summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--cpu-all.h8
-rw-r--r--cpu-common.h1
-rw-r--r--cpu-defs.h1
-rw-r--r--cpu-exec.c27
-rw-r--r--cpus.c126
-rw-r--r--exec.c70
-rw-r--r--kvm-all.c46
-rw-r--r--kvm.h4
-rw-r--r--monitor.c15
-rw-r--r--os-posix.c10
-rw-r--r--os-win32.c5
-rw-r--r--osdep.h1
-rw-r--r--qemu-common.h6
-rw-r--r--qmp-commands.hx3
-rw-r--r--target-i386/cpu.h13
-rw-r--r--target-i386/cpuid.c1
-rw-r--r--target-i386/exec.h15
-rw-r--r--target-i386/helper.c190
-rw-r--r--target-i386/kvm.c593
-rw-r--r--target-i386/kvm_x86.h25
-rw-r--r--target-i386/machine.c2
-rw-r--r--target-ppc/kvm.c14
-rw-r--r--target-s390x/kvm.c7
-rw-r--r--vl.c1
24 files changed, 618 insertions, 566 deletions
diff --git a/cpu-all.h b/cpu-all.h
index 87b0f86667..4f4631d79c 100644
--- a/cpu-all.h
+++ b/cpu-all.h
@@ -863,10 +863,14 @@ target_phys_addr_t cpu_get_phys_page_debug(CPUState *env, target_ulong addr);
extern int phys_ram_fd;
extern ram_addr_t ram_size;
+/* RAM is pre-allocated and passed into qemu_ram_alloc_from_ptr */
+#define RAM_PREALLOC_MASK (1 << 0)
+
typedef struct RAMBlock {
uint8_t *host;
ram_addr_t offset;
ram_addr_t length;
+ uint32_t flags;
char idstr[256];
QLIST_ENTRY(RAMBlock) next;
#if defined(__linux__) && !defined(TARGET_S390X)
@@ -971,8 +975,4 @@ void dump_exec_info(FILE *f, fprintf_function cpu_fprintf);
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,
- int broadcast);
-
#endif /* CPU_ALL_H */
diff --git a/cpu-common.h b/cpu-common.h
index 54d21d4717..ef4e8dab7a 100644
--- a/cpu-common.h
+++ b/cpu-common.h
@@ -50,6 +50,7 @@ ram_addr_t qemu_ram_alloc_from_ptr(DeviceState *dev, const char *name,
ram_addr_t size, void *host);
ram_addr_t qemu_ram_alloc(DeviceState *dev, const char *name, ram_addr_t size);
void qemu_ram_free(ram_addr_t addr);
+void qemu_ram_remap(ram_addr_t addr, ram_addr_t length);
/* This should only be used for ram local to a device. */
void *qemu_get_ram_ptr(ram_addr_t addr);
/* Same but slower, to use for migration, where the order of
diff --git a/cpu-defs.h b/cpu-defs.h
index 2b59fa6fb0..db48a7afef 100644
--- a/cpu-defs.h
+++ b/cpu-defs.h
@@ -203,6 +203,7 @@ typedef struct CPUWatchpoint {
int nr_cores; /* number of cores within this CPU package */ \
int nr_threads;/* number of threads within this CPU */ \
int running; /* Nonzero if cpu is currently running(usermode). */ \
+ int thread_id; \
/* user data */ \
void *opaque; \
\
diff --git a/cpu-exec.c b/cpu-exec.c
index 34eaedca04..5cc937904a 100644
--- a/cpu-exec.c
+++ b/cpu-exec.c
@@ -196,6 +196,30 @@ static inline TranslationBlock *tb_find_fast(void)
return tb;
}
+static CPUDebugExcpHandler *debug_excp_handler;
+
+CPUDebugExcpHandler *cpu_set_debug_excp_handler(CPUDebugExcpHandler *handler)
+{
+ CPUDebugExcpHandler *old_handler = debug_excp_handler;
+
+ debug_excp_handler = handler;
+ return old_handler;
+}
+
+static void cpu_handle_debug_exception(CPUState *env)
+{
+ CPUWatchpoint *wp;
+
+ if (!env->watchpoint_hit) {
+ QTAILQ_FOREACH(wp, &env->watchpoints, entry) {
+ wp->flags &= ~BP_WATCHPOINT_HIT;
+ }
+ }
+ if (debug_excp_handler) {
+ debug_excp_handler(env);
+ }
+}
+
/* main execution loop */
volatile sig_atomic_t exit_request;
@@ -269,6 +293,9 @@ int cpu_exec(CPUState *env1)
if (env->exception_index >= EXCP_INTERRUPT) {
/* exit request from the cpu execution loop */
ret = env->exception_index;
+ if (ret == EXCP_DEBUG) {
+ cpu_handle_debug_exception(env);
+ }
break;
} else {
#if defined(CONFIG_USER_ONLY)
diff --git a/cpus.c b/cpus.c
index b6e658da62..41bec7cc56 100644
--- a/cpus.c
+++ b/cpus.c
@@ -148,7 +148,8 @@ static bool cpu_thread_is_idle(CPUState *env)
if (env->stopped || !vm_running) {
return true;
}
- if (!env->halted || qemu_cpu_has_work(env)) {
+ if (!env->halted || qemu_cpu_has_work(env) ||
+ (kvm_enabled() && kvm_irqchip_in_kernel())) {
return false;
}
return true;
@@ -166,29 +167,8 @@ static bool all_cpu_threads_idle(void)
return true;
}
-static CPUDebugExcpHandler *debug_excp_handler;
-
-CPUDebugExcpHandler *cpu_set_debug_excp_handler(CPUDebugExcpHandler *handler)
+static void cpu_handle_guest_debug(CPUState *env)
{
- CPUDebugExcpHandler *old_handler = debug_excp_handler;
-
- debug_excp_handler = handler;
- return old_handler;
-}
-
-static void cpu_handle_debug_exception(CPUState *env)
-{
- CPUWatchpoint *wp;
-
- if (!env->watchpoint_hit) {
- QTAILQ_FOREACH(wp, &env->watchpoints, entry) {
- wp->flags &= ~BP_WATCHPOINT_HIT;
- }
- }
- if (debug_excp_handler) {
- debug_excp_handler(env);
- }
-
gdb_set_stop_cpu(env);
qemu_system_debug_request();
#ifdef CONFIG_IOTHREAD
@@ -245,11 +225,58 @@ static void qemu_init_sigbus(void)
prctl(PR_MCE_KILL, PR_MCE_KILL_SET, PR_MCE_KILL_EARLY, 0, 0);
}
+static void qemu_kvm_eat_signals(CPUState *env)
+{
+ struct timespec ts = { 0, 0 };
+ siginfo_t siginfo;
+ sigset_t waitset;
+ sigset_t chkset;
+ int r;
+
+ sigemptyset(&waitset);
+ sigaddset(&waitset, SIG_IPI);
+ sigaddset(&waitset, SIGBUS);
+
+ do {
+ r = sigtimedwait(&waitset, &siginfo, &ts);
+ if (r == -1 && !(errno == EAGAIN || errno == EINTR)) {
+ perror("sigtimedwait");
+ exit(1);
+ }
+
+ switch (r) {
+ case SIGBUS:
+ if (kvm_on_sigbus_vcpu(env, siginfo.si_code, siginfo.si_addr)) {
+ sigbus_reraise();
+ }
+ break;
