#include <sys/mman.h>
#endif
#include "config.h"
-#include "monitor.h"
-#include "sysemu.h"
-#include "arch_init.h"
+#include "monitor/monitor.h"
+#include "sysemu/sysemu.h"
+#include "qemu/bitops.h"
+#include "qemu/bitmap.h"
+#include "sysemu/arch_init.h"
#include "audio/audio.h"
-#include "hw/pc.h"
-#include "hw/pci.h"
-#include "hw/audiodev.h"
-#include "kvm.h"
-#include "migration.h"
-#include "net.h"
-#include "gdbstub.h"
-#include "hw/smbios.h"
-#include "exec-memory.h"
-#include "hw/pcspk.h"
-#include "qemu/page_cache.h"
+#include "hw/i386/pc.h"
+#include "hw/pci/pci.h"
+#include "hw/audio/audio.h"
+#include "sysemu/kvm.h"
+#include "migration/migration.h"
+#include "hw/i386/smbios.h"
+#include "exec/address-spaces.h"
+#include "hw/audio/pcspk.h"
+#include "migration/page_cache.h"
+#include "qemu/config-file.h"
+#include "qmp-commands.h"
+#include "trace.h"
+#include "exec/cpu-all.h"
+#include "hw/acpi/acpi.h"
#ifdef DEBUG_ARCH_INIT
#define DPRINTF(fmt, ...) \
#else
int graphic_width = 800;
int graphic_height = 600;
-int graphic_depth = 15;
+int graphic_depth = 32;
#endif
#define QEMU_ARCH QEMU_ARCH_MICROBLAZE
#elif defined(TARGET_MIPS)
#define QEMU_ARCH QEMU_ARCH_MIPS
+#elif defined(TARGET_MOXIE)
+#define QEMU_ARCH QEMU_ARCH_MOXIE
#elif defined(TARGET_OPENRISC)
#define QEMU_ARCH QEMU_ARCH_OPENRISC
#elif defined(TARGET_PPC)
#endif
const uint32_t arch_type = QEMU_ARCH;
+static bool mig_throttle_on;
+static int dirty_rate_high_cnt;
+static void check_guest_throttling(void);
/***********************************************************/
/* ram save/restore */
#define RAM_SAVE_FLAG_EOS 0x10
#define RAM_SAVE_FLAG_CONTINUE 0x20
#define RAM_SAVE_FLAG_XBZRLE 0x40
-
-#ifdef __ALTIVEC__
-#include <altivec.h>
-#define VECTYPE vector unsigned char
-#define SPLAT(p) vec_splat(vec_ld(0, p), 0)
-#define ALL_EQ(v1, v2) vec_all_eq(v1, v2)
-/* altivec.h may redefine the bool macro as vector type.
- * Reset it to POSIX semantics. */
-#undef bool
-#define bool _Bool
-#elif defined __SSE2__
-#include <emmintrin.h>
-#define VECTYPE __m128i
-#define SPLAT(p) _mm_set1_epi8(*(p))
-#define ALL_EQ(v1, v2) (_mm_movemask_epi8(_mm_cmpeq_epi8(v1, v2)) == 0xFFFF)
-#else
-#define VECTYPE unsigned long
-#define SPLAT(p) (*(p) * (~0UL / 255))
-#define ALL_EQ(v1, v2) ((v1) == (v2))
-#endif
+/* 0x80 is reserved in migration.h start with 0x100 next */
static struct defconfig_file {
/* Indicates it is an user config file (disabled by -no-user-config) */
bool userconfig;
} default_config_files[] = {
- { CONFIG_QEMU_DATADIR "/cpus-" TARGET_ARCH ".conf", false },
{ CONFIG_QEMU_CONFDIR "/qemu.conf", true },
- { CONFIG_QEMU_CONFDIR "/target-" TARGET_ARCH ".conf", true },
+ { CONFIG_QEMU_CONFDIR "/target-" TARGET_NAME ".conf", true },
{ NULL }, /* end of list */
};
return ret;
}
}
-
+
return 0;
}
-static int is_dup_page(uint8_t *page)
+static inline bool is_zero_range(uint8_t *p, uint64_t size)
{
- VECTYPE *p = (VECTYPE *)page;
- VECTYPE val = SPLAT(page);
- int i;
-
- for (i = 0; i < TARGET_PAGE_SIZE / sizeof(VECTYPE); i++) {
- if (!ALL_EQ(val, p[i])) {
- return 0;
- }
- }
-
- return 1;
+ return buffer_find_nonzero_offset(p, size) == size;
}
/* struct contains XBZRLE cache and a static page
/* accounting for migration statistics */
typedef struct AccountingInfo {
uint64_t dup_pages;
