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.c | 2035 | ||||
| -rw-r--r-- | virt/kvm/assigned-dev.c | 46 | ||||
| -rw-r--r-- | virt/kvm/async_pf.c | 60 | ||||
| -rw-r--r-- | virt/kvm/coalesced_mmio.c | 8 | ||||
| -rw-r--r-- | virt/kvm/eventfd.c | 150 | ||||
| -rw-r--r-- | virt/kvm/ioapic.c | 283 | ||||
| -rw-r--r-- | virt/kvm/ioapic.h | 24 | ||||
| -rw-r--r-- | virt/kvm/iommu.c | 42 | ||||
| -rw-r--r-- | virt/kvm/irq_comm.c | 219 | ||||
| -rw-r--r-- | virt/kvm/irqchip.c | 238 | ||||
| -rw-r--r-- | virt/kvm/kvm_main.c | 814 | ||||
| -rw-r--r-- | virt/kvm/vfio.c | 277 |
14 files changed, 3885 insertions, 639 deletions
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig index d01b24b72c6..13f2d19793e 100644 --- a/virt/kvm/Kconfig +++ b/virt/kvm/Kconfig @@ -6,6 +6,9 @@ config HAVE_KVM config HAVE_KVM_IRQCHIP bool +config HAVE_KVM_IRQ_ROUTING + bool + config HAVE_KVM_EVENTFD bool select EVENTFD @@ -19,8 +22,15 @@ 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 00000000000..22fa819a9b6 --- /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.c b/virt/kvm/arm/vgic.c new file mode 100644 index 00000000000..476d3bf540a --- /dev/null +++ b/virt/kvm/arm/vgic.c @@ -0,0 +1,2035 @@ +/* + * 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 + * - VGIC pending interrupts are stored on the vgic.irq_state 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) and indicate the 'wire' state. + * - 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_state & dist->irq_enable + * - SPI: dist->irq_state & dist->irq_enable & dist->irq_spi_target + * - irq_spi_target is a 'formatted' version of the GICD_ICFGR + * registers, stored on each vcpu. We only keep one bit of + * information per interrupt, making sure that only one vcpu can + * accept the interrupt. + * - 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_active 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_active. This allow the + * interrupt line to be sampled again. + */ + +#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 + +/* Physical address of vgic virtual cpu interface */ +static phys_addr_t vgic_vcpu_base; + +/* Virtual control interface base address */ +static void __iomem *vgic_vctrl_base; + +static struct device_node *vgic_node; + +#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_update_state(struct kvm *kvm); +static void vgic_kick_vcpus(struct kvm *kvm); +static void vgic_dispatch_sgi(struct kvm_vcpu *vcpu, u32 reg); +static u32 vgic_nr_lr; + +static unsigned int vgic_maint_irq; + +static u32 *vgic_bitmap_get_reg(struct vgic_bitmap *x, + int cpuid, u32 offset) +{ + offset >>= 2; + if (!offset) + return x->percpu[cpuid].reg; + else + return x->shared.reg + offset - 1; +} + +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->percpu[cpuid].reg_ul); + + return test_bit(irq - VGIC_NR_PRIVATE_IRQS, x->shared.reg_ul); +} + +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->percpu[cpuid].reg_ul; + } else { + reg = x->shared.reg_ul; + 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) +{ + if (unlikely(cpuid >= VGIC_MAX_CPUS)) + return NULL; + return x->percpu[cpuid].reg_ul; +} + +static unsigned long *vgic_bitmap_get_shared_map(struct vgic_bitmap *x) +{ + return x->shared.reg_ul; +} + +static u32 *vgic_bytemap_get_reg(struct vgic_bytemap *x, int cpuid, u32 offset) +{ + offset >>= 2; + BUG_ON(offset > (VGIC_NR_IRQS / 4)); + if (offset < 8) + return x->percpu[cpuid] + offset; + else + return x->shared + offset - 8; +} + +#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_active(struct kvm_vcpu *vcpu, int irq) +{ + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + + return vgic_bitmap_get_irq_val(&dist->irq_active, vcpu->vcpu_id, irq); +} + +static void vgic_irq_set_active(struct kvm_vcpu *vcpu, int irq) +{ + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + + vgic_bitmap_set_irq_val(&dist->irq_active, vcpu->vcpu_id, irq, 1); +} + +static void vgic_irq_clear_active(struct kvm_vcpu *vcpu, int irq) +{ + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + + vgic_bitmap_set_irq_val(&dist->irq_active, 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_state, vcpu->vcpu_id, irq); +} + +static void vgic_dist_irq_set(struct kvm_vcpu *vcpu, int irq) +{ + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + + vgic_bitmap_set_irq_val(&dist->irq_state, vcpu->vcpu_id, irq, 1); +} + +static void vgic_dist_irq_clear(struct kvm_vcpu *vcpu, int irq) +{ + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + + vgic_bitmap_set_irq_val(&dist->irq_state, 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 u32 mmio_data_read(struct kvm_exit_mmio *mmio, u32 mask) +{ + return *((u32 *)mmio->data) & mask; +} + +static void mmio_data_write(struct kvm_exit_mmio *mmio, u32 mask, u32 value) +{ + *((u32 *)mmio->data) = 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 |= (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 = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_state, + 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_pending_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_state, + vcpu->vcpu_id, offset); + vgic_reg_access(mmio, reg, offset, + ACCESS_READ_VALUE | ACCESS_WRITE_CLEARBIT); + if (mmio->is_write) { + 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; +} + +#define LR_CPUID(lr) \ + (((lr) & GICH_LR_PHYSID_CPUID) >> GICH_LR_PHYSID_CPUID_SHIFT) +#define LR_IRQID(lr) \ + ((lr) & GICH_LR_VIRTUALID) + +static void vgic_retire_lr(int lr_nr, int irq, struct vgic_cpu *vgic_cpu) +{ + clear_bit(lr_nr, vgic_cpu->lr_used); + vgic_cpu->vgic_lr[lr_nr] &= ~GICH_LR_STATE; + vgic_cpu->vgic_irq_lr_map[irq] = LR_EMPTY; +} + +/** + * 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, irq, source_cpu; + u32 *lr; + + for_each_set_bit(i, vgic_cpu->lr_used, vgic_cpu->nr_lr) { + lr = &vgic_cpu->vgic_lr[i]; + irq = LR_IRQID(*lr); + source_cpu = LR_CPUID(*lr); + + /* + * 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 & GICH_LR_STATE) == GICH_LR_ACTIVE_BIT) + 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(vcpu, irq); + if (irq < VGIC_NR_SGIS) + dist->irq_sgi_sources[vcpu_id][irq] |= 1 << source_cpu; + *lr &= ~GICH_LR_PENDING_BIT; + + /* + * 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 & GICH_LR_STATE)) + vgic_retire_lr(i, irq, vgic_cpu); + + /* 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) * 4; + 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)dist->irq_sgi_sources[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) * 4; + 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)); + if (set) { + if ((dist->irq_sgi_sources[vcpu_id][sgi] & mask) != mask) + updated = true; + dist->irq_sgi_sources[vcpu_id][sgi] |= mask; + } else { + if (dist->irq_sgi_sources[vcpu_id][sgi] & mask) + updated = true; + dist->irq_sgi_sources[vcpu_id][sgi] &= ~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; + 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, + .handle_mmio = handle_mmio_misc, + }, + { + .base = GIC_DIST_IGROUP, + .len = VGIC_NR_IRQS / 8, + .handle_mmio = handle_mmio_raz_wi, + }, + { + .base = GIC_DIST_ENABLE_SET, + .len = VGIC_NR_IRQS / 8, + .handle_mmio = handle_mmio_set_enable_reg, + }, + { + .base = GIC_DIST_ENABLE_CLEAR, + .len = VGIC_NR_IRQS / 8, + .handle_mmio = handle_mmio_clear_enable_reg, + }, + { + .base = GIC_DIST_PENDING_SET, + .len = VGIC_NR_IRQS / 8, + .handle_mmio = handle_mmio_set_pending_reg, + }, + { + .base = GIC_DIST_PENDING_CLEAR, + .len = VGIC_NR_IRQS / 8, + .handle_mmio = handle_mmio_clear_pending_reg, + }, + { + .base = GIC_DIST_ACTIVE_SET, + .len = VGIC_NR_IRQS / 8, + .handle_mmio = handle_mmio_raz_wi, + }, + { + .base = GIC_DIST_ACTIVE_CLEAR, + .len = VGIC_NR_IRQS / 8, + .handle_mmio = handle_mmio_raz_wi, + }, + { + .base = GIC_DIST_PRI, + .len = VGIC_NR_IRQS, + .handle_mmio = handle_mmio_priority_reg, + }, + { + .base = GIC_DIST_TARGET, + .len = VGIC_NR_IRQS, + .handle_mmio = handle_mmio_target_reg, + }, + { + .base = GIC_DIST_CONFIG, + .len = VGIC_NR_IRQS / 4, + .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; +} + +/** + * 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; + updated_state = range->handle_mmio(vcpu, mmio, offset); + 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 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(vcpu, sgi); + dist->irq_sgi_sources[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 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 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_state, 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_state); + enabled = vgic_bitmap_get_shared_map(&dist->irq_enabled); + bitmap_and(pend_shared, pending, enabled, VGIC_NR_SHARED_IRQS); + bitmap_and(pend_shared, pend_shared, + vgic_bitmap_get_shared_map(&dist->irq_spi_target[vcpu_id]), + VGIC_NR_SHARED_IRQS); + + pending_private = find_first_bit(pend_percpu, VGIC_NR_PRIVATE_IRQS); + pending_shared = find_first_bit(pend_shared, VGIC_NR_SHARED_IRQS); + return (pending_private < VGIC_NR_PRIVATE_IRQS || + pending_shared < VGIC_NR_SHARED_IRQS); +} + +/* + * 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); + } + } +} + +#define MK_LR_PEND(src, irq) \ + (GICH_LR_PENDING_BIT | ((src) << GICH_LR_PHYSID_CPUID_SHIFT) | (irq)) + +/* + * 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_cpu->nr_lr) { + int irq = vgic_cpu->vgic_lr[lr] & GICH_LR_VIRTUALID; + + if (!vgic_irq_is_enabled(vcpu, irq)) { + vgic_retire_lr(lr, irq, vgic_cpu); + if (vgic_irq_is_active(vcpu, irq)) + vgic_irq_clear_active(vcpu, 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; + int lr; + + /* Sanitize the input... */ + BUG_ON(sgi_source_id & ~7); + BUG_ON(sgi_source_id && irq >= VGIC_NR_SGIS); + BUG_ON(irq >= VGIC_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 && + (LR_CPUID(vgic_cpu->vgic_lr[lr]) == sgi_source_id)) { + kvm_debug("LR%d piggyback for IRQ%d %x\n", + lr, irq, vgic_cpu->vgic_lr[lr]); + BUG_ON(!test_bit(lr, vgic_cpu->lr_used)); + vgic_cpu->vgic_lr[lr] |= GICH_LR_PENDING_BIT; + return true; + } + + /* Try to use another LR for this interrupt */ + lr = find_first_zero_bit((unsigned long *)vgic_cpu->lr_used, + vgic_cpu->nr_lr); + if (lr >= vgic_cpu->nr_lr) + return false; + + kvm_debug("LR%d allocated for IRQ%d %x\n", lr, irq, sgi_source_id); + vgic_cpu->vgic_lr[lr] = MK_LR_PEND(sgi_source_id, irq); + vgic_cpu->vgic_irq_lr_map[irq] = lr; + set_bit(lr, vgic_cpu->lr_used); + + if (!vgic_irq_is_edge(vcpu, irq)) + vgic_cpu->vgic_lr[lr] |= GICH_LR_EOI; + + 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 = dist->irq_sgi_sources[vcpu_id][irq]; + + for_each_set_bit(c, &sources, VGIC_MAX_CPUS) { + if (vgic_queue_irq(vcpu, c, irq)) + clear_bit(c, &sources); + } + + dist->irq_sgi_sources[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(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_irq_is_active(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(vcpu, irq); + vgic_cpu_irq_clear(vcpu, irq); + } else { + vgic_irq_set_active(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) { + if (!vgic_queue_hwirq(vcpu, i + VGIC_NR_PRIVATE_IRQS)) + overflow = 1; + } + +epilog: + if (overflow) { + vgic_cpu->vgic_hcr |= GICH_HCR_UIE; + } else { + vgic_cpu->vgic_hcr &= ~GICH_HCR_UIE; + /* + * 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) +{ + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + bool level_pending = false; + + kvm_debug("MISR = %08x\n", vgic_cpu->vgic_misr); + + if (vgic_cpu->vgic_misr & GICH_MISR_EOI) { + /* + * Some level interrupts have been EOIed. Clear their + * active bit. + */ + int lr, irq; + + for_each_set_bit(lr, (unsigned long *)vgic_cpu->vgic_eisr, + vgic_cpu->nr_lr) { + irq = vgic_cpu->vgic_lr[lr] & GICH_LR_VIRTUALID; + + vgic_irq_clear_active(vcpu, irq); + vgic_cpu->vgic_lr[lr] &= ~GICH_LR_EOI; + + /* Any additional pending interrupt? */ + if (vgic_dist_irq_is_pending(vcpu, irq)) { + vgic_cpu_irq_set(vcpu, irq); + level_pending = true; + } else { + vgic_cpu_irq_clear(vcpu, irq); + } + + /* + * Despite being EOIed, the LR may not have + * been marked as empty. + */ + set_bit(lr, (unsigned long *)vgic_cpu->vgic_elrsr); + vgic_cpu->vgic_lr[lr] &= ~GICH_LR_ACTIVE_BIT; + } + } + + if (vgic_cpu->vgic_misr & GICH_MISR_U) + vgic_cpu->vgic_hcr &= ~GICH_HCR_UIE; + + 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; + int lr, pending; + bool level_pending; + + level_pending = vgic_process_maintenance(vcpu); + + /* Clear mappings for empty LRs */ + for_each_set_bit(lr, (unsigned long *)vgic_cpu->vgic_elrsr, + vgic_cpu->nr_lr) { + int irq; + + if (!test_and_clear_bit(lr, vgic_cpu->lr_used)) + continue; + + irq = vgic_cpu->vgic_lr[lr] & GICH_LR_VIRTUALID; + + BUG_ON(irq >= VGIC_NR_IRQS); + vgic_cpu->vgic_irq_lr_map[irq] = LR_EMPTY; + } + + /* Check if we still have something up our sleeve... */ + pending = find_first_zero_bit((unsigned long *)vgic_cpu->vgic_elrsr, + vgic_cpu->nr_lr); + if (level_pending || pending < vgic_cpu->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 is_edge = vgic_irq_is_edge(vcpu, irq); + int state = vgic_dist_irq_is_pending(vcpu, irq); + + /* + * Only inject an interrupt if: + * - edge triggered and we have a rising edge + * - level triggered and we change level + */ + if (is_edge) + return level > state; + else + return level != state; +} + +static bool vgic_update_irq_state(struct kvm *kvm, int cpuid, + unsigned int irq_num, bool level) +{ + struct vgic_dist *dist = &kvm->arch.vgic; + struct kvm_vcpu *vcpu; + int is_edge, is_level; + int enabled; + bool ret = true; + + spin_lock(&dist->lock); + + vcpu = kvm_get_vcpu(kvm, cpuid); + is_edge = vgic_irq_is_edge(vcpu, irq_num); + is_level = !is_edge; + + 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) + vgic_dist_irq_set(vcpu, irq_num); + else + vgic_dist_irq_clear(vcpu, irq_num); + + enabled = vgic_irq_is_enabled(vcpu, irq_num); + + if (!enabled) { + ret = false; + goto out; + } + + if (is_level && vgic_irq_is_active(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 (vgic_update_irq_state(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; +} + +/** + * 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 + */ +int 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; + + if (vcpu->vcpu_id >= VGIC_MAX_CPUS) + return -EBUSY; + + for (i = 0; i < VGIC_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; + } + + /* + * By forcing VMCR to zero, the GIC will restore the binary + * points to their reset values. Anything else resets to zero + * anyway. + */ + vgic_cpu->vgic_vmcr = 0; + + vgic_cpu->nr_lr = vgic_nr_lr; + vgic_cpu->vgic_hcr = GICH_HCR_EN; /* Get the show on the road... */ + + return 0; +} + +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, +}; + +int kvm_vgic_hyp_init(void) +{ + int ret; + struct resource vctrl_res; + struct resource vcpu_res; + + vgic_node = of_find_compatible_node(NULL, NULL, "arm,cortex-a15-gic"); + if (!vgic_node) { + kvm_err("error: no compatible vgic node in DT\n"); + return -ENODEV; + } + + 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 = 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); + goto out; + } + + ret = __register_cpu_notifier(&vgic_cpu_nb); + if (ret) { + kvm_err("Cannot register vgic CPU notifier\n"); + goto out_free_irq; + } + + ret = of_address_to_resource(vgic_node, 2, &vctrl_res); + if (ret) { + kvm_err("Cannot obtain VCTRL resource\n"); + goto out_free_irq; + } + + vgic_vctrl_base = of_iomap(vgic_node, 2); + if (!vgic_vctrl_base) { + kvm_err("Cannot ioremap VCTRL\n"); + ret = -ENOMEM; + goto out_free_irq; + } + + 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 VCPU 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); + on_each_cpu(vgic_init_maintenance_interrupt, NULL, 1); + + goto out; + +out_unmap: + iounmap(vgic_vctrl_base); +out_free_irq: + free_percpu_irq(vgic_maint_irq, kvm_get_running_vcpus()); +out: + of_node_put(vgic_node); + 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) +{ + 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 = 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; + } + + for (i = VGIC_NR_PRIVATE_IRQS; i < VGIC_NR_IRQS; i += 4) + vgic_set_target_reg(kvm, 0, i); + + kvm->arch.vgic.ready = true; +out: + 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.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 bool 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) +{ + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + u32 reg, mask = 0, shift = 0; + bool updated = false; + + switch (offset & ~0x3) { + case GIC_CPU_CTRL: + mask = GICH_VMCR_CTRL_MASK; + shift = GICH_VMCR_CTRL_SHIFT; + break; + case GIC_CPU_PRIMASK: + mask = GICH_VMCR_PRIMASK_MASK; + shift = GICH_VMCR_PRIMASK_SHIFT; + break; + case GIC_CPU_BINPOINT: + mask = GICH_VMCR_BINPOINT_MASK; + shift = GICH_VMCR_BINPOINT_SHIFT; + break; + case GIC_CPU_ALIAS_BINPOINT: + mask = GICH_VMCR_ALIAS_BINPOINT_MASK; + shift = GICH_VMCR_ALIAS_BINPOINT_SHIFT; + break; + } + + if (!mmio->is_write) { + reg = (vgic_cpu->vgic_vmcr & mask) >> shift; + mmio_data_write(mmio, ~0, reg); + } else { + reg = mmio_data_read(mmio, ~0); + reg = (reg << shift) & mask; + if (reg != (vgic_cpu->vgic_vmcr & mask)) + updated = true; + vgic_cpu->vgic_vmcr &= ~mask; + vgic_cpu->vgic_vmcr |= reg; + } + 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); + + 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); + } + + } + + 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; + } + + } + + 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); + } + 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); +} + +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, +}; diff --git a/virt/kvm/assigned-dev.c b/virt/kvm/assigned-dev.c index 3642239252b..bf06577fea5 100644 --- a/virt/kvm/assigned-dev.c +++ b/virt/kvm/assigned-dev.c @@ -80,11 +80,12 @@ kvm_assigned_dev_raise_guest_irq(struct kvm_assigned_dev_kernel *assigned_dev, spin_lock(&assigned_dev->intx_mask_lock); if (!(assigned_dev->flags & KVM_DEV_ASSIGN_MASK_INTX)) kvm_set_irq(assigned_dev->kvm, - assigned_dev->irq_source_id, vector, 1); + assigned_dev->irq_source_id, vector, 1, + false); spin_unlock(&assigned_dev->intx_mask_lock); } else kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id, - vector, 1); + vector, 1, false); } static irqreturn_t kvm_assigned_dev_thread_intx(int irq, void *dev_id) @@ -165,7 +166,7 @@ static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian) container_of(kian, struct kvm_assigned_dev_kernel, ack_notifier); - kvm_set_irq(dev->kvm, dev->irq_source_id, dev->guest_irq, 0); + kvm_set_irq(dev->kvm, dev->irq_source_id, dev->guest_irq, 0, false); spin_lock(&dev->intx_mask_lock); @@ -188,7 +189,7 @@ static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian) if (reassert) kvm_set_irq(dev->kvm, dev->irq_source_id, - dev->guest_irq, 1); + dev->guest_irq, 1, false); } spin_unlock(&dev->intx_mask_lock); @@ -202,7 +203,7 @@ static void deassign_guest_irq(struct kvm *kvm, &assigned_dev->ack_notifier); kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id, - assigned_dev->guest_irq, 0); + assigned_dev->guest_irq, 0, false); if (assigned_dev->irq_source_id != -1) kvm_free_irq_source_id(kvm, assigned_dev->irq_source_id); @@ -394,7 +395,8 @@ static int assigned_device_enable_host_msix(struct kvm *kvm, if (dev->entries_nr == 0) return r; - r = pci_enable_msix(dev->dev, dev->host_msix_entries, dev->entries_nr); + r = pci_enable_msix_exact(dev->dev, + dev->host_msix_entries, dev->entries_nr); if (r) return r; @@ -901,7 +903,7 @@ static int kvm_vm_ioctl_set_pci_irq_mask(struct kvm *kvm, if (match->irq_requested_type & KVM_DEV_IRQ_GUEST_INTX) { if (assigned_dev->flags & KVM_DEV_ASSIGN_MASK_INTX) { kvm_set_irq(match->kvm, match->irq_source_id, - match->guest_irq, 0); + match->guest_irq, 0, false); /* * Masking at hardware-level is performed on demand, * i.e. when an IRQ actually arrives at the host. @@ -982,36 +984,6 @@ long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl, goto out; break; } -#ifdef KVM_CAP_IRQ_ROUTING - case KVM_SET_GSI_ROUTING: { - struct kvm_irq_routing routing; - struct kvm_irq_routing __user *urouting; - struct kvm_irq_routing_entry *entries; - - r = -EFAULT; - if (copy_from_user(&routing, argp, sizeof(routing))) - goto out; - r = -EINVAL; - if (routing.nr >= KVM_MAX_IRQ_ROUTES) - goto out; - if (routing.flags) - goto out; - r = -ENOMEM; - entries = vmalloc(routing.nr * sizeof(*entries)); - if (!entries) - goto out; - r = -EFAULT; - urouting = argp; - if (copy_from_user(entries, urouting->entries, - routing.nr * sizeof(*entries))) - goto out_free_irq_routing; - r = kvm_set_irq_routing(kvm, entries, routing.nr, - routing.flags); - out_free_irq_routing: - vfree(entries); - break; - } -#endif /* KVM_CAP_IRQ_ROUTING */ #ifdef __KVM_HAVE_MSIX case KVM_ASSIGN_SET_MSIX_NR: { struct kvm_assigned_msix_nr entry_nr; diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c index ea475cd0351..d6a3d0993d8 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/coalesced_mmio.c b/virt/kvm/coalesced_mmio.c index 88b2fe3ddf4..00d86427af0 100644 --- a/virt/kvm/coalesced_mmio.c +++ b/virt/kvm/coalesced_mmio.c @@ -154,17 +154,13 @@ int kvm_vm_ioctl_register_coalesced_mmio(struct kvm *kvm, list_add_tail(&dev->list, &kvm->coalesced_zones); mutex_unlock(&kvm->slots_lock); - return ret; + return 0; out_free_dev: mutex_unlock(&kvm->slots_lock); - kfree(dev); - if (dev == NULL) - return -ENXIO; - - return 0; + return ret; } int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm, diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index b6eea5cc7b3..20c3af7692c 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -31,11 +31,12 @@ #include <linux/list.h> #include <linux/eventfd.h> #include <linux/kernel.h> +#include <linux/srcu.h> #include <linux/slab.h> #include "iodev.h" -#ifdef __KVM_HAVE_IOAPIC +#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING /* * -------------------------------------------------------------------- * irqfd: Allows an fd to be used to inject an interrupt to the guest @@ -100,11 +101,13 @@ irqfd_inject(struct work_struct *work) struct kvm *kvm = irqfd->kvm; if (!irqfd->resampler) { - kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 1); - kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 0); + kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 1, + false); + kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 0, + false); } else kvm_set_irq(kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID, - irqfd->gsi, 1); + irqfd->gsi, 1, false); } /* @@ -116,19 +119,22 @@ 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, - resampler->notifier.gsi, 0); + 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 @@ -140,13 +146,13 @@ 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); kvm_unregister_irq_ack_notifier(kvm, &resampler->notifier); kvm_set_irq(kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID, - resampler->notifier.gsi, 0); + resampler->notifier.gsi, 0, false); kfree(resampler); } @@ -219,16 +225,18 @@ irqfd_wakeup(wait_queue_t *wait, unsigned mode, int sync, void *key) unsigned long flags = (unsigned long)key; struct kvm_kernel_irq_routing_entry *irq; struct kvm *kvm = irqfd->kvm; + int idx; if (flags & POLLIN) { - rcu_read_lock(); - irq = rcu_dereference(irqfd->irq_entry); + idx = srcu_read_lock(&kvm->irq_srcu); + irq = srcu_dereference(irqfd->irq_entry, &kvm->irq_srcu); /* An event