#include "exec/memory.h"
#include "exec/address-spaces.h"
#include "qemu/event_notifier.h"
+#include "trace.h"
/* This check must be after config-host.h is included */
#ifdef CONFIG_EVENTFD
KVMState *kvm_state;
bool kvm_kernel_irqchip;
bool kvm_async_interrupts_allowed;
+bool kvm_halt_in_kernel_allowed;
bool kvm_irqfds_allowed;
bool kvm_msi_via_irqfd_allowed;
bool kvm_gsi_routing_allowed;
+bool kvm_allowed;
+bool kvm_readonly_mem_allowed;
static const KVMCapabilityInfo kvm_required_capabilites[] = {
KVM_CAP_INFO(USER_MEMORY),
mem.slot = slot->slot;
mem.guest_phys_addr = slot->start_addr;
- mem.memory_size = slot->memory_size;
mem.userspace_addr = (unsigned long)slot->ram;
mem.flags = slot->flags;
if (s->migration_log) {
mem.flags |= KVM_MEM_LOG_DIRTY_PAGES;
}
+
+ if (slot->memory_size && mem.flags & KVM_MEM_READONLY) {
+ /* Set the slot size to 0 before setting the slot to the desired
+ * value. This is needed based on KVM commit 75d61fbc. */
+ mem.memory_size = 0;
+ kvm_vm_ioctl(s, KVM_SET_USER_MEMORY_REGION, &mem);
+ }
+ mem.memory_size = slot->memory_size;
return kvm_vm_ioctl(s, KVM_SET_USER_MEMORY_REGION, &mem);
}
kvm_arch_reset_vcpu(cpu);
}
-int kvm_init_vcpu(CPUArchState *env)
+int kvm_init_vcpu(CPUState *cpu)
{
- CPUState *cpu = ENV_GET_CPU(env);
KVMState *s = kvm_state;
long mmap_size;
int ret;
DPRINTF("kvm_init_vcpu\n");
- ret = kvm_vm_ioctl(s, KVM_CREATE_VCPU, env->cpu_index);
+ ret = kvm_vm_ioctl(s, KVM_CREATE_VCPU, (void *)kvm_arch_vcpu_id(cpu));
if (ret < 0) {
DPRINTF("kvm_create_vcpu failed\n");
goto err;
* dirty pages logging control
*/
-static int kvm_mem_flags(KVMState *s, bool log_dirty)
+static int kvm_mem_flags(KVMState *s, bool log_dirty, bool readonly)
{
- return log_dirty ? KVM_MEM_LOG_DIRTY_PAGES : 0;
+ int flags = 0;
+ flags = log_dirty ? KVM_MEM_LOG_DIRTY_PAGES : 0;
+ if (readonly && kvm_readonly_mem_allowed) {
+ flags |= KVM_MEM_READONLY;
+ }
+ return flags;
}
static int kvm_slot_dirty_pages_log_change(KVMSlot *mem, bool log_dirty)
old_flags = mem->flags;
- flags = (mem->flags & ~mask) | kvm_mem_flags(s, log_dirty);
+ flags = (mem->flags & ~mask) | kvm_mem_flags(s, log_dirty, false);
mem->flags = flags;
/* If nothing changed effectively, no need to issue ioctl */
int r;
r = kvm_dirty_pages_log_change(section->offset_within_address_space,
- section->size, true);
+ int128_get64(section->size), true);
if (r < 0) {
abort();
}
int r;
r = kvm_dirty_pages_log_change(section->offset_within_address_space,
- section->size, false);
+ int128_get64(section->size), false);
if (r < 0) {
abort();
}
unsigned int i, j;
unsigned long page_number, c;
hwaddr addr, addr1;
- unsigned int len = ((section->size / getpagesize()) + HOST_LONG_BITS - 1) / HOST_LONG_BITS;
+ unsigned int pages = int128_get64(section->size) / getpagesize();
+ unsigned int len = (pages + HOST_LONG_BITS - 1) / HOST_LONG_BITS;
unsigned long hpratio = getpagesize() / TARGET_PAGE_SIZE;
/*
KVMSlot *mem;
int ret = 0;
hwaddr start_addr = section->offset_within_address_space;