+ uint64_t skipped_pages;
uint64_t norm_pages;
uint64_t iterations;
uint64_t xbzrle_bytes;
return acct_info.dup_pages;
}
+uint64_t skipped_mig_bytes_transferred(void)
+{
+ return acct_info.skipped_pages * TARGET_PAGE_SIZE;
+}
+
+uint64_t skipped_mig_pages_transferred(void)
+{
+ return acct_info.skipped_pages;
+}
+
uint64_t norm_mig_bytes_transferred(void)
{
return acct_info.norm_pages * TARGET_PAGE_SIZE;
return acct_info.xbzrle_overflows;
}
-static void save_block_hdr(QEMUFile *f, RAMBlock *block, ram_addr_t offset,
- int cont, int flag)
+static size_t save_block_hdr(QEMUFile *f, RAMBlock *block, ram_addr_t offset,
+ int cont, int flag)
{
- qemu_put_be64(f, offset | cont | flag);
- if (!cont) {
- qemu_put_byte(f, strlen(block->idstr));
- qemu_put_buffer(f, (uint8_t *)block->idstr,
- strlen(block->idstr));
- }
+ size_t size;
+
+ qemu_put_be64(f, offset | cont | flag);
+ size = 8;
+ if (!cont) {
+ qemu_put_byte(f, strlen(block->idstr));
+ qemu_put_buffer(f, (uint8_t *)block->idstr,
+ strlen(block->idstr));
+ size += 1 + strlen(block->idstr);
+ }
+ return size;
}
#define ENCODING_FLAG_XBZRLE 0x1
if (!cache_is_cached(XBZRLE.cache, current_addr)) {
if (!last_stage) {
- cache_insert(XBZRLE.cache, current_addr,
- g_memdup(current_data, TARGET_PAGE_SIZE));
+ cache_insert(XBZRLE.cache, current_addr, current_data);
}
acct_info.xbzrle_cache_miss++;
return -1;
}
/* Send XBZRLE based compressed page */
- save_block_hdr(f, block, offset, cont, RAM_SAVE_FLAG_XBZRLE);
+ bytes_sent = save_block_hdr(f, block, offset, cont, RAM_SAVE_FLAG_XBZRLE);
qemu_put_byte(f, ENCODING_FLAG_XBZRLE);
qemu_put_be16(f, encoded_len);
qemu_put_buffer(f, XBZRLE.encoded_buf, encoded_len);
- bytes_sent = encoded_len + 1 + 2;
+ bytes_sent += encoded_len + 1 + 2;
acct_info.xbzrle_pages++;
acct_info.xbzrle_bytes += bytes_sent;
return bytes_sent;
}
-static RAMBlock *last_block;
+
+/* This is the last block that we have visited serching for dirty pages
+ */
+static RAMBlock *last_seen_block;
+/* This is the last block from where we have sent data */
+static RAMBlock *last_sent_block;
static ram_addr_t last_offset;
+static unsigned long *migration_bitmap;
+static uint64_t migration_dirty_pages;
+static uint32_t last_version;
+static bool ram_bulk_stage;
+
+static inline
+ram_addr_t migration_bitmap_find_and_reset_dirty(MemoryRegion *mr,
+ ram_addr_t start)
+{
+ unsigned long base = mr->ram_addr >> TARGET_PAGE_BITS;
+ unsigned long nr = base + (start >> TARGET_PAGE_BITS);
+ uint64_t mr_size = TARGET_PAGE_ALIGN(memory_region_size(mr));
+ unsigned long size = base + (mr_size >> TARGET_PAGE_BITS);
+
+ unsigned long next;
+
+ if (ram_bulk_stage && nr > base) {
+ next = nr + 1;
+ } else {
+ next = find_next_bit(migration_bitmap, size, nr);
+ }
+
+ if (next < size) {
+ clear_bit(next, migration_bitmap);
+ migration_dirty_pages--;
+ }
+ return (next - base) << TARGET_PAGE_BITS;
+}
+
+static inline bool migration_bitmap_set_dirty(MemoryRegion *mr,
+ ram_addr_t offset)
+{
+ bool ret;
+ int nr = (mr->ram_addr + offset) >> TARGET_PAGE_BITS;
+
+ ret = test_and_set_bit(nr, migration_bitmap);
+
+ if (!ret) {
+ migration_dirty_pages++;
+ }
+ return ret;
+}
+
+/* Needs iothread lock! */
+
+static void migration_bitmap_sync(void)
+{
+ RAMBlock *block;
+ ram_addr_t addr;
+ uint64_t num_dirty_pages_init = migration_dirty_pages;
