diff options
Diffstat (limited to 'arch/ia64/kvm/kvm-ia64.c')
| -rw-r--r-- | arch/ia64/kvm/kvm-ia64.c | 685 |
1 files changed, 407 insertions, 278 deletions
diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c index 28f982045f2..6a4309bb821 100644 --- a/arch/ia64/kvm/kvm-ia64.c +++ b/arch/ia64/kvm/kvm-ia64.c @@ -1,5 +1,5 @@ /* - * kvm_ia64.c: Basic KVM suppport On Itanium series processors + * kvm_ia64.c: Basic KVM support On Itanium series processors * * * Copyright (C) 2007, Intel Corporation. @@ -23,8 +23,8 @@ #include <linux/module.h> #include <linux/errno.h> #include <linux/percpu.h> -#include <linux/gfp.h> #include <linux/fs.h> +#include <linux/slab.h> #include <linux/smp.h> #include <linux/kvm_host.h> #include <linux/kvm.h> @@ -33,6 +33,7 @@ #include <linux/uaccess.h> #include <linux/iommu.h> #include <linux/intel-iommu.h> +#include <linux/pci.h> #include <asm/pgtable.h> #include <asm/gcc_intrin.h> @@ -41,6 +42,9 @@ #include <asm/div64.h> #include <asm/tlb.h> #include <asm/elf.h> +#include <asm/sn/addrs.h> +#include <asm/sn/clksupport.h> +#include <asm/sn/shub_mmr.h> #include "misc.h" #include "vti.h" @@ -65,12 +69,22 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { NULL } }; +static unsigned long kvm_get_itc(struct kvm_vcpu *vcpu) +{ +#if defined(CONFIG_IA64_SGI_SN2) || defined(CONFIG_IA64_GENERIC) + if (vcpu->kvm->arch.is_sn2) + return rtc_time(); + else +#endif + return ia64_getreg(_IA64_REG_AR_ITC); +} + static void kvm_flush_icache(unsigned long start, unsigned long len) { int l; for (l = 0; l < (len + 32); l += 32) - ia64_fc(start + l); + ia64_fc((void *)(start + l)); ia64_sync_i(); ia64_srlz_i(); @@ -111,7 +125,7 @@ long ia64_pal_vp_create(u64 *vpd, u64 *host_iva, u64 *opt_handler) static DEFINE_SPINLOCK(vp_lock); -void kvm_arch_hardware_enable(void *garbage) +int kvm_arch_hardware_enable(void *garbage) { long status; long tmp_base; @@ -119,21 +133,21 @@ void kvm_arch_hardware_enable(void *garbage) unsigned long saved_psr; int slot; - pte = pte_val(mk_pte_phys(__pa(kvm_vmm_base), - PAGE_KERNEL)); + pte = pte_val(mk_pte_phys(__pa(kvm_vmm_base), PAGE_KERNEL)); local_irq_save(saved_psr); slot = ia64_itr_entry(0x3, KVM_VMM_BASE, pte, KVM_VMM_SHIFT); local_irq_restore(saved_psr); if (slot < 0) - return; + return -EINVAL; spin_lock(&vp_lock); status = ia64_pal_vp_init_env(kvm_vsa_base ? VP_INIT_ENV : VP_INIT_ENV_INITALIZE, __pa(kvm_vm_buffer), KVM_VM_BUFFER_BASE, &tmp_base); if (status != 0) { + spin_unlock(&vp_lock); printk(KERN_WARNING"kvm: Failed to Enable VT Support!!!!\n"); - return ; + return -EINVAL; } if (!kvm_vsa_base) { @@ -142,6 +156,8 @@ void kvm_arch_hardware_enable(void *garbage) } spin_unlock(&vp_lock); ia64_ptr_entry(0x3, slot); + + return 0; } void kvm_arch_hardware_disable(void *garbage) @@ -182,15 +198,18 @@ int kvm_dev_ioctl_check_extension(long ext) switch (ext) { case KVM_CAP_IRQCHIP: case KVM_CAP_MP_STATE: - + case KVM_CAP_IRQ_INJECT_STATUS: + case KVM_CAP_IOAPIC_POLARITY_IGNORED: r = 1; break; case KVM_CAP_COALESCED_MMIO: r = KVM_COALESCED_MMIO_PAGE_OFFSET; break; +#ifdef CONFIG_KVM_DEVICE_ASSIGNMENT case KVM_CAP_IOMMU: - r = iommu_found(); + r = iommu_present(&pci_bus_type); break; +#endif default: r = 0; } @@ -198,16 +217,6 @@ int kvm_dev_ioctl_check_extension(long ext) } -static struct kvm_io_device *vcpu_find_mmio_dev(struct kvm_vcpu *vcpu, - gpa_t addr, int len, int is_write) -{ - struct kvm_io_device *dev; - - dev = kvm_io_bus_find_dev(&vcpu->kvm->mmio_bus, addr, len, is_write); - - return dev; -} - static int handle_vm_error(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { kvm_run->exit_reason = KVM_EXIT_UNKNOWN; @@ -219,32 +228,30 @@ static int handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { struct kvm_mmio_req *p; struct kvm_io_device *mmio_dev; + int r; p = kvm_get_vcpu_ioreq(vcpu); if ((p->addr & PAGE_MASK) == IOAPIC_DEFAULT_BASE_ADDRESS) goto mmio; vcpu->mmio_needed = 1; - vcpu->mmio_phys_addr = kvm_run->mmio.phys_addr = p->addr; - vcpu->mmio_size = kvm_run->mmio.len = p->size; + vcpu->mmio_fragments[0].gpa = kvm_run->mmio.phys_addr = p->addr; + vcpu->mmio_fragments[0].len = kvm_run->mmio.len = p->size; vcpu->mmio_is_write = kvm_run->mmio.is_write = !p->dir; if (vcpu->mmio_is_write) - memcpy(vcpu->mmio_data, &p->data, p->size); + memcpy(vcpu->arch.mmio_data, &p->data, p->size); memcpy(kvm_run->mmio.data, &p->data, p->size); kvm_run->exit_reason = KVM_EXIT_MMIO; return 0; mmio: - mmio_dev = vcpu_find_mmio_dev(vcpu, p->addr, p->size, !p->dir); - if (mmio_dev) { - if (!p->dir) - kvm_iodevice_write(mmio_dev, p->addr, p->size, - &p->data); - else - kvm_iodevice_read(mmio_dev, p->addr, p->size, - &p->data); - - } else + if (p->dir) + r = kvm_io_bus_read(vcpu->kvm, KVM_MMIO_BUS, p->addr, + p->size, &p->data); + else + r = kvm_io_bus_write(vcpu->kvm, KVM_MMIO_BUS, p->addr, + p->size, &p->data); + if (r) printk(KERN_ERR"kvm: No iodevice found! addr:%lx\n", p->addr); p->state = STATE_IORESP_READY; @@ -283,6 +290,18 @@ static int handle_sal_call(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } +static int __apic_accept_irq(struct kvm_vcpu *vcpu, uint64_t vector) +{ + struct vpd *vpd = to_host(vcpu->kvm, vcpu->arch.vpd); + + if (!test_and_set_bit(vector, &vpd->irr[0])) { + vcpu->arch.irq_new_pending = 1; + kvm_vcpu_kick(vcpu); + return 1; + } + return 0; +} + /* * offset: address offset to IPI space. * value: deliver value. @@ -292,20 +311,20 @@ static void vcpu_deliver_ipi(struct kvm_vcpu *vcpu, uint64_t dm, { switch (dm) { case SAPIC_FIXED: - kvm_apic_set_irq(vcpu, vector, 0); break; case SAPIC_NMI: - kvm_apic_set_irq(vcpu, 2, 0); + vector = 2; break; case SAPIC_EXTINT: - kvm_apic_set_irq(vcpu, 0, 0); + vector = 0; break; case SAPIC_INIT: case SAPIC_PMI: default: printk(KERN_ERR"kvm: Unimplemented Deliver reserved IPI!\n"); - break; + return; } + __apic_accept_irq(vcpu, vector); } static struct kvm_vcpu *lid_to_vcpu(struct kvm *kvm, unsigned long id, @@ -313,13 +332,12 @@ static struct kvm_vcpu *lid_to_vcpu(struct kvm *kvm, unsigned long id, { union ia64_lid lid; int i; + struct kvm_vcpu *vcpu; - for (i = 0; i < KVM_MAX_VCPUS; i++) { - if (kvm->vcpus[i]) { - lid.val = VCPU_LID(kvm->vcpus[i]); - if (lid.id == id && lid.eid == eid) - return kvm->vcpus[i]; - } + kvm_for_each_vcpu(i, vcpu, kvm) { + lid.val = VCPU_LID(vcpu); + if (lid.id == id && lid.eid == eid) + return vcpu; } return NULL; @@ -385,21 +403,21 @@ static int handle_global_purge(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) struct kvm *kvm = vcpu->kvm; struct call_data call_data; int i; + struct kvm_vcpu *vcpui; call_data.ptc_g_data = p->u.ptc_g_data; - for (i = 0; i < KVM_MAX_VCPUS; i++) { - if (!kvm->vcpus[i] || kvm->vcpus[i]->arch.mp_state == - KVM_MP_STATE_UNINITIALIZED || - vcpu == kvm->vcpus[i]) + kvm_for_each_vcpu(i, vcpui, kvm) { + if (vcpui->arch.mp_state == KVM_MP_STATE_UNINITIALIZED || + vcpu == vcpui) continue; - if (waitqueue_active(&kvm->vcpus[i]->wq)) - wake_up_interruptible(&kvm->vcpus[i]->wq); + if (waitqueue_active(&vcpui->wq)) + wake_up_interruptible(&vcpui->wq); - if (kvm->vcpus[i]->cpu != -1) { - call_data.vcpu = kvm->vcpus[i]; - smp_call_function_single(kvm->vcpus[i]->cpu, + if (vcpui->cpu != -1) { + call_data.vcpu = vcpui; + smp_call_function_single(vcpui->cpu, vcpu_global_purge, &call_data, 1); } else printk(KERN_WARNING"kvm: Uninit vcpu received ipi!\n"); @@ -413,6 +431,23 @@ static int handle_switch_rr6(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return 1; } +static int kvm_sn2_setup_mappings(struct kvm_vcpu *vcpu) +{ + unsigned long pte, rtc_phys_addr, map_addr; + int slot; + + map_addr = KVM_VMM_BASE + (1UL << KVM_VMM_SHIFT); + rtc_phys_addr = LOCAL_MMR_OFFSET | SH_RTC; + pte = pte_val(mk_pte_phys(rtc_phys_addr, PAGE_KERNEL_UC)); + slot = ia64_itr_entry(0x3, map_addr, pte, PAGE_SHIFT); + vcpu->arch.sn_rtc_tr_slot = slot; + if (slot < 0) { + printk(KERN_ERR "Mayday mayday! RTC mapping failed!