These changes are the raw update to qemu-2.6.

Collission happened in the following patches:

migration: do cleanup operation after completion(738df5b9)
Bug fix.(1750c932f86)
kvmclock: add a new function to update env->tsc.(b52baab2)

The code provided by the patches was already in the upstreamed
version.

Change-Id: I3cc11841a6a76ae20887b2e245710199e1ea7f9a
Signed-off-by: José Pekkarinen <jose.pekkarinen@nokia.com>

1 files changed, 1111 insertions, 219 deletions

diff --git a/qemu/migration/ram.c b/qemu/migration/ram.c
index 6249f6e60..3f057388c 100644
--- a/qemu/migration/ram.c
+++ b/qemu/migration/ram.c
@@ -25,13 +25,16 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
  * THE SOFTWARE.
  */
-#include <stdint.h>
+#include "qemu/osdep.h"
 #include <zlib.h>
+#include "qapi-event.h"
+#include "qemu/cutils.h"
 #include "qemu/bitops.h"
 #include "qemu/bitmap.h"
 #include "qemu/timer.h"
 #include "qemu/main-loop.h"
 #include "migration/migration.h"
+#include "migration/postcopy-ram.h"
 #include "exec/address-spaces.h"
 #include "migration/page_cache.h"
 #include "qemu/error-report.h"
@@ -47,9 +50,7 @@
     do { } while (0)
 #endif
 
-static bool mig_throttle_on;
 static int dirty_rate_high_cnt;
-static void check_guest_throttling(void);
 
 static uint64_t bitmap_sync_count;
 
@@ -221,12 +222,34 @@ 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 QemuMutex migration_bitmap_mutex;
 static uint64_t migration_dirty_pages;
 static uint32_t last_version;
 static bool ram_bulk_stage;
 
+/* used by the search for pages to send */
+struct PageSearchStatus {
+    /* Current block being searched */
+    RAMBlock    *block;
+    /* Current offset to search from */
+    ram_addr_t   offset;
+    /* Set once we wrap around */
+    bool         complete_round;
+};
+typedef struct PageSearchStatus PageSearchStatus;
+
+static struct BitmapRcu {
+    struct rcu_head rcu;
+    /* Main migration bitmap */
+    unsigned long *bmap;
+    /* bitmap of pages that haven't been sent even once
+     * only maintained and used in postcopy at the moment
+     * where it's used to send the dirtymap at the start
+     * of the postcopy phase
+     */
+    unsigned long *unsentmap;
+} *migration_bitmap_rcu;
+
 struct CompressParam {
     bool start;
     bool done;
@@ -243,7 +266,7 @@ struct DecompressParam {
     QemuMutex mutex;
     QemuCond cond;
     void *des;
-    uint8 *compbuf;
+    uint8_t *compbuf;
     int len;
 };
 typedef struct DecompressParam DecompressParam;
@@ -264,7 +287,6 @@ static bool quit_comp_thread;
 static bool quit_decomp_thread;
 static DecompressParam *decomp_param;
 static QemuThread *decompress_threads;
-static uint8_t *compressed_data_buf;
 
 static int do_compress_ram_page(CompressParam *param);
 
@@ -396,6 +418,29 @@ static size_t save_page_header(QEMUFile *f, RAMBlock *block, ram_addr_t offset)
     return size;
 }
 
+/* Reduce amount of guest cpu execution to hopefully slow down memory writes.
+ * If guest dirty memory rate is reduced below the rate at which we can
+ * transfer pages to the destination then we should be able to complete
+ * migration. Some workloads dirty memory way too fast and will not effectively
+ * converge, even with auto-converge.
+ */
+static void mig_throttle_guest_down(void)
+{
+    MigrationState *s = migrate_get_current();
+    uint64_t pct_initial =
+            s->parameters[MIGRATION_PARAMETER_X_CPU_THROTTLE_INITIAL];
+    uint64_t pct_icrement =
+            s->parameters[MIGRATION_PARAMETER_X_CPU_THROTTLE_INCREMENT];
+
+    /* We have not started throttling yet. Let's start it. */
+    if (!cpu_throttle_active()) {
+        cpu_throttle_set(pct_initial);
+    } else {
+        /* Throttling already on, just increase the rate */
+        cpu_throttle_set(cpu_throttle_get_percentage() + pct_icrement);
+    }
+}
+
 /* Update the xbzrle cache to reflect a page that's been sent as all 0.
  * The important thing is that a stale (not-yet-0'd) page be replaced
  * by the new data.
@@ -495,43 +540,60 @@ static int save_xbzrle_page(QEMUFile *f, uint8_t **current_data,
     return 1;
 }
 
-/* Called with rcu_read_lock() to protect migration_bitmap */
+/* Called with rcu_read_lock() to protect migration_bitmap
+ * rb: The RAMBlock  to search for dirty pages in
+ * start: Start address (typically so we can continue from previous page)
+ * ram_addr_abs: Pointer into which to store the address of the dirty page
+ *               within the global ram_addr space
+ *
+ * Returns: byte offset within memory region of the start of a dirty page
+ */
 static inline
-ram_addr_t migration_bitmap_find_and_reset_dirty(MemoryRegion *mr,
-                                                 ram_addr_t start)
+ram_addr_t migration_bitmap_find_dirty(RAMBlock *rb,
+                                       ram_addr_t start,
+                                       ram_addr_t *ram_addr_abs)
 {
-    unsigned long base = mr->ram_addr >> TARGET_PAGE_BITS;
+    unsigned long base = rb->offset >> 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);
+    uint64_t rb_size = rb->used_length;
+    unsigned long size = base + (rb_size >> TARGET_PAGE_BITS);
     unsigned long *bitmap;
 
     unsigned long next;
 
-    bitmap = atomic_rcu_read(&migration_bitmap);
+    bitmap = atomic_rcu_read(&migration_bitmap_rcu)->bmap;
     if (ram_bulk_stage && nr > base) {
         next = nr + 1;
     } else {
         next = find_next_bit(bitmap, size, nr);
     }
 
-    if (next < size) {
-        clear_bit(next, bitmap);
+    *ram_addr_abs = next << TARGET_PAGE_BITS;
+    return (next - base) << TARGET_PAGE_BITS;
+}
+
+static inline bool migration_bitmap_clear_dirty(ram_addr_t addr)
+{
+    bool ret;
+    int nr = addr >> TARGET_PAGE_BITS;
+    unsigned long *bitmap = atomic_rcu_read(&migration_bitmap_rcu)->bmap;
+
+    ret = test_and_clear_bit(nr, bitmap);
+
+    if (ret) {
         migration_dirty_pages--;
     }
-    return (next - base) << TARGET_PAGE_BITS;
+    return ret;
 }
 
-/* Called with rcu_read_lock() to protect migration_bitmap */
 static void migration_bitmap_sync_range(ram_addr_t start, ram_addr_t length)
 {
     unsigned long *bitmap;
-    bitmap = atomic_rcu_read(&migration_bitmap);
+    bitmap = atomic_rcu_read(&migration_bitmap_rcu)->bmap;
     migration_dirty_pages +=
         cpu_physical_memory_sync_dirty_bitmap(bitmap, start, length);
 }
 
-
 /* Fix me: there are too many global variables used in migration process. */
 static int64_t start_time;
 static int64_t bytes_xfer_prev;
@@ -548,7 +610,6 @@ static void migration_bitmap_sync_init(void)
     iterations_prev = 0;
 }
 
