diff options
Diffstat (limited to 'arch/arm64/kvm/hyp.S')
-rw-r--r-- | arch/arm64/kvm/hyp.S | 1277 |
1 files changed, 16 insertions, 1261 deletions
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S index 64f9e60b31da..8d231f19453e 100644 --- a/arch/arm64/kvm/hyp.S +++ b/arch/arm64/kvm/hyp.S @@ -17,1106 +17,9 @@ #include <linux/linkage.h> -#include <asm/asm-offsets.h> +#include <asm/alternative.h> #include <asm/assembler.h> -#include <asm/debug-monitors.h> -#include <asm/esr.h> -#include <asm/fpsimdmacros.h> -#include <asm/kvm.h> -#include <asm/kvm_arm.h> -#include <asm/kvm_asm.h> -#include <asm/kvm_mmu.h> -#include <asm/memory.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_SPSR_OFFSET(x) CPU_GP_REG_OFFSET(CPU_SPSR + 8*x) -#define CPU_SYSREG_OFFSET(x) (CPU_SYSREGS + 8*x) - - .text - .pushsection .hyp.text, "ax" - .align PAGE_SHIFT - -.macro save_common_regs - // x2: base address for cpu context - // x3: tmp register - - add x3, x2, #CPU_XREG_OFFSET(19) - stp x19, x20, [x3] - stp x21, x22, [x3, #16] - stp x23, x24, [x3, #32] - stp x25, x26, [x3, #48] - stp x27, x28, [x3, #64] - stp x29, lr, [x3, #80] - - mrs x19, sp_el0 - mrs x20, elr_el2 // EL1 PC - mrs x21, spsr_el2 // EL1 pstate - - stp x19, x20, [x3, #96] - str x21, [x3, #112] - - mrs x22, sp_el1 - mrs x23, elr_el1 - mrs x24, spsr_el1 - - str x22, [x2, #CPU_GP_REG_OFFSET(CPU_SP_EL1)] - str x23, [x2, #CPU_GP_REG_OFFSET(CPU_ELR_EL1)] - str x24, [x2, #CPU_SPSR_OFFSET(KVM_SPSR_EL1)] -.endm - -.macro restore_common_regs - // x2: base address for cpu context - // x3: tmp register - - ldr x22, [x2, #CPU_GP_REG_OFFSET(CPU_SP_EL1)] - ldr x23, [x2, #CPU_GP_REG_OFFSET(CPU_ELR_EL1)] - ldr x24, [x2, #CPU_SPSR_OFFSET(KVM_SPSR_EL1)] - - msr sp_el1, x22 - msr elr_el1, x23 - msr spsr_el1, x24 - - add x3, x2, #CPU_XREG_OFFSET(31) // SP_EL0 - ldp x19, x20, [x3] - ldr x21, [x3, #16] - - msr sp_el0, x19 - msr elr_el2, x20 // EL1 PC - msr spsr_el2, x21 // EL1 pstate - - add x3, x2, #CPU_XREG_OFFSET(19) - ldp x19, x20, [x3] - ldp x21, x22, [x3, #16] - ldp x23, x24, [x3, #32] - ldp x25, x26, [x3, #48] - ldp x27, x28, [x3, #64] - ldp x29, lr, [x3, #80] -.endm - -.macro save_host_regs - save_common_regs -.endm - -.macro restore_host_regs - restore_common_regs -.endm - -.macro save_fpsimd - // x2: cpu context address - // x3, x4: tmp regs - add x3, x2, #CPU_GP_REG_OFFSET(CPU_FP_REGS) - fpsimd_save x3, 4 -.endm - -.macro restore_fpsimd - // x2: cpu context address - // x3, x4: tmp regs - add x3, x2, #CPU_GP_REG_OFFSET(CPU_FP_REGS) - fpsimd_restore x3, 4 -.endm - -.macro save_guest_regs - // x0 is the vcpu address - // x1 is the return code, do not corrupt! - // x2 is the cpu context - // x3 is a tmp register - // Guest's x0-x3 are on the stack - - // Compute base to save registers - add x3, x2, #CPU_XREG_OFFSET(4) - stp x4, x5, [x3] - stp x6, x7, [x3, #16] - stp x8, x9, [x3, #32] - stp x10, x11, [x3, #48] - stp x12, x13, [x3, #64] - stp x14, x15, [x3, #80] - stp x16, x17, [x3, #96] - str x18, [x3, #112] - - pop x6, x7 // x2, x3 - pop x4, x5 // x0, x1 - - add x3, x2, #CPU_XREG_OFFSET(0) - stp x4, x5, [x3] - stp x6, x7, [x3, #16] - - save_common_regs -.endm - -.macro restore_guest_regs - // x0 is the vcpu address. - // x2 is the cpu context - // x3 is a tmp register - - // Prepare x0-x3 for later restore - add x3, x2, #CPU_XREG_OFFSET(0) - ldp x4, x5, [x3] - ldp x6, x7, [x3, #16] - push x4, x5 // Push x0-x3 on the stack - push x6, x7 - - // x4-x18 - ldp x4, x5, [x3, #32] - ldp x6, x7, [x3, #48] - ldp