#include "hw/isa.h"
#include "hw/baum.h"
#include "hw/bt.h"
+#include "hw/smbios.h"
+#include "hw/xen.h"
#include "bt-host.h"
#include "net.h"
#include "monitor.h"
int cirrus_vga_enabled = 1;
int std_vga_enabled = 0;
int vmsvga_enabled = 0;
+int xenfb_enabled = 0;
#ifdef TARGET_SPARC
int graphic_width = 1024;
int graphic_height = 768;
int rtc_td_hack = 0;
#endif
int usb_enabled = 0;
+int singlestep = 0;
int smp_cpus = 1;
const char *vnc_display;
int acpi_enabled = 1;
int nb_drives_opt;
struct drive_opt drives_opt[MAX_DRIVES];
+int nb_numa_nodes;
+uint64_t node_mem[MAX_NODES];
+uint64_t node_cpumask[MAX_NODES];
+
static CPUState *cur_cpu;
static CPUState *next_cpu;
-static int event_pending = 1;
+static int timer_alarm_pending = 1;
/* Conversion factor from emulated instructions to virtual clock ticks. */
static int icount_time_shift;
/* Arbitrarily pick 1MIPS as the minimum allowable speed. */
{
LOG_IOPORT("outb: %04x %02x\n", addr, val);
ioport_write(0, addr, val);
-#ifdef USE_KQEMU
+#ifdef CONFIG_KQEMU
if (env)
env->last_io_time = cpu_get_time_fast();
#endif
{
LOG_IOPORT("outw: %04x %04x\n", addr, val);
ioport_write(1, addr, val);
-#ifdef USE_KQEMU
+#ifdef CONFIG_KQEMU
if (env)
env->last_io_time = cpu_get_time_fast();
#endif
{
LOG_IOPORT("outl: %04x %08x\n", addr, val);
ioport_write(2, addr, val);
-#ifdef USE_KQEMU
+#ifdef CONFIG_KQEMU
if (env)
env->last_io_time = cpu_get_time_fast();
#endif
int val;
val = ioport_read(0, addr);
LOG_IOPORT("inb : %04x %02x\n", addr, val);
-#ifdef USE_KQEMU
+#ifdef CONFIG_KQEMU
if (env)
env->last_io_time = cpu_get_time_fast();
#endif
int val;
val = ioport_read(1, addr);
LOG_IOPORT("inw : %04x %04x\n", addr, val);
-#ifdef USE_KQEMU
+#ifdef CONFIG_KQEMU
if (env)
env->last_io_time = cpu_get_time_fast();
#endif
int val;
val = ioport_read(2, addr);
LOG_IOPORT("inl : %04x %08x\n", addr, val);
-#ifdef USE_KQEMU
+#ifdef CONFIG_KQEMU
if (env)
env->last_io_time = cpu_get_time_fast();
#endif
#define MIN_TIMER_REARM_US 250
static struct qemu_alarm_timer *alarm_timer;
-#ifndef _WIN32
-static int alarm_timer_rfd, alarm_timer_wfd;
-#endif
#ifdef _WIN32
struct qemu_alarm_win32 {
MMRESULT timerId;
- HANDLE host_alarm;
unsigned int period;
} alarm_win32_data = {0, NULL, -1};
qemu_rearm_alarm_timer(alarm_timer);
}
/* Interrupt execution to force deadline recalculation. */
- if (use_icount && cpu_single_env) {
- cpu_exit(cpu_single_env);
- }
+ if (use_icount)
+ qemu_notify_event();
}
}
return 0;
}
+static void qemu_event_increment(void);
+
#ifdef _WIN32
static void CALLBACK host_alarm_handler(UINT uTimerID, UINT uMsg,
DWORD_PTR dwUser, DWORD_PTR dw1,
qemu_get_clock(rt_clock))) {
CPUState *env = next_cpu;
-#ifdef _WIN32
- struct qemu_alarm_win32 *data = ((struct qemu_alarm_timer*)dwUser)->priv;
- SetEvent(data->host_alarm);
-#else
- static const char byte = 0;
- write(alarm_timer_wfd, &byte, sizeof(byte));
-#endif
+ qemu_event_increment();
alarm_timer->flags |= ALARM_FLAG_EXPIRED;
if (env) {
/* stop the currently executing cpu because a timer occured */
cpu_exit(env);
-#ifdef USE_KQEMU
+#ifdef CONFIG_KQEMU
if (env->kqemu_enabled) {
kqemu_cpu_interrupt(env);
}
#endif
}
- event_pending = 1;
+ timer_alarm_pending = 1;
+ qemu_notify_event();
}
}
#endif /* !defined(_WIN32) */
-static void try_to_rearm_timer(void *opaque)
-{
- struct qemu_alarm_timer *t = opaque;
-#ifndef _WIN32
- ssize_t len;
-
- /* Drain the notify pipe */
- do {
- char buffer[512];
- len = read(alarm_timer_rfd, buffer, sizeof(buffer));
- } while ((len == -1 && errno == EINTR) || len > 0);
-#endif
-
- if (t->flags & ALARM_FLAG_EXPIRED) {
- alarm_timer->flags &= ~ALARM_FLAG_EXPIRED;
- qemu_rearm_alarm_timer(alarm_timer);
- }
-}
#ifdef _WIN32
struct qemu_alarm_win32 *data = t->priv;
