1 files changed, 76 insertions, 1 deletions

diff --git a/migration/ram.c b/migration/ram.c
index 189931d24d..f7c165dfb3 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -937,10 +937,85 @@ bool ramblock_page_is_discarded(RAMBlock *rb, ram_addr_t start)
 }
 
 /* Called with RCU critical section */
+static uint64_t physical_memory_sync_dirty_bitmap(RAMBlock *rb,
+                                                  ram_addr_t start,
+                                                  ram_addr_t length)
+{
+    ram_addr_t addr;
+    unsigned long word = BIT_WORD((start + rb->offset) >> TARGET_PAGE_BITS);
+    uint64_t num_dirty = 0;
+    unsigned long *dest = rb->bmap;
+
+    /* start address and length is aligned at the start of a word? */
+    if (((word * BITS_PER_LONG) << TARGET_PAGE_BITS) ==
+         (start + rb->offset) &&
+        !(length & ((BITS_PER_LONG << TARGET_PAGE_BITS) - 1))) {
+        int k;
+        int nr = BITS_TO_LONGS(length >> TARGET_PAGE_BITS);
+        unsigned long * const *src;
+        unsigned long idx = (word * BITS_PER_LONG) / DIRTY_MEMORY_BLOCK_SIZE;
+        unsigned long offset = BIT_WORD((word * BITS_PER_LONG) %
+                                        DIRTY_MEMORY_BLOCK_SIZE);
+        unsigned long page = BIT_WORD(start >> TARGET_PAGE_BITS);
+
+        src = qatomic_rcu_read(
+                &ram_list.dirty_memory[DIRTY_MEMORY_MIGRATION])->blocks;
+
+        for (k = page; k < page + nr; k++) {
+            if (src[idx][offset]) {
+                unsigned long bits = qatomic_xchg(&src[idx][offset], 0);
+                unsigned long new_dirty;
+                new_dirty = ~dest[k];
+                dest[k] |= bits;
+                new_dirty &= bits;
+                num_dirty += ctpopl(new_dirty);
+            }
+
+            if (++offset >= BITS_TO_LONGS(DIRTY_MEMORY_BLOCK_SIZE)) {
+                offset = 0;
+                idx++;
+            }
+        }
+        if (num_dirty) {
+            cpu_physical_memory_dirty_bits_cleared(start, length);
+        }
+
+        if (rb->clear_bmap) {
+            /*
+             * Postpone the dirty bitmap clear to the point before we
+             * really send the pages, also we will split the clear
+             * dirty procedure into smaller chunks.
+             */
+            clear_bmap_set(rb, start >> TARGET_PAGE_BITS,
+                           length >> TARGET_PAGE_BITS);
+        } else {
+            /* Slow path - still do that in a huge chunk */
+            memory_region_clear_dirty_bitmap(rb->mr, start, length);
+        }
+    } else {
+        ram_addr_t offset = rb->offset;
+
+        for (addr = 0; addr < length; addr += TARGET_PAGE_SIZE) {
+            if (cpu_physical_memory_test_and_clear_dirty(
+                        start + addr + offset,
+                        TARGET_PAGE_SIZE,
+                        DIRTY_MEMORY_MIGRATION)) {
+                long k = (start + addr) >> TARGET_PAGE_BITS;
+                if (!test_and_set_bit(k, dest)) {
+                    num_dirty++;
+                }
+            }
+        }
+    }
+
+    return num_dirty;
+}
+
+/* Called with RCU critical section */
 static void ramblock_sync_dirty_bitmap(RAMState *rs, RAMBlock *rb)
 {
     uint64_t new_dirty_pages =
-        cpu_physical_memory_sync_dirty_bitmap(rb, 0, rb->used_length);
+        physical_memory_sync_dirty_bitmap(rb, 0, rb->used_length);
 
     rs->migration_dirty_pages += new_dirty_pages;
     rs->num_dirty_pages_period += new_dirty_pages;