diff mbox series

[RFC,v2,08/19] RISC-V: KVM: Implement VCPU world-switch

Message ID 20190802074620.115029-9-anup.patel@wdc.com (mailing list archive)
State New, archived
Headers show
Series KVM RISC-V Support | expand

Commit Message

Anup Patel Aug. 2, 2019, 7:47 a.m. UTC 
This patch implements the VCPU world-switch for KVM RISC-V.

The KVM RISC-V world-switch (i.e. __kvm_riscv_switch_to()) mostly
switches general purpose registers, SSTATUS, STVEC, SSCRATCH and
HSTATUS CSRs. Other CSRs are switched via vcpu_load() and vcpu_put()
interface in kvm_arch_vcpu_load() and kvm_arch_vcpu_put() functions
respectively.

Signed-off-by: Anup Patel <anup.patel@wdc.com>
---
 arch/riscv/include/asm/kvm_host.h |   9 +-
 arch/riscv/kernel/asm-offsets.c   |  76 ++++++++++++
 arch/riscv/kvm/Makefile           |   2 +-
 arch/riscv/kvm/vcpu.c             |  30 ++++-
 arch/riscv/kvm/vcpu_switch.S      | 194 ++++++++++++++++++++++++++++++
 5 files changed, 307 insertions(+), 4 deletions(-)
 create mode 100644 arch/riscv/kvm/vcpu_switch.S

Comments

Paolo Bonzini Aug. 2, 2019, 8:30 a.m. UTC | #1 
On 02/08/19 09:47, Anup Patel wrote:
> +	/* Save Host SSTATUS, HSTATUS, SCRATCH and STVEC */
> +	csrr	t0, CSR_SSTATUS
> +	REG_S	t0, (KVM_ARCH_HOST_SSTATUS)(a0)
> +	csrr	t1, CSR_HSTATUS
> +	REG_S	t1, (KVM_ARCH_HOST_HSTATUS)(a0)
> +	csrr	t2, CSR_SSCRATCH
> +	REG_S	t2, (KVM_ARCH_HOST_SSCRATCH)(a0)
> +	csrr	t3, CSR_STVEC
> +	REG_S	t3, (KVM_ARCH_HOST_STVEC)(a0)
> +

A possible optimization: if these cannot change while Linux runs (I am
thinking especially of STVEC and HSTATUS, but perhaps SSCRATCH can be
saved on kvm_arch_vcpu_load too) you can avoid the csrr and store.

Paolo
Anup Patel Aug. 2, 2019, 8:43 a.m. UTC | #2 
On Fri, Aug 2, 2019 at 2:00 PM Paolo Bonzini <pbonzini@redhat.com> wrote:
>
> On 02/08/19 09:47, Anup Patel wrote:
> > +     /* Save Host SSTATUS, HSTATUS, SCRATCH and STVEC */
> > +     csrr    t0, CSR_SSTATUS
> > +     REG_S   t0, (KVM_ARCH_HOST_SSTATUS)(a0)
> > +     csrr    t1, CSR_HSTATUS
> > +     REG_S   t1, (KVM_ARCH_HOST_HSTATUS)(a0)
> > +     csrr    t2, CSR_SSCRATCH
> > +     REG_S   t2, (KVM_ARCH_HOST_SSCRATCH)(a0)
> > +     csrr    t3, CSR_STVEC
> > +     REG_S   t3, (KVM_ARCH_HOST_STVEC)(a0)
> > +
>
> A possible optimization: if these cannot change while Linux runs (I am
> thinking especially of STVEC and HSTATUS, but perhaps SSCRATCH can be
> saved on kvm_arch_vcpu_load too) you can avoid the csrr and store.

Actual exception vector of Host Linux is different so we switch STVEC
every time.

HSTATUS.SPV is set whenever we come back from Guest world so
while we are in in-kernel run loop with interrupts enabled we can get
external interrupt and HSTATUS.SPV bit can affect SRET of interrupt
handler. To handle this we switch HSTATUS every time.