+ MigrationState *s = migrate_get_current();
+ static int64_t start_time;
+ static int64_t bytes_xfer_prev;
+ static int64_t num_dirty_pages_period;
+ int64_t end_time;
+ int64_t bytes_xfer_now;
+
+ if (!bytes_xfer_prev) {
+ bytes_xfer_prev = ram_bytes_transferred();
+ }
+
+ if (!start_time) {
+ start_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
+ }
+
+ trace_migration_bitmap_sync_start();
+ address_space_sync_dirty_bitmap(&address_space_memory);
+
+ QTAILQ_FOREACH(block, &ram_list.blocks, next) {
+ for (addr = 0; addr < block->length; addr += TARGET_PAGE_SIZE) {
+ if (memory_region_test_and_clear_dirty(block->mr,
+ addr, TARGET_PAGE_SIZE,
+ DIRTY_MEMORY_MIGRATION)) {
+ migration_bitmap_set_dirty(block->mr, addr);
+ }
+ }
+ }
+ trace_migration_bitmap_sync_end(migration_dirty_pages
+ - num_dirty_pages_init);
+ num_dirty_pages_period += migration_dirty_pages - num_dirty_pages_init;
+ end_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
+
+ /* more than 1 second = 1000 millisecons */
+ if (end_time > start_time + 1000) {
+ if (migrate_auto_converge()) {
+ /* The following detection logic can be refined later. For now:
+ Check to see if the dirtied bytes is 50% more than the approx.
+ amount of bytes that just got transferred since the last time we
+ were in this routine. If that happens >N times (for now N==4)
+ we turn on the throttle down logic */
+ bytes_xfer_now = ram_bytes_transferred();
+ if (s->dirty_pages_rate &&
+ (num_dirty_pages_period * TARGET_PAGE_SIZE >
+ (bytes_xfer_now - bytes_xfer_prev)/2) &&
+ (dirty_rate_high_cnt++ > 4)) {
+ trace_migration_throttle();
+ mig_throttle_on = true;
+ dirty_rate_high_cnt = 0;
+ }
+ bytes_xfer_prev = bytes_xfer_now;
+ } else {
+ mig_throttle_on = false;
+ }
+ s->dirty_pages_rate = num_dirty_pages_period * 1000
+ / (end_time - start_time);
+ s->dirty_bytes_rate = s->dirty_pages_rate * TARGET_PAGE_SIZE;
+ start_time = end_time;
+ num_dirty_pages_period = 0;
+ }
+}
/*
* ram_save_block: Writes a page of memory to the stream f
*
- * Returns: 0: if the page hasn't changed
- * -1: if there are no more dirty pages
- * n: the amount of bytes written in other case
+ * Returns: The number of bytes written.
+ * 0 means no dirty pages
*/
static int ram_save_block(QEMUFile *f, bool last_stage)
{
- RAMBlock *block = last_block;
+ RAMBlock *block = last_seen_block;
ram_addr_t offset = last_offset;
- int bytes_sent = -1;
+ bool complete_round = false;
+ int bytes_sent = 0;
MemoryRegion *mr;
ram_addr_t current_addr;
if (!block)
- block = QLIST_FIRST(&ram_list.blocks);
+ block = QTAILQ_FIRST(&ram_list.blocks);
- do {
+ while (true) {
mr = block->mr;
- if (memory_region_get_dirty(mr, offset, TARGET_PAGE_SIZE,
- DIRTY_MEMORY_MIGRATION)) {
+ offset = migration_bitmap_find_and_reset_dirty(mr, offset);
+ if (complete_round && block == last_seen_block &&
+ offset >= last_offset) {
+ break;
+ }
+ if (offset >= block->length) {
+ offset = 0;
+ block = QTAILQ_NEXT(block, next);
+ if (!block) {
+ block = QTAILQ_FIRST(&ram_list.blocks);
+ complete_round = true;
+ ram_bulk_stage = false;
+ }
+ } else {
+ int ret;
uint8_t *p;
- int cont = (block == last_block) ? RAM_SAVE_FLAG_CONTINUE : 0;
-
- memory_region_reset_dirty(mr, offset, TARGET_PAGE_SIZE,
- DIRTY_MEMORY_MIGRATION);
+ int cont = (block == last_sent_block) ?