x8, x9, [x3, #64] - ldp x10, x11, [x3, #80] - ldp x12, x13, [x3, #96] - ldp x14, x15, [x3, #112] - ldp x16, x17, [x3, #128] - ldr x18, [x3, #144] - - // x19-x29, lr, sp*, elr*, spsr* - restore_common_regs - - // Last bits of the 64bit state - pop x2, x3 - pop x0, x1 - - // Do not touch any register after this! -.endm - -/* - * Macros to perform system register save/restore. - * - * Ordering here is absolutely critical, and must be kept consistent - * in {save,restore}_sysregs, {save,restore}_guest_32bit_state, - * and in kvm_asm.h. - * - * In other words, don't touch any of these unless you know what - * you are doing. - */ -.macro save_sysregs - // x2: base address for cpu context - // x3: tmp register - - add x3, x2, #CPU_SYSREG_OFFSET(MPIDR_EL1) - - mrs x4, vmpidr_el2 - mrs x5, csselr_el1 - mrs x6, sctlr_el1 - mrs x7, actlr_el1 - mrs x8, cpacr_el1 - mrs x9, ttbr0_el1 - mrs x10, ttbr1_el1 - mrs x11, tcr_el1 - mrs x12, esr_el1 - mrs x13, afsr0_el1 - mrs x14, afsr1_el1 - mrs x15, far_el1 - mrs x16, mair_el1 - mrs x17, vbar_el1 - mrs x18, contextidr_el1 - mrs x19, tpidr_el0 - mrs x20, tpidrro_el0 - mrs x21, tpidr_el1 - mrs x22, amair_el1 - mrs x23, cntkctl_el1 - mrs x24, par_el1 - mrs x25, mdscr_el1 - - stp x4, x5, [x3] - stp x6, x7, [x3, #16] - stp x8, x9, [x3, #32] - stp x10, x11, [x3, #48] - stp x12, x13, [x3, #64] - stp x14, x15, [x3, #80] - stp x16, x17, [x3, #96] - stp x18, x19, [x3, #112] - stp x20, x21, [x3, #128] - stp x22, x23, [x3, #144] - stp x24, x25, [x3, #160] -.endm - -.macro save_debug - // x2: base address for cpu context - // x3: tmp register - - mrs x26, id_aa64dfr0_el1 - ubfx x24, x26, #12, #4 // Extract BRPs - ubfx x25, x26, #20, #4 // Extract WRPs - mov w26, #15 - sub w24, w26, w24 // How many BPs to skip - sub w25, w26, w25 // How many WPs to skip - - add x3, x2, #CPU_SYSREG_OFFSET(DBGBCR0_EL1) - - adr x26, 1f - add x26, x26, x24, lsl #2 - br x26 -1: - mrs x20, dbgbcr15_el1 - mrs x19, dbgbcr14_el1 - mrs x18, dbgbcr13_el1 - mrs x17, dbgbcr12_el1 - mrs x16, dbgbcr11_el1 - mrs x15, dbgbcr10_el1 - mrs x14, dbgbcr9_el1 - mrs x13, dbgbcr8_el1 - mrs x12, dbgbcr7_el1 - mrs x11, dbgbcr6_el1 - mrs x10, dbgbcr5_el1 - mrs x9, dbgbcr4_el1 - mrs x8, dbgbcr3_el1 - mrs x7, dbgbcr2_el1 - mrs x6, dbgbcr1_el1 - mrs x5, dbgbcr0_el1 - - adr x26, 1f - add x26, x26, x24, lsl #2 - br x26 - -1: - str x20, [x3, #(15 * 8)] - str x19, [x3, #(14 * 8)] - str x18, [x3, #(13 * 8)] - str x17, [x3, #(12 * 8)] - str x16, [x3, #(11 * 8)] - str x15, [x3, #(10 * 8)] - str x14, [x3, #(9 * 8)] - str x13, [x3, #(8 * 8)] - str x12, [x3, #(7 * 8)] - str x11, [x3, #(6 * 8)] - str x10, [x3, #(5 * 8)] - str x9, [x3, #(4 * 8)] - str x8, [x3, #(3 * 8)] - str x7, [x3, #(2 * 8)] - str x6, [x3, #(1 * 8)] - str x5, [x3, #(0 * 8)] - - add x3, x2, #CPU_SYSREG_OFFSET(DBGBVR0_EL1) - - adr x26, 1f - add x26, x26, x24, lsl #2 - br x26 -1: - mrs x20, dbgbvr15_el1 - mrs x19, dbgbvr14_el1 - mrs x18, dbgbvr13_el1 - mrs x17, dbgbvr12_el1 - mrs x16, dbgbvr11_el1 - mrs x15, dbgbvr10_el1 - mrs x14, dbgbvr9_el1 - mrs x13, dbgbvr8_el1 - mrs x12, dbgbvr7_el1 - mrs x11, dbgbvr6_el1 - mrs x10, dbgbvr5_el1 - mrs x9, dbgbvr4_el1 - mrs x8, dbgbvr3_el1 - mrs x7, dbgbvr2_el1 - mrs x6, dbgbvr1_el1 - mrs x5, dbgbvr0_el1 - - adr x26, 1f - add x26, x26, x24, lsl #2 - br x26 - -1: - str x20, [x3, #(15 * 8)] - str x19, [x3, #(14 * 8)] - str x18, [x3, #(13 * 8)] - str x17, [x3, #(12 * 8)] - str x16, [x3, #(11 * 8)] - str x15, [x3, #(10 * 8)] - str x14, [x3, #(9 * 8)] - str