#include "kvm.h"
#include "bswap.h"
#include "memory.h"
+#include "exec-memory.h"
/* This check must be after config-host.h is included */
#ifdef CONFIG_EVENTFD
#include <sys/eventfd.h>
#endif
-/* KVM uses PAGE_SIZE in it's definition of COALESCED_MMIO_MAX */
+/* KVM uses PAGE_SIZE in its definition of COALESCED_MMIO_MAX */
#define PAGE_SIZE TARGET_PAGE_SIZE
//#define DEBUG_KVM
#ifdef KVM_CAP_SET_GUEST_DEBUG
struct kvm_sw_breakpoint_head kvm_sw_breakpoints;
#endif
- int irqchip_in_kernel;
- int pit_in_kernel;
+ int pit_state2;
int xsave, xcrs;
int many_ioeventfds;
- int irqchip_inject_ioctl;
+ /* The man page (and posix) say ioctl numbers are signed int, but
+ * they're not. Linux, glibc and *BSD all treat ioctl numbers as
+ * unsigned, and treating them as signed here can break things */
+ unsigned irqchip_inject_ioctl;
#ifdef KVM_CAP_IRQ_ROUTING
struct kvm_irq_routing *irq_routes;
int nr_allocated_irq_routes;
};
KVMState *kvm_state;
+bool kvm_kernel_irqchip;
static const KVMCapabilityInfo kvm_required_capabilites[] = {
KVM_CAP_INFO(USER_MEMORY),
static void kvm_reset_vcpu(void *opaque)
{
- CPUState *env = opaque;
+ CPUArchState *env = opaque;
kvm_arch_reset_vcpu(env);
}
-int kvm_irqchip_in_kernel(void)
-{
- return kvm_state->irqchip_in_kernel;
-}
-
-int kvm_pit_in_kernel(void)
-{
- return kvm_state->pit_in_kernel;
-}
-
-int kvm_init_vcpu(CPUState *env)
+int kvm_init_vcpu(CPUArchState *env)
{
KVMState *s = kvm_state;
long mmap_size;
zone.addr = start;
zone.size = size;
+ zone.pad = 0;
ret = kvm_vm_ioctl(s, KVM_REGISTER_COALESCED_MMIO, &zone);
}
zone.addr = start;
zone.size = size;
+ zone.pad = 0;
ret = kvm_vm_ioctl(s, KVM_UNREGISTER_COALESCED_MMIO, &zone);
}
target_phys_addr_t start_addr = section->offset_within_address_space;
ram_addr_t size = section->size;
void *ram = NULL;
+ unsigned delta;
/* 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);
+ delta = TARGET_PAGE_ALIGN(size) - size;
+ if (delta > size) {
+ return;
+ }
+ start_addr += delta;
+ size -= delta;
+ size &= TARGET_PAGE_MASK;
+ if (!size || (start_addr & ~TARGET_PAGE_MASK)) {
+ return;
+ }
if (!memory_region_is_ram(mr)) {
return;
}
- ram = memory_region_get_ram_ptr(mr) + section->offset_within_region;
+ ram = memory_region_get_ram_ptr(mr) + section->offset_within_region + delta;
while (1) {
mem = kvm_lookup_overlapping_slot(s, start_addr, start_addr + size);
}
}
+static void kvm_begin(MemoryListener *listener)
+{
+}
+
+static void kvm_commit(MemoryListener *listener)
+{
+}
+
static void kvm_region_add(MemoryListener *listener,
MemoryRegionSection *section)
{
kvm_set_phys_mem(section, false);
}
+static void kvm_region_nop(MemoryListener *listener,
+ MemoryRegionSection *section)
+{
+}
+
static void kvm_log_sync(MemoryListener *listener,
MemoryRegionSection *section)
{
assert(r >= 0);
}
+static void kvm_mem_ioeventfd_add(MemoryRegionSection *section,
