From 9ed24f4b712b855dcf7be3025b75b051cb73a2b7 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 13 May 2020 11:40:34 +0100 Subject: KVM: arm64: Move virt/kvm/arm to arch/arm64 Now that the 32bit KVM/arm host is a distant memory, let's move the whole of the KVM/arm64 code into the arm64 tree. As they said in the song: Welcome Home (Sanitarium). Signed-off-by: Marc Zyngier Acked-by: Will Deacon Link: https://lore.kernel.org/r/20200513104034.74741-1-maz@kernel.org --- virt/kvm/arm/aarch32.c | 204 --- virt/kvm/arm/arch_timer.c | 1180 --------------- virt/kvm/arm/arm.c | 1681 --------------------- virt/kvm/arm/hyp/aarch32.c | 140 -- virt/kvm/arm/hyp/timer-sr.c | 49 - virt/kvm/arm/hyp/vgic-v3-sr.c | 1130 -------------- virt/kvm/arm/hypercalls.c | 71 - virt/kvm/arm/mmio.c | 200 --- virt/kvm/arm/mmu.c | 2447 ------------------------------ virt/kvm/arm/perf.c | 57 - virt/kvm/arm/pmu.c | 869 ----------- virt/kvm/arm/psci.c | 564 ------- virt/kvm/arm/pvtime.c | 131 -- virt/kvm/arm/trace.h | 379 ----- virt/kvm/arm/vgic/trace.h | 38 - virt/kvm/arm/vgic/vgic-debug.c | 300 ---- virt/kvm/arm/vgic/vgic-init.c | 556 ------- virt/kvm/arm/vgic/vgic-irqfd.c | 141 -- virt/kvm/arm/vgic/vgic-its.c | 2783 ----------------------------------- virt/kvm/arm/vgic/vgic-kvm-device.c | 741 ---------- virt/kvm/arm/vgic/vgic-mmio-v2.c | 550 ------- virt/kvm/arm/vgic/vgic-mmio-v3.c | 1063 ------------- virt/kvm/arm/vgic/vgic-mmio.c | 1088 -------------- virt/kvm/arm/vgic/vgic-mmio.h | 227 --- virt/kvm/arm/vgic/vgic-v2.c | 504 ------- virt/kvm/arm/vgic/vgic-v3.c | 693 --------- virt/kvm/arm/vgic/vgic-v4.c | 453 ------ virt/kvm/arm/vgic/vgic.c | 1011 ------------- virt/kvm/arm/vgic/vgic.h | 321 ---- 29 files changed, 19571 deletions(-) delete mode 100644 virt/kvm/arm/aarch32.c delete mode 100644 virt/kvm/arm/arch_timer.c delete mode 100644 virt/kvm/arm/arm.c delete mode 100644 virt/kvm/arm/hyp/aarch32.c delete mode 100644 virt/kvm/arm/hyp/timer-sr.c delete mode 100644 virt/kvm/arm/hyp/vgic-v3-sr.c delete mode 100644 virt/kvm/arm/hypercalls.c delete mode 100644 virt/kvm/arm/mmio.c delete mode 100644 virt/kvm/arm/mmu.c delete mode 100644 virt/kvm/arm/perf.c delete mode 100644 virt/kvm/arm/pmu.c delete mode 100644 virt/kvm/arm/psci.c delete mode 100644 virt/kvm/arm/pvtime.c delete mode 100644 virt/kvm/arm/trace.h delete mode 100644 virt/kvm/arm/vgic/trace.h delete mode 100644 virt/kvm/arm/vgic/vgic-debug.c delete mode 100644 virt/kvm/arm/vgic/vgic-init.c delete mode 100644 virt/kvm/arm/vgic/vgic-irqfd.c delete mode 100644 virt/kvm/arm/vgic/vgic-its.c delete mode 100644 virt/kvm/arm/vgic/vgic-kvm-device.c delete mode 100644 virt/kvm/arm/vgic/vgic-mmio-v2.c delete mode 100644 virt/kvm/arm/vgic/vgic-mmio-v3.c delete mode 100644 virt/kvm/arm/vgic/vgic-mmio.c delete mode 100644 virt/kvm/arm/vgic/vgic-mmio.h delete mode 100644 virt/kvm/arm/vgic/vgic-v2.c delete mode 100644 virt/kvm/arm/vgic/vgic-v3.c delete mode 100644 virt/kvm/arm/vgic/vgic-v4.c delete mode 100644 virt/kvm/arm/vgic/vgic.c delete mode 100644 virt/kvm/arm/vgic/vgic.h (limited to 'virt') diff --git a/virt/kvm/arm/aarch32.c b/virt/kvm/arm/aarch32.c deleted file mode 100644 index 0a356aa91aa1..000000000000 --- a/virt/kvm/arm/aarch32.c +++ /dev/null @@ -1,204 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * (not much of an) Emulation layer for 32bit guests. - * - * Copyright (C) 2012,2013 - ARM Ltd - * Author: Marc Zyngier - * - * based on arch/arm/kvm/emulate.c - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Author: Christoffer Dall - */ - -#include -#include -#include -#include - -#define DFSR_FSC_EXTABT_LPAE 0x10 -#define DFSR_FSC_EXTABT_nLPAE 0x08 -#define DFSR_LPAE BIT(9) - -/* - * Table taken from ARMv8 ARM DDI0487B-B, table G1-10. - */ -static const u8 return_offsets[8][2] = { - [0] = { 0, 0 }, /* Reset, unused */ - [1] = { 4, 2 }, /* Undefined */ - [2] = { 0, 0 }, /* SVC, unused */ - [3] = { 4, 4 }, /* Prefetch abort */ - [4] = { 8, 8 }, /* Data abort */ - [5] = { 0, 0 }, /* HVC, unused */ - [6] = { 4, 4 }, /* IRQ, unused */ - [7] = { 4, 4 }, /* FIQ, unused */ -}; - -/* - * When an exception is taken, most CPSR fields are left unchanged in the - * handler. However, some are explicitly overridden (e.g. M[4:0]). - * - * The SPSR/SPSR_ELx layouts differ, and the below is intended to work with - * either format. Note: SPSR.J bit doesn't exist in SPSR_ELx, but this bit was - * obsoleted by the ARMv7 virtualization extensions and is RES0. - * - * For the SPSR layout seen from AArch32, see: - * - ARM DDI 0406C.d, page B1-1148 - * - ARM DDI 0487E.a, page G8-6264 - * - * For the SPSR_ELx layout for AArch32 seen from AArch64, see: - * - ARM DDI 0487E.a, page C5-426 - * - * Here we manipulate the fields in order of the AArch32 SPSR_ELx layout, from - * MSB to LSB. - */ -static unsigned long get_except32_cpsr(struct kvm_vcpu *vcpu, u32 mode) -{ - u32 sctlr = vcpu_cp15(vcpu, c1_SCTLR); - unsigned long old, new; - - old = *vcpu_cpsr(vcpu); - new = 0; - - new |= (old & PSR_AA32_N_BIT); - new |= (old & PSR_AA32_Z_BIT); - new |= (old & PSR_AA32_C_BIT); - new |= (old & PSR_AA32_V_BIT); - new |= (old & PSR_AA32_Q_BIT); - - // CPSR.IT[7:0] are set to zero upon any exception - // See ARM DDI 0487E.a, section G1.12.3 - // See ARM DDI 0406C.d, section B1.8.3 - - new |= (old & PSR_AA32_DIT_BIT); - - // CPSR.SSBS is set to SCTLR.DSSBS upon any exception - // See ARM DDI 0487E.a, page G8-6244 - if (sctlr & BIT(31)) - new |= PSR_AA32_SSBS_BIT; - - // CPSR.PAN is unchanged unless SCTLR.SPAN == 0b0 - // SCTLR.SPAN is RES1 when ARMv8.1-PAN is not implemented - // See ARM DDI 0487E.a, page G8-6246 - new |= (old & PSR_AA32_PAN_BIT); - if (!(sctlr & BIT(23))) - new |= PSR_AA32_PAN_BIT; - - // SS does not exist in AArch32, so ignore - - // CPSR.IL is set to zero upon any exception - // See ARM DDI 0487E.a, page G1-5527 - - new |= (old & PSR_AA32_GE_MASK); - - // CPSR.IT[7:0] are set to zero upon any exception - // See prior comment above - - // CPSR.E is set to SCTLR.EE upon any exception - // See ARM DDI 0487E.a, page G8-6245 - // See ARM DDI 0406C.d, page B4-1701 - if (sctlr & BIT(25)) - new |= PSR_AA32_E_BIT; - - // CPSR.A is unchanged upon an exception to Undefined, Supervisor - // CPSR.A is set upon an exception to other modes - // See ARM DDI 0487E.a, pages G1-5515 to G1-5516 - // See ARM DDI 0406C.d, page B1-1182 - new |= (old & PSR_AA32_A_BIT); - if (mode != PSR_AA32_MODE_UND && mode != PSR_AA32_MODE_SVC) - new |= PSR_AA32_A_BIT; - - // CPSR.I is set upon any exception - // See ARM DDI 0487E.a, pages G1-5515 to G1-5516 - // See ARM DDI 0406C.d, page B1-1182 - new |= PSR_AA32_I_BIT; - - // CPSR.F is set upon an exception to FIQ - // CPSR.F is unchanged upon an exception to other modes - // See ARM DDI 0487E.a, pages G1-5515 to G1-5516 - // See ARM DDI 0406C.d, page B1-1182 - new |= (old & PSR_AA32_F_BIT); - if (mode == PSR_AA32_MODE_FIQ) - new |= PSR_AA32_F_BIT; - - // CPSR.T is set to SCTLR.TE upon any exception - // See ARM DDI 0487E.a, page G8-5514 - // See ARM DDI 0406C.d, page B1-1181 - if (sctlr & BIT(30)) - new |= PSR_AA32_T_BIT; - - new |= mode; - - return new; -} - -static void prepare_fault32(struct kvm_vcpu *vcpu, u32 mode, u32 vect_offset) -{ - unsigned long spsr = *vcpu_cpsr(vcpu); - bool is_thumb = (spsr & PSR_AA32_T_BIT); - u32 return_offset = return_offsets[vect_offset >> 2][is_thumb]; - u32 sctlr = vcpu_cp15(vcpu, c1_SCTLR); - - *vcpu_cpsr(vcpu) = get_except32_cpsr(vcpu, mode); - - /* Note: These now point to the banked copies */ - vcpu_write_spsr(vcpu, host_spsr_to_spsr32(spsr)); - *vcpu_reg32(vcpu, 14) = *vcpu_pc(vcpu) + return_offset; - - /* Branch to exception vector */ - if (sctlr & (1 << 13)) - vect_offset += 0xffff0000; - else /* always have