 14);			\
-			/* Fall through */				\
-	case 13:	write_debug(ptr[13], reg, 13);			\
-			/* Fall through */				\
-	case 12:	write_debug(ptr[12], reg, 12);			\
-			/* Fall through */				\
-	case 11:	write_debug(ptr[11], reg, 11);			\
-			/* Fall through */				\
-	case 10:	write_debug(ptr[10], reg, 10);			\
-			/* Fall through */				\
-	case 9:		write_debug(ptr[9], reg, 9);			\
-			/* Fall through */				\
-	case 8:		write_debug(ptr[8], reg, 8);			\
-			/* Fall through */				\
-	case 7:		write_debug(ptr[7], reg, 7);			\
-			/* Fall through */				\
-	case 6:		write_debug(ptr[6], reg, 6);			\
-			/* Fall through */				\
-	case 5:		write_debug(ptr[5], reg, 5);			\
-			/* Fall through */				\
-	case 4:		write_debug(ptr[4], reg, 4);			\
-			/* Fall through */				\
-	case 3:		write_debug(ptr[3], reg, 3);			\
-			/* Fall through */				\
-	case 2:		write_debug(ptr[2], reg, 2);			\
-			/* Fall through */				\
-	case 1:		write_debug(ptr[1], reg, 1);			\
-			/* Fall through */				\
-	default:	write_debug(ptr[0], reg, 0);			\
-	}
-
-static void __hyp_text __debug_save_spe_nvhe(u64 *pmscr_el1)
-{
-	u64 reg;
-
-	/* Clear pmscr in case of early return */
-	*pmscr_el1 = 0;
-
-	/* SPE present on this CPU? */
-	if (!cpuid_feature_extract_unsigned_field(read_sysreg(id_aa64dfr0_el1),
-						  ID_AA64DFR0_PMSVER_SHIFT))
-		return;
-
-	/* Yes; is it owned by EL3? */
-	reg = read_sysreg_s(SYS_PMBIDR_EL1);
-	if (reg & BIT(SYS_PMBIDR_EL1_P_SHIFT))
-		return;
-
-	/* No; is the host actually using the thing? */
-	reg = read_sysreg_s(SYS_PMBLIMITR_EL1);
-	if (!(reg & BIT(SYS_PMBLIMITR_EL1_E_SHIFT)))
-		return;
-
-	/* Yes; save the control register and disable data generation */
-	*pmscr_el1 = read_sysreg_s(SYS_PMSCR_EL1);
-	write_sysreg_s(0, SYS_PMSCR_EL1);
-	isb();
-
-	/* Now drain all buffered data to memory */
-	psb_csync();
-	dsb(nsh);
-}
-
-static void __hyp_text __debug_restore_spe_nvhe(u64 pmscr_el1)
-{
-	if (!pmscr_el1)
-		return;
-
-	/* The host page table is installed, but not yet synchronised */
-	isb();
-
-	/* Re-enable data generation */
-	write_sysreg_s(pmscr_el1, SYS_PMSCR_EL1);
-}
-
-static void __hyp_text __debug_save_state(struct kvm_vcpu *vcpu,
-					  struct kvm_guest_debug_arch *dbg,
-					  struct kvm_cpu_context *ctxt)
-{
-	u64 aa64dfr0;
-	int brps, wrps;
-
-	aa64dfr0 = read_sysreg(id_aa64dfr0_el1);
-	brps = (aa64dfr0 >> 12) & 0xf;
-	wrps = (aa64dfr0 >> 20) & 0xf;
-
-	save_debug(dbg->dbg_bcr, dbgbcr, brps);
-	save_debug(dbg->dbg_bvr, dbgbvr, brps);
-	save_debug(dbg->dbg_wcr, dbgwcr, wrps);
-	save_debug(dbg->dbg_wvr, dbgwvr, wrps);
-
-	ctxt->sys_regs[MDCCINT_EL1] = read_sysreg(mdccint_el1);
-}
-
-static void __hyp_text __debug_restore_state(struct kvm_vcpu *vcpu,
-					     struct kvm_guest_debug_arch *dbg,
-					     struct kvm_cpu_context *ctxt)
-{
-	u64 aa64dfr0;
-	int brps, wrps;
-
-	aa64dfr0 = read_sysreg(id_aa64dfr0_el1);
-
-	brps = (aa64dfr0 >> 12) & 0xf;
-	wrps = (aa64dfr0 >> 20) & 0xf;
-
-	restore_debug(dbg->dbg_bcr, dbgbcr, brps);
-	restore_debug(dbg->dbg_bvr, dbgbvr, brps);
-	restore_debug(dbg->dbg_wcr, dbgwcr, wrps);
-	restore_debug(dbg->dbg_wvr, dbgwvr, wrps);
-
-	write_sysreg(ctxt->sys_regs[MDCCINT_EL1], mdccint_el1);
-}
-
-void __hyp_text __debug_switch_to_guest(struct kvm_vcpu *vcpu)
-{
-	struct kvm_cpu_context *host_ctxt;
-	struct kvm_cpu_context *guest_ctxt;
-	struct kvm_guest_debug_arch *host_dbg;
-	struct kvm_guest_debug_arch *guest_dbg;
-
-	/*
-	 * Non-VHE: Disable and flush SPE data generation
-	 * VHE: The vcpu can run, but it can't hide.
-	 */
-	if (!has_vhe())
-		__debug_save_spe_nvhe(&vcpu->arch.host_debug_state.pmscr_el1);
-
-	if (!(vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY))
-		return;
-
-	host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
-	guest_ctxt = &vcpu->arch.ctxt;
-	host_dbg = &vcpu->arch.host_debug_state.regs;
-	guest_dbg = kern_hyp_va(vcpu->arch.debug_ptr);
-
-	__debug_save_state(vcpu, host_dbg, host_ctxt);
-	__debug_restore_state(vcpu, guest_dbg, guest_ctxt);
-}
-
-void __hyp_text __debug_switch_to_host(struct kvm_vcpu *vcpu)
-{
-	struct kvm_cpu_context *host_ctxt;
-	struct kvm_cpu_context *guest_ctxt;
-	struct kvm_guest_debug_arch *host_dbg;
-	struct kvm_guest_debug_arch *guest_dbg;
-
-	if (!has_vhe())
-		__debug_restore_spe_nvhe(vcpu->arch.host_debug_state.pmscr_el1);
-
-	if (!(vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY))
-		return;
-
-	host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
-	guest_ctxt = &vcpu->arch.ctxt;
-	host_dbg = &vcpu->arch.host_debug_state.regs;
-	guest_dbg = kern_hyp_va(vcpu->arch.debug_ptr);
-
-	__debug_save_state(vcpu, guest_dbg, guest_ctxt);
-	__debug_restore_state(vcpu, host_dbg, host_ctxt);
-
-	vcpu->arch.flags &= ~KVM_ARM64_DEBUG_DIRTY;
-}
-
-u32 __hyp_text __kvm_get_mdcr_el2(void)
-{
-	return read_sysreg(mdcr_el2);
-}
diff --git a/arch/arm64/kvm/hyp/include/hyp/debug-sr.h b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
new file mode 100644
index 000000000000..e041dbd23243
--- /dev/null
+++ b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
@@ -0,0 +1,170 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#ifndef __ARM64_KVM_HYP_DEBUG_SR_H__
+#define __ARM64_KVM_HYP_DEBUG_SR_H__
+
+#include <linux/compiler.h>
+#include <linux/kvm_host.h>
+
+#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)
+
+#define save_debug(ptr,reg,nr)						\
+	switch (nr) {							\
+	case 15:	ptr[15] = read_debug(reg, 15);			\
+			/* Fall through */				\
+	case 14:	ptr[14] = read_debug(reg, 14);			\
+			/* Fall through */				\
+	case 13:	ptr[13] = read_debug(reg, 13);			\
+			/* Fall through */				\
+	case 12:	ptr[12] = read_debug(reg, 12);			\
+			/* Fall through */				\
+	case 11:	ptr[11] = read_debug(reg, 11);			\
+			/* Fall through */				\
+	case 10:	ptr[10] = read_debug(reg, 10);			\
+			/* Fall through */				\
+	case 9:		ptr[9] = read_debug(reg, 9);			\
+			/* Fall through */				\
+	case 8:		ptr[8] = read_debug(reg, 8);			\
+			/* Fall through */				\
+	case 7:		ptr[7] = read_debug(reg, 7);			\
+			/* Fall through */				\
+	case 6:		ptr[6] = read_debug(reg, 6);			\
+			/* Fall through */				\
+	case 5:		ptr[5] = read_debug(reg, 5);			\
+			/* Fall through */				\
+	case 4:		ptr[4] = read_debug(reg, 4);			\
+			/* Fall through */				\
+	case 3:		ptr[3] = read_debug(reg, 3);			\
+			/* Fall through */				\
+	case 2:		ptr[2] = read_debug(reg, 2);			\
+			/* Fall through */				\
+	case 1:		ptr[1] = read_debug(reg, 1);			\
+			/* Fall through */				\
+	default:	ptr[0] = read_debug(reg, 0);			\
+	}
+
+#define restore_debug(ptr,reg,nr)					\
+	switch (nr) {							\
+	case 15:	write_debug(ptr[15], reg, 15);			\
+			/* Fall through */				\
+	case 14:	write_debug(ptr[14], reg, 14);			\
+			/* Fall through */				\
+	case 13:	write_debug(ptr[13], reg, 13);			\
+			/* Fall through */				\
+	case 12:	write_debug(ptr[12], reg, 12);			\
+			/* Fall through */				\
+	case 11:	write_debug(ptr[11], reg, 11);			\
+			/* Fall through */				\
+	case 10:	write_debug(ptr[10], reg, 10);			\
+			/* Fall through */				\
+	case 9:		write_debug(ptr[9], reg, 9);			\
+			/* Fall through */				\
+	case 8:		write_debug(ptr[8], reg, 8);			\
+			/* Fall through */				\
+	case 7:		write_debug(ptr[7], reg, 7);			\
+			/* Fall through */				\
+	case 6:		write_debug(ptr[6], reg, 6);			\
+			/* Fall through */				\
+	case 5:		write_debug(ptr[5], reg, 5);			\
+			/* Fall through */				\
+	case 4:		write_debug(ptr[4], reg, 4);			\
+			/* Fall through */				\
+	case 3:		write_debug(ptr[3], reg, 3);			\
+			/* Fall through */				\
+	case 2:		write_debug(ptr[2], reg, 2);			\
+			/* Fall through */				\
+	case 1:		write_debug(ptr[1], reg, 1);			\
+			/* Fall through */				\
+	default:	write_debug(ptr[0], reg, 0);			\
+	}
+
+static inline void __hyp_text __debug_save_state(struct kvm_vcpu *vcpu,
+						 struct kvm_guest_debug_arch *dbg,
+						 struct kvm_cpu_context *ctxt)
+{
+	u64 aa64dfr0;
+	int brps, wrps;
+
+	aa64dfr0 = read_sysreg(id_aa64dfr0_el1);
+	brps = (aa64dfr0 >> 12) & 0xf;
+	wrps = (aa64dfr0 >> 20) & 0xf;
+
+	save_debug(dbg->dbg_bcr, dbgbcr, brps);
+	save_debug(dbg->dbg_bvr, dbgbvr, brps);
+	save_debug(dbg->dbg_wcr, dbgwcr, wrps);
+	save_debug(dbg->dbg_wvr, dbgwvr, wrps);
+
+	ctxt->sys_regs[MDCCINT_EL1] = read_sysreg(mdccint_el1);
+}
+
+static inline void __hyp_text __debug_restore_state(struct kvm_vcpu *vcpu,
+						    struct kvm_guest_debug_arch *dbg,
+						    struct kvm_cpu_context *ctxt)
+{
+	u64 aa64dfr0;
+	int brps, wrps;
+
+	aa64dfr0 = read_sysreg(id_aa64dfr0_el1);
+
+	brps = (aa64dfr0 >> 12) & 0xf;
+	wrps = (aa64dfr0 >> 20) & 0xf;
+
+	restore_debug(dbg->dbg_bcr, dbgbcr, brps);
+	restore_debug(dbg->dbg_bvr, dbgbvr, brps);
+	restore_debug(dbg->dbg_wcr, dbgwcr, wrps);
+	restore_debug(dbg->dbg_wvr, dbgwvr, wrps);
+
+	write_sysreg(ctxt->sys_regs[MDCCINT_EL1], mdccint_el1);
+}
+
+static inline void __hyp_text __debug_switch_to_guest_common(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpu_context *host_ctxt;
+	struct kvm_cpu_context *guest_ctxt;
+	struct kvm_guest_debug_arch *host_dbg;
+	struct kvm_guest_debug_arch *guest_dbg;
+
+	if (!(vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY))
+		return;
+
+	host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
+	guest_ctxt = &vcpu->arch.ctxt;
+	host_dbg = &vcpu->arch.host_debug_state.regs;
+	guest_dbg = kern_hyp_va(vcpu->arch.debug_ptr);
+
+	__debug_save_state(vcpu, host_dbg, host_ctxt);
+	__debug_restore_state(vcpu, guest_dbg, guest_ctxt);
+}
+
+static inline void __hyp_text __debug_switch_to_host_common(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpu_context *host_ctxt;
+	struct kvm_cpu_context *guest_ctxt;
+	struct kvm_guest_debug_arch *host_dbg;
+	struct kvm_guest_debug_arch *guest_dbg;
+
+	if (!(vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY))
+		return;
+
+	host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
+	guest_ctxt = &vcpu->arch.ctxt;
+	host_dbg = &vcpu->arch.host_debug_state.regs;
+	guest_dbg = kern_hyp_va(vcpu->arch.debug_ptr);
+
+	__debug_save_state(vcpu, guest_dbg, guest_ctxt);
+	__debug_restore_state(vcpu, host_dbg, host_ctxt);
+
+	vcpu->arch.flags &= ~KVM_ARM64_DEBUG_DIRTY;
+}
+
+#endif /* __ARM64_KVM_HYP_DEBUG_SR_H__ */
diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile
index 8b3ac38eaa44..b3cb67b63d67 100644
--- a/arch/arm64/kvm/hyp/nvhe/Makefile
+++ b/arch/arm64/kvm/hyp/nvhe/Makefile
@@ -6,7 +6,7 @@
 asflags-y := -D__KVM_NVHE_HYPERVISOR__
 ccflags-y := -D__KVM_NVHE_HYPERVISOR__
 
-obj-y := switch.o tlb.o hyp-init.o ../hyp-entry.o
+obj-y := debug-sr.o switch.o tlb.o hyp-init.o ../hyp-entry.o
 
 obj-y := $(patsubst %.o,%.hyp.o,$(obj-y))
 extra-y := $(patsubst %.hyp.o,%.hyp.tmp.o,$(obj-y))
diff --git a/arch/arm64/kvm/hyp/nvhe/debug-sr.c b/arch/arm64/kvm/hyp/nvhe/debug-sr.c
new file mode 100644
index 000000000000..828c0d48e790
--- /dev/null
+++ b/arch/arm64/kvm/hyp/nvhe/debug-sr.c
@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#include <hyp/debug-sr.h>
+
+#include <linux/compiler.h>
+#include <linux/kvm_host.h>
+
+#include <asm/debug-monitors.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_hyp.h>
+#include <asm/kvm_mmu.h>
+
+static void __hyp_text __debug_save_spe(u64 *pmscr_el1)
+{
+	u64 reg;
+
+	/* Clear pmscr in case of early return */
+	*pmscr_el1 = 0;
+
+	/* SPE present on this CPU? */
+	if (!cpuid_feature_extract_unsigned_field(read_sysreg(id_aa64dfr0_el1),
+						  ID_AA64DFR0_PMSVER_SHIFT))
+		return;
+
+	/* Yes; is it owned by EL3? */
+	reg = read_sysreg_s(SYS_PMBIDR_EL1);
+	if (reg & BIT(SYS_PMBIDR_EL1_P_SHIFT))
+		return;
+
+	/* No; is the host actually using the thing? */
+	reg = read_sysreg_s(SYS_PMBLIMITR_EL1);
+	if (!(reg & BIT(SYS_PMBLIMITR_EL1_E_SHIFT)))
+		return;
+
+	/* Yes; save the control register and disable data generation */
+	*pmscr_el1 = read_sysreg_s(SYS_PMSCR_EL1);
+	write_sysreg_s(0, SYS_PMSCR_EL1);
+	isb();
+
+	/* Now drain all buffered data to memory */
+	psb_csync();
+	dsb(nsh);
+}
+
+static void __hyp_text __debug_restore_spe(u64 pmscr_el1)
+{
+	if (!pmscr_el1)
+		return;
+
+	/* The host page table is installed, but not yet synchronised */
+	isb();
+
+	/* Re-enable data generation */
+	write_sysreg_s(pmscr_el1, SYS_PMSCR_EL1);
+}
+
+void __hyp_text __debug_switch_to_guest(struct kvm_vcpu *vcpu)
+{
+	/* Disable and flush SPE data generation */
+	__debug_save_spe(&vcpu->arch.host_debug_state.pmscr_el1);
+	__debug_switch_to_guest_common(vcpu);
+}
+
+void __hyp_text __debug_switch_to_host(struct kvm_vcpu *vcpu)
+{
+	__debug_restore_spe(vcpu->arch.host_debug_state.pmscr_el1);
+	__debug_switch_to_host_common(vcpu);
+}
+
+u32 __hyp_text __kvm_get_mdcr_el2(void)
+{
+	return read_sysreg(mdcr_el2);
+}
diff --git a/arch/arm64/kvm/hyp/vhe/Makefile b/arch/arm64/kvm/hyp/vhe/Makefile
index 9f71cd3ba50d..62bdaf272b03 100644
--- a/arch/arm64/kvm/hyp/vhe/Makefile
+++ b/arch/arm64/kvm/hyp/vhe/Makefile
@@ -6,7 +6,7 @@
 asflags-y := -D__KVM_VHE_HYPERVISOR__
 ccflags-y := -D__KVM_VHE_HYPERVISOR__
 
-obj-y := switch.o tlb.o ../hyp-entry.o
+obj-y := debug-sr.o switch.o tlb.o ../hyp-entry.o
 
 # KVM code is run at a different exception code with a different map, so
 # compiler instrumentation that inserts callbacks or checks into the code may
diff --git a/arch/arm64/kvm/hyp/vhe/debug-sr.c b/arch/arm64/kvm/hyp/vhe/debug-sr.c
new file mode 100644
index 000000000000..f1e2e5a00933
--- /dev/null
+++ b/arch/arm64/kvm/hyp/vhe/debug-sr.c
@@ -0,0 +1,26 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#include <hyp/debug-sr.h>
+
+#include <linux/kvm_host.h>
+
+#include <asm/kvm_hyp.h>
+
+void __debug_switch_to_guest(struct kvm_vcpu *vcpu)
+{
+	__debug_switch_to_guest_common(vcpu);
+}
+
+void __debug_switch_to_host(struct kvm_vcpu *vcpu)
+{
+	__debug_switch_to_host_common(vcpu);
+}
+
+u32 __kvm_get_mdcr_el2(void)
+{
+	return read_sysreg(mdcr_el2);
+}
-- 
cgit 


From 13aeb9b400c5d7c5e979fdbbf994c787487f7889 Mon Sep 17 00:00:00 2001
From: David Brazdil <dbrazdil@google.com>
Date: Thu, 25 Jun 2020 14:14:16 +0100
Subject: KVM: arm64: Split hyp/sysreg-sr.c to VHE/nVHE

sysreg-sr.c contains KVM's code for saving/restoring system registers, with
some code shared between VHE/nVHE. These common routines are moved to
a header file, VHE-specific code is moved to vhe/sysreg-sr.c and nVHE-specific
code to nvhe/sysreg-sr.c.

Signed-off-by: David Brazdil <dbrazdil@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200625131420.71444-12-dbrazdil@google.com
---
 arch/arm64/include/asm/kvm_host.h          |   6 +-
 arch/arm64/include/asm/kvm_hyp.h           |   5 +-
 arch/arm64/kernel/image-vars.h             |   7 -
 arch/arm64/kvm/arm.c                       |   8 +-
 arch/arm64/kvm/hyp/Makefile                |   4 +-
 arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h | 203 ++++++++++++++++++
 arch/arm64/kvm/hyp/nvhe/Makefile           |   2 +-
 arch/arm64/kvm/hyp/nvhe/switch.c           |   1 +
 arch/arm64/kvm/hyp/nvhe/sysreg-sr.c        |  46 ++++
 arch/arm64/kvm/hyp/sysreg-sr.c             | 333 -----------------------------
 arch/arm64/kvm/hyp/vhe/Makefile            |   2 +-
 arch/arm64/kvm/hyp/vhe/switch.c            |   2 +-
 arch/arm64/kvm/hyp/vhe/sysreg-sr.c         | 114 ++++++++++
 13 files changed, 380 insertions(+), 353 deletions(-)
 create mode 100644 arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
 create mode 100644 arch/arm64/kvm/hyp/nvhe/sysreg-sr.c
 delete mode 100644 arch/arm64/kvm/hyp/sysreg-sr.c
 create mode 100644 arch/arm64/kvm/hyp/vhe/sysreg-sr.c

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 49d1a5cd8f8f..e0920df1d0c1 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -338,7 +338,7 @@ struct kvm_vcpu_arch {
 	struct vcpu_reset_state	reset_state;
 
 	/* True when deferrable sysregs are loaded on the physical CPU,
-	 * see kvm_vcpu_load_sysregs and kvm_vcpu_put_sysregs. */
+	 * see kvm_vcpu_load_sysregs_vhe and kvm_vcpu_put_sysregs_vhe. */
 	bool sysregs_loaded_on_cpu;
 
 	/* Guest PV state */
@@ -639,8 +639,8 @@ static inline int kvm_arm_have_ssbd(void)
 	}
 }
 
-void kvm_vcpu_load_sysregs(struct kvm_vcpu *vcpu);
-void kvm_vcpu_put_sysregs(struct kvm_vcpu *vcpu);
+void kvm_vcpu_load_sysregs_vhe(struct kvm_vcpu *vcpu);
+void kvm_vcpu_put_sysregs_vhe(struct kvm_vcpu *vcpu);
 
 int kvm_set_ipa_limit(void);
 
diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index 82fa05d15b8b..997c5bda1ac7 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -66,14 +66,15 @@ int __vgic_v3_perform_cpuif_access(struct kvm_vcpu *vcpu);
 void __timer_enable_traps(struct kvm_vcpu *vcpu);
 void __timer_disable_traps(struct kvm_vcpu *vcpu);
 
+#ifdef __KVM_NVHE_HYPERVISOR__
 void __sysreg_save_state_nvhe(struct kvm_cpu_context *ctxt);
 void __sysreg_restore_state_nvhe(struct kvm_cpu_context *ctxt);
+#else
 void sysreg_save_host_state_vhe(struct kvm_cpu_context *ctxt);
 void sysreg_restore_host_state_vhe(struct kvm_cpu_context *ctxt);
 void sysreg_save_guest_state_vhe(struct kvm_cpu_context *ctxt);
 void sysreg_restore_guest_state_vhe(struct kvm_cpu_context *ctxt);
-void __sysreg32_save_state(struct kvm_vcpu *vcpu);
-void __sysreg32_restore_state(struct kvm_vcpu *vcpu);
+#endif
 
 void __debug_switch_to_guest(struct kvm_vcpu *vcpu);
 void __debug_switch_to_host(struct kvm_vcpu *vcpu);
diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index c44ca4e7dd66..59eb55893eaf 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -76,13 +76,6 @@ KVM_NVHE_ALIAS(abort_guest_exit_start);
 KVM_NVHE_ALIAS(__fpsimd_restore_state);
 KVM_NVHE_ALIAS(__fpsimd_save_state);
 
-/* Symbols defined in sysreg-sr.c (not yet compiled with nVHE build rules). */
-KVM_NVHE_ALIAS(__kvm_enable_ssbs);
-KVM_NVHE_ALIAS(__sysreg32_restore_state);
-KVM_NVHE_ALIAS(__sysreg32_save_state);
-KVM_NVHE_ALIAS(__sysreg_restore_state_nvhe);
-KVM_NVHE_ALIAS(__sysreg_save_state_nvhe);
-
 /* Symbols defined in timer-sr.c (not yet compiled with nVHE build rules). */
 KVM_NVHE_ALIAS(__kvm_timer_set_cntvoff);
 KVM_NVHE_ALIAS(__timer_disable_traps);
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 26780b78a523..0bf2cf5614c6 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -351,7 +351,8 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 	kvm_vgic_load(vcpu);
 	kvm_timer_vcpu_load(vcpu);
-	kvm_vcpu_load_sysregs(vcpu);
+	if (has_vhe())
+		kvm_vcpu_load_sysregs_vhe(vcpu);
 	kvm_arch_vcpu_load_fp(vcpu);
 	kvm_vcpu_pmu_restore_guest(vcpu);
 	if (kvm_arm_is_pvtime_enabled(&vcpu->arch))
@@ -369,7 +370,8 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
 	kvm_arch_vcpu_put_fp(vcpu);
-	kvm_vcpu_put_sysregs(vcpu);
+	if (has_vhe())
+		kvm_vcpu_put_sysregs_vhe(vcpu);
 	kvm_timer_vcpu_put(vcpu);
 	kvm_vgic_put(vcpu);
 	kvm_vcpu_pmu_restore_host(vcpu);
@@ -1302,7 +1304,7 @@ static void cpu_init_hyp_mode(void)
 	 */
 	if (this_cpu_has_cap(ARM64_SSBS) &&
 	    arm64_get_ssbd_state() == ARM64_SSBD_FORCE_DISABLE) {
-		kvm_call_hyp(__kvm_enable_ssbs);
+		kvm_call_hyp_nvhe(__kvm_enable_ssbs);
 	}
 }
 
diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile
index fc09025d2e97..f49797237818 100644
--- a/arch/arm64/kvm/hyp/Makefile
+++ b/arch/arm64/kvm/hyp/Makefile
@@ -13,8 +13,8 @@ subdir-ccflags-y := -I$(incdir)				\
 obj-$(CONFIG_KVM) += hyp.o vhe/ nvhe/
 obj-$(CONFIG_KVM_INDIRECT_VECTORS) += smccc_wa.o
 
-hyp-y := vgic-v3-sr.o timer-sr.o aarch32.o vgic-v2-cpuif-proxy.o sysreg-sr.o \
-	 entry.o fpsimd.o
+hyp-y := vgic-v3-sr.o timer-sr.o aarch32.o vgic-v2-cpuif-proxy.o entry.o \
+	 fpsimd.o
 
 # KVM code is run at a different exception code with a different map, so
 # compiler instrumentation that inserts callbacks or checks into the code may
diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
new file mode 100644
index 000000000000..3e0585fbd403
--- /dev/null
+++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
@@ -0,0 +1,203 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2012-2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#ifndef __ARM64_KVM_HYP_SYSREG_SR_H__
+#define __ARM64_KVM_HYP_SYSREG_SR_H__
+
+#include <linux/compiler.h>
+#include <linux/kvm_host.h>
+
+#include <asm/kprobes.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_hyp.h>
+
+static inline void __hyp_text __sysreg_save_common_state(struct kvm_cpu_context *ctxt)
+{
+	ctxt->sys_regs[MDSCR_EL1]	= read_sysreg(mdscr_el1);
+}
+
+static inline void __hyp_text __sysreg_save_user_state(struct kvm_cpu_context *ctxt)
+{
+	ctxt->sys_regs[TPIDR_EL0]	= read_sysreg(tpidr_el0);
+	ctxt->sys_regs[TPIDRRO_EL0]	= read_sysreg(tpidrro_el0);
+}
+
+static inline void __hyp_text __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
+{
+	ctxt->sys_regs[CSSELR_EL1]	= read_sysreg(csselr_el1);
+	ctxt->sys_regs[SCTLR_EL1]	= read_sysreg_el1(SYS_SCTLR);
+	ctxt->sys_regs[CPACR_EL1]	= read_sysreg_el1(SYS_CPACR);
+	ctxt->sys_regs[TTBR0_EL1]	= read_sysreg_el1(SYS_TTBR0);
+	ctxt->sys_regs[TTBR1_EL1]	= read_sysreg_el1(SYS_TTBR1);
+	ctxt->sys_regs[TCR_EL1]		= read_sysreg_el1(SYS_TCR);
+	ctxt->sys_regs[ESR_EL1]		= read_sysreg_el1(SYS_ESR);
+	ctxt->sys_regs[AFSR0_EL1]	= read_sysreg_el1(SYS_AFSR0);
+	ctxt->sys_regs[AFSR1_EL1]	= read_sysreg_el1(SYS_AFSR1);
+	ctxt->sys_regs[FAR_EL1]		= read_sysreg_el1(SYS_FAR);
+	ctxt->sys_regs[MAIR_EL1]	= read_sysreg_el1(SYS_MAIR);
+	ctxt->sys_regs[VBAR_EL1]	= read_sysreg_el1(SYS_VBAR);
+	ctxt->sys_regs[CONTEXTIDR_EL1]	= read_sysreg_el1(SYS_CONTEXTIDR);
+	ctxt->sys_regs[AMAIR_EL1]	= read_sysreg_el1(SYS_AMAIR);
+	ctxt->sys_regs[CNTKCTL_EL1]	= read_sysreg_el1(SYS_CNTKCTL);
+	ctxt->sys_regs[PAR_EL1]		= read_sysreg(par_el1);
+	ctxt->sys_regs[TPIDR_EL1]	= read_sysreg(tpidr_el1);
+
+	ctxt->gp_regs.sp_el1		= read_sysreg(sp_el1);
+	ctxt->gp_regs.elr_el1		= read_sysreg_el1(SYS_ELR);
+	ctxt->gp_regs.spsr[KVM_SPSR_EL1]= read_sysreg_el1(SYS_SPSR);
+}
+
+static inline void __hyp_text __sysreg_save_el2_return_state(struct kvm_cpu_context *ctxt)
+{
+	ctxt->gp_regs.regs.pc		= read_sysreg_el2(SYS_ELR);
+	ctxt->gp_regs.regs.pstate	= read_sysreg_el2(SYS_SPSR);
+
+	if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN))
+		ctxt->sys_regs[DISR_EL1] = read_sysreg_s(SYS_VDISR_EL2);
+}
+
+static inline void __hyp_text __sysreg_restore_common_state(struct kvm_cpu_context *ctxt)
+{
+	write_sysreg(ctxt->sys_regs[MDSCR_EL1],	  mdscr_el1);
+}
+
+static inline void __hyp_text __sysreg_restore_user_state(struct kvm_cpu_context *ctxt)
+{
+	write_sysreg(ctxt->sys_regs[TPIDR_EL0],		tpidr_el0);
+	write_sysreg(ctxt->sys_regs[TPIDRRO_EL0],	tpidrro_el0);
+}
+
+static inline void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
+{
+	write_sysreg(ctxt->sys_regs[MPIDR_EL1],		vmpidr_el2);
+	write_sysreg(ctxt->sys_regs[CSSELR_EL1],	csselr_el1);
+
+	if (has_vhe() ||
+	    !cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
+		write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1],	SYS_SCTLR);
+		write_sysreg_el1(ctxt->sys_regs[TCR_EL1],	SYS_TCR);
+	} else	if (!ctxt->__hyp_running_vcpu) {
+		/*
+		 * Must only be done for guest registers, hence the context
+		 * test. We're coming from the host, so SCTLR.M is already
+		 * set. Pairs with nVHE's __activate_traps().
+		 */
+		write_sysreg_el1((ctxt->sys_regs[TCR_EL1] |
+				  TCR_EPD1_MASK | TCR_EPD0_MASK),
+				 SYS_TCR);
+		isb();
+	}
+
+	write_sysreg_el1(ctxt->sys_regs[CPACR_EL1],	SYS_CPACR);
+	write_sysreg_el1(ctxt->sys_regs[TTBR0_EL1],	SYS_TTBR0);
+	write_sysreg_el1(ctxt->sys_regs[TTBR1_EL1],	SYS_TTBR1);
+	write_sysreg_el1(ctxt->sys_regs[ESR_EL1],	SYS_ESR);
+	write_sysreg_el1(ctxt->sys_regs[AFSR0_EL1],	SYS_AFSR0);
+	write_sysreg_el1(ctxt->sys_regs[AFSR1_EL1],	SYS_AFSR1);
+	write_sysreg_el1(ctxt->sys_regs[FAR_EL1],	SYS_FAR);
+	write_sysreg_el1(ctxt->sys_regs[MAIR_EL1],	SYS_MAIR);
+	write_sysreg_el1(ctxt->sys_regs[VBAR_EL1],	SYS_VBAR);
+	write_sysreg_el1(ctxt->sys_regs[CONTEXTIDR_EL1],SYS_CONTEXTIDR);
+	write_sysreg_el1(ctxt->sys_regs[AMAIR_EL1],	SYS_AMAIR);
+	write_sysreg_el1(ctxt->sys_regs[CNTKCTL_EL1],	SYS_CNTKCTL);
+	write_sysreg(ctxt->sys_regs[PAR_EL1],		par_el1);
+	write_sysreg(ctxt->sys_regs[TPIDR_EL1],		tpidr_el1);
+
+	if (!has_vhe() &&
+	    cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT) &&
+	    ctxt->__hyp_running_vcpu) {
+		/*
+		 * Must only be done for host registers, hence the context
+		 * test. Pairs with nVHE's __deactivate_traps().
+		 */
+		isb();
+		/*
+		 * At this stage, and thanks to the above isb(), S2 is
+		 * deconfigured and disabled. We can now restore the host's
+		 * S1 configuration: SCTLR, and only then TCR.
+		 */
+		write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1],	SYS_SCTLR);
+		isb();
+		write_sysreg_el1(ctxt->sys_regs[TCR_EL1],	SYS_TCR);
+	}
+
+	write_sysreg(ctxt->gp_regs.sp_el1,		sp_el1);
+	write_sysreg_el1(ctxt->gp_regs.elr_el1,		SYS_ELR);
+	write_sysreg_el1(ctxt->gp_regs.spsr[KVM_SPSR_EL1],SYS_SPSR);
+}
+
+static inline void __hyp_text __sysreg_restore_el2_return_state(struct kvm_cpu_context *ctxt)
+{
+	u64 pstate = ctxt->gp_regs.regs.pstate;
+	u64 mode = pstate & PSR_AA32_MODE_MASK;
+
+	/*
+	 * Safety check to ensure we're setting the CPU up to enter the guest
+	 * in a less privileged mode.
+	 *
+	 * If we are attempting a return to EL2 or higher in AArch64 state,
+	 * program SPSR_EL2 with M=EL2h and the IL bit set which ensures that
+	 * we'll take an illegal exception state exception immediately after
+	 * the ERET to the guest.  Attempts to return to AArch32 Hyp will
+	 * result in an illegal exception return because EL2's execution state
+	 * is determined by SCR_EL3.RW.
+	 */
+	if (!(mode & PSR_MODE32_BIT) && mode >= PSR_MODE_EL2t)
+		pstate = PSR_MODE_EL2h | PSR_IL_BIT;
+
+	write_sysreg_el2(ctxt->gp_regs.regs.pc,		SYS_ELR);
+	write_sysreg_el2(pstate,			SYS_SPSR);
+
+	if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN))
+		write_sysreg_s(ctxt->sys_regs[DISR_EL1], SYS_VDISR_EL2);
+}
+
+static inline void __hyp_text __sysreg32_save_state(struct kvm_vcpu *vcpu)
+{
+	u64 *spsr, *sysreg;
+
+	if (!vcpu_el1_is_32bit(vcpu))
+		return;
+
+	spsr = vcpu->arch.ctxt.gp_regs.spsr;
+	sysreg = vcpu->arch.ctxt.sys_regs;
+
+	spsr[KVM_SPSR_ABT] = read_sysreg(spsr_abt);
+	spsr[KVM_SPSR_UND] = read_sysreg(spsr_und);
+	spsr[KVM_SPSR_IRQ] = read_sysreg(spsr_irq);
+	spsr[KVM_SPSR_FIQ] = read_sysreg(spsr_fiq);
+
+	sysreg[DACR32_EL2] = read_sysreg(dacr32_el2);
+	sysreg[IFSR32_EL2] = read_sysreg(ifsr32_el2);
+
+	if (has_vhe() || vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY)
+		sysreg[DBGVCR32_EL2] = read_sysreg(dbgvcr32_el2);
+}
+
+static inline void __hyp_text __sysreg32_restore_state(struct kvm_vcpu *vcpu)
+{
+	u64 *spsr, *sysreg;
+
+	if (!vcpu_el1_is_32bit(vcpu))
+		return;
+
+	spsr = vcpu->arch.ctxt.gp_regs.spsr;
+	sysreg = vcpu->arch.ctxt.sys_regs;
+
+	write_sysreg(spsr[KVM_SPSR_ABT], spsr_abt);
+	write_sysreg(spsr[KVM_SPSR_UND], spsr_und);
+	write_sysreg(spsr[KVM_SPSR_IRQ], spsr_irq);
+	write_sysreg(spsr[KVM_SPSR_FIQ], spsr_fiq);
+
+	write_sysreg(sysreg[DACR32_EL2], dacr32_el2);
+	write_sysreg(sysreg[IFSR32_EL2], ifsr32_el2);
+
+	if (has_vhe() || vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY)
+		write_sysreg(sysreg[DBGVCR32_EL2], dbgvcr32_el2);
+}
+
+#endif /* __ARM64_KVM_HYP_SYSREG_SR_H__ */
diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile
index b3cb67b63d67..61a8160f0dd9 100644
--- a/arch/arm64/kvm/hyp/nvhe/Makefile
+++ b/arch/arm64/kvm/hyp/nvhe/Makefile
@@ -6,7 +6,7 @@
 asflags-y := -D__KVM_NVHE_HYPERVISOR__
 ccflags-y := -D__KVM_NVHE_HYPERVISOR__
 
-obj-y := debug-sr.o switch.o tlb.o hyp-init.o ../hyp-entry.o
+obj-y := sysreg-sr.o debug-sr.o switch.o tlb.o hyp-init.o ../hyp-entry.o
 
 obj-y := $(patsubst %.o,%.hyp.o,$(obj-y))
 extra-y := $(patsubst %.hyp.o,%.hyp.tmp.o,$(obj-y))
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index 7f6b8d3dc637..f08bfb951df6 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -5,6 +5,7 @@
  */
 