UINT flags;
- data->host_alarm = CreateEvent(NULL, FALSE, FALSE, NULL);
- if (!data->host_alarm) {
- perror("Failed CreateEvent");
- return -1;
- }
-
memset(&tc, 0, sizeof(tc));
timeGetDevCaps(&tc, sizeof(tc));
if (!data->timerId) {
perror("Failed to initialize win32 alarm timer");
-
timeEndPeriod(data->period);
- CloseHandle(data->host_alarm);
return -1;
}
- qemu_add_wait_object(data->host_alarm, try_to_rearm_timer, t);
-
return 0;
}
timeKillEvent(data->timerId);
timeEndPeriod(data->period);
-
- CloseHandle(data->host_alarm);
}
static void win32_rearm_timer(struct qemu_alarm_timer *t)
perror("Failed to re-arm win32 alarm timer");
timeEndPeriod(data->period);
- CloseHandle(data->host_alarm);
exit(1);
}
}
struct qemu_alarm_timer *t = NULL;
int i, err = -1;
-#ifndef _WIN32
- int fds[2];
-
- err = pipe(fds);
- if (err == -1)
- return -errno;
-
- err = fcntl_setfl(fds[0], O_NONBLOCK);
- if (err < 0)
- goto fail;
-
- err = fcntl_setfl(fds[1], O_NONBLOCK);
- if (err < 0)
- goto fail;
-
- alarm_timer_rfd = fds[0];
- alarm_timer_wfd = fds[1];
-#endif
-
for (i = 0; alarm_timers[i].name; i++) {
t = &alarm_timers[i];
goto fail;
}
-#ifndef _WIN32
- qemu_set_fd_handler2(alarm_timer_rfd, NULL,
- try_to_rearm_timer, NULL, t);
-#endif
-
alarm_timer = t;
return 0;
fail:
-#ifndef _WIN32
- close(fds[0]);
- close(fds[1]);
-#endif
return err;
}
}
#endif
-const char *get_opt_name(char *buf, int buf_size, const char *p)
+const char *get_opt_name(char *buf, int buf_size, const char *p, char delim)
{
char *q;
q = buf;
- while (*p != '\0' && *p != '=') {
+ while (*p != '\0' && *p != delim) {
if (q && (q - buf) < buf_size - 1)
*q++ = *p;
p++;
p = str;
for(;;) {
- p = get_opt_name(option, sizeof(option), p);
+ p = get_opt_name(option, sizeof(option), p, '=');
if (*p != '=')
break;
p++;
int i;
p = str;
- for(;;) {
- p = get_opt_name(buf, buf_size, p);
+ while (*p != '\0') {
+ p = get_opt_name(buf, buf_size, p, '=');
if (*p != '=')
return -1;
p++;
} else if (!strcmp(buf, "virtio")) {
type = IF_VIRTIO;
max_devs = 0;
- } else {
+ } else if (!strcmp(buf, "xen")) {
+ type = IF_XEN;
+ max_devs = 0;
+ } else {
fprintf(stderr, "qemu: '%s' unsupported bus type '%s'\n", str, buf);
return -1;
}
switch(type) {
case IF_IDE:
case IF_SCSI:
+ case IF_XEN:
switch(media) {
case MEDIA_DISK:
if (cyls != 0) {
return drives_table_idx;
}
+static void numa_add(const char *optarg)
+{
+ char option[128];
+ char *endptr;
+ unsigned long long value, endvalue;
+ int nodenr;
+
+ optarg = get_opt_name(option, 128, optarg, ',') + 1;
+ if (!strcmp(option, "node")) {
+ if (get_param_value(option, 128, "nodeid", optarg) == 0) {
+ nodenr = nb_numa_nodes;
+ } else {
+ nodenr = strtoull(option, NULL, 10);
+ }
+
+ if (get_param_value(option, 128, "mem", optarg) == 0) {
+ node_mem[nodenr] = 0;
+ } else {
+ value = strtoull(option, &endptr, 0);
+ switch (*endptr) {
+ case 0: case 'M': case 'm':
+ value <<= 20;
+ break;
+ case 'G': case 'g':
+ value <<= 30;
+ break;
+ }
+ node_mem[nodenr] = value;
+ }
+ if (get_param_value(option, 128, "cpus", optarg) == 0) {
+ node_cpumask[nodenr] = 0;
+ } else {
+ value = strtoull(option, &endptr, 10);
+ if (value >= 64) {
+ value = 63;
+ fprintf(stderr, "only 64 CPUs in NUMA mode supported.\n");
+ } else {
+ if (*endptr == '-') {
+ endvalue = strtoull(endptr+1, &endptr, 10);
+ if (endvalue >= 63) {
+ endvalue = 62;
+ fprintf(stderr,
+ "only 63 CPUs in NUMA mode supported.\n");
+ }
+ value = (1 << (endvalue + 1)) - (1 << value);
+ } else {
+ value = 1 << value;
+ }
+ }
+ node_cpumask[nodenr] = value;
+ }
+ nb_numa_nodes++;
+ }
+ return;
+}
+
/***********************************************************/
/* USB devices */
int ret;
ram_addr_t i;
- if (qemu_get_be32(f) != phys_ram_size)
