Merge remote-tracking branch 'quintela/migration-next-20120808' into staging

* quintela/migration-next-20120808:
  Restart optimization on stage3 update version
  Add XBZRLE statistics
  Add migration accounting for normal and duplicate pages
  Change total_time to total-time in MigrationStats
  Add migrate_set_cache_size command
  Add XBZRLE to ram_save_block and ram_save_live
  Add xbzrle_encode_buffer and xbzrle_decode_buffer functions
  Add uleb encoding/decoding functions
  Add cache handling functions
  Add XBZRLE documentation
  Add migrate-set-capabilities
  Add migration capabilities

Makefile.objs

@@ -77,6 +77,7 @@ common-obj-y += qemu-char.o #aio.o
 common-obj-y += block-migration.o iohandler.o
 common-obj-y += pflib.o
 common-obj-y += bitmap.o bitops.o
+common-obj-y += page_cache.o
 
 common-obj-$(CONFIG_POSIX) += migration-exec.o migration-unix.o migration-fd.o
 common-obj-$(CONFIG_WIN32) += version.o

arch_init.c

@@ -43,6 +43,7 @@
 #include "hw/smbios.h"
 #include "exec-memory.h"
 #include "hw/pcspk.h"
+#include "qemu/page_cache.h"
 
 #ifdef DEBUG_ARCH_INIT
 #define DPRINTF(fmt, ...) \
@@ -106,6 +107,7 @@ const uint32_t arch_type = QEMU_ARCH;
 #define RAM_SAVE_FLAG_PAGE     0x08
 #define RAM_SAVE_FLAG_EOS      0x10
 #define RAM_SAVE_FLAG_CONTINUE 0x20
+#define RAM_SAVE_FLAG_XBZRLE   0x40
 
 #ifdef __ALTIVEC__
 #include <altivec.h>
@@ -173,6 +175,92 @@ static int is_dup_page(uint8_t *page)
     return 1;
 }
 
+/* struct contains XBZRLE cache and a static page
+   used by the compression */
+static struct {
+    /* buffer used for XBZRLE encoding */
+    uint8_t *encoded_buf;
+    /* buffer for storing page content */
+    uint8_t *current_buf;
+    /* buffer used for XBZRLE decoding */
+    uint8_t *decoded_buf;
+    /* Cache for XBZRLE */
+    PageCache *cache;
+} XBZRLE = {
+    .encoded_buf = NULL,
+    .current_buf = NULL,
+    .decoded_buf = NULL,
+    .cache = NULL,
+};
+
+
+int64_t xbzrle_cache_resize(int64_t new_size)
+{
+    if (XBZRLE.cache != NULL) {
+        return cache_resize(XBZRLE.cache, new_size / TARGET_PAGE_SIZE) *
+            TARGET_PAGE_SIZE;
+    }
+    return pow2floor(new_size);
+}
+
+/* accounting for migration statistics */
+typedef struct AccountingInfo {
+    uint64_t dup_pages;
+    uint64_t norm_pages;
+    uint64_t iterations;
+    uint64_t xbzrle_bytes;
+    uint64_t xbzrle_pages;
+    uint64_t xbzrle_cache_miss;
+    uint64_t xbzrle_overflows;
+} AccountingInfo;
+
+static AccountingInfo acct_info;
+
+static void acct_clear(void)
+{
+    memset(&acct_info, 0, sizeof(acct_info));
+}
+
+uint64_t dup_mig_bytes_transferred(void)
+{
+    return acct_info.dup_pages * TARGET_PAGE_SIZE;
+}
+
+uint64_t dup_mig_pages_transferred(void)
+{
+    return acct_info.dup_pages;
+}
+
+uint64_t norm_mig_bytes_transferred(void)
+{
+    return acct_info.norm_pages * TARGET_PAGE_SIZE;
+}
+
+uint64_t norm_mig_pages_transferred(void)
+{
+    return acct_info.norm_pages;
+}
+
+uint64_t xbzrle_mig_bytes_transferred(void)
+{
+    return acct_info.xbzrle_bytes;
+}
+
+uint64_t xbzrle_mig_pages_transferred(void)
+{
+    return acct_info.xbzrle_pages;
+}
+
+uint64_t xbzrle_mig_pages_cache_miss(void)
+{
+    return acct_info.xbzrle_cache_miss;
+}
+
+uint64_t xbzrle_mig_pages_overflow(void)
+{
+    return acct_info.xbzrle_overflows;
+}
+
 static void save_block_hdr(QEMUFile *f, RAMBlock *block, ram_addr_t offset,
         int cont, int flag)
 {
@@ -185,6 +273,61 @@ static void save_block_hdr(QEMUFile *f, RAMBlock *block, ram_addr_t offset,
 
 }
 
+#define ENCODING_FLAG_XBZRLE 0x1
+
+static int save_xbzrle_page(QEMUFile *f, uint8_t *current_data,
+                            ram_addr_t current_addr, RAMBlock *block,
+                            ram_addr_t offset, int cont, bool last_stage)
+{
+    int encoded_len = 0, bytes_sent = -1;
+    uint8_t *prev_cached_page;
+
+    if (!cache_is_cached(XBZRLE.cache, current_addr)) {
+        if (!last_stage) {
+            cache_insert(XBZRLE.cache, current_addr,
+                         g_memdup(current_data, TARGET_PAGE_SIZE));
+        }
+        acct_info.xbzrle_cache_miss++;
+        return -1;
+    }
+
+    prev_cached_page = get_cached_data(XBZRLE.cache, current_addr);
+
+    /* save current buffer into memory */
+    memcpy(XBZRLE.current_buf, current_data, TARGET_PAGE_SIZE);
+
+    /* XBZRLE encoding (if there is no overflow) */
+    encoded_len = xbzrle_encode_buffer(prev_cached_page, XBZRLE.current_buf,
+                                       TARGET_PAGE_SIZE, XBZRLE.encoded_buf,
+                                       TARGET_PAGE_SIZE);
+    if (encoded_len == 0) {
+        DPRINTF("Skipping unmodified page\n");
+        return 0;
+    } else if (encoded_len == -1) {
+        DPRINTF("Overflow\n");
+        acct_info.xbzrle_overflows++;
+        /* update data in the cache */
+        memcpy(prev_cached_page, current_data, TARGET_PAGE_SIZE);
+        return -1;
+    }
+
+    /* we need to update the data in the cache, in order to get the same data */
+    if (!last_stage) {
+        memcpy(prev_cached_page, XBZRLE.current_buf, TARGET_PAGE_SIZE);
+    }
+
+    /* Send XBZRLE based compressed page */
+    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;
+    acct_info.xbzrle_pages++;
+    acct_info.xbzrle_bytes += bytes_sent;
+
+    return bytes_sent;
+}
+
 static RAMBlock *last_block;
 static ram_addr_t last_offset;
 
@@ -196,12 +339,13 @@ static ram_addr_t last_offset;
  *           n: the amount of bytes written in other case
  */
 
-static int ram_save_block(QEMUFile *f)
+static int ram_save_block(QEMUFile *f, bool last_stage)
 {
     RAMBlock *block = last_block;
     ram_addr_t offset = last_offset;
     int bytes_sent = -1;
     MemoryRegion *mr;
+    ram_addr_t current_addr;
 
     if (!block)
         block = QLIST_FIRST(&ram_list.blocks);
@@ -219,16 +363,31 @@ static int ram_save_block(QEMUFile *f)
             p = memory_region_get_ram_ptr(mr) + offset;
 
             if (is_dup_page(p)) {
+                acct_info.dup_pages++;
                 save_block_hdr(f, block, offset, cont, RAM_SAVE_FLAG_COMPRESS);
                 qemu_put_byte(f, *p);
                 bytes_sent = 1;
-            } else {
+            } else if (migrate_use_xbzrle()) {
+                current_addr = block->offset + offset;
+                bytes_sent = save_xbzrle_page(f, p, current_addr, block,
+                                              offset, cont, last_stage);
+                if (!last_stage) {
+                    p = get_cached_data(XBZRLE.cache, current_addr);
+                }
+            }
+
+            /* either we didn't send yet (we may have had XBZRLE overflow) */
+            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;
+                acct_info.norm_pages++;
             }
 