 #include <hyp/switch.h>
+#include <hyp/sysreg-sr.h>
 
 #include <linux/arm-smccc.h>
 #include <linux/kvm_host.h>
diff --git a/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c b/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c
new file mode 100644
index 000000000000..710cf28ab1ec
--- /dev/null
+++ b/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c
@@ -0,0 +1,46 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2012-2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#include <hyp/sysreg-sr.h>
+
+#include <linux/compiler.h>
+#include <linux/kvm_host.h>
+
+#include <asm/kprobes.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_hyp.h>
+
+/*
+ * Non-VHE: Both host and guest must save everything.
+ */
+
+void __hyp_text __sysreg_save_state_nvhe(struct kvm_cpu_context *ctxt)
+{
+	__sysreg_save_el1_state(ctxt);
+	__sysreg_save_common_state(ctxt);
+	__sysreg_save_user_state(ctxt);
+	__sysreg_save_el2_return_state(ctxt);
+}
+
+void __hyp_text __sysreg_restore_state_nvhe(struct kvm_cpu_context *ctxt)
+{
+	__sysreg_restore_el1_state(ctxt);
+	__sysreg_restore_common_state(ctxt);
+	__sysreg_restore_user_state(ctxt);
+	__sysreg_restore_el2_return_state(ctxt);
+}
+
+void __hyp_text __kvm_enable_ssbs(void)
+{
+	u64 tmp;
+
+	asm volatile(
+	"mrs	%0, sctlr_el2\n"
+	"orr	%0, %0, %1\n"
+	"msr	sctlr_el2, %0"
+	: "=&r" (tmp) : "L" (SCTLR_ELx_DSSBS));
+}
diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c
deleted file mode 100644
index 2493439a5c54..000000000000
--- a/arch/arm64/kvm/hyp/sysreg-sr.c
+++ /dev/null
@@ -1,333 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Copyright (C) 2012-2015 - ARM Ltd
- * Author: Marc Zyngier <marc.zyngier@arm.com>
- */
-
-#include <linux/compiler.h>
-#include <linux/kvm_host.h>
-
-#include <asm/kprobes.h>
-#include <asm/kvm_asm.h>
-#include <asm/kvm_emulate.h>
-#include <asm/kvm_hyp.h>
-
-/*
- * Non-VHE: Both host and guest must save everything.
- *
- * VHE: Host and guest must save mdscr_el1 and sp_el0 (and the PC and
- * pstate, which are handled as part of the el2 return state) on every
- * switch (sp_el0 is being dealt with in the assembly code).
- * tpidr_el0 and tpidrro_el0 only need to be switched when going
- * to host userspace or a different VCPU.  EL1 registers only need to be
- * switched when potentially going to run a different VCPU.  The latter two
- * classes are handled as part of kvm_arch_vcpu_load and kvm_arch_vcpu_put.
- */
-
-static void __hyp_text __sysreg_save_common_state(struct kvm_cpu_context *ctxt)
-{
-	ctxt->sys_regs[MDSCR_EL1]	= read_sysreg(mdscr_el1);
-}
-
-static void __hyp_text __sysreg_save_user_state(struct kvm_cpu_context *ctxt)
-{
-	ctxt->sys_regs[TPIDR_EL0]	= read_sysreg(tpidr_el0);
-	ctxt->sys_regs[TPIDRRO_EL0]	= read_sysreg(tpidrro_el0);
-}
-
-static void __hyp_text __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
-{
-	ctxt->sys_regs[CSSELR_EL1]	= read_sysreg(csselr_el1);
-	ctxt->sys_regs[SCTLR_EL1]	= read_sysreg_el1(SYS_SCTLR);
-	ctxt->sys_regs[CPACR_EL1]	= read_sysreg_el1(SYS_CPACR);
-	ctxt->sys_regs[TTBR0_EL1]	= read_sysreg_el1(SYS_TTBR0);
-	ctxt->sys_regs[TTBR1_EL1]	= read_sysreg_el1(SYS_TTBR1);
-	ctxt->sys_regs[TCR_EL1]		= read_sysreg_el1(SYS_TCR);
-	ctxt->sys_regs[ESR_EL1]		= read_sysreg_el1(SYS_ESR);
-	ctxt->sys_regs[AFSR0_EL1]	= read_sysreg_el1(SYS_AFSR0);
-	ctxt->sys_regs[AFSR1_EL1]	= read_sysreg_el1(SYS_AFSR1);
-	ctxt->sys_regs[FAR_EL1]		= read_sysreg_el1(SYS_FAR);
-	ctxt->sys_regs[MAIR_EL1]	= read_sysreg_el1(SYS_MAIR);
-	ctxt->sys_regs[VBAR_EL1]	= read_sysreg_el1(SYS_VBAR);
-	ctxt->sys_regs[CONTEXTIDR_EL1]	= read_sysreg_el1(SYS_CONTEXTIDR);
-	ctxt->sys_regs[AMAIR_EL1]	= read_sysreg_el1(SYS_AMAIR);
-	ctxt->sys_regs[CNTKCTL_EL1]	= read_sysreg_el1(SYS_CNTKCTL);
-	ctxt->sys_regs[PAR_EL1]		= read_sysreg(par_el1);
-	ctxt->sys_regs[TPIDR_EL1]	= read_sysreg(tpidr_el1);
-
-	ctxt->gp_regs.sp_el1		= read_sysreg(sp_el1);
-	ctxt->gp_regs.elr_el1		= read_sysreg_el1(SYS_ELR);
-	ctxt->gp_regs.spsr[KVM_SPSR_EL1]= read_sysreg_el1(SYS_SPSR);
-}
-
-static void __hyp_text __sysreg_save_el2_return_state(struct kvm_cpu_context *ctxt)
-{
-	ctxt->gp_regs.regs.pc		= read_sysreg_el2(SYS_ELR);
-	ctxt->gp_regs.regs.pstate	= read_sysreg_el2(SYS_SPSR);
-
-	if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN))
-		ctxt->sys_regs[DISR_EL1] = read_sysreg_s(SYS_VDISR_EL2);
-}
-
-void __hyp_text __sysreg_save_state_nvhe(struct kvm_cpu_context *ctxt)
-{
-	__sysreg_save_el1_state(ctxt);
-	__sysreg_save_common_state(ctxt);
-	__sysreg_save_user_state(ctxt);
-	__sysreg_save_el2_return_state(ctxt);
-}
-
-void sysreg_save_host_state_vhe(struct kvm_cpu_context *ctxt)
-{
-	__sysreg_save_common_state(ctxt);
-}
-NOKPROBE_SYMBOL(sysreg_save_host_state_vhe);
-
-void sysreg_save_guest_state_vhe(struct kvm_cpu_context *ctxt)
-{
-	__sysreg_save_common_state(ctxt);
-	__sysreg_save_el2_return_state(ctxt);
-}
-NOKPROBE_SYMBOL(sysreg_save_guest_state_vhe);
-
-static void __hyp_text __sysreg_restore_common_state(struct kvm_cpu_context *ctxt)
-{
-	write_sysreg(ctxt->sys_regs[MDSCR_EL1],	  mdscr_el1);
-}
-
-static void __hyp_text __sysreg_restore_user_state(struct kvm_cpu_context *ctxt)
-{
-	write_sysreg(ctxt->sys_regs[TPIDR_EL0],		tpidr_el0);
-	write_sysreg(ctxt->sys_regs[TPIDRRO_EL0],	tpidrro_el0);
-}
-
-static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
-{
-	write_sysreg(ctxt->sys_regs[MPIDR_EL1],		vmpidr_el2);
-	write_sysreg(ctxt->sys_regs[CSSELR_EL1],	csselr_el1);
-
-	if (has_vhe() ||
-	    !cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
-		write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1],	SYS_SCTLR);
-		write_sysreg_el1(ctxt->sys_regs[TCR_EL1],	SYS_TCR);
-	} else	if (!ctxt->__hyp_running_vcpu) {
-		/*
-		 * Must only be done for guest registers, hence the context
-		 * test. We're coming from the host, so SCTLR.M is already
-		 * set. Pairs with nVHE's __activate_traps().
-		 */
-		write_sysreg_el1((ctxt->sys_regs[TCR_EL1] |
-				  TCR_EPD1_MASK | TCR_EPD0_MASK),
-				 SYS_TCR);
-		isb();
-	}
-
-	write_sysreg_el1(ctxt->sys_regs[CPACR_EL1],	SYS_CPACR);
-	write_sysreg_el1(ctxt->sys_regs[TTBR0_EL1],	SYS_TTBR0);
-	write_sysreg_el1(ctxt->sys_regs[TTBR1_EL1],	SYS_TTBR1);
-	write_sysreg_el1(ctxt->sys_regs[ESR_EL1],	SYS_ESR);
-	write_sysreg_el1(ctxt->sys_regs[AFSR0_EL1],	SYS_AFSR0);
-	write_sysreg_el1(ctxt->sys_regs[AFSR1_EL1],	SYS_AFSR1);
-	write_sysreg_el1(ctxt->sys_regs[FAR_EL1],	SYS_FAR);
-	write_sysreg_el1(ctxt->sys_regs[MAIR_EL1],	SYS_MAIR);
-	write_sysreg_el1(ctxt->sys_regs[VBAR_EL1],	SYS_VBAR);
-	write_sysreg_el1(ctxt->sys_regs[CONTEXTIDR_EL1],SYS_CONTEXTIDR);
-	write_sysreg_el1(ctxt->sys_regs[AMAIR_EL1],	SYS_AMAIR);
-	write_sysreg_el1(ctxt->sys_regs[CNTKCTL_EL1],	SYS_CNTKCTL);
-	write_sysreg(ctxt->sys_regs[PAR_EL1],		par_el1);
-	write_sysreg(ctxt->sys_regs[TPIDR_EL1],		tpidr_el1);
-
-	if (!has_vhe() &&
-	    cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT) &&
-	    ctxt->__hyp_running_vcpu) {
-		/*
-		 * Must only be done for host registers, hence the context
-		 * test. Pairs with nVHE's __deactivate_traps().
-		 */
-		isb();
-		/*
-		 * At this stage, and thanks to the above isb(), S2 is
-		 * deconfigured and disabled. We can now restore the host's
-		 * S1 configuration: SCTLR, and only then TCR.
-		 */
-		write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1],	SYS_SCTLR);
-		isb();
-		write_sysreg_el1(ctxt->sys_regs[TCR_EL1],	SYS_TCR);
-	}
-
-	write_sysreg(ctxt->gp_regs.sp_el1,		sp_el1);
-	write_sysreg_el1(ctxt->gp_regs.elr_el1,		SYS_ELR);
-	write_sysreg_el1(ctxt->gp_regs.spsr[KVM_SPSR_EL1],SYS_SPSR);
-}
-
-static void __hyp_text
-__sysreg_restore_el2_return_state(struct kvm_cpu_context *ctxt)
-{
-	u64 pstate = ctxt->gp_regs.regs.pstate;
-	u64 mode = pstate & PSR_AA32_MODE_MASK;
-
-	/*
-	 * Safety check to ensure we're setting the CPU up to enter the guest
-	 * in a less privileged mode.
-	 *
-	 * If we are attempting a return to EL2 or higher in AArch64 state,
-	 * program SPSR_EL2 with M=EL2h and the IL bit set which ensures that
-	 * we'll take an illegal exception state exception immediately after
-	 * the ERET to the guest.  Attempts to return to AArch32 Hyp will
-	 * result in an illegal exception return because EL2's execution state
-	 * is determined by SCR_EL3.RW.
-	 */
-	if (!(mode & PSR_MODE32_BIT) && mode >= PSR_MODE_EL2t)
-		pstate = PSR_MODE_EL2h | PSR_IL_BIT;
-
-	write_sysreg_el2(ctxt->gp_regs.regs.pc,		SYS_ELR);
-	write_sysreg_el2(pstate,			SYS_SPSR);
-
-	if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN))
-		write_sysreg_s(ctxt->sys_regs[DISR_EL1], SYS_VDISR_EL2);
-}
-
-void __hyp_text __sysreg_restore_state_nvhe(struct kvm_cpu_context *ctxt)
-{
-	__sysreg_restore_el1_state(ctxt);
-	__sysreg_restore_common_state(ctxt);
-	__sysreg_restore_user_state(ctxt);
-	__sysreg_restore_el2_return_state(ctxt);
-}
-
-void sysreg_restore_host_state_vhe(struct kvm_cpu_context *ctxt)
-{
-	__sysreg_restore_common_state(ctxt);
-}
-NOKPROBE_SYMBOL(sysreg_restore_host_state_vhe);
-
-void sysreg_restore_guest_state_vhe(struct kvm_cpu_context *ctxt)
-{
-	__sysreg_restore_common_state(ctxt);
-	__sysreg_restore_el2_return_state(ctxt);
-}
-NOKPROBE_SYMBOL(sysreg_restore_guest_state_vhe);
-
-void __hyp_text __sysreg32_save_state(struct kvm_vcpu *vcpu)
-{
-	u64 *spsr, *sysreg;
-
-	if (!vcpu_el1_is_32bit(vcpu))
-		return;
-
-	spsr = vcpu->arch.ctxt.gp_regs.spsr;
-	sysreg = vcpu->arch.ctxt.sys_regs;
-
-	spsr[KVM_SPSR_ABT] = read_sysreg(spsr_abt);
-	spsr[KVM_SPSR_UND] = read_sysreg(spsr_und);
-	spsr[KVM_SPSR_IRQ] = read_sysreg(spsr_irq);
-	spsr[KVM_SPSR_FIQ] = read_sysreg(spsr_fiq);
-
-	sysreg[DACR32_EL2] = read_sysreg(dacr32_el2);
-	sysreg[IFSR32_EL2] = read_sysreg(ifsr32_el2);
-
-	if (has_vhe() || vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY)
-		sysreg[DBGVCR32_EL2] = read_sysreg(dbgvcr32_el2);
-}
-
-void __hyp_text __sysreg32_restore_state(struct kvm_vcpu *vcpu)
-{
-	u64 *spsr, *sysreg;
-
-	if (!vcpu_el1_is_32bit(vcpu))
-		return;
-
-	spsr = vcpu->arch.ctxt.gp_regs.spsr;
-	sysreg = vcpu->arch.ctxt.sys_regs;
-
-	write_sysreg(spsr[KVM_SPSR_ABT], spsr_abt);
-	write_sysreg(spsr[KVM_SPSR_UND], spsr_und);
-	write_sysreg(spsr[KVM_SPSR_IRQ], spsr_irq);
-	write_sysreg(spsr[KVM_SPSR_FIQ], spsr_fiq);
-
-	write_sysreg(sysreg[DACR32_EL2], dacr32_el2);
-	write_sysreg(sysreg[IFSR32_EL2], ifsr32_el2);
-
-	if (has_vhe() || vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY)
-		write_sysreg(sysreg[DBGVCR32_EL2], dbgvcr32_el2);
-}
-
-/**
- * kvm_vcpu_load_sysregs - Load guest system registers to the physical CPU
- *
- * @vcpu: The VCPU pointer
- *
- * Load system registers that do not affect the host's execution, for
- * example EL1 system registers on a VHE system where the host kernel
- * runs at EL2.  This function is called from KVM's vcpu_load() function
- * and loading system register state early avoids having to load them on
- * every entry to the VM.
- */
-void kvm_vcpu_load_sysregs(struct kvm_vcpu *vcpu)
-{
-	struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt;
-	struct kvm_cpu_context *host_ctxt;
-
-	if (!has_vhe())
-		return;
-
-	host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
-	__sysreg_save_user_state(host_ctxt);
-
-	/*
-	 * Load guest EL1 and user state
-	 *
-	 * We must restore the 32-bit state before the sysregs, thanks
-	 * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72).
-	 */
-	__sysreg32_restore_state(vcpu);
-	__sysreg_restore_user_state(guest_ctxt);
-	__sysreg_restore_el1_state(guest_ctxt);
-
-	vcpu->arch.sysregs_loaded_on_cpu = true;
-
-	activate_traps_vhe_load(vcpu);
-}
-
-/**
- * kvm_vcpu_put_sysregs - Restore host system registers to the physical CPU
- *
- * @vcpu: The VCPU pointer
- *
- * Save guest system registers that do not affect the host's execution, for
- * example EL1 system registers on a VHE system where the host kernel
- * runs at EL2.  This function is called from KVM's vcpu_put() function
- * and deferring saving system register state until we're no longer running the
- * VCPU avoids having to save them on every exit from the VM.
- */
-void kvm_vcpu_put_sysregs(struct kvm_vcpu *vcpu)
-{
-	struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt;
-	struct kvm_cpu_context *host_ctxt;
-
-	if (!has_vhe())
-		return;
-
-	host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
-	deactivate_traps_vhe_put();
-
-	__sysreg_save_el1_state(guest_ctxt);
-	__sysreg_save_user_state(guest_ctxt);
-	__sysreg32_save_state(vcpu);
-
-	/* Restore host user state */
-	__sysreg_restore_user_state(host_ctxt);
-
-	vcpu->arch.sysregs_loaded_on_cpu = false;
-}
-
-void __hyp_text __kvm_enable_ssbs(void)
-{
-	u64 tmp;
-
-	asm volatile(
-	"mrs	%0, sctlr_el2\n"
-	"orr	%0, %0, %1\n"
-	"msr	sctlr_el2, %0"
-	: "=&r" (tmp) : "L" (SCTLR_ELx_DSSBS));
-}
diff --git a/arch/arm64/kvm/hyp/vhe/Makefile b/arch/arm64/kvm/hyp/vhe/Makefile
index 62bdaf272b03..2801582a739a 100644
--- a/arch/arm64/kvm/hyp/vhe/Makefile
+++ b/arch/arm64/kvm/hyp/vhe/Makefile
@@ -6,7 +6,7 @@
 asflags-y := -D__KVM_VHE_HYPERVISOR__
 ccflags-y := -D__KVM_VHE_HYPERVISOR__
 
-obj-y := debug-sr.o switch.o tlb.o ../hyp-entry.o
+obj-y := sysreg-sr.o debug-sr.o switch.o tlb.o ../hyp-entry.o
 
 # KVM code is run at a different exception code with a different map, so
 # compiler instrumentation that inserts callbacks or checks into the code may
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index e8d76cab44e4..c0d33deba77e 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -120,7 +120,7 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
 	 * HCR_EL2.TGE.
 	 *
 	 * We have already configured the guest's stage 1 translation in
-	 * kvm_vcpu_load_sysregs above.  We must now call __activate_vm
+	 * kvm_vcpu_load_sysregs_vhe above.  We must now call __activate_vm
 	 * before __activate_traps, because __activate_vm configures
 	 * stage 2 translation, and __activate_traps clear HCR_EL2.TGE
 	 * (among other things).
diff --git a/arch/arm64/kvm/hyp/vhe/sysreg-sr.c b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
new file mode 100644
index 000000000000..996471e4c138
--- /dev/null
+++ b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
@@ -0,0 +1,114 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2012-2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#include <hyp/sysreg-sr.h>
+
+#include <linux/compiler.h>
+#include <linux/kvm_host.h>
+
+#include <asm/kprobes.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_hyp.h>
+
+/*
+ * VHE: Host and guest must save mdscr_el1 and sp_el0 (and the PC and
+ * pstate, which are handled as part of the el2 return state) on every
+ * switch (sp_el0 is being dealt with in the assembly code).
+ * tpidr_el0 and tpidrro_el0 only need to be switched when going
+ * to host userspace or a different VCPU.  EL1 registers only need to be
+ * switched when potentially going to run a different VCPU.  The latter two
+ * classes are handled as part of kvm_arch_vcpu_load and kvm_arch_vcpu_put.
+ */
+
+void sysreg_save_host_state_vhe(struct kvm_cpu_context *ctxt)
+{
+	__sysreg_save_common_state(ctxt);
+}
+NOKPROBE_SYMBOL(sysreg_save_host_state_vhe);
+
+void sysreg_save_guest_state_vhe(struct kvm_cpu_context *ctxt)
+{
+	__sysreg_save_common_state(ctxt);
+	__sysreg_save_el2_return_state(ctxt);
+}
+NOKPROBE_SYMBOL(sysreg_save_guest_state_vhe);
+
+void sysreg_restore_host_state_vhe(struct kvm_cpu_context *ctxt)
+{
+	__sysreg_restore_common_state(ctxt);
+}
+NOKPROBE_SYMBOL(sysreg_restore_host_state_vhe);
+
+void sysreg_restore_guest_state_vhe(struct kvm_cpu_context *ctxt)
+{
+	__sysreg_restore_common_state(ctxt);
+	__sysreg_restore_el2_return_state(ctxt);
+}
+NOKPROBE_SYMBOL(sysreg_restore_guest_state_vhe);
+
+/**
+ * kvm_vcpu_load_sysregs_vhe - Load guest system registers to the physical CPU
+ *
+ * @vcpu: The VCPU pointer
+ *
+ * Load system registers that do not affect the host's execution, for
+ * example EL1 system registers on a VHE system where the host kernel
+ * runs at EL2.  This function is called from KVM's vcpu_load() function
+ * and loading system register state early avoids having to load them on
+ * every entry to the VM.
+ */
+void kvm_vcpu_load_sysregs_vhe(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt;
+	struct kvm_cpu_context *host_ctxt;
+
+	host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
+	__sysreg_save_user_state(host_ctxt);
+
+	/*
+	 * Load guest EL1 and user state
+	 *
+	 * We must restore the 32-bit state before the sysregs, thanks
+	 * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72).
+	 */
+	__sysreg32_restore_state(vcpu);
+	__sysreg_restore_user_state(guest_ctxt);
+	__sysreg_restore_el1_state(guest_ctxt);
+
+	vcpu->arch.sysregs_loaded_on_cpu = true;
+
+	activate_traps_vhe_load(vcpu);
+}
+
+/**
+ * kvm_vcpu_put_sysregs_vhe - Restore host system registers to the physical CPU
+ *
+ * @vcpu: The VCPU pointer
+ *
+ * Save guest system registers that do not affect the host's execution, for
+ * example EL1 system registers on a VHE system where the host kernel
+ * runs at EL2.  This function is called from KVM's vcpu_put() function
+ * and deferring saving system register state until we're no longer running the
+ * VCPU avoids having to save them on every exit from the VM.
+ */
+void kvm_vcpu_put_sysregs_vhe(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt;
+	struct kvm_cpu_context *host_ctxt;
+
+	host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
+	deactivate_traps_vhe_put();
+
+	__sysreg_save_el1_state(guest_ctxt);
+	__sysreg_save_user_state(guest_ctxt);
+	__sysreg32_save_state(vcpu);
+
+	/* Restore host user state */
+	__sysreg_restore_user_state(host_ctxt);
+
+	vcpu->arch.sysregs_loaded_on_cpu = false;
+}
-- 
cgit 


From 9aebdea494b5d2d5fe0ba54d71e9d6c5acfe76b4 Mon Sep 17 00:00:00 2001
From: David Brazdil <dbrazdil@google.com>
Date: Thu, 25 Jun 2020 14:14:17 +0100
Subject: KVM: arm64: Duplicate hyp/timer-sr.c for VHE/nVHE

timer-sr.c contains a HVC handler for setting CNTVOFF_EL2 and two helper
functions for controlling access to physical counter. The former is used by
both VHE/nVHE and is duplicated, the latter are used only by nVHE and moved
to nvhe/timer-sr.c.

Signed-off-by: David Brazdil <dbrazdil@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200625131420.71444-13-dbrazdil@google.com
---
 arch/arm64/include/asm/kvm_hyp.h   |  2 ++
 arch/arm64/kernel/image-vars.h     |  5 ----
 arch/arm64/kvm/hyp/Makefile        |  2 +-
 arch/arm64/kvm/hyp/nvhe/Makefile   |  3 ++-
 arch/arm64/kvm/hyp/nvhe/timer-sr.c | 48 ++++++++++++++++++++++++++++++++++++++
 arch/arm64/kvm/hyp/timer-sr.c      | 48 --------------------------------------
 arch/arm64/kvm/hyp/vhe/Makefile    |  2 +-
 arch/arm64/kvm/hyp/vhe/timer-sr.c  | 12 ++++++++++
 8 files changed, 66 insertions(+), 56 deletions(-)
 create mode 100644 arch/arm64/kvm/hyp/nvhe/timer-sr.c
 delete mode 100644 arch/arm64/kvm/hyp/timer-sr.c
 create mode 100644 arch/arm64/kvm/hyp/vhe/timer-sr.c

diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index 997c5bda1ac7..19f8b40fe6cf 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -63,8 +63,10 @@ void __vgic_v3_save_aprs(struct vgic_v3_cpu_if *cpu_if);
 void __vgic_v3_restore_aprs(struct vgic_v3_cpu_if *cpu_if);
 int __vgic_v3_perform_cpuif_access(struct kvm_vcpu *vcpu);
 
+#ifdef __KVM_NVHE_HYPERVISOR__
 void __timer_enable_traps(struct kvm_vcpu *vcpu);
 void __timer_disable_traps(struct kvm_vcpu *vcpu);
+#endif
 
 #ifdef __KVM_NVHE_HYPERVISOR__
 void __sysreg_save_state_nvhe(struct kvm_cpu_context *ctxt);
diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index 59eb55893eaf..2757d3512704 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -76,11 +76,6 @@ KVM_NVHE_ALIAS(abort_guest_exit_start);
 KVM_NVHE_ALIAS(__fpsimd_restore_state);
 KVM_NVHE_ALIAS(__fpsimd_save_state);
 
-/* Symbols defined in timer-sr.c (not yet compiled with nVHE build rules). */
-KVM_NVHE_ALIAS(__kvm_timer_set_cntvoff);
-KVM_NVHE_ALIAS(__timer_disable_traps);
-KVM_NVHE_ALIAS(__timer_enable_traps);
-
 /* Symbols defined in vgic-v2-cpuif-proxy.c (not yet compiled with nVHE build rules). */
 KVM_NVHE_ALIAS(__vgic_v2_perform_cpuif_access);
 
diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile
index f49797237818..ef1aa7fe8f5a 100644
--- a/arch/arm64/kvm/hyp/Makefile
+++ b/arch/arm64/kvm/hyp/Makefile
@@ -13,7 +13,7 @@ subdir-ccflags-y := -I$(incdir)				\
 obj-$(CONFIG_KVM) += hyp.o vhe/ nvhe/
 obj-$(CONFIG_KVM_INDIRECT_VECTORS) += smccc_wa.o
 
-hyp-y := vgic-v3-sr.o timer-sr.o aarch32.o vgic-v2-cpuif-proxy.o entry.o \
+hyp-y := vgic-v3-sr.o aarch32.o vgic-v2-cpuif-proxy.o entry.o \
 	 fpsimd.o
 
 # KVM code is run at a different exception code with a different map, so
diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile
index 61a8160f0dd9..0f4c544f07db 100644
--- a/arch/arm64/kvm/hyp/nvhe/Makefile
+++ b/arch/arm64/kvm/hyp/nvhe/Makefile
@@ -6,7 +6,8 @@
 asflags-y := -D__KVM_NVHE_HYPERVISOR__
 ccflags-y := -D__KVM_NVHE_HYPERVISOR__
 
-obj-y := sysreg-sr.o debug-sr.o switch.o tlb.o hyp-init.o ../hyp-entry.o
+obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o hyp-init.o \
+	 ../hyp-entry.o
 
 obj-y := $(patsubst %.o,%.hyp.o,$(obj-y))
 extra-y := $(patsubst %.hyp.o,%.hyp.tmp.o,$(obj-y))
diff --git a/arch/arm64/kvm/hyp/nvhe/timer-sr.c b/arch/arm64/kvm/hyp/nvhe/timer-sr.c
new file mode 100644
index 000000000000..42c8ed71d06e
--- /dev/null
+++ b/arch/arm64/kvm/hyp/nvhe/timer-sr.c
@@ -0,0 +1,48 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2012-2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#include <clocksource/arm_arch_timer.h>
+#include <linux/compiler.h>
+#include <linux/kvm_host.h>
+
+#include <asm/kvm_hyp.h>
+
+void __kvm_timer_set_cntvoff(u64 cntvoff)
+{
+	write_sysreg(cntvoff, cntvoff_el2);
+}
+
+/*
+ * Should only be called on non-VHE systems.
+ * VHE systems use EL2 timers and configure EL1 timers in kvm_timer_init_vhe().
+ */
+void __hyp_text __timer_disable_traps(struct kvm_vcpu *vcpu)
+{
+	u64 val;
+
+	/* Allow physical timer/counter access for the host */
+	val = read_sysreg(cnthctl_el2);
+	val |= CNTHCTL_EL1PCTEN | CNTHCTL_EL1PCEN;
+	write_sysreg(val, cnthctl_el2);
+}
+
+/*
+ * Should only be called on non-VHE systems.
+ * VHE systems use EL2 timers and configure EL1 timers in kvm_timer_init_vhe().
+ */
+void __hyp_text __timer_enable_traps(struct kvm_vcpu *vcpu)
+{
+	u64 val;
+
+	/*
+	 * Disallow physical timer access for the guest
+	 * Physical counter access is allowed
+	 */
+	val = read_sysreg(cnthctl_el2);
+	val &= ~CNTHCTL_EL1PCEN;
+	val |= CNTHCTL_EL1PCTEN;
+	write_sysreg(val, cnthctl_el2);
+}
diff --git a/arch/arm64/kvm/hyp/timer-sr.c b/arch/arm64/kvm/hyp/timer-sr.c
deleted file mode 100644
index fb5c0be33223..000000000000
--- a/arch/arm64/kvm/hyp/timer-sr.c
+++ /dev/null
@@ -1,48 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Copyright (C) 2012-2015 - ARM Ltd
- * Author: Marc Zyngier <marc.zyngier@arm.com>
- */
-
-#include <clocksource/arm_arch_timer.h>
-#include <linux/compiler.h>
-#include <linux/kvm_host.h>
-
-#include <asm/kvm_hyp.h>
-
-void __hyp_text __kvm_timer_set_cntvoff(u64 cntvoff)
-{
-	write_sysreg(cntvoff, cntvoff_el2);
-}
-
-/*
- * Should only be called on non-VHE systems.
- * VHE systems use EL2 timers and configure EL1 timers in kvm_timer_init_vhe().
- */
-void __hyp_text __timer_disable_traps(struct kvm_vcpu *vcpu)
-{
-	u64 val;
-
-	/* Allow physical timer/counter access for the host */
-	val = read_sysreg(cnthctl_el2);
-	val |= CNTHCTL_EL1PCTEN | CNTHCTL_EL1PCEN;
-	write_sysreg(val, cnthctl_el2);
-}
-
-/*
- * Should only be called on non-VHE systems.
- * VHE systems use EL2 timers and configure EL1 timers in kvm_timer_init_vhe().
- */
-void __hyp_text __timer_enable_traps(struct kvm_vcpu *vcpu)
-{
-	u64 val;
-
-	/*
-	 * Disallow physical timer access for the guest
-	 * Physical counter access is allowed
-	 */
-	val = read_sysreg(cnthctl_el2);
-	val &= ~CNTHCTL_EL1PCEN;
-	val |= CNTHCTL_EL1PCTEN;
-	write_sysreg(val, cnthctl_el2);
-}
diff --git a/arch/arm64/kvm/hyp/vhe/Makefile b/arch/arm64/kvm/hyp/vhe/Makefile
index 2801582a739a..a1dbbc5409bd 100644
--- a/arch/arm64/kvm/hyp/vhe/Makefile
+++ b/arch/arm64/kvm/hyp/vhe/Makefile
@@ -6,7 +6,7 @@
 asflags-y := -D__KVM_VHE_HYPERVISOR__
 ccflags-y := -D__KVM_VHE_HYPERVISOR__
 
-obj-y := sysreg-sr.o debug-sr.o switch.o tlb.o ../hyp-entry.o
+obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o ../hyp-entry.o
 
 # KVM code is run at a different exception code with a different map, so
 # compiler instrumentation that inserts callbacks or checks into the code may
diff --git a/arch/arm64/kvm/hyp/vhe/timer-sr.c b/arch/arm64/kvm/hyp/vhe/timer-sr.c
new file mode 100644
index 000000000000..4cda674a8be6
--- /dev/null
+++ b/arch/arm64/kvm/hyp/vhe/timer-sr.c
@@ -0,0 +1,12 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2012-2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#include <asm/kvm_hyp.h>
+
+void __kvm_timer_set_cntvoff(u64 cntvoff)
+{
+	write_sysreg(cntvoff, cntvoff_el2);
+}
-- 
cgit 


From c04dd455eb311d2d289c9d81d080eaf11a06cebf Mon Sep 17 00:00:00 2001
From: David Brazdil <dbrazdil@google.com>
Date: Thu, 25 Jun 2020 14:14:18 +0100
Subject: KVM: arm64: Compile remaining hyp/ files for both VHE/nVHE

The following files in hyp/ contain only code shared by VHE/nVHE:
  vgic-v3-sr.c, aarch32.c, vgic-v2-cpuif-proxy.c, entry.S, fpsimd.S
Compile them under both configurations. Deletions in image-vars.h reflect
eliminated dependencies of nVHE code on the rest of the kernel.

Signed-off-by: David Brazdil <dbrazdil@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200625131420.71444-14-dbrazdil@google.com
---
 arch/arm64/kernel/image-vars.h   | 29 -----------------------------
 arch/arm64/kvm/hyp/Makefile      | 13 +------------
 arch/arm64/kvm/hyp/nvhe/Makefile |  5 +++--
 arch/arm64/kvm/hyp/vhe/Makefile  |  4 +++-
 4 files changed, 7 insertions(+), 44 deletions(-)

diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index 2757d3512704..9e897c500237 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -63,35 +63,6 @@ __efistub__ctype		= _ctype;
 
 #define KVM_NVHE_ALIAS(sym) __kvm_nvhe_##sym = sym;
 
-/* Symbols defined in aarch32.c (not yet compiled with nVHE build rules). */
-KVM_NVHE_ALIAS(kvm_skip_instr32);
-
-/* Symbols defined in entry.S (not yet compiled with nVHE build rules). */
-KVM_NVHE_ALIAS(__guest_enter);
-KVM_NVHE_ALIAS(__guest_exit);
-KVM_NVHE_ALIAS(abort_guest_exit_end);
-KVM_NVHE_ALIAS(abort_guest_exit_start);
-
-/* Symbols defined in fpsimd.S (not yet compiled with nVHE build rules). */
-KVM_NVHE_ALIAS(__fpsimd_restore_state);
-KVM_NVHE_ALIAS(__fpsimd_save_state);
-
-/* Symbols defined in vgic-v2-cpuif-proxy.c (not yet compiled with nVHE build rules). */
-KVM_NVHE_ALIAS(__vgic_v2_perform_cpuif_access);
-
-/* Symbols defined in vgic-v3-sr.c (not yet compiled with nVHE build rules). */
-KVM_NVHE_ALIAS(__vgic_v3_activate_traps);
-KVM_NVHE_ALIAS(__vgic_v3_deactivate_traps);
-KVM_NVHE_ALIAS(__vgic_v3_get_ich_vtr_el2);
-KVM_NVHE_ALIAS(__vgic_v3_init_lrs);
-KVM_NVHE_ALIAS(__vgic_v3_perform_cpuif_access);
-KVM_NVHE_ALIAS(__vgic_v3_read_vmcr);
-KVM_NVHE_ALIAS(__vgic_v3_restore_aprs);
-KVM_NVHE_ALIAS(__vgic_v3_restore_state);
-KVM_NVHE_ALIAS(__vgic_v3_save_aprs);
-KVM_NVHE_ALIAS(__vgic_v3_save_state);
-KVM_NVHE_ALIAS(__vgic_v3_write_vmcr);
-
 /* Alternative callbacks for init-time patching of nVHE hyp code. */
 KVM_NVHE_ALIAS(arm64_enable_wa2_handling);
 KVM_NVHE_ALIAS(kvm_patch_vector_branch);
diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile
index ef1aa7fe8f5a..f54f0e89a71c 100644
--- a/arch/arm64/kvm/hyp/Makefile
+++ b/arch/arm64/kvm/hyp/Makefile
@@ -10,16 +10,5 @@ subdir-ccflags-y := -I$(incdir)				\
 		    -DDISABLE_BRANCH_PROFILING		\
 		    $(DISABLE_STACKLEAK_PLUGIN)
 
-obj-$(CONFIG_KVM) += hyp.o vhe/ nvhe/
+obj-$(CONFIG_KVM) += vhe/ nvhe/
 obj-$(CONFIG_KVM_INDIRECT_VECTORS) += smccc_wa.o
-
-hyp-y := vgic-v3-sr.o aarch32.o vgic-v2-cpuif-proxy.o entry.o \
-	 fpsimd.o
-
-# KVM code is run at a different exception code with a different map, so
-# compiler instrumentation that inserts callbacks or checks into the code may
-# cause crashes. Just disable it.
-GCOV_PROFILE	:= n
-KASAN_SANITIZE	:= n
-UBSAN_SANITIZE	:= n
-KCOV_INSTRUMENT	:= n
diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile
index 0f4c544f07db..ad8729f5e814 100644
--- a/arch/arm64/kvm/hyp/nvhe/Makefile
+++ b/arch/arm64/kvm/hyp/nvhe/Makefile
@@ -6,8 +6,9 @@
 asflags-y := -D__KVM_NVHE_HYPERVISOR__
 ccflags-y := -D__KVM_NVHE_HYPERVISOR__
 
-obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o hyp-init.o \
-	 ../hyp-entry.o
+obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o hyp-init.o
+obj-y += ../vgic-v3-sr.o ../aarch32.o ../vgic-v2-cpuif-proxy.o ../entry.o \
+	 ../fpsimd.o ../hyp-entry.o
 
 obj-y := $(patsubst %.o,%.hyp.o,$(obj-y))
 extra-y := $(patsubst %.hyp.o,%.hyp.tmp.o,$(obj-y))
diff --git a/arch/arm64/kvm/hyp/vhe/Makefile b/arch/arm64/kvm/hyp/vhe/Makefile
index a1dbbc5409bd..090fd1e14be2 100644
--- a/arch/arm64/kvm/hyp/vhe/Makefile
+++ b/arch/arm64/kvm/hyp/vhe/Makefile
@@ -6,7 +6,9 @@
 asflags-y := -D__KVM_VHE_HYPERVISOR__
 ccflags-y := -D__KVM_VHE_HYPERVISOR__
 
-obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o ../hyp-entry.o
+obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o
+obj-y += ../vgic-v3-sr.o ../aarch32.o ../vgic-v2-cpuif-proxy.o ../entry.o \
+	 ../fpsimd.o ../hyp-entry.o
 
 # KVM code is run at a different exception code with a different map, so
 # compiler instrumentation that inserts callbacks or checks into the code may
-- 
cgit 


From c50cb04303cb88c517715b078e3e010c024af1a5 Mon Sep 17 00:00:00 2001
From: David Brazdil <dbrazdil@google.com>
Date: Thu, 25 Jun 2020 14:14:19 +0100
Subject: KVM: arm64: Remove __hyp_text macro, use build rules instead

With nVHE code now fully separated from the rest of the kernel, the effects of
the __hyp_text macro (which had to be applied on all nVHE code) can be
achieved with build rules instead. The macro used to:
  (a) move code to .hyp.text ELF section, now done by renaming .text using
      `objcopy`, and
  (b) `notrace` and `__noscs` would negate effects of CC_FLAGS_FTRACE and
      CC_FLAGS_SCS, respectivelly, now those flags are  erased from
      KBUILD_CFLAGS (same way as in EFI stub).

Note that by removing __hyp_text from code shared with VHE, all VHE code is now
compiled into .text and without `notrace` and `__noscs`.

Use of '.pushsection .hyp.text' removed from assembly files as this is now also
covered by the build rules.

For MAINTAINERS: if needed to re-run, uses of macro were removed with the
following command. Formatting was fixed up manually.

  find arch/arm64/kvm/hyp -type f -name '*.c' -o -name '*.h' \
       -exec sed -i 's/ __hyp_text//g' {} +

Signed-off-by: David Brazdil <dbrazdil@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200625131420.71444-15-dbrazdil@google.com
---
 arch/arm64/include/asm/kvm_emulate.h       |   2 +-
 arch/arm64/include/asm/kvm_hyp.h           |   2 -
 arch/arm64/kvm/hyp/aarch32.c               |   6 +-
 arch/arm64/kvm/hyp/entry.S                 |   1 -
 arch/arm64/kvm/hyp/fpsimd.S                |   1 -
 arch/arm64/kvm/hyp/hyp-entry.S             |   1 -
 arch/arm64/kvm/hyp/include/hyp/debug-sr.h  |  16 ++--
 arch/arm64/kvm/hyp/include/hyp/switch.h    |  36 ++++----
 arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h |  20 ++---
 arch/arm64/kvm/hyp/nvhe/Makefile           |   8 +-
 arch/arm64/kvm/hyp/nvhe/debug-sr.c         |  10 +--
 arch/arm64/kvm/hyp/nvhe/switch.c           |  18 ++--
 arch/arm64/kvm/hyp/nvhe/sysreg-sr.c        |   6 +-
 arch/arm64/kvm/hyp/nvhe/timer-sr.c         |   4 +-
 arch/arm64/kvm/hyp/nvhe/tlb.c              |  14 ++--
 arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c   |   4 +-
 arch/arm64/kvm/hyp/vgic-v3-sr.c            | 130 +++++++++++++----------------
 17 files changed, 132 insertions(+), 147 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 4d0f8ea600ba..269a76cd51ff 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -516,7 +516,7 @@ static __always_inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_i
  * Skip an instruction which has been emulated at hyp while most guest sysregs
  * are live.
  */
-static __always_inline void __hyp_text __kvm_skip_instr(struct kvm_vcpu *vcpu)
+static __always_inline void __kvm_skip_instr(struct kvm_vcpu *vcpu)
 {
 	*vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR);
 	vcpu->arch.ctxt.gp_regs.regs.pstate = read_sysreg_el2(SYS_SPSR);
diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index 19f8b40fe6cf..46689e7db46c 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -12,8 +12,6 @@
 #include <asm/alternative.h>
 #include <asm/sysreg.h>
 
-#define __hyp_text __section(.hyp.text) notrace __noscs
-
 #define read_sysreg_elx(r,nvh,vh)					\
 	({								\
 		u64 reg;						\
diff --git a/arch/arm64/kvm/hyp/aarch32.c b/arch/arm64/kvm/hyp/aarch32.c
index 25c0e47d57cb..f9ff67dfbf0b 100644
--- a/arch/arm64/kvm/hyp/aarch32.c
+++ b/arch/arm64/kvm/hyp/aarch32.c
@@ -44,7 +44,7 @@ static const unsigned short cc_map[16] = {
 /*
  * Check if a trapped instruction should have been executed or not.
  */
-bool __hyp_text kvm_condition_valid32(const struct kvm_vcpu *vcpu)
+bool kvm_condition_valid32(const struct kvm_vcpu *vcpu)
 {
 	unsigned long cpsr;
 	u32 cpsr_cond;
@@ -93,7 +93,7 @@ bool __hyp_text kvm_condition_valid32(const struct kvm_vcpu *vcpu)
  *
  * IT[7:0] -> CPSR[26:25],CPSR[15:10]
  */
-static void __hyp_text kvm_adjust_itstate(struct kvm_vcpu *vcpu)
+static void kvm_adjust_itstate(struct kvm_vcpu *vcpu)
 {
 	unsigned long itbits, cond;
 	unsigned long cpsr = *vcpu_cpsr(vcpu);
@@ -123,7 +123,7 @@ static void __hyp_text kvm_adjust_itstate(struct kvm_vcpu *vcpu)
  * kvm_skip_instr - skip a trapped instruction and proceed to the next
  * @vcpu: The vcpu pointer
  */
-void __hyp_text kvm_skip_instr32(struct kvm_vcpu *vcpu, bool is_wide_instr)
+void kvm_skip_instr32(struct kvm_vcpu *vcpu, bool is_wide_instr)
 {
 	u32 pc = *vcpu_pc(vcpu);
 	bool is_thumb;
diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S
index 90186cf6473e..dfb4e6d359ab 100644
--- a/arch/arm64/kvm/hyp/entry.S
+++ b/arch/arm64/kvm/hyp/entry.S
@@ -21,7 +21,6 @@
 #define CPU_SP_EL0_OFFSET	(CPU_XREG_OFFSET(30) + 8)
 
 	.text
-	.pushsection	.hyp.text, "ax"
 
 /*
  * We treat x18 as callee-saved as the host may use it as a platform
diff --git a/arch/arm64/kvm/hyp/fpsimd.S b/arch/arm64/kvm/hyp/fpsimd.S
index 5b8ff517ff10..01f114aa47b0 100644
--- a/arch/arm64/kvm/hyp/fpsimd.S
+++ b/arch/arm64/kvm/hyp/fpsimd.S
@@ -9,7 +9,6 @@
 #include <asm/fpsimdmacros.h>
 
 	.text
-	.pushsection	.hyp.text, "ax"
 
 SYM_FUNC_START(__fpsimd_save_state)
 	fpsimd_save	x0, 1
diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S
index 8316ee67d6a0..689fccbc9de7 100644
--- a/arch/arm64/kvm/hyp/hyp-entry.S
+++ b/arch/arm64/kvm/hyp/hyp-entry.S
@@ -16,7 +16,6 @@
 #include <asm/mmu.h>
 
 	.text
-	.pushsection	.hyp.text, "ax"
 
 .macro do_el2_call
 	/*
diff --git a/arch/arm64/kvm/hyp/include/hyp/debug-sr.h b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
index e041dbd23243..24e8acf9ec10 100644
--- a/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
@@ -88,9 +88,9 @@
 	default:	write_debug(ptr[0], reg, 0);			\
 	}
 
-static inline void __hyp_text __debug_save_state(struct kvm_vcpu *vcpu,
-						 struct kvm_guest_debug_arch *dbg,
-						 struct kvm_cpu_context *ctxt)
+static inline void __debug_save_state(struct kvm_vcpu *vcpu,
+				      struct kvm_guest_debug_arch *dbg,
+				      struct kvm_cpu_context *ctxt)
 {
 	u64 aa64dfr0;
 	int brps, wrps;
@@ -107,9 +107,9 @@ static inline void __hyp_text __debug_save_state(struct kvm_vcpu *vcpu,
 	ctxt->sys_regs[MDCCINT_EL1] = read_sysreg(mdccint_el1);
 }
 
