aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rwxr-xr-xconfigure36
-rw-r--r--cpu-all.h5
-rw-r--r--cpus.c2
-rw-r--r--hmp-commands.hx6
-rw-r--r--kvm-all.c247
-rw-r--r--kvm-stub.c2
-rw-r--r--kvm.h14
-rw-r--r--monitor.c7
-rw-r--r--target-i386/cpu.h9
-rw-r--r--target-i386/cpuid.c5
-rw-r--r--target-i386/helper.c97
-rw-r--r--target-i386/kvm.c751
-rw-r--r--target-i386/kvm_x86.h5
-rw-r--r--target-ppc/kvm.c10
-rw-r--r--target-s390x/kvm.c6
-rw-r--r--vl.c2
16 files changed, 716 insertions, 488 deletions
diff --git a/configure b/configure
index 81573b9830..598e8e1ebb 100755
--- a/configure
+++ b/configure
@@ -1663,15 +1663,31 @@ if test "$kvm" != "no" ; then
#if !defined(KVM_API_VERSION) || KVM_API_VERSION < 12 || KVM_API_VERSION > 12
#error Invalid KVM version
#endif
-#if !defined(KVM_CAP_USER_MEMORY)
-#error Missing KVM capability KVM_CAP_USER_MEMORY
-#endif
-#if !defined(KVM_CAP_SET_TSS_ADDR)
-#error Missing KVM capability KVM_CAP_SET_TSS_ADDR
-#endif
-#if !defined(KVM_CAP_DESTROY_MEMORY_REGION_WORKS)
-#error Missing KVM capability KVM_CAP_DESTROY_MEMORY_REGION_WORKS
+EOF
+ must_have_caps="KVM_CAP_USER_MEMORY \
+ KVM_CAP_DESTROY_MEMORY_REGION_WORKS \
+ KVM_CAP_COALESCED_MMIO \
+ KVM_CAP_SYNC_MMU \
+ "
+ if test \( "$cpu" = "i386" -o "$cpu" = "x86_64" \) ; then
+ must_have_caps="$caps \
+ KVM_CAP_SET_TSS_ADDR \
+ KVM_CAP_EXT_CPUID \
+ KVM_CAP_CLOCKSOURCE \
+ KVM_CAP_NOP_IO_DELAY \
+ KVM_CAP_PV_MMU \
+ KVM_CAP_MP_STATE \
+ KVM_CAP_USER_NMI \
+ "
+ fi
+ for c in $must_have_caps ; do
+ cat >> $TMPC <<EOF
+#if !defined($c)
+#error Missing KVM capability $c
#endif
+EOF
+ done
+ cat >> $TMPC <<EOF
int main(void) { return 0; }
EOF
if test "$kerneldir" != "" ; then
@@ -1706,8 +1722,8 @@ EOF
| awk -F "error: " '{if (NR>1) printf(", "); printf("%s",$2);}'`
if test "$kvmerr" != "" ; then
echo -e "${kvmerr}\n\
- NOTE: To enable KVM support, update your kernel to 2.6.29+ or install \
- recent kvm-kmod from http://sourceforge.net/projects/kvm."
+NOTE: To enable KVM support, update your kernel to 2.6.29+ or install \
+recent kvm-kmod from http://sourceforge.net/projects/kvm."
fi
fi
feature_not_found "kvm"
diff --git a/cpu-all.h b/cpu-all.h
index 30ae17d41d..ffbd6a4df8 100644
--- a/cpu-all.h
+++ b/cpu-all.h
@@ -765,6 +765,8 @@ int page_check_range(target_ulong start, target_ulong len, int flags);
CPUState *cpu_copy(CPUState *env);
CPUState *qemu_get_cpu(int cpu);
+#define CPU_DUMP_CODE 0x00010000
+
void cpu_dump_state(CPUState *env, FILE *f, fprintf_function cpu_fprintf,
int flags);
void cpu_dump_statistics(CPUState *env, FILE *f, fprintf_function cpu_fprintf,
@@ -964,6 +966,7 @@ int cpu_memory_rw_debug(CPUState *env, target_ulong addr,
uint8_t *buf, int len, int is_write);
void cpu_inject_x86_mce(CPUState *cenv, int bank, uint64_t status,
- uint64_t mcg_status, uint64_t addr, uint64_t misc);
+ uint64_t mcg_status, uint64_t addr, uint64_t misc,
+ int broadcast);
#endif /* CPU_ALL_H */
diff --git a/cpus.c b/cpus.c
index 0309189bfd..4c9928e2ce 100644
--- a/cpus.c
+++ b/cpus.c
@@ -735,9 +735,7 @@ static sigset_t block_io_signals(void)
void qemu_mutex_lock_iothread(void)
{
if (kvm_enabled()) {
- qemu_mutex_lock(&qemu_fair_mutex);
qemu_mutex_lock(&qemu_global_mutex);
- qemu_mutex_unlock(&qemu_fair_mutex);
} else {
qemu_mutex_lock(&qemu_fair_mutex);
if (qemu_mutex_trylock(&qemu_global_mutex)) {
diff --git a/hmp-commands.hx b/hmp-commands.hx
index a923817a1d..38e1eb7ebb 100644
--- a/hmp-commands.hx
+++ b/hmp-commands.hx
@@ -1152,9 +1152,9 @@ ETEXI
{
.name = "mce",
- .args_type = "cpu_index:i,bank:i,status:l,mcg_status:l,addr:l,misc:l",
- .params = "cpu bank status mcgstatus addr misc",
- .help = "inject a MCE on the given CPU",
+ .args_type = "broadcast:-b,cpu_index:i,bank:i,status:l,mcg_status:l,addr:l,misc:l",
+ .params = "[-b] cpu bank status mcgstatus addr misc",
+ .help = "inject a MCE on the given CPU [and broadcast to other CPUs with -b option]",
.mhandler.cmd = do_inject_mce,
},
diff --git a/kvm-all.c b/kvm-all.c
index 8f0e17cbf3..2ec9e0980d 100644
--- a/kvm-all.c
+++ b/kvm-all.c
@@ -63,9 +63,7 @@ struct KVMState
int fd;
int vmfd;
int coalesced_mmio;
-#ifdef KVM_CAP_COALESCED_MMIO
struct kvm_coalesced_mmio_ring *coalesced_mmio_ring;
-#endif
int broken_set_mem_region;
int migration_log;
int vcpu_events;
@@ -82,16 +80,24 @@ struct KVMState
static KVMState *kvm_state;
+static const KVMCapabilityInfo kvm_required_capabilites[] = {
+ KVM_CAP_INFO(USER_MEMORY),
+ KVM_CAP_INFO(DESTROY_MEMORY_REGION_WORKS),
+ KVM_CAP_LAST_INFO
+};
+
static KVMSlot *kvm_alloc_slot(KVMState *s)
{
int i;
for (i = 0; i < ARRAY_SIZE(s->slots); i++) {
/* KVM private memory slots */
- if (i >= 8 && i < 12)
+ if (i >= 8 && i < 12) {
continue;
- if (s->slots[i].memory_size == 0)
+ }
+ if (s->slots[i].memory_size == 0) {
return &s->slots[i];
+ }
}
fprintf(stderr, "%s: no free slot available\n", __func__);
@@ -225,11 +231,10 @@ int kvm_init_vcpu(CPUState *env)
goto err;
}
-#ifdef KVM_CAP_COALESCED_MMIO
- if (s->coalesced_mmio && !s->coalesced_mmio_ring)
- s->coalesced_mmio_ring = (void *) env->kvm_run +
- s->coalesced_mmio * PAGE_SIZE;
-#endif
+ if (s->coalesced_mmio && !s->coalesced_mmio_ring) {
+ s->coalesced_mmio_ring =
+ (void *)env->kvm_run + s->coalesced_mmio * PAGE_SIZE;
+ }
ret = kvm_arch_init_vcpu(env);
if (ret == 0) {
@@ -275,16 +280,14 @@ static int kvm_dirty_pages_log_change(target_phys_addr_t phys_addr,
int kvm_log_start(target_phys_addr_t phys_addr, ram_addr_t size)
{
- return kvm_dirty_pages_log_change(phys_addr, size,
- KVM_MEM_LOG_DIRTY_PAGES,
- KVM_MEM_LOG_DIRTY_PAGES);
+ return kvm_dirty_pages_log_change(phys_addr, size, KVM_MEM_LOG_DIRTY_PAGES,
+ KVM_MEM_LOG_DIRTY_PAGES);
}
int kvm_log_stop(target_phys_addr_t phys_addr, ram_addr_t size)
{
- return kvm_dirty_pages_log_change(phys_addr, size,
- 0,
- KVM_MEM_LOG_DIRTY_PAGES);
+ return kvm_dirty_pages_log_change(phys_addr, size, 0,
+ KVM_MEM_LOG_DIRTY_PAGES);
}
static int kvm_set_migration_log(int enable)
@@ -356,7 +359,7 @@ static int kvm_get_dirty_pages_log_range(unsigned long start_addr,
* @end_addr: end of logged region.
*/
static int kvm_physical_sync_dirty_bitmap(target_phys_addr_t start_addr,
- target_phys_addr_t end_addr)
+ target_phys_addr_t end_addr)
{
KVMState *s = kvm_state;
unsigned long size, allocated_size = 0;
@@ -400,7 +403,6 @@ static int kvm_physical_sync_dirty_bitmap(target_phys_addr_t start_addr,
int kvm_coalesce_mmio_region(target_phys_addr_t start, ram_addr_t size)
{
int ret = -ENOSYS;
-#ifdef KVM_CAP_COALESCED_MMIO
KVMState *s = kvm_state;
if (s->coalesced_mmio) {
@@ -411,7 +413,6 @@ int kvm_coalesce_mmio_region(target_phys_addr_t start, ram_addr_t size)
ret = kvm_vm_ioctl(s, KVM_REGISTER_COALESCED_MMIO, &zone);
}
-#endif
return ret;
}
@@ -419,7 +420,6 @@ int kvm_coalesce_mmio_region(target_phys_addr_t start, ram_addr_t size)
int kvm_uncoalesce_mmio_region(target_phys_addr_t start, ram_addr_t size)
{
int ret = -ENOSYS;
-#ifdef KVM_CAP_COALESCED_MMIO
KVMState *s = kvm_state;
if (s->coalesced_mmio) {
@@ -430,7 +430,6 @@ int kvm_uncoalesce_mmio_region(target_phys_addr_t start, ram_addr_t size)
ret = kvm_vm_ioctl(s, KVM_UNREGISTER_COALESCED_MMIO, &zone);
}
-#endif
return ret;
}
@@ -484,9 +483,20 @@ static int kvm_check_many_ioeventfds(void)
#endif
}
-static void kvm_set_phys_mem(target_phys_addr_t start_addr,
- ram_addr_t size,
- ram_addr_t phys_offset)
+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)
{
KVMState *s = kvm_state;
ram_addr_t flags = phys_offset & ~TARGET_PAGE_MASK;
@@ -593,13 +603,13 @@ static void kvm_set_phys_mem(target_phys_addr_t start_addr,
}
/* in case the KVM bug workaround already "consumed" the new slot */
- if (!size)
+ if (!size) {
return;
-
+ }
/* KVM does not need to know about this memory */
- if (flags >= IO_MEM_UNASSIGNED)
+ if (flags >= IO_MEM_UNASSIGNED) {
return;
-
+ }
mem = kvm_alloc_slot(s);
mem->memory_size = size;
mem->start_addr = start_addr;
@@ -615,38 +625,38 @@ static void kvm_set_phys_mem(target_phys_addr_t start_addr,
}
static void kvm_client_set_memory(struct CPUPhysMemoryClient *client,
- target_phys_addr_t start_addr,
- ram_addr_t size,
- ram_addr_t phys_offset)
+ target_phys_addr_t start_addr,
+ ram_addr_t size, ram_addr_t phys_offset)
{
- kvm_set_phys_mem(start_addr, size, phys_offset);
+ kvm_set_phys_mem(start_addr, size, phys_offset);
}
static int kvm_client_sync_dirty_bitmap(struct CPUPhysMemoryClient *client,
- target_phys_addr_t start_addr,
- target_phys_addr_t end_addr)
+ target_phys_addr_t start_addr,
+ target_phys_addr_t end_addr)
{
- return kvm_physical_sync_dirty_bitmap(start_addr, end_addr);
+ return kvm_physical_sync_dirty_bitmap(start_addr, end_addr);
}
static int kvm_client_migration_log(struct CPUPhysMemoryClient *client,
- int enable)
+ int enable)
{
- return kvm_set_migration_log(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,
+ .set_memory = kvm_client_set_memory,
+ .sync_dirty_bitmap = kvm_client_sync_dirty_bitmap,
+ .migration_log = kvm_client_migration_log,
};
-int kvm_init(int smp_cpus)
+int kvm_init(void)
{
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";
KVMState *s;
+ const KVMCapabilityInfo *missing_cap;
int ret;
int i;
@@ -655,9 +665,9 @@ int kvm_init(int smp_cpus)
#ifdef KVM_CAP_SET_GUEST_DEBUG
QTAILQ_INIT(&s->kvm_sw_breakpoints);
#endif
- for (i = 0; i < ARRAY_SIZE(s->slots); i++)
+ for (i = 0; i < ARRAY_SIZE(s->slots); i++) {
s->slots[i].slot = i;
-
+ }
s->vmfd = -1;
s->fd = qemu_open("/dev/kvm", O_RDWR);
if (s->fd == -1) {
@@ -668,8 +678,9 @@ int kvm_init(int smp_cpus)
ret = kvm_ioctl(s, KVM_GET_API_VERSION, 0);
if (ret < KVM_API_VERSION) {
- if (ret > 0)
+ if (ret > 0) {
ret = -EINVAL;
+ }
fprintf(stderr, "kvm version too old\n");
goto err;
}
@@ -689,39 +700,23 @@ int kvm_init(int smp_cpus)
goto err;
}
- /* initially, KVM allocated its own memory and we had to jump through
- * hooks to make phys_ram_base point to this. Modern versions of KVM
- * just use a user allocated buffer so we can use regular pages
- * unmodified. Make sure we have a sufficiently modern version of KVM.