+ RAM_SAVE_FLAG_CONTINUE : 0;
p = memory_region_get_ram_ptr(mr) + offset;
- if (is_dup_page(p)) {
+ /* In doubt sent page as normal */
+ bytes_sent = -1;
+ ret = ram_control_save_page(f, block->offset,
+ offset, TARGET_PAGE_SIZE, &bytes_sent);
+
+ if (ret != RAM_SAVE_CONTROL_NOT_SUPP) {
+ if (ret != RAM_SAVE_CONTROL_DELAYED) {
+ if (bytes_sent > 0) {
+ acct_info.norm_pages++;
+ } else if (bytes_sent == 0) {
+ acct_info.dup_pages++;
+ }
+ }
+ } else if (is_zero_range(p, TARGET_PAGE_SIZE)) {
acct_info.dup_pages++;
- save_block_hdr(f, block, offset, cont, RAM_SAVE_FLAG_COMPRESS);
- qemu_put_byte(f, *p);
- bytes_sent = 1;
- } else if (migrate_use_xbzrle()) {
+ bytes_sent = save_block_hdr(f, block, offset, cont,
+ RAM_SAVE_FLAG_COMPRESS);
+ qemu_put_byte(f, 0);
+ bytes_sent++;
+ } else if (!ram_bulk_stage && migrate_use_xbzrle()) {
current_addr = block->offset + offset;
bytes_sent = save_xbzrle_page(f, p, current_addr, block,
offset, cont, last_stage);
}
}
- /* either we didn't send yet (we may have had XBZRLE overflow) */
+ /* XBZRLE overflow or normal page */
if (bytes_sent == -1) {
- save_block_hdr(f, block, offset, cont, RAM_SAVE_FLAG_PAGE);
- qemu_put_buffer(f, p, TARGET_PAGE_SIZE);
- bytes_sent = TARGET_PAGE_SIZE;
+ bytes_sent = save_block_hdr(f, block, offset, cont, RAM_SAVE_FLAG_PAGE);
+ qemu_put_buffer_async(f, p, TARGET_PAGE_SIZE);
+ bytes_sent += TARGET_PAGE_SIZE;
acct_info.norm_pages++;
}
/* if page is unmodified, continue to the next */
- if (bytes_sent != 0) {
+ if (bytes_sent > 0) {
+ last_sent_block = block;
break;
}
}
-
- offset += TARGET_PAGE_SIZE;
- if (offset >= block->length) {
- offset = 0;
- block = QLIST_NEXT(block, next);
- if (!block)
- block = QLIST_FIRST(&ram_list.blocks);
- }
- } while (block != last_block || offset != last_offset);
-
- last_block = block;
+ }
+ last_seen_block = block;
last_offset = offset;
return bytes_sent;
static uint64_t bytes_transferred;
+void acct_update_position(QEMUFile *f, size_t size, bool zero)
+{
+ uint64_t pages = size / TARGET_PAGE_SIZE;
+ if (zero) {
+ acct_info.dup_pages += pages;
+ } else {
+ acct_info.norm_pages += pages;
+ bytes_transferred += size;
+ qemu_update_position(f, size);
+ }
+}
+
static ram_addr_t ram_save_remaining(void)
{
- return ram_list.dirty_pages;
+ return migration_dirty_pages;
}
uint64_t ram_bytes_remaining(void)
RAMBlock *block;
uint64_t total = 0;
- QLIST_FOREACH(block, &ram_list.blocks, next)
+ QTAILQ_FOREACH(block, &ram_list.blocks, next)
total += block->length;
return total;
}
-static int block_compar(const void *a, const void *b)
-{
- RAMBlock * const *ablock = a;
- RAMBlock * const *bblock = b;
-
- return strcmp((*ablock)->idstr, (*bblock)->idstr);
-}
-
-static void sort_ram_list(void)
-{
- RAMBlock *block, *nblock, **blocks;
- int n;
- n = 0;
- QLIST_FOREACH(block, &ram_list.blocks, next) {
- ++n;
- }
- blocks = g_malloc(n * sizeof *blocks);
- n = 0;
- QLIST_FOREACH_SAFE(block, &ram_list.blocks, next, nblock) {
- blocks[n++] = block;
- QLIST_REMOVE(block, next);
- }
- qsort(blocks, n, sizeof *blocks, block_compar);
- while (--n >= 0) {
- QLIST_INSERT_HEAD(&ram_list.blocks, blocks[n], next);
- }
- g_free(blocks);
-}
-
static void migration_end(void)
{
- memory_global_dirty_log_stop();
+ if (migration_bitmap) {
+ memory_global_dirty_log_stop();
+ g_free(migration_bitmap);
+ migration_bitmap = NULL;
+ }
- if (migrate_use_xbzrle()) {
+ if (XBZRLE.cache) {
cache_fini(XBZRLE.cache);