+ if (qemu_get_be32(f) != last_ram_offset)
return -EINVAL;
- for(i = 0; i < phys_ram_size; i+= TARGET_PAGE_SIZE) {
- ret = ram_get_page(f, phys_ram_base + i, TARGET_PAGE_SIZE);
+ for(i = 0; i < last_ram_offset; i+= TARGET_PAGE_SIZE) {
+ ret = ram_get_page(f, qemu_get_ram_ptr(i), TARGET_PAGE_SIZE);
if (ret)
return ret;
}
ram_addr_t addr = 0;
int found = 0;
- while (addr < phys_ram_size) {
+ while (addr < last_ram_offset) {
if (cpu_physical_memory_get_dirty(current_addr, MIGRATION_DIRTY_FLAG)) {
- uint8_t ch;
+ uint8_t *p;
cpu_physical_memory_reset_dirty(current_addr,
current_addr + TARGET_PAGE_SIZE,
MIGRATION_DIRTY_FLAG);
- ch = *(phys_ram_base + current_addr);
+ p = qemu_get_ram_ptr(current_addr);
- if (is_dup_page(phys_ram_base + current_addr, ch)) {
+ if (is_dup_page(p, *p)) {
qemu_put_be64(f, current_addr | RAM_SAVE_FLAG_COMPRESS);
- qemu_put_byte(f, ch);
+ qemu_put_byte(f, *p);
} else {
qemu_put_be64(f, current_addr | RAM_SAVE_FLAG_PAGE);
- qemu_put_buffer(f, phys_ram_base + current_addr, TARGET_PAGE_SIZE);
+ qemu_put_buffer(f, p, TARGET_PAGE_SIZE);
}
found = 1;
break;
}
addr += TARGET_PAGE_SIZE;
- current_addr = (saved_addr + addr) % phys_ram_size;
+ current_addr = (saved_addr + addr) % last_ram_offset;
}
return found;
ram_addr_t addr;
ram_addr_t count = 0;
- for (addr = 0; addr < phys_ram_size; addr += TARGET_PAGE_SIZE) {
+ for (addr = 0; addr < last_ram_offset; addr += TARGET_PAGE_SIZE) {
if (cpu_physical_memory_get_dirty(addr, MIGRATION_DIRTY_FLAG))
count++;
}
if (stage == 1) {
/* Make sure all dirty bits are set */
- for (addr = 0; addr < phys_ram_size; addr += TARGET_PAGE_SIZE) {
+ for (addr = 0; addr < last_ram_offset; addr += TARGET_PAGE_SIZE) {
if (!cpu_physical_memory_get_dirty(addr, MIGRATION_DIRTY_FLAG))
cpu_physical_memory_set_dirty(addr);
}
/* Enable dirty memory tracking */
cpu_physical_memory_set_dirty_tracking(1);
- qemu_put_be64(f, phys_ram_size | RAM_SAVE_FLAG_MEM_SIZE);
+ qemu_put_be64(f, last_ram_offset | RAM_SAVE_FLAG_MEM_SIZE);
}
while (!qemu_file_rate_limit(f)) {
/* try transferring iterative blocks of memory */
if (stage == 3) {
- cpu_physical_memory_set_dirty_tracking(0);
/* flush all remaining blocks regardless of rate limiting */
while (ram_save_block(f) != 0);
+ cpu_physical_memory_set_dirty_tracking(0);
}
qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
if (ram_decompress_open(s, f) < 0)
return -EINVAL;
- for(i = 0; i < phys_ram_size; i+= BDRV_HASH_BLOCK_SIZE) {
+ for(i = 0; i < last_ram_offset; i+= BDRV_HASH_BLOCK_SIZE) {
if (ram_decompress_buf(s, buf, 1) < 0) {
fprintf(stderr, "Error while reading ram block header\n");
goto error;
}
if (buf[0] == 0) {
- if (ram_decompress_buf(s, phys_ram_base + i, BDRV_HASH_BLOCK_SIZE) < 0) {
+ if (ram_decompress_buf(s, qemu_get_ram_ptr(i),
+ BDRV_HASH_BLOCK_SIZE) < 0) {
fprintf(stderr, "Error while reading ram block address=0x%08" PRIx64, (uint64_t)i);
goto error;
}
return ram_load_v1(f, opaque);
if (version_id == 2) {
- if (qemu_get_be32(f) != phys_ram_size)
+ if (qemu_get_be32(f) != last_ram_offset)
return -EINVAL;
return ram_load_dead(f, opaque);
}
addr &= TARGET_PAGE_MASK;
if (flags & RAM_SAVE_FLAG_MEM_SIZE) {
- if (addr != phys_ram_size)
+ if (addr != last_ram_offset)
return -EINVAL;
}
if (flags & RAM_SAVE_FLAG_COMPRESS) {
uint8_t ch = qemu_get_byte(f);
- memset(phys_ram_base + addr, ch, TARGET_PAGE_SIZE);
+ memset(qemu_get_ram_ptr(addr), ch, TARGET_PAGE_SIZE);
} else if (flags & RAM_SAVE_FLAG_PAGE)
- qemu_get_buffer(f, phys_ram_base + addr, TARGET_PAGE_SIZE);
+ qemu_get_buffer(f, qemu_get_ram_ptr(addr), TARGET_PAGE_SIZE);
} while (!(flags & RAM_SAVE_FLAG_EOS));
return 0;
void qemu_service_io(void)
{
- CPUState *env = cpu_single_env;
- if (env) {