- */
- if (!kvm_check_extension(s, KVM_CAP_USER_MEMORY)) {
- ret = -EINVAL;
- fprintf(stderr, "kvm does not support KVM_CAP_USER_MEMORY\n%s",
- upgrade_note);
- goto err;
+ missing_cap = kvm_check_extension_list(s, kvm_required_capabilites);
+ if (!missing_cap) {
+ missing_cap =
+ kvm_check_extension_list(s, kvm_arch_required_capabilities);
}
-
- /* There was a nasty bug in < kvm-80 that prevents memory slots from being
- * destroyed properly. Since we rely on this capability, refuse to work
- * with any kernel without this capability. */
- if (!kvm_check_extension(s, KVM_CAP_DESTROY_MEMORY_REGION_WORKS)) {
+ if (missing_cap) {
ret = -EINVAL;
-
- fprintf(stderr,
- "KVM kernel module broken (DESTROY_MEMORY_REGION).\n%s",
- upgrade_note);
+ fprintf(stderr, "kvm does not support %s\n%s",
+ missing_cap->name, upgrade_note);
goto err;
}
- s->coalesced_mmio = 0;
-#ifdef KVM_CAP_COALESCED_MMIO
s->coalesced_mmio = kvm_check_extension(s, KVM_CAP_COALESCED_MMIO);
- s->coalesced_mmio_ring = NULL;
-#endif
s->broken_set_mem_region = 1;
#ifdef KVM_CAP_JOIN_MEMORY_REGIONS_WORKS
- ret = kvm_ioctl(s, KVM_CHECK_EXTENSION, KVM_CAP_JOIN_MEMORY_REGIONS_WORKS);
+ ret = kvm_check_extension(s, KVM_CAP_JOIN_MEMORY_REGIONS_WORKS);
if (ret > 0) {
s->broken_set_mem_region = 0;
}
@@ -753,9 +748,10 @@ int kvm_init(int smp_cpus)
s->xcrs = kvm_check_extension(s, KVM_CAP_XCRS);
#endif
- ret = kvm_arch_init(s, smp_cpus);
- if (ret < 0)
+ ret = kvm_arch_init(s);
+ if (ret < 0) {
goto err;
+ }
kvm_state = s;
cpu_register_phys_memory_client(&kvm_cpu_phys_memory_client);
@@ -766,10 +762,12 @@ int kvm_init(int smp_cpus)
err:
if (s) {
- if (s->vmfd != -1)
+ if (s->vmfd != -1) {
close(s->vmfd);
- if (s->fd != -1)
+ }
+ if (s->fd != -1) {
close(s->fd);
+ }
}
qemu_free(s);
@@ -816,36 +814,36 @@ static int kvm_handle_io(uint16_t port, void *data, int direction, int size,
}
#ifdef KVM_CAP_INTERNAL_ERROR_DATA
-static void kvm_handle_internal_error(CPUState *env, struct kvm_run *run)
+static int kvm_handle_internal_error(CPUState *env, struct kvm_run *run)
{
-
+ fprintf(stderr, "KVM internal error.");
if (kvm_check_extension(kvm_state, KVM_CAP_INTERNAL_ERROR_DATA)) {
int i;
- fprintf(stderr, "KVM internal error. Suberror: %d\n",
- run->internal.suberror);
-
+ fprintf(stderr, " Suberror: %d\n", run->internal.suberror);
for (i = 0; i < run->internal.ndata; ++i) {
fprintf(stderr, "extra data[%d]: %"PRIx64"\n",
i, (uint64_t)run->internal.data[i]);
}
+ } else {
+ fprintf(stderr, "\n");
}
- cpu_dump_state(env, stderr, fprintf, 0);
if (run->internal.suberror == KVM_INTERNAL_ERROR_EMULATION) {
fprintf(stderr, "emulation failure\n");
- if (!kvm_arch_stop_on_emulation_error(env))
- return;
+ if (!kvm_arch_stop_on_emulation_error(env)) {
+ cpu_dump_state(env, stderr, fprintf, CPU_DUMP_CODE);
+ return 0;
+ }
}
/* FIXME: Should trigger a qmp message to let management know
* something went wrong.
*/
- vm_stop(0);
+ return -1;
}
#endif
void kvm_flush_coalesced_mmio_buffer(void)
{
-#ifdef KVM_CAP_COALESCED_MMIO
KVMState *s = kvm_state;
if (s->coalesced_mmio_ring) {
struct kvm_coalesced_mmio_ring *ring = s->coalesced_mmio_ring;
@@ -859,7 +857,6 @@ void kvm_flush_coalesced_mmio_buffer(void)
ring->first = (ring->first + 1) % KVM_COALESCED_MMIO_MAX;
}
}
-#endif
}
static void do_kvm_cpu_synchronize_state(void *_env)
@@ -874,8 +871,9 @@ static void do_kvm_cpu_synchronize_state(void *_env)
void kvm_cpu_synchronize_state(CPUState *env)
{
- if (!env->kvm_vcpu_dirty)
+ if (!env->kvm_vcpu_dirty) {
run_on_cpu(env, do_kvm_cpu_synchronize_state, env);
+ }
}
void kvm_cpu_synchronize_post_reset(CPUState *env)
@@ -924,6 +922,8 @@ int kvm_cpu_exec(CPUState *env)
cpu_single_env = env;
kvm_arch_post_run(env, run);
+ kvm_flush_coalesced_mmio_buffer();
+
if (ret == -EINTR || ret == -EAGAIN) {
cpu_exit(env);
DPRINTF("io window exit\n");
@@ -936,8 +936,6 @@ int kvm_cpu_exec(CPUState *env)
abort();
}
- kvm_flush_coalesced_mmio_buffer();
-
ret = 0; /* exit loop */
switch (run->exit_reason) {
case KVM_EXIT_IO:
@@ -965,17 +963,13 @@ int kvm_cpu_exec(CPUState *env)
ret = 1;
break;
case KVM_EXIT_UNKNOWN:
- DPRINTF("kvm_exit_unknown\n");
- break;
- case KVM_EXIT_FAIL_ENTRY:
- DPRINTF("kvm_exit_fail_entry\n");
- break;
- case KVM_EXIT_EXCEPTION:
- DPRINTF("kvm_exit_exception\n");
+ fprintf(stderr, "KVM: unknown exit, hardware reason %" PRIx64 "\n",
+ (uint64_t)run->hw.hardware_exit_reason);
+ ret = -1;
break;
#ifdef KVM_CAP_INTERNAL_ERROR_DATA
case KVM_EXIT_INTERNAL_ERROR:
- kvm_handle_internal_error(env, run);
+ ret = kvm_handle_internal_error(env, run);
break;
#endif
case KVM_EXIT_DEBUG:
@@ -996,6 +990,11 @@ int kvm_cpu_exec(CPUState *env)
}
} while (ret > 0);
+ if (ret < 0) {
+ cpu_dump_state(env, stderr, fprintf, CPU_DUMP_CODE);
+ vm_stop(0);
+ env->exit_request = 1;
+ }
if (env->exit_request) {
env->exit_request = 0;
env->exception_index = EXCP_INTERRUPT;
@@ -1015,9 +1014,9 @@ int kvm_ioctl(KVMState *s, int type, ...)
va_end(ap);
ret = ioctl(s->fd, type, arg);
- if (ret == -1)
+ if (ret == -1) {
ret = -errno;
-
+ }
return ret;
}
@@ -1032,9 +1031,9 @@ int kvm_vm_ioctl(KVMState *s, int type, ...)
va_end(ap);
ret = ioctl(s->vmfd, type, arg);
- if (ret == -1)
+ if (ret == -1) {
ret = -errno;
-
+ }
return ret;
}
@@ -1049,21 +1048,15 @@ int kvm_vcpu_ioctl(CPUState *env, int type, ...)