g_free(XBZRLE.cache);
g_free(XBZRLE.encoded_buf);
migration_end();
}
+static void reset_ram_globals(void)
+{
+ last_seen_block = NULL;
+ last_sent_block = NULL;
+ last_offset = 0;
+ last_version = ram_list.version;
+ ram_bulk_stage = true;
+}
+
#define MAX_WAIT 50 /* ms, half buffered_file limit */
static int ram_save_setup(QEMUFile *f, void *opaque)
{
- ram_addr_t addr;
RAMBlock *block;
+ int64_t ram_pages = last_ram_offset() >> TARGET_PAGE_BITS;
- bytes_transferred = 0;
- last_block = NULL;
- last_offset = 0;
- sort_ram_list();
+ migration_bitmap = bitmap_new(ram_pages);
+ bitmap_set(migration_bitmap, 0, ram_pages);
+ migration_dirty_pages = ram_pages;
+ mig_throttle_on = false;
+ dirty_rate_high_cnt = 0;
if (migrate_use_xbzrle()) {
XBZRLE.cache = cache_init(migrate_xbzrle_cache_size() /
acct_clear();
}
- /* Make sure all dirty bits are set */
- QLIST_FOREACH(block, &ram_list.blocks, next) {
- for (addr = 0; addr < block->length; addr += TARGET_PAGE_SIZE) {
- if (!memory_region_get_dirty(block->mr, addr, TARGET_PAGE_SIZE,
- DIRTY_MEMORY_MIGRATION)) {
- memory_region_set_dirty(block->mr, addr, TARGET_PAGE_SIZE);
- }
- }
- }
+ qemu_mutex_lock_iothread();
+ qemu_mutex_lock_ramlist();
+ bytes_transferred = 0;
+ reset_ram_globals();
memory_global_dirty_log_start();
+ migration_bitmap_sync();
+ qemu_mutex_unlock_iothread();
qemu_put_be64(f, ram_bytes_total() | RAM_SAVE_FLAG_MEM_SIZE);
- QLIST_FOREACH(block, &ram_list.blocks, next) {
+ QTAILQ_FOREACH(block, &ram_list.blocks, next) {
qemu_put_byte(f, strlen(block->idstr));
qemu_put_buffer(f, (uint8_t *)block->idstr, strlen(block->idstr));
qemu_put_be64(f, block->length);
}
+ qemu_mutex_unlock_ramlist();
+
+ ram_control_before_iterate(f, RAM_CONTROL_SETUP);
+ ram_control_after_iterate(f, RAM_CONTROL_SETUP);
+
qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
return 0;
static int ram_save_iterate(QEMUFile *f, void *opaque)
{
- uint64_t bytes_transferred_last;
- double bwidth = 0;
int ret;
int i;
- uint64_t expected_time;
+ int64_t t0;
+ int total_sent = 0;
- bytes_transferred_last = bytes_transferred;
- bwidth = qemu_get_clock_ns(rt_clock);
+ qemu_mutex_lock_ramlist();
+ if (ram_list.version != last_version) {
+ reset_ram_globals();
+ }
+
+ ram_control_before_iterate(f, RAM_CONTROL_ROUND);
+
+ t0 = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
i = 0;
while ((ret = qemu_file_rate_limit(f)) == 0) {
int bytes_sent;
bytes_sent = ram_save_block(f, false);
/* no more blocks to sent */
- if (bytes_sent < 0) {
+ if (bytes_sent == 0) {
break;
}
- bytes_transferred += bytes_sent;
+ total_sent += bytes_sent;
acct_info.iterations++;
+ check_guest_throttling();
/* we want to check in the 1st loop, just in case it was the 1st time
and we had to sync the dirty bitmap.
qemu_get_clock_ns() is a bit expensive, so we only check each some
iterations
*/
if ((i & 63) == 0) {
- uint64_t t1 = (qemu_get_clock_ns(rt_clock) - bwidth) / 1000000;
+ uint64_t t1 = (qemu_clock_get_ns(QEMU_CLOCK_REALTIME) - t0) / 1000000;
if (t1 > MAX_WAIT) {
- DPRINTF("big wait: " PRIu64 " milliseconds, %d iterations\n",
+ DPRINTF("big wait: %" PRIu64 " milliseconds, %d iterations\n",
t1, i);
break;
}
i++;
}
- if (ret < 0) {
- return ret;
- }
+ qemu_mutex_unlock_ramlist();
- bwidth = qemu_get_clock_ns(rt_clock) - bwidth;
- bwidth = (bytes_transferred - bytes_transferred_last) / bwidth;
+ /*
+ * Must occur before EOS (or any QEMUFile operation)
+ * because of RDMA protocol.