-            break;
+            /* if page is unmodified, continue to the next */
+            if (bytes_sent != 0) {
+                break;
+            }
         }
 
         offset += TARGET_PAGE_SIZE;
@@ -306,6 +465,15 @@ static void sort_ram_list(void)
 static void migration_end(void)
 {
     memory_global_dirty_log_stop();
+
+    if (migrate_use_xbzrle()) {
+        cache_fini(XBZRLE.cache);
+        g_free(XBZRLE.cache);
+        g_free(XBZRLE.encoded_buf);
+        g_free(XBZRLE.current_buf);
+        g_free(XBZRLE.decoded_buf);
+        XBZRLE.cache = NULL;
+    }
 }
 
 static void ram_migration_cancel(void *opaque)
@@ -325,6 +493,19 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
     last_offset = 0;
     sort_ram_list();
 
+    if (migrate_use_xbzrle()) {
+        XBZRLE.cache = cache_init(migrate_xbzrle_cache_size() /
+                                  TARGET_PAGE_SIZE,
+                                  TARGET_PAGE_SIZE);
+        if (!XBZRLE.cache) {
+            DPRINTF("Error creating cache\n");
+            return -1;
+        }
+        XBZRLE.encoded_buf = g_malloc0(TARGET_PAGE_SIZE);
+        XBZRLE.current_buf = g_malloc(TARGET_PAGE_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) {
@@ -365,12 +546,13 @@ static int ram_save_iterate(QEMUFile *f, void *opaque)
     while ((ret = qemu_file_rate_limit(f)) == 0) {
         int bytes_sent;
 
-        bytes_sent = ram_save_block(f);
+        bytes_sent = ram_save_block(f, false);
         /* no more blocks to sent */
         if (bytes_sent < 0) {
             break;
         }
         bytes_transferred += bytes_sent;
+        acct_info.iterations++;
         /* 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
@@ -426,7 +608,7 @@ static int ram_save_complete(QEMUFile *f, void *opaque)
     while (true) {
         int bytes_sent;
 
-        bytes_sent = ram_save_block(f);
+        bytes_sent = ram_save_block(f, true);
         /* no more blocks to sent */
         if (bytes_sent < 0) {
             break;
@@ -440,6 +622,47 @@ static int ram_save_complete(QEMUFile *f, void *opaque)
     return 0;
 }
 
+static int load_xbzrle(QEMUFile *f, ram_addr_t addr, void *host)
+{
+    int ret, rc = 0;
+    unsigned int xh_len;
+    int xh_flags;
+
+    if (!XBZRLE.decoded_buf) {
+        XBZRLE.decoded_buf = g_malloc(TARGET_PAGE_SIZE);
+    }
+
+    /* extract RLE header */
+    xh_flags = qemu_get_byte(f);
+    xh_len = qemu_get_be16(f);
+
+    if (xh_flags != ENCODING_FLAG_XBZRLE) {
+        fprintf(stderr, "Failed to load XBZRLE page - wrong compression!\n");
+        return -1;
+    }
+
+    if (xh_len > TARGET_PAGE_SIZE) {
+        fprintf(stderr, "Failed to load XBZRLE page - len overflow!\n");
+        return -1;
+    }
+    /* load data and decode */
+    qemu_get_buffer(f, XBZRLE.decoded_buf, xh_len);
+
+    /* decode RLE */
+    ret = xbzrle_decode_buffer(XBZRLE.decoded_buf, xh_len, host,
+                               TARGET_PAGE_SIZE);
+    if (ret == -1) {
+        fprintf(stderr, "Failed to load XBZRLE page - decode error!\n");
+        rc = -1;
+    } else  if (ret > TARGET_PAGE_SIZE) {
+        fprintf(stderr, "Failed to load XBZRLE page - size %d exceeds %d!\n",
+                ret, TARGET_PAGE_SIZE);
+        abort();
+    }
+
+    return rc;
+}
+
 static inline void *host_from_stream_offset(QEMUFile *f,
                                             ram_addr_t offset,
                                             int flags)
@@ -553,6 +776,19 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
             }
 
             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;
+            }
+
+            if (load_xbzrle(f, addr, host) < 0) {
+                ret = -EINVAL;
+                goto done;
+            }
         }
         error = qemu_file_get_error(f);
         if (error) {

cutils.c

@@ -382,3 +382,45 @@ int qemu_parse_fd(const char *param)
     }
     return fd;
 }
+
+/* round down to the nearest power of 2*/
+int64_t pow2floor(int64_t value)
+{
+    if (!is_power_of_2(value)) {
+        value = 0x8000000000000000ULL >> clz64(value);
+    }
+    return value;
+}
+
+/*
+ * Implementation of  ULEB128 (http://en.wikipedia.org/wiki/LEB128)
+ * Input is limited to 14-bit numbers
+ */
+int uleb128_encode_small(uint8_t *out, uint32_t n)
+{
+    g_assert(n <= 0x3fff);
+    if (n < 0x80) {
+        *out++ = n;
+        return 1;
+    } else {
+        *out++ = (n & 0x7f) | 0x80;
+        *out++ = n >> 7;
+        return 2;
+    }
+}
+
+int uleb128_decode_small(const uint8_t *in, uint32_t *n)
+{
+    if (!(*in & 0x80)) {
+        *n = *in++;
+        return 1;
+    } else {
+        *n = *in++ & 0x7f;
+        /* we exceed 14 bit number */
+        if (*in & 0x80) {
+            return -1;
+        }
+        *n |= *in++ << 7;
+        return 2;
+    }
+}

