diff options
Diffstat (limited to 'virt/kvm')
| -rw-r--r-- | virt/kvm/Kconfig | 106 | ||||
| -rw-r--r-- | virt/kvm/Makefile.kvm | 15 | ||||
| -rw-r--r-- | virt/kvm/arm/arch_timer.c | 284 | ||||
| -rw-r--r-- | virt/kvm/arm/vgic.c | 1499 | ||||
| -rw-r--r-- | virt/kvm/assigned-dev.c | 1023 | ||||
| -rw-r--r-- | virt/kvm/async_pf.c | 176 | ||||
| -rw-r--r-- | virt/kvm/async_pf.h | 18 | ||||
| -rw-r--r-- | virt/kvm/binary_stats.c | 144 | ||||
| -rw-r--r-- | virt/kvm/coalesced_mmio.c | 105 | ||||
| -rw-r--r-- | virt/kvm/coalesced_mmio.h | 5 | ||||
| -rw-r--r-- | virt/kvm/dirty_ring.c | 271 | ||||
| -rw-r--r-- | virt/kvm/eventfd.c | 723 | ||||
| -rw-r--r-- | virt/kvm/guest_memfd.c | 1016 | ||||
| -rw-r--r-- | virt/kvm/ioapic.c | 603 | ||||
| -rw-r--r-- | virt/kvm/ioapic.h | 103 | ||||
| -rw-r--r-- | virt/kvm/iodev.h | 70 | ||||
| -rw-r--r-- | virt/kvm/iommu.c | 357 | ||||
| -rw-r--r-- | virt/kvm/irq_comm.c | 372 | ||||
| -rw-r--r-- | virt/kvm/irqchip.c | 238 | ||||
| -rw-r--r-- | virt/kvm/kvm_main.c | 6326 | ||||
| -rw-r--r-- | virt/kvm/kvm_mm.h | 97 | ||||
| -rw-r--r-- | virt/kvm/pfncache.c | 484 | ||||
| -rw-r--r-- | virt/kvm/vfio.c | 387 | ||||
| -rw-r--r-- | virt/kvm/vfio.h | 18 |
24 files changed, 8150 insertions, 6290 deletions
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig index 779262f59e25..267c7369c765 100644 --- a/virt/kvm/Kconfig +++ b/virt/kvm/Kconfig @@ -1,6 +1,13 @@ +# SPDX-License-Identifier: GPL-2.0 # KVM common configuration items and defaults -config HAVE_KVM +config KVM_COMMON + bool + select EVENTFD + select INTERVAL_TREE + select PREEMPT_NOTIFIERS + +config HAVE_KVM_PFNCACHE bool config HAVE_KVM_IRQCHIP @@ -9,12 +16,28 @@ config HAVE_KVM_IRQCHIP config HAVE_KVM_IRQ_ROUTING bool -config HAVE_KVM_EVENTFD +config HAVE_KVM_DIRTY_RING bool - select EVENTFD -config KVM_APIC_ARCHITECTURE +# Only strongly ordered architectures can select this, as it doesn't +# put any explicit constraint on userspace ordering. They can also +# select the _ACQ_REL version. +config HAVE_KVM_DIRTY_RING_TSO + bool + select HAVE_KVM_DIRTY_RING + depends on X86 + +# Weakly ordered architectures can only select this, advertising +# to userspace the additional ordering requirements. +config HAVE_KVM_DIRTY_RING_ACQ_REL bool + select HAVE_KVM_DIRTY_RING + +# Allow enabling both the dirty bitmap and dirty ring. Only architectures +# that need to dirty memory outside of a vCPU context should select this. +config NEED_KVM_DIRTY_RING_WITH_BITMAP + bool + depends on HAVE_KVM_DIRTY_RING config KVM_MMIO bool @@ -22,8 +45,83 @@ 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_READONLY_MEM + bool + config HAVE_KVM_CPU_RELAX_INTERCEPT bool + +config KVM_VFIO + bool + +config HAVE_KVM_INVALID_WAKEUPS + bool + +config KVM_GENERIC_DIRTYLOG_READ_PROTECT + bool + +config KVM_GENERIC_PRE_FAULT_MEMORY + bool + +config KVM_COMPAT + def_bool y + depends on KVM && COMPAT && !(S390 || ARM64 || RISCV) + +config HAVE_KVM_IRQ_BYPASS + tristate + select IRQ_BYPASS_MANAGER + +config HAVE_KVM_VCPU_RUN_PID_CHANGE + bool + +config HAVE_KVM_NO_POLL + bool + +config VIRT_XFER_TO_GUEST_WORK + bool + +config HAVE_KVM_PM_NOTIFIER + bool + +config KVM_GENERIC_HARDWARE_ENABLING + bool + +config KVM_GENERIC_MMU_NOTIFIER + select MMU_NOTIFIER + bool + +config KVM_ELIDE_TLB_FLUSH_IF_YOUNG + depends on KVM_GENERIC_MMU_NOTIFIER + bool + +config KVM_MMU_LOCKLESS_AGING + depends on KVM_GENERIC_MMU_NOTIFIER + bool + +config KVM_GENERIC_MEMORY_ATTRIBUTES + depends on KVM_GENERIC_MMU_NOTIFIER + bool + +config KVM_GUEST_MEMFD + depends on KVM_GENERIC_MMU_NOTIFIER + select XARRAY_MULTI + bool + +config HAVE_KVM_ARCH_GMEM_PREPARE + bool + depends on KVM_GUEST_MEMFD + +config HAVE_KVM_ARCH_GMEM_INVALIDATE + bool + depends on KVM_GUEST_MEMFD + +config HAVE_KVM_ARCH_GMEM_POPULATE + bool + depends on KVM_GUEST_MEMFD diff --git a/virt/kvm/Makefile.kvm b/virt/kvm/Makefile.kvm new file mode 100644 index 000000000000..d047d4cf58c9 --- /dev/null +++ b/virt/kvm/Makefile.kvm @@ -0,0 +1,15 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for Kernel-based Virtual Machine module +# + +KVM ?= ../../../virt/kvm + +kvm-y := $(KVM)/kvm_main.o $(KVM)/eventfd.o $(KVM)/binary_stats.o +kvm-$(CONFIG_KVM_VFIO) += $(KVM)/vfio.o +kvm-$(CONFIG_KVM_MMIO) += $(KVM)/coalesced_mmio.o +kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o +kvm-$(CONFIG_HAVE_KVM_IRQ_ROUTING) += $(KVM)/irqchip.o +kvm-$(CONFIG_HAVE_KVM_DIRTY_RING) += $(KVM)/dirty_ring.o +kvm-$(CONFIG_HAVE_KVM_PFNCACHE) += $(KVM)/pfncache.o +kvm-$(CONFIG_KVM_GUEST_MEMFD) += $(KVM)/guest_memfd.o diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c deleted file mode 100644 index c2e1ef4604e8..000000000000 --- a/virt/kvm/arm/arch_timer.c +++ /dev/null @@ -1,284 +0,0 @@ -/* - * 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); -} - - -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 deleted file mode 100644 index 17c5ac7d10ed..000000000000 --- a/virt/kvm/arm/vgic.c +++ /dev/null @@ -1,1499 +0,0 @@ -/* - * 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/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) - -/* 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 < 4) - 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: /* 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: /* 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: /* IIDR */ - reg = 0x4B00043B; - 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; - struct kvm_vcpu *vcpu; - int i, c; - unsigned long *bmap; - u32 val = 0; - - irq -= VGIC_NR_PRIVATE_IRQS; - - kvm_for_each_vcpu(c, vcpu, kvm) { - bmap = vgic_bitmap_get_shared_map(&dist->irq_spi_target[c]); - for (i = 0; i < GICD_IRQS_PER_ITARGETSR; i++) - if (test_bit(irq + i, bmap)) - val |= 1 << (c + 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 = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_cfg, - vcpu->vcpu_id, offset >> 1); - if (offset & 2) - 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 < 4) { - *reg = ~0U; /* Force PPIs/SGIs to 1 */ - return false; - } - - val = vgic_cfg_compress(val); - if (offset & 2) { - *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; -} - -/* - * 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_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, - }, - {} -}; - -static const -struct mmio_range *find_matching_range(const struct mmio_range *ranges, - struct kvm_exit_mmio *mmio, - phys_addr_t base) -{ - const struct mmio_range *r = ranges; - phys_addr_t addr = mmio->phys_addr - base; - - while (r->len) { - if (addr >= r->base && - (addr + 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; - } - - range = find_matching_range(vgic_ranges, mmio, base); - 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; - - 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 LR_CPUID(lr) \ - (((lr) & GICH_LR_PHYSID_CPUID) >> GICH_LR_PHYSID_CPUID_SHIFT) -#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_cpu->vgic_irq_lr_map[irq] = LR_EMPTY; - clear_bit(lr, vgic_cpu->lr_used); - vgic_cpu->vgic_lr[lr] &= ~GICH_LR_STATE; - 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; -} - -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 (!irqchip_in_kernel(vcpu->kvm)) - return 0; - - 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; - } - - 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); - - if (of_address_to_resource(vgic_node, 3, &vcpu_res)) { - kvm_err("Cannot obtain VCPU resource\n"); - ret = -ENXIO; - goto out_unmap; - } - vgic_vcpu_base = vcpu_res.start; - - 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; -} - -int kvm_vgic_init(struct kvm *kvm) -{ - int ret = 0, i; - - 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_timer_init(kvm); - kvm->arch.vgic.ready = true; -out: - mutex_unlock(&kvm->lock); - return ret; -} - -int kvm_vgic_create(struct kvm *kvm) -{ - int ret = 0; - - mutex_lock(&kvm->lock); - - if (atomic_read(&kvm->online_vcpus) || kvm->arch.vgic.vctrl_base) { - ret = -EEXIST; - goto out; - } - - 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: - 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 (!IS_VGIC_ADDR_UNDEF(*ioaddr)) - return -EEXIST; - if (addr + size < addr) - return -EINVAL; - - ret = vgic_ioaddr_overlap(kvm); - if (ret) - return ret; - *ioaddr = addr; - return ret; -} - -int kvm_vgic_set_addr(struct kvm *kvm, unsigned long type, u64 addr) -{ - int r = 0; - struct vgic_dist *vgic = &kvm->arch.vgic; - - if (addr & ~KVM_PHYS_MASK) - return -E2BIG; - - if (addr & (SZ_4K - 1)) - return -EINVAL; - - mutex_lock(&kvm->lock); - switch (type) { - case KVM_VGIC_V2_ADDR_TYPE_DIST: - r = vgic_ioaddr_assign(kvm, &vgic->vgic_dist_base, - addr, KVM_VGIC_V2_DIST_SIZE); - break; - case KVM_VGIC_V2_ADDR_TYPE_CPU: - r = vgic_ioaddr_assign(kvm, &vgic->vgic_cpu_base, - addr, KVM_VGIC_V2_CPU_SIZE); - break; - default: - r = -ENODEV; - } - - mutex_unlock(&kvm->lock); - return r; -} diff --git a/virt/kvm/assigned-dev.c b/virt/kvm/assigned-dev.c deleted file mode 100644 index 8db43701016f..000000000000 --- a/virt/kvm/assigned-dev.c +++ /dev/null @@ -1,1023 +0,0 @@ -/* - * Kernel-based Virtual Machine - device assignment support - * - * Copyright (C) 2010 Red Hat, Inc. and/or its affiliates. - * - * This work is licensed under the terms of the GNU GPL, version 2. See - * the COPYING file in the top-level directory. - * - */ - -#include <linux/kvm_host.h> -#include <linux/kvm.h> -#include <linux/uaccess.h> -#include <linux/vmalloc.h> -#include <linux/errno.h> -#include <linux/spinlock.h> -#include <linux/pci.h> -#include <linux/interrupt.h> -#include <linux/slab.h> -#include <linux/namei.h> -#include <linux/fs.h> -#include "irq.h" - -static struct kvm_assigned_dev_kernel *kvm_find_assigned_dev(struct list_head *head, - int assigned_dev_id) -{ - struct list_head *ptr; - struct kvm_assigned_dev_kernel *match; - - list_for_each(ptr, head) { - match = list_entry(ptr, struct kvm_assigned_dev_kernel, list); - if (match->assigned_dev_id == assigned_dev_id) - return match; - } - return NULL; -} - -static int find_index_from_host_irq(struct kvm_assigned_dev_kernel - *assigned_dev, int irq) -{ - int i, index; - struct msix_entry *host_msix_entries; - - host_msix_entries = assigned_dev->host_msix_entries; - - index = -1; - for (i = 0; i < assigned_dev->entries_nr; i++) - if (irq == host_msix_entries[i].vector) { - index = i; - break; - } - if (index < 0) - printk(KERN_WARNING "Fail to find correlated MSI-X entry!\n"); - - return index; -} - -static irqreturn_t kvm_assigned_dev_intx(int irq, void *dev_id) -{ - struct kvm_assigned_dev_kernel *assigned_dev = dev_id; - int ret; - - spin_lock(&assigned_dev->intx_lock); - if (pci_check_and_mask_intx(assigned_dev->dev)) { - assigned_dev->host_irq_disabled = true; - ret = IRQ_WAKE_THREAD; - } else - ret = IRQ_NONE; - spin_unlock(&assigned_dev->intx_lock); - - return ret; -} - -static void -kvm_assigned_dev_raise_guest_irq(struct kvm_assigned_dev_kernel *assigned_dev, - int vector) -{ - if (unlikely(assigned_dev->irq_requested_type & - KVM_DEV_IRQ_GUEST_INTX)) { - 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, - false); - spin_unlock(&assigned_dev->intx_mask_lock); - } else - kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id, - vector, 1, false); -} - -static irqreturn_t kvm_assigned_dev_thread_intx(int irq, void *dev_id) -{ - struct kvm_assigned_dev_kernel *assigned_dev = dev_id; - - if (!(assigned_dev->flags & KVM_DEV_ASSIGN_PCI_2_3)) { - spin_lock_irq(&assigned_dev->intx_lock); - disable_irq_nosync(irq); - assigned_dev->host_irq_disabled = true; - spin_unlock_irq(&assigned_dev->intx_lock); - } - - kvm_assigned_dev_raise_guest_irq(assigned_dev, - assigned_dev->guest_irq); - - return IRQ_HANDLED; -} - -#ifdef __KVM_HAVE_MSI -static irqreturn_t kvm_assigned_dev_msi(int irq, void *dev_id) -{ - struct kvm_assigned_dev_kernel *assigned_dev = dev_id; - int ret = kvm_set_irq_inatomic(assigned_dev->kvm, - assigned_dev->irq_source_id, - assigned_dev->guest_irq, 1); - return unlikely(ret == -EWOULDBLOCK) ? IRQ_WAKE_THREAD : IRQ_HANDLED; -} - -static irqreturn_t kvm_assigned_dev_thread_msi(int irq, void *dev_id) -{ - struct kvm_assigned_dev_kernel *assigned_dev = dev_id; - - kvm_assigned_dev_raise_guest_irq(assigned_dev, - assigned_dev->guest_irq); - - return IRQ_HANDLED; -} -#endif - -#ifdef __KVM_HAVE_MSIX -static irqreturn_t kvm_assigned_dev_msix(int irq, void *dev_id) -{ - struct kvm_assigned_dev_kernel *assigned_dev = dev_id; - int index = find_index_from_host_irq(assigned_dev, irq); - u32 vector; - int ret = 0; - - if (index >= 0) { - vector = assigned_dev->guest_msix_entries[index].vector; - ret = kvm_set_irq_inatomic(assigned_dev->kvm, - assigned_dev->irq_source_id, - vector, 1); - } - - return unlikely(ret == -EWOULDBLOCK) ? IRQ_WAKE_THREAD : IRQ_HANDLED; -} - -static irqreturn_t kvm_assigned_dev_thread_msix(int irq, void *dev_id) -{ - struct kvm_assigned_dev_kernel *assigned_dev = dev_id; - int index = find_index_from_host_irq(assigned_dev, irq); - u32 vector; - - if (index >= 0) { - vector = assigned_dev->guest_msix_entries[index].vector; - kvm_assigned_dev_raise_guest_irq(assigned_dev, vector); - } - - return IRQ_HANDLED; -} -#endif - -/* Ack the irq line for an assigned device */ -static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian) -{ - struct kvm_assigned_dev_kernel *dev = - container_of(kian, struct kvm_assigned_dev_kernel, - ack_notifier); - - kvm_set_irq(dev->kvm, dev->irq_source_id, dev->guest_irq, 0, false); - - spin_lock(&dev->intx_mask_lock); - - if (!(dev->flags & KVM_DEV_ASSIGN_MASK_INTX)) { - bool reassert = false; - - spin_lock_irq(&dev->intx_lock); - /* - * The guest IRQ may be shared so this ack can come from an - * IRQ for another guest device. - */ - if (dev->host_irq_disabled) { - if (!(dev->flags & KVM_DEV_ASSIGN_PCI_2_3)) - enable_irq(dev->host_irq); - else if (!pci_check_and_unmask_intx(dev->dev)) - reassert = true; - dev->host_irq_disabled = reassert; - } - spin_unlock_irq(&dev->intx_lock); - - if (reassert) - kvm_set_irq(dev->kvm, dev->irq_source_id, - dev->guest_irq, 1, false); - } - - spin_unlock(&dev->intx_mask_lock); -} - -static void deassign_guest_irq(struct kvm *kvm, - struct kvm_assigned_dev_kernel *assigned_dev) -{ - if (assigned_dev->ack_notifier.gsi != -1) - kvm_unregister_irq_ack_notifier(kvm, - &assigned_dev->ack_notifier); - - kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id, - assigned_dev->guest_irq, 0, false); - - if (assigned_dev->irq_source_id != -1) - kvm_free_irq_source_id(kvm, assigned_dev->irq_source_id); - assigned_dev->irq_source_id = -1; - assigned_dev->irq_requested_type &= ~(KVM_DEV_IRQ_GUEST_MASK); -} - -/* The function implicit hold kvm->lock mutex due to cancel_work_sync() */ -static void deassign_host_irq(struct kvm *kvm, - struct kvm_assigned_dev_kernel *assigned_dev) -{ - /* - * We disable irq here to prevent further events. - * - * Notice this maybe result in nested disable if the interrupt type is - * INTx, but it's OK for we are going to free it. - * - * If this function is a part of VM destroy, please ensure that till - * now, the kvm state is still legal for probably we also have to wait - * on a currently running IRQ handler. - */ - if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) { - int i; - for (i = 0; i < assigned_dev->entries_nr; i++) - disable_irq(assigned_dev->host_msix_entries[i].vector); - - for (i = 0; i < assigned_dev->entries_nr; i++) - free_irq(assigned_dev->host_msix_entries[i].vector, - assigned_dev); - - assigned_dev->entries_nr = 0; - kfree(assigned_dev->host_msix_entries); - kfree(assigned_dev->guest_msix_entries); - pci_disable_msix(assigned_dev->dev); - } else { - /* Deal with MSI and INTx */ - if ((assigned_dev->irq_requested_type & - KVM_DEV_IRQ_HOST_INTX) && - (assigned_dev->flags & KVM_DEV_ASSIGN_PCI_2_3)) { - spin_lock_irq(&assigned_dev->intx_lock); - pci_intx(assigned_dev->dev, false); - spin_unlock_irq(&assigned_dev->intx_lock); - synchronize_irq(assigned_dev->host_irq); - } else - disable_irq(assigned_dev->host_irq); - - free_irq(assigned_dev->host_irq, assigned_dev); - - if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSI) - pci_disable_msi(assigned_dev->dev); - } - - assigned_dev->irq_requested_type &= ~(KVM_DEV_IRQ_HOST_MASK); -} - -static int kvm_deassign_irq(struct kvm *kvm, - struct kvm_assigned_dev_kernel *assigned_dev, - unsigned long irq_requested_type) -{ - unsigned long guest_irq_type, host_irq_type; - - if (!irqchip_in_kernel(kvm)) - return -EINVAL; - /* no irq assignment to deassign */ - if (!assigned_dev->irq_requested_type) - return -ENXIO; - - host_irq_type = irq_requested_type & KVM_DEV_IRQ_HOST_MASK; - guest_irq_type = irq_requested_type & KVM_DEV_IRQ_GUEST_MASK; - - if (host_irq_type) - deassign_host_irq(kvm, assigned_dev); - if (guest_irq_type) - deassign_guest_irq(kvm, assigned_dev); - - return 0; -} - -static void kvm_free_assigned_irq(struct kvm *kvm, - struct kvm_assigned_dev_kernel *assigned_dev) -{ - kvm_deassign_irq(kvm, assigned_dev, assigned_dev->irq_requested_type); -} - -static void kvm_free_assigned_device(struct kvm *kvm, - struct kvm_assigned_dev_kernel - *assigned_dev) -{ - kvm_free_assigned_irq(kvm, assigned_dev); - - pci_reset_function(assigned_dev->dev); - if (pci_load_and_free_saved_state(assigned_dev->dev, - &assigned_dev->pci_saved_state)) - printk(KERN_INFO "%s: Couldn't reload %s saved state\n", - __func__, dev_name(&assigned_dev->dev->dev)); - else - pci_restore_state(assigned_dev->dev); - - assigned_dev->dev->dev_flags &= ~PCI_DEV_FLAGS_ASSIGNED; - - pci_release_regions(assigned_dev->dev); - pci_disable_device(assigned_dev->dev); - pci_dev_put(assigned_dev->dev); - - list_del(&assigned_dev->list); - kfree(assigned_dev); -} - -void kvm_free_all_assigned_devices(struct kvm *kvm) -{ - struct list_head *ptr, *ptr2; - struct kvm_assigned_dev_kernel *assigned_dev; - - list_for_each_safe(ptr, ptr2, &kvm->arch.assigned_dev_head) { - assigned_dev = list_entry(ptr, - struct kvm_assigned_dev_kernel, - list); - - kvm_free_assigned_device(kvm, assigned_dev); - } -} - -static int assigned_device_enable_host_intx(struct kvm *kvm, - struct kvm_assigned_dev_kernel *dev) -{ - irq_handler_t irq_handler; - unsigned long flags; - - dev->host_irq = dev->dev->irq; - - /* - * We can only share the IRQ line with other host devices if we are - * able to disable the IRQ source at device-level - independently of - * the guest driver. Otherwise host devices may suffer from unbounded - * IRQ latencies when the guest keeps the line asserted. - */ - if (dev->flags & KVM_DEV_ASSIGN_PCI_2_3) { - irq_handler = kvm_assigned_dev_intx; - flags = IRQF_SHARED; - } else { - irq_handler = NULL; - flags = IRQF_ONESHOT; - } - if (request_threaded_irq(dev->host_irq, irq_handler, - kvm_assigned_dev_thread_intx, flags, - dev->irq_name, dev)) - return -EIO; - - if (dev->flags & KVM_DEV_ASSIGN_PCI_2_3) { - spin_lock_irq(&dev->intx_lock); - pci_intx(dev->dev, true); - spin_unlock_irq(&dev->intx_lock); - } - return 0; -} - -#ifdef __KVM_HAVE_MSI -static int assigned_device_enable_host_msi(struct kvm *kvm, - struct kvm_assigned_dev_kernel *dev) -{ - int r; - - if (!dev->dev->msi_enabled) { - r = pci_enable_msi(dev->dev); - if (r) - return r; - } - - dev->host_irq = dev->dev->irq; - if (request_threaded_irq(dev->host_irq, kvm_assigned_dev_msi, - kvm_assigned_dev_thread_msi, 0, - dev->irq_name, dev)) { - pci_disable_msi(dev->dev); - return -EIO; - } - - return 0; -} -#endif - -#ifdef __KVM_HAVE_MSIX -static int assigned_device_enable_host_msix(struct kvm *kvm, - struct kvm_assigned_dev_kernel *dev) -{ - int i, r = -EINVAL; - - /* host_msix_entries and guest_msix_entries should have been - * initialized */ - if (dev->entries_nr == 0) - return r; - - r = pci_enable_msix(dev->dev, dev->host_msix_entries, dev->entries_nr); - if (r) - return r; - - for (i = 0; i < dev->entries_nr; i++) { - r = request_threaded_irq(dev->host_msix_entries[i].vector, - kvm_assigned_dev_msix, - kvm_assigned_dev_thread_msix, - 0, dev->irq_name, dev); - if (r) - goto err; - } - - return 0; -err: - for (i -= 1; i >= 0; i--) - free_irq(dev->host_msix_entries[i].vector, dev); - pci_disable_msix(dev->dev); - return r; -} - -#endif - -static int assigned_device_enable_guest_intx(struct kvm *kvm, - struct kvm_assigned_dev_kernel *dev, - struct kvm_assigned_irq *irq) -{ - dev->guest_irq = irq->guest_irq; - dev->ack_notifier.gsi = irq->guest_irq; - return 0; -} - -#ifdef __KVM_HAVE_MSI -static int assigned_device_enable_guest_msi(struct kvm *kvm, - struct kvm_assigned_dev_kernel *dev, - struct kvm_assigned_irq *irq) -{ - dev->guest_irq = irq->guest_irq; - dev->ack_notifier.gsi = -1; - return 0; -} -#endif - -#ifdef __KVM_HAVE_MSIX -static int assigned_device_enable_guest_msix(struct kvm *kvm, - struct kvm_assigned_dev_kernel *dev, - struct kvm_assigned_irq *irq) -{ - dev->guest_irq = irq->guest_irq; - dev->ack_notifier.gsi = -1; - return 0; -} -#endif - -static int assign_host_irq(struct kvm *kvm, - struct kvm_assigned_dev_kernel *dev, - __u32 host_irq_type) -{ - int r = -EEXIST; - - if (dev->irq_requested_type & KVM_DEV_IRQ_HOST_MASK) - return r; - - snprintf(dev->irq_name, sizeof(dev->irq_name), "kvm:%s", - pci_name(dev->dev)); - - switch (host_irq_type) { - case KVM_DEV_IRQ_HOST_INTX: - r = assigned_device_enable_host_intx(kvm, dev); - break; -#ifdef __KVM_HAVE_MSI - case KVM_DEV_IRQ_HOST_MSI: - r = assigned_device_enable_host_msi(kvm, dev); - break; -#endif -#ifdef __KVM_HAVE_MSIX - case KVM_DEV_IRQ_HOST_MSIX: - r = assigned_device_enable_host_msix(kvm, dev); - break; -#endif - default: - r = -EINVAL; - } - dev->host_irq_disabled = false; - - if (!r) - dev->irq_requested_type |= host_irq_type; - - return r; -} - -static int assign_guest_irq(struct kvm *kvm, - struct kvm_assigned_dev_kernel *dev, - struct kvm_assigned_irq *irq, - unsigned long guest_irq_type) -{ - int id; - int r = -EEXIST; - - if (dev->irq_requested_type & KVM_DEV_IRQ_GUEST_MASK) - return r; - - id = kvm_request_irq_source_id(kvm); - if (id < 0) - return id; - - dev->irq_source_id = id; - - switch (guest_irq_type) { - case KVM_DEV_IRQ_GUEST_INTX: - r = assigned_device_enable_guest_intx(kvm, dev, irq); - break; -#ifdef __KVM_HAVE_MSI - case KVM_DEV_IRQ_GUEST_MSI: - r = assigned_device_enable_guest_msi(kvm, dev, irq); - break; -#endif -#ifdef __KVM_HAVE_MSIX - case KVM_DEV_IRQ_GUEST_MSIX: - r = assigned_device_enable_guest_msix(kvm, dev, irq); - break; -#endif - default: - r = -EINVAL; - } - - if (!r) { - dev->irq_requested_type |= guest_irq_type; - if (dev->ack_notifier.gsi != -1) - kvm_register_irq_ack_notifier(kvm, &dev->ack_notifier); - } else - kvm_free_irq_source_id(kvm, dev->irq_source_id); - - return r; -} - -/* TODO Deal with KVM_DEV_IRQ_ASSIGNED_MASK_MSIX */ -static int kvm_vm_ioctl_assign_irq(struct kvm *kvm, - struct kvm_assigned_irq *assigned_irq) -{ - int r = -EINVAL; - struct kvm_assigned_dev_kernel *match; - unsigned long host_irq_type, guest_irq_type; - - if (!irqchip_in_kernel(kvm)) - return r; - - mutex_lock(&kvm->lock); - r = -ENODEV; - match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, - assigned_irq->assigned_dev_id); - if (!match) - goto out; - - host_irq_type = (assigned_irq->flags & KVM_DEV_IRQ_HOST_MASK); - guest_irq_type = (assigned_irq->flags & KVM_DEV_IRQ_GUEST_MASK); - - r = -EINVAL; - /* can only assign one type at a time */ - if (hweight_long(host_irq_type) > 1) - goto out; - if (hweight_long(guest_irq_type) > 1) - goto out; - if (host_irq_type == 0 && guest_irq_type == 0) - goto out; - - r = 0; - if (host_irq_type) - r = assign_host_irq(kvm, match, host_irq_type); - if (r) - goto out; - - if (guest_irq_type) - r = assign_guest_irq(kvm, match, assigned_irq, guest_irq_type); -out: - mutex_unlock(&kvm->lock); - return r; -} - -static int kvm_vm_ioctl_deassign_dev_irq(struct kvm *kvm, - struct kvm_assigned_irq - *assigned_irq) -{ - int r = -ENODEV; - struct kvm_assigned_dev_kernel *match; - unsigned long irq_type; - - mutex_lock(&kvm->lock); - - match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, - assigned_irq->assigned_dev_id); - if (!match) - goto out; - - irq_type = assigned_irq->flags & (KVM_DEV_IRQ_HOST_MASK | - KVM_DEV_IRQ_GUEST_MASK); - r = kvm_deassign_irq(kvm, match, irq_type); -out: - mutex_unlock(&kvm->lock); - return r; -} - -/* - * We want to test whether the caller has been granted permissions to - * use this device. To be able to configure and control the device, - * the user needs access to PCI configuration space and BAR resources. - * These are accessed through PCI sysfs. PCI config space is often - * passed to the process calling this ioctl via file descriptor, so we - * can't rely on access to that file. We can check for permissions - * on each of the BAR resource files, which is a pretty clear - * indicator that the user has been granted access to the device. - */ -static int probe_sysfs_permissions(struct pci_dev *dev) -{ -#ifdef CONFIG_SYSFS - int i; - bool bar_found = false; - - for (i = PCI_STD_RESOURCES; i <= PCI_STD_RESOURCE_END; i++) { - char *kpath, *syspath; - struct path path; - struct inode *inode; - int r; - - if (!pci_resource_len(dev, i)) - continue; - - kpath = kobject_get_path(&dev->dev.kobj, GFP_KERNEL); - if (!kpath) - return -ENOMEM; - - /* Per sysfs-rules, sysfs is always at /sys */ - syspath = kasprintf(GFP_KERNEL, "/sys%s/resource%d", kpath, i); - kfree(kpath); - if (!syspath) - return -ENOMEM; - - r = kern_path(syspath, LOOKUP_FOLLOW, &path); - kfree(syspath); - if (r) - return r; - - inode = path.dentry->d_inode; - - r = inode_permission(inode, MAY_READ | MAY_WRITE | MAY_ACCESS); - path_put(&path); - if (r) - return r; - - bar_found = true; - } - - /* If no resources, probably something special */ - if (!bar_found) - return -EPERM; - - return 0; -#else - return -EINVAL; /* No way to control the device without sysfs */ -#endif -} - -static int kvm_vm_ioctl_assign_device(struct kvm *kvm, - struct kvm_assigned_pci_dev *assigned_dev) -{ - int r = 0, idx; - struct kvm_assigned_dev_kernel *match; - struct pci_dev *dev; - - if (!(assigned_dev->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU)) - return -EINVAL; - - mutex_lock(&kvm->lock); - idx = srcu_read_lock(&kvm->srcu); - - match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, - assigned_dev->assigned_dev_id); - if (match) { - /* device already assigned */ - r = -EEXIST; - goto out; - } - - match = kzalloc(sizeof(struct kvm_assigned_dev_kernel), GFP_KERNEL); - if (match == NULL) { - printk(KERN_INFO "%s: Couldn't allocate memory\n", - __func__); - r = -ENOMEM; - goto out; - } - dev = pci_get_domain_bus_and_slot(assigned_dev->segnr, - assigned_dev->busnr, - assigned_dev->devfn); - if (!dev) { - printk(KERN_INFO "%s: host device not found\n", __func__); - r = -EINVAL; - goto out_free; - } - - /* Don't allow bridges to be assigned */ - if (dev->hdr_type != PCI_HEADER_TYPE_NORMAL) { - r = -EPERM; - goto out_put; - } - - r = probe_sysfs_permissions(dev); - if (r) - goto out_put; - - if (pci_enable_device(dev)) { - printk(KERN_INFO "%s: Could not enable PCI device\n", __func__); - r = -EBUSY; - goto out_put; - } - r = pci_request_regions(dev, "kvm_assigned_device"); - if (r) { - printk(KERN_INFO "%s: Could not get access to device regions\n", - __func__); - goto out_disable; - } - - pci_reset_function(dev); - pci_save_state(dev); - match->pci_saved_state = pci_store_saved_state(dev); - if (!match->pci_saved_state) - printk(KERN_DEBUG "%s: Couldn't store %s saved state\n", - __func__, dev_name(&dev->dev)); - - if (!pci_intx_mask_supported(dev)) - assigned_dev->flags &= ~KVM_DEV_ASSIGN_PCI_2_3; - - match->assigned_dev_id = assigned_dev->assigned_dev_id; - match->host_segnr = assigned_dev->segnr; - match->host_busnr = assigned_dev->busnr; - match->host_devfn = assigned_dev->devfn; - match->flags = assigned_dev->flags; - match->dev = dev; - spin_lock_init(&match->intx_lock); - spin_lock_init(&match->intx_mask_lock); - match->irq_source_id = -1; - match->kvm = kvm; - match->ack_notifier.irq_acked = kvm_assigned_dev_ack_irq; - - list_add(&match->list, &kvm->arch.assigned_dev_head); - - if (!kvm->arch.iommu_domain) { - r = kvm_iommu_map_guest(kvm); - if (r) - goto out_list_del; - } - r = kvm_assign_device(kvm, match); - if (r) - goto out_list_del; - -out: - srcu_read_unlock(&kvm->srcu, idx); - mutex_unlock(&kvm->lock); - return r; -out_list_del: - if (pci_load_and_free_saved_state(dev, &match->pci_saved_state)) - printk(KERN_INFO "%s: Couldn't reload %s saved state\n", - __func__, dev_name(&dev->dev)); - list_del(&match->list); - pci_release_regions(dev); -out_disable: - pci_disable_device(dev); -out_put: - pci_dev_put(dev); -out_free: - kfree(match); - srcu_read_unlock(&kvm->srcu, idx); - mutex_unlock(&kvm->lock); - return r; -} - -static int kvm_vm_ioctl_deassign_device(struct kvm *kvm, - struct kvm_assigned_pci_dev *assigned_dev) -{ - int r = 0; - struct kvm_assigned_dev_kernel *match; - - mutex_lock(&kvm->lock); - - match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, - assigned_dev->assigned_dev_id); - if (!match) { - printk(KERN_INFO "%s: device hasn't been assigned before, " - "so cannot be deassigned\n", __func__); - r = -EINVAL; - goto out; - } - - kvm_deassign_device(kvm, match); - - kvm_free_assigned_device(kvm, match); - -out: - mutex_unlock(&kvm->lock); - return r; -} - - -#ifdef __KVM_HAVE_MSIX -static int kvm_vm_ioctl_set_msix_nr(struct kvm *kvm, - struct kvm_assigned_msix_nr *entry_nr) -{ - int r = 0; - struct kvm_assigned_dev_kernel *adev; - - mutex_lock(&kvm->lock); - - adev = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, - entry_nr->assigned_dev_id); - if (!adev) { - r = -EINVAL; - goto msix_nr_out; - } - - if (adev->entries_nr == 0) { - adev->entries_nr = entry_nr->entry_nr; - if (adev->entries_nr == 0 || - adev->entries_nr > KVM_MAX_MSIX_PER_DEV) { - r = -EINVAL; - goto msix_nr_out; - } - - adev->host_msix_entries = kzalloc(sizeof(struct msix_entry) * - entry_nr->entry_nr, - GFP_KERNEL); - if (!adev->host_msix_entries) { - r = -ENOMEM; - goto msix_nr_out; - } - adev->guest_msix_entries = - kzalloc(sizeof(struct msix_entry) * entry_nr->entry_nr, - GFP_KERNEL); - if (!adev->guest_msix_entries) { - kfree(adev->host_msix_entries); - r = -ENOMEM; - goto msix_nr_out; - } - } else /* Not allowed set MSI-X number twice */ - r = -EINVAL; -msix_nr_out: - mutex_unlock(&kvm->lock); - return r; -} - -static int kvm_vm_ioctl_set_msix_entry(struct kvm *kvm, - struct kvm_assigned_msix_entry *entry) -{ - int r = 0, i; - struct kvm_assigned_dev_kernel *adev; - - mutex_lock(&kvm->lock); - - adev = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, - entry->assigned_dev_id); - - if (!adev) { - r = -EINVAL; - goto msix_entry_out; - } - - for (i = 0; i < adev->entries_nr; i++) - if (adev->guest_msix_entries[i].vector == 0 || - adev->guest_msix_entries[i].entry == entry->entry) { - adev->guest_msix_entries[i].entry = entry->entry; - adev->guest_msix_entries[i].vector = entry->gsi; - adev->host_msix_entries[i].entry = entry->entry; - break; - } - if (i == adev->entries_nr) { - r = -ENOSPC; - goto msix_entry_out; - } - -msix_entry_out: - mutex_unlock(&kvm->lock); - - return r; -} -#endif - -static int kvm_vm_ioctl_set_pci_irq_mask(struct kvm *kvm, - struct kvm_assigned_pci_dev *assigned_dev) -{ - int r = 0; - struct kvm_assigned_dev_kernel *match; - - mutex_lock(&kvm->lock); - - match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, - assigned_dev->assigned_dev_id); - if (!match) { - r = -ENODEV; - goto out; - } - - spin_lock(&match->intx_mask_lock); - - match->flags &= ~KVM_DEV_ASSIGN_MASK_INTX; - match->flags |= assigned_dev->flags & KVM_DEV_ASSIGN_MASK_INTX; - - 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, false); - /* - * Masking at hardware-level is performed on demand, - * i.e. when an IRQ actually arrives at the host. - */ - } else if (!(assigned_dev->flags & KVM_DEV_ASSIGN_PCI_2_3)) { - /* - * Unmask the IRQ line if required. Unmasking at - * device level will be performed by user space. - */ - spin_lock_irq(&match->intx_lock); - if (match->host_irq_disabled) { - enable_irq(match->host_irq); - match->host_irq_disabled = false; - } - spin_unlock_irq(&match->intx_lock); - } - } - - spin_unlock(&match->intx_mask_lock); - -out: - mutex_unlock(&kvm->lock); - return r; -} - -long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl, - unsigned long arg) -{ - void __user *argp = (void __user *)arg; - int r; - - switch (ioctl) { - case KVM_ASSIGN_PCI_DEVICE: { - struct kvm_assigned_pci_dev assigned_dev; - - r = -EFAULT; - if (copy_from_user(&assigned_dev, argp, sizeof assigned_dev)) - goto out; - r = kvm_vm_ioctl_assign_device(kvm, &assigned_dev); - if (r) - goto out; - break; - } - case KVM_ASSIGN_IRQ: { - r = -EOPNOTSUPP; - break; - } - case KVM_ASSIGN_DEV_IRQ: { - struct kvm_assigned_irq assigned_irq; - - r = -EFAULT; - if (copy_from_user(&assigned_irq, argp, sizeof assigned_irq)) - goto out; - r = kvm_vm_ioctl_assign_irq(kvm, &assigned_irq); - if (r) - goto out; - break; - } - case KVM_DEASSIGN_DEV_IRQ: { - struct kvm_assigned_irq assigned_irq; - - r = -EFAULT; - if (copy_from_user(&assigned_irq, argp, sizeof assigned_irq)) - goto out; - r = kvm_vm_ioctl_deassign_dev_irq(kvm, &assigned_irq); - if (r) - goto out; - break; - } - case KVM_DEASSIGN_PCI_DEVICE: { - struct kvm_assigned_pci_dev assigned_dev; - - r = -EFAULT; - if (copy_from_user(&assigned_dev, argp, sizeof assigned_dev)) - goto out; - r = kvm_vm_ioctl_deassign_device(kvm, &assigned_dev); - if (r) - goto out; - break; - } -#ifdef __KVM_HAVE_MSIX - case KVM_ASSIGN_SET_MSIX_NR: { - struct kvm_assigned_msix_nr entry_nr; - r = -EFAULT; - if (copy_from_user(&entry_nr, argp, sizeof entry_nr)) - goto out; - r = kvm_vm_ioctl_set_msix_nr(kvm, &entry_nr); - if (r) - goto out; - break; - } - case KVM_ASSIGN_SET_MSIX_ENTRY: { - struct kvm_assigned_msix_entry entry; - r = -EFAULT; - if (copy_from_user(&entry, argp, sizeof entry)) - goto out; - r = kvm_vm_ioctl_set_msix_entry(kvm, &entry); - if (r) - goto out; - break; - } -#endif - case KVM_ASSIGN_SET_INTX_MASK: { - struct kvm_assigned_pci_dev assigned_dev; - - r = -EFAULT; - if (copy_from_user(&assigned_dev, argp, sizeof assigned_dev)) - goto out; - r = kvm_vm_ioctl_set_pci_irq_mask(kvm, &assigned_dev); - break; - } - default: - r = -ENOTTY; - break; - } -out: - return r; -} diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c index ea475cd03511..b8aaa96b799b 100644 --- a/virt/kvm/async_pf.c +++ b/virt/kvm/async_pf.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * kvm asynchronous fault support * @@ -5,25 +6,13 @@ * * Author: * Gleb Natapov <gleb@redhat.com> - * - * This file is free software; you can redistribute it and/or modify - * it under the terms of version 2 of the GNU General Public License - * 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., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301, USA. */ #include <linux/kvm_host.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/mmu_context.h> +#include <linux/sched/mm.h> #include "async_pf.h" #include <trace/events/kvm.h> @@ -42,8 +31,7 @@ int kvm_async_pf_init(void) void kvm_async_pf_deinit(void) { - if (async_pf_cache) - kmem_cache_destroy(async_pf_cache); + kmem_cache_destroy(async_pf_cache); async_pf_cache = NULL; } @@ -56,40 +44,77 @@ 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; struct kvm_vcpu *vcpu = apf->vcpu; + struct mm_struct *mm = vcpu->kvm->mm; unsigned long addr = apf->addr; - gva_t gva = apf->gva; + gpa_t cr2_or_gpa = apf->cr2_or_gpa; + int locked = 1; + bool first; might_sleep(); - use_mm(mm); - down_read(&mm->mmap_sem); - get_user_pages(current, mm, addr, 1, 1, 0, &page, NULL); - up_read(&mm->mmap_sem); - unuse_mm(mm); + /* + * Attempt to pin the VM's host address space, and simply skip gup() if + * acquiring a pin fail, i.e. if the process is exiting. Note, KVM + * holds a reference to its associated mm_struct until the very end of + * kvm_destroy_vm(), i.e. the struct itself won't be freed before this + * work item is fully processed. + */ + if (mmget_not_zero(mm)) { + mmap_read_lock(mm); + get_user_pages_remote(mm, addr, 1, FOLL_WRITE, NULL, &locked); + if (locked) + mmap_read_unlock(mm); + mmput(mm); + } + + /* + * Notify and kick the vCPU even if faulting in the page failed, e.g. + * so that the vCPU can retry the fault synchronously. + */ + if (IS_ENABLED(CONFIG_KVM_ASYNC_PF_SYNC)) + kvm_arch_async_page_present(vcpu, apf); spin_lock(&vcpu->async_pf.lock); + first = list_empty(&vcpu->async_pf.done); list_add_tail(&apf->link, &vcpu->async_pf.done); - apf->page = page; - apf->done = true; spin_unlock(&vcpu->async_pf.lock); /* - * apf may be freed by kvm_check_async_pf_completion() after - * this point + * The apf struct may be freed by kvm_check_async_pf_completion() as + * soon as the lock is dropped. Nullify it to prevent improper usage. */ + apf = NULL; + + if (!IS_ENABLED(CONFIG_KVM_ASYNC_PF_SYNC) && first) + kvm_arch_async_page_present_queued(vcpu); - trace_kvm_async_pf_completed(addr, page, gva); + trace_kvm_async_pf_completed(addr, cr2_or_gpa); - if (waitqueue_active(&vcpu->wq)) - wake_up_interruptible(&vcpu->wq); + __kvm_vcpu_wake_up(vcpu); +} - mmdrop(mm); - kvm_put_kvm(vcpu->kvm); +static void kvm_flush_and_free_async_pf_work(struct kvm_async_pf *work) +{ + /* + * The async #PF is "done", but KVM must wait for the work item itself, + * i.e. async_pf_execute(), to run to completion. If KVM is a module, + * KVM must ensure *no* code owned by the KVM (the module) can be run + * after the last call to module_put(). Note, flushing the work item + * is always required when the item is taken off the completion queue. + * E.g. even if the vCPU handles the item in the "normal" path, the VM + * could be terminated before async_pf_execute() completes. + * + * Wake all events skip the queue and go straight done, i.e. don't + * need to be flushed (but sanity check that the work wasn't queued). + */ + if (work->wakeup_all) + WARN_ON_ONCE(work->work.func); + else + flush_work(&work->work); + kmem_cache_free(async_pf_cache, work); } void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu) @@ -97,23 +122,28 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu) /* cancel outstanding work queue item */ while (!list_empty(&vcpu->async_pf.queue)) { struct kvm_async_pf *work = - list_entry(vcpu->async_pf.queue.next, - typeof(*work), queue); - cancel_work_sync(&work->work); + list_first_entry(&vcpu->async_pf.queue, + typeof(*work), queue); 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)) kmem_cache_free(async_pf_cache, work); +#endif } spin_lock(&vcpu->async_pf.lock); while (!list_empty(&vcpu->async_pf.done)) { struct kvm_async_pf *work = - list_entry(vcpu->async_pf.done.next, - typeof(*work), link); + list_first_entry(&vcpu->async_pf.done, + 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); + kvm_flush_and_free_async_pf_work(work); + spin_lock(&vcpu->async_pf.lock); } spin_unlock(&vcpu->async_pf.lock); @@ -125,34 +155,38 @@ void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu) struct kvm_async_pf *work; while (!list_empty_careful(&vcpu->async_pf.done) && - kvm_arch_can_inject_async_page_present(vcpu)) { + kvm_arch_can_dequeue_async_page_present(vcpu)) { spin_lock(&vcpu->async_pf.lock); work = list_first_entry(&vcpu->async_pf.done, typeof(*work), link); 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); + if (!IS_ENABLED(CONFIG_KVM_ASYNC_PF_SYNC)) + kvm_arch_async_page_present(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); + kvm_flush_and_free_async_pf_work(work); } } -int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn, - struct kvm_arch_async_pf *arch) +/* + * Try to schedule a job to handle page fault asynchronously. Returns 'true' on + * success, 'false' on failure (page fault has to be handled synchronously). + */ +bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, + unsigned long hva, struct kvm_arch_async_pf *arch) { struct kvm_async_pf *work; if (vcpu->async_pf.queued >= ASYNC_PF_PER_VCPU) - return 0; + return false; - /* setup delayed work */ + /* Arch specific code should not do async PF in this case */ + if (unlikely(kvm_is_error_hva(hva))) + return false; /* * do alloc nowait since if we are going to sleep anyway we @@ -160,41 +194,29 @@ int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn, */ work = kmem_cache_zalloc(async_pf_cache, GFP_NOWAIT); if (!work) - return 0; + return false; - 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->cr2_or_gpa = cr2_or_gpa; + work->addr = hva; work->arch = *arch; - work->mm = current->mm; - atomic_inc(&work->mm->mm_count); - kvm_get_kvm(work->vcpu->kvm); - - /* this can't really happen otherwise gfn_to_pfn_async - would succeed */ - if (unlikely(kvm_is_error_hva(work->addr))) - goto retry_sync; INIT_WORK(&work->work, async_pf_execute); - if (!schedule_work(&work->work)) - goto retry_sync; list_add_tail(&work->queue, &vcpu->async_pf.queue); vcpu->async_pf.queued++; - kvm_arch_async_page_not_present(vcpu, work); - return 1; -retry_sync: - kvm_put_kvm(work->vcpu->kvm); - mmdrop(work->mm); - kmem_cache_free(async_pf_cache, work); - return 0; + work->notpresent_injected = kvm_arch_async_page_not_present(vcpu, work); + + schedule_work(&work->work); + + return true; } int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu) { struct kvm_async_pf *work; + bool first; if (!list_empty_careful(&vcpu->async_pf.done)) return 0; @@ -203,13 +225,17 @@ 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); + first = list_empty(&vcpu->async_pf.done); list_add_tail(&work->link, &vcpu->async_pf.done); spin_unlock(&vcpu->async_pf.lock); + if (!IS_ENABLED(CONFIG_KVM_ASYNC_PF_SYNC) && first) + kvm_arch_async_page_present_queued(vcpu); + vcpu->async_pf.queued++; return 0; } diff --git a/virt/kvm/async_pf.h b/virt/kvm/async_pf.h index e7ef6447cb82..90d1a7d8c6de 100644 --- a/virt/kvm/async_pf.h +++ b/virt/kvm/async_pf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * kvm asynchronous fault support * @@ -5,19 +6,6 @@ * * Author: * Gleb Natapov <gleb@redhat.com> - * - * This file is free software; you can redistribute it and/or modify - * it under the terms of version 2 of the GNU General Public License - * 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., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301, USA. */ #ifndef __KVM_ASYNC_PF_H__ @@ -29,8 +17,8 @@ void kvm_async_pf_deinit(void); void kvm_async_pf_vcpu_init(struct kvm_vcpu *vcpu); #else #define kvm_async_pf_init() (0) -#define kvm_async_pf_deinit() do{}while(0) -#define kvm_async_pf_vcpu_init(C) do{}while(0) +#define kvm_async_pf_deinit() do {} while (0) +#define kvm_async_pf_vcpu_init(C) do {} while (0) #endif #endif diff --git a/virt/kvm/binary_stats.c b/virt/kvm/binary_stats.c new file mode 100644 index 000000000000..eefca6c69f51 --- /dev/null +++ b/virt/kvm/binary_stats.c @@ -0,0 +1,144 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * KVM binary statistics interface implementation + * + * Copyright 2021 Google LLC + */ + +#include <linux/kvm_host.h> +#include <linux/kvm.h> +#include <linux/errno.h> +#include <linux/uaccess.h> + +/** + * kvm_stats_read() - Common function to read from the binary statistics + * file descriptor. + * + * @id: identification string of the stats + * @header: stats header for a vm or a vcpu + * @desc: start address of an array of stats descriptors for a vm or a vcpu + * @stats: start address of stats data block for a vm or a vcpu + * @size_stats: the size of stats data block pointed by @stats + * @user_buffer: start address of userspace buffer + * @size: requested read size from userspace + * @offset: the start position from which the content will be read for the + * corresponding vm or vcp file descriptor + * + * The file content of a vm/vcpu file descriptor is now defined as below: + * +-------------+ + * | Header | + * +-------------+ + * | id string | + * +-------------+ + * | Descriptors | + * +-------------+ + * | Stats Data | + * +-------------+ + * Although this function allows userspace to read any amount of data (as long + * as in the limit) from any position, the typical usage would follow below + * steps: + * 1. Read header from offset 0. Get the offset of descriptors and stats data + * and some other necessary information. This is a one-time work for the + * lifecycle of the corresponding vm/vcpu stats fd. + * 2. Read id string from its offset. This is a one-time work for the lifecycle + * of the corresponding vm/vcpu stats fd. + * 3. Read descriptors from its offset and discover all the stats by parsing + * descriptors. This is a one-time work for the lifecycle of the + * corresponding vm/vcpu stats fd. + * 4. Periodically read stats data from its offset using pread. + * + * Return: the number of bytes that has been successfully read + */ +ssize_t kvm_stats_read(char *id, const struct kvm_stats_header *header, + const struct _kvm_stats_desc *desc, + void *stats, size_t size_stats, + char __user *user_buffer, size_t size, loff_t *offset) +{ + ssize_t len; + ssize_t copylen; + ssize_t remain = size; + size_t size_desc; + size_t size_header; + void *src; + loff_t pos = *offset; + char __user *dest = user_buffer; + + size_header = sizeof(*header); + size_desc = header->num_desc * sizeof(*desc); + + len = KVM_STATS_NAME_SIZE + size_header + size_desc + size_stats - pos; + len = min(len, remain); + if (len <= 0) + return 0; + remain = len; + + /* + * Copy kvm stats header. + * The header is the first block of content userspace usually read out. + * The pos is 0 and the copylen and remain would be the size of header. + * The copy of the header would be skipped if offset is larger than the + * size of header. That usually happens when userspace reads stats + * descriptors and stats data. + */ + copylen = size_header - pos; + copylen = min(copylen, remain); + if (copylen > 0) { + src = (void *)header + pos; + if (copy_to_user(dest, src, copylen)) + return -EFAULT; + remain -= copylen; + pos += copylen; + dest += copylen; + } + + /* + * Copy kvm stats header id string. + * The id string is unique for every vm/vcpu, which is stored in kvm + * and kvm_vcpu structure. + * The id string is part of the stat header from the perspective of + * userspace, it is usually read out together with previous constant + * header part and could be skipped for later descriptors and stats + * data readings. + */ + copylen = header->id_offset + KVM_STATS_NAME_SIZE - pos; + copylen = min(copylen, remain); + if (copylen > 0) { + src = id + pos - header->id_offset; + if (copy_to_user(dest, src, copylen)) + return -EFAULT; + remain -= copylen; + pos += copylen; + dest += copylen; + } + + /* + * Copy kvm stats descriptors. + * The descriptors copy would be skipped in the typical case that + * userspace periodically read stats data, since the pos would be + * greater than the end address of descriptors + * (header->header.desc_offset + size_desc) causing copylen <= 0. + */ + copylen = header->desc_offset + size_desc - pos; + copylen = min(copylen, remain); + if (copylen > 0) { + src = (void *)desc + pos - header->desc_offset; + if (copy_to_user(dest, src, copylen)) + return -EFAULT; + remain -= copylen; + pos += copylen; + dest += copylen; + } + + /* Copy kvm stats values */ + copylen = header->data_offset + size_stats - pos; + copylen = min(copylen, remain); + if (copylen > 0) { + src = stats + pos - header->data_offset; + if (copy_to_user(dest, src, copylen)) + return -EFAULT; + pos += copylen; + } + + *offset = pos; + return len; +} diff --git a/virt/kvm/coalesced_mmio.c b/virt/kvm/coalesced_mmio.c index 88b2fe3ddf42..375d6285475e 100644 --- a/virt/kvm/coalesced_mmio.c +++ b/virt/kvm/coalesced_mmio.