va_end(ap);
ret = ioctl(env->kvm_fd, type, arg);
- if (ret == -1)
+ if (ret == -1) {
ret = -errno;
-
+ }
return ret;
}
int kvm_has_sync_mmu(void)
{
-#ifdef KVM_CAP_SYNC_MMU
- KVMState *s = kvm_state;
-
- return kvm_check_extension(s, KVM_CAP_SYNC_MMU);
-#else
- return 0;
-#endif
+ return kvm_check_extension(kvm_state, KVM_CAP_SYNC_MMU);
}
int kvm_has_vcpu_events(void)
@@ -1120,8 +1113,9 @@ struct kvm_sw_breakpoint *kvm_find_sw_breakpoint(CPUState *env,
struct kvm_sw_breakpoint *bp;
QTAILQ_FOREACH(bp, &env->kvm_state->kvm_sw_breakpoints, entry) {
- if (bp->pc == pc)
+ if (bp->pc == pc) {
return bp;
+ }
}
return NULL;
}
@@ -1176,8 +1170,9 @@ int kvm_insert_breakpoint(CPUState *current_env, target_ulong addr,
}
bp = qemu_malloc(sizeof(struct kvm_sw_breakpoint));
- if (!bp)
+ if (!bp) {
return -ENOMEM;
+ }
bp->pc = addr;
bp->use_count = 1;
@@ -1191,14 +1186,16 @@ int kvm_insert_breakpoint(CPUState *current_env, target_ulong addr,
bp, entry);
} else {
err = kvm_arch_insert_hw_breakpoint(addr, len, type);
- if (err)
+ if (err) {
return err;
+ }
}
for (env = first_cpu; env != NULL; env = env->next_cpu) {
err = kvm_update_guest_debug(env, 0);
- if (err)
+ if (err) {
return err;
+ }
}
return 0;
}
@@ -1212,8 +1209,9 @@ int kvm_remove_breakpoint(CPUState *current_env, target_ulong addr,
if (type == GDB_BREAKPOINT_SW) {
bp = kvm_find_sw_breakpoint(current_env, addr);
- if (!bp)
+ if (!bp) {
return -ENOENT;
+ }
if (bp->use_count > 1) {
bp->use_count--;
@@ -1221,21 +1219,24 @@ int kvm_remove_breakpoint(CPUState *current_env, target_ulong addr,
}
err = kvm_arch_remove_sw_breakpoint(current_env, bp);
- if (err)
+ if (err) {
return err;
+ }
QTAILQ_REMOVE(&current_env->kvm_state->kvm_sw_breakpoints, bp, entry);
qemu_free(bp);
} else {
err = kvm_arch_remove_hw_breakpoint(addr, len, type);
- if (err)
+ if (err) {
return err;
+ }
}
for (env = first_cpu; env != NULL; env = env->next_cpu) {
err = kvm_update_guest_debug(env, 0);
- if (err)
+ if (err) {
return err;
+ }
}
return 0;
}
@@ -1250,15 +1251,17 @@ void kvm_remove_all_breakpoints(CPUState *current_env)
if (kvm_arch_remove_sw_breakpoint(current_env, bp) != 0) {
/* Try harder to find a CPU that currently sees the breakpoint. */
for (env = first_cpu; env != NULL; env = env->next_cpu) {
- if (kvm_arch_remove_sw_breakpoint(env, bp) == 0)
+ if (kvm_arch_remove_sw_breakpoint(env, bp) == 0) {
break;
+ }
}
}
}
kvm_arch_remove_all_hw_breakpoints();
- for (env = first_cpu; env != NULL; env = env->next_cpu)
+ for (env = first_cpu; env != NULL; env = env->next_cpu) {
kvm_update_guest_debug(env, 0);
+ }
}
#else /* !KVM_CAP_SET_GUEST_DEBUG */
@@ -1290,8 +1293,9 @@ int kvm_set_signal_mask(CPUState *env, const sigset_t *sigset)
struct kvm_signal_mask *sigmask;
int r;
- if (!sigset)
+ if (!sigset) {
return kvm_vcpu_ioctl(env, KVM_SET_SIGNAL_MASK, NULL);
+ }
sigmask = qemu_malloc(sizeof(*sigmask) + sizeof(*sigset));
@@ -1346,13 +1350,16 @@ int kvm_set_ioeventfd_pio_word(int fd, uint16_t addr, uint16_t val, bool assign)
.fd = fd,
};
int r;
- if (!kvm_enabled())
+ if (!kvm_enabled()) {
return -ENOSYS;
- if (!assign)
+ }
+ if (!assign) {
kick.flags |= KVM_IOEVENTFD_FLAG_DEASSIGN;
+ }
r = kvm_vm_ioctl(kvm_state, KVM_IOEVENTFD, &kick);
- if (r < 0)
+ if (r < 0) {
return r;
+ }
return 0;
#else
return -ENOSYS;
diff --git a/kvm-stub.c b/kvm-stub.c
index 33d4476fa3..88682f288b 100644
--- a/kvm-stub.c
+++ b/kvm-stub.c
@@ -58,7 +58,7 @@ int kvm_check_extension(KVMState *s, unsigned int extension)
return 0;
}
-int kvm_init(int smp_cpus)
+int kvm_init(void)
{
return -ENOSYS;
}
diff --git a/kvm.h b/kvm.h
index ce08d42756..ca57517af2 100644
--- a/kvm.h
+++ b/kvm.h
@@ -32,9 +32,17 @@ extern int kvm_allowed;
struct kvm_run;
+typedef struct KVMCapabilityInfo {
+ const char *name;
+ int value;
+} KVMCapabilityInfo;
+
+#define KVM_CAP_INFO(CAP) { "KVM_CAP_" stringify(CAP), KVM_CAP_##CAP }
+#define KVM_CAP_LAST_INFO { NULL, 0 }
+
/* external API */
-int kvm_init(int smp_cpus);
+int kvm_init(void);
int kvm_has_sync_mmu(void);
int kvm_has_vcpu_events(void);
@@ -86,6 +94,8 @@ int kvm_vcpu_ioctl(CPUState *env, int type, ...);
/* Arch specific hooks */
+extern const KVMCapabilityInfo kvm_arch_required_capabilities[];
+
int kvm_arch_post_run(CPUState *env, struct kvm_run *run);
int kvm_arch_handle_exit(CPUState *env, struct kvm_run *run);
@@ -105,7 +115,7 @@ int kvm_arch_get_registers(CPUState *env);
int kvm_arch_put_registers(CPUState *env, int level);
-int kvm_arch_init(KVMState *s, int smp_cpus);
+int kvm_arch_init(KVMState *s);
int kvm_arch_init_vcpu(CPUState *env);
diff --git a/monitor.c b/monitor.c
index acbe0e6b30..34c347c0fb 100644
--- a/monitor.c
+++ b/monitor.c
@@ -2709,12 +2709,15 @@ static void do_inject_mce(Monitor *mon, const QDict *qdict)
uint64_t mcg_status = qdict_get_int(qdict, "mcg_status");
uint64_t addr = qdict_get_int(qdict, "addr");
uint64_t misc = qdict_get_int(qdict, "misc");
+ int broadcast = qdict_get_try_bool(qdict, "broadcast", 0);
- for (cenv = first_cpu; cenv != NULL; cenv = cenv->next_cpu)
+ for (cenv = first_cpu; cenv != NULL; cenv = cenv->next_cpu) {
if (cenv->cpu_index == cpu_index && cenv->mcg_cap) {
- cpu_inject_x86_mce(cenv, bank, status, mcg_status, addr, misc);
+ cpu_inject_x86_mce(cenv, bank, status, mcg_status, addr, misc,
+ broadcast);
break;
}
+ }
}
#endif
diff --git a/target-i386/cpu.h b/target-i386/cpu.h
index f0c07cde3b..af701a4412 100644
--- a/target-i386/cpu.h
+++ b/target-i386/cpu.h
@@ -699,6 +699,10 @@ typedef struct CPUX86State {
uint32_t smbase;
int old_exception; /* exception in flight */
+ /* KVM states, automatically cleared on reset */
+ uint8_t nmi_injected;
+ uint8_t nmi_pending;
+
CPU_COMMON
/* processor features (e.g. for CPUID insn) */
@@ -726,8 +730,6 @@ typedef struct CPUX86State {
int32_t exception_injected;
int32_t interrupt_injected;
uint8_t soft_interrupt;
- uint8_t nmi_injected;
- uint8_t nmi_pending;
uint8_t has_error_code;
uint32_t sipi_vector;
uint32_t cpuid_kvm_features;
@@ -760,6 +762,7 @@ int cpu_x86_exec(CPUX86State *s);
void cpu_x86_close(CPUX86State *s);
void x86_cpu_list (FILE *f, fprintf_function cpu_fprintf, const char *optarg);
void x86_cpudef_setup(void);
+int cpu_x86_support_mca_broadcast(CPUState *env);
int cpu_get_pic_interrupt(CPUX86State *s);
/* MSDOS compatibility mode FPU exception support */
@@ -873,6 +876,8 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
uint32_t *ecx, uint32_t *edx);
int cpu_x86_register (CPUX86State *env, const char *cpu_model);
void cpu_clear_apic_feature(CPUX86State *env);
+void host_cpuid(uint32_t function, uint32_t count,
+ uint32_t *eax, uint32_t *ebx, uint32_t *ecx, uint32_t *edx);
/* helper.c */
int cpu_x86_handle_mmu_fault(CPUX86State *env, target_ulong addr,
diff --git a/target-i386/cpuid.c b/target-i386/cpuid.c
index 165045ec42..5382a283f5 100644
--- a/target-i386/cpuid.c
+++ b/target-i386/cpuid.c
@@ -103,9 +103,8 @@ typedef struct model_features_t {
int check_cpuid = 0;
int enforce_cpuid = 0;
-static void host_cpuid(uint32_t function, uint32_t count,
- uint32_t *eax, uint32_t *ebx,
- uint32_t *ecx, uint32_t *edx)
+void host_cpuid(uint32_t function, uint32_t count,
+ uint32_t *eax, uint32_t *ebx, uint32_t *ecx, uint32_t *edx)
{
#if defined(CONFIG_KVM)
uint32_t vec[4];
diff --git a/target-i386/helper.c b/target-i386/helper.c
index 25a3e36138..1217452e71 100644
--- a/target-i386/helper.c
+++ b/target-i386/helper.c
@@ -110,6 +110,32 @@ void cpu_x86_close(CPUX86State *env)
qemu_free(env);
}
+static void cpu_x86_version(CPUState *env, int *family, int *model)
+{
+ int cpuver = env->cpuid_version;
+
+ if (family == NULL || model == NULL) {
+ return;
+ }
+
+ *family = (cpuver >> 8) & 0x0f;
+ *model = ((cpuver >> 12) & 0xf0) + ((cpuver >> 4) & 0x0f);
+}
+
+/* Broadcast MCA signal for processor version 06H_EH and above */
+int cpu_x86_support_mca_broadcast(CPUState *env)
+{
+ int family = 0;
+ int model = 0;
+
+ cpu_x86_version(env, &family, &model);
+ if ((family == 6 && model >= 14) || family > 6) {
+ return 1;
+ }
+
+ return 0;
+}
+
/***********************************************************/
/* x86 debug */
@@ -223,6 +249,9 @@ done:
cpu_fprintf(f, "\n");
}
+#define DUMP_CODE_BYTES_TOTAL 50
+#define DUMP_CODE_BYTES_BACKWARD 20
+
void cpu_dump_state(CPUState *env, FILE *f, fprintf_function cpu_fprintf,
int flags)
{
@@ -408,6 +437,24 @@ void cpu_dump_state(CPUState *env, FILE *f, fprintf_function cpu_fprintf,
cpu_fprintf(f, " ");
}
}
+ if (flags & CPU_DUMP_CODE) {
+ target_ulong base = env->segs[R_CS].base + env->eip;
+ target_ulong offs = MIN(env->eip, DUMP_CODE_BYTES_BACKWARD);
+ uint8_t code;
+ char codestr[3];
+
+ cpu_fprintf(f, "Code=");
+ for (i = 0; i < DUMP_CODE_BYTES_TOTAL; i++) {
+ if (cpu_memory_rw_debug(env, base - offs + i, &code, 1, 0) == 0) {
+ snprintf(codestr, sizeof(codestr), "%02x", code);
+ } else {
+ snprintf(codestr, sizeof(codestr), "??");
+ }
+ cpu_fprintf(f, "%s%s%s%s", i > 0 ? " " : "",
+ i == offs ? "<" : "", codestr, i == offs ? ">" : "");
+ }
+ cpu_fprintf(f, "\n");
+ }
}
/***********************************************************/
@@ -1021,21 +1068,12 @@ static void breakpoint_handler(CPUState *env)
/* This should come from sysemu.h - if we could include it here... */
void qemu_system_reset_request(void);
-void cpu_inject_x86_mce(CPUState *cenv, int bank, uint64_t status,
+static void qemu_inject_x86_mce(CPUState *cenv, int bank, uint64_t status,
uint64_t mcg_status, uint64_t addr, uint64_t misc)
{
uint64_t mcg_cap = cenv->mcg_cap;
- unsigned bank_num = mcg_cap & 0xff;
uint64_t *banks = cenv->mce_banks;
- if (bank >= bank_num || !(status & MCI_STATUS_VAL))
- return;
-
- if (kvm_enabled()) {
- kvm_inject_x86_mce(cenv, bank, status, mcg_status, addr, misc, 0);
- return;
- }
-
/*
* if MSR_MCG_CTL is not all 1s, the uncorrected error
* reporting is disabled
@@ -1076,6 +1114,45 @@ void cpu_inject_x86_mce(CPUState *cenv, int bank, uint64_t status,
} else
banks[1] |= MCI_STATUS_OVER;
}
+
+void cpu_inject_x86_mce(CPUState *cenv, int bank, uint64_t status,
+ uint64_t mcg_status, uint64_t addr, uint64_t misc,
+ int broadcast)
+{
+ unsigned bank_num = cenv->mcg_cap & 0xff;
+ CPUState *env;
+ int flag = 0;
+
+ if (bank >= bank_num || !(status & MCI_STATUS_VAL)) {
+ return;
+ }
+
+ if (broadcast) {
+ if (!cpu_x86_support_mca_broadcast(cenv)) {
