diff options
Diffstat (limited to 'virt')
-rw-r--r-- | virt/kvm/Kconfig | 10 | ||||
-rw-r--r-- | virt/kvm/arm/arch_timer.c | 318 | ||||
-rw-r--r-- | virt/kvm/arm/vgic-v2.c | 265 | ||||
-rw-r--r-- | virt/kvm/arm/vgic-v3.c | 247 | ||||
-rw-r--r-- | virt/kvm/arm/vgic.c | 2464 | ||||
-rw-r--r-- | virt/kvm/async_pf.c | 60 | ||||
-rw-r--r-- | virt/kvm/eventfd.c | 154 | ||||
-rw-r--r-- | virt/kvm/ioapic.c | 2 | ||||
-rw-r--r-- | virt/kvm/ioapic.h | 1 | ||||
-rw-r--r-- | virt/kvm/iommu.c | 12 | ||||
-rw-r--r-- | virt/kvm/irq_comm.c | 41 | ||||
-rw-r--r-- | virt/kvm/irqchip.c | 107 | ||||
-rw-r--r-- | virt/kvm/kvm_main.c | 388 | ||||
-rw-r--r-- | virt/kvm/vfio.c | 228 |
14 files changed, 3931 insertions, 366 deletions
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig index 779262f59e25..fc0c5e603eb4 100644 --- a/virt/kvm/Kconfig +++ b/virt/kvm/Kconfig @@ -6,6 +6,9 @@ config HAVE_KVM config HAVE_KVM_IRQCHIP bool +config HAVE_KVM_IRQFD + bool + config HAVE_KVM_IRQ_ROUTING bool @@ -22,8 +25,15 @@ config KVM_MMIO config KVM_ASYNC_PF bool +# Toggle to switch between direct notification and batch job +config KVM_ASYNC_PF_SYNC + bool + config HAVE_KVM_MSI bool config HAVE_KVM_CPU_RELAX_INTERCEPT bool + +config KVM_VFIO + bool diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c new file mode 100644 index 000000000000..5081e809821f --- /dev/null +++ b/virt/kvm/arm/arch_timer.c @@ -0,0 +1,318 @@ +/* + * Copyright (C) 2012 ARM Ltd. + * Author: Marc Zyngier <marc.zyngier@arm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#include <linux/cpu.h> +#include <linux/of_irq.h> +#include <linux/kvm.h> +#include <linux/kvm_host.h> +#include <linux/interrupt.h> + +#include <clocksource/arm_arch_timer.h> +#include <asm/arch_timer.h> + +#include <kvm/arm_vgic.h> +#include <kvm/arm_arch_timer.h> + +static struct timecounter *timecounter; +static struct workqueue_struct *wqueue; +static unsigned int host_vtimer_irq; + +static cycle_t kvm_phys_timer_read(void) +{ + return timecounter->cc->read(timecounter->cc); +} + +static bool timer_is_armed(struct arch_timer_cpu *timer) +{ + return timer->armed; +} + +/* timer_arm: as in "arm the timer", not as in ARM the company */ +static void timer_arm(struct arch_timer_cpu *timer, u64 ns) +{ + timer->armed = true; + hrtimer_start(&timer->timer, ktime_add_ns(ktime_get(), ns), + HRTIMER_MODE_ABS); +} + +static void timer_disarm(struct arch_timer_cpu *timer) +{ + if (timer_is_armed(timer)) { + hrtimer_cancel(&timer->timer); + cancel_work_sync(&timer->expired); + timer->armed = false; + } +} + +static void kvm_timer_inject_irq(struct kvm_vcpu *vcpu) +{ + struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; + + timer->cntv_ctl |= ARCH_TIMER_CTRL_IT_MASK; + kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id, + timer->irq->irq, + timer->irq->level); +} + +static irqreturn_t kvm_arch_timer_handler(int irq, void *dev_id) +{ + struct kvm_vcpu *vcpu = *(struct kvm_vcpu **)dev_id; + + /* + * We disable the timer in the world switch and let it be + * handled by kvm_timer_sync_hwstate(). Getting a timer + * interrupt at this point is a sure sign of some major + * breakage. + */ + pr_warn("Unexpected interrupt %d on vcpu %p\n", irq, vcpu); + return IRQ_HANDLED; +} + +static void kvm_timer_inject_irq_work(struct work_struct *work) +{ + struct kvm_vcpu *vcpu; + + vcpu = container_of(work, struct kvm_vcpu, arch.timer_cpu.expired); + vcpu->arch.timer_cpu.armed = false; + kvm_timer_inject_irq(vcpu); +} + +static enum hrtimer_restart kvm_timer_expire(struct hrtimer *hrt) +{ + struct arch_timer_cpu *timer; + timer = container_of(hrt, struct arch_timer_cpu, timer); + queue_work(wqueue, &timer->expired); + return HRTIMER_NORESTART; +} + +/** + * kvm_timer_flush_hwstate - prepare to move the virt timer to the cpu + * @vcpu: The vcpu pointer + * + * Disarm any pending soft timers, since the world-switch code will write the + * virtual timer state back to the physical CPU. + */ +void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu) +{ + struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; + + /* + * We're about to run this vcpu again, so there is no need to + * keep the background timer running, as we're about to + * populate the CPU timer again. + */ + timer_disarm(timer); +} + +/** + * kvm_timer_sync_hwstate - sync timer state from cpu + * @vcpu: The vcpu pointer + * + * Check if the virtual timer was armed and either schedule a corresponding + * soft timer or inject directly if already expired. + */ +void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu) +{ + struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; + cycle_t cval, now; + u64 ns; + + if ((timer->cntv_ctl & ARCH_TIMER_CTRL_IT_MASK) || + !(timer->cntv_ctl & ARCH_TIMER_CTRL_ENABLE)) + return; + + cval = timer->cntv_cval; + now = kvm_phys_timer_read() - vcpu->kvm->arch.timer.cntvoff; + + BUG_ON(timer_is_armed(timer)); + + if (cval <= now) { + /* + * Timer has already expired while we were not + * looking. Inject the interrupt and carry on. + */ + kvm_timer_inject_irq(vcpu); + return; + } + + ns = cyclecounter_cyc2ns(timecounter->cc, cval - now); + timer_arm(timer, ns); +} + +void kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu, + const struct kvm_irq_level *irq) +{ + struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; + + /* + * The vcpu timer irq number cannot be determined in + * kvm_timer_vcpu_init() because it is called much before + * kvm_vcpu_set_target(). To handle this, we determine + * vcpu timer irq number when the vcpu is reset. + */ + timer->irq = irq; +} + +void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu) +{ + struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; + + INIT_WORK(&timer->expired, kvm_timer_inject_irq_work); + hrtimer_init(&timer->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); + timer->timer.function = kvm_timer_expire; +} + +static void kvm_timer_init_interrupt(void *info) +{ + enable_percpu_irq(host_vtimer_irq, 0); +} + +int kvm_arm_timer_set_reg(struct kvm_vcpu *vcpu, u64 regid, u64 value) +{ + struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; + + switch (regid) { + case KVM_REG_ARM_TIMER_CTL: + timer->cntv_ctl = value; + break; + case KVM_REG_ARM_TIMER_CNT: + vcpu->kvm->arch.timer.cntvoff = kvm_phys_timer_read() - value; + break; + case KVM_REG_ARM_TIMER_CVAL: + timer->cntv_cval = value; + break; + default: + return -1; + } + return 0; +} + +u64 kvm_arm_timer_get_reg(struct kvm_vcpu *vcpu, u64 regid) +{ + struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; + + switch (regid) { + case KVM_REG_ARM_TIMER_CTL: + return timer->cntv_ctl; + case KVM_REG_ARM_TIMER_CNT: + return kvm_phys_timer_read() - vcpu->kvm->arch.timer.cntvoff; + case KVM_REG_ARM_TIMER_CVAL: + return timer->cntv_cval; + } + return (u64)-1; +} + +static int kvm_timer_cpu_notify(struct notifier_block *self, + unsigned long action, void *cpu) +{ + switch (action) { + case CPU_STARTING: + case CPU_STARTING_FROZEN: + kvm_timer_init_interrupt(NULL); + break; + case CPU_DYING: + case CPU_DYING_FROZEN: + disable_percpu_irq(host_vtimer_irq); + break; + } + + return NOTIFY_OK; +} + +static struct notifier_block kvm_timer_cpu_nb = { + .notifier_call = kvm_timer_cpu_notify, +}; + +static const struct of_device_id arch_timer_of_match[] = { + { .compatible = "arm,armv7-timer", }, + { .compatible = "arm,armv8-timer", }, + {}, +}; + +int kvm_timer_hyp_init(void) +{ + struct device_node *np; + unsigned int ppi; + int err; + + timecounter = arch_timer_get_timecounter(); + if (!timecounter) + return -ENODEV; + + np = of_find_matching_node(NULL, arch_timer_of_match); + if (!np) { + kvm_err("kvm_arch_timer: can't find DT node\n"); + return -ENODEV; + } + + ppi = irq_of_parse_and_map(np, 2); + if (!ppi) { + kvm_err("kvm_arch_timer: no virtual timer interrupt\n"); + err = -EINVAL; + goto out; + } + + err = request_percpu_irq(ppi, kvm_arch_timer_handler, + "kvm guest timer", kvm_get_running_vcpus()); + if (err) { + kvm_err("kvm_arch_timer: can't request interrupt %d (%d)\n", + ppi, err); + goto out; + } + + host_vtimer_irq = ppi; + + err = register_cpu_notifier(&kvm_timer_cpu_nb); + if (err) { + kvm_err("Cannot register timer CPU notifier\n"); + goto out_free; + } + + wqueue = create_singlethread_workqueue("kvm_arch_timer"); + if (!wqueue) { + err = -ENOMEM; + goto out_free; + } + + kvm_info("%s IRQ%d\n", np->name, ppi); + on_each_cpu(kvm_timer_init_interrupt, NULL, 1); + + goto out; +out_free: + free_percpu_irq(ppi, kvm_get_running_vcpus()); +out: + of_node_put(np); + return err; +} + +void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu) +{ + struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; + + timer_disarm(timer); +} + +int kvm_timer_init(struct kvm *kvm) +{ + if (timecounter && wqueue) { + kvm->arch.timer.cntvoff = kvm_phys_timer_read(); + kvm->arch.timer.enabled = 1; + } + + return 0; +} diff --git a/virt/kvm/arm/vgic-v2.c b/virt/kvm/arm/vgic-v2.c new file mode 100644 index 000000000000..01124ef3690a --- /dev/null +++ b/virt/kvm/arm/vgic-v2.c @@ -0,0 +1,265 @@ +/* + * Copyright (C) 2012,2013 ARM Limited, All Rights Reserved. + * Author: Marc Zyngier <marc.zyngier@arm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include <linux/cpu.h> +#include <linux/kvm.h> +#include <linux/kvm_host.h> +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/of.h> +#include <linux/of_address.h> +#include <linux/of_irq.h> + +#include <linux/irqchip/arm-gic.h> + +#include <asm/kvm_emulate.h> +#include <asm/kvm_arm.h> +#include <asm/kvm_mmu.h> + +static struct vgic_lr vgic_v2_get_lr(const struct kvm_vcpu *vcpu, int lr) +{ + struct vgic_lr lr_desc; + u32 val = vcpu->arch.vgic_cpu.vgic_v2.vgic_lr[lr]; + + lr_desc.irq = val & GICH_LR_VIRTUALID; + if (lr_desc.irq <= 15) + lr_desc.source = (val >> GICH_LR_PHYSID_CPUID_SHIFT) & 0x7; + else + lr_desc.source = 0; + lr_desc.state = 0; + + if (val & GICH_LR_PENDING_BIT) + lr_desc.state |= LR_STATE_PENDING; + if (val & GICH_LR_ACTIVE_BIT) + lr_desc.state |= LR_STATE_ACTIVE; + if (val & GICH_LR_EOI) + lr_desc.state |= LR_EOI_INT; + + return lr_desc; +} + +static void vgic_v2_set_lr(struct kvm_vcpu *vcpu, int lr, + struct vgic_lr lr_desc) +{ + u32 lr_val = (lr_desc.source << GICH_LR_PHYSID_CPUID_SHIFT) | lr_desc.irq; + + if (lr_desc.state & LR_STATE_PENDING) + lr_val |= GICH_LR_PENDING_BIT; + if (lr_desc.state & LR_STATE_ACTIVE) + lr_val |= GICH_LR_ACTIVE_BIT; + if (lr_desc.state & LR_EOI_INT) + lr_val |= GICH_LR_EOI; + + vcpu->arch.vgic_cpu.vgic_v2.vgic_lr[lr] = lr_val; +} + +static void vgic_v2_sync_lr_elrsr(struct kvm_vcpu *vcpu, int lr, + struct vgic_lr lr_desc) +{ + if (!(lr_desc.state & LR_STATE_MASK)) + set_bit(lr, (unsigned long *)vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr); +} + +static u64 vgic_v2_get_elrsr(const struct kvm_vcpu *vcpu) +{ + u64 val; + +#if BITS_PER_LONG == 64 + val = vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr[1]; + val <<= 32; + val |= vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr[0]; +#else + val = *(u64 *)vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr; +#endif + return val; +} + +static u64 vgic_v2_get_eisr(const struct kvm_vcpu *vcpu) +{ + u64 val; + +#if BITS_PER_LONG == 64 + val = vcpu->arch.vgic_cpu.vgic_v2.vgic_eisr[1]; + val <<= 32; + val |= vcpu->arch.vgic_cpu.vgic_v2.vgic_eisr[0]; +#else + val = *(u64 *)vcpu->arch.vgic_cpu.vgic_v2.vgic_eisr; +#endif + return val; +} + +static u32 vgic_v2_get_interrupt_status(const struct kvm_vcpu *vcpu) +{ + u32 misr = vcpu->arch.vgic_cpu.vgic_v2.vgic_misr; + u32 ret = 0; + + if (misr & GICH_MISR_EOI) + ret |= INT_STATUS_EOI; + if (misr & GICH_MISR_U) + ret |= INT_STATUS_UNDERFLOW; + + return ret; +} + +static void vgic_v2_enable_underflow(struct kvm_vcpu *vcpu) +{ + vcpu->arch.vgic_cpu.vgic_v2.vgic_hcr |= GICH_HCR_UIE; +} + +static void vgic_v2_disable_underflow(struct kvm_vcpu *vcpu) +{ + vcpu->arch.vgic_cpu.vgic_v2.vgic_hcr &= ~GICH_HCR_UIE; +} + +static void vgic_v2_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp) +{ + u32 vmcr = vcpu->arch.vgic_cpu.vgic_v2.vgic_vmcr; + + vmcrp->ctlr = (vmcr & GICH_VMCR_CTRL_MASK) >> GICH_VMCR_CTRL_SHIFT; + vmcrp->abpr = (vmcr & GICH_VMCR_ALIAS_BINPOINT_MASK) >> GICH_VMCR_ALIAS_BINPOINT_SHIFT; + vmcrp->bpr = (vmcr & GICH_VMCR_BINPOINT_MASK) >> GICH_VMCR_BINPOINT_SHIFT; + vmcrp->pmr = (vmcr & GICH_VMCR_PRIMASK_MASK) >> GICH_VMCR_PRIMASK_SHIFT; +} + +static void vgic_v2_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp) +{ + u32 vmcr; + + vmcr = (vmcrp->ctlr << GICH_VMCR_CTRL_SHIFT) & GICH_VMCR_CTRL_MASK; + vmcr |= (vmcrp->abpr << GICH_VMCR_ALIAS_BINPOINT_SHIFT) & GICH_VMCR_ALIAS_BINPOINT_MASK; + vmcr |= (vmcrp->bpr << GICH_VMCR_BINPOINT_SHIFT) & GICH_VMCR_BINPOINT_MASK; + vmcr |= (vmcrp->pmr << GICH_VMCR_PRIMASK_SHIFT) & GICH_VMCR_PRIMASK_MASK; + + vcpu->arch.vgic_cpu.vgic_v2.vgic_vmcr = vmcr; +} + +static void vgic_v2_enable(struct kvm_vcpu *vcpu) +{ + /* + * By forcing VMCR to zero, the GIC will restore the binary + * points to their reset values. Anything else resets to zero + * anyway. + */ + vcpu->arch.vgic_cpu.vgic_v2.vgic_vmcr = 0; + + /* Get the show on the road... */ + vcpu->arch.vgic_cpu.vgic_v2.vgic_hcr = GICH_HCR_EN; +} + +static const struct vgic_ops vgic_v2_ops = { + .get_lr = vgic_v2_get_lr, + .set_lr = vgic_v2_set_lr, + .sync_lr_elrsr = vgic_v2_sync_lr_elrsr, + .get_elrsr = vgic_v2_get_elrsr, + .get_eisr = vgic_v2_get_eisr, + .get_interrupt_status = vgic_v2_get_interrupt_status, + .enable_underflow = vgic_v2_enable_underflow, + .disable_underflow = vgic_v2_disable_underflow, + .get_vmcr = vgic_v2_get_vmcr, + .set_vmcr = vgic_v2_set_vmcr, + .enable = vgic_v2_enable, +}; + +static struct vgic_params vgic_v2_params; + +/** + * vgic_v2_probe - probe for a GICv2 compatible interrupt controller in DT + * @node: pointer to the DT node + * @ops: address of a pointer to the GICv2 operations + * @params: address of a pointer to HW-specific parameters + * + * Returns 0 if a GICv2 has been found, with the low level operations + * in *ops and the HW parameters in *params. Returns an error code + * otherwise. + */ +int vgic_v2_probe(struct device_node *vgic_node, + const struct vgic_ops **ops, + const struct vgic_params **params) +{ + int ret; + struct resource vctrl_res; + struct resource vcpu_res; + struct vgic_params *vgic = &vgic_v2_params; + + vgic->maint_irq = irq_of_parse_and_map(vgic_node, 0); + if (!vgic->maint_irq) { + kvm_err("error getting vgic maintenance irq from DT\n"); + ret = -ENXIO; + goto out; + } + + ret = of_address_to_resource(vgic_node, 2, &vctrl_res); + if (ret) { + kvm_err("Cannot obtain GICH resource\n"); + goto out; + } + + vgic->vctrl_base = of_iomap(vgic_node, 2); + if (!vgic->vctrl_base) { + kvm_err("Cannot ioremap GICH\n"); + ret = -ENOMEM; + goto out; + } + + vgic->nr_lr = readl_relaxed(vgic->vctrl_base + GICH_VTR); + vgic->nr_lr = (vgic->nr_lr & 0x3f) + 1; + + ret = create_hyp_io_mappings(vgic->vctrl_base, + vgic->vctrl_base + resource_size(&vctrl_res), + vctrl_res.start); + if (ret) { + kvm_err("Cannot map VCTRL into hyp\n"); + goto out_unmap; + } + + if (of_address_to_resource(vgic_node, 3, &vcpu_res)) { + kvm_err("Cannot obtain GICV resource\n"); + ret = -ENXIO; + goto out_unmap; + } + + if (!PAGE_ALIGNED(vcpu_res.start)) { + kvm_err("GICV physical address 0x%llx not page aligned\n", + (unsigned long long)vcpu_res.start); + ret = -ENXIO; + goto out_unmap; + } + + if (!PAGE_ALIGNED(resource_size(&vcpu_res))) { + kvm_err("GICV size 0x%llx not a multiple of page size 0x%lx\n", + (unsigned long long)resource_size(&vcpu_res), + PAGE_SIZE); + ret = -ENXIO; + goto out_unmap; + } + + vgic->vcpu_base = vcpu_res.start; + + kvm_info("%s@%llx IRQ%d\n", vgic_node->name, + vctrl_res.start, vgic->maint_irq); + + vgic->type = VGIC_V2; + *ops = &vgic_v2_ops; + *params = vgic; + goto out; + +out_unmap: + iounmap(vgic->vctrl_base); +out: + of_node_put(vgic_node); + return ret; +} diff --git a/virt/kvm/arm/vgic-v3.c b/virt/kvm/arm/vgic-v3.c new file mode 100644 index 000000000000..1c2c8eef0599 --- /dev/null +++ b/virt/kvm/arm/vgic-v3.c @@ -0,0 +1,247 @@ +/* + * Copyright (C) 2013 ARM Limited, All Rights Reserved. + * Author: Marc Zyngier <marc.zyngier@arm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include <linux/cpu.h> +#include <linux/kvm.h> +#include <linux/kvm_host.h> +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/of.h> +#include <linux/of_address.h> +#include <linux/of_irq.h> + +#include <linux/irqchip/arm-gic-v3.h> + +#include <asm/kvm_emulate.h> +#include <asm/kvm_arm.h> +#include <asm/kvm_mmu.h> + +/* These are for GICv2 emulation only */ +#define GICH_LR_VIRTUALID (0x3ffUL << 0) +#define GICH_LR_PHYSID_CPUID_SHIFT (10) +#define GICH_LR_PHYSID_CPUID (7UL << GICH_LR_PHYSID_CPUID_SHIFT) + +/* + * LRs are stored in reverse order in memory. make sure we index them + * correctly. + */ +#define LR_INDEX(lr) (VGIC_V3_MAX_LRS - 1 - lr) + +static u32 ich_vtr_el2; + +static struct vgic_lr vgic_v3_get_lr(const struct kvm_vcpu *vcpu, int lr) +{ + struct vgic_lr lr_desc; + u64 val = vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[LR_INDEX(lr)]; + + lr_desc.irq = val & GICH_LR_VIRTUALID; + if (lr_desc.irq <= 15) + lr_desc.source = (val >> GICH_LR_PHYSID_CPUID_SHIFT) & 0x7; + else + lr_desc.source = 0; + lr_desc.state = 0; + + if (val & ICH_LR_PENDING_BIT) + lr_desc.state |= LR_STATE_PENDING; + if (val & ICH_LR_ACTIVE_BIT) + lr_desc.state |= LR_STATE_ACTIVE; + if (val & ICH_LR_EOI) + lr_desc.state |= LR_EOI_INT; + + return lr_desc; +} + +static void vgic_v3_set_lr(struct kvm_vcpu *vcpu, int lr, + struct vgic_lr lr_desc) +{ + u64 lr_val = (((u32)lr_desc.source << GICH_LR_PHYSID_CPUID_SHIFT) | + lr_desc.irq); + + if (lr_desc.state & LR_STATE_PENDING) + lr_val |= ICH_LR_PENDING_BIT; + if (lr_desc.state & LR_STATE_ACTIVE) + lr_val |= ICH_LR_ACTIVE_BIT; + if (lr_desc.state & LR_EOI_INT) + lr_val |= ICH_LR_EOI; + + vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[LR_INDEX(lr)] = lr_val; +} + +static void vgic_v3_sync_lr_elrsr(struct kvm_vcpu *vcpu, int lr, + struct vgic_lr lr_desc) +{ + if (!