+ */
+ ram_control_after_iterate(f, RAM_CONTROL_ROUND);
- /* if we haven't transferred anything this round, force expected_time to a
- * a very high value, but without crashing */
- if (bwidth == 0) {
- bwidth = 0.000001;
- }
+ bytes_transferred += total_sent;
+ /*
+ * Do not count these 8 bytes into total_sent, so that we can
+ * return 0 if no page had been dirtied.
+ */
qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
+ bytes_transferred += 8;
- expected_time = ram_save_remaining() * TARGET_PAGE_SIZE / bwidth;
-
- DPRINTF("ram_save_live: expected(" PRIu64 ") <= max(" PRIu64 ")?\n",
- expected_time, migrate_max_downtime());
-
- if (expected_time <= migrate_max_downtime()) {
- memory_global_sync_dirty_bitmap(get_system_memory());
- expected_time = ram_save_remaining() * TARGET_PAGE_SIZE / bwidth;
-
- return expected_time <= migrate_max_downtime();
+ ret = qemu_file_get_error(f);
+ if (ret < 0) {
+ return ret;
}
- return 0;
+
+ return total_sent;
}
static int ram_save_complete(QEMUFile *f, void *opaque)
{
- memory_global_sync_dirty_bitmap(get_system_memory());
+ qemu_mutex_lock_ramlist();
+ migration_bitmap_sync();
+
+ ram_control_before_iterate(f, RAM_CONTROL_FINISH);
/* try transferring iterative blocks of memory */
bytes_sent = ram_save_block(f, true);
/* no more blocks to sent */
- if (bytes_sent < 0) {
+ if (bytes_sent == 0) {
break;
}
bytes_transferred += bytes_sent;
}
- memory_global_dirty_log_stop();
+ ram_control_after_iterate(f, RAM_CONTROL_FINISH);
+ migration_end();
+
+ qemu_mutex_unlock_ramlist();
qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
return 0;
}
+static uint64_t ram_save_pending(QEMUFile *f, void *opaque, uint64_t max_size)
+{
+ uint64_t remaining_size;
+
+ remaining_size = ram_save_remaining() * TARGET_PAGE_SIZE;
+
+ if (remaining_size < max_size) {
+ qemu_mutex_lock_iothread();
+ migration_bitmap_sync();
+ qemu_mutex_unlock_iothread();
+ remaining_size = ram_save_remaining() * TARGET_PAGE_SIZE;
+ }
+ return remaining_size;
+}
+
static int load_xbzrle(QEMUFile *f, ram_addr_t addr, void *host)
{
int ret, rc = 0;
qemu_get_buffer(f, (uint8_t *)id, len);
id[len] = 0;
- QLIST_FOREACH(block, &ram_list.blocks, next) {
+ QTAILQ_FOREACH(block, &ram_list.blocks, next) {
if (!strncmp(id, block->idstr, sizeof(id)))
return memory_region_get_ram_ptr(block->mr) + offset;
}
return NULL;
}
+/*
+ * If a page (or a whole RDMA chunk) has been
+ * determined to be zero, then zap it.