- cpu_exit(env);
-#ifdef USE_KQEMU
- if (env->kqemu_enabled) {
- kqemu_cpu_interrupt(env);
- }
-#endif
- }
+ qemu_notify_event();
}
/***********************************************************/
void qemu_bh_schedule(QEMUBH *bh)
{
- CPUState *env = cpu_single_env;
if (bh->scheduled)
return;
bh->scheduled = 1;
bh->idle = 0;
/* stop the currently executing CPU to execute the BH ASAP */
- if (env) {
- cpu_exit(env);
- }
+ qemu_notify_event();
}
void qemu_bh_cancel(QEMUBH *bh)
static int reset_requested;
static int shutdown_requested;
static int powerdown_requested;
+static int debug_requested;
int qemu_shutdown_requested(void)
{
return r;
}
+static int qemu_debug_requested(void)
+{
+ int r = debug_requested;
+ debug_requested = 0;
+ return r;
+}
+
void qemu_register_reset(QEMUResetHandler *func, void *opaque)
{
QEMUResetEntry **pre, *re;
for(re = first_reset_entry; re != NULL; re = re->next) {
re->func(re->opaque);
}
+ if (kvm_enabled())
+ kvm_sync_vcpus();
}
void qemu_system_reset_request(void)
} else {
reset_requested = 1;
}
- if (cpu_single_env)
- cpu_exit(cpu_single_env);
+ qemu_notify_event();
}
void qemu_system_shutdown_request(void)
{
shutdown_requested = 1;
- if (cpu_single_env)
- cpu_exit(cpu_single_env);
+ qemu_notify_event();
}
void qemu_system_powerdown_request(void)
{
powerdown_requested = 1;
- if (cpu_single_env)
- cpu_exit(cpu_single_env);
+ qemu_notify_event();
+}
+
+void qemu_notify_event(void)
+{
+ CPUState *env = cpu_single_env;
+
+ if (env) {
+ cpu_exit(env);
+#ifdef USE_KQEMU
+ if (env->kqemu_enabled)
+ kqemu_cpu_interrupt(env);
+#endif
+ }
+}
+
+#ifndef _WIN32
+static int io_thread_fd = -1;
+
+static void qemu_event_increment(void)
+{
+ static const char byte = 0;
+
+ if (io_thread_fd == -1)
+ return;
+
+ write(io_thread_fd, &byte, sizeof(byte));
+}
+
+static void qemu_event_read(void *opaque)
+{
+ int fd = (unsigned long)opaque;
+ ssize_t len;
+
+ /* Drain the notify pipe */
+ do {
+ char buffer[512];
+ len = read(fd, buffer, sizeof(buffer));
+ } while ((len == -1 && errno == EINTR) || len > 0);
+}
+
+static int qemu_event_init(void)
+{
+ int err;
+ int fds[2];
+
+ err = pipe(fds);
+ if (err == -1)
+ return -errno;
+
+ err = fcntl_setfl(fds[0], O_NONBLOCK);
+ if (err < 0)
+ goto fail;
+
+ err = fcntl_setfl(fds[1], O_NONBLOCK);
+ if (err < 0)
+ goto fail;
+
+ qemu_set_fd_handler2(fds[0], NULL, qemu_event_read, NULL,
+ (void *)(unsigned long)fds[0]);
+
+ io_thread_fd = fds[1];
+fail:
+ close(fds[0]);
+ close(fds[1]);
+ return err;
}
+#else
+HANDLE qemu_event_handle;
+
+static void dummy_event_handler(void *opaque)
+{
+}
+
+static int qemu_event_init(void)
+{
+ qemu_event_handle = CreateEvent(NULL, FALSE, FALSE, NULL);
+ if (!qemu_event_handle) {
+ perror("Failed CreateEvent");
+ return -1;
+ }
+ qemu_add_wait_object(qemu_event_handle, dummy_event_handler, NULL);
+ return 0;
+}
+
+static void qemu_event_increment(void)
+{
+ SetEvent(qemu_event_handle);
+}
+#endif
+
+static int qemu_init_main_loop(void)
+{
+ return qemu_event_init();
+}
+
+void qemu_init_vcpu(void *_env)
+{
+ CPUState *env = _env;
+
+ if (kvm_enabled())
+ kvm_init_vcpu(env);
+ return;
+}
+
+int qemu_cpu_self(void *env)
+{
+ return 1;
+}
+
+void qemu_cpu_kick(void *env)
+{
+ return;
+}
+
+#define qemu_mutex_lock_iothread() do { } while (0)
+#define qemu_mutex_unlock_iothread() do { } while (0)
#ifdef _WIN32
static void host_main_loop_wait(int *timeout)
slirp_select_fill(&nfds, &rfds, &wfds, &xfds);
}
#endif
+ qemu_mutex_unlock_iothread();
ret = select(nfds + 1, &rfds, &wfds, &xfds, &tv);
+ qemu_mutex_lock_iothread();
if (ret > 0) {
IOHandlerRecord **pioh;
}
#endif
+ /* rearm timer, if not periodic */
+ if (alarm_timer->flags & ALARM_FLAG_EXPIRED) {
