diff options
129 files changed, 3632 insertions, 2261 deletions
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index fc34332c8d9a..4eaefb0983a8 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -4148,6 +4148,14 @@ Override pmtimer IOPort with a hex value. e.g. pmtmr=0x508 + pmu_override= [PPC] Override the PMU. + This option takes over the PMU facility, so it is no + longer usable by perf. Setting this option starts the + PMU counters by setting MMCR0 to 0 (the FC bit is + cleared). If a number is given, then MMCR1 is set to + that number, otherwise (e.g., 'pmu_override=on'), MMCR1 + remains 0. + pm_debug_messages [SUSPEND,KNL] Enable suspend/resume debug messages during boot up. diff --git a/Documentation/virt/kvm/mmu.rst b/Documentation/virt/kvm/mmu.rst index f60f5488e121..5b1ebad24c77 100644 --- a/Documentation/virt/kvm/mmu.rst +++ b/Documentation/virt/kvm/mmu.rst @@ -161,7 +161,7 @@ Shadow pages contain the following information: If clear, this page corresponds to a guest page table denoted by the gfn field. role.quadrant: - When role.gpte_is_8_bytes=0, the guest uses 32-bit gptes while the host uses 64-bit + When role.has_4_byte_gpte=1, the guest uses 32-bit gptes while the host uses 64-bit sptes. That means a guest page table contains more ptes than the host, so multiple shadow pages are needed to shadow one guest page. For first-level shadow pages, role.quadrant can be 0 or 1 and denotes the @@ -177,9 +177,9 @@ Shadow pages contain the following information: The page is invalid and should not be used. It is a root page that is currently pinned (by a cpu hardware register pointing to it); once it is unpinned it will be destroyed. - role.gpte_is_8_bytes: - Reflects the size of the guest PTE for which the page is valid, i.e. '1' - if 64-bit gptes are in use, '0' if 32-bit gptes are in use. + role.has_4_byte_gpte: + Reflects the size of the guest PTE for which the page is valid, i.e. '0' + if direct map or 64-bit gptes are in use, '1' if 32-bit gptes are in use. role.efer_nx: Contains the value of efer.nx for which the page is valid. role.cr0_wp: diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index f4871e47b2d0..28acc65ccb17 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -41,6 +41,8 @@ void kvm_inject_vabt(struct kvm_vcpu *vcpu); void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr); void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr); +void kvm_vcpu_wfi(struct kvm_vcpu *vcpu); + static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu) { return !(vcpu->arch.hcr_el2 & HCR_RW); diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 2a5f7f38006f..0e75277be5d5 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -717,7 +717,6 @@ void kvm_arm_vcpu_ptrauth_trap(struct kvm_vcpu *vcpu); static inline void kvm_arch_hardware_unsetup(void) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} -static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {} void kvm_arm_init_debug(void); void kvm_arm_vcpu_init_debug(struct kvm_vcpu *vcpu); diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index 8ffcbe29395e..f1f8fc069a97 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -39,6 +39,7 @@ menuconfig KVM select HAVE_KVM_IRQ_BYPASS select HAVE_KVM_VCPU_RUN_PID_CHANGE select SCHED_INFO + select INTERVAL_TREE help Support hosting virtualized guest machines. diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile index 989bb5dad2c8..04a53f71a6b6 100644 --- a/arch/arm64/kvm/Makefile +++ b/arch/arm64/kvm/Makefile @@ -5,14 +5,12 @@ ccflags-y += -I $(srctree)/$(src) -KVM=../../../virt/kvm +include $(srctree)/virt/kvm/Makefile.kvm obj-$(CONFIG_KVM) += kvm.o obj-$(CONFIG_KVM) += hyp/ -kvm-y := $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o \ - $(KVM)/vfio.o $(KVM)/irqchip.o $(KVM)/binary_stats.o \ - arm.o mmu.o mmio.o psci.o perf.o hypercalls.o pvtime.o \ +kvm-y += arm.o mmu.o mmio.o psci.o perf.o hypercalls.o pvtime.o \ inject_fault.o va_layout.o handle_exit.o \ guest.o debug.o reset.o sys_regs.o \ vgic-sys-reg-v3.o fpsimd.o pmu.o \ diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c index 3df67c127489..6e542e2eae32 100644 --- a/arch/arm64/kvm/arch_timer.c +++ b/arch/arm64/kvm/arch_timer.c @@ -467,7 +467,7 @@ out: } /* - * Schedule the background timer before calling kvm_vcpu_block, so that this + * Schedule the background timer before calling kvm_vcpu_halt, so that this * thread is removed from its waitqueue and made runnable when there's a timer * interrupt to handle. */ @@ -649,7 +649,6 @@ void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu) { struct arch_timer_cpu *timer = vcpu_timer(vcpu); struct timer_map map; - struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu); if (unlikely(!timer->enabled)) return; @@ -672,7 +671,7 @@ void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu) if (map.emul_ptimer) soft_timer_cancel(&map.emul_ptimer->hrtimer); - if (rcuwait_active(wait)) + if (kvm_vcpu_is_blocking(vcpu)) kvm_timer_blocking(vcpu); /* @@ -750,7 +749,7 @@ int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu) /* Make the updates of cntvoff for all vtimer contexts atomic */ static void update_vtimer_cntvoff(struct kvm_vcpu *vcpu, u64 cntvoff) { - int i; + unsigned long i; struct kvm *kvm = vcpu->kvm; struct kvm_vcpu *tmp; @@ -1189,8 +1188,8 @@ void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu) static bool timer_irqs_are_valid(struct kvm_vcpu *vcpu) { - int vtimer_irq, ptimer_irq; - int i, ret; + int vtimer_irq, ptimer_irq, ret; + unsigned long i; vtimer_irq = vcpu_vtimer(vcpu)->irq.irq; ret = kvm_vgic_set_owner(vcpu, vtimer_irq, vcpu_vtimer(vcpu)); @@ -1297,7 +1296,7 @@ void kvm_timer_init_vhe(void) static void set_timer_irqs(struct kvm *kvm, int vtimer_irq, int ptimer_irq) { struct kvm_vcpu *vcpu; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { vcpu_vtimer(vcpu)->irq.irq = vtimer_irq; diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index e4727dc771bf..14106a7c75b5 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -175,19 +175,11 @@ vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf) */ void kvm_arch_destroy_vm(struct kvm *kvm) { - int i; - bitmap_free(kvm->arch.pmu_filter); kvm_vgic_destroy(kvm); - for (i = 0; i < KVM_MAX_VCPUS; ++i) { - if (kvm->vcpus[i]) { - kvm_vcpu_destroy(kvm->vcpus[i]); - kvm->vcpus[i] = NULL; - } - } - atomic_set(&kvm->online_vcpus, 0); + kvm_destroy_vcpus(kvm); } int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) @@ -368,27 +360,12 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) { - /* - * If we're about to block (most likely because we've just hit a - * WFI), we need to sync back the state of the GIC CPU interface - * so that we have the latest PMR and group enables. This ensures - * that kvm_arch_vcpu_runnable has up-to-date data to decide - * whether we have pending interrupts. - * - * For the same reason, we want to tell GICv4 that we need - * doorbells to be signalled, should an interrupt become pending. - */ - preempt_disable(); - kvm_vgic_vmcr_sync(vcpu); - vgic_v4_put(vcpu, true); - preempt_enable(); + } void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) { - preempt_disable(); - vgic_v4_load(vcpu); - preempt_enable(); + } void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) @@ -639,7 +616,7 @@ bool kvm_arch_intc_initialized(struct kvm *kvm) void kvm_arm_halt_guest(struct kvm *kvm) { - int i; + unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) @@ -649,12 +626,12 @@ void kvm_arm_halt_guest(struct kvm *kvm) void kvm_arm_resume_guest(struct kvm *kvm) { - int i; + unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) { vcpu->arch.pause = false; - rcuwait_wake_up(kvm_arch_vcpu_get_wait(vcpu)); + __kvm_vcpu_wake_up(vcpu); } } @@ -679,6 +656,39 @@ static void vcpu_req_sleep(struct kvm_vcpu *vcpu) smp_rmb(); } +/** + * kvm_vcpu_wfi - emulate Wait-For-Interrupt behavior + * @vcpu: The VCPU pointer + * + * Suspend execution of a vCPU until a valid wake event is detected, i.e. until + * the vCPU is runnable. The vCPU may or may not be scheduled out, depending + * on when a wake event arrives, e.g. there may already be a pending wake event. + */ +void kvm_vcpu_wfi(struct kvm_vcpu *vcpu) +{ + /* + * Sync back the state of the GIC CPU interface so that we have + * the latest PMR and group enables. This ensures that + * kvm_arch_vcpu_runnable has up-to-date data to decide whether + * we have pending interrupts, e.g. when determining if the + * vCPU should block. + * + * For the same reason, we want to tell GICv4 that we need + * doorbells to be signalled, should an interrupt become pending. + */ + preempt_disable(); + kvm_vgic_vmcr_sync(vcpu); + vgic_v4_put(vcpu, true); + preempt_enable(); + + kvm_vcpu_halt(vcpu); + kvm_clear_request(KVM_REQ_UNHALT, vcpu); + + preempt_disable(); + vgic_v4_load(vcpu); + preempt_enable(); +} + static int kvm_vcpu_initialized(struct kvm_vcpu *vcpu) { return vcpu->arch.target >= 0; @@ -2035,7 +2045,7 @@ static int finalize_hyp_mode(void) struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr) { struct kvm_vcpu *vcpu; - int i; + unsigned long i; mpidr &= MPIDR_HWID_BITMASK; kvm_for_each_vcpu(i, vcpu, kvm) { diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index 275a27368a04..6d0baf71aa67 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -82,7 +82,7 @@ static int handle_no_fpsimd(struct kvm_vcpu *vcpu) * * WFE: Yield the CPU and come back to this vcpu when the scheduler * decides to. - * WFI: Simply call kvm_vcpu_block(), which will halt execution of + * WFI: Simply call kvm_vcpu_halt(), which will halt execution of * world-switches and schedule other host processes until there is an * incoming IRQ or FIQ to the VM. */ @@ -95,8 +95,7 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu) } else { trace_kvm_wfx_arm64(*vcpu_pc(vcpu), false); vcpu->stat.wfi_exit_stat++; - kvm_vcpu_block(vcpu); - kvm_clear_request(KVM_REQ_UNHALT, vcpu); + kvm_vcpu_wfi(vcpu); } kvm_incr_pc(vcpu); diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 326cdfec74a1..e65acf35cee3 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -210,13 +210,13 @@ static void stage2_flush_vm(struct kvm *kvm) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; - int idx; + int idx, bkt; idx = srcu_read_lock(&kvm->srcu); spin_lock(&kvm->mmu_lock); slots = kvm_memslots(kvm); - kvm_for_each_memslot(memslot, slots) + kvm_for_each_memslot(memslot, bkt, slots) stage2_flush_memslot(kvm, memslot); spin_unlock(&kvm->mmu_lock); @@ -595,14 +595,14 @@ void stage2_unmap_vm(struct kvm *kvm) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; - int idx; + int idx, bkt; idx = srcu_read_lock(&kvm->srcu); mmap_read_lock(current->mm); spin_lock(&kvm->mmu_lock); slots = kvm_memslots(kvm); - kvm_for_each_memslot(memslot, slots) + kvm_for_each_memslot(memslot, bkt, slots) stage2_unmap_memslot(kvm, memslot); spin_unlock(&kvm->mmu_lock); @@ -1463,7 +1463,6 @@ out: } void kvm_arch_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) @@ -1473,25 +1472,24 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, * allocated dirty_bitmap[], dirty pages will be tracked while the * memory slot is write protected. */ - if (change != KVM_MR_DELETE && mem->flags & KVM_MEM_LOG_DIRTY_PAGES) { + if (change != KVM_MR_DELETE && new->flags & KVM_MEM_LOG_DIRTY_PAGES) { /* * If we're with initial-all-set, we don't need to write * protect any pages because they're all reported as dirty. * Huge pages and normal pages will be write protect gradually. */ if (!kvm_dirty_log_manual_protect_and_init_set(kvm)) { - kvm_mmu_wp_memory_region(kvm, mem->slot); + kvm_mmu_wp_memory_region(kvm, new->id); } } } int kvm_arch_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, enum kvm_mr_change change) { - hva_t hva = mem->userspace_addr; - hva_t reg_end = hva + mem->memory_size; + hva_t hva, reg_end; int ret = 0; if (change != KVM_MR_CREATE && change != KVM_MR_MOVE && @@ -1502,9 +1500,12 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, * Prevent userspace from creating a memory region outside of the IPA * space addressable by the KVM guest IPA space. */ - if ((memslot->base_gfn + memslot->npages) > (kvm_phys_size(kvm) >> PAGE_SHIFT)) + if ((new->base_gfn + new->npages) > (kvm_phys_size(kvm) >> PAGE_SHIFT)) return -EFAULT; + hva = new->userspace_addr; + reg_end = hva + (new->npages << PAGE_SHIFT); + mmap_read_lock(current->mm); /* * A memory region could potentially cover multiple VMAs, and any holes @@ -1536,7 +1537,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, if (vma->vm_flags & VM_PFNMAP) { /* IO region dirty page logging not allowed */ - if (memslot->flags & KVM_MEM_LOG_DIRTY_PAGES) { + if (new->flags & KVM_MEM_LOG_DIRTY_PAGES) { ret = -EINVAL; break; } diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index a5e4bbf5e68f..0404357705a8 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -900,7 +900,7 @@ static int kvm_arm_pmu_v3_init(struct kvm_vcpu *vcpu) */ static bool pmu_irq_is_valid(struct kvm *kvm, int irq) { - int i; + unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) { diff --git a/arch/arm64/kvm/psci.c b/arch/arm64/kvm/psci.c index 74c47d420253..ad6c9ef32928 100644 --- a/arch/arm64/kvm/psci.c +++ b/arch/arm64/kvm/psci.c @@ -46,7 +46,7 @@ static unsigned long kvm_psci_vcpu_suspend(struct kvm_vcpu *vcpu) * specification (ARM DEN 0022A). This means all suspend states * for KVM will preserve the register state. */ - kvm_vcpu_block(vcpu); + kvm_vcpu_halt(vcpu); kvm_clear_request(KVM_REQ_UNHALT, vcpu); return PSCI_RET_SUCCESS; @@ -121,8 +121,8 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu) { - int i, matching_cpus = 0; - unsigned long mpidr; + int matching_cpus = 0; + unsigned long i, mpidr; unsigned long target_affinity; unsigned long target_affinity_mask; unsigned long lowest_affinity_level; @@ -164,7 +164,7 @@ static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu) static void kvm_prepare_system_event(struct kvm_vcpu *vcpu, u32 type) { - int i; + unsigned long i; struct kvm_vcpu *tmp; /* diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index 426bd7fbc3fd..97de30a79770 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -170,7 +170,7 @@ static bool vcpu_allowed_register_width(struct kvm_vcpu *vcpu) { struct kvm_vcpu *tmp; bool is32bit; - int i; + unsigned long i; is32bit = vcpu_has_feature(vcpu, KVM_ARM_VCPU_EL1_32BIT); if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1) && is32bit) diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index 0a06d0648970..a7382bda9676 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -70,8 +70,9 @@ void kvm_vgic_early_init(struct kvm *kvm) */ int kvm_vgic_create(struct kvm *kvm, u32 type) { - int i, ret; struct kvm_vcpu *vcpu; + unsigned long i; + int ret; if (irqchip_in_kernel(kvm)) return -EEXIST; @@ -255,7 +256,8 @@ int vgic_init(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; struct kvm_vcpu *vcpu; - int ret = 0, i, idx; + int ret = 0, i; + unsigned long idx; if (vgic_initialized(kvm)) return 0; @@ -308,7 +310,7 @@ int vgic_init(struct kvm *kvm) goto out; } - kvm_for_each_vcpu(i, vcpu, kvm) + kvm_for_each_vcpu(idx, vcpu, kvm) kvm_vgic_vcpu_enable(vcpu); ret = kvm_vgic_setup_default_irq_routing(kvm); @@ -370,7 +372,7 @@ void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) static void __kvm_vgic_destroy(struct kvm *kvm) { struct kvm_vcpu *vcpu; - int i; + unsigned long i; vgic_debug_destroy(kvm); diff --git a/arch/arm64/kvm/vgic/vgic-kvm-device.c b/arch/arm64/kvm/vgic/vgic-kvm-device.c index 0d000d2fe8d2..c6d52a1fd9c8 100644 --- a/arch/arm64/kvm/vgic/vgic-kvm-device.c +++ b/arch/arm64/kvm/vgic/vgic-kvm-device.c @@ -325,7 +325,7 @@ void unlock_all_vcpus(struct kvm *kvm) bool lock_all_vcpus(struct kvm *kvm) { struct kvm_vcpu *tmp_vcpu; - int c; + unsigned long c; /* * Any time a vcpu is run, vcpu_load is called which tries to grab the diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v2.c b/arch/arm64/kvm/vgic/vgic-mmio-v2.c index 5f9014ae595b..12e4c223e6b8 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio-v2.c +++ b/arch/arm64/kvm/vgic/vgic-mmio-v2.c @@ -113,9 +113,8 @@ static void vgic_mmio_write_sgir(struct kvm_vcpu *source_vcpu, int intid = val & 0xf; int targets = (val >> 16) & 0xff; int mode = (val >> 24) & 0x03; - int c; struct kvm_vcpu *vcpu; - unsigned long flags; + unsigned long flags, c; switch (mode) { case 0x0: /* as specified by targets */ diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c index bf7ec4a78497..82906cb3f713 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c +++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c @@ -754,7 +754,8 @@ static void vgic_unregister_redist_iodev(struct kvm_vcpu *vcpu) static int vgic_register_all_redist_iodevs(struct kvm *kvm) { struct kvm_vcpu *vcpu; - int c, ret = 0; + unsigned long c; + int ret = 0; kvm_for_each_vcpu(c, vcpu, kvm) { ret = vgic_register_redist_iodev(vcpu); @@ -995,10 +996,10 @@ void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg, bool allow_group1) struct kvm_vcpu *c_vcpu; u16 target_cpus; u64 mpidr; - int sgi, c; + int sgi; int vcpu_id = vcpu->vcpu_id; bool broadcast; - unsigned long flags; + unsigned long c, flags; sgi = (reg & ICC_SGI1R_SGI_ID_MASK) >> ICC_SGI1R_SGI_ID_SHIFT; broadcast = reg & BIT_ULL(ICC_SGI1R_IRQ_ROUTING_MODE_BIT); diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c index 04f62c4b07fb..5fedaee15e72 100644 --- a/arch/arm64/kvm/vgic/vgic-v3.c +++ b/arch/arm64/kvm/vgic/vgic-v3.c @@ -542,13 +542,13 @@ int vgic_v3_map_resources(struct kvm *kvm) struct vgic_dist *dist = &kvm->arch.vgic; struct kvm_vcpu *vcpu; int ret = 0; - int c; + unsigned long c; kvm_for_each_vcpu(c, vcpu, kvm) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; if (IS_VGIC_ADDR_UNDEF(vgic_cpu->rd_iodev.base_addr)) { - kvm_debug("vcpu %d redistributor base not set\n", c); + kvm_debug("vcpu %ld redistributor base not set\n", c); return -ENXIO; } } diff --git a/arch/arm64/kvm/vgic/vgic-v4.c b/arch/arm64/kvm/vgic/vgic-v4.c index 772dd15a22c7..ad06ba6c9b00 100644 --- a/arch/arm64/kvm/vgic/vgic-v4.c +++ b/arch/arm64/kvm/vgic/vgic-v4.c @@ -189,7 +189,7 @@ void vgic_v4_configure_vsgis(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; struct kvm_vcpu *vcpu; - int i; + unsigned long i; kvm_arm_halt_guest(kvm); @@ -235,7 +235,8 @@ int vgic_v4_init(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; struct kvm_vcpu *vcpu; - int i, nr_vcpus, ret; + int nr_vcpus, ret; + unsigned long i; if (!kvm_vgic_global_state.has_gicv4) return 0; /* Nothing to see here... move along. */ diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c index 5dad4996cfb2..9b98876a8a93 100644 --- a/arch/arm64/kvm/vgic/vgic.c +++ b/arch/arm64/kvm/vgic/vgic.c @@ -990,7 +990,7 @@ int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu) void vgic_kick_vcpus(struct kvm *kvm) { struct kvm_vcpu *vcpu; - int c; + unsigned long c; /* * We've injected an interrupt, time to find out who deserves diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index 696f6b009377..72b90d45a46e 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -897,7 +897,6 @@ static inline void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) {} static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {} static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {} -static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {} #define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLB int kvm_arch_flush_remote_tlb(struct kvm *kvm); diff --git a/arch/mips/kvm/Kconfig b/arch/mips/kvm/Kconfig index a77297480f56..91d197bee9c0 100644 --- a/arch/mips/kvm/Kconfig +++ b/arch/mips/kvm/Kconfig @@ -27,6 +27,7 @@ config KVM select KVM_MMIO select MMU_NOTIFIER select SRCU + select INTERVAL_TREE help Support for hosting Guest kernels. diff --git a/arch/mips/kvm/Makefile b/arch/mips/kvm/Makefile index d3710959da55..21ff75bcdbc4 100644 --- a/arch/mips/kvm/Makefile +++ b/arch/mips/kvm/Makefile @@ -2,9 +2,10 @@ # Makefile for KVM support for MIPS # +include $(srctree)/virt/kvm/Makefile.kvm + ccflags-y += -Ivirt/kvm -Iarch/mips/kvm -kvm-y := $(addprefix ../../../virt/kvm/, kvm_main.o coalesced_mmio.o eventfd.o binary_stats.o) kvm-$(CONFIG_CPU_HAS_MSA) += msa.o kvm-y += mips.o emulate.o entry.o \ diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c index 22e745e49b0a..b494d8d39290 100644 --- a/arch/mips/kvm/emulate.c +++ b/arch/mips/kvm/emulate.c @@ -952,7 +952,7 @@ enum emulation_result kvm_mips_emul_wait(struct kvm_vcpu *vcpu) if (!vcpu->arch.pending_exceptions) { kvm_vz_lose_htimer(vcpu); vcpu->arch.wait = 1; - kvm_vcpu_block(vcpu); + kvm_vcpu_halt(vcpu); /* * We we are runnable, then definitely go off to user space to diff --git a/arch/mips/kvm/loongson_ipi.c b/arch/mips/kvm/loongson_ipi.c index 3681fc8fba38..5d53f32d837c 100644 --- a/arch/mips/kvm/loongson_ipi.c +++ b/arch/mips/kvm/loongson_ipi.c @@ -120,7 +120,7 @@ static int loongson_vipi_write(struct loongson_kvm_ipi *ipi, s->status |= data; irq.cpu = id; irq.irq = 6; - kvm_vcpu_ioctl_interrupt(kvm->vcpus[id], &irq); + kvm_vcpu_ioctl_interrupt(kvm_get_vcpu(kvm, id), &irq); break; case CORE0_CLEAR_OFF: @@ -128,7 +128,7 @@ static int loongson_vipi_write(struct loongson_kvm_ipi *ipi, if (!s->status) { irq.cpu = id; irq.irq = -6; - kvm_vcpu_ioctl_interrupt(kvm->vcpus[id], &irq); + kvm_vcpu_ioctl_interrupt(kvm_get_vcpu(kvm, id), &irq); } break; diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index aa20d074d388..e59cb6246f76 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -171,25 +171,6 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) return 0; } -void kvm_mips_free_vcpus(struct kvm *kvm) -{ - unsigned int i; - struct kvm_vcpu *vcpu; - - kvm_for_each_vcpu(i, vcpu, kvm) { - kvm_vcpu_destroy(vcpu); - } - - mutex_lock(&kvm->lock); - - for (i = 0; i < atomic_read(&kvm->online_vcpus); i++) - kvm->vcpus[i] = NULL; - - atomic_set(&kvm->online_vcpus, 0); - - mutex_unlock(&kvm->lock); -} - static void kvm_mips_free_gpa_pt(struct kvm *kvm) { /* It should always be safe to remove after flushing the whole range */ @@ -199,7 +180,7 @@ static void kvm_mips_free_gpa_pt(struct kvm *kvm) void kvm_arch_destroy_vm(struct kvm *kvm) { - kvm_mips_free_vcpus(kvm); + kvm_destroy_vcpus(kvm); kvm_mips_free_gpa_pt(kvm); } @@ -233,25 +214,20 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm, } int kvm_arch_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, enum kvm_mr_change change) { return 0; } void kvm_arch_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { int needs_flush; - kvm_debug("%s: kvm: %p slot: %d, GPA: %llx, size: %llx, QVA: %llx\n", - __func__, kvm, mem->slot, mem->guest_phys_addr, - mem->memory_size, mem->userspace_addr); - /* * If dirty page logging is enabled, write protect all pages in the slot * ready for dirty logging. @@ -498,7 +474,7 @@ int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, if (irq->cpu == -1) dvcpu = vcpu; else - dvcpu = vcpu->kvm->vcpus[irq->cpu]; + dvcpu = kvm_get_vcpu(vcpu->kvm, irq->cpu); if (intr == 2 || intr == 3 || intr == 4 || intr == 6) { kvm_mips_callbacks->queue_io_int(dvcpu, irq); diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h index 222823861a67..41b8a1e1144a 100644 --- a/arch/powerpc/include/asm/asm-prototypes.h +++ b/arch/powerpc/include/asm/asm-prototypes.h @@ -141,11 +141,6 @@ static inline void kvmppc_restore_tm_hv(struct kvm_vcpu *vcpu, u64 msr, bool preserve_nv) { } #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ -void kvmhv_save_host_pmu(void); -void kvmhv_load_host_pmu(void); -void kvmhv_save_guest_pmu(struct kvm_vcpu *vcpu, bool pmu_in_use); -void kvmhv_load_guest_pmu(struct kvm_vcpu *vcpu); - void kvmppc_p9_enter_guest(struct kvm_vcpu *vcpu); long kvmppc_h_set_dabr(struct kvm_vcpu *vcpu, unsigned long dabr); diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h index fbbf3cec92e9..d68d71987d5c 100644 --- a/arch/powerpc/include/asm/kvm_asm.h +++ b/arch/powerpc/include/asm/kvm_asm.h @@ -79,6 +79,7 @@ #define BOOK3S_INTERRUPT_FP_UNAVAIL 0x800 #define BOOK3S_INTERRUPT_DECREMENTER 0x900 #define BOOK3S_INTERRUPT_HV_DECREMENTER 0x980 +#define BOOK3S_INTERRUPT_NESTED_HV_DECREMENTER 0x1980 #define BOOK3S_INTERRUPT_DOORBELL 0xa00 #define BOOK3S_INTERRUPT_SYSCALL 0xc00 #define BOOK3S_INTERRUPT_TRACE 0xd00 diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index 3d31f2c59e43..91c9f937edcd 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -406,6 +406,12 @@ static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu) return vcpu->arch.fault_dar; } +/* Expiry time of vcpu DEC relative to host TB */ +static inline u64 kvmppc_dec_expires_host_tb(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.dec_expires - vcpu->arch.vcore->tb_offset; +} + static inline bool is_kvmppc_resume_guest(int r) { return (r == RESUME_GUEST || r == RESUME_GUEST_NV); diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index fff391b9b97b..fe07558173ef 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -44,7 +44,6 @@ struct kvm_nested_guest { struct mutex tlb_lock; /* serialize page faults and tlbies */ struct kvm_nested_guest *next; cpumask_t need_tlb_flush; - cpumask_t cpu_in_guest; short prev_cpu[NR_CPUS]; u8 radix; /* is this nested guest radix */ }; @@ -154,7 +153,9 @@ static inline bool kvmhv_vcpu_is_radix(struct kvm_vcpu *vcpu) return radix; } -int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpcr); +unsigned long kvmppc_msr_hard_disable_set_facilities(struct kvm_vcpu *vcpu, unsigned long msr); + +int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpcr, u64 *tb); #define KVM_DEFAULT_HPT_ORDER 24 /* 16MB HPT by default */ #endif diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index e4d23193eba7..a770443cd6e0 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -287,7 +287,6 @@ struct kvm_arch { u32 online_vcores; atomic_t hpte_mod_interest; cpumask_t need_tlb_flush; - cpumask_t cpu_in_guest; u8 radix; u8 fwnmi_enabled; u8 secure_guest; @@ -579,6 +578,10 @@ struct kvm_vcpu_arch { ulong cfar; ulong ppr; u32 pspb; + u8 load_ebb; +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + u8 load_tm; +#endif ulong fscr; ulong shadow_fscr; ulong ebbhr; @@ -741,7 +744,7 @@ struct kvm_vcpu_arch { struct hrtimer dec_timer; u64 dec_jiffies; - u64 dec_expires; + u64 dec_expires; /* Relative to guest timebase. */ unsigned long pending_exceptions; u8 ceded; u8 prodded; @@ -749,6 +752,7 @@ struct kvm_vcpu_arch { u8 irq_pending; /* Used by XIVE to signal pending guest irqs */ u32 last_inst; + struct rcuwait wait; struct rcuwait *waitp; struct kvmppc_vcore *vcore; int ret; @@ -864,6 +868,5 @@ static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} static inline void kvm_arch_exit(void) {} static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {} static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {} -static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {} #endif /* __POWERPC_KVM_HOST_H__ */ diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index 671fbd1a765e..a14dbcd1b8ce 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -200,12 +200,11 @@ extern void kvmppc_core_destroy_vm(struct kvm *kvm); extern void kvmppc_core_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot); extern int kvmppc_core_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, enum kvm_mr_change change); extern void kvmppc_core_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old, + struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change); extern int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm, @@ -274,12 +273,11 @@ struct kvmppc_ops { int (*get_dirty_log)(struct kvm *kvm, struct kvm_dirty_log *log); void (*flush_memslot)(struct kvm *kvm, struct kvm_memory_slot *memslot); int (*prepare_memory_region)(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, enum kvm_mr_change change); void (*commit_memory_region)(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old, + struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change); bool (*unmap_gfn_range)(struct kvm *kvm, struct kvm_gfn_range *range); @@ -552,8 +550,7 @@ extern void kvm_hv_vm_activated(void); extern void kvm_hv_vm_deactivated(void); extern bool kvm_hv_mode_active(void); -extern void kvmppc_check_need_tlb_flush(struct kvm *kvm, int pcpu, - struct kvm_nested_guest *nested); +extern void kvmppc_check_need_tlb_flush(struct kvm *kvm, int pcpu); #else static inline void __init kvm_cma_reserve(void) @@ -760,6 +757,7 @@ void kvmppc_realmode_machine_check(struct kvm_vcpu *vcpu); void kvmppc_subcore_enter_guest(void); void kvmppc_subcore_exit_guest(void); long kvmppc_realmode_hmi_handler(void); +long kvmppc_p9_realmode_hmi_handler(struct kvm_vcpu *vcpu); long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags, long pte_index, unsigned long pteh, unsigned long ptel); long kvmppc_h_remove(struct kvm_vcpu *vcpu, unsigned long flags, diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h index 9d1fbd8be1c7..1f43ef696033 100644 --- a/arch/powerpc/include/asm/switch_to.h +++ b/arch/powerpc/include/asm/switch_to.h @@ -112,6 +112,9 @@ static inline void clear_task_ebb(struct task_struct *t) #endif } +void kvmppc_save_user_regs(void); +void kvmppc_save_current_sprs(void); + extern int set_thread_tidr(struct task_struct *t); #endif /* _ASM_POWERPC_SWITCH_TO_H */ diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h index 8c2c3dd4ddba..924b2157882f 100644 --- a/arch/powerpc/include/asm/time.h +++ b/arch/powerpc/include/asm/time.h @@ -18,6 +18,8 @@ #include <asm/vdso/timebase.h> /* time.c */ +extern u64 decrementer_max; + extern unsigned long tb_ticks_per_jiffy; extern unsigned long tb_ticks_per_usec; extern unsigned long tb_ticks_per_sec; @@ -97,19 +99,16 @@ extern void div128_by_32(u64 dividend_high, u64 dividend_low, extern void secondary_cpu_time_init(void); extern void __init time_init(void); -#ifdef CONFIG_PPC64 -static inline unsigned long test_irq_work_pending(void) -{ - unsigned long x; +DECLARE_PER_CPU(u64, decrementers_next_tb); - asm volatile("lbz %0,%1(13)" - : "=r" (x) - : "i" (offsetof(struct paca_struct, irq_work_pending))); - return x; +static inline u64 timer_get_next_tb(void) +{ + return __this_cpu_read(decrementers_next_tb); } -#endif -DECLARE_PER_CPU(u64, decrementers_next_tb); +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE +void timer_rearm_host_dec(u64 now); +#endif /* Convert timebase ticks to nanoseconds */ unsigned long long tb_to_ns(unsigned long long tb_ticks); diff --git a/arch/powerpc/kernel/cpu_setup_power.c b/arch/powerpc/kernel/cpu_setup_power.c index 3cca88ee96d7..3dc61e203f37 100644 --- a/arch/powerpc/kernel/cpu_setup_power.c +++ b/arch/powerpc/kernel/cpu_setup_power.c @@ -109,7 +109,7 @@ static void init_PMU_HV_ISA207(void) static void init_PMU(void) { mtspr(SPRN_MMCRA, 0); - mtspr(SPRN_MMCR0, 0); + mtspr(SPRN_MMCR0, MMCR0_FC); mtspr(SPRN_MMCR1, 0); mtspr(SPRN_MMCR2, 0); } @@ -123,7 +123,7 @@ static void init_PMU_ISA31(void) { mtspr(SPRN_MMCR3, 0); mtspr(SPRN_MMCRA, MMCRA_BHRB_DISABLE); - mtspr(SPRN_MMCR0, MMCR0_PMCCEXT); + mtspr(SPRN_MMCR0, MMCR0_FC | MMCR0_PMCCEXT); } /* @@ -137,6 +137,7 @@ void __setup_cpu_power7(unsigned long offset, struct cpu_spec *t) return; mtspr(SPRN_LPID, 0); + mtspr(SPRN_AMOR, ~0); mtspr(SPRN_PCR, PCR_MASK); init_LPCR_ISA206(mfspr(SPRN_LPCR), LPCR_LPES1 >> LPCR_LPES_SH); } @@ -150,6 +151,7 @@ void __restore_cpu_power7(void) return; mtspr(SPRN_LPID, 0); + mtspr(SPRN_AMOR, ~0); mtspr(SPRN_PCR, PCR_MASK); init_LPCR_ISA206(mfspr(SPRN_LPCR), LPCR_LPES1 >> LPCR_LPES_SH); } @@ -164,6 +166,7 @@ void __setup_cpu_power8(unsigned long offset, struct cpu_spec *t) return; mtspr(SPRN_LPID, 0); + mtspr(SPRN_AMOR, ~0); mtspr(SPRN_PCR, PCR_MASK); init_LPCR_ISA206(mfspr(SPRN_LPCR) | LPCR_PECEDH, 0); /* LPES = 0 */ init_HFSCR(); @@ -184,6 +187,7 @@ void __restore_cpu_power8(void) return; mtspr(SPRN_LPID, 0); + mtspr(SPRN_AMOR, ~0); mtspr(SPRN_PCR, PCR_MASK); init_LPCR_ISA206(mfspr(SPRN_LPCR) | LPCR_PECEDH, 0); /* LPES = 0 */ init_HFSCR(); @@ -202,6 +206,7 @@ void __setup_cpu_power9(unsigned long offset, struct cpu_spec *t) mtspr(SPRN_PSSCR, 0); mtspr(SPRN_LPID, 0); mtspr(SPRN_PID, 0); + mtspr(SPRN_AMOR, ~0); mtspr(SPRN_PCR, PCR_MASK); init_LPCR_ISA300((mfspr(SPRN_LPCR) | LPCR_PECEDH | LPCR_PECE_HVEE |\ LPCR_HVICE | LPCR_HEIC) & ~(LPCR_UPRT | LPCR_HR), 0); @@ -223,6 +228,7 @@ void __restore_cpu_power9(void) mtspr(SPRN_PSSCR, 0); mtspr(SPRN_LPID, 0); mtspr(SPRN_PID, 0); + mtspr(SPRN_AMOR, ~0); mtspr(SPRN_PCR, PCR_MASK); init_LPCR_ISA300((mfspr(SPRN_LPCR) | LPCR_PECEDH | LPCR_PECE_HVEE |\ LPCR_HVICE | LPCR_HEIC) & ~(LPCR_UPRT | LPCR_HR), 0); @@ -242,6 +248,7 @@ void __setup_cpu_power10(unsigned long offset, struct cpu_spec *t) mtspr(SPRN_PSSCR, 0); mtspr(SPRN_LPID, 0); mtspr(SPRN_PID, 0); + mtspr(SPRN_AMOR, ~0); mtspr(SPRN_PCR, PCR_MASK); init_LPCR_ISA300((mfspr(SPRN_LPCR) | LPCR_PECEDH | LPCR_PECE_HVEE |\ LPCR_HVICE | LPCR_HEIC) & ~(LPCR_UPRT | LPCR_HR), 0); @@ -264,6 +271,7 @@ void __restore_cpu_power10(void) mtspr(SPRN_PSSCR, 0); mtspr(SPRN_LPID, 0); mtspr(SPRN_PID, 0); + mtspr(SPRN_AMOR, ~0); mtspr(SPRN_PCR, PCR_MASK); init_LPCR_ISA300((mfspr(SPRN_LPCR) | LPCR_PECEDH | LPCR_PECE_HVEE |\ LPCR_HVICE | LPCR_HEIC) & ~(LPCR_UPRT | LPCR_HR), 0); diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index ba527fb52993..d2b35fb9181d 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -80,6 +80,7 @@ static void __restore_cpu_cpufeatures(void) mtspr(SPRN_LPCR, system_registers.lpcr); if (hv_mode) { mtspr(SPRN_LPID, 0); + mtspr(SPRN_AMOR, ~0); mtspr(SPRN_HFSCR, system_registers.hfscr); mtspr(SPRN_PCR, system_registers.pcr); } @@ -216,6 +217,7 @@ static int __init feat_enable_hv(struct dt_cpu_feature *f) } mtspr(SPRN_LPID, 0); + mtspr(SPRN_AMOR, ~0); lpcr = mfspr(SPRN_LPCR); lpcr &= ~LPCR_LPES0; /* HV external interrupts */ @@ -351,7 +353,7 @@ static void init_pmu_power8(void) } mtspr(SPRN_MMCRA, 0); - mtspr(SPRN_MMCR0, 0); + mtspr(SPRN_MMCR0, MMCR0_FC); mtspr(SPRN_MMCR1, 0); mtspr(SPRN_MMCR2, 0); mtspr(SPRN_MMCRS, 0); @@ -390,7 +392,7 @@ static void init_pmu_power9(void) mtspr(SPRN_MMCRC, 0); mtspr(SPRN_MMCRA, 0); - mtspr(SPRN_MMCR0, 0); + mtspr(SPRN_MMCR0, MMCR0_FC); mtspr(SPRN_MMCR1, 0); mtspr(SPRN_MMCR2, 0); } @@ -426,7 +428,7 @@ static void init_pmu_power10(void) mtspr(SPRN_MMCR3, 0); mtspr(SPRN_MMCRA, MMCRA_BHRB_DISABLE); - mtspr(SPRN_MMCR0, MMCR0_PMCCEXT); + mtspr(SPRN_MMCR0, MMCR0_FC | MMCR0_PMCCEXT); } static int __init feat_enable_pmu_power10(struct dt_cpu_feature *f) diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 406d7ee9e322..5d2333d2a283 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1156,6 +1156,40 @@ static inline void save_sprs(struct thread_struct *t) #endif } +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE +void kvmppc_save_user_regs(void) +{ + unsigned long usermsr; + + if (!current->thread.regs) + return; + + usermsr = current->thread.regs->msr; + + if (usermsr & MSR_FP) + save_fpu(current); + + if (usermsr & MSR_VEC) + save_altivec(current); + +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (usermsr & MSR_TM) { + current->thread.tm_tfhar = mfspr(SPRN_TFHAR); + current->thread.tm_tfiar = mfspr(SPRN_TFIAR); + current->thread.tm_texasr = mfspr(SPRN_TEXASR); + current->thread.regs->msr &= ~MSR_TM; + } +#endif +} +EXPORT_SYMBOL_GPL(kvmppc_save_user_regs); + +void kvmppc_save_current_sprs(void) +{ + save_sprs(¤t->thread); +} +EXPORT_SYMBOL_GPL(kvmppc_save_current_sprs); +#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */ + static inline void restore_sprs(struct thread_struct *old_thread, struct thread_struct *new_thread) { diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index cae8f03a44fe..f7cddb82938f 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -88,6 +88,7 @@ static struct clocksource clocksource_timebase = { #define DECREMENTER_DEFAULT_MAX 0x7FFFFFFF u64 decrementer_max = DECREMENTER_DEFAULT_MAX; +EXPORT_SYMBOL_GPL(decrementer_max); /* for KVM HDEC */ static int decrementer_set_next_event(unsigned long evt, struct clock_event_device *dev); @@ -107,6 +108,7 @@ struct clock_event_device decrementer_clockevent = { EXPORT_SYMBOL(decrementer_clockevent); DEFINE_PER_CPU(u64, decrementers_next_tb); +EXPORT_SYMBOL_GPL(decrementers_next_tb); static DEFINE_PER_CPU(struct clock_event_device, decrementers); #define XSEC_PER_SEC (1024*1024) @@ -496,6 +498,16 @@ EXPORT_SYMBOL(profile_pc); * 64-bit uses a byte in the PACA, 32-bit uses a per-cpu variable... */ #ifdef CONFIG_PPC64 +static inline unsigned long test_irq_work_pending(void) +{ + unsigned long x; + + asm volatile("lbz %0,%1(13)" + : "=r" (x) + : "i" (offsetof(struct paca_struct, irq_work_pending))); + return x; +} + static inline void set_irq_work_pending_flag(void) { asm volatile("stb %0,%1(13)" : : @@ -539,13 +551,44 @@ void arch_irq_work_raise(void) preempt_enable(); } +static void set_dec_or_work(u64 val) +{ + set_dec(val); + /* We may have raced with new irq work */ + if (unlikely(test_irq_work_pending())) + set_dec(1); +} + #else /* CONFIG_IRQ_WORK */ #define test_irq_work_pending() 0 #define clear_irq_work_pending() +static void set_dec_or_work(u64 val) +{ + set_dec(val); +} #endif /* CONFIG_IRQ_WORK */ +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE +void timer_rearm_host_dec(u64 now) +{ + u64 *next_tb = this_cpu_ptr(&decrementers_next_tb); + + WARN_ON_ONCE(!arch_irqs_disabled()); + WARN_ON_ONCE(mfmsr() & MSR_EE); + + if (now >= *next_tb) { + local_paca->irq_happened |= PACA_IRQ_DEC; + } else { + now = *next_tb - now; + if (now <= decrementer_max) + set_dec_or_work(now); + } +} +EXPORT_SYMBOL_GPL(timer_rearm_host_dec); +#endif + /* * timer_interrupt - gets called when the decrementer overflows, * with interrupts disabled. @@ -606,10 +649,7 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt) } else { now = *next_tb - now; if (now <= decrementer_max) - set_dec(now); - /* We may have raced with new irq work */ - if (test_irq_work_pending()) - set_dec(1); + set_dec_or_work(now); __this_cpu_inc(irq_stat.timer_irqs_others); } @@ -843,11 +883,7 @@ static int decrementer_set_next_event(unsigned long evt, struct clock_event_device *dev) { __this_cpu_write(decrementers_next_tb, get_tb() + evt); - set_dec(evt); - - /* We may have raced with new irq work */ - if (test_irq_work_pending()) - set_dec(1); + set_dec_or_work(evt); return 0; } diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index ff581d70f20c..c8e156011db9 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -26,6 +26,7 @@ config KVM select KVM_VFIO select IRQ_BYPASS_MANAGER select HAVE_KVM_IRQ_BYPASS + select INTERVAL_TREE config KVM_BOOK3S_HANDLER bool @@ -130,6 +131,21 @@ config KVM_BOOK3S_HV_EXIT_TIMING If unsure, say N. +config KVM_BOOK3S_HV_NESTED_PMU_WORKAROUND + bool "Nested L0 host workaround for L1 KVM host PMU handling bug" if EXPERT + depends on KVM_BOOK3S_HV_POSSIBLE + default !EXPERT + help + Old nested HV capable Linux guests have a bug where they don't + reflect the PMU in-use status of their L2 guest to the L0 host + while the L2 PMU registers are live. This can result in loss + of L2 PMU register state, causing perf to not work correctly in + L2 guests. + + Selecting this option for the L0 host implements a workaround for + those buggy L1s which saves the L2 state, at the cost of performance + in all nested-capable guest entry/exit. + config KVM_BOOKE_HV bool diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile index 583c14ef596e..9bdfc8b50899 100644 --- a/arch/powerpc/kvm/Makefile +++ b/arch/powerpc/kvm/Makefile @@ -4,11 +4,8 @@ # ccflags-y := -Ivirt/kvm -Iarch/powerpc/kvm -KVM := ../../../virt/kvm -common-objs-y = $(KVM)/kvm_main.o $(KVM)/eventfd.o $(KVM)/binary_stats.o -common-objs-$(CONFIG_KVM_VFIO) += $(KVM)/vfio.o -common-objs-$(CONFIG_KVM_MMIO) += $(KVM)/coalesced_mmio.o +include $(srctree)/virt/kvm/Makefile.kvm common-objs-y += powerpc.o emulate_loadstore.o obj-$(CONFIG_KVM_EXIT_TIMING) += timing.o @@ -125,9 +122,8 @@ kvm-book3s_32-objs := \ kvm-objs-$(CONFIG_KVM_BOOK3S_32) := $(kvm-book3s_32-objs) kvm-objs-$(CONFIG_KVM_MPIC) += mpic.o -kvm-objs-$(CONFIG_HAVE_KVM_IRQ_ROUTING) += $(KVM)/irqchip.o -kvm-objs := $(kvm-objs-m) $(kvm-objs-y) +kvm-y += $(kvm-objs-m) $(kvm-objs-y) obj-$(CONFIG_KVM_E500V2) += kvm.o obj-$(CONFIG_KVM_E500MC) += kvm.o diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index b785f6772391..6d525285dbe8 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -847,21 +847,19 @@ void kvmppc_core_flush_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot) } int kvmppc_core_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, - enum kvm_mr_change change) + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, + enum kvm_mr_change change) { - return kvm->arch.kvm_ops->prepare_memory_region(kvm, memslot, mem, - change); + return kvm->arch.kvm_ops->prepare_memory_region(kvm, old, new, change); } void kvmppc_core_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old, + struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { - kvm->arch.kvm_ops->commit_memory_region(kvm, mem, old, new, change); + kvm->arch.kvm_ops->commit_memory_region(kvm, old, new, change); } bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) diff --git a/arch/powerpc/kvm/book3s_32_mmu.c b/arch/powerpc/kvm/book3s_32_mmu.c index 3fbd570f9c1e..0215f32932a9 100644 --- a/arch/powerpc/kvm/book3s_32_mmu.c +++ b/arch/powerpc/kvm/book3s_32_mmu.c @@ -337,7 +337,7 @@ static void kvmppc_mmu_book3s_32_mtsrin(struct kvm_vcpu *vcpu, u32 srnum, static void kvmppc_mmu_book3s_32_tlbie(struct kvm_vcpu *vcpu, ulong ea, bool large) { - int i; + unsigned long i; struct kvm_vcpu *v; /* flush this VA on all cpus */ diff --git a/arch/powerpc/kvm/book3s_64_entry.S b/arch/powerpc/kvm/book3s_64_entry.S index 983b8c18bc31..05e003eb5d90 100644 --- a/arch/powerpc/kvm/book3s_64_entry.S +++ b/arch/powerpc/kvm/book3s_64_entry.S @@ -374,11 +374,16 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX) BEGIN_FTR_SECTION mtspr SPRN_DAWRX1,r10 END_FTR_SECTION_IFSET(CPU_FTR_DAWR1) - mtspr SPRN_PID,r10 /* - * Switch to host MMU mode + * Switch to host MMU mode (don't have the real host PID but we aren't + * going back to userspace). */ + hwsync + isync + + mtspr SPRN_PID,r10 + ld r10, HSTATE_KVM_VCPU(r13) ld r10, VCPU_KVM(r10) lwz r10, KVM_HOST_LPID(r10) @@ -389,6 +394,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_DAWR1) ld r10, KVM_HOST_LPCR(r10) mtspr SPRN_LPCR,r10 + isync + /* * Set GUEST_MODE_NONE so the handler won't branch to KVM, and clear * MSR_RI in r12 ([H]SRR1) so the handler won't try to return. diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c index feee40cb2ba1..61290282fd9e 100644 --- a/arch/powerpc/kvm/book3s_64_mmu.c +++ b/arch/powerpc/kvm/book3s_64_mmu.c @@ -530,7 +530,7 @@ static void kvmppc_mmu_book3s_64_tlbie(struct kvm_vcpu *vcpu, ulong va, bool large) { u64 mask = 0xFFFFFFFFFULL; - long i; + unsigned long i; struct kvm_vcpu *v; dprintk("KVM MMU: tlbie(0x%lx)\n", va); diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index c63e263312a4..213232914367 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -734,11 +734,11 @@ void kvmppc_rmap_reset(struct kvm *kvm) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; - int srcu_idx; + int srcu_idx, bkt; srcu_idx = srcu_read_lock(&kvm->srcu); slots = kvm_memslots(kvm); - kvm_for_each_memslot(memslot, slots) { + kvm_for_each_memslot(memslot, bkt, slots) { /* Mutual exclusion with kvm_unmap_hva_range etc. */ spin_lock(&kvm->mmu_lock); /* diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index 