diff options
Diffstat (limited to 'accel/kvm/kvm-all.c')
| -rw-r--r-- | accel/kvm/kvm-all.c | 231 |
1 files changed, 25 insertions, 206 deletions
diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c index 3f7eafe08c..e39a810a4e 100644 --- a/accel/kvm/kvm-all.c +++ b/accel/kvm/kvm-all.c @@ -90,8 +90,6 @@ bool kvm_kernel_irqchip; bool kvm_split_irqchip; bool kvm_async_interrupts_allowed; bool kvm_halt_in_kernel_allowed; -bool kvm_eventfds_allowed; -bool kvm_irqfds_allowed; bool kvm_resamplefds_allowed; bool kvm_msi_via_irqfd_allowed; bool kvm_gsi_routing_allowed; @@ -99,8 +97,6 @@ bool kvm_gsi_direct_mapping; bool kvm_allowed; bool kvm_readonly_mem_allowed; bool kvm_vm_attributes_allowed; -bool kvm_direct_msi_allowed; -bool kvm_ioeventfd_any_length_allowed; bool kvm_msi_use_devid; bool kvm_has_guest_debug; static int kvm_sstep_flags; @@ -111,6 +107,9 @@ static const KVMCapabilityInfo kvm_required_capabilites[] = { KVM_CAP_INFO(USER_MEMORY), KVM_CAP_INFO(DESTROY_MEMORY_REGION_WORKS), KVM_CAP_INFO(JOIN_MEMORY_REGIONS_WORKS), + KVM_CAP_INFO(INTERNAL_ERROR_DATA), + KVM_CAP_INFO(IOEVENTFD), + KVM_CAP_INFO(IOEVENTFD_ANY_LENGTH), KVM_CAP_LAST_INFO }; @@ -1106,13 +1105,6 @@ static void kvm_coalesce_pio_del(MemoryListener *listener, } } -static MemoryListener kvm_coalesced_pio_listener = { - .name = "kvm-coalesced-pio", - .coalesced_io_add = kvm_coalesce_pio_add, - .coalesced_io_del = kvm_coalesce_pio_del, - .priority = MEMORY_LISTENER_PRIORITY_MIN, -}; - int kvm_check_extension(KVMState *s, unsigned int extension) { int ret; @@ -1254,43 +1246,6 @@ static int kvm_set_ioeventfd_pio(int fd, uint16_t addr, uint16_t val, } -static int kvm_check_many_ioeventfds(void) -{ - /* Userspace can use ioeventfd for io notification. This requires a host - * that supports eventfd(2) and an I/O thread; since eventfd does not - * support SIGIO it cannot interrupt the vcpu. - * - * Older kernels have a 6 device limit on the KVM io bus. Find out so we - * can avoid creating too many ioeventfds. - */ -#if defined(CONFIG_EVENTFD) - int ioeventfds[7]; - int i, ret = 0; - for (i = 0; i < ARRAY_SIZE(ioeventfds); i++) { - ioeventfds[i] = eventfd(0, EFD_CLOEXEC); - if (ioeventfds[i] < 0) { - break; - } - ret = kvm_set_ioeventfd_pio(ioeventfds[i], 0, i, true, 2, true); - if (ret < 0) { - close(ioeventfds[i]); - break; - } - } - - /* Decide whether many devices are supported or not */ - ret = i == ARRAY_SIZE(ioeventfds); - - while (i-- > 0) { - kvm_set_ioeventfd_pio(ioeventfds[i], 0, i, false, 2, true); - close(ioeventfds[i]); - } - return ret; -#else - return 0; -#endif -} - static const KVMCapabilityInfo * kvm_check_extension_list(KVMState *s, const KVMCapabilityInfo *list) { @@ -1806,6 +1761,8 @@ void kvm_memory_listener_register(KVMState *s, KVMMemoryListener *kml, static MemoryListener