diff options
Diffstat (limited to 'arch/arm64/kvm')
25 files changed, 1121 insertions, 208 deletions
diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile index 5e33c2d4645a..c0c050e53157 100644 --- a/arch/arm64/kvm/Makefile +++ b/arch/arm64/kvm/Makefile @@ -14,7 +14,7 @@ kvm-y += arm.o mmu.o mmio.o psci.o hypercalls.o pvtime.o \ inject_fault.o va_layout.o handle_exit.o \ guest.o debug.o reset.o sys_regs.o stacktrace.o \ vgic-sys-reg-v3.o fpsimd.o pkvm.o \ - arch_timer.o trng.o vmid.o \ + arch_timer.o trng.o vmid.o emulate-nested.o nested.o \ vgic/vgic.o vgic/vgic-init.o \ vgic/vgic-irqfd.o vgic/vgic-v2.o \ vgic/vgic-v3.o vgic/vgic-v4.o \ diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c index 23346585a294..00610477ec7b 100644 --- a/arch/arm64/kvm/arch_timer.c +++ b/arch/arm64/kvm/arch_timer.c @@ -428,14 +428,17 @@ static void timer_emulate(struct arch_timer_context *ctx) * scheduled for the future. If the timer cannot fire at all, * then we also don't need a soft timer. */ - if (!kvm_timer_irq_can_fire(ctx)) { - soft_timer_cancel(&ctx->hrtimer); + if (should_fire || !kvm_timer_irq_can_fire(ctx)) return; - } soft_timer_start(&ctx->hrtimer, kvm_timer_compute_delta(ctx)); } +static void set_cntvoff(u64 cntvoff) +{ + kvm_call_hyp(__kvm_timer_set_cntvoff, cntvoff); +} + static void timer_save_state(struct arch_timer_context *ctx) { struct arch_timer_cpu *timer = vcpu_timer(ctx->vcpu); @@ -459,6 +462,22 @@ static void timer_save_state(struct arch_timer_context *ctx) write_sysreg_el0(0, SYS_CNTV_CTL); isb(); + /* + * The kernel may decide to run userspace after + * calling vcpu_put, so we reset cntvoff to 0 to + * ensure a consistent read between user accesses to + * the virtual counter and kernel access to the + * physical counter of non-VHE case. + * + * For VHE, the virtual counter uses a fixed virtual + * offset of zero, so no need to zero CNTVOFF_EL2 + * register, but this is actually useful when switching + * between EL1/vEL2 with NV. + * + * Do it unconditionally, as this is either unavoidable + * or dirt cheap. + */ + set_cntvoff(0); break; case TIMER_PTIMER: timer_set_ctl(ctx, read_sysreg_el0(SYS_CNTP_CTL)); @@ -532,6 +551,7 @@ static void timer_restore_state(struct arch_timer_context *ctx) switch (index) { case TIMER_VTIMER: + set_cntvoff(timer_get_offset(ctx)); write_sysreg_el0(timer_get_cval(ctx), SYS_CNTV_CVAL); isb(); write_sysreg_el0(timer_get_ctl(ctx), SYS_CNTV_CTL); @@ -552,11 +572,6 @@ out: local_irq_restore(flags); } -static void set_cntvoff(u64 cntvoff) -{ - kvm_call_hyp(__kvm_timer_set_cntvoff, cntvoff); -} - static inline void set_timer_irq_phys_active(struct arch_timer_context *ctx, bool active) { int r; @@ -631,8 +646,6 @@ void kvm_timer_vcpu_load(struct kvm_vcpu *vcpu) kvm_timer_vcpu_load_nogic(vcpu); } - set_cntvoff(timer_get_offset(map.direct_vtimer)); - kvm_timer_unblocking(vcpu); timer_restore_state(map.direct_vtimer); @@ -688,15 +701,6 @@ void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu) if (kvm_vcpu_is_blocking(vcpu)) kvm_timer_blocking(vcpu); - - /* - * The kernel may decide to run userspace after calling vcpu_put, so - * we reset cntvoff to 0 to ensure a consistent read between user - * accesses to the virtual counter and kernel access to the physical - * counter of non-VHE case. For VHE, the virtual counter uses a fixed - * virtual offset of zero, so no need to zero CNTVOFF_EL2 register. - */ - set_cntvoff(0); } /* @@ -934,14 +938,22 @@ u64 kvm_arm_timer_read_sysreg(struct kvm_vcpu *vcpu, enum kvm_arch_timers tmr, enum kvm_arch_timer_regs treg) { + struct arch_timer_context *timer; + struct timer_map map; u64 val; + get_timer_map(vcpu, &map); + timer = vcpu_get_timer(vcpu, tmr); + + if (timer == map.emul_ptimer) + return kvm_arm_timer_read(vcpu, timer, treg); + preempt_disable(); - kvm_timer_vcpu_put(vcpu); + timer_save_state(timer); - val = kvm_arm_timer_read(vcpu, vcpu_get_timer(vcpu, tmr), treg); + val = kvm_arm_timer_read(vcpu, timer, treg); - kvm_timer_vcpu_load(vcpu); + timer_restore_state(timer); preempt_enable(); return val; @@ -975,13 +987,22 @@ void kvm_arm_timer_write_sysreg(struct kvm_vcpu *vcpu, enum kvm_arch_timer_regs treg, u64 val) { - preempt_disable(); - kvm_timer_vcpu_put(vcpu); - - kvm_arm_timer_write(vcpu, vcpu_get_timer(vcpu, tmr), treg, val); + struct arch_timer_context *timer; + struct timer_map map; - kvm_timer_vcpu_load(vcpu); - preempt_enable(); + get_timer_map(vcpu, &map); + timer = vcpu_get_timer(vcpu, tmr); + if (timer == map.emul_ptimer) { + soft_timer_cancel(&timer->hrtimer); + kvm_arm_timer_write(vcpu, timer, treg, val); + timer_emulate(timer); + } else { + preempt_disable(); + timer_save_state(timer); + kvm_arm_timer_write(vcpu, timer, treg, val); + timer_restore_state(timer); + preempt_enable(); + } } static int timer_irq_set_vcpu_affinity(struct irq_data *d, void *vcpu) diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 698787ed87e9..3bd732eaf087 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -136,7 +136,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) if (ret) goto err_unshare_kvm; - if (!zalloc_cpumask_var(&kvm->arch.supported_cpus, GFP_KERNEL)) { + if (!zalloc_cpumask_var(&kvm->arch.supported_cpus, GFP_KERNEL_ACCOUNT)) { ret = -ENOMEM; goto err_unshare_kvm; } @@ -1899,6 +1899,7 @@ static void kvm_hyp_init_symbols(void) kvm_nvhe_sym(id_aa64mmfr0_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); kvm_nvhe_sym(id_aa64mmfr1_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1); kvm_nvhe_sym(id_aa64mmfr2_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64MMFR2_EL1); + kvm_nvhe_sym(id_aa64smfr0_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64SMFR0_EL1); kvm_nvhe_sym(__icache_flags) = __icache_flags; kvm_nvhe_sym(kvm_arm_vmid_bits) = kvm_arm_vmid_bits; } @@ -1921,9 +1922,7 @@ static int __init kvm_hyp_init_protection(u32 hyp_va_bits) return 0; } -/** - * Inits Hyp-mode on all online CPUs - */ +/* Inits Hyp-mode on all online CPUs */ static int __init init_hyp_mode(void) { u32 hyp_va_bits; @@ -2199,9 +2198,7 @@ void kvm_arch_irq_bypass_start(struct irq_bypass_consumer *cons) kvm_arm_resume_guest(irqfd->kvm); } -/** - * Initialize Hyp-mode and memory mappings on all CPUs. - */ +/* Initialize Hyp-mode and memory mappings on all CPUs */ static __init int kvm_arm_init(void) { int err; @@ -2325,6 +2322,11 @@ static int __init early_kvm_mode_cfg(char *arg) return 0; } + if (strcmp(arg, "nested") == 0 && !WARN_ON(!is_kernel_in_hyp_mode())) { + kvm_mode = KVM_MODE_NV; + return 0; + } + return -EINVAL; } early_param("kvm-arm.mode", early_kvm_mode_cfg); diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c new file mode 100644 index 000000000000..b96662029fb1 --- /dev/null +++ b/arch/arm64/kvm/emulate-nested.c @@ -0,0 +1,203 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2016 - Linaro and Columbia University + * Author: Jintack Lim <jintack.lim@linaro.org> + */ + +#include <linux/kvm.h> +#include <linux/kvm_host.h> + +#include <asm/kvm_emulate.h> +#include <asm/kvm_nested.h> + +#include "hyp/include/hyp/adjust_pc.h" + +#include "trace.h" + +static u64 kvm_check_illegal_exception_return(struct kvm_vcpu *vcpu, u64 spsr) +{ + u64 mode = spsr & PSR_MODE_MASK; + + /* + * Possible causes for an Illegal Exception Return from EL2: + * - trying to return to EL3 + * - trying to return to an illegal M value + * - trying to return to a 32bit EL + * - trying to return to EL1 with HCR_EL2.TGE set + */ + if (mode == PSR_MODE_EL3t || mode == PSR_MODE_EL3h || + mode == 0b00001 || (mode & BIT(1)) || + (spsr & PSR_MODE32_BIT) || + (vcpu_el2_tge_is_set(vcpu) && (mode == PSR_MODE_EL1t || + mode == PSR_MODE_EL1h))) { + /* + * The guest is playing with our nerves. Preserve EL, SP, + * masks, flags from the existing PSTATE, and set IL. + * The HW will then generate an Illegal State Exception + * immediately after ERET. + */ + spsr = *vcpu_cpsr(vcpu); + + spsr &= (PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT | + PSR_N_BIT | PSR_Z_BIT | PSR_C_BIT | PSR_V_BIT | + PSR_MODE_MASK | PSR_MODE32_BIT); + spsr |= PSR_IL_BIT; + } + + return spsr; +} + +void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu) +{ + u64 spsr, elr, mode; + bool direct_eret; + + /* + * Going through the whole put/load motions is a waste of time + * if this is a VHE guest hypervisor returning to its own + * userspace, or the hypervisor performing a local exception + * return. No need to save/restore registers, no need to + * switch S2 MMU. Just do the canonical ERET. + */ + spsr = vcpu_read_sys_reg(vcpu, SPSR_EL2); + spsr = kvm_check_illegal_exception_return(vcpu, spsr); + + mode = spsr & (PSR_MODE_MASK | PSR_MODE32_BIT); + + direct_eret = (mode == PSR_MODE_EL0t && + vcpu_el2_e2h_is_set(vcpu) && + vcpu_el2_tge_is_set(vcpu)); + direct_eret |= (mode == PSR_MODE_EL2h || mode == PSR_MODE_EL2t); + + if (direct_eret) { + *vcpu_pc(vcpu) = vcpu_read_sys_reg(vcpu, ELR_EL2); + *vcpu_cpsr(vcpu) = spsr; + trace_kvm_nested_eret(vcpu, *vcpu_pc(vcpu), spsr); + return; + } + + preempt_disable(); + kvm_arch_vcpu_put(vcpu); + + elr = __vcpu_sys_reg(vcpu, ELR_EL2); + + trace_kvm_nested_eret(vcpu, elr, spsr); + + /* + * Note that the current exception level is always the virtual EL2, + * since we set HCR_EL2.NV bit only when entering the virtual EL2. + */ + *vcpu_pc(vcpu) = elr; + *vcpu_cpsr(vcpu) = spsr; + + kvm_arch_vcpu_load(vcpu, smp_processor_id()); + preempt_enable(); +} + +static void kvm_inject_el2_exception(struct kvm_vcpu *vcpu, u64 esr_el2, + enum exception_type type) +{ + trace_kvm_inject_nested_exception(vcpu, esr_el2, type); + + switch (type) { + case except_type_sync: + kvm_pend_exception(vcpu, EXCEPT_AA64_EL2_SYNC); + vcpu_write_sys_reg(vcpu, esr_el2, ESR_EL2); + break; + case except_type_irq: + kvm_pend_exception(vcpu, EXCEPT_AA64_EL2_IRQ); + break; + default: + WARN_ONCE(1, "Unsupported EL2 exception injection %d\n", type); + } +} + +/* + * Emulate taking an exception to EL2. + * See ARM ARM J8.1.2 AArch64.TakeException() + */ +static int kvm_inject_nested(struct kvm_vcpu *vcpu, u64 esr_el2, + enum exception_type type) +{ + u64 pstate, mode; + bool direct_inject; + + if (!vcpu_has_nv(vcpu)) { + kvm_err("Unexpected call to %s for the non-nesting configuration\n", + __func__); + return -EINVAL; + } + + /* + * As for ERET, we can avoid doing too much on the injection path by + * checking that we either took the exception from a VHE host + * userspace or from vEL2. In these cases, there is no change in + * translation regime (or anything else), so let's do as little as + * possible. + */ + pstate = *vcpu_cpsr(vcpu); + mode = pstate & (PSR_MODE_MASK | PSR_MODE32_BIT); + + direct_inject = (mode == PSR_MODE_EL0t && + vcpu_el2_e2h_is_set(vcpu) && + vcpu_el2_tge_is_set(vcpu)); + direct_inject |= (mode == PSR_MODE_EL2h || mode == PSR_MODE_EL2t); + + if (direct_inject) { + kvm_inject_el2_exception(vcpu, esr_el2, type); + return 1; + } + + preempt_disable(); + + /* + * We may have an exception or PC update in the EL0/EL1 context. + * Commit it before entering EL2. + */ + __kvm_adjust_pc(vcpu); + + kvm_arch_vcpu_put(vcpu); + + kvm_inject_el2_exception(vcpu, esr_el2, type); + + /* + * A hard requirement is that a switch between EL1 and EL2 + * contexts has to happen between a put/load, so that we can + * pick the correct timer and interrupt configuration, among + * other things. + * + * Make sure the exception actually took place before we load + * the new context. + */ + __kvm_adjust_pc(vcpu); + + kvm_arch_vcpu_load(vcpu, smp_processor_id()); + preempt_enable(); + + return 1; +} + +int kvm_inject_nested_sync(struct kvm_vcpu *vcpu, u64 esr_el2) +{ + return kvm_inject_nested(vcpu, esr_el2, except_type_sync); +} + +int kvm_inject_nested_irq(struct kvm_vcpu *vcpu) +{ + /* + * Do not inject an irq if the: + * - Current exception level is EL2, and + * - virtual HCR_EL2.TGE == 0 + * - virtual HCR_EL2.IMO == 0 + * + * See Table D1-17 "Physical interrupt target and masking when EL3 is + * not implemented and EL2 is implemented" in ARM DDI 0487C.a. + */ + + if (vcpu_is_el2(vcpu) && !vcpu_el2_tge_is_set(vcpu) && + !(__vcpu_sys_reg(vcpu, HCR_EL2) & HCR_IMO)) + return 1; + + /* esr_el2 value doesn't matter for exits due to irqs. */ + return kvm_inject_nested(vcpu, 0, except_type_irq); +} diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index 02dd7e9ebd39..1279949599b5 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -143,7 +143,7 @@ void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu) fp_state.st = &vcpu->arch.ctxt.fp_regs; fp_state.sve_state = vcpu->arch.sve_state; fp_state.sve_vl = vcpu->arch.sve_max_vl; - fp_state.za_state = NULL; + fp_state.sme_state = NULL; fp_state.svcr = &vcpu->arch.svcr; fp_state.fp_type = &vcpu->arch.fp_type; @@ -184,6 +184,7 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu) sysreg_clear_set(CPACR_EL1, CPACR_EL1_SMEN_EL0EN, CPACR_EL1_SMEN_EL1EN); + isb(); } if (vcpu->arch.fp_state == FP_STATE_GUEST_OWNED) { diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index cf4c495a4321..07444fa22888 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -24,6 +24,7 @@ #include <asm/fpsimd.h> #include <asm/kvm.h> #include <asm/kvm_emulate.h> +#include <asm/kvm_nested.h> #include <asm/sigcontext.h> #include "trace.h" @@ -253,6 +254,11 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) if (!vcpu_el1_is_32bit(vcpu)) return -EINVAL; break; + case PSR_MODE_EL2h: + case PSR_MODE_EL2t: + if (!vcpu_has_nv(vcpu)) + return -EINVAL; + fallthrough; case PSR_MODE_EL0t: case PSR_MODE_EL1t: case PSR_MODE_EL1h: diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index e778eefcf214..a798c0b4d717 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -16,6 +16,7 @@ #include <asm/kvm_asm.h> #include <asm/kvm_emulate.h> #include <asm/kvm_mmu.h> +#include <asm/kvm_nested.h> #include <asm/debug-monitors.h> #include <asm/stacktrace/nvhe.h> #include <asm/traps.h> @@ -41,6 +42,16 @@ static int handle_hvc(struct kvm_vcpu *vcpu) kvm_vcpu_hvc_get_imm(vcpu)); vcpu->stat.hvc_exit_stat++; + /* Forward hvc instructions to the virtual EL2 if the guest has EL2. */ + if (vcpu_has_nv(vcpu)) { + if (vcpu_read_sys_reg(vcpu, HCR_EL2) & HCR_HCD) + kvm_inject_undefined(vcpu); + else + kvm_inject_nested_sync(vcpu, kvm_vcpu_get_esr(vcpu)); + + return 1; + } + ret = kvm_hvc_call_handler(vcpu); if (ret < 0) { vcpu_set_reg(vcpu, 0, ~0UL); @@ -52,6 +63,8 @@ static int handle_hvc(struct kvm_vcpu *vcpu) static int handle_smc(struct kvm_vcpu *vcpu) { + int ret; + /* * "If an SMC instruction executed at Non-secure EL1 is * trapped to EL2 because HCR_EL2.TSC is 1, the exception is a @@ -59,10 +72,30 @@ static int handle_smc(struct kvm_vcpu *vcpu) * * We need to advance the PC after the trap, as it would * otherwise return to the same address... + * + * Only handle SMCs from the virtual EL2 with an immediate of zero and + * skip it otherwise. */ - vcpu_set_reg(vcpu, 0, ~0UL); + if (!vcpu_is_el2(vcpu) || kvm_vcpu_hvc_get_imm(vcpu)) { + vcpu_set_reg(vcpu, 0, ~0UL); + kvm_incr_pc(vcpu); + return 1; + } + + /* + * If imm is zero then it is likely an SMCCC call. + * + * Note that on ARMv8.3, even if EL3 is not implemented, SMC executed + * at Non-secure EL1 is trapped to EL2 if HCR_EL2.TSC==1, rather than + * being treated as UNDEFINED. + */ + ret = kvm_hvc_call_handler(vcpu); + if (ret < 0) + vcpu_set_reg(vcpu, 0, ~0UL); + kvm_incr_pc(vcpu); - return 1; + + return ret; } /* @@ -196,6 +229,15 @@ static int kvm_handle_ptrauth(struct kvm_vcpu *vcpu) return 1; } +static int kvm_handle_eret(struct kvm_vcpu *vcpu) +{ + if (kvm_vcpu_get_esr(vcpu) & ESR_ELx_ERET_ISS_ERET) + return kvm_handle_ptrauth(vcpu); + + kvm_emulate_nested_eret(vcpu); + return 1; +} + static exit_handle_fn arm_exit_handlers[] = { [0 ... ESR_ELx_EC_MAX] = kvm_handle_unknown_ec, [ESR_ELx_EC_WFx] = kvm_handle_wfx, @@ -211,6 +253,7 @@ static exit_handle_fn arm_exit_handlers[] = { [ESR_ELx_EC_SMC64] = handle_smc, [ESR_ELx_EC_SYS64] = kvm_handle_sys_reg, [ESR_ELx_EC_SVE] = handle_sve, + [ESR_ELx_EC_ERET] = kvm_handle_eret, [ESR_ELx_EC_IABT_LOW] = kvm_handle_guest_abort, [ESR_ELx_EC_DABT_LOW] = kvm_handle_guest_abort, [ESR_ELx_EC_SOFTSTP_LOW]= kvm_handle_guest_debug, diff --git a/arch/arm64/kvm/hyp/exception.c b/arch/arm64/kvm/hyp/exception.c index 791d3de76771..424a5107cddb 100644 --- a/arch/arm64/kvm/hyp/exception.c +++ b/arch/arm64/kvm/hyp/exception.c @@ -14,6 +14,7 @@ #include <linux/kvm_host.h> #include <asm/kvm_emulate.h> #include <asm/kvm_mmu.h> +#include <asm/kvm_nested.h> #if !defined (__KVM_NVHE_HYPERVISOR__) && !defined (__KVM_VHE_HYPERVISOR__) #error Hypervisor code only! @@ -23,7 +24,9 @@ static inline u64 __vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg) { u64 val; - if (__vcpu_read_sys_reg_from_cpu(reg, &val)) + if (unlikely(vcpu_has_nv(vcpu))) + return vcpu_read_sys_reg(vcpu, reg); + else if (__vcpu_read_sys_reg_from_cpu(reg, &val)) return val; return __vcpu_sys_reg(vcpu, reg); @@ -31,18 +34,25 @@ static inline u64 __vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg) static inline void __vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg) { - if (__vcpu_write_sys_reg_to_cpu(val, reg)) - return; - - __vcpu_sys_reg(vcpu, reg) = val; + if (unlikely(vcpu_has_nv(vcpu))) + vcpu_write_sys_reg(vcpu, val, reg); + else if (!