+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) && defined(CONFIG_IOTHREAD)
+ 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_word(ioeventfds[i], 0, i, 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_word(ioeventfds[i], 0, i, false);
+ close(ioeventfds[i]);
+ }
+ return ret;
+#else
+ return 0;
+#endif
+}
+
+static const KVMCapabilityInfo *
+kvm_check_extension_list(KVMState *s, const KVMCapabilityInfo *list)
+{
+ while (list->name) {
+ if (!kvm_check_extension(s, list->value)) {
+ return list;
+ }
+ list++;
+ }
+ return NULL;
+}
+
+static void kvm_set_phys_mem(target_phys_addr_t start_addr, ram_addr_t size,
+ ram_addr_t phys_offset, bool log_dirty)
+{
+ KVMState *s = kvm_state;
+ ram_addr_t flags = phys_offset & ~TARGET_PAGE_MASK;
+ KVMSlot *mem, old;
+ int err;
+
+ /* kvm works in page size chunks, but the function may be called
+ with sub-page size and unaligned start address. */
+ size = TARGET_PAGE_ALIGN(size);
+ start_addr = TARGET_PAGE_ALIGN(start_addr);
+
+ /* KVM does not support read-only slots */
+ phys_offset &= ~IO_MEM_ROM;
+
+ while (1) {
+ mem = kvm_lookup_overlapping_slot(s, start_addr, start_addr + size);
+ if (!mem) {
+ break;
+ }
+
+ if (flags < IO_MEM_UNASSIGNED && start_addr >= mem->start_addr &&
+ (start_addr + size <= mem->start_addr + mem->memory_size) &&
+ (phys_offset - start_addr == mem->phys_offset - mem->start_addr)) {
+ /* The new slot fits into the existing one and comes with
+ * identical parameters - update flags and done. */
+ kvm_slot_dirty_pages_log_change(mem, log_dirty);
+ return;
+ }
+
+ old = *mem;
+
+ /* unregister the overlapping slot */
+ mem->memory_size = 0;
+ err = kvm_set_user_memory_region(s, mem);
+ if (err) {
+ fprintf(stderr, "%s: error unregistering overlapping slot: %s\n",
+ __func__, strerror(-err));
+ abort();
+ }
+
+ /* Workaround for older KVM versions: we can't join slots, even not by
+ * unregistering the previous ones and then registering the larger
+ * slot. We have to maintain the existing fragmentation. Sigh.
+ *
+ * This workaround assumes that the new slot starts at the same
+ * address as the first existing one. If not or if some overlapping
+ * slot comes around later, we will fail (not seen in practice so far)
+ * - and actually require a recent KVM version. */
+ if (s->broken_set_mem_region &&
+ old.start_addr == start_addr && old.memory_size < size &&
+ flags < IO_MEM_UNASSIGNED) {
+ mem = kvm_alloc_slot(s);
+ mem->memory_size = old.memory_size;
+ mem->start_addr = old.start_addr;
+ mem->phys_offset = old.phys_offset;
+ mem->flags = kvm_mem_flags(s, log_dirty);
+
+ err = kvm_set_user_memory_region(s, mem);
+ if (err) {
+ fprintf(stderr, "%s: error updating slot: %s\n", __func__,
+ strerror(-err));
+ abort();
+ }
+
+ start_addr += old.memory_size;
+ phys_offset += old.memory_size;
+ size -= old.memory_size;
+ continue;
+ }
+
+ /* register prefix slot */
+ if (old.start_addr < start_addr) {
+ mem = kvm_alloc_slot(s);
+ mem->memory_size = start_addr - old.start_addr;
+ mem->start_addr = old.start_addr;
+ mem->phys_offset = old.phys_offset;
+ mem->flags = kvm_mem_flags(s, log_dirty);
+
+ err = kvm_set_user_memory_region(s, mem);
+ if (err) {
+ fprintf(stderr, "%s: error registering prefix slot: %s\n",
+ __func__, strerror(-err));
+#ifdef TARGET_PPC
+ fprintf(stderr, "%s: This is probably because your kernel's " \
+ "PAGE_SIZE is too big. Please try to use 4k " \
+ "PAGE_SIZE!\n", __func__);
+#endif
+ abort();
+ }
+ }
+
+ /* register suffix slot */
+ if (old.start_addr + old.memory_size > start_addr + size) {
+ ram_addr_t size_delta;
+
+ mem = kvm_alloc_slot(s);
+ mem->start_addr = start_addr + size;
+ size_delta = mem->start_addr - old.start_addr;
+ mem->memory_size = old.memory_size - size_delta;
+ mem->phys_offset = old.phys_offset + size_delta;
+ mem->flags = kvm_mem_flags(s, log_dirty);
+
+ err = kvm_set_user_memory_region(s, mem);
+ if (err) {
+ fprintf(stderr, "%s: error registering suffix slot: %s\n",
+ __func__, strerror(-err));
+ abort();
+ }
+ }
+ }
+
+ /* in case the KVM bug workaround already "consumed" the new slot */
+ if (!size) {
+ return;
+ }
+ /* KVM does not need to know about this memory */
+ if (flags >= IO_MEM_UNASSIGNED) {
+ return;
+ }
+ mem = kvm_alloc_slot(s);
+ mem->memory_size = size;
+ mem->start_addr = start_addr;
+ mem->phys_offset = phys_offset;
+ mem->flags = kvm_mem_flags(s, log_dirty);
+
+ err = kvm_set_user_memory_region(s, mem);
+ if (err) {
+ fprintf(stderr, "%s: error registering slot: %s\n", __func__,
+ strerror(-err));
+ abort();
+ }
+}
+
+static void kvm_client_set_memory(struct CPUPhysMemoryClient *client,
+ target_phys_addr_t start_addr,
+ ram_addr_t size, ram_addr_t phys_offset,
+ bool log_dirty)
+{
+ kvm_set_phys_mem(start_addr, size, phys_offset, log_dirty);
+}
+
+static int kvm_client_sync_dirty_bitmap(struct CPUPhysMemoryClient *client,
+ target_phys_addr_t start_addr,
+ target_phys_addr_t end_addr)
+{
+ return kvm_physical_sync_dirty_bitmap(start_addr, end_addr);
+}
+
+static int kvm_client_migration_log(struct CPUPhysMemoryClient *client,
+ int enable)
+{
+ return kvm_set_migration_log(enable);
+}
+
+static CPUPhysMemoryClient kvm_cpu_phys_memory_client = {
+ .set_memory = kvm_client_set_memory,
+ .sync_dirty_bitmap = kvm_client_sync_dirty_bitmap,
+ .migration_log = kvm_client_migration_log,
+ .log_start = kvm_log_start,
+ .log_stop = kvm_log_stop,
+};
+
+static void kvm_handle_interrupt(CPUState *env, int mask)
+{
+ env->interrupt_request |= mask;
+
+ if (!qemu_cpu_is_self(env)) {
+ qemu_cpu_kick(env);
+ }
+}
+
+int kvm_init(void)