- hwaddr end_addr = start_addr + section->size;
+ hwaddr end_addr = start_addr + int128_get64(section->size);
d.dirty_bitmap = NULL;
while (start_addr < end_addr) {
return ret;
}
+static int kvm_set_ioeventfd_mmio(int fd, uint32_t 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;
+
+ if (!kvm_enabled()) {
+ return -ENOSYS;
+ }
+
+ if (datamatch) {
+ iofd.flags |= KVM_IOEVENTFD_FLAG_DATAMATCH;
+ }
+ if (!assign) {
+ iofd.flags |= KVM_IOEVENTFD_FLAG_DEASSIGN;
+ }
+
+ ret = kvm_vm_ioctl(kvm_state, KVM_IOEVENTFD, &iofd);
+
+ if (ret < 0) {
+ return -errno;
+ }
+
+ return 0;
+}
+
+static int kvm_set_ioeventfd_pio(int fd, uint16_t addr, uint16_t val,
+ bool assign, uint32_t size, bool datamatch)
+{
+ struct kvm_ioeventfd kick = {
+ .datamatch = datamatch ? val : 0,
+ .addr = addr,
+ .flags = KVM_IOEVENTFD_FLAG_PIO,
+ .len = size,
+ .fd = fd,
+ };
+ int r;
+ if (!kvm_enabled()) {
+ return -ENOSYS;
+ }
+ if (datamatch) {
+ kick.flags |= KVM_IOEVENTFD_FLAG_DATAMATCH;
+ }
+ if (!assign) {
+ kick.flags |= KVM_IOEVENTFD_FLAG_DEASSIGN;
+ }
+ r = kvm_vm_ioctl(kvm_state, KVM_IOEVENTFD, &kick);
+ if (r < 0) {
+ return r;
+ }
+ return 0;
+}
+
+
static int kvm_check_many_ioeventfds(void)
{
/* Userspace can use ioeventfd for io notification. This requires a host
if (ioeventfds[i] < 0) {
break;
}
- ret = kvm_set_ioeventfd_pio_word(ioeventfds[i], 0, i, true);
+ ret = kvm_set_ioeventfd_pio(ioeventfds[i], 0, i, true, 2, true);
if (ret < 0) {
close(ioeventfds[i]);
break;
ret = i == ARRAY_SIZE(ioeventfds);
while (i-- > 0) {
- kvm_set_ioeventfd_pio_word(ioeventfds[i], 0, i, false);
+ kvm_set_ioeventfd_pio(ioeventfds[i], 0, i, false, 2, true);
close(ioeventfds[i]);
}
return ret;
int err;
MemoryRegion *mr = section->mr;
bool log_dirty = memory_region_is_logging(mr);
+ bool writeable = !mr->readonly && !mr->rom_device;
+ bool readonly_flag = mr->readonly || memory_region_is_romd(mr);
hwaddr start_addr = section->offset_within_address_space;
- ram_addr_t size = section->size;
+ ram_addr_t size = int128_get64(section->size);
void *ram = NULL;
unsigned delta;
}
if (!memory_region_is_ram(mr)) {
- return;
+ if (writeable || !kvm_readonly_mem_allowed) {
+ return;
+ } else if (!mr->romd_mode) {
+ /* If the memory device is not in romd_mode, then we actually want
+ * to remove the kvm memory slot so all accesses will trap. */
+ add = false;
+ }
}
ram = memory_region_get_ram_ptr(mr) + section->offset_within_region + delta;
mem->memory_size = old.memory_size;
mem->start_addr = old.start_addr;
mem->ram = old.ram;
- mem->flags = kvm_mem_flags(s, log_dirty);
+ mem->flags = kvm_mem_flags(s, log_dirty, readonly_flag);
err = kvm_set_user_memory_region(s, mem);
if (err) {
mem->memory_size = start_addr - old.start_addr;
mem->start_addr = old.start_addr;
mem->ram = old.ram;
- mem->flags = kvm_mem_flags(s, log_dirty);
+ mem->flags = kvm_mem_flags(s, log_dirty, readonly_flag);
err = kvm_set_user_memory_region(s, mem);
if (err) {