__vcpu_write_sys_reg_to_cpu(val, reg)) + __vcpu_sys_reg(vcpu, reg) = val; } -static void __vcpu_write_spsr(struct kvm_vcpu *vcpu, u64 val) +static void __vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long target_mode, + u64 val) { - if (has_vhe()) + if (unlikely(vcpu_has_nv(vcpu))) { + if (target_mode == PSR_MODE_EL1h) + vcpu_write_sys_reg(vcpu, val, SPSR_EL1); + else + vcpu_write_sys_reg(vcpu, val, SPSR_EL2); + } else if (has_vhe()) { write_sysreg_el1(val, SYS_SPSR); - else + } else { __vcpu_sys_reg(vcpu, SPSR_EL1) = val; + } } static void __vcpu_write_spsr_abt(struct kvm_vcpu *vcpu, u64 val) @@ -101,6 +111,11 @@ static void enter_exception64(struct kvm_vcpu *vcpu, unsigned long target_mode, sctlr = __vcpu_read_sys_reg(vcpu, SCTLR_EL1); __vcpu_write_sys_reg(vcpu, *vcpu_pc(vcpu), ELR_EL1); break; + case PSR_MODE_EL2h: + vbar = __vcpu_read_sys_reg(vcpu, VBAR_EL2); + sctlr = __vcpu_read_sys_reg(vcpu, SCTLR_EL2); + __vcpu_write_sys_reg(vcpu, *vcpu_pc(vcpu), ELR_EL2); + break; default: /* Don't do that */ BUG(); @@ -153,7 +168,7 @@ static void enter_exception64(struct kvm_vcpu *vcpu, unsigned long target_mode, new |= target_mode; *vcpu_cpsr(vcpu) = new; - __vcpu_write_spsr(vcpu, old); + __vcpu_write_spsr(vcpu, target_mode, old); } /* @@ -323,11 +338,20 @@ static void kvm_inject_exception(struct kvm_vcpu *vcpu) case unpack_vcpu_flag(EXCEPT_AA64_EL1_SYNC): enter_exception64(vcpu, PSR_MODE_EL1h, except_type_sync); break; + + case unpack_vcpu_flag(EXCEPT_AA64_EL2_SYNC): + enter_exception64(vcpu, PSR_MODE_EL2h, except_type_sync); + break; + + case unpack_vcpu_flag(EXCEPT_AA64_EL2_IRQ): + enter_exception64(vcpu, PSR_MODE_EL2h, except_type_irq); + break; + default: /* - * Only EL1_SYNC makes sense so far, EL2_{SYNC,IRQ} - * will be implemented at some point. Everything - * else gets silently ignored. + * Only EL1_SYNC and EL2_{SYNC,IRQ} makes + * sense so far. Everything else gets silently + * ignored. */ break; } diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h index baa5b9b3dde5..699ea1f8d409 100644 --- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h +++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h @@ -39,7 +39,6 @@ static inline bool ctxt_has_mte(struct kvm_cpu_context *ctxt) static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt) { - 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); @@ -95,7 +94,6 @@ static inline void __sysreg_restore_user_state(struct kvm_cpu_context *ctxt) static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt) { 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)) { @@ -156,9 +154,26 @@ static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt) write_sysreg_el1(ctxt_sys_reg(ctxt, SPSR_EL1), SYS_SPSR); } +/* Read the VCPU state's PSTATE, but translate (v)EL2 to EL1. */ +static inline u64 to_hw_pstate(const struct kvm_cpu_context *ctxt) +{ + u64 mode = ctxt->regs.pstate & (PSR_MODE_MASK | PSR_MODE32_BIT); + + switch (mode) { + case PSR_MODE_EL2t: + mode = PSR_MODE_EL1t; + break; + case PSR_MODE_EL2h: + mode = PSR_MODE_EL1h; + break; + } + + return (ctxt->regs.pstate & ~(PSR_MODE_MASK | PSR_MODE32_BIT)) | mode; +} + static inline void __sysreg_restore_el2_return_state(struct kvm_cpu_context *ctxt) { - u64 pstate = ctxt->regs.pstate; + u64 pstate = to_hw_pstate(ctxt); u64 mode = pstate & PSR_AA32_MODE_MASK; /* diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-init.S b/arch/arm64/kvm/hyp/nvhe/hyp-init.S index c953fb4b9a13..a6d67c2bb5ae 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-init.S +++ b/arch/arm64/kvm/hyp/nvhe/hyp-init.S @@ -183,6 +183,7 @@ SYM_CODE_START_LOCAL(__kvm_hyp_init_cpu) /* Initialize EL2 CPU state to sane values. */ init_el2_state // Clobbers x0..x2 + finalise_el2_state /* Enable MMU, set vectors and stack. */ mov x0, x28 diff --git a/arch/arm64/kvm/hyp/nvhe/sys_regs.c b/arch/arm64/kvm/hyp/nvhe/sys_regs.c index 0f9ac25afdf4..08d2b004f4b7 100644 --- a/arch/arm64/kvm/hyp/nvhe/sys_regs.c +++ b/arch/arm64/kvm/hyp/nvhe/sys_regs.c @@ -26,6 +26,7 @@ u64 id_aa64isar2_el1_sys_val; u64 id_aa64mmfr0_el1_sys_val; u64 id_aa64mmfr1_el1_sys_val; u64 id_aa64mmfr2_el1_sys_val; +u64 id_aa64smfr0_el1_sys_val; /* * Inject an unknown/undefined exception to an AArch64 guest while most of its diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index b11cf2c618a6..3d61bd3e591d 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -168,6 +168,25 @@ static int kvm_pgtable_visitor_cb(struct kvm_pgtable_walk_data *data, return walker->cb(ctx, visit); } +static bool kvm_pgtable_walk_continue(const struct kvm_pgtable_walker *walker, + int r) +{ + /* + * Visitor callbacks return EAGAIN when the conditions that led to a + * fault are no longer reflected in the page tables due to a race to + * update a PTE. In the context of a fault handler this is interpreted + * as a signal to retry guest execution. + * + * Ignore the return code altogether for walkers outside a fault handler + * (e.g. write protecting a range of memory) and chug along with the + * page table walk. + */ + if (r == -EAGAIN) + return !(walker->flags & KVM_PGTABLE_WALK_HANDLE_FAULT); + + return !r; +} + static int __kvm_pgtable_walk(struct kvm_pgtable_walk_data *data, struct kvm_pgtable_mm_ops *mm_ops, kvm_pteref_t pgtable, u32 level); @@ -200,7 +219,7 @@ static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data, table = kvm_pte_table(ctx.old, level); } - if (ret) + if (!kvm_pgtable_walk_continue(data->walker, ret)) goto out; if (!table) { @@ -211,13 +230,16 @@ static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data, childp = (kvm_pteref_t)kvm_pte_follow(ctx.old, mm_ops); ret = __kvm_pgtable_walk(data, mm_ops, childp, level + 1); - if (ret) + if (!kvm_pgtable_walk_continue(data->walker, ret)) goto out; if (ctx.flags & KVM_PGTABLE_WALK_TABLE_POST) ret = kvm_pgtable_visitor_cb(data, &ctx, KVM_PGTABLE_WALK_TABLE_POST); out: + if (kvm_pgtable_walk_continue(data->walker, ret)) + return 0; + return ret; } @@ -584,12 +606,14 @@ u64 kvm_get_vtcr(u64 mmfr0, u64 mmfr1, u32 phys_shift) lvls = 2; vtcr |= VTCR_EL2_LVLS_TO_SL0(lvls); +#ifdef CONFIG_ARM64_HW_AFDBM /* * Enable the Hardware Access Flag management, unconditionally * on all CPUs. The features is RES0 on CPUs without the support * and must be ignored by the CPUs. */ vtcr |= VTCR_EL2_HA; +#endif /* CONFIG_ARM64_HW_AFDBM */ /* Set the vmid bits */ vtcr |= (get_vmid_bits(mmfr1) == 16) ? @@ -1026,7 +1050,7 @@ static int stage2_attr_walker(const struct kvm_pgtable_visit_ctx *ctx, struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; if (!kvm_pte_valid(ctx->old)) - return 0; + return -EAGAIN; data->level = ctx->level; data->pte = pte; @@ -1094,9 +1118,15 @@ int kvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size) kvm_pte_t kvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr) { kvm_pte_t pte = 0; - stage2_update_leaf_attrs(pgt, addr, 1, KVM_PTE_LEAF_ATTR_LO_S2_AF, 0, - &pte, NULL, 0); - dsb(ishst); + int ret; + + ret = stage2_update_leaf_attrs(pgt, addr, 1, KVM_PTE_LEAF_ATTR_LO_S2_AF, 0, + &pte, NULL, + KVM_PGTABLE_WALK_HANDLE_FAULT | + KVM_PGTABLE_WALK_SHARED); + if (!ret) + dsb(ishst); + return pte; } @@ -1141,6 +1171,7 @@ int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr, clr |= KVM_PTE_LEAF_ATTR_HI_S2_XN; ret = stage2_update_leaf_attrs(pgt, addr, 1, set, clr, NULL, &level, + KVM_PGTABLE_WALK_HANDLE_FAULT | KVM_PGTABLE_WALK_SHARED); if (!ret) kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, pgt->mmu, addr, level); diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 1a97391fedd2..cd3f3117bf16 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -40,7 +40,7 @@ static void __activate_traps(struct kvm_vcpu *vcpu) ___activate_traps(vcpu); val = read_sysreg(cpacr_el1); - val |= CPACR_EL1_TTA; + val |= CPACR_ELx_TTA; val &= ~(CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN | CPACR_EL1_SMEN_EL0EN | CPACR_EL1_SMEN_EL1EN); @@ -120,6 +120,25 @@ static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu) static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code) { + /* + * If we were in HYP context on entry, adjust