The world switch code uses SSCRATCH to save vcpu->arch pointer
which is later used on return path. Now, I did not want to restrict Host
Linux from using SSCRATCH for some other purpose hence we
switch SSCRATCH every time.

Regards,
Anup
Paolo Bonzini Aug. 2, 2019, 8:59 a.m. UTC | #3 
On 02/08/19 10:43, Anup Patel wrote:
>> A possible optimization: if these cannot change while Linux runs (I am
>> thinking especially of STVEC and HSTATUS, but perhaps SSCRATCH can be
>> saved on kvm_arch_vcpu_load too) you can avoid the csrr and store.
> Actual exception vector of Host Linux is different so we switch STVEC
> every time.
> 
> HSTATUS.SPV is set whenever we come back from Guest world so
> while we are in in-kernel run loop with interrupts enabled we can get
> external interrupt and HSTATUS.SPV bit can affect SRET of interrupt
> handler. To handle this we switch HSTATUS every time.
> 
> The world switch code uses SSCRATCH to save vcpu->arch pointer
> which is later used on return path. Now, I did not want to restrict Host
> Linux from using SSCRATCH for some other purpose hence we
> switch SSCRATCH every time.

Right, I'm not saying not to save these registers.  I'm saying not to
read the host value on every world switch, instead load it in
hardware_enable (if it's the same for all physical CPUs) or
kvm_arch_vcpu_load (if it's different for every physical CPU).

IIUC Linux does not use SSCRATCH while in the kernel (it must be zero
while handling an exception, but handle_exception takes care of that).
I think it's okay if you make this assumption, but if you don't want to
make it, you can still save it in kvm_arch_vcpu_load rather than here
since you "own" the thread while in KVM_RUN.

Paolo
diff mbox series

Patch

diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h
index a6d81e5eb064..02c52f6082dd 100644
--- a/arch/riscv/include/asm/kvm_host.h
+++ b/arch/riscv/include/asm/kvm_host.h
@@ -110,6 +110,13 @@  struct kvm_vcpu_arch {
 	/* ISA feature bits (similar to MISA) */
 	unsigned long isa;
 
+	/* SSCRATCH and STVEC of Host */
+	unsigned long host_sscratch;
+	unsigned long host_stvec;
+
+	/* CPU context of Host */
+	struct kvm_cpu_context host_context;
+
 	/* CPU context of Guest VCPU */
 	struct kvm_cpu_context guest_context;
 
@@ -148,7 +155,7 @@  int kvm_riscv_vcpu_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run);
 int kvm_riscv_vcpu_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 			unsigned long scause, unsigned long stval);
 
-static inline void __kvm_riscv_switch_to(struct kvm_vcpu_arch *vcpu_arch) {}
+void __kvm_riscv_switch_to(struct kvm_vcpu_arch *vcpu_arch);
 
 int kvm_riscv_vcpu_set_interrupt(struct kvm_vcpu *vcpu, unsigned int irq);
 int kvm_riscv_vcpu_unset_interrupt(struct kvm_vcpu *vcpu, unsigned int irq);
diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c
index 9f5628c38ac9..711656710190 100644
--- a/arch/riscv/kernel/asm-offsets.c
+++ b/arch/riscv/kernel/asm-offsets.c
@@ -7,7 +7,9 @@ 
 #define GENERATING_ASM_OFFSETS
 
 #include <linux/kbuild.h>
+#include <linux/mm.h>
 #include <linux/sched.h>
+#include <asm/kvm_host.h>
 #include <asm/thread_info.h>
 #include <asm/ptrace.h>
 
@@ -109,6 +111,80 @@  void asm_offsets(void)
 	OFFSET(PT_SBADADDR, pt_regs, sbadaddr);
 	OFFSET(PT_SCAUSE, pt_regs, scause);
 