+ default:
+ break;
+ }
+
+ r = sigpending(&chkset);
+ if (r == -1) {
+ perror("sigpending");
+ exit(1);
+ }
+ } while (sigismember(&chkset, SIG_IPI) || sigismember(&chkset, SIGBUS));
+
+#ifndef CONFIG_IOTHREAD
+ if (sigismember(&chkset, SIGIO) || sigismember(&chkset, SIGALRM)) {
+ qemu_notify_event();
+ }
+#endif
+}
+
#else /* !CONFIG_LINUX */
static void qemu_init_sigbus(void)
{
}
+
+static void qemu_kvm_eat_signals(CPUState *env)
+{
+}
#endif /* !CONFIG_LINUX */
#ifndef _WIN32
@@ -455,49 +482,6 @@ static void qemu_tcg_init_cpu_signals(void)
#endif
}
-static void qemu_kvm_eat_signals(CPUState *env)
-{
- struct timespec ts = { 0, 0 };
- siginfo_t siginfo;
- sigset_t waitset;
- sigset_t chkset;
- int r;
-
- sigemptyset(&waitset);
- sigaddset(&waitset, SIG_IPI);
- sigaddset(&waitset, SIGBUS);
-
- do {
- r = sigtimedwait(&waitset, &siginfo, &ts);
- if (r == -1 && !(errno == EAGAIN || errno == EINTR)) {
- perror("sigtimedwait");
- exit(1);
- }
-
- switch (r) {
- case SIGBUS:
- if (kvm_on_sigbus_vcpu(env, siginfo.si_code, siginfo.si_addr)) {
- sigbus_reraise();
- }
- break;
- default:
- break;
- }
-
- r = sigpending(&chkset);
- if (r == -1) {
- perror("sigpending");
- exit(1);
- }
- } while (sigismember(&chkset, SIG_IPI) || sigismember(&chkset, SIGBUS));
-
-#ifndef CONFIG_IOTHREAD
- if (sigismember(&chkset, SIGIO) || sigismember(&chkset, SIGALRM)) {
- qemu_notify_event();
- }
-#endif
-}
-
#else /* _WIN32 */
HANDLE qemu_event_handle;
@@ -526,10 +510,6 @@ static void qemu_event_increment(void)
}
}
-static void qemu_kvm_eat_signals(CPUState *env)
-{
-}
-
static int qemu_signal_init(void)
{
return 0;
@@ -796,6 +776,7 @@ static void *qemu_kvm_cpu_thread_fn(void *arg)
qemu_mutex_lock(&qemu_global_mutex);
qemu_thread_get_self(env->thread);
+ env->thread_id = qemu_get_thread_id();
r = kvm_init_vcpu(env);
if (r < 0) {
@@ -818,7 +799,7 @@ static void *qemu_kvm_cpu_thread_fn(void *arg)
if (cpu_can_run(env)) {
r = kvm_cpu_exec(env);
if (r == EXCP_DEBUG) {
- cpu_handle_debug_exception(env);
+ cpu_handle_guest_debug(env);
}
}
qemu_kvm_wait_io_event(env);
@@ -837,6 +818,7 @@ static void *qemu_tcg_cpu_thread_fn(void *arg)
/* signal CPU creation */
qemu_mutex_lock(&qemu_global_mutex);
for (env = first_cpu; env != NULL; env = env->next_cpu) {
+ env->thread_id = qemu_get_thread_id();
env->created = 1;
}
qemu_cond_signal(&qemu_cpu_cond);
@@ -1110,7 +1092,7 @@ bool cpu_exec_all(void)
r = tcg_cpu_exec(env);
}
if (r == EXCP_DEBUG) {
- cpu_handle_debug_exception(env);
+ cpu_handle_guest_debug(env);
break;
}
} else if (env->stop || env->stopped) {
diff --git a/exec.c b/exec.c
index 3d78063437..964ce318fb 100644
--- a/exec.c
+++ b/exec.c
@@ -638,6 +638,9 @@ void cpu_exec_init(CPUState *env)
env->numa_node = 0;
QTAILQ_INIT(&env->breakpoints);
QTAILQ_INIT(&env->watchpoints);
+#ifndef CONFIG_USER_ONLY
+ env->thread_id = qemu_get_thread_id();
+#endif
*penv = env;
#if defined(CONFIG_USER_ONLY)
cpu_list_unlock();
@@ -2867,6 +2870,7 @@ ram_addr_t qemu_ram_alloc_from_ptr(DeviceState *dev, const char *name,
if (host) {
new_block->host = host;
+ new_block->flags |= RAM_PREALLOC_MASK;
} else {
if (mem_path) {
#if defined (__linux__) && !defined(TARGET_S390X)
@@ -2920,7 +2924,9 @@ void qemu_ram_free(ram_addr_t addr)
QLIST_FOREACH(block, &ram_list.blocks, next) {
if (addr == block->offset) {
QLIST_REMOVE(block, next);
- if (mem_path) {
+ if (block->flags & RAM_PREALLOC_MASK) {
+ ;
+ } else if (mem_path) {
#if defined (__linux__) && !defined(TARGET_S390X)
if (block->fd) {
munmap(block->host, block->length);
@@ -2928,6 +2934,8 @@ void qemu_ram_free(ram_addr_t addr)
} else {
qemu_vfree(block->host);
}
+#else
+ abort();
#endif
} else {
#if defined(TARGET_S390X) && defined(CONFIG_KVM)
@@ -2943,6 +2951,66 @@ void qemu_ram_free(ram_addr_t addr)
}
+#ifndef _WIN32
+void qemu_ram_remap(ram_addr_t addr, ram_addr_t length)
+{
+ RAMBlock *block;
+ ram_addr_t offset;
+ int flags;
+ void *area, *vaddr;
+
+ QLIST_FOREACH(block, &ram_list.blocks, next) {
+ offset = addr - block->offset;
+ if (offset < block->length) {
+ vaddr = block->host + offset;
+ if (block->flags & RAM_PREALLOC_MASK) {
+ ;
+ } else {
+ flags = MAP_FIXED;
+ munmap(vaddr, length);
+ if (mem_path) {
+#if defined(__linux__) && !defined(TARGET_S390X)
+ if (block->fd) {
+#ifdef MAP_POPULATE
+ flags |= mem_prealloc ? MAP_POPULATE | MAP_SHARED :
+ MAP_PRIVATE;
+#else
+ flags |= MAP_PRIVATE;
+#endif
+ area = mmap(vaddr, length, PROT_READ | PROT_WRITE,
+ flags, block->fd, offset);
+ } else {
+ flags |= MAP_PRIVATE | MAP_ANONYMOUS;
+ area = mmap(vaddr, length, PROT_READ | PROT_WRITE,
+ flags, -1, 0);
+ }
+#else
+ abort();
+#endif
+ } else {
+#if defined(TARGET_S390X) && defined(CONFIG_KVM)
+ flags |= MAP_SHARED | MAP_ANONYMOUS;
+ area = mmap(vaddr, length, PROT_EXEC|PROT_READ|PROT_WRITE,
+ flags, -1, 0);
+#else
+ flags |= MAP_PRIVATE | MAP_ANONYMOUS;
+ area = mmap(vaddr, length, PROT_READ | PROT_WRITE,
+ flags, -1, 0);
+#endif
+ }
+ if (area != vaddr) {
+ fprintf(stderr, "Could not remap addr: %lx@%lx\n",
+ length, addr);
+ exit(1);
+ }
+ qemu_madvise(vaddr, length, QEMU_MADV_MERGEABLE);
+ }
+ return;
+ }
+ }
+}
+#endif /* !_WIN32 */
+
/* Return a host pointer to ram allocated with qemu_ram_alloc.
