#include "qemu/option.h"
#include "qemu/config-file.h"
#include "sysemu/sysemu.h"
+#include "sysemu/accel.h"
#include "hw/hw.h"
#include "hw/pci/msi.h"
#include "hw/s390x/adapter.h"
#include <sys/eventfd.h>
#endif
-#ifdef CONFIG_VALGRIND_H
-#include <valgrind/memcheck.h>
-#endif
-
/* KVM uses PAGE_SIZE in its definition of COALESCED_MMIO_MAX */
#define PAGE_SIZE TARGET_PAGE_SIZE
struct KVMState
{
+ AccelState parent_obj;
+
KVMSlot *slots;
int nr_slots;
int fd;
#endif
};
+#define TYPE_KVM_ACCEL ACCEL_CLASS_NAME("kvm")
+
+#define KVM_STATE(obj) \
+ OBJECT_CHECK(KVMState, (obj), TYPE_KVM_ACCEL)
+
KVMState *kvm_state;
bool kvm_kernel_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;
bool kvm_gsi_direct_mapping;
bool kvm_allowed;
bool kvm_readonly_mem_allowed;
+bool kvm_vm_attributes_allowed;
static const KVMCapabilityInfo kvm_required_capabilites[] = {
KVM_CAP_INFO(USER_MEMORY),
KVM_CAP_LAST_INFO
};
-static KVMSlot *kvm_alloc_slot(KVMState *s)
+static KVMSlot *kvm_get_free_slot(KVMState *s)
{
int i;
}
}
+ return NULL;
+}
+
+bool kvm_has_free_slot(MachineState *ms)
+{
+ return kvm_get_free_slot(KVM_STATE(ms->accelerator));
+}
+
+static KVMSlot *kvm_alloc_slot(KVMState *s)
+{
+ KVMSlot *slot = kvm_get_free_slot(s);
+
+ if (slot) {
+ return slot;
+ }
+
fprintf(stderr, "%s: no free slot available\n", __func__);
abort();
}
}
}
-static int kvm_set_migration_log(int enable)
+static int kvm_set_migration_log(bool enable)
{
KVMState *s = kvm_state;
KVMSlot *mem;
{
KVMState *s = kvm_state;
unsigned long size, allocated_size = 0;
- KVMDirtyLog d;
+ KVMDirtyLog d = {};
KVMSlot *mem;
int ret = 0;
hwaddr start_addr = section->offset_within_address_space;
return ret;
}
+static uint32_t adjust_ioeventfd_endianness(uint32_t val, uint32_t size)
+{
+#if defined(HOST_WORDS_BIGENDIAN) != defined(TARGET_WORDS_BIGENDIAN)
+ /* The kernel expects ioeventfd values in HOST_WORDS_BIGENDIAN
+ * endianness, but the memory core hands them in target endianness.
+ * For example, PPC is always treated as big-endian even if running
+ * on KVM and on PPC64LE. Correct here.
+ */
+ switch (size) {
+ case 2:
+ val = bswap16(val);
+ break;
+ case 4:
+ val = bswap32(val);
+ break;
+ }
+#endif
+ return val;
+}
+
static int kvm_set_ioeventfd_mmio(int fd, hwaddr addr, uint32_t val,
bool assign, uint32_t size, bool datamatch)
{
int ret;
- struct kvm_ioeventfd iofd;
-
- iofd.datamatch = datamatch ? val : 0;
- iofd.addr = addr;
- iofd.len = size;
- iofd.flags = 0;
- iofd.fd = fd;
+ struct kvm_ioeventfd iofd = {
+ .datamatch = datamatch ? adjust_ioeventfd_endianness(val, size) : 0,
+ .addr = addr,
+ .len = size,
+ .flags = 0,
+ .fd = fd,
+ };
if (!kvm_enabled()) {
return -ENOSYS;
bool assign, uint32_t size, bool datamatch)
{
struct kvm_ioeventfd kick = {
- .datamatch = datamatch ? val : 0,
+ .datamatch = datamatch ? adjust_ioeventfd_endianness(val, size) : 0,
.addr = addr,
.flags = KVM_IOEVENTFD_FLAG_PIO,
.len = size,
unsigned delta;
/* kvm works in page size chunks, but the function may be called
- with sub-page size and unaligned start address. */
- delta = TARGET_PAGE_ALIGN(size) - size;
+ with sub-page size and unaligned start address. Pad the start
+ address to next and truncate size to previous page boundary. */