(lr_desc.state & LR_STATE_MASK)) + vcpu->arch.vgic_cpu.vgic_v3.vgic_elrsr |= (1U << lr); +} + +static u64 vgic_v3_get_elrsr(const struct kvm_vcpu *vcpu) +{ + return vcpu->arch.vgic_cpu.vgic_v3.vgic_elrsr; +} + +static u64 vgic_v3_get_eisr(const struct kvm_vcpu *vcpu) +{ + return vcpu->arch.vgic_cpu.vgic_v3.vgic_eisr; +} + +static u32 vgic_v3_get_interrupt_status(const struct kvm_vcpu *vcpu) +{ + u32 misr = vcpu->arch.vgic_cpu.vgic_v3.vgic_misr; + u32 ret = 0; + + if (misr & ICH_MISR_EOI) + ret |= INT_STATUS_EOI; + if (misr & ICH_MISR_U) + ret |= INT_STATUS_UNDERFLOW; + + return ret; +} + +static void vgic_v3_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp) +{ + u32 vmcr = vcpu->arch.vgic_cpu.vgic_v3.vgic_vmcr; + + vmcrp->ctlr = (vmcr & ICH_VMCR_CTLR_MASK) >> ICH_VMCR_CTLR_SHIFT; + vmcrp->abpr = (vmcr & ICH_VMCR_BPR1_MASK) >> ICH_VMCR_BPR1_SHIFT; + vmcrp->bpr = (vmcr & ICH_VMCR_BPR0_MASK) >> ICH_VMCR_BPR0_SHIFT; + vmcrp->pmr = (vmcr & ICH_VMCR_PMR_MASK) >> ICH_VMCR_PMR_SHIFT; +} + +static void vgic_v3_enable_underflow(struct kvm_vcpu *vcpu) +{ + vcpu->arch.vgic_cpu.vgic_v3.vgic_hcr |= ICH_HCR_UIE; +} + +static void vgic_v3_disable_underflow(struct kvm_vcpu *vcpu) +{ + vcpu->arch.vgic_cpu.vgic_v3.vgic_hcr &= ~ICH_HCR_UIE; +} + +static void vgic_v3_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp) +{ + u32 vmcr; + + vmcr = (vmcrp->ctlr << ICH_VMCR_CTLR_SHIFT) & ICH_VMCR_CTLR_MASK; + vmcr |= (vmcrp->abpr << ICH_VMCR_BPR1_SHIFT) & ICH_VMCR_BPR1_MASK; + vmcr |= (vmcrp->bpr << ICH_VMCR_BPR0_SHIFT) & ICH_VMCR_BPR0_MASK; + vmcr |= (vmcrp->pmr << ICH_VMCR_PMR_SHIFT) & ICH_VMCR_PMR_MASK; + + vcpu->arch.vgic_cpu.vgic_v3.vgic_vmcr = vmcr; +} + +static void vgic_v3_enable(struct kvm_vcpu *vcpu) +{ + /* + * By forcing VMCR to zero, the GIC will restore the binary + * points to their reset values. Anything else resets to zero + * anyway. + */ + vcpu->arch.vgic_cpu.vgic_v3.vgic_vmcr = 0; + + /* Get the show on the road... */ + vcpu->arch.vgic_cpu.vgic_v3.vgic_hcr = ICH_HCR_EN; +} + +static const struct vgic_ops vgic_v3_ops = { + .get_lr = vgic_v3_get_lr, + .set_lr = vgic_v3_set_lr, + .sync_lr_elrsr = vgic_v3_sync_lr_elrsr, + .get_elrsr = vgic_v3_get_elrsr, + .get_eisr = vgic_v3_get_eisr, + .get_interrupt_status = vgic_v3_get_interrupt_status, + .enable_underflow = vgic_v3_enable_underflow, + .disable_underflow = vgic_v3_disable_underflow, + .get_vmcr = vgic_v3_get_vmcr, + .set_vmcr = vgic_v3_set_vmcr, + .enable = vgic_v3_enable, +}; + +static struct vgic_params vgic_v3_params; + +/** + * vgic_v3_probe - probe for a GICv3 compatible interrupt controller in DT + * @node: pointer to the DT node + * @ops: address of a pointer to the GICv3 operations + * @params: address of a pointer to HW-specific parameters + * + * Returns 0 if a GICv3 has been found, with the low level operations + * in *ops and the HW parameters in *params. Returns an error code + * otherwise. + */ +int vgic_v3_probe(struct device_node *vgic_node, + const struct vgic_ops **ops, + const struct vgic_params **params) +{ + int ret = 0; + u32 gicv_idx; + struct resource vcpu_res; + struct vgic_params *vgic = &vgic_v3_params; + + vgic->maint_irq = irq_of_parse_and_map(vgic_node, 0); + if (!vgic->maint_irq) { + kvm_err("error getting vgic maintenance irq from DT\n"); + ret = -ENXIO; + goto out; + } + + ich_vtr_el2 = kvm_call_hyp(__vgic_v3_get_ich_vtr_el2); + + /* + * The ListRegs field is 5 bits, but there is a architectural + * maximum of 16 list registers. Just ignore bit 4... + */ + vgic->nr_lr = (ich_vtr_el2 & 0xf) + 1; + + if (of_property_read_u32(vgic_node, "#redistributor-regions", &gicv_idx)) + gicv_idx = 1; + + gicv_idx += 3; /* Also skip GICD, GICC, GICH */ + if (of_address_to_resource(vgic_node, gicv_idx, &vcpu_res)) { + kvm_err("Cannot obtain GICV region\n"); + ret = -ENXIO; + goto out; + } + + if (!PAGE_ALIGNED(vcpu_res.start)) { + kvm_err("GICV physical address 0x%llx not page aligned\n", + (unsigned long long)vcpu_res.start); + ret = -ENXIO; + goto out; + } + + if (!PAGE_ALIGNED(resource_size(&vcpu_res))) { + kvm_err("GICV size 0x%llx not a multiple of page size 0x%lx\n", + (unsigned long long)resource_size(&vcpu_res), + PAGE_SIZE); + ret = -ENXIO; + goto out; + } + + vgic->vcpu_base = vcpu_res.start; + vgic->vctrl_base = NULL; + vgic->type = VGIC_V3; + + kvm_info("%s@%llx IRQ%d\n", vgic_node->name, + vcpu_res.start, vgic->maint_irq); + + *ops = &vgic_v3_ops; + *params = vgic; + +out: + of_node_put(vgic_node); + return ret; +} diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c new file mode 100644 index 000000000000..8e1dc03342c3 --- /dev/null +++ b/virt/kvm/arm/vgic.c @@ -0,0 +1,2464 @@ +/* + * Copyright (C) 2012 ARM Ltd. + * Author: Marc Zyngier <marc.zyngier@arm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#include <linux/cpu.h> +#include <linux/kvm.h> +#include <linux/kvm_host.h> +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/of.h> +#include <linux/of_address.h> +#include <linux/of_irq.h> +#include <linux/uaccess.h> + +#include <linux/irqchip/arm-gic.h> + +#include <asm/kvm_emulate.h> +#include <asm/kvm_arm.h> +#include <asm/kvm_mmu.h> + +/* + * How the whole thing works (courtesy of Christoffer Dall): + * + * - At any time, the dist->irq_pending_on_cpu is the oracle that knows if + * something is pending on the CPU interface. + * - Interrupts that are pending on the distributor are stored on the + * vgic.irq_pending vgic bitmap (this bitmap is updated by both user land + * ioctls and guest mmio ops, and other in-kernel peripherals such as the + * arch. timers). + * - Every time the bitmap changes, the irq_pending_on_cpu oracle is + * recalculated + * - To calculate the oracle, we need info for each cpu from + * compute_pending_for_cpu, which considers: + * - PPI: dist->irq_pending & dist->irq_enable + * - SPI: dist->irq_pending & dist->irq_enable & dist->irq_spi_target + * - irq_spi_target is a 'formatted' version of the GICD_ITARGETSRn + * registers, stored on each vcpu. We only keep one bit of + * information per interrupt, making sure that only one vcpu can + * accept the interrupt. + * - If any of the above state changes, we must recalculate the oracle. + * - The same is true when injecting an interrupt, except that we only + * consider a single interrupt at a time. The irq_spi_cpu array + * contains the target CPU for each SPI. + * + * The handling of level interrupts adds some extra complexity. We + * need to track when the interrupt has been EOIed, so we can sample + * the 'line' again. This is achieved as such: + * + * - When a level interrupt is moved onto a vcpu, the corresponding + * bit in irq_queued is set. As long as this bit is set, the line + * will be ignored for further interrupts. The interrupt is injected + * into the vcpu with the GICH_LR_EOI bit set (generate a + * maintenance interrupt on EOI). + * - When the interrupt is EOIed, the maintenance interrupt fires, + * and clears the corresponding bit in irq_queued. This allows the + * interrupt line to be sampled again. + * - Note that level-triggered interrupts can also be set to pending from + * writes to GICD_ISPENDRn and lowering the external input line does not + * cause the interrupt to become inactive in such a situation. + * Conversely, writes to GICD_ICPENDRn do not cause the interrupt to become + * inactive as long as the external input line is held high. + */ + +#define VGIC_ADDR_UNDEF (-1) +#define IS_VGIC_ADDR_UNDEF(_x) ((_x) == VGIC_ADDR_UNDEF) + +#define PRODUCT_ID_KVM 0x4b /* ASCII code K */ +#define IMPLEMENTER_ARM 0x43b +#define GICC_ARCH_VERSION_V2 0x2 + +#define ACCESS_READ_VALUE (1 << 0) +#define ACCESS_READ_RAZ (0 << 0) +#define ACCESS_READ_MASK(x) ((x) & (1 << 0)) +#define ACCESS_WRITE_IGNORED (0 << 1) +#define ACCESS_WRITE_SETBIT (1 << 1) +#define ACCESS_WRITE_CLEARBIT (2 << 1) +#define ACCESS_WRITE_VALUE (3 << 1) +#define ACCESS_WRITE_MASK(x) ((x) & (3 << 1)) + +static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu); +static void vgic_retire_lr(int lr_nr, int irq, struct kvm_vcpu *vcpu); +static void vgic_update_state(struct kvm *kvm); +static void vgic_kick_vcpus(struct kvm *kvm); +static u8 *vgic_get_sgi_sources(struct vgic_dist *dist, int vcpu_id, int sgi); +static void vgic_dispatch_sgi(struct kvm_vcpu *vcpu, u32 reg); +static struct vgic_lr vgic_get_lr(const struct kvm_vcpu *vcpu, int lr); +static void vgic_set_lr(struct kvm_vcpu *vcpu, int lr, struct vgic_lr lr_desc); +static void vgic_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr); +static void vgic_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr); + +static const struct vgic_ops *vgic_ops; +static const struct vgic_params *vgic; + +/* + * struct vgic_bitmap contains a bitmap made of unsigned longs, but + * extracts u32s out of them. + * + * This does not work on 64-bit BE systems, because the bitmap access + * will store two consecutive 32-bit words with the higher-addressed + * register's bits at the lower index and the lower-addressed register's + * bits at the higher index. + * + * Therefore, swizzle the register index when accessing the 32-bit word + * registers to access the right register's value. + */ +#if defined(CONFIG_CPU_BIG_ENDIAN) && BITS_PER_LONG == 64 +#define REG_OFFSET_SWIZZLE 1 +#else +#define REG_OFFSET_SWIZZLE 0 +#endif + +static int vgic_init_bitmap(struct vgic_bitmap *b, int nr_cpus, int nr_irqs) +{ + int nr_longs; + + nr_longs = nr_cpus + BITS_TO_LONGS(nr_irqs - VGIC_NR_PRIVATE_IRQS); + + b->private = kzalloc(sizeof(unsigned long) * nr_longs, GFP_KERNEL); + if (!b->private) + return -ENOMEM; + + b->shared = b->private + nr_cpus; + + return 0; +} + +static void vgic_free_bitmap(struct vgic_bitmap *b) +{ + kfree(b->private); + b->private = NULL; + b->shared = NULL; +} + +static u32 *vgic_bitmap_get_reg(struct vgic_bitmap *x, + int cpuid, u32 offset) +{ + offset >>= 2; + if (!offset) + return (u32 *)(x->private + cpuid) + REG_OFFSET_SWIZZLE; + else + return (u32 *)(x->shared) + ((offset - 1) ^ REG_OFFSET_SWIZZLE); +} + +static int vgic_bitmap_get_irq_val(struct vgic_bitmap *x, + int cpuid, int irq) +{ + if (irq < VGIC_NR_PRIVATE_IRQS) + return test_bit(irq, x->private + cpuid); + + return test_bit(irq - VGIC_NR_PRIVATE_IRQS, x->shared); +} + +static void vgic_bitmap_set_irq_val(struct vgic_bitmap *x, int cpuid, + int irq, int val) +{ + unsigned long *reg; + + if (irq < VGIC_NR_PRIVATE_IRQS) { + reg = x->private + cpuid; + } else { + reg = x->shared; + irq -= VGIC_NR_PRIVATE_IRQS; + } + + if (val) + set_bit(irq, reg); + else + clear_bit(irq, reg); +} + +static unsigned long *vgic_bitmap_get_cpu_map(struct vgic_bitmap *x, int cpuid) +{ + return x->private + cpuid; +} + +static unsigned long *vgic_bitmap_get_shared_map(struct vgic_bitmap *x) +{ + return x->shared; +} + +static int vgic_init_bytemap(struct vgic_bytemap *x, int nr_cpus, int nr_irqs) +{ + int size; + + size = nr_cpus * VGIC_NR_PRIVATE_IRQS; + size += nr_irqs - VGIC_NR_PRIVATE_IRQS; + + x->private = kzalloc(size, GFP_KERNEL); + if (!x->private) + return -ENOMEM; + + x->shared = x->private + nr_cpus * VGIC_NR_PRIVATE_IRQS / sizeof(u32); + return 0; +} + +static void vgic_free_bytemap(struct vgic_bytemap *b) +{ + kfree(b->private); + b->private = NULL; + b->shared = NULL; +} + +static u32 *vgic_bytemap_get_reg(struct vgic_bytemap *x, int cpuid, u32 offset) +{ + u32 *reg; + + if (offset < VGIC_NR_PRIVATE_IRQS) { + reg = x->private; + offset += cpuid * VGIC_NR_PRIVATE_IRQS; + } else { + reg = x->shared; + offset -= VGIC_NR_PRIVATE_IRQS; + } + + return reg + (offset / sizeof(u32)); +} + +#define VGIC_CFG_LEVEL 0 +#define VGIC_CFG_EDGE 1 + +static bool vgic_irq_is_edge(struct kvm_vcpu *vcpu, int irq) +{ + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + int irq_val; + + irq_val = vgic_bitmap_get_irq_val(&dist->irq_cfg, vcpu->vcpu_id, irq); + return irq_val == VGIC_CFG_EDGE; +} + +static int vgic_irq_is_enabled(struct kvm_vcpu *vcpu, int irq) +{ + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + + return vgic_bitmap_get_irq_val(&dist->irq_enabled, vcpu->vcpu_id, irq); +} + +static int vgic_irq_is_queued(struct kvm_vcpu *vcpu, int irq) +{ + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + + return vgic_bitmap_get_irq_val(&dist->irq_queued, vcpu->vcpu_id, irq); +} + +static void vgic_irq_set_queued(struct kvm_vcpu *vcpu, int irq) +{ + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + + vgic_bitmap_set_irq_val(&dist->irq_queued, vcpu->vcpu_id, irq, 1); +} + +static void vgic_irq_clear_queued(struct kvm_vcpu *vcpu, int irq) +{ + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + + vgic_bitmap_set_irq_val(&dist->irq_queued, vcpu->vcpu_id, irq, 0); +} + +static int vgic_dist_irq_get_level(struct kvm_vcpu *vcpu, int irq) +{ + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + + return vgic_bitmap_get_irq_val(&dist->irq_level, vcpu->vcpu_id, irq); +} + +static void vgic_dist_irq_set_level(struct kvm_vcpu *vcpu, int irq) +{ + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + + vgic_bitmap_set_irq_val(&dist->irq_level, vcpu->vcpu_id, irq, 1); +} + +static void vgic_dist_irq_clear_level(struct kvm_vcpu *vcpu, int irq) +{ + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + + vgic_bitmap_set_irq_val(&dist->irq_level, vcpu->vcpu_id, irq, 0); +} + +static int vgic_dist_irq_soft_pend(struct kvm_vcpu *vcpu, int irq) +{ + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + + return vgic_bitmap_get_irq_val(&dist->irq_soft_pend, vcpu->vcpu_id, irq); +} + +static void vgic_dist_irq_clear_soft_pend(struct kvm_vcpu *vcpu, int irq) +{ + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + + vgic_bitmap_set_irq_val(&dist->irq_soft_pend, vcpu->vcpu_id, irq, 0); +} + +static int vgic_dist_irq_is_pending(struct kvm_vcpu *vcpu, int irq) +{ + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + + return vgic_bitmap_get_irq_val(&dist->irq_pending, vcpu->vcpu_id, irq); +} + +static void vgic_dist_irq_set_pending(struct kvm_vcpu *vcpu, int irq) +{ + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + + vgic_bitmap_set_irq_val(&dist->irq_pending, vcpu->vcpu_id, irq, 1); +} + +static void vgic_dist_irq_clear_pending(struct kvm_vcpu *vcpu, int irq) +{ + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + + vgic_bitmap_set_irq_val(&dist->irq_pending, vcpu->vcpu_id, irq, 0); +} + +static void vgic_cpu_irq_set(struct kvm_vcpu *vcpu, int irq) +{ + if (irq < VGIC_NR_PRIVATE_IRQS) + set_bit(irq, vcpu->arch.vgic_cpu.pending_percpu); + else + set_bit(irq - VGIC_NR_PRIVATE_IRQS, + vcpu->arch.vgic_cpu.pending_shared); +} + +static void vgic_cpu_irq_clear(struct kvm_vcpu *vcpu, int irq) +{ + if (irq < VGIC_NR_PRIVATE_IRQS) + clear_bit(irq, vcpu->arch.vgic_cpu.pending_percpu); + else + clear_bit(irq - VGIC_NR_PRIVATE_IRQS, + vcpu->arch.vgic_cpu.pending_shared); +} + +static bool vgic_can_sample_irq(struct kvm_vcpu *vcpu, int irq) +{ + return vgic_irq_is_edge(vcpu, irq) || !vgic_irq_is_queued(vcpu, irq); +} + +static u32 mmio_data_read(struct kvm_exit_mmio *mmio, u32 mask) +{ + return le32_to_cpu(*((u32 *)mmio->data)) & mask; +} + +static void mmio_data_write(struct kvm_exit_mmio *mmio, u32 mask, u32 value) +{ + *((u32 *)mmio->data) = cpu_to_le32(value) & mask; +} + +/** + * vgic_reg_access - access vgic register + * @mmio: pointer to the data describing the mmio access + * @reg: pointer to the virtual backing of vgic distributor data + * @offset: least significant 2 bits used for word offset + * @mode: ACCESS_ mode (see defines above) + * + * Helper to make vgic register access easier using one of the access + * modes defined for vgic register access + * (read,raz,write-ignored,setbit,clearbit,write) + */ +static void