+ */
+void ram_handle_compressed(void *host, uint8_t ch, uint64_t size)
+{
+ if (ch != 0 || !is_zero_range(host, size)) {
+ memset(host, ch, size);
+ }
+}
+
static int ram_load(QEMUFile *f, void *opaque, int version_id)
{
ram_addr_t addr;
id[len] = 0;
length = qemu_get_be64(f);
- QLIST_FOREACH(block, &ram_list.blocks, next) {
+ QTAILQ_FOREACH(block, &ram_list.blocks, next) {
if (!strncmp(id, block->idstr, sizeof(id))) {
if (block->length != length) {
+ fprintf(stderr,
+ "Length mismatch: %s: " RAM_ADDR_FMT
+ " in != " RAM_ADDR_FMT "\n", id, length,
+ block->length);
ret = -EINVAL;
goto done;
}
}
ch = qemu_get_byte(f);
- memset(host, ch, TARGET_PAGE_SIZE);
-#ifndef _WIN32
- if (ch == 0 &&
- (!kvm_enabled() || kvm_has_sync_mmu())) {
- qemu_madvise(host, TARGET_PAGE_SIZE, QEMU_MADV_DONTNEED);
- }
-#endif
+ ram_handle_compressed(host, ch, TARGET_PAGE_SIZE);
} else if (flags & RAM_SAVE_FLAG_PAGE) {
void *host;
qemu_get_buffer(f, host, TARGET_PAGE_SIZE);
} else if (flags & RAM_SAVE_FLAG_XBZRLE) {
- if (!migrate_use_xbzrle()) {
- return -EINVAL;
- }
void *host = host_from_stream_offset(f, addr, flags);
if (!host) {
return -EINVAL;
ret = -EINVAL;
goto done;
}
+ } else if (flags & RAM_SAVE_FLAG_HOOK) {
+ ram_control_load_hook(f, flags);
}
error = qemu_file_get_error(f);
if (error) {
} while (!(flags & RAM_SAVE_FLAG_EOS));
done:
- DPRINTF("Completed load of VM with exit code %d seq iteration " PRIu64 "\n",
- ret, seq_iter);
+ DPRINTF("Completed load of VM with exit code %d seq iteration "
+ "%" PRIu64 "\n", ret, seq_iter);
return ret;
}
.save_live_setup = ram_save_setup,
.save_live_iterate = ram_save_iterate,
.save_live_complete = ram_save_complete,
+ .save_live_pending = ram_save_pending,
.load_state = ram_load,
.cancel = ram_migration_cancel,
};
-#ifdef HAS_AUDIO
struct soundhw {
const char *name;
const char *descr;
} init;
};
-static struct soundhw soundhw[] = {
-#ifdef HAS_AUDIO_CHOICE
-#ifdef CONFIG_PCSPK
- {
- "pcspk",
- "PC speaker",
- 0,
- 1,
- { .init_isa = pcspk_audio_init }
- },
-#endif
-
-#ifdef CONFIG_SB16
- {
- "sb16",
- "Creative Sound Blaster 16",
- 0,
- 1,
- { .init_isa = SB16_init }
- },
-#endif
+static struct soundhw soundhw[9];
+static int soundhw_count;
-#ifdef CONFIG_CS4231A
- {
- "cs4231a",
- "CS4231A",
- 0,
- 1,
- { .init_isa = cs4231a_init }
- },
-#endif
-
-#ifdef CONFIG_ADLIB
- {
- "adlib",
-#ifdef HAS_YMF262
- "Yamaha YMF262 (OPL3)",
-#else
- "Yamaha YM3812 (OPL2)",
-#endif
- 0,
- 1,
- { .init_isa = Adlib_init }
- },
-#endif
-
-#ifdef CONFIG_GUS
- {
- "gus",
- "Gravis Ultrasound GF1",
- 0,
- 1,
- { .init_isa = GUS_init }
- },
-#endif
-
-#ifdef CONFIG_AC97
- {
- "ac97",
- "Intel 82801AA AC97 Audio",
- 0,
- 0,
- { .init_pci = ac97_init }
- },
-#endif
-
-#ifdef CONFIG_ES1370
- {
- "es1370",
- "ENSONIQ AudioPCI ES1370",
- 0,
- 0,
- { .init_pci = es1370_init }
- },
-#endif
-
-#ifdef CONFIG_HDA
- {
- "hda",
- "Intel HD Audio",
- 0,
- 0,
- { .init_pci = intel_hda_and_codec_init }
- },
-#endif
-
-#endif /* HAS_AUDIO_CHOICE */
+void isa_register_soundhw(const char *name, const char *descr,
+ int (*init_isa)(ISABus *bus))
+{
+ assert(soundhw_count < ARRAY_SIZE(soundhw) - 1);
+ soundhw[soundhw_count].name = name;
+ soundhw[soundhw_count].descr = descr;
+ soundhw[soundhw_count].isa = 1;
+ soundhw[soundhw_count].init.init_isa = init_isa;
+ soundhw_count++;
+}
- { NULL, NULL, 0, 0, { NULL } }
-};
+void pci_register_soundhw(const char *name, const char *descr,
+ int (*init_pci)(PCIBus *bus))
+{
+ assert(soundhw_count < ARRAY_SIZE(soundhw) - 1);
+ soundhw[soundhw_count].name = name;
+ soundhw[soundhw_count].descr = descr;
+ soundhw[soundhw_count].isa = 0;
+ soundhw[soundhw_count].init.init_pci = init_pci;
+ soundhw_count++;
+}
void select_soundhw(const char *optarg)