-static inline void __hyp_text __debug_restore_state(struct kvm_vcpu *vcpu,
-						    struct kvm_guest_debug_arch *dbg,
-						    struct kvm_cpu_context *ctxt)
+static inline void __debug_restore_state(struct kvm_vcpu *vcpu,
+					 struct kvm_guest_debug_arch *dbg,
+					 struct kvm_cpu_context *ctxt)
 {
 	u64 aa64dfr0;
 	int brps, wrps;
@@ -127,7 +127,7 @@ static inline void __hyp_text __debug_restore_state(struct kvm_vcpu *vcpu,
 	write_sysreg(ctxt->sys_regs[MDCCINT_EL1], mdccint_el1);
 }
 
-static inline void __hyp_text __debug_switch_to_guest_common(struct kvm_vcpu *vcpu)
+static inline void __debug_switch_to_guest_common(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpu_context *host_ctxt;
 	struct kvm_cpu_context *guest_ctxt;
@@ -146,7 +146,7 @@ static inline void __hyp_text __debug_switch_to_guest_common(struct kvm_vcpu *vc
 	__debug_restore_state(vcpu, guest_dbg, guest_ctxt);
 }
 
-static inline void __hyp_text __debug_switch_to_host_common(struct kvm_vcpu *vcpu)
+static inline void __debug_switch_to_host_common(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpu_context *host_ctxt;
 	struct kvm_cpu_context *guest_ctxt;
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 65d2a879b93b..8f622688fa64 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -30,7 +30,7 @@
 extern const char __hyp_panic_string[];
 
 /* Check whether the FP regs were dirtied while in the host-side run loop: */
-static inline bool __hyp_text update_fp_enabled(struct kvm_vcpu *vcpu)
+static inline bool update_fp_enabled(struct kvm_vcpu *vcpu)
 {
 	/*
 	 * When the system doesn't support FP/SIMD, we cannot rely on
@@ -48,7 +48,7 @@ static inline bool __hyp_text update_fp_enabled(struct kvm_vcpu *vcpu)
 }
 
 /* Save the 32-bit only FPSIMD system register state */
-static inline void __hyp_text __fpsimd_save_fpexc32(struct kvm_vcpu *vcpu)
+static inline void __fpsimd_save_fpexc32(struct kvm_vcpu *vcpu)
 {
 	if (!vcpu_el1_is_32bit(vcpu))
 		return;
@@ -56,7 +56,7 @@ static inline void __hyp_text __fpsimd_save_fpexc32(struct kvm_vcpu *vcpu)
 	vcpu->arch.ctxt.sys_regs[FPEXC32_EL2] = read_sysreg(fpexc32_el2);
 }
 
-static inline void __hyp_text __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
+static inline void __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
 {
 	/*
 	 * We are about to set CPTR_EL2.TFP to trap all floating point
@@ -73,7 +73,7 @@ static inline void __hyp_text __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
 	}
 }
 
-static inline void __hyp_text __activate_traps_common(struct kvm_vcpu *vcpu)
+static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
 {
 	/* Trap on AArch32 cp15 c15 (impdef sysregs) accesses (EL1 or EL0) */
 	write_sysreg(1 << 15, hstr_el2);
@@ -89,13 +89,13 @@ static inline void __hyp_text __activate_traps_common(struct kvm_vcpu *vcpu)
 	write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2);
 }
 
-static inline void __hyp_text __deactivate_traps_common(void)
+static inline void __deactivate_traps_common(void)
 {
 	write_sysreg(0, hstr_el2);
 	write_sysreg(0, pmuserenr_el0);
 }
 
-static inline void __hyp_text ___activate_traps(struct kvm_vcpu *vcpu)
+static inline void ___activate_traps(struct kvm_vcpu *vcpu)
 {
 	u64 hcr = vcpu->arch.hcr_el2;
 
@@ -108,7 +108,7 @@ static inline void __hyp_text ___activate_traps(struct kvm_vcpu *vcpu)
 		write_sysreg_s(vcpu->arch.vsesr_el2, SYS_VSESR_EL2);
 }
 
-static inline void __hyp_text ___deactivate_traps(struct kvm_vcpu *vcpu)
+static inline void ___deactivate_traps(struct kvm_vcpu *vcpu)
 {
 	/*
 	 * If we pended a virtual abort, preserve it until it gets
@@ -122,12 +122,12 @@ static inline void __hyp_text ___deactivate_traps(struct kvm_vcpu *vcpu)
 	}
 }
 
-static inline void __hyp_text __activate_vm(struct kvm *kvm)
+static inline void __activate_vm(struct kvm *kvm)
 {
 	__load_guest_stage2(kvm);
 }
 
-static inline bool __hyp_text __translate_far_to_hpfar(u64 far, u64 *hpfar)
+static inline bool __translate_far_to_hpfar(u64 far, u64 *hpfar)
 {
 	u64 par, tmp;
 
@@ -156,7 +156,7 @@ static inline bool __hyp_text __translate_far_to_hpfar(u64 far, u64 *hpfar)
 	return true;
 }
 
-static inline bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu)
+static inline bool __populate_fault_info(struct kvm_vcpu *vcpu)
 {
 	u8 ec;
 	u64 esr;
@@ -196,7 +196,7 @@ static inline bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu)
 }
 
 /* Check for an FPSIMD/SVE trap and handle as appropriate */
-static inline bool __hyp_text __hyp_handle_fpsimd(struct kvm_vcpu *vcpu)
+static inline bool __hyp_handle_fpsimd(struct kvm_vcpu *vcpu)
 {
 	bool vhe, sve_guest, sve_host;
 	u8 hsr_ec;
@@ -283,7 +283,7 @@ static inline bool __hyp_text __hyp_handle_fpsimd(struct kvm_vcpu *vcpu)
 	return true;
 }
 
-static inline bool __hyp_text handle_tx2_tvm(struct kvm_vcpu *vcpu)
+static inline bool handle_tx2_tvm(struct kvm_vcpu *vcpu)
 {
 	u32 sysreg = esr_sys64_to_sysreg(kvm_vcpu_get_hsr(vcpu));
 	int rt = kvm_vcpu_sys_get_rt(vcpu);
@@ -338,7 +338,7 @@ static inline bool __hyp_text handle_tx2_tvm(struct kvm_vcpu *vcpu)
 	return true;
 }
 
-static inline bool __hyp_text esr_is_ptrauth_trap(u32 esr)
+static inline bool esr_is_ptrauth_trap(u32 esr)
 {
 	u32 ec = ESR_ELx_EC(esr);
 
@@ -371,7 +371,7 @@ static inline bool __hyp_text esr_is_ptrauth_trap(u32 esr)
 	regs[key ## KEYHI_EL1] = read_sysreg_s(SYS_ ## key ## KEYHI_EL1);	\
 })
 
-static inline bool __hyp_text __hyp_handle_ptrauth(struct kvm_vcpu *vcpu)
+static inline bool __hyp_handle_ptrauth(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpu_context *ctxt;
 	u64 val;
@@ -401,7 +401,7 @@ static inline bool __hyp_text __hyp_handle_ptrauth(struct kvm_vcpu *vcpu)
  * the guest, false when we should restore the host state and return to the
  * main run loop.
  */
-static inline bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
+static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
 {
 	if (ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ)
 		vcpu->arch.fault.esr_el2 = read_sysreg_el2(SYS_ESR);
@@ -473,7 +473,7 @@ exit:
 	return false;
 }
 
-static inline bool __hyp_text __needs_ssbd_off(struct kvm_vcpu *vcpu)
+static inline bool __needs_ssbd_off(struct kvm_vcpu *vcpu)
 {
 	if (!cpus_have_final_cap(ARM64_SSBD))
 		return false;
@@ -481,7 +481,7 @@ static inline bool __hyp_text __needs_ssbd_off(struct kvm_vcpu *vcpu)
 	return !(vcpu->arch.workaround_flags & VCPU_WORKAROUND_2_FLAG);
 }
 
-static inline void __hyp_text __set_guest_arch_workaround_state(struct kvm_vcpu *vcpu)
+static inline void __set_guest_arch_workaround_state(struct kvm_vcpu *vcpu)
 {
 #ifdef CONFIG_ARM64_SSBD
 	/*
@@ -494,7 +494,7 @@ static inline void __hyp_text __set_guest_arch_workaround_state(struct kvm_vcpu
 #endif
 }
 
-static inline void __hyp_text __set_host_arch_workaround_state(struct kvm_vcpu *vcpu)
+static inline void __set_host_arch_workaround_state(struct kvm_vcpu *vcpu)
 {
 #ifdef CONFIG_ARM64_SSBD
 	/*
diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
index 3e0585fbd403..6e04e061f762 100644
--- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
@@ -15,18 +15,18 @@
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_hyp.h>
 
-static inline void __hyp_text __sysreg_save_common_state(struct kvm_cpu_context *ctxt)
+static inline void __sysreg_save_common_state(struct kvm_cpu_context *ctxt)
 {
 	ctxt->sys_regs[MDSCR_EL1]	= read_sysreg(mdscr_el1);
 }
 
-static inline void __hyp_text __sysreg_save_user_state(struct kvm_cpu_context *ctxt)
+static inline void __sysreg_save_user_state(struct kvm_cpu_context *ctxt)
 {
 	ctxt->sys_regs[TPIDR_EL0]	= read_sysreg(tpidr_el0);
 	ctxt->sys_regs[TPIDRRO_EL0]	= read_sysreg(tpidrro_el0);
 }
 
-static inline void __hyp_text __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
+static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
 {
 	ctxt->sys_regs[CSSELR_EL1]	= read_sysreg(csselr_el1);
 	ctxt->sys_regs[SCTLR_EL1]	= read_sysreg_el1(SYS_SCTLR);
@@ -51,7 +51,7 @@ static inline void __hyp_text __sysreg_save_el1_state(struct kvm_cpu_context *ct
 	ctxt->gp_regs.spsr[KVM_SPSR_EL1]= read_sysreg_el1(SYS_SPSR);
 }
 
-static inline void __hyp_text __sysreg_save_el2_return_state(struct kvm_cpu_context *ctxt)
+static inline void __sysreg_save_el2_return_state(struct kvm_cpu_context *ctxt)
 {
 	ctxt->gp_regs.regs.pc		= read_sysreg_el2(SYS_ELR);
 	ctxt->gp_regs.regs.pstate	= read_sysreg_el2(SYS_SPSR);
@@ -60,18 +60,18 @@ static inline void __hyp_text __sysreg_save_el2_return_state(struct kvm_cpu_cont
 		ctxt->sys_regs[DISR_EL1] = read_sysreg_s(SYS_VDISR_EL2);
 }
 
-static inline void __hyp_text __sysreg_restore_common_state(struct kvm_cpu_context *ctxt)
+static inline void __sysreg_restore_common_state(struct kvm_cpu_context *ctxt)
 {
 	write_sysreg(ctxt->sys_regs[MDSCR_EL1],	  mdscr_el1);
 }
 
-static inline void __hyp_text __sysreg_restore_user_state(struct kvm_cpu_context *ctxt)
+static inline void __sysreg_restore_user_state(struct kvm_cpu_context *ctxt)
 {
 	write_sysreg(ctxt->sys_regs[TPIDR_EL0],		tpidr_el0);
 	write_sysreg(ctxt->sys_regs[TPIDRRO_EL0],	tpidrro_el0);
 }
 
-static inline void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
+static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
 {
 	write_sysreg(ctxt->sys_regs[MPIDR_EL1],		vmpidr_el2);
 	write_sysreg(ctxt->sys_regs[CSSELR_EL1],	csselr_el1);
@@ -130,7 +130,7 @@ static inline void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context
 	write_sysreg_el1(ctxt->gp_regs.spsr[KVM_SPSR_EL1],SYS_SPSR);
 }
 
-static inline void __hyp_text __sysreg_restore_el2_return_state(struct kvm_cpu_context *ctxt)
+static inline void __sysreg_restore_el2_return_state(struct kvm_cpu_context *ctxt)
 {
 	u64 pstate = ctxt->gp_regs.regs.pstate;
 	u64 mode = pstate & PSR_AA32_MODE_MASK;
@@ -156,7 +156,7 @@ static inline void __hyp_text __sysreg_restore_el2_return_state(struct kvm_cpu_c
 		write_sysreg_s(ctxt->sys_regs[DISR_EL1], SYS_VDISR_EL2);
 }
 
-static inline void __hyp_text __sysreg32_save_state(struct kvm_vcpu *vcpu)
+static inline void __sysreg32_save_state(struct kvm_vcpu *vcpu)
 {
 	u64 *spsr, *sysreg;
 
@@ -178,7 +178,7 @@ static inline void __hyp_text __sysreg32_save_state(struct kvm_vcpu *vcpu)
 		sysreg[DBGVCR32_EL2] = read_sysreg(dbgvcr32_el2);
 }
 
-static inline void __hyp_text __sysreg32_restore_state(struct kvm_vcpu *vcpu)
+static inline void __sysreg32_restore_state(struct kvm_vcpu *vcpu)
 {
 	u64 *spsr, *sysreg;
 
diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile
index ad8729f5e814..0b34414557d6 100644
--- a/arch/arm64/kvm/hyp/nvhe/Makefile
+++ b/arch/arm64/kvm/hyp/nvhe/Makefile
@@ -21,7 +21,13 @@ $(obj)/%.hyp.o: $(obj)/%.hyp.tmp.o FORCE
 	$(call if_changed,hypcopy)
 
 quiet_cmd_hypcopy = HYPCOPY $@
-      cmd_hypcopy = $(OBJCOPY) --prefix-symbols=__kvm_nvhe_ $< $@
+      cmd_hypcopy = $(OBJCOPY)	--prefix-symbols=__kvm_nvhe_		\
+				--rename-section=.text=.hyp.text	\
+				$< $@
+
+# Remove ftrace and Shadow Call Stack CFLAGS.
+# This is equivalent to the 'notrace' and '__noscs' annotations.
+KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS), $(KBUILD_CFLAGS))
 
 # KVM nVHE code is run at a different exception code with a different map, so
 # compiler instrumentation that inserts callbacks or checks into the code may
diff --git a/arch/arm64/kvm/hyp/nvhe/debug-sr.c b/arch/arm64/kvm/hyp/nvhe/debug-sr.c
index 828c0d48e790..91a711aa8382 100644
--- a/arch/arm64/kvm/hyp/nvhe/debug-sr.c
+++ b/arch/arm64/kvm/hyp/nvhe/debug-sr.c
@@ -14,7 +14,7 @@
 #include <asm/kvm_hyp.h>
 #include <asm/kvm_mmu.h>
 
-static void __hyp_text __debug_save_spe(u64 *pmscr_el1)
+static void __debug_save_spe(u64 *pmscr_el1)
 {
 	u64 reg;
 
@@ -46,7 +46,7 @@ static void __hyp_text __debug_save_spe(u64 *pmscr_el1)
 	dsb(nsh);
 }
 
-static void __hyp_text __debug_restore_spe(u64 pmscr_el1)
+static void __debug_restore_spe(u64 pmscr_el1)
 {
 	if (!pmscr_el1)
 		return;
@@ -58,20 +58,20 @@ static void __hyp_text __debug_restore_spe(u64 pmscr_el1)
 	write_sysreg_s(pmscr_el1, SYS_PMSCR_EL1);
 }
 
-void __hyp_text __debug_switch_to_guest(struct kvm_vcpu *vcpu)
+void __debug_switch_to_guest(struct kvm_vcpu *vcpu)
 {
 	/* Disable and flush SPE data generation */
 	__debug_save_spe(&vcpu->arch.host_debug_state.pmscr_el1);
 	__debug_switch_to_guest_common(vcpu);
 }
 
-void __hyp_text __debug_switch_to_host(struct kvm_vcpu *vcpu)
+void __debug_switch_to_host(struct kvm_vcpu *vcpu)
 {
 	__debug_restore_spe(vcpu->arch.host_debug_state.pmscr_el1);
 	__debug_switch_to_host_common(vcpu);
 }
 
-u32 __hyp_text __kvm_get_mdcr_el2(void)
+u32 __kvm_get_mdcr_el2(void)
 {
 	return read_sysreg(mdcr_el2);
 }
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index f08bfb951df6..a1dcf59bd45e 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -27,7 +27,7 @@
 #include <asm/processor.h>
 #include <asm/thread_info.h>
 
-static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu)
+static void __activate_traps(struct kvm_vcpu *vcpu)
 {
 	u64 val;
 
@@ -58,7 +58,7 @@ static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu)
 	}
 }
 
-static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu)
+static void __deactivate_traps(struct kvm_vcpu *vcpu)
 {
 	u64 mdcr_el2;
 
@@ -93,13 +93,13 @@ static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu)
 	write_sysreg(CPTR_EL2_DEFAULT, cptr_el2);
 }
 
-static void __hyp_text __deactivate_vm(struct kvm_vcpu *vcpu)
+static void __deactivate_vm(struct kvm_vcpu *vcpu)
 {
 	write_sysreg(0, vttbr_el2);
 }
 
 /* Save VGICv3 state on non-VHE systems */
-static void __hyp_text __hyp_vgic_save_state(struct kvm_vcpu *vcpu)
+static void __hyp_vgic_save_state(struct kvm_vcpu *vcpu)
 {
 	if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) {
 		__vgic_v3_save_state(&vcpu->arch.vgic_cpu.vgic_v3);
@@ -108,7 +108,7 @@ static void __hyp_text __hyp_vgic_save_state(struct kvm_vcpu *vcpu)
 }
 
 /* Restore VGICv3 state on non_VEH systems */
-static void __hyp_text __hyp_vgic_restore_state(struct kvm_vcpu *vcpu)
+static void __hyp_vgic_restore_state(struct kvm_vcpu *vcpu)
 {
 	if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) {
 		__vgic_v3_activate_traps(&vcpu->arch.vgic_cpu.vgic_v3);
@@ -119,7 +119,7 @@ static void __hyp_text __hyp_vgic_restore_state(struct kvm_vcpu *vcpu)
 /**
  * Disable host events, enable guest events
  */
-static bool __hyp_text __pmu_switch_to_guest(struct kvm_cpu_context *host_ctxt)
+static bool __pmu_switch_to_guest(struct kvm_cpu_context *host_ctxt)
 {
 	struct kvm_host_data *host;
 	struct kvm_pmu_events *pmu;
@@ -139,7 +139,7 @@ static bool __hyp_text __pmu_switch_to_guest(struct kvm_cpu_context *host_ctxt)
 /**
  * Disable guest events, enable host events
  */
-static void __hyp_text __pmu_switch_to_host(struct kvm_cpu_context *host_ctxt)
+static void __pmu_switch_to_host(struct kvm_cpu_context *host_ctxt)
 {
 	struct kvm_host_data *host;
 	struct kvm_pmu_events *pmu;
@@ -155,7 +155,7 @@ static void __hyp_text __pmu_switch_to_host(struct kvm_cpu_context *host_ctxt)
 }
 
 /* Switch to the guest for legacy non-VHE systems */
-int __hyp_text __kvm_vcpu_run(struct kvm_vcpu *vcpu)
+int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpu_context *host_ctxt;
 	struct kvm_cpu_context *guest_ctxt;
@@ -242,7 +242,7 @@ int __hyp_text __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 	return exit_code;
 }
 
-void __hyp_text __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt)
+void __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt)
 {
 	u64 spsr = read_sysreg_el2(SYS_SPSR);
 	u64 elr = read_sysreg_el2(SYS_ELR);
diff --git a/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c b/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c
index 710cf28ab1ec..88a25fc8fcd3 100644
--- a/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c
@@ -18,7 +18,7 @@
  * Non-VHE: Both host and guest must save everything.
  */
 
-void __hyp_text __sysreg_save_state_nvhe(struct kvm_cpu_context *ctxt)
+void __sysreg_save_state_nvhe(struct kvm_cpu_context *ctxt)
 {
 	__sysreg_save_el1_state(ctxt);
 	__sysreg_save_common_state(ctxt);
@@ -26,7 +26,7 @@ void __hyp_text __sysreg_save_state_nvhe(struct kvm_cpu_context *ctxt)
 	__sysreg_save_el2_return_state(ctxt);
 }
 
-void __hyp_text __sysreg_restore_state_nvhe(struct kvm_cpu_context *ctxt)
+void __sysreg_restore_state_nvhe(struct kvm_cpu_context *ctxt)
 {
 	__sysreg_restore_el1_state(ctxt);
 	__sysreg_restore_common_state(ctxt);
@@ -34,7 +34,7 @@ void __hyp_text __sysreg_restore_state_nvhe(struct kvm_cpu_context *ctxt)
 	__sysreg_restore_el2_return_state(ctxt);
 }
 
-void __hyp_text __kvm_enable_ssbs(void)
+void __kvm_enable_ssbs(void)
 {
 	u64 tmp;
 
diff --git a/arch/arm64/kvm/hyp/nvhe/timer-sr.c b/arch/arm64/kvm/hyp/nvhe/timer-sr.c
index 42c8ed71d06e..9072e71693ba 100644
--- a/arch/arm64/kvm/hyp/nvhe/timer-sr.c
+++ b/arch/arm64/kvm/hyp/nvhe/timer-sr.c
@@ -19,7 +19,7 @@ void __kvm_timer_set_cntvoff(u64 cntvoff)
  * Should only be called on non-VHE systems.
  * VHE systems use EL2 timers and configure EL1 timers in kvm_timer_init_vhe().
  */
-void __hyp_text __timer_disable_traps(struct kvm_vcpu *vcpu)
+void __timer_disable_traps(struct kvm_vcpu *vcpu)
 {
 	u64 val;
 
@@ -33,7 +33,7 @@ void __hyp_text __timer_disable_traps(struct kvm_vcpu *vcpu)
  * Should only be called on non-VHE systems.
  * VHE systems use EL2 timers and configure EL1 timers in kvm_timer_init_vhe().
  */
-void __hyp_text __timer_enable_traps(struct kvm_vcpu *vcpu)
+void __timer_enable_traps(struct kvm_vcpu *vcpu)
 {
 	u64 val;
 
diff --git a/arch/arm64/kvm/hyp/nvhe/tlb.c b/arch/arm64/kvm/hyp/nvhe/tlb.c
index deb48c8c00ee..d4475f8340c4 100644
--- a/arch/arm64/kvm/hyp/nvhe/tlb.c
+++ b/arch/arm64/kvm/hyp/nvhe/tlb.c
@@ -12,8 +12,7 @@ struct tlb_inv_context {
 	u64		tcr;
 };
 
-static void __hyp_text __tlb_switch_to_guest(struct kvm *kvm,
-					     struct tlb_inv_context *cxt)
+static void __tlb_switch_to_guest(struct kvm *kvm, struct tlb_inv_context *cxt)
 {
 	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
 		u64 val;
@@ -36,8 +35,7 @@ static void __hyp_text __tlb_switch_to_guest(struct kvm *kvm,
 	asm(ALTERNATIVE("isb", "nop", ARM64_WORKAROUND_SPECULATIVE_AT));
 }
 
-static void __hyp_text __tlb_switch_to_host(struct kvm *kvm,
-					    struct tlb_inv_context *cxt)
+static void __tlb_switch_to_host(struct kvm *kvm, struct tlb_inv_context *cxt)
 {
 	write_sysreg(0, vttbr_el2);
 
@@ -49,7 +47,7 @@ static void __hyp_text __tlb_switch_to_host(struct kvm *kvm,
 	}
 }
 
-void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
+void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 {
 	struct tlb_inv_context cxt;
 
@@ -103,7 +101,7 @@ void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 	__tlb_switch_to_host(kvm, &cxt);
 }
 
-void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm)
+void __kvm_tlb_flush_vmid(struct kvm *kvm)
 {
 	struct tlb_inv_context cxt;
 
@@ -120,7 +118,7 @@ void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm)
 	__tlb_switch_to_host(kvm, &cxt);
 }
 
-void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
+void __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
 {
 	struct kvm *kvm = kern_hyp_va(kern_hyp_va(vcpu)->kvm);
 	struct tlb_inv_context cxt;
@@ -135,7 +133,7 @@ void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
 	__tlb_switch_to_host(kvm, &cxt);
 }
 
-void __hyp_text __kvm_flush_vm_context(void)
+void __kvm_flush_vm_context(void)
 {
 	dsb(ishst);
 	__tlbi(alle1is);
diff --git a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
index 4f3a087e36d5..bd1bab551d48 100644
--- a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
+++ b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
@@ -13,7 +13,7 @@
 #include <asm/kvm_hyp.h>
 #include <asm/kvm_mmu.h>
 
-static bool __hyp_text __is_be(struct kvm_vcpu *vcpu)
+static bool __is_be(struct kvm_vcpu *vcpu)
 {
 	if (vcpu_mode_is_32bit(vcpu))
 		return !!(read_sysreg_el2(SYS_SPSR) & PSR_AA32_E_BIT);
@@ -32,7 +32,7 @@ static bool __hyp_text __is_be(struct kvm_vcpu *vcpu)
  *  0: Not a GICV access
  * -1: Illegal GICV access successfully performed
  */
-int __hyp_text __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu)
+int __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu)
 {
 	struct kvm *kvm = kern_hyp_va(vcpu->kvm);
 	struct vgic_dist *vgic = &kvm->arch.vgic;
diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c
index 10ed539835c1..d31eb6266f2e 100644
--- a/arch/arm64/kvm/hyp/vgic-v3-sr.c
+++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c
@@ -16,7 +16,7 @@
 #define vtr_to_nr_pre_bits(v)		((((u32)(v) >> 26) & 7) + 1)
 #define vtr_to_nr_apr_regs(v)		(1 << (vtr_to_nr_pre_bits(v) - 5))
 
-static u64 __hyp_text __gic_v3_get_lr(unsigned int lr)
+static u64 __gic_v3_get_lr(unsigned int lr)
 {
 	switch (lr & 0xf) {
 	case 0:
@@ -56,7 +56,7 @@ static u64 __hyp_text __gic_v3_get_lr(unsigned int lr)
 	unreachable();
 }
 
-static void __hyp_text __gic_v3_set_lr(u64 val, int lr)
+static void __gic_v3_set_lr(u64 val, int lr)
 {
 	switch (lr & 0xf) {
 	case 0:
@@ -110,7 +110,7 @@ static void __hyp_text __gic_v3_set_lr(u64 val, int lr)
 	}
 }
 
-static void __hyp_text __vgic_v3_write_ap0rn(u32 val, int n)
+static void __vgic_v3_write_ap0rn(u32 val, int n)
 {
 	switch (n) {
 	case 0:
@@ -128,7 +128,7 @@ static void __hyp_text __vgic_v3_write_ap0rn(u32 val, int n)
 	}
 }
 
-static void __hyp_text __vgic_v3_write_ap1rn(u32 val, int n)
+static void __vgic_v3_write_ap1rn(u32 val, int n)
 {
 	switch (n) {
 	case 0:
@@ -146,7 +146,7 @@ static void __hyp_text __vgic_v3_write_ap1rn(u32 val, int n)
 	}
 }
 
-static u32 __hyp_text __vgic_v3_read_ap0rn(int n)
+static u32 __vgic_v3_read_ap0rn(int n)
 {
 	u32 val;
 
@@ -170,7 +170,7 @@ static u32 __hyp_text __vgic_v3_read_ap0rn(int n)
 	return val;
 }
 
-static u32 __hyp_text __vgic_v3_read_ap1rn(int n)
+static u32 __vgic_v3_read_ap1rn(int n)
 {
 	u32 val;
 
@@ -194,7 +194,7 @@ static u32 __hyp_text __vgic_v3_read_ap1rn(int n)
 	return val;
 }
 
-void __hyp_text __vgic_v3_save_state(struct vgic_v3_cpu_if *cpu_if)
+void __vgic_v3_save_state(struct vgic_v3_cpu_if *cpu_if)
 {
 	u64 used_lrs = cpu_if->used_lrs;
 
@@ -229,7 +229,7 @@ void __hyp_text __vgic_v3_save_state(struct vgic_v3_cpu_if *cpu_if)
 	}
 }
 
-void __hyp_text __vgic_v3_restore_state(struct vgic_v3_cpu_if *cpu_if)
+void __vgic_v3_restore_state(struct vgic_v3_cpu_if *cpu_if)
 {
 	u64 used_lrs = cpu_if->used_lrs;
 	int i;
@@ -255,7 +255,7 @@ void __hyp_text __vgic_v3_restore_state(struct vgic_v3_cpu_if *cpu_if)
 	}
 }
 
-void __hyp_text __vgic_v3_activate_traps(struct vgic_v3_cpu_if *cpu_if)
+void __vgic_v3_activate_traps(struct vgic_v3_cpu_if *cpu_if)
 {
 	/*
 	 * VFIQEn is RES1 if ICC_SRE_EL1.SRE is 1. This causes a
@@ -302,7 +302,7 @@ void __hyp_text __vgic_v3_activate_traps(struct vgic_v3_cpu_if *cpu_if)
 		write_gicreg(cpu_if->vgic_hcr, ICH_HCR_EL2);
 }
 
-void __hyp_text __vgic_v3_deactivate_traps(struct vgic_v3_cpu_if *cpu_if)
+void __vgic_v3_deactivate_traps(struct vgic_v3_cpu_if *cpu_if)
 {
 	u64 val;
 
@@ -328,7 +328,7 @@ void __hyp_text __vgic_v3_deactivate_traps(struct vgic_v3_cpu_if *cpu_if)
 		write_gicreg(0, ICH_HCR_EL2);
 }
 
-void __hyp_text __vgic_v3_save_aprs(struct vgic_v3_cpu_if *cpu_if)
+void __vgic_v3_save_aprs(struct vgic_v3_cpu_if *cpu_if)
 {
 	u64 val;
 	u32 nr_pre_bits;
@@ -361,7 +361,7 @@ void __hyp_text __vgic_v3_save_aprs(struct vgic_v3_cpu_if *cpu_if)
 	}
 }
 
-void __hyp_text __vgic_v3_restore_aprs(struct vgic_v3_cpu_if *cpu_if)
+void __vgic_v3_restore_aprs(struct vgic_v3_cpu_if *cpu_if)
 {
 	u64 val;
 	u32 nr_pre_bits;
@@ -394,7 +394,7 @@ void __hyp_text __vgic_v3_restore_aprs(struct vgic_v3_cpu_if *cpu_if)
 	}
 }
 
-void __hyp_text __vgic_v3_init_lrs(void)
+void __vgic_v3_init_lrs(void)
 {
 	int max_lr_idx = vtr_to_max_lr_idx(read_gicreg(ICH_VTR_EL2));
 	int i;
@@ -403,28 +403,28 @@ void __hyp_text __vgic_v3_init_lrs(void)
 		__gic_v3_set_lr(0, i);
 }
 
-u64 __hyp_text __vgic_v3_get_ich_vtr_el2(void)
+u64 __vgic_v3_get_ich_vtr_el2(void)
 {
 	return read_gicreg(ICH_VTR_EL2);
 }
 
-u64 __hyp_text __vgic_v3_read_vmcr(void)
+u64 __vgic_v3_read_vmcr(void)
 {
 	return read_gicreg(ICH_VMCR_EL2);
 }
 
-void __hyp_text __vgic_v3_write_vmcr(u32 vmcr)
+void __vgic_v3_write_vmcr(u32 vmcr)
 {
 	write_gicreg(vmcr, ICH_VMCR_EL2);
 }
 
-static int __hyp_text __vgic_v3_bpr_min(void)
+static int __vgic_v3_bpr_min(void)
 {
 	/* See Pseudocode for VPriorityGroup */
 	return 8 - vtr_to_nr_pre_bits(read_gicreg(ICH_VTR_EL2));
 }
 
-static int __hyp_text __vgic_v3_get_group(struct kvm_vcpu *vcpu)
+static int __vgic_v3_get_group(struct kvm_vcpu *vcpu)
 {
 	u32 esr = kvm_vcpu_get_hsr(vcpu);
 	u8 crm = (esr & ESR_ELx_SYS64_ISS_CRM_MASK) >> ESR_ELx_SYS64_ISS_CRM_SHIFT;
@@ -434,9 +434,8 @@ static int __hyp_text __vgic_v3_get_group(struct kvm_vcpu *vcpu)
 
 #define GICv3_IDLE_PRIORITY	0xff
 
-static int __hyp_text __vgic_v3_highest_priority_lr(struct kvm_vcpu *vcpu,
-						    u32 vmcr,
-						    u64 *lr_val)
+static int __vgic_v3_highest_priority_lr(struct kvm_vcpu *vcpu, u32 vmcr,
+					 u64 *lr_val)
 {
 	unsigned int used_lrs = vcpu->arch.vgic_cpu.vgic_v3.used_lrs;
 	u8 priority = GICv3_IDLE_PRIORITY;
@@ -474,8 +473,8 @@ static int __hyp_text __vgic_v3_highest_priority_lr(struct kvm_vcpu *vcpu,
 	return lr;
 }
 
-static int __hyp_text __vgic_v3_find_active_lr(struct kvm_vcpu *vcpu,
-					       int intid, u64 *lr_val)
+static int __vgic_v3_find_active_lr(struct kvm_vcpu *vcpu, int intid,
+				    u64 *lr_val)
 {
 	unsigned int used_lrs = vcpu->arch.vgic_cpu.vgic_v3.used_lrs;
 	int i;
@@ -494,7 +493,7 @@ static int __hyp_text __vgic_v3_find_active_lr(struct kvm_vcpu *vcpu,
 	return -1;
 }
 
-static int __hyp_text __vgic_v3_get_highest_active_priority(void)
+static int __vgic_v3_get_highest_active_priority(void)
 {
 	u8 nr_apr_regs = vtr_to_nr_apr_regs(read_gicreg(ICH_VTR_EL2));
 	u32 hap = 0;
@@ -526,12 +525,12 @@ static int __hyp_text __vgic_v3_get_highest_active_priority(void)
 	return GICv3_IDLE_PRIORITY;
 }
 
-static unsigned int __hyp_text __vgic_v3_get_bpr0(u32 vmcr)
+static unsigned int __vgic_v3_get_bpr0(u32 vmcr)
 {
 	return (vmcr & ICH_VMCR_BPR0_MASK) >> ICH_VMCR_BPR0_SHIFT;
 }
 
-static unsigned int __hyp_text __vgic_v3_get_bpr1(u32 vmcr)
+static unsigned int __vgic_v3_get_bpr1(u32 vmcr)
 {
 	unsigned int bpr;
 
@@ -550,7 +549,7 @@ static unsigned int __hyp_text __vgic_v3_get_bpr1(u32 vmcr)
  * Convert a priority to a preemption level, taking the relevant BPR
  * into account by zeroing the sub-priority bits.
  */
-static u8 __hyp_text __vgic_v3_pri_to_pre(u8 pri, u32 vmcr, int grp)
+static u8 __vgic_v3_pri_to_pre(u8 pri, u32 vmcr, int grp)
 {
 	unsigned int bpr;
 
@@ -568,7 +567,7 @@ static u8 __hyp_text __vgic_v3_pri_to_pre(u8 pri, u32 vmcr, int grp)
  * matter what the guest does with its BPR, we can always set/get the
  * same value of a priority.
  */
-static void __hyp_text __vgic_v3_set_active_priority(u8 pri, u32 vmcr, int grp)
+static void __vgic_v3_set_active_priority(u8 pri, u32 vmcr, int grp)
 {
 	u8 pre, ap;
 	u32 val;
@@ -587,7 +586,7 @@ static void __hyp_text __vgic_v3_set_active_priority(u8 pri, u32 vmcr, int grp)
 	}
 }
 
-static int __hyp_text __vgic_v3_clear_highest_active_priority(void)
+static int __vgic_v3_clear_highest_active_priority(void)
 {
 	u8 nr_apr_regs = vtr_to_nr_apr_regs(read_gicreg(ICH_VTR_EL2));
 	u32 hap = 0;
@@ -625,7 +624,7 @@ static int __hyp_text __vgic_v3_clear_highest_active_priority(void)
 	return GICv3_IDLE_PRIORITY;
 }
 
-static void __hyp_text __vgic_v3_read_iar(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
+static void __vgic_v3_read_iar(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	u64 lr_val;
 	u8 lr_prio, pmr;
@@ -661,7 +660,7 @@ spurious:
 	vcpu_set_reg(vcpu, rt, ICC_IAR1_EL1_SPURIOUS);
 }
 
-static void __hyp_text __vgic_v3_clear_active_lr(int lr, u64 lr_val)
+static void __vgic_v3_clear_active_lr(int lr, u64 lr_val)
 {
 	lr_val &= ~ICH_LR_ACTIVE_BIT;
 	if (lr_val & ICH_LR_HW) {
@@ -674,7 +673,7 @@ static void __hyp_text __vgic_v3_clear_active_lr(int lr, u64 lr_val)
 	__gic_v3_set_lr(lr_val, lr);
 }
 
-static void __hyp_text __vgic_v3_bump_eoicount(void)
+static void __vgic_v3_bump_eoicount(void)
 {
 	u32 hcr;
 
@@ -683,8 +682,7 @@ static void __hyp_text __vgic_v3_bump_eoicount(void)
 	write_gicreg(hcr, ICH_HCR_EL2);
 }
 
-static void __hyp_text __vgic_v3_write_dir(struct kvm_vcpu *vcpu,
-					   u32 vmcr, int rt)
+static void __vgic_v3_write_dir(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	u32 vid = vcpu_get_reg(vcpu, rt);
 	u64 lr_val;
@@ -707,7 +705,7 @@ static void __hyp_text __vgic_v3_write_dir(struct kvm_vcpu *vcpu,
 	__vgic_v3_clear_active_lr(lr, lr_val);
 }
 
-static void __hyp_text __vgic_v3_write_eoir(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
+static void __vgic_v3_write_eoir(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	u32 vid = vcpu_get_reg(vcpu, rt);
 	u64 lr_val;
@@ -744,17 +742,17 @@ static void __hyp_text __vgic_v3_write_eoir(struct kvm_vcpu *vcpu, u32 vmcr, int
 	__vgic_v3_clear_active_lr(lr, lr_val);
 }
 
-static void __hyp_text __vgic_v3_read_igrpen0(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
+static void __vgic_v3_read_igrpen0(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	vcpu_set_reg(vcpu, rt, !!(vmcr & ICH_VMCR_ENG0_MASK));
 }
 
-static void __hyp_text __vgic_v3_read_igrpen1(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
+static void __vgic_v3_read_igrpen1(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	vcpu_set_reg(vcpu, rt, !!(vmcr & ICH_VMCR_ENG1_MASK));
 }
 
-static void __hyp_text __vgic_v3_write_igrpen0(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
+static void __vgic_v3_write_igrpen0(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	u64 val = vcpu_get_reg(vcpu, rt);
 
@@ -766,7 +764,7 @@ static void __hyp_text __vgic_v3_write_igrpen0(struct kvm_vcpu *vcpu, u32 vmcr,
 	__vgic_v3_write_vmcr(vmcr);
 }
 
-static void __hyp_text __vgic_v3_write_igrpen1(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
+static void __vgic_v3_write_igrpen1(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	u64 val = vcpu_get_reg(vcpu, rt);
 
@@ -778,17 +776,17 @@ static void __hyp_text __vgic_v3_write_igrpen1(struct kvm_vcpu *vcpu, u32 vmcr,
 	__vgic_v3_write_vmcr(vmcr);
 }
 
-static void __hyp_text __vgic_v3_read_bpr0(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
+static void __vgic_v3_read_bpr0(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	vcpu_set_reg(vcpu, rt, __vgic_v3_get_bpr0(vmcr));
 }
 
-static void __hyp_text __vgic_v3_read_bpr1(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
+static void __vgic_v3_read_bpr1(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	vcpu_set_reg(vcpu, rt, __vgic_v3_get_bpr1(vmcr));
 }
 
-static void __hyp_text __vgic_v3_write_bpr0(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
+static void __vgic_v3_write_bpr0(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	u64 val = vcpu_get_reg(vcpu, rt);
 	u8 bpr_min = __vgic_v3_bpr_min() - 1;
@@ -805,7 +803,7 @@ static void __hyp_text __vgic_v3_write_bpr0(struct kvm_vcpu *vcpu, u32 vmcr, int
 	__vgic_v3_write_vmcr(vmcr);
 }
 
-static void __hyp_text __vgic_v3_write_bpr1(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
+static void __vgic_v3_write_bpr1(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	u64 val = vcpu_get_reg(vcpu, rt);
 	u8 bpr_min = __vgic_v3_bpr_min();
@@ -825,7 +823,7 @@ static void __hyp_text __vgic_v3_write_bpr1(struct kvm_vcpu *vcpu, u32 vmcr, int
 	__vgic_v3_write_vmcr(vmcr);
 }
 
-static void __hyp_text __vgic_v3_read_apxrn(struct kvm_vcpu *vcpu, int rt, int n)
+static void __vgic_v3_read_apxrn(struct kvm_vcpu *vcpu, int rt, int n)
 {
 	u32 val;
 
@@ -837,7 +835,7 @@ static void __hyp_text __vgic_v3_read_apxrn(struct kvm_vcpu *vcpu, int rt, int n
 	vcpu_set_reg(vcpu, rt, val);
 }
 
-static void __hyp_text __vgic_v3_write_apxrn(struct kvm_vcpu *vcpu, int rt, int n)
+static void __vgic_v3_write_apxrn(struct kvm_vcpu *vcpu, int rt, int n)
 {
 	u32 val = vcpu_get_reg(vcpu, rt);
 
@@ -847,56 +845,49 @@ static void __hyp_text __vgic_v3_write_apxrn(struct kvm_vcpu *vcpu, int rt, int
 		__vgic_v3_write_ap1rn(val, n);
 }
 
-static void __hyp_text __vgic_v3_read_apxr0(struct kvm_vcpu *vcpu,
+static void __vgic_v3_read_apxr0(struct kvm_vcpu *vcpu,
 					    u32 vmcr, int rt)
 {
 	__vgic_v3_read_apxrn(vcpu, rt, 0);
 }
 
-static void __hyp_text __vgic_v3_read_apxr1(struct kvm_vcpu *vcpu,
+static void __vgic_v3_read_apxr1(struct kvm_vcpu *vcpu,
 					    u32 vmcr, int rt)
 {
 	__vgic_v3_read_apxrn(vcpu, rt, 1);
 }
 
-static void __hyp_text __vgic_v3_read_apxr2(struct kvm_vcpu *vcpu,
-					    u32 vmcr, int rt)
+static void __vgic_v3_read_apxr2(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	__vgic_v3_read_apxrn(vcpu, rt, 2);
 }
 
-static void __hyp_text __vgic_v3_read_apxr3(struct kvm_vcpu *vcpu,
-					    u32 vmcr, int rt)
+static void __vgic_v3_read_apxr3(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	__vgic_v3_read_apxrn(vcpu, rt, 3);
 }
 
-static void __hyp_text __vgic_v3_write_apxr0(struct kvm_vcpu *vcpu,
-					     u32 vmcr, int rt)
+static void __vgic_v3_write_apxr0(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	__vgic_v3_write_apxrn(vcpu, rt, 0);
 }
 
-static void __hyp_text __vgic_v3_write_apxr1(struct kvm_vcpu *vcpu,
-					     u32 vmcr, int rt)
+static void __vgic_v3_write_apxr1(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	__vgic_v3_write_apxrn(vcpu, rt, 1);
 }
 
-static void __hyp_text __vgic_v3_write_apxr2(struct kvm_vcpu *vcpu,
-					     u32 vmcr, int rt)
+static void __vgic_v3_write_apxr2(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	__vgic_v3_write_apxrn(vcpu, rt, 2);
 }
 
-static void __hyp_text __vgic_v3_write_apxr3(struct kvm_vcpu *vcpu,
-					     u32 vmcr, int rt)
+static void __vgic_v3_write_apxr3(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	__vgic_v3_write_apxrn(vcpu, rt, 3);
 }
 
-static void __hyp_text __vgic_v3_read_hppir(struct kvm_vcpu *vcpu,
-					    u32 vmcr, int rt)
+static void __vgic_v3_read_hppir(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	u64 lr_val;
 	int lr, lr_grp, grp;
@@ -915,16 +906,14 @@ spurious:
 	vcpu_set_reg(vcpu, rt, lr_val & ICH_LR_VIRTUAL_ID_MASK);
 }
 
-static void __hyp_text __vgic_v3_read_pmr(struct kvm_vcpu *vcpu,
-					  u32 vmcr, int rt)
+static void __vgic_v3_read_pmr(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	vmcr &= ICH_VMCR_PMR_MASK;
 	vmcr >>= ICH_VMCR_PMR_SHIFT;
 	vcpu_set_reg(vcpu, rt, vmcr);
 }
 
-static void __hyp_text __vgic_v3_write_pmr(struct kvm_vcpu *vcpu,
-					   u32 vmcr, int rt)
+static void __vgic_v3_write_pmr(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	u32 val = vcpu_get_reg(vcpu, rt);
 
@@ -936,15 +925,13 @@ static void __hyp_text __vgic_v3_write_pmr(struct kvm_vcpu *vcpu,
 	write_gicreg(vmcr, ICH_VMCR_EL2);
 }
 
-static void __hyp_text __vgic_v3_read_rpr(struct kvm_vcpu *vcpu,
-					  u32 vmcr, int rt)
+static void __vgic_v3_read_rpr(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	u32 val = __vgic_v3_get_highest_active_priority();
 	vcpu_set_reg(vcpu, rt, val);
 }
 
-static void __hyp_text __vgic_v3_read_ctlr(struct kvm_vcpu *vcpu,
-					   u32 vmcr, int rt)
+static void __vgic_v3_read_ctlr(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	u32 vtr, val;
 
@@ -965,8 +952,7 @@ static void __hyp_text __vgic_v3_read_ctlr(struct kvm_vcpu *vcpu,
 	vcpu_set_reg(vcpu, rt, val);
 }
 
-static void __hyp_text __vgic_v3_write_ctlr(struct kvm_vcpu *vcpu,
-					    u32 vmcr, int rt)
+static void __vgic_v3_write_ctlr(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	u32 val = vcpu_get_reg(vcpu, rt);
 
@@ -983,7 +969,7 @@ static void __hyp_text __vgic_v3_write_ctlr(struct kvm_vcpu *vcpu,
 	write_gicreg(vmcr, ICH_VMCR_EL2);
 }
 
-int __hyp_text __vgic_v3_perform_cpuif_access(struct kvm_vcpu *vcpu)
+int __vgic_v3_perform_cpuif_access(struct kvm_vcpu *vcpu)
 {
 	int rt;
 	u32 esr;
-- 
cgit 


From f9a026e3d38ba81cd274725f1caaf64322a86aa5 Mon Sep 17 00:00:00 2001
From: David Brazdil <dbrazdil@google.com>
Date: Thu, 25 Jun 2020 14:14:20 +0100
Subject: KVM: arm64: Lift instrumentation restrictions on VHE

With VHE and nVHE executable code completely separated, remove build config
that disabled GCOV/KASAN/UBSAN/KCOV instrumentation for VHE as these now
execute under the same memory mappings as the rest of the kernel.