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * KVM coalesced MMIO * @@ -8,7 +9,7 @@ * */ -#include "iodev.h" +#include <kvm/iodev.h> #include <linux/kvm_host.h> #include <linux/slab.h> @@ -39,50 +40,40 @@ static int coalesced_mmio_in_range(struct kvm_coalesced_mmio_dev *dev, return 1; } -static int coalesced_mmio_has_room(struct kvm_coalesced_mmio_dev *dev) -{ - struct kvm_coalesced_mmio_ring *ring; - unsigned avail; - - /* Are we able to batch it ? */ - - /* last is the first free entry - * check if we don't meet the first used entry - * there is always one unused entry in the buffer - */ - ring = dev->kvm->coalesced_mmio_ring; - avail = (ring->first - ring->last - 1) % KVM_COALESCED_MMIO_MAX; - if (avail == 0) { - /* full */ - return 0; - } - - return 1; -} - -static int coalesced_mmio_write(struct kvm_io_device *this, - gpa_t addr, int len, const void *val) +static int coalesced_mmio_write(struct kvm_vcpu *vcpu, + struct kvm_io_device *this, gpa_t addr, + int len, const void *val) { struct kvm_coalesced_mmio_dev *dev = to_mmio(this); struct kvm_coalesced_mmio_ring *ring = dev->kvm->coalesced_mmio_ring; + __u32 insert; if (!coalesced_mmio_in_range(dev, addr, len)) return -EOPNOTSUPP; spin_lock(&dev->kvm->ring_lock); - if (!coalesced_mmio_has_room(dev)) { + /* + * last is the index of the entry to fill. Verify userspace hasn't + * set last to be out of range, and that there is room in the ring. + * Leave one entry free in the ring so that userspace can differentiate + * between an empty ring and a full ring. + */ + insert = READ_ONCE(ring->last); + if (insert >= KVM_COALESCED_MMIO_MAX || + (insert + 1) % KVM_COALESCED_MMIO_MAX == READ_ONCE(ring->first)) { spin_unlock(&dev->kvm->ring_lock); return -EOPNOTSUPP; } /* copy data in first free entry of the ring */ - ring->coalesced_mmio[ring->last].phys_addr = addr; - ring->coalesced_mmio[ring->last].len = len; - memcpy(ring->coalesced_mmio[ring->last].data, val, len); + ring->coalesced_mmio[insert].phys_addr = addr; + ring->coalesced_mmio[insert].len = len; + memcpy(ring->coalesced_mmio[insert].data, val, len); + ring->coalesced_mmio[insert].pio = dev->zone.pio; smp_wmb(); - ring->last = (ring->last + 1) % KVM_COALESCED_MMIO_MAX; + ring->last = (insert + 1) % KVM_COALESCED_MMIO_MAX; spin_unlock(&dev->kvm->ring_lock); return 0; } @@ -104,26 +95,22 @@ static const struct kvm_io_device_ops coalesced_mmio_ops = { int kvm_coalesced_mmio_init(struct kvm *kvm) { struct page *page; - int ret; - ret = -ENOMEM; - page = alloc_page(GFP_KERNEL | __GFP_ZERO); + page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!page) - goto out_err; + return -ENOMEM; - ret = 0; kvm->coalesced_mmio_ring = page_address(page); /* * We're using this spinlock to sync access to the coalesced ring. - * The list doesn't need it's own lock since device registration and + * The list doesn't need its own lock since device registration and * unregistration should only happen when kvm->slots_lock is held. */ spin_lock_init(&kvm->ring_lock); INIT_LIST_HEAD(&kvm->coalesced_zones); -out_err: - return ret; + return 0; } void kvm_coalesced_mmio_free(struct kvm *kvm) @@ -138,7 +125,11 @@ int kvm_vm_ioctl_register_coalesced_mmio(struct kvm *kvm, int ret; struct kvm_coalesced_mmio_dev *dev; - dev = kzalloc(sizeof(struct kvm_coalesced_mmio_dev), GFP_KERNEL); + if (zone->pio != 1 && zone->pio != 0) + return -EINVAL; + + dev = kzalloc(sizeof(struct kvm_coalesced_mmio_dev), + GFP_KERNEL_ACCOUNT); if (!dev) return -ENOMEM; @@ -147,40 +138,54 @@ int kvm_vm_ioctl_register_coalesced_mmio(struct kvm *kvm, dev->zone = *zone; mutex_lock(&kvm->slots_lock); - ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, zone->addr, - zone->size, &dev->dev); + ret = kvm_io_bus_register_dev(kvm, + zone->pio ? KVM_PIO_BUS : KVM_MMIO_BUS, + zone->addr, zone->size, &dev->dev); if (ret < 0) goto out_free_dev; 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, struct kvm_coalesced_mmio_zone *zone) { struct kvm_coalesced_mmio_dev *dev, *tmp; + int r; + + if (zone->pio != 1 && zone->pio != 0) + return -EINVAL; mutex_lock(&kvm->slots_lock); - list_for_each_entry_safe(dev, tmp, &kvm->coalesced_zones, list) - if (coalesced_mmio_in_range(dev, zone->addr, zone->size)) { - kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &dev->dev); - kvm_iodevice_destructor(&dev->dev); + list_for_each_entry_safe(dev, tmp, &kvm->coalesced_zones, list) { + if (zone->pio == dev->zone.pio && + coalesced_mmio_in_range(dev, zone->addr, zone->size)) { + r = kvm_io_bus_unregister_dev(kvm, + zone->pio ? KVM_PIO_BUS : KVM_MMIO_BUS, &dev->dev); + /* + * On failure, unregister destroys all devices on the + * bus, including the target device. There's no need + * to restart the walk as there aren't any zones left. + */ + if (r) + break; } + } mutex_unlock(&kvm->slots_lock); + /* + * Ignore the result of kvm_io_bus_unregister_dev(), from userspace's + * perspective, the coalesced MMIO is most definitely unregistered. + */ return 0; } diff --git a/virt/kvm/coalesced_mmio.h b/virt/kvm/coalesced_mmio.h index b280c20444d1..36f84264ed25 100644 --- a/virt/kvm/coalesced_mmio.h +++ b/virt/kvm/coalesced_mmio.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __KVM_COALESCED_MMIO_H__ #define __KVM_COALESCED_MMIO_H__ @@ -24,9 +25,9 @@ struct kvm_coalesced_mmio_dev { int kvm_coalesced_mmio_init(struct kvm *kvm); void kvm_coalesced_mmio_free(struct kvm *kvm); int kvm_vm_ioctl_register_coalesced_mmio(struct kvm *kvm, - struct kvm_coalesced_mmio_zone *zone); + struct kvm_coalesced_mmio_zone *zone); int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm, - struct kvm_coalesced_mmio_zone *zone); + struct kvm_coalesced_mmio_zone *zone); #else diff --git a/virt/kvm/dirty_ring.c b/virt/kvm/dirty_ring.c new file mode 100644 index 000000000000..02bc6b00d76c --- /dev/null +++ b/virt/kvm/dirty_ring.c @@ -0,0 +1,271 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * KVM dirty ring implementation + * + * Copyright 2019 Red Hat, Inc. + */ +#include <linux/kvm_host.h> +#include <linux/kvm.h> +#include <linux/vmalloc.h> +#include <linux/kvm_dirty_ring.h> +#include <trace/events/kvm.h> +#include "kvm_mm.h" + +int __weak kvm_cpu_dirty_log_size(struct kvm *kvm) +{ + return 0; +} + +u32 kvm_dirty_ring_get_rsvd_entries(struct kvm *kvm) +{ + return KVM_DIRTY_RING_RSVD_ENTRIES + kvm_cpu_dirty_log_size(kvm); +} + +bool kvm_use_dirty_bitmap(struct kvm *kvm) +{ + lockdep_assert_held(&kvm->slots_lock); + + return !kvm->dirty_ring_size || kvm->dirty_ring_with_bitmap; +} + +#ifndef CONFIG_NEED_KVM_DIRTY_RING_WITH_BITMAP +bool kvm_arch_allow_write_without_running_vcpu(struct kvm *kvm) +{ + return false; +} +#endif + +static u32 kvm_dirty_ring_used(struct kvm_dirty_ring *ring) +{ + return READ_ONCE(ring->dirty_index) - READ_ONCE(ring->reset_index); +} + +static bool kvm_dirty_ring_soft_full(struct kvm_dirty_ring *ring) +{ + return kvm_dirty_ring_used(ring) >= ring->soft_limit; +} + +static bool kvm_dirty_ring_full(struct kvm_dirty_ring *ring) +{ + return kvm_dirty_ring_used(ring) >= ring->size; +} + +static void kvm_reset_dirty_gfn(struct kvm *kvm, u32 slot, u64 offset, u64 mask) +{ + struct kvm_memory_slot *memslot; + int as_id, id; + + as_id = slot >> 16; + id = (u16)slot; + + if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_USER_MEM_SLOTS) + return; + + memslot = id_to_memslot(__kvm_memslots(kvm, as_id), id); + + if (!memslot || (offset + __fls(mask)) >= memslot->npages) + return; + + KVM_MMU_LOCK(kvm); + kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot, offset, mask); + KVM_MMU_UNLOCK(kvm); +} + +int kvm_dirty_ring_alloc(struct kvm *kvm, struct kvm_dirty_ring *ring, + int index, u32 size) +{ + ring->dirty_gfns = vzalloc(size); + if (!ring->dirty_gfns) + return -ENOMEM; + + ring->size = size / sizeof(struct kvm_dirty_gfn); + ring->soft_limit = ring->size - kvm_dirty_ring_get_rsvd_entries(kvm); + ring->dirty_index = 0; + ring->reset_index = 0; + ring->index = index; + + return 0; +} + +static inline void kvm_dirty_gfn_set_invalid(struct kvm_dirty_gfn *gfn) +{ + smp_store_release(&gfn->flags, 0); +} + +static inline void kvm_dirty_gfn_set_dirtied(struct kvm_dirty_gfn *gfn) +{ + gfn->flags = KVM_DIRTY_GFN_F_DIRTY; +} + +static inline bool kvm_dirty_gfn_harvested(struct kvm_dirty_gfn *gfn) +{ + return smp_load_acquire(&gfn->flags) & KVM_DIRTY_GFN_F_RESET; +} + +int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring, + int *nr_entries_reset) +{ + /* + * To minimize mmu_lock contention, batch resets for harvested entries + * whose gfns are in the same slot, and are within N frame numbers of + * each other, where N is the number of bits in an unsigned long. For + * simplicity, process the current set of entries when the next entry + * can't be included in the batch. + * + * Track the current batch slot, the gfn offset into the slot for the + * batch, and the bitmask of gfns that need to be reset (relative to + * offset). Note, the offset may be adjusted backwards, e.g. so that + * a sequence of gfns X, X-1, ... X-N-1 can be batched. + */ + u32 cur_slot, next_slot; + u64 cur_offset, next_offset; + unsigned long mask = 0; + struct kvm_dirty_gfn *entry; + + /* + * Ensure concurrent calls to KVM_RESET_DIRTY_RINGS are serialized, + * e.g. so that KVM fully resets all entries processed by a given call + * before returning to userspace. Holding slots_lock also protects + * the various memslot accesses. + */ + lockdep_assert_held(&kvm->slots_lock); + + while (likely((*nr_entries_reset) < INT_MAX)) { + if (signal_pending(current)) + return -EINTR; + + entry = &ring->dirty_gfns[ring->reset_index & (ring->size - 1)]; + + if (!kvm_dirty_gfn_harvested(entry)) + break; + + next_slot = READ_ONCE(entry->slot); + next_offset = READ_ONCE(entry->offset); + + /* Update the flags to reflect that this GFN is reset */ + kvm_dirty_gfn_set_invalid(entry); + + ring->reset_index++; + (*nr_entries_reset)++; + + if (mask) { + /* + * While the size of each ring is fixed, it's possible + * for the ring to be constantly re-dirtied/harvested + * while the reset is in-progress (the hard limit exists + * only to guard against the count becoming negative). + */ + cond_resched(); + + /* + * Try to coalesce the reset operations when the guest + * is scanning pages in the same slot. + */ + if (next_slot == cur_slot) { + s64 delta = next_offset - cur_offset; + + if (delta >= 0 && delta < BITS_PER_LONG) { + mask |= 1ull << delta; + continue; + } + + /* Backwards visit, careful about overflows! */ + if (delta > -BITS_PER_LONG && delta < 0 && + (mask << -delta >> -delta) == mask) { + cur_offset = next_offset; + mask = (mask << -delta) | 1; + continue; + } + } + + /* + * Reset the slot for all the harvested entries that + * have been gathered, but not yet fully processed. + */ + kvm_reset_dirty_gfn(kvm, cur_slot, cur_offset, mask); + } + + /* + * The current slot was reset or this is the first harvested + * entry, (re)initialize the metadata. + */ + cur_slot = next_slot; + cur_offset = next_offset; + mask = 1; + } + + /* + * Perform a final reset if there are harvested entries that haven't + * been processed, which is guaranteed if at least one harvested was + * found. The loop only performs a reset when the "next" entry can't + * be batched with the "current" entry(s), and that reset processes the + * _current_ entry(s); i.e. the last harvested entry, a.k.a. next, will + * always be left pending. + */ + if (mask) + kvm_reset_dirty_gfn(kvm, cur_slot, cur_offset, mask); + + /* + * The request KVM_REQ_DIRTY_RING_SOFT_FULL will be cleared + * by the VCPU thread next time when it enters the guest. + */ + + trace_kvm_dirty_ring_reset(ring); + + return 0; +} + +void kvm_dirty_ring_push(struct kvm_vcpu *vcpu, u32 slot, u64 offset) +{ + struct kvm_dirty_ring *ring = &vcpu->dirty_ring; + struct kvm_dirty_gfn *entry; + + /* It should never get full */ + WARN_ON_ONCE(kvm_dirty_ring_full(ring)); + + entry = &ring->dirty_gfns[ring->dirty_index & (ring->size - 1)]; + + entry->slot = slot; + entry->offset = offset; + /* + * Make sure the data is filled in before we publish this to + * the userspace program. There's no paired kernel-side reader. + */ + smp_wmb(); + kvm_dirty_gfn_set_dirtied(entry); + ring->dirty_index++; + trace_kvm_dirty_ring_push(ring, slot, offset); + + if (kvm_dirty_ring_soft_full(ring)) + kvm_make_request(KVM_REQ_DIRTY_RING_SOFT_FULL, vcpu); +} + +bool kvm_dirty_ring_check_request(struct kvm_vcpu *vcpu) +{ + /* + * The VCPU isn't runnable when the dirty ring becomes soft full. + * The KVM_REQ_DIRTY_RING_SOFT_FULL event is always set to prevent + * the VCPU from running until the dirty pages are harvested and + * the dirty ring is reset by userspace. + */ + if (kvm_check_request(KVM_REQ_DIRTY_RING_SOFT_FULL, vcpu) && + kvm_dirty_ring_soft_full(&vcpu->dirty_ring)) { + kvm_make_request(KVM_REQ_DIRTY_RING_SOFT_FULL, vcpu); + vcpu->run->exit_reason = KVM_EXIT_DIRTY_RING_FULL; + trace_kvm_dirty_ring_exit(vcpu); + return true; + } + + return false; +} + +struct page *kvm_dirty_ring_get_page(struct kvm_dirty_ring *ring, u32 offset) +{ + return vmalloc_to_page((void *)ring->dirty_gfns + offset * PAGE_SIZE); +} + +void kvm_dirty_ring_free(struct kvm_dirty_ring *ring) +{ + vfree(ring->dirty_gfns); + ring->dirty_gfns = NULL; +} diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index 1550637d1b10..0e8b5277be3b 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * kvm eventfd support - use eventfd objects to signal various KVM events * @@ -6,23 +7,11 @@ * * Author: * Gregory Haskins <ghaskins@novell.com> - * - * This file is free software; you can redistribute it and/or modify - * it under the terms of version 2 of the GNU General Public License - * 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., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301, USA. */ #include <linux/kvm_host.h> #include <linux/kvm.h> +#include <linux/kvm_irqfd.h> #include <linux/workqueue.h> #include <linux/syscalls.h> #include <linux/wait.h> @@ -31,72 +20,29 @@ #include <linux/list.h> #include <linux/eventfd.h> #include <linux/kernel.h> +#include <linux/srcu.h> #include <linux/slab.h> +#include <linux/seqlock.h> +#include <linux/irqbypass.h> +#include <trace/events/kvm.h> -#include "iodev.h" +#include <kvm/iodev.h> -#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING -/* - * -------------------------------------------------------------------- - * irqfd: Allows an fd to be used to inject an interrupt to the guest - * - * Credit goes to Avi Kivity for the original idea. - * -------------------------------------------------------------------- - */ - -/* - * Resampling irqfds are a special variety of irqfds used to emulate - * level triggered interrupts. The interrupt is asserted on eventfd - * trigger. On acknowledgement through the irq ack notifier, the - * interrupt is de-asserted and userspace is notified through the - * resamplefd. All resamplers on the same gsi are de-asserted - * together, so we don't need to track the state of each individual - * user. We can also therefore share the same irq source ID. - */ -struct _irqfd_resampler { - struct kvm *kvm; - /* - * List of resampling struct _irqfd objects sharing this gsi. - * RCU list modified under kvm->irqfds.resampler_lock - */ - struct list_head list; - struct kvm_irq_ack_notifier notifier; - /* - * Entry in list of kvm->irqfd.resampler_list. Use for sharing - * resamplers among irqfds on the same gsi. - * Accessed and modified under kvm->irqfds.resampler_lock - */ - struct list_head link; -}; - -struct _irqfd { - /* Used for MSI fast-path */ - struct kvm *kvm; - wait_queue_t wait; - /* Update side is protected by irqfds.lock */ - struct kvm_kernel_irq_routing_entry __rcu *irq_entry; - /* Used for level IRQ fast-path */ - int gsi; - struct work_struct inject; - /* The resampler used by this irqfd (resampler-only) */ - struct _irqfd_resampler *resampler; - /* Eventfd notified on resample (resampler-only) */ - struct eventfd_ctx *resamplefd; - /* Entry in list of irqfds for a resampler (resampler-only) */ - struct list_head resampler_link; - /* Used for setup/shutdown */ - struct eventfd_ctx *eventfd; - struct list_head list; - poll_table pt; - struct work_struct shutdown; -}; +#ifdef CONFIG_HAVE_KVM_IRQCHIP static struct workqueue_struct *irqfd_cleanup_wq; +bool __attribute__((weak)) +kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args) +{ + return true; +} + static void irqfd_inject(struct work_struct *work) { - struct _irqfd *irqfd = container_of(work, struct _irqfd, inject); + struct kvm_kernel_irqfd *irqfd = + container_of(work, struct kvm_kernel_irqfd, inject); struct kvm *kvm = irqfd->kvm; if (!irqfd->resampler) { @@ -109,6 +55,15 @@ irqfd_inject(struct work_struct *work) irqfd->gsi, 1, false); } +static void irqfd_resampler_notify(struct kvm_kernel_irqfd_resampler *resampler) +{ + struct kvm_kernel_irqfd *irqfd; + + list_for_each_entry_srcu(irqfd, &resampler->list, resampler_link, + srcu_read_lock_held(&resampler->kvm->irq_srcu)) + eventfd_signal(irqfd->resamplefd); +} + /* * Since resampler irqfds share an IRQ source ID, we de-assert once * then notify all of the resampler irqfds using this GSI. We can't @@ -117,39 +72,44 @@ irqfd_inject(struct work_struct *work) static void irqfd_resampler_ack(struct kvm_irq_ack_notifier *kian) { - struct _irqfd_resampler *resampler; - struct _irqfd *irqfd; + struct kvm_kernel_irqfd_resampler *resampler; + struct kvm *kvm; + int idx; - resampler = container_of(kian, struct _irqfd_resampler, notifier); + resampler = container_of(kian, + struct kvm_kernel_irqfd_resampler, notifier); + kvm = resampler->kvm; - kvm_set_irq(resampler->kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID, + kvm_set_irq(kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID, resampler->notifier.gsi, 0, false); - rcu_read_lock(); - - list_for_each_entry_rcu(irqfd, &resampler->list, resampler_link) - eventfd_signal(irqfd->resamplefd, 1); - - rcu_read_unlock(); + idx = srcu_read_lock(&kvm->irq_srcu); + irqfd_resampler_notify(resampler); + srcu_read_unlock(&kvm->irq_srcu, idx); } static void -irqfd_resampler_shutdown(struct _irqfd *irqfd) +irqfd_resampler_shutdown(struct kvm_kernel_irqfd *irqfd) { - struct _irqfd_resampler *resampler = irqfd->resampler; + struct kvm_kernel_irqfd_resampler *resampler = irqfd->resampler; struct kvm *kvm = resampler->kvm; mutex_lock(&kvm->irqfds.resampler_lock); list_del_rcu(&irqfd->resampler_link); - synchronize_rcu(); if (list_empty(&resampler->list)) { - list_del(&resampler->link); + list_del_rcu(&resampler->link); kvm_unregister_irq_ack_notifier(kvm, &resampler->notifier); + /* + * synchronize_srcu_expedited(&kvm->irq_srcu) already called + * in kvm_unregister_irq_ack_notifier(). + */ kvm_set_irq(kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID, resampler->notifier.gsi, 0, false); kfree(resampler); + } else { + synchronize_srcu_expedited(&kvm->irq_srcu); } mutex_unlock(&kvm->irqfds.resampler_lock); @@ -161,9 +121,14 @@ irqfd_resampler_shutdown(struct _irqfd *irqfd) static void irqfd_shutdown(struct work_struct *work) { - struct _irqfd *irqfd = container_of(work, struct _irqfd, shutdown); + struct kvm_kernel_irqfd *irqfd = + container_of(work, struct kvm_kernel_irqfd, shutdown); + struct kvm *kvm = irqfd->kvm; u64 cnt; + /* Make sure irqfd has been initialized in assign path. */ + synchronize_srcu_expedited(&kvm->irq_srcu); + /* * Synchronize with the wait-queue and unhook ourselves to prevent * further events. @@ -184,6 +149,9 @@ irqfd_shutdown(struct work_struct *work) /* * It is now safe to release the object's resources */ +#if IS_ENABLED(CONFIG_HAVE_KVM_IRQ_BYPASS) + irq_bypass_unregister_consumer(&irqfd->consumer); +#endif eventfd_ctx_put(irqfd->eventfd); kfree(irqfd); } @@ -191,7 +159,7 @@ irqfd_shutdown(struct work_struct *work) /* assumes kvm->irqfds.lock is held */ static bool -irqfd_is_active(struct _irqfd *irqfd) +irqfd_is_active(struct kvm_kernel_irqfd *irqfd) { return list_empty(&irqfd->list) ? false : true; } @@ -202,7 +170,7 @@ irqfd_is_active(struct _irqfd *irqfd) * assumes kvm->irqfds.lock is held */ static void -irqfd_deactivate(struct _irqfd *irqfd) +irqfd_deactivate(struct kvm_kernel_irqfd *irqfd) { BUG_ON(!irqfd_is_active(irqfd)); @@ -211,34 +179,63 @@ irqfd_deactivate(struct _irqfd *irqfd) queue_work(irqfd_cleanup_wq, &irqfd->shutdown); } +int __attribute__((weak)) kvm_arch_set_irq_inatomic( + struct kvm_kernel_irq_routing_entry *irq, + struct kvm *kvm, int irq_source_id, + int level, + bool line_status) +{ + return -EWOULDBLOCK; +} + /* * Called with wqh->lock held and interrupts disabled */ static int -irqfd_wakeup(wait_queue_t *wait, unsigned mode, int sync, void *key) +irqfd_wakeup(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { - struct _irqfd *irqfd = container_of(wait, struct _irqfd, wait); - unsigned long flags = (unsigned long)key; - struct kvm_kernel_irq_routing_entry *irq; + struct kvm_kernel_irqfd *irqfd = + container_of(wait, struct kvm_kernel_irqfd, wait); + __poll_t flags = key_to_poll(key); + struct kvm_kernel_irq_routing_entry irq; struct kvm *kvm = irqfd->kvm; + unsigned seq; + int idx; + int ret = 0; - if (flags & POLLIN) { - rcu_read_lock(); - irq = rcu_dereference(irqfd->irq_entry); + if (flags & EPOLLIN) { + /* + * WARNING: Do NOT take irqfds.lock in any path except EPOLLHUP, + * as KVM holds irqfds.lock when registering the irqfd with the + * eventfd. + */ + u64 cnt; + eventfd_ctx_do_read(irqfd->eventfd, &cnt); + + idx = srcu_read_lock(&kvm->irq_srcu); + do { + seq = read_seqcount_begin(&irqfd->irq_entry_sc); + irq = irqfd->irq_entry; + } while (read_seqcount_retry(&irqfd->irq_entry_sc, seq)); /* An event has been signaled, inject an interrupt */ - if (irq) - kvm_set_msi(irq, kvm, KVM_USERSPACE_IRQ_SOURCE_ID, 1, - false); - else + if (kvm_arch_set_irq_inatomic(&irq, kvm, + KVM_USERSPACE_IRQ_SOURCE_ID, 1, + false) == -EWOULDBLOCK) schedule_work(&irqfd->inject); - rcu_read_unlock(); + srcu_read_unlock(&kvm->irq_srcu, idx); + ret = 1; } - if (flags & POLLHUP) { + if (flags & EPOLLHUP) { /* The eventfd is closing, detach from KVM */ - unsigned long flags; + unsigned long iflags; - spin_lock_irqsave(&kvm->irqfds.lock, flags); + /* + * Taking irqfds.lock is safe here, as KVM holds a reference to + * the eventfd when registering the irqfd, i.e. this path can't + * be reached while kvm_irqfd_add() is running. + */ + spin_lock_irqsave(&kvm->irqfds.lock, iflags); /* * We must check if someone deactivated the irqfd before @@ -252,51 +249,126 @@ irqfd_wakeup(wait_queue_t *wait, unsigned mode, int sync, void *key) if (irqfd_is_active(irqfd)) irqfd_deactivate(irqfd); - spin_unlock_irqrestore(&kvm->irqfds.lock, flags); + spin_unlock_irqrestore(&kvm->irqfds.lock, iflags); } - return 0; + return ret; } -static void -irqfd_ptable_queue_proc(struct file *file, wait_queue_head_t *wqh, - poll_table *pt) +static void irqfd_update(struct kvm *kvm, struct kvm_kernel_irqfd *irqfd) { - struct _irqfd *irqfd = container_of(pt, struct _irqfd, pt); - add_wait_queue(wqh, &irqfd->wait); + struct kvm_kernel_irq_routing_entry *e; + struct kvm_kernel_irq_routing_entry entries[KVM_NR_IRQCHIPS]; + int n_entries; + + lockdep_assert_held(&kvm->irqfds.lock); + + n_entries = kvm_irq_map_gsi(kvm, entries, irqfd->gsi); + + write_seqcount_begin(&irqfd->irq_entry_sc); + + e = entries; + if (n_entries == 1) + irqfd->irq_entry = *e; + else + irqfd->irq_entry.type = 0; + + write_seqcount_end(&irqfd->irq_entry_sc); } -/* Must be called under irqfds.lock */ -static void irqfd_update(struct kvm *kvm, struct _irqfd *irqfd, - struct kvm_irq_routing_table *irq_rt) +struct kvm_irqfd_pt { + struct kvm_kernel_irqfd *irqfd; + struct kvm *kvm; + poll_table pt; + int ret; +}; + +static void kvm_irqfd_register(struct file *file, wait_queue_head_t *wqh, + poll_table *pt) { - struct kvm_kernel_irq_routing_entry *e; + struct kvm_irqfd_pt *p = container_of(pt, struct kvm_irqfd_pt, pt); + struct kvm_kernel_irqfd *irqfd = p->irqfd; + struct kvm *kvm = p->kvm; - if (irqfd->gsi >= irq_rt->nr_rt_entries) { - rcu_assign_pointer(irqfd->irq_entry, NULL); - return; - } + /* + * Note, irqfds.lock protects the irqfd's irq_entry, i.e. its routing, + * and irqfds.items. It does NOT protect registering with the eventfd. + */ + spin_lock_irq(&kvm->irqfds.lock); - 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); - else - rcu_assign_pointer(irqfd->irq_entry, NULL); - } + /* + * Initialize the routing information prior to adding the irqfd to the + * eventfd's waitqueue, as irqfd_wakeup() can be invoked as soon as the + * irqfd is registered. + */ + irqfd_update(kvm, irqfd); + + /* + * Add the irqfd as a priority waiter on the eventfd, with a custom + * wake-up handler, so that KVM *and only KVM* is notified whenever the + * underlying eventfd is signaled. + */ + init_waitqueue_func_entry(&irqfd->wait, irqfd_wakeup); + + /* + * Temporarily lie to lockdep about holding irqfds.lock to avoid a + * false positive regarding potential deadlock with irqfd_wakeup() + * (see irqfd_wakeup() for details). + * + * Adding to the wait queue will fail if there is already a priority + * waiter, i.e. if the eventfd is associated with another irqfd (in any + * VM). Note, kvm_irqfd_deassign() waits for all in-flight shutdown + * jobs to complete, i.e. ensures the irqfd has been removed from the + * eventfd's waitqueue before returning to userspace. + */ + spin_release(&kvm->irqfds.lock.dep_map, _RET_IP_); + p->ret = add_wait_queue_priority_exclusive(wqh, &irqfd->wait); + spin_acquire(&kvm->irqfds.lock.dep_map, 0, 0, _RET_IP_); + if (p->ret) + goto out; + + list_add_tail(&irqfd->list, &kvm->irqfds.items); + +out: + spin_unlock_irq(&kvm->irqfds.lock); +} + +#if IS_ENABLED(CONFIG_HAVE_KVM_IRQ_BYPASS) +void __attribute__((weak)) kvm_arch_irq_bypass_stop( + struct irq_bypass_consumer *cons) +{ } +void __attribute__((weak)) kvm_arch_irq_bypass_start( + struct irq_bypass_consumer *cons) +{ +} + +void __weak kvm_arch_update_irqfd_routing(struct kvm_kernel_irqfd *irqfd, + struct kvm_kernel_irq_routing_entry *old, + struct kvm_kernel_irq_routing_entry *new) +{ + +} +#endif + static int kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args) { - struct kvm_irq_routing_table *irq_rt; - struct _irqfd *irqfd, *tmp; - struct file *file = NULL; + struct kvm_kernel_irqfd *irqfd; struct eventfd_ctx *eventfd = NULL, *resamplefd = NULL; + struct kvm_irqfd_pt irqfd_pt; int ret; - unsigned int events; + __poll_t events; + int idx; + + if (!kvm_arch_intc_initialized(kvm)) + return -EAGAIN; + + if (!kvm_arch_irqfd_allowed(kvm, args)) + return -EINVAL; - irqfd = kzalloc(sizeof(*irqfd), GFP_KERNEL); + irqfd = kzalloc(sizeof(*irqfd), GFP_KERNEL_ACCOUNT); if (!irqfd) return -ENOMEM; @@ -305,23 +377,24 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args) INIT_LIST_HEAD(&irqfd->list); INIT_WORK(&irqfd->inject, irqfd_inject); INIT_WORK(&irqfd->shutdown, irqfd_shutdown); + seqcount_spinlock_init(&irqfd->irq_entry_sc, &kvm->irqfds.lock); - file = eventfd_fget(args->fd); - if (IS_ERR(file)) { - ret = PTR_ERR(file); - goto fail; + CLASS(fd, f)(args->fd); + if (fd_empty(f)) { + ret = -EBADF; + goto out; } - eventfd = eventfd_ctx_fileget(file); + eventfd = eventfd_ctx_fileget(fd_file(f)); if (IS_ERR(eventfd)) { ret = PTR_ERR(eventfd); - goto fail; + goto out; } irqfd->eventfd = eventfd; if (args->flags & KVM_IRQFD_FLAG_RESAMPLE) { - struct _irqfd_resampler *resampler; + struct kvm_kernel_irqfd_resampler *resampler; resamplefd = eventfd_ctx_fdget(args->resamplefd); if (IS_ERR(resamplefd)) { @@ -343,7 +416,8 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args) } if (!irqfd->resampler) { - resampler = kzalloc(sizeof(*resampler), GFP_KERNEL); + resampler = kzalloc(sizeof(*resampler), + GFP_KERNEL_ACCOUNT); if (!resampler) { ret = -ENOMEM; mutex_unlock(&kvm->irqfds.resampler_lock); @@ -356,62 +430,67 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args) resampler->notifier.irq_acked = irqfd_resampler_ack; INIT_LIST_HEAD(&resampler->link); - list_add(&resampler->link, &kvm->irqfds.resampler_list); + list_add_rcu(&resampler->link, &kvm->irqfds.resampler_list); kvm_register_irq_ack_notifier(kvm, &resampler->notifier); irqfd->resampler = resampler; } list_add_rcu(&irqfd->resampler_link, &irqfd->resampler->list); - synchronize_rcu(); + synchronize_srcu_expedited(&kvm->irq_srcu); mutex_unlock(&kvm->irqfds.resampler_lock); } /* - * Install our own custom wake-up handling so we are notified via - * a callback whenever someone signals the underlying eventfd + * Set the irqfd routing and add it to KVM's list before registering + * the irqfd with the eventfd, so that the routing information is valid + * and stays valid, e.g. if there are GSI routing changes, prior to + * making the irqfd visible, i.e. before it might be signaled. + * + * Note, holding SRCU ensures a stable read of routing information, and + * also prevents irqfd_shutdown() from freeing the irqfd before it's + * fully initialized. */ - init_waitqueue_func_entry(&irqfd->wait, irqfd_wakeup); - init_poll_funcptr(&irqfd->pt, irqfd_ptable_queue_proc); - - spin_lock_irq(&kvm->irqfds.lock); + idx = srcu_read_lock(&kvm->irq_srcu); - ret = 0; - list_for_each_entry(tmp, &kvm->irqfds.items, list) { - if (irqfd->eventfd != tmp->eventfd) - continue; - /* This fd is used for another irq already. */ - ret = -EBUSY; - spin_unlock_irq(&kvm->irqfds.lock); - goto fail; - } - - irq_rt = rcu_dereference_protected(kvm->irq_routing, - lockdep_is_held(&kvm->irqfds.lock)); - irqfd_update(kvm, irqfd, irq_rt); + /* + * Register the irqfd with the eventfd by polling on the eventfd, and + * simultaneously and the irqfd to KVM's list. If there was en event + * pending on the eventfd prior to registering, manually trigger IRQ + * injection. + */ + irqfd_pt.irqfd = irqfd; + irqfd_pt.kvm = kvm; + init_poll_funcptr(&irqfd_pt.pt, kvm_irqfd_register); - events = file->f_op->poll(file, &irqfd->pt); + events = vfs_poll(fd_file(f), &irqfd_pt.pt); - list_add_tail(&irqfd->list, &kvm->irqfds.items); + ret = irqfd_pt.ret; + if (ret) + goto fail_poll; - /* - * Check if there was an event already pending on the eventfd - * before we registered, and trigger it as if we didn't miss it. - */ - if (events & POLLIN) + if (events & EPOLLIN) 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); +#if IS_ENABLED(CONFIG_HAVE_KVM_IRQ_BYPASS) + if (kvm_arch_has_irq_bypass()) { + irqfd->consumer.add_producer = kvm_arch_irq_bypass_add_producer; + irqfd->consumer.del_producer = kvm_arch_irq_bypass_del_producer; + irqfd->consumer.stop = kvm_arch_irq_bypass_stop; + irqfd->consumer.start = kvm_arch_irq_bypass_start; + ret = irq_bypass_register_consumer(&irqfd->consumer, irqfd->eventfd); + if (ret) + pr_info("irq bypass consumer (eventfd %p) registration fails: %d\n", + irqfd->eventfd, ret); + } +#endif + srcu_read_unlock(&kvm->irq_srcu, idx); return 0; +fail_poll: + srcu_read_unlock(&kvm->irq_srcu, idx); fail: if (irqfd->resampler) irqfd_resampler_shutdown(irqfd); @@ -422,34 +501,81 @@ fail: if (eventfd && !IS_ERR(eventfd)) eventfd_ctx_put(eventfd); - if (!IS_ERR(file)) - fput(file); - +out: kfree(irqfd); return ret; } -#endif -void -kvm_eventfd_init(struct kvm *kvm) +bool kvm_irq_has_notifier(struct kvm *kvm, unsigned irqchip, unsigned pin) { -#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); - mutex_init(&kvm->irqfds.resampler_lock); -#endif - INIT_LIST_HEAD(&kvm->ioeventfds); + struct kvm_irq_ack_notifier *kian; + int gsi, idx; + + idx = srcu_read_lock(&kvm->irq_srcu); + gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin); + if (gsi != -1) + hlist_for_each_entry_srcu(kian, &kvm->irq_ack_notifier_list, + link, srcu_read_lock_held(&kvm->irq_srcu)) + if (kian->gsi == gsi) { + srcu_read_unlock(&kvm->irq_srcu, idx); + return true; + } + + srcu_read_unlock(&kvm->irq_srcu, idx); + + return false; +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_irq_has_notifier); + +void kvm_notify_acked_gsi(struct kvm *kvm, int gsi) +{ + struct kvm_irq_ack_notifier *kian; + + hlist_for_each_entry_srcu(kian, &kvm->irq_ack_notifier_list, + link, srcu_read_lock_held(&kvm->irq_srcu)) + if (kian->gsi == gsi) + kian->irq_acked(kian); +} + +void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin) +{ + int gsi, idx; + + trace_kvm_ack_irq(irqchip, pin); + + idx = srcu_read_lock(&kvm->irq_srcu); + gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin); + if (gsi != -1) + kvm_notify_acked_gsi(kvm, gsi); + 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); + kvm_arch_post_irq_ack_notifier_list_update(kvm); +} + +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_expedited(&kvm->irq_srcu); + kvm_arch_post_irq_ack_notifier_list_update(kvm); } -#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING /* * shutdown any irqfd's that match fd+gsi */ static int kvm_irqfd_deassign(struct kvm *kvm, struct kvm_irqfd *args) { - struct _irqfd *irqfd, *tmp; + struct kvm_kernel_irqfd *irqfd, *tmp; struct eventfd_ctx *eventfd; eventfd = eventfd_ctx_fdget(args->fd); @@ -461,14 +587,14 @@ kvm_irqfd_deassign(struct kvm *kvm, struct kvm_irqfd *args) list_for_each_entry_safe(irqfd, tmp, &kvm->irqfds.items, list) { if (irqfd->eventfd == eventfd && irqfd->gsi == args->gsi) { /* - * This rcu_assign_pointer is needed for when + * This clearing of irq_entry.type is needed for when * another thread calls kvm_irq_routing_update before * we flush workqueue below (we synchronize with * kvm_irq_routing_update using irqfds.lock). - * It is paired with synchronize_rcu done by caller - * of that function. */ - rcu_assign_pointer(irqfd->irq_entry, NULL); + write_seqcount_begin(&irqfd->irq_entry_sc); + irqfd->irq_entry.type = 0; + write_seqcount_end(&irqfd->irq_entry_sc); irqfd_deactivate(irqfd); } } @@ -505,7 +631,7 @@ kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args) void kvm_irqfd_release(struct kvm *kvm) { - struct _irqfd *irqfd, *tmp; + struct kvm_kernel_irqfd *irqfd, *tmp; spin_lock_irq(&kvm->irqfds.lock); @@ -523,32 +649,65 @@ kvm_irqfd_release(struct kvm *kvm) } /* - * Change irq_routing and irqfd. - * Caller must invoke synchronize_rcu afterwards. + * Take note of a change in irq routing. + * Caller must invoke synchronize_srcu_expedited(&kvm->irq_srcu) afterwards. */ -void kvm_irq_routing_update(struct kvm *kvm, - struct kvm_irq_routing_table *irq_rt) +void kvm_irq_routing_update(struct kvm *kvm) { - struct _irqfd *irqfd; + struct kvm_kernel_irqfd *irqfd; spin_lock_irq(&kvm->irqfds.lock); - rcu_assign_pointer(kvm->irq_routing, irq_rt); + list_for_each_entry(irqfd, &kvm->irqfds.items, list) { +#if IS_ENABLED(CONFIG_HAVE_KVM_IRQ_BYPASS) + /* Under irqfds.lock, so can read irq_entry safely */ + struct kvm_kernel_irq_routing_entry old = irqfd->irq_entry; +#endif + + irqfd_update(kvm, irqfd); - list_for_each_entry(irqfd, &kvm->irqfds.items, list) - irqfd_update(kvm, irqfd, irq_rt); +#if IS_ENABLED(CONFIG_HAVE_KVM_IRQ_BYPASS) + if (irqfd->producer) + kvm_arch_update_irqfd_routing(irqfd, &old, &irqfd->irq_entry); +#endif + } spin_unlock_irq(&kvm->irqfds.lock); } +bool kvm_notify_irqfd_resampler(struct kvm *kvm, + unsigned int irqchip, + unsigned int pin) +{ + struct kvm_kernel_irqfd_resampler *resampler; + int gsi, idx; + + idx = srcu_read_lock(&kvm->irq_srcu); + gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin); + if (gsi != -1) { + list_for_each_entry_srcu(resampler, + &kvm->irqfds.resampler_list, link, + srcu_read_lock_held(&kvm->irq_srcu)) { + if (resampler->notifier.gsi == gsi) { + irqfd_resampler_notify(resampler); + srcu_read_unlock(&kvm->irq_srcu, idx); + return true; + } + } + } + srcu_read_unlock(&kvm->irq_srcu, idx); + + return false; +} + /* * create a host-wide workqueue for issuing deferred shutdown requests - * aggregated from all vm* instances. We need our own isolated single-thread - * queue to prevent deadlock against flushing the normal work-queue. + * aggregated from all vm* instances. We need our own isolated + * queue to ease flushing work items when a VM exits. */ int kvm_irqfd_init(void) { - irqfd_cleanup_wq = create_singlethread_workqueue("kvm-irqfd-cleanup"); + irqfd_cleanup_wq = alloc_workqueue("kvm-irqfd-cleanup", WQ_PERCPU, 0); if (!irqfd_cleanup_wq) return -ENOMEM; @@ -600,7 +759,15 @@ 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; @@ -629,20 +796,20 @@ ioeventfd_in_range(struct _ioeventfd *p, gpa_t addr, int len, const void *val) return false; } - return _val == p->datamatch ? true : false; + return _val == p->datamatch; } /* MMIO/PIO writes trigger an event if the addr/val match */ static int -ioeventfd_write(struct kvm_io_device *this, gpa_t addr, int len, - const void *val) +ioeventfd_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this, gpa_t addr, + int len, const void *val) { struct _ioeventfd *p = to_ioeventfd(this); if (!ioeventfd_in_range(p, addr, len, val)) return -EOPNOTSUPP; - eventfd_signal(p->eventfd, 1); + eventfd_signal(p->eventfd); return 0; } @@ -671,9 +838,11 @@ ioeventfd_check_collision(struct kvm *kvm, struct _ioeventfd *p) list_for_each_entry(_p, &kvm->ioeventfds, list) if (_p->bus_idx == p->bus_idx && - _p->addr == p->addr && _p->length == p->length && - (_p->wildcard || p->wildcard || - _p->datamatch == p->datamatch)) + _p->addr == p->addr && + (!_p->length || !p->length || + (_p->length == p->length && + (_p->wildcard || p->wildcard || + _p->datamatch == p->datamatch)))) return true; return false; @@ -688,39 +857,20 @@ static enum kvm_bus ioeventfd_bus_from_flags(__u32 flags) return KVM_MMIO_BUS; } -static int -kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) +static int kvm_assign_ioeventfd_idx(struct kvm *kvm, + enum kvm_bus bus_idx, + struct kvm_ioeventfd *args) { - enum kvm_bus bus_idx; - struct _ioeventfd *p; - struct eventfd_ctx *eventfd; - int ret; - - bus_idx = ioeventfd_bus_from_flags(args->flags); - /* must be natural-word sized */ - switch (args->len) { - case 1: - case 2: - case 4: - case 8: - break; - default: - return -EINVAL; - } - /* check for range overflow */ - if (args->addr + args->len < args->addr) - return -EINVAL; - - /* check for extra flags that we don't understand */ - if (args->flags & ~KVM_IOEVENTFD_VALID_FLAG_MASK) - return -EINVAL; + struct eventfd_ctx *eventfd; + struct _ioeventfd *p; + int ret; eventfd = eventfd_ctx_fdget(args->fd); if (IS_ERR(eventfd)) return PTR_ERR(eventfd); - p = kzalloc(sizeof(*p), GFP_KERNEL); + p = kzalloc(sizeof(*p), GFP_KERNEL_ACCOUNT); if (!p) { ret = -ENOMEM; goto fail; @@ -753,7 +903,7 @@ kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) if (ret < 0) goto unlock_fail; - kvm->buses[bus_idx]->ioeventfd_count++; + kvm_get_bus(kvm, bus_idx)->ioeventfd_count++; list_add_tail(&p->list, &kvm->ioeventfds); mutex_unlock(&kvm->slots_lock); @@ -762,32 +912,33 @@ kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) unlock_fail: mutex_unlock(&kvm->slots_lock); + kfree(p); fail: - kfree(p); eventfd_ctx_put(eventfd); return ret; } static int -kvm_deassign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) +kvm_deassign_ioeventfd_idx(struct kvm *kvm, enum kvm_bus bus_idx, + struct kvm_ioeventfd *args) { - enum kvm_bus bus_idx; - struct _ioeventfd *p, *tmp; + struct _ioeventfd *p; struct eventfd_ctx *eventfd; + struct kvm_io_bus *bus; int ret = -ENOENT; + bool wildcard; - bus_idx = ioeventfd_bus_from_flags(args->flags); eventfd = eventfd_ctx_fdget(args->fd); if (IS_ERR(eventfd)) return PTR_ERR(eventfd); - mutex_lock(&kvm->slots_lock); + wildcard = !(args->flags & KVM_IOEVENTFD_FLAG_DATAMATCH); - list_for_each_entry_safe(p, tmp, &kvm->ioeventfds, list) { - bool wildcard = !(args->flags & KVM_IOEVENTFD_FLAG_DATAMATCH); + mutex_lock(&kvm->slots_lock); + list_for_each_entry(p, &kvm->ioeventfds, list) { if (p->bus_idx != bus_idx || p->eventfd != eventfd || p->addr != args->addr || @@ -799,8 +950,9 @@ kvm_deassign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) continue; kvm_io_bus_unregister_dev(kvm, bus_idx, &p->dev); - kvm->buses[bus_idx]->ioeventfd_count--; - ioeventfd_release(p); + bus = kvm_get_bus(kvm, bus_idx); + if (bus) + bus->ioeventfd_count--; ret = 0; break; } @@ -812,6 +964,69 @@ kvm_deassign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) return ret; } +static int kvm_deassign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) +{ + enum kvm_bus bus_idx = ioeventfd_bus_from_flags(args->flags); + int ret = kvm_deassign_ioeventfd_idx(kvm, bus_idx, args); + + if (!args->len && bus_idx == KVM_MMIO_BUS) + kvm_deassign_ioeventfd_idx(kvm, KVM_FAST_MMIO_BUS, args); + + return ret; +} + +static int +kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) +{ + enum kvm_bus bus_idx; + int ret; + + 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: + case 8: + break; + default: + return -EINVAL; + } + + /* check for range overflow */ + if (args->addr + args->len < args->addr) + return -EINVAL; + + /* check for extra flags that we don't understand */ + 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_DATAMATCH)) + return -EINVAL; + + ret = kvm_assign_ioeventfd_idx(kvm, bus_idx, args); + if (ret) + goto fail; + + /* When length is ignored, MMIO is also put on a separate bus, for + * faster lookups. + */ + if (!args->len && bus_idx == KVM_MMIO_BUS) { + ret = kvm_assign_ioeventfd_idx(kvm, KVM_FAST_MMIO_BUS, args); + if (ret < 0) + goto fast_fail; + } + + return 0; + +fast_fail: + kvm_deassign_ioeventfd_idx(kvm, bus_idx, args); +fail: + return ret; +} + int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) { @@ -820,3 +1035,15 @@ kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) return kvm_assign_ioeventfd(kvm, args); } + +void +kvm_eventfd_init(struct kvm *kvm) +{ +#ifdef CONFIG_HAVE_KVM_IRQCHIP + spin_lock_init(&kvm->irqfds.lock); + INIT_LIST_HEAD(&kvm->irqfds.items); + INIT_LIST_HEAD(&kvm->irqfds.resampler_list); + mutex_init(&kvm->irqfds.resampler_lock); +#endif + INIT_LIST_HEAD(&kvm->ioeventfds); +} diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c new file mode 100644 index 000000000000..fdaea3422c30 --- /dev/null +++ b/virt/kvm/guest_memfd.c @@ -0,0 +1,1016 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/anon_inodes.h> +#include <linux/backing-dev.h> +#include <linux/falloc.h> +#include <linux/fs.h> +#include <linux/kvm_host.h> +#include <linux/mempolicy.h> +#include <linux/pseudo_fs.h> +#include <linux/pagemap.h> + +#include "kvm_mm.h" + +static struct vfsmount *kvm_gmem_mnt; + +/* + * A guest_memfd instance can be associated multiple VMs, each with its own + * "view" of the underlying physical memory. + * + * The gmem's inode is effectively the raw underlying physical storage, and is + * used to track properties of the physical memory, while each gmem file is + * effectively a single VM's view of that storage, and is used to track assets + * specific to its associated VM, e.g. memslots=>gmem bindings. + */ +struct gmem_file { + struct kvm *kvm; + struct xarray bindings; + struct list_head entry; +}; + +struct gmem_inode { + struct shared_policy policy; + struct inode vfs_inode; + + u64 flags; +}; + +static __always_inline struct gmem_inode *GMEM_I(struct inode *inode) +{ + return container_of(inode, struct gmem_inode, vfs_inode); +} + +#define kvm_gmem_for_each_file(f, mapping) \ + list_for_each_entry(f, &(mapping)->i_private_list, entry) + +/** + * folio_file_pfn - like folio_file_page, but return a pfn. + * @folio: The folio which contains this index. + * @index: The index we want to look up. + * + * Return: The pfn for this index. + */ +static inline kvm_pfn_t folio_file_pfn(struct folio *folio, pgoff_t index) +{ + return folio_pfn(folio) + (index & (folio_nr_pages(folio) - 1)); +} + +static pgoff_t kvm_gmem_get_index(struct kvm_memory_slot *slot, gfn_t gfn) +{ + return gfn - slot->base_gfn + slot->gmem.pgoff; +} + +static int __kvm_gmem_prepare_folio(struct kvm *kvm, struct kvm_memory_slot *slot, + pgoff_t index, struct folio *folio) +{ +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE + kvm_pfn_t pfn = folio_file_pfn(folio, index); + gfn_t gfn = slot->base_gfn + index - slot->gmem.pgoff; + int rc = kvm_arch_gmem_prepare(kvm, gfn, pfn, folio_order(folio)); + if (rc) { + pr_warn_ratelimited("gmem: Failed to prepare folio for index %lx GFN %llx PFN %llx error %d.\n", + index, gfn, pfn, rc); + return rc; + } +#endif + + return 0; +} + +static inline void kvm_gmem_mark_prepared(struct folio *folio) +{ + folio_mark_uptodate(folio); +} + +/* + * Process @folio, which contains @gfn, so that the guest can use it. + * The folio must be locked and the gfn must be contained in @slot. + * On successful return the guest sees a zero page so as to avoid + * leaking host data and the up-to-date flag is set. + */ +static int kvm_gmem_prepare_folio(struct kvm *kvm, struct kvm_memory_slot *slot, + gfn_t gfn, struct folio *folio) +{ + unsigned long nr_pages, i; + pgoff_t index; + int r; + + nr_pages = folio_nr_pages(folio); + for (i = 0; i < nr_pages; i++) + clear_highpage(folio_page(folio, i)); + + /* + * Preparing huge folios should always be safe, since it should + * be possible to split them later if needed. + * + * Right now the folio order is always going to be zero, but the + * code is ready for huge folios. The only assumption is that + * the base pgoff of memslots is naturally aligned with the + * requested page order, ensuring that huge folios can also use + * huge page table entries for GPA->HPA mapping. + * + * The order will be passed when creating the guest_memfd, and + * checked when creating memslots. + */ + WARN_ON(!IS_ALIGNED(slot->gmem.pgoff, folio_nr_pages(folio))); + index = kvm_gmem_get_index(slot, gfn); + index = ALIGN_DOWN(index, folio_nr_pages(folio)); + r = __kvm_gmem_prepare_folio(kvm, slot, index, folio); + if (!r) + kvm_gmem_mark_prepared(folio); + + return r; +} + +/* + * Returns a locked folio on success. The caller is responsible for + * setting the up-to-date flag before the memory is mapped into the guest. + * There is no backing storage for the memory, so the folio will remain + * up-to-date until it's removed. + * + * Ignore accessed, referenced, and dirty flags. The memory is + * unevictable and there is no storage to write back to. + */ +static struct folio *kvm_gmem_get_folio(struct inode *inode, pgoff_t index) +{ + /* TODO: Support huge pages. */ + struct mempolicy *policy; + struct folio *folio; + + /* + * Fast-path: See if folio is already present in mapping to avoid + * policy_lookup. + */ + folio = __filemap_get_folio(inode->i_mapping, index, + FGP_LOCK | FGP_ACCESSED, 0); + if (!IS_ERR(folio)) + return folio; + + policy = mpol_shared_policy_lookup(&GMEM_I(inode)->policy, index); + folio = __filemap_get_folio_mpol(inode->i_mapping, index, + FGP_LOCK | FGP_ACCESSED | FGP_CREAT, + mapping_gfp_mask(inode->i_mapping), policy); + mpol_cond_put(policy); + + return folio; +} + +static enum kvm_gfn_range_filter kvm_gmem_get_invalidate_filter(struct inode *inode) +{ + if (GMEM_I(inode)->flags & GUEST_MEMFD_FLAG_INIT_SHARED) + return KVM_FILTER_SHARED; + + return KVM_FILTER_PRIVATE; +} + +static void __kvm_gmem_invalidate_begin(struct gmem_file *f, pgoff_t start, + pgoff_t end, + enum kvm_gfn_range_filter attr_filter) +{ + bool flush = false, found_memslot = false; + struct kvm_memory_slot *slot; + struct kvm *kvm = f->kvm; + unsigned long index; + + xa_for_each_range(&f->bindings, index, slot, start, end - 1) { + pgoff_t pgoff = slot->gmem.pgoff; + + struct kvm_gfn_range gfn_range = { + .start = slot->base_gfn + max(pgoff, start) - pgoff, + .end = slot->base_gfn + min(pgoff + slot->npages, end) - pgoff, + .slot = slot, + .may_block = true, + .attr_filter = attr_filter, + }; + + if (!found_memslot) { + found_memslot = true; + + KVM_MMU_LOCK(kvm); + kvm_mmu_invalidate_begin(kvm); + } + + flush |= kvm_mmu_unmap_gfn_range(kvm, &gfn_range); + } + + if (flush) + kvm_flush_remote_tlbs(kvm); + + if (found_memslot) + KVM_MMU_UNLOCK(kvm); +} + +static void kvm_gmem_invalidate_begin(struct inode *inode, pgoff_t start, + pgoff_t end) +{ + enum kvm_gfn_range_filter attr_filter; + struct gmem_file *f; + + attr_filter = kvm_gmem_get_invalidate_filter(inode); + + kvm_gmem_for_each_file(f, inode->i_mapping) + __kvm_gmem_invalidate_begin(f, start, end, attr_filter); +} + +static void __kvm_gmem_invalidate_end(struct gmem_file *f, pgoff_t start, + pgoff_t end) +{ + struct kvm *kvm = f->kvm; + + if (xa_find(&f->bindings, &start, end - 1, XA_PRESENT)) { + KVM_MMU_LOCK(kvm); + kvm_mmu_invalidate_end(kvm); + KVM_MMU_UNLOCK(kvm); + } +} + +static void kvm_gmem_invalidate_end(struct inode *inode, pgoff_t start, + pgoff_t end) +{ + struct gmem_file *f; + + kvm_gmem_for_each_file(f, inode->i_mapping) + __kvm_gmem_invalidate_end(f, start, end); +} + +static long kvm_gmem_punch_hole(struct inode *inode, loff_t offset, loff_t len) +{ + pgoff_t start = offset >> PAGE_SHIFT; + pgoff_t end = (offset + len) >> PAGE_SHIFT; + + /* + * Bindings must be stable across invalidation to ensure the start+end + * are balanced. + */ + filemap_invalidate_lock(inode->i_mapping); + + kvm_gmem_invalidate_begin(inode, start, end); + + truncate_inode_pages_range(inode->i_mapping, offset, offset + len - 1); + + kvm_gmem_invalidate_end(inode, start, end); + + filemap_invalidate_unlock(inode->i_mapping); + + return 0; +} + +static long kvm_gmem_allocate(struct inode *inode, loff_t offset, loff_t len) +{ + struct address_space *mapping = inode->i_mapping; + pgoff_t start, index, end; + int r; + + /* Dedicated guest is immutable by default. */ + if (offset + len > i_size_read(inode)) + return -EINVAL; + + filemap_invalidate_lock_shared(mapping); + + start = offset >> PAGE_SHIFT; + end = (offset + len) >> PAGE_SHIFT; + + r = 0; + for (index = start; index < end; ) { + struct folio *folio; + + if (signal_pending(current)) { + r = -EINTR; + break; + } + + folio = kvm_gmem_get_folio(inode, index); + if (IS_ERR(folio)) { + r = PTR_ERR(folio); + break; + } + + index = folio_next_index(folio); + + folio_unlock(folio); + folio_put(folio); + + /* 64-bit only, wrapping the index should be impossible. */ + if (WARN_ON_ONCE(!index)) + break; + + cond_resched(); + } + + filemap_invalidate_unlock_shared(mapping); + + return r; +} + +static long kvm_gmem_fallocate(struct file *file, int mode, loff_t offset, + loff_t len) +{ + int ret; + + if (!