accel/tcg: Store some tlb flags in CPUTLBEntryFull

We have run out of bits we can use within the CPUTLBEntry comparators,
as TLB_FLAGS_MASK cannot overlap alignment.

Store slow_flags[] in CPUTLBEntryFull, and merge with the flags from
the comparator.  A new TLB_FORCE_SLOW bit is set within the comparator
as an indication that the slow path must be used.

Move TLB_BSWAP to TLB_SLOW_FLAGS_MASK.  Since we are out of bits,
we cannot create a new bit without moving an old one.

Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

include/exec/cpu-all.h

@@ -327,17 +327,30 @@ CPUArchState *cpu_copy(CPUArchState *env);
 #define TLB_MMIO            (1 << (TARGET_PAGE_BITS_MIN - 3))
 /* Set if TLB entry contains a watchpoint.  */
 #define TLB_WATCHPOINT      (1 << (TARGET_PAGE_BITS_MIN - 4))
-/* Set if TLB entry requires byte swap.  */
-#define TLB_BSWAP           (1 << (TARGET_PAGE_BITS_MIN - 5))
+/* Set if the slow path must be used; more flags in CPUTLBEntryFull. */
+#define TLB_FORCE_SLOW      (1 << (TARGET_PAGE_BITS_MIN - 5))
 /* Set if TLB entry writes ignored.  */
 #define TLB_DISCARD_WRITE   (1 << (TARGET_PAGE_BITS_MIN - 6))
 
-/* Use this mask to check interception with an alignment mask
+/*
+ * Use this mask to check interception with an alignment mask
  * in a TCG backend.
  */
 #define TLB_FLAGS_MASK \
     (TLB_INVALID_MASK | TLB_NOTDIRTY | TLB_MMIO \
-    | TLB_WATCHPOINT | TLB_BSWAP | TLB_DISCARD_WRITE)
+    | TLB_WATCHPOINT | TLB_FORCE_SLOW | TLB_DISCARD_WRITE)
+
+/*
+ * Flags stored in CPUTLBEntryFull.slow_flags[x].
+ * TLB_FORCE_SLOW must be set in CPUTLBEntry.addr_idx[x].
+ */
+/* Set if TLB entry requires byte swap.  */
+#define TLB_BSWAP            (1 << 0)
+
+#define TLB_SLOW_FLAGS_MASK  TLB_BSWAP
+
+/* The two sets of flags must not overlap. */
+QEMU_BUILD_BUG_ON(TLB_FLAGS_MASK & TLB_SLOW_FLAGS_MASK);
 
 /**
  * tlb_hit_page: return true if page aligned @addr is a hit against the

include/exec/cpu-defs.h

@@ -124,6 +124,12 @@ typedef struct CPUTLBEntryFull {
     /* @lg_page_size contains the log2 of the page size. */
     uint8_t lg_page_size;
 
+    /*
+     * Additional tlb flags for use by the slow path. If non-zero,
+     * the corresponding CPUTLBEntry comparator must have TLB_FORCE_SLOW.
+     */
+    uint8_t slow_flags[MMU_ACCESS_COUNT];
+
     /*
      * Allow target-specific additions to this structure.
      * This may be used to cache items from the guest cpu