1 files changed, 40 insertions, 8 deletions

diff --git a/exec.c b/exec.c
index 4722e521d4..629a508385 100644
--- a/exec.c
+++ b/exec.c
@@ -623,6 +623,13 @@ static int cpu_common_post_load(void *opaque, int version_id)
     cpu->interrupt_request &= ~0x01;
     tlb_flush(cpu);
 
+    /* loadvm has just updated the content of RAM, bypassing the
+     * usual mechanisms that ensure we flush TBs for writes to
+     * memory we've translated code from. So we must flush all TBs,
+     * which will now be stale.
+     */
+    tb_flush(cpu);
+
     return 0;
 }
 
@@ -1605,7 +1612,13 @@ static void *file_ram_alloc(RAMBlock *block,
     void *area;
 
     block->page_size = qemu_fd_getpagesize(fd);
-    block->mr->align = block->page_size;
+    if (block->mr->align % block->page_size) {
+        error_setg(errp, "alignment 0x%" PRIx64
+                   " must be multiples of page size 0x%zx",
+                   block->mr->align, block->page_size);
+        return NULL;
+    }
+    block->mr->align = MAX(block->page_size, block->mr->align);
 #if defined(__s390x__)
     if (kvm_enabled()) {
         block->mr->align = MAX(block->mr->align, QEMU_VMALLOC_ALIGN);
@@ -1660,7 +1673,10 @@ static void *file_ram_alloc(RAMBlock *block,
 }
 #endif
 
-/* Called with the ramlist lock held.  */
+/* Allocate space within the ram_addr_t space that governs the
+ * dirty bitmaps.
+ * Called with the ramlist lock held.
+ */
 static ram_addr_t find_ram_offset(ram_addr_t size)
 {
     RAMBlock *block, *next_block;
@@ -1673,19 +1689,33 @@ static ram_addr_t find_ram_offset(ram_addr_t size)
     }
 
     RAMBLOCK_FOREACH(block) {
-        ram_addr_t end, next = RAM_ADDR_MAX;
+        ram_addr_t candidate, next = RAM_ADDR_MAX;
 
-        end = block->offset + block->max_length;
+        /* Align blocks to start on a 'long' in the bitmap
+         * which makes the bitmap sync'ing take the fast path.
+         */
+        candidate = block->offset + block->max_length;
+        candidate = ROUND_UP(candidate, BITS_PER_LONG << TARGET_PAGE_BITS);
 
+        /* Search for the closest following block
+         * and find the gap.
+         */
         RAMBLOCK_FOREACH(next_block) {
-            if (next_block->offset >= end) {
+            if (next_block->offset >= candidate) {
                 next = MIN(next, next_block->offset);
             }
         }
-        if (next - end >= size && next - end < mingap) {
-            offset = end;
-            mingap = next - end;
+
+        /* If it fits remember our place and remember the size
+         * of gap, but keep going so that we might find a smaller
+         * gap to fill so avoiding fragmentation.
+         */
+        if (next - candidate >= size && next - candidate < mingap) {
+            offset = candidate;
+            mingap = next - candidate;
         }
+
+        trace_find_ram_offset_loop(size, candidate, offset, next, mingap);
     }
 
     if (offset == RAM_ADDR_MAX) {
@@ -1694,6 +1724,8 @@ static ram_addr_t find_ram_offset(ram_addr_t size)
         abort();
     }
 
+    trace_find_ram_offset(size, offset);
+
     return offset;
 }