(mode & FALLOC_FL_KEEP_SIZE)) + return -EOPNOTSUPP; + + if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE)) + return -EOPNOTSUPP; + + if (!PAGE_ALIGNED(offset) || !PAGE_ALIGNED(len)) + return -EINVAL; + + if (mode & FALLOC_FL_PUNCH_HOLE) + ret = kvm_gmem_punch_hole(file_inode(file), offset, len); + else + ret = kvm_gmem_allocate(file_inode(file), offset, len); + + if (!ret) + file_modified(file); + return ret; +} + +static int kvm_gmem_release(struct inode *inode, struct file *file) +{ + struct gmem_file *f = file->private_data; + struct kvm_memory_slot *slot; + struct kvm *kvm = f->kvm; + unsigned long index; + + /* + * Prevent concurrent attempts to *unbind* a memslot. This is the last + * reference to the file and thus no new bindings can be created, but + * dereferencing the slot for existing bindings needs to be protected + * against memslot updates, specifically so that unbind doesn't race + * and free the memslot (kvm_gmem_get_file() will return NULL). + * + * Since .release is called only when the reference count is zero, + * after which file_ref_get() and get_file_active() fail, + * kvm_gmem_get_pfn() cannot be using the file concurrently. + * file_ref_put() provides a full barrier, and get_file_active() the + * matching acquire barrier. + */ + mutex_lock(&kvm->slots_lock); + + filemap_invalidate_lock(inode->i_mapping); + + xa_for_each(&f->bindings, index, slot) + WRITE_ONCE(slot->gmem.file, NULL); + + /* + * All in-flight operations are gone and new bindings can be created. + * Zap all SPTEs pointed at by this file. Do not free the backing + * memory, as its lifetime is associated with the inode, not the file. + */ + __kvm_gmem_invalidate_begin(f, 0, -1ul, + kvm_gmem_get_invalidate_filter(inode)); + __kvm_gmem_invalidate_end(f, 0, -1ul); + + list_del(&f->entry); + + filemap_invalidate_unlock(inode->i_mapping); + + mutex_unlock(&kvm->slots_lock); + + xa_destroy(&f->bindings); + kfree(f); + + kvm_put_kvm(kvm); + + return 0; +} + +static inline struct file *kvm_gmem_get_file(struct kvm_memory_slot *slot) +{ + /* + * Do not return slot->gmem.file if it has already been closed; + * there might be some time between the last fput() and when + * kvm_gmem_release() clears slot->gmem.file. + */ + return get_file_active(&slot->gmem.file); +} + +DEFINE_CLASS(gmem_get_file, struct file *, if (_T) fput(_T), + kvm_gmem_get_file(slot), struct kvm_memory_slot *slot); + +static bool kvm_gmem_supports_mmap(struct inode *inode) +{ + return GMEM_I(inode)->flags & GUEST_MEMFD_FLAG_MMAP; +} + +static vm_fault_t kvm_gmem_fault_user_mapping(struct vm_fault *vmf) +{ + struct inode *inode = file_inode(vmf->vma->vm_file); + struct folio *folio; + vm_fault_t ret = VM_FAULT_LOCKED; + + if (((loff_t)vmf->pgoff << PAGE_SHIFT) >= i_size_read(inode)) + return VM_FAULT_SIGBUS; + + if (!(GMEM_I(inode)->flags & GUEST_MEMFD_FLAG_INIT_SHARED)) + return VM_FAULT_SIGBUS; + + folio = kvm_gmem_get_folio(inode, vmf->pgoff); + if (IS_ERR(folio)) { + if (PTR_ERR(folio) == -EAGAIN) + return VM_FAULT_RETRY; + + return vmf_error(PTR_ERR(folio)); + } + + if (WARN_ON_ONCE(folio_test_large(folio))) { + ret = VM_FAULT_SIGBUS; + goto out_folio; + } + + if (!folio_test_uptodate(folio)) { + clear_highpage(folio_page(folio, 0)); + kvm_gmem_mark_prepared(folio); + } + + vmf->page = folio_file_page(folio, vmf->pgoff); + +out_folio: + if (ret != VM_FAULT_LOCKED) { + folio_unlock(folio); + folio_put(folio); + } + + return ret; +} + +#ifdef CONFIG_NUMA +static int kvm_gmem_set_policy(struct vm_area_struct *vma, struct mempolicy *mpol) +{ + struct inode *inode = file_inode(vma->vm_file); + + return mpol_set_shared_policy(&GMEM_I(inode)->policy, vma, mpol); +} + +static struct mempolicy *kvm_gmem_get_policy(struct vm_area_struct *vma, + unsigned long addr, pgoff_t *pgoff) +{ + struct inode *inode = file_inode(vma->vm_file); + + *pgoff = vma->vm_pgoff + ((addr - vma->vm_start) >> PAGE_SHIFT); + + /* + * Return the memory policy for this index, or NULL if none is set. + * + * Returning NULL, e.g. instead of the current task's memory policy, is + * important for the .get_policy kernel ABI: it indicates that no + * explicit policy has been set via mbind() for this memory. The caller + * can then replace NULL with the default memory policy instead of the + * current task's memory policy. + */ + return mpol_shared_policy_lookup(&GMEM_I(inode)->policy, *pgoff); +} +#endif /* CONFIG_NUMA */ + +static const struct vm_operations_struct kvm_gmem_vm_ops = { + .fault = kvm_gmem_fault_user_mapping, +#ifdef CONFIG_NUMA + .get_policy = kvm_gmem_get_policy, + .set_policy = kvm_gmem_set_policy, +#endif +}; + +static int kvm_gmem_mmap(struct file *file, struct vm_area_struct *vma) +{ + if (!kvm_gmem_supports_mmap(file_inode(file))) + return -ENODEV; + + if ((vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) != + (VM_SHARED | VM_MAYSHARE)) { + return -EINVAL; + } + + vma->vm_ops = &kvm_gmem_vm_ops; + + return 0; +} + +static struct file_operations kvm_gmem_fops = { + .mmap = kvm_gmem_mmap, + .open = generic_file_open, + .release = kvm_gmem_release, + .fallocate = kvm_gmem_fallocate, +}; + +static int kvm_gmem_migrate_folio(struct address_space *mapping, + struct folio *dst, struct folio *src, + enum migrate_mode mode) +{ + WARN_ON_ONCE(1); + return -EINVAL; +} + +static int kvm_gmem_error_folio(struct address_space *mapping, struct folio *folio) +{ + pgoff_t start, end; + + filemap_invalidate_lock_shared(mapping); + + start = folio->index; + end = start + folio_nr_pages(folio); + + kvm_gmem_invalidate_begin(mapping->host, start, end); + + /* + * Do not truncate the range, what action is taken in response to the + * error is userspace's decision (assuming the architecture supports + * gracefully handling memory errors). If/when the guest attempts to + * access a poisoned page, kvm_gmem_get_pfn() will return -EHWPOISON, + * at which point KVM can either terminate the VM or propagate the + * error to userspace. + */ + + kvm_gmem_invalidate_end(mapping->host, start, end); + + filemap_invalidate_unlock_shared(mapping); + + return MF_DELAYED; +} + +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE +static void kvm_gmem_free_folio(struct folio *folio) +{ + struct page *page = folio_page(folio, 0); + kvm_pfn_t pfn = page_to_pfn(page); + int order = folio_order(folio); + + kvm_arch_gmem_invalidate(pfn, pfn + (1ul << order)); +} +#endif + +static const struct address_space_operations kvm_gmem_aops = { + .dirty_folio = noop_dirty_folio, + .migrate_folio = kvm_gmem_migrate_folio, + .error_remove_folio = kvm_gmem_error_folio, +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE + .free_folio = kvm_gmem_free_folio, +#endif +}; + +static int kvm_gmem_setattr(struct mnt_idmap *idmap, struct dentry *dentry, + struct iattr *attr) +{ + return -EINVAL; +} +static const struct inode_operations kvm_gmem_iops = { + .setattr = kvm_gmem_setattr, +}; + +bool __weak kvm_arch_supports_gmem_init_shared(struct kvm *kvm) +{ + return true; +} + +static int __kvm_gmem_create(struct kvm *kvm, loff_t size, u64 flags) +{ + static const char *name = "[kvm-gmem]"; + struct gmem_file *f; + struct inode *inode; + struct file *file; + int fd, err; + + fd = get_unused_fd_flags(0); + if (fd < 0) + return fd; + + f = kzalloc(sizeof(*f), GFP_KERNEL); + if (!f) { + err = -ENOMEM; + goto err_fd; + } + + /* __fput() will take care of fops_put(). */ + if (!fops_get(&kvm_gmem_fops)) { + err = -ENOENT; + goto err_gmem; + } + + inode = anon_inode_make_secure_inode(kvm_gmem_mnt->mnt_sb, name, NULL); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + goto err_fops; + } + + inode->i_op = &kvm_gmem_iops; + inode->i_mapping->a_ops = &kvm_gmem_aops; + inode->i_mode |= S_IFREG; + inode->i_size = size; + mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER); + mapping_set_inaccessible(inode->i_mapping); + /* Unmovable mappings are supposed to be marked unevictable as well. */ + WARN_ON_ONCE(!mapping_unevictable(inode->i_mapping)); + + GMEM_I(inode)->flags = flags; + + file = alloc_file_pseudo(inode, kvm_gmem_mnt, name, O_RDWR, &kvm_gmem_fops); + if (IS_ERR(file)) { + err = PTR_ERR(file); + goto err_inode; + } + + file->f_flags |= O_LARGEFILE; + file->private_data = f; + + kvm_get_kvm(kvm); + f->kvm = kvm; + xa_init(&f->bindings); + list_add(&f->entry, &inode->i_mapping->i_private_list); + + fd_install(fd, file); + return fd; + +err_inode: + iput(inode); +err_fops: + fops_put(&kvm_gmem_fops); +err_gmem: + kfree(f); +err_fd: + put_unused_fd(fd); + return err; +} + +int kvm_gmem_create(struct kvm *kvm, struct kvm_create_guest_memfd *args) +{ + loff_t size = args->size; + u64 flags = args->flags; + + if (flags & ~kvm_gmem_get_supported_flags(kvm)) + return -EINVAL; + + if (size <= 0 || !PAGE_ALIGNED(size)) + return -EINVAL; + + return __kvm_gmem_create(kvm, size, flags); +} + +int kvm_gmem_bind(struct kvm *kvm, struct kvm_memory_slot *slot, + unsigned int fd, loff_t offset) +{ + loff_t size = slot->npages << PAGE_SHIFT; + unsigned long start, end; + struct gmem_file *f; + struct inode *inode; + struct file *file; + int r = -EINVAL; + + BUILD_BUG_ON(sizeof(gfn_t) != sizeof(slot->gmem.pgoff)); + + file = fget(fd); + if (!file) + return -EBADF; + + if (file->f_op != &kvm_gmem_fops) + goto err; + + f = file->private_data; + if (f->kvm != kvm) + goto err; + + inode = file_inode(file); + + if (offset < 0 || !PAGE_ALIGNED(offset) || + offset + size > i_size_read(inode)) + goto err; + + filemap_invalidate_lock(inode->i_mapping); + + start = offset >> PAGE_SHIFT; + end = start + slot->npages; + + if (!xa_empty(&f->bindings) && + xa_find(&f->bindings, &start, end - 1, XA_PRESENT)) { + filemap_invalidate_unlock(inode->i_mapping); + goto err; + } + + /* + * memslots of flag KVM_MEM_GUEST_MEMFD are immutable to change, so + * kvm_gmem_bind() must occur on a new memslot. Because the memslot + * is not visible yet, kvm_gmem_get_pfn() is guaranteed to see the file. + */ + WRITE_ONCE(slot->gmem.file, file); + slot->gmem.pgoff = start; + if (kvm_gmem_supports_mmap(inode)) + slot->flags |= KVM_MEMSLOT_GMEM_ONLY; + + xa_store_range(&f->bindings, start, end - 1, slot, GFP_KERNEL); + filemap_invalidate_unlock(inode->i_mapping); + + /* + * Drop the reference to the file, even on success. The file pins KVM, + * not the other way 'round. Active bindings are invalidated if the + * file is closed before memslots are destroyed. + */ + r = 0; +err: + fput(file); + return r; +} + +static void __kvm_gmem_unbind(struct kvm_memory_slot *slot, struct gmem_file *f) +{ + unsigned long start = slot->gmem.pgoff; + unsigned long end = start + slot->npages; + + xa_store_range(&f->bindings, start, end - 1, NULL, GFP_KERNEL); + + /* + * synchronize_srcu(&kvm->srcu) ensured that kvm_gmem_get_pfn() + * cannot see this memslot. + */ + WRITE_ONCE(slot->gmem.file, NULL); +} + +void kvm_gmem_unbind(struct kvm_memory_slot *slot) +{ + /* + * Nothing to do if the underlying file was _already_ closed, as + * kvm_gmem_release() invalidates and nullifies all bindings. + */ + if (!slot->gmem.file) + return; + + CLASS(gmem_get_file, file)(slot); + + /* + * However, if the file is _being_ closed, then the bindings need to be + * removed as kvm_gmem_release() might not run until after the memslot + * is freed. Note, modifying the bindings is safe even though the file + * is dying as kvm_gmem_release() nullifies slot->gmem.file under + * slots_lock, and only puts its reference to KVM after destroying all + * bindings. I.e. reaching this point means kvm_gmem_release() hasn't + * yet destroyed the bindings or freed the gmem_file, and can't do so + * until the caller drops slots_lock. + */ + if (!file) { + __kvm_gmem_unbind(slot, slot->gmem.file->private_data); + return; + } + + filemap_invalidate_lock(file->f_mapping); + __kvm_gmem_unbind(slot, file->private_data); + filemap_invalidate_unlock(file->f_mapping); +} + +/* Returns a locked folio on success. */ +static struct folio *__kvm_gmem_get_pfn(struct file *file, + struct kvm_memory_slot *slot, + pgoff_t index, kvm_pfn_t *pfn, + bool *is_prepared, int *max_order) +{ + struct file *slot_file = READ_ONCE(slot->gmem.file); + struct gmem_file *f = file->private_data; + struct folio *folio; + + if (file != slot_file) { + WARN_ON_ONCE(slot_file); + return ERR_PTR(-EFAULT); + } + + if (xa_load(&f->bindings, index) != slot) { + WARN_ON_ONCE(xa_load(&f->bindings, index)); + return ERR_PTR(-EIO); + } + + folio = kvm_gmem_get_folio(file_inode(file), index); + if (IS_ERR(folio)) + return folio; + + if (folio_test_hwpoison(folio)) { + folio_unlock(folio); + folio_put(folio); + return ERR_PTR(-EHWPOISON); + } + + *pfn = folio_file_pfn(folio, index); + if (max_order) + *max_order = 0; + + *is_prepared = folio_test_uptodate(folio); + return folio; +} + +int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot, + gfn_t gfn, kvm_pfn_t *pfn, struct page **page, + int *max_order) +{ + pgoff_t index = kvm_gmem_get_index(slot, gfn); + struct folio *folio; + bool is_prepared = false; + int r = 0; + + CLASS(gmem_get_file, file)(slot); + if (!file) + return -EFAULT; + + folio = __kvm_gmem_get_pfn(file, slot, index, pfn, &is_prepared, max_order); + if (IS_ERR(folio)) + return PTR_ERR(folio); + + if (!is_prepared) + r = kvm_gmem_prepare_folio(kvm, slot, gfn, folio); + + folio_unlock(folio); + + if (!r) + *page = folio_file_page(folio, index); + else + folio_put(folio); + + return r; +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_gmem_get_pfn); + +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_POPULATE +long kvm_gmem_populate(struct kvm *kvm, gfn_t start_gfn, void __user *src, long npages, + kvm_gmem_populate_cb post_populate, void *opaque) +{ + struct kvm_memory_slot *slot; + void __user *p; + + int ret = 0, max_order; + long i; + + lockdep_assert_held(&kvm->slots_lock); + + if (WARN_ON_ONCE(npages <= 0)) + return -EINVAL; + + slot = gfn_to_memslot(kvm, start_gfn); + if (!kvm_slot_has_gmem(slot)) + return -EINVAL; + + CLASS(gmem_get_file, file)(slot); + if (!file) + return -EFAULT; + + filemap_invalidate_lock(file->f_mapping); + + npages = min_t(ulong, slot->npages - (start_gfn - slot->base_gfn), npages); + for (i = 0; i < npages; i += (1 << max_order)) { + struct folio *folio; + gfn_t gfn = start_gfn + i; + pgoff_t index = kvm_gmem_get_index(slot, gfn); + bool is_prepared = false; + kvm_pfn_t pfn; + + if (signal_pending(current)) { + ret = -EINTR; + break; + } + + folio = __kvm_gmem_get_pfn(file, slot, index, &pfn, &is_prepared, &max_order); + if (IS_ERR(folio)) { + ret = PTR_ERR(folio); + break; + } + + if (is_prepared) { + folio_unlock(folio); + folio_put(folio); + ret = -EEXIST; + break; + } + + folio_unlock(folio); + WARN_ON(!IS_ALIGNED(gfn, 1 << max_order) || + (npages - i) < (1 << max_order)); + + ret = -EINVAL; + while (!kvm_range_has_memory_attributes(kvm, gfn, gfn + (1 << max_order), + KVM_MEMORY_ATTRIBUTE_PRIVATE, + KVM_MEMORY_ATTRIBUTE_PRIVATE)) { + if (!max_order) + goto put_folio_and_exit; + max_order--; + } + + p = src ? src + i * PAGE_SIZE : NULL; + ret = post_populate(kvm, gfn, pfn, p, max_order, opaque); + if (!ret) + kvm_gmem_mark_prepared(folio); + +put_folio_and_exit: + folio_put(folio); + if (ret) + break; + } + + filemap_invalidate_unlock(file->f_mapping); + + return ret && !i ? ret : i; +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_gmem_populate); +#endif + +static struct kmem_cache *kvm_gmem_inode_cachep; + +static void kvm_gmem_init_inode_once(void *__gi) +{ + struct gmem_inode *gi = __gi; + + /* + * Note! Don't initialize the inode with anything specific to the + * guest_memfd instance, or that might be specific to how the inode is + * used (from the VFS-layer's perspective). This hook is called only + * during the initial slab allocation, i.e. only fields/state that are + * idempotent across _all_ use of the inode _object_ can be initialized + * at this time! + */ + inode_init_once(&gi->vfs_inode); +} + +static struct inode *kvm_gmem_alloc_inode(struct super_block *sb) +{ + struct gmem_inode *gi; + + gi = alloc_inode_sb(sb, kvm_gmem_inode_cachep, GFP_KERNEL); + if (!gi) + return NULL; + + mpol_shared_policy_init(&gi->policy, NULL); + + gi->flags = 0; + return &gi->vfs_inode; +} + +static void kvm_gmem_destroy_inode(struct inode *inode) +{ + mpol_free_shared_policy(&GMEM_I(inode)->policy); +} + +static void kvm_gmem_free_inode(struct inode *inode) +{ + kmem_cache_free(kvm_gmem_inode_cachep, GMEM_I(inode)); +} + +static const struct super_operations kvm_gmem_super_operations = { + .statfs = simple_statfs, + .alloc_inode = kvm_gmem_alloc_inode, + .destroy_inode = kvm_gmem_destroy_inode, + .free_inode = kvm_gmem_free_inode, +}; + +static int kvm_gmem_init_fs_context(struct fs_context *fc) +{ + struct pseudo_fs_context *ctx; + + if (!init_pseudo(fc, GUEST_MEMFD_MAGIC)) + return -ENOMEM; + + fc->s_iflags |= SB_I_NOEXEC; + fc->s_iflags |= SB_I_NODEV; + ctx = fc->fs_private; + ctx->ops = &kvm_gmem_super_operations; + + return 0; +} + +static struct file_system_type kvm_gmem_fs = { + .name = "guest_memfd", + .init_fs_context = kvm_gmem_init_fs_context, + .kill_sb = kill_anon_super, +}; + +static int kvm_gmem_init_mount(void) +{ + kvm_gmem_mnt = kern_mount(&kvm_gmem_fs); + + if (IS_ERR(kvm_gmem_mnt)) + return PTR_ERR(kvm_gmem_mnt); + + kvm_gmem_mnt->mnt_flags |= MNT_NOEXEC; + return 0; +} + +int kvm_gmem_init(struct module *module) +{ + struct kmem_cache_args args = { + .align = 0, + .ctor = kvm_gmem_init_inode_once, + }; + int ret; + + kvm_gmem_fops.owner = module; + kvm_gmem_inode_cachep = kmem_cache_create("kvm_gmem_inode_cache", + sizeof(struct gmem_inode), + &args, SLAB_ACCOUNT); + if (!kvm_gmem_inode_cachep) + return -ENOMEM; + + ret = kvm_gmem_init_mount(); + if (ret) { + kmem_cache_destroy(kvm_gmem_inode_cachep); + return ret; + } + return 0; +} + +void kvm_gmem_exit(void) +{ + kern_unmount(kvm_gmem_mnt); + kvm_gmem_mnt = NULL; + rcu_barrier(); + kmem_cache_destroy(kvm_gmem_inode_cachep); +} diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c deleted file mode 100644 index 2d682977ce82..000000000000 --- a/virt/kvm/ioapic.c +++ /dev/null @@ -1,603 +0,0 @@ -/* - * Copyright (C) 2001 MandrakeSoft S.A. - * Copyright 2010 Red Hat, Inc. and/or its affiliates. - * - * MandrakeSoft S.A. - * 43, rue d'Aboukir - * 75002 Paris - France - * http://www.linux-mandrake.com/ - * http://www.mandrakesoft.com/ - * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This library 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 - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * - * Yunhong Jiang <yunhong.jiang@intel.com> - * Yaozu (Eddie) Dong <eddie.dong@intel.com> - * Based on Xen 3.1 code. - */ - -#include <linux/kvm_host.h> -#include <linux/kvm.h> -#include <linux/mm.h> -#include <linux/highmem.h> -#include <linux/smp.h> -#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> -#include <trace/events/kvm.h> - -#include "ioapic.h" -#include "lapic.h" -#include "irq.h" - -#if 0 -#define ioapic_debug(fmt,arg...) printk(KERN_WARNING fmt,##arg) -#else -#define ioapic_debug(fmt, arg...) -#endif -static int ioapic_deliver(struct kvm_ioapic *vioapic, int irq, - bool line_status); - -static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic, - unsigned long addr, - unsigned long length) -{ - unsigned long result = 0; - - switch (ioapic->ioregsel) { - case IOAPIC_REG_VERSION: - result = ((((IOAPIC_NUM_PINS - 1) & 0xff) << 16) - | (IOAPIC_VERSION_ID & 0xff)); - break; - - case IOAPIC_REG_APIC_ID: - case IOAPIC_REG_ARB_ID: - result = ((ioapic->id & 0xf) << 24); - break; - - default: - { - u32 redir_index = (ioapic->ioregsel - 0x10) >> 1; - u64 redir_content; - - if (redir_index < IOAPIC_NUM_PINS) - redir_content = - ioapic->redirtbl[redir_index].bits; - else - redir_content = ~0ULL; - - result = (ioapic->ioregsel & 0x1) ? - (redir_content >> 32) & 0xffffffff : - redir_content & 0xffffffff; - break; - } - } - - return result; -} - -static void rtc_irq_eoi_tracking_reset(struct kvm_ioapic *ioapic) -{ - ioapic->rtc_status.pending_eoi = 0; - bitmap_zero(ioapic->rtc_status.dest_map, KVM_MAX_VCPUS); -} - -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--; - } - - WARN_ON(ioapic->rtc_status.pending_eoi < 0); -} - -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; - - WARN_ON(ioapic->rtc_status.pending_eoi < 0); -} - -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_service(struct kvm_ioapic *ioapic, unsigned int idx, - bool line_status) -{ - union kvm_ioapic_redirect_entry *pent; - int injected = -1; - - pent = &ioapic->redirtbl[idx]; - - if (!pent->fields.mask) { - injected = ioapic_deliver(ioapic, idx, line_status); - if (injected && pent->fields.trig_mode == IOAPIC_LEVEL_TRIG) - pent->fields.remote_irr = 1; - } - - return injected; -} - -static void update_handled_vectors(struct kvm_ioapic *ioapic) -{ - DECLARE_BITMAP(handled_vectors, 256); - int i; - - memset(handled_vectors, 0, sizeof(handled_vectors)); - for (i = 0; i < IOAPIC_NUM_PINS; ++i) - __set_bit(ioapic->redirtbl[i].fields.vector, handled_vectors); - memcpy(ioapic->handled_vectors, handled_vectors, - sizeof(handled_vectors)); - 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; - bool mask_before, mask_after; - union kvm_ioapic_redirect_entry *e; - - switch (ioapic->ioregsel) { - case IOAPIC_REG_VERSION: - /* Writes are ignored. */ - break; - - case IOAPIC_REG_APIC_ID: - ioapic->id = (val >> 24) & 0xf; - break; - - case IOAPIC_REG_ARB_ID: - break; - - default: - index = (ioapic->ioregsel - 0x10) >> 1; - - ioapic_debug("change redir index %x val %x\n", index, val); - if (index >= IOAPIC_NUM_PINS) - return; - e = &ioapic->redirtbl[index]; - mask_before = e->fields.mask; - if (ioapic->ioregsel & 1) { - e->bits &= 0xffffffff; - e->bits |= (u64) val << 32; - } else { - e->bits &= ~0xffffffffULL; - e->bits |= (u32) val; - e->fields.remote_irr = 0; - } - update_handled_vectors(ioapic); - mask_after = e->fields.mask; - if (mask_before != mask_after) - 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, false); - kvm_vcpu_request_scan_ioapic(ioapic->kvm); - break; - } -} - -static int ioapic_deliver(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; - - ioapic_debug("dest=%x dest_mode=%x delivery_mode=%x " - "vector=%x trig_mode=%x\n", - entry->fields.dest_id, entry->fields.dest_mode, - entry->fields.delivery_mode, entry->fields.vector, - entry->fields.trig_mode); - - irqe.dest_id = entry->fields.dest_id; - irqe.vector = entry->fields.vector; - irqe.dest_mode = entry->fields.dest_mode; - irqe.trig_mode = entry->fields.trig_mode; - irqe.delivery_mode = entry->fields.delivery_mode << 8; - irqe.level = 1; - irqe.shorthand = 0; - - if (irq == RTC_GSI && line_status) { - 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; - } else - ret = kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe, NULL); - - return ret; -} - -int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id, - 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); - - if (irq == RTC_GSI && line_status && - rtc_irq_check_coalesced(ioapic)) { - ret = 0; /* coalesced */ - goto out; - } - ioapic->irr |= mask; - if ((edge && old_irr != ioapic->irr) || - (!edge && !entry.fields.remote_irr)) - ret = ioapic_service(ioapic, irq, line_status); - else - ret = 0; /* report coalesced interrupt */ - } -out: - trace_kvm_ioapic_set_irq(entry.bits, irq, ret == 0); - spin_unlock(&ioapic->lock); - - return ret; -} - -void kvm_ioapic_clear_all(struct kvm_ioapic *ioapic, int irq_source_id) -{ - int i; - - spin_lock(&ioapic->lock); - for (i = 0; i < KVM_IOAPIC_NUM_PINS; i++) - __clear_bit(irq_source_id, &ioapic->irq_states[i]); - spin_unlock(&ioapic->lock); -} - -static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, - struct kvm_ioapic *ioapic, int vector, int trigger_mode) -{ - int i; - - for (i = 0; i < IOAPIC_NUM_PINS; i++) { - union kvm_ioapic_redirect_entry *ent = &ioapic->redirtbl[i]; - - 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 - * recursively. Since remote_irr is cleared only after call - * to notifiers if the same vector will be delivered while lock - * is dropped it will be put into irr and will be delivered - * after ack notifier returns. - */ - spin_unlock(&ioapic->lock); - kvm_notify_acked_irq(ioapic->kvm, KVM_IRQCHIP_IOAPIC, i); - spin_lock(&ioapic->lock); - - if (trigger_mode != IOAPIC_LEVEL_TRIG) - continue; - - 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, false); - } -} - -bool kvm_ioapic_handles_vector(struct kvm *kvm, int vector) -{ - struct kvm_ioapic *ioapic = kvm->arch.vioapic; - smp_rmb(); - return test_bit(vector, ioapic->handled_vectors); -} - -void kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, int vector, int trigger_mode) -{ - struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic; - - spin_lock(&ioapic->lock); - __kvm_ioapic_update_eoi(vcpu, ioapic, vector, trigger_mode); - spin_unlock(&ioapic->lock); -} - -static inline struct kvm_ioapic *to_ioapic(struct kvm_io_device *dev) -{ - return container_of(dev, struct kvm_ioapic, dev); -} - -static inline int ioapic_in_range(struct kvm_ioapic *ioapic, gpa_t addr) -{ - return ((addr >= ioapic->base_address && - (addr < ioapic->base_address + IOAPIC_MEM_LENGTH))); -} - -static int ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len, - void *val) -{ - struct kvm_ioapic *ioapic = to_ioapic(this); - u32 result; - if (!ioapic_in_range(ioapic, addr)) - return -EOPNOTSUPP; - - ioapic_debug("addr %lx\n", (unsigned long)addr); - ASSERT(!(addr & 0xf)); /* check alignment */ - - addr &= 0xff; - spin_lock(&ioapic->lock); - switch (addr) { - case IOAPIC_REG_SELECT: - result = ioapic->ioregsel; - break; - - case IOAPIC_REG_WINDOW: - result = ioapic_read_indirect(ioapic, addr, len); - break; - - default: - result = 0; - break; - } - spin_unlock(&ioapic->lock); - - switch (len) { - case 8: - *(u64 *) val = result; - break; - case 1: - case 2: - case 4: - memcpy(val, (char *)&result, len); - break; - default: - printk(KERN_WARNING "ioapic: wrong length %d\n", len); - } - return 0; -} - -static int ioapic_mmio_write(struct kvm_io_device *this, gpa_t addr, int len, - const void *val) -{ - struct kvm_ioapic *ioapic = to_ioapic(this); - u32 data; - if (!ioapic_in_range(ioapic, addr)) - return -EOPNOTSUPP; - - ioapic_debug("ioapic_mmio_write addr=%p len=%d val=%p\n", - (void*)addr, len, val); - ASSERT(!(addr & 0xf)); /* check alignment */ - - switch (len) { - case 8: - case 4: - data = *(u32 *) val; - break; - case 2: - data = *(u16 *) val; - break; - case 1: - data = *(u8 *) val; - break; - default: - printk(KERN_WARNING "ioapic: Unsupported size %d\n", len); - return 0; - } - - addr &= 0xff; - spin_lock(&ioapic->lock); - switch (addr) { - case IOAPIC_REG_SELECT: - ioapic->ioregsel = data & 0xFF; /* 8-bit register */ - break; - - case IOAPIC_REG_WINDOW: - ioapic_write_indirect(ioapic, data); - break; -#ifdef CONFIG_IA64 - case IOAPIC_REG_EOI: - __kvm_ioapic_update_eoi(NULL, ioapic, data, IOAPIC_LEVEL_TRIG); - break; -#endif - - default: - break; - } - spin_unlock(&ioapic->lock); - return 0; -} - -void kvm_ioapic_reset(struct kvm_ioapic *ioapic) -{ - int i; - - for (i = 0; i < IOAPIC_NUM_PINS; i++) - ioapic->redirtbl[i].fields.mask = 1; - ioapic->base_address = IOAPIC_DEFAULT_BASE_ADDRESS; - ioapic->ioregsel = 0; - ioapic->irr = 0; - ioapic->id = 0; - rtc_irq_eoi_tracking_reset(ioapic); - update_handled_vectors(ioapic); -} - -static const struct kvm_io_device_ops ioapic_mmio_ops = { - .read = ioapic_mmio_read, - .write = ioapic_mmio_write, -}; - -int kvm_ioapic_init(struct kvm *kvm) -{ - struct kvm_ioapic *ioapic; - int ret; - - ioapic = kzalloc(sizeof(struct kvm_ioapic), GFP_KERNEL); - if (!ioapic) - return -ENOMEM; - spin_lock_init(&ioapic->lock); - kvm->arch.vioapic = ioapic; - kvm_ioapic_reset(ioapic); - kvm_iodevice_init(&ioapic->dev, &ioapic_mmio_ops); - ioapic->kvm = kvm; - mutex_lock(&kvm->slots_lock); - ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, ioapic->base_address, - IOAPIC_MEM_LENGTH, &ioapic->dev); - mutex_unlock(&kvm->slots_lock); - if (ret < 0) { - kvm->arch.vioapic = NULL; - kfree(ioapic); - } - - return ret; -} - -void kvm_ioapic_destroy(struct kvm *kvm) -{ - struct kvm_ioapic *ioapic = kvm->arch.vioapic; - - if (ioapic) { - kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &ioapic->dev); - kvm->arch.vioapic = NULL; - kfree(ioapic); - } -} - -int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state) -{ - struct kvm_ioapic *ioapic = ioapic_irqchip(kvm); - if (!ioapic) - return -EINVAL; - - spin_lock(&ioapic->lock); - memcpy(state, ioapic, sizeof(struct kvm_ioapic_state)); - spin_unlock(&ioapic->lock); - return 0; -} - -int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state) -{ - struct kvm_ioapic *ioapic = ioapic_irqchip(kvm); - if (!ioapic) - return -EINVAL; - - spin_lock(&ioapic->lock); - memcpy(ioapic, state, sizeof(struct kvm_ioapic_state)); - update_handled_vectors(ioapic); - kvm_vcpu_request_scan_ioapic(kvm); - kvm_rtc_eoi_tracking_restore_all(ioapic); - spin_unlock(&ioapic->lock); - return 0; -} diff --git a/virt/kvm/ioapic.h b/virt/kvm/ioapic.h deleted file mode 100644 index 615d8c995c3c..000000000000 --- a/virt/kvm/ioapic.h +++ /dev/null @@ -1,103 +0,0 @@ -#ifndef __KVM_IO_APIC_H -#define __KVM_IO_APIC_H - -#include <linux/kvm_host.h> - -#include "iodev.h" - -struct kvm; -struct kvm_vcpu; - -#define IOAPIC_NUM_PINS KVM_IOAPIC_NUM_PINS -#define IOAPIC_VERSION_ID 0x11 /* IOAPIC version */ -#define IOAPIC_EDGE_TRIG 0 -#define IOAPIC_LEVEL_TRIG 1 - -#define IOAPIC_DEFAULT_BASE_ADDRESS 0xfec00000 -#define IOAPIC_MEM_LENGTH 0x100 - -/* Direct registers. */ -#define IOAPIC_REG_SELECT 0x00 -#define IOAPIC_REG_WINDOW 0x10 -#define IOAPIC_REG_EOI 0x40 /* IA64 IOSAPIC only */ - -/* Indirect registers. */ -#define IOAPIC_REG_APIC_ID 0x00 /* x86 IOAPIC only */ -#define IOAPIC_REG_VERSION 0x01 -#define IOAPIC_REG_ARB_ID 0x02 /* x86 IOAPIC only */ - -/*ioapic delivery mode*/ -#define IOAPIC_FIXED 0x0 -#define IOAPIC_LOWEST_PRIORITY 0x1 -#define IOAPIC_PMI 0x2 -#define IOAPIC_NMI 0x4 -#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; - u32 id; - u32 irr; - u32 pad; - union kvm_ioapic_redirect_entry redirtbl[IOAPIC_NUM_PINS]; - unsigned long irq_states[IOAPIC_NUM_PINS]; - struct kvm_io_device dev; - struct kvm *kvm; - void (*ack_notifier)(void *opaque, int irq); - spinlock_t lock; - DECLARE_BITMAP(handled_vectors, 256); - struct rtc_status rtc_status; -}; - -#ifdef DEBUG -#define ASSERT(x) \ -do { \ - if (!(x)) { \ - printk(KERN_EMERG "assertion failed %s: %d: %s\n", \ - __FILE__, __LINE__, #x); \ - BUG(); \ - } \ -} while (0) -#else -#define ASSERT(x) do { } while (0) -#endif - -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_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, bool line_status); -void kvm_ioapic_clear_all(struct kvm_ioapic *ioapic, int irq_source_id); -void kvm_ioapic_reset(struct kvm_ioapic *ioapic); -int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, - struct kvm_lapic_irq *irq, unsigned long *dest_map); -int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state); -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/iodev.h b/virt/kvm/iodev.h deleted file mode 100644 index 12fd3caffd2b..000000000000 --- a/virt/kvm/iodev.h +++ /dev/null @@ -1,70 +0,0 @@ -/* - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License. - * - * 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, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. - */ - -#ifndef __KVM_IODEV_H__ -#define __KVM_IODEV_H__ - -#include <linux/kvm_types.h> -#include <asm/errno.h> - -struct kvm_io_device; - -/** - * kvm_io_device_ops are called under kvm slots_lock. - * read and write handlers return 0 if the transaction has been handled, - * or non-zero to have it passed to the next device. - **/ -struct kvm_io_device_ops { - int (*read)(struct kvm_io_device *this, - gpa_t addr, - int len, - void *val); - int (*write)(struct kvm_io_device *this, - gpa_t addr, - int len, - const void *val); - void (*destructor)(struct kvm_io_device *this); -}; - - -struct kvm_io_device { - const struct kvm_io_device_ops *ops; -}; - -static inline void kvm_iodevice_init(struct kvm_io_device *dev, - const struct kvm_io_device_ops *ops) -{ - dev->ops = ops; -} - -static inline int kvm_iodevice_read(struct kvm_io_device *dev, - gpa_t addr, int l, void *v) -{ - return dev->ops->read ? dev->ops->read(dev, addr, l, v) : -EOPNOTSUPP; -} - -static inline int kvm_iodevice_write(struct kvm_io_device *dev, - gpa_t addr, int l, const void *v) -{ - return dev->ops->write ? dev->ops->write(dev, addr, l, v) : -EOPNOTSUPP; -} - -static inline void kvm_iodevice_destructor(struct kvm_io_device *dev) -{ - if (dev->ops->destructor) - dev->ops->destructor(dev); -} - -#endif /* __KVM_IODEV_H__ */ diff --git a/virt/kvm/iommu.c b/virt/kvm/iommu.c deleted file mode 100644 index 72a130bc448a..000000000000 --- a/virt/kvm/iommu.c +++ /dev/null @@ -1,357 +0,0 @@ -/* - * Copyright (c) 2006, Intel Corporation. - * - * 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. - * - * Copyright (C) 2006-2008 Intel Corporation - * Copyright IBM Corporation, 2008 - * Copyright 2010 Red Hat, Inc. and/or its affiliates. - * - * Author: Allen M. Kay <allen.m.kay@intel.com> - * Author: Weidong Han <weidong.han@intel.com> - * Author: Ben-Ami Yassour <benami@il.ibm.com> - */ - -#include <linux/list.h> -#include <linux/kvm_host.h> -#include <linux/module.h> -#include <linux/pci.h> -#include <linux/stat.h> -#include <linux/dmar.h> -#include <linux/iommu.h> -#include <linux/intel-iommu.h> - -static bool allow_unsafe_assigned_interrupts; -module_param_named(allow_unsafe_assigned_interrupts, - allow_unsafe_assigned_interrupts, bool, S_IRUGO | S_IWUSR); -MODULE_PARM_DESC(allow_unsafe_assigned_interrupts, - "Enable device assignment on platforms without interrupt remapping support."); - -static int kvm_iommu_unmap_memslots(struct kvm *kvm); -static void kvm_iommu_put_pages(struct kvm *kvm, - gfn_t base_gfn, unsigned long npages); - -static pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn, - unsigned long size) -{ - gfn_t end_gfn; - pfn_t pfn; - - pfn = gfn_to_pfn_memslot(slot, gfn); - end_gfn = gfn + (size >> PAGE_SHIFT); - gfn += 1; - - if (is_error_noslot_pfn(pfn)) - return pfn; - - while (gfn < end_gfn) - gfn_to_pfn_memslot(slot, gfn++); - - return pfn; -} - -int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot) -{ - gfn_t gfn, end_gfn; - pfn_t pfn; - int r = 0; - struct iommu_domain *domain = kvm->arch.iommu_domain; - int flags; - - /* check if iommu exists and in use */ - if (!domain) - return 0; - - gfn = slot->base_gfn; - end_gfn = gfn + slot->npages; - - flags = IOMMU_READ; - if (!(slot->flags & KVM_MEM_READONLY)) - flags |= IOMMU_WRITE; - if (kvm->arch.iommu_flags & KVM_IOMMU_CACHE_COHERENCY) - flags |= IOMMU_CACHE; - - - while (gfn < end_gfn) { - unsigned long page_size; - - /* Check if already mapped */ - if (iommu_iova_to_phys(domain, gfn_to_gpa(gfn))) { - gfn += 1; - continue; - } - - /* Get the page size we could use to map */ - page_size = kvm_host_page_size(kvm, gfn); - - /* Make sure the page_size does not exceed the memslot */ - while ((gfn + (page_size >> PAGE_SHIFT)) > end_gfn) - page_size >>= 1; - - /* Make sure gfn is aligned to the page size we want to map */ - while ((gfn << PAGE_SHIFT) & (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. - */ - pfn = kvm_pin_pages(slot, gfn, page_size); - if (is_error_noslot_pfn(pfn)) { - gfn += 1; - continue; - } - - /* Map into IO address space */ - r = iommu_map(domain, gfn_to_gpa(gfn), pfn_to_hpa(pfn), - page_size, flags); - if (r) { - printk(KERN_ERR "kvm_iommu_map_address:" - "iommu failed to map pfn=%llx\n", pfn); - goto unmap_pages; - } - - gfn += page_size >> PAGE_SHIFT; - - - } - - return 0; - -unmap_pages: - kvm_iommu_put_pages(kvm, slot->base_gfn, gfn); - return r; -} - -static int kvm_iommu_map_memslots(struct kvm *kvm) -{ - int idx, r = 0; - struct kvm_memslots *slots; - struct kvm_memory_slot *memslot; - - idx = srcu_read_lock(&kvm->srcu); - slots = kvm_memslots(kvm); - - kvm_for_each_memslot(memslot, slots) { - r = kvm_iommu_map_pages(kvm, memslot); - if (r) - break; - } - srcu_read_unlock(&kvm->srcu, idx); - - return r; -} - -int kvm_assign_device(struct kvm *kvm, - struct kvm_assigned_dev_kernel *assigned_dev) -{ - struct pci_dev *pdev = NULL; - struct iommu_domain *domain = kvm->arch.iommu_domain; - int r, last_flags; - - /* check if iommu exists and in use */ - if (!domain) - return 0; - - pdev = assigned_dev->dev; - if (pdev == NULL) - return -ENODEV; - - r = iommu_attach_device(domain, &pdev->dev); - if (r) { - dev_err(&pdev->dev, "kvm assign device failed ret %d", r); - 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; - - /* Check if need to update IOMMU page table for guest memory */ - if ((last_flags ^ kvm->arch.iommu_flags) == - KVM_IOMMU_CACHE_COHERENCY) { - kvm_iommu_unmap_memslots(kvm); - r = kvm_iommu_map_memslots(kvm); - if (r) - goto out_unmap; - } - - 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)); - - return 0; -out_unmap: - kvm_iommu_unmap_memslots(kvm); - return r; -} - -int kvm_deassign_device(struct kvm *kvm, - struct kvm_assigned_dev_kernel *assigned_dev) -{ - struct iommu_domain *domain = kvm->arch.iommu_domain; - struct pci_dev *pdev = NULL; - - /* check if iommu exists and in use */ - if (!domain) - return 0; - - pdev = assigned_dev->dev; - if (pdev == NULL) - return -ENODEV; - - iommu_detach_device(domain, &pdev->dev); - - 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)); - - return 0; -} - -int kvm_iommu_map_guest(struct kvm *kvm) -{ - int r; - - if (!iommu_present(&pci_bus_type)) { - printk(KERN_ERR "%s: iommu not found\n", __func__); - return -ENODEV; - } - - mutex_lock(&kvm->slots_lock); - - kvm->arch.iommu_domain = iommu_domain_alloc(&pci_bus_type); - if (!kvm->arch.iommu_domain) { - r = -ENOMEM; - goto out_unlock; - } - - if (!allow_unsafe_assigned_interrupts && - !iommu_domain_has_cap(kvm->arch.iommu_domain, - IOMMU_CAP_INTR_REMAP)) { - printk(KERN_WARNING "%s: No interrupt remapping support," - " disallowing device assignment." - " Re-enble with \"allow_unsafe_assigned_interrupts=1\"" - " module option.\n", __func__); - iommu_domain_free(kvm->arch.iommu_domain); - kvm->arch.iommu_domain = NULL; - r = -EPERM; - goto out_unlock; - } - - r = kvm_iommu_map_memslots(kvm); - if (r) - kvm_iommu_unmap_memslots(kvm); - -out_unlock: - mutex_unlock(&kvm->slots_lock); - return r; -} - -static void kvm_unpin_pages(struct kvm *kvm, pfn_t pfn, unsigned long npages) -{ - unsigned long i; - - for (i = 0; i < npages; ++i) - kvm_release_pfn_clean(pfn + i); -} - -static void kvm_iommu_put_pages(struct kvm *kvm, - gfn_t base_gfn, unsigned long npages) -{ - struct iommu_domain *domain; - gfn_t end_gfn, gfn; - pfn_t pfn; - u64 phys; - - domain = kvm->arch.iommu_domain; - end_gfn = base_gfn + npages; - gfn = base_gfn; - - /* check if iommu exists and in use */ - if (!domain) - return; - - while (gfn < end_gfn) { - unsigned long unmap_pages; - size_t size; - - /* Get physical address */ - phys = iommu_iova_to_phys(domain, gfn_to_gpa(gfn)); - - if (!phys) { - gfn++; - continue; - } - - pfn = phys >> PAGE_SHIFT; - - /* Unmap address from IO address space */ - size = iommu_unmap(domain, gfn_to_gpa(gfn), PAGE_SIZE); - unmap_pages = 1ULL << get_order(size); - - /* Unpin all pages we just unmapped to not leak any memory */ - kvm_unpin_pages(kvm, pfn, unmap_pages); - - gfn += unmap_pages; - } -} - -void kvm_iommu_unmap_pages(struct kvm *kvm, struct kvm_memory_slot *slot) -{ - kvm_iommu_put_pages(kvm, slot->base_gfn, slot->npages); -} - -static int kvm_iommu_unmap_memslots(struct kvm *kvm) -{ - int idx; - struct kvm_memslots *slots; - struct kvm_memory_slot *memslot; - - idx = srcu_read_lock(&kvm->srcu); - slots = kvm_memslots(kvm); - - kvm_for_each_memslot(memslot, slots) - kvm_iommu_unmap_pages(kvm, memslot); - - srcu_read_unlock(&kvm->srcu, idx); - - return 0; -} - -int kvm_iommu_unmap_guest(struct kvm *kvm) -{ - struct iommu_domain *domain = kvm->arch.iommu_domain; - - /* check if iommu exists and in use */ - if (!domain) - return 0; - - mutex_lock(&kvm->slots_lock); - kvm_iommu_unmap_memslots(kvm); - kvm->arch.iommu_domain = NULL; - mutex_unlock(&kvm->slots_lock); - - iommu_domain_free(domain); - return 0; -} diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c deleted file mode 100644 index e2e6b4473a96..000000000000 --- a/virt/kvm/irq_comm.c +++ /dev/null @@ -1,372 +0,0 @@ -/* - * irq_comm.c: Common API for in kernel interrupt controller - * Copyright (c) 2007, Intel Corporation. - * - * 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. - * Authors: - * Yaozu (Eddie) Dong <Eddie.dong@intel.com> - * - * Copyright 2010 Red Hat, Inc. and/or its affiliates. - */ - -#include <linux/kvm_host.h> -#include <linux/slab.h> -#include <linux/export.h> -#include <trace/events/kvm.h> - -#include <asm/msidef.h> -#ifdef CONFIG_IA64 -#include <asm/iosapic.h> -#endif - -#include "irq.h" - -#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, - bool line_status) -{ -#ifdef CONFIG_X86 - struct kvm_pic *pic = pic_irqchip(kvm); - return kvm_pic_set_irq(pic, e->irqchip.pin, irq_source_id, level); -#else - return -1; -#endif -} - -static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e, - 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, - line_status); -} - -inline static bool kvm_is_dm_lowest_prio(struct kvm_lapic_irq *irq) -{ -#ifdef CONFIG_IA64 - return irq->delivery_mode == - (IOSAPIC_LOWEST_PRIORITY << IOSAPIC_DELIVERY_SHIFT); -#else - return irq->delivery_mode == APIC_DM_LOWEST; -#endif -} - -int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, - struct kvm_lapic_irq *irq, unsigned long *dest_map) -{ - int i, r = -1; - struct kvm_vcpu *vcpu, *lowest = NULL; - - if (irq->dest_mode == 0 && irq->dest_id == 0xff && - kvm_is_dm_lowest_prio(irq)) { - printk(KERN_INFO "kvm: apic: phys broadcast and lowest prio\n"); - irq->delivery_mode = APIC_DM_FIXED; - } - - if (kvm_irq_delivery_to_apic_fast(kvm, src, irq, &r, dest_map)) - return r; - - kvm_for_each_vcpu(i, vcpu, kvm) { - if (!kvm_apic_present(vcpu)) - continue; - - if (!kvm_apic_match_dest(vcpu, src, irq->shorthand, - irq->dest_id, irq->dest_mode)) - continue; - - if (!kvm_is_dm_lowest_prio(irq)) { - if (r < 0) - r = 0; - r += kvm_apic_set_irq(vcpu, irq, dest_map); - } else if (kvm_lapic_enabled(vcpu)) { - if (!lowest) - lowest = vcpu; - else if (kvm_apic_compare_prio(vcpu, lowest) < 0) - lowest = vcpu; - } - } - - if (lowest) - r = kvm_apic_set_irq(lowest, irq, dest_map); - - return r; -} - -static inline void kvm_set_msi_irq(struct kvm_kernel_irq_routing_entry *e, - struct kvm_lapic_irq *irq) -{ - trace_kvm_msi_set_irq(e->msi.address_lo, e->msi.data); - - irq->dest_id = (e->msi.address_lo & - MSI_ADDR_DEST_ID_MASK) >> MSI_ADDR_DEST_ID_SHIFT; - irq->vector = (e->msi.data & - MSI_DATA_VECTOR_MASK) >> MSI_DATA_VECTOR_SHIFT; - irq->dest_mode = (1 << MSI_ADDR_DEST_MODE_SHIFT) & e->msi.address_lo; - irq->trig_mode = (1 << MSI_DATA_TRIGGER_SHIFT) & e->msi.data; - irq->delivery_mode = e->msi.data & 0x700; - irq->level = 1; - irq->shorthand = 0; - /* TODO Deal with RH bit of MSI message address */ -} - -int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, - struct kvm *kvm, int irq_source_id, int level, bool line_status) -{ - struct kvm_lapic_irq irq; - - if (!level) - return -1; - - kvm_set_msi_irq(e, &irq); - - return kvm_irq_delivery_to_apic(kvm, NULL, &irq, NULL); -} - - -static int kvm_set_msi_inatomic(struct kvm_kernel_irq_routing_entry *e, - struct kvm *kvm) -{ - struct kvm_lapic_irq irq; - int r; - - kvm_set_msi_irq(e, &irq); - - if (kvm_irq_delivery_to_apic_fast(kvm, NULL, &irq, &r, NULL)) - return r; - else - return -EWOULDBLOCK; -} - -/* - * Deliver an IRQ in an atomic context if we can, or return a failure, - * user can retry in a process context. - * Return value: - * -EWOULDBLOCK - Can't deliver in atomic context: retry in a process context. - * Other values - No need to retry. - */ -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; - - trace_kvm_set_irq(irq, level, irq_source_id); - - /* - * Injection into either PIC or IOAPIC might need to scan all CPUs, - * which would need to be retried from thread context; when same GSI - * is connected to both PIC and IOAPIC, we'd have to report a - * partial failure here. - * Since there's no easy way to do this, we only support injecting MSI - * which is limited to 1:1 GSI mapping. - */ - rcu_read_lock(); - irq_rt = rcu_dereference(kvm->irq_routing); - if (irq < irq_rt->nr_rt_entries) - hlist_for_each_entry(e, &irq_rt->map[irq], link) { - if (likely(e->type == KVM_IRQ_ROUTING_MSI)) - ret = kvm_set_msi_inatomic(e, kvm); - else - ret = -EWOULDBLOCK; - break; - } - rcu_read_unlock(); - return ret; -} - -int kvm_request_irq_source_id(struct kvm *kvm) -{ - unsigned long *bitmap = &kvm->arch.irq_sources_bitmap; - int irq_source_id; - - mutex_lock(&kvm->irq_lock); - irq_source_id = find_first_zero_bit(bitmap, BITS_PER_LONG); - - if (irq_source_id >= BITS_PER_LONG) { - printk(KERN_WARNING "kvm: exhaust allocatable IRQ sources!\n"); - irq_source_id = -EFAULT; - goto unlock; - } - - ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID); -#ifdef CONFIG_X86 - ASSERT(irq_source_id != KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID); -#endif - set_bit(irq_source_id, bitmap); -unlock: - mutex_unlock(&kvm->irq_lock); - - return irq_source_id; -} - -void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id) -{ - ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID); -#ifdef CONFIG_X86 - ASSERT(irq_source_id != KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID); -#endif - - mutex_lock(&kvm->irq_lock); - if (irq_source_id < 0 || - irq_source_id >= BITS_PER_LONG) { - printk(KERN_ERR "kvm: IRQ source ID out of range!