docs/xbzrle.txt

@@ -0,0 +1,128 @@
+XBZRLE (Xor Based Zero Run Length Encoding)
+===========================================
+
+Using XBZRLE (Xor Based Zero Run Length Encoding) allows for the reduction
+of VM downtime and the total live-migration time of Virtual machines.
+It is particularly useful for virtual machines running memory write intensive
+workloads that are typical of large enterprise applications such as SAP ERP
+Systems, and generally speaking for any application that uses a sparse memory
+update pattern.
+
+Instead of sending the changed guest memory page this solution will send a
+compressed version of the updates, thus reducing the amount of data sent during
+live migration.
+In order to be able to calculate the update, the previous memory pages need to
+be stored on the source. Those pages are stored in a dedicated cache
+(hash table) and are accessed by their address.
+The larger the cache size the better the chances are that the page has already
+been stored in the cache.
+A small cache size will result in high cache miss rate.
+Cache size can be changed before and during migration.
+
+Format
+=======
+
+The compression format performs a XOR between the previous and current content
+of the page, where zero represents an unchanged value.
+The page data delta is represented by zero and non zero runs.
+A zero run is represented by its length (in bytes).
+A non zero run is represented by its length (in bytes) and the new data.
+The run length is encoded using ULEB128 (http://en.wikipedia.org/wiki/LEB128)
+
+There can be more than one valid encoding, the sender may send a longer encoding
+for the benefit of reducing computation cost.
+
+page = zrun nzrun
+       | zrun nzrun page
+
+zrun = length
+
+nzrun = length byte...
+
+length = uleb128 encoded integer
+
+On the sender side XBZRLE is used as a compact delta encoding of page updates,
+retrieving the old page content from the cache (default size of 512 MB). The
+receiving side uses the existing page's content and XBZRLE to decode the new
+page's content.
+
+This work was originally based on research results published
+VEE 2011: Evaluation of Delta Compression Techniques for Efficient Live
+Migration of Large Virtual Machines by Benoit, Svard, Tordsson and Elmroth.
+Additionally the delta encoder XBRLE was improved further using the XBZRLE
+instead.
+
+XBZRLE has a sustained bandwidth of 2-2.5 GB/s for typical workloads making it
+ideal for in-line, real-time encoding such as is needed for live-migration.
+
+Example
+old buffer:
+1001 zeros
+05 06 07 08 09 0a 0b 0c 0d 0e 0f 10 11 12 13 68 00 00 6b 00 6d
+3074 zeros
+
+new buffer:
+1001 zeros
+01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f 68 00 00 67 00 69
+3074 zeros
+
+encoded buffer:
+
+encoded length 24
+e9 07 0f 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f 03 01 67 01 01 69
+
+Usage
+======================
+1. Verify the destination QEMU version is able to decode the new format.
+    {qemu} info migrate_capabilities
+    {qemu} xbzrle: off , ...
+
+2. Activate xbzrle on both source and destination:
+   {qemu} migrate_set_capability xbzrle on
+
+3. Set the XBZRLE cache size - the cache size is in MBytes and should be a
+power of 2. The cache default value is 64MBytes. (on source only)
+    {qemu} migrate_set_cache_size 256m
+
+4. Start outgoing migration
+    {qemu} migrate -d tcp:destination.host:4444
+    {qemu} info migrate
+    capabilities: xbzrle: on
+    Migration status: active
+    transferred ram: A kbytes
+    remaining ram: B kbytes
+    total ram: C kbytes
+    total time: D milliseconds
+    duplicate: E pages
+    normal: F pages
+    normal bytes: G kbytes
+    cache size: H bytes
+    xbzrle transferred: I kbytes
+    xbzrle pages: J pages
+    xbzrle cache miss: K
+    xbzrle overflow : L
+
+xbzrle cache-miss: the number of cache misses to date - high cache-miss rate
+indicates that the cache size is set too low.
+xbzrle overflow: the number of overflows in the decoding which where the delta
+could not be compressed. This can happen if the changes in the pages are too
+large or there are many short changes; for example, changing every second byte
+(half a page).
+
+Testing: Testing indicated that live migration with XBZRLE was completed in 110
+seconds, whereas without it would not be able to complete.
+
+A simple synthetic memory r/w load generator:
+..    include <stdlib.h>
+..    include <stdio.h>
+..    int main()
+..    {
+..        char *buf = (char *) calloc(4096, 4096);
+..        while (1) {
+..            int i;
+..            for (i = 0; i < 4096 * 4; i++) {
+..                buf[i * 4096 / 4]++;
+..            }
+..            printf(".");
+..        }
+..    }

hmp-commands.hx

@@ -829,6 +829,26 @@ STEXI
 @item migrate_cancel
 @findex migrate_cancel
 Cancel the current VM migration.
+
+ETEXI
+
+    {
+        .name       = "migrate_set_cache_size",
+        .args_type  = "value:o",
+        .params     = "value",
+        .help       = "set cache size (in bytes) for XBZRLE migrations,"
+                      "the cache size will be rounded down to the nearest "
+                      "power of 2.\n"
+                      "The cache size affects the number of cache misses."
+                      "In case of a high cache miss ratio you need to increase"
+                      " the cache size",
+        .mhandler.cmd = hmp_migrate_set_cache_size,
+    },
+
+STEXI
+@item migrate_set_cache_size @var{value}
+@findex migrate_set_cache_size
+Set cache size to @var{value} (in bytes) for xbzrle migrations.
 ETEXI
 
     {
@@ -858,6 +878,20 @@ STEXI
 @item migrate_set_downtime @var{second}
 @findex migrate_set_downtime
 Set maximum tolerated downtime (in seconds) for migration.
+ETEXI
+
+    {
+        .name       = "migrate_set_capability",
+        .args_type  = "capability:s,state:b",
+        .params     = "capability state",
+        .help       = "Enable/Disable the usage of a capability for migration",
+        .mhandler.cmd = hmp_migrate_set_capability,
+    },
+
+STEXI
+@item migrate_set_capability @var{capability} @var{state}
+@findex migrate_set_capability
+Enable/Disable the usage of a capability @var{capability} for migration.
 ETEXI
 
     {
@@ -1417,6 +1451,10 @@ show CPU statistics
 show user network stack connection states
 @item info migrate
 show migration status
+@item info migrate_capabilities
+show current migration capabilities
+@item info migrate_cache_size
+show current migration XBZRLE cache size
 @item info balloon
 show balloon information
 @item info qtree

hmp.c

@@ -131,8 +131,21 @@ void hmp_info_mice(Monitor *mon)
 void hmp_info_migrate(Monitor *mon)
 {
     MigrationInfo *info;
+    MigrationCapabilityStatusList *caps, *cap;
 
     info = qmp_query_migrate(NULL);
+    caps = qmp_query_migrate_capabilities(NULL);
+
+    /* do not display parameters during setup */
+    if (info->has_status && caps) {
+        monitor_printf(mon, "capabilities: ");
+        for (cap = caps; cap; cap = cap->next) {
+            monitor_printf(mon, "%s: %s ",
+                           MigrationCapability_lookup[cap->value->capability],
+                           cap->value->state ? "on" : "off");
+        }
+        monitor_printf(mon, "\n");
+    }
 
     if (info->has_status) {
         monitor_printf(mon, "Migration status: %s\n", info->status);
@@ -147,6 +160,12 @@ void hmp_info_migrate(Monitor *mon)
                        info->ram->total >> 10);
         monitor_printf(mon, "total time: %" PRIu64 " milliseconds\n",
                        info->ram->total_time);
+        monitor_printf(mon, "duplicate: %" PRIu64 " pages\n",
+                       info->ram->duplicate);
+        monitor_printf(mon, "normal: %" PRIu64 " pages\n",
+                       info->ram->normal);
+        monitor_printf(mon, "normal bytes: %" PRIu64 " kbytes\n",
+                       info->ram->normal_bytes >> 10);
     }
 
     if (info->has_disk) {
@@ -158,7 +177,46 @@ void hmp_info_migrate(Monitor *mon)
                        info->disk->total >> 10);
     }
 