16359525a40f..8cebe5542256 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -57,6 +57,8 @@ unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid, preempt_disable(); + asm volatile("hwsync" ::: "memory"); + isync(); /* switch the lpid first to avoid running host with unallocated pid */ old_lpid = mfspr(SPRN_LPID); if (old_lpid != lpid) @@ -75,6 +77,8 @@ unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid, ret = __copy_to_user_inatomic((void __user *)to, from, n); pagefault_enable(); + asm volatile("hwsync" ::: "memory"); + isync(); /* switch the pid first to avoid running host with unallocated pid */ if (quadrant == 1 && pid != old_pid) mtspr(SPRN_PID, old_pid); diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 7b74fc0a986b..d1817cd9a691 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -80,6 +80,7 @@ #include <asm/plpar_wrappers.h> #include "book3s.h" +#include "book3s_hv.h" #define CREATE_TRACE_POINTS #include "trace_hv.h" @@ -127,11 +128,6 @@ static bool nested = true; module_param(nested, bool, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(nested, "Enable nested virtualization (only on POWER9)"); -static inline bool nesting_enabled(struct kvm *kvm) -{ - return kvm->arch.nested_enable && kvm_is_radix(kvm); -} - static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu); /* @@ -276,22 +272,26 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu) * they should never fail.) */ -static void kvmppc_core_start_stolen(struct kvmppc_vcore *vc) +static void kvmppc_core_start_stolen(struct kvmppc_vcore *vc, u64 tb) { unsigned long flags; + WARN_ON_ONCE(cpu_has_feature(CPU_FTR_ARCH_300)); + spin_lock_irqsave(&vc->stoltb_lock, flags); - vc->preempt_tb = mftb(); + vc->preempt_tb = tb; spin_unlock_irqrestore(&vc->stoltb_lock, flags); } -static void kvmppc_core_end_stolen(struct kvmppc_vcore *vc) +static void kvmppc_core_end_stolen(struct kvmppc_vcore *vc, u64 tb) { unsigned long flags; + WARN_ON_ONCE(cpu_has_feature(CPU_FTR_ARCH_300)); + spin_lock_irqsave(&vc->stoltb_lock, flags); if (vc->preempt_tb != TB_NIL) { - vc->stolen_tb += mftb() - vc->preempt_tb; + vc->stolen_tb += tb - vc->preempt_tb; vc->preempt_tb = TB_NIL; } spin_unlock_irqrestore(&vc->stoltb_lock, flags); @@ -301,6 +301,12 @@ static void kvmppc_core_vcpu_load_hv(struct kvm_vcpu *vcpu, int cpu) { struct kvmppc_vcore *vc = vcpu->arch.vcore; unsigned long flags; + u64 now; + + if (cpu_has_feature(CPU_FTR_ARCH_300)) + return; + + now = mftb(); /* * We can test vc->runner without taking the vcore lock, @@ -309,12 +315,12 @@ static void kvmppc_core_vcpu_load_hv(struct kvm_vcpu *vcpu, int cpu) * ever sets it to NULL. */ if (vc->runner == vcpu && vc->vcore_state >= VCORE_SLEEPING) - kvmppc_core_end_stolen(vc); + kvmppc_core_end_stolen(vc, now); spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags); if (vcpu->arch.state == KVMPPC_VCPU_BUSY_IN_HOST && vcpu->arch.busy_preempt != TB_NIL) { - vcpu->arch.busy_stolen += mftb() - vcpu->arch.busy_preempt; + vcpu->arch.busy_stolen += now - vcpu->arch.busy_preempt; vcpu->arch.busy_preempt = TB_NIL; } spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags); @@ -324,13 +330,19 @@ static void kvmppc_core_vcpu_put_hv(struct kvm_vcpu *vcpu) { struct kvmppc_vcore *vc = vcpu->arch.vcore; unsigned long flags; + u64 now; + + if (cpu_has_feature(CPU_FTR_ARCH_300)) + return; + + now = mftb(); if (vc->runner == vcpu && vc->vcore_state >= VCORE_SLEEPING) - kvmppc_core_start_stolen(vc); + kvmppc_core_start_stolen(vc, now); spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags); if (vcpu->arch.state == KVMPPC_VCPU_BUSY_IN_HOST) - vcpu->arch.busy_preempt = mftb(); + vcpu->arch.busy_preempt = now; spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags); } @@ -675,6 +687,8 @@ static u64 vcore_stolen_time(struct kvmppc_vcore *vc, u64 now) u64 p; unsigned long flags; + WARN_ON_ONCE(cpu_has_feature(CPU_FTR_ARCH_300)); + spin_lock_irqsave(&vc->stoltb_lock, flags); p = vc->stolen_tb; if (vc->vcore_state != VCORE_INACTIVE && @@ -684,35 +698,30 @@ static u64 vcore_stolen_time(struct kvmppc_vcore *vc, u64 now) return p; } -static void kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu, - struct kvmppc_vcore *vc) +static void __kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu, + unsigned int pcpu, u64 now, + unsigned long stolen) { struct dtl_entry *dt; struct lppaca *vpa; - unsigned long stolen; - unsigned long core_stolen; - u64 now; - unsigned long flags; dt = vcpu->arch.dtl_ptr; vpa = vcpu->arch.vpa.pinned_addr; - now = mftb(); - core_stolen = vcore_stolen_time(vc, now); - stolen = core_stolen - vcpu->arch.stolen_logged; - vcpu->arch.stolen_logged = core_stolen; - spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags); - stolen += vcpu->arch.busy_stolen; - vcpu->arch.busy_stolen = 0; - spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags); + if (!dt || !vpa) return; - memset(dt, 0, sizeof(struct dtl_entry)); + dt->dispatch_reason = 7; - dt->processor_id = cpu_to_be16(vc->pcpu + vcpu->arch.ptid); - dt->timebase = cpu_to_be64(now + vc->tb_offset); + dt->preempt_reason = 0; + dt->processor_id = cpu_to_be16(pcpu + vcpu->arch.ptid); dt->enqueue_to_dispatch_time = cpu_to_be32(stolen); + dt->ready_to_enqueue_time = 0; + dt->waiting_to_ready_time = 0; + dt->timebase = cpu_to_be64(now); + dt->fault_addr = 0; dt->srr0 = cpu_to_be64(kvmppc_get_pc(vcpu)); dt->srr1 = cpu_to_be64(vcpu->arch.shregs.msr); + ++dt; if (dt == vcpu->arch.dtl.pinned_end) dt = vcpu->arch.dtl.pinned_addr; @@ -723,6 +732,27 @@ static void kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu, vcpu->arch.dtl.dirty = true; } +static void kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu, + struct kvmppc_vcore *vc) +{ + unsigned long stolen; + unsigned long core_stolen; + u64 now; + unsigned long flags; + + now = mftb(); + + core_stolen = vcore_stolen_time(vc, now); + stolen = core_stolen - vcpu->arch.stolen_logged; + vcpu->arch.stolen_logged = core_stolen; + spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags); + stolen += vcpu->arch.busy_stolen; + vcpu->arch.busy_stolen = 0; + spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags); + + __kvmppc_create_dtl_entry(vcpu, vc->pcpu, now + vc->tb_offset, stolen); +} + /* See if there is a doorbell interrupt pending for a vcpu */ static bool kvmppc_doorbell_pending(struct kvm_vcpu *vcpu) { @@ -731,6 +761,8 @@ static bool kvmppc_doorbell_pending(struct kvm_vcpu *vcpu) if (vcpu->arch.doorbell_request) return true; + if (cpu_has_feature(CPU_FTR_ARCH_300)) + return false; /* * Ensure that the read of vcore->dpdes comes after the read * of vcpu->doorbell_request. This barrier matches the @@ -900,13 +932,14 @@ static int kvm_arch_vcpu_yield_to(struct kvm_vcpu *target) * mode handler is not called but no other threads are in the * source vcore. */ - - spin_lock(&vcore->lock); - if (target->arch.state == KVMPPC_VCPU_RUNNABLE && - vcore->vcore_state != VCORE_INACTIVE && - vcore->runner) - target = vcore->runner; - spin_unlock(&vcore->lock); + if (!cpu_has_feature(CPU_FTR_ARCH_300)) { + spin_lock(&vcore->lock); + if (target->arch.state == KVMPPC_VCPU_RUNNABLE && + vcore->vcore_state != VCORE_INACTIVE && + vcore->runner) + target = vcore->runner; + spin_unlock(&vcore->lock); + } return kvm_vcpu_yield_to(target); } @@ -1421,6 +1454,43 @@ static int kvmppc_emulate_doorbell_instr(struct kvm_vcpu *vcpu) return RESUME_GUEST; } +/* + * If the lppaca had pmcregs_in_use clear when we exited the guest, then + * HFSCR_PM is cleared for next entry. If the guest then tries to access + * the PMU SPRs, we get this facility unavailable interrupt. Putting HFSCR_PM + * back in the guest HFSCR will cause the next entry to load the PMU SPRs and + * allow the guest access to continue. + */ +static int kvmppc_pmu_unavailable(struct kvm_vcpu *vcpu) +{ + if (!(vcpu->arch.hfscr_permitted & HFSCR_PM)) + return EMULATE_FAIL; + + vcpu->arch.hfscr |= HFSCR_PM; + + return RESUME_GUEST; +} + +static int kvmppc_ebb_unavailable(struct kvm_vcpu *vcpu) +{ + if (!(vcpu->arch.hfscr_permitted & HFSCR_EBB)) + return EMULATE_FAIL; + + vcpu->arch.hfscr |= HFSCR_EBB; + + return RESUME_GUEST; +} + +static int kvmppc_tm_unavailable(struct kvm_vcpu *vcpu) +{ + if (!(vcpu->arch.hfscr_permitted & HFSCR_TM)) + return EMULATE_FAIL; + + vcpu->arch.hfscr |= HFSCR_TM; + + return RESUME_GUEST; +} + static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, struct task_struct *tsk) { @@ -1451,6 +1521,10 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, run->ready_for_interrupt_injection = 1; switch (vcpu->arch.trap) { /* We're good on these - the host merely wanted to get our attention */ + case BOOK3S_INTERRUPT_NESTED_HV_DECREMENTER: + WARN_ON_ONCE(1); /* Should never happen */ + vcpu->arch.trap = BOOK3S_INTERRUPT_HV_DECREMENTER; + fallthrough; case BOOK3S_INTERRUPT_HV_DECREMENTER: vcpu->stat.dec_exits++; r = RESUME_GUEST; @@ -1575,7 +1649,8 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, unsigned long vsid; long err; - if (vcpu->arch.fault_dsisr == HDSISR_CANARY) { + if (cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG) && + unlikely(vcpu->arch.fault_dsisr == HDSISR_CANARY)) { r = RESUME_GUEST; /* Just retry if it's the canary */ break; } @@ -1702,16 +1777,26 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, * to emulate. * Otherwise, we just generate a program interrupt to the guest. */ - case BOOK3S_INTERRUPT_H_FAC_UNAVAIL: + case BOOK3S_INTERRUPT_H_FAC_UNAVAIL: { + u64 cause = vcpu->arch.hfscr >> 56; + r = EMULATE_FAIL; - if (((vcpu->arch.hfscr >> 56) == FSCR_MSGP_LG) && - cpu_has_feature(CPU_FTR_ARCH_300)) - r = kvmppc_emulate_doorbell_instr(vcpu); + if (cpu_has_feature(CPU_FTR_ARCH_300)) { + if (cause == FSCR_MSGP_LG) + r = kvmppc_emulate_doorbell_instr(vcpu); + if (cause == FSCR_PM_LG) + r = kvmppc_pmu_unavailable(vcpu); + if (cause == FSCR_EBB_LG) + r = kvmppc_ebb_unavailable(vcpu); + if (cause == FSCR_TM_LG) + r = kvmppc_tm_unavailable(vcpu); + } if (r == EMULATE_FAIL) { kvmppc_core_queue_program(vcpu, SRR1_PROGILL); r = RESUME_GUEST; } break; + } case BOOK3S_INTERRUPT_HV_RM_HARD: r = RESUME_PASSTHROUGH; @@ -1768,6 +1853,12 @@ static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu) vcpu->stat.ext_intr_exits++; r = RESUME_GUEST; break; + /* These need to go to the nested HV */ + case BOOK3S_INTERRUPT_NESTED_HV_DECREMENTER: + vcpu->arch.trap = BOOK3S_INTERRUPT_HV_DECREMENTER; + vcpu->stat.dec_exits++; + r = RESUME_HOST; + break; /* SR/HMI/PMI are HV interrupts that host has handled. Resume guest.*/ case BOOK3S_INTERRUPT_HMI: case BOOK3S_INTERRUPT_PERFMON: @@ -1993,7 +2084,7 @@ static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr, */ if ((new_lpcr & LPCR_ILE) != (vc->lpcr & LPCR_ILE)) { struct kvm_vcpu *vcpu; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu->arch.vcore != vc) @@ -2096,8 +2187,10 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, * either vcore->dpdes or doorbell_request. * On POWER8, doorbell_request is 0. */ - *val = get_reg_val(id, vcpu->arch.vcore->dpdes | - vcpu->arch.doorbell_request); + if (cpu_has_feature(CPU_FTR_ARCH_300)) + *val = get_reg_val(id, vcpu->arch.doorbell_request); + else + *val = get_reg_val(id, vcpu->arch.vcore->dpdes); break; case KVM_REG_PPC_VTB: *val = get_reg_val(id, vcpu->arch.vcore->vtb); @@ -2238,8 +2331,7 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, *val = get_reg_val(id, vcpu->arch.vcore->arch_compat); break; case KVM_REG_PPC_DEC_EXPIRY: - *val = get_reg_val(id, vcpu->arch.dec_expires + - vcpu->arch.vcore->tb_offset); + *val = get_reg_val(id, vcpu->arch.dec_expires); break; case KVM_REG_PPC_ONLINE: *val = get_reg_val(id, vcpu->arch.online); @@ -2335,7 +2427,10 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, vcpu->arch.pspb = set_reg_val(id, *val); break; case KVM_REG_PPC_DPDES: - vcpu->arch.vcore->dpdes = set_reg_val(id, *val); + if (cpu_has_feature(CPU_FTR_ARCH_300)) + vcpu->arch.doorbell_request = set_reg_val(id, *val) & 1; + else + vcpu->arch.vcore->dpdes = set_reg_val(id, *val); break; case KVM_REG_PPC_VTB: vcpu->arch.vcore->vtb = set_reg_val(id, *val); @@ -2491,8 +2586,7 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, r = kvmppc_set_arch_compat(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_DEC_EXPIRY: - vcpu->arch.dec_expires = set_reg_val(id, *val) - - vcpu->arch.vcore->tb_offset; + vcpu->arch.dec_expires = set_reg_val(id, *val); break; case KVM_REG_PPC_ONLINE: i = set_reg_val(id, *val); @@ -2715,6 +2809,11 @@ static int kvmppc_core_vcpu_create_hv(struct kvm_vcpu *vcpu) #endif #endif vcpu->arch.mmcr[0] = MMCR0_FC; + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + vcpu->arch.mmcr[0] |= MMCR0_PMCCEXT; + vcpu->arch.mmcra = MMCRA_BHRB_DISABLE; + } + vcpu->arch.ctrl = CTRL_RUNLATCH; /* default to host PVR, since we can't spoof it */ kvmppc_set_pvr_hv(vcpu, mfspr(SPRN_PVR)); @@ -2745,6 +2844,11 @@ static int kvmppc_core_vcpu_create_hv(struct kvm_vcpu *vcpu) vcpu->arch.hfscr_permitted = vcpu->arch.hfscr; + /* + * PM, EBB, TM are demand-faulted so start with it clear. + */ + vcpu->arch.hfscr &= ~(HFSCR_PM | HFSCR_EBB | HFSCR_TM); + kvmppc_mmu_book3s_hv_init(vcpu); vcpu->arch.state = KVMPPC_VCPU_NOTREADY; @@ -2869,13 +2973,13 @@ static void kvmppc_set_timer(struct kvm_vcpu *vcpu) unsigned long dec_nsec, now; now = get_tb(); - if (now > vcpu->arch.dec_expires) { + if (now > kvmppc_dec_expires_host_tb(vcpu)) { /* decrementer has already gone negative */ kvmppc_core_queue_dec(vcpu); kvmppc_core_prepare_to_enter(vcpu); return; } - dec_nsec = tb_to_ns(vcpu->arch.dec_expires - now); + dec_nsec = tb_to_ns(kvmppc_dec_expires_host_tb(vcpu) - now); hrtimer_start(&vcpu->arch.dec_timer, dec_nsec, HRTIMER_MODE_REL); vcpu->arch.timer_running = 1; } @@ -2883,14 +2987,14 @@ static void kvmppc_set_timer(struct kvm_vcpu *vcpu) extern int __kvmppc_vcore_entry(void); static void kvmppc_remove_runnable(struct kvmppc_vcore *vc, - struct kvm_vcpu *vcpu) + struct kvm_vcpu *vcpu, u64 tb) { u64 now; if (vcpu->arch.state != KVMPPC_VCPU_RUNNABLE) return; spin_lock_irq(&vcpu->arch.tbacct_lock); - now = mftb(); + now = tb; vcpu->arch.busy_stolen += vcore_stolen_time(vc, now) - vcpu->arch.stolen_logged; vcpu->arch.busy_preempt = now; @@ -2945,30 +3049,59 @@ static void kvmppc_release_hwthread(int cpu) tpaca->kvm_hstate.kvm_split_mode = NULL; } +static DEFINE_PER_CPU(struct kvm *, cpu_in_guest); + static void radix_flush_cpu(struct kvm *kvm, int cpu, struct kvm_vcpu *vcpu) { struct kvm_nested_guest *nested = vcpu->arch.nested; - cpumask_t *cpu_in_guest; + cpumask_t *need_tlb_flush; int i; + if (nested) + need_tlb_flush = &nested->need_tlb_flush; + else + need_tlb_flush = &kvm->arch.need_tlb_flush; + cpu = cpu_first_tlb_thread_sibling(cpu); - if (nested) { - cpumask_set_cpu(cpu, &nested->need_tlb_flush); - cpu_in_guest = &nested->cpu_in_guest; - } else { - cpumask_set_cpu(cpu, &kvm->arch.need_tlb_flush); - cpu_in_guest = &kvm->arch.cpu_in_guest; - } + for (i = cpu; i <= cpu_last_tlb_thread_sibling(cpu); + i += cpu_tlb_thread_sibling_step()) + cpumask_set_cpu(i, need_tlb_flush); + /* - * Make sure setting of bit in need_tlb_flush precedes - * testing of cpu_in_guest bits. The matching barrier on - * the other side is the first smp_mb() in kvmppc_run_core(). + * Make sure setting of bit in need_tlb_flush precedes testing of + * cpu_in_guest. The matching barrier on the other side is hwsync + * when switching to guest MMU mode, which happens between + * cpu_in_guest being set to the guest kvm, and need_tlb_flush bit + * being tested. */ smp_mb(); + for (i = cpu; i <= cpu_last_tlb_thread_sibling(cpu); - i += cpu_tlb_thread_sibling_step()) - if (cpumask_test_cpu(i, cpu_in_guest)) + i += cpu_tlb_thread_sibling_step()) { + struct kvm *running = *per_cpu_ptr(&cpu_in_guest, i); + + if (running == kvm) smp_call_function_single(i, do_nothing, NULL, 1); + } +} + +static void do_migrate_away_vcpu(void *arg) +{ + struct kvm_vcpu *vcpu = arg; + struct kvm *kvm = vcpu->kvm; + + /* + * If the guest has GTSE, it may execute tlbie, so do a eieio; tlbsync; + * ptesync sequence on the old CPU before migrating to a new one, in + * case we interrupted the guest between a tlbie ; eieio ; + * tlbsync; ptesync sequence. + * + * Otherwise, ptesync is sufficient for ordering tlbiel sequences. + */ + if (kvm->arch.lpcr & LPCR_GTSE) + asm volatile("eieio; tlbsync; ptesync"); + else + asm volatile("ptesync"); } static void kvmppc_prepare_radix_vcpu(struct kvm_vcpu *vcpu, int pcpu) @@ -2994,14 +3127,17 @@ static void kvmppc_prepare_radix_vcpu(struct kvm_vcpu *vcpu, int pcpu) * can move around between pcpus. To cope with this, when * a vcpu moves from one pcpu to another, we need to tell * any vcpus running on the same core as this vcpu previously - * ran to flush the TLB. The TLB is shared between threads, - * so we use a single bit in .need_tlb_flush for all 4 threads. + * ran to flush the TLB. */ if (prev_cpu != pcpu) { - if (prev_cpu >= 0 && - cpu_first_tlb_thread_sibling(prev_cpu) != - cpu_first_tlb_thread_sibling(pcpu)) - radix_flush_cpu(kvm, prev_cpu, vcpu); + if (prev_cpu >= 0) { + if (cpu_first_tlb_thread_sibling(prev_cpu) != + cpu_first_tlb_thread_sibling(pcpu)) + radix_flush_cpu(kvm, prev_cpu, vcpu); + + smp_call_function_single(prev_cpu, + do_migrate_away_vcpu, vcpu, 1); + } if (nested) nested->prev_cpu[vcpu->arch.nested_vcpu_id] = pcpu; else @@ -3013,7 +3149,6 @@ static void kvmppc_start_thread(struct kvm_vcpu *vcpu, struct kvmppc_vcore *vc) { int cpu; struct paca_struct *tpaca; - struct kvm *kvm = vc->kvm; cpu = vc->pcpu; if (vcpu) { @@ -3024,7 +3159,6 @@ static void kvmppc_start_thread(struct kvm_vcpu *vcpu, struct kvmppc_vcore *vc) cpu += vcpu->arch.ptid; vcpu->cpu = vc->pcpu; vcpu->arch.thread_cpu = cpu; - cpumask_set_cpu(cpu, &kvm->arch.cpu_in_guest); } tpaca = paca_ptrs[cpu]; tpaca->kvm_hstate.kvm_vcpu = vcpu; @@ -3125,6 +3259,8 @@ static void kvmppc_vcore_preempt(struct kvmppc_vcore *vc) { struct preempted_vcore_list *lp = this_cpu_ptr(&preempted_vcores); + WARN_ON_ONCE(cpu_has_feature(CPU_FTR_ARCH_300)); + vc->vcore_state = VCORE_PREEMPT; vc->pcpu = smp_processor_id(); if (vc->num_threads < threads_per_vcore(vc->kvm)) { @@ -3134,14 +3270,16 @@ static void kvmppc_vcore_preempt(struct kvmppc_vcore *vc) } /* Start accumulating stolen time */ - kvmppc_core_start_stolen(vc); + kvmppc_core_start_stolen(vc, mftb()); } static void kvmppc_vcore_end_preempt(struct kvmppc_vcore *vc) { struct preempted_vcore_list *lp; - kvmppc_core_end_stolen(vc); + WARN_ON_ONCE(cpu_has_feature(CPU_FTR_ARCH_300)); + + kvmppc_core_end_stolen(vc, mftb()); if (!list_empty(&vc->preempt_list)) { lp = &per_cpu(preempted_vcores, vc->pcpu); spin_lock(&lp->lock); @@ -3268,7 +3406,7 @@ static void prepare_threads(struct kvmppc_vcore *vc) vcpu->arch.ret = RESUME_GUEST; else continue; - kvmppc_remove_runnable(vc, vcpu); + kvmppc_remove_runnable(vc, vcpu, mftb()); wake_up(&vcpu->arch.cpu_run); } } @@ -3287,7 +3425,7 @@ static void collect_piggybacks(struct core_info *cip, int target_threads) list_del_init(&pvc->preempt_list); if (pvc->runner == NULL) { pvc->vcore_state = VCORE_INACTIVE; - kvmppc_core_end_stolen(pvc); + kvmppc_core_end_stolen(pvc, mftb()); } spin_unlock(&pvc->lock); continue; @@ -3296,7 +3434,7 @@ static void collect_piggybacks(struct core_info *cip, int target_threads) spin_unlock(&pvc->lock); continue; } - kvmppc_core_end_stolen(pvc); + kvmppc_core_end_stolen(pvc, mftb()); pvc->vcore_state = VCORE_PIGGYBACK; if (cip->total_threads >= target_threads) break; @@ -3340,7 +3478,7 @@ static void post_guest_process(struct kvmppc_vcore *vc, bool is_master) */ spin_unlock(&vc->lock); /* cancel pending dec exception if dec is positive */ - if (now < vcpu->arch.dec_expires && + if (now < kvmppc_dec_expires_host_tb(vcpu) && kvmppc_core_pending_dec(vcpu)) kvmppc_core_dequeue_dec(vcpu); @@ -3363,7 +3501,7 @@ static void post_guest_process(struct kvmppc_vcore *vc, bool is_master) else ++still_running; } else { - kvmppc_remove_runnable(vc, vcpu); + kvmppc_remove_runnable(vc, vcpu, mftb()); wake_up(&vcpu->arch.cpu_run); } } @@ -3372,7 +3510,7 @@ static void post_guest_process(struct kvmppc_vcore *vc, bool is_master) kvmppc_vcore_preempt(vc); } else if (vc->runner) { vc->vcore_state = VCORE_PREEMPT; - kvmppc_core_start_stolen(vc); + kvmppc_core_start_stolen(vc, mftb()); } else { vc->vcore_state = VCORE_INACTIVE; } @@ -3503,7 +3641,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) ((vc->num_threads > threads_per_subcore) || !on_primary_thread())) { for_each_runnable_thread(i, vcpu, vc) { vcpu->arch.ret = -EBUSY; - kvmppc_remove_runnable(vc, vcpu); + kvmppc_remove_runnable(vc, vcpu, mftb()); wake_up(&vcpu->arch.cpu_run); } goto out; @@ -3748,7 +3886,6 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) kvmppc_release_hwthread(pcpu + i); if (sip && sip->napped[i]) kvmppc_ipi_thread(pcpu + i); - cpumask_clear_cpu(pcpu + i, &vc->kvm->arch.cpu_in_guest); } spin_unlock(&vc->lock); @@ -3770,211 +3907,137 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) trace_kvmppc_run_core(vc, 1); } -static void load_spr_state(struct kvm_vcpu *vcpu) -{ - mtspr(SPRN_DSCR, vcpu->arch.dscr); - mtspr(SPRN_IAMR, vcpu->arch.iamr); - mtspr(SPRN_PSPB, vcpu->arch.pspb); - mtspr(SPRN_FSCR, vcpu->arch.fscr); - mtspr(SPRN_TAR, vcpu->arch.tar); - mtspr(SPRN_EBBHR, vcpu->arch.ebbhr); - mtspr(SPRN_EBBRR, vcpu->arch.ebbrr); - mtspr(SPRN_BESCR, vcpu->arch.bescr); - mtspr(SPRN_TIDR, vcpu->arch.tid); - mtspr(SPRN_AMR, vcpu->arch.amr); - mtspr(SPRN_UAMOR, vcpu->arch.uamor); - - /* - * DAR, DSISR, and for nested HV, SPRGs must be set with MSR[RI] - * clear (or hstate set appropriately to catch those registers - * being clobbered if we take a MCE or SRESET), so those are done - * later. - */ - - if (!(vcpu->arch.ctrl & 1)) - mtspr(SPRN_CTRLT, mfspr(SPRN_CTRLF) & ~1); -} - -static void store_spr_state(struct kvm_vcpu *vcpu) -{ - vcpu->arch.ctrl = mfspr(SPRN_CTRLF); - - vcpu->arch.iamr = mfspr(SPRN_IAMR); - vcpu->arch.pspb = mfspr(SPRN_PSPB); - vcpu->arch.fscr = mfspr(SPRN_FSCR); - vcpu->arch.tar = mfspr(SPRN_TAR); - vcpu->arch.ebbhr = mfspr(SPRN_EBBHR); - vcpu->arch.ebbrr = mfspr(SPRN_EBBRR); - vcpu->arch.bescr = mfspr(SPRN_BESCR); - vcpu->arch.tid = mfspr(SPRN_TIDR); - vcpu->arch.amr = mfspr(SPRN_AMR); - vcpu->arch.uamor = mfspr(SPRN_UAMOR); - vcpu->arch.dscr = mfspr(SPRN_DSCR); -} - -/* - * Privileged (non-hypervisor) host registers to save. - */ -struct p9_host_os_sprs { - unsigned long dscr; - unsigned long tidr; - unsigned long iamr; - unsigned long amr; - unsigned long fscr; -}; - -static void save_p9_host_os_sprs(struct p9_host_os_sprs *host_os_sprs) -{ - host_os_sprs->dscr = mfspr(SPRN_DSCR); - host_os_sprs->tidr = mfspr(SPRN_TIDR); - host_os_sprs->iamr = mfspr(SPRN_IAMR); - host_os_sprs->amr = mfspr(SPRN_AMR); - host_os_sprs->fscr = mfspr(SPRN_FSCR); -} - -/* vcpu guest regs must already be saved */ -static void restore_p9_host_os_sprs(struct kvm_vcpu *vcpu, - struct p9_host_os_sprs *host_os_sprs) -{ - mtspr(SPRN_PSPB, 0); - mtspr(SPRN_UAMOR, 0); - - mtspr(SPRN_DSCR, host_os_sprs->dscr); - mtspr(SPRN_TIDR, host_os_sprs->tidr); - mtspr(SPRN_IAMR, host_os_sprs->iamr); - - if (host_os_sprs->amr != vcpu->arch.amr) - mtspr(SPRN_AMR, host_os_sprs->amr); - - if (host_os_sprs->fscr != vcpu->arch.fscr) - mtspr(SPRN_FSCR, host_os_sprs->fscr); - - /* Save guest CTRL register, set runlatch to 1 */ - if (!(vcpu->arch.ctrl & 1)) - mtspr(SPRN_CTRLT, 1); -} - static inline bool hcall_is_xics(unsigned long req) { return req == H_EOI || req == H_CPPR || req == H_IPI || req == H_IPOLL || req == H_XIRR || req == H_XIRR_X; } -/* - * Guest entry for POWER9 and later CPUs. - */ -static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, - unsigned long lpcr) +static void vcpu_vpa_increment_dispatch(struct kvm_vcpu *vcpu) +{ + struct lppaca *lp = vcpu->arch.vpa.pinned_addr; + if (lp) { + u32 yield_count = be32_to_cpu(lp->yield_count) + 1; + lp->yield_count = cpu_to_be32(yield_count); + vcpu->arch.vpa.dirty = 1; + } +} + +/* call our hypervisor to load up HV regs and go */ +static int kvmhv_vcpu_entry_p9_nested(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpcr, u64 *tb) { struct kvmppc_vcore *vc = vcpu->arch.vcore; + unsigned long host_psscr; + unsigned long msr; + struct hv_guest_state hvregs; struct p9_host_os_sprs host_os_sprs; s64 dec; - u64 tb; - int trap, save_pmu; + int trap; - WARN_ON_ONCE(vcpu->arch.ceded); - - dec = mfspr(SPRN_DEC); - tb = mftb(); - if (dec < 0) - return BOOK3S_INTERRUPT_HV_DECREMENTER; - local_paca->kvm_hstate.dec_expires = dec + tb; - if (local_paca->kvm_hstate.dec_expires < time_limit) - time_limit = local_paca->kvm_hstate.dec_expires; + msr = mfmsr(); save_p9_host_os_sprs(&host_os_sprs); - kvmhv_save_host_pmu(); /* saves it to PACA kvm_hstate */ + /* + * We need to save and restore the guest visible part of the + * psscr (i.e. using SPRN_PSSCR_PR) since the hypervisor + * doesn't do this for us. Note only required if pseries since + * this is done in kvmhv_vcpu_entry_p9() below otherwise. + */ + host_psscr = mfspr(SPRN_PSSCR_PR); - kvmppc_subcore_enter_guest(); + kvmppc_msr_hard_disable_set_facilities(vcpu, msr); + if (lazy_irq_pending()) + return 0; - vc->entry_exit_map = 1; - vc->in_guest = 1; + if (unlikely(load_vcpu_state(vcpu, &host_os_sprs))) + msr = mfmsr(); /* TM restore can update msr */ - if (vcpu->arch.vpa.pinned_addr) { - struct lppaca *lp = vcpu->arch.vpa.pinned_addr; - u32 yield_count = be32_to_cpu(lp->yield_count) + 1; - lp->yield_count = cpu_to_be32(yield_count); - vcpu->arch.vpa.dirty = 1; - } - - if (cpu_has_feature(CPU_FTR_TM) || - cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) - kvmppc_restore_tm_hv(vcpu, vcpu->arch.shregs.msr, true); + if (vcpu->arch.psscr != host_psscr) + mtspr(SPRN_PSSCR_PR, vcpu->arch.psscr); -#ifdef CONFIG_PPC_PSERIES - if (kvmhv_on_pseries()) { - barrier(); - if (vcpu->arch.vpa.pinned_addr) { - struct lppaca *lp = vcpu->arch.vpa.pinned_addr; - get_lppaca()->pmcregs_in_use = lp->pmcregs_in_use; - } else { - get_lppaca()->pmcregs_in_use = 1; - } - barrier(); + kvmhv_save_hv_regs(vcpu, &hvregs); + hvregs.lpcr = lpcr; + vcpu->arch.regs.msr = vcpu->arch.shregs.msr; + hvregs.version = HV_GUEST_STATE_VERSION; + if (vcpu->arch.nested) { + hvregs.lpid = vcpu->arch.nested->shadow_lpid; + hvregs.vcpu_token = vcpu->arch.nested_vcpu_id; + } else { + hvregs.lpid = vcpu->kvm->arch.lpid; + hvregs.vcpu_token = vcpu->vcpu_id; } -#endif - kvmhv_load_guest_pmu(vcpu); - - msr_check_and_set(MSR_FP | MSR_VEC | MSR_VSX); - load_fp_state(&vcpu->arch.fp); -#ifdef CONFIG_ALTIVEC - load_vr_state(&vcpu->arch.vr); -#endif - mtspr(SPRN_VRSAVE, vcpu->arch.vrsave); - - load_spr_state(vcpu); + hvregs.hdec_expiry = time_limit; /* - * When setting DEC, we must always deal with irq_work_raise via NMI vs - * setting DEC. The problem occurs right as we switch into guest mode - * if a NMI hits and sets pending work and sets DEC, then that will - * apply to the guest and not bring us back to the host. + * When setting DEC, we must always deal with irq_work_raise + * via NMI vs setting DEC. The problem occurs right as we + * switch into guest mode if a NMI hits and sets pending work + * and sets DEC, then that will apply to the guest and not + * bring us back to the host. * - * irq_work_raise could check a flag (or possibly LPCR[HDICE] for - * example) and set HDEC to 1? That wouldn't solve the nested hv - * case which needs to abort the hcall or zero the time limit. + * irq_work_raise could check a flag (or possibly LPCR[HDICE] + * for example) and set HDEC to 1? That wouldn't solve the + * nested hv case which needs to abort the hcall or zero the + * time limit. * * XXX: Another day's problem. */ - mtspr(SPRN_DEC, vcpu->arch.dec_expires - mftb()); + mtspr(SPRN_DEC, kvmppc_dec_expires_host_tb(vcpu) - *tb); + + mtspr(SPRN_DAR, vcpu->arch.shregs.dar); + mtspr(SPRN_DSISR, vcpu->arch.shregs.dsisr); + switch_pmu_to_guest(vcpu, &host_os_sprs); + trap = plpar_hcall_norets(H_ENTER_NESTED, __pa(&hvregs), + __pa(&vcpu->arch.regs)); + kvmhv_restore_hv_return_state(vcpu, &hvregs); + switch_pmu_to_host(vcpu, &host_os_sprs); + vcpu->arch.shregs.msr = vcpu->arch.regs.msr; + vcpu->arch.shregs.dar = mfspr(SPRN_DAR); + vcpu->arch.shregs.dsisr = mfspr(SPRN_DSISR); + vcpu->arch.psscr = mfspr(SPRN_PSSCR_PR); + + store_vcpu_state(vcpu); - if (kvmhv_on_pseries()) { - /* - * We need to save and restore the guest visible part of the - * psscr (i.e. using SPRN_PSSCR_PR) since the hypervisor - * doesn't do this for us. Note only required if pseries since - * this is done in kvmhv_vcpu_entry_p9() below otherwise. - */ - unsigned long host_psscr; - /* call our hypervisor to load up HV regs and go */ - struct hv_guest_state hvregs; + dec = mfspr(SPRN_DEC); + if (!(lpcr & LPCR_LD)) /* Sign extend if not using large decrementer */ + dec = (s32) dec; + *tb = mftb(); + vcpu->arch.dec_expires = dec + (*tb + vc->tb_offset); - host_psscr = mfspr(SPRN_PSSCR_PR); - mtspr(SPRN_PSSCR_PR, vcpu->arch.psscr); - kvmhv_save_hv_regs(vcpu, &hvregs); - hvregs.lpcr = lpcr; - vcpu->arch.regs.msr = vcpu->arch.shregs.msr; - hvregs.version = HV_GUEST_STATE_VERSION; - if (vcpu->arch.nested) { - hvregs.lpid = vcpu->arch.nested->shadow_lpid; - hvregs.vcpu_token = vcpu->arch.nested_vcpu_id; - } else { - hvregs.lpid = vcpu->kvm->arch.lpid; - hvregs.vcpu_token = vcpu->vcpu_id; - } - hvregs.hdec_expiry = time_limit; - mtspr(SPRN_DAR, vcpu->arch.shregs.dar); - mtspr(SPRN_DSISR, vcpu->arch.shregs.dsisr); - trap = plpar_hcall_norets(H_ENTER_NESTED, __pa(&hvregs), - __pa(&vcpu->arch.regs)); - kvmhv_restore_hv_return_state(vcpu, &hvregs); - vcpu->arch.shregs.msr = vcpu->arch.regs.msr; - vcpu->arch.shregs.dar = mfspr(SPRN_DAR); - vcpu->arch.shregs.dsisr = mfspr(SPRN_DSISR); - vcpu->arch.psscr = mfspr(SPRN_PSSCR_PR); + timer_rearm_host_dec(*tb); + + restore_p9_host_os_sprs(vcpu, &host_os_sprs); + if (vcpu->arch.psscr != host_psscr) mtspr(SPRN_PSSCR_PR, host_psscr); + return trap; +} + +/* + * Guest entry for POWER9 and later CPUs. + */ +static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, + unsigned long lpcr, u64 *tb) +{ + u64 next_timer; + int trap; + + next_timer = timer_get_next_tb(); + if (*tb >= next_timer) + return BOOK3S_INTERRUPT_HV_DECREMENTER; + if (next_timer < time_limit) + time_limit = next_timer; + else if (*tb >= time_limit) /* nested time limit */ + return BOOK3S_INTERRUPT_NESTED_HV_DECREMENTER; + + vcpu->arch.ceded = 0; + + vcpu_vpa_increment_dispatch(vcpu); + + if (kvmhv_on_pseries()) { + trap = kvmhv_vcpu_entry_p9_nested(vcpu, time_limit, lpcr, tb); + /* H_CEDE has to be handled now, not later */ if (trap == BOOK3S_INTERRUPT_SYSCALL && !vcpu->arch.nested && kvmppc_get_gpr(vcpu, 3) == H_CEDE) { @@ -3982,9 +4045,16 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, kvmppc_set_gpr(vcpu, 3, 0); trap = 0; } + } else { + struct kvm *kvm = vcpu->kvm; + kvmppc_xive_push_vcpu(vcpu); - trap = kvmhv_vcpu_entry_p9(vcpu, time_limit, lpcr); + + __this_cpu_write(cpu_in_guest, kvm); + trap = kvmhv_vcpu_entry_p9(vcpu, time_limit, lpcr, tb); + __this_cpu_write(cpu_in_guest, NULL); + if (trap == BOOK3S_INTERRUPT_SYSCALL && !vcpu->arch.nested && !(vcpu->arch.shregs.msr & MSR_PR)) { unsigned long req = kvmppc_get_gpr(vcpu, 3); @@ -4009,65 +4079,11 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, } kvmppc_xive_pull_vcpu(vcpu); - if (kvm_is_radix(vcpu->kvm)) + if (kvm_is_radix(kvm)) vcpu->arch.slb_max = 0; } - dec = mfspr(SPRN_DEC); - if (!(lpcr & LPCR_LD)) /* Sign extend if not using large decrementer */ - dec = (s32) dec; - tb = mftb(); - vcpu->arch.dec_expires = dec + tb; - vcpu->cpu = -1; - vcpu->arch.thread_cpu = -1; - - store_spr_state(vcpu); - - restore_p9_host_os_sprs(vcpu, &host_os_sprs); - - msr_check_and_set(MSR_FP | MSR_VEC | MSR_VSX); - store_fp_state(&vcpu->arch.fp); -#ifdef CONFIG_ALTIVEC - store_vr_state(&vcpu->arch.vr); -#endif - vcpu->arch.vrsave = mfspr(SPRN_VRSAVE); - - if (cpu_has_feature(CPU_FTR_TM) || - cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) - kvmppc_save_tm_hv(vcpu, vcpu->arch.shregs.msr, true); - - save_pmu = 1; - if (vcpu->arch.vpa.pinned_addr) { - struct lppaca *lp = vcpu->arch.vpa.pinned_addr; - u32 yield_count = be32_to_cpu(lp->yield_count) + 1; - lp->yield_count = cpu_to_be32(yield_count); - vcpu->arch.vpa.dirty = 1; - save_pmu = lp->pmcregs_in_use; - } - /* Must save pmu if this guest is capable of running nested guests */ - save_pmu |= nesting_enabled(vcpu->kvm); - - kvmhv_save_guest_pmu(vcpu, save_pmu); -#ifdef CONFIG_PPC_PSERIES - if (kvmhv_on_pseries()) { - barrier(); - get_lppaca()->pmcregs_in_use = ppc_get_pmu_inuse(); - barrier(); - } -#endif - - vc->entry_exit_map = 0x101; - vc->in_guest = 0; - - mtspr(SPRN_DEC, local_paca->kvm_hstate.dec_expires - mftb()); - /* We may have raced with new irq work */ - if (test_irq_work_pending()) - set_dec(1); - mtspr(SPRN_SPRG_VDSO_WRITE, local_paca->sprg_vdso); - - kvmhv_load_host_pmu(); - - kvmppc_subcore_exit_guest(); + vcpu_vpa_increment_dispatch(vcpu); return trap; } @@ -4132,6 +4148,13 @@ static bool kvmppc_vcpu_woken(struct kvm_vcpu *vcpu) return false; } +static bool kvmppc_vcpu_check_block(struct kvm_vcpu *vcpu) +{ + if (!vcpu->arch.ceded || kvmppc_vcpu_woken(vcpu)) + return true; + return false; +} + /* * Check to see if any of the runnable vcpus on the vcore have pending * exceptions or are no longer ceded @@ -4142,7 +4165,7 @@ static int kvmppc_vcore_check_block(struct kvmppc_vcore *vc) int i; for_each_runnable_thread(i, vcpu, vc) { - if (!vcpu->arch.ceded || kvmppc_vcpu_woken(vcpu)) + if (kvmppc_vcpu_check_block(vcpu)) return 1; } @@ -4159,6 +4182,8 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc) int do_sleep = 1; u64 block_ns; + WARN_ON_ONCE(cpu_has_feature(CPU_FTR_ARCH_300)); + /* Poll for pending exceptions and ceded state */ cur = start_poll = ktime_get(); if (vc->halt_poll_ns) { @@ -4355,7 +4380,7 @@ static int kvmppc_run_vcpu(struct kvm_vcpu *vcpu) for_each_runnable_thread(i, v, vc) { kvmppc_core_prepare_to_enter(v); if (signal_pending(v->arch.run_task)) { - kvmppc_remove_runnable(vc, v); + kvmppc_remove_runnable(vc, v, mftb()); v->stat.signal_exits++; v->run->exit_reason = KVM_EXIT_INTR; v->arch.ret = -EINTR; @@ -4396,7 +4421,7 @@ static int kvmppc_run_vcpu(struct kvm_vcpu *vcpu) kvmppc_vcore_end_preempt(vc); if (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE) { - kvmppc_remove_runnable(vc, vcpu); + kvmppc_remove_runnable(vc, vcpu, mftb()); vcpu->stat.signal_exits++; run->exit_reason = KVM_EXIT_INTR; vcpu->arch.ret = -EINTR; @@ -4417,12 +4442,15 @@ static int kvmppc_run_vcpu(struct kvm_vcpu *vcpu) int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpcr) { + struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu); struct kvm_run *run = vcpu->run; int trap, r, pcpu; int srcu_idx; struct kvmppc_vcore *vc; struct kvm *kvm = vcpu->kvm; struct kvm_nested_guest *nested = vcpu->arch.nested; + unsigned long flags; + u64 tb; trace_kvmppc_run_vcpu_enter(vcpu); @@ -4433,16 +4461,11 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, vc = vcpu->arch.vcore; vcpu->arch.ceded = 0; vcpu->arch.run_task = current; - vcpu->arch.stolen_logged = vcore_stolen_time(vc, mftb()); vcpu->arch.state = KVMPPC_VCPU_RUNNABLE; - vcpu->arch.busy_preempt = TB_NIL; vcpu->arch.last_inst = KVM_INST_FETCH_FAILED; - vc->runnable_threads[0] = vcpu; - vc->n_runnable = 1; - vc->runner = vcpu; /* See if the MMU is ready to go */ - if (!kvm->arch.mmu_ready) { + if (unlikely(!kvm->arch.mmu_ready)) { r = kvmhv_setup_mmu(vcpu); if (r) { run->exit_reason = KVM_EXIT_FAIL_ENTRY; @@ -4457,29 +4480,21 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, kvmppc_update_vpas(vcpu); - init_vcore_to_run(vc); - vc->preempt_tb = TB_NIL; - preempt_disable(); pcpu = smp_processor_id(); - vc->pcpu = pcpu; if (kvm_is_radix(kvm)) kvmppc_prepare_radix_vcpu(vcpu, pcpu); - local_irq_disable(); - hard_irq_disable(); + /* flags save not required, but irq_pmu has no disable/enable API */ + powerpc_local_irq_pmu_save(flags); + if (signal_pending(current)) goto sigpend; - if (lazy_irq_pending() || need_resched() || !kvm->arch.mmu_ready) + if (need_resched() || !kvm->arch.mmu_ready) goto out; if (!nested) { kvmppc_core_prepare_to_enter(vcpu); - if (vcpu->arch.doorbell_request) { - vc->dpdes = 1; - smp_wmb(); - vcpu->arch.doorbell_request = 0; - } if (test_bit(BOOK3S_IRQPRIO_EXTERNAL, &vcpu->arch.pending_exceptions)) lpcr |= LPCR_MER; @@ -4490,16 +4505,23 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, goto out; } - kvmppc_clear_host_core(pcpu); + if (vcpu->arch.timer_running) { + hrtimer_try_to_cancel(&vcpu->arch.dec_timer); + vcpu->arch.timer_running = 0; + } - local_paca->kvm_hstate.napping = 0; - local_paca->kvm_hstate.kvm_split_mode = NULL; - kvmppc_start_thread(vcpu, vc); - kvmppc_create_dtl_entry(vcpu, vc); - trace_kvm_guest_enter(vcpu); + tb = mftb(); - vc->vcore_state = VCORE_RUNNING; - trace_kvmppc_run_core(vc, 0); + vcpu->cpu = pcpu; + vcpu->arch.thread_cpu = pcpu; + vc->pcpu = pcpu; + local_paca->kvm_hstate.kvm_vcpu = vcpu; + local_paca->kvm_hstate.ptid = 0; + local_paca->kvm_hstate.fake_suspend = 0; + + __kvmppc_create_dtl_entry(vcpu, pcpu, tb + vc->tb_offset, 0); + + trace_kvm_guest_enter(vcpu); guest_enter_irqoff(); @@ -4510,7 +4532,7 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, /* Tell lockdep that we're about to enable interrupts */ trace_hardirqs_on(); - trap = kvmhv_p9_guest_entry(vcpu, time_limit, lpcr); + trap = kvmhv_p9_guest_entry(vcpu, time_limit, lpcr, &tb); vcpu->arch.trap = trap; trace_hardirqs_off(); @@ -4521,8 +4543,6 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, set_irq_happened(trap); - kvmppc_set_host_core(pcpu); - context_tracking_guest_exit(); if (!vtime_accounting_enabled_this_cpu()) { local_irq_enable(); @@ -4538,9 +4558,10 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, } vtime_account_guest_exit(); - local_irq_enable(); + vcpu->cpu = -1; + vcpu->arch.thread_cpu = -1; - cpumask_clear_cpu(pcpu, &kvm->arch.cpu_in_guest); + powerpc_local_irq_pmu_restore(flags); preempt_enable(); @@ -4550,7 +4571,7 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, * by L2 and the L1 decrementer is provided in hdec_expires */ if (kvmppc_core_pending_dec(vcpu) && - ((get_tb() < vcpu->arch.dec_expires) || + ((tb < kvmppc_dec_expires_host_tb(vcpu)) || (trap == BOOK3S_INTERRUPT_SYSCALL && kvmppc_get_gpr(vcpu, 3) == H_ENTER_NESTED))) kvmppc_core_dequeue_dec(vcpu); @@ -4565,28 +4586,31 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, } vcpu->arch.ret = r; - if (is_kvmppc_resume_guest(r) && vcpu->arch.ceded && - !kvmppc_vcpu_woken(vcpu)) { + if (is_kvmppc_resume_guest(r) && !kvmppc_vcpu_check_block(vcpu)) { kvmppc_set_timer(vcpu); - while (vcpu->arch.ceded && !kvmppc_vcpu_woken(vcpu)) { + + prepare_to_rcuwait(wait); + for (;;) { + set_current_state(TASK_INTERRUPTIBLE); if (signal_pending(current)) { vcpu->stat.signal_exits++; run->exit_reason = KVM_EXIT_INTR; vcpu->arch.ret = -EINTR; break; } - spin_lock(&vc->lock); - kvmppc_vcore_blocked(vc); - spin_unlock(&vc->lock); + + if (kvmppc_vcpu_check_block(vcpu)) + break; + + trace_kvmppc_vcore_blocked(vc, 0); + schedule(); + trace_kvmppc_vcore_blocked(vc, 1); } + finish_rcuwait(wait); } vcpu->arch.ceded = 0; - vc->vcore_state = VCORE_INACTIVE; - trace_kvmppc_run_core(vc, 1); - done: - kvmppc_remove_runnable(vc, vcpu); trace_kvmppc_run_vcpu_exit(vcpu); return vcpu->arch.ret; @@ -4596,7 +4620,7 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, run->exit_reason = KVM_EXIT_INTR; vcpu->arch.ret = -EINTR; out: - local_irq_enable(); + powerpc_local_irq_pmu_restore(flags); preempt_enable(); goto done; } @@ -4606,23 +4630,25 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu) struct kvm_run *run = vcpu->run; int r; int srcu_idx; - unsigned long ebb_regs[3] = {}; /* shut up GCC */ - unsigned long user_tar = 0; - unsigned int user_vrsave; struct kvm *kvm; + unsigned long msr; if (!vcpu->arch.sane) { run->exit_reason = KVM_EXIT_INTERNAL_ERROR; return -EINVAL; } + /* No need to go into the guest when all we'll do is come back out */ + if (signal_pending(current)) { + run->exit_reason = KVM_EXIT_INTR; + return -EINTR; + } + +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM /* * Don't allow entry with a suspended transaction, because * the guest entry/exit code will lose it. - * If the guest has TM enabled, save away their TM-related SPRs - * (they will get restored by the TM unavailable interrupt). */ -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM if (cpu_has_feature(CPU_FTR_TM) && current->thread.regs && (current->thread.regs->msr & MSR_TM)) { if (MSR_TM_ACTIVE(current->thread.regs->msr)) { @@ -4630,12 +4656,6 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu) run->fail_entry.hardware_entry_failure_reason = 0; return -EINVAL; } - /* Enable TM so we can read the TM SPRs */ - mtmsr(mfmsr() | MSR_TM); - current->thread.tm_tfhar = mfspr(SPRN_TFHAR); - current->thread.tm_tfiar = mfspr(SPRN_TFIAR); - current->thread.tm_texasr = mfspr(SPRN_TEXASR); - current->thread.regs->msr &= ~MSR_TM; } #endif @@ -4650,29 +4670,30 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu) kvmppc_core_prepare_to_enter(vcpu); - /* No need to go into the guest when all we'll do is come back out */ - if (signal_pending(current)) { - run->exit_reason = KVM_EXIT_INTR; - return -EINTR; - } - kvm = vcpu->kvm; atomic_inc(&kvm->arch.vcpus_running); /* Order vcpus_running vs. mmu_ready, see kvmppc_alloc_reset_hpt */ smp_mb(); - flush_all_to_thread(current); + msr = 0; + if (IS_ENABLED(CONFIG_PPC_FPU)) + msr |= MSR_FP; + if (cpu_has_feature(CPU_FTR_ALTIVEC)) + msr |= MSR_VEC; + if (cpu_has_feature(CPU_FTR_VSX)) + msr |= MSR_VSX; + if ((cpu_has_feature(CPU_FTR_TM) || + cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) && + (vcpu->arch.hfscr & HFSCR_TM)) + msr |= MSR_TM; + msr = msr_check_and_set(msr); - /* Save userspace EBB and other register values */ - if (cpu_has_feature(CPU_FTR_ARCH_207S)) { - ebb_regs[0] = mfspr(SPRN_EBBHR); - ebb_regs[1] = mfspr(SPRN_EBBRR); - ebb_regs[2] = mfspr(SPRN_BESCR); - user_tar = mfspr(SPRN_TAR); - } - user_vrsave = mfspr(SPRN_VRSAVE); + kvmppc_save_user_regs(); + + kvmppc_save_current_sprs(); - vcpu->arch.waitp = &vcpu->arch.vcore->wait; + if (!cpu_has_feature(CPU_FTR_ARCH_300)) + vcpu->arch.waitp = &vcpu->arch.vcore->wait; vcpu->arch.pgdir = kvm->mm->pgd; vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST; @@ -4711,15 +4732,6 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu) } } while (is_kvmppc_resume_guest(r)); - /* Restore userspace EBB and other register values */ - if (cpu_has_feature(CPU_FTR_ARCH_207S)) { - mtspr(SPRN_EBBHR, ebb_regs[0]); - mtspr(SPRN_EBBRR, ebb_regs[1]); - mtspr(SPRN_BESCR, ebb_regs[2]); - mtspr(SPRN_TAR, user_tar); - } - mtspr(SPRN_VRSAVE, user_vrsave); - vcpu->arch.state = KVMPPC_VCPU_NOTREADY; atomic_dec(&kvm->arch.vcpus_running); @@ -4786,8 +4798,8 @@ static int kvm_vm_ioctl_get_dirty_log_hv(struct kvm *kvm, { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; - int i, r; - unsigned long n; + int r; + unsigned long n, i; unsigned long *buf, *p; struct kvm_vcpu *vcpu; @@ -4854,37 +4866,38 @@ static void kvmppc_core_free_memslot_hv(struct kvm_memory_slot *slot) } static int kvmppc_core_prepare_memory_region_hv(struct kvm *kvm, - struct kvm_memory_slot *slot, - const struct kvm_userspace_memory_region *mem, - enum kvm_mr_change change) + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, + enum kvm_mr_change change) { - unsigned long npages = mem->memory_size >> PAGE_SHIFT; - if (change == KVM_MR_CREATE) { - slot->arch.rmap = vzalloc(array_size(npages, - sizeof(*slot->arch.rmap))); - if (!slot->arch.rmap) + unsigned long size = array_size(new->npages, sizeof(*new->arch.rmap)); + + if ((size >> PAGE_SHIFT) > totalram_pages()) + return -ENOMEM; + + new->arch.rmap = vzalloc(size); + if (!new->arch.rmap) return -ENOMEM; + } else if (change != KVM_MR_DELETE) { + new->arch.rmap = old->arch.rmap; } return 0; } static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old, + struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { - unsigned long npages = mem->memory_size >> PAGE_SHIFT; - /* - * If we are making a new memslot, it might make + * If we are creating or modifying a memslot, it might make * some address that was previously cached as emulated * MMIO be no longer emulated MMIO, so invalidate * all the caches of emulated MMIO translations. */ - if (npages) + if (change != KVM_MR_DELETE) atomic64_inc(&kvm->arch.mmio_update); /* @@ -5072,6 +5085,8 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) */ int kvmppc_switch_mmu_to_hpt(struct kvm *kvm) { + unsigned long lpcr, lpcr_mask; + if (nesting_enabled(kvm)) kvmhv_release_all_nested(kvm); kvmppc_rmap_reset(kvm); @@ -5081,8 +5096,13 @@ int kvmppc_switch_mmu_to_hpt(struct kvm *kvm) kvm->arch.radix = 0; spin_unlock(&kvm->mmu_lock); kvmppc_free_radix(kvm); - kvmppc_update_lpcr(kvm, LPCR_VPM1, - LPCR_VPM1 | LPCR_UPRT | LPCR_GTSE | LPCR_HR); + + lpcr = LPCR_VPM1; + lpcr_mask = LPCR_VPM1 | LPCR_UPRT | LPCR_GTSE | LPCR_HR; + if (cpu_has_feature(CPU_FTR_ARCH_31)) + lpcr_mask |= LPCR_HAIL; + kvmppc_update_lpcr(kvm, lpcr, lpcr_mask); + return 0; } @@ -5092,6 +5112,7 @@ int kvmppc_switch_mmu_to_hpt(struct kvm *kvm) */ int kvmppc_switch_mmu_to_radix(struct kvm *kvm) { + unsigned long lpcr, lpcr_mask; int err; err = kvmppc_init_vm_radix(kvm); @@ -5103,8 +5124,17 @@ int kvmppc_switch_mmu_to_radix(struct kvm *kvm) kvm->arch.radix = 1; spin_unlock(&kvm->mmu_lock); kvmppc_free_hpt(&kvm->arch.hpt); - kvmppc_update_lpcr(kvm, LPCR_UPRT | LPCR_GTSE | LPCR_HR, - LPCR_VPM1 | LPCR_UPRT | LPCR_GTSE | LPCR_HR); + + lpcr = LPCR_UPRT | LPCR_GTSE | LPCR_HR; + lpcr_mask = LPCR_VPM1 | LPCR_UPRT | LPCR_GTSE | LPCR_HR; + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + lpcr_mask |= LPCR_HAIL; + if (cpu_has_feature(CPU_FTR_HVMODE) && + (kvm->arch.host_lpcr & LPCR_HAIL)) + lpcr |= LPCR_HAIL; + } + kvmppc_update_lpcr(kvm, lpcr, lpcr_mask); + return 0; } @@ -5126,6 +5156,9 @@ void kvmppc_alloc_host_rm_ops(void) int cpu, core; int size; + if (cpu_has_feature(CPU_FTR_ARCH_300)) + return; + /* Not the first time here ? */ if (kvmppc_host_rm_ops_hv != NULL) return; @@ -5268,6 +5301,10 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm) kvm->arch.mmu_ready = 1; lpcr &= ~LPCR_VPM1; lpcr |= LPCR_UPRT | LPCR_GTSE | LPCR_HR; + if (cpu_has_feature(CPU_FTR_HVMODE) && + cpu_has_feature(CPU_FTR_ARCH_31) && + (kvm->arch.host_lpcr & LPCR_HAIL)) + lpcr |= LPCR_HAIL; ret = kvmppc_init_vm_radix(kvm); if (ret) { kvmppc_free_lpid(kvm->arch.lpid); @@ -5861,7 +5898,7 @@ static int kvmhv_svm_off(struct kvm *kvm) int mmu_was_ready; int srcu_idx; int ret = 0; - int i; + unsigned long i; if (!