\n"); - goto unlock; - } - clear_bit(irq_source_id, &kvm->arch.irq_sources_bitmap); - if (!irqchip_in_kernel(kvm)) - goto unlock; - - kvm_ioapic_clear_all(kvm->arch.vioapic, irq_source_id); -#ifdef CONFIG_X86 - kvm_pic_clear_all(pic_irqchip(kvm), irq_source_id); -#endif -unlock: - mutex_unlock(&kvm->irq_lock); -} - -void kvm_register_irq_mask_notifier(struct kvm *kvm, int irq, - struct kvm_irq_mask_notifier *kimn) -{ - mutex_lock(&kvm->irq_lock); - kimn->irq = irq; - hlist_add_head_rcu(&kimn->link, &kvm->mask_notifier_list); - mutex_unlock(&kvm->irq_lock); -} - -void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq, - struct kvm_irq_mask_notifier *kimn) -{ - mutex_lock(&kvm->irq_lock); - hlist_del_rcu(&kimn->link); - mutex_unlock(&kvm->irq_lock); - synchronize_rcu(); -} - -void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin, - bool mask) -{ - struct kvm_irq_mask_notifier *kimn; - int gsi; - - rcu_read_lock(); - gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin]; - if (gsi != -1) - hlist_for_each_entry_rcu(kimn, &kvm->mask_notifier_list, link) - if (kimn->irq == gsi) - kimn->func(kimn, mask); - rcu_read_unlock(); -} - -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; - - switch (ue->type) { - case KVM_IRQ_ROUTING_IRQCHIP: - delta = 0; - switch (ue->u.irqchip.irqchip) { - case KVM_IRQCHIP_PIC_MASTER: - e->set = kvm_set_pic_irq; - max_pin = PIC_NUM_PINS; - break; - case KVM_IRQCHIP_PIC_SLAVE: - e->set = kvm_set_pic_irq; - max_pin = PIC_NUM_PINS; - delta = 8; - break; - case KVM_IRQCHIP_IOAPIC: - max_pin = KVM_IOAPIC_NUM_PINS; - e->set = kvm_set_ioapic_irq; - break; - default: - goto out; - } - e->irqchip.irqchip = ue->u.irqchip.irqchip; - e->irqchip.pin = ue->u.irqchip.pin + delta; - if (e->irqchip.pin >= max_pin) - goto out; - rt->chip[ue->u.irqchip.irqchip][e->irqchip.pin] = ue->gsi; - break; - case KVM_IRQ_ROUTING_MSI: - e->set = kvm_set_msi; - e->msi.address_lo = ue->u.msi.address_lo; - e->msi.address_hi = ue->u.msi.address_hi; - e->msi.data = ue->u.msi.data; - break; - default: - goto out; - } - - r = 0; -out: - return r; -} - -#define IOAPIC_ROUTING_ENTRY(irq) \ - { .gsi = irq, .type = KVM_IRQ_ROUTING_IRQCHIP, \ - .u.irqchip.irqchip = KVM_IRQCHIP_IOAPIC, .u.irqchip.pin = (irq) } -#define ROUTING_ENTRY1(irq) IOAPIC_ROUTING_ENTRY(irq) - -#ifdef CONFIG_X86 -# define PIC_ROUTING_ENTRY(irq) \ - { .gsi = irq, .type = KVM_IRQ_ROUTING_IRQCHIP, \ - .u.irqchip.irqchip = SELECT_PIC(irq), .u.irqchip.pin = (irq) % 8 } -# define ROUTING_ENTRY2(irq) \ - IOAPIC_ROUTING_ENTRY(irq), PIC_ROUTING_ENTRY(irq) -#else -# define ROUTING_ENTRY2(irq) \ - IOAPIC_ROUTING_ENTRY(irq) -#endif - -static const struct kvm_irq_routing_entry default_routing[] = { - ROUTING_ENTRY2(0), ROUTING_ENTRY2(1), - ROUTING_ENTRY2(2), ROUTING_ENTRY2(3), - ROUTING_ENTRY2(4), ROUTING_ENTRY2(5), - ROUTING_ENTRY2(6), ROUTING_ENTRY2(7), - ROUTING_ENTRY2(8), ROUTING_ENTRY2(9), - ROUTING_ENTRY2(10), ROUTING_ENTRY2(11), - ROUTING_ENTRY2(12), ROUTING_ENTRY2(13), - ROUTING_ENTRY2(14), ROUTING_ENTRY2(15), - ROUTING_ENTRY1(16), ROUTING_ENTRY1(17), - ROUTING_ENTRY1(18), ROUTING_ENTRY1(19), - ROUTING_ENTRY1(20), ROUTING_ENTRY1(21), - ROUTING_ENTRY1(22), ROUTING_ENTRY1(23), -#ifdef CONFIG_IA64 - ROUTING_ENTRY1(24), ROUTING_ENTRY1(25), - ROUTING_ENTRY1(26), ROUTING_ENTRY1(27), - ROUTING_ENTRY1(28), ROUTING_ENTRY1(29), - ROUTING_ENTRY1(30), ROUTING_ENTRY1(31), - ROUTING_ENTRY1(32), ROUTING_ENTRY1(33), - ROUTING_ENTRY1(34), ROUTING_ENTRY1(35), - ROUTING_ENTRY1(36), ROUTING_ENTRY1(37), - ROUTING_ENTRY1(38), ROUTING_ENTRY1(39), - ROUTING_ENTRY1(40), ROUTING_ENTRY1(41), - ROUTING_ENTRY1(42), ROUTING_ENTRY1(43), - ROUTING_ENTRY1(44), ROUTING_ENTRY1(45), - ROUTING_ENTRY1(46), ROUTING_ENTRY1(47), -#endif -}; - -int kvm_setup_default_irq_routing(struct kvm *kvm) -{ - return kvm_set_irq_routing(kvm, default_routing, - ARRAY_SIZE(default_routing), 0); -} diff --git a/virt/kvm/irqchip.c b/virt/kvm/irqchip.c index 20dc9e4a8f6c..6ccabfd32287 100644 --- a/virt/kvm/irqchip.c +++ b/virt/kvm/irqchip.c @@ -1,22 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * 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: @@ -26,81 +14,49 @@ #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) +int kvm_irq_map_gsi(struct kvm *kvm, + struct kvm_kernel_irq_routing_entry *entries, int gsi) { - struct kvm_irq_ack_notifier *kian; - int gsi; - - rcu_read_lock(); - gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin]; - if (gsi != -1) - hlist_for_each_entry_rcu(kian, &kvm->irq_ack_notifier_list, - link) - if (kian->gsi == gsi) { - rcu_read_unlock(); - return true; - } - - rcu_read_unlock(); - - return false; -} -EXPORT_SYMBOL_GPL(kvm_irq_has_notifier); + struct kvm_irq_routing_table *irq_rt; + struct kvm_kernel_irq_routing_entry *e; + int n = 0; + + irq_rt = srcu_dereference_check(kvm->irq_routing, &kvm->irq_srcu, + lockdep_is_held(&kvm->irq_lock)); + if (irq_rt && gsi < irq_rt->nr_rt_entries) { + hlist_for_each_entry(e, &irq_rt->map[gsi], link) { + entries[n] = *e; + ++n; + } + } -void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin) -{ - struct kvm_irq_ack_notifier *kian; - int gsi; - - trace_kvm_ack_irq(irqchip, pin); - - rcu_read_lock(); - gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin]; - if (gsi != -1) - hlist_for_each_entry_rcu(kian, &kvm->irq_ack_notifier_list, - link) - if (kian->gsi == gsi) - kian->irq_acked(kian); - rcu_read_unlock(); + return n; } -void kvm_register_irq_ack_notifier(struct kvm *kvm, - struct kvm_irq_ack_notifier *kian) +int kvm_irq_map_chip_pin(struct kvm *kvm, unsigned irqchip, unsigned pin) { - mutex_lock(&kvm->irq_lock); - hlist_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 -} + struct kvm_irq_routing_table *irq_rt; -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(); -#ifdef __KVM_HAVE_IOAPIC - kvm_vcpu_request_scan_ioapic(kvm); -#endif + irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu); + return irq_rt->chip[irqchip][pin]; } int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi) { struct kvm_kernel_irq_routing_entry route; - if (!irqchip_in_kernel(kvm) || msi->flags != 0) + if (!kvm_arch_irqchip_in_kernel(kvm) || (msi->flags & ~KVM_MSI_VALID_DEVID)) return -EINVAL; route.msi.address_lo = msi->address_lo; route.msi.address_hi = msi->address_hi; route.msi.data = msi->data; + route.msi.flags = msi->flags; + route.msi.devid = msi->devid; return kvm_set_msi(&route, kvm, KVM_USERSPACE_IRQ_SOURCE_ID, 1, false); } @@ -114,9 +70,8 @@ int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi) int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level, bool line_status) { - struct kvm_kernel_irq_routing_entry *e, irq_set[KVM_NR_IRQCHIPS]; - int ret = -1, i = 0; - struct kvm_irq_routing_table *irq_rt; + struct kvm_kernel_irq_routing_entry irq_set[KVM_NR_IRQCHIPS]; + int ret = -1, i, idx; trace_kvm_set_irq(irq, level, irq_source_id); @@ -124,14 +79,11 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level, * IOAPIC. So set the bit in both. The guest will ignore * writes to the unused one. */ - rcu_read_lock(); - irq_rt = rcu_dereference(kvm->irq_routing); - if (irq < irq_rt->nr_rt_entries) - hlist_for_each_entry(e, &irq_rt->map[irq], link) - irq_set[i++] = *e; - rcu_read_unlock(); - - while(i--) { + idx = srcu_read_lock(&kvm->irq_srcu); + i = kvm_irq_map_gsi(kvm, irq_set, irq); + srcu_read_unlock(&kvm->irq_srcu, idx); + + while (i--) { int r; r = irq_set[i].set(&irq_set[i], kvm, irq_source_id, level, line_status); @@ -144,40 +96,73 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level, return ret; } +static void free_irq_routing_table(struct kvm_irq_routing_table *rt) +{ + int i; + + if (!rt) + return; + + for (i = 0; i < rt->nr_rt_entries; ++i) { + struct kvm_kernel_irq_routing_entry *e; + struct hlist_node *n; + + hlist_for_each_entry_safe(e, n, &rt->map[i], link) { + hlist_del(&e->link); + kfree(e); + } + } + + kfree(rt); +} + 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); + struct kvm_irq_routing_table *rt = rcu_access_pointer(kvm->irq_routing); + free_irq_routing_table(rt); } -static int setup_routing_entry(struct kvm_irq_routing_table *rt, +static int setup_routing_entry(struct kvm *kvm, + 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; + int r; + u32 gsi = array_index_nospec(ue->gsi, KVM_MAX_IRQ_ROUTES); /* * Do not allow GSI to be mapped to the same irqchip more than once. - * Allow only one to one mapping between GSI and MSI. + * Allow only one to one mapping between GSI and non-irqchip routing. */ - hlist_for_each_entry(ei, &rt->map[ue->gsi], link) - if (ei->type == KVM_IRQ_ROUTING_MSI || - ue->type == KVM_IRQ_ROUTING_MSI || + hlist_for_each_entry(ei, &rt->map[gsi], link) + if (ei->type != KVM_IRQ_ROUTING_IRQCHIP || + ue->type != KVM_IRQ_ROUTING_IRQCHIP || ue->u.irqchip.irqchip == ei->irqchip.irqchip) - return r; + return -EINVAL; - e->gsi = ue->gsi; + e->gsi = gsi; e->type = ue->type; - r = kvm_set_routing_entry(rt, e, ue); + r = kvm_set_routing_entry(kvm, e, ue); if (r) - goto out; + return r; + if (e->type == KVM_IRQ_ROUTING_IRQCHIP) + rt->chip[e->irqchip.irqchip][e->irqchip.pin] = e->gsi; hlist_add_head(&e->link, &rt->map[e->gsi]); - r = 0; -out: - return r; + + return 0; +} + +void __attribute__((weak)) kvm_arch_irq_routing_update(struct kvm *kvm) +{ +} + +bool __weak kvm_arch_can_set_irq_routing(struct kvm *kvm) +{ + return true; } int kvm_set_irq_routing(struct kvm *kvm, @@ -186,6 +171,7 @@ int kvm_set_irq_routing(struct kvm *kvm, unsigned flags) { struct kvm_irq_routing_table *new, *old; + struct kvm_kernel_irq_routing_entry *e; u32 i, j, nr_rt_entries = 0; int r; @@ -197,41 +183,79 @@ int kvm_set_irq_routing(struct kvm *kvm, 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); - + new = kzalloc(struct_size(new, map, nr_rt_entries), GFP_KERNEL_ACCOUNT); 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) + r = -ENOMEM; + e = kzalloc(sizeof(*e), GFP_KERNEL_ACCOUNT); + if (!e) goto out; - r = setup_routing_entry(new, &new->rt_entries[i], ue); + + r = -EINVAL; + switch (ue->type) { + case KVM_IRQ_ROUTING_MSI: + if (ue->flags & ~KVM_MSI_VALID_DEVID) + goto free_entry; + break; + default: + if (ue->flags) + goto free_entry; + break; + } + r = setup_routing_entry(kvm, new, e, ue); if (r) - goto out; + goto free_entry; ++ue; } mutex_lock(&kvm->irq_lock); - old = kvm->irq_routing; - kvm_irq_routing_update(kvm, new); + old = rcu_dereference_protected(kvm->irq_routing, 1); + rcu_assign_pointer(kvm->irq_routing, new); + kvm_irq_routing_update(kvm); + kvm_arch_irq_routing_update(kvm); mutex_unlock(&kvm->irq_lock); - synchronize_rcu(); + synchronize_srcu_expedited(&kvm->irq_srcu); new = old; r = 0; + goto out; +free_entry: + kfree(e); out: - kfree(new); + free_irq_routing_table(new); + return r; } + +/* + * Allocate empty IRQ routing by default so that additional setup isn't needed + * when userspace-driven IRQ routing is activated, and so that kvm->irq_routing + * is guaranteed to be non-NULL. + */ +int kvm_init_irq_routing(struct kvm *kvm) +{ + struct kvm_irq_routing_table *new; + int chip_size; + + new = kzalloc(struct_size(new, map, 1), GFP_KERNEL_ACCOUNT); + if (!new) + return -ENOMEM; + + new->nr_rt_entries = 1; + + chip_size = sizeof(int) * KVM_NR_IRQCHIPS * KVM_IRQCHIP_NUM_PINS; + memset(new->chip, -1, chip_size); + + RCU_INIT_POINTER(kvm->irq_routing, new); + + return 0; +} diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 1580dd4ace4e..5fcd401a5897 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1,8 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-only /* - * Kernel-based Virtual Machine driver for Linux - * - * This module enables machines with Intel VT-x extensions to run virtual - * machines without emulation or binary translation. + * Kernel-based Virtual Machine (KVM) Hypervisor * * Copyright (C) 2006 Qumranet, Inc. * Copyright 2010 Red Hat, Inc. and/or its affiliates. @@ -10,13 +8,9 @@ * Authors: * Avi Kivity <avi@qumranet.com> * Yaniv Kamay <yaniv@qumranet.com> - * - * This work is licensed under the terms of the GNU GPL, version 2. See - * the COPYING file in the top-level directory. - * */ -#include "iodev.h" +#include <kvm/iodev.h> #include <linux/kvm_host.h> #include <linux/kvm.h> @@ -32,7 +26,9 @@ #include <linux/file.h> #include <linux/syscore_ops.h> #include <linux/cpu.h> -#include <linux/sched.h> +#include <linux/sched/signal.h> +#include <linux/sched/mm.h> +#include <linux/sched/stat.h> #include <linux/cpumask.h> #include <linux/smp.h> #include <linux/anon_inodes.h> @@ -49,369 +45,834 @@ #include <linux/slab.h> #include <linux/sort.h> #include <linux/bsearch.h> +#include <linux/io.h> +#include <linux/lockdep.h> +#include <linux/kthread.h> +#include <linux/suspend.h> +#include <linux/rseq.h> #include <asm/processor.h> -#include <asm/io.h> -#include <asm/uaccess.h> -#include <asm/pgtable.h> +#include <asm/ioctl.h> +#include <linux/uaccess.h> #include "coalesced_mmio.h" #include "async_pf.h" +#include "kvm_mm.h" +#include "vfio.h" + +#include <trace/events/ipi.h> #define CREATE_TRACE_POINTS #include <trace/events/kvm.h> +#include <linux/kvm_dirty_ring.h> + + +/* Worst case buffer size needed for holding an integer. */ +#define ITOA_MAX_LEN 12 + MODULE_AUTHOR("Qumranet"); +MODULE_DESCRIPTION("Kernel-based Virtual Machine (KVM) Hypervisor"); MODULE_LICENSE("GPL"); +/* Architectures should define their poll value according to the halt latency */ +unsigned int halt_poll_ns = KVM_HALT_POLL_NS_DEFAULT; +module_param(halt_poll_ns, uint, 0644); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(halt_poll_ns); + +/* Default doubles per-vcpu halt_poll_ns. */ +unsigned int halt_poll_ns_grow = 2; +module_param(halt_poll_ns_grow, uint, 0644); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(halt_poll_ns_grow); + +/* The start value to grow halt_poll_ns from */ +unsigned int halt_poll_ns_grow_start = 10000; /* 10us */ +module_param(halt_poll_ns_grow_start, uint, 0644); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(halt_poll_ns_grow_start); + +/* Default halves per-vcpu halt_poll_ns. */ +unsigned int halt_poll_ns_shrink = 2; +module_param(halt_poll_ns_shrink, uint, 0644); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(halt_poll_ns_shrink); + +/* + * Allow direct access (from KVM or the CPU) without MMU notifier protection + * to unpinned pages. + */ +static bool allow_unsafe_mappings; +module_param(allow_unsafe_mappings, bool, 0444); + /* * Ordering of locks: * - * kvm->lock --> kvm->slots_lock --> kvm->irq_lock + * kvm->lock --> kvm->slots_lock --> kvm->irq_lock */ -DEFINE_RAW_SPINLOCK(kvm_lock); +DEFINE_MUTEX(kvm_lock); LIST_HEAD(vm_list); -static cpumask_var_t cpus_hardware_enabled; -static int kvm_usage_count = 0; -static atomic_t hardware_enable_failed; - -struct kmem_cache *kvm_vcpu_cache; -EXPORT_SYMBOL_GPL(kvm_vcpu_cache); +static struct kmem_cache *kvm_vcpu_cache; static __read_mostly struct preempt_ops kvm_preempt_ops; +static DEFINE_PER_CPU(struct kvm_vcpu *, kvm_running_vcpu); + +static struct dentry *kvm_debugfs_dir; -struct dentry *kvm_debugfs_dir; +static const struct file_operations stat_fops_per_vm; static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl, unsigned long arg); -#ifdef CONFIG_COMPAT +#ifdef CONFIG_KVM_COMPAT static long kvm_vcpu_compat_ioctl(struct file *file, unsigned int ioctl, unsigned long arg); +#define KVM_COMPAT(c) .compat_ioctl = (c) +#else +/* + * For architectures that don't implement a compat infrastructure, + * adopt a double line of defense: + * - Prevent a compat task from opening /dev/kvm + * - If the open has been done by a 64bit task, and the KVM fd + * passed to a compat task, let the ioctls fail. + */ +static long kvm_no_compat_ioctl(struct file *file, unsigned int ioctl, + unsigned long arg) { return -EINVAL; } + +static int kvm_no_compat_open(struct inode *inode, struct file *file) +{ + return is_compat_task() ? -ENODEV : 0; +} +#define KVM_COMPAT(c) .compat_ioctl = kvm_no_compat_ioctl, \ + .open = kvm_no_compat_open #endif -static int hardware_enable_all(void); -static void hardware_disable_all(void); static void kvm_io_bus_destroy(struct kvm_io_bus *bus); -bool kvm_rebooting; -EXPORT_SYMBOL_GPL(kvm_rebooting); +#define KVM_EVENT_CREATE_VM 0 +#define KVM_EVENT_DESTROY_VM 1 +static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm); +static unsigned long long kvm_createvm_count; +static unsigned long long kvm_active_vms; -static bool largepages_enabled = true; +static DEFINE_PER_CPU(cpumask_var_t, cpu_kick_mask); -bool kvm_is_mmio_pfn(pfn_t pfn) +__weak void kvm_arch_guest_memory_reclaimed(struct kvm *kvm) { - 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); - } - - return true; } /* * Switches to specified vcpu, until a matching vcpu_put() */ -int vcpu_load(struct kvm_vcpu *vcpu) +void vcpu_load(struct kvm_vcpu *vcpu) { - int cpu; + int cpu = get_cpu(); - if (mutex_lock_killable(&vcpu->mutex)) - return -EINTR; - if (unlikely(vcpu->pid != current->pids[PIDTYPE_PID].pid)) { - /* The thread running this VCPU changed. */ - struct pid *oldpid = vcpu->pid; - struct pid *newpid = get_task_pid(current, PIDTYPE_PID); - rcu_assign_pointer(vcpu->pid, newpid); - synchronize_rcu(); - put_pid(oldpid); - } - cpu = get_cpu(); + __this_cpu_write(kvm_running_vcpu, vcpu); preempt_notifier_register(&vcpu->preempt_notifier); kvm_arch_vcpu_load(vcpu, cpu); put_cpu(); - return 0; } +EXPORT_SYMBOL_FOR_KVM_INTERNAL(vcpu_load); void vcpu_put(struct kvm_vcpu *vcpu) { preempt_disable(); kvm_arch_vcpu_put(vcpu); preempt_notifier_unregister(&vcpu->preempt_notifier); + __this_cpu_write(kvm_running_vcpu, NULL); preempt_enable(); - mutex_unlock(&vcpu->mutex); } +EXPORT_SYMBOL_FOR_KVM_INTERNAL(vcpu_put); -static void ack_flush(void *_completed) +/* TODO: merge with kvm_arch_vcpu_should_kick */ +static bool kvm_request_needs_ipi(struct kvm_vcpu *vcpu, unsigned req) { + int mode = kvm_vcpu_exiting_guest_mode(vcpu); + + /* + * We need to wait for the VCPU to reenable interrupts and get out of + * READING_SHADOW_PAGE_TABLES mode. + */ + if (req & KVM_REQUEST_WAIT) + return mode != OUTSIDE_GUEST_MODE; + + /* + * Need to kick a running VCPU, but otherwise there is nothing to do. + */ + return mode == IN_GUEST_MODE; } -static bool make_all_cpus_request(struct kvm *kvm, unsigned int req) +static void ack_kick(void *_completed) { - int i, cpu, me; - cpumask_var_t cpus; - bool called = true; - struct kvm_vcpu *vcpu; +} + +static inline bool kvm_kick_many_cpus(struct cpumask *cpus, bool wait) +{ + if (cpumask_empty(cpus)) + return false; - zalloc_cpumask_var(&cpus, GFP_ATOMIC); + smp_call_function_many(cpus, ack_kick, NULL, wait); + return true; +} + +static void kvm_make_vcpu_request(struct kvm_vcpu *vcpu, unsigned int req, + struct cpumask *tmp, int current_cpu) +{ + int cpu; + + if (likely(!(req & KVM_REQUEST_NO_ACTION))) + __kvm_make_request(req, vcpu); + + if (!(req & KVM_REQUEST_NO_WAKEUP) && kvm_vcpu_wake_up(vcpu)) + return; + + /* + * Note, the vCPU could get migrated to a different pCPU at any point + * after kvm_request_needs_ipi(), which could result in sending an IPI + * to the previous pCPU. But, that's OK because the purpose of the IPI + * is to ensure the vCPU returns to OUTSIDE_GUEST_MODE, which is + * satisfied if the vCPU migrates. Entering READING_SHADOW_PAGE_TABLES + * after this point is also OK, as the requirement is only that KVM wait + * for vCPUs that were reading SPTEs _before_ any changes were + * finalized. See kvm_vcpu_kick() for more details on handling requests. + */ + if (kvm_request_needs_ipi(vcpu, req)) { + cpu = READ_ONCE(vcpu->cpu); + if (cpu != -1 && cpu != current_cpu) + __cpumask_set_cpu(cpu, tmp); + } +} + +bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, + unsigned long *vcpu_bitmap) +{ + struct kvm_vcpu *vcpu; + struct cpumask *cpus; + int i, me; + bool called; me = get_cpu(); - kvm_for_each_vcpu(i, vcpu, kvm) { - kvm_make_request(req, vcpu); - cpu = vcpu->cpu; - /* Set ->requests bit before we read ->mode */ - smp_mb(); + cpus = this_cpu_cpumask_var_ptr(cpu_kick_mask); + cpumask_clear(cpus); - if (cpus != NULL && cpu != -1 && cpu != me && - kvm_vcpu_exiting_guest_mode(vcpu) != OUTSIDE_GUEST_MODE) - cpumask_set_cpu(cpu, cpus); + for_each_set_bit(i, vcpu_bitmap, KVM_MAX_VCPUS) { + vcpu = kvm_get_vcpu(kvm, i); + if (!vcpu) + continue; + kvm_make_vcpu_request(vcpu, req, cpus, me); } - if (unlikely(cpus == NULL)) - smp_call_function_many(cpu_online_mask, ack_flush, NULL, 1); - else if (!cpumask_empty(cpus)) - smp_call_function_many(cpus, ack_flush, NULL, 1); - else - called = false; + + called = kvm_kick_many_cpus(cpus, !!(req & KVM_REQUEST_WAIT)); + put_cpu(); + + return called; +} + +bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req) +{ + struct kvm_vcpu *vcpu; + struct cpumask *cpus; + unsigned long i; + bool called; + int me; + + me = get_cpu(); + + cpus = this_cpu_cpumask_var_ptr(cpu_kick_mask); + cpumask_clear(cpus); + + kvm_for_each_vcpu(i, vcpu, kvm) + kvm_make_vcpu_request(vcpu, req, cpus, me); + + called = kvm_kick_many_cpus(cpus, !!(req & KVM_REQUEST_WAIT)); put_cpu(); - free_cpumask_var(cpus); + return called; } +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_make_all_cpus_request); void kvm_flush_remote_tlbs(struct kvm *kvm) { - long dirty_count = kvm->tlbs_dirty; + ++kvm->stat.generic.remote_tlb_flush_requests; + + /* + * We want to publish modifications to the page tables before reading + * mode. Pairs with a memory barrier in arch-specific code. + * - x86: smp_mb__after_srcu_read_unlock in vcpu_enter_guest + * and smp_mb in walk_shadow_page_lockless_begin/end. + * - powerpc: smp_mb in kvmppc_prepare_to_enter. + * + * There is already an smp_mb__after_atomic() before + * kvm_make_all_cpus_request() reads vcpu->mode. We reuse that + * barrier here. + */ + if (!kvm_arch_flush_remote_tlbs(kvm) + || kvm_make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH)) + ++kvm->stat.generic.remote_tlb_flush; +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_flush_remote_tlbs); + +void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages) +{ + if (!kvm_arch_flush_remote_tlbs_range(kvm, gfn, nr_pages)) + return; - smp_mb(); - if (make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH)) - ++kvm->stat.remote_tlb_flush; - cmpxchg(&kvm->tlbs_dirty, dirty_count, 0); + /* + * Fall back to a flushing entire TLBs if the architecture range-based + * TLB invalidation is unsupported or can't be performed for whatever + * reason. + */ + kvm_flush_remote_tlbs(kvm); } -void kvm_reload_remote_mmus(struct kvm *kvm) +void kvm_flush_remote_tlbs_memslot(struct kvm *kvm, + const struct kvm_memory_slot *memslot) { - make_all_cpus_request(kvm, KVM_REQ_MMU_RELOAD); + /* + * All current use cases for flushing the TLBs for a specific memslot + * are related to dirty logging, and many do the TLB flush out of + * mmu_lock. The interaction between the various operations on memslot + * must be serialized by slots_lock to ensure the TLB flush from one + * operation is observed by any other operation on the same memslot. + */ + lockdep_assert_held(&kvm->slots_lock); + kvm_flush_remote_tlbs_range(kvm, memslot->base_gfn, memslot->npages); } -void kvm_make_mclock_inprogress_request(struct kvm *kvm) +static void kvm_flush_shadow_all(struct kvm *kvm) { - make_all_cpus_request(kvm, KVM_REQ_MCLOCK_INPROGRESS); + kvm_arch_flush_shadow_all(kvm); + kvm_arch_guest_memory_reclaimed(kvm); } -void kvm_make_scan_ioapic_request(struct kvm *kvm) +#ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE +static inline void *mmu_memory_cache_alloc_obj(struct kvm_mmu_memory_cache *mc, + gfp_t gfp_flags) { - make_all_cpus_request(kvm, KVM_REQ_SCAN_IOAPIC); + void *page; + + gfp_flags |= mc->gfp_zero; + + if (mc->kmem_cache) + return kmem_cache_alloc(mc->kmem_cache, gfp_flags); + + page = (void *)__get_free_page(gfp_flags); + if (page && mc->init_value) + memset64(page, mc->init_value, PAGE_SIZE / sizeof(u64)); + return page; } -int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id) +int __kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int capacity, int min) { - struct page *page; - int r; + gfp_t gfp = mc->gfp_custom ? mc->gfp_custom : GFP_KERNEL_ACCOUNT; + void *obj; + + if (mc->nobjs >= min) + return 0; + + if (unlikely(!mc->objects)) { + if (WARN_ON_ONCE(!capacity)) + return -EIO; + + /* + * Custom init values can be used only for page allocations, + * and obviously conflict with __GFP_ZERO. + */ + if (WARN_ON_ONCE(mc->init_value && (mc->kmem_cache || mc->gfp_zero))) + return -EIO; + mc->objects = kvmalloc_array(capacity, sizeof(void *), gfp); + if (!mc->objects) + return -ENOMEM; + + mc->capacity = capacity; + } + + /* It is illegal to request a different capacity across topups. */ + if (WARN_ON_ONCE(mc->capacity != capacity)) + return -EIO; + + while (mc->nobjs < mc->capacity) { + obj = mmu_memory_cache_alloc_obj(mc, gfp); + if (!obj) + return mc->nobjs >= min ? 0 : -ENOMEM; + mc->objects[mc->nobjs++] = obj; + } + return 0; +} + +int kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int min) +{ + return __kvm_mmu_topup_memory_cache(mc, KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE, min); +} + +int kvm_mmu_memory_cache_nr_free_objects(struct kvm_mmu_memory_cache *mc) +{ + return mc->nobjs; +} + +void kvm_mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc) +{ + while (mc->nobjs) { + if (mc->kmem_cache) + kmem_cache_free(mc->kmem_cache, mc->objects[--mc->nobjs]); + else + free_page((unsigned long)mc->objects[--mc->nobjs]); + } + + kvfree(mc->objects); + + mc->objects = NULL; + mc->capacity = 0; +} + +void *kvm_mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc) +{ + void *p; + + if (WARN_ON(!mc->nobjs)) + p = mmu_memory_cache_alloc_obj(mc, GFP_ATOMIC | __GFP_ACCOUNT); + else + p = mc->objects[--mc->nobjs]; + BUG_ON(!p); + return p; +} +#endif + +static void kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id) +{ mutex_init(&vcpu->mutex); vcpu->cpu = -1; vcpu->kvm = kvm; vcpu->vcpu_id = id; vcpu->pid = NULL; - init_waitqueue_head(&vcpu->wq); + rwlock_init(&vcpu->pid_lock); +#ifndef __KVM_HAVE_ARCH_WQP + rcuwait_init(&vcpu->wait); +#endif kvm_async_pf_vcpu_init(vcpu); - page = alloc_page(GFP_KERNEL | __GFP_ZERO); - if (!page) { - r = -ENOMEM; - goto fail; - } - vcpu->run = page_address(page); - kvm_vcpu_set_in_spin_loop(vcpu, false); kvm_vcpu_set_dy_eligible(vcpu, false); vcpu->preempted = false; + vcpu->ready = false; + preempt_notifier_init(&vcpu->preempt_notifier, &kvm_preempt_ops); + vcpu->last_used_slot = NULL; - r = kvm_arch_vcpu_init(vcpu); - if (r < 0) - goto fail_free_run; - return 0; - -fail_free_run: - free_page((unsigned long)vcpu->run); -fail: - return r; + /* Fill the stats id string for the vcpu */ + snprintf(vcpu->stats_id, sizeof(vcpu->stats_id), "kvm-%d/vcpu-%d", + task_pid_nr(current), id); } -EXPORT_SYMBOL_GPL(kvm_vcpu_init); -void kvm_vcpu_uninit(struct kvm_vcpu *vcpu) +static void kvm_vcpu_destroy(struct kvm_vcpu *vcpu) { + kvm_arch_vcpu_destroy(vcpu); + kvm_dirty_ring_free(&vcpu->dirty_ring); + + /* + * No need for rcu_read_lock as VCPU_RUN is the only place that changes + * the vcpu->pid pointer, and at destruction time all file descriptors + * are already gone. + */ put_pid(vcpu->pid); - kvm_arch_vcpu_uninit(vcpu); + free_page((unsigned long)vcpu->run); + kmem_cache_free(kvm_vcpu_cache, vcpu); +} + +void kvm_destroy_vcpus(struct kvm *kvm) +{ + unsigned long i; + struct kvm_vcpu *vcpu; + + kvm_for_each_vcpu(i, vcpu, kvm) { + kvm_vcpu_destroy(vcpu); + xa_erase(&kvm->vcpu_array, i); + + /* + * Assert that the vCPU isn't visible in any way, to ensure KVM + * doesn't trigger a use-after-free if destroying vCPUs results + * in VM-wide request, e.g. to flush remote TLBs when tearing + * down MMUs, or to mark the VM dead if a KVM_BUG_ON() fires. + */ + WARN_ON_ONCE(xa_load(&kvm->vcpu_array, i) || kvm_get_vcpu(kvm, i)); + } + + atomic_set(&kvm->online_vcpus, 0); } -EXPORT_SYMBOL_GPL(kvm_vcpu_uninit); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_destroy_vcpus); -#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) +#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER static inline struct kvm *mmu_notifier_to_kvm(struct mmu_notifier *mn) { return container_of(mn, struct kvm, mmu_notifier); } -static void kvm_mmu_notifier_invalidate_page(struct mmu_notifier *mn, - struct mm_struct *mm, - unsigned long address) -{ - struct kvm *kvm = mmu_notifier_to_kvm(mn); - int need_tlb_flush, idx; +typedef bool (*gfn_handler_t)(struct kvm *kvm, struct kvm_gfn_range *range); + +typedef void (*on_lock_fn_t)(struct kvm *kvm); +struct kvm_mmu_notifier_range { /* - * When ->invalidate_page runs, the linux pte has been zapped - * already but the page is still allocated until - * ->invalidate_page returns. So if we increase the sequence - * here the kvm page fault will notice if the spte can't be - * established because the page is going to be freed. If - * instead the kvm page fault establishes the spte before - * ->invalidate_page runs, kvm_unmap_hva will release it - * before returning. - * - * The sequence increase only need to be seen at spin_unlock - * time, and not at spin_lock time. - * - * Increasing the sequence after the spin_unlock would be - * unsafe because the kvm page fault could then establish the - * pte after kvm_unmap_hva returned, without noticing the page - * is going to be freed. + * 64-bit addresses, as KVM notifiers can operate on host virtual + * addresses (unsigned long) and guest physical addresses (64-bit). */ + u64 start; + u64 end; + union kvm_mmu_notifier_arg arg; + gfn_handler_t handler; + on_lock_fn_t on_lock; + bool flush_on_ret; + bool may_block; + bool lockless; +}; + +/* + * The inner-most helper returns a tuple containing the return value from the + * arch- and action-specific handler, plus a flag indicating whether or not at + * least one memslot was found, i.e. if the handler found guest memory. + * + * Note, most notifiers are averse to booleans, so even though KVM tracks the + * return from arch code as a bool, outer helpers will cast it to an int. :-( + */ +typedef struct kvm_mmu_notifier_return { + bool ret; + bool found_memslot; +} kvm_mn_ret_t; + +/* + * Use a dedicated stub instead of NULL to indicate that there is no callback + * function/handler. The compiler technically can't guarantee that a real + * function will have a non-zero address, and so it will generate code to + * check for !NULL, whereas comparing against a stub will be elided at compile + * time (unless the compiler is getting long in the tooth, e.g. gcc 4.9). + */ +static void kvm_null_fn(void) +{ + +} +#define IS_KVM_NULL_FN(fn) ((fn) == (void *)kvm_null_fn) + +/* Iterate over each memslot intersecting [start, last] (inclusive) range */ +#define kvm_for_each_memslot_in_hva_range(node, slots, start, last) \ + for (node = interval_tree_iter_first(&slots->hva_tree, start, last); \ + node; \ + node = interval_tree_iter_next(node, start, last)) \ + +static __always_inline kvm_mn_ret_t kvm_handle_hva_range(struct kvm *kvm, + const struct kvm_mmu_notifier_range *range) +{ + struct kvm_mmu_notifier_return r = { + .ret = false, + .found_memslot = false, + }; + struct kvm_gfn_range gfn_range; + struct kvm_memory_slot *slot; + struct kvm_memslots *slots; + int i, idx; + + if (WARN_ON_ONCE(range->end <= range->start)) + return r; + + /* A null handler is allowed if and only if on_lock() is provided. */ + if (WARN_ON_ONCE(IS_KVM_NULL_FN(range->on_lock) && + IS_KVM_NULL_FN(range->handler))) + return r; + + /* on_lock will never be called for lockless walks */ + if (WARN_ON_ONCE(range->lockless && !IS_KVM_NULL_FN(range->on_lock))) + return r; + idx = srcu_read_lock(&kvm->srcu); - spin_lock(&kvm->mmu_lock); - kvm->mmu_notifier_seq++; - need_tlb_flush = kvm_unmap_hva(kvm, address) | kvm->tlbs_dirty; - /* we've to flush the tlb before the pages can be freed */ - if (need_tlb_flush) + for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { + struct interval_tree_node *node; + + slots = __kvm_memslots(kvm, i); + kvm_for_each_memslot_in_hva_range(node, slots, + range->start, range->end - 1) { + unsigned long hva_start, hva_end; + + slot = container_of(node, struct kvm_memory_slot, hva_node[slots->node_idx]); + hva_start = max_t(unsigned long, range->start, slot->userspace_addr); + hva_end = min_t(unsigned long, range->end, + slot->userspace_addr + (slot->npages << PAGE_SHIFT)); + + /* + * To optimize for the likely case where the address + * range is covered by zero or one memslots, don't + * bother making these conditional (to avoid writes on + * the second or later invocation of the handler). + */ + gfn_range.arg = range->arg; + gfn_range.may_block = range->may_block; + /* + * HVA-based notifications aren't relevant to private + * mappings as they don't have a userspace mapping. + */ + gfn_range.attr_filter = KVM_FILTER_SHARED; + + /* + * {gfn(page) | page intersects with [hva_start, hva_end)} = + * {gfn_start, gfn_start+1, ..., gfn_end-1}. + */ + gfn_range.start = hva_to_gfn_memslot(hva_start, slot); + gfn_range.end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, slot); + gfn_range.slot = slot; + gfn_range.lockless = range->lockless; + + if (!r.found_memslot) { + r.found_memslot = true; + if (!range->lockless) { + KVM_MMU_LOCK(kvm); + if (!IS_KVM_NULL_FN(range->on_lock)) + range->on_lock(kvm); + + if (IS_KVM_NULL_FN(range->handler)) + goto mmu_unlock; + } + } + r.ret |= range->handler(kvm, &gfn_range); + } + } + + if (range->flush_on_ret && r.ret) kvm_flush_remote_tlbs(kvm); - spin_unlock(&kvm->mmu_lock); +mmu_unlock: + if (r.found_memslot && !range->lockless) + KVM_MMU_UNLOCK(kvm); + srcu_read_unlock(&kvm->srcu, idx); + + return r; } -static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn, - struct mm_struct *mm, - unsigned long address, - pte_t pte) +static __always_inline int kvm_age_hva_range(struct mmu_notifier *mn, + unsigned long start, + unsigned long end, + gfn_handler_t handler, + bool flush_on_ret) { struct kvm *kvm = mmu_notifier_to_kvm(mn); - int idx; + const struct kvm_mmu_notifier_range range = { + .start = start, + .end = end, + .handler = handler, + .on_lock = (void *)kvm_null_fn, + .flush_on_ret = flush_on_ret, + .may_block = false, + .lockless = IS_ENABLED(CONFIG_KVM_MMU_LOCKLESS_AGING), + }; - idx = srcu_read_lock(&kvm->srcu); - spin_lock(&kvm->mmu_lock); - kvm->mmu_notifier_seq++; - kvm_set_spte_hva(kvm, address, pte); - spin_unlock(&kvm->mmu_lock); - srcu_read_unlock(&kvm->srcu, idx); + return kvm_handle_hva_range(kvm, &range).ret; } -static void kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, - struct mm_struct *mm, - unsigned long start, - unsigned long end) +static __always_inline int kvm_age_hva_range_no_flush(struct mmu_notifier *mn, + unsigned long start, + unsigned long end, + gfn_handler_t handler) { - struct kvm *kvm = mmu_notifier_to_kvm(mn); - int need_tlb_flush = 0, idx; + return kvm_age_hva_range(mn, start, end, handler, false); +} - idx = srcu_read_lock(&kvm->srcu); - spin_lock(&kvm->mmu_lock); +void kvm_mmu_invalidate_begin(struct kvm *kvm) +{ + lockdep_assert_held_write(&kvm->mmu_lock); /* * The count increase must become visible at unlock time as no * spte can be established without taking the mmu_lock and * count is also read inside the mmu_lock critical section. */ - kvm->mmu_notifier_count++; - need_tlb_flush = kvm_unmap_hva_range(kvm, start, end); - need_tlb_flush |= kvm->tlbs_dirty; - /* we've to flush the tlb before the pages can be freed */ - if (need_tlb_flush) - kvm_flush_remote_tlbs(kvm); + kvm->mmu_invalidate_in_progress++; - spin_unlock(&kvm->mmu_lock); - srcu_read_unlock(&kvm->srcu, idx); + if (likely(kvm->mmu_invalidate_in_progress == 1)) { + kvm->mmu_invalidate_range_start = INVALID_GPA; + kvm->mmu_invalidate_range_end = INVALID_GPA; + } } -static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn, - struct mm_struct *mm, - unsigned long start, - unsigned long end) +void kvm_mmu_invalidate_range_add(struct kvm *kvm, gfn_t start, gfn_t end) +{ + lockdep_assert_held_write(&kvm->mmu_lock); + + WARN_ON_ONCE(!kvm->mmu_invalidate_in_progress); + + if (likely(kvm->mmu_invalidate_range_start == INVALID_GPA)) { + kvm->mmu_invalidate_range_start = start; + kvm->mmu_invalidate_range_end = end; + } else { + /* + * Fully tracking multiple concurrent ranges has diminishing + * returns. Keep things simple and just find the minimal range + * which includes the current and new ranges. As there won't be + * enough information to subtract a range after its invalidate + * completes, any ranges invalidated concurrently will + * accumulate and persist until all outstanding invalidates + * complete. + */ + kvm->mmu_invalidate_range_start = + min(kvm->mmu_invalidate_range_start, start); + kvm->mmu_invalidate_range_end = + max(kvm->mmu_invalidate_range_end, end); + } +} + +bool kvm_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) +{ + kvm_mmu_invalidate_range_add(kvm, range->start, range->end); + return kvm_unmap_gfn_range(kvm, range); +} + +static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, + const struct mmu_notifier_range *range) { struct kvm *kvm = mmu_notifier_to_kvm(mn); + const struct kvm_mmu_notifier_range hva_range = { + .start = range->start, + .end = range->end, + .handler = kvm_mmu_unmap_gfn_range, + .on_lock = kvm_mmu_invalidate_begin, + .flush_on_ret = true, + .may_block = mmu_notifier_range_blockable(range), + }; + + trace_kvm_unmap_hva_range(range->start, range->end); + + /* + * Prevent memslot modification between range_start() and range_end() + * so that conditionally locking provides the same result in both + * functions. Without that guarantee, the mmu_invalidate_in_progress + * adjustments will be imbalanced. + * + * Pairs with the decrement in range_end(). + */ + spin_lock(&kvm->mn_invalidate_lock); + kvm->mn_active_invalidate_count++; + spin_unlock(&kvm->mn_invalidate_lock); + + /* + * Invalidate pfn caches _before_ invalidating the secondary MMUs, i.e. + * before acquiring mmu_lock, to avoid holding mmu_lock while acquiring + * each cache's lock. There are relatively few caches in existence at + * any given time, and the caches themselves can check for hva overlap, + * i.e. don't need to rely on memslot overlap checks for performance. + * Because this runs without holding mmu_lock, the pfn caches must use + * mn_active_invalidate_count (see above) instead of + * mmu_invalidate_in_progress. + */ + gfn_to_pfn_cache_invalidate_start(kvm, range->start, range->end); + + /* + * If one or more memslots were found and thus zapped, notify arch code + * that guest memory has been reclaimed. This needs to be done *after* + * dropping mmu_lock, as x86's reclaim path is slooooow. + */ + if (kvm_handle_hva_range(kvm, &hva_range).found_memslot) + kvm_arch_guest_memory_reclaimed(kvm); + + return 0; +} + +void kvm_mmu_invalidate_end(struct kvm *kvm) +{ + lockdep_assert_held_write(&kvm->mmu_lock); - spin_lock(&kvm->mmu_lock); /* * This sequence increase will notify the kvm page fault that * the page that is going to be mapped in the spte could have * been freed. */ - kvm->mmu_notifier_seq++; + kvm->mmu_invalidate_seq++; smp_wmb(); /* * The above sequence increase must be visible before the * below count decrease, which is ensured by the smp_wmb above - * in conjunction with the smp_rmb in mmu_notifier_retry(). + * in conjunction with the smp_rmb in mmu_invalidate_retry(). */ - kvm->mmu_notifier_count--; - spin_unlock(&kvm->mmu_lock); + kvm->mmu_invalidate_in_progress--; + KVM_BUG_ON(kvm->mmu_invalidate_in_progress < 0, kvm); - BUG_ON(kvm->mmu_notifier_count < 0); + /* + * Assert that at least one range was added between start() and end(). + * Not adding a range isn't fatal, but it is a KVM bug. + */ + WARN_ON_ONCE(kvm->mmu_invalidate_range_start == INVALID_GPA); } -static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn, - struct mm_struct *mm, - unsigned long address) +static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn, + const struct mmu_notifier_range *range) { struct kvm *kvm = mmu_notifier_to_kvm(mn); - int young, idx; + const struct kvm_mmu_notifier_range hva_range = { + .start = range->start, + .end = range->end, + .handler = (void *)kvm_null_fn, + .on_lock = kvm_mmu_invalidate_end, + .flush_on_ret = false, + .may_block = mmu_notifier_range_blockable(range), + }; + bool wake; - idx = srcu_read_lock(&kvm->srcu); - spin_lock(&kvm->mmu_lock); + kvm_handle_hva_range(kvm, &hva_range); - young = kvm_age_hva(kvm, address); - if (young) - kvm_flush_remote_tlbs(kvm); + /* Pairs with the increment in range_start(). */ + spin_lock(&kvm->mn_invalidate_lock); + if (!WARN_ON_ONCE(!kvm->mn_active_invalidate_count)) + --kvm->mn_active_invalidate_count; + wake = !kvm->mn_active_invalidate_count; + spin_unlock(&kvm->mn_invalidate_lock); - spin_unlock(&kvm->mmu_lock); - srcu_read_unlock(&kvm->srcu, idx); + /* + * There can only be one waiter, since the wait happens under + * slots_lock. + */ + if (wake) + rcuwait_wake_up(&kvm->mn_memslots_update_rcuwait); +} + +static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn, + struct mm_struct *mm, + unsigned long start, + unsigned long end) +{ + trace_kvm_age_hva(start, end); - return young; + return kvm_age_hva_range(mn, start, end, kvm_age_gfn, + !IS_ENABLED(CONFIG_KVM_ELIDE_TLB_FLUSH_IF_YOUNG)); +} + +static int kvm_mmu_notifier_clear_young(struct mmu_notifier *mn, + struct mm_struct *mm, + unsigned long start, + unsigned long end) +{ + trace_kvm_age_hva(start, end); + + /* + * Even though we do not flush TLB, this will still adversely + * affect performance on pre-Haswell Intel EPT, where there is + * no EPT Access Bit to clear so that we have to tear down EPT + * tables instead. If we find this unacceptable, we can always + * add a parameter to kvm_age_hva so that it effectively doesn't + * do anything on clear_young. + * + * Also note that currently we never issue secondary TLB flushes + * from clear_young, leaving this job up to the regular system + * cadence. If we find this inaccurate, we might come up with a + * more sophisticated heuristic later. + */ + return kvm_age_hva_range_no_flush(mn, start, end, kvm_age_gfn); } static int kvm_mmu_notifier_test_young(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long address) { - struct kvm *kvm = mmu_notifier_to_kvm(mn); - int young, idx; + trace_kvm_test_age_hva(address); - idx = srcu_read_lock(&kvm->srcu); - spin_lock(&kvm->mmu_lock); - young = kvm_test_age_hva(kvm, address); - spin_unlock(&kvm->mmu_lock); - srcu_read_unlock(&kvm->srcu, idx); - - return young; + return kvm_age_hva_range_no_flush(mn, address, address + 1, + kvm_test_age_gfn); } static void kvm_mmu_notifier_release(struct mmu_notifier *mn, @@ -421,17 +882,16 @@ static void kvm_mmu_notifier_release(struct mmu_notifier *mn, int idx; idx = srcu_read_lock(&kvm->srcu); - kvm_arch_flush_shadow_all(kvm); + kvm_flush_shadow_all(kvm); srcu_read_unlock(&kvm->srcu, idx); } static const struct mmu_notifier_ops kvm_mmu_notifier_ops = { - .invalidate_page = kvm_mmu_notifier_invalidate_page, .invalidate_range_start = kvm_mmu_notifier_invalidate_range_start, .invalidate_range_end = kvm_mmu_notifier_invalidate_range_end, .clear_flush_young = kvm_mmu_notifier_clear_flush_young, + .clear_young = kvm_mmu_notifier_clear_young, .test_young = kvm_mmu_notifier_test_young, - .change_pte = kvm_mmu_notifier_change_pte, .release = kvm_mmu_notifier_release, }; @@ -441,156 +901,371 @@ static int kvm_init_mmu_notifier(struct kvm *kvm) return mmu_notifier_register(&kvm->mmu_notifier, current->mm); } -#else /* !