x13, [x3, #(8 * 8)] - str x12, [x3, #(7 * 8)] - str x11, [x3, #(6 * 8)] - str x10, [x3, #(5 * 8)] - str x9, [x3, #(4 * 8)] - str x8, [x3, #(3 * 8)] - str x7, [x3, #(2 * 8)] - str x6, [x3, #(1 * 8)] - str x5, [x3, #(0 * 8)] - - add x3, x2, #CPU_SYSREG_OFFSET(DBGWCR0_EL1) - - adr x26, 1f - add x26, x26, x25, lsl #2 - br x26 -1: - mrs x20, dbgwcr15_el1 - mrs x19, dbgwcr14_el1 - mrs x18, dbgwcr13_el1 - mrs x17, dbgwcr12_el1 - mrs x16, dbgwcr11_el1 - mrs x15, dbgwcr10_el1 - mrs x14, dbgwcr9_el1 - mrs x13, dbgwcr8_el1 - mrs x12, dbgwcr7_el1 - mrs x11, dbgwcr6_el1 - mrs x10, dbgwcr5_el1 - mrs x9, dbgwcr4_el1 - mrs x8, dbgwcr3_el1 - mrs x7, dbgwcr2_el1 - mrs x6, dbgwcr1_el1 - mrs x5, dbgwcr0_el1 - - adr x26, 1f - add x26, x26, x25, lsl #2 - br x26 - -1: - str x20, [x3, #(15 * 8)] - str x19, [x3, #(14 * 8)] - str x18, [x3, #(13 * 8)] - str x17, [x3, #(12 * 8)] - str x16, [x3, #(11 * 8)] - str x15, [x3, #(10 * 8)] - str x14, [x3, #(9 * 8)] - str x13, [x3, #(8 * 8)] - str x12, [x3, #(7 * 8)] - str x11, [x3, #(6 * 8)] - str x10, [x3, #(5 * 8)] - str x9, [x3, #(4 * 8)] - str x8, [x3, #(3 * 8)] - str x7, [x3, #(2 * 8)] - str x6, [x3, #(1 * 8)] - str x5, [x3, #(0 * 8)] - - add x3, x2, #CPU_SYSREG_OFFSET(DBGWVR0_EL1) - - adr x26, 1f - add x26, x26, x25, lsl #2 - br x26 -1: - mrs x20, dbgwvr15_el1 - mrs x19, dbgwvr14_el1 - mrs x18, dbgwvr13_el1 - mrs x17, dbgwvr12_el1 - mrs x16, dbgwvr11_el1 - mrs x15, dbgwvr10_el1 - mrs x14, dbgwvr9_el1 - mrs x13, dbgwvr8_el1 - mrs x12, dbgwvr7_el1 - mrs x11, dbgwvr6_el1 - mrs x10, dbgwvr5_el1 - mrs x9, dbgwvr4_el1 - mrs x8, dbgwvr3_el1 - mrs x7, dbgwvr2_el1 - mrs x6, dbgwvr1_el1 - mrs x5, dbgwvr0_el1 - - adr x26, 1f - add x26, x26, x25, lsl #2 - br x26 - -1: - str x20, [x3, #(15 * 8)] - str x19, [x3, #(14 * 8)] - str x18, [x3, #(13 * 8)] - str x17, [x3, #(12 * 8)] - str x16, [x3, #(11 * 8)] - str x15, [x3, #(10 * 8)] - str x14, [x3, #(9 * 8)] - str x13, [x3, #(8 * 8)] - str x12, [x3, #(7 * 8)] - str x11, [x3, #(6 * 8)] - str x10, [x3, #(5 * 8)] - str x9, [x3, #(4 * 8)] - str x8, [x3, #(3 * 8)] - str x7, [x3, #(2 * 8)] - str x6, [x3, #(1 * 8)] - str x5, [x3, #(0 * 8)] - - mrs x21, mdccint_el1 - str x21, [x2, #CPU_SYSREG_OFFSET(MDCCINT_EL1)] -.endm - -.macro restore_sysregs - // x2: base address for cpu context - // x3: tmp register - - add x3, x2, #CPU_SYSREG_OFFSET(MPIDR_EL1) - - ldp x4, x5, [x3] - ldp x6, x7, [x3, #16] - ldp x8, x9, [x3, #32] - ldp x10, x11, [x3, #48] - ldp x12, x13, [x3, #64] - ldp x14, x15, [x3, #80] - ldp x16, x17, [x3, #96] - ldp x18, x19, [x3, #112] - ldp x20, x21, [x3, #128] - ldp x22, x23, [x3, #144] - ldp x24, x25, [x3, #160] - - msr vmpidr_el2, x4 - msr csselr_el1, x5 - msr sctlr_el1, x6 - msr actlr_el1, x7 - msr cpacr_el1, x8 - msr ttbr0_el1, x9 - msr ttbr1_el1, x10 - msr tcr_el1, x11 - msr esr_el1, x12 - msr afsr0_el1, x13 - msr afsr1_el1, x14 - msr far_el1, x15 - msr mair_el1, x16 - msr vbar_el1, x17 - msr contextidr_el1, x18 - msr tpidr_el0, x19 - msr tpidrro_el0, x20 - msr tpidr_el1, x21 - msr amair_el1, x22 - msr cntkctl_el1, x23 - msr par_el1, x24 - msr mdscr_el1, x25 -.endm - -.macro restore_debug - // x2: base address for cpu context - // x3: tmp register - - mrs x26, id_aa64dfr0_el1 - ubfx x24, x26, #12, #4 // Extract BRPs - ubfx x25, x26, #20, #4 // Extract WRPs - mov w26, #15 - sub w24, w26, w24 // How many BPs to skip - sub w25, w26, w25 // How many WPs to skip - - add x3, x2, #CPU_SYSREG_OFFSET(DBGBCR0_EL1) - - adr x26, 1f - add x26, x26, x24, lsl #2 - br x26 -1: - ldr