With the exception of the softmmu code in this file, this should
only be used for local memory (e.g. video ram) that the device owns,
diff --git a/kvm-all.c b/kvm-all.c
index e6a7de4722..1d7e8eabf4 100644
--- a/kvm-all.c
+++ b/kvm-all.c
@@ -211,6 +211,7 @@ int kvm_init_vcpu(CPUState *env)
env->kvm_fd = ret;
env->kvm_state = s;
+ env->kvm_vcpu_dirty = 1;
mmap_size = kvm_ioctl(s, KVM_GET_VCPU_MMAP_SIZE, 0);
if (mmap_size < 0) {
@@ -830,7 +831,7 @@ static int kvm_handle_internal_error(CPUState *env, struct kvm_run *run)
fprintf(stderr, "emulation failure\n");
if (!kvm_arch_stop_on_emulation_error(env)) {
cpu_dump_state(env, stderr, fprintf, CPU_DUMP_CODE);
- return 0;
+ return EXCP_INTERRUPT;
}
}
/* FIXME: Should trigger a qmp message to let management know
@@ -889,11 +890,11 @@ void kvm_cpu_synchronize_post_init(CPUState *env)
int kvm_cpu_exec(CPUState *env)
{
struct kvm_run *run = env->kvm_run;
- int ret;
+ int ret, run_ret;
DPRINTF("kvm_cpu_exec()\n");
- if (kvm_arch_process_irqchip_events(env)) {
+ if (kvm_arch_process_async_events(env)) {
env->exit_request = 0;
return EXCP_HLT;
}
@@ -919,7 +920,7 @@ int kvm_cpu_exec(CPUState *env)
cpu_single_env = NULL;
qemu_mutex_unlock_iothread();
- ret = kvm_vcpu_ioctl(env, KVM_RUN, 0);
+ run_ret = kvm_vcpu_ioctl(env, KVM_RUN, 0);
qemu_mutex_lock_iothread();
cpu_single_env = env;
@@ -927,18 +928,16 @@ int kvm_cpu_exec(CPUState *env)
kvm_flush_coalesced_mmio_buffer();
- if (ret == -EINTR || ret == -EAGAIN) {
- DPRINTF("io window exit\n");
- ret = 0;
- break;
- }
-
- if (ret < 0) {
- DPRINTF("kvm run failed %s\n", strerror(-ret));
+ if (run_ret < 0) {
+ if (run_ret == -EINTR || run_ret == -EAGAIN) {
+ DPRINTF("io window exit\n");
+ ret = EXCP_INTERRUPT;
+ break;
+ }
+ DPRINTF("kvm run failed %s\n", strerror(-run_ret));
abort();
}
- ret = 0; /* exit loop */
switch (run->exit_reason) {
case KVM_EXIT_IO:
DPRINTF("handle_io\n");
@@ -947,7 +946,7 @@ int kvm_cpu_exec(CPUState *env)
run->io.direction,
run->io.size,
run->io.count);
- ret = 1;
+ ret = 0;
break;
case KVM_EXIT_MMIO:
DPRINTF("handle_mmio\n");
@@ -955,14 +954,16 @@ int kvm_cpu_exec(CPUState *env)
run->mmio.data,
run->mmio.len,
run->mmio.is_write);
- ret = 1;
+ ret = 0;
break;
case KVM_EXIT_IRQ_WINDOW_OPEN:
DPRINTF("irq_window_open\n");
+ ret = EXCP_INTERRUPT;
break;
case KVM_EXIT_SHUTDOWN:
DPRINTF("shutdown\n");
qemu_system_reset_request();
+ ret = EXCP_INTERRUPT;
break;
case KVM_EXIT_UNKNOWN:
fprintf(stderr, "KVM: unknown exit, hardware reason %" PRIx64 "\n",
@@ -974,31 +975,18 @@ int kvm_cpu_exec(CPUState *env)
ret = kvm_handle_internal_error(env, run);
break;
#endif
- case KVM_EXIT_DEBUG:
- DPRINTF("kvm_exit_debug\n");
-#ifdef KVM_CAP_SET_GUEST_DEBUG
- if (kvm_arch_debug(&run->debug.arch)) {
- ret = EXCP_DEBUG;
- goto out;
- }
- /* re-enter, this exception was guest-internal */
- ret = 1;
-#endif /* KVM_CAP_SET_GUEST_DEBUG */
- break;
default:
DPRINTF("kvm_arch_handle_exit\n");
ret = kvm_arch_handle_exit(env, run);
break;
}
- } while (ret > 0);
+ } while (ret == 0);
if (ret < 0) {
cpu_dump_state(env, stderr, fprintf, CPU_DUMP_CODE);
vm_stop(VMSTOP_PANIC);
}
- ret = EXCP_INTERRUPT;
-out:
env->exit_request = 0;
cpu_single_env = NULL;
return ret;
diff --git a/kvm.h b/kvm.h
index 59b2c29fd9..d565dba1da 100644
--- a/kvm.h
+++ b/kvm.h
@@ -102,7 +102,7 @@ void kvm_arch_post_run(CPUState *env, struct kvm_run *run);
int kvm_arch_handle_exit(CPUState *env, struct kvm_run *run);
-int kvm_arch_process_irqchip_events(CPUState *env);
+int kvm_arch_process_async_events(CPUState *env);
int kvm_arch_get_registers(CPUState *env);
@@ -136,8 +136,6 @@ struct kvm_sw_breakpoint {
QTAILQ_HEAD(kvm_sw_breakpoint_head, kvm_sw_breakpoint);
-int kvm_arch_debug(struct kvm_debug_exit_arch *arch_info);
-
struct kvm_sw_breakpoint *kvm_find_sw_breakpoint(CPUState *env,
target_ulong pc);
diff --git a/monitor.c b/monitor.c
index 413c963e34..552e951f7d 100644
--- a/monitor.c
+++ b/monitor.c
@@ -897,6 +897,9 @@ static void print_cpu_iter(QObject *obj, void *opaque)
monitor_printf(mon, " (halted)");
}
+ monitor_printf(mon, " thread_id=%" PRId64 " ",
+ qdict_get_int(cpu, "thread_id"));
+
monitor_printf(mon, "\n");
}
@@ -941,6 +944,7 @@ static void do_info_cpus(Monitor *mon, QObject **ret_data)
#elif defined(TARGET_MIPS)
qdict_put(cpu, "PC", qint_from_int(env->active_tc.PC));
#endif
+ qdict_put(cpu, "thread_id", qint_from_int(env->thread_id));
qlist_append(cpu_list, cpu);
}
@@ -2709,12 +2713,15 @@ 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);
+ int flags = MCE_INJECT_UNCOND_AO;
+ if (qdict_get_try_bool(qdict, "broadcast", 0)) {
+ flags |= MCE_INJECT_BROADCAST;
+ }
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,
- broadcast);
+ if (cenv->cpu_index == cpu_index) {
+ cpu_x86_inject_mce(mon, cenv, bank, status, mcg_status, addr, misc,
+ flags);
break;
}
}
diff --git a/os-posix.c b/os-posix.c
index 38c29d1afe..7971f8620b 100644
--- a/os-posix.c
+++ b/os-posix.c
@@ -41,6 +41,7 @@
#ifdef CONFIG_LINUX
#include <sys/prctl.h>
+#include <sys/syscall.h>
#endif
#ifdef CONFIG_EVENTFD
@@ -382,3 +383,12 @@ int qemu_create_pidfile(const char *filename)
return 0;
}
+
+int qemu_get_thread_id(void)
+{
+#if defined (__linux__)
+ return syscall(SYS_gettid);
+#else
+ return getpid();
+#endif
+}
diff --git a/os-win32.c b/os-win32.c
index c971d928ab..d6d54c60b9 100644
--- a/os-win32.c
+++ b/os-win32.c
@@ -266,3 +266,8 @@ int qemu_create_pidfile(const char *filename)
}
return 0;
}
+
+int qemu_get_thread_id(void)
+{
+ return GetCurrentThreadId();
+}
diff --git a/osdep.h b/osdep.h
index 5e4886030e..970d767078 100644
--- a/osdep.h
+++ b/osdep.h
@@ -128,6 +128,7 @@ void qemu_vfree(void *ptr);
int qemu_madvise(void *addr, size_t len, int advice);
int qemu_create_pidfile(const char *filename);