{
if (is_help_option(optarg)) {
show_valid_cards:
- printf("Valid sound card names (comma separated):\n");
- for (c = soundhw; c->name; ++c) {
- printf ("%-11s %s\n", c->name, c->descr);
+ if (soundhw_count) {
+ printf("Valid sound card names (comma separated):\n");
+ for (c = soundhw; c->name; ++c) {
+ printf ("%-11s %s\n", c->name, c->descr);
+ }
+ printf("\n-soundhw all will enable all of the above\n");
+ } else {
+ printf("Machine has no user-selectable audio hardware "
+ "(it may or may not have always-present audio hardware).\n");
}
- printf("\n-soundhw all will enable all of the above\n");
exit(!is_help_option(optarg));
}
else {
}
}
-void audio_init(ISABus *isa_bus, PCIBus *pci_bus)
+void audio_init(void)
{
struct soundhw *c;
+ ISABus *isa_bus = (ISABus *) object_resolve_path_type("", TYPE_ISA_BUS, NULL);
+ PCIBus *pci_bus = (PCIBus *) object_resolve_path_type("", TYPE_PCI_BUS, NULL);
for (c = soundhw; c->name; ++c) {
if (c->enabled) {
if (c->isa) {
- if (isa_bus) {
- c->init.init_isa(isa_bus);
+ if (!isa_bus) {
+ fprintf(stderr, "ISA bus not available for %s\n", c->name);
+ exit(1);
}
+ c->init.init_isa(isa_bus);
} else {
- if (pci_bus) {
- c->init.init_pci(pci_bus);
+ if (!pci_bus) {
+ fprintf(stderr, "PCI bus not available for %s\n", c->name);
+ exit(1);
}
+ c->init.init_pci(pci_bus);
}
}
}
}
-#else
-void select_soundhw(const char *optarg)
-{
-}
-void audio_init(ISABus *isa_bus, PCIBus *pci_bus)
-{
-}
-#endif
int qemu_uuid_parse(const char *str, uint8_t *uuid)
{
if (ret != 16) {
return -1;
}
-#ifdef TARGET_I386
- smbios_add_field(1, offsetof(struct smbios_type_1, uuid), 16, uuid);
-#endif
return 0;
}
-void do_acpitable_option(const char *optarg)
+void do_acpitable_option(const QemuOpts *opts)
{
#ifdef TARGET_I386
- if (acpi_table_add(optarg) < 0) {
- fprintf(stderr, "Wrong acpi table provided\n");
+ Error *err = NULL;
+
+ acpi_table_add(opts, &err);
+ if (err) {
+ error_report("Wrong acpi table provided: %s",
+ error_get_pretty(err));
+ error_free(err);
exit(1);
}
#endif
}
-void do_smbios_option(const char *optarg)
+void do_smbios_option(QemuOpts *opts)
{
#ifdef TARGET_I386
- if (smbios_entry_add(optarg) < 0) {
- fprintf(stderr, "Wrong smbios provided\n");
- exit(1);
- }
+ smbios_entry_add(opts);
#endif
}
#endif
}
-int audio_available(void)
-{
-#ifdef HAS_AUDIO
- return 1;
-#else
- return 0;
-#endif
-}
-
int tcg_available(void)
{
return 1;
return 0;
#endif
}
+
+
+TargetInfo *qmp_query_target(Error **errp)
+{
+ TargetInfo *info = g_malloc0(sizeof(*info));
+
+ info->arch = g_strdup(TARGET_NAME);
+
+ return info;
+}
+
+/* Stub function that's gets run on the vcpu when its brought out of the
+ VM to run inside qemu via async_run_on_cpu()*/
+static void mig_sleep_cpu(void *opq)
+{
+ qemu_mutex_unlock_iothread();
+ g_usleep(30*1000);
+ qemu_mutex_lock_iothread();
+}
+
+/* To reduce the dirty rate explicitly disallow the VCPUs from spending
+ much time in the VM. The migration thread will try to catchup.
+ Workload will experience a performance drop.
+*/
+static void mig_throttle_guest_down(void)
+{
+ CPUState *cpu;
+
+ qemu_mutex_lock_iothread();
+ CPU_FOREACH(cpu) {
+ async_run_on_cpu(cpu, mig_sleep_cpu, NULL);
+ }
+ qemu_mutex_unlock_iothread();
+}
+
+static void check_guest_throttling(void)
+{
+ static int64_t t0;
+ int64_t t1;
+
+ if (!mig_throttle_on) {
+ return;
+ }
+
+ if (!t0) {
+ t0 = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
+ return;
+ }
+
+ t1 = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
+
+ /* If it has been more than 40 ms since the last time the guest
+ * was throttled then do it again.
+ */
+ if (40 < (t1-t0)/1000000) {
+ mig_throttle_guest_down();
+ t0 = t1;
+ }
+}
projects / qemu.git / blobdiff