+ fprintf(stderr, "Current CPU does not support broadcast\n");
+ return;
+ }
+ }
+
+ if (kvm_enabled()) {
+ if (broadcast) {
+ flag |= MCE_BROADCAST;
+ }
+
+ kvm_inject_x86_mce(cenv, bank, status, mcg_status, addr, misc, flag);
+ } else {
+ qemu_inject_x86_mce(cenv, bank, status, mcg_status, addr, misc);
+ if (broadcast) {
+ for (env = first_cpu; env != NULL; env = env->next_cpu) {
+ if (cenv == env) {
+ continue;
+ }
+
+ qemu_inject_x86_mce(env, 1, 0xa000000000000000, 0, 0, 0);
+ }
+ }
+ }
+}
#endif /* !CONFIG_USER_ONLY */
static void mce_init(CPUX86State *cenv)
diff --git a/target-i386/kvm.c b/target-i386/kvm.c
index 7dfc357e42..05010bbc38 100644
--- a/target-i386/kvm.c
+++ b/target-i386/kvm.c
@@ -54,9 +54,19 @@
#define BUS_MCEERR_AO 5
#endif
-static int lm_capable_kernel;
+const KVMCapabilityInfo kvm_arch_required_capabilities[] = {
+ KVM_CAP_INFO(SET_TSS_ADDR),
+ KVM_CAP_INFO(EXT_CPUID),
+ KVM_CAP_INFO(MP_STATE),
+ KVM_CAP_LAST_INFO
+};
-#ifdef KVM_CAP_EXT_CPUID
+static bool has_msr_star;
+static bool has_msr_hsave_pa;
+#if defined(CONFIG_KVM_PARA) && defined(KVM_CAP_ASYNC_PF)
+static bool has_msr_async_pf_en;
+#endif
+static int lm_capable_kernel;
static struct kvm_cpuid2 *try_get_cpuid(KVMState *s, int max)
{
@@ -91,10 +101,6 @@ uint32_t kvm_arch_get_supported_cpuid(CPUState *env, uint32_t function,
uint32_t ret = 0;
uint32_t cpuid_1_edx;
- if (!kvm_check_extension(env->kvm_state, KVM_CAP_EXT_CPUID)) {
- return -1U;
- }
-
max = 1;
while ((cpuid = try_get_cpuid(env->kvm_state, max)) == NULL) {
max *= 2;
@@ -138,46 +144,33 @@ uint32_t kvm_arch_get_supported_cpuid(CPUState *env, uint32_t function,
return ret;
}
-#else
-
-uint32_t kvm_arch_get_supported_cpuid(CPUState *env, uint32_t function,
- uint32_t index, int reg)
-{
- return -1U;
-}
-
-#endif
-
#ifdef CONFIG_KVM_PARA
struct kvm_para_features {
- int cap;
- int feature;
+ int cap;
+ int feature;
} para_features[] = {
-#ifdef KVM_CAP_CLOCKSOURCE
- { KVM_CAP_CLOCKSOURCE, KVM_FEATURE_CLOCKSOURCE },
-#endif
-#ifdef KVM_CAP_NOP_IO_DELAY
- { KVM_CAP_NOP_IO_DELAY, KVM_FEATURE_NOP_IO_DELAY },
-#endif
-#ifdef KVM_CAP_PV_MMU
- { KVM_CAP_PV_MMU, KVM_FEATURE_MMU_OP },
-#endif
+ { KVM_CAP_CLOCKSOURCE, KVM_FEATURE_CLOCKSOURCE },
+ { KVM_CAP_NOP_IO_DELAY, KVM_FEATURE_NOP_IO_DELAY },
+ { KVM_CAP_PV_MMU, KVM_FEATURE_MMU_OP },
#ifdef KVM_CAP_ASYNC_PF
- { KVM_CAP_ASYNC_PF, KVM_FEATURE_ASYNC_PF },
+ { KVM_CAP_ASYNC_PF, KVM_FEATURE_ASYNC_PF },
#endif
- { -1, -1 }
+ { -1, -1 }
};
static int get_para_features(CPUState *env)
{
- int i, features = 0;
+ int i, features = 0;
- for (i = 0; i < ARRAY_SIZE(para_features) - 1; i++) {
- if (kvm_check_extension(env->kvm_state, para_features[i].cap))
- features |= (1 << para_features[i].feature);
+ for (i = 0; i < ARRAY_SIZE(para_features) - 1; i++) {
+ if (kvm_check_extension(env->kvm_state, para_features[i].cap)) {
+ features |= (1 << para_features[i].feature);
}
-
- return features;
+ }
+#ifdef KVM_CAP_ASYNC_PF
+ has_msr_async_pf_en = features & (1 << KVM_FEATURE_ASYNC_PF);
+#endif
+ return features;
}
#endif
@@ -187,7 +180,7 @@ static int kvm_get_mce_cap_supported(KVMState *s, uint64_t *mce_cap,
{
int r;
- r = kvm_ioctl(s, KVM_CHECK_EXTENSION, KVM_CAP_MCE);
+ r = kvm_check_extension(s, KVM_CAP_MCE);
if (r > 0) {
*max_banks = r;
return kvm_ioctl(s, KVM_X86_GET_MCE_CAP_SUPPORTED, mce_cap);
@@ -219,7 +212,7 @@ static int kvm_get_msr(CPUState *env, struct kvm_msr_entry *msrs, int n)
}
/* FIXME: kill this and kvm_get_msr, use env->mcg_status instead */
-static int kvm_mce_in_exception(CPUState *env)
+static int kvm_mce_in_progress(CPUState *env)
{
struct kvm_msr_entry msr_mcg_status = {
.index = MSR_MCG_STATUS,
@@ -228,7 +221,8 @@ static int kvm_mce_in_exception(CPUState *env)
r = kvm_get_msr(env, &msr_mcg_status, 1);
if (r == -1 || r == 0) {
- return -1;
+ fprintf(stderr, "Failed to get MCE status\n");
+ return 0;
}
return !!(msr_mcg_status.data & MCG_STATUS_MCIP);
}
@@ -248,10 +242,7 @@ static void kvm_do_inject_x86_mce(void *_data)
/* If there is an MCE exception being processed, ignore this SRAO MCE */
if ((data->env->mcg_cap & MCG_SER_P) &&
!(data->mce->status & MCI_STATUS_AR)) {
- r = kvm_mce_in_exception(data->env);
- if (r == -1) {
- fprintf(stderr, "Failed to get MCE status\n");
- } else if (r) {
+ if (kvm_mce_in_progress(data->env)) {
return;
}
}
@@ -264,11 +255,30 @@ static void kvm_do_inject_x86_mce(void *_data)
}
}
}
+
+static void kvm_inject_x86_mce_on(CPUState *env, struct kvm_x86_mce *mce,
+ int flag)
+{
+ struct kvm_x86_mce_data data = {
+ .env = env,
+ .mce = mce,
+ .abort_on_error = (flag & ABORT_ON_ERROR),
+ };
+
+ if (!env->mcg_cap) {
+ fprintf(stderr, "MCE support is not enabled!\n");
+ return;
+ }
+
+ run_on_cpu(env, kvm_do_inject_x86_mce, &data);
+}
+
+static void kvm_mce_broadcast_rest(CPUState *env);
#endif
void kvm_inject_x86_mce(CPUState *cenv, int bank, uint64_t status,
uint64_t mcg_status, uint64_t addr, uint64_t misc,
- int abort_on_error)
+ int flag)
{
#ifdef KVM_CAP_MCE
struct kvm_x86_mce mce = {
@@ -278,20 +288,16 @@ void kvm_inject_x86_mce(CPUState *cenv, int bank, uint64_t status,
.addr = addr,
.misc = misc,
};
- struct kvm_x86_mce_data data = {
- .env = cenv,
- .mce = &mce,
- };
- if (!cenv->mcg_cap) {
- fprintf(stderr, "MCE support is not enabled!\n");
- return;
+ if (flag & MCE_BROADCAST) {
+ kvm_mce_broadcast_rest(cenv);
}
- run_on_cpu(cenv, kvm_do_inject_x86_mce, &data);
+ kvm_inject_x86_mce_on(cenv, &mce, flag);
#else
- if (abort_on_error)
+ if (flag & ABORT_ON_ERROR) {
abort();
+ }
#endif
}
@@ -304,12 +310,10 @@ int kvm_arch_init_vcpu(CPUState *env)
uint32_t limit, i, j, cpuid_i;
uint32_t unused;
struct kvm_cpuid_entry2 *c;
-#ifdef KVM_CPUID_SIGNATURE
+#ifdef CONFIG_KVM_PARA
uint32_t signature[3];
#endif
- env->mp_state = KVM_MP_STATE_RUNNABLE;
-
env->cpuid_features &= kvm_arch_get_supported_cpuid(env, 1, 0, R_EDX);
i = env->cpuid_ext_features & CPUID_EXT_HYPERVISOR;
@@ -376,13 +380,15 @@ int kvm_arch_init_vcpu(CPUState *env)
c->index = j;
cpu_x86_cpuid(env, i, j, &c->eax, &c->ebx, &c->ecx, &c->edx);
- if (i == 4 && c->eax == 0)
+ if (i == 4 && c->eax == 0) {
break;
- if (i == 0xb && !(c->ecx & 0xff00))
+ }
+ if (i == 0xb && !(c->ecx & 0xff00)) {
break;
- if (i == 0xd && c->eax == 0)
+ }
+ if (i == 0xd && c->eax == 0) {
break;
-
+ }
c = &cpuid_data.entries[cpuid_i++];
}
break;
@@ -412,17 +418,18 @@ int kvm_arch_init_vcpu(CPUState *env)
uint64_t mcg_cap;
int banks;
- if (kvm_get_mce_cap_supported(env->kvm_state, &mcg_cap, &banks))
+ if (kvm_get_mce_cap_supported(env->kvm_state, &mcg_cap, &banks)) {
perror("kvm_get_mce_cap_supported FAILED");
- else {
+ } else {
if (banks > MCE_BANKS_DEF)
banks = MCE_BANKS_DEF;
mcg_cap &= MCE_CAP_DEF;
mcg_cap |= banks;
- if (kvm_setup_mce(env, &mcg_cap))
+ if (kvm_setup_mce(env, &mcg_cap)) {
perror("kvm_setup_mce FAILED");
- else
+ } else {
env->mcg_cap = mcg_cap;
+ }
}
}
#endif
@@ -434,8 +441,7 @@ void kvm_arch_reset_vcpu(CPUState *env)
{
env->exception_injected = -1;
env->interrupt_injected = -1;
- env->nmi_injected = 0;
- env->nmi_pending = 0;
+ env->xcr0 = 1;
if (kvm_irqchip_in_kernel()) {
env->mp_state = cpu_is_bsp(env) ? KVM_MP_STATE_RUNNABLE :
KVM_MP_STATE_UNINITIALIZED;
@@ -444,13 +450,10 @@ void kvm_arch_reset_vcpu(CPUState *env)
}
}
-int has_msr_star;
-int has_msr_hsave_pa;
-
-static void kvm_supported_msrs(CPUState *env)
+static int kvm_get_supported_msrs(KVMState *s)
{
static int kvm_supported_msrs;
- int ret;
+ int ret = 0;
/* first time */
if (kvm_supported_msrs == 0) {
@@ -461,9 +464,9 @@ static void kvm_supported_msrs(CPUState *env)
/* Obtain MSR list from KVM. These are the MSRs that we must
* save/restore */
msr_list.nmsrs = 0;
- ret = kvm_ioctl(env->kvm_state, KVM_GET_MSR_INDEX_LIST, &msr_list);
+ ret = kvm_ioctl(s, KVM_GET_MSR_INDEX_LIST, &msr_list);
if (ret < 0 && ret != -E2BIG) {
- return;
+ return ret;
}
/* Old kernel modules had a bug and could write beyond the provided
memory. Allocate at least a safe amount of 1K. */
@@ -472,17 +475,17 @@ static void kvm_supported_msrs(CPUState *env)
sizeof(msr_list.indices[0])));
kvm_msr_list->nmsrs = msr_list.nmsrs;
- ret = kvm_ioctl(env->kvm_state, KVM_GET_MSR_INDEX_LIST, kvm_msr_list);
+ ret = kvm_ioctl(s, KVM_GET_MSR_INDEX_LIST, kvm_msr_list);
if (ret >= 0) {
int i;
for (i = 0; i < kvm_msr_list->nmsrs; i++) {
if (kvm_msr_list->indices[i] == MSR_STAR) {
- has_msr_star = 1;
+ has_msr_star = true;
continue;
}
if (kvm_msr_list->indices[i] == MSR_VM_HSAVE_PA) {
- has_msr_hsave_pa = 1;
+ has_msr_hsave_pa = true;
continue;
}
}
@@ -491,80 +494,61 @@ static void kvm_supported_msrs(CPUState *env)
free(kvm_msr_list);
}
- return;
-}
-
-static int kvm_has_msr_hsave_pa(CPUState *env)
-{
- kvm_supported_msrs(env);
- return has_msr_hsave_pa;
-}
-
-static int kvm_has_msr_star(CPUState *env)
-{
- kvm_supported_msrs(env);
- return has_msr_star;
+ return ret;
}
-static int kvm_init_identity_map_page(KVMState *s)
+int kvm_arch_init(KVMState *s)
{
-#ifdef KVM_CAP_SET_IDENTITY_MAP_ADDR
+ uint64_t identity_base = 0xfffbc000;
int ret;
- uint64_t addr = 0xfffbc000;
-
- if (!kvm_check_extension(s, KVM_CAP_SET_IDENTITY_MAP_ADDR)) {
- return 0;
- }
+ struct utsname utsname;
- ret = kvm_vm_ioctl(s, KVM_SET_IDENTITY_MAP_ADDR, &addr);
+ ret = kvm_get_supported_msrs(s);
if (ret < 0) {
- fprintf(stderr, "kvm_set_identity_map_addr: %s\n", strerror(ret));
return ret;
}
-#endif
- return 0;
-}
-
-int kvm_arch_init(KVMState *s, int smp_cpus)
-{
- int ret;
-
- struct utsname utsname;
uname(&utsname);
lm_capable_kernel = strcmp(utsname.machine, "x86_64") == 0;
- /* create vm86 tss. KVM uses vm86 mode to emulate 16-bit code
- * directly. In order to use vm86 mode, a TSS is needed. Since this
- * must be part of guest physical memory, we need to allocate it. Older
- * versions of KVM just assumed that it would be at the end of physical
- * memory but that doesn't work with more than 4GB of memory. We simply
- * refuse to work with those older versions of KVM. */
- ret = kvm_ioctl(s, KVM_CHECK_EXTENSION, KVM_CAP_SET_TSS_ADDR);
- if (ret <= 0) {
- fprintf(stderr, "kvm does not support KVM_CAP_SET_TSS_ADDR\n");
- return ret;
- }
-
- /* this address is 3 pages before the bios, and the bios should present
- * as unavaible memory. FIXME, need to ensure the e820 map deals with
- * this?