has been signaled, inject an interrupt */ if (irq) - kvm_set_msi(irq, kvm, KVM_USERSPACE_IRQ_SOURCE_ID, 1); + 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) { @@ -268,14 +276,13 @@ static void irqfd_update(struct kvm *kvm, struct _irqfd *irqfd, struct kvm_irq_routing_table *irq_rt) { struct kvm_kernel_irq_routing_entry *e; - struct hlist_node *n; if (irqfd->gsi >= irq_rt->nr_rt_entries) { rcu_assign_pointer(irqfd->irq_entry, NULL); return; } - hlist_for_each_entry(e, n, &irq_rt->map[irqfd->gsi], link) { + hlist_for_each_entry(e, &irq_rt->map[irqfd->gsi], link) { /* Only fast-path MSI. */ if (e->type == KVM_IRQ_ROUTING_MSI) rcu_assign_pointer(irqfd->irq_entry, e); @@ -289,7 +296,7 @@ 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 fd f; struct eventfd_ctx *eventfd = NULL, *resamplefd = NULL; int ret; unsigned int events; @@ -304,13 +311,13 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args) INIT_WORK(&irqfd->inject, irqfd_inject); INIT_WORK(&irqfd->shutdown, irqfd_shutdown); - file = eventfd_fget(args->fd); - if (IS_ERR(file)) { - ret = PTR_ERR(file); - goto fail; + f = fdget(args->fd); + if (!f.file) { + ret = -EBADF; + goto out; } - eventfd = eventfd_ctx_fileget(file); + eventfd = eventfd_ctx_fileget(f.file); if (IS_ERR(eventfd)) { ret = PTR_ERR(eventfd); goto fail; @@ -361,7 +368,7 @@ 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); } @@ -389,24 +396,24 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args) lockdep_is_held(&kvm->irqfds.lock)); irqfd_update(kvm, irqfd, irq_rt); - events = file->f_op->poll(file, &irqfd->pt); - list_add_tail(&irqfd->list, &kvm->irqfds.items); + spin_unlock_irq(&kvm->irqfds.lock); + /* * Check if there was an event already pending on the eventfd * before we registered, and trigger it as if we didn't miss it. */ + events = f.file->f_op->poll(f.file, &irqfd->pt); + if (events & POLLIN) schedule_work(&irqfd->inject); - spin_unlock_irq(&kvm->irqfds.lock); - /* * do not drop the file until the irqfd is fully initialized, otherwise * we might race against the POLLHUP */ - fput(file); + fdput(f); return 0; @@ -420,9 +427,9 @@ fail: if (eventfd && !IS_ERR(eventfd)) eventfd_ctx_put(eventfd); - if (!IS_ERR(file)) - fput(file); + fdput(f); +out: kfree(irqfd); return ret; } @@ -431,7 +438,7 @@ fail: void kvm_eventfd_init(struct kvm *kvm) { -#ifdef __KVM_HAVE_IOAPIC +#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING spin_lock_init(&kvm->irqfds.lock); INIT_LIST_HEAD(&kvm->irqfds.items); INIT_LIST_HEAD(&kvm->irqfds.resampler_list); @@ -440,7 +447,7 @@ kvm_eventfd_init(struct kvm *kvm) INIT_LIST_HEAD(&kvm->ioeventfds); } -#ifdef __KVM_HAVE_IOAPIC +#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING /* * shutdown any irqfd's that match fd+gsi */ @@ -463,7 +470,7 @@ kvm_irqfd_deassign(struct kvm *kvm, struct kvm_irqfd *args) * 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 + * It is paired with synchronize_srcu done by caller * of that function. */ rcu_assign_pointer(irqfd->irq_entry, NULL); @@ -522,7 +529,7 @@ kvm_irqfd_release(struct kvm *kvm) /* * Change irq_routing and irqfd. - * Caller must invoke synchronize_rcu afterwards. + * Caller must invoke synchronize_srcu(&kvm->irq_srcu) afterwards. */ void kvm_irq_routing_update(struct kvm *kvm, struct kvm_irq_routing_table *irq_rt) @@ -544,7 +551,7 @@ void kvm_irq_routing_update(struct kvm *kvm, * aggregated from all vm* instances. We need our own isolated single-thread * queue to prevent deadlock against flushing the normal work-queue. */ -static int __init irqfd_module_init(void) +int kvm_irqfd_init(void) { irqfd_cleanup_wq = create_singlethread_workqueue("kvm-irqfd-cleanup"); if (!irqfd_cleanup_wq) @@ -553,13 +560,10 @@ static int __init irqfd_module_init(void) return 0; } -static void __exit irqfd_module_exit(void) +void kvm_irqfd_exit(void) { destroy_workqueue(irqfd_cleanup_wq); } - -module_init(irqfd_module_init); -module_exit(irqfd_module_exit); #endif /* @@ -578,6 +582,7 @@ struct _ioeventfd { struct eventfd_ctx *eventfd; u64 datamatch; struct kvm_io_device dev; + u8 bus_idx; bool wildcard; }; @@ -600,7 +605,15 @@ ioeventfd_in_range(struct _ioeventfd *p, gpa_t addr, int len, const void *val) { u64 _val; - if (!(addr == p->addr && len == p->length)) + if (addr != p->addr) + /* address must be precise for a hit */ + return false; + + if (!p->length) + /* length = 0 means only look at the address, so always a hit */ + return true; + + if (len != p->length) /* address-range must be precise for a hit */ return false; @@ -670,25 +683,38 @@ ioeventfd_check_collision(struct kvm *kvm, struct _ioeventfd *p) struct _ioeventfd *_p; list_for_each_entry(_p, &kvm->ioeventfds, list) - if (_p->addr == p->addr && _p->length == p->length && - (_p->wildcard || p->wildcard || - _p->datamatch == p->datamatch)) + if (_p->bus_idx == p->bus_idx && + _p->addr == p->addr && + (!_p->length || !p->length || + (_p->length == p->length && + (_p->wildcard || p->wildcard || + _p->datamatch == p->datamatch)))) return true; return false; } +static enum kvm_bus ioeventfd_bus_from_flags(__u32 flags) +{ + if (flags & KVM_IOEVENTFD_FLAG_PIO) + return KVM_PIO_BUS; + if (flags & KVM_IOEVENTFD_FLAG_VIRTIO_CCW_NOTIFY) + return KVM_VIRTIO_CCW_NOTIFY_BUS; + return KVM_MMIO_BUS; +} + static int kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) { - int pio = args->flags & KVM_IOEVENTFD_FLAG_PIO; - enum kvm_bus bus_idx = pio ? KVM_PIO_BUS : KVM_MMIO_BUS; + enum kvm_bus bus_idx; struct _ioeventfd *p; struct eventfd_ctx *eventfd; int ret; - /* must be natural-word sized */ + bus_idx = ioeventfd_bus_from_flags(args->flags); + /* must be natural-word sized, or 0 to ignore length */ switch (args->len) { + case 0: case 1: case 2: case 4: @@ -706,6 +732,12 @@ kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) if (args->flags & ~KVM_IOEVENTFD_VALID_FLAG_MASK) return -EINVAL; + /* ioeventfd with no length can't be combined with DATAMATCH */ + if (!args->len && + args->flags & (KVM_IOEVENTFD_FLAG_PIO | + KVM_IOEVENTFD_FLAG_DATAMATCH)) + return -EINVAL; + eventfd = eventfd_ctx_fdget(args->fd); if (IS_ERR(eventfd)) return PTR_ERR(eventfd); @@ -718,6 +750,7 @@ kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) INIT_LIST_HEAD(&p->list); p->addr = args->addr; + p->bus_idx = bus_idx; p->length = args->len; p->eventfd = eventfd; @@ -742,12 +775,25 @@ kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) if (ret < 0) goto unlock_fail; + /* When length is ignored, MMIO is also put on a separate bus, for + * faster lookups. + */ + if (!args->len && !(args->flags & KVM_IOEVENTFD_FLAG_PIO)) { + ret = kvm_io_bus_register_dev(kvm, KVM_FAST_MMIO_BUS, + p->addr, 0, &p->dev); + if (ret < 0) + goto register_fail; + } + + kvm->buses[bus_idx]->ioeventfd_count++; list_add_tail(&p->list, &kvm->ioeventfds); mutex_unlock(&kvm->slots_lock); return 0; +register_fail: + kvm_io_bus_unregister_dev(kvm, bus_idx, &p->dev); unlock_fail: mutex_unlock(&kvm->slots_lock); @@ -761,12 +807,12 @@ fail: static int kvm_deassign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) { - int pio = args->flags & KVM_IOEVENTFD_FLAG_PIO; - enum kvm_bus bus_idx = pio ? KVM_PIO_BUS : KVM_MMIO_BUS; + enum kvm_bus bus_idx; struct _ioeventfd *p, *tmp; struct eventfd_ctx *eventfd; int ret = -ENOENT; + bus_idx = ioeventfd_bus_from_flags(args->flags); eventfd = eventfd_ctx_fdget(args->fd); if (IS_ERR(eventfd)) return PTR_ERR(eventfd); @@ -776,7 +822,8 @@ kvm_deassign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) list_for_each_entry_safe(p, tmp, &kvm->ioeventfds, list) { bool wildcard = !(args->flags & KVM_IOEVENTFD_FLAG_DATAMATCH); - if (p->eventfd != eventfd || + if (p->bus_idx != bus_idx || + p->eventfd != eventfd || p->addr != args->addr || p->length != args->len || p->wildcard != wildcard) @@ -786,6 +833,11 @@ kvm_deassign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) continue; kvm_io_bus_unregister_dev(kvm, bus_idx, &p->dev); + if (!p->length) { + kvm_io_bus_unregister_dev(kvm, KVM_FAST_MMIO_BUS, + &p->dev); + } + kvm->buses[bus_idx]->ioeventfd_count--; ioeventfd_release(p); ret = 0; break; diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c index cfb7e4d52dc..2458a1dc2ba 100644 --- a/virt/kvm/ioapic.c +++ b/virt/kvm/ioapic.c @@ -35,6 +35,7 @@ #include <linux/hrtimer.h> #include <linux/io.h> #include <linux/slab.h> +#include <linux/export.h> #include <asm/processor.h> #include <asm/page.h> #include <asm/current.h> @@ -49,7 +50,8 @@ #else #define ioapic_debug(fmt, arg...) #endif -static int ioapic_deliver(struct kvm_ioapic *vioapic, int irq); +static int ioapic_service(struct kvm_ioapic *vioapic, int irq, + bool line_status); static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic, unsigned long addr, @@ -73,9 +75,12 @@ static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic, u32 redir_index = (ioapic->ioregsel - 0x10) >> 1; u64 redir_content; - ASSERT(redir_index < IOAPIC_NUM_PINS); + if (redir_index < IOAPIC_NUM_PINS) + redir_content = + ioapic->redirtbl[redir_index].bits; + else + redir_content = ~0ULL; - redir_content = ioapic->redirtbl[redir_index].bits; result = (ioapic->ioregsel & 0x1) ? (redir_content >> 32) & 0xffffffff : redir_content & 0xffffffff; @@ -86,22 +91,146 @@ static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic, return result; } -static int ioapic_service(struct kvm_ioapic *ioapic, unsigned int idx) +static void rtc_irq_eoi_tracking_reset(struct kvm_ioapic *ioapic) { - union kvm_ioapic_redirect_entry *pent; - int injected = -1; + ioapic->rtc_status.pending_eoi = 0; + bitmap_zero(ioapic->rtc_status.dest_map, KVM_MAX_VCPUS); +} + +static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic); + +static void rtc_status_pending_eoi_check_valid(struct kvm_ioapic *ioapic) +{ + if (WARN_ON(ioapic->rtc_status.pending_eoi < 0)) + kvm_rtc_eoi_tracking_restore_all(ioapic); +} + +static void __rtc_irq_eoi_tracking_restore_one(struct kvm_vcpu *vcpu) +{ + bool new_val, old_val; + struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic; + union kvm_ioapic_redirect_entry *e; + + e = &ioapic->redirtbl[RTC_GSI]; + if (!kvm_apic_match_dest(vcpu, NULL, 0, e->fields.dest_id, + e->fields.dest_mode)) + return; + + new_val = kvm_apic_pending_eoi(vcpu, e->fields.vector); + old_val = test_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map); + + if (new_val == old_val) + return; + + if (new_val) { + __set_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map); + ioapic->rtc_status.pending_eoi++; + } else { + __clear_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map); + ioapic->rtc_status.pending_eoi--; + rtc_status_pending_eoi_check_valid(ioapic); + } +} + +void kvm_rtc_eoi_tracking_restore_one(struct kvm_vcpu *vcpu) +{ + struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic; + + spin_lock(&ioapic->lock); + __rtc_irq_eoi_tracking_restore_one(vcpu); + spin_unlock(&ioapic->lock); +} + +static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic) +{ + struct kvm_vcpu *vcpu; + int i; + + if (RTC_GSI >= IOAPIC_NUM_PINS) + return; + + rtc_irq_eoi_tracking_reset(ioapic); + kvm_for_each_vcpu(i, vcpu, ioapic->kvm) + __rtc_irq_eoi_tracking_restore_one(vcpu); +} + +static void rtc_irq_eoi(struct kvm_ioapic *ioapic, struct kvm_vcpu *vcpu) +{ + if (test_and_clear_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map)) { + --ioapic->rtc_status.pending_eoi; + rtc_status_pending_eoi_check_valid(ioapic); + } +} + +static bool rtc_irq_check_coalesced(struct kvm_ioapic *ioapic) +{ + if (ioapic->rtc_status.pending_eoi > 0) + return true; /* coalesced */ + + return false; +} + +static int ioapic_set_irq(struct kvm_ioapic *ioapic, unsigned int irq, + int irq_level, bool line_status) +{ + union kvm_ioapic_redirect_entry entry; + u32 mask = 1 << irq; + u32 old_irr; + int edge, ret; + + entry = ioapic->redirtbl[irq]; + edge = (entry.fields.trig_mode == IOAPIC_EDGE_TRIG); - pent = &ioapic->redirtbl[idx]; + if (!irq_level) { + ioapic->irr &= ~mask; + ret = 1; + goto out; + } - if (!pent->fields.mask) { - injected = ioapic_deliver(ioapic, idx); - if (injected && pent->fields.trig_mode == IOAPIC_LEVEL_TRIG) - pent->fields.remote_irr = 1; + /* + * Return 0 for coalesced interrupts; for edge-triggered interrupts, + * this only happens if a previous edge has not been delivered due + * do masking. For level interrupts, the remote_irr field tells + * us if the interrupt is waiting for an EOI. + * + * RTC is special: it is edge-triggered, but userspace likes to know + * if it has been already ack-ed via EOI because coalesced RTC + * interrupts lead to time drift in Windows guests. So we track + * EOI manually for the RTC interrupt. + */ + if (irq == RTC_GSI && line_status && + rtc_irq_check_coalesced(ioapic)) { + ret = 0; + goto out; } - return injected; + old_irr = ioapic->irr; + ioapic->irr |= mask; + if ((edge && old_irr == ioapic->irr) || + (!edge && entry.fields.remote_irr)) { + ret = 0; + goto out; + } + + ret = ioapic_service(ioapic, irq, line_status); + +out: + trace_kvm_ioapic_set_irq(entry.bits, irq, ret == 0); + return ret; +} + +static void kvm_ioapic_inject_all(struct kvm_ioapic *ioapic, unsigned long irr) +{ + u32 idx; + + rtc_irq_eoi_tracking_reset(ioapic); + for_each_set_bit(idx, &irr, IOAPIC_NUM_PINS) + ioapic_set_irq(ioapic, idx, 1, true); + + kvm_rtc_eoi_tracking_restore_all(ioapic); } + static void update_handled_vectors(struct kvm_ioapic *ioapic) { DECLARE_BITMAP(handled_vectors, 256); @@ -115,6 +244,49 @@ static void update_handled_vectors(struct kvm_ioapic *ioapic) smp_wmb(); } +void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap, + u32 *tmr) +{ + struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic; + union kvm_ioapic_redirect_entry *e; + int index; + + spin_lock(&ioapic->lock); + for (index = 0; index < IOAPIC_NUM_PINS; index++) { + e = &ioapic->redirtbl[index]; + if (!e->fields.mask && + (e->fields.trig_mode == IOAPIC_LEVEL_TRIG || + kvm_irq_has_notifier(ioapic->kvm, KVM_IRQCHIP_IOAPIC, + index) || index == RTC_GSI)) { + if (kvm_apic_match_dest(vcpu, NULL, 0, + e->fields.dest_id, e->fields.dest_mode)) { + __set_bit(e->fields.vector, + (unsigned long *)eoi_exit_bitmap); + if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG) + __set_bit(e->fields.vector, + (unsigned long *)tmr); + } + } + } + spin_unlock(&ioapic->lock); +} + +#ifdef CONFIG_X86 +void kvm_vcpu_request_scan_ioapic(struct kvm *kvm) +{ + struct kvm_ioapic *ioapic = kvm->arch.vioapic; + + if (!ioapic) + return; + kvm_make_scan_ioapic_request(kvm); +} +#else +void kvm_vcpu_request_scan_ioapic(struct kvm *kvm) +{ + return; +} +#endif + static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) { unsigned index; @@ -155,15 +327,20 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) kvm_fire_mask_notifiers(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index, mask_after); if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG && ioapic->irr & (1 << index)) - ioapic_service(ioapic, index); + ioapic_service(ioapic, index, false); + kvm_vcpu_request_scan_ioapic(ioapic->kvm); break; } } -static int ioapic_deliver(struct kvm_ioapic *ioapic, int irq) +static int ioapic_service(struct kvm_ioapic *ioapic, int irq, bool line_status) { union kvm_ioapic_redirect_entry *entry = &ioapic->redirtbl[irq]; struct kvm_lapic_irq irqe; + int ret; + + if (entry->fields.mask) + return -1; ioapic_debug("dest=%x dest_mode=%x delivery_mode=%x " "vector=%x trig_mode=%x\n", @@ -179,47 +356,41 @@ static int ioapic_deliver(struct kvm_ioapic *ioapic, int irq) irqe.level = 1; irqe.shorthand = 0; -#ifdef CONFIG_X86 - /* Always delivery PIT interrupt to vcpu 0 */ - if (irq == 0) { - irqe.dest_mode = 0; /* Physical mode. */ - /* need to read apic_id from apic regiest since - * it can be rewritten */ - irqe.dest_id = ioapic->kvm->bsp_vcpu_id; - } -#endif - return kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe); + if (irqe.trig_mode == IOAPIC_EDGE_TRIG) + ioapic->irr &= ~(1 << irq); + + if (irq == RTC_GSI && line_status) { + /* + * pending_eoi cannot ever become negative (see + * rtc_status_pending_eoi_check_valid) and the caller + * ensures that it is only called if it is >= zero, namely + * if rtc_irq_check_coalesced returns false). + */ + BUG_ON(ioapic->rtc_status.pending_eoi != 0); + ret = kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe, + ioapic->rtc_status.dest_map); + ioapic->rtc_status.pending_eoi = (ret < 0 ? 0 : ret); + } else + ret = kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe, NULL); + + if (ret && irqe.trig_mode == IOAPIC_LEVEL_TRIG) + entry->fields.remote_irr = 1; + + return ret; } int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id, - int level) + int level, bool line_status) { - u32 old_irr; - u32 mask = 1 << irq; - union kvm_ioapic_redirect_entry entry; int ret, irq_level; BUG_ON(irq < 0 || irq >= IOAPIC_NUM_PINS); spin_lock(&ioapic->lock); - old_irr = ioapic->irr; irq_level = __kvm_irq_line_state(&ioapic->irq_states[irq], irq_source_id, level); - entry = ioapic->redirtbl[irq]; - irq_level ^= entry.fields.polarity; - if (!irq_level) { - ioapic->irr &= ~mask; - ret = 1; - } else { - int edge = (entry.fields.trig_mode == IOAPIC_EDGE_TRIG); - ioapic->irr |= mask; - if ((edge && old_irr != ioapic->irr) || - (!edge && !entry.fields.remote_irr)) - ret = ioapic_service(ioapic, irq); - else - ret = 0; /* report coalesced interrupt */ - } - trace_kvm_ioapic_set_irq(entry.bits, irq, ret == 0); + ret = ioapic_set_irq(ioapic, irq, irq_level, line_status); + spin_unlock(&ioapic->lock); return ret; @@ -235,8 +406,8 @@ void kvm_ioapic_clear_all(struct kvm_ioapic *ioapic, int irq_source_id) spin_unlock(&ioapic->lock); } -static void __kvm_ioapic_update_eoi(struct kvm_ioapic *ioapic, int vector, - int trigger_mode) +static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, + struct kvm_ioapic *ioapic, int vector, int trigger_mode) { int i; @@ -246,6 +417,8 @@ static void __kvm_ioapic_update_eoi(struct kvm_ioapic *ioapic, int vector, if (ent->fields.vector != vector) continue; + if (i == RTC_GSI) + rtc_irq_eoi(ioapic, vcpu); /* * We are dropping lock while calling ack notifiers because ack * notifier callbacks for assigned devices call into IOAPIC @@ -263,8 +436,8 @@ static void __kvm_ioapic_update_eoi(struct kvm_ioapic *ioapic, int vector, ASSERT(ent->fields.trig_mode == IOAPIC_LEVEL_TRIG); ent->fields.remote_irr = 0; - if (!ent->fields.mask && (ioapic->irr & (1 << i))) - ioapic_service(ioapic, i); + if (ioapic->irr & (1 << i)) + ioapic_service(ioapic, i, false); } } @@ -275,12 +448,12 @@ bool kvm_ioapic_handles_vector(struct kvm *kvm, int vector) return test_bit(vector, ioapic->handled_vectors); } -void kvm_ioapic_update_eoi(struct kvm *kvm, int vector, int trigger_mode) +void kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, int vector, int trigger_mode) { - struct kvm_ioapic *ioapic = kvm->arch.vioapic; + struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic; spin_lock(&ioapic->lock); - __kvm_ioapic_update_eoi(ioapic, vector, trigger_mode); + __kvm_ioapic_update_eoi(vcpu, ioapic, vector, trigger_mode); spin_unlock(&ioapic->lock); } @@ -378,7 +551,7 @@ static int ioapic_mmio_write(struct kvm_io_device *this, gpa_t addr, int len, break; #ifdef CONFIG_IA64 case IOAPIC_REG_EOI: - __kvm_ioapic_update_eoi(ioapic, data, IOAPIC_LEVEL_TRIG); + __kvm_ioapic_update_eoi(NULL, ioapic, data, IOAPIC_LEVEL_TRIG); break; #endif @@ -389,7 +562,7 @@ 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; @@ -399,6 +572,7 @@ void kvm_ioapic_reset(struct kvm_ioapic *ioapic) ioapic->ioregsel = 0; ioapic->irr = 0; ioapic->id = 0; + rtc_irq_eoi_tracking_reset(ioapic); update_handled_vectors(ioapic); } @@ -463,7 +637,10 @@ int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state) spin_lock(&ioapic->lock); memcpy(ioapic, state, sizeof(struct kvm_ioapic_state)); + ioapic->irr = 0; update_handled_vectors(ioapic); + kvm_vcpu_request_scan_ioapic(kvm); + kvm_ioapic_inject_all(ioapic, state->irr); spin_unlock(&ioapic->lock); return 0; } diff --git a/virt/kvm/ioapic.h b/virt/kvm/ioapic.h index a30abfe6ed1..90d43e95dcf 100644 --- a/virt/kvm/ioapic.h +++ b/virt/kvm/ioapic.h @@ -34,6 +34,17 @@ struct kvm_vcpu; #define IOAPIC_INIT 0x5 #define IOAPIC_EXTINT 0x7 +#ifdef CONFIG_X86 +#define RTC_GSI 8 +#else +#define RTC_GSI -1U +#endif + +struct rtc_status { + int pending_eoi; + DECLARE_BITMAP(dest_map, KVM_MAX_VCPUS); +}; + struct kvm_ioapic { u64 base_address; u32 ioregsel; @@ -47,6 +58,7 @@ struct kvm_ioapic { void (*ack_notifier)(void *opaque, int irq); spinlock_t lock; DECLARE_BITMAP(handled_vectors, 256); + struct rtc_status rtc_status; }; #ifdef DEBUG @@ -67,20 +79,24 @@ static inline struct kvm_ioapic *ioapic_irqchip(struct kvm *kvm) return kvm->arch.vioapic; } +void kvm_rtc_eoi_tracking_restore_one(struct kvm_vcpu *vcpu); int kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, int short_hand, int dest, int dest_mode); int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2); -void kvm_ioapic_update_eoi(struct kvm *kvm, int vector, int trigger_mode); +void kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, int vector, + int trigger_mode); bool kvm_ioapic_handles_vector(struct kvm *kvm, int vector); int kvm_ioapic_init(struct kvm *kvm); void kvm_ioapic_destroy(struct kvm *kvm); int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id, - int level); + 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); + struct kvm_lapic_irq *irq, unsigned long *dest_map); int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state); int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state); +void kvm_vcpu_request_scan_ioapic(struct kvm *kvm); +void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap, + u32 *tmr); #endif diff --git a/virt/kvm/iommu.c b/virt/kvm/iommu.c index 4a340cb2301..0df7d4b34df 100644 --- a/virt/kvm/iommu.c +++ b/virt/kvm/iommu.c @@ -76,8 +76,10 @@ int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot) gfn = slot->base_gfn; end_gfn = gfn + slot->npages; - flags = IOMMU_READ | IOMMU_WRITE; - if (kvm->arch.iommu_flags & KVM_IOMMU_CACHE_COHERENCY) + flags = IOMMU_READ; + if (!