(CONFIG_MMU_NOTIFIER && KVM_ARCH_WANT_MMU_NOTIFIER) */ +#else /* !CONFIG_KVM_GENERIC_MMU_NOTIFIER */ static int kvm_init_mmu_notifier(struct kvm *kvm) { return 0; } -#endif /* CONFIG_MMU_NOTIFIER && KVM_ARCH_WANT_MMU_NOTIFIER */ +#endif /* CONFIG_KVM_GENERIC_MMU_NOTIFIER */ -static void kvm_init_memslots_id(struct kvm *kvm) +#ifdef CONFIG_HAVE_KVM_PM_NOTIFIER +static int kvm_pm_notifier_call(struct notifier_block *bl, + unsigned long state, + void *unused) { - int i; - struct kvm_memslots *slots = kvm->memslots; + struct kvm *kvm = container_of(bl, struct kvm, pm_notifier); - for (i = 0; i < KVM_MEM_SLOTS_NUM; i++) - slots->id_to_index[i] = slots->memslots[i].id = i; + return kvm_arch_pm_notifier(kvm, state); } -static struct kvm *kvm_create_vm(unsigned long type) +static void kvm_init_pm_notifier(struct kvm *kvm) { - int r, i; - struct kvm *kvm = kvm_arch_alloc_vm(); + kvm->pm_notifier.notifier_call = kvm_pm_notifier_call; + /* Suspend KVM before we suspend ftrace, RCU, etc. */ + kvm->pm_notifier.priority = INT_MAX; + register_pm_notifier(&kvm->pm_notifier); +} - if (!kvm) - return ERR_PTR(-ENOMEM); +static void kvm_destroy_pm_notifier(struct kvm *kvm) +{ + unregister_pm_notifier(&kvm->pm_notifier); +} +#else /* !CONFIG_HAVE_KVM_PM_NOTIFIER */ +static void kvm_init_pm_notifier(struct kvm *kvm) +{ +} - r = kvm_arch_init_vm(kvm, type); - if (r) - goto out_err_nodisable; +static void kvm_destroy_pm_notifier(struct kvm *kvm) +{ +} +#endif /* CONFIG_HAVE_KVM_PM_NOTIFIER */ - r = hardware_enable_all(); - if (r) - goto out_err_nodisable; +static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot) +{ + if (!memslot->dirty_bitmap) + return; -#ifdef CONFIG_HAVE_KVM_IRQCHIP - INIT_HLIST_HEAD(&kvm->mask_notifier_list); - INIT_HLIST_HEAD(&kvm->irq_ack_notifier_list); -#endif + vfree(memslot->dirty_bitmap); + memslot->dirty_bitmap = NULL; +} - BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX); +/* This does not remove the slot from struct kvm_memslots data structures */ +static void kvm_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) +{ + if (slot->flags & KVM_MEM_GUEST_MEMFD) + kvm_gmem_unbind(slot); - r = -ENOMEM; - kvm->memslots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL); - if (!kvm->memslots) - goto out_err_nosrcu; - kvm_init_memslots_id(kvm); - if (init_srcu_struct(&kvm->srcu)) - goto out_err_nosrcu; - for (i = 0; i < KVM_NR_BUSES; i++) { - kvm->buses[i] = kzalloc(sizeof(struct kvm_io_bus), - GFP_KERNEL); - if (!kvm->buses[i]) - goto out_err; - } + kvm_destroy_dirty_bitmap(slot); - spin_lock_init(&kvm->mmu_lock); - kvm->mm = current->mm; - atomic_inc(&kvm->mm->mm_count); - kvm_eventfd_init(kvm); - mutex_init(&kvm->lock); - mutex_init(&kvm->irq_lock); - mutex_init(&kvm->slots_lock); - atomic_set(&kvm->users_count, 1); - INIT_LIST_HEAD(&kvm->devices); + kvm_arch_free_memslot(kvm, slot); - r = kvm_init_mmu_notifier(kvm); - if (r) - goto out_err; + kfree(slot); +} - raw_spin_lock(&kvm_lock); - list_add(&kvm->vm_list, &vm_list); - raw_spin_unlock(&kvm_lock); +static void kvm_free_memslots(struct kvm *kvm, struct kvm_memslots *slots) +{ + struct hlist_node *idnode; + struct kvm_memory_slot *memslot; + int bkt; - return kvm; + /* + * The same memslot objects live in both active and inactive sets, + * arbitrarily free using index '1' so the second invocation of this + * function isn't operating over a structure with dangling pointers + * (even though this function isn't actually touching them). + */ + if (!slots->node_idx) + return; -out_err: - cleanup_srcu_struct(&kvm->srcu); -out_err_nosrcu: - hardware_disable_all(); -out_err_nodisable: - for (i = 0; i < KVM_NR_BUSES; i++) - kfree(kvm->buses[i]); - kfree(kvm->memslots); - kvm_arch_free_vm(kvm); - return ERR_PTR(r); + hash_for_each_safe(slots->id_hash, bkt, idnode, memslot, id_node[1]) + kvm_free_memslot(kvm, memslot); } -/* - * Avoid using vmalloc for a small buffer. - * Should not be used when the size is statically known. - */ -void *kvm_kvzalloc(unsigned long size) +static umode_t kvm_stats_debugfs_mode(const struct _kvm_stats_desc *pdesc) { - if (size > PAGE_SIZE) - return vzalloc(size); - else - return kzalloc(size, GFP_KERNEL); + switch (pdesc->desc.flags & KVM_STATS_TYPE_MASK) { + case KVM_STATS_TYPE_INSTANT: + return 0444; + case KVM_STATS_TYPE_CUMULATIVE: + case KVM_STATS_TYPE_PEAK: + default: + return 0644; + } } -void kvm_kvfree(const void *addr) + +static void kvm_destroy_vm_debugfs(struct kvm *kvm) { - if (is_vmalloc_addr(addr)) - vfree(addr); - else - kfree(addr); + int i; + int kvm_debugfs_num_entries = kvm_vm_stats_header.num_desc + + kvm_vcpu_stats_header.num_desc; + + if (IS_ERR(kvm->debugfs_dentry)) + return; + + debugfs_remove_recursive(kvm->debugfs_dentry); + + if (kvm->debugfs_stat_data) { + for (i = 0; i < kvm_debugfs_num_entries; i++) + kfree(kvm->debugfs_stat_data[i]); + kfree(kvm->debugfs_stat_data); + } } -static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot) +static int kvm_create_vm_debugfs(struct kvm *kvm, const char *fdname) { - if (!memslot->dirty_bitmap) - return; + static DEFINE_MUTEX(kvm_debugfs_lock); + struct dentry *dent; + char dir_name[ITOA_MAX_LEN * 2]; + struct kvm_stat_data *stat_data; + const struct _kvm_stats_desc *pdesc; + int i, ret = -ENOMEM; + int kvm_debugfs_num_entries = kvm_vm_stats_header.num_desc + + kvm_vcpu_stats_header.num_desc; - kvm_kvfree(memslot->dirty_bitmap); - memslot->dirty_bitmap = NULL; + if (!debugfs_initialized()) + return 0; + + snprintf(dir_name, sizeof(dir_name), "%d-%s", task_pid_nr(current), fdname); + mutex_lock(&kvm_debugfs_lock); + dent = debugfs_lookup(dir_name, kvm_debugfs_dir); + if (dent) { + pr_warn_ratelimited("KVM: debugfs: duplicate directory %s\n", dir_name); + dput(dent); + mutex_unlock(&kvm_debugfs_lock); + return 0; + } + dent = debugfs_create_dir(dir_name, kvm_debugfs_dir); + mutex_unlock(&kvm_debugfs_lock); + if (IS_ERR(dent)) + return 0; + + kvm->debugfs_dentry = dent; + kvm->debugfs_stat_data = kcalloc(kvm_debugfs_num_entries, + sizeof(*kvm->debugfs_stat_data), + GFP_KERNEL_ACCOUNT); + if (!kvm->debugfs_stat_data) + goto out_err; + + for (i = 0; i < kvm_vm_stats_header.num_desc; ++i) { + pdesc = &kvm_vm_stats_desc[i]; + stat_data = kzalloc(sizeof(*stat_data), GFP_KERNEL_ACCOUNT); + if (!stat_data) + goto out_err; + + stat_data->kvm = kvm; + stat_data->desc = pdesc; + stat_data->kind = KVM_STAT_VM; + kvm->debugfs_stat_data[i] = stat_data; + debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc), + kvm->debugfs_dentry, stat_data, + &stat_fops_per_vm); + } + + for (i = 0; i < kvm_vcpu_stats_header.num_desc; ++i) { + pdesc = &kvm_vcpu_stats_desc[i]; + stat_data = kzalloc(sizeof(*stat_data), GFP_KERNEL_ACCOUNT); + if (!stat_data) + goto out_err; + + stat_data->kvm = kvm; + stat_data->desc = pdesc; + stat_data->kind = KVM_STAT_VCPU; + kvm->debugfs_stat_data[i + kvm_vm_stats_header.num_desc] = stat_data; + debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc), + kvm->debugfs_dentry, stat_data, + &stat_fops_per_vm); + } + + kvm_arch_create_vm_debugfs(kvm); + return 0; +out_err: + kvm_destroy_vm_debugfs(kvm); + return ret; } /* - * Free any memory in @free but not in @dont. + * Called just after removing the VM from the vm_list, but before doing any + * other destruction. */ -static void kvm_free_physmem_slot(struct kvm_memory_slot *free, - struct kvm_memory_slot *dont) +void __weak kvm_arch_pre_destroy_vm(struct kvm *kvm) { - if (!dont || free->dirty_bitmap != dont->dirty_bitmap) - kvm_destroy_dirty_bitmap(free); +} - kvm_arch_free_memslot(free, dont); +/* + * Called after per-vm debugfs created. When called kvm->debugfs_dentry should + * be setup already, so we can create arch-specific debugfs entries under it. + * Cleanup should be automatic done in kvm_destroy_vm_debugfs() recursively, so + * a per-arch destroy interface is not needed. + */ +void __weak kvm_arch_create_vm_debugfs(struct kvm *kvm) +{ +} - free->npages = 0; +/* Called only on cleanup and destruction paths when there are no users. */ +static inline struct kvm_io_bus *kvm_get_bus_for_destruction(struct kvm *kvm, + enum kvm_bus idx) +{ + return rcu_dereference_protected(kvm->buses[idx], + !refcount_read(&kvm->users_count)); } -void kvm_free_physmem(struct kvm *kvm) +static struct kvm *kvm_create_vm(unsigned long type, const char *fdname) { - struct kvm_memslots *slots = kvm->memslots; - struct kvm_memory_slot *memslot; + struct kvm *kvm = kvm_arch_alloc_vm(); + struct kvm_memslots *slots; + int r, i, j; + + if (!kvm) + return ERR_PTR(-ENOMEM); + + KVM_MMU_LOCK_INIT(kvm); + mmgrab(current->mm); + kvm->mm = current->mm; + kvm_eventfd_init(kvm); + mutex_init(&kvm->lock); + mutex_init(&kvm->irq_lock); + mutex_init(&kvm->slots_lock); + mutex_init(&kvm->slots_arch_lock); + spin_lock_init(&kvm->mn_invalidate_lock); + rcuwait_init(&kvm->mn_memslots_update_rcuwait); + xa_init(&kvm->vcpu_array); +#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES + xa_init(&kvm->mem_attr_array); +#endif + + INIT_LIST_HEAD(&kvm->gpc_list); + spin_lock_init(&kvm->gpc_lock); + + INIT_LIST_HEAD(&kvm->devices); + kvm->max_vcpus = KVM_MAX_VCPUS; + + BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX); + + /* + * Force subsequent debugfs file creations to fail if the VM directory + * is not created (by kvm_create_vm_debugfs()). + */ + kvm->debugfs_dentry = ERR_PTR(-ENOENT); - kvm_for_each_memslot(memslot, slots) - kvm_free_physmem_slot(memslot, NULL); + snprintf(kvm->stats_id, sizeof(kvm->stats_id), "kvm-%d", + task_pid_nr(current)); - kfree(kvm->memslots); + r = -ENOMEM; + if (init_srcu_struct(&kvm->srcu)) + goto out_err_no_srcu; + if (init_srcu_struct(&kvm->irq_srcu)) + goto out_err_no_irq_srcu; + + r = kvm_init_irq_routing(kvm); + if (r) + goto out_err_no_irq_routing; + + refcount_set(&kvm->users_count, 1); + + for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { + for (j = 0; j < 2; j++) { + slots = &kvm->__memslots[i][j]; + + atomic_long_set(&slots->last_used_slot, (unsigned long)NULL); + slots->hva_tree = RB_ROOT_CACHED; + slots->gfn_tree = RB_ROOT; + hash_init(slots->id_hash); + slots->node_idx = j; + + /* Generations must be different for each address space. */ + slots->generation = i; + } + + rcu_assign_pointer(kvm->memslots[i], &kvm->__memslots[i][0]); + } + + r = -ENOMEM; + for (i = 0; i < KVM_NR_BUSES; i++) { + rcu_assign_pointer(kvm->buses[i], + kzalloc(sizeof(struct kvm_io_bus), GFP_KERNEL_ACCOUNT)); + if (!kvm->buses[i]) + goto out_err_no_arch_destroy_vm; + } + + r = kvm_arch_init_vm(kvm, type); + if (r) + goto out_err_no_arch_destroy_vm; + + r = kvm_enable_virtualization(); + if (r) + goto out_err_no_disable; + +#ifdef CONFIG_HAVE_KVM_IRQCHIP + INIT_HLIST_HEAD(&kvm->irq_ack_notifier_list); +#endif + + r = kvm_init_mmu_notifier(kvm); + if (r) + goto out_err_no_mmu_notifier; + + r = kvm_coalesced_mmio_init(kvm); + if (r < 0) + goto out_no_coalesced_mmio; + + r = kvm_create_vm_debugfs(kvm, fdname); + if (r) + goto out_err_no_debugfs; + + mutex_lock(&kvm_lock); + list_add(&kvm->vm_list, &vm_list); + mutex_unlock(&kvm_lock); + + preempt_notifier_inc(); + kvm_init_pm_notifier(kvm); + + return kvm; + +out_err_no_debugfs: + kvm_coalesced_mmio_free(kvm); +out_no_coalesced_mmio: +#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER + if (kvm->mmu_notifier.ops) + mmu_notifier_unregister(&kvm->mmu_notifier, current->mm); +#endif +out_err_no_mmu_notifier: + kvm_disable_virtualization(); +out_err_no_disable: + kvm_arch_destroy_vm(kvm); +out_err_no_arch_destroy_vm: + WARN_ON_ONCE(!refcount_dec_and_test(&kvm->users_count)); + for (i = 0; i < KVM_NR_BUSES; i++) + kfree(kvm_get_bus_for_destruction(kvm, i)); + kvm_free_irq_routing(kvm); +out_err_no_irq_routing: + cleanup_srcu_struct(&kvm->irq_srcu); +out_err_no_irq_srcu: + cleanup_srcu_struct(&kvm->srcu); +out_err_no_srcu: + kvm_arch_free_vm(kvm); + mmdrop(current->mm); + return ERR_PTR(r); } static void kvm_destroy_devices(struct kvm *kvm) { - struct list_head *node, *tmp; + struct kvm_device *dev, *tmp; - list_for_each_safe(node, tmp, &kvm->devices) { - struct kvm_device *dev = - list_entry(node, struct kvm_device, vm_node); - - list_del(node); + /* + * We do not need to take the kvm->lock here, because nobody else + * has a reference to the struct kvm at this point and therefore + * cannot access the devices list anyhow. + * + * The device list is generally managed as an rculist, but list_del() + * is used intentionally here. If a bug in KVM introduced a reader that + * was not backed by a reference on the kvm struct, the hope is that + * it'd consume the poisoned forward pointer instead of suffering a + * use-after-free, even though this cannot be guaranteed. + */ + list_for_each_entry_safe(dev, tmp, &kvm->devices, vm_node) { + list_del(&dev->vm_node); dev->ops->destroy(dev); } } @@ -600,41 +1275,98 @@ 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); + kvm_destroy_pm_notifier(kvm); + kvm_uevent_notify_change(KVM_EVENT_DESTROY_VM, kvm); + kvm_destroy_vm_debugfs(kvm); + mutex_lock(&kvm_lock); list_del(&kvm->vm_list); - raw_spin_unlock(&kvm_lock); + mutex_unlock(&kvm_lock); + kvm_arch_pre_destroy_vm(kvm); + kvm_free_irq_routing(kvm); - for (i = 0; i < KVM_NR_BUSES; i++) - kvm_io_bus_destroy(kvm->buses[i]); + for (i = 0; i < KVM_NR_BUSES; i++) { + struct kvm_io_bus *bus = kvm_get_bus_for_destruction(kvm, i); + + if (bus) + kvm_io_bus_destroy(bus); + kvm->buses[i] = NULL; + } kvm_coalesced_mmio_free(kvm); -#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) +#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER mmu_notifier_unregister(&kvm->mmu_notifier, kvm->mm); + /* + * At this point, pending calls to invalidate_range_start() + * have completed but no more MMU notifiers will run, so + * mn_active_invalidate_count may remain unbalanced. + * No threads can be waiting in kvm_swap_active_memslots() as the + * last reference on KVM has been dropped, but freeing + * memslots would deadlock without this manual intervention. + * + * If the count isn't unbalanced, i.e. KVM did NOT unregister its MMU + * notifier between a start() and end(), then there shouldn't be any + * in-progress invalidations. + */ + WARN_ON(rcuwait_active(&kvm->mn_memslots_update_rcuwait)); + if (kvm->mn_active_invalidate_count) + kvm->mn_active_invalidate_count = 0; + else + WARN_ON(kvm->mmu_invalidate_in_progress); #else - kvm_arch_flush_shadow_all(kvm); + kvm_flush_shadow_all(kvm); #endif kvm_arch_destroy_vm(kvm); kvm_destroy_devices(kvm); - kvm_free_physmem(kvm); + for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { + kvm_free_memslots(kvm, &kvm->__memslots[i][0]); + kvm_free_memslots(kvm, &kvm->__memslots[i][1]); + } + cleanup_srcu_struct(&kvm->irq_srcu); + srcu_barrier(&kvm->srcu); cleanup_srcu_struct(&kvm->srcu); +#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES + xa_destroy(&kvm->mem_attr_array); +#endif kvm_arch_free_vm(kvm); - hardware_disable_all(); + preempt_notifier_dec(); + kvm_disable_virtualization(); mmdrop(mm); } void kvm_get_kvm(struct kvm *kvm) { - atomic_inc(&kvm->users_count); + refcount_inc(&kvm->users_count); } EXPORT_SYMBOL_GPL(kvm_get_kvm); +/* + * Make sure the vm is not during destruction, which is a safe version of + * kvm_get_kvm(). Return true if kvm referenced successfully, false otherwise. + */ +bool kvm_get_kvm_safe(struct kvm *kvm) +{ + return refcount_inc_not_zero(&kvm->users_count); +} +EXPORT_SYMBOL_GPL(kvm_get_kvm_safe); + void kvm_put_kvm(struct kvm *kvm) { - if (atomic_dec_and_test(&kvm->users_count)) + if (refcount_dec_and_test(&kvm->users_count)) kvm_destroy_vm(kvm); } EXPORT_SYMBOL_GPL(kvm_put_kvm); +/* + * Used to put a reference that was taken on behalf of an object associated + * with a user-visible file descriptor, e.g. a vcpu or device, if installation + * of the new file descriptor fails and the reference cannot be transferred to + * its final owner. In such cases, the caller is still actively using @kvm and + * will fail miserably if the refcount unexpectedly hits zero. + */ +void kvm_put_kvm_no_destroy(struct kvm *kvm) +{ + WARN_ON(refcount_dec_and_test(&kvm->users_count)); +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_put_kvm_no_destroy); static int kvm_vm_release(struct inode *inode, struct file *filp) { @@ -646,76 +1378,241 @@ static int kvm_vm_release(struct inode *inode, struct file *filp) return 0; } +int kvm_trylock_all_vcpus(struct kvm *kvm) +{ + struct kvm_vcpu *vcpu; + unsigned long i, j; + + lockdep_assert_held(&kvm->lock); + + kvm_for_each_vcpu(i, vcpu, kvm) + if (!mutex_trylock_nest_lock(&vcpu->mutex, &kvm->lock)) + goto out_unlock; + return 0; + +out_unlock: + kvm_for_each_vcpu(j, vcpu, kvm) { + if (i == j) + break; + mutex_unlock(&vcpu->mutex); + } + return -EINTR; +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_trylock_all_vcpus); + +int kvm_lock_all_vcpus(struct kvm *kvm) +{ + struct kvm_vcpu *vcpu; + unsigned long i, j; + int r; + + lockdep_assert_held(&kvm->lock); + + kvm_for_each_vcpu(i, vcpu, kvm) { + r = mutex_lock_killable_nest_lock(&vcpu->mutex, &kvm->lock); + if (r) + goto out_unlock; + } + return 0; + +out_unlock: + kvm_for_each_vcpu(j, vcpu, kvm) { + if (i == j) + break; + mutex_unlock(&vcpu->mutex); + } + return r; +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_lock_all_vcpus); + +void kvm_unlock_all_vcpus(struct kvm *kvm) +{ + struct kvm_vcpu *vcpu; + unsigned long i; + + lockdep_assert_held(&kvm->lock); + + kvm_for_each_vcpu(i, vcpu, kvm) + mutex_unlock(&vcpu->mutex); +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_unlock_all_vcpus); + /* * Allocation size is twice as large as the actual dirty bitmap size. - * See x86's kvm_vm_ioctl_get_dirty_log() why this is needed. + * See kvm_vm_ioctl_get_dirty_log() why this is needed. */ -static int kvm_create_dirty_bitmap(struct kvm_memory_slot *memslot) +static int kvm_alloc_dirty_bitmap(struct kvm_memory_slot *memslot) { -#ifndef CONFIG_S390 - unsigned long dirty_bytes = 2 * kvm_dirty_bitmap_bytes(memslot); + unsigned long dirty_bytes = kvm_dirty_bitmap_bytes(memslot); - memslot->dirty_bitmap = kvm_kvzalloc(dirty_bytes); + memslot->dirty_bitmap = __vcalloc(2, dirty_bytes, GFP_KERNEL_ACCOUNT); if (!memslot->dirty_bitmap) return -ENOMEM; -#endif /* !CONFIG_S390 */ return 0; } -static int cmp_memslot(const void *slot1, const void *slot2) +static struct kvm_memslots *kvm_get_inactive_memslots(struct kvm *kvm, int as_id) { - struct kvm_memory_slot *s1, *s2; - - s1 = (struct kvm_memory_slot *)slot1; - s2 = (struct kvm_memory_slot *)slot2; + struct kvm_memslots *active = __kvm_memslots(kvm, as_id); + int node_idx_inactive = active->node_idx ^ 1; - if (s1->npages < s2->npages) - return 1; - if (s1->npages > s2->npages) - return -1; - - return 0; + return &kvm->__memslots[as_id][node_idx_inactive]; } /* - * Sort the memslots base on its size, so the larger slots - * will get better fit. + * Helper to get the address space ID when one of memslot pointers may be NULL. + * This also serves as a sanity that at least one of the pointers is non-NULL, + * and that their address space IDs don't diverge. */ -static void sort_memslots(struct kvm_memslots *slots) +static int kvm_memslots_get_as_id(struct kvm_memory_slot *a, + struct kvm_memory_slot *b) { - int i; + if (WARN_ON_ONCE(!a && !b)) + return 0; - sort(slots->memslots, KVM_MEM_SLOTS_NUM, - sizeof(struct kvm_memory_slot), cmp_memslot, NULL); + if (!a) + return b->as_id; + if (!b) + return a->as_id; - for (i = 0; i < KVM_MEM_SLOTS_NUM; i++) - slots->id_to_index[slots->memslots[i].id] = i; + WARN_ON_ONCE(a->as_id != b->as_id); + return a->as_id; } -void update_memslots(struct kvm_memslots *slots, struct kvm_memory_slot *new, - u64 last_generation) +static void kvm_insert_gfn_node(struct kvm_memslots *slots, + struct kvm_memory_slot *slot) { - if (new) { - int id = new->id; - struct kvm_memory_slot *old = id_to_memslot(slots, id); - unsigned long npages = old->npages; + struct rb_root *gfn_tree = &slots->gfn_tree; + struct rb_node **node, *parent; + int idx = slots->node_idx; + + parent = NULL; + for (node = &gfn_tree->rb_node; *node; ) { + struct kvm_memory_slot *tmp; - *old = *new; - if (new->npages != npages) - sort_memslots(slots); + tmp = container_of(*node, struct kvm_memory_slot, gfn_node[idx]); + parent = *node; + if (slot->base_gfn < tmp->base_gfn) + node = &(*node)->rb_left; + else if (slot->base_gfn > tmp->base_gfn) + node = &(*node)->rb_right; + else + BUG(); } - slots->generation = last_generation + 1; + rb_link_node(&slot->gfn_node[idx], parent, node); + rb_insert_color(&slot->gfn_node[idx], gfn_tree); +} + +static void kvm_erase_gfn_node(struct kvm_memslots *slots, + struct kvm_memory_slot *slot) +{ + rb_erase(&slot->gfn_node[slots->node_idx], &slots->gfn_tree); +} + +static void kvm_replace_gfn_node(struct kvm_memslots *slots, + struct kvm_memory_slot *old, + struct kvm_memory_slot *new) +{ + int idx = slots->node_idx; + + WARN_ON_ONCE(old->base_gfn != new->base_gfn); + + rb_replace_node(&old->gfn_node[idx], &new->gfn_node[idx], + &slots->gfn_tree); +} + +/* + * Replace @old with @new in the inactive memslots. + * + * With NULL @old this simply adds @new. + * With NULL @new this simply removes @old. + * + * If @new is non-NULL its hva_node[slots_idx] range has to be set + * appropriately. + */ +static void kvm_replace_memslot(struct kvm *kvm, + struct kvm_memory_slot *old, + struct kvm_memory_slot *new) +{ + int as_id = kvm_memslots_get_as_id(old, new); + struct kvm_memslots *slots = kvm_get_inactive_memslots(kvm, as_id); + int idx = slots->node_idx; + + if (old) { + hash_del(&old->id_node[idx]); + interval_tree_remove(&old->hva_node[idx], &slots->hva_tree); + + if ((long)old == atomic_long_read(&slots->last_used_slot)) + atomic_long_set(&slots->last_used_slot, (long)new); + + if (!new) { + kvm_erase_gfn_node(slots, old); + return; + } + } + + /* + * Initialize @new's hva range. Do this even when replacing an @old + * slot, kvm_copy_memslot() deliberately does not touch node data. + */ + new->hva_node[idx].start = new->userspace_addr; + new->hva_node[idx].last = new->userspace_addr + + (new->npages << PAGE_SHIFT) - 1; + + /* + * (Re)Add the new memslot. There is no O(1) interval_tree_replace(), + * hva_node needs to be swapped with remove+insert even though hva can't + * change when replacing an existing slot. + */ + hash_add(slots->id_hash, &new->id_node[idx], new->id); + interval_tree_insert(&new->hva_node[idx], &slots->hva_tree); + + /* + * If the memslot gfn is unchanged, rb_replace_node() can be used to + * switch the node in the gfn tree instead of removing the old and + * inserting the new as two separate operations. Replacement is a + * single O(1) operation versus two O(log(n)) operations for + * remove+insert. + */ + if (old && old->base_gfn == new->base_gfn) { + kvm_replace_gfn_node(slots, old, new); + } else { + if (old) + kvm_erase_gfn_node(slots, old); + kvm_insert_gfn_node(slots, new); + } } -static int check_memory_region_flags(struct kvm_userspace_memory_region *mem) +/* + * Flags that do not access any of the extra space of struct + * kvm_userspace_memory_region2. KVM_SET_USER_MEMORY_REGION_V1_FLAGS + * only allows these. + */ +#define KVM_SET_USER_MEMORY_REGION_V1_FLAGS \ + (KVM_MEM_LOG_DIRTY_PAGES | KVM_MEM_READONLY) + +static int check_memory_region_flags(struct kvm *kvm, + const struct kvm_userspace_memory_region2 *mem) { u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES; -#ifdef KVM_CAP_READONLY_MEM - valid_flags |= KVM_MEM_READONLY; -#endif + if (IS_ENABLED(CONFIG_KVM_GUEST_MEMFD)) + valid_flags |= KVM_MEM_GUEST_MEMFD; + + /* Dirty logging private memory is not currently supported. */ + if (mem->flags & KVM_MEM_GUEST_MEMFD) + valid_flags &= ~KVM_MEM_LOG_DIRTY_PAGES; + + /* + * GUEST_MEMFD is incompatible with read-only memslots, as writes to + * read-only memslots have emulated MMIO, not page fault, semantics, + * and KVM doesn't allow emulated MMIO for private memory. + */ + if (kvm_arch_has_readonly_mem(kvm) && + !(mem->flags & KVM_MEM_GUEST_MEMFD)) + valid_flags |= KVM_MEM_READONLY; if (mem->flags & ~valid_flags) return -EINVAL; @@ -723,306 +1620,1087 @@ 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) +static void kvm_swap_active_memslots(struct kvm *kvm, int as_id) { - struct kvm_memslots *old_memslots = kvm->memslots; + struct kvm_memslots *slots = kvm_get_inactive_memslots(kvm, as_id); + + /* Grab the generation from the activate memslots. */ + u64 gen = __kvm_memslots(kvm, as_id)->generation; + + WARN_ON(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS); + slots->generation = gen | KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS; + + /* + * Do not store the new memslots while there are invalidations in + * progress, otherwise the locking in invalidate_range_start and + * invalidate_range_end will be unbalanced. + */ + spin_lock(&kvm->mn_invalidate_lock); + prepare_to_rcuwait(&kvm->mn_memslots_update_rcuwait); + while (kvm->mn_active_invalidate_count) { + set_current_state(TASK_UNINTERRUPTIBLE); + spin_unlock(&kvm->mn_invalidate_lock); + schedule(); + spin_lock(&kvm->mn_invalidate_lock); + } + finish_rcuwait(&kvm->mn_memslots_update_rcuwait); + rcu_assign_pointer(kvm->memslots[as_id], slots); + spin_unlock(&kvm->mn_invalidate_lock); + + /* + * Acquired in kvm_set_memslot. Must be released before synchronize + * SRCU below in order to avoid deadlock with another thread + * acquiring the slots_arch_lock in an srcu critical section. + */ + mutex_unlock(&kvm->slots_arch_lock); - update_memslots(slots, new, kvm->memslots->generation); - rcu_assign_pointer(kvm->memslots, slots); synchronize_srcu_expedited(&kvm->srcu); - return old_memslots; + + /* + * Increment the new memslot generation a second time, dropping the + * update in-progress flag and incrementing the generation based on + * the number of address spaces. This provides a unique and easily + * identifiable generation number while the memslots are in flux. + */ + gen = slots->generation & ~KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS; + + /* + * Generations must be unique even across address spaces. We do not need + * a global counter for that, instead the generation space is evenly split + * across address spaces. For example, with two address spaces, address + * space 0 will use generations 0, 2, 4, ... while address space 1 will + * use generations 1, 3, 5, ... + */ + gen += kvm_arch_nr_memslot_as_ids(kvm); + + kvm_arch_memslots_updated(kvm, gen); + + slots->generation = gen; +} + +static int kvm_prepare_memory_region(struct kvm *kvm, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, + enum kvm_mr_change change) +{ + int r; + + /* + * If dirty logging is disabled, nullify the bitmap; the old bitmap + * will be freed on "commit". If logging is enabled in both old and + * new, reuse the existing bitmap. If logging is enabled only in the + * new and KVM isn't using a ring buffer, allocate and initialize a + * new bitmap. + */ + if (change != KVM_MR_DELETE) { + if (!(new->flags & KVM_MEM_LOG_DIRTY_PAGES)) + new->dirty_bitmap = NULL; + else if (old && old->dirty_bitmap) + new->dirty_bitmap = old->dirty_bitmap; + else if (kvm_use_dirty_bitmap(kvm)) { + r = kvm_alloc_dirty_bitmap(new); + if (r) + return r; + + if (kvm_dirty_log_manual_protect_and_init_set(kvm)) + bitmap_set(new->dirty_bitmap, 0, new->npages); + } + } + + r = kvm_arch_prepare_memory_region(kvm, old, new, change); + + /* Free the bitmap on failure if it was allocated above. */ + if (r && new && new->dirty_bitmap && (!old || !old->dirty_bitmap)) + kvm_destroy_dirty_bitmap(new); + + return r; +} + +static void kvm_commit_memory_region(struct kvm *kvm, + struct kvm_memory_slot *old, + const struct kvm_memory_slot *new, + enum kvm_mr_change change) +{ + int old_flags = old ? old->flags : 0; + int new_flags = new ? new->flags : 0; + /* + * Update the total number of memslot pages before calling the arch + * hook so that architectures can consume the result directly. + */ + if (change == KVM_MR_DELETE) + kvm->nr_memslot_pages -= old->npages; + else if (change == KVM_MR_CREATE) + kvm->nr_memslot_pages += new->npages; + + if ((old_flags ^ new_flags) & KVM_MEM_LOG_DIRTY_PAGES) { + int change = (new_flags & KVM_MEM_LOG_DIRTY_PAGES) ? 1 : -1; + atomic_set(&kvm->nr_memslots_dirty_logging, + atomic_read(&kvm->nr_memslots_dirty_logging) + change); + } + + kvm_arch_commit_memory_region(kvm, old, new, change); + + switch (change) { + case KVM_MR_CREATE: + /* Nothing more to do. */ + break; + case KVM_MR_DELETE: + /* Free the old memslot and all its metadata. */ + kvm_free_memslot(kvm, old); + break; + case KVM_MR_MOVE: + case KVM_MR_FLAGS_ONLY: + /* + * Free the dirty bitmap as needed; the below check encompasses + * both the flags and whether a ring buffer is being used) + */ + if (old->dirty_bitmap && !new->dirty_bitmap) + kvm_destroy_dirty_bitmap(old); + + /* + * The final quirk. Free the detached, old slot, but only its + * memory, not any metadata. Metadata, including arch specific + * data, may be reused by @new. + */ + kfree(old); + break; + default: + BUG(); + } } /* - * Allocate some memory and give it an address in the guest physical address - * space. - * - * Discontiguous memory is allowed, mostly for framebuffers. + * Activate @new, which must be installed in the inactive slots by the caller, + * by swapping the active slots and then propagating @new to @old once @old is + * unreachable and can be safely modified. * - * Must be called holding mmap_sem for write. + * With NULL @old this simply adds @new to @active (while swapping the sets). + * With NULL @new this simply removes @old from @active and frees it + * (while also swapping the sets). */ -int __kvm_set_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem) +static void kvm_activate_memslot(struct kvm *kvm, + struct kvm_memory_slot *old, + struct kvm_memory_slot *new) { - int r; - gfn_t base_gfn; - unsigned long npages; - struct kvm_memory_slot *slot; - struct kvm_memory_slot old, new; - struct kvm_memslots *slots = NULL, *old_memslots; - enum kvm_mr_change change; + int as_id = kvm_memslots_get_as_id(old, new); - r = check_memory_region_flags(mem); - if (r) - goto out; + kvm_swap_active_memslots(kvm, as_id); - r = -EINVAL; - /* General sanity checks */ - if (mem->memory_size & (PAGE_SIZE - 1)) - goto out; - if (mem->guest_phys_addr & (PAGE_SIZE - 1)) - goto out; - /* We can read the guest memory with __xxx_user() later on. */ - if ((mem->slot < KVM_USER_MEM_SLOTS) && - ((mem->userspace_addr & (PAGE_SIZE - 1)) || - !access_ok(VERIFY_WRITE, - (void __user *)(unsigned long)mem->userspace_addr, - mem->memory_size))) - goto out; - if (mem->slot >= KVM_MEM_SLOTS_NUM) - goto out; - if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr) - goto out; + /* Propagate the new memslot to the now inactive memslots. */ + kvm_replace_memslot(kvm, old, new); +} - slot = id_to_memslot(kvm->memslots, mem->slot); - base_gfn = mem->guest_phys_addr >> PAGE_SHIFT; - npages = mem->memory_size >> PAGE_SHIFT; +static void kvm_copy_memslot(struct kvm_memory_slot *dest, + const struct kvm_memory_slot *src) +{ + dest->base_gfn = src->base_gfn; + dest->npages = src->npages; + dest->dirty_bitmap = src->dirty_bitmap; + dest->arch = src->arch; + dest->userspace_addr = src->userspace_addr; + dest->flags = src->flags; + dest->id = src->id; + dest->as_id = src->as_id; +} - r = -EINVAL; - if (npages > KVM_MEM_MAX_NR_PAGES) - goto out; +static void kvm_invalidate_memslot(struct kvm *kvm, + struct kvm_memory_slot *old, + struct kvm_memory_slot *invalid_slot) +{ + /* + * Mark the current slot INVALID. As with all memslot modifications, + * this must be done on an unreachable slot to avoid modifying the + * current slot in the active tree. + */ + kvm_copy_memslot(invalid_slot, old); + invalid_slot->flags |= KVM_MEMSLOT_INVALID; + kvm_replace_memslot(kvm, old, invalid_slot); - if (!npages) - mem->flags &= ~KVM_MEM_LOG_DIRTY_PAGES; + /* + * Activate the slot that is now marked INVALID, but don't propagate + * the slot to the now inactive slots. The slot is either going to be + * deleted or recreated as a new slot. + */ + kvm_swap_active_memslots(kvm, old->as_id); - new = old = *slot; + /* + * From this point no new shadow pages pointing to a deleted, or moved, + * memslot will be created. Validation of sp->gfn happens in: + * - gfn_to_hva (kvm_read_guest, gfn_to_pfn) + * - kvm_is_visible_gfn (mmu_check_root) + */ + kvm_arch_flush_shadow_memslot(kvm, old); + kvm_arch_guest_memory_reclaimed(kvm); - new.id = mem->slot; - new.base_gfn = base_gfn; - new.npages = npages; - new.flags = mem->flags; + /* Was released by kvm_swap_active_memslots(), reacquire. */ + mutex_lock(&kvm->slots_arch_lock); - r = -EINVAL; - 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; + /* + * Copy the arch-specific field of the newly-installed slot back to the + * old slot as the arch data could have changed between releasing + * slots_arch_lock in kvm_swap_active_memslots() and re-acquiring the lock + * above. Writers are required to retrieve memslots *after* acquiring + * slots_arch_lock, thus the active slot's data is guaranteed to be fresh. + */ + old->arch = invalid_slot->arch; +} - 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; - } +static void kvm_create_memslot(struct kvm *kvm, + struct kvm_memory_slot *new) +{ + /* Add the new memslot to the inactive set and activate. */ + kvm_replace_memslot(kvm, NULL, new); + kvm_activate_memslot(kvm, NULL, new); +} + +static void kvm_delete_memslot(struct kvm *kvm, + struct kvm_memory_slot *old, + struct kvm_memory_slot *invalid_slot) +{ + /* + * Remove the old memslot (in the inactive memslots) by passing NULL as + * the "new" slot, and for the invalid version in the active slots. + */ + kvm_replace_memslot(kvm, old, NULL); + kvm_activate_memslot(kvm, invalid_slot, NULL); +} + +static void kvm_move_memslot(struct kvm *kvm, + struct kvm_memory_slot *old, + struct kvm_memory_slot *new, + struct kvm_memory_slot *invalid_slot) +{ + /* + * Replace the old memslot in the inactive slots, and then swap slots + * and replace the current INVALID with the new as well. + */ + kvm_replace_memslot(kvm, old, new); + kvm_activate_memslot(kvm, invalid_slot, new); +} + +static void kvm_update_flags_memslot(struct kvm *kvm, + struct kvm_memory_slot *old, + struct kvm_memory_slot *new) +{ + /* + * Similar to the MOVE case, but the slot doesn't need to be zapped as + * an intermediate step. Instead, the old memslot is simply replaced + * with a new, updated copy in both memslot sets. + */ + kvm_replace_memslot(kvm, old, new); + kvm_activate_memslot(kvm, old, new); +} + +static int kvm_set_memslot(struct kvm *kvm, + struct kvm_memory_slot *old, + struct kvm_memory_slot *new, + enum kvm_mr_change change) +{ + struct kvm_memory_slot *invalid_slot; + int r; + + /* + * Released in kvm_swap_active_memslots(). + * + * Must be held from before the current memslots are copied until after + * the new memslots are installed with rcu_assign_pointer, then + * released before the synchronize srcu in kvm_swap_active_memslots(). + * + * When modifying memslots outside of the slots_lock, must be held + * before reading the pointer to the current memslots until after all + * changes to those memslots are complete. + * + * These rules ensure that installing new memslots does not lose + * changes made to the previous memslots. + */ + mutex_lock(&kvm->slots_arch_lock); + + /* + * Invalidate the old slot if it's being deleted or moved. This is + * done prior to actually deleting/moving the memslot to allow vCPUs to + * continue running by ensuring there are no mappings or shadow pages + * for the memslot when it is deleted/moved. Without pre-invalidation + * (and without a lock), a window would exist between effecting the + * delete/move and committing the changes in arch code where KVM or a + * guest could access a non-existent memslot. + * + * Modifications are done on a temporary, unreachable slot. The old + * slot needs to be preserved in case a later step fails and the + * invalidation needs to be reverted. + */ + if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) { + invalid_slot = kzalloc(sizeof(*invalid_slot), GFP_KERNEL_ACCOUNT); + if (!invalid_slot) { + mutex_unlock(&kvm->slots_arch_lock); + return -ENOMEM; } - } else if (old.npages) { - change = KVM_MR_DELETE; - } else /* Modify a non-existent slot: disallowed. */ - goto out; + kvm_invalidate_memslot(kvm, old, invalid_slot); + } - 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; + r = kvm_prepare_memory_region(kvm, old, new, change); + if (r) { + /* + * For DELETE/MOVE, revert the above INVALID change. No + * modifications required since the original slot was preserved + * in the inactive slots. Changing the active memslots also + * release slots_arch_lock. + */ + if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) { + kvm_activate_memslot(kvm, invalid_slot, old); + kfree(invalid_slot); + } else { + mutex_unlock(&kvm->slots_arch_lock); } + return r; } - /* Free page dirty bitmap if unneeded */ - if (!(new.flags & KVM_MEM_LOG_DIRTY_PAGES)) - new.dirty_bitmap = NULL; + /* + * For DELETE and MOVE, the working slot is now active as the INVALID + * version of the old slot. MOVE is particularly special as it reuses + * the old slot and returns a copy of the old slot (in working_slot). + * For CREATE, there is no old slot. For DELETE and FLAGS_ONLY, the + * old slot is detached but otherwise preserved. + */ + if (change == KVM_MR_CREATE) + kvm_create_memslot(kvm, new); + else if (change == KVM_MR_DELETE) + kvm_delete_memslot(kvm, old, invalid_slot); + else if (change == KVM_MR_MOVE) + kvm_move_memslot(kvm, old, new, invalid_slot); + else if (change == KVM_MR_FLAGS_ONLY) + kvm_update_flags_memslot(kvm, old, new); + else + BUG(); - r = -ENOMEM; - if (change == KVM_MR_CREATE) { - new.userspace_addr = mem->userspace_addr; + /* Free the temporary INVALID slot used for DELETE and MOVE. */ + if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) + kfree(invalid_slot); - if (kvm_arch_create_memslot(&new, npages)) - goto out_free; - } + /* + * No need to refresh new->arch, changes after dropping slots_arch_lock + * will directly hit the final, active memslot. Architectures are + * responsible for knowing that new->arch may be stale. + */ + kvm_commit_memory_region(kvm, old, new, change); - /* Allocate page dirty bitmap if needed */ - if ((new.flags & KVM_MEM_LOG_DIRTY_PAGES) && !new.dirty_bitmap) { - if (kvm_create_dirty_bitmap(&new) < 0) - goto out_free; - } + return 0; +} - if ((change == KVM_MR_DELETE) || (change == KVM_MR_MOVE)) { - r = -ENOMEM; - slots = kmemdup(kvm->memslots, sizeof(struct kvm_memslots), - GFP_KERNEL); - if (!slots) - goto out_free; - slot = id_to_memslot(slots, mem->slot); - slot->flags |= KVM_MEMSLOT_INVALID; - - old_memslots = install_new_memslots(kvm, slots, NULL); - - /* 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. - * - * validation of sp->gfn happens in: - * - gfn_to_hva (kvm_read_guest, gfn_to_pfn) - * - kvm_is_visible_gfn (mmu_check_roots) - */ - kvm_arch_flush_shadow_memslot(kvm, slot); - slots = old_memslots; +static bool kvm_check_memslot_overlap(struct kvm_memslots *slots, int id, + gfn_t start, gfn_t end) +{ + struct kvm_memslot_iter iter; + + kvm_for_each_memslot_in_gfn_range(&iter, slots, start, end) { + if (iter.slot->id != id) + return true; } - r = kvm_arch_prepare_memory_region(kvm, &new, mem, change); + return false; +} + +static int kvm_set_memory_region(struct kvm *kvm, + const struct kvm_userspace_memory_region2 *mem) +{ + struct kvm_memory_slot *old, *new; + struct kvm_memslots *slots; + enum kvm_mr_change change; + unsigned long npages; + gfn_t base_gfn; + int as_id, id; + int r; + + lockdep_assert_held(&kvm->slots_lock); + + r = check_memory_region_flags(kvm, mem); if (r) - goto out_slots; + return r; + + as_id = mem->slot >> 16; + id = (u16)mem->slot; + + /* General sanity checks */ + if ((mem->memory_size & (PAGE_SIZE - 1)) || + (mem->memory_size != (unsigned long)mem->memory_size)) + return -EINVAL; + if (mem->guest_phys_addr & (PAGE_SIZE - 1)) + return -EINVAL; + /* We can read the guest memory with __xxx_user() later on. */ + if ((mem->userspace_addr & (PAGE_SIZE - 1)) || + (mem->userspace_addr != untagged_addr(mem->userspace_addr)) || + !access_ok((void __user *)(unsigned long)mem->userspace_addr, + mem->memory_size)) + return -EINVAL; + if (mem->flags & KVM_MEM_GUEST_MEMFD && + (mem->guest_memfd_offset & (PAGE_SIZE - 1) || + mem->guest_memfd_offset + mem->memory_size < mem->guest_memfd_offset)) + return -EINVAL; + if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_MEM_SLOTS_NUM) + return -EINVAL; + if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr) + return -EINVAL; - r = -ENOMEM; /* - * 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. + * The size of userspace-defined memory regions is restricted in order + * to play nice with dirty bitmap operations, which are indexed with an + * "unsigned int". KVM's internal memory regions don't support dirty + * logging, and so are exempt. */ - if (!slots) { - slots = kmemdup(kvm->memslots, sizeof(struct kvm_memslots), - GFP_KERNEL); - if (!slots) - goto out_free; - } + if (id < KVM_USER_MEM_SLOTS && + (mem->memory_size >> PAGE_SHIFT) > KVM_MEM_MAX_NR_PAGES) + return -EINVAL; + + slots = __kvm_memslots(kvm, as_id); /* - * 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. + * Note, the old memslot (and the pointer itself!) may be invalidated + * and/or destroyed by kvm_set_memslot(). */ - if ((change == KVM_MR_CREATE) || (change == KVM_MR_MOVE)) { - r = kvm_iommu_map_pages(kvm, &new); - if (r) - goto out_slots; + old = id_to_memslot(slots, id); + + if (!mem->memory_size) { + if (!old || !old->npages) + return -EINVAL; + + if (WARN_ON_ONCE(kvm->nr_memslot_pages < old->npages)) + return -EIO; + + return kvm_set_memslot(kvm, old, NULL, KVM_MR_DELETE); } - /* actual memory is freed via old in kvm_free_physmem_slot below */ - if (change == KVM_MR_DELETE) { - new.dirty_bitmap = NULL; - memset(&new.arch, 0, sizeof(new.arch)); + base_gfn = (mem->guest_phys_addr >> PAGE_SHIFT); + npages = (mem->memory_size >> PAGE_SHIFT); + + if (!old || !old->npages) { + change = KVM_MR_CREATE; + + /* + * To simplify KVM internals, the total number of pages across + * all memslots must fit in an unsigned long. + */ + if ((kvm->nr_memslot_pages + npages) < kvm->nr_memslot_pages) + return -EINVAL; + } else { /* Modify an existing slot. */ + /* Private memslots are immutable, they can only be deleted. */ + if (mem->flags & KVM_MEM_GUEST_MEMFD) + return -EINVAL; + if ((mem->userspace_addr != old->userspace_addr) || + (npages != old->npages) || + ((mem->flags ^ old->flags) & KVM_MEM_READONLY)) + return -EINVAL; + + if (base_gfn != old->base_gfn) + change = KVM_MR_MOVE; + else if (mem->flags != old->flags) + change = KVM_MR_FLAGS_ONLY; + else /* Nothing to change. */ + return 0; } - old_memslots = install_new_memslots(kvm, slots, &new); + if ((change == KVM_MR_CREATE || change == KVM_MR_MOVE) && + kvm_check_memslot_overlap(slots, id, base_gfn, base_gfn + npages)) + return -EEXIST; + + /* Allocate a slot that will persist in the memslot. */ + new = kzalloc(sizeof(*new), GFP_KERNEL_ACCOUNT); + if (!new) + return -ENOMEM; - kvm_arch_commit_memory_region(kvm, mem, &old, change); + new->as_id = as_id; + new->id = id; + new->base_gfn = base_gfn; + new->npages = npages; + new->flags = mem->flags; + new->userspace_addr = mem->userspace_addr; + if (mem->flags & KVM_MEM_GUEST_MEMFD) { + r = kvm_gmem_bind(kvm, new, mem->guest_memfd, mem->guest_memfd_offset); + if (r) + goto out; + } - kvm_free_physmem_slot(&old, &new); - kfree(old_memslots); + r = kvm_set_memslot(kvm, old, new, change); + if (r) + goto out_unbind; return 0; -out_slots: - kfree(slots); -out_free: - kvm_free_physmem_slot(&new, &old); +out_unbind: + if (mem->flags & KVM_MEM_GUEST_MEMFD) + kvm_gmem_unbind(new); out: + kfree(new); return r; } -EXPORT_SYMBOL_GPL(__kvm_set_memory_region); -int kvm_set_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem) +int kvm_set_internal_memslot(struct kvm *kvm, + const struct kvm_userspace_memory_region2 *mem) { - int r; + if (WARN_ON_ONCE(mem->slot < KVM_USER_MEM_SLOTS)) + return -EINVAL; - mutex_lock(&kvm->slots_lock); - r = __kvm_set_memory_region(kvm, mem); - mutex_unlock(&kvm->slots_lock); - return r; + if (WARN_ON_ONCE(mem->flags)) + return -EINVAL; + + return kvm_set_memory_region(kvm, mem); } -EXPORT_SYMBOL_GPL(kvm_set_memory_region); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_set_internal_memslot); -int kvm_vm_ioctl_set_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem) +static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm, + struct kvm_userspace_memory_region2 *mem) { - if (mem->slot >= KVM_USER_MEM_SLOTS) + if ((u16)mem->slot >= KVM_USER_MEM_SLOTS) return -EINVAL; + + guard(mutex)(&kvm->slots_lock); return kvm_set_memory_region(kvm, mem); } -int kvm_get_dirty_log(struct kvm *kvm, - struct kvm_dirty_log *log, int *is_dirty) +#ifndef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT +/** + * kvm_get_dirty_log - get a snapshot of dirty pages + * @kvm: pointer to kvm instance + * @log: slot id and address to which we copy the log + * @is_dirty: set to '1' if any dirty pages were found + * @memslot: set to the associated memslot, always valid on success + */ +int kvm_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log, + int *is_dirty, struct kvm_memory_slot **memslot) { - struct kvm_memory_slot *memslot; - int r, i; + struct kvm_memslots *slots; + int i, as_id, id; unsigned long n; unsigned long any = 0; - r = -EINVAL; - if (log->slot >= KVM_USER_MEM_SLOTS) - goto out; + /* Dirty ring tracking may be exclusive to dirty log tracking */ + if (!kvm_use_dirty_bitmap(kvm)) + return -ENXIO; - memslot = id_to_memslot(kvm->memslots, log->slot); - r = -ENOENT; - if (!memslot->dirty_bitmap) - goto out; + *memslot = NULL; + *is_dirty = 0; - n = kvm_dirty_bitmap_bytes(memslot); + as_id = log->slot >> 16; + id = (u16)log->slot; + if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_USER_MEM_SLOTS) + return -EINVAL; + + slots = __kvm_memslots(kvm, as_id); + *memslot = id_to_memslot(slots, id); + if (!(*memslot) || !(*memslot)->dirty_bitmap) + return -ENOENT; + + kvm_arch_sync_dirty_log(kvm, *memslot); + + n = kvm_dirty_bitmap_bytes(*memslot); for (i = 0; !any && i < n/sizeof(long); ++i) - any = memslot->dirty_bitmap[i]; + any = (*memslot)->dirty_bitmap[i]; - r = -EFAULT; - if (copy_to_user(log->dirty_bitmap, memslot->dirty_bitmap, n)) - goto out; + if (copy_to_user(log->dirty_bitmap, (*memslot)->dirty_bitmap, n)) + return -EFAULT; if (any) *is_dirty = 1; + return 0; +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_get_dirty_log); - r = 0; -out: +#else /* CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT */ +/** + * kvm_get_dirty_log_protect - get a snapshot of dirty pages + * and reenable dirty page tracking for the corresponding pages. + * @kvm: pointer to kvm instance + * @log: slot id and address to which we copy the log + * + * We need to keep it in mind that VCPU threads can write to the bitmap + * concurrently. So, to avoid losing track of dirty pages we keep the + * following order: + * + * 1. Take a snapshot of the bit and clear it if needed. + * 2. Write protect the corresponding page. + * 3. Copy the snapshot to the userspace. + * 4. Upon return caller flushes TLB's if needed. + * + * Between 2 and 4, the guest may write to the page using the remaining TLB + * entry. This is not a problem because the page is reported dirty using + * the snapshot taken before and step 4 ensures that writes done after + * exiting to userspace will be logged for the next call. + * + */ +static int kvm_get_dirty_log_protect(struct kvm *kvm, struct kvm_dirty_log *log) +{ + struct kvm_memslots *slots; + struct kvm_memory_slot *memslot; + int i, as_id, id; + unsigned long n; + unsigned long *dirty_bitmap; + unsigned long *dirty_bitmap_buffer; + bool flush; + + /* Dirty ring tracking may be exclusive to dirty log tracking */ + if (!kvm_use_dirty_bitmap(kvm)) + return -ENXIO; + + as_id = log->slot >> 16; + id = (u16)log->slot; + if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_USER_MEM_SLOTS) + return -EINVAL; + + slots = __kvm_memslots(kvm, as_id); + memslot = id_to_memslot(slots, id); + if (!memslot || !memslot->dirty_bitmap) + return -ENOENT; + + dirty_bitmap = memslot->dirty_bitmap; + + kvm_arch_sync_dirty_log(kvm, memslot); + + n = kvm_dirty_bitmap_bytes(memslot); + flush = false; + if (kvm->manual_dirty_log_protect) { + /* + * Unlike kvm_get_dirty_log, we always return false in *flush, + * because no flush is needed until KVM_CLEAR_DIRTY_LOG. There + * is some code duplication between this function and + * kvm_get_dirty_log, but hopefully all architecture + * transition to kvm_get_dirty_log_protect and kvm_get_dirty_log + * can be eliminated. + */ + dirty_bitmap_buffer = dirty_bitmap; + } else { + dirty_bitmap_buffer = kvm_second_dirty_bitmap(memslot); + memset(dirty_bitmap_buffer, 0, n); + + KVM_MMU_LOCK(kvm); + for (i = 0; i < n / sizeof(long); i++) { + unsigned long mask; + gfn_t offset; + + if (!dirty_bitmap[i]) + continue; + + flush = true; + mask = xchg(&dirty_bitmap[i], 0); + dirty_bitmap_buffer[i] = mask; + + offset = i * BITS_PER_LONG; + kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot, + offset, mask); + } + KVM_MMU_UNLOCK(kvm); + } + + if (flush) + kvm_flush_remote_tlbs_memslot(kvm, memslot); + + if (copy_to_user(log->dirty_bitmap, dirty_bitmap_buffer, n)) + return -EFAULT; + return 0; +} + + +/** + * kvm_vm_ioctl_get_dirty_log - get and clear the log of dirty pages in a slot + * @kvm: kvm instance + * @log: slot id and address to which we copy the log + * + * Steps 1-4 below provide general overview of dirty page logging. See + * kvm_get_dirty_log_protect() function description for additional details. + * + * We call kvm_get_dirty_log_protect() to handle steps 1-3, upon return we + * always flush the TLB (step 4) even if previous step failed and the dirty + * bitmap may be corrupt. Regardless of previous outcome the KVM logging API + * does not preclude user space subsequent dirty log read. Flushing TLB ensures + * writes will be marked dirty for next log read. + * + * 1. Take a snapshot of the bit and clear it if needed. + * 2. Write protect the corresponding page. + * 3. Copy the snapshot to the userspace. + * 4. Flush TLB's if needed. + */ +static int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, + struct kvm_dirty_log *log) +{ + int r; + + mutex_lock(&kvm->slots_lock); + + r = kvm_get_dirty_log_protect(kvm, log); + + mutex_unlock(&kvm->slots_lock); + return r; +} + +/** + * kvm_clear_dirty_log_protect - clear dirty bits in the bitmap + * and reenable dirty page tracking for the corresponding pages. + * @kvm: pointer to kvm instance + * @log: slot id and address from which to fetch the bitmap of dirty pages + */ +static int kvm_clear_dirty_log_protect(struct kvm *kvm, + struct kvm_clear_dirty_log *log) +{ + struct kvm_memslots *slots; + struct kvm_memory_slot *memslot; + int as_id, id; + gfn_t offset; + unsigned long i, n; + unsigned long *dirty_bitmap; + unsigned long *dirty_bitmap_buffer; + bool flush; + + /* Dirty ring tracking may be exclusive to dirty log tracking */ + if (!kvm_use_dirty_bitmap(kvm)) + return -ENXIO; + + as_id = log->slot >> 16; + id = (u16)log->slot; + if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_USER_MEM_SLOTS) + return -EINVAL; + + if (log->first_page & 63) + return -EINVAL; + + slots = __kvm_memslots(kvm, as_id); + memslot = id_to_memslot(slots, id); + if (!memslot || !memslot->dirty_bitmap) + return -ENOENT; + + dirty_bitmap = memslot->dirty_bitmap; + + n = ALIGN(log->num_pages, BITS_PER_LONG) / 8; + + if (log->first_page > memslot->npages || + log->num_pages > memslot->npages - log->first_page || + (log->num_pages < memslot->npages - log->first_page && (log->num_pages & 63))) + return -EINVAL; + + kvm_arch_sync_dirty_log(kvm, memslot); + + flush = false; + dirty_bitmap_buffer = kvm_second_dirty_bitmap(memslot); + if (copy_from_user(dirty_bitmap_buffer, log->dirty_bitmap, n)) + return -EFAULT; + + KVM_MMU_LOCK(kvm); + for (offset = log->first_page, i = offset / BITS_PER_LONG, + n = DIV_ROUND_UP(log->num_pages, BITS_PER_LONG); n--; + i++, offset += BITS_PER_LONG) { + unsigned long mask = *dirty_bitmap_buffer++; + atomic_long_t *p = (atomic_long_t *) &dirty_bitmap[i]; + if (!mask) + continue; + + mask &= atomic_long_fetch_andnot(mask, p); + + /* + * mask contains the bits that really have been cleared. This + * never includes any bits beyond the length of the memslot (if + * the length is not aligned to 64 pages), therefore it is not + * a problem if userspace sets them in log->dirty_bitmap. + */ + if (mask) { + flush = true; + kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot, + offset, mask); + } + } + KVM_MMU_UNLOCK(kvm); + + if (flush) + kvm_flush_remote_tlbs_memslot(kvm, memslot); + + return 0; +} + +static int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm, + struct kvm_clear_dirty_log *log) +{ + int r; + + mutex_lock(&kvm->slots_lock); + + r = kvm_clear_dirty_log_protect(kvm, log); + + mutex_unlock(&kvm->slots_lock); return r; } +#endif /* CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT */ + +#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES +static u64 kvm_supported_mem_attributes(struct kvm *kvm) +{ + if (!kvm || kvm_arch_has_private_mem(kvm)) + return KVM_MEMORY_ATTRIBUTE_PRIVATE; + + return 0; +} + +/* + * Returns true if _all_ gfns in the range [@start, @end) have attributes + * such that the bits in @mask match @attrs. + */ +bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end, + unsigned long mask, unsigned long attrs) +{ + XA_STATE(xas, &kvm->mem_attr_array, start); + unsigned long index; + void *entry; + + mask &= kvm_supported_mem_attributes(kvm); + if (attrs & ~mask) + return false; + + if (end == start + 1) + return (kvm_get_memory_attributes(kvm, start) & mask) == attrs; + + guard(rcu)(); + if (!attrs) + return !xas_find(&xas, end - 1); + + for (index = start; index < end; index++) { + do { + entry = xas_next(&xas); + } while (xas_retry(&xas, entry)); + + if (xas.xa_index != index || + (xa_to_value(entry) & mask) != attrs) + return false; + } + + return true; +} + +static __always_inline void kvm_handle_gfn_range(struct kvm *kvm, + struct kvm_mmu_notifier_range *range) +{ + struct kvm_gfn_range gfn_range; + struct kvm_memory_slot *slot; + struct kvm_memslots *slots; + struct kvm_memslot_iter iter; + bool found_memslot = false; + bool ret = false; + int i; + + gfn_range.arg = range->arg; + gfn_range.may_block = range->may_block; + + /* + * If/when KVM supports more attributes beyond private .vs shared, this + * _could_ set