- */
/*
- * Tell fw_cfg to notify the BIOS to reserve the range.
+ * On older Intel CPUs, KVM uses vm86 mode to emulate 16-bit code directly.
+ * In order to use vm86 mode, an EPT identity map and a TSS are needed.
+ * Since these must be part of guest physical memory, we need to allocate
+ * them, both by setting their start addresses in the kernel and by
+ * creating a corresponding e820 entry. We need 4 pages before the BIOS.
+ *
+ * Older KVM versions may not support setting the identity map base. In
+ * that case we need to stick with the default, i.e. a 256K maximum BIOS
+ * size.
*/
- if (e820_add_entry(0xfffbc000, 0x4000, E820_RESERVED) < 0) {
- perror("e820_add_entry() table is full");
- exit(1);
+#ifdef KVM_CAP_SET_IDENTITY_MAP_ADDR
+ if (kvm_check_extension(s, KVM_CAP_SET_IDENTITY_MAP_ADDR)) {
+ /* Allows up to 16M BIOSes. */
+ identity_base = 0xfeffc000;
+
+ ret = kvm_vm_ioctl(s, KVM_SET_IDENTITY_MAP_ADDR, &identity_base);
+ if (ret < 0) {
+ return ret;
+ }
}
- ret = kvm_vm_ioctl(s, KVM_SET_TSS_ADDR, 0xfffbd000);
+#endif
+ /* Set TSS base one page after EPT identity map. */
+ ret = kvm_vm_ioctl(s, KVM_SET_TSS_ADDR, identity_base + 0x1000);
if (ret < 0) {
return ret;
}
- return kvm_init_identity_map_page(s);
+ /* Tell fw_cfg to notify the BIOS to reserve the range. */
+ ret = e820_add_entry(identity_base, 0x4000, E820_RESERVED);
+ if (ret < 0) {
+ fprintf(stderr, "e820_add_entry() table is full\n");
+ return ret;
+ }
+
+ return 0;
}
-
+
static void set_v8086_seg(struct kvm_segment *lhs, const SegmentCache *rhs)
{
lhs->selector = rhs->selector;
@@ -589,7 +573,7 @@ static void set_seg(struct kvm_segment *lhs, const SegmentCache *rhs)
lhs->limit = rhs->limit;
lhs->type = (flags >> DESC_TYPE_SHIFT) & 15;
lhs->present = (flags & DESC_P_MASK) != 0;
- lhs->dpl = rhs->selector & 3;
+ lhs->dpl = (flags >> DESC_DPL_SHIFT) & 3;
lhs->db = (flags >> DESC_B_SHIFT) & 1;
lhs->s = (flags & DESC_S_MASK) != 0;
lhs->l = (flags >> DESC_L_SHIFT) & 1;
@@ -603,23 +587,23 @@ static void get_seg(SegmentCache *lhs, const struct kvm_segment *rhs)
lhs->selector = rhs->selector;
lhs->base = rhs->base;
lhs->limit = rhs->limit;
- lhs->flags =
- (rhs->type << DESC_TYPE_SHIFT)
- | (rhs->present * DESC_P_MASK)
- | (rhs->dpl << DESC_DPL_SHIFT)
- | (rhs->db << DESC_B_SHIFT)
- | (rhs->s * DESC_S_MASK)
- | (rhs->l << DESC_L_SHIFT)
- | (rhs->g * DESC_G_MASK)
- | (rhs->avl * DESC_AVL_MASK);
+ lhs->flags = (rhs->type << DESC_TYPE_SHIFT) |
+ (rhs->present * DESC_P_MASK) |
+ (rhs->dpl << DESC_DPL_SHIFT) |
+ (rhs->db << DESC_B_SHIFT) |
+ (rhs->s * DESC_S_MASK) |
+ (rhs->l << DESC_L_SHIFT) |
+ (rhs->g * DESC_G_MASK) |
+ (rhs->avl * DESC_AVL_MASK);
}
static void kvm_getput_reg(__u64 *kvm_reg, target_ulong *qemu_reg, int set)
{
- if (set)
+ if (set) {
*kvm_reg = *qemu_reg;
- else
+ } else {
*qemu_reg = *kvm_reg;
+ }
}
static int kvm_getput_regs(CPUState *env, int set)
@@ -629,8 +613,9 @@ static int kvm_getput_regs(CPUState *env, int set)
if (!set) {
ret = kvm_vcpu_ioctl(env, KVM_GET_REGS, &regs);
- if (ret < 0)
+ if (ret < 0) {
return ret;
+ }
}
kvm_getput_reg(&regs.rax, &env->regs[R_EAX], set);
@@ -655,8 +640,9 @@ static int kvm_getput_regs(CPUState *env, int set)
kvm_getput_reg(&regs.rflags, &env->eflags, set);
kvm_getput_reg(&regs.rip, &env->eip, set);
- if (set)
+ if (set) {
ret = kvm_vcpu_ioctl(env, KVM_SET_REGS, &regs);
+ }
return ret;
}
@@ -670,8 +656,9 @@ static int kvm_put_fpu(CPUState *env)
fpu.fsw = env->fpus & ~(7 << 11);
fpu.fsw |= (env->fpstt & 7) << 11;
fpu.fcw = env->fpuc;
- for (i = 0; i < 8; ++i)
- fpu.ftwx |= (!env->fptags[i]) << i;
+ for (i = 0; i < 8; ++i) {
+ fpu.ftwx |= (!env->fptags[i]) << i;
+ }
memcpy(fpu.fpr, env->fpregs, sizeof env->fpregs);
memcpy(fpu.xmm, env->xmm_regs, sizeof env->xmm_regs);
fpu.mxcsr = env->mxcsr;
@@ -696,8 +683,9 @@ static int kvm_put_xsave(CPUState *env)
struct kvm_xsave* xsave;
uint16_t cwd, swd, twd, fop;
- if (!kvm_has_xsave())
+ if (!kvm_has_xsave()) {
return kvm_put_fpu(env);
+ }
xsave = qemu_memalign(4096, sizeof(struct kvm_xsave));
memset(xsave, 0, sizeof(struct kvm_xsave));
@@ -705,8 +693,9 @@ static int kvm_put_xsave(CPUState *env)
swd = env->fpus & ~(7 << 11);
swd |= (env->fpstt & 7) << 11;
cwd = env->fpuc;
- for (i = 0; i < 8; ++i)
+ for (i = 0; i < 8; ++i) {
twd |= (!env->fptags[i]) << i;
+ }
xsave->region[0] = (uint32_t)(swd << 16) + cwd;
xsave->region[1] = (uint32_t)(fop << 16) + twd;
memcpy(&xsave->region[XSAVE_ST_SPACE], env->fpregs,
@@ -730,8 +719,9 @@ static int kvm_put_xcrs(CPUState *env)
#ifdef KVM_CAP_XCRS
struct kvm_xcrs xcrs;
- if (!kvm_has_xcrs())
+ if (!kvm_has_xcrs()) {
return 0;
+ }
xcrs.nr_xcrs = 1;
xcrs.flags = 0;
@@ -754,26 +744,19 @@ static int kvm_put_sregs(CPUState *env)
}
if ((env->eflags & VM_MASK)) {
- set_v8086_seg(&sregs.cs, &env->segs[R_CS]);
- set_v8086_seg(&sregs.ds, &env->segs[R_DS]);
- set_v8086_seg(&sregs.es, &env->segs[R_ES]);
- set_v8086_seg(&sregs.fs, &env->segs[R_FS]);
- set_v8086_seg(&sregs.gs, &env->segs[R_GS]);
- set_v8086_seg(&sregs.ss, &env->segs[R_SS]);
+ set_v8086_seg(&sregs.cs, &env->segs[R_CS]);
+ set_v8086_seg(&sregs.ds, &env->segs[R_DS]);
+ set_v8086_seg(&sregs.es, &env->segs[R_ES]);
+ set_v8086_seg(&sregs.fs, &env->segs[R_FS]);
+ set_v8086_seg(&sregs.gs, &env->segs[R_GS]);
+ set_v8086_seg(&sregs.ss, &env->segs[R_SS]);
} else {
- set_seg(&sregs.cs, &env->segs[R_CS]);
- set_seg(&sregs.ds, &env->segs[R_DS]);
- set_seg(&sregs.es, &env->segs[R_ES]);
- set_seg(&sregs.fs, &env->segs[R_FS]);
- set_seg(&sregs.gs, &env->segs[R_GS]);
- set_seg(&sregs.ss, &env->segs[R_SS]);
-
- if (env->cr[0] & CR0_PE_MASK) {
- /* force ss cpl to cs cpl */
- sregs.ss.selector = (sregs.ss.selector & ~3) |
- (sregs.cs.selector & 3);
- sregs.ss.dpl = sregs.ss.selector & 3;
- }
+ set_seg(&sregs.cs, &env->segs[R_CS]);
+ set_seg(&sregs.ds, &env->segs[R_DS]);
+ set_seg(&sregs.es, &env->segs[R_ES]);
+ set_seg(&sregs.fs, &env->segs[R_FS]);
+ set_seg(&sregs.gs, &env->segs[R_GS]);
+ set_seg(&sregs.ss, &env->segs[R_SS]);
}
set_seg(&sregs.tr, &env->tr);
@@ -816,10 +799,12 @@ static int kvm_put_msrs(CPUState *env, int level)
kvm_msr_entry_set(&msrs[n++], MSR_IA32_SYSENTER_CS, env->sysenter_cs);
kvm_msr_entry_set(&msrs[n++], MSR_IA32_SYSENTER_ESP, env->sysenter_esp);
kvm_msr_entry_set(&msrs[n++], MSR_IA32_SYSENTER_EIP, env->sysenter_eip);
- if (kvm_has_msr_star(env))
- kvm_msr_entry_set(&msrs[n++], MSR_STAR, env->star);
- if (kvm_has_msr_hsave_pa(env))
+ if (has_msr_star) {
+ kvm_msr_entry_set(&msrs[n++], MSR_STAR, env->star);
+ }
+ if (has_msr_hsave_pa) {
kvm_msr_entry_set(&msrs[n++], MSR_VM_HSAVE_PA, env->vm_hsave);
+ }
#ifdef TARGET_X86_64
if (lm_capable_kernel) {
kvm_msr_entry_set(&msrs[n++], MSR_CSTAR, env->cstar);
@@ -838,23 +823,35 @@ static int kvm_put_msrs(CPUState *env, int level)
if (smp_cpus == 1 || env->tsc != 0) {
kvm_msr_entry_set(&msrs[n++], MSR_IA32_TSC, env->tsc);
}
+ }
+ /*
+ * The following paravirtual MSRs have side effects on the guest or are
+ * too heavy for normal writeback. Limit them to reset or full state
+ * updates.
