[PATCH v2 4/5] migration: Use non-atomic ops for clear log bitmap

[Peter Xu <peterx@redhat.com>]

Since we already have bitmap_mutex to protect either the dirty bitmap or
the clear log bitmap, we don't need atomic operations to set/clear/test on
the clear log bitmap.  Switching all ops from atomic to non-atomic
versions, meanwhile touch up the comments to show which lock is in charge.

Introduced non-atomic version of bitmap_test_and_clear_atomic(), mostly the
same as the atomic version but simplified a few places, e.g. dropped the
"old_bits" variable, and also the explicit memory barriers.

Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
---
 include/exec/ram_addr.h | 11 +++++-----
 include/exec/ramblock.h |  3 +++
 include/qemu/bitmap.h   |  1 +
 util/bitmap.c           | 45 +++++++++++++++++++++++++++++++++++++++++
 4 files changed, 55 insertions(+), 5 deletions(-)

diff --git a/include/exec/ram_addr.h b/include/exec/ram_addr.h
index f3e0c78161..5092a2e0ff 100644
--- a/include/exec/ram_addr.h
+++ b/include/exec/ram_addr.h
@@ -42,7 +42,8 @@ static inline long clear_bmap_size(uint64_t pages, uint8_t shift)
 }
 
 /**
- * clear_bmap_set: set clear bitmap for the page range
+ * clear_bmap_set: set clear bitmap for the page range.  Must be with
+ * bitmap_mutex held.
  *
  * @rb: the ramblock to operate on
  * @start: the start page number
@@ -55,12 +56,12 @@ static inline void clear_bmap_set(RAMBlock *rb, uint64_t start,
 {
     uint8_t shift = rb->clear_bmap_shift;
 
-    bitmap_set_atomic(rb->clear_bmap, start >> shift,
-                      clear_bmap_size(npages, shift));
+    bitmap_set(rb->clear_bmap, start >> shift, clear_bmap_size(npages, shift));
 }
 
 /**
- * clear_bmap_test_and_clear: test clear bitmap for the page, clear if set
+ * clear_bmap_test_and_clear: test clear bitmap for the page, clear if set.
+ * Must be with bitmap_mutex held.
  *
  * @rb: the ramblock to operate on
  * @page: the page number to check
@@ -71,7 +72,7 @@ static inline bool clear_bmap_test_and_clear(RAMBlock *rb, uint64_t page)
 {
     uint8_t shift = rb->clear_bmap_shift;
 
-    return bitmap_test_and_clear_atomic(rb->clear_bmap, page >> shift, 1);
+    return bitmap_test_and_clear(rb->clear_bmap, page >> shift, 1);
 }
 
 static inline bool offset_in_ramblock(RAMBlock *b, ram_addr_t offset)
diff --git a/include/exec/ramblock.h b/include/exec/ramblock.h
index 6cbedf9e0c..adc03df59c 100644
--- a/include/exec/ramblock.h
+++ b/include/exec/ramblock.h
@@ -53,6 +53,9 @@ struct RAMBlock {
      * and split clearing of dirty bitmap on the remote node (e.g.,
      * KVM).  The bitmap will be set only when doing global sync.
      *
+     * It is only used during src side of ram migration, and it is
+     * protected by the global ram_state.bitmap_mutex.
+     *
      * NOTE: this bitmap is different comparing to the other bitmaps
      * in that one bit can represent multiple guest pages (which is
      * decided by the `clear_bmap_shift' variable below).  On
diff --git a/include/qemu/bitmap.h b/include/qemu/bitmap.h
index 82a1d2f41f..3ccb00865f 100644
--- a/include/qemu/bitmap.h
+++ b/include/qemu/bitmap.h
@@ -253,6 +253,7 @@ void bitmap_set(unsigned long *map, long i, long len);
 void bitmap_set_atomic(unsigned long *map, long i, long len);
 void bitmap_clear(unsigned long *map, long start, long nr);
 bool bitmap_test_and_clear_atomic(unsigned long *map, long start, long nr);
+bool bitmap_test_and_clear(unsigned long *map, long start, long nr);
 void bitmap_copy_and_clear_atomic(unsigned long *dst, unsigned long *src,
                                   long nr);
 unsigned long bitmap_find_next_zero_area(unsigned long *map,
diff --git a/util/bitmap.c b/util/bitmap.c
index f81d8057a7..8d12e90a5a 100644
--- a/util/bitmap.c
+++ b/util/bitmap.c
@@ -240,6 +240,51 @@ void bitmap_clear(unsigned long *map, long start, long nr)
     }
 }
 
+bool bitmap_test_and_clear(unsigned long *map, long start, long nr)
+{
+    unsigned long *p = map + BIT_WORD(start);
+    const long size = start + nr;
+    int bits_to_clear = BITS_PER_LONG - (start % BITS_PER_LONG);
+    unsigned long mask_to_clear = BITMAP_FIRST_WORD_MASK(start);
+    bool dirty = false;
+
+    assert(start >= 0 && nr >= 0);
+
+    /* First word */
+    if (nr - bits_to_clear > 0) {
+        if ((*p) & mask_to_clear) {
+            dirty = true;
+        }
+        *p &= ~mask_to_clear;
+        nr -= bits_to_clear;
+        bits_to_clear = BITS_PER_LONG;
+        p++;
+    }
+
+    /* Full words */
+    if (bits_to_clear == BITS_PER_LONG) {
+        while (nr >= BITS_PER_LONG) {
+            if (*p) {
+                dirty = true;
+                *p = 0;
+            }
+            nr -= BITS_PER_LONG;
+            p++;
+        }
+    }
+
+    /* Last word */
+    if (nr) {
+        mask_to_clear &= BITMAP_LAST_WORD_MASK(size);
+        if ((*p) & mask_to_clear) {
+            dirty = true;
+        }
+        *p &= ~mask_to_clear;
+    }
+
+    return dirty;
+}
+
 bool bitmap_test_and_clear_atomic(unsigned long *map, long start, long nr)
 {
     unsigned long *p = map + BIT_WORD(start);
-- 
2.37.3