+ alarm_timer->flags &= ~ALARM_FLAG_EXPIRED;
+ qemu_rearm_alarm_timer(alarm_timer);
+ }
+
/* vm time timers */
if (vm_running && likely(!(cur_cpu->singlestep_enabled & SSTEP_NOTIMER)))
qemu_run_timers(&active_timers[QEMU_TIMER_VIRTUAL],
}
-static int main_loop(void)
+static int qemu_cpu_exec(CPUState *env)
{
- int ret, timeout;
+ int ret;
#ifdef CONFIG_PROFILER
int64_t ti;
#endif
- CPUState *env;
-
- cur_cpu = first_cpu;
- next_cpu = cur_cpu->next_cpu ?: first_cpu;
- for(;;) {
- if (vm_running) {
- for(;;) {
- /* get next cpu */
- env = next_cpu;
#ifdef CONFIG_PROFILER
- ti = profile_getclock();
+ ti = profile_getclock();
#endif
- if (use_icount) {
- int64_t count;
- int decr;
- qemu_icount -= (env->icount_decr.u16.low + env->icount_extra);
- env->icount_decr.u16.low = 0;
- env->icount_extra = 0;
- count = qemu_next_deadline();
- count = (count + (1 << icount_time_shift) - 1)
- >> icount_time_shift;
- qemu_icount += count;
- decr = (count > 0xffff) ? 0xffff : count;
- count -= decr;
- env->icount_decr.u16.low = decr;
- env->icount_extra = count;
- }
- ret = cpu_exec(env);
+ if (use_icount) {
+ int64_t count;
+ int decr;
+ qemu_icount -= (env->icount_decr.u16.low + env->icount_extra);
+ env->icount_decr.u16.low = 0;
+ env->icount_extra = 0;
+ count = qemu_next_deadline();
+ count = (count + (1 << icount_time_shift) - 1)
+ >> icount_time_shift;
+ qemu_icount += count;
+ decr = (count > 0xffff) ? 0xffff : count;
+ count -= decr;
+ env->icount_decr.u16.low = decr;
+ env->icount_extra = count;
+ }
+ ret = cpu_exec(env);
#ifdef CONFIG_PROFILER
- qemu_time += profile_getclock() - ti;
+ qemu_time += profile_getclock() - ti;
#endif
- if (use_icount) {
- /* Fold pending instructions back into the
- instruction counter, and clear the interrupt flag. */
- qemu_icount -= (env->icount_decr.u16.low
- + env->icount_extra);
- env->icount_decr.u32 = 0;
- env->icount_extra = 0;
- }
- next_cpu = env->next_cpu ?: first_cpu;
- if (event_pending && likely(ret != EXCP_DEBUG)) {
- ret = EXCP_INTERRUPT;
- event_pending = 0;
- break;
- }
- if (ret == EXCP_HLT) {
- /* Give the next CPU a chance to run. */
- cur_cpu = env;
- continue;
- }
- if (ret != EXCP_HALTED)
- break;
- /* all CPUs are halted ? */
- if (env == cur_cpu)
- break;
- }
- cur_cpu = env;
+ if (use_icount) {
+ /* Fold pending instructions back into the
+ instruction counter, and clear the interrupt flag. */
+ qemu_icount -= (env->icount_decr.u16.low
+ + env->icount_extra);
+ env->icount_decr.u32 = 0;
+ env->icount_extra = 0;
+ }
+ return ret;
+}
- if (shutdown_requested) {
- ret = EXCP_INTERRUPT;
- if (no_shutdown) {
- vm_stop(0);
- no_shutdown = 0;
- }
- else
- break;
- }
- if (reset_requested) {
- reset_requested = 0;
- qemu_system_reset();
- ret = EXCP_INTERRUPT;
- }
- if (powerdown_requested) {
- powerdown_requested = 0;
- qemu_system_powerdown();
- ret = EXCP_INTERRUPT;
- }
- if (unlikely(ret == EXCP_DEBUG)) {
- gdb_set_stop_cpu(cur_cpu);
- vm_stop(EXCP_DEBUG);
- }
- /* If all cpus are halted then wait until the next IRQ */
- /* XXX: use timeout computed from timers */
- if (ret == EXCP_HALTED) {
- if (use_icount) {
- int64_t add;
- int64_t delta;
- /* Advance virtual time to the next event. */
- if (use_icount == 1) {
- /* When not using an adaptive execution frequency
- we tend to get badly out of sync with real time,
- so just delay for a reasonable amount of time. */
- delta = 0;
- } else {
- delta = cpu_get_icount() - cpu_get_clock();
- }
- if (delta > 0) {
- /* If virtual time is ahead of real time then just
- wait for IO. */
- timeout = (delta / 1000000) + 1;
- } else {
- /* Wait for either IO to occur or the next
- timer event. */
- add = qemu_next_deadline();
- /* We advance the timer before checking for IO.
