exec: Handle multipage ranges in invalidate_and_set_dirty()

The code in invalidate_and_set_dirty() needs to handle addr/length
combinations which cross guest physical page boundaries. This can happen,
for example, when disk I/O reads large blocks into guest RAM which previously
held code that we have cached translations for. Unfortunately we were only
checking the clean/dirty status of the first page in the range, and then
were calling a tb_invalidate function which only handles ranges that don't
cross page boundaries. Fix the function to deal with multipage ranges.

The symptoms of this bug were that guest code would misbehave (eg segfault),
in particular after a guest reboot but potentially any time the guest
reused a page of its physical RAM for new code.

Cc: [email protected]
Signed-off-by: Peter Maydell <[email protected]>
Reviewed-by: Paolo Bonzini <[email protected]>
Message-id: [email protected]
(cherry picked from commit f874bf9)
Signed-off-by: Michael Roth <[email protected]>

Author: pm215

exec.c

@@ -2009,10 +2009,8 @@ int cpu_memory_rw_debug(CPUState *cpu, target_ulong addr,
 static void invalidate_and_set_dirty(hwaddr addr,
                                      hwaddr length)
 {
-    if (cpu_physical_memory_is_clean(addr)) {
-        /* invalidate code */
-        tb_invalidate_phys_page_range(addr, addr + length, 0);
-        /* set dirty bit */
+    if (cpu_physical_memory_range_includes_clean(addr, length)) {
+        tb_invalidate_phys_range(addr, addr + length, 0);
         cpu_physical_memory_set_dirty_range_nocode(addr, length);
     }
     xen_modified_memory(addr, length);

include/exec/ram_addr.h

@@ -49,6 +49,21 @@ static inline bool cpu_physical_memory_get_dirty(ram_addr_t start,
     return next < end;
 }
 
+static inline bool cpu_physical_memory_get_clean(ram_addr_t start,
+                                                 ram_addr_t length,
+                                                 unsigned client)
+{
+    unsigned long end, page, next;
+
+    assert(client < DIRTY_MEMORY_NUM);
+
+    end = TARGET_PAGE_ALIGN(start + length) >> TARGET_PAGE_BITS;
+    page = start >> TARGET_PAGE_BITS;
+    next = find_next_zero_bit(ram_list.dirty_memory[client], end, page);
+
+    return next < end;
+}
+
 static inline bool cpu_physical_memory_get_dirty_flag(ram_addr_t addr,
                                                       unsigned client)
 {
@@ -64,6 +79,16 @@ static inline bool cpu_physical_memory_is_clean(ram_addr_t addr)
     return !(vga && code && migration);
 }
 
+static inline bool cpu_physical_memory_range_includes_clean(ram_addr_t start,
+                                                            ram_addr_t length)
+{
+    bool vga = cpu_physical_memory_get_clean(start, length, DIRTY_MEMORY_VGA);
+    bool code = cpu_physical_memory_get_clean(start, length, DIRTY_MEMORY_CODE);
+    bool migration =
+        cpu_physical_memory_get_clean(start, length, DIRTY_MEMORY_MIGRATION);
+    return vga || code || migration;
+}
+
 static inline void cpu_physical_memory_set_dirty_flag(ram_addr_t addr,
                                                       unsigned client)
 {