the PSTATE view + * so that the usual helpers work correctly. + */ + if (unlikely(vcpu_get_flag(vcpu, VCPU_HYP_CONTEXT))) { + u64 mode = *vcpu_cpsr(vcpu) & (PSR_MODE_MASK | PSR_MODE32_BIT); + + switch (mode) { + case PSR_MODE_EL1t: + mode = PSR_MODE_EL2t; + break; + case PSR_MODE_EL1h: + mode = PSR_MODE_EL2h; + break; + } + + *vcpu_cpsr(vcpu) &= ~(PSR_MODE_MASK | PSR_MODE32_BIT); + *vcpu_cpsr(vcpu) |= mode; + } } /* Switch to the guest for VHE systems running in EL2 */ @@ -154,6 +173,11 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) sysreg_restore_guest_state_vhe(guest_ctxt); __debug_switch_to_guest(vcpu); + if (is_hyp_ctxt(vcpu)) + vcpu_set_flag(vcpu, VCPU_HYP_CONTEXT); + else + vcpu_clear_flag(vcpu, VCPU_HYP_CONTEXT); + do { /* Jump in the fire! */ exit_code = __guest_enter(vcpu); diff --git a/arch/arm64/kvm/hypercalls.c b/arch/arm64/kvm/hypercalls.c index c9f401fa01a9..64c086c02c60 100644 --- a/arch/arm64/kvm/hypercalls.c +++ b/arch/arm64/kvm/hypercalls.c @@ -198,7 +198,7 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu) break; case ARM_SMCCC_HV_PV_TIME_ST: gpa = kvm_init_stolen_time(vcpu); - if (gpa != GPA_INVALID) + if (gpa != INVALID_GPA) val[0] = gpa; break; case ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID: diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c index f32f4a2a347f..64c3aec0d937 100644 --- a/arch/arm64/kvm/inject_fault.c +++ b/arch/arm64/kvm/inject_fault.c @@ -12,17 +12,55 @@ #include <linux/kvm_host.h> #include <asm/kvm_emulate.h> +#include <asm/kvm_nested.h> #include <asm/esr.h> +static void pend_sync_exception(struct kvm_vcpu *vcpu) +{ + /* If not nesting, EL1 is the only possible exception target */ + if (likely(!vcpu_has_nv(vcpu))) { + kvm_pend_exception(vcpu, EXCEPT_AA64_EL1_SYNC); + return; + } + + /* + * With NV, we need to pick between EL1 and EL2. Note that we + * never deal with a nesting exception here, hence never + * changing context, and the exception itself can be delayed + * until the next entry. + */ + switch(*vcpu_cpsr(vcpu) & PSR_MODE_MASK) { + case PSR_MODE_EL2h: + case PSR_MODE_EL2t: + kvm_pend_exception(vcpu, EXCEPT_AA64_EL2_SYNC); + break; + case PSR_MODE_EL1h: + case PSR_MODE_EL1t: + kvm_pend_exception(vcpu, EXCEPT_AA64_EL1_SYNC); + break; + case PSR_MODE_EL0t: + if (vcpu_el2_tge_is_set(vcpu)) + kvm_pend_exception(vcpu, EXCEPT_AA64_EL2_SYNC); + else + kvm_pend_exception(vcpu, EXCEPT_AA64_EL1_SYNC); + break; + default: + BUG(); + } +} + +static bool match_target_el(struct kvm_vcpu *vcpu, unsigned long target) +{ + return (vcpu_get_flag(vcpu, EXCEPT_MASK) == target); +} + static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr) { unsigned long cpsr = *vcpu_cpsr(vcpu); bool is_aarch32 = vcpu_mode_is_32bit(vcpu); u64 esr = 0; - kvm_pend_exception(vcpu, EXCEPT_AA64_EL1_SYNC); - - vcpu_write_sys_reg(vcpu, addr, FAR_EL1); + pend_sync_exception(vcpu); /* * Build an {i,d}abort, depending on the level and the @@ -43,14 +81,22 @@ static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr if (!is_iabt) esr |= ESR_ELx_EC_DABT_LOW << ESR_ELx_EC_SHIFT; - vcpu_write_sys_reg(vcpu, esr | ESR_ELx_FSC_EXTABT, ESR_EL1); + esr |= ESR_ELx_FSC_EXTABT; + + if (match_target_el(vcpu, unpack_vcpu_flag(EXCEPT_AA64_EL1_SYNC))) { + vcpu_write_sys_reg(vcpu, addr, FAR_EL1); + vcpu_write_sys_reg(vcpu, esr, ESR_EL1); + } else { + vcpu_write_sys_reg(vcpu, addr, FAR_EL2); + vcpu_write_sys_reg(vcpu, esr, ESR_EL2); + } } static void inject_undef64(struct kvm_vcpu *vcpu) { u64 esr = (ESR_ELx_EC_UNKNOWN << ESR_ELx_EC_SHIFT); - kvm_pend_exception(vcpu, EXCEPT_AA64_EL1_SYNC); + pend_sync_exception(vcpu); /* * Build an unknown exception, depending on the instruction @@ -59,7 +105,10 @@ static void inject_undef64(struct kvm_vcpu *vcpu) if (kvm_vcpu_trap_il_is32bit(vcpu)) esr |= ESR_ELx_IL; - vcpu_write_sys_reg(vcpu, esr, ESR_EL1); + if (match_target_el(vcpu, unpack_vcpu_flag(EXCEPT_AA64_EL1_SYNC))) + vcpu_write_sys_reg(vcpu, esr, ESR_EL1); + else + vcpu_write_sys_reg(vcpu, esr, ESR_EL2); } #define DFSR_FSC_EXTABT_LPAE 0x10 diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 01352f5838a0..7113587222ff 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -46,16 +46,17 @@ static phys_addr_t stage2_range_addr_end(phys_addr_t addr, phys_addr_t end) * long will also starve other vCPUs. We have to also make sure that the page * tables are not freed while we released the lock. */ -static int stage2_apply_range(struct kvm *kvm, phys_addr_t addr, +static int stage2_apply_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end, int (*fn)(struct kvm_pgtable *, u64, u64), bool resched) { + struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu); int ret; u64 next; do { - struct kvm_pgtable *pgt = kvm->arch.mmu.pgt; + struct kvm_pgtable *pgt = mmu->pgt; if (!pgt) return -EINVAL; @@ -71,8 +72,8 @@ static int stage2_apply_range(struct kvm *kvm, phys_addr_t addr, return ret; } -#define stage2_apply_range_resched(kvm, addr, end, fn) \ - stage2_apply_range(kvm, addr, end, fn, true) +#define stage2_apply_range_resched(mmu, addr, end, fn) \ + stage2_apply_range(mmu, addr, end, fn, true) static bool memslot_is_logging(struct kvm_memory_slot *memslot) { @@ -235,7 +236,7 @@ static void __unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 lockdep_assert_held_write(&kvm->mmu_lock); WARN_ON(size & ~PAGE_MASK); - WARN_ON(stage2_apply_range(kvm, start, end, kvm_pgtable_stage2_unmap, + WARN_ON(stage2_apply_range(mmu, start, end, kvm_pgtable_stage2_unmap, may_block)); } @@ -250,7 +251,7 @@ static void stage2_flush_memslot(struct kvm *kvm, phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT; phys_addr_t end = addr + PAGE_SIZE * memslot->npages; - stage2_apply_range_resched(kvm, addr, end, kvm_pgtable_stage2_flush); + stage2_apply_range_resched(&kvm->arch.mmu, addr, end, kvm_pgtable_stage2_flush); } /** @@ -934,8 +935,7 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa, */ static void stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end) { - struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu); - stage2_apply_range_resched(kvm, addr, end, kvm_pgtable_stage2_wrprotect); + stage2_apply_range_resched(mmu, addr, end, kvm_pgtable_stage2_wrprotect); } /** @@ -1383,7 +1383,9 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, else ret = kvm_pgtable_stage2_map(pgt, fault_ipa, vma_pagesize, __pfn_to_phys(pfn), prot, - memcache, KVM_PGTABLE_WALK_SHARED); + memcache, + KVM_PGTABLE_WALK_HANDLE_FAULT | + KVM_PGTABLE_WALK_SHARED); /* Mark the page dirty only if the fault is handled successfully */ if (writable && !ret) { @@ -1401,20 +1403,18 @@ out_unlock: /* Resolve the access fault by making the page young again. */ static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa) { - pte_t pte; - kvm_pte_t kpte; + kvm_pte_t pte; struct kvm_s2_mmu *mmu; trace_kvm_access_fault(fault_ipa); - write_lock(&vcpu->kvm->mmu_lock); + read_lock(&vcpu->kvm->mmu_lock); mmu = vcpu->arch.hw_mmu; - kpte = kvm_pgtable_stage2_mkyoung(mmu->pgt, fault_ipa); - write_unlock(&vcpu->kvm->mmu_lock); + pte = kvm_pgtable_stage2_mkyoung(mmu->pgt, fault_ipa); + read_unlock(&vcpu->kvm->mmu_lock); - pte = __pte(kpte); - if (pte_valid(pte)) - kvm_set_pfn_accessed(pte_pfn(pte)); + if (kvm_pte_valid(pte)) + kvm_set_pfn_accessed(kvm_pte_to_pfn(pte)); } /** diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c new file mode 100644 index 000000000000..315354d27978 --- /dev/null +++ b/arch/arm64/kvm/nested.c @@ -0,0 +1,161 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2017 - Columbia University and Linaro Ltd. + * Author: Jintack Lim <jintack.lim@linaro.org> + */ + +#include <linux/kvm.h> +#include <linux/kvm_host.h> + +#include <asm/kvm_emulate.h> +#include <asm/kvm_nested.h> +#include <asm/sysreg.h> + +#include "sys_regs.h" + +/* Protection against the sysreg repainting madness... */ +#define NV_FTR(r, f) ID_AA64##r##_EL1_##f + +/* + * Our emulated CPU doesn't support all the possible features. For the + * sake of simplicity (and probably mental sanity), wipe out a number + * of feature bits we don't intend to support for the time being. + * This list should get updated as new features get added to the NV + * support, and new extension to the architecture. + */ +void access_nested_id_reg(struct kvm_vcpu *v, struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + u32 id = reg_to_encoding(r); + u64 val, tmp; + + val = p->regval; + + switch (id) { + case SYS_ID_AA64ISAR0_EL1: + /* Support