+int qemu_get_thread_id(void);
#ifdef _WIN32
static inline void qemu_timersub(const struct timeval *val1,
diff --git a/qemu-common.h b/qemu-common.h
index 3fe1719d03..7a96dd14e8 100644
--- a/qemu-common.h
+++ b/qemu-common.h
@@ -18,6 +18,9 @@ typedef struct QEMUFile QEMUFile;
typedef struct QEMUBH QEMUBH;
typedef struct DeviceState DeviceState;
+struct Monitor;
+typedef struct Monitor Monitor;
+
/* we put basic includes here to avoid repeating them in device drivers */
#include <stdlib.h>
#include <stdio.h>
@@ -327,9 +330,6 @@ void qemu_iovec_memset(QEMUIOVector *qiov, int c, size_t count);
void qemu_iovec_memset_skip(QEMUIOVector *qiov, int c, size_t count,
size_t skip);
-struct Monitor;
-typedef struct Monitor Monitor;
-
/* Convert a byte between binary and BCD. */
static inline uint8_t to_bcd(uint8_t val)
{
diff --git a/qmp-commands.hx b/qmp-commands.hx
index df40a3d42e..1f72a8d422 100644
--- a/qmp-commands.hx
+++ b/qmp-commands.hx
@@ -1194,6 +1194,7 @@ Return a json-array. Each CPU is represented by a json-object, which contains:
"nip": PPC (json-int)
"pc" and "npc": sparc (json-int)
"PC": mips (json-int)
+- "thread_id": ID of the underlying host thread (json-int)
Example:
@@ -1205,12 +1206,14 @@ Example:
"current":true,
"halted":false,
"pc":3227107138
+ "thread_id":3134
},
{
"CPU":1,
"current":false,
"halted":true,
"pc":7108165
+ "thread_id":3135
}
]
}
diff --git a/target-i386/cpu.h b/target-i386/cpu.h
index 5f1df8b4d3..c7047d5912 100644
--- a/target-i386/cpu.h
+++ b/target-i386/cpu.h
@@ -685,7 +685,7 @@ typedef struct CPUX86State {
uint64_t tsc;
- uint64_t pat;
+ uint64_t mcg_status;
/* exception/interrupt handling */
int error_code;
@@ -705,6 +705,8 @@ typedef struct CPUX86State {
CPU_COMMON
+ uint64_t pat;
+
/* processor features (e.g. for CPUID insn) */
uint32_t cpuid_level;
uint32_t cpuid_vendor1;
@@ -741,7 +743,6 @@ typedef struct CPUX86State {
struct DeviceState *apic_state;
uint64_t mcg_cap;
- uint64_t mcg_status;
uint64_t mcg_ctl;
uint64_t mce_banks[MCE_BANKS_DEF*4];
@@ -985,4 +986,12 @@ static inline void cpu_get_tb_cpu_state(CPUState *env, target_ulong *pc,
void do_cpu_init(CPUState *env);
void do_cpu_sipi(CPUState *env);
+
+#define MCE_INJECT_BROADCAST 1
+#define MCE_INJECT_UNCOND_AO 2
+
+void cpu_x86_inject_mce(Monitor *mon, CPUState *cenv, int bank,
+ uint64_t status, uint64_t mcg_status, uint64_t addr,
+ uint64_t misc, int flags);
+
#endif /* CPU_I386_H */
diff --git a/target-i386/cpuid.c b/target-i386/cpuid.c
index 5382a283f5..814d13e767 100644
--- a/target-i386/cpuid.c
+++ b/target-i386/cpuid.c
@@ -847,7 +847,6 @@ int cpu_x86_register (CPUX86State *env, const char *cpu_model)
env->cpuid_version |= ((def->model & 0xf) << 4) | ((def->model >> 4) << 16);
env->cpuid_version |= def->stepping;
env->cpuid_features = def->features;
- env->pat = 0x0007040600070406ULL;
env->cpuid_ext_features = def->ext_features;
env->cpuid_ext2_features = def->ext2_features;
env->cpuid_ext3_features = def->ext3_features;
diff --git a/target-i386/exec.h b/target-i386/exec.h
index 3e7386e91c..6f9f709d8a 100644
--- a/target-i386/exec.h
+++ b/target-i386/exec.h
@@ -293,15 +293,12 @@ static inline void load_eflags(int eflags, int update_mask)
static inline int cpu_has_work(CPUState *env)
{
- int work;
-
- work = (env->interrupt_request & CPU_INTERRUPT_HARD) &&
- (env->eflags & IF_MASK);
- work |= env->interrupt_request & CPU_INTERRUPT_NMI;
- work |= env->interrupt_request & CPU_INTERRUPT_INIT;
- work |= env->interrupt_request & CPU_INTERRUPT_SIPI;
-
- return work;
+ return ((env->interrupt_request & CPU_INTERRUPT_HARD) &&
+ (env->eflags & IF_MASK)) ||
+ (env->interrupt_request & (CPU_INTERRUPT_NMI |
+ CPU_INTERRUPT_INIT |
+ CPU_INTERRUPT_SIPI |
+ CPU_INTERRUPT_MCE));
}
/* load efer and update the corresponding hflags. XXX: do consistency
diff --git a/target-i386/helper.c b/target-i386/helper.c
index f0c546df5c..d15fca591e 100644
--- a/target-i386/helper.c
+++ b/target-i386/helper.c
@@ -27,7 +27,10 @@
#include "exec-all.h"
#include "qemu-common.h"
#include "kvm.h"
-#include "kvm_x86.h"
+#ifndef CONFIG_USER_ONLY
+#include "sysemu.h"
+#include "monitor.h"
+#endif
//#define DEBUG_MMU
@@ -96,13 +99,13 @@ void cpu_reset(CPUX86State *env)
env->mxcsr = 0x1f80;
+ env->pat = 0x0007040600070406ULL;
+
memset(env->dr, 0, sizeof(env->dr));
env->dr[6] = DR6_FIXED_1;
env->dr[7] = DR7_FIXED_1;
cpu_breakpoint_remove_all(env, BP_CPU);
cpu_watchpoint_remove_all(env, BP_CPU);
-
- env->mcg_status = 0;
}
void cpu_x86_close(CPUX86State *env)
@@ -1065,91 +1068,138 @@ static void breakpoint_handler(CPUState *env)
prev_debug_excp_handler(env);
}
-/* This should come from sysemu.h - if we could include it here... */
-void qemu_system_reset_request(void);
-
-static void qemu_inject_x86_mce(CPUState *cenv, int bank, uint64_t status,
- uint64_t mcg_status, uint64_t addr, uint64_t misc)
+typedef struct MCEInjectionParams {
+ Monitor *mon;
+ CPUState *env;
+ int bank;
+ uint64_t status;
+ uint64_t mcg_status;
+ uint64_t addr;
+ uint64_t misc;
+ int flags;
+} MCEInjectionParams;
+
+static void do_inject_x86_mce(void *data)
{
- uint64_t mcg_cap = cenv->mcg_cap;
- uint64_t *banks = cenv->mce_banks;
+ MCEInjectionParams *params = data;
+ CPUState *cenv = params->env;
+ uint64_t *banks = cenv->mce_banks + 4 * params->bank;
+
+ cpu_synchronize_state(cenv);
/*
- * if MSR_MCG_CTL is not all 1s, the uncorrected error
- * reporting is disabled
- */
- if ((status & MCI_STATUS_UC) && (mcg_cap & MCG_CTL_P) &&
- cenv->mcg_ctl != ~(uint64_t)0)
- return;
- banks += 4 * bank;
- /*
- * if MSR_MCi_CTL is not all 1s, the uncorrected error
- * reporting is disabled for the bank
+ * If there is an MCE exception being processed, ignore this SRAO MCE
+ * unless unconditional injection was requested.