\n"); + slot = 0; + } + return slot; +} + int kvm_emulate_halt(struct kvm_vcpu *vcpu) { @@ -426,7 +461,7 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu) if (irqchip_in_kernel(vcpu->kvm)) { - vcpu_now_itc = ia64_getreg(_IA64_REG_AR_ITC) + vcpu->arch.itc_offset; + vcpu_now_itc = kvm_get_itc(vcpu) + vcpu->arch.itc_offset; if (time_after(vcpu_now_itc, vpd->itm)) { vcpu->arch.timer_check = 1; @@ -447,10 +482,10 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu) hrtimer_cancel(p_ht); vcpu->arch.ht_active = 0; - if (test_and_clear_bit(KVM_REQ_UNHALT, &vcpu->requests)) + if (test_and_clear_bit(KVM_REQ_UNHALT, &vcpu->requests) || + kvm_cpu_has_pending_timer(vcpu)) if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED) - vcpu->arch.mp_state = - KVM_MP_STATE_RUNNABLE; + vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; if (vcpu->arch.mp_state != KVM_MP_STATE_RUNNABLE) return -EINTR; @@ -551,22 +586,35 @@ static int kvm_insert_vmm_mapping(struct kvm_vcpu *vcpu) if (r < 0) goto out; vcpu->arch.vm_tr_slot = r; + +#if defined(CONFIG_IA64_SGI_SN2) || defined(CONFIG_IA64_GENERIC) + if (kvm->arch.is_sn2) { + r = kvm_sn2_setup_mappings(vcpu); + if (r < 0) + goto out; + } +#endif + r = 0; out: return r; - } static void kvm_purge_vmm_mapping(struct kvm_vcpu *vcpu) { - + struct kvm *kvm = vcpu->kvm; ia64_ptr_entry(0x3, vcpu->arch.vmm_tr_slot); ia64_ptr_entry(0x3, vcpu->arch.vm_tr_slot); - +#if defined(CONFIG_IA64_SGI_SN2) || defined(CONFIG_IA64_GENERIC) + if (kvm->arch.is_sn2) + ia64_ptr_entry(0x3, vcpu->arch.sn_rtc_tr_slot); +#endif } static int kvm_vcpu_pre_transition(struct kvm_vcpu *vcpu) { + unsigned long psr; + int r; int cpu = smp_processor_id(); if (vcpu->arch.last_run_cpu != cpu || @@ -578,62 +626,58 @@ static int kvm_vcpu_pre_transition(struct kvm_vcpu *vcpu) vcpu->arch.host_rr6 = ia64_get_rr(RR6); vti_set_rr6(vcpu->arch.vmm_rr); - return kvm_insert_vmm_mapping(vcpu); + local_irq_save(psr); + r = kvm_insert_vmm_mapping(vcpu); + local_irq_restore(psr); + return r; } + static void kvm_vcpu_post_transition(struct kvm_vcpu *vcpu) { kvm_purge_vmm_mapping(vcpu); vti_set_rr6(vcpu->arch.host_rr6); } -static int vti_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { union context *host_ctx, *guest_ctx; - int r; - - /*Get host and guest context with guest address space.*/ - host_ctx = kvm_get_host_context(vcpu); - guest_ctx = kvm_get_guest_context(vcpu); + int r, idx; - r = kvm_vcpu_pre_transition(vcpu); - if (r < 0) - goto out; - kvm_vmm_info->tramp_entry(host_ctx, guest_ctx); - kvm_vcpu_post_transition(vcpu); - r = 0; -out: - return r; -} - -static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) -{ - int r; + idx = srcu_read_lock(&vcpu->kvm->srcu); again: - preempt_disable(); - local_irq_disable(); - if (signal_pending(current)) { - local_irq_enable(); - preempt_enable(); r = -EINTR; kvm_run->exit_reason = KVM_EXIT_INTR; goto out; } - vcpu->guest_mode = 1; + preempt_disable(); + local_irq_disable(); + + /*Get host and guest context with guest address space.*/ + host_ctx = kvm_get_host_context(vcpu); + guest_ctx = kvm_get_guest_context(vcpu); + + clear_bit(KVM_REQ_KICK, &vcpu->requests); + + r = kvm_vcpu_pre_transition(vcpu); + if (r < 0) + goto vcpu_run_fail; + + srcu_read_unlock(&vcpu->kvm->srcu, idx); + vcpu->mode = IN_GUEST_MODE; kvm_guest_enter(); - down_read(&vcpu->kvm->slots_lock); - r = vti_vcpu_run(vcpu, kvm_run); - if (r < 0) { - local_irq_enable(); - preempt_enable(); - kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY; - goto out; - } + + /* + * Transition to the guest + */ + kvm_vmm_info->tramp_entry(host_ctx, guest_ctx); + + kvm_vcpu_post_transition(vcpu); vcpu->arch.launched = 1; - vcpu->guest_mode = 0; + set_bit(KVM_REQ_KICK, &vcpu->requests); local_irq_enable(); /* @@ -644,9 +688,11 @@ again: */ barrier(); kvm_guest_exit(); - up_read(&vcpu->kvm->slots_lock); + vcpu->mode = OUTSIDE_GUEST_MODE; preempt_enable(); + idx = srcu_read_lock(&vcpu->kvm->srcu); + r = kvm_handle_exit(kvm_run, vcpu); if (r > 0) { @@ -655,12 +701,20 @@ again: } out: + srcu_read_unlock(&vcpu->kvm->srcu, idx); if (r > 0) { - kvm_resched(vcpu); + cond_resched(); + idx = srcu_read_lock(&vcpu->kvm->srcu); goto again; } return r; + +vcpu_run_fail: + local_irq_enable(); + preempt_enable(); + kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY; + goto out; } static void