x20, [x3, #(15 * 8)] - ldr x19, [x3, #(14 * 8)] - ldr x18, [x3, #(13 * 8)] - ldr x17, [x3, #(12 * 8)] - ldr x16, [x3, #(11 * 8)] - ldr x15, [x3, #(10 * 8)] - ldr x14, [x3, #(9 * 8)] - ldr x13, [x3, #(8 * 8)] - ldr x12, [x3, #(7 * 8)] - ldr x11, [x3, #(6 * 8)] - ldr x10, [x3, #(5 * 8)] - ldr x9, [x3, #(4 * 8)] - ldr x8, [x3, #(3 * 8)] - ldr x7, [x3, #(2 * 8)] - ldr x6, [x3, #(1 * 8)] - ldr x5, [x3, #(0 * 8)] - - adr x26, 1f - add x26, x26, x24, lsl #2 - br x26 -1: - msr dbgbcr15_el1, x20 - msr dbgbcr14_el1, x19 - msr dbgbcr13_el1, x18 - msr dbgbcr12_el1, x17 - msr dbgbcr11_el1, x16 - msr dbgbcr10_el1, x15 - msr dbgbcr9_el1, x14 - msr dbgbcr8_el1, x13 - msr dbgbcr7_el1, x12 - msr dbgbcr6_el1, x11 - msr dbgbcr5_el1, x10 - msr dbgbcr4_el1, x9 - msr dbgbcr3_el1, x8 - msr dbgbcr2_el1, x7 - msr dbgbcr1_el1, x6 - msr dbgbcr0_el1, x5 - - add x3, x2, #CPU_SYSREG_OFFSET(DBGBVR0_EL1) - - adr x26, 1f - add x26, x26, x24, lsl #2 - br x26 -1: - ldr x20, [x3, #(15 * 8)] - ldr x19, [x3, #(14 * 8)] - ldr x18, [x3, #(13 * 8)] - ldr x17, [x3, #(12 * 8)] - ldr x16, [x3, #(11 * 8)] - ldr x15, [x3, #(10 * 8)] - ldr x14, [x3, #(9 * 8)] - ldr x13, [x3, #(8 * 8)] - ldr x12, [x3, #(7 * 8)] - ldr x11, [x3, #(6 * 8)] - ldr x10, [x3, #(5 * 8)] - ldr x9, [x3, #(4 * 8)] - ldr x8, [x3, #(3 * 8)] - ldr x7, [x3, #(2 * 8)] - ldr x6, [x3, #(1 * 8)] - ldr x5, [x3, #(0 * 8)] - - adr x26, 1f - add x26, x26, x24, lsl #2 - br x26 -1: - msr dbgbvr15_el1, x20 - msr dbgbvr14_el1, x19 - msr dbgbvr13_el1, x18 - msr dbgbvr12_el1, x17 - msr dbgbvr11_el1, x16 - msr dbgbvr10_el1, x15 - msr dbgbvr9_el1, x14 - msr dbgbvr8_el1, x13 - msr dbgbvr7_el1, x12 - msr dbgbvr6_el1, x11 - msr dbgbvr5_el1, x10 - msr dbgbvr4_el1, x9 - msr dbgbvr3_el1, x8 - msr dbgbvr2_el1, x7 - msr dbgbvr1_el1, x6 - msr dbgbvr0_el1, x5 - - add x3, x2, #CPU_SYSREG_OFFSET(DBGWCR0_EL1) - - adr x26, 1f - add x26, x26, x25, lsl #2 - br x26 -1: - ldr x20, [x3, #(15 * 8)] - ldr x19, [x3, #(14 * 8)] - ldr x18, [x3, #(13 * 8)] - ldr x17, [x3, #(12 * 8)] - ldr x16, [x3, #(11 * 8)] - ldr x15, [x3, #(10 * 8)] - ldr x14, [x3, #(9 * 8)] - ldr x13, [x3, #(8 * 8)] - ldr x12, [x3, #(7 * 8)] - ldr x11, [x3, #(6 * 8)] - ldr x10, [x3, #(5 * 8)] - ldr x9, [x3, #(4 * 8)] - ldr x8, [x3, #(3 * 8)] - ldr x7, [x3, #(2 * 8)] - ldr x6, [x3, #(1 * 8)] - ldr x5, [x3, #(0 * 8)] - - adr x26, 1f - add x26, x26, x25, lsl #2 - br x26 -1: - msr dbgwcr15_el1, x20 - msr dbgwcr14_el1, x19 - msr dbgwcr13_el1, x18 - msr dbgwcr12_el1, x17 - msr dbgwcr11_el1, x16 - msr dbgwcr10_el1, x15 - msr dbgwcr9_el1, x14 - msr dbgwcr8_el1, x13 - msr dbgwcr7_el1, x12 - msr dbgwcr6_el1, x11 - msr dbgwcr5_el1, x10 - msr dbgwcr4_el1, x9 - msr dbgwcr3_el1, x8 - msr dbgwcr2_el1, x7 - msr dbgwcr1_el1, x6 - msr dbgwcr0_el1, x5 - - add x3, x2, #CPU_SYSREG_OFFSET(DBGWVR0_EL1) - - adr x26, 1f - add x26, x26, x25, lsl #2 - br x26 -1: - ldr x20, [x3, #(15 * 8)] - ldr x19, [x3, #(14 * 8)] - ldr x18, [x3, #(13 * 8)] - ldr x17, [x3, #(12 * 8)] - ldr x16, [x3, #(11 * 8)] - ldr x15, [x3, #(10 * 8)] - ldr x14, [x3, #(9 * 8)] - ldr x13, [x3, #(8 * 8)] - ldr x12, [x3, #(7 * 8)] - ldr x11, [x3, #(6 * 8)] - ldr x10, [x3, #(5 * 8)] - ldr x9, [x3, #(4 * 8)] - ldr x8, [x3, #(3 * 8)] - ldr x7, [x3, #(2 * 8)] - ldr x6, [x3, #(1 * 8)] - ldr x5, [x3, #(0 * 8)] - - adr x26, 1f - add x26, x26, x25, lsl #2 - br x26 -1: - msr dbgwvr15_el1, x20 - msr dbgwvr14_el1, x19 - msr dbgwvr13_el1, x18 - msr dbgwvr12_el1, x17 - msr dbgwvr11_el1, x16 - msr dbgwvr10_el1, x15 - msr dbgwvr9_el1, x14 - msr