+	OFFSET(KVM_ARCH_GUEST_ZERO, kvm_vcpu_arch, guest_context.zero);
+	OFFSET(KVM_ARCH_GUEST_RA, kvm_vcpu_arch, guest_context.ra);
+	OFFSET(KVM_ARCH_GUEST_SP, kvm_vcpu_arch, guest_context.sp);
+	OFFSET(KVM_ARCH_GUEST_GP, kvm_vcpu_arch, guest_context.gp);
+	OFFSET(KVM_ARCH_GUEST_TP, kvm_vcpu_arch, guest_context.tp);
+	OFFSET(KVM_ARCH_GUEST_T0, kvm_vcpu_arch, guest_context.t0);
+	OFFSET(KVM_ARCH_GUEST_T1, kvm_vcpu_arch, guest_context.t1);
+	OFFSET(KVM_ARCH_GUEST_T2, kvm_vcpu_arch, guest_context.t2);
+	OFFSET(KVM_ARCH_GUEST_S0, kvm_vcpu_arch, guest_context.s0);
+	OFFSET(KVM_ARCH_GUEST_S1, kvm_vcpu_arch, guest_context.s1);
+	OFFSET(KVM_ARCH_GUEST_A0, kvm_vcpu_arch, guest_context.a0);
+	OFFSET(KVM_ARCH_GUEST_A1, kvm_vcpu_arch, guest_context.a1);
+	OFFSET(KVM_ARCH_GUEST_A2, kvm_vcpu_arch, guest_context.a2);
+	OFFSET(KVM_ARCH_GUEST_A3, kvm_vcpu_arch, guest_context.a3);
+	OFFSET(KVM_ARCH_GUEST_A4, kvm_vcpu_arch, guest_context.a4);
+	OFFSET(KVM_ARCH_GUEST_A5, kvm_vcpu_arch, guest_context.a5);
+	OFFSET(KVM_ARCH_GUEST_A6, kvm_vcpu_arch, guest_context.a6);
+	OFFSET(KVM_ARCH_GUEST_A7, kvm_vcpu_arch, guest_context.a7);
+	OFFSET(KVM_ARCH_GUEST_S2, kvm_vcpu_arch, guest_context.s2);
+	OFFSET(KVM_ARCH_GUEST_S3, kvm_vcpu_arch, guest_context.s3);
+	OFFSET(KVM_ARCH_GUEST_S4, kvm_vcpu_arch, guest_context.s4);
+	OFFSET(KVM_ARCH_GUEST_S5, kvm_vcpu_arch, guest_context.s5);
+	OFFSET(KVM_ARCH_GUEST_S6, kvm_vcpu_arch, guest_context.s6);
+	OFFSET(KVM_ARCH_GUEST_S7, kvm_vcpu_arch, guest_context.s7);
+	OFFSET(KVM_ARCH_GUEST_S8, kvm_vcpu_arch, guest_context.s8);
+	OFFSET(KVM_ARCH_GUEST_S9, kvm_vcpu_arch, guest_context.s9);
+	OFFSET(KVM_ARCH_GUEST_S10, kvm_vcpu_arch, guest_context.s10);
+	OFFSET(KVM_ARCH_GUEST_S11, kvm_vcpu_arch, guest_context.s11);
+	OFFSET(KVM_ARCH_GUEST_T3, kvm_vcpu_arch, guest_context.t3);
+	OFFSET(KVM_ARCH_GUEST_T4, kvm_vcpu_arch, guest_context.t4);
+	OFFSET(KVM_ARCH_GUEST_T5, kvm_vcpu_arch, guest_context.t5);
+	OFFSET(KVM_ARCH_GUEST_T6, kvm_vcpu_arch, guest_context.t6);
+	OFFSET(KVM_ARCH_GUEST_SEPC, kvm_vcpu_arch, guest_context.sepc);
+	OFFSET(KVM_ARCH_GUEST_SSTATUS, kvm_vcpu_arch, guest_context.sstatus);
+	OFFSET(KVM_ARCH_GUEST_HSTATUS, kvm_vcpu_arch, guest_context.hstatus);
+
+	OFFSET(KVM_ARCH_HOST_ZERO, kvm_vcpu_arch, host_context.zero);
+	OFFSET(KVM_ARCH_HOST_RA, kvm_vcpu_arch, host_context.ra);
+	OFFSET(KVM_ARCH_HOST_SP, kvm_vcpu_arch, host_context.sp);