vgic_reg_access(struct kvm_exit_mmio *mmio, u32 *reg, + phys_addr_t offset, int mode) +{ + int word_offset = (offset & 3) * 8; + u32 mask = (1UL << (mmio->len * 8)) - 1; + u32 regval; + + /* + * Any alignment fault should have been delivered to the guest + * directly (ARM ARM B3.12.7 "Prioritization of aborts"). + */ + + if (reg) { + regval = *reg; + } else { + BUG_ON(mode != (ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED)); + regval = 0; + } + + if (mmio->is_write) { + u32 data = mmio_data_read(mmio, mask) << word_offset; + switch (ACCESS_WRITE_MASK(mode)) { + case ACCESS_WRITE_IGNORED: + return; + + case ACCESS_WRITE_SETBIT: + regval |= data; + break; + + case ACCESS_WRITE_CLEARBIT: + regval &= ~data; + break; + + case ACCESS_WRITE_VALUE: + regval = (regval & ~(mask << word_offset)) | data; + break; + } + *reg = regval; + } else { + switch (ACCESS_READ_MASK(mode)) { + case ACCESS_READ_RAZ: + regval = 0; + /* fall through */ + + case ACCESS_READ_VALUE: + mmio_data_write(mmio, mask, regval >> word_offset); + } + } +} + +static bool handle_mmio_misc(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, phys_addr_t offset) +{ + u32 reg; + u32 word_offset = offset & 3; + + switch (offset & ~3) { + case 0: /* GICD_CTLR */ + reg = vcpu->kvm->arch.vgic.enabled; + vgic_reg_access(mmio, ®, word_offset, + ACCESS_READ_VALUE | ACCESS_WRITE_VALUE); + if (mmio->is_write) { + vcpu->kvm->arch.vgic.enabled = reg & 1; + vgic_update_state(vcpu->kvm); + return true; + } + break; + + case 4: /* GICD_TYPER */ + reg = (atomic_read(&vcpu->kvm->online_vcpus) - 1) << 5; + reg |= (vcpu->kvm->arch.vgic.nr_irqs >> 5) - 1; + vgic_reg_access(mmio, ®, word_offset, + ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED); + break; + + case 8: /* GICD_IIDR */ + reg = (PRODUCT_ID_KVM << 24) | (IMPLEMENTER_ARM << 0); + vgic_reg_access(mmio, ®, word_offset, + ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED); + break; + } + + return false; +} + +static bool handle_mmio_raz_wi(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, phys_addr_t offset) +{ + vgic_reg_access(mmio, NULL, offset, + ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED); + return false; +} + +static bool handle_mmio_set_enable_reg(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, + phys_addr_t offset) +{ + u32 *reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_enabled, + vcpu->vcpu_id, offset); + vgic_reg_access(mmio, reg, offset, + ACCESS_READ_VALUE | ACCESS_WRITE_SETBIT); + if (mmio->is_write) { + vgic_update_state(vcpu->kvm); + return true; + } + + return false; +} + +static bool handle_mmio_clear_enable_reg(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, + phys_addr_t offset) +{ + u32 *reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_enabled, + vcpu->vcpu_id, offset); + vgic_reg_access(mmio, reg, offset, + ACCESS_READ_VALUE | ACCESS_WRITE_CLEARBIT); + if (mmio->is_write) { + if (offset < 4) /* Force SGI enabled */ + *reg |= 0xffff; + vgic_retire_disabled_irqs(vcpu); + vgic_update_state(vcpu->kvm); + return true; + } + + return false; +} + +static bool handle_mmio_set_pending_reg(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, + phys_addr_t offset) +{ + u32 *reg, orig; + u32 level_mask; + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + + reg = vgic_bitmap_get_reg(&dist->irq_cfg, vcpu->vcpu_id, offset); + level_mask = (~(*reg)); + + /* Mark both level and edge triggered irqs as pending */ + reg = vgic_bitmap_get_reg(&dist->irq_pending, vcpu->vcpu_id, offset); + orig = *reg; + vgic_reg_access(mmio, reg, offset, + ACCESS_READ_VALUE | ACCESS_WRITE_SETBIT); + + if (mmio->is_write) { + /* Set the soft-pending flag only for level-triggered irqs */ + reg = vgic_bitmap_get_reg(&dist->irq_soft_pend, + vcpu->vcpu_id, offset); + vgic_reg_access(mmio, reg, offset, + ACCESS_READ_VALUE | ACCESS_WRITE_SETBIT); + *reg &= level_mask; + + /* Ignore writes to SGIs */ + if (offset < 2) { + *reg &= ~0xffff; + *reg |= orig & 0xffff; + } + + vgic_update_state(vcpu->kvm); + return true; + } + + return false; +} + +static bool handle_mmio_clear_pending_reg(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, + phys_addr_t offset) +{ + u32 *level_active; + u32 *reg, orig; + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + + reg = vgic_bitmap_get_reg(&dist->irq_pending, vcpu->vcpu_id, offset); + orig = *reg; + vgic_reg_access(mmio, reg, offset, + ACCESS_READ_VALUE | ACCESS_WRITE_CLEARBIT); + if (mmio->is_write) { + /* Re-set level triggered level-active interrupts */ + level_active = vgic_bitmap_get_reg(&dist->irq_level, + vcpu->vcpu_id, offset); + reg = vgic_bitmap_get_reg(&dist->irq_pending, + vcpu->vcpu_id, offset); + *reg |= *level_active; + + /* Ignore writes to SGIs */ + if (offset < 2) { + *reg &= ~0xffff; + *reg |= orig & 0xffff; + } + + /* Clear soft-pending flags */ + reg = vgic_bitmap_get_reg(&dist->irq_soft_pend, + vcpu->vcpu_id, offset); + vgic_reg_access(mmio, reg, offset, + ACCESS_READ_VALUE | ACCESS_WRITE_CLEARBIT); + + vgic_update_state(vcpu->kvm); + return true; + } + + return false; +} + +static bool handle_mmio_priority_reg(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, + phys_addr_t offset) +{ + u32 *reg = vgic_bytemap_get_reg(&vcpu->kvm->arch.vgic.irq_priority, + vcpu->vcpu_id, offset); + vgic_reg_access(mmio, reg, offset, + ACCESS_READ_VALUE | ACCESS_WRITE_VALUE); + return false; +} + +#define GICD_ITARGETSR_SIZE 32 +#define GICD_CPUTARGETS_BITS 8 +#define GICD_IRQS_PER_ITARGETSR (GICD_ITARGETSR_SIZE / GICD_CPUTARGETS_BITS) +static u32 vgic_get_target_reg(struct kvm *kvm, int irq) +{ + struct vgic_dist *dist = &kvm->arch.vgic; + int i; + u32 val = 0; + + irq -= VGIC_NR_PRIVATE_IRQS; + + for (i = 0; i < GICD_IRQS_PER_ITARGETSR; i++) + val |= 1 << (dist->irq_spi_cpu[irq + i] + i * 8); + + return val; +} + +static void vgic_set_target_reg(struct kvm *kvm, u32 val, int irq) +{ + struct vgic_dist *dist = &kvm->arch.vgic; + struct kvm_vcpu *vcpu; + int i, c; + unsigned long *bmap; + u32 target; + + irq -= VGIC_NR_PRIVATE_IRQS; + + /* + * Pick the LSB in each byte. This ensures we target exactly + * one vcpu per IRQ. If the byte is null, assume we target + * CPU0. + */ + for (i = 0; i < GICD_IRQS_PER_ITARGETSR; i++) { + int shift = i * GICD_CPUTARGETS_BITS; + target = ffs((val >> shift) & 0xffU); + target = target ? (target - 1) : 0; + dist->irq_spi_cpu[irq + i] = target; + kvm_for_each_vcpu(c, vcpu, kvm) { + bmap = vgic_bitmap_get_shared_map(&dist->irq_spi_target[c]); + if (c == target) + set_bit(irq + i, bmap); + else + clear_bit(irq + i, bmap); + } + } +} + +static bool handle_mmio_target_reg(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, + phys_addr_t offset) +{ + u32 reg; + + /* We treat the banked interrupts targets as read-only */ + if (offset < 32) { + u32 roreg = 1 << vcpu->vcpu_id; + roreg |= roreg << 8; + roreg |= roreg << 16; + + vgic_reg_access(mmio, &roreg, offset, + ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED); + return false; + } + + reg = vgic_get_target_reg(vcpu->kvm, offset & ~3U); + vgic_reg_access(mmio, ®, offset, + ACCESS_READ_VALUE | ACCESS_WRITE_VALUE); + if (mmio->is_write) { + vgic_set_target_reg(vcpu->kvm, reg, offset & ~3U); + vgic_update_state(vcpu->kvm); + return true; + } + + return false; +} + +static u32 vgic_cfg_expand(u16 val) +{ + u32 res = 0; + int i; + + /* + * Turn a 16bit value like abcd...mnop into a 32bit word + * a0b0c0d0...m0n0o0p0, which is what the HW cfg register is. + */ + for (i = 0; i < 16; i++) + res |= ((val >> i) & VGIC_CFG_EDGE) << (2 * i + 1); + + return res; +} + +static u16 vgic_cfg_compress(u32 val) +{ + u16 res = 0; + int i; + + /* + * Turn a 32bit word a0b0c0d0...m0n0o0p0 into 16bit value like + * abcd...mnop which is what we really care about. + */ + for (i = 0; i < 16; i++) + res |= ((val >> (i * 2 + 1)) & VGIC_CFG_EDGE) << i; + + return res; +} + +/* + * The distributor uses 2 bits per IRQ for the CFG register, but the + * LSB is always 0. As such, we only keep the upper bit, and use the + * two above functions to compress/expand the bits + */ +static bool handle_mmio_cfg_reg(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, phys_addr_t offset) +{ + u32 val; + u32 *reg; + + reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_cfg, + vcpu->vcpu_id, offset >> 1); + + if (offset & 4) + val = *reg >> 16; + else + val = *reg & 0xffff; + + val = vgic_cfg_expand(val); + vgic_reg_access(mmio, &val, offset, + ACCESS_READ_VALUE | ACCESS_WRITE_VALUE); + if (mmio->is_write) { + if (offset < 8) { + *reg = ~0U; /* Force PPIs/SGIs to 1 */ + return false; + } + + val = vgic_cfg_compress(val); + if (offset & 4) { + *reg &= 0xffff; + *reg |= val << 16; + } else { + *reg &= 0xffff << 16; + *reg |= val; + } + } + + return false; +} + +static bool handle_mmio_sgi_reg(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, phys_addr_t offset) +{ + u32 reg; + vgic_reg_access(mmio, ®, offset, + ACCESS_READ_RAZ | ACCESS_WRITE_VALUE); + if (mmio->is_write) { + vgic_dispatch_sgi(vcpu, reg); + vgic_update_state(vcpu->kvm); + return true; + } + + return false; +} + +/** + * vgic_unqueue_irqs - move pending IRQs from LRs to the distributor + * @vgic_cpu: Pointer to the vgic_cpu struct holding the LRs + * + * Move any pending IRQs that have already been assigned to LRs back to the + * emulated distributor state so that the complete emulated state can be read + * from the main emulation structures without investigating the LRs. + * + * Note that IRQs in the active state in the LRs get their pending state moved + * to the distributor but the active state stays in the LRs, because we don't + * track the active state on the distributor side. + */ +static void vgic_unqueue_irqs(struct kvm_vcpu *vcpu) +{ + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + int vcpu_id = vcpu->vcpu_id; + int i; + + for_each_set_bit(i, vgic_cpu->lr_used, vgic_cpu->nr_lr) { + struct vgic_lr lr = vgic_get_lr(vcpu, i); + + /* + * There are three options for the state bits: + * + * 01: pending + * 10: active + * 11: pending and active + * + * If the LR holds only an active interrupt (not pending) then + * just leave it alone. + */ + if ((lr.state & LR_STATE_MASK) == LR_STATE_ACTIVE) + continue; + + /* + * Reestablish the pending state on the distributor and the + * CPU interface. It may have already been pending, but that + * is fine, then we are only setting a few bits that were + * already set. + */ + vgic_dist_irq_set_pending(vcpu, lr.irq); + if (lr.irq < VGIC_NR_SGIS) + *vgic_get_sgi_sources(dist, vcpu_id, lr.irq) |= 1 << lr.source; + lr.state &= ~LR_STATE_PENDING; + vgic_set_lr(vcpu, i, lr); + + /* + * If there's no state left on the LR (it could still be + * active), then the LR does not hold any useful info and can + * be marked as free for other use. + */ + if (!(lr.state & LR_STATE_MASK)) { + vgic_retire_lr(i, lr.irq, vcpu); + vgic_irq_clear_queued(vcpu, lr.irq); + } + + /* Finally update the VGIC state. */ + vgic_update_state(vcpu->kvm); + } +} + +/* Handle reads of GICD_CPENDSGIRn and GICD_SPENDSGIRn */ +static bool read_set_clear_sgi_pend_reg(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, + phys_addr_t offset) +{ + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + int sgi; + int min_sgi = (offset & ~0x3); + int max_sgi = min_sgi + 3; + int vcpu_id = vcpu->vcpu_id; + u32 reg = 0; + + /* Copy source SGIs from distributor side */ + for (sgi = min_sgi; sgi <= max_sgi; sgi++) { + int shift = 8 * (sgi - min_sgi); + reg |= ((u32)*vgic_get_sgi_sources(dist, vcpu_id, sgi)) << shift; + } + + mmio_data_write(mmio, ~0, reg); + return false; +} + +static bool write_set_clear_sgi_pend_reg(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, + phys_addr_t offset, bool set) +{ + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + int sgi; + int min_sgi = (offset & ~0x3); + int max_sgi = min_sgi + 3; + int vcpu_id = vcpu->vcpu_id; + u32 reg; + bool updated = false; + + reg = mmio_data_read(mmio, ~0); + + /* Clear pending SGIs on the distributor */ + for (sgi = min_sgi; sgi <= max_sgi; sgi++) { + u8 mask = reg >> (8 * (sgi - min_sgi)); + u8 *src = vgic_get_sgi_sources(dist, vcpu_id, sgi); + if (set) { + if ((*src & mask) != mask) + updated = true; + *src |= mask; + } else { + if (*src & mask) + updated = true; + *src &= ~mask; + } + } + + if (updated) + vgic_update_state(vcpu->kvm); + + return updated; +} + +static bool handle_mmio_sgi_set(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, + phys_addr_t offset) +{ + if (!mmio->is_write) + return read_set_clear_sgi_pend_reg(vcpu, mmio, offset); + else + return write_set_clear_sgi_pend_reg(vcpu, mmio, offset, true); +} + +static bool handle_mmio_sgi_clear(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, + phys_addr_t offset) +{ + if (!mmio->is_write) + return read_set_clear_sgi_pend_reg(vcpu, mmio, offset); + else + return write_set_clear_sgi_pend_reg(vcpu, mmio, offset, false); +} + +/* + * I would have liked to use the kvm_bus_io_*() API instead, but it + * cannot cope with banked registers (only the VM pointer is passed + * around, and we need the vcpu). One of these days, someone please + * fix it! + */ +struct mmio_range { + phys_addr_t base; + unsigned long len; + int bits_per_irq; + bool (*handle_mmio)(struct kvm_vcpu *vcpu, struct kvm_exit_mmio *mmio, + phys_addr_t offset); +}; + +static const struct mmio_range vgic_dist_ranges[] = { + { + .base = GIC_DIST_CTRL, + .len = 12, + .bits_per_irq = 0, + .handle_mmio = handle_mmio_misc, + }, + { + .base = GIC_DIST_IGROUP, + .len = VGIC_MAX_IRQS / 8, + .bits_per_irq = 1, + .handle_mmio = handle_mmio_raz_wi, + }, + { + .base = GIC_DIST_ENABLE_SET, + .len = VGIC_MAX_IRQS / 8, + .bits_per_irq = 1, + .handle_mmio = handle_mmio_set_enable_reg, + }, + { + .base = GIC_DIST_ENABLE_CLEAR, + .len = VGIC_MAX_IRQS / 8, + .bits_per_irq = 1, + .handle_mmio = handle_mmio_clear_enable_reg, + }, + { + .base = GIC_DIST_PENDING_SET, + .len = VGIC_MAX_IRQS / 8, + .bits_per_irq = 1, + .handle_mmio = handle_mmio_set_pending_reg, + }, + { + .base = GIC_DIST_PENDING_CLEAR, + .len = VGIC_MAX_IRQS / 8, + .bits_per_irq = 1, + .handle_mmio = handle_mmio_clear_pending_reg, + }, + { + .base = GIC_DIST_ACTIVE_SET, + .len = VGIC_MAX_IRQS / 8, + .bits_per_irq = 1, + .handle_mmio = handle_mmio_raz_wi, + }, + { + .base = GIC_DIST_ACTIVE_CLEAR, + .len = VGIC_MAX_IRQS / 8, + .bits_per_irq = 1, + .handle_mmio = handle_mmio_raz_wi, + }, + { + .base = GIC_DIST_PRI, + .len = VGIC_MAX_IRQS, + .bits_per_irq = 8, + .handle_mmio = handle_mmio_priority_reg, + }, + { + .base = GIC_DIST_TARGET, + .len = VGIC_MAX_IRQS, + .bits_per_irq = 8, + .handle_mmio = handle_mmio_target_reg, + }, + { + .base = GIC_DIST_CONFIG, + .len = VGIC_MAX_IRQS / 4, + .bits_per_irq = 2, + .handle_mmio = handle_mmio_cfg_reg, + }, + { + .base = GIC_DIST_SOFTINT, + .len = 4, + .handle_mmio = handle_mmio_sgi_reg, + }, + { + .base = GIC_DIST_SGI_PENDING_CLEAR, + .len = VGIC_NR_SGIS, + .handle_mmio = handle_mmio_sgi_clear, + }, + { + .base = GIC_DIST_SGI_PENDING_SET, + .len = VGIC_NR_SGIS, + .handle_mmio = handle_mmio_sgi_set, + }, + {} +}; + +static const +struct mmio_range *find_matching_range(const struct mmio_range *ranges, + struct kvm_exit_mmio *mmio, + phys_addr_t offset) +{ + const struct mmio_range *r = ranges; + + while (r->len) { + if (offset >= r->base && + (offset + mmio->len) <= (r->base + r->len)) + return r; + r++; + } + + return NULL; +} + +static bool vgic_validate_access(const struct vgic_dist *dist, + const struct mmio_range *range, + unsigned long offset) +{ + int irq; + + if (!range->bits_per_irq) + return true; /* Not an irq-based access */ + + irq = offset * 8 / range->bits_per_irq; + if (irq >= dist->nr_irqs) + return false; + + return true; +} + +/** + * vgic_handle_mmio - handle an in-kernel MMIO access + * @vcpu: pointer to the vcpu performing the access + * @run: pointer to the kvm_run structure + * @mmio: pointer to the data describing the access + * + * returns true if the MMIO access has been performed in kernel space, + * and false if it needs to be emulated in user space. + */ +bool vgic_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run, + struct kvm_exit_mmio *mmio) +{ + const struct mmio_range *range; + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + unsigned long base = dist->vgic_dist_base; + bool updated_state; + unsigned long offset; + + if (!irqchip_in_kernel(vcpu->kvm) || + mmio->phys_addr < base || + (mmio->phys_addr + mmio->len) > (base + KVM_VGIC_V2_DIST_SIZE)) + return false; + + /* We don't support ldrd / strd or ldm / stm to the emulated vgic */ + if (mmio->len > 4) { + kvm_inject_dabt(vcpu, mmio->phys_addr); + return true; + } + + offset = mmio->phys_addr - base; + range = find_matching_range(vgic_dist_ranges, mmio, offset); + if (unlikely(!range || !range->handle_mmio)) { + pr_warn("Unhandled access %d %08llx %d\n", + mmio->is_write, mmio->phys_addr, mmio->len); + return false; + } + + spin_lock(&vcpu->kvm->arch.vgic.lock); + offset = mmio->phys_addr - range->base - base; + if (vgic_validate_access(dist, range, offset)) { + updated_state = range->handle_mmio(vcpu, mmio, offset); + } else { + vgic_reg_access(mmio, NULL, offset, + ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED); + updated_state = false; + } + spin_unlock(&vcpu->kvm->arch.vgic.lock); + kvm_prepare_mmio(run, mmio); + kvm_handle_mmio_return(vcpu, run); + + if (updated_state) + vgic_kick_vcpus(vcpu->kvm); + + return true; +} + +static u8 *vgic_get_sgi_sources(struct vgic_dist *dist, int vcpu_id, int sgi) +{ + return dist->irq_sgi_sources + vcpu_id * VGIC_NR_SGIS + sgi; +} + +static void vgic_dispatch_sgi(struct kvm_vcpu *vcpu, u32 reg) +{ + struct kvm *kvm = vcpu->kvm; + struct vgic_dist *dist = &kvm->arch.vgic; + int nrcpus = atomic_read(&kvm->online_vcpus); + u8 target_cpus; + int sgi, mode, c, vcpu_id; + + vcpu_id = vcpu->vcpu_id; + + sgi = reg & 0xf; + target_cpus = (reg >> 16) & 0xff; + mode = (reg >> 24) & 3; + + switch (mode) { + case 0: + if (!target_cpus) + return; + break; + + case 1: + target_cpus = ((1 << nrcpus) - 1) & ~(1 << vcpu_id) & 0xff; + break; + + case 2: + target_cpus = 1 << vcpu_id; + break; + } + + kvm_for_each_vcpu(c, vcpu, kvm) { + if (target_cpus & 1) { + /* Flag the SGI as pending */ + vgic_dist_irq_set_pending(vcpu, sgi); + *vgic_get_sgi_sources(dist, c, sgi) |= 1 << vcpu_id; + kvm_debug("SGI%d from CPU%d to CPU%d\n", sgi, vcpu_id, c); + } + + target_cpus >>= 1; + } +} + +static int vgic_nr_shared_irqs(struct vgic_dist *dist) +{ + return dist->nr_irqs - VGIC_NR_PRIVATE_IRQS; +} + +static int compute_pending_for_cpu(struct kvm_vcpu *vcpu) +{ + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + unsigned long *pending, *enabled, *pend_percpu, *pend_shared; + unsigned long pending_private, pending_shared; + int nr_shared = vgic_nr_shared_irqs(dist); + int vcpu_id; + + vcpu_id = vcpu->vcpu_id; + pend_percpu = vcpu->arch.vgic_cpu.pending_percpu; + pend_shared = vcpu->arch.vgic_cpu.pending_shared; + + pending = vgic_bitmap_get_cpu_map(&dist->irq_pending, vcpu_id); + enabled = vgic_bitmap_get_cpu_map(&dist->irq_enabled, vcpu_id); + bitmap_and(pend_percpu, pending, enabled, VGIC_NR_PRIVATE_IRQS); + + pending = vgic_bitmap_get_shared_map(&dist->irq_pending); + enabled = vgic_bitmap_get_shared_map(&dist->irq_enabled); + bitmap_and(pend_shared, pending, enabled, nr_shared); + bitmap_and(pend_shared, pend_shared, + vgic_bitmap_get_shared_map(&dist->irq_spi_target[vcpu_id]), + nr_shared); + + pending_private = find_first_bit(pend_percpu, VGIC_NR_PRIVATE_IRQS); + pending_shared = find_first_bit(pend_shared, nr_shared); + return (pending_private < VGIC_NR_PRIVATE_IRQS || + pending_shared < vgic_nr_shared_irqs(dist)); +} + +/* + * Update the interrupt state and determine which CPUs have pending + * interrupts. Must be called with distributor lock held. + */ +static void vgic_update_state(struct kvm *kvm) +{ + struct vgic_dist *dist = &kvm->arch.vgic; + struct kvm_vcpu *vcpu; + int c; + + if (!dist->enabled) { + set_bit(0, dist->irq_pending_on_cpu); + return; + } + + kvm_for_each_vcpu(c, vcpu, kvm) { + if (compute_pending_for_cpu(vcpu)) { + pr_debug("CPU%d has pending interrupts\n", c); + set_bit(c, dist->irq_pending_on_cpu); + } + } +} + +static struct vgic_lr vgic_get_lr(const struct kvm_vcpu *vcpu, int lr) +{ + return vgic_ops->get_lr(vcpu, lr); +} + +static void vgic_set_lr(struct kvm_vcpu *vcpu, int lr, + struct vgic_lr vlr) +{ + vgic_ops->set_lr(vcpu, lr, vlr); +} + +static void vgic_sync_lr_elrsr(struct kvm_vcpu *vcpu, int lr, + struct vgic_lr vlr) +{ + vgic_ops->sync_lr_elrsr(vcpu, lr, vlr); +} + +static inline u64 vgic_get_elrsr(struct kvm_vcpu *vcpu) +{ + return vgic_ops->get_elrsr(vcpu); +} + +static inline u64 vgic_get_eisr(struct kvm_vcpu *vcpu) +{ + return vgic_ops->get_eisr(vcpu); +} + +static inline u32 vgic_get_interrupt_status(struct kvm_vcpu *vcpu) +{ + return vgic_ops->get_interrupt_status(vcpu); +} + +static inline void vgic_enable_underflow(struct kvm_vcpu *vcpu) +{ + vgic_ops->enable_underflow(vcpu); +} + +static inline void vgic_disable_underflow(struct kvm_vcpu *vcpu) +{ + vgic_ops->disable_underflow(vcpu); +} + +static inline void vgic_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr) +{ + vgic_ops->get_vmcr(vcpu, vmcr); +} + +static void vgic_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr) +{ + vgic_ops->set_vmcr(vcpu, vmcr); +} + +static inline void vgic_enable(struct kvm_vcpu *vcpu) +{ + vgic_ops->enable(vcpu); +} + +static void vgic_retire_lr(int lr_nr, int irq, struct kvm_vcpu *vcpu) +{ + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + struct vgic_lr vlr = vgic_get_lr(vcpu, lr_nr); + + vlr.state = 0; + vgic_set_lr(vcpu, lr_nr, vlr); + clear_bit(lr_nr, vgic_cpu->lr_used); + vgic_cpu->vgic_irq_lr_map[irq] = LR_EMPTY; +} + +/* + * An interrupt may have been disabled after being made pending on the + * CPU interface (the classic case is a timer running while we're + * rebooting the guest - the interrupt would kick as soon as the CPU + * interface gets enabled, with deadly consequences). + * + * The solution is to examine already active LRs, and check the + * interrupt is still enabled. If not, just retire it. + */ +static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu) +{ + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + int lr; + + for_each_set_bit(lr, vgic_cpu->lr_used, vgic->nr_lr) { + struct vgic_lr vlr = vgic_get_lr(vcpu, lr); + + if (!vgic_irq_is_enabled(vcpu, vlr.irq)) { + vgic_retire_lr(lr, vlr.irq, vcpu); + if (vgic_irq_is_queued(vcpu, vlr.irq)) + vgic_irq_clear_queued(vcpu, vlr.irq); + } + } +} + +/* + * Queue an interrupt to a CPU virtual interface. Return true on success, + * or false if it wasn't possible to queue it. + */ +static bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq) +{ + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + struct vgic_lr vlr; + int lr; + + /* Sanitize the input... */ + BUG_ON(sgi_source_id & ~7); + BUG_ON(sgi_source_id && irq >= VGIC_NR_SGIS); + BUG_ON(irq >= dist->nr_irqs); + + kvm_debug("Queue IRQ%d\n", irq); + + lr = vgic_cpu->vgic_irq_lr_map[irq]; + + /* Do we have an active interrupt for the same CPUID? */ + if (lr != LR_EMPTY) { + vlr = vgic_get_lr(vcpu, lr); + if (vlr.source == sgi_source_id) { + kvm_debug("LR%d piggyback for IRQ%d\n", lr, vlr.irq); + BUG_ON(!test_bit(lr, vgic_cpu->lr_used)); + vlr.state |= LR_STATE_PENDING; + vgic_set_lr(vcpu, lr, vlr); + return true; + } + } + + /* Try to use another LR for this interrupt */ + lr = find_first_zero_bit((unsigned long *)vgic_cpu->lr_used, + vgic->nr_lr); + if (lr >= vgic->nr_lr) + return false; + + kvm_debug("LR%d allocated for IRQ%d %x\n", lr, irq, sgi_source_id); + vgic_cpu->vgic_irq_lr_map[irq] = lr; + set_bit(lr, vgic_cpu->lr_used); + + vlr.irq = irq; + vlr.source = sgi_source_id; + vlr.state = LR_STATE_PENDING; + if (!vgic_irq_is_edge(vcpu, irq)) + vlr.state |= LR_EOI_INT; + + vgic_set_lr(vcpu, lr, vlr); + + return true; +} + +static bool vgic_queue_sgi(struct kvm_vcpu *vcpu, int irq) +{ + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + unsigned long sources; + int vcpu_id = vcpu->vcpu_id; + int c; + + sources = *vgic_get_sgi_sources(dist, vcpu_id, irq); + + for_each_set_bit(c, &sources, dist->nr_cpus) { + if (vgic_queue_irq(vcpu, c, irq)) + clear_bit(c, &sources); + } + + *vgic_get_sgi_sources(dist, vcpu_id, irq) = sources; + + /* + * If the sources bitmap has been cleared it means that we + * could queue all the SGIs onto link registers (see the + * clear_bit above), and therefore we are done with them in + * our emulated gic and can get rid of them. + */ + if (!sources) { + vgic_dist_irq_clear_pending(vcpu, irq); + vgic_cpu_irq_clear(vcpu, irq); + return true; + } + + return false; +} + +static bool vgic_queue_hwirq(struct kvm_vcpu *vcpu, int irq) +{ + if (!vgic_can_sample_irq(vcpu, irq)) + return true; /* level interrupt, already queued */ + + if (vgic_queue_irq(vcpu, 0, irq)) { + if (vgic_irq_is_edge(vcpu, irq)) { + vgic_dist_irq_clear_pending(vcpu, irq); + vgic_cpu_irq_clear(vcpu, irq); + } else { + vgic_irq_set_queued(vcpu, irq); + } + + return true; + } + + return false; +} + +/* + * Fill the list registers with pending interrupts before running the + * guest. + */ +static void __kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu) +{ + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + int i, vcpu_id; + int overflow = 0; + + vcpu_id = vcpu->vcpu_id; + + /* + * We may not have any pending interrupt, or the interrupts + * may have been serviced from another vcpu. In all cases, + * move along. + */ + if (!kvm_vgic_vcpu_pending_irq(vcpu)) { + pr_debug("CPU%d has no pending interrupt\n", vcpu_id); + goto epilog; + } + + /* SGIs */ + for_each_set_bit(i, vgic_cpu->pending_percpu, VGIC_NR_SGIS) { + if (!vgic_queue_sgi(vcpu, i)) + overflow = 1; + } + + /* PPIs */ + for_each_set_bit_from(i, vgic_cpu->pending_percpu, VGIC_NR_PRIVATE_IRQS) { + if (!vgic_queue_hwirq(vcpu, i)) + overflow = 1; + } + + /* SPIs */ + for_each_set_bit(i, vgic_cpu->pending_shared, vgic_nr_shared_irqs(dist)) { + if (!vgic_queue_hwirq(vcpu, i + VGIC_NR_PRIVATE_IRQS)) + overflow = 1; + } + +epilog: + if (overflow) { + vgic_enable_underflow(vcpu); + } else { + vgic_disable_underflow(vcpu); + /* + * We're about to run this VCPU, and we've consumed + * everything the distributor had in store for + * us. Claim we don't have anything pending. We'll + * adjust that if needed while exiting. + */ + clear_bit(vcpu_id, dist->irq_pending_on_cpu); + } +} + +static bool vgic_process_maintenance(struct kvm_vcpu *vcpu) +{ + u32 status = vgic_get_interrupt_status(vcpu); + bool level_pending = false; + + kvm_debug("STATUS = %08x\n", status); + + if (status & INT_STATUS_EOI) { + /* + * Some level interrupts have been EOIed. Clear their + * active bit. + */ + u64 eisr = vgic_get_eisr(vcpu); + unsigned long *eisr_ptr = (unsigned long *)&eisr; + int lr; + + for_each_set_bit(lr, eisr_ptr, vgic->nr_lr) { + struct vgic_lr vlr = vgic_get_lr(vcpu, lr); + WARN_ON(vgic_irq_is_edge(vcpu, vlr.irq)); + + vgic_irq_clear_queued(vcpu, vlr.irq); + WARN_ON(vlr.state & LR_STATE_MASK); + vlr.state = 0; + vgic_set_lr(vcpu, lr, vlr); + + /* + * If the IRQ was EOIed it was also ACKed and we we + * therefore assume we can clear the soft pending + * state (should it had been set) for this interrupt. + * + * Note: if the IRQ soft pending state was set after + * the IRQ was acked, it actually shouldn't be + * cleared, but we have no way of knowing that unless + * we start trapping ACKs when the soft-pending state + * is set. + */ + vgic_dist_irq_clear_soft_pend(vcpu, vlr.irq); + + /* Any additional pending interrupt? */ + if (vgic_dist_irq_get_level(vcpu, vlr.irq)) { + vgic_cpu_irq_set(vcpu, vlr.irq); + level_pending = true; + } else { + vgic_dist_irq_clear_pending(vcpu, vlr.irq); + vgic_cpu_irq_clear(vcpu, vlr.irq); + } + + /* + * Despite being EOIed, the LR may not have + * been marked as empty. + */ + vgic_sync_lr_elrsr(vcpu, lr, vlr); + } + } + + if (status & INT_STATUS_UNDERFLOW) + vgic_disable_underflow(vcpu); + + return level_pending; +} + +/* + * Sync back the VGIC state after a guest run. The distributor lock is + * needed so we don't get preempted in the middle of the state processing. + */ +static void __kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu) +{ + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + u64 elrsr; + unsigned long *elrsr_ptr; + int lr, pending; + bool level_pending; + + level_pending = vgic_process_maintenance(vcpu); + elrsr = vgic_get_elrsr(vcpu); + elrsr_ptr = (unsigned long *)&elrsr; + + /* Clear mappings for empty LRs */ + for_each_set_bit(lr, elrsr_ptr, vgic->nr_lr) { + struct vgic_lr vlr; + + if (!test_and_clear_bit(lr, vgic_cpu->lr_used)) + continue; + + vlr = vgic_get_lr(vcpu, lr); + + BUG_ON(vlr.irq >= dist->nr_irqs); + vgic_cpu->vgic_irq_lr_map[vlr.irq] = LR_EMPTY; + } + + /* Check if we still have something up our sleeve... */ + pending = find_first_zero_bit(elrsr_ptr, vgic->nr_lr); + if (level_pending || pending < vgic->nr_lr) + set_bit(vcpu->vcpu_id, dist->irq_pending_on_cpu); +} + +void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu) +{ + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + + if (!irqchip_in_kernel(vcpu->kvm)) + return; + + spin_lock(&dist->lock); + __kvm_vgic_flush_hwstate(vcpu); + spin_unlock(&dist->lock); +} + +void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu) +{ + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + + if (!irqchip_in_kernel(vcpu->kvm)) + return; + + spin_lock(&dist->lock); + __kvm_vgic_sync_hwstate(vcpu); + spin_unlock(&dist->lock); +} + +int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu) +{ + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + + if (!irqchip_in_kernel(vcpu->kvm)) + return 0; + + return test_bit(vcpu->vcpu_id, dist->irq_pending_on_cpu); +} + +static void vgic_kick_vcpus(struct kvm *kvm) +{ + struct kvm_vcpu *vcpu; + int c; + + /* + * We've injected an interrupt, time to find out who deserves + * a good kick... + */ + kvm_for_each_vcpu(c, vcpu, kvm) { + if (kvm_vgic_vcpu_pending_irq(vcpu)) + kvm_vcpu_kick(vcpu); + } +} + +static int vgic_validate_injection(struct kvm_vcpu *vcpu, int irq, int level) +{ + int edge_triggered = vgic_irq_is_edge(vcpu, irq); + + /* + * Only inject an interrupt if: + * - edge triggered and we have a rising edge + * - level triggered and we change level + */ + if (edge_triggered) { + int state = vgic_dist_irq_is_pending(vcpu, irq); + return level > state; + } else { + int state = vgic_dist_irq_get_level(vcpu, irq); + return level != state; + } +} + +static bool vgic_update_irq_pending(struct kvm *kvm, int cpuid, + unsigned int irq_num, bool level) +{ + struct vgic_dist *dist = &kvm->arch.vgic; + struct kvm_vcpu *vcpu; + int edge_triggered, level_triggered; + int enabled; + bool ret = true; + + spin_lock(&dist->lock); + + vcpu = kvm_get_vcpu(kvm, cpuid); + edge_triggered = vgic_irq_is_edge(vcpu, irq_num); + level_triggered = !edge_triggered; + + if (!vgic_validate_injection(vcpu, irq_num, level)) { + ret = false; + goto out; + } + + if (irq_num >= VGIC_NR_PRIVATE_IRQS) { + cpuid = dist->irq_spi_cpu[irq_num - VGIC_NR_PRIVATE_IRQS]; + vcpu = kvm_get_vcpu(kvm, cpuid); + } + + kvm_debug("Inject IRQ%d level %d CPU%d\n", irq_num, level, cpuid); + + if (level) { + if (level_triggered) + vgic_dist_irq_set_level(vcpu, irq_num); + vgic_dist_irq_set_pending(vcpu, irq_num); + } else { + if (level_triggered) { + vgic_dist_irq_clear_level(vcpu, irq_num); + if (!vgic_dist_irq_soft_pend(vcpu, irq_num)) + vgic_dist_irq_clear_pending(vcpu, irq_num); + } else { + vgic_dist_irq_clear_pending(vcpu, irq_num); + } + } + + enabled = vgic_irq_is_enabled(vcpu, irq_num); + + if (!enabled) { + ret = false; + goto out; + } + + if (!vgic_can_sample_irq(vcpu, irq_num)) { + /* + * Level interrupt in progress, will be picked up + * when EOId. + */ + ret = false; + goto out; + } + + if (level) { + vgic_cpu_irq_set(vcpu, irq_num); + set_bit(cpuid, dist->irq_pending_on_cpu); + } + +out: + spin_unlock(&dist->lock); + + return ret; +} + +/** + * kvm_vgic_inject_irq - Inject an IRQ from a device to the vgic + * @kvm: The VM structure pointer + * @cpuid: The CPU for PPIs + * @irq_num: The IRQ number that is assigned to the device + * @level: Edge-triggered: true: to trigger the interrupt + * false: to ignore the call + * Level-sensitive true: activates an interrupt + * false: deactivates an interrupt + * + * The GIC is not concerned with devices being active-LOW or active-HIGH for + * level-sensitive interrupts. You can think of the level parameter as 1 + * being HIGH and 0 being LOW and all devices being active-HIGH. + */ +int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num, + bool level) +{ + if (likely(vgic_initialized(kvm)) && + vgic_update_irq_pending(kvm, cpuid, irq_num, level)) + vgic_kick_vcpus(kvm); + + return 0; +} + +static irqreturn_t vgic_maintenance_handler(int irq, void *data) +{ + /* + * We cannot rely on the vgic maintenance interrupt to be + * delivered synchronously. This means we can only use it to + * exit the VM, and we perform the handling of EOIed + * interrupts on the exit path (see vgic_process_maintenance). + */ + return IRQ_HANDLED; +} + +void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) +{ + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + + kfree(vgic_cpu->pending_shared); + kfree(vgic_cpu->vgic_irq_lr_map); + vgic_cpu->pending_shared = NULL; + vgic_cpu->vgic_irq_lr_map = NULL; +} + +static int vgic_vcpu_init_maps(struct kvm_vcpu *vcpu, int nr_irqs) +{ + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + + int sz = (nr_irqs - VGIC_NR_PRIVATE_IRQS) / 8; + vgic_cpu->pending_shared = kzalloc(sz, GFP_KERNEL); + vgic_cpu->vgic_irq_lr_map = kzalloc(nr_irqs, GFP_KERNEL); + + if (!vgic_cpu->pending_shared || !vgic_cpu->vgic_irq_lr_map) { + kvm_vgic_vcpu_destroy(vcpu); + return -ENOMEM; + } + + return 0; +} + +/** + * kvm_vgic_vcpu_init - Initialize per-vcpu VGIC state + * @vcpu: pointer to the vcpu struct + * + * Initialize the vgic_cpu struct and vgic_dist struct fields pertaining to + * this vcpu and enable the VGIC for this VCPU + */ +static void kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu) +{ + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + int i; + + for (i = 0; i < dist->nr_irqs; i++) { + if (i < VGIC_NR_PPIS) + vgic_bitmap_set_irq_val(&dist->irq_enabled, + vcpu->vcpu_id, i, 1); + if (i < VGIC_NR_PRIVATE_IRQS) + vgic_bitmap_set_irq_val(&dist->irq_cfg, + vcpu->vcpu_id, i, VGIC_CFG_EDGE); + + vgic_cpu->vgic_irq_lr_map[i] = LR_EMPTY; + } + + /* + * Store the number of LRs per vcpu, so we don't have to go + * all the way to the distributor structure to find out. Only + * assembly code should use this one. + */ + vgic_cpu->nr_lr = vgic->nr_lr; + + vgic_enable(vcpu); +} + +void kvm_vgic_destroy(struct kvm *kvm) +{ + struct vgic_dist *dist = &kvm->arch.vgic; + struct kvm_vcpu *vcpu; + int i; + + kvm_for_each_vcpu(i, vcpu, kvm) + kvm_vgic_vcpu_destroy(vcpu); + + vgic_free_bitmap(&dist->irq_enabled); + vgic_free_bitmap(&dist->irq_level); + vgic_free_bitmap(&dist->irq_pending); + vgic_free_bitmap(&dist->irq_soft_pend); + vgic_free_bitmap(&dist->irq_queued); + vgic_free_bitmap(&dist->irq_cfg); + vgic_free_bytemap(&dist->irq_priority); + if (dist->irq_spi_target) { + for (i = 0; i < dist->nr_cpus; i++) + vgic_free_bitmap(&dist->irq_spi_target[i]); + } + kfree(dist->irq_sgi_sources); + kfree(dist->irq_spi_cpu); + kfree(dist->irq_spi_target); + kfree(dist->irq_pending_on_cpu); + dist->irq_sgi_sources = NULL; + dist->irq_spi_cpu = NULL; + dist->irq_spi_target = NULL; + dist->irq_pending_on_cpu = NULL; +} + +/* + * Allocate and initialize the various data structures. Must be called + * with kvm->lock held! + */ +static int vgic_init_maps(struct kvm *kvm) +{ + struct vgic_dist *dist = &kvm->arch.vgic; + struct kvm_vcpu *vcpu; + int nr_cpus, nr_irqs; + int ret, i; + + if (dist->nr_cpus) /* Already allocated */ + return 0; + + nr_cpus = dist->nr_cpus = atomic_read(&kvm->online_vcpus); + if (!nr_cpus) /* No vcpus? Can't be good... */ + return -EINVAL; + + /* + * If nobody configured the number of interrupts, use the + * legacy one. + */ + if (!dist->nr_irqs) + dist->nr_irqs = VGIC_NR_IRQS_LEGACY; + + nr_irqs = dist->nr_irqs; + + ret = vgic_init_bitmap(&dist->irq_enabled, nr_cpus, nr_irqs); + ret |= vgic_init_bitmap(&dist->irq_level, nr_cpus, nr_irqs); + ret |= vgic_init_bitmap(&dist->irq_pending, nr_cpus, nr_irqs); + ret |= vgic_init_bitmap(&dist->irq_soft_pend, nr_cpus, nr_irqs); + ret |= vgic_init_bitmap(&dist->irq_queued, nr_cpus, nr_irqs); + ret |= vgic_init_bitmap(&dist->irq_cfg, nr_cpus, nr_irqs); + ret |= vgic_init_bytemap(&dist->irq_priority, nr_cpus, nr_irqs); + + if (ret) + goto out; + + dist->irq_sgi_sources = kzalloc(nr_cpus * VGIC_NR_SGIS, GFP_KERNEL); + dist->irq_spi_cpu = kzalloc(nr_irqs - VGIC_NR_PRIVATE_IRQS, GFP_KERNEL); + dist->irq_spi_target = kzalloc(sizeof(*dist->irq_spi_target) * nr_cpus, + GFP_KERNEL); + dist->irq_pending_on_cpu = kzalloc(BITS_TO_LONGS(nr_cpus) * sizeof(long), + GFP_KERNEL); + if (!dist->irq_sgi_sources || + !dist->irq_spi_cpu || + !dist->irq_spi_target || + !dist->irq_pending_on_cpu) { + ret = -ENOMEM; + goto out; + } + + for (i = 0; i < nr_cpus; i++) + ret |= vgic_init_bitmap(&dist->irq_spi_target[i], + nr_cpus, nr_irqs); + + if (ret) + goto out; + + kvm_for_each_vcpu(i, vcpu, kvm) { + ret = vgic_vcpu_init_maps(vcpu, nr_irqs); + if (ret) { + kvm_err("VGIC: Failed to allocate vcpu memory\n"); + break; + } + } + + for (i = VGIC_NR_PRIVATE_IRQS; i < dist->nr_irqs; i += 4) + vgic_set_target_reg(kvm, 0, i); + +out: + if (ret) + kvm_vgic_destroy(kvm); + + return ret; +} + +/** + * kvm_vgic_init - Initialize global VGIC state before running any VCPUs + * @kvm: pointer to the kvm struct + * + * Map the virtual CPU interface into the VM before running any VCPUs. We + * can't do this at creation time, because user space must first set the + * virtual CPU interface address in the guest physical address space. Also + * initialize the ITARGETSRn regs to 0 on the emulated distributor. + */ +int kvm_vgic_init(struct kvm *kvm) +{ + struct kvm_vcpu *vcpu; + int ret = 0, i; + + if (!irqchip_in_kernel(kvm)) + return 0; + + mutex_lock(&kvm->lock); + + if (vgic_initialized(kvm)) + goto out; + + if (IS_VGIC_ADDR_UNDEF(kvm->arch.vgic.vgic_dist_base) || + IS_VGIC_ADDR_UNDEF(kvm->arch.vgic.vgic_cpu_base)) { + kvm_err("Need to set vgic cpu and dist addresses first\n"); + ret = -ENXIO; + goto out; + } + + ret = vgic_init_maps(kvm); + if (ret) { + kvm_err("Unable to allocate maps\n"); + goto out; + } + + ret = kvm_phys_addr_ioremap(kvm, kvm->arch.vgic.vgic_cpu_base, + vgic->vcpu_base, KVM_VGIC_V2_CPU_SIZE); + if (ret) { + kvm_err("Unable to remap VGIC CPU to VCPU\n"); + goto out; + } + + kvm_for_each_vcpu(i, vcpu, kvm) + kvm_vgic_vcpu_init(vcpu); + + kvm->arch.vgic.ready = true; +out: + if (ret) + kvm_vgic_destroy(kvm); + mutex_unlock(&kvm->lock); + return ret; +} + +int kvm_vgic_create(struct kvm *kvm) +{ + int i, vcpu_lock_idx = -1, ret = 0; + struct kvm_vcpu *vcpu; + + mutex_lock(&kvm->lock); + + if (kvm->arch.vgic.vctrl_base) { + ret = -EEXIST; + goto out; + } + + /* + * Any time a vcpu is run, vcpu_load is called which tries to grab the + * vcpu->mutex. By grabbing the vcpu->mutex of all VCPUs we ensure + * that no other VCPUs are run while we create the vgic. + */ + kvm_for_each_vcpu(i, vcpu, kvm) { + if (!mutex_trylock(&vcpu->mutex)) + goto out_unlock; + vcpu_lock_idx = i; + } + + kvm_for_each_vcpu(i, vcpu, kvm) { + if (vcpu->arch.has_run_once) { + ret = -EBUSY; + goto out_unlock; + } + } + + spin_lock_init(&kvm->arch.vgic.lock); + kvm->arch.vgic.in_kernel = true; + kvm->arch.vgic.vctrl_base = vgic->vctrl_base; + kvm->arch.vgic.vgic_dist_base = VGIC_ADDR_UNDEF; + kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF; + +out_unlock: + for (; vcpu_lock_idx >= 0; vcpu_lock_idx--) { + vcpu = kvm_get_vcpu(kvm, vcpu_lock_idx); + mutex_unlock(&vcpu->mutex); + } + +out: + mutex_unlock(&kvm->lock); + return ret; +} + +static int vgic_ioaddr_overlap(struct kvm *kvm) +{ + phys_addr_t dist = kvm->arch.vgic.vgic_dist_base; + phys_addr_t cpu = kvm->arch.vgic.vgic_cpu_base; + + if (IS_VGIC_ADDR_UNDEF(dist) || IS_VGIC_ADDR_UNDEF(cpu)) + return 0; + if ((dist <= cpu && dist + KVM_VGIC_V2_DIST_SIZE > cpu) || + (cpu <= dist && cpu + KVM_VGIC_V2_CPU_SIZE > dist)) + return -EBUSY; + return 0; +} + +static int vgic_ioaddr_assign(struct kvm *kvm, phys_addr_t *ioaddr, + phys_addr_t addr, phys_addr_t size) +{ + int ret; + + if (addr & ~KVM_PHYS_MASK) + return -E2BIG; + + if (addr & (SZ_4K - 1)) + return -EINVAL; + + if (!IS_VGIC_ADDR_UNDEF(*ioaddr)) + return -EEXIST; + if (addr + size < addr) + return -EINVAL; + + *ioaddr = addr; + ret = vgic_ioaddr_overlap(kvm); + if (ret) + *ioaddr = VGIC_ADDR_UNDEF; + + return ret; +} + +/** + * kvm_vgic_addr - set or get vgic VM base addresses + * @kvm: pointer to the vm struct + * @type: the VGIC addr type, one of KVM_VGIC_V2_ADDR_TYPE_XXX + * @addr: pointer to address value + * @write: if true set the address in the VM address space, if false read the + * address + * + * Set or get the vgic base addresses for the distributor and the virtual CPU + * interface in the VM physical address space. These addresses are properties + * of the emulated core/SoC and therefore user space initially knows this + * information. + */ +int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write) +{ + int r = 0; + struct vgic_dist *vgic = &kvm->arch.vgic; + + mutex_lock(&kvm->lock); + switch (type) { + case KVM_VGIC_V2_ADDR_TYPE_DIST: + if (write) { + r = vgic_ioaddr_assign(kvm, &vgic->vgic_dist_base, + *addr, KVM_VGIC_V2_DIST_SIZE); + } else { + *addr = vgic->vgic_dist_base; + } + break; + case KVM_VGIC_V2_ADDR_TYPE_CPU: + if (write) { + r = vgic_ioaddr_assign(kvm, &vgic->vgic_cpu_base, + *addr, KVM_VGIC_V2_CPU_SIZE); + } else { + *addr = vgic->vgic_cpu_base; + } + break; + default: + r = -ENODEV; + } + + mutex_unlock(&kvm->lock); + return r; +} + +static bool handle_cpu_mmio_misc(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, phys_addr_t offset) +{ + bool updated = false; + struct vgic_vmcr vmcr; + u32 *vmcr_field; + u32 reg; + + vgic_get_vmcr(vcpu, &vmcr); + + switch (offset & ~0x3) { + case GIC_CPU_CTRL: + vmcr_field = &vmcr.ctlr; + break; + case GIC_CPU_PRIMASK: + vmcr_field = &vmcr.pmr; + break; + case GIC_CPU_BINPOINT: + vmcr_field = &vmcr.bpr; + break; + case GIC_CPU_ALIAS_BINPOINT: + vmcr_field = &vmcr.abpr; + break; + default: + BUG(); + } + + if (!mmio->is_write) { + reg = *vmcr_field; + mmio_data_write(mmio, ~0, reg); + } else { + reg = mmio_data_read(mmio, ~0); + if (reg != *vmcr_field) { + *vmcr_field = reg; + vgic_set_vmcr(vcpu, &vmcr); + updated = true; + } + } + return updated; +} + +static bool handle_mmio_abpr(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, phys_addr_t offset) +{ + return handle_cpu_mmio_misc(vcpu, mmio, GIC_CPU_ALIAS_BINPOINT); +} + +static bool handle_cpu_mmio_ident(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, + phys_addr_t offset) +{ + u32 reg; + + if (mmio->is_write) + return false; + + /* GICC_IIDR */ + reg = (PRODUCT_ID_KVM << 20) | + (GICC_ARCH_VERSION_V2 << 16) | + (IMPLEMENTER_ARM << 0); + mmio_data_write(mmio, ~0, reg); + return false; +} + +/* + * CPU Interface Register accesses - these are not accessed by the VM, but by + * user space for saving and restoring VGIC state. + */ +static const struct mmio_range vgic_cpu_ranges[] = { + { + .base = GIC_CPU_CTRL, + .len = 12, + .handle_mmio = handle_cpu_mmio_misc, + }, + { + .base = GIC_CPU_ALIAS_BINPOINT, + .len = 4, + .handle_mmio = handle_mmio_abpr, + }, + { + .base = GIC_CPU_ACTIVEPRIO, + .len = 16, + .handle_mmio = handle_mmio_raz_wi, + }, + { + .base = GIC_CPU_IDENT, + .len = 4, + .handle_mmio = handle_cpu_mmio_ident, + }, +}; + +static int vgic_attr_regs_access(struct kvm_device *dev, + struct kvm_device_attr *attr, + u32 *reg, bool is_write) +{ + const struct mmio_range *r = NULL, *ranges; + phys_addr_t offset; + int ret, cpuid, c; + struct kvm_vcpu *vcpu, *tmp_vcpu; + struct vgic_dist *vgic; + struct kvm_exit_mmio mmio; + + offset = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK; + cpuid = (attr->attr & KVM_DEV_ARM_VGIC_CPUID_MASK) >> + KVM_DEV_ARM_VGIC_CPUID_SHIFT; + + mutex_lock(&dev->kvm->lock); + + ret = vgic_init_maps(dev->kvm); + if (ret) + goto out; + + if (cpuid >= atomic_read(&dev->kvm->online_vcpus)) { + ret = -EINVAL; + goto out; + } + + vcpu = kvm_get_vcpu(dev->kvm, cpuid); + vgic = &dev->kvm->arch.vgic; + + mmio.len = 4; + mmio.is_write = is_write; + if (is_write) + mmio_data_write(&mmio, ~0, *reg); + switch (attr->group) { + case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: + mmio.phys_addr = vgic->vgic_dist_base + offset; + ranges = vgic_dist_ranges; + break; + case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: + mmio.phys_addr = vgic->vgic_cpu_base + offset; + ranges = vgic_cpu_ranges; + break; + default: + BUG(); + } + r = find_matching_range(ranges, &mmio, offset); + + if (unlikely(!r || !r->handle_mmio)) { + ret = -ENXIO; + goto out; + } + + + spin_lock(&vgic->lock); + + /* + * Ensure that no other VCPU is running by checking the vcpu->cpu + * field. If no other VPCUs are running we can safely access the VGIC + * state, because even if another VPU is run after this point, that + * VCPU will not touch the vgic state, because it will block on + * getting the vgic->lock in kvm_vgic_sync_hwstate(). + */ + kvm_for_each_vcpu(c, tmp_vcpu, dev->kvm) { + if (unlikely(tmp_vcpu->cpu != -1)) { + ret = -EBUSY; + goto out_vgic_unlock; + } + } + + /* + * Move all pending IRQs from the LRs on all VCPUs so the pending + * state can be properly represented in the register state accessible + * through this API. + */ + kvm_for_each_vcpu(c, tmp_vcpu, dev->kvm) + vgic_unqueue_irqs(tmp_vcpu); + + offset -= r->base; + r->handle_mmio(vcpu, &mmio, offset); + + if (!is_write) + *reg = mmio_data_read(&mmio, ~0); + + ret = 0; +out_vgic_unlock: + spin_unlock(&vgic->lock); +out: + mutex_unlock(&dev->kvm->lock); + return ret; +} + +static int vgic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr) +{ + int r; + + switch (attr->group) { + case KVM_DEV_ARM_VGIC_GRP_ADDR: { + u64 __user *uaddr = (u64 __user *)(long)attr->addr; + u64 addr; + unsigned long type = (unsigned long)attr->attr; + + if (copy_from_user(&addr, uaddr, sizeof(addr))) + return -EFAULT; + + r = kvm_vgic_addr(dev->kvm, type, &addr, true); + return (r == -ENODEV) ? -ENXIO : r; + } + + case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: + case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: { + u32 __user *uaddr = (u32 __user *)(long)attr->addr; + u32 reg; + + if (get_user(reg, uaddr)) + return -EFAULT; + + return vgic_attr_regs_access(dev, attr, ®, true); + } + case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: { + u32 __user *uaddr = (u32 __user *)(long)attr->addr; + u32 val; + int ret = 0; + + if (get_user(val, uaddr)) + return -EFAULT; + + /* + * We require: + * - at least 32 SPIs on top of the 16 SGIs and 16 PPIs + * - at most 1024 interrupts + * - a multiple of 32 interrupts + */ + if (val < (VGIC_NR_PRIVATE_IRQS + 32) || + val > VGIC_MAX_IRQS || + (val & 31)) + return -EINVAL; + + mutex_lock(&dev->kvm->lock); + + if (vgic_initialized(dev->kvm) || dev->kvm->arch.vgic.nr_irqs) + ret = -EBUSY; + else + dev->kvm->arch.vgic.nr_irqs = val; + + mutex_unlock(&dev->kvm->lock); + + return ret; + } + + } + + return -ENXIO; +} + +static int vgic_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr) +{ + int r = -ENXIO; + + switch (attr->group) { + case KVM_DEV_ARM_VGIC_GRP_ADDR: { + u64 __user *uaddr = (u64 __user *)(long)attr->addr; + u64 addr; + unsigned long type = (unsigned long)attr->attr; + + r = kvm_vgic_addr(dev->kvm, type, &addr, false); + if (r) + return (r == -ENODEV) ? -ENXIO : r; + + if (copy_to_user(uaddr, &addr, sizeof(addr))) + return -EFAULT; + break; + } + + case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: + case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: { + u32 __user *uaddr = (u32 __user *)(long)attr->addr; + u32 reg = 0; + + r = vgic_attr_regs_access(dev, attr, ®, false); + if (r) + return r; + r = put_user(reg, uaddr); + break; + } + case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: { + u32 __user *uaddr = (u32 __user *)(long)attr->addr; + r = put_user(dev->kvm->arch.vgic.nr_irqs, uaddr); + break; + } + + } + + return r; +} + +static int vgic_has_attr_regs(const struct mmio_range *ranges, + phys_addr_t offset) +{ + struct kvm_exit_mmio dev_attr_mmio; + + dev_attr_mmio.len = 4; + if (find_matching_range(ranges, &dev_attr_mmio, offset)) + return 0; + else + return -ENXIO; +} + +static int vgic_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr) +{ + phys_addr_t offset; + + switch (attr->group) { + case KVM_DEV_ARM_VGIC_GRP_ADDR: + switch (attr->attr) { + case KVM_VGIC_V2_ADDR_TYPE_DIST: + case KVM_VGIC_V2_ADDR_TYPE_CPU: + return 0; + } + break; + case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: + offset = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK; + return vgic_has_attr_regs(vgic_dist_ranges, offset); + case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: + offset = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK; + return vgic_has_attr_regs(vgic_cpu_ranges, offset); + case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: + return 0; + } + return -ENXIO; +} + +static void vgic_destroy(struct kvm_device *dev) +{ + kfree(dev); +} + +static int vgic_create(struct kvm_device *dev, u32 type) +{ + return kvm_vgic_create(dev->kvm); +} + +static struct kvm_device_ops kvm_arm_vgic_v2_ops = { + .name = "kvm-arm-vgic", + .create = vgic_create, + .destroy = vgic_destroy, + .set_attr = vgic_set_attr, + .get_attr = vgic_get_attr, + .has_attr = vgic_has_attr, +}; + +static void vgic_init_maintenance_interrupt(void *info) +{ + enable_percpu_irq(vgic->maint_irq, 0); +} + +static int vgic_cpu_notify(struct notifier_block *self, + unsigned long action, void *cpu) +{ + switch (action) { + case CPU_STARTING: + case CPU_STARTING_FROZEN: + vgic_init_maintenance_interrupt(NULL); + break; + case CPU_DYING: + case CPU_DYING_FROZEN: + disable_percpu_irq(vgic->maint_irq); + break; + } + + return NOTIFY_OK; +} + +static struct notifier_block vgic_cpu_nb = { + .notifier_call = vgic_cpu_notify, +}; + +static const struct of_device_id vgic_ids[] = { + { .compatible = "arm,cortex-a15-gic", .data = vgic_v2_probe, }, + { .compatible = "arm,gic-v3", .data = vgic_v3_probe, }, + {}, +}; + +int kvm_vgic_hyp_init(void) +{ + const struct of_device_id *matched_id; + int (*vgic_probe)(struct device_node *,const struct vgic_ops **, + const struct vgic_params **); + struct device_node *vgic_node; + int ret; + + vgic_node = of_find_matching_node_and_match(NULL, + vgic_ids, &matched_id); + if (!vgic_node) { + kvm_err("error: no compatible GIC node found\n"); + return -ENODEV; + } + + vgic_probe = matched_id->data; + ret = vgic_probe(vgic_node, &vgic_ops, &vgic); + if (ret) + return ret; + + ret = request_percpu_irq(vgic->maint_irq, vgic_maintenance_handler, + "vgic", kvm_get_running_vcpus()); + if (ret) { + kvm_err("Cannot register interrupt %d\n", vgic->maint_irq); + return ret; + } + + ret = register_cpu_notifier(&vgic_cpu_nb); + if (ret) { + kvm_err("Cannot register vgic CPU notifier\n"); + goto out_free_irq; + } + + /* Callback into for arch code for setup */ + vgic_arch_setup(vgic); + + on_each_cpu(vgic_init_maintenance_interrupt, NULL, 1); + + return kvm_register_device_ops(&kvm_arm_vgic_v2_ops, + KVM_DEV_TYPE_ARM_VGIC_V2); + +out_free_irq: + free_percpu_irq(vgic->maint_irq, kvm_get_running_vcpus()); + return ret; +} diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c index ea475cd03511..d6a3d0993d88 100644 --- a/virt/kvm/async_pf.c +++ b/virt/kvm/async_pf.c @@ -28,6 +28,21 @@ #include "async_pf.h" #include <trace/events/kvm.h> +static inline void kvm_async_page_present_sync(struct kvm_vcpu *vcpu, + struct kvm_async_pf *work) +{ +#ifdef CONFIG_KVM_ASYNC_PF_SYNC + kvm_arch_async_page_present(vcpu, work); +#endif +} +static inline void kvm_async_page_present_async(struct kvm_vcpu *vcpu, + struct kvm_async_pf *work) +{ +#ifndef CONFIG_KVM_ASYNC_PF_SYNC + kvm_arch_async_page_present(vcpu, work); +#endif +} + static struct kmem_cache *async_pf_cache; int kvm_async_pf_init(void) @@ -56,7 +71,6 @@ void kvm_async_pf_vcpu_init(struct kvm_vcpu *vcpu) static void async_pf_execute(struct work_struct *work) { - struct page *page = NULL; struct kvm_async_pf *apf = container_of(work, struct kvm_async_pf, work); struct mm_struct *mm = apf->mm; @@ -66,16 +80,13 @@ static void async_pf_execute(struct work_struct *work) might_sleep(); - use_mm(mm); down_read(&mm->mmap_sem); - get_user_pages(current, mm, addr, 1, 1, 0, &page, NULL); + get_user_pages(NULL, mm, addr, 1, 1, 0, NULL, NULL); up_read(&mm->mmap_sem); - unuse_mm(mm); + kvm_async_page_present_sync(vcpu, apf); spin_lock(&vcpu->async_pf.lock); list_add_tail(&apf->link, &vcpu->async_pf.done); - apf->page = page; - apf->done = true; spin_unlock(&vcpu->async_pf.lock); /* @@ -83,12 +94,12 @@ static void async_pf_execute(struct work_struct *work) * this point */ - trace_kvm_async_pf_completed(addr, page, gva); + trace_kvm_async_pf_completed(addr, gva); if (waitqueue_active(&vcpu->wq)) wake_up_interruptible(&vcpu->wq); - mmdrop(mm); + mmput(mm); kvm_put_kvm(vcpu->kvm); } @@ -99,10 +110,17 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu) struct kvm_async_pf *work = list_entry(vcpu->async_pf.queue.next, typeof(*work), queue); - cancel_work_sync(&work->work); list_del(&work->queue); - if (!work->done) /* work was canceled */ + +#ifdef CONFIG_KVM_ASYNC_PF_SYNC + flush_work(&work->work); +#else + if (cancel_work_sync(&work->work)) { + mmput(work->mm); + kvm_put_kvm(vcpu->kvm); /* == work->vcpu->kvm */ kmem_cache_free(async_pf_cache, work); + } +#endif } spin_lock(&vcpu->async_pf.lock); @@ -111,8 +129,6 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu) list_entry(vcpu->async_pf.done.next, typeof(*work), link); list_del(&work->link); - if (!is_error_page(work->page)) - kvm_release_page_clean(work->page); kmem_cache_free(async_pf_cache, work); } spin_unlock(&vcpu->async_pf.lock); @@ -132,19 +148,16 @@ void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu) list_del(&work->link); spin_unlock(&vcpu->async_pf.lock); - if (work->page) - kvm_arch_async_page_ready(vcpu, work); - kvm_arch_async_page_present(vcpu, work); + kvm_arch_async_page_ready(vcpu, work); + kvm_async_page_present_async(vcpu, work); list_del(&work->queue); vcpu->async_pf.queued--; - if (!is_error_page(work->page)) - kvm_release_page_clean(work->page); kmem_cache_free(async_pf_cache, work); } } -int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn, +int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva, struct kvm_arch_async_pf *arch) { struct kvm_async_pf *work; @@ -162,14 +175,13 @@ int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn, if (!work) return 0; - work->page = NULL; - work->done = false; + work->wakeup_all = false; work->vcpu = vcpu; work->gva = gva; - work->addr = gfn_to_hva(vcpu->kvm, gfn); + work->addr = hva; work->arch = *arch; work->mm = current->mm; - atomic_inc(&work->mm->mm_count); + atomic_inc(&work->mm->mm_users); kvm_get_kvm(work->vcpu->kvm); /* this can't really happen otherwise gfn_to_pfn_async @@ -187,7 +199,7 @@ int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn, return 1; retry_sync: kvm_put_kvm(work->vcpu->kvm); - mmdrop(work->mm); + mmput(work->mm); kmem_cache_free(async_pf_cache, work); return 0; } @@ -203,7 +215,7 @@ int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu) if (!work) return -ENOMEM; - work->page = KVM_ERR_PTR_BAD_PAGE; + work->wakeup_all = true; INIT_LIST_HEAD(&work->queue); /* for list_del to work */ spin_lock(&vcpu->async_pf.lock); diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index 64ee720b75c7..71ed39941b9c 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -31,11 +31,14 @@ #include <linux/list.h> #include <linux/eventfd.h> #include <linux/kernel.h> +#include <linux/srcu.h> #include <linux/slab.h> +#include <linux/seqlock.h> +#include <trace/events/kvm.h> #include "iodev.h" -#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING +#ifdef CONFIG_HAVE_KVM_IRQFD /* * -------------------------------------------------------------------- * irqfd: Allows an fd to be used to inject an interrupt to the guest @@ -74,7 +77,8 @@ struct _irqfd { struct kvm *kvm; wait_queue_t wait; /* Update side is protected by irqfds.lock */ - struct kvm_kernel_irq_routing_entry __rcu *irq_entry; + struct kvm_kernel_irq_routing_entry irq_entry; + seqcount_t irq_entry_sc; /* Used for level IRQ fast-path */ int gsi; struct work_struct inject; @@ -118,19 +122,22 @@ static void irqfd_resampler_ack(struct kvm_irq_ack_notifier *kian) { struct _irqfd_resampler *resampler; + struct kvm *kvm; struct _irqfd *irqfd; + int idx; resampler = container_of(kian, struct _irqfd_resampler, notifier); + kvm = resampler->kvm; - kvm_set_irq(resampler->kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID, + kvm_set_irq(kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID, resampler->notifier.gsi, 0, false); - rcu_read_lock(); + idx = srcu_read_lock(&kvm->irq_srcu); list_for_each_entry_rcu(irqfd, &resampler->list, resampler_link) eventfd_signal(irqfd->resamplefd, 1); - rcu_read_unlock(); + srcu_read_unlock(&kvm->irq_srcu, idx); } static void @@ -142,7 +149,7 @@ irqfd_resampler_shutdown(struct _irqfd *irqfd) mutex_lock(&kvm->irqfds.resampler_lock); list_del_rcu(&irqfd->resampler_link); - synchronize_rcu(); + synchronize_srcu(&kvm->irq_srcu); if (list_empty(&resampler->list)) { list_del(&resampler->link); @@ -219,19 +226,24 @@ irqfd_wakeup(wait_queue_t *wait, unsigned mode, int sync, void *key) { struct _irqfd *irqfd = container_of(wait, struct _irqfd, wait); unsigned long flags = (unsigned long)key; - struct kvm_kernel_irq_routing_entry *irq; + struct kvm_kernel_irq_routing_entry irq; struct kvm *kvm = irqfd->kvm; + unsigned seq; + int idx; if (flags & POLLIN) { - rcu_read_lock(); - irq = rcu_dereference(irqfd->irq_entry); + idx = srcu_read_lock(&kvm->irq_srcu); + do { + seq = read_seqcount_begin(&irqfd->irq_entry_sc); + irq = irqfd->irq_entry; + } while (read_seqcount_retry(&irqfd->irq_entry_sc, seq)); /* An event has been signaled, inject an interrupt */ - if (irq) - kvm_set_msi(irq, kvm, KVM_USERSPACE_IRQ_SOURCE_ID, 1, + if (irq.type == KVM_IRQ_ROUTING_MSI) + kvm_set_msi(&irq, kvm, KVM_USERSPACE_IRQ_SOURCE_ID, 1, false); else schedule_work(&irqfd->inject); - rcu_read_unlock(); + srcu_read_unlock(&kvm->irq_srcu, idx); } if (flags & POLLHUP) { @@ -267,34 +279,37 @@ irqfd_ptable_queue_proc(struct file *file, wait_queue_head_t *wqh, } /* Must be called under irqfds.lock */ -static void irqfd_update(struct kvm *kvm, struct _irqfd *irqfd, - struct kvm_irq_routing_table *irq_rt) +static void irqfd_update(struct kvm *kvm, struct _irqfd *irqfd) { struct kvm_kernel_irq_routing_entry *e; + struct kvm_kernel_irq_routing_entry entries[KVM_NR_IRQCHIPS]; + int i, n_entries; - if (irqfd->gsi >= irq_rt->nr_rt_entries) { - rcu_assign_pointer(irqfd->irq_entry, NULL); - return; - } + n_entries = kvm_irq_map_gsi(kvm, entries, irqfd->gsi); + + write_seqcount_begin(&irqfd->irq_entry_sc); + + irqfd->irq_entry.type = 0; - hlist_for_each_entry(e, &irq_rt->map[irqfd->gsi], link) { + e = entries; + for (i = 0; i < n_entries; ++i, ++e) { /* Only fast-path MSI. */ if (e->type == KVM_IRQ_ROUTING_MSI) - rcu_assign_pointer(irqfd->irq_entry, e); - else - rcu_assign_pointer(irqfd->irq_entry, NULL); + irqfd->irq_entry = *e; } + + write_seqcount_end(&irqfd->irq_entry_sc); } static int kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args) { - struct kvm_irq_routing_table *irq_rt; struct _irqfd *irqfd, *tmp; struct file *file = NULL; struct eventfd_ctx *eventfd = NULL, *resamplefd = NULL; int ret; unsigned int events; + int idx; irqfd = kzalloc(sizeof(*irqfd), GFP_KERNEL); if (!irqfd) @@ -305,6 +320,7 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args) INIT_LIST_HEAD(&irqfd->list); INIT_WORK(&irqfd->inject, irqfd_inject); INIT_WORK(&irqfd->shutdown, irqfd_shutdown); + seqcount_init(&irqfd->irq_entry_sc); file = eventfd_fget(args->fd); if (IS_ERR(file)) { @@ -363,7 +379,7 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args) } list_add_rcu(&irqfd->resampler_link, &irqfd->resampler->list); - synchronize_rcu(); + synchronize_srcu(&kvm->irq_srcu); mutex_unlock(&kvm->irqfds.resampler_lock); } @@ -387,9 +403,9 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args) goto fail; } - irq_rt = rcu_dereference_protected(kvm->irq_routing, - lockdep_is_held(&kvm->irqfds.lock)); - irqfd_update(kvm, irqfd, irq_rt); + idx = srcu_read_lock(&kvm->irq_srcu); + irqfd_update(kvm, irqfd); + srcu_read_unlock(&kvm->irq_srcu, idx); events = file->f_op->poll(file, &irqfd->pt); @@ -428,12 +444,73 @@ fail: kfree(irqfd); return ret; } + +bool kvm_irq_has_notifier(struct kvm *kvm, unsigned irqchip, unsigned pin) +{ + struct kvm_irq_ack_notifier *kian; + int gsi, idx; + + idx = srcu_read_lock(&kvm->irq_srcu); + gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin); + if (gsi != -1) + hlist_for_each_entry_rcu(kian, &kvm->irq_ack_notifier_list, + link) + if (kian->gsi == gsi) { + srcu_read_unlock(&kvm->irq_srcu, idx); + return true; + } + + srcu_read_unlock(&kvm->irq_srcu, idx); + + return false; +} +EXPORT_SYMBOL_GPL(kvm_irq_has_notifier); + +void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin) +{ + struct kvm_irq_ack_notifier *kian; + int gsi, idx; + + trace_kvm_ack_irq(irqchip, pin); + + idx = srcu_read_lock(&kvm->irq_srcu); + gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin); + if (gsi != -1) + hlist_for_each_entry_rcu(kian, &kvm->irq_ack_notifier_list, + link) + if (kian->gsi == gsi) + kian->irq_acked(kian); + srcu_read_unlock(&kvm->irq_srcu, idx); +} + +void kvm_register_irq_ack_notifier(struct kvm *kvm, + struct kvm_irq_ack_notifier *kian) +{ + mutex_lock(&kvm->irq_lock); + hlist_add_head_rcu(&kian->link, &kvm->irq_ack_notifier_list); + mutex_unlock(&kvm->irq_lock); +#ifdef __KVM_HAVE_IOAPIC + kvm_vcpu_request_scan_ioapic(kvm); +#endif +} + +void kvm_unregister_irq_ack_notifier(struct kvm *kvm, + struct kvm_irq_ack_notifier *kian) +{ + mutex_lock(&kvm->irq_lock); + hlist_del_init_rcu(&kian->link); + mutex_unlock(&kvm->irq_lock); + synchronize_srcu(&kvm->irq_srcu); +#ifdef __KVM_HAVE_IOAPIC + kvm_vcpu_request_scan_ioapic(kvm); +#endif +} #endif void kvm_eventfd_init(struct kvm *kvm) { -#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING +#ifdef CONFIG_HAVE_KVM_IRQFD spin_lock_init(&kvm->irqfds.lock); INIT_LIST_HEAD(&kvm->irqfds.items); INIT_LIST_HEAD(&kvm->irqfds.resampler_list); @@ -442,7 +519,7 @@ kvm_eventfd_init(struct kvm *kvm) INIT_LIST_HEAD(&kvm->ioeventfds); } -#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING +#ifdef CONFIG_HAVE_KVM_IRQFD /* * shutdown any irqfd's that match fd+gsi */ @@ -461,14 +538,14 @@ kvm_irqfd_deassign(struct kvm *kvm, struct kvm_irqfd *args) list_for_each_entry_safe(irqfd, tmp, &kvm->irqfds.items, list) { if (irqfd->eventfd == eventfd && irqfd->gsi == args->gsi) { /* - * This rcu_assign_pointer is needed for when + * This clearing of irq_entry.type is needed for when * another thread calls kvm_irq_routing_update before * we flush workqueue below (we synchronize with * kvm_irq_routing_update using irqfds.lock). - * It is paired with synchronize_rcu done by caller - * of that function. */ - rcu_assign_pointer(irqfd->irq_entry, NULL); + write_seqcount_begin(&irqfd->irq_entry_sc); + irqfd->irq_entry.type = 0; + write_seqcount_end(&irqfd->irq_entry_sc); irqfd_deactivate(irqfd); } } @@ -523,20 +600,17 @@ kvm_irqfd_release(struct kvm *kvm) } /* - * Change irq_routing and irqfd. - * Caller must invoke synchronize_rcu afterwards. + * Take note of a change in irq routing. + * Caller must invoke synchronize_srcu(&kvm->irq_srcu) afterwards. */ -void kvm_irq_routing_update(struct kvm *kvm, - struct kvm_irq_routing_table *irq_rt) +void kvm_irq_routing_update(struct kvm *kvm) { struct _irqfd *irqfd; spin_lock_irq(&kvm->irqfds.lock); - rcu_assign_pointer(kvm->irq_routing, irq_rt); - list_for_each_entry(irqfd, &kvm->irqfds.items, list) - irqfd_update(kvm, irqfd, irq_rt); + irqfd_update(kvm, irqfd); spin_unlock_irq(&kvm->irqfds.lock); } diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c index 5eaf18f90e83..b47541dd798f 100644 --- a/virt/kvm/ioapic.c +++ b/virt/kvm/ioapic.c @@ -519,7 +519,7 @@ static int ioapic_mmio_write(struct kvm_io_device *this, gpa_t addr, int len, return 0; } -void kvm_ioapic_reset(struct kvm_ioapic *ioapic) +static void kvm_ioapic_reset(struct kvm_ioapic *ioapic) { int i; diff --git a/virt/kvm/ioapic.h b/virt/kvm/ioapic.h index 615d8c995c3c..90d43e95dcf8 100644 --- a/virt/kvm/ioapic.h +++ b/virt/kvm/ioapic.h @@ -91,7 +91,6 @@ void kvm_ioapic_destroy(struct kvm *kvm); int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id, int level, bool line_status); void kvm_ioapic_clear_all(struct kvm_ioapic *ioapic, int irq_source_id); -void kvm_ioapic_reset(struct kvm_ioapic *ioapic); int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, struct kvm_lapic_irq *irq, unsigned long *dest_map); int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state); diff --git a/virt/kvm/iommu.c b/virt/kvm/iommu.c index a650aa48c786..36f4e82c6b24 100644 --- a/virt/kvm/iommu.c +++ b/virt/kvm/iommu.c @@ -203,11 +203,7 @@ int kvm_assign_device(struct kvm *kvm, pdev->dev_flags |= PCI_DEV_FLAGS_ASSIGNED; - printk(KERN_DEBUG "assign device %x:%x:%x.%x\n", - assigned_dev->host_segnr, - assigned_dev->host_busnr, - PCI_SLOT(assigned_dev->host_devfn), - PCI_FUNC(assigned_dev->host_devfn)); + dev_info(&pdev->dev, "kvm assign device\n"); return 0; out_unmap: @@ -233,11 +229,7 @@ int kvm_deassign_device(struct kvm *kvm, pdev->dev_flags &= ~PCI_DEV_FLAGS_ASSIGNED; - printk(KERN_DEBUG "deassign device %x:%x:%x.