- Limit the amount we advance so that early IO
- activity won't get the guest too far ahead. */
- if (add > 10000000)
- add = 10000000;
- delta += add;
- add = (add + (1 << icount_time_shift) - 1)
- >> icount_time_shift;
- qemu_icount += add;
- timeout = delta / 1000000;
- if (timeout < 0)
- timeout = 0;
- }
- } else {
- timeout = 5000;
- }
- } else {
- timeout = 0;
- }
+static void tcg_cpu_exec(void)
+{
+ int ret;
+
+ if (next_cpu == NULL)
+ next_cpu = first_cpu;
+ for (; next_cpu != NULL; next_cpu = next_cpu->next_cpu) {
+ CPUState *env = cur_cpu = next_cpu;
+
+ if (!vm_running)
+ break;
+ if (timer_alarm_pending) {
+ timer_alarm_pending = 0;
+ break;
+ }
+ ret = qemu_cpu_exec(env);
+ if (ret == EXCP_DEBUG) {
+ gdb_set_stop_cpu(env);
+ debug_requested = 1;
+ break;
+ }
+ }
+}
+
+static int cpu_has_work(CPUState *env)
+{
+ if (!env->halted)
+ return 1;
+ if (qemu_cpu_has_work(env))
+ return 1;
+ return 0;
+}
+
+static int tcg_has_work(void)
+{
+ CPUState *env;
+
+ for (env = first_cpu; env != NULL; env = env->next_cpu)
+ if (cpu_has_work(env))
+ return 1;
+ return 0;
+}
+
+static int qemu_calculate_timeout(void)
+{
+ int timeout;
+
+ if (!vm_running)
+ timeout = 5000;
+ else if (tcg_has_work())
+ timeout = 0;
+ else if (!use_icount)
+ timeout = 5000;
+ else {
+ /* XXX: use timeout computed from timers */
+ int64_t add;
+ int64_t delta;
+ /* Advance virtual time to the next event. */
+ if (use_icount == 1) {
+ /* When not using an adaptive execution frequency
+ we tend to get badly out of sync with real time,
+ so just delay for a reasonable amount of time. */
+ delta = 0;
} else {
- if (shutdown_requested) {
- ret = EXCP_INTERRUPT;
- break;
- }
- timeout = 5000;
+ delta = cpu_get_icount() - cpu_get_clock();
+ }
+ if (delta > 0) {
+ /* If virtual time is ahead of real time then just
+ wait for IO. */
+ timeout = (delta / 1000000) + 1;
+ } else {
+ /* Wait for either IO to occur or the next
+ timer event. */
+ add = qemu_next_deadline();
+ /* We advance the timer before checking for IO.
+ Limit the amount we advance so that early IO
+ activity won't get the guest too far ahead. */
+ if (add > 10000000)
+ add = 10000000;
+ delta += add;
+ add = (add + (1 << icount_time_shift) - 1)
+ >> icount_time_shift;
+ qemu_icount += add;
+ timeout = delta / 1000000;
+ if (timeout < 0)
+ timeout = 0;
}
+ }
+
+ return timeout;
+}
+
+static int vm_can_run(void)
+{
+ if (powerdown_requested)
+ return 0;
+ if (reset_requested)
+ return 0;
+ if (shutdown_requested)
+ return 0;
+ if (debug_requested)
+ return 0;
+ return 1;
+}
+
+static void main_loop(void)
+{
+ for (;;) {
+
+ do {
+#ifdef CONFIG_PROFILER
+ int64_t ti;
+#endif
+ tcg_cpu_exec();
#ifdef CONFIG_PROFILER
- ti = profile_getclock();
+ ti = profile_getclock();
#endif
- main_loop_wait(timeout);
+ main_loop_wait(qemu_calculate_timeout());
#ifdef CONFIG_PROFILER
- dev_time += profile_getclock() - ti;
+ dev_time += profile_getclock() - ti;
#endif
+ } while (vm_can_run());
+
+ if (qemu_debug_requested())
+ vm_stop(EXCP_DEBUG);
+ if (qemu_shutdown_requested()) {
+ if (no_shutdown) {
+ vm_stop(0);
+ no_shutdown = 0;
+ } else
+ break;
+ }
+ if (qemu_reset_requested())
+ qemu_system_reset();
+ if (qemu_powerdown_requested())
+ qemu_system_powerdown();
}
- cpu_disable_ticks();
- return ret;
+}
+
+static void version(void)
+{
+ printf("QEMU PC emulator version " QEMU_VERSION QEMU_PKGVERSION ", Copyright (c) 2003-2008 Fabrice Bellard\n");
}
static void help(int exitcode)
{
- printf("QEMU PC emulator version " QEMU_VERSION ", Copyright (c) 2003-2008 Fabrice Bellard\n"
- "usage: %s [options] [disk_image]\n"
+ version();