kvm_io_listener = { .name = "kvm-io", + .coalesced_io_add = kvm_coalesce_pio_add, + .coalesced_io_del = kvm_coalesce_pio_del, .eventfd_add = kvm_io_ioeventfd_add, .eventfd_del = kvm_io_ioeventfd_del, .priority = MEMORY_LISTENER_PRIORITY_DEV_BACKEND, @@ -1847,7 +1804,7 @@ static void clear_gsi(KVMState *s, unsigned int gsi) void kvm_init_irq_routing(KVMState *s) { - int gsi_count, i; + int gsi_count; gsi_count = kvm_check_extension(s, KVM_CAP_IRQ_ROUTING) - 1; if (gsi_count > 0) { @@ -1859,12 +1816,6 @@ void kvm_init_irq_routing(KVMState *s) s->irq_routes = g_malloc0(sizeof(*s->irq_routes)); s->nr_allocated_irq_routes = 0; - if (!kvm_direct_msi_allowed) { - for (i = 0; i < KVM_MSI_HASHTAB_SIZE; i++) { - QTAILQ_INIT(&s->msi_hashtab[i]); - } - } - kvm_arch_init_irq_routing(s); } @@ -1984,41 +1935,10 @@ void kvm_irqchip_change_notify(void) notifier_list_notify(&kvm_irqchip_change_notifiers, NULL); } -static unsigned int kvm_hash_msi(uint32_t data) -{ - /* This is optimized for IA32 MSI layout. However, no other arch shall - * repeat the mistake of not providing a direct MSI injection API. */ - return data & 0xff; -} - -static void kvm_flush_dynamic_msi_routes(KVMState *s) -{ - KVMMSIRoute *route, *next; - unsigned int hash; - - for (hash = 0; hash < KVM_MSI_HASHTAB_SIZE; hash++) { - QTAILQ_FOREACH_SAFE(route, &s->msi_hashtab[hash], entry, next) { - kvm_irqchip_release_virq(s, route->kroute.gsi); - QTAILQ_REMOVE(&s->msi_hashtab[hash], route, entry); - g_free(route); - } - } -} - static int kvm_irqchip_get_virq(KVMState *s) { int next_virq; - /* - * PIC and IOAPIC share the first 16 GSI numbers, thus the available - * GSI numbers are more than the number of IRQ route. Allocating a GSI - * number can succeed even though a new route entry cannot be added. - * When this happens, flush dynamic MSI entries to free IRQ route entries. - */ - if (!kvm_direct_msi_allowed && s->irq_routes->nr == s->gsi_count) { - kvm_flush_dynamic_msi_routes(s); - } - /* Return the lowest unused GSI in the bitmap */ next_virq = find_first_zero_bit(s->used_gsi_bitmap, s->gsi_count); if (next_virq >= s->gsi_count) { @@ -2028,63 +1948,17 @@ static int kvm_irqchip_get_virq(KVMState *s) } } -static KVMMSIRoute *kvm_lookup_msi_route(KVMState *s, MSIMessage msg) -{ - unsigned int hash = kvm_hash_msi(msg.data); - KVMMSIRoute *route; - - QTAILQ_FOREACH(route, &s->msi_hashtab[hash], entry) { - if (route->kroute.u.msi.address_lo == (uint32_t)msg.address && - route->kroute.u.msi.address_hi == (msg.address >> 32) && - route->kroute.u.msi.data == le32_to_cpu(msg.data)) { - return route; - } - } - return NULL; -} - int kvm_irqchip_send_msi(KVMState *s, MSIMessage msg) { struct kvm_msi msi; - KVMMSIRoute *route; - - if (kvm_direct_msi_allowed) { - msi.address_lo = (uint32_t)msg.address; - msi.address_hi = msg.address >> 32; - msi.data = le32_to_cpu(msg.data); - msi.flags = 0; - memset(msi.pad, 0, sizeof(msi.pad)); - return kvm_vm_ioctl(s, KVM_SIGNAL_MSI, &msi); - } - - route = kvm_lookup_msi_route(s, msg); - if (!route) { - int virq; - - virq = kvm_irqchip_get_virq(s); - if (virq < 0) { - return virq; - } + msi.address_lo = (uint32_t)msg.address; + msi.address_hi = msg.address >> 32; + msi.data = le32_to_cpu(msg.data); + msi.flags = 0; + memset(msi.pad, 0, sizeof(msi.pad)); - route = g_new0(KVMMSIRoute, 1); - route->kroute.gsi = virq; - route->kroute.type = KVM_IRQ_ROUTING_MSI; - route->kroute.flags = 0; - route->kroute.u.msi.address_lo = (uint32_t)msg.address; - route->kroute.u.msi.address_hi = msg.address >> 32; - route->kroute.u.msi.data = le32_to_cpu(msg.data); - - kvm_add_routing_entry(s, &route->kroute); - kvm_irqchip_commit_routes(s); - - QTAILQ_INSERT_TAIL(&s->msi_hashtab[kvm_hash_msi(msg.data)], route, - entry); - } - - assert(route->kroute.type == KVM_IRQ_ROUTING_MSI); - - return kvm_set_irq(s, route->kroute.gsi, 1); + return kvm_vm_ioctl(s, KVM_SIGNAL_MSI, &msi); } int kvm_irqchip_add_msi_route(KVMRouteChange *c, int vector, PCIDevice *dev) @@ -2211,10 +2085,6 @@ static int kvm_irqchip_assign_irqfd(KVMState *s, EventNotifier *event, } } - if (!kvm_irqfds_enabled()) { - return -ENOSYS; - } - return kvm_vm_ioctl(s, KVM_IRQFD, &irqfd); } @@ -2375,6 +2245,11 @@ static void kvm_irqchip_create(KVMState *s) return; } + if (kvm_check_extension(s, KVM_CAP_IRQFD) <= 0) { + fprintf(stderr, "kvm: irqfd not implemented\n"); + exit(1); + } + /* First probe and see if there's a arch-specific hook to create the * in-kernel irqchip for us */ ret = kvm_arch_irqchip_create(s); @@ -2649,22 +2524,8 @@ static int kvm_init(MachineState *ms) #ifdef KVM_CAP_VCPU_EVENTS s->vcpu_events = kvm_check_extension(s, KVM_CAP_VCPU_EVENTS); #endif - - s->robust_singlestep = - kvm_check_extension(s, KVM_CAP_X86_ROBUST_SINGLESTEP); - -#ifdef KVM_CAP_DEBUGREGS - s->debugregs = kvm_check_extension(s, KVM_CAP_DEBUGREGS); -#endif - s->max_nested_state_len = kvm_check_extension(s, KVM_CAP_NESTED_STATE); -#ifdef KVM_CAP_IRQ_ROUTING - kvm_direct_msi_allowed = (kvm_check_extension(s, KVM_CAP_SIGNAL_MSI) > 0); -#endif - - s->intx_set_mask = kvm_check_extension(s, KVM_CAP_PCI_2_3); - s->irq_set_ioctl = KVM_IRQ_LINE; if (kvm_check_extension(s, KVM_CAP_IRQ_INJECT_STATUS)) { s->irq_set_ioctl = KVM_IRQ_LINE_STATUS; @@ -2673,21 +2534,12 @@ static int kvm_init(MachineState *ms) kvm_readonly_mem_allowed = (kvm_check_extension(s, KVM_CAP_READONLY_MEM) > 0); - kvm_eventfds_allowed = - (kvm_check_extension(s, KVM_CAP_IOEVENTFD) > 0); - - kvm_irqfds_allowed = - (kvm_check_extension(s, KVM_CAP_IRQFD) > 0); - kvm_resamplefds_allowed = (kvm_check_extension(s, KVM_CAP_IRQFD_RESAMPLE) > 