(slot->flags & KVM_MEM_READONLY)) + flags |= IOMMU_WRITE; + if (!kvm->arch.iommu_noncoherent) flags |= IOMMU_CACHE; @@ -101,6 +103,10 @@ int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot) while ((gfn << PAGE_SHIFT) & (page_size - 1)) page_size >>= 1; + /* Make sure hva is aligned to the page size we want to map */ + while (__gfn_to_hva_memslot(slot, gfn) & (page_size - 1)) + page_size >>= 1; + /* * Pin all pages we are about to map in memory. This is * important because we unmap and unpin in 4kb steps later. @@ -138,6 +144,9 @@ static int kvm_iommu_map_memslots(struct kvm *kvm) struct kvm_memslots *slots; struct kvm_memory_slot *memslot; + if (kvm->arch.iommu_noncoherent) + kvm_arch_register_noncoherent_dma(kvm); + idx = srcu_read_lock(&kvm->srcu); slots = kvm_memslots(kvm); @@ -156,7 +165,8 @@ int kvm_assign_device(struct kvm *kvm, { struct pci_dev *pdev = NULL; struct iommu_domain *domain = kvm->arch.iommu_domain; - int r, last_flags; + int r; + bool noncoherent; /* check if iommu exists and in use */ if (!domain) @@ -172,15 +182,13 @@ int kvm_assign_device(struct kvm *kvm, return r; } - last_flags = kvm->arch.iommu_flags; - if (iommu_domain_has_cap(kvm->arch.iommu_domain, - IOMMU_CAP_CACHE_COHERENCY)) - kvm->arch.iommu_flags |= KVM_IOMMU_CACHE_COHERENCY; + noncoherent = !iommu_domain_has_cap(kvm->arch.iommu_domain, + IOMMU_CAP_CACHE_COHERENCY); /* Check if need to update IOMMU page table for guest memory */ - if ((last_flags ^ kvm->arch.iommu_flags) == - KVM_IOMMU_CACHE_COHERENCY) { + if (noncoherent != kvm->arch.iommu_noncoherent) { kvm_iommu_unmap_memslots(kvm); + kvm->arch.iommu_noncoherent = noncoherent; r = kvm_iommu_map_memslots(kvm); if (r) goto out_unmap; @@ -188,11 +196,7 @@ 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: @@ -218,11 +222,7 @@ 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; } @@ -334,6 +334,9 @@ static int kvm_iommu_unmap_memslots(struct kvm *kvm) srcu_read_unlock(&kvm->srcu, idx); + if (kvm->arch.iommu_noncoherent) + kvm_arch_unregister_noncoherent_dma(kvm); + return 0; } @@ -348,6 +351,7 @@ int kvm_iommu_unmap_guest(struct kvm *kvm) mutex_lock(&kvm->slots_lock); kvm_iommu_unmap_memslots(kvm); kvm->arch.iommu_domain = NULL; + kvm->arch.iommu_noncoherent = false; mutex_unlock(&kvm->slots_lock); iommu_domain_free(domain); diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c index 656fa455e15..ced4a542a03 100644 --- a/virt/kvm/irq_comm.c +++ b/virt/kvm/irq_comm.c @@ -22,6 +22,7 @@ #include <linux/kvm_host.h> #include <linux/slab.h> +#include <linux/export.h> #include <trace/events/kvm.h> #include <asm/msidef.h> @@ -34,7 +35,8 @@ #include "ioapic.h" static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e, - struct kvm *kvm, int irq_source_id, int level) + struct kvm *kvm, int irq_source_id, int level, + bool line_status) { #ifdef CONFIG_X86 struct kvm_pic *pic = pic_irqchip(kvm); @@ -45,10 +47,12 @@ static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e, } static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e, - struct kvm *kvm, int irq_source_id, int level) + struct kvm *kvm, int irq_source_id, int level, + bool line_status) { struct kvm_ioapic *ioapic = kvm->arch.vioapic; - return kvm_ioapic_set_irq(ioapic, e->irqchip.pin, irq_source_id, level); + return kvm_ioapic_set_irq(ioapic, e->irqchip.pin, irq_source_id, level, + line_status); } inline static bool kvm_is_dm_lowest_prio(struct kvm_lapic_irq *irq) @@ -62,7 +66,7 @@ inline static bool kvm_is_dm_lowest_prio(struct kvm_lapic_irq *irq) } int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, - struct kvm_lapic_irq *irq) + struct kvm_lapic_irq *irq, unsigned long *dest_map) { int i, r = -1; struct kvm_vcpu *vcpu, *lowest = NULL; @@ -73,7 +77,7 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, irq->delivery_mode = APIC_DM_FIXED; } - if (kvm_irq_delivery_to_apic_fast(kvm, src, irq, &r)) + if (kvm_irq_delivery_to_apic_fast(kvm, src, irq, &r, dest_map)) return r; kvm_for_each_vcpu(i, vcpu, kvm) { @@ -87,7 +91,7 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, if (!kvm_is_dm_lowest_prio(irq)) { if (r < 0) r = 0; - r += kvm_apic_set_irq(vcpu, irq); + r += kvm_apic_set_irq(vcpu, irq, dest_map); } else if (kvm_lapic_enabled(vcpu)) { if (!lowest) lowest = vcpu; @@ -97,7 +101,7 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, } if (lowest) - r = kvm_apic_set_irq(lowest, irq); + r = kvm_apic_set_irq(lowest, irq, dest_map); return r; } @@ -120,7 +124,7 @@ static inline void kvm_set_msi_irq(struct kvm_kernel_irq_routing_entry *e, } int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, - struct kvm *kvm, int irq_source_id, int level) + struct kvm *kvm, int irq_source_id, int level, bool line_status) { struct kvm_lapic_irq irq; @@ -129,7 +133,7 @@ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, kvm_set_msi_irq(e, &irq); - return kvm_irq_delivery_to_apic(kvm, NULL, &irq); + return kvm_irq_delivery_to_apic(kvm, NULL, &irq, NULL); } @@ -141,64 +145,12 @@ static int kvm_set_msi_inatomic(struct kvm_kernel_irq_routing_entry *e, kvm_set_msi_irq(e, &irq); - if (kvm_irq_delivery_to_apic_fast(kvm, NULL, &irq, &r)) + if (kvm_irq_delivery_to_apic_fast(kvm, NULL, &irq, &r, NULL)) return r; else return -EWOULDBLOCK; } -int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi) -{ - struct kvm_kernel_irq_routing_entry route; - - if (!irqchip_in_kernel(kvm) || msi->flags != 0) - return -EINVAL; - - route.msi.address_lo = msi->address_lo; - route.msi.address_hi = msi->address_hi; - route.msi.data = msi->data; - - return kvm_set_msi(&route, kvm, KVM_USERSPACE_IRQ_SOURCE_ID, 1); -} - -/* - * Return value: - * < 0 Interrupt was ignored (masked or not delivered for other reasons) - * = 0 Interrupt was coalesced (previous irq is still pending) - * > 0 Number of CPUs interrupt was delivered to - */ -int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level) -{ - 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 hlist_node *n; - - trace_kvm_set_irq(irq, level, irq_source_id); - - /* Not possible to detect if the guest uses the PIC or the - * 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, n, &irq_rt->map[irq], link) - irq_set[i++] = *e; - rcu_read_unlock(); - - while(i--) { - int r; - r = irq_set[i].set(&irq_set[i], kvm, irq_source_id, level); - if (r < 0) - continue; - - ret = r + ((ret < 0) ? 0 : ret); - } - - return ret; -} - /* * Deliver an IRQ in an atomic context if we can, or return a failure, * user can retry in a process context. @@ -211,7 +163,7 @@ int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level) struct kvm_kernel_irq_routing_entry *e; int ret = -EINVAL; struct kvm_irq_routing_table *irq_rt; - struct hlist_node *n; + int idx; trace_kvm_set_irq(irq, level, irq_source_id); @@ -223,55 +175,20 @@ 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); + idx = srcu_read_lock(&kvm->irq_srcu); + irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu); if (irq < irq_rt->nr_rt_entries) - hlist_for_each_entry(e, n, &irq_rt->map[irq], link) { + 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(); + srcu_read_unlock(&kvm->irq_srcu, idx); return ret; } -void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin) -{ - struct kvm_irq_ack_notifier *kian; - struct hlist_node *n; - 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, n, &kvm->irq_ack_notifier_list, - link) - if (kian->gsi == gsi) - kian->irq_acked(kian); - rcu_read_unlock(); -} - -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); -} - -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_rcu(); -} - int kvm_request_irq_source_id(struct kvm *kvm) { unsigned long *bitmap = &kvm->arch.irq_sources_bitmap; @@ -337,54 +254,32 @@ 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; - struct hlist_node *n; - 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 = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu)->chip[irqchip][pin]; if (gsi != -1) - hlist_for_each_entry_rcu(kimn, n, &kvm->mask_notifier_list, link) + 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); } -void kvm_free_irq_routing(struct kvm *kvm) -{ - /* Called only during vm destruction. Nobody can use the pointer - at this stage */ - kfree(kvm->irq_routing); -} - -static int setup_routing_entry(struct kvm_irq_routing_table *rt, - struct kvm_kernel_irq_routing_entry *e, - const struct kvm_irq_routing_entry *ue) +int kvm_set_routing_entry(struct kvm_irq_routing_table *rt, + struct kvm_kernel_irq_routing_entry *e, + const struct kvm_irq_routing_entry *ue) { int r = -EINVAL; int delta; unsigned max_pin; - struct kvm_kernel_irq_routing_entry *ei; - struct hlist_node *n; - /* - * Do not allow GSI to be mapped to the same irqchip more than once. - * Allow only one to one mapping between GSI and MSI. - */ - hlist_for_each_entry(ei, n, &rt->map[ue->gsi], link) - if (ei->type == KVM_IRQ_ROUTING_MSI || - ue->type == KVM_IRQ_ROUTING_MSI || - ue->u.irqchip.irqchip == ei->irqchip.irqchip) - return r; - - e->gsi = ue->gsi; - e->type = ue->type; switch (ue->type) { case KVM_IRQ_ROUTING_IRQCHIP: delta = 0; @@ -421,66 +316,8 @@ static int setup_routing_entry(struct kvm_irq_routing_table *rt, goto out; } - hlist_add_head(&e->link, &rt->map[e->gsi]); - r = 0; -out: - return r; -} - - -int kvm_set_irq_routing(struct kvm *kvm, - const struct kvm_irq_routing_entry *ue, - unsigned nr, - unsigned flags) -{ - struct kvm_irq_routing_table *new, *old; - u32 i, j, nr_rt_entries = 0; - int r; - - for (i = 0; i < nr; ++i) { - if (ue[i].gsi >= KVM_MAX_IRQ_ROUTES) - return -EINVAL; - nr_rt_entries = max(nr_rt_entries, ue[i].gsi); - } - - nr_rt_entries += 1; - - new = kzalloc(sizeof(*new) + (nr_rt_entries * sizeof(struct hlist_head)) - + (nr * sizeof(struct kvm_kernel_irq_routing_entry)), - GFP_KERNEL); - - if (!new) - return -ENOMEM; - - new->rt_entries = (void *)&new->map[nr_rt_entries]; - - new->nr_rt_entries = nr_rt_entries; - for (i = 0; i < 3; i++) - for (j = 0; j < KVM_IOAPIC_NUM_PINS; j++) - new->chip[i][j] = -1; - - for (i = 0; i < nr; ++i) { - r = -EINVAL; - if (ue->flags) - goto out; - r = setup_routing_entry(new, &new->rt_entries[i], ue); - if (r) - goto out; - ++ue; - } - - mutex_lock(&kvm->irq_lock); - old = kvm->irq_routing; - kvm_irq_routing_update(kvm, new); - mutex_unlock(&kvm->irq_lock); - - synchronize_rcu(); - - new = old; r = 0; - out: - kfree(new); return r; } diff --git a/virt/kvm/irqchip.c b/virt/kvm/irqchip.c new file mode 100644 index 00000000000..b43c275775c --- /dev/null +++ b/virt/kvm/irqchip.c @@ -0,0 +1,238 @@ +/* + * irqchip.c: Common API for in kernel interrupt controllers + * Copyright (c) 2007, Intel Corporation. + * Copyright 2010 Red Hat, Inc. and/or its affiliates. + * Copyright (c) 2013, Alexander Graf <agraf@suse.de> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope 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. + * + * This file is derived from virt/kvm/irq_comm.c. + * + * Authors: + * Yaozu (Eddie) Dong <Eddie.dong@intel.com> + * Alexander Graf <agraf@suse.de> + */ + +#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, idx; + + idx = srcu_read_lock(&kvm->irq_srcu); + gsi = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu)->chip[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 = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu)->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); + 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 +} + +int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi) +{ + struct kvm_kernel_irq_routing_entry route; + + if (!irqchip_in_kernel(kvm) || msi->flags != 0) + return -EINVAL; + + route.msi.address_lo = msi->address_lo; + route.msi.address_hi = msi->address_hi; + route.msi.data = msi->data; + + return kvm_set_msi(&route, kvm, KVM_USERSPACE_IRQ_SOURCE_ID, 1, false); +} + +/* + * Return value: + * < 0 Interrupt was ignored (masked or not delivered for other reasons) + * = 0 Interrupt was coalesced (previous irq is still pending) + * > 0 Number of CPUs interrupt was delivered to + */ +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, idx; + struct kvm_irq_routing_table *irq_rt; + + trace_kvm_set_irq(irq, level, irq_source_id); + + /* Not possible to detect if the guest uses the PIC or the + * IOAPIC. So set the bit in both. The guest will ignore + * writes to the unused one. + */ + idx = srcu_read_lock(&kvm->irq_srcu); + irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu); + if (irq < irq_rt->nr_rt_entries) + hlist_for_each_entry(e, &irq_rt->map[irq], link) + irq_set[i++] = *e; + srcu_read_unlock(&kvm->irq_srcu, idx); + + while(i--) { + int r; + r = irq_set[i].set(&irq_set[i], kvm, irq_source_id, level, + line_status); + if (r < 0) + continue; + + ret = r + ((ret < 0) ? 