kvm_set_mmio_data(struct kvm_vcpu *vcpu) @@ -668,7 +722,7 @@ static void kvm_set_mmio_data(struct kvm_vcpu *vcpu) struct kvm_mmio_req *p = kvm_get_vcpu_ioreq(vcpu); if (!vcpu->mmio_is_write) - memcpy(&p->data, vcpu->mmio_data, 8); + memcpy(&p->data, vcpu->arch.mmio_data, 8); p->state = STATE_IORESP_READY; } @@ -677,8 +731,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) int r; sigset_t sigsaved; - vcpu_load(vcpu); - if (vcpu->sigset_active) sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved); @@ -690,7 +742,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } if (vcpu->mmio_needed) { - memcpy(vcpu->mmio_data, kvm_run->mmio.data, 8); + memcpy(vcpu->arch.mmio_data, kvm_run->mmio.data, 8); kvm_set_mmio_data(vcpu); vcpu->mmio_read_completed = 1; vcpu->mmio_needed = 0; @@ -700,11 +752,10 @@ out: if (vcpu->sigset_active) sigprocmask(SIG_SETMASK, &sigsaved, NULL); - vcpu_put(vcpu); return r; } -static struct kvm *kvm_alloc_kvm(void) +struct kvm *kvm_arch_alloc_vm(void) { struct kvm *kvm; @@ -715,7 +766,7 @@ static struct kvm *kvm_alloc_kvm(void) vm_base = __get_free_pages(GFP_KERNEL, get_order(KVM_VM_DATA_SIZE)); if (!vm_base) - return ERR_PTR(-ENOMEM); + return NULL; memset((void *)vm_base, 0, KVM_VM_DATA_SIZE); kvm = (struct kvm *)(vm_base + @@ -726,13 +777,13 @@ static struct kvm *kvm_alloc_kvm(void) return kvm; } -struct kvm_io_range { +struct kvm_ia64_io_range { unsigned long start; unsigned long size; unsigned long type; }; -static const struct kvm_io_range io_ranges[] = { +static const struct kvm_ia64_io_range io_ranges[] = { {VGA_IO_START, VGA_IO_SIZE, GPFN_FRAME_BUFFER}, {MMIO_START, MMIO_SIZE, GPFN_LOW_MMIO}, {LEGACY_IO_START, LEGACY_IO_SIZE, GPFN_LEGACY_IO}, @@ -761,10 +812,15 @@ static void kvm_build_io_pmt(struct kvm *kvm) #define GUEST_PHYSICAL_RR4 0x2739 #define VMM_INIT_RR 0x1660 -static void kvm_init_vm(struct kvm *kvm) +int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) { BUG_ON(!kvm); + if (type) + return -EINVAL; + + kvm->arch.is_sn2 = ia64_platform_is("sn2"); + kvm->arch.metaphysical_rr0 = GUEST_PHYSICAL_RR0; kvm->arch.metaphysical_rr4 = GUEST_PHYSICAL_RR4; kvm->arch.vmm_init_rr = VMM_INIT_RR; @@ -778,18 +834,8 @@ static void kvm_init_vm(struct kvm *kvm) /* Reserve bit 0 of irq_sources_bitmap for userspace irq source */ set_bit(KVM_USERSPACE_IRQ_SOURCE_ID, &kvm->arch.irq_sources_bitmap); -} - -struct kvm *kvm_arch_create_vm(void) -{ - struct kvm *kvm = kvm_alloc_kvm(); - - if (IS_ERR(kvm)) - return ERR_PTR(-ENOMEM); - kvm_init_vm(kvm); - - return kvm; + return 0; } static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm, @@ -800,8 +846,7 @@ static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm, r = 0; switch (chip->chip_id) { case KVM_IRQCHIP_IOAPIC: - memcpy(&chip->chip.ioapic, ioapic_irqchip(kvm), - sizeof(struct kvm_ioapic_state)); + r = kvm_get_ioapic(kvm, &chip->chip.ioapic); break; default: r = -EINVAL; @@ -817,9 +862,7 @@ static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) r = 0; switch (chip->chip_id) { case KVM_IRQCHIP_IOAPIC: - memcpy(ioapic_irqchip(kvm), - &chip->chip.ioapic, - sizeof(struct kvm_ioapic_state)); + r = kvm_set_ioapic(kvm, &chip->chip.ioapic); break; default: r = -EINVAL; @@ -835,8 +878,6 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) struct vpd *vpd = to_host(vcpu->kvm, vcpu->arch.vpd); int i; - vcpu_load(vcpu); - for (i = 0; i < 16; i++) { vpd->vgr[i] = regs->vpd.vgr[i]; vpd->vbgr[i] = regs->vpd.vbgr[i]; @@ -880,11 +921,21 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) RESTORE_REGS(saved_gp); vcpu->arch.irq_new_pending = 1; - vcpu->arch.itc_offset = regs->saved_itc - ia64_getreg(_IA64_REG_AR_ITC); + vcpu->arch.itc_offset = regs->saved_itc - kvm_get_itc(vcpu); set_bit(KVM_REQ_RESUME, &vcpu->requests); - vcpu_put(vcpu); + return 0; +} + +int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_event, + bool line_status) +{ + if (!irqchip_in_kernel(kvm)) + return -ENXIO; + irq_event->status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, + irq_event->irq, irq_event->level, + line_status); return 0; } @@ -893,48 +944,22 @@ long kvm_arch_vm_ioctl(struct file *filp, { struct kvm *kvm = filp->private_data; void __user *argp = (void __user *)arg; - int r = -EINVAL; + int r = -ENOTTY; switch (ioctl) { - case KVM_SET_MEMORY_REGION: { - struct kvm_memory_region kvm_mem; - struct kvm_userspace_memory_region kvm_userspace_mem; - - r = -EFAULT; - if (copy_from_user(&kvm_mem, argp, sizeof kvm_mem)) - goto out; - kvm_userspace_mem.slot = kvm_mem.slot; - kvm_userspace_mem.flags = kvm_mem.flags; - kvm_userspace_mem.guest_phys_addr = - kvm_mem.guest_phys_addr; - kvm_userspace_mem.memory_size = kvm_mem.memory_size; - r = kvm_vm_ioctl_set_memory_region(kvm, - &kvm_userspace_mem, 0); - if (r) - goto out; - break; - } case KVM_CREATE_IRQCHIP: r = -EFAULT; r = kvm_ioapic_init(kvm); if (r) goto out; - break; - case KVM_IRQ_LINE: { - struct kvm_irq_level irq_event; - - r = -EFAULT; - if (copy_from_user(&irq_event, argp, sizeof irq_event)) + r = kvm_setup_default_irq_routing(kvm); + if (r) { + mutex_lock(&kvm->slots_lock); + kvm_ioapic_destroy(kvm); + mutex_unlock(&kvm->slots_lock); goto out; - if (irqchip_in_kernel(kvm)) { - mutex_lock(&kvm->lock); - kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, - irq_event.irq, irq_event.level); - mutex_unlock(&kvm->lock); - r = 0; } break; - } case KVM_GET_IRQCHIP: { /* 0: PIC master, 1: PIC slave, 2: IOAPIC */ struct kvm_irqchip chip; @@ -1026,10 +1051,6 @@ static void kvm_free_vmm_area(void) } } -static void vti_vcpu_load(struct kvm_vcpu *vcpu, int cpu) -{ -} - static int vti_init_vpd(struct kvm_vcpu *vcpu) { int i; @@ -1125,6 +1146,11 @@ out: #define PALE_RESET_ENTRY 0x80000000ffffffb0UL +bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu) +{ + return irqchip_in_kernel(vcpu->kvm) == (vcpu->arch.apic != NULL); +} + int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) { struct kvm_vcpu *v; @@ -1141,14 +1167,14 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) if (IS_ERR(vmm_vcpu)) return PTR_ERR(vmm_vcpu); - if (vcpu->vcpu_id == 0) { + if (kvm_vcpu_is_bsp(vcpu)) { vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; /*Set entry address for first run.*/ regs->cr_iip = PALE_RESET_ENTRY; /*Initialize itc offset for vcpus*/ - itc_offset = 0UL - ia64_getreg(_IA64_REG_AR_ITC); + itc_offset = 0UL - kvm_get_itc(vcpu); for (i = 0; i < KVM_MAX_VCPUS; i++) { v = (struct kvm_vcpu *)((char *)vcpu + sizeof(struct kvm_vcpu_data) * i); @@ -1180,7 +1206,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) p_ctx->cr[2] = (unsigned long)kvm_vmm_info->vmm_ivt; p_ctx->cr[8] = 0x3c; - /*Initilize region register*/ + /*Initialize region register*/ p_ctx->rr[0] = 0x30; p_ctx->rr[1] = 0x30; p_ctx->rr[2] = 0x30; @@ -1189,7 +1215,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) p_ctx->rr[5] = 0x30; p_ctx->rr[7] = 0x30; - /*Initilize branch register 0*/ + /*Initialize branch register 0*/ p_ctx->br[0] = *(unsigned long *)kvm_vmm_info->vmm_entry; vcpu->arch.vmm_rr = kvm->arch.vmm_init_rr; @@ -1220,6 +1246,7 @@ static int vti_vcpu_setup(struct kvm_vcpu *vcpu, int id) local_irq_save(psr); r = kvm_insert_vmm_mapping(vcpu); + local_irq_restore(psr); if (r) goto fail; r = kvm_vcpu_init(vcpu, vcpu->kvm, id); @@ -1237,13 +1264,11 @@ static int vti_vcpu_setup(struct kvm_vcpu *vcpu, int id) goto uninit; kvm_purge_vmm_mapping(vcpu); - local_irq_restore(psr); return 0; uninit: kvm_vcpu_uninit(vcpu); fail: - local_irq_restore(psr); return r; } @@ -1274,7 +1299,6 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, vcpu->kvm = kvm; cpu = get_cpu(); - vti_vcpu_load(vcpu, cpu); r = vti_vcpu_setup(vcpu, id); put_cpu(); @@ -1293,6 +1317,11 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) return 0; } +int kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) +{ + return 0; +} + int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { return -EINVAL; @@ -1303,13 +1332,13 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) return -EINVAL; } -int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu, - struct kvm_debug_guest *dbg) +int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, + struct kvm_guest_debug *dbg) { return -EINVAL; } -static void free_kvm(struct kvm *kvm) +void kvm_arch_free_vm(struct kvm *kvm) { unsigned long vm_base = kvm->arch.vm_base; @@ -1322,14 +1351,12 @@ static void free_kvm(struct kvm *kvm) static void kvm_release_vm_pages(struct kvm *kvm) { + struct kvm_memslots *slots; struct kvm_memory_slot *memslot; - int i, j; - unsigned long base_gfn; - - for (i = 0; i < kvm->nmemslots; i++) { - memslot = &kvm->memslots[i]; - base_gfn = memslot->base_gfn; + int j; + slots = kvm_memslots(kvm); + kvm_for_each_memslot(memslot, slots) { for (j = 0; j < memslot->npages; j++) { if (memslot->rmap[j]) put_page((struct page *)memslot->rmap[j]); @@ -1344,13 +1371,9 @@ void kvm_arch_sync_events(struct kvm *kvm) void kvm_arch_destroy_vm(struct kvm *kvm) { kvm_iommu_unmap_guest(kvm); -#ifdef KVM_CAP_DEVICE_ASSIGNMENT kvm_free_all_assigned_devices(kvm); -#endif kfree(kvm->arch.vioapic); kvm_release_vm_pages(kvm); - kvm_free_physmem(kvm); - free_kvm(kvm); } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) @@ -1408,7 +1431,7 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) } for (i = 0; i < 4; i++) regs->insvc[i] = vcpu->arch.insvc[i]; - regs->saved_itc = vcpu->arch.itc_offset + ia64_getreg(_IA64_REG_AR_ITC); + regs->saved_itc = vcpu->arch.itc_offset + kvm_get_itc(vcpu); SAVE_REGS(xtp); SAVE_REGS(metaphysical_rr0); SAVE_REGS(metaphysical_rr4); @@ -1421,6 +1444,23 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) return 0; } +int kvm_arch_vcpu_ioctl_get_stack(struct kvm_vcpu *vcpu, + struct kvm_ia64_vcpu_stack *stack) +{ + memcpy(stack, vcpu, sizeof(struct kvm_ia64_vcpu_stack)); + return 0; +} + +int kvm_arch_vcpu_ioctl_set_stack(struct kvm_vcpu *vcpu, + struct kvm_ia64_vcpu_stack *stack) +{ + memcpy(vcpu + 1, &stack->stack[0] + sizeof(struct kvm_vcpu), + sizeof(struct kvm_ia64_vcpu_stack) - sizeof(struct kvm_vcpu)); + + vcpu->arch.exit_data = ((struct kvm_vcpu *)stack)->arch.exit_data; + return 0; +} + void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) { @@ -1430,20 +1470,110 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) long kvm_arch_vcpu_ioctl(struct file *filp, - unsigned int ioctl, unsigned long arg) + unsigned int ioctl, unsigned long arg) { - return -EINVAL; + struct kvm_vcpu *vcpu = filp->private_data; + void __user *argp = (void __user *)arg; + struct kvm_ia64_vcpu_stack *stack = NULL; + long r; + + switch (ioctl) { + case KVM_IA64_VCPU_GET_STACK: { + struct kvm_ia64_vcpu_stack __user *user_stack; + void __user *first_p = argp; + + r = -EFAULT; + if (copy_from_user(&user_stack, first_p, sizeof(void *))) + goto out; + + if (!access_ok(VERIFY_WRITE, user_stack, + sizeof(struct kvm_ia64_vcpu_stack))) { + printk(KERN_INFO "KVM_IA64_VCPU_GET_STACK: " + "Illegal user destination address for stack\n"); + goto out; + } + stack = kzalloc(sizeof(struct kvm_ia64_vcpu_stack), GFP_KERNEL); + if (!stack) { + r = -ENOMEM; + goto out; + } + + r = kvm_arch_vcpu_ioctl_get_stack(vcpu, stack); + if (r) + goto out; + + if (copy_to_user(user_stack, stack, + sizeof(struct kvm_ia64_vcpu_stack))) { + r = -EFAULT; + goto out; + } + + break; + } + case KVM_IA64_VCPU_SET_STACK: { + struct kvm_ia64_vcpu_stack __user *user_stack; + void __user *first_p = argp; + + r = -EFAULT; + if (copy_from_user(&user_stack, first_p, sizeof(void *))) + goto out; + + if (!access_ok(VERIFY_READ, user_stack, + sizeof(struct kvm_ia64_vcpu_stack))) { + printk(KERN_INFO "KVM_IA64_VCPU_SET_STACK: " + "Illegal user address for stack\n"); + goto out; + } + stack = kmalloc(sizeof(struct kvm_ia64_vcpu_stack), GFP_KERNEL); + if (!stack) { + r = -ENOMEM; + goto out; + } + if (copy_from_user(stack, user_stack, + sizeof(struct kvm_ia64_vcpu_stack))) + goto out; + + r = kvm_arch_vcpu_ioctl_set_stack(vcpu, stack); + break; + } + + default: + r = -EINVAL; + } + +out: + kfree(stack); + return r; } -int kvm_arch_set_memory_region(struct kvm *kvm, +int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf) +{ + return VM_FAULT_SIGBUS; +} + +void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, + struct kvm_memory_slot *dont) +{ +} + +int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, + unsigned long npages) +{ + return 0; +} + +void kvm_arch_memslots_updated(struct kvm *kvm) +{ +} + +int kvm_arch_prepare_memory_region(struct kvm *kvm, + struct kvm_memory_slot *memslot, struct kvm_userspace_memory_region *mem, - struct kvm_memory_slot old, - int user_alloc) + enum kvm_mr_change change) { unsigned long i; unsigned long pfn; - int npages = mem->memory_size >> PAGE_SHIFT; - struct kvm_memory_slot *memslot = &kvm->memslots[mem->slot]; + int npages = memslot->npages; unsigned long base_gfn = memslot->base_gfn; if (base_gfn + npages > (KVM_MAX_MEM_SIZE >> PAGE_SHIFT)) @@ -1467,12 +1597,27 @@ int kvm_arch_set_memory_region(struct kvm *kvm, return 0; } -void kvm_arch_flush_shadow(struct kvm *kvm) +void kvm_arch_commit_memory_region(struct kvm *kvm, + struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + enum kvm_mr_change change) +{ + return; +} + +void kvm_arch_flush_shadow_all(struct kvm *kvm) { + kvm_flush_remote_tlbs(kvm); +} + +void kvm_arch_flush_shadow_memslot(struct kvm *kvm, + struct kvm_memory_slot *slot) +{ + kvm_arch_flush_shadow_all(); } long kvm_arch_dev_ioctl(struct file *filp, - unsigned int ioctl, unsigned long arg) + unsigned int ioctl, unsigned long arg) { return -EINVAL; } @@ -1511,8 +1656,37 @@ out: return 0; } + +/* + * On SN2, the ITC isn't stable, so copy in fast path code to use the + * SN2 RTC, replacing the ITC based default verion. + */ +static void kvm_patch_vmm(struct kvm_vmm_info *vmm_info, + struct module *module) +{ + unsigned long new_ar, new_ar_sn2; + unsigned long module_base; + + if (!ia64_platform_is("sn2")) + return; + + module_base = (unsigned long)module->module_core; + + new_ar = kvm_vmm_base + vmm_info->patch_mov_ar - module_base; + new_ar_sn2 = kvm_vmm_base + vmm_info->patch_mov_ar_sn2 - module_base; + + printk(KERN_INFO "kvm: Patching ITC emulation to use SGI SN2 RTC " + "as source\n"); + + /* + * Copy the SN2 version of mov_ar into place. They are both + * the same size, so 6 bundles is sufficient (6 * 0x10). + */ + memcpy((void *)new_ar, (void *)new_ar_sn2, 0x60); +} + static int kvm_relocate_vmm(struct kvm_vmm_info *vmm_info, - struct module *module) + struct module *module) { unsigned long module_base; unsigned long vmm_size; @@ -1523,7 +1697,7 @@ static int kvm_relocate_vmm(struct kvm_vmm_info *vmm_info, BUG_ON(!module); if (!kvm_vmm_base) { - printk("kvm: kvm area hasn't been initilized yet!!\n"); + printk("kvm: kvm area hasn't been initialized yet!!\n"); return -EFAULT; } @@ -1534,6 +1708,7 @@ static int kvm_relocate_vmm(struct kvm_vmm_info *vmm_info, return -EFAULT; memcpy((void *)kvm_vmm_base, (void *)module_base, vmm_size); + kvm_patch_vmm(vmm_info, module); kvm_flush_icache(kvm_vmm_base, vmm_size); /*Recalculate kvm_vmm_info based on new VMM*/ @@ -1617,50 +1792,46 @@ void kvm_arch_exit(void) kvm_vmm_info = NULL; } -static int kvm_ia64_sync_dirty_log(struct kvm *kvm, - struct kvm_dirty_log *log) +static void kvm_ia64_sync_dirty_log(struct kvm *kvm, + struct kvm_memory_slot *memslot) { - struct kvm_memory_slot *memslot; - int r, i; - long n, base; + int i; + long base; + unsigned long n; unsigned long *dirty_bitmap = (unsigned long *)(kvm->arch.vm_base + offsetof(struct kvm_vm_data, kvm_mem_dirty_log)); - r = -EINVAL; - if (log->slot >= KVM_MEMORY_SLOTS) - goto out; - - memslot = &kvm->memslots[log->slot]; - r = -ENOENT; - if (!memslot->dirty_bitmap) - goto out; - - n = ALIGN(memslot->npages, BITS_PER_LONG) / 8; + n = kvm_dirty_bitmap_bytes(memslot); base = memslot->base_gfn / BITS_PER_LONG; + spin_lock(&kvm->arch.dirty_log_lock); for (i = 0; i < n/sizeof(long); ++i) { memslot->dirty_bitmap[i] = dirty_bitmap[base + i]; dirty_bitmap[base + i] = 0; } - r = 0; -out: - return r; + spin_unlock(&kvm->arch.dirty_log_lock); } int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) { int r; - int n; + unsigned long n; struct kvm_memory_slot *memslot; int is_dirty = 0; - spin_lock(&kvm->arch.dirty_log_lock); + mutex_lock(&kvm->slots_lock); - r = kvm_ia64_sync_dirty_log(kvm, log); - if (r) + r = -EINVAL; + if (log->slot >= KVM_USER_MEM_SLOTS) goto out; + memslot = id_to_memslot(kvm->memslots, log->slot); + r = -ENOENT; + if (!memslot->dirty_bitmap) + goto out; + + kvm_ia64_sync_dirty_log(kvm, memslot); r = kvm_get_dirty_log(kvm, log, &is_dirty); if (r) goto out; @@ -1668,13 +1839,12 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, /* If nothing is dirty, don't bother messing with page tables. */ if (is_dirty) { kvm_flush_remote_tlbs(kvm); - memslot = &kvm->memslots[log->slot]; - n = ALIGN(memslot->npages, BITS_PER_LONG) / 8; + n = kvm_dirty_bitmap_bytes(memslot); memset(memslot->dirty_bitmap, 0, n); } r = 0; out: - spin_unlock(&kvm->arch.dirty_log_lock); + mutex_unlock(&kvm->slots_lock); return r; } @@ -1687,38 +1857,9 @@ void kvm_arch_hardware_unsetup(void) { } -static void vcpu_kick_intr(void *info) +int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq) { -#ifdef DEBUG - struct kvm_vcpu *vcpu = (struct kvm_vcpu *)info; - printk(KERN_DEBUG"vcpu_kick_intr %p \n", vcpu); -#endif -} - -void kvm_vcpu_kick(struct kvm_vcpu *vcpu) -{ - int ipi_pcpu = vcpu->cpu; - int cpu = get_cpu(); - - if (waitqueue_active(&vcpu->wq)) - wake_up_interruptible(&vcpu->wq); - - if (vcpu->guest_mode && cpu != ipi_pcpu) - smp_call_function_single(ipi_pcpu, vcpu_kick_intr, vcpu, 0); - put_cpu(); -} - -int kvm_apic_set_irq(struct kvm_vcpu *vcpu, u8 vec, u8 trig) -{ - - struct vpd *vpd = to_host(vcpu->kvm, vcpu->arch.vpd); - - if (!test_and_set_bit(vec, &vpd->irr[0])) { - vcpu->arch.irq_new_pending = 1; - kvm_vcpu_kick(vcpu); - return 1; - } - return 0; + return __apic_accept_irq(vcpu, irq->vector); } int kvm_apic_match_physical_addr(struct kvm_lapic *apic, u16 dest) @@ -1731,20 +1872,18 @@ int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda) return 0; } -struct kvm_vcpu *kvm_get_lowest_prio_vcpu(struct kvm *kvm, u8 vector, - unsigned long bitmap) +int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2) { - struct kvm_vcpu *lvcpu = kvm->vcpus[0]; - int i; - - for (i = 1; i < KVM_MAX_VCPUS; i++) { - if (!kvm->vcpus[i]) - continue; - if (lvcpu->arch.xtp > kvm->vcpus[i]->arch.xtp) - lvcpu = kvm->vcpus[i]; - } + return vcpu1->arch.xtp - vcpu2->arch.xtp; +} - return lvcpu; +int kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, + int short_hand, int dest, int dest_mode) +{ + struct kvm_lapic *target = vcpu->arch.apic; + return (dest_mode == 0) ? + kvm_apic_match_physical_addr(target, dest) : + kvm_apic_match_logical_addr(target, dest); } static int find_highest_bits(int *dat) @@ -1776,34 +1915,26 @@ int kvm_highest_pending_irq(struct kvm_vcpu *vcpu) return find_highest_bits((int *)&vpd->irr[0]); } -int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu) -{ - if (kvm_highest_pending_irq(vcpu) != -1) - return 1; - return 0; -} - int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) { return vcpu->arch.timer_fired; } -gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn) +int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) { - return gfn; + return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE) || + (kvm_highest_pending_irq(vcpu) != -1); } -int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) +int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) { - return vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE; + return (!test_and_set_bit(KVM_REQ_KICK, &vcpu->requests)); } int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { - vcpu_load(vcpu); mp_state->mp_state = vcpu->arch.mp_state; - vcpu_put(vcpu); return 0; } @@ -1813,6 +1944,7 @@ static int vcpu_reset(struct kvm_vcpu *vcpu) long psr; local_irq_save(psr); r = kvm_insert_vmm_mapping(vcpu); + local_irq_restore(psr); if (r) goto fail; @@ -1825,7 +1957,6 @@ static int vcpu_reset(struct kvm_vcpu *vcpu) kvm_purge_vmm_mapping(vcpu); r = 0; fail: - local_irq_restore(psr); return r; } @@ -1834,10 +1965,8 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, { int r = 0; - vcpu_load(vcpu); vcpu->arch.mp_state = mp_state->mp_state; if (vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED) r = vcpu_reset(vcpu); - vcpu_put(vcpu); return r; } |