everything but TME, O.S. and Range TLBIs */ + val &= ~(NV_FTR(ISAR0, TLB) | + NV_FTR(ISAR0, TME)); + break; + + case SYS_ID_AA64ISAR1_EL1: + /* Support everything but PtrAuth and Spec Invalidation */ + val &= ~(GENMASK_ULL(63, 56) | + NV_FTR(ISAR1, SPECRES) | + NV_FTR(ISAR1, GPI) | + NV_FTR(ISAR1, GPA) | + NV_FTR(ISAR1, API) | + NV_FTR(ISAR1, APA)); + break; + + case SYS_ID_AA64PFR0_EL1: + /* No AMU, MPAM, S-EL2, RAS or SVE */ + val &= ~(GENMASK_ULL(55, 52) | + NV_FTR(PFR0, AMU) | + NV_FTR(PFR0, MPAM) | + NV_FTR(PFR0, SEL2) | + NV_FTR(PFR0, RAS) | + NV_FTR(PFR0, SVE) | + NV_FTR(PFR0, EL3) | + NV_FTR(PFR0, EL2) | + NV_FTR(PFR0, EL1)); + /* 64bit EL1/EL2/EL3 only */ + val |= FIELD_PREP(NV_FTR(PFR0, EL1), 0b0001); + val |= FIELD_PREP(NV_FTR(PFR0, EL2), 0b0001); + val |= FIELD_PREP(NV_FTR(PFR0, EL3), 0b0001); + break; + + case SYS_ID_AA64PFR1_EL1: + /* Only support SSBS */ + val &= NV_FTR(PFR1, SSBS); + break; + + case SYS_ID_AA64MMFR0_EL1: + /* Hide ECV, FGT, ExS, Secure Memory */ + val &= ~(GENMASK_ULL(63, 43) | + NV_FTR(MMFR0, TGRAN4_2) | + NV_FTR(MMFR0, TGRAN16_2) | + NV_FTR(MMFR0, TGRAN64_2) | + NV_FTR(MMFR0, SNSMEM)); + + /* Disallow unsupported S2 page sizes */ + switch (PAGE_SIZE) { + case SZ_64K: + val |= FIELD_PREP(NV_FTR(MMFR0, TGRAN16_2), 0b0001); + fallthrough; + case SZ_16K: + val |= FIELD_PREP(NV_FTR(MMFR0, TGRAN4_2), 0b0001); + fallthrough; + case SZ_4K: + /* Support everything */ + break; + } + /* + * Since we can't support a guest S2 page size smaller than + * the host's own page size (due to KVM only populating its + * own S2 using the kernel's page size), advertise the + * limitation using FEAT_GTG. + */ + switch (PAGE_SIZE) { + case SZ_4K: + val |= FIELD_PREP(NV_FTR(MMFR0, TGRAN4_2), 0b0010); + fallthrough; + case SZ_16K: + val |= FIELD_PREP(NV_FTR(MMFR0, TGRAN16_2), 0b0010); + fallthrough; + case SZ_64K: + val |= FIELD_PREP(NV_FTR(MMFR0, TGRAN64_2), 0b0010); + break; + } + /* Cap PARange to 48bits */ + tmp = FIELD_GET(NV_FTR(MMFR0, PARANGE), val); + if (tmp > 0b0101) { + val &= ~NV_FTR(MMFR0, PARANGE); + val |= FIELD_PREP(NV_FTR(MMFR0, PARANGE), 0b0101); + } + break; + + case SYS_ID_AA64MMFR1_EL1: + val &= (NV_FTR(MMFR1, PAN) | + NV_FTR(MMFR1, LO) | + NV_FTR(MMFR1, HPDS) | + NV_FTR(MMFR1, VH) | + NV_FTR(MMFR1, VMIDBits)); + break; + + case SYS_ID_AA64MMFR2_EL1: + val &= ~(NV_FTR(MMFR2, EVT) | + NV_FTR(MMFR2, BBM) | + NV_FTR(MMFR2, TTL) | + GENMASK_ULL(47, 44) | + NV_FTR(MMFR2, ST) | + NV_FTR(MMFR2, CCIDX) | + NV_FTR(MMFR2, VARange)); + + /* Force TTL support */ + val |= FIELD_PREP(NV_FTR(MMFR2, TTL), 0b0001); + break; + + case SYS_ID_AA64DFR0_EL1: + /* Only limited support for PMU, Debug, BPs and WPs */ + val &= (NV_FTR(DFR0, PMUVer) | + NV_FTR(DFR0, WRPs) | + NV_FTR(DFR0, BRPs) | + NV_FTR(DFR0, DebugVer)); + + /* Cap Debug to ARMv8.1 */ + tmp = FIELD_GET(NV_FTR(DFR0, DebugVer), val); + if (tmp > 0b0111) { + val &= ~NV_FTR(DFR0, DebugVer); + val |= FIELD_PREP(NV_FTR(DFR0, DebugVer), 0b0111); + } + break; + + default: + /* Unknown register, just wipe it clean */ + val = 0; + break; + } + + p->regval = val; +} diff --git a/arch/arm64/kvm/pvtime.c b/arch/arm64/kvm/pvtime.c index 78a09f7a6637..4ceabaa4c30b 100644 --- a/arch/arm64/kvm/pvtime.c +++ b/arch/arm64/kvm/pvtime.c @@ -19,7 +19,7 @@ void kvm_update_stolen_time(struct kvm_vcpu *vcpu) u64 steal = 0; int idx; - if (base == GPA_INVALID) + if (base == INVALID_GPA) return; idx = srcu_read_lock(&kvm->srcu); @@ -40,7 +40,7 @@ long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu) switch (feature) { case ARM_SMCCC_HV_PV_TIME_FEATURES: case ARM_SMCCC_HV_PV_TIME_ST: - if (vcpu->arch.steal.base != GPA_INVALID) + if (vcpu->arch.steal.base != INVALID_GPA) val = SMCCC_RET_SUCCESS; break; } @@ -54,7 +54,7 @@ gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu) struct kvm *kvm = vcpu->kvm; u64 base = vcpu->arch.steal.base; - if (base == GPA_INVALID) + if (base == INVALID_GPA) return base; /* @@ -89,7 +89,7 @@ int kvm_arm_pvtime_set_attr(struct kvm_vcpu *vcpu, return -EFAULT; if (!IS_ALIGNED(ipa, 64)) return -EINVAL; - if (vcpu->arch.steal.base != GPA_INVALID) + if (vcpu->arch.steal.base != INVALID_GPA) return -EEXIST; /* Check the address is in a valid memslot */ diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index 2bc74739a6df..49a3257dec46 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -27,6 +27,7 @@ #include <asm/kvm_asm.h> #include <asm/kvm_emulate.h> #include <asm/kvm_mmu.h> +#include <asm/kvm_nested.h> #include <asm/virt.h> /* Maximum phys_shift supported for any VM on this host */ @@ -38,6 +39,9 @@ static u32 __ro_after_init kvm_ipa_limit; #define VCPU_RESET_PSTATE_EL1 (PSR_MODE_EL1h | PSR_A_BIT | PSR_I_BIT | \ PSR_F_BIT | PSR_D_BIT) +#define VCPU_RESET_PSTATE_EL2 (PSR_MODE_EL2h | PSR_A_BIT | PSR_I_BIT | \ + PSR_F_BIT | PSR_D_BIT) + #define VCPU_RESET_PSTATE_SVC (PSR_AA32_MODE_SVC | PSR_AA32_A_BIT | \ PSR_AA32_I_BIT | PSR_AA32_F_BIT) @@ -157,6 +161,7 @@ void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu) if (sve_state) kvm_unshare_hyp(sve_state, sve_state + vcpu_sve_state_size(vcpu)); kfree(sve_state); + kfree(vcpu->arch.ccsidr); } static void kvm_vcpu_reset_sve(struct kvm_vcpu *vcpu) @@ -220,6 +225,10 @@ static int kvm_set_vm_width(struct kvm_vcpu *vcpu) if (kvm_has_mte(kvm) && is32bit) return -EINVAL; + /* NV is incompatible with AArch32 */ + if (vcpu_has_nv(vcpu) && is32bit) + return -EINVAL; + if (is32bit) set_bit(KVM_ARCH_FLAG_EL1_32BIT, &kvm->arch.flags); @@ -272,6 +281,12 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) if (loaded) kvm_arch_vcpu_put(vcpu); + /* Disallow NV+SVE for the time being */ + if (vcpu_has_nv(vcpu) && vcpu_has_feature(vcpu, KVM_ARM_VCPU_SVE)) { + ret = -EINVAL; + goto out; + } + if (!kvm_arm_vcpu_sve_finalized(vcpu)) { if (test_bit(KVM_ARM_VCPU_SVE, vcpu->arch.features)) { ret = kvm_vcpu_enable_sve(vcpu); @@ -294,6 +309,8 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) default: if (vcpu_el1_is_32bit(vcpu)) { pstate = VCPU_RESET_PSTATE_SVC; + } else if (vcpu_has_nv(vcpu)) { + pstate = VCPU_RESET_PSTATE_EL2; } else { pstate = VCPU_RESET_PSTATE_EL1; } diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 46d161fe08d3..53749d3a0996 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -11,6 +11,7 @@ #include <linux/bitfield.h> #include <linux/bsearch.h> +#include <linux/cacheinfo.h> #include <linux/kvm_host.h> #include <linux/mm.h> #include <linux/printk.h> @@ -24,6 +25,7 @@ #include <asm/kvm_emulate.h> #include <asm/kvm_hyp.h> #include <asm/kvm_mmu.h> +#include <asm/kvm_nested.h> #include <asm/perf_event.h> #include <asm/sysreg.h> @@ -78,28 +80,112 @@ void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg) __vcpu_write_sys_reg_to_cpu(val, reg)) return; - __vcpu_sys_reg(vcpu, reg) = val; + __vcpu_sys_reg(vcpu, reg) = val; } -/* 3 bits per cache level, as per CLIDR, but non-existent caches always 0 */ -static u32 __ro_after_init cache_levels; - /* CSSELR values; used to index KVM_REG_ARM_DEMUX_ID_CCSIDR */ #define CSSELR_MAX 14 +/* + * Returns the minimum line size for the selected cache, expressed as + * Log2(bytes). + */ +static u8 get_min_cache_line_size(bool icache) +{ + u64 ctr = read_sanitised_ftr_reg(SYS_CTR_EL0); + u8 field; + + if (icache) + field = SYS_FIELD_GET(CTR_EL0, IminLine, ctr); + else + field = SYS_FIELD_GET(CTR_EL0, DminLine, ctr); + + /* + * Cache line size is represented as Log2(words) in CTR_EL0. + * Log2(bytes) can be derived with the following: + * + * Log2(words) + 2 = Log2(bytes / 4) + 2 + * = Log2(bytes) - 2 + 2 + * = Log2(bytes) + */ + return field + 2; +} + /* Which cache CCSIDR represents depends on CSSELR value. */ -static u32 get_ccsidr(u32 csselr) +static u32 get_ccsidr(struct kvm_vcpu *vcpu, u32 csselr) { - u32 ccsidr; + u8 line_size; - /* Make sure noone else changes CSSELR during this! */ - local_irq_disable(); - write_sysreg(csselr, csselr_el1); - isb(); - ccsidr = read_sysreg(ccsidr_el1); - local_irq_enable(); + if (vcpu->arch.ccsidr) + return vcpu->arch.ccsidr[csselr]; - return ccsidr; + line_size = get_min_cache_line_size(csselr & CSSELR_EL1_InD); + + /* + * Fabricate a CCSIDR value as the overriding value does not exist. + * The real CCSIDR value will not be used as it can vary by the + * physical CPU which the vcpu currently resides in. + * + * The line size is determined with get_min_cache_line_size(), which + * should be valid for all CPUs even if they have different cache + * configuration. + * + * The associativity