+ bool match_data, uint64_t data, int fd)
+{
+ int r;
+
+ assert(match_data && section->size <= 8);
+
+ r = kvm_set_ioeventfd_mmio(fd, section->offset_within_address_space,
+ data, true, section->size);
+ if (r < 0) {
+ abort();
+ }
+}
+
+static void kvm_mem_ioeventfd_del(MemoryRegionSection *section,
+ bool match_data, uint64_t data, int fd)
+{
+ int r;
+
+ r = kvm_set_ioeventfd_mmio(fd, section->offset_within_address_space,
+ data, false, section->size);
+ if (r < 0) {
+ abort();
+ }
+}
+
+static void kvm_io_ioeventfd_add(MemoryRegionSection *section,
+ bool match_data, uint64_t data, int fd)
+{
+ int r;
+
+ assert(match_data && section->size == 2);
+
+ r = kvm_set_ioeventfd_pio_word(fd, section->offset_within_address_space,
+ data, true);
+ if (r < 0) {
+ abort();
+ }
+}
+
+static void kvm_io_ioeventfd_del(MemoryRegionSection *section,
+ bool match_data, uint64_t data, int fd)
+
+{
+ int r;
+
+ r = kvm_set_ioeventfd_pio_word(fd, section->offset_within_address_space,
+ data, false);
+ if (r < 0) {
+ abort();
+ }
+}
+
+static void kvm_eventfd_add(MemoryListener *listener,
+ MemoryRegionSection *section,
+ bool match_data, uint64_t data, int fd)
+{
+ if (section->address_space == get_system_memory()) {
+ kvm_mem_ioeventfd_add(section, match_data, data, fd);
+ } else {
+ kvm_io_ioeventfd_add(section, match_data, data, fd);
+ }
+}
+
+static void kvm_eventfd_del(MemoryListener *listener,
+ MemoryRegionSection *section,
+ bool match_data, uint64_t data, int fd)
+{
+ if (section->address_space == get_system_memory()) {
+ kvm_mem_ioeventfd_del(section, match_data, data, fd);
+ } else {
+ kvm_io_ioeventfd_del(section, match_data, data, fd);
+ }
+}
+
static MemoryListener kvm_memory_listener = {
+ .begin = kvm_begin,
+ .commit = kvm_commit,
.region_add = kvm_region_add,
.region_del = kvm_region_del,
+ .region_nop = kvm_region_nop,
.log_start = kvm_log_start,
.log_stop = kvm_log_stop,
.log_sync = kvm_log_sync,
.log_global_start = kvm_log_global_start,
.log_global_stop = kvm_log_global_stop,
+ .eventfd_add = kvm_eventfd_add,
+ .eventfd_del = kvm_eventfd_del,
+ .priority = 10,
};
-static void kvm_handle_interrupt(CPUState *env, int mask)
+static void kvm_handle_interrupt(CPUArchState *env, int mask)
{
env->interrupt_request |= mask;
struct kvm_irq_level event;
int ret;
- assert(s->irqchip_in_kernel);
+ assert(kvm_irqchip_in_kernel());
event.level = level;
event.irq = irq;
unsigned int gsi_bits, i;
/* Round up so we can search ints using ffs */
- gsi_bits = (gsi_count + 31) / 32;
+ gsi_bits = ALIGN(gsi_count, 32);
s->used_gsi_bitmap = g_malloc0(gsi_bits / 8);
s->max_gsi = gsi_bits;
if (kvm_check_extension(s, KVM_CAP_IRQ_INJECT_STATUS)) {
s->irqchip_inject_ioctl = KVM_IRQ_LINE_STATUS;
}
- s->irqchip_in_kernel = 1;
+ kvm_kernel_irqchip = true;
kvm_init_irq_routing(s);
s->xcrs = kvm_check_extension(s, KVM_CAP_XCRS);
#endif
+#ifdef KVM_CAP_PIT_STATE2