size_delta = mem->start_addr - old.start_addr;
mem->memory_size = old.memory_size - size_delta;
mem->ram = old.ram + size_delta;
- mem->flags = kvm_mem_flags(s, log_dirty);
+ mem->flags = kvm_mem_flags(s, log_dirty, readonly_flag);
err = kvm_set_user_memory_region(s, mem);
if (err) {
mem->memory_size = size;
mem->start_addr = start_addr;
mem->ram = ram;
- mem->flags = kvm_mem_flags(s, log_dirty);
+ mem->flags = kvm_mem_flags(s, log_dirty, readonly_flag);
err = kvm_set_user_memory_region(s, mem);
if (err) {
static void kvm_region_add(MemoryListener *listener,
MemoryRegionSection *section)
{
+ memory_region_ref(section->mr);
kvm_set_phys_mem(section, true);
}
MemoryRegionSection *section)
{
kvm_set_phys_mem(section, false);
+ memory_region_unref(section->mr);
}
static void kvm_log_sync(MemoryListener *listener,
int fd = event_notifier_get_fd(e);
int r;
- assert(match_data && section->size <= 8);
-
r = kvm_set_ioeventfd_mmio(fd, section->offset_within_address_space,
- data, true, section->size);
+ data, true, int128_get64(section->size),
+ match_data);
if (r < 0) {
abort();
}
int r;
r = kvm_set_ioeventfd_mmio(fd, section->offset_within_address_space,
- data, false, section->size);
+ data, false, int128_get64(section->size),
+ match_data);
if (r < 0) {
abort();
}
int fd = event_notifier_get_fd(e);
int r;
- assert(match_data && section->size == 2);
-
- r = kvm_set_ioeventfd_pio_word(fd, section->offset_within_address_space,
- data, true);
+ r = kvm_set_ioeventfd_pio(fd, section->offset_within_address_space,
+ data, true, int128_get64(section->size),
+ match_data);
if (r < 0) {
abort();
}
int fd = event_notifier_get_fd(e);
int r;
- r = kvm_set_ioeventfd_pio_word(fd, section->offset_within_address_space,
- data, false);
+ r = kvm_set_ioeventfd_pio(fd, section->offset_within_address_space,
+ data, false, int128_get64(section->size),
+ match_data);
if (r < 0) {
abort();
}
.priority = 10,
};
-static void kvm_handle_interrupt(CPUArchState *env, int mask)
+static void kvm_handle_interrupt(CPUState *cpu, int mask)
{
- CPUState *cpu = ENV_GET_CPU(env);
-
- env->interrupt_request |= mask;
+ cpu->interrupt_request |= mask;
if (!qemu_cpu_is_self(cpu)) {
qemu_cpu_kick(cpu);
s->used_gsi_bitmap[gsi / 32] &= ~(1U << (gsi % 32));
}
-static void kvm_init_irq_routing(KVMState *s)
+void kvm_init_irq_routing(KVMState *s)
{
int gsi_count, i;
kvm_arch_init_irq_routing(s);
}
-static void kvm_irqchip_commit_routes(KVMState *s)
+void kvm_irqchip_commit_routes(KVMState *s)
{
int ret;
new->u = entry->u;
set_gsi(s, entry->gsi);
-
- kvm_irqchip_commit_routes(s);
}
static int kvm_update_routing_entry(KVMState *s,
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 == msg.data) {
+ route->kroute.u.msi.data == le32_to_cpu(msg.data)) {
return route;
}
}
if (s->direct_msi) {
msi.address_lo = (uint32_t)msg.address;
msi.address_hi = msg.address >> 32;
- msi.data = msg.data;
+ msi.data = le32_to_cpu(msg.data);
msi.flags = 0;
memset(msi.pad, 0, sizeof(msi.pad));