-/* Called with iothread lock held, to protect ram_list.dirty_memory[] */
 static void migration_bitmap_sync(void)
 {
     RAMBlock *block;
@@ -573,7 +634,7 @@ static void migration_bitmap_sync(void)
     qemu_mutex_lock(&migration_bitmap_mutex);
     rcu_read_lock();
     QLIST_FOREACH_RCU(block, &ram_list.blocks, next) {
-        migration_bitmap_sync_range(block->mr->ram_addr, block->used_length);
+        migration_bitmap_sync_range(block->offset, block->used_length);
     }
     rcu_read_unlock();
     qemu_mutex_unlock(&migration_bitmap_mutex);
@@ -589,21 +650,21 @@ static void migration_bitmap_sync(void)
             /* 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 */
+               were in this routine. If that happens twice, start or increase
+               throttling */
             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)) {
+               (dirty_rate_high_cnt++ >= 2)) {
                     trace_migration_throttle();
-                    mig_throttle_on = true;
                     dirty_rate_high_cnt = 0;
+                    mig_throttle_guest_down();
              }
              bytes_xfer_prev = bytes_xfer_now;
-        } else {
-             mig_throttle_on = false;
         }
+
         if (migrate_use_xbzrle()) {
             if (iterations_prev != acct_info.iterations) {
                 acct_info.xbzrle_cache_miss_rate =
@@ -621,6 +682,9 @@ static void migration_bitmap_sync(void)
         num_dirty_pages_period = 0;
     }
     s->dirty_sync_count = bitmap_sync_count;
+    if (migrate_use_events()) {
+        qapi_event_send_migration_pass(bitmap_sync_count, NULL);
+    }
 }
 
 /**
@@ -655,6 +719,9 @@ static int save_zero_page(QEMUFile *f, RAMBlock *block, ram_addr_t offset,
  * ram_save_page: Send the given page to the stream
  *
  * Returns: Number of pages written.
+ *          < 0 - error
+ *          >=0 - Number of pages written - this might legally be 0
+ *                if xbzrle noticed the page was the same.
  *
  * @f: QEMUFile where to send the data
  * @block: block that contains the page we want to send
@@ -662,18 +729,19 @@ static int save_zero_page(QEMUFile *f, RAMBlock *block, ram_addr_t offset,
  * @last_stage: if we are at the completion stage
  * @bytes_transferred: increase it with the number of transferred bytes
  */
-static int ram_save_page(QEMUFile *f, RAMBlock* block, ram_addr_t offset,
+static int ram_save_page(QEMUFile *f, PageSearchStatus *pss,
                          bool last_stage, uint64_t *bytes_transferred)
 {
     int pages = -1;
     uint64_t bytes_xmit;
     ram_addr_t current_addr;
-    MemoryRegion *mr = block->mr;
     uint8_t *p;
     int ret;
     bool send_async = true;
+    RAMBlock *block = pss->block;
+    ram_addr_t offset = pss->offset;
 
-    p = memory_region_get_ram_ptr(mr) + offset;
+    p = block->host + offset;
 
     /* In doubt sent page as normal */
     bytes_xmit = 0;
@@ -744,7 +812,7 @@ static int do_compress_ram_page(CompressParam *param)
     RAMBlock *block = param->block;
     ram_addr_t offset = param->offset;
 
-    p = memory_region_get_ram_ptr(block->mr) + (offset & TARGET_PAGE_MASK);
+    p = block->host + (offset & TARGET_PAGE_MASK);
 
     bytes_sent = save_page_header(param->file, block, offset |
                                   RAM_SAVE_FLAG_COMPRESS_PAGE);
@@ -846,17 +914,18 @@ static int compress_page_with_multi_thread(QEMUFile *f, RAMBlock *block,
  * @last_stage: if we are at the completion stage
  * @bytes_transferred: increase it with the number of transferred bytes
  */
-static int ram_save_compressed_page(QEMUFile *f, RAMBlock *block,
-                                    ram_addr_t offset, bool last_stage,
+static int ram_save_compressed_page(QEMUFile *f, PageSearchStatus *pss,
+                                    bool last_stage,
                                     uint64_t *bytes_transferred)
 {
     int pages = -1;
     uint64_t bytes_xmit;
-    MemoryRegion *mr = block->mr;
     uint8_t *p;
     int ret;
+    RAMBlock *block = pss->block;
+    ram_addr_t offset = pss->offset;
 
-    p = memory_region_get_ram_ptr(mr) + offset;
+    p = block->host + offset;
 
     bytes_xmit = 0;
     ret = ram_control_save_page(f, block->offset,
@@ -909,6 +978,340 @@ static int ram_save_compressed_page(QEMUFile *f, RAMBlock *block,
     return pages;
 }
 