+ */
+ if (level >= KVM_PUT_RESET_STATE) {
kvm_msr_entry_set(&msrs[n++], MSR_KVM_SYSTEM_TIME,
env->system_time_msr);
kvm_msr_entry_set(&msrs[n++], MSR_KVM_WALL_CLOCK, env->wall_clock_msr);
-#ifdef KVM_CAP_ASYNC_PF
- kvm_msr_entry_set(&msrs[n++], MSR_KVM_ASYNC_PF_EN, env->async_pf_en_msr);
+#if defined(CONFIG_KVM_PARA) && defined(KVM_CAP_ASYNC_PF)
+ if (has_msr_async_pf_en) {
+ kvm_msr_entry_set(&msrs[n++], MSR_KVM_ASYNC_PF_EN,
+ env->async_pf_en_msr);
+ }
#endif
}
#ifdef KVM_CAP_MCE
if (env->mcg_cap) {
int i;
- if (level == KVM_PUT_RESET_STATE)
+
+ if (level == KVM_PUT_RESET_STATE) {
kvm_msr_entry_set(&msrs[n++], MSR_MCG_STATUS, env->mcg_status);
- else if (level == KVM_PUT_FULL_STATE) {
+ } else if (level == KVM_PUT_FULL_STATE) {
kvm_msr_entry_set(&msrs[n++], MSR_MCG_STATUS, env->mcg_status);
kvm_msr_entry_set(&msrs[n++], MSR_MCG_CTL, env->mcg_ctl);
- for (i = 0; i < (env->mcg_cap & 0xff) * 4; i++)
+ for (i = 0; i < (env->mcg_cap & 0xff) * 4; i++) {
kvm_msr_entry_set(&msrs[n++], MSR_MC0_CTL + i, env->mce_banks[i]);
+ }
}
}
#endif
@@ -872,14 +869,16 @@ static int kvm_get_fpu(CPUState *env)
int i, ret;
ret = kvm_vcpu_ioctl(env, KVM_GET_FPU, &fpu);
- if (ret < 0)
+ if (ret < 0) {
return ret;
+ }
env->fpstt = (fpu.fsw >> 11) & 7;
env->fpus = fpu.fsw;
env->fpuc = fpu.fcw;
- for (i = 0; i < 8; ++i)
- env->fptags[i] = !((fpu.ftwx >> i) & 1);
+ for (i = 0; i < 8; ++i) {
+ env->fptags[i] = !((fpu.ftwx >> i) & 1);
+ }
memcpy(env->fpregs, fpu.fpr, sizeof env->fpregs);
memcpy(env->xmm_regs, fpu.xmm, sizeof env->xmm_regs);
env->mxcsr = fpu.mxcsr;
@@ -894,8 +893,9 @@ static int kvm_get_xsave(CPUState *env)
int ret, i;
uint16_t cwd, swd, twd, fop;
- if (!kvm_has_xsave())
+ if (!kvm_has_xsave()) {
return kvm_get_fpu(env);
+ }
xsave = qemu_memalign(4096, sizeof(struct kvm_xsave));
ret = kvm_vcpu_ioctl(env, KVM_GET_XSAVE, xsave);
@@ -911,8 +911,9 @@ static int kvm_get_xsave(CPUState *env)
env->fpstt = (swd >> 11) & 7;
env->fpus = swd;
env->fpuc = cwd;
- for (i = 0; i < 8; ++i)
+ for (i = 0; i < 8; ++i) {
env->fptags[i] = !((twd >> i) & 1);
+ }
env->mxcsr = xsave->region[XSAVE_MXCSR];
memcpy(env->fpregs, &xsave->region[XSAVE_ST_SPACE],
sizeof env->fpregs);
@@ -934,19 +935,22 @@ static int kvm_get_xcrs(CPUState *env)
int i, ret;
struct kvm_xcrs xcrs;
- if (!kvm_has_xcrs())
+ if (!kvm_has_xcrs()) {
return 0;
+ }
ret = kvm_vcpu_ioctl(env, KVM_GET_XCRS, &xcrs);
- if (ret < 0)
+ if (ret < 0) {
return ret;
+ }
- for (i = 0; i < xcrs.nr_xcrs; i++)
+ for (i = 0; i < xcrs.nr_xcrs; i++) {
/* Only support xcr0 now */
if (xcrs.xcrs[0].xcr == 0) {
env->xcr0 = xcrs.xcrs[0].value;
break;
}
+ }
return 0;
#else
return 0;
@@ -960,8 +964,9 @@ static int kvm_get_sregs(CPUState *env)
int bit, i, ret;
ret = kvm_vcpu_ioctl(env, KVM_GET_SREGS, &sregs);
- if (ret < 0)
+ if (ret < 0) {
return ret;
+ }
/* There can only be one pending IRQ set in the bitmap at a time, so try
to find it and save its number instead (-1 for none). */
@@ -999,21 +1004,19 @@ static int kvm_get_sregs(CPUState *env)
env->efer = sregs.efer;
//cpu_set_apic_tpr(env->apic_state, sregs.cr8);
-#define HFLAG_COPY_MASK ~( \
- HF_CPL_MASK | HF_PE_MASK | HF_MP_MASK | HF_EM_MASK | \
- HF_TS_MASK | HF_TF_MASK | HF_VM_MASK | HF_IOPL_MASK | \
- HF_OSFXSR_MASK | HF_LMA_MASK | HF_CS32_MASK | \
- HF_SS32_MASK | HF_CS64_MASK | HF_ADDSEG_MASK)
-
-
+#define HFLAG_COPY_MASK \
+ ~( HF_CPL_MASK | HF_PE_MASK | HF_MP_MASK | HF_EM_MASK | \
+ HF_TS_MASK | HF_TF_MASK | HF_VM_MASK | HF_IOPL_MASK | \
+ HF_OSFXSR_MASK | HF_LMA_MASK | HF_CS32_MASK | \
+ HF_SS32_MASK | HF_CS64_MASK | HF_ADDSEG_MASK)
hflags = (env->segs[R_CS].flags >> DESC_DPL_SHIFT) & HF_CPL_MASK;
hflags |= (env->cr[0] & CR0_PE_MASK) << (HF_PE_SHIFT - CR0_PE_SHIFT);
hflags |= (env->cr[0] << (HF_MP_SHIFT - CR0_MP_SHIFT)) &
- (HF_MP_MASK | HF_EM_MASK | HF_TS_MASK);
+ (HF_MP_MASK | HF_EM_MASK | HF_TS_MASK);
hflags |= (env->eflags & (HF_TF_MASK | HF_VM_MASK | HF_IOPL_MASK));
hflags |= (env->cr[4] & CR4_OSFXSR_MASK) <<
- (HF_OSFXSR_SHIFT - CR4_OSFXSR_SHIFT);
+ (HF_OSFXSR_SHIFT - CR4_OSFXSR_SHIFT);
if (env->efer & MSR_EFER_LMA) {
hflags |= HF_LMA_MASK;
@@ -1023,19 +1026,16 @@ static int kvm_get_sregs(CPUState *env)
hflags |= HF_CS32_MASK | HF_SS32_MASK | HF_CS64_MASK;
} else {
hflags |= (env->segs[R_CS].flags & DESC_B_MASK) >>
- (DESC_B_SHIFT - HF_CS32_SHIFT);
+ (DESC_B_SHIFT - HF_CS32_SHIFT);
hflags |= (env->segs[R_SS].flags & DESC_B_MASK) >>
- (DESC_B_SHIFT - HF_SS32_SHIFT);
- if (!(env->cr[0] & CR0_PE_MASK) ||
- (env->eflags & VM_MASK) ||
- !(hflags & HF_CS32_MASK)) {
- hflags |= HF_ADDSEG_MASK;
- } else {
- hflags |= ((env->segs[R_DS].base |
- env->segs[R_ES].base |
- env->segs[R_SS].base) != 0) <<
- HF_ADDSEG_SHIFT;
- }
+ (DESC_B_SHIFT - HF_SS32_SHIFT);
+ if (!(env->cr[0] & CR0_PE_MASK) || (env->eflags & VM_MASK) ||
+ !(hflags & HF_CS32_MASK)) {
+ hflags |= HF_ADDSEG_MASK;
+ } else {
+ hflags |= ((env->segs[R_DS].base | env->segs[R_ES].base |
+ env->segs[R_SS].base) != 0) << HF_ADDSEG_SHIFT;
+ }
}
env->hflags = (env->hflags & HFLAG_COPY_MASK) | hflags;
@@ -1055,10 +1055,12 @@ static int kvm_get_msrs(CPUState *env)
msrs[n++].index = MSR_IA32_SYSENTER_CS;
msrs[n++].index = MSR_IA32_SYSENTER_ESP;
msrs[n++].index = MSR_IA32_SYSENTER_EIP;
- if (kvm_has_msr_star(env))
- msrs[n++].index = MSR_STAR;
- if (kvm_has_msr_hsave_pa(env))
+ if (has_msr_star) {
+ msrs[n++].index = MSR_STAR;
+ }
+ if (has_msr_hsave_pa) {
msrs[n++].index = MSR_VM_HSAVE_PA;
+ }
msrs[n++].index = MSR_IA32_TSC;
#ifdef TARGET_X86_64
if (lm_capable_kernel) {
@@ -1070,23 +1072,27 @@ static int kvm_get_msrs(CPUState *env)
#endif
msrs[n++].index = MSR_KVM_SYSTEM_TIME;
msrs[n++].index = MSR_KVM_WALL_CLOCK;
-#ifdef KVM_CAP_ASYNC_PF
- msrs[n++].index = MSR_KVM_ASYNC_PF_EN;
+#if defined(CONFIG_KVM_PARA) && defined(KVM_CAP_ASYNC_PF)
+ if (has_msr_async_pf_en) {
+ msrs[n++].index = MSR_KVM_ASYNC_PF_EN;
+ }
#endif
#ifdef KVM_CAP_MCE
if (env->mcg_cap) {
msrs[n++].index = MSR_MCG_STATUS;
msrs[n++].index = MSR_MCG_CTL;
- for (i = 0; i < (env->mcg_cap & 0xff) * 4; i++)
+ for (i = 0; i < (env->mcg_cap & 0xff) * 4; i++) {
msrs[n++].index = MSR_MC0_CTL + i;
+ }
}
#endif
msr_data.info.nmsrs = n;
ret = kvm_vcpu_ioctl(env, KVM_GET_MSRS, &msr_data);
- if (ret < 0)
+ if (ret < 0) {
return ret;
+ }
for (i = 0; i < ret; i++) {
switch (msrs[i].index) {
@@ -1144,7 +1150,7 @@ static int kvm_get_msrs(CPUState *env)
}
#endif
break;
-#ifdef KVM_CAP_ASYNC_PF
+#if defined(CONFIG_KVM_PARA) && defined(KVM_CAP_ASYNC_PF)
case MSR_KVM_ASYNC_PF_EN:
env->async_pf_en_msr = msrs[i].data;
break;
@@ -1172,6 +1178,9 @@ static int kvm_get_mp_state(CPUState *env)
return ret;
}
env->mp_state = mp_state.mp_state;
+ if (kvm_irqchip_in_kernel()) {
+ env->halted = (mp_state.mp_state == KVM_MP_STATE_HALTED);
+ }
return 0;
}
@@ -1314,7 +1323,7 @@ static int kvm_get_debugregs(CPUState *env)
ret = kvm_vcpu_ioctl(env, KVM_GET_DEBUGREGS, &dbgregs);
if (ret < 0) {
- return ret;
+ return ret;
}
for (i = 0; i < 4; i++) {
env->dr[i] = dbgregs.db[i];
@@ -1333,44 +1342,44 @@ int kvm_arch_put_registers(CPUState *env, int level)
assert(cpu_is_stopped(env) || qemu_cpu_self(env));
ret = kvm_getput_regs(env, 1);
- if (ret < 0)
+ if (ret < 0) {
return ret;
-
+ }
ret = kvm_put_xsave(env);
- if (ret < 0)
+ if (ret < 0) {
return ret;
-
+ }
ret = kvm_put_xcrs(env);
- if (ret < 0)
+ if (ret < 0) {
return ret;
-
+ }
ret = kvm_put_sregs(env);
- if (ret < 0)
+ if (ret < 0) {
return ret;
-
+ }
ret = kvm_put_msrs(env, level);
- if (ret < 0)
+ if (ret < 0) {
return ret;
-
+ }
if (level >= KVM_PUT_RESET_STATE) {