+    if (info->has_xbzrle_cache) {
+        monitor_printf(mon, "cache size: %" PRIu64 " bytes\n",
+                       info->xbzrle_cache->cache_size);
+        monitor_printf(mon, "xbzrle transferred: %" PRIu64 " kbytes\n",
+                       info->xbzrle_cache->bytes >> 10);
+        monitor_printf(mon, "xbzrle pages: %" PRIu64 " pages\n",
+                       info->xbzrle_cache->pages);
+        monitor_printf(mon, "xbzrle cache miss: %" PRIu64 "\n",
+                       info->xbzrle_cache->cache_miss);
+        monitor_printf(mon, "xbzrle overflow : %" PRIu64 "\n",
+                       info->xbzrle_cache->overflow);
+    }
+
     qapi_free_MigrationInfo(info);
+    qapi_free_MigrationCapabilityStatusList(caps);
+}
+
+void hmp_info_migrate_capabilities(Monitor *mon)
+{
+    MigrationCapabilityStatusList *caps, *cap;
+
+    caps = qmp_query_migrate_capabilities(NULL);
+
+    if (caps) {
+        monitor_printf(mon, "capabilities: ");
+        for (cap = caps; cap; cap = cap->next) {
+            monitor_printf(mon, "%s: %s ",
+                           MigrationCapability_lookup[cap->value->capability],
+                           cap->value->state ? "on" : "off");
+        }
+        monitor_printf(mon, "\n");
+    }
+
+    qapi_free_MigrationCapabilityStatusList(caps);
+}
+
+void hmp_info_migrate_cache_size(Monitor *mon)
+{
+    monitor_printf(mon, "xbzrel cache size: %" PRId64 " kbytes\n",
+                   qmp_query_migrate_cache_size(NULL) >> 10);
 }
 
 void hmp_info_cpus(Monitor *mon)
@@ -731,12 +789,57 @@ void hmp_migrate_set_downtime(Monitor *mon, const QDict *qdict)
     qmp_migrate_set_downtime(value, NULL);
 }
 
+void hmp_migrate_set_cache_size(Monitor *mon, const QDict *qdict)
+{
+    int64_t value = qdict_get_int(qdict, "value");
+    Error *err = NULL;
+
+    qmp_migrate_set_cache_size(value, &err);
+    if (err) {
+        monitor_printf(mon, "%s\n", error_get_pretty(err));
+        error_free(err);
+        return;
+    }
+}
+
 void hmp_migrate_set_speed(Monitor *mon, const QDict *qdict)
 {
     int64_t value = qdict_get_int(qdict, "value");
     qmp_migrate_set_speed(value, NULL);
 }
 
+void hmp_migrate_set_capability(Monitor *mon, const QDict *qdict)
+{
+    const char *cap = qdict_get_str(qdict, "capability");
+    bool state = qdict_get_bool(qdict, "state");
+    Error *err = NULL;
+    MigrationCapabilityStatusList *caps = g_malloc0(sizeof(*caps));
+    int i;
+
+    for (i = 0; i < MIGRATION_CAPABILITY_MAX; i++) {
+        if (strcmp(cap, MigrationCapability_lookup[i]) == 0) {
+            caps->value = g_malloc0(sizeof(*caps->value));
+            caps->value->capability = i;
+            caps->value->state = state;
+            caps->next = NULL;
+            qmp_migrate_set_capabilities(caps, &err);
+            break;
+        }
+    }
+
+    if (i == MIGRATION_CAPABILITY_MAX) {
+        error_set(&err, QERR_INVALID_PARAMETER, cap);
+    }
+
+    qapi_free_MigrationCapabilityStatusList(caps);
+
+    if (err) {
+        monitor_printf(mon, "migrate_set_parameter: %s\n",
+                       error_get_pretty(err));
+        error_free(err);
+    }
+}
+
 void hmp_set_password(Monitor *mon, const QDict *qdict)
 {
     const char *protocol  = qdict_get_str(qdict, "protocol");

hmp.h

@@ -25,6 +25,8 @@ void hmp_info_uuid(Monitor *mon);
 void hmp_info_chardev(Monitor *mon);
 void hmp_info_mice(Monitor *mon);
 void hmp_info_migrate(Monitor *mon);
+void hmp_info_migrate_capabilities(Monitor *mon);
+void hmp_info_migrate_cache_size(Monitor *mon);
 void hmp_info_cpus(Monitor *mon);
 void hmp_info_block(Monitor *mon);
 void hmp_info_blockstats(Monitor *mon);
@@ -51,6 +53,8 @@ void hmp_snapshot_blkdev(Monitor *mon, const QDict *qdict);
 void hmp_migrate_cancel(Monitor *mon, const QDict *qdict);
 void hmp_migrate_set_downtime(Monitor *mon, const QDict *qdict);
 void hmp_migrate_set_speed(Monitor *mon, const QDict *qdict);
+void hmp_migrate_set_capability(Monitor *mon, const QDict *qdict);
+void hmp_migrate_set_cache_size(Monitor *mon, const QDict *qdict);
 void hmp_set_password(Monitor *mon, const QDict *qdict);
 void hmp_expire_password(Monitor *mon, const QDict *qdict);
 void hmp_eject(Monitor *mon, const QDict *qdict);

include/qemu/page_cache.h

@@ -0,0 +1,79 @@
+/*
+ * Page cache for QEMU
+ * The cache is base on a hash of the page address
+ *
+ * Copyright 2012 Red Hat, Inc. and/or its affiliates
+ *
+ * Authors:
+ *  Orit Wasserman  <owasserm@redhat.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 PAGE_CACHE_H
+#define PAGE_CACHE_H
+
+/* Page cache for storing guest pages */
+typedef struct PageCache PageCache;
+
+/**
+ * cache_init: Initialize the page cache
+ *
+ *
+ * Returns new allocated cache or NULL on error
+ *
+ * @cache pointer to the PageCache struct
+ * @num_pages: cache maximal number of cached pages
+ * @page_size: cache page size
+ */
+PageCache *cache_init(int64_t num_pages, unsigned int page_size);
+
+/**
+ * cache_fini: free all cache resources
+ * @cache pointer to the PageCache struct
+ */
+void cache_fini(PageCache *cache);
+
+/**
+ * cache_is_cached: Checks to see if the page is cached
+ *
+ * Returns %true if page is cached
+ *
+ * @cache pointer to the PageCache struct
+ * @addr: page addr
+ */
+bool cache_is_cached(const PageCache *cache, uint64_t addr);
+
+/**
+ * get_cached_data: Get the data cached for an addr
+ *
+ * Returns pointer to the data cached or NULL if not cached
+ *
+ * @cache pointer to the PageCache struct
+ * @addr: page addr
+ */
+uint8_t *get_cached_data(const PageCache *cache, uint64_t addr);
+
+/**
+ * cache_insert: insert the page into the cache. the previous value will be overwritten
+ *
+ * @cache pointer to the PageCache struct
+ * @addr: page address
+ * @pdata: pointer to the page
+ */
+void cache_insert(PageCache *cache, uint64_t addr, uint8_t *pdata);
+
+/**
+ * cache_resize: resize the page cache. In case of size reduction the extra
+ * pages will be freed
+ *
+ * Returns -1 on error new cache size on success
+ *
+ * @cache pointer to the PageCache struct
+ * @num_pages: new page cache size (in pages)
+ */
+int64_t cache_resize(PageCache *cache, int64_t num_pages);
+
+#endif

migration.c

@@ -43,6 +43,9 @@ enum {
 
 #define MAX_THROTTLE  (32 << 20)      /* Migration speed throttling */
 
+/* Migration XBZRLE default cache size */
+#define DEFAULT_MIGRATE_CACHE_SIZE (64 * 1024 * 1024)
+
 static NotifierList migration_state_notifiers =
     NOTIFIER_LIST_INITIALIZER(migration_state_notifiers);
 
@@ -55,6 +58,7 @@ static MigrationState *migrate_get_current(void)
     static MigrationState current_migration = {
         .state = MIG_STATE_SETUP,
         .bandwidth_limit = MAX_THROTTLE,
+        .xbzrle_cache_size = DEFAULT_MIGRATE_CACHE_SIZE,
     };
 
     return &current_migration;
@@ -113,6 +117,43 @@ uint64_t migrate_max_downtime(void)
     return max_downtime;
 }
 