+/*
+ * Find the next dirty page and update any state associated with
+ * the search process.
+ *
+ * Returns: True if a page is found
+ *
+ * @f: Current migration stream.
+ * @pss: Data about the state of the current dirty page scan.
+ * @*again: Set to false if the search has scanned the whole of RAM
+ * *ram_addr_abs: Pointer into which to store the address of the dirty page
+ *               within the global ram_addr space
+ */
+static bool find_dirty_block(QEMUFile *f, PageSearchStatus *pss,
+                             bool *again, ram_addr_t *ram_addr_abs)
+{
+    pss->offset = migration_bitmap_find_dirty(pss->block, pss->offset,
+                                              ram_addr_abs);
+    if (pss->complete_round && pss->block == last_seen_block &&
+        pss->offset >= last_offset) {
+        /*
+         * We've been once around the RAM and haven't found anything.
+         * Give up.
+         */
+        *again = false;
+        return false;
+    }
+    if (pss->offset >= pss->block->used_length) {
+        /* Didn't find anything in this RAM Block */
+        pss->offset = 0;
+        pss->block = QLIST_NEXT_RCU(pss->block, next);
+        if (!pss->block) {
+            /* Hit the end of the list */
+            pss->block = QLIST_FIRST_RCU(&ram_list.blocks);
+            /* Flag that we've looped */
+            pss->complete_round = true;
+            ram_bulk_stage = false;
+            if (migrate_use_xbzrle()) {
+                /* If xbzrle is on, stop using the data compression at this
+                 * point. In theory, xbzrle can do better than compression.
+                 */
+                flush_compressed_data(f);
+                compression_switch = false;
+            }
+        }
+        /* Didn't find anything this time, but try again on the new block */
+        *again = true;
+        return false;
+    } else {
+        /* Can go around again, but... */
+        *again = true;
+        /* We've found something so probably don't need to */
+        return true;
+    }
+}
+
+/*
+ * Helper for 'get_queued_page' - gets a page off the queue
+ *      ms:      MigrationState in
+ * *offset:      Used to return the offset within the RAMBlock
+ * ram_addr_abs: global offset in the dirty/sent bitmaps
+ *
+ * Returns:      block (or NULL if none available)
+ */
+static RAMBlock *unqueue_page(MigrationState *ms, ram_addr_t *offset,
+                              ram_addr_t *ram_addr_abs)
+{
+    RAMBlock *block = NULL;
+
+    qemu_mutex_lock(&ms->src_page_req_mutex);
+    if (!QSIMPLEQ_EMPTY(&ms->src_page_requests)) {
+        struct MigrationSrcPageRequest *entry =
+                                QSIMPLEQ_FIRST(&ms->src_page_requests);
+        block = entry->rb;
+        *offset = entry->offset;
+        *ram_addr_abs = (entry->offset + entry->rb->offset) &
+                        TARGET_PAGE_MASK;
+
+        if (entry->len > TARGET_PAGE_SIZE) {
+            entry->len -= TARGET_PAGE_SIZE;
+            entry->offset += TARGET_PAGE_SIZE;
+        } else {
+            memory_region_unref(block->mr);
+            QSIMPLEQ_REMOVE_HEAD(&ms->src_page_requests, next_req);
+            g_free(entry);
+        }
+    }
+    qemu_mutex_unlock(&ms->src_page_req_mutex);
+
+    return block;
+}
+
+/*
+ * Unqueue a page from the queue fed by postcopy page requests; skips pages
+ * that are already sent (!dirty)
+ *
+ *      ms:      MigrationState in
+ *     pss:      PageSearchStatus structure updated with found block/offset
+ * ram_addr_abs: global offset in the dirty/sent bitmaps
+ *
+ * Returns:      true if a queued page is found
+ */
+static bool get_queued_page(MigrationState *ms, PageSearchStatus *pss,
+                            ram_addr_t *ram_addr_abs)
+{
+    RAMBlock  *block;
+    ram_addr_t offset;
+    bool dirty;
+
+    do {
+        block = unqueue_page(ms, &offset, ram_addr_abs);
+        /*
+         * We're sending this page, and since it's postcopy nothing else
+         * will dirty it, and we must make sure it doesn't get sent again
+         * even if this queue request was received after the background
+         * search already sent it.
+         */
+        if (block) {
+            unsigned long *bitmap;
+            bitmap = atomic_rcu_read(&migration_bitmap_rcu)->bmap;
+            dirty = test_bit(*ram_addr_abs >> TARGET_PAGE_BITS, bitmap);
+            if (!dirty) {
+                trace_get_queued_page_not_dirty(
+                    block->idstr, (uint64_t)offset,
+                    (uint64_t)*ram_addr_abs,
+                    test_bit(*ram_addr_abs >> TARGET_PAGE_BITS,
+                         atomic_rcu_read(&migration_bitmap_rcu)->unsentmap));
+            } else {
+                trace_get_queued_page(block->idstr,
+                                      (uint64_t)offset,
+                                      (uint64_t)*ram_addr_abs);
+            }
+        }
+
+    } while (block && !dirty);
+
+    if (block) {
+        /*
+         * As soon as we start servicing pages out of order, then we have
+         * to kill the bulk stage, since the bulk stage assumes
+         * in (migration_bitmap_find_and_reset_dirty) that every page is
+         * dirty, that's no longer true.
+         */
+        ram_bulk_stage = false;
+
+        /*
+         * We want the background search to continue from the queued page
+         * since the guest is likely to want other pages near to the page
+         * it just requested.
+         */
+        pss->block = block;
+        pss->offset = offset;
+    }
+
+    return !!block;
+}
+
+/**
+ * flush_page_queue: Flush any remaining pages in the ram request queue
+ *    it should be empty at the end anyway, but in error cases there may be
+ *    some left.
+ *
+ * ms: MigrationState
+ */
+void flush_page_queue(MigrationState *ms)
+{
+    struct MigrationSrcPageRequest *mspr, *next_mspr;
+    /* This queue generally should be empty - but in the case of a failed
+     * migration might have some droppings in.
+     */
+    rcu_read_lock();
+    QSIMPLEQ_FOREACH_SAFE(mspr, &ms->src_page_requests, next_req, next_mspr) {
+        memory_region_unref(mspr->rb->mr);
+        QSIMPLEQ_REMOVE_HEAD(&ms->src_page_requests, next_req);
+        g_free(mspr);
+    }
+    rcu_read_unlock();
+}
+
+/**
+ * Queue the pages for transmission, e.g. a request from postcopy destination
+ *   ms: MigrationStatus in which the queue is held
+ *   rbname: The RAMBlock the request is for - may be NULL (to mean reuse last)
+ *   start: Offset from the start of the RAMBlock
+ *   len: Length (in bytes) to send
+ *   Return: 0 on success
+ */
+int ram_save_queue_pages(MigrationState *ms, const char *rbname,
+                         ram_addr_t start, ram_addr_t len)
+{
+    RAMBlock *ramblock;
+
+    rcu_read_lock();
+    if (!rbname) {
+        /* Reuse last RAMBlock */
+        ramblock = ms->last_req_rb;
+
+        if (!ramblock) {
+            /*
+             * Shouldn't happen, we can't reuse the last RAMBlock if
+             * it's the 1st request.
+             */
+            error_report("ram_save_queue_pages no previous block");
+            goto err;
+        }
+    } else {
+        ramblock = qemu_ram_block_by_name(rbname);
+
+        if (!ramblock) {
+            /* We shouldn't be asked for a non-existent RAMBlock */
+            error_report("ram_save_queue_pages no block '%s'", rbname);
+            goto err;
+        }
+        ms->last_req_rb = ramblock;
+    }
+    trace_ram_save_queue_pages(ramblock->idstr, start, len);
+    if (start+len > ramblock->used_length) {
+        error_report("%s request overrun start=" RAM_ADDR_FMT " len="
+                     RAM_ADDR_FMT " blocklen=" RAM_ADDR_FMT,
+                     __func__, start, len, ramblock->used_length);
+        goto err;
+    }
+
+    struct MigrationSrcPageRequest *new_entry =
+        g_malloc0(sizeof(struct MigrationSrcPageRequest));
+    new_entry->rb = ramblock;
+    new_entry->offset = start;
+    new_entry->len = len;
+
+    memory_region_ref(ramblock->mr);
+    qemu_mutex_lock(&ms->src_page_req_mutex);
+    QSIMPLEQ_INSERT_TAIL(&ms->src_page_requests, new_entry, next_req);
+    qemu_mutex_unlock(&ms->src_page_req_mutex);
+    rcu_read_unlock();
+
+    return 0;
+
+err:
+    rcu_read_unlock();
+    return -1;
+}
+
+/**
+ * ram_save_target_page: Save one target page
+ *
+ *
+ * @f: QEMUFile where to send the data
+ * @block: pointer to block that contains the page we want to send
+ * @offset: offset inside the block for the page;
+ * @last_stage: if we are at the completion stage
+ * @bytes_transferred: increase it with the number of transferred bytes
+ * @dirty_ram_abs: Address of the start of the dirty page in ram_addr_t space
+ *
+ * Returns: Number of pages written.
+ */
+static int ram_save_target_page(MigrationState *ms, QEMUFile *f,
+                                PageSearchStatus *pss,
+                                bool last_stage,
+                                uint64_t *bytes_transferred,
+                                ram_addr_t dirty_ram_abs)
+{
+    int res = 0;
+
+    /* Check the pages is dirty and if it is send it */
+    if (migration_bitmap_clear_dirty(dirty_ram_abs)) {
+        unsigned long *unsentmap;
+        if (compression_switch && migrate_use_compression()) {
+            res = ram_save_compressed_page(f, pss,
+                                           last_stage,
+                                           bytes_transferred);
+        } else {
+            res = ram_save_page(f, pss, last_stage,
+                                bytes_transferred);
+        }
+
+        if (res < 0) {
+            return res;
+        }
+        unsentmap = atomic_rcu_read(&migration_bitmap_rcu)->unsentmap;
+        if (unsentmap) {
+            clear_bit(dirty_ram_abs >> TARGET_PAGE_BITS, unsentmap);
+        }
+        /* Only update last_sent_block if a block was actually sent; xbzrle
+         * might have decided the page was identical so didn't bother writing
+         * to the stream.
+         */
+        if (res > 0) {
+            last_sent_block = pss->block;
+        }
+    }
+
+    return res;
+}
+
+/**
+ * ram_save_host_page: Starting at *offset send pages upto the end
+ *                     of the current host page.  It's valid for the initial
+ *                     offset to point into the middle of a host page
+ *                     in which case the remainder of the hostpage is sent.
+ *                     Only dirty target pages are sent.
+ *
+ * Returns: Number of pages written.
+ *
+ * @f: QEMUFile where to send the data
+ * @block: pointer to block that contains the page we want to send
+ * @offset: offset inside the block for the page; updated to last target page
+ *          sent
+ * @last_stage: if we are at the completion stage
+ * @bytes_transferred: increase it with the number of transferred bytes
+ * @dirty_ram_abs: Address of the start of the dirty page in ram_addr_t space
+ */
+static int ram_save_host_page(MigrationState *ms, QEMUFile *f,
+                              PageSearchStatus *pss,
+                              bool last_stage,
+                              uint64_t *bytes_transferred,
+                              ram_addr_t dirty_ram_abs)
+{
+    int tmppages, pages = 0;
+    do {
+        tmppages = ram_save_target_page(ms, f, pss, last_stage,
+                                        bytes_transferred, dirty_ram_abs);
+        if (tmppages < 0) {
+            return tmppages;
+        }
+
+        pages += tmppages;
+        pss->offset += TARGET_PAGE_SIZE;
+        dirty_ram_abs += TARGET_PAGE_SIZE;
+    } while (pss->offset & (qemu_host_page_size - 1));
+
+    /* The offset we leave with is the last one we looked at */
+    pss->offset -= TARGET_PAGE_SIZE;
+    return pages;
+}
+
 /**
  * ram_find_and_save_block: Finds a dirty page and sends it to f
  *
@@ -920,61 +1323,47 @@ static int ram_save_compressed_page(QEMUFile *f, RAMBlock *block,
  * @f: QEMUFile where to send the data
  * @last_stage: if we are at the completion stage
  * @bytes_transferred: increase it with the number of transferred bytes
+ *
+ * On systems where host-page-size > target-page-size it will send all the
+ * pages in a host page that are dirty.
  */
 