*/
- if ((status & MCI_STATUS_UC) && banks[0] != ~(uint64_t)0)
+ if (!(params->flags & MCE_INJECT_UNCOND_AO)
+ && !(params->status & MCI_STATUS_AR)
+ && (cenv->mcg_status & MCG_STATUS_MCIP)) {
return;
- if (status & MCI_STATUS_UC) {
+ }
+
+ if (params->status & MCI_STATUS_UC) {
+ /*
+ * if MSR_MCG_CTL is not all 1s, the uncorrected error
+ * reporting is disabled
+ */
+ if ((cenv->mcg_cap & MCG_CTL_P) && cenv->mcg_ctl != ~(uint64_t)0) {
+ monitor_printf(params->mon,
+ "CPU %d: Uncorrected error reporting disabled\n",
+ cenv->cpu_index);
+ return;
+ }
+
+ /*
+ * if MSR_MCi_CTL is not all 1s, the uncorrected error
+ * reporting is disabled for the bank
+ */
+ if (banks[0] != ~(uint64_t)0) {
+ monitor_printf(params->mon,
+ "CPU %d: Uncorrected error reporting disabled for"
+ " bank %d\n",
+ cenv->cpu_index, params->bank);
+ return;
+ }
+
if ((cenv->mcg_status & MCG_STATUS_MCIP) ||
!(cenv->cr[4] & CR4_MCE_MASK)) {
- fprintf(stderr, "injects mce exception while previous "
- "one is in progress!\n");
+ monitor_printf(params->mon,
+ "CPU %d: Previous MCE still in progress, raising"
+ " triple fault\n",
+ cenv->cpu_index);
qemu_log_mask(CPU_LOG_RESET, "Triple fault\n");
qemu_system_reset_request();
return;
}
- if (banks[1] & MCI_STATUS_VAL)
- status |= MCI_STATUS_OVER;
- banks[2] = addr;
- banks[3] = misc;
- cenv->mcg_status = mcg_status;
- banks[1] = status;
+ if (banks[1] & MCI_STATUS_VAL) {
+ params->status |= MCI_STATUS_OVER;
+ }
+ banks[2] = params->addr;
+ banks[3] = params->misc;
+ cenv->mcg_status = params->mcg_status;
+ banks[1] = params->status;
cpu_interrupt(cenv, CPU_INTERRUPT_MCE);
} else if (!(banks[1] & MCI_STATUS_VAL)
|| !(banks[1] & MCI_STATUS_UC)) {
- if (banks[1] & MCI_STATUS_VAL)
- status |= MCI_STATUS_OVER;
- banks[2] = addr;
- banks[3] = misc;
- banks[1] = status;
- } else
+ if (banks[1] & MCI_STATUS_VAL) {
+ params->status |= MCI_STATUS_OVER;
+ }
+ banks[2] = params->addr;
+ banks[3] = params->misc;
+ banks[1] = params->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)
+void cpu_x86_inject_mce(Monitor *mon, CPUState *cenv, int bank,
+ uint64_t status, uint64_t mcg_status, uint64_t addr,
+ uint64_t misc, int flags)
{
+ MCEInjectionParams params = {
+ .mon = mon,
+ .env = cenv,
+ .bank = bank,
+ .status = status,
+ .mcg_status = mcg_status,
+ .addr = addr,
+ .misc = misc,
+ .flags = flags,
+ };
unsigned bank_num = cenv->mcg_cap & 0xff;
CPUState *env;
- int flag = 0;
- if (bank >= bank_num || !(status & MCI_STATUS_VAL)) {
+ if (!cenv->mcg_cap) {
+ monitor_printf(mon, "MCE injection not supported\n");
return;
}
-
- if (broadcast) {
- if (!cpu_x86_support_mca_broadcast(cenv)) {
- fprintf(stderr, "Current CPU does not support broadcast\n");
- return;
- }
+ if (bank >= bank_num) {
+ monitor_printf(mon, "Invalid MCE bank number\n");
+ return;
+ }
+ if (!(status & MCI_STATUS_VAL)) {
+ monitor_printf(mon, "Invalid MCE status code\n");
+ return;
+ }
+ if ((flags & MCE_INJECT_BROADCAST)
+ && !cpu_x86_support_mca_broadcast(cenv)) {
+ monitor_printf(mon, "Guest CPU does not support MCA 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, MCI_STATUS_VAL | MCI_STATUS_UC,
- MCG_STATUS_MCIP | MCG_STATUS_RIPV, 0, 0);
+ run_on_cpu(cenv, do_inject_x86_mce, &params);
+ if (flags & MCE_INJECT_BROADCAST) {
+ params.bank = 1;
+ params.status = MCI_STATUS_VAL | MCI_STATUS_UC;
+ params.mcg_status = MCG_STATUS_MCIP | MCG_STATUS_RIPV;
+ params.addr = 0;
+ params.misc = 0;
+ for (env = first_cpu; env != NULL; env = env->next_cpu) {
+ if (cenv == env) {
+ continue;
}
+ params.env = env;
+ run_on_cpu(cenv, do_inject_x86_mce, &params);
}
}
}
@@ -1157,15 +1207,16 @@ void cpu_inject_x86_mce(CPUState *cenv, int bank, uint64_t status,
static void mce_init(CPUX86State *cenv)
{
- unsigned int bank, bank_num;
+ unsigned int bank;
- if (((cenv->cpuid_version >> 8)&0xf) >= 6
- && (cenv->cpuid_features&(CPUID_MCE|CPUID_MCA)) == (CPUID_MCE|CPUID_MCA)) {
+ if (((cenv->cpuid_version >> 8) & 0xf) >= 6
+ && (cenv->cpuid_features & (CPUID_MCE | CPUID_MCA)) ==
+ (CPUID_MCE | CPUID_MCA)) {
cenv->mcg_cap = MCE_CAP_DEF | MCE_BANKS_DEF;
cenv->mcg_ctl = ~(uint64_t)0;
- bank_num = MCE_BANKS_DEF;
- for (bank = 0; bank < bank_num; bank++)
- cenv->mce_banks[bank*4] = ~(uint64_t)0;
+ for (bank = 0; bank < MCE_BANKS_DEF; bank++) {
+ cenv->mce_banks[bank * 4] = ~(uint64_t)0;
+ }
}
}
@@ -1231,8 +1282,11 @@ CPUX86State *cpu_x86_init(const char *cpu_model)
void do_cpu_init(CPUState *env)
{
int sipi = env->interrupt_request & CPU_INTERRUPT_SIPI;
+ uint64_t pat = env->pat;
+
cpu_reset(env);
env->interrupt_request = sipi;
+ env->pat = pat;
apic_init_reset(env->apic_state);
env->halted = !cpu_is_bsp(env);
}
diff --git a/target-i386/kvm.c b/target-i386/kvm.c
index 1f12cbf19e..a13599db81 100644
--- a/target-i386/kvm.c
+++ b/target-i386/kvm.c
@@ -28,7 +28,6 @@
#include "hw/pc.h"
#include "hw/apic.h"
#include "ioport.h"
-#include "kvm_x86.h"
#ifdef CONFIG_KVM_PARA
#include <linux/kvm_para.h>
@@ -172,9 +171,42 @@ static int get_para_features(CPUState *env)
#endif
return features;
}
-#endif
+#endif /* CONFIG_KVM_PARA */
+
+typedef struct HWPoisonPage {
+ ram_addr_t ram_addr;
+ QLIST_ENTRY(HWPoisonPage) list;
+} HWPoisonPage;
+
+static QLIST_HEAD(, HWPoisonPage) hwpoison_page_list =
+ QLIST_HEAD_INITIALIZER(hwpoison_page_list);
+
+static void kvm_unpoison_all(void *param)
+{
+ HWPoisonPage *page, *next_page;
+
+ QLIST_FOREACH_SAFE(page, &hwpoison_page_list, list, next_page) {
+ QLIST_REMOVE(page, list);
+ qemu_ram_remap(page->ram_addr, TARGET_PAGE_SIZE);
+ qemu_free(page);
+ }
+}
#ifdef KVM_CAP_MCE
+static void kvm_hwpoison_page_add(ram_addr_t ram_addr)
+{
+ HWPoisonPage *page;
+
+ QLIST_FOREACH(page, &hwpoison_page_list, list) {
+ if (page->ram_addr == ram_addr) {
+ return;
+ }
+ }
+ page = qemu_malloc(sizeof(HWPoisonPage));
+ page->ram_addr = ram_addr;
+ QLIST_INSERT_HEAD(&hwpoison_page_list, page, list);
+}
+
static int kvm_get_mce_cap_supported(KVMState *s, uint64_t *mce_cap,
int *max_banks)
{
@@ -188,117 +220,129 @@ static int kvm_get_mce_cap_supported(KVMState *s, uint64_t *mce_cap,
return -ENOSYS;
}
-static int kvm_setup_mce(CPUState *env, uint64_t *mcg_cap)
+static void kvm_mce_inject(CPUState *env, target_phys_addr_t paddr, int code)
{
- return kvm_vcpu_ioctl(env, KVM_X86_SETUP_MCE, mcg_cap);
-}
+ uint64_t status = MCI_STATUS_VAL | MCI_STATUS_UC | MCI_STATUS_EN |
+ MCI_STATUS_MISCV | MCI_STATUS_ADDRV | MCI_STATUS_S;
+ uint64_t mcg_status = MCG_STATUS_MCIP;
-static int kvm_set_mce(CPUState *env, struct kvm_x86_mce *m)
-{
- return kvm_vcpu_ioctl(env, KVM_X86_SET_MCE, m);
+ if (code == BUS_MCEERR_AR) {
+ status |= MCI_STATUS_AR | 0x134;
+ mcg_status |= MCG_STATUS_EIPV;
+ } else {
+ status |= 0xc0;
+ mcg_status |= MCG_STATUS_RIPV;
+ }
+ cpu_x86_inject_mce(NULL, env, 9, status, mcg_status, paddr,
+ (MCM_ADDR_PHYS << 6) | 0xc,
+ cpu_x86_support_mca_broadcast(env) ?