KVM_FILTER_{SHARED,PRIVATE} appropriately if the entire target + * range already has the desired private vs. shared state (it's unclear + * if that is a net win). For now, KVM reaches this point if and only + * if the private flag is being toggled, i.e. all mappings are in play. + */ + + for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { + slots = __kvm_memslots(kvm, i); + + kvm_for_each_memslot_in_gfn_range(&iter, slots, range->start, range->end) { + slot = iter.slot; + gfn_range.slot = slot; + + gfn_range.start = max(range->start, slot->base_gfn); + gfn_range.end = min(range->end, slot->base_gfn + slot->npages); + if (gfn_range.start >= gfn_range.end) + continue; + + if (!found_memslot) { + found_memslot = true; + KVM_MMU_LOCK(kvm); + if (!IS_KVM_NULL_FN(range->on_lock)) + range->on_lock(kvm); + } + + ret |= range->handler(kvm, &gfn_range); + } + } + + if (range->flush_on_ret && ret) + kvm_flush_remote_tlbs(kvm); + + if (found_memslot) + KVM_MMU_UNLOCK(kvm); +} -bool kvm_largepages_enabled(void) +static bool kvm_pre_set_memory_attributes(struct kvm *kvm, + struct kvm_gfn_range *range) { - return largepages_enabled; + /* + * Unconditionally add the range to the invalidation set, regardless of + * whether or not the arch callback actually needs to zap SPTEs. E.g. + * if KVM supports RWX attributes in the future and the attributes are + * going from R=>RW, zapping isn't strictly necessary. Unconditionally + * adding the range allows KVM to require that MMU invalidations add at + * least one range between begin() and end(), e.g. allows KVM to detect + * bugs where the add() is missed. Relaxing the rule *might* be safe, + * but it's not obvious that allowing new mappings while the attributes + * are in flux is desirable or worth the complexity. + */ + kvm_mmu_invalidate_range_add(kvm, range->start, range->end); + + return kvm_arch_pre_set_memory_attributes(kvm, range); } -void kvm_disable_largepages(void) +/* Set @attributes for the gfn range [@start, @end). */ +static int kvm_vm_set_mem_attributes(struct kvm *kvm, gfn_t start, gfn_t end, + unsigned long attributes) { - largepages_enabled = false; + struct kvm_mmu_notifier_range pre_set_range = { + .start = start, + .end = end, + .arg.attributes = attributes, + .handler = kvm_pre_set_memory_attributes, + .on_lock = kvm_mmu_invalidate_begin, + .flush_on_ret = true, + .may_block = true, + }; + struct kvm_mmu_notifier_range post_set_range = { + .start = start, + .end = end, + .arg.attributes = attributes, + .handler = kvm_arch_post_set_memory_attributes, + .on_lock = kvm_mmu_invalidate_end, + .may_block = true, + }; + unsigned long i; + void *entry; + int r = 0; + + entry = attributes ? xa_mk_value(attributes) : NULL; + + trace_kvm_vm_set_mem_attributes(start, end, attributes); + + mutex_lock(&kvm->slots_lock); + + /* Nothing to do if the entire range has the desired attributes. */ + if (kvm_range_has_memory_attributes(kvm, start, end, ~0, attributes)) + goto out_unlock; + + /* + * Reserve memory ahead of time to avoid having to deal with failures + * partway through setting the new attributes. + */ + for (i = start; i < end; i++) { + r = xa_reserve(&kvm->mem_attr_array, i, GFP_KERNEL_ACCOUNT); + if (r) + goto out_unlock; + + cond_resched(); + } + + kvm_handle_gfn_range(kvm, &pre_set_range); + + for (i = start; i < end; i++) { + r = xa_err(xa_store(&kvm->mem_attr_array, i, entry, + GFP_KERNEL_ACCOUNT)); + KVM_BUG_ON(r, kvm); + cond_resched(); + } + + kvm_handle_gfn_range(kvm, &post_set_range); + +out_unlock: + mutex_unlock(&kvm->slots_lock); + + return r; } -EXPORT_SYMBOL_GPL(kvm_disable_largepages); +static int kvm_vm_ioctl_set_mem_attributes(struct kvm *kvm, + struct kvm_memory_attributes *attrs) +{ + gfn_t start, end; + + /* flags is currently not used. */ + if (attrs->flags) + return -EINVAL; + if (attrs->attributes & ~kvm_supported_mem_attributes(kvm)) + return -EINVAL; + if (attrs->size == 0 || attrs->address + attrs->size < attrs->address) + return -EINVAL; + if (!PAGE_ALIGNED(attrs->address) || !PAGE_ALIGNED(attrs->size)) + return -EINVAL; + + start = attrs->address >> PAGE_SHIFT; + end = (attrs->address + attrs->size) >> PAGE_SHIFT; + + /* + * xarray tracks data using "unsigned long", and as a result so does + * KVM. For simplicity, supports generic attributes only on 64-bit + * architectures. + */ + BUILD_BUG_ON(sizeof(attrs->attributes) != sizeof(unsigned long)); + + return kvm_vm_set_mem_attributes(kvm, start, end, attrs->attributes); +} +#endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */ struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn) { return __gfn_to_memslot(kvm_memslots(kvm), gfn); } -EXPORT_SYMBOL_GPL(gfn_to_memslot); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(gfn_to_memslot); -int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn) +struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn) +{ + struct kvm_memslots *slots = kvm_vcpu_memslots(vcpu); + u64 gen = slots->generation; + struct kvm_memory_slot *slot; + + /* + * This also protects against using a memslot from a different address space, + * since different address spaces have different generation numbers. + */ + if (unlikely(gen != vcpu->last_used_slot_gen)) { + vcpu->last_used_slot = NULL; + vcpu->last_used_slot_gen = gen; + } + + slot = try_get_memslot(vcpu->last_used_slot, gfn); + if (slot) + return slot; + + /* + * Fall back to searching all memslots. We purposely use + * search_memslots() instead of __gfn_to_memslot() to avoid + * thrashing the VM-wide last_used_slot in kvm_memslots. + */ + slot = search_memslots(slots, gfn, false); + if (slot) { + vcpu->last_used_slot = slot; + return slot; + } + + return NULL; +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_vcpu_gfn_to_memslot); + +bool 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_USER_MEM_SLOTS || - memslot->flags & KVM_MEMSLOT_INVALID) - return 0; + return kvm_is_visible_memslot(memslot); +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_is_visible_gfn); + +bool kvm_vcpu_is_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn) +{ + struct kvm_memory_slot *memslot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); - return 1; + return kvm_is_visible_memslot(memslot); } -EXPORT_SYMBOL_GPL(kvm_is_visible_gfn); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_vcpu_is_visible_gfn); -unsigned long kvm_host_page_size(struct kvm *kvm, gfn_t gfn) +unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn) { struct vm_area_struct *vma; unsigned long addr, size; size = PAGE_SIZE; - addr = gfn_to_hva(kvm, gfn); + addr = kvm_vcpu_gfn_to_hva_prot(vcpu, gfn, NULL); if (kvm_is_error_hva(addr)) return PAGE_SIZE; - down_read(¤t->mm->mmap_sem); + mmap_read_lock(current->mm); vma = find_vma(current->mm, addr); if (!vma) goto out; @@ -1030,17 +2708,17 @@ unsigned long kvm_host_page_size(struct kvm *kvm, gfn_t gfn) size = vma_kernel_pagesize(vma); out: - up_read(¤t->mm->mmap_sem); + mmap_read_unlock(current->mm); return size; } -static bool memslot_is_readonly(struct kvm_memory_slot *slot) +static bool memslot_is_readonly(const struct kvm_memory_slot *slot) { return slot->flags & KVM_MEM_READONLY; } -static unsigned long __gfn_to_hva_many(struct kvm_memory_slot *slot, gfn_t gfn, +static unsigned long __gfn_to_hva_many(const struct kvm_memory_slot *slot, gfn_t gfn, gfn_t *nr_pages, bool write) { if (!slot || slot->flags & KVM_MEMSLOT_INVALID) @@ -1062,84 +2740,144 @@ 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); } -EXPORT_SYMBOL_GPL(gfn_to_hva_memslot); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(gfn_to_hva_memslot); unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn) { return gfn_to_hva_many(gfn_to_memslot(kvm, gfn), gfn, NULL); } -EXPORT_SYMBOL_GPL(gfn_to_hva); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(gfn_to_hva); + +unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn) +{ + return gfn_to_hva_many(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn, NULL); +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_vcpu_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(). + * Return the hva of a @gfn and the R/W attribute if possible. + * + * @slot: the kvm_memory_slot which contains @gfn + * @gfn: the gfn to be translated + * @writable: used to return the read/write attribute of the @slot if the hva + * is valid and @writable is not NULL */ -static unsigned long gfn_to_hva_read(struct kvm *kvm, gfn_t gfn) +unsigned long gfn_to_hva_memslot_prot(struct kvm_memory_slot *slot, + gfn_t gfn, bool *writable) +{ + unsigned long hva = __gfn_to_hva_many(slot, gfn, NULL, false); + + if (!kvm_is_error_hva(hva) && writable) + *writable = !memslot_is_readonly(slot); + + return hva; +} + +unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable) { - return __gfn_to_hva_many(gfn_to_memslot(kvm, gfn), gfn, NULL, false); + struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn); + + return gfn_to_hva_memslot_prot(slot, gfn, writable); } -static int kvm_read_hva(void *data, void __user *hva, int len) +unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *writable) { - return __copy_from_user(data, hva, len); + struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); + + return gfn_to_hva_memslot_prot(slot, gfn, writable); } -static int kvm_read_hva_atomic(void *data, void __user *hva, int len) +static bool kvm_is_ad_tracked_page(struct page *page) { - return __copy_from_user_inatomic(data, hva, len); + /* + * Per page-flags.h, pages tagged PG_reserved "should in general not be + * touched (e.g. set dirty) except by its owner". + */ + return !PageReserved(page); } -static int get_user_page_nowait(struct task_struct *tsk, struct mm_struct *mm, - unsigned long start, int write, struct page **page) +static void kvm_set_page_dirty(struct page *page) { - int flags = FOLL_TOUCH | FOLL_NOWAIT | FOLL_HWPOISON | FOLL_GET; + if (kvm_is_ad_tracked_page(page)) + SetPageDirty(page); +} - if (write) - flags |= FOLL_WRITE; +static void kvm_set_page_accessed(struct page *page) +{ + if (kvm_is_ad_tracked_page(page)) + mark_page_accessed(page); +} + +void kvm_release_page_clean(struct page *page) +{ + if (!page) + return; + + kvm_set_page_accessed(page); + put_page(page); +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_release_page_clean); + +void kvm_release_page_dirty(struct page *page) +{ + if (!page) + return; - return __get_user_pages(tsk, mm, start, 1, flags, page, NULL, NULL); + kvm_set_page_dirty(page); + kvm_release_page_clean(page); } +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_release_page_dirty); -static inline int check_user_page_hwpoison(unsigned long addr) +static kvm_pfn_t kvm_resolve_pfn(struct kvm_follow_pfn *kfp, struct page *page, + struct follow_pfnmap_args *map, bool writable) { - int rc, flags = FOLL_TOUCH | FOLL_HWPOISON | FOLL_WRITE; + kvm_pfn_t pfn; + + WARN_ON_ONCE(!!page == !!map); + + if (kfp->map_writable) + *kfp->map_writable = writable; - rc = __get_user_pages(current, current->mm, addr, 1, - flags, NULL, NULL, NULL); - return rc == -EHWPOISON; + if (map) + pfn = map->pfn; + else + pfn = page_to_pfn(page); + + *kfp->refcounted_page = page; + + return pfn; } /* - * The atomic path to get the writable pfn which will be stored in @pfn, + * The fast path to get the writable pfn which will be stored in @pfn, * true indicates success, otherwise false is returned. */ -static bool hva_to_pfn_fast(unsigned long addr, bool atomic, bool *async, - bool write_fault, bool *writable, pfn_t *pfn) +static bool hva_to_pfn_fast(struct kvm_follow_pfn *kfp, kvm_pfn_t *pfn) { - struct page *page[1]; - int npages; - - if (!(async || atomic)) - return false; + struct page *page; + bool r; /* - * Fast pin a writable pfn only if it is a write fault request - * or the caller allows to map a writable pfn for a read fault - * request. + * Try the fast-only path when the caller wants to pin/get the page for + * writing. If the caller only wants to read the page, KVM must go + * down the full, slow path in order to avoid racing an operation that + * breaks Copy-on-Write (CoW), e.g. so that KVM doesn't end up pointing + * at the old, read-only page while mm/ points at a new, writable page. */ - if (!(write_fault || writable)) + if (!((kfp->flags & FOLL_WRITE) || kfp->map_writable)) return false; - npages = __get_user_pages_fast(addr, 1, 1, page); - if (npages == 1) { - *pfn = page_to_pfn(page[0]); + if (kfp->pin) + r = pin_user_pages_fast(kfp->hva, 1, FOLL_WRITE, &page) == 1; + else + r = get_user_page_fast_only(kfp->hva, FOLL_WRITE, &page); - if (writable) - *writable = true; + if (r) { + *pfn = kvm_resolve_pfn(kfp, page, NULL, true); return true; } @@ -1150,42 +2888,48 @@ static bool hva_to_pfn_fast(unsigned long addr, bool atomic, bool *async, * The slow path to get the pfn of the specified host virtual address, * 1 indicates success, -errno is returned if error is detected. */ -static int hva_to_pfn_slow(unsigned long addr, bool *async, bool write_fault, - bool *writable, pfn_t *pfn) +static int hva_to_pfn_slow(struct kvm_follow_pfn *kfp, kvm_pfn_t *pfn) { - struct page *page[1]; - int npages = 0; - - might_sleep(); - - if (writable) - *writable = write_fault; + /* + * When a VCPU accesses a page that is not mapped into the secondary + * MMU, we lookup the page using GUP to map it, so the guest VCPU can + * make progress. We always want to honor NUMA hinting faults in that + * case, because GUP usage corresponds to memory accesses from the VCPU. + * Otherwise, we'd not trigger NUMA hinting faults once a page is + * mapped into the secondary MMU and gets accessed by a VCPU. + * + * Note that get_user_page_fast_only() and FOLL_WRITE for now + * implicitly honor NUMA hinting faults and don't need this flag. + */ + unsigned int flags = FOLL_HWPOISON | FOLL_HONOR_NUMA_FAULT | kfp->flags; + struct page *page, *wpage; + int npages; - if (async) { - down_read(¤t->mm->mmap_sem); - npages = get_user_page_nowait(current, current->mm, - addr, write_fault, page); - up_read(¤t->mm->mmap_sem); - } else - npages = get_user_pages_fast(addr, 1, write_fault, - page); + if (kfp->pin) + npages = pin_user_pages_unlocked(kfp->hva, 1, &page, flags); + else + npages = get_user_pages_unlocked(kfp->hva, 1, &page, flags); if (npages != 1) return npages; - /* map read fault as writable if possible */ - if (unlikely(!write_fault) && writable) { - struct page *wpage[1]; - - npages = __get_user_pages_fast(addr, 1, 1, wpage); - if (npages == 1) { - *writable = true; - put_page(page[0]); - page[0] = wpage[0]; - } + /* + * Pinning is mutually exclusive with opportunistically mapping a read + * fault as writable, as KVM should never pin pages when mapping memory + * into the guest (pinning is only for direct accesses from KVM). + */ + if (WARN_ON_ONCE(kfp->map_writable && kfp->pin)) + goto out; - npages = 1; + /* map read fault as writable if possible */ + if (!(flags & FOLL_WRITE) && kfp->map_writable && + get_user_page_fast_only(kfp->hva, FOLL_WRITE, &wpage)) { + put_page(page); + page = wpage; + flags |= FOLL_WRITE; } - *pfn = page_to_pfn(page[0]); + +out: + *pfn = kvm_resolve_pfn(kfp, page, NULL, flags & FOLL_WRITE); return npages; } @@ -1200,238 +2944,238 @@ static bool vma_is_valid(struct vm_area_struct *vma, bool write_fault) return true; } -/* - * Pin guest page in memory and return its pfn. - * @addr: host virtual address which maps memory to the guest - * @atomic: whether this function can sleep - * @async: whether this function need to wait IO complete if the - * host page is not in the memory - * @write_fault: whether we should get a writable host page - * @writable: whether it allows to map a writable host page for !@write_fault - * - * The function will map a writable host page for these two cases: - * 1): @write_fault = true - * 2): @write_fault = false && @writable, @writable will tell the caller - * whether the mapping is writable. - */ -static pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool *async, - bool write_fault, bool *writable) +static int hva_to_pfn_remapped(struct vm_area_struct *vma, + struct kvm_follow_pfn *kfp, kvm_pfn_t *p_pfn) { - struct vm_area_struct *vma; - pfn_t pfn = 0; - int npages; + struct follow_pfnmap_args args = { .vma = vma, .address = kfp->hva }; + bool write_fault = kfp->flags & FOLL_WRITE; + int r; - /* we can do it either atomically or asynchronously, not both */ - BUG_ON(atomic && async); + /* + * Remapped memory cannot be pinned in any meaningful sense. Bail if + * the caller wants to pin the page, i.e. access the page outside of + * MMU notifier protection, and unsafe umappings are disallowed. + */ + if (kfp->pin && !allow_unsafe_mappings) + return -EINVAL; - if (hva_to_pfn_fast(addr, atomic, async, write_fault, writable, &pfn)) - return pfn; + r = follow_pfnmap_start(&args); + if (r) { + /* + * get_user_pages fails for VM_IO and VM_PFNMAP vmas and does + * not call the fault handler, so do it here. + */ + bool unlocked = false; + r = fixup_user_fault(current->mm, kfp->hva, + (write_fault ? FAULT_FLAG_WRITE : 0), + &unlocked); + if (unlocked) + return -EAGAIN; + if (r) + return r; + + r = follow_pfnmap_start(&args); + if (r) + return r; + } + + if (write_fault && !args.writable) { + *p_pfn = KVM_PFN_ERR_RO_FAULT; + goto out; + } + + *p_pfn = kvm_resolve_pfn(kfp, NULL, &args, args.writable); +out: + follow_pfnmap_end(&args); + return r; +} + +kvm_pfn_t hva_to_pfn(struct kvm_follow_pfn *kfp) +{ + struct vm_area_struct *vma; + kvm_pfn_t pfn; + int npages, r; + + might_sleep(); - if (atomic) + if (WARN_ON_ONCE(!kfp->refcounted_page)) return KVM_PFN_ERR_FAULT; - npages = hva_to_pfn_slow(addr, async, write_fault, writable, &pfn); - if (npages == 1) + if (hva_to_pfn_fast(kfp, &pfn)) return pfn; - down_read(¤t->mm->mmap_sem); - if (npages == -EHWPOISON || - (!async && check_user_page_hwpoison(addr))) { - pfn = KVM_PFN_ERR_HWPOISON; - goto exit; - } + npages = hva_to_pfn_slow(kfp, &pfn); + if (npages == 1) + return pfn; + if (npages == -EINTR || npages == -EAGAIN) + return KVM_PFN_ERR_SIGPENDING; + if (npages == -EHWPOISON) + return KVM_PFN_ERR_HWPOISON; - vma = find_vma_intersection(current->mm, addr, addr + 1); + mmap_read_lock(current->mm); +retry: + vma = vma_lookup(current->mm, kfp->hva); if (vma == NULL) pfn = KVM_PFN_ERR_FAULT; - else if ((vma->vm_flags & VM_PFNMAP)) { - pfn = ((addr - vma->vm_start) >> PAGE_SHIFT) + - vma->vm_pgoff; - BUG_ON(!kvm_is_mmio_pfn(pfn)); + else if (vma->vm_flags & (VM_IO | VM_PFNMAP)) { + r = hva_to_pfn_remapped(vma, kfp, &pfn); + if (r == -EAGAIN) + goto retry; + if (r < 0) + pfn = KVM_PFN_ERR_FAULT; } else { - if (async && vma_is_valid(vma, write_fault)) - *async = true; - pfn = KVM_PFN_ERR_FAULT; + if ((kfp->flags & FOLL_NOWAIT) && + vma_is_valid(vma, kfp->flags & FOLL_WRITE)) + pfn = KVM_PFN_ERR_NEEDS_IO; + else + pfn = KVM_PFN_ERR_FAULT; } -exit: - up_read(¤t->mm->mmap_sem); + mmap_read_unlock(current->mm); return pfn; } -static pfn_t -__gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, bool atomic, - bool *async, bool write_fault, bool *writable) +static kvm_pfn_t kvm_follow_pfn(struct kvm_follow_pfn *kfp) { - unsigned long addr = __gfn_to_hva_many(slot, gfn, NULL, write_fault); + kfp->hva = __gfn_to_hva_many(kfp->slot, kfp->gfn, NULL, + kfp->flags & FOLL_WRITE); - if (addr == KVM_HVA_ERR_RO_BAD) + if (kfp->hva == KVM_HVA_ERR_RO_BAD) return KVM_PFN_ERR_RO_FAULT; - if (kvm_is_error_hva(addr)) + if (kvm_is_error_hva(kfp->hva)) return KVM_PFN_NOSLOT; - /* Do not map writable pfn in the readonly memslot. */ - if (writable && memslot_is_readonly(slot)) { - *writable = false; - writable = NULL; + if (memslot_is_readonly(kfp->slot) && kfp->map_writable) { + *kfp->map_writable = false; + kfp->map_writable = NULL; } - return hva_to_pfn(addr, atomic, async, write_fault, - writable); -} - -static pfn_t __gfn_to_pfn(struct kvm *kvm, gfn_t gfn, bool atomic, bool *async, - bool write_fault, bool *writable) -{ - struct kvm_memory_slot *slot; - - if (async) - *async = false; - - slot = gfn_to_memslot(kvm, gfn); - - return __gfn_to_pfn_memslot(slot, gfn, atomic, async, write_fault, - writable); -} - -pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn) -{ - return __gfn_to_pfn(kvm, gfn, true, NULL, true, NULL); + return hva_to_pfn(kfp); } -EXPORT_SYMBOL_GPL(gfn_to_pfn_atomic); -pfn_t gfn_to_pfn_async(struct kvm *kvm, gfn_t gfn, bool *async, - bool write_fault, bool *writable) +kvm_pfn_t __kvm_faultin_pfn(const struct kvm_memory_slot *slot, gfn_t gfn, + unsigned int foll, bool *writable, + struct page **refcounted_page) { - return __gfn_to_pfn(kvm, gfn, false, async, write_fault, writable); -} -EXPORT_SYMBOL_GPL(gfn_to_pfn_async); - -pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn) -{ - return __gfn_to_pfn(kvm, gfn, false, NULL, true, NULL); -} -EXPORT_SYMBOL_GPL(gfn_to_pfn); + struct kvm_follow_pfn kfp = { + .slot = slot, + .gfn = gfn, + .flags = foll, + .map_writable = writable, + .refcounted_page = refcounted_page, + }; -pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault, - bool *writable) -{ - return __gfn_to_pfn(kvm, gfn, false, NULL, write_fault, writable); -} -EXPORT_SYMBOL_GPL(gfn_to_pfn_prot); + if (WARN_ON_ONCE(!writable || !refcounted_page)) + return KVM_PFN_ERR_FAULT; -pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn) -{ - return __gfn_to_pfn_memslot(slot, gfn, false, NULL, true, NULL); -} + *writable = false; + *refcounted_page = NULL; -pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn) -{ - return __gfn_to_pfn_memslot(slot, gfn, true, NULL, true, NULL); + return kvm_follow_pfn(&kfp); } -EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot_atomic); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(__kvm_faultin_pfn); -int gfn_to_page_many_atomic(struct kvm *kvm, gfn_t gfn, struct page **pages, - int nr_pages) +int kvm_prefetch_pages(struct kvm_memory_slot *slot, gfn_t gfn, + struct page **pages, int nr_pages) { unsigned long addr; - gfn_t entry; + gfn_t entry = 0; - addr = gfn_to_hva_many(gfn_to_memslot(kvm, gfn), gfn, &entry); + addr = gfn_to_hva_many(slot, gfn, &entry); if (kvm_is_error_hva(addr)) return -1; if (entry < nr_pages) return 0; - return __get_user_pages_fast(addr, nr_pages, 1, pages); + return get_user_pages_fast_only(addr, nr_pages, FOLL_WRITE, pages); } -EXPORT_SYMBOL_GPL(gfn_to_page_many_atomic); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_prefetch_pages); -static struct page *kvm_pfn_to_page(pfn_t pfn) -{ - if (is_error_noslot_pfn(pfn)) - return KVM_ERR_PTR_BAD_PAGE; - - if (kvm_is_mmio_pfn(pfn)) { - WARN_ON(1); - return KVM_ERR_PTR_BAD_PAGE; - } +/* + * Don't use this API unless you are absolutely, positively certain that KVM + * needs to get a struct page, e.g. to pin the page for firmware DMA. + * + * FIXME: Users of this API likely need to FOLL_PIN the page, not just elevate + * its refcount. + */ +struct page *__gfn_to_page(struct kvm *kvm, gfn_t gfn, bool write) +{ + struct page *refcounted_page = NULL; + struct kvm_follow_pfn kfp = { + .slot = gfn_to_memslot(kvm, gfn), + .gfn = gfn, + .flags = write ? FOLL_WRITE : 0, + .refcounted_page = &refcounted_page, + }; - return pfn_to_page(pfn); + (void)kvm_follow_pfn(&kfp); + return refcounted_page; } +EXPORT_SYMBOL_FOR_KVM_INTERNAL(__gfn_to_page); -struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn) +int __kvm_vcpu_map(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map, + bool writable) { - pfn_t pfn; - - pfn = gfn_to_pfn(kvm, gfn); - - return kvm_pfn_to_page(pfn); -} + struct kvm_follow_pfn kfp = { + .slot = gfn_to_memslot(vcpu->kvm, gfn), + .gfn = gfn, + .flags = writable ? FOLL_WRITE : 0, + .refcounted_page = &map->pinned_page, + .pin = true, + }; -EXPORT_SYMBOL_GPL(gfn_to_page); + map->pinned_page = NULL; + map->page = NULL; + map->hva = NULL; + map->gfn = gfn; + map->writable = writable; -void kvm_release_page_clean(struct page *page) -{ - WARN_ON(is_error_page(page)); + map->pfn = kvm_follow_pfn(&kfp); + if (is_error_noslot_pfn(map->pfn)) + return -EINVAL; - kvm_release_pfn_clean(page_to_pfn(page)); -} -EXPORT_SYMBOL_GPL(kvm_release_page_clean); + if (pfn_valid(map->pfn)) { + map->page = pfn_to_page(map->pfn); + map->hva = kmap(map->page); +#ifdef CONFIG_HAS_IOMEM + } else { + map->hva = memremap(pfn_to_hpa(map->pfn), PAGE_SIZE, MEMREMAP_WB); +#endif + } -void kvm_release_pfn_clean(pfn_t pfn) -{ - if (!is_error_noslot_pfn(pfn) && !kvm_is_mmio_pfn(pfn)) - put_page(pfn_to_page(pfn)); + return map->hva ? 0 : -EFAULT; } -EXPORT_SYMBOL_GPL(kvm_release_pfn_clean); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(__kvm_vcpu_map); -void kvm_release_page_dirty(struct page *page) +void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map) { - WARN_ON(is_error_page(page)); - - kvm_release_pfn_dirty(page_to_pfn(page)); -} -EXPORT_SYMBOL_GPL(kvm_release_page_dirty); + if (!map->hva) + return; -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); + if (map->page) + kunmap(map->page); +#ifdef CONFIG_HAS_IOMEM + else + memunmap(map->hva); +#endif -void kvm_set_page_dirty(struct page *page) -{ - kvm_set_pfn_dirty(page_to_pfn(page)); -} -EXPORT_SYMBOL_GPL(kvm_set_page_dirty); + if (map->writable) + kvm_vcpu_mark_page_dirty(vcpu, map->gfn); -void kvm_set_pfn_dirty(pfn_t pfn) -{ - if (!kvm_is_mmio_pfn(pfn)) { - struct page *page = pfn_to_page(pfn); - if (!PageReserved(page)) - SetPageDirty(page); + if (map->pinned_page) { + if (map->writable) + kvm_set_page_dirty(map->pinned_page); + kvm_set_page_accessed(map->pinned_page); + unpin_user_page(map->pinned_page); } -} -EXPORT_SYMBOL_GPL(kvm_set_pfn_dirty); - -void kvm_set_pfn_accessed(pfn_t pfn) -{ - if (!kvm_is_mmio_pfn(pfn)) - mark_page_accessed(pfn_to_page(pfn)); -} -EXPORT_SYMBOL_GPL(kvm_set_pfn_accessed); -void kvm_get_pfn(pfn_t pfn) -{ - if (!kvm_is_mmio_pfn(pfn)) - get_page(pfn_to_page(pfn)); + map->hva = NULL; + map->page = NULL; + map->pinned_page = NULL; } -EXPORT_SYMBOL_GPL(kvm_get_pfn); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_vcpu_unmap); static int next_segment(unsigned long len, int offset) { @@ -1441,21 +3185,42 @@ static int next_segment(unsigned long len, int offset) return len; } -int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, - int len) +/* Copy @len bytes from guest memory at '(@gfn * PAGE_SIZE) + @offset' to @data */ +static int __kvm_read_guest_page(struct kvm_memory_slot *slot, gfn_t gfn, + void *data, int offset, int len) { int r; unsigned long addr; - addr = gfn_to_hva_read(kvm, gfn); + if (WARN_ON_ONCE(offset + len > PAGE_SIZE)) + return -EFAULT; + + addr = gfn_to_hva_memslot_prot(slot, gfn, NULL); if (kvm_is_error_hva(addr)) return -EFAULT; - r = kvm_read_hva(data, (void __user *)addr + offset, len); + r = __copy_from_user(data, (void __user *)addr + offset, len); if (r) return -EFAULT; return 0; } -EXPORT_SYMBOL_GPL(kvm_read_guest_page); + +int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, + int len) +{ + struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn); + + return __kvm_read_guest_page(slot, gfn, data, offset, len); +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_read_guest_page); + +int kvm_vcpu_read_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, void *data, + int offset, int len) +{ + struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); + + return __kvm_read_guest_page(slot, gfn, data, offset, len); +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_vcpu_read_guest_page); int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len) { @@ -1475,44 +3240,97 @@ int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len) } return 0; } -EXPORT_SYMBOL_GPL(kvm_read_guest); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_read_guest); -int kvm_read_guest_atomic(struct kvm *kvm, gpa_t gpa, void *data, - unsigned long len) +int kvm_vcpu_read_guest(struct kvm_vcpu *vcpu, gpa_t gpa, void *data, unsigned long len) { - int r; - unsigned long addr; gfn_t gfn = gpa >> PAGE_SHIFT; + int seg; int offset = offset_in_page(gpa); + int ret; + + while ((seg = next_segment(len, offset)) != 0) { + ret = kvm_vcpu_read_guest_page(vcpu, gfn, data, offset, seg); + if (ret < 0) + return ret; + offset = 0; + len -= seg; + data += seg; + ++gfn; + } + return 0; +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_vcpu_read_guest); + +static int __kvm_read_guest_atomic(struct kvm_memory_slot *slot, gfn_t gfn, + void *data, int offset, unsigned long len) +{ + int r; + unsigned long addr; - addr = gfn_to_hva_read(kvm, gfn); + if (WARN_ON_ONCE(offset + len > PAGE_SIZE)) + return -EFAULT; + + addr = gfn_to_hva_memslot_prot(slot, gfn, NULL); if (kvm_is_error_hva(addr)) return -EFAULT; pagefault_disable(); - r = kvm_read_hva_atomic(data, (void __user *)addr + offset, len); + r = __copy_from_user_inatomic(data, (void __user *)addr + offset, len); pagefault_enable(); if (r) return -EFAULT; return 0; } -EXPORT_SYMBOL(kvm_read_guest_atomic); -int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn, const void *data, - int offset, int len) +int kvm_vcpu_read_guest_atomic(struct kvm_vcpu *vcpu, gpa_t gpa, + void *data, unsigned long len) +{ + gfn_t gfn = gpa >> PAGE_SHIFT; + struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); + int offset = offset_in_page(gpa); + + return __kvm_read_guest_atomic(slot, gfn, data, offset, len); +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_vcpu_read_guest_atomic); + +/* Copy @len bytes from @data into guest memory at '(@gfn * PAGE_SIZE) + @offset' */ +static int __kvm_write_guest_page(struct kvm *kvm, + struct kvm_memory_slot *memslot, gfn_t gfn, + const void *data, int offset, int len) { int r; unsigned long addr; - addr = gfn_to_hva(kvm, gfn); + if (WARN_ON_ONCE(offset + len > PAGE_SIZE)) + return -EFAULT; + + addr = gfn_to_hva_memslot(memslot, gfn); if (kvm_is_error_hva(addr)) return -EFAULT; r = __copy_to_user((void __user *)addr + offset, data, len); if (r) return -EFAULT; - mark_page_dirty(kvm, gfn); + mark_page_dirty_in_slot(kvm, memslot, gfn); return 0; } -EXPORT_SYMBOL_GPL(kvm_write_guest_page); + +int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn, + const void *data, int offset, int len) +{ + struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn); + + return __kvm_write_guest_page(kvm, slot, gfn, data, offset, len); +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_write_guest_page); + +int kvm_vcpu_write_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, + const void *data, int offset, int len) +{ + struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); + + return __kvm_write_guest_page(vcpu->kvm, slot, gfn, data, offset, len); +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_vcpu_write_guest_page); int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data, unsigned long len) @@ -1533,111 +3351,163 @@ int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data, } return 0; } +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_write_guest); -int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc, - gpa_t gpa, unsigned long len) +int kvm_vcpu_write_guest(struct kvm_vcpu *vcpu, gpa_t gpa, const void *data, + unsigned long len) +{ + gfn_t gfn = gpa >> PAGE_SHIFT; + int seg; + int offset = offset_in_page(gpa); + int ret; + + while ((seg = next_segment(len, offset)) != 0) { + ret = kvm_vcpu_write_guest_page(vcpu, gfn, data, offset, seg); + if (ret < 0) + return ret; + offset = 0; + len -= seg; + data += seg; + ++gfn; + } + return 0; +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_vcpu_write_guest); + +static int __kvm_gfn_to_hva_cache_init(struct kvm_memslots *slots, + struct gfn_to_hva_cache *ghc, + gpa_t gpa, unsigned long len) { - struct kvm_memslots *slots = kvm_memslots(kvm); int offset = offset_in_page(gpa); 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; + /* Update ghc->generation before performing any error checks. */ ghc->generation = slots->generation; - 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) { + + if (start_gfn > end_gfn) { + ghc->hva = KVM_HVA_ERR_BAD; + return -EINVAL; + } + + /* + * If the requested region crosses two memslots, we still + * verify that the entire region is valid here. + */ + for ( ; start_gfn <= end_gfn; start_gfn += nr_pages_avail) { + ghc->memslot = __gfn_to_memslot(slots, start_gfn); + ghc->hva = gfn_to_hva_many(ghc->memslot, start_gfn, + &nr_pages_avail); + if (kvm_is_error_hva(ghc->hva)) + return -EFAULT; + } + + /* Use the slow path for cross page reads and writes. */ + if (nr_pages_needed == 1) ghc->hva += offset; - } 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. */ + else ghc->memslot = NULL; - } + + ghc->gpa = gpa; + ghc->len = len; return 0; } -EXPORT_SYMBOL_GPL(kvm_gfn_to_hva_cache_init); -int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, - void *data, unsigned long len) +int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc, + gpa_t gpa, unsigned long len) { struct kvm_memslots *slots = kvm_memslots(kvm); - int r; + return __kvm_gfn_to_hva_cache_init(slots, ghc, gpa, len); +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_gfn_to_hva_cache_init); - BUG_ON(len > ghc->len); +int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, + void *data, unsigned int offset, + unsigned long len) +{ + struct kvm_memslots *slots = kvm_memslots(kvm); + int r; + gpa_t gpa = ghc->gpa + offset; - if (slots->generation != ghc->generation) - kvm_gfn_to_hva_cache_init(kvm, ghc, ghc->gpa, ghc->len); + if (WARN_ON_ONCE(len + offset > ghc->len)) + return -EINVAL; - if (unlikely(!ghc->memslot)) - return kvm_write_guest(kvm, ghc->gpa, data, len); + if (slots->generation != ghc->generation) { + if (__kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len)) + return -EFAULT; + } if (kvm_is_error_hva(ghc->hva)) return -EFAULT; - r = __copy_to_user((void __user *)ghc->hva, data, len); + if (unlikely(!ghc->memslot)) + return kvm_write_guest(kvm, gpa, data, len); + + r = __copy_to_user((void __user *)ghc->hva + offset, data, len); if (r) return -EFAULT; - mark_page_dirty_in_slot(kvm, ghc->memslot, ghc->gpa >> PAGE_SHIFT); + mark_page_dirty_in_slot(kvm, ghc->memslot, gpa >> PAGE_SHIFT); return 0; } -EXPORT_SYMBOL_GPL(kvm_write_guest_cached); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_write_guest_offset_cached); -int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, +int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, void *data, unsigned long len) { + return kvm_write_guest_offset_cached(kvm, ghc, data, 0, len); +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_write_guest_cached); + +int kvm_read_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, + void *data, unsigned int offset, + unsigned long len) +{ struct kvm_memslots *slots = kvm_memslots(kvm); int r; + gpa_t gpa = ghc->gpa + offset; - BUG_ON(len > ghc->len); - - if (slots->generation != ghc->generation) - kvm_gfn_to_hva_cache_init(kvm, ghc, ghc->gpa, ghc->len); + if (WARN_ON_ONCE(len + offset > ghc->len)) + return -EINVAL; - if (unlikely(!ghc->memslot)) - return kvm_read_guest(kvm, ghc->gpa, data, len); + if (slots->generation != ghc->generation) { + if (__kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len)) + return -EFAULT; + } if (kvm_is_error_hva(ghc->hva)) return -EFAULT; - r = __copy_from_user(data, (void __user *)ghc->hva, len); + if (unlikely(!ghc->memslot)) + return kvm_read_guest(kvm, gpa, data, len); + + r = __copy_from_user(data, (void __user *)ghc->hva + offset, len); if (r) return -EFAULT; return 0; } -EXPORT_SYMBOL_GPL(kvm_read_guest_cached); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_read_guest_offset_cached); -int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len) +int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, + void *data, unsigned long len) { - return kvm_write_guest_page(kvm, gfn, (const void *) empty_zero_page, - offset, len); + return kvm_read_guest_offset_cached(kvm, ghc, data, 0, len); } -EXPORT_SYMBOL_GPL(kvm_clear_guest_page); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_read_guest_cached); int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len) { + const void *zero_page = (const void *) __va(page_to_phys(ZERO_PAGE(0))); gfn_t gfn = gpa >> PAGE_SHIFT; int seg; int offset = offset_in_page(gpa); int ret; - while ((seg = next_segment(len, offset)) != 0) { - ret = kvm_clear_guest_page(kvm, gfn, offset, seg); + while ((seg = next_segment(len, offset)) != 0) { + ret = kvm_write_guest_page(kvm, gfn, zero_page, offset, seg); if (ret < 0) return ret; offset = 0; @@ -1646,17 +3516,32 @@ int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len) } return 0; } -EXPORT_SYMBOL_GPL(kvm_clear_guest); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_clear_guest); -void mark_page_dirty_in_slot(struct kvm *kvm, struct kvm_memory_slot *memslot, - gfn_t gfn) +void mark_page_dirty_in_slot(struct kvm *kvm, + const struct kvm_memory_slot *memslot, + gfn_t gfn) { - if (memslot && memslot->dirty_bitmap) { + struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); + +#ifdef CONFIG_HAVE_KVM_DIRTY_RING + if (WARN_ON_ONCE(vcpu && vcpu->kvm != kvm)) + return; + + WARN_ON_ONCE(!vcpu && !kvm_arch_allow_write_without_running_vcpu(kvm)); +#endif + + if (memslot && kvm_slot_dirty_track_enabled(memslot)) { unsigned long rel_gfn = gfn - memslot->base_gfn; + u32 slot = (memslot->as_id << 16) | memslot->id; - set_bit_le(rel_gfn, memslot->dirty_bitmap); + if (kvm->dirty_ring_size && vcpu) + kvm_dirty_ring_push(vcpu, slot, rel_gfn); + else if (memslot->dirty_bitmap) + set_bit_le(rel_gfn, memslot->dirty_bitmap); } } +EXPORT_SYMBOL_FOR_KVM_INTERNAL(mark_page_dirty_in_slot); void mark_page_dirty(struct kvm *kvm, gfn_t gfn) { @@ -1665,97 +3550,348 @@ 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_FOR_KVM_INTERNAL(mark_page_dirty); + +void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn) +{ + struct kvm_memory_slot *memslot; + + memslot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); + mark_page_dirty_in_slot(vcpu->kvm, memslot, gfn); +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_vcpu_mark_page_dirty); + +void kvm_sigset_activate(struct kvm_vcpu *vcpu) +{ + if (!vcpu->sigset_active) + return; + + /* + * This does a lockless modification of ->real_blocked, which is fine + * because, only current can change ->real_blocked and all readers of + * ->real_blocked don't care as long ->real_blocked is always a subset + * of ->blocked. + */ + sigprocmask(SIG_SETMASK, &vcpu->sigset, ¤t->real_blocked); +} + +void kvm_sigset_deactivate(struct kvm_vcpu *vcpu) +{ + if (!vcpu->sigset_active) + return; + + sigprocmask(SIG_SETMASK, ¤t->real_blocked, NULL); + sigemptyset(¤t->real_blocked); +} + +static void grow_halt_poll_ns(struct kvm_vcpu *vcpu) +{ + unsigned int old, val, grow, grow_start; + + old = val = vcpu->halt_poll_ns; + grow_start = READ_ONCE(halt_poll_ns_grow_start); + grow = READ_ONCE(halt_poll_ns_grow); + if (!grow) + goto out; + + val *= grow; + if (val < grow_start) + val = grow_start; + + vcpu->halt_poll_ns = val; +out: + trace_kvm_halt_poll_ns_grow(vcpu->vcpu_id, val, old); +} + +static void shrink_halt_poll_ns(struct kvm_vcpu *vcpu) +{ + unsigned int old, val, shrink, grow_start; + + old = val = vcpu->halt_poll_ns; + shrink = READ_ONCE(halt_poll_ns_shrink); + grow_start = READ_ONCE(halt_poll_ns_grow_start); + if (shrink == 0) + val = 0; + else + val /= shrink; + + if (val < grow_start) + val = 0; + + vcpu->halt_poll_ns = val; + trace_kvm_halt_poll_ns_shrink(vcpu->vcpu_id, val, old); +} + +static int kvm_vcpu_check_block(struct kvm_vcpu *vcpu) +{ + int ret = -EINTR; + int idx = srcu_read_lock(&vcpu->kvm->srcu); + + if (kvm_arch_vcpu_runnable(vcpu)) + goto out; + if (kvm_cpu_has_pending_timer(vcpu)) + goto out; + if (signal_pending(current)) + goto out; + if (kvm_check_request(KVM_REQ_UNBLOCK, vcpu)) + goto out; + + ret = 0; +out: + srcu_read_unlock(&vcpu->kvm->srcu, idx); + return ret; +} /* - * The vCPU has executed a HLT instruction with in-kernel mode enabled. + * Block the vCPU until the vCPU is runnable, an event arrives, or a signal is + * pending. This is mostly used when halting a vCPU, but may also be used + * directly for other vCPU non-runnable states, e.g. x86's Wait-For-SIPI. */ -void kvm_vcpu_block(struct kvm_vcpu *vcpu) +bool kvm_vcpu_block(struct kvm_vcpu *vcpu) { - DEFINE_WAIT(wait); + struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu); + bool waited = false; + + vcpu->stat.generic.blocking = 1; + + preempt_disable(); + kvm_arch_vcpu_blocking(vcpu); + prepare_to_rcuwait(wait); + preempt_enable(); for (;;) { - prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE); + set_current_state(TASK_INTERRUPTIBLE); - if (kvm_arch_vcpu_runnable(vcpu)) { - kvm_make_request(KVM_REQ_UNHALT, vcpu); - break; - } - if (kvm_cpu_has_pending_timer(vcpu)) - break; - if (signal_pending(current)) + if (kvm_vcpu_check_block(vcpu) < 0) break; + waited = true; schedule(); } - finish_wait(&vcpu->wq, &wait); + preempt_disable(); + finish_rcuwait(wait); + kvm_arch_vcpu_unblocking(vcpu); + preempt_enable(); + + vcpu->stat.generic.blocking = 0; + + return waited; +} + +static inline void update_halt_poll_stats(struct kvm_vcpu *vcpu, ktime_t start, + ktime_t end, bool success) +{ + struct kvm_vcpu_stat_generic *stats = &vcpu->stat.generic; + u64 poll_ns = ktime_to_ns(ktime_sub(end, start)); + + ++vcpu->stat.generic.halt_attempted_poll; + + if (success) { + ++vcpu->stat.generic.halt_successful_poll; + + if (!vcpu_valid_wakeup(vcpu)) + ++vcpu->stat.generic.halt_poll_invalid; + + stats->halt_poll_success_ns += poll_ns; + KVM_STATS_LOG_HIST_UPDATE(stats->halt_poll_success_hist, poll_ns); + } else { + stats->halt_poll_fail_ns += poll_ns; + KVM_STATS_LOG_HIST_UPDATE(stats->halt_poll_fail_hist, poll_ns); + } +} + +static unsigned int kvm_vcpu_max_halt_poll_ns(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + + if (kvm->override_halt_poll_ns) { + /* + * Ensure kvm->max_halt_poll_ns is not read before + * kvm->override_halt_poll_ns. + * + * Pairs with the smp_wmb() when enabling KVM_CAP_HALT_POLL. + */ + smp_rmb(); + return READ_ONCE(kvm->max_halt_poll_ns); + } + + return READ_ONCE(halt_poll_ns); } -#ifndef CONFIG_S390 /* - * Kick a sleeping VCPU, or a guest VCPU in guest mode, into host kernel mode. + * Emulate a vCPU halt condition, e.g. HLT on x86, WFI on arm, etc... If halt + * polling is enabled, busy wait for a short time before blocking to avoid the + * expensive block+unblock sequence if a wake event arrives soon after the vCPU + * is halted. */ -void kvm_vcpu_kick(struct kvm_vcpu *vcpu) +void kvm_vcpu_halt(struct kvm_vcpu *vcpu) { - int me; - int cpu = vcpu->cpu; - wait_queue_head_t *wqp; + unsigned int max_halt_poll_ns = kvm_vcpu_max_halt_poll_ns(vcpu); + bool halt_poll_allowed = !kvm_arch_no_poll(vcpu); + ktime_t start, cur, poll_end; + bool waited = false; + bool do_halt_poll; + u64 halt_ns; + + if (vcpu->halt_poll_ns > max_halt_poll_ns) + vcpu->halt_poll_ns = max_halt_poll_ns; + + do_halt_poll = halt_poll_allowed && vcpu->halt_poll_ns; + + start = cur = poll_end = ktime_get(); + if (do_halt_poll) { + ktime_t stop = ktime_add_ns(start, vcpu->halt_poll_ns); - wqp = kvm_arch_vcpu_wq(vcpu); - if (waitqueue_active(wqp)) { - wake_up_interruptible(wqp); - ++vcpu->stat.halt_wakeup; + do { + if (kvm_vcpu_check_block(vcpu) < 0) + goto out; + cpu_relax(); + poll_end = cur = ktime_get(); + } while (kvm_vcpu_can_poll(cur, stop)); } - me = get_cpu(); - if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) - if (kvm_arch_vcpu_should_kick(vcpu)) - smp_send_reschedule(cpu); - put_cpu(); + waited = kvm_vcpu_block(vcpu); + + cur = ktime_get(); + if (waited) { + vcpu->stat.generic.halt_wait_ns += + ktime_to_ns(cur) - ktime_to_ns(poll_end); + KVM_STATS_LOG_HIST_UPDATE(vcpu->stat.generic.halt_wait_hist, + ktime_to_ns(cur) - ktime_to_ns(poll_end)); + } +out: + /* The total time the vCPU was "halted", including polling time. */ + halt_ns = ktime_to_ns(cur) - ktime_to_ns(start); + + /* + * Note, halt-polling is considered successful so long as the vCPU was + * never actually scheduled out, i.e. even if the wake event arrived + * after of the halt-polling loop itself, but before the full wait. + */ + if (do_halt_poll) + update_halt_poll_stats(vcpu, start, poll_end, !waited); + + if (halt_poll_allowed) { + /* Recompute the max halt poll time in case it changed. */ + max_halt_poll_ns = kvm_vcpu_max_halt_poll_ns(vcpu); + + if (!vcpu_valid_wakeup(vcpu)) { + shrink_halt_poll_ns(vcpu); + } else if (max_halt_poll_ns) { + if (halt_ns <= vcpu->halt_poll_ns) + ; + /* we had a long block, shrink polling */ + else if (vcpu->halt_poll_ns && + halt_ns > max_halt_poll_ns) + shrink_halt_poll_ns(vcpu); + /* we had a short halt and our poll time is too small */ + else if (vcpu->halt_poll_ns < max_halt_poll_ns && + halt_ns < max_halt_poll_ns) + grow_halt_poll_ns(vcpu); + } else { + vcpu->halt_poll_ns = 0; + } + } + + trace_kvm_vcpu_wakeup(halt_ns, waited, vcpu_valid_wakeup(vcpu)); } -EXPORT_SYMBOL_GPL(kvm_vcpu_kick); -#endif /* !CONFIG_S390 */ +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_vcpu_halt); + +bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu) +{ + if (__kvm_vcpu_wake_up(vcpu)) { + WRITE_ONCE(vcpu->ready, true); + ++vcpu->stat.generic.halt_wakeup; + return true; + } + + return false; +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_vcpu_wake_up); -void kvm_resched(struct kvm_vcpu *vcpu) +#ifndef CONFIG_S390 +/* + * Kick a sleeping VCPU, or a guest VCPU in guest mode, into host kernel mode. + */ +void __kvm_vcpu_kick(struct kvm_vcpu *vcpu, bool wait) { - if (!need_resched()) + int me, cpu; + + if (kvm_vcpu_wake_up(vcpu)) return; - cond_resched(); + + me = get_cpu(); + /* + * The only state change done outside the vcpu mutex is IN_GUEST_MODE + * to EXITING_GUEST_MODE. Therefore the moderately expensive "should + * kick" check does not need atomic operations if kvm_vcpu_kick is used + * within the vCPU thread itself. + */ + if (vcpu == __this_cpu_read(kvm_running_vcpu)) { + if (vcpu->mode == IN_GUEST_MODE) + WRITE_ONCE(vcpu->mode, EXITING_GUEST_MODE); + goto out; + } + + /* + * Note, the vCPU could get migrated to a different pCPU at any point + * after kvm_arch_vcpu_should_kick(), which could result in sending an + * IPI to the previous pCPU. But, that's ok because the purpose of the + * IPI is to force the vCPU to leave IN_GUEST_MODE, and migrating the + * vCPU also requires it to leave IN_GUEST_MODE. + */ + if (kvm_arch_vcpu_should_kick(vcpu)) { + cpu = READ_ONCE(vcpu->cpu); + if (cpu != me && (unsigned int)cpu < nr_cpu_ids && cpu_online(cpu)) { + /* + * Use a reschedule IPI to kick the vCPU if the caller + * doesn't need to wait for a response, as KVM allows + * kicking vCPUs while IRQs are disabled, but using the + * SMP function call framework with IRQs disabled can + * deadlock due to taking cross-CPU locks. + */ + if (wait) + smp_call_function_single(cpu, ack_kick, NULL, wait); + else + smp_send_reschedule(cpu); + } + } +out: + put_cpu(); } -EXPORT_SYMBOL_GPL(kvm_resched); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(__kvm_vcpu_kick); +#endif /* !CONFIG_S390 */ -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; - bool ret = false; + int ret; + + if (!read_trylock(&target->pid_lock)) + return 0; - rcu_read_lock(); - pid = rcu_dereference(target->pid); - if (pid) + if (target->pid) task = get_pid_task(target->pid, PIDTYPE_PID); - rcu_read_unlock(); + + read_unlock(&target->pid_lock); + if (!task) - return ret; - if (task->flags & PF_VCPU) { - put_task_struct(task); - return ret; - } + return 0; ret = yield_to(task, 1); put_task_struct(task); return ret; } -EXPORT_SYMBOL_GPL(kvm_vcpu_yield_to); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(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: * * (a) VCPU which has not done pl-exit or cpu relax intercepted recently * (preempted lock holder), indicated by @in_spin_loop. - * Set at the beiginning and cleared at the end of interception/PLE handler. + * Set at the beginning and cleared at the end of interception/PLE handler. * * (b) VCPU which has done pl-exit/ cpu relax intercepted but did not get * chance last time (mostly it has become eligible now since we have probably @@ -1771,64 +3907,130 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_yield_to); * locking does not harm. It may result in trying to yield to same VCPU, fail * and continue with next VCPU and so on. */ -bool kvm_vcpu_eligible_for_directed_yield(struct kvm_vcpu *vcpu) +static bool kvm_vcpu_eligible_for_directed_yield(struct kvm_vcpu *vcpu) { +#ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT bool eligible; eligible = !vcpu->spin_loop.in_spin_loop || - (vcpu->spin_loop.in_spin_loop && - vcpu->spin_loop.dy_eligible); + vcpu->spin_loop.dy_eligible; if (vcpu->spin_loop.in_spin_loop) kvm_vcpu_set_dy_eligible(vcpu, !vcpu->spin_loop.dy_eligible); return eligible; +#else + return true; +#endif } + +/* + * Unlike kvm_arch_vcpu_runnable, this function is called outside + * a vcpu_load/vcpu_put pair. However, for most architectures + * kvm_arch_vcpu_runnable does not require vcpu_load. + */ +bool __weak kvm_arch_dy_runnable(struct kvm_vcpu *vcpu) +{ + return kvm_arch_vcpu_runnable(vcpu); +} + +static bool vcpu_dy_runnable(struct kvm_vcpu *vcpu) +{ + if (kvm_arch_dy_runnable(vcpu)) + return true; + +#ifdef CONFIG_KVM_ASYNC_PF + if (!list_empty_careful(&vcpu->async_pf.done)) + return true; #endif -void kvm_vcpu_on_spin(struct kvm_vcpu *me) + return false; +} + +/* + * By default, simply query the target vCPU's current mode when checking if a + * vCPU was preempted in kernel mode. All architectures except x86 (or more + * specifical, except VMX) allow querying whether or not a vCPU is in kernel + * mode even if the vCPU is NOT loaded, i.e. using kvm_arch_vcpu_in_kernel() + * directly for cross-vCPU checks is functionally correct and accurate. + */ +bool __weak kvm_arch_vcpu_preempted_in_kernel(struct kvm_vcpu *vcpu) +{ + return kvm_arch_vcpu_in_kernel(vcpu); +} + +bool __weak kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu) { + return false; +} + +void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode) +{ + int nr_vcpus, start, i, idx, yielded; 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; + + nr_vcpus = atomic_read(&kvm->online_vcpus); + if (nr_vcpus < 2) + return; + + /* Pairs with the smp_wmb() in kvm_vm_ioctl_create_vcpu(). */ + smp_rmb(); kvm_vcpu_set_in_spin_loop(me, true); + /* - * We boost the priority of a VCPU that is runnable but not - * currently running, because it got preempted by something - * else and called schedule in __vcpu_run. Hopefully that - * VCPU is holding the lock that we need and will release it. - * We approximate round-robin by starting at the last boosted VCPU. + * The current vCPU ("me") is spinning in kernel mode, i.e. is likely + * waiting for a resource to become available. Attempt to yield to a + * vCPU that is runnable, but not currently running, e.g. because the + * vCPU was preempted by a higher priority task. With luck, the vCPU + * that was preempted is holding a lock or some other resource that the + * current vCPU is waiting to acquire, and yielding to the other vCPU + * will allow it to make forward progress and release the lock (or kick + * the spinning vCPU, etc). + * + * Since KVM has no insight into what exactly the guest is doing, + * approximate a round-robin selection by iterating over all vCPUs, + * starting at the last boosted vCPU. I.e. if N=kvm->last_boosted_vcpu, + * iterate over vCPU[N+1]..vCPU[N-1], wrapping as needed. + * + * Note, this is inherently racy, e.g. if multiple vCPUs are spinning, + * they may all try to yield to the same vCPU(s). But as above, this + * is all best effort due to KVM's lack of visibility into the guest. */ - 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)) - continue; - if (!kvm_vcpu_eligible_for_directed_yield(vcpu)) - continue; + start = READ_ONCE(kvm->last_boosted_vcpu) + 1; + for (i = 0; i < nr_vcpus; i++) { + idx = (start + i) % nr_vcpus; + if (idx == me->vcpu_idx) + continue; + + vcpu = xa_load(&kvm->vcpu_array, idx); + if (!READ_ONCE(vcpu->ready)) + continue; + if (kvm_vcpu_is_blocking(vcpu) && !vcpu_dy_runnable(vcpu)) + continue; - yielded = kvm_vcpu_yield_to(vcpu); - if (yielded > 0) { - kvm->last_boosted_vcpu = i; - break; - } else if (yielded < 0) { - try--; - if (!try) - break; - } + /* + * Treat the target vCPU as being in-kernel if it has a pending + * interrupt, as the vCPU trying to yield may be spinning + * waiting on IPI delivery, i.e. the target vCPU is in-kernel + * for the purposes of directed yield. + */ + if (READ_ONCE(vcpu->preempted) && yield_to_kernel_mode && + !kvm_arch_dy_has_pending_interrupt(vcpu) && + !kvm_arch_vcpu_preempted_in_kernel(vcpu)) + continue; + + if (!kvm_vcpu_eligible_for_directed_yield(vcpu)) + continue; + + yielded = kvm_vcpu_yield_to(vcpu); + if (yielded > 0) { + WRITE_ONCE(kvm->last_boosted_vcpu, idx); + break; + } else if (yielded < 0 && !