+	OFFSET(KVM_ARCH_HOST_GP, kvm_vcpu_arch, host_context.gp);
+	OFFSET(KVM_ARCH_HOST_TP, kvm_vcpu_arch, host_context.tp);
+	OFFSET(KVM_ARCH_HOST_T0, kvm_vcpu_arch, host_context.t0);
+	OFFSET(KVM_ARCH_HOST_T1, kvm_vcpu_arch, host_context.t1);
+	OFFSET(KVM_ARCH_HOST_T2, kvm_vcpu_arch, host_context.t2);
+	OFFSET(KVM_ARCH_HOST_S0, kvm_vcpu_arch, host_context.s0);
+	OFFSET(KVM_ARCH_HOST_S1, kvm_vcpu_arch, host_context.s1);
+	OFFSET(KVM_ARCH_HOST_A0, kvm_vcpu_arch, host_context.a0);
+	OFFSET(KVM_ARCH_HOST_A1, kvm_vcpu_arch, host_context.a1);
+	OFFSET(KVM_ARCH_HOST_A2, kvm_vcpu_arch, host_context.a2);
+	OFFSET(KVM_ARCH_HOST_A3, kvm_vcpu_arch, host_context.a3);
+	OFFSET(KVM_ARCH_HOST_A4, kvm_vcpu_arch, host_context.a4);
+	OFFSET(KVM_ARCH_HOST_A5, kvm_vcpu_arch, host_context.a5);
+	OFFSET(KVM_ARCH_HOST_A6, kvm_vcpu_arch, host_context.a6);
+	OFFSET(KVM_ARCH_HOST_A7, kvm_vcpu_arch, host_context.a7);
+	OFFSET(KVM_ARCH_HOST_S2, kvm_vcpu_arch, host_context.s2);
+	OFFSET(KVM_ARCH_HOST_S3, kvm_vcpu_arch, host_context.s3);
+	OFFSET(KVM_ARCH_HOST_S4, kvm_vcpu_arch, host_context.s4);
+	OFFSET(KVM_ARCH_HOST_S5, kvm_vcpu_arch, host_context.s5);
+	OFFSET(KVM_ARCH_HOST_S6, kvm_vcpu_arch, host_context.s6);
+	OFFSET(KVM_ARCH_HOST_S7, kvm_vcpu_arch, host_context.s7);
+	OFFSET(KVM_ARCH_HOST_S8, kvm_vcpu_arch, host_context.s8);
+	OFFSET(KVM_ARCH_HOST_S9, kvm_vcpu_arch, host_context.s9);
+	OFFSET(KVM_ARCH_HOST_S10, kvm_vcpu_arch, host_context.s10);
+	OFFSET(KVM_ARCH_HOST_S11, kvm_vcpu_arch, host_context.s11);
+	OFFSET(KVM_ARCH_HOST_T3, kvm_vcpu_arch, host_context.t3);
+	OFFSET(KVM_ARCH_HOST_T4, kvm_vcpu_arch, host_context.t4);
+	OFFSET(KVM_ARCH_HOST_T5, kvm_vcpu_arch, host_context.t5);
+	OFFSET(KVM_ARCH_HOST_T6, kvm_vcpu_arch, host_context.t6);
+	OFFSET(KVM_ARCH_HOST_SEPC, kvm_vcpu_arch, host_context.sepc);
+	OFFSET(KVM_ARCH_HOST_SSTATUS, kvm_vcpu_arch, host_context.sstatus);
+	OFFSET(KVM_ARCH_HOST_HSTATUS, kvm_vcpu_arch, host_context.hstatus);
+	OFFSET(KVM_ARCH_HOST_SSCRATCH, kvm_vcpu_arch, host_sscratch);
+	OFFSET(KVM_ARCH_HOST_STVEC, kvm_vcpu_arch, host_stvec);
+
 	/*
 	 * THREAD_{F,X}* might be larger than a S-type offset can handle, but
 	 * these are used in performance-sensitive assembly so we can't resort
diff --git a/arch/riscv/kvm/Makefile b/arch/riscv/kvm/Makefile
index 37b5a59d4f4f..845579273727 100644
--- a/arch/riscv/kvm/Makefile
+++ b/arch/riscv/kvm/Makefile
@@ -8,6 +8,6 @@  ccflags-y := -Ivirt/kvm -Iarch/riscv/kvm
 