+MigrationCapabilityStatusList *qmp_query_migrate_capabilities(Error **errp)
+{
+    MigrationCapabilityStatusList *head = NULL;
+    MigrationCapabilityStatusList *caps;
+    MigrationState *s = migrate_get_current();
+    int i;
+
+    for (i = 0; i < MIGRATION_CAPABILITY_MAX; i++) {
+        if (head == NULL) {
+            head = g_malloc0(sizeof(*caps));
+            caps = head;
+        } else {
+            caps->next = g_malloc0(sizeof(*caps));
+            caps = caps->next;
+        }
+        caps->value =
+            g_malloc(sizeof(*caps->value));
+        caps->value->capability = i;
+        caps->value->state = s->enabled_capabilities[i];
+    }
+
+    return head;
+}
+
+static void get_xbzrle_cache_stats(MigrationInfo *info)
+{
+    if (migrate_use_xbzrle()) {
+        info->has_xbzrle_cache = true;
+        info->xbzrle_cache = g_malloc0(sizeof(*info->xbzrle_cache));
+        info->xbzrle_cache->cache_size = migrate_xbzrle_cache_size();
+        info->xbzrle_cache->bytes = xbzrle_mig_bytes_transferred();
+        info->xbzrle_cache->pages = xbzrle_mig_pages_transferred();
+        info->xbzrle_cache->cache_miss = xbzrle_mig_pages_cache_miss();
+        info->xbzrle_cache->overflow = xbzrle_mig_pages_overflow();
+    }
+}
+
 MigrationInfo *qmp_query_migrate(Error **errp)
 {
     MigrationInfo *info = g_malloc0(sizeof(*info));
@@ -133,6 +174,9 @@ MigrationInfo *qmp_query_migrate(Error **errp)
         info->ram->total = ram_bytes_total();
         info->ram->total_time = qemu_get_clock_ms(rt_clock)
             - s->total_time;
+        info->ram->duplicate = dup_mig_pages_transferred();
+        info->ram->normal = norm_mig_pages_transferred();
+        info->ram->normal_bytes = norm_mig_bytes_transferred();
 
         if (blk_mig_active()) {
             info->has_disk = true;
@@ -141,8 +185,12 @@ MigrationInfo *qmp_query_migrate(Error **errp)
             info->disk->remaining = blk_mig_bytes_remaining();
             info->disk->total = blk_mig_bytes_total();
         }
+
+        get_xbzrle_cache_stats(info);
         break;
     case MIG_STATE_COMPLETED:
+        get_xbzrle_cache_stats(info);
+
         info->has_status = true;
         info->status = g_strdup("completed");
 
@@ -152,6 +200,9 @@ MigrationInfo *qmp_query_migrate(Error **errp)
         info->ram->remaining = 0;
         info->ram->total = ram_bytes_total();
         info->ram->total_time = s->total_time;
+        info->ram->duplicate = dup_mig_pages_transferred();
+        info->ram->normal = norm_mig_pages_transferred();
+        info->ram->normal_bytes = norm_mig_bytes_transferred();
         break;
     case MIG_STATE_ERROR:
         info->has_status = true;
@@ -166,6 +217,22 @@ MigrationInfo *qmp_query_migrate(Error **errp)
     return info;
 }
 
+void qmp_migrate_set_capabilities(MigrationCapabilityStatusList *params,
+                                  Error **errp)
+{
+    MigrationState *s = migrate_get_current();
+    MigrationCapabilityStatusList *cap;
+
+    if (s->state == MIG_STATE_ACTIVE) {
+        error_set(errp, QERR_MIGRATION_ACTIVE);
+        return;
+    }
+
+    for (cap = params; cap; cap = cap->next) {
+        s->enabled_capabilities[cap->value->capability] = cap->value->state;
+    }
+}
+
 /* shared migration helpers */
 
 static int migrate_fd_cleanup(MigrationState *s)
@@ -375,10 +442,18 @@ static MigrationState *migrate_init(const MigrationParams *params)
 {
     MigrationState *s = migrate_get_current();
     int64_t bandwidth_limit = s->bandwidth_limit;
+    bool enabled_capabilities[MIGRATION_CAPABILITY_MAX];
+    int64_t xbzrle_cache_size = s->xbzrle_cache_size;
+
+    memcpy(enabled_capabilities, s->enabled_capabilities,
+           sizeof(enabled_capabilities));
 
     memset(s, 0, sizeof(*s));
     s->bandwidth_limit = bandwidth_limit;
     s->params = *params;
+    memcpy(s->enabled_capabilities, enabled_capabilities,
+           sizeof(enabled_capabilities));
+    s->xbzrle_cache_size = xbzrle_cache_size;
 
     s->bandwidth_limit = bandwidth_limit;
     s->state = MIG_STATE_SETUP;
@@ -459,6 +534,25 @@ void qmp_migrate_cancel(Error **errp)
     migrate_fd_cancel(migrate_get_current());
 }
 
+void qmp_migrate_set_cache_size(int64_t value, Error **errp)
+{
+    MigrationState *s = migrate_get_current();
+
+    /* Check for truncation */
+    if (value != (size_t)value) {
+        error_set(errp, QERR_INVALID_PARAMETER_VALUE, "cache size",
+                  "exceeding address space");
+        return;
+    }
+
+    s->xbzrle_cache_size = xbzrle_cache_resize(value);
+}
+
+int64_t qmp_query_migrate_cache_size(Error **errp)
+{
+    return migrate_xbzrle_cache_size();
+}
+
 void qmp_migrate_set_speed(int64_t value, Error **errp)
 {
     MigrationState *s;
@@ -478,3 +572,21 @@ void qmp_migrate_set_downtime(double value, Error **errp)
     value = MAX(0, MIN(UINT64_MAX, value));
     max_downtime = (uint64_t)value;
 }
+
+int migrate_use_xbzrle(void)
+{
+    MigrationState *s;
+
+    s = migrate_get_current();
+
+    return s->enabled_capabilities[MIGRATION_CAPABILITY_XBZRLE];
+}
+
+int64_t migrate_xbzrle_cache_size(void)
+{
+    MigrationState *s;
+
+    s = migrate_get_current();
+
+    return s->xbzrle_cache_size;
+}

migration.h

@@ -19,6 +19,7 @@
 #include "notify.h"
 #include "error.h"
 #include "vmstate.h"
+#include "qapi-types.h"
 
 struct MigrationParams {
     bool blk;
@@ -39,6 +40,8 @@ struct MigrationState
     void *opaque;
     MigrationParams params;
     int64_t total_time;
+    bool enabled_capabilities[MIGRATION_CAPABILITY_MAX];
+    int64_t xbzrle_cache_size;
 };
 
 void process_incoming_migration(QEMUFile *f);
@@ -84,6 +87,15 @@ uint64_t ram_bytes_total(void);
 
 extern SaveVMHandlers savevm_ram_handlers;
 
+uint64_t dup_mig_bytes_transferred(void);
+uint64_t dup_mig_pages_transferred(void);
+uint64_t norm_mig_bytes_transferred(void);
+uint64_t norm_mig_pages_transferred(void);
+uint64_t xbzrle_mig_bytes_transferred(void);
+uint64_t xbzrle_mig_pages_transferred(void);
+uint64_t xbzrle_mig_pages_overflow(void);
+uint64_t xbzrle_mig_pages_cache_miss(void);
+
 /**
  * @migrate_add_blocker - prevent migration from proceeding
  *
@@ -98,4 +110,13 @@ void migrate_add_blocker(Error *reason);
  */
 void migrate_del_blocker(Error *reason);
 
