linux/arch/riscv/kvm/vcpu_switch.S
Vincent Chen 823f53a30e RISC-V: KVM: Refine __kvm_riscv_switch_to() implementation
Kernel uses __kvm_riscv_switch_to() and __kvm_switch_return() to switch
the context of host kernel and guest kernel. Several CSRs belonging to the
context will be read and written during the context switch. To ensure
atomic read-modify-write control of CSR and ordering of CSR accesses, some
hardware blocks flush the pipeline when writing a CSR. In this
circumstance, grouping CSR executions together as much as possible can
reduce the performance impact of the pipeline. Therefore, this commit
reorders the CSR instructions to enhance the context switch performance..

Signed-off-by: Vincent Chen <vincent.chen@sifive.com>
Suggested-by: Hsinyi Lee <hsinyi.lee@sifive.com>
Suggested-by: Fu-Ching Yang <fu-ching.yang@sifive.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
2022-03-11 19:02:22 +05:30

409 lines
11 KiB
ArmAsm

/* 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)
/* Load Guest CSR values */
REG_L t0, (KVM_ARCH_GUEST_SSTATUS)(a0)
REG_L t1, (KVM_ARCH_GUEST_HSTATUS)(a0)
REG_L t2, (KVM_ARCH_GUEST_SCOUNTEREN)(a0)
la t4, __kvm_switch_return
REG_L t5, (KVM_ARCH_GUEST_SEPC)(a0)
/* Save Host and Restore Guest SSTATUS */
csrrw t0, CSR_SSTATUS, t0
/* Save Host and Restore Guest HSTATUS */
csrrw t1, CSR_HSTATUS, t1
/* Save Host and Restore Guest SCOUNTEREN */
csrrw t2, CSR_SCOUNTEREN, t2
/* Save Host STVEC and change it to return path */
csrrw t4, CSR_STVEC, t4
/* Save Host SSCRATCH and change it to struct kvm_vcpu_arch pointer */
csrrw t3, CSR_SSCRATCH, a0
/* Restore Guest SEPC */
csrw CSR_SEPC, t5
/* Store Host CSR values */
REG_S t0, (KVM_ARCH_HOST_SSTATUS)(a0)
REG_S t1, (KVM_ARCH_HOST_HSTATUS)(a0)
REG_S t2, (KVM_ARCH_HOST_SCOUNTEREN)(a0)
REG_S t3, (KVM_ARCH_HOST_SSCRATCH)(a0)
REG_S t4, (KVM_ARCH_HOST_STVEC)(a0)
/* 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)
/* 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)
/* Load Host CSR values */
REG_L t1, (KVM_ARCH_HOST_STVEC)(a0)
REG_L t2, (KVM_ARCH_HOST_SSCRATCH)(a0)
REG_L t3, (KVM_ARCH_HOST_SCOUNTEREN)(a0)
REG_L t4, (KVM_ARCH_HOST_HSTATUS)(a0)
REG_L t5, (KVM_ARCH_HOST_SSTATUS)(a0)
/* Save Guest SEPC */
csrr t0, CSR_SEPC
/* Save Guest A0 and Restore Host SSCRATCH */
csrrw t2, CSR_SSCRATCH, t2
/* Restore Host STVEC */
csrw CSR_STVEC, t1
/* Save Guest and Restore Host SCOUNTEREN */
csrrw t3, CSR_SCOUNTEREN, t3
/* Save Guest and Restore Host HSTATUS */
csrrw t4, CSR_HSTATUS, t4
/* Save Guest and Restore Host SSTATUS */
csrrw t5, CSR_SSTATUS, t5
/* Store Guest CSR values */
REG_S t0, (KVM_ARCH_GUEST_SEPC)(a0)
REG_S t2, (KVM_ARCH_GUEST_A0)(a0)
REG_S t3, (KVM_ARCH_GUEST_SCOUNTEREN)(a0)
REG_S t4, (KVM_ARCH_GUEST_HSTATUS)(a0)
REG_S t5, (KVM_ARCH_GUEST_SSTATUS)(a0)
/* 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)
ENTRY(__kvm_riscv_unpriv_trap)
/*
* We assume that faulting unpriv load/store instruction is
* 4-byte long and blindly increment SEPC by 4.
*
* The trap details will be saved at address pointed by 'A0'
* register and we use 'A1' register as temporary.