+ printf("usage: %s [options] [disk_image]\n"
"\n"
"'disk_image' is a raw hard image image for IDE hard disk 0\n"
"\n"
{
const char *opts;
+ cirrus_vga_enabled = 0;
+ std_vga_enabled = 0;
+ vmsvga_enabled = 0;
+ xenfb_enabled = 0;
if (strstart(p, "std", &opts)) {
std_vga_enabled = 1;
- cirrus_vga_enabled = 0;
- vmsvga_enabled = 0;
} else if (strstart(p, "cirrus", &opts)) {
cirrus_vga_enabled = 1;
- std_vga_enabled = 0;
- vmsvga_enabled = 0;
} else if (strstart(p, "vmware", &opts)) {
- cirrus_vga_enabled = 0;
- std_vga_enabled = 0;
vmsvga_enabled = 1;
- } else if (strstart(p, "none", &opts)) {
- cirrus_vga_enabled = 0;
- std_vga_enabled = 0;
- vmsvga_enabled = 0;
- } else {
+ } else if (strstart(p, "xenfb", &opts)) {
+ xenfb_enabled = 1;
+ } else if (!strstart(p, "none", &opts)) {
invalid_vga:
fprintf(stderr, "Unknown vga type: %s\n", p);
exit(1);
}
#endif
-static int qemu_uuid_parse(const char *str, uint8_t *uuid)
+int qemu_uuid_parse(const char *str, uint8_t *uuid)
{
int ret;
if(ret != 16)
return -1;
+#ifdef TARGET_I386
+ smbios_add_field(1, offsetof(struct smbios_type_1, uuid), 16, uuid);
+#endif
+
return 0;
}
int main(int argc, char **argv, char **envp)
{
#ifdef CONFIG_GDBSTUB
- int use_gdbstub;
- const char *gdbstub_port;
+ const char *gdbstub_dev = NULL;
#endif
uint32_t boot_devices_bitmap = 0;
int i;
const char *chroot_dir = NULL;
const char *run_as = NULL;
#endif
+ CPUState *env;
qemu_cache_utils_init(envp);
initrd_filename = NULL;
ram_size = 0;
vga_ram_size = VGA_RAM_SIZE;
-#ifdef CONFIG_GDBSTUB
- use_gdbstub = 0;
- gdbstub_port = DEFAULT_GDBSTUB_PORT;
-#endif
snapshot = 0;
nographic = 0;
curses = 0;
virtio_consoles[i] = NULL;
virtio_console_index = 0;
+ for (i = 0; i < MAX_NODES; i++) {
+ node_mem[i] = 0;
+ node_cpumask[i] = 0;
+ }
+
usb_devices_index = 0;
nb_net_clients = 0;
nb_bt_opts = 0;
nb_drives = 0;
nb_drives_opt = 0;
+ nb_numa_nodes = 0;
hda_index = -1;
nb_nics = 0;
",trans=none" : "");
}
break;
+ case QEMU_OPTION_numa:
+ if (nb_numa_nodes >= MAX_NODES) {
+ fprintf(stderr, "qemu: too many NUMA nodes\n");
+ exit(1);
+ }
+ numa_add(optarg);
+ break;
case QEMU_OPTION_nographic:
nographic = 1;
break;
break;
#endif
case QEMU_OPTION_redir:
- net_slirp_redir(optarg);
+ net_slirp_redir(NULL, optarg);
break;
#endif
case QEMU_OPTION_bt:
case QEMU_OPTION_h:
help(0);
break;
+ case QEMU_OPTION_version:
+ version();
+ exit(0);
+ break;
case QEMU_OPTION_m: {
uint64_t value;
char *ptr;
/* On 32-bit hosts, QEMU is limited by virtual address space */
if (value > (2047 << 20)
-#ifndef USE_KQEMU
+#ifndef CONFIG_KQEMU
&& HOST_LONG_BITS == 32
#endif
) {
break;
#ifdef CONFIG_GDBSTUB
case QEMU_OPTION_s:
- use_gdbstub = 1;
+ gdbstub_dev = "tcp::" DEFAULT_GDBSTUB_PORT;
break;
- case QEMU_OPTION_p:
- gdbstub_port = optarg;
+ case QEMU_OPTION_gdb:
+ gdbstub_dev = optarg;
break;
#endif
case QEMU_OPTION_L:
case QEMU_OPTION_bios:
bios_name = optarg;
break;
+ case QEMU_OPTION_singlestep:
+ singlestep = 1;
+ break;
case QEMU_OPTION_S:
autostart = 0;
break;
exit(1);
}
break;
+ case QEMU_OPTION_smbios:
+ if(smbios_entry_add(optarg) < 0) {
+ fprintf(stderr, "Wrong smbios provided\n");
+ exit(1);
+ }
+ break;
#endif
-#ifdef USE_KQEMU
+#ifdef CONFIG_KQEMU
case QEMU_OPTION_no_kqemu:
kqemu_allowed = 0;
break;
#ifdef CONFIG_KVM
case QEMU_OPTION_enable_kvm:
kvm_allowed = 1;
-#ifdef USE_KQEMU
+#ifdef CONFIG_KQEMU
kqemu_allowed = 0;
#endif
break;
run_as = optarg;
break;
#endif
+#ifdef CONFIG_XEN
+ case QEMU_OPTION_xen_domid:
+ xen_domid = atoi(optarg);
+ break;
+ case QEMU_OPTION_xen_create:
+ xen_mode = XEN_CREATE;
+ break;
+ case QEMU_OPTION_xen_attach:
+ xen_mode = XEN_ATTACH;