0); kvm_vm_attributes_allowed = (kvm_check_extension(s, KVM_CAP_VM_ATTRIBUTES) > 0); - kvm_ioeventfd_any_length_allowed = - (kvm_check_extension(s, KVM_CAP_IOEVENTFD_ANY_LENGTH) > 0); - #ifdef KVM_CAP_SET_GUEST_DEBUG kvm_has_guest_debug = (kvm_check_extension(s, KVM_CAP_SET_GUEST_DEBUG) > 0); @@ -2724,24 +2576,16 @@ static int kvm_init(MachineState *ms) kvm_irqchip_create(s); } - if (kvm_eventfds_allowed) { - s->memory_listener.listener.eventfd_add = kvm_mem_ioeventfd_add; - s->memory_listener.listener.eventfd_del = kvm_mem_ioeventfd_del; - } + s->memory_listener.listener.eventfd_add = kvm_mem_ioeventfd_add; + s->memory_listener.listener.eventfd_del = kvm_mem_ioeventfd_del; s->memory_listener.listener.coalesced_io_add = kvm_coalesce_mmio_region; s->memory_listener.listener.coalesced_io_del = kvm_uncoalesce_mmio_region; kvm_memory_listener_register(s, &s->memory_listener, &address_space_memory, 0, "kvm-memory"); - if (kvm_eventfds_allowed) { - memory_listener_register(&kvm_io_listener, - &address_space_io); - } - memory_listener_register(&kvm_coalesced_pio_listener, + memory_listener_register(&kvm_io_listener, &address_space_io); - s->many_ioeventfds = kvm_check_many_ioeventfds(); - s->sync_mmu = !!kvm_vm_check_extension(kvm_state, KVM_CAP_SYNC_MMU); if (!s->sync_mmu) { ret = ram_block_discard_disable(true); @@ -2794,16 +2638,14 @@ static void kvm_handle_io(uint16_t port, MemTxAttrs attrs, void *data, int direc static int kvm_handle_internal_error(CPUState *cpu, struct kvm_run *run) { + int i; + fprintf(stderr, "KVM internal error. Suberror: %d\n", run->internal.suberror); - if (kvm_check_extension(kvm_state, KVM_CAP_INTERNAL_ERROR_DATA)) { - int i; - - for (i = 0; i < run->internal.ndata; ++i) { - fprintf(stderr, "extra data[%d]: 0x%016"PRIx64"\n", - i, (uint64_t)run->internal.data[i]); - } + for (i = 0; i < run->internal.ndata; ++i) { + fprintf(stderr, "extra data[%d]: 0x%016"PRIx64"\n", + i, (uint64_t)run->internal.data[i]); } if (run->internal.suberror == KVM_INTERNAL_ERROR_EMULATION) { fprintf(stderr, "emulation failure\n"); @@ -3297,29 +3139,11 @@ int kvm_has_vcpu_events(void) return kvm_state->vcpu_events; } -int kvm_has_robust_singlestep(void) -{ - return kvm_state->robust_singlestep; -} - -int kvm_has_debugregs(void) -{ - return kvm_state->debugregs; -} - int kvm_max_nested_state_length(void) { return kvm_state->max_nested_state_len; } -int kvm_has_many_ioeventfds(void) -{ - if (!kvm_enabled()) { - return 0; - } - return kvm_state->many_ioeventfds; -} - int kvm_has_gsi_routing(void) { #ifdef KVM_CAP_IRQ_ROUTING @@ -3329,11 +3153,6 @@ int kvm_has_gsi_routing(void) #endif } -int kvm_has_intx_set_mask(void) -{ - return kvm_state->intx_set_mask; -} - bool kvm_arm_supports_user_irq(void) { return kvm_check_extension(kvm_state, KVM_CAP_ARM_USER_IRQ); |