+ MCE_INJECT_BROADCAST : 0);
}
+#endif /* KVM_CAP_MCE */
-static int kvm_get_msr(CPUState *env, struct kvm_msr_entry *msrs, int n)
+static void hardware_memory_error(void)
{
- struct kvm_msrs *kmsrs = qemu_malloc(sizeof *kmsrs + n * sizeof *msrs);
- int r;
-
- kmsrs->nmsrs = n;
- memcpy(kmsrs->entries, msrs, n * sizeof *msrs);
- r = kvm_vcpu_ioctl(env, KVM_GET_MSRS, kmsrs);
- memcpy(msrs, kmsrs->entries, n * sizeof *msrs);
- free(kmsrs);
- return r;
+ fprintf(stderr, "Hardware memory error!\n");
+ exit(1);
}
-/* FIXME: kill this and kvm_get_msr, use env->mcg_status instead */
-static int kvm_mce_in_progress(CPUState *env)
+int kvm_arch_on_sigbus_vcpu(CPUState *env, int code, void *addr)
{
- struct kvm_msr_entry msr_mcg_status = {
- .index = MSR_MCG_STATUS,
- };
- int r;
+#ifdef KVM_CAP_MCE
+ ram_addr_t ram_addr;
+ target_phys_addr_t paddr;
- r = kvm_get_msr(env, &msr_mcg_status, 1);
- if (r == -1 || r == 0) {
- fprintf(stderr, "Failed to get MCE status\n");
- return 0;
+ if ((env->mcg_cap & MCG_SER_P) && addr
+ && (code == BUS_MCEERR_AR || code == BUS_MCEERR_AO)) {
+ if (qemu_ram_addr_from_host(addr, &ram_addr) ||
+ !kvm_physical_memory_addr_from_ram(env->kvm_state, ram_addr,
+ &paddr)) {
+ fprintf(stderr, "Hardware memory error for memory used by "
+ "QEMU itself instead of guest system!\n");
+ /* Hope we are lucky for AO MCE */
+ if (code == BUS_MCEERR_AO) {
+ return 0;
+ } else {
+ hardware_memory_error();
+ }
+ }
+ kvm_hwpoison_page_add(ram_addr);
+ kvm_mce_inject(env, paddr, code);
+ } else
+#endif /* KVM_CAP_MCE */
+ {
+ if (code == BUS_MCEERR_AO) {
+ return 0;
+ } else if (code == BUS_MCEERR_AR) {
+ hardware_memory_error();
+ } else {
+ return 1;
+ }
}
- return !!(msr_mcg_status.data & MCG_STATUS_MCIP);
+ return 0;
}
-struct kvm_x86_mce_data
-{
- CPUState *env;
- struct kvm_x86_mce *mce;
- int abort_on_error;
-};
-
-static void kvm_do_inject_x86_mce(void *_data)
+int kvm_arch_on_sigbus(int code, void *addr)
{
- struct kvm_x86_mce_data *data = _data;
- int r;
+#ifdef KVM_CAP_MCE
+ if ((first_cpu->mcg_cap & MCG_SER_P) && addr && code == BUS_MCEERR_AO) {
+ ram_addr_t ram_addr;
+ target_phys_addr_t paddr;
- /* 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)) {
- if (kvm_mce_in_progress(data->env)) {
- return;
+ /* Hope we are lucky for AO MCE */
+ if (qemu_ram_addr_from_host(addr, &ram_addr) ||
+ !kvm_physical_memory_addr_from_ram(first_cpu->kvm_state, ram_addr,
+ &paddr)) {
+ fprintf(stderr, "Hardware memory error for memory used by "
+ "QEMU itself instead of guest system!: %p\n", addr);
+ return 0;
}
- }
-
- r = kvm_set_mce(data->env, data->mce);
- if (r < 0) {
- perror("kvm_set_mce FAILED");
- if (data->abort_on_error) {
- abort();
+ kvm_hwpoison_page_add(ram_addr);
+ kvm_mce_inject(first_cpu, paddr, code);
+ } else
+#endif /* KVM_CAP_MCE */
+ {
+ if (code == BUS_MCEERR_AO) {
+ return 0;
+ } else if (code == BUS_MCEERR_AR) {
+ hardware_memory_error();
+ } else {
+ return 1;
}
}
+ return 0;
}
-static void kvm_inject_x86_mce_on(CPUState *env, struct kvm_x86_mce *mce,
- int flag)
+static int kvm_inject_mce_oldstyle(CPUState *env)
{
- 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);
-}
+#ifdef KVM_CAP_MCE
+ if (!kvm_has_vcpu_events() && env->exception_injected == EXCP12_MCHK) {
+ unsigned int bank, bank_num = env->mcg_cap & 0xff;
+ struct kvm_x86_mce mce;
-static void kvm_mce_broadcast_rest(CPUState *env);
-#endif
+ env->exception_injected = -1;
-void kvm_inject_x86_mce(CPUState *cenv, int bank, uint64_t status,
- uint64_t mcg_status, uint64_t addr, uint64_t misc,
- int flag)
-{
-#ifdef KVM_CAP_MCE
- struct kvm_x86_mce mce = {
- .bank = bank,
- .status = status,
- .mcg_status = mcg_status,
- .addr = addr,
- .misc = misc,
- };
+ /*
+ * There must be at least one bank in use if an MCE is pending.
+ * Find it and use its values for the event injection.