 kvm-objs := $(common-objs-y)
 
-kvm-objs += main.o vm.o mmu.o vcpu.o vcpu_exit.o
+kvm-objs += main.o vm.o mmu.o vcpu.o vcpu_exit.o vcpu_switch.o
 
 obj-$(CONFIG_KVM)	+= kvm.o
diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c
index c6877d9e229a..652004aa1c2b 100644
--- a/arch/riscv/kvm/vcpu.c
+++ b/arch/riscv/kvm/vcpu.c
@@ -568,14 +568,40 @@  int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
-	/* TODO: */
+	struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
+
+	csr_write(CSR_VSSTATUS, csr->vsstatus);
+	csr_write(CSR_VSIE, csr->vsie);
+	csr_write(CSR_VSTVEC, csr->vstvec);
+	csr_write(CSR_VSSCRATCH, csr->vsscratch);
+	csr_write(CSR_VSEPC, csr->vsepc);
+	csr_write(CSR_VSCAUSE, csr->vscause);
+	csr_write(CSR_VSTVAL, csr->vstval);
+	csr_write(CSR_VSIP, csr->vsip);
+	csr_write(CSR_VSATP, csr->vsatp);
 
 	kvm_riscv_stage2_update_hgatp(vcpu);
+
+	vcpu->cpu = cpu;
 }
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
-	/* TODO: */
+	struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
+
+	vcpu->cpu = -1;
+
+	csr_write(CSR_HGATP, 0);
+
+	csr->vsstatus = csr_read(CSR_VSSTATUS);
+	csr->vsie = csr_read(CSR_VSIE);
+	csr->vstvec = csr_read(CSR_VSTVEC);
+	csr->vsscratch = csr_read(CSR_VSSCRATCH);
+	csr->vsepc = csr_read(CSR_VSEPC);
+	csr->vscause = csr_read(CSR_VSCAUSE);
+	csr->vstval = csr_read(CSR_VSTVAL);
+	csr->vsip = csr_read(CSR_VSIP);
+	csr->vsatp = csr_read(CSR_VSATP);
 }
 