ret = kvm_put_mp_state(env);
- if (ret < 0)
+ if (ret < 0) {
return ret;
+ }
}
-
ret = kvm_put_vcpu_events(env, level);
- if (ret < 0)
+ if (ret < 0) {
return ret;
-
+ }
+ ret = kvm_put_debugregs(env);
+ if (ret < 0) {
+ return ret;
+ }
/* must be last */
ret = kvm_guest_debug_workarounds(env);
- if (ret < 0)
- return ret;
-
- ret = kvm_put_debugregs(env);
- if (ret < 0)
+ if (ret < 0) {
return ret;
-
+ }
return 0;
}
@@ -1381,42 +1390,49 @@ int kvm_arch_get_registers(CPUState *env)
assert(cpu_is_stopped(env) || qemu_cpu_self(env));
ret = kvm_getput_regs(env, 0);
- if (ret < 0)
+ if (ret < 0) {
return ret;
-
+ }
ret = kvm_get_xsave(env);
- if (ret < 0)
+ if (ret < 0) {
return ret;
-
+ }
ret = kvm_get_xcrs(env);
- if (ret < 0)
+ if (ret < 0) {
return ret;
-
+ }
ret = kvm_get_sregs(env);
- if (ret < 0)
+ if (ret < 0) {
return ret;
-
+ }
ret = kvm_get_msrs(env);
- if (ret < 0)
+ if (ret < 0) {
return ret;
-
+ }
ret = kvm_get_mp_state(env);
- if (ret < 0)
+ if (ret < 0) {
return ret;
-
+ }
ret = kvm_get_vcpu_events(env);
- if (ret < 0)
+ if (ret < 0) {
return ret;
-
+ }
ret = kvm_get_debugregs(env);
- if (ret < 0)
+ if (ret < 0) {
return ret;
-
+ }
return 0;
}
int kvm_arch_pre_run(CPUState *env, struct kvm_run *run)
{
+ /* Inject NMI */
+ if (env->interrupt_request & CPU_INTERRUPT_NMI) {
+ env->interrupt_request &= ~CPU_INTERRUPT_NMI;
+ DPRINTF("injected NMI\n");
+ kvm_vcpu_ioctl(env, KVM_NMI);
+ }
+
/* Try to inject an interrupt if the guest can accept it */
if (run->ready_for_interrupt_injection &&
(env->interrupt_request & CPU_INTERRUPT_HARD) &&
@@ -1438,10 +1454,11 @@ int kvm_arch_pre_run(CPUState *env, struct kvm_run *run)
* interrupt, request an interrupt window exit. This will
* cause a return to userspace as soon as the guest is ready to
* receive interrupts. */
- if ((env->interrupt_request & CPU_INTERRUPT_HARD))
+ if ((env->interrupt_request & CPU_INTERRUPT_HARD)) {
run->request_interrupt_window = 1;
- else
+ } else {
run->request_interrupt_window = 0;
+ }
DPRINTF("setting tpr\n");
run->cr8 = cpu_get_apic_tpr(env->apic_state);
@@ -1451,11 +1468,11 @@ int kvm_arch_pre_run(CPUState *env, struct kvm_run *run)
int kvm_arch_post_run(CPUState *env, struct kvm_run *run)
{
- if (run->if_flag)
+ if (run->if_flag) {
env->eflags |= IF_MASK;
- else
+ } else {
env->eflags &= ~IF_MASK;
-
+ }
cpu_set_apic_tpr(env->apic_state, run->cr8);
cpu_set_apic_base(env->apic_state, run->apic_base);
@@ -1491,8 +1508,19 @@ static int kvm_handle_halt(CPUState *env)
return 1;
}
+static bool host_supports_vmx(void)
+{
+ uint32_t ecx, unused;
+
+ host_cpuid(1, 0, &unused, &unused, &ecx, &unused);
+ return ecx & CPUID_EXT_VMX;
+}
+
+#define VMX_INVALID_GUEST_STATE 0x80000021
+
int kvm_arch_handle_exit(CPUState *env, struct kvm_run *run)
{
+ uint64_t code;
int ret = 0;
switch (run->exit_reason) {
@@ -1500,6 +1528,35 @@ int kvm_arch_handle_exit(CPUState *env, struct kvm_run *run)
DPRINTF("handle_hlt\n");
ret = kvm_handle_halt(env);
break;
+ case KVM_EXIT_SET_TPR:
+ ret = 1;
+ break;
+ case KVM_EXIT_FAIL_ENTRY:
+ code = run->fail_entry.hardware_entry_failure_reason;
+ fprintf(stderr, "KVM: entry failed, hardware error 0x%" PRIx64 "\n",
+ code);
+ if (host_supports_vmx() && code == VMX_INVALID_GUEST_STATE) {
+ fprintf(stderr,
+ "\nIf you're runnning a guest on an Intel machine without "
+ "unrestricted mode\n"
+ "support, the failure can be most likely due to the guest "
+ "entering an invalid\n"
+ "state for Intel VT. For example, the guest maybe running "
+ "in big real mode\n"
+ "which is not supported on less recent Intel processors."
+ "\n\n");
+ }
+ ret = -1;
+ break;
+ case KVM_EXIT_EXCEPTION:
+ fprintf(stderr, "KVM: exception %d exit (error code 0x%x)\n",
+ run->ex.exception, run->ex.error_code);
+ ret = -1;
+ break;
+ default:
+ fprintf(stderr, "KVM: unknown exit reason %d\n", run->exit_reason);
+ ret = -1;
+ break;
}
return ret;
@@ -1511,8 +1568,9 @@ int kvm_arch_insert_sw_breakpoint(CPUState *env, struct kvm_sw_breakpoint *bp)
static const uint8_t int3 = 0xcc;
if (cpu_memory_rw_debug(env, bp->pc, (uint8_t *)&bp->saved_insn, 1, 0) ||
- cpu_memory_rw_debug(env, bp->pc, (uint8_t *)&int3, 1, 1))
+ cpu_memory_rw_debug(env, bp->pc, (uint8_t *)&int3, 1, 1)) {
return -EINVAL;
+ }
return 0;
}
@@ -1521,8 +1579,9 @@ int kvm_arch_remove_sw_breakpoint(CPUState *env, struct kvm_sw_breakpoint *bp)
uint8_t int3;
if (cpu_memory_rw_debug(env, bp->pc, &int3, 1, 0) || int3 != 0xcc ||
- cpu_memory_rw_debug(env, bp->pc, (uint8_t *)&bp->saved_insn, 1, 1))
+ cpu_memory_rw_debug(env, bp->pc, (uint8_t *)&bp->saved_insn, 1, 1)) {
return -EINVAL;
+ }
return 0;
}
@@ -1538,10 +1597,12 @@ static int find_hw_breakpoint(target_ulong addr, int len, int type)
{
int n;
- for (n = 0; n < nb_hw_breakpoint; n++)
+ for (n = 0; n < nb_hw_breakpoint; n++) {
if (hw_breakpoint[n].addr == addr && hw_breakpoint[n].type == type &&
- (hw_breakpoint[n].len == len || len == -1))
+ (hw_breakpoint[n].len == len || len == -1)) {
return n;
+ }
+ }
return -1;
}
@@ -1560,8 +1621,9 @@ int kvm_arch_insert_hw_breakpoint(target_ulong addr,
case 2:
case 4:
case 8:
- if (addr & (len - 1))
+ if (addr & (len - 1)) {
return -EINVAL;
+ }
break;
default:
return -EINVAL;
@@ -1571,12 +1633,12 @@ int kvm_arch_insert_hw_breakpoint(target_ulong addr,
return -ENOSYS;
}
- if (nb_hw_breakpoint == 4)
+ if (nb_hw_breakpoint == 4) {
return -ENOBUFS;
-
- if (find_hw_breakpoint(addr, len, type) >= 0)
+ }
+ if (find_hw_breakpoint(addr, len, type) >= 0) {
return -EEXIST;
-
+ }
hw_breakpoint[nb_hw_breakpoint].addr = addr;
hw_breakpoint[nb_hw_breakpoint].len = len;
hw_breakpoint[nb_hw_breakpoint].type = type;
@@ -1591,9 +1653,9 @@ int kvm_arch_remove_hw_breakpoint(target_ulong addr,
int n;
n = find_hw_breakpoint(addr, (type == GDB_BREAKPOINT_HW) ? 1 : len, type);
- if (n < 0)
+ if (n < 0) {
return -ENOENT;
-
+ }
nb_hw_breakpoint--;
hw_breakpoint[n] = hw_breakpoint[nb_hw_breakpoint];
@@ -1614,11 +1676,12 @@ int kvm_arch_debug(struct kvm_debug_exit_arch *arch_info)
if (arch_info->exception == 1) {
if (arch_info->dr6 & (1 << 14)) {
- if (cpu_single_env->singlestep_enabled)
+ if (cpu_single_env->singlestep_enabled) {
handle = 1;
+ }
} else {
- for (n = 0; n < 4; n++)
- if (arch_info->dr6 & (1 << n))
+ for (n = 0; n < 4; n++) {
+ if (arch_info->dr6 & (1 << n)) {
switch ((arch_info->dr7 >> (16 + n*4)) & 0x3) {
case 0x0:
handle = 1;
@@ -1636,10 +1699,12 @@ int kvm_arch_debug(struct kvm_debug_exit_arch *arch_info)
hw_watchpoint.flags = BP_MEM_ACCESS;
break;
}
+ }
+ }
}
- } else if (kvm_find_sw_breakpoint(cpu_single_env, arch_info->pc))
+ } else if (kvm_find_sw_breakpoint(cpu_single_env, arch_info->pc)) {
handle = 1;
-
+ }
if (!handle) {
cpu_synchronize_state(cpu_single_env);
assert(cpu_single_env->exception_injected == -1);
@@ -1663,9 +1728,9 @@ void kvm_arch_update_guest_debug(CPUState *env, struct kvm_guest_debug *dbg)
};
int n;
- if (kvm_sw_breakpoints_active(env))
+ if (kvm_sw_breakpoints_active(env)) {
dbg->control |= KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP;
-
+ }
if (nb_hw_breakpoint > 0) {
dbg->control |= KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_HW_BP;
dbg->arch.debugreg[7] = 0x0600;
@@ -1673,18 +1738,16 @@ void kvm_arch_update_guest_debug(CPUState *env, struct kvm_guest_debug *dbg)
dbg->arch.debugreg[n] = hw_breakpoint[n].addr;
dbg->arch.debugreg[7] |= (2 << (n * 2)) |
(type_code[hw_breakpoint[n].type] << (16 + n*4)) |
- (len_code[hw_breakpoint[n].len] << (18 + n*4));
+ ((uint32_t)len_code[hw_breakpoint[n].len] << (18 + n*4));
}
}