dbgwvr8_el1, x13 - msr dbgwvr7_el1, x12 - msr dbgwvr6_el1, x11 - msr dbgwvr5_el1, x10 - msr dbgwvr4_el1, x9 - msr dbgwvr3_el1, x8 - msr dbgwvr2_el1, x7 - msr dbgwvr1_el1, x6 - msr dbgwvr0_el1, x5 - - ldr x21, [x2, #CPU_SYSREG_OFFSET(MDCCINT_EL1)] - msr mdccint_el1, x21 -.endm - -.macro skip_32bit_state tmp, target - // Skip 32bit state if not needed - mrs \tmp, hcr_el2 - tbnz \tmp, #HCR_RW_SHIFT, \target -.endm - -.macro skip_tee_state tmp, target - // Skip ThumbEE state if not needed - mrs \tmp, id_pfr0_el1 - tbz \tmp, #12, \target -.endm - -.macro skip_debug_state tmp, target - ldr \tmp, [x0, #VCPU_DEBUG_FLAGS] - tbz \tmp, #KVM_ARM64_DEBUG_DIRTY_SHIFT, \target -.endm - -.macro compute_debug_state target - // Compute debug state: If any of KDE, MDE or KVM_ARM64_DEBUG_DIRTY - // is set, we do a full save/restore cycle and disable trapping. - add x25, x0, #VCPU_CONTEXT - - // Check the state of MDSCR_EL1 - ldr x25, [x25, #CPU_SYSREG_OFFSET(MDSCR_EL1)] - and x26, x25, #DBG_MDSCR_KDE - and x25, x25, #DBG_MDSCR_MDE - adds xzr, x25, x26 - b.eq 9998f // Nothing to see there - - // If any interesting bits was set, we must set the flag - mov x26, #KVM_ARM64_DEBUG_DIRTY - str x26, [x0, #VCPU_DEBUG_FLAGS] - b 9999f // Don't skip restore - -9998: - // Otherwise load the flags from memory in case we recently - // trapped - skip_debug_state x25, \target -9999: -.endm - -.macro save_guest_32bit_state - skip_32bit_state x3, 1f - - add x3, x2, #CPU_SPSR_OFFSET(KVM_SPSR_ABT) - mrs x4, spsr_abt - mrs x5, spsr_und - mrs x6, spsr_irq - mrs x7, spsr_fiq - stp x4, x5, [x3] - stp x6, x7, [x3, #16] - - add x3, x2, #CPU_SYSREG_OFFSET(DACR32_EL2) - mrs x4, dacr32_el2 - mrs x5, ifsr32_el2 - mrs x6, fpexc32_el2 - stp x4, x5, [x3] - str x6, [x3, #16] - - skip_debug_state x8, 2f - mrs x7, dbgvcr32_el2 - str x7, [x3, #24] -2: - skip_tee_state x8, 1f - - add x3, x2, #CPU_SYSREG_OFFSET(TEECR32_EL1) - mrs x4, teecr32_el1 - mrs x5, teehbr32_el1 - stp x4, x5, [x3] -1: -.endm - -.macro restore_guest_32bit_state - skip_32bit_state x3, 1f - - add x3, x2, #CPU_SPSR_OFFSET(KVM_SPSR_ABT) - ldp x4, x5, [x3] - ldp x6, x7, [x3, #16] - msr spsr_abt, x4 - msr spsr_und, x5 - msr spsr_irq, x6 - msr spsr_fiq, x7 - - add x3, x2, #CPU_SYSREG_OFFSET(DACR32_EL2) - ldp x4, x5, [x3] - ldr x6, [x3, #16] - msr dacr32_el2, x4 - msr ifsr32_el2, x5 - msr fpexc32_el2, x6 - - skip_debug_state x8, 2f - ldr x7, [x3, #24] - msr dbgvcr32_el2, x7 -2: - skip_tee_state x8, 1f - - add x3, x2, #CPU_SYSREG_OFFSET(TEECR32_EL1) - ldp x4, x5, [x3] - msr teecr32_el1, x4 - msr teehbr32_el1, x5 -1: -.endm - -.macro activate_traps - ldr x2, [x0, #VCPU_HCR_EL2] - msr hcr_el2, x2 - mov x2, #CPTR_EL2_TTA - msr cptr_el2, x2 - - mov x2, #(1 << 15) // Trap CP15 Cr=15 - msr hstr_el2, x2 - - mrs x2, mdcr_el2 - and x2, x2, #MDCR_EL2_HPMN_MASK - orr x2, x2, #(MDCR_EL2_TPM | MDCR_EL2_TPMCR) - orr x2, x2, #(MDCR_EL2_TDRA | MDCR_EL2_TDOSA) - - // Check for KVM_ARM64_DEBUG_DIRTY, and set debug to trap - // if not dirty. - ldr x3, [x0, #VCPU_DEBUG_FLAGS] - tbnz x3, #KVM_ARM64_DEBUG_DIRTY_SHIFT, 1f - orr x2, x2, #MDCR_EL2_TDA -1: - msr mdcr_el2, x2 -.endm - -.macro deactivate_traps - mov x2, #HCR_RW - msr hcr_el2, x2 - msr cptr_el2, xzr - msr hstr_el2, xzr - - mrs x2, mdcr_el2 - and x2, x2, #MDCR_EL2_HPMN_MASK - msr mdcr_el2, x2 -.endm - -.macro activate_vm - ldr x1, [x0, #VCPU_KVM] - kern_hyp_va x1 - ldr x2, [x1, #KVM_VTTBR] - msr vttbr_el2, x2 -.endm - -.macro deactivate_vm - msr vttbr_el2, xzr -.endm - -/* - * Call into the