(kvm->arch.secure_guest & KVMPPC_SECURE_INIT_START)) return ret; @@ -5883,11 +5920,12 @@ static int kvmhv_svm_off(struct kvm *kvm) for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { struct kvm_memory_slot *memslot; struct kvm_memslots *slots = __kvm_memslots(kvm, i); + int bkt; if (!slots) continue; - kvm_for_each_memslot(memslot, slots) { + kvm_for_each_memslot(memslot, bkt, slots) { kvmppc_uvmem_drop_pages(memslot, kvm, true); uv_unregister_mem_slot(kvm->arch.lpid, memslot->id); } @@ -6063,9 +6101,11 @@ static int kvmppc_book3s_init_hv(void) if (r) return r; - r = kvm_init_subcore_bitmap(); - if (r) - return r; + if (!cpu_has_feature(CPU_FTR_ARCH_300)) { + r = kvm_init_subcore_bitmap(); + if (r) + return r; + } /* * We need a way of accessing the XICS interrupt controller, diff --git a/arch/powerpc/kvm/book3s_hv.h b/arch/powerpc/kvm/book3s_hv.h new file mode 100644 index 000000000000..6b7f07d9026b --- /dev/null +++ b/arch/powerpc/kvm/book3s_hv.h @@ -0,0 +1,42 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* + * Privileged (non-hypervisor) host registers to save. + */ +struct p9_host_os_sprs { + unsigned long iamr; + unsigned long amr; + + unsigned int pmc1; + unsigned int pmc2; + unsigned int pmc3; + unsigned int pmc4; + unsigned int pmc5; + unsigned int pmc6; + unsigned long mmcr0; + unsigned long mmcr1; + unsigned long mmcr2; + unsigned long mmcr3; + unsigned long mmcra; + unsigned long siar; + unsigned long sier1; + unsigned long sier2; + unsigned long sier3; + unsigned long sdar; +}; + +static inline bool nesting_enabled(struct kvm *kvm) +{ + return kvm->arch.nested_enable && kvm_is_radix(kvm); +} + +bool load_vcpu_state(struct kvm_vcpu *vcpu, + struct p9_host_os_sprs *host_os_sprs); +void store_vcpu_state(struct kvm_vcpu *vcpu); +void save_p9_host_os_sprs(struct p9_host_os_sprs *host_os_sprs); +void restore_p9_host_os_sprs(struct kvm_vcpu *vcpu, + struct p9_host_os_sprs *host_os_sprs); +void switch_pmu_to_guest(struct kvm_vcpu *vcpu, + struct p9_host_os_sprs *host_os_sprs); +void switch_pmu_to_host(struct kvm_vcpu *vcpu, + struct p9_host_os_sprs *host_os_sprs); diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c index 70b7a8f97153..7d6d91338c3f 100644 --- a/arch/powerpc/kvm/book3s_hv_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_builtin.c @@ -649,6 +649,8 @@ void kvmppc_guest_entry_inject_int(struct kvm_vcpu *vcpu) int ext; unsigned long lpcr; + WARN_ON_ONCE(cpu_has_feature(CPU_FTR_ARCH_300)); + /* Insert EXTERNAL bit into LPCR at the MER bit position */ ext = (vcpu->arch.pending_exceptions >> BOOK3S_IRQPRIO_EXTERNAL) & 1; lpcr = mfspr(SPRN_LPCR); @@ -682,60 +684,23 @@ static void flush_guest_tlb(struct kvm *kvm) unsigned long rb, set; rb = PPC_BIT(52); /* IS = 2 */ - if (kvm_is_radix(kvm)) { - /* R=1 PRS=1 RIC=2 */ + for (set = 0; set < kvm->arch.tlb_sets; ++set) { + /* R=0 PRS=0 RIC=0 */ asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1) - : : "r" (rb), "i" (1), "i" (1), "i" (2), + : : "r" (rb), "i" (0), "i" (0), "i" (0), "r" (0) : "memory"); - for (set = 1; set < kvm->arch.tlb_sets; ++set) { - rb += PPC_BIT(51); /* increment set number */ - /* R=1 PRS=1 RIC=0 */ - asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1) - : : "r" (rb), "i" (1), "i" (1), "i" (0), - "r" (0) : "memory"); - } - asm volatile("ptesync": : :"memory"); - // POWER9 congruence-class TLBIEL leaves ERAT. Flush it now. - asm volatile(PPC_RADIX_INVALIDATE_ERAT_GUEST : : :"memory"); - } else { - for (set = 0; set < kvm->arch.tlb_sets; ++set) { - /* R=0 PRS=0 RIC=0 */ - asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1) - : : "r" (rb), "i" (0), "i" (0), "i" (0), - "r" (0) : "memory"); - rb += PPC_BIT(51); /* increment set number */ - } - asm volatile("ptesync": : :"memory"); - // POWER9 congruence-class TLBIEL leaves ERAT. Flush it now. - if (cpu_has_feature(CPU_FTR_ARCH_300)) - asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT : : :"memory"); + rb += PPC_BIT(51); /* increment set number */ } + asm volatile("ptesync": : :"memory"); } -void kvmppc_check_need_tlb_flush(struct kvm *kvm, int pcpu, - struct kvm_nested_guest *nested) +void kvmppc_check_need_tlb_flush(struct kvm *kvm, int pcpu) { - cpumask_t *need_tlb_flush; - - /* - * On POWER9, individual threads can come in here, but the - * TLB is shared between the 4 threads in a core, hence - * invalidating on one thread invalidates for all. - * Thus we make all 4 threads use the same bit. - */ - if (cpu_has_feature(CPU_FTR_ARCH_300)) - pcpu = cpu_first_tlb_thread_sibling(pcpu); - - if (nested) - need_tlb_flush = &nested->need_tlb_flush; - else - need_tlb_flush = &kvm->arch.need_tlb_flush; - - if (cpumask_test_cpu(pcpu, need_tlb_flush)) { + if (cpumask_test_cpu(pcpu, &kvm->arch.need_tlb_flush)) { flush_guest_tlb(kvm); /* Clear the bit after the TLB flush */ - cpumask_clear_cpu(pcpu, need_tlb_flush); + cpumask_clear_cpu(pcpu, &kvm->arch.need_tlb_flush); } } EXPORT_SYMBOL_GPL(kvmppc_check_need_tlb_flush); diff --git a/arch/powerpc/kvm/book3s_hv_hmi.c b/arch/powerpc/kvm/book3s_hv_hmi.c index 9af660476314..1ec50c69678b 100644 --- a/arch/powerpc/kvm/book3s_hv_hmi.c +++ b/arch/powerpc/kvm/book3s_hv_hmi.c @@ -20,10 +20,15 @@ void wait_for_subcore_guest_exit(void) /* * NULL bitmap pointer indicates that KVM module hasn't - * been loaded yet and hence no guests are running. + * been loaded yet and hence no guests are running, or running + * on POWER9 or newer CPU. + * * If no KVM is in use, no need to co-ordinate among threads * as all of them will always be in host and no one is going * to modify TB other than the opal hmi handler. + * + * POWER9 and newer don't need this synchronisation. + * * Hence, just return from here. */ if (!local_paca->sibling_subcore_state) diff --git a/arch/powerpc/kvm/book3s_hv_interrupts.S b/arch/powerpc/kvm/book3s_hv_interrupts.S index 4444f83cb133..59d89e4b154a 100644 --- a/arch/powerpc/kvm/book3s_hv_interrupts.S +++ b/arch/powerpc/kvm/book3s_hv_interrupts.S @@ -104,7 +104,10 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) mtlr r0 blr -_GLOBAL(kvmhv_save_host_pmu) +/* + * void kvmhv_save_host_pmu(void) + */ +kvmhv_save_host_pmu: BEGIN_FTR_SECTION /* Work around P8 PMAE bug */ li r3, -1 @@ -138,14 +141,6 @@ BEGIN_FTR_SECTION std r8, HSTATE_MMCR2(r13) std r9, HSTATE_SIER(r13) END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) -BEGIN_FTR_SECTION - mfspr r5, SPRN_MMCR3 - mfspr r6, SPRN_SIER2 - mfspr r7, SPRN_SIER3 - std r5, HSTATE_MMCR3(r13) - std r6, HSTATE_SIER2(r13) - std r7, HSTATE_SIER3(r13) -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_31) mfspr r3, SPRN_PMC1 mfspr r5, SPRN_PMC2 mfspr r6, SPRN_PMC3 diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c index ed8a2c9f5629..8f8daaeeb3b7 100644 --- a/arch/powerpc/kvm/book3s_hv_nested.c +++ b/arch/powerpc/kvm/book3s_hv_nested.c @@ -358,6 +358,7 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu) /* convert TB values/offsets to host (L0) values */ hdec_exp = l2_hv.hdec_expiry - vc->tb_offset; vc->tb_offset += l2_hv.tb_offset; + vcpu->arch.dec_expires += l2_hv.tb_offset; /* set L1 state to L2 state */ vcpu->arch.nested = l2; @@ -374,11 +375,6 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu) vcpu->arch.ret = RESUME_GUEST; vcpu->arch.trap = 0; do { - if (mftb() >= hdec_exp) { - vcpu->arch.trap = BOOK3S_INTERRUPT_HV_DECREMENTER; - r = RESUME_HOST; - break; - } r = kvmhv_run_single_vcpu(vcpu, hdec_exp, lpcr); } while (is_kvmppc_resume_guest(r)); @@ -399,6 +395,8 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu) if (l2_regs.msr & MSR_TS_MASK) vcpu->arch.shregs.msr |= MSR_TS_S; vc->tb_offset = saved_l1_hv.tb_offset; + /* XXX: is this always the same delta as saved_l1_hv.tb_offset? */ + vcpu->arch.dec_expires -= l2_hv.tb_offset; restore_hv_regs(vcpu, &saved_l1_hv); vcpu->arch.purr += delta_purr; vcpu->arch.spurr += delta_spurr; @@ -582,7 +580,7 @@ long kvmhv_copy_tofrom_guest_nested(struct kvm_vcpu *vcpu) if (eaddr & (0xFFFUL << 52)) return H_PARAMETER; - buf = kzalloc(n, GFP_KERNEL); + buf = kzalloc(n, GFP_KERNEL | __GFP_NOWARN); if (!buf) return H_NO_MEM; @@ -749,7 +747,7 @@ void kvmhv_release_all_nested(struct kvm *kvm) struct kvm_nested_guest *gp; struct kvm_nested_guest *freelist = NULL; struct kvm_memory_slot *memslot; - int srcu_idx; + int srcu_idx, bkt; spin_lock(&kvm->mmu_lock); for (i = 0; i <= kvm->arch.max_nested_lpid; i++) { @@ -770,7 +768,7 @@ void kvmhv_release_all_nested(struct kvm *kvm) } srcu_idx = srcu_read_lock(&kvm->srcu); - kvm_for_each_memslot(memslot, kvm_memslots(kvm)) + kvm_for_each_memslot(memslot, bkt, kvm_memslots(kvm)) kvmhv_free_memslot_nest_rmap(memslot); srcu_read_unlock(&kvm->srcu, srcu_idx); } diff --git a/arch/powerpc/kvm/book3s_hv_p9_entry.c b/arch/powerpc/kvm/book3s_hv_p9_entry.c index 961b3d70483c..a28e5b3daabd 100644 --- a/arch/powerpc/kvm/book3s_hv_p9_entry.c +++ b/arch/powerpc/kvm/book3s_hv_p9_entry.c @@ -4,8 +4,439 @@ #include <asm/asm-prototypes.h> #include <asm/dbell.h> #include <asm/kvm_ppc.h> +#include <asm/pmc.h> #include <asm/ppc-opcode.h> +#include "book3s_hv.h" + +static void freeze_pmu(unsigned long mmcr0, unsigned long mmcra) +{ + if (!(mmcr0 & MMCR0_FC)) + goto do_freeze; + if (mmcra & MMCRA_SAMPLE_ENABLE) + goto do_freeze; + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + if (!(mmcr0 & MMCR0_PMCCEXT)) + goto do_freeze; + if (!(mmcra & MMCRA_BHRB_DISABLE)) + goto do_freeze; + } + return; + +do_freeze: + mmcr0 = MMCR0_FC; + mmcra = 0; + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + mmcr0 |= MMCR0_PMCCEXT; + mmcra = MMCRA_BHRB_DISABLE; + } + + mtspr(SPRN_MMCR0, mmcr0); + mtspr(SPRN_MMCRA, mmcra); + isync(); +} + +void switch_pmu_to_guest(struct kvm_vcpu *vcpu, + struct p9_host_os_sprs *host_os_sprs) +{ + struct lppaca *lp; + int load_pmu = 1; + + lp = vcpu->arch.vpa.pinned_addr; + if (lp) + load_pmu = lp->pmcregs_in_use; + + /* Save host */ + if (ppc_get_pmu_inuse()) { + /* + * It might be better to put PMU handling (at least for the + * host) in the perf subsystem because it knows more about what + * is being used. + */ + + /* POWER9, POWER10 do not implement HPMC or SPMC */ + + host_os_sprs->mmcr0 = mfspr(SPRN_MMCR0); + host_os_sprs->mmcra = mfspr(SPRN_MMCRA); + + freeze_pmu(host_os_sprs->mmcr0, host_os_sprs->mmcra); + + host_os_sprs->pmc1 = mfspr(SPRN_PMC1); + host_os_sprs->pmc2 = mfspr(SPRN_PMC2); + host_os_sprs->pmc3 = mfspr(SPRN_PMC3); + host_os_sprs->pmc4 = mfspr(SPRN_PMC4); + host_os_sprs->pmc5 = mfspr(SPRN_PMC5); + host_os_sprs->pmc6 = mfspr(SPRN_PMC6); + host_os_sprs->mmcr1 = mfspr(SPRN_MMCR1); + host_os_sprs->mmcr2 = mfspr(SPRN_MMCR2); + host_os_sprs->sdar = mfspr(SPRN_SDAR); + host_os_sprs->siar = mfspr(SPRN_SIAR); + host_os_sprs->sier1 = mfspr(SPRN_SIER); + + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + host_os_sprs->mmcr3 = mfspr(SPRN_MMCR3); + host_os_sprs->sier2 = mfspr(SPRN_SIER2); + host_os_sprs->sier3 = mfspr(SPRN_SIER3); + } + } + +#ifdef CONFIG_PPC_PSERIES + /* After saving PMU, before loading guest PMU, flip pmcregs_in_use */ + if (kvmhv_on_pseries()) { + barrier(); + get_lppaca()->pmcregs_in_use = load_pmu; + barrier(); + } +#endif + + /* + * Load guest. If the VPA said the PMCs are not in use but the guest + * tried to access them anyway, HFSCR[PM] will be set by the HFAC + * fault so we can make forward progress. + */ + if (load_pmu || (vcpu->arch.hfscr & HFSCR_PM)) { + mtspr(SPRN_PMC1, vcpu->arch.pmc[0]); + mtspr(SPRN_PMC2, vcpu->arch.pmc[1]); + mtspr(SPRN_PMC3, vcpu->arch.pmc[2]); + mtspr(SPRN_PMC4, vcpu->arch.pmc[3]); + mtspr(SPRN_PMC5, vcpu->arch.pmc[4]); + mtspr(SPRN_PMC6, vcpu->arch.pmc[5]); + mtspr(SPRN_MMCR1, vcpu->arch.mmcr[1]); + mtspr(SPRN_MMCR2, vcpu->arch.mmcr[2]); + mtspr(SPRN_SDAR, vcpu->arch.sdar); + mtspr(SPRN_SIAR, vcpu->arch.siar); + mtspr(SPRN_SIER, vcpu->arch.sier[0]); + + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + mtspr(SPRN_MMCR3, vcpu->arch.mmcr[3]); + mtspr(SPRN_SIER2, vcpu->arch.sier[1]); + mtspr(SPRN_SIER3, vcpu->arch.sier[2]); + } + + /* Set MMCRA then MMCR0 last */ + mtspr(SPRN_MMCRA, vcpu->arch.mmcra); + mtspr(SPRN_MMCR0, vcpu->arch.mmcr[0]); + /* No isync necessary because we're starting counters */ + + if (!vcpu->arch.nested && + (vcpu->arch.hfscr_permitted & HFSCR_PM)) + vcpu->arch.hfscr |= HFSCR_PM; + } +} +EXPORT_SYMBOL_GPL(switch_pmu_to_guest); + +void switch_pmu_to_host(struct kvm_vcpu *vcpu, + struct p9_host_os_sprs *host_os_sprs) +{ + struct lppaca *lp; + int save_pmu = 1; + + lp = vcpu->arch.vpa.pinned_addr; + if (lp) + save_pmu = lp->pmcregs_in_use; + if (IS_ENABLED(CONFIG_KVM_BOOK3S_HV_NESTED_PMU_WORKAROUND)) { + /* + * Save pmu if this guest is capable of running nested guests. + * This is option is for old L1s that do not set their + * lppaca->pmcregs_in_use properly when entering their L2. + */ + save_pmu |= nesting_enabled(vcpu->kvm); + } + + if (save_pmu) { + vcpu->arch.mmcr[0] = mfspr(SPRN_MMCR0); + vcpu->arch.mmcra = mfspr(SPRN_MMCRA); + + freeze_pmu(vcpu->arch.mmcr[0], vcpu->arch.mmcra); + + vcpu->arch.pmc[0] = mfspr(SPRN_PMC1); + vcpu->arch.pmc[1] = mfspr(SPRN_PMC2); + vcpu->arch.pmc[2] = mfspr(SPRN_PMC3); + vcpu->arch.pmc[3] = mfspr(SPRN_PMC4); + vcpu->arch.pmc[4] = mfspr(SPRN_PMC5); + vcpu->arch.pmc[5] = mfspr(SPRN_PMC6); + vcpu->arch.mmcr[1] = mfspr(SPRN_MMCR1); + vcpu->arch.mmcr[2] = mfspr(SPRN_MMCR2); + vcpu->arch.sdar = mfspr(SPRN_SDAR); + vcpu->arch.siar = mfspr(SPRN_SIAR); + vcpu->arch.sier[0] = mfspr(SPRN_SIER); + + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + vcpu->arch.mmcr[3] = mfspr(SPRN_MMCR3); + vcpu->arch.sier[1] = mfspr(SPRN_SIER2); + vcpu->arch.sier[2] = mfspr(SPRN_SIER3); + } + + } else if (vcpu->arch.hfscr & HFSCR_PM) { + /* + * The guest accessed PMC SPRs without specifying they should + * be preserved, or it cleared pmcregs_in_use after the last + * access. Just ensure they are frozen. + */ + freeze_pmu(mfspr(SPRN_MMCR0), mfspr(SPRN_MMCRA)); + + /* + * Demand-fault PMU register access in the guest. + * + * This is used to grab the guest's VPA pmcregs_in_use value + * and reflect it into the host's VPA in the case of a nested + * hypervisor. + * + * It also avoids having to zero-out SPRs after each guest + * exit to avoid side-channels when. + * + * This is cleared here when we exit the guest, so later HFSCR + * interrupt handling can add it back to run the guest with + * PM enabled next time. + */ + if (!vcpu->arch.nested) + vcpu->arch.hfscr &= ~HFSCR_PM; + } /* otherwise the PMU should still be frozen */ + +#ifdef CONFIG_PPC_PSERIES + if (kvmhv_on_pseries()) { + barrier(); + get_lppaca()->pmcregs_in_use = ppc_get_pmu_inuse(); + barrier(); + } +#endif + + if (ppc_get_pmu_inuse()) { + mtspr(SPRN_PMC1, host_os_sprs->pmc1); + mtspr(SPRN_PMC2, host_os_sprs->pmc2); + mtspr(SPRN_PMC3, host_os_sprs->pmc3); + mtspr(SPRN_PMC4, host_os_sprs->pmc4); + mtspr(SPRN_PMC5, host_os_sprs->pmc5); + mtspr(SPRN_PMC6, host_os_sprs->pmc6); + mtspr(SPRN_MMCR1, host_os_sprs->mmcr1); + mtspr(SPRN_MMCR2, host_os_sprs->mmcr2); + mtspr(SPRN_SDAR, host_os_sprs->sdar); + mtspr(SPRN_SIAR, host_os_sprs->siar); + mtspr(SPRN_SIER, host_os_sprs->sier1); + + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + mtspr(SPRN_MMCR3, host_os_sprs->mmcr3); + mtspr(SPRN_SIER2, host_os_sprs->sier2); + mtspr(SPRN_SIER3, host_os_sprs->sier3); + } + + /* Set MMCRA then MMCR0 last */ + mtspr(SPRN_MMCRA, host_os_sprs->mmcra); + mtspr(SPRN_MMCR0, host_os_sprs->mmcr0); + isync(); + } +} +EXPORT_SYMBOL_GPL(switch_pmu_to_host); + +static void load_spr_state(struct kvm_vcpu *vcpu, + struct p9_host_os_sprs *host_os_sprs) +{ + /* TAR is very fast */ + mtspr(SPRN_TAR, vcpu->arch.tar); + +#ifdef CONFIG_ALTIVEC + if (cpu_has_feature(CPU_FTR_ALTIVEC) && + current->thread.vrsave != vcpu->arch.vrsave) + mtspr(SPRN_VRSAVE, vcpu->arch.vrsave); +#endif + + if (vcpu->arch.hfscr & HFSCR_EBB) { + if (current->thread.ebbhr != vcpu->arch.ebbhr) + mtspr(SPRN_EBBHR, vcpu->arch.ebbhr); + if (current->thread.ebbrr != vcpu->arch.ebbrr) + mtspr(SPRN_EBBRR, vcpu->arch.ebbrr); + if (current->thread.bescr != vcpu->arch.bescr) + mtspr(SPRN_BESCR, vcpu->arch.bescr); + } + + if (cpu_has_feature(CPU_FTR_P9_TIDR) && + current->thread.tidr != vcpu->arch.tid) + mtspr(SPRN_TIDR, vcpu->arch.tid); + if (host_os_sprs->iamr != vcpu->arch.iamr) + mtspr(SPRN_IAMR, vcpu->arch.iamr); + if (host_os_sprs->amr != vcpu->arch.amr) + mtspr(SPRN_AMR, vcpu->arch.amr); + if (vcpu->arch.uamor != 0) + mtspr(SPRN_UAMOR, vcpu->arch.uamor); + if (current->thread.fscr != vcpu->arch.fscr) + mtspr(SPRN_FSCR, vcpu->arch.fscr); + if (current->thread.dscr != vcpu->arch.dscr) + mtspr(SPRN_DSCR, vcpu->arch.dscr); + if (vcpu->arch.pspb != 0) + mtspr(SPRN_PSPB, vcpu->arch.pspb); + + /* + * DAR, DSISR, and for nested HV, SPRGs must be set with MSR[RI] + * clear (or hstate set appropriately to catch those registers + * being clobbered if we take a MCE or SRESET), so those are done + * later. + */ + + if (!(vcpu->arch.ctrl & 1)) + mtspr(SPRN_CTRLT, 0); +} + +static void store_spr_state(struct kvm_vcpu *vcpu) +{ + vcpu->arch.tar = mfspr(SPRN_TAR); + +#ifdef CONFIG_ALTIVEC + if (cpu_has_feature(CPU_FTR_ALTIVEC)) + vcpu->arch.vrsave = mfspr(SPRN_VRSAVE); +#endif + + if (vcpu->arch.hfscr & HFSCR_EBB) { + vcpu->arch.ebbhr = mfspr(SPRN_EBBHR); + vcpu->arch.ebbrr = mfspr(SPRN_EBBRR); + vcpu->arch.bescr = mfspr(SPRN_BESCR); + } + + if (cpu_has_feature(CPU_FTR_P9_TIDR)) + vcpu->arch.tid = mfspr(SPRN_TIDR); + vcpu->arch.iamr = mfspr(SPRN_IAMR); + vcpu->arch.amr = mfspr(SPRN_AMR); + vcpu->arch.uamor = mfspr(SPRN_UAMOR); + vcpu->arch.fscr = mfspr(SPRN_FSCR); + vcpu->arch.dscr = mfspr(SPRN_DSCR); + vcpu->arch.pspb = mfspr(SPRN_PSPB); + + vcpu->arch.ctrl = mfspr(SPRN_CTRLF); +} + +/* Returns true if current MSR and/or guest MSR may have changed */ +bool load_vcpu_state(struct kvm_vcpu *vcpu, + struct p9_host_os_sprs *host_os_sprs) +{ + bool ret = false; + +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (cpu_has_feature(CPU_FTR_TM) || + cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) { + unsigned long guest_msr = vcpu->arch.shregs.msr; + if (MSR_TM_ACTIVE(guest_msr)) { + kvmppc_restore_tm_hv(vcpu, guest_msr, true); + ret = true; + } else if (vcpu->arch.hfscr & HFSCR_TM) { + mtspr(SPRN_TEXASR, vcpu->arch.texasr); + mtspr(SPRN_TFHAR, vcpu->arch.tfhar); + mtspr(SPRN_TFIAR, vcpu->arch.tfiar); + } + } +#endif + + load_spr_state(vcpu, host_os_sprs); + + load_fp_state(&vcpu->arch.fp); +#ifdef CONFIG_ALTIVEC + load_vr_state(&vcpu->arch.vr); +#endif + + return ret; +} +EXPORT_SYMBOL_GPL(load_vcpu_state); + +void store_vcpu_state(struct kvm_vcpu *vcpu) +{ + store_spr_state(vcpu); + + store_fp_state(&vcpu->arch.fp); +#ifdef CONFIG_ALTIVEC + store_vr_state(&vcpu->arch.vr); +#endif + +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (cpu_has_feature(CPU_FTR_TM) || + cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) { + unsigned long guest_msr = vcpu->arch.shregs.msr; + if (MSR_TM_ACTIVE(guest_msr)) { + kvmppc_save_tm_hv(vcpu, guest_msr, true); + } else if (vcpu->arch.hfscr & HFSCR_TM) { + vcpu->arch.texasr = mfspr(SPRN_TEXASR); + vcpu->arch.tfhar = mfspr(SPRN_TFHAR); + vcpu->arch.tfiar = mfspr(SPRN_TFIAR); + + if (!vcpu->arch.nested) { + vcpu->arch.load_tm++; /* see load_ebb comment */ + if (!vcpu->arch.load_tm) + vcpu->arch.hfscr &= ~HFSCR_TM; + } + } + } +#endif +} +EXPORT_SYMBOL_GPL(store_vcpu_state); + +void save_p9_host_os_sprs(struct p9_host_os_sprs *host_os_sprs) +{ + host_os_sprs->iamr = mfspr(SPRN_IAMR); + host_os_sprs->amr = mfspr(SPRN_AMR); +} +EXPORT_SYMBOL_GPL(save_p9_host_os_sprs); + +/* vcpu guest regs must already be saved */ +void restore_p9_host_os_sprs(struct kvm_vcpu *vcpu, + struct p9_host_os_sprs *host_os_sprs) +{ + /* + * current->thread.xxx registers must all be restored to host + * values before a potential context switch, othrewise the context + * switch itself will overwrite current->thread.xxx with the values + * from the guest SPRs. + */ + + mtspr(SPRN_SPRG_VDSO_WRITE, local_paca->sprg_vdso); + + if (cpu_has_feature(CPU_FTR_P9_TIDR) && + current->thread.tidr != vcpu->arch.tid) + mtspr(SPRN_TIDR, current->thread.tidr); + if (host_os_sprs->iamr != vcpu->arch.iamr) + mtspr(SPRN_IAMR, host_os_sprs->iamr); + if (vcpu->arch.uamor != 0) + mtspr(SPRN_UAMOR, 0); + if (host_os_sprs->amr != vcpu->arch.amr) + mtspr(SPRN_AMR, host_os_sprs->amr); + if (current->thread.fscr != vcpu->arch.fscr) + mtspr(SPRN_FSCR, current->thread.fscr); + if (current->thread.dscr != vcpu->arch.dscr) + mtspr(SPRN_DSCR, current->thread.dscr); + if (vcpu->arch.pspb != 0) + mtspr(SPRN_PSPB, 0); + + /* Save guest CTRL register, set runlatch to 1 */ + if (!(vcpu->arch.ctrl & 1)) + mtspr(SPRN_CTRLT, 1); + +#ifdef CONFIG_ALTIVEC + if (cpu_has_feature(CPU_FTR_ALTIVEC) && + vcpu->arch.vrsave != current->thread.vrsave) + mtspr(SPRN_VRSAVE, current->thread.vrsave); +#endif + if (vcpu->arch.hfscr & HFSCR_EBB) { + if (vcpu->arch.bescr != current->thread.bescr) + mtspr(SPRN_BESCR, current->thread.bescr); + if (vcpu->arch.ebbhr != current->thread.ebbhr) + mtspr(SPRN_EBBHR, current->thread.ebbhr); + if (vcpu->arch.ebbrr != current->thread.ebbrr) + mtspr(SPRN_EBBRR, current->thread.ebbrr); + + if (!vcpu->arch.nested) { + /* + * This is like load_fp in context switching, turn off + * the facility after it wraps the u8 to try avoiding + * saving and restoring the registers each partition + * switch. + */ + vcpu->arch.load_ebb++; + if (!vcpu->arch.load_ebb) + vcpu->arch.hfscr &= ~HFSCR_EBB; + } + } + + if (vcpu->arch.tar != current->thread.tar) + mtspr(SPRN_TAR, current->thread.tar); +} +EXPORT_SYMBOL_GPL(restore_p9_host_os_sprs); + #ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING static void __start_timing(struct kvm_vcpu *vcpu, struct kvmhv_tb_accumulator *next) { @@ -56,10 +487,22 @@ static void __accumulate_time(struct kvm_vcpu *vcpu, struct kvmhv_tb_accumulator #define accumulate_time(vcpu, next) do {} while (0) #endif -static inline void mfslb(unsigned int idx, u64 *slbee, u64 *slbev) +static inline u64 mfslbv(unsigned int idx) { - asm volatile("slbmfev %0,%1" : "=r" (*slbev) : "r" (idx)); - asm volatile("slbmfee %0,%1" : "=r" (*slbee) : "r" (idx)); + u64 slbev; + + asm volatile("slbmfev %0,%1" : "=r" (slbev) : "r" (idx)); + + return slbev; +} + +static inline u64 mfslbe(unsigned int idx) +{ + u64 slbee; + + asm volatile("slbmfee %0,%1" : "=r" (slbee) : "r" (idx)); + + return slbee; } static inline void mtslb(u64 slbee, u64 slbev) @@ -100,17 +543,19 @@ static void switch_mmu_to_guest_radix(struct kvm *kvm, struct kvm_vcpu *vcpu, u6 lpid = nested ? nested->shadow_lpid : kvm->arch.lpid; /* - * All the isync()s are overkill but trivially follow the ISA - * requirements. Some can likely be replaced with justification - * comment for why they are not needed. + * Prior memory accesses to host PID Q3 must be completed before we + * start switching, and stores must be drained to avoid not-my-LPAR + * logic (see switch_mmu_to_host). */ + asm volatile("hwsync" ::: "memory"); isync(); mtspr(SPRN_LPID, lpid); - isync(); mtspr(SPRN_LPCR, lpcr); - isync(); mtspr(SPRN_PID, vcpu->arch.pid); - isync(); + /* + * isync not required here because we are HRFID'ing to guest before + * any guest context access, which is context synchronising. + */ } static void switch_mmu_to_guest_hpt(struct kvm *kvm, struct kvm_vcpu *vcpu, u64 lpcr) @@ -120,25 +565,41 @@ static void switch_mmu_to_guest_hpt(struct kvm *kvm, struct kvm_vcpu *vcpu, u64 lpid = kvm->arch.lpid; + /* + * See switch_mmu_to_guest_radix. ptesync should not be required here + * even if the host is in HPT mode because speculative accesses would + * not cause RC updates (we are in real mode). + */ + asm volatile("hwsync" ::: "memory"); + isync(); mtspr(SPRN_LPID, lpid); mtspr(SPRN_LPCR, lpcr); mtspr(SPRN_PID, vcpu->arch.pid); for (i = 0; i < vcpu->arch.slb_max; i++) mtslb(vcpu->arch.slb[i].orige, vcpu->arch.slb[i].origv); - - isync(); + /* + * isync not required here, see switch_mmu_to_guest_radix. + */ } static void switch_mmu_to_host(struct kvm *kvm, u32 pid) { + /* + * The guest has exited, so guest MMU context is no longer being + * non-speculatively accessed, but a hwsync is needed before the + * mtLPIDR / mtPIDR switch, in order to ensure all stores are drained, + * so the not-my-LPAR tlbie logic does not overlook them. + */ + asm volatile("hwsync" ::: "memory"); isync(); mtspr(SPRN_PID, pid); - isync(); mtspr(SPRN_LPID, kvm->arch.host_lpid); - isync(); mtspr(SPRN_LPCR, kvm->arch.host_lpcr); - isync(); + /* + * isync is not required after the switch, because mtmsrd with L=0 + * is performed after this switch, which is context synchronising. + */ if (!radix_enabled()) slb_restore_bolted_realmode(); @@ -171,8 +632,10 @@ static void save_clear_guest_mmu(struct kvm *kvm, struct kvm_vcpu *vcpu) */ for (i = 0; i < vcpu->arch.slb_nr; i++) { u64 slbee, slbev; - mfslb(i, &slbee, &slbev); + + slbee = mfslbe(i); if (slbee & SLB_ESID_V) { + slbev = mfslbv(i); vcpu->arch.slb[nr].orige = slbee | i; vcpu->arch.slb[nr].origv = slbev; nr++; @@ -183,15 +646,128 @@ static void save_clear_guest_mmu(struct kvm *kvm, struct kvm_vcpu *vcpu) } } -int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpcr) +static void flush_guest_tlb(struct kvm *kvm) { + unsigned long rb, set; + + rb = PPC_BIT(52); /* IS = 2 */ + if (kvm_is_radix(kvm)) { + /* R=1 PRS=1 RIC=2 */ + asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1) + : : "r" (rb), "i" (1), "i" (1), "i" (2), + "r" (0) : "memory"); + for (set = 1; set < kvm->arch.tlb_sets; ++set) { + rb += PPC_BIT(51); /* increment set number */ + /* R=1 PRS=1 RIC=0 */ + asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1) + : : "r" (rb), "i" (1), "i" (1), "i" (0), + "r" (0) : "memory"); + } + asm volatile("ptesync": : :"memory"); + // POWER9 congruence-class TLBIEL leaves ERAT. Flush it now. + asm volatile(PPC_RADIX_INVALIDATE_ERAT_GUEST : : :"memory"); + } else { + for (set = 0; set < kvm->arch.tlb_sets; ++set) { + /* R=0 PRS=0 RIC=0 */ + asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1) + : : "r" (rb), "i" (0), "i" (0), "i" (0), + "r" (0) : "memory"); + rb += PPC_BIT(51); /* increment set number */ + } + asm volatile("ptesync": : :"memory"); + // POWER9 congruence-class TLBIEL leaves ERAT. Flush it now. + asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT : : :"memory"); + } +} + +static void check_need_tlb_flush(struct kvm *kvm, int pcpu, + struct kvm_nested_guest *nested) +{ + cpumask_t *need_tlb_flush; + bool all_set = true; + int i; + + if (nested) + need_tlb_flush = &nested->need_tlb_flush; + else + need_tlb_flush = &kvm->arch.need_tlb_flush; + + if (likely(!cpumask_test_cpu(pcpu, need_tlb_flush))) + return; + + /* + * Individual threads can come in here, but the TLB is shared between + * the 4 threads in a core, hence invalidating on one thread + * invalidates for all, so only invalidate the first time (if all bits + * were set. The others must still execute a ptesync. + * + * If a race occurs and two threads do the TLB flush, that is not a + * problem, just sub-optimal. + */ + for (i = cpu_first_tlb_thread_sibling(pcpu); + i <= cpu_last_tlb_thread_sibling(pcpu); + i += cpu_tlb_thread_sibling_step()) { + if (!cpumask_test_cpu(i, need_tlb_flush)) { + all_set = false; + break; + } + } + if (all_set) + flush_guest_tlb(kvm); + else + asm volatile("ptesync" ::: "memory"); + + /* Clear the bit after the TLB flush */ + cpumask_clear_cpu(pcpu, need_tlb_flush); +} + +unsigned long kvmppc_msr_hard_disable_set_facilities(struct kvm_vcpu *vcpu, unsigned long msr) +{ + unsigned long msr_needed = 0; + + msr &= ~MSR_EE; + + /* MSR bits may have been cleared by context switch so must recheck */ + if (IS_ENABLED(CONFIG_PPC_FPU)) + msr_needed |= MSR_FP; + if (cpu_has_feature(CPU_FTR_ALTIVEC)) + msr_needed |= MSR_VEC; + if (cpu_has_feature(CPU_FTR_VSX)) + msr_needed |= MSR_VSX; + if ((cpu_has_feature(CPU_FTR_TM) || + cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) && + (vcpu->arch.hfscr & HFSCR_TM)) + msr_needed |= MSR_TM; + + /* + * This could be combined with MSR[RI] clearing, but that expands + * the unrecoverable window. It would be better to cover unrecoverable + * with KVM bad interrupt handling rather than use MSR[RI] at all. + * + * Much more difficult and less worthwhile to combine with IR/DR + * disable. + */ + if ((msr & msr_needed) != msr_needed) { + msr |= msr_needed; + __mtmsrd(msr, 0); + } else { + __hard_irq_disable(); + } + local_paca->irq_happened |= PACA_IRQ_HARD_DIS; + + return msr; +} +EXPORT_SYMBOL_GPL(kvmppc_msr_hard_disable_set_facilities); + +int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpcr, u64 *tb) +{ + struct p9_host_os_sprs host_os_sprs; struct kvm *kvm = vcpu->kvm; struct kvm_nested_guest *nested = vcpu->arch.nested; struct kvmppc_vcore *vc = vcpu->arch.vcore; - s64 hdec; - u64 tb, purr, spurr; + s64 hdec, dec; + u64 purr, spurr; u64 *exsave; - bool ri_set; int trap; unsigned long msr; unsigned long host_hfscr; @@ -199,11 +775,13 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc unsigned long host_dawr0; unsigned long host_dawrx0; unsigned long host_psscr; + unsigned long host_hpsscr; unsigned long host_pidr; unsigned long host_dawr1; unsigned long host_dawrx1; + unsigned long dpdes; - hdec = time_limit - mftb(); + hdec = time_limit - *tb; if (hdec < 0) return BOOK3S_INTERRUPT_HV_DECREMENTER; @@ -214,51 +792,84 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc vcpu->arch.ceded = 0; - if (vc->tb_offset) { - u64 new_tb = mftb() + vc->tb_offset; - mtspr(SPRN_TBU40, new_tb); - tb = mftb(); - if ((tb & 0xffffff) < (new_tb & 0xffffff)) - mtspr(SPRN_TBU40, new_tb + 0x1000000); - vc->tb_offset_applied = vc->tb_offset; - } - - msr = mfmsr(); + /* Save MSR for restore, with EE clear. */ + msr = mfmsr() & ~MSR_EE; host_hfscr = mfspr(SPRN_HFSCR); host_ciabr = mfspr(SPRN_CIABR); - host_dawr0 = mfspr(SPRN_DAWR0); - host_dawrx0 = mfspr(SPRN_DAWRX0); - host_psscr = mfspr(SPRN_PSSCR); + host_psscr = mfspr(SPRN_PSSCR_PR); + if (cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) + host_hpsscr = mfspr(SPRN_PSSCR); host_pidr = mfspr(SPRN_PID); - if (cpu_has_feature(CPU_FTR_DAWR1)) { - host_dawr1 = mfspr(SPRN_DAWR1); - host_dawrx1 = mfspr(SPRN_DAWRX1); - } - if (vc->pcr) - mtspr(SPRN_PCR, vc->pcr | PCR_MASK); - mtspr(SPRN_DPDES, vc->dpdes); - mtspr(SPRN_VTB, vc->vtb); + if (dawr_enabled()) { + host_dawr0 = mfspr(SPRN_DAWR0); + host_dawrx0 = mfspr(SPRN_DAWRX0); + if (cpu_has_feature(CPU_FTR_DAWR1)) { + host_dawr1 = mfspr(SPRN_DAWR1); + host_dawrx1 = mfspr(SPRN_DAWRX1); + } + } local_paca->kvm_hstate.host_purr = mfspr(SPRN_PURR); local_paca->kvm_hstate.host_spurr = mfspr(SPRN_SPURR); + + save_p9_host_os_sprs(&host_os_sprs); + + msr = kvmppc_msr_hard_disable_set_facilities(vcpu, msr); + if (lazy_irq_pending()) { + trap = 0; + goto out; + } + + if (unlikely(load_vcpu_state(vcpu, &host_os_sprs))) + msr = mfmsr(); /* MSR may have been updated */ + + if (vc->tb_offset) { + u64 new_tb = *tb + vc->tb_offset; + mtspr(SPRN_TBU40, new_tb); + if ((mftb() & 0xffffff) < (new_tb & 0xffffff)) { + new_tb += 0x1000000; + mtspr(SPRN_TBU40, new_tb); + } + *tb = new_tb; + vc->tb_offset_applied = vc->tb_offset; + } + + mtspr(SPRN_VTB, vc->vtb); mtspr(SPRN_PURR, vcpu->arch.purr); mtspr(SPRN_SPURR, vcpu->arch.spurr); + if (vc->pcr) + mtspr(SPRN_PCR, vc->pcr | PCR_MASK); + if (vcpu->arch.doorbell_request) { + vcpu->arch.doorbell_request = 0; + mtspr(SPRN_DPDES, 1); + } + if (dawr_enabled()) { - mtspr(SPRN_DAWR0, vcpu->arch.dawr0); - mtspr(SPRN_DAWRX0, vcpu->arch.dawrx0); + if (vcpu->arch.dawr0 != host_dawr0) + mtspr(SPRN_DAWR0, vcpu->arch.dawr0); + if (vcpu->arch.dawrx0 != host_dawrx0) + mtspr(SPRN_DAWRX0, vcpu->arch.dawrx0); if (cpu_has_feature(CPU_FTR_DAWR1)) { - mtspr(SPRN_DAWR1, vcpu->arch.dawr1); - mtspr(SPRN_DAWRX1, vcpu->arch.dawrx1); + if (vcpu->arch.dawr1 != host_dawr1) + mtspr(SPRN_DAWR1, vcpu->arch.dawr1); + if (vcpu->arch.dawrx1 != host_dawrx1) + mtspr(SPRN_DAWRX1, vcpu->arch.dawrx1); } } - mtspr(SPRN_CIABR, vcpu->arch.ciabr); - mtspr(SPRN_IC, vcpu->arch.ic); + if (vcpu->arch.ciabr != host_ciabr) + mtspr(SPRN_CIABR, vcpu->arch.ciabr); - mtspr(SPRN_PSSCR, vcpu->arch.psscr | PSSCR_EC | - (local_paca->kvm_hstate.fake_suspend << PSSCR_FAKE_SUSPEND_LG)); + + if (cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) { + mtspr(SPRN_PSSCR, vcpu->arch.psscr | PSSCR_EC | + (local_paca->kvm_hstate.fake_suspend << PSSCR_FAKE_SUSPEND_LG)); + } else { + if (vcpu->arch.psscr != host_psscr) + mtspr(SPRN_PSSCR_PR, vcpu->arch.psscr); + } mtspr(SPRN_HFSCR, vcpu->arch.hfscr); @@ -276,18 +887,34 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc * HDSI which should correctly update the HDSISR the second time HDSI * entry. * - * Just do this on all p9 processors for now. + * The "radix prefetch bug" test can be used to test for this bug, as + * it also exists fo DD2.1 and below. */ - mtspr(SPRN_HDSISR, HDSISR_CANARY); + if (cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG)) + mtspr(SPRN_HDSISR, HDSISR_CANARY); mtspr(SPRN_SPRG0, vcpu->arch.shregs.sprg0); mtspr(SPRN_SPRG1, vcpu->arch.shregs.sprg1); mtspr(SPRN_SPRG2, vcpu->arch.shregs.sprg2); mtspr(SPRN_SPRG3, vcpu->arch.shregs.sprg3); - mtspr(SPRN_AMOR, ~0UL); + /* + * It might be preferable to load_vcpu_state here, in order to get the + * GPR/FP register loads executing in parallel with the previous mtSPR + * instructions, but for now that can't be done because the TM handling + * in load_vcpu_state can change some SPRs and vcpu state (nip, msr). + * But TM could be split out if this would be a significant benefit. + */ - local_paca->kvm_hstate.in_guest = KVM_GUEST_MODE_HV_P9; + /* + * MSR[RI] does not need to be cleared (and is not, for radix guests + * with no prefetch bug), because in_guest is set. If we take a SRESET + * or MCE with in_guest set but still in HV mode, then + * kvmppc_p9_bad_interrupt handles the interrupt, which effectively + * clears MSR[RI] and doesn't return. + */ + WRITE_ONCE(local_paca->kvm_hstate.in_guest, KVM_GUEST_MODE_HV_P9); + barrier(); /* Open in_guest critical section */ /* * Hash host, hash guest, or radix guest with prefetch bug, all have @@ -299,17 +926,13 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc save_clear_host_mmu(kvm); - if (kvm_is_radix(kvm)) { + if (kvm_is_radix(kvm)) switch_mmu_to_guest_radix(kvm, vcpu, lpcr); - if (!cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG)) - __mtmsrd(0, 1); /* clear RI */ - - } else { + else switch_mmu_to_guest_hpt(kvm, vcpu, lpcr); - } /* TLBIEL uses LPID=LPIDR, so run this after setting guest LPID */ - kvmppc_check_need_tlb_flush(kvm, vc->pcpu, nested); + check_need_tlb_flush(kvm, vc->pcpu, nested); /* * P9 suppresses the HDEC exception when LPCR[HDICE] = 0, @@ -317,6 +940,8 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc */ mtspr(SPRN_HDEC, hdec); + mtspr(SPRN_DEC, vcpu->arch.dec_expires - *tb); + #ifdef CONFIG_PPC_TRANSACTIONAL_MEM tm_return_to_guest: #endif @@ -327,7 +952,9 @@ tm_return_to_guest: accumulate_time(vcpu, &vcpu->arch.guest_time); + switch_pmu_to_guest(vcpu, &host_os_sprs); kvmppc_p9_enter_guest(vcpu); + switch_pmu_to_host(vcpu, &host_os_sprs); accumulate_time(vcpu, &vcpu->arch.rm_intr); @@ -340,36 +967,27 @@ tm_return_to_guest: /* 0x2 bit for HSRR is only used by PR and P7/8 HV paths, clear it */ trap = local_paca->kvm_hstate.scratch0 & ~0x2; - /* HSRR interrupts leave MSR[RI] unchanged, SRR interrupts clear it. */ - ri_set = false; - if (likely(trap > BOOK3S_INTERRUPT_MACHINE_CHECK)) { - if (trap != BOOK3S_INTERRUPT_SYSCALL && - (vcpu->arch.shregs.msr & MSR_RI)) - ri_set = true; + if (likely(trap > BOOK3S_INTERRUPT_MACHINE_CHECK)) exsave = local_paca->exgen; - } else if (trap == BOOK3S_INTERRUPT_SYSTEM_RESET) { + else if (trap == BOOK3S_INTERRUPT_SYSTEM_RESET) exsave = local_paca->exnmi; - } else { /* trap == 0x200 */ + else /* trap == 0x200 */ exsave = local_paca->exmc; - } vcpu->arch.regs.gpr[1] = local_paca->kvm_hstate.scratch1; vcpu->arch.regs.gpr[3] = local_paca->kvm_hstate.scratch2; /* - * Only set RI after reading machine check regs (DAR, DSISR, SRR0/1) - * and hstate scratch (which we need to move into exsave to make - * re-entrant vs SRESET/MCE) + * After reading machine check regs (DAR, DSISR, SRR0/1) and hstate + * scratch (which we need to move into exsave to make re-entrant vs + * SRESET/MCE), register state is protected from reentrancy. However + * timebase, MMU, among other state is still set to guest, so don't + * enable MSR[RI] here. It gets enabled at the end, after in_guest + * is cleared. + * + * It is possible an NMI could come in here, which is why it is + * important to save the above state early so it can be debugged. */ - if (ri_set) { - if (unlikely(!(mfmsr() & MSR_RI))) { - __mtmsrd(MSR_RI, 1); - WARN_ON_ONCE(1); - } - } else { - WARN_ON_ONCE(mfmsr() & MSR_RI); - __mtmsrd(MSR_RI, 1); - } vcpu->arch.regs.gpr[9] = exsave[EX_R9/sizeof(u64)]; vcpu->arch.regs.gpr[10] = exsave[EX_R10/sizeof(u64)]; @@ -388,7 +1006,7 @@ tm_return_to_guest: kvmppc_realmode_machine_check(vcpu); } else if (unlikely(trap == BOOK3S_INTERRUPT_HMI)) { - kvmppc_realmode_hmi_handler(); + kvmppc_p9_realmode_hmi_handler(vcpu); } else if (trap == BOOK3S_INTERRUPT_H_EMUL_ASSIST) { vcpu->arch.emul_inst = mfspr(SPRN_HEIR); @@ -427,13 +1045,6 @@ tm_return_to_guest: */ mtspr(SPRN_HSRR0, vcpu->arch.regs.nip); mtspr(SPRN_HSRR1, vcpu->arch.shregs.msr); - - /* - * tm_return_to_guest re-loads SRR0/1, DAR, - * DSISR after RI is cleared, in case they had - * been clobbered by a MCE. - */ - __mtmsrd(0, 1); /* clear RI */ goto tm_return_to_guest; } } @@ -445,81 +1056,109 @@ tm_return_to_guest: /* Advance host PURR/SPURR by the amount used by guest */ purr = mfspr(SPRN_PURR); spurr = mfspr(SPRN_SPURR); - mtspr(SPRN_PURR, local_paca->kvm_hstate.host_purr + - purr - vcpu->arch.purr); - mtspr(SPRN_SPURR, local_paca->kvm_hstate.host_spurr + - spurr - vcpu->arch.spurr); + local_paca->kvm_hstate.host_purr += purr - vcpu->arch.purr; + local_paca->kvm_hstate.host_spurr += spurr - vcpu->arch.spurr; vcpu->arch.purr = purr; vcpu->arch.spurr = spurr; vcpu->arch.ic = mfspr(SPRN_IC); vcpu->arch.pid = mfspr(SPRN_PID); - vcpu->arch.psscr = mfspr(SPRN_PSSCR) & PSSCR_GUEST_VIS; + vcpu->arch.psscr = mfspr(SPRN_PSSCR_PR); vcpu->arch.shregs.sprg0 = mfspr(SPRN_SPRG0); vcpu->arch.shregs.sprg1 = mfspr(SPRN_SPRG1); vcpu->arch.shregs.sprg2 = mfspr(SPRN_SPRG2); vcpu->arch.shregs.sprg3 = mfspr(SPRN_SPRG3); - /* Preserve PSSCR[FAKE_SUSPEND] until we've called kvmppc_save_tm_hv */ - mtspr(SPRN_PSSCR, host_psscr | - (local_paca->kvm_hstate.fake_suspend << PSSCR_FAKE_SUSPEND_LG)); - mtspr(SPRN_HFSCR, host_hfscr); - mtspr(SPRN_CIABR, host_ciabr); - mtspr(SPRN_DAWR0, host_dawr0); - mtspr(SPRN_DAWRX0, host_dawrx0); - if (cpu_has_feature(CPU_FTR_DAWR1)) { - mtspr(SPRN_DAWR1, host_dawr1); - mtspr(SPRN_DAWRX1, host_dawrx1); - } - - if (kvm_is_radix(kvm)) { - /* - * Since this is radix, do a eieio; tlbsync; ptesync sequence - * in case we interrupted the guest between a tlbie and a - * ptesync. - */ - asm volatile("eieio; tlbsync; ptesync"); - } + dpdes = mfspr(SPRN_DPDES); + if (dpdes) + vcpu->arch.doorbell_request = 1; - /* - * cp_abort is required if the processor supports local copy-paste - * to clear the copy buffer that was under control of the guest. - */ - if (cpu_has_feature(CPU_FTR_ARCH_31)) - asm volatile(PPC_CP_ABORT); - - vc->dpdes = mfspr(SPRN_DPDES); vc->vtb = mfspr(SPRN_VTB); - mtspr(SPRN_DPDES, 0); - if (vc->pcr) - mtspr(SPRN_PCR, PCR_MASK); + + dec = mfspr(SPRN_DEC); + if (!