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 = msg.data;
+ 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);
kroute.flags = 0;
kroute.u.msi.address_lo = (uint32_t)msg.address;
kroute.u.msi.address_hi = msg.address >> 32;
- kroute.u.msi.data = msg.data;
+ kroute.u.msi.data = le32_to_cpu(msg.data);
kvm_add_routing_entry(s, &kroute);
+ kvm_irqchip_commit_routes(s);
return virq;
}
kroute.flags = 0;
kroute.u.msi.address_lo = (uint32_t)msg.address;
kroute.u.msi.address_hi = msg.address >> 32;
- kroute.u.msi.data = msg.data;
+ kroute.u.msi.data = le32_to_cpu(msg.data);
return kvm_update_routing_entry(s, &kroute);
}
#else /* !KVM_CAP_IRQ_ROUTING */
-static void kvm_init_irq_routing(KVMState *s)
+void kvm_init_irq_routing(KVMState *s)
{
}
{
abort();
}
+
+int kvm_irqchip_update_msi_route(KVMState *s, int virq, MSIMessage msg)
+{
+ return -ENOSYS;
+}
#endif /* !KVM_CAP_IRQ_ROUTING */
int kvm_irqchip_add_irqfd_notifier(KVMState *s, EventNotifier *n, int virq)
* interrupt delivery (though the reverse is not necessarily true)
*/
kvm_async_interrupts_allowed = true;
+ kvm_halt_in_kernel_allowed = true;
kvm_init_irq_routing(s);
s->irq_set_ioctl = KVM_IRQ_LINE_STATUS;
}
+#ifdef KVM_CAP_READONLY_MEM
+ kvm_readonly_mem_allowed =
+ (kvm_check_extension(s, KVM_CAP_READONLY_MEM) > 0);
+#endif
+
ret = kvm_arch_init(s);
if (ret < 0) {
goto err;
}
}
-static int kvm_handle_internal_error(CPUArchState *env, struct kvm_run *run)
+static int kvm_handle_internal_error(CPUState *cpu, struct kvm_run *run)
{
- CPUState *cpu = ENV_GET_CPU(env);
-
fprintf(stderr, "KVM internal error.");
if (kvm_check_extension(kvm_state, KVM_CAP_INTERNAL_ERROR_DATA)) {
int i;
if (run->internal.suberror == KVM_INTERNAL_ERROR_EMULATION) {
fprintf(stderr, "emulation failure\n");
if (!kvm_arch_stop_on_emulation_error(cpu)) {
- cpu_dump_state(env, stderr, fprintf, CPU_DUMP_CODE);
+ cpu_dump_state(cpu, stderr, fprintf, CPU_DUMP_CODE);
return EXCP_INTERRUPT;
}
}
}
}
-void kvm_cpu_synchronize_state(CPUArchState *env)
+void kvm_cpu_synchronize_state(CPUState *cpu)
{
- CPUState *cpu = ENV_GET_CPU(env);
-
if (!cpu->kvm_vcpu_dirty) {
run_on_cpu(cpu, do_kvm_cpu_synchronize_state, cpu);
}
}
-void kvm_cpu_synchronize_post_reset(CPUArchState *env)
+void kvm_cpu_synchronize_post_reset(CPUState *cpu)
{
- CPUState *cpu = ENV_GET_CPU(env);
-
kvm_arch_put_registers(cpu, KVM_PUT_RESET_STATE);
cpu->kvm_vcpu_dirty = false;
}
-void kvm_cpu_synchronize_post_init(CPUArchState *env)
+void kvm_cpu_synchronize_post_init(CPUState *cpu)
{
- CPUState *cpu = ENV_GET_CPU(env);
-
kvm_arch_put_registers(cpu, KVM_PUT_FULL_STATE);
cpu->kvm_vcpu_dirty = false;
}
-int kvm_cpu_exec(CPUArchState *env)
+int kvm_cpu_exec(CPUState *cpu)
{
- CPUState *cpu = ENV_GET_CPU(env);
struct kvm_run *run = cpu->kvm_run;
int ret, run_ret;
DPRINTF("kvm_cpu_exec()\n");
if (kvm_arch_process_async_events(cpu)) {
- env->exit_request = 0;
+ cpu->exit_request = 0;
return EXCP_HLT;
}
}
kvm_arch_pre_run(cpu, run);
- if (env->exit_request) {