No violations are currently being reported by either KASAN or UBSAN.

Signed-off-by: David Brazdil <dbrazdil@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200625131420.71444-16-dbrazdil@google.com
---
 arch/arm64/kvm/hyp/vhe/Makefile | 8 --------
 1 file changed, 8 deletions(-)

diff --git a/arch/arm64/kvm/hyp/vhe/Makefile b/arch/arm64/kvm/hyp/vhe/Makefile
index 090fd1e14be2..461e97c375cc 100644
--- a/arch/arm64/kvm/hyp/vhe/Makefile
+++ b/arch/arm64/kvm/hyp/vhe/Makefile
@@ -9,11 +9,3 @@ ccflags-y := -D__KVM_VHE_HYPERVISOR__
 obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o
 obj-y += ../vgic-v3-sr.o ../aarch32.o ../vgic-v2-cpuif-proxy.o ../entry.o \
 	 ../fpsimd.o ../hyp-entry.o
-
-# KVM code is run at a different exception code with a different map, so
-# compiler instrumentation that inserts callbacks or checks into the code may
-# cause crashes. Just disable it.
-GCOV_PROFILE	:= n
-KASAN_SANITIZE	:= n
-UBSAN_SANITIZE	:= n
-KCOV_INSTRUMENT	:= n
-- 
cgit 


From 731532176716e2775a5d21115bb9c5c61e0cb704 Mon Sep 17 00:00:00 2001
From: Alexander Graf <graf@amazon.com>
Date: Wed, 1 Jul 2020 16:02:06 +0200
Subject: KVM: arm64: vgic-its: Change default outer cacheability for {PEND,
 PROP}BASER

PENDBASER and PROPBASER define the outer caching mode for LPI tables.
The memory backing them may not be outer sharable, so we mark them as nC
by default. This however, breaks Windows on ARM which only accepts
SameAsInner or RaWaWb as values for outer cachability.

We do today already allow the outer mode to be set to SameAsInner
explicitly, so the easy fix is to default to that instead of nC for
situations when an OS asks for a not fulfillable cachability request.

This fixes booting Windows in KVM with vgicv3 and ITS enabled for me.

Signed-off-by: Alexander Graf <graf@amazon.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200701140206.8664-1-graf@amazon.com
---
 arch/arm64/kvm/vgic/vgic-mmio-v3.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c
index d2339a2b9fb9..5c786b915cd3 100644
--- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c
@@ -389,7 +389,7 @@ u64 vgic_sanitise_outer_cacheability(u64 field)
 	case GIC_BASER_CACHE_nC:
 		return field;
 	default:
-		return GIC_BASER_CACHE_nC;
+		return GIC_BASER_CACHE_SameAsInner;
 	}
 }
 
-- 
cgit 


From 95fa0ba83e66dea0d3af48ad69842ae8c1dd9af2 Mon Sep 17 00:00:00 2001
From: Peng Hao <richard.peng@oppo.com>
Date: Wed, 1 Jul 2020 08:07:09 -0400
Subject: KVM: arm64: Drop long gone function parameter documentation

update_vmid() just has one parameter "vmid".The other parameter
"kvm" is no longer used.

Signed-off-by: Peng Hao <richard.peng@oppo.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200701120709.388377-1-richard.peng@oppo.com
---
 arch/arm64/kvm/arm.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 90cb90561446..5bf9bf54b22c 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -466,7 +466,6 @@ static bool need_new_vmid_gen(struct kvm_vmid *vmid)
 
 /**
  * update_vmid - Update the vmid with a valid VMID for the current generation
- * @kvm: The guest that struct vmid belongs to
  * @vmid: The stage-2 VMID information struct
  */
 static void update_vmid(struct kvm_vmid *vmid)
-- 
cgit 


From 3a949f4c93548751a377691b2a208063da05e369 Mon Sep 17 00:00:00 2001
From: Gavin Shan <gshan@redhat.com>
Date: Tue, 30 Jun 2020 11:57:05 +1000
Subject: KVM: arm64: Rename HSR to ESR

kvm/arm32 isn't supported since commit 541ad0150ca4 ("arm: Remove
32bit KVM host support"). So HSR isn't meaningful since then. This
renames HSR to ESR accordingly. This shouldn't cause any functional
changes:

   * Rename kvm_vcpu_get_hsr() to kvm_vcpu_get_esr() to make the
     function names self-explanatory.
   * Rename variables from @hsr to @esr to make them self-explanatory.

Note that the renaming on uapi and tracepoint will cause ABI changes,
which we should avoid. Specificly, there are 4 related source files
in this regard:

   * arch/arm64/include/uapi/asm/kvm.h  (struct kvm_debug_exit_arch::hsr)
   * arch/arm64/kvm/handle_exit.c       (struct kvm_debug_exit_arch::hsr)
   * arch/arm64/kvm/trace_arm.h         (tracepoints)
   * arch/arm64/kvm/trace_handle_exit.h (tracepoints)

Signed-off-by: Gavin Shan <gshan@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Acked-by: Andrew Scull <ascull@google.com>
Link: https://lore.kernel.org/r/20200630015705.103366-1-gshan@redhat.com
---
 arch/arm64/include/asm/kvm_emulate.h | 34 +++++++++++++++++-----------------
 arch/arm64/kvm/handle_exit.c         | 32 ++++++++++++++++----------------
 arch/arm64/kvm/hyp/aarch32.c         |  2 +-
 arch/arm64/kvm/hyp/switch.c          | 14 +++++++-------
 arch/arm64/kvm/hyp/vgic-v3-sr.c      |  4 ++--
 arch/arm64/kvm/mmu.c                 |  6 +++---
 arch/arm64/kvm/sys_regs.c            | 28 ++++++++++++++--------------
 7 files changed, 60 insertions(+), 60 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 4d0f8ea600ba..c9ba0df47f7d 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -259,14 +259,14 @@ static inline bool vcpu_mode_priv(const struct kvm_vcpu *vcpu)
 	return mode != PSR_MODE_EL0t;
 }
 
-static __always_inline u32 kvm_vcpu_get_hsr(const struct kvm_vcpu *vcpu)
+static __always_inline u32 kvm_vcpu_get_esr(const struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.fault.esr_el2;
 }
 
 static __always_inline int kvm_vcpu_get_condition(const struct kvm_vcpu *vcpu)
 {
-	u32 esr = kvm_vcpu_get_hsr(vcpu);
+	u32 esr = kvm_vcpu_get_esr(vcpu);
 
 	if (esr & ESR_ELx_CV)
 		return (esr & ESR_ELx_COND_MASK) >> ESR_ELx_COND_SHIFT;
@@ -291,64 +291,64 @@ static inline u64 kvm_vcpu_get_disr(const struct kvm_vcpu *vcpu)
 
 static inline u32 kvm_vcpu_hvc_get_imm(const struct kvm_vcpu *vcpu)
 {
-	return kvm_vcpu_get_hsr(vcpu) & ESR_ELx_xVC_IMM_MASK;
+	return kvm_vcpu_get_esr(vcpu) & ESR_ELx_xVC_IMM_MASK;
 }
 
 static __always_inline bool kvm_vcpu_dabt_isvalid(const struct kvm_vcpu *vcpu)
 {
-	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_ISV);
+	return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_ISV);
 }
 
 static inline unsigned long kvm_vcpu_dabt_iss_nisv_sanitized(const struct kvm_vcpu *vcpu)
 {
-	return kvm_vcpu_get_hsr(vcpu) & (ESR_ELx_CM | ESR_ELx_WNR | ESR_ELx_FSC);
+	return kvm_vcpu_get_esr(vcpu) & (ESR_ELx_CM | ESR_ELx_WNR | ESR_ELx_FSC);
 }
 
 static inline bool kvm_vcpu_dabt_issext(const struct kvm_vcpu *vcpu)
 {
-	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SSE);
+	return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_SSE);
 }
 
 static inline bool kvm_vcpu_dabt_issf(const struct kvm_vcpu *vcpu)
 {
-	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SF);
+	return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_SF);
 }
 
 static __always_inline int kvm_vcpu_dabt_get_rd(const struct kvm_vcpu *vcpu)
 {
-	return (kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SRT_MASK) >> ESR_ELx_SRT_SHIFT;
+	return (kvm_vcpu_get_esr(vcpu) & ESR_ELx_SRT_MASK) >> ESR_ELx_SRT_SHIFT;
 }
 
 static __always_inline bool kvm_vcpu_dabt_iss1tw(const struct kvm_vcpu *vcpu)
 {
-	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_S1PTW);
+	return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_S1PTW);
 }
 
 static __always_inline bool kvm_vcpu_dabt_iswrite(const struct kvm_vcpu *vcpu)
 {
-	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_WNR) ||
+	return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_WNR) ||
 		kvm_vcpu_dabt_iss1tw(vcpu); /* AF/DBM update */
 }
 
 static inline bool kvm_vcpu_dabt_is_cm(const struct kvm_vcpu *vcpu)
 {
-	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_CM);
+	return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_CM);
 }
 
 static __always_inline unsigned int kvm_vcpu_dabt_get_as(const struct kvm_vcpu *vcpu)
 {
-	return 1 << ((kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SAS) >> ESR_ELx_SAS_SHIFT);
+	return 1 << ((kvm_vcpu_get_esr(vcpu) & ESR_ELx_SAS) >> ESR_ELx_SAS_SHIFT);
 }
 
 /* This one is not specific to Data Abort */
 static __always_inline bool kvm_vcpu_trap_il_is32bit(const struct kvm_vcpu *vcpu)
 {
-	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_IL);
+	return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_IL);
 }
 
 static __always_inline u8 kvm_vcpu_trap_get_class(const struct kvm_vcpu *vcpu)
 {
-	return ESR_ELx_EC(kvm_vcpu_get_hsr(vcpu));
+	return ESR_ELx_EC(kvm_vcpu_get_esr(vcpu));
 }
 
 static inline bool kvm_vcpu_trap_is_iabt(const struct kvm_vcpu *vcpu)
@@ -358,12 +358,12 @@ static inline bool kvm_vcpu_trap_is_iabt(const struct kvm_vcpu *vcpu)
 
 static __always_inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu)
 {
-	return kvm_vcpu_get_hsr(vcpu) & ESR_ELx_FSC;
+	return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC;
 }
 
 static __always_inline u8 kvm_vcpu_trap_get_fault_type(const struct kvm_vcpu *vcpu)
 {
-	return kvm_vcpu_get_hsr(vcpu) & ESR_ELx_FSC_TYPE;
+	return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC_TYPE;
 }
 
 static __always_inline bool kvm_vcpu_dabt_isextabt(const struct kvm_vcpu *vcpu)
@@ -387,7 +387,7 @@ static __always_inline bool kvm_vcpu_dabt_isextabt(const struct kvm_vcpu *vcpu)
 
 static __always_inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu)
 {
-	u32 esr = kvm_vcpu_get_hsr(vcpu);
+	u32 esr = kvm_vcpu_get_esr(vcpu);
 	return ESR_ELx_SYS64_ISS_RT(esr);
 }
 
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 5a02d4c90559..98ab33139982 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -89,7 +89,7 @@ static int handle_no_fpsimd(struct kvm_vcpu *vcpu, struct kvm_run *run)
  */
 static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
-	if (kvm_vcpu_get_hsr(vcpu) & ESR_ELx_WFx_ISS_WFE) {
+	if (kvm_vcpu_get_esr(vcpu) & ESR_ELx_WFx_ISS_WFE) {
 		trace_kvm_wfx_arm64(*vcpu_pc(vcpu), true);
 		vcpu->stat.wfe_exit_stat++;
 		kvm_vcpu_on_spin(vcpu, vcpu_mode_priv(vcpu));
@@ -119,13 +119,13 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
  */
 static int kvm_handle_guest_debug(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
-	u32 hsr = kvm_vcpu_get_hsr(vcpu);
+	u32 esr = kvm_vcpu_get_esr(vcpu);
 	int ret = 0;
 
 	run->exit_reason = KVM_EXIT_DEBUG;
-	run->debug.arch.hsr = hsr;
+	run->debug.arch.hsr = esr;
 
-	switch (ESR_ELx_EC(hsr)) {
+	switch (ESR_ELx_EC(esr)) {
 	case ESR_ELx_EC_WATCHPT_LOW:
 		run->debug.arch.far = vcpu->arch.fault.far_el2;
 		/* fall through */
@@ -135,8 +135,8 @@ static int kvm_handle_guest_debug(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	case ESR_ELx_EC_BRK64:
 		break;
 	default:
-		kvm_err("%s: un-handled case hsr: %#08x\n",
-			__func__, (unsigned int) hsr);
+		kvm_err("%s: un-handled case esr: %#08x\n",
+			__func__, (unsigned int) esr);
 		ret = -1;
 		break;
 	}
@@ -146,10 +146,10 @@ static int kvm_handle_guest_debug(struct kvm_vcpu *vcpu, struct kvm_run *run)
 
 static int kvm_handle_unknown_ec(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
-	u32 hsr = kvm_vcpu_get_hsr(vcpu);
+	u32 esr = kvm_vcpu_get_esr(vcpu);
 
-	kvm_pr_unimpl("Unknown exception class: hsr: %#08x -- %s\n",
-		      hsr, esr_get_class_string(hsr));
+	kvm_pr_unimpl("Unknown exception class: esr: %#08x -- %s\n",
+		      esr, esr_get_class_string(esr));
 
 	kvm_inject_undefined(vcpu);
 	return 1;
@@ -200,10 +200,10 @@ static exit_handle_fn arm_exit_handlers[] = {
 
 static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu)
 {
-	u32 hsr = kvm_vcpu_get_hsr(vcpu);
-	u8 hsr_ec = ESR_ELx_EC(hsr);
+	u32 esr = kvm_vcpu_get_esr(vcpu);
+	u8 esr_ec = ESR_ELx_EC(esr);
 
-	return arm_exit_handlers[hsr_ec];
+	return arm_exit_handlers[esr_ec];
 }
 
 /*
@@ -241,15 +241,15 @@ int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		       int exception_index)
 {
 	if (ARM_SERROR_PENDING(exception_index)) {
-		u8 hsr_ec = ESR_ELx_EC(kvm_vcpu_get_hsr(vcpu));
+		u8 esr_ec = ESR_ELx_EC(kvm_vcpu_get_esr(vcpu));
 
 		/*
 		 * HVC/SMC already have an adjusted PC, which we need
 		 * to correct in order to return to after having
 		 * injected the SError.
 		 */
-		if (hsr_ec == ESR_ELx_EC_HVC32 || hsr_ec == ESR_ELx_EC_HVC64 ||
-		    hsr_ec == ESR_ELx_EC_SMC32 || hsr_ec == ESR_ELx_EC_SMC64) {
+		if (esr_ec == ESR_ELx_EC_HVC32 || esr_ec == ESR_ELx_EC_HVC64 ||
+		    esr_ec == ESR_ELx_EC_SMC32 || esr_ec == ESR_ELx_EC_SMC64) {
 			u32 adj =  kvm_vcpu_trap_il_is32bit(vcpu) ? 4 : 2;
 			*vcpu_pc(vcpu) -= adj;
 		}
@@ -307,5 +307,5 @@ void handle_exit_early(struct kvm_vcpu *vcpu, struct kvm_run *run,
 	exception_index = ARM_EXCEPTION_CODE(exception_index);
 
 	if (exception_index == ARM_EXCEPTION_EL1_SERROR)
-		kvm_handle_guest_serror(vcpu, kvm_vcpu_get_hsr(vcpu));
+		kvm_handle_guest_serror(vcpu, kvm_vcpu_get_esr(vcpu));
 }
diff --git a/arch/arm64/kvm/hyp/aarch32.c b/arch/arm64/kvm/hyp/aarch32.c
index 25c0e47d57cb..1e948704d60f 100644
--- a/arch/arm64/kvm/hyp/aarch32.c
+++ b/arch/arm64/kvm/hyp/aarch32.c
@@ -51,7 +51,7 @@ bool __hyp_text kvm_condition_valid32(const struct kvm_vcpu *vcpu)
 	int cond;
 
 	/* Top two bits non-zero?  Unconditional. */
-	if (kvm_vcpu_get_hsr(vcpu) >> 30)
+	if (kvm_vcpu_get_esr(vcpu) >> 30)
 		return true;
 
 	/* Is condition field valid? */
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index db1c4487d95d..5164074c1ae1 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -356,7 +356,7 @@ static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu)
 static bool __hyp_text __hyp_handle_fpsimd(struct kvm_vcpu *vcpu)
 {
 	bool vhe, sve_guest, sve_host;
-	u8 hsr_ec;
+	u8 esr_ec;
 
 	if (!system_supports_fpsimd())
 		return false;
@@ -371,14 +371,14 @@ static bool __hyp_text __hyp_handle_fpsimd(struct kvm_vcpu *vcpu)
 		vhe = has_vhe();
 	}
 
-	hsr_ec = kvm_vcpu_trap_get_class(vcpu);
-	if (hsr_ec != ESR_ELx_EC_FP_ASIMD &&
-	    hsr_ec != ESR_ELx_EC_SVE)
+	esr_ec = kvm_vcpu_trap_get_class(vcpu);
+	if (esr_ec != ESR_ELx_EC_FP_ASIMD &&
+	    esr_ec != ESR_ELx_EC_SVE)
 		return false;
 
 	/* Don't handle SVE traps for non-SVE vcpus here: */
 	if (!sve_guest)
-		if (hsr_ec != ESR_ELx_EC_FP_ASIMD)
+		if (esr_ec != ESR_ELx_EC_FP_ASIMD)
 			return false;
 
 	/* Valid trap.  Switch the context: */
@@ -437,7 +437,7 @@ static bool __hyp_text __hyp_handle_fpsimd(struct kvm_vcpu *vcpu)
 
 static bool __hyp_text handle_tx2_tvm(struct kvm_vcpu *vcpu)
 {
-	u32 sysreg = esr_sys64_to_sysreg(kvm_vcpu_get_hsr(vcpu));
+	u32 sysreg = esr_sys64_to_sysreg(kvm_vcpu_get_esr(vcpu));
 	int rt = kvm_vcpu_sys_get_rt(vcpu);
 	u64 val = vcpu_get_reg(vcpu, rt);
 
@@ -529,7 +529,7 @@ static bool __hyp_text __hyp_handle_ptrauth(struct kvm_vcpu *vcpu)
 	u64 val;
 
 	if (!vcpu_has_ptrauth(vcpu) ||
-	    !esr_is_ptrauth_trap(kvm_vcpu_get_hsr(vcpu)))
+	    !esr_is_ptrauth_trap(kvm_vcpu_get_esr(vcpu)))
 		return false;
 
 	ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c
index 10ed539835c1..bee0a74671ca 100644
--- a/arch/arm64/kvm/hyp/vgic-v3-sr.c
+++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c
@@ -426,7 +426,7 @@ static int __hyp_text __vgic_v3_bpr_min(void)
 
 static int __hyp_text __vgic_v3_get_group(struct kvm_vcpu *vcpu)
 {
-	u32 esr = kvm_vcpu_get_hsr(vcpu);
+	u32 esr = kvm_vcpu_get_esr(vcpu);
 	u8 crm = (esr & ESR_ELx_SYS64_ISS_CRM_MASK) >> ESR_ELx_SYS64_ISS_CRM_SHIFT;
 
 	return crm != 8;
@@ -992,7 +992,7 @@ int __hyp_text __vgic_v3_perform_cpuif_access(struct kvm_vcpu *vcpu)
 	bool is_read;
 	u32 sysreg;
 
-	esr = kvm_vcpu_get_hsr(vcpu);
+	esr = kvm_vcpu_get_esr(vcpu);
 	if (vcpu_mode_is_32bit(vcpu)) {
 		if (!kvm_condition_valid(vcpu)) {
 			__kvm_skip_instr(vcpu);
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 8c0035cab6b6..36506112480e 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -2079,7 +2079,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		 * For RAS the host kernel may handle this abort.
 		 * There is no need to pass the error into the guest.
 		 */
-		if (!kvm_handle_guest_sea(fault_ipa, kvm_vcpu_get_hsr(vcpu)))
+		if (!kvm_handle_guest_sea(fault_ipa, kvm_vcpu_get_esr(vcpu)))
 			return 1;
 
 		if (unlikely(!is_iabt)) {
@@ -2088,7 +2088,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		}
 	}
 
-	trace_kvm_guest_fault(*vcpu_pc(vcpu), kvm_vcpu_get_hsr(vcpu),
+	trace_kvm_guest_fault(*vcpu_pc(vcpu), kvm_vcpu_get_esr(vcpu),
 			      kvm_vcpu_get_hfar(vcpu), fault_ipa);
 
 	/* Check the stage-2 fault is trans. fault or write fault */
@@ -2097,7 +2097,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		kvm_err("Unsupported FSC: EC=%#x xFSC=%#lx ESR_EL2=%#lx\n",
 			kvm_vcpu_trap_get_class(vcpu),
 			(unsigned long)kvm_vcpu_trap_get_fault(vcpu),
-			(unsigned long)kvm_vcpu_get_hsr(vcpu));
+			(unsigned long)kvm_vcpu_get_esr(vcpu));
 		return -EFAULT;
 	}
 
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index baf5ce9225ce..a96dd62a90ce 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -2220,10 +2220,10 @@ static int emulate_cp(struct kvm_vcpu *vcpu,
 static void unhandled_cp_access(struct kvm_vcpu *vcpu,
 				struct sys_reg_params *params)
 {
-	u8 hsr_ec = kvm_vcpu_trap_get_class(vcpu);
+	u8 esr_ec = kvm_vcpu_trap_get_class(vcpu);
 	int cp = -1;
 
-	switch(hsr_ec) {
+	switch (esr_ec) {
 	case ESR_ELx_EC_CP15_32:
 	case ESR_ELx_EC_CP15_64:
 		cp = 15;
@@ -2254,17 +2254,17 @@ static int kvm_handle_cp_64(struct kvm_vcpu *vcpu,
 			    size_t nr_specific)
 {
 	struct sys_reg_params params;
-	u32 hsr = kvm_vcpu_get_hsr(vcpu);
+	u32 esr = kvm_vcpu_get_esr(vcpu);
 	int Rt = kvm_vcpu_sys_get_rt(vcpu);
-	int Rt2 = (hsr >> 10) & 0x1f;
+	int Rt2 = (esr >> 10) & 0x1f;
 
 	params.is_aarch32 = true;
 	params.is_32bit = false;
-	params.CRm = (hsr >> 1) & 0xf;
-	params.is_write = ((hsr & 1) == 0);
+	params.CRm = (esr >> 1) & 0xf;
+	params.is_write = ((esr & 1) == 0);
 
 	params.Op0 = 0;
-	params.Op1 = (hsr >> 16) & 0xf;
+	params.Op1 = (esr >> 16) & 0xf;
 	params.Op2 = 0;
 	params.CRn = 0;
 
@@ -2311,18 +2311,18 @@ static int kvm_handle_cp_32(struct kvm_vcpu *vcpu,
 			    size_t nr_specific)
 {
 	struct sys_reg_params params;
-	u32 hsr = kvm_vcpu_get_hsr(vcpu);
+	u32 esr = kvm_vcpu_get_esr(vcpu);
 	int Rt  = kvm_vcpu_sys_get_rt(vcpu);
 
 	params.is_aarch32 = true;
 	params.is_32bit = true;
-	params.CRm = (hsr >> 1) & 0xf;
+	params.CRm = (esr >> 1) & 0xf;
 	params.regval = vcpu_get_reg(vcpu, Rt);
-	params.is_write = ((hsr & 1) == 0);
-	params.CRn = (hsr >> 10) & 0xf;
+	params.is_write = ((esr & 1) == 0);
+	params.CRn = (esr >> 10) & 0xf;
 	params.Op0 = 0;
-	params.Op1 = (hsr >> 14) & 0x7;
-	params.Op2 = (hsr >> 17) & 0x7;
+	params.Op1 = (esr >> 14) & 0x7;
+	params.Op2 = (esr >> 17) & 0x7;
 
 	if (!emulate_cp(vcpu, &params, target_specific, nr_specific) ||
 	    !emulate_cp(vcpu, &params, global, nr_global)) {
@@ -2421,7 +2421,7 @@ static void reset_sys_reg_descs(struct kvm_vcpu *vcpu,
 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);
+	unsigned long esr = kvm_vcpu_get_esr(vcpu);
 	int Rt = kvm_vcpu_sys_get_rt(vcpu);
 	int ret;
 
-- 
cgit 


From a0e50aa3f4a8a5c9fb791b8f32d624e2a1a735bd Mon Sep 17 00:00:00 2001
From: Christoffer Dall <christoffer.dall@arm.com>
Date: Fri, 4 Jan 2019 21:09:05 +0100
Subject: KVM: arm64: Factor out stage 2 page table data from struct kvm

As we are about to reuse our stage 2 page table manipulation code for
shadow stage 2 page tables in the context of nested virtualization, we
are going to manage multiple stage 2 page tables for a single VM.

This requires some pretty invasive changes to our data structures,
which moves the vmid and pgd pointers into a separate structure and
change pretty much all of our mmu code to operate on this structure
instead.

The new structure is called struct kvm_s2_mmu.

There is no intended functional change by this patch alone.

Reviewed-by: James Morse <james.morse@arm.com>
Reviewed-by: Alexandru Elisei <alexandru.elisei@arm.com>
[Designed data structure layout in collaboration]
Signed-off-by: Christoffer Dall <christoffer.dall@arm.com>
Co-developed-by: Marc Zyngier <maz@kernel.org>
[maz: Moved the last_vcpu_ran down to the S2 MMU structure as well]
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_asm.h        |   7 +-
 arch/arm64/include/asm/kvm_host.h       |  32 +++-
 arch/arm64/include/asm/kvm_mmu.h        |  16 +-
 arch/arm64/kvm/arm.c                    |  36 ++--
 arch/arm64/kvm/hyp/include/hyp/switch.h |   4 +-
 arch/arm64/kvm/hyp/nvhe/switch.c        |   2 +-
 arch/arm64/kvm/hyp/nvhe/tlb.c           |  33 ++--
 arch/arm64/kvm/hyp/vhe/switch.c         |   2 +-
 arch/arm64/kvm/hyp/vhe/tlb.c            |  26 +--
 arch/arm64/kvm/mmu.c                    | 280 ++++++++++++++++++--------------
 10 files changed, 240 insertions(+), 198 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 5a91aaae78d2..18d39b30d9c9 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -77,6 +77,7 @@
 
 struct kvm;
 struct kvm_vcpu;
+struct kvm_s2_mmu;
 
 DECLARE_KVM_NVHE_SYM(__kvm_hyp_init);
 DECLARE_KVM_HYP_SYM(__kvm_hyp_vector);
@@ -90,9 +91,9 @@ DECLARE_KVM_HYP_SYM(__bp_harden_hyp_vecs);
 #endif
 
 extern void __kvm_flush_vm_context(void);
-extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
-extern void __kvm_tlb_flush_vmid(struct kvm *kvm);
-extern void __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu);
+extern void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa);
+extern void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu);
+extern void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu);
 
 extern void __kvm_timer_set_cntvoff(u64 cntvoff);
 
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index e0920df1d0c1..85a529eeeae3 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -66,19 +66,34 @@ struct kvm_vmid {
 	u32    vmid;
 };
 
-struct kvm_arch {
+struct kvm_s2_mmu {
 	struct kvm_vmid vmid;
 
-	/* stage2 entry level table */
-	pgd_t *pgd;
-	phys_addr_t pgd_phys;
-
-	/* VTCR_EL2 value for this VM */
-	u64    vtcr;
+	/*
+	 * stage2 entry level table
+	 *
+	 * Two kvm_s2_mmu structures in the same VM can point to the same
+	 * pgd here.  This happens when running a guest using a
+	 * translation regime that isn't affected by its own stage-2
+	 * translation, such as a non-VHE hypervisor running at vEL2, or
+	 * for vEL1/EL0 with vHCR_EL2.VM == 0.  In that case, we use the
+	 * canonical stage-2 page tables.
+	 */
+	pgd_t		*pgd;
+	phys_addr_t	pgd_phys;
 
 	/* The last vcpu id that ran on each physical CPU */
 	int __percpu *last_vcpu_ran;
 
+	struct kvm *kvm;
+};
+
+struct kvm_arch {
+	struct kvm_s2_mmu mmu;
+
+	/* VTCR_EL2 value for this VM */
+	u64    vtcr;
+
 	/* The maximum number of vCPUs depends on the used GIC model */
 	int max_vcpus;
 
@@ -254,6 +269,9 @@ struct kvm_vcpu_arch {
 	void *sve_state;
 	unsigned int sve_max_vl;
 
+	/* Stage 2 paging state used by the hardware on next switch */
+	struct kvm_s2_mmu *hw_mmu;
+
 	/* HYP configuration */
 	u64 hcr_el2;
 	u32 mdcr_el2;
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index b12bfc1f051a..22157ded04ca 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -134,8 +134,8 @@ int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size,
 void free_hyp_pgds(void);
 
 void stage2_unmap_vm(struct kvm *kvm);
-int kvm_alloc_stage2_pgd(struct kvm *kvm);
-void kvm_free_stage2_pgd(struct kvm *kvm);
+int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu);
+void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu);
 int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
 			  phys_addr_t pa, unsigned long size, bool writable);
 
@@ -577,13 +577,13 @@ static inline u64 kvm_vttbr_baddr_mask(struct kvm *kvm)
 	return vttbr_baddr_mask(kvm_phys_shift(kvm), kvm_stage2_levels(kvm));
 }
 
-static __always_inline u64 kvm_get_vttbr(struct kvm *kvm)
+static __always_inline u64 kvm_get_vttbr(struct kvm_s2_mmu *mmu)
 {
-	struct kvm_vmid *vmid = &kvm->arch.vmid;
+	struct kvm_vmid *vmid = &mmu->vmid;
 	u64 vmid_field, baddr;
 	u64 cnp = system_supports_cnp() ? VTTBR_CNP_BIT : 0;
 
-	baddr = kvm->arch.pgd_phys;
+	baddr = mmu->pgd_phys;
 	vmid_field = (u64)vmid->vmid << VTTBR_VMID_SHIFT;
 	return kvm_phys_to_vttbr(baddr) | vmid_field | cnp;
 }
@@ -592,10 +592,10 @@ static __always_inline u64 kvm_get_vttbr(struct kvm *kvm)
  * Must be called from hyp code running at EL2 with an updated VTTBR
  * and interrupts disabled.
  */
-static __always_inline void __load_guest_stage2(struct kvm *kvm)
+static __always_inline void __load_guest_stage2(struct kvm_s2_mmu *mmu)
 {
-	write_sysreg(kvm->arch.vtcr, vtcr_el2);
-	write_sysreg(kvm_get_vttbr(kvm), vttbr_el2);
+	write_sysreg(kern_hyp_va(mmu->kvm)->arch.vtcr, vtcr_el2);
+	write_sysreg(kvm_get_vttbr(mmu), vttbr_el2);
 
 	/*
 	 * ARM errata 1165522 and 1530923 require the actual execution of the
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 0bf2cf5614c6..beb0e68cccaa 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -106,22 +106,15 @@ static int kvm_arm_default_max_vcpus(void)
  */
 int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 {
-	int ret, cpu;
+	int ret;
 
 	ret = kvm_arm_setup_stage2(kvm, type);
 	if (ret)
 		return ret;
 
-	kvm->arch.last_vcpu_ran = alloc_percpu(typeof(*kvm->arch.last_vcpu_ran));
-	if (!kvm->arch.last_vcpu_ran)
-		return -ENOMEM;
-
-	for_each_possible_cpu(cpu)
-		*per_cpu_ptr(kvm->arch.last_vcpu_ran, cpu) = -1;
-
-	ret = kvm_alloc_stage2_pgd(kvm);
+	ret = kvm_init_stage2_mmu(kvm, &kvm->arch.mmu);
 	if (ret)
-		goto out_fail_alloc;
+		return ret;
 
 	ret = create_hyp_mappings(kvm, kvm + 1, PAGE_HYP);
 	if (ret)
@@ -129,18 +122,12 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 
 	kvm_vgic_early_init(kvm);
 
-	/* Mark the initial VMID generation invalid */
-	kvm->arch.vmid.vmid_gen = 0;
-
 	/* The maximum number of VCPUs is limited by the host's GIC model */
 	kvm->arch.max_vcpus = kvm_arm_default_max_vcpus();
 
 	return ret;
 out_free_stage2_pgd:
-	kvm_free_stage2_pgd(kvm);
-out_fail_alloc:
-	free_percpu(kvm->arch.last_vcpu_ran);
-	kvm->arch.last_vcpu_ran = NULL;
+	kvm_free_stage2_pgd(&kvm->arch.mmu);
 	return ret;
 }
 
@@ -160,9 +147,6 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 
 	kvm_vgic_destroy(kvm);
 
-	free_percpu(kvm->arch.last_vcpu_ran);
-	kvm->arch.last_vcpu_ran = NULL;
-
 	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
 		if (kvm->vcpus[i]) {
 			kvm_vcpu_destroy(kvm->vcpus[i]);
@@ -279,6 +263,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 
 	kvm_arm_pvtime_vcpu_init(&vcpu->arch);
 
+	vcpu->arch.hw_mmu = &vcpu->kvm->arch.mmu;
+
 	err = kvm_vgic_vcpu_init(vcpu);
 	if (err)
 		return err;
@@ -334,16 +320,18 @@ void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu)
 
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
+	struct kvm_s2_mmu *mmu;
 	int *last_ran;
 
-	last_ran = this_cpu_ptr(vcpu->kvm->arch.last_vcpu_ran);
+	mmu = vcpu->arch.hw_mmu;
+	last_ran = this_cpu_ptr(mmu->last_vcpu_ran);
 
 	/*
 	 * We might get preempted before the vCPU actually runs, but
 	 * over-invalidation doesn't affect correctness.
 	 */
 	if (*last_ran != vcpu->vcpu_id) {
-		kvm_call_hyp(__kvm_tlb_flush_local_vmid, vcpu);
+		kvm_call_hyp(__kvm_tlb_flush_local_vmid, mmu);
 		*last_ran = vcpu->vcpu_id;
 	}
 
@@ -680,7 +668,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		 */
 		cond_resched();
 
-		update_vmid(&vcpu->kvm->arch.vmid);
+		update_vmid(&vcpu->arch.hw_mmu->vmid);
 
 		check_vcpu_requests(vcpu);
 
@@ -729,7 +717,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		 */
 		smp_store_mb(vcpu->mode, IN_GUEST_MODE);
 
-		if (ret <= 0 || need_new_vmid_gen(&vcpu->kvm->arch.vmid) ||
+		if (ret <= 0 || need_new_vmid_gen(&vcpu->arch.hw_mmu->vmid) ||
 		    kvm_request_pending(vcpu)) {
 			vcpu->mode = OUTSIDE_GUEST_MODE;
 			isb(); /* Ensure work in x_flush_hwstate is committed */
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 8f622688fa64..5c03441b5b6c 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -122,9 +122,9 @@ static inline void ___deactivate_traps(struct kvm_vcpu *vcpu)
 	}
 }
 
-static inline void __activate_vm(struct kvm *kvm)
+static inline void __activate_vm(struct kvm_s2_mmu *mmu)
 {
-	__load_guest_stage2(kvm);
+	__load_guest_stage2(mmu);
 }
 
 static inline bool __translate_far_to_hpfar(u64 far, u64 *hpfar)
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index a1dcf59bd45e..37321b2157d9 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -194,7 +194,7 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 	__sysreg32_restore_state(vcpu);
 	__sysreg_restore_state_nvhe(guest_ctxt);
 
-	__activate_vm(kern_hyp_va(vcpu->kvm));
+	__activate_vm(kern_hyp_va(vcpu->arch.hw_mmu));
 	__activate_traps(vcpu);
 
 	__hyp_vgic_restore_state(vcpu);
diff --git a/arch/arm64/kvm/hyp/nvhe/tlb.c b/arch/arm64/kvm/hyp/nvhe/tlb.c
index d4475f8340c4..11dbe031f0ba 100644
--- a/arch/arm64/kvm/hyp/nvhe/tlb.c
+++ b/arch/arm64/kvm/hyp/nvhe/tlb.c
@@ -12,7 +12,8 @@ struct tlb_inv_context {
 	u64		tcr;
 };
 
-static void __tlb_switch_to_guest(struct kvm *kvm, struct tlb_inv_context *cxt)
+static void __tlb_switch_to_guest(struct kvm_s2_mmu *mmu,
+				  struct tlb_inv_context *cxt)
 {
 	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
 		u64 val;
@@ -30,12 +31,10 @@ static void __tlb_switch_to_guest(struct kvm *kvm, struct tlb_inv_context *cxt)
 		isb();
 	}
 
-	/* __load_guest_stage2() includes an ISB for the workaround. */
-	__load_guest_stage2(kvm);
-	asm(ALTERNATIVE("isb", "nop", ARM64_WORKAROUND_SPECULATIVE_AT));
+	__load_guest_stage2(mmu);
 }
 
-static void __tlb_switch_to_host(struct kvm *kvm, struct tlb_inv_context *cxt)
+static void __tlb_switch_to_host(struct tlb_inv_context *cxt)
 {
 	write_sysreg(0, vttbr_el2);
 
@@ -47,15 +46,15 @@ static void __tlb_switch_to_host(struct kvm *kvm, struct tlb_inv_context *cxt)
 	}
 }
 
-void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
+void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa)
 {
 	struct tlb_inv_context cxt;
 
 	dsb(ishst);
 
 	/* Switch to requested VMID */
-	kvm = kern_hyp_va(kvm);
-	__tlb_switch_to_guest(kvm, &cxt);
+	mmu = kern_hyp_va(mmu);
+	__tlb_switch_to_guest(mmu, &cxt);
 
 	/*
 	 * We could do so much better if we had the VA as well.
@@ -98,39 +97,39 @@ void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 	if (icache_is_vpipt())
 		__flush_icache_all();
 
-	__tlb_switch_to_host(kvm, &cxt);
+	__tlb_switch_to_host(&cxt);
 }
 
-void __kvm_tlb_flush_vmid(struct kvm *kvm)
+void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu)
 {
 	struct tlb_inv_context cxt;
 
 	dsb(ishst);
 