--try) { + break; } } kvm_vcpu_set_in_spin_loop(me, false); @@ -1836,11 +4038,22 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me) /* Ensure vcpu is not eligible during next spinloop */ kvm_vcpu_set_dy_eligible(me, false); } -EXPORT_SYMBOL_GPL(kvm_vcpu_on_spin); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_vcpu_on_spin); -static int kvm_vcpu_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +static bool kvm_page_in_dirty_ring(struct kvm *kvm, unsigned long pgoff) { - struct kvm_vcpu *vcpu = vma->vm_file->private_data; +#ifdef CONFIG_HAVE_KVM_DIRTY_RING + return (pgoff >= KVM_DIRTY_LOG_PAGE_OFFSET) && + (pgoff < KVM_DIRTY_LOG_PAGE_OFFSET + + kvm->dirty_ring_size / PAGE_SIZE); +#else + return false; +#endif +} + +static vm_fault_t kvm_vcpu_fault(struct vm_fault *vmf) +{ + struct kvm_vcpu *vcpu = vmf->vma->vm_file->private_data; struct page *page; if (vmf->pgoff == 0) @@ -1849,10 +4062,14 @@ static int kvm_vcpu_fault(struct vm_area_struct *vma, struct vm_fault *vmf) else if (vmf->pgoff == KVM_PIO_PAGE_OFFSET) page = virt_to_page(vcpu->arch.pio_data); #endif -#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET +#ifdef CONFIG_KVM_MMIO else if (vmf->pgoff == KVM_COALESCED_MMIO_PAGE_OFFSET) page = virt_to_page(vcpu->kvm->coalesced_mmio_ring); #endif + else if (kvm_page_in_dirty_ring(vcpu->kvm, vmf->pgoff)) + page = kvm_dirty_ring_get_page( + &vcpu->dirty_ring, + vmf->pgoff - KVM_DIRTY_LOG_PAGE_OFFSET); else return kvm_arch_vcpu_fault(vcpu, vmf); get_page(page); @@ -1866,6 +4083,14 @@ static const struct vm_operations_struct kvm_vcpu_vm_ops = { static int kvm_vcpu_mmap(struct file *file, struct vm_area_struct *vma) { + struct kvm_vcpu *vcpu = file->private_data; + unsigned long pages = vma_pages(vma); + + if ((kvm_page_in_dirty_ring(vcpu->kvm, vma->vm_pgoff) || + kvm_page_in_dirty_ring(vcpu->kvm, vma->vm_pgoff + pages - 1)) && + ((vma->vm_flags & VM_EXEC) || !(vma->vm_flags & VM_SHARED))) + return -EINVAL; + vma->vm_ops = &kvm_vcpu_vm_ops; return 0; } @@ -1881,11 +4106,9 @@ static int kvm_vcpu_release(struct inode *inode, struct file *filp) static struct file_operations kvm_vcpu_fops = { .release = kvm_vcpu_release, .unlocked_ioctl = kvm_vcpu_ioctl, -#ifdef CONFIG_COMPAT - .compat_ioctl = kvm_vcpu_compat_ioctl, -#endif .mmap = kvm_vcpu_mmap, .llseek = noop_llseek, + KVM_COMPAT(kvm_vcpu_compat_ioctl), }; /* @@ -1893,65 +4116,163 @@ 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); + char name[8 + 1 + ITOA_MAX_LEN + 1]; + + snprintf(name, sizeof(name), "kvm-vcpu:%d", vcpu->vcpu_id); + return anon_inode_getfd(name, &kvm_vcpu_fops, vcpu, O_RDWR | O_CLOEXEC); +} + +#ifdef __KVM_HAVE_ARCH_VCPU_DEBUGFS +static int vcpu_get_pid(void *data, u64 *val) +{ + struct kvm_vcpu *vcpu = data; + + read_lock(&vcpu->pid_lock); + *val = pid_nr(vcpu->pid); + read_unlock(&vcpu->pid_lock); + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(vcpu_get_pid_fops, vcpu_get_pid, NULL, "%llu\n"); + +static void kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu) +{ + struct dentry *debugfs_dentry; + char dir_name[ITOA_MAX_LEN * 2]; + + if (!debugfs_initialized()) + return; + + snprintf(dir_name, sizeof(dir_name), "vcpu%d", vcpu->vcpu_id); + debugfs_dentry = debugfs_create_dir(dir_name, + vcpu->kvm->debugfs_dentry); + debugfs_create_file("pid", 0444, debugfs_dentry, vcpu, + &vcpu_get_pid_fops); + + kvm_arch_create_vcpu_debugfs(vcpu, debugfs_dentry); } +#endif /* * Creates some virtual cpus. Good luck creating more than one. */ -static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) +static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, unsigned long id) { int r; - struct kvm_vcpu *vcpu, *v; + struct kvm_vcpu *vcpu; + struct page *page; - vcpu = kvm_arch_vcpu_create(kvm, id); - if (IS_ERR(vcpu)) - return PTR_ERR(vcpu); + /* + * KVM tracks vCPU IDs as 'int', be kind to userspace and reject + * too-large values instead of silently truncating. + * + * Ensure KVM_MAX_VCPU_IDS isn't pushed above INT_MAX without first + * changing the storage type (at the very least, IDs should be tracked + * as unsigned ints). + */ + BUILD_BUG_ON(KVM_MAX_VCPU_IDS > INT_MAX); + if (id >= KVM_MAX_VCPU_IDS) + return -EINVAL; - preempt_notifier_init(&vcpu->preempt_notifier, &kvm_preempt_ops); + mutex_lock(&kvm->lock); + if (kvm->created_vcpus >= kvm->max_vcpus) { + mutex_unlock(&kvm->lock); + return -EINVAL; + } + + r = kvm_arch_vcpu_precreate(kvm, id); + if (r) { + mutex_unlock(&kvm->lock); + return r; + } + + kvm->created_vcpus++; + mutex_unlock(&kvm->lock); - r = kvm_arch_vcpu_setup(vcpu); + vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL_ACCOUNT); + if (!vcpu) { + r = -ENOMEM; + goto vcpu_decrement; + } + + BUILD_BUG_ON(sizeof(struct kvm_run) > PAGE_SIZE); + page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); + if (!page) { + r = -ENOMEM; + goto vcpu_free; + } + vcpu->run = page_address(page); + + kvm_vcpu_init(vcpu, kvm, id); + + r = kvm_arch_vcpu_create(vcpu); if (r) - goto vcpu_destroy; + goto vcpu_free_run_page; - mutex_lock(&kvm->lock); - if (!kvm_vcpu_compatible(vcpu)) { - r = -EINVAL; - goto unlock_vcpu_destroy; + if (kvm->dirty_ring_size) { + r = kvm_dirty_ring_alloc(kvm, &vcpu->dirty_ring, + id, kvm->dirty_ring_size); + if (r) + goto arch_vcpu_destroy; } - if (atomic_read(&kvm->online_vcpus) == KVM_MAX_VCPUS) { - r = -EINVAL; + + mutex_lock(&kvm->lock); + + if (kvm_get_vcpu_by_id(kvm, id)) { + r = -EEXIST; goto unlock_vcpu_destroy; } - kvm_for_each_vcpu(r, v, kvm) - if (v->vcpu_id == id) { - r = -EEXIST; - goto unlock_vcpu_destroy; - } - - BUG_ON(kvm->vcpus[atomic_read(&kvm->online_vcpus)]); + vcpu->vcpu_idx = atomic_read(&kvm->online_vcpus); + r = xa_insert(&kvm->vcpu_array, vcpu->vcpu_idx, vcpu, GFP_KERNEL_ACCOUNT); + WARN_ON_ONCE(r == -EBUSY); + if (r) + goto unlock_vcpu_destroy; - /* Now it's all set up, let userspace reach it */ + /* + * Now it's all set up, let userspace reach it. Grab the vCPU's mutex + * so that userspace can't invoke vCPU ioctl()s until the vCPU is fully + * visible (per online_vcpus), e.g. so that KVM doesn't get tricked + * into a NULL-pointer dereference because KVM thinks the _current_ + * vCPU doesn't exist. As a bonus, taking vcpu->mutex ensures lockdep + * knows it's taken *inside* kvm->lock. + */ + mutex_lock(&vcpu->mutex); kvm_get_kvm(kvm); r = create_vcpu_fd(vcpu); - if (r < 0) { - kvm_put_kvm(kvm); - goto unlock_vcpu_destroy; - } + if (r < 0) + goto kvm_put_xa_erase; - kvm->vcpus[atomic_read(&kvm->online_vcpus)] = vcpu; + /* + * Pairs with smp_rmb() in kvm_get_vcpu. Store the vcpu + * pointer before kvm->online_vcpu's incremented value. + */ smp_wmb(); atomic_inc(&kvm->online_vcpus); + mutex_unlock(&vcpu->mutex); mutex_unlock(&kvm->lock); kvm_arch_vcpu_postcreate(vcpu); + kvm_create_vcpu_debugfs(vcpu); return r; +kvm_put_xa_erase: + mutex_unlock(&vcpu->mutex); + kvm_put_kvm_no_destroy(kvm); + xa_erase(&kvm->vcpu_array, vcpu->vcpu_idx); unlock_vcpu_destroy: mutex_unlock(&kvm->lock); -vcpu_destroy: + kvm_dirty_ring_free(&vcpu->dirty_ring); +arch_vcpu_destroy: kvm_arch_vcpu_destroy(vcpu); +vcpu_free_run_page: + free_page((unsigned long)vcpu->run); +vcpu_free: + kmem_cache_free(kvm_vcpu_cache, vcpu); +vcpu_decrement: + mutex_lock(&kvm->lock); + kvm->created_vcpus--; + mutex_unlock(&kvm->lock); return r; } @@ -1966,6 +4287,129 @@ static int kvm_vcpu_ioctl_set_sigmask(struct kvm_vcpu *vcpu, sigset_t *sigset) return 0; } +static ssize_t kvm_vcpu_stats_read(struct file *file, char __user *user_buffer, + size_t size, loff_t *offset) +{ + struct kvm_vcpu *vcpu = file->private_data; + + return kvm_stats_read(vcpu->stats_id, &kvm_vcpu_stats_header, + &kvm_vcpu_stats_desc[0], &vcpu->stat, + sizeof(vcpu->stat), user_buffer, size, offset); +} + +static int kvm_vcpu_stats_release(struct inode *inode, struct file *file) +{ + struct kvm_vcpu *vcpu = file->private_data; + + kvm_put_kvm(vcpu->kvm); + return 0; +} + +static const struct file_operations kvm_vcpu_stats_fops = { + .owner = THIS_MODULE, + .read = kvm_vcpu_stats_read, + .release = kvm_vcpu_stats_release, + .llseek = noop_llseek, +}; + +static int kvm_vcpu_ioctl_get_stats_fd(struct kvm_vcpu *vcpu) +{ + int fd; + struct file *file; + char name[15 + ITOA_MAX_LEN + 1]; + + snprintf(name, sizeof(name), "kvm-vcpu-stats:%d", vcpu->vcpu_id); + + fd = get_unused_fd_flags(O_CLOEXEC); + if (fd < 0) + return fd; + + file = anon_inode_getfile_fmode(name, &kvm_vcpu_stats_fops, vcpu, + O_RDONLY, FMODE_PREAD); + if (IS_ERR(file)) { + put_unused_fd(fd); + return PTR_ERR(file); + } + + kvm_get_kvm(vcpu->kvm); + fd_install(fd, file); + + return fd; +} + +#ifdef CONFIG_KVM_GENERIC_PRE_FAULT_MEMORY +static int kvm_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu, + struct kvm_pre_fault_memory *range) +{ + int idx; + long r; + u64 full_size; + + if (range->flags) + return -EINVAL; + + if (!PAGE_ALIGNED(range->gpa) || + !PAGE_ALIGNED(range->size) || + range->gpa + range->size <= range->gpa) + return -EINVAL; + + vcpu_load(vcpu); + idx = srcu_read_lock(&vcpu->kvm->srcu); + + full_size = range->size; + do { + if (signal_pending(current)) { + r = -EINTR; + break; + } + + r = kvm_arch_vcpu_pre_fault_memory(vcpu, range); + if (WARN_ON_ONCE(r == 0 || r == -EIO)) + break; + + if (r < 0) + break; + + range->size -= r; + range->gpa += r; + cond_resched(); + } while (range->size); + + srcu_read_unlock(&vcpu->kvm->srcu, idx); + vcpu_put(vcpu); + + /* Return success if at least one page was mapped successfully. */ + return full_size == range->size ? r : 0; +} +#endif + +static int kvm_wait_for_vcpu_online(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + + /* + * In practice, this happy path will always be taken, as a well-behaved + * VMM will never invoke a vCPU ioctl() before KVM_CREATE_VCPU returns. + */ + if (likely(vcpu->vcpu_idx < atomic_read(&kvm->online_vcpus))) + return 0; + + /* + * Acquire and release the vCPU's mutex to wait for vCPU creation to + * complete (kvm_vm_ioctl_create_vcpu() holds the mutex until the vCPU + * is fully online). + */ + if (mutex_lock_killable(&vcpu->mutex)) + return -EINTR; + + mutex_unlock(&vcpu->mutex); + + if (WARN_ON_ONCE(!kvm_get_vcpu(kvm, vcpu->vcpu_idx))) + return -EIO; + + return 0; +} + static long kvm_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -1975,30 +4419,73 @@ static long kvm_vcpu_ioctl(struct file *filp, struct kvm_fpu *fpu = NULL; struct kvm_sregs *kvm_sregs = NULL; - if (vcpu->kvm->mm != current->mm) + if (vcpu->kvm->mm != current->mm || vcpu->kvm->vm_dead) return -EIO; -#if defined(CONFIG_S390) || defined(CONFIG_PPC) || defined(CONFIG_MIPS) + if (unlikely(_IOC_TYPE(ioctl) != KVMIO)) + return -EINVAL; + /* - * Special cases: vcpu ioctls that are asynchronous to vcpu execution, - * so vcpu_load() would break it. + * Wait for the vCPU to be online before handling the ioctl(), as KVM + * assumes the vCPU is reachable via vcpu_array, i.e. may dereference + * a NULL pointer if userspace invokes an ioctl() before KVM is ready. */ - if (ioctl == KVM_S390_INTERRUPT || ioctl == KVM_INTERRUPT) - return kvm_arch_vcpu_ioctl(filp, ioctl, arg); -#endif - - - r = vcpu_load(vcpu); + r = kvm_wait_for_vcpu_online(vcpu); if (r) return r; + + /* + * Let arch code handle select vCPU ioctls without holding vcpu->mutex, + * e.g. to support ioctls that can run asynchronous to vCPU execution. + */ + r = kvm_arch_vcpu_unlocked_ioctl(filp, ioctl, arg); + if (r != -ENOIOCTLCMD) + return r; + + if (mutex_lock_killable(&vcpu->mutex)) + return -EINTR; switch (ioctl) { - case KVM_RUN: + case KVM_RUN: { + struct pid *oldpid; r = -EINVAL; if (arg) goto out; - r = kvm_arch_vcpu_ioctl_run(vcpu, vcpu->run); + + /* + * Note, vcpu->pid is primarily protected by vcpu->mutex. The + * dedicated r/w lock allows other tasks, e.g. other vCPUs, to + * read vcpu->pid while this vCPU is in KVM_RUN, e.g. to yield + * directly to this vCPU + */ + oldpid = vcpu->pid; + if (unlikely(oldpid != task_pid(current))) { + /* The thread running this VCPU changed. */ + struct pid *newpid; + + r = kvm_arch_vcpu_run_pid_change(vcpu); + if (r) + break; + + newpid = get_task_pid(current, PIDTYPE_PID); + write_lock(&vcpu->pid_lock); + vcpu->pid = newpid; + write_unlock(&vcpu->pid_lock); + + put_pid(oldpid); + } + vcpu->wants_to_run = !READ_ONCE(vcpu->run->immediate_exit__unsafe); + r = kvm_arch_vcpu_ioctl_run(vcpu); + vcpu->wants_to_run = false; + + /* + * FIXME: Remove this hack once all KVM architectures + * support the generic TIF bits, i.e. a dedicated TIF_RSEQ. + */ + rseq_virt_userspace_exit(); + trace_kvm_userspace_exit(vcpu->run->exit_reason, r); break; + } case KVM_GET_REGS: { struct kvm_regs *kvm_regs; @@ -2020,7 +4507,6 @@ out_free1: case KVM_SET_REGS: { struct kvm_regs *kvm_regs; - r = -ENOMEM; kvm_regs = memdup_user(argp, sizeof(*kvm_regs)); if (IS_ERR(kvm_regs)) { r = PTR_ERR(kvm_regs); @@ -2061,7 +4547,7 @@ out_free1: if (r) goto out; r = -EFAULT; - if (copy_to_user(argp, &mp_state, sizeof mp_state)) + if (copy_to_user(argp, &mp_state, sizeof(mp_state))) goto out; r = 0; break; @@ -2070,7 +4556,7 @@ out_free1: struct kvm_mp_state mp_state; r = -EFAULT; - if (copy_from_user(&mp_state, argp, sizeof mp_state)) + if (copy_from_user(&mp_state, argp, sizeof(mp_state))) goto out; r = kvm_arch_vcpu_ioctl_set_mpstate(vcpu, &mp_state); break; @@ -2079,13 +4565,13 @@ out_free1: struct kvm_translation tr; r = -EFAULT; - if (copy_from_user(&tr, argp, sizeof tr)) + if (copy_from_user(&tr, argp, sizeof(tr))) goto out; r = kvm_arch_vcpu_ioctl_translate(vcpu, &tr); if (r) goto out; r = -EFAULT; - if (copy_to_user(argp, &tr, sizeof tr)) + if (copy_to_user(argp, &tr, sizeof(tr))) goto out; r = 0; break; @@ -2094,7 +4580,7 @@ out_free1: struct kvm_guest_debug dbg; r = -EFAULT; - if (copy_from_user(&dbg, argp, sizeof dbg)) + if (copy_from_user(&dbg, argp, sizeof(dbg))) goto out; r = kvm_arch_vcpu_ioctl_set_guest_debug(vcpu, &dbg); break; @@ -2108,14 +4594,14 @@ out_free1: if (argp) { r = -EFAULT; if (copy_from_user(&kvm_sigmask, argp, - sizeof kvm_sigmask)) + sizeof(kvm_sigmask))) goto out; r = -EINVAL; - if (kvm_sigmask.len != sizeof sigset) + if (kvm_sigmask.len != sizeof(sigset)) goto out; r = -EFAULT; if (copy_from_user(&sigset, sigmask_arg->sigset, - sizeof sigset)) + sizeof(sigset))) goto out; p = &sigset; } @@ -2146,17 +4632,35 @@ out_free1: r = kvm_arch_vcpu_ioctl_set_fpu(vcpu, fpu); break; } + case KVM_GET_STATS_FD: { + r = kvm_vcpu_ioctl_get_stats_fd(vcpu); + break; + } +#ifdef CONFIG_KVM_GENERIC_PRE_FAULT_MEMORY + case KVM_PRE_FAULT_MEMORY: { + struct kvm_pre_fault_memory range; + + r = -EFAULT; + if (copy_from_user(&range, argp, sizeof(range))) + break; + r = kvm_vcpu_pre_fault_memory(vcpu, &range); + /* Pass back leftover range. */ + if (copy_to_user(argp, &range, sizeof(range))) + r = -EFAULT; + break; + } +#endif default: r = kvm_arch_vcpu_ioctl(filp, ioctl, arg); } out: - vcpu_put(vcpu); + mutex_unlock(&vcpu->mutex); kfree(fpu); kfree(kvm_sregs); return r; } -#ifdef CONFIG_COMPAT +#ifdef CONFIG_KVM_COMPAT static long kvm_vcpu_compat_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -2164,29 +4668,27 @@ static long kvm_vcpu_compat_ioctl(struct file *filp, void __user *argp = compat_ptr(arg); int r; - if (vcpu->kvm->mm != current->mm) + if (vcpu->kvm->mm != current->mm || vcpu->kvm->vm_dead) return -EIO; switch (ioctl) { case KVM_SET_SIGNAL_MASK: { struct kvm_signal_mask __user *sigmask_arg = argp; struct kvm_signal_mask kvm_sigmask; - compat_sigset_t csigset; sigset_t sigset; if (argp) { r = -EFAULT; if (copy_from_user(&kvm_sigmask, argp, - sizeof kvm_sigmask)) + sizeof(kvm_sigmask))) goto out; r = -EINVAL; - if (kvm_sigmask.len != sizeof csigset) + if (kvm_sigmask.len != sizeof(compat_sigset_t)) goto out; r = -EFAULT; - if (copy_from_user(&csigset, sigmask_arg->sigset, - sizeof csigset)) + if (get_compat_sigset(&sigset, + (compat_sigset_t __user *)sigmask_arg->sigset)) goto out; - sigset_from_compat(&sigset, &csigset); r = kvm_vcpu_ioctl_set_sigmask(vcpu, &sigset); } else r = kvm_vcpu_ioctl_set_sigmask(vcpu, NULL); @@ -2201,6 +4703,16 @@ out: } #endif +static int kvm_device_mmap(struct file *filp, struct vm_area_struct *vma) +{ + struct kvm_device *dev = filp->private_data; + + if (dev->ops->mmap) + return dev->ops->mmap(dev, vma); + + return -ENODEV; +} + static int kvm_device_ioctl_attr(struct kvm_device *dev, int (*accessor)(struct kvm_device *dev, struct kvm_device_attr *attr), @@ -2222,6 +4734,9 @@ static long kvm_device_ioctl(struct file *filp, unsigned int ioctl, { struct kvm_device *dev = filp->private_data; + if (dev->kvm->mm != current->mm || dev->kvm->vm_dead) + return -EIO; + switch (ioctl) { case KVM_SET_DEVICE_ATTR: return kvm_device_ioctl_attr(dev, dev->ops->set_attr, arg); @@ -2242,16 +4757,23 @@ static int kvm_device_release(struct inode *inode, struct file *filp) struct kvm_device *dev = filp->private_data; struct kvm *kvm = dev->kvm; + if (dev->ops->release) { + mutex_lock(&kvm->lock); + list_del_rcu(&dev->vm_node); + synchronize_rcu(); + dev->ops->release(dev); + mutex_unlock(&kvm->lock); + } + kvm_put_kvm(kvm); return 0; } -static const struct file_operations kvm_device_fops = { +static struct file_operations kvm_device_fops = { .unlocked_ioctl = kvm_device_ioctl, -#ifdef CONFIG_COMPAT - .compat_ioctl = kvm_device_ioctl, -#endif .release = kvm_device_release, + KVM_COMPAT(kvm_device_ioctl), + .mmap = kvm_device_mmap, }; struct kvm_device *kvm_device_from_filp(struct file *filp) @@ -2262,58 +4784,373 @@ struct kvm_device *kvm_device_from_filp(struct file *filp) return filp->private_data; } +static const struct kvm_device_ops *kvm_device_ops_table[KVM_DEV_TYPE_MAX] = { +#ifdef CONFIG_KVM_MPIC + [KVM_DEV_TYPE_FSL_MPIC_20] = &kvm_mpic_ops, + [KVM_DEV_TYPE_FSL_MPIC_42] = &kvm_mpic_ops, +#endif +}; + +int kvm_register_device_ops(const struct kvm_device_ops *ops, u32 type) +{ + if (type >= ARRAY_SIZE(kvm_device_ops_table)) + return -ENOSPC; + + if (kvm_device_ops_table[type] != NULL) + return -EEXIST; + + kvm_device_ops_table[type] = ops; + return 0; +} + +void kvm_unregister_device_ops(u32 type) +{ + if (kvm_device_ops_table[type] != NULL) + kvm_device_ops_table[type] = NULL; +} + static int kvm_ioctl_create_device(struct kvm *kvm, struct kvm_create_device *cd) { - struct kvm_device_ops *ops = NULL; + const struct kvm_device_ops *ops; struct kvm_device *dev; bool test = cd->flags & KVM_CREATE_DEVICE_TEST; + int type; int ret; - switch (cd->type) { -#ifdef CONFIG_KVM_MPIC - case KVM_DEV_TYPE_FSL_MPIC_20: - case KVM_DEV_TYPE_FSL_MPIC_42: - ops = &kvm_mpic_ops; - break; -#endif -#ifdef CONFIG_KVM_XICS - case KVM_DEV_TYPE_XICS: - ops = &kvm_xics_ops; - break; -#endif - default: + if (cd->type >= ARRAY_SIZE(kvm_device_ops_table)) + return -ENODEV; + + type = array_index_nospec(cd->type, ARRAY_SIZE(kvm_device_ops_table)); + ops = kvm_device_ops_table[type]; + if (ops == NULL) return -ENODEV; - } if (test) return 0; - dev = kzalloc(sizeof(*dev), GFP_KERNEL); + dev = kzalloc(sizeof(*dev), GFP_KERNEL_ACCOUNT); if (!dev) return -ENOMEM; dev->ops = ops; dev->kvm = kvm; - ret = ops->create(dev, cd->type); + mutex_lock(&kvm->lock); + ret = ops->create(dev, type); if (ret < 0) { + mutex_unlock(&kvm->lock); kfree(dev); return ret; } + list_add_rcu(&dev->vm_node, &kvm->devices); + mutex_unlock(&kvm->lock); - ret = anon_inode_getfd(ops->name, &kvm_device_fops, dev, O_RDWR); + if (ops->init) + ops->init(dev); + + kvm_get_kvm(kvm); + ret = anon_inode_getfd(ops->name, &kvm_device_fops, dev, O_RDWR | O_CLOEXEC); if (ret < 0) { - ops->destroy(dev); + kvm_put_kvm_no_destroy(kvm); + mutex_lock(&kvm->lock); + list_del_rcu(&dev->vm_node); + synchronize_rcu(); + if (ops->release) + ops->release(dev); + mutex_unlock(&kvm->lock); + if (ops->destroy) + ops->destroy(dev); return ret; } - list_add(&dev->vm_node, &kvm->devices); - kvm_get_kvm(kvm); cd->fd = ret; return 0; } +static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) +{ + switch (arg) { + case KVM_CAP_USER_MEMORY: + case KVM_CAP_USER_MEMORY2: + case KVM_CAP_DESTROY_MEMORY_REGION_WORKS: + case KVM_CAP_JOIN_MEMORY_REGIONS_WORKS: + case KVM_CAP_INTERNAL_ERROR_DATA: +#ifdef CONFIG_HAVE_KVM_MSI + case KVM_CAP_SIGNAL_MSI: +#endif +#ifdef CONFIG_HAVE_KVM_IRQCHIP + case KVM_CAP_IRQFD: +#endif + case KVM_CAP_IOEVENTFD_ANY_LENGTH: + case KVM_CAP_CHECK_EXTENSION_VM: + case KVM_CAP_ENABLE_CAP_VM: + case KVM_CAP_HALT_POLL: + return 1; +#ifdef CONFIG_KVM_MMIO + case KVM_CAP_COALESCED_MMIO: + return KVM_COALESCED_MMIO_PAGE_OFFSET; + case KVM_CAP_COALESCED_PIO: + return 1; +#endif +#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT + case KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2: + return KVM_DIRTY_LOG_MANUAL_CAPS; +#endif +#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING + case KVM_CAP_IRQ_ROUTING: + return KVM_MAX_IRQ_ROUTES; +#endif +#if KVM_MAX_NR_ADDRESS_SPACES > 1 + case KVM_CAP_MULTI_ADDRESS_SPACE: + if (kvm) + return kvm_arch_nr_memslot_as_ids(kvm); + return KVM_MAX_NR_ADDRESS_SPACES; +#endif + case KVM_CAP_NR_MEMSLOTS: + return KVM_USER_MEM_SLOTS; + case KVM_CAP_DIRTY_LOG_RING: +#ifdef CONFIG_HAVE_KVM_DIRTY_RING_TSO + return KVM_DIRTY_RING_MAX_ENTRIES * sizeof(struct kvm_dirty_gfn); +#else + return 0; +#endif + case KVM_CAP_DIRTY_LOG_RING_ACQ_REL: +#ifdef CONFIG_HAVE_KVM_DIRTY_RING_ACQ_REL + return KVM_DIRTY_RING_MAX_ENTRIES * sizeof(struct kvm_dirty_gfn); +#else + return 0; +#endif +#ifdef CONFIG_NEED_KVM_DIRTY_RING_WITH_BITMAP + case KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP: +#endif + case KVM_CAP_BINARY_STATS_FD: + case KVM_CAP_SYSTEM_EVENT_DATA: + case KVM_CAP_DEVICE_CTRL: + return 1; +#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES + case KVM_CAP_MEMORY_ATTRIBUTES: + return kvm_supported_mem_attributes(kvm); +#endif +#ifdef CONFIG_KVM_GUEST_MEMFD + case KVM_CAP_GUEST_MEMFD: + return 1; + case KVM_CAP_GUEST_MEMFD_FLAGS: + return kvm_gmem_get_supported_flags(kvm); +#endif + default: + break; + } + return kvm_vm_ioctl_check_extension(kvm, arg); +} + +static int kvm_vm_ioctl_enable_dirty_log_ring(struct kvm *kvm, u32 size) +{ + int r; + + if (!KVM_DIRTY_LOG_PAGE_OFFSET) + return -EINVAL; + + /* the size should be power of 2 */ + if (!size || (size & (size - 1))) + return -EINVAL; + + /* Should be bigger to keep the reserved entries, or a page */ + if (size < kvm_dirty_ring_get_rsvd_entries(kvm) * + sizeof(struct kvm_dirty_gfn) || size < PAGE_SIZE) + return -EINVAL; + + if (size > KVM_DIRTY_RING_MAX_ENTRIES * + sizeof(struct kvm_dirty_gfn)) + return -E2BIG; + + /* We only allow it to set once */ + if (kvm->dirty_ring_size) + return -EINVAL; + + mutex_lock(&kvm->lock); + + if (kvm->created_vcpus) { + /* We don't allow to change this value after vcpu created */ + r = -EINVAL; + } else { + kvm->dirty_ring_size = size; + r = 0; + } + + mutex_unlock(&kvm->lock); + return r; +} + +static int kvm_vm_ioctl_reset_dirty_pages(struct kvm *kvm) +{ + unsigned long i; + struct kvm_vcpu *vcpu; + int cleared = 0, r; + + if (!kvm->dirty_ring_size) + return -EINVAL; + + mutex_lock(&kvm->slots_lock); + + kvm_for_each_vcpu(i, vcpu, kvm) { + r = kvm_dirty_ring_reset(vcpu->kvm, &vcpu->dirty_ring, &cleared); + if (r) + break; + } + + mutex_unlock(&kvm->slots_lock); + + if (cleared) + kvm_flush_remote_tlbs(kvm); + + return cleared; +} + +int __attribute__((weak)) kvm_vm_ioctl_enable_cap(struct kvm *kvm, + struct kvm_enable_cap *cap) +{ + return -EINVAL; +} + +bool kvm_are_all_memslots_empty(struct kvm *kvm) +{ + int i; + + lockdep_assert_held(&kvm->slots_lock); + + for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { + if (!kvm_memslots_empty(__kvm_memslots(kvm, i))) + return false; + } + + return true; +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_are_all_memslots_empty); + +static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm, + struct kvm_enable_cap *cap) +{ + switch (cap->cap) { +#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT + case KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2: { + u64 allowed_options = KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE; + + if (cap->args[0] & KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE) + allowed_options = KVM_DIRTY_LOG_MANUAL_CAPS; + + if (cap->flags || (cap->args[0] & ~allowed_options)) + return -EINVAL; + kvm->manual_dirty_log_protect = cap->args[0]; + return 0; + } +#endif + case KVM_CAP_HALT_POLL: { + if (cap->flags || cap->args[0] != (unsigned int)cap->args[0]) + return -EINVAL; + + kvm->max_halt_poll_ns = cap->args[0]; + + /* + * Ensure kvm->override_halt_poll_ns does not become visible + * before kvm->max_halt_poll_ns. + * + * Pairs with the smp_rmb() in kvm_vcpu_max_halt_poll_ns(). + */ + smp_wmb(); + kvm->override_halt_poll_ns = true; + + return 0; + } + case KVM_CAP_DIRTY_LOG_RING: + case KVM_CAP_DIRTY_LOG_RING_ACQ_REL: + if (!kvm_vm_ioctl_check_extension_generic(kvm, cap->cap)) + return -EINVAL; + + return kvm_vm_ioctl_enable_dirty_log_ring(kvm, cap->args[0]); + case KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP: { + int r = -EINVAL; + + if (!IS_ENABLED(CONFIG_NEED_KVM_DIRTY_RING_WITH_BITMAP) || + !kvm->dirty_ring_size || cap->flags) + return r; + + mutex_lock(&kvm->slots_lock); + + /* + * For simplicity, allow enabling ring+bitmap if and only if + * there are no memslots, e.g. to ensure all memslots allocate + * a bitmap after the capability is enabled. + */ + if (kvm_are_all_memslots_empty(kvm)) { + kvm->dirty_ring_with_bitmap = true; + r = 0; + } + + mutex_unlock(&kvm->slots_lock); + + return r; + } + default: + return kvm_vm_ioctl_enable_cap(kvm, cap); + } +} + +static ssize_t kvm_vm_stats_read(struct file *file, char __user *user_buffer, + size_t size, loff_t *offset) +{ + struct kvm *kvm = file->private_data; + + return kvm_stats_read(kvm->stats_id, &kvm_vm_stats_header, + &kvm_vm_stats_desc[0], &kvm->stat, + sizeof(kvm->stat), user_buffer, size, offset); +} + +static int kvm_vm_stats_release(struct inode *inode, struct file *file) +{ + struct kvm *kvm = file->private_data; + + kvm_put_kvm(kvm); + return 0; +} + +static const struct file_operations kvm_vm_stats_fops = { + .owner = THIS_MODULE, + .read = kvm_vm_stats_read, + .release = kvm_vm_stats_release, + .llseek = noop_llseek, +}; + +static int kvm_vm_ioctl_get_stats_fd(struct kvm *kvm) +{ + int fd; + struct file *file; + + fd = get_unused_fd_flags(O_CLOEXEC); + if (fd < 0) + return fd; + + file = anon_inode_getfile_fmode("kvm-vm-stats", + &kvm_vm_stats_fops, kvm, O_RDONLY, FMODE_PREAD); + if (IS_ERR(file)) { + put_unused_fd(fd); + return PTR_ERR(file); + } + + kvm_get_kvm(kvm); + fd_install(fd, file); + + return fd; +} + +#define SANITY_CHECK_MEM_REGION_FIELD(field) \ +do { \ + BUILD_BUG_ON(offsetof(struct kvm_userspace_memory_region, field) != \ + offsetof(struct kvm_userspace_memory_region2, field)); \ + BUILD_BUG_ON(sizeof_field(struct kvm_userspace_memory_region, field) != \ + sizeof_field(struct kvm_userspace_memory_region2, field)); \ +} while (0) + static long kvm_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -2321,45 +5158,91 @@ static long kvm_vm_ioctl(struct file *filp, void __user *argp = (void __user *)arg; int r; - if (kvm->mm != current->mm) + if (kvm->mm != current->mm || kvm->vm_dead) return -EIO; switch (ioctl) { case KVM_CREATE_VCPU: r = kvm_vm_ioctl_create_vcpu(kvm, arg); break; + case KVM_ENABLE_CAP: { + struct kvm_enable_cap cap; + + r = -EFAULT; + if (copy_from_user(&cap, argp, sizeof(cap))) + goto out; + r = kvm_vm_ioctl_enable_cap_generic(kvm, &cap); + break; + } + case KVM_SET_USER_MEMORY_REGION2: case KVM_SET_USER_MEMORY_REGION: { - struct kvm_userspace_memory_region kvm_userspace_mem; + struct kvm_userspace_memory_region2 mem; + unsigned long size; + + if (ioctl == KVM_SET_USER_MEMORY_REGION) { + /* + * Fields beyond struct kvm_userspace_memory_region shouldn't be + * accessed, but avoid leaking kernel memory in case of a bug. + */ + memset(&mem, 0, sizeof(mem)); + size = sizeof(struct kvm_userspace_memory_region); + } else { + size = sizeof(struct kvm_userspace_memory_region2); + } + + /* Ensure the common parts of the two structs are identical. */ + SANITY_CHECK_MEM_REGION_FIELD(slot); + SANITY_CHECK_MEM_REGION_FIELD(flags); + SANITY_CHECK_MEM_REGION_FIELD(guest_phys_addr); + SANITY_CHECK_MEM_REGION_FIELD(memory_size); + SANITY_CHECK_MEM_REGION_FIELD(userspace_addr); r = -EFAULT; - if (copy_from_user(&kvm_userspace_mem, argp, - sizeof kvm_userspace_mem)) + if (copy_from_user(&mem, argp, size)) goto out; - r = kvm_vm_ioctl_set_memory_region(kvm, &kvm_userspace_mem); + r = -EINVAL; + if (ioctl == KVM_SET_USER_MEMORY_REGION && + (mem.flags & ~KVM_SET_USER_MEMORY_REGION_V1_FLAGS)) + goto out; + + r = kvm_vm_ioctl_set_memory_region(kvm, &mem); break; } case KVM_GET_DIRTY_LOG: { struct kvm_dirty_log log; r = -EFAULT; - if (copy_from_user(&log, argp, sizeof log)) + if (copy_from_user(&log, argp, sizeof(log))) goto out; r = kvm_vm_ioctl_get_dirty_log(kvm, &log); break; } -#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET +#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT + case KVM_CLEAR_DIRTY_LOG: { + struct kvm_clear_dirty_log log; + + r = -EFAULT; + if (copy_from_user(&log, argp, sizeof(log))) + goto out; + r = kvm_vm_ioctl_clear_dirty_log(kvm, &log); + break; + } +#endif +#ifdef CONFIG_KVM_MMIO case KVM_REGISTER_COALESCED_MMIO: { struct kvm_coalesced_mmio_zone zone; + r = -EFAULT; - if (copy_from_user(&zone, argp, sizeof zone)) + if (copy_from_user(&zone, argp, sizeof(zone))) goto out; r = kvm_vm_ioctl_register_coalesced_mmio(kvm, &zone); break; } case KVM_UNREGISTER_COALESCED_MMIO: { struct kvm_coalesced_mmio_zone zone; + r = -EFAULT; - if (copy_from_user(&zone, argp, sizeof zone)) + if (copy_from_user(&zone, argp, sizeof(zone))) goto out; r = kvm_vm_ioctl_unregister_coalesced_mmio(kvm, &zone); break; @@ -2369,7 +5252,7 @@ static long kvm_vm_ioctl(struct file *filp, struct kvm_irqfd data; r = -EFAULT; - if (copy_from_user(&data, argp, sizeof data)) + if (copy_from_user(&data, argp, sizeof(data))) goto out; r = kvm_irqfd(kvm, &data); break; @@ -2378,28 +5261,17 @@ static long kvm_vm_ioctl(struct file *filp, struct kvm_ioeventfd data; r = -EFAULT; - if (copy_from_user(&data, argp, sizeof data)) + if (copy_from_user(&data, argp, sizeof(data))) goto out; r = kvm_ioeventfd(kvm, &data); break; } -#ifdef CONFIG_KVM_APIC_ARCHITECTURE - case KVM_SET_BOOT_CPU_ID: - r = 0; - mutex_lock(&kvm->lock); - if (atomic_read(&kvm->online_vcpus) != 0) - r = -EBUSY; - else - kvm->bsp_vcpu_id = arg; - mutex_unlock(&kvm->lock); - break; -#endif #ifdef CONFIG_HAVE_KVM_MSI case KVM_SIGNAL_MSI: { struct kvm_msi msi; r = -EFAULT; - if (copy_from_user(&msi, argp, sizeof msi)) + if (copy_from_user(&msi, argp, sizeof(msi))) goto out; r = kvm_send_userspace_msi(kvm, &msi); break; @@ -2411,7 +5283,7 @@ static long kvm_vm_ioctl(struct file *filp, struct kvm_irq_level irq_event; r = -EFAULT; - if (copy_from_user(&irq_event, argp, sizeof irq_event)) + if (copy_from_user(&irq_event, argp, sizeof(irq_event))) goto out; r = kvm_vm_ioctl_irq_line(kvm, &irq_event, @@ -2421,7 +5293,7 @@ static long kvm_vm_ioctl(struct file *filp, r = -EFAULT; if (ioctl == KVM_IRQ_LINE_STATUS) { - if (copy_to_user(argp, &irq_event, sizeof irq_event)) + if (copy_to_user(argp, &irq_event, sizeof(irq_event))) goto out; } @@ -2433,32 +5305,45 @@ static long kvm_vm_ioctl(struct file *filp, case KVM_SET_GSI_ROUTING: { struct kvm_irq_routing routing; struct kvm_irq_routing __user *urouting; - struct kvm_irq_routing_entry *entries; + struct kvm_irq_routing_entry *entries = NULL; r = -EFAULT; if (copy_from_user(&routing, argp, sizeof(routing))) goto out; r = -EINVAL; - if (routing.nr >= KVM_MAX_IRQ_ROUTES) + if (!kvm_arch_can_set_irq_routing(kvm)) goto out; - if (routing.flags) + if (routing.nr > KVM_MAX_IRQ_ROUTES) goto out; - r = -ENOMEM; - entries = vmalloc(routing.nr * sizeof(*entries)); - if (!entries) + if (routing.flags) goto out; - r = -EFAULT; - urouting = argp; - if (copy_from_user(entries, urouting->entries, - routing.nr * sizeof(*entries))) - goto out_free_irq_routing; + if (routing.nr) { + urouting = argp; + entries = vmemdup_array_user(urouting->entries, + routing.nr, sizeof(*entries)); + if (IS_ERR(entries)) { + r = PTR_ERR(entries); + goto out; + } + } r = kvm_set_irq_routing(kvm, entries, routing.nr, routing.flags); - out_free_irq_routing: - vfree(entries); + kvfree(entries); break; } #endif /* CONFIG_HAVE_KVM_IRQ_ROUTING */ +#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES + case KVM_SET_MEMORY_ATTRIBUTES: { + struct kvm_memory_attributes attrs; + + r = -EFAULT; + if (copy_from_user(&attrs, argp, sizeof(attrs))) + goto out; + + r = kvm_vm_ioctl_set_mem_attributes(kvm, &attrs); + break; + } +#endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */ case KVM_CREATE_DEVICE: { struct kvm_create_device cd; @@ -2477,16 +5362,35 @@ static long kvm_vm_ioctl(struct file *filp, r = 0; break; } + case KVM_CHECK_EXTENSION: + r = kvm_vm_ioctl_check_extension_generic(kvm, arg); + break; + case KVM_RESET_DIRTY_RINGS: + r = kvm_vm_ioctl_reset_dirty_pages(kvm); + break; + case KVM_GET_STATS_FD: + r = kvm_vm_ioctl_get_stats_fd(kvm); + break; +#ifdef CONFIG_KVM_GUEST_MEMFD + case KVM_CREATE_GUEST_MEMFD: { + struct kvm_create_guest_memfd guest_memfd; + + r = -EFAULT; + if (copy_from_user(&guest_memfd, argp, sizeof(guest_memfd))) + goto out; + + r = kvm_gmem_create(kvm, &guest_memfd); + break; + } +#endif default: r = kvm_arch_vm_ioctl(filp, ioctl, arg); - if (r == -ENOTTY) - r = kvm_vm_ioctl_assigned_device(kvm, ioctl, arg); } out: return r; } -#ifdef CONFIG_COMPAT +#ifdef CONFIG_KVM_COMPAT struct compat_kvm_dirty_log { __u32 slot; __u32 padding1; @@ -2496,23 +5400,61 @@ struct compat_kvm_dirty_log { }; }; +struct compat_kvm_clear_dirty_log { + __u32 slot; + __u32 num_pages; + __u64 first_page; + union { + compat_uptr_t dirty_bitmap; /* one bit per page */ + __u64 padding2; + }; +}; + +long __weak kvm_arch_vm_compat_ioctl(struct file *filp, unsigned int ioctl, + unsigned long arg) +{ + return -ENOTTY; +} + static long kvm_vm_compat_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { struct kvm *kvm = filp->private_data; int r; - if (kvm->mm != current->mm) + if (kvm->mm != current->mm || kvm->vm_dead) return -EIO; + + r = kvm_arch_vm_compat_ioctl(filp, ioctl, arg); + if (r != -ENOTTY) + return r; + switch (ioctl) { +#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT + case KVM_CLEAR_DIRTY_LOG: { + struct compat_kvm_clear_dirty_log compat_log; + struct kvm_clear_dirty_log log; + + if (copy_from_user(&compat_log, (void __user *)arg, + sizeof(compat_log))) + return -EFAULT; + log.slot = compat_log.slot; + log.num_pages = compat_log.num_pages; + log.first_page = compat_log.first_page; + log.padding2 = compat_log.padding2; + log.dirty_bitmap = compat_ptr(compat_log.dirty_bitmap); + + r = kvm_vm_ioctl_clear_dirty_log(kvm, &log); + break; + } +#endif case KVM_GET_DIRTY_LOG: { struct compat_kvm_dirty_log compat_log; struct kvm_dirty_log log; - r = -EFAULT; if (copy_from_user(&compat_log, (void __user *)arg, sizeof(compat_log))) - goto out; + return -EFAULT; log.slot = compat_log.slot; log.padding1 = compat_log.padding1; log.padding2 = compat_log.padding2; @@ -2524,110 +5466,73 @@ static long kvm_vm_compat_ioctl(struct file *filp, default: r = kvm_vm_ioctl(filp, ioctl, arg); } - -out: return r; } #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, + KVM_COMPAT(kvm_vm_compat_ioctl), }; +bool file_is_kvm(struct file *file) +{ + return file && file->f_op == &kvm_vm_fops; +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(file_is_kvm); + static int kvm_dev_ioctl_create_vm(unsigned long type) { - int r; + char fdname[ITOA_MAX_LEN + 1]; + int r, fd; struct kvm *kvm; + struct file *file; - kvm = kvm_create_vm(type); - if (IS_ERR(kvm)) - return PTR_ERR(kvm); -#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET - r = kvm_coalesced_mmio_init(kvm); - if (r < 0) { - kvm_put_kvm(kvm); - return r; - } -#endif - r = anon_inode_getfd("kvm-vm", &kvm_vm_fops, kvm, O_RDWR); - if (r < 0) - kvm_put_kvm(kvm); + fd = get_unused_fd_flags(O_CLOEXEC); + if (fd < 0) + return fd; - return r; -} + snprintf(fdname, sizeof(fdname), "%d", fd); -static long kvm_dev_ioctl_check_extension_generic(long arg) -{ - switch (arg) { - case KVM_CAP_USER_MEMORY: - case KVM_CAP_DESTROY_MEMORY_REGION_WORKS: - case KVM_CAP_JOIN_MEMORY_REGIONS_WORKS: -#ifdef CONFIG_KVM_APIC_ARCHITECTURE - case KVM_CAP_SET_BOOT_CPU_ID: -#endif - case KVM_CAP_INTERNAL_ERROR_DATA: -#ifdef CONFIG_HAVE_KVM_MSI - case KVM_CAP_SIGNAL_MSI: -#endif -#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING - case KVM_CAP_IRQFD_RESAMPLE: -#endif - return 1; -#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING - case KVM_CAP_IRQ_ROUTING: - return KVM_MAX_IRQ_ROUTES; -#endif - default: - break; + kvm = kvm_create_vm(type, fdname); + if (IS_ERR(kvm)) { + r = PTR_ERR(kvm); + goto put_fd; + } + + file = anon_inode_getfile("kvm-vm", &kvm_vm_fops, kvm, O_RDWR); + if (IS_ERR(file)) { + r = PTR_ERR(file); + goto put_kvm; } - return kvm_dev_ioctl_check_extension(arg); + + /* + * Don't call kvm_put_kvm anymore at this point; file->f_op is + * already set, with ->release() being kvm_vm_release(). In error + * cases it will be called by the final fput(file) and will take + * care of doing kvm_put_kvm(kvm). + */ + kvm_uevent_notify_change(KVM_EVENT_CREATE_VM, kvm); + + fd_install(fd, file); + return fd; + +put_kvm: + kvm_put_kvm(kvm); +put_fd: + put_unused_fd(fd); + return r; } static long kvm_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { - long r = -EINVAL; + int r = -EINVAL; switch (ioctl) { case KVM_GET_API_VERSION: - r = -EINVAL; if (arg) goto out; r = KVM_API_VERSION; @@ -2636,25 +5541,19 @@ static long kvm_dev_ioctl(struct file *filp, r = kvm_dev_ioctl_create_vm(arg); break; case KVM_CHECK_EXTENSION: - r = kvm_dev_ioctl_check_extension_generic(arg); + r = kvm_vm_ioctl_check_extension_generic(NULL, arg); break; case KVM_GET_VCPU_MMAP_SIZE: - r = -EINVAL; if (arg) goto out; r = PAGE_SIZE; /* struct kvm_run */ #ifdef CONFIG_X86 r += PAGE_SIZE; /* pio data page */ #endif -#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET +#ifdef CONFIG_KVM_MMIO r += PAGE_SIZE; /* coalesced mmio ring page */ #endif break; - case KVM_TRACE_ENABLE: - case KVM_TRACE_PAUSE: - case KVM_TRACE_DISABLE: - r = -EOPNOTSUPP; - break; default: return kvm_arch_dev_ioctl(filp, ioctl, arg); } @@ -2664,8 +5563,8 @@ out: static struct file_operations kvm_chardev_ops = { .unlocked_ioctl = kvm_dev_ioctl, - .compat_ioctl = kvm_dev_ioctl, .llseek = noop_llseek, + KVM_COMPAT(kvm_dev_ioctl), }; static struct miscdevice kvm_dev = { @@ -2674,131 +5573,212 @@ static struct miscdevice kvm_dev = { &kvm_chardev_ops, }; -static void hardware_enable_nolock(void *junk) +#ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING +bool enable_virt_at_load = true; +module_param(enable_virt_at_load, bool, 0444); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(enable_virt_at_load); + +__visible bool kvm_rebooting; +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_rebooting); + +static DEFINE_PER_CPU(bool, virtualization_enabled); +static DEFINE_MUTEX(kvm_usage_lock); +static int kvm_usage_count; + +__weak void kvm_arch_enable_virtualization(void) { - int cpu = raw_smp_processor_id(); - int r; - if (cpumask_test_cpu(cpu, cpus_hardware_enabled)) - return; +} - cpumask_set_cpu(cpu, cpus_hardware_enabled); +__weak void kvm_arch_disable_virtualization(void) +{ - r = kvm_arch_hardware_enable(NULL); +} - if (r) { - cpumask_clear_cpu(cpu, cpus_hardware_enabled); - atomic_inc(&hardware_enable_failed); - printk(KERN_INFO "kvm: enabling virtualization on " - "CPU%d failed\n", cpu); +static int kvm_enable_virtualization_cpu(void) +{ + if (__this_cpu_read(virtualization_enabled)) + return 0; + + if (kvm_arch_enable_virtualization_cpu()) { + pr_info("kvm: enabling virtualization on CPU%d failed\n", + raw_smp_processor_id()); + return -EIO; } + + __this_cpu_write(virtualization_enabled, true); + return 0; } -static void hardware_enable(void *junk) +static int kvm_online_cpu(unsigned int cpu) { - raw_spin_lock(&kvm_lock); - hardware_enable_nolock(junk); - raw_spin_unlock(&kvm_lock); + /* + * Abort the CPU online process if hardware virtualization cannot + * be enabled. Otherwise running VMs would encounter unrecoverable + * errors when scheduled to this CPU. + */ + return kvm_enable_virtualization_cpu(); } -static void hardware_disable_nolock(void *junk) +static void kvm_disable_virtualization_cpu(void *ign) { - int cpu = raw_smp_processor_id(); - - if (!cpumask_test_cpu(cpu, cpus_hardware_enabled)) + if (!