 static int ram_find_and_save_block(QEMUFile *f, bool last_stage,
                                    uint64_t *bytes_transferred)
 {
-    RAMBlock *block = last_seen_block;
-    ram_addr_t offset = last_offset;
-    bool complete_round = false;
+    PageSearchStatus pss;
+    MigrationState *ms = migrate_get_current();
     int pages = 0;
-    MemoryRegion *mr;
+    bool again, found;
+    ram_addr_t dirty_ram_abs; /* Address of the start of the dirty page in
+                                 ram_addr_t space */
 
-    if (!block)
-        block = QLIST_FIRST_RCU(&ram_list.blocks);
+    pss.block = last_seen_block;
+    pss.offset = last_offset;
+    pss.complete_round = false;
 
-    while (true) {
-        mr = block->mr;
-        offset = migration_bitmap_find_and_reset_dirty(mr, offset);
-        if (complete_round && block == last_seen_block &&
-            offset >= last_offset) {
-            break;
+    if (!pss.block) {
+        pss.block = QLIST_FIRST_RCU(&ram_list.blocks);
+    }
+
+    do {
+        again = true;
+        found = get_queued_page(ms, &pss, &dirty_ram_abs);
+
+        if (!found) {
+            /* priority queue empty, so just search for something dirty */
+            found = find_dirty_block(f, &pss, &again, &dirty_ram_abs);
         }
-        if (offset >= block->used_length) {
-            offset = 0;
-            block = QLIST_NEXT_RCU(block, next);
-            if (!block) {
-                block = QLIST_FIRST_RCU(&ram_list.blocks);
-                complete_round = true;
-                ram_bulk_stage = false;
-                if (migrate_use_xbzrle()) {
-                    /* If xbzrle is on, stop using the data compression at this
-                     * point. In theory, xbzrle can do better than compression.
-                     */
-                    flush_compressed_data(f);
-                    compression_switch = false;
-                }
-            }
-        } else {
-            if (compression_switch && migrate_use_compression()) {
-                pages = ram_save_compressed_page(f, block, offset, last_stage,
-                                                 bytes_transferred);
-            } else {
-                pages = ram_save_page(f, block, offset, last_stage,
-                                      bytes_transferred);
-            }
 
-            /* if page is unmodified, continue to the next */
-            if (pages > 0) {
-                last_sent_block = block;
-                break;
-            }
+        if (found) {
+            pages = ram_save_host_page(ms, f, &pss,
+                                       last_stage, bytes_transferred,
+                                       dirty_ram_abs);
         }
-    }
+    } while (!pages && again);
 
-    last_seen_block = block;
-    last_offset = offset;
+    last_seen_block = pss.block;
+    last_offset = pss.offset;
 
     return pages;
 }
@@ -1024,17 +1413,23 @@ void free_xbzrle_decoded_buf(void)
     xbzrle_decoded_buf = NULL;
 }
 
-static void migration_end(void)
+static void migration_bitmap_free(struct BitmapRcu *bmap)
+{
+    g_free(bmap->bmap);
+    g_free(bmap->unsentmap);
+    g_free(bmap);
+}
+
+static void ram_migration_cleanup(void *opaque)
 {
     /* caller have hold iothread lock or is in a bh, so there is
      * no writing race against this migration_bitmap
      */
-    unsigned long *bitmap = migration_bitmap;
-    atomic_rcu_set(&migration_bitmap, NULL);
+    struct BitmapRcu *bitmap = migration_bitmap_rcu;
+    atomic_rcu_set(&migration_bitmap_rcu, NULL);
     if (bitmap) {
         memory_global_dirty_log_stop();
-        synchronize_rcu();
-        g_free(bitmap);
+        call_rcu(bitmap, migration_bitmap_free, rcu);
     }
 
     XBZRLE_cache_lock();
@@ -1049,11 +1444,6 @@ static void migration_end(void)
     XBZRLE_cache_unlock();
 }
 
-static void ram_migration_cancel(void *opaque)
-{
-    migration_end();
-}
-
 static void reset_ram_globals(void)
 {
     last_seen_block = NULL;
@@ -1070,9 +1460,10 @@ void migration_bitmap_extend(ram_addr_t old, ram_addr_t new)
     /* called in qemu main thread, so there is
      * no writing race against this migration_bitmap
      */
-    if (migration_bitmap) {
-        unsigned long *old_bitmap = migration_bitmap, *bitmap;
-        bitmap = bitmap_new(new);
+    if (migration_bitmap_rcu) {
+        struct BitmapRcu *old_bitmap = migration_bitmap_rcu, *bitmap;
+        bitmap = g_new(struct BitmapRcu, 1);
+        bitmap->bmap = bitmap_new(new);
 