+ delta = (TARGET_PAGE_SIZE - (start_addr & ~TARGET_PAGE_MASK));
+ delta &= ~TARGET_PAGE_MASK;
if (delta > size) {
return;
}
old = *mem;
- if (mem->flags & KVM_MEM_LOG_DIRTY_PAGES) {
+ if ((mem->flags & KVM_MEM_LOG_DIRTY_PAGES) || s->migration_log) {
kvm_physical_sync_dirty_bitmap(section);
}
{
uint32_t *word = s->used_gsi_bitmap;
int max_words = ALIGN(s->gsi_count, 32) / 32;
- int i, bit;
+ int i, zeroes;
bool retry = true;
again:
/* Return the lowest unused GSI in the bitmap */
for (i = 0; i < max_words; i++) {
- bit = ffs(~word[i]);
- if (!bit) {
+ zeroes = ctz32(~word[i]);
+ if (zeroes == 32) {
continue;
}
- return bit - 1 + i * 32;
+ return zeroes + i * 32;
}
if (!s->direct_msi && retry) {
retry = false;
kroute.u.msi.address_lo = (uint32_t)msg.address;
kroute.u.msi.address_hi = msg.address >> 32;
kroute.u.msi.data = le32_to_cpu(msg.data);
+ if (kvm_arch_fixup_msi_route(&kroute, msg.address, msg.data)) {
+ kvm_irqchip_release_virq(s, virq);
+ return -EINVAL;
+ }
kvm_add_routing_entry(s, &kroute);
kvm_irqchip_commit_routes(s);
kroute.u.msi.address_lo = (uint32_t)msg.address;
kroute.u.msi.address_hi = msg.address >> 32;
kroute.u.msi.data = le32_to_cpu(msg.data);
+ if (kvm_arch_fixup_msi_route(&kroute, msg.address, msg.data)) {
+ return -EINVAL;
+ }
return kvm_update_routing_entry(s, &kroute);
}
int kvm_irqchip_add_adapter_route(KVMState *s, AdapterInfo *adapter)
{
- struct kvm_irq_routing_entry kroute;
+ struct kvm_irq_routing_entry kroute = {};
int virq;
if (!kvm_gsi_routing_enabled()) {
false);
}
-static int kvm_irqchip_create(KVMState *s)
+static int kvm_irqchip_create(MachineState *machine, KVMState *s)
{
int ret;
- if (!qemu_opt_get_bool(qemu_get_machine_opts(), "kernel_irqchip", true) ||
+ if (!machine_kernel_irqchip_allowed(machine) ||
(!kvm_check_extension(s, KVM_CAP_IRQCHIP) &&
(kvm_vm_enable_cap(s, KVM_CAP_S390_IRQCHIP, 0) < 0))) {
return 0;
return (ret) ? ret : kvm_recommended_vcpus(s);
}
-int kvm_init(MachineClass *mc)
+static int kvm_init(MachineState *ms)
{
+ MachineClass *mc = MACHINE_GET_CLASS(ms);
static const char upgrade_note[] =
"Please upgrade to at least kernel 2.6.29 or recent kvm-kmod\n"
"(see http://sourceforge.net/projects/kvm).\n";
int i, type = 0;
const char *kvm_type;
- s = g_malloc0(sizeof(KVMState));
+ s = KVM_STATE(ms->accelerator);
/*
* On systems where the kernel can support different base page
strerror(-ret));
#ifdef TARGET_S390X
- fprintf(stderr, "Please add the 'switch_amode' kernel parameter to "
- "your host kernel command line\n");
+ if (ret == -EINVAL) {
+ fprintf(stderr,
+ "Host kernel setup problem detected. Please verify:\n");
+ fprintf(stderr, "- for kernels supporting the switch_amode or"
+ " user_mode parameters, whether\n");
+ fprintf(stderr,
+ " user space is running in primary address space\n");
+ fprintf(stderr,
+ "- for kernels supporting the vm.allocate_pgste sysctl, "
+ "whether it is enabled\n");
+ }
#endif
goto err;
}
kvm_eventfds_allowed =
(kvm_check_extension(s, KVM_CAP_IOEVENTFD) > 0);
- ret = kvm_arch_init(s);
+ 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);
+
+ ret = kvm_arch_init(ms, s);
if (ret < 0) {
goto err;
}
- ret = kvm_irqchip_create(s);