__this_cpu_read(virtualization_enabled)) return; - cpumask_clear_cpu(cpu, cpus_hardware_enabled); - kvm_arch_hardware_disable(NULL); + + kvm_arch_disable_virtualization_cpu(); + + __this_cpu_write(virtualization_enabled, false); } -static void hardware_disable(void *junk) +static int kvm_offline_cpu(unsigned int cpu) { - raw_spin_lock(&kvm_lock); - hardware_disable_nolock(junk); - raw_spin_unlock(&kvm_lock); + kvm_disable_virtualization_cpu(NULL); + return 0; } -static void hardware_disable_all_nolock(void) +static void kvm_shutdown(void *data) { - BUG_ON(!kvm_usage_count); + /* + * Disable hardware virtualization and set kvm_rebooting to indicate + * that KVM has asynchronously disabled hardware virtualization, i.e. + * that relevant errors and exceptions aren't entirely unexpected. + * Some flavors of hardware virtualization need to be disabled before + * transferring control to firmware (to perform shutdown/reboot), e.g. + * on x86, virtualization can block INIT interrupts, which are used by + * firmware to pull APs back under firmware control. Note, this path + * is used for both shutdown and reboot scenarios, i.e. neither name is + * 100% comprehensive. + */ + pr_info("kvm: exiting hardware virtualization\n"); + kvm_rebooting = true; + on_each_cpu(kvm_disable_virtualization_cpu, NULL, 1); +} - kvm_usage_count--; - if (!kvm_usage_count) - on_each_cpu(hardware_disable_nolock, NULL, 1); +static int kvm_suspend(void *data) +{ + /* + * Secondary CPUs and CPU hotplug are disabled across the suspend/resume + * callbacks, i.e. no need to acquire kvm_usage_lock to ensure the usage + * count is stable. Assert that kvm_usage_lock is not held to ensure + * the system isn't suspended while KVM is enabling hardware. Hardware + * enabling can be preempted, but the task cannot be frozen until it has + * dropped all locks (userspace tasks are frozen via a fake signal). + */ + lockdep_assert_not_held(&kvm_usage_lock); + lockdep_assert_irqs_disabled(); + + kvm_disable_virtualization_cpu(NULL); + return 0; } -static void hardware_disable_all(void) +static void kvm_resume(void *data) { - raw_spin_lock(&kvm_lock); - hardware_disable_all_nolock(); - raw_spin_unlock(&kvm_lock); + lockdep_assert_not_held(&kvm_usage_lock); + lockdep_assert_irqs_disabled(); + + WARN_ON_ONCE(kvm_enable_virtualization_cpu()); } -static int hardware_enable_all(void) +static const struct syscore_ops kvm_syscore_ops = { + .suspend = kvm_suspend, + .resume = kvm_resume, + .shutdown = kvm_shutdown, +}; + +static struct syscore kvm_syscore = { + .ops = &kvm_syscore_ops, +}; + +int kvm_enable_virtualization(void) { - int r = 0; + int r; - raw_spin_lock(&kvm_lock); + guard(mutex)(&kvm_usage_lock); - kvm_usage_count++; - if (kvm_usage_count == 1) { - atomic_set(&hardware_enable_failed, 0); - on_each_cpu(hardware_enable_nolock, NULL, 1); + if (kvm_usage_count++) + return 0; - if (atomic_read(&hardware_enable_failed)) { - hardware_disable_all_nolock(); - r = -EBUSY; - } + kvm_arch_enable_virtualization(); + + r = cpuhp_setup_state(CPUHP_AP_KVM_ONLINE, "kvm/cpu:online", + kvm_online_cpu, kvm_offline_cpu); + if (r) + goto err_cpuhp; + + register_syscore(&kvm_syscore); + + /* + * Undo virtualization enabling and bail if the system is going down. + * If userspace initiated a forced reboot, e.g. reboot -f, then it's + * possible for an in-flight operation to enable virtualization after + * syscore_shutdown() is called, i.e. without kvm_shutdown() being + * invoked. Note, this relies on system_state being set _before_ + * kvm_shutdown(), e.g. to ensure either kvm_shutdown() is invoked + * or this CPU observes the impending shutdown. Which is why KVM uses + * a syscore ops hook instead of registering a dedicated reboot + * notifier (the latter runs before system_state is updated). + */ + if (system_state == SYSTEM_HALT || system_state == SYSTEM_POWER_OFF || + system_state == SYSTEM_RESTART) { + r = -EBUSY; + goto err_rebooting; } - raw_spin_unlock(&kvm_lock); + return 0; +err_rebooting: + unregister_syscore(&kvm_syscore); + cpuhp_remove_state(CPUHP_AP_KVM_ONLINE); +err_cpuhp: + kvm_arch_disable_virtualization(); + --kvm_usage_count; return r; } +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_enable_virtualization); -static int kvm_cpu_hotplug(struct notifier_block *notifier, unsigned long val, - void *v) +void kvm_disable_virtualization(void) { - int cpu = (long)v; + guard(mutex)(&kvm_usage_lock); - if (!kvm_usage_count) - return NOTIFY_OK; + if (--kvm_usage_count) + return; - val &= ~CPU_TASKS_FROZEN; - switch (val) { - case CPU_DYING: - printk(KERN_INFO "kvm: disabling virtualization on CPU%d\n", - cpu); - hardware_disable(NULL); - break; - case CPU_STARTING: - printk(KERN_INFO "kvm: enabling virtualization on CPU%d\n", - cpu); - hardware_enable(NULL); - break; - } - return NOTIFY_OK; + unregister_syscore(&kvm_syscore); + cpuhp_remove_state(CPUHP_AP_KVM_ONLINE); + kvm_arch_disable_virtualization(); } +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_disable_virtualization); -static int kvm_reboot(struct notifier_block *notifier, unsigned long val, - void *v) +static int kvm_init_virtualization(void) { - /* - * Some (well, at least mine) BIOSes hang on reboot if - * in vmx root mode. - * - * And Intel TXT required VMX off for all cpu when system shutdown. - */ - printk(KERN_INFO "kvm: exiting hardware virtualization\n"); - kvm_rebooting = true; - on_each_cpu(hardware_disable_nolock, NULL, 1); - return NOTIFY_OK; + if (enable_virt_at_load) + return kvm_enable_virtualization(); + + return 0; } -static struct notifier_block kvm_reboot_notifier = { - .notifier_call = kvm_reboot, - .priority = 0, -}; +static void kvm_uninit_virtualization(void) +{ + if (enable_virt_at_load) + kvm_disable_virtualization(); +} +#else /* CONFIG_KVM_GENERIC_HARDWARE_ENABLING */ +static int kvm_init_virtualization(void) +{ + return 0; +} + +static void kvm_uninit_virtualization(void) +{ + +} +#endif /* CONFIG_KVM_GENERIC_HARDWARE_ENABLING */ + +static void kvm_iodevice_destructor(struct kvm_io_device *dev) +{ + if (dev->ops->destructor) + dev->ops->destructor(dev); +} static void kvm_io_bus_destroy(struct kvm_io_bus *bus) { @@ -2812,31 +5792,34 @@ static void kvm_io_bus_destroy(struct kvm_io_bus *bus) kfree(bus); } -static 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; + gpa_t addr1 = r1->addr; + gpa_t addr2 = r2->addr; - if (r1->addr < r2->addr) + if (addr1 < addr2) return -1; - if (r1->addr + r1->len > r2->addr + r2->len) + + /* If r2->len == 0, match the exact address. If r2->len != 0, + * accept any overlapping write. Any order is acceptable for + * overlapping ranges, because kvm_io_bus_get_first_dev ensures + * we process all of them. + */ + if (r2->len) { + addr1 += r1->len; + addr2 += r2->len; + } + + if (addr1 > addr2) return 1; + return 0; } -static int kvm_io_bus_insert_dev(struct kvm_io_bus *bus, struct kvm_io_device *dev, - gpa_t addr, int len) +static int kvm_io_bus_sort_cmp(const void *p1, const void *p2) { - bus->range[bus->dev_count++] = (struct kvm_io_range) { - .addr = addr, - .len = len, - .dev = dev, - }; - - sort(bus->range, bus->dev_count, sizeof(struct kvm_io_range), - kvm_io_bus_sort_cmp, NULL); - - return 0; + return kvm_io_bus_cmp(p1, p2); } static int kvm_io_bus_get_first_dev(struct kvm_io_bus *bus, @@ -2857,17 +5840,67 @@ static 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; } -/* 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) +static int __kvm_io_bus_write(struct kvm_vcpu *vcpu, 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(vcpu, bus->range[idx].dev, range->addr, + range->len, val)) + return idx; + idx++; + } + + return -EOPNOTSUPP; +} + +static struct kvm_io_bus *kvm_get_bus_srcu(struct kvm *kvm, enum kvm_bus idx) +{ + /* + * Ensure that any updates to kvm_buses[] observed by the previous vCPU + * machine instruction are also visible to the vCPU machine instruction + * that triggered this call. + */ + smp_mb__after_srcu_read_lock(); + + return srcu_dereference(kvm->buses[idx], &kvm->srcu); +} + +int kvm_io_bus_write(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, + int len, const void *val) +{ + struct kvm_io_bus *bus; + struct kvm_io_range range; + int r; + + range = (struct kvm_io_range) { + .addr = addr, + .len = len, + }; + + bus = kvm_get_bus_srcu(vcpu->kvm, bus_idx); + if (!bus) + return -ENOMEM; + r = __kvm_io_bus_write(vcpu, bus, &range, val); + return r < 0 ? r : 0; +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_io_bus_write); + +int kvm_io_bus_write_cookie(struct kvm_vcpu *vcpu, 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; @@ -2876,204 +5909,469 @@ int kvm_io_bus_write(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, .len = len, }; - bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu); - idx = kvm_io_bus_get_first_dev(bus, addr, len); + bus = kvm_get_bus_srcu(vcpu->kvm, bus_idx); + if (!bus) + return -ENOMEM; + + /* 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(vcpu, 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(vcpu, bus, &range, val); +} + +static int __kvm_io_bus_read(struct kvm_vcpu *vcpu, 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(vcpu, bus->range[idx].dev, range->addr, + range->len, val)) + return idx; idx++; } return -EOPNOTSUPP; } -/* 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 kvm_io_bus_read(struct kvm_vcpu *vcpu, 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, .len = len, }; - bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu); - idx = kvm_io_bus_get_first_dev(bus, addr, len); - if (idx < 0) - return -EOPNOTSUPP; + bus = kvm_get_bus_srcu(vcpu->kvm, bus_idx); + if (!bus) + return -ENOMEM; + r = __kvm_io_bus_read(vcpu, bus, &range, val); + return r < 0 ? r : 0; +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_io_bus_read); - 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++; - } +static void __free_bus(struct rcu_head *rcu) +{ + struct kvm_io_bus *bus = container_of(rcu, struct kvm_io_bus, rcu); - return -EOPNOTSUPP; + kfree(bus); } -/* 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) { + int i; struct kvm_io_bus *new_bus, *bus; + struct kvm_io_range range; + + lockdep_assert_held(&kvm->slots_lock); + + bus = kvm_get_bus(kvm, bus_idx); + if (!bus) + return -ENOMEM; - bus = kvm->buses[bus_idx]; /* 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) * - sizeof(struct kvm_io_range)), GFP_KERNEL); + new_bus = kmalloc(struct_size(bus, range, bus->dev_count + 1), + GFP_KERNEL_ACCOUNT); if (!new_bus) return -ENOMEM; - memcpy(new_bus, bus, sizeof(*bus) + (bus->dev_count * - sizeof(struct kvm_io_range))); - kvm_io_bus_insert_dev(new_bus, dev, addr, len); + + range = (struct kvm_io_range) { + .addr = addr, + .len = len, + .dev = dev, + }; + + for (i = 0; i < bus->dev_count; i++) + if (kvm_io_bus_cmp(&bus->range[i], &range) > 0) + break; + + memcpy(new_bus, bus, sizeof(*bus) + i * sizeof(struct kvm_io_range)); + new_bus->dev_count++; + new_bus->range[i] = range; + memcpy(new_bus->range + i + 1, bus->range + i, + (bus->dev_count - i) * sizeof(struct kvm_io_range)); rcu_assign_pointer(kvm->buses[bus_idx], new_bus); - synchronize_srcu_expedited(&kvm->srcu); - kfree(bus); + call_srcu(&kvm->srcu, &bus->rcu, __free_bus); return 0; } -/* Caller must hold slots_lock. */ int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx, struct kvm_io_device *dev) { - int i, r; + int i; struct kvm_io_bus *new_bus, *bus; - bus = kvm->buses[bus_idx]; - r = -ENOENT; - for (i = 0; i < bus->dev_count; i++) + lockdep_assert_held(&kvm->slots_lock); + + bus = kvm_get_bus(kvm, bus_idx); + if (!bus) + return 0; + + for (i = 0; i < bus->dev_count; i++) { if (bus->range[i].dev == dev) { - r = 0; break; } + } - if (r) - return r; - - new_bus = kzalloc(sizeof(*bus) + ((bus->dev_count - 1) * - sizeof(struct kvm_io_range)), GFP_KERNEL); - if (!new_bus) - return -ENOMEM; + if (i == bus->dev_count) + return 0; - memcpy(new_bus, bus, sizeof(*bus) + i * sizeof(struct kvm_io_range)); - new_bus->dev_count--; - memcpy(new_bus->range + i, bus->range + i + 1, - (new_bus->dev_count - i) * sizeof(struct kvm_io_range)); + new_bus = kmalloc(struct_size(bus, range, bus->dev_count - 1), + GFP_KERNEL_ACCOUNT); + if (new_bus) { + memcpy(new_bus, bus, struct_size(bus, range, i)); + new_bus->dev_count--; + memcpy(new_bus->range + i, bus->range + i + 1, + flex_array_size(new_bus, range, new_bus->dev_count - i)); + } rcu_assign_pointer(kvm->buses[bus_idx], new_bus); synchronize_srcu_expedited(&kvm->srcu); + + /* + * If NULL bus is installed, destroy the old bus, including all the + * attached devices. Otherwise, destroy the caller's device only. + */ + if (!new_bus) { + pr_err("kvm: failed to shrink bus, removing it completely\n"); + kvm_io_bus_destroy(bus); + return -ENOMEM; + } + + kvm_iodevice_destructor(dev); kfree(bus); - return r; + return 0; } -static struct notifier_block kvm_cpu_notifier = { - .notifier_call = kvm_cpu_hotplug, -}; +struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx, + gpa_t addr) +{ + struct kvm_io_bus *bus; + int dev_idx, srcu_idx; + struct kvm_io_device *iodev = NULL; -static int vm_stat_get(void *_offset, u64 *val) + srcu_idx = srcu_read_lock(&kvm->srcu); + + bus = kvm_get_bus_srcu(kvm, bus_idx); + if (!bus) + goto out_unlock; + + dev_idx = kvm_io_bus_get_first_dev(bus, addr, 1); + if (dev_idx < 0) + goto out_unlock; + + iodev = bus->range[dev_idx].dev; + +out_unlock: + srcu_read_unlock(&kvm->srcu, srcu_idx); + + return iodev; +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_io_bus_get_dev); + +static int kvm_debugfs_open(struct inode *inode, struct file *file, + int (*get)(void *, u64 *), int (*set)(void *, u64), + const char *fmt) { - unsigned offset = (long)_offset; - struct kvm *kvm; + int ret; + struct kvm_stat_data *stat_data = inode->i_private; + + /* + * The debugfs files are a reference to the kvm struct which + * is still valid when kvm_destroy_vm is called. kvm_get_kvm_safe + * avoids the race between open and the removal of the debugfs directory. + */ + if (!kvm_get_kvm_safe(stat_data->kvm)) + return -ENOENT; + + ret = simple_attr_open(inode, file, get, + kvm_stats_debugfs_mode(stat_data->desc) & 0222 + ? set : NULL, fmt); + if (ret) + kvm_put_kvm(stat_data->kvm); + + return ret; +} + +static int kvm_debugfs_release(struct inode *inode, struct file *file) +{ + struct kvm_stat_data *stat_data = inode->i_private; + + simple_attr_release(inode, file); + kvm_put_kvm(stat_data->kvm); - *val = 0; - raw_spin_lock(&kvm_lock); - list_for_each_entry(kvm, &vm_list, vm_list) - *val += *(u32 *)((void *)kvm + offset); - raw_spin_unlock(&kvm_lock); return 0; } -DEFINE_SIMPLE_ATTRIBUTE(vm_stat_fops, vm_stat_get, NULL, "%llu\n"); +static int kvm_get_stat_per_vm(struct kvm *kvm, size_t offset, u64 *val) +{ + *val = *(u64 *)((void *)(&kvm->stat) + offset); -static int vcpu_stat_get(void *_offset, u64 *val) + return 0; +} + +static int kvm_clear_stat_per_vm(struct kvm *kvm, size_t offset) { - unsigned offset = (long)_offset; - struct kvm *kvm; + *(u64 *)((void *)(&kvm->stat) + offset) = 0; + + return 0; +} + +static int kvm_get_stat_per_vcpu(struct kvm *kvm, size_t offset, u64 *val) +{ + unsigned long i; struct kvm_vcpu *vcpu; - int i; *val = 0; - raw_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); + kvm_for_each_vcpu(i, vcpu, kvm) + *val += *(u64 *)((void *)(&vcpu->stat) + offset); + return 0; } -DEFINE_SIMPLE_ATTRIBUTE(vcpu_stat_fops, vcpu_stat_get, NULL, "%llu\n"); +static int kvm_clear_stat_per_vcpu(struct kvm *kvm, size_t offset) +{ + unsigned long i; + struct kvm_vcpu *vcpu; + + kvm_for_each_vcpu(i, vcpu, kvm) + *(u64 *)((void *)(&vcpu->stat) + offset) = 0; -static const struct file_operations *stat_fops[] = { - [KVM_STAT_VCPU] = &vcpu_stat_fops, - [KVM_STAT_VM] = &vm_stat_fops, -}; + return 0; +} -static int kvm_init_debug(void) +static int kvm_stat_data_get(void *data, u64 *val) { int r = -EFAULT; - struct kvm_stats_debugfs_item *p; + struct kvm_stat_data *stat_data = data; - kvm_debugfs_dir = debugfs_create_dir("kvm", NULL); - if (kvm_debugfs_dir == NULL) - goto out; + switch (stat_data->kind) { + case KVM_STAT_VM: + r = kvm_get_stat_per_vm(stat_data->kvm, + stat_data->desc->desc.offset, val); + break; + case KVM_STAT_VCPU: + r = kvm_get_stat_per_vcpu(stat_data->kvm, + stat_data->desc->desc.offset, val); + break; + } - for (p = debugfs_entries; p->name; ++p) { - p->dentry = debugfs_create_file(p->name, 0444, kvm_debugfs_dir, - (void *)(long)p->offset, - stat_fops[p->kind]); - if (p->dentry == NULL) - goto out_dir; + return r; +} + +static int kvm_stat_data_clear(void *data, u64 val) +{ + int r = -EFAULT; + struct kvm_stat_data *stat_data = data; + + if (val) + return -EINVAL; + + switch (stat_data->kind) { + case KVM_STAT_VM: + r = kvm_clear_stat_per_vm(stat_data->kvm, + stat_data->desc->desc.offset); + break; + case KVM_STAT_VCPU: + r = kvm_clear_stat_per_vcpu(stat_data->kvm, + stat_data->desc->desc.offset); + break; } + return r; +} + +static int kvm_stat_data_open(struct inode *inode, struct file *file) +{ + __simple_attr_check_format("%llu\n", 0ull); + return kvm_debugfs_open(inode, file, kvm_stat_data_get, + kvm_stat_data_clear, "%llu\n"); +} + +static const struct file_operations stat_fops_per_vm = { + .owner = THIS_MODULE, + .open = kvm_stat_data_open, + .release = kvm_debugfs_release, + .read = simple_attr_read, + .write = simple_attr_write, +}; + +static int vm_stat_get(void *_offset, u64 *val) +{ + unsigned offset = (long)_offset; + struct kvm *kvm; + u64 tmp_val; + + *val = 0; + mutex_lock(&kvm_lock); + list_for_each_entry(kvm, &vm_list, vm_list) { + kvm_get_stat_per_vm(kvm, offset, &tmp_val); + *val += tmp_val; + } + mutex_unlock(&kvm_lock); return 0; +} -out_dir: - debugfs_remove_recursive(kvm_debugfs_dir); -out: - return r; +static int vm_stat_clear(void *_offset, u64 val) +{ + unsigned offset = (long)_offset; + struct kvm *kvm; + + if (val) + return -EINVAL; + + mutex_lock(&kvm_lock); + list_for_each_entry(kvm, &vm_list, vm_list) { + kvm_clear_stat_per_vm(kvm, offset); + } + mutex_unlock(&kvm_lock); + + return 0; } -static void kvm_exit_debug(void) +DEFINE_SIMPLE_ATTRIBUTE(vm_stat_fops, vm_stat_get, vm_stat_clear, "%llu\n"); +DEFINE_SIMPLE_ATTRIBUTE(vm_stat_readonly_fops, vm_stat_get, NULL, "%llu\n"); + +static int vcpu_stat_get(void *_offset, u64 *val) { - struct kvm_stats_debugfs_item *p; + unsigned offset = (long)_offset; + struct kvm *kvm; + u64 tmp_val; - for (p = debugfs_entries; p->name; ++p) - debugfs_remove(p->dentry); - debugfs_remove(kvm_debugfs_dir); + *val = 0; + mutex_lock(&kvm_lock); + list_for_each_entry(kvm, &vm_list, vm_list) { + kvm_get_stat_per_vcpu(kvm, offset, &tmp_val); + *val += tmp_val; + } + mutex_unlock(&kvm_lock); + return 0; } -static int kvm_suspend(void) +static int vcpu_stat_clear(void *_offset, u64 val) { - if (kvm_usage_count) - hardware_disable_nolock(NULL); + unsigned offset = (long)_offset; + struct kvm *kvm; + + if (val) + return -EINVAL; + + mutex_lock(&kvm_lock); + list_for_each_entry(kvm, &vm_list, vm_list) { + kvm_clear_stat_per_vcpu(kvm, offset); + } + mutex_unlock(&kvm_lock); + return 0; } -static void kvm_resume(void) +DEFINE_SIMPLE_ATTRIBUTE(vcpu_stat_fops, vcpu_stat_get, vcpu_stat_clear, + "%llu\n"); +DEFINE_SIMPLE_ATTRIBUTE(vcpu_stat_readonly_fops, vcpu_stat_get, NULL, "%llu\n"); + +static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm) { - if (kvm_usage_count) { - WARN_ON(raw_spin_is_locked(&kvm_lock)); - hardware_enable_nolock(NULL); + struct kobj_uevent_env *env; + unsigned long long created, active; + + if (!kvm_dev.this_device || !kvm) + return; + + mutex_lock(&kvm_lock); + if (type == KVM_EVENT_CREATE_VM) { + kvm_createvm_count++; + kvm_active_vms++; + } else if (type == KVM_EVENT_DESTROY_VM) { + kvm_active_vms--; + } + created = kvm_createvm_count; + active = kvm_active_vms; + mutex_unlock(&kvm_lock); + + env = kzalloc(sizeof(*env), GFP_KERNEL); + if (!env) + return; + + add_uevent_var(env, "CREATED=%llu", created); + add_uevent_var(env, "COUNT=%llu", active); + + if (type == KVM_EVENT_CREATE_VM) { + add_uevent_var(env, "EVENT=create"); + kvm->userspace_pid = task_pid_nr(current); + } else if (type == KVM_EVENT_DESTROY_VM) { + add_uevent_var(env, "EVENT=destroy"); + } + add_uevent_var(env, "PID=%d", kvm->userspace_pid); + + if (!IS_ERR(kvm->debugfs_dentry)) { + char *tmp, *p = kmalloc(PATH_MAX, GFP_KERNEL); + + if (p) { + tmp = dentry_path_raw(kvm->debugfs_dentry, p, PATH_MAX); + if (!IS_ERR(tmp)) + add_uevent_var(env, "STATS_PATH=%s", tmp); + kfree(p); + } } + /* no need for checks, since we are adding at most only 5 keys */ + env->envp[env->envp_idx++] = NULL; + kobject_uevent_env(&kvm_dev.this_device->kobj, KOBJ_CHANGE, env->envp); + kfree(env); } -static struct syscore_ops kvm_syscore_ops = { - .suspend = kvm_suspend, - .resume = kvm_resume, -}; +static void kvm_init_debug(void) +{ + const struct file_operations *fops; + const struct _kvm_stats_desc *pdesc; + int i; + + kvm_debugfs_dir = debugfs_create_dir("kvm", NULL); + + for (i = 0; i < kvm_vm_stats_header.num_desc; ++i) { + pdesc = &kvm_vm_stats_desc[i]; + if (kvm_stats_debugfs_mode(pdesc) & 0222) + fops = &vm_stat_fops; + else + fops = &vm_stat_readonly_fops; + debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc), + kvm_debugfs_dir, + (void *)(long)pdesc->desc.offset, fops); + } + + for (i = 0; i < kvm_vcpu_stats_header.num_desc; ++i) { + pdesc = &kvm_vcpu_stats_desc[i]; + if (kvm_stats_debugfs_mode(pdesc) & 0222) + fops = &vcpu_stat_fops; + else + fops = &vcpu_stat_readonly_fops; + debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc), + kvm_debugfs_dir, + (void *)(long)pdesc->desc.offset, fops); + } +} static inline struct kvm_vcpu *preempt_notifier_to_vcpu(struct preempt_notifier *pn) @@ -3084,10 +6382,14 @@ 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; + WRITE_ONCE(vcpu->preempted, false); + WRITE_ONCE(vcpu->ready, false); + + __this_cpu_write(kvm_running_vcpu, vcpu); kvm_arch_vcpu_load(vcpu, cpu); + + WRITE_ONCE(vcpu->scheduled_out, false); } static void kvm_sched_out(struct preempt_notifier *pn, @@ -3095,128 +6397,196 @@ 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; + WRITE_ONCE(vcpu->scheduled_out, true); + + if (task_is_runnable(current) && vcpu->wants_to_run) { + WRITE_ONCE(vcpu->preempted, true); + WRITE_ONCE(vcpu->ready, true); + } kvm_arch_vcpu_put(vcpu); + __this_cpu_write(kvm_running_vcpu, NULL); } -int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align, - struct module *module) +/** + * kvm_get_running_vcpu - get the vcpu running on the current CPU. + * + * We can disable preemption locally around accessing the per-CPU variable, + * and use the resolved vcpu pointer after enabling preemption again, + * because even if the current thread is migrated to another CPU, reading + * the per-CPU value later will give us the same value as we update the + * per-CPU variable in the preempt notifier handlers. + */ +struct kvm_vcpu *kvm_get_running_vcpu(void) { - int r; - int cpu; + struct kvm_vcpu *vcpu; - r = kvm_arch_init(opaque); - if (r) - goto out_fail; + preempt_disable(); + vcpu = __this_cpu_read(kvm_running_vcpu); + preempt_enable(); - /* - * 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; + return vcpu; +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_get_running_vcpu); - if (!zalloc_cpumask_var(&cpus_hardware_enabled, GFP_KERNEL)) { - r = -ENOMEM; - goto out_free_0; - } +/** + * kvm_get_running_vcpus - get the per-CPU array of currently running vcpus. + */ +struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void) +{ + return &kvm_running_vcpu; +} - r = kvm_arch_hardware_setup(); - if (r < 0) - goto out_free_0a; +#ifdef CONFIG_GUEST_PERF_EVENTS +static unsigned int kvm_guest_state(void) +{ + struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); + unsigned int state; - for_each_online_cpu(cpu) { - smp_call_function_single(cpu, - kvm_arch_check_processor_compat, - &r, 1); - if (r < 0) - goto out_free_1; - } + if (!kvm_arch_pmi_in_guest(vcpu)) + return 0; - r = register_cpu_notifier(&kvm_cpu_notifier); - if (r) - goto out_free_2; - register_reboot_notifier(&kvm_reboot_notifier); + state = PERF_GUEST_ACTIVE; + if (!kvm_arch_vcpu_in_kernel(vcpu)) + state |= PERF_GUEST_USER; + + return state; +} + +static unsigned long kvm_guest_get_ip(void) +{ + struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); + + /* Retrieving the IP must be guarded by a call to kvm_guest_state(). */ + if (WARN_ON_ONCE(!kvm_arch_pmi_in_guest(vcpu))) + return 0; + + return kvm_arch_vcpu_get_ip(vcpu); +} + +static struct perf_guest_info_callbacks kvm_guest_cbs = { + .state = kvm_guest_state, + .get_ip = kvm_guest_get_ip, + .handle_intel_pt_intr = NULL, +}; + +void kvm_register_perf_callbacks(unsigned int (*pt_intr_handler)(void)) +{ + kvm_guest_cbs.handle_intel_pt_intr = pt_intr_handler; + perf_register_guest_info_callbacks(&kvm_guest_cbs); +} +void kvm_unregister_perf_callbacks(void) +{ + perf_unregister_guest_info_callbacks(&kvm_guest_cbs); +} +#endif + +int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module) +{ + int r; + int cpu; /* A kmem cache lets us meet the alignment requirements of fx_save. */ if (!vcpu_align) vcpu_align = __alignof__(struct kvm_vcpu); - kvm_vcpu_cache = kmem_cache_create("kvm_vcpu", vcpu_size, vcpu_align, - 0, NULL); - if (!kvm_vcpu_cache) { - r = -ENOMEM; - goto out_free_3; + kvm_vcpu_cache = + kmem_cache_create_usercopy("kvm_vcpu", vcpu_size, vcpu_align, + SLAB_ACCOUNT, + offsetof(struct kvm_vcpu, arch), + offsetofend(struct kvm_vcpu, stats_id) + - offsetof(struct kvm_vcpu, arch), + NULL); + if (!kvm_vcpu_cache) + return -ENOMEM; + + for_each_possible_cpu(cpu) { + if (!alloc_cpumask_var_node(&per_cpu(cpu_kick_mask, cpu), + GFP_KERNEL, cpu_to_node(cpu))) { + r = -ENOMEM; + goto err_cpu_kick_mask; + } } + r = kvm_irqfd_init(); + if (r) + goto err_irqfd; + r = kvm_async_pf_init(); if (r) - goto out_free; + goto err_async_pf; kvm_chardev_ops.owner = module; kvm_vm_fops.owner = module; kvm_vcpu_fops.owner = module; - - r = misc_register(&kvm_dev); - if (r) { - printk(KERN_ERR "kvm: misc device register failed\n"); - goto out_unreg; - } - - register_syscore_ops(&kvm_syscore_ops); + kvm_device_fops.owner = module; kvm_preempt_ops.sched_in = kvm_sched_in; kvm_preempt_ops.sched_out = kvm_sched_out; - r = kvm_init_debug(); + kvm_init_debug(); + + r = kvm_vfio_ops_init(); + if (WARN_ON_ONCE(r)) + goto err_vfio; + + r = kvm_gmem_init(module); + if (r) + goto err_gmem; + + r = kvm_init_virtualization(); + if (r) + goto err_virt; + + /* + * Registration _must_ be the very last thing done, as this exposes + * /dev/kvm to userspace, i.e. all infrastructure must be setup! + */ + r = misc_register(&kvm_dev); if (r) { - printk(KERN_ERR "kvm: create debugfs files failed\n"); - goto out_undebugfs; + pr_err("kvm: misc device register failed\n"); + goto err_register; } return 0; -out_undebugfs: - unregister_syscore_ops(&kvm_syscore_ops); - misc_deregister(&kvm_dev); -out_unreg: +err_register: + kvm_uninit_virtualization(); +err_virt: + kvm_gmem_exit(); +err_gmem: + kvm_vfio_ops_exit(); +err_vfio: kvm_async_pf_deinit(); -out_free: - kmem_cache_destroy(kvm_vcpu_cache); -out_free_3: - unregister_reboot_notifier(&kvm_reboot_notifier); - unregister_cpu_notifier(&kvm_cpu_notifier); -out_free_2: -out_free_1: - kvm_arch_hardware_unsetup(); -out_free_0a: - free_cpumask_var(cpus_hardware_enabled); -out_free_0: +err_async_pf: kvm_irqfd_exit(); -out_irqfd: - kvm_arch_exit(); -out_fail: +err_irqfd: +err_cpu_kick_mask: + for_each_possible_cpu(cpu) + free_cpumask_var(per_cpu(cpu_kick_mask, cpu)); + kmem_cache_destroy(kvm_vcpu_cache); return r; } -EXPORT_SYMBOL_GPL(kvm_init); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_init); void kvm_exit(void) { - kvm_exit_debug(); + int cpu; + + /* + * Note, unregistering /dev/kvm doesn't strictly need to come first, + * fops_get(), a.k.a. try_module_get(), prevents acquiring references + * to KVM while the module is being stopped. + */ misc_deregister(&kvm_dev); + + kvm_uninit_virtualization(); + + debugfs_remove_recursive(kvm_debugfs_dir); + for_each_possible_cpu(cpu) + free_cpumask_var(per_cpu(cpu_kick_mask, cpu)); kmem_cache_destroy(kvm_vcpu_cache); + kvm_gmem_exit(); + kvm_vfio_ops_exit(); kvm_async_pf_deinit(); - unregister_syscore_ops(&kvm_syscore_ops); - unregister_reboot_notifier(&kvm_reboot_notifier); - unregister_cpu_notifier(&kvm_cpu_notifier); - 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); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_exit); diff --git a/virt/kvm/kvm_mm.h b/virt/kvm/kvm_mm.h new file mode 100644 index 000000000000..9fcc5d5b7f8d --- /dev/null +++ b/virt/kvm/kvm_mm.h @@ -0,0 +1,97 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __KVM_MM_H__ +#define __KVM_MM_H__ 1 + +/* + * Architectures can choose whether to use an rwlock or spinlock + * for the mmu_lock. These macros, for use in common code + * only, avoids using #ifdefs in places that must deal with + * multiple architectures. + */ + +#ifdef KVM_HAVE_MMU_RWLOCK +#define KVM_MMU_LOCK_INIT(kvm) rwlock_init(&(kvm)->mmu_lock) +#define KVM_MMU_LOCK(kvm) write_lock(&(kvm)->mmu_lock) +#define KVM_MMU_UNLOCK(kvm) write_unlock(&(kvm)->mmu_lock) +#else +#define KVM_MMU_LOCK_INIT(kvm) spin_lock_init(&(kvm)->mmu_lock) +#define KVM_MMU_LOCK(kvm) spin_lock(&(kvm)->mmu_lock) +#define KVM_MMU_UNLOCK(kvm) spin_unlock(&(kvm)->mmu_lock) +#endif /* KVM_HAVE_MMU_RWLOCK */ + + +struct kvm_follow_pfn { + const struct kvm_memory_slot *slot; + const gfn_t gfn; + + unsigned long hva; + + /* FOLL_* flags modifying lookup behavior, e.g. FOLL_WRITE. */ + unsigned int flags; + + /* + * Pin the page (effectively FOLL_PIN, which is an mm/ internal flag). + * The page *must* be pinned if KVM will write to the page via a kernel + * mapping, e.g. via kmap(), mremap(), etc. + */ + bool pin; + + /* + * If non-NULL, try to get a writable mapping even for a read fault. + * Set to true if a writable mapping was obtained. + */ + bool *map_writable; + + /* + * Optional output. Set to a valid "struct page" if the returned pfn + * is for a refcounted or pinned struct page, NULL if the returned pfn + * has no struct page or if the struct page is not being refcounted + * (e.g. tail pages of non-compound higher order allocations from + * IO/PFNMAP mappings). + */ + struct page **refcounted_page; +}; + +kvm_pfn_t hva_to_pfn(struct kvm_follow_pfn *kfp); + +#ifdef CONFIG_HAVE_KVM_PFNCACHE +void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm, + unsigned long start, + unsigned long end); +#else +static inline void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm, + unsigned long start, + unsigned long end) +{ +} +#endif /* HAVE_KVM_PFNCACHE */ + +#ifdef CONFIG_KVM_GUEST_MEMFD +int kvm_gmem_init(struct module *module); +void kvm_gmem_exit(void); +int kvm_gmem_create(struct kvm *kvm, struct kvm_create_guest_memfd *args); +int kvm_gmem_bind(struct kvm *kvm, struct kvm_memory_slot *slot, + unsigned int fd, loff_t offset); +void kvm_gmem_unbind(struct kvm_memory_slot *slot); +#else +static inline int kvm_gmem_init(struct module *module) +{ + return 0; +} +static inline void kvm_gmem_exit(void) {}; +static inline int kvm_gmem_bind(struct kvm *kvm, + struct kvm_memory_slot *slot, + unsigned int fd, loff_t offset) +{ + WARN_ON_ONCE(1); + return -EIO; +} + +static inline void kvm_gmem_unbind(struct kvm_memory_slot *slot) +{ + WARN_ON_ONCE(1); +} +#endif /* CONFIG_KVM_GUEST_MEMFD */ + +#endif /* __KVM_MM_H__ */ diff --git a/virt/kvm/pfncache.c b/virt/kvm/pfncache.c new file mode 100644 index 000000000000..728d2c1b488a --- /dev/null +++ b/virt/kvm/pfncache.c @@ -0,0 +1,484 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Kernel-based Virtual Machine driver for Linux + * + * This module enables kernel and guest-mode vCPU access to guest physical + * memory with suitable invalidation mechanisms. + * + * Copyright © 2021 Amazon.com, Inc. or its affiliates. + * + * Authors: + * David Woodhouse <dwmw2@infradead.org> + */ + +#include <linux/kvm_host.h> +#include <linux/kvm.h> +#include <linux/highmem.h> +#include <linux/module.h> +#include <linux/errno.h> + +#include "kvm_mm.h" + +/* + * MMU notifier 'invalidate_range_start' hook. + */ +void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm, unsigned long start, + unsigned long end) +{ + struct gfn_to_pfn_cache *gpc; + + spin_lock(&kvm->gpc_lock); + list_for_each_entry(gpc, &kvm->gpc_list, list) { + read_lock_irq(&gpc->lock); + + /* Only a single page so no need to care about length */ + if (gpc->valid && !is_error_noslot_pfn(gpc->pfn) && + gpc->uhva >= start && gpc->uhva < end) { + read_unlock_irq(&gpc->lock); + + /* + * There is a small window here where the cache could + * be modified, and invalidation would no longer be + * necessary. Hence check again whether invalidation + * is still necessary once the write lock has been + * acquired. + */ + + write_lock_irq(&gpc->lock); + if (gpc->valid && !is_error_noslot_pfn(gpc->pfn) && + gpc->uhva >= start && gpc->uhva < end) + gpc->valid = false; + write_unlock_irq(&gpc->lock); + continue; + } + + read_unlock_irq(&gpc->lock); + } + spin_unlock(&kvm->gpc_lock); +} + +static bool kvm_gpc_is_valid_len(gpa_t gpa, unsigned long uhva, + unsigned long len) +{ + unsigned long offset = kvm_is_error_gpa(gpa) ? offset_in_page(uhva) : + offset_in_page(gpa); + + /* + * The cached access must fit within a single page. The 'len' argument + * to activate() and refresh() exists only to enforce that. + */ + return offset + len <= PAGE_SIZE; +} + +bool kvm_gpc_check(struct gfn_to_pfn_cache *gpc, unsigned long len) +{ + struct kvm_memslots *slots = kvm_memslots(gpc->kvm); + + if (!gpc->active) + return false; + + /* + * If the page was cached from a memslot, make sure the memslots have + * not been re-configured. + */ + if (!kvm_is_error_gpa(gpc->gpa) && gpc->generation != slots->generation) + return false; + + if (kvm_is_error_hva(gpc->uhva)) + return false; + + if (!kvm_gpc_is_valid_len(gpc->gpa, gpc->uhva, len)) + return false; + + if (!gpc->valid) + return false; + + return true; +} + +static void *gpc_map(kvm_pfn_t pfn) +{ + if (pfn_valid(pfn)) + return kmap(pfn_to_page(pfn)); + +#ifdef CONFIG_HAS_IOMEM + return memremap(pfn_to_hpa(pfn), PAGE_SIZE, MEMREMAP_WB); +#else + return NULL; +#endif +} + +static void gpc_unmap(kvm_pfn_t pfn, void *khva) +{ + /* Unmap the old pfn/page if it was mapped before. */ + if (is_error_noslot_pfn(pfn) || !khva) + return; + + if (pfn_valid(pfn)) { + kunmap(pfn_to_page(pfn)); + return; + } + +#ifdef CONFIG_HAS_IOMEM + memunmap(khva); +#endif +} + +static inline bool mmu_notifier_retry_cache(struct kvm *kvm, unsigned long mmu_seq) +{ + /* + * mn_active_invalidate_count acts for all intents and purposes + * like mmu_invalidate_in_progress here; but the latter cannot + * be used here because the invalidation of caches in the + * mmu_notifier event occurs _before_ mmu_invalidate_in_progress + * is elevated. + * + * Note, it does not matter that mn_active_invalidate_count + * is not protected by gpc->lock. It is guaranteed to + * be elevated before the mmu_notifier acquires gpc->lock, and + * isn't dropped until after mmu_invalidate_seq is updated. + */ + if (kvm->mn_active_invalidate_count) + return true; + + /* + * Ensure mn_active_invalidate_count is read before + * mmu_invalidate_seq. This pairs with the smp_wmb() in + * mmu_notifier_invalidate_range_end() to guarantee either the + * old (non-zero) value of mn_active_invalidate_count or the + * new (incremented) value of mmu_invalidate_seq is observed. + */ + smp_rmb(); + return kvm->mmu_invalidate_seq != mmu_seq; +} + +static kvm_pfn_t hva_to_pfn_retry(struct gfn_to_pfn_cache *gpc) +{ + /* Note, the new page offset may be different than the old! */ + void *old_khva = (void *)PAGE_ALIGN_DOWN((uintptr_t)gpc->khva); + kvm_pfn_t new_pfn = KVM_PFN_ERR_FAULT; + void *new_khva = NULL; + unsigned long mmu_seq; + struct page *page; + + struct kvm_follow_pfn kfp = { + .slot = gpc->memslot, + .gfn = gpa_to_gfn(gpc->gpa), + .flags = FOLL_WRITE, + .hva = gpc->uhva, + .refcounted_page = &page, + }; + + lockdep_assert_held(&gpc->refresh_lock); + + lockdep_assert_held_write(&gpc->lock); + + /* + * Invalidate the cache prior to dropping gpc->lock, the gpa=>uhva + * assets have already been updated and so a concurrent check() from a + * different task may not fail the gpa/uhva/generation checks. + */ + gpc->valid = false; + + do { + mmu_seq = gpc->kvm->mmu_invalidate_seq; + smp_rmb(); + + write_unlock_irq(&gpc->lock); + + /* + * If the previous iteration "failed" due to an mmu_notifier + * event, release the pfn and unmap the kernel virtual address + * from the previous attempt. Unmapping might sleep, so this + * needs to be done after dropping the lock. Opportunistically + * check for resched while the lock isn't held. + */ + if (new_pfn != KVM_PFN_ERR_FAULT) { + /* + * Keep the mapping if the previous iteration reused + * the existing mapping and didn't create a new one. + */ + if (new_khva != old_khva) + gpc_unmap(new_pfn, new_khva); + + kvm_release_page_unused(page); + + cond_resched(); + } + + new_pfn = hva_to_pfn(&kfp); + if (is_error_noslot_pfn(new_pfn)) + goto out_error; + + /* + * Obtain a new kernel mapping if KVM itself will access the + * pfn. Note, kmap() and memremap() can both sleep, so this + * too must be done outside of gpc->lock! + */ + if (new_pfn == gpc->pfn) + new_khva = old_khva; + else + new_khva = gpc_map(new_pfn); + + if (!new_khva) { + kvm_release_page_unused(page); + goto out_error; + } + + write_lock_irq(&gpc->lock); + + /* + * Other tasks must wait for _this_ refresh to complete before + * attempting to refresh. + */ + WARN_ON_ONCE(gpc->valid); + } while (mmu_notifier_retry_cache(gpc->kvm, mmu_seq)); + + gpc->valid = true; + gpc->pfn = new_pfn; + gpc->khva = new_khva + offset_in_page(gpc->uhva); + + /* + * Put the reference to the _new_ page. The page is now tracked by the + * cache and can be safely migrated, swapped, etc... as the cache will + * invalidate any mappings in response to relevant mmu_notifier events. + */ + kvm_release_page_clean(page); + + return 0; + +out_error: + write_lock_irq(&gpc->lock); + + return -EFAULT; +} + +static int __kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned long uhva) +{ + unsigned long page_offset; + bool unmap_old = false; + unsigned long old_uhva; + kvm_pfn_t old_pfn; + bool hva_change = false; + void *old_khva; + int ret; + + /* Either gpa or uhva must be valid, but not both */ + if (WARN_ON_ONCE(kvm_is_error_gpa(gpa) == kvm_is_error_hva(uhva))) + return -EINVAL; + + lockdep_assert_held(&gpc->refresh_lock); + + write_lock_irq(&gpc->lock); + + if (!gpc->active) { + ret = -EINVAL; + goto out_unlock; + } + + old_pfn = gpc->pfn; + old_khva = (void *)PAGE_ALIGN_DOWN((uintptr_t)gpc->khva); + old_uhva = PAGE_ALIGN_DOWN(gpc->uhva); + + if (kvm_is_error_gpa(gpa)) { + page_offset = offset_in_page(uhva); + + gpc->gpa = INVALID_GPA; + gpc->memslot = NULL; + gpc->uhva = PAGE_ALIGN_DOWN(uhva); + + if (gpc->uhva != old_uhva) + hva_change = true; + } else { + struct kvm_memslots *slots = kvm_memslots(gpc->kvm); + + page_offset = offset_in_page(gpa); + + if (gpc->gpa != gpa || gpc->generation != slots->generation || + kvm_is_error_hva(gpc->uhva)) { + gfn_t gfn = gpa_to_gfn(gpa); + + gpc->gpa = gpa; + gpc->generation = slots->generation; + gpc->memslot = __gfn_to_memslot(slots, gfn); + gpc->uhva = gfn_to_hva_memslot(gpc->memslot, gfn); + + if (kvm_is_error_hva(gpc->uhva)) { + ret = -EFAULT; + goto out; + } + + /* + * Even if the GPA and/or the memslot generation changed, the + * HVA may still be the same. + */ + if (gpc->uhva != old_uhva) + hva_change = true; + } else { + gpc->uhva = old_uhva; + } + } + + /* Note: the offset must be correct before calling hva_to_pfn_retry() */ + gpc->uhva += page_offset; + + /* + * If the userspace HVA changed or the PFN was already invalid, + * drop the lock and do the HVA to PFN lookup again. + */ + if (!gpc->valid || hva_change) { + ret = hva_to_pfn_retry(gpc); + } else { + /* + * If the HVA→PFN mapping was already valid, don't unmap it. + * But do update gpc->khva because the offset within the page + * may have changed. + */ + gpc->khva = old_khva + page_offset; + ret = 0; + goto out_unlock; + } + + out: + /* + * Invalidate the cache and purge the pfn/khva if the refresh failed. + * Some/all of the uhva, gpa, and memslot generation info may still be + * valid, leave it as is. + */ + if (ret) { + gpc->valid = false; + gpc->pfn = KVM_PFN_ERR_FAULT; + gpc->khva = NULL; + } + + /* Detect a pfn change before dropping the lock! */ + unmap_old = (old_pfn != gpc->pfn); + +out_unlock: + write_unlock_irq(&gpc->lock); + + if (unmap_old) + gpc_unmap(old_pfn, old_khva); + + return ret; +} + +int kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, unsigned long len) +{ + unsigned long uhva; + + guard(mutex)(&gpc->refresh_lock); + + if (!kvm_gpc_is_valid_len(gpc->gpa, gpc->uhva, len)) + return -EINVAL; + + /* + * If the GPA is valid then ignore the HVA, as a cache can be GPA-based + * or HVA-based, not both. For GPA-based caches, the HVA will be + * recomputed during refresh if necessary. + */ + uhva = kvm_is_error_gpa(gpc->gpa) ? gpc->uhva : KVM_HVA_ERR_BAD; + + return __kvm_gpc_refresh(gpc, gpc->gpa, uhva); +} + +void kvm_gpc_init(struct gfn_to_pfn_cache *gpc, struct kvm *kvm) +{ + rwlock_init(&gpc->lock); + mutex_init(&gpc->refresh_lock); + + gpc->kvm = kvm; + gpc->pfn = KVM_PFN_ERR_FAULT; + gpc->gpa = INVALID_GPA; + gpc->uhva = KVM_HVA_ERR_BAD; + gpc->active = gpc->valid = false; +} + +static int __kvm_gpc_activate(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned long uhva, + unsigned long len) +{ + struct kvm *kvm = gpc->kvm; + + if (!kvm_gpc_is_valid_len(gpa, uhva, len)) + return -EINVAL; + + guard(mutex)(&gpc->refresh_lock); + + if (!gpc->active) { + if (KVM_BUG_ON(gpc->valid, kvm)) + return -EIO; + + spin_lock(&kvm->gpc_lock); + list_add(&gpc->list, &kvm->gpc_list); + spin_unlock(&kvm->gpc_lock); + + /* + * Activate the cache after adding it to the list, a concurrent + * refresh must not establish a mapping until the cache is + * reachable by mmu_notifier events. + */ + write_lock_irq(&gpc->lock); + gpc->active = true; + write_unlock_irq(&gpc->lock); + } + return __kvm_gpc_refresh(gpc, gpa, uhva); +} + +int kvm_gpc_activate(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned long len) +{ + /* + * Explicitly disallow INVALID_GPA so that the magic value can be used + * by KVM to differentiate between GPA-based and HVA-based caches. + */ + if (WARN_ON_ONCE(kvm_is_error_gpa(gpa))) + return -EINVAL; + + return __kvm_gpc_activate(gpc, gpa, KVM_HVA_ERR_BAD, len); +} + +int kvm_gpc_activate_hva(struct gfn_to_pfn_cache *gpc, unsigned long uhva, unsigned long len) +{ + if (!access_ok((void __user *)uhva, len)) + return -EINVAL; + + return __kvm_gpc_activate(gpc, INVALID_GPA, uhva, len); +} + +void kvm_gpc_deactivate(struct gfn_to_pfn_cache *gpc) +{ + struct kvm *kvm = gpc->kvm; + kvm_pfn_t old_pfn; + void *old_khva; + + guard(mutex)(&gpc->refresh_lock); + + if (gpc->active) { + /* + * Deactivate the cache before removing it from the list, KVM + * must stall mmu_notifier events until all users go away, i.e. + * until gpc->lock is dropped and refresh is guaranteed to fail. + */ + write_lock_irq(&gpc->lock); + gpc->active = false; + gpc->valid = false; + + /* + * Leave the GPA => uHVA cache intact, it's protected by the + * memslot generation. The PFN lookup needs to be redone every + * time as mmu_notifier protection is lost when the cache is + * removed from the VM's gpc_list. + */ + old_khva = gpc->khva - offset_in_page(gpc->khva); + gpc->khva = NULL; + + old_pfn = gpc->pfn; + gpc->pfn = KVM_PFN_ERR_FAULT; + write_unlock_irq(&gpc->lock); + + spin_lock(&kvm->gpc_lock); + list_del(&gpc->list); + spin_unlock(&kvm->gpc_lock); + + gpc_unmap(old_pfn, old_khva); + } +} diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c new file mode 100644 index 000000000000..be50514bbd11 --- /dev/null +++ b/virt/kvm/vfio.c @@ -0,0 +1,387 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * VFIO-KVM bridge pseudo device + * + * Copyright (C) 2013 Red Hat, Inc. All rights reserved. + * Author: Alex Williamson <alex.williamson@redhat.com> + */ + +#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> +#include "vfio.h" + +#ifdef CONFIG_SPAPR_TCE_IOMMU +#include <asm/kvm_ppc.h> +#endif + +struct kvm_vfio_file { + struct list_head node; + struct file *file; +#ifdef CONFIG_SPAPR_TCE_IOMMU + struct iommu_group *iommu_group; +#endif +}; + +struct kvm_vfio { + struct list_head file_list; + struct mutex lock; + bool noncoherent; +}; + +static void kvm_vfio_file_set_kvm(struct file *file, struct kvm *kvm) +{ + void (*fn)(struct file *file, struct kvm *kvm); + + fn = symbol_get(vfio_file_set_kvm); + if (!fn) + return; + + fn(file, kvm); + + symbol_put(vfio_file_set_kvm); +} + +static bool kvm_vfio_file_enforced_coherent(struct file *file) +{ + bool (*fn)(struct file *file); + bool ret; + + fn = symbol_get(vfio_file_enforced_coherent); + if (!fn) + return false; + + ret = fn(file); + + symbol_put(vfio_file_enforced_coherent); + + return ret; +} + +static bool kvm_vfio_file_is_valid(struct file *file) +{ + bool (*fn)(struct file *file); + bool ret; + + fn = symbol_get(vfio_file_is_valid); + if (!fn) + return false; + + ret = fn(file); + + symbol_put(vfio_file_is_valid); + + return ret; +} + +#ifdef CONFIG_SPAPR_TCE_IOMMU +static struct iommu_group *kvm_vfio_file_iommu_group(struct file *file) +{ + struct iommu_group *(*fn)(struct file *file); + struct iommu_group *ret; + + fn = symbol_get(vfio_file_iommu_group); + if (!fn) + return NULL; + + ret = fn(file); + + symbol_put(vfio_file_iommu_group); + + return ret; +} + +static void kvm_spapr_tce_release_vfio_group(struct kvm *kvm, + struct kvm_vfio_file *kvf) +{ + if (WARN_ON_ONCE(!kvf->iommu_group)) + return; + + kvm_spapr_tce_release_iommu_group(kvm, kvf->iommu_group); + iommu_group_put(kvf->iommu_group); + kvf->iommu_group = NULL; +} +#endif + +/* + * Groups/devices can use the same or different IOMMU domains. If the same + * then adding a new group/device may change the coherency of groups/devices + * we've previously been told about. We don't want to care about any of + * that so we retest each group/device 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_file *kvf; + + list_for_each_entry(kvf, &kv->file_list, node) { + if (!kvm_vfio_file_enforced_coherent(kvf->file)) { + 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); + } +} + +static int kvm_vfio_file_add(struct kvm_device *dev, unsigned int fd) +{ + struct kvm_vfio *kv = dev->private; + struct kvm_vfio_file *kvf; + struct file *filp; + int ret = 0; + + filp = fget(fd); + if (!filp) + return -EBADF; + + /* Ensure the FD is a vfio FD. */ + if (!kvm_vfio_file_is_valid(filp)) { + ret = -EINVAL; + goto out_fput; + } + + mutex_lock(&kv->lock); + + list_for_each_entry(kvf, &kv->file_list, node) { + if (kvf->file == filp) { + ret = -EEXIST; + goto out_unlock; + } + } + + kvf = kzalloc(sizeof(*kvf), GFP_KERNEL_ACCOUNT); + if (!kvf) { + ret = -ENOMEM; + goto out_unlock; + } + + kvf->file = get_file(filp); + list_add_tail(&kvf->node, &kv->file_list); + + kvm_vfio_file_set_kvm(kvf->file, dev->kvm); + kvm_vfio_update_coherency(dev); + +out_unlock: + mutex_unlock(&kv->lock); +out_fput: + fput(filp); + return ret; +} + +static int kvm_vfio_file_del(struct kvm_device *dev, unsigned int fd) +{ + struct kvm_vfio *kv = dev->private; + struct kvm_vfio_file *kvf; + CLASS(fd, f)(fd); + int ret; + + if (fd_empty(f)) + return -EBADF; + + ret = -ENOENT; + + mutex_lock(&kv->lock); + + list_for_each_entry(kvf, &kv->file_list, node) { + if (kvf->file != fd_file(f)) + continue; + + list_del(&kvf->node); +#ifdef CONFIG_SPAPR_TCE_IOMMU + kvm_spapr_tce_release_vfio_group(dev->kvm, kvf); +#endif + kvm_vfio_file_set_kvm(kvf->file, NULL); + fput(kvf->file); + kfree(kvf); + ret = 0; + break; + } + + kvm_vfio_update_coherency(dev); + + mutex_unlock(&kv->lock); + return ret; +} + +#ifdef CONFIG_SPAPR_TCE_IOMMU +static int kvm_vfio_file_set_spapr_tce(struct kvm_device *dev, + void __user *arg) +{ + struct kvm_vfio_spapr_tce param; + struct kvm_vfio *kv = dev->private; + struct kvm_vfio_file *kvf; + int ret; + + if (copy_from_user(¶m, arg, sizeof(struct kvm_vfio_spapr_tce))) + return -EFAULT; + + CLASS(fd, f)(param.groupfd); + if (fd_empty(f)) + return -EBADF; + + ret = -ENOENT; + + mutex_lock(&kv->lock); + + list_for_each_entry(kvf, &kv->file_list, node) { + if (kvf->file != fd_file(f)) + continue; + + if (!kvf->iommu_group) { + kvf->iommu_group = kvm_vfio_file_iommu_group(kvf->file); + if (WARN_ON_ONCE(!kvf->iommu_group)) { + ret = -EIO; + goto err_fdput; + } + } + + ret = kvm_spapr_tce_attach_iommu_group(dev->kvm, param.tablefd, + kvf->iommu_group); + break; + } + +err_fdput: + mutex_unlock(&kv->lock); + return ret; +} +#endif + +static int kvm_vfio_set_file(struct kvm_device *dev, long attr, + void __user *arg) +{ + int32_t __user *argp = arg; + int32_t fd; + + switch (attr) { + case KVM_DEV_VFIO_FILE_ADD: + if (get_user(fd, argp)) + return -EFAULT; + return kvm_vfio_file_add(dev, fd); + + case KVM_DEV_VFIO_FILE_DEL: + if (get_user(fd, argp)) + return -EFAULT; + return kvm_vfio_file_del(dev, fd); + +#ifdef CONFIG_SPAPR_TCE_IOMMU + case KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE: + return kvm_vfio_file_set_spapr_tce(dev, arg); +#endif + } + + return -ENXIO; +} + +static int kvm_vfio_set_attr(struct kvm_device *dev, + struct kvm_device_attr *attr) +{ + switch (attr->group) { + case KVM_DEV_VFIO_FILE: + return kvm_vfio_set_file(dev, attr->attr, + u64_to_user_ptr(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_FILE: + switch (attr->attr) { + case KVM_DEV_VFIO_FILE_ADD: + case KVM_DEV_VFIO_FILE_DEL: +#ifdef CONFIG_SPAPR_TCE_IOMMU + case KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE: +#endif + return 0; + } + + break; + } + + return -ENXIO; +} + +static void kvm_vfio_release(struct kvm_device *dev) +{ + struct kvm_vfio *kv = dev->private; + struct kvm_vfio_file *kvf, *tmp; + + list_for_each_entry_safe(kvf, tmp, &kv->file_list, node) { +#ifdef CONFIG_SPAPR_TCE_IOMMU + kvm_spapr_tce_release_vfio_group(dev->kvm, kvf); +#endif + kvm_vfio_file_set_kvm(kvf->file, NULL); + fput(kvf->file); + list_del(&kvf->node); + kfree(kvf); + } + + kvm_vfio_update_coherency(dev); + + kfree(kv); + kfree(dev); /* alloc by kvm_ioctl_create_device, free by .release */ +} + +static int kvm_vfio_create(struct kvm_device *dev, u32 type); + +static const struct kvm_device_ops kvm_vfio_ops = { + .name = "kvm-vfio", + .create = kvm_vfio_create, + .release = kvm_vfio_release, + .set_attr = kvm_vfio_set_attr, + .has_attr = kvm_vfio_has_attr, +}; + +static int kvm_vfio_create(struct kvm_device *dev, u32 type) +{ + struct kvm_device *tmp; + struct kvm_vfio *kv; + + lockdep_assert_held(&dev->kvm->lock); + + /* 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_ACCOUNT); + if (!kv) + return -ENOMEM; + + INIT_LIST_HEAD(&kv->file_list); + mutex_init(&kv->lock); + + dev->private = kv; + + return 0; +} + +int kvm_vfio_ops_init(void) +{ + return kvm_register_device_ops(&kvm_vfio_ops, KVM_DEV_TYPE_VFIO); +} + +void kvm_vfio_ops_exit(void) +{ + kvm_unregister_device_ops(KVM_DEV_TYPE_VFIO); +} diff --git a/virt/kvm/vfio.h b/virt/kvm/vfio.h new file mode 100644 index 000000000000..e130a4a03530 --- /dev/null +++ b/virt/kvm/vfio.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __KVM_VFIO_H +#define __KVM_VFIO_H + +#ifdef CONFIG_KVM_VFIO +int kvm_vfio_ops_init(void); +void kvm_vfio_ops_exit(void); +#else +static inline int kvm_vfio_ops_init(void) +{ + return 0; +} +static inline void kvm_vfio_ops_exit(void) +{ +} +#endif + +#endif |