security exceptions */ - vect_offset += vcpu_cp15(vcpu, c12_VBAR); - - *vcpu_pc(vcpu) = vect_offset; -} - -void kvm_inject_undef32(struct kvm_vcpu *vcpu) -{ - prepare_fault32(vcpu, PSR_AA32_MODE_UND, 4); -} - -/* - * Modelled after TakeDataAbortException() and TakePrefetchAbortException - * pseudocode. - */ -static void inject_abt32(struct kvm_vcpu *vcpu, bool is_pabt, - unsigned long addr) -{ - u32 vect_offset; - u32 *far, *fsr; - bool is_lpae; - - if (is_pabt) { - vect_offset = 12; - far = &vcpu_cp15(vcpu, c6_IFAR); - fsr = &vcpu_cp15(vcpu, c5_IFSR); - } else { /* !iabt */ - vect_offset = 16; - far = &vcpu_cp15(vcpu, c6_DFAR); - fsr = &vcpu_cp15(vcpu, c5_DFSR); - } - - prepare_fault32(vcpu, PSR_AA32_MODE_ABT, vect_offset); - - *far = addr; - - /* Give the guest an IMPLEMENTATION DEFINED exception */ - is_lpae = (vcpu_cp15(vcpu, c2_TTBCR) >> 31); - if (is_lpae) { - *fsr = DFSR_LPAE | DFSR_FSC_EXTABT_LPAE; - } else { - /* no need to shuffle FS[4] into DFSR[10] as its 0 */ - *fsr = DFSR_FSC_EXTABT_nLPAE; - } -} - -void kvm_inject_dabt32(struct kvm_vcpu *vcpu, unsigned long addr) -{ - inject_abt32(vcpu, false, addr); -} - -void kvm_inject_pabt32(struct kvm_vcpu *vcpu, unsigned long addr) -{ - inject_abt32(vcpu, true, addr); -} diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c deleted file mode 100644 index 93bd59b46848..000000000000 --- a/virt/kvm/arm/arch_timer.c +++ /dev/null @@ -1,1180 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2012 ARM Ltd. - * Author: Marc Zyngier - */ - -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include - -#include -#include - -#include "trace.h" - -static struct timecounter *timecounter; -static unsigned int host_vtimer_irq; -static unsigned int host_ptimer_irq; -static u32 host_vtimer_irq_flags; -static u32 host_ptimer_irq_flags; - -static DEFINE_STATIC_KEY_FALSE(has_gic_active_state); - -static const struct kvm_irq_level default_ptimer_irq = { - .irq = 30, - .level = 1, -}; - -static const struct kvm_irq_level default_vtimer_irq = { - .irq = 27, - .level = 1, -}; - -static bool kvm_timer_irq_can_fire(struct arch_timer_context *timer_ctx); -static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level, - struct arch_timer_context *timer_ctx); -static bool kvm_timer_should_fire(struct arch_timer_context *timer_ctx); -static void kvm_arm_timer_write(struct kvm_vcpu *vcpu, - struct arch_timer_context *timer, - enum kvm_arch_timer_regs treg, - u64 val); -static u64 kvm_arm_timer_read(struct kvm_vcpu *vcpu, - struct arch_timer_context *timer, - enum kvm_arch_timer_regs treg); - -u64 kvm_phys_timer_read(void) -{ - return timecounter->cc->read(timecounter->cc); -} - -static void get_timer_map(struct kvm_vcpu *vcpu, struct timer_map *map) -{ - if (has_vhe()) { - map->direct_vtimer = vcpu_vtimer(vcpu); - map->direct_ptimer = vcpu_ptimer(vcpu); - map->emul_ptimer = NULL; - } else { - map->direct_vtimer = vcpu_vtimer(vcpu); - map->direct_ptimer = NULL; - map->emul_ptimer = vcpu_ptimer(vcpu); - } - - trace_kvm_get_timer_map(vcpu->vcpu_id, map); -} - -static inline bool userspace_irqchip(struct kvm *kvm) -{ - return static_branch_unlikely(&userspace_irqchip_in_use) && - unlikely(!irqchip_in_kernel(kvm)); -} - -static void soft_timer_start(struct hrtimer *hrt, u64 ns) -{ - hrtimer_start(hrt, ktime_add_ns(ktime_get(), ns), - HRTIMER_MODE_ABS_HARD); -} - -static void soft_timer_cancel(struct hrtimer *hrt) -{ - hrtimer_cancel(hrt); -} - -static irqreturn_t kvm_arch_timer_handler(int irq, void *dev_id) -{ - struct kvm_vcpu *vcpu = *(struct kvm_vcpu **)dev_id; - struct arch_timer_context *ctx; - struct timer_map map; - - /* - * We may see a timer interrupt after vcpu_put() has been called which - * sets the CPU's vcpu pointer to NULL, because even though the timer - * has been disabled in timer_save_state(), the hardware interrupt - * signal may not have been retired from the interrupt controller yet. - */ - if (!vcpu) - return IRQ_HANDLED; - - get_timer_map(vcpu, &map); - - if (irq == host_vtimer_irq) - ctx = map.direct_vtimer; - else - ctx = map.direct_ptimer; - - if (kvm_timer_should_fire(ctx)) - kvm_timer_update_irq(vcpu, true, ctx); - - if (userspace_irqchip(vcpu->kvm) && - !static_branch_unlikely(&has_gic_active_state)) - disable_percpu_irq(host_vtimer_irq); - - return IRQ_HANDLED; -} - -static u64 kvm_timer_compute_delta(struct arch_timer_context *timer_ctx) -{ - u64 cval, now; - - cval = timer_ctx->cnt_cval; - now = kvm_phys_timer_read() - timer_ctx->cntvoff; - - if (now < cval) { - u64 ns; - - ns = cyclecounter_cyc2ns(timecounter->cc, - cval - now, - timecounter->mask, - &timecounter->frac); - return ns; - } - - return 0; -} - -static bool kvm_timer_irq_can_fire(struct arch_timer_context *timer_ctx) -{ - WARN_ON(timer_ctx && timer_ctx->loaded); - return timer_ctx && - !(timer_ctx->cnt_ctl & ARCH_TIMER_CTRL_IT_MASK) && - (timer_ctx->cnt_ctl & ARCH_TIMER_CTRL_ENABLE); -} - -/* - * Returns the earliest expiration time in ns among guest timers. - * Note that it will return 0 if none of timers can fire. - */ -static u64 kvm_timer_earliest_exp(struct kvm_vcpu *vcpu) -{ - u64 min_delta = ULLONG_MAX; - int i; - - for (i = 0; i < NR_KVM_TIMERS; i++) { - struct arch_timer_context *ctx = &vcpu->arch.timer_cpu.timers[i]; - - WARN(ctx->loaded, "timer %d loaded\n", i); - if (kvm_timer_irq_can_fire(ctx)) - min_delta = min(min_delta, kvm_timer_compute_delta(ctx)); - } - - /* If none of timers can fire, then return 0 */ - if (min_delta == ULLONG_MAX) - return 0; - - return min_delta; -} - -static enum hrtimer_restart kvm_bg_timer_expire(struct hrtimer *hrt) -{ - struct arch_timer_cpu *timer; - struct kvm_vcpu *vcpu; - u64 ns; - - timer = container_of(hrt, struct arch_timer_cpu, bg_timer); - vcpu = container_of(timer, struct kvm_vcpu, arch.timer_cpu); - - /* - * Check that the timer has really expired from the guest's - * PoV (NTP on the host may have forced it to expire - * early). If we should have slept longer, restart it. - */ - ns = kvm_timer_earliest_exp(vcpu); - if (unlikely(ns)) { - hrtimer_forward_now(hrt, ns_to_ktime(ns)); - return HRTIMER_RESTART; - } - - kvm_vcpu_wake_up(vcpu); - return HRTIMER_NORESTART; -} - -static enum hrtimer_restart kvm_hrtimer_expire(struct hrtimer *hrt) -{ - struct arch_timer_context *ctx; - struct kvm_vcpu *vcpu; - u64 ns; - - ctx = container_of(hrt, struct arch_timer_context, hrtimer); - vcpu = ctx->vcpu; - - trace_kvm_timer_hrtimer_expire(ctx); - - /* - * Check that the timer has really expired from the guest's - * PoV (NTP on the host may have forced it to expire - * early). If not ready, schedule for a later time. - */ - ns = kvm_timer_compute_delta(ctx); - if (unlikely(ns)) { - hrtimer_forward_now(hrt, ns_to_ktime(ns)); - return HRTIMER_RESTART; - } - - kvm_timer_update_irq(vcpu, true, ctx); - return HRTIMER_NORESTART; -} - -static bool kvm_timer_should_fire(struct arch_timer_context *timer_ctx) -{ - enum kvm_arch_timers index; - u64 cval, now; - - if (!timer_ctx) - return false; - - index = arch_timer_ctx_index(timer_ctx); - - if (timer_ctx->loaded) { - u32 cnt_ctl = 0; - - switch (index) { - case TIMER_VTIMER: - cnt_ctl = read_sysreg_el0(SYS_CNTV_CTL); - break; - case TIMER_PTIMER: - cnt_ctl = read_sysreg_el0(SYS_CNTP_CTL); - break; - case NR_KVM_TIMERS: - /* GCC is braindead */ - cnt_ctl = 0; - break; - } - - return (cnt_ctl & ARCH_TIMER_CTRL_ENABLE) && - (cnt_ctl & ARCH_TIMER_CTRL_IT_STAT) && - !