(lpcr & LPCR_LD)) /* Sign extend if not using large decrementer */ + dec = (s32) dec; + *tb = mftb(); + vcpu->arch.dec_expires = dec + *tb; if (vc->tb_offset_applied) { - u64 new_tb = mftb() - vc->tb_offset_applied; + u64 new_tb = *tb - vc->tb_offset_applied; mtspr(SPRN_TBU40, new_tb); - tb = mftb(); - if ((tb & 0xffffff) < (new_tb & 0xffffff)) - mtspr(SPRN_TBU40, new_tb + 0x1000000); + if ((mftb() & 0xffffff) < (new_tb & 0xffffff)) { + new_tb += 0x1000000; + mtspr(SPRN_TBU40, new_tb); + } + *tb = new_tb; vc->tb_offset_applied = 0; } - mtspr(SPRN_HDEC, 0x7fffffff); - save_clear_guest_mmu(kvm, vcpu); switch_mmu_to_host(kvm, host_pidr); - local_paca->kvm_hstate.in_guest = KVM_GUEST_MODE_NONE; /* - * If we are in real mode, only switch MMU on after the MMU is - * switched to host, to avoid the P9_RADIX_PREFETCH_BUG. + * Enable MSR here in order to have facilities enabled to save + * guest registers. This enables MMU (if we were in realmode), so + * only switch MMU on after the MMU is switched to host, to avoid + * the P9_RADIX_PREFETCH_BUG or hash guest context. */ if (IS_ENABLED(CONFIG_PPC_TRANSACTIONAL_MEM) && - vcpu->arch.shregs.msr & MSR_TS_MASK) + vcpu->arch.shregs.msr & MSR_TS_MASK) msr |= MSR_TS_S; - __mtmsrd(msr, 0); + store_vcpu_state(vcpu); + + mtspr(SPRN_PURR, local_paca->kvm_hstate.host_purr); + mtspr(SPRN_SPURR, local_paca->kvm_hstate.host_spurr); + + if (cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) { + /* Preserve PSSCR[FAKE_SUSPEND] until we've called kvmppc_save_tm_hv */ + mtspr(SPRN_PSSCR, host_hpsscr | + (local_paca->kvm_hstate.fake_suspend << PSSCR_FAKE_SUSPEND_LG)); + } + + mtspr(SPRN_HFSCR, host_hfscr); + if (vcpu->arch.ciabr != host_ciabr) + mtspr(SPRN_CIABR, host_ciabr); + + if (dawr_enabled()) { + if (vcpu->arch.dawr0 != host_dawr0) + mtspr(SPRN_DAWR0, host_dawr0); + if (vcpu->arch.dawrx0 != host_dawrx0) + mtspr(SPRN_DAWRX0, host_dawrx0); + if (cpu_has_feature(CPU_FTR_DAWR1)) { + if (vcpu->arch.dawr1 != host_dawr1) + mtspr(SPRN_DAWR1, host_dawr1); + if (vcpu->arch.dawrx1 != host_dawrx1) + mtspr(SPRN_DAWRX1, host_dawrx1); + } + } + + if (dpdes) + mtspr(SPRN_DPDES, 0); + if (vc->pcr) + mtspr(SPRN_PCR, PCR_MASK); + + /* HDEC must be at least as large as DEC, so decrementer_max fits */ + mtspr(SPRN_HDEC, decrementer_max); + + timer_rearm_host_dec(*tb); + + restore_p9_host_os_sprs(vcpu, &host_os_sprs); + + barrier(); /* Close in_guest critical section */ + WRITE_ONCE(local_paca->kvm_hstate.in_guest, KVM_GUEST_MODE_NONE); + /* Interrupts are recoverable at this point */ + + /* + * cp_abort is required if the processor supports local copy-paste + * to clear the copy buffer that was under control of the guest. + */ + if (cpu_has_feature(CPU_FTR_ARCH_31)) + asm volatile(PPC_CP_ABORT); + +out: end_timing(vcpu); return trap; diff --git a/arch/powerpc/kvm/book3s_hv_ras.c b/arch/powerpc/kvm/book3s_hv_ras.c index d4bca93b79f6..ccfd96965630 100644 --- a/arch/powerpc/kvm/book3s_hv_ras.c +++ b/arch/powerpc/kvm/book3s_hv_ras.c @@ -136,6 +136,60 @@ void kvmppc_realmode_machine_check(struct kvm_vcpu *vcpu) vcpu->arch.mce_evt = mce_evt; } + +long kvmppc_p9_realmode_hmi_handler(struct kvm_vcpu *vcpu) +{ + struct kvmppc_vcore *vc = vcpu->arch.vcore; + long ret = 0; + + /* + * Unapply and clear the offset first. That way, if the TB was not + * resynced then it will remain in host-offset, and if it was resynced + * then it is brought into host-offset. Then the tb offset is + * re-applied before continuing with the KVM exit. + * + * This way, we don't need to actually know whether not OPAL resynced + * the timebase or do any of the complicated dance that the P7/8 + * path requires. + */ + if (vc->tb_offset_applied) { + u64 new_tb = mftb() - vc->tb_offset_applied; + mtspr(SPRN_TBU40, new_tb); + if ((mftb() & 0xffffff) < (new_tb & 0xffffff)) { + new_tb += 0x1000000; + mtspr(SPRN_TBU40, new_tb); + } + vc->tb_offset_applied = 0; + } + + local_paca->hmi_irqs++; + + if (hmi_handle_debugtrig(NULL) >= 0) { + ret = 1; + goto out; + } + + if (ppc_md.hmi_exception_early) + ppc_md.hmi_exception_early(NULL); + +out: + if (vc->tb_offset) { + u64 new_tb = mftb() + vc->tb_offset; + mtspr(SPRN_TBU40, new_tb); + if ((mftb() & 0xffffff) < (new_tb & 0xffffff)) { + new_tb += 0x1000000; + mtspr(SPRN_TBU40, new_tb); + } + vc->tb_offset_applied = vc->tb_offset; + } + + return ret; +} + +/* + * The following subcore HMI handling is all only for pre-POWER9 CPUs. + */ + /* Check if dynamic split is in force and return subcore size accordingly. */ static inline int kvmppc_cur_subcore_size(void) { diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c index 2c1f3c6e72d1..2257fb18cb72 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c +++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c @@ -55,12 +55,6 @@ static int global_invalidates(struct kvm *kvm) smp_wmb(); cpumask_setall(&kvm->arch.need_tlb_flush); cpu = local_paca->kvm_hstate.kvm_vcore->pcpu; - /* - * On POWER9, threads are independent but the TLB is shared, - * so use the bit for the first thread to represent the core. - */ - if (cpu_has_feature(CPU_FTR_ARCH_300)) - cpu = cpu_first_tlb_thread_sibling(cpu); cpumask_clear_cpu(cpu, &kvm->arch.need_tlb_flush); } diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 32a4b4d412b9..3f1aeff72438 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -778,17 +778,14 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) /* Restore AMR and UAMOR, set AMOR to all 1s */ ld r5,VCPU_AMR(r4) ld r6,VCPU_UAMOR(r4) - li r7,-1 mtspr SPRN_AMR,r5 mtspr SPRN_UAMOR,r6 - mtspr SPRN_AMOR,r7 - /* Restore state of CTRL run bit; assume 1 on entry */ + /* Restore state of CTRL run bit; the host currently has it set to 1 */ lwz r5,VCPU_CTRL(r4) andi. r5,r5,1 bne 4f - mfspr r6,SPRN_CTRLF - clrrdi r6,r6,1 + li r6,0 mtspr SPRN_CTRLT,r6 4: /* Secondary threads wait for primary to have done partition switch */ @@ -817,10 +814,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) * Set the decrementer to the guest decrementer. */ ld r8,VCPU_DEC_EXPIRES(r4) - /* r8 is a host timebase value here, convert to guest TB */ - ld r5,HSTATE_KVM_VCORE(r13) - ld r6,VCORE_TB_OFFSET_APPL(r5) - add r8,r8,r6 mftb r7 subf r3,r7,r8 mtspr SPRN_DEC,r3 @@ -1195,9 +1188,6 @@ guest_bypass: mftb r6 extsw r5,r5 16: add r5,r5,r6 - /* r5 is a guest timebase value here, convert to host TB */ - ld r4,VCORE_TB_OFFSET_APPL(r3) - subf r5,r4,r5 std r5,VCPU_DEC_EXPIRES(r9) /* Increment exit count, poke other threads to exit */ @@ -1211,12 +1201,12 @@ guest_bypass: stw r0, VCPU_CPU(r9) stw r0, VCPU_THREAD_CPU(r9) - /* Save guest CTRL register, set runlatch to 1 */ + /* Save guest CTRL register, set runlatch to 1 if it was clear */ mfspr r6,SPRN_CTRLF stw r6,VCPU_CTRL(r9) andi. r0,r6,1 bne 4f - ori r6,r6,1 + li r6,1 mtspr SPRN_CTRLT,r6 4: /* @@ -2163,9 +2153,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_TM) /* save expiry time of guest decrementer */ add r3, r3, r5 ld r4, HSTATE_KVM_VCPU(r13) - ld r5, HSTATE_KVM_VCORE(r13) - ld r6, VCORE_TB_OFFSET_APPL(r5) - subf r3, r6, r3 /* convert to host TB value */ std r3, VCPU_DEC_EXPIRES(r4) #ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING @@ -2186,8 +2173,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_TM) * Also clear the runlatch bit before napping. */ kvm_do_nap: - mfspr r0, SPRN_CTRLF - clrrdi r0, r0, 1 + li r0,0 mtspr SPRN_CTRLT, r0 li r0,1 @@ -2206,8 +2192,7 @@ kvm_nap_sequence: /* desired LPCR value in r5 */ bl isa206_idle_insn_mayloss - mfspr r0, SPRN_CTRLF - ori r0, r0, 1 + li r0,1 mtspr SPRN_CTRLT, r0 mtspr SPRN_SRR1, r3 @@ -2264,9 +2249,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_TM) /* Restore guest decrementer */ ld r3, VCPU_DEC_EXPIRES(r4) - ld r5, HSTATE_KVM_VCORE(r13) - ld r6, VCORE_TB_OFFSET_APPL(r5) - add r3, r3, r6 /* convert host TB to guest TB value */ mftb r7 subf r3, r7, r3 mtspr SPRN_DEC, r3 @@ -2778,10 +2760,11 @@ kvmppc_msr_interrupt: blr /* + * void kvmhv_load_guest_pmu(struct kvm_vcpu *vcpu) + * * Load up guest PMU state. R3 points to the vcpu struct. */ -_GLOBAL(kvmhv_load_guest_pmu) -EXPORT_SYMBOL_GPL(kvmhv_load_guest_pmu) +kvmhv_load_guest_pmu: mr r4, r3 mflr r0 li r3, 1 @@ -2816,26 +2799,16 @@ END_FTR_SECTION_IFSET(CPU_FTR_PMAO_BUG) mtspr SPRN_SIAR, r7 mtspr SPRN_SDAR, r8 BEGIN_FTR_SECTION - ld r5, VCPU_MMCR + 24(r4) - ld r6, VCPU_SIER + 8(r4) - ld r7, VCPU_SIER + 16(r4) - mtspr SPRN_MMCR3, r5 - mtspr SPRN_SIER2, r6 - mtspr SPRN_SIER3, r7 -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_31) -BEGIN_FTR_SECTION ld r5, VCPU_MMCR + 16(r4) ld r6, VCPU_SIER(r4) mtspr SPRN_MMCR2, r5 mtspr SPRN_SIER, r6 -BEGIN_FTR_SECTION_NESTED(96) lwz r7, VCPU_PMC + 24(r4) lwz r8, VCPU_PMC + 28(r4) ld r9, VCPU_MMCRS(r4) mtspr SPRN_SPMC1, r7 mtspr SPRN_SPMC2, r8 mtspr SPRN_MMCRS, r9 -END_FTR_SECTION_NESTED(CPU_FTR_ARCH_300, 0, 96) END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) mtspr SPRN_MMCR0, r3 isync @@ -2843,10 +2816,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) blr /* + * void kvmhv_load_host_pmu(void) + * * Reload host PMU state saved in the PACA by kvmhv_save_host_pmu. */ -_GLOBAL(kvmhv_load_host_pmu) -EXPORT_SYMBOL_GPL(kvmhv_load_host_pmu) +kvmhv_load_host_pmu: mflr r0 lbz r4, PACA_PMCINUSE(r13) /* is the host using the PMU? */ cmpwi r4, 0 @@ -2884,25 +2858,18 @@ BEGIN_FTR_SECTION mtspr SPRN_MMCR2, r8 mtspr SPRN_SIER, r9 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) -BEGIN_FTR_SECTION - ld r5, HSTATE_MMCR3(r13) - ld r6, HSTATE_SIER2(r13) - ld r7, HSTATE_SIER3(r13) - mtspr SPRN_MMCR3, r5 - mtspr SPRN_SIER2, r6 - mtspr SPRN_SIER3, r7 -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_31) mtspr SPRN_MMCR0, r3 isync mtlr r0 23: blr /* + * void kvmhv_save_guest_pmu(struct kvm_vcpu *vcpu, bool pmu_in_use) + * * Save guest PMU state into the vcpu struct. * r3 = vcpu, r4 = full save flag (PMU in use flag set in VPA) */ -_GLOBAL(kvmhv_save_guest_pmu) -EXPORT_SYMBOL_GPL(kvmhv_save_guest_pmu) +kvmhv_save_guest_pmu: mr r9, r3 mr r8, r4 BEGIN_FTR_SECTION @@ -2951,14 +2918,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) BEGIN_FTR_SECTION std r10, VCPU_MMCR + 16(r9) END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) -BEGIN_FTR_SECTION - mfspr r5, SPRN_MMCR3 - mfspr r6, SPRN_SIER2 - mfspr r7, SPRN_SIER3 - std r5, VCPU_MMCR + 24(r9) - std r6, VCPU_SIER + 8(r9) - std r7, VCPU_SIER + 16(r9) -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_31) std r7, VCPU_SIAR(r9) std r8, VCPU_SDAR(r9) mfspr r3, SPRN_PMC1 @@ -2976,7 +2935,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_31) BEGIN_FTR_SECTION mfspr r5, SPRN_SIER std r5, VCPU_SIER(r9) -BEGIN_FTR_SECTION_NESTED(96) mfspr r6, SPRN_SPMC1 mfspr r7, SPRN_SPMC2 mfspr r8, SPRN_MMCRS @@ -2985,7 +2943,6 @@ BEGIN_FTR_SECTION_NESTED(96) std r8, VCPU_MMCRS(r9) lis r4, 0x8000 mtspr SPRN_MMCRS, r4 -END_FTR_SECTION_NESTED(CPU_FTR_ARCH_300, 0, 96) END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) 22: blr diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c index 28c436df9935..e414ca44839f 100644 --- a/arch/powerpc/kvm/book3s_hv_uvmem.c +++ b/arch/powerpc/kvm/book3s_hv_uvmem.c @@ -459,7 +459,7 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm) struct kvm_memslots *slots; struct kvm_memory_slot *memslot, *m; int ret = H_SUCCESS; - int srcu_idx; + int srcu_idx, bkt; kvm->arch.secure_guest = KVMPPC_SECURE_INIT_START; @@ -478,7 +478,7 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm) /* register the memslot */ slots = kvm_memslots(kvm); - kvm_for_each_memslot(memslot, slots) { + kvm_for_each_memslot(memslot, bkt, slots) { ret = __kvmppc_uvmem_memslot_create(kvm, memslot); if (ret) break; @@ -486,7 +486,7 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm) if (ret) { slots = kvm_memslots(kvm); - kvm_for_each_memslot(m, slots) { + kvm_for_each_memslot(m, bkt, slots) { if (m == memslot) break; __kvmppc_uvmem_memslot_delete(kvm, memslot); @@ -647,7 +647,7 @@ void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *slot, unsigned long kvmppc_h_svm_init_abort(struct kvm *kvm) { - int srcu_idx; + int srcu_idx, bkt; struct kvm_memory_slot *memslot; /* @@ -662,7 +662,7 @@ unsigned long kvmppc_h_svm_init_abort(struct kvm *kvm) srcu_idx = srcu_read_lock(&kvm->srcu); - kvm_for_each_memslot(memslot, kvm_memslots(kvm)) + kvm_for_each_memslot(memslot, bkt, kvm_memslots(kvm)) kvmppc_uvmem_drop_pages(memslot, kvm, false); srcu_read_unlock(&kvm->srcu, srcu_idx); @@ -821,7 +821,7 @@ unsigned long kvmppc_h_svm_init_done(struct kvm *kvm) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; - int srcu_idx; + int srcu_idx, bkt; long ret = H_SUCCESS; if (!(kvm->arch.secure_guest & KVMPPC_SECURE_INIT_START)) @@ -830,7 +830,7 @@ unsigned long kvmppc_h_svm_init_done(struct kvm *kvm) /* migrate any unmoved normal pfn to device pfns*/ srcu_idx = srcu_read_lock(&kvm->srcu); slots = kvm_memslots(kvm); - kvm_for_each_memslot(memslot, slots) { + kvm_for_each_memslot(memslot, bkt, slots) { ret = kvmppc_uv_migrate_mem_slot(kvm, memslot); if (ret) { /* diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index 6bc9425acb32..34a801c3604a 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -428,7 +428,7 @@ static int kvmppc_core_check_requests_pr(struct kvm_vcpu *vcpu) /************* MMU Notifiers *************/ static bool do_kvm_unmap_gfn(struct kvm *kvm, struct kvm_gfn_range *range) { - long i; + unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) @@ -492,7 +492,7 @@ static void kvmppc_set_msr_pr(struct kvm_vcpu *vcpu, u64 msr) if (msr & MSR_POW) { if (!vcpu->arch.pending_exceptions) { - kvm_vcpu_block(vcpu); + kvm_vcpu_halt(vcpu); kvm_clear_request(KVM_REQ_UNHALT, vcpu); vcpu->stat.generic.halt_wakeup++; @@ -1899,16 +1899,15 @@ static void kvmppc_core_flush_memslot_pr(struct kvm *kvm, } static int kvmppc_core_prepare_memory_region_pr(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, - enum kvm_mr_change change) + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, + enum kvm_mr_change change) { return 0; } static void kvmppc_core_commit_memory_region_pr(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old, + struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c index ac14239f3424..1f10e7dfcdd0 100644 --- a/arch/powerpc/kvm/book3s_pr_papr.c +++ b/arch/powerpc/kvm/book3s_pr_papr.c @@ -376,7 +376,7 @@ int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd) return kvmppc_h_pr_stuff_tce(vcpu); case H_CEDE: kvmppc_set_msr_fast(vcpu, kvmppc_get_msr(vcpu) | MSR_EE); - kvm_vcpu_block(vcpu); + kvm_vcpu_halt(vcpu); kvm_clear_request(KVM_REQ_UNHALT, vcpu); vcpu->stat.generic.halt_wakeup++; return EMULATE_DONE; diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c index ebd5d920de8c..9cc466006e8b 100644 --- a/arch/powerpc/kvm/book3s_xics.c +++ b/arch/powerpc/kvm/book3s_xics.c @@ -942,8 +942,8 @@ static int xics_debug_show(struct seq_file *m, void *private) struct kvmppc_xics *xics = m->private; struct kvm *kvm = xics->kvm; struct kvm_vcpu *vcpu; - int icsid, i; - unsigned long flags; + int icsid; + unsigned long flags, i; unsigned long t_rm_kick_vcpu, t_rm_check_resend; unsigned long t_rm_notify_eoi; unsigned long t_reject, t_check_resend; @@ -1340,7 +1340,7 @@ static int xics_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr) static void kvmppc_xics_release(struct kvm_device *dev) { struct kvmppc_xics *xics = dev->private; - int i; + unsigned long i; struct kvm *kvm = xics->kvm; struct kvm_vcpu *vcpu; diff --git a/arch/powerpc/kvm/book3s_xics.h b/arch/powerpc/kvm/book3s_xics.h index 6231f76bdd66..8e4c79e2fcd8 100644 --- a/arch/powerpc/kvm/book3s_xics.h +++ b/arch/powerpc/kvm/book3s_xics.h @@ -116,7 +116,7 @@ static inline struct kvmppc_icp *kvmppc_xics_find_server(struct kvm *kvm, u32 nr) { struct kvm_vcpu *vcpu = NULL; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu->arch.icp && nr == vcpu->arch.icp->server_num) diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c index 225008882958..e216c068075d 100644 --- a/arch/powerpc/kvm/book3s_xive.c +++ b/arch/powerpc/kvm/book3s_xive.c @@ -368,7 +368,8 @@ static int xive_check_provisioning(struct kvm *kvm, u8 prio) { struct kvmppc_xive *xive = kvm->arch.xive; struct kvm_vcpu *vcpu; - int i, rc; + unsigned long i; + int rc; lockdep_assert_held(&xive->lock); @@ -439,7 +440,8 @@ static int xive_try_pick_queue(struct kvm_vcpu *vcpu, u8 prio) int kvmppc_xive_select_target(struct kvm *kvm, u32 *server, u8 prio) { struct kvm_vcpu *vcpu; - int i, rc; + unsigned long i; + int rc; /* Locate target server */ vcpu = kvmppc_xive_find_server(kvm, *server); @@ -1519,7 +1521,8 @@ static void xive_pre_save_queue(struct kvmppc_xive *xive, struct xive_q *q) static void xive_pre_save_scan(struct kvmppc_xive *xive) { struct kvm_vcpu *vcpu = NULL; - int i, j; + unsigned long i; + int j; /* * See comment in xive_get_source() about how this @@ -1700,7 +1703,7 @@ static bool xive_check_delayed_irq(struct kvmppc_xive *xive, u32 irq) { struct kvm *kvm = xive->kvm; struct kvm_vcpu *vcpu = NULL; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu; @@ -2037,7 +2040,7 @@ static void kvmppc_xive_release(struct kvm_device *dev) struct kvmppc_xive *xive = dev->private; struct kvm *kvm = xive->kvm; struct kvm_vcpu *vcpu; - int i; + unsigned long i; pr_devel("Releasing xive device\n"); @@ -2291,7 +2294,7 @@ static int xive_debug_show(struct seq_file *m, void *private) u64 t_vm_h_cppr = 0; u64 t_vm_h_eoi = 0; u64 t_vm_h_ipi = 0; - unsigned int i; + unsigned long i; if (!kvm) return 0; diff --git a/arch/powerpc/kvm/book3s_xive.h b/arch/powerpc/kvm/book3s_xive.h index e6a9651c6f1e..09d0657596c3 100644 --- a/arch/powerpc/kvm/book3s_xive.h +++ b/arch/powerpc/kvm/book3s_xive.h @@ -199,7 +199,7 @@ struct kvmppc_xive_vcpu { static inline struct kvm_vcpu *kvmppc_xive_find_server(struct kvm *kvm, u32 nr) { struct kvm_vcpu *vcpu = NULL; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu->arch.xive_vcpu && nr == vcpu->arch.xive_vcpu->server_num) @@ -240,7 +240,7 @@ static inline u32 kvmppc_xive_vp(struct kvmppc_xive *xive, u32 server) static inline bool kvmppc_xive_vp_in_use(struct kvm *kvm, u32 vp_id) { struct kvm_vcpu *vcpu = NULL; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu->arch.xive_vcpu && vp_id == vcpu->arch.xive_vcpu->vp_id) diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c index 99db9ac49901..561a5bfe0468 100644 --- a/arch/powerpc/kvm/book3s_xive_native.c +++ b/arch/powerpc/kvm/book3s_xive_native.c @@ -807,7 +807,7 @@ static int kvmppc_xive_reset(struct kvmppc_xive *xive) { struct kvm *kvm = xive->kvm; struct kvm_vcpu *vcpu; - unsigned int i; + unsigned long i; pr_devel("%s\n", __func__); @@ -916,7 +916,7 @@ static int kvmppc_xive_native_eq_sync(struct kvmppc_xive *xive) { struct kvm *kvm = xive->kvm; struct kvm_vcpu *vcpu; - unsigned int i; + unsigned long i; pr_devel("%s\n", __func__); @@ -1017,7 +1017,7 @@ static void kvmppc_xive_native_release(struct kvm_device *dev) struct kvmppc_xive *xive = dev->private; struct kvm *kvm = xive->kvm; struct kvm_vcpu *vcpu; - int i; + unsigned long i; pr_devel("Releasing xive native device\n"); @@ -1214,7 +1214,7 @@ static int xive_native_debug_show(struct seq_file *m, void *private) struct kvmppc_xive *xive = m->private; struct kvm *kvm = xive->kvm; struct kvm_vcpu *vcpu; - unsigned int i; + unsigned long i; if (!kvm) return 0; diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 8c15c90dd3a9..06c5830a93f9 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -718,7 +718,7 @@ int kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu) if (vcpu->arch.shared->msr & MSR_WE) { local_irq_enable(); - kvm_vcpu_block(vcpu); + kvm_vcpu_halt(vcpu); kvm_clear_request(KVM_REQ_UNHALT, vcpu); hard_irq_disable(); @@ -1821,16 +1821,15 @@ void kvmppc_core_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) } int kvmppc_core_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, enum kvm_mr_change change) { return 0; } void kvmppc_core_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old, + struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { diff --git a/arch/powerpc/kvm/e500_emulate.c b/arch/powerpc/kvm/e500_emulate.c index 64eb833e9f02..051102d50c31 100644 --- a/arch/powerpc/kvm/e500_emulate.c +++ b/arch/powerpc/kvm/e500_emulate.c @@ -65,7 +65,7 @@ static int kvmppc_e500_emul_msgsnd(struct kvm_vcpu *vcpu, int rb) ulong param = vcpu->arch.regs.gpr[rb]; int prio = dbell2prio(rb); int pir = param & PPC_DBELL_PIR_MASK; - int i; + unsigned long i; struct kvm_vcpu *cvcpu; if (prio < 0) diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index a72920f4f221..2ad0ccd202d5 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -236,7 +236,7 @@ int kvmppc_kvm_pv(struct kvm_vcpu *vcpu) break; case EV_HCALL_TOKEN(EV_IDLE): r = EV_SUCCESS; - kvm_vcpu_block(vcpu); + kvm_vcpu_halt(vcpu); kvm_clear_request(KVM_REQ_UNHALT, vcpu); break; default: @@ -463,9 +463,6 @@ err_out: void kvm_arch_destroy_vm(struct kvm *kvm) { - unsigned int i; - struct kvm_vcpu *vcpu; - #ifdef CONFIG_KVM_XICS /* * We call kick_all_cpus_sync() to ensure that all @@ -476,14 +473,9 @@ void kvm_arch_destroy_vm(struct kvm *kvm) kick_all_cpus_sync(); #endif - kvm_for_each_vcpu(i, vcpu, kvm) - kvm_vcpu_destroy(vcpu); + kvm_destroy_vcpus(kvm); mutex_lock(&kvm->lock); - for (i = 0; i < atomic_read(&kvm->online_vcpus); i++) - kvm->vcpus[i] = NULL; - - atomic_set(&kvm->online_vcpus, 0); kvmppc_core_destroy_vm(kvm); @@ -706,20 +698,19 @@ void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) } int kvm_arch_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, enum kvm_mr_change change) { - return kvmppc_core_prepare_memory_region(kvm, memslot, mem, change); + return kvmppc_core_prepare_memory_region(kvm, old, new, change); } void kvm_arch_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { - kvmppc_core_commit_memory_region(kvm, mem, old, new, change); + kvmppc_core_commit_memory_region(kvm, old, new, change); } void kvm_arch_flush_shadow_memslot(struct kvm *kvm, @@ -762,7 +753,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) if (err) goto out_vcpu_uninit; - vcpu->arch.waitp = &vcpu->wait; + rcuwait_init(&vcpu->arch.wait); + vcpu->arch.waitp = &vcpu->arch.wait; kvmppc_create_vcpu_debugfs(vcpu, vcpu->vcpu_id); return 0; diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c index 3a600bd7fbc6..77820036c722 100644 --- a/arch/powerpc/mm/book3s64/radix_pgtable.c +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c @@ -572,18 +572,6 @@ void __init radix__early_init_devtree(void) return; } -static void radix_init_amor(void) -{ - /* - * In HV mode, we init AMOR (Authority Mask Override Register) so that - * the hypervisor and guest can setup IAMR (Instruction Authority Mask - * Register), enable key 0 and set it to 1. - * - * AMOR = 0b1100 .... 0000 (Mask for key 0 is 11) - */ - mtspr(SPRN_AMOR, (3ul << 62)); -} - void __init radix__early_init_mmu(void) { unsigned long lpcr; @@ -644,7 +632,6 @@ void __init radix__early_init_mmu(void) lpcr = mfspr(SPRN_LPCR); mtspr(SPRN_LPCR, lpcr | LPCR_UPRT | LPCR_HR); radix_init_partition_table(); - radix_init_amor(); } else { radix_init_pseries(); } @@ -668,8 +655,6 @@ void radix__early_init_mmu_secondary(void) set_ptcr_when_no_uv(__pa(partition_tb) | (PATB_SIZE_SHIFT - 12)); - - radix_init_amor(); } radix__switch_mmu_context(NULL, &init_mm); diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 73e62e9b179b..8d4ff93462fb 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -2419,8 +2419,24 @@ int register_power_pmu(struct power_pmu *pmu) } #ifdef CONFIG_PPC64 +static bool pmu_override = false; +static unsigned long pmu_override_val; +static void do_pmu_override(void *data) +{ + ppc_set_pmu_inuse(1); + if (pmu_override_val) + mtspr(SPRN_MMCR1, pmu_override_val); + mtspr(SPRN_MMCR0, mfspr(SPRN_MMCR0) & ~MMCR0_FC); +} + static int __init init_ppc64_pmu(void) { + if (cpu_has_feature(CPU_FTR_HVMODE) && pmu_override) { + pr_warn("disabling perf due to pmu_override= command line option.\n"); + on_each_cpu(do_pmu_override, NULL, 1); + return 0; + } + /* run through all the pmu drivers one at a time */ if (!init_power5_pmu()) return 0; @@ -2442,4 +2458,23 @@ static int __init init_ppc64_pmu(void) return init_generic_compat_pmu(); } early_initcall(init_ppc64_pmu); + +static int __init pmu_setup(char *str) +{ + unsigned long val; + + if (!early_cpu_has_feature(CPU_FTR_HVMODE)) + return 0; + + pmu_override = true; + + if (kstrtoul(str, 0, &val)) + val = 0; + + pmu_override_val = val; + + return 1; +} +__setup("pmu_override=", pmu_setup); + #endif diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c index e3ffdc8e8567..3bc84e2fe064 100644 --- a/arch/powerpc/platforms/powernv/idle.c +++ b/arch/powerpc/platforms/powernv/idle.c @@ -306,8 +306,8 @@ struct p7_sprs { /* per thread SPRs that get lost in shallow states */ u64 amr; u64 iamr; - u64 amor; u64 uamor; + /* amor is restored to constant ~0 */ }; static unsigned long power7_idle_insn(unsigned long type) @@ -378,7 +378,6 @@ static unsigned long power7_idle_insn(unsigned long type) if (cpu_has_feature(CPU_FTR_ARCH_207S)) { sprs.amr = mfspr(SPRN_AMR); sprs.iamr = mfspr(SPRN_IAMR); - sprs.amor = mfspr(SPRN_AMOR); sprs.uamor = mfspr(SPRN_UAMOR); } @@ -397,7 +396,7 @@ static unsigned long power7_idle_insn(unsigned long type) */ mtspr(SPRN_AMR, sprs.amr); mtspr(SPRN_IAMR, sprs.iamr); - mtspr(SPRN_AMOR, sprs.amor); + mtspr(SPRN_AMOR, ~0); mtspr(SPRN_UAMOR, sprs.uamor); } } @@ -589,7 +588,6 @@ struct p9_sprs { u64 purr; u64 spurr; u64 dscr; - u64 wort; u64 ciabr; u64 mmcra; @@ -687,7 +685,6 @@ static unsigned long power9_idle_stop(unsigned long psscr) sprs.amr = mfspr(SPRN_AMR); sprs.iamr = mfspr(SPRN_IAMR); - sprs.amor = mfspr(SPRN_AMOR); sprs.uamor = mfspr(SPRN_UAMOR); srr1 = isa300_idle_stop_mayloss(psscr); /* go idle */ @@ -708,7 +705,7 @@ static unsigned long power9_idle_stop(unsigned long psscr) */ mtspr(SPRN_AMR, sprs.amr); mtspr(SPRN_IAMR, sprs.iamr); - mtspr(SPRN_AMOR, sprs.amor); + mtspr(SPRN_AMOR, ~0); mtspr(SPRN_UAMOR, sprs.uamor); /* diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 8b28ff9d98d1..83100c6524cc 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -2107,8 +2107,14 @@ static void dump_300_sprs(void) if (!cpu_has_feature(CPU_FTR_ARCH_300)) return; - printf("pidr = %.16lx tidr = %.16lx\n", - mfspr(SPRN_PID), mfspr(SPRN_TIDR)); + if (cpu_has_feature(CPU_FTR_P9_TIDR)) { + printf("pidr = %.16lx tidr = %.16lx\n", + mfspr(SPRN_PID), mfspr(SPRN_TIDR)); + } else { + printf("pidr = %.16lx\n", + mfspr(SPRN_PID)); + } + printf("psscr = %.16lx\n", hv ? mfspr(SPRN_PSSCR) : mfspr(SPRN_PSSCR_PR)); diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h index 2639b9ee48f9..907fafea787e 100644 --- a/arch/riscv/include/asm/kvm_host.h +++ b/arch/riscv/include/asm/kvm_host.h @@ -208,7 +208,6 @@ struct kvm_vcpu_arch { static inline void kvm_arch_hardware_unsetup(void) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} -static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {} #define KVM_ARCH_WANT_MMU_NOTIFIER diff --git a/arch/riscv/kvm/Makefile b/arch/riscv/kvm/Makefile index 30cdd1df0098..300590225348 100644 --- a/arch/riscv/kvm/Makefile +++ b/arch/riscv/kvm/Makefile @@ -5,14 +5,10 @@ ccflags-y += -I $(srctree)/$(src) -KVM := ../../../virt/kvm +include $(srctree)/virt/kvm/Makefile.kvm obj-$(CONFIG_KVM) += kvm.o -kvm-y += $(KVM)/kvm_main.o -kvm-y += $(KVM)/coalesced_mmio.o -kvm-y += $(KVM)/binary_stats.o -kvm-y += $(KVM)/eventfd.o kvm-y += main.o kvm-y += vm.o kvm-y += vmid.o diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c index fc058ff5f4b6..7d884b15cf5e 100644 --- a/arch/riscv/kvm/mmu.c +++ b/arch/riscv/kvm/mmu.c @@ -462,7 +462,6 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm, } void kvm_arch_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) @@ -472,18 +471,18 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, * allocated dirty_bitmap[], dirty pages will be tracked while * the memory slot is write protected. */ - if (change != KVM_MR_DELETE && mem->flags & KVM_MEM_LOG_DIRTY_PAGES) - stage2_wp_memory_region(kvm, mem->slot); + if (change != KVM_MR_DELETE && new->flags & KVM_MEM_LOG_DIRTY_PAGES) + stage2_wp_memory_region(kvm, new->id); } int kvm_arch_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, enum kvm_mr_change change) { - hva_t hva = mem->userspace_addr; - hva_t reg_end = hva + mem->memory_size; - bool writable = !(mem->flags & KVM_MEM_READONLY); + hva_t hva, reg_end, size; + gpa_t base_gpa; + bool writable; int ret = 0; if (change != KVM_MR_CREATE && change != KVM_MR_MOVE && @@ -494,10 +493,16 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, * Prevent userspace from creating a memory region outside of the GPA * space addressable by the KVM guest GPA space. */ - if ((memslot->base_gfn + memslot->npages) >= + if ((new->base_gfn + new->npages) >= (stage2_gpa_size >> PAGE_SHIFT)) return -EFAULT; + hva = new->userspace_addr; + size = new->npages << PAGE_SHIFT; + reg_end = hva + size; + base_gpa = new->base_gfn << PAGE_SHIFT; + writable = !(new->flags & KVM_MEM_READONLY); + mmap_read_lock(current->mm); /* @@ -533,15 +538,14 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, vm_end = min(reg_end, vma->vm_end); if (vma->vm_flags & VM_PFNMAP) { - gpa_t gpa = mem->guest_phys_addr + - (vm_start - mem->userspace_addr); + gpa_t gpa = base_gpa + (vm_start - hva); phys_addr_t pa; pa = (phys_addr_t)vma->vm_pgoff << PAGE_SHIFT; pa += vm_start - vma->vm_start; /* IO region dirty page logging not allowed */ - if (memslot->flags & KVM_MEM_LOG_DIRTY_PAGES) { + if (new->flags & KVM_MEM_LOG_DIRTY_PAGES) { ret = -EINVAL; goto out; } @@ -559,8 +563,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, spin_lock(&kvm->mmu_lock); if (ret) - stage2_unmap_range(kvm, mem->guest_phys_addr, - mem->memory_size, false); + stage2_unmap_range(kvm, base_gpa, size, false); spin_unlock(&kvm->mmu_lock); out: diff --git a/arch/riscv/kvm/vcpu_exit.c b/arch/riscv/kvm/vcpu_exit.c index 7f2d742ae4c6..571f319e995a 100644 --- a/arch/riscv/kvm/vcpu_exit.c +++ b/arch/riscv/kvm/vcpu_exit.c @@ -146,7 +146,7 @@ static int system_opcode_insn(struct kvm_vcpu *vcpu, vcpu->stat.wfi_exit_stat++; if (!kvm_arch_vcpu_runnable(vcpu)) { srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx); - kvm_vcpu_block(vcpu); + kvm_vcpu_halt(vcpu); vcpu->arch.srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); kvm_clear_request(KVM_REQ_UNHALT, vcpu); } diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c index 3b0e703d22cf..d0d2bcab2f7b 100644 --- a/arch/riscv/kvm/vcpu_sbi.c +++ b/arch/riscv/kvm/vcpu_sbi.c @@ -60,7 +60,7 @@ int kvm_riscv_vcpu_sbi_return(struct kvm_vcpu *vcpu, struct kvm_run *run) static void kvm_sbi_system_shutdown(struct kvm_vcpu *vcpu, struct kvm_run *run, u32 type) { - int i; + unsigned long i; struct kvm_vcpu *tmp; kvm_for_each_vcpu(i, tmp, vcpu->kvm) diff --git a/arch/riscv/kvm/vm.c b/arch/riscv/kvm/vm.c index fb18af34a4b5..7619691d8953 100644 --- a/arch/riscv/kvm/vm.c +++ b/arch/riscv/kvm/vm.c @@ -46,15 +46,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) void kvm_arch_destroy_vm(struct kvm *kvm) { - int i; - - for (i = 0; i < KVM_MAX_VCPUS; ++i) { - if (kvm->vcpus[i]) { - kvm_vcpu_destroy(kvm->vcpus[i]); - kvm->vcpus[i] = NULL; - } - } - atomic_set(&kvm->online_vcpus, 0); + kvm_destroy_vcpus(kvm); } int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) diff --git a/arch/riscv/kvm/vmid.c b/arch/riscv/kvm/vmid.c index 2c6253b293bc..807228f8f409 100644 --- a/arch/riscv/kvm/vmid.c +++ b/arch/riscv/kvm/vmid.c @@ -65,7 +65,7 @@ bool kvm_riscv_stage2_vmid_ver_changed(struct kvm_vmid *vmid) void kvm_riscv_stage2_vmid_update(struct kvm_vcpu *vcpu) { - int i; + unsigned long i; struct kvm_vcpu *v; struct cpumask hmask; struct kvm_vmid *vmid = &vcpu->kvm->arch.vmid; diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index a604d51acfc8..a22c9266ea05 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -1010,6 +1010,4 @@ static inline void kvm_arch_flush_shadow_memslot(struct kvm *kvm, static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {} static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {} -void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu); - #endif diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig index 67a8e770e369..2e84d3922f7c 100644 --- a/arch/s390/kvm/Kconfig +++ b/arch/s390/kvm/Kconfig @@ -33,6 +33,7 @@ config KVM select HAVE_KVM_NO_POLL select SRCU select KVM_VFIO + select INTERVAL_TREE help Support hosting paravirtualized guest machines using the SIE virtualization capability on the mainframe. This should work diff --git a/arch/s390/kvm/Makefile b/arch/s390/kvm/Makefile index b3aaadc60ead..26f4a74e5ce4 100644 --- a/arch/s390/kvm/Makefile +++ b/arch/s390/kvm/Makefile @@ -3,13 +3,11 @@ # # Copyright IBM Corp. 2008 -KVM := ../../../virt/kvm -common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o $(KVM)/async_pf.o \ - $(KVM)/irqchip.o $(KVM)/vfio.o $(KVM)/binary_stats.o +include $(srctree)/virt/kvm/Makefile.kvm ccflags-y := -Ivirt/kvm -Iarch/s390/kvm -kvm-objs := $(common-objs) kvm-s390.o intercept.o interrupt.o priv.o sigp.o -kvm-objs += diag.o gaccess.o guestdbg.o vsie.o pv.o +kvm-y += kvm-s390.o intercept.o interrupt.o priv.o sigp.o +kvm-y += diag.o gaccess.o guestdbg.o vsie.o pv.o obj-$(CONFIG_KVM) += kvm.o diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index c3bd993fdd0c..dbabd6f2404e 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -1335,7 +1335,8 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu) VCPU_EVENT(vcpu, 4, "enabled wait: %llu ns", sltime); no_timer: srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); - kvm_vcpu_block(vcpu); + kvm_vcpu_halt(vcpu); + vcpu->valid_wakeup = false; __unset_cpu_idle(vcpu); vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); @@ -2659,7 +2660,7 @@ static int flic_ais_mode_set_all(struct kvm *kvm, struct kvm_device_attr *attr) static int flic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { int r = 0; - unsigned int i; + unsigned long i; struct kvm_vcpu *vcpu; switch (attr->group) { diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 14a18ba5ff2c..dd099d352753 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -295,7 +295,7 @@ static int kvm_clock_sync(struct notifier_block *notifier, unsigned long val, { struct kvm *kvm; struct kvm_vcpu *vcpu; - int i; + unsigned long i; unsigned long long *delta = v; list_for_each_entry(kvm, &vm_list, vm_list) { @@ -682,7 +682,7 @@ out: static void icpt_operexc_on_all_vcpus(struct kvm *kvm) { - unsigned int i; + unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) { @@ -936,7 +936,7 @@ static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu); void kvm_s390_vcpu_crypto_reset_all(struct kvm *kvm) { struct kvm_vcpu *vcpu; - int i; + unsigned long i; kvm_s390_vcpu_block_all(kvm); @@ -1021,7 +1021,7 @@ static int kvm_s390_vm_set_crypto(struct kvm *kvm, struct kvm_device_attr *attr) static void kvm_s390_sync_request_broadcast(struct kvm *kvm, int req) { - int cx; + unsigned long cx; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(cx, vcpu, kvm) @@ -1037,13 +1037,13 @@ static int kvm_s390_vm_start_migration(struct kvm *kvm) struct kvm_memory_slot *ms; struct kvm_memslots *slots; unsigned long ram_pages = 0; - int slotnr; + int bkt; /* migration mode already enabled */ if (kvm->arch.migration_mode) return 0; slots = kvm_memslots(kvm); - if (!slots || !slots->used_slots) + if (!slots || kvm_memslots_empty(slots)) return -EINVAL; if (!kvm->arch.use_cmma) { @@ -1051,8 +1051,7 @@ static int kvm_s390_vm_start_migration(struct kvm *kvm) return 0; } /* mark all the pages in active slots as dirty */ - for (slotnr = 0; slotnr < slots->used_slots; slotnr++) { - ms = slots->memslots + slotnr; + kvm_for_each_memslot(ms, bkt, slots) { if (!ms->dirty_bitmap) return -EINVAL; /* @@ -1943,41 +1942,6 @@ out: /* for consistency */ #define KVM_S390_CMMA_SIZE_MAX ((u32)KVM_S390_SKEYS_MAX) -/* - * Similar to gfn_to_memslot, but returns the index of a memslot also when the - * address falls in a hole. In that case the index of one of the memslots - * bordering the hole is returned. - */ -static int gfn_to_memslot_approx(struct kvm_memslots *slots, gfn_t gfn) -{ - int start = 0, end = slots->used_slots; - int slot = atomic_read(&slots->last_used_slot); - struct kvm_memory_slot *memslots = slots->memslots; - - if (gfn >= memslots[slot].base_gfn && - gfn < memslots[slot].base_gfn + memslots[slot].npages) - return slot; - - while (start < end) { - slot = start + (end - start) / 2; - - if (gfn >= memslots[slot].base_gfn) - end = slot; - else - start = slot + 1; - } - - if (start >= slots->used_slots) - return slots->used_slots - 1; - - if (gfn >= memslots[start].base_gfn && - gfn < memslots[start].base_gfn + memslots[start].npages) { - atomic_set(&slots->last_used_slot, start); - } - - return start; -} - static int kvm_s390_peek_cmma(struct kvm *kvm, struct kvm_s390_cmma_log *args, u8 *res, unsigned long bufsize) { @@ -2001,26 +1965,31 @@ static int kvm_s390_peek_cmma(struct kvm *kvm, struct kvm_s390_cmma_log *args, return 0; } +static struct kvm_memory_slot *gfn_to_memslot_approx(struct kvm_memslots *slots, + gfn_t gfn) +{ + return ____gfn_to_memslot(slots, gfn, true); +} + static unsigned long kvm_s390_next_dirty_cmma(struct kvm_memslots *slots, unsigned long cur_gfn) { - int slotidx = gfn_to_memslot_approx(slots, cur_gfn); - struct kvm_memory_slot *ms = slots->memslots + slotidx; + struct kvm_memory_slot *ms = gfn_to_memslot_approx(slots, cur_gfn); unsigned long ofs = cur_gfn - ms->base_gfn; + struct rb_node *mnode = &ms->gfn_node[slots->node_idx]; if (ms->base_gfn + ms->npages <= cur_gfn) { - slotidx--; + mnode = rb_next(mnode); /* If we are above the highest slot, wrap around */ - if (slotidx < 0) - slotidx = slots->used_slots - 1; + if (!mnode) + mnode = rb_first(&slots->gfn_tree); - ms = slots->memslots + slotidx; + ms = container_of(mnode, struct kvm_memory_slot, gfn_node[slots->node_idx]); ofs = 0; } ofs = find_next_bit(kvm_second_dirty_bitmap(ms), ms->npages, ofs); - while ((slotidx > 0) && (ofs >= ms->npages)) { - slotidx--; - ms = slots->memslots + slotidx; + while (ofs >= ms->npages && (mnode = rb_next(mnode))) { + ms = container_of(mnode, struct kvm_memory_slot, gfn_node[slots->node_idx]); ofs = find_next_bit(kvm_second_dirty_bitmap(ms), ms->npages, 0); } return ms->base_gfn + ofs; @@ -2033,7 +2002,7 @@ static int kvm_s390_get_cmma(struct kvm *kvm, struct kvm_s390_cmma_log *args, struct kvm_memslots *slots = kvm_memslots(kvm); struct kvm_memory_slot *ms; - if (unlikely(!slots->used_slots)) + if (unlikely(kvm_memslots_empty(slots))) return 0; cur_gfn = kvm_s390_next_dirty_cmma(slots, args->start_gfn); @@ -2043,7 +2012,7 @@ static int kvm_s390_get_cmma(struct kvm *kvm, struct kvm_s390_cmma_log *args, if (!ms) return 0; next_gfn = kvm_s390_next_dirty_cmma(slots, cur_gfn + 1); - mem_end = slots->memslots[0].base_gfn + slots->memslots[0].npages; + mem_end = kvm_s390_get_gfn_end(slots); while (args->count < bufsize) { hva = gfn_to_hva(kvm, cur_gfn); @@ -2206,7 +2175,7 @@ static int kvm_s390_cpus_from_pv(struct kvm *kvm, u16 *rcp, u16 *rrcp) struct kvm_vcpu *vcpu; u16 rc, rrc; int ret = 0; - int i; + unsigned long i; /* * We ignore failures and try to destroy as many CPUs as possible. @@ -2230,7 +2199,8 @@ static int kvm_s390_cpus_from_pv(struct kvm *kvm, u16 *rcp, u16 *rrcp) static int kvm_s390_cpus_to_pv(struct kvm *kvm, u16 *rc, u16 *rrc) { - int i, r = 0; + unsigned long i; + int r = 0; u16 dummy; struct kvm_vcpu *vcpu; @@ -2821,27 +2791,11 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) free_page((unsigned long)(vcpu->arch.sie_block)); } -static void kvm_free_vcpus(struct kvm *kvm) -{ - unsigned int i; - struct kvm_vcpu *vcpu; - - kvm_for_each_vcpu(i, vcpu, kvm) - kvm_vcpu_destroy(vcpu); - - mutex_lock(&kvm->lock); - for (i = 0; i < atomic_read(&kvm->online_vcpus); i++) - kvm->vcpus[i] = NULL; - - atomic_set(&kvm->online_vcpus, 0); - mutex_unlock(&kvm->lock); -} - void kvm_arch_destroy_vm(struct kvm *kvm) { u16 rc, rrc; - kvm_free_vcpus(kvm); + kvm_destroy_vcpus(kvm); sca_dispose(kvm); kvm_s390_gisa_destroy(kvm); /* @@ -2945,7 +2899,7 @@ static int sca_switch_to_extended(struct kvm *kvm) struct bsca_block *old_sca = kvm->arch.sca; struct esca_block *new_sca; struct kvm_vcpu *vcpu; - unsigned int vcpu_idx; + unsigned long vcpu_idx; u32 scaol, scaoh; if (kvm->arch.use_esca) @@ -3427,7 +3381,7 @@ static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start, struct kvm *kvm = gmap->private; struct kvm_vcpu *vcpu; unsigned long prefix; - int i; + unsigned long i; if (gmap_is_shadow(gmap)) return; @@ -3449,7 +3403,7 @@ bool kvm_arch_no_poll(struct kvm_vcpu *vcpu) { /* do not poll with more than halt_poll_max_steal percent of steal time */ if (S390_lowcore.avg_steal_timer * 100 / (TICK_USEC << 12) >= - halt_poll_max_steal) { + READ_ONCE(halt_poll_max_steal)) { vcpu->stat.halt_no_poll_steal++; return true; } @@ -3920,7 +3874,7 @@ void kvm_s390_set_tod_clock(struct kvm *kvm, { struct kvm_vcpu *vcpu; union tod_clock clk; - int i; + unsigned long i; mutex_lock(&kvm->lock); preempt_disable(); @@ -4552,7 +4506,7 @@ static void __disable_ibs_on_vcpu(struct kvm_vcpu *vcpu) static void __disable_ibs_on_all_vcpus(struct kvm *kvm) { - unsigned int i; + unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) { @@ -4590,7 +4544,7 @@ int kvm_s390_vcpu_start(struct kvm_vcpu *vcpu) } for (i = 0; i < online_vcpus; i++) { - if (!is_vcpu_stopped(vcpu->kvm->vcpus[i])) + if (!is_vcpu_stopped(kvm_get_vcpu(vcpu->kvm, i))) started_vcpus++; } @@ -4652,9 +4606,11 @@ int kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu) __disable_ibs_on_vcpu(vcpu); for (i = 0; i < online_vcpus; i++) { - if (!is_vcpu_stopped(vcpu->kvm->vcpus[i])) { + struct kvm_vcpu *tmp = kvm_get_vcpu(vcpu->kvm, i); + + if (!is_vcpu_stopped(tmp)) { started_vcpus++; - started_vcpu = vcpu->kvm->vcpus[i]; + started_vcpu = tmp; } } @@ -5020,32 +4976,38 @@ vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf) /* Section: memory related */ int kvm_arch_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, enum kvm_mr_change change) { + gpa_t size; + + /* When we are protected, we should not change the memory slots */ + if (kvm_s390_pv_get_handle(kvm)) + return -EINVAL; + + if (change == KVM_MR_DELETE || change == KVM_MR_FLAGS_ONLY) + return 0; + /* A few sanity checks. We can have memory slots which have to be located/ended at a segment boundary (1MB). The memory in userland is ok to be fragmented into various different vmas. It is okay to mmap() and munmap() stuff in this slot after doing this call at any time */ - if (mem->userspace_addr & 0xffffful) + if (new->userspace_addr & 0xffffful) return -EINVAL; - if (mem->memory_size & 0xffffful) + size = new->npages * PAGE_SIZE; + if (size & 0xffffful) return -EINVAL; - if (mem->guest_phys_addr + mem->memory_size > kvm->arch.mem_limit) + if ((new->base_gfn * PAGE_SIZE) + size > kvm->arch.mem_limit) return -EINVAL; - /* When we are protected, we should not change the memory slots */ - if (kvm_s390_pv_get_handle(kvm)) - return -EINVAL; return 0; } void kvm_arch_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) @@ -5064,8 +5026,9 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, break; fallthrough; case KVM_MR_CREATE: - rc = gmap_map_segment(kvm->arch.gmap, mem->userspace_addr, - mem->guest_phys_addr, mem->memory_size); + rc = gmap_map_segment(kvm->arch.gmap, new->userspace_addr, + new->base_gfn * PAGE_SIZE, + new->npages * PAGE_SIZE); break; case KVM_MR_FLAGS_ONLY: break; @@ -5084,11 +5047,6 @@ static inline unsigned long nonhyp_mask(int i) return 0x0000ffffffffffffUL >> (nonhyp_fai << 4); } -void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) -{ - vcpu->valid_wakeup = false; -} - static int __init kvm_s390_init(void) { int i; diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index c07a050d757d..60f0effcce99 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -217,6 +217,20 @@ static inline void kvm_s390_set_user_cpu_state_ctrl(struct kvm *kvm) kvm->arch.user_cpu_state_ctrl = 1; } +/* get the end gfn of the last (highest gfn) memslot */ +static inline unsigned long kvm_s390_get_gfn_end(struct kvm_memslots *slots) +{ + struct rb_node *node; + struct kvm_memory_slot *ms; + + if (WARN_ON(kvm_memslots_empty(slots))) + return 0; + + node = rb_last(&slots->gfn_tree); + ms = container_of(node, struct kvm_memory_slot, gfn_node[slots->node_idx]); + return ms->base_gfn + ms->npages; +} + /* implemented in pv.c */ int kvm_s390_pv_destroy_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc); int kvm_s390_pv_create_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc); @@ -357,7 +371,7 @@ int kvm_s390_handle_diag(struct kvm_vcpu *vcpu); static inline void kvm_s390_vcpu_block_all(struct kvm *kvm) { - int i; + unsigned long i; struct kvm_vcpu *vcpu; WARN_ON(!mutex_is_locked(&kvm->lock)); @@ -367,7 +381,7 @@ static inline void kvm_s390_vcpu_block_all(struct kvm *kvm) static inline void kvm_s390_vcpu_unblock_all(struct kvm *kvm) { - int i; + unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c index 00d272d134c2..7f7c0d6af2ce 100644 --- a/arch/s390/kvm/pv.c +++ b/arch/s390/kvm/pv.c @@ -116,7 +116,6 @@ static int kvm_s390_pv_alloc_vm(struct kvm *kvm) unsigned long base = uv_info.guest_base_stor_len; unsigned long virt = uv_info.guest_virt_var_stor_len; unsigned long npages = 0, vlen = 0; - struct kvm_memory_slot *memslot; kvm->arch.pv.stor_var = NULL; kvm->arch.pv.stor_base = __get_free_pages(GFP_KERNEL_ACCOUNT, get_order(base)); @@ -130,8 +129,7 @@ static int kvm_s390_pv_alloc_vm(struct kvm *kvm) * Slots are sorted by GFN */ mutex_lock(&kvm->slots_lock); - memslot = kvm_memslots(kvm)->memslots; - npages = memslot->base_gfn + memslot->npages; + npages = kvm_s390_get_gfn_end(kvm_memslots(kvm)); mutex_unlock(&kvm->slots_lock); kvm->arch.pv.guest_len = npages * PAGE_SIZE; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 555f4de47ef2..344ced0b6b68 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -135,7 +135,7 @@ #define KVM_HPAGE_MASK(x) (~(KVM_HPAGE_SIZE(x) - 1)) #define KVM_PAGES_PER_HPAGE(x) (KVM_HPAGE_SIZE(x) / PAGE_SIZE) -#define KVM_PERMILLE_MMU_PAGES 20 +#define KVM_MEMSLOT_PAGES_TO_MMU_PAGES_RATIO 50 #define KVM_MIN_ALLOC_MMU_PAGES 64UL #define KVM_MMU_HASH_SHIFT 12 #define KVM_NUM_MMU_PAGES (1 << KVM_MMU_HASH_SHIFT) @@ -291,25 +291,31 @@ struct kvm_kernel_irq_routing_entry; * the number of unique SPs that can theoretically be created is 2^n, where n * is the number of bits that are used to compute the role. * - * But, even though there are 18 bits in the mask below, not all combinations - * of modes and flags are possible. The maximum number of possible upper-level - * shadow pages for a single gfn is in the neighborhood of 2^13. + * But, even though there are 19 bits in the mask below, not all combinations + * of modes and flags are possible: * - * - invalid shadow pages are not accounted. - * - level is effectively limited to four combinations, not 16 as the number - * bits would imply, as 4k SPs are not tracked (allowed to go unsync). - * - level is effectively unused for non-PAE paging because there is exactly - * one upper level (see 4k SP exception above). - * - quadrant is used only for non-PAE paging and is exclusive with - * gpte_is_8_bytes. - * - execonly and ad_disabled are used only for nested EPT, which makes it - * exclusive with quadrant. + * - invalid shadow pages are not accounted, so the bits are effectively 18 + * + * - quadrant will only be used if has_4_byte_gpte=1 (non-PAE paging); + * execonly and ad_disabled are only used for nested EPT which has + * has_4_byte_gpte=0. Therefore, 2 bits are always unused. + * + * - the 4 bits of level are effectively limited to the values 2/3/4/5, + * as 4k SPs are not tracked (allowed to go unsync). In addition non-PAE + * paging has exactly one upper level, making level completely redundant + * when has_4_byte_gpte=1. + * + * - on top of this, smep_andnot_wp and smap_andnot_wp are only set if + * cr0_wp=0, therefore these three bits only give rise to 5 possibilities. + * + * Therefore, the maximum number of possible upper-level shadow pages for a + * single gfn is a bit less than 2^13. */ union kvm_mmu_page_role { u32 word; struct { unsigned level:4; - unsigned gpte_is_8_bytes:1; + unsigned has_4_byte_gpte:1; unsigned quadrant:2; unsigned direct:1; unsigned access:3; @@ -420,10 +426,9 @@ struct kvm_mmu { int (*page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault); void (*inject_page_fault)(struct kvm_vcpu *vcpu, struct x86_exception *fault); - gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gpa_t gva_or_gpa, - u32 access, struct x86_exception *exception); - gpa_t (*translate_gpa)(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, - struct x86_exception *exception); + gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, + gpa_t gva_or_gpa, u32 access, + struct x86_exception *exception); int (*sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp); void (*invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa); @@ -1587,10 +1592,9 @@ void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, const struct kvm_memory_slot *memslot); void kvm_mmu_zap_all(struct kvm *kvm); void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen); -unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm); void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long kvm_nr_mmu_pages); -int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3); +int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3); int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, const void *val, int bytes); @@ -1640,7 +1644,8 @@ extern u64 kvm_mce_cap_supported; * * EMULTYPE_SKIP - Set when emulating solely to skip an instruction, i.e. to * decode the instruction length. For use *only* by - * kvm_x86_ops.skip_emulated_instruction() implementations. + * kvm_x86_ops.skip_emulated_instruction() implementations if + * EMULTYPE_COMPLETE_USER_EXIT is not set. * * EMULTYPE_ALLOW_RETRY_PF - Set when the emulator should resume the guest to * retry native execution under certain conditions, @@ -1660,6 +1665,10 @@ extern u64 kvm_mce_cap_supported; * * EMULTYPE_PF - Set when emulating MMIO by way of an intercepted #PF, in which * case the CR2/GPA value pass on the stack is valid. + * + * EMULTYPE_COMPLETE_USER_EXIT - Set when the emulator should update interruptibility + * state and inject single-step #DBs after skipping + * an instruction (after completing userspace I/O). */ #define EMULTYPE_NO_DECODE (1 << 0) #define EMULTYPE_TRAP_UD (1 << 1) @@ -1668,6 +1677,7 @@ extern u64 kvm_mce_cap_supported; #define EMULTYPE_TRAP_UD_FORCED (1 << 4) #define EMULTYPE_VMWARE_GP (1 << 5) #define EMULTYPE_PF (1 << 6) +#define EMULTYPE_COMPLETE_USER_EXIT (1 << 7) int kvm_emulate_instruction(struct kvm_vcpu *vcpu, int emulation_type); int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu, @@ -1692,7 +1702,7 @@ int kvm_emulate_monitor(struct kvm_vcpu *vcpu); int kvm_fast_pio(struct kvm_vcpu *vcpu, int size, unsigned short port, int in); int kvm_emulate_cpuid(struct kvm_vcpu *vcpu); int kvm_emulate_halt(struct kvm_vcpu *vcpu); -int kvm_vcpu_halt(struct kvm_vcpu *vcpu); +int kvm_emulate_halt_noskip(struct kvm_vcpu *vcpu); int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu); int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu); @@ -1758,12 +1768,9 @@ void kvm_inject_nmi(struct kvm_vcpu *vcpu); void kvm_update_dr7(struct kvm_vcpu *vcpu); int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn); -void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu); void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, ulong roots_to_free); void kvm_mmu_free_guest_mode_roots(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu); -gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, - struct x86_exception *exception); gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception); gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva, @@ -1927,8 +1934,6 @@ static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) static_call_cond(kvm_x86_vcpu_unblocking)(vcpu); } -static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {} - static inline int kvm_cpu_get_apicid(int mps_cpu) { #ifdef CONFIG_X86_LOCAL_APIC diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h index 9d4a3b1b25b9..eb186bc57f6a 100644 --- a/arch/x86/include/asm/kvm_page_track.h +++ b/arch/x86/include/asm/kvm_page_track.h @@ -63,9 +63,9 @@ void kvm_slot_page_track_add_page(struct kvm *kvm, void kvm_slot_page_track_remove_page(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn, enum kvm_page_track_mode mode); -bool kvm_slot_page_track_is_active(struct kvm_vcpu *vcpu, - struct kvm_memory_slot *slot, gfn_t gfn, - enum kvm_page_track_mode mode); +bool kvm_slot_page_track_is_active(struct kvm *kvm, + const struct kvm_memory_slot *slot, + gfn_t gfn, enum kvm_page_track_mode mode); void kvm_page_track_register_notifier(struct kvm *kvm, diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 619186138176..03b2ce34e7f4 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -27,6 +27,7 @@ config KVM select MMU_NOTIFIER select HAVE_KVM_IRQCHIP select HAVE_KVM_IRQFD + select HAVE_KVM_DIRTY_RING select IRQ_BYPASS_MANAGER select HAVE_KVM_IRQ_BYPASS select HAVE_KVM_IRQ_ROUTING @@ -43,6 +44,7 @@ config KVM select KVM_GENERIC_DIRTYLOG_READ_PROTECT select KVM_VFIO select SRCU + select INTERVAL_TREE select HAVE_KVM_PM_NOTIFIER if PM help Support hosting fully virtualized guest machines using hardware diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 75dfd27b6e8a..30f244b64523 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -7,12 +7,7 @@ ifeq ($(CONFIG_FRAME_POINTER),y) OBJECT_FILES_NON_STANDARD_vmenter.o := y endif -KVM := ../../../virt/kvm - -kvm-y += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \ - $(KVM)/eventfd.o $(KVM)/irqchip.o $(KVM)/vfio.o \ - $(KVM)/dirty_ring.o $(KVM)/binary_stats.o -kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o +include $(srctree)/virt/kvm/Makefile.kvm kvm-y += x86.o emulate.o i8259.o irq.o lapic.o \ i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \ diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 07e9215e911d..0b920e12bb6d 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -523,7 +523,7 @@ void kvm_set_cpu_caps(void) F(CR8_LEGACY) | F(ABM) | F(SSE4A) | F(MISALIGNSSE) | F(3DNOWPREFETCH) | F(OSVW) | 0 /* IBS */ | F(XOP) | 0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM) | - F(TOPOEXT) | F(PERFCTR_CORE) + F(TOPOEXT) | 0 /* PERFCTR_CORE */ ); kvm_cpu_cap_mask(CPUID_8000_0001_EDX, diff --git a/arch/x86/kvm/debugfs.c b/arch/x86/kvm/debugfs.c index 54a83a744538..543a8c04025c 100644 --- a/arch/x86/kvm/debugfs.c +++ b/arch/x86/kvm/debugfs.c @@ -107,9 +107,10 @@ static int kvm_mmu_rmaps_stat_show(struct seq_file *m, void *v) write_lock(&kvm->mmu_lock); for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + int bkt; + slots = __kvm_memslots(kvm, i); - for (j = 0; j < slots->used_slots; j++) { - slot = &slots->memslots[j]; + kvm_for_each_memslot(slot, bkt, slots) for (k = 0; k < KVM_NR_PAGE_SIZES; k++) { rmap = slot->arch.rmap[k]; lpage_size = kvm_mmu_slot_lpages(slot, k + 1); @@ -121,7 +122,6 @@ static int kvm_mmu_rmaps_stat_show(struct seq_file *m, void *v) cur[index]++; } } - } } write_unlock(&kvm->mmu_lock); diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 8d8c1cc7cb53..6e38a7d22e97 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -164,7 +164,7 @@ static int synic_set_sint(struct kvm_vcpu_hv_synic *synic, int sint, static struct kvm_vcpu *get_vcpu_by_vpidx(struct kvm *kvm, u32 vpidx) { struct kvm_vcpu *vcpu = NULL; - int i; + unsigned long i; if (vpidx >= KVM_MAX_VCPUS) return NULL; @@ -1716,7 +1716,8 @@ static __always_inline unsigned long *sparse_set_to_vcpu_mask( { struct kvm_hv *hv = to_kvm_hv(kvm); struct kvm_vcpu *vcpu; - int i, bank, sbank = 0; + int bank, sbank = 0; + unsigned long i; memset(vp_bitmap, 0, KVM_HV_MAX_SPARSE_VCPU_SET_BITS * sizeof(*vp_bitmap)); @@ -1863,7 +1864,7 @@ static void kvm_send_ipi_to_many(struct kvm *kvm, u32 vector, .vector = vector }; struct kvm_vcpu *vcpu; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu_bitmap && !test_bit(i, vcpu_bitmap)) @@ -2519,6 +2520,8 @@ int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, case HYPERV_CPUID_NESTED_FEATURES: ent->eax = evmcs_ver; + if (evmcs_ver) + ent->eax |= HV_X64_NESTED_MSR_BITMAP; break; diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 5a69cce4d72d..0b65a764ed3a 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -242,7 +242,7 @@ static void pit_do_work(struct kthread_work *work) struct kvm_pit *pit = container_of(work, struct kvm_pit, expired); struct kvm *kvm = pit->kvm; struct kvm_vcpu *vcpu; - int i; + unsigned long i; struct kvm_kpit_state *ps = &pit->pit_state; if (atomic_read(&ps->reinject) && !atomic_xchg(&ps->irq_ack, 0)) diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index 0b80263d46d8..814064d06016 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -50,7 +50,7 @@ static void pic_unlock(struct kvm_pic *s) { bool wakeup = s->wakeup_needed; struct kvm_vcpu *vcpu; - int i; + unsigned long i; s->wakeup_needed = false; @@ -270,7 +270,8 @@ int kvm_pic_read_irq(struct kvm *kvm) static void kvm_pic_reset(struct kvm_kpic_state *s) { - int irq, i; + int irq; + unsigned long i; struct kvm_vcpu *vcpu; u8 edge_irr = s->irr & ~s->elcr; bool found = false; diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 816a82515dcd..decfa36b7891 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -149,7 +149,7 @@ void kvm_rtc_eoi_tracking_restore_one(struct kvm_vcpu *vcpu) static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic) { struct kvm_vcpu *vcpu; - int i; + unsigned long i; if (RTC_GSI >= IOAPIC_NUM_PINS) return; @@ -184,7 +184,7 @@ static bool rtc_irq_check_coalesced(struct kvm_ioapic *ioapic) static void ioapic_lazy_update_eoi(struct kvm_ioapic *ioapic, int irq) { - int i; + unsigned long i; struct kvm_vcpu *vcpu; union kvm_ioapic_redirect_entry *entry = &ioapic->redirtbl[irq]; diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index d5b72a08e566..39ad02d6dc63 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -45,9 +45,9 @@ static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e, int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, struct kvm_lapic_irq *irq, struct dest_map *dest_map) { - int i, r = -1; + int r = -1; struct kvm_vcpu *vcpu, *lowest = NULL; - unsigned long dest_vcpu_bitmap[BITS_TO_LONGS(KVM_MAX_VCPUS)]; + unsigned long i, dest_vcpu_bitmap[BITS_TO_LONGS(KVM_MAX_VCPUS)]; unsigned int dest_vcpus = 0; if (kvm_irq_delivery_to_apic_fast(kvm, src, irq, &r, dest_map)) @@ -320,7 +320,8 @@ int kvm_set_routing_entry(struct kvm *kvm, bool kvm_intr_is_single_vcpu(struct kvm *kvm, struct kvm_lapic_irq *irq, struct kvm_vcpu **dest_vcpu) { - int i, r = 0; + int r = 0; + unsigned long i; struct kvm_vcpu *vcpu; if (kvm_intr_is_single_vcpu_fast(kvm, irq, dest_vcpu)) diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index 90e1ffdc05b7..3febc342360c 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -9,6 +9,12 @@ (X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR \ | X86_CR4_OSXMMEXCPT | X86_CR4_PGE | X86_CR4_TSD | X86_CR4_FSGSBASE) +#define X86_CR0_PDPTR_BITS (X86_CR0_CD | X86_CR0_NW | X86_CR0_PG) +#define X86_CR4_TLBFLUSH_BITS (X86_CR4_PGE | X86_CR4_PCIDE | X86_CR4_PAE | X86_CR4_SMEP) +#define X86_CR4_PDPTR_BITS (X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_SMEP) + +static_assert(!(KVM_POSSIBLE_CR0_GUEST_BITS & X86_CR0_PDPTR_BITS)); + #define BUILD_KVM_GPR_ACCESSORS(lname, uname) \ static __always_inline unsigned long kvm_##lname##_read(struct kvm_vcpu *vcpu)\ { \ @@ -37,6 +43,13 @@ BUILD_KVM_GPR_ACCESSORS(r14, R14) BUILD_KVM_GPR_ACCESSORS(r15, R15) #endif +/* + * avail dirty + * 0 0 register in VMCS/VMCB + * 0 1 *INVALID* + * 1 0 register in vcpu->arch + * 1 1 register in vcpu->arch, needs to be stored back + */ static inline bool kvm_register_is_available(struct kvm_vcpu *vcpu, enum kvm_reg reg) { @@ -55,13 +68,6 @@ static inline void kvm_register_mark_available(struct kvm_vcpu *vcpu, __set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); } -static inline void kvm_register_clear_available(struct kvm_vcpu *vcpu, - enum kvm_reg reg) -{ - __clear_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); - __clear_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty); -} - static inline void kvm_register_mark_dirty(struct kvm_vcpu *vcpu, enum kvm_reg reg) { diff --git a/arch/x86/kvm/kvm_onhyperv.c b/arch/x86/kvm/kvm_onhyperv.c index c7db2df50a7a..b469f45e3fe4 100644 --- a/arch/x86/kvm/kvm_onhyperv.c +++ b/arch/x86/kvm/kvm_onhyperv.c @@ -33,7 +33,8 @@ int hv_remote_flush_tlb_with_range(struct kvm *kvm, { struct kvm_arch *kvm_arch = &kvm->arch; struct kvm_vcpu *vcpu; - int ret = 0, i, nr_unique_valid_roots; + int ret = 0, nr_unique_valid_roots; + unsigned long i; hpa_t root; spin_lock(&kvm_arch->hv_root_tdp_lock); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index f206fc35deff..c5028e6b0f96 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -185,7 +185,7 @@ void kvm_recalculate_apic_map(struct kvm *kvm) { struct kvm_apic_map *new, *old = NULL; struct kvm_vcpu *vcpu; - int i; + unsigned long i; u32 max_id = 255; /* enough space for any xAPIC ID */ /* Read kvm->arch.apic_map_dirty before kvm->arch.apic_map. */ @@ -673,35 +673,34 @@ static inline bool pv_eoi_enabled(struct kvm_vcpu *vcpu) return vcpu->arch.pv_eoi.msr_val & KVM_MSR_ENABLED; } -static bool pv_eoi_get_pending(struct kvm_vcpu *vcpu) -{ - u8 val; - if (pv_eoi_get_user(vcpu, &val) < 0) { - printk(KERN_WARNING "Can't read EOI MSR value: 0x%llx\n", - (unsigned long long)vcpu->arch.pv_eoi.msr_val); - return false; - } - return val & KVM_PV_EOI_ENABLED; -} - static void pv_eoi_set_pending(struct kvm_vcpu *vcpu) { - if (pv_eoi_put_user(vcpu, KVM_PV_EOI_ENABLED) < 0) { - printk(KERN_WARNING "Can't set EOI MSR value: 0x%llx\n", - (unsigned long long)vcpu->arch.pv_eoi.msr_val); + if (pv_eoi_put_user(vcpu, KVM_PV_EOI_ENABLED) < 0) return; - } + __set_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention); } -static void pv_eoi_clr_pending(struct kvm_vcpu *vcpu) +static bool pv_eoi_test_and_clr_pending(struct kvm_vcpu *vcpu) { - if (pv_eoi_put_user(vcpu, KVM_PV_EOI_DISABLED) < 0) { - printk(KERN_WARNING "Can't clear EOI MSR value: 0x%llx\n", - (unsigned long long)vcpu->arch.pv_eoi.msr_val); - return; - } + u8 val; + + if (pv_eoi_get_user(vcpu, &val) < 0) + return false; + + val &= KVM_PV_EOI_ENABLED; + + if (val && pv_eoi_put_user(vcpu, KVM_PV_EOI_DISABLED) < 0) + return false; + + /* + * Clear pending bit in any case: it will be set again on vmentry. + * While this might not be ideal from performance point of view, + * this makes sure pv eoi is only enabled when we know it's safe. + */ __clear_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention); + + return val; } static int apic_has_interrupt_for_ppr(struct kvm_lapic *apic, u32 ppr) @@ -1101,6 +1100,9 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, kvm_lapic_set_irr(vector, apic); kvm_make_request(KVM_REQ_EVENT, vcpu); kvm_vcpu_kick(vcpu); + } else { + trace_kvm_apicv_accept_irq(vcpu->vcpu_id, delivery_mode, + trig_mode, vector); } break; @@ -1172,8 +1174,8 @@ void kvm_bitmap_or_dest_vcpus(struct kvm *kvm, struct kvm_lapic_irq *irq, struct kvm_lapic *src = NULL; struct kvm_apic_map *map; struct kvm_vcpu *vcpu; - unsigned long bitmap; - int i, vcpu_idx; + unsigned long bitmap, i; + int vcpu_idx; bool ret; rcu_read_lock(); @@ -1931,7 +1933,7 @@ void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu) /* If the preempt notifier has already run, it also called apic_timer_expired */ if (!apic->lapic_timer.hv_timer_in_use) goto out; - WARN_ON(rcuwait_active(&vcpu->wait)); + WARN_ON(kvm_vcpu_is_blocking(vcpu)); apic_timer_expired(apic, false); cancel_hv_timer(apic); @@ -2677,7 +2679,6 @@ void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu) static void apic_sync_pv_eoi_from_guest(struct kvm_vcpu *vcpu, struct kvm_lapic *apic) { - bool pending; int vector; /* * PV EOI state is derived from KVM_APIC_PV_EOI_PENDING in host @@ -2691,14 +2692,8 @@ static void apic_sync_pv_eoi_from_guest(struct kvm_vcpu *vcpu, * -> host enabled PV EOI, guest executed EOI. */ BUG_ON(!pv_eoi_enabled(vcpu)); - pending = pv_eoi_get_pending(vcpu); - /* - * Clear pending bit in any case: it will be set again on vmentry. - * While this might not be ideal from performance point of view, - * this makes sure pv eoi is only enabled when we know it's safe. - */ - pv_eoi_clr_pending(vcpu); - if (pending) + + if (pv_eoi_test_and_clr_pending(vcpu)) return; vector = apic_set_eoi(apic); trace_kvm_pv_eoi(apic, vector); diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 9ae6168d381e..e9fbb2c8bbe2 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -71,7 +71,8 @@ void kvm_init_mmu(struct kvm_vcpu *vcpu); void kvm_init_shadow_npt_mmu(struct kvm_vcpu *vcpu, unsigned long cr0, unsigned long cr4, u64 efer, gpa_t nested_cr3); void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, - bool accessed_dirty, gpa_t new_eptp); + int huge_page_level, bool accessed_dirty, + gpa_t new_eptp); bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu); int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, u64 fault_address, char *insn, int insn_len); @@ -351,4 +352,17 @@ static inline void kvm_update_page_stats(struct kvm *kvm, int level, int count) { atomic64_add(count, &kvm->stat.pages[level - 1]); } + +gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, + struct x86_exception *exception); + +static inline gpa_t kvm_translate_gpa(struct kvm_vcpu *vcpu, + struct kvm_mmu *mmu, + gpa_t gpa, u32 access, + struct x86_exception *exception) +{ + if (mmu != &vcpu->arch.nested_mmu) + return gpa; + return translate_nested_gpa(vcpu, gpa, access, exception); +} #endif diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index fcdf3f8bb59a..1d275e9d76b5 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -335,12 +335,6 @@ static bool check_mmio_spte(struct kvm_vcpu *vcpu, u64 spte) return likely(kvm_gen == spte_gen); } -static gpa_t translate_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, - struct x86_exception *exception) -{ - return gpa; -} - static int is_cpuid_PSE36(void) { return 1; @@ -1454,7 +1448,7 @@ static bool kvm_set_pte_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, { u64 *sptep; struct rmap_iterator iter; - int need_flush = 0; + bool need_flush = false; u64 new_spte; kvm_pfn_t new_pfn; @@ -1466,7 +1460,7 @@ restart: rmap_printk("spte %p %llx gfn %llx (%d)\n", sptep, *sptep, gfn, level); - need_flush = 1; + need_flush = true; if (pte_write(pte)) { pte_list_remove(kvm, rmap_head, sptep); @@ -1482,7 +1476,7 @@ restart: if (need_flush && kvm_available_flush_tlb_with_range()) { kvm_flush_remote_tlbs_with_address(kvm, gfn, 1); - return 0; + return false; } return need_flush; @@ -1623,8 +1617,8 @@ static bool kvm_test_age_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, for_each_rmap_spte(rmap_head, &iter, sptep) if (is_accessed_spte(*sptep)) - return 1; - return 0; + return true; + return false; } #define RMAP_RECYCLE_THRESHOLD 1000 @@ -2086,10 +2080,8 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, role = vcpu->arch.mmu->mmu_role.base; role.level = level; role.direct = direct; - if (role.direct) - role.gpte_is_8_bytes = true; role.access = access; - if (!direct_mmu && vcpu->arch.mmu->root_level <= PT32_ROOT_LEVEL) { + if (role.has_4_byte_gpte) { quadrant = gaddr >> (PAGE_SHIFT + (PT64_PT_BITS * level)); quadrant &= (1 << ((PT32_PT_BITS - PT64_PT_BITS) * level)) - 1; role.quadrant = quadrant; @@ -2565,10 +2557,10 @@ static int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva) return r; } -static void kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) +static void kvm_unsync_page(struct kvm *kvm, struct kvm_mmu_page *sp) { trace_kvm_mmu_unsync_page(sp); - ++vcpu->kvm->stat.mmu_unsync; + ++kvm->stat.mmu_unsync; sp->unsync = 1; kvm_mmu_mark_parents_unsync(sp); @@ -2580,7 +2572,7 @@ static void kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) * were marked unsync (or if there is no shadow page), -EPERM if the SPTE must * be write-protected. */ -int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, +int mmu_try_to_unsync_pages(struct kvm *kvm, const struct kvm_memory_slot *slot, gfn_t gfn, bool can_unsync, bool prefetch) { struct kvm_mmu_page *sp; @@ -2591,7 +2583,7 @@ int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, * track machinery is used to write-protect upper-level shadow pages, * i.e. this guards the role.level == 4K assertion below! */ - if (kvm_slot_page_track_is_active(vcpu, slot, gfn, KVM_PAGE_TRACK_WRITE)) + if (kvm_slot_page_track_is_active(kvm, slot, gfn, KVM_PAGE_TRACK_WRITE)) return -EPERM; /* @@ -2600,7 +2592,7 @@ int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, * that case, KVM must complete emulation of the guest TLB flush before * allowing shadow pages to become unsync (writable by the guest). */ - for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn) { + for_each_gfn_indirect_valid_sp(kvm, sp, gfn) { if (!can_unsync) return -EPERM; @@ -2619,7 +2611,7 @@ int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, */ if (!locked) { locked = true; - spin_lock(&vcpu->kvm->arch.mmu_unsync_pages_lock); + spin_lock(&kvm->arch.mmu_unsync_pages_lock); /* * Recheck after taking the spinlock, a different vCPU @@ -2634,10 +2626,10 @@ int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, } WARN_ON(sp->role.level != PG_LEVEL_4K); - kvm_unsync_page(vcpu, sp); + kvm_unsync_page(kvm, sp); } if (locked) - spin_unlock(&vcpu->kvm->arch.mmu_unsync_pages_lock); + spin_unlock(&kvm->arch.mmu_unsync_pages_lock); /* * We need to ensure that the marking of unsync pages is visible @@ -3409,7 +3401,7 @@ static int mmu_first_shadow_root_alloc(struct kvm *kvm) { struct kvm_memslots *slots; struct kvm_memory_slot *slot; - int r = 0, i; + int r = 0, i, bkt; /* * Check if this is the first shadow root being allocated before @@ -3434,7 +3426,7 @@ static int mmu_first_shadow_root_alloc(struct kvm *kvm) for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { slots = __kvm_memslots(kvm, i); - kvm_for_each_memslot(slot, slots) { + kvm_for_each_memslot(slot, bkt, slots) { /* * Both of these functions are no-ops if the target is * already allocated, so unconditionally calling both @@ -3734,21 +3726,13 @@ void kvm_mmu_sync_prev_roots(struct kvm_vcpu *vcpu) kvm_mmu_free_roots(vcpu, vcpu->arch.mmu, roots_to_free); } -static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gpa_t vaddr, - u32 access, struct x86_exception *exception) +static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, + gpa_t vaddr, u32 access, + struct x86_exception *exception) { if (exception) exception->error_code = 0; - return vaddr; -} - -static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gpa_t vaddr, - u32 access, - struct x86_exception *exception) -{ - if (exception) - exception->error_code = 0; - return vcpu->arch.nested_mmu.translate_gpa(vcpu, vaddr, access, exception); + return kvm_translate_gpa(vcpu, mmu, vaddr, access, exception); } static bool mmio_info_in_cache(struct kvm_vcpu *vcpu, u64 addr, bool direct) @@ -3888,7 +3872,7 @@ static bool page_fault_handle_page_track(struct kvm_vcpu *vcpu, * guest is writing the page which is write tracked which can * not be fixed by page fault handler. */ - if (kvm_slot_page_track_is_active(vcpu, fault->slot, fault->gfn, KVM_PAGE_TRACK_WRITE)) + if (kvm_slot_page_track_is_active(vcpu->kvm, fault->slot, fault->gfn, KVM_PAGE_TRACK_WRITE)) return true; return false; @@ -4388,22 +4372,28 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, static void __reset_rsvds_bits_mask_ept(struct rsvd_bits_validate *rsvd_check, - u64 pa_bits_rsvd, bool execonly) + u64 pa_bits_rsvd, bool execonly, int huge_page_level) { u64 high_bits_rsvd = pa_bits_rsvd & rsvd_bits(0, 51); + u64 large_1g_rsvd = 0, large_2m_rsvd = 0; u64 bad_mt_xwr; + if (huge_page_level < PG_LEVEL_1G) + large_1g_rsvd = rsvd_bits(7, 7); + if (huge_page_level < PG_LEVEL_2M) + large_2m_rsvd = rsvd_bits(7, 7); + rsvd_check->rsvd_bits_mask[0][4] = high_bits_rsvd | rsvd_bits(3, 7); rsvd_check->rsvd_bits_mask[0][3] = high_bits_rsvd | rsvd_bits(3, 7); - rsvd_check->rsvd_bits_mask[0][2] = high_bits_rsvd | rsvd_bits(3, 6); - rsvd_check->rsvd_bits_mask[0][1] = high_bits_rsvd | rsvd_bits(3, 6); + rsvd_check->rsvd_bits_mask[0][2] = high_bits_rsvd | rsvd_bits(3, 6) | large_1g_rsvd; + rsvd_check->rsvd_bits_mask[0][1] = high_bits_rsvd | rsvd_bits(3, 6) | large_2m_rsvd; rsvd_check->rsvd_bits_mask[0][0] = high_bits_rsvd; /* large page */ rsvd_check->rsvd_bits_mask[1][4] = rsvd_check->rsvd_bits_mask[0][4]; rsvd_check->rsvd_bits_mask[1][3] = rsvd_check->rsvd_bits_mask[0][3]; - rsvd_check->rsvd_bits_mask[1][2] = high_bits_rsvd | rsvd_bits(12, 29); - rsvd_check->rsvd_bits_mask[1][1] = high_bits_rsvd | rsvd_bits(12, 20); + rsvd_check->rsvd_bits_mask[1][2] = high_bits_rsvd | rsvd_bits(12, 29) | large_1g_rsvd; + rsvd_check->rsvd_bits_mask[1][1] = high_bits_rsvd | rsvd_bits(12, 20) | large_2m_rsvd; rsvd_check->rsvd_bits_mask[1][0] = rsvd_check->rsvd_bits_mask[0][0]; bad_mt_xwr = 0xFFull << (2 * 8); /* bits 3..5 must not be 2 */ @@ -4419,10 +4409,11 @@ __reset_rsvds_bits_mask_ept(struct rsvd_bits_validate *rsvd_check, } static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu, - struct kvm_mmu *context, bool execonly) + struct kvm_mmu *context, bool execonly, int huge_page_level) { __reset_rsvds_bits_mask_ept(&context->guest_rsvd_check, - vcpu->arch.reserved_gpa_bits, execonly); + vcpu->arch.reserved_gpa_bits, execonly, + huge_page_level); } static inline u64 reserved_hpa_bits(void) @@ -4498,7 +4489,8 @@ reset_tdp_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, false, true); else __reset_rsvds_bits_mask_ept(shadow_zero_check, - reserved_hpa_bits(), false); + reserved_hpa_bits(), false, + max_huge_page_level); if (!shadow_me_mask) return; @@ -4518,7 +4510,8 @@ reset_ept_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context, bool execonly) { __reset_rsvds_bits_mask_ept(&context->shadow_zero_check, - reserved_hpa_bits(), execonly); + reserved_hpa_bits(), execonly, + max_huge_page_level); } #define BYTE_MASK(access) \ @@ -4767,7 +4760,7 @@ kvm_calc_tdp_mmu_root_page_role(struct kvm_vcpu *vcpu, role.base.ad_disabled = (shadow_accessed_mask == 0); role.base.level = kvm_mmu_get_tdp_level(vcpu); role.base.direct = true; - role.base.gpte_is_8_bytes = true; + role.base.has_4_byte_gpte = false; return role; } @@ -4812,7 +4805,7 @@ kvm_calc_shadow_root_page_role_common(struct kvm_vcpu *vcpu, role.base.smep_andnot_wp = role.ext.cr4_smep && !____is_cr0_wp(regs); role.base.smap_andnot_wp = role.ext.cr4_smap && !____is_cr0_wp(regs); - role.base.gpte_is_8_bytes = ____is_cr0_pg(regs) && ____is_cr4_pae(regs); + role.base.has_4_byte_gpte = ____is_cr0_pg(regs) && !____is_cr4_pae(regs); return role; } @@ -4911,7 +4904,7 @@ kvm_calc_shadow_ept_root_page_role(struct kvm_vcpu *vcpu, bool accessed_dirty, role.base.smm = vcpu->arch.root_mmu.mmu_role.base.smm; role.base.level = level; - role.base.gpte_is_8_bytes = true; + role.base.has_4_byte_gpte = false; role.base.direct = false; role.base.ad_disabled = !accessed_dirty; role.base.guest_mode = true; @@ -4926,7 +4919,8 @@ kvm_calc_shadow_ept_root_page_role(struct kvm_vcpu *vcpu, bool accessed_dirty, } void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, - bool accessed_dirty, gpa_t new_eptp) + int huge_page_level, bool accessed_dirty, + gpa_t new_eptp) { struct kvm_mmu *context = &vcpu->arch.guest_mmu; u8 level = vmx_eptp_page_walk_level(new_eptp); @@ -4953,7 +4947,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, update_permission_bitmask(context, true); context->pkru_mask = 0; - reset_rsvds_bits_mask_ept(vcpu, context, execonly); + reset_rsvds_bits_mask_ept(vcpu, context, execonly, huge_page_level); reset_ept_shadow_zero_bits_mask(vcpu, context, execonly); } EXPORT_SYMBOL_GPL(kvm_init_shadow_ept_mmu); @@ -5017,13 +5011,13 @@ static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu) * the gva_to_gpa functions between mmu and nested_mmu are swapped. */ if (!is_paging(vcpu)) - g_context->gva_to_gpa = nonpaging_gva_to_gpa_nested; + g_context->gva_to_gpa = nonpaging_gva_to_gpa; else if (is_long_mode(vcpu)) - g_context->gva_to_gpa = paging64_gva_to_gpa_nested; + g_context->gva_to_gpa = paging64_gva_to_gpa; else if (is_pae(vcpu)) - g_context->gva_to_gpa = paging64_gva_to_gpa_nested; + g_context->gva_to_gpa = paging64_gva_to_gpa; else - g_context->gva_to_gpa = paging32_gva_to_gpa_nested; + g_context->gva_to_gpa = paging32_gva_to_gpa; reset_guest_paging_metadata(vcpu, g_context); } @@ -5188,7 +5182,7 @@ static bool detect_write_misaligned(struct kvm_mmu_page *sp, gpa_t gpa, gpa, bytes, sp->role.word); offset = offset_in_page(gpa); - pte_size = sp->role.gpte_is_8_bytes ? 8 : 4; + pte_size = sp->role.has_4_byte_gpte ? 4 : 8; /* * Sometimes, the OS only writes the last one bytes to update status @@ -5212,7 +5206,7 @@ static u64 *get_written_sptes(struct kvm_mmu_page *sp, gpa_t gpa, int *nspte) page_offset = offset_in_page(gpa); level = sp->role.level; *nspte = 1; - if (!sp->role.gpte_is_8_bytes) { + if (sp->role.has_4_byte_gpte) { page_offset <<= 1; /* 32->64 */ /* * A 32-bit pde maps 4MB while the shadow pdes map @@ -5524,10 +5518,13 @@ static int __kvm_mmu_create(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu) mmu->root_hpa = INVALID_PAGE; mmu->root_pgd = 0; - mmu->translate_gpa = translate_gpa; for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) mmu->prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID; + /* vcpu->arch.guest_mmu isn't used when !tdp_enabled. */ + if (!tdp_enabled && mmu == &vcpu->arch.guest_mmu) + return 0; + /* * When using PAE paging, the four PDPTEs are treated as 'root' pages, * while the PDP table is a per-vCPU construct that's allocated at MMU @@ -5537,7 +5534,7 @@ static int __kvm_mmu_create(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu) * generally doesn't use PAE paging and can skip allocating the PDP * table. The main exception, handled here, is SVM's 32-bit NPT. The * other exception is for shadowing L1's 32-bit or PAE NPT on 64-bit - * KVM; that horror is handled on-demand by mmu_alloc_shadow_roots(). + * KVM; that horror is handled on-demand by mmu_alloc_special_roots(). */ if (tdp_enabled && kvm_mmu_get_tdp_level(vcpu) > PT32E_ROOT_LEVEL) return 0; @@ -5582,8 +5579,6 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu) vcpu->arch.mmu = &vcpu->arch.root_mmu; vcpu->arch.walk_mmu = &vcpu->arch.root_mmu; - vcpu->arch.nested_mmu.translate_gpa = translate_nested_gpa; - ret = __kvm_mmu_create(vcpu, &vcpu->arch.guest_mmu); if (ret) return ret; @@ -5742,6 +5737,7 @@ static bool __kvm_zap_rmaps(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) { const struct kvm_memory_slot *memslot; struct kvm_memslots *slots; + struct kvm_memslot_iter iter; bool flush = false; gfn_t start, end; int i; @@ -5751,10 +5747,12 @@ static bool __kvm_zap_rmaps(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { slots = __kvm_memslots(kvm, i); - kvm_for_each_memslot(memslot, slots) { + + kvm_for_each_memslot_in_gfn_range(&iter, slots, gfn_start, gfn_end) { + memslot = iter.slot; start = max(gfn_start, memslot->base_gfn); end = min(gfn_end, memslot->base_gfn + memslot->npages); - if (start >= end) + if (WARN_ON_ONCE(start >= end)) continue; flush = slot_handle_level_range(kvm, memslot, kvm_zap_rmapp, @@ -5775,6 +5773,9 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) bool flush; int i; + if (WARN_ON_ONCE(gfn_end <= gfn_start)) + return; + write_lock(&kvm->mmu_lock); kvm_inc_notifier_count(kvm, gfn_start, gfn_end); @@ -6164,30 +6165,6 @@ out: return ret; } -/* - * Calculate mmu pages needed for kvm. - */ -unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm) -{ - unsigned long nr_mmu_pages; - unsigned long nr_pages = 0; - struct kvm_memslots *slots; - struct kvm_memory_slot *memslot; - int i; - - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { - slots = __kvm_memslots(kvm, i); - - kvm_for_each_memslot(memslot, slots) - nr_pages += memslot->npages; - } - - nr_mmu_pages = nr_pages * KVM_PERMILLE_MMU_PAGES / 1000; - nr_mmu_pages = max(nr_mmu_pages, KVM_MIN_ALLOC_MMU_PAGES); - - return nr_mmu_pages; -} - void kvm_mmu_destroy(struct kvm_vcpu *vcpu) { kvm_mmu_unload(vcpu); diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index 52c6527b1a06..da6166b5c377 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -104,7 +104,7 @@ static inline int kvm_mmu_page_as_id(struct kvm_mmu_page *sp) return kvm_mmu_role_as_id(sp->role); } -static inline bool kvm_vcpu_ad_need_write_protect(struct kvm_vcpu *vcpu) +static inline bool kvm_mmu_page_ad_need_write_protect(struct kvm_mmu_page *sp) { /* * When using the EPT page-modification log, the GPAs in the CPU dirty @@ -112,13 +112,12 @@ static inline bool kvm_vcpu_ad_need_write_protect(struct kvm_vcpu *vcpu) * on write protection to record dirty pages, which bypasses PML, since * writes now result in a vmexit. Note, the check on CPU dirty logging * being enabled is mandatory as the bits used to denote WP-only SPTEs - * are reserved for NPT w/ PAE (32-bit KVM). + * are reserved for PAE paging (32-bit KVM). */ - return vcpu->arch.mmu == &vcpu->arch.guest_mmu && - kvm_x86_ops.cpu_dirty_log_size; + return kvm_x86_ops.cpu_dirty_log_size && sp->role.guest_mode; } -int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, +int mmu_try_to_unsync_pages(struct kvm *kvm, const struct kvm_memory_slot *slot, gfn_t gfn, bool can_unsync, bool prefetch); void kvm_mmu_gfn_disallow_lpage(const struct kvm_memory_slot *slot, gfn_t gfn); diff --git a/arch/x86/kvm/mmu/mmutrace.h b/arch/x86/kvm/mmu/mmutrace.h index b8151bbca36a..de5e8e4e1aa7 100644 --- a/arch/x86/kvm/mmu/mmutrace.h +++ b/arch/x86/kvm/mmu/mmutrace.h @@ -35,7 +35,7 @@ " %snxe %sad root %u %s%c", \ __entry->mmu_valid_gen, \ __entry->gfn, role.level, \ - role.gpte_is_8_bytes ? 8 : 4, \ + role.has_4_byte_gpte ? 4 : 8, \ role.quadrant, \ role.direct ? " direct" : "", \ access_str[role.access], \ diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c index cc4eb5b7fb76..68eb1fb548b6 100644 --- a/arch/x86/kvm/mmu/page_track.c +++ b/arch/x86/kvm/mmu/page_track.c @@ -173,9 +173,9 @@ EXPORT_SYMBOL_GPL(kvm_slot_page_track_remove_page); /* * check if the corresponding access on the specified guest page is tracked. */ -bool kvm_slot_page_track_is_active(struct kvm_vcpu *vcpu, - struct kvm_memory_slot *slot, gfn_t gfn, - enum kvm_page_track_mode mode) +bool kvm_slot_page_track_is_active(struct kvm *kvm, + const struct kvm_memory_slot *slot, + gfn_t gfn, enum kvm_page_track_mode mode) { int index; @@ -186,7 +186,7 @@ bool kvm_slot_page_track_is_active(struct kvm_vcpu *vcpu, return false; if (mode == KVM_PAGE_TRACK_WRITE && - !kvm_page_track_write_tracking_enabled(vcpu->kvm)) + !kvm_page_track_write_tracking_enabled(kvm)) return false; index = gfn_to_index(gfn, slot->base_gfn, PG_LEVEL_4K); diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 708a5d297fe1..5b5bdac97c7b 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -403,9 +403,8 @@ retry_walk: walker->table_gfn[walker->level - 1] = table_gfn; walker->pte_gpa[walker->level - 1] = pte_gpa; - real_gpa = mmu->translate_gpa(vcpu, gfn_to_gpa(table_gfn), - nested_access, - &walker->fault); + real_gpa = kvm_translate_gpa(vcpu, mmu, gfn_to_gpa(table_gfn), + nested_access, &walker->fault); /* * FIXME: This can happen if emulation (for of an INS/OUTS @@ -467,7 +466,7 @@ retry_walk: if (PTTYPE == 32 && walker->level > PG_LEVEL_4K && is_cpuid_PSE36()) gfn += pse36_gfn_delta(pte); - real_gpa = mmu->translate_gpa(vcpu, gfn_to_gpa(gfn), access, &walker->fault); + real_gpa = kvm_translate_gpa(vcpu, mmu, gfn_to_gpa(gfn), access, &walker->fault); if (real_gpa == UNMAPPED_GVA) return 0; @@ -547,16 +546,6 @@ static int FNAME(walk_addr)(struct guest_walker *walker, access); } -#if PTTYPE != PTTYPE_EPT -static int FNAME(walk_addr_nested)(struct guest_walker *walker, - struct kvm_vcpu *vcpu, gva_t addr, - u32 access) -{ - return FNAME(walk_addr_generic)(walker, vcpu, &vcpu->arch.nested_mmu, - addr, access); -} -#endif - static bool FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, u64 *spte, pt_element_t gpte, bool no_dirty_log) @@ -1000,50 +989,29 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa) } /* Note, @addr is a GPA when gva_to_gpa() translates an L2 GPA to an L1 GPA. */ -static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gpa_t addr, u32 access, +static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, + gpa_t addr, u32 access, struct x86_exception *exception) { struct guest_walker walker; gpa_t gpa = UNMAPPED_GVA; int r; - r = FNAME(walk_addr)(&walker, vcpu, addr, access); - - if (r) { - gpa = gfn_to_gpa(walker.gfn); - gpa |= addr & ~PAGE_MASK; - } else if (exception) - *exception = walker.fault; - - return gpa; -} - -#if PTTYPE != PTTYPE_EPT -/* Note, gva_to_gpa_nested() is only used to translate L2 GVAs. */ -static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gpa_t vaddr, - u32 access, - struct x86_exception *exception) -{ - struct guest_walker walker; - gpa_t gpa = UNMAPPED_GVA; - int r; - #ifndef CONFIG_X86_64 /* A 64-bit GVA should be impossible on 32-bit KVM. */ - WARN_ON_ONCE(vaddr >> 32); + WARN_ON_ONCE((addr >> 32) && mmu == vcpu->arch.walk_mmu); #endif - r = FNAME(walk_addr_nested)(&walker, vcpu, vaddr, access); + r = FNAME(walk_addr_generic)(&walker, vcpu, mmu, addr, access); if (r) { gpa = gfn_to_gpa(walker.gfn); - gpa |= vaddr & ~PAGE_MASK; + gpa |= addr & ~PAGE_MASK; } else if (exception) *exception = walker.fault; return gpa; } -#endif /* * Using the cached information from sp->gfns is safe because: diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c index 0c76c45fdb68..8a7b03207762 100644 --- a/arch/x86/kvm/mmu/spte.c +++ b/arch/x86/kvm/mmu/spte.c @@ -90,7 +90,7 @@ static bool kvm_is_mmio_pfn(kvm_pfn_t pfn) } bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, - struct kvm_memory_slot *slot, + const struct kvm_memory_slot *slot, unsigned int pte_access, gfn_t gfn, kvm_pfn_t pfn, u64 old_spte, bool prefetch, bool can_unsync, bool host_writable, u64 *new_spte) @@ -101,7 +101,7 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, if (sp->role.ad_disabled) spte |= SPTE_TDP_AD_DISABLED_MASK; - else if (kvm_vcpu_ad_need_write_protect(vcpu)) + else if (kvm_mmu_page_ad_need_write_protect(sp)) spte |= SPTE_TDP_AD_WRPROT_ONLY_MASK; /* @@ -161,7 +161,7 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, * e.g. it's write-tracked (upper-level SPs) or has one or more * shadow pages and unsync'ing pages is not allowed. */ - if (mmu_try_to_unsync_pages(vcpu, slot, gfn, can_unsync, prefetch)) { + if (mmu_try_to_unsync_pages(vcpu->kvm, slot, gfn, can_unsync, prefetch)) { pgprintk("%s: found shadow page for %llx, marking ro\n", __func__, gfn); wrprot = true; diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index cc432f9a966b..a4af2a42695c 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -330,7 +330,7 @@ static inline u64 get_mmio_spte_generation(u64 spte) } bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, - struct kvm_memory_slot *slot, + const struct kvm_memory_slot *slot, unsigned int pte_access, gfn_t gfn, kvm_pfn_t pfn, u64 old_spte, bool prefetch, bool can_unsync, bool host_writable, u64 *new_spte); diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 1beb4ca90560..7b1bc816b7c3 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -165,7 +165,7 @@ static union kvm_mmu_page_role page_role_for_level(struct kvm_vcpu *vcpu, role = vcpu->arch.mmu->mmu_role.base; role.level = level; role.direct = true; - role.gpte_is_8_bytes = true; + role.has_4_byte_gpte = false; role.access = ACC_ALL; role.ad_disabled = !shadow_accessed_mask; diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 8f9af7b7dbbe..0e5b49294086 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -293,7 +293,7 @@ static void avic_kick_target_vcpus(struct kvm *kvm, struct kvm_lapic *source, u32 icrl, u32 icrh) { struct kvm_vcpu *vcpu; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { bool m = kvm_apic_match_dest(vcpu, source, @@ -675,10 +675,18 @@ int svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec) smp_mb__after_atomic(); if (avic_vcpu_is_running(vcpu)) { - int cpuid = vcpu->cpu; + int cpu = READ_ONCE(vcpu->cpu); - if (cpuid != get_cpu()) - wrmsrl(SVM_AVIC_DOORBELL, kvm_cpu_get_apicid(cpuid)); + /* + * Note, the vCPU could get migrated to a different pCPU at any + * point, which could result in signalling the wrong/previous + * pCPU. But if that happens the vCPU is guaranteed to do a + * VMRUN (after being migrated) and thus will process pending + * interrupts, i.e. a doorbell is not needed (and the spurious + * one is harmless). + */ + if (cpu != get_cpu()) + wrmsrl(SVM_AVIC_DOORBELL, kvm_cpu_get_apicid(cpu)); put_cpu(); } else kvm_vcpu_wake_up(vcpu); diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index f8b7bc04b3e7..cf206855ebf0 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -58,8 +58,9 @@ static void svm_inject_page_fault_nested(struct kvm_vcpu *vcpu, struct x86_excep struct vcpu_svm *svm = to_svm(vcpu); WARN_ON(!is_guest_mode(vcpu)); - if (vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_EXCEPTION_OFFSET + PF_VECTOR) && - !svm->nested.nested_run_pending) { + if (vmcb12_is_intercept(&svm->nested.ctl, + INTERCEPT_EXCEPTION_OFFSET + PF_VECTOR) && + !svm->nested.nested_run_pending) { svm->vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + PF_VECTOR; svm->vmcb->control.exit_code_hi = 0; svm->vmcb->control.exit_info_1 = fault->error_code; @@ -121,7 +122,8 @@ static void nested_svm_uninit_mmu_context(struct kvm_vcpu *vcpu) void recalc_intercepts(struct vcpu_svm *svm) { - struct vmcb_control_area *c, *h, *g; + struct vmcb_control_area *c, *h; + struct vmcb_ctrl_area_cached *g; unsigned int i; vmcb_mark_dirty(svm->vmcb, VMCB_INTERCEPTS); @@ -163,37 +165,6 @@ void recalc_intercepts(struct vcpu_svm *svm) vmcb_set_intercept(c, INTERCEPT_VMSAVE); } -static void copy_vmcb_control_area(struct vmcb_control_area *dst, - struct vmcb_control_area *from) -{ - unsigned int i; - - for (i = 0; i < MAX_INTERCEPT; i++) - dst->intercepts[i] = from->intercepts[i]; - - dst->iopm_base_pa = from->iopm_base_pa; - dst->msrpm_base_pa = from->msrpm_base_pa; - dst->tsc_offset = from->tsc_offset; - /* asid not copied, it is handled manually for svm->vmcb. */ - dst->tlb_ctl = from->tlb_ctl; - dst->int_ctl = from->int_ctl; - dst->int_vector = from->int_vector; - dst->int_state = from->int_state; - dst->exit_code = from->exit_code; - dst->exit_code_hi = from->exit_code_hi; - dst->exit_info_1 = from->exit_info_1; - dst->exit_info_2 = from->exit_info_2; - dst->exit_int_info = from->exit_int_info; - dst->exit_int_info_err = from->exit_int_info_err; - dst->nested_ctl = from->nested_ctl; - dst->event_inj = from->event_inj; - dst->event_inj_err = from->event_inj_err; - dst->nested_cr3 = from->nested_cr3; - dst->virt_ext = from->virt_ext; - dst->pause_filter_count = from->pause_filter_count; - dst->pause_filter_thresh = from->pause_filter_thresh; -} - static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) { /* @@ -203,7 +174,7 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) */ int i; - if (!(vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT))) + if (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT))) return true; for (i = 0; i < MSRPM_OFFSETS; i++) { @@ -250,10 +221,10 @@ static bool nested_svm_check_tlb_ctl(struct kvm_vcpu *vcpu, u8 tlb_ctl) } } -static bool nested_vmcb_check_controls(struct kvm_vcpu *vcpu, - struct vmcb_control_area *control) +static bool __nested_vmcb_check_controls(struct kvm_vcpu *vcpu, + struct vmcb_ctrl_area_cached *control) { - if (CC(!vmcb_is_intercept(control, INTERCEPT_VMRUN))) + if (CC(!vmcb12_is_intercept(control, INTERCEPT_VMRUN))) return false; if (CC(control->asid == 0)) @@ -275,9 +246,20 @@ static bool nested_vmcb_check_controls(struct kvm_vcpu *vcpu, return true; } -static bool nested_vmcb_check_cr3_cr4(struct kvm_vcpu *vcpu, - struct vmcb_save_area *save) +/* Common checks that apply to both L1 and L2 state. */ +static bool __nested_vmcb_check_save(struct kvm_vcpu *vcpu, + struct vmcb_save_area_cached *save) { + if (CC(!(save->efer & EFER_SVME))) + return false; + + if (CC((save->cr0 & X86_CR0_CD) == 0 && (save->cr0 & X86_CR0_NW)) || + CC(save->cr0 & ~0xffffffffULL)) + return false; + + if (CC(!kvm_dr6_valid(save->dr6)) || CC(!kvm_dr7_valid(save->dr7))) + return false; + /* * These checks are also performed by KVM_SET_SREGS, * except that EFER.LMA is not checked by SVM against @@ -293,48 +275,90 @@ static bool nested_vmcb_check_cr3_cr4(struct kvm_vcpu *vcpu, if (CC(!kvm_is_valid_cr4(vcpu, save->cr4))) return false; + if (CC(!kvm_valid_efer(vcpu, save->efer))) + return false; + return true; } -/* Common checks that apply to both L1 and L2 state. */ -static bool nested_vmcb_valid_sregs(struct kvm_vcpu *vcpu, - struct vmcb_save_area *save) +static bool nested_vmcb_check_save(struct kvm_vcpu *vcpu) { - /* - * FIXME: these should be done after copying the fields, - * to avoid TOC/TOU races. For these save area checks - * the possible damage is limited since kvm_set_cr0 and - * kvm_set_cr4 handle failure; EFER_SVME is an exception - * so it is force-set later in nested_prepare_vmcb_save. - */ - if (CC(!(save->efer & EFER_SVME))) - return false; + struct vcpu_svm *svm = to_svm(vcpu); + struct vmcb_save_area_cached *save = &svm->nested.save; - if (CC((save->cr0 & X86_CR0_CD) == 0 && (save->cr0 & X86_CR0_NW)) || - CC(save->cr0 & ~0xffffffffULL)) - return false; + return __nested_vmcb_check_save(vcpu, save); +} - if (CC(!kvm_dr6_valid(save->dr6)) || CC(!kvm_dr7_valid(save->dr7))) - return false; +static bool nested_vmcb_check_controls(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + struct vmcb_ctrl_area_cached *ctl = &svm->nested.ctl; - if (!nested_vmcb_check_cr3_cr4(vcpu, save)) - return false; + return __nested_vmcb_check_controls(vcpu, ctl); +} - if (CC(!kvm_valid_efer(vcpu, save->efer))) - return false; +static +void __nested_copy_vmcb_control_to_cache(struct vmcb_ctrl_area_cached *to, + struct vmcb_control_area *from) +{ + unsigned int i; - return true; + for (i = 0; i < MAX_INTERCEPT; i++) + to->intercepts[i] = from->intercepts[i]; + + to->iopm_base_pa = from->iopm_base_pa; + to->msrpm_base_pa = from->msrpm_base_pa; + to->tsc_offset = from->tsc_offset; + to->tlb_ctl = from->tlb_ctl; + to->int_ctl = from->int_ctl; + to->int_vector = from->int_vector; + to->int_state = from->int_state; + to->exit_code = from->exit_code; + to->exit_code_hi = from->exit_code_hi; + to->exit_info_1 = from->exit_info_1; + to->exit_info_2 = from->exit_info_2; + to->exit_int_info = from->exit_int_info; + to->exit_int_info_err = from->exit_int_info_err; + to->nested_ctl = from->nested_ctl; + to->event_inj = from->event_inj; + to->event_inj_err = from->event_inj_err; + to->nested_cr3 = from->nested_cr3; + to->virt_ext = from->virt_ext; + to->pause_filter_count = from->pause_filter_count; + to->pause_filter_thresh = from->pause_filter_thresh; + + /* Copy asid here because nested_vmcb_check_controls will check it. */ + to->asid = from->asid; + to->msrpm_base_pa &= ~0x0fffULL; + to->iopm_base_pa &= ~0x0fffULL; } -void nested_load_control_from_vmcb12(struct vcpu_svm *svm, - struct vmcb_control_area *control) +void nested_copy_vmcb_control_to_cache(struct vcpu_svm *svm, + struct vmcb_control_area *control) { - copy_vmcb_control_area(&svm->nested.ctl, control); + __nested_copy_vmcb_control_to_cache(&svm->nested.ctl, control); +} + +static void __nested_copy_vmcb_save_to_cache(struct vmcb_save_area_cached *to, + struct vmcb_save_area *from) +{ + /* + * Copy only fields that are validated, as we need them + * to avoid TOC/TOU races. + */ + to->efer = from->efer; + to->cr0 = from->cr0; + to->cr3 = from->cr3; + to->cr4 = from->cr4; - /* Copy it here because nested_svm_check_controls will check it. */ - svm->nested.ctl.asid = control->asid; - svm->nested.ctl.msrpm_base_pa &= ~0x0fffULL; - svm->nested.ctl.iopm_base_pa &= ~0x0fffULL; + to->dr6 = from->dr6; + to->dr7 = from->dr7; +} + +void nested_copy_vmcb_save_to_cache(struct vcpu_svm *svm, + struct vmcb_save_area *save) +{ + __nested_copy_vmcb_save_to_cache(&svm->nested.save, save); } /* @@ -437,14 +461,13 @@ static int nested_svm_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, return -EINVAL; if (reload_pdptrs && !nested_npt && is_pae_paging(vcpu) && - CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))) + CC(!load_pdptrs(vcpu, cr3))) return -EINVAL; if (!nested_npt) kvm_mmu_new_pgd(vcpu, cr3); vcpu->arch.cr3 = cr3; - kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); /* Re-initialize the MMU, e.g. to pick up CR4 MMU role changes. */ kvm_init_mmu(vcpu); @@ -490,15 +513,10 @@ static void nested_vmcb02_prepare_save(struct vcpu_svm *svm, struct vmcb *vmcb12 kvm_set_rflags(&svm->vcpu, vmcb12->save.rflags | X86_EFLAGS_FIXED); - /* - * Force-set EFER_SVME even though it is checked earlier on the - * VMCB12, because the guest can flip the bit between the check - * and now. Clearing EFER_SVME would call svm_free_nested. - */ - svm_set_efer(&svm->vcpu, vmcb12->save.efer | EFER_SVME); + svm_set_efer(&svm->vcpu, svm->nested.save.efer); - svm_set_cr0(&svm->vcpu, vmcb12->save.cr0); - svm_set_cr4(&svm->vcpu, vmcb12->save.cr4); + svm_set_cr0(&svm->vcpu, svm->nested.save.cr0); + svm_set_cr4(&svm->vcpu, svm->nested.save.cr4); svm->vcpu.arch.cr2 = vmcb12->save.cr2; @@ -513,8 +531,8 @@ static void nested_vmcb02_prepare_save(struct vcpu_svm *svm, struct vmcb *vmcb12 /* These bits will be set properly on the first execution when new_vmc12 is true */ if (unlikely(new_vmcb12 || vmcb_is_dirty(vmcb12, VMCB_DR))) { - svm->vmcb->save.dr7 = vmcb12->save.dr7 | DR7_FIXED_1; - svm->vcpu.arch.dr6 = vmcb12->save.dr6 | DR6_ACTIVE_LOW; + svm->vmcb->save.dr7 = svm->nested.save.dr7 | DR7_FIXED_1; + svm->vcpu.arch.dr6 = svm->nested.save.dr6 | DR6_ACTIVE_LOW; vmcb_mark_dirty(svm->vmcb, VMCB_DR); } } @@ -628,7 +646,7 @@ int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb12_gpa, nested_vmcb02_prepare_control(svm); nested_vmcb02_prepare_save(svm, vmcb12); - ret = nested_svm_load_cr3(&svm->vcpu, vmcb12->save.cr3, + ret = nested_svm_load_cr3(&svm->vcpu, svm->nested.save.cr3, nested_npt_enabled(svm), from_vmrun); if (ret) return ret; @@ -678,10 +696,11 @@ int nested_svm_vmrun(struct kvm_vcpu *vcpu) if (WARN_ON_ONCE(!svm->nested.initialized)) return -EINVAL; - nested_load_control_from_vmcb12(svm, &vmcb12->control); + nested_copy_vmcb_control_to_cache(svm, &vmcb12->control); + nested_copy_vmcb_save_to_cache(svm, &vmcb12->save); - if (!nested_vmcb_valid_sregs(vcpu, &vmcb12->save) || - !nested_vmcb_check_controls(vcpu, &svm->nested.ctl)) { + if (!nested_vmcb_check_save(vcpu) || + !nested_vmcb_check_controls(vcpu)) { vmcb12->control.exit_code = SVM_EXIT_ERR; vmcb12->control.exit_code_hi = 0; vmcb12->control.exit_info_1 = 0; @@ -988,7 +1007,7 @@ static int nested_svm_exit_handled_msr(struct vcpu_svm *svm) u32 offset, msr, value; int write, mask; - if (!(vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT))) + if (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT))) return NESTED_EXIT_HOST; msr = svm->vcpu.arch.regs[VCPU_REGS_RCX]; @@ -1015,7 +1034,7 @@ static int nested_svm_intercept_ioio(struct vcpu_svm *svm) u8 start_bit; u64 gpa; - if (!(vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_IOIO_PROT))) + if (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_IOIO_PROT))) return NESTED_EXIT_HOST; port = svm->vmcb->control.exit_info_1 >> 16; @@ -1046,12 +1065,12 @@ static int nested_svm_intercept(struct vcpu_svm *svm) vmexit = nested_svm_intercept_ioio(svm); break; case SVM_EXIT_READ_CR0 ... SVM_EXIT_WRITE_CR8: { - if (vmcb_is_intercept(&svm->nested.ctl, exit_code)) + if (vmcb12_is_intercept(&svm->nested.ctl, exit_code)) vmexit = NESTED_EXIT_DONE; break; } case SVM_EXIT_READ_DR0 ... SVM_EXIT_WRITE_DR7: { - if (vmcb_is_intercept(&svm->nested.ctl, exit_code)) + if (vmcb12_is_intercept(&svm->nested.ctl, exit_code)) vmexit = NESTED_EXIT_DONE; break; } @@ -1069,7 +1088,7 @@ static int nested_svm_intercept(struct vcpu_svm *svm) break; } default: { - if (vmcb_is_intercept(&svm->nested.ctl, exit_code)) + if (vmcb12_is_intercept(&svm->nested.ctl, exit_code)) vmexit = NESTED_EXIT_DONE; } } @@ -1147,7 +1166,7 @@ static void nested_svm_inject_exception_vmexit(struct vcpu_svm *svm) static inline bool nested_exit_on_init(struct vcpu_svm *svm) { - return vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_INIT); + return vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_INIT); } static int svm_check_nested_events(struct kvm_vcpu *vcpu) @@ -1251,11 +1270,47 @@ void nested_svm_update_tsc_ratio_msr(struct kvm_vcpu *vcpu) svm_write_tsc_multiplier(vcpu, vcpu->arch.tsc_scaling_ratio); } +/* Inverse operation of nested_copy_vmcb_control_to_cache(). asid is copied too. */ +static void nested_copy_vmcb_cache_to_control(struct vmcb_control_area *dst, + struct vmcb_ctrl_area_cached *from) +{ + unsigned int i; + + memset(dst, 0, sizeof(struct vmcb_control_area)); + + for (i = 0; i < MAX_INTERCEPT; i++) + dst->intercepts[i] = from->intercepts[i]; + + dst->iopm_base_pa = from->iopm_base_pa; + dst->msrpm_base_pa = from->msrpm_base_pa; + dst->tsc_offset = from->tsc_offset; + dst->asid = from->asid; + dst->tlb_ctl = from->tlb_ctl; + dst->int_ctl = from->int_ctl; + dst->int_vector = from->int_vector; + dst->int_state = from->int_state; + dst->exit_code = from->exit_code; + dst->exit_code_hi = from->exit_code_hi; + dst->exit_info_1 = from->exit_info_1; + dst->exit_info_2 = from->exit_info_2; + dst->exit_int_info = from->exit_int_info; + dst->exit_int_info_err = from->exit_int_info_err; + dst->nested_ctl = from->nested_ctl; + dst->event_inj = from->event_inj; + dst->event_inj_err = from->event_inj_err; + dst->nested_cr3 = from->nested_cr3; + dst->virt_ext = from->virt_ext; + dst->pause_filter_count = from->pause_filter_count; + dst->pause_filter_thresh = from->pause_filter_thresh; +} + static int svm_get_nested_state(struct kvm_vcpu *vcpu, struct kvm_nested_state __user *user_kvm_nested_state, u32 user_data_size) { struct vcpu_svm *svm; + struct vmcb_control_area *ctl; + unsigned long r; struct kvm_nested_state kvm_state = { .flags = 0, .format = KVM_STATE_NESTED_FORMAT_SVM, @@ -1297,9 +1352,18 @@ static int svm_get_nested_state(struct kvm_vcpu *vcpu, */ if (clear_user(user_vmcb, KVM_STATE_NESTED_SVM_VMCB_SIZE)) return -EFAULT; - if (copy_to_user(&user_vmcb->control, &svm->nested.ctl, - sizeof(user_vmcb->control))) + + ctl = kzalloc(sizeof(*ctl), GFP_KERNEL); + if (!ctl) + return -ENOMEM; + + nested_copy_vmcb_cache_to_control(ctl, &svm->nested.ctl); + r = copy_to_user(&user_vmcb->control, ctl, + sizeof(user_vmcb->control)); + kfree(ctl); + if (r) return -EFAULT; + if (copy_to_user(&user_vmcb->save, &svm->vmcb01.ptr->save, sizeof(user_vmcb->save))) return -EFAULT; @@ -1316,6 +1380,8 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, &user_kvm_nested_state->data.svm[0]; struct vmcb_control_area *ctl; struct vmcb_save_area *save; + struct vmcb_save_area_cached save_cached; + struct vmcb_ctrl_area_cached ctl_cached; unsigned long cr0; int ret; @@ -1368,7 +1434,8 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, goto out_free; ret = -EINVAL; - if (!nested_vmcb_check_controls(vcpu, ctl)) + __nested_copy_vmcb_control_to_cache(&ctl_cached, ctl); + if (!__nested_vmcb_check_controls(vcpu, &ctl_cached)) goto out_free; /* @@ -1383,10 +1450,11 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, * Validate host state saved from before VMRUN (see * nested_svm_check_permissions). */ + __nested_copy_vmcb_save_to_cache(&save_cached, save); if (!(save->cr0 & X86_CR0_PG) || !(save->cr0 & X86_CR0_PE) || (save->rflags & X86_EFLAGS_VM) || - !nested_vmcb_valid_sregs(vcpu, save)) + !__nested_vmcb_check_save(vcpu, &save_cached)) goto out_free; /* @@ -1422,7 +1490,7 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, svm->nested.vmcb12_gpa = kvm_state->hdr.svm.vmcb_pa; svm_copy_vmrun_state(&svm->vmcb01.ptr->save, save); - nested_load_control_from_vmcb12(svm, ctl); + nested_copy_vmcb_control_to_cache(svm, ctl); svm_switch_vmcb(svm, &svm->nested.vmcb02); nested_vmcb02_prepare_control(svm); @@ -1449,7 +1517,7 @@ static bool svm_get_nested_state_pages(struct kvm_vcpu *vcpu) * the guest CR3 might be restored prior to setting the nested * state which can lead to a load of wrong PDPTRs. */ - if (CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, vcpu->arch.cr3))) + if (CC(!load_pdptrs(vcpu, vcpu->arch.cr3))) return false; if (!nested_svm_vmrun_msrpm(svm)) { diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index b4095dfeeee6..0cf05e4caa4c 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -16,6 +16,7 @@ #include "cpuid.h" #include "lapic.h" #include "pmu.h" +#include "svm.h" enum pmu_type { PMU_TYPE_COUNTER = 0, @@ -100,6 +101,9 @@ static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr, { struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu); + if (!pmu) + return NULL; + switch (msr) { case MSR_F15H_PERF_CTL0: case MSR_F15H_PERF_CTL1: diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 7656a2c5662a..322553322202 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -636,7 +636,8 @@ static int __sev_launch_update_vmsa(struct kvm *kvm, struct kvm_vcpu *vcpu, static int sev_launch_update_vmsa(struct kvm *kvm, struct kvm_sev_cmd *argp) { struct kvm_vcpu *vcpu; - int i, ret; + unsigned long i; + int ret; if (!sev_es_guest(kvm)) return -ENOTTY; @@ -1593,7 +1594,7 @@ static void sev_unlock_two_vms(struct kvm *dst_kvm, struct kvm *src_kvm) static int sev_lock_vcpus_for_migration(struct kvm *kvm) { struct kvm_vcpu *vcpu; - int i, j; + unsigned long i, j; kvm_for_each_vcpu(i, vcpu, kvm) { if (mutex_lock_killable(&vcpu->mutex)) @@ -1615,7 +1616,7 @@ out_unlock: static void sev_unlock_vcpus_for_migration(struct kvm *kvm) { struct kvm_vcpu *vcpu; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { mutex_unlock(&vcpu->mutex); @@ -1642,7 +1643,7 @@ static void sev_migrate_from(struct kvm_sev_info *dst, static int sev_es_migrate_from(struct kvm *dst, struct kvm *src) { - int i; + unsigned long i; struct kvm_vcpu *dst_vcpu, *src_vcpu; struct vcpu_svm *dst_svm, *src_svm; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 5151efa424ac..5557867dcb69 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -192,6 +192,10 @@ module_param(vgif, int, 0444); static int lbrv = true; module_param(lbrv, int, 0444); +/* enable/disable PMU virtualization */ +bool pmu = true; +module_param(pmu, bool, 0444); + static int tsc_scaling = true; module_param(tsc_scaling, int, 0444); @@ -265,7 +269,7 @@ u32 svm_msrpm_offset(u32 msr) #define MAX_INST_SIZE 15 -static int get_max_npt_level(void) +static int get_npt_level(void) { #ifdef CONFIG_X86_64 return pgtable_l5_enabled() ? PT64_ROOT_5LEVEL : PT64_ROOT_4LEVEL; @@ -585,12 +589,10 @@ static int svm_cpu_init(int cpu) if (!sd) return ret; sd->cpu = cpu; - sd->save_area = alloc_page(GFP_KERNEL); + sd->save_area = alloc_page(GFP_KERNEL | __GFP_ZERO); if (!sd->save_area) goto free_cpu_data; - clear_page(page_address(sd->save_area)); - ret = sev_cpu_init(sd); if (ret) goto free_save_area; @@ -954,6 +956,10 @@ static __init void svm_set_cpu_caps(void) boot_cpu_has(X86_FEATURE_AMD_SSBD)) kvm_cpu_cap_set(X86_FEATURE_VIRT_SSBD); + /* AMD PMU PERFCTR_CORE CPUID */ + if (pmu && boot_cpu_has(X86_FEATURE_PERFCTR_CORE)) + kvm_cpu_cap_set(X86_FEATURE_PERFCTR_CORE); + /* CPUID 0x8000001F (SME/SEV features) */ sev_set_cpu_caps(); } @@ -1029,9 +1035,9 @@ static __init int svm_hardware_setup(void) if (!boot_cpu_has(X86_FEATURE_NPT)) npt_enabled = false; - /* Force VM NPT level equal to the host's max NPT level */ - kvm_configure_mmu(npt_enabled, get_max_npt_level(), - get_max_npt_level(), PG_LEVEL_1G); + /* Force VM NPT level equal to the host's paging level */ + kvm_configure_mmu(npt_enabled, get_npt_level(), + get_npt_level(), PG_LEVEL_1G); pr_info("kvm: Nested Paging %sabled\n", npt_enabled ? "en" : "dis"); /* Note, SEV setup consumes npt_enabled. */ @@ -1087,6 +1093,9 @@ static __init int svm_hardware_setup(void) pr_info("LBR virtualization supported\n"); } + if (!pmu) + pr_info("PMU virtualization is disabled\n"); + svm_set_cpu_caps(); /* @@ -1596,10 +1605,16 @@ static bool svm_get_if_flag(struct kvm_vcpu *vcpu) static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) { + kvm_register_mark_available(vcpu, reg); + switch (reg) { case VCPU_EXREG_PDPTR: - BUG_ON(!npt_enabled); - load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu)); + /* + * When !npt_enabled, mmu->pdptrs[] is already available since + * it is always updated per SDM when moving to CRs. + */ + if (npt_enabled) + load_pdptrs(vcpu, kvm_read_cr3(vcpu)); break; default: KVM_BUG_ON(1, vcpu->kvm); @@ -2517,7 +2532,7 @@ static bool check_selective_cr0_intercepted(struct kvm_vcpu *vcpu, bool ret = false; if (!is_guest_mode(vcpu) || - (!(vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_SELECTIVE_CR0)))) + (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_SELECTIVE_CR0)))) return false; cr0 &= ~SVM_CR0_SELECTIVE_MASK; @@ -3931,6 +3946,7 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) vcpu->arch.regs[VCPU_REGS_RSP] = svm->vmcb->save.rsp; vcpu->arch.regs[VCPU_REGS_RIP] = svm->vmcb->save.rip; } + vcpu->arch.regs_dirty = 0; if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI)) kvm_before_interrupt(vcpu); @@ -3965,8 +3981,7 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) vcpu->arch.apf.host_apf_flags = kvm_read_and_reset_apf_flags(); - if (npt_enabled) - kvm_register_clear_available(vcpu, VCPU_EXREG_PDPTR); + vcpu->arch.regs_avail &= ~SVM_REGS_LAZY_LOAD_SET; /* * We need to handle MC intercepts here before the vcpu has a chance to @@ -3996,9 +4011,6 @@ static void svm_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, hv_track_root_tdp(vcpu, root_hpa); - /* Loading L2's CR3 is handled by enter_svm_guest_mode. */ - if (!test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail)) - return; cr3 = vcpu->arch.cr3; } else if (vcpu->arch.mmu->shadow_root_level >= PT64_ROOT_4LEVEL) { cr3 = __sme_set(root_hpa) | kvm_get_active_pcid(vcpu); @@ -4217,7 +4229,7 @@ static int svm_check_intercept(struct kvm_vcpu *vcpu, info->intercept == x86_intercept_clts) break; - if (!(vmcb_is_intercept(&svm->nested.ctl, + if (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_SELECTIVE_CR0))) break; @@ -4436,7 +4448,8 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) */ vmcb12 = map.hva; - nested_load_control_from_vmcb12(svm, &vmcb12->control); + nested_copy_vmcb_control_to_cache(svm, &vmcb12->control); + nested_copy_vmcb_save_to_cache(svm, &vmcb12->save); ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12, false); unmap_save: diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 1c7306c370fa..9f153c59f2c8 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -32,6 +32,7 @@ extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; extern bool npt_enabled; extern bool intercept_smi; +extern bool pmu; /* * Clean bits in VMCB. @@ -105,6 +106,40 @@ struct kvm_vmcb_info { uint64_t asid_generation; }; +struct vmcb_save_area_cached { + u64 efer; + u64 cr4; + u64 cr3; + u64 cr0; + u64 dr7; + u64 dr6; +}; + +struct vmcb_ctrl_area_cached { + u32 intercepts[MAX_INTERCEPT]; + u16 pause_filter_thresh; + u16 pause_filter_count; + u64 iopm_base_pa; + u64 msrpm_base_pa; + u64 tsc_offset; + u32 asid; + u8 tlb_ctl; + u32 int_ctl; + u32 int_vector; + u32 int_state; + u32 exit_code; + u32 exit_code_hi; + u64 exit_info_1; + u64 exit_info_2; + u32 exit_int_info; + u32 exit_int_info_err; + u64 nested_ctl; + u32 event_inj; + u32 event_inj_err; + u64 nested_cr3; + u64 virt_ext; +}; + struct svm_nested_state { struct kvm_vmcb_info vmcb02; u64 hsave_msr; @@ -120,7 +155,13 @@ struct svm_nested_state { bool nested_run_pending; /* cache for control fields of the guest */ - struct vmcb_control_area ctl; + struct vmcb_ctrl_area_cached ctl; + + /* + * Note: this struct is not kept up-to-date while L2 runs; it is only + * valid within nested_svm_vmrun. + */ + struct vmcb_save_area_cached save; bool initialized; }; @@ -285,6 +326,16 @@ static __always_inline struct vcpu_svm *to_svm(struct kvm_vcpu *vcpu) return container_of(vcpu, struct vcpu_svm, vcpu); } +/* + * Only the PDPTRs are loaded on demand into the shadow MMU. All other + * fields are synchronized in handle_exit, because accessing the VMCB is cheap. + * + * CR3 might be out of date in the VMCB but it is not marked dirty; instead, + * KVM_REQ_LOAD_MMU_PGD is always requested when the cached vcpu->arch.cr3 + * is changed. svm_load_mmu_pgd() then syncs the new CR3 value into the VMCB. + */ +#define SVM_REGS_LAZY_LOAD_SET (1 << VCPU_EXREG_PDPTR) + static inline void vmcb_set_intercept(struct vmcb_control_area *control, u32 bit) { WARN_ON_ONCE(bit >= 32 * MAX_INTERCEPT); @@ -303,6 +354,12 @@ static inline bool vmcb_is_intercept(struct vmcb_control_area *control, u32 bit) return test_bit(bit, (unsigned long *)&control->intercepts); } +static inline bool vmcb12_is_intercept(struct vmcb_ctrl_area_cached *control, u32 bit) +{ + WARN_ON_ONCE(bit >= 32 * MAX_INTERCEPT); + return test_bit(bit, (unsigned long *)&control->intercepts); +} + static inline void set_dr_intercepts(struct vcpu_svm *svm) { struct vmcb *vmcb = svm->vmcb01.ptr; @@ -455,17 +512,17 @@ static inline bool nested_svm_virtualize_tpr(struct kvm_vcpu *vcpu) static inline bool nested_exit_on_smi(struct vcpu_svm *svm) { - return vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_SMI); + return vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_SMI); } static inline bool nested_exit_on_intr(struct vcpu_svm *svm) { - return vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_INTR); + return vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_INTR); } static inline bool nested_exit_on_nmi(struct vcpu_svm *svm) { - return vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_NMI); + return vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_NMI); } int enter_svm_guest_mode(struct kvm_vcpu *vcpu, @@ -494,8 +551,10 @@ int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, int nested_svm_exit_special(struct vcpu_svm *svm); void nested_svm_update_tsc_ratio_msr(struct kvm_vcpu *vcpu); void svm_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 multiplier); -void nested_load_control_from_vmcb12(struct vcpu_svm *svm, - struct vmcb_control_area *control); +void nested_copy_vmcb_control_to_cache(struct vcpu_svm *svm, + struct vmcb_control_area *control); +void nested_copy_vmcb_save_to_cache(struct vcpu_svm *svm, + struct vmcb_save_area *save); void nested_sync_control_from_vmcb02(struct vcpu_svm *svm); void nested_vmcb02_compute_g_pat(struct vcpu_svm *svm); void svm_switch_vmcb(struct vcpu_svm *svm, struct kvm_vmcb_info *target_vmcb); diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 953b0fcb21ee..92e6f6702f00 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -1356,6 +1356,30 @@ TRACE_EVENT(kvm_apicv_update_request, __entry->bit) ); +TRACE_EVENT(kvm_apicv_accept_irq, + TP_PROTO(__u32 apicid, __u16 dm, __u16 tm, __u8 vec), + TP_ARGS(apicid, dm, tm, vec), + + TP_STRUCT__entry( + __field( __u32, apicid ) + __field( __u16, dm ) + __field( __u16, tm ) + __field( __u8, vec ) + ), + + TP_fast_assign( + __entry->apicid = apicid; + __entry->dm = dm; + __entry->tm = tm; + __entry->vec = vec; + ), + + TP_printk("apicid %x vec %u (%s|%s)", + __entry->apicid, __entry->vec, + __print_symbolic((__entry->dm >> 8 & 0x7), kvm_deliver_mode), + __entry->tm ? "level" : "edge") +); + /* * Tracepoint for AMD AVIC */ diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index 4705ad55abb5..c8029b7845b6 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -312,6 +312,15 @@ static inline bool cpu_has_vmx_ept_1g_page(void) return vmx_capability.ept & VMX_EPT_1GB_PAGE_BIT; } +static inline int ept_caps_to_lpage_level(u32 ept_caps) +{ + if (ept_caps & VMX_EPT_1GB_PAGE_BIT) + return PG_LEVEL_1G; + if (ept_caps & VMX_EPT_2MB_PAGE_BIT) + return PG_LEVEL_2M; + return PG_LEVEL_4K; +} + static inline bool cpu_has_vmx_ept_ad_bits(void) { return vmx_capability.ept & VMX_EPT_AD_BIT; diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 9c941535f78c..2f6f465e575f 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -269,7 +269,13 @@ static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs) vmx_sync_vmcs_host_state(vmx, prev); put_cpu(); - vmx_register_cache_reset(vcpu); + vcpu->arch.regs_avail = ~VMX_REGS_LAZY_LOAD_SET; + + /* + * All lazily updated registers will be reloaded from VMCS12 on both + * vmentry and vmexit. + */ + vcpu->arch.regs_dirty = 0; } /* @@ -391,9 +397,11 @@ static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu, static void nested_ept_new_eptp(struct kvm_vcpu *vcpu) { - kvm_init_shadow_ept_mmu(vcpu, - to_vmx(vcpu)->nested.msrs.ept_caps & - VMX_EPT_EXECUTE_ONLY_BIT, + struct vcpu_vmx *vmx = to_vmx(vcpu); + bool execonly = vmx->nested.msrs.ept_caps & VMX_EPT_EXECUTE_ONLY_BIT; + int ept_lpage_level = ept_caps_to_lpage_level(vmx->nested.msrs.ept_caps); + + kvm_init_shadow_ept_mmu(vcpu, execonly, ept_lpage_level, nested_ept_ad_enabled(vcpu), nested_ept_get_eptp(vcpu)); } @@ -591,6 +599,7 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, int msr; unsigned long *msr_bitmap_l1; unsigned long *msr_bitmap_l0 = vmx->nested.vmcs02.msr_bitmap; + struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs; struct kvm_host_map *map = &vmx->nested.msr_bitmap_map; /* Nothing to do if the MSR bitmap is not in use. */ @@ -598,6 +607,19 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, !nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS)) return false; + /* + * MSR bitmap update can be skipped when: + * - MSR bitmap for L1 hasn't changed. + * - Nested hypervisor (L1) is attempting to launch the same L2 as + * before. + * - Nested hypervisor (L1) has enabled 'Enlightened MSR Bitmap' feature + * and tells KVM (L0) there were no changes in MSR bitmap for L2. + */ + if (!vmx->nested.force_msr_bitmap_recalc && evmcs && + evmcs->hv_enlightenments_control.msr_bitmap && + evmcs->hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP) + return true; + if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->msr_bitmap), map)) return false; @@ -664,6 +686,8 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, kvm_vcpu_unmap(vcpu, &vmx->nested.msr_bitmap_map, false); + vmx->nested.force_msr_bitmap_recalc = false; + return true; } @@ -1095,7 +1119,7 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, * must not be dereferenced. */ if (reload_pdptrs && !nested_ept && is_pae_paging(vcpu) && - CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))) { + CC(!load_pdptrs(vcpu, cr3))) { *entry_failure_code = ENTRY_FAIL_PDPTE; return -EINVAL; } @@ -1104,7 +1128,7 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, kvm_mmu_new_pgd(vcpu, cr3); vcpu->arch.cr3 = cr3; - kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); + kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3); /* Re-initialize the MMU, e.g. to pick up CR4 MMU role changes. */ kvm_init_mmu(vcpu); @@ -2021,10 +2045,13 @@ static enum nested_evmptrld_status nested_vmx_handle_enlightened_vmptrld( * Clean fields data can't be used on VMLAUNCH and when we switch * between different L2 guests as KVM keeps a single VMCS12 per L1. */ - if (from_launch || evmcs_gpa_changed) + if (from_launch || evmcs_gpa_changed) { vmx->nested.hv_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; + vmx->nested.force_msr_bitmap_recalc = true; + } + return EVMPTRLD_SUCCEEDED; } @@ -3027,7 +3054,7 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long cr3, cr4; + unsigned long cr4; bool vm_fail; if (!nested_early_check) @@ -3050,12 +3077,6 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) */ vmcs_writel(GUEST_RFLAGS, 0); - cr3 = __get_current_cr3_fast(); - if (unlikely(cr3 != vmx->loaded_vmcs->host_state.cr3)) { - vmcs_writel(HOST_CR3, cr3); - vmx->loaded_vmcs->host_state.cr3 = cr3; - } - cr4 = cr4_read_shadow(); if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) { vmcs_writel(HOST_CR4, cr4); @@ -3145,7 +3166,7 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) * the guest CR3 might be restored prior to setting the nested * state which can lead to a load of wrong PDPTRs. */ - if (CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, vcpu->arch.cr3))) + if (CC(!load_pdptrs(vcpu, vcpu->arch.cr3))) return false; } @@ -3603,7 +3624,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) !(nested_cpu_has(vmcs12, CPU_BASED_INTR_WINDOW_EXITING) && (vmcs12->guest_rflags & X86_EFLAGS_IF))) { vmx->nested.nested_run_pending = 0; - return kvm_vcpu_halt(vcpu); + return kvm_emulate_halt_noskip(vcpu); } break; case GUEST_ACTIVITY_WAIT_SIPI: @@ -5258,6 +5279,7 @@ static void set_current_vmptr(struct vcpu_vmx *vmx, gpa_t vmptr) vmx->nested.need_vmcs12_to_shadow_sync = true; } vmx->nested.dirty_vmcs12 = true; + vmx->nested.force_msr_bitmap_recalc = true; } /* Emulate the VMPTRLD instruction */ @@ -6393,6 +6415,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, goto error_guest_mode; vmx->nested.dirty_vmcs12 = true; + vmx->nested.force_msr_bitmap_recalc = true; ret = nested_vmx_enter_non_root_mode(vcpu, false); if (ret) goto error_guest_mode; diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c index 1c94783b5a54..88c53c521094 100644 --- a/arch/x86/kvm/vmx/posted_intr.c +++ b/arch/x86/kvm/vmx/posted_intr.c @@ -11,10 +11,22 @@ #include "vmx.h" /* - * We maintain a per-CPU linked-list of vCPU, so in wakeup_handler() we - * can find which vCPU should be waken up. + * Maintain a per-CPU list of vCPUs that need to be awakened by wakeup_handler() + * when a WAKEUP_VECTOR interrupted is posted. vCPUs are added to the list when + * the vCPU is scheduled out and is blocking (e.g. in HLT) with IRQs enabled. + * The vCPUs posted interrupt descriptor is updated at the same time to set its + * notification vector to WAKEUP_VECTOR, so that posted interrupt from devices + * wake the target vCPUs. vCPUs are removed from the list and the notification + * vector is reset when the vCPU is scheduled in. */ static DEFINE_PER_CPU(struct list_head, blocked_vcpu_on_cpu); +/* + * Protect the per-CPU list with a per-CPU spinlock to handle task migration. + * When a blocking vCPU is awakened _and_ migrated to a different pCPU, the + * ->sched_in() path will need to take the vCPU off the list of the _previous_ + * CPU. IRQs must be disabled when taking this lock, otherwise deadlock will + * occur if a wakeup IRQ arrives and attempts to acquire the lock. + */ static DEFINE_PER_CPU(spinlock_t, blocked_vcpu_on_cpu_lock); static inline struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu) @@ -22,6 +34,20 @@ static inline struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu) return &(to_vmx(vcpu)->pi_desc); } +static int pi_try_set_control(struct pi_desc *pi_desc, u64 old, u64 new) +{ + /* + * PID.ON can be set at any time by a different vCPU or by hardware, + * e.g. a device. PID.control must be written atomically, and the + * update must be retried with a fresh snapshot an ON change causes + * the cmpxchg to fail. + */ + if (cmpxchg64(&pi_desc->control, old, new) != old) + return -EBUSY; + + return 0; +} + void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) { struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); @@ -29,11 +55,14 @@ void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) unsigned int dest; /* - * In case of hot-plug or hot-unplug, we may have to undo - * vmx_vcpu_pi_put even if there is no assigned device. And we - * always keep PI.NDST up to date for simplicity: it makes the - * code easier, and CPU migration is not a fast path. + * To simplify hot-plug and dynamic toggling of APICv, keep PI.NDST and + * PI.SN up-to-date even if there is no assigned device or if APICv is + * deactivated due to a dynamic inhibit bit, e.g. for Hyper-V's SyncIC. */ + if (!enable_apicv || !lapic_in_kernel(vcpu)) + return; + + /* Nothing to do if PI.SN and PI.NDST both have the desired value. */ if (!pi_test_sn(pi_desc) && vcpu->cpu == cpu) return; @@ -49,20 +78,17 @@ void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) goto after_clear_sn; } - /* The full case. */ - do { - old.control = new.control = pi_desc->control; - - dest = cpu_physical_id(cpu); + /* The full case. Set the new destination and clear SN. */ + dest = cpu_physical_id(cpu); + if (!x2apic_mode) + dest = (dest << 8) & 0xFF00; - if (x2apic_mode) - new.ndst = dest; - else - new.ndst = (dest << 8) & 0xFF00; + do { + old.control = new.control = READ_ONCE(pi_desc->control); + new.ndst = dest; new.sn = 0; - } while (cmpxchg64(&pi_desc->control, old.control, - new.control) != old.control); + } while (pi_try_set_control(pi_desc, old.control, new.control)); after_clear_sn: @@ -103,29 +129,31 @@ static void __pi_post_block(struct kvm_vcpu *vcpu) struct pi_desc old, new; unsigned int dest; - do { - old.control = new.control = pi_desc->control; - WARN(old.nv != POSTED_INTR_WAKEUP_VECTOR, - "Wakeup handler not enabled while the VCPU is blocked\n"); + /* + * Remove the vCPU from the wakeup list of the _previous_ pCPU, which + * will not be the same as the current pCPU if the task was migrated. + */ + spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); + list_del(&vcpu->blocked_vcpu_list); + spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); - dest = cpu_physical_id(vcpu->cpu); + dest = cpu_physical_id(vcpu->cpu); + if (!x2apic_mode) + dest = (dest << 8) & 0xFF00; - if (x2apic_mode) - new.ndst = dest; - else - new.ndst = (dest << 8) & 0xFF00; + WARN(pi_desc->nv != POSTED_INTR_WAKEUP_VECTOR, + "Wakeup handler not enabled while the vCPU was blocking"); + + do { + old.control = new.control = READ_ONCE(pi_desc->control); + + new.ndst = dest; /* set 'NV' to 'notification vector' */ new.nv = POSTED_INTR_VECTOR; - } while (cmpxchg64(&pi_desc->control, old.control, - new.control) != old.control); - - if (!WARN_ON_ONCE(vcpu->pre_pcpu == -1)) { - spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); - list_del(&vcpu->blocked_vcpu_list); - spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); - vcpu->pre_pcpu = -1; - } + } while (pi_try_set_control(pi_desc, old.control, new.control)); + + vcpu->pre_pcpu = -1; } /* @@ -134,7 +162,6 @@ static void __pi_post_block(struct kvm_vcpu *vcpu) * - Store the vCPU to the wakeup list, so when interrupts happen * we can find the right vCPU to wake up. * - Change the Posted-interrupt descriptor as below: - * 'NDST' <-- vcpu->pre_pcpu * 'NV' <-- POSTED_INTR_WAKEUP_VECTOR * - If 'ON' is set during this process, which means at least one * interrupt is posted for this vCPU, we cannot block it, in @@ -143,68 +170,50 @@ static void __pi_post_block(struct kvm_vcpu *vcpu) */ int pi_pre_block(struct kvm_vcpu *vcpu) { - unsigned int dest; struct pi_desc old, new; struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); + unsigned long flags; - if (!vmx_can_use_vtd_pi(vcpu->kvm)) + if (!vmx_can_use_vtd_pi(vcpu->kvm) || + vmx_interrupt_blocked(vcpu)) return 0; - WARN_ON(irqs_disabled()); - local_irq_disable(); - if (!WARN_ON_ONCE(vcpu->pre_pcpu != -1)) { - vcpu->pre_pcpu = vcpu->cpu; - spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); - list_add_tail(&vcpu->blocked_vcpu_list, - &per_cpu(blocked_vcpu_on_cpu, - vcpu->pre_pcpu)); - spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); - } - - do { - old.control = new.control = pi_desc->control; + local_irq_save(flags); - WARN((pi_desc->sn == 1), - "Warning: SN field of posted-interrupts " - "is set before blocking\n"); + vcpu->pre_pcpu = vcpu->cpu; + spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->cpu)); + list_add_tail(&vcpu->blocked_vcpu_list, + &per_cpu(blocked_vcpu_on_cpu, vcpu->cpu)); + spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->cpu)); - /* - * Since vCPU can be preempted during this process, - * vcpu->cpu could be different with pre_pcpu, we - * need to set pre_pcpu as the destination of wakeup - * notification event, then we can find the right vCPU - * to wakeup in wakeup handler if interrupts happen - * when the vCPU is in blocked state. - */ - dest = cpu_physical_id(vcpu->pre_pcpu); + WARN(pi_desc->sn == 1, + "Posted Interrupt Suppress Notification set before blocking"); - if (x2apic_mode) - new.ndst = dest; - else - new.ndst = (dest << 8) & 0xFF00; + do { + old.control = new.control = READ_ONCE(pi_desc->control); /* set 'NV' to 'wakeup vector' */ new.nv = POSTED_INTR_WAKEUP_VECTOR; - } while (cmpxchg64(&pi_desc->control, old.control, - new.control) != old.control); + } while (pi_try_set_control(pi_desc, old.control, new.control)); /* We should not block the vCPU if an interrupt is posted for it. */ - if (pi_test_on(pi_desc) == 1) + if (pi_test_on(pi_desc)) __pi_post_block(vcpu); - local_irq_enable(); + local_irq_restore(flags); return (vcpu->pre_pcpu == -1); } void pi_post_block(struct kvm_vcpu *vcpu) { + unsigned long flags; + if (vcpu->pre_pcpu == -1) return; - WARN_ON(irqs_disabled()); - local_irq_disable(); + local_irq_save(flags); __pi_post_block(vcpu); - local_irq_enable(); + local_irq_restore(flags); } /* @@ -220,7 +229,7 @@ void pi_wakeup_handler(void) blocked_vcpu_list) { struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); - if (pi_test_on(pi_desc) == 1) + if (pi_test_on(pi_desc)) kvm_vcpu_kick(vcpu); } spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu)); diff --git a/arch/x86/kvm/vmx/posted_intr.h b/arch/x86/kvm/vmx/posted_intr.h index 7f7b2326caf5..36ae035f14aa 100644 --- a/arch/x86/kvm/vmx/posted_intr.h +++ b/arch/x86/kvm/vmx/posted_intr.h @@ -40,7 +40,7 @@ static inline bool pi_test_and_clear_on(struct pi_desc *pi_desc) (unsigned long *)&pi_desc->control); } -static inline int pi_test_and_set_pir(int vector, struct pi_desc *pi_desc) +static inline bool pi_test_and_set_pir(int vector, struct pi_desc *pi_desc) { return test_and_set_bit(vector, (unsigned long *)pi_desc->pir); } @@ -74,13 +74,13 @@ static inline void pi_clear_sn(struct pi_desc *pi_desc) (unsigned long *)&pi_desc->control); } -static inline int pi_test_on(struct pi_desc *pi_desc) +static inline bool pi_test_on(struct pi_desc *pi_desc) { return test_bit(POSTED_INTR_ON, (unsigned long *)&pi_desc->control); } -static inline int pi_test_sn(struct pi_desc *pi_desc) +static inline bool pi_test_sn(struct pi_desc *pi_desc) { return test_bit(POSTED_INTR_SN, (unsigned long *)&pi_desc->control); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 0dbf94eb954f..9bf65e5e4840 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -602,15 +602,13 @@ static int vmx_set_guest_uret_msr(struct vcpu_vmx *vmx, unsigned int slot = msr - vmx->guest_uret_msrs; int ret = 0; - u64 old_msr_data = msr->data; - msr->data = data; if (msr->load_into_hardware) { preempt_disable(); - ret = kvm_set_user_return_msr(slot, msr->data, msr->mask); + ret = kvm_set_user_return_msr(slot, data, msr->mask); preempt_enable(); - if (ret) - msr->data = old_msr_data; } + if (!ret) + msr->data = data; return ret; } @@ -1105,6 +1103,7 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) #ifdef CONFIG_X86_64 int cpu = raw_smp_processor_id(); #endif + unsigned long cr3; unsigned long fs_base, gs_base; u16 fs_sel, gs_sel; int i; @@ -1169,6 +1168,14 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) #endif vmx_set_host_fs_gs(host_state, fs_sel, gs_sel, fs_base, gs_base); + + /* Host CR3 including its PCID is stable when guest state is loaded. */ + cr3 = __get_current_cr3_fast(); + if (unlikely(cr3 != host_state->cr3)) { + vmcs_writel(HOST_CR3, cr3); + host_state->cr3 = cr3; + } + vmx->guest_state_loaded = true; } @@ -1271,7 +1278,6 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu, if (!already_loaded) { void *gdt = get_current_gdt_ro(); - unsigned long sysenter_esp; /* * Flush all EPTP/VPID contexts, the new pCPU may have stale @@ -1287,8 +1293,11 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu, (unsigned long)&get_cpu_entry_area(cpu)->tss.x86_tss); vmcs_writel(HOST_GDTR_BASE, (unsigned long)gdt); /* 22.2.4 */ - rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp); - vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */ + if (IS_ENABLED(CONFIG_IA32_EMULATION) || IS_ENABLED(CONFIG_X86_32)) { + /* 22.2.3 */ + vmcs_writel(HOST_IA32_SYSENTER_ESP, + (unsigned long)(cpu_entry_stack(cpu) + 1)); + } vmx->loaded_vmcs->cpu = cpu; } @@ -1753,7 +1762,7 @@ static int vmx_get_msr_feature(struct kvm_msr_entry *msr) } /* - * Reads an msr value (of 'msr_index') into 'pdata'. + * Reads an msr value (of 'msr_info->index') into 'msr_info->data'. * Returns 0 on success, non-0 otherwise. * Assumes vcpu_load() was already called. */ @@ -2100,9 +2109,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) } ret = kvm_set_msr_common(vcpu, msr_info); break; - case MSR_IA32_TSC_ADJUST: - ret = kvm_set_msr_common(vcpu, msr_info); - break; case MSR_IA32_MCG_EXT_CTL: if ((!msr_info->host_initiated && !