exec: fix migration with devices that use address_space_rw

Devices that use address_space_rw to write large areas to memory
(as opposed to address_space_map/unmap) were broken with respect
to migration since fe680d0 (exec: Limit translation limiting in
address_space_translate to xen, 2014-05-07).  Such devices include
IDE CD-ROMs.

The reason is that invalidate_and_set_dirty (called by address_space_rw
but not address_space_map/unmap) was only setting the dirty bit for
the first page in the translation.

To fix this, introduce cpu_physical_memory_set_dirty_range_nocode that
is the same as cpu_physical_memory_set_dirty_range except it does not
muck with the DIRTY_MEMORY_CODE bitmap.  This function can be used if
the caller invalidates translations with tb_invalidate_phys_page_range.

There is another difference between cpu_physical_memory_set_dirty_range
and cpu_physical_memory_set_dirty_flag; the former includes a call
to xen_modified_memory.  This is handled separately in
invalidate_and_set_dirty, and is not needed in other callers of
cpu_physical_memory_set_dirty_range_nocode, so leave it alone.

Just one nit: now that invalidate_and_set_dirty takes care of handling
multiple pages, there is no need for address_space_unmap to wrap it
in a loop.  In fact that loop would now be O(n^2).

Reported-by: Dave Gilbert <dgilbert@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Gerd Hoffmann <kraxel@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

exec.c

@@ -1568,8 +1568,7 @@ static void notdirty_mem_write(void *opaque, hwaddr ram_addr,
     default:
         abort();
     }
-    cpu_physical_memory_set_dirty_flag(ram_addr, DIRTY_MEMORY_MIGRATION);
-    cpu_physical_memory_set_dirty_flag(ram_addr, DIRTY_MEMORY_VGA);
+    cpu_physical_memory_set_dirty_range_nocode(ram_addr, size);
     /* we remove the notdirty callback only if the code has been
        flushed */
     if (!cpu_physical_memory_is_clean(ram_addr)) {
@@ -1978,8 +1977,7 @@ static void invalidate_and_set_dirty(hwaddr addr,
         /* invalidate code */
         tb_invalidate_phys_page_range(addr, addr + length, 0);
         /* set dirty bit */
-        cpu_physical_memory_set_dirty_flag(addr, DIRTY_MEMORY_VGA);
-        cpu_physical_memory_set_dirty_flag(addr, DIRTY_MEMORY_MIGRATION);
+        cpu_physical_memory_set_dirty_range_nocode(addr, length);
     }
     xen_modified_memory(addr, length);
 }
@@ -2335,15 +2333,7 @@ void address_space_unmap(AddressSpace *as, void *buffer, hwaddr len,
         mr = qemu_ram_addr_from_host(buffer, &addr1);
         assert(mr != NULL);
         if (is_write) {
-            while (access_len) {
-                unsigned l;
-                l = TARGET_PAGE_SIZE;
-                if (l > access_len)
-                    l = access_len;
-                invalidate_and_set_dirty(addr1, l);
-                addr1 += l;
-                access_len -= l;
-            }
+            invalidate_and_set_dirty(addr1, access_len);
         }
         if (xen_enabled()) {
             xen_invalidate_map_cache_entry(buffer);
@@ -2581,9 +2571,7 @@ void stl_phys_notdirty(AddressSpace *as, hwaddr addr, uint32_t val)
                 /* invalidate code */
                 tb_invalidate_phys_page_range(addr1, addr1 + 4, 0);
                 /* set dirty bit */
-                cpu_physical_memory_set_dirty_flag(addr1,
-                                                   DIRTY_MEMORY_MIGRATION);
-                cpu_physical_memory_set_dirty_flag(addr1, DIRTY_MEMORY_VGA);
+                cpu_physical_memory_set_dirty_range_nocode(addr1, 4);
             }
         }
     }

include/exec/ram_addr.h

@@ -71,6 +71,17 @@ 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);
+}
+
 static inline void cpu_physical_memory_set_dirty_range(ram_addr_t start,
                                                        ram_addr_t length)
 {