 	/* Switch to requested VMID */
-	kvm = kern_hyp_va(kvm);
-	__tlb_switch_to_guest(kvm, &cxt);
+	mmu = kern_hyp_va(mmu);
+	__tlb_switch_to_guest(mmu, &cxt);
 
 	__tlbi(vmalls12e1is);
 	dsb(ish);
 	isb();
 
-	__tlb_switch_to_host(kvm, &cxt);
+	__tlb_switch_to_host(&cxt);
 }
 
-void __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
+void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu)
 {
-	struct kvm *kvm = kern_hyp_va(kern_hyp_va(vcpu)->kvm);
 	struct tlb_inv_context cxt;
 
 	/* Switch to requested VMID */
-	__tlb_switch_to_guest(kvm, &cxt);
+	mmu = kern_hyp_va(mmu);
+	__tlb_switch_to_guest(mmu, &cxt);
 
 	__tlbi(vmalle1);
 	dsb(nsh);
 	isb();
 
-	__tlb_switch_to_host(kvm, &cxt);
+	__tlb_switch_to_host(&cxt);
 }
 
 void __kvm_flush_vm_context(void)
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index c0d33deba77e..c52d714e0d75 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -125,7 +125,7 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
 	 * stage 2 translation, and __activate_traps clear HCR_EL2.TGE
 	 * (among other things).
 	 */
-	__activate_vm(vcpu->kvm);
+	__activate_vm(vcpu->arch.hw_mmu);
 	__activate_traps(vcpu);
 
 	sysreg_restore_guest_state_vhe(guest_ctxt);
diff --git a/arch/arm64/kvm/hyp/vhe/tlb.c b/arch/arm64/kvm/hyp/vhe/tlb.c
index b275101e9c9c..ada1d56f0709 100644
--- a/arch/arm64/kvm/hyp/vhe/tlb.c
+++ b/arch/arm64/kvm/hyp/vhe/tlb.c
@@ -16,7 +16,8 @@ struct tlb_inv_context {
 	u64		sctlr;
 };
 
-static void __tlb_switch_to_guest(struct kvm *kvm, struct tlb_inv_context *cxt)
+static void __tlb_switch_to_guest(struct kvm_s2_mmu *mmu,
+				  struct tlb_inv_context *cxt)
 {
 	u64 val;
 
@@ -52,14 +53,14 @@ static void __tlb_switch_to_guest(struct kvm *kvm, struct tlb_inv_context *cxt)
 	 * place before clearing TGE. __load_guest_stage2() already
 	 * has an ISB in order to deal with this.
 	 */
-	__load_guest_stage2(kvm);
+	__load_guest_stage2(mmu);
 	val = read_sysreg(hcr_el2);
 	val &= ~HCR_TGE;
 	write_sysreg(val, hcr_el2);
 	isb();
 }
 
-static void __tlb_switch_to_host(struct kvm *kvm, struct tlb_inv_context *cxt)
+static void __tlb_switch_to_host(struct tlb_inv_context *cxt)
 {
 	/*
 	 * We're done with the TLB operation, let's restore the host's
@@ -78,14 +79,14 @@ static void __tlb_switch_to_host(struct kvm *kvm, struct tlb_inv_context *cxt)
 	local_irq_restore(cxt->flags);
 }
 
-void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
+void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa)
 {
 	struct tlb_inv_context cxt;
 
 	dsb(ishst);
 
 	/* Switch to requested VMID */
-	__tlb_switch_to_guest(kvm, &cxt);
+	__tlb_switch_to_guest(mmu, &cxt);
 
 	/*
 	 * We could do so much better if we had the VA as well.
@@ -106,38 +107,37 @@ void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 	dsb(ish);
 	isb();
 
-	__tlb_switch_to_host(kvm, &cxt);
+	__tlb_switch_to_host(&cxt);
 }
 
-void __kvm_tlb_flush_vmid(struct kvm *kvm)
+void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu)
 {
 	struct tlb_inv_context cxt;
 
 	dsb(ishst);
 
 	/* Switch to requested VMID */
-	__tlb_switch_to_guest(kvm, &cxt);
+	__tlb_switch_to_guest(mmu, &cxt);
 
 	__tlbi(vmalls12e1is);
 	dsb(ish);
 	isb();
 
-	__tlb_switch_to_host(kvm, &cxt);
+	__tlb_switch_to_host(&cxt);
 }
 
-void __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
+void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu)
 {
-	struct kvm *kvm = vcpu->kvm;
 	struct tlb_inv_context cxt;
 
 	/* Switch to requested VMID */
-	__tlb_switch_to_guest(kvm, &cxt);
+	__tlb_switch_to_guest(mmu, &cxt);
 
 	__tlbi(vmalle1);
 	dsb(nsh);
 	isb();
 
-	__tlb_switch_to_host(kvm, &cxt);
+	__tlb_switch_to_host(&cxt);
 }
 
 void __kvm_flush_vm_context(void)
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 8c0035cab6b6..2c6d59b509a5 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -55,12 +55,12 @@ static bool memslot_is_logging(struct kvm_memory_slot *memslot)
  */
 void kvm_flush_remote_tlbs(struct kvm *kvm)
 {
-	kvm_call_hyp(__kvm_tlb_flush_vmid, kvm);
+	kvm_call_hyp(__kvm_tlb_flush_vmid, &kvm->arch.mmu);
 }
 
-static void kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
+static void kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa)
 {
-	kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, kvm, ipa);
+	kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ipa);
 }
 
 /*
@@ -90,37 +90,39 @@ static bool kvm_is_device_pfn(unsigned long pfn)
 
 /**
  * stage2_dissolve_pmd() - clear and flush huge PMD entry
- * @kvm:	pointer to kvm structure.
+ * @mmu:	pointer to mmu structure to operate on
  * @addr:	IPA
  * @pmd:	pmd pointer for IPA
  *
  * Function clears a PMD entry, flushes addr 1st and 2nd stage TLBs.
  */
-static void stage2_dissolve_pmd(struct kvm *kvm, phys_addr_t addr, pmd_t *pmd)
+static void stage2_dissolve_pmd(struct kvm_s2_mmu *mmu, phys_addr_t addr, pmd_t *pmd)
 {
 	if (!pmd_thp_or_huge(*pmd))
 		return;
 
 	pmd_clear(pmd);
-	kvm_tlb_flush_vmid_ipa(kvm, addr);
+	kvm_tlb_flush_vmid_ipa(mmu, addr);
 	put_page(virt_to_page(pmd));
 }
 
 /**
  * stage2_dissolve_pud() - clear and flush huge PUD entry
- * @kvm:	pointer to kvm structure.
+ * @mmu:	pointer to mmu structure to operate on
  * @addr:	IPA
  * @pud:	pud pointer for IPA
  *
  * Function clears a PUD entry, flushes addr 1st and 2nd stage TLBs.
  */
-static void stage2_dissolve_pud(struct kvm *kvm, phys_addr_t addr, pud_t *pudp)
+static void stage2_dissolve_pud(struct kvm_s2_mmu *mmu, phys_addr_t addr, pud_t *pudp)
 {
+	struct kvm *kvm = mmu->kvm;
+
 	if (!stage2_pud_huge(kvm, *pudp))
 		return;
 
 	stage2_pud_clear(kvm, pudp);
-	kvm_tlb_flush_vmid_ipa(kvm, addr);
+	kvm_tlb_flush_vmid_ipa(mmu, addr);
 	put_page(virt_to_page(pudp));
 }
 
@@ -156,40 +158,44 @@ static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc)
 	return p;
 }
 
-static void clear_stage2_pgd_entry(struct kvm *kvm, pgd_t *pgd, phys_addr_t addr)
+static void clear_stage2_pgd_entry(struct kvm_s2_mmu *mmu, pgd_t *pgd, phys_addr_t addr)
 {
+	struct kvm *kvm = mmu->kvm;
 	p4d_t *p4d_table __maybe_unused = stage2_p4d_offset(kvm, pgd, 0UL);
 	stage2_pgd_clear(kvm, pgd);
-	kvm_tlb_flush_vmid_ipa(kvm, addr);
+	kvm_tlb_flush_vmid_ipa(mmu, addr);
 	stage2_p4d_free(kvm, p4d_table);
 	put_page(virt_to_page(pgd));
 }
 
-static void clear_stage2_p4d_entry(struct kvm *kvm, p4d_t *p4d, phys_addr_t addr)
+static void clear_stage2_p4d_entry(struct kvm_s2_mmu *mmu, p4d_t *p4d, phys_addr_t addr)
 {
+	struct kvm *kvm = mmu->kvm;
 	pud_t *pud_table __maybe_unused = stage2_pud_offset(kvm, p4d, 0);
 	stage2_p4d_clear(kvm, p4d);
-	kvm_tlb_flush_vmid_ipa(kvm, addr);
+	kvm_tlb_flush_vmid_ipa(mmu, addr);
 	stage2_pud_free(kvm, pud_table);
 	put_page(virt_to_page(p4d));
 }
 
-static void clear_stage2_pud_entry(struct kvm *kvm, pud_t *pud, phys_addr_t addr)
+static void clear_stage2_pud_entry(struct kvm_s2_mmu *mmu, pud_t *pud, phys_addr_t addr)
 {
+	struct kvm *kvm = mmu->kvm;
 	pmd_t *pmd_table __maybe_unused = stage2_pmd_offset(kvm, pud, 0);
+
 	VM_BUG_ON(stage2_pud_huge(kvm, *pud));
 	stage2_pud_clear(kvm, pud);
-	kvm_tlb_flush_vmid_ipa(kvm, addr);
+	kvm_tlb_flush_vmid_ipa(mmu, addr);
 	stage2_pmd_free(kvm, pmd_table);
 	put_page(virt_to_page(pud));
 }
 
-static void clear_stage2_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr)
+static void clear_stage2_pmd_entry(struct kvm_s2_mmu *mmu, pmd_t *pmd, phys_addr_t addr)
 {
 	pte_t *pte_table = pte_offset_kernel(pmd, 0);
 	VM_BUG_ON(pmd_thp_or_huge(*pmd));
 	pmd_clear(pmd);
-	kvm_tlb_flush_vmid_ipa(kvm, addr);
+	kvm_tlb_flush_vmid_ipa(mmu, addr);
 	free_page((unsigned long)pte_table);
 	put_page(virt_to_page(pmd));
 }
@@ -255,7 +261,7 @@ static inline void kvm_pgd_populate(pgd_t *pgdp, p4d_t *p4dp)
  * we then fully enforce cacheability of RAM, no matter what the guest
  * does.
  */
-static void unmap_stage2_ptes(struct kvm *kvm, pmd_t *pmd,
+static void unmap_stage2_ptes(struct kvm_s2_mmu *mmu, pmd_t *pmd,
 		       phys_addr_t addr, phys_addr_t end)
 {
 	phys_addr_t start_addr = addr;
@@ -267,7 +273,7 @@ static void unmap_stage2_ptes(struct kvm *kvm, pmd_t *pmd,
 			pte_t old_pte = *pte;
 
 			kvm_set_pte(pte, __pte(0));
-			kvm_tlb_flush_vmid_ipa(kvm, addr);
+			kvm_tlb_flush_vmid_ipa(mmu, addr);
 
 			/* No need to invalidate the cache for device mappings */
 			if (!kvm_is_device_pfn(pte_pfn(old_pte)))
@@ -277,13 +283,14 @@ static void unmap_stage2_ptes(struct kvm *kvm, pmd_t *pmd,
 		}
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 
-	if (stage2_pte_table_empty(kvm, start_pte))
-		clear_stage2_pmd_entry(kvm, pmd, start_addr);
+	if (stage2_pte_table_empty(mmu->kvm, start_pte))
+		clear_stage2_pmd_entry(mmu, pmd, start_addr);
 }
 
-static void unmap_stage2_pmds(struct kvm *kvm, pud_t *pud,
+static void unmap_stage2_pmds(struct kvm_s2_mmu *mmu, pud_t *pud,
 		       phys_addr_t addr, phys_addr_t end)
 {
+	struct kvm *kvm = mmu->kvm;
 	phys_addr_t next, start_addr = addr;
 	pmd_t *pmd, *start_pmd;
 
@@ -295,24 +302,25 @@ static void unmap_stage2_pmds(struct kvm *kvm, pud_t *pud,
 				pmd_t old_pmd = *pmd;
 
 				pmd_clear(pmd);
-				kvm_tlb_flush_vmid_ipa(kvm, addr);
+				kvm_tlb_flush_vmid_ipa(mmu, addr);
 
 				kvm_flush_dcache_pmd(old_pmd);
 
 				put_page(virt_to_page(pmd));
 			} else {
-				unmap_stage2_ptes(kvm, pmd, addr, next);
+				unmap_stage2_ptes(mmu, pmd, addr, next);
 			}
 		}
 	} while (pmd++, addr = next, addr != end);
 
 	if (stage2_pmd_table_empty(kvm, start_pmd))
-		clear_stage2_pud_entry(kvm, pud, start_addr);
+		clear_stage2_pud_entry(mmu, pud, start_addr);
 }
 
-static void unmap_stage2_puds(struct kvm *kvm, p4d_t *p4d,
+static void unmap_stage2_puds(struct kvm_s2_mmu *mmu, p4d_t *p4d,
 		       phys_addr_t addr, phys_addr_t end)
 {
+	struct kvm *kvm = mmu->kvm;
 	phys_addr_t next, start_addr = addr;
 	pud_t *pud, *start_pud;
 
@@ -324,22 +332,23 @@ static void unmap_stage2_puds(struct kvm *kvm, p4d_t *p4d,
 				pud_t old_pud = *pud;
 
 				stage2_pud_clear(kvm, pud);
-				kvm_tlb_flush_vmid_ipa(kvm, addr);
+				kvm_tlb_flush_vmid_ipa(mmu, addr);
 				kvm_flush_dcache_pud(old_pud);
 				put_page(virt_to_page(pud));
 			} else {
-				unmap_stage2_pmds(kvm, pud, addr, next);
+				unmap_stage2_pmds(mmu, pud, addr, next);
 			}
 		}
 	} while (pud++, addr = next, addr != end);
 
 	if (stage2_pud_table_empty(kvm, start_pud))
-		clear_stage2_p4d_entry(kvm, p4d, start_addr);
+		clear_stage2_p4d_entry(mmu, p4d, start_addr);
 }
 
-static void unmap_stage2_p4ds(struct kvm *kvm, pgd_t *pgd,
+static void unmap_stage2_p4ds(struct kvm_s2_mmu *mmu, pgd_t *pgd,
 		       phys_addr_t addr, phys_addr_t end)
 {
+	struct kvm *kvm = mmu->kvm;
 	phys_addr_t next, start_addr = addr;
 	p4d_t *p4d, *start_p4d;
 
@@ -347,11 +356,11 @@ static void unmap_stage2_p4ds(struct kvm *kvm, pgd_t *pgd,
 	do {
 		next = stage2_p4d_addr_end(kvm, addr, end);
 		if (!stage2_p4d_none(kvm, *p4d))
-			unmap_stage2_puds(kvm, p4d, addr, next);
+			unmap_stage2_puds(mmu, p4d, addr, next);
 	} while (p4d++, addr = next, addr != end);
 
 	if (stage2_p4d_table_empty(kvm, start_p4d))
-		clear_stage2_pgd_entry(kvm, pgd, start_addr);
+		clear_stage2_pgd_entry(mmu, pgd, start_addr);
 }
 
 /**
@@ -365,8 +374,9 @@ static void unmap_stage2_p4ds(struct kvm *kvm, pgd_t *pgd,
  * destroying the VM), otherwise another faulting VCPU may come in and mess
  * with things behind our backs.
  */
-static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size)
+static void unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size)
 {
+	struct kvm *kvm = mmu->kvm;
 	pgd_t *pgd;
 	phys_addr_t addr = start, end = start + size;
 	phys_addr_t next;
@@ -374,18 +384,18 @@ static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size)
 	assert_spin_locked(&kvm->mmu_lock);
 	WARN_ON(size & ~PAGE_MASK);
 
-	pgd = kvm->arch.pgd + stage2_pgd_index(kvm, addr);
+	pgd = mmu->pgd + stage2_pgd_index(kvm, addr);
 	do {
 		/*
 		 * Make sure the page table is still active, as another thread
 		 * could have possibly freed the page table, while we released
 		 * the lock.
 		 */
-		if (!READ_ONCE(kvm->arch.pgd))
+		if (!READ_ONCE(mmu->pgd))
 			break;
 		next = stage2_pgd_addr_end(kvm, addr, end);
 		if (!stage2_pgd_none(kvm, *pgd))
-			unmap_stage2_p4ds(kvm, pgd, addr, next);
+			unmap_stage2_p4ds(mmu, pgd, addr, next);
 		/*
 		 * If the range is too large, release the kvm->mmu_lock
 		 * to prevent starvation and lockup detector warnings.
@@ -395,7 +405,7 @@ static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size)
 	} while (pgd++, addr = next, addr != end);
 }
 
-static void stage2_flush_ptes(struct kvm *kvm, pmd_t *pmd,
+static void stage2_flush_ptes(struct kvm_s2_mmu *mmu, pmd_t *pmd,
 			      phys_addr_t addr, phys_addr_t end)
 {
 	pte_t *pte;
@@ -407,9 +417,10 @@ static void stage2_flush_ptes(struct kvm *kvm, pmd_t *pmd,
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 }
 
-static void stage2_flush_pmds(struct kvm *kvm, pud_t *pud,
+static void stage2_flush_pmds(struct kvm_s2_mmu *mmu, pud_t *pud,
 			      phys_addr_t addr, phys_addr_t end)
 {
+	struct kvm *kvm = mmu->kvm;
 	pmd_t *pmd;
 	phys_addr_t next;
 
@@ -420,14 +431,15 @@ static void stage2_flush_pmds(struct kvm *kvm, pud_t *pud,
 			if (pmd_thp_or_huge(*pmd))
 				kvm_flush_dcache_pmd(*pmd);
 			else
-				stage2_flush_ptes(kvm, pmd, addr, next);
+				stage2_flush_ptes(mmu, pmd, addr, next);
 		}
 	} while (pmd++, addr = next, addr != end);
 }
 
-static void stage2_flush_puds(struct kvm *kvm, p4d_t *p4d,
+static void stage2_flush_puds(struct kvm_s2_mmu *mmu, p4d_t *p4d,
 			      phys_addr_t addr, phys_addr_t end)
 {
+	struct kvm *kvm = mmu->kvm;
 	pud_t *pud;
 	phys_addr_t next;
 
@@ -438,14 +450,15 @@ static void stage2_flush_puds(struct kvm *kvm, p4d_t *p4d,
 			if (stage2_pud_huge(kvm, *pud))
 				kvm_flush_dcache_pud(*pud);
 			else
-				stage2_flush_pmds(kvm, pud, addr, next);
+				stage2_flush_pmds(mmu, pud, addr, next);
 		}
 	} while (pud++, addr = next, addr != end);
 }
 
-static void stage2_flush_p4ds(struct kvm *kvm, pgd_t *pgd,
+static void stage2_flush_p4ds(struct kvm_s2_mmu *mmu, pgd_t *pgd,
 			      phys_addr_t addr, phys_addr_t end)
 {
+	struct kvm *kvm = mmu->kvm;
 	p4d_t *p4d;
 	phys_addr_t next;
 
@@ -453,23 +466,24 @@ static void stage2_flush_p4ds(struct kvm *kvm, pgd_t *pgd,
 	do {
 		next = stage2_p4d_addr_end(kvm, addr, end);
 		if (!stage2_p4d_none(kvm, *p4d))
-			stage2_flush_puds(kvm, p4d, addr, next);
+			stage2_flush_puds(mmu, p4d, addr, next);
 	} while (p4d++, addr = next, addr != end);
 }
 
 static void stage2_flush_memslot(struct kvm *kvm,
 				 struct kvm_memory_slot *memslot)
 {
+	struct kvm_s2_mmu *mmu = &kvm->arch.mmu;
 	phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT;
 	phys_addr_t end = addr + PAGE_SIZE * memslot->npages;
 	phys_addr_t next;
 	pgd_t *pgd;
 
-	pgd = kvm->arch.pgd + stage2_pgd_index(kvm, addr);
+	pgd = mmu->pgd + stage2_pgd_index(kvm, addr);
 	do {
 		next = stage2_pgd_addr_end(kvm, addr, end);
 		if (!stage2_pgd_none(kvm, *pgd))
-			stage2_flush_p4ds(kvm, pgd, addr, next);
+			stage2_flush_p4ds(mmu, pgd, addr, next);
 
 		if (next != end)
 			cond_resched_lock(&kvm->mmu_lock);
@@ -996,21 +1010,23 @@ int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size,
 }
 
 /**
- * kvm_alloc_stage2_pgd - allocate level-1 table for stage-2 translation.
- * @kvm:	The KVM struct pointer for the VM.
+ * kvm_init_stage2_mmu - Initialise a S2 MMU strucrure
+ * @kvm:	The pointer to the KVM structure
+ * @mmu:	The pointer to the s2 MMU structure
  *
  * Allocates only the stage-2 HW PGD level table(s) of size defined by
- * stage2_pgd_size(kvm).
+ * stage2_pgd_size(mmu->kvm).
  *
  * Note we don't need locking here as this is only called when the VM is
  * created, which can only be done once.
  */
-int kvm_alloc_stage2_pgd(struct kvm *kvm)
+int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu)
 {
 	phys_addr_t pgd_phys;
 	pgd_t *pgd;
+	int cpu;
 
-	if (kvm->arch.pgd != NULL) {
+	if (mmu->pgd != NULL) {
 		kvm_err("kvm_arch already initialized?\n");
 		return -EINVAL;
 	}
@@ -1024,8 +1040,20 @@ int kvm_alloc_stage2_pgd(struct kvm *kvm)
 	if (WARN_ON(pgd_phys & ~kvm_vttbr_baddr_mask(kvm)))
 		return -EINVAL;
 
-	kvm->arch.pgd = pgd;
-	kvm->arch.pgd_phys = pgd_phys;
+	mmu->last_vcpu_ran = alloc_percpu(typeof(*mmu->last_vcpu_ran));
+	if (!mmu->last_vcpu_ran) {
+		free_pages_exact(pgd, stage2_pgd_size(kvm));
+		return -ENOMEM;
+	}
+
+	for_each_possible_cpu(cpu)
+		*per_cpu_ptr(mmu->last_vcpu_ran, cpu) = -1;
+
+	mmu->kvm = kvm;
+	mmu->pgd = pgd;
+	mmu->pgd_phys = pgd_phys;
+	mmu->vmid.vmid_gen = 0;
+
 	return 0;
 }
 
@@ -1064,7 +1092,7 @@ static void stage2_unmap_memslot(struct kvm *kvm,
 
 		if (!(vma->vm_flags & VM_PFNMAP)) {
 			gpa_t gpa = addr + (vm_start - memslot->userspace_addr);
-			unmap_stage2_range(kvm, gpa, vm_end - vm_start);
+			unmap_stage2_range(&kvm->arch.mmu, gpa, vm_end - vm_start);
 		}
 		hva = vm_end;
 	} while (hva < reg_end);
@@ -1096,39 +1124,34 @@ void stage2_unmap_vm(struct kvm *kvm)
 	srcu_read_unlock(&kvm->srcu, idx);
 }
 
-/**
- * kvm_free_stage2_pgd - free all stage-2 tables
- * @kvm:	The KVM struct pointer for the VM.
- *
- * Walks the level-1 page table pointed to by kvm->arch.pgd and frees all
- * underlying level-2 and level-3 tables before freeing the actual level-1 table
- * and setting the struct pointer to NULL.
- */
-void kvm_free_stage2_pgd(struct kvm *kvm)
+void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu)
 {
+	struct kvm *kvm = mmu->kvm;
 	void *pgd = NULL;
 
 	spin_lock(&kvm->mmu_lock);
-	if (kvm->arch.pgd) {
-		unmap_stage2_range(kvm, 0, kvm_phys_size(kvm));
-		pgd = READ_ONCE(kvm->arch.pgd);
-		kvm->arch.pgd = NULL;
-		kvm->arch.pgd_phys = 0;
+	if (mmu->pgd) {
+		unmap_stage2_range(mmu, 0, kvm_phys_size(kvm));
+		pgd = READ_ONCE(mmu->pgd);
+		mmu->pgd = NULL;
 	}
 	spin_unlock(&kvm->mmu_lock);
 
 	/* Free the HW pgd, one page at a time */
-	if (pgd)
+	if (pgd) {
 		free_pages_exact(pgd, stage2_pgd_size(kvm));
+		free_percpu(mmu->last_vcpu_ran);
+	}
 }
 
-static p4d_t *stage2_get_p4d(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
+static p4d_t *stage2_get_p4d(struct kvm_s2_mmu *mmu, struct kvm_mmu_memory_cache *cache,
 			     phys_addr_t addr)
 {
+	struct kvm *kvm = mmu->kvm;
 	pgd_t *pgd;
 	p4d_t *p4d;
 
-	pgd = kvm->arch.pgd + stage2_pgd_index(kvm, addr);
+	pgd = mmu->pgd + stage2_pgd_index(kvm, addr);
 	if (stage2_pgd_none(kvm, *pgd)) {
 		if (!cache)
 			return NULL;
@@ -1140,13 +1163,14 @@ static p4d_t *stage2_get_p4d(struct kvm *kvm, struct kvm_mmu_memory_cache *cache
 	return stage2_p4d_offset(kvm, pgd, addr);
 }
 
-static pud_t *stage2_get_pud(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
+static pud_t *stage2_get_pud(struct kvm_s2_mmu *mmu, struct kvm_mmu_memory_cache *cache,
 			     phys_addr_t addr)
 {
+	struct kvm *kvm = mmu->kvm;
 	p4d_t *p4d;
 	pud_t *pud;
 
-	p4d = stage2_get_p4d(kvm, cache, addr);
+	p4d = stage2_get_p4d(mmu, cache, addr);
 	if (stage2_p4d_none(kvm, *p4d)) {
 		if (!cache)
 			return NULL;
@@ -1158,13 +1182,14 @@ static pud_t *stage2_get_pud(struct kvm *kvm, struct kvm_mmu_memory_cache *cache
 	return stage2_pud_offset(kvm, p4d, addr);
 }
 
-static pmd_t *stage2_get_pmd(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
+static pmd_t *stage2_get_pmd(struct kvm_s2_mmu *mmu, struct kvm_mmu_memory_cache *cache,
 			     phys_addr_t addr)
 {
+	struct kvm *kvm = mmu->kvm;
 	pud_t *pud;
 	pmd_t *pmd;
 
-	pud = stage2_get_pud(kvm, cache, addr);
+	pud = stage2_get_pud(mmu, cache, addr);
 	if (!pud || stage2_pud_huge(kvm, *pud))
 		return NULL;
 
@@ -1179,13 +1204,14 @@ static pmd_t *stage2_get_pmd(struct kvm *kvm, struct kvm_mmu_memory_cache *cache
 	return stage2_pmd_offset(kvm, pud, addr);
 }
 
-static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache
-			       *cache, phys_addr_t addr, const pmd_t *new_pmd)
+static int stage2_set_pmd_huge(struct kvm_s2_mmu *mmu,
+			       struct kvm_mmu_memory_cache *cache,
+			       phys_addr_t addr, const pmd_t *new_pmd)
 {
 	pmd_t *pmd, old_pmd;
 
 retry:
-	pmd = stage2_get_pmd(kvm, cache, addr);
+	pmd = stage2_get_pmd(mmu, cache, addr);
 	VM_BUG_ON(!pmd);
 
 	old_pmd = *pmd;
@@ -1218,7 +1244,7 @@ retry:
 		 * get handled accordingly.
 		 */
 		if (!pmd_thp_or_huge(old_pmd)) {
-			unmap_stage2_range(kvm, addr & S2_PMD_MASK, S2_PMD_SIZE);
+			unmap_stage2_range(mmu, addr & S2_PMD_MASK, S2_PMD_SIZE);
 			goto retry;
 		}
 		/*
@@ -1234,7 +1260,7 @@ retry:
 		 */
 		WARN_ON_ONCE(pmd_pfn(old_pmd) != pmd_pfn(*new_pmd));
 		pmd_clear(pmd);
-		kvm_tlb_flush_vmid_ipa(kvm, addr);
+		kvm_tlb_flush_vmid_ipa(mmu, addr);
 	} else {
 		get_page(virt_to_page(pmd));
 	}
@@ -1243,13 +1269,15 @@ retry:
 	return 0;
 }
 
-static int stage2_set_pud_huge(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
+static int stage2_set_pud_huge(struct kvm_s2_mmu *mmu,
+			       struct kvm_mmu_memory_cache *cache,
 			       phys_addr_t addr, const pud_t *new_pudp)
 {
+	struct kvm *kvm = mmu->kvm;
 	pud_t *pudp, old_pud;
 
 retry:
-	pudp = stage2_get_pud(kvm, cache, addr);
+	pudp = stage2_get_pud(mmu, cache, addr);
 	VM_BUG_ON(!pudp);
 
 	old_pud = *pudp;
@@ -1268,13 +1296,13 @@ retry:
 		 * the range for this block and retry.
 		 */
 		if (!stage2_pud_huge(kvm, old_pud)) {
-			unmap_stage2_range(kvm, addr & S2_PUD_MASK, S2_PUD_SIZE);
+			unmap_stage2_range(mmu, addr & S2_PUD_MASK, S2_PUD_SIZE);
 			goto retry;
 		}
 
 		WARN_ON_ONCE(kvm_pud_pfn(old_pud) != kvm_pud_pfn(*new_pudp));
 		stage2_pud_clear(kvm, pudp);
-		kvm_tlb_flush_vmid_ipa(kvm, addr);
+		kvm_tlb_flush_vmid_ipa(mmu, addr);
 	} else {
 		get_page(virt_to_page(pudp));
 	}
@@ -1289,9 +1317,10 @@ retry:
  * leaf-entry is returned in the appropriate level variable - pudpp,
  * pmdpp, ptepp.
  */
-static bool stage2_get_leaf_entry(struct kvm *kvm, phys_addr_t addr,
+static bool stage2_get_leaf_entry(struct kvm_s2_mmu *mmu, phys_addr_t addr,
 				  pud_t **pudpp, pmd_t **pmdpp, pte_t **ptepp)
 {
+	struct kvm *kvm = mmu->kvm;
 	pud_t *pudp;
 	pmd_t *pmdp;
 	pte_t *ptep;
@@ -1300,7 +1329,7 @@ static bool stage2_get_leaf_entry(struct kvm *kvm, phys_addr_t addr,
 	*pmdpp = NULL;
 	*ptepp = NULL;
 
-	pudp = stage2_get_pud(kvm, NULL, addr);
+	pudp = stage2_get_pud(mmu, NULL, addr);
 	if (!pudp || stage2_pud_none(kvm, *pudp) || !stage2_pud_present(kvm, *pudp))
 		return false;
 
@@ -1326,14 +1355,14 @@ static bool stage2_get_leaf_entry(struct kvm *kvm, phys_addr_t addr,
 	return true;
 }
 
-static bool stage2_is_exec(struct kvm *kvm, phys_addr_t addr)
+static bool stage2_is_exec(struct kvm_s2_mmu *mmu, phys_addr_t addr)
 {
 	pud_t *pudp;
 	pmd_t *pmdp;
 	pte_t *ptep;
 	bool found;
 
-	found = stage2_get_leaf_entry(kvm, addr, &pudp, &pmdp, &ptep);
+	found = stage2_get_leaf_entry(mmu, addr, &pudp, &pmdp, &ptep);
 	if (!found)
 		return false;
 
@@ -1345,10 +1374,12 @@ static bool stage2_is_exec(struct kvm *kvm, phys_addr_t addr)
 		return kvm_s2pte_exec(ptep);
 }
 
-static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
+static int stage2_set_pte(struct kvm_s2_mmu *mmu,
+			  struct kvm_mmu_memory_cache *cache,
 			  phys_addr_t addr, const pte_t *new_pte,
 			  unsigned long flags)
 {
+	struct kvm *kvm = mmu->kvm;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte, old_pte;
@@ -1358,7 +1389,7 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
 	VM_BUG_ON(logging_active && !cache);
 
 	/* Create stage-2 page table mapping - Levels 0 and 1 */
-	pud = stage2_get_pud(kvm, cache, addr);
+	pud = stage2_get_pud(mmu, cache, addr);
 	if (!pud) {
 		/*
 		 * Ignore calls from kvm_set_spte_hva for unallocated
@@ -1372,7 +1403,7 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
 	 * on to allocate page.
 	 */
 	if (logging_active)
-		stage2_dissolve_pud(kvm, addr, pud);
+		stage2_dissolve_pud(mmu, addr, pud);
 
 	if (stage2_pud_none(kvm, *pud)) {
 		if (!cache)
@@ -1396,7 +1427,7 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
 	 * allocate page.
 	 */
 	if (logging_active)
-		stage2_dissolve_pmd(kvm, addr, pmd);
+		stage2_dissolve_pmd(mmu, addr, pmd);
 
 	/* Create stage-2 page mappings - Level 2 */
 	if (pmd_none(*pmd)) {
@@ -1420,7 +1451,7 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
 			return 0;
 
 		kvm_set_pte(pte, __pte(0));
-		kvm_tlb_flush_vmid_ipa(kvm, addr);
+		kvm_tlb_flush_vmid_ipa(mmu, addr);
 	} else {
 		get_page(virt_to_page(pte));
 	}
@@ -1486,8 +1517,8 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
 		if (ret)
 			goto out;
 		spin_lock(&kvm->mmu_lock);
-		ret = stage2_set_pte(kvm, &cache, addr, &pte,
-						KVM_S2PTE_FLAG_IS_IOMAP);
+		ret = stage2_set_pte(&kvm->arch.mmu, &cache, addr, &pte,
+				     KVM_S2PTE_FLAG_IS_IOMAP);
 		spin_unlock(&kvm->mmu_lock);
 		if (ret)
 			goto out;
@@ -1526,9 +1557,10 @@ static void stage2_wp_ptes(pmd_t *pmd, phys_addr_t addr, phys_addr_t end)
  * @addr:	range start address
  * @end:	range end address
  */
-static void stage2_wp_pmds(struct kvm *kvm, pud_t *pud,
+static void stage2_wp_pmds(struct kvm_s2_mmu *mmu, pud_t *pud,
 			   phys_addr_t addr, phys_addr_t end)
 {
+	struct kvm *kvm = mmu->kvm;
 	pmd_t *pmd;
 	phys_addr_t next;
 
@@ -1549,13 +1581,14 @@ static void stage2_wp_pmds(struct kvm *kvm, pud_t *pud,
 
 /**
  * stage2_wp_puds - write protect P4D range
- * @pgd:	pointer to pgd entry
+ * @p4d:	pointer to p4d entry
  * @addr:	range start address
  * @end:	range end address
  */
-static void  stage2_wp_puds(struct kvm *kvm, p4d_t *p4d,
+static void  stage2_wp_puds(struct kvm_s2_mmu *mmu, p4d_t *p4d,
 			    phys_addr_t addr, phys_addr_t end)
 {
+	struct kvm *kvm = mmu->kvm;
 	pud_t *pud;
 	phys_addr_t next;
 
@@ -1567,7 +1600,7 @@ static void  stage2_wp_puds(struct kvm *kvm, p4d_t *p4d,
 				if (!kvm_s2pud_readonly(pud))
 					kvm_set_s2pud_readonly(pud);
 			} else {
-				stage2_wp_pmds(kvm, pud, addr, next);
+				stage2_wp_pmds(mmu, pud, addr, next);
 			}
 		}
 	} while (pud++, addr = next, addr != end);
@@ -1579,9 +1612,10 @@ static void  stage2_wp_puds(struct kvm *kvm, p4d_t *p4d,
  * @addr:	range start address
  * @end:	range end address
  */
-static void  stage2_wp_p4ds(struct kvm *kvm, pgd_t *pgd,
+static void  stage2_wp_p4ds(struct kvm_s2_mmu *mmu, pgd_t *pgd,
 			    phys_addr_t addr, phys_addr_t end)
 {
+	struct kvm *kvm = mmu->kvm;
 	p4d_t *p4d;
 	phys_addr_t next;
 
@@ -1589,7 +1623,7 @@ static void  stage2_wp_p4ds(struct kvm *kvm, pgd_t *pgd,
 	do {
 		next = stage2_p4d_addr_end(kvm, addr, end);
 		if (!stage2_p4d_none(kvm, *p4d))
-			stage2_wp_puds(kvm, p4d, addr, next);
+			stage2_wp_puds(mmu, p4d, addr, next);
 	} while (p4d++, addr = next, addr != end);
 }
 
@@ -1599,12 +1633,13 @@ static void  stage2_wp_p4ds(struct kvm *kvm, pgd_t *pgd,
  * @addr:	Start address of range
  * @end:	End address of range
  */
-static void stage2_wp_range(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
+static void stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end)
 {
+	struct kvm *kvm = mmu->kvm;
 	pgd_t *pgd;
 	phys_addr_t next;
 
-	pgd = kvm->arch.pgd + stage2_pgd_index(kvm, addr);
+	pgd = mmu->pgd + stage2_pgd_index(kvm, addr);
 	do {
 		/*
 		 * Release kvm_mmu_lock periodically if the memory region is
@@ -1616,11 +1651,11 @@ static void stage2_wp_range(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
 		 * the lock.
 		 */
 		cond_resched_lock(&kvm->mmu_lock);
-		if (!READ_ONCE(kvm->arch.pgd))
+		if (!READ_ONCE(mmu->pgd))
 			break;
 		next = stage2_pgd_addr_end(kvm, addr, end);
 		if (stage2_pgd_present(kvm, *pgd))
-			stage2_wp_p4ds(kvm, pgd, addr, next);
+			stage2_wp_p4ds(mmu, pgd, addr, next);
 	} while (pgd++, addr = next, addr != end);
 }
 
@@ -1650,7 +1685,7 @@ void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot)
 	end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT;
 
 	spin_lock(&kvm->mmu_lock);
-	stage2_wp_range(kvm, start, end);
+	stage2_wp_range(&kvm->arch.mmu, start, end);
 	spin_unlock(&kvm->mmu_lock);
 	kvm_flush_remote_tlbs(kvm);
 }
@@ -1674,7 +1709,7 @@ static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm,
 	phys_addr_t start = (base_gfn +  __ffs(mask)) << PAGE_SHIFT;
 	phys_addr_t end = (base_gfn + __fls(mask) + 1) << PAGE_SHIFT;
 
-	stage2_wp_range(kvm, start, end);
+	stage2_wp_range(&kvm->arch.mmu, start, end);
 }
 
 /*
@@ -1837,6 +1872,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	pgprot_t mem_type = PAGE_S2;
 	bool logging_active = memslot_is_logging(memslot);
 	unsigned long vma_pagesize, flags = 0;
+	struct kvm_s2_mmu *mmu = vcpu->arch.hw_mmu;
 
 	write_fault = kvm_is_write_fault(vcpu);
 	exec_fault = kvm_vcpu_trap_is_iabt(vcpu);
@@ -1958,7 +1994,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 * execute permissions, and we preserve whatever we have.
 	 */
 	needs_exec = exec_fault ||
-		(fault_status == FSC_PERM && stage2_is_exec(kvm, fault_ipa));
+		(fault_status == FSC_PERM && stage2_is_exec(mmu, fault_ipa));
 
 	if (vma_pagesize == PUD_SIZE) {
 		pud_t new_pud = kvm_pfn_pud(pfn, mem_type);
@@ -1970,7 +2006,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		if (needs_exec)
 			new_pud = kvm_s2pud_mkexec(new_pud);
 
-		ret = stage2_set_pud_huge(kvm, memcache, fault_ipa, &new_pud);
+		ret = stage2_set_pud_huge(mmu, memcache, fault_ipa, &new_pud);
 	} else if (vma_pagesize == PMD_SIZE) {
 		pmd_t new_pmd = kvm_pfn_pmd(pfn, mem_type);
 
@@ -1982,7 +2018,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		if (needs_exec)
 			new_pmd = kvm_s2pmd_mkexec(new_pmd);
 
-		ret = stage2_set_pmd_huge(kvm, memcache, fault_ipa, &new_pmd);
+		ret = stage2_set_pmd_huge(mmu, memcache, fault_ipa, &new_pmd);
 	} else {
 		pte_t new_pte = kvm_pfn_pte(pfn, mem_type);
 
@@ -1994,7 +2030,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		if (needs_exec)
 			new_pte = kvm_s2pte_mkexec(new_pte);
 
-		ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte, flags);
+		ret = stage2_set_pte(mmu, memcache, fault_ipa, &new_pte, flags);
 	}
 
 out_unlock:
@@ -2023,7 +2059,7 @@ static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
 
 	spin_lock(&vcpu->kvm->mmu_lock);
 
-	if (!stage2_get_leaf_entry(vcpu->kvm, fault_ipa, &pud, &pmd, &pte))
+	if (!stage2_get_leaf_entry(vcpu->arch.hw_mmu, fault_ipa, &pud, &pmd, &pte))
 		goto out;
 
 	if (pud) {		/* HugeTLB */
@@ -2197,14 +2233,14 @@ static int handle_hva_to_gpa(struct kvm *kvm,
 
 static int kvm_unmap_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data)
 {
-	unmap_stage2_range(kvm, gpa, size);
+	unmap_stage2_range(&kvm->arch.mmu, gpa, size);
 	return 0;
 }
 
 int kvm_unmap_hva_range(struct kvm *kvm,
 			unsigned long start, unsigned long end)
 {
-	if (!kvm->arch.pgd)
+	if (!kvm->arch.mmu.pgd)
 		return 0;
 
 	trace_kvm_unmap_hva_range(start, end);
@@ -2224,7 +2260,7 @@ static int kvm_set_spte_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data
 	 * therefore stage2_set_pte() never needs to clear out a huge PMD
 	 * through this calling path.
 	 */
-	stage2_set_pte(kvm, NULL, gpa, pte, 0);
+	stage2_set_pte(&kvm->arch.mmu, NULL, gpa, pte, 0);
 	return 0;
 }
 
@@ -2235,7 +2271,7 @@ int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
 	kvm_pfn_t pfn = pte_pfn(pte);
 	pte_t stage2_pte;
 
-	if (!kvm->arch.pgd)
+	if (!kvm->arch.mmu.pgd)
 		return 0;
 
 	trace_kvm_set_spte_hva(hva);
@@ -2258,7 +2294,7 @@ static int kvm_age_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data)
 	pte_t *pte;
 
 	WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE);
-	if (!stage2_get_leaf_entry(kvm, gpa, &pud, &pmd, &pte))
+	if (!stage2_get_leaf_entry(&kvm->arch.mmu, gpa, &pud, &pmd, &pte))
 		return 0;
 
 	if (pud)
@@ -2276,7 +2312,7 @@ static int kvm_test_age_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *
 	pte_t *pte;
 
 	WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE);
-	if (!stage2_get_leaf_entry(kvm, gpa, &pud, &pmd, &pte))
+	if (!stage2_get_leaf_entry(&kvm->arch.mmu, gpa, &pud, &pmd, &pte))
 		return 0;
 
 	if (pud)
@@ -2289,7 +2325,7 @@ static int kvm_test_age_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *
 
 int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end)
 {
-	if (!kvm->arch.pgd)
+	if (!kvm->arch.mmu.pgd)
 		return 0;
 	trace_kvm_age_hva(start, end);
 	return handle_hva_to_gpa(kvm, start, end, kvm_age_hva_handler, NULL);
@@ -2297,7 +2333,7 @@ int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end)
 
 int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
 {
-	if (!kvm->arch.pgd)
+	if (!kvm->arch.mmu.pgd)
 		return 0;
 	trace_kvm_test_age_hva(hva);
 	return handle_hva_to_gpa(kvm, hva, hva + PAGE_SIZE,
@@ -2510,7 +2546,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 
 	spin_lock(&kvm->mmu_lock);
 	if (ret)
-		unmap_stage2_range(kvm, mem->guest_phys_addr, mem->memory_size);
+		unmap_stage2_range(&kvm->arch.mmu, mem->guest_phys_addr, mem->memory_size);
 	else
 		stage2_flush_memslot(kvm, memslot);
 	spin_unlock(&kvm->mmu_lock);
@@ -2529,7 +2565,7 @@ void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen)
 
 void kvm_arch_flush_shadow_all(struct kvm *kvm)
 {
-	kvm_free_stage2_pgd(kvm);
+	kvm_free_stage2_pgd(&kvm->arch.mmu);
 }
 
 void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
@@ -2539,7 +2575,7 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 	phys_addr_t size = slot->npages << PAGE_SHIFT;
 
 	spin_lock(&kvm->mmu_lock);
-	unmap_stage2_range(kvm, gpa, size);
+	unmap_stage2_range(&kvm->arch.mmu, gpa, size);
 	spin_unlock(&kvm->mmu_lock);
 }
 
-- 
cgit 


From efaa5b93afde088411b67a0dde34e67aedc6e72f Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Wed, 2 Jan 2019 12:34:25 +0000
Subject: KVM: arm64: Use TTL hint in when invalidating stage-2 translations

Since we often have a precise idea of the level we're dealing with
when invalidating TLBs, we can provide it to as a hint to our
invalidation helper.