+ */
+ for (bank = 0; bank < bank_num; bank++) {
+ if (env->mce_banks[bank * 4 + 1] & MCI_STATUS_VAL) {
+ break;
+ }
+ }
+ assert(bank < bank_num);
- if (flag & MCE_BROADCAST) {
- kvm_mce_broadcast_rest(cenv);
- }
+ mce.bank = bank;
+ mce.status = env->mce_banks[bank * 4 + 1];
+ mce.mcg_status = env->mcg_status;
+ mce.addr = env->mce_banks[bank * 4 + 2];
+ mce.misc = env->mce_banks[bank * 4 + 3];
- kvm_inject_x86_mce_on(cenv, &mce, flag);
-#else
- if (flag & ABORT_ON_ERROR) {
- abort();
+ return kvm_vcpu_ioctl(env, KVM_X86_SET_MCE, &mce);
}
-#endif
+#endif /* KVM_CAP_MCE */
+ return 0;
}
static void cpu_update_state(void *opaque, int running, int reason)
@@ -426,20 +470,26 @@ int kvm_arch_init_vcpu(CPUState *env)
&& kvm_check_extension(env->kvm_state, KVM_CAP_MCE) > 0) {
uint64_t mcg_cap;
int banks;
+ int ret;
- if (kvm_get_mce_cap_supported(env->kvm_state, &mcg_cap, &banks)) {
- perror("kvm_get_mce_cap_supported FAILED");
- } 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)) {
- perror("kvm_setup_mce FAILED");
- } else {
- env->mcg_cap = mcg_cap;
- }
+ ret = kvm_get_mce_cap_supported(env->kvm_state, &mcg_cap, &banks);
+ if (ret < 0) {
+ fprintf(stderr, "kvm_get_mce_cap_supported: %s", strerror(-ret));
+ return ret;
+ }
+
+ if (banks > MCE_BANKS_DEF) {
+ banks = MCE_BANKS_DEF;
}
+ mcg_cap &= MCE_CAP_DEF;
+ mcg_cap |= banks;
+ ret = kvm_vcpu_ioctl(env, KVM_X86_SETUP_MCE, &mcg_cap);
+ if (ret < 0) {
+ fprintf(stderr, "KVM_X86_SETUP_MCE: %s", strerror(-ret));
+ return ret;
+ }
+
+ env->mcg_cap = mcg_cap;
}
#endif
@@ -556,6 +606,7 @@ int kvm_arch_init(KVMState *s)
fprintf(stderr, "e820_add_entry() table is full\n");
return ret;
}
+ qemu_register_reset(kvm_unpoison_all, NULL);
return 0;
}
@@ -810,6 +861,7 @@ 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);
+ kvm_msr_entry_set(&msrs[n++], MSR_PAT, env->pat);
if (has_msr_star) {
kvm_msr_entry_set(&msrs[n++], MSR_STAR, env->star);
}
@@ -855,14 +907,10 @@ static int kvm_put_msrs(CPUState *env, int level)
if (env->mcg_cap) {
int i;
- 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) {
- 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++) {
- kvm_msr_entry_set(&msrs[n++], MSR_MC0_CTL + i, env->mce_banks[i]);
- }
+ 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++) {
+ kvm_msr_entry_set(&msrs[n++], MSR_MC0_CTL + i, env->mce_banks[i]);
}
}
#endif
@@ -1066,6 +1114,7 @@ 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;
+ msrs[n++].index = MSR_PAT;
if (has_msr_star) {
msrs[n++].index = MSR_STAR;
}
@@ -1121,6 +1170,9 @@ static int kvm_get_msrs(CPUState *env)
case MSR_IA32_SYSENTER_EIP:
env->sysenter_eip = msrs[i].data;
break;
+ case MSR_PAT:
+ env->pat = msrs[i].data;
+ break;
case MSR_STAR:
env->star = msrs[i].data;
break;
@@ -1373,6 +1425,11 @@ int kvm_arch_put_registers(CPUState *env, int level)
if (ret < 0) {
return ret;
}
+ /* must be before kvm_put_msrs */
+ ret = kvm_inject_mce_oldstyle(env);
+ if (ret < 0) {
+ return ret;
+ }
ret = kvm_put_msrs(env, level);
if (ret < 0) {
return ret;
@@ -1509,13 +1566,38 @@ void kvm_arch_post_run(CPUState *env, struct kvm_run *run)
cpu_set_apic_base(env->apic_state, run->apic_base);
}
-int kvm_arch_process_irqchip_events(CPUState *env)
+int kvm_arch_process_async_events(CPUState *env)
{
+ if (env->interrupt_request & CPU_INTERRUPT_MCE) {
+ /* We must not raise CPU_INTERRUPT_MCE if it's not supported. */
+ assert(env->mcg_cap);
+
+ env->interrupt_request &= ~CPU_INTERRUPT_MCE;
+
+ kvm_cpu_synchronize_state(env);
+
+ if (env->exception_injected == EXCP08_DBLE) {
+ /* this means triple fault */
+ qemu_system_reset_request();
+ env->exit_request = 1;
+ return 0;
+ }
+ env->exception_injected = EXCP12_MCHK;
+ env->has_error_code = 0;
+
+ env->halted = 0;
+ if (kvm_irqchip_in_kernel() && env->mp_state == KVM_MP_STATE_HALTED) {
+ env->mp_state = KVM_MP_STATE_RUNNABLE;
+ }
+ }
+
if (kvm_irqchip_in_kernel()) {
return 0;
}
- if (env->interrupt_request & (CPU_INTERRUPT_HARD | CPU_INTERRUPT_NMI)) {
+ if (((env->interrupt_request & CPU_INTERRUPT_HARD) &&
+ (env->eflags & IF_MASK)) ||
+ (env->interrupt_request & CPU_INTERRUPT_NMI)) {
env->halted = 0;
}
if (env->interrupt_request & CPU_INTERRUPT_INIT) {
@@ -1536,64 +1618,10 @@ static int kvm_handle_halt(CPUState *env)
(env->eflags & IF_MASK)) &&
!(env->interrupt_request & CPU_INTERRUPT_NMI)) {
env->halted = 1;
- return 0;
+ return EXCP_HLT;
}
- 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) {
- case KVM_EXIT_HLT:
- 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;
+ return 0;
}
#ifdef KVM_CAP_SET_GUEST_DEBUG
@@ -1703,31 +1731,31 @@ void kvm_arch_remove_all_hw_breakpoints(void)
static CPUWatchpoint hw_watchpoint;
-int kvm_arch_debug(struct kvm_debug_exit_arch *arch_info)
+static int kvm_handle_debug(struct kvm_debug_exit_arch *arch_info)
{
- int handle = 0;
+ int ret = 0;
int n;
if (arch_info->exception == 1) {
if (arch_info->dr6 & (1 << 14)) {
if (cpu_single_env->singlestep_enabled) {
- handle = 1;
+ ret = EXCP_DEBUG;
}
} else {
for (n = 0; n < 4; n++) {
if (arch_info->dr6 & (1 << n)) {
switch ((arch_info->dr7 >> (16 + n*4)) & 0x3) {
case 0x0:
- handle = 1;
+ ret = EXCP_DEBUG;
break;
case 0x1:
- handle = 1;
+ ret = EXCP_DEBUG;
cpu_single_env->watchpoint_hit = &hw_watchpoint;
hw_watchpoint.vaddr = hw_breakpoint[n].addr;
hw_watchpoint.flags = BP_MEM_WRITE;
break;
case 0x3:
- handle = 1;
+ ret = EXCP_DEBUG;
cpu_single_env->watchpoint_hit = &hw_watchpoint;
hw_watchpoint.vaddr = hw_breakpoint[n].addr;
hw_watchpoint.flags = BP_MEM_ACCESS;
@@ -1737,17 +1765,18 @@ int kvm_arch_debug(struct kvm_debug_exit_arch *arch_info)
}
}
} else if (kvm_find_sw_breakpoint(cpu_single_env, arch_info->pc)) {
- handle = 1;
+ ret = EXCP_DEBUG;
}
- if (!handle) {
+ if (ret == 0) {
cpu_synchronize_state(cpu_single_env);
assert(cpu_single_env->exception_injected == -1);
+ /* pass to guest */
cpu_single_env->exception_injected = arch_info->exception;
cpu_single_env->has_error_code = 0;
}
- return handle;
+ return ret;
}
void kvm_arch_update_guest_debug(CPUState *env, struct kvm_guest_debug *dbg)
@@ -1778,178 +1807,68 @@ void kvm_arch_update_guest_debug(CPUState *env, struct kvm_guest_debug *dbg)
}
#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);
-}
-
-static void hardware_memory_error(void)
-{
- fprintf(stderr, "Hardware memory error!\n");
- exit(1);
-}
-
-#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;
-
- /* Broadcast MCA signal for processor version 06H_EH and above */