+ s->pit_state2 = kvm_check_extension(s, KVM_CAP_PIT_STATE2);
+#endif
+
ret = kvm_arch_init(s);
if (ret < 0) {
goto err;
}
kvm_state = s;
- memory_listener_register(&kvm_memory_listener);
+ memory_listener_register(&kvm_memory_listener, NULL);
s->many_ioeventfds = kvm_check_many_ioeventfds();
}
}
-static int kvm_handle_internal_error(CPUState *env, struct kvm_run *run)
+static int kvm_handle_internal_error(CPUArchState *env, struct kvm_run *run)
{
fprintf(stderr, "KVM internal error.");
if (kvm_check_extension(kvm_state, KVM_CAP_INTERNAL_ERROR_DATA)) {
static void do_kvm_cpu_synchronize_state(void *_env)
{
- CPUState *env = _env;
+ CPUArchState *env = _env;
if (!env->kvm_vcpu_dirty) {
kvm_arch_get_registers(env);
}
}
-void kvm_cpu_synchronize_state(CPUState *env)
+void kvm_cpu_synchronize_state(CPUArchState *env)
{
if (!env->kvm_vcpu_dirty) {
run_on_cpu(env, do_kvm_cpu_synchronize_state, env);
}
}
-void kvm_cpu_synchronize_post_reset(CPUState *env)
+void kvm_cpu_synchronize_post_reset(CPUArchState *env)
{
kvm_arch_put_registers(env, KVM_PUT_RESET_STATE);
env->kvm_vcpu_dirty = 0;
}
-void kvm_cpu_synchronize_post_init(CPUState *env)
+void kvm_cpu_synchronize_post_init(CPUArchState *env)
{
kvm_arch_put_registers(env, KVM_PUT_FULL_STATE);
env->kvm_vcpu_dirty = 0;
}
-int kvm_cpu_exec(CPUState *env)
+int kvm_cpu_exec(CPUArchState *env)
{
struct kvm_run *run = env->kvm_run;
int ret, run_ret;
return EXCP_HLT;
}
- cpu_single_env = env;
-
do {
if (env->kvm_vcpu_dirty) {
kvm_arch_put_registers(env, KVM_PUT_RUNTIME_STATE);
*/
qemu_cpu_kick_self();
}
- cpu_single_env = NULL;
qemu_mutex_unlock_iothread();
run_ret = kvm_vcpu_ioctl(env, KVM_RUN, 0);
qemu_mutex_lock_iothread();
- cpu_single_env = env;
kvm_arch_post_run(env, run);
kvm_flush_coalesced_mmio_buffer();
}
env->exit_request = 0;
- cpu_single_env = NULL;
return ret;
}
return ret;
}
-int kvm_vcpu_ioctl(CPUState *env, int type, ...)
+int kvm_vcpu_ioctl(CPUArchState *env, int type, ...)
{
int ret;
void *arg;
return kvm_state->xcrs;
}
+int kvm_has_pit_state2(void)
+{
+ return kvm_state->pit_state2;
+}
+
int kvm_has_many_ioeventfds(void)
{
if (!kvm_enabled()) {
int kvm_allows_irq0_override(void)
{
- return !kvm_enabled() || !kvm_irqchip_in_kernel() || kvm_has_gsi_routing();
+ return !kvm_irqchip_in_kernel() || kvm_has_gsi_routing();
}
void kvm_setup_guest_memory(void *start, size_t size)
}
#ifdef KVM_CAP_SET_GUEST_DEBUG
-struct kvm_sw_breakpoint *kvm_find_sw_breakpoint(CPUState *env,
+struct kvm_sw_breakpoint *kvm_find_sw_breakpoint(CPUArchState *env,
target_ulong pc)
{
struct kvm_sw_breakpoint *bp;
return NULL;
}
-int kvm_sw_breakpoints_active(CPUState *env)
+int kvm_sw_breakpoints_active(CPUArchState *env)
{
return !QTAILQ_EMPTY(&env->kvm_state->kvm_sw_breakpoints);
}
struct kvm_set_guest_debug_data {
struct kvm_guest_debug dbg;
- CPUState *env;
+ CPUArchState *env;