(to_vmx(vcpu)->msr_ia32_feature_control & @@ -2985,7 +2991,7 @@ void ept_save_pdptrs(struct kvm_vcpu *vcpu) mmu->pdptrs[2] = vmcs_read64(GUEST_PDPTR2); mmu->pdptrs[3] = vmcs_read64(GUEST_PDPTR3); - kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR); + kvm_register_mark_available(vcpu, VCPU_EXREG_PDPTR); } #define CR3_EXITING_BITS (CPU_BASED_CR3_LOAD_EXITING | \ @@ -3110,9 +3116,9 @@ static void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, if (!enable_unrestricted_guest && !is_paging(vcpu)) guest_cr3 = to_kvm_vmx(kvm)->ept_identity_map_addr; - else if (test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail)) + else if (kvm_register_is_dirty(vcpu, VCPU_EXREG_CR3)) guest_cr3 = vcpu->arch.cr3; - else /* vmcs01.GUEST_CR3 is already up-to-date. */ + else /* vmcs.GUEST_CR3 is already up-to-date. */ update_guest_cr3 = false; vmx_ept_load_pdptrs(vcpu); } else { @@ -3687,6 +3693,19 @@ void free_vpid(int vpid) spin_unlock(&vmx_vpid_lock); } +static void vmx_msr_bitmap_l01_changed(struct vcpu_vmx *vmx) +{ + /* + * When KVM is a nested hypervisor on top of Hyper-V and uses + * 'Enlightened MSR Bitmap' feature L0 needs to know that MSR + * bitmap has changed. + */ + if (static_branch_unlikely(&enable_evmcs)) + evmcs_touch_msr_bitmap(); + + vmx->nested.force_msr_bitmap_recalc = true; +} + void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -3695,8 +3714,7 @@ void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type) if (!cpu_has_vmx_msr_bitmap()) return; - if (static_branch_unlikely(&enable_evmcs)) - evmcs_touch_msr_bitmap(); + vmx_msr_bitmap_l01_changed(vmx); /* * Mark the desired intercept state in shadow bitmap, this is needed @@ -3740,8 +3758,7 @@ void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type) if (!cpu_has_vmx_msr_bitmap()) return; - if (static_branch_unlikely(&enable_evmcs)) - evmcs_touch_msr_bitmap(); + vmx_msr_bitmap_l01_changed(vmx); /* * Mark the desired intercept state in shadow bitmap, this is needed @@ -3931,6 +3948,19 @@ static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu, */ vmx->nested.pi_pending = true; kvm_make_request(KVM_REQ_EVENT, vcpu); + + /* + * This pairs with the smp_mb_*() after setting vcpu->mode in + * vcpu_enter_guest() to guarantee the vCPU sees the event + * request if triggering a posted interrupt "fails" because + * vcpu->mode != IN_GUEST_MODE. The extra barrier is needed as + * the smb_wmb() in kvm_make_request() only ensures everything + * done before making the request is visible when the request + * is visible, it doesn't ensure ordering between the store to + * vcpu->requests and the load from vcpu->mode. + */ + smp_mb__after_atomic(); + /* the PIR and ON have been set by L1. */ if (!kvm_vcpu_trigger_posted_interrupt(vcpu, true)) kvm_vcpu_kick(vcpu); @@ -3964,6 +3994,12 @@ static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) if (pi_test_and_set_on(&vmx->pi_desc)) return 0; + /* + * The implied barrier in pi_test_and_set_on() pairs with the smp_mb_*() + * after setting vcpu->mode in vcpu_enter_guest(), thus the vCPU is + * guaranteed to see PID.ON=1 and sync the PIR to IRR if triggering a + * posted interrupt "fails" because vcpu->mode != IN_GUEST_MODE. + */ if (!kvm_vcpu_trigger_posted_interrupt(vcpu, false)) kvm_vcpu_kick(vcpu); @@ -4021,6 +4057,12 @@ void vmx_set_constant_host_state(struct vcpu_vmx *vmx) rdmsr(MSR_IA32_SYSENTER_CS, low32, high32); vmcs_write32(HOST_IA32_SYSENTER_CS, low32); + + /* + * If 32-bit syscall is enabled, vmx_vcpu_load_vcms rewrites + * HOST_IA32_SYSENTER_ESP. + */ + vmcs_writel(HOST_IA32_SYSENTER_ESP, 0); rdmsrl(MSR_IA32_SYSENTER_EIP, tmpl); vmcs_writel(HOST_IA32_SYSENTER_EIP, tmpl); /* 22.2.3 */ @@ -4039,8 +4081,10 @@ void set_cr4_guest_host_mask(struct vcpu_vmx *vmx) vcpu->arch.cr4_guest_owned_bits = KVM_POSSIBLE_CR4_GUEST_BITS & ~vcpu->arch.cr4_guest_rsvd_bits; - if (!enable_ept) - vcpu->arch.cr4_guest_owned_bits &= ~X86_CR4_PGE; + if (!enable_ept) { + vcpu->arch.cr4_guest_owned_bits &= ~X86_CR4_TLBFLUSH_BITS; + vcpu->arch.cr4_guest_owned_bits &= ~X86_CR4_PDPTR_BITS; + } if (is_guest_mode(&vmx->vcpu)) vcpu->arch.cr4_guest_owned_bits &= ~get_vmcs12(vcpu)->cr4_guest_host_mask; @@ -4692,7 +4736,7 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu, if (kvm_emulate_instruction(vcpu, 0)) { if (vcpu->arch.halt_request) { vcpu->arch.halt_request = 0; - return kvm_vcpu_halt(vcpu); + return kvm_emulate_halt_noskip(vcpu); } return 1; } @@ -5363,7 +5407,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) if (vcpu->arch.halt_request) { vcpu->arch.halt_request = 0; - return kvm_vcpu_halt(vcpu); + return kvm_emulate_halt_noskip(vcpu); } /* @@ -6615,7 +6659,7 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long cr3, cr4; + unsigned long cr4; /* Record the guest's net vcpu time for enforced NMI injections. */ if (unlikely(!enable_vnmi && @@ -6656,12 +6700,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]); if (kvm_register_is_dirty(vcpu, VCPU_REGS_RIP)) vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]); - - cr3 = __get_current_cr3_fast(); - if (unlikely(cr3 != vmx->loaded_vmcs->host_state.cr3)) { - vmcs_writel(HOST_CR3, cr3); - vmx->loaded_vmcs->host_state.cr3 = cr3; - } + vcpu->arch.regs_dirty = 0; cr4 = cr4_read_shadow(); if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) { @@ -6750,7 +6789,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) loadsegment(es, __USER_DS); #endif - vmx_register_cache_reset(vcpu); + vcpu->arch.regs_avail &= ~VMX_REGS_LAZY_LOAD_SET; pt_guest_exit(vmx); @@ -6969,7 +7008,6 @@ static int __init vmx_check_processor_compat(void) static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) { u8 cache; - u64 ipat = 0; /* We wanted to honor guest CD/MTRR/PAT, but doing so could result in * memory aliases with conflicting memory types and sometimes MCEs. @@ -6989,30 +7027,22 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) * EPT memory type is used to emulate guest CD/MTRR. */ - if (is_mmio) { - cache = MTRR_TYPE_UNCACHABLE; - goto exit; - } + if (is_mmio) + return MTRR_TYPE_UNCACHABLE << VMX_EPT_MT_EPTE_SHIFT; - if (!kvm_arch_has_noncoherent_dma(vcpu->kvm)) { - ipat = VMX_EPT_IPAT_BIT; - cache = MTRR_TYPE_WRBACK; - goto exit; - } + if (!kvm_arch_has_noncoherent_dma(vcpu->kvm)) + return (MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT) | VMX_EPT_IPAT_BIT; if (kvm_read_cr0(vcpu) & X86_CR0_CD) { - ipat = VMX_EPT_IPAT_BIT; if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED)) cache = MTRR_TYPE_WRBACK; else cache = MTRR_TYPE_UNCACHABLE; - goto exit; - } - cache = kvm_mtrr_get_guest_memory_type(vcpu, gfn); + return (cache << VMX_EPT_MT_EPTE_SHIFT) | VMX_EPT_IPAT_BIT; + } -exit: - return (cache << VMX_EPT_MT_EPTE_SHIFT) | ipat; + return kvm_mtrr_get_guest_memory_type(vcpu, gfn) << VMX_EPT_MT_EPTE_SHIFT; } static void vmcs_set_secondary_exec_control(struct vcpu_vmx *vmx, u32 new_ctl) @@ -7723,7 +7753,7 @@ static __init int hardware_setup(void) { unsigned long host_bndcfgs; struct desc_ptr dt; - int r, ept_lpage_level; + int r; store_idt(&dt); host_idt_base = dt.address; @@ -7820,16 +7850,8 @@ static __init int hardware_setup(void) kvm_mmu_set_ept_masks(enable_ept_ad_bits, cpu_has_vmx_ept_execute_only()); - if (!enable_ept) - ept_lpage_level = 0; - else if (cpu_has_vmx_ept_1g_page()) - ept_lpage_level = PG_LEVEL_1G; - else if (cpu_has_vmx_ept_2m_page()) - ept_lpage_level = PG_LEVEL_2M; - else - ept_lpage_level = PG_LEVEL_4K; kvm_configure_mmu(enable_ept, 0, vmx_get_max_tdp_level(), - ept_lpage_level); + ept_caps_to_lpage_level(vmx_capability.ept)); /* * Only enable PML when hardware supports PML feature, and both EPT diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 4df2ac24ffc1..6c2c1aff1c3d 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -159,6 +159,15 @@ struct nested_vmx { bool dirty_vmcs12; /* + * Indicates whether MSR bitmap for L2 needs to be rebuilt due to + * changes in MSR bitmap for L1 or switching to a different L2. Note, + * this flag can only be used reliably in conjunction with a paravirt L1 + * which informs L0 whether any changes to MSR bitmap for L2 were done + * on its side. + */ + bool force_msr_bitmap_recalc; + + /* * Indicates lazily loaded guest state has not yet been decached from * vmcs02. */ @@ -473,19 +482,21 @@ BUILD_CONTROLS_SHADOW(pin, PIN_BASED_VM_EXEC_CONTROL) BUILD_CONTROLS_SHADOW(exec, CPU_BASED_VM_EXEC_CONTROL) BUILD_CONTROLS_SHADOW(secondary_exec, SECONDARY_VM_EXEC_CONTROL) -static inline void vmx_register_cache_reset(struct kvm_vcpu *vcpu) -{ - vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP) - | (1 << VCPU_EXREG_RFLAGS) - | (1 << VCPU_EXREG_PDPTR) - | (1 << VCPU_EXREG_SEGMENTS) - | (1 << VCPU_EXREG_CR0) - | (1 << VCPU_EXREG_CR3) - | (1 << VCPU_EXREG_CR4) - | (1 << VCPU_EXREG_EXIT_INFO_1) - | (1 << VCPU_EXREG_EXIT_INFO_2)); - vcpu->arch.regs_dirty = 0; -} +/* + * VMX_REGS_LAZY_LOAD_SET - The set of registers that will be updated in the + * cache on demand. Other registers not listed here are synced to + * the cache immediately after VM-Exit. + */ +#define VMX_REGS_LAZY_LOAD_SET ((1 << VCPU_REGS_RIP) | \ + (1 << VCPU_REGS_RSP) | \ + (1 << VCPU_EXREG_RFLAGS) | \ + (1 << VCPU_EXREG_PDPTR) | \ + (1 << VCPU_EXREG_SEGMENTS) | \ + (1 << VCPU_EXREG_CR0) | \ + (1 << VCPU_EXREG_CR3) | \ + (1 << VCPU_EXREG_CR4) | \ + (1 << VCPU_EXREG_EXIT_INFO_1) | \ + (1 << VCPU_EXREG_EXIT_INFO_2)) static inline struct kvm_vmx *to_kvm_vmx(struct kvm *kvm) { diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index e50e97ac4408..8912f44c640d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -118,6 +118,7 @@ static void enter_smm(struct kvm_vcpu *vcpu); static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags); static void store_regs(struct kvm_vcpu *vcpu); static int sync_regs(struct kvm_vcpu *vcpu); +static int kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu); static int __set_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2); static void __get_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2); @@ -710,6 +711,17 @@ int kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err) } EXPORT_SYMBOL_GPL(kvm_complete_insn_gp); +static int complete_emulated_insn_gp(struct kvm_vcpu *vcpu, int err) +{ + if (err) { + kvm_inject_gp(vcpu, 0); + return 1; + } + + return kvm_emulate_instruction(vcpu, EMULTYPE_NO_DECODE | EMULTYPE_SKIP | + EMULTYPE_COMPLETE_USER_EXIT); +} + void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault) { ++vcpu->stat.pf_guest; @@ -798,8 +810,9 @@ static inline u64 pdptr_rsvd_bits(struct kvm_vcpu *vcpu) /* * Load the pae pdptrs. Return 1 if they are all valid, 0 otherwise. */ -int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3) +int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3) { + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; gfn_t pdpt_gfn = cr3 >> PAGE_SHIFT; gpa_t real_gpa; int i; @@ -810,8 +823,8 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3) * If the MMU is nested, CR3 holds an L2 GPA and needs to be translated * to an L1 GPA. */ - real_gpa = mmu->translate_gpa(vcpu, gfn_to_gpa(pdpt_gfn), - PFERR_USER_MASK | PFERR_WRITE_MASK, NULL); + real_gpa = kvm_translate_gpa(vcpu, mmu, gfn_to_gpa(pdpt_gfn), + PFERR_USER_MASK | PFERR_WRITE_MASK, NULL); if (real_gpa == UNMAPPED_GVA) return 0; @@ -828,8 +841,12 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3) } } - memcpy(mmu->pdptrs, pdpte, sizeof(mmu->pdptrs)); - kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR); + kvm_register_mark_available(vcpu, VCPU_EXREG_PDPTR); + if (memcmp(mmu->pdptrs, pdpte, sizeof(mmu->pdptrs))) { + memcpy(mmu->pdptrs, pdpte, sizeof(mmu->pdptrs)); + kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR); + kvm_make_request(KVM_REQ_LOAD_MMU_PGD, vcpu); + } vcpu->arch.pdptrs_from_userspace = false; return 1; @@ -856,7 +873,6 @@ EXPORT_SYMBOL_GPL(kvm_post_set_cr0); int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { unsigned long old_cr0 = kvm_read_cr0(vcpu); - unsigned long pdptr_bits = X86_CR0_CD | X86_CR0_NW | X86_CR0_PG; cr0 |= X86_CR0_ET; @@ -886,8 +902,8 @@ int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) } #endif if (!(vcpu->arch.efer & EFER_LME) && (cr0 & X86_CR0_PG) && - is_pae(vcpu) && ((cr0 ^ old_cr0) & pdptr_bits) && - !load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu))) + is_pae(vcpu) && ((cr0 ^ old_cr0) & X86_CR0_PDPTR_BITS) && + !load_pdptrs(vcpu, kvm_read_cr3(vcpu))) return 1; if (!(cr0 & X86_CR0_PG) && @@ -1051,8 +1067,6 @@ EXPORT_SYMBOL_GPL(kvm_post_set_cr4); int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { unsigned long old_cr4 = kvm_read_cr4(vcpu); - unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE | - X86_CR4_SMEP; if (!kvm_is_valid_cr4(vcpu, cr4)) return 1; @@ -1063,9 +1077,8 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) if ((cr4 ^ old_cr4) & X86_CR4_LA57) return 1; } else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE) - && ((cr4 ^ old_cr4) & pdptr_bits) - && !load_pdptrs(vcpu, vcpu->arch.walk_mmu, - kvm_read_cr3(vcpu))) + && ((cr4 ^ old_cr4) & X86_CR4_PDPTR_BITS) + && !load_pdptrs(vcpu, kvm_read_cr3(vcpu))) return 1; if ((cr4 & X86_CR4_PCIDE) && !(old_cr4 & X86_CR4_PCIDE)) { @@ -1154,14 +1167,14 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) if (kvm_vcpu_is_illegal_gpa(vcpu, cr3)) return 1; - if (is_pae_paging(vcpu) && !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)) + if (is_pae_paging(vcpu) && !load_pdptrs(vcpu, cr3)) return 1; if (cr3 != kvm_read_cr3(vcpu)) kvm_mmu_new_pgd(vcpu, cr3); vcpu->arch.cr3 = cr3; - kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); + kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3); handle_tlb_flush: /* @@ -1815,22 +1828,36 @@ int kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data) } EXPORT_SYMBOL_GPL(kvm_set_msr); -static int complete_emulated_rdmsr(struct kvm_vcpu *vcpu) +static void complete_userspace_rdmsr(struct kvm_vcpu *vcpu) { - int err = vcpu->run->msr.error; - if (!err) { + if (!vcpu->run->msr.error) { kvm_rax_write(vcpu, (u32)vcpu->run->msr.data); kvm_rdx_write(vcpu, vcpu->run->msr.data >> 32); } +} - return static_call(kvm_x86_complete_emulated_msr)(vcpu, err); +static int complete_emulated_msr_access(struct kvm_vcpu *vcpu) +{ + return complete_emulated_insn_gp(vcpu, vcpu->run->msr.error); +} + +static int complete_emulated_rdmsr(struct kvm_vcpu *vcpu) +{ + complete_userspace_rdmsr(vcpu); + return complete_emulated_msr_access(vcpu); } -static int complete_emulated_wrmsr(struct kvm_vcpu *vcpu) +static int complete_fast_msr_access(struct kvm_vcpu *vcpu) { return static_call(kvm_x86_complete_emulated_msr)(vcpu, vcpu->run->msr.error); } +static int complete_fast_rdmsr(struct kvm_vcpu *vcpu) +{ + complete_userspace_rdmsr(vcpu); + return complete_fast_msr_access(vcpu); +} + static u64 kvm_msr_reason(int r) { switch (r) { @@ -1865,18 +1892,6 @@ static int kvm_msr_user_space(struct kvm_vcpu *vcpu, u32 index, return 1; } -static int kvm_get_msr_user_space(struct kvm_vcpu *vcpu, u32 index, int r) -{ - return kvm_msr_user_space(vcpu, index, KVM_EXIT_X86_RDMSR, 0, - complete_emulated_rdmsr, r); -} - -static int kvm_set_msr_user_space(struct kvm_vcpu *vcpu, u32 index, u64 data, int r) -{ - return kvm_msr_user_space(vcpu, index, KVM_EXIT_X86_WRMSR, data, - complete_emulated_wrmsr, r); -} - int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu) { u32 ecx = kvm_rcx_read(vcpu); @@ -1885,18 +1900,16 @@ int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu) r = kvm_get_msr(vcpu, ecx, &data); - /* MSR read failed? See if we should ask user space */ - if (r && kvm_get_msr_user_space(vcpu, ecx, r)) { - /* Bounce to user space */ - return 0; - } - if (!r) { trace_kvm_msr_read(ecx, data); kvm_rax_write(vcpu, data & -1u); kvm_rdx_write(vcpu, (data >> 32) & -1u); } else { + /* MSR read failed? See if we should ask user space */ + if (kvm_msr_user_space(vcpu, ecx, KVM_EXIT_X86_RDMSR, 0, + complete_fast_rdmsr, r)) + return 0; trace_kvm_msr_read_ex(ecx); } @@ -1912,19 +1925,18 @@ int kvm_emulate_wrmsr(struct kvm_vcpu *vcpu) r = kvm_set_msr(vcpu, ecx, data); - /* MSR write failed? See if we should ask user space */ - if (r && kvm_set_msr_user_space(vcpu, ecx, data, r)) - /* Bounce to user space */ - return 0; - - /* Signal all other negative errors to userspace */ - if (r < 0) - return r; - - if (!r) + if (!r) { trace_kvm_msr_write(ecx, data); - else + } else { + /* MSR write failed? See if we should ask user space */ + if (kvm_msr_user_space(vcpu, ecx, KVM_EXIT_X86_WRMSR, data, + complete_fast_msr_access, r)) + return 0; + /* Signal all other negative errors to userspace */ + if (r < 0) + return r; trace_kvm_msr_write_ex(ecx, data); + } return static_call(kvm_x86_complete_emulated_msr)(vcpu, r); } @@ -2817,7 +2829,7 @@ static void kvm_end_pvclock_update(struct kvm *kvm) { struct kvm_arch *ka = &kvm->arch; struct kvm_vcpu *vcpu; - int i; + unsigned long i; write_seqcount_end(&ka->pvclock_sc); raw_spin_unlock_irq(&ka->tsc_write_lock); @@ -3066,7 +3078,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) static void kvmclock_update_fn(struct work_struct *work) { - int i; + unsigned long i; struct delayed_work *dwork = to_delayed_work(work); struct kvm_arch *ka = container_of(dwork, struct kvm_arch, kvmclock_update_work); @@ -5693,7 +5705,7 @@ void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot) * VM-Exit. */ struct kvm_vcpu *vcpu; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) kvm_vcpu_kick(vcpu); @@ -5962,7 +5974,8 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp) static int kvm_arch_suspend_notifier(struct kvm *kvm) { struct kvm_vcpu *vcpu; - int i, ret = 0; + unsigned long i; + int ret = 0; mutex_lock(&kvm->lock); kvm_for_each_vcpu(i, vcpu, kvm) { @@ -6505,13 +6518,14 @@ void kvm_get_segment(struct kvm_vcpu *vcpu, gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, struct x86_exception *exception) { + struct kvm_mmu *mmu = vcpu->arch.mmu; gpa_t t_gpa; BUG_ON(!mmu_is_nested(vcpu)); /* NPT walks are always user-walks */ access |= PFERR_USER_MASK; - t_gpa = vcpu->arch.mmu->gva_to_gpa(vcpu, gpa, access, exception); + t_gpa = mmu->gva_to_gpa(vcpu, mmu, gpa, access, exception); return t_gpa; } @@ -6519,25 +6533,31 @@ gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception) { + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; + u32 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; - return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); + return mmu->gva_to_gpa(vcpu, mmu, gva, access, exception); } EXPORT_SYMBOL_GPL(kvm_mmu_gva_to_gpa_read); gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception) { + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; + u32 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; access |= PFERR_FETCH_MASK; - return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); + return mmu->gva_to_gpa(vcpu, mmu, gva, access, exception); } gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception) { + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; + u32 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; access |= PFERR_WRITE_MASK; - return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); + return mmu->gva_to_gpa(vcpu, mmu, gva, access, exception); } EXPORT_SYMBOL_GPL(kvm_mmu_gva_to_gpa_write); @@ -6545,19 +6565,21 @@ EXPORT_SYMBOL_GPL(kvm_mmu_gva_to_gpa_write); gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception) { - return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, 0, exception); + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; + + return mmu->gva_to_gpa(vcpu, mmu, gva, 0, exception); } static int kvm_read_guest_virt_helper(gva_t addr, void *val, unsigned int bytes, struct kvm_vcpu *vcpu, u32 access, struct x86_exception *exception) { + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; void *data = val; int r = X86EMUL_CONTINUE; while (bytes) { - gpa_t gpa = vcpu->arch.walk_mmu->gva_to_gpa(vcpu, addr, access, - exception); + gpa_t gpa = mmu->gva_to_gpa(vcpu, mmu, addr, access, exception); unsigned offset = addr & (PAGE_SIZE-1); unsigned toread = min(bytes, (unsigned)PAGE_SIZE - offset); int ret; @@ -6585,13 +6607,14 @@ static int kvm_fetch_guest_virt(struct x86_emulate_ctxt *ctxt, struct x86_exception *exception) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; u32 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; unsigned offset; int ret; /* Inline kvm_read_guest_virt_helper for speed. */ - gpa_t gpa = vcpu->arch.walk_mmu->gva_to_gpa(vcpu, addr, access|PFERR_FETCH_MASK, - exception); + gpa_t gpa = mmu->gva_to_gpa(vcpu, mmu, addr, access|PFERR_FETCH_MASK, + exception); if (unlikely(gpa == UNMAPPED_GVA)) return X86EMUL_PROPAGATE_FAULT; @@ -6650,13 +6673,12 @@ static int kvm_write_guest_virt_helper(gva_t addr, void *val, unsigned int bytes struct kvm_vcpu *vcpu, u32 access, struct x86_exception *exception) { + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; void *data = val; int r = X86EMUL_CONTINUE; while (bytes) { - gpa_t gpa = vcpu->arch.walk_mmu->gva_to_gpa(vcpu, addr, - access, - exception); + gpa_t gpa = mmu->gva_to_gpa(vcpu, mmu, addr, access, exception); unsigned offset = addr & (PAGE_SIZE-1); unsigned towrite = min(bytes, (unsigned)PAGE_SIZE - offset); int ret; @@ -6743,6 +6765,7 @@ static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva, gpa_t *gpa, struct x86_exception *exception, bool write) { + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; u32 access = ((static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0) | (write ? PFERR_WRITE_MASK : 0); @@ -6760,7 +6783,7 @@ static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva, return 1; } - *gpa = vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); + *gpa = mmu->gva_to_gpa(vcpu, mmu, gva, access, exception); if (*gpa == UNMAPPED_GVA) return -1; @@ -7394,7 +7417,8 @@ static int emulator_get_msr(struct x86_emulate_ctxt *ctxt, r = kvm_get_msr(vcpu, msr_index, pdata); - if (r && kvm_get_msr_user_space(vcpu, msr_index, r)) { + if (r && kvm_msr_user_space(vcpu, msr_index, KVM_EXIT_X86_RDMSR, 0, + complete_emulated_rdmsr, r)) { /* Bounce to user space */ return X86EMUL_IO_NEEDED; } @@ -7410,7 +7434,8 @@ static int emulator_set_msr(struct x86_emulate_ctxt *ctxt, r = kvm_set_msr(vcpu, msr_index, data); - if (r && kvm_set_msr_user_space(vcpu, msr_index, data, r)) { + if (r && kvm_msr_user_space(vcpu, msr_index, KVM_EXIT_X86_WRMSR, data, + complete_emulated_msr_access, r)) { /* Bounce to user space */ return X86EMUL_IO_NEEDED; } @@ -8128,12 +8153,23 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, } /* - * Note, EMULTYPE_SKIP is intended for use *only* by vendor callbacks - * for kvm_skip_emulated_instruction(). The caller is responsible for - * updating interruptibility state and injecting single-step #DBs. + * EMULTYPE_SKIP without EMULTYPE_COMPLETE_USER_EXIT is intended for + * use *only* by vendor callbacks for kvm_skip_emulated_instruction(). + * The caller is responsible for updating interruptibility state and + * injecting single-step #DBs. */ if (emulation_type & EMULTYPE_SKIP) { - kvm_rip_write(vcpu, ctxt->_eip); + if (ctxt->mode != X86EMUL_MODE_PROT64) + ctxt->eip = (u32)ctxt->_eip; + else + ctxt->eip = ctxt->_eip; + + if (emulation_type & EMULTYPE_COMPLETE_USER_EXIT) { + r = 1; + goto writeback; + } + + kvm_rip_write(vcpu, ctxt->eip); if (ctxt->eflags & X86_EFLAGS_RF) kvm_set_rflags(vcpu, ctxt->eflags & ~X86_EFLAGS_RF); return 1; @@ -8197,11 +8233,15 @@ restart: writeback = false; r = 0; vcpu->arch.complete_userspace_io = complete_emulated_mmio; + } else if (vcpu->arch.complete_userspace_io) { + writeback = false; + r = 0; } else if (r == EMULATION_RESTART) goto restart; else r = 1; +writeback: if (writeback) { unsigned long rflags = static_call(kvm_x86_get_rflags)(vcpu); toggle_interruptibility(vcpu, ctxt->interruptibility); @@ -8394,7 +8434,8 @@ static void __kvmclock_cpufreq_notifier(struct cpufreq_freqs *freq, int cpu) { struct kvm *kvm; struct kvm_vcpu *vcpu; - int i, send_ipi = 0; + int send_ipi = 0; + unsigned long i; /* * We allow guests to temporarily run on slowing clocks, @@ -8567,9 +8608,8 @@ static struct perf_guest_info_callbacks kvm_guest_cbs = { static void pvclock_gtod_update_fn(struct work_struct *work) { struct kvm *kvm; - struct kvm_vcpu *vcpu; - int i; + unsigned long i; mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) @@ -8730,8 +8770,15 @@ void kvm_arch_exit(void) #endif } -static int __kvm_vcpu_halt(struct kvm_vcpu *vcpu, int state, int reason) +static int __kvm_emulate_halt(struct kvm_vcpu *vcpu, int state, int reason) { + /* + * The vCPU has halted, e.g. executed HLT. Update the run state if the + * local APIC is in-kernel, the run loop will detect the non-runnable + * state and halt the vCPU. Exit to userspace if the local APIC is + * managed by userspace, in which case userspace is responsible for + * handling wake events. + */ ++vcpu->stat.halt_exits; if (lapic_in_kernel(vcpu)) { vcpu->arch.mp_state = state; @@ -8742,11 +8789,11 @@ static int __kvm_vcpu_halt(struct kvm_vcpu *vcpu, int state, int reason) } } -int kvm_vcpu_halt(struct kvm_vcpu *vcpu) +int kvm_emulate_halt_noskip(struct kvm_vcpu *vcpu) { - return __kvm_vcpu_halt(vcpu, KVM_MP_STATE_HALTED, KVM_EXIT_HLT); + return __kvm_emulate_halt(vcpu, KVM_MP_STATE_HALTED, KVM_EXIT_HLT); } -EXPORT_SYMBOL_GPL(kvm_vcpu_halt); +EXPORT_SYMBOL_GPL(kvm_emulate_halt_noskip); int kvm_emulate_halt(struct kvm_vcpu *vcpu) { @@ -8755,7 +8802,7 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu) * TODO: we might be squashing a GUESTDBG_SINGLESTEP-triggered * KVM_EXIT_DEBUG here. */ - return kvm_vcpu_halt(vcpu) && ret; + return kvm_emulate_halt_noskip(vcpu) && ret; } EXPORT_SYMBOL_GPL(kvm_emulate_halt); @@ -8763,7 +8810,8 @@ int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu) { int ret = kvm_skip_emulated_instruction(vcpu); - return __kvm_vcpu_halt(vcpu, KVM_MP_STATE_AP_RESET_HOLD, KVM_EXIT_AP_RESET_HOLD) && ret; + return __kvm_emulate_halt(vcpu, KVM_MP_STATE_AP_RESET_HOLD, + KVM_EXIT_AP_RESET_HOLD) && ret; } EXPORT_SYMBOL_GPL(kvm_emulate_ap_reset_hold); @@ -9996,7 +10044,10 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) if (!kvm_arch_vcpu_runnable(vcpu) && (!kvm_x86_ops.pre_block || static_call(kvm_x86_pre_block)(vcpu) == 0)) { srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); - kvm_vcpu_block(vcpu); + if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED) + kvm_vcpu_halt(vcpu); + else + kvm_vcpu_block(vcpu); vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); if (kvm_x86_ops.post_block) @@ -10556,7 +10607,7 @@ static int __set_sregs_common(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs, vcpu->arch.cr2 = sregs->cr2; *mmu_reset_needed |= kvm_read_cr3(vcpu) != sregs->cr3; vcpu->arch.cr3 = sregs->cr3; - kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); + kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3); kvm_set_cr8(vcpu, sregs->cr8); @@ -10573,7 +10624,7 @@ static int __set_sregs_common(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs, if (update_pdptrs) { idx = srcu_read_lock(&vcpu->kvm->srcu); if (is_pae_paging(vcpu)) { - load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu)); + load_pdptrs(vcpu, kvm_read_cr3(vcpu)); *mmu_reset_needed = 1; } srcu_read_unlock(&vcpu->kvm->srcu, idx); @@ -10671,7 +10722,7 @@ static void kvm_arch_vcpu_guestdbg_update_apicv_inhibit(struct kvm *kvm) { bool inhibit = false; struct kvm_vcpu *vcpu; - int i; + unsigned long i; down_write(&kvm->arch.apicv_update_lock); @@ -11159,7 +11210,7 @@ int kvm_arch_hardware_enable(void) { struct kvm *kvm; struct kvm_vcpu *vcpu; - int i; + unsigned long i; int ret; u64 local_tsc; u64 max_tsc = 0; @@ -11412,7 +11463,7 @@ static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu) static void kvm_free_vcpus(struct kvm *kvm) { - unsigned int i; + unsigned long i; struct kvm_vcpu *vcpu; /* @@ -11422,15 +11473,8 @@ static void kvm_free_vcpus(struct kvm *kvm) kvm_clear_async_pf_completion_queue(vcpu); kvm_unload_vcpu_mmu(vcpu); } - kvm_for_each_vcpu(i, vcpu, kvm) - kvm_vcpu_destroy(vcpu); - mutex_lock(&kvm->lock); - for (i = 0; i < atomic_read(&kvm->online_vcpus); i++) - kvm->vcpus[i] = NULL; - - atomic_set(&kvm->online_vcpus, 0); - mutex_unlock(&kvm->lock); + kvm_destroy_vcpus(kvm); } void kvm_arch_sync_events(struct kvm *kvm) @@ -11598,9 +11642,9 @@ int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages) } static int kvm_alloc_memslot_metadata(struct kvm *kvm, - struct kvm_memory_slot *slot, - unsigned long npages) + struct kvm_memory_slot *slot) { + unsigned long npages = slot->npages; int i, r; /* @@ -11665,7 +11709,7 @@ out_free: void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) { struct kvm_vcpu *vcpu; - int i; + unsigned long i; /* * memslots->generation has been incremented. @@ -11679,13 +11723,18 @@ void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) } int kvm_arch_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, - enum kvm_mr_change change) + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, + enum kvm_mr_change change) { if (change == KVM_MR_CREATE || change == KVM_MR_MOVE) - return kvm_alloc_memslot_metadata(kvm, memslot, - mem->memory_size >> PAGE_SHIFT); + return kvm_alloc_memslot_metadata(kvm, new); + + if (change == KVM_MR_FLAGS_ONLY) + memcpy(&new->arch, &old->arch, sizeof(old->arch)); + else if (WARN_ON_ONCE(change != KVM_MR_DELETE)) + return -EIO; + return 0; } @@ -11709,13 +11758,15 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, const struct kvm_memory_slot *new, enum kvm_mr_change change) { - bool log_dirty_pages = new->flags & KVM_MEM_LOG_DIRTY_PAGES; + u32 old_flags = old ? old->flags : 0; + u32 new_flags = new ? new->flags : 0; + bool log_dirty_pages = new_flags & KVM_MEM_LOG_DIRTY_PAGES; /* * Update CPU dirty logging if dirty logging is being toggled. This * applies to all operations. */ - if ((old->flags ^ new->flags) & KVM_MEM_LOG_DIRTY_PAGES) + if ((old_flags ^ new_flags) & KVM_MEM_LOG_DIRTY_PAGES) kvm_mmu_update_cpu_dirty_logging(kvm, log_dirty_pages); /* @@ -11733,7 +11784,7 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, * MOVE/DELETE: The old mappings will already have been cleaned up by * kvm_arch_flush_shadow_memslot(). */ - if ((change != KVM_MR_FLAGS_ONLY) || (new->flags & KVM_MEM_READONLY)) + if ((change != KVM_MR_FLAGS_ONLY) || (new_flags & KVM_MEM_READONLY)) return; /* @@ -11741,7 +11792,7 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, * other flag is LOG_DIRTY_PAGES, i.e. something is wrong if dirty * logging isn't being toggled on or off. */ - if (WARN_ON_ONCE(!((old->flags ^ new->flags) & KVM_MEM_LOG_DIRTY_PAGES))) + if (WARN_ON_ONCE(!((old_flags ^ new_flags) & KVM_MEM_LOG_DIRTY_PAGES))) return; if (!log_dirty_pages) { @@ -11777,14 +11828,18 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, } void kvm_arch_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { - if (!kvm->arch.n_requested_mmu_pages) - kvm_mmu_change_mmu_pages(kvm, - kvm_mmu_calculate_default_mmu_pages(kvm)); + if (!kvm->arch.n_requested_mmu_pages && + (change == KVM_MR_CREATE || change == KVM_MR_DELETE)) { + unsigned long nr_mmu_pages; + + nr_mmu_pages = kvm->nr_memslot_pages / KVM_MEMSLOT_PAGES_TO_MMU_PAGES_RATIO; + nr_mmu_pages = max(nr_mmu_pages, KVM_MIN_ALLOC_MMU_PAGES); + kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages); + } kvm_mmu_slot_apply_flags(kvm, old, new, change); @@ -12294,12 +12349,13 @@ EXPORT_SYMBOL_GPL(kvm_spec_ctrl_test_value); void kvm_fixup_and_inject_pf_error(struct kvm_vcpu *vcpu, gva_t gva, u16 error_code) { + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; struct x86_exception fault; u32 access = error_code & (PFERR_WRITE_MASK | PFERR_FETCH_MASK | PFERR_USER_MASK); if (!(error_code & PFERR_PRESENT_MASK) || - vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, &fault) != UNMAPPED_GVA) { + mmu->gva_to_gpa(vcpu, mmu, gva, access, &fault) != UNMAPPED_GVA) { /* * If vcpu->arch.walk_mmu->gva_to_gpa succeeded, the page * tables probably do not match the TLB. Just proceed @@ -12636,6 +12692,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_unaccelerated_access); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_incomplete_ipi); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_ga_log); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_apicv_update_request); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_apicv_accept_irq); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_enter); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_exit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_enter); diff --git a/include/linux/kvm_dirty_ring.h b/include/linux/kvm_dirty_ring.h index 120e5e90fa1d..4da8d4a4140b 100644 --- a/include/linux/kvm_dirty_ring.h +++ b/include/linux/kvm_dirty_ring.h @@ -27,9 +27,9 @@ struct kvm_dirty_ring { int index; }; -#if (KVM_DIRTY_LOG_PAGE_OFFSET == 0) +#ifndef CONFIG_HAVE_KVM_DIRTY_RING /* - * If KVM_DIRTY_LOG_PAGE_OFFSET not defined, kvm_dirty_ring.o should + * If CONFIG_HAVE_HVM_DIRTY_RING not defined, kvm_dirty_ring.o should * not be included as well, so define these nop functions for the arch. */ static inline u32 kvm_dirty_ring_get_rsvd_entries(void) @@ -74,7 +74,7 @@ static inline bool kvm_dirty_ring_soft_full(struct kvm_dirty_ring *ring) return true; } -#else /* KVM_DIRTY_LOG_PAGE_OFFSET == 0 */ +#else /* CONFIG_HAVE_KVM_DIRTY_RING */ u32 kvm_dirty_ring_get_rsvd_entries(void); int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring, int index, u32 size); @@ -98,6 +98,6 @@ struct page *kvm_dirty_ring_get_page(struct kvm_dirty_ring *ring, u32 offset); void kvm_dirty_ring_free(struct kvm_dirty_ring *ring); bool kvm_dirty_ring_soft_full(struct kvm_dirty_ring *ring); -#endif /* KVM_DIRTY_LOG_PAGE_OFFSET == 0 */ +#endif /* CONFIG_HAVE_KVM_DIRTY_RING */ #endif /* KVM_DIRTY_RING_H */ diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index c310648cc8f1..f8ed799e8674 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -29,6 +29,10 @@ #include <linux/refcount.h> #include <linux/nospec.h> #include <linux/notifier.h> +#include <linux/hashtable.h> +#include <linux/interval_tree.h> +#include <linux/rbtree.h> +#include <linux/xarray.h> #include <asm/signal.h> #include <linux/kvm.h> @@ -310,7 +314,9 @@ struct kvm_vcpu { struct mutex mutex; struct kvm_run *run; +#ifndef __KVM_HAVE_ARCH_WQP struct rcuwait wait; +#endif struct pid __rcu *pid; int sigset_active; sigset_t sigset; @@ -355,11 +361,13 @@ struct kvm_vcpu { struct kvm_dirty_ring dirty_ring; /* - * The index of the most recently used memslot by this vCPU. It's ok - * if this becomes stale due to memslot changes since we always check - * it is a valid slot. + * The most recently used memslot by this vCPU and the slots generation + * for which it is valid. + * No wraparound protection is needed since generations won't overflow in + * thousands of years, even assuming 1M memslot operations per second. */ - int last_used_slot; + struct kvm_memory_slot *last_used_slot; + u64 last_used_slot_gen; }; /* must be called with irqs disabled */ @@ -424,7 +432,26 @@ static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu) */ #define KVM_MEM_MAX_NR_PAGES ((1UL << 31) - 1) +/* + * Since at idle each memslot belongs to two memslot sets it has to contain + * two embedded nodes for each data structure that it forms a part of. + * + * Two memslot sets (one active and one inactive) are necessary so the VM + * continues to run on one memslot set while the other is being modified. + * + * These two memslot sets normally point to the same set of memslots. + * They can, however, be desynchronized when performing a memslot management + * operation by replacing the memslot to be modified by its copy. + * After the operation is complete, both memslot sets once again point to + * the same, common set of memslot data. + * + * The memslots themselves are independent of each other so they can be + * individually added or deleted. + */ struct kvm_memory_slot { + struct hlist_node id_node[2]; + struct interval_tree_node hva_node[2]; + struct rb_node gfn_node[2]; gfn_t base_gfn; unsigned long npages; unsigned long *dirty_bitmap; @@ -435,7 +462,7 @@ struct kvm_memory_slot { u16 as_id; }; -static inline bool kvm_slot_dirty_track_enabled(struct kvm_memory_slot *slot) +static inline bool kvm_slot_dirty_track_enabled(const struct kvm_memory_slot *slot) { return slot->flags & KVM_MEM_LOG_DIRTY_PAGES; } @@ -519,18 +546,21 @@ static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu) } #endif -/* - * Note: - * memslots are not sorted by id anymore, please use id_to_memslot() - * to get the memslot by its id. - */ struct kvm_memslots { u64 generation; - /* The mapping table from slot id to the index in memslots[]. */ - short id_to_index[KVM_MEM_SLOTS_NUM]; - atomic_t last_used_slot; - int used_slots; - struct kvm_memory_slot memslots[]; + atomic_long_t last_used_slot; + struct rb_root_cached hva_tree; + struct rb_root gfn_tree; + /* + * The mapping table from slot id to memslot. + * + * 7-bit bucket count matches the size of the old id to index array for + * 512 slots, while giving good performance with this slot count. + * Higher bucket counts bring only small performance improvements but + * always result in higher memory usage (even for lower memslot counts). + */ + DECLARE_HASHTABLE(id_hash, 7); + int node_idx; }; struct kvm { @@ -551,8 +581,12 @@ struct kvm { */ struct mutex slots_arch_lock; struct mm_struct *mm; /* userspace tied to this vm */ + unsigned long nr_memslot_pages; + /* The two memslot sets - active and inactive (per address space) */ + struct kvm_memslots __memslots[KVM_ADDRESS_SPACE_NUM][2]; + /* The current active memslot set for each address space */ struct kvm_memslots __rcu *memslots[KVM_ADDRESS_SPACE_NUM]; - struct kvm_vcpu *vcpus[KVM_MAX_VCPUS]; + struct xarray vcpu_array; /* Used to wait for completion of MMU notifiers. */ spinlock_t mn_invalidate_lock; @@ -701,19 +735,17 @@ static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i) /* Pairs with smp_wmb() in kvm_vm_ioctl_create_vcpu. */ smp_rmb(); - return kvm->vcpus[i]; + return xa_load(&kvm->vcpu_array, i); } -#define kvm_for_each_vcpu(idx, vcpup, kvm) \ - for (idx = 0; \ - idx < atomic_read(&kvm->online_vcpus) && \ - (vcpup = kvm_get_vcpu(kvm, idx)) != NULL; \ - idx++) +#define kvm_for_each_vcpu(idx, vcpup, kvm) \ + xa_for_each_range(&kvm->vcpu_array, idx, vcpup, 0, \ + (atomic_read(&kvm->online_vcpus) - 1)) static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id) { struct kvm_vcpu *vcpu = NULL; - int i; + unsigned long i; if (id < 0) return NULL; @@ -727,13 +759,12 @@ static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id) return NULL; } -#define kvm_for_each_memslot(memslot, slots) \ - for (memslot = &slots->memslots[0]; \ - memslot < slots->memslots + slots->used_slots; memslot++) \ - if (WARN_ON_ONCE(!memslot->npages)) { \ - } else +static inline int kvm_vcpu_get_idx(struct kvm_vcpu *vcpu) +{ + return vcpu->vcpu_idx; +} -void kvm_vcpu_destroy(struct kvm_vcpu *vcpu); +void kvm_destroy_vcpus(struct kvm *kvm); void vcpu_load(struct kvm_vcpu *vcpu); void vcpu_put(struct kvm_vcpu *vcpu); @@ -793,21 +824,124 @@ static inline struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu) return __kvm_memslots(vcpu->kvm, as_id); } +static inline bool kvm_memslots_empty(struct kvm_memslots *slots) +{ + return RB_EMPTY_ROOT(&slots->gfn_tree); +} + +#define kvm_for_each_memslot(memslot, bkt, slots) \ + hash_for_each(slots->id_hash, bkt, memslot, id_node[slots->node_idx]) \ + if (WARN_ON_ONCE(!memslot->npages)) { \ + } else + static inline struct kvm_memory_slot *id_to_memslot(struct kvm_memslots *slots, int id) { - int index = slots->id_to_index[id]; struct kvm_memory_slot *slot; + int idx = slots->node_idx; - if (index < 0) - return NULL; + hash_for_each_possible(slots->id_hash, slot, id_node[idx], id) { + if (slot->id == id) + return slot; + } + + return NULL; +} + +/* Iterator used for walking memslots that overlap a gfn range. */ +struct kvm_memslot_iter { + struct kvm_memslots *slots; + struct rb_node *node; + struct kvm_memory_slot *slot; +}; - slot = &slots->memslots[index]; +static inline void kvm_memslot_iter_next(struct kvm_memslot_iter *iter) +{ + iter->node = rb_next(iter->node); + if (!iter->node) + return; - WARN_ON(slot->id != id); - return slot; + iter->slot = container_of(iter->node, struct kvm_memory_slot, gfn_node[iter->slots->node_idx]); } +static inline void kvm_memslot_iter_start(struct kvm_memslot_iter *iter, + struct kvm_memslots *slots, + gfn_t start) +{ + int idx = slots->node_idx; + struct rb_node *tmp; + struct kvm_memory_slot *slot; + + iter->slots = slots; + + /* + * Find the so called "upper bound" of a key - the first node that has + * its key strictly greater than the searched one (the start gfn in our case). + */ + iter->node = NULL; + for (tmp = slots->gfn_tree.rb_node; tmp; ) { + slot = container_of(tmp, struct kvm_memory_slot, gfn_node[idx]); + if (start < slot->base_gfn) { + iter->node = tmp; + tmp = tmp->rb_left; + } else { + tmp = tmp->rb_right; + } + } + + /* + * Find the slot with the lowest gfn that can possibly intersect with + * the range, so we'll ideally have slot start <= range start + */ + if (iter->node) { + /* + * A NULL previous node means that the very