0 : ret); + } + + return ret; +} + +void kvm_free_irq_routing(struct kvm *kvm) +{ + /* Called only during vm destruction. Nobody can use the pointer + at this stage */ + kfree(kvm->irq_routing); +} + +static int setup_routing_entry(struct kvm_irq_routing_table *rt, + struct kvm_kernel_irq_routing_entry *e, + const struct kvm_irq_routing_entry *ue) +{ + int r = -EINVAL; + struct kvm_kernel_irq_routing_entry *ei; + + /* + * Do not allow GSI to be mapped to the same irqchip more than once. + * Allow only one to one mapping between GSI and MSI. + */ + hlist_for_each_entry(ei, &rt->map[ue->gsi], link) + if (ei->type == KVM_IRQ_ROUTING_MSI || + ue->type == KVM_IRQ_ROUTING_MSI || + ue->u.irqchip.irqchip == ei->irqchip.irqchip) + return r; + + e->gsi = ue->gsi; + e->type = ue->type; + r = kvm_set_routing_entry(rt, e, ue); + if (r) + goto out; + + hlist_add_head(&e->link, &rt->map[e->gsi]); + r = 0; +out: + return r; +} + +int kvm_set_irq_routing(struct kvm *kvm, + const struct kvm_irq_routing_entry *ue, + unsigned nr, + unsigned flags) +{ + struct kvm_irq_routing_table *new, *old; + u32 i, j, nr_rt_entries = 0; + int r; + + for (i = 0; i < nr; ++i) { + if (ue[i].gsi >= KVM_MAX_IRQ_ROUTES) + return -EINVAL; + nr_rt_entries = max(nr_rt_entries, ue[i].gsi); + } + + nr_rt_entries += 1; + + new = kzalloc(sizeof(*new) + (nr_rt_entries * sizeof(struct hlist_head)) + + (nr * sizeof(struct kvm_kernel_irq_routing_entry)), + GFP_KERNEL); + + if (!new) + return -ENOMEM; + + new->rt_entries = (void *)&new->map[nr_rt_entries]; + + new->nr_rt_entries = nr_rt_entries; + for (i = 0; i < KVM_NR_IRQCHIPS; i++) + for (j = 0; j < KVM_IRQCHIP_NUM_PINS; j++) + new->chip[i][j] = -1; + + for (i = 0; i < nr; ++i) { + r = -EINVAL; + if (ue->flags) + goto out; + r = setup_routing_entry(new, &new->rt_entries[i], ue); + if (r) + goto out; + ++ue; + } + + mutex_lock(&kvm->irq_lock); + old = kvm->irq_routing; + kvm_irq_routing_update(kvm, new); + mutex_unlock(&kvm->irq_lock); + + synchronize_srcu_expedited(&kvm->irq_srcu); + + new = old; + r = 0; + +out: + kfree(new); + return r; +} diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 1cd693a76a5..4b6c01b477f 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -70,7 +70,8 @@ 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; @@ -94,36 +95,22 @@ 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_trans_head(tail); - reserved = PageReserved(head); - if (head != tail) { - /* - * "head" is not a dangling pointer - * (compound_trans_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 PageReserved(pfn_to_page(pfn)); return true; } @@ -206,6 +193,7 @@ void kvm_flush_remote_tlbs(struct kvm *kvm) ++kvm->stat.remote_tlb_flush; cmpxchg(&kvm->tlbs_dirty, dirty_count, 0); } +EXPORT_SYMBOL_GPL(kvm_flush_remote_tlbs); void kvm_reload_remote_mmus(struct kvm *kvm) { @@ -217,6 +205,11 @@ void kvm_make_mclock_inprogress_request(struct kvm *kvm) make_all_cpus_request(kvm, KVM_REQ_MCLOCK_INPROGRESS); } +void kvm_make_scan_ioapic_request(struct kvm *kvm) +{ + make_all_cpus_request(kvm, KVM_REQ_SCAN_IOAPIC); +} + int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id) { struct page *page; @@ -239,6 +232,7 @@ int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id) kvm_vcpu_set_in_spin_loop(vcpu, false); kvm_vcpu_set_dy_eligible(vcpu, false); + vcpu->preempted = false; r = kvm_arch_vcpu_init(vcpu); if (r < 0) @@ -463,24 +457,28 @@ 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); INIT_HLIST_HEAD(&kvm->irq_ack_notifier_list); #endif + BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX); + 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); @@ -496,22 +494,25 @@ static struct kvm *kvm_create_vm(unsigned long type) mutex_init(&kvm->irq_lock); mutex_init(&kvm->slots_lock); atomic_set(&kvm->users_count, 1); + INIT_LIST_HEAD(&kvm->devices); r = kvm_init_mmu_notifier(kvm); 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); @@ -551,37 +552,50 @@ 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); } +static void kvm_destroy_devices(struct kvm *kvm) +{ + struct list_head *node, *tmp; + + list_for_each_safe(node, tmp, &kvm->devices) { + struct kvm_device *dev = + list_entry(node, struct kvm_device, vm_node); + + list_del(node); + dev->ops->destroy(dev); + } +} + static void kvm_destroy_vm(struct kvm *kvm) { int i; 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]); @@ -592,7 +606,9 @@ static void kvm_destroy_vm(struct kvm *kvm) kvm_arch_flush_shadow_all(kvm); #endif 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(); @@ -629,14 +645,12 @@ static int kvm_vm_release(struct inode *inode, struct file *filp) */ static int kvm_create_dirty_bitmap(struct kvm_memory_slot *memslot) { -#ifndef CONFIG_S390 unsigned long dirty_bytes = 2 * kvm_dirty_bitmap_bytes(memslot); memslot->dirty_bitmap = kvm_kvzalloc(dirty_bytes); if (!memslot->dirty_bitmap) return -ENOMEM; -#endif /* !CONFIG_S390 */ return 0; } @@ -670,7 +684,9 @@ 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) +static void update_memslots(struct kvm_memslots *slots, + struct kvm_memory_slot *new, + u64 last_generation) { if (new) { int id = new->id; @@ -682,7 +698,7 @@ void update_memslots(struct kvm_memslots *slots, struct kvm_memory_slot *new) sort_memslots(slots); } - slots->generation++; + slots->generation = last_generation + 1; } static int check_memory_region_flags(struct kvm_userspace_memory_region *mem) @@ -699,6 +715,20 @@ static int check_memory_region_flags(struct kvm_userspace_memory_region *mem) return 0; } +static struct kvm_memslots *install_new_memslots(struct kvm *kvm, + struct kvm_memslots *slots, struct kvm_memory_slot *new) +{ + struct kvm_memslots *old_memslots = kvm->memslots; + + update_memslots(slots, new, kvm->memslots->generation); + rcu_assign_pointer(kvm->memslots, slots); + synchronize_srcu_expedited(&kvm->srcu); + + kvm_arch_memslots_updated(kvm); + + return old_memslots; +} + /* * Allocate some memory and give it an address in the guest physical address * space. @@ -708,15 +738,15 @@ static int check_memory_region_flags(struct kvm_userspace_memory_region *mem) * Must be called holding mmap_sem for write. */ int __kvm_set_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem, - int user_alloc) + struct kvm_userspace_memory_region *mem) { int r; gfn_t base_gfn; unsigned long npages; - struct kvm_memory_slot *memslot, *slot; + struct kvm_memory_slot *slot; struct kvm_memory_slot old, new; - struct kvm_memslots *slots, *old_memslots; + struct kvm_memslots *slots = NULL, *old_memslots; + enum kvm_mr_change change; r = check_memory_region_flags(mem); if (r) @@ -729,7 +759,7 @@ int __kvm_set_memory_region(struct kvm *kvm, if (mem->guest_phys_addr & (PAGE_SIZE - 1)) goto out; /* We can read the guest memory with __xxx_user() later on. */ - if (user_alloc && + if ((mem->slot < KVM_USER_MEM_SLOTS) && ((mem->userspace_addr & (PAGE_SIZE - 1)) || !access_ok(VERIFY_WRITE, (void __user *)(unsigned long)mem->userspace_addr, @@ -740,7 +770,7 @@ int __kvm_set_memory_region(struct kvm *kvm, if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr) goto out; - memslot = id_to_memslot(kvm->memslots, mem->slot); + slot = id_to_memslot(kvm->memslots, mem->slot); base_gfn = mem->guest_phys_addr >> PAGE_SHIFT; npages = mem->memory_size >> PAGE_SHIFT; @@ -751,26 +781,48 @@ int __kvm_set_memory_region(struct kvm *kvm, if (!npages) mem->flags &= ~KVM_MEM_LOG_DIRTY_PAGES; - new = old = *memslot; + new = old = *slot; new.id = mem->slot; new.base_gfn = base_gfn; new.npages = npages; new.flags = mem->flags; - /* Disallow changing a memory slot's size. */ r = -EINVAL; - if (npages && old.npages && npages != old.npages) - goto out_free; + if (npages) { + if (!old.npages) + change = KVM_MR_CREATE; + else { /* Modify an existing slot. */ + if ((mem->userspace_addr != old.userspace_addr) || + (npages != old.npages) || + ((new.flags ^ old.flags) & KVM_MEM_READONLY)) + goto out; - /* Check for overlaps */ - r = -EEXIST; - kvm_for_each_memslot(slot, kvm->memslots) { - if (slot->id >= KVM_MEMORY_SLOTS || slot == memslot) - continue; - if (!((base_gfn + npages <= slot->base_gfn) || - (base_gfn >= slot->base_gfn + slot->npages))) - goto out_free; + if (base_gfn != old.base_gfn) + change = KVM_MR_MOVE; + else if (new.flags != old.flags) + change = KVM_MR_FLAGS_ONLY; + else { /* Nothing to change. */ + r = 0; + goto out; + } + } + } else if (old.npages) { + change = KVM_MR_DELETE; + } else /* Modify a non-existent slot: disallowed. */ + goto out; + + if ((change == KVM_MR_CREATE) || (change == KVM_MR_MOVE)) { + /* Check for overlaps */ + r = -EEXIST; + kvm_for_each_memslot(slot, kvm->memslots) { + if ((slot->id >= KVM_USER_MEM_SLOTS) || + (slot->id == mem->slot)) + continue; + if (!((base_gfn + npages <= slot->base_gfn) || + (base_gfn >= slot->base_gfn + slot->npages))) + goto out; + } } /* Free page dirty bitmap if unneeded */ @@ -778,13 +830,10 @@ int __kvm_set_memory_region(struct kvm *kvm, new.dirty_bitmap = NULL; r = -ENOMEM; - - /* Allocate if a slot is being created */ - if (npages && !old.npages) { - new.user_alloc = user_alloc; + 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; } @@ -792,12 +841,9 @@ int __kvm_set_memory_region(struct kvm *kvm, if ((new.flags & KVM_MEM_LOG_DIRTY_PAGES) && !new.dirty_bitmap) { if (kvm_create_dirty_bitmap(&new) < 0) goto out_free; - /* destroy any largepage mappings for dirty tracking */ } - if (!npages || base_gfn != old.base_gfn) { - struct kvm_memory_slot *slot; - + if ((change == KVM_MR_DELETE) || (change == KVM_MR_MOVE)) { r = -ENOMEM; slots = kmemdup(kvm->memslots, sizeof(struct kvm_memslots), GFP_KERNEL); @@ -806,11 +852,10 @@ int __kvm_set_memory_region(struct kvm *kvm, slot = id_to_memslot(slots, mem->slot); slot->flags |= KVM_MEMSLOT_INVALID; - update_memslots(slots, NULL); + old_memslots = install_new_memslots(kvm, slots, NULL); - old_memslots = kvm->memslots; - rcu_assign_pointer(kvm->memslots, slots); - synchronize_srcu_expedited(&kvm->srcu); + /* slot was deleted or moved, clear iommu mapping */ + kvm_iommu_unmap_pages(kvm, &old); /* From this point no new shadow pages pointing to a deleted, * or moved, memslot will be created. * @@ -819,74 +864,82 @@ int __kvm_set_memory_region(struct kvm *kvm, * - kvm_is_visible_gfn (mmu_check_roots) */ kvm_arch_flush_shadow_memslot(kvm, slot); - kfree(old_memslots); + slots = old_memslots; } - r = kvm_arch_prepare_memory_region(kvm, &new, old, mem, user_alloc); + r = kvm_arch_prepare_memory_region(kvm, &new, mem, change); if (r) - goto out_free; - - /* map/unmap the pages in iommu page table */ - if (npages) { - r = kvm_iommu_map_pages(kvm, &new); - if (r) - goto out_free; - } else - kvm_iommu_unmap_pages(kvm, &old); + goto out_slots; r = -ENOMEM; - slots = kmemdup(kvm->memslots, sizeof(struct kvm_memslots), - GFP_KERNEL); - if (!slots) - goto out_free; + /* + * We can re-use the old_memslots from above, the only difference + * from the currently installed memslots is the invalid flag. This + * will get overwritten by update_memslots anyway. + */ + if (!slots) { + slots = kmemdup(kvm->memslots, sizeof(struct kvm_memslots), + GFP_KERNEL); + if (!slots) + goto out_free; + } /* actual memory is freed via old in kvm_free_physmem_slot below */ - if (!npages) { + if (change == KVM_MR_DELETE) { new.dirty_bitmap = NULL; memset(&new.arch, 0, sizeof(new.arch)); } - update_memslots(slots, &new); - old_memslots = kvm->memslots; - rcu_assign_pointer(kvm->memslots, slots); - synchronize_srcu_expedited(&kvm->srcu); + old_memslots = install_new_memslots(kvm, slots, &new); - kvm_arch_commit_memory_region(kvm, mem, old, user_alloc); + kvm_arch_commit_memory_region(kvm, mem, &old, change); - kvm_free_physmem_slot(&old, &new); + 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 + * unmapping is handled above with slot deletion, mapping alone is + * needed here. Anything else the iommu might care about for existing + * slots (size changes, userspace addr