bits are cleared, meaning the geometry of all data + * and unified caches (which are guaranteed to be PIPT and thus + * non-aliasing) are 1 set and 1 way. + * Guests should not be doing cache operations by set/way at all, and + * for this reason, we trap them and attempt to infer the intent, so + * that we can flush the entire guest's address space at the appropriate + * time. The exposed geometry minimizes the number of the traps. + * [If guests should attempt to infer aliasing properties from the + * geometry (which is not permitted by the architecture), they would + * only do so for virtually indexed caches.] + * + * We don't check if the cache level exists as it is allowed to return + * an UNKNOWN value if not. + */ + return SYS_FIELD_PREP(CCSIDR_EL1, LineSize, line_size - 4); +} + +static int set_ccsidr(struct kvm_vcpu *vcpu, u32 csselr, u32 val) +{ + u8 line_size = FIELD_GET(CCSIDR_EL1_LineSize, val) + 4; + u32 *ccsidr = vcpu->arch.ccsidr; + u32 i; + + if ((val & CCSIDR_EL1_RES0) || + line_size < get_min_cache_line_size(csselr & CSSELR_EL1_InD)) + return -EINVAL; + + if (!ccsidr) { + if (val == get_ccsidr(vcpu, csselr)) + return 0; + + ccsidr = kmalloc_array(CSSELR_MAX, sizeof(u32), GFP_KERNEL_ACCOUNT); + if (!ccsidr) + return -ENOMEM; + + for (i = 0; i < CSSELR_MAX; i++) + ccsidr[i] = get_ccsidr(vcpu, i); + + vcpu->arch.ccsidr = ccsidr; + } + + ccsidr[csselr] = val; + + return 0; +} + +static bool access_rw(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + if (p->is_write) + vcpu_write_sys_reg(vcpu, p->regval, r->reg); + else + p->regval = vcpu_read_sys_reg(vcpu, r->reg); + + return true; } /* @@ -260,6 +346,14 @@ static bool trap_raz_wi(struct kvm_vcpu *vcpu, return read_zero(vcpu, p); } +static bool trap_undef(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + kvm_inject_undefined(vcpu); + return false; +} + /* * ARMv8.1 mandates at least a trivial LORegion implementation, where all the * RW registers are RES0 (which we can implement as RAZ/WI). On an ARMv8.0 @@ -370,12 +464,9 @@ static bool trap_debug_regs(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { - if (p->is_write) { - vcpu_write_sys_reg(vcpu, p->regval, r->reg); + access_rw(vcpu, p, r); + if (p->is_write) vcpu_set_flag(vcpu, DEBUG_DIRTY); - } else { - p->regval = vcpu_read_sys_reg(vcpu, r->reg); - } trace_trap_reg(__func__, r->reg, p->is_write, p->regval); @@ -1049,7 +1140,9 @@ static bool access_arch_timer(struct kvm_vcpu *vcpu, treg = TIMER_REG_CVAL; break; default: - BUG(); + print_sys_reg_msg(p, "%s", "Unhandled trapped timer register"); + kvm_inject_undefined(vcpu); + return false; } if (p->is_write) @@ -1155,6 +1248,12 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu, struct sys_reg_desc const *r val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_DFR0_EL1_PerfMon), pmuver_to_perfmon(vcpu_pmuver(vcpu))); break; + case SYS_ID_AA64MMFR2_EL1: + val &= ~ID_AA64MMFR2_EL1_CCIDX_MASK; + break; + case SYS_ID_MMFR4_EL1: + val &= ~ARM64_FEATURE_MASK(ID_MMFR4_EL1_CCIDX); + break; } return val; @@ -1205,6 +1304,9 @@ static bool access_id_reg(struct kvm_vcpu *vcpu, return write_to_read_only(vcpu, p, r); p->regval = read_id_reg(vcpu, r); + if (vcpu_has_nv(vcpu)) + access_nested_id_reg(vcpu, p, r); + return true; } @@ -1385,10 +1487,78 @@ static bool access_clidr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, if (p->is_write) return write_to_read_only(vcpu, p, r); - p->regval = read_sysreg(clidr_el1); + p->regval = __vcpu_sys_reg(vcpu, r->reg); return true; } +/* + * Fabricate a CLIDR_EL1 value instead of using the real value, which can vary + * by the physical CPU which the vcpu currently resides in. + */ +static void reset_clidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) +{ + u64 ctr_el0 = read_sanitised_ftr_reg(SYS_CTR_EL0); + u64 clidr; + u8 loc; + + if ((ctr_el0 & CTR_EL0_IDC)) { + /* + * Data cache clean to the PoU is not required so LoUU and LoUIS + * will not be set and a unified cache, which will be marked as + * LoC, will be added. + * + * If not DIC, let the unified cache L2 so that an instruction + * cache can be added as L1 later. + */ + loc = (ctr_el0 & CTR_EL0_DIC) ? 1 : 2; + clidr = CACHE_TYPE_UNIFIED << CLIDR_CTYPE_SHIFT(loc); + } else { + /* + * Data cache clean to the PoU is required so let L1 have a data + * cache and mark it as LoUU and LoUIS. As L1 has a data cache, + * it can be marked as LoC too. + */ + loc = 1; + clidr = 1 << CLIDR_LOUU_SHIFT; + clidr |= 1 << CLIDR_LOUIS_SHIFT; + clidr |= CACHE_TYPE_DATA << CLIDR_CTYPE_SHIFT(1); + } + + /* + * Instruction cache invalidation to the PoU is required so let L1 have + * an instruction cache. If L1 already has a data cache, it will be + * CACHE_TYPE_SEPARATE. + */ + if (!(ctr_el0 & CTR_EL0_DIC)) + clidr |= CACHE_TYPE_INST << CLIDR_CTYPE_SHIFT(1); + + clidr |= loc << CLIDR_LOC_SHIFT; + + /* + * Add tag cache unified to data cache. Allocation tags and data are + * unified in a cache line so that it looks valid even if there is only + * one cache line. + */ + if (kvm_has_mte(vcpu->kvm)) + clidr |= 2 << CLIDR_TTYPE_SHIFT(loc); + + __vcpu_sys_reg(vcpu, r->reg) = clidr; +} + +static int set_clidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, + u64 val) +{ + u64 ctr_el0 = read_sanitised_ftr_reg(SYS_CTR_EL0); + u64 idc = !CLIDR_LOC(val) || (!CLIDR_LOUIS(val) && !CLIDR_LOUU(val)); + + if ((val & CLIDR_EL1_RES0) || (!(ctr_el0 & CTR_EL0_IDC) && idc)) + return -EINVAL; + + __vcpu_sys_reg(vcpu, rd->reg) = val; + + return 0; +} + static bool access_csselr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { @@ -1410,22 +1580,10 @@ static bool access_ccsidr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, return write_to_read_only(vcpu, p, r); csselr = vcpu_read_sys_reg(vcpu, CSSELR_EL1); - p->regval = get_ccsidr(csselr); + csselr &= CSSELR_EL1_Level | CSSELR_EL1_InD; + if (csselr < CSSELR_MAX) + p->regval = get_ccsidr(vcpu, csselr); - /* - * Guests should not be doing cache operations by set/way at all, and - * for this reason, we trap them and attempt to infer the intent, so - * that we can flush the entire guest's address space at the appropriate - * time. - * To prevent this trapping from causing performance problems, let's - * expose the geometry of all data and unified caches (which are - * guaranteed to be PIPT and thus non-aliasing) as 1 set and 1 way. - * [If guests should attempt to infer aliasing properties from the - * geometry (which is not permitted by the architecture), they would - * only do so for virtually indexed caches.] - */ - if (!(csselr & 1)) // data or unified cache - p->regval &= ~GENMASK(27, 3); return true; } @@ -1446,6 +1604,44 @@ static unsigned int mte_visibility(const struct kvm_vcpu *vcpu, .visibility = mte_visibility, \ } +static unsigned int el2_visibility(const struct kvm_vcpu *vcpu, + const struct sys_reg_desc *rd) +{ + if (vcpu_has_nv(vcpu)) + return 0; + + return REG_HIDDEN; +} + +#define EL2_REG(name, acc, rst, v) { \ + SYS_DESC(SYS_##name), \ + .access = acc, \ + .reset = rst, \ + .reg = name, \ + .visibility = el2_visibility, \ + .val = v, \ +} + +/* + * EL{0,1}2 registers are the EL2 view on an EL0 or EL1 register when + * HCR_EL2.E2H==1, and only in the sysreg table for convenience of + * handling traps. Given that, they are always hidden from userspace. + */ +static unsigned int elx2_visibility(const struct kvm_vcpu *vcpu, + const struct sys_reg_desc *rd) +{ + return REG_HIDDEN_USER; +} + +#define EL12_REG(name, acc, rst, v) { \ + SYS_DESC(SYS_##name##_EL12), \ + .access = acc, \ + .reset = rst, \ + .reg = name##_EL1, \ + .val = v, \ + .visibility = elx2_visibility, \ +} + /* sys_reg_desc initialiser for known cpufeature ID registers */ #define ID_SANITISED(name) { \ SYS_DESC(SYS_##name), \ @@ -1490,6 +1686,42 @@ static unsigned int mte_visibility(const struct kvm_vcpu *vcpu, .visibility = raz_visibility, \ } +static bool access_sp_el1(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + if (p->is_write) + __vcpu_sys_reg(vcpu, SP_EL1) = p->regval; + else + p->regval = __vcpu_sys_reg(vcpu, SP_EL1); + + return true; +} + +static bool access_elr(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + if (p->is_write) + vcpu_write_sys_reg(vcpu, p->regval, ELR_EL1); + else + p->regval = vcpu_read_sys_reg(vcpu, ELR_EL1); + + return true; +} + +static bool access_spsr(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + if (p->is_write) + __vcpu_sys_reg(vcpu, SPSR_EL1) = p->regval; + else + p->regval = __vcpu_sys_reg(vcpu, SPSR_EL1); + + return true; +} + /* * Architected system registers. * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2 @@ -1646,6 +1878,9 @@ static const struct sys_reg_desc sys_reg_descs[] = { PTRAUTH_KEY(APDB), PTRAUTH_KEY(APGA), + { SYS_DESC(SYS_SPSR_EL1), access_spsr}, + { SYS_DESC(SYS_ELR_EL1), access_elr}, + { SYS_DESC(SYS_AFSR0_EL1), access_vm_reg, reset_unknown, AFSR0_EL1 }, { SYS_DESC(SYS_AFSR1_EL1), access_vm_reg, reset_unknown, AFSR1_EL1 }, { SYS_DESC(SYS_ESR_EL1), access_vm_reg, reset_unknown, ESR_EL1 }, @@ -1693,7 +1928,7 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_LORC_EL1), trap_loregion }, { SYS_DESC(SYS_LORID_EL1), trap_loregion }, - { SYS_DESC(SYS_VBAR_EL1), NULL, reset_val, VBAR_EL1, 0 }, + { SYS_DESC(SYS_VBAR_EL1), access_rw, reset_val, VBAR_EL1, 0 }, { SYS_DESC(SYS_DISR_EL1), NULL, reset_val, DISR_EL1, 0 }, { SYS_DESC(SYS_ICC_IAR0_EL1), write_to_read_only }, @@ -1717,7 +1952,9 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_CNTKCTL_EL1), NULL, reset_val, CNTKCTL_EL1, 0}, { SYS_DESC(SYS_CCSIDR_EL1), access_ccsidr }, - { SYS_DESC(SYS_CLIDR_EL1), access_clidr }, + { SYS_DESC(SYS_CLIDR_EL1), access_clidr, reset_clidr, CLIDR_EL1, + .set_user = set_clidr }, + { SYS_DESC(SYS_CCSIDR2_EL1), undef_access }, { SYS_DESC(SYS_SMIDR_EL1), undef_access }, { SYS_DESC(SYS_CSSELR_EL1), access_csselr, reset_unknown, CSSELR_EL1 }, { SYS_DESC(SYS_CTR_EL0), access_ctr }, @@ -1913,9 +2150,67 @@ static const struct sys_reg_desc sys_reg_descs[] = { { PMU_SYS_REG(SYS_PMCCFILTR_EL0), .access = access_pmu_evtyper, .reset = reset_val, .reg = PMCCFILTR_EL0, .val = 0 }, + EL2_REG(VPIDR_EL2, access_rw, reset_unknown, 0), + EL2_REG(VMPIDR_EL2, access_rw, reset_unknown, 0), + EL2_REG(SCTLR_EL2, access_rw, reset_val, SCTLR_EL2_RES1), + EL2_REG(ACTLR_EL2, access_rw, reset_val, 0), + EL2_REG(HCR_EL2, access_rw, reset_val, 0), + EL2_REG(MDCR_EL2, access_rw, reset_val, 0), + EL2_REG(CPTR_EL2, access_rw, reset_val, CPTR_EL2_DEFAULT ), + EL2_REG(HSTR_EL2, access_rw, reset_val, 0), + EL2_REG(HACR_EL2, access_rw, reset_val, 0), + + EL2_REG(TTBR0_EL2, access_rw, reset_val, 0), + EL2_REG(TTBR1_EL2, access_rw, reset_val, 0), + EL2_REG(TCR_EL2, access_rw, reset_val, TCR_EL2_RES1), + EL2_REG(VTTBR_EL2, access_rw, reset_val, 0), + EL2_REG(VTCR_EL2, access_rw, reset_val, 0), + { SYS_DESC(SYS_DACR32_EL2), NULL, reset_unknown, DACR32_EL2 }, + EL2_REG(SPSR_EL2, access_rw, reset_val, 0), + EL2_REG(ELR_EL2, access_rw, reset_val, 0), + { SYS_DESC(SYS_SP_EL1), access_sp_el1}, + { SYS_DESC(SYS_IFSR32_EL2), NULL, reset_unknown, IFSR32_EL2 }, + EL2_REG(AFSR0_EL2, access_rw, reset_val, 0), + EL2_REG(AFSR1_EL2, access_rw, reset_val, 0), + EL2_REG(ESR_EL2, access_rw, reset_val, 0), { SYS_DESC(SYS_FPEXC32_EL2), NULL, reset_val, FPEXC32_EL2, 0x700 }, + + EL2_REG(FAR_EL2, access_rw, reset_val, 0), + EL2_REG(HPFAR_EL2, access_rw, reset_val, 0), + + EL2_REG(MAIR_EL2, access_rw, reset_val, 0), + EL2_REG(AMAIR_EL2, access_rw, reset_val, 0), + + EL2_REG(VBAR_EL2, access_rw, reset_val, 0), + EL2_REG(RVBAR_EL2, access_rw, reset_val, 0), + { SYS_DESC(SYS_RMR_EL2), trap_undef }, + + EL2_REG(CONTEXTIDR_EL2, access_rw, reset_val, 0), + EL2_REG(TPIDR_EL2, access_rw, reset_val, 0), + + EL2_REG(CNTVOFF_EL2, access_rw, reset_val, 0), + EL2_REG(CNTHCTL_EL2, access_rw, reset_val, 0), + + EL12_REG(SCTLR, access_vm_reg, reset_val, 0x00C50078), + EL12_REG(CPACR, access_rw, reset_val, 0), + EL12_REG(TTBR0, access_vm_reg, reset_unknown, 0), + EL12_REG(TTBR1, access_vm_reg, reset_unknown, 0), + EL12_REG(TCR, access_vm_reg, reset_val, 0), + { SYS_DESC(SYS_SPSR_EL12), access_spsr}, + { SYS_DESC(SYS_ELR_EL12), access_elr}, + EL12_REG(AFSR0, access_vm_reg, reset_unknown, 0), + EL12_REG(AFSR1, access_vm_reg, reset_unknown, 0), + EL12_REG(ESR, access_vm_reg, reset_unknown, 0), + EL12_REG(FAR, access_vm_reg, reset_unknown, 0), + EL12_REG(MAIR, access_vm_reg, reset_unknown, 0), + EL12_REG(AMAIR, access_vm_reg, reset_amair_el1, 0), + EL12_REG(VBAR, access_rw, reset_val, 0), + EL12_REG(CONTEXTIDR, access_vm_reg, reset_val, 0), + EL12_REG(CNTKCTL, access_rw, reset_val, 0), + + EL2_REG(SP_EL2, NULL, reset_unknown, 0), }; static bool trap_dbgdidr(struct kvm_vcpu *vcpu, @@ -2219,6 +2514,10 @@ static const struct sys_reg_desc cp15_regs[] = { { Op1(1), CRn( 0), CRm( 0), Op2(0), access_ccsidr }, { Op1(1), CRn( 0), CRm( 0), Op2(1), access_clidr }, + + /* CCSIDR2 */ + { Op1(1), CRn( 0), CRm( 0), Op2(2), undef_access }, + { Op1(2), CRn( 0), CRm( 0), Op2(0), access_csselr, NULL, CSSELR_EL1 }, }; @@ -2724,7 +3023,6 @@ id_to_sys_reg_desc(struct kvm_vcpu *vcpu, u64 id, FUNCTION_INVARIANT(midr_el1) FUNCTION_INVARIANT(revidr_el1) -FUNCTION_INVARIANT(clidr_el1) FUNCTION_INVARIANT(aidr_el1) static void get_ctr_el0(struct kvm_vcpu *v, const struct sys_reg_desc *r) @@ -2736,7 +3034,6 @@ static void get_ctr_el0(struct kvm_vcpu *v, const struct sys_reg_desc *r) static struct sys_reg_desc invariant_sys_regs[] __ro_after_init = { { SYS_DESC(SYS_MIDR_EL1), NULL, get_midr_el1 }, { SYS_DESC(SYS_REVIDR_EL1), NULL, get_revidr_el1 }, - { SYS_DESC(SYS_CLIDR_EL1), NULL, get_clidr_el1 }, { SYS_DESC(SYS_AIDR_EL1), NULL, get_aidr_el1 }, { SYS_DESC(SYS_CTR_EL0), NULL, get_ctr_el0 }, }; @@ -2773,33 +3070,7 @@ static int set_invariant_sys_reg(u64 id, u64 __user *uaddr) return 0; } -static bool is_valid_cache(u32 val) -{ - u32 level, ctype; - - if (val >= CSSELR_MAX) - return false; - - /* Bottom bit is Instruction or Data bit. Next 3 bits are level. */ - level = (val >> 1); - ctype = (cache_levels >> (level * 3)) & 7; - - switch (ctype) { - case 0: /* No cache */ - return false; - case 1: /* Instruction cache only */ - return (val & 1); - case 2: /* Data cache only */ - case 4: /* Unified cache */ - return !(val & 1); - case 3: /* Separate instruction and data caches */ - return true; - default: /* Reserved: we can't know instruction or data. */ - return false; - } -} - -static int demux_c15_get(u64 id, void __user *uaddr) +static int demux_c15_get(struct kvm_vcpu *vcpu, u64 id, void __user *uaddr) { u32 val; u32 __user *uval = uaddr; @@ -2815,16 +3086,16 @@ static int demux_c15_get(u64 id, void __user *uaddr) return -ENOENT; val = (id & KVM_REG_ARM_DEMUX_VAL_MASK) >> KVM_REG_ARM_DEMUX_VAL_SHIFT; - if (!is_valid_cache(val)) + if (val >= CSSELR_MAX) return -ENOENT; - return put_user(get_ccsidr(val), uval); + return put_user(get_ccsidr(vcpu, val), uval); default: return -ENOENT; } } -static int demux_c15_set(u64 id, void __user *uaddr) +static int demux_c15_set(struct kvm_vcpu *vcpu, u64 id, void __user *uaddr) { u32 val, newval; u32 __user *uval = uaddr; @@ -2840,16 +3111,13 @@ static int demux_c15_set(u64 id, void __user *uaddr) return -ENOENT; val = (id & KVM_REG_ARM_DEMUX_VAL_MASK) >> KVM_REG_ARM_DEMUX_VAL_SHIFT; - if (!is_valid_cache(val)) + if (val >= CSSELR_MAX) return -ENOENT; if (get_user(newval, uval)) return -EFAULT; - /* This is also invariant: you can't change it. */ - if (newval != get_ccsidr(val)) - return -EINVAL; - return 0; + return set_ccsidr(vcpu, val, newval); default: return -ENOENT; } @@ -2864,7 +3132,7 @@ int kvm_sys_reg_get_user(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg, int ret; r = id_to_sys_reg_desc(vcpu, reg->id, table, num); - if (!r) + if (!r || sysreg_hidden_user(vcpu, r)) return -ENOENT; if (r->get_user) { @@ -2886,7 +3154,7 @@ int kvm_arm_sys_reg_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg int err; if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_DEMUX) - return demux_c15_get(reg->id, uaddr); + return demux_c15_get(vcpu, reg->id, uaddr); err = get_invariant_sys_reg(reg->id, uaddr); if (err != -ENOENT) @@ -2908,7 +3176,7 @@ int kvm_sys_reg_set_user(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg, return -EFAULT; r = id_to_sys_reg_desc(vcpu, reg->id, table, num); - if (!r) + if (!r || sysreg_hidden_user(vcpu, r)) return -ENOENT; if (sysreg_user_write_ignore(vcpu, r)) @@ -2930,7 +3198,7 @@ int kvm_arm_sys_reg_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg int err; if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_DEMUX) - return demux_c15_set(reg->id, uaddr); + return demux_c15_set(vcpu, reg->id, uaddr); err = set_invariant_sys_reg(reg->id, uaddr); if (err != -ENOENT) @@ -2942,13 +3210,7 @@ int kvm_arm_sys_reg_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg static unsigned int num_demux_regs(void) { - unsigned int i, count = 0; - - for (i = 0; i < CSSELR_MAX; i++) - if (is_valid_cache(i)) - count++; - - return count; + return CSSELR_MAX; } static int write_demux_regids(u64 __user *uindices) @@ -2958,8 +3220,6 @@ static int write_demux_regids(u64 __user *uindices) val |= KVM_REG_ARM_DEMUX_ID_CCSIDR; for (i = 0; i < CSSELR_MAX; i++) { - if (!is_valid_cache(i)) - continue; if (put_user(val | i, uindices)) return -EFAULT; uindices++; @@ -3002,7 +3262,7 @@ static int walk_one_sys_reg(const struct kvm_vcpu *vcpu, if (!