 static void kvm_riscv_check_vcpu_requests(struct kvm_vcpu *vcpu)
diff --git a/arch/riscv/kvm/vcpu_switch.S b/arch/riscv/kvm/vcpu_switch.S
new file mode 100644
index 000000000000..e1a17df1b379
--- /dev/null
+++ b/arch/riscv/kvm/vcpu_switch.S
@@ -0,0 +1,194 @@ 
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2019 Western Digital Corporation or its affiliates.
+ *
+ * Authors:
+ *     Anup Patel <anup.patel@wdc.com>
+ */
+
+#include <linux/linkage.h>
+#include <asm/asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/csr.h>
+
+	.text
+	.altmacro
+	.option norelax
+
+ENTRY(__kvm_riscv_switch_to)
+	/* Save Host GPRs (except A0 and T0-T6) */
+	REG_S	ra, (KVM_ARCH_HOST_RA)(a0)
+	REG_S	sp, (KVM_ARCH_HOST_SP)(a0)
+	REG_S	gp, (KVM_ARCH_HOST_GP)(a0)
+	REG_S	tp, (KVM_ARCH_HOST_TP)(a0)
+	REG_S	s0, (KVM_ARCH_HOST_S0)(a0)
+	REG_S	s1, (KVM_ARCH_HOST_S1)(a0)
+	REG_S	a1, (KVM_ARCH_HOST_A1)(a0)
+	REG_S	a2, (KVM_ARCH_HOST_A2)(a0)
+	REG_S	a3, (KVM_ARCH_HOST_A3)(a0)
+	REG_S	a4, (KVM_ARCH_HOST_A4)(a0)
+	REG_S	a5, (KVM_ARCH_HOST_A5)(a0)
+	REG_S	a6, (KVM_ARCH_HOST_A6)(a0)
+	REG_S	a7, (KVM_ARCH_HOST_A7)(a0)
+	REG_S	s2, (KVM_ARCH_HOST_S2)(a0)
+	REG_S	s3, (KVM_ARCH_HOST_S3)(a0)
+	REG_S	s4, (KVM_ARCH_HOST_S4)(a0)
+	REG_S	s5, (KVM_ARCH_HOST_S5)(a0)
+	REG_S	s6, (KVM_ARCH_HOST_S6)(a0)
+	REG_S	s7, (KVM_ARCH_HOST_S7)(a0)
+	REG_S	s8, (KVM_ARCH_HOST_S8)(a0)
+	REG_S	s9, (KVM_ARCH_HOST_S9)(a0)
+	REG_S	s10, (KVM_ARCH_HOST_S10)(a0)
+	REG_S	s11, (KVM_ARCH_HOST_S11)(a0)
+
+	/* Save Host SSTATUS, HSTATUS, SCRATCH and STVEC */
+	csrr	t0, CSR_SSTATUS
+	REG_S	t0, (KVM_ARCH_HOST_SSTATUS)(a0)
+	csrr	t1, CSR_HSTATUS
+	REG_S	t1, (KVM_ARCH_HOST_HSTATUS)(a0)
+	csrr	t2, CSR_SSCRATCH
+	REG_S	t2, (KVM_ARCH_HOST_SSCRATCH)(a0)
+	csrr	t3, CSR_STVEC
+	REG_S	t3, (KVM_ARCH_HOST_STVEC)(a0)
+
+	/* Change Host exception vector to return path */
+	la	t4, __kvm_switch_return
+	csrw	CSR_STVEC, t4
+
+	/* Restore Guest HSTATUS, SSTATUS and SEPC */
+	REG_L	t4, (KVM_ARCH_GUEST_SEPC)(a0)
+	csrw	CSR_SEPC, t4
+	REG_L	t5, (KVM_ARCH_GUEST_SSTATUS)(a0)
+	csrw	CSR_SSTATUS, t5