*/
csrr a1, CSR_SEPC
REG_S a1, (KVM_ARCH_TRAP_SEPC)(a0)
addi a1, a1, 4
csrw CSR_SEPC, a1
csrr a1, CSR_SCAUSE
REG_S a1, (KVM_ARCH_TRAP_SCAUSE)(a0)
csrr a1, CSR_STVAL
REG_S a1, (KVM_ARCH_TRAP_STVAL)(a0)
csrr a1, CSR_HTVAL
REG_S a1, (KVM_ARCH_TRAP_HTVAL)(a0)
csrr a1, CSR_HTINST
REG_S a1, (KVM_ARCH_TRAP_HTINST)(a0)
sret
ENDPROC(__kvm_riscv_unpriv_trap)
#ifdef CONFIG_FPU
.align 3
.global __kvm_riscv_fp_f_save
__kvm_riscv_fp_f_save:
csrr t2, CSR_SSTATUS
li t1, SR_FS
csrs CSR_SSTATUS, t1
frcsr t0
fsw f0, KVM_ARCH_FP_F_F0(a0)
fsw f1, KVM_ARCH_FP_F_F1(a0)
fsw f2, KVM_ARCH_FP_F_F2(a0)
fsw f3, KVM_ARCH_FP_F_F3(a0)
fsw f4, KVM_ARCH_FP_F_F4(a0)
fsw f5, KVM_ARCH_FP_F_F5(a0)
fsw f6, KVM_ARCH_FP_F_F6(a0)
fsw f7, KVM_ARCH_FP_F_F7(a0)
fsw f8, KVM_ARCH_FP_F_F8(a0)
fsw f9, KVM_ARCH_FP_F_F9(a0)
fsw f10, KVM_ARCH_FP_F_F10(a0)
fsw f11, KVM_ARCH_FP_F_F11(a0)
fsw f12, KVM_ARCH_FP_F_F12(a0)
fsw f13, KVM_ARCH_FP_F_F13(a0)
fsw f14, KVM_ARCH_FP_F_F14(a0)
fsw f15, KVM_ARCH_FP_F_F15(a0)
fsw f16, KVM_ARCH_FP_F_F16(a0)
fsw f17, KVM_ARCH_FP_F_F17(a0)
fsw f18, KVM_ARCH_FP_F_F18(a0)
fsw f19, KVM_ARCH_FP_F_F19(a0)
fsw f20, KVM_ARCH_FP_F_F20(a0)
fsw f21, KVM_ARCH_FP_F_F21(a0)
fsw f22, KVM_ARCH_FP_F_F22(a0)
fsw f23, KVM_ARCH_FP_F_F23(a0)
fsw f24, KVM_ARCH_FP_F_F24(a0)
fsw f25, KVM_ARCH_FP_F_F25(a0)
fsw f26, KVM_ARCH_FP_F_F26(a0)
fsw f27, KVM_ARCH_FP_F_F27(a0)
fsw f28, KVM_ARCH_FP_F_F28(a0)
fsw f29, KVM_ARCH_FP_F_F29(a0)
fsw f30, KVM_ARCH_FP_F_F30(a0)
fsw f31, KVM_ARCH_FP_F_F31(a0)
sw t0, KVM_ARCH_FP_F_FCSR(a0)
csrw CSR_SSTATUS, t2
ret
.align 3
.global __kvm_riscv_fp_d_save
__kvm_riscv_fp_d_save:
csrr t2, CSR_SSTATUS
li t1, SR_FS
csrs CSR_SSTATUS, t1
frcsr t0
fsd f0, KVM_ARCH_FP_D_F0(a0)
fsd f1, KVM_ARCH_FP_D_F1(a0)
fsd f2, KVM_ARCH_FP_D_F2(a0)
fsd f3, KVM_ARCH_FP_D_F3(a0)
fsd f4, KVM_ARCH_FP_D_F4(a0)
fsd f5, KVM_ARCH_FP_D_F5(a0)
fsd f6, KVM_ARCH_FP_D_F6(a0)
fsd f7, KVM_ARCH_FP_D_F7(a0)
fsd f8, KVM_ARCH_FP_D_F8(a0)
fsd f9, KVM_ARCH_FP_D_F9(a0)
fsd f10, KVM_ARCH_FP_D_F10(a0)
fsd f11, KVM_ARCH_FP_D_F11(a0)
fsd f12, KVM_ARCH_FP_D_F12(a0)
fsd f13, KVM_ARCH_FP_D_F13(a0)
fsd f14, KVM_ARCH_FP_D_F14(a0)
fsd f15, KVM_ARCH_FP_D_F15(a0)
fsd f16, KVM_ARCH_FP_D_F16(a0)
fsd f17, KVM_ARCH_FP_D_F17(a0)
fsd f18, KVM_ARCH_FP_D_F18(a0)
fsd f19, KVM_ARCH_FP_D_F19(a0)
fsd f20, KVM_ARCH_FP_D_F20(a0)
fsd f21, KVM_ARCH_FP_D_F21(a0)
fsd f22, KVM_ARCH_FP_D_F22(a0)
fsd f23, KVM_ARCH_FP_D_F23(a0)
fsd f24, KVM_ARCH_FP_D_F24(a0)
fsd f25, KVM_ARCH_FP_D_F25(a0)
fsd f26, KVM_ARCH_FP_D_F26(a0)
fsd f27, KVM_ARCH_FP_D_F27(a0)