int err;
};
static void kvm_invoke_set_guest_debug(void *data)
{
struct kvm_set_guest_debug_data *dbg_data = data;
- CPUState *env = dbg_data->env;
+ CPUArchState *env = dbg_data->env;
dbg_data->err = kvm_vcpu_ioctl(env, KVM_SET_GUEST_DEBUG, &dbg_data->dbg);
}
-int kvm_update_guest_debug(CPUState *env, unsigned long reinject_trap)
+int kvm_update_guest_debug(CPUArchState *env, unsigned long reinject_trap)
{
struct kvm_set_guest_debug_data data;
return data.err;
}
-int kvm_insert_breakpoint(CPUState *current_env, target_ulong addr,
+int kvm_insert_breakpoint(CPUArchState *current_env, target_ulong addr,
target_ulong len, int type)
{
struct kvm_sw_breakpoint *bp;
- CPUState *env;
+ CPUArchState *env;
int err;
if (type == GDB_BREAKPOINT_SW) {
return 0;
}
-int kvm_remove_breakpoint(CPUState *current_env, target_ulong addr,
+int kvm_remove_breakpoint(CPUArchState *current_env, target_ulong addr,
target_ulong len, int type)
{
struct kvm_sw_breakpoint *bp;
- CPUState *env;
+ CPUArchState *env;
int err;
if (type == GDB_BREAKPOINT_SW) {
return 0;
}
-void kvm_remove_all_breakpoints(CPUState *current_env)
+void kvm_remove_all_breakpoints(CPUArchState *current_env)
{
struct kvm_sw_breakpoint *bp, *next;
KVMState *s = current_env->kvm_state;
- CPUState *env;
+ CPUArchState *env;
QTAILQ_FOREACH_SAFE(bp, &s->kvm_sw_breakpoints, entry, next) {
if (kvm_arch_remove_sw_breakpoint(current_env, bp) != 0) {
#else /* !KVM_CAP_SET_GUEST_DEBUG */
-int kvm_update_guest_debug(CPUState *env, unsigned long reinject_trap)
+int kvm_update_guest_debug(CPUArchState *env, unsigned long reinject_trap)
{
return -EINVAL;
}
-int kvm_insert_breakpoint(CPUState *current_env, target_ulong addr,
+int kvm_insert_breakpoint(CPUArchState *current_env, target_ulong addr,
target_ulong len, int type)
{
return -EINVAL;
}
-int kvm_remove_breakpoint(CPUState *current_env, target_ulong addr,
+int kvm_remove_breakpoint(CPUArchState *current_env, target_ulong addr,
target_ulong len, int type)
{
return -EINVAL;
}
-void kvm_remove_all_breakpoints(CPUState *current_env)
+void kvm_remove_all_breakpoints(CPUArchState *current_env)
{
}
#endif /* !KVM_CAP_SET_GUEST_DEBUG */
-int kvm_set_signal_mask(CPUState *env, const sigset_t *sigset)
+int kvm_set_signal_mask(CPUArchState *env, const sigset_t *sigset)
{
struct kvm_signal_mask *sigmask;
int r;
return r;
}
-int kvm_set_ioeventfd_mmio_long(int fd, uint32_t addr, uint32_t val, bool assign)
+int kvm_set_ioeventfd_mmio(int fd, uint32_t addr, uint32_t val, bool assign,
+ uint32_t size)
{
int ret;
struct kvm_ioeventfd iofd;
iofd.datamatch = val;
iofd.addr = addr;
- iofd.len = 4;
+ iofd.len = size;
iofd.flags = KVM_IOEVENTFD_FLAG_DATAMATCH;
iofd.fd = fd;
return 0;
}
-int kvm_on_sigbus_vcpu(CPUState *env, int code, void *addr)
+int kvm_on_sigbus_vcpu(CPUArchState *env, int code, void *addr)
{
return kvm_arch_on_sigbus_vcpu(env, code, addr);
}