changes and read-only flag + * changes) is disallowed above, so any other attribute changes getting + * here can be skipped. + */ + if ((change == KVM_MR_CREATE) || (change == KVM_MR_MOVE)) { + r = kvm_iommu_map_pages(kvm, &new); + return r; + } + return 0; +out_slots: + kfree(slots); out_free: - kvm_free_physmem_slot(&new, &old); + kvm_free_physmem_slot(kvm, &new, &old); out: return r; - } EXPORT_SYMBOL_GPL(__kvm_set_memory_region); int kvm_set_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem, - int user_alloc) + struct kvm_userspace_memory_region *mem) { int r; mutex_lock(&kvm->slots_lock); - r = __kvm_set_memory_region(kvm, mem, user_alloc); + r = __kvm_set_memory_region(kvm, mem); mutex_unlock(&kvm->slots_lock); return r; } EXPORT_SYMBOL_GPL(kvm_set_memory_region); -int kvm_vm_ioctl_set_memory_region(struct kvm *kvm, - struct - kvm_userspace_memory_region *mem, - int user_alloc) +static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm, + struct kvm_userspace_memory_region *mem) { - if (mem->slot >= KVM_MEMORY_SLOTS) + if (mem->slot >= KVM_USER_MEM_SLOTS) return -EINVAL; - return kvm_set_memory_region(kvm, mem, user_alloc); + return kvm_set_memory_region(kvm, mem); } int kvm_get_dirty_log(struct kvm *kvm, @@ -898,7 +951,7 @@ int kvm_get_dirty_log(struct kvm *kvm, unsigned long any = 0; r = -EINVAL; - if (log->slot >= KVM_MEMORY_SLOTS) + if (log->slot >= KVM_USER_MEM_SLOTS) goto out; memslot = id_to_memslot(kvm->memslots, log->slot); @@ -922,6 +975,7 @@ int kvm_get_dirty_log(struct kvm *kvm, out: return r; } +EXPORT_SYMBOL_GPL(kvm_get_dirty_log); bool kvm_largepages_enabled(void) { @@ -944,7 +998,7 @@ int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn) { struct kvm_memory_slot *memslot = gfn_to_memslot(kvm, gfn); - if (!memslot || memslot->id >= KVM_MEMORY_SLOTS || + if (!memslot || memslot->id >= KVM_USER_MEM_SLOTS || memslot->flags & KVM_MEMSLOT_INVALID) return 0; @@ -1003,7 +1057,7 @@ 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); } @@ -1016,12 +1070,18 @@ 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_prot(struct kvm *kvm, gfn_t gfn, bool *writable) { - return __gfn_to_hva_many(gfn_to_memslot(kvm, gfn), gfn, NULL, false); + struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn); + 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; } static int kvm_read_hva(void *data, void __user *hva, int len) @@ -1034,7 +1094,7 @@ static int kvm_read_hva_atomic(void *data, void __user *hva, int len) return __copy_from_user_inatomic(data, hva, len); } -int get_user_page_nowait(struct task_struct *tsk, struct mm_struct *mm, +static int get_user_page_nowait(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, int write, struct page **page) { int flags = FOLL_TOUCH | FOLL_NOWAIT | FOLL_HWPOISON | FOLL_GET; @@ -1337,18 +1397,11 @@ 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) { @@ -1388,7 +1441,7 @@ 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); @@ -1426,7 +1479,7 @@ 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(); @@ -1476,21 +1529,38 @@ int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data, } int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc, - gpa_t gpa) + gpa_t gpa, unsigned long len) { struct kvm_memslots *slots = kvm_memslots(kvm); int offset = offset_in_page(gpa); - gfn_t gfn = gpa >> PAGE_SHIFT; + gfn_t start_gfn = gpa >> PAGE_SHIFT; + gfn_t end_gfn = (gpa + len - 1) >> PAGE_SHIFT; + gfn_t nr_pages_needed = end_gfn - start_gfn + 1; + gfn_t nr_pages_avail; ghc->gpa = gpa; ghc->generation = slots->generation; - ghc->memslot = gfn_to_memslot(kvm, gfn); - ghc->hva = gfn_to_hva_many(ghc->memslot, gfn, NULL); - if (!kvm_is_error_hva(ghc->hva)) + ghc->len = len; + ghc->memslot = gfn_to_memslot(kvm, start_gfn); + ghc->hva = gfn_to_hva_many(ghc->memslot, start_gfn, &nr_pages_avail); + if (!kvm_is_error_hva(ghc->hva) && nr_pages_avail >= nr_pages_needed) { ghc->hva += offset; - else - return -EFAULT; - + } else { + /* + * If the requested region crosses two memslots, we still + * verify that the entire region is valid here. + */ + while (start_gfn <= end_gfn) { + ghc->memslot = gfn_to_memslot(kvm, start_gfn); + ghc->hva = gfn_to_hva_many(ghc->memslot, start_gfn, + &nr_pages_avail); + if (kvm_is_error_hva(ghc->hva)) + return -EFAULT; + start_gfn += nr_pages_avail; + } + /* Use the slow path for cross page reads and writes. */ + ghc->memslot = NULL; + } return 0; } EXPORT_SYMBOL_GPL(kvm_gfn_to_hva_cache_init); @@ -1501,8 +1571,13 @@ int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, struct kvm_memslots *slots = kvm_memslots(kvm); int r; + BUG_ON(len > ghc->len); + if (slots->generation != ghc->generation) - kvm_gfn_to_hva_cache_init(kvm, ghc, ghc->gpa); + kvm_gfn_to_hva_cache_init(kvm, ghc, ghc->gpa, ghc->len); + + if (unlikely(!ghc->memslot)) + return kvm_write_guest(kvm, ghc->gpa, data, len); if (kvm_is_error_hva(ghc->hva)) return -EFAULT; @@ -1522,8 +1597,13 @@ int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, struct kvm_memslots *slots = kvm_memslots(kvm); int r; + BUG_ON(len > ghc->len); + if (slots->generation != ghc->generation) - kvm_gfn_to_hva_cache_init(kvm, ghc, ghc->gpa); + kvm_gfn_to_hva_cache_init(kvm, ghc, ghc->gpa, ghc->len); + + if (unlikely(!ghc->memslot)) + return kvm_read_guest(kvm, ghc->gpa, data, len); if (kvm_is_error_hva(ghc->hva)) return -EFAULT; @@ -1538,8 +1618,9 @@ 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); @@ -1562,8 +1643,9 @@ 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; @@ -1579,6 +1661,7 @@ void mark_page_dirty(struct kvm *kvm, gfn_t gfn) memslot = gfn_to_memslot(kvm, gfn); mark_page_dirty_in_slot(kvm, memslot, gfn); } +EXPORT_SYMBOL_GPL(mark_page_dirty); /* * The vCPU has executed a HLT instruction with in-kernel mode enabled. @@ -1604,6 +1687,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) finish_wait(&vcpu->wq, &wait); } +EXPORT_SYMBOL_GPL(kvm_vcpu_block); #ifndef CONFIG_S390 /* @@ -1627,20 +1711,14 @@ void kvm_vcpu_kick(struct kvm_vcpu *vcpu) smp_send_reschedule(cpu); put_cpu(); } +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) +int kvm_vcpu_yield_to(struct kvm_vcpu *target) { struct pid *pid; struct task_struct *task = NULL; + int ret = 0; rcu_read_lock(); pid = rcu_dereference(target->pid); @@ -1648,21 +1726,18 @@ bool kvm_vcpu_yield_to(struct kvm_vcpu *target) task = get_pid_task(target->pid, PIDTYPE_PID); rcu_read_unlock(); if (!task) - return false; + return ret; if (task->flags & PF_VCPU) { put_task_struct(task); - return false; - } - if (yield_to(task, 1)) { - put_task_struct(task); - return true; + return ret; } + ret = yield_to(task, 1); put_task_struct(task); - return false; + + return ret; } 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: @@ -1685,8 +1760,9 @@ 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 || @@ -1697,14 +1773,18 @@ bool kvm_vcpu_eligible_for_directed_yield(struct kvm_vcpu *vcpu) 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) { struct kvm *kvm = me->kvm; struct kvm_vcpu *vcpu; int last_boosted_vcpu = me->kvm->last_boosted_vcpu; int yielded = 0; + int try = 3; int pass; int i; @@ -1716,23 +1796,30 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me) * VCPU is holding the lock that we need and will release it. * We approximate round-robin by starting at the last boosted VCPU. */ - for (pass = 0; pass < 2 && !yielded; pass++) { + for (pass = 0; pass < 2 && !yielded && try; pass++) { kvm_for_each_vcpu(i, vcpu, kvm) { if (!pass && i <= last_boosted_vcpu) { i = last_boosted_vcpu; continue; } else if (pass && i > last_boosted_vcpu) break; + if (!ACCESS_ONCE(vcpu->preempted)) + 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; - if (kvm_vcpu_yield_to(vcpu)) { + + yielded = kvm_vcpu_yield_to(vcpu); + if (yielded > 0) { kvm->last_boosted_vcpu = i; - yielded = 1; break; + } else if (yielded < 0) { + try--; + if (!try) + break; } } } @@ -1798,7 +1885,7 @@ 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); } /* @@ -1809,6 +1896,9 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) int r; struct kvm_vcpu *vcpu, *v; + if (id >= KVM_MAX_VCPUS) + return -EINVAL; + vcpu = kvm_arch_vcpu_create(kvm, id); if (IS_ERR(vcpu)) return PTR_ERR(vcpu); @@ -1883,7 +1973,7 @@ static long kvm_vcpu_ioctl(struct file *filp, if (vcpu->kvm->mm != current->mm) return -EIO; -#if defined(CONFIG_S390) || defined(CONFIG_PPC) +#if defined(CONFIG_S390) || defined(CONFIG_PPC) || defined(CONFIG_MIPS) /* * Special cases: vcpu ioctls that are asynchronous to vcpu execution, * so vcpu_load() would break it. @@ -2106,6 +2196,134 @@ out: } #endif +static int kvm_device_ioctl_attr(struct kvm_device *dev, + int (*accessor)(struct kvm_device *dev, + struct kvm_device_attr *attr), + unsigned long arg) +{ + struct kvm_device_attr attr; + + if (!accessor) + return -EPERM; + + if (copy_from_user(&attr, (void __user *)arg, sizeof(attr))) + return -EFAULT; + + return accessor(dev, &attr); +} + +static long kvm_device_ioctl(struct file *filp, unsigned int ioctl, + unsigned long arg) +{ + struct kvm_device *dev = filp->private_data; + + switch (ioctl) { + case KVM_SET_DEVICE_ATTR: + return kvm_device_ioctl_attr(dev, dev->ops->set_attr, arg); + case KVM_GET_DEVICE_ATTR: + return kvm_device_ioctl_attr(dev, dev->ops->get_attr, arg); + case KVM_HAS_DEVICE_ATTR: + return kvm_device_ioctl_attr(dev, dev->ops->has_attr, arg); + default: + if (dev->ops->ioctl) + return dev->ops->ioctl(dev, ioctl, arg); + + return -ENOTTY; + } +} + +static int kvm_device_release(struct inode *inode, struct file *filp) +{ + struct kvm_device *dev = filp->private_data; + struct kvm *kvm = dev->kvm; + + kvm_put_kvm(kvm); + return 0; +} + +static const struct file_operations kvm_device_fops = { + .unlocked_ioctl = kvm_device_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = kvm_device_ioctl, +#endif + .release = kvm_device_release, +}; + +struct kvm_device *kvm_device_from_filp(struct file *filp) +{ + if (filp->f_op != &kvm_device_fops) + return NULL; + + return filp->private_data; +} + +static int kvm_ioctl_create_device(struct kvm *kvm, + struct kvm_create_device *cd) +{ + struct kvm_device_ops *ops = NULL; + struct kvm_device *dev; + 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 +#ifdef CONFIG_KVM_VFIO + case KVM_DEV_TYPE_VFIO: + ops = &kvm_vfio_ops; + break; +#endif +#ifdef CONFIG_KVM_ARM_VGIC + case KVM_DEV_TYPE_ARM_VGIC_V2: + ops = &kvm_arm_vgic_v2_ops; + break; +#endif +#ifdef CONFIG_S390 + case KVM_DEV_TYPE_FLIC: + ops = &kvm_flic_ops; + break; +#endif + default: + return -ENODEV; + } + + if (test) + return 0; + + dev = kzalloc(sizeof(*dev), GFP_KERNEL); + if (!dev) + return -ENOMEM; + + dev->ops = ops; + dev->kvm = kvm; + + ret = ops->create(dev, cd->type); + if (ret < 0) { + kfree(dev); + return ret; + } + + ret = anon_inode_getfd(ops->name, &kvm_device_fops, dev, O_RDWR | O_CLOEXEC); + if (ret < 0) { + ops->destroy(dev); + return ret; + } + + list_add(&dev->vm_node, &kvm->devices); + kvm_get_kvm(kvm); + cd->fd = ret; + return 0; +} + static long kvm_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -2127,7 +2345,7 @@ static long kvm_vm_ioctl(struct file *filp, sizeof kvm_userspace_mem)) goto out; - r = kvm_vm_ioctl_set_memory_region(kvm, &kvm_userspace_mem, 1); + r = kvm_vm_ioctl_set_memory_region(kvm, &kvm_userspace_mem); break; } case KVM_GET_DIRTY_LOG: { @@ -2206,7 +2424,8 @@ static long kvm_vm_ioctl(struct file *filp, if (copy_from_user(&irq_event, argp, sizeof irq_event)) goto out; - r = kvm_vm_ioctl_irq_line(kvm, &irq_event); + r = kvm_vm_ioctl_irq_line(kvm, &irq_event, + ioctl == KVM_IRQ_LINE_STATUS); if (r) goto out; @@ -2220,6 +2439,54 @@ static long kvm_vm_ioctl(struct file *filp, break; } #endif +#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING + case KVM_SET_GSI_ROUTING: { + struct kvm_irq_routing routing; + struct kvm_irq_routing __user *urouting; + struct kvm_irq_routing_entry *entries; + + r = -EFAULT; + if (copy_from_user(&routing, argp, sizeof(routing))) + goto out; + r = -EINVAL; + if (routing.nr >= KVM_MAX_IRQ_ROUTES) + goto out; + if (routing.flags) + goto out; + r = -ENOMEM; + entries = vmalloc(routing.nr * sizeof(*entries)); + if (!entries) + goto out; + r = -EFAULT; + urouting = argp; + if (copy_from_user(entries, urouting->entries, + routing.nr * sizeof(*entries))) + goto out_free_irq_routing; + r = kvm_set_irq_routing(kvm, entries, routing.nr, + routing.flags); + out_free_irq_routing: + vfree(entries); + break; + } +#endif /* CONFIG_HAVE_KVM_IRQ_ROUTING */ + case KVM_CREATE_DEVICE: { + struct kvm_create_device cd; + + r = -EFAULT; + if (copy_from_user(&cd, argp, sizeof(cd))) + goto out; + + r = kvm_ioctl_create_device(kvm, &cd); + if (r) + goto out; + + r = -EFAULT; + if (copy_to_user(argp, &cd, sizeof(cd))) + goto out; + + r = 0; + break; + } default: r = kvm_arch_vm_ioctl(filp, ioctl, arg); if (r == -ENOTTY) @@ -2273,44 +2540,12 @@ 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, }; @@ -2329,7 +2564,7 @@ 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); @@ -2349,8 +2584,11 @@ static long kvm_dev_ioctl_check_extension_generic(long arg) #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 KVM_CAP_IRQ_ROUTING +#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING case KVM_CAP_IRQ_ROUTING: return KVM_MAX_IRQ_ROUTES; #endif @@ -2434,11 +2672,12 @@ 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) @@ -2451,11 +2690,12 @@ static void hardware_disable_nolock(void *junk) kvm_arch_hardware_disable(NULL); } -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) @@ -2469,16 +2709,16 @@ 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) { @@ -2491,7 +2731,7 @@ static int hardware_enable_all(void) } } - raw_spin_unlock(&kvm_lock); + raw_spin_unlock(&kvm_count_lock); return r; } @@ -2501,33 +2741,22 @@ 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; } - -asmlinkage void kvm_spurious_fault(void) -{ - /* Fault while not rebooting. We want the trace. */ - BUG(); -} -EXPORT_SYMBOL_GPL(kvm_spurious_fault); - static int kvm_reboot(struct notifier_block *notifier, unsigned long val, void *v) { @@ -2560,11 +2789,9 @@ static void kvm_io_bus_destroy(struct kvm_io_bus *bus) kfree(bus); } -int kvm_io_bus_sort_cmp(const void *p1, const void *p2) +static inline int kvm_io_bus_cmp(const struct kvm_io_range *r1, + const struct kvm_io_range *r2) { - const struct kvm_io_range *r1 = p1; - const struct kvm_io_range *r2 = p2; - if (r1->addr < r2->addr) return -1; if (r1->addr + r1->len > r2->addr + r2->len) @@ -2572,7 +2799,12 @@ int kvm_io_bus_sort_cmp(const void *p1, const void *p2) return 0; } -int kvm_io_bus_insert_dev(struct kvm_io_bus *bus, struct kvm_io_device *dev, +static int kvm_io_bus_sort_cmp(const void *p1, const void *p2) +{ + return kvm_io_bus_cmp(p1, p2); +} + +static int kvm_io_bus_insert_dev(struct kvm_io_bus *bus, struct kvm_io_device *dev, gpa_t addr, int len) { bus->range[bus->dev_count++] = (struct kvm_io_range) { @@ -2587,7 +2819,7 @@ int kvm_io_bus_insert_dev(struct kvm_io_bus *bus, struct kvm_io_device *dev, return 0; } -int kvm_io_bus_get_first_dev(struct kvm_io_bus *bus, +static int kvm_io_bus_get_first_dev(struct kvm_io_bus *bus, gpa_t addr, int len) { struct kvm_io_range *range, key; @@ -2605,19 +2837,39 @@ int kvm_io_bus_get_first_dev(struct kvm_io_bus *bus, off = range - bus->range; - while (off > 0 && kvm_io_bus_sort_cmp(&key, &bus->range[off-1]) == 0) + while (off > 0 && kvm_io_bus_cmp(&key, &bus->range[off-1]) == 0) off--; return off; } +static int __kvm_io_bus_write(struct kvm_io_bus *bus, + struct kvm_io_range *range, const void *val) +{ + int idx; + + idx = kvm_io_bus_get_first_dev(bus, range->addr, range->len); + if (idx < 0) + return -EOPNOTSUPP; + + while (idx < bus->dev_count && + kvm_io_bus_cmp(range, &bus->range[idx]) == 0) { + if (!kvm_iodevice_write(bus->range[idx].dev, range->addr, + range->len, val)) + return idx; + idx++; + } + + return -EOPNOTSUPP; +} + /* kvm_io_bus_write - called under kvm->slots_lock */ int kvm_io_bus_write(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, int len, const void *val) { - int idx; struct kvm_io_bus *bus; struct kvm_io_range range; + int r; range = (struct kvm_io_range) { .addr = addr, @@ -2625,27 +2877,66 @@ int kvm_io_bus_write(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, }; bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu); - idx = kvm_io_bus_get_first_dev(bus, addr, len); + r = __kvm_io_bus_write(bus, &range, val); + return r < 0 ? r : 0; +} + +/* kvm_io_bus_write_cookie - called under kvm->slots_lock */ +int kvm_io_bus_write_cookie(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, + int len, const void *val, long cookie) +{ + struct kvm_io_bus *bus; + struct kvm_io_range range; + + range = (struct kvm_io_range) { + .addr = addr, + .len = len, + }; + + bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu); + + /* First try the device referenced by cookie. */ + if ((cookie >= 0) && (cookie < bus->dev_count) && + (kvm_io_bus_cmp(&range, &bus->range[cookie]) == 0)) + if (!kvm_iodevice_write(bus->range[cookie].dev, addr, len, + val)) + return cookie; + + /* + * cookie contained garbage; fall back to search and return the + * correct cookie value. + */ + return __kvm_io_bus_write(bus, &range, val); +} + +static int __kvm_io_bus_read(struct kvm_io_bus *bus, struct kvm_io_range *range, + void *val) +{ + int idx; + + idx = kvm_io_bus_get_first_dev(bus, range->addr, range->len); if (idx < 0) return -EOPNOTSUPP; while (idx < bus->dev_count && - kvm_io_bus_sort_cmp(&range, &bus->range[idx]) == 0) { - if (!kvm_iodevice_write(bus->range[idx].dev, addr, len, val)) - return 0; + kvm_io_bus_cmp(range, &bus->range[idx]) == 0) { + if (!kvm_iodevice_read(bus->range[idx].dev, range->addr, + range->len, val)) + return idx; idx++; } return -EOPNOTSUPP; } +EXPORT_SYMBOL_GPL(kvm_io_bus_write); /* kvm_io_bus_read - called under kvm->slots_lock */ int kvm_io_bus_read(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, int len, void *val) { - int idx; struct kvm_io_bus *bus; struct kvm_io_range range; + int r; range = (struct kvm_io_range) { .addr = addr, @@ -2653,20 +2944,11 @@ int kvm_io_bus_read(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, }; bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu); - idx = kvm_io_bus_get_first_dev(bus, addr, len); - if (idx < 0) - return -EOPNOTSUPP; - - while (idx < bus->dev_count && - kvm_io_bus_sort_cmp(&range, &bus->range[idx]) == 0) { - if (!kvm_iodevice_read(bus->range[idx].dev, addr, len, val)) - return 0; - idx++; - } - - return -EOPNOTSUPP; + r = __kvm_io_bus_read(bus, &range, val); + return r < 0 ? r : 0; } + /* Caller must hold slots_lock. */ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, int len, struct kvm_io_device *dev) @@ -2674,7 +2956,8 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, struct kvm_io_bus *new_bus, *bus; bus = kvm->buses[bus_idx]; - if (bus->dev_count > NR_IOBUS_DEVS - 1) + /* exclude ioeventfd which is limited by maximum fd */ + if (bus->dev_count - bus->ioeventfd_count > NR_IOBUS_DEVS - 1) return -ENOSPC; new_bus = kzalloc(sizeof(*bus) + ((bus->dev_count + 1) * @@ -2735,10 +3018,10 @@ 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; } @@ -2752,12 +3035,12 @@ 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; } @@ -2770,7 +3053,7 @@ 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); @@ -2812,7 +3095,7 @@ 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); } } @@ -2831,6 +3114,8 @@ struct kvm_vcpu *preempt_notifier_to_vcpu(struct preempt_notifier *pn) static void kvm_sched_in(struct preempt_notifier *pn, int cpu) { struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn); + if (vcpu->preempted) + vcpu->preempted = false; kvm_arch_vcpu_load(vcpu, cpu); } @@ -2840,6 +3125,8 @@ static void kvm_sched_out(struct preempt_notifier *pn, { struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn); + if (current->state == TASK_RUNNING) + vcpu->preempted = true; kvm_arch_vcpu_put(vcpu); } @@ -2853,6 +3140,17 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align, if (r) goto out_fail; + /* + * kvm_arch_init makes sure there's at most one caller + * for architectures that support multiple implementations, + * like intel and amd on x86. + * kvm_arch_init must be called before kvm_irqfd_init to avoid creating + * conflicts in case kvm is already setup for another implementation. + */ + r = kvm_irqfd_init(); + if (r) + goto out_irqfd; + if (!zalloc_cpumask_var(&cpus_hardware_enabled, GFP_KERNEL)) { r = -ENOMEM; goto out_free_0; @@ -2914,6 +3212,7 @@ 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: @@ -2927,6 +3226,8 @@ out_free_1: out_free_0a: free_cpumask_var(cpus_hardware_enabled); out_free_0: + kvm_irqfd_exit(); +out_irqfd: kvm_arch_exit(); out_fail: return r; @@ -2945,6 +3246,7 @@ void kvm_exit(void) on_each_cpu(hardware_disable_nolock, NULL, 1); kvm_arch_hardware_unsetup(); kvm_arch_exit(); + kvm_irqfd_exit(); free_cpumask_var(cpus_hardware_enabled); } EXPORT_SYMBOL_GPL(kvm_exit); diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c new file mode 100644 index 00000000000..ba1a93f935c --- /dev/null +++ b/virt/kvm/vfio.c @@ -0,0 +1,277 @@ +/* + * 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; + bool noncoherent; +}; + +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 bool kvm_vfio_group_is_coherent(struct vfio_group *vfio_group) +{ + long (*fn)(struct vfio_group *, unsigned long); + long ret; + + fn = symbol_get(vfio_external_check_extension); + if (!fn) + return false; + + ret = fn(vfio_group, VFIO_DMA_CC_IOMMU); + + symbol_put(vfio_external_check_extension); + + return ret > 0; +} + +/* + * Groups can use the same or different IOMMU domains. If the same then + * adding a new group may change the coherency of groups we've previously + * been told about. We don't want to care about any of that so we retest + * each group and bail as soon as we find one that's noncoherent. This + * means we only ever [un]register_noncoherent_dma once for the whole device. + */ +static void kvm_vfio_update_coherency(struct kvm_device *dev) +{ + struct kvm_vfio *kv = dev->private; + bool noncoherent = false; + struct kvm_vfio_group *kvg; + + mutex_lock(&kv->lock); + + list_for_each_entry(kvg, &kv->group_list, node) { + if (!kvm_vfio_group_is_coherent(kvg->vfio_group)) { + noncoherent = true; + break; + } + } + + if (noncoherent != kv->noncoherent) { + kv->noncoherent = noncoherent; + + if (kv->noncoherent) + kvm_arch_register_noncoherent_dma(dev->kvm); + else + kvm_arch_unregister_noncoherent_dma(dev->kvm); + } + + mutex_unlock(&kv->lock); +} + +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; + int32_t __user *argp = (int32_t __user *)(unsigned long)arg; + struct fd f; + int32_t fd; + int ret; + + switch (attr) { + case KVM_DEV_VFIO_GROUP_ADD: + if (get_user(fd, 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); + + kvm_vfio_update_coherency(dev); + + return 0; + + case KVM_DEV_VFIO_GROUP_DEL: + if (get_user(fd, 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); + + kvm_vfio_update_coherency(dev); + + 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); + } + + kvm_vfio_update_coherency(dev); + + kfree(kv); + kfree(dev); /* alloc by kvm_ioctl_create_device, free by .destroy */ +} + +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; +} + +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, +}; |