fsd f28, KVM_ARCH_FP_D_F28(a0)
fsd f29, KVM_ARCH_FP_D_F29(a0)
fsd f30, KVM_ARCH_FP_D_F30(a0)
fsd f31, KVM_ARCH_FP_D_F31(a0)
sw t0, KVM_ARCH_FP_D_FCSR(a0)
csrw CSR_SSTATUS, t2
ret
.align 3
.global __kvm_riscv_fp_f_restore
__kvm_riscv_fp_f_restore:
csrr t2, CSR_SSTATUS
li t1, SR_FS
lw t0, KVM_ARCH_FP_F_FCSR(a0)
csrs CSR_SSTATUS, t1
flw f0, KVM_ARCH_FP_F_F0(a0)
flw f1, KVM_ARCH_FP_F_F1(a0)
flw f2, KVM_ARCH_FP_F_F2(a0)
flw f3, KVM_ARCH_FP_F_F3(a0)
flw f4, KVM_ARCH_FP_F_F4(a0)
flw f5, KVM_ARCH_FP_F_F5(a0)
flw f6, KVM_ARCH_FP_F_F6(a0)
flw f7, KVM_ARCH_FP_F_F7(a0)
flw f8, KVM_ARCH_FP_F_F8(a0)
flw f9, KVM_ARCH_FP_F_F9(a0)
flw f10, KVM_ARCH_FP_F_F10(a0)
flw f11, KVM_ARCH_FP_F_F11(a0)
flw f12, KVM_ARCH_FP_F_F12(a0)
flw f13, KVM_ARCH_FP_F_F13(a0)
flw f14, KVM_ARCH_FP_F_F14(a0)
flw f15, KVM_ARCH_FP_F_F15(a0)
flw f16, KVM_ARCH_FP_F_F16(a0)
flw f17, KVM_ARCH_FP_F_F17(a0)
flw f18, KVM_ARCH_FP_F_F18(a0)
flw f19, KVM_ARCH_FP_F_F19(a0)
flw f20, KVM_ARCH_FP_F_F20(a0)
flw f21, KVM_ARCH_FP_F_F21(a0)
flw f22, KVM_ARCH_FP_F_F22(a0)
flw f23, KVM_ARCH_FP_F_F23(a0)
flw f24, KVM_ARCH_FP_F_F24(a0)
flw f25, KVM_ARCH_FP_F_F25(a0)
flw f26, KVM_ARCH_FP_F_F26(a0)
flw f27, KVM_ARCH_FP_F_F27(a0)
flw f28, KVM_ARCH_FP_F_F28(a0)
flw f29, KVM_ARCH_FP_F_F29(a0)
flw f30, KVM_ARCH_FP_F_F30(a0)
flw f31, KVM_ARCH_FP_F_F31(a0)
fscsr t0
csrw CSR_SSTATUS, t2
ret
.align 3
.global __kvm_riscv_fp_d_restore
__kvm_riscv_fp_d_restore:
csrr t2, CSR_SSTATUS
li t1, SR_FS
lw t0, KVM_ARCH_FP_D_FCSR(a0)
csrs CSR_SSTATUS, t1
fld f0, KVM_ARCH_FP_D_F0(a0)
fld f1, KVM_ARCH_FP_D_F1(a0)
fld f2, KVM_ARCH_FP_D_F2(a0)
fld f3, KVM_ARCH_FP_D_F3(a0)
fld f4, KVM_ARCH_FP_D_F4(a0)
fld f5, KVM_ARCH_FP_D_F5(a0)
fld f6, KVM_ARCH_FP_D_F6(a0)
fld f7, KVM_ARCH_FP_D_F7(a0)
fld f8, KVM_ARCH_FP_D_F8(a0)
fld f9, KVM_ARCH_FP_D_F9(a0)
fld f10, KVM_ARCH_FP_D_F10(a0)
fld f11, KVM_ARCH_FP_D_F11(a0)
fld f12, KVM_ARCH_FP_D_F12(a0)
fld f13, KVM_ARCH_FP_D_F13(a0)
fld f14, KVM_ARCH_FP_D_F14(a0)
fld f15, KVM_ARCH_FP_D_F15(a0)
fld f16, KVM_ARCH_FP_D_F16(a0)
fld f17, KVM_ARCH_FP_D_F17(a0)
fld f18, KVM_ARCH_FP_D_F18(a0)
fld f19, KVM_ARCH_FP_D_F19(a0)
fld f20, KVM_ARCH_FP_D_F20(a0)
fld f21, KVM_ARCH_FP_D_F21(a0)
fld f22, KVM_ARCH_FP_D_F22(a0)
fld f23, KVM_ARCH_FP_D_F23(a0)
fld f24, KVM_ARCH_FP_D_F24(a0)
fld f25, KVM_ARCH_FP_D_F25(a0)
fld f26, KVM_ARCH_FP_D_F26(a0)
fld f27, KVM_ARCH_FP_D_F27(a0)
fld f28, KVM_ARCH_FP_D_F28(a0)
fld f29, KVM_ARCH_FP_D_F29(a0)
fld f30, KVM_ARCH_FP_D_F30(a0)
fld f31, KVM_ARCH_FP_D_F31(a0)
fscsr t0
csrw CSR_SSTATUS, t2
ret
#endif