         /* prevent migration_bitmap content from being set bit
          * by migration_bitmap_sync_range() at the same time.
@@ -1080,16 +1471,410 @@ void migration_bitmap_extend(ram_addr_t old, ram_addr_t new)
          * at the same time.
          */
         qemu_mutex_lock(&migration_bitmap_mutex);
-        bitmap_copy(bitmap, old_bitmap, old);
-        bitmap_set(bitmap, old, new - old);
-        atomic_rcu_set(&migration_bitmap, bitmap);
+        bitmap_copy(bitmap->bmap, old_bitmap->bmap, old);
+        bitmap_set(bitmap->bmap, old, new - old);
+
+        /* We don't have a way to safely extend the sentmap
+         * with RCU; so mark it as missing, entry to postcopy
+         * will fail.
+         */
+        bitmap->unsentmap = NULL;
+
+        atomic_rcu_set(&migration_bitmap_rcu, bitmap);
         qemu_mutex_unlock(&migration_bitmap_mutex);
         migration_dirty_pages += new - old;
-        synchronize_rcu();
-        g_free(old_bitmap);
+        call_rcu(old_bitmap, migration_bitmap_free, rcu);
+    }
+}
+
+/*
+ * 'expected' is the value you expect the bitmap mostly to be full
+ * of; it won't bother printing lines that are all this value.
+ * If 'todump' is null the migration bitmap is dumped.
+ */
+void ram_debug_dump_bitmap(unsigned long *todump, bool expected)
+{
+    int64_t ram_pages = last_ram_offset() >> TARGET_PAGE_BITS;
+
+    int64_t cur;
+    int64_t linelen = 128;
+    char linebuf[129];
+
+    if (!todump) {
+        todump = atomic_rcu_read(&migration_bitmap_rcu)->bmap;
+    }
+
+    for (cur = 0; cur < ram_pages; cur += linelen) {
+        int64_t curb;
+        bool found = false;
+        /*
+         * Last line; catch the case where the line length
+         * is longer than remaining ram
+         */
+        if (cur + linelen > ram_pages) {
+            linelen = ram_pages - cur;
+        }
+        for (curb = 0; curb < linelen; curb++) {
+            bool thisbit = test_bit(cur + curb, todump);
+            linebuf[curb] = thisbit ? '1' : '.';
+            found = found || (thisbit != expected);
+        }
+        if (found) {
+            linebuf[curb] = '\0';
+            fprintf(stderr,  "0x%08" PRIx64 " : %s\n", cur, linebuf);
+        }
+    }
+}
+
+/* **** functions for postcopy ***** */
+
+/*
+ * Callback from postcopy_each_ram_send_discard for each RAMBlock
+ * Note: At this point the 'unsentmap' is the processed bitmap combined
+ *       with the dirtymap; so a '1' means it's either dirty or unsent.
+ * start,length: Indexes into the bitmap for the first bit
+ *            representing the named block and length in target-pages
+ */
+static int postcopy_send_discard_bm_ram(MigrationState *ms,
+                                        PostcopyDiscardState *pds,
+                                        unsigned long start,
+                                        unsigned long length)
+{
+    unsigned long end = start + length; /* one after the end */
+    unsigned long current;
+    unsigned long *unsentmap;
+
+    unsentmap = atomic_rcu_read(&migration_bitmap_rcu)->unsentmap;
+    for (current = start; current < end; ) {
+        unsigned long one = find_next_bit(unsentmap, end, current);
+
+        if (one <= end) {
+            unsigned long zero = find_next_zero_bit(unsentmap, end, one + 1);
+            unsigned long discard_length;
+
+            if (zero >= end) {
+                discard_length = end - one;
+            } else {
+                discard_length = zero - one;
+            }
+            postcopy_discard_send_range(ms, pds, one, discard_length);
+            current = one + discard_length;
+        } else {
+            current = one;
+        }
+    }
+
+    return 0;
+}
+
+/*
+ * Utility for the outgoing postcopy code.
+ *   Calls postcopy_send_discard_bm_ram for each RAMBlock
+ *   passing it bitmap indexes and name.
+ * Returns: 0 on success
+ * (qemu_ram_foreach_block ends up passing unscaled lengths
+ *  which would mean postcopy code would have to deal with target page)
+ */
+static int postcopy_each_ram_send_discard(MigrationState *ms)
+{
+    struct RAMBlock *block;
+    int ret;
+
+    QLIST_FOREACH_RCU(block, &ram_list.blocks, next) {
+        unsigned long first = block->offset >> TARGET_PAGE_BITS;
+        PostcopyDiscardState *pds = postcopy_discard_send_init(ms,
+                                                               first,
+                                                               block->idstr);
+
+        /*
+         * Postcopy sends chunks of bitmap over the wire, but it
+         * just needs indexes at this point, avoids it having
+         * target page specific code.
+         */
+        ret = postcopy_send_discard_bm_ram(ms, pds, first,
+                                    block->used_length >> TARGET_PAGE_BITS);
+        postcopy_discard_send_finish(ms, pds);
+        if (ret) {
+            return ret;
+        }
+    }
+
+    return 0;
+}
+
+/*
+ * Helper for postcopy_chunk_hostpages; it's called twice to cleanup
+ *   the two bitmaps, that are similar, but one is inverted.
+ *
+ * We search for runs of target-pages that don't start or end on a
+ * host page boundary;
+ * unsent_pass=true: Cleans up partially unsent host pages by searching
+ *                 the unsentmap
+ * unsent_pass=false: Cleans up partially dirty host pages by searching
+ *                 the main migration bitmap
+ *
+ */
+static void postcopy_chunk_hostpages_pass(MigrationState *ms, bool unsent_pass,
+                                          RAMBlock *block,
+                                          PostcopyDiscardState *pds)
+{
+    unsigned long *bitmap;
+    unsigned long *unsentmap;
+    unsigned int host_ratio = qemu_host_page_size / TARGET_PAGE_SIZE;
+    unsigned long first = block->offset >> TARGET_PAGE_BITS;
+    unsigned long len = block->used_length >> TARGET_PAGE_BITS;
+    unsigned long last = first + (len - 1);
+    unsigned long run_start;
+
+    bitmap = atomic_rcu_read(&migration_bitmap_rcu)->bmap;
+    unsentmap = atomic_rcu_read(&migration_bitmap_rcu)->unsentmap;
+
+    if (unsent_pass) {
+        /* Find a sent page */
+        run_start = find_next_zero_bit(unsentmap, last + 1, first);
+    } else {
+        /* Find a dirty page */
+        run_start = find_next_bit(bitmap, last + 1, first);
+    }
+
+    while (run_start <= last) {
+        bool do_fixup = false;
+        unsigned long fixup_start_addr;
+        unsigned long host_offset;
+
+        /*
+         * If the start of this run of pages is in the middle of a host
+         * page, then we need to fixup this host page.
+         */
+        host_offset = run_start % host_ratio;
+        if (host_offset) {
+            do_fixup = true;
+            run_start -= host_offset;
+            fixup_start_addr = run_start;
+            /* For the next pass */
+            run_start = run_start + host_ratio;
+        } else {
+            /* Find the end of this run */
+            unsigned long run_end;
+            if (unsent_pass) {
+                run_end = find_next_bit(unsentmap, last + 1, run_start + 1);
+            } else {
+                run_end = find_next_zero_bit(bitmap, last + 1, run_start + 1);
+            }
+            /*
+             * If the end isn't at the start of a host page, then the
+             * run doesn't finish at the end of a host page
+             * and we need to discard.
+             */
+            host_offset = run_end % host_ratio;
+            if (host_offset) {
+                do_fixup = true;
+                fixup_start_addr = run_end - host_offset;
+                /*
+                 * This host page has gone, the next loop iteration starts
+                 * from after the fixup
+                 */
+                run_start = fixup_start_addr + host_ratio;
+            } else {
+                /*
+                 * No discards on this iteration, next loop starts from
+                 * next sent/dirty page
+                 */
+                run_start = run_end + 1;
+            }
+        }
+
+        if (do_fixup) {
+            unsigned long page;
+
+            /* Tell the destination to discard this page */
+            if (unsent_pass || !test_bit(fixup_start_addr, unsentmap)) {
+                /* For the unsent_pass we:
+                 *     discard partially sent pages
+                 * For the !unsent_pass (dirty) we:
+                 *     discard partially dirty pages that were sent
+                 *     (any partially sent pages were already discarded
+                 *     by the previous unsent_pass)
+                 */
+                postcopy_discard_send_range(ms, pds, fixup_start_addr,
+                                            host_ratio);
+            }
+
+            /* Clean up the bitmap */
+            for (page = fixup_start_addr;
+                 page < fixup_start_addr + host_ratio; page++) {
+                /* All pages in this host page are now not sent */
+                set_bit(page, unsentmap);
+
+                /*
+                 * Remark them as dirty, updating the count for any pages
+                 * that weren't previously dirty.
+                 */
+                migration_dirty_pages += !test_and_set_bit(page, bitmap);
+            }
+        }
+
+        if (unsent_pass) {
+            /* Find the next sent page for the next iteration */
+            run_start = find_next_zero_bit(unsentmap, last + 1,
+                                           run_start);
+        } else {
+            /* Find the next dirty page for the next iteration */
+            run_start = find_next_bit(bitmap, last + 1, run_start);
+        }
+    }
+}
+
+/*
+ * Utility for the outgoing postcopy code.
+ *
+ * Discard any partially sent host-page size chunks, mark any partially
+ * dirty host-page size chunks as all dirty.
+ *
+ * Returns: 0 on success
+ */
+static int postcopy_chunk_hostpages(MigrationState *ms)
+{
+    struct RAMBlock *block;
+
+    if (qemu_host_page_size == TARGET_PAGE_SIZE) {
+        /* Easy case - TPS==HPS - nothing to be done */
+        return 0;
+    }
+
+    /* Easiest way to make sure we don't resume in the middle of a host-page */
+    last_seen_block = NULL;
+    last_sent_block = NULL;
+    last_offset     = 0;
+
+    QLIST_FOREACH_RCU(block, &ram_list.blocks, next) {
+        unsigned long first = block->offset >> TARGET_PAGE_BITS;
+
+        PostcopyDiscardState *pds =
+                         postcopy_discard_send_init(ms, first, block->idstr);
+
+        /* First pass: Discard all partially sent host pages */
+        postcopy_chunk_hostpages_pass(ms, true, block, pds);
+        /*
+         * Second pass: Ensure that all partially dirty host pages are made
+         * fully dirty.
+         */
+        postcopy_chunk_hostpages_pass(ms, false, block, pds);
+
+        postcopy_discard_send_finish(ms, pds);
+    } /* ram_list loop */
+
+    return 0;
+}
+
+/*
+ * Transmit the set of pages to be discarded after precopy to the target
+ * these are pages that:
+ *     a) Have been previously transmitted but are now dirty again
+ *     b) Pages that have never been transmitted, this ensures that
+ *        any pages on the destination that have been mapped by background
+ *        tasks get discarded (transparent huge pages is the specific concern)
+ * Hopefully this is pretty sparse
+ */
+int ram_postcopy_send_discard_bitmap(MigrationState *ms)
+{
+    int ret;
+    unsigned long *bitmap, *unsentmap;
+
+    rcu_read_lock();
+
+    /* This should be our last sync, the src is now paused */
+    migration_bitmap_sync();
+
+    unsentmap = atomic_rcu_read(&migration_bitmap_rcu)->unsentmap;
+    if (!unsentmap) {
+        /* We don't have a safe way to resize the sentmap, so
+         * if the bitmap was resized it will be NULL at this
+         * point.
+         */
+        error_report("migration ram resized during precopy phase");
+        rcu_read_unlock();
+        return -EINVAL;
+    }
+
+    /* Deal with TPS != HPS */
+    ret = postcopy_chunk_hostpages(ms);
+    if (ret) {
+        rcu_read_unlock();
+        return ret;
+    }
+
+    /*
+     * Update the unsentmap to be unsentmap = unsentmap | dirty
+     */
+    bitmap = atomic_rcu_read(&migration_bitmap_rcu)->bmap;
+    bitmap_or(unsentmap, unsentmap, bitmap,
+               last_ram_offset() >> TARGET_PAGE_BITS);
+
+
+    trace_ram_postcopy_send_discard_bitmap();
+#ifdef DEBUG_POSTCOPY
+    ram_debug_dump_bitmap(unsentmap, true);
+#endif
+
+    ret = postcopy_each_ram_send_discard(ms);
+    rcu_read_unlock();
+
+    return ret;
+}
+
+/*
+ * At the start of the postcopy phase of migration, any now-dirty
+ * precopied pages are discarded.
+ *
+ * start, length describe a byte address range within the RAMBlock
+ *
+ * Returns 0 on success.
+ */
+int ram_discard_range(MigrationIncomingState *mis,
+                      const char *block_name,
+                      uint64_t start, size_t length)
+{
+    int ret = -1;
+
+    rcu_read_lock();
+    RAMBlock *rb = qemu_ram_block_by_name(block_name);
+
+    if (!rb) {
+        error_report("ram_discard_range: Failed to find block '%s'",
+                     block_name);
+        goto err;
     }
+
+    uint8_t *host_startaddr = rb->host + start;
+
+    if ((uintptr_t)host_startaddr & (qemu_host_page_size - 1)) {
+        error_report("ram_discard_range: Unaligned start address: %p",
+                     host_startaddr);
+        goto err;
+    }
+
+    if ((start + length) <= rb->used_length) {
+        uint8_t *host_endaddr = host_startaddr + length;
+        if ((uintptr_t)host_endaddr & (qemu_host_page_size - 1)) {
+            error_report("ram_discard_range: Unaligned end address: %p",
+                         host_endaddr);
+            goto err;
+        }
+        ret = postcopy_ram_discard_range(mis, host_startaddr, length);
+    } else {
+        error_report("ram_discard_range: Overrun block '%s' (%" PRIu64
+                     "/%zx/" RAM_ADDR_FMT")",
+                     block_name, start, length, rb->used_length);
+    }
+
+err:
+    rcu_read_unlock();
+
+    return ret;
 }
 