+ if (cpu->exit_request) {
DPRINTF("interrupt exit requested\n");
/*
* KVM requires us to reenter the kernel after IO exits to complete
abort();
}
+ trace_kvm_run_exit(cpu->cpu_index, run->exit_reason);
switch (run->exit_reason) {
case KVM_EXIT_IO:
DPRINTF("handle_io\n");
ret = -1;
break;
case KVM_EXIT_INTERNAL_ERROR:
- ret = kvm_handle_internal_error(env, run);
+ ret = kvm_handle_internal_error(cpu, run);
break;
default:
DPRINTF("kvm_arch_handle_exit\n");
} while (ret == 0);
if (ret < 0) {
- cpu_dump_state(env, stderr, fprintf, CPU_DUMP_CODE);
+ cpu_dump_state(cpu, stderr, fprintf, CPU_DUMP_CODE);
vm_stop(RUN_STATE_INTERNAL_ERROR);
}
- env->exit_request = 0;
+ cpu->exit_request = 0;
return ret;
}
arg = va_arg(ap, void *);
va_end(ap);
+ trace_kvm_ioctl(type, arg);
ret = ioctl(s->fd, type, arg);
if (ret == -1) {
ret = -errno;
arg = va_arg(ap, void *);
va_end(ap);
+ trace_kvm_vm_ioctl(type, arg);
ret = ioctl(s->vmfd, type, arg);
if (ret == -1) {
ret = -errno;
arg = va_arg(ap, void *);
va_end(ap);
+ trace_kvm_vcpu_ioctl(cpu->cpu_index, type, arg);
ret = ioctl(cpu->kvm_fd, type, arg);
if (ret == -1) {
ret = -errno;
return kvm_state->intx_set_mask;
}
-void *kvm_vmalloc(ram_addr_t size)
+void *kvm_ram_alloc(ram_addr_t size)
{
#ifdef TARGET_S390X
void *mem;
- mem = kvm_arch_vmalloc(size);
+ mem = kvm_arch_ram_alloc(size);
if (mem) {
return mem;
}
#endif
- return qemu_vmalloc(size);
+ return qemu_anon_ram_alloc(size);
}
void kvm_setup_guest_memory(void *start, size_t size)
}
#endif /* !KVM_CAP_SET_GUEST_DEBUG */
-int kvm_set_signal_mask(CPUArchState *env, const sigset_t *sigset)
+int kvm_set_signal_mask(CPUState *cpu, const sigset_t *sigset)
{
- CPUState *cpu = ENV_GET_CPU(env);
struct kvm_signal_mask *sigmask;
int r;
return r;
}
-
-int kvm_set_ioeventfd_mmio(int fd, uint32_t addr, uint32_t val, bool assign,
- uint32_t size)
+int kvm_on_sigbus_vcpu(CPUState *cpu, int code, void *addr)
{
- int ret;
- struct kvm_ioeventfd iofd;
-
- iofd.datamatch = val;
- iofd.addr = addr;
- iofd.len = size;
- iofd.flags = KVM_IOEVENTFD_FLAG_DATAMATCH;
- iofd.fd = fd;
-
- if (!kvm_enabled()) {
- return -ENOSYS;
- }
-
- if (!assign) {
- iofd.flags |= KVM_IOEVENTFD_FLAG_DEASSIGN;
- }
-
- ret = kvm_vm_ioctl(kvm_state, KVM_IOEVENTFD, &iofd);
-
- if (ret < 0) {
- return -errno;
- }
-
- return 0;
-}
-
-int kvm_set_ioeventfd_pio_word(int fd, uint16_t addr, uint16_t val, bool assign)
-{
- struct kvm_ioeventfd kick = {
- .datamatch = val,
- .addr = addr,
- .len = 2,
- .flags = KVM_IOEVENTFD_FLAG_DATAMATCH | KVM_IOEVENTFD_FLAG_PIO,
- .fd = fd,
- };
- int r;
- if (!kvm_enabled()) {
- return -ENOSYS;
- }
- if (!assign) {
- kick.flags |= KVM_IOEVENTFD_FLAG_DEASSIGN;
- }
- r = kvm_vm_ioctl(kvm_state, KVM_IOEVENTFD, &kick);
- if (r < 0) {
- return r;
- }
- return 0;
-}
-
-int kvm_on_sigbus_vcpu(CPUArchState *env, int code, void *addr)
-{
- CPUState *cpu = ENV_GET_CPU(env);
return kvm_arch_on_sigbus_vcpu(cpu, code, addr);
}
projects / qemu.git / blobdiff