+ break;
+#endif
}
}
}
-#if defined(CONFIG_KVM) && defined(USE_KQEMU)
+#if defined(CONFIG_KVM) && defined(CONFIG_KQEMU)
if (kvm_allowed && kqemu_allowed) {
fprintf(stderr,
"You can not enable both KVM and kqemu at the same time\n");
}
#endif
-#ifdef USE_KQEMU
+#ifdef CONFIG_KQEMU
if (smp_cpus > 1)
kqemu_allowed = 0;
#endif
+ if (qemu_init_main_loop()) {
+ fprintf(stderr, "qemu_init_main_loop failed\n");
+ exit(1);
+ }
linux_boot = (kernel_filename != NULL);
net_boot = (boot_devices_bitmap >> ('n' - 'a')) & 0xF;
exit(1);
/* init the memory */
- phys_ram_size = machine->ram_require & ~RAMSIZE_FIXED;
-
- if (machine->ram_require & RAMSIZE_FIXED) {
- if (ram_size > 0) {
- if (ram_size < phys_ram_size) {
- fprintf(stderr, "Machine `%s' requires %llu bytes of memory\n",
- machine->name, (unsigned long long) phys_ram_size);
- exit(-1);
- }
-
- phys_ram_size = ram_size;
- } else
- ram_size = phys_ram_size;
- } else {
- if (ram_size == 0)
- ram_size = DEFAULT_RAM_SIZE * 1024 * 1024;
-
- phys_ram_size += ram_size;
- }
-
- phys_ram_base = qemu_vmalloc(phys_ram_size);
- if (!phys_ram_base) {
- fprintf(stderr, "Could not allocate physical memory\n");
- exit(1);
+ if (ram_size == 0)
+ ram_size = DEFAULT_RAM_SIZE * 1024 * 1024;
+
+#ifdef CONFIG_KQEMU
+ /* FIXME: This is a nasty hack because kqemu can't cope with dynamic
+ guest ram allocation. It needs to go away. */
+ if (kqemu_allowed) {
+ kqemu_phys_ram_size = ram_size + VGA_RAM_SIZE + 4 * 1024 * 1024;
+ kqemu_phys_ram_base = qemu_vmalloc(kqemu_phys_ram_size);
+ if (!kqemu_phys_ram_base) {
+ fprintf(stderr, "Could not allocate physical memory\n");
+ exit(1);
+ }
}
+#endif
/* init the dynamic translator */
cpu_exec_init_all(tb_size * 1024 * 1024);
}
}
+ if (nb_numa_nodes > 0) {
+ int i;
+
+ if (nb_numa_nodes > smp_cpus) {
+ nb_numa_nodes = smp_cpus;
+ }
+
+ /* If no memory size if given for any node, assume the default case
+ * and distribute the available memory equally across all nodes
+ */
+ for (i = 0; i < nb_numa_nodes; i++) {
+ if (node_mem[i] != 0)
+ break;
+ }
+ if (i == nb_numa_nodes) {
+ uint64_t usedmem = 0;
+
+ /* On Linux, the each node's border has to be 8MB aligned,
+ * the final node gets the rest.
+ */
+ for (i = 0; i < nb_numa_nodes - 1; i++) {
+ node_mem[i] = (ram_size / nb_numa_nodes) & ~((1 << 23UL) - 1);
+ usedmem += node_mem[i];
+ }
+ node_mem[i] = ram_size - usedmem;
+ }
+
+ for (i = 0; i < nb_numa_nodes; i++) {
+ if (node_cpumask[i] != 0)
+ break;
+ }
+ /* assigning the VCPUs round-robin is easier to implement, guest OSes
+ * must cope with this anyway, because there are BIOSes out there in
+ * real machines which also use this scheme.
+ */
+ if (i == nb_numa_nodes) {
+ for (i = 0; i < smp_cpus; i++) {
+ node_cpumask[i % nb_numa_nodes] |= 1 << i;
+ }
+ }
+ }
+
if (kvm_enabled()) {
int ret;
machine->init(ram_size, vga_ram_size, boot_devices,
kernel_filename, kernel_cmdline, initrd_filename, cpu_model);
+
+ for (env = first_cpu; env != NULL; env = env->next_cpu) {
+ for (i = 0; i < nb_numa_nodes; i++) {
+ if (node_cpumask[i] & (1 << env->cpu_index)) {
+ env->numa_node = i;
+ }
+ }
+ }
+
current_machine = machine;
/* Set KVM's vcpu state to qemu's initial CPUState. */
}
#ifdef CONFIG_GDBSTUB
- if (use_gdbstub) {
- /* XXX: use standard host:port notation and modify options
- accordingly. */
- if (gdbserver_start(gdbstub_port) < 0) {
- fprintf(stderr, "qemu: could not open gdbstub device on port '%s'\n",
- gdbstub_port);
- exit(1);
- }
+ if (gdbstub_dev && gdbserver_start(gdbstub_dev) < 0) {
+ fprintf(stderr, "qemu: could not open gdbserver on device '%s'\n",
+ gdbstub_dev);
+ exit(1);
}
#endif