+	REG_L	t6, (KVM_ARCH_GUEST_HSTATUS)(a0)
+	csrw	CSR_HSTATUS, t6
+
+	/* Restore Guest GPRs (except A0) */
+	REG_L	ra, (KVM_ARCH_GUEST_RA)(a0)
+	REG_L	sp, (KVM_ARCH_GUEST_SP)(a0)
+	REG_L	gp, (KVM_ARCH_GUEST_GP)(a0)
+	REG_L	tp, (KVM_ARCH_GUEST_TP)(a0)
+	REG_L	t0, (KVM_ARCH_GUEST_T0)(a0)
+	REG_L	t1, (KVM_ARCH_GUEST_T1)(a0)
+	REG_L	t2, (KVM_ARCH_GUEST_T2)(a0)
+	REG_L	s0, (KVM_ARCH_GUEST_S0)(a0)
+	REG_L	s1, (KVM_ARCH_GUEST_S1)(a0)
+	REG_L	a1, (KVM_ARCH_GUEST_A1)(a0)
+	REG_L	a2, (KVM_ARCH_GUEST_A2)(a0)
+	REG_L	a3, (KVM_ARCH_GUEST_A3)(a0)
+	REG_L	a4, (KVM_ARCH_GUEST_A4)(a0)
+	REG_L	a5, (KVM_ARCH_GUEST_A5)(a0)
+	REG_L	a6, (KVM_ARCH_GUEST_A6)(a0)
+	REG_L	a7, (KVM_ARCH_GUEST_A7)(a0)
+	REG_L	s2, (KVM_ARCH_GUEST_S2)(a0)
+	REG_L	s3, (KVM_ARCH_GUEST_S3)(a0)
+	REG_L	s4, (KVM_ARCH_GUEST_S4)(a0)
+	REG_L	s5, (KVM_ARCH_GUEST_S5)(a0)
+	REG_L	s6, (KVM_ARCH_GUEST_S6)(a0)
+	REG_L	s7, (KVM_ARCH_GUEST_S7)(a0)
+	REG_L	s8, (KVM_ARCH_GUEST_S8)(a0)
+	REG_L	s9, (KVM_ARCH_GUEST_S9)(a0)
+	REG_L	s10, (KVM_ARCH_GUEST_S10)(a0)
+	REG_L	s11, (KVM_ARCH_GUEST_S11)(a0)
+	REG_L	t3, (KVM_ARCH_GUEST_T3)(a0)
+	REG_L	t4, (KVM_ARCH_GUEST_T4)(a0)
+	REG_L	t5, (KVM_ARCH_GUEST_T5)(a0)
+	REG_L	t6, (KVM_ARCH_GUEST_T6)(a0)
+
+	/* Save Host A0 in SSCRATCH */
+	csrw	CSR_SSCRATCH, a0
+
+	/* Restore Guest A0 */
+	REG_L	a0, (KVM_ARCH_GUEST_A0)(a0)
+
+	/* Resume Guest */
+	sret
+
+	/* Back to Host */
+	.align 2
+__kvm_switch_return:
+	/* Swap Guest A0 with SSCRATCH */
+	csrrw	a0, CSR_SSCRATCH, a0
+
+	/* Save Guest GPRs (except A0) */
+	REG_S	ra, (KVM_ARCH_GUEST_RA)(a0)
+	REG_S	sp, (KVM_ARCH_GUEST_SP)(a0)
+	REG_S	gp, (KVM_ARCH_GUEST_GP)(a0)
+	REG_S	tp, (KVM_ARCH_GUEST_TP)(a0)
+	REG_S	t0, (KVM_ARCH_GUEST_T0)(a0)
+	REG_S	t1, (KVM_ARCH_GUEST_T1)(a0)
+	REG_S	t2, (KVM_ARCH_GUEST_T2)(a0)
+	REG_S	s0, (KVM_ARCH_GUEST_S0)(a0)
+	REG_S	s1, (KVM_ARCH_GUEST_S1)(a0)
+	REG_S	a1, (KVM_ARCH_GUEST_A1)(a0)
+	REG_S	a2, (KVM_ARCH_GUEST_A2)(a0)
+	REG_S	a3, (KVM_ARCH_GUEST_A3)(a0)
+	REG_S	a4, (KVM_ARCH_GUEST_A4)(a0)
+	REG_S	a5, (KVM_ARCH_GUEST_A5)(a0)
+	REG_S	a6, (KVM_ARCH_GUEST_A6)(a0)
+	REG_S	a7, (KVM_ARCH_GUEST_A7)(a0)