(rd->reg || rd->get_user)) return 0; - if (sysreg_hidden(vcpu, rd)) + if (sysreg_hidden_user(vcpu, rd)) return 0; if (!copy_reg_to_user(rd, uind)) @@ -3061,7 +3321,6 @@ int __init kvm_sys_reg_table_init(void) { bool valid = true; unsigned int i; - struct sys_reg_desc clidr; /* Make sure tables are unique and in order. */ valid &= check_sysreg_table(sys_reg_descs, ARRAY_SIZE(sys_reg_descs), false); @@ -3078,23 +3337,5 @@ int __init kvm_sys_reg_table_init(void) for (i = 0; i < ARRAY_SIZE(invariant_sys_regs); i++) invariant_sys_regs[i].reset(NULL, &invariant_sys_regs[i]); - /* - * CLIDR format is awkward, so clean it up. See ARM B4.1.20: - * - * If software reads the Cache Type fields from Ctype1 - * upwards, once it has seen a value of 0b000, no caches - * exist at further-out levels of the hierarchy. So, for - * example, if Ctype3 is the first Cache Type field with a - * value of 0b000, the values of Ctype4 to Ctype7 must be - * ignored. - */ - get_clidr_el1(NULL, &clidr); /* Ugly... */ - cache_levels = clidr.val; - for (i = 0; i < 7; i++) - if (((cache_levels >> (i*3)) & 7) == 0) - break; - /* Clear all higher bits. */ - cache_levels &= (1 << (i*3))-1; - return 0; } diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h index e4ebb3a379fd..6b11f2cc7146 100644 --- a/arch/arm64/kvm/sys_regs.h +++ b/arch/arm64/kvm/sys_regs.h @@ -85,8 +85,9 @@ struct sys_reg_desc { }; #define REG_HIDDEN (1 << 0) /* hidden from userspace and guest */ -#define REG_RAZ (1 << 1) /* RAZ from userspace and guest */ -#define REG_USER_WI (1 << 2) /* WI from userspace only */ +#define REG_HIDDEN_USER (1 << 1) /* hidden from userspace only */ +#define REG_RAZ (1 << 2) /* RAZ from userspace and guest */ +#define REG_USER_WI (1 << 3) /* WI from userspace only */ static __printf(2, 3) inline void print_sys_reg_msg(const struct sys_reg_params *p, @@ -152,6 +153,15 @@ static inline bool sysreg_hidden(const struct kvm_vcpu *vcpu, return sysreg_visibility(vcpu, r) & REG_HIDDEN; } +static inline bool sysreg_hidden_user(const struct kvm_vcpu *vcpu, + const struct sys_reg_desc *r) +{ + if (likely(!r->visibility)) + return false; + + return r->visibility(vcpu, r) & (REG_HIDDEN | REG_HIDDEN_USER); +} + static inline bool sysreg_visible_as_raz(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { diff --git a/arch/arm64/kvm/trace_arm.h b/arch/arm64/kvm/trace_arm.h index 33e4e7dd2719..f3e46a976125 100644 --- a/arch/arm64/kvm/trace_arm.h +++ b/arch/arm64/kvm/trace_arm.h @@ -2,6 +2,7 @@ #if !defined(_TRACE_ARM_ARM64_KVM_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_ARM_ARM64_KVM_H +#include <asm/kvm_emulate.h> #include <kvm/arm_arch_timer.h> #include <linux/tracepoint.h> @@ -301,6 +302,64 @@ TRACE_EVENT(kvm_timer_emulate, __entry->timer_idx, __entry->should_fire) ); +TRACE_EVENT(kvm_nested_eret, + TP_PROTO(struct kvm_vcpu *vcpu, unsigned long elr_el2, + unsigned long spsr_el2), + TP_ARGS(vcpu, elr_el2, spsr_el2), + + TP_STRUCT__entry( + __field(struct kvm_vcpu *, vcpu) + __field(unsigned long, elr_el2) + __field(unsigned long, spsr_el2) + __field(unsigned long, target_mode) + __field(unsigned long, hcr_el2) + ), + + TP_fast_assign( + __entry->vcpu = vcpu; + __entry->elr_el2 = elr_el2; + __entry->spsr_el2 = spsr_el2; + __entry->target_mode = spsr_el2 & (PSR_MODE_MASK | PSR_MODE32_BIT); + __entry->hcr_el2 = __vcpu_sys_reg(vcpu, HCR_EL2); + ), + + TP_printk("elr_el2: 0x%lx spsr_el2: 0x%08lx (M: %s) hcr_el2: %lx", + __entry->elr_el2, __entry->spsr_el2, + __print_symbolic(__entry->target_mode, kvm_mode_names), + __entry->hcr_el2) +); + +TRACE_EVENT(kvm_inject_nested_exception, + TP_PROTO(struct kvm_vcpu *vcpu, u64 esr_el2, int type), + TP_ARGS(vcpu, esr_el2, type), + + TP_STRUCT__entry( + __field(struct kvm_vcpu *, vcpu) + __field(unsigned long, esr_el2) + __field(int, type) + __field(unsigned long, spsr_el2) + __field(unsigned long, pc) + __field(unsigned long, source_mode) + __field(unsigned long, hcr_el2) + ), + + TP_fast_assign( + __entry->vcpu = vcpu; + __entry->esr_el2 = esr_el2; + __entry->type = type; + __entry->spsr_el2 = *vcpu_cpsr(vcpu); + __entry->pc = *vcpu_pc(vcpu); + __entry->source_mode = *vcpu_cpsr(vcpu) & (PSR_MODE_MASK | PSR_MODE32_BIT); + __entry->hcr_el2 = __vcpu_sys_reg(vcpu, HCR_EL2); + ), + + TP_printk("%s: esr_el2 0x%lx elr_el2: 0x%lx spsr_el2: 0x%08lx (M: %s) hcr_el2: %lx", + __print_symbolic(__entry->type, kvm_exception_type_names), + __entry->esr_el2, __entry->pc, __entry->spsr_el2, + __print_symbolic(__entry->source_mode, kvm_mode_names), + __entry->hcr_el2) +); + #endif /* _TRACE_ARM_ARM64_KVM_H */ #undef TRACE_INCLUDE_PATH diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index 6c7f6ae21ec0..cd134db41a57 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -570,7 +570,7 @@ int kvm_vgic_hyp_init(void) if (ret) return ret; - if (!has_mask) + if (!has_mask && !kvm_vgic_global_state.maint_irq) return 0; ret = request_percpu_irq(kvm_vgic_global_state.maint_irq, diff --git a/arch/arm64/kvm/vgic/vgic-mmio.c b/arch/arm64/kvm/vgic/vgic-mmio.c index b32d434c1d4a..e67b3b2c8044 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio.c +++ b/arch/arm64/kvm/vgic/vgic-mmio.c @@ -473,9 +473,10 @@ int vgic_uaccess_write_cpending(struct kvm_vcpu *vcpu, * active state can be overwritten when the VCPU's state is synced coming back * from the guest. * - * For shared interrupts as well as GICv3 private interrupts, we have to - * stop all the VCPUs because interrupts can be migrated while we don't hold - * the IRQ locks and we don't want to be chasing moving targets. + * For shared interrupts as well as GICv3 private interrupts accessed from the + * non-owning CPU, we have to stop all the VCPUs because interrupts can be + * migrated while we don't hold the IRQ locks and we don't want to be chasing + * moving targets. * * For GICv2 private interrupts we don't have to do anything because * userspace accesses to the VGIC state already require all VCPUs to be @@ -484,7 +485,8 @@ int vgic_uaccess_write_cpending(struct kvm_vcpu *vcpu, */ static void vgic_access_active_prepare(struct kvm_vcpu *vcpu, u32 intid) { - if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 || + if ((vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 && + vcpu != kvm_get_running_vcpu()) || intid >= VGIC_NR_PRIVATE_IRQS) kvm_arm_halt_guest(vcpu->kvm); } @@ -492,7 +494,8 @@ static void vgic_access_active_prepare(struct kvm_vcpu *vcpu, u32 intid) /* See vgic_access_active_prepare */ static void vgic_access_active_finish(struct kvm_vcpu *vcpu, u32 intid) { - if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 || + if ((vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 && + vcpu != kvm_get_running_vcpu()) || intid >= VGIC_NR_PRIVATE_IRQS) kvm_arm_resume_guest(vcpu->kvm); } diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c index 684bdfaad4a9..469d816f356f 100644 --- a/arch/arm64/kvm/vgic/vgic-v3.c +++ b/arch/arm64/kvm/vgic/vgic-v3.c @@ -3,6 +3,7 @@ #include <linux/irqchip/arm-gic-v3.h> #include <linux/irq.h> #include <linux/irqdomain.h> +#include <linux/kstrtox.h> #include <linux/kvm.h> #include <linux/kvm_host.h> #include <kvm/arm_vgic.h> @@ -584,25 +585,25 @@ DEFINE_STATIC_KEY_FALSE(vgic_v3_cpuif_trap); static int __init early_group0_trap_cfg(char *buf) { - return strtobool(buf, &group0_trap); + return kstrtobool(buf, &group0_trap); } early_param("kvm-arm.vgic_v3_group0_trap", early_group0_trap_cfg); static int __init early_group1_trap_cfg(char *buf) { - return strtobool(buf, &group1_trap); + return kstrtobool(buf, &group1_trap); } early_param("kvm-arm.vgic_v3_group1_trap", early_group1_trap_cfg); static int __init early_common_trap_cfg(char *buf) { - return strtobool(buf, &common_trap); + return kstrtobool(buf, &common_trap); } early_param("kvm-arm.vgic_v3_common_trap", early_common_trap_cfg); static int __init early_gicv4_enable(char *buf) { - return strtobool(buf, &gicv4_enable); + return kstrtobool(buf, &gicv4_enable); } early_param("kvm-arm.vgic_v4_enable", early_gicv4_enable); |