%x\n", - assigned_dev->host_segnr, - assigned_dev->host_busnr, - PCI_SLOT(assigned_dev->host_devfn), - PCI_FUNC(assigned_dev->host_devfn)); + dev_info(&pdev->dev, "kvm deassign device\n"); return 0; } diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c index e2e6b4473a96..963b8995a9e8 100644 --- a/virt/kvm/irq_comm.c +++ b/virt/kvm/irq_comm.c @@ -160,9 +160,10 @@ static int kvm_set_msi_inatomic(struct kvm_kernel_irq_routing_entry *e, */ int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level) { + struct kvm_kernel_irq_routing_entry entries[KVM_NR_IRQCHIPS]; struct kvm_kernel_irq_routing_entry *e; int ret = -EINVAL; - struct kvm_irq_routing_table *irq_rt; + int idx; trace_kvm_set_irq(irq, level, irq_source_id); @@ -174,17 +175,15 @@ int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level) * Since there's no easy way to do this, we only support injecting MSI * which is limited to 1:1 GSI mapping. */ - rcu_read_lock(); - irq_rt = rcu_dereference(kvm->irq_routing); - if (irq < irq_rt->nr_rt_entries) - hlist_for_each_entry(e, &irq_rt->map[irq], link) { - if (likely(e->type == KVM_IRQ_ROUTING_MSI)) - ret = kvm_set_msi_inatomic(e, kvm); - else - ret = -EWOULDBLOCK; - break; - } - rcu_read_unlock(); + idx = srcu_read_lock(&kvm->irq_srcu); + if (kvm_irq_map_gsi(kvm, entries, irq) > 0) { + e = &entries[0]; + if (likely(e->type == KVM_IRQ_ROUTING_MSI)) + ret = kvm_set_msi_inatomic(e, kvm); + else + ret = -EWOULDBLOCK; + } + srcu_read_unlock(&kvm->irq_srcu, idx); return ret; } @@ -253,26 +252,25 @@ void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq, mutex_lock(&kvm->irq_lock); hlist_del_rcu(&kimn->link); mutex_unlock(&kvm->irq_lock); - synchronize_rcu(); + synchronize_srcu(&kvm->irq_srcu); } void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin, bool mask) { struct kvm_irq_mask_notifier *kimn; - int gsi; + int idx, gsi; - rcu_read_lock(); - gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin]; + idx = srcu_read_lock(&kvm->irq_srcu); + gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin); if (gsi != -1) hlist_for_each_entry_rcu(kimn, &kvm->mask_notifier_list, link) if (kimn->irq == gsi) kimn->func(kimn, mask); - rcu_read_unlock(); + srcu_read_unlock(&kvm->irq_srcu, idx); } -int kvm_set_routing_entry(struct kvm_irq_routing_table *rt, - struct kvm_kernel_irq_routing_entry *e, +int kvm_set_routing_entry(struct kvm_kernel_irq_routing_entry *e, const struct kvm_irq_routing_entry *ue) { int r = -EINVAL; @@ -303,7 +301,6 @@ int kvm_set_routing_entry(struct kvm_irq_routing_table *rt, e->irqchip.pin = ue->u.irqchip.pin + delta; if (e->irqchip.pin >= max_pin) goto out; - rt->chip[ue->u.irqchip.irqchip][e->irqchip.pin] = ue->gsi; break; case KVM_IRQ_ROUTING_MSI: e->set = kvm_set_msi; @@ -322,13 +319,13 @@ out: #define IOAPIC_ROUTING_ENTRY(irq) \ { .gsi = irq, .type = KVM_IRQ_ROUTING_IRQCHIP, \ - .u.irqchip.irqchip = KVM_IRQCHIP_IOAPIC, .u.irqchip.pin = (irq) } + .u.irqchip = { .irqchip = KVM_IRQCHIP_IOAPIC, .pin = (irq) } } #define ROUTING_ENTRY1(irq) IOAPIC_ROUTING_ENTRY(irq) #ifdef CONFIG_X86 # define PIC_ROUTING_ENTRY(irq) \ { .gsi = irq, .type = KVM_IRQ_ROUTING_IRQCHIP, \ - .u.irqchip.irqchip = SELECT_PIC(irq), .u.irqchip.pin = (irq) % 8 } + .u.irqchip = { .irqchip = SELECT_PIC(irq), .pin = (irq) % 8 } } # define ROUTING_ENTRY2(irq) \ IOAPIC_ROUTING_ENTRY(irq), PIC_ROUTING_ENTRY(irq) #else diff --git a/virt/kvm/irqchip.c b/virt/kvm/irqchip.c index 20dc9e4a8f6c..7f256f31df10 100644 --- a/virt/kvm/irqchip.c +++ b/virt/kvm/irqchip.c @@ -26,69 +26,47 @@ #include <linux/kvm_host.h> #include <linux/slab.h> +#include <linux/srcu.h> #include <linux/export.h> #include <trace/events/kvm.h> #include "irq.h" -bool kvm_irq_has_notifier(struct kvm *kvm, unsigned irqchip, unsigned pin) -{ - struct kvm_irq_ack_notifier *kian; - int gsi; - - rcu_read_lock(); - gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin]; - if (gsi != -1) - hlist_for_each_entry_rcu(kian, &kvm->irq_ack_notifier_list, - link) - if (kian->gsi == gsi) { - rcu_read_unlock(); - return true; - } - - rcu_read_unlock(); - - return false; -} -EXPORT_SYMBOL_GPL(kvm_irq_has_notifier); +struct kvm_irq_routing_table { + int chip[KVM_NR_IRQCHIPS][KVM_IRQCHIP_NUM_PINS]; + struct kvm_kernel_irq_routing_entry *rt_entries; + u32 nr_rt_entries; + /* + * Array indexed by gsi. Each entry contains list of irq chips + * the gsi is connected to. + */ + struct hlist_head map[0]; +}; -void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin) +int kvm_irq_map_gsi(struct kvm *kvm, + struct kvm_kernel_irq_routing_entry *entries, int gsi) { - struct kvm_irq_ack_notifier *kian; - int gsi; - - trace_kvm_ack_irq(irqchip, pin); - - rcu_read_lock(); - gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin]; - if (gsi != -1) - hlist_for_each_entry_rcu(kian, &kvm->irq_ack_notifier_list, - link) - if (kian->gsi == gsi) - kian->irq_acked(kian); - rcu_read_unlock(); -} + struct kvm_irq_routing_table *irq_rt; + struct kvm_kernel_irq_routing_entry *e; + int n = 0; + + irq_rt = srcu_dereference_check(kvm->irq_routing, &kvm->irq_srcu, + lockdep_is_held(&kvm->irq_lock)); + if (gsi < irq_rt->nr_rt_entries) { + hlist_for_each_entry(e, &irq_rt->map[gsi], link) { + entries[n] = *e; + ++n; + } + } -void kvm_register_irq_ack_notifier(struct kvm *kvm, - struct kvm_irq_ack_notifier *kian) -{ - mutex_lock(&kvm->irq_lock); - hlist_add_head_rcu(&kian->link, &kvm->irq_ack_notifier_list); - mutex_unlock(&kvm->irq_lock); -#ifdef __KVM_HAVE_IOAPIC - kvm_vcpu_request_scan_ioapic(kvm); -#endif + return n; } -void kvm_unregister_irq_ack_notifier(struct kvm *kvm, - struct kvm_irq_ack_notifier *kian) +int kvm_irq_map_chip_pin(struct kvm *kvm, unsigned irqchip, unsigned pin) { - mutex_lock(&kvm->irq_lock); - hlist_del_init_rcu(&kian->link); - mutex_unlock(&kvm->irq_lock); - synchronize_rcu(); -#ifdef __KVM_HAVE_IOAPIC - kvm_vcpu_request_scan_ioapic(kvm); -#endif + struct kvm_irq_routing_table *irq_rt; + + irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu); + return irq_rt->chip[irqchip][pin]; } int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi) @@ -114,9 +92,8 @@ int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi) int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level, bool line_status) { - struct kvm_kernel_irq_routing_entry *e, irq_set[KVM_NR_IRQCHIPS]; - int ret = -1, i = 0; - struct kvm_irq_routing_table *irq_rt; + struct kvm_kernel_irq_routing_entry irq_set[KVM_NR_IRQCHIPS]; + int ret = -1, i, idx; trace_kvm_set_irq(irq, level, irq_source_id); @@ -124,12 +101,9 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level, * IOAPIC. So set the bit in both. The guest will ignore * writes to the unused one. */ - rcu_read_lock(); - irq_rt = rcu_dereference(kvm->irq_routing); - if (irq < irq_rt->nr_rt_entries) - hlist_for_each_entry(e, &irq_rt->map[irq], link) - irq_set[i++] = *e; - rcu_read_unlock(); + idx = srcu_read_lock(&kvm->irq_srcu); + i = kvm_irq_map_gsi(kvm, irq_set, irq); + srcu_read_unlock(&kvm->irq_srcu, idx); while(i--) { int r; @@ -170,9 +144,11 @@ static int setup_routing_entry(struct kvm_irq_routing_table *rt, e->gsi = ue->gsi; e->type = ue->type; - r = kvm_set_routing_entry(rt, e, ue); + r = kvm_set_routing_entry(e, ue); if (r) goto out; + if (e->type == KVM_IRQ_ROUTING_IRQCHIP) + rt->chip[e->irqchip.irqchip][e->irqchip.pin] = e->gsi; hlist_add_head(&e->link, &rt->map[e->gsi]); r = 0; @@ -223,10 +199,11 @@ int kvm_set_irq_routing(struct kvm *kvm, mutex_lock(&kvm->irq_lock); old = kvm->irq_routing; - kvm_irq_routing_update(kvm, new); + rcu_assign_pointer(kvm->irq_routing, new); + kvm_irq_routing_update(kvm); mutex_unlock(&kvm->irq_lock); - synchronize_rcu(); + synchronize_srcu_expedited(&kvm->irq_srcu); new = old; r = 0; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index a17f190be58e..4eed4cd9b58b 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -71,7 +71,8 @@ MODULE_LICENSE("GPL"); * kvm->lock --> kvm->slots_lock --> kvm->irq_lock */ -DEFINE_RAW_SPINLOCK(kvm_lock); +DEFINE_SPINLOCK(kvm_lock); +static DEFINE_RAW_SPINLOCK(kvm_count_lock); LIST_HEAD(vm_list); static cpumask_var_t cpus_hardware_enabled; @@ -95,36 +96,22 @@ static int hardware_enable_all(void); static void hardware_disable_all(void); static void kvm_io_bus_destroy(struct kvm_io_bus *bus); +static void update_memslots(struct kvm_memslots *slots, + struct kvm_memory_slot *new, u64 last_generation); -bool kvm_rebooting; +static void kvm_release_pfn_dirty(pfn_t pfn); +static void mark_page_dirty_in_slot(struct kvm *kvm, + struct kvm_memory_slot *memslot, gfn_t gfn); + +__visible bool kvm_rebooting; EXPORT_SYMBOL_GPL(kvm_rebooting); static bool largepages_enabled = true; bool kvm_is_mmio_pfn(pfn_t pfn) { - if (pfn_valid(pfn)) { - int reserved; - struct page *tail = pfn_to_page(pfn); - struct page *head = compound_head(tail); - reserved = PageReserved(head); - if (head != tail) { - /* - * "head" is not a dangling pointer - * (compound_head takes care of that) - * but the hugepage may have been splitted - * from under us (and we may not hold a - * reference count on the head page so it can - * be reused before we run PageReferenced), so - * we've to check PageTail before returning - * what we just read. - */ - smp_rmb(); - if (PageTail(tail)) - return reserved; - } - return PageReserved(tail); - } + if (pfn_valid(pfn)) + return !is_zero_pfn(pfn) && PageReserved(pfn_to_page(pfn)); return true; } @@ -143,7 +130,8 @@ int vcpu_load(struct kvm_vcpu *vcpu) struct pid *oldpid = vcpu->pid; struct pid *newpid = get_task_pid(current, PIDTYPE_PID); rcu_assign_pointer(vcpu->pid, newpid); - synchronize_rcu(); + if (oldpid) + synchronize_rcu(); put_pid(oldpid); } cpu = get_cpu(); @@ -470,14 +458,16 @@ static struct kvm *kvm_create_vm(unsigned long type) r = kvm_arch_init_vm(kvm, type); if (r) - goto out_err_nodisable; + goto out_err_no_disable; r = hardware_enable_all(); if (r) - goto out_err_nodisable; + goto out_err_no_disable; #ifdef CONFIG_HAVE_KVM_IRQCHIP INIT_HLIST_HEAD(&kvm->mask_notifier_list); +#endif +#ifdef CONFIG_HAVE_KVM_IRQFD INIT_HLIST_HEAD(&kvm->irq_ack_notifier_list); #endif @@ -486,10 +476,12 @@ static struct kvm *kvm_create_vm(unsigned long type) r = -ENOMEM; kvm->memslots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL); if (!kvm->memslots) - goto out_err_nosrcu; + goto out_err_no_srcu; kvm_init_memslots_id(kvm); if (init_srcu_struct(&kvm->srcu)) - goto out_err_nosrcu; + goto out_err_no_srcu; + if (init_srcu_struct(&kvm->irq_srcu)) + goto out_err_no_irq_srcu; for (i = 0; i < KVM_NR_BUSES; i++) { kvm->buses[i] = kzalloc(sizeof(struct kvm_io_bus), GFP_KERNEL); @@ -511,17 +503,19 @@ static struct kvm *kvm_create_vm(unsigned long type) if (r) goto out_err; - raw_spin_lock(&kvm_lock); + spin_lock(&kvm_lock); list_add(&kvm->vm_list, &vm_list); - raw_spin_unlock(&kvm_lock); + spin_unlock(&kvm_lock); return kvm; out_err: + cleanup_srcu_struct(&kvm->irq_srcu); +out_err_no_irq_srcu: cleanup_srcu_struct(&kvm->srcu); -out_err_nosrcu: +out_err_no_srcu: hardware_disable_all(); -out_err_nodisable: +out_err_no_disable: for (i = 0; i < KVM_NR_BUSES; i++) kfree(kvm->buses[i]); kfree(kvm->memslots); @@ -561,24 +555,24 @@ static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot) /* * Free any memory in @free but not in @dont. */ -static void kvm_free_physmem_slot(struct kvm_memory_slot *free, +static void kvm_free_physmem_slot(struct kvm *kvm, struct kvm_memory_slot *free, struct kvm_memory_slot *dont) { if (!dont || free->dirty_bitmap != dont->dirty_bitmap) kvm_destroy_dirty_bitmap(free); - kvm_arch_free_memslot(free, dont); + kvm_arch_free_memslot(kvm, free, dont); free->npages = 0; } -void kvm_free_physmem(struct kvm *kvm) +static void kvm_free_physmem(struct kvm *kvm) { struct kvm_memslots *slots = kvm->memslots; struct kvm_memory_slot *memslot; kvm_for_each_memslot(memslot, slots) - kvm_free_physmem_slot(memslot, NULL); + kvm_free_physmem_slot(kvm, memslot, NULL); kfree(kvm->memslots); } @@ -602,9 +596,9 @@ static void kvm_destroy_vm(struct kvm *kvm) struct mm_struct *mm = kvm->mm; kvm_arch_sync_events(kvm); - raw_spin_lock(&kvm_lock); + spin_lock(&kvm_lock); list_del(&kvm->vm_list); - raw_spin_unlock(&kvm_lock); + spin_unlock(&kvm_lock); kvm_free_irq_routing(kvm); for (i = 0; i < KVM_NR_BUSES; i++) kvm_io_bus_destroy(kvm->buses[i]); @@ -617,6 +611,7 @@ static void kvm_destroy_vm(struct kvm *kvm) kvm_arch_destroy_vm(kvm); kvm_destroy_devices(kvm); kvm_free_physmem(kvm); + cleanup_srcu_struct(&kvm->irq_srcu); cleanup_srcu_struct(&kvm->srcu); kvm_arch_free_vm(kvm); hardware_disable_all(); @@ -694,8 +689,9 @@ static void sort_memslots(struct kvm_memslots *slots) slots->id_to_index[slots->memslots[i].id] = i; } -void update_memslots(struct kvm_memslots *slots, struct kvm_memory_slot *new, - u64 last_generation) +static void update_memslots(struct kvm_memslots *slots, + struct kvm_memory_slot *new, + u64 last_generation) { if (new) { int id = new->id; @@ -714,7 +710,7 @@ static int check_memory_region_flags(struct kvm_userspace_memory_region *mem) { u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES; -#ifdef KVM_CAP_READONLY_MEM +#ifdef __KVM_HAVE_READONLY_MEM valid_flags |= KVM_MEM_READONLY; #endif @@ -732,7 +728,10 @@ static struct kvm_memslots *install_new_memslots(struct kvm *kvm, update_memslots(slots, new, kvm->memslots->generation); rcu_assign_pointer(kvm->memslots, slots); synchronize_srcu_expedited(&kvm->srcu); - return old_memslots; + + kvm_arch_memslots_updated(kvm); + + return old_memslots; } /* @@ -780,7 +779,6 @@ int __kvm_set_memory_region(struct kvm *kvm, base_gfn = mem->guest_phys_addr >> PAGE_SHIFT; npages = mem->memory_size >> PAGE_SHIFT; - r = -EINVAL; if (npages > KVM_MEM_MAX_NR_PAGES) goto out; @@ -794,7 +792,6 @@ int __kvm_set_memory_region(struct kvm *kvm, new.npages = npages; new.flags = mem->flags; - r = -EINVAL; if (npages) { if (!old.npages) change = KVM_MR_CREATE; @@ -839,7 +836,7 @@ int __kvm_set_memory_region(struct kvm *kvm, if (change == KVM_MR_CREATE) { new.userspace_addr = mem->userspace_addr; - if (kvm_arch_create_memslot(&new, npages)) + if (kvm_arch_create_memslot(kvm, &new, npages)) goto out_free; } @@ -850,7 +847,6 @@ int __kvm_set_memory_region(struct kvm *kvm, } if ((change == KVM_MR_DELETE) || (change == KVM_MR_MOVE)) { - r = -ENOMEM; slots = kmemdup(kvm->memslots, sizeof(struct kvm_memslots), GFP_KERNEL); if (!slots) @@ -890,6 +886,19 @@ int __kvm_set_memory_region(struct kvm *kvm, goto out_free; } + /* actual memory is freed via old in kvm_free_physmem_slot below */ + if (change == KVM_MR_DELETE) { + new.dirty_bitmap = NULL; + memset(&new.arch, 0, sizeof(new.arch)); + } + + old_memslots = install_new_memslots(kvm, slots, &new); + + kvm_arch_commit_memory_region(kvm, mem, &old, change); + + kvm_free_physmem_slot(kvm, &old, &new); + kfree(old_memslots); + /* * IOMMU mapping: New slots need to be mapped. Old slots need to be * un-mapped and re-mapped if their base changes. Since base change @@ -901,29 +910,15 @@ int __kvm_set_memory_region(struct kvm *kvm, */ if ((change == KVM_MR_CREATE) || (change == KVM_MR_MOVE)) { r = kvm_iommu_map_pages(kvm, &new); - if (r) - goto out_slots; - } - - /* actual memory is freed via old in kvm_free_physmem_slot below */ - if (change == KVM_MR_DELETE) { - new.dirty_bitmap = NULL; - memset(&new.arch, 0, sizeof(new.arch)); + return r; } - old_memslots = install_new_memslots(kvm, slots, &new); - - kvm_arch_commit_memory_region(kvm, mem, &old, change); - - kvm_free_physmem_slot(&old, &new); - kfree(old_memslots); - return 0; out_slots: kfree(slots); out_free: - kvm_free_physmem_slot(&new, &old); + kvm_free_physmem_slot(kvm, &new, &old); out: return r; } @@ -941,8 +936,8 @@ int kvm_set_memory_region(struct kvm *kvm, } EXPORT_SYMBOL_GPL(kvm_set_memory_region); -int kvm_vm_ioctl_set_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem) +static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm, + struct kvm_userspace_memory_region *mem) { if (mem->slot >= KVM_USER_MEM_SLOTS) return -EINVAL; @@ -1063,7 +1058,7 @@ static unsigned long gfn_to_hva_many(struct kvm_memory_slot *slot, gfn_t gfn, } unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot, - gfn_t gfn) + gfn_t gfn) { return gfn_to_hva_many(slot, gfn, NULL); } @@ -1076,12 +1071,25 @@ unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn) EXPORT_SYMBOL_GPL(gfn_to_hva); /* - * The hva returned by this function is only allowed to be read. - * It should pair with kvm_read_hva() or kvm_read_hva_atomic(). + * If writable is set to false, the hva returned by this function is only + * allowed to be read. */ -static unsigned long gfn_to_hva_read(struct kvm *kvm, gfn_t gfn) +unsigned long gfn_to_hva_memslot_prot(struct kvm_memory_slot *slot, + gfn_t gfn, bool *writable) { - return __gfn_to_hva_many(gfn_to_memslot(kvm, gfn), gfn, NULL, false); + unsigned long hva = __gfn_to_hva_many(slot, gfn, NULL, false); + + if (!kvm_is_error_hva(hva) && writable) + *writable = !memslot_is_readonly(slot); + + return hva; +} + +unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable) +{ + struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn); + + return gfn_to_hva_memslot_prot(slot, gfn, writable); } static int kvm_read_hva(void *data, void __user *hva, int len) @@ -1397,18 +1405,11 @@ void kvm_release_page_dirty(struct page *page) } EXPORT_SYMBOL_GPL(kvm_release_page_dirty); -void kvm_release_pfn_dirty(pfn_t pfn) +static void kvm_release_pfn_dirty(pfn_t pfn) { kvm_set_pfn_dirty(pfn); kvm_release_pfn_clean(pfn); } -EXPORT_SYMBOL_GPL(kvm_release_pfn_dirty); - -void kvm_set_page_dirty(struct page *page) -{ - kvm_set_pfn_dirty(page_to_pfn(page)); -} -EXPORT_SYMBOL_GPL(kvm_set_page_dirty); void kvm_set_pfn_dirty(pfn_t pfn) { @@ -1448,7 +1449,7 @@ int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, int r; unsigned long addr; - addr = gfn_to_hva_read(kvm, gfn); + addr = gfn_to_hva_prot(kvm, gfn, NULL); if (kvm_is_error_hva(addr)) return -EFAULT; r = kvm_read_hva(data, (void __user *)addr + offset, len); @@ -1486,7 +1487,7 @@ int kvm_read_guest_atomic(struct kvm *kvm, gpa_t gpa, void *data, gfn_t gfn = gpa >> PAGE_SHIFT; int offset = offset_in_page(gpa); - addr = gfn_to_hva_read(kvm, gfn); + addr = gfn_to_hva_prot(kvm, gfn, NULL); if (kvm_is_error_hva(addr)) return -EFAULT; pagefault_disable(); @@ -1625,8 +1626,9 @@ EXPORT_SYMBOL_GPL(kvm_read_guest_cached); int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len) { - return kvm_write_guest_page(kvm, gfn, (const void *) empty_zero_page, - offset, len); + const void *zero_page = (const void *) __va(page_to_phys(ZERO_PAGE(0))); + + return kvm_write_guest_page(kvm, gfn, zero_page, offset, len); } EXPORT_SYMBOL_GPL(kvm_clear_guest_page); @@ -1649,8 +1651,9 @@ int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len) } EXPORT_SYMBOL_GPL(kvm_clear_guest); -void mark_page_dirty_in_slot(struct kvm *kvm, struct kvm_memory_slot *memslot, - gfn_t gfn) +static void mark_page_dirty_in_slot(struct kvm *kvm, + struct kvm_memory_slot *memslot, + gfn_t gfn) { if (memslot && memslot->dirty_bitmap) { unsigned long rel_gfn = gfn - memslot->base_gfn; @@ -1717,14 +1720,6 @@ void kvm_vcpu_kick(struct kvm_vcpu *vcpu) EXPORT_SYMBOL_GPL(kvm_vcpu_kick); #endif /* !CONFIG_S390 */ -void kvm_resched(struct kvm_vcpu *vcpu) -{ - if (!need_resched()) - return; - cond_resched(); -} -EXPORT_SYMBOL_GPL(kvm_resched); - bool kvm_vcpu_yield_to(struct kvm_vcpu *target) { struct pid *pid; @@ -1734,7 +1729,7 @@ bool kvm_vcpu_yield_to(struct kvm_vcpu *target) rcu_read_lock(); pid = rcu_dereference(target->pid); if (pid) - task = get_pid_task(target->pid, PIDTYPE_PID); + task = get_pid_task(pid, PIDTYPE_PID); rcu_read_unlock(); if (!task) return ret; @@ -1749,7 +1744,6 @@ bool kvm_vcpu_yield_to(struct kvm_vcpu *target) } EXPORT_SYMBOL_GPL(kvm_vcpu_yield_to); -#ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT /* * Helper that checks whether a VCPU is eligible for directed yield. * Most eligible candidate to yield is decided by following heuristics: @@ -1772,20 +1766,22 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_yield_to); * locking does not harm. It may result in trying to yield to same VCPU, fail * and continue with next VCPU and so on. */ -bool kvm_vcpu_eligible_for_directed_yield(struct kvm_vcpu *vcpu) +static bool kvm_vcpu_eligible_for_directed_yield(struct kvm_vcpu *vcpu) { +#ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT bool eligible; eligible = !vcpu->spin_loop.in_spin_loop || - (vcpu->spin_loop.in_spin_loop && - vcpu->spin_loop.dy_eligible); + vcpu->spin_loop.dy_eligible; if (vcpu->spin_loop.in_spin_loop) kvm_vcpu_set_dy_eligible(vcpu, !vcpu->spin_loop.dy_eligible); return eligible; -} +#else + return true; #endif +} void kvm_vcpu_on_spin(struct kvm_vcpu *me) { @@ -1816,7 +1812,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me) continue; if (vcpu == me) continue; - if (waitqueue_active(&vcpu->wq)) + if (waitqueue_active(&vcpu->wq) && !kvm_arch_vcpu_runnable(vcpu)) continue; if (!kvm_vcpu_eligible_for_directed_yield(vcpu)) continue; @@ -1894,7 +1890,7 @@ static struct file_operations kvm_vcpu_fops = { */ static int create_vcpu_fd(struct kvm_vcpu *vcpu) { - return anon_inode_getfd("kvm-vcpu", &kvm_vcpu_fops, vcpu, O_RDWR); + return anon_inode_getfd("kvm-vcpu", &kvm_vcpu_fops, vcpu, O_RDWR | O_CLOEXEC); } /* @@ -2269,6 +2265,29 @@ struct kvm_device *kvm_device_from_filp(struct file *filp) return filp->private_data; } +static struct kvm_device_ops *kvm_device_ops_table[KVM_DEV_TYPE_MAX] = { +#ifdef CONFIG_KVM_MPIC + [KVM_DEV_TYPE_FSL_MPIC_20] = &kvm_mpic_ops, + [KVM_DEV_TYPE_FSL_MPIC_42] = &kvm_mpic_ops, +#endif + +#ifdef CONFIG_KVM_XICS + [KVM_DEV_TYPE_XICS] = &kvm_xics_ops, +#endif +}; + +int kvm_register_device_ops(struct kvm_device_ops *ops, u32 type) +{ + if (type >= ARRAY_SIZE(kvm_device_ops_table)) + return -ENOSPC; + + if (kvm_device_ops_table[type] != NULL) + return -EEXIST; + + kvm_device_ops_table[type] = ops; + return 0; +} + static int kvm_ioctl_create_device(struct kvm *kvm, struct kvm_create_device *cd) { @@ -2277,21 +2296,12 @@ static int kvm_ioctl_create_device(struct kvm *kvm, bool test = cd->flags & KVM_CREATE_DEVICE_TEST; int ret; - switch (cd->type) { -#ifdef CONFIG_KVM_MPIC - case KVM_DEV_TYPE_FSL_MPIC_20: - case KVM_DEV_TYPE_FSL_MPIC_42: - ops = &kvm_mpic_ops; - break; -#endif -#ifdef CONFIG_KVM_XICS - case KVM_DEV_TYPE_XICS: - ops = &kvm_xics_ops; - break; -#endif - default: + if (cd->type >= ARRAY_SIZE(kvm_device_ops_table)) + return -ENODEV; + + ops = kvm_device_ops_table[cd->type]; + if (ops == NULL) return -ENODEV; - } if (test) return 0; @@ -2309,7 +2319,7 @@ static int kvm_ioctl_create_device(struct kvm *kvm, return ret; } - ret = anon_inode_getfd(ops->name, &kvm_device_fops, dev, O_RDWR); + ret = anon_inode_getfd(ops->name, &kvm_device_fops, dev, O_RDWR | O_CLOEXEC); if (ret < 0) { ops->destroy(dev); return ret; @@ -2321,6 +2331,34 @@ static int kvm_ioctl_create_device(struct kvm *kvm, return 0; } +static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) +{ + switch (arg) { + case KVM_CAP_USER_MEMORY: + case KVM_CAP_DESTROY_MEMORY_REGION_WORKS: + case KVM_CAP_JOIN_MEMORY_REGIONS_WORKS: +#ifdef CONFIG_KVM_APIC_ARCHITECTURE + case KVM_CAP_SET_BOOT_CPU_ID: +#endif + case KVM_CAP_INTERNAL_ERROR_DATA: +#ifdef CONFIG_HAVE_KVM_MSI + case KVM_CAP_SIGNAL_MSI: +#endif +#ifdef CONFIG_HAVE_KVM_IRQFD + case KVM_CAP_IRQFD_RESAMPLE: +#endif + case KVM_CAP_CHECK_EXTENSION_VM: + return 1; +#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING + case KVM_CAP_IRQ_ROUTING: + return KVM_MAX_IRQ_ROUTES; +#endif + default: + break; + } + return kvm_vm_ioctl_check_extension(kvm, arg); +} + static long kvm_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -2484,6 +2522,9 @@ static long kvm_vm_ioctl(struct file *filp, r = 0; break; } + case KVM_CHECK_EXTENSION: + r = kvm_vm_ioctl_check_extension_generic(kvm, arg); + break; default: r = kvm_arch_vm_ioctl(filp, ioctl, arg); if (r == -ENOTTY) @@ -2537,44 +2578,12 @@ out: } #endif -static int kvm_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf) -{ - struct page *page[1]; - unsigned long addr; - int npages; - gfn_t gfn = vmf->pgoff; - struct kvm *kvm = vma->vm_file->private_data; - - addr = gfn_to_hva(kvm, gfn); - if (kvm_is_error_hva(addr)) - return VM_FAULT_SIGBUS; - - npages = get_user_pages(current, current->mm, addr, 1, 1, 0, page, - NULL); - if (unlikely(npages != 1)) - return VM_FAULT_SIGBUS; - - vmf->page = page[0]; - return 0; -} - -static const struct vm_operations_struct kvm_vm_vm_ops = { - .fault = kvm_vm_fault, -}; - -static int kvm_vm_mmap(struct file *file, struct vm_area_struct *vma) -{ - vma->vm_ops = &kvm_vm_vm_ops; - return 0; -} - static struct file_operations kvm_vm_fops = { .release = kvm_vm_release, .unlocked_ioctl = kvm_vm_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = kvm_vm_compat_ioctl, #endif - .mmap = kvm_vm_mmap, .llseek = noop_llseek, }; @@ -2593,40 +2602,13 @@ static int kvm_dev_ioctl_create_vm(unsigned long type) return r; } #endif - r = anon_inode_getfd("kvm-vm", &kvm_vm_fops, kvm, O_RDWR); + r = anon_inode_getfd("kvm-vm", &kvm_vm_fops, kvm, O_RDWR | O_CLOEXEC); if (r < 0) kvm_put_kvm(kvm); return r; } -static long kvm_dev_ioctl_check_extension_generic(long arg) -{ - switch (arg) { - case KVM_CAP_USER_MEMORY: - case KVM_CAP_DESTROY_MEMORY_REGION_WORKS: - case KVM_CAP_JOIN_MEMORY_REGIONS_WORKS: -#ifdef CONFIG_KVM_APIC_ARCHITECTURE - case KVM_CAP_SET_BOOT_CPU_ID: -#endif - case KVM_CAP_INTERNAL_ERROR_DATA: -#ifdef CONFIG_HAVE_KVM_MSI - case KVM_CAP_SIGNAL_MSI: -#endif -#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING - case KVM_CAP_IRQFD_RESAMPLE: -#endif - return 1; -#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING - case KVM_CAP_IRQ_ROUTING: - return KVM_MAX_IRQ_ROUTES; -#endif - default: - break; - } - return kvm_dev_ioctl_check_extension(arg); -} - static long kvm_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -2634,7 +2616,6 @@ static long kvm_dev_ioctl(struct file *filp, switch (ioctl) { case KVM_GET_API_VERSION: - r = -EINVAL; if (arg) goto out; r = KVM_API_VERSION; @@ -2643,10 +2624,9 @@ static long kvm_dev_ioctl(struct file *filp, r = kvm_dev_ioctl_create_vm(arg); break; case KVM_CHECK_EXTENSION: - r = kvm_dev_ioctl_check_extension_generic(arg); + r = kvm_vm_ioctl_check_extension_generic(NULL, arg); break; case KVM_GET_VCPU_MMAP_SIZE: - r = -EINVAL; if (arg) goto out; r = PAGE_SIZE; /* struct kvm_run */ @@ -2691,7 +2671,7 @@ static void hardware_enable_nolock(void *junk) cpumask_set_cpu(cpu, cpus_hardware_enabled); - r = kvm_arch_hardware_enable(NULL); + r = kvm_arch_hardware_enable(); if (r) { cpumask_clear_cpu(cpu, cpus_hardware_enabled); @@ -2701,11 +2681,12 @@ static void hardware_enable_nolock(void *junk) } } -static void hardware_enable(void *junk) +static void hardware_enable(void) { - raw_spin_lock(&kvm_lock); - hardware_enable_nolock(junk); - raw_spin_unlock(&kvm_lock); + raw_spin_lock(&kvm_count_lock); + if (kvm_usage_count) + hardware_enable_nolock(NULL); + raw_spin_unlock(&kvm_count_lock); } static void hardware_disable_nolock(void *junk) @@ -2715,14 +2696,15 @@ static void hardware_disable_nolock(void *junk) if (!cpumask_test_cpu(cpu, cpus_hardware_enabled)) return; cpumask_clear_cpu(cpu, cpus_hardware_enabled); - kvm_arch_hardware_disable(NULL); + kvm_arch_hardware_disable(); } -static void hardware_disable(void *junk) +static void hardware_disable(void) { - raw_spin_lock(&kvm_lock); - hardware_disable_nolock(junk); - raw_spin_unlock(&kvm_lock); + raw_spin_lock(&kvm_count_lock); + if (kvm_usage_count) + hardware_disable_nolock(NULL); + raw_spin_unlock(&kvm_count_lock); } static void hardware_disable_all_nolock(void) @@ -2736,16 +2718,16 @@ static void hardware_disable_all_nolock(void) static void hardware_disable_all(void) { - raw_spin_lock(&kvm_lock); + raw_spin_lock(&kvm_count_lock); hardware_disable_all_nolock(); - raw_spin_unlock(&kvm_lock); + raw_spin_unlock(&kvm_count_lock); } static int hardware_enable_all(void) { int r = 0; - raw_spin_lock(&kvm_lock); + raw_spin_lock(&kvm_count_lock); kvm_usage_count++; if (kvm_usage_count == 1) { @@ -2758,7 +2740,7 @@ static int hardware_enable_all(void) } } - raw_spin_unlock(&kvm_lock); + raw_spin_unlock(&kvm_count_lock); return r; } @@ -2768,20 +2750,17 @@ static int kvm_cpu_hotplug(struct notifier_block *notifier, unsigned long val, { int cpu = (long)v; - if (!kvm_usage_count) - return NOTIFY_OK; - val &= ~CPU_TASKS_FROZEN; switch (val) { case CPU_DYING: printk(KERN_INFO "kvm: disabling virtualization on CPU%d\n", cpu); - hardware_disable(NULL); + hardware_disable(); break; case CPU_STARTING: printk(KERN_INFO "kvm: enabling virtualization on CPU%d\n", cpu); - hardware_enable(NULL); + hardware_enable(); break; } return NOTIFY_OK; @@ -2994,10 +2973,10 @@ static int vm_stat_get(void *_offset, u64 *val) struct kvm *kvm; *val = 0; - raw_spin_lock(&kvm_lock); + spin_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) *val += *(u32 *)((void *)kvm + offset); - raw_spin_unlock(&kvm_lock); + spin_unlock(&kvm_lock); return 0; } @@ -3011,12 +2990,12 @@ static int vcpu_stat_get(void *_offset, u64 *val) int i; *val = 0; - raw_spin_lock(&kvm_lock); + spin_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) kvm_for_each_vcpu(i, vcpu, kvm) *val += *(u32 *)((void *)vcpu + offset); - raw_spin_unlock(&kvm_lock); + spin_unlock(&kvm_lock); return 0; } @@ -3029,7 +3008,7 @@ static const struct file_operations *stat_fops[] = { static int kvm_init_debug(void) { - int r = -EFAULT; + int r = -EEXIST; struct kvm_stats_debugfs_item *p; kvm_debugfs_dir = debugfs_create_dir("kvm", NULL); @@ -3071,7 +3050,7 @@ static int kvm_suspend(void) static void kvm_resume(void) { if (kvm_usage_count) { - WARN_ON(raw_spin_is_locked(&kvm_lock)); + WARN_ON(raw_spin_is_locked(&kvm_count_lock)); hardware_enable_nolock(NULL); } } @@ -3093,6 +3072,8 @@ static void kvm_sched_in(struct preempt_notifier *pn, int cpu) if (vcpu->preempted) vcpu->preempted = false; + kvm_arch_sched_in(vcpu, cpu); + kvm_arch_vcpu_load(vcpu, cpu); } @@ -3188,6 +3169,7 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align, out_undebugfs: unregister_syscore_ops(&kvm_syscore_ops); + misc_deregister(&kvm_dev); out_unreg: kvm_async_pf_deinit(); out_free: diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c new file mode 100644 index 000000000000..475487e238e1 --- /dev/null +++ b/virt/kvm/vfio.c @@ -0,0 +1,228 @@ +/* + * VFIO-KVM bridge pseudo device + * + * Copyright (C) 2013 Red Hat, Inc. All rights reserved. + * Author: Alex Williamson <alex.williamson@redhat.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/errno.h> +#include <linux/file.h> +#include <linux/kvm_host.h> +#include <linux/list.h> +#include <linux/module.h> +#include <linux/mutex.h> +#include <linux/slab.h> +#include <linux/uaccess.h> +#include <linux/vfio.h> + +struct kvm_vfio_group { + struct list_head node; + struct vfio_group *vfio_group; +}; + +struct kvm_vfio { + struct list_head group_list; + struct mutex lock; +}; + +static struct vfio_group *kvm_vfio_group_get_external_user(struct file *filep) +{ + struct vfio_group *vfio_group; + struct vfio_group *(*fn)(struct file *); + + fn = symbol_get(vfio_group_get_external_user); + if (!fn) + return ERR_PTR(-EINVAL); + + vfio_group = fn(filep); + + symbol_put(vfio_group_get_external_user); + + return vfio_group; +} + +static void kvm_vfio_group_put_external_user(struct vfio_group *vfio_group) +{ + void (*fn)(struct vfio_group *); + + fn = symbol_get(vfio_group_put_external_user); + if (!fn) + return; + + fn(vfio_group); + + symbol_put(vfio_group_put_external_user); +} + +static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg) +{ + struct kvm_vfio *kv = dev->private; + struct vfio_group *vfio_group; + struct kvm_vfio_group *kvg; + void __user *argp = (void __user *)arg; + struct fd f; + int32_t fd; + int ret; + + switch (attr) { + case KVM_DEV_VFIO_GROUP_ADD: + if (get_user(fd, (int32_t __user *)argp)) + return -EFAULT; + + f = fdget(fd); + if (!f.file) + return -EBADF; + + vfio_group = kvm_vfio_group_get_external_user(f.file); + fdput(f); + + if (IS_ERR(vfio_group)) + return PTR_ERR(vfio_group); + + mutex_lock(&kv->lock); + + list_for_each_entry(kvg, &kv->group_list, node) { + if (kvg->vfio_group == vfio_group) { + mutex_unlock(&kv->lock); + kvm_vfio_group_put_external_user(vfio_group); + return -EEXIST; + } + } + + kvg = kzalloc(sizeof(*kvg), GFP_KERNEL); + if (!kvg) { + mutex_unlock(&kv->lock); + kvm_vfio_group_put_external_user(vfio_group); + return -ENOMEM; + } + + list_add_tail(&kvg->node, &kv->group_list); + kvg->vfio_group = vfio_group; + + mutex_unlock(&kv->lock); + + return 0; + + case KVM_DEV_VFIO_GROUP_DEL: + if (get_user(fd, (int32_t __user *)argp)) + return -EFAULT; + + f = fdget(fd); + if (!f.file) + return -EBADF; + + vfio_group = kvm_vfio_group_get_external_user(f.file); + fdput(f); + + if (IS_ERR(vfio_group)) + return PTR_ERR(vfio_group); + + ret = -ENOENT; + + mutex_lock(&kv->lock); + + list_for_each_entry(kvg, &kv->group_list, node) { + if (kvg->vfio_group != vfio_group) + continue; + + list_del(&kvg->node); + kvm_vfio_group_put_external_user(kvg->vfio_group); + kfree(kvg); + ret = 0; + break; + } + + mutex_unlock(&kv->lock); + + kvm_vfio_group_put_external_user(vfio_group); + + return ret; + } + + return -ENXIO; +} + +static int kvm_vfio_set_attr(struct kvm_device *dev, + struct kvm_device_attr *attr) +{ + switch (attr->group) { + case KVM_DEV_VFIO_GROUP: + return kvm_vfio_set_group(dev, attr->attr, attr->addr); + } + + return -ENXIO; +} + +static int kvm_vfio_has_attr(struct kvm_device *dev, + struct kvm_device_attr *attr) +{ + switch (attr->group) { + case KVM_DEV_VFIO_GROUP: + switch (attr->attr) { + case KVM_DEV_VFIO_GROUP_ADD: + case KVM_DEV_VFIO_GROUP_DEL: + return 0; + } + + break; + } + + return -ENXIO; +} + +static void kvm_vfio_destroy(struct kvm_device *dev) +{ + struct kvm_vfio *kv = dev->private; + struct kvm_vfio_group *kvg, *tmp; + + list_for_each_entry_safe(kvg, tmp, &kv->group_list, node) { + kvm_vfio_group_put_external_user(kvg->vfio_group); + list_del(&kvg->node); + kfree(kvg); + } + + kfree(kv); + kfree(dev); /* alloc by kvm_ioctl_create_device, free by .destroy */ +} + +static int kvm_vfio_create(struct kvm_device *dev, u32 type); + +static struct kvm_device_ops kvm_vfio_ops = { + .name = "kvm-vfio", + .create = kvm_vfio_create, + .destroy = kvm_vfio_destroy, + .set_attr = kvm_vfio_set_attr, + .has_attr = kvm_vfio_has_attr, +}; + +static int kvm_vfio_create(struct kvm_device *dev, u32 type) +{ + struct kvm_device *tmp; + struct kvm_vfio *kv; + + /* Only one VFIO "device" per VM */ + list_for_each_entry(tmp, &dev->kvm->devices, vm_node) + if (tmp->ops == &kvm_vfio_ops) + return -EBUSY; + + kv = kzalloc(sizeof(*kv), GFP_KERNEL); + if (!kv) + return -ENOMEM; + + INIT_LIST_HEAD(&kv->group_list); + mutex_init(&kv->lock); + + dev->private = kv; + + return 0; +} + +static int __init kvm_vfio_ops_init(void) +{ + return kvm_register_device_ops(&kvm_vfio_ops, KVM_DEV_TYPE_VFIO); +} +module_init(kvm_vfio_ops_init); |