+int xbzrle_encode_buffer(uint8_t *old_buf, uint8_t *new_buf, int slen,
+                         uint8_t *dst, int dlen);
+int xbzrle_decode_buffer(uint8_t *src, int slen, uint8_t *dst, int dlen);
+
+int migrate_use_xbzrle(void);
+int64_t migrate_xbzrle_cache_size(void);
+
+int64_t xbzrle_cache_resize(int64_t new_size);
+
 #endif

monitor.c

@@ -2654,6 +2654,20 @@ static mon_cmd_t info_cmds[] = {
         .help       = "show migration status",
         .mhandler.info = hmp_info_migrate,
     },
+    {
+        .name       = "migrate_capabilities",
+        .args_type  = "",
+        .params     = "",
+        .help       = "show current migration capabilities",
+        .mhandler.info = hmp_info_migrate_capabilities,
+    },
+    {
+        .name       = "migrate_cache_size",
+        .args_type  = "",
+        .params     = "",
+        .help       = "show current migration xbzrle cache size",
+        .mhandler.info = hmp_info_migrate_cache_size,
+    },
     {
         .name       = "balloon",
         .args_type  = "",

page_cache.c

@@ -0,0 +1,218 @@
+/*
+ * Page cache for QEMU
+ * The cache is base on a hash of the page address
+ *
+ * Copyright 2012 Red Hat, Inc. and/or its affiliates
+ *
+ * Authors:
+ *  Orit Wasserman  <owasserm@redhat.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.
+ *
+ */
+
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <strings.h>
+#include <string.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <stdbool.h>
+#include <glib.h>
+#include <strings.h>
+
+#include "qemu-common.h"
+#include "qemu/page_cache.h"
+
+#ifdef DEBUG_CACHE
+#define DPRINTF(fmt, ...) \
+    do { fprintf(stdout, "cache: " fmt, ## __VA_ARGS__); } while (0)
+#else
+#define DPRINTF(fmt, ...) \
+    do { } while (0)
+#endif
+
+typedef struct CacheItem CacheItem;
+
+struct CacheItem {
+    uint64_t it_addr;
+    uint64_t it_age;
+    uint8_t *it_data;
+};
+
+struct PageCache {
+    CacheItem *page_cache;
+    unsigned int page_size;
+    int64_t max_num_items;
+    uint64_t max_item_age;
+    int64_t num_items;
+};
+
+PageCache *cache_init(int64_t num_pages, unsigned int page_size)
+{
+    int64_t i;
+
+    PageCache *cache;
+
+    if (num_pages <= 0) {
+        DPRINTF("invalid number of pages\n");
+        return NULL;
+    }
+
+    cache = g_malloc(sizeof(*cache));
+
+    /* round down to the nearest power of 2 */
+    if (!is_power_of_2(num_pages)) {
+        num_pages = pow2floor(num_pages);
+        DPRINTF("rounding down to %" PRId64 "\n", num_pages);
+    }
+    cache->page_size = page_size;
+    cache->num_items = 0;
+    cache->max_item_age = 0;
+    cache->max_num_items = num_pages;
+
+    DPRINTF("Setting cache buckets to %" PRId64 "\n", cache->max_num_items);
+
+    cache->page_cache = g_malloc((cache->max_num_items) *
+                                 sizeof(*cache->page_cache));
+
+    for (i = 0; i < cache->max_num_items; i++) {
+        cache->page_cache[i].it_data = NULL;
+        cache->page_cache[i].it_age = 0;
+        cache->page_cache[i].it_addr = -1;
+    }
+
+    return cache;
+}
+
+void cache_fini(PageCache *cache)
+{
+    int64_t i;
+
+    g_assert(cache);
+    g_assert(cache->page_cache);
+
+    for (i = 0; i < cache->max_num_items; i++) {
+        g_free(cache->page_cache[i].it_data);
+    }
+
+    g_free(cache->page_cache);
+    cache->page_cache = NULL;
+}
+
+static size_t cache_get_cache_pos(const PageCache *cache,
+                                  uint64_t address)
+{
+    size_t pos;
+
+    g_assert(cache->max_num_items);
+    pos = (address / cache->page_size) & (cache->max_num_items - 1);
+    return pos;
+}
+
+bool cache_is_cached(const PageCache *cache, uint64_t addr)
+{
+    size_t pos;
+
+    g_assert(cache);
+    g_assert(cache->page_cache);
+
+    pos = cache_get_cache_pos(cache, addr);
+
+    return (cache->page_cache[pos].it_addr == addr);
+}
+
+static CacheItem *cache_get_by_addr(const PageCache *cache, uint64_t addr)
+{
+    size_t pos;
+
+    g_assert(cache);
+    g_assert(cache->page_cache);
+
+    pos = cache_get_cache_pos(cache, addr);
+
+    return &cache->page_cache[pos];
+}
+
+uint8_t *get_cached_data(const PageCache *cache, uint64_t addr)
+{
+    return cache_get_by_addr(cache, addr)->it_data;
+}
+
+void cache_insert(PageCache *cache, uint64_t addr, uint8_t *pdata)
+{
+
+    CacheItem *it = NULL;
+
+    g_assert(cache);
+    g_assert(cache->page_cache);
+
+    /* actual update of entry */
+    it = cache_get_by_addr(cache, addr);
+
+    if (!it->it_data) {
+        cache->num_items++;
+    }
+
+    it->it_data = pdata;
+    it->it_age = ++cache->max_item_age;
+    it->it_addr = addr;
+}
+
+int64_t cache_resize(PageCache *cache, int64_t new_num_pages)
+{
+    PageCache *new_cache;
+    int64_t i;
+
+    CacheItem *old_it, *new_it;
+
+    g_assert(cache);
+
+    /* cache was not inited */
+    if (cache->page_cache == NULL) {
+        return -1;
+    }
+
+    /* same size */
+    if (pow2floor(new_num_pages) == cache->max_num_items) {
+        return cache->max_num_items;
+    }
+
+    new_cache = cache_init(new_num_pages, cache->page_size);
+    if (!(new_cache)) {
+        DPRINTF("Error creating new cache\n");
+        return -1;
+    }
+
+    /* move all data from old cache */
+    for (i = 0; i < cache->max_num_items; i++) {
+        old_it = &cache->page_cache[i];
+        if (old_it->it_addr != -1) {
+            /* check for collision, if there is, keep MRU page */
+            new_it = cache_get_by_addr(new_cache, old_it->it_addr);
+            if (new_it->it_data) {
+                /* keep the MRU page */
+                if (new_it->it_age >= old_it->it_age) {
+                    g_free(old_it->it_data);
+                } else {
+                    g_free(new_it->it_data);
+                    new_it->it_data = old_it->it_data;
+                    new_it->it_age = old_it->it_age;
+                    new_it->it_addr = old_it->it_addr;
+                }
+            } else {
+                cache_insert(new_cache, old_it->it_addr, old_it->it_data);
+            }
+        }
+    }
+
+    cache->page_cache = new_cache->page_cache;
+    cache->max_num_items = new_cache->max_num_items;
+    cache->num_items = new_cache->num_items;
+
+    g_free(new_cache);
+
+    return cache->max_num_items;
+}

qapi-schema.json

@@ -260,15 +260,43 @@
 #
 # @total: total amount of bytes involved in the migration process
 #
-# @total_time: tota0l amount of ms since migration started.  If
+# @total-time: total amount of ms since migration started.  If
 #        migration has ended, it returns the total migration
 #        time. (since 1.2)
 #
-# Since: 0.14.0.
+# @duplicate: number of duplicate pages (since 1.2)
+#
+# @normal : number of normal pages (since 1.2)
+#
+# @normal-bytes : number of normal bytes sent (since 1.2)
+#
+# Since: 0.14.0
 ##
 { 'type': 'MigrationStats',
   'data': {'transferred': 'int', 'remaining': 'int', 'total': 'int' ,
-           'total_time': 'int' } }
+           'total-time': 'int', 'duplicate': 'int', 'normal': 'int',
+           'normal-bytes': 'int' } }
+
+##
+# @XBZRLECacheStats
+#
+# Detailed XBZRLE migration cache statistics
+#
+# @cache-size: XBZRLE cache size
+#
+# @bytes: amount of bytes already transferred to the target VM
+#
+# @pages: amount of pages transferred to the target VM
+#
+# @cache-miss: number of cache miss
+#
+# @overflow: number of overflows
+#
+# Since: 1.2
+##
+{ 'type': 'XBZRLECacheStats',
+  'data': {'cache-size': 'int', 'bytes': 'int', 'pages': 'int',
+           'cache-miss': 'int', 'overflow': 'int' } }
 