+
 /* Each of ram_save_setup, ram_save_iterate and ram_save_complete has
  * long-running RCU critical section.  When rcu-reclaims in the code
  * start to become numerous it will be necessary to reduce the
@@ -1101,7 +1886,6 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
     RAMBlock *block;
     int64_t ram_bitmap_pages; /* Size of bitmap in pages, including gaps */
 
-    mig_throttle_on = false;
     dirty_rate_high_cnt = 0;
     bitmap_sync_count = 0;
     migration_bitmap_sync_init();
@@ -1137,16 +1921,23 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
         acct_clear();
     }
 
-    /* iothread lock needed for ram_list.dirty_memory[] */
+    /* For memory_global_dirty_log_start below.  */
     qemu_mutex_lock_iothread();
+
     qemu_mutex_lock_ramlist();
     rcu_read_lock();
     bytes_transferred = 0;
     reset_ram_globals();
 
     ram_bitmap_pages = last_ram_offset() >> TARGET_PAGE_BITS;
-    migration_bitmap = bitmap_new(ram_bitmap_pages);
-    bitmap_set(migration_bitmap, 0, ram_bitmap_pages);
+    migration_bitmap_rcu = g_new0(struct BitmapRcu, 1);
+    migration_bitmap_rcu->bmap = bitmap_new(ram_bitmap_pages);
+    bitmap_set(migration_bitmap_rcu->bmap, 0, ram_bitmap_pages);
+
+    if (migrate_postcopy_ram()) {
+        migration_bitmap_rcu->unsentmap = bitmap_new(ram_bitmap_pages);
+        bitmap_set(migration_bitmap_rcu->unsentmap, 0, ram_bitmap_pages);
+    }
 
     /*
      * Count the total number of pages used by ram blocks not including any
@@ -1206,7 +1997,7 @@ static int ram_save_iterate(QEMUFile *f, void *opaque)
         }
         pages_sent += pages;
         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
@@ -1247,7 +2038,9 @@ static int ram_save_complete(QEMUFile *f, void *opaque)
 {
     rcu_read_lock();
 
-    migration_bitmap_sync();
+    if (!migration_in_postcopy(migrate_get_current())) {
+        migration_bitmap_sync();
+    }
 
     ram_control_before_iterate(f, RAM_CONTROL_FINISH);
 
@@ -1274,13 +2067,16 @@ static int ram_save_complete(QEMUFile *f, void *opaque)
     return 0;
 }
 
-static uint64_t ram_save_pending(QEMUFile *f, void *opaque, uint64_t max_size)
+static void ram_save_pending(QEMUFile *f, void *opaque, uint64_t max_size,
+                             uint64_t *non_postcopiable_pending,
+                             uint64_t *postcopiable_pending)
 {
     uint64_t remaining_size;
 
     remaining_size = ram_save_remaining() * TARGET_PAGE_SIZE;
 
-    if (remaining_size < max_size) {
+    if (!migration_in_postcopy(migrate_get_current()) &&
+        remaining_size < max_size) {
         qemu_mutex_lock_iothread();
         rcu_read_lock();
         migration_bitmap_sync();
@@ -1288,17 +2084,21 @@ static uint64_t ram_save_pending(QEMUFile *f, void *opaque, uint64_t max_size)
         qemu_mutex_unlock_iothread();
         remaining_size = ram_save_remaining() * TARGET_PAGE_SIZE;
     }
-    return remaining_size;
+
+    /* We can do postcopy, and all the data is postcopiable */
+    *postcopiable_pending += remaining_size;
 }
 
 static int load_xbzrle(QEMUFile *f, ram_addr_t addr, void *host)
 {
     unsigned int xh_len;
     int xh_flags;
+    uint8_t *loaded_data;
 
     if (!xbzrle_decoded_buf) {
         xbzrle_decoded_buf = g_malloc(TARGET_PAGE_SIZE);
     }
+    loaded_data = xbzrle_decoded_buf;
 