vgic backend for state saving - */ -.macro save_vgic_state - adr x24, __vgic_sr_vectors - ldr x24, [x24, VGIC_SAVE_FN] - kern_hyp_va x24 - blr x24 - mrs x24, hcr_el2 - mov x25, #HCR_INT_OVERRIDE - neg x25, x25 - and x24, x24, x25 - msr hcr_el2, x24 -.endm - -/* - * Call into the vgic backend for state restoring - */ -.macro restore_vgic_state - mrs x24, hcr_el2 - ldr x25, [x0, #VCPU_IRQ_LINES] - orr x24, x24, #HCR_INT_OVERRIDE - orr x24, x24, x25 - msr hcr_el2, x24 - adr x24, __vgic_sr_vectors - ldr x24, [x24, #VGIC_RESTORE_FN] - kern_hyp_va x24 - blr x24 -.endm - -.macro save_timer_state - // x0: vcpu pointer - ldr x2, [x0, #VCPU_KVM] - kern_hyp_va x2 - ldr w3, [x2, #KVM_TIMER_ENABLED] - cbz w3, 1f - - mrs x3, cntv_ctl_el0 - and x3, x3, #3 - str w3, [x0, #VCPU_TIMER_CNTV_CTL] - - isb - - mrs x3, cntv_cval_el0 - str x3, [x0, #VCPU_TIMER_CNTV_CVAL] - -1: - // Disable the virtual timer - msr cntv_ctl_el0, xzr - - // Allow physical timer/counter access for the host - mrs x2, cnthctl_el2 - orr x2, x2, #3 - msr cnthctl_el2, x2 - - // Clear cntvoff for the host - msr cntvoff_el2, xzr -.endm - -.macro restore_timer_state - // x0: vcpu pointer - // Disallow physical timer access for the guest - // Physical counter access is allowed - mrs x2, cnthctl_el2 - orr x2, x2, #1 - bic x2, x2, #2 - msr cnthctl_el2, x2 - - ldr x2, [x0, #VCPU_KVM] - kern_hyp_va x2 - ldr w3, [x2, #KVM_TIMER_ENABLED] - cbz w3, 1f - - ldr x3, [x2, #KVM_TIMER_CNTVOFF] - msr cntvoff_el2, x3 - ldr x2, [x0, #VCPU_TIMER_CNTV_CVAL] - msr cntv_cval_el0, x2 - isb - - ldr w2, [x0, #VCPU_TIMER_CNTV_CTL] - and x2, x2, #3 - msr cntv_ctl_el0, x2 -1: -.endm - -__save_sysregs: - save_sysregs - ret - -__restore_sysregs: - restore_sysregs - ret - -__save_debug: - save_debug - ret - -__restore_debug: - restore_debug - ret - -__save_fpsimd: - save_fpsimd - ret - -__restore_fpsimd: - restore_fpsimd - ret - -/* - * u64 __kvm_vcpu_run(struct kvm_vcpu *vcpu); - * - * This is the world switch. The first half of the function - * deals with entering the guest, and anything from __kvm_vcpu_return - * to the end of the function deals with reentering the host. - * On the enter path, only x0 (vcpu pointer) must be preserved until - * the last moment. On the exit path, x0 (vcpu pointer) and x1 (exception - * code) must both be preserved until the epilogue. - * In both cases, x2 points to the CPU context we're saving/restoring from/to. - */ -ENTRY(__kvm_vcpu_run) - kern_hyp_va x0 - msr tpidr_el2, x0 // Save the vcpu register - - // Host context - ldr x2, [x0, #VCPU_HOST_CONTEXT] - kern_hyp_va x2 - - save_host_regs - bl __save_fpsimd - bl __save_sysregs - - compute_debug_state 1f - bl __save_debug -1: - activate_traps - activate_vm - - restore_vgic_state - restore_timer_state - - // Guest context - add x2, x0, #VCPU_CONTEXT - - // We must restore the 32-bit state before the sysregs, thanks - // to Cortex-A57 erratum #852523. - restore_guest_32bit_state - bl __restore_sysregs - bl __restore_fpsimd - - skip_debug_state x3, 1f - bl __restore_debug -1: - restore_guest_regs - - // That's it, no more messing around. - eret - -__kvm_vcpu_return: - // Assume x0 is the vcpu pointer, x1 the return code - // Guest's x0-x3 are on the stack - - // Guest context - add x2, x0, #VCPU_CONTEXT - - save_guest_regs - bl __save_fpsimd - bl __save_sysregs - - skip_debug_state x3, 1f - bl __save_debug -1: - save_guest_32bit_state - - save_timer_state - save_vgic_state - - deactivate_traps - deactivate_vm - - // Host