- /* Legal xcr0 for loading */
- env->xcr0 = 1;
}
#endif /* KVM_CAP_SET_GUEST_DEBUG */
bool kvm_arch_stop_on_emulation_error(CPUState *env)
{
- return !(env->cr[0] & CR0_PE_MASK) ||
- ((env->segs[R_CS].selector & 3) != 3);
+ return !(env->cr[0] & CR0_PE_MASK) ||
+ ((env->segs[R_CS].selector & 3) != 3);
}
static void hardware_memory_error(void)
@@ -1696,64 +1759,96 @@ static void hardware_memory_error(void)
#ifdef KVM_CAP_MCE
static void kvm_mce_broadcast_rest(CPUState *env)
{
+ struct kvm_x86_mce mce = {
+ .bank = 1,
+ .status = MCI_STATUS_VAL | MCI_STATUS_UC,
+ .mcg_status = MCG_STATUS_MCIP | MCG_STATUS_RIPV,
+ .addr = 0,
+ .misc = 0,
+ };
CPUState *cenv;
- int family, model, cpuver = env->cpuid_version;
-
- family = (cpuver >> 8) & 0xf;
- model = ((cpuver >> 12) & 0xf0) + ((cpuver >> 4) & 0xf);
/* Broadcast MCA signal for processor version 06H_EH and above */
- if ((family == 6 && model >= 14) || family > 6) {
+ if (cpu_x86_support_mca_broadcast(env)) {
for (cenv = first_cpu; cenv != NULL; cenv = cenv->next_cpu) {
if (cenv == env) {
continue;
}
- kvm_inject_x86_mce(cenv, 1, MCI_STATUS_VAL | MCI_STATUS_UC,
- MCG_STATUS_MCIP | MCG_STATUS_RIPV, 0, 0, 1);
+ kvm_inject_x86_mce_on(cenv, &mce, ABORT_ON_ERROR);
}
}
}
+
+static void kvm_mce_inj_srar_dataload(CPUState *env, target_phys_addr_t paddr)
+{
+ struct kvm_x86_mce mce = {
+ .bank = 9,
+ .status = MCI_STATUS_VAL | MCI_STATUS_UC | MCI_STATUS_EN
+ | MCI_STATUS_MISCV | MCI_STATUS_ADDRV | MCI_STATUS_S
+ | MCI_STATUS_AR | 0x134,
+ .mcg_status = MCG_STATUS_MCIP | MCG_STATUS_EIPV,
+ .addr = paddr,
+ .misc = (MCM_ADDR_PHYS << 6) | 0xc,
+ };
+ int r;
+
+ r = kvm_set_mce(env, &mce);
+ if (r < 0) {
+ fprintf(stderr, "kvm_set_mce: %s\n", strerror(errno));
+ abort();
+ }
+ kvm_mce_broadcast_rest(env);
+}
+
+static void kvm_mce_inj_srao_memscrub(CPUState *env, target_phys_addr_t paddr)
+{
+ struct kvm_x86_mce mce = {
+ .bank = 9,
+ .status = MCI_STATUS_VAL | MCI_STATUS_UC | MCI_STATUS_EN
+ | MCI_STATUS_MISCV | MCI_STATUS_ADDRV | MCI_STATUS_S
+ | 0xc0,
+ .mcg_status = MCG_STATUS_MCIP | MCG_STATUS_RIPV,
+ .addr = paddr,
+ .misc = (MCM_ADDR_PHYS << 6) | 0xc,
+ };
+ int r;
+
+ r = kvm_set_mce(env, &mce);
+ if (r < 0) {
+ fprintf(stderr, "kvm_set_mce: %s\n", strerror(errno));
+ abort();
+ }
+ kvm_mce_broadcast_rest(env);
+}
+
+static void kvm_mce_inj_srao_memscrub2(CPUState *env, target_phys_addr_t paddr)
+{
+ struct kvm_x86_mce mce = {
+ .bank = 9,
+ .status = MCI_STATUS_VAL | MCI_STATUS_UC | MCI_STATUS_EN
+ | MCI_STATUS_MISCV | MCI_STATUS_ADDRV | MCI_STATUS_S
+ | 0xc0,
+ .mcg_status = MCG_STATUS_MCIP | MCG_STATUS_RIPV,
+ .addr = paddr,
+ .misc = (MCM_ADDR_PHYS << 6) | 0xc,
+ };
+
+ kvm_inject_x86_mce_on(env, &mce, ABORT_ON_ERROR);
+ kvm_mce_broadcast_rest(env);
+}
+
#endif
int kvm_on_sigbus_vcpu(CPUState *env, int code, void *addr)
{
#if defined(KVM_CAP_MCE)
- struct kvm_x86_mce mce = {
- .bank = 9,
- };
void *vaddr;
ram_addr_t ram_addr;
target_phys_addr_t paddr;
- int r;
if ((env->mcg_cap & MCG_SER_P) && addr
&& (code == BUS_MCEERR_AR
|| code == BUS_MCEERR_AO)) {
- if (code == BUS_MCEERR_AR) {
- /* Fake an Intel architectural Data Load SRAR UCR */
- mce.status = MCI_STATUS_VAL | MCI_STATUS_UC | MCI_STATUS_EN
- | MCI_STATUS_MISCV | MCI_STATUS_ADDRV | MCI_STATUS_S
- | MCI_STATUS_AR | 0x134;
- mce.misc = (MCM_ADDR_PHYS << 6) | 0xc;
- mce.mcg_status = MCG_STATUS_MCIP | MCG_STATUS_EIPV;
- } else {
- /*
- * If there is an MCE excpetion being processed, ignore
- * this SRAO MCE
- */
- r = kvm_mce_in_exception(env);
- if (r == -1) {
- fprintf(stderr, "Failed to get MCE status\n");
- } else if (r) {
- return 0;
- }
- /* Fake an Intel architectural Memory scrubbing UCR */
- mce.status = MCI_STATUS_VAL | MCI_STATUS_UC | MCI_STATUS_EN
- | MCI_STATUS_MISCV | MCI_STATUS_ADDRV | MCI_STATUS_S
- | 0xc0;
- mce.misc = (MCM_ADDR_PHYS << 6) | 0xc;
- mce.mcg_status = MCG_STATUS_MCIP | MCG_STATUS_RIPV;
- }
vaddr = (void *)addr;
if (qemu_ram_addr_from_host(vaddr, &ram_addr) ||
!kvm_physical_memory_addr_from_ram(env->kvm_state, ram_addr, &paddr)) {
@@ -1766,13 +1861,20 @@ int kvm_on_sigbus_vcpu(CPUState *env, int code, void *addr)
hardware_memory_error();
}
}
- mce.addr = paddr;
- r = kvm_set_mce(env, &mce);
- if (r < 0) {
- fprintf(stderr, "kvm_set_mce: %s\n", strerror(errno));
- abort();
+
+ if (code == BUS_MCEERR_AR) {
+ /* Fake an Intel architectural Data Load SRAR UCR */
+ kvm_mce_inj_srar_dataload(env, paddr);
+ } else {
+ /*
+ * If there is an MCE excpetion being processed, ignore
+ * this SRAO MCE
+ */
+ if (!kvm_mce_in_progress(env)) {
+ /* Fake an Intel architectural Memory scrubbing UCR */
+ kvm_mce_inj_srao_memscrub(env, paddr);
+ }
}
- kvm_mce_broadcast_rest(env);
} else
#endif
{
@@ -1791,7 +1893,6 @@ int kvm_on_sigbus(int code, void *addr)
{
#if defined(KVM_CAP_MCE)
if ((first_cpu->mcg_cap & MCG_SER_P) && addr && code == BUS_MCEERR_AO) {
- uint64_t status;
void *vaddr;
ram_addr_t ram_addr;
target_phys_addr_t paddr;
@@ -1804,13 +1905,7 @@ int kvm_on_sigbus(int code, void *addr)
"QEMU itself instead of guest system!: %p\n", addr);
return 0;
}
- status = MCI_STATUS_VAL | MCI_STATUS_UC | MCI_STATUS_EN
- | MCI_STATUS_MISCV | MCI_STATUS_ADDRV | MCI_STATUS_S
- | 0xc0;
- kvm_inject_x86_mce(first_cpu, 9, status,
- MCG_STATUS_MCIP | MCG_STATUS_RIPV, paddr,
- (MCM_ADDR_PHYS << 6) | 0xc, 1);
- kvm_mce_broadcast_rest(first_cpu);
+ kvm_mce_inj_srao_memscrub2(first_cpu, paddr);
} else
#endif
{
diff --git a/target-i386/kvm_x86.h b/target-i386/kvm_x86.h
index 04932cf4c8..9d7b584267 100644
--- a/target-i386/kvm_x86.h
+++ b/target-i386/kvm_x86.h
@@ -15,8 +15,11 @@
#ifndef __KVM_X86_H__
#define __KVM_X86_H__
+#define ABORT_ON_ERROR 0x01
+#define MCE_BROADCAST 0x02
+
void kvm_inject_x86_mce(CPUState *cenv, int bank, uint64_t status,
uint64_t mcg_status, uint64_t addr, uint64_t misc,
- int abort_on_error);
+ int flag);
#endif
diff --git a/target-ppc/kvm.c b/target-ppc/kvm.c
index 5caa07cba8..710eca1dca 100644
--- a/target-ppc/kvm.c
+++ b/target-ppc/kvm.c
@@ -37,6 +37,10 @@
do { } while (0)
#endif
+const KVMCapabilityInfo kvm_arch_required_capabilities[] = {
+ KVM_CAP_LAST_INFO
+};
+
static int cap_interrupt_unset = false;
static int cap_interrupt_level = false;
@@ -56,7 +60,7 @@ static void kvm_kick_env(void *env)
qemu_cpu_kick(env);
}
-int kvm_arch_init(KVMState *s, int smp_cpus)
+int kvm_arch_init(KVMState *s)
{
#ifdef KVM_CAP_PPC_UNSET_IRQ
cap_interrupt_unset = kvm_check_extension(s, KVM_CAP_PPC_UNSET_IRQ);
@@ -307,6 +311,10 @@ int kvm_arch_handle_exit(CPUState *env, struct kvm_run *run)
dprintf("handle halt\n");
ret = kvmppc_handle_halt(env);
break;
+ default:
+ fprintf(stderr, "KVM: unknown exit reason %d\n", run->exit_reason);
+ ret = -1;
+ break;
}
return ret;
diff --git a/target-s390x/kvm.c b/target-s390x/kvm.c
index adf4a9e1e5..38823f54f7 100644
--- a/target-s390x/kvm.c
+++ b/target-s390x/kvm.c
@@ -70,7 +70,11 @@
#define SCLP_CMDW_READ_SCP_INFO 0x00020001
#define SCLP_CMDW_READ_SCP_INFO_FORCED 0x00120001
-int kvm_arch_init(KVMState *s, int smp_cpus)
+const KVMCapabilityInfo kvm_arch_required_capabilities[] = {
+ KVM_CAP_LAST_INFO
+};
+
+int kvm_arch_init(KVMState *s)
{
return 0;
}
diff --git a/vl.c b/vl.c
index ce5708bbbd..655617f9f3 100644
--- a/vl.c
+++ b/vl.c
@@ -2860,7 +2860,7 @@ int main(int argc, char **argv, char **envp)
}
if (kvm_allowed) {
- int ret = kvm_init(smp_cpus);
+ int ret = kvm_init();
if (ret < 0) {
if (!kvm_available()) {
printf("KVM not supported for this target\n");
generated by cgit v1.2.3 (git 2.26.2) at 2024-12-16 20:40:31 +0000