(cnt_ctl & ARCH_TIMER_CTRL_IT_MASK); - } - - if (!kvm_timer_irq_can_fire(timer_ctx)) - return false; - - cval = timer_ctx->cnt_cval; - now = kvm_phys_timer_read() - timer_ctx->cntvoff; - - return cval <= now; -} - -bool kvm_timer_is_pending(struct kvm_vcpu *vcpu) -{ - struct timer_map map; - - get_timer_map(vcpu, &map); - - return kvm_timer_should_fire(map.direct_vtimer) || - kvm_timer_should_fire(map.direct_ptimer) || - kvm_timer_should_fire(map.emul_ptimer); -} - -/* - * Reflect the timer output level into the kvm_run structure - */ -void kvm_timer_update_run(struct kvm_vcpu *vcpu) -{ - struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); - struct arch_timer_context *ptimer = vcpu_ptimer(vcpu); - struct kvm_sync_regs *regs = &vcpu->run->s.regs; - - /* Populate the device bitmap with the timer states */ - regs->device_irq_level &= ~(KVM_ARM_DEV_EL1_VTIMER | - KVM_ARM_DEV_EL1_PTIMER); - if (kvm_timer_should_fire(vtimer)) - regs->device_irq_level |= KVM_ARM_DEV_EL1_VTIMER; - if (kvm_timer_should_fire(ptimer)) - regs->device_irq_level |= KVM_ARM_DEV_EL1_PTIMER; -} - -static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level, - struct arch_timer_context *timer_ctx) -{ - int ret; - - timer_ctx->irq.level = new_level; - trace_kvm_timer_update_irq(vcpu->vcpu_id, timer_ctx->irq.irq, - timer_ctx->irq.level); - - if (!userspace_irqchip(vcpu->kvm)) { - ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id, - timer_ctx->irq.irq, - timer_ctx->irq.level, - timer_ctx); - WARN_ON(ret); - } -} - -/* Only called for a fully emulated timer */ -static void timer_emulate(struct arch_timer_context *ctx) -{ - bool should_fire = kvm_timer_should_fire(ctx); - - trace_kvm_timer_emulate(ctx, should_fire); - - if (should_fire != ctx->irq.level) { - kvm_timer_update_irq(ctx->vcpu, should_fire, ctx); - return; - } - - /* - * If the timer can fire now, we don't need to have a soft timer - * 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); - return; - } - - soft_timer_start(&ctx->hrtimer, kvm_timer_compute_delta(ctx)); -} - -static void timer_save_state(struct arch_timer_context *ctx) -{ - struct arch_timer_cpu *timer = vcpu_timer(ctx->vcpu); - enum kvm_arch_timers index = arch_timer_ctx_index(ctx); - unsigned long flags; - - if (!timer->enabled) - return; - - local_irq_save(flags); - - if (!ctx->loaded) - goto out; - - switch (index) { - case TIMER_VTIMER: - ctx->cnt_ctl = read_sysreg_el0(SYS_CNTV_CTL); - ctx->cnt_cval = read_sysreg_el0(SYS_CNTV_CVAL); - - /* Disable the timer */ - write_sysreg_el0(0, SYS_CNTV_CTL); - isb(); - - break; - case TIMER_PTIMER: - ctx->cnt_ctl = read_sysreg_el0(SYS_CNTP_CTL); - ctx->cnt_cval = read_sysreg_el0(SYS_CNTP_CVAL); - - /* Disable the timer */ - write_sysreg_el0(0, SYS_CNTP_CTL); - isb(); - - break; - case NR_KVM_TIMERS: - BUG(); - } - - trace_kvm_timer_save_state(ctx); - - ctx->loaded = false; -out: - local_irq_restore(flags); -} - -/* - * Schedule the background timer before calling kvm_vcpu_block, so that this - * thread is removed from its waitqueue and made runnable when there's a timer - * interrupt to handle. - */ -static void kvm_timer_blocking(struct kvm_vcpu *vcpu) -{ - struct arch_timer_cpu *timer = vcpu_timer(vcpu); - struct timer_map map; - - get_timer_map(vcpu, &map); - - /* - * If no timers are capable of raising interrupts (disabled or - * masked), then there's no more work for us to do. - */ - if (!kvm_timer_irq_can_fire(map.direct_vtimer) && - !kvm_timer_irq_can_fire(map.direct_ptimer) && - !kvm_timer_irq_can_fire(map.emul_ptimer)) - return; - - /* - * At least one guest time will expire. Schedule a background timer. - * Set the earliest expiration time among the guest timers. - */ - soft_timer_start(&timer->bg_timer, kvm_timer_earliest_exp(vcpu)); -} - -static void kvm_timer_unblocking(struct kvm_vcpu *vcpu) -{ - struct arch_timer_cpu *timer = vcpu_timer(vcpu); - - soft_timer_cancel(&timer->bg_timer); -} - -static void timer_restore_state(struct arch_timer_context *ctx) -{ - struct arch_timer_cpu *timer = vcpu_timer(ctx->vcpu); - enum kvm_arch_timers index = arch_timer_ctx_index(ctx); - unsigned long flags; - - if (!timer->enabled) - return; - - local_irq_save(flags); - - if (ctx->loaded) - goto out; - - switch (index) { - case TIMER_VTIMER: - write_sysreg_el0(ctx->cnt_cval, SYS_CNTV_CVAL); - isb(); - write_sysreg_el0(ctx->cnt_ctl, SYS_CNTV_CTL); - break; - case TIMER_PTIMER: - write_sysreg_el0(ctx->cnt_cval, SYS_CNTP_CVAL); - isb(); - write_sysreg_el0(ctx->cnt_ctl, SYS_CNTP_CTL); - break; - case NR_KVM_TIMERS: - BUG(); - } - - trace_kvm_timer_restore_state(ctx); - - ctx->loaded = true; -out: - local_irq_restore(flags); -} - -static void set_cntvoff(u64 cntvoff) -{ - u32 low = lower_32_bits(cntvoff); - u32 high = upper_32_bits(cntvoff); - - /* - * Since kvm_call_hyp doesn't fully support the ARM PCS especially on - * 32-bit systems, but rather passes register by register shifted one - * place (we put the function address in r0/x0), we cannot simply pass - * a 64-bit value as an argument, but have to split the value in two - * 32-bit halves. - */ - kvm_call_hyp(__kvm_timer_set_cntvoff, low, high); -} - -static inline void set_timer_irq_phys_active(struct arch_timer_context *ctx, bool active) -{ - int r; - r = irq_set_irqchip_state(ctx->host_timer_irq, IRQCHIP_STATE_ACTIVE, active); - WARN_ON(r); -} - -static void kvm_timer_vcpu_load_gic(struct arch_timer_context *ctx) -{ - struct kvm_vcpu *vcpu = ctx->vcpu; - bool phys_active = false; - - /* - * Update the timer output so that it is likely to match the - * state we're about to restore. If the timer expires between - * this point and the register restoration, we'll take the - * interrupt anyway. - */ - kvm_timer_update_irq(ctx->vcpu, kvm_timer_should_fire(ctx), ctx); - - if (irqchip_in_kernel(vcpu->kvm)) - phys_active = kvm_vgic_map_is_active(vcpu, ctx->irq.irq); - - phys_active |= ctx->irq.level; - - set_timer_irq_phys_active(ctx, phys_active); -} - -static void kvm_timer_vcpu_load_nogic(struct kvm_vcpu *vcpu) -{ - struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); - - /* - * Update the timer output so that it is likely to match the - * state we're about to restore. If the timer expires between - * this point and the register restoration, we'll take the - * interrupt anyway. - */ - kvm_timer_update_irq(vcpu, kvm_timer_should_fire(vtimer), vtimer); - - /* - * When using a userspace irqchip with the architected timers and a - * host interrupt controller that doesn't support an active state, we - * must still prevent continuously exiting from the guest, and - * therefore mask the physical interrupt by disabling it on the host - * interrupt controller when the virtual level is high, such that the - * guest can make forward progress. Once we detect the output level - * being de-asserted, we unmask the interrupt again so that we exit - * from the guest when the timer fires. - */ - if (vtimer->irq.level) - disable_percpu_irq(host_vtimer_irq); - else - enable_percpu_irq(host_vtimer_irq, host_vtimer_irq_flags); -} - -void kvm_timer_vcpu_load(struct kvm_vcpu *vcpu) -{ - struct arch_timer_cpu *timer = vcpu_timer(vcpu); - struct timer_map map; - - if (unlikely(!timer->enabled)) - return; - - get_timer_map(vcpu, &map); - - if (static_branch_likely(&has_gic_active_state)) { - kvm_timer_vcpu_load_gic(map.direct_vtimer); - if (map.direct_ptimer) - kvm_timer_vcpu_load_gic(map.direct_ptimer); - } else { - kvm_timer_vcpu_load_nogic(vcpu); - } - - set_cntvoff(map.direct_vtimer->cntvoff); - - kvm_timer_unblocking(vcpu); - - timer_restore_state(map.direct_vtimer); - if (map.direct_ptimer) - timer_restore_state(map.direct_ptimer); - - if (map.emul_ptimer) - timer_emulate(map.emul_ptimer); -} - -bool kvm_timer_should_notify_user(struct kvm_vcpu *vcpu) -{ - struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); - struct arch_timer_context *ptimer = vcpu_ptimer(vcpu); - struct kvm_sync_regs *sregs = &vcpu->run->s.regs; - bool vlevel, plevel; - - if (likely(irqchip_in_kernel(vcpu->kvm))) - return false; - - vlevel = sregs->device_irq_level & KVM_ARM_DEV_EL1_VTIMER; - plevel = sregs->device_irq_level & KVM_ARM_DEV_EL1_PTIMER; - - return kvm_timer_should_fire(vtimer) != vlevel || - kvm_timer_should_fire(ptimer) != plevel; -} - -void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu) -{ - struct arch_timer_cpu *timer = vcpu_timer(vcpu); - struct timer_map map; - - if (unlikely(!timer->enabled)) - return; - - get_timer_map(vcpu, &map); - - timer_save_state(map.direct_vtimer); - if (map.direct_ptimer) - timer_save_state(map.direct_ptimer); - - /* - * Cancel soft timer emulation, because the only case where we - * need it after a vcpu_put is in the context of a sleeping VCPU, and - * in that case we already factor in the deadline for the physical - * timer when scheduling the bg_timer. - * - * In any case, we re-schedule the hrtimer for the physical timer when - * coming back to the VCPU thread in kvm_timer_vcpu_load(). - */ - if (map.emul_ptimer) - soft_timer_cancel(&map.emul_ptimer->hrtimer); - - if (swait_active(kvm_arch_vcpu_wq(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); -} - -/* - * With a userspace irqchip we have to check if the guest de-asserted the - * timer and if so, unmask the timer irq signal on the host interrupt - * controller to ensure that we see future timer signals. - */ -static void unmask_vtimer_irq_user(struct kvm_vcpu *vcpu) -{ - struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); - - if (!kvm_timer_should_fire(vtimer)) { - kvm_timer_update_irq(vcpu, false, vtimer); - if (static_branch_likely(&has_gic_active_state)) - set_timer_irq_phys_active(vtimer, false); - else - enable_percpu_irq(host_vtimer_irq, host_vtimer_irq_flags); - } -} - -void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu) -{ - struct arch_timer_cpu *timer = vcpu_timer(vcpu); - - if (unlikely(!timer->enabled)) - return; - - if (unlikely(!irqchip_in_kernel(vcpu->kvm))) - unmask_vtimer_irq_user(vcpu); -} - -int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu) -{ - struct arch_timer_cpu *timer = vcpu_timer(vcpu); - struct timer_map map; - - get_timer_map(vcpu, &map); - - /* - * The bits in CNTV_CTL are architecturally reset to UNKNOWN for ARMv8 - * and to 0 for ARMv7. We provide an implementation that always - * resets the timer to be disabled and unmasked and is compliant with - * the ARMv7 architecture. - */ - vcpu_vtimer(vcpu)->cnt_ctl = 0; - vcpu_ptimer(vcpu)->cnt_ctl = 0; - - if (timer->enabled) { - kvm_timer_update_irq(vcpu, false, vcpu_vtimer(vcpu)); - kvm_timer_update_irq(vcpu, false, vcpu_ptimer(vcpu)); - - if (irqchip_in_kernel(vcpu->kvm)) { - kvm_vgic_reset_mapped_irq(vcpu, map.direct_vtimer->irq.irq); - if (map.direct_ptimer) - kvm_vgic_reset_mapped_irq(vcpu, map.direct_ptimer->irq.irq); - } - } - - if (map.emul_ptimer) - soft_timer_cancel(&map.emul_ptimer->hrtimer); - - return 0; -} - -/* Make the updates of cntvoff for all vtimer contexts atomic */ -static void update_vtimer_cntvoff(struct kvm_vcpu *vcpu, u64 cntvoff) -{ - int i; - struct kvm *kvm = vcpu->kvm; - struct kvm_vcpu *tmp; - - mutex_lock(&kvm->lock); - kvm_for_each_vcpu(i, tmp, kvm) - vcpu_vtimer(tmp)->cntvoff = cntvoff; - - /* - * When called from the vcpu create path, the CPU being created is not - * included in the loop above, so we just set it here as well. - */ - vcpu_vtimer(vcpu)->cntvoff = cntvoff; - mutex_unlock(&kvm->lock); -} - -void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu) -{ - struct arch_timer_cpu *timer = vcpu_timer(vcpu); - struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); - struct arch_timer_context *ptimer = vcpu_ptimer(vcpu); - - /* Synchronize cntvoff across all vtimers of a VM. */ - update_vtimer_cntvoff(vcpu, kvm_phys_timer_read()); - ptimer->cntvoff = 0; - - hrtimer_init(&timer->bg_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); - timer->bg_timer.function = kvm_bg_timer_expire; - - hrtimer_init(&vtimer->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); - hrtimer_init(&ptimer->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); - vtimer->hrtimer.function = kvm_hrtimer_expire; - ptimer->hrtimer.function = kvm_hrtimer_expire; - - vtimer->irq.irq = default_vtimer_irq.irq; - ptimer->irq.irq = default_ptimer_irq.irq; - - vtimer->host_timer_irq = host_vtimer_irq; - ptimer->host_timer_irq = host_ptimer_irq; - - vtimer->host_timer_irq_flags = host_vtimer_irq_flags; - ptimer->host_timer_irq_flags = host_ptimer_irq_flags; - - vtimer->vcpu = vcpu; - ptimer->vcpu = vcpu; -} - -static void kvm_timer_init_interrupt(void *info) -{ - enable_percpu_irq(host_vtimer_irq, host_vtimer_irq_flags); - enable_percpu_irq(host_ptimer_irq, host_ptimer_irq_flags); -} - -int kvm_arm_timer_set_reg(struct kvm_vcpu *vcpu, u64 regid, u64 value) -{ - struct arch_timer_context *timer; - - switch (regid) { - case KVM_REG_ARM_TIMER_CTL: - timer = vcpu_vtimer(vcpu); - kvm_arm_timer_write(vcpu, timer, TIMER_REG_CTL, value); - break; - case KVM_REG_ARM_TIMER_CNT: - timer = vcpu_vtimer(vcpu); - update_vtimer_cntvoff(vcpu, kvm_phys_timer_read() - value); - break; - case KVM_REG_ARM_TIMER_CVAL: - timer = vcpu_vtimer(vcpu); - kvm_arm_timer_write(vcpu, timer, TIMER_REG_CVAL, value); - break; - case KVM_REG_ARM_PTIMER_CTL: - timer = vcpu_ptimer(vcpu); - kvm_arm_timer_write(vcpu, timer, TIMER_REG_CTL, value); - break; - case KVM_REG_ARM_PTIMER_CVAL: - timer = vcpu_ptimer(vcpu); - kvm_arm_timer_write(vcpu, timer, TIMER_REG_CVAL, value); - break; - - default: - return -1; - } - - return 0; -} - -static u64 read_timer_ctl(struct arch_timer_context *timer) -{ - /* - * Set ISTATUS bit if it's expired. - * Note that according to ARMv8 ARM Issue A.k, ISTATUS bit is - * UNKNOWN when ENABLE bit is 0, so we chose to set ISTATUS bit - * regardless of ENABLE bit for our implementation convenience. - */ - if (!kvm_timer_compute_delta(timer)) - return timer->cnt_ctl | ARCH_TIMER_CTRL_IT_STAT; - else - return timer->cnt_ctl; -} - -u64 kvm_arm_timer_get_reg(struct kvm_vcpu *vcpu, u64 regid) -{ - switch (regid) { - case KVM_REG_ARM_TIMER_CTL: - return kvm_arm_timer_read(vcpu, - vcpu_vtimer(vcpu), TIMER_REG_CTL); - case KVM_REG_ARM_TIMER_CNT: - return kvm_arm_timer_read(vcpu, - vcpu_vtimer(vcpu), TIMER_REG_CNT); - case KVM_REG_ARM_TIMER_CVAL: - return kvm_arm_timer_read(vcpu, - vcpu_vtimer(vcpu), TIMER_REG_CVAL); - case KVM_REG_ARM_PTIMER_CTL: - return kvm_arm_timer_read(vcpu, - vcpu_ptimer(vcpu), TIMER_REG_CTL); - case KVM_REG_ARM_PTIMER_CNT: - return kvm_arm_timer_read(vcpu, - vcpu_ptimer(vcpu), TIMER_REG_CNT); - case KVM_REG_ARM_PTIMER_CVAL: - return kvm_arm_timer_read(vcpu, - vcpu_ptimer(vcpu), TIMER_REG_CVAL); - } - return (u64)-1; -} - -static u64 kvm_arm_timer_read(struct kvm_vcpu *vcpu, - struct arch_timer_context *timer, - enum kvm_arch_timer_regs treg) -{ - u64 val; - - switch (treg) { - case TIMER_REG_TVAL: - val = timer->cnt_cval - kvm_phys_timer_read() + timer->cntvoff; - val &= lower_32_bits(val); - break; - - case TIMER_REG_CTL: - val = read_timer_ctl(timer); - break; - - case TIMER_REG_CVAL: - val = timer->cnt_cval; - break; - - case TIMER_REG_CNT: - val = kvm_phys_timer_read() - timer->cntvoff; - break; - - default: - BUG(); - } - - return val; -} - -u64 kvm_arm_timer_read_sysreg(struct kvm_vcpu *vcpu, - enum kvm_arch_timers tmr, - enum kvm_arch_timer_regs treg) -{ - u64 val; - - preempt_disable(); - kvm_timer_vcpu_put(vcpu); - - val = kvm_arm_timer_read(vcpu, vcpu_get_timer(vcpu, tmr), treg); - - kvm_timer_vcpu_load(vcpu); - preempt_enable(); - - return val; -} - -static void kvm_arm_timer_write(struct kvm_vcpu *vcpu, - struct arch_timer_context *timer, - enum kvm_arch_timer_regs treg, - u64 val) -{ - switch (treg) { - case TIMER_REG_TVAL: - timer->cnt_cval = kvm_phys_timer_read() - timer->cntvoff + (s32)val; - break; - - case TIMER_REG_CTL: - timer->cnt_ctl = val & ~ARCH_TIMER_CTRL_IT_STAT; - break; - - case TIMER_REG_CVAL: - timer->cnt_cval = val; - break; - - default: - BUG(); - } -} - -void kvm_arm_timer_write_sysreg(struct kvm_vcpu *vcpu, - enum kvm_arch_timers tmr, - 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); - - kvm_timer_vcpu_load(vcpu); - preempt_enable(); -} - -static int kvm_timer_starting_cpu(unsigned int cpu) -{ - kvm_timer_init_interrupt(NULL); - return 0; -} - -static int kvm_timer_dying_cpu(unsigned int cpu) -{ - disable_percpu_irq(host_vtimer_irq); - return 0; -} - -int kvm_timer_hyp_init(bool has_gic) -{ - struct arch_timer_kvm_info *info; - int err; - - info = arch_timer_get_kvm_info(); - timecounter = &info->timecounter; - - if (!timecounter->cc) { - kvm_err("kvm_arch_timer: uninitialized timecounter\n"); - return -ENODEV; - } - - /* First, do the virtual EL1 timer irq */ - - if (info->virtual_irq <= 0) { - kvm_err("kvm_arch_timer: invalid virtual timer IRQ: %d\n", - info->virtual_irq); - return -ENODEV; - } - host_vtimer_irq = info->virtual_irq; - - host_vtimer_irq_flags = irq_get_trigger_type(host_vtimer_irq); - if (host_vtimer_irq_flags != IRQF_TRIGGER_HIGH && - host_vtimer_irq_flags != IRQF_TRIGGER_LOW) { - kvm_err("Invalid trigger for vtimer IRQ%d, assuming level low\n", - host_vtimer_irq); - host_vtimer_irq_flags = IRQF_TRIGGER_LOW; - } - - err = request_percpu_irq(host_vtimer_irq, kvm_arch_timer_handler, - "kvm guest vtimer", kvm_get_running_vcpus()); - if (err) { - kvm_err("kvm_arch_timer: can't request vtimer interrupt %d (%d)\n", - host_vtimer_irq, err); - return err; - } - - if (has_gic) { - err = irq_set_vcpu_affinity(host_vtimer_irq, - kvm_get_running_vcpus()); - if (err) { - kvm_err("kvm_arch_timer: error setting vcpu affinity\n"); - goto out_free_irq; - } - - static_branch_enable(&has_gic_active_state); - } - - kvm_debug("virtual timer IRQ%d\n", host_vtimer_irq); - - /* Now let's do the physical EL1 timer irq */ - - if (info->physical_irq > 0) { - host_ptimer_irq = info->physical_irq; - host_ptimer_irq_flags = irq_get_trigger_type(host_ptimer_irq); - if (host_ptimer_irq_flags != IRQF_TRIGGER_HIGH && - host_ptimer_irq_flags != IRQF_TRIGGER_LOW) { - kvm_err("Invalid trigger for ptimer IRQ%d, assuming level low\n", - host_ptimer_irq); - host_ptimer_irq_flags = IRQF_TRIGGER_LOW; - } - - err = request_percpu_irq(host_ptimer_irq, kvm_arch_timer_handler, - "kvm guest ptimer", kvm_get_running_vcpus()); - if (err) { - kvm_err("kvm_arch_timer: can't request ptimer interrupt %d (%d)\n", - host_ptimer_irq, err); - return err; - } - - if (has_gic) { - err = irq_set_vcpu_affinity(host_ptimer_irq, - kvm_get_running_vcpus()); - if (err) { - kvm_err("kvm_arch_timer: error setting vcpu affinity\n"); - goto out_free_irq; - } - } - - kvm_debug("physical timer IRQ%d\n", host_ptimer_irq); - } else if (has_vhe()) { - kvm_err("kvm_arch_timer: invalid physical timer IRQ: %d\n", - info->physical_irq); - err = -ENODEV; - goto out_free_irq; - } - - cpuhp_setup_state(CPUHP_AP_KVM_ARM_TIMER_STARTING, - "kvm/arm/timer:starting", kvm_timer_starting_cpu, - kvm_timer_dying_cpu); - return 0; -out_free_irq: - free_percpu_irq(host_vtimer_irq, kvm_get_running_vcpus()); - return err; -} - -void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu) -{ - struct arch_timer_cpu *timer = vcpu_timer(vcpu); - - soft_timer_cancel(&timer->bg_timer); -} - -static bool timer_irqs_are_valid(struct kvm_vcpu *vcpu) -{ - int vtimer_irq, ptimer_irq; - int i, ret; - - vtimer_irq = vcpu_vtimer(vcpu)->irq.irq; - ret = kvm_vgic_set_owner(vcpu, vtimer_irq, vcpu_vtimer(vcpu)); - if (ret) - return false; - - ptimer_irq = vcpu_ptimer(vcpu)->irq.irq; - ret = kvm_vgic_set_owner(vcpu, ptimer_irq, vcpu_ptimer(vcpu)); - if (ret) - return false; - - kvm_for_each_vcpu(i, vcpu, vcpu->kvm) { - if (vcpu_vtimer(vcpu)->irq.irq != vtimer_irq || - vcpu_ptimer(vcpu)->irq.irq != ptimer_irq) - return false; - } - - return true; -} - -bool kvm_arch_timer_get_input_level(int vintid) -{ - struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); - struct arch_timer_context *timer; - - if (vintid == vcpu_vtimer(vcpu)->irq.irq) - timer = vcpu_vtimer(vcpu); - else if (vintid == vcpu_ptimer(vcpu)->irq.irq) - timer = vcpu_ptimer(vcpu); - else - BUG(); - - return kvm_timer_should_fire(timer); -} - -int kvm_timer_enable(struct kvm_vcpu *vcpu) -{ - struct arch_timer_cpu *timer = vcpu_timer(vcpu); - struct timer_map map; - int ret; - - if (timer->enabled) - return 0; - - /* Without a VGIC we do not map virtual IRQs to physical IRQs */ - if (!irqchip_in_kernel(vcpu->kvm)) - goto no_vgic; - - if (!vgic_initialized(vcpu->kvm)) - return -ENODEV; - - if (!timer_irqs_are_valid(vcpu)) { - kvm_debug("incorrectly configured timer irqs\n"); - return -EINVAL; - } - - get_timer_map(vcpu, &map); - - ret = kvm_vgic_map_phys_irq(vcpu, - map.direct_vtimer->host_timer_irq, - map.direct_vtimer->irq.irq, - kvm_arch_timer_get_input_level); - if (ret) - return ret; - - if (map.direct_ptimer) { - ret = kvm_vgic_map_phys_irq(vcpu, - map.direct_ptimer->host_timer_irq, - map.direct_ptimer->irq.irq, - kvm_arch_timer_get_input_level); - } - - if (ret) - return ret; - -no_vgic: - timer->enabled = 1; - return 0; -} - -/* - * On VHE system, we only need to configure the EL2 timer trap register once, - * not for every world switch. - * The host kernel runs at EL2 with HCR_EL2.TGE == 1, - * and this makes those bits have no effect for the host kernel execution. - */ -void kvm_timer_init_vhe(void) -{ - /* When HCR_EL2.E2H ==1, EL1PCEN and EL1PCTEN are shifted by 10 */ - u32 cnthctl_shift = 10; - u64 val; - - /* - * VHE systems allow the guest direct access to the EL1 physical - * timer/counter. - */ - val = read_sysreg(cnthctl_el2); - val |= (CNTHCTL_EL1PCEN << cnthctl_shift); - val |= (CNTHCTL_EL1PCTEN << cnthctl_shift); - write_sysreg(val, cnthctl_el2); -} - -static void set_timer_irqs(struct kvm *kvm, int vtimer_irq, int ptimer_irq) -{ - struct kvm_vcpu *vcpu; - int i; - - kvm_for_each_vcpu(i, vcpu, kvm) { - vcpu_vtimer(vcpu)->irq.irq = vtimer_irq; - vcpu_ptimer(vcpu)->irq.irq = ptimer_irq; - } -} - -int kvm_arm_timer_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) -{ - int __user *uaddr = (int __user *)(long)attr->addr; - struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); - struct arch_timer_context *ptimer = vcpu_ptimer(vcpu); - int irq; - - if (!irqchip_in_kernel(vcpu->kvm)) - return -EINVAL; - - if (get_user(irq, uaddr)) - return -EFAULT; - - if (!(irq_is_ppi(irq))) - return -EINVAL; - - if (vcpu->arch.timer_cpu.enabled) - return -EBUSY; - - switch (attr->attr) { - case KVM_ARM_VCPU_TIMER_IRQ_VTIMER: - set_timer_irqs(vcpu->kvm, irq, ptimer->irq.irq); - break; - case KVM_ARM_VCPU_TIMER_IRQ_PTIMER: - set_timer_irqs(vcpu->kvm, vtimer->irq.irq, irq); - break; - default: - return -ENXIO; - } - - return 0; -} - -int kvm_arm_timer_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) -{ - int __user *uaddr = (int __user *)(long)attr->addr; - struct arch_timer_context *timer; - int irq; - - switch (attr->attr) { - case KVM_ARM_VCPU_TIMER_IRQ_VTIMER: - timer = vcpu_vtimer(vcpu); - break; - case KVM_ARM_VCPU_TIMER_IRQ_PTIMER: - timer = vcpu_ptimer(vcpu); - break; - default: - return -ENXIO; - } - - irq = timer->irq.irq; - return put_user(irq, uaddr); -} - -int kvm_arm_timer_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) -{ - switch (attr->attr) { - case KVM_ARM_VCPU_TIMER_IRQ_VTIMER: - case KVM_ARM_VCPU_TIMER_IRQ_PTIMER: - return 0; - } - - return -ENXIO; -} diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c deleted file mode 100644 index 48d0ec44ad77..000000000000 --- a/virt/kvm/arm/arm.c +++ /dev/null @@ -1,1681 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Author: Christoffer Dall - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#define CREATE_TRACE_POINTS -#include "trace.h" - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include - -#ifdef REQUIRES_VIRT -__asm__(".arch_extension virt"); -#endif - -DEFINE_PER_CPU(kvm_host_data_t, kvm_host_data); -static DEFINE_PER_CPU(unsigned long, kvm_arm_hyp_stack_page); - -/* The VMID used in the VTTBR */ -static atomic64_t kvm_vmid_gen = ATOMIC64_INIT(1); -static u32 kvm_next_vmid; -static DEFINE_SPINLOCK(kvm_vmid_lock); - -static bool vgic_present; - -static DEFINE_PER_CPU(unsigned char, kvm_arm_hardware_enabled); -DEFINE_STATIC_KEY_FALSE(userspace_irqchip_in_use); - -int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) -{ - return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE; -} - -int kvm_arch_hardware_setup(void *opaque) -{ - return 0; -} - -int kvm_arch_check_processor_compat(void *opaque) -{ - return 0; -} - -int kvm_vm_ioctl_enable_cap(struct kvm *kvm, - struct kvm_enable_cap *cap) -{ - int r; - - if (cap->flags) - return -EINVAL; - - switch (cap->cap) { - case KVM_CAP_ARM_NISV_TO_USER: - r = 0; - kvm->arch.return_nisv_io_abort_to_user = true; - break; - default: - r = -EINVAL; - break; - } - - return r; -} - -/** - * kvm_arch_init_vm - initializes a VM data structure - * @kvm: pointer to the KVM struct - */ -int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) -{ - int ret, cpu; - - ret = kvm_arm_setup_stage2(kvm, type); - if (ret) - return ret; - - kvm->arch.last_vcpu_ran = alloc_percpu(typeof(*kvm->arch.last_vcpu_ran)); - if (!kvm->arch.last_vcpu_ran) - return -ENOMEM; - - for_each_possible_cpu(cpu) - *per_cpu_ptr(kvm->arch.last_vcpu_ran, cpu) = -1; - - ret = kvm_alloc_stage2_pgd(kvm); - if (ret) - goto out_fail_alloc; - - ret = create_hyp_mappings(kvm, kvm + 1, PAGE_HYP); - if (ret) - goto out_free_stage2_pgd; - - kvm_vgic_early_init(kvm); - - /* Mark the initial VMID generation invalid */ - kvm->arch.vmid.vmid_gen = 0; - - /* The maximum number of VCPUs is limited by the host's GIC model */ - kvm->arch.max_vcpus = vgic_present ? - kvm_vgic_get_max_vcpus() : KVM_MAX_VCPUS; - - return ret; -out_free_stage2_pgd: - kvm_free_stage2_pgd(kvm); -out_fail_alloc: - free_percpu(kvm->arch.last_vcpu_ran); - kvm->arch.last_vcpu_ran = NULL; - return ret; -} - -int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu) -{ - return 0; -} - -vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf) -{ - return VM_FAULT_SIGBUS; -} - - -/** - * kvm_arch_destroy_vm - destroy the VM data structure - * @kvm: pointer to the KVM struct - */ -void kvm_arch_destroy_vm(struct kvm *kvm) -{ - int i; - - kvm_vgic_destroy(kvm); - - free_percpu(kvm->arch.last_vcpu_ran); - kvm->arch.last_vcpu_ran = NULL; - - for (i = 0; i < KVM_MAX_VCPUS; ++i) { - if (kvm->vcpus[i]) { - kvm_vcpu_destroy(kvm->vcpus[i]); - kvm->vcpus[i] = NULL; - } - } - atomic_set(&kvm->online_vcpus, 0); -} - -int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) -{ - int r; - switch (ext) { - case KVM_CAP_IRQCHIP: - r = vgic_present; - break; - case KVM_CAP_IOEVENTFD: - case KVM_CAP_DEVICE_CTRL: - case KVM_CAP_USER_MEMORY: - case KVM_CAP_SYNC_MMU: - case KVM_CAP_DESTROY_MEMORY_REGION_WORKS: - case KVM_CAP_ONE_REG: - case KVM_CAP_ARM_PSCI: - case KVM_CAP_ARM_PSCI_0_2: - case KVM_CAP_READONLY_MEM: - case KVM_CAP_MP_STATE: - case KVM_CAP_IMMEDIATE_EXIT: - case KVM_CAP_VCPU_EVENTS: - case KVM_CAP_ARM_IRQ_LINE_LAYOUT_2: - case KVM_CAP_ARM_NISV_TO_USER: - case KVM_CAP_ARM_INJECT_EXT_DABT: - r = 1; - break; - case KVM_CAP_ARM_SET_DEVICE_ADDR: - r = 1; - break; - case KVM_CAP_NR_VCPUS: - r = num_online_cpus(); - break; - case KVM_CAP_MAX_VCPUS: - r = KVM_MAX_VCPUS; - break; - case KVM_CAP_MAX_VCPU_ID: - r = KVM_MAX_VCPU_ID; - break; - case KVM_CAP_MSI_DEVID: - if (!kvm) - r = -EINVAL; - else - r = kvm->arch.vgic.msis_require_devid; - break; - case KVM_CAP_ARM_USER_IRQ: - /* - * 1: EL1_VTIMER, EL1_PTIMER, and PMU. - * (bump this number if adding more devices) - */ - r = 1; - break; - default: - r = kvm_arch_vm_ioctl_check_extension(kvm, ext); - break; - } - return r; -} - -long kvm_arch_dev_ioctl(struct file *filp, - unsigned int ioctl, unsigned long arg) -{ - return -EINVAL; -} - -struct kvm *kvm_arch_alloc_vm(void) -{ - if (!has_vhe()) - return kzalloc(sizeof(struct kvm), GFP_KERNEL); - - return vzalloc(sizeof(struct kvm)); -} - -void kvm_arch_free_vm(struct kvm *kvm) -{ - if (!has_vhe()) - kfree(kvm); - else - vfree(kvm); -} - -int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id) -{ - if (irqchip_in_kernel(kvm) && vgic_initialized(kvm)) - return -EBUSY; - - if (id >= kvm->arch.max_vcpus) - return -EINVAL; - - return 0; -} - -int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) -{ - int err; - - /* Force users to call KVM_ARM_VCPU_INIT */ - vcpu->arch.target = -1; - bitmap_zero(vcpu->arch.features, KVM_VCPU_MAX_FEATURES); - - /* Set up the timer */ - kvm_timer_vcpu_init(vcpu); - - kvm_pmu_vcpu_init(vcpu); - - kvm_arm_reset_debug_ptr(vcpu); - - kvm_arm_pvtime_vcpu_init(&vcpu->arch); - - err = kvm_vgic_vcpu_init(vcpu); - if (err) - return err; - - return create_hyp_mappings(vcpu, vcpu + 1, PAGE_HYP); -} - -void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) -{ -} - -void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) -{ - if (vcpu->arch.has_run_once && unlikely(!irqchip_in_kernel(vcpu->kvm))) - static_branch_dec(&userspace_irqchip_in_use); - - kvm_mmu_free_memory_caches(vcpu); - kvm_timer_vcpu_terminate(vcpu); - kvm_pmu_vcpu_destroy(vcpu); - - kvm_arm_vcpu_destroy(vcpu); -} - -int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) -{ - return kvm_timer_is_pending(vcpu); -} - -void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) -{ - /* - * If we're about to block (most likely because we've just hit a - * WFI), we need to sync back the state of the GIC CPU interface - * so that we have the latest PMR and group enables. This ensures - * that kvm_arch_vcpu_runnable has up-to-date data to decide - * whether we have pending interrupts. - * - * For the same reason, we want to tell GICv4 that we need - * doorbells to be signalled, should an interrupt become pending. - */ - preempt_disable(); - kvm_vgic_vmcr_sync(vcpu); - vgic_v4_put(vcpu, true); - preempt_enable(); -} - -void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) -{ - preempt_disable(); - vgic_v4_load(vcpu); - preempt_enable(); -} - -void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) -{ - int *last_ran; - kvm_host_data_t *cpu_data; - - last_ran = this_cpu_ptr(vcpu->kvm->arch.last_vcpu_ran); - cpu_data = this_cpu_ptr(&kvm_host_data); - - /* - * We might get preempted before the vCPU actually runs, but - * over-invalidation doesn't affect correctness. - */ - if (*last_ran != vcpu->vcpu_id) { - kvm_call_hyp(__kvm_tlb_flush_local_vmid, vcpu); - *last_ran = vcpu->vcpu_id; - } - - vcpu->cpu = cpu; - vcpu->arch.host_cpu_context = &cpu_data->host_ctxt; - - kvm_vgic_load(vcpu); - kvm_timer_vcpu_load(vcpu); - kvm_vcpu_load_sysregs(vcpu); - kvm_arch_vcpu_load_fp(vcpu); - kvm_vcpu_pmu_restore_guest(vcpu); - if (kvm_arm_is_pvtime_enabled(&vcpu->arch)) - kvm_make_request(KVM_REQ_RECORD_STEAL, vcpu); - - if (single_task_running()) - vcpu_clear_wfx_traps(vcpu); - else - vcpu_set_wfx_traps(vcpu); - - vcpu_ptrauth_setup_lazy(vcpu); -} - -void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) -{ - kvm_arch_vcpu_put_fp(vcpu); - kvm_vcpu_put_sysregs(vcpu); - kvm_timer_vcpu_put(vcpu); - kvm_vgic_put(vcpu); - kvm_vcpu_pmu_restore_host(vcpu); - - vcpu->cpu = -1; -} - -static void vcpu_power_off(struct kvm_vcpu *vcpu) -{ - vcpu->arch.power_off = true; - kvm_make_request(KVM_REQ_SLEEP, vcpu); - kvm_vcpu_kick(vcpu); -} - -int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, - struct kvm_mp_state *mp_state) -{ - if (vcpu->arch.power_off) - mp_state->mp_state = KVM_MP_STATE_STOPPED; - else - mp_state->mp_state = KVM_MP_STATE_RUNNABLE; - - return 0; -} - -int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, - struct kvm_mp_state *mp_state) -{ - int ret = 0; - - switch (mp_state->mp_state) { - case KVM_MP_STATE_RUNNABLE: - vcpu->arch.power_off = false; - break; - case KVM_MP_STATE_STOPPED: - vcpu_power_off(vcpu); - break; - default: - ret = -EINVAL; - } - - return ret; -} - -/** - * kvm_arch_vcpu_runnable - determine if the vcpu can be scheduled - * @v: The VCPU pointer - * - * If the guest CPU is not waiting for interrupts or an interrupt line is - * asserted, the CPU is by definition runnable. - */ -int kvm_arch_vcpu_runnable(struct kvm_vcpu *v) -{ - bool irq_lines = *vcpu_hcr(v) & (HCR_VI | HCR_VF); - return ((irq_lines || kvm_vgic_vcpu_pending_irq(v)) - && !v->arch.power_off && !v->arch.pause); -} - -bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu) -{ - return vcpu_mode_priv(vcpu); -} - -/* Just ensure a guest exit from a particular CPU */ -static void exit_vm_noop(void *info) -{ -} - -void force_vm_exit(const cpumask_t *mask) -{ - preempt_disable(); - smp_call_function_many(mask, exit_vm_noop, NULL, true); - preempt_enable(); -} - -/** - * need_new_vmid_gen - check that the VMID is still valid - * @vmid: The VMID to check - * - * return true if there is a new generation of VMIDs being used - * - * The hardware supports a limited set of values with the value zero reserved - * for the host, so we check if an assigned value belongs to a previous - * generation, which which requires us to assign a new value. If we're the - * first to use a VMID for the new generation, we must flush necessary caches - * and TLBs on all CPUs. - */ -static bool need_new_vmid_gen(struct kvm_vmid *vmid) -{ - u64 current_vmid_gen = atomic64_read(&kvm_vmid_gen); - smp_rmb(); /* Orders read of kvm_vmid_gen and kvm->arch.vmid */ - return unlikely(READ_ONCE(vmid->vmid_gen) != current_vmid_gen); -} - -/** - * update_vmid - Update the vmid with a valid VMID for the current generation - * @kvm: The guest that struct vmid belongs to - * @vmid: The stage-2 VMID information struct - */ -static void update_vmid(struct kvm_vmid *vmid) -{ - if (!need_new_vmid_gen(vmid)) - return; - - spin_lock(&kvm_vmid_lock); - - /* - * We need to re-check the vmid_gen here to ensure that if another vcpu - * already allocated a valid vmid for this vm, then this vcpu should - * use the same vmid. - */ - if (!need_new_vmid_gen(vmid)) { - spin_unlock(&kvm_vmid_lock); - return; - } - - /* First user of a new VMID generation? */ - if (unlikely(kvm_next_vmid == 0)) { - atomic64_inc(&kvm_vmid_gen); - kvm_next_vmid = 1; - - /* - * On SMP we know no other CPUs can use this CPU's or each - * other's VMID after force_vm_exit returns since the - * kvm_vmid_lock blocks them from reentry to the guest. - */ - force_vm_exit(cpu_all_mask); - /* - * Now broadcast TLB + ICACHE invalidation over the inner - * shareable domain to make sure all data structures are - * clean. - */ - kvm_call_hyp(__kvm_flush_vm_context); - } - - vmid->vmid = kvm_next_vmid; - kvm_next_vmid++; - kvm_next_vmid &= (1 << kvm_get_vmid_bits()) - 1; - - smp_wmb(); - WRITE_ONCE(vmid->vmid_gen, atomic64_read(&kvm_vmid_gen)); - - spin_unlock(&kvm_vmid_lock); -} - -static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu) -{ - struct kvm *kvm = vcpu->kvm; - int ret = 0; - - if (likely(vcpu->arch.has_run_once)) - return 0; - - if (!kvm_arm_vcpu_is_finalized(vcpu)) - return -EPERM; - - vcpu->arch.has_run_once = true; - - if (likely(irqchip_in_kernel(kvm))) { - /* - * Map the VGIC hardware resources before running a vcpu the - * first time on this VM. - */ - if (unlikely(!vgic_ready(kvm))) { - ret = kvm_vgic_map_resources(kvm); - if (ret) - return ret; - } - } else { - /* - * Tell the rest of the code that there are userspace irqchip - * VMs in the wild. - */ - static_branch_inc(&userspace_irqchip_in_use); - } - - ret = kvm_timer_enable(vcpu); - if (ret) - return ret; - - ret = kvm_arm_pmu_v3_enable(vcpu); - - return ret; -} - -bool kvm_arch_intc_initialized(struct kvm *kvm) -{ - return vgic_initialized(kvm); -} - -void kvm_arm_halt_guest(struct kvm *kvm) -{ - int i; - struct kvm_vcpu *vcpu; - - kvm_for_each_vcpu(i, vcpu, kvm) - vcpu->arch.pause = true; - kvm_make_all_cpus_request(kvm, KVM_REQ_SLEEP); -} - -void kvm_arm_resume_guest(struct kvm *kvm) -{ - int i; - struct kvm_vcpu *vcpu; - - kvm_for_each_vcpu(i, vcpu, kvm) { - vcpu->arch.pause = false; - swake_up_one(kvm_arch_vcpu_wq(vcpu)); - } -} - -static void vcpu_req_sleep(struct kvm_vcpu *vcpu) -{ - struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu); - - swait_event_interruptible_exclusive(*wq, ((!vcpu->arch.power_off) && - (!vcpu->arch.pause))); - - if (vcpu->arch.power_off || vcpu->arch.pause) { - /* Awaken to handle a signal, request we sleep again later. */ - kvm_make_request(KVM_REQ_SLEEP, vcpu); - } - - /* - * Make sure we will observe a potential reset request if we've - * observed a change to the power state. Pairs with the smp_wmb() in - * kvm_psci_vcpu_on(). - */ - smp_rmb(); -} - -static int kvm_vcpu_initialized(struct kvm_vcpu *vcpu) -{ - return vcpu->arch.target >= 0; -} - -static void check_vcpu_requests(struct kvm_vcpu *vcpu) -{ - if (kvm_request_pending(vcpu)) { - if (kvm_check_request(KVM_REQ_SLEEP, vcpu)) - vcpu_req_sleep(vcpu); - - if (kvm_check_request(KVM_REQ_VCPU_RESET, vcpu)) - kvm_reset_vcpu(vcpu); - - /* - * Clear IRQ_PENDING requests that were made to guarantee - * that a VCPU sees new virtual interrupts. - */ - kvm_check_request(KVM_REQ_IRQ_PENDING, vcpu); - - if (kvm_check_request(KVM_REQ_RECORD_STEAL, vcpu)) - kvm_update_stolen_time(vcpu); - - if (kvm_check_request(KVM_REQ_RELOAD_GICv4, vcpu)) { - /* The distributor enable bits were changed */ - preempt_disable(); - vgic_v4_put(vcpu, false); - vgic_v4_load(vcpu); - preempt_enable(); - } - } -} - -/** - * kvm_arch_vcpu_ioctl_run - the main VCPU run function to execute guest code - * @vcpu: The VCPU pointer - * @run: The kvm_run structure pointer used for userspace state exchange - * - * This function is called through the VCPU_RUN ioctl called from user space. It - * will execute VM code in a loop until the time slice for the process is used - * or some emulation is needed from user space in which case the function will - * return with return value 0 and with the kvm_run structure filled in with the - * required data for the requested emulation. - */ -int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) -{ - int ret; - - if (unlikely(!kvm_vcpu_initialized(vcpu))) - return -ENOEXEC; - - ret = kvm_vcpu_first_run_init(vcpu); - if (ret) - return ret; - - if (run->exit_reason == KVM_EXIT_MMIO) { - ret = kvm_handle_mmio_return(vcpu, vcpu->run); - if (ret) - return ret; - } - - if (run->immediate_exit) - return -EINTR; - - vcpu_load(vcpu); - - kvm_sigset_activate(vcpu); - - ret = 1; - run->exit_reason = KVM_EXIT_UNKNOWN; - while (ret > 0) { - /* - * Check conditions before entering the guest - */ - cond_resched(); - - update_vmid(&vcpu->kvm->arch.vmid); - - check_vcpu_requests(vcpu); - - /* - * Preparing the interrupts to be injected also - * involves poking the GIC, which must be done in a - * non-preemptible context. - */ - preempt_disable(); - - kvm_pmu_flush_hwstate(vcpu); - - local_irq_disable(); - - kvm_vgic_flush_hwstate(vcpu); - - /* - * Exit if we have a signal pending so that we can deliver the - * signal to user space. - */ - if (signal_pending(current)) { - ret = -EINTR; - run->exit_reason = KVM_EXIT_INTR; - } - - /* - * If we're using a userspace irqchip, then check if we need - * to tell a userspace irqchip about timer or PMU level - * changes and if so, exit to userspace (the actual level - * state gets updated in kvm_timer_update_run and - * kvm_pmu_update_run below). - */ - if (static_branch_unlikely(&userspace_irqchip_in_use)) { - if (kvm_timer_should_notify_user(vcpu) || - kvm_pmu_should_notify_user(vcpu)) { - ret = -EINTR; - run->exit_reason = KVM_EXIT_INTR; - } - } - - /* - * Ensure we set mode to IN_GUEST_MODE after we disable - * interrupts and before the final VCPU requests check. - * See the comment in kvm_vcpu_exiting_guest_mode() and - * Documentation/virt/kvm/vcpu-requests.rst - */ - smp_store_mb(vcpu->mode, IN_GUEST_MODE); - - if (ret <= 0 || need_new_vmid_gen(&vcpu->kvm->arch.vmid) || - kvm_request_pending(vcpu)) { - vcpu->mode = OUTSIDE_GUEST_MODE; - isb(); /* Ensure work in x_flush_hwstate is committed */ - kvm_pmu_sync_hwstate(vcpu); - if (static_branch_unlikely(&userspace_irqchip_in_use)) - kvm_timer_sync_hwstate(vcpu); - kvm_vgic_sync_hwstate(vcpu); - local_irq_enable(); - preempt_enable(); - continue; - } - - kvm_arm_setup_debug(vcpu); - - /************************************************************** - * Enter the guest - */ - trace_kvm_entry(*vcpu_pc(vcpu)); - guest_enter_irqoff(); - - if (has_vhe()) { - ret = kvm_vcpu_run_vhe(vcpu); - } else { - ret = kvm_call_hyp_ret(__kvm_vcpu_run_nvhe, vcpu); - } - - vcpu->mode = OUTSIDE_GUEST_MODE; - vcpu->stat.exits++; - /* - * Back from guest - *************************************************************/ - - kvm_arm_clear_debug(vcpu); - - /* - * We must sync the PMU state before the vgic state so - * that the vgic can properly sample the updated state of the - * interrupt line. - */ - kvm_pmu_sync_hwstate(vcpu); - - /* - * Sync the vgic state before syncing the timer state because - * the timer code needs to know if the virtual timer - * interrupts are active. - */ - kvm_vgic_sync_hwstate(vcpu); - - /* - * Sync the timer hardware state before enabling interrupts as - * we don't want vtimer interrupts to race with syncing the - * timer virtual interrupt state. - */ - if (static_branch_unlikely(&userspace_irqchip_in_use)) - kvm_timer_sync_hwstate(vcpu); - - kvm_arch_vcpu_ctxsync_fp(vcpu); - - /* - * We may have taken a host interrupt in HYP mode (ie - * while executing the guest). This interrupt is still - * pending, as we haven't serviced it yet! - * - * We're now back in SVC mode, with interrupts - * disabled. Enabling the interrupts now will have - * the effect of taking the interrupt again, in SVC - * mode this time. - */ - local_irq_enable(); - - /* - * We do local_irq_enable() before calling guest_exit() so - * that if a timer interrupt hits while running the guest we - * account that tick as being spent in the guest. We enable - * preemption after calling guest_exit() so that if we get - * preempted we make sure ticks after that is not counted as - * guest time. - */ - guest_exit(); - trace_kvm_exit(ret, kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu)); - - /* Exit types that need handling before we can be preempted */ - handle_exit_early(vcpu, run, ret); - - preempt_enable(); - - ret = handle_exit(vcpu, run, ret); - } - - /* Tell userspace about in-kernel device output levels */ - if (unlikely(!irqchip_in_kernel(vcpu->kvm))) { - kvm_timer_update_run(vcpu); - kvm_pmu_update_run(vcpu); - } - - kvm_sigset_deactivate(vcpu); - - vcpu_put(vcpu); - return ret; -} - -static int vcpu_interrupt_line(struct kvm_vcpu *vcpu, int number, bool level) -{ - int bit_index; - bool set; - unsigned long *hcr; - - if (number == KVM_ARM_IRQ_CPU_IRQ) - bit_index = __ffs(HCR_VI); - else /* KVM_ARM_IRQ_CPU_FIQ */ - bit_index = __ffs(HCR_VF); - - hcr = vcpu_hcr(vcpu); - if (level) - set = test_and_set_bit(bit_index, hcr); - else - set = test_and_clear_bit(bit_index, hcr); - - /* - * If we didn't change anything, no need to wake up or kick other CPUs - */ - if (set == level) - return 0; - - /* - * The vcpu irq_lines field was updated, wake up sleeping VCPUs and - * trigger a world-switch round on the running physical CPU to set the - * virtual IRQ/FIQ fields in the HCR appropriately. - */ - kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu); - kvm_vcpu_kick(vcpu); - - return 0; -} - -int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level, - bool line_status) -{ - u32 irq = irq_level->irq; - unsigned int irq_type, vcpu_idx, irq_num; - int nrcpus = atomic_read(&kvm->online_vcpus); - struct kvm_vcpu *vcpu = NULL; - bool level = irq_level->level; - - irq_type = (irq >> KVM_ARM_IRQ_TYPE_SHIFT) & KVM_ARM_IRQ_TYPE_MASK; - vcpu_idx = (irq >> KVM_ARM_IRQ_VCPU_SHIFT) & KVM_ARM_IRQ_VCPU_MASK; - vcpu_idx += ((irq >> KVM_ARM_IRQ_VCPU2_SHIFT) & KVM_ARM_IRQ_VCPU2_MASK) * (KVM_ARM_IRQ_VCPU_MASK + 1); - irq_num = (irq >> KVM_ARM_IRQ_NUM_SHIFT) & KVM_ARM_IRQ_NUM_MASK; - - trace_kvm_irq_line(irq_type, vcpu_idx, irq_num, irq_level->level); - - switch (irq_type) { - case KVM_ARM_IRQ_TYPE_CPU: - if (irqchip_in_kernel(kvm)) - return -ENXIO; - - if (vcpu_idx >= nrcpus) - return -EINVAL; - - vcpu = kvm_get_vcpu(kvm, vcpu_idx); - if (!vcpu) - return -EINVAL; - - if (irq_num > KVM_ARM_IRQ_CPU_FIQ) - return -EINVAL; - - return vcpu_interrupt_line(vcpu, irq_num, level); - case KVM_ARM_IRQ_TYPE_PPI: - if (!irqchip_in_kernel(kvm)) - return -ENXIO; - - if (vcpu_idx >= nrcpus) - return -EINVAL; - - vcpu = kvm_get_vcpu(kvm, vcpu_idx); - if (!vcpu) - return -EINVAL; - - if (irq_num < VGIC_NR_SGIS || irq_num >= VGIC_NR_PRIVATE_IRQS) - return -EINVAL; - - return kvm_vgic_inject_irq(kvm, vcpu->vcpu_id, irq_num, level, NULL); - case KVM_ARM_IRQ_TYPE_SPI: - if (!irqchip_in_kernel(kvm)) - return -ENXIO; - - if (irq_num < VGIC_NR_PRIVATE_IRQS) - return -EINVAL; - - return kvm_vgic_inject_irq(kvm, 0, irq_num, level, NULL); - } - - return -EINVAL; -} - -static int kvm_vcpu_set_target(struct kvm_vcpu *vcpu, - const struct kvm_vcpu_init *init) -{ - unsigned int i, ret; - int phys_target = kvm_target_cpu(); - - if (init->target != phys_target) - return -EINVAL; - - /* - * Secondary and subsequent calls to KVM_ARM_VCPU_INIT must - * use the same target. - */ - if (vcpu->arch.target != -1 && vcpu->arch.target != init->target) - return -EINVAL; - - /* -ENOENT for unknown features, -EINVAL for invalid combinations. */ - for (i = 0; i < sizeof(init->features) * 8; i++) { - bool set = (init->features[i / 32] & (1 << (i % 32))); - - if (set && i >= KVM_VCPU_MAX_FEATURES) - return -ENOENT; - - /* - * Secondary and subsequent calls to KVM_ARM_VCPU_INIT must - * use the same feature set. - */ - if (vcpu->arch.target != -1 && i < KVM_VCPU_MAX_FEATURES && - test_bit(i, vcpu->arch.features) != set) - return -EINVAL; - - if (set) - set_bit(i, vcpu->arch.features); - } - - vcpu->arch.target = phys_target; - - /* Now we know what it is, we can reset it. */ - ret = kvm_reset_vcpu(vcpu); - if (ret) { - vcpu->arch.target = -1; - bitmap_zero(vcpu->arch.features, KVM_VCPU_MAX_FEATURES); - } - - return ret; -} - -static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu, - struct kvm_vcpu_init *init) -{ - int ret; - - ret = kvm_vcpu_set_target(vcpu, init); - if (ret) - return ret; - - /* - * Ensure a rebooted VM will fault in RAM pages and detect if the - * guest MMU is turned off and flush the caches as needed. - */ - if (vcpu->arch.has_run_once) - stage2_unmap_vm(vcpu->kvm); - - vcpu_reset_hcr(vcpu); - - /* - * Handle the "start in power-off" case. - */ - if (test_bit(KVM_ARM_VCPU_POWER_OFF, vcpu->arch.features)) - vcpu_power_off(vcpu); - else - vcpu->arch.power_off = false; - - return 0; -} - -static int kvm_arm_vcpu_set_attr(struct kvm_vcpu *vcpu, - str