+	REG_S	s2, (KVM_ARCH_GUEST_S2)(a0)
+	REG_S	s3, (KVM_ARCH_GUEST_S3)(a0)
+	REG_S	s4, (KVM_ARCH_GUEST_S4)(a0)
+	REG_S	s5, (KVM_ARCH_GUEST_S5)(a0)
+	REG_S	s6, (KVM_ARCH_GUEST_S6)(a0)
+	REG_S	s7, (KVM_ARCH_GUEST_S7)(a0)
+	REG_S	s8, (KVM_ARCH_GUEST_S8)(a0)
+	REG_S	s9, (KVM_ARCH_GUEST_S9)(a0)
+	REG_S	s10, (KVM_ARCH_GUEST_S10)(a0)
+	REG_S	s11, (KVM_ARCH_GUEST_S11)(a0)
+	REG_S	t3, (KVM_ARCH_GUEST_T3)(a0)
+	REG_S	t4, (KVM_ARCH_GUEST_T4)(a0)
+	REG_S	t5, (KVM_ARCH_GUEST_T5)(a0)
+	REG_S	t6, (KVM_ARCH_GUEST_T6)(a0)
+
+	/* Save Guest A0 */
+	csrr	t0, CSR_SSCRATCH
+	REG_S	t0, (KVM_ARCH_GUEST_A0)(a0)
+
+	/* Save Guest HSTATUS, SSTATUS, and SEPC */
+	csrr	t0, CSR_SEPC
+	REG_S	t0, (KVM_ARCH_GUEST_SEPC)(a0)
+	csrr	t1, CSR_SSTATUS
+	REG_S	t1, (KVM_ARCH_GUEST_SSTATUS)(a0)
+	csrr	t2, CSR_HSTATUS
+	REG_S	t2, (KVM_ARCH_GUEST_HSTATUS)(a0)
+
+	/* Restore Host SSTATUS, HSTATUS, SCRATCH and STVEC */
+	REG_L	t3, (KVM_ARCH_HOST_SSTATUS)(a0)
+	csrw	CSR_SSTATUS, t3
+	REG_L	t4, (KVM_ARCH_HOST_HSTATUS)(a0)
+	csrw	CSR_HSTATUS, t4
+	REG_L	t5, (KVM_ARCH_HOST_SSCRATCH)(a0)
+	csrw	CSR_SSCRATCH, t5
+	REG_L	t6, (KVM_ARCH_HOST_STVEC)(a0)
+	csrw	CSR_STVEC, t6
+
+	/* Restore Host GPRs (except A0 and T0-T6) */
+	REG_L	ra, (KVM_ARCH_HOST_RA)(a0)
+	REG_L	sp, (KVM_ARCH_HOST_SP)(a0)
+	REG_L	gp, (KVM_ARCH_HOST_GP)(a0)
+	REG_L	tp, (KVM_ARCH_HOST_TP)(a0)
+	REG_L	s0, (KVM_ARCH_HOST_S0)(a0)
+	REG_L	s1, (KVM_ARCH_HOST_S1)(a0)
+	REG_L	a1, (KVM_ARCH_HOST_A1)(a0)
+	REG_L	a2, (KVM_ARCH_HOST_A2)(a0)
+	REG_L	a3, (KVM_ARCH_HOST_A3)(a0)
+	REG_L	a4, (KVM_ARCH_HOST_A4)(a0)
+	REG_L	a5, (KVM_ARCH_HOST_A5)(a0)
+	REG_L	a6, (KVM_ARCH_HOST_A6)(a0)
+	REG_L	a7, (KVM_ARCH_HOST_A7)(a0)
+	REG_L	s2, (KVM_ARCH_HOST_S2)(a0)
+	REG_L	s3, (KVM_ARCH_HOST_S3)(a0)
+	REG_L	s4, (KVM_ARCH_HOST_S4)(a0)
+	REG_L	s5, (KVM_ARCH_HOST_S5)(a0)
+	REG_L	s6, (KVM_ARCH_HOST_S6)(a0)
+	REG_L	s7, (KVM_ARCH_HOST_S7)(a0)
+	REG_L	s8, (KVM_ARCH_HOST_S8)(a0)
+	REG_L	s9, (KVM_ARCH_HOST_S9)(a0)
+	REG_L	s10, (KVM_ARCH_HOST_S10)(a0)
+	REG_L	s11, (KVM_ARCH_HOST_S11)(a0)
+
+	/* Return to C code */
+	ret
+ENDPROC(__kvm_riscv_switch_to)