Reviewed-by: James Morse <james.morse@arm.com>
Reviewed-by: Alexandru Elisei <alexandru.elisei@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_asm.h |  3 ++-
 arch/arm64/kvm/hyp/nvhe/tlb.c    |  5 +++--
 arch/arm64/kvm/hyp/vhe/tlb.c     |  5 +++--
 arch/arm64/kvm/mmu.c             | 29 +++++++++++++++--------------
 4 files changed, 23 insertions(+), 19 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 18d39b30d9c9..61f654a4ae00 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -91,7 +91,8 @@ DECLARE_KVM_HYP_SYM(__bp_harden_hyp_vecs);
 #endif
 
 extern void __kvm_flush_vm_context(void);
-extern void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa);
+extern void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa,
+				     int level);
 extern void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu);
 extern void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu);
 
diff --git a/arch/arm64/kvm/hyp/nvhe/tlb.c b/arch/arm64/kvm/hyp/nvhe/tlb.c
index 11dbe031f0ba..69eae608d670 100644
--- a/arch/arm64/kvm/hyp/nvhe/tlb.c
+++ b/arch/arm64/kvm/hyp/nvhe/tlb.c
@@ -46,7 +46,8 @@ static void __tlb_switch_to_host(struct tlb_inv_context *cxt)
 	}
 }
 
-void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa)
+void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu,
+			      phys_addr_t ipa, int level)
 {
 	struct tlb_inv_context cxt;
 
@@ -62,7 +63,7 @@ void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa)
 	 * whole of Stage-1. Weep...
 	 */
 	ipa >>= 12;
-	__tlbi(ipas2e1is, ipa);
+	__tlbi_level(ipas2e1is, ipa, level);
 
 	/*
 	 * We have to ensure completion of the invalidation at Stage-2,
diff --git a/arch/arm64/kvm/hyp/vhe/tlb.c b/arch/arm64/kvm/hyp/vhe/tlb.c
index ada1d56f0709..fd7895945bbc 100644
--- a/arch/arm64/kvm/hyp/vhe/tlb.c
+++ b/arch/arm64/kvm/hyp/vhe/tlb.c
@@ -79,7 +79,8 @@ static void __tlb_switch_to_host(struct tlb_inv_context *cxt)
 	local_irq_restore(cxt->flags);
 }
 
-void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa)
+void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu,
+			      phys_addr_t ipa, int level)
 {
 	struct tlb_inv_context cxt;
 
@@ -94,7 +95,7 @@ void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa)
 	 * whole of Stage-1. Weep...
 	 */
 	ipa >>= 12;
-	__tlbi(ipas2e1is, ipa);
+	__tlbi_level(ipas2e1is, ipa, level);
 
 	/*
 	 * We have to ensure completion of the invalidation at Stage-2,
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 2c6d59b509a5..41eedbfd961e 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -58,9 +58,10 @@ void kvm_flush_remote_tlbs(struct kvm *kvm)
 	kvm_call_hyp(__kvm_tlb_flush_vmid, &kvm->arch.mmu);
 }
 
-static void kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa)
+static void kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa,
+				   int level)
 {
-	kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ipa);
+	kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ipa, level);
 }
 
 /*
@@ -102,7 +103,7 @@ static void stage2_dissolve_pmd(struct kvm_s2_mmu *mmu, phys_addr_t addr, pmd_t
 		return;
 
 	pmd_clear(pmd);
-	kvm_tlb_flush_vmid_ipa(mmu, addr);
+	kvm_tlb_flush_vmid_ipa(mmu, addr, S2_PMD_LEVEL);
 	put_page(virt_to_page(pmd));
 }
 
@@ -122,7 +123,7 @@ static void stage2_dissolve_pud(struct kvm_s2_mmu *mmu, phys_addr_t addr, pud_t
 		return;
 
 	stage2_pud_clear(kvm, pudp);
-	kvm_tlb_flush_vmid_ipa(mmu, addr);
+	kvm_tlb_flush_vmid_ipa(mmu, addr, S2_PUD_LEVEL);
 	put_page(virt_to_page(pudp));
 }
 
@@ -163,7 +164,7 @@ static void clear_stage2_pgd_entry(struct kvm_s2_mmu *mmu, pgd_t *pgd, phys_addr
 	struct kvm *kvm = mmu->kvm;
 	p4d_t *p4d_table __maybe_unused = stage2_p4d_offset(kvm, pgd, 0UL);
 	stage2_pgd_clear(kvm, pgd);
-	kvm_tlb_flush_vmid_ipa(mmu, addr);
+	kvm_tlb_flush_vmid_ipa(mmu, addr, S2_NO_LEVEL_HINT);
 	stage2_p4d_free(kvm, p4d_table);
 	put_page(virt_to_page(pgd));
 }
@@ -173,7 +174,7 @@ static void clear_stage2_p4d_entry(struct kvm_s2_mmu *mmu, p4d_t *p4d, phys_addr
 	struct kvm *kvm = mmu->kvm;
 	pud_t *pud_table __maybe_unused = stage2_pud_offset(kvm, p4d, 0);
 	stage2_p4d_clear(kvm, p4d);
-	kvm_tlb_flush_vmid_ipa(mmu, addr);
+	kvm_tlb_flush_vmid_ipa(mmu, addr, S2_NO_LEVEL_HINT);
 	stage2_pud_free(kvm, pud_table);
 	put_page(virt_to_page(p4d));
 }
@@ -185,7 +186,7 @@ static void clear_stage2_pud_entry(struct kvm_s2_mmu *mmu, pud_t *pud, phys_addr
 
 	VM_BUG_ON(stage2_pud_huge(kvm, *pud));
 	stage2_pud_clear(kvm, pud);
-	kvm_tlb_flush_vmid_ipa(mmu, addr);
+	kvm_tlb_flush_vmid_ipa(mmu, addr, S2_NO_LEVEL_HINT);
 	stage2_pmd_free(kvm, pmd_table);
 	put_page(virt_to_page(pud));
 }
@@ -195,7 +196,7 @@ static void clear_stage2_pmd_entry(struct kvm_s2_mmu *mmu, pmd_t *pmd, phys_addr
 	pte_t *pte_table = pte_offset_kernel(pmd, 0);
 	VM_BUG_ON(pmd_thp_or_huge(*pmd));
 	pmd_clear(pmd);
-	kvm_tlb_flush_vmid_ipa(mmu, addr);
+	kvm_tlb_flush_vmid_ipa(mmu, addr, S2_NO_LEVEL_HINT);
 	free_page((unsigned long)pte_table);
 	put_page(virt_to_page(pmd));
 }
@@ -273,7 +274,7 @@ static void unmap_stage2_ptes(struct kvm_s2_mmu *mmu, pmd_t *pmd,
 			pte_t old_pte = *pte;
 
 			kvm_set_pte(pte, __pte(0));
-			kvm_tlb_flush_vmid_ipa(mmu, addr);
+			kvm_tlb_flush_vmid_ipa(mmu, addr, S2_PTE_LEVEL);
 
 			/* No need to invalidate the cache for device mappings */
 			if (!kvm_is_device_pfn(pte_pfn(old_pte)))
@@ -302,7 +303,7 @@ static void unmap_stage2_pmds(struct kvm_s2_mmu *mmu, pud_t *pud,
 				pmd_t old_pmd = *pmd;
 
 				pmd_clear(pmd);
-				kvm_tlb_flush_vmid_ipa(mmu, addr);
+				kvm_tlb_flush_vmid_ipa(mmu, addr, S2_PMD_LEVEL);
 
 				kvm_flush_dcache_pmd(old_pmd);
 
@@ -332,7 +333,7 @@ static void unmap_stage2_puds(struct kvm_s2_mmu *mmu, p4d_t *p4d,
 				pud_t old_pud = *pud;
 
 				stage2_pud_clear(kvm, pud);
-				kvm_tlb_flush_vmid_ipa(mmu, addr);
+				kvm_tlb_flush_vmid_ipa(mmu, addr, S2_PUD_LEVEL);
 				kvm_flush_dcache_pud(old_pud);
 				put_page(virt_to_page(pud));
 			} else {
@@ -1260,7 +1261,7 @@ retry:
 		 */
 		WARN_ON_ONCE(pmd_pfn(old_pmd) != pmd_pfn(*new_pmd));
 		pmd_clear(pmd);
-		kvm_tlb_flush_vmid_ipa(mmu, addr);
+		kvm_tlb_flush_vmid_ipa(mmu, addr, S2_PMD_LEVEL);
 	} else {
 		get_page(virt_to_page(pmd));
 	}
@@ -1302,7 +1303,7 @@ retry:
 
 		WARN_ON_ONCE(kvm_pud_pfn(old_pud) != kvm_pud_pfn(*new_pudp));
 		stage2_pud_clear(kvm, pudp);
-		kvm_tlb_flush_vmid_ipa(mmu, addr);
+		kvm_tlb_flush_vmid_ipa(mmu, addr, S2_PUD_LEVEL);
 	} else {
 		get_page(virt_to_page(pudp));
 	}
@@ -1451,7 +1452,7 @@ static int stage2_set_pte(struct kvm_s2_mmu *mmu,
 			return 0;
 
 		kvm_set_pte(pte, __pte(0));
-		kvm_tlb_flush_vmid_ipa(mmu, addr);
+		kvm_tlb_flush_vmid_ipa(mmu, addr, S2_PTE_LEVEL);
 	} else {
 		get_page(virt_to_page(pte));
 	}
-- 
cgit 


From 1b422dd7fc3c85556df656e3d8f1475ce99f93a0 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Wed, 26 Jun 2019 19:57:41 +0100
Subject: KVM: arm64: Introduce accessor for ctxt->sys_reg

In order to allow the disintegration of the per-vcpu sysreg array,
let's introduce a new helper (ctxt_sys_reg()) that returns the
in-memory copy of a system register, picked from a given context.

__vcpu_sys_reg() is rewritten to use this helper.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_host.h | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 85a529eeeae3..5b168226088e 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -405,12 +405,17 @@ struct kvm_vcpu_arch {
 #define vcpu_gp_regs(v)		(&(v)->arch.ctxt.gp_regs)
 
 /*
- * Only use __vcpu_sys_reg if you know you want the memory backed version of a
- * register, and not the one most recently accessed by a running VCPU.  For
- * example, for userspace access or for system registers that are never context
- * switched, but only emulated.
+ * Only use __vcpu_sys_reg/ctxt_sys_reg if you know you want the
+ * memory backed version of a register, and not the one most recently
+ * accessed by a running VCPU.  For example, for userspace access or
+ * for system registers that are never context switched, but only
+ * emulated.
  */
-#define __vcpu_sys_reg(v,r)	((v)->arch.ctxt.sys_regs[(r)])
+#define __ctxt_sys_reg(c,r)	(&(c)->sys_regs[(r)])
+
+#define ctxt_sys_reg(c,r)	(*__ctxt_sys_reg(c,r))
+
+#define __vcpu_sys_reg(v,r)	(ctxt_sys_reg(&(v)->arch.ctxt, (r)))
 
 u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg);
 void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg);
-- 
cgit 


From 71071acfd392c51d9c0b286067033534b59f6be4 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Sun, 12 Apr 2020 14:00:43 +0100
Subject: KVM: arm64: hyp: Use ctxt_sys_reg/__vcpu_sys_reg instead of raw
 sys_regs access

Switch the hypervisor code to using ctxt_sys_reg/__vcpu_sys_reg instead
of raw sys_regs accesses. No intended functionnal change.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_host.h          |   2 +-
 arch/arm64/kvm/hyp/include/hyp/debug-sr.h  |   4 +-
 arch/arm64/kvm/hyp/include/hyp/switch.h    |   7 +-
 arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h | 110 ++++++++++++++---------------
 arch/arm64/kvm/hyp/nvhe/switch.c           |   4 +-
 5 files changed, 62 insertions(+), 65 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 5b168226088e..d9360f91ef44 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -561,7 +561,7 @@ DECLARE_PER_CPU(kvm_host_data_t, kvm_host_data);
 static inline void kvm_init_host_cpu_context(struct kvm_cpu_context *cpu_ctxt)
 {
 	/* The host's MPIDR is immutable, so let's set it up at boot time */
-	cpu_ctxt->sys_regs[MPIDR_EL1] = read_cpuid_mpidr();
+	ctxt_sys_reg(cpu_ctxt, MPIDR_EL1) = read_cpuid_mpidr();
 }
 
 static inline bool kvm_arch_requires_vhe(void)
diff --git a/arch/arm64/kvm/hyp/include/hyp/debug-sr.h b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
index 24e8acf9ec10..5499d6c1fd9f 100644
--- a/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
@@ -104,7 +104,7 @@ static inline void __debug_save_state(struct kvm_vcpu *vcpu,
 	save_debug(dbg->dbg_wcr, dbgwcr, wrps);
 	save_debug(dbg->dbg_wvr, dbgwvr, wrps);
 
-	ctxt->sys_regs[MDCCINT_EL1] = read_sysreg(mdccint_el1);
+	ctxt_sys_reg(ctxt, MDCCINT_EL1) = read_sysreg(mdccint_el1);
 }
 
 static inline void __debug_restore_state(struct kvm_vcpu *vcpu,
@@ -124,7 +124,7 @@ static inline void __debug_restore_state(struct kvm_vcpu *vcpu,
 	restore_debug(dbg->dbg_wcr, dbgwcr, wrps);
 	restore_debug(dbg->dbg_wvr, dbgwvr, wrps);
 
-	write_sysreg(ctxt->sys_regs[MDCCINT_EL1], mdccint_el1);
+	write_sysreg(ctxt_sys_reg(ctxt, MDCCINT_EL1), mdccint_el1);
 }
 
 static inline void __debug_switch_to_guest_common(struct kvm_vcpu *vcpu)
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 5c03441b5b6c..7cf14e4f9f77 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -53,7 +53,7 @@ static inline void __fpsimd_save_fpexc32(struct kvm_vcpu *vcpu)
 	if (!vcpu_el1_is_32bit(vcpu))
 		return;
 
-	vcpu->arch.ctxt.sys_regs[FPEXC32_EL2] = read_sysreg(fpexc32_el2);
+	__vcpu_sys_reg(vcpu, FPEXC32_EL2) = read_sysreg(fpexc32_el2);
 }
 
 static inline void __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
@@ -268,15 +268,14 @@ static inline bool __hyp_handle_fpsimd(struct kvm_vcpu *vcpu)
 		sve_load_state(vcpu_sve_pffr(vcpu),
 			       &vcpu->arch.ctxt.gp_regs.fp_regs.fpsr,
 			       sve_vq_from_vl(vcpu->arch.sve_max_vl) - 1);
-		write_sysreg_s(vcpu->arch.ctxt.sys_regs[ZCR_EL1], SYS_ZCR_EL12);
+		write_sysreg_s(__vcpu_sys_reg(vcpu, ZCR_EL1), SYS_ZCR_EL12);
 	} else {
 		__fpsimd_restore_state(&vcpu->arch.ctxt.gp_regs.fp_regs);
 	}
 
 	/* Skip restoring fpexc32 for AArch64 guests */
 	if (!(read_sysreg(hcr_el2) & HCR_RW))
-		write_sysreg(vcpu->arch.ctxt.sys_regs[FPEXC32_EL2],
-			     fpexc32_el2);
+		write_sysreg(__vcpu_sys_reg(vcpu, FPEXC32_EL2), fpexc32_el2);
 
 	vcpu->arch.flags |= KVM_ARM64_FP_ENABLED;
 
diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
index 6e04e061f762..37ef3e2cdbef 100644
--- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
@@ -17,34 +17,34 @@
 
 static inline void __sysreg_save_common_state(struct kvm_cpu_context *ctxt)
 {
-	ctxt->sys_regs[MDSCR_EL1]	= read_sysreg(mdscr_el1);
+	ctxt_sys_reg(ctxt, MDSCR_EL1)	= read_sysreg(mdscr_el1);
 }
 
 static inline void __sysreg_save_user_state(struct kvm_cpu_context *ctxt)
 {
-	ctxt->sys_regs[TPIDR_EL0]	= read_sysreg(tpidr_el0);
-	ctxt->sys_regs[TPIDRRO_EL0]	= read_sysreg(tpidrro_el0);
+	ctxt_sys_reg(ctxt, TPIDR_EL0)	= read_sysreg(tpidr_el0);
+	ctxt_sys_reg(ctxt, TPIDRRO_EL0)	= read_sysreg(tpidrro_el0);
 }
 
 static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
 {
-	ctxt->sys_regs[CSSELR_EL1]	= read_sysreg(csselr_el1);
-	ctxt->sys_regs[SCTLR_EL1]	= read_sysreg_el1(SYS_SCTLR);
-	ctxt->sys_regs[CPACR_EL1]	= read_sysreg_el1(SYS_CPACR);
-	ctxt->sys_regs[TTBR0_EL1]	= read_sysreg_el1(SYS_TTBR0);
-	ctxt->sys_regs[TTBR1_EL1]	= read_sysreg_el1(SYS_TTBR1);
-	ctxt->sys_regs[TCR_EL1]		= read_sysreg_el1(SYS_TCR);
-	ctxt->sys_regs[ESR_EL1]		= read_sysreg_el1(SYS_ESR);
-	ctxt->sys_regs[AFSR0_EL1]	= read_sysreg_el1(SYS_AFSR0);
-	ctxt->sys_regs[AFSR1_EL1]	= read_sysreg_el1(SYS_AFSR1);
-	ctxt->sys_regs[FAR_EL1]		= read_sysreg_el1(SYS_FAR);
-	ctxt->sys_regs[MAIR_EL1]	= read_sysreg_el1(SYS_MAIR);
-	ctxt->sys_regs[VBAR_EL1]	= read_sysreg_el1(SYS_VBAR);
-	ctxt->sys_regs[CONTEXTIDR_EL1]	= read_sysreg_el1(SYS_CONTEXTIDR);
-	ctxt->sys_regs[AMAIR_EL1]	= read_sysreg_el1(SYS_AMAIR);
-	ctxt->sys_regs[CNTKCTL_EL1]	= read_sysreg_el1(SYS_CNTKCTL);
-	ctxt->sys_regs[PAR_EL1]		= read_sysreg(par_el1);
-	ctxt->sys_regs[TPIDR_EL1]	= read_sysreg(tpidr_el1);
+	ctxt_sys_reg(ctxt, CSSELR_EL1)	= read_sysreg(csselr_el1);
+	ctxt_sys_reg(ctxt, SCTLR_EL1)	= read_sysreg_el1(SYS_SCTLR);
+	ctxt_sys_reg(ctxt, CPACR_EL1)	= read_sysreg_el1(SYS_CPACR);
+	ctxt_sys_reg(ctxt, TTBR0_EL1)	= read_sysreg_el1(SYS_TTBR0);
+	ctxt_sys_reg(ctxt, TTBR1_EL1)	= read_sysreg_el1(SYS_TTBR1);
+	ctxt_sys_reg(ctxt, TCR_EL1)	= read_sysreg_el1(SYS_TCR);
+	ctxt_sys_reg(ctxt, ESR_EL1)	= read_sysreg_el1(SYS_ESR);
+	ctxt_sys_reg(ctxt, AFSR0_EL1)	= read_sysreg_el1(SYS_AFSR0);
+	ctxt_sys_reg(ctxt, AFSR1_EL1)	= read_sysreg_el1(SYS_AFSR1);
+	ctxt_sys_reg(ctxt, FAR_EL1)	= read_sysreg_el1(SYS_FAR);
+	ctxt_sys_reg(ctxt, MAIR_EL1)	= read_sysreg_el1(SYS_MAIR);
+	ctxt_sys_reg(ctxt, VBAR_EL1)	= read_sysreg_el1(SYS_VBAR);
+	ctxt_sys_reg(ctxt, CONTEXTIDR_EL1) = read_sysreg_el1(SYS_CONTEXTIDR);
+	ctxt_sys_reg(ctxt, AMAIR_EL1)	= read_sysreg_el1(SYS_AMAIR);
+	ctxt_sys_reg(ctxt, CNTKCTL_EL1)	= read_sysreg_el1(SYS_CNTKCTL);
+	ctxt_sys_reg(ctxt, PAR_EL1)	= read_sysreg(par_el1);
+	ctxt_sys_reg(ctxt, TPIDR_EL1)	= read_sysreg(tpidr_el1);
 
 	ctxt->gp_regs.sp_el1		= read_sysreg(sp_el1);
 	ctxt->gp_regs.elr_el1		= read_sysreg_el1(SYS_ELR);
@@ -57,55 +57,55 @@ static inline void __sysreg_save_el2_return_state(struct kvm_cpu_context *ctxt)
 	ctxt->gp_regs.regs.pstate	= read_sysreg_el2(SYS_SPSR);
 
 	if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN))
-		ctxt->sys_regs[DISR_EL1] = read_sysreg_s(SYS_VDISR_EL2);
+		ctxt_sys_reg(ctxt, DISR_EL1) = read_sysreg_s(SYS_VDISR_EL2);
 }
 
 static inline void __sysreg_restore_common_state(struct kvm_cpu_context *ctxt)
 {
-	write_sysreg(ctxt->sys_regs[MDSCR_EL1],	  mdscr_el1);
+	write_sysreg(ctxt_sys_reg(ctxt, MDSCR_EL1),  mdscr_el1);
 }
 
 static inline void __sysreg_restore_user_state(struct kvm_cpu_context *ctxt)
 {
-	write_sysreg(ctxt->sys_regs[TPIDR_EL0],		tpidr_el0);
-	write_sysreg(ctxt->sys_regs[TPIDRRO_EL0],	tpidrro_el0);
+	write_sysreg(ctxt_sys_reg(ctxt, TPIDR_EL0),	tpidr_el0);
+	write_sysreg(ctxt_sys_reg(ctxt, TPIDRRO_EL0),	tpidrro_el0);
 }
 
 static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
 {
-	write_sysreg(ctxt->sys_regs[MPIDR_EL1],		vmpidr_el2);
-	write_sysreg(ctxt->sys_regs[CSSELR_EL1],	csselr_el1);
+	write_sysreg(ctxt_sys_reg(ctxt, MPIDR_EL1),	vmpidr_el2);
+	write_sysreg(ctxt_sys_reg(ctxt, CSSELR_EL1),	csselr_el1);
 
 	if (has_vhe() ||
 	    !cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
-		write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1],	SYS_SCTLR);
-		write_sysreg_el1(ctxt->sys_regs[TCR_EL1],	SYS_TCR);
+		write_sysreg_el1(ctxt_sys_reg(ctxt, SCTLR_EL1),	SYS_SCTLR);
+		write_sysreg_el1(ctxt_sys_reg(ctxt, TCR_EL1),	SYS_TCR);
 	} else	if (!ctxt->__hyp_running_vcpu) {
 		/*
 		 * Must only be done for guest registers, hence the context
 		 * test. We're coming from the host, so SCTLR.M is already
 		 * set. Pairs with nVHE's __activate_traps().
 		 */
-		write_sysreg_el1((ctxt->sys_regs[TCR_EL1] |
+		write_sysreg_el1((ctxt_sys_reg(ctxt, TCR_EL1) |
 				  TCR_EPD1_MASK | TCR_EPD0_MASK),
 				 SYS_TCR);
 		isb();
 	}
 
-	write_sysreg_el1(ctxt->sys_regs[CPACR_EL1],	SYS_CPACR);
-	write_sysreg_el1(ctxt->sys_regs[TTBR0_EL1],	SYS_TTBR0);
-	write_sysreg_el1(ctxt->sys_regs[TTBR1_EL1],	SYS_TTBR1);
-	write_sysreg_el1(ctxt->sys_regs[ESR_EL1],	SYS_ESR);
-	write_sysreg_el1(ctxt->sys_regs[AFSR0_EL1],	SYS_AFSR0);
-	write_sysreg_el1(ctxt->sys_regs[AFSR1_EL1],	SYS_AFSR1);
-	write_sysreg_el1(ctxt->sys_regs[FAR_EL1],	SYS_FAR);
-	write_sysreg_el1(ctxt->sys_regs[MAIR_EL1],	SYS_MAIR);
-	write_sysreg_el1(ctxt->sys_regs[VBAR_EL1],	SYS_VBAR);
-	write_sysreg_el1(ctxt->sys_regs[CONTEXTIDR_EL1],SYS_CONTEXTIDR);
-	write_sysreg_el1(ctxt->sys_regs[AMAIR_EL1],	SYS_AMAIR);
-	write_sysreg_el1(ctxt->sys_regs[CNTKCTL_EL1],	SYS_CNTKCTL);
-	write_sysreg(ctxt->sys_regs[PAR_EL1],		par_el1);
-	write_sysreg(ctxt->sys_regs[TPIDR_EL1],		tpidr_el1);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, CPACR_EL1),	SYS_CPACR);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, TTBR0_EL1),	SYS_TTBR0);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, TTBR1_EL1),	SYS_TTBR1);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, ESR_EL1),	SYS_ESR);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, AFSR0_EL1),	SYS_AFSR0);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, AFSR1_EL1),	SYS_AFSR1);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, FAR_EL1),	SYS_FAR);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, MAIR_EL1),	SYS_MAIR);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, VBAR_EL1),	SYS_VBAR);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, CONTEXTIDR_EL1), SYS_CONTEXTIDR);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, AMAIR_EL1),	SYS_AMAIR);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, CNTKCTL_EL1), SYS_CNTKCTL);
+	write_sysreg(ctxt_sys_reg(ctxt, PAR_EL1),	par_el1);
+	write_sysreg(ctxt_sys_reg(ctxt, TPIDR_EL1),	tpidr_el1);
 
 	if (!has_vhe() &&
 	    cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT) &&
@@ -120,9 +120,9 @@ static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
 		 * deconfigured and disabled. We can now restore the host's
 		 * S1 configuration: SCTLR, and only then TCR.
 		 */
-		write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1],	SYS_SCTLR);
+		write_sysreg_el1(ctxt_sys_reg(ctxt, SCTLR_EL1),	SYS_SCTLR);
 		isb();
-		write_sysreg_el1(ctxt->sys_regs[TCR_EL1],	SYS_TCR);
+		write_sysreg_el1(ctxt_sys_reg(ctxt, TCR_EL1),	SYS_TCR);
 	}
 
 	write_sysreg(ctxt->gp_regs.sp_el1,		sp_el1);
@@ -153,51 +153,49 @@ static inline void __sysreg_restore_el2_return_state(struct kvm_cpu_context *ctx
 	write_sysreg_el2(pstate,			SYS_SPSR);
 
 	if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN))
-		write_sysreg_s(ctxt->sys_regs[DISR_EL1], SYS_VDISR_EL2);
+		write_sysreg_s(ctxt_sys_reg(ctxt, DISR_EL1), SYS_VDISR_EL2);
 }
 
 static inline void __sysreg32_save_state(struct kvm_vcpu *vcpu)
 {
-	u64 *spsr, *sysreg;
+	u64 *spsr;
 
 	if (!vcpu_el1_is_32bit(vcpu))
 		return;
 
 	spsr = vcpu->arch.ctxt.gp_regs.spsr;
-	sysreg = vcpu->arch.ctxt.sys_regs;
 
 	spsr[KVM_SPSR_ABT] = read_sysreg(spsr_abt);
 	spsr[KVM_SPSR_UND] = read_sysreg(spsr_und);
 	spsr[KVM_SPSR_IRQ] = read_sysreg(spsr_irq);
 	spsr[KVM_SPSR_FIQ] = read_sysreg(spsr_fiq);
 
-	sysreg[DACR32_EL2] = read_sysreg(dacr32_el2);
-	sysreg[IFSR32_EL2] = read_sysreg(ifsr32_el2);
+	__vcpu_sys_reg(vcpu, DACR32_EL2) = read_sysreg(dacr32_el2);
+	__vcpu_sys_reg(vcpu, IFSR32_EL2) = read_sysreg(ifsr32_el2);
 
 	if (has_vhe() || vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY)
-		sysreg[DBGVCR32_EL2] = read_sysreg(dbgvcr32_el2);
+		__vcpu_sys_reg(vcpu, DBGVCR32_EL2) = read_sysreg(dbgvcr32_el2);
 }
 
 static inline void __sysreg32_restore_state(struct kvm_vcpu *vcpu)
 {
-	u64 *spsr, *sysreg;
+	u64 *spsr;
 
 	if (!vcpu_el1_is_32bit(vcpu))
 		return;
 
 	spsr = vcpu->arch.ctxt.gp_regs.spsr;
-	sysreg = vcpu->arch.ctxt.sys_regs;
 
 	write_sysreg(spsr[KVM_SPSR_ABT], spsr_abt);
 	write_sysreg(spsr[KVM_SPSR_UND], spsr_und);
 	write_sysreg(spsr[KVM_SPSR_IRQ], spsr_irq);
 	write_sysreg(spsr[KVM_SPSR_FIQ], spsr_fiq);
 
-	write_sysreg(sysreg[DACR32_EL2], dacr32_el2);
-	write_sysreg(sysreg[IFSR32_EL2], ifsr32_el2);
+	write_sysreg(__vcpu_sys_reg(vcpu, DACR32_EL2), dacr32_el2);
+	write_sysreg(__vcpu_sys_reg(vcpu, IFSR32_EL2), ifsr32_el2);
 
 	if (has_vhe() || vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY)
-		write_sysreg(sysreg[DBGVCR32_EL2], dbgvcr32_el2);
+		write_sysreg(__vcpu_sys_reg(vcpu, DBGVCR32_EL2), dbgvcr32_el2);
 }
 
 #endif /* __ARM64_KVM_HYP_SYSREG_SR_H__ */
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index 37321b2157d9..341be2f2f312 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -52,9 +52,9 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
 		 * configured and enabled. We can now restore the guest's S1
 		 * configuration: SCTLR, and only then TCR.
 		 */
-		write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1],	SYS_SCTLR);
+		write_sysreg_el1(ctxt_sys_reg(ctxt, SCTLR_EL1),	SYS_SCTLR);
 		isb();
-		write_sysreg_el1(ctxt->sys_regs[TCR_EL1],	SYS_TCR);
+		write_sysreg_el1(ctxt_sys_reg(ctxt, TCR_EL1),	SYS_TCR);
 	}
 }
 
-- 
cgit 


From 308472c69213cea9b22a2156a19ea9ec06ea3bc1 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Thu, 4 Jul 2019 17:25:09 +0100
Subject: KVM: arm64: sve: Use __vcpu_sys_reg() instead of raw sys_regs access

Now that we have a wrapper for the sysreg accesses, let's use that
consistently.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/fpsimd.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c
index e329a36b2bee..e503caff14d1 100644
--- a/arch/arm64/kvm/fpsimd.c
+++ b/arch/arm64/kvm/fpsimd.c
@@ -109,12 +109,10 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu)
 	local_irq_save(flags);
 
 	if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) {
-		u64 *guest_zcr = &vcpu->arch.ctxt.sys_regs[ZCR_EL1];
-
 		fpsimd_save_and_flush_cpu_state();
 
 		if (guest_has_sve)
-			*guest_zcr = read_sysreg_s(SYS_ZCR_EL12);
+			__vcpu_sys_reg(vcpu, ZCR_EL1) = read_sysreg_s(SYS_ZCR_EL12);
 	} else if (host_has_sve) {
 		/*
 		 * The FPSIMD/SVE state in the CPU has not been touched, and we
-- 
cgit 


From 2c3db77c62b681af60757378219edcc93f658ba1 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Fri, 5 Jul 2019 11:21:27 +0100
Subject: KVM: arm64: pauth: Use ctxt_sys_reg() instead of raw sys_regs access

Now that we have a wrapper for the sysreg accesses, let's use that
consistently.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/hyp/include/hyp/switch.h | 23 +++++++++++++----------
 1 file changed, 13 insertions(+), 10 deletions(-)

diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 7cf14e4f9f77..70367699d69a 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -364,11 +364,14 @@ static inline bool esr_is_ptrauth_trap(u32 esr)
 	return false;
 }
 
-#define __ptrauth_save_key(regs, key)						\
-({										\
-	regs[key ## KEYLO_EL1] = read_sysreg_s(SYS_ ## key ## KEYLO_EL1);	\
-	regs[key ## KEYHI_EL1] = read_sysreg_s(SYS_ ## key ## KEYHI_EL1);	\
-})
+#define __ptrauth_save_key(ctxt, key)					\
+	do {								\
+	u64 __val;                                                      \
+	__val = read_sysreg_s(SYS_ ## key ## KEYLO_EL1);                \
+	ctxt_sys_reg(ctxt, key ## KEYLO_EL1) = __val;                   \
+	__val = read_sysreg_s(SYS_ ## key ## KEYHI_EL1);                \
+	ctxt_sys_reg(ctxt, key ## KEYHI_EL1) = __val;                   \
+} while(0)
 
 static inline bool __hyp_handle_ptrauth(struct kvm_vcpu *vcpu)
 {
@@ -380,11 +383,11 @@ static inline bool __hyp_handle_ptrauth(struct kvm_vcpu *vcpu)
 		return false;
 
 	ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
-	__ptrauth_save_key(ctxt->sys_regs, APIA);
-	__ptrauth_save_key(ctxt->sys_regs, APIB);
-	__ptrauth_save_key(ctxt->sys_regs, APDA);
-	__ptrauth_save_key(ctxt->sys_regs, APDB);
-	__ptrauth_save_key(ctxt->sys_regs, APGA);
+	__ptrauth_save_key(ctxt, APIA);
+	__ptrauth_save_key(ctxt, APIB);
+	__ptrauth_save_key(ctxt, APDA);
+	__ptrauth_save_key(ctxt, APDB);
+	__ptrauth_save_key(ctxt, APGA);
 
 	vcpu_ptrauth_enable(vcpu);
 
-- 
cgit 


From 5b78077a00f8109f7a4717b19309ef0a76d73372 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Fri, 5 Jul 2019 11:25:10 +0100
Subject: KVM: arm64: debug: Drop useless vpcu parameter

As part of the ongoing spring cleanup, remove the now useless
vcpu parameter that is passed around (host and guest contexts
give us everything we need).

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/hyp/include/hyp/debug-sr.h | 18 ++++++++----------
 1 file changed, 8 insertions(+), 10 deletions(-)

diff --git a/arch/arm64/kvm/hyp/include/hyp/debug-sr.h b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
index 5499d6c1fd9f..0297dc63988c 100644
--- a/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
@@ -88,9 +88,8 @@
 	default:	write_debug(ptr[0], reg, 0);			\
 	}
 
-static inline void __debug_save_state(struct kvm_vcpu *vcpu,
-				      struct kvm_guest_debug_arch *dbg,
-				      struct kvm_cpu_context *ctxt)
+static void __debug_save_state(struct kvm_guest_debug_arch *dbg,
+			       struct kvm_cpu_context *ctxt)
 {
 	u64 aa64dfr0;
 	int brps, wrps;
@@ -107,9 +106,8 @@ static inline void __debug_save_state(struct kvm_vcpu *vcpu,
 	ctxt_sys_reg(ctxt, MDCCINT_EL1) = read_sysreg(mdccint_el1);
 }
 
-static inline void __debug_restore_state(struct kvm_vcpu *vcpu,
-					 struct kvm_guest_debug_arch *dbg,
-					 struct kvm_cpu_context *ctxt)
+static void __debug_restore_state(struct kvm_guest_debug_arch *dbg,
+				  struct kvm_cpu_context *ctxt)
 {
 	u64 aa64dfr0;
 	int brps, wrps;
@@ -142,8 +140,8 @@ static inline void __debug_switch_to_guest_common(struct kvm_vcpu *vcpu)
 	host_dbg = &vcpu->arch.host_debug_state.regs;
 	guest_dbg = kern_hyp_va(vcpu->arch.debug_ptr);
 
-	__debug_save_state(vcpu, host_dbg, host_ctxt);
-	__debug_restore_state(vcpu, guest_dbg, guest_ctxt);
+	__debug_save_state(host_dbg, host_ctxt);
+	__debug_restore_state(guest_dbg, guest_ctxt);
 }
 
 static inline void __debug_switch_to_host_common(struct kvm_vcpu *vcpu)
@@ -161,8 +159,8 @@ static inline void __debug_switch_to_host_common(struct kvm_vcpu *vcpu)
 	host_dbg = &vcpu->arch.host_debug_state.regs;
 	guest_dbg = kern_hyp_va(vcpu->arch.debug_ptr);
 
-	__debug_save_state(vcpu, guest_dbg, guest_ctxt);
-	__debug_restore_state(vcpu, host_dbg, host_ctxt);
+	__debug_save_state(guest_dbg, guest_ctxt);
+	__debug_restore_state(host_dbg, host_ctxt);
 
 	vcpu->arch.flags &= ~KVM_ARM64_DEBUG_DIRTY;
 }
-- 
cgit 


From e47c2055c68e06977d7d8b7dbc2f7468a36d3658 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Fri, 28 Jun 2019 22:40:58 +0100
Subject: KVM: arm64: Make struct kvm_regs userspace-only

struct kvm_regs is used by userspace to indicate which register gets
accessed by the {GET,SET}_ONE_REG API. But as we're about to refactor
the layout of the in-kernel register structures, we need the kernel to
move away from it.

Let's make kvm_regs userspace only, and let the kernel map it to its own
internal representation.