context - ldr x2, [x0, #VCPU_HOST_CONTEXT] - kern_hyp_va x2 - - bl __restore_sysregs - bl __restore_fpsimd - - skip_debug_state x3, 1f - // Clear the dirty flag for the next run, as all the state has - // already been saved. Note that we nuke the whole 64bit word. - // If we ever add more flags, we'll have to be more careful... - str xzr, [x0, #VCPU_DEBUG_FLAGS] - bl __restore_debug -1: - restore_host_regs - - mov x0, x1 - ret -END(__kvm_vcpu_run) - -// void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa); -ENTRY(__kvm_tlb_flush_vmid_ipa) - dsb ishst - - kern_hyp_va x0 - ldr x2, [x0, #KVM_VTTBR] - msr vttbr_el2, x2 - isb - - /* - * 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... - */ - lsr x1, x1, #12 - tlbi ipas2e1is, x1 - /* - * 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 - - msr vttbr_el2, xzr - ret -ENDPROC(__kvm_tlb_flush_vmid_ipa) - -/** - * void __kvm_tlb_flush_vmid(struct kvm *kvm) - Flush per-VMID TLBs - * @struct kvm *kvm - pointer to kvm structure - * - * Invalidates all Stage 1 and 2 TLB entries for current VMID. - */ -ENTRY(__kvm_tlb_flush_vmid) - dsb ishst - - kern_hyp_va x0 - ldr x2, [x0, #KVM_VTTBR] - msr vttbr_el2, x2 - isb - - tlbi vmalls12e1is - dsb ish - isb - - msr vttbr_el2, xzr - ret -ENDPROC(__kvm_tlb_flush_vmid) - -ENTRY(__kvm_flush_vm_context) - dsb ishst - tlbi alle1is - ic ialluis - dsb ish - ret -ENDPROC(__kvm_flush_vm_context) - - // struct vgic_sr_vectors __vgi_sr_vectors; - .align 3 -ENTRY(__vgic_sr_vectors) - .skip VGIC_SR_VECTOR_SZ -ENDPROC(__vgic_sr_vectors) - -__kvm_hyp_panic: - // Guess the context by looking at VTTBR: - // If zero, then we're already a host. - // Otherwise restore a minimal host context before panicing. - mrs x0, vttbr_el2 - cbz x0, 1f - - mrs x0, tpidr_el2 - - deactivate_traps - deactivate_vm - - ldr x2, [x0, #VCPU_HOST_CONTEXT] - kern_hyp_va x2 - - bl __restore_sysregs - -1: adr x0, __hyp_panic_str - adr x1, 2f - ldp x2, x3, [x1] - sub x0, x0, x2 - add x0, x0, x3 - mrs x1, spsr_el2 - mrs x2, elr_el2 - mrs x3, esr_el2 - mrs x4, far_el2 - mrs x5, hpfar_el2 - mrs x6, par_el1 - mrs x7, tpidr_el2 - - mov lr, #(PSR_F_BIT | PSR_I_BIT | PSR_A_BIT | PSR_D_BIT |\ - PSR_MODE_EL1h) - msr spsr_el2, lr - ldr lr, =panic - msr elr_el2, lr - eret - - .align 3 -2: .quad HYP_PAGE_OFFSET - .quad PAGE_OFFSET -ENDPROC(__kvm_hyp_panic) - -__hyp_panic_str: - .ascii "HYP panic:\nPS:%08x PC:%p ESR:%p\nFAR:%p HPFAR:%p PAR:%p\nVCPU:%p\n\0" - - .align 2 +#include <asm/cpufeature.h> /* * u64 kvm_call_hyp(void *hypfn, ...); @@ -1130,172 +33,24 @@ __hyp_panic_str: * passed as x0, x1, and x2 (a maximum of 3 arguments in addition to the * function pointer can be passed). The function being called must be mapped * in Hyp mode (see init_hyp_mode in arch/arm/kvm/arm.c). Return values are - * passed in r0 and r1. + * passed in x0. * - * A function pointer with a value of 0 has a special meaning, and is - * used to implement __hyp_get_vectors in the same way as in + * A function pointer with a value less than 0xfff has a special meaning, + * and is used to implement __hyp_get_vectors in the same way as in * arch/arm64/kernel/hyp_stub.S. + * HVC behaves as a 'bl' call and will clobber lr. */ ENTRY(kvm_call_hyp) +alternative_if_not ARM64_HAS_VIRT_HOST_EXTN + str lr, [sp, #-16]! hvc #0 - ret + ldr lr, [sp], #16 + ret +alternative_else + b __vhe_hyp_call + nop + nop + nop +alternative_endif ENDPROC(kvm_call_hyp) -.macro invalid_vector label, target - .align 2 -\label: - b \target -ENDPROC(\label) -.endm - - /* None of these should ever happen */ - invalid_vector el2t_sync_invalid, __kvm_hyp_panic - invalid_vector el2t_irq_invalid, __kvm_hyp_panic - invalid_vector el2t_fiq_invalid, __kvm_hyp_panic - invalid_vector el2t_error_invalid, __kvm_hyp_panic - invalid_vector el2h_sync_invalid, __kvm_hyp_panic - invalid_vector el2h_irq_invalid, __kvm_hyp_panic - invalid_vector el2h_fiq_invalid, __kvm_hyp_panic - invalid_vector el2h_error_invalid, __kvm_hyp_panic - invalid_vector el1_sync_invalid, __kvm_hyp_panic - invalid_vector el1_irq_invalid, __kvm_hyp_panic - invalid_vector el1_fiq_invalid, __kvm_hyp_panic - invalid_vector el1_error_invalid, __kvm_hyp_panic - -el1_sync: // Guest trapped into EL2 - push x0, x1 - push x2, x3 - - mrs x1, esr_el2 - lsr x2, x1, #ESR_ELx_EC_SHIFT - - cmp x2, #ESR_ELx_EC_HVC64 - b.ne el1_trap - - mrs x3, vttbr_el2 // If vttbr is valid, the 64bit guest - cbnz x3, el1_trap // called HVC - - /* Here, we're pretty sure the host called HVC. */ - pop x2, x3 - pop x0, x1 - - /* Check for __hyp_get_vectors */ - cbnz x0, 1f - mrs x0, vbar_el2 - b 2f - -1: push lr, xzr - - /* - * Compute the function address in EL2, and shuffle the parameters. - */ - kern_hyp_va x0 - mov lr, x0 - mov x0, x1 - mov x1, x2 - mov x2, x3 - blr lr - - pop lr, xzr -2: eret - -el1_trap: - /* - * x1: ESR - * x2: ESR_EC - */ - cmp x2, #ESR_ELx_EC_DABT_LOW - mov x0, #ESR_ELx_EC_IABT_LOW - ccmp x2, x0, #4, ne - b.ne 1f // Not an abort we care about - - /* This is an abort. Check for permission fault */ - and x2, x1, #ESR_ELx_FSC_TYPE - cmp x2, #FSC_PERM - b.ne 1f // Not a permission fault - - /* - * Check for Stage-1 page table walk, which is guaranteed - * to give a valid HPFAR_EL2. - */ - tbnz x1, #7, 1f // S1PTW is set - - /* Preserve PAR_EL1 */ - mrs x3, par_el1 - push x3, xzr - - /* - * Permission fault, HPFAR_EL2 is invalid. - * 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. - */ - mrs x2, far_el2 - at s1e1r, x2 - isb - - /* Read result */ - mrs x3, par_el1 - pop x0, xzr // Restore PAR_EL1 from the stack - msr par_el1, x0 - tbnz x3, #0, 3f // Bail out if we failed the translation - ubfx x3, x3, #12, #36 // Extract IPA - lsl x3, x3, #4 // and present it like HPFAR - b 2f - -1: mrs x3, hpfar_el2 - mrs x2, far_el2 - -2: mrs x0, tpidr_el2 - str w1, [x0, #VCPU_ESR_EL2] - str x2, [x0, #VCPU_FAR_EL2] - str x3, [x0, #VCPU_HPFAR_EL2] - - mov x1, #ARM_EXCEPTION_TRAP - b __kvm_vcpu_return - - /* - * Translation failed. Just return to the guest and - * let it fault again. Another CPU is probably playing - * behind our back. - */ -3: pop x2, x3 - pop x0, x1 - - eret - -el1_irq: - push x0, x1 - push x2, x3 - mrs x0, tpidr_el2 - mov x1, #ARM_EXCEPTION_IRQ - b __kvm_vcpu_return - - .ltorg - - .align 11 - -ENTRY(__kvm_hyp_vector) - ventry el2t_sync_invalid // Synchronous EL2t - ventry el2t_irq_invalid // IRQ EL2t - ventry el2t_fiq_invalid // FIQ EL2t - ventry el2t_error_invalid // Error EL2t - - ventry el2h_sync_invalid // Synchronous EL2h - ventry el2h_irq_invalid // IRQ EL2h - ventry el2h_fiq_invalid // FIQ EL2h - ventry el2h_error_invalid // Error EL2h - - ventry el1_sync // Synchronous 64-bit EL1 - ventry el1_irq // IRQ 64-bit EL1 - ventry el1_fiq_invalid // FIQ 64-bit EL1 - ventry el1_error_invalid // Error 64-bit EL1 - - ventry el1_sync // Synchronous 32-bit EL1 - ventry el1_irq // IRQ 32-bit EL1 - ventry el1_fiq_invalid // FIQ 32-bit EL1 - ventry el1_error_invalid // Error 32-bit EL1 -ENDPROC(__kvm_hyp_vector) - - .popsection |