exec: pass client mask to cpu_physical_memory_set_dirty_range

This cuts in half the cost of bitmap operations (which will become more
expensive when made atomic) during migration on non-VRAM regions.

Reviewed-by: Fam Zheng <famz@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

exec.c

@@ -1351,7 +1351,8 @@ int qemu_ram_resize(ram_addr_t base, ram_addr_t newsize, Error **errp)
 
     cpu_physical_memory_clear_dirty_range(block->offset, block->used_length);
     block->used_length = newsize;
-    cpu_physical_memory_set_dirty_range(block->offset, block->used_length);
+    cpu_physical_memory_set_dirty_range(block->offset, block->used_length,
+                                        DIRTY_CLIENTS_ALL);
     memory_region_set_size(block->mr, newsize);
     if (block->resized) {
         block->resized(block->idstr, newsize, block->host);
@@ -1425,7 +1426,8 @@ static ram_addr_t ram_block_add(RAMBlock *new_block, Error **errp)
        }
     }
     cpu_physical_memory_set_dirty_range(new_block->offset,
-                                        new_block->used_length);
+                                        new_block->used_length,
+                                        DIRTY_CLIENTS_ALL);
 
     if (new_block->host) {
         qemu_ram_setup_dump(new_block->host, new_block->max_length);
@@ -1813,7 +1815,11 @@ static void notdirty_mem_write(void *opaque, hwaddr ram_addr,
     default:
         abort();
     }
-    cpu_physical_memory_set_dirty_range_nocode(ram_addr, size);
+    /* Set both VGA and migration bits for simplicity and to remove
+     * the notdirty callback faster.
+     */
+    cpu_physical_memory_set_dirty_range(ram_addr, size,
+                                        DIRTY_CLIENTS_NOCODE);
     /* we remove the notdirty callback only if the code has been
        flushed */
     if (!cpu_physical_memory_is_clean(ram_addr)) {
@@ -2259,9 +2265,7 @@ static void invalidate_and_set_dirty(MemoryRegion *mr, hwaddr addr,
             tb_invalidate_phys_range(addr, addr + length);
             dirty_log_mask &= ~(1 << DIRTY_MEMORY_CODE);
         }
-        if (dirty_log_mask) {
+        cpu_physical_memory_set_dirty_range(addr, length, dirty_log_mask);
-            cpu_physical_memory_set_dirty_range_nocode(addr, length);
-        }
     } else {
         xen_modified_memory(addr, length);
     }
@@ -3014,9 +3018,7 @@ void address_space_stl_notdirty(AddressSpace *as, hwaddr addr, uint32_t val,
 
         dirty_log_mask = memory_region_get_dirty_log_mask(mr);
         dirty_log_mask &= ~(1 << DIRTY_MEMORY_CODE);
-        if (dirty_log_mask) {
+        cpu_physical_memory_set_dirty_range(addr1, 4, dirty_log_mask);
-            cpu_physical_memory_set_dirty_range_nocode(addr1, 4);
-        }
         r = MEMTX_OK;
     }
     if (result) {

include/exec/ram_addr.h

@@ -41,6 +41,9 @@ void qemu_ram_free_from_ptr(ram_addr_t addr);
 
 int qemu_ram_resize(ram_addr_t base, ram_addr_t newsize, Error **errp);
 
+#define DIRTY_CLIENTS_ALL     ((1 << DIRTY_MEMORY_NUM) - 1)
+#define DIRTY_CLIENTS_NOCODE  (DIRTY_CLIENTS_ALL & ~(1 << DIRTY_MEMORY_CODE))
+
 static inline bool cpu_physical_memory_get_dirty(ram_addr_t start,
                                                  ram_addr_t length,
                                                  unsigned client)
@@ -103,28 +106,23 @@ static inline void cpu_physical_memory_set_dirty_flag(ram_addr_t addr,
     set_bit(addr >> TARGET_PAGE_BITS, ram_list.dirty_memory[client]);
 }
 
-static inline void cpu_physical_memory_set_dirty_range_nocode(ram_addr_t start,
-                                                              ram_addr_t length)
-{
-    unsigned long end, page;
-
-    end = TARGET_PAGE_ALIGN(start + length) >> TARGET_PAGE_BITS;
-    page = start >> TARGET_PAGE_BITS;
-    bitmap_set(ram_list.dirty_memory[DIRTY_MEMORY_MIGRATION], page, end - page);
-    bitmap_set(ram_list.dirty_memory[DIRTY_MEMORY_VGA], page, end - page);
-    xen_modified_memory(start, length);
-}
-
 static inline void cpu_physical_memory_set_dirty_range(ram_addr_t start,
-                                                       ram_addr_t length)
+                                                       ram_addr_t length,
+                                                       uint8_t mask)
 {
     unsigned long end, page;
 
     end = TARGET_PAGE_ALIGN(start + length) >> TARGET_PAGE_BITS;
     page = start >> TARGET_PAGE_BITS;
-    bitmap_set(ram_list.dirty_memory[DIRTY_MEMORY_MIGRATION], page, end - page);
+    if (likely(mask & (1 << DIRTY_MEMORY_MIGRATION))) {
-    bitmap_set(ram_list.dirty_memory[DIRTY_MEMORY_VGA], page, end - page);
+        bitmap_set(ram_list.dirty_memory[DIRTY_MEMORY_MIGRATION], page, end - page);
-    bitmap_set(ram_list.dirty_memory[DIRTY_MEMORY_CODE], page, end - page);
+    }
+    if (unlikely(mask & (1 << DIRTY_MEMORY_VGA))) {
+        bitmap_set(ram_list.dirty_memory[DIRTY_MEMORY_VGA], page, end - page);
+    }
+    if (unlikely(mask & (1 << DIRTY_MEMORY_CODE))) {
+        bitmap_set(ram_list.dirty_memory[DIRTY_MEMORY_CODE], page, end - page);
+    }
     xen_modified_memory(start, length);
 }
 
@@ -172,7 +170,8 @@ static inline void cpu_physical_memory_set_dirty_lebitmap(unsigned long *bitmap,
                     addr = page_number * TARGET_PAGE_SIZE;
                     ram_addr = start + addr;
                     cpu_physical_memory_set_dirty_range(ram_addr,
-                                       TARGET_PAGE_SIZE * hpratio);
+                                       TARGET_PAGE_SIZE * hpratio,
+                                       DIRTY_CLIENTS_ALL);
                 } while (c != 0);
             }
         }

memory.c

@@ -1461,7 +1461,8 @@ void memory_region_set_dirty(MemoryRegion *mr, hwaddr addr,
                              hwaddr size)
 {
     assert(mr->terminates);
-    cpu_physical_memory_set_dirty_range(mr->ram_addr + addr, size);
+    cpu_physical_memory_set_dirty_range(mr->ram_addr + addr, size,
+                                        memory_region_get_dirty_log_mask(mr));
 }
 
 bool memory_region_test_and_clear_dirty(MemoryRegion *mr, hwaddr addr,