 ##
 # @MigrationInfo
@@ -288,11 +316,16 @@
 #        status, only returned if status is 'active' and it is a block
 #        migration
 #
+# @xbzrle-cache: #optional @XBZRLECacheStats containing detailed XBZRLE
+#                migration statistics, only returned if XBZRLE feature is on and
+#                status is 'active' or 'completed' (since 1.2)
+#
 # Since: 0.14.0
 ##
 { 'type': 'MigrationInfo',
   'data': {'*status': 'str', '*ram': 'MigrationStats',
-           '*disk': 'MigrationStats'} }
+           '*disk': 'MigrationStats',
+           '*xbzrle-cache': 'XBZRLECacheStats'} }
 
 ##
 # @query-migrate
@@ -305,6 +338,57 @@
 ##
 { 'command': 'query-migrate', 'returns': 'MigrationInfo' }
 
+##
+# @MigrationCapability
+#
+# Migration capabilities enumeration
+#
+# @xbzrle: Migration supports xbzrle (Xor Based Zero Run Length Encoding).
+#          This feature allows us to minimize migration traffic for certain work
+#          loads, by sending compressed difference of the pages
+#
+# Since: 1.2
+##
+{ 'enum': 'MigrationCapability',
+  'data': ['xbzrle'] }
+
+##
+# @MigrationCapabilityStatus
+#
+# Migration capability information
+#
+# @capability: capability enum
+#
+# @state: capability state bool
+#
+# Since: 1.2
+##
+{ 'type': 'MigrationCapabilityStatus',
+  'data': { 'capability' : 'MigrationCapability', 'state' : 'bool' } }
+
+##
+# @migrate-set-capabilities
+#
+# Enable/Disable the following migration capabilities (like xbzrle)
+#
+# @capabilities: json array of capability modifications to make
+#
+# Since: 1.2
+##
+{ 'command': 'migrate-set-capabilities',
+  'data': { 'capabilities': ['MigrationCapabilityStatus'] } }
+
+##
+# @query-migrate-capabilities
+#
+# Returns information about the current migration capabilities status
+#
+# Returns: @MigrationCapabilitiesStatus
+#
+# Since: 1.2
+##
+{ 'command': 'query-migrate-capabilities', 'returns':   ['MigrationCapabilityStatus']}
+
 ##
 # @MouseInfo:
 #
@@ -1343,6 +1427,33 @@
 ##
 { 'command': 'migrate_set_speed', 'data': {'value': 'int'} }
 
+##
+# @migrate-set-cache-size
+#
+# Set XBZRLE cache size
+#
+# @value: cache size in bytes
+#
+# The size will be rounded down to the nearest power of 2.
+# The cache size can be modified before and during ongoing migration
+#
+# Returns: nothing on success
+#
+# Since: 1.2
+##
+{ 'command': 'migrate-set-cache-size', 'data': {'value': 'int'} }
+
+##
+# @query-migrate-cache-size
+#
+# query XBZRLE cache size
+#
+# Returns: XBZRLE cache size in bytes
+#
+# Since: 1.2
+##
+{ 'command': 'query-migrate-cache-size', 'returns': 'int' }
+
 ##
 # @ObjectPropertyInfo:
 #

qemu-common.h

@@ -1,3 +1,4 @@
+
 /* Common header file that is included by all of qemu.  */
 #ifndef QEMU_COMMON_H
 #define QEMU_COMMON_H
@@ -429,6 +430,26 @@ static inline uint64_t muldiv64(uint64_t a, uint32_t b, uint32_t c)
 /* Round number up to multiple */
 #define QEMU_ALIGN_UP(n, m) QEMU_ALIGN_DOWN((n) + (m) - 1, (m))
 
+static inline bool is_power_of_2(uint64_t value)
+{
+    if (!value) {
+        return 0;
+    }
+
+    return !(value & (value - 1));
+}
+
+/* round down to the nearest power of 2*/
+int64_t pow2floor(int64_t value);
+
 #include "module.h"
 
+/*
+ * Implementation of ULEB128 (http://en.wikipedia.org/wiki/LEB128)
+ * Input is limited to 14-bit numbers
+ */
+
+int uleb128_encode_small(uint8_t *out, uint32_t n);
+int uleb128_decode_small(const uint8_t *in, uint32_t *n);
+
 #endif

qmp-commands.hx

@@ -519,6 +519,50 @@ Example:
 -> { "execute": "migrate_cancel" }
 <- { "return": {} }
 
+EQMP
+{
+        .name       = "migrate-set-cache-size",
+        .args_type  = "value:o",
+        .mhandler.cmd_new = qmp_marshal_input_migrate_set_cache_size,
+    },
+
+SQMP
+migrate-set-cache-size
+---------------------
+
+Set cache size to be used by XBZRLE migration, the cache size will be rounded
+down to the nearest power of 2
+
+Arguments:
+
+- "value": cache size in bytes (json-int)
+
+Example:
+
+-> { "execute": "migrate-set-cache-size", "arguments": { "value": 536870912 } }
+<- { "return": {} }
+
+EQMP
+    {
+        .name       = "query-migrate-cache-size",
+        .args_type  = "",
+        .mhandler.cmd_new = qmp_marshal_input_query_migrate_cache_size,
+    },
+
+SQMP
+query-migrate-cache-size
+---------------------
+
+Show cache size to be used by XBZRLE migration
+
+returns a json-object with the following information:
+- "size" : json-int
+
+Example:
+
+-> { "execute": "query-migrate-cache-size" }
+<- { "return": 67108864 }
+
 EQMP
 
     {
@@ -2078,12 +2122,24 @@ The main json-object contains the following:
          - "transferred": amount transferred (json-int)
          - "remaining": amount remaining (json-int)
          - "total": total (json-int)
+         - "total-time": total amount of ms since migration started.  If
+                         migration has ended, it returns the total migration time
+                         (json-int)
+         - "duplicate": number of duplicated pages (json-int)
+         - "normal" : number of normal pages transferred (json-int)
+         - "normal-bytes" : number of normal bytes transferred (json-int)
 - "disk": only present if "status" is "active" and it is a block migration,
   it is a json-object with the following disk information (in bytes):
          - "transferred": amount transferred (json-int)
          - "remaining": amount remaining (json-int)
          - "total": total (json-int)
-
+- "xbzrle-cache": only present if XBZRLE is active.
+  It is a json-object with the following XBZRLE information:
+         - "cache-size": XBZRLE cache size
+         - "bytes": total XBZRLE bytes transferred
+         - "pages": number of XBZRLE compressed pages
+         - "cache-miss": number of cache misses
+         - "overflow": number of XBZRLE overflows
 Examples:
 