Reviewed-by: James Morse <james.morse@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_emulate.h       | 18 ++++----
 arch/arm64/include/asm/kvm_host.h          | 12 ++++-
 arch/arm64/kernel/asm-offsets.c            |  3 +-
 arch/arm64/kvm/fpsimd.c                    |  2 +-
 arch/arm64/kvm/guest.c                     | 70 ++++++++++++++++++++++++------
 arch/arm64/kvm/hyp/entry.S                 |  3 +-
 arch/arm64/kvm/hyp/include/hyp/switch.h    |  4 +-
 arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h | 24 +++++-----
 arch/arm64/kvm/regmap.c                    |  6 +--
 arch/arm64/kvm/reset.c                     |  2 +-
 10 files changed, 96 insertions(+), 48 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 269a76cd51ff..cd607999abc2 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -124,12 +124,12 @@ static inline void vcpu_set_vsesr(struct kvm_vcpu *vcpu, u64 vsesr)
 
 static __always_inline unsigned long *vcpu_pc(const struct kvm_vcpu *vcpu)
 {
-	return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.pc;
+	return (unsigned long *)&vcpu_gp_regs(vcpu)->pc;
 }
 
 static inline unsigned long *__vcpu_elr_el1(const struct kvm_vcpu *vcpu)
 {
-	return (unsigned long *)&vcpu_gp_regs(vcpu)->elr_el1;
+	return (unsigned long *)&vcpu->arch.ctxt.elr_el1;
 }
 
 static inline unsigned long vcpu_read_elr_el1(const struct kvm_vcpu *vcpu)
@@ -150,7 +150,7 @@ static inline void vcpu_write_elr_el1(const struct kvm_vcpu *vcpu, unsigned long
 
 static __always_inline unsigned long *vcpu_cpsr(const struct kvm_vcpu *vcpu)
 {
-	return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.pstate;
+	return (unsigned long *)&vcpu_gp_regs(vcpu)->pstate;
 }
 
 static __always_inline bool vcpu_mode_is_32bit(const struct kvm_vcpu *vcpu)
@@ -179,14 +179,14 @@ static inline void vcpu_set_thumb(struct kvm_vcpu *vcpu)
 static __always_inline unsigned long vcpu_get_reg(const struct kvm_vcpu *vcpu,
 					 u8 reg_num)
 {
-	return (reg_num == 31) ? 0 : vcpu_gp_regs(vcpu)->regs.regs[reg_num];
+	return (reg_num == 31) ? 0 : vcpu_gp_regs(vcpu)->regs[reg_num];
 }
 
 static __always_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;
+		vcpu_gp_regs(vcpu)->regs[reg_num] = val;
 }
 
 static inline unsigned long vcpu_read_spsr(const struct kvm_vcpu *vcpu)
@@ -197,7 +197,7 @@ static inline unsigned long vcpu_read_spsr(const struct kvm_vcpu *vcpu)
 	if (vcpu->arch.sysregs_loaded_on_cpu)
 		return read_sysreg_el1(SYS_SPSR);
 	else
-		return vcpu_gp_regs(vcpu)->spsr[KVM_SPSR_EL1];
+		return vcpu->arch.ctxt.spsr[KVM_SPSR_EL1];
 }
 
 static inline void vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long v)
@@ -210,7 +210,7 @@ static inline void vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long v)
 	if (vcpu->arch.sysregs_loaded_on_cpu)
 		write_sysreg_el1(v, SYS_SPSR);
 	else
-		vcpu_gp_regs(vcpu)->spsr[KVM_SPSR_EL1] = v;
+		vcpu->arch.ctxt.spsr[KVM_SPSR_EL1] = v;
 }
 
 /*
@@ -519,11 +519,11 @@ static __always_inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_i
 static __always_inline void __kvm_skip_instr(struct kvm_vcpu *vcpu)
 {
 	*vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR);
-	vcpu->arch.ctxt.gp_regs.regs.pstate = read_sysreg_el2(SYS_SPSR);
+	vcpu_gp_regs(vcpu)->pstate = read_sysreg_el2(SYS_SPSR);
 
 	kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
 
-	write_sysreg_el2(vcpu->arch.ctxt.gp_regs.regs.pstate, SYS_SPSR);
+	write_sysreg_el2(vcpu_gp_regs(vcpu)->pstate, SYS_SPSR);
 	write_sysreg_el2(*vcpu_pc(vcpu), SYS_ELR);
 }
 
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index d9360f91ef44..bc1e91573d00 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -236,7 +236,15 @@ enum vcpu_sysreg {
 #define NR_COPRO_REGS	(NR_SYS_REGS * 2)
 
 struct kvm_cpu_context {
-	struct kvm_regs	gp_regs;
+	struct user_pt_regs regs;	/* sp = sp_el0 */
+
+	u64	sp_el1;
+	u64	elr_el1;
+
+	u64	spsr[KVM_NR_SPSR];
+
+	struct user_fpsimd_state fp_regs;
+
 	union {
 		u64 sys_regs[NR_SYS_REGS];
 		u32 copro[NR_COPRO_REGS];
@@ -402,7 +410,7 @@ struct kvm_vcpu_arch {
 				  system_supports_generic_auth()) && \
 				 ((vcpu)->arch.flags & KVM_ARM64_GUEST_HAS_PTRAUTH))
 
-#define vcpu_gp_regs(v)		(&(v)->arch.ctxt.gp_regs)
+#define vcpu_gp_regs(v)		(&(v)->arch.ctxt.regs)
 
 /*
  * Only use __vcpu_sys_reg/ctxt_sys_reg if you know you want the
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 0577e2142284..7d32fc959b1a 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -102,13 +102,12 @@ int main(void)
   DEFINE(VCPU_FAULT_DISR,	offsetof(struct kvm_vcpu, arch.fault.disr_el1));
   DEFINE(VCPU_WORKAROUND_FLAGS,	offsetof(struct kvm_vcpu, arch.workaround_flags));
   DEFINE(VCPU_HCR_EL2,		offsetof(struct kvm_vcpu, arch.hcr_el2));
-  DEFINE(CPU_GP_REGS,		offsetof(struct kvm_cpu_context, gp_regs));
+  DEFINE(CPU_USER_PT_REGS,	offsetof(struct kvm_cpu_context, regs));
   DEFINE(CPU_APIAKEYLO_EL1,	offsetof(struct kvm_cpu_context, sys_regs[APIAKEYLO_EL1]));
   DEFINE(CPU_APIBKEYLO_EL1,	offsetof(struct kvm_cpu_context, sys_regs[APIBKEYLO_EL1]));
   DEFINE(CPU_APDAKEYLO_EL1,	offsetof(struct kvm_cpu_context, sys_regs[APDAKEYLO_EL1]));
   DEFINE(CPU_APDBKEYLO_EL1,	offsetof(struct kvm_cpu_context, sys_regs[APDBKEYLO_EL1]));
   DEFINE(CPU_APGAKEYLO_EL1,	offsetof(struct kvm_cpu_context, sys_regs[APGAKEYLO_EL1]));
-  DEFINE(CPU_USER_PT_REGS,	offsetof(struct kvm_regs, regs));
   DEFINE(HOST_CONTEXT_VCPU,	offsetof(struct kvm_cpu_context, __hyp_running_vcpu));
   DEFINE(HOST_DATA_CONTEXT,	offsetof(struct kvm_host_data, host_ctxt));
 #endif
diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c
index e503caff14d1..3e081d556e81 100644
--- a/arch/arm64/kvm/fpsimd.c
+++ b/arch/arm64/kvm/fpsimd.c
@@ -85,7 +85,7 @@ void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu)
 	WARN_ON_ONCE(!irqs_disabled());
 
 	if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) {
-		fpsimd_bind_state_to_cpu(&vcpu->arch.ctxt.gp_regs.fp_regs,
+		fpsimd_bind_state_to_cpu(&vcpu->arch.ctxt.fp_regs,
 					 vcpu->arch.sve_state,
 					 vcpu->arch.sve_max_vl);
 
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index aea43ec60f37..9dd5bbeefae6 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -101,19 +101,60 @@ static int core_reg_size_from_offset(const struct kvm_vcpu *vcpu, u64 off)
 	return size;
 }
 
-static int validate_core_offset(const struct kvm_vcpu *vcpu,
-				const struct kvm_one_reg *reg)
+static void *core_reg_addr(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 {
 	u64 off = core_reg_offset_from_id(reg->id);
 	int size = core_reg_size_from_offset(vcpu, off);
 
 	if (size < 0)
-		return -EINVAL;
+		return NULL;
 
 	if (KVM_REG_SIZE(reg->id) != size)
-		return -EINVAL;
+		return NULL;
 
-	return 0;
+	switch (off) {
+	case KVM_REG_ARM_CORE_REG(regs.regs[0]) ...
+	     KVM_REG_ARM_CORE_REG(regs.regs[30]):
+		off -= KVM_REG_ARM_CORE_REG(regs.regs[0]);
+		off /= 2;
+		return &vcpu->arch.ctxt.regs.regs[off];
+
+	case KVM_REG_ARM_CORE_REG(regs.sp):
+		return &vcpu->arch.ctxt.regs.sp;
+
+	case KVM_REG_ARM_CORE_REG(regs.pc):
+		return &vcpu->arch.ctxt.regs.pc;
+
+	case KVM_REG_ARM_CORE_REG(regs.pstate):
+		return &vcpu->arch.ctxt.regs.pstate;
+
+	case KVM_REG_ARM_CORE_REG(sp_el1):
+		return &vcpu->arch.ctxt.sp_el1;
+
+	case KVM_REG_ARM_CORE_REG(elr_el1):
+		return &vcpu->arch.ctxt.elr_el1;
+
+	case KVM_REG_ARM_CORE_REG(spsr[0]) ...
+	     KVM_REG_ARM_CORE_REG(spsr[KVM_NR_SPSR - 1]):
+		off -= KVM_REG_ARM_CORE_REG(spsr[0]);
+		off /= 2;
+		return &vcpu->arch.ctxt.spsr[off];
+
+	case KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]) ...
+	     KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]):
+		off -= KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]);
+		off /= 4;
+		return &vcpu->arch.ctxt.fp_regs.vregs[off];
+
+	case KVM_REG_ARM_CORE_REG(fp_regs.fpsr):
+		return &vcpu->arch.ctxt.fp_regs.fpsr;
+
+	case KVM_REG_ARM_CORE_REG(fp_regs.fpcr):
+		return &vcpu->arch.ctxt.fp_regs.fpcr;
+
+	default:
+		return NULL;
+	}
 }
 
 static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
@@ -125,8 +166,8 @@ static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	 * off the index in the "array".
 	 */
 	__u32 __user *uaddr = (__u32 __user *)(unsigned long)reg->addr;
-	struct kvm_regs *regs = vcpu_gp_regs(vcpu);
-	int nr_regs = sizeof(*regs) / sizeof(__u32);
+	int nr_regs = sizeof(struct kvm_regs) / sizeof(__u32);
+	void *addr;
 	u32 off;
 
 	/* Our ID is an index into the kvm_regs struct. */
@@ -135,10 +176,11 @@ static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	    (off + (KVM_REG_SIZE(reg->id) / sizeof(__u32))) >= nr_regs)
 		return -ENOENT;
 
-	if (validate_core_offset(vcpu, reg))
+	addr = core_reg_addr(vcpu, reg);
+	if (!addr)
 		return -EINVAL;
 
-	if (copy_to_user(uaddr, ((u32 *)regs) + off, KVM_REG_SIZE(reg->id)))
+	if (copy_to_user(uaddr, addr, KVM_REG_SIZE(reg->id)))
 		return -EFAULT;
 
 	return 0;
@@ -147,10 +189,9 @@ static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 {
 	__u32 __user *uaddr = (__u32 __user *)(unsigned long)reg->addr;
-	struct kvm_regs *regs = vcpu_gp_regs(vcpu);
-	int nr_regs = sizeof(*regs) / sizeof(__u32);
+	int nr_regs = sizeof(struct kvm_regs) / sizeof(__u32);
 	__uint128_t tmp;
-	void *valp = &tmp;
+	void *valp = &tmp, *addr;
 	u64 off;
 	int err = 0;
 
@@ -160,7 +201,8 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	    (off + (KVM_REG_SIZE(reg->id) / sizeof(__u32))) >= nr_regs)
 		return -ENOENT;
 
-	if (validate_core_offset(vcpu, reg))
+	addr = core_reg_addr(vcpu, reg);
+	if (!addr)
 		return -EINVAL;
 
 	if (KVM_REG_SIZE(reg->id) > sizeof(tmp))
@@ -198,7 +240,7 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 		}
 	}
 
-	memcpy((u32 *)regs + off, valp, KVM_REG_SIZE(reg->id));
+	memcpy(addr, valp, KVM_REG_SIZE(reg->id));
 
 	if (*vcpu_cpsr(vcpu) & PSR_MODE32_BIT) {
 		int i;
diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S
index dfb4e6d359ab..ee32a7743389 100644
--- a/arch/arm64/kvm/hyp/entry.S
+++ b/arch/arm64/kvm/hyp/entry.S
@@ -16,8 +16,7 @@
 #include <asm/kvm_mmu.h>
 #include <asm/kvm_ptrauth.h>
 
-#define CPU_GP_REG_OFFSET(x)	(CPU_GP_REGS + x)
-#define CPU_XREG_OFFSET(x)	CPU_GP_REG_OFFSET(CPU_USER_PT_REGS + 8*x)
+#define CPU_XREG_OFFSET(x)	(CPU_USER_PT_REGS + 8*x)
 #define CPU_SP_EL0_OFFSET	(CPU_XREG_OFFSET(30) + 8)
 
 	.text
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 70367699d69a..784a581071fc 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -266,11 +266,11 @@ static inline bool __hyp_handle_fpsimd(struct kvm_vcpu *vcpu)
 
 	if (sve_guest) {
 		sve_load_state(vcpu_sve_pffr(vcpu),
-			       &vcpu->arch.ctxt.gp_regs.fp_regs.fpsr,
+			       &vcpu->arch.ctxt.fp_regs.fpsr,
 			       sve_vq_from_vl(vcpu->arch.sve_max_vl) - 1);
 		write_sysreg_s(__vcpu_sys_reg(vcpu, ZCR_EL1), SYS_ZCR_EL12);
 	} else {
-		__fpsimd_restore_state(&vcpu->arch.ctxt.gp_regs.fp_regs);
+		__fpsimd_restore_state(&vcpu->arch.ctxt.fp_regs);
 	}
 
 	/* Skip restoring fpexc32 for AArch64 guests */
diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
index 37ef3e2cdbef..50938093cc5d 100644
--- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
@@ -46,15 +46,15 @@ static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
 	ctxt_sys_reg(ctxt, PAR_EL1)	= read_sysreg(par_el1);
 	ctxt_sys_reg(ctxt, TPIDR_EL1)	= read_sysreg(tpidr_el1);
 
-	ctxt->gp_regs.sp_el1		= read_sysreg(sp_el1);
-	ctxt->gp_regs.elr_el1		= read_sysreg_el1(SYS_ELR);
-	ctxt->gp_regs.spsr[KVM_SPSR_EL1]= read_sysreg_el1(SYS_SPSR);
+	ctxt->sp_el1			= read_sysreg(sp_el1);
+	ctxt->elr_el1			= read_sysreg_el1(SYS_ELR);
+	ctxt->spsr[KVM_SPSR_EL1]	= read_sysreg_el1(SYS_SPSR);
 }
 
 static inline void __sysreg_save_el2_return_state(struct kvm_cpu_context *ctxt)
 {
-	ctxt->gp_regs.regs.pc		= read_sysreg_el2(SYS_ELR);
-	ctxt->gp_regs.regs.pstate	= read_sysreg_el2(SYS_SPSR);
+	ctxt->regs.pc			= read_sysreg_el2(SYS_ELR);
+	ctxt->regs.pstate		= read_sysreg_el2(SYS_SPSR);
 
 	if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN))
 		ctxt_sys_reg(ctxt, DISR_EL1) = read_sysreg_s(SYS_VDISR_EL2);
@@ -125,14 +125,14 @@ static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
 		write_sysreg_el1(ctxt_sys_reg(ctxt, TCR_EL1),	SYS_TCR);
 	}
 
-	write_sysreg(ctxt->gp_regs.sp_el1,		sp_el1);
-	write_sysreg_el1(ctxt->gp_regs.elr_el1,		SYS_ELR);
-	write_sysreg_el1(ctxt->gp_regs.spsr[KVM_SPSR_EL1],SYS_SPSR);
+	write_sysreg(ctxt->sp_el1,			sp_el1);
+	write_sysreg_el1(ctxt->elr_el1,			SYS_ELR);
+	write_sysreg_el1(ctxt->spsr[KVM_SPSR_EL1],	SYS_SPSR);
 }
 
 static inline void __sysreg_restore_el2_return_state(struct kvm_cpu_context *ctxt)
 {
-	u64 pstate = ctxt->gp_regs.regs.pstate;
+	u64 pstate = ctxt->regs.pstate;
 	u64 mode = pstate & PSR_AA32_MODE_MASK;
 
 	/*
@@ -149,7 +149,7 @@ static inline void __sysreg_restore_el2_return_state(struct kvm_cpu_context *ctx
 	if (!(mode & PSR_MODE32_BIT) && mode >= PSR_MODE_EL2t)
 		pstate = PSR_MODE_EL2h | PSR_IL_BIT;
 
-	write_sysreg_el2(ctxt->gp_regs.regs.pc,		SYS_ELR);
+	write_sysreg_el2(ctxt->regs.pc,			SYS_ELR);
 	write_sysreg_el2(pstate,			SYS_SPSR);
 
 	if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN))
@@ -163,7 +163,7 @@ static inline void __sysreg32_save_state(struct kvm_vcpu *vcpu)
 	if (!vcpu_el1_is_32bit(vcpu))
 		return;
 
-	spsr = vcpu->arch.ctxt.gp_regs.spsr;
+	spsr = vcpu->arch.ctxt.spsr;
 
 	spsr[KVM_SPSR_ABT] = read_sysreg(spsr_abt);
 	spsr[KVM_SPSR_UND] = read_sysreg(spsr_und);
@@ -184,7 +184,7 @@ static inline void __sysreg32_restore_state(struct kvm_vcpu *vcpu)
 	if (!vcpu_el1_is_32bit(vcpu))
 		return;
 
-	spsr = vcpu->arch.ctxt.gp_regs.spsr;
+	spsr = vcpu->arch.ctxt.spsr;
 
 	write_sysreg(spsr[KVM_SPSR_ABT], spsr_abt);
 	write_sysreg(spsr[KVM_SPSR_UND], spsr_und);
diff --git a/arch/arm64/kvm/regmap.c b/arch/arm64/kvm/regmap.c
index a900181e3867..b1596f314087 100644
--- a/arch/arm64/kvm/regmap.c
+++ b/arch/arm64/kvm/regmap.c
@@ -100,7 +100,7 @@ static const unsigned long vcpu_reg_offsets[VCPU_NR_MODES][16] = {
  */
 unsigned long *vcpu_reg32(const struct kvm_vcpu *vcpu, u8 reg_num)
 {
-	unsigned long *reg_array = (unsigned long *)&vcpu->arch.ctxt.gp_regs.regs;
+	unsigned long *reg_array = (unsigned long *)&vcpu->arch.ctxt.regs;
 	unsigned long mode = *vcpu_cpsr(vcpu) & PSR_AA32_MODE_MASK;
 
 	switch (mode) {
@@ -148,7 +148,7 @@ unsigned long vcpu_read_spsr32(const struct kvm_vcpu *vcpu)
 	int spsr_idx = vcpu_spsr32_mode(vcpu);
 
 	if (!vcpu->arch.sysregs_loaded_on_cpu)
-		return vcpu_gp_regs(vcpu)->spsr[spsr_idx];
+		return vcpu->arch.ctxt.spsr[spsr_idx];
 
 	switch (spsr_idx) {
 	case KVM_SPSR_SVC:
@@ -171,7 +171,7 @@ void vcpu_write_spsr32(struct kvm_vcpu *vcpu, unsigned long v)
 	int spsr_idx = vcpu_spsr32_mode(vcpu);
 
 	if (!vcpu->arch.sysregs_loaded_on_cpu) {
-		vcpu_gp_regs(vcpu)->spsr[spsr_idx] = v;
+		vcpu->arch.ctxt.spsr[spsr_idx] = v;
 		return;
 	}
 
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index d3b209023727..8ca8607f5a9f 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -288,7 +288,7 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 
 	/* Reset core registers */
 	memset(vcpu_gp_regs(vcpu), 0, sizeof(*vcpu_gp_regs(vcpu)));
-	vcpu_gp_regs(vcpu)->regs.pstate = pstate;
+	vcpu_gp_regs(vcpu)->pstate = pstate;
 
 	/* Reset system registers */
 	kvm_reset_sys_regs(vcpu);
-- 
cgit 


From 98909e6d1c811b6368c9c84fa6b3f0817c32ac2f Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Fri, 28 Jun 2019 23:05:38 +0100
Subject: KVM: arm64: Move ELR_EL1 to the system register array

As ELR-EL1 is a VNCR-capable register with ARMv8.4-NV, let's move it to
the sys_regs array and repaint the accessors. While we're at it, let's
kill the now useless accessors used only on the fault injection path.

Reviewed-by: James Morse <james.morse@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_emulate.h       | 21 ---------------------
 arch/arm64/include/asm/kvm_host.h          |  3 ++-
 arch/arm64/kvm/guest.c                     |  2 +-
 arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h |  4 ++--
 arch/arm64/kvm/inject_fault.c              |  2 +-
 arch/arm64/kvm/sys_regs.c                  |  2 ++
 6 files changed, 8 insertions(+), 26 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index cd607999abc2..a12b5dc5db0d 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -127,27 +127,6 @@ static __always_inline unsigned long *vcpu_pc(const struct kvm_vcpu *vcpu)
 	return (unsigned long *)&vcpu_gp_regs(vcpu)->pc;
 }
 
-static inline unsigned long *__vcpu_elr_el1(const struct kvm_vcpu *vcpu)
-{
-	return (unsigned long *)&vcpu->arch.ctxt.elr_el1;
-}
-
-static inline unsigned long vcpu_read_elr_el1(const struct kvm_vcpu *vcpu)
-{
-	if (vcpu->arch.sysregs_loaded_on_cpu)
-		return read_sysreg_el1(SYS_ELR);
-	else
-		return *__vcpu_elr_el1(vcpu);
-}
-
-static inline void vcpu_write_elr_el1(const struct kvm_vcpu *vcpu, unsigned long v)
-{
-	if (vcpu->arch.sysregs_loaded_on_cpu)
-		write_sysreg_el1(v, SYS_ELR);
-	else
-		*__vcpu_elr_el1(vcpu) = v;
-}
-
 static __always_inline unsigned long *vcpu_cpsr(const struct kvm_vcpu *vcpu)
 {
 	return (unsigned long *)&vcpu_gp_regs(vcpu)->pstate;
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index bc1e91573d00..f255507dd916 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -185,6 +185,8 @@ enum vcpu_sysreg {
 	APGAKEYLO_EL1,
 	APGAKEYHI_EL1,
 
+	ELR_EL1,
+
 	/* 32bit specific registers. Keep them at the end of the range */
 	DACR32_EL2,	/* Domain Access Control Register */
 	IFSR32_EL2,	/* Instruction Fault Status Register */
@@ -239,7 +241,6 @@ struct kvm_cpu_context {
 	struct user_pt_regs regs;	/* sp = sp_el0 */
 
 	u64	sp_el1;
-	u64	elr_el1;
 
 	u64	spsr[KVM_NR_SPSR];
 
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 9dd5bbeefae6..99ff09ad24e8 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -132,7 +132,7 @@ static void *core_reg_addr(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 		return &vcpu->arch.ctxt.sp_el1;
 
 	case KVM_REG_ARM_CORE_REG(elr_el1):
-		return &vcpu->arch.ctxt.elr_el1;
+		return __ctxt_sys_reg(&vcpu->arch.ctxt, ELR_EL1);
 
 	case KVM_REG_ARM_CORE_REG(spsr[0]) ...
 	     KVM_REG_ARM_CORE_REG(spsr[KVM_NR_SPSR - 1]):
diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
index 50938093cc5d..9ebbd626d4ab 100644
--- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
@@ -47,7 +47,7 @@ static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
 	ctxt_sys_reg(ctxt, TPIDR_EL1)	= read_sysreg(tpidr_el1);
 
 	ctxt->sp_el1			= read_sysreg(sp_el1);
-	ctxt->elr_el1			= read_sysreg_el1(SYS_ELR);
+	ctxt_sys_reg(ctxt, ELR_EL1)	= read_sysreg_el1(SYS_ELR);
 	ctxt->spsr[KVM_SPSR_EL1]	= read_sysreg_el1(SYS_SPSR);
 }
 
@@ -126,7 +126,7 @@ static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
 	}
 
 	write_sysreg(ctxt->sp_el1,			sp_el1);
-	write_sysreg_el1(ctxt->elr_el1,			SYS_ELR);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, ELR_EL1),	SYS_ELR);
 	write_sysreg_el1(ctxt->spsr[KVM_SPSR_EL1],	SYS_SPSR);
 }
 
diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c
index e21fdd93027a..ebfdfc27b2bd 100644
--- a/arch/arm64/kvm/inject_fault.c
+++ b/arch/arm64/kvm/inject_fault.c
@@ -64,7 +64,7 @@ static void enter_exception64(struct kvm_vcpu *vcpu, unsigned long target_mode,
 	case PSR_MODE_EL1h:
 		vbar = vcpu_read_sys_reg(vcpu, VBAR_EL1);
 		sctlr = vcpu_read_sys_reg(vcpu, SCTLR_EL1);
-		vcpu_write_elr_el1(vcpu, *vcpu_pc(vcpu));
+		vcpu_write_sys_reg(vcpu, *vcpu_pc(vcpu), ELR_EL1);
 		break;
 	default:
 		/* Don't do that */
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index baf5ce9225ce..6657b83c0647 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -94,6 +94,7 @@ static bool __vcpu_read_sys_reg_from_cpu(int reg, u64 *val)
 	case TPIDR_EL1:		*val = read_sysreg_s(SYS_TPIDR_EL1);	break;
 	case AMAIR_EL1:		*val = read_sysreg_s(SYS_AMAIR_EL12);	break;
 	case CNTKCTL_EL1:	*val = read_sysreg_s(SYS_CNTKCTL_EL12);	break;
+	case ELR_EL1:		*val = read_sysreg_s(SYS_ELR_EL12);	break;
 	case PAR_EL1:		*val = read_sysreg_s(SYS_PAR_EL1);	break;
 	case DACR32_EL2:	*val = read_sysreg_s(SYS_DACR32_EL2);	break;
 	case IFSR32_EL2:	*val = read_sysreg_s(SYS_IFSR32_EL2);	break;
@@ -133,6 +134,7 @@ static bool __vcpu_write_sys_reg_to_cpu(u64 val, int reg)
 	case TPIDR_EL1:		write_sysreg_s(val, SYS_TPIDR_EL1);	break;
 	case AMAIR_EL1:		write_sysreg_s(val, SYS_AMAIR_EL12);	break;
 	case CNTKCTL_EL1:	write_sysreg_s(val, SYS_CNTKCTL_EL12);	break;
+	case ELR_EL1:		write_sysreg_s(val, SYS_ELR_EL12);	break;
 	case PAR_EL1:		write_sysreg_s(val, SYS_PAR_EL1);	break;
 	case DACR32_EL2:	write_sysreg_s(val, SYS_DACR32_EL2);	break;
 	case IFSR32_EL2:	write_sysreg_s(val, SYS_IFSR32_EL2);	break;
-- 
cgit 


From 1bded23ea71cee2053fe1dd55c5d36d35bec56aa Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Fri, 28 Jun 2019 23:05:38 +0100
Subject: KVM: arm64: Move SP_EL1 to the system register array

SP_EL1 being a VNCR-capable register with ARMv8.4-NV, move it to the
system register array and update the accessors.

Reviewed-by: James Morse <james.morse@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_host.h          | 3 +--
 arch/arm64/kvm/guest.c                     | 2 +-
 arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h | 4 ++--
 3 files changed, 4 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index f255507dd916..2bd6285eaf4c 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -186,6 +186,7 @@ enum vcpu_sysreg {
 	APGAKEYHI_EL1,
 
 	ELR_EL1,
+	SP_EL1,
 
 	/* 32bit specific registers. Keep them at the end of the range */
 	DACR32_EL2,	/* Domain Access Control Register */
@@ -240,8 +241,6 @@ enum vcpu_sysreg {
 struct kvm_cpu_context {
 	struct user_pt_regs regs;	/* sp = sp_el0 */
 
-	u64	sp_el1;
-
 	u64	spsr[KVM_NR_SPSR];
 
 	struct user_fpsimd_state fp_regs;
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 99ff09ad24e8..d614716e073b 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -129,7 +129,7 @@ static void *core_reg_addr(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 		return &vcpu->arch.ctxt.regs.pstate;
 
 	case KVM_REG_ARM_CORE_REG(sp_el1):
-		return &vcpu->arch.ctxt.sp_el1;
+		return __ctxt_sys_reg(&vcpu->arch.ctxt, SP_EL1);
 
 	case KVM_REG_ARM_CORE_REG(elr_el1):
 		return __ctxt_sys_reg(&vcpu->arch.ctxt, ELR_EL1);
diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
index 9ebbd626d4ab..4c26ba72120e 100644
--- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
@@ -46,7 +46,7 @@ static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
 	ctxt_sys_reg(ctxt, PAR_EL1)	= read_sysreg(par_el1);
 	ctxt_sys_reg(ctxt, TPIDR_EL1)	= read_sysreg(tpidr_el1);
 
-	ctxt->sp_el1			= read_sysreg(sp_el1);
+	ctxt_sys_reg(ctxt, SP_EL1)	= read_sysreg(sp_el1);
 	ctxt_sys_reg(ctxt, ELR_EL1)	= read_sysreg_el1(SYS_ELR);
 	ctxt->spsr[KVM_SPSR_EL1]	= read_sysreg_el1(SYS_SPSR);
 }
@@ -125,7 +125,7 @@ static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
 		write_sysreg_el1(ctxt_sys_reg(ctxt, TCR_EL1),	SYS_TCR);
 	}
 
-	write_sysreg(ctxt->sp_el1,			sp_el1);
+	write_sysreg(ctxt_sys_reg(ctxt, SP_EL1),	sp_el1);
 	write_sysreg_el1(ctxt_sys_reg(ctxt, ELR_EL1),	SYS_ELR);
 	write_sysreg_el1(ctxt->spsr[KVM_SPSR_EL1],	SYS_SPSR);
 }
-- 
cgit 


From fd85b66789aaa594a158f0a8aa4482c3ed0fed3d Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Fri, 28 Jun 2019 23:36:42 +0100
Subject: KVM: arm64: Disintegrate SPSR array

As we're about to move SPSR_EL1 into the VNCR page, we need to
disassociate it from the rest of the 32bit cruft. Let's break
the array into individual fields.

Reviewed-by: James Morse <james.morse@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_emulate.h       |  4 ++--
 arch/arm64/include/asm/kvm_host.h          |  6 ++++-
 arch/arm64/kvm/guest.c                     | 19 +++++++++++-----
 arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h | 28 +++++++++---------------
 arch/arm64/kvm/regmap.c                    | 35 +++++++++++++++++++++++++++---
 5 files changed, 63 insertions(+), 29 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index a12b5dc5db0d..5f959fedff09 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -176,7 +176,7 @@ static inline unsigned long vcpu_read_spsr(const struct kvm_vcpu *vcpu)
 	if (vcpu->arch.sysregs_loaded_on_cpu)
 		return read_sysreg_el1(SYS_SPSR);
 	else
-		return vcpu->arch.ctxt.spsr[KVM_SPSR_EL1];
+		return vcpu->arch.ctxt.spsr_el1;
 }
 
 static inline void vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long v)
@@ -189,7 +189,7 @@ static inline void vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long v)
 	if (vcpu->arch.sysregs_loaded_on_cpu)
 		write_sysreg_el1(v, SYS_SPSR);
 	else
-		vcpu->arch.ctxt.spsr[KVM_SPSR_EL1] = v;
+		vcpu->arch.ctxt.spsr_el1 = v;
 }
 
 /*
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 2bd6285eaf4c..dfb97ed2f680 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -241,7 +241,11 @@ enum vcpu_sysreg {
 struct kvm_cpu_context {
 	struct user_pt_regs regs;	/* sp = sp_el0 */
 
-	u64	spsr[KVM_NR_SPSR];
+	u64	spsr_el1;		/* aka spsr_svc */
+	u64	spsr_abt;
+	u64	spsr_und;
+	u64	spsr_irq;
+	u64	spsr_fiq;
 
 	struct user_fpsimd_state fp_regs;
 
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index d614716e073b..70215f3a6f89 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -134,11 +134,20 @@ static void *core_reg_addr(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	case KVM_REG_ARM_CORE_REG(elr_el1):
 		return __ctxt_sys_reg(&vcpu->arch.ctxt, ELR_EL1);
 
-	case KVM_REG_ARM_CORE_REG(spsr[0]) ...
-	     KVM_REG_ARM_CORE_REG(spsr[KVM_NR_SPSR - 1]):
-		off -= KVM_REG_ARM_CORE_REG(spsr[0]);
-		off /= 2;
-		return &vcpu->arch.ctxt.spsr[off];
+	case KVM_REG_ARM_CORE_REG(spsr[KVM_SPSR_EL1]):
+		return &vcpu->arch.ctxt.spsr_el1;
+
+	case KVM_REG_ARM_CORE_REG(spsr[KVM_SPSR_ABT]):
+		return &vcpu->arch.ctxt.spsr_abt;
+
+	case KVM_REG_ARM_CORE_REG(spsr[KVM_SPSR_UND]):
+		return &vcpu->arch.ctxt.spsr_und;
+
+	case KVM_REG_ARM_CORE_REG(spsr[KVM_SPSR_IRQ]):
+		return &vcpu->arch.ctxt.spsr_irq;
+
+	case KVM_REG_ARM_CORE_REG(spsr[KVM_SPSR_FIQ]):
+		return &vcpu->arch.ctxt.spsr_fiq;
 
 	case KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]) ...
 	     KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]):
diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
index 4c26ba72120e..fb4bc42e72c5 100644
--- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
@@ -48,7 +48,7 @@ static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
 
 	ctxt_sys_reg(ctxt, SP_EL1)	= read_sysreg(sp_el1);
 	ctxt_sys_reg(ctxt, ELR_EL1)	= read_sysreg_el1(SYS_ELR);
-	ctxt->spsr[KVM_SPSR_EL1]	= read_sysreg_el1(SYS_SPSR);
+	ctxt->spsr_el1			= read_sysreg_el1(SYS_SPSR);
 }
 
 static inline void __sysreg_save_el2_return_state(struct kvm_cpu_context *ctxt)
@@ -127,7 +127,7 @@ static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
 
 	write_sysreg(ctxt_sys_reg(ctxt, SP_EL1),	sp_el1);
 	write_sysreg_el1(ctxt_sys_reg(ctxt, ELR_EL1),	SYS_ELR);
-	write_sysreg_el1(ctxt->spsr[KVM_SPSR_EL1],	SYS_SPSR);
+	write_sysreg_el1(ctxt->spsr_el1,		SYS_SPSR);
 }
 
 static inline void __sysreg_restore_el2_return_state(struct kvm_cpu_context *ctxt)
@@ -158,17 +158,13 @@ static inline void __sysreg_restore_el2_return_state(struct kvm_cpu_context *ctx
 
 static inline void __sysreg32_save_state(struct kvm_vcpu *vcpu)
 {
-	u64 *spsr;
-
 	if (!vcpu_el1_is_32bit(vcpu))
 		return;
 
-	spsr = vcpu->arch.ctxt.spsr;
-
-	spsr[KVM_SPSR_ABT] = read_sysreg(spsr_abt);
-	spsr[KVM_SPSR_UND] = read_sysreg(spsr_und);
-	spsr[KVM_SPSR_IRQ] = read_sysreg(spsr_irq);
-	spsr[KVM_SPSR_FIQ] = read_sysreg(spsr_fiq);
+	vcpu->arch.ctxt.spsr_abt = read_sysreg(spsr_abt);
+	vcpu->arch.ctxt.spsr_und = read_sysreg(spsr_und);
+	vcpu->arch.ctxt.spsr_irq = read_sysreg(spsr_irq);
+	vcpu->arch.ctxt.spsr_fiq = read_sysreg(spsr_fiq);
 
 	__vcpu_sys_reg(vcpu, DACR32_EL2) = read_sysreg(dacr32_el2);
 	__vcpu_sys_reg(vcpu, IFSR32_EL2) = read_sysreg(ifsr32_el2);
@@ -179,17 +175,13 @@ static inline void __sysreg32_save_state(struct kvm_vcpu *vcpu)
 
 static inline void __sysreg32_restore_state(struct kvm_vcpu *vcpu)
 {
-	u64 *spsr;
-
 	if (!vcpu_el1_is_32bit(vcpu))
 		return;
 
-	spsr = vcpu->arch.ctxt.spsr;
-
-	write_sysreg(spsr[KVM_SPSR_ABT], spsr_abt);
-	write_sysreg(spsr[KVM_SPSR_UND], spsr_und);
-	write_sysreg(spsr[KVM_SPSR_IRQ], spsr_irq);
-	write_sysreg(spsr[KVM_SPSR_FIQ], spsr_fiq);
+	write_sysreg(vcpu->arch.ctxt.spsr_abt, spsr_abt);
+	write_sysreg(vcpu->arch.ctxt.spsr_und, spsr_und);
+	write_sysreg(vcpu->arch.ctxt.spsr_irq, spsr_irq);
+	write_sysreg(vcpu->arch.ctxt.spsr_fiq, spsr_fiq);
 
 	write_sysreg(__vcpu_sys_reg(vcpu, DACR32_EL2), dacr32_el2);
 	write_sysreg(__vcpu_sys_reg(vcpu, IFSR32_EL2), ifsr32_el2);
diff --git a/arch/arm64/kvm/regmap.c b/arch/arm64/kvm/regmap.c
index b1596f314087..97c110810527 100644
--- a/arch/arm64/kvm/regmap.c
+++ b/arch/arm64/kvm/regmap.c
@@ -147,8 +147,20 @@ unsigned long vcpu_read_spsr32(const struct kvm_vcpu *vcpu)
 {
 	int spsr_idx = vcpu_spsr32_mode(vcpu);
 
-	if (!vcpu->arch.sysregs_loaded_on_cpu)
-		return vcpu->arch.ctxt.spsr[spsr_idx];
+	if (!vcpu->arch.sysregs_loaded_on_cpu) {
+		switch (spsr_idx) {
+		case KVM_SPSR_SVC:
+			return vcpu->arch.ctxt.spsr_el1;
+		case KVM_SPSR_ABT:
+			return vcpu->arch.ctxt.spsr_abt;
+		case KVM_SPSR_UND:
+			return vcpu->arch.ctxt.spsr_und;
+		case KVM_SPSR_IRQ:
+			return vcpu->arch.ctxt.spsr_irq;
+		case KVM_SPSR_FIQ:
+			return vcpu->arch.ctxt.spsr_fiq;
+		}
+	}
 
 	switch (spsr_idx) {
 	case KVM_SPSR_SVC:
@@ -171,7 +183,24 @@ void vcpu_write_spsr32(struct kvm_vcpu *vcpu, unsigned long v)
 	int spsr_idx = vcpu_spsr32_mode(vcpu);
 
 	if (!vcpu->arch.sysregs_loaded_on_cpu) {
-		vcpu->arch.ctxt.spsr[spsr_idx] = v;
+		switch (spsr_idx) {
+		case KVM_SPSR_SVC:
+			vcpu->arch.ctxt.spsr_el1 = v;
+			break;
+		case KVM_SPSR_ABT:
+			vcpu->arch.ctxt.spsr_abt = v;
+			break;
+		case KVM_SPSR_UND:
+			vcpu->arch.ctxt.spsr_und = v;
+			break;
+		case KVM_SPSR_IRQ:
+			vcpu->arch.ctxt.spsr_irq = v;
+			break;
+		case KVM_SPSR_FIQ:
+			vcpu->arch.ctxt.spsr_fiq = v;
+			break;
+		}
+
 		return;
 	}
 
-- 
cgit 


From 710f1982187afd3f25413d92a0804ccd780634f7 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Fri, 28 Jun 2019 23:05:38 +0100
Subject: KVM: arm64: Move SPSR_EL1 to the system register array

SPSR_EL1 being a VNCR-capable register with ARMv8.4-NV, move it to
the sysregs array and update the accessors.

Reviewed-by: James Morse <james.morse@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_emulate.h       | 4 ++--
 arch/arm64/include/asm/kvm_host.h          | 2 +-
 arch/arm64/kvm/guest.c                     | 2 +-
 arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h | 4 ++--
 arch/arm64/kvm/regmap.c                    | 4 ++--
 5 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 5f959fedff09..57f9042e7270 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -176,7 +176,7 @@ static inline unsigned long vcpu_read_spsr(const struct kvm_vcpu *vcpu)
 	if (vcpu->arch.sysregs_loaded_on_cpu)
 		return read_sysreg_el1(SYS_SPSR);
 	else
-		return vcpu->arch.ctxt.spsr_el1;
+		return __vcpu_sys_reg(vcpu, SPSR_EL1);
 }
 
 static inline void vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long v)
@@ -189,7 +189,7 @@ static inline void vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long v)
 	if (vcpu->arch.sysregs_loaded_on_cpu)
 		write_sysreg_el1(v, SYS_SPSR);
 	else
-		vcpu->arch.ctxt.spsr_el1 = v;
+		__vcpu_sys_reg(vcpu, SPSR_EL1) = v;
 }
 
 /*
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index dfb97ed2f680..91b1adb6789c 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -187,6 +187,7 @@ enum vcpu_sysreg {
 
 	ELR_EL1,
 	SP_EL1,
+	SPSR_EL1,
 
 	/* 32bit specific registers. Keep them at the end of the range */
 	DACR32_EL2,	/* Domain Access Control Register */
@@ -241,7 +242,6 @@ enum vcpu_sysreg {
 struct kvm_cpu_context {
 	struct user_pt_regs regs;	/* sp = sp_el0 */
 
-	u64	spsr_el1;		/* aka spsr_svc */
 	u64	spsr_abt;
 	u64	spsr_und;
 	u64	spsr_irq;
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 70215f3a6f89..dfb5218137ca 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -135,7 +135,7 @@ static void *core_reg_addr(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 		return __ctxt_sys_reg(&vcpu->arch.ctxt, ELR_EL1);
 
 	case KVM_REG_ARM_CORE_REG(spsr[KVM_SPSR_EL1]):
-		return &vcpu->arch.ctxt.spsr_el1;
+		return __ctxt_sys_reg(&vcpu->arch.ctxt, SPSR_EL1);
 
 	case KVM_REG_ARM_CORE_REG(spsr[KVM_SPSR_ABT]):
 		return &vcpu->arch.ctxt.spsr_abt;
diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
index fb4bc42e72c5..7a986030145f 100644
--- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
@@ -48,7 +48,7 @@ static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
 
 	ctxt_sys_reg(ctxt, SP_EL1)	= read_sysreg(sp_el1);
 	ctxt_sys_reg(ctxt, ELR_EL1)	= read_sysreg_el1(SYS_ELR);
-	ctxt->spsr_el1			= read_sysreg_el1(SYS_SPSR);
+	ctxt_sys_reg(ctxt, SPSR_EL1)	= read_sysreg_el1(SYS_SPSR);
 }
 
 static inline void __sysreg_save_el2_return_state(struct kvm_cpu_context *ctxt)
@@ -127,7 +127,7 @@ static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
 
 	write_sysreg(ctxt_sys_reg(ctxt, SP_EL1),	sp_el1);
 	write_sysreg_el1(ctxt_sys_reg(ctxt, ELR_EL1),	SYS_ELR);
-	write_sysreg_el1(ctxt->spsr_el1,		SYS_SPSR);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, SPSR_EL1),	SYS_SPSR);
 }
 
 static inline void __sysreg_restore_el2_return_state(struct kvm_cpu_context *ctxt)
diff --git a/arch/arm64/kvm/regmap.c b/arch/arm64/kvm/regmap.c
index 97c110810527..accc1d5fba61 100644
--- a/arch/arm64/kvm/regmap.c
+++ b/arch/arm64/kvm/regmap.c
@@ -150,7 +150,7 @@ unsigned long vcpu_read_spsr32(const struct kvm_vcpu *vcpu)
 	if (!vcpu->arch.sysregs_loaded_on_cpu) {
 		switch (spsr_idx) {
 		case KVM_SPSR_SVC:
-			return vcpu->arch.ctxt.spsr_el1;
+			return __vcpu_sys_reg(vcpu, SPSR_EL1);
 		case KVM_SPSR_ABT:
 			return vcpu->arch.ctxt.spsr_abt;
 		case KVM_SPSR_UND:
@@ -185,7 +185,7 @@ void vcpu_write_spsr32(struct kvm_vcpu *vcpu, unsigned long v)
 	if (!vcpu->arch.sysregs_loaded_on_cpu) {
 		switch (spsr_idx) {
 		case KVM_SPSR_SVC:
-			vcpu->arch.ctxt.spsr_el1 = v;
+			__vcpu_sys_reg(vcpu, SPSR_EL1) = v;
 			break;
 		case KVM_SPSR_ABT:
 			vcpu->arch.ctxt.spsr_abt = v;
-- 
cgit 


From 3c5ff0c60f2febb170bc4096d4b8a8390ebb0bad Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Wed, 22 Apr 2020 08:58:22 +0100
Subject: KVM: arm64: timers: Rename kvm_timer_sync_hwstate to
 kvm_timer_sync_user

kvm_timer_sync_hwstate() has nothing to do with the timer HW state,
but more to do with the state of a userspace interrupt controller.
Change the suffix from _hwstate to_user, in keeping with the rest
of the code.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/arch_timer.c  | 2 +-
 arch/arm64/kvm/arm.c         | 4 ++--
 include/kvm/arm_arch_timer.h | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c
index a1fe0ea3254e..33d85a504720 100644
--- a/arch/arm64/kvm/arch_timer.c
+++ b/arch/arm64/kvm/arch_timer.c
@@ -615,7 +615,7 @@ static void unmask_vtimer_irq_user(struct kvm_vcpu *vcpu)
 	}
 }
 
-void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu)
+void kvm_timer_sync_user(struct kvm_vcpu *vcpu)
 {
 	struct arch_timer_cpu *timer = vcpu_timer(vcpu);
 
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index beb0e68cccaa..e52f2b2305b5 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -723,7 +723,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 			isb(); /* Ensure work in x_flush_hwstate is committed */
 			kvm_pmu_sync_hwstate(vcpu);
 			if (static_branch_unlikely(&userspace_irqchip_in_use))
-				kvm_timer_sync_hwstate(vcpu);
+				kvm_timer_sync_user(vcpu);
 			kvm_vgic_sync_hwstate(vcpu);
 			local_irq_enable();
 			preempt_enable();
@@ -768,7 +768,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		 * timer virtual interrupt state.
 		 */
 		if (static_branch_unlikely(&userspace_irqchip_in_use))
-			kvm_timer_sync_hwstate(vcpu);
+			kvm_timer_sync_user(vcpu);
 
 		kvm_arch_vcpu_ctxsync_fp(vcpu);
 
diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h
index d120e6c323e7..a821dd1df0cf 100644
--- a/include/kvm/arm_arch_timer.h
+++ b/include/kvm/arm_arch_timer.h
@@ -71,7 +71,7 @@ int kvm_timer_hyp_init(bool);
 int kvm_timer_enable(struct kvm_vcpu *vcpu);
 int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu);
 void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu);
-void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu);
+void kvm_timer_sync_user(struct kvm_vcpu *vcpu);
 bool kvm_timer_should_notify_user(struct kvm_vcpu *vcpu);
 void kvm_timer_update_run(struct kvm_vcpu *vcpu);
 void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu);
-- 
cgit 


From 41ce82f63c0624556b94b90551e4f70a0c913879 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Fri, 28 Jun 2019 15:23:43 +0100
Subject: KVM: arm64: timers: Move timer registers to the sys_regs file

Move the timer gsisters to the sysreg file. This will further help when
they are directly changed by a nesting hypervisor in the VNCR page.