     /* extract RLE header */
     xh_flags = qemu_get_byte(f);
@@ -1314,10 +2114,10 @@ static int load_xbzrle(QEMUFile *f, ram_addr_t addr, void *host)
         return -1;
     }
     /* load data and decode */
-    qemu_get_buffer(f, xbzrle_decoded_buf, xh_len);
+    qemu_get_buffer_in_place(f, &loaded_data, xh_len);
 
     /* decode RLE */
-    if (xbzrle_decode_buffer(xbzrle_decoded_buf, xh_len, host,
+    if (xbzrle_decode_buffer(loaded_data, xh_len, host,
                              TARGET_PAGE_SIZE) == -1) {
         error_report("Failed to load XBZRLE page - decode error!");
         return -1;
@@ -1329,36 +2129,48 @@ static int load_xbzrle(QEMUFile *f, ram_addr_t addr, void *host)
 /* Must be called from within a rcu critical section.
  * Returns a pointer from within the RCU-protected ram_list.
  */
-static inline void *host_from_stream_offset(QEMUFile *f,
-                                            ram_addr_t offset,
-                                            int flags)
+/*
+ * Read a RAMBlock ID from the stream f.
+ *
+ * f: Stream to read from
+ * flags: Page flags (mostly to see if it's a continuation of previous block)
+ */
+static inline RAMBlock *ram_block_from_stream(QEMUFile *f,
+                                              int flags)
 {
     static RAMBlock *block = NULL;
     char id[256];
     uint8_t len;
 
     if (flags & RAM_SAVE_FLAG_CONTINUE) {
-        if (!block || block->max_length <= offset) {
+        if (!block) {
             error_report("Ack, bad migration stream!");
             return NULL;
         }
-
-        return memory_region_get_ram_ptr(block->mr) + offset;
+        return block;
     }
 
     len = qemu_get_byte(f);
     qemu_get_buffer(f, (uint8_t *)id, len);
     id[len] = 0;
 
-    QLIST_FOREACH_RCU(block, &ram_list.blocks, next) {
-        if (!strncmp(id, block->idstr, sizeof(id)) &&
-            block->max_length > offset) {
-            return memory_region_get_ram_ptr(block->mr) + offset;
-        }
+    block = qemu_ram_block_by_name(id);
+    if (!block) {
+        error_report("Can't find block %s", id);
+        return NULL;
     }
 
-    error_report("Can't find block %s!", id);
-    return NULL;
+    return block;
+}
+
+static inline void *host_from_ram_block_offset(RAMBlock *block,
+                                               ram_addr_t offset)
+{
+    if (!offset_in_ramblock(block, offset)) {
+        return NULL;
+    }
+
+    return block->host + offset;
 }
 
 /*
@@ -1406,7 +2218,6 @@ void migrate_decompress_threads_create(void)
     thread_count = migrate_decompress_threads();
     decompress_threads = g_new0(QemuThread, thread_count);
     decomp_param = g_new0(DecompressParam, thread_count);
-    compressed_data_buf = g_malloc0(compressBound(TARGET_PAGE_SIZE));
     quit_decomp_thread = false;
     for (i = 0; i < thread_count; i++) {
         qemu_mutex_init(&decomp_param[i].mutex);
@@ -1437,13 +2248,11 @@ void migrate_decompress_threads_join(void)
     }
     g_free(decompress_threads);
     g_free(decomp_param);
-    g_free(compressed_data_buf);
     decompress_threads = NULL;
     decomp_param = NULL;
-    compressed_data_buf = NULL;
 }
 
-static void decompress_data_with_multi_threads(uint8_t *compbuf,
+static void decompress_data_with_multi_threads(QEMUFile *f,
                                                void *host, int len)
 {
     int idx, thread_count;
@@ -1452,7 +2261,7 @@ static void decompress_data_with_multi_threads(uint8_t *compbuf,
     while (true) {
         for (idx = 0; idx < thread_count; idx++) {
             if (!decomp_param[idx].start) {
-                memcpy(decomp_param[idx].compbuf, compbuf, len);
+                qemu_get_buffer(f, decomp_param[idx].compbuf, len);
                 decomp_param[idx].des = host;
                 decomp_param[idx].len = len;
                 start_decompression(&decomp_param[idx]);
@@ -1465,11 +2274,150 @@ static void decompress_data_with_multi_threads(uint8_t *compbuf,
     }
 }
 
+/*
+ * Allocate data structures etc needed by incoming migration with postcopy-ram
+ * postcopy-ram's similarly names postcopy_ram_incoming_init does the work
+ */
+int ram_postcopy_incoming_init(MigrationIncomingState *mis)
+{
+    size_t ram_pages = last_ram_offset() >> TARGET_PAGE_BITS;
+
+    return postcopy_ram_incoming_init(mis, ram_pages);
+}
+
+/*
+ * Called in postcopy mode by ram_load().
+ * rcu_read_lock is taken prior to this being called.
+ */
+static int ram_load_postcopy(QEMUFile *f)
+{
+    int flags = 0, ret = 0;
+    bool place_needed = false;
+    bool matching_page_sizes = qemu_host_page_size == TARGET_PAGE_SIZE;
+    MigrationIncomingState *mis = migration_incoming_get_current();
+    /* Temporary page that is later 'placed' */
+    void *postcopy_host_page = postcopy_get_tmp_page(mis);
+    void *last_host = NULL;
+    bool all_zero = false;
+
+    while (!ret && !(flags & RAM_SAVE_FLAG_EOS)) {
+        ram_addr_t addr;
+        void *host = NULL;
+        void *page_buffer = NULL;
+        void *place_source = NULL;
+        uint8_t ch;
+
+        addr = qemu_get_be64(f);
+        flags = addr & ~TARGET_PAGE_MASK;
+        addr &= TARGET_PAGE_MASK;
+
+        trace_ram_load_postcopy_loop((uint64_t)addr, flags);
+        place_needed = false;
+        if (flags & (RAM_SAVE_FLAG_COMPRESS | RAM_SAVE_FLAG_PAGE)) {
+            RAMBlock *block = ram_block_from_stream(f, flags);
+
+            host = host_from_ram_block_offset(block, addr);
+            if (!host) {
+                error_report("Illegal RAM offset " RAM_ADDR_FMT, addr);
+                ret = -EINVAL;
+                break;
+            }
+            page_buffer = host;
+            /*
+             * Postcopy requires that we place whole host pages atomically.
+             * To make it atomic, the data is read into a temporary page
+             * that's moved into place later.
+             * The migration protocol uses,  possibly smaller, target-pages
+             * however the source ensures it always sends all the components
+             * of a host page in order.
+             */
+            page_buffer = postcopy_host_page +
+                          ((uintptr_t)host & ~qemu_host_page_mask);
+            /* If all TP are zero then we can optimise the place */
+            if (!((uintptr_t)host & ~qemu_host_page_mask)) {
+                all_zero = true;
+            } else {
+                /* not the 1st TP within the HP */
+                if (host != (last_host + TARGET_PAGE_SIZE)) {
+                    error_report("Non-sequential target page %p/%p",
+                                  host, last_host);
+                    ret = -EINVAL;
+                    break;
+                }
+            }
+
+
+            /*
+             * If it's the last part of a host page then we place the host
+             * page
+             */
+            place_needed = (((uintptr_t)host + TARGET_PAGE_SIZE) &
+                                     ~qemu_host_page_mask) == 0;
+            place_source = postcopy_host_page;
+        }
+        last_host = host;
+
+        switch (flags & ~RAM_SAVE_FLAG_CONTINUE) {
+        case RAM_SAVE_FLAG_COMPRESS:
+            ch = qemu_get_byte(f);
+            memset(page_buffer, ch, TARGET_PAGE_SIZE);
+            if (ch) {
+                all_zero = false;
+            }
+            break;
+
+        case RAM_SAVE_FLAG_PAGE:
+            all_zero = false;
+            if (!place_needed || !matching_page_sizes) {
+                qemu_get_buffer(f, page_buffer, TARGET_PAGE_SIZE);
+            } else {
+                /* Avoids the qemu_file copy during postcopy, which is
+                 * going to do a copy later; can only do it when we
+                 * do this read in one go (matching page sizes)
+                 */
+                qemu_get_buffer_in_place(f, (uint8_t **)&place_source,
+                                         TARGET_PAGE_SIZE);
+            }
+            break;
+        case RAM_SAVE_FLAG_EOS:
+            /* normal exit */
+            break;
+        default:
+            error_report("Unknown combination of migration flags: %#x"
+                         " (postcopy mode)", flags);
+            ret = -EINVAL;
+        }
+
+        if (place_needed) {
+            /* This gets called at the last target page in the host page */
+            if (all_zero) {
+                ret = postcopy_place_page_zero(mis,
+                                               host + TARGET_PAGE_SIZE -
+                                               qemu_host_page_size);
+            } else {
+                ret = postcopy_place_page(mis, host + TARGET_PAGE_SIZE -
+                                               qemu_host_page_size,
+                                               place_source);
+            }
+        }
+        if (!ret) {
+            ret = qemu_file_get_error(f);
+        }
+    }
+
+    return ret;
+}
+
 static int ram_load(QEMUFile *f, void *opaque, int version_id)
 {
     int flags = 0, ret = 0;
     static uint64_t seq_iter;
     int len = 0;
+    /*
+     * If system is running in postcopy mode, page inserts to host memory must
+     * be atomic
+     */
+    bool postcopy_running = postcopy_state_get() >= POSTCOPY_INCOMING_LISTENING;
 
