[PULL 7/7] migration: clear the memory region dirty bitmap when skipping free pages

[Dr. David Alan Gilbert (git)]

From: Wei Wang <wei.w.wang@intel.com>

When skipping free pages to send, their corresponding dirty bits in the
memory region dirty bitmap need to be cleared. Otherwise the skipped
pages will be sent in the next round after the migration thread syncs
dirty bits from the memory region dirty bitmap.

Cc: David Hildenbrand <david@redhat.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Michael S. Tsirkin <mst@redhat.com>
Reported-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Wei Wang <wei.w.wang@intel.com>
Message-Id: <20210722083055.23352-1-wei.w.wang@intel.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
---
 migration/ram.c | 74 +++++++++++++++++++++++++++++++++++++------------
 1 file changed, 56 insertions(+), 18 deletions(-)

diff --git a/migration/ram.c b/migration/ram.c
index 08b3cb7a4a..7a43bfd7af 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -789,6 +789,53 @@ unsigned long migration_bitmap_find_dirty(RAMState *rs, 
RAMBlock *rb,
     return find_next_bit(bitmap, size, start);
 }
 
+static void migration_clear_memory_region_dirty_bitmap(RAMState *rs,
+                                                       RAMBlock *rb,
+                                                       unsigned long page)
+{
+    uint8_t shift;
+    hwaddr size, start;
+
+    if (!rb->clear_bmap || !clear_bmap_test_and_clear(rb, page)) {
+        return;
+    }
+
+    shift = rb->clear_bmap_shift;
+    /*
+     * CLEAR_BITMAP_SHIFT_MIN should always guarantee this... this
+     * can make things easier sometimes since then start address
+     * of the small chunk will always be 64 pages aligned so the
+     * bitmap will always be aligned to unsigned long. We should
+     * even be able to remove this restriction but I'm simply
+     * keeping it.
+     */
+    assert(shift >= 6);
+
+    size = 1ULL << (TARGET_PAGE_BITS + shift);
+    start = (((ram_addr_t)page) << TARGET_PAGE_BITS) & (-size);
+    trace_migration_bitmap_clear_dirty(rb->idstr, start, size, page);
+    memory_region_clear_dirty_bitmap(rb->mr, start, size);
+}
+
+static void
+migration_clear_memory_region_dirty_bitmap_range(RAMState *rs,
+                                                 RAMBlock *rb,
+                                                 unsigned long start,
+                                                 unsigned long npages)
+{
+    unsigned long i, chunk_pages = 1UL << rb->clear_bmap_shift;
+    unsigned long chunk_start = QEMU_ALIGN_DOWN(start, chunk_pages);
+    unsigned long chunk_end = QEMU_ALIGN_UP(start + npages, chunk_pages);
+
+    /*
+     * Clear pages from start to start + npages - 1, so the end boundary is
+     * exclusive.
+     */
+    for (i = chunk_start; i < chunk_end; i += chunk_pages) {
+        migration_clear_memory_region_dirty_bitmap(rs, rb, i);
+    }
+}
+
 static inline bool migration_bitmap_clear_dirty(RAMState *rs,
                                                 RAMBlock *rb,
                                                 unsigned long page)
@@ -803,26 +850,9 @@ static inline bool migration_bitmap_clear_dirty(RAMState 
*rs,
      * the page in the chunk we clear the remote dirty bitmap for all.
      * Clearing it earlier won't be a problem, but too late will.
      */
-    if (rb->clear_bmap && clear_bmap_test_and_clear(rb, page)) {
-        uint8_t shift = rb->clear_bmap_shift;
-        hwaddr size = 1ULL << (TARGET_PAGE_BITS + shift);
-        hwaddr start = (((ram_addr_t)page) << TARGET_PAGE_BITS) & (-size);
-
-        /*
-         * CLEAR_BITMAP_SHIFT_MIN should always guarantee this... this
-         * can make things easier sometimes since then start address
-         * of the small chunk will always be 64 pages aligned so the
-         * bitmap will always be aligned to unsigned long.  We should
-         * even be able to remove this restriction but I'm simply
-         * keeping it.
-         */
-        assert(shift >= 6);
-        trace_migration_bitmap_clear_dirty(rb->idstr, start, size, page);
-        memory_region_clear_dirty_bitmap(rb->mr, start, size);
-    }
+    migration_clear_memory_region_dirty_bitmap(rs, rb, page);
 
     ret = test_and_clear_bit(page, rb->bmap);
-
     if (ret) {
         rs->migration_dirty_pages--;
     }
@@ -2741,6 +2771,14 @@ void qemu_guest_free_page_hint(void *addr, size_t len)
         npages = used_len >> TARGET_PAGE_BITS;
 
         qemu_mutex_lock(&ram_state->bitmap_mutex);
+        /*
+         * The skipped free pages are equavalent to be sent from clear_bmap's
+         * perspective, so clear the bits from the memory region bitmap which
+         * are initially set. Otherwise those skipped pages will be sent in
+         * the next round after syncing from the memory region bitmap.
+         */
+        migration_clear_memory_region_dirty_bitmap_range(ram_state, block,
+                                                         start, npages);
         ram_state->migration_dirty_pages -=
                       bitmap_count_one_with_offset(block->bmap, start, npages);
         bitmap_clear(block->bmap, start, npages);
-- 
2.31.1