This requires moving the initialisation of the timer struct so that some
of the helpers (such as arch_timer_ctx_index) can work correctly at an
early stage.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_host.h |   6 ++
 arch/arm64/kvm/arch_timer.c       | 155 ++++++++++++++++++++++++++++++--------
 arch/arm64/kvm/trace_arm.h        |   8 +-
 include/kvm/arm_arch_timer.h      |  11 +--
 4 files changed, 136 insertions(+), 44 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 91b1adb6789c..e1a32c0707bb 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -189,6 +189,12 @@ enum vcpu_sysreg {
 	SP_EL1,
 	SPSR_EL1,
 
+	CNTVOFF_EL2,
+	CNTV_CVAL_EL0,
+	CNTV_CTL_EL0,
+	CNTP_CVAL_EL0,
+	CNTP_CTL_EL0,
+
 	/* 32bit specific registers. Keep them at the end of the range */
 	DACR32_EL2,	/* Domain Access Control Register */
 	IFSR32_EL2,	/* Instruction Fault Status Register */
diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c
index 33d85a504720..32ba6fbc3814 100644
--- a/arch/arm64/kvm/arch_timer.c
+++ b/arch/arm64/kvm/arch_timer.c
@@ -51,6 +51,93 @@ static u64 kvm_arm_timer_read(struct kvm_vcpu *vcpu,
 			      struct arch_timer_context *timer,
 			      enum kvm_arch_timer_regs treg);
 
+u32 timer_get_ctl(struct arch_timer_context *ctxt)
+{
+	struct kvm_vcpu *vcpu = ctxt->vcpu;
+
+	switch(arch_timer_ctx_index(ctxt)) {
+	case TIMER_VTIMER:
+		return __vcpu_sys_reg(vcpu, CNTV_CTL_EL0);
+	case TIMER_PTIMER:
+		return __vcpu_sys_reg(vcpu, CNTP_CTL_EL0);
+	default:
+		WARN_ON(1);
+		return 0;
+	}
+}
+
+u64 timer_get_cval(struct arch_timer_context *ctxt)
+{
+	struct kvm_vcpu *vcpu = ctxt->vcpu;
+
+	switch(arch_timer_ctx_index(ctxt)) {
+	case TIMER_VTIMER:
+		return __vcpu_sys_reg(vcpu, CNTV_CVAL_EL0);
+	case TIMER_PTIMER:
+		return __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0);
+	default:
+		WARN_ON(1);
+		return 0;
+	}
+}
+
+static u64 timer_get_offset(struct arch_timer_context *ctxt)
+{
+	struct kvm_vcpu *vcpu = ctxt->vcpu;
+
+	switch(arch_timer_ctx_index(ctxt)) {
+	case TIMER_VTIMER:
+		return __vcpu_sys_reg(vcpu, CNTVOFF_EL2);
+	default:
+		return 0;
+	}
+}
+
+static void timer_set_ctl(struct arch_timer_context *ctxt, u32 ctl)
+{
+	struct kvm_vcpu *vcpu = ctxt->vcpu;
+
+	switch(arch_timer_ctx_index(ctxt)) {
+	case TIMER_VTIMER:
+		__vcpu_sys_reg(vcpu, CNTV_CTL_EL0) = ctl;
+		break;
+	case TIMER_PTIMER:
+		__vcpu_sys_reg(vcpu, CNTP_CTL_EL0) = ctl;
+		break;
+	default:
+		WARN_ON(1);
+	}
+}
+
+static void timer_set_cval(struct arch_timer_context *ctxt, u64 cval)
+{
+	struct kvm_vcpu *vcpu = ctxt->vcpu;
+
+	switch(arch_timer_ctx_index(ctxt)) {
+	case TIMER_VTIMER:
+		__vcpu_sys_reg(vcpu, CNTV_CVAL_EL0) = cval;
+		break;
+	case TIMER_PTIMER:
+		__vcpu_sys_reg(vcpu, CNTP_CVAL_EL0) = cval;
+		break;
+	default:
+		WARN_ON(1);
+	}
+}
+
+static void timer_set_offset(struct arch_timer_context *ctxt, u64 offset)
+{
+	struct kvm_vcpu *vcpu = ctxt->vcpu;
+
+	switch(arch_timer_ctx_index(ctxt)) {
+	case TIMER_VTIMER:
+		__vcpu_sys_reg(vcpu, CNTVOFF_EL2) = offset;
+		break;
+	default:
+		WARN(offset, "timer %ld\n", arch_timer_ctx_index(ctxt));
+	}
+}
+
 u64 kvm_phys_timer_read(void)
 {
 	return timecounter->cc->read(timecounter->cc);
@@ -124,8 +211,8 @@ static u64 kvm_timer_compute_delta(struct arch_timer_context *timer_ctx)
 {
 	u64 cval, now;
 
-	cval = timer_ctx->cnt_cval;
-	now = kvm_phys_timer_read() - timer_ctx->cntvoff;
+	cval = timer_get_cval(timer_ctx);
+	now = kvm_phys_timer_read() - timer_get_offset(timer_ctx);
 
 	if (now < cval) {
 		u64 ns;
@@ -144,8 +231,8 @@ static bool kvm_timer_irq_can_fire(struct arch_timer_context *timer_ctx)
 {
 	WARN_ON(timer_ctx && timer_ctx->loaded);
 	return timer_ctx &&
-	       !(timer_ctx->cnt_ctl & ARCH_TIMER_CTRL_IT_MASK) &&
-		(timer_ctx->cnt_ctl & ARCH_TIMER_CTRL_ENABLE);
+		((timer_get_ctl(timer_ctx) &
+		  (ARCH_TIMER_CTRL_IT_MASK | ARCH_TIMER_CTRL_ENABLE)) == ARCH_TIMER_CTRL_ENABLE);
 }
 
 /*
@@ -256,8 +343,8 @@ static bool kvm_timer_should_fire(struct arch_timer_context *timer_ctx)
 	if (!kvm_timer_irq_can_fire(timer_ctx))
 		return false;
 
-	cval = timer_ctx->cnt_cval;
-	now = kvm_phys_timer_read() - timer_ctx->cntvoff;
+	cval = timer_get_cval(timer_ctx);
+	now = kvm_phys_timer_read() - timer_get_offset(timer_ctx);
 
 	return cval <= now;
 }
@@ -350,8 +437,8 @@ static void timer_save_state(struct arch_timer_context *ctx)
 
 	switch (index) {
 	case TIMER_VTIMER:
-		ctx->cnt_ctl = read_sysreg_el0(SYS_CNTV_CTL);
-		ctx->cnt_cval = read_sysreg_el0(SYS_CNTV_CVAL);
+		timer_set_ctl(ctx, read_sysreg_el0(SYS_CNTV_CTL));
+		timer_set_cval(ctx, read_sysreg_el0(SYS_CNTV_CVAL));
 
 		/* Disable the timer */
 		write_sysreg_el0(0, SYS_CNTV_CTL);
@@ -359,8 +446,8 @@ static void timer_save_state(struct arch_timer_context *ctx)
 
 		break;
 	case TIMER_PTIMER:
-		ctx->cnt_ctl = read_sysreg_el0(SYS_CNTP_CTL);
-		ctx->cnt_cval = read_sysreg_el0(SYS_CNTP_CVAL);
+		timer_set_ctl(ctx, read_sysreg_el0(SYS_CNTP_CTL));
+		timer_set_cval(ctx, read_sysreg_el0(SYS_CNTP_CVAL));
 
 		/* Disable the timer */
 		write_sysreg_el0(0, SYS_CNTP_CTL);
@@ -429,14 +516,14 @@ static void timer_restore_state(struct arch_timer_context *ctx)
 
 	switch (index) {
 	case TIMER_VTIMER:
-		write_sysreg_el0(ctx->cnt_cval, SYS_CNTV_CVAL);
+		write_sysreg_el0(timer_get_cval(ctx), SYS_CNTV_CVAL);
 		isb();
-		write_sysreg_el0(ctx->cnt_ctl, SYS_CNTV_CTL);
+		write_sysreg_el0(timer_get_ctl(ctx), SYS_CNTV_CTL);
 		break;
 	case TIMER_PTIMER:
-		write_sysreg_el0(ctx->cnt_cval, SYS_CNTP_CVAL);
+		write_sysreg_el0(timer_get_cval(ctx), SYS_CNTP_CVAL);
 		isb();
-		write_sysreg_el0(ctx->cnt_ctl, SYS_CNTP_CTL);
+		write_sysreg_el0(timer_get_ctl(ctx), SYS_CNTP_CTL);
 		break;
 	case NR_KVM_TIMERS:
 		BUG();
@@ -528,7 +615,7 @@ void kvm_timer_vcpu_load(struct kvm_vcpu *vcpu)
 		kvm_timer_vcpu_load_nogic(vcpu);
 	}
 
-	set_cntvoff(map.direct_vtimer->cntvoff);
+	set_cntvoff(timer_get_offset(map.direct_vtimer));
 
 	kvm_timer_unblocking(vcpu);
 
@@ -639,8 +726,8 @@ int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu)
 	 * resets the timer to be disabled and unmasked and is compliant with
 	 * the ARMv7 architecture.
 	 */
-	vcpu_vtimer(vcpu)->cnt_ctl = 0;
-	vcpu_ptimer(vcpu)->cnt_ctl = 0;
+	timer_set_ctl(vcpu_vtimer(vcpu), 0);
+	timer_set_ctl(vcpu_ptimer(vcpu), 0);
 
 	if (timer->enabled) {
 		kvm_timer_update_irq(vcpu, false, vcpu_vtimer(vcpu));
@@ -668,13 +755,13 @@ static void update_vtimer_cntvoff(struct kvm_vcpu *vcpu, u64 cntvoff)
 
 	mutex_lock(&kvm->lock);
 	kvm_for_each_vcpu(i, tmp, kvm)
-		vcpu_vtimer(tmp)->cntvoff = cntvoff;
+		timer_set_offset(vcpu_vtimer(tmp), cntvoff);
 
 	/*
 	 * When called from the vcpu create path, the CPU being created is not
 	 * included in the loop above, so we just set it here as well.
 	 */
-	vcpu_vtimer(vcpu)->cntvoff = cntvoff;
+	timer_set_offset(vcpu_vtimer(vcpu), cntvoff);
 	mutex_unlock(&kvm->lock);
 }
 
@@ -684,9 +771,12 @@ void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu)
 	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
 	struct arch_timer_context *ptimer = vcpu_ptimer(vcpu);
 
+	vtimer->vcpu = vcpu;
+	ptimer->vcpu = vcpu;
+
 	/* Synchronize cntvoff across all vtimers of a VM. */
 	update_vtimer_cntvoff(vcpu, kvm_phys_timer_read());
-	ptimer->cntvoff = 0;
+	timer_set_offset(ptimer, 0);
 
 	hrtimer_init(&timer->bg_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
 	timer->bg_timer.function = kvm_bg_timer_expire;
@@ -704,9 +794,6 @@ void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu)
 
 	vtimer->host_timer_irq_flags = host_vtimer_irq_flags;
 	ptimer->host_timer_irq_flags = host_ptimer_irq_flags;
-
-	vtimer->vcpu = vcpu;
-	ptimer->vcpu = vcpu;
 }
 
 static void kvm_timer_init_interrupt(void *info)
@@ -756,10 +843,12 @@ static u64 read_timer_ctl(struct arch_timer_context *timer)
 	 * UNKNOWN when ENABLE bit is 0, so we chose to set ISTATUS bit
 	 * regardless of ENABLE bit for our implementation convenience.
 	 */
+	u32 ctl = timer_get_ctl(timer);
+
 	if (!kvm_timer_compute_delta(timer))
-		return timer->cnt_ctl | ARCH_TIMER_CTRL_IT_STAT;
-	else
-		return timer->cnt_ctl;
+		ctl |= ARCH_TIMER_CTRL_IT_STAT;
+
+	return ctl;
 }
 
 u64 kvm_arm_timer_get_reg(struct kvm_vcpu *vcpu, u64 regid)
@@ -795,8 +884,8 @@ static u64 kvm_arm_timer_read(struct kvm_vcpu *vcpu,
 
 	switch (treg) {
 	case TIMER_REG_TVAL:
-		val = timer->cnt_cval - kvm_phys_timer_read() + timer->cntvoff;
-		val &= lower_32_bits(val);
+		val = timer_get_cval(timer) - kvm_phys_timer_read() + timer_get_offset(timer);
+		val = lower_32_bits(val);
 		break;
 
 	case TIMER_REG_CTL:
@@ -804,11 +893,11 @@ static u64 kvm_arm_timer_read(struct kvm_vcpu *vcpu,
 		break;
 
 	case TIMER_REG_CVAL:
-		val = timer->cnt_cval;
+		val = timer_get_cval(timer);
 		break;
 
 	case TIMER_REG_CNT:
-		val = kvm_phys_timer_read() - timer->cntvoff;
+		val = kvm_phys_timer_read() - timer_get_offset(timer);
 		break;
 
 	default:
@@ -842,15 +931,15 @@ static void kvm_arm_timer_write(struct kvm_vcpu *vcpu,
 {
 	switch (treg) {
 	case TIMER_REG_TVAL:
-		timer->cnt_cval = kvm_phys_timer_read() - timer->cntvoff + (s32)val;
+		timer_set_cval(timer, kvm_phys_timer_read() - timer_get_offset(timer) + (s32)val);
 		break;
 
 	case TIMER_REG_CTL:
-		timer->cnt_ctl = val & ~ARCH_TIMER_CTRL_IT_STAT;
+		timer_set_ctl(timer, val & ~ARCH_TIMER_CTRL_IT_STAT);
 		break;
 
 	case TIMER_REG_CVAL:
-		timer->cnt_cval = val;
+		timer_set_cval(timer, val);
 		break;
 
 	default:
diff --git a/arch/arm64/kvm/trace_arm.h b/arch/arm64/kvm/trace_arm.h
index 4c71270cc097..4691053c5ee4 100644
--- a/arch/arm64/kvm/trace_arm.h
+++ b/arch/arm64/kvm/trace_arm.h
@@ -301,8 +301,8 @@ TRACE_EVENT(kvm_timer_save_state,
 	),
 
 	TP_fast_assign(
-		__entry->ctl			= ctx->cnt_ctl;
-		__entry->cval			= ctx->cnt_cval;
+		__entry->ctl			= timer_get_ctl(ctx);
+		__entry->cval			= timer_get_cval(ctx);
 		__entry->timer_idx		= arch_timer_ctx_index(ctx);
 	),
 
@@ -323,8 +323,8 @@ TRACE_EVENT(kvm_timer_restore_state,
 	),
 
 	TP_fast_assign(
-		__entry->ctl			= ctx->cnt_ctl;
-		__entry->cval			= ctx->cnt_cval;
+		__entry->ctl			= timer_get_ctl(ctx);
+		__entry->cval			= timer_get_cval(ctx);
 		__entry->timer_idx		= arch_timer_ctx_index(ctx);
 	),
 
diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h
index a821dd1df0cf..51c19381108c 100644
--- a/include/kvm/arm_arch_timer.h
+++ b/include/kvm/arm_arch_timer.h
@@ -26,16 +26,9 @@ enum kvm_arch_timer_regs {
 struct arch_timer_context {
 	struct kvm_vcpu			*vcpu;
 
-	/* Registers: control register, timer value */
-	u32				cnt_ctl;
-	u64				cnt_cval;
-
 	/* Timer IRQ */
 	struct kvm_irq_level		irq;
 
-	/* Virtual offset */
-	u64				cntvoff;
-
 	/* Emulated Timer (may be unused) */
 	struct hrtimer			hrtimer;
 
@@ -109,4 +102,8 @@ void kvm_arm_timer_write_sysreg(struct kvm_vcpu *vcpu,
 				enum kvm_arch_timer_regs treg,
 				u64 val);
 
+/* Needed for tracing */
+u32 timer_get_ctl(struct arch_timer_context *ctxt);
+u64 timer_get_cval(struct arch_timer_context *ctxt);
+
 #endif
-- 
cgit 


From 6de7dd31ded078b31a3812a46d8874f871b4e82f Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 7 Jul 2020 15:34:06 +0100
Subject: KVM: arm64: Don't use has_vhe() for CHOOSE_HYP_SYM()

The recently introduced CHOOSE_HYP_SYM() macro picks one symbol
or another, depending on whether the kernel run as a VHE
hypervisor or not. For that, it uses the has_vhe() helper, which
is itself implemented as a final capability.

Unfortunately, __copy_hyp_vect_bpi now indirectly uses CHOOSE_HYP_SYM
to get the __bp_harden_hyp_vecs symbol, using has_vhe() in the process.
At this stage, the capability isn't final and things explode:

[    0.000000] ACPI: SRAT not present
[    0.000000] percpu: Embedded 34 pages/cpu s101264 r8192 d29808 u139264
[    0.000000] Detected PIPT I-cache on CPU0
[    0.000000] ------------[ cut here ]------------
[    0.000000] kernel BUG at arch/arm64/include/asm/cpufeature.h:459!
[    0.000000] Internal error: Oops - BUG: 0 [#1] PREEMPT SMP
[    0.000000] Modules linked in:
[    0.000000] CPU: 0 PID: 0 Comm: swapper Not tainted 5.8.0-rc4-00080-gd630681366e5 #1388
[    0.000000] pstate: 80000085 (Nzcv daIf -PAN -UAO BTYPE=--)
[    0.000000] pc : check_branch_predictor+0x3a4/0x408
[    0.000000] lr : check_branch_predictor+0x2a4/0x408
[    0.000000] sp : ffff800011693e90
[    0.000000] x29: ffff800011693e90 x28: ffff8000116a1530
[    0.000000] x27: ffff8000112c1008 x26: ffff800010ca6ff8
[    0.000000] x25: ffff8000112c1000 x24: ffff8000116a1320
[    0.000000] x23: 0000000000000000 x22: ffff8000112c1000
[    0.000000] x21: ffff800010177120 x20: ffff8000116ae108
[    0.000000] x19: 0000000000000000 x18: ffff800011965c90
[    0.000000] x17: 0000000000022000 x16: 0000000000000003
[    0.000000] x15: 00000000ffffffff x14: ffff8000118c3a38
[    0.000000] x13: 0000000000000021 x12: 0000000000000022
[    0.000000] x11: d37a6f4de9bd37a7 x10: 000000000000001d
[    0.000000] x9 : 0000000000000000 x8 : ffff800011f8dad8
[    0.000000] x7 : ffff800011965ad0 x6 : 0000000000000003
[    0.000000] x5 : 0000000000000000 x4 : 0000000000000000
[    0.000000] x3 : 0000000000000100 x2 : 0000000000000004
[    0.000000] x1 : ffff8000116ae148 x0 : 0000000000000000
[    0.000000] Call trace:
[    0.000000]  check_branch_predictor+0x3a4/0x408
[    0.000000]  update_cpu_capabilities+0x84/0x138
[    0.000000]  init_cpu_features+0x2c0/0x2d8
[    0.000000]  cpuinfo_store_boot_cpu+0x54/0x64
[    0.000000]  smp_prepare_boot_cpu+0x2c/0x60
[    0.000000]  start_kernel+0x16c/0x574
[    0.000000] Code: 17ffffc7 91010281 14000198 17ffffca (d4210000)

This is addressed using a two-fold process:
- Replace has_vhe() with is_kernel_in_hyp_mode(), which tests
  whether we are running at EL2.
- Make CHOOSE_HYP_SYM() return an *undefined* symbol when
  compiled in the nVHE hypervisor, as we really should never
  use this helper in the nVHE-specific code.

With this in place, we're back to a bootable kernel again.

Fixes: b877e9849d41 ("KVM: arm64: Build hyp-entry.S separately for VHE/nVHE")
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_asm.h | 20 +++++++++++++++++++-
 1 file changed, 19 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 5a91aaae78d2..1a66815ea01b 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -62,8 +62,26 @@
 
 #define CHOOSE_VHE_SYM(sym)	sym
 #define CHOOSE_NVHE_SYM(sym)	kvm_nvhe_sym(sym)
-#define CHOOSE_HYP_SYM(sym)	(has_vhe() ? CHOOSE_VHE_SYM(sym) \
+
+#ifndef __KVM_NVHE_HYPERVISOR__
+/*
+ * BIG FAT WARNINGS:
+ *
+ * - Don't be tempted to change the following is_kernel_in_hyp_mode()
+ *   to has_vhe(). has_vhe() is implemented as a *final* capability,
+ *   while this is used early at boot time, when the capabilities are
+ *   not final yet....
+ *
+ * - Don't let the nVHE hypervisor have access to this, as it will
+ *   pick the *wrong* symbol (yes, it runs at EL2...).
+ */
+#define CHOOSE_HYP_SYM(sym)	(is_kernel_in_hyp_mode() ? CHOOSE_VHE_SYM(sym) \
 					   : CHOOSE_NVHE_SYM(sym))
+#else
+/* The nVHE hypervisor shouldn't even try to access anything */
+extern void *__nvhe_undefined_symbol;
+#define CHOOSE_HYP_SYM(sym)	__nvhe_undefined_symbol
+#endif
 
 /* Translate a kernel address @ptr into its equivalent linear mapping */
 #define kvm_ksym_ref(ptr)						\
-- 
cgit 


From 24f69c0fa4e252f706884114b7d6353aa07678b5 Mon Sep 17 00:00:00 2001
From: David Brazdil <dbrazdil@google.com>
Date: Tue, 21 Jul 2020 10:44:44 +0100
Subject: KVM: arm64: Make nVHE ASLR conditional on RANDOMIZE_BASE

If there are spare bits in non-VHE hyp VA, KVM unconditionally replaces them
with a random tag chosen at init. Disable this if the kernel is built without
RANDOMIZE_BASE to align with kernel behavior.

Signed-off-by: David Brazdil <dbrazdil@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200721094445.82184-2-dbrazdil@google.com
---
 arch/arm64/kvm/va_layout.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/va_layout.c b/arch/arm64/kvm/va_layout.c
index a4f48c1ac28c..e0404bcab019 100644
--- a/arch/arm64/kvm/va_layout.c
+++ b/arch/arm64/kvm/va_layout.c
@@ -48,7 +48,7 @@ __init void kvm_compute_layout(void)
 	va_mask = GENMASK_ULL(tag_lsb - 1, 0);
 	tag_val = hyp_va_msb;
 
-	if (tag_lsb != (vabits_actual - 1)) {
+	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && tag_lsb != (vabits_actual - 1)) {
 		/* We have some free bits to insert a random tag. */
 		tag_val |= get_random_long() & GENMASK_ULL(vabits_actual - 2, tag_lsb);
 	}
-- 
cgit 


From a59a2edbbba7397fede86e40a3da17e5beebf98b Mon Sep 17 00:00:00 2001
From: David Brazdil <dbrazdil@google.com>
Date: Tue, 21 Jul 2020 10:44:45 +0100
Subject: KVM: arm64: Substitute RANDOMIZE_BASE for HARDEN_EL2_VECTORS

The HARDEN_EL2_VECTORS config maps vectors at a fixed location on cores which
are susceptible to Spector variant 3a (A57, A72) to prevent defeating hyp
layout randomization by leaking the value of VBAR_EL2.

Since this feature is only applicable when EL2 layout randomization is enabled,
unify both behind the same RANDOMIZE_BASE Kconfig. Majority of code remains
conditional on a capability selected for the affected cores.

Signed-off-by: David Brazdil <dbrazdil@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200721094445.82184-3-dbrazdil@google.com
---
 arch/arm64/Kconfig             | 16 ----------------
 arch/arm64/include/asm/mmu.h   |  6 ++----
 arch/arm64/kernel/cpu_errata.c |  4 ++--
 arch/arm64/kvm/Kconfig         |  2 +-
 4 files changed, 5 insertions(+), 23 deletions(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 31380da53689..152deef3277e 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1182,22 +1182,6 @@ config HARDEN_BRANCH_PREDICTOR
 
 	  If unsure, say Y.
 
-config HARDEN_EL2_VECTORS
-	bool "Harden EL2 vector mapping against system register leak" if EXPERT
-	default y
-	help
-	  Speculation attacks against some high-performance processors can
-	  be used to leak privileged information such as the vector base
-	  register, resulting in a potential defeat of the EL2 layout
-	  randomization.
-
-	  This config option will map the vectors to a fixed location,
-	  independent of the EL2 code mapping, so that revealing VBAR_EL2
-	  to an attacker does not give away any extra information. This
-	  only gets enabled on affected CPUs.
-
-	  If unsure, say Y.
-
 config ARM64_SSBD
 	bool "Speculative Store Bypass Disable" if EXPERT
 	default y
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index 68140fdd89d6..bd12011eb560 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -42,12 +42,10 @@ struct bp_hardening_data {
 	bp_hardening_cb_t	fn;
 };
 
-#if (defined(CONFIG_HARDEN_BRANCH_PREDICTOR) ||	\
-     defined(CONFIG_HARDEN_EL2_VECTORS))
-
+#ifdef CONFIG_KVM_INDIRECT_VECTORS
 extern char __bp_harden_hyp_vecs[];
 extern atomic_t arm64_el2_vector_last_slot;
-#endif  /* CONFIG_HARDEN_BRANCH_PREDICTOR || CONFIG_HARDEN_EL2_VECTORS */
+#endif
 
 #ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
 DECLARE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data);
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index ad06d6802d2e..a524142e55d0 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -635,7 +635,7 @@ has_neoverse_n1_erratum_1542419(const struct arm64_cpu_capabilities *entry,
 	return is_midr_in_range(midr, &range) && has_dic;
 }
 
-#if defined(CONFIG_HARDEN_EL2_VECTORS)
+#ifdef CONFIG_RANDOMIZE_BASE
 
 static const struct midr_range ca57_a72[] = {
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A57),
@@ -880,7 +880,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
 		.matches = check_branch_predictor,
 	},
-#ifdef CONFIG_HARDEN_EL2_VECTORS
+#ifdef CONFIG_RANDOMIZE_BASE
 	{
 		.desc = "EL2 vector hardening",
 		.capability = ARM64_HARDEN_EL2_VECTORS,
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index 13489aff4440..318c8f2df245 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -58,7 +58,7 @@ config KVM_ARM_PMU
 	  virtual machines.
 
 config KVM_INDIRECT_VECTORS
-	def_bool HARDEN_BRANCH_PREDICTOR || HARDEN_EL2_VECTORS
+	def_bool HARDEN_BRANCH_PREDICTOR || RANDOMIZE_BASE
 
 endif # KVM
 
-- 
cgit 


From bdbc0c7a070c0cbe3009cd271c6ec8d87d69cc7a Mon Sep 17 00:00:00 2001
From: David Brazdil <dbrazdil@google.com>
Date: Thu, 30 Jul 2020 14:25:19 +0100
Subject: KVM: arm64: Ensure that all nVHE hyp code is in .hyp.text

Some compilers may put a subset of generated functions into '.text.*'
ELF sections and the linker may leverage this division to optimize ELF
layout. Unfortunately, the recently introduced HYPCOPY command assumes
that all executable code (with the exception of specialized sections
such as '.hyp.idmap.text') is in the '.text' section. If this
assumption is broken, code in '.text.*' will be merged into kernel
proper '.text' instead of the '.hyp.text' that is mapped in EL2.

To ensure that this cannot happen, insert an OBJDUMP assertion into
HYPCOPY. The command dumps a list of ELF sections in the input object
file and greps for '.text.'. If found, compilation fails. Tested with
both binutils' and LLVM's objdump (the output format is different).

GCC offers '-fno-reorder-functions' to disable this behaviour. Select
the flag if it is available. From inspection of GCC source (latest
Git in July 2020), this flag does force all code into '.text'.
By default, GCC uses profile data, heuristics and attributes to select
a subsection.

LLVM/Clang currently does not have a similar optimization pass. It can
place static constructors into '.text.startup' and it's optimizer can
be provided with profile data to reorder hot/cold functions. Neither
of these is applicable to nVHE hyp code. If this changes in the future,
the OBJDUMP assertion should alert users to the problem.

Signed-off-by: David Brazdil <dbrazdil@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200730132519.48787-1-dbrazdil@google.com
---
 arch/arm64/kvm/hyp/nvhe/Makefile | 26 +++++++++++++++++++++++---
 1 file changed, 23 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile
index 0b34414557d6..aef76487edc2 100644
--- a/arch/arm64/kvm/hyp/nvhe/Makefile
+++ b/arch/arm64/kvm/hyp/nvhe/Makefile
@@ -20,10 +20,30 @@ $(obj)/%.hyp.tmp.o: $(src)/%.S FORCE
 $(obj)/%.hyp.o: $(obj)/%.hyp.tmp.o FORCE
 	$(call if_changed,hypcopy)
 
+# Disable reordering functions by GCC (enabled at -O2).
+# This pass puts functions into '.text.*' sections to aid the linker
+# in optimizing ELF layout. See HYPCOPY comment below for more info.
+ccflags-y += $(call cc-option,-fno-reorder-functions)
+
+# The HYPCOPY command uses `objcopy` to prefix all ELF symbol names
+# and relevant ELF section names to avoid clashes with VHE code/data.
+#
+# Hyp code is assumed to be in the '.text' section of the input object
+# files (with the exception of specialized sections such as
+# '.hyp.idmap.text'). This assumption may be broken by a compiler that
+# divides code into sections like '.text.unlikely' so as to optimize
+# ELF layout. HYPCOPY checks that no such sections exist in the input
+# using `objdump`, otherwise they would be linked together with other
+# kernel code and not memory-mapped correctly at runtime.
 quiet_cmd_hypcopy = HYPCOPY $@
-      cmd_hypcopy = $(OBJCOPY)	--prefix-symbols=__kvm_nvhe_		\
-				--rename-section=.text=.hyp.text	\
-				$< $@
+      cmd_hypcopy =							\
+	if $(OBJDUMP) -h $< | grep -F '.text.'; then			\
+		echo "$@: function reordering not supported in nVHE hyp code" >&2; \
+		/bin/false;						\
+	fi;								\
+	$(OBJCOPY) --prefix-symbols=__kvm_nvhe_				\
+		   --rename-section=.text=.hyp.text			\
+		   $< $@
 
 # Remove ftrace and Shadow Call Stack CFLAGS.
 # This is equivalent to the 'notrace' and '__noscs' annotations.
-- 
cgit 


From 1ccf2fe35c30f79102ad129c5aa71059daaaed7f Mon Sep 17 00:00:00 2001
From: Alexander Graf <graf@amazon.com>
Date: Thu, 30 Jul 2020 11:44:41 +0200
Subject: KVM: arm: Add trace name for ARM_NISV

Commit c726200dd106d ("KVM: arm/arm64: Allow reporting non-ISV data aborts
to userspace") introduced a mechanism to deflect MMIO traffic the kernel
can not handle to user space. For that, it introduced a new exit reason.

However, it did not update the trace point array that gives human readable
names to these exit reasons inside the trace log.

Let's fix that up after the fact, so that trace logs are pretty even when
we get user space MMIO traps on ARM.

Fixes: c726200dd106d ("KVM: arm/arm64: Allow reporting non-ISV data aborts to userspace")
Signed-off-by: Alexander Graf <graf@amazon.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200730094441.18231-1-graf@amazon.com
---
 include/trace/events/kvm.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h
index 2c735a3e6613..9417a34aad08 100644
--- a/include/trace/events/kvm.h
+++ b/include/trace/events/kvm.h
@@ -17,7 +17,7 @@
 	ERSN(NMI), ERSN(INTERNAL_ERROR), ERSN(OSI), ERSN(PAPR_HCALL),	\
 	ERSN(S390_UCONTROL), ERSN(WATCHDOG), ERSN(S390_TSCH), ERSN(EPR),\
 	ERSN(SYSTEM_EVENT), ERSN(S390_STSI), ERSN(IOAPIC_EOI),          \
-	ERSN(HYPERV)
+	ERSN(HYPERV), ERSN(ARM_NISV)
 
 TRACE_EVENT(kvm_userspace_exit,
 	    TP_PROTO(__u32 reason, int errno),
-- 
cgit 


From c9a636f29b5f236441ff059cef0b2fe734c05afd Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Wed, 29 Jul 2020 11:28:18 +0100
Subject: KVM: arm64: Rename kvm_vcpu_dabt_isextabt()

kvm_vcpu_dabt_isextabt() is not specific to data aborts and, unlike
kvm_vcpu_dabt_issext(), has nothing to do with sign extension.

Rename it to 'kvm_vcpu_abt_issea()'.

Signed-off-by: Will Deacon <will@kernel.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Quentin Perret <qperret@google.com>
Link: https://lore.kernel.org/r/20200729102821.23392-2-will@kernel.org
---
 arch/arm64/include/asm/kvm_emulate.h | 2 +-
 arch/arm64/kvm/hyp/switch.c          | 2 +-
 arch/arm64/kvm/mmu.c                 | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index c9ba0df47f7d..e0536946abed 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -366,7 +366,7 @@ static __always_inline u8 kvm_vcpu_trap_get_fault_type(const struct kvm_vcpu *vc
 	return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC_TYPE;
 }
 
-static __always_inline bool kvm_vcpu_dabt_isextabt(const struct kvm_vcpu *vcpu)
+static __always_inline bool kvm_vcpu_abt_issea(const struct kvm_vcpu *vcpu)
 {
 	switch (kvm_vcpu_trap_get_fault(vcpu)) {
 	case FSC_SEA:
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index 5164074c1ae1..36a1f0a9ce2e 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -594,7 +594,7 @@ static bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
 		valid = kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_DABT_LOW &&
 			kvm_vcpu_trap_get_fault_type(vcpu) == FSC_FAULT &&
 			kvm_vcpu_dabt_isvalid(vcpu) &&
-			!kvm_vcpu_dabt_isextabt(vcpu) &&
+			!kvm_vcpu_abt_issea(vcpu) &&
 			!kvm_vcpu_dabt_iss1tw(vcpu);
 
 		if (valid) {
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 36506112480e..8004f1f68946 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -2074,7 +2074,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	is_iabt = kvm_vcpu_trap_is_iabt(vcpu);
 
 	/* Synchronous External Abort? */
-	if (kvm_vcpu_dabt_isextabt(vcpu)) {
+	if (kvm_vcpu_abt_issea(vcpu)) {
 		/*
 		 * For RAS the host kernel may handle this abort.
 		 * There is no need to pass the error into the guest.
-- 
cgit 


From 84b951a803a5464b0bff2fb1366e96f07f75b066 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Wed, 29 Jul 2020 11:28:19 +0100
Subject: KVM: arm64: Handle data and instruction external aborts the same way

If the guest generates a synchronous external abort which is not handled
by the host, we inject it back into the guest as a virtual SError, but
only if the original fault was reported on the data side. Instruction
faults are reported as "Unsupported FSC", causing the vCPU run loop to
bail with -EFAULT.

Although synchronous external aborts from a guest are pretty unusual,
treat them the same regardless of whether they are taken as data or
instruction aborts by EL2.

Signed-off-by: Will Deacon <will@kernel.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Quentin Perret <qperret@google.com>
Link: https://lore.kernel.org/r/20200729102821.23392-3-will@kernel.org
---
 arch/arm64/kvm/mmu.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 8004f1f68946..14c6a9df5c9f 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -2079,13 +2079,10 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		 * For RAS the host kernel may handle this abort.
 		 * There is no need to pass the error into the guest.
 		 */
-		if (!kvm_handle_guest_sea(fault_ipa, kvm_vcpu_get_esr(vcpu)))
-			return 1;
-
-		if (unlikely(!is_iabt)) {
+		if (kvm_handle_guest_sea(fault_ipa, kvm_vcpu_get_esr(vcpu)))
 			kvm_inject_vabt(vcpu);
-			return 1;
-		}
+
+		return 1;
 	}
 
 	trace_kvm_guest_fault(*vcpu_pc(vcpu), kvm_vcpu_get_esr(vcpu),
-- 
cgit 


From 54dc0d2404dd7aa0dd4e4f388a65622b68c6eaff Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Wed, 29 Jul 2020 11:28:20 +0100
Subject: KVM: arm64: Don't skip cache maintenance for read-only memslots

If a guest performs cache maintenance on a read-only memslot, we should
inform userspace rather than skip the instruction altogether.

Signed-off-by: Will Deacon <will@kernel.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Quentin Perret <qperret@google.com>
Link: https://lore.kernel.org/r/20200729102821.23392-4-will@kernel.org
---
 arch/arm64/kvm/mmu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 14c6a9df5c9f..85b0ec9dd9ef 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -2121,7 +2121,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		 * So let's assume that the guest is just being
 		 * cautious, and skip the instruction.
 		 */
-		if (kvm_vcpu_dabt_is_cm(vcpu)) {
+		if (kvm_is_error_hva(hva) && kvm_vcpu_dabt_is_cm(vcpu)) {
 			kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
 			ret = 1;
 			goto out_unlock;
-- 
cgit 


From 022c8328dc8021248047b373b9f67790641b8f2d Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Wed, 29 Jul 2020 11:28:21 +0100
Subject: KVM: arm64: Move S1PTW S2 fault logic out of io_mem_abort()

To allow for re-injection of stage-2 faults on stage-1 page-table walks
due to either a missing or read-only memslot, move the triage logic out
of io_mem_abort() and into kvm_handle_guest_abort(), where these aborts
can be handled before anything else.

Signed-off-by: Will Deacon <will@kernel.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Quentin Perret <qperret@google.com>
Link: https://lore.kernel.org/r/20200729102821.23392-5-will@kernel.org
---
 arch/arm64/kvm/mmio.c |  6 ------
 arch/arm64/kvm/mmu.c  | 13 ++++++++++++-
 2 files changed, 12 insertions(+), 7 deletions(-)

diff --git a/arch/arm64/kvm/mmio.c b/arch/arm64/kvm/mmio.c
index 4e0366759726..58de2ae4f6bb 100644
--- a/arch/arm64/kvm/mmio.c
+++ b/arch/arm64/kvm/mmio.c
@@ -145,12 +145,6 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		return -ENOSYS;
 	}
 
-	/* Page table accesses IO mem: tell guest to fix its TTBR */
-	if (kvm_vcpu_dabt_iss1tw(vcpu)) {
-		kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu));
-		return 1;
-	}
-
 	/*
 	 * Prepare MMIO operation. First decode the syndrome data we get
 	 * from the CPU. Then try if some in-kernel emulation feels
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 85b0ec9dd9ef..dc8464669efd 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -2105,12 +2105,23 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	hva = gfn_to_hva_memslot_prot(memslot, gfn, &writable);
 	write_fault = kvm_is_write_fault(vcpu);
 	if (kvm_is_error_hva(hva) || (write_fault && !writable)) {
+		/*
+		 * The guest has put either its instructions or its page-tables
+		 * somewhere it shouldn't have. Userspace won't be able to do
+		 * anything about this (there's no syndrome for a start), so
+		 * re-inject the abort back into the guest.
+		 */
 		if (is_iabt) {
-			/* Prefetch Abort on I/O address */
 			ret = -ENOEXEC;
 			goto out;
 		}
 
+		if (kvm_vcpu_dabt_iss1tw(vcpu)) {
+			kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu));
+			ret = 1;
+			goto out_unlock;
+		}
+
 		/*
 		 * Check for a cache maintenance operation. Since we
 		 * ended-up here, we know it is outside of any memory
-- 
cgit