 1. Before the first migration
@@ -2094,7 +2150,19 @@ Examples:
 2. Migration is done and has succeeded
 
 -> { "execute": "query-migrate" }
-<- { "return": { "status": "completed" } }
+<- { "return": {
+        "status": "completed",
+        "ram":{
+          "transferred":123,
+          "remaining":123,
+          "total":246,
+          "total-time":12345,
+          "duplicate":123,
+          "normal":123,
+          "normal-bytes":123456
+        }
+     }
+   }
 
 3. Migration is done and has failed
 
@@ -2110,7 +2178,11 @@ Examples:
          "ram":{
             "transferred":123,
             "remaining":123,
-            "total":246
+            "total":246,
+            "total-time":12345,
+            "duplicate":123,
+            "normal":123,
+            "normal-bytes":123456
          }
       }
    }
@@ -2124,7 +2196,11 @@ Examples:
          "ram":{
             "total":1057024,
             "remaining":1053304,
-            "transferred":3720
+            "transferred":3720,
+            "total-time":12345,
+            "duplicate":123,
+            "normal":123,
+            "normal-bytes":123456
          },
          "disk":{
             "total":20971520,
@@ -2134,6 +2210,32 @@ Examples:
       }
    }
 
+6. Migration is being performed and XBZRLE is active:
+
+-> { "execute": "query-migrate" }
+<- {
+      "return":{
+         "status":"active",
+         "capabilities" : [ { "capability": "xbzrle", "state" : true } ],
+         "ram":{
+            "total":1057024,
+            "remaining":1053304,
+            "transferred":3720,
+            "total-time":12345,
+            "duplicate":10,
+            "normal":3333,
+            "normal-bytes":3412992
+         },
+         "xbzrle-cache":{
+            "cache-size":67108864,
+            "bytes":20971520,
+            "pages":2444343,
+            "cache-miss":2244,
+            "overflow":34434
+         }
+      }
+   }
+
 EQMP
 
     {
@@ -2142,6 +2244,55 @@ EQMP
         .mhandler.cmd_new = qmp_marshal_input_query_migrate,
     },
 
+SQMP
+migrate-set-capabilities
+-------
+
+Enable/Disable migration capabilities
+
+- "xbzrle": xbzrle support
+
+Arguments:
+
+Example:
+
+-> { "execute": "migrate-set-capabilities" , "arguments":
+     { "capabilities": [ { "capability": "xbzrle", "state": true } ] } }
+
+EQMP
+
+    {
+        .name       = "migrate-set-capabilities",
+        .args_type  = "capabilities:O",
+        .params     = "capability:s,state:b",
+	.mhandler.cmd_new = qmp_marshal_input_migrate_set_capabilities,
+    },
+SQMP
+query-migrate-capabilities
+-------
+
+Query current migration capabilities
+
+- "capabilities": migration capabilities state
+         - "xbzrle" : XBZRLE state (json-bool)
+
+Arguments:
+
+Example:
+
+-> { "execute": "query-migrate-capabilities" }
+<- { "return": {
+        "capabilities" :  [ { "capability" : "xbzrle", "state" : false } ]
+     }
+   }
+EQMP
+
+    {
+        .name       = "query-migrate-capabilities",
+        .args_type  = "",
+        .mhandler.cmd_new = qmp_marshal_input_query_migrate_capabilities,
+    },
+
 SQMP
 query-balloon
 -------------

savevm.c

@@ -2392,3 +2392,162 @@ void vmstate_register_ram_global(MemoryRegion *mr)
 {
     vmstate_register_ram(mr, NULL);
 }
+
+/*
+  page = zrun nzrun
+       | zrun nzrun page
+
+  zrun = length
+
+  nzrun = length byte...
+
+  length = uleb128 encoded integer
+ */
+int xbzrle_encode_buffer(uint8_t *old_buf, uint8_t *new_buf, int slen,
+                         uint8_t *dst, int dlen)
+{
+    uint32_t zrun_len = 0, nzrun_len = 0;
+    int d = 0, i = 0;
+    long res, xor;
+    uint8_t *nzrun_start = NULL;
+
+    g_assert(!(((uintptr_t)old_buf | (uintptr_t)new_buf | slen) %
+               sizeof(long)));
+
+    while (i < slen) {
+        /* overflow */
+        if (d + 2 > dlen) {
+            return -1;
+        }
+
+        /* not aligned to sizeof(long) */
+        res = (slen - i) % sizeof(long);
+        while (res && old_buf[i] == new_buf[i]) {
+            zrun_len++;
+            i++;
+            res--;
+        }
+
+        /* word at a time for speed */
+        if (!res) {
+            while (i < slen &&
+                   (*(long *)(old_buf + i)) == (*(long *)(new_buf + i))) {
+                i += sizeof(long);
+                zrun_len += sizeof(long);
+            }
+
+            /* go over the rest */
+            while (i < slen && old_buf[i] == new_buf[i]) {
+                zrun_len++;
+                i++;
+            }
+        }
+
+        /* buffer unchanged */
+        if (zrun_len == slen) {
+            return 0;
+        }
+
+        /* skip last zero run */
+        if (i == slen) {
+            return d;
+        }
+
+        d += uleb128_encode_small(dst + d, zrun_len);
+
+        zrun_len = 0;
+        nzrun_start = new_buf + i;
+
+        /* overflow */
+        if (d + 2 > dlen) {
+            return -1;
+        }
+        /* not aligned to sizeof(long) */
+        res = (slen - i) % sizeof(long);
+        while (res && old_buf[i] != new_buf[i]) {
+            i++;
+            nzrun_len++;
+            res--;
+        }
+
+        /* word at a time for speed, use of 32-bit long okay */
+        if (!res) {
+            /* truncation to 32-bit long okay */
+            long mask = 0x0101010101010101ULL;
+            while (i < slen) {
+                xor = *(long *)(old_buf + i) ^ *(long *)(new_buf + i);
+                if ((xor - mask) & ~xor & (mask << 7)) {
+                    /* found the end of an nzrun within the current long */
+                    while (old_buf[i] != new_buf[i]) {
+                        nzrun_len++;
+                        i++;
+                    }
+                    break;
+                } else {
+                    i += sizeof(long);
+                    nzrun_len += sizeof(long);
+                }
+            }
+        }
+
+        d += uleb128_encode_small(dst + d, nzrun_len);
+        /* overflow */
+        if (d + nzrun_len > dlen) {
+            return -1;
+        }
+        memcpy(dst + d, nzrun_start, nzrun_len);
+        d += nzrun_len;
+        nzrun_len = 0;
+    }
+
+    return d;
+}
+
+int xbzrle_decode_buffer(uint8_t *src, int slen, uint8_t *dst, int dlen)
+{
+    int i = 0, d = 0;
+    int ret;
+    uint32_t count = 0;
+
+    while (i < slen) {
+
+        /* zrun */
+        if ((slen - i) < 2) {
+            return -1;
+        }
+
+        ret = uleb128_decode_small(src + i, &count);
+        if (ret < 0 || (i && !count)) {
+            return -1;
+        }
+        i += ret;
+        d += count;
+
+        /* overflow */
+        if (d > dlen) {
+            return -1;
+        }
+
+        /* nzrun */
+        if ((slen - i) < 2) {
+            return -1;
+        }
+
+        ret = uleb128_decode_small(src + i, &count);
+        if (ret < 0 || !count) {
+            return -1;
+        }
+        i += ret;
+
+        /* overflow */
+        if (d + count > dlen || i + count > slen) {
+            return -1;
+        }
+
+        memcpy(dst + d, src + i, count);
+        d += count;
+        i += count;
+    }
+
+    return d;
+}