Re: [PATCH v2] qemu-kvm: Speed up of the dirty-bitmap-traveling

[OHMURA Kei <ohmura.kei@lab.ntt.co.jp>]

dirty-bitmap-traveling is carried out by byte size in qemu-kvm.c.
But We think that dirty-bitmap-traveling by long size is faster than by byte
size especially when most of memory is not dirty.

Signed-off-by: OHMURA Kei <ohmura.kei@lab.ntt.co.jp>
---
 bswap.h    |    2 ++
 qemu-kvm.c |   31 ++++++++++++++++---------------
 2 files changed, 18 insertions(+), 15 deletions(-)

diff --git a/bswap.h b/bswap.h
index 4558704..1f87e6d 100644
--- a/bswap.h
+++ b/bswap.h
@@ -205,8 +205,10 @@ static inline void cpu_to_be32wu(uint32_t *p, uint32_t v)
 
 #ifdef HOST_WORDS_BIGENDIAN
 #define cpu_to_32wu cpu_to_be32wu
+#define leul_to_cpu(v) le ## HOST_LONG_BITS ## _to_cpu(v)
 #else
 #define cpu_to_32wu cpu_to_le32wu
+#define leul_to_cpu(v) (v)
 #endif
 
 #undef le_bswap
diff --git a/qemu-kvm.c b/qemu-kvm.c
index a305907..6952aa5 100644
--- a/qemu-kvm.c
+++ b/qemu-kvm.c
@@ -2434,31 +2434,32 @@ int kvm_physical_memory_set_dirty_tracking(int enable)
 
 /* get kvm's dirty pages bitmap and update qemu's */
 static int kvm_get_dirty_pages_log_range(unsigned long start_addr,
-                                         unsigned char *bitmap,
+                                         unsigned long *bitmap,
                                          unsigned long offset,
                                          unsigned long mem_size)
 {
-    unsigned int i, j, n = 0;
-    unsigned char c;
-    unsigned long page_number, addr, addr1;
+    unsigned int i, j;
+    unsigned long page_number, addr, addr1, c;
     ram_addr_t ram_addr;
-    unsigned int len = ((mem_size / TARGET_PAGE_SIZE) + 7) / 8;
+    unsigned int len = ((mem_size / TARGET_PAGE_SIZE) + HOST_LONG_BITS - 1) /
+        HOST_LONG_BITS;
 
     /* 
      * bitmap-traveling is faster than memory-traveling (for addr...) 
      * especially when most of the memory is not dirty.
      */
     for (i = 0; i < len; i++) {
-        c = bitmap[i];
-        while (c > 0) {
-            j = ffsl(c) - 1;
-            c &= ~(1u << j);
-            page_number = i * 8 + j;
-            addr1 = page_number * TARGET_PAGE_SIZE;
-            addr = offset + addr1;
-            ram_addr = cpu_get_physical_page_desc(addr);
-            cpu_physical_memory_set_dirty(ram_addr);
-            n++;
+        if (bitmap[i] != 0) {
+            c = leul_to_cpu(bitmap[i]);
+            do {
+                j = ffsl(c) - 1;
+                c &= ~(1ul << j);
+                page_number = i * HOST_LONG_BITS + j;
+                addr1 = page_number * TARGET_PAGE_SIZE;
+                addr = offset + addr1;
+                ram_addr = cpu_get_physical_page_desc(addr);
+                cpu_physical_memory_set_dirty(ram_addr);
+            } while (c != 0);
         }
     }
     return 0;
-- 
1.6.3.3