+ ret = kvm_irqchip_create(ms, s);
if (ret < 0) {
goto err;
}
close(s->fd);
}
g_free(s->slots);
- g_free(s);
return ret;
}
s->sigmask_len = sigmask_len;
}
-static void kvm_handle_io(uint16_t port, void *data, int direction, int size,
- uint32_t count)
+static void kvm_handle_io(uint16_t port, MemTxAttrs attrs, void *data, int direction,
+ int size, uint32_t count)
{
int i;
uint8_t *ptr = data;
for (i = 0; i < count; i++) {
- address_space_rw(&address_space_io, port, ptr, size,
+ address_space_rw(&address_space_io, port, attrs,
+ ptr, size,
direction == KVM_EXIT_IO_OUT);
ptr += size;
}
run_on_cpu(cpu, do_kvm_cpu_synchronize_post_init, cpu);
}
+void kvm_cpu_clean_state(CPUState *cpu)
+{
+ cpu->kvm_vcpu_dirty = false;
+}
+
int kvm_cpu_exec(CPUState *cpu)
{
struct kvm_run *run = cpu->kvm_run;
}
do {
+ MemTxAttrs attrs;
+
if (cpu->kvm_vcpu_dirty) {
kvm_arch_put_registers(cpu, KVM_PUT_RUNTIME_STATE);
cpu->kvm_vcpu_dirty = false;
run_ret = kvm_vcpu_ioctl(cpu, KVM_RUN, 0);
qemu_mutex_lock_iothread();
- kvm_arch_post_run(cpu, run);
+ attrs = kvm_arch_post_run(cpu, run);
if (run_ret < 0) {
if (run_ret == -EINTR || run_ret == -EAGAIN) {
}
fprintf(stderr, "error: kvm run failed %s\n",
strerror(-run_ret));
- abort();
+ ret = -1;
+ break;
}
trace_kvm_run_exit(cpu->cpu_index, run->exit_reason);
switch (run->exit_reason) {
case KVM_EXIT_IO:
DPRINTF("handle_io\n");
- kvm_handle_io(run->io.port,
+ kvm_handle_io(run->io.port, attrs,
(uint8_t *)run + run->io.data_offset,
run->io.direction,
run->io.size,
break;
case KVM_EXIT_MMIO:
DPRINTF("handle_mmio\n");
- cpu_physical_memory_rw(run->mmio.phys_addr,
- run->mmio.data,
- run->mmio.len,
- run->mmio.is_write);
+ address_space_rw(&address_space_memory,
+ run->mmio.phys_addr, attrs,
+ run->mmio.data,
+ run->mmio.len,
+ run->mmio.is_write);
ret = 0;
break;
case KVM_EXIT_IRQ_WINDOW_OPEN:
return ret;
}
+int kvm_vm_check_attr(KVMState *s, uint32_t group, uint64_t attr)
+{
+ int ret;
+ struct kvm_device_attr attribute = {
+ .group = group,
+ .attr = attr,
+ };
+
+ if (!kvm_vm_attributes_allowed) {
+ return 0;
+ }
+
+ ret = kvm_vm_ioctl(s, KVM_HAS_DEVICE_ATTR, &attribute);
+ /* kvm returns 0 on success for HAS_DEVICE_ATTR */
+ return ret ? 0 : 1;
+}
+
int kvm_has_sync_mmu(void)
{
return kvm_check_extension(kvm_state, KVM_CAP_SYNC_MMU);
void kvm_setup_guest_memory(void *start, size_t size)
{
-#ifdef CONFIG_VALGRIND_H
- VALGRIND_MAKE_MEM_DEFINED(start, size);
-#endif
if (!kvm_has_sync_mmu()) {
int ret = qemu_madvise(start, size, QEMU_MADV_DONTFORK);
}
bp = g_malloc(sizeof(struct kvm_sw_breakpoint));
- if (!bp) {
- return -ENOMEM;
- }
-
bp->pc = addr;
bp->use_count = 1;
err = kvm_arch_insert_sw_breakpoint(cpu, bp);
}
return r;
}
+
+static void kvm_accel_class_init(ObjectClass *oc, void *data)
+{
+ AccelClass *ac = ACCEL_CLASS(oc);
+ ac->name = "KVM";
+ ac->init_machine = kvm_init;
+ ac->allowed = &kvm_allowed;
+}
+
+static const TypeInfo kvm_accel_type = {
+ .name = TYPE_KVM_ACCEL,
+ .parent = TYPE_ACCEL,
+ .class_init = kvm_accel_class_init,
+ .instance_size = sizeof(KVMState),
+};
+
+static void kvm_type_init(void)
+{
+ type_register_static(&kvm_accel_type);
+}
+
+type_init(kvm_type_init);
projects / mirror_qemu.git / blobdiff