     seq_iter++;
 
@@ -1483,15 +2431,32 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
      * critical section.
      */
     rcu_read_lock();
-    while (!ret && !(flags & RAM_SAVE_FLAG_EOS)) {
+
+    if (postcopy_running) {
+        ret = ram_load_postcopy(f);
+    }
+
+    while (!postcopy_running && !ret && !(flags & RAM_SAVE_FLAG_EOS)) {
         ram_addr_t addr, total_ram_bytes;
-        void *host;
+        void *host = NULL;
         uint8_t ch;
 
         addr = qemu_get_be64(f);
         flags = addr & ~TARGET_PAGE_MASK;
         addr &= TARGET_PAGE_MASK;
 
+        if (flags & (RAM_SAVE_FLAG_COMPRESS | RAM_SAVE_FLAG_PAGE |
+                     RAM_SAVE_FLAG_COMPRESS_PAGE | RAM_SAVE_FLAG_XBZRLE)) {
+            RAMBlock *block = ram_block_from_stream(f, flags);
+
+            host = host_from_ram_block_offset(block, addr);
+            if (!host) {
+                error_report("Illegal RAM offset " RAM_ADDR_FMT, addr);
+                ret = -EINVAL;
+                break;
+            }
+        }
+
         switch (flags & ~RAM_SAVE_FLAG_CONTINUE) {
         case RAM_SAVE_FLAG_MEM_SIZE:
             /* Synchronize RAM block list */
@@ -1506,23 +2471,20 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
                 id[len] = 0;
                 length = qemu_get_be64(f);
 
-                QLIST_FOREACH_RCU(block, &ram_list.blocks, next) {
-                    if (!strncmp(id, block->idstr, sizeof(id))) {
-                        if (length != block->used_length) {
-                            Error *local_err = NULL;
+                block = qemu_ram_block_by_name(id);
+                if (block) {
+                    if (length != block->used_length) {
+                        Error *local_err = NULL;
 
-                            ret = qemu_ram_resize(block->offset, length, &local_err);
-                            if (local_err) {
-                                error_report_err(local_err);
-                            }
+                        ret = qemu_ram_resize(block->offset, length,
+                                              &local_err);
+                        if (local_err) {
+                            error_report_err(local_err);
                         }
-                        ram_control_load_hook(f, RAM_CONTROL_BLOCK_REG,
-                                              block->idstr);
-                        break;
                     }
-                }
-
-                if (!block) {
+                    ram_control_load_hook(f, RAM_CONTROL_BLOCK_REG,
+                                          block->idstr);
+                } else {
                     error_report("Unknown ramblock \"%s\", cannot "
                                  "accept migration", id);
                     ret = -EINVAL;
@@ -1531,49 +2493,27 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
                 total_ram_bytes -= length;
             }
             break;
+
         case RAM_SAVE_FLAG_COMPRESS:
-            host = host_from_stream_offset(f, addr, flags);
-            if (!host) {
-                error_report("Illegal RAM offset " RAM_ADDR_FMT, addr);
-                ret = -EINVAL;
-                break;
-            }
             ch = qemu_get_byte(f);
             ram_handle_compressed(host, ch, TARGET_PAGE_SIZE);
             break;
+
         case RAM_SAVE_FLAG_PAGE:
-            host = host_from_stream_offset(f, addr, flags);
-            if (!host) {
-                error_report("Illegal RAM offset " RAM_ADDR_FMT, addr);
-                ret = -EINVAL;
-                break;
-            }
             qemu_get_buffer(f, host, TARGET_PAGE_SIZE);
             break;
-        case RAM_SAVE_FLAG_COMPRESS_PAGE:
-            host = host_from_stream_offset(f, addr, flags);
-            if (!host) {
-                error_report("Invalid RAM offset " RAM_ADDR_FMT, addr);
-                ret = -EINVAL;
-                break;
-            }
 
+        case RAM_SAVE_FLAG_COMPRESS_PAGE:
             len = qemu_get_be32(f);
             if (len < 0 || len > compressBound(TARGET_PAGE_SIZE)) {
                 error_report("Invalid compressed data length: %d", len);
                 ret = -EINVAL;
                 break;
             }
-            qemu_get_buffer(f, compressed_data_buf, len);
-            decompress_data_with_multi_threads(compressed_data_buf, host, len);
+            decompress_data_with_multi_threads(f, host, len);
             break;
+
         case RAM_SAVE_FLAG_XBZRLE:
-            host = host_from_stream_offset(f, addr, flags);
-            if (!host) {
-                error_report("Illegal RAM offset " RAM_ADDR_FMT, addr);
-                ret = -EINVAL;
-                break;
-            }
             if (load_xbzrle(f, addr, host) < 0) {
                 error_report("Failed to decompress XBZRLE page at "
                              RAM_ADDR_FMT, addr);
@@ -1607,10 +2547,11 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
 static SaveVMHandlers savevm_ram_handlers = {
     .save_live_setup = ram_save_setup,
     .save_live_iterate = ram_save_iterate,
-    .save_live_complete = ram_save_complete,
+    .save_live_complete_postcopy = ram_save_complete,
+    .save_live_complete_precopy = ram_save_complete,
     .save_live_pending = ram_save_pending,
     .load_state = ram_load,
-    .cancel = ram_migration_cancel,
+    .cleanup = ram_migration_cleanup,
 };
 
 void ram_mig_init(void)
@@ -1618,52 +2559,3 @@ void ram_mig_init(void)
     qemu_mutex_init(&XBZRLE.lock);
     register_savevm_live(NULL, "ram", 0, 4, &savevm_ram_handlers, NULL);
 }
-/* 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;
-    }
-}