- 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_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)
+static bool host_supports_vmx(void)
{
- 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,
- };
+ uint32_t ecx, unused;
- kvm_inject_x86_mce_on(env, &mce, ABORT_ON_ERROR);
- kvm_mce_broadcast_rest(env);
+ host_cpuid(1, 0, &unused, &unused, &ecx, &unused);
+ return ecx & CPUID_EXT_VMX;
}
-#endif
+#define VMX_INVALID_GUEST_STATE 0x80000021
-int kvm_arch_on_sigbus_vcpu(CPUState *env, int code, void *addr)
+int kvm_arch_handle_exit(CPUState *env, struct kvm_run *run)
{
-#if defined(KVM_CAP_MCE)
- void *vaddr;
- ram_addr_t ram_addr;
- target_phys_addr_t paddr;
-
- if ((env->mcg_cap & MCG_SER_P) && addr
- && (code == BUS_MCEERR_AR
- || code == BUS_MCEERR_AO)) {
- vaddr = (void *)addr;
- if (qemu_ram_addr_from_host(vaddr, &ram_addr) ||
- !kvm_physical_memory_addr_from_ram(env->kvm_state, ram_addr, &paddr)) {
- fprintf(stderr, "Hardware memory error for memory used by "
- "QEMU itself instead of guest system!\n");
- /* Hope we are lucky for AO MCE */
- if (code == BUS_MCEERR_AO) {
- return 0;
- } else {
- hardware_memory_error();
- }
- }
+ uint64_t code;
+ int ret;
- 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);
- }
- }
- } else
-#endif
- {
- if (code == BUS_MCEERR_AO) {
- return 0;
- } else if (code == BUS_MCEERR_AR) {
- hardware_memory_error();
- } else {
- return 1;
+ switch (run->exit_reason) {
+ case KVM_EXIT_HLT:
+ DPRINTF("handle_hlt\n");
+ ret = kvm_handle_halt(env);
+ break;
+ case KVM_EXIT_SET_TPR:
+ ret = 0;
+ 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;
+#ifdef KVM_CAP_SET_GUEST_DEBUG
+ case KVM_EXIT_DEBUG:
+ DPRINTF("kvm_exit_debug\n");
+ ret = kvm_handle_debug(&run->debug.arch);
+ break;
+#endif /* KVM_CAP_SET_GUEST_DEBUG */
+ default:
+ fprintf(stderr, "KVM: unknown exit reason %d\n", run->exit_reason);
+ ret = -1;
+ break;
}
- return 0;
+
+ return ret;
}
-int kvm_arch_on_sigbus(int code, void *addr)
+bool kvm_arch_stop_on_emulation_error(CPUState *env)
{
-#if defined(KVM_CAP_MCE)
- if ((first_cpu->mcg_cap & MCG_SER_P) && addr && code == BUS_MCEERR_AO) {
- void *vaddr;
- ram_addr_t ram_addr;
- target_phys_addr_t paddr;
-
- /* Hope we are lucky for AO MCE */
- vaddr = addr;
- if (qemu_ram_addr_from_host(vaddr, &ram_addr) ||
- !kvm_physical_memory_addr_from_ram(first_cpu->kvm_state, ram_addr, &paddr)) {
- fprintf(stderr, "Hardware memory error for memory used by "
- "QEMU itself instead of guest system!: %p\n", addr);
- return 0;
- }
- kvm_mce_inj_srao_memscrub2(first_cpu, paddr);
- } else
-#endif
- {
- if (code == BUS_MCEERR_AO) {
- return 0;
- } else if (code == BUS_MCEERR_AR) {
- hardware_memory_error();
- } else {
- return 1;
- }
- }
- return 0;
+ return !(env->cr[0] & CR0_PE_MASK) ||
+ ((env->segs[R_CS].selector & 3) != 3);
}
diff --git a/target-i386/kvm_x86.h b/target-i386/kvm_x86.h
deleted file mode 100644
index 9d7b584267..0000000000
--- a/target-i386/kvm_x86.h
+++ /dev/null
@@ -1,25 +0,0 @@
-/*
- * QEMU KVM support
- *
- * Copyright (C) 2009 Red Hat Inc.
- * Copyright IBM, Corp. 2008
- *
- * Authors:
- * Anthony Liguori <aliguori@us.ibm.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2 or later.
- * See the COPYING file in the top-level directory.
- *
- */
-
-#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 flag);
-
-#endif
diff --git a/target-i386/machine.c b/target-i386/machine.c
index d78eceb779..6384f54b95 100644
--- a/target-i386/machine.c
+++ b/target-i386/machine.c
@@ -491,6 +491,8 @@ static const VMStateDescription vmstate_cpu = {
VMSTATE_UINT64_V(xcr0, CPUState, 12),
VMSTATE_UINT64_V(xstate_bv, CPUState, 12),
VMSTATE_YMMH_REGS_VARS(ymmh_regs, CPUState, CPU_NB_REGS, 12),
+
+ VMSTATE_UINT64_V(pat, CPUState, 13),
VMSTATE_END_OF_LIST()
/* The above list is not sorted /wrt version numbers, watch out! */
},
diff --git a/target-ppc/kvm.c b/target-ppc/kvm.c
index 31345907d5..0e2e67b34d 100644
--- a/target-ppc/kvm.c
+++ b/target-ppc/kvm.c
@@ -222,7 +222,7 @@ int kvmppc_set_interrupt(CPUState *env, int irq, int level)
#define PPC_INPUT_INT PPC6xx_INPUT_INT
#endif
-int kvm_arch_pre_run(CPUState *env, struct kvm_run *run)
+void kvm_arch_pre_run(CPUState *env, struct kvm_run *run)
{
int r;
unsigned irq;
@@ -253,15 +253,15 @@ int kvm_arch_pre_run(CPUState *env, struct kvm_run *run)
/* We don't know if there are more interrupts pending after this. However,
* the guest will return to userspace in the course of handling this one
* anyways, so we will get a chance to deliver the rest. */
- return 0;
}
void kvm_arch_post_run(CPUState *env, struct kvm_run *run)
{
}
-void kvm_arch_process_irqchip_events(CPUState *env)
+int kvm_arch_process_async_events(CPUState *env)
{
+ return 0;
}
static int kvmppc_handle_halt(CPUState *env)
@@ -271,7 +271,7 @@ static int kvmppc_handle_halt(CPUState *env)
env->exception_index = EXCP_HLT;
}
- return 1;
+ return 0;
}
/* map dcr access to existing qemu dcr emulation */
@@ -280,7 +280,7 @@ static int kvmppc_handle_dcr_read(CPUState *env, uint32_t dcrn, uint32_t *data)
if (ppc_dcr_read(env->dcr_env, dcrn, data) < 0)
fprintf(stderr, "Read to unhandled DCR (0x%x)\n", dcrn);
- return 1;
+ return 0;
}
static int kvmppc_handle_dcr_write(CPUState *env, uint32_t dcrn, uint32_t data)
@@ -288,12 +288,12 @@ static int kvmppc_handle_dcr_write(CPUState *env, uint32_t dcrn, uint32_t data)
if (ppc_dcr_write(env->dcr_env, dcrn, data) < 0)
fprintf(stderr, "Write to unhandled DCR (0x%x)\n", dcrn);
- return 1;
+ return 0;
}
int kvm_arch_handle_exit(CPUState *env, struct kvm_run *run)
{
- int ret = 0;
+ int ret;
switch (run->exit_reason) {
case KVM_EXIT_DCR:
diff --git a/target-s390x/kvm.c b/target-s390x/kvm.c
index 6e9427431d..91232038ea 100644
--- a/target-s390x/kvm.c
+++ b/target-s390x/kvm.c
@@ -177,7 +177,7 @@ void kvm_arch_post_run(CPUState *env, struct kvm_run *run)
{
}
-int kvm_arch_process_irqchip_events(CPUState *env)
+int kvm_arch_process_async_events(CPUState *env)
{
return 0;
}
@@ -497,6 +497,11 @@ int kvm_arch_handle_exit(CPUState *env, struct kvm_run *run)
break;
}
+ if (ret == 0) {
+ ret = EXCP_INTERRUPT;
+ } else if (ret > 0) {
+ ret = 0;
+ }
return ret;
}
diff --git a/vl.c b/vl.c
index 48150cf0ce..ac4721110c 100644
--- a/vl.c
+++ b/vl.c
@@ -1450,6 +1450,7 @@ static void main_loop(void)
}
if (qemu_reset_requested()) {
pause_all_vcpus();
+ cpu_synchronize_all_states();
qemu_system_reset();
resume_all_vcpus();
}