first slot + * already has a higher start gfn. + * In this case slot start > range start. + */ + tmp = rb_prev(iter->node); + if (tmp) + iter->node = tmp; + } else { + /* a NULL node below means no slots */ + iter->node = rb_last(&slots->gfn_tree); + } + + if (iter->node) { + iter->slot = container_of(iter->node, struct kvm_memory_slot, gfn_node[idx]); + + /* + * It is possible in the slot start < range start case that the + * found slot ends before or at range start (slot end <= range start) + * and so it does not overlap the requested range. + * + * In such non-overlapping case the next slot (if it exists) will + * already have slot start > range start, otherwise the logic above + * would have found it instead of the current slot. + */ + if (iter->slot->base_gfn + iter->slot->npages <= start) + kvm_memslot_iter_next(iter); + } +} + +static inline bool kvm_memslot_iter_is_valid(struct kvm_memslot_iter *iter, gfn_t end) +{ + if (!iter->node) + return false; + + /* + * If this slot starts beyond or at the end of the range so does + * every next one + */ + return iter->slot->base_gfn < end; +} + +/* Iterate over each memslot at least partially intersecting [start, end) range */ +#define kvm_for_each_memslot_in_gfn_range(iter, slots, start, end) \ + for (kvm_memslot_iter_start(iter, slots, start); \ + kvm_memslot_iter_is_valid(iter, end); \ + kvm_memslot_iter_next(iter)) + /* * KVM_SET_USER_MEMORY_REGION ioctl allows the following operations: * - create a new memory slot @@ -833,11 +967,10 @@ int __kvm_set_memory_region(struct kvm *kvm, void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot); void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen); int kvm_arch_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, enum kvm_mr_change change); void kvm_arch_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change); @@ -863,9 +996,9 @@ void kvm_set_page_accessed(struct page *page); kvm_pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn); kvm_pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault, bool *writable); -kvm_pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn); -kvm_pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn); -kvm_pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, +kvm_pfn_t gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn); +kvm_pfn_t gfn_to_pfn_memslot_atomic(const struct kvm_memory_slot *slot, gfn_t gfn); +kvm_pfn_t __gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn, bool atomic, bool *async, bool write_fault, bool *writable, hva_t *hva); @@ -942,7 +1075,7 @@ struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn); bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn); bool kvm_vcpu_is_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn); unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn); -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); void mark_page_dirty(struct kvm *kvm, gfn_t gfn); struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu); @@ -969,7 +1102,8 @@ void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn); void kvm_sigset_activate(struct kvm_vcpu *vcpu); void kvm_sigset_deactivate(struct kvm_vcpu *vcpu); -void kvm_vcpu_block(struct kvm_vcpu *vcpu); +void kvm_vcpu_halt(struct kvm_vcpu *vcpu); +bool kvm_vcpu_block(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu); bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu); @@ -1152,6 +1286,20 @@ static inline struct rcuwait *kvm_arch_vcpu_get_wait(struct kvm_vcpu *vcpu) #endif } +/* + * Wake a vCPU if necessary, but don't do any stats/metadata updates. Returns + * true if the vCPU was blocking and was awakened, false otherwise. + */ +static inline bool __kvm_vcpu_wake_up(struct kvm_vcpu *vcpu) +{ + return !!rcuwait_wake_up(kvm_arch_vcpu_get_wait(vcpu)); +} + +static inline bool kvm_vcpu_is_blocking(struct kvm_vcpu *vcpu) +{ + return rcuwait_active(kvm_arch_vcpu_get_wait(vcpu)); +} + #ifdef __KVM_HAVE_ARCH_INTC_INITIALIZED /* * returns true if the virtual interrupt controller is initialized and @@ -1205,25 +1353,15 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id); bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args); /* - * Returns a pointer to the memslot at slot_index if it contains gfn. + * Returns a pointer to the memslot if it contains gfn. * Otherwise returns NULL. */ static inline struct kvm_memory_slot * -try_get_memslot(struct kvm_memslots *slots, int slot_index, gfn_t gfn) +try_get_memslot(struct kvm_memory_slot *slot, gfn_t gfn) { - struct kvm_memory_slot *slot; - - if (slot_index < 0 || slot_index >= slots->used_slots) + if (!slot) return NULL; - /* - * slot_index can come from vcpu->last_used_slot which is not kept - * in sync with userspace-controllable memslot deletion. So use nospec - * to prevent the CPU from speculating past the end of memslots[]. - */ - slot_index = array_index_nospec(slot_index, slots->used_slots); - slot = &slots->memslots[slot_index]; - if (gfn >= slot->base_gfn && gfn < slot->base_gfn + slot->npages) return slot; else @@ -1231,63 +1369,63 @@ try_get_memslot(struct kvm_memslots *slots, int slot_index, gfn_t gfn) } /* - * Returns a pointer to the memslot that contains gfn and records the index of - * the slot in index. Otherwise returns NULL. + * Returns a pointer to the memslot that contains gfn. Otherwise returns NULL. * - * IMPORTANT: Slots are sorted from highest GFN to lowest GFN! + * With "approx" set returns the memslot also when the address falls + * in a hole. In that case one of the memslots bordering the hole is + * returned. */ static inline struct kvm_memory_slot * -search_memslots(struct kvm_memslots *slots, gfn_t gfn, int *index) +search_memslots(struct kvm_memslots *slots, gfn_t gfn, bool approx) { - int start = 0, end = slots->used_slots; - struct kvm_memory_slot *memslots = slots->memslots; struct kvm_memory_slot *slot; - - if (unlikely(!slots->used_slots)) - return NULL; - - while (start < end) { - int slot = start + (end - start) / 2; - - if (gfn >= memslots[slot].base_gfn) - end = slot; - else - start = slot + 1; - } - - slot = try_get_memslot(slots, start, gfn); - if (slot) { - *index = start; - return slot; + struct rb_node *node; + int idx = slots->node_idx; + + slot = NULL; + for (node = slots->gfn_tree.rb_node; node; ) { + slot = container_of(node, struct kvm_memory_slot, gfn_node[idx]); + if (gfn >= slot->base_gfn) { + if (gfn < slot->base_gfn + slot->npages) + return slot; + node = node->rb_right; + } else + node = node->rb_left; } - return NULL; + return approx ? slot : NULL; } -/* - * __gfn_to_memslot() and its descendants are here because it is called from - * non-modular code in arch/powerpc/kvm/book3s_64_vio{,_hv}.c. gfn_to_memslot() - * itself isn't here as an inline because that would bloat other code too much. - */ static inline struct kvm_memory_slot * -__gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn) +____gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn, bool approx) { struct kvm_memory_slot *slot; - int slot_index = atomic_read(&slots->last_used_slot); - slot = try_get_memslot(slots, slot_index, gfn); + slot = (struct kvm_memory_slot *)atomic_long_read(&slots->last_used_slot); + slot = try_get_memslot(slot, gfn); if (slot) return slot; - slot = search_memslots(slots, gfn, &slot_index); + slot = search_memslots(slots, gfn, approx); if (slot) { - atomic_set(&slots->last_used_slot, slot_index); + atomic_long_set(&slots->last_used_slot, (unsigned long)slot); return slot; } return NULL; } +/* + * __gfn_to_memslot() and its descendants are here to allow arch code to inline + * the lookups in hot paths. gfn_to_memslot() itself isn't here as an inline + * because that would bloat other code too much. + */ +static inline struct kvm_memory_slot * +__gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn) +{ + return ____gfn_to_memslot(slots, gfn, false); +} + static inline unsigned long __gfn_to_hva_memslot(const struct kvm_memory_slot *slot, gfn_t gfn) { @@ -1463,7 +1601,8 @@ struct _kvm_stats_desc { STATS_DESC_LOGHIST_TIME_NSEC(VCPU_GENERIC, halt_poll_fail_hist, \ HALT_POLL_HIST_COUNT), \ STATS_DESC_LOGHIST_TIME_NSEC(VCPU_GENERIC, halt_wait_hist, \ - HALT_POLL_HIST_COUNT) + HALT_POLL_HIST_COUNT), \ + STATS_DESC_ICOUNTER(VCPU_GENERIC, blocking) extern struct dentry *kvm_debugfs_dir; diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index 234eab059839..888ef12862c9 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -87,6 +87,7 @@ struct kvm_vcpu_stat_generic { u64 halt_poll_success_hist[HALT_POLL_HIST_COUNT]; u64 halt_poll_fail_hist[HALT_POLL_HIST_COUNT]; u64 halt_wait_hist[HALT_POLL_HIST_COUNT]; + u64 blocking; }; #define KVM_STATS_NAME_SIZE 48 diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig index 62b39149b8c8..97cf5413ac25 100644 --- a/virt/kvm/Kconfig +++ b/virt/kvm/Kconfig @@ -13,6 +13,9 @@ config HAVE_KVM_IRQFD config HAVE_KVM_IRQ_ROUTING bool +config HAVE_KVM_DIRTY_RING + bool + config HAVE_KVM_EVENTFD bool select EVENTFD diff --git a/virt/kvm/Makefile.kvm b/virt/kvm/Makefile.kvm new file mode 100644 index 000000000000..ffdcad3cc97a --- /dev/null +++ b/virt/kvm/Makefile.kvm @@ -0,0 +1,13 @@ +# 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 diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c index dd777688d14a..9bfe1d6f6529 100644 --- a/virt/kvm/async_pf.c +++ b/virt/kvm/async_pf.c @@ -85,7 +85,7 @@ static void async_pf_execute(struct work_struct *work) trace_kvm_async_pf_completed(addr, cr2_or_gpa); - rcuwait_wake_up(&vcpu->wait); + __kvm_vcpu_wake_up(vcpu); mmput(mm); kvm_put_kvm(vcpu->kvm); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 72c4e6b39389..b0f7e6eb00ff 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -305,8 +305,9 @@ bool kvm_make_all_cpus_request_except(struct kvm *kvm, unsigned int req, { struct kvm_vcpu *vcpu; struct cpumask *cpus; + unsigned long i; bool called; - int i, me; + int me; me = get_cpu(); @@ -421,7 +422,9 @@ static void kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id) vcpu->kvm = kvm; vcpu->vcpu_id = id; vcpu->pid = NULL; +#ifndef __KVM_HAVE_ARCH_WQP rcuwait_init(&vcpu->wait); +#endif kvm_async_pf_vcpu_init(vcpu); vcpu->pre_pcpu = -1; @@ -432,10 +435,10 @@ static void kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id) vcpu->preempted = false; vcpu->ready = false; preempt_notifier_init(&vcpu->preempt_notifier, &kvm_preempt_ops); - vcpu->last_used_slot = 0; + vcpu->last_used_slot = NULL; } -void kvm_vcpu_destroy(struct kvm_vcpu *vcpu) +static void kvm_vcpu_destroy(struct kvm_vcpu *vcpu) { kvm_dirty_ring_free(&vcpu->dirty_ring); kvm_arch_vcpu_destroy(vcpu); @@ -450,7 +453,20 @@ void kvm_vcpu_destroy(struct kvm_vcpu *vcpu) free_page((unsigned long)vcpu->run); kmem_cache_free(kvm_vcpu_cache, vcpu); } -EXPORT_SYMBOL_GPL(kvm_vcpu_destroy); + +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); + } + + atomic_set(&kvm->online_vcpus, 0); +} +EXPORT_SYMBOL_GPL(kvm_destroy_vcpus); #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) static inline struct kvm *mmu_notifier_to_kvm(struct mmu_notifier *mn) @@ -498,6 +514,12 @@ 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 int __kvm_handle_hva_range(struct kvm *kvm, const struct kvm_hva_range *range) { @@ -507,6 +529,9 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm, struct kvm_memslots *slots; int i, idx; + if (WARN_ON_ONCE(range->end <= range->start)) + return 0; + /* 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))) @@ -515,15 +540,17 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm, idx = srcu_read_lock(&kvm->srcu); for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + struct interval_tree_node *node; + slots = __kvm_memslots(kvm, i); - kvm_for_each_memslot(slot, slots) { + 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(range->start, slot->userspace_addr); hva_end = min(range->end, slot->userspace_addr + (slot->npages << PAGE_SHIFT)); - if (hva_start >= hva_end) - continue; /* * To optimize for the likely case where the address @@ -851,21 +878,6 @@ static void kvm_destroy_pm_notifier(struct kvm *kvm) } #endif /* CONFIG_HAVE_KVM_PM_NOTIFIER */ -static struct kvm_memslots *kvm_alloc_memslots(void) -{ - int i; - struct kvm_memslots *slots; - - slots = kvzalloc(sizeof(struct kvm_memslots), GFP_KERNEL_ACCOUNT); - if (!slots) - return NULL; - - for (i = 0; i < KVM_MEM_SLOTS_NUM; i++) - slots->id_to_index[i] = -1; - - return slots; -} - static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot) { if (!memslot->dirty_bitmap) @@ -875,27 +887,33 @@ static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot) memslot->dirty_bitmap = NULL; } +/* 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) { kvm_destroy_dirty_bitmap(slot); kvm_arch_free_memslot(kvm, slot); - slot->flags = 0; - slot->npages = 0; + kfree(slot); } static void kvm_free_memslots(struct kvm *kvm, struct kvm_memslots *slots) { + struct hlist_node *idnode; struct kvm_memory_slot *memslot; + int bkt; - if (!slots) + /* + * 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; - kvm_for_each_memslot(memslot, slots) + hash_for_each_safe(slots->id_hash, bkt, idnode, memslot, id_node[1]) kvm_free_memslot(kvm, memslot); - - kvfree(slots); } static umode_t kvm_stats_debugfs_mode(const struct _kvm_stats_desc *pdesc) @@ -1034,8 +1052,9 @@ int __weak kvm_arch_create_vm_debugfs(struct kvm *kvm) static struct kvm *kvm_create_vm(unsigned long type) { struct kvm *kvm = kvm_arch_alloc_vm(); + struct kvm_memslots *slots; int r = -ENOMEM; - int i; + int i, j; if (!kvm) return ERR_PTR(-ENOMEM); @@ -1050,6 +1069,7 @@ static struct kvm *kvm_create_vm(unsigned long type) 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); INIT_LIST_HEAD(&kvm->devices); @@ -1062,13 +1082,20 @@ static struct kvm *kvm_create_vm(unsigned long type) refcount_set(&kvm->users_count, 1); for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { - struct kvm_memslots *slots = kvm_alloc_memslots(); + for (j = 0; j < 2; j++) { + slots = &kvm->__memslots[i][j]; - if (!slots) - goto out_err_no_arch_destroy_vm; - /* Generations must be different for each address space. */ - slots->generation = i; - rcu_assign_pointer(kvm->memslots[i], slots); + 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]); } for (i = 0; i < KVM_NR_BUSES; i++) { @@ -1122,8 +1149,6 @@ 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(kvm, i)); - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) - kvm_free_memslots(kvm, __kvm_memslots(kvm, i)); cleanup_srcu_struct(&kvm->irq_srcu); out_err_no_irq_srcu: cleanup_srcu_struct(&kvm->srcu); @@ -1188,8 +1213,10 @@ static void kvm_destroy_vm(struct kvm *kvm) #endif kvm_arch_destroy_vm(kvm); kvm_destroy_devices(kvm); - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) - kvm_free_memslots(kvm, __kvm_memslots(kvm, i)); + for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + kvm_free_memslots(kvm, &kvm->__memslots[i][0]); + kvm_free_memslots(kvm, &kvm->__memslots[i][1]); + } cleanup_srcu_struct(&kvm->irq_srcu); cleanup_srcu_struct(&kvm->srcu); kvm_arch_free_vm(kvm); @@ -1259,165 +1286,136 @@ static int kvm_alloc_dirty_bitmap(struct kvm_memory_slot *memslot) return 0; } -/* - * Delete a memslot by decrementing the number of used slots and shifting all - * other entries in the array forward one spot. - */ -static inline void kvm_memslot_delete(struct kvm_memslots *slots, - struct kvm_memory_slot *memslot) +static struct kvm_memslots *kvm_get_inactive_memslots(struct kvm *kvm, int as_id) { - struct kvm_memory_slot *mslots = slots->memslots; - int i; - - if (WARN_ON(slots->id_to_index[memslot->id] == -1)) - return; - - slots->used_slots--; + struct kvm_memslots *active = __kvm_memslots(kvm, as_id); + int node_idx_inactive = active->node_idx ^ 1; - if (atomic_read(&slots->last_used_slot) >= slots->used_slots) - atomic_set(&slots->last_used_slot, 0); - - for (i = slots->id_to_index[memslot->id]; i < slots->used_slots; i++) { - mslots[i] = mslots[i + 1]; - slots->id_to_index[mslots[i].id] = i; - } - mslots[i] = *memslot; - slots->id_to_index[memslot->id] = -1; + return &kvm->__memslots[as_id][node_idx_inactive]; } /* - * "Insert" a new memslot by incrementing the number of used slots. Returns - * the new slot's initial index into the memslots array. + * 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 inline int kvm_memslot_insert_back(struct kvm_memslots *slots) +static int kvm_memslots_get_as_id(struct kvm_memory_slot *a, + struct kvm_memory_slot *b) { - return slots->used_slots++; -} + if (WARN_ON_ONCE(!a && !b)) + return 0; -/* - * Move a changed memslot backwards in the array by shifting existing slots - * with a higher GFN toward the front of the array. Note, the changed memslot - * itself is not preserved in the array, i.e. not swapped at this time, only - * its new index into the array is tracked. Returns the changed memslot's - * current index into the memslots array. - */ -static inline int kvm_memslot_move_backward(struct kvm_memslots *slots, - struct kvm_memory_slot *memslot) -{ - struct kvm_memory_slot *mslots = slots->memslots; - int i; + if (!a) + return b->as_id; + if (!b) + return a->as_id; - if (WARN_ON_ONCE(slots->id_to_index[memslot->id] == -1) || - WARN_ON_ONCE(!slots->used_slots)) - return -1; + WARN_ON_ONCE(a->as_id != b->as_id); + return a->as_id; +} - /* - * Move the target memslot backward in the array by shifting existing - * memslots with a higher GFN (than the target memslot) towards the - * front of the array. - */ - for (i = slots->id_to_index[memslot->id]; i < slots->used_slots - 1; i++) { - if (memslot->base_gfn > mslots[i + 1].base_gfn) - break; +static void kvm_insert_gfn_node(struct kvm_memslots *slots, + struct kvm_memory_slot *slot) +{ + struct rb_root *gfn_tree = &slots->gfn_tree; + struct rb_node **node, *parent; + int idx = slots->node_idx; - WARN_ON_ONCE(memslot->base_gfn == mslots[i + 1].base_gfn); + parent = NULL; + for (node = &gfn_tree->rb_node; *node; ) { + struct kvm_memory_slot *tmp; - /* Shift the next memslot forward one and update its index. */ - mslots[i] = mslots[i + 1]; - slots->id_to_index[mslots[i].id] = i; + 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(); } - return i; + + rb_link_node(&slot->gfn_node[idx], parent, node); + rb_insert_color(&slot->gfn_node[idx], gfn_tree); } -/* - * Move a changed memslot forwards in the array by shifting existing slots with - * a lower GFN toward the back of the array. Note, the changed memslot itself - * is not preserved in the array, i.e. not swapped at this time, only its new - * index into the array is tracked. Returns the changed memslot's final index - * into the memslots array. - */ -static inline int kvm_memslot_move_forward(struct kvm_memslots *slots, - struct kvm_memory_slot *memslot, - int start) +static void kvm_erase_gfn_node(struct kvm_memslots *slots, + struct kvm_memory_slot *slot) { - struct kvm_memory_slot *mslots = slots->memslots; - int i; + rb_erase(&slot->gfn_node[slots->node_idx], &slots->gfn_tree); +} - for (i = start; i > 0; i--) { - if (memslot->base_gfn < mslots[i - 1].base_gfn) - break; +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(memslot->base_gfn == mslots[i - 1].base_gfn); + WARN_ON_ONCE(old->base_gfn != new->base_gfn); - /* Shift the next memslot back one and update its index. */ - mslots[i] = mslots[i - 1]; - slots->id_to_index[mslots[i].id] = i; - } - return i; + rb_replace_node(&old->gfn_node[idx], &new->gfn_node[idx], + &slots->gfn_tree); } /* - * Re-sort memslots based on their GFN to account for an added, deleted, or - * moved memslot. Sorting memslots by GFN allows using a binary search during - * memslot lookup. + * Replace @old with @new in the inactive memslots. * - * IMPORTANT: Slots are sorted from highest GFN to lowest GFN! I.e. the entry - * at memslots[0] has the highest GFN. + * With NULL @old this simply adds @new. + * With NULL @new this simply removes @old. * - * The sorting algorithm takes advantage of having initially sorted memslots - * and knowing the position of the changed memslot. Sorting is also optimized - * by not swapping the updated memslot and instead only shifting other memslots - * and tracking the new index for the update memslot. Only once its final - * index is known is the updated memslot copied into its position in the array. - * - * - When deleting a memslot, the deleted memslot simply needs to be moved to - * the end of the array. - * - * - When creating a memslot, the algorithm "inserts" the new memslot at the - * end of the array and then it forward to its correct location. - * - * - When moving a memslot, the algorithm first moves the updated memslot - * backward to handle the scenario where the memslot's GFN was changed to a - * lower value. update_memslots() then falls through and runs the same flow - * as creating a memslot to move the memslot forward to handle the scenario - * where its GFN was changed to a higher value. - * - * Note, slots are sorted from highest->lowest instead of lowest->highest for - * historical reasons. Originally, invalid memslots where denoted by having - * GFN=0, thus sorting from highest->lowest naturally sorted invalid memslots - * to the end of the array. The current algorithm uses dedicated logic to - * delete a memslot and thus does not rely on invalid memslots having GFN=0. - * - * The other historical motiviation for highest->lowest was to improve the - * performance of memslot lookup. KVM originally used a linear search starting - * at memslots[0]. On x86, the largest memslot usually has one of the highest, - * if not *the* highest, GFN, as the bulk of the guest's RAM is located in a - * single memslot above the 4gb boundary. As the largest memslot is also the - * most likely to be referenced, sorting it to the front of the array was - * advantageous. The current binary search starts from the middle of the array - * and uses an LRU pointer to improve performance for all memslots and GFNs. + * If @new is non-NULL its hva_node[slots_idx] range has to be set + * appropriately. */ -static void update_memslots(struct kvm_memslots *slots, - struct kvm_memory_slot *memslot, - enum kvm_mr_change change) +static void kvm_replace_memslot(struct kvm *kvm, + struct kvm_memory_slot *old, + struct kvm_memory_slot *new) { - int i; + 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 (change == KVM_MR_DELETE) { - kvm_memslot_delete(slots, memslot); - } else { - if (change == KVM_MR_CREATE) - i = kvm_memslot_insert_back(slots); - else - i = kvm_memslot_move_backward(slots, memslot); - i = kvm_memslot_move_forward(slots, memslot, i); + if (old) { + hash_del(&old->id_node[idx]); + interval_tree_remove(&old->hva_node[idx], &slots->hva_tree); - /* - * Copy the memslot to its new position in memslots and update - * its index accordingly. - */ - slots->memslots[i] = *memslot; - slots->id_to_index[memslot->id] = i; + 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); } } @@ -1435,11 +1433,12 @@ static int check_memory_region_flags(const struct kvm_userspace_memory_region *m return 0; } -static struct kvm_memslots *install_new_memslots(struct kvm *kvm, - int as_id, struct kvm_memslots *slots) +static void kvm_swap_active_memslots(struct kvm *kvm, int as_id) { - struct kvm_memslots *old_memslots = __kvm_memslots(kvm, as_id); - u64 gen = old_memslots->generation; + 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; @@ -1490,60 +1489,226 @@ static struct kvm_memslots *install_new_memslots(struct kvm *kvm, kvm_arch_memslots_updated(kvm, gen); slots->generation = gen; - - return old_memslots; } -static size_t kvm_memslots_size(int slots) +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) { - return sizeof(struct kvm_memslots) + - (sizeof(struct kvm_memory_slot) * slots); + 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->dirty_ring_size) { + 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_copy_memslots(struct kvm_memslots *to, - struct kvm_memslots *from) +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) { - memcpy(to, from, kvm_memslots_size(from->used_slots)); + /* + * 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; + + 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(); + } } /* - * Note, at a minimum, the current number of used slots must be allocated, even - * when deleting a memslot, as we need a complete duplicate of the memslots for - * use when invalidating a memslot prior to deleting/moving the memslot. + * 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. + * + * 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). */ -static struct kvm_memslots *kvm_dup_memslots(struct kvm_memslots *old, - enum kvm_mr_change change) +static void kvm_activate_memslot(struct kvm *kvm, + struct kvm_memory_slot *old, + struct kvm_memory_slot *new) { - struct kvm_memslots *slots; - size_t new_size; + int as_id = kvm_memslots_get_as_id(old, new); - if (change == KVM_MR_CREATE) - new_size = kvm_memslots_size(old->used_slots + 1); - else - new_size = kvm_memslots_size(old->used_slots); + kvm_swap_active_memslots(kvm, as_id); + + /* Propagate the new memslot to the now inactive memslots. */ + kvm_replace_memslot(kvm, old, new); +} + +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; +} + +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); + + /* + * 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); + + /* + * 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); + + /* Was released by kvm_swap_active_memslots, reacquire. */ + mutex_lock(&kvm->slots_arch_lock); - slots = kvzalloc(new_size, GFP_KERNEL_ACCOUNT); - if (likely(slots)) - kvm_copy_memslots(slots, old); + /* + * 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 install_new_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; +} - return slots; +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, - const struct kvm_userspace_memory_region *mem, - struct kvm_memory_slot *new, int as_id, + struct kvm_memory_slot *old, + struct kvm_memory_slot *new, enum kvm_mr_change change) { - struct kvm_memory_slot *slot, old; - struct kvm_memslots *slots; + struct kvm_memory_slot *invalid_slot; int r; /* - * Released in install_new_memslots. + * 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 install_new_memslots. + * 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 @@ -1554,114 +1719,88 @@ static int kvm_set_memslot(struct kvm *kvm, */ mutex_lock(&kvm->slots_arch_lock); - slots = kvm_dup_memslots(__kvm_memslots(kvm, as_id), change); - if (!slots) { - mutex_unlock(&kvm->slots_arch_lock); - return -ENOMEM; - } - + /* + * 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) { - /* - * Note, the INVALID flag needs to be in the appropriate entry - * in the freshly allocated memslots, not in @old or @new. - */ - slot = id_to_memslot(slots, new->id); - slot->flags |= KVM_MEMSLOT_INVALID; - - /* - * We can re-use the memory from the old memslots. - * It will be overwritten with a copy of the new memslots - * after reacquiring the slots_arch_lock below. - */ - slots = install_new_memslots(kvm, as_id, slots); - - /* 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, slot); - - /* Released in install_new_memslots. */ - mutex_lock(&kvm->slots_arch_lock); + invalid_slot = kzalloc(sizeof(*invalid_slot), GFP_KERNEL_ACCOUNT); + if (!invalid_slot) { + mutex_unlock(&kvm->slots_arch_lock); + return -ENOMEM; + } + kvm_invalidate_memslot(kvm, old, invalid_slot); + } + r = kvm_prepare_memory_region(kvm, old, new, change); + if (r) { /* - * The arch-specific fields of the memslots could have changed - * between releasing the slots_arch_lock in - * install_new_memslots and here, so get a fresh copy of the - * slots. + * 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. */ - kvm_copy_memslots(slots, __kvm_memslots(kvm, as_id)); + 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; } /* - * Make a full copy of the old memslot, the pointer will become stale - * when the memslots are re-sorted by update_memslots(), and the old - * memslot needs to be referenced after calling update_memslots(), e.g. - * to free its resources and for arch specific behavior. This needs to - * happen *after* (re)acquiring slots_arch_lock. + * 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. */ - slot = id_to_memslot(slots, new->id); - if (slot) { - old = *slot; - } else { - WARN_ON_ONCE(change != KVM_MR_CREATE); - memset(&old, 0, sizeof(old)); - old.id = new->id; - old.as_id = as_id; - } - - /* Copy the arch-specific data, again after (re)acquiring slots_arch_lock. */ - memcpy(&new->arch, &old.arch, sizeof(old.arch)); - - r = kvm_arch_prepare_memory_region(kvm, new, mem, change); - if (r) - goto out_slots; - - update_memslots(slots, new, change); - slots = install_new_memslots(kvm, as_id, slots); + 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(); - kvm_arch_commit_memory_region(kvm, mem, &old, new, change); + /* Free the temporary INVALID slot used for DELETE and MOVE. */ + if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) + kfree(invalid_slot); - /* Free the old memslot's metadata. Note, this is the full copy!!! */ - if (change == KVM_MR_DELETE) - kvm_free_memslot(kvm, &old); + /* + * No need to refresh new->arch, changes after dropping slots_arch_lock + * will directly hit the final, active memsot. Architectures are + * responsible for knowing that new->arch may be stale. + */ + kvm_commit_memory_region(kvm, old, new, change); - kvfree(slots); return 0; - -out_slots: - if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) { - slot = id_to_memslot(slots, new->id); - slot->flags &= ~KVM_MEMSLOT_INVALID; - slots = install_new_memslots(kvm, as_id, slots); - } else { - mutex_unlock(&kvm->slots_arch_lock); - } - kvfree(slots); - return r; } -static int kvm_delete_memslot(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, - struct kvm_memory_slot *old, int as_id) +static bool kvm_check_memslot_overlap(struct kvm_memslots *slots, int id, + gfn_t start, gfn_t end) { - struct kvm_memory_slot new; + struct kvm_memslot_iter iter; - if (!old->npages) - return -EINVAL; - - memset(&new, 0, sizeof(new)); - new.id = old->id; - /* - * This is only for debugging purpose; it should never be referenced - * for a removed memslot. - */ - new.as_id = as_id; + kvm_for_each_memslot_in_gfn_range(&iter, slots, start, end) { + if (iter.slot->id != id) + return true; + } - return kvm_set_memslot(kvm, mem, &new, as_id, KVM_MR_DELETE); + return false; } /* @@ -1675,9 +1814,11 @@ static int kvm_delete_memslot(struct kvm *kvm, int __kvm_set_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem) { - struct kvm_memory_slot old, new; - struct kvm_memory_slot *tmp; + 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; @@ -1704,89 +1845,72 @@ int __kvm_set_memory_region(struct kvm *kvm, return -EINVAL; if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr) return -EINVAL; + if ((mem->memory_size >> PAGE_SHIFT) > KVM_MEM_MAX_NR_PAGES) + return -EINVAL; + + slots = __kvm_memslots(kvm, as_id); /* - * Make a full copy of the old memslot, the pointer will become stale - * when the memslots are re-sorted by update_memslots(), and the old - * memslot needs to be referenced after calling update_memslots(), e.g. - * to free its resources and for arch specific behavior. + * Note, the old memslot (and the pointer itself!) may be invalidated + * and/or destroyed by kvm_set_memslot(). */ - tmp = id_to_memslot(__kvm_memslots(kvm, as_id), id); - if (tmp) { - old = *tmp; - tmp = NULL; - } else { - memset(&old, 0, sizeof(old)); - old.id = id; - } + old = id_to_memslot(slots, id); - if (!mem->memory_size) - return kvm_delete_memslot(kvm, mem, &old, as_id); + if (!mem->memory_size) { + if (!old || !old->npages) + return -EINVAL; - new.as_id = as_id; - new.id = id; - new.base_gfn = mem->guest_phys_addr >> PAGE_SHIFT; - new.npages = mem->memory_size >> PAGE_SHIFT; - new.flags = mem->flags; - new.userspace_addr = mem->userspace_addr; + if (WARN_ON_ONCE(kvm->nr_memslot_pages < old->npages)) + return -EIO; - if (new.npages > KVM_MEM_MAX_NR_PAGES) - return -EINVAL; + return kvm_set_memslot(kvm, old, NULL, KVM_MR_DELETE); + } + + base_gfn = (mem->guest_phys_addr >> PAGE_SHIFT); + npages = (mem->memory_size >> PAGE_SHIFT); - if (!old.npages) { + if (!old || !old->npages) { change = KVM_MR_CREATE; - new.dirty_bitmap = NULL; + + /* + * 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. */ - if ((new.userspace_addr != old.userspace_addr) || - (new.npages != old.npages) || - ((new.flags ^ old.flags) & KVM_MEM_READONLY)) + if ((mem->userspace_addr != old->userspace_addr) || + (npages != old->npages) || + ((mem->flags ^ old->flags) & KVM_MEM_READONLY)) return -EINVAL; - if (new.base_gfn != old.base_gfn) + if (base_gfn != old->base_gfn) change = KVM_MR_MOVE; - else if (new.flags != old.flags) + else if (mem->flags != old->flags) change = KVM_MR_FLAGS_ONLY; else /* Nothing to change. */ return 0; - - /* Copy dirty_bitmap from the current memslot. */ - new.dirty_bitmap = old.dirty_bitmap; } - if ((change == KVM_MR_CREATE) || (change == KVM_MR_MOVE)) { - /* Check for overlaps */ - kvm_for_each_memslot(tmp, __kvm_memslots(kvm, as_id)) { - if (tmp->id == id) - continue; - if (!((new.base_gfn + new.npages <= tmp->base_gfn) || - (new.base_gfn >= tmp->base_gfn + tmp->npages))) - return -EEXIST; - } - } + if ((change == KVM_MR_CREATE || change == KVM_MR_MOVE) && + kvm_check_memslot_overlap(slots, id, base_gfn, base_gfn + npages)) + return -EEXIST; - /* Allocate/free page dirty bitmap as needed */ - if (!(new.flags & KVM_MEM_LOG_DIRTY_PAGES)) - new.dirty_bitmap = NULL; - else if (!new.dirty_bitmap && !kvm->dirty_ring_size) { - r = kvm_alloc_dirty_bitmap(&new); - if (r) - return r; + /* Allocate a slot that will persist in the memslot. */ + new = kzalloc(sizeof(*new), GFP_KERNEL_ACCOUNT); + if (!new) + return -ENOMEM; - if (kvm_dirty_log_manual_protect_and_init_set(kvm)) - bitmap_set(new.dirty_bitmap, 0, new.npages); - } + 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; - r = kvm_set_memslot(kvm, mem, &new, as_id, change); + r = kvm_set_memslot(kvm, old, new, change); if (r) - goto out_bitmap; - - if (old.dirty_bitmap && !new.dirty_bitmap) - kvm_destroy_dirty_bitmap(&old); - return 0; - -out_bitmap: - if (new.dirty_bitmap && !old.dirty_bitmap) - kvm_destroy_dirty_bitmap(&new); + kfree(new); return r; } EXPORT_SYMBOL_GPL(__kvm_set_memory_region); @@ -2092,21 +2216,30 @@ EXPORT_SYMBOL_GPL(gfn_to_memslot); 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; - int slot_index; - slot = try_get_memslot(slots, vcpu->last_used_slot, gfn); + /* + * 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_index in kvm_memslots. + * thrashing the VM-wide last_used_slot in kvm_memslots. */ - slot = search_memslots(slots, gfn, &slot_index); + slot = search_memslots(slots, gfn, false); if (slot) { - vcpu->last_used_slot = slot_index; + vcpu->last_used_slot = slot; return slot; } @@ -2154,12 +2287,12 @@ out: 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) @@ -2454,7 +2587,7 @@ exit: return pfn; } -kvm_pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, +kvm_pfn_t __gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn, bool atomic, bool *async, bool write_fault, bool *writable, hva_t *hva) { @@ -2494,13 +2627,13 @@ kvm_pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault, } EXPORT_SYMBOL_GPL(gfn_to_pfn_prot); -kvm_pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn) +kvm_pfn_t gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn) { return __gfn_to_pfn_memslot(slot, gfn, false, NULL, true, NULL, NULL); } EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot); -kvm_pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn) +kvm_pfn_t gfn_to_pfn_memslot_atomic(const struct kvm_memory_slot *slot, gfn_t gfn) { return __gfn_to_pfn_memslot(slot, gfn, true, NULL, true, NULL, NULL); } @@ -3019,7 +3152,7 @@ int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len) EXPORT_SYMBOL_GPL(kvm_clear_guest); void mark_page_dirty_in_slot(struct kvm *kvm, - struct kvm_memory_slot *memslot, + const struct kvm_memory_slot *memslot, gfn_t gfn) { if (memslot && kvm_slot_dirty_track_enabled(memslot)) { @@ -3139,68 +3272,93 @@ out: return ret; } -static inline void -update_halt_poll_stats(struct kvm_vcpu *vcpu, u64 poll_ns, bool waited) +/* + * 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. + */ +bool kvm_vcpu_block(struct kvm_vcpu *vcpu) { - if (waited) - vcpu->stat.generic.halt_poll_fail_ns += poll_ns; - else - vcpu->stat.generic.halt_poll_success_ns += poll_ns; + struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu); + bool waited = false; + + vcpu->stat.generic.blocking = 1; + + kvm_arch_vcpu_blocking(vcpu); + + prepare_to_rcuwait(wait); + for (;;) { + set_current_state(TASK_INTERRUPTIBLE); + + if (kvm_vcpu_check_block(vcpu) < 0) + break; + + waited = true; + schedule(); + } + finish_rcuwait(wait); + + kvm_arch_vcpu_unblocking(vcpu); + + 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); + } } /* - * The vCPU has executed a HLT instruction with in-kernel mode enabled. + * 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_block(struct kvm_vcpu *vcpu) +void kvm_vcpu_halt(struct kvm_vcpu *vcpu) { + bool halt_poll_allowed = !kvm_arch_no_poll(vcpu); + bool do_halt_poll = halt_poll_allowed && vcpu->halt_poll_ns; ktime_t start, cur, poll_end; bool waited = false; - u64 block_ns; - - kvm_arch_vcpu_blocking(vcpu); + u64 halt_ns; start = cur = poll_end = ktime_get(); - if (vcpu->halt_poll_ns && !kvm_arch_no_poll(vcpu)) { - ktime_t stop = ktime_add_ns(ktime_get(), vcpu->halt_poll_ns); + if (do_halt_poll) { + ktime_t stop = ktime_add_ns(start, vcpu->halt_poll_ns); - ++vcpu->stat.generic.halt_attempted_poll; do { /* * This sets KVM_REQ_UNHALT if an interrupt * arrives. */ - if (kvm_vcpu_check_block(vcpu) < 0) { - ++vcpu->stat.generic.halt_successful_poll; - if (!vcpu_valid_wakeup(vcpu)) - ++vcpu->stat.generic.halt_poll_invalid; - - KVM_STATS_LOG_HIST_UPDATE( - vcpu->stat.generic.halt_poll_success_hist, - ktime_to_ns(ktime_get()) - - ktime_to_ns(start)); + if (kvm_vcpu_check_block(vcpu) < 0) goto out; - } cpu_relax(); poll_end = cur = ktime_get(); } while (kvm_vcpu_can_poll(cur, stop)); - - KVM_STATS_LOG_HIST_UPDATE( - vcpu->stat.generic.halt_poll_fail_hist, - ktime_to_ns(ktime_get()) - ktime_to_ns(start)); } + waited = kvm_vcpu_block(vcpu); - prepare_to_rcuwait(&vcpu->wait); - for (;;) { - set_current_state(TASK_INTERRUPTIBLE); - - if (kvm_vcpu_check_block(vcpu) < 0) - break; - - waited = true; - schedule(); - } - finish_rcuwait(&vcpu->wait); cur = ktime_get(); if (waited) { vcpu->stat.generic.halt_wait_ns += @@ -3209,42 +3367,43 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) ktime_to_ns(cur) - ktime_to_ns(poll_end)); } out: - kvm_arch_vcpu_unblocking(vcpu); - block_ns = ktime_to_ns(cur) - ktime_to_ns(start); + /* The total time the vCPU was "halted", including polling time. */ + halt_ns = ktime_to_ns(cur) - ktime_to_ns(start); - update_halt_poll_stats( - vcpu, ktime_to_ns(ktime_sub(poll_end, start)), waited); + /* + * 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 (!kvm_arch_no_poll(vcpu)) { + if (halt_poll_allowed) { if (!vcpu_valid_wakeup(vcpu)) { shrink_halt_poll_ns(vcpu); } else if (vcpu->kvm->max_halt_poll_ns) { - if (block_ns <= vcpu->halt_poll_ns) + if (halt_ns <= vcpu->halt_poll_ns) ; /* we had a long block, shrink polling */ else if (vcpu->halt_poll_ns && - block_ns > vcpu->kvm->max_halt_poll_ns) + halt_ns > vcpu->kvm->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 < vcpu->kvm->max_halt_poll_ns && - block_ns < vcpu->kvm->max_halt_poll_ns) + halt_ns < vcpu->kvm->max_halt_poll_ns) grow_halt_poll_ns(vcpu); } else { vcpu->halt_poll_ns = 0; } } - trace_kvm_vcpu_wakeup(block_ns, waited, vcpu_valid_wakeup(vcpu)); - kvm_arch_vcpu_block_finish(vcpu); + trace_kvm_vcpu_wakeup(halt_ns, waited, vcpu_valid_wakeup(vcpu)); } -EXPORT_SYMBOL_GPL(kvm_vcpu_block); +EXPORT_SYMBOL_GPL(kvm_vcpu_halt); bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu) { - struct rcuwait *waitp; - - waitp = kvm_arch_vcpu_get_wait(vcpu); - if (rcuwait_wake_up(waitp)) { + if (__kvm_vcpu_wake_up(vcpu)) { WRITE_ONCE(vcpu->ready, true); ++vcpu->stat.generic.halt_wakeup; return true; @@ -3265,6 +3424,19 @@ void kvm_vcpu_kick(struct kvm_vcpu *vcpu) if (kvm_vcpu_wake_up(vcpu)) return; + 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 @@ -3272,12 +3444,12 @@ void kvm_vcpu_kick(struct kvm_vcpu *vcpu) * IPI is to force the vCPU to leave IN_GUEST_MODE, and migrating the * vCPU also requires it to leave IN_GUEST_MODE. */ - me = get_cpu(); if (kvm_arch_vcpu_should_kick(vcpu)) { cpu = READ_ONCE(vcpu->cpu); if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) smp_send_reschedule(cpu); } +out: put_cpu(); } EXPORT_SYMBOL_GPL(kvm_vcpu_kick); @@ -3375,10 +3547,10 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode) struct kvm *kvm = me->kvm; struct kvm_vcpu *vcpu; int last_boosted_vcpu = me->kvm->last_boosted_vcpu; + unsigned long i; int yielded = 0; int try = 3; int pass; - int i; kvm_vcpu_set_in_spin_loop(me, true); /* @@ -3399,8 +3571,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode) continue; if (vcpu == me) continue; - if (rcuwait_active(&vcpu->wait) && - !vcpu_dy_runnable(vcpu)) + if (kvm_vcpu_is_blocking(vcpu) && !vcpu_dy_runnable(vcpu)) continue; if (READ_ONCE(vcpu->preempted) && yield_to_kernel_mode && !kvm_arch_dy_has_pending_interrupt(vcpu) && @@ -3429,7 +3600,7 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_on_spin); static bool kvm_page_in_dirty_ring(struct kvm *kvm, unsigned long pgoff) { -#if KVM_DIRTY_LOG_PAGE_OFFSET > 0 +#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); @@ -3585,7 +3756,10 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) } vcpu->vcpu_idx = atomic_read(&kvm->online_vcpus); - BUG_ON(kvm->vcpus[vcpu->vcpu_idx]); + r = xa_insert(&kvm->vcpu_array, vcpu->vcpu_idx, vcpu, GFP_KERNEL_ACCOUNT); + BUG_ON(r == -EBUSY); + if (r) + goto unlock_vcpu_destroy; /* Fill the stats id string for the vcpu */ snprintf(vcpu->stats_id, sizeof(vcpu->stats_id), "kvm-%d/vcpu-%d", @@ -3595,15 +3769,14 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) kvm_get_kvm(kvm); r = create_vcpu_fd(vcpu); if (r < 0) { + xa_erase(&kvm->vcpu_array, vcpu->vcpu_idx); kvm_put_kvm_no_destroy(kvm); goto unlock_vcpu_destroy; } - kvm->vcpus[vcpu->vcpu_idx] = vcpu; - /* - * Pairs with smp_rmb() in kvm_get_vcpu. Write kvm->vcpus - * before kvm->online_vcpu's incremented value. + * 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); @@ -4132,7 +4305,7 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) case KVM_CAP_NR_MEMSLOTS: return KVM_USER_MEM_SLOTS; case KVM_CAP_DIRTY_LOG_RING: -#if KVM_DIRTY_LOG_PAGE_OFFSET > 0 +#ifdef CONFIG_HAVE_KVM_DIRTY_RING return KVM_DIRTY_RING_MAX_ENTRIES * sizeof(struct kvm_dirty_gfn); #else return 0; @@ -4185,7 +4358,7 @@ static int kvm_vm_ioctl_enable_dirty_log_ring(struct kvm *kvm, u32 size) static int kvm_vm_ioctl_reset_dirty_pages(struct kvm *kvm) { - int i; + unsigned long i; struct kvm_vcpu *vcpu; int cleared = 0; @@ -5104,7 +5277,7 @@ static int kvm_clear_stat_per_vm(struct kvm *kvm, size_t offset) static int kvm_get_stat_per_vcpu(struct kvm *kvm, size_t offset, u64 *val) { - int i; + unsigned long i; struct kvm_vcpu *vcpu; *val = 0; @@ -5117,7 +5290,7 @@ static int kvm_get_stat_per_vcpu(struct kvm *kvm, size_t offset